html_url,issue_url,id,node_id,user,user_label,created_at,updated_at,author_association,body,reactions,issue,issue_label,performed_via_github_app
https://github.com/simonw/datasette/issues/2104#issuecomment-1641082395,https://api.github.com/repos/simonw/datasette/issues/2104,1641082395,IC_kwDOBm6k_c5h0O4b,15178711,asg017,2023-07-18T22:41:37Z,2023-07-18T22:41:37Z,CONTRIBUTOR,"For filtering virtual table's ""shadow tables"" (ex the FTS5 _content and most the spatialite tables), you can use `pragma_table_list` (first appeared in SQLite 3.37 (2021-11-27), which has a `type` column that calls out `type=""shadow""` tables https://www.sqlite.org/pragma.html#pragma_table_list","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1808215339,Tables starting with an underscore should be treated as hidden,
https://github.com/simonw/sqlite-utils/issues/433#issuecomment-1640826795,https://api.github.com/repos/simonw/sqlite-utils/issues/433,1640826795,IC_kwDOCGYnMM5hzQer,76528036,J450n-4-W,2023-07-18T19:08:50Z,2023-07-18T19:08:50Z,NONE,"Came here to report this, but instead I'll confirm the issue across two terminal emulators (Gnome Terminal and Alacritty) on Pop_OS! 22.04 (currently based on Ubuntu/Gnome). Also messes up the formatting of the terminal. Can also confirm that reset fixes it until the next sqlite-utils command. ","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1239034903,CLI eats my cursor,
https://github.com/simonw/datasette/issues/2102#issuecomment-1640064620,https://api.github.com/repos/simonw/datasette/issues/2102,1640064620,IC_kwDOBm6k_c5hwWZs,9599,simonw,2023-07-18T11:47:21Z,2023-07-18T11:47:21Z,OWNER,"I think I've figured out the problem here.
The question being asked is ""can this actor access this resource, which is within this database within this instance"".
The answer to this question needs to consider the full set of questions at once - yes they can access within this instance IF they have access to the specified table and that's the table being asked about.
But the questions are currently being asked independently, which means the plugin hook acting on `view-instance` can't see that the answer here should be yes because it's actually about a table that the actor has explicit permission to view.
So I think I may need to redesign the plugin hook to always see the full hierarchy of checks, not just a single check at a time.
","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1805076818,API tokens with view-table but not view-database/view-instance cannot access the table,
https://github.com/simonw/sqlite-utils/issues/567#issuecomment-1638926655,https://api.github.com/repos/simonw/sqlite-utils/issues/567,1638926655,IC_kwDOCGYnMM5hsAk_,9599,simonw,2023-07-17T21:42:37Z,2023-07-17T21:42:37Z,OWNER,"I really like this. I'm also interested in:
- Plugins that make new custom SQL functions available - similar to this Datasette hook: https://docs.datasette.io/en/stable/plugin_hooks.html#prepare-connection-conn-database-datasette
- Plugins that register functions that can be used as recipes for `sqlite-utils convert` https://sqlite-utils.datasette.io/en/stable/cli.html#sqlite-utils-convert-recipes
The upload-data-to-Datasette problem is planned to be solved by a future version of https://github.com/simonw/dclient ","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1801394744,Plugin system,
https://github.com/simonw/sqlite-utils/issues/567#issuecomment-1638910473,https://api.github.com/repos/simonw/sqlite-utils/issues/567,1638910473,IC_kwDOCGYnMM5hr8oJ,15178711,asg017,2023-07-17T21:27:41Z,2023-07-17T21:27:41Z,NONE,"Another use-case: I want to make a `sqlite-utils` plugin that'll help me insert data into Datasette.
```bash
sqlite-utils insert-datasette \
--token $DATASETTE_API_KEY \
https://latest.datasette.io/fixtures/my-table \
'select ...'
```
This could also be a datasette plugin (ex `datasette upload-data ...`, but you can also think of `sqlite-utils` plugins that upload to S3, a postgres table, other DBMS's, etc.)","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1801394744,Plugin system,
https://github.com/simonw/datasette/issues/2102#issuecomment-1638567228,https://api.github.com/repos/simonw/datasette/issues/2102,1638567228,IC_kwDOBm6k_c5hqo08,9599,simonw,2023-07-17T17:24:19Z,2023-07-17T17:25:12Z,OWNER,"Confirmed that this is an issue with regular Datasette signed tokens as well. I created one on https://latest.datasette.io/-/create-token with these details:
```json
{
""_r"": {
""r"": {
""fixtures"": {
""sortable"": [
""vt""
]
}
}
},
""a"": ""root"",
""d"": 3600,
""t"": 1689614483
}
```
Run like this:
```
curl -H 'Authorization: Bearer dstok_eyJhIjoicm9vdCIsInQiOjE2ODk2MTQ0ODMsImQiOjM2MDAsIl9yIjp7InIiOnsiZml4dHVyZXMiOnsic29ydGFibGUiOlsidnQiXX19fX0.n-VGxxawz1Q0WK7sqLfhXUgcvY0' \
https://latest.datasette.io/fixtures/sortable.json
```
Returned an HTML Forbidden page:
```html
Forbidden
...
```
Same token againts `/-/actor.json` returns:
```json
{
""actor"": {
""id"": ""root"",
""token"": ""dstok"",
""_r"": {
""r"": {
""fixtures"": {
""sortable"": [
""vt""
]
}
}
},
""token_expires"": 1689618083
}
}
```
Reminder - `""_r""` means restrict, `""r""` means resource.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1805076818,API tokens with view-table but not view-database/view-instance cannot access the table,
https://github.com/simonw/datasette/issues/2104#issuecomment-1638552567,https://api.github.com/repos/simonw/datasette/issues/2104,1638552567,IC_kwDOBm6k_c5hqlP3,9599,simonw,2023-07-17T17:14:20Z,2023-07-17T17:14:20Z,OWNER,Relevant code: https://github.com/simonw/datasette/blob/0f7192b6154edb576c41b55bd3f2a3f53e5f436a/datasette/database.py#L391-L451,"{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1808215339,Tables starting with an underscore should be treated as hidden,
https://github.com/simonw/datasette/issues/670#issuecomment-1637293044,https://api.github.com/repos/simonw/datasette/issues/670,1637293044,IC_kwDOBm6k_c5hlxv0,4863782,yairlenga,2023-07-17T02:23:32Z,2023-07-17T02:23:32Z,NONE,Is there any working version of datasette/postgresql ?,"{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",564833696,Prototoype for Datasette on PostgreSQL,
https://github.com/simonw/datasette/issues/2087#issuecomment-1636134091,https://api.github.com/repos/simonw/datasette/issues/2087,1636134091,IC_kwDOBm6k_c5hhWzL,653549,adarshp,2023-07-14T17:02:03Z,2023-07-14T17:02:03Z,NONE,"@asg017 - the docs say that the autodetection only occurs in configuration directory mode. I for one would also be interested in the `--settings settings.json` feature.
For context, I am developing a large database for use with Datasette, but the database lives in a different network volume than my source code, since the volume in which my source code lives is aggressively backed up, while the location where the database lives is meant for temporary files and is not as aggressively backed up (since the backups would get unreasonably large).","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1765870617,`--settings settings.json` option,
https://github.com/simonw/datasette/issues/2102#issuecomment-1636093730,https://api.github.com/repos/simonw/datasette/issues/2102,1636093730,IC_kwDOBm6k_c5hhM8i,9599,simonw,2023-07-14T16:26:27Z,2023-07-14T16:32:49Z,OWNER,"Here's that crucial comment:
> If _r is defined then we use those to further restrict the actor.
>
>Crucially, we only use this to say NO (return False) - we never use it to return YES (True) because that might over-ride other restrictions placed on this actor
So that's why I implemented it like this.
The goal here is to be able to issue a token which can't do anything _more_ than the actor it is associated with, but CAN be configured to do less.
So I think the solution here is for the `_r` checking code to perhaps implement its own view cascade logic - it notices if you have `view-table` and consequently fails to block `view-table` and `view-instance`.
I'm not sure that's going to work though - would that mean that granting `view-table` grants `view-database` in a surprising and harmful way?
Maybe that's OK: if you have `view-database` but permission checks fail for individual tables and queries you shouldn't be able to see a thing that you shouldn't. Need to verify that though.
Also, do `Permission` instances have enough information to implement this kind of cascade without hard-coding anything?
","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1805076818,API tokens with view-table but not view-database/view-instance cannot access the table,
https://github.com/simonw/datasette/issues/2102#issuecomment-1636053060,https://api.github.com/repos/simonw/datasette/issues/2102,1636053060,IC_kwDOBm6k_c5hhDBE,9599,simonw,2023-07-14T15:51:36Z,2023-07-14T16:14:05Z,OWNER,"This might only be an issue with the code that checks `_r` on actors.
https://github.com/simonw/datasette/blob/0f7192b6154edb576c41b55bd3f2a3f53e5f436a/datasette/default_permissions.py#L185-L222
Added in https://github.com/simonw/datasette/commit/bcc781f4c50a8870e3389c4e60acb625c34b0317 - refs:
- #1855 ","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1805076818,API tokens with view-table but not view-database/view-instance cannot access the table,
https://github.com/simonw/datasette/issues/2102#issuecomment-1636042066,https://api.github.com/repos/simonw/datasette/issues/2102,1636042066,IC_kwDOBm6k_c5hhAVS,9599,simonw,2023-07-14T15:41:54Z,2023-07-14T15:42:32Z,OWNER,"I tried some code spelunking and came across https://github.com/simonw/datasette/commit/d6e03b04302a0852e7133dc030eab50177c37be7 which says:
> - If you have table permission but not database permission you can now view the table page
Refs:
- #832
Which suggests that my initial design decision wasn't what appears to be implemented today.
Needs more investigation.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1805076818,API tokens with view-table but not view-database/view-instance cannot access the table,
https://github.com/simonw/datasette/issues/2102#issuecomment-1636040164,https://api.github.com/repos/simonw/datasette/issues/2102,1636040164,IC_kwDOBm6k_c5hg_3k,9599,simonw,2023-07-14T15:40:21Z,2023-07-14T15:40:21Z,OWNER,"Relevant code:
https://github.com/simonw/datasette/blob/0f7192b6154edb576c41b55bd3f2a3f53e5f436a/datasette/app.py#L822-L855","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1805076818,API tokens with view-table but not view-database/view-instance cannot access the table,
https://github.com/simonw/datasette/issues/2102#issuecomment-1636036312,https://api.github.com/repos/simonw/datasette/issues/2102,1636036312,IC_kwDOBm6k_c5hg-7Y,9599,simonw,2023-07-14T15:37:14Z,2023-07-14T15:37:14Z,OWNER,"I think I made this decision because I was thinking about default deny: obviously if a user has been denied access to a database. It doesn't make sense that they could access tables within it.
But now that I am spending more time with authentication tokens, which default to denying everything, except for the things that you have explicitly listed, this policy, no longer makes as much sense.
","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1805076818,API tokens with view-table but not view-database/view-instance cannot access the table,
https://github.com/simonw/datasette/issues/2101#issuecomment-1634443907,https://api.github.com/repos/simonw/datasette/issues/2101,1634443907,IC_kwDOBm6k_c5ha6KD,9599,simonw,2023-07-13T15:24:17Z,2023-07-13T15:24:17Z,OWNER,https://github.com/simonw/datasette/blob/0f7192b6154edb576c41b55bd3f2a3f53e5f436a/datasette/views/table.py#L486-L506,"{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1803264272,alter: true support for JSON write API,
https://github.com/simonw/datasette/pull/2052#issuecomment-1632867333,https://api.github.com/repos/simonw/datasette/issues/2052,1632867333,IC_kwDOBm6k_c5hU5QF,22429695,codecov[bot],2023-07-12T16:38:27Z,2023-07-12T16:38:27Z,NONE,"## [Codecov](https://app.codecov.io/gh/simonw/datasette/pull/2052?src=pr&el=h1&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison) Report
Patch coverage has no change and project coverage change: **`-0.02`** :warning:
> Comparison is base [(`3feed1f`)](https://app.codecov.io/gh/simonw/datasette/commit/3feed1f66e2b746f349ee56970a62246a18bb164?el=desc&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison) 92.46% compared to head [(`cf5a9df`)](https://app.codecov.io/gh/simonw/datasette/pull/2052?src=pr&el=desc&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison) 92.45%.
Additional details and impacted files
```diff
@@ Coverage Diff @@
## main #2052 +/- ##
==========================================
- Coverage 92.46% 92.45% -0.02%
==========================================
Files 38 39 +1
Lines 5750 5802 +52
==========================================
+ Hits 5317 5364 +47
- Misses 433 438 +5
```
[see 6 files with indirect coverage changes](https://app.codecov.io/gh/simonw/datasette/pull/2052/indirect-changes?src=pr&el=tree-more&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison)
[:umbrella: View full report in Codecov by Sentry](https://app.codecov.io/gh/simonw/datasette/pull/2052?src=pr&el=continue&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison).
:loudspeaker: Do you have feedback about the report comment? [Let us know in this issue](https://about.codecov.io/codecov-pr-comment-feedback/?utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison).
","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1651082214,"feat: Javascript Plugin API (Custom panels, column menu items with JS actions)",
https://github.com/simonw/datasette/pull/2052#issuecomment-1630776144,https://api.github.com/repos/simonw/datasette/issues/2052,1630776144,IC_kwDOBm6k_c5hM6tQ,9020979,hydrosquall,2023-07-11T12:54:03Z,2023-07-11T12:54:03Z,NONE,"Thanks for the review and the code pointers @simonw - I've made the suggested edits, fixed the renamed variable, and confirmed that the panels still render on the `table` and `database` views. ","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1651082214,"feat: Javascript Plugin API (Custom panels, column menu items with JS actions)",
https://github.com/simonw/datasette/pull/2052#issuecomment-1629337927,https://api.github.com/repos/simonw/datasette/issues/2052,1629337927,IC_kwDOBm6k_c5hHblH,9599,simonw,2023-07-10T16:43:38Z,2023-07-10T16:44:23Z,OWNER,"I tried running this locally just now. I made one edit:
```diff
diff --git a/demos/plugins/example_js_manager_plugins.py b/demos/plugins/example_js_manager_plugins.py
index 7bdb9f3f..f9dfa8e6 100644
--- a/demos/plugins/example_js_manager_plugins.py
+++ b/demos/plugins/example_js_manager_plugins.py
@@ -15,6 +15,6 @@ def extra_js_urls(view_name):
if view_name in PERMITTED_VIEWS:
return [
{
- ""url"": f""/-/demos/plugins/static/table-example-plugins.js"",
+ ""url"": f""/static/table-example-plugins.js"",
}
]
```
And then started it running like this:
```bash
wget https://datasette.io/content.db
```
```bash
datasette content.db \
--plugins-dir demos/plugins \
--static static:datasette/demos/plugins/static
```
It didn't quite work for me - I got this error on a table page:
And this error on a query page:
","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1651082214,"feat: Javascript Plugin API (Custom panels, column menu items with JS actions)",
https://github.com/dogsheep/healthkit-to-sqlite/issues/14#issuecomment-1629123734,https://api.github.com/repos/dogsheep/healthkit-to-sqlite/issues/14,1629123734,IC_kwDOC8tyDs5hGnSW,44622670,philipp-heinrich,2023-07-10T14:46:52Z,2023-07-10T14:46:52Z,NONE,@simonw any chance to get this fixed soon? ,"{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",771608692,UNIQUE constraint failed: workouts.id,
https://github.com/simonw/sqlite-utils/issues/566#issuecomment-1627598570,https://api.github.com/repos/simonw/sqlite-utils/issues/566,1627598570,IC_kwDOCGYnMM5hAy7q,9599,simonw,2023-07-09T04:13:34Z,2023-07-09T04:13:34Z,OWNER,On consulting https://pypi.org/project/tabulate/ it looks like most of those formats don't actually makes sense without headers - so the right thing here might be to raise an error if `--fmt` and `--no-headers` are used at the same time.,"{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1795219865,`--no-headers` doesn't work on most formats,
https://github.com/simonw/sqlite-utils/issues/566#issuecomment-1627597872,https://api.github.com/repos/simonw/sqlite-utils/issues/566,1627597872,IC_kwDOCGYnMM5hAyww,9599,simonw,2023-07-09T04:09:56Z,2023-07-09T04:09:56Z,OWNER,"Thanks, looks like a bug.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1795219865,`--no-headers` doesn't work on most formats,
https://github.com/dogsheep/pocket-to-sqlite/issues/12#issuecomment-1627564127,https://api.github.com/repos/dogsheep/pocket-to-sqlite/issues/12,1627564127,IC_kwDODLZ_YM5hAqhf,9599,simonw,2023-07-09T01:19:42Z,2023-07-09T01:19:42Z,MEMBER,https://github.com/dogsheep/pocket-to-sqlite/tree/0.2.3 and https://pypi.org/project/pocket-to-sqlite/0.2.3/,"{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1795187493,Switch to pyproject.toml,
https://github.com/dogsheep/pocket-to-sqlite/issues/12#issuecomment-1627563202,https://api.github.com/repos/dogsheep/pocket-to-sqlite/issues/12,1627563202,IC_kwDODLZ_YM5hAqTC,9599,simonw,2023-07-09T01:14:27Z,2023-07-09T01:14:27Z,MEMBER,I tested this locally with `python -m build` and then `pip install ...whl` in a fresh virtual environment.,"{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1795187493,Switch to pyproject.toml,
https://github.com/simonw/datasette/issues/1153#issuecomment-1627480353,https://api.github.com/repos/simonw/datasette/issues/1153,1627480353,IC_kwDOBm6k_c5hAWEh,9599,simonw,2023-07-08T20:09:48Z,2023-07-08T20:09:48Z,OWNER,https://docs.datasette.io/en/latest/writing_plugins.html#writing-plugins-that-accept-configuration is fixed now.,"{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",771202454,"Use YAML examples in documentation by default, not JSON",
https://github.com/simonw/datasette/issues/1153#issuecomment-1627478910,https://api.github.com/repos/simonw/datasette/issues/1153,1627478910,IC_kwDOBm6k_c5hAVt-,9599,simonw,2023-07-08T20:01:19Z,2023-07-08T20:01:19Z,OWNER,"Some examples:
- https://docs.datasette.io/en/latest/sql_queries.html#canned-queries
- https://docs.datasette.io/en/latest/sql_queries.html#canned-query-parameters
- https://docs.datasette.io/en/latest/authentication.html#access-to-an-instance
- https://docs.datasette.io/en/latest/facets.html#facets-in-metadata
- https://docs.datasette.io/en/latest/full_text_search.html#configuring-full-text-search-for-a-table-or-view
- https://docs.datasette.io/en/latest/metadata.html
- https://docs.datasette.io/en/latest/custom_templates.html#custom-css-and-javascript
- https://docs.datasette.io/en/latest/plugins.html#plugin-configuration
I need to fix this section: https://docs.datasette.io/en/latest/writing_plugins.html#writing-plugins-that-accept-configuration","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",771202454,"Use YAML examples in documentation by default, not JSON",
https://github.com/simonw/datasette/issues/1153#issuecomment-1627455892,https://api.github.com/repos/simonw/datasette/issues/1153,1627455892,IC_kwDOBm6k_c5hAQGU,9599,simonw,2023-07-08T18:39:19Z,2023-07-08T18:39:19Z,OWNER,"```
ERROR: Could not find a version that satisfies the requirement Sphinx==6.1.3; extra == ""docs"" (from datasette[docs,test]) (from versions: 0.1.61611, 0.1.61798, 0.1.61843, 0.1.61945, 0.1.61950, 0.2, 0.3, 0.4, 0.4.1, 0.4.2, 0.4.3, 0.5, 0.5.1, 0.5.2b1, 0.5.2, 0.6b1, 0.6, 0.6.1, 0.6.2, 0.6.3, 0.6.4, 0.6.5, 0.6.6, 0.6.7, 1.0b1, 1.0b2, 1.0, 1.0.1, 1.0.2, 1.0.3, 1.0.4, 1.0.5, 1.0.6, 1.0.7, 1.0.8, 1.1, 1.1.1, 1.1.2, 1.1.3, 1.2b1, 1.2b2, 1.2b3, 1.2, 1.2.1, 1.2.2, 1.2.3, 1.3b1, 1.3b2, 1.3b3, 1.3, 1.3.1, 1.3.2, 1.3.3, 1.3.4, 1.3.5, 1.3.6, 1.4a1, 1.4b1, 1.4, 1.4.1, 1.4.2, 1.4.3, 1.4.4, 1.4.5, 1.4.6, 1.4.7, 1.4.8, 1.4.9, 1.5a1, 1.5a2, 1.5b1, 1.5, 1.5.1, 1.5.2, 1.5.3, 1.5.4, 1.5.5, 1.5.6, 1.6b1, 1.6b2, 1.6b3, 1.6.1, 1.6.2, 1.6.3, 1.6.4, 1.6.5, 1.6.6, 1.6.7, 1.7.0b1, 1.7.0b2, 1.7.0, 1.7.1, 1.7.2, 1.7.3, 1.7.4, 1.7.5, 1.7.6, 1.7.7, 1.7.8, 1.7.9, 1.8.0b1, 1.8.0, 1.8.1, 1.8.2, 1.8.3, 1.8.4, 1.8.5, 1.8.6, 2.0.0b1, 2.0.0b2, 2.0.0, 2.0.1, 2.1.0, 2.1.1, 2.1.2, 2.2.0, 2.2.1, 2.2.2, 2.3.0, 2.3.1, 2.4.0, 2.4.1, 2.4.2, 2.4.3, 2.4.4, 2.4.5, 3.0.0b1, 3.0.0, 3.0.1, 3.0.2, 3.0.3, 3.0.4, 3.1.0, 3.1.1, 3.1.2, 3.2.0, 3.2.1, 3.3.0, 3.3.1, 3.4.0, 3.4.1, 3.4.2, 3.4.3, 3.5.0, 3.5.1, 3.5.2, 3.5.3, 3.5.4, 4.0.0b1, 4.0.0b2, 4.0.0, 4.0.1, 4.0.2, 4.0.3, 4.1.0, 4.1.1, 4.1.2, 4.2.0, 4.3.0, 4.3.1, 4.3.2, 4.4.0, 4.5.0, 5.0.0b1, 5.0.0, 5.0.1, 5.0.2, 5.1.0, 5.1.1, 5.2.0, 5.2.0.post0, 5.2.1, 5.2.2, 5.2.3, 5.3.0)
ERROR: No matching distribution found for Sphinx==6.1.3; extra == ""docs""
```
I'm going to drop Python 3.7.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",771202454,"Use YAML examples in documentation by default, not JSON",
https://github.com/simonw/datasette/issues/1153#issuecomment-1627451646,https://api.github.com/repos/simonw/datasette/issues/1153,1627451646,IC_kwDOBm6k_c5hAPD-,9599,simonw,2023-07-08T18:21:24Z,2023-07-08T18:21:24Z,OWNER,"This one was tricky:
I wanted complete control over the YAML example here, so I could ensure it used multi-line strings correctly.
I ended up changing my cog helper function to this:
```python
import json
import textwrap
from yaml import safe_dump
from ruamel.yaml import round_trip_load
def metadata_example(cog, data=None, yaml=None):
assert data or yaml, ""Must provide data= or yaml=""
assert not (data and yaml), ""Cannot use data= and yaml=""
output_yaml = None
if yaml:
# dedent it first
yaml = textwrap.dedent(yaml).strip()
# round_trip_load to preserve key order:
data = round_trip_load(yaml)
output_yaml = yaml
else:
output_yaml = safe_dump(data, sort_keys=False)
cog.out(""\n.. tab:: YAML\n\n"")
cog.out("" .. code-block:: yaml\n\n"")
cog.out(textwrap.indent(output_yaml, "" ""))
cog.out(""\n\n.. tab:: JSON\n\n"")
cog.out("" .. code-block:: json\n\n"")
cog.out(textwrap.indent(json.dumps(data, indent=2), "" ""))
cog.out(""\n"")
```
This allows me to call it ith YAML in some places:
```
.. [[[cog
metadata_example(cog, yaml=""""""
databases:
fixtures:
queries:
neighborhood_search:
fragment: fragment-goes-here
hide_sql: true
sql: |-
select neighborhood, facet_cities.name, state
from facetable join facet_cities on facetable.city_id = facet_cities.id
where neighborhood like '%' || :text || '%' order by neighborhood;
"""""")
.. ]]]
```
I had to introduce https://pypi.org/project/ruamel.yaml/ as a dependency here in order to load YAML from disk while maintaining key order.
I'm still using `safe_dump(data, sort_keys=False)` from PyYAML as I couldn't get the result I wanted for outputting YAML from an input of JSON using PyYAML.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",771202454,"Use YAML examples in documentation by default, not JSON",
https://github.com/simonw/datasette/issues/1153#issuecomment-1627450852,https://api.github.com/repos/simonw/datasette/issues/1153,1627450852,IC_kwDOBm6k_c5hAO3k,9599,simonw,2023-07-08T18:17:35Z,2023-07-08T18:17:35Z,OWNER,"I figured out a workaround:
```python
extensions = [
""sphinx.ext.extlinks"",
""sphinx.ext.autodoc"",
""sphinx_copybutton"",
]
if not os.environ.get(""DISABLE_SPHINX_INLINE_TABS""):
extensions += [""sphinx_inline_tabs""]
```
That way I can run `sphinx-build -b xml . _build` successfully if I set that environment variable.
I get some noisy warnings, but it runs OK. And the resulting `docs.db` file has rows like this, which I think are fine:
","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",771202454,"Use YAML examples in documentation by default, not JSON",
https://github.com/simonw/datasette/issues/1153#issuecomment-1627448542,https://api.github.com/repos/simonw/datasette/issues/1153,1627448542,IC_kwDOBm6k_c5hAOTe,9599,simonw,2023-07-08T18:05:44Z,2023-07-08T18:05:44Z,OWNER,"Running with `-P` opens a debugger when it hits the error:
```bash
sphinx-build -P -b xml . _build
```
```
(Pdb) list
2023
2024 Raise an exception unless overridden.
2025 """"""
2026 if (self.document.settings.strict_visitor
2027 or node.__class__.__name__ not in self.optional):
2028 -> raise NotImplementedError(
2029 '%s visiting unknown node type: %s'
2030 % (self.__class__, node.__class__.__name__))
2031
2032 def unknown_departure(self, node):
2033 """"""
(Pdb) self.optional
('meta',)
(Pdb) node.__class__.__name__
'TabContainer'
(Pdb) self.document.settings.strict_visitor
(Pdb) type(self.document.settings.strict_visitor)
```
So if I can get `TabContainer` into that `self.optional` list I'll have fixed this problem.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",771202454,"Use YAML examples in documentation by default, not JSON",
https://github.com/simonw/datasette/issues/1153#issuecomment-1627448180,https://api.github.com/repos/simonw/datasette/issues/1153,1627448180,IC_kwDOBm6k_c5hAON0,9599,simonw,2023-07-08T18:03:31Z,2023-07-08T18:03:31Z,OWNER,"Relevant code: https://github.com/docutils/docutils/blob/3b53ded52bc439d8068b6ecb20ea0a761247e479/docutils/docutils/nodes.py#L2021-L2031
```python
def unknown_visit(self, node):
""""""
Called when entering unknown `Node` types.
Raise an exception unless overridden.
""""""
if (self.document.settings.strict_visitor
or node.__class__.__name__ not in self.optional):
raise NotImplementedError(
'%s visiting unknown node type: %s'
% (self.__class__, node.__class__.__name__))
```","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",771202454,"Use YAML examples in documentation by default, not JSON",
https://github.com/simonw/datasette/issues/1153#issuecomment-1627447750,https://api.github.com/repos/simonw/datasette/issues/1153,1627447750,IC_kwDOBm6k_c5hAOHG,9599,simonw,2023-07-08T18:00:56Z,2023-07-08T18:00:56Z,OWNER,"Actually no it's in `sphinx-build`:
```
% sphinx-build -b xml . _build
Running Sphinx v6.1.3
building [mo]: targets for 0 po files that are out of date
writing output...
building [xml]: targets for 28 source files that are out of date
updating environment: [new config] 28 added, 0 changed, 0 removed
reading sources... [100%] writing_plugins
looking for now-outdated files... none found
pickling environment... done
checking consistency... done
preparing documents... done
writing output... [ 3%] authentication
Exception occurred:
File ""/Users/simon/.local/share/virtualenvs/datasette-AWNrQs95/lib/python3.10/site-packages/docutils/nodes.py"", line 2028, in unknown_visit
raise NotImplementedError(
NotImplementedError: visiting unknown node type: TabContainer
The full traceback has been saved in /var/folders/x6/31xf1vxj0nn9mxqq8z0mmcfw0000gn/T/sphinx-err-1wkxmkji.log, if you want to report the issue to the developers.
Please also report this if it was a user error, so that a better error message can be provided next time.
A bug report can be filed in the tracker at . Thanks!
```","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",771202454,"Use YAML examples in documentation by default, not JSON",
https://github.com/simonw/datasette/issues/1153#issuecomment-1627447478,https://api.github.com/repos/simonw/datasette/issues/1153,1627447478,IC_kwDOBm6k_c5hAOC2,9599,simonw,2023-07-08T17:59:25Z,2023-07-08T17:59:25Z,OWNER,"Hit a problem:
```
Exception occurred:
File ""/opt/hostedtoolcache/Python/3.9.17/x64/lib/python3.9/site-packages/docutils/nodes.py"", line 2028, in unknown_visit
raise NotImplementedError(
NotImplementedError: visiting unknown node type: TabContainer
The full traceback has been saved in /tmp/sphinx-err-tfujyw1h.log, if you want to report the issue to the developers.
Please also report this if it was a user error, so that a better error message can be provided next time.
A bug report can be filed in the tracker at . Thanks!
```
That's happening here: https://github.com/simonw/datasette/blob/0183e1a72d4d93b1d9a9363f4d47fcc0b5d5849c/.github/workflows/deploy-latest.yml#L42-L48
My https://github.com/simonw/sphinx-to-sqlite tool can't handle the new `TabContainer` elements introduced by `sphinx-inline-tabs`.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",771202454,"Use YAML examples in documentation by default, not JSON",
https://github.com/simonw/datasette/issues/1153#issuecomment-1627396658,https://api.github.com/repos/simonw/datasette/issues/1153,1627396658,IC_kwDOBm6k_c5hABoy,9599,simonw,2023-07-08T16:40:07Z,2023-07-08T16:40:07Z,OWNER,"https://docs.datasette.io/en/latest/metadata.html
![inline-tabs](https://github.com/simonw/datasette/assets/9599/975bdff5-74ac-451e-92c3-a7dd05d4b862)
","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",771202454,"Use YAML examples in documentation by default, not JSON",
https://github.com/simonw/datasette/issues/1153#issuecomment-1627396450,https://api.github.com/repos/simonw/datasette/issues/1153,1627396450,IC_kwDOBm6k_c5hABli,9599,simonw,2023-07-08T16:38:58Z,2023-07-08T16:38:58Z,OWNER,"I'm using `cog` and this utility function to generate the YAML/JSON tabs:
https://github.com/simonw/datasette/blob/3b336d8071fb5707bd006de1d614f701d20246a3/docs/metadata_doc.py#L1-L13
Example usage:
https://github.com/simonw/datasette/blob/3b336d8071fb5707bd006de1d614f701d20246a3/docs/metadata.rst?plain=1#L17-L53","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",771202454,"Use YAML examples in documentation by default, not JSON",
https://github.com/simonw/datasette/issues/1153#issuecomment-1627395947,https://api.github.com/repos/simonw/datasette/issues/1153,1627395947,IC_kwDOBm6k_c5hABdr,9599,simonw,2023-07-08T16:35:45Z,2023-07-08T16:35:45Z,OWNER,I was inspired to finally address this after seeing `sphinx-inline-tabs` at work in https://webcolors.readthedocs.io/en/latest/install.html,"{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",771202454,"Use YAML examples in documentation by default, not JSON",
https://github.com/simonw/sqlite-utils/issues/565#issuecomment-1618380888,https://api.github.com/repos/simonw/sqlite-utils/issues/565,1618380888,IC_kwDOCGYnMM5gdohY,9599,simonw,2023-07-03T14:09:11Z,2023-07-03T14:09:31Z,OWNER,"For the CLI:
```bash
sqlite-utils rename-table data.db old_table_name new_table_name
```
For the Python code, should it go on Table or on Database?
```python
db[""foo""].rename_table(""bar"")
db.rename_table(""foo"", ""bar"")
```
I think I like the second better, it's slightly more clear.
Also need a design for an option for the `.transform()` method to indicate that the new table should be created with a new name without dropping the old one.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1786258502,Table renaming utilities,
https://github.com/simonw/sqlite-utils/issues/563#issuecomment-1617395444,https://api.github.com/repos/simonw/sqlite-utils/issues/563,1617395444,IC_kwDOCGYnMM5gZ370,9599,simonw,2023-07-03T05:44:43Z,2023-07-03T05:44:43Z,OWNER,Documentation at the bottom of this section: https://sqlite-utils.datasette.io/en/latest/cli.html#inserting-csv-or-tsv-data,"{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1785360409,`--empty-null` option when importing CSV,
https://github.com/simonw/datasette/issues/2087#issuecomment-1616853644,https://api.github.com/repos/simonw/datasette/issues/2087,1616853644,IC_kwDOBm6k_c5gXzqM,15178711,asg017,2023-07-02T22:00:48Z,2023-07-02T22:00:48Z,CONTRIBUTOR,"I just saw in the docs that Dasette auto-detects `settings.json`:
> settings.json - settings that would normally be passed using --setting - here they should be stored as a JSON object of key/value pairs
> [*Source*](https://docs.datasette.io/en/stable/settings.html#:~:text=settings.json%20%2D%20settings%20that%20would%20normally%20be%20passed%20using%20%2D%2Dsetting%20%2D%20here%20they%20should%20be%20stored%20as%20a%20JSON%20object%20of%20key/value%20pairs)","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1765870617,`--settings settings.json` option,
https://github.com/simonw/sqlite-utils/issues/562#issuecomment-1616782404,https://api.github.com/repos/simonw/sqlite-utils/issues/562,1616782404,IC_kwDOCGYnMM5gXiRE,9599,simonw,2023-07-02T19:24:14Z,2023-07-02T19:26:39Z,OWNER,"[Dataclasses](https://docs.python.org/3/library/dataclasses.html) were added in Python 3.7 and `sqlite-utils` was originally written for Python 3.6 - but both 3.6 and 3.7 are EOL now.
The thing that makes Dataclasses particularly interesting is the potential to use type annotations with them to help specify the types of the related SQLite columns.
Example for https://datasette.io/content/users
```sql
CREATE TABLE [users] (
[login] TEXT,
[id] INTEGER PRIMARY KEY,
[node_id] TEXT,
[avatar_url] TEXT,
[gravatar_id] TEXT,
[html_url] TEXT,
[type] TEXT,
[site_admin] INTEGER,
[name] TEXT
);
```
And the dataclass:
```python
from dataclasses import dataclass
@dataclass
class User:
id: int
login: str
node_id: str
avatar_url: str
gravatar_id: str
html_url: str
type: str
site_admin: int
name: str
```
","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1784794489,Explore the intersection between sqlite-utils and dataclasses,
https://github.com/simonw/datasette/issues/2093#issuecomment-1616286848,https://api.github.com/repos/simonw/datasette/issues/2093,1616286848,IC_kwDOBm6k_c5gVpSA,15178711,asg017,2023-07-02T02:17:46Z,2023-07-02T02:17:46Z,CONTRIBUTOR,"Storing metadata in the database won't be required. I imagine there'll be many different ways to store metadata, including any possible `datasette_metadata` or sqlite-docs, or the older metadata.json way.
The next question will be how precedence should work - i'd imagine metadata.json > plugins > datasette_metadata > sqlite-docs","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1781530343,"Proposal: Combine settings, metadata, static, etc. into a single `datasette.toml` File",
https://github.com/simonw/datasette/issues/2093#issuecomment-1616195496,https://api.github.com/repos/simonw/datasette/issues/2093,1616195496,IC_kwDOBm6k_c5gVS-o,273509,terinjokes,2023-07-02T00:06:54Z,2023-07-02T00:07:17Z,NONE,"I'm not keen on requiring metadata to be within the database. I commonly have multiple DBs, from various sources, and having one config file to provide the metadata works out very well. I use Datasette with databases where I'm not the original source, needing to mutate them to add a metadata table or sqlite-docs makes me uncomfortable.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1781530343,"Proposal: Combine settings, metadata, static, etc. into a single `datasette.toml` File",
https://github.com/simonw/datasette/pull/2052#issuecomment-1616095810,https://api.github.com/repos/simonw/datasette/issues/2052,1616095810,IC_kwDOBm6k_c5gU6pC,15178711,asg017,2023-07-01T20:31:31Z,2023-07-01T20:31:31Z,CONTRIBUTOR,"> Just curious, is there a query that can be used to compile this programmatically, or did you identify these through memory?
I just did a github search for `user:simonw ""def extra_js_urls(""` ! Though I'm sure other plugins made by people other than Simon also exist out there https://github.com/search?q=user%3Asimonw+%22def+extra_js_urls%28%22&type=code","{""total_count"": 1, ""+1"": 1, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1651082214,"feat: Javascript Plugin API (Custom panels, column menu items with JS actions)",
https://github.com/simonw/datasette/pull/2052#issuecomment-1615997736,https://api.github.com/repos/simonw/datasette/issues/2052,1615997736,IC_kwDOBm6k_c5gUiso,9020979,hydrosquall,2023-07-01T16:55:24Z,2023-07-01T16:55:24Z,NONE,"> Ok @hydrosquall a couple things before this PR should be good to go:
Thank you @asg017 ! I've pushed both suggested changes onto this branch.
> Not sure how difficult it'll be to inject it server-side
If we are OK with having a build system, it would free me up to do do many things! We could make datasette-manager.js a server-side rendered file as a ""template"" instead of having it as a static JS file, but I'm not sure it's worth the extra jump in complexity / loss of syntax highlighting in the JS file.
In the short-term, I could see an intermediary solution where a unit test in the preferred language was able to read both `version.py` and `datasette-manager.js`, and make sure that the strings versions are in sync. (This assumes that we want the manager and datasette's versions to be synced, and not decoupled). Since the version is not changing very often, a ""manual sync"" might be good enough.
> In terms of how to integrate this into Datasette, a few options I can see working:
This sounds good to me. I'm not sure how to add a settings flag, but will be interested to see the PR that adds support for it.
> I'm also curious to see how ""plugins for a plugin' would work
I'm comfortable to wait until we have a realistic usecase for this. In the short term, I think we could give plugins a way to grant access to a ""public API of other plugins"", and also ask to be notified when plugins with other names have loaded, but don't picture the datasette manager getting more involved than that.
> here's a list of Simon's Datasette plugins that use ""extra_js_urls()""
Neat, thanks for compiling this list! Just curious, is there a query that can be used to compile this programmatically, or did you identify these through memory?
> I want to make a javascript plugin on top of the code-mirror editor to make a few things nicer (function auto-complete, table/column descriptions, etc.)
I look forward to trying this out 👍
","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1651082214,"feat: Javascript Plugin API (Custom panels, column menu items with JS actions)",
https://github.com/simonw/datasette/issues/2093#issuecomment-1614652001,https://api.github.com/repos/simonw/datasette/issues/2093,1614652001,IC_kwDOBm6k_c5gPaJh,9599,simonw,2023-06-30T13:27:13Z,2023-06-30T13:27:13Z,OWNER,"I agree, settings in the DB doesn't make sense but metadata does.
On the JSON v YAML v TOML issue I just spotted Caddy has a concept of config adapters which they use to resolve exactly that problem: https://caddyserver.com/docs/config-adapters","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1781530343,"Proposal: Combine settings, metadata, static, etc. into a single `datasette.toml` File",
https://github.com/simonw/datasette/issues/2093#issuecomment-1613896210,https://api.github.com/repos/simonw/datasette/issues/2093,1613896210,IC_kwDOBm6k_c5gMhoS,15178711,asg017,2023-06-29T22:53:33Z,2023-06-29T22:53:33Z,CONTRIBUTOR,"Maybe we can have a separate issue for revamping `metadata.json`? A `datasette_metadata` table or the `sqlite-docs` extension seem like two reasonable additions that we can work through. Storing metadata inside a SQLite database makes sense, but I don't think storing `datasette.*` style config (ex ports, settings, etc.) inside a SQLite DB makes sense, since it's very environment-dependent","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1781530343,"Proposal: Combine settings, metadata, static, etc. into a single `datasette.toml` File",
https://github.com/simonw/datasette/issues/2093#issuecomment-1613895188,https://api.github.com/repos/simonw/datasette/issues/2093,1613895188,IC_kwDOBm6k_c5gMhYU,15178711,asg017,2023-06-29T22:51:53Z,2023-06-29T22:51:53Z,CONTRIBUTOR,"I agree with not liking `metadata.json` stuff in a `datasette.*` config file. Editing description of a table/column in a file like `datasette.*` seems odd to me.
Though since plugin configuration currently lives in `metadata.json`, I think it should be removed from there and placed in `datasette.*`, at least for top-level config like `datasette-auth-github`'s config. Keeping `metadata.json` strictly for documentation/licensing/column units makes sense to me, but anything plugin related should be in some config file, like `datasette.*`.
And ya, supporting both `datasette.*` and CLI flags makes a lot of sense to me. Any `--setting` flag should override anything in `datasette.*` for easier debugging, with possibly a warning message so people don't get confused. Same with `--port` and a port defined in `datasette.*`","{""total_count"": 1, ""+1"": 1, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1781530343,"Proposal: Combine settings, metadata, static, etc. into a single `datasette.toml` File",
https://github.com/simonw/datasette/issues/2093#issuecomment-1613889979,https://api.github.com/repos/simonw/datasette/issues/2093,1613889979,IC_kwDOBm6k_c5gMgG7,9599,simonw,2023-06-29T22:44:08Z,2023-06-30T13:25:39Z,OWNER,"I do like also being able to set options using command line options though - for things like SQL time limits I'd much rather be able to throw on `--setting sql_time_limit_ms 10000` than have to save a config file to disk.
So I'd want to support both. Which maybe means also having a way to set plugin options with CLI options. `datasette publish` kind of has that ability already:
```
datasette publish heroku my_database.db \
--name my-heroku-app-demo \
--install=datasette-auth-github \
--plugin-secret datasette-auth-github client_id your_client_id \
--plugin-secret datasette-auth-github client_secret your_client_secret
```","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1781530343,"Proposal: Combine settings, metadata, static, etc. into a single `datasette.toml` File",
https://github.com/simonw/datasette/issues/2093#issuecomment-1613887492,https://api.github.com/repos/simonw/datasette/issues/2093,1613887492,IC_kwDOBm6k_c5gMfgE,9599,simonw,2023-06-29T22:40:25Z,2023-06-29T22:40:25Z,OWNER,"I'm strongly in favour of combining settings, configuration and plugin configuration.
I'm not keen on mixing in metadata as well - that feels like a different concept to me, and I'm unhappy with how that's already had things like plugin settings leak into it.
I'm not yet sold on TOML - I actually find it less intuitive than YAML, surprisingly. They all have their warts I guess.
Datasette already has the ability to consume JSON or YAML for metadata - maybe it could grow TOML support too? That way users could have a `datasette.json` or `datasette.yaml` or `datasette.toml` file depending on their preference.
In terms of metadata: since that's means to be driven by a plugin hook anyway, maybe one of the potential sources of metadata is a `metadata` nested object in that `datasette.*` configuration file. Or you can have it in a separate `metadata.json` or bundled into the SQLite database or some other plugin-driven mechanism.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1781530343,"Proposal: Combine settings, metadata, static, etc. into a single `datasette.toml` File",
https://github.com/simonw/datasette/pull/2052#issuecomment-1613778296,https://api.github.com/repos/simonw/datasette/issues/2052,1613778296,IC_kwDOBm6k_c5gME14,15178711,asg017,2023-06-29T20:36:09Z,2023-06-29T20:36:09Z,CONTRIBUTOR,"Ok @hydrosquall a couple things before this PR should be good to go:
- Can we move `datasette/static/table-example-plugins.js` into `demos/plugins/static`?
- For `datasetteManager.VERSION`, can we fill that in or just comment it out for now? Not sure how difficult it'll be to inject it server-side. I imagine we could also have a small build process with esbuild/rollup that just injects a version string into `manager.js` directly, so we don't have to worry about server-rendering (but that can be a future PR)
In terms of how to integrate this into Datasette, a few options I can see working:
- Push this as-is and figure it out before the next release
- Hide this feature behind a settings flag (`--setting unstable-js-plugins on`) and use that setting to hide/show `` in `base.html`
I'll let @simonw decide which one to work with. I kindof like the idea of having an ""unstable"" opt-in process to enable JS plugins, to give us time to try it out with a wide variety of plugins until we feel its ready.
I'm also curious to see how ""plugins for a plugin' would work, like #1542. For example, if the leaflet plugin showed default markers, but also included its own hook for other plugins to add more markers/styling. I'm imagine that the individual plugin would re-create their own plugin system compared to this, since handling ""plugins of plugins"" at the top with Datasette seems really convoluted.
Also for posterity, here's a list of Simon's Datasette plugins that use ""extra_js_urls()"", which probably means they can be ported/re-written to use this new plugin system:
- [`datasette-vega`](https://github.com/simonw/datasette-vega/blob/00de059ab1ef77394ba9f9547abfacf966c479c4/datasette_vega/__init__.py#L25)
- [`datasette-cluster-map`](https://github.com/simonw/datasette-cluster-map/blob/795d25ad9ff6cba0307191f44fecc8f8070bef5c/datasette_cluster_map/__init__.py#L14)
- [`datasette-leaflet-geojson`](https://github.com/simonw/datasette-leaflet-geojson/blob/64713aa497750400b9ac2c12e8bb6ffab8eb77f3/datasette_leaflet_geojson/__init__.py#L47)
- [`datasette-pretty-traces`](https://github.com/simonw/datasette-pretty-traces/blob/5219d65eca3d7d7a73bb9d3120df42fe046a1315/datasette_pretty_traces/__init__.py#L5)
- [`datasette-youtube-embed`](https://github.com/simonw/datasette-youtube-embed/blob/4b4a0d7e58ebe15f47e9baf68beb9908c1d899da/datasette_youtube_embed/__init__.py#L55)
- [`datasette-leaflet-freedraw`](https://github.com/simonw/datasette-leaflet-freedraw/blob/8f28c2c2080ec9d29f18386cc6a2573a1c8fbde7/datasette_leaflet_freedraw/__init__.py#L66)
- [`datasette-hovercards`](https://github.com/simonw/datasette-hovercards/blob/9439ba46b7140fb03223faff0d21aeba5615a287/datasette_hovercards/__init__.py#L5)
- [`datasette-mp3-audio`](https://github.com/simonw/datasette-mp3-audio/blob/4402168792f452a46ab7b488e40ec49cd4b12185/datasette_mp3_audio/__init__.py#L6)
- [`datasette-geojson-map`](https://github.com/simonw/datasette-geojson-map/blob/32af5f1fd1a07278bbf8071fbb20a61e0f613246/datasette_geojson_map/__init__.py#L30)","{""total_count"": 1, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 1}",1651082214,"feat: Javascript Plugin API (Custom panels, column menu items with JS actions)",
https://github.com/simonw/datasette/issues/2092#issuecomment-1613381990,https://api.github.com/repos/simonw/datasette/issues/2092,1613381990,IC_kwDOBm6k_c5gKkFm,9599,simonw,2023-06-29T15:23:04Z,2023-06-29T15:26:28Z,OWNER,"Felt lazy:
```bash
symbex test_homepage -f tests/test_api.py | \
llm -m 4 --system 'Change all of the == some integer tests in this code to isinstance(thing, int) instead'
```
Output:
```python
# File: tests/test_api.py Line: 26
@pytest.mark.asyncio
async def test_homepage(ds_client):
response = await ds_client.get(""/.json"")
assert response.status_code == 200
assert ""application/json; charset=utf-8"" == response.headers[""content-type""]
data = response.json()
assert isinstance(data.keys(), int)
d = data[""fixtures""]
assert d[""name""] == ""fixtures""
assert isinstance(d[""tables_count""], int)
assert isinstance(len(d[""tables_and_views_truncated""]), int)
assert d[""tables_and_views_more""] is True
# 4 hidden FTS tables + no_primary_key (hidden in metadata)
assert isinstance(d[""hidden_tables_count""], int)
# 201 in no_primary_key, plus 6 in other hidden tables:
assert isinstance(d[""hidden_table_rows_sum""], int), data
assert isinstance(d[""views_count""], int)
```
I'll use most of that and delete the obsoleted comments.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1781047747,test_homepage intermittent failure,
https://github.com/simonw/datasette/issues/2092#issuecomment-1613375407,https://api.github.com/repos/simonw/datasette/issues/2092,1613375407,IC_kwDOBm6k_c5gKiev,9599,simonw,2023-06-29T15:20:52Z,2023-06-29T15:21:05Z,OWNER,I'm going to remove this assertion entirely. The homepage JSON needs a refactor anyway.,"{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1781047747,test_homepage intermittent failure,
https://github.com/simonw/datasette/issues/2091#issuecomment-1613369355,https://api.github.com/repos/simonw/datasette/issues/2091,1613369355,IC_kwDOBm6k_c5gKhAL,9599,simonw,2023-06-29T15:18:34Z,2023-06-29T15:18:34Z,OWNER,Posted on the Glitch feedback forum about this here: https://support.glitch.com/t/upgrade-python-version-from-3-7-which-is-now-eol-to-something-more-recent/63011,"{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1781022369,Drop support for Python 3.7,
https://github.com/simonw/datasette/issues/2091#issuecomment-1613360413,https://api.github.com/repos/simonw/datasette/issues/2091,1613360413,IC_kwDOBm6k_c5gKe0d,9599,simonw,2023-06-29T15:13:04Z,2023-06-29T15:13:04Z,OWNER,"One problem: https://glitch.com/ still provides 3.7:
```
$ python3 --version
Python 3.7.10
```
","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1781022369,Drop support for Python 3.7,
https://github.com/simonw/datasette/issues/2090#issuecomment-1613346412,https://api.github.com/repos/simonw/datasette/issues/2090,1613346412,IC_kwDOBm6k_c5gKbZs,9599,simonw,2023-06-29T15:05:04Z,2023-06-29T15:05:04Z,OWNER,"Decided to fix just those ""Ambiguous variable name"" ones:
```bash
ruff check . | grep E741
```
Then iterated through and fixed them all.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1781005740,Adopt ruff for linting,
https://github.com/simonw/datasette/issues/2090#issuecomment-1613339404,https://api.github.com/repos/simonw/datasette/issues/2090,1613339404,IC_kwDOBm6k_c5gKZsM,9599,simonw,2023-06-29T15:01:01Z,2023-06-29T15:01:20Z,OWNER,"I tried it just now and got some interesting results.
I dropped in a `ruff.toml` file:
```toml
line-length = 160
```
Because the default line length limit of 88 was causing a lot of noisy errors.
Then run:
```bash
pip install ruff
ruff check .
```
Plenty of warnings about unused imports - running `ruff check . --fix` fixed those automatically, but I think I still need to manually review them as some might be imports which are deliberate and should be in `__all__` to ensure they are visible from that module as well.
Some lines in tests are longer than even 160 chars, e.g.:
https://github.com/simonw/datasette/blob/99ba05118891db9dc30f1dca22ad6709775560de/tests/test_html.py#L673-L681
These can have ` # noqa: E501` added to the end of those lines to skip the check for them.
That got it down to:
```
% ruff check .
datasette/views/table.py:23:5: F811 Redefinition of unused `format_bytes` from line 19
run_tests.py:2:5: E401 Multiple imports on one line
tests/test_api.py:591:40: F811 Redefinition of unused `app_client_no_files` from line 7
tests/test_api.py:629:35: F811 Redefinition of unused `app_client_no_files` from line 7
tests/test_api.py:635:54: F811 Redefinition of unused `app_client_with_dot` from line 8
tests/test_api.py:661:25: F811 Redefinition of unused `app_client_shorter_time_limit` from line 9
tests/test_api.py:759:25: F811 Redefinition of unused `app_client_two_attached_databases_one_immutable` from line 10
tests/test_api.py:892:28: F811 Redefinition of unused `app_client_larger_cache_size` from line 11
tests/test_api.py:928:5: F811 Redefinition of unused `app_client_with_cors` from line 12
tests/test_api.py:929:5: F811 Redefinition of unused `app_client_two_attached_databases_one_immutable` from line 10
tests/test_api.py:969:38: F811 Redefinition of unused `app_client_two_attached_databases` from line 13
tests/test_api.py:976:39: F811 Redefinition of unused `app_client_conflicting_database_names` from line 14
tests/test_api.py:987:38: F811 Redefinition of unused `app_client_immutable_and_inspect_file` from line 15
tests/test_api.py:1002:24: F811 Redefinition of unused `app_client` from line 6
tests/test_csv.py:67:33: F811 Redefinition of unused `app_client_with_cors` from line 6
tests/test_csv.py:157:21: F811 Redefinition of unused `app_client_csv_max_mb_one` from line 5
tests/test_csv.py:198:20: F811 Redefinition of unused `app_client_with_trace` from line 7
tests/test_csv.py:209:53: F811 Redefinition of unused `app_client_with_trace` from line 7
tests/test_csv.py:215:53: F811 Redefinition of unused `app_client_with_trace` from line 7
tests/test_filters.py:102:11: F811 Redefinition of unused `test_through_filters_from_request` from line 81
tests/test_html.py:19:19: F811 Redefinition of unused `app_client_two_attached_databases` from line 7
tests/test_html.py:175:25: F811 Redefinition of unused `app_client_shorter_time_limit` from line 6
tests/test_html.py:469:51: F811 Redefinition of unused `app_client` from line 4
tests/test_html.py:797:26: F811 Redefinition of unused `app_client_base_url_prefix` from line 5
tests/test_html.py:840:44: F811 Redefinition of unused `app_client_base_url_prefix` from line 5
tests/test_html.py:850:51: F811 Redefinition of unused `app_client_base_url_prefix` from line 5
tests/test_pagination.py:50:43: F821 Undefined name `parse_next`
tests/test_pagination.py:82:7: F811 Redefinition of unused `KeysetPaginator` from line 36
tests/test_plugins.py:115:15: E741 Ambiguous variable name: `l`
tests/test_plugins.py:482:161: E501 Line too long (170 > 160 characters)
tests/test_plugins.py:543:29: E741 Ambiguous variable name: `l`
tests/test_plugins.py:563:161: E501 Line too long (170 > 160 characters)
tests/test_plugins.py:940:62: E741 Ambiguous variable name: `l`
tests/test_table_api.py:739:5: F811 Redefinition of unused `app_client_returned_rows_matches_page_size` from line 6
tests/test_table_api.py:1066:45: F811 Redefinition of unused `app_client_with_trace` from line 5
tests/test_table_html.py:484:29: E741 Ambiguous variable name: `l`
tests/test_table_html.py:524:29: E741 Ambiguous variable name: `l`
tests/test_table_html.py:675:161: E501 Line too long (165 > 160 characters)
tests/test_table_html.py:897:161: E501 Line too long (164 > 160 characters)
tests/test_table_html.py:902:161: E501 Line too long (164 > 160 characters)
tests/test_utils.py:141:161: E501 Line too long (176 > 160 characters)
Found 41 errors.
```
Those ""Redefinition of unused `app_client_two_attached_databases`"" lines are caused because of the fixtures pattern I'm using here:
https://github.com/simonw/datasette/blob/99ba05118891db9dc30f1dca22ad6709775560de/tests/test_html.py#L3-L20
I could fix that by getting rid of `fixtures.py` and moving those into `conftest.py`.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1781005740,Adopt ruff for linting,
https://github.com/simonw/datasette/issues/2089#issuecomment-1613316722,https://api.github.com/repos/simonw/datasette/issues/2089,1613316722,IC_kwDOBm6k_c5gKUJy,9599,simonw,2023-06-29T14:48:10Z,2023-06-29T14:48:10Z,OWNER,Spell check is passing now.,"{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1780973290,codespell test failure,
https://github.com/simonw/datasette/issues/2089#issuecomment-1613315851,https://api.github.com/repos/simonw/datasette/issues/2089,1613315851,IC_kwDOBm6k_c5gKT8L,9599,simonw,2023-06-29T14:47:38Z,2023-06-29T14:47:38Z,OWNER,"Confirmed, this was a 2.2.5 change: https://github.com/codespell-project/codespell/releases/tag/v2.2.5
> - Add displaing->displaying by [@peternewman](https://github.com/peternewman) in [#2808](https://github.com/codespell-project/codespell/pull/2808)","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1780973290,codespell test failure,
https://github.com/simonw/datasette/issues/2089#issuecomment-1613307716,https://api.github.com/repos/simonw/datasette/issues/2089,1613307716,IC_kwDOBm6k_c5gKR9E,9599,simonw,2023-06-29T14:42:23Z,2023-06-29T14:42:23Z,OWNER,"Yes, upgrading locally got me the correct version and the test failure:
```
% pip install -U codespell
Requirement already satisfied: codespell in /Users/simon/.local/share/virtualenvs/datasette-AWNrQs95/lib/python3.10/site-packages (2.2.2)
Collecting codespell
Downloading codespell-2.2.5-py3-none-any.whl (242 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 242.7/242.7 kB 4.9 MB/s eta 0:00:00
Installing collected packages: codespell
Attempting uninstall: codespell
Found existing installation: codespell 2.2.2
Uninstalling codespell-2.2.2:
Successfully uninstalled codespell-2.2.2
Successfully installed codespell-2.2.5
% codespell docs/metadata.rst
docs/metadata.rst:192: displaing ==> displaying
```","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1780973290,codespell test failure,
https://github.com/simonw/datasette/issues/2089#issuecomment-1613306787,https://api.github.com/repos/simonw/datasette/issues/2089,1613306787,IC_kwDOBm6k_c5gKRuj,9599,simonw,2023-06-29T14:41:47Z,2023-06-29T14:41:47Z,OWNER,"Looks like in CI it's running 2.2.5:
```
Collecting codespell (from datasette==1.0a2)
Downloading codespell-2.2.5-py3-none-any.whl (242 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 242.7/242.7 kB 31.1 MB/s eta 0:00:00
```
But on my laptop it's 2.2.2:
```
% codespell --version
2.2.2
```","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1780973290,codespell test failure,
https://github.com/simonw/datasette/issues/2089#issuecomment-1613305070,https://api.github.com/repos/simonw/datasette/issues/2089,1613305070,IC_kwDOBm6k_c5gKRTu,9599,simonw,2023-06-29T14:40:44Z,2023-06-29T14:40:44Z,OWNER,"I'm not sure why I can't duplicate this failure in my local development environment:
```
% codespell docs/metadata.rst
```
It finds no errors.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1780973290,codespell test failure,
https://github.com/simonw/datasette/pull/2077#issuecomment-1613290899,https://api.github.com/repos/simonw/datasette/issues/2077,1613290899,IC_kwDOBm6k_c5gKN2T,9599,simonw,2023-06-29T14:32:16Z,2023-06-29T14:32:16Z,OWNER,@dependabot recreate,"{""total_count"": 1, ""+1"": 1, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1719759468,Bump furo from 2023.3.27 to 2023.5.20,
https://github.com/simonw/datasette/issues/1510#issuecomment-1610512875,https://api.github.com/repos/simonw/datasette/issues/1510,1610512875,IC_kwDOBm6k_c5f_nnr,9599,simonw,2023-06-28T02:02:10Z,2023-06-28T02:05:21Z,OWNER,"I prototyped an approach to this using dataclasses and a `cog` mechanism for turning those into rendered tables in Sphinx. Here's what that prototype looks like:
See https://github.com/simonw/datasette/commit/68223784167fdec4e7ebfca56002a6548ba7b423 for how it works.
Here's the class that documented:
https://github.com/simonw/datasette/blob/68223784167fdec4e7ebfca56002a6548ba7b423/datasette/context.py#L54-L68
And the code that generates the rST: https://github.com/simonw/datasette/blob/68223784167fdec4e7ebfca56002a6548ba7b423/datasette/context.py#L19-L45
And the bit that cog executes: https://github.com/simonw/datasette/blob/68223784167fdec4e7ebfca56002a6548ba7b423/docs/template_context.rst?plain=1#L9-L12","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1054244712,Datasette 1.0 documented template context (maybe via API docs),
https://github.com/simonw/sqlite-utils/issues/561#issuecomment-1610040517,https://api.github.com/repos/simonw/sqlite-utils/issues/561,1610040517,IC_kwDOCGYnMM5f90TF,9599,simonw,2023-06-27T18:44:31Z,2023-06-27T18:44:38Z,OWNER,"Got this working:
```bash
sqlite-utils insert /tmp/playground.db Playground_Submission_Data \
~/Downloads/Playground_Submission_Data.csv --csv --stop-after 2000
```
","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1777548699,`--stop-after` option for `insert` and `upsert` commands,
https://github.com/simonw/sqlite-utils/issues/235#issuecomment-1606415188,https://api.github.com/repos/simonw/sqlite-utils/issues/235,1606415188,IC_kwDOCGYnMM5fv_NU,9599,simonw,2023-06-26T01:46:47Z,2023-06-26T01:47:01Z,OWNER,"I just tested this in a brand new virtual environment using the macOS Python 3:
```bash
pipenv shell --python /Applications/Xcode.app/Contents/Developer/usr/bin/python3
```
Then in that virtual environment I ran:
```bash
pip install sqlite-utils
# Confirm the right one is on the path:
which sqlite-utils
curl ""https://data.nasa.gov/resource/y77d-th95.json"" | \
sqlite-utils insert meteorites.db meteorites - --pk=id
sqlite-utils extract meteorites.db meteorites recclass
```
This threw the same error reported above. Then I did this:
```bash
rm meteorites.db
pip install sqlean.py
curl ""https://data.nasa.gov/resource/y77d-th95.json"" | \
sqlite-utils insert meteorites.db meteorites - --pk=id
sqlite-utils extract meteorites.db meteorites recclass
```
And that second time it worked correctly.","{""total_count"": 1, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 1, ""rocket"": 0, ""eyes"": 0}",810618495,Extract columns cannot create foreign key relation: sqlite3.OperationalError: table sqlite_master may not be modified,
https://github.com/simonw/sqlite-utils/issues/235#issuecomment-1606411508,https://api.github.com/repos/simonw/sqlite-utils/issues/235,1606411508,IC_kwDOCGYnMM5fv-T0,9599,simonw,2023-06-26T01:42:10Z,2023-06-26T01:42:22Z,OWNER,https://sqlite-utils.datasette.io/en/stable/changelog.html#v3-33 - upgrading to `sqlite-utils>=3.33` and then installing both `sqlean.py` and `sqlite-dump` in the same virtual environment as `sqlite-utils` should fix this issue.,"{""total_count"": 1, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 1, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",810618495,Extract columns cannot create foreign key relation: sqlite3.OperationalError: table sqlite_master may not be modified,
https://github.com/simonw/datasette/pull/2052#issuecomment-1606352600,https://api.github.com/repos/simonw/datasette/issues/2052,1606352600,IC_kwDOBm6k_c5fvv7Y,15178711,asg017,2023-06-26T00:17:04Z,2023-06-26T00:17:04Z,CONTRIBUTOR,":wave: would love to see this get merged soon! I want to make a javascript plugin on top of the code-mirror editor to make a few things nicer (function auto-complete, table/column descriptions, etc.), and this would help out a bunch","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1651082214,"feat: Javascript Plugin API (Custom panels, column menu items with JS actions)",
https://github.com/simonw/sqlite-utils/pull/560#issuecomment-1606315321,https://api.github.com/repos/simonw/sqlite-utils/issues/560,1606315321,IC_kwDOCGYnMM5fvm05,9599,simonw,2023-06-25T23:18:33Z,2023-06-25T23:18:33Z,OWNER,Documentation preview: https://sqlite-utils--560.org.readthedocs.build/en/560/installation.html#alternatives-to-sqlite3,"{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1773458985,Use sqlean if available in environment,
https://github.com/simonw/sqlite-utils/pull/560#issuecomment-1606310630,https://api.github.com/repos/simonw/sqlite-utils/issues/560,1606310630,IC_kwDOCGYnMM5fvlrm,9599,simonw,2023-06-25T23:06:07Z,2023-06-25T23:06:07Z,OWNER,"Filed an issue about the above with `pysqlite3` (which `sqlean.py` is based on) here:
- https://github.com/coleifer/pysqlite3/issues/58","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1773458985,Use sqlean if available in environment,
https://github.com/simonw/sqlite-utils/pull/560#issuecomment-1606297356,https://api.github.com/repos/simonw/sqlite-utils/issues/560,1606297356,IC_kwDOCGYnMM5fvicM,9599,simonw,2023-06-25T22:42:41Z,2023-06-25T22:42:41Z,OWNER,"Yes that does seem to do the trick:
```pycon
>>> import sqlean
>>> db = sqlean.connect(""/tmp/4.db"")
>>> db.execute('PRAGMA journal_mode;').fetchall()
[('delete',)]
>>> db.isolation_level
''
>>> db.execute('PRAGMA journal_mode=wal;')
Traceback (most recent call last):
File """", line 1, in
sqlean.dbapi2.OperationalError: cannot change into wal mode from within a transaction
>>> db.isolation_level = None
>>> db.isolation_level
>>> db.execute('PRAGMA journal_mode=wal;')
```
Weird how `isolation_level` of empty string causes the error, but setting that to `None` fixes the error.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1773458985,Use sqlean if available in environment,
https://github.com/simonw/sqlite-utils/pull/560#issuecomment-1606294627,https://api.github.com/repos/simonw/sqlite-utils/issues/560,1606294627,IC_kwDOCGYnMM5fvhxj,9599,simonw,2023-06-25T22:40:10Z,2023-06-25T22:40:10Z,OWNER,I suspect this has something to do with `autocommit` mode in `sqlite3` - which I may be able to turn off by setting `con.isolation_level = None`.,"{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1773458985,Use sqlean if available in environment,
https://github.com/simonw/sqlite-utils/pull/560#issuecomment-1606293382,https://api.github.com/repos/simonw/sqlite-utils/issues/560,1606293382,IC_kwDOCGYnMM5fvheG,9599,simonw,2023-06-25T22:34:47Z,2023-06-25T22:34:47Z,OWNER,"```pycon
>>> import sqlite3
>>> db = sqlite3.connect(""/tmp/1.db"")
>>> db.execute('PRAGMA journal_mode=wal;')
>>> import sqlean
>>> db2 = sqlean.connect(""/tmp/2.db"")
>>> db2.execute('PRAGMA journal_mode=wal;')
Traceback (most recent call last):
File """", line 1, in
sqlean.dbapi2.OperationalError: cannot change into wal mode from within a transaction
```","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1773458985,Use sqlean if available in environment,
https://github.com/simonw/sqlite-utils/pull/560#issuecomment-1606290917,https://api.github.com/repos/simonw/sqlite-utils/issues/560,1606290917,IC_kwDOCGYnMM5fvg3l,9599,simonw,2023-06-25T22:32:28Z,2023-06-25T22:32:28Z,OWNER,"I've fixed most of the test failures, but I still need to fix this one:
> cannot change into wal mode from within a transaction","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1773458985,Use sqlean if available in environment,
https://github.com/simonw/sqlite-utils/pull/560#issuecomment-1606273005,https://api.github.com/repos/simonw/sqlite-utils/issues/560,1606273005,IC_kwDOCGYnMM5fvcft,9599,simonw,2023-06-25T21:47:47Z,2023-06-25T21:47:47Z,OWNER,I can use https://github.com/simonw/sqlite-dump as an optional dependency to handle the missing `.iterdump()` method.,"{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1773458985,Use sqlean if available in environment,
https://github.com/simonw/sqlite-utils/pull/560#issuecomment-1606270887,https://api.github.com/repos/simonw/sqlite-utils/issues/560,1606270887,IC_kwDOCGYnMM5fvb-n,9599,simonw,2023-06-25T21:37:12Z,2023-06-26T08:21:00Z,OWNER,"On my own laptop I got a crash running the tests - details here:
- https://github.com/nalgeon/sqlean.py/issues/3","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1773458985,Use sqlean if available in environment,
https://github.com/simonw/sqlite-utils/pull/560#issuecomment-1606270055,https://api.github.com/repos/simonw/sqlite-utils/issues/560,1606270055,IC_kwDOCGYnMM5fvbxn,9599,simonw,2023-06-25T21:31:56Z,2023-06-25T21:31:56Z,OWNER,"Lots of failures now that I'm trying to run the tests against `sqlean.py` on macOS and Python 3.10: https://github.com/simonw/sqlite-utils/actions/runs/5371800108/jobs/9744802953
A bunch of these, because `pysqlite3` chooses not to implement `.iterdump()`:
```
@pytest.fixture
def db_to_analyze_path(db_to_analyze, tmpdir):
path = str(tmpdir / ""test.db"")
db = sqlite3.connect(path)
> db.executescript(""\n"".join(db_to_analyze.conn.iterdump()))
E AttributeError: 'sqlean.dbapi2.Connection' object has no attribute 'iterdump'
```
Also some of these:
```
def test_analyze_whole_database(db):
assert set(db.table_names()) == {""one_index"", ""two_indexes""}
db.analyze()
> assert set(db.table_names()) == {""one_index"", ""two_indexes"", ""sqlite_stat1""}
E AssertionError: assert {'one_index',...'two_indexes'} == {'one_index',...'two_indexes'}
E Extra items in the left set:
E 'sqlite_stat4'
E Full diff:
E - {'two_indexes', 'sqlite_stat1', 'one_index'}
E + {'two_indexes', 'sqlite_stat1', 'sqlite_stat4', 'one_index'}
E ? ++++++++++++++++
```
Apparently `sqlean.py` adds a `sqlite_stat4` table that the tests are not expecting.
Plus some errors that look like this:
```
def test_enable_wal():
runner = CliRunner()
dbs = [""test.db"", ""test2.db""]
with runner.isolated_filesystem():
for dbname in dbs:
db = Database(dbname)
db[""t""].create({""pk"": int}, pk=""pk"")
assert db.journal_mode == ""delete""
result = runner.invoke(cli.cli, [""enable-wal""] + dbs)
> assert 0 == result.exit_code
E AssertionError: assert 0 == 1
E + where 1 = .exit_code
```
Test summary:
```
============ 13 failed, 909 passed, 16 skipped, 2 errors in 19.29s =============
```","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1773458985,Use sqlean if available in environment,
https://github.com/simonw/sqlite-utils/pull/560#issuecomment-1606237836,https://api.github.com/repos/simonw/sqlite-utils/issues/560,1606237836,IC_kwDOCGYnMM5fvT6M,22429695,codecov[bot],2023-06-25T19:49:45Z,2023-06-26T08:20:59Z,NONE,"## [Codecov](https://app.codecov.io/gh/simonw/sqlite-utils/pull/560?src=pr&el=h1&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison) Report
Patch coverage: **`80.55`**% and project coverage change: **`-0.15`** :warning:
> Comparison is base [(`2747257`)](https://app.codecov.io/gh/simonw/sqlite-utils/commit/2747257a3334d55e890b40ec58fada57ae8cfbfd?el=desc&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison) 96.36% compared to head [(`5e7d27e`)](https://app.codecov.io/gh/simonw/sqlite-utils/pull/560?src=pr&el=desc&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison) 96.22%.
Additional details and impacted files
```diff
@@ Coverage Diff @@
## main #560 +/- ##
==========================================
- Coverage 96.36% 96.22% -0.15%
==========================================
Files 6 6
Lines 2726 2752 +26
==========================================
+ Hits 2627 2648 +21
- Misses 99 104 +5
```
| [Impacted Files](https://app.codecov.io/gh/simonw/sqlite-utils/pull/560?src=pr&el=tree&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison) | Coverage Δ | |
|---|---|---|
| [sqlite\_utils/utils.py](https://app.codecov.io/gh/simonw/sqlite-utils/pull/560?src=pr&el=tree&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison#diff-c3FsaXRlX3V0aWxzL3V0aWxzLnB5) | `94.56% <63.63%> (-0.62%)` | :arrow_down: |
| [sqlite\_utils/db.py](https://app.codecov.io/gh/simonw/sqlite-utils/pull/560?src=pr&el=tree&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison#diff-c3FsaXRlX3V0aWxzL2RiLnB5) | `97.33% <86.36%> (-0.20%)` | :arrow_down: |
| [sqlite\_utils/cli.py](https://app.codecov.io/gh/simonw/sqlite-utils/pull/560?src=pr&el=tree&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison#diff-c3FsaXRlX3V0aWxzL2NsaS5weQ==) | `95.22% <100.00%> (ø)` | |
[:umbrella: View full report in Codecov by Sentry](https://app.codecov.io/gh/simonw/sqlite-utils/pull/560?src=pr&el=continue&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison).
:loudspeaker: Do you have feedback about the report comment? [Let us know in this issue](https://about.codecov.io/codecov-pr-comment-feedback/?utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison).
","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1773458985,Use sqlean if available in environment,
https://github.com/simonw/sqlite-utils/issues/235#issuecomment-1604379952,https://api.github.com/repos/simonw/sqlite-utils/issues/235,1604379952,IC_kwDOCGYnMM5foOUw,9599,simonw,2023-06-23T14:39:55Z,2023-06-23T15:39:32Z,OWNER,"Ideally a workaround for this right now would be to install `pysqlite3` in the same virtual environment:
sqlite-utils install pysqlite3-binary
But `pysqlite3-binary` doesn't yet ship a wheel for macOS so this probably won't work for most people.
The ""easiest"" fix at the moment is to use Python from Homebrew - so `brew install sqlite-utils` for example won't suffer from this problem. Not a great solution for people who aren't using Homebrew though!","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",810618495,Extract columns cannot create foreign key relation: sqlite3.OperationalError: table sqlite_master may not be modified,
https://github.com/simonw/datasette/issues/260#issuecomment-1600778057,https://api.github.com/repos/simonw/datasette/issues/260,1600778057,IC_kwDOBm6k_c5fae9J,9599,simonw,2023-06-21T12:51:22Z,2023-06-21T12:51:22Z,OWNER,"Another example of confusion from this today: https://discord.com/channels/823971286308356157/823971286941302908/1121042411238457374
See also https://gist.github.com/BinomeDeNewton/651ac8b50dd5420f8e54d1682eee5fed?permalink_comment_id=4605982#gistcomment-4605982","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",323223872,Validate metadata.json on startup,
https://github.com/simonw/sqlite-utils/issues/535#issuecomment-1592617271,https://api.github.com/repos/simonw/sqlite-utils/issues/535,1592617271,IC_kwDOCGYnMM5e7Wk3,13780613,erlend-aasland,2023-06-15T08:39:49Z,2023-06-15T08:39:49Z,NONE,"> piping to `jq` is good enough usually
... or `python -m json.tool`[^1], if you don't have `jq` installed.
[^1]: no fancy colouring, like `jq`; only pretty-printing","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1655860104,rows: --transpose or psql extended view-like functionality,
https://github.com/simonw/sqlite-utils/issues/529#issuecomment-1592110694,https://api.github.com/repos/simonw/sqlite-utils/issues/529,1592110694,IC_kwDOCGYnMM5e5a5m,7908073,chapmanjacobd,2023-06-14T23:11:47Z,2023-06-14T23:12:12Z,CONTRIBUTOR,"sorry i was wrong. `sqlite-utils --raw-lines` works correctly
```
sqlite-utils --raw-lines :memory: ""SELECT * FROM (VALUES ('test'), ('line2'))"" | cat -A
test$
line2$
sqlite-utils --csv --no-headers :memory: ""SELECT * FROM (VALUES ('test'), ('line2'))"" | cat -A
test$
line2$
```
I think this was fixed somewhat recently","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1581090327,Microsoft line endings,
https://github.com/simonw/sqlite-utils/issues/535#issuecomment-1592052320,https://api.github.com/repos/simonw/sqlite-utils/issues/535,1592052320,IC_kwDOCGYnMM5e5Mpg,7908073,chapmanjacobd,2023-06-14T22:05:28Z,2023-06-14T22:05:28Z,CONTRIBUTOR,piping to `jq` is good enough usually,"{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1655860104,rows: --transpose or psql extended view-like functionality,
https://github.com/simonw/sqlite-utils/issues/555#issuecomment-1592047502,https://api.github.com/repos/simonw/sqlite-utils/issues/555,1592047502,IC_kwDOCGYnMM5e5LeO,7908073,chapmanjacobd,2023-06-14T22:00:10Z,2023-06-14T22:01:57Z,CONTRIBUTOR,"You may want to try doing a performance comparison between this and just selecting all the ids with few constraints and then doing the filtering within python.
That might seem like a lazy-programmer, inefficient way but queries with large resultsets are a different profile than what databases like SQLITE are designed for. That is not to say that SQLITE is slow or that python is always faster but when you start reading >20% of an index there is an equilibrium that is reached. Especially when adding in writing extra temp tables and stuff to memory/disk. And especially given the `NOT IN` style of query...
You may also try chunking like this:
```py
def chunks(lst, n) -> Generator:
for i in range(0, len(lst), n):
yield lst[i : i + n]
SQLITE_PARAM_LIMIT = 32765
data = []
chunked = chunks(video_ids, consts.SQLITE_PARAM_LIMIT)
for ids in chunked:
data.expand(
list(
db.query(
f""""""SELECT * from videos
WHERE id in (""""""
+ "","".join([""?""] * len(ids))
+ "")"",
(*ids,),
)
)
)
```
but that actually won't work with your `NOT IN` requirements. You need to query the full resultset to check any row.
Since you are doing stuff with files/videos in SQLITE you might be interested in my side project: https://github.com/chapmanjacobd/library","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1733198948,Filter table by a large bunch of ids,
https://github.com/simonw/sqlite-utils/issues/557#issuecomment-1590531892,https://api.github.com/repos/simonw/sqlite-utils/issues/557,1590531892,IC_kwDOCGYnMM5ezZc0,7908073,chapmanjacobd,2023-06-14T06:09:21Z,2023-06-14T06:09:21Z,CONTRIBUTOR,"I put together a [simple script](https://github.com/chapmanjacobd/library/blob/42129c5ebe15f9d74653c0f5ca4ed0c991d383e0/xklb/scripts/dedupe_db.py) to upsert and remove duplicate rows based on business keys. If anyone has similar problems with above this might help
```
CREATE TABLE my_table (
id INTEGER PRIMARY KEY,
column1 TEXT,
column2 TEXT,
column3 TEXT
);
INSERT INTO my_table (column1, column2, column3)
VALUES
('Value 1', 'Duplicate 1', 'Duplicate A'),
('Value 2', 'Duplicate 2', 'Duplicate B'),
('Value 3', 'Duplicate 2', 'Duplicate C'),
('Value 4', 'Duplicate 3', 'Duplicate D'),
('Value 5', 'Duplicate 3', 'Duplicate E'),
('Value 6', 'Duplicate 3', 'Duplicate F');
```
```
library dedupe-db test.db my_table --bk column2
```","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1740150327,Aliased ROWID option for tables created from alter=True commands,
https://github.com/simonw/datasette/pull/2052#issuecomment-1585149909,https://api.github.com/repos/simonw/datasette/issues/2052,1585149909,IC_kwDOBm6k_c5ee3fV,9020979,hydrosquall,2023-06-09T21:35:00Z,2023-06-09T21:35:00Z,NONE,"Thanks @cldellow for the thoughtful comments! These are all things that I'll keep in mind as we figure out how/if this API is actually used by plugin authors once it's actually out in the world.
> Yes, this would work - but it requires me to continue to communicate the column names out of band (in order to fetch the facet data per-column before registering my plugin), vs being able to re-use them from the plugin implementation.
Ah, I understand now! Thanks for explaining. ","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1651082214,"feat: Javascript Plugin API (Custom panels, column menu items with JS actions)",
https://github.com/simonw/sqlite-utils/issues/433#issuecomment-1578840450,https://api.github.com/repos/simonw/sqlite-utils/issues/433,1578840450,IC_kwDOCGYnMM5eGzGC,392720,jonafato,2023-06-06T14:09:04Z,2023-06-06T14:09:04Z,NONE,"I also ran into this recently. See below for a patch for one possible solution (tested via ""it works on my machine"", but I don't expect that this behavior would vary a whole lot across terminal emulators and shells). Another possible solution might be to subclass click's `ProgressBar` to keep the logic within the original context manager. Happy to send a PR or for this patch to serve as the basis for a fix that someone else authors.
```patch
diff --git a/sqlite_utils/utils.py b/sqlite_utils/utils.py
index 06c1a4c..530a3a3 100644
--- a/sqlite_utils/utils.py
+++ b/sqlite_utils/utils.py
@@ -147,14 +147,23 @@ def decode_base64_values(doc):
class UpdateWrapper:
- def __init__(self, wrapped, update):
+ def __init__(self, wrapped, update, render_finish):
self._wrapped = wrapped
self._update = update
+ self._render_finish = render_finish
def __iter__(self):
- for line in self._wrapped:
- self._update(len(line))
- yield line
+ return self
+
+ def __next__(self):
+ try:
+ line = next(self._wrapped)
+ except StopIteration as e:
+ self._render_finish()
+ raise
+
+ self._update(len(line))
+ return line
def read(self, size=-1):
data = self._wrapped.read(size)
@@ -178,7 +187,7 @@ def file_progress(file, silent=False, **kwargs):
else:
file_length = os.path.getsize(file.name)
with click.progressbar(length=file_length, **kwargs) as bar:
- yield UpdateWrapper(file, bar.update)
+ yield UpdateWrapper(file, bar.update, bar.render_finish)
class Format(enum.Enum):
```","{""total_count"": 1, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 1, ""eyes"": 0}",1239034903,CLI eats my cursor,
https://github.com/simonw/sqlite-utils/issues/557#issuecomment-1577355134,https://api.github.com/repos/simonw/sqlite-utils/issues/557,1577355134,IC_kwDOCGYnMM5eBId-,7908073,chapmanjacobd,2023-06-05T19:26:26Z,2023-06-05T19:26:26Z,CONTRIBUTOR,"this isn't really actionable... I'm just being a whiny baby. I have tasted the milk of being able to use `upsert_all`, `insert_all`, etc without having to write DDL to create tables. The meat of the issue is that SQLITE doesn't make rowid stable between vacuums so it is not possible to take shortcuts","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1740150327,Aliased ROWID option for tables created from alter=True commands,
https://github.com/simonw/sqlite-utils/issues/556#issuecomment-1575310378,https://api.github.com/repos/simonw/sqlite-utils/issues/556,1575310378,IC_kwDOCGYnMM5d5VQq,601708,mcint,2023-06-04T01:21:15Z,2023-06-04T01:21:15Z,CONTRIBUTOR,"I've resolved my use, with the line-buffered output and while read loop for line buffered input, but I leave this here so the incremental saving or line-buffered use-case can be explicitly handled or rejected (or deferred).","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1740026046,Support storing incrementally piped values,
https://github.com/simonw/datasette/pull/2053#issuecomment-1565058994,https://api.github.com/repos/simonw/datasette/issues/2053,1565058994,IC_kwDOBm6k_c5dSOey,9599,simonw,2023-05-26T23:13:02Z,2023-05-26T23:13:02Z,OWNER,"I should have an extra called `extra_html_context` which bundles together all of the weird extra stuff needed by the HTML template, and is then passed as the root context when the template is rendered (with the other stuff from extras patched into it).","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1656432059,WIP new JSON for queries,
https://github.com/simonw/datasette/pull/2053#issuecomment-1563793781,https://api.github.com/repos/simonw/datasette/issues/2053,1563793781,IC_kwDOBm6k_c5dNZl1,9599,simonw,2023-05-26T04:27:55Z,2023-05-26T04:27:55Z,OWNER,"I should split out a `canned_query.html` template too, as something that extends the `query.html` template.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1656432059,WIP new JSON for queries,
https://github.com/simonw/datasette/pull/2053#issuecomment-1563667574,https://api.github.com/repos/simonw/datasette/issues/2053,1563667574,IC_kwDOBm6k_c5dM6x2,9599,simonw,2023-05-26T00:40:22Z,2023-05-26T00:40:22Z,OWNER,"Or maybe...
- `BaseQueryView(View)` - knows how to render the results of a SQL query
- `QueryView(BaseQueryView)` - renders from `?sql=`
- `CannedQueryView(BaseQueryView)` - renders for a named canned query
And then later perhaps:
- `RowQueryView(BaseQueryView)` - renders the `select * from t where pk = ?`
- `TableQueryView(BaseQueryView)` - replaces the super complex existing `TableView`","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1656432059,WIP new JSON for queries,
https://github.com/simonw/datasette/pull/2053#issuecomment-1563663925,https://api.github.com/repos/simonw/datasette/issues/2053,1563663925,IC_kwDOBm6k_c5dM541,9599,simonw,2023-05-26T00:32:47Z,2023-05-26T00:35:47Z,OWNER,"I'm going to entirely split canned queries off from `?sql=` queries - they share a bunch of code right now which is just making everything much harder to follow.
I'll refactor their shared bits into functions that they both call.
Or _maybe_ I'll try having `CannedQueryView` as a subclass of `QueryView`.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1656432059,WIP new JSON for queries,
https://github.com/simonw/datasette/pull/2053#issuecomment-1563663616,https://api.github.com/repos/simonw/datasette/issues/2053,1563663616,IC_kwDOBm6k_c5dM50A,9599,simonw,2023-05-26T00:32:08Z,2023-05-26T00:32:08Z,OWNER,"Now that I have the new `View` subclass from #2078 I want to use it to simplify this code.
Challenge: there are several things to consider here:
- The `/db` page without `?sql=` displays a list of tables in that database
- With `?sql=` it shows the query results for that query (or an error)
- If it's a `/db/name-of-canned-query` it works a bit like the query page, but executes a canned query instead of the `?sql=` query
- POST `/db/name-of-canned-query` is support for writable canned queries","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1656432059,WIP new JSON for queries,
https://github.com/simonw/datasette/pull/2080#issuecomment-1563650990,https://api.github.com/repos/simonw/datasette/issues/2080,1563650990,IC_kwDOBm6k_c5dM2uu,9599,simonw,2023-05-26T00:08:59Z,2023-05-26T00:08:59Z,OWNER,"I'm not going to document this yet, I want to let it bake for a bit longer first.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1726603778,New View base class,
https://github.com/simonw/datasette/pull/2080#issuecomment-1563629348,https://api.github.com/repos/simonw/datasette/issues/2080,1563629348,IC_kwDOBm6k_c5dMxck,22429695,codecov[bot],2023-05-25T23:31:10Z,2023-05-26T00:07:34Z,NONE,"## [Codecov](https://app.codecov.io/gh/simonw/datasette/pull/2080?src=pr&el=h1&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison) Report
Patch coverage: **`95.45`**% and project coverage change: **`+0.01`** :tada:
> Comparison is base [(`b49fa44`)](https://app.codecov.io/gh/simonw/datasette/commit/b49fa446d683ddcaf6faf2944dacc0d866bf2d70?el=desc&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison) 92.40% compared to head [(`df5fd73`)](https://app.codecov.io/gh/simonw/datasette/pull/2080?src=pr&el=desc&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison) 92.41%.
> :exclamation: Current head df5fd73 differs from pull request most recent head e990fbc. Consider uploading reports for the commit e990fbc to get more accurate results
Additional details and impacted files
```diff
@@ Coverage Diff @@
## main #2080 +/- ##
==========================================
+ Coverage 92.40% 92.41% +0.01%
==========================================
Files 39 39
Lines 5768 5790 +22
==========================================
+ Hits 5330 5351 +21
- Misses 438 439 +1
```
| [Impacted Files](https://app.codecov.io/gh/simonw/datasette/pull/2080?src=pr&el=tree&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison) | Coverage Δ | |
|---|---|---|
| [datasette/views/base.py](https://app.codecov.io/gh/simonw/datasette/pull/2080?src=pr&el=tree&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison#diff-ZGF0YXNldHRlL3ZpZXdzL2Jhc2UucHk=) | `92.97% <95.45%> (+0.18%)` | :arrow_up: |
[:umbrella: View full report in Codecov by Sentry](https://app.codecov.io/gh/simonw/datasette/pull/2080?src=pr&el=continue&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison).
:loudspeaker: Do you have feedback about the report comment? [Let us know in this issue](https://about.codecov.io/codecov-pr-comment-feedback/?utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison).
","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1726603778,New View base class,
https://github.com/simonw/datasette/pull/2080#issuecomment-1563626231,https://api.github.com/repos/simonw/datasette/issues/2080,1563626231,IC_kwDOBm6k_c5dMwr3,9599,simonw,2023-05-25T23:25:17Z,2023-05-25T23:25:17Z,OWNER,I'm going to try using this for the `/-/patterns` page.,"{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1726603778,New View base class,
https://github.com/simonw/datasette/issues/2078#issuecomment-1563625093,https://api.github.com/repos/simonw/datasette/issues/2078,1563625093,IC_kwDOBm6k_c5dMwaF,9599,simonw,2023-05-25T23:23:15Z,2023-05-25T23:23:15Z,OWNER,"Rest of the work on this will happen in the PR:
- #2080","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1726236847,Resolve the difference between `wrap_view()` and `BaseView`,
https://github.com/simonw/datasette/issues/2079#issuecomment-1563607291,https://api.github.com/repos/simonw/datasette/issues/2079,1563607291,IC_kwDOBm6k_c5dMsD7,9599,simonw,2023-05-25T22:56:28Z,2023-05-25T22:56:28Z,OWNER,Wrote this up as a TIL: https://til.simonwillison.net/http/testing-cors-max-age,"{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1726531350,Datasette should serve Access-Control-Max-Age,
https://github.com/simonw/datasette/issues/2079#issuecomment-1563597589,https://api.github.com/repos/simonw/datasette/issues/2079,1563597589,IC_kwDOBm6k_c5dMpsV,9599,simonw,2023-05-25T22:42:07Z,2023-05-25T22:42:07Z,OWNER,"Mystery solved as to why I wasn't seeing this work:
I had ""Disable Cache"" checked!
I ran this experiment after un-checking that box:
```javascript
fetch('https://latest.datasette.io/ephemeral/foo/1/-/update', {
method: 'POST',
headers: {
'Content-Type': 'application/json'
},
body: JSON.stringify({ test: 'test' })
});
// And run it again
fetch('https://latest.datasette.io/ephemeral/foo/1/-/update', {
method: 'POST',
headers: {
'Content-Type': 'application/json'
},
body: JSON.stringify({ test: 'test' })
});
// Now try a thing that doesn't serve that max-age header yet:
fetch('https://latest-with-plugins.datasette.io/ephemeral/foo/1/-/update', {
method: 'POST',
headers: {
'Content-Type': 'application/json'
},
body: JSON.stringify({ test: 'test' })
});
// And a second time but within 5s
fetch('https://latest-with-plugins.datasette.io/ephemeral/foo/1/-/update', {
method: 'POST',
headers: {
'Content-Type': 'application/json'
},
body: JSON.stringify({ test: 'test' })
});
// Third time after waiting longer than 5s
fetch('https://latest-with-plugins.datasette.io/ephemeral/foo/1/-/update', {
method: 'POST',
headers: {
'Content-Type': 'application/json'
},
body: JSON.stringify({ test: 'test' })
});
// Try that original one again - still within the 1hr cache time
fetch('https://latest.datasette.io/ephemeral/foo/1/-/update', {
method: 'POST',
headers: {
'Content-Type': 'application/json'
},
body: JSON.stringify({ test: 'test' })
});
```
The results show that the cache of 1hr was being obeyed for `latest.datasette.io` while the `latest-with-plugins.datasette.io` default cache of 5s was being obeyed too.
","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1726531350,Datasette should serve Access-Control-Max-Age,
https://github.com/simonw/datasette/issues/2079#issuecomment-1563588199,https://api.github.com/repos/simonw/datasette/issues/2079,1563588199,IC_kwDOBm6k_c5dMnZn,9599,simonw,2023-05-25T22:29:47Z,2023-05-25T22:30:12Z,OWNER,"https://fetch.spec.whatwg.org/#http-access-control-max-age says:
> Indicates the number of seconds (5 by default) the information provided by the [Access-Control-Allow-Methods](https://fetch.spec.whatwg.org/#http-access-control-allow-methods) and [Access-Control-Allow-Headers](https://fetch.spec.whatwg.org/#http-access-control-allow-headers) [headers](https://fetch.spec.whatwg.org/#concept-header) can be cached.
So there was already a 5s cache anyway.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1726531350,Datasette should serve Access-Control-Max-Age,
https://github.com/simonw/datasette/issues/2079#issuecomment-1563587230,https://api.github.com/repos/simonw/datasette/issues/2079,1563587230,IC_kwDOBm6k_c5dMnKe,9599,simonw,2023-05-25T22:28:20Z,2023-05-25T22:28:20Z,OWNER,"Weird... after the deploy went out:
But the request did indeed get the new header:
So I'm not sure why it's making multiple `POST` requests like that.
Maybe it's because the attempted `POST` failed with a 404?","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1726531350,Datasette should serve Access-Control-Max-Age,
https://github.com/simonw/datasette/issues/2079#issuecomment-1563565407,https://api.github.com/repos/simonw/datasette/issues/2079,1563565407,IC_kwDOBm6k_c5dMh1f,9599,simonw,2023-05-25T22:09:53Z,2023-05-25T22:09:53Z,OWNER,Updated docs: https://docs.datasette.io/en/latest/json_api.html#enabling-cors,"{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1726531350,Datasette should serve Access-Control-Max-Age,
https://github.com/simonw/datasette/issues/2079#issuecomment-1563563438,https://api.github.com/repos/simonw/datasette/issues/2079,1563563438,IC_kwDOBm6k_c5dMhWu,9599,simonw,2023-05-25T22:08:28Z,2023-05-25T22:08:28Z,OWNER,"I ran this on https://www.example.com/ twice using the console:
```javascript
fetch(
`https://latest.datasette.io/ephemeral/foo/1/-/update`,
{
method: ""POST"",
mode: ""cors"",
headers: {
Authorization: `Bearer tok`,
""Content-Type"": ""application/json"",
},
body: JSON.stringify({update: {blah: 1}}),
}
)
.then((r) => r.json())
.then((data) => {
console.log(data);
});
```
And got this in the network pane:
","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1726531350,Datasette should serve Access-Control-Max-Age,
https://github.com/simonw/datasette/issues/2079#issuecomment-1563558915,https://api.github.com/repos/simonw/datasette/issues/2079,1563558915,IC_kwDOBm6k_c5dMgQD,9599,simonw,2023-05-25T22:04:41Z,2023-05-25T22:04:41Z,OWNER,I'm going with 3600 for 1 hour instead of 600 for 10 minutes.,"{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1726531350,Datasette should serve Access-Control-Max-Age,
https://github.com/simonw/datasette/issues/2079#issuecomment-1563547097,https://api.github.com/repos/simonw/datasette/issues/2079,1563547097,IC_kwDOBm6k_c5dMdXZ,9599,simonw,2023-05-25T21:51:38Z,2023-05-25T21:51:38Z,OWNER,"Also need to update this documentation:
https://github.com/simonw/datasette/blob/9584879534ff0556e04e4c420262972884cac87b/docs/json_api.rst?plain=1#L453-L465
Or maybe make that automated via `cog`.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1726531350,Datasette should serve Access-Control-Max-Age,
https://github.com/simonw/datasette/issues/2078#issuecomment-1563522011,https://api.github.com/repos/simonw/datasette/issues/2078,1563522011,IC_kwDOBm6k_c5dMXPb,9599,simonw,2023-05-25T21:22:30Z,2023-05-25T21:22:30Z,OWNER,"This is bad:
```python
async def __call__(self, request, datasette):
try:
handler = getattr(self, request.method.lower())
return await handler(request, datasette)
except AttributeError:
return await self.method_not_allowed(request)
```
Because it hides any `AttributeError` exceptions that might occur in the view code.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1726236847,Resolve the difference between `wrap_view()` and `BaseView`,
https://github.com/simonw/datasette/issues/2078#issuecomment-1563511171,https://api.github.com/repos/simonw/datasette/issues/2078,1563511171,IC_kwDOBm6k_c5dMUmD,9599,simonw,2023-05-25T21:11:20Z,2023-05-25T21:13:05Z,OWNER,I'm going to call this `VerbView` for the moment. Might even rename it to `View` later.,"{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1726236847,Resolve the difference between `wrap_view()` and `BaseView`,
https://github.com/simonw/datasette/issues/2078#issuecomment-1563498048,https://api.github.com/repos/simonw/datasette/issues/2078,1563498048,IC_kwDOBm6k_c5dMRZA,9599,simonw,2023-05-25T20:57:52Z,2023-05-25T20:58:13Z,OWNER,"Here's a new `BaseView` class that automatically populates `OPTIONS` based on available methods:
```python
class BaseView:
async def head(self, *args, **kwargs):
try:
response = await self.get(*args, **kwargs)
response.body = b""""
return response
except AttributeError:
raise
async def method_not_allowed(self, request):
if (
request.path.endswith("".json"")
or request.headers.get(""content-type"") == ""application/json""
):
response = Response.json(
{""ok"": False, ""error"": ""Method not allowed""}, status=405
)
else:
response = Response.text(""Method not allowed"", status=405)
return response
async def options(self, request, *args, **kwargs):
response = Response.text(""ok"")
response.headers[""allow""] = "", "".join(
method.upper()
for method in (""head"", ""get"", ""post"", ""put"", ""patch"", ""delete"")
if hasattr(self, method)
)
return response
async def __call__(self, request, datasette):
try:
handler = getattr(self, request.method.lower())
return await handler(request, datasette)
except AttributeError:
return await self.method_not_allowed(request)
class DemoView(BaseView):
async def get(self, datasette, request):
return Response.text(""Hello there! {} - {}"".format(datasette, request))
post = get
```","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1726236847,Resolve the difference between `wrap_view()` and `BaseView`,
https://github.com/simonw/datasette/issues/2078#issuecomment-1563488929,https://api.github.com/repos/simonw/datasette/issues/2078,1563488929,IC_kwDOBm6k_c5dMPKh,9599,simonw,2023-05-25T20:48:12Z,2023-05-25T20:48:39Z,OWNER,"Actually no need for that extra level of parameter detection: `BaseView.__call__` should _always_ take `datasette, request` - `scope` and `receive` are both available on `request`, and `send` is only needed if you're not planning on returning a `Response` object.
So the `get` and `post` and suchlike methods should take `datasette` and `request` too.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1726236847,Resolve the difference between `wrap_view()` and `BaseView`,
https://github.com/simonw/datasette/issues/2078#issuecomment-1563444296,https://api.github.com/repos/simonw/datasette/issues/2078,1563444296,IC_kwDOBm6k_c5dMERI,9599,simonw,2023-05-25T20:06:08Z,2023-05-25T20:06:08Z,OWNER,"This prototype seems to work well:
```diff
diff --git a/datasette/app.py b/datasette/app.py
index d7dace67..ed0edf28 100644
--- a/datasette/app.py
+++ b/datasette/app.py
@@ -17,6 +17,7 @@ import secrets
import sys
import threading
import time
+import types
import urllib.parse
from concurrent import futures
from pathlib import Path
@@ -1266,6 +1267,8 @@ class Datasette:
# TODO: /favicon.ico and /-/static/ deserve far-future cache expires
add_route(favicon, ""/favicon.ico"")
+ add_route(wrap_view(DemoView, self), '/demo')
+
add_route(
asgi_static(app_root / ""datasette"" / ""static""), r""/-/static/(?P.*)$""
)
@@ -1673,8 +1676,46 @@ def _cleaner_task_str(task):
return _cleaner_task_str_re.sub("""", s)
-def wrap_view(view_fn, datasette):
- @functools.wraps(view_fn)
+class DemoView:
+ async def __call__(self, datasette, request):
+ return Response.text(""Hello there! {} - {}"".format(datasette, request))
+
+def wrap_view(view_fn_or_class, datasette):
+ is_function = isinstance(view_fn_or_class, types.FunctionType)
+ if is_function:
+ return wrap_view_function(view_fn_or_class, datasette)
+ else:
+ if not isinstance(view_fn_or_class, type):
+ raise ValueError(""view_fn_or_class must be a function or a class"")
+ return wrap_view_class(view_fn_or_class, datasette)
+
+
+def wrap_view_class(view_class, datasette):
+ async def async_view_for_class(request, send):
+ instance = view_class()
+ if inspect.iscoroutinefunction(instance.__call__):
+ return await async_call_with_supported_arguments(
+ instance.__call__,
+ scope=request.scope,
+ receive=request.receive,
+ send=send,
+ request=request,
+ datasette=datasette,
+ )
+ else:
+ return call_with_supported_arguments(
+ instance.__call__,
+ scope=request.scope,
+ receive=request.receive,
+ send=send,
+ request=request,
+ datasette=datasette,
+ )
+
+ return async_view_for_class
+
+
+def wrap_view_function(view_fn, datasette):
async def async_view_fn(request, send):
if inspect.iscoroutinefunction(view_fn):
response = await async_call_with_supported_arguments(
```","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1726236847,Resolve the difference between `wrap_view()` and `BaseView`,
https://github.com/simonw/datasette/issues/2078#issuecomment-1563419066,https://api.github.com/repos/simonw/datasette/issues/2078,1563419066,IC_kwDOBm6k_c5dL-G6,9599,simonw,2023-05-25T19:42:16Z,2023-05-25T19:43:08Z,OWNER,"Maybe what I want here is the ability to register classes with the router - and have the router know that if it's a class it should instantiate it via its constructor and then await `__call__` it.
The neat thing about it is that it can reduce the risk of having a class instance that accidentally shares state between requests.
It also encourages that each class only responds based on the `datasette, request, ...` objects that are passed to its methods.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1726236847,Resolve the difference between `wrap_view()` and `BaseView`,
https://github.com/simonw/datasette/issues/2078#issuecomment-1563359114,https://api.github.com/repos/simonw/datasette/issues/2078,1563359114,IC_kwDOBm6k_c5dLveK,9599,simonw,2023-05-25T18:47:57Z,2023-05-25T18:47:57Z,OWNER,"Oops, that broke everything:
```
@documented
async def await_me_maybe(value: typing.Any) -> typing.Any:
""If value is callable, call it. If awaitable, await it. Otherwise return it.""
> if callable(value):
E TypeError: 'module' object is not callable
```","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1726236847,Resolve the difference between `wrap_view()` and `BaseView`,
https://github.com/simonw/datasette/issues/2078#issuecomment-1563329245,https://api.github.com/repos/simonw/datasette/issues/2078,1563329245,IC_kwDOBm6k_c5dLoLd,9599,simonw,2023-05-25T18:26:47Z,2023-05-25T18:28:08Z,OWNER,"With type hints and a namedtuple:
```python
import asyncio
import types
from typing import NamedTuple, Any
class CallableStatus(NamedTuple):
is_callable: bool
is_async_callable: bool
def check_callable(obj: Any) -> CallableStatus:
if not callable(obj):
return CallableStatus(False, False)
if isinstance(obj, type):
# It's a class
return CallableStatus(True, False)
if isinstance(obj, types.FunctionType):
return CallableStatus(True, asyncio.iscoroutinefunction(obj))
if hasattr(obj, ""__call__""):
return CallableStatus(True, asyncio.iscoroutinefunction(obj.__call__))
assert False, ""obj {} is somehow callable with no __call__ method"".format(repr(obj))
```
```python
for thing in (
async_func,
non_async_func,
AsyncClass(),
NotAsyncClass(),
ClassNoCall(),
AsyncClass,
NotAsyncClass,
ClassNoCall,
):
print(thing, check_callable(thing))
```
```
CallableStatus(is_callable=True, is_async_callable=True)
CallableStatus(is_callable=True, is_async_callable=False)
<__main__.AsyncClass object at 0x106ba7490> CallableStatus(is_callable=True, is_async_callable=True)
<__main__.NotAsyncClass object at 0x106740150> CallableStatus(is_callable=True, is_async_callable=False)
<__main__.ClassNoCall object at 0x10676d910> CallableStatus(is_callable=False, is_async_callable=False)
CallableStatus(is_callable=True, is_async_callable=False)
CallableStatus(is_callable=True, is_async_callable=False)
CallableStatus(is_callable=True, is_async_callable=False)
```","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1726236847,Resolve the difference between `wrap_view()` and `BaseView`,
https://github.com/simonw/datasette/issues/2078#issuecomment-1563326000,https://api.github.com/repos/simonw/datasette/issues/2078,1563326000,IC_kwDOBm6k_c5dLnYw,9599,simonw,2023-05-25T18:23:38Z,2023-05-25T18:23:38Z,OWNER,I don't like that `is_callable()` implies a single boolean result but actually returns a pair. I'll call it `check_callable(obj)` instead.,"{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1726236847,Resolve the difference between `wrap_view()` and `BaseView`,
https://github.com/simonw/datasette/issues/2078#issuecomment-1563318598,https://api.github.com/repos/simonw/datasette/issues/2078,1563318598,IC_kwDOBm6k_c5dLllG,9599,simonw,2023-05-25T18:17:03Z,2023-05-25T18:21:25Z,OWNER,"I think I want that to return `(is_callable, is_async)` - so I can both test if the thing can be called AND if it should be awaited in the same operation (without any exceptions).
I tried this:
```python
def is_callable(obj):
""Returns (is_callable, is_async_callable)""
if not callable(obj):
return False, False
if isinstance(obj, types.FunctionType):
return True, asyncio.iscoroutinefunction(obj)
if hasattr(obj, '__call__'):
return True, asyncio.iscoroutinefunction(obj.__call__)
return False, False
```
```python
for thing in (
async_func, non_async_func, AsyncClass(), NotAsyncClass(), ClassNoCall(),
AsyncClass, NotAsyncClass, ClassNoCall
):
print(thing, is_callable(thing))
```
And got:
```
(True, True)
(True, False)
<__main__.AsyncClass object at 0x106cce490> (True, True)
<__main__.NotAsyncClass object at 0x106ccf710> (True, False)
<__main__.ClassNoCall object at 0x106ccc810> (False, False)
(True, True)
(True, False)
(True, False)
```
Which is almost right, but I don't like that `AsyncClass` is shown as callable (which it is, since it's a class) and awaitable (which it is not - the `__call__` method may be async but calling the class constructor is not).
So I'm going to detect classes using `isinstance(obj, type)`.
```python
def is_callable(obj):
""Returns (is_callable, is_async_callable)""
if not callable(obj):
return False, False
if isinstance(obj, type):
# It's a class
return True, False
if isinstance(obj, types.FunctionType):
return True, asyncio.iscoroutinefunction(obj)
if hasattr(obj, '__call__'):
return True, asyncio.iscoroutinefunction(obj.__call__)
assert False, ""obj {} somehow is callable with no __call__ method"".format(obj)
```
I am reasonably confident the `AssertionError` can never be raised.
And now:
```
(True, True)
(True, False)
<__main__.AsyncClass object at 0x106ccfa50> (True, True)
<__main__.NotAsyncClass object at 0x106ccc8d0> (True, False)
<__main__.ClassNoCall object at 0x106cd7690> (False, False)
(True, False)
(True, False)
(True, False)
```
Which is what I wanted.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1726236847,Resolve the difference between `wrap_view()` and `BaseView`,
https://github.com/simonw/datasette/issues/2078#issuecomment-1563308919,https://api.github.com/repos/simonw/datasette/issues/2078,1563308919,IC_kwDOBm6k_c5dLjN3,9599,simonw,2023-05-25T18:08:34Z,2023-05-25T18:08:34Z,OWNER,"After much fiddling this seems to work:
```python
import asyncio, types
def is_async_callable(obj):
if not callable(obj):
raise ValueError(""Object is not callable"")
if isinstance(obj, types.FunctionType):
return asyncio.iscoroutinefunction(obj)
if hasattr(obj, '__call__'):
return asyncio.iscoroutinefunction(obj.__call__)
raise ValueError(""Not a function and has no __call__ attribute"")
```
Tested like so:
```python
class AsyncClass:
async def __call__(self):
pass
class NotAsyncClass:
def __call__(self):
pass
class ClassNoCall:
pass
async def async_func():
pass
def non_async_func():
pass
for thing in (AsyncClass(), NotAsyncClass(), ClassNoCall(), async_func, non_async_func):
try:
print(thing, is_async_callable(thing))
except Exception as ex:
print(thing, ex)
```
```
<__main__.AsyncClass object at 0x106c32150> True
<__main__.NotAsyncClass object at 0x106c32390> False
<__main__.ClassNoCall object at 0x106c32750> Object is not callable
True
False
```","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1726236847,Resolve the difference between `wrap_view()` and `BaseView`,
https://github.com/simonw/datasette/issues/2078#issuecomment-1563294669,https://api.github.com/repos/simonw/datasette/issues/2078,1563294669,IC_kwDOBm6k_c5dLfvN,9599,simonw,2023-05-25T17:57:06Z,2023-05-25T17:57:06Z,OWNER,"I may need to be able to detect if a class instance has an `async def __call__` method - I think I can do that like so:
```python
def iscoroutinefunction(obj):
if inspect.iscoroutinefunction(obj):
return True
if hasattr(obj, '__call__') and inspect.iscoroutinefunction(obj.__call__):
return True
return False
```
From https://github.com/encode/starlette/issues/886#issuecomment-606585152","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1726236847,Resolve the difference between `wrap_view()` and `BaseView`,
https://github.com/simonw/datasette/issues/2078#issuecomment-1563292373,https://api.github.com/repos/simonw/datasette/issues/2078,1563292373,IC_kwDOBm6k_c5dLfLV,9599,simonw,2023-05-25T17:55:12Z,2023-05-25T17:55:30Z,OWNER,"So I think subclasses of `BaseView` need to offer a callable which accepts all five of the DI arguments - `datasette`, `request`, `scope`, `send`, `receive` - and then makes a decision based on the HTTP verb as to which method of the class to call. Those methods themselves can accept a subset of those parameters and will only be sent on to them.
Having two layers of parameter detection feels a little bit untidy, but I think it will work.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1726236847,Resolve the difference between `wrap_view()` and `BaseView`,
https://github.com/simonw/datasette/pull/2053#issuecomment-1563285150,https://api.github.com/repos/simonw/datasette/issues/2053,1563285150,IC_kwDOBm6k_c5dLdae,9599,simonw,2023-05-25T17:48:50Z,2023-05-25T17:49:52Z,OWNER,"Uncommitted experimental code:
```diff
diff --git a/datasette/views/database.py b/datasette/views/database.py
index 455ebd1f..85775433 100644
--- a/datasette/views/database.py
+++ b/datasette/views/database.py
@@ -909,12 +909,13 @@ async def query_view(
elif format_ in datasette.renderers.keys():
# Dispatch request to the correct output format renderer
# (CSV is not handled here due to streaming)
+ print(data)
result = call_with_supported_arguments(
datasette.renderers[format_][0],
datasette=datasette,
- columns=columns,
- rows=rows,
- sql=sql,
+ columns=data[""rows""][0].keys(),
+ rows=data[""rows""],
+ sql='',
query_name=None,
database=db.name,
table=None,
@@ -923,7 +924,7 @@ async def query_view(
# These will be deprecated in Datasette 1.0:
args=request.args,
data={
- ""rows"": rows,
+ ""rows"": data[""rows""],
}, # TODO what should this be?
)
result = await await_me_maybe(result)
diff --git a/docs/index.rst b/docs/index.rst
index 5a9cc7ed..254ed3da 100644
--- a/docs/index.rst
+++ b/docs/index.rst
@@ -57,6 +57,7 @@ Contents
settings
introspection
custom_templates
+ template_context
plugins
writing_plugins
plugin_hooks
```
Where `docs/template_context.rst` looked like this:
```rst
.. _template_context:
Template context
================
.. currentmodule:: datasette.context
This page describes the variables made available to templates used by Datasette to render different pages of the application.
.. autoclass:: QueryContext
:members:
```
And `datasette/context.py` had this:
```python
from dataclasses import dataclass
@dataclass
class QueryContext:
""""""
Used by the ``/database`` page when showing the results of a SQL query
""""""
id: int
""Id is a thing""
rows: list[dict]
""Name is another thing""
```","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1656432059,WIP new JSON for queries,
https://github.com/simonw/datasette/issues/2078#issuecomment-1563283939,https://api.github.com/repos/simonw/datasette/issues/2078,1563283939,IC_kwDOBm6k_c5dLdHj,9599,simonw,2023-05-25T17:47:38Z,2023-05-25T17:47:38Z,OWNER,"The idea behind `wrap_view()` is dependency injection - it's mainly used by plugins:
https://docs.datasette.io/en/0.64.3/plugin_hooks.html#register-routes-datasette
But I like the pattern so I started using it for some of Datasette's own features.
I should use it for _all_ of Datasette's own features.
But I still like the way `BaseView` helps with running different code for GET/POST/etc verbs.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1726236847,Resolve the difference between `wrap_view()` and `BaseView`,
https://github.com/simonw/datasette/issues/2078#issuecomment-1563282327,https://api.github.com/repos/simonw/datasette/issues/2078,1563282327,IC_kwDOBm6k_c5dLcuX,9599,simonw,2023-05-25T17:46:05Z,2023-05-25T17:46:05Z,OWNER,"Here's what `wrap_view()` does:
https://github.com/simonw/datasette/blob/49184c569cd70efbda4f3f062afef3a34401d8d5/datasette/app.py#L1676-L1700
It's used e.g. here:
https://github.com/simonw/datasette/blob/49184c569cd70efbda4f3f062afef3a34401d8d5/datasette/app.py#L1371-L1375
The `BaseView` thing meanwhile works like this:
https://github.com/simonw/datasette/blob/d97e82df3c8a3f2e97038d7080167be9bb74a68d/datasette/views/base.py#L56-L157","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1726236847,Resolve the difference between `wrap_view()` and `BaseView`,
https://github.com/simonw/sqlite-utils/issues/554#issuecomment-1557607516,https://api.github.com/repos/simonw/sqlite-utils/issues/554,1557607516,IC_kwDOCGYnMM5c1zRc,1231935,xavdid,2023-05-22T17:18:33Z,2023-05-22T17:18:33Z,NONE,"Oh and for context - this goes away if I use `.upsert` instead of `insert(..., ignore=True)`, but I don't want to update the value if it's written, just do an insert if it's new. The code is basically:
```py
def save_items(table, items):
db[""users""].insert(build_user(items[0]), pk=""id"",ignore=True)
db[table].insert_all(items)
if comments := fetch_comments():
save_items('comments', comments)
if posts := fetch_posts():
save_items('posts', posts)
```
So either `comments` or `post` could create the relevant user if those items exist. In cases where they _both_ exist, I get this error. I need the `pk` because either call could create the table.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1720096994,"`IndexError` when doing `.insert(..., pk='id')` after `insert_all`",
https://github.com/simonw/datasette/pull/2077#issuecomment-1557289070,https://api.github.com/repos/simonw/datasette/issues/2077,1557289070,IC_kwDOBm6k_c5c0lhu,22429695,codecov[bot],2023-05-22T14:08:33Z,2023-06-29T14:40:35Z,NONE,"## [Codecov](https://app.codecov.io/gh/simonw/datasette/pull/2077?src=pr&el=h1&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison) Report
Patch and project coverage have no change.
> Comparison is base [(`ede6203`)](https://app.codecov.io/gh/simonw/datasette/commit/ede62036180993dbd9d4e5d280fc21c183cda1c3?el=desc&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison) 92.40% compared to head [(`9785c4f`)](https://app.codecov.io/gh/simonw/datasette/pull/2077?src=pr&el=desc&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison) 92.40%.
Additional details and impacted files
```diff
@@ Coverage Diff @@
## main #2077 +/- ##
=======================================
Coverage 92.40% 92.40%
=======================================
Files 39 39
Lines 5803 5803
=======================================
Hits 5362 5362
Misses 441 441
```
[:umbrella: View full report in Codecov by Sentry](https://app.codecov.io/gh/simonw/datasette/pull/2077?src=pr&el=continue&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison).
:loudspeaker: Do you have feedback about the report comment? [Let us know in this issue](https://about.codecov.io/codecov-pr-comment-feedback/?utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison).
","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1719759468,Bump furo from 2023.3.27 to 2023.5.20,
https://github.com/simonw/sqlite-utils/issues/552#issuecomment-1556292204,https://api.github.com/repos/simonw/sqlite-utils/issues/552,1556292204,IC_kwDOCGYnMM5cwyJs,9599,simonw,2023-05-21T21:05:15Z,2023-05-21T21:05:15Z,OWNER,Now live at https://sqlite-utils.datasette.io/en/latest/installation.html#setting-up-shell-completion,"{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1718612569,Document how to setup shell auto-completion,
https://github.com/simonw/sqlite-utils/issues/551#issuecomment-1556291915,https://api.github.com/repos/simonw/sqlite-utils/issues/551,1556291915,IC_kwDOCGYnMM5cwyFL,9599,simonw,2023-05-21T21:04:03Z,2023-05-21T21:04:03Z,OWNER,Now live at https://sqlite-utils.datasette.io/en/latest/cli.html,"{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1718607907,Make as many examples in the CLI docs as possible copy-and-pastable,
https://github.com/simonw/sqlite-utils/pull/553#issuecomment-1556288300,https://api.github.com/repos/simonw/sqlite-utils/issues/553,1556288300,IC_kwDOCGYnMM5cwxMs,9599,simonw,2023-05-21T20:48:01Z,2023-05-21T20:48:01Z,OWNER,If https://sqlite-utils--553.org.readthedocs.build/en/553/cli.html#running-sql-queries looks good I can merge this.,"{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1718635018,Reformatted CLI examples in docs,
https://github.com/simonw/sqlite-utils/issues/551#issuecomment-1556288270,https://api.github.com/repos/simonw/sqlite-utils/issues/551,1556288270,IC_kwDOCGYnMM5cwxMO,9599,simonw,2023-05-21T20:47:51Z,2023-05-21T20:47:51Z,OWNER,This page has all of the changes: https://sqlite-utils--553.org.readthedocs.build/en/553/cli.html#running-sql-queries,"{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1718607907,Make as many examples in the CLI docs as possible copy-and-pastable,
https://github.com/simonw/sqlite-utils/pull/553#issuecomment-1556287870,https://api.github.com/repos/simonw/sqlite-utils/issues/553,1556287870,IC_kwDOCGYnMM5cwxF-,22429695,codecov[bot],2023-05-21T20:45:58Z,2023-05-21T20:57:08Z,NONE,"## [Codecov](https://app.codecov.io/gh/simonw/sqlite-utils/pull/553?src=pr&el=h1&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison) Report
Patch and project coverage have no change.
> Comparison is base [(`e240133`)](https://app.codecov.io/gh/simonw/sqlite-utils/commit/e240133b11588d31dc22c632f7a7ca636c72978d?el=desc&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison) 96.36% compared to head [(`0b81794`)](https://app.codecov.io/gh/simonw/sqlite-utils/pull/553?src=pr&el=desc&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison) 96.36%.
> :exclamation: Current head 0b81794 differs from pull request most recent head 21036a5. Consider uploading reports for the commit 21036a5 to get more accurate results
Additional details and impacted files
```diff
@@ Coverage Diff @@
## main #553 +/- ##
=======================================
Coverage 96.36% 96.36%
=======================================
Files 6 6
Lines 2726 2726
=======================================
Hits 2627 2627
Misses 99 99
```
[:umbrella: View full report in Codecov by Sentry](https://app.codecov.io/gh/simonw/sqlite-utils/pull/553?src=pr&el=continue&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison).
:loudspeaker: Do you have feedback about the report comment? [Let us know in this issue](https://about.codecov.io/codecov-pr-comment-feedback/?utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison).
","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1718635018,Reformatted CLI examples in docs,
https://github.com/simonw/sqlite-utils/issues/551#issuecomment-1556287599,https://api.github.com/repos/simonw/sqlite-utils/issues/551,1556287599,IC_kwDOCGYnMM5cwxBv,9599,simonw,2023-05-21T20:44:55Z,2023-05-21T20:44:55Z,OWNER,"Put this in a PR so I can preview it:
- #553
","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1718607907,Make as many examples in the CLI docs as possible copy-and-pastable,
https://github.com/simonw/sqlite-utils/issues/545#issuecomment-1556269616,https://api.github.com/repos/simonw/sqlite-utils/issues/545,1556269616,IC_kwDOCGYnMM5cwsow,9599,simonw,2023-05-21T19:33:13Z,2023-05-21T19:33:13Z,OWNER,Now released: https://sqlite-utils.datasette.io/en/stable/changelog.html#v3-32,"{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1718517882,Try out Trogon for a tui interface,
https://github.com/simonw/sqlite-utils/issues/551#issuecomment-1556265772,https://api.github.com/repos/simonw/sqlite-utils/issues/551,1556265772,IC_kwDOCGYnMM5cwrss,9599,simonw,2023-05-21T19:16:15Z,2023-05-21T19:16:15Z,OWNER,"Another option:
That's using this markup:
```
Newline-delimited JSON
~~~~~~~~~~~~~~~~~~~~~~
Use ``--nl`` to get back newline-delimited JSON objects:
.. code-block:: bash
sqlite-utils dogs.db ""select * from dogs"" --nl
.. code-block:: output
{""id"": 1, ""age"": 4, ""name"": ""Cleo""}
{""id"": 2, ""age"": 2, ""name"": ""Pancakes""}
```
And this extra CSS:
```css
.highlight-output .highlight {
border-left: 9px solid #30c94f;
}
```","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1718607907,Make as many examples in the CLI docs as possible copy-and-pastable,
https://github.com/simonw/sqlite-utils/issues/551#issuecomment-1556263182,https://api.github.com/repos/simonw/sqlite-utils/issues/551,1556263182,IC_kwDOCGYnMM5cwrEO,9599,simonw,2023-05-21T19:06:48Z,2023-05-21T19:06:48Z,OWNER,"I could split them up into two blocks like this:
I do miss the visual indication that one of these is the command and one is the output though.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1718607907,Make as many examples in the CLI docs as possible copy-and-pastable,
https://github.com/simonw/sqlite-utils/issues/551#issuecomment-1556262574,https://api.github.com/repos/simonw/sqlite-utils/issues/551,1556262574,IC_kwDOCGYnMM5cwq6u,9599,simonw,2023-05-21T19:04:59Z,2023-05-21T19:04:59Z,OWNER,"I wrote the docs like this because early examples include both the command and its output:
https://sqlite-utils.datasette.io/en/stable/cli.html#returning-json
","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1718607907,Make as many examples in the CLI docs as possible copy-and-pastable,
https://github.com/simonw/sqlite-utils/issues/550#issuecomment-1556255309,https://api.github.com/repos/simonw/sqlite-utils/issues/550,1556255309,IC_kwDOCGYnMM5cwpJN,9599,simonw,2023-05-21T18:42:25Z,2023-05-21T18:42:25Z,OWNER,Tests passed here: https://github.com/simonw/sqlite-utils/actions/runs/5039119716,"{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1718595700,AttributeError: 'EntryPoints' object has no attribute 'get' for flake8 on Python 3.7,
https://github.com/simonw/sqlite-utils/issues/550#issuecomment-1556250236,https://api.github.com/repos/simonw/sqlite-utils/issues/550,1556250236,IC_kwDOCGYnMM5cwn58,9599,simonw,2023-05-21T18:25:26Z,2023-05-21T18:25:26Z,OWNER,"Relevant issues:
- https://github.com/python/importlib_metadata/issues/406
- https://github.com/PyCQA/flake8/issues/1701
It looks to me like this is only a problem for `flake8` on Python 3.7 - 3.8 and higher work OK.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1718595700,AttributeError: 'EntryPoints' object has no attribute 'get' for flake8 on Python 3.7,
https://github.com/simonw/sqlite-utils/issues/550#issuecomment-1556249984,https://api.github.com/repos/simonw/sqlite-utils/issues/550,1556249984,IC_kwDOCGYnMM5cwn2A,9599,simonw,2023-05-21T18:24:48Z,2023-05-21T18:24:48Z,OWNER,"This is blocking:
- #549","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1718595700,AttributeError: 'EntryPoints' object has no attribute 'get' for flake8 on Python 3.7,
https://github.com/simonw/sqlite-utils/issues/545#issuecomment-1556247818,https://api.github.com/repos/simonw/sqlite-utils/issues/545,1556247818,IC_kwDOCGYnMM5cwnUK,9599,simonw,2023-05-21T18:17:46Z,2023-05-21T18:17:46Z,OWNER,Draft documentation: https://sqlite-utils--549.org.readthedocs.build/en/549/cli.html#cli-tui,"{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1718517882,Try out Trogon for a tui interface,
https://github.com/simonw/sqlite-utils/pull/549#issuecomment-1556242262,https://api.github.com/repos/simonw/sqlite-utils/issues/549,1556242262,IC_kwDOCGYnMM5cwl9W,9599,simonw,2023-05-21T18:00:05Z,2023-05-21T18:00:05Z,OWNER,"Failing `mypy` test: https://github.com/simonw/sqlite-utils/actions/runs/5038983349/jobs/9036828465
```
sqlite_utils/cli.py:37: error: Skipping analyzing ""trogon"": module is installed, but missing library stubs or py.typed marker [import]
sqlite_utils/cli.py:37: note: See https://mypy.readthedocs.io/en/stable/running_mypy.html#missing-imports
Found 1 error in 1 file (checked 52 source files)
```","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1718586377,TUI powered by Trogon,
https://github.com/simonw/sqlite-utils/pull/549#issuecomment-1556241812,https://api.github.com/repos/simonw/sqlite-utils/issues/549,1556241812,IC_kwDOCGYnMM5cwl2U,9599,simonw,2023-05-21T17:58:25Z,2023-05-21T17:58:25Z,OWNER,Documentation: https://sqlite-utils--549.org.readthedocs.build/en/549/cli.html#cli-tui,"{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1718586377,TUI powered by Trogon,
https://github.com/simonw/sqlite-utils/pull/549#issuecomment-1556241555,https://api.github.com/repos/simonw/sqlite-utils/issues/549,1556241555,IC_kwDOCGYnMM5cwlyT,22429695,codecov[bot],2023-05-21T17:57:24Z,2023-05-21T18:28:44Z,NONE,"## [Codecov](https://app.codecov.io/gh/simonw/sqlite-utils/pull/549?src=pr&el=h1&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison) Report
Patch coverage: **`83.33`**% and project coverage change: **`+0.06`** :tada:
> Comparison is base [(`b3b100d`)](https://app.codecov.io/gh/simonw/sqlite-utils/commit/b3b100d7f5b2a76ccd4bfe8b0301a29e321d0375?el=desc&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison) 96.30% compared to head [(`948692a`)](https://app.codecov.io/gh/simonw/sqlite-utils/pull/549?src=pr&el=desc&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison) 96.36%.
Additional details and impacted files
```diff
@@ Coverage Diff @@
## main #549 +/- ##
==========================================
+ Coverage 96.30% 96.36% +0.06%
==========================================
Files 6 6
Lines 2707 2726 +19
==========================================
+ Hits 2607 2627 +20
+ Misses 100 99 -1
```
| [Impacted Files](https://app.codecov.io/gh/simonw/sqlite-utils/pull/549?src=pr&el=tree&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison) | Coverage Δ | |
|---|---|---|
| [sqlite\_utils/cli.py](https://app.codecov.io/gh/simonw/sqlite-utils/pull/549?src=pr&el=tree&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison#diff-c3FsaXRlX3V0aWxzL2NsaS5weQ==) | `95.22% <83.33%> (-0.03%)` | :arrow_down: |
... and [1 file with indirect coverage changes](https://app.codecov.io/gh/simonw/sqlite-utils/pull/549/indirect-changes?src=pr&el=tree-more&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison)
[:umbrella: View full report in Codecov by Sentry](https://app.codecov.io/gh/simonw/sqlite-utils/pull/549?src=pr&el=continue&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison).
:loudspeaker: Do you have feedback about the report comment? [Let us know in this issue](https://about.codecov.io/codecov-pr-comment-feedback/?utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison).
","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1718586377,TUI powered by Trogon,
https://github.com/simonw/sqlite-utils/issues/548#issuecomment-1556231832,https://api.github.com/repos/simonw/sqlite-utils/issues/548,1556231832,IC_kwDOCGYnMM5cwjaY,9599,simonw,2023-05-21T17:24:13Z,2023-05-21T17:24:13Z,OWNER,"Oh, I see why that is now:
https://github.com/simonw/sqlite-utils/blob/6027f3ea6939a399aeef2578fca17efec0e539df/sqlite_utils/cli.py#L2670-L2679
This is because of the following command:
sqlite-utils analyze-tables table1 table2 --column x
Since you can pass multiple tables AND multiple columns, the tool currently assumes that the column(s) you specify may be available on a subset of the provided tables.
I'm going to change this so if the column is not on ANY of those tables you get an error.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1718576761,analyze-tables should validate provide --column names,
https://github.com/simonw/sqlite-utils/issues/547#issuecomment-1556228395,https://api.github.com/repos/simonw/sqlite-utils/issues/547,1556228395,IC_kwDOCGYnMM5cwikr,9599,simonw,2023-05-21T17:11:15Z,2023-05-21T17:11:15Z,OWNER,"This will be a cosmetic change to the CLI output only - the options to save data to the database and the Python API function will continue to return `[(None, 158)]`.
I can add an optimization though to avoid running the SQL count query if we know that it's all `null`.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1718572201,No need to show common values if everything is null,
https://github.com/simonw/sqlite-utils/issues/544#issuecomment-1556225788,https://api.github.com/repos/simonw/sqlite-utils/issues/544,1556225788,IC_kwDOCGYnMM5cwh78,9599,simonw,2023-05-21T17:02:05Z,2023-05-21T17:02:05Z,OWNER,"New docs:
- https://sqlite-utils.datasette.io/en/latest/cli.html#cli-analyze-tables
- https://sqlite-utils.datasette.io/en/latest/cli-reference.html#analyze-tables
- https://sqlite-utils.datasette.io/en/latest/python-api.html#analyzing-a-column
- https://sqlite-utils.datasette.io/en/latest/reference.html#sqlite_utils.db.Table.analyze_column
New help output:
```
% sqlite-utils analyze-tables --help
Usage: sqlite-utils analyze-tables [OPTIONS] PATH [TABLES]...
Analyze the columns in one or more tables
Example:
sqlite-utils analyze-tables data.db trees
Options:
-c, --column TEXT Specific columns to analyze
--save Save results to _analyze_tables table
--common-limit INTEGER How many common values
--no-most Skip most common values
--no-least Skip least common values
--load-extension TEXT Path to SQLite extension, with optional :entrypoint
-h, --help Show this message and exit.
```","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1718515590,New options for analyze-tables --common-limit --no-most and --no-least,
https://github.com/simonw/sqlite-utils/pull/546#issuecomment-1556213396,https://api.github.com/repos/simonw/sqlite-utils/issues/546,1556213396,IC_kwDOCGYnMM5cwe6U,9599,simonw,2023-05-21T15:58:12Z,2023-05-21T16:18:46Z,OWNER,"Documentation preview:
- https://sqlite-utils--546.org.readthedocs.build/en/546/cli.html#cli-analyze-tables
- https://sqlite-utils--546.org.readthedocs.build/en/546/cli-reference.html#analyze-tables
- https://sqlite-utils--546.org.readthedocs.build/en/546/python-api.html#analyzing-a-column
- https://sqlite-utils--546.org.readthedocs.build/en/546/reference.html#sqlite_utils.db.Table.analyze_column","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1718550688,"Analyze tables options: --common-limit, --no-most, --no-least",
https://github.com/simonw/sqlite-utils/pull/546#issuecomment-1556213031,https://api.github.com/repos/simonw/sqlite-utils/issues/546,1556213031,IC_kwDOCGYnMM5cwe0n,22429695,codecov[bot],2023-05-21T15:56:05Z,2023-05-21T16:18:03Z,NONE,"## [Codecov](https://app.codecov.io/gh/simonw/sqlite-utils/pull/546?src=pr&el=h1&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison) Report
Patch coverage: **`93.75`**% and no project coverage change.
> Comparison is base [(`b3b100d`)](https://app.codecov.io/gh/simonw/sqlite-utils/commit/b3b100d7f5b2a76ccd4bfe8b0301a29e321d0375?el=desc&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison) 96.30% compared to head [(`9f23e68`)](https://app.codecov.io/gh/simonw/sqlite-utils/pull/546?src=pr&el=desc&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison) 96.31%.
> :exclamation: Current head 9f23e68 differs from pull request most recent head 2eca17d. Consider uploading reports for the commit 2eca17d to get more accurate results
Additional details and impacted files
```diff
@@ Coverage Diff @@
## main #546 +/- ##
=======================================
Coverage 96.30% 96.31%
=======================================
Files 6 6
Lines 2707 2712 +5
=======================================
+ Hits 2607 2612 +5
Misses 100 100
```
| [Impacted Files](https://app.codecov.io/gh/simonw/sqlite-utils/pull/546?src=pr&el=tree&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison) | Coverage Δ | |
|---|---|---|
| [sqlite\_utils/db.py](https://app.codecov.io/gh/simonw/sqlite-utils/pull/546?src=pr&el=tree&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison#diff-c3FsaXRlX3V0aWxzL2RiLnB5) | `97.37% <90.90%> (+<0.01%)` | :arrow_up: |
| [sqlite\_utils/cli.py](https://app.codecov.io/gh/simonw/sqlite-utils/pull/546?src=pr&el=tree&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison#diff-c3FsaXRlX3V0aWxzL2NsaS5weQ==) | `95.26% <100.00%> (+0.01%)` | :arrow_up: |
[:umbrella: View full report in Codecov by Sentry](https://app.codecov.io/gh/simonw/sqlite-utils/pull/546?src=pr&el=continue&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison).
:loudspeaker: Do you have feedback about the report comment? [Let us know in this issue](https://about.codecov.io/codecov-pr-comment-feedback/?utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison).
","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1718550688,"Analyze tables options: --common-limit, --no-most, --no-least",
https://github.com/simonw/sqlite-utils/issues/544#issuecomment-1556211643,https://api.github.com/repos/simonw/sqlite-utils/issues/544,1556211643,IC_kwDOCGYnMM5cwee7,9599,simonw,2023-05-21T15:48:17Z,2023-05-21T15:48:17Z,OWNER,I generated the commit message in https://github.com/simonw/sqlite-utils/commit/1c1991b447a1ddd3d61d9d4a8a1d6a9da47ced20 using `git diff | llm --system 'describe this change'`.,"{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1718515590,New options for analyze-tables --common-limit --no-most and --no-least,
https://github.com/simonw/sqlite-utils/issues/545#issuecomment-1556210844,https://api.github.com/repos/simonw/sqlite-utils/issues/545,1556210844,IC_kwDOCGYnMM5cweSc,9599,simonw,2023-05-21T15:44:10Z,2023-05-21T15:44:10Z,OWNER,"It looks like `nargs=-1` on a positional argument isn't yet supported - opened an issue here:
- https://github.com/Textualize/trogon/issues/4","{""total_count"": 1, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 1, ""rocket"": 0, ""eyes"": 0}",1718517882,Try out Trogon for a tui interface,
https://github.com/simonw/sqlite-utils/issues/545#issuecomment-1556191894,https://api.github.com/repos/simonw/sqlite-utils/issues/545,1556191894,IC_kwDOCGYnMM5cwZqW,9599,simonw,2023-05-21T14:20:14Z,2023-05-21T14:20:14Z,OWNER,"Opened a feature request for customizing the help and command name:
- https://github.com/Textualize/trogon/issues/2","{""total_count"": 2, ""+1"": 1, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 1, ""rocket"": 0, ""eyes"": 0}",1718517882,Try out Trogon for a tui interface,
https://github.com/simonw/sqlite-utils/issues/545#issuecomment-1556190531,https://api.github.com/repos/simonw/sqlite-utils/issues/545,1556190531,IC_kwDOCGYnMM5cwZVD,9599,simonw,2023-05-21T14:13:43Z,2023-05-21T14:13:43Z,OWNER,"OK, this works!
![trogon](https://github.com/simonw/sqlite-utils/assets/9599/2ae194c5-ec82-471a-9d1b-b01b3f2632f3)
To try it out, install that branch from GitHub:
pip install https://github.com/simonw/sqlite-utils/archive/refs/heads/trogon.zip
Then run this:
sqlite-utils install trogon
And this:
sqlite-utils tui
","{""total_count"": 5, ""+1"": 2, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 3, ""eyes"": 0}",1718517882,Try out Trogon for a tui interface,
https://github.com/simonw/sqlite-utils/issues/545#issuecomment-1556189823,https://api.github.com/repos/simonw/sqlite-utils/issues/545,1556189823,IC_kwDOCGYnMM5cwZJ_,9599,simonw,2023-05-21T14:09:59Z,2023-05-21T14:09:59Z,OWNER,"I don't want to add `trogon` as a default dependency because it's a little heavy - it pulls in all of Rich and Textual as well. People who use `sqlite-utils` just for its Python API won't benefit from this - it's a CLI feature only.
But I have a `sqlite-utils install ...` command for helping people to install packages into the same virtual environment as `sqlite-utils` no matter how they installed that tool: https://sqlite-utils.datasette.io/en/stable/cli.html#cli-install
So I can treat Trogon as an optional dependency and add the `sqlite-utils tui` command only if that package is also installed.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1718517882,Try out Trogon for a tui interface,
https://github.com/simonw/sqlite-utils/issues/399#issuecomment-1548913065,https://api.github.com/repos/simonw/sqlite-utils/issues/399,1548913065,IC_kwDOCGYnMM5cUomp,433780,chrislkeller,2023-05-16T03:11:03Z,2023-05-16T03:11:52Z,NONE,"Using this thread and some [other resources](https://sqlite-utils.datasette.io/en/stable/cli.html#spatialite-helpers) I managed to cobble together a couple of sqlite-utils lines to add a geometry column for a table that already has a lat/lng column.
```
# add a geometry column
sqlite-utils add-geometry-column [db name] [table name] geometry --type POINT --srid 4326
# add a point for each row to geometry column
sqlite-utils --load-extension=spatialite [db name] 'update [table name] SET Geometry=MakePoint(longitude, latitude, 4326);'
```","{""total_count"": 1, ""+1"": 1, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1124731464,"Make it easier to insert geometries, with documentation and maybe code",
https://github.com/simonw/datasette/pull/2052#issuecomment-1548617257,https://api.github.com/repos/simonw/datasette/issues/2052,1548617257,IC_kwDOBm6k_c5cTgYp,193185,cldellow,2023-05-15T21:32:20Z,2023-05-15T21:32:20Z,CONTRIBUTOR,"> Were you picturing that the whole plugin config object could be returned as a promise, or that the individual hooks (like makeColumnActions or makeAboveTablePanelConfigs supported returning a promise of arrays instead only returning plain arrays?
The latter - that you could return a promise of arrays, so it parallels the [""await me maybe"" pattern in Datasette](https://simonwillison.net/2020/Sep/2/await-me-maybe/), where you can return either a value, a callable or an awaitable.
> I have a hunch that what you're describing might be achievable without adding Promises to the API with something
Oops, I did a poor job explaining. Yes, this would work - but it requires me to continue to communicate the column names out of band (in order to fetch the facet data per-column before registering my plugin), vs being able to re-use them from the plugin implementation.
This isn't that big of a deal - it'd be a nice ergonomic improvement, but nowhere near as a big of an improvement as having an officially sanctioned way to add stuff to the column menus in the first place.
This could also be layered on in a future commit without breaking v1 users, too, so it's not at all urgent.
> especially if those lines are encapsulated by a function we provide (maybe something that's available on the window provided by Datasette as an inline script tag
Ah, this is maybe the the key point. Since it's all hosted inside Datasette, Datasette can provide some arbitrary sugar to make it easier to work with.
My experience with async scripts in JS is that people sometimes don't understand the race conditions inherent to them. If they copy/paste from a tutorial, it does just work. But then they'll delete half the code, and by chance it still works on their machine/Datasette templates, and now someone's headed for an annoying debugging session -- maybe them, maybe someone else who tries to re-use their plugin.
Again, a fairly minor thing, though.","{""total_count"": 1, ""+1"": 1, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1651082214,"feat: Javascript Plugin API (Custom panels, column menu items with JS actions)",
https://github.com/simonw/datasette/pull/2075#issuecomment-1547944971,https://api.github.com/repos/simonw/datasette/issues/2075,1547944971,IC_kwDOBm6k_c5cQ8QL,22429695,codecov[bot],2023-05-15T14:12:20Z,2023-05-15T14:12:20Z,NONE,"## [Codecov](https://app.codecov.io/gh/simonw/datasette/pull/2075?src=pr&el=h1&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison) Report
Patch and project coverage have no change.
> Comparison is base [(`49184c5`)](https://app.codecov.io/gh/simonw/datasette/commit/49184c569cd70efbda4f3f062afef3a34401d8d5?el=desc&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison) 92.40% compared to head [(`b99e1d3`)](https://app.codecov.io/gh/simonw/datasette/pull/2075?src=pr&el=desc&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison) 92.40%.
Additional details and impacted files
```diff
@@ Coverage Diff @@
## main #2075 +/- ##
=======================================
Coverage 92.40% 92.40%
=======================================
Files 38 38
Lines 5751 5751
=======================================
Hits 5314 5314
Misses 437 437
```
[:umbrella: View full report in Codecov by Sentry](https://app.codecov.io/gh/simonw/datasette/pull/2075?src=pr&el=continue&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison).
:loudspeaker: Do you have feedback about the report comment? [Let us know in this issue](https://about.codecov.io/codecov-pr-comment-feedback/?utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison).
","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1710164693,Bump sphinx from 6.1.3 to 7.0.1,
https://github.com/simonw/datasette/pull/2068#issuecomment-1547911570,https://api.github.com/repos/simonw/datasette/issues/2068,1547911570,IC_kwDOBm6k_c5cQ0GS,49699333,dependabot[bot],2023-05-15T13:59:35Z,2023-05-15T13:59:35Z,CONTRIBUTOR,Superseded by #2075.,"{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1690842199,Bump sphinx from 6.1.3 to 7.0.0,
https://github.com/simonw/datasette/pull/2052#issuecomment-1546362374,https://api.github.com/repos/simonw/datasette/issues/2052,1546362374,IC_kwDOBm6k_c5cK54G,9020979,hydrosquall,2023-05-12T22:09:03Z,2023-05-12T22:09:03Z,NONE,"Hey @cldellow , thanks for the thoughtful feedback and describing the ""lazy facets"" feature!
It sounds like the [postTask](https://developer.mozilla.org/en-US/docs/Web/API/Scheduler/postTask) API might be relevant for the types of network request scheduling you have in mind.
Addressing your points inline below:
> It might also be nice if the plugins could return Promises.
Were you picturing that the whole plugin config object could be returned as a promise, or that the individual hooks (like `makeColumnActions` or `makeAboveTablePanelConfigs` supported returning a promise of arrays instead only returning plain arrays?
I think what you're describing can be achievable, but I want to make sure I do so in a way that addresses your need / keeps the complexity of the plugin core system at a level this is approachable .
I have a hunch that what you're describing might be achievable without adding Promises to the API with something like
```
fetch('/api/with-custom-facets').then(myFacets => {
// reusing the go() idiom
go(manager, myFacets);
})
```
but I'd like to confirm if that's the case before investigating adding support.
> bulletproof plugin registration code that is robust against the order in which the script tags load
Yes, I think what you wrote looks right to me! While it looks a little bit verbose compared to the second example, I'm hoping we can mitigate the cost of that during this API incubation phase by making it an easy-to-copy paste code snippet.
I haven't heard of the GA queing pattern before, thanks for the example. I won't have time to implement of proof of concept in the next few weeks, but I took some time to think through the pros/cons to decide whether we may want to add this in a future release:
I can see that this approach brings advantages
- Plugin developers don't need to know the name of the datasette initialization event to start their plugin
- Pushing a function to an array probably is easier (definitely more concise) than adding a document event listener
- One less event listener sitting in memory
It also has some minor costs
- A malicious plugin could choose to (or accidentally) mess with the order of the queue if multiple scripts are lined up
- Some risk in encouraging people to mutate global state
- (not a cost, more a moot point): changing this API may not make a meaningful difference if we're discussing whether people enter 2 vs 5 lines of code, especially if those lines are encapsulated by a function we provide (maybe something that's available on the `window` provided by Datasette as an inline script tag).
","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1651082214,"feat: Javascript Plugin API (Custom panels, column menu items with JS actions)",
https://github.com/simonw/datasette/issues/2073#issuecomment-1546119773,https://api.github.com/repos/simonw/datasette/issues/2073,1546119773,IC_kwDOBm6k_c5cJ-pd,9599,simonw,2023-05-12T18:24:07Z,2023-05-12T18:24:07Z,OWNER,"Here's a demo of this breaking in Datasette Lite:
https://lite.datasette.io/?sql=https://gist.github.com/simonw/261564c0ca01567df6eeb9b222b8be84&json=https%3A%2F%2Fcdn.jsdelivr.net%2Fnpm%2Fweb-features%2Findex.json#/data/baseline?_filter_column_1=is_baseline&_filter_op_1=exact&_filter_value_1=1&_filter_column_2=&_filter_op_2=notnull__1&_filter_value_2=1&_filter_column=&_filter_op=exact&_filter_value=&_sort=&_facet=is_baseline
Here's a SQL query that demonstrates the underlying issue:
```sql
select 'working', count(*) from baseline where is_baseline = 1
union all
select 'broken', count(*) from baseline where is_baseline = '1'
```
https://lite.datasette.io/?sql=https://gist.github.com/simonw/261564c0ca01567df6eeb9b222b8be84&json=https%3A%2F%2Fcdn.jsdelivr.net%2Fnpm%2Fweb-features%2Findex.json#/data?sql=select+%27working%27%2C+count%28*%29+from+baseline+where+is_baseline+%3D+1%0Aunion+all%0Aselect+%27broken%27%2C+count%28*%29+from+baseline+where+is_baseline+%3D+%271%27
","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1708030220,Faceting doesn't work against integer columns in views,
https://github.com/simonw/datasette/issues/2073#issuecomment-1546117538,https://api.github.com/repos/simonw/datasette/issues/2073,1546117538,IC_kwDOBm6k_c5cJ-Gi,9599,simonw,2023-05-12T18:21:38Z,2023-05-12T18:21:38Z,OWNER,"https://latest.datasette.io/fixtures doesn't currently have a view with any integer columns in it, making this bug harder to demonstrate there.
I can't replicate the bug using https://datasette.io/content/plugins?_facet=stargazers_count&stargazers_count=3 - I would expect that not to work correctly.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1708030220,Faceting doesn't work against integer columns in views,
https://github.com/simonw/sqlite-utils/issues/527#issuecomment-1540900733,https://api.github.com/repos/simonw/sqlite-utils/issues/527,1540900733,IC_kwDOCGYnMM5b2Ed9,167893,mcarpenter,2023-05-09T21:15:05Z,2023-05-09T21:15:05Z,CONTRIBUTOR,"Sorry, I completely missed your first comment whilst on Easter break.
This looks like a good practical compromise before v4. Thanks!","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1578790070,`Table.convert()` skips falsey values,
https://github.com/simonw/datasette/issues/2070#issuecomment-1540494121,https://api.github.com/repos/simonw/datasette/issues/2070,1540494121,IC_kwDOBm6k_c5b0hMp,9599,simonw,2023-05-09T16:25:00Z,2023-05-09T16:25:00Z,OWNER,Can now be used here: https://github.com/simonw/datasette/actions/workflows/deploy-branch-preview.yml,"{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1702354223,Mechanism for deploying a preview of a branch using Vercel,
https://github.com/simonw/datasette/issues/2070#issuecomment-1540491751,https://api.github.com/repos/simonw/datasette/issues/2070,1540491751,IC_kwDOBm6k_c5b0gnn,9599,simonw,2023-05-09T16:23:12Z,2023-05-09T16:23:12Z,OWNER,Added a actions `BRANCH_PREVIEW_VERCEL_TOKEN` secret to this repository.,"{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1702354223,Mechanism for deploying a preview of a branch using Vercel,
https://github.com/simonw/sqlite-utils/pull/537#issuecomment-1539157643,https://api.github.com/repos/simonw/sqlite-utils/issues/537,1539157643,IC_kwDOCGYnMM5bva6L,9599,simonw,2023-05-08T22:45:09Z,2023-05-08T22:45:21Z,OWNER,"Here's an example from the new tests:
https://github.com/simonw/sqlite-utils/blob/a75abeb61b91a28650d3b9933e7ec80ad0d92529/tests/test_create.py#L291-L307","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1665200812,Support self-referencing FKs in `Table.create`,
https://github.com/simonw/sqlite-utils/issues/448#issuecomment-1539109816,https://api.github.com/repos/simonw/sqlite-utils/issues/448,1539109816,IC_kwDOCGYnMM5bvPO4,9599,simonw,2023-05-08T22:01:00Z,2023-05-08T22:01:00Z,OWNER,"This is being handled in:
- #520","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1279144769,Reading rows from a file => AttributeError: '_io.StringIO' object has no attribute 'readinto',
https://github.com/simonw/sqlite-utils/issues/520#issuecomment-1539109587,https://api.github.com/repos/simonw/sqlite-utils/issues/520,1539109587,IC_kwDOCGYnMM5bvPLT,9599,simonw,2023-05-08T22:00:46Z,2023-05-08T22:00:46Z,OWNER,"> Hey, isn't this essentially the same issue as #448 ?
Yes it is, good catch!","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1516644980,rows_from_file() raises confusing error if file-like object is not in binary mode,
https://github.com/simonw/sqlite-utils/issues/525#issuecomment-1539108140,https://api.github.com/repos/simonw/sqlite-utils/issues/525,1539108140,IC_kwDOCGYnMM5bvO0s,9599,simonw,2023-05-08T21:59:41Z,2023-05-08T21:59:41Z,OWNER,That original example passes against `main` now.,"{""total_count"": 1, ""+1"": 1, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1575131737,Repeated calls to `Table.convert()` fail,
https://github.com/simonw/sqlite-utils/issues/525#issuecomment-1539101853,https://api.github.com/repos/simonw/sqlite-utils/issues/525,1539101853,IC_kwDOCGYnMM5bvNSd,9599,simonw,2023-05-08T21:52:44Z,2023-05-08T21:52:44Z,OWNER,I like the `lambda-{uuid}` idea.,"{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1575131737,Repeated calls to `Table.convert()` fail,
https://github.com/simonw/sqlite-utils/issues/514#issuecomment-1539100300,https://api.github.com/repos/simonw/sqlite-utils/issues/514,1539100300,IC_kwDOCGYnMM5bvM6M,9599,simonw,2023-05-08T21:50:51Z,2023-05-08T21:50:51Z,OWNER,Seeing as `sqlite-utils` doesn't currently provide mechanisms for adding `check` constraints like this I'm going to leave this - I'm happy with the fix I put in for the `not null` constraints.,"{""total_count"": 1, ""+1"": 1, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1465194249,upsert of new row with check constraints fails,
https://github.com/simonw/sqlite-utils/issues/514#issuecomment-1539099703,https://api.github.com/repos/simonw/sqlite-utils/issues/514,1539099703,IC_kwDOCGYnMM5bvMw3,9599,simonw,2023-05-08T21:50:06Z,2023-05-08T21:50:06Z,OWNER,"Applying the fix from the PR here doesn't fix the above problem either:
- https://github.com/simonw/sqlite-utils/pull/515
So it looks like these kinds of `check` constraints currently aren't compatible with how `upsert()` works.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1465194249,upsert of new row with check constraints fails,
https://github.com/simonw/sqlite-utils/issues/514#issuecomment-1539094287,https://api.github.com/repos/simonw/sqlite-utils/issues/514,1539094287,IC_kwDOCGYnMM5bvLcP,9599,simonw,2023-05-08T21:44:11Z,2023-05-08T21:44:11Z,OWNER,"OK, this fails silently:
```python
import sqlite_utils
db = sqlite_utils.Database(memory=True)
db.execute('''CREATE TABLE employees (
id INTEGER PRIMARY KEY,
name TEXT,
age INTEGER,
salary REAL,
CHECK (salary is not null and salary > 0)
);''')
db[""employees""].upsert({""id"": 1, ""name"": ""Bob""}, pk=""id"")
list(db[""employees""].rows)
````
It outputs:
```python
[]
```","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1465194249,upsert of new row with check constraints fails,
https://github.com/simonw/sqlite-utils/issues/514#issuecomment-1539079507,https://api.github.com/repos/simonw/sqlite-utils/issues/514,1539079507,IC_kwDOCGYnMM5bvH1T,9599,simonw,2023-05-08T21:28:37Z,2023-05-08T21:28:37Z,OWNER,"> This means that a table with NON NULL (or other constraint) columns that aren't part of the pkey can't have new rows upserted.
Huh... on that basis, it's possible my fix in https://github.com/simonw/sqlite-utils/commit/2376c452a56b0c3e75e7ca698273434e32945304 is incomplete. I only covered the 'not null' case.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1465194249,upsert of new row with check constraints fails,
https://github.com/simonw/sqlite-utils/issues/514#issuecomment-1539078429,https://api.github.com/repos/simonw/sqlite-utils/issues/514,1539078429,IC_kwDOCGYnMM5bvHkd,9599,simonw,2023-05-08T21:27:40Z,2023-05-08T21:27:40Z,OWNER,"Dupe of:
- #538","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1465194249,upsert of new row with check constraints fails,
https://github.com/simonw/sqlite-utils/pull/515#issuecomment-1539077777,https://api.github.com/repos/simonw/sqlite-utils/issues/515,1539077777,IC_kwDOCGYnMM5bvHaR,9599,simonw,2023-05-08T21:27:10Z,2023-05-08T21:27:10Z,OWNER,I should have spotted this PR before I shipped my own fix! https://github.com/simonw/sqlite-utils/commit/2376c452a56b0c3e75e7ca698273434e32945304,"{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1465194930,"upsert new rows with constraints, fixes #514",
https://github.com/simonw/sqlite-utils/pull/519#issuecomment-1539058795,https://api.github.com/repos/simonw/sqlite-utils/issues/519,1539058795,IC_kwDOCGYnMM5bvCxr,9599,simonw,2023-05-08T21:12:52Z,2023-05-08T21:12:52Z,OWNER,"This is a really neat fix, thank you.","{""total_count"": 1, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 1, ""rocket"": 0, ""eyes"": 0}",1505568103,Fixes breaking DEFAULT values,
https://github.com/simonw/sqlite-utils/pull/537#issuecomment-1539055393,https://api.github.com/repos/simonw/sqlite-utils/issues/537,1539055393,IC_kwDOCGYnMM5bvB8h,9599,simonw,2023-05-08T21:10:06Z,2023-05-08T21:10:06Z,OWNER,Thanks!,"{""total_count"": 1, ""+1"": 1, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1665200812,Support self-referencing FKs in `Table.create`,
https://github.com/simonw/sqlite-utils/pull/528#issuecomment-1539053230,https://api.github.com/repos/simonw/sqlite-utils/issues/528,1539053230,IC_kwDOCGYnMM5bvBau,9599,simonw,2023-05-08T21:08:23Z,2023-05-08T21:08:23Z,OWNER,"I fixed this in:
- #527
Will fully remove this misfeature in:
- #542","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1578793661,Enable `Table.convert()` on falsey values,
https://github.com/simonw/sqlite-utils/issues/542#issuecomment-1539052467,https://api.github.com/repos/simonw/sqlite-utils/issues/542,1539052467,IC_kwDOCGYnMM5bvBOz,9599,simonw,2023-05-08T21:07:41Z,2023-05-08T21:07:41Z,OWNER,"Relevant commits (will mostly revert these):
- https://github.com/simonw/sqlite-utils/commit/455c35b512895c19bf922c2b804d750d27cb8dbd
- https://github.com/simonw/sqlite-utils/commit/e0ec4c345129996011951e400388fd74865f65a2","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1700936245,Remove `skip_false=True` and `--no-skip-false` in `sqlite-utils` 4.0,
https://github.com/simonw/sqlite-utils/issues/527#issuecomment-1539051724,https://api.github.com/repos/simonw/sqlite-utils/issues/527,1539051724,IC_kwDOCGYnMM5bvBDM,9599,simonw,2023-05-08T21:07:04Z,2023-05-08T21:07:04Z,OWNER,"Updated documentation:
- https://sqlite-utils.datasette.io/en/latest/python-api.html#converting-data-in-columns
- https://sqlite-utils.datasette.io/en/latest/cli.html#converting-data-in-columns
- https://sqlite-utils.datasette.io/en/latest/cli-reference.html#convert","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1578790070,`Table.convert()` skips falsey values,
https://github.com/simonw/sqlite-utils/issues/527#issuecomment-1539035838,https://api.github.com/repos/simonw/sqlite-utils/issues/527,1539035838,IC_kwDOCGYnMM5bu9K-,9599,simonw,2023-05-08T20:55:00Z,2023-05-08T20:55:00Z,OWNER,"I'm going to go with `--no-skip-false` as the CLI option. It's ugly, but this whole thing is ugly. I'm going to make a note to remove this misfeature in `sqlite-utils` 4.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1578790070,`Table.convert()` skips falsey values,
https://github.com/simonw/sqlite-utils/issues/527#issuecomment-1539033736,https://api.github.com/repos/simonw/sqlite-utils/issues/527,1539033736,IC_kwDOCGYnMM5bu8qI,9599,simonw,2023-05-08T20:52:51Z,2023-05-08T20:52:51Z,OWNER,"OK, I implemented that at the Python API level. I need to decide how it should work for the `sqlite-utils convert` command too: https://sqlite-utils.datasette.io/en/stable/cli-reference.html#convert","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1578790070,`Table.convert()` skips falsey values,
https://github.com/simonw/sqlite-utils/issues/530#issuecomment-1539018912,https://api.github.com/repos/simonw/sqlite-utils/issues/530,1539018912,IC_kwDOCGYnMM5bu5Cg,9599,simonw,2023-05-08T20:39:00Z,2023-05-08T20:39:00Z,OWNER,"I think the natural place to add these in the Python library API would be https://sqlite-utils.datasette.io/en/stable/python-api.html#adding-foreign-key-constraints - maybe something like this:
```python
db[""books""].add_foreign_key(""author_id"", ""authors"", ""id"", on_delete=RESTRICT)
```
Then for the CLI tool could be added to https://sqlite-utils.datasette.io/en/stable/cli-reference.html#add-foreign-key
```
sqlite-utils add-foreign-key my.db books author_id authors id --on-update SET_NULL
```
I wouldn't support these for the other methods of adding foreign keys - `foreign_keys(...)` for the various `.insert()` etc methods and the `add_foreign_keys(...)` bulk menthod.","{""total_count"": 1, ""+1"": 0, ""-1"": 0, ""laugh"": 1, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1595340692,"add ability to configure ""on delete"" and ""on update"" attributes of foreign keys:",
https://github.com/simonw/sqlite-utils/issues/530#issuecomment-1539015064,https://api.github.com/repos/simonw/sqlite-utils/issues/530,1539015064,IC_kwDOCGYnMM5bu4GY,9599,simonw,2023-05-08T20:35:07Z,2023-05-08T20:35:07Z,OWNER,"Wow, this is a neat feature I didn't know about. Looks like there are a bunch of options:
- NO ACTION (default)
- RESTRICT: application is prohibited from deleting a parent key when there exists one or more child keys mapped to it
- SET NULL: when a parent key is deleted the child key columns of all rows in the child table that mapped to the parent key are set to contain SQL NULL values
- SET DEFAULT: set a specific default
- CASCADE: propagates the delete or update operation on the parent key to each dependent child key","{""total_count"": 1, ""+1"": 1, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1595340692,"add ability to configure ""on delete"" and ""on update"" attributes of foreign keys:",
https://github.com/simonw/sqlite-utils/issues/532#issuecomment-1539009453,https://api.github.com/repos/simonw/sqlite-utils/issues/532,1539009453,IC_kwDOCGYnMM5bu2ut,9599,simonw,2023-05-08T20:30:29Z,2023-05-08T20:30:42Z,OWNER,"Here's an improvement:
```
% sqlite-utils insert /tmp/b.db blah /tmp/blah.txt
[####################################] 100%
Error: Invalid JSON - use --csv for CSV or --tsv for TSV files
JSON error: Expecting value: line 1 column 1 (char 0)
```","{""total_count"": 1, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 1, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1620254998,Show more information when JSON can't be imported with sqlite-utils insert,
https://github.com/simonw/sqlite-utils/issues/532#issuecomment-1539006509,https://api.github.com/repos/simonw/sqlite-utils/issues/532,1539006509,IC_kwDOCGYnMM5bu2At,9599,simonw,2023-05-08T20:28:56Z,2023-05-08T20:28:56Z,OWNER,Was this a newline-delimited JSON file perhaps?,"{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1620254998,Show more information when JSON can't be imported with sqlite-utils insert,
https://github.com/simonw/sqlite-utils/issues/538#issuecomment-1538975545,https://api.github.com/repos/simonw/sqlite-utils/issues/538,1538975545,IC_kwDOCGYnMM5buuc5,1231935,xavdid,2023-05-08T20:06:35Z,2023-05-08T20:06:35Z,NONE,"perfect, thank you!","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1695428235,`table.upsert_all` fails to write rows when `not_null` is present,
https://github.com/simonw/sqlite-utils/issues/541#issuecomment-1538963959,https://api.github.com/repos/simonw/sqlite-utils/issues/541,1538963959,IC_kwDOCGYnMM5burn3,9599,simonw,2023-05-08T19:59:34Z,2023-05-08T19:59:34Z,OWNER,"There are 8 failing tests left:
```
==== short test summary info ====
FAILED tests/test_cli_memory.py::test_memory_csv[False-test] - pytest.PytestUnraisableExceptionWarning: Exception ignored in: <_io.FileIO [closed]>
FAILED tests/test_cli_memory.py::test_memory_csv[False-t] - pytest.PytestUnraisableExceptionWarning: Exception ignored in: <_io.FileIO [closed]>
FAILED tests/test_cli_memory.py::test_memory_csv[False-t1] - pytest.PytestUnraisableExceptionWarning: Exception ignored in: <_io.FileIO [closed]>
FAILED tests/test_cli_memory.py::test_memory_tsv[False] - pytest.PytestUnraisableExceptionWarning: Exception ignored in: <_io.FileIO [closed]>
FAILED tests/test_cli_memory.py::test_memory_dump[extra_args0] - pytest.PytestUnraisableExceptionWarning: Exception ignored in: <_io.FileIO [closed]>
FAILED tests/test_cli_memory.py::test_memory_two_files_with_same_stem - pytest.PytestUnraisableExceptionWarning: Exception ignored in: <_io.FileIO [closed]>
FAILED tests/test_recipes.py::test_dateparse_errors[None-parsedate] - pytest.PytestUnraisableExceptionWarning: Exception ignored in: .convert_value at 0x106bcaca0>
FAILED tests/test_recipes.py::test_dateparse_errors[None-parsedatetime] - pytest.PytestUnraisableExceptionWarning: Exception ignored in: .convert_value at 0x106bc9620>
ERROR tests/test_cli.py::test_upsert_analyze - pytest.PytestUnraisableExceptionWarning: Exception ignored in: <_io.FileIO [closed]>
==== 8 failed, 894 passed, 4 skipped, 1 error in 6.27s ====
```
Full traceback here: https://gist.github.com/simonw/b40b3e814729d6c02a0302a84ce54d9e","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1700840265,Get tests to pass with `pytest -Werror`,
https://github.com/simonw/sqlite-utils/issues/534#issuecomment-1538933540,https://api.github.com/repos/simonw/sqlite-utils/issues/534,1538933540,IC_kwDOCGYnMM5bukMk,9599,simonw,2023-05-08T19:34:37Z,2023-05-08T19:34:37Z,OWNER,"On macOS this shows the same warning:
```
% python -Wdefault $(which sqlite-utils) insert dogs.db dogs dogs.csv --csv
[############------------------------] 35%
[####################################] 100%/Users/simon/Dropbox/Development/sqlite-utils/sqlite_utils/cli.py:1187: ResourceWarning: unclosed file <_io.TextIOWrapper name='dogs.csv' encoding='utf-8-sig'>
insert_upsert_implementation(
ResourceWarning: Enable tracemalloc to get the object allocation traceback
```
The file itself is a `click.File` which is automatically closed - https://click.palletsprojects.com/en/8.1.x/api/#click.File - but it looks like it's the `_io.TextIOWrapper` which is not being closed:
https://github.com/simonw/sqlite-utils/blob/2376c452a56b0c3e75e7ca698273434e32945304/sqlite_utils/cli.py#L949-L956","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1622640374, ResourceWarning: unclosed file,
https://github.com/simonw/sqlite-utils/issues/538#issuecomment-1538921774,https://api.github.com/repos/simonw/sqlite-utils/issues/538,1538921774,IC_kwDOCGYnMM5buhUu,9599,simonw,2023-05-08T19:24:41Z,2023-05-08T19:24:41Z,OWNER,That fix seems to work!,"{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1695428235,`table.upsert_all` fails to write rows when `not_null` is present,
https://github.com/simonw/sqlite-utils/issues/538#issuecomment-1538910894,https://api.github.com/repos/simonw/sqlite-utils/issues/538,1538910894,IC_kwDOCGYnMM5buequ,9599,simonw,2023-05-08T19:16:52Z,2023-05-08T19:17:00Z,OWNER,"How about if I had logic which checked that all not-null columns were provided in the call to `upsert_all()` - and if they were, modified the `INSERT OR IGNORE INTO` to include a placeholder value for those columns that would then be fixed by the later `UPDATE`?
Something like this:
```python
[
('INSERT OR IGNORE INTO [comments]([id], name) VALUES(?, ?);', [1, '']),
('UPDATE [comments] SET [name] = ? WHERE [id] = ?', ['Cleo', 1])
]
```","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1695428235,`table.upsert_all` fails to write rows when `not_null` is present,
https://github.com/simonw/sqlite-utils/issues/538#issuecomment-1538903556,https://api.github.com/repos/simonw/sqlite-utils/issues/538,1538903556,IC_kwDOCGYnMM5buc4E,9599,simonw,2023-05-08T19:11:24Z,2023-05-08T19:13:23Z,OWNER,"I could detect if this happens using `cursor.rowcount` - not sure how I would recover from it though.
This would also require some major re-engineering, since currently it all works by generating a list of SQL queries in advance and applying them inside a loop in `.insert_chunk()`:
https://github.com/simonw/sqlite-utils/blob/80763edaa2bdaf1113717378b8d62075c4dcbcfb/sqlite_utils/db.py#L2839-L2878
","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1695428235,`table.upsert_all` fails to write rows when `not_null` is present,
https://github.com/simonw/sqlite-utils/issues/538#issuecomment-1538893329,https://api.github.com/repos/simonw/sqlite-utils/issues/538,1538893329,IC_kwDOCGYnMM5buaYR,9599,simonw,2023-05-08T19:04:47Z,2023-05-08T19:04:47Z,OWNER,"This feels like a fundamental flaw in the way upserts are implemented by `sqlite-utils`.
One fix would be to switch to using the `UPSERT` feature in SQLite: https://www.sqlite.org/lang_UPSERT.html
But...
> UPSERT syntax was added to SQLite with version 3.24.0 (2018-06-04).
I still want to support SQLite versions earlier than that.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1695428235,`table.upsert_all` fails to write rows when `not_null` is present,
https://github.com/simonw/sqlite-utils/issues/538#issuecomment-1538889482,https://api.github.com/repos/simonw/sqlite-utils/issues/538,1538889482,IC_kwDOCGYnMM5buZcK,9599,simonw,2023-05-08T19:02:38Z,2023-05-08T19:02:38Z,OWNER,"Here's the code at fault:
https://github.com/simonw/sqlite-utils/blob/80763edaa2bdaf1113717378b8d62075c4dcbcfb/sqlite_utils/db.py#L2774-L2788","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1695428235,`table.upsert_all` fails to write rows when `not_null` is present,
https://github.com/simonw/sqlite-utils/issues/538#issuecomment-1538887361,https://api.github.com/repos/simonw/sqlite-utils/issues/538,1538887361,IC_kwDOCGYnMM5buY7B,9599,simonw,2023-05-08T19:01:20Z,2023-05-08T19:01:20Z,OWNER,"Here's the problem:
```python
import sqlite3
db = sqlite3.connect("":memory:"")
db.execute('create table foo (id integer primary key, name not null)')
db.execute('insert into foo (id) values (1)')
```
Produces:
```
IntegrityError: NOT NULL constraint failed: foo.name
```
But this:
```python
db.execute('insert or ignore into foo (id) values (1)')
```
Completes without an exception.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1695428235,`table.upsert_all` fails to write rows when `not_null` is present,
https://github.com/simonw/sqlite-utils/issues/538#issuecomment-1538801855,https://api.github.com/repos/simonw/sqlite-utils/issues/538,1538801855,IC_kwDOCGYnMM5buEC_,9599,simonw,2023-05-08T18:00:17Z,2023-05-08T18:00:17Z,OWNER,"From time in the debugger, after creating the table it ends up doing this:
```
(Pdb) queries_and_params
[
('INSERT OR IGNORE INTO [comments]([id]) VALUES(?);', [1]),
('UPDATE [comments] SET [name] = ? WHERE [id] = ?', ['Cleo', 1])
]
```","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1695428235,`table.upsert_all` fails to write rows when `not_null` is present,
https://github.com/simonw/sqlite-utils/issues/538#issuecomment-1538793817,https://api.github.com/repos/simonw/sqlite-utils/issues/538,1538793817,IC_kwDOCGYnMM5buCFZ,9599,simonw,2023-05-08T17:55:10Z,2023-05-08T17:55:10Z,OWNER,"Confirmed - I added this test and it fails:
```python
def test_upsert_all_not_null(fresh_db):
# https://github.com/simonw/sqlite-utils/issues/538
fresh_db[""comments""].upsert_all(
[{""id"": 1, ""name"": ""Cleo""}],
pk=""id"",
not_null=[""name""],
)
assert list(fresh_db[""comments""].rows) == [{""id"": 1, ""name"": ""Cleo""}]
```","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1695428235,`table.upsert_all` fails to write rows when `not_null` is present,
https://github.com/simonw/sqlite-utils/issues/540#issuecomment-1537744000,https://api.github.com/repos/simonw/sqlite-utils/issues/540,1537744000,IC_kwDOCGYnMM5bqByA,42327,pquentin,2023-05-08T04:56:12Z,2023-05-08T04:56:12Z,NONE,"Hey @simonw, urllib3 maintainer here :wave:
Sorry for breaking your CI. I understand you may prefer to pin the Python version, but note that specifying just `python: ""3""` will get you the latest. We use that in urllib3: https://github.com/urllib3/urllib3/blob/main/.readthedocs.yml
I can open PRs to sqlite-utils / datasette if you're interested","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1699184583,sphinx.builders.linkcheck build error,
https://github.com/simonw/sqlite-utils/issues/539#issuecomment-1537514610,https://api.github.com/repos/simonw/sqlite-utils/issues/539,1537514610,IC_kwDOCGYnMM5bpJxy,9599,simonw,2023-05-07T18:43:24Z,2023-05-07T18:43:24Z,OWNER,"Documentation:
- https://sqlite-utils.datasette.io/en/latest/cli.html#returning-raw-data-such-as-binary-content
- https://sqlite-utils.datasette.io/en/latest/cli-reference.html#query
- https://sqlite-utils.datasette.io/en/latest/cli-reference.html#memory","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1699174055,"`--raw-lines` option, like `--raw` for multiple lines",
https://github.com/simonw/sqlite-utils/issues/540#issuecomment-1537514069,https://api.github.com/repos/simonw/sqlite-utils/issues/540,1537514069,IC_kwDOCGYnMM5bpJpV,9599,simonw,2023-05-07T18:40:18Z,2023-05-07T18:40:18Z,OWNER,"https://docs.readthedocs.io/en/stable/config-file/v2.html suggests:
```yaml
build:
os: ubuntu-22.04
tools:
python: ""3.11""
```","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1699184583,sphinx.builders.linkcheck build error,
https://github.com/simonw/sqlite-utils/issues/540#issuecomment-1537513912,https://api.github.com/repos/simonw/sqlite-utils/issues/540,1537513912,IC_kwDOCGYnMM5bpJm4,9599,simonw,2023-05-07T18:39:29Z,2023-05-07T18:39:29Z,OWNER,"https://readthedocs.org/projects/sqlite-utils/builds/20513034/ said:
> Problem in your project's configuration. Invalid ""python.version"": expected one of (2, 2.7, 3, 3.5, 3.6, 3.7, 3.8, pypy3.5), got 3.11","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1699184583,sphinx.builders.linkcheck build error,
https://github.com/simonw/sqlite-utils/issues/540#issuecomment-1537513653,https://api.github.com/repos/simonw/sqlite-utils/issues/540,1537513653,IC_kwDOCGYnMM5bpJi1,9599,simonw,2023-05-07T18:37:59Z,2023-05-07T18:38:19Z,OWNER,"Useful comment here:
- https://github.com/urllib3/urllib3/issues/2168#issuecomment-1537360928
> I faced the same issue. I switched to a different Python kernel (3.11.2) and it worked.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1699184583,sphinx.builders.linkcheck build error,
https://github.com/simonw/sqlite-utils/issues/539#issuecomment-1537507676,https://api.github.com/repos/simonw/sqlite-utils/issues/539,1537507676,IC_kwDOCGYnMM5bpIFc,9599,simonw,2023-05-07T18:09:43Z,2023-05-07T18:09:54Z,OWNER,"This worked:
```bash
sqlite-utils memory /tmp/books3.json:nl \
'select name from books3' --raw-lines > titles.txt
```","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1699174055,"`--raw-lines` option, like `--raw` for multiple lines",
https://github.com/simonw/sqlite-utils/issues/539#issuecomment-1537507525,https://api.github.com/repos/simonw/sqlite-utils/issues/539,1537507525,IC_kwDOCGYnMM5bpIDF,9599,simonw,2023-05-07T18:09:09Z,2023-05-07T18:09:09Z,OWNER,"I'm tempted to upgrade `--raw` to do this instead, but that would be a breaking change.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1699174055,"`--raw-lines` option, like `--raw` for multiple lines",
https://github.com/simonw/sqlite-utils/issues/539#issuecomment-1537507394,https://api.github.com/repos/simonw/sqlite-utils/issues/539,1537507394,IC_kwDOCGYnMM5bpIBC,9599,simonw,2023-05-07T18:08:44Z,2023-05-07T18:08:44Z,OWNER,"Prototype:
```diff
diff --git a/docs/cli-reference.rst b/docs/cli-reference.rst
index 153e5f9..c830518 100644
--- a/docs/cli-reference.rst
+++ b/docs/cli-reference.rst
@@ -124,6 +124,7 @@ See :ref:`cli_query`.
--json-cols Detect JSON cols and output them as JSON, not
escaped strings
-r, --raw Raw output, first column of first row
+ --raw-lines Raw output, first column of each row
-p, --param ... Named :parameters for SQL query
--functions TEXT Python code defining one or more custom SQL
functions
@@ -192,6 +193,7 @@ See :ref:`cli_memory`.
--json-cols Detect JSON cols and output them as JSON, not
escaped strings
-r, --raw Raw output, first column of first row
+ --raw-lines Raw output, first column of each row
-p, --param ... Named :parameters for SQL query
--encoding TEXT Character encoding for CSV input, defaults to
utf-8
diff --git a/sqlite_utils/cli.py b/sqlite_utils/cli.py
index d25b1df..da0e4b6 100644
--- a/sqlite_utils/cli.py
+++ b/sqlite_utils/cli.py
@@ -1653,6 +1653,7 @@ def drop_view(path, view, ignore, load_extension):
)
@output_options
@click.option(""-r"", ""--raw"", is_flag=True, help=""Raw output, first column of first row"")
+@click.option(""--raw-lines"", is_flag=True, help=""Raw output, first column of each row"")
@click.option(
""-p"",
""--param"",
@@ -1677,6 +1678,7 @@ def query(
fmt,
json_cols,
raw,
+ raw_lines,
param,
load_extension,
functions,
@@ -1700,7 +1702,19 @@ def query(
_register_functions(db, functions)
_execute_query(
- db, sql, param, raw, table, csv, tsv, no_headers, fmt, nl, arrays, json_cols
+ db,
+ sql,
+ param,
+ raw,
+ raw_lines,
+ table,
+ csv,
+ tsv,
+ no_headers,
+ fmt,
+ nl,
+ arrays,
+ json_cols,
)
@@ -1728,6 +1742,7 @@ def query(
)
@output_options
@click.option(""-r"", ""--raw"", is_flag=True, help=""Raw output, first column of first row"")
+@click.option(""--raw-lines"", is_flag=True, help=""Raw output, first column of each row"")
@click.option(
""-p"",
""--param"",
@@ -1773,6 +1788,7 @@ def memory(
fmt,
json_cols,
raw,
+ raw_lines,
param,
encoding,
no_detect_types,
@@ -1879,12 +1895,36 @@ def memory(
_register_functions(db, functions)
_execute_query(
- db, sql, param, raw, table, csv, tsv, no_headers, fmt, nl, arrays, json_cols
+ db,
+ sql,
+ param,
+ raw,
+ raw_lines,
+ table,
+ csv,
+ tsv,
+ no_headers,
+ fmt,
+ nl,
+ arrays,
+ json_cols,
)
def _execute_query(
- db, sql, param, raw, table, csv, tsv, no_headers, fmt, nl, arrays, json_cols
+ db,
+ sql,
+ param,
+ raw,
+ raw_lines,
+ table,
+ csv,
+ tsv,
+ no_headers,
+ fmt,
+ nl,
+ arrays,
+ json_cols,
):
with db.conn:
try:
@@ -1903,6 +1943,13 @@ def _execute_query(
sys.stdout.buffer.write(data)
else:
sys.stdout.write(str(data))
+ elif raw_lines:
+ for row in cursor:
+ data = row[0]
+ if isinstance(data, bytes):
+ sys.stdout.buffer.write(data + b""\n"")
+ else:
+ sys.stdout.write(str(data) + ""\n"")
elif fmt or table:
print(
tabulate.tabulate(
```
Needs tests and more documentation.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1699174055,"`--raw-lines` option, like `--raw` for multiple lines",
https://github.com/simonw/datasette/issues/2069#issuecomment-1537277919,https://api.github.com/repos/simonw/datasette/issues/2069,1537277919,IC_kwDOBm6k_c5boP_f,31861128,yqlbu,2023-05-07T03:17:35Z,2023-05-07T03:17:35Z,NONE,"Some updates:
I notice that there is an option in the CLI where we can explicitly set `immutable` mode when spinning up the server
```console
Options:
-i, --immutable PATH Database files to open in immutable mode
```
Then, the question is - how can I disable immutable mode in the deployed instance on Vercel?","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1698865182,[BUG] Cannot insert new data to deployed instance,
https://github.com/simonw/sqlite-utils/issues/496#issuecomment-1532481862,https://api.github.com/repos/simonw/sqlite-utils/issues/496,1532481862,IC_kwDOCGYnMM5bV9FG,1231935,xavdid,2023-05-03T05:53:26Z,2023-05-03T05:53:26Z,NONE,"Would love to put our heads together for improvements here.
I _think_ anything that is `argname=DEFAULT` needs to be typed as `argname: str | Default = DEFAULT` (replacing `str` with the appropriate type(s)). We may be able to get clever and tie the types to that key in the `_defaults` dict (definitely possible in Typescript, but I'm less familiar with advanced python types).
Right now, all args are typed as `Default`, which means all callers get type errors.
As for table/view, given that they don't have the same methods, it would be nice to be able to get one or the other specifically.
","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1393202060,devrel/python api: Pylance type hinting,
https://github.com/simonw/datasette/issues/2067#issuecomment-1532304714,https://api.github.com/repos/simonw/datasette/issues/2067,1532304714,IC_kwDOBm6k_c5bVR1K,39538958,justmars,2023-05-03T00:16:03Z,2023-05-03T00:16:03Z,NONE,"Curiously, after running commands on the database that was litestream-restored, datasette starts to work again, e.g.
```sh
litestream restore -o data/db.sqlite s3://mytestbucketxx/db
datasette data/db.sqlite
# fails (OperationalError described above)
```
```sh
litestream restore -o data/db.sqlite s3://mytestbucketxx/db
sqlite-utils enable-wal data/db.sqlite
datasette data/db.sqlite
# works
```
```sh
litestream restore -o data/db.sqlite s3://mytestbucketxx/db
sqlite-utils optimize data/db.sqlite
datasette data/db.sqlite
# works
```
```sh
litestream restore -o data/db.sqlite s3://mytestbucketxx/db
sqlite3 data/db.sqlite "".clone test.db""
datasette test.db
# works
```","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1690765434,Litestream-restored db: errors on 3.11 and 3.10.8; but works on py3.10.7 and 3.10.6,
https://github.com/simonw/datasette/pull/2052#issuecomment-1530822437,https://api.github.com/repos/simonw/datasette/issues/2052,1530822437,IC_kwDOBm6k_c5bPn8l,193185,cldellow,2023-05-02T03:35:30Z,2023-05-02T16:02:38Z,CONTRIBUTOR,"Also, just checking - is this how I'd write bulletproof plugin registration code that is robust against the order in which the script tags load (eg if both my code and the Datasette code are loaded via a `` tag)?
```js
if (window.__DATASETTE__)
go(window.__DATASETTE__);
else
document.addEventListener(""datasette_init"", (evt) => go(evt.detail));
function go(manager) {
manager.registerPlugin(...)
}
```
I don't know if it'd make sense, but you could also consider the asynchronous queuing pattern that Google Analytics uses (see [this Stack Overflow post](https://stackoverflow.com/questions/6963779/whats-the-name-of-google-analytics-async-design-pattern-and-where-is-it-used) for more details):
```js
__DATASETTE__ = __DATASETTE__ || [];
__DATASETTE__.push(go);
function go(manager) {
manager.registerPlugin(...);
}
```","{""total_count"": 2, ""+1"": 1, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 1}",1651082214,"feat: Javascript Plugin API (Custom panels, column menu items with JS actions)",
https://github.com/simonw/datasette/pull/2052#issuecomment-1530817667,https://api.github.com/repos/simonw/datasette/issues/2052,1530817667,IC_kwDOBm6k_c5bPmyD,193185,cldellow,2023-05-02T03:24:53Z,2023-05-02T03:24:53Z,CONTRIBUTOR,"Thanks for putting this together! I've been slammed with work/personal stuff so haven't been able to actually prototype anything with this. :(
tl;dr: I think this would be useful immediately as is. It might also be nice if the plugins could return `Promise`s.
The long version: I read the design notes and example plugin. I think I'd be able to use this in [datasette-ui-extras](https://github.com/cldellow/datasette-ui-extras) for my lazy-facets feature.
The lazy-facets feature tries to provide a snappier user experience. It does this by altering how suggested facets work.
First, at page render time:
(A) it lies to Datasette and claims that no columns support facets, this avoids the lengthy delays/timeouts that can happen if the dataset is large.
(B) there's a python plugin that implements the [extra_body_script](https://docs.datasette.io/en/stable/plugin_hooks.html#extra-body-script-template-database-table-columns-view-name-request-datasette) hook, to write out the list of column names for future use by JavaScript
Second, at page load time: there is some JavaScript that:
(C) makes AJAX requests to suggest facets for each column - it makes 1 request per column, using the data from (B)
(D) wires up the column menus to add Facet-by-this options for each facet
With the currently proposed plugin scheme, I think (D) could be moved into the plugin. I'd do the ajax requests, then register the plugin.
If the plugin scheme also supported promises, I think (B) and (C) could also be moved into the plugin.
Does that make sense? Sorry for the wall of text!","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1651082214,"feat: Javascript Plugin API (Custom panels, column menu items with JS actions)",
https://github.com/simonw/datasette/pull/2064#issuecomment-1529737426,https://api.github.com/repos/simonw/datasette/issues/2064,1529737426,IC_kwDOBm6k_c5bLfDS,49699333,dependabot[bot],2023-05-01T13:58:50Z,2023-05-01T13:58:50Z,CONTRIBUTOR,Superseded by #2068.,"{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1683229834,Bump sphinx from 6.1.3 to 6.2.1,
https://github.com/simonw/datasette/issues/2065#issuecomment-1524709988,https://api.github.com/repos/simonw/datasette/issues/2065,1524709988,IC_kwDOBm6k_c5a4Tpk,9599,simonw,2023-04-27T05:09:36Z,2023-04-27T05:09:36Z,OWNER,"That fixed it - after installing `main.zip` again I ran this and it worked:
~/.rye/tools/main-zip/bin/datasette install datasette-graphql
```
% ~/.rye/tools/main-zip/bin/datasette plugins
[
{
""name"": ""datasette-graphql"",
""static"": true,
""templates"": true,
""version"": ""2.2"",
""hooks"": [
""database_actions"",
""extra_template_vars"",
""menu_links"",
""register_routes"",
""startup"",
""table_actions""
]
}
]
```","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1686033652,Datasette cannot be installed with Rye,
https://github.com/simonw/datasette/issues/2065#issuecomment-1524707628,https://api.github.com/repos/simonw/datasette/issues/2065,1524707628,IC_kwDOBm6k_c5a4TEs,9599,simonw,2023-04-27T05:06:44Z,2023-04-27T05:06:44Z,OWNER,"I need `pip` as a dependency too:
```
% ~/.rye/tools/main-zip/bin/datasette install datasette-graphql
Traceback (most recent call last):
File ""/Users/simon/.rye/tools/main-zip/bin/datasette"", line 8, in
sys.exit(cli())
^^^^^
File ""/Users/simon/.rye/tools/main-zip/lib/python3.11/site-packages/click/core.py"", line 1130, in __call__
return self.main(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^
File ""/Users/simon/.rye/tools/main-zip/lib/python3.11/site-packages/click/core.py"", line 1055, in main
rv = self.invoke(ctx)
^^^^^^^^^^^^^^^^
File ""/Users/simon/.rye/tools/main-zip/lib/python3.11/site-packages/click/core.py"", line 1657, in invoke
return _process_result(sub_ctx.command.invoke(sub_ctx))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File ""/Users/simon/.rye/tools/main-zip/lib/python3.11/site-packages/click/core.py"", line 1404, in invoke
return ctx.invoke(self.callback, **ctx.params)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File ""/Users/simon/.rye/tools/main-zip/lib/python3.11/site-packages/click/core.py"", line 760, in invoke
return __callback(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File ""/Users/simon/.rye/tools/main-zip/lib/python3.11/site-packages/datasette/cli.py"", line 365, in install
run_module(""pip"", run_name=""__main__"")
File """", line 222, in run_module
File """", line 142, in _get_module_details
ImportError: No module named pip
```","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1686033652,Datasette cannot be installed with Rye,
https://github.com/simonw/datasette/issues/2065#issuecomment-1524699863,https://api.github.com/repos/simonw/datasette/issues/2065,1524699863,IC_kwDOBm6k_c5a4RLX,9599,simonw,2023-04-27T04:56:22Z,2023-04-27T04:56:22Z,OWNER,Turned this into a TIL: https://til.simonwillison.net/python/rye,"{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1686033652,Datasette cannot be installed with Rye,
https://github.com/simonw/datasette/issues/2066#issuecomment-1524680160,https://api.github.com/repos/simonw/datasette/issues/2066,1524680160,IC_kwDOBm6k_c5a4MXg,9599,simonw,2023-04-27T04:27:50Z,2023-04-27T04:27:50Z,OWNER,That fixed it.,"{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1686042269,Failing test: httpx.InvalidURL: URL too long,
https://github.com/simonw/datasette/issues/2066#issuecomment-1524675817,https://api.github.com/repos/simonw/datasette/issues/2066,1524675817,IC_kwDOBm6k_c5a4LTp,9599,simonw,2023-04-27T04:21:03Z,2023-04-27T04:21:03Z,OWNER,I went with this to generate the long string: https://github.com/simonw/datasette/blob/0b0c5cd7a94fe3f151a3e10261b5c84ee64f2f18/tests/test_csv.py#L157-L176,"{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1686042269,Failing test: httpx.InvalidURL: URL too long,
https://github.com/simonw/datasette/issues/2066#issuecomment-1524669124,https://api.github.com/repos/simonw/datasette/issues/2066,1524669124,IC_kwDOBm6k_c5a4JrE,9599,simonw,2023-04-27T04:10:44Z,2023-04-27T04:10:52Z,OWNER,"I need an alternative way of generating a long string with a shorter URL.
```sql
select group_concat('abcabcabc', '') from json_each(json_array(1, 2, 3, 4, 5, 6, 7, 8, 9, 10))
```
https://latest.datasette.io/_memory?sql=select+group_concat%28%27abcabcabc%27%2C+%27%27%29+from+json_each%28json_array%281%2C+2%2C+3%2C+4%2C+5%2C+6%2C+7%2C+8%2C+9%2C+10%29%29","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1686042269,Failing test: httpx.InvalidURL: URL too long,
https://github.com/simonw/datasette/issues/2066#issuecomment-1524666049,https://api.github.com/repos/simonw/datasette/issues/2066,1524666049,IC_kwDOBm6k_c5a4I7B,9599,simonw,2023-04-27T04:06:18Z,2023-04-27T04:06:18Z,OWNER,"Most recent `httpx` release is 0.24 a couple of weeks ago. Here's what changed in that version: https://github.com/encode/httpx/compare/0.23.3...0.24.0
It looks like that URL limit is new: https://github.com/encode/httpx/commit/57daabf673705954afa94686c0002801c93d31f3#diff-78d8d93b5dd4c77d99c3e2b46b7286ba71a8fd60e92d8bd4eee5fb200b4f87bfR149-R155
```python
def urlparse(url: str = """", **kwargs: typing.Optional[str]) -> ParseResult:
# Initial basic checks on allowable URLs.
# ---------------------------------------
# Hard limit the maximum allowable URL length.
if len(url) > MAX_URL_LENGTH:
raise InvalidURL(""URL too long"")
```
https://github.com/encode/httpx/blob/32e25497a36e6222cc64a758c98275b450dac28d/httpx/_urlparse.py#L153-L155","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1686042269,Failing test: httpx.InvalidURL: URL too long,
https://github.com/simonw/datasette/issues/2066#issuecomment-1524660603,https://api.github.com/repos/simonw/datasette/issues/2066,1524660603,IC_kwDOBm6k_c5a4Hl7,9599,simonw,2023-04-27T04:02:55Z,2023-04-27T04:02:55Z,OWNER,"In the debugger:
```
(Pdb) MAX_URL_LENGTH
65536
```
Weird this only seems to be a problem with `httpx` on Python 3.7 though.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1686042269,Failing test: httpx.InvalidURL: URL too long,
https://github.com/simonw/datasette/issues/2066#issuecomment-1524659084,https://api.github.com/repos/simonw/datasette/issues/2066,1524659084,IC_kwDOBm6k_c5a4HOM,9599,simonw,2023-04-27T04:02:07Z,2023-04-27T04:02:07Z,OWNER,"This is the failing test:
https://github.com/simonw/datasette/blob/249fcf8e3e2a90e763f41b080c1b9ec8017f5005/tests/test_csv.py#L156-L167","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1686042269,Failing test: httpx.InvalidURL: URL too long,
https://github.com/simonw/datasette/issues/2066#issuecomment-1524655203,https://api.github.com/repos/simonw/datasette/issues/2066,1524655203,IC_kwDOBm6k_c5a4GRj,9599,simonw,2023-04-27T03:59:56Z,2023-04-27T03:59:56Z,OWNER,"In a fresh Datasette checkout I ran:
pipenv shell --python /Users/simon/.pyenv/versions/3.7.16/bin/python
That gave me a virtual environment with 3.7.16 Python.
Then I ran:
pip install -e '.[test]'
Weirdly that gave me a `which pytest` of `/opt/homebrew/bin/pytest` which ran the tests on 3.11.
I figured out the location of the virtual environment with `which python` and then ran this:
```
% /Users/simon/.local/share/virtualenvs/datasette-cZYvnUqY/bin/pytest tests/test_csv.py
============================================================================================== test session starts ===============================================================================================
platform darwin -- Python 3.7.16, pytest-7.3.1, pluggy-1.0.0
SQLite: 3.39.5
rootdir: /private/tmp/datasette
configfile: pytest.ini
plugins: asyncio-0.21.0, timeout-2.1.0, xdist-3.2.1, anyio-3.6.2
asyncio: mode=strict
collected 15 items
tests/test_csv.py ..........F.... [100%]
==================================================================================================== FAILURES ====================================================================================================
________________________________________________________________________________________________ test_max_csv_mb _________________________________________________________________________________________________
app_client_csv_max_mb_one =
def test_max_csv_mb(app_client_csv_max_mb_one):
response = app_client_csv_max_mb_one.get(
(
""/fixtures.csv?sql=select+'{}'+""
""from+compound_three_primary_keys&_stream=1&_size=max""
> ).format(""abcdefg"" * 10000)
)
/private/tmp/datasette/tests/test_csv.py:161:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
/Users/simon/.local/share/virtualenvs/datasette-cZYvnUqY/lib/python3.7/site-packages/asgiref/sync.py:240: in __call__
return call_result.result()
/Users/simon/.pyenv/versions/3.7.16/lib/python3.7/concurrent/futures/_base.py:428: in result
return self.__get_result()
/Users/simon/.pyenv/versions/3.7.16/lib/python3.7/concurrent/futures/_base.py:384: in __get_result
raise self._exception
/Users/simon/.local/share/virtualenvs/datasette-cZYvnUqY/lib/python3.7/site-packages/asgiref/sync.py:306: in main_wrap
result = await self.awaitable(*args, **kwargs)
/private/tmp/datasette/datasette/utils/testing.py:76: in get
headers=headers,
/private/tmp/datasette/datasette/utils/testing.py:167: in _request
content=post_body,
/private/tmp/datasette/datasette/app.py:1787: in request
method, self._fix(path, avoid_path_rewrites), **kwargs
/Users/simon/.local/share/virtualenvs/datasette-cZYvnUqY/lib/python3.7/site-packages/httpx/_client.py:1528: in request
extensions=extensions,
/Users/simon/.local/share/virtualenvs/datasette-cZYvnUqY/lib/python3.7/site-packages/httpx/_client.py:346: in build_request
url = self._merge_url(url)
/Users/simon/.local/share/virtualenvs/datasette-cZYvnUqY/lib/python3.7/site-packages/httpx/_client.py:376: in _merge_url
merge_url = URL(url)
/Users/simon/.local/share/virtualenvs/datasette-cZYvnUqY/lib/python3.7/site-packages/httpx/_urls.py:113: in __init__
self._uri_reference = urlparse(url, **kwargs)
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
url = ""http://localhost/fixtures.csv?sql=select+'abcdefgabcdefgabcdefgabcdefgabcdefgabcdefgabcdefgabcdefgabcdefgabcdefgabcde...gabcdefgabcdefgabcdefgabcdefgabcdefgabcdefgabcdefgabcdefgabcdefg'+from+compound_three_primary_keys&_stream=1&_size=max""
kwargs = {}
def urlparse(url: str = """", **kwargs: typing.Optional[str]) -> ParseResult:
# Initial basic checks on allowable URLs.
# ---------------------------------------
# Hard limit the maximum allowable URL length.
if len(url) > MAX_URL_LENGTH:
> raise InvalidURL(""URL too long"")
E httpx.InvalidURL: URL too long
/Users/simon/.local/share/virtualenvs/datasette-cZYvnUqY/lib/python3.7/site-packages/httpx/_urlparse.py:155: InvalidURL
============================================================================================ short test summary info =============================================================================================
FAILED tests/test_csv.py::test_max_csv_mb - httpx.InvalidURL: URL too long
========================================================================================== 1 failed, 14 passed in 1.83s ==========================================================================================
(datasette) simon@Simons-MacBook-Pro datasette %
```","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1686042269,Failing test: httpx.InvalidURL: URL too long,
https://github.com/simonw/datasette/issues/2066#issuecomment-1524648995,https://api.github.com/repos/simonw/datasette/issues/2066,1524648995,IC_kwDOBm6k_c5a4Ewj,9599,simonw,2023-04-27T03:56:42Z,2023-04-27T03:57:11Z,OWNER,"I don't have 3.7 locally. Trying to install it with `pyenv`.
brew install pyenv
Then:
pyenv install --list | grep 3.7
Installing:
pyenv install 3.7.16
Output:
Installed Python-3.7.16 to /Users/simon/.pyenv/versions/3.7.16
So the executable is `/Users/simon/.pyenv/versions/3.7.16/bin/python`.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1686042269,Failing test: httpx.InvalidURL: URL too long,
https://github.com/simonw/datasette/issues/2066#issuecomment-1524638233,https://api.github.com/repos/simonw/datasette/issues/2066,1524638233,IC_kwDOBm6k_c5a4CIZ,9599,simonw,2023-04-27T03:50:51Z,2023-04-27T03:50:51Z,OWNER,Failure was on 3.7. I'll try that.,"{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1686042269,Failing test: httpx.InvalidURL: URL too long,
https://github.com/simonw/datasette/issues/2066#issuecomment-1524637376,https://api.github.com/repos/simonw/datasette/issues/2066,1524637376,IC_kwDOBm6k_c5a4B7A,9599,simonw,2023-04-27T03:50:19Z,2023-04-27T03:50:19Z,OWNER,"Having trouble replicating this on my laptop. I tried a fresh virtual environment with fresh packages (in case this is a `httpx` change) but this passed:
pytest tests/test_csv.py","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1686042269,Failing test: httpx.InvalidURL: URL too long,
https://github.com/simonw/datasette/issues/2065#issuecomment-1524616740,https://api.github.com/repos/simonw/datasette/issues/2065,1524616740,IC_kwDOBm6k_c5a384k,9599,simonw,2023-04-27T03:38:21Z,2023-04-27T03:38:21Z,OWNER,"Tried this:
rye install https://github.com/simonw/datasette/archive/refs/heads/main.zip
But got this error:
Error: Expected one of `@`, `(`, `<`, `=`, `>`, `~`, `!`, `;`, found `:`
I instead downloaded that file and ran:
rye install main.zip
This worked! And now:
```
~/.rye/tools/main-zip/bin/datasette --version
```
```
datasette, version 1.0a2
```","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1686033652,Datasette cannot be installed with Rye,
https://github.com/simonw/datasette/pull/2063#issuecomment-1521837780,https://api.github.com/repos/simonw/datasette/issues/2063,1521837780,IC_kwDOBm6k_c5atWbU,49699333,dependabot[bot],2023-04-25T13:57:52Z,2023-04-25T13:57:52Z,CONTRIBUTOR,Superseded by #2064.,"{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1681339696,Bump sphinx from 6.1.3 to 6.2.0,
https://github.com/simonw/datasette/pull/2052#issuecomment-1515694393,https://api.github.com/repos/simonw/datasette/issues/2052,1515694393,IC_kwDOBm6k_c5aV6k5,9020979,hydrosquall,2023-04-20T04:25:55Z,2023-04-20T04:25:55Z,NONE,"Thanks for the thoughtful review and generous examples @asg017 ! I'll make the changes you suggested soon. Bonus thoughts inlined below.
> comments
These were very much appreciated, it's important to a plugin system that details like this feel right! I'll address them in batch later in the week.
> I know TypeScript can be a little controversial
FWIW I am in favor of doing Typescript - I just wanted to keep the initial set of files in this PR as simple as possible to review. Really appreciate you scaffolding this initial set of types + I think it would be a welcome addition to maintain a set of types.d.ts files.
I'm entertaining the idea of writing the actual source code in Typescript as long as the compiled output is readable b/c it can be tricky to keep the types and plain JS files in sync. Curious if you have encountered projects that are good at preventing drift.
> Maybe they should have more ""action-y"" names
This is a great observation. I'm inclined towards something like `make*` or `build*` since to me `add*` make me think the thing the method is attached to is being mutated, but I agree that any of these may be clearer than the current `get*` setup. I'll go through and update these.
> Maybe we can make it easier to do pure-js datasette plugins?
I really like this idea! It'll be easier to get contributors if they don't have to touch the python side at _all_.
> And then do the PERMITTED_VIEWS filtering in JS rather than Python.
One cost of doing this is that pages that won't use the JS would still have to load the unused code (given that I'm not sending up anything complex like lazy loading). But hopefully the manager core size is close to negligible, and it won't be a big deal. ","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1651082214,"feat: Javascript Plugin API (Custom panels, column menu items with JS actions)",
https://github.com/simonw/datasette/pull/2052#issuecomment-1510423215,https://api.github.com/repos/simonw/datasette/issues/2052,1510423215,IC_kwDOBm6k_c5aBzqv,9020979,hydrosquall,2023-04-16T16:12:59Z,2023-04-16T16:12:59Z,NONE,"## Research notes
- I stuck to the ""minimal dependencies"" ethos of datasette (no React, Typescript, JS linting, etc).
- Main threads on JS plugin development
- Main: sketch of pluggy-inspired system: https://github.com/simonw/datasette/issues/983
- Main: provide locations in Datasette HTML that are designed for multiple plugins to safely cooperate with each other (starting with the panel, but eventually could extend to ""search boxes""): https://github.com/simonw/datasette/issues/1191
- Main: HTML hooks for JS plugin authors: https://github.com/simonw/datasette/issues/987
- Prior threads on JS plugins in Datasette for future design directions
- Idea: pass useful strings to JS plugins: https://github.com/simonw/datasette/issues/1565
- Idea: help with plugin dependency loading: https://github.com/simonw/datasette/issues/1542 . (IMO - the plugin providing the dependency can emit an event once it's done. Other plugins can listen for it, or ask the manager to inform them when the dependency is available).
- Idea: help plugins to manage state in shareable URLs (plugins shouldn't have to interact with the URL directly, should have some basic insulation from clobbering each others' keys): https://github.com/simonw/datasette/issues/1144
- Articles on plugins reviewed
- https://css-tricks.com/designing-a-javascript-plugin-system/
- Plugin/Extension systems reviewed (mostly JS).
- Yarn: https://yarnpkg.com/advanced/plugin-tutorial
- Tappable https://github.com/webpack/tapable (used by Auto, webpack)
- Pluggy: https://pluggy.readthedocs.io/en/stable/
- VSCode: https://code.visualstudio.com/api/get-started/your-first-extension
- Chrome: https://developer.chrome.com/docs/extensions/reference/
- Figma/Figjam Widget: https://www.figma.com/widget-docs/
- Datadog Apps: [Programming Model](https://github.com/DataDog/apps/blob/master/docs/en/programming-model.md)
- Storybook: https://storybook.js.org/docs/react/addons/addons-api","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1651082214,"feat: Javascript Plugin API (Custom panels, column menu items with JS actions)",
https://github.com/simonw/datasette/pull/2052#issuecomment-1510423051,https://api.github.com/repos/simonw/datasette/issues/2052,1510423051,IC_kwDOBm6k_c5aBzoL,9020979,hydrosquall,2023-04-16T16:12:14Z,2023-04-20T05:14:39Z,NONE,"# Javascript Plugin Docs (alpha)
## Motivation
The Datasette JS Plugin API allows developers to add interactive features to the UI, without having to modify the Python source code.
## Setup
No external/NPM dependencies are needed.
Plugin behavior is coordinated by the Datasette `manager`. Every page has 1 `manager`.
There are 2 ways to add your plugin to the `manager`.
1. Read `window.__DATASETTE__` if the manager was already loaded.
```js
const manager = window.__DATASETTE__;
```
2. Wait for the `datasette_init` event to fire if your code was loaded before the manager is ready.
```js
document.addEventListener(""datasette_init"", function (evt) {
const { detail: manager } = evt;
// register plugin here
});
```
3. Add plugin to the manager by calling `manager.registerPlugin` in a JS file. Each plugin will supply 1 or more hooks with
- unique name (`YOUR_PLUGIN_NAME`)
- a numeric version (starting at `0.1`),
- configuration value, the details vary by hook. (In this example, `getColumnActions` takes a function)
```js
manager.registerPlugin(""YOUR_PLUGIN_NAME"", {
version: 0.1,
makeColumnActions: (columnMeta) => {
return [
{
label: ""Copy name to clipboard"",
// evt = native click event
onClick: (evt) => copyToClipboard(columnMeta.column),
}
];
},
});
```
There are 2 plugin hooks available to `manager.registerPlugin`:
- `makeColumnActions` - Add items to the cog menu for headers on datasette table pages
- `makeAboveTablePanelConfigs` - Add items to ""tabbed"" panel above the `
` on pages that use the Datasette table template.
While there are additional properties on the `manager`, but it's not advised to depend on them directly as the shape is subject to change.
4. To make your JS file available as a Datasette plugin from the Python side, you can add a python file resembling [this](https://github.com/simonw/datasette/pull/2052/files#diff-c5ecf3d22075a60d04a4e95da2e15c612cf1bc84e38d777b67ba60dbd156e293) to your plugins directory. Note that you could host your JS file anywhere, it doesn't have to be served from the Datasette statics folder.
I welcome ideas for more hooks, or feedback on the current design!
## Examples
See the [example plugins file](https://github.com/simonw/datasette/blob/2d92b9328022d86505261bcdac419b6ed9cb2236/datasette/static/table-example-plugins.js) for additional examples.
## Hooks API Guide
### `makeAboveTablePanelConfigs`
Provide a function with a list of panel objects. Each panel object should contain
1. A unique string `id`
2. A string `label` for the tab
3. A `render` function. The first argument is reference to an HTML [Element](https://developer.mozilla.org/en-US/docs/Web/API/Element).
Example:
```js
manager.registerPlugin(""panel-plugin-graphs"", {
version: 0.1,
makeAboveTablePanelConfigs: () => {
return [
{
id: 'first-panel',
label: ""My new panel"",
render: node => {
const description = document.createElement('p');
description.innerText = 'Hello world';
node.appendChild(description);
}
}
];
},
});
```
### `makeColumnActions`
Provide a function that returns a list of action objects. Each action object has
1. A string `label` for the menu dropdown label
2. An onClick `render` function.
Example:
```js
manager.registerPlugin(""column-name-plugin"", {
version: 0.1,
getColumnActions: (columnMeta) => {
// Info about selected column.
const { columnName, columnNotNull, columnType, isPk } = columnMeta;
return [
{
label: ""Copy name to clipboard"",
onClick: (evt) => copyToClipboard(column),
}
];
},
});
```
The getColumnActions callback has access to an object with metadata about the clicked column. These fields include:
- columnName: string (name of the column)
- columnNotNull: boolean
- columnType: sqlite datatype enum (text, number, etc)
- isPk: Whether this is the primary key: boolean
You can use this column metadata to customize the action config objects (for example, handling different summaries for text vs number columns).
","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1651082214,"feat: Javascript Plugin API (Custom panels, column menu items with JS actions)",
https://github.com/simonw/sqlite-utils/issues/425#issuecomment-1509951952,https://api.github.com/repos/simonw/sqlite-utils/issues/425,1509951952,IC_kwDOCGYnMM5aAAnQ,89400147,Dhyanesh97,2023-04-15T20:14:58Z,2023-04-15T20:14:58Z,NONE,is this change released ? Because when we run docker containers issue still persists for production deployments.,"{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1203842656,`sqlite3.NotSupportedError`: deterministic=True requires SQLite 3.8.3 or higher,
https://github.com/simonw/datasette/pull/2056#issuecomment-1509852821,https://api.github.com/repos/simonw/datasette/issues/2056,1509852821,IC_kwDOBm6k_c5Z_oaV,3709715,cclauss,2023-04-15T14:24:45Z,2023-04-15T14:24:45Z,NONE,Status?,"{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1661860507,GitHub Action to lint Python code with ruff,
https://github.com/simonw/datasette/pull/2052#issuecomment-1509461324,https://api.github.com/repos/simonw/datasette/issues/2052,1509461324,IC_kwDOBm6k_c5Z-I1M,9020979,hydrosquall,2023-04-15T01:57:06Z,2023-04-15T01:57:06Z,NONE,Notes from 1:1 - it _is_ possible to pass in URL params into a ObservableHQ notebook: https://observablehq.com/@bherbertlc/pass-values-as-url-parameters,"{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1651082214,"feat: Javascript Plugin API (Custom panels, column menu items with JS actions)",
https://github.com/dogsheep/apple-notes-to-sqlite/issues/6#issuecomment-1508784533,https://api.github.com/repos/dogsheep/apple-notes-to-sqlite/issues/6,1508784533,IC_kwDOJHON9s5Z7jmV,579727,sirnacnud,2023-04-14T15:22:09Z,2023-04-14T15:22:09Z,NONE,"Just changing the encoding in `extract_notes` to `utf8` seems to fix it for my titles that were messed up.
![Screen Shot 2023-04-14 at 5 14 18 PM](https://user-images.githubusercontent.com/579727/232086062-e7edc4d1-0880-417a-925b-fd6c65b05155.png)
","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1617602868,Character encoding problem,
https://github.com/simonw/datasette/issues/2058#issuecomment-1507264934,https://api.github.com/repos/simonw/datasette/issues/2058,1507264934,IC_kwDOBm6k_c5Z1wmm,1138559,esagara,2023-04-13T16:35:21Z,2023-04-13T16:35:21Z,NONE,"I tried deploying the fix you submitted, but still getting the same errors. I can past the logs here if needed, but I really don't see anything new in them.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1663399821,"500 ""attempt to write a readonly database"" error caused by ""PRAGMA schema_version""",
https://github.com/simonw/datasette/pull/2056#issuecomment-1506485287,https://api.github.com/repos/simonw/datasette/issues/2056,1506485287,IC_kwDOBm6k_c5ZyyQn,3709715,cclauss,2023-04-13T07:29:38Z,2023-04-13T07:41:55Z,NONE,"Ruff (written in Rust, not Python) is a 23MB executable so the time to download and pip install it dwarfs its runtime.
Let's run ruff with and without GitHub Actions pip cache side-by-side to see the relative performance.
Once you approve the workflows below, `ruff_with_cache` should echo `cache-hit = false` but if you rerun that job hopefully it should echo `cache-hit = true`. That will be the execution time that we are interested to compare.
There are two great problems in computer science: ;-)
1. Naming things
2. Cache invalidation
3. Off-by-one errors
For 2., https://github.com/actions/setup-python#caching-packages-dependencies is vital reading.
Only _exactly pinned requirements_ can be cached. Currently in `setup.py` the only pinned dependencies are:
1. Sphinx==6.1.3
2. furo==2023.3.27
3. black==23.3.0
4. blacken-docs==1.13.0 # but unpinned elsewhere in `setup.py`
This means that there will be very few cache hits in the current actions. See the link below to print out cache hits:
https://github.com/actions/setup-python/blob/main/docs/advanced-usage.md#cache-hit
> PyPI uses Fastly's CDN to quickly serve content to end-users, allowing us to minimize our hosting infrastructure and obscure possible downtime. -- https://pypi.org/sponsors
I would be shocked if Fastly does not have beefy CDN nodes in the same datacenters where GitHub Actions run so GHA requests to download `ruff` probably never hit a PyPI server.
","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1661860507,GitHub Action to lint Python code with ruff,
https://github.com/simonw/sqlite-utils/issues/527#issuecomment-1506223848,https://api.github.com/repos/simonw/sqlite-utils/issues/527,1506223848,IC_kwDOCGYnMM5Zxybo,9599,simonw,2023-04-13T02:08:16Z,2023-04-13T02:08:16Z,OWNER,"I agree, this is a design flaw.
It's technically a breaking change. As such, I would need to bump to v4 to responsibly release this.
I'd rather bundle in a few more breaking changes before shipping that version.
One thing we could do here is add an extra argument to `.convert()` - something like this:
```python
table.convert(col, lambda x: x+1, skip_false=False)
```
This would trigger the new, improved behaviour without breaking existing code that depends on how it works at the moment.
Then in `sqlite-utils` 4 we can change the default of that option.
What do you think?
(I'm open to suggestions for better names for this parameter too)","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1578790070,`Table.convert()` skips falsey values,
https://github.com/simonw/datasette/issues/2058#issuecomment-1506203550,https://api.github.com/repos/simonw/datasette/issues/2058,1506203550,IC_kwDOBm6k_c5Zxtee,547438,cephillips,2023-04-13T01:48:21Z,2023-04-13T01:48:21Z,NONE,Really interesting how you are using ChatGPT in this.,"{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1663399821,"500 ""attempt to write a readonly database"" error caused by ""PRAGMA schema_version""",
https://github.com/simonw/sqlite-utils/pull/537#issuecomment-1506200813,https://api.github.com/repos/simonw/sqlite-utils/issues/537,1506200813,IC_kwDOCGYnMM5Zxszt,22429695,codecov[bot],2023-04-13T01:45:22Z,2023-04-13T01:45:22Z,NONE,"## [Codecov](https://codecov.io/gh/simonw/sqlite-utils/pull/537?src=pr&el=h1&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison) Report
Patch coverage: **`100.00`**% and no project coverage change.
> Comparison is base [(`c0251cc`)](https://codecov.io/gh/simonw/sqlite-utils/commit/c0251cc9271260de73b4227859a51fab9b4cb745?el=desc&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison) 96.25% compared to head [(`a75abeb`)](https://codecov.io/gh/simonw/sqlite-utils/pull/537?src=pr&el=desc&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison) 96.25%.
Additional details and impacted files
```diff
@@ Coverage Diff @@
## main #537 +/- ##
=======================================
Coverage 96.25% 96.25%
=======================================
Files 6 6
Lines 2671 2673 +2
=======================================
+ Hits 2571 2573 +2
Misses 100 100
```
| [Impacted Files](https://codecov.io/gh/simonw/sqlite-utils/pull/537?src=pr&el=tree&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison) | Coverage Δ | |
|---|---|---|
| [sqlite\_utils/db.py](https://codecov.io/gh/simonw/sqlite-utils/pull/537?src=pr&el=tree&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison#diff-c3FsaXRlX3V0aWxzL2RiLnB5) | `97.33% <100.00%> (+<0.01%)` | :arrow_up: |
Help us with your feedback. Take ten seconds to tell us [how you rate us](https://about.codecov.io/nps?utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison). Have a feature suggestion? [Share it here.](https://app.codecov.io/gh/feedback/?utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison)
[:umbrella: View full report in Codecov by Sentry](https://codecov.io/gh/simonw/sqlite-utils/pull/537?src=pr&el=continue&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison).
:loudspeaker: Do you have feedback about the report comment? [Let us know in this issue](https://about.codecov.io/codecov-pr-comment-feedback/?utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison).
","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1665200812,Support self-referencing FKs in `Table.create`,
https://github.com/simonw/datasette/pull/2056#issuecomment-1506179555,https://api.github.com/repos/simonw/datasette/issues/2056,1506179555,IC_kwDOBm6k_c5Zxnnj,9599,simonw,2023-04-13T01:21:05Z,2023-04-13T01:22:08Z,OWNER,"OK, I'm sold - this is a really neat improvement.
One thing to change in the PR: right now it runs `pip install --user ruff` on every commit, which hits PyPI to install the package.
I prefer to avoid hitting PyPI every time, so I like to use the GitHub Actions cache. My usual pattern for that looks like this:
https://github.com/simonw/datasette/blob/5890a20c374fb0812d88c9b0ef26a838bfa06c76/.github/workflows/test-pyodide.yml#L16-L20
Then a separate command that runs `pip install ...` will benefit from that cache.
Are you OK to make that change?","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1661860507,GitHub Action to lint Python code with ruff,
https://github.com/simonw/datasette/pull/2056#issuecomment-1506177857,https://api.github.com/repos/simonw/datasette/issues/2056,1506177857,IC_kwDOBm6k_c5ZxnNB,9599,simonw,2023-04-13T01:18:18Z,2023-04-13T01:18:18Z,OWNER,"Cool - and now https://github.com/simonw/datasette/pull/2056/files is showing me those inline annotations:
","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1661860507,GitHub Action to lint Python code with ruff,
https://github.com/simonw/datasette/pull/2056#issuecomment-1506177115,https://api.github.com/repos/simonw/datasette/issues/2056,1506177115,IC_kwDOBm6k_c5ZxnBb,9599,simonw,2023-04-13T01:17:16Z,2023-04-13T01:17:16Z,OWNER,"Here are the failures: https://github.com/simonw/datasette/actions/runs/4684460653/jobs/8300630794?pr=2056
","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1661860507,GitHub Action to lint Python code with ruff,
https://github.com/simonw/datasette/pull/2056#issuecomment-1506175208,https://api.github.com/repos/simonw/datasette/issues/2056,1506175208,IC_kwDOBm6k_c5Zxmjo,9599,simonw,2023-04-13T01:14:13Z,2023-04-13T01:14:13Z,OWNER,https://github.com/simonw/datasette/actions/runs/4664796647/jobs/8300596121?pr=2056 it's pretty fast - that finished in 9s.,"{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1661860507,GitHub Action to lint Python code with ruff,
https://github.com/simonw/datasette/issues/2059#issuecomment-1506174353,https://api.github.com/repos/simonw/datasette/issues/2059,1506174353,IC_kwDOBm6k_c5ZxmWR,9599,simonw,2023-04-13T01:13:00Z,2023-04-13T01:13:00Z,OWNER,"Can you provide a URL to an example, and/or a screenshot of this? Is it a browser warning or is it a warning from Heroku itself?","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1665053646,"""Deceptive site ahead"" alert on Heroku deployment",
https://github.com/simonw/datasette/issues/2058#issuecomment-1504426792,https://api.github.com/repos/simonw/datasette/issues/2058,1504426792,IC_kwDOBm6k_c5Zq7so,9599,simonw,2023-04-12T02:02:42Z,2023-04-12T02:02:42Z,OWNER,"I tightened up the benchmark (it was measuring the time taken to create the tables too) and got this:
![image](https://user-images.githubusercontent.com/9599/231328328-85ca35ac-a11b-46f4-b132-dae367103570.png)
","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1663399821,"500 ""attempt to write a readonly database"" error caused by ""PRAGMA schema_version""",
https://github.com/simonw/datasette/issues/2058#issuecomment-1504328395,https://api.github.com/repos/simonw/datasette/issues/2058,1504328395,IC_kwDOBm6k_c5ZqjrL,9599,simonw,2023-04-12T00:28:38Z,2023-04-12T00:28:38Z,OWNER,"Here's a much better chart, which shows that MD5 performance unsurprisingly gets worse as the number of tables increases while `schema_version` remains constant:
![image](https://user-images.githubusercontent.com/9599/231316778-513bd99f-5ea4-495c-b86d-c572a7106369.png)
","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1663399821,"500 ""attempt to write a readonly database"" error caused by ""PRAGMA schema_version""",
https://github.com/simonw/datasette/issues/2058#issuecomment-1504315697,https://api.github.com/repos/simonw/datasette/issues/2058,1504315697,IC_kwDOBm6k_c5Zqgkx,9599,simonw,2023-04-12T00:16:22Z,2023-04-12T00:27:12Z,OWNER,"I got ChatGPT (code execution alpha) to run a micro-benchmark for me. This was the conclusion:
> The benchmark using `PRAGMA schema_version` is approximately 1.36 times faster than the benchmark using `hashlib.md5` for the case with 100 tables. For the case with 200 tables, the benchmark using `PRAGMA schema_version` is approximately 2.33 times faster than the benchmark using `hashlib.md5`.
Here's the chart it drew me:
![image](https://user-images.githubusercontent.com/9599/231315366-3a12b6d3-08d7-419d-a1fd-36eb24da0d85.png)
(It's a pretty rubbish chart though, it only took measurements at 100 and 200 and drew a line between the two, I should have told it to measure every 10 and plot that)
And the full transcript: https://gist.github.com/simonw/2fc46effbfbe49e6de0bcfdc9e31b235
The benchmark looks good enough on first glance that I don't feel the need to be more thorough with it. `PRAGMA schema_version` is faster, but not so fast that I feel like the MD5 hack is worth worrying about too much.
I'm tempted to add something to the `/-/versions` page that tries to identify if this is a problem or not though.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1663399821,"500 ""attempt to write a readonly database"" error caused by ""PRAGMA schema_version""",
https://github.com/simonw/datasette/issues/2058#issuecomment-1504298448,https://api.github.com/repos/simonw/datasette/issues/2058,1504298448,IC_kwDOBm6k_c5ZqcXQ,9599,simonw,2023-04-12T00:04:01Z,2023-04-12T00:04:01Z,OWNER,"Here's a potential workaround: when I store the schema versions, I could also score an MD5 hash of the full schema (`select group_concat(sql) from sqlite_master`). When I read the schema version with `PRAGMA schema_version` I could catch that exception and, if I see it, I could calculate that MD5 hash again as a fallback and use that to determine if the schema has changed instead.
The performance overhead of this needs investigating - how much more expensive is `md5(... that SQL query result)` compared to just `PRAGMA schema_version`, especially on a database with a lot of tables?","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1663399821,"500 ""attempt to write a readonly database"" error caused by ""PRAGMA schema_version""",
https://github.com/simonw/datasette/issues/2058#issuecomment-1504295345,https://api.github.com/repos/simonw/datasette/issues/2058,1504295345,IC_kwDOBm6k_c5Zqbmx,9599,simonw,2023-04-12T00:01:42Z,2023-04-12T00:02:26Z,OWNER,"Here's the relevant code:
https://github.com/simonw/datasette/blob/5890a20c374fb0812d88c9b0ef26a838bfa06c76/datasette/app.py#L421-L437
This function is called on almost every request (everything that subclasses `BaseView` at least - need to remember that for the refactor in #2053 etc).
https://github.com/simonw/datasette/blob/5890a20c374fb0812d88c9b0ef26a838bfa06c76/datasette/views/base.py#L101-L103
It uses `PRAGMA schema_version` as a cheap way to determine if the schema has changed, in which case it needs to refresh the internal schema tables.
This was already the cause of a subtle bug here:
- #1231
","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1663399821,"500 ""attempt to write a readonly database"" error caused by ""PRAGMA schema_version""",
https://github.com/simonw/datasette/issues/2058#issuecomment-1504292145,https://api.github.com/repos/simonw/datasette/issues/2058,1504292145,IC_kwDOBm6k_c5Zqa0x,9599,simonw,2023-04-11T23:58:59Z,2023-04-11T23:58:59Z,OWNER,Asked on the SQLite Forum if anyone has seen this before: https://sqlite.org/forum/forumpost/793a2ed75b,"{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1663399821,"500 ""attempt to write a readonly database"" error caused by ""PRAGMA schema_version""",
https://github.com/simonw/datasette/issues/2058#issuecomment-1504291892,https://api.github.com/repos/simonw/datasette/issues/2058,1504291892,IC_kwDOBm6k_c5Zqaw0,9599,simonw,2023-04-11T23:58:45Z,2023-04-11T23:58:45Z,OWNER,"I thought it might relate to the ""defensive mode"" issue described here:
- https://github.com/simonw/sqlite-utils/issues/235
But I have since determined that the Datasette official Docker image does NOT run anything in defensive mode, so I don't think it's related to that.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1663399821,"500 ""attempt to write a readonly database"" error caused by ""PRAGMA schema_version""",
https://github.com/simonw/sqlite-utils/issues/235#issuecomment-1504288134,https://api.github.com/repos/simonw/sqlite-utils/issues/235,1504288134,IC_kwDOCGYnMM5ZqZ2G,9599,simonw,2023-04-11T23:55:06Z,2023-04-12T03:34:32Z,OWNER,"Also checked the official Datasette Docker image - I had to run that in Codespaces because it doesn't currently work on my M2 Mac:
```
codespace@codespaces-112c61:/workspaces/sqlite-utils$ docker pull datasetteproject/datasette
Using default tag: latest
...
codespace@codespaces-112c61:/workspaces/sqlite-utils$ docker run -it datasetteproject/datasette /
bin/bash
root@75ba34f501ec:/# python
Python 3.11.0 (main, Dec 6 2022, 13:31:55) [GCC 10.2.1 20210110] on linux
Type ""help"", ""copyright"", ""credits"" or ""license"" for more information.
>>> import sqlite3
.executescript(""""""
PRAGMA writable_schema = 1;
UPDATE sqlite_master SET sql = 'CREATE TABLE [foos] (id integer primary key)';
PRAGMA writable_schema = 0;
"""""")>>> db = sqlite3.connect("":memory:"")
>>> db.executescript(""""""
... PRAGMA writable_schema = 1;
... UPDATE sqlite_master SET sql = 'CREATE TABLE [foos] (id integer primary key)';
... PRAGMA writable_schema = 0;
... """""")
>>>
```
So that confirms that the official image also has a Python with a SQLite that's not in defensive mode.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",810618495,Extract columns cannot create foreign key relation: sqlite3.OperationalError: table sqlite_master may not be modified,
https://github.com/simonw/sqlite-utils/issues/235#issuecomment-1504245029,https://api.github.com/repos/simonw/sqlite-utils/issues/235,1504245029,IC_kwDOCGYnMM5ZqPUl,9599,simonw,2023-04-11T23:13:41Z,2023-04-11T23:14:39Z,OWNER,"I also tested this against the current `ubuntu:latest` Docker image (on an M2 Mac), in Python 3.10 and 3.11:
```
docker run -it ubuntu:latest /bin/bash
```
Then in the container:
```
apt-get update
apt-get install python3
python3
# pasted in the above recipe
apt install software-properties-common
add-apt-repository ppa:deadsnakes/ppa
apt install python3.11
python3.11
# pasted it in again
```
In both cases the Python code did not raise an exception, which suggests that on Ubuntu those two Python versions do not have the defensive mode set.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",810618495,Extract columns cannot create foreign key relation: sqlite3.OperationalError: table sqlite_master may not be modified,
https://github.com/simonw/datasette/issues/2057#issuecomment-1503838640,https://api.github.com/repos/simonw/datasette/issues/2057,1503838640,IC_kwDOBm6k_c5ZosGw,9599,simonw,2023-04-11T17:48:23Z,2023-04-11T17:48:23Z,OWNER,"> This looks wrong to me - I would expect something like `is_directory()` not `is_file()` for telling if `static/` is a directory.
I was right about that:
```pycon
>>> importlib.resources.files('datasette_graphql')
PosixPath('/Users/simon/.local/share/virtualenvs/datasette-big-local-6Yn-280V/lib/python3.11/site-packages/datasette_graphql')
>>> importlib.resources.files('datasette_graphql').joinpath(""static"")
PosixPath('/Users/simon/.local/share/virtualenvs/datasette-big-local-6Yn-280V/lib/python3.11/site-packages/datasette_graphql/static')
>>> p = importlib.resources.files('datasette_graphql').joinpath(""static"")
>>> p
PosixPath('/Users/simon/.local/share/virtualenvs/datasette-big-local-6Yn-280V/lib/python3.11/site-packages/datasette_graphql/static')
>>> p.is_
p.is_absolute() p.is_char_device() p.is_fifo() p.is_mount() p.is_reserved() p.is_symlink()
p.is_block_device() p.is_dir() p.is_file() p.is_relative_to( p.is_socket()
>>> p.is_dir()
True
>>> p.is_file()
False
```","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1662951875,DeprecationWarning: pkg_resources is deprecated as an API,
https://github.com/simonw/datasette/issues/2057#issuecomment-1503833906,https://api.github.com/repos/simonw/datasette/issues/2057,1503833906,IC_kwDOBm6k_c5Zoq8y,9599,simonw,2023-04-11T17:44:16Z,2023-04-11T17:45:45Z,OWNER,"Another prompt:
> How to fix this:
>
> `pkg_resources.get_distribution(package).version`
Response:
```python
import importlib.metadata
# Get the version number of the specified package
package_version = importlib.metadata.version(package)
```
That seems to work:
```pycon
>>> import importlib.metadata
>>> importlib.metadata.version(""datasette"")
'0.64.2'
>>> importlib.metadata.version(""pluggy"")
'1.0.0'
>>> importlib.metadata.version(""not-a-package"")
...
importlib.metadata.PackageNotFoundError: No package metadata was found for not-a-package
```
","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1662951875,DeprecationWarning: pkg_resources is deprecated as an API,
https://github.com/simonw/datasette/issues/2057#issuecomment-1503832422,https://api.github.com/repos/simonw/datasette/issues/2057,1503832422,IC_kwDOBm6k_c5Zoqlm,9599,simonw,2023-04-11T17:42:57Z,2023-04-11T17:46:42Z,OWNER,"I ran this prompt against ChatGPT with the Browsing alpha:
> ```python
> if pkg_resources.resource_isdir(plugin.__name__, ""static""):
> static_path = pkg_resources.resource_filename(
> plugin.__name__, ""static""
> )
> if pkg_resources.resource_isdir(plugin.__name__, ""templates""):
> templates_path = pkg_resources.resource_filename(
> plugin.__name__, ""templates""
> )
> ```
> This code gives a deprecation warning in Python 3.11 - fix it
It looked up the fix for me:
And suggested:
```python
import importlib.resources
# Replace pkg_resources.resource_isdir with importlib.resources.files().is_file()
if importlib.resources.files(plugin.__name__).joinpath(""static"").is_file():
static_path = importlib.resources.as_file(
importlib.resources.files(plugin.__name__).joinpath(""static"")
)
if importlib.resources.files(plugin.__name__).joinpath(""templates"").is_file():
templates_path = importlib.resources.as_file(
importlib.resources.files(plugin.__name__).joinpath(""templates"")
)
```
This looks wrong to me - I would expect something like `is_directory()` not `is_file()` for telling if `static/` is a directory.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1662951875,DeprecationWarning: pkg_resources is deprecated as an API,
https://github.com/dogsheep/swarm-to-sqlite/issues/13#issuecomment-1502629404,https://api.github.com/repos/dogsheep/swarm-to-sqlite/issues/13,1502629404,IC_kwDODD6af85ZkE4c,9599,simonw,2023-04-11T03:15:47Z,2023-04-11T03:46:17Z,MEMBER,"I think `swarm-to-sqlite` needs to avoid this error, maybe by setting up foreign keys in another way - or even by skipping foreign keys entirely on databases that don't support this kind of operation.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1373210675,fails before generating views. ERR: table sqlite_master may not be modified,
https://github.com/dogsheep/swarm-to-sqlite/issues/13#issuecomment-1502629219,https://api.github.com/repos/dogsheep/swarm-to-sqlite/issues/13,1502629219,IC_kwDODD6af85ZkE1j,9599,simonw,2023-04-11T03:15:26Z,2023-04-11T03:15:26Z,MEMBER,"OK, I figured this out. Unfortunately it's an error that occurs on Python versions that have defensive mode turned on, and it doesn't look like there's a way to turn that mode off. See notes above.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1373210675,fails before generating views. ERR: table sqlite_master may not be modified,
https://github.com/simonw/sqlite-utils/issues/235#issuecomment-1502559442,https://api.github.com/repos/simonw/sqlite-utils/issues/235,1502559442,IC_kwDOCGYnMM5ZjzzS,9599,simonw,2023-04-11T01:32:30Z,2023-04-11T01:33:27Z,OWNER,"This seems to work:
```python
import sqlite3
db = sqlite3.connect("":memory:"")
db.executescript(""""""
PRAGMA writable_schema = 1;
UPDATE sqlite_master SET sql = 'CREATE TABLE [foos] (id integer primary key)';
PRAGMA writable_schema = 0;
"""""")
```
It succeeds on my Python 3.11 and raises the following exception on my broken Python 3.9:
```
sqlite3.OperationalError: table sqlite_master may not be modified
```
Removing the `PRAGMA writable_schema = 1;` causes the same exception to be raised on both Pythons.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",810618495,Extract columns cannot create foreign key relation: sqlite3.OperationalError: table sqlite_master may not be modified,
https://github.com/simonw/sqlite-utils/issues/235#issuecomment-1502557629,https://api.github.com/repos/simonw/sqlite-utils/issues/235,1502557629,IC_kwDOCGYnMM5ZjzW9,9599,simonw,2023-04-11T01:30:12Z,2023-04-11T01:30:12Z,OWNER,"I'll ask on the SQLite forum if it's possible to toggle that mode on and off using regular SQL. My hunch is that it isn't.
In which case `sqlite-utils` should at least know how to catch this error and display a much more readable error message, maybe with a link to further documentation.
A utility function that can detect this mode would be really useful too. I'd probably have to do a test that tries to modify `sqlite_master` on a new in-memory database to catch if it's possible or not.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",810618495,Extract columns cannot create foreign key relation: sqlite3.OperationalError: table sqlite_master may not be modified,
https://github.com/simonw/sqlite-utils/issues/235#issuecomment-1502556111,https://api.github.com/repos/simonw/sqlite-utils/issues/235,1502556111,IC_kwDOCGYnMM5Zjy_P,9599,simonw,2023-04-11T01:28:41Z,2023-04-11T01:28:41Z,OWNER,"Investigating this one now.
The `sqlite-utils` test suite passes without errors on my Python 3.11.2 installation... but it fails with this error on a Python 3.9.6 installation.
In the broken version's virtual environment directory I ran this:
```
cat pyvenv.cfg
home = /Applications/Xcode.app/Contents/Developer/usr/bin
implementation = CPython
version_info = 3.9.6.final.0
virtualenv = 20.17.1
include-system-site-packages = false
base-prefix = /Applications/Xcode.app/Contents/Developer/Library/Frameworks/Python3.framework/Versions/3.9
base-exec-prefix = /Applications/Xcode.app/Contents/Developer/Library/Frameworks/Python3.framework/Versions/3.9
base-executable = /Applications/Xcode.app/Contents/Developer/usr/bin/python3
```
So it looks like the Xcode `python3` has ""defensive"" mode turned on for SQLite.
As far as I can tell there's no way to turn it OFF again in Python.
My virtual environment that DOES work has this:
```
home = /opt/homebrew/opt/python@3.11/bin
implementation = CPython
version_info = 3.11.2.final.0
virtualenv = 20.17.1
include-system-site-packages = false
base-prefix = /opt/homebrew/opt/python@3.11/Frameworks/Python.framework/Versions/3.11
base-exec-prefix = /opt/homebrew/opt/python@3.11/Frameworks/Python.framework/Versions/3.11
base-executable = /opt/homebrew/opt/python@3.11/bin/python3.11
```
So the Python 3.11 I installed through Homebrew doesn't exhibit this bug.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",810618495,Extract columns cannot create foreign key relation: sqlite3.OperationalError: table sqlite_master may not be modified,
https://github.com/dogsheep/swarm-to-sqlite/issues/13#issuecomment-1502546045,https://api.github.com/repos/dogsheep/swarm-to-sqlite/issues/13,1502546045,IC_kwDODD6af85Zjwh9,9599,simonw,2023-04-11T01:14:50Z,2023-04-11T01:14:50Z,MEMBER,"Related:
- https://github.com/simonw/sqlite-utils/issues/235","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1373210675,fails before generating views. ERR: table sqlite_master may not be modified,
https://github.com/dogsheep/swarm-to-sqlite/issues/13#issuecomment-1502543165,https://api.github.com/repos/dogsheep/swarm-to-sqlite/issues/13,1502543165,IC_kwDODD6af85Zjv09,9599,simonw,2023-04-11T01:10:36Z,2023-04-11T01:11:47Z,MEMBER,"I just had that error myself on macOS while running the tests:
```
ERROR tests/test_save_checkin.py::test_tables - sqlite3.OperationalError: table sqlite_master may not be modified
ERROR tests/test_save_checkin.py::test_venue - sqlite3.OperationalError: table sqlite_master may not be modified
ERROR tests/test_save_checkin.py::test_event - sqlite3.OperationalError: table sqlite_master may not be modified
ERROR tests/test_save_checkin.py::test_sticker - sqlite3.OperationalError: table sqlite_master may not be modified
ERROR tests/test_save_checkin.py::test_likes - sqlite3.OperationalError: table sqlite_master may not be modified
ERROR tests/test_save_checkin.py::test_with_ - sqlite3.OperationalError: table sqlite_master may not be modified
ERROR tests/test_save_checkin.py::test_users - sqlite3.OperationalError: table sqlite_master may not be modified
ERROR tests/test_save_checkin.py::test_photos - sqlite3.OperationalError: table sqlite_master may not be modified
ERROR tests/test_save_checkin.py::test_posts - sqlite3.OperationalError: table sqlite_master may not be modified
ERROR tests/test_save_checkin.py::test_view - sqlite3.OperationalError: table sqlite_master may not be modified
```
`pytest --pdb` shows it happening in the bit that adds foreign keys:
```
> /Users/simon/.local/share/virtualenvs/swarm-to-sqlite-daPW7yIJ/lib/python3.9/site-packages/sqlite_utils/db.py(1096)add_foreign_keys()
-> cursor.execute(
(Pdb) list
1096 >> cursor.execute(
1097 ""UPDATE sqlite_master SET sql = ? WHERE name = ?"",
1098 (new_sql, table_name),
1099 )
1100 cursor.execute(""PRAGMA schema_version = %d"" % (schema_version + 1))
1101 -> cursor.execute(""PRAGMA writable_schema = 0"")
1102 # Have to VACUUM outside the transaction to ensure .foreign_keys property
1103 # can see the newly created foreign key.
1104 self.vacuum()
```","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1373210675,fails before generating views. ERR: table sqlite_master may not be modified,
https://github.com/simonw/sqlite-utils/pull/531#issuecomment-1501017004,https://api.github.com/repos/simonw/sqlite-utils/issues/531,1501017004,IC_kwDOCGYnMM5Zd7Os,25778,eyeseast,2023-04-09T01:49:43Z,2023-04-09T01:49:43Z,CONTRIBUTOR,I'm going to close this in favor of #536. Will try a cleaner approach to custom paths once that one is merge.,"{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1620164673,Add paths for homebrew on Apple silicon,
https://github.com/simonw/sqlite-utils/pull/536#issuecomment-1500893216,https://api.github.com/repos/simonw/sqlite-utils/issues/536,1500893216,IC_kwDOCGYnMM5ZddAg,22429695,codecov[bot],2023-04-08T13:35:42Z,2023-04-08T13:35:42Z,NONE,"## [Codecov](https://codecov.io/gh/simonw/sqlite-utils/pull/536?src=pr&el=h1&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison) Report
Patch and project coverage have no change.
> Comparison is base [(`c0251cc`)](https://codecov.io/gh/simonw/sqlite-utils/commit/c0251cc9271260de73b4227859a51fab9b4cb745?el=desc&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison) 96.25% compared to head [(`cea05dc`)](https://codecov.io/gh/simonw/sqlite-utils/pull/536?src=pr&el=desc&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison) 96.25%.
Additional details and impacted files
```diff
@@ Coverage Diff @@
## main #536 +/- ##
=======================================
Coverage 96.25% 96.25%
=======================================
Files 6 6
Lines 2671 2671
=======================================
Hits 2571 2571
Misses 100 100
```
| [Impacted Files](https://codecov.io/gh/simonw/sqlite-utils/pull/536?src=pr&el=tree&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison) | Coverage Δ | |
|---|---|---|
| [sqlite\_utils/utils.py](https://codecov.io/gh/simonw/sqlite-utils/pull/536?src=pr&el=tree&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison#diff-c3FsaXRlX3V0aWxzL3V0aWxzLnB5) | `95.13% <ø> (ø)` | |
Help us with your feedback. Take ten seconds to tell us [how you rate us](https://about.codecov.io/nps?utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison). Have a feature suggestion? [Share it here.](https://app.codecov.io/gh/feedback/?utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison)
[:umbrella: View full report in Codecov by Sentry](https://codecov.io/gh/simonw/sqlite-utils/pull/536?src=pr&el=continue&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison).
:loudspeaker: Do you have feedback about the report comment? [Let us know in this issue](https://about.codecov.io/codecov-pr-comment-feedback/?utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison).
","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1659525418,Add paths for homebrew on Apple silicon,
https://github.com/simonw/datasette/issues/2054#issuecomment-1500608101,https://api.github.com/repos/simonw/datasette/issues/2054,1500608101,IC_kwDOBm6k_c5ZcXZl,9599,simonw,2023-04-07T20:14:38Z,2023-04-07T20:14:38Z,OWNER,"Ooh that one's really interesting - very different from the others:
```ruby
# app.rb
require ""roda""
class App < Roda
route do |r|
r.root do
""Home page""
end
r.on ""pages"" do
r.get "":slug"" do |slug|
""Page: #{slug}""
end
end
r.on ""news"" do
r.get "":yyyy/:mm/:dd"" do |yyyy, mm, dd|
""News for #{yyyy}/#{mm}/#{dd}""
end
end
end
end
# config.ru
require_relative ""app""
run App.freeze.app
```","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1657861026,"Make detailed notes on how table, query and row views work right now",
https://github.com/simonw/datasette/issues/2054#issuecomment-1499797384,https://api.github.com/repos/simonw/datasette/issues/2054,1499797384,IC_kwDOBm6k_c5ZZReI,6213,dsisnero,2023-04-07T00:46:50Z,2023-04-07T00:46:50Z,NONE,you should have a look at Roda written in ruby . ,"{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1657861026,"Make detailed notes on how table, query and row views work right now",
https://github.com/simonw/datasette/issues/2054#issuecomment-1499604822,https://api.github.com/repos/simonw/datasette/issues/2054,1499604822,IC_kwDOBm6k_c5ZYidW,9599,simonw,2023-04-06T20:48:19Z,2023-04-06T20:48:55Z,OWNER,"I actually quite like that. I could even use `@classmethod` and have utility methods defined on that class that both `get()` and `post()` could call.
The crucial rule here is NO INSTANCE STATE - that's what makes routing to classes particularly damaging, and encourages code that's hard to maintain.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1657861026,"Make detailed notes on how table, query and row views work right now",
https://github.com/simonw/datasette/issues/2054#issuecomment-1499604066,https://api.github.com/repos/simonw/datasette/issues/2054,1499604066,IC_kwDOBm6k_c5ZYiRi,9599,simonw,2023-04-06T20:47:30Z,2023-04-06T20:47:30Z,OWNER,"I'm contemplating a new approach: using a class with static methods. Something like this:
```python
class TableView(MethodRouter):
@staticmethod
async def get(request):
return Response.text(""GET"")
@staticmethod
async def post(request):
return Response.text(""POST"")
```
So effectively the class is just there to bundle together verb implementations, and to provide a `route(request)` method which knows how to dispatch them to the right place.
It can offer default HEAD and OPTIONS methods too.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1657861026,"Make detailed notes on how table, query and row views work right now",
https://github.com/simonw/datasette/issues/2054#issuecomment-1499596941,https://api.github.com/repos/simonw/datasette/issues/2054,1499596941,IC_kwDOBm6k_c5ZYgiN,9599,simonw,2023-04-06T20:39:35Z,2023-04-06T20:39:35Z,OWNER,"I think there are two main approaches:
- Map path to a function, that function then behaves differently on GET/POST/etc
- Map method AND path to a function - the `app.get('/example')` v.s. `app.post('/example')` ones
The decorator approach is calling out to me a bit now.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1657861026,"Make detailed notes on how table, query and row views work right now",
https://github.com/simonw/datasette/issues/2054#issuecomment-1499530921,https://api.github.com/repos/simonw/datasette/issues/2054,1499530921,IC_kwDOBm6k_c5ZYQap,9599,simonw,2023-04-06T19:41:52Z,2023-04-06T19:42:09Z,OWNER,Turned this into a TIL: https://til.simonwillison.net/gpt3/gpt4-api-design,"{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1657861026,"Make detailed notes on how table, query and row views work right now",
https://github.com/simonw/datasette/issues/2054#issuecomment-1499491258,https://api.github.com/repos/simonw/datasette/issues/2054,1499491258,IC_kwDOBm6k_c5ZYGu6,9599,simonw,2023-04-06T19:00:16Z,2023-04-06T20:40:16Z,OWNER,"I asked GPT-4 to compare URL routing based on path and verb approaches in different languages and frameworks and spit out some examples. Full transcript here: https://gist.github.com/simonw/fa2379b97420404a81b0fcdb4db79657
Initial prompt:
> Show me code examples of different web frameworks in Python and JavaScript and Go illustrating how HTTP routing works - in particular the problem of mapping an incoming HTTP request to some code based on both the URL path and the HTTP verb
>
> Don't show installation instructions, just get straight to the code snippets
Flask:
```python
from flask import Flask
app = Flask(__name__)
@app.route('/example', methods=['GET'])
def get_example():
return ""This is a GET request.""
@app.route('/example', methods=['POST'])
def post_example():
return ""This is a POST request.""
if __name__ == '__main__':
app.run()
```
Express:
```javascript
const express = require('express');
const app = express();
app.get('/example', (req, res) => {
res.send('This is a GET request.');
});
app.post('/example', (req, res) => {
res.send('This is a POST request.');
});
app.listen(3000, () => {
console.log('Server is running on port 3000');
});
```
Gin:
```go
package main
import (
""github.com/gin-gonic/gin""
)
func main() {
r := gin.Default()
r.GET(""/example"", func(c *gin.Context) {
c.String(200, ""This is a GET request."")
})
r.POST(""/example"", func(c *gin.Context) {
c.String(200, ""This is a POST request."")
})
r.Run()
}
```
Actix-web:
```rust
use actix_web::{web, App, HttpResponse, HttpServer, Responder};
async fn get_example() -> impl Responder {
HttpResponse::Ok().body(""This is a GET request."")
}
async fn post_example() -> impl Responder {
HttpResponse::Ok().body(""This is a POST request."")
}
#[actix_web::main]
async fn main() -> std::io::Result<()> {
HttpServer::new(|| {
App::new()
.route(""/example"", web::get().to(get_example))
.route(""/example"", web::post().to(post_example))
})
.bind(""127.0.0.1:8080"")?
.run()
.await
}
```
Koa:
```javascript
const Koa = require('koa');
const Router = require('koa-router');
const app = new Koa();
const router = new Router();
router.get('/example', (ctx) => {
ctx.body = 'This is a GET request.';
});
router.post('/example', (ctx) => {
ctx.body = 'This is a POST request.';
});
app.use(router.routes());
app.use(router.allowedMethods());
app.listen(3000, () => {
console.log('Server is running on port 3000');
});
```
Django:
```python
from django.http import HttpResponse
from django.views import View
class ExampleView(View):
def get(self, request):
return HttpResponse(""This is a GET request."")
def post(self, request):
return HttpResponse(""This is a POST request."")
```
```python
from django.urls import path
from .views import ExampleView
urlpatterns = [
path('example/', ExampleView.as_view(), name='example'),
]
```
Rocket:
```rust
#![feature(proc_macro_hygiene, decl_macro)]
#[macro_use] extern crate rocket;
use rocket::response::content;
#[get(""/example"")]
fn get_example() -> content::Plain<&'static str> {
content::Plain(""This is a GET request."")
}
#[post(""/example"")]
fn post_example() -> content::Plain<&'static str> {
content::Plain(""This is a POST request."")
}
#[launch]
fn rocket() -> _ {
rocket::build().mount(""/"", routes![get_example, post_example])
}
```
Elixir/Phoenix:
```elixir
defmodule ExampleAppWeb.Router do
use ExampleAppWeb, :router
pipeline :api do
plug :accepts, [""json""]
end
scope ""/api"", ExampleAppWeb do
pipe_through :api
get ""/example"", ExampleController, :get_example
post ""/example"", ExampleController, :post_example
end
end
```
Bottle:
```python
from bottle import Bottle, run
app = Bottle()
@app.route('/example', method='GET')
def get_example():
return ""This is a GET request.""
@app.route('/example', method='POST')
def post_example():
return ""This is a POST request.""
if __name__ == '__main__':
run(app, host='localhost', port=8080)
```
FastAPI:
```python
from fastapi import FastAPI
app = FastAPI()
@app.get(""/example"")
async def get_example():
return {""message"": ""This is a GET request.""}
@app.post(""/example"")
async def post_example():
return {""message"": ""This is a POST request.""}
if __name__ == ""__main__"":
import uvicorn
uvicorn.run(app, host=""127.0.0.1"", port=8000)
```","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1657861026,"Make detailed notes on how table, query and row views work right now",
https://github.com/simonw/datasette/issues/2054#issuecomment-1499467703,https://api.github.com/repos/simonw/datasette/issues/2054,1499467703,IC_kwDOBm6k_c5ZYA-3,9599,simonw,2023-04-06T18:37:22Z,2023-04-06T18:57:22Z,OWNER,"I've been hoping to move entirely away from class-based views, but now I'm wondering if that's the right decision given the need to support HTTP verbs.
It is cleaner to have a class that has methods for each verb, or to have a single function that can behave differently depending on the verb?
Or should I have a mechanism for dispatching to separate functions based on the verbs that isn't implemented in a base class?
The trouble with using base classes is that I've already shown that they tempt me to put logic in weird places, which makes code harder to modify later on.
The thing here is that the ONLY thing I want to use the base class for is as an HTTP verb switcher - which makes me doubt that I should risk taking on the other temptations of having a base class.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1657861026,"Make detailed notes on how table, query and row views work right now",
https://github.com/simonw/datasette/issues/2054#issuecomment-1499465648,https://api.github.com/repos/simonw/datasette/issues/2054,1499465648,IC_kwDOBm6k_c5ZYAew,9599,simonw,2023-04-06T18:35:03Z,2023-04-06T18:35:03Z,OWNER,"There are actually five classes that subclass `DataView`:
https://github.com/simonw/datasette/blob/8b9d7fdbd8de7e74414cc29e3005382669a812dc/datasette/views/row.py#L16
https://github.com/simonw/datasette/blob/8b9d7fdbd8de7e74414cc29e3005382669a812dc/datasette/views/database.py#L34
https://github.com/simonw/datasette/blob/8b9d7fdbd8de7e74414cc29e3005382669a812dc/datasette/views/database.py#L172
https://github.com/simonw/datasette/blob/8b9d7fdbd8de7e74414cc29e3005382669a812dc/datasette/views/database.py#L215
https://github.com/simonw/datasette/blob/8b9d7fdbd8de7e74414cc29e3005382669a812dc/datasette/views/table.py#L72
I don't think `DatabaseView` and `DatabaseDownload` should have subclassed that at all, since they don't return a table of data.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1657861026,"Make detailed notes on how table, query and row views work right now",
https://github.com/simonw/datasette/issues/2054#issuecomment-1499462324,https://api.github.com/repos/simonw/datasette/issues/2054,1499462324,IC_kwDOBm6k_c5ZX_q0,9599,simonw,2023-04-06T18:31:56Z,2023-04-06T18:31:56Z,OWNER,"The `DataView` class does a LOT of work - mostly involving CSV responses.
https://github.com/simonw/datasette/blob/8b9d7fdbd8de7e74414cc29e3005382669a812dc/datasette/views/base.py#L160-L544
It has a `redirect()` method with some complex logic and CORS handling:
https://github.com/simonw/datasette/blob/8b9d7fdbd8de7e74414cc29e3005382669a812dc/datasette/views/base.py#L163-L172
It uses this method a lot, which has to be over-ridden in the `TableView` and `RowView` and `QueryView` subclasses:
https://github.com/simonw/datasette/blob/8b9d7fdbd8de7e74414cc29e3005382669a812dc/datasette/views/base.py#L174-L175
This method:
https://github.com/simonw/datasette/blob/8b9d7fdbd8de7e74414cc29e3005382669a812dc/datasette/views/base.py#L180
Is the bulk of the complexity, because it knows how to both turn a list of SQLite rows into a CSV file but also knows how to call `.data()` repeatedly with different pagination arguments in order to stream CSV back for a large table.
The `async def get()` method for GET requests is also very complicated. It mainly handles format stuff - knowing how to render HTML v.s. JSON v.s. CSV v.s. other formats specified using this plugin hook: https://docs.datasette.io/en/1.0a2/plugin_hooks.html#register-output-renderer-datasette
Plus it catches interrupted queries and returns a special error page for those (and other error messages too): https://github.com/simonw/datasette/blob/8b9d7fdbd8de7e74414cc29e3005382669a812dc/datasette/views/base.py#L381-L408
It adds the time taken to execute the queries: https://github.com/simonw/datasette/blob/8b9d7fdbd8de7e74414cc29e3005382669a812dc/datasette/views/base.py#L410-L411","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1657861026,"Make detailed notes on how table, query and row views work right now",
https://github.com/simonw/datasette/issues/2054#issuecomment-1499457291,https://api.github.com/repos/simonw/datasette/issues/2054,1499457291,IC_kwDOBm6k_c5ZX-cL,9599,simonw,2023-04-06T18:26:45Z,2023-04-06T18:26:45Z,OWNER,"
Here's `BaseView`:
https://github.com/simonw/datasette/blob/8b9d7fdbd8de7e74414cc29e3005382669a812dc/datasette/views/base.py#L56-L145
It has methods for the `options`, `get`, `post`, `delete`, `put`, `patch` and `head` HTTP verbs, most defaulting to returinng a 405 Method not allowed message in plain text or JSON, depending on this check:
https://github.com/simonw/datasette/blob/8b9d7fdbd8de7e74414cc29e3005382669a812dc/datasette/views/base.py#L71-L81
Also adds CORS headers to anything if CORS mode is on:
https://github.com/simonw/datasette/blob/8b9d7fdbd8de7e74414cc29e3005382669a812dc/datasette/views/base.py#L106-L107
And adds the `database_color` (weirdly) and the `select_templates` variables to the template context:
https://github.com/simonw/datasette/blob/8b9d7fdbd8de7e74414cc29e3005382669a812dc/datasette/views/base.py#L112-L122
And has special code for setting the `Link: ...; rel=""alternate""` HTTP header:
https://github.com/simonw/datasette/blob/8b9d7fdbd8de7e74414cc29e3005382669a812dc/datasette/views/base.py#L124-L136","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1657861026,"Make detailed notes on how table, query and row views work right now",
https://github.com/simonw/datasette/issues/2054#issuecomment-1499457201,https://api.github.com/repos/simonw/datasette/issues/2054,1499457201,IC_kwDOBm6k_c5ZX-ax,9599,simonw,2023-04-06T18:26:39Z,2023-04-06T18:26:39Z,OWNER,These classes - `TableView` and `RowView` and `QueryView` - all subclass `DataView` which subclasses` BaseView`.,"{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1657861026,"Make detailed notes on how table, query and row views work right now",
https://github.com/simonw/datasette/issues/2054#issuecomment-1499452122,https://api.github.com/repos/simonw/datasette/issues/2054,1499452122,IC_kwDOBm6k_c5ZX9La,9599,simonw,2023-04-06T18:21:51Z,2023-04-06T18:21:51Z,OWNER,"I'm going to make notes against the code in the most recent alpha release, ignoring the recent work I did to refactor `TableView`.
https://github.com/simonw/datasette/tree/1.0a2/datasette/views","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1657861026,"Make detailed notes on how table, query and row views work right now",
https://github.com/simonw/datasette/pull/2053#issuecomment-1498279469,https://api.github.com/repos/simonw/datasette/issues/2053,1498279469,IC_kwDOBm6k_c5ZTe4t,9599,simonw,2023-04-05T23:28:53Z,2023-04-05T23:28:53Z,OWNER,"Table errors page currently does this:
```json
{
""ok"": false,
""error"": ""no such column: blah"",
""status"": 400,
""title"": ""Invalid SQL""
}
```","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1656432059,WIP new JSON for queries,
https://github.com/simonw/datasette/issues/2049#issuecomment-1498275621,https://api.github.com/repos/simonw/datasette/issues/2049,1498275621,IC_kwDOBm6k_c5ZTd8l,9599,simonw,2023-04-05T23:23:01Z,2023-04-05T23:23:01Z,OWNER,"The default representation here can be even smaller.
For rows it's this:
```json
{
""ok"": true,
""next"": ""d,v"",
""rows"": [...]
}
```
For SQL queries I'm considering this:
```json
{
""ok"": true,
""rows"": [...]
}
```
I considered adding `""sql""` and `""params""` too, but on further thought those would be entirely a waste of bytes the majority of the time. If a user wants those they can request them with an `?_extra=query` as seen here:
http://localhost:8001/content/releases.json?_size=0&_extra=query
```json
{
""ok"": true,
""next"": null,
""query"": {
""sql"": ""select html_url, id, author, node_id, tag_name, target_commitish, name, draft, prerelease, created_at, published_at, body, repo, reactions, mentions_count from releases order by id limit 1"",
""params"": {}
},
""rows"": []
}
```","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1646734246,Custom SQL queries should use new JSON ?_extra= format,
https://github.com/dogsheep/github-to-sqlite/issues/79#issuecomment-1498167714,https://api.github.com/repos/dogsheep/github-to-sqlite/issues/79,1498167714,IC_kwDODFdgUs5ZTDmi,9599,simonw,2023-04-05T21:12:55Z,2023-04-05T21:12:55Z,MEMBER,"It's a rate limiting problem: https://github.com/dogsheep/github-to-sqlite/actions/runs/4622674009/jobs/8175633155
```
File ""/home/runner/work/github-to-sqlite/github-to-sqlite/github_to_sqlite/cli.py"", line 407, in commits
utils.save_commits(db, commits, repo_full[""id""])
File ""/home/runner/work/github-to-sqlite/github-to-sqlite/github_to_sqlite/utils.py"", line 635, in save_commits
for commit in commits:
File ""/home/runner/work/github-to-sqlite/github-to-sqlite/github_to_sqlite/utils.py"", line 417, in fetch_commits
for commits in paginate(url, headers):
File ""/home/runner/work/github-to-sqlite/github-to-sqlite/github_to_sqlite/utils.py"", line 478, in paginate
raise GitHubError.from_response(response)
github_to_sqlite.utils.GitHubError: ('API rate limit exceeded for user ID 9599.', 403)
Error: Process completed with exit code 1.
```","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1570375808,Deploy demo job is failing due to rate limit,
https://github.com/simonw/sqlite-utils/issues/235#issuecomment-1495780111,https://api.github.com/repos/simonw/sqlite-utils/issues/235,1495780111,IC_kwDOCGYnMM5ZJ8sP,19786848,Thomascountz,2023-04-04T11:09:56Z,2023-04-04T11:13:40Z,NONE,"@wpears' workaround also worked for me, but also required me to manually set `PRAGMA writable_schema`.
```sql
PRAGMA writable_schema = 1;
UPDATE sqlite_master SET sql = 'CREATE TABLE [foos] (...)'
PRAGMA writable_schema = 0;
```
```shell
$ python --version
Python 3.11.2
$ sqlite3 --version
3.41.2 2023-03-22 11:56:21 0d1fc92f94cb6b76bffe3ec34d69cffde2924203304e8ffc4155597af0c191da
$ sqlite-utils --version
sqlite-utils, version 3.30
```","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",810618495,Extract columns cannot create foreign key relation: sqlite3.OperationalError: table sqlite_master may not be modified,
https://github.com/dogsheep/apple-notes-to-sqlite/issues/6#issuecomment-1493442956,https://api.github.com/repos/dogsheep/apple-notes-to-sqlite/issues/6,1493442956,IC_kwDOJHON9s5ZBCGM,14314871,amlestin,2023-04-02T21:20:43Z,2023-04-02T21:25:37Z,NONE,"I'm experiencing something similar. My apostrophes (') turn into (’) and the output is truncated. Hoping to debug next weekend
","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1617602868,Character encoding problem,
https://github.com/simonw/sqlite-utils/issues/265#issuecomment-1493052396,https://api.github.com/repos/simonw/sqlite-utils/issues/265,1493052396,IC_kwDOCGYnMM5Y_ivs,154364,dracos,2023-04-01T17:27:18Z,2023-04-01T17:27:18Z,NONE,"`enable_fts` is a function in datasette, not in this repo, which doesn't do any escaping of search terms. It sounds like from https://docs.datasette.io/en/stable/full_text_search.html#advanced-sqlite-search-queries you might want to enable raw searching, as otherwise it's disabled and everything is escaped by default.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",907795562,Using enable_fts before search term,
https://github.com/simonw/sqlite-utils/issues/159#issuecomment-1493051222,https://api.github.com/repos/simonw/sqlite-utils/issues/159,1493051222,IC_kwDOCGYnMM5Y_idW,154364,dracos,2023-04-01T17:21:05Z,2023-04-01T17:21:05Z,NONE,"In a related issue, nearly a year later I just stumbled across this again, as I wondered why none of my rebuild-fts were rebuilding. It looks like: disable_fts in db.py commits; enable_fts partly commits except the last step (due to executescript committing a pending transaction); rebuild_fts won't commit unless manually done as above with e.g. a context manager.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",702386948,.delete_where() does not auto-commit (unlike .insert() or .upsert()),
https://github.com/simonw/sqlite-utils/issues/235#issuecomment-1492777509,https://api.github.com/repos/simonw/sqlite-utils/issues/235,1492777509,IC_kwDOCGYnMM5Y-fol,9020979,hydrosquall,2023-04-01T01:31:48Z,2023-04-01T01:31:48Z,NONE,"My current workaround is to use this library from a python script instead of as a CLI tool.
This lets me set the foreign key constraint at table creation time, instead of trying to modify an existing table. [docs](https://sqlite-utils.datasette.io/en/stable/python-api.html#specifying-foreign-keys)
I found this [stackoverflow helpful](https://stackoverflow.com/a/1884841/5129731), as it explained that Sqlite doesn't support modifying existing tables directly.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",810618495,Extract columns cannot create foreign key relation: sqlite3.OperationalError: table sqlite_master may not be modified,
https://github.com/simonw/datasette/issues/2050#issuecomment-1492387771,https://api.github.com/repos/simonw/datasette/issues/2050,1492387771,IC_kwDOBm6k_c5Y9Ae7,9599,simonw,2023-03-31T17:59:48Z,2023-03-31T17:59:48Z,OWNER,"Some of the extras from the table view make sense here. A few custom ones make sense too - including this already existing but undocumented one:
https://github.com/simonw/datasette/blob/5890a20c374fb0812d88c9b0ef26a838bfa06c76/datasette/views/row.py#L86-L89","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1649791661,Row page JSON should use new ?_extra= format,
https://github.com/simonw/datasette/issues/2035#issuecomment-1492206593,https://api.github.com/repos/simonw/datasette/issues/2035,1492206593,IC_kwDOBm6k_c5Y8UQB,9599,simonw,2023-03-31T16:09:08Z,2023-03-31T16:09:08Z,OWNER,"I could ship this as part of:
- #2049 ","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1615692818,Potential feature: special support for `?a=1&a=2` on the query page,
https://github.com/simonw/datasette/issues/1989#issuecomment-1491357104,https://api.github.com/repos/simonw/datasette/issues/1989,1491357104,IC_kwDOBm6k_c5Y5E2w,1231935,xavdid,2023-03-31T06:17:23Z,2023-03-31T06:18:05Z,NONE,"I'm running into a similar use case as pax above- I made a `nice` view that just has the data I'm interested in (which doesn't include the `id`, since it's not important in this case). But, by excluding `id` from the view, I can't do fts queries against it because the view has no `id` field to tie to `rowid`:
```
ERROR: conn=,
sql = 'select time, text, permalink, num_children from nice where id in
(select rowid from items_fts where items_fts match :search) limit 101',
params = {'search': 'whatever'}: no such column: id
```
It works fine when I include `id` in my view, but now my `nice` view is cluttered up. Would be great to hide it permanently in the `config.json`.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1531991339,Suggestion: Hiding columns,
https://github.com/simonw/datasette/issues/2049#issuecomment-1489530555,https://api.github.com/repos/simonw/datasette/issues/2049,1489530555,IC_kwDOBm6k_c5YyG67,9599,simonw,2023-03-30T00:51:27Z,2023-03-30T00:51:27Z,OWNER,"I'd really like to refactor all of the extras functions into a `datasette/extras.py` module. The table ones currently rely a LOT on local variables in scope though, so I would need to rewrite those such that EVERY dependency they take is passed to `asyncinject` explicitly.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1646734246,Custom SQL queries should use new JSON ?_extra= format,
https://github.com/simonw/datasette/issues/2049#issuecomment-1489530037,https://api.github.com/repos/simonw/datasette/issues/2049,1489530037,IC_kwDOBm6k_c5YyGy1,9599,simonw,2023-03-30T00:50:30Z,2023-03-30T00:50:30Z,OWNER,"Two things to consider here: `_shape=` and `_extra=`.
Most of the shapes make sense, with the exception of `?_shape=object` since we don't know which column we would use as a primary key.
Looking at the (undocumented) list of extras from the table view, here are the ones I think make sense:
- `count` - YES
- `facet_results` - no
- `facets_timed_out` - no
- `suggested_facets` - no
- `human_description_en` - no
- `next_url` - MAYBE
- `columns` - YES
- `primary_keys` - no
- `display_columns` - YES
- `display_rows` - YES
- `debug` - YES?
- `request` - YES
- `query` - YES
- `metadata` - YES
- `extras` - YES
- `database` - YES
- `table` - no
- `database_color` - no?
- `table_actions` - no
- `filters` - no
- `renderers` - YES
- `custom_table_templates` - no
- `sorted_facet_results` - no
- `table_definition` - no
- `view_definition` - no
- `is_view` - no
- `private` - YES
- `expandable_columns` - no
- `form_hidden_args` - no
Just the YES ones:
- `count` - this is new
- `columns`
- `display_columns`
- `display_rows`
- `debug`
- `request`
- `query`
- `metadata`
- `extras`
- `database`
- `renderers`
- `private`
The `count` one is interesting - I think I can provide that by optionally running `select count(*) from (inner query)`. It's a new feature though and not one I want to expose on the HTML view since it could result in poor performance - but having it as an extra that API users can opt into may make sense.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1646734246,Custom SQL queries should use new JSON ?_extra= format,
https://github.com/simonw/datasette/issues/2049#issuecomment-1489526501,https://api.github.com/repos/simonw/datasette/issues/2049,1489526501,IC_kwDOBm6k_c5YyF7l,9599,simonw,2023-03-30T00:44:05Z,2023-03-30T00:44:05Z,OWNER,"As part of this I should be able to figure out which bits of the new code I wrote for the table view should actually be shared with the query view. That stuff is mostly going to be from this commit: https://github.com/simonw/datasette/commit/d97e82df3c8a3f2e97038d7080167be9bb74a68d
Here's the existing QueryView class I need to replace:
https://github.com/simonw/datasette/blob/4c1e277edbd783d06840d3f9b20bf00783478ce4/datasette/views/database.py#L215-L532","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1646734246,Custom SQL queries should use new JSON ?_extra= format,
https://github.com/simonw/datasette/pull/2034#issuecomment-1489306198,https://api.github.com/repos/simonw/datasette/issues/2034,1489306198,IC_kwDOBm6k_c5YxQJW,4370201,wenhoujx,2023-03-29T20:56:19Z,2023-03-29T20:56:19Z,NONE,@simonw any idea why the test coverage check fails? ,"{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1613974869,remove an unused `app` var in cli.py,
https://github.com/dogsheep/hacker-news-to-sqlite/pull/6#issuecomment-1489110168,https://api.github.com/repos/dogsheep/hacker-news-to-sqlite/issues/6,1489110168,IC_kwDODtX3eM5YwgSY,1231935,xavdid,2023-03-29T18:36:16Z,2023-03-29T18:36:16Z,NONE,@simonw can you take a look when you have a chance?,"{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1641117021,Add permalink virtual field to items table,
https://github.com/simonw/datasette/issues/262#issuecomment-1488010837,https://api.github.com/repos/simonw/datasette/issues/262,1488010837,IC_kwDOBm6k_c5YsT5V,9599,simonw,2023-03-29T06:22:21Z,2023-03-29T06:22:21Z,OWNER,I need to get the arbitrary query page to return the same format. It likely won't have nearly as many extras.,"{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",323658641,Add ?_extra= mechanism for requesting extra properties in JSON,
https://github.com/simonw/datasette/pull/2014#issuecomment-1487999503,https://api.github.com/repos/simonw/datasette/issues/2014,1487999503,IC_kwDOBm6k_c5YsRIP,49699333,dependabot[bot],2023-03-29T06:09:11Z,2023-03-29T06:09:11Z,CONTRIBUTOR,Superseded by #2047.,"{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1566081801,Bump black from 22.12.0 to 23.1.0,
https://github.com/simonw/datasette/pull/2014#issuecomment-1487998788,https://api.github.com/repos/simonw/datasette/issues/2014,1487998788,IC_kwDOBm6k_c5YsQ9E,9599,simonw,2023-03-29T06:08:23Z,2023-03-29T06:08:23Z,OWNER,@dependabot recreate,"{""total_count"": 1, ""+1"": 1, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1566081801,Bump black from 22.12.0 to 23.1.0,
https://github.com/simonw/datasette/pull/2043#issuecomment-1486944644,https://api.github.com/repos/simonw/datasette/issues/2043,1486944644,IC_kwDOBm6k_c5YoPmE,49699333,dependabot[bot],2023-03-28T13:58:20Z,2023-03-28T13:58:20Z,CONTRIBUTOR,Superseded by #2046.,"{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1639446870,Bump furo from 2022.12.7 to 2023.3.23,
https://github.com/simonw/sqlite-utils/issues/388#issuecomment-1484277416,https://api.github.com/repos/simonw/sqlite-utils/issues/388,1484277416,IC_kwDOCGYnMM5YeEao,9599,simonw,2023-03-26T23:43:12Z,2023-03-26T23:43:12Z,OWNER,Fixed: https://sqlite-utils.datasette.io/en/latest/reference.html,"{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1114543475,Link to stable docs from older versions,
https://github.com/simonw/datasette/issues/1608#issuecomment-1484276946,https://api.github.com/repos/simonw/datasette/issues/1608,1484276946,IC_kwDOBm6k_c5YeETS,9599,simonw,2023-03-26T23:41:11Z,2023-03-26T23:41:11Z,OWNER,It's working again now: https://docs.datasette.io/en/latest/sql_queries.html,"{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1109808154,Documentation should clarify /stable/ vs /latest/,
https://github.com/simonw/sqlite-utils/issues/388#issuecomment-1484276302,https://api.github.com/repos/simonw/sqlite-utils/issues/388,1484276302,IC_kwDOCGYnMM5YeEJO,9599,simonw,2023-03-26T23:39:27Z,2023-03-26T23:39:27Z,OWNER,"Actually final Datasette fix was:
```html+jinja
{% block scripts %}
{{ super() }}
{% endblock %}
```","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1114543475,Link to stable docs from older versions,
https://github.com/simonw/datasette/issues/1608#issuecomment-1484274796,https://api.github.com/repos/simonw/datasette/issues/1608,1484274796,IC_kwDOBm6k_c5YeDxs,9599,simonw,2023-03-26T23:38:18Z,2023-03-26T23:38:18Z,OWNER,"ChatGPT prompt:
> ```
> jQuery(function ($) {
> // Show banner linking to /stable/ if this is a /latest/ page
> if (!/\/latest\//.test(location.pathname)) {
> return;
> }
> var stableUrl = location.pathname.replace(""/latest/"", ""/stable/"");
> // Check it's not a 404
> fetch(stableUrl, { method: ""HEAD"" }).then((response) => {
> if (response.status == 200) {
> var warning = $(
> `
>
Note
>
> This documentation covers the development version of Datasette.
']]
FAILED tests/test_table_html.py::test_metadata_sort - AttributeError: 'NoneType' object has no attribute 'string'
FAILED tests/test_table_html.py::test_metadata_sort_desc - AttributeError: 'NoneType' object has no attribute 'string'
FAILED tests/test_table_html.py::test_facet_more_links[5-/fixtures/facetable?_facet=_neighborhood-2-True-/fixtures/facetable?_facet=_neighborhood&_facet_size=max] - assert 0 == 2
FAILED tests/test_table_html.py::test_facet_more_links[5-/fixtures/facetable?_facet=_neighborhood&_facet_size=50-5-True-/fixtures/facetable?_facet=_neighborhood&_facet_size=max] - assert 0 == 5
FAILED tests/test_table_html.py::test_facet_total - assert 500 == 200
```
Deduped that's 30 tests:
```
FAILED tests/test_table_html.py::test_add_filter_redirects
FAILED tests/test_table_html.py::test_binary_data_display_in_table
FAILED tests/test_table_html.py::test_compound_primary_key_with_foreign_key_references
FAILED tests/test_table_html.py::test_csv_json_export_links_include_labels_if_foreign_keys
FAILED tests/test_table_html.py::test_empty_search_parameter_gets_removed
FAILED tests/test_table_html.py::test_existing_filter_redirects
FAILED tests/test_table_html.py::test_extra_where_clauses
FAILED tests/test_table_html.py::test_facet_more_links
FAILED tests/test_table_html.py::test_facet_total
FAILED tests/test_table_html.py::test_facets_persist_through_filter_form
FAILED tests/test_table_html.py::test_metadata_sort
FAILED tests/test_table_html.py::test_metadata_sort_desc
FAILED tests/test_table_html.py::test_next_does_not_persist_in_hidden_field
FAILED tests/test_table_html.py::test_other_hidden_form_fields
FAILED tests/test_table_html.py::test_reflected_hidden_form_fields
FAILED tests/test_table_html.py::test_rowid_sortable_no_primary_key
FAILED tests/test_table_html.py::test_search_and_sort_fields_not_duplicated
FAILED tests/test_table_html.py::test_searchable_view_persists_fts_table
FAILED tests/test_table_html.py::test_sort_by_desc_redirects
FAILED tests/test_table_html.py::test_sort_links
FAILED tests/test_table_html.py::test_table_csv_json_export_interface
FAILED tests/test_table_html.py::test_table_html_compound_primary_key
FAILED tests/test_table_html.py::test_table_html_disable_foreign_key_links_with_labels
FAILED tests/test_table_html.py::test_table_html_filter_form_column_options
FAILED tests/test_table_html.py::test_table_html_filter_form_still_shows_nocol_columns
FAILED tests/test_table_html.py::test_table_html_foreign_key_custom_label_column
FAILED tests/test_table_html.py::test_table_html_foreign_key_links
FAILED tests/test_table_html.py::test_table_html_no_primary_key
FAILED tests/test_table_html.py::test_table_html_simple_primary_key
FAILED tests/test_table_html.py::test_view_html
```","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1551694938,?_extra= support (draft),
https://github.com/simonw/datasette/pull/1999#issuecomment-1475074025,https://api.github.com/repos/simonw/datasette/issues/1999,1475074025,IC_kwDOBm6k_c5X69fp,9599,simonw,2023-03-19T02:14:28Z,2023-03-19T02:14:51Z,OWNER,"I had to replicate quite a bit of this logic from `base.py`:
https://github.com/simonw/datasette/blob/56b0758a5fbf85d01ff80a40c9b028469d7bb65f/datasette/views/base.py#L526-L544
I should refactor this when I move the canned / arbitrary query views away from that base class too.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1551694938,?_extra= support (draft),
https://github.com/simonw/datasette/pull/1999#issuecomment-1475016834,https://api.github.com/repos/simonw/datasette/issues/1999,1475016834,IC_kwDOBm6k_c5X6viC,9599,simonw,2023-03-18T22:30:31Z,2023-03-18T22:30:31Z,OWNER,"`test_paginate_using_link_header` will be tricky.
The reason the tests are failing is that `json_renderer()` attempts to populate the `link` header using `data[""next_url""]` - but that's not present unless `?_extra=next_url` has been passed:
https://github.com/simonw/datasette/blob/2f38479dcc81f11a4362f4e28511fa88afc34e61/datasette/renderer.py#L101-L102
But I can only rely on `next` being present, not `next_url`.
I thought I could maybe assemble the `link` header using `next`, by turning that into a `next_url` link - but there's some custom logic which kicks in for pagination against SQL views (offset/limit pagination) to calculate the `next_url` which isn't easily replicable at the `json_renderer()` layer, in the `_next_value_and_url()` utility function:
https://github.com/simonw/datasette/blob/2f38479dcc81f11a4362f4e28511fa88afc34e61/datasette/views/table.py#L2275-L2282
","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1551694938,?_extra= support (draft),
https://github.com/simonw/datasette/pull/1999#issuecomment-1475003292,https://api.github.com/repos/simonw/datasette/issues/1999,1475003292,IC_kwDOBm6k_c5X6sOc,9599,simonw,2023-03-18T21:46:20Z,2023-03-18T21:46:20Z,OWNER,"Now 25 failures in `test_table_api.py`:
```
FAILED tests/test_table_api.py::test_expand_labels - assert {'2': {'pk': 2, 'created': '2019-01-14 08:00:00', 'planet_int': 1, 'on_earth': 1, 'state': 'CA', '_city_id': 1, '_neighborhood': 'Dogpatch', 'tags': '[""tag1"", ""tag3""]', 'complex_array'...
FAILED tests/test_table_api.py::test_expand_label - AssertionError: assert {'1': {'pk': '1', 'foreign_key_with_label': '1', 'foreign_key_with_blank_label': '3', 'foreign_key_with_no_label': '1', 'foreign_key_compound_pk1': 'a', 'foreign_key_co...
FAILED tests/test_table_api.py::test_ttl_parameter[/fixtures/facetable.json-max-age=5] - KeyError: 'Cache-Control'
FAILED tests/test_table_api.py::test_ttl_parameter[/fixtures/facetable.json?_ttl=invalid-max-age=5] - KeyError: 'Cache-Control'
FAILED tests/test_table_api.py::test_ttl_parameter[/fixtures/facetable.json?_ttl=10-max-age=10] - KeyError: 'Cache-Control'
FAILED tests/test_table_api.py::test_ttl_parameter[/fixtures/facetable.json?_ttl=0-no-cache] - KeyError: 'Cache-Control'
FAILED tests/test_table_api.py::test_infinity_returned_as_null - AssertionError: assert [{'rowid': 1, 'value': inf}, {'rowid': 2, 'value': -inf}, {'rowid': 3, 'value': 1.5}] == [{'rowid': 1, 'value': None}, {'rowid': 2, 'value': None}, {'rowid': 3, 'value'...
FAILED tests/test_table_api.py::test_null_and_compound_foreign_keys_are_not_expanded - AssertionError: assert [{'pk': '1', 'foreign_key_with_label': '1', 'foreign_key_with_blank_label': '3', 'foreign_key_with_no_label': '1', 'foreign_key_compound_pk1': 'a', 'foreign_key_compoun...
FAILED tests/test_table_api.py::test_binary_data_in_json[/fixtures/binary_data.json?_shape=array-expected_json0-None] - assert [{'rowid': 1, 'data': ""b'\\x15\\x1c\\x02\\xc7\\xad\\x05\\xfe'""}, {'rowid': 2, 'data': ""b'\\x15\\x1c\\x03\\xc7\\xad\\x05\\xfe'""}, {'rowid': 3, 'data': None}] == [{'rowid': 1, 'data': {'...
FAILED tests/test_table_api.py::test_binary_data_in_json[/fixtures/binary_data.json?_shape=array&_nl=on-None-{""rowid"": 1, ""data"": {""$base64"": true, ""encoded"": ""FRwCx60F/g==""}}\n{""rowid"": 2, ""data"": {""$base64"": true, ""encoded"": ""FRwDx60F/g==""}}\n{""rowid"": 3, ""data"": null}] - assert '{""ok"": false, ""error"": ""Object of type bytes is not JSON serializable"", ""status"": 500, ""title"": null}' == '{""rowid"": 1, ""data"": {""$base64"": true, ""encoded"": ""FRwCx60F/g==""}}\n{""rowid""...
FAILED tests/test_table_api.py::test_paginate_using_link_header[] - assert 1 == 21
FAILED tests/test_table_api.py::test_paginate_using_link_header[?_shape=arrays] - assert 1 == 21
FAILED tests/test_table_api.py::test_paginate_using_link_header[?_shape=arrayfirst] - assert 400 == 200
FAILED tests/test_table_api.py::test_paginate_using_link_header[?_shape=object] - assert 1 == 21
FAILED tests/test_table_api.py::test_paginate_using_link_header[?_shape=objects] - assert 1 == 21
FAILED tests/test_table_api.py::test_paginate_using_link_header[?_shape=array] - assert 1 == 21
FAILED tests/test_table_api.py::test_paginate_using_link_header[?_shape=array&_nl=on] - assert 1 == 21
FAILED tests/test_table_api.py::test_col_nocol[/fixtures/facetable.json?_col=created-expected_columns0] - KeyError: 'columns'
FAILED tests/test_table_api.py::test_col_nocol[/fixtures/facetable.json?_nocol=created-expected_columns1] - KeyError: 'columns'
FAILED tests/test_table_api.py::test_col_nocol[/fixtures/facetable.json?_col=state&_col=created-expected_columns2] - KeyError: 'columns'
FAILED tests/test_table_api.py::test_col_nocol[/fixtures/facetable.json?_col=state&_col=state-expected_columns3] - KeyError: 'columns'
FAILED tests/test_table_api.py::test_col_nocol[/fixtures/facetable.json?_col=state&_col=created&_nocol=created-expected_columns4] - KeyError: 'columns'
FAILED tests/test_table_api.py::test_col_nocol[/fixtures/facetable.json?_nocol=state&_facet=state-expected_columns5] - KeyError: 'columns'
FAILED tests/test_table_api.py::test_col_nocol[/fixtures/simple_view.json?_nocol=content-expected_columns6] - KeyError: 'columns'
FAILED tests/test_table_api.py::test_col_nocol[/fixtures/simple_view.json?_col=content-expected_columns7] - KeyError: 'columns'
============================================================================= 25 failed, 86 passed, 1 xfailed in 7.18s =============================================================================
```","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1551694938,?_extra= support (draft),
https://github.com/simonw/datasette/pull/1999#issuecomment-1474704790,https://api.github.com/repos/simonw/datasette/issues/1999,1474704790,IC_kwDOBm6k_c5X5jWW,9599,simonw,2023-03-18T04:52:59Z,2023-03-18T04:52:59Z,OWNER,"Here are the next set of tests to get passing:
```
% pytest tests/test_table_api.py
```
```
FAILED tests/test_table_api.py::test_facets[/fixtures/facetable.json?_facet=state&_facet=_city_id-expected_facet_results0] - KeyError: 'name'
FAILED tests/test_table_api.py::test_facets[/fixtures/facetable.json?_facet=state&_facet=_city_id&state=MI-expected_facet_results1] - KeyError: 'name'
FAILED tests/test_table_api.py::test_facets[/fixtures/facetable.json?_facet=planet_int-expected_facet_results2] - KeyError: 'name'
FAILED tests/test_table_api.py::test_facets[/fixtures/facetable.json?_facet=planet_int&planet_int=1-expected_facet_results3] - KeyError: 'name'
FAILED tests/test_table_api.py::test_suggested_facets - KeyError: 'suggested_facets'
FAILED tests/test_table_api.py::test_allow_facet_off - KeyError: 'suggested_facets'
FAILED tests/test_table_api.py::test_suggest_facets_off - KeyError: 'suggested_facets'
FAILED tests/test_table_api.py::test_nofacet[True] - KeyError: 'suggested_facets'
FAILED tests/test_table_api.py::test_nofacet[False] - KeyError: 'suggested_facets'
FAILED tests/test_table_api.py::test_nosuggest[True] - KeyError: 'suggested_facets'
FAILED tests/test_table_api.py::test_nosuggest[False] - KeyError: 'suggested_facets'
FAILED tests/test_table_api.py::test_nocount[True-None] - KeyError: 'count'
FAILED tests/test_table_api.py::test_nocount[False-15] - KeyError: 'count'
FAILED tests/test_table_api.py::test_expand_labels - AssertionError: assert {'13': {'_cit...:00:00', ...}} == {'13': {'_cit...:00:00', ...}}
FAILED tests/test_table_api.py::test_expand_label - AssertionError: assert {'1': {'forei...l': '1', ...}} == {'1': {'forei...': '1'}, ...}}
FAILED tests/test_table_api.py::test_ttl_parameter[/fixtures/facetable.json-max-age=5] - KeyError: 'Cache-Control'
FAILED tests/test_table_api.py::test_ttl_parameter[/fixtures/facetable.json?_ttl=invalid-max-age=5] - KeyError: 'Cache-Control'
FAILED tests/test_table_api.py::test_ttl_parameter[/fixtures/facetable.json?_ttl=10-max-age=10] - KeyError: 'Cache-Control'
FAILED tests/test_table_api.py::test_ttl_parameter[/fixtures/facetable.json?_ttl=0-no-cache] - KeyError: 'Cache-Control'
FAILED tests/test_table_api.py::test_infinity_returned_as_null - AssertionError: assert [{'rowid': 1,...'value': 1.5}] == [{'rowid': 1,...'value': 1.5}]
FAILED tests/test_table_api.py::test_null_and_compound_foreign_keys_are_not_expanded - AssertionError: assert [{'foreign_ke...': None, ...}] == [{'foreign_ke...': None, ...}]
FAILED tests/test_table_api.py::test_binary_data_in_json[/fixtures/binary_data.json?_shape=array-expected_json0-None] - assert [{'data': ""b'..., 'rowid': 3}] == [{'data': {'$..., 'rowid': 3}]
FAILED tests/test_table_api.py::test_binary_data_in_json[/fixtures/binary_data.json?_shape=array&_nl=on-None-{""rowid"": 1, ""data"": {""$base64"": true, ""encoded"": ""FRwCx60F/g==""}}\n{""rowid"": 2, ""data"": {""$base64"": true, ""encoded"": ""FRwDx60F/g==""}}\n{""rowid"": 3, ""data"": null}] - assert '{""ok"": false...title"": null}' == '{""rowid"": 1,...""data"": null}'
FAILED tests/test_table_api.py::test_paginate_using_link_header[] - assert 1 == 21
FAILED tests/test_table_api.py::test_paginate_using_link_header[?_shape=arrays] - assert 1 == 21
FAILED tests/test_table_api.py::test_paginate_using_link_header[?_shape=arrayfirst] - assert 400 == 200
FAILED tests/test_table_api.py::test_paginate_using_link_header[?_shape=object] - assert 1 == 21
FAILED tests/test_table_api.py::test_paginate_using_link_header[?_shape=objects] - assert 1 == 21
FAILED tests/test_table_api.py::test_paginate_using_link_header[?_shape=array] - assert 1 == 21
FAILED tests/test_table_api.py::test_paginate_using_link_header[?_shape=array&_nl=on] - assert 1 == 21
FAILED tests/test_table_api.py::test_col_nocol[/fixtures/facetable.json?_col=created-expected_columns0] - KeyError: 'columns'
FAILED tests/test_table_api.py::test_col_nocol[/fixtures/facetable.json?_nocol=created-expected_columns1] - KeyError: 'columns'
FAILED tests/test_table_api.py::test_col_nocol[/fixtures/facetable.json?_col=state&_col=created-expected_columns2] - KeyError: 'columns'
FAILED tests/test_table_api.py::test_col_nocol[/fixtures/facetable.json?_col=state&_col=state-expected_columns3] - KeyError: 'columns'
FAILED tests/test_table_api.py::test_col_nocol[/fixtures/facetable.json?_col=state&_col=created&_nocol=created-expected_columns4] - KeyError: 'columns'
FAILED tests/test_table_api.py::test_col_nocol[/fixtures/facetable.json?_nocol=state&_facet=state-expected_columns5] - KeyError: 'columns'
FAILED tests/test_table_api.py::test_col_nocol[/fixtures/simple_view.json?_nocol=content-expected_columns6] - KeyError: 'columns'
FAILED tests/test_table_api.py::test_col_nocol[/fixtures/simple_view.json?_col=content-expected_columns7] - KeyError: 'columns'
============================================================================= 38 failed, 73 passed, 1 xfailed in 7.25s =============================================================================
```
","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1551694938,?_extra= support (draft),
https://github.com/dogsheep/apple-notes-to-sqlite/issues/8#issuecomment-1468898285,https://api.github.com/repos/dogsheep/apple-notes-to-sqlite/issues/8,1468898285,IC_kwDOJHON9s5XjZvt,41546558,RhetTbull,2023-03-14T22:00:21Z,2023-03-14T22:00:21Z,NONE,"Well that's embarrassing. I made a fork using macnotesapp and it's actually slower. This is because the Scripting Bridge sometimes fails to return the folder and thus macnotesapp resorts to AppleScript in this situation. The repeated AppleScript calls on a large library are slower than your ""slurp it all in"" approach. I've got some ideas about how to improve this--will make another attempt if I can fix the issues.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1617823309,Increase performance using macnotesapp,
https://github.com/simonw/sqlite-utils/pull/531#issuecomment-1465315726,https://api.github.com/repos/simonw/sqlite-utils/issues/531,1465315726,IC_kwDOCGYnMM5XVvGO,25778,eyeseast,2023-03-12T22:21:56Z,2023-03-12T22:21:56Z,CONTRIBUTOR,"Exactly, that's what I was running into. On my M2 MacBook, SpatiaLite ends up in what is -- for the moment -- a non-standard location, so even when I passed in the location with `--load-extension`, I still hit an error on `create-spatial-index`.
What I learned doing this originally is that SQLite needs to load the extension for each connection, even if all the SpatiaLite stuff is already in the database. So that's why `init_spatialite()` gets called again.
Here's the code where I hit the error: https://github.com/eyeseast/boston-parcels/blob/main/Makefile#L30 It works using this branch.
I'm not attached to this solution if you can think of something better. And I'm not sure, TBH, my test would actually catch what I'm after here.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1620164673,Add paths for homebrew on Apple silicon,
https://github.com/simonw/sqlite-utils/issues/533#issuecomment-1465303378,https://api.github.com/repos/simonw/sqlite-utils/issues/533,1465303378,IC_kwDOCGYnMM5XVsFS,9599,simonw,2023-03-12T21:24:04Z,2023-03-12T21:24:04Z,OWNER,"Upgraded to Sphinx 6 locally and got the same error:
```
% just docs
Cogging README.md
Cogging docs/changelog.rst
Cogging docs/cli-reference.rst
Cogging docs/cli.rst
Cogging docs/contributing.rst
Cogging docs/index.rst
Cogging docs/installation.rst
Cogging docs/python-api.rst
Cogging docs/reference.rst
sphinx-autobuild -a -b html ""."" ""_build"" --watch ../sqlite_utils
[sphinx-autobuild] > sphinx-build -b html -a /Users/simon/Dropbox/Development/sqlite-utils/docs /Users/simon/Dropbox/Development/sqlite-utils/docs/_build
Running Sphinx v6.1.3
loading pickled environment... failed
failed: Can't get attribute '_stable_repr_object' on
building [mo]: all of 0 po files
writing output...
building [html]: all source files
updating environment: [new config] 8 added, 0 changed, 0 removed
reading sources... [ 12%] changelog
Exception occurred:
File ""/Users/simon/.local/share/virtualenvs/sqlite-utils-C4Ilevlm/lib/python3.11/site-packages/sphinx/ext/extlinks.py"", line 103, in role
title = caption % part
~~~~~~~~^~~~~~
TypeError: not all arguments converted during string formatting
The full traceback has been saved in /var/folders/x6/31xf1vxj0nn9mxqq8z0mmcfw0000gn/T/sphinx-err-1ey36c1n.log, if you want to report the issue to the developers.
```","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1620516340,ReadTheDocs error: not all arguments converted during string formatting,
https://github.com/simonw/sqlite-utils/issues/533#issuecomment-1465302936,https://api.github.com/repos/simonw/sqlite-utils/issues/533,1465302936,IC_kwDOCGYnMM5XVr-Y,9599,simonw,2023-03-12T21:22:09Z,2023-03-12T21:22:09Z,OWNER,"Could be the same problem as:
- https://github.com/simonw/datasette/issues/1972
Which I fixed in https://github.com/simonw/datasette/commit/3af313e165215696af899e772f47bf7c27873ae3","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1620516340,ReadTheDocs error: not all arguments converted during string formatting,
https://github.com/simonw/sqlite-utils/pull/531#issuecomment-1465302343,https://api.github.com/repos/simonw/sqlite-utils/issues/531,1465302343,IC_kwDOCGYnMM5XVr1H,9599,simonw,2023-03-12T21:19:13Z,2023-03-12T21:19:13Z,OWNER,"Aah, I think I see why you wrote it like that.
The problem is that `init_spatialite()` does other stuff too:
https://github.com/simonw/sqlite-utils/blob/fc221f9b62ed8624b1d2098e564f525c84497969/sqlite_utils/db.py#L1161-L1171
So it needs to be able to load the SpatiaLite extension from the correct place, and THEN run `select InitSpatialMetadata()` to configure the database, if needed.
So the problem you're trying to solve here is to let people optionally pass in the path to SpatiaLite if it's not one of the ones that are searched by default.
","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1620164673,Add paths for homebrew on Apple silicon,
https://github.com/simonw/datasette/issues/236#issuecomment-1465208436,https://api.github.com/repos/simonw/datasette/issues/236,1465208436,IC_kwDOBm6k_c5XVU50,545193,sopel,2023-03-12T14:04:15Z,2023-03-12T14:04:15Z,NONE,"I keep coming back to this in search for the related exploration, so I'll just link it now:
@simonw has meanwhile researched _how to deploy Datasette to AWS Lambda using function URLs and Mangum_ via https://github.com/simonw/public-notes/issues/6 and concluded _that's everything I need to know in order to build a datasette-publish-lambda plugin_.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",317001500,datasette publish lambda plugin,
https://github.com/simonw/sqlite-utils/pull/531#issuecomment-1465038901,https://api.github.com/repos/simonw/sqlite-utils/issues/531,1465038901,IC_kwDOCGYnMM5XUrg1,22429695,codecov[bot],2023-03-11T22:29:19Z,2023-04-07T18:19:49Z,NONE,"## [Codecov](https://codecov.io/gh/simonw/sqlite-utils/pull/531?src=pr&el=h1&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison) Report
Patch coverage: **`100.00`**% and project coverage change: **`+0.03`** :tada:
> Comparison is base [(`c0251cc`)](https://codecov.io/gh/simonw/sqlite-utils/commit/c0251cc9271260de73b4227859a51fab9b4cb745?el=desc&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison) 96.25% compared to head [(`afdf618`)](https://codecov.io/gh/simonw/sqlite-utils/pull/531?src=pr&el=desc&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison) 96.29%.
Additional details and impacted files
```diff
@@ Coverage Diff @@
## main #531 +/- ##
==========================================
+ Coverage 96.25% 96.29% +0.03%
==========================================
Files 6 6
Lines 2671 2671
==========================================
+ Hits 2571 2572 +1
+ Misses 100 99 -1
```
| [Impacted Files](https://codecov.io/gh/simonw/sqlite-utils/pull/531?src=pr&el=tree&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison) | Coverage Δ | |
|---|---|---|
| [sqlite\_utils/utils.py](https://codecov.io/gh/simonw/sqlite-utils/pull/531?src=pr&el=tree&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison#diff-c3FsaXRlX3V0aWxzL3V0aWxzLnB5) | `95.13% <ø> (ø)` | |
| [sqlite\_utils/cli.py](https://codecov.io/gh/simonw/sqlite-utils/pull/531?src=pr&el=tree&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison#diff-c3FsaXRlX3V0aWxzL2NsaS5weQ==) | `95.26% <100.00%> (+0.09%)` | :arrow_up: |
Help us with your feedback. Take ten seconds to tell us [how you rate us](https://about.codecov.io/nps?utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison). Have a feature suggestion? [Share it here.](https://app.codecov.io/gh/feedback/?utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison)
[:umbrella: View full report in Codecov by Sentry](https://codecov.io/gh/simonw/sqlite-utils/pull/531?src=pr&el=continue&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison).
:loudspeaker: Do you have feedback about the report comment? [Let us know in this issue](https://about.codecov.io/codecov-pr-comment-feedback/?utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Simon+Willison).
","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1620164673,Add paths for homebrew on Apple silicon,
https://github.com/dogsheep/healthkit-to-sqlite/issues/24#issuecomment-1464796494,https://api.github.com/repos/dogsheep/healthkit-to-sqlite/issues/24,1464796494,IC_kwDOC8tyDs5XTwVO,956433,Mjboothaus,2023-03-11T02:23:42Z,2023-03-11T02:23:42Z,NONE,@simonw - maybe put in some error handling to trap for poorly formed XML (from Apple engineers) so that it suggests that there are problems with export.zip rather than odd looking Python errors :),"{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1515883470,DOC: xml.etree.ElementTree.ParseError due to healthkit version 12 ,
https://github.com/dogsheep/healthkit-to-sqlite/issues/24#issuecomment-1464786643,https://api.github.com/repos/dogsheep/healthkit-to-sqlite/issues/24,1464786643,IC_kwDOC8tyDs5XTt7T,956433,Mjboothaus,2023-03-11T02:01:27Z,2023-03-11T02:01:27Z,NONE,Thanks for reporting this and providing a solution -- I was puzzled by this error when I revisited my walking data and experienced this issues. I haven't tried the fix yet.,"{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1515883470,DOC: xml.etree.ElementTree.ParseError due to healthkit version 12 ,
https://github.com/simonw/datasette/pull/1999#issuecomment-1463113856,https://api.github.com/repos/simonw/datasette/issues/1999,1463113856,IC_kwDOBm6k_c5XNViA,9599,simonw,2023-03-10T02:13:15Z,2023-03-10T02:13:15Z,OWNER,Idea for if this change ends up making a bunch of breaking changes to the templates (which I think it should) - I can generate a GitHub diff link between the old and new templates and include that link in the 1.0 upgrade documentation to help people who wrote custom templates see what they might need to change - with minimal effort from myself to document those changes.,"{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1551694938,?_extra= support (draft),
https://github.com/simonw/datasette/issues/2038#issuecomment-1463112173,https://api.github.com/repos/simonw/datasette/issues/2038,1463112173,IC_kwDOBm6k_c5XNVHt,9599,simonw,2023-03-10T02:11:06Z,2023-03-10T02:11:06Z,OWNER,"Here's an example of something that would break:
https://github.com/simonw/datasette/blob/56b0758a5fbf85d01ff80a40c9b028469d7bb65f/datasette/templates/database.html#L12-L15
Because `metadata` is an empty dictionary sometimes, so `{{ metadata.title or database }}` would raise an error and need to be replaced by `{{ metadata.get(""title"") or database }}`.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1618249044,Consider a `strict_templates` setting,
https://github.com/simonw/datasette/issues/2038#issuecomment-1463110978,https://api.github.com/repos/simonw/datasette/issues/2038,1463110978,IC_kwDOBm6k_c5XNU1C,9599,simonw,2023-03-10T02:09:41Z,2023-03-10T02:09:41Z,OWNER,"I'm torn on this. It's useful for me right now for refactoring, but I feel like it should be a permanent thing, not a setting - or it should default to on and people should turn it off, but who would ever do that?","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1618249044,Consider a `strict_templates` setting,
https://github.com/simonw/datasette/pull/1999#issuecomment-1463024951,https://api.github.com/repos/simonw/datasette/issues/1999,1463024951,IC_kwDOBm6k_c5XM_03,9599,simonw,2023-03-10T00:17:58Z,2023-03-10T00:17:58Z,OWNER,"Renderers have an impact on three different pages: query results, table page and row page.
The row page feature is incomplete though:
https://congress-legislators.datasettes.com/legislators/social_media/A000055
Why is there no `.csv` link there?","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1551694938,?_extra= support (draft),
https://github.com/simonw/datasette/pull/1999#issuecomment-1463023674,https://api.github.com/repos/simonw/datasette/issues/1999,1463023674,IC_kwDOBm6k_c5XM_g6,9599,simonw,2023-03-10T00:16:03Z,2023-03-10T00:16:03Z,OWNER,"I also need to figure out the `renderers` stuff, so I can link to the right URLs for CSV and JSON and other formats:
https://github.com/simonw/datasette/blob/6d07a7da1531cd749844fc6827d9a1e57009b2ea/datasette/views/base.py#L474-L518","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1551694938,?_extra= support (draft),
https://github.com/simonw/datasette/pull/1999#issuecomment-1463022397,https://api.github.com/repos/simonw/datasette/issues/1999,1463022397,IC_kwDOBm6k_c5XM_M9,9599,simonw,2023-03-10T00:14:21Z,2023-03-10T00:14:21Z,OWNER,"Ironically the thing I most need right now is comprehensive documentation of what variables are being passed to the templates!
One big challenge is that I need to untangle the template context that happens in `BaseView` - I'm hacking that together at the moment, but I need a real answer for how that should work in a world in which view functions aren't using that base class.
https://github.com/simonw/datasette/blob/56b0758a5fbf85d01ff80a40c9b028469d7bb65f/datasette/views/base.py#L110-L145","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1551694938,?_extra= support (draft),
https://github.com/simonw/datasette/pull/1999#issuecomment-1463021383,https://api.github.com/repos/simonw/datasette/issues/1999,1463021383,IC_kwDOBm6k_c5XM-9H,9599,simonw,2023-03-10T00:12:50Z,2023-03-10T00:12:50Z,OWNER,"Now at 34 failed, 34 passed.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1551694938,?_extra= support (draft),
https://github.com/simonw/datasette/pull/1999#issuecomment-1463005744,https://api.github.com/repos/simonw/datasette/issues/1999,1463005744,IC_kwDOBm6k_c5XM7Iw,9599,simonw,2023-03-09T23:52:15Z,2023-03-09T23:52:23Z,OWNER,"I need to figure out what to do about `extra_context_from_filters` - which was previously passed straight to the HTML context.
https://github.com/simonw/datasette/blob/11f7feb7a3f7166c71389786880863d60ed3d165/datasette/views/table.py#L406-L422","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1551694938,?_extra= support (draft),
https://github.com/simonw/datasette/pull/1999#issuecomment-1462997800,https://api.github.com/repos/simonw/datasette/issues/1999,1462997800,IC_kwDOBm6k_c5XM5Mo,9599,simonw,2023-03-09T23:39:47Z,2023-03-09T23:39:47Z,OWNER,"Found a neat trick:
```diff
diff --git a/datasette/app.py b/datasette/app.py
index 186f192d..40416713 100644
--- a/datasette/app.py
+++ b/datasette/app.py
@@ -23,7 +23,13 @@ from pathlib import Path
from markupsafe import Markup, escape
from itsdangerous import URLSafeSerializer
-from jinja2 import ChoiceLoader, Environment, FileSystemLoader, PrefixLoader
+from jinja2 import (
+ ChoiceLoader,
+ Environment,
+ FileSystemLoader,
+ PrefixLoader,
+ StrictUndefined,
+)
from jinja2.environment import Template
from jinja2.exceptions import TemplateNotFound
@@ -394,7 +400,10 @@ class Datasette:
]
)
self.jinja_env = Environment(
- loader=template_loader, autoescape=True, enable_async=True
+ loader=template_loader,
+ autoescape=True,
+ enable_async=True,
+ undefined=StrictUndefined,
)
self.jinja_env.filters[""escape_css_string""] = escape_css_string
self.jinja_env.filters[""quote_plus""] = urllib.parse.quote_plus
```
This causes Jinja to raise a hard error if there are any variables referenced in the template that are not available in the context.
It's helping me spot things that are still missing, rather than just relying on failed unit tests.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1551694938,?_extra= support (draft),
https://github.com/dogsheep/apple-notes-to-sqlite/issues/11#issuecomment-1462968053,https://api.github.com/repos/dogsheep/apple-notes-to-sqlite/issues/11,1462968053,IC_kwDOJHON9s5XMx71,9599,simonw,2023-03-09T23:24:01Z,2023-03-09T23:24:01Z,MEMBER,"I improved the readability by removing some unnecessary table aliases:
```sql
with recursive nested_folders(folder_id, descendant_folder_id) as (
-- base case: select all immediate children of the root folder
select id, id from folders where parent is null
union all
-- recursive case: select all children of the previous level of nested folders
select nested_folders.folder_id, folders.id from nested_folders
join folders on nested_folders.descendant_folder_id = folders.parent
)
-- Find notes within all descendants of folder 1
select *
from notes
where folder in (
select descendant_folder_id from nested_folders where folder_id = 1
);
```","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1618130434,Implement a SQL view to make it easier to query files in a nested folder,
https://github.com/dogsheep/apple-notes-to-sqlite/issues/11#issuecomment-1462965256,https://api.github.com/repos/dogsheep/apple-notes-to-sqlite/issues/11,1462965256,IC_kwDOJHON9s5XMxQI,9599,simonw,2023-03-09T23:22:12Z,2023-03-09T23:22:12Z,MEMBER,"Here's what the CTE from that looks like:
","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1618130434,Implement a SQL view to make it easier to query files in a nested folder,
https://github.com/dogsheep/apple-notes-to-sqlite/issues/11#issuecomment-1462962682,https://api.github.com/repos/dogsheep/apple-notes-to-sqlite/issues/11,1462962682,IC_kwDOJHON9s5XMwn6,9599,simonw,2023-03-09T23:20:35Z,2023-03-09T23:22:41Z,MEMBER,"Here's a query that returns all notes in folder 1, including notes in descendant folders:
```sql
with recursive nested_folders(folder_id, descendant_folder_id) as (
-- base case: select all immediate children of the root folder
select id, id from folders where parent is null
union all
-- recursive case: select all children of the previous level of nested folders
select nf.folder_id, f.id from nested_folders nf
join folders f on nf.descendant_folder_id = f.parent
)
-- Find notes within all descendants of folder 1
select *
from notes
where folder in (
select descendant_folder_id from nested_folders where folder_id = 1
);
```
With assistance from ChatGPT. Prompts were:
```
SQLite schema:
CREATE TABLE [folders] (
[id] INTEGER PRIMARY KEY,
[long_id] TEXT,
[name] TEXT,
[parent] INTEGER,
FOREIGN KEY([parent]) REFERENCES [folders]([id])
);
Write a recursive CTE that returns the following:
folder_id | descendant_folder_id
With a row for every nested child of every folder - so the top level folder has lots of rows
```
Then I tweaked it a bit, then ran this:
```
WITH RECURSIVE nested_folders(folder_id, descendant_folder_id) AS (
-- base case: select all immediate children of the root folder
SELECT id, id FROM folders WHERE parent IS NULL
UNION ALL
-- recursive case: select all children of the previous level of nested folders
SELECT nf.folder_id, f.id FROM nested_folders nf
JOIN folders f ON nf.descendant_folder_id = f.parent
)
-- select all rows from the recursive CTE
SELECT * from notes where folder in (select descendant_folder_id FROM nested_folders where folder_id = 1)
Convert all SQL keywords to lower case, and re-indent
```","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1618130434,Implement a SQL view to make it easier to query files in a nested folder,
https://github.com/simonw/datasette/pull/2031#issuecomment-1462921890,https://api.github.com/repos/simonw/datasette/issues/2031,1462921890,IC_kwDOBm6k_c5XMmqi,9599,simonw,2023-03-09T22:35:30Z,2023-03-09T22:35:30Z,OWNER,"> I've implemented the test (thanks for pointing me in the right direction!).
>
> At [tmcl-it/datasette:0.64.1+row-view-expand-labels](https://github.com/tmcl-it/datasette/tree/0.64.1%2Brow-view-expand-labels) I also have a variant of this patch that applies to the 0.64.x branch. Please let me know if you'd be interested in merging that as well and I'll open another PR.
Sure, let's merge that one too - it can go out in the next `0.64.x` series release (maybe even a 0.65).","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1605481359,Expand foreign key references in row view as well,
https://github.com/simonw/datasette/pull/2034#issuecomment-1462921010,https://api.github.com/repos/simonw/datasette/issues/2034,1462921010,IC_kwDOBm6k_c5XMmcy,9599,simonw,2023-03-09T22:34:29Z,2023-03-09T22:34:29Z,OWNER,"Good catch, thanks.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1613974869,remove an unused `app` var in cli.py,
https://github.com/dogsheep/apple-notes-to-sqlite/issues/7#issuecomment-1462693867,https://api.github.com/repos/dogsheep/apple-notes-to-sqlite/issues/7,1462693867,IC_kwDOJHON9s5XLu_r,9599,simonw,2023-03-09T20:01:39Z,2023-03-09T20:02:11Z,MEMBER,"My `folders` table will have:
- `id` - rowid
- `long_id` - that long unique string ID
- `name` - the name
- `parent` - foreign key to `id`","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1617769847,Folder support,
https://github.com/dogsheep/apple-notes-to-sqlite/issues/7#issuecomment-1462691466,https://api.github.com/repos/dogsheep/apple-notes-to-sqlite/issues/7,1462691466,IC_kwDOJHON9s5XLuaK,9599,simonw,2023-03-09T19:59:52Z,2023-03-09T19:59:52Z,MEMBER,"Improved script:
```zsh
osascript -e 'tell application ""Notes""
set allFolders to folders
repeat with aFolder in allFolders
set folderId to id of aFolder
set folderName to name of aFolder
set folderContainer to container of aFolder
if class of folderContainer is folder then
set folderContainerId to id of folderContainer
else
set folderContainerId to """"
end if
log ""ID: "" & folderId
log ""Name: "" & folderName
log ""Container: "" & folderContainerId
log "" ""
end repeat
end tell
'
```
```
ID: x-coredata://D2D50498-BBD1-4097-B122-D15ABD32BDEC/ICFolder/p6113
Name: Blog posts
Container:
ID: x-coredata://D2D50498-BBD1-4097-B122-D15ABD32BDEC/ICFolder/p698
Name: JSK
Container:
ID: x-coredata://D2D50498-BBD1-4097-B122-D15ABD32BDEC/ICFolder/p7995
Name: Nested inside blog posts
Container: x-coredata://D2D50498-BBD1-4097-B122-D15ABD32BDEC/ICFolder/p6113
ID: x-coredata://D2D50498-BBD1-4097-B122-D15ABD32BDEC/ICFolder/p3526
Name: New Folder
Container:
ID: x-coredata://D2D50498-BBD1-4097-B122-D15ABD32BDEC/ICFolder/p3839
Name: New Folder 1
Container:
ID: x-coredata://D2D50498-BBD1-4097-B122-D15ABD32BDEC/ICFolder/p2
Name: Notes
Container:
ID: x-coredata://D2D50498-BBD1-4097-B122-D15ABD32BDEC/ICFolder/p6059
Name: Quick Notes
Container:
ID: x-coredata://D2D50498-BBD1-4097-B122-D15ABD32BDEC/ICFolder/p7283
Name: UK Christmas 2022
Container:
```
I filtered out things where the parent was an account and not a folder using `if class of folderContainer is folder then`.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1617769847,Folder support,
https://github.com/dogsheep/apple-notes-to-sqlite/issues/7#issuecomment-1462682795,https://api.github.com/repos/dogsheep/apple-notes-to-sqlite/issues/7,1462682795,IC_kwDOJHON9s5XLsSr,9599,simonw,2023-03-09T19:52:20Z,2023-03-09T19:52:44Z,MEMBER,"Created through several rounds with ChatGPT (including hints like ""rewrite that using setdefault()""):
```python
def topological_sort(nodes):
children = {}
for node in nodes:
parent_id = node[""parent""]
if parent_id is not None:
children.setdefault(parent_id, []).append(node)
def traverse(node, result):
result.append(node)
if node[""id""] in children:
for child in children[node[""id""]]:
traverse(child, result)
sorted_data = []
for node in nodes:
if node[""parent""] is None:
traverse(node, sorted_data)
return sorted_data
```","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1617769847,Folder support,
https://github.com/dogsheep/apple-notes-to-sqlite/issues/7#issuecomment-1462570187,https://api.github.com/repos/dogsheep/apple-notes-to-sqlite/issues/7,1462570187,IC_kwDOJHON9s5XLQzL,9599,simonw,2023-03-09T18:30:24Z,2023-03-09T18:30:24Z,MEMBER,"I used ChatGPT to write this:
```
osascript -e 'tell application ""Notes""
set allFolders to folders
repeat with aFolder in allFolders
set folderId to id of aFolder
set folderName to name of aFolder
set folderContainer to container of aFolder
set folderContainerName to name of folderContainer
log ""Folder ID: "" & folderId
log ""Folder Name: "" & folderName
log ""Folder Container: "" & folderContainerName
log "" ""
--check for nested folders
if count of folders of aFolder > 0 then
set nestedFolders to folders of aFolder
repeat with aNestedFolder in nestedFolders
set nestedFolderId to id of aNestedFolder
set nestedFolderName to name of aNestedFolder
set nestedFolderContainer to container of aNestedFolder
set nestedFolderContainerName to name of nestedFolderContainer
log "" Nested Folder ID: "" & nestedFolderId
log "" Nested Folder Name: "" & nestedFolderName
log "" Nested Folder Container: "" & nestedFolderContainerName
log "" ""
end repeat
end if
end repeat
end tell
'
```
Which for my account output this:
```
Folder ID: x-coredata://D2D50498-BBD1-4097-B122-D15ABD32BDEC/ICFolder/p6113
Folder Name: Blog posts
Folder Container: iCloud
Nested Folder ID: x-coredata://D2D50498-BBD1-4097-B122-D15ABD32BDEC/ICFolder/p7995
Nested Folder Name: Nested inside blog posts
Nested Folder Container: Blog posts
Folder ID: x-coredata://D2D50498-BBD1-4097-B122-D15ABD32BDEC/ICFolder/p698
Folder Name: JSK
Folder Container: iCloud
Folder ID: x-coredata://D2D50498-BBD1-4097-B122-D15ABD32BDEC/ICFolder/p7995
Folder Name: Nested inside blog posts
Folder Container: Blog posts
Folder ID: x-coredata://D2D50498-BBD1-4097-B122-D15ABD32BDEC/ICFolder/p3526
Folder Name: New Folder
Folder Container: iCloud
Folder ID: x-coredata://D2D50498-BBD1-4097-B122-D15ABD32BDEC/ICFolder/p3839
Folder Name: New Folder 1
Folder Container: iCloud
Folder ID: x-coredata://D2D50498-BBD1-4097-B122-D15ABD32BDEC/ICFolder/p2
Folder Name: Notes
Folder Container: iCloud
Folder ID: x-coredata://D2D50498-BBD1-4097-B122-D15ABD32BDEC/ICFolder/p6059
Folder Name: Quick Notes
Folder Container: iCloud
Folder ID: x-coredata://D2D50498-BBD1-4097-B122-D15ABD32BDEC/ICFolder/p7283
Folder Name: UK Christmas 2022
Folder Container: iCloud
```
So I think the correct approach here is to run code at the start to list all of the folders (no need to do fancy recursion though, just a flat list with the parent containers is enough) and create a model of that hierarchy in SQLite.
Then when I import notes I can foreign key reference them back to their containing folder.
I'm tempted to use `rowid` for the foreign keys because the official IDs are pretty long.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1617769847,Folder support,
https://github.com/dogsheep/apple-notes-to-sqlite/issues/7#issuecomment-1462564717,https://api.github.com/repos/dogsheep/apple-notes-to-sqlite/issues/7,1462564717,IC_kwDOJHON9s5XLPdt,9599,simonw,2023-03-09T18:25:39Z,2023-03-09T18:25:39Z,MEMBER,So it looks like folders can be hierarchical?,"{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1617769847,Folder support,
https://github.com/dogsheep/apple-notes-to-sqlite/issues/7#issuecomment-1462562735,https://api.github.com/repos/dogsheep/apple-notes-to-sqlite/issues/7,1462562735,IC_kwDOJHON9s5XLO-v,9599,simonw,2023-03-09T18:23:56Z,2023-03-09T18:25:22Z,MEMBER,"From the Script Editor library docs:
A note has a:
> - `container` (folder), r/o) : the folder of the note
Here's what a folder looks like:
> folder n : a folder containing notes
> elements:
>
> - contains folders, notes; contained by application, accounts, folders.
>
> properties:
>
> - `name` (text) : the name of the folder
> - `id` (text, r/o) : the unique identifier of the folder
> - `shared` (boolean, r/o) : Is the folder shared?
> - `container` (account or folder, r/o) : the container of the folder
","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1617769847,Folder support,
https://github.com/dogsheep/apple-notes-to-sqlite/issues/4#issuecomment-1462556829,https://api.github.com/repos/dogsheep/apple-notes-to-sqlite/issues/4,1462556829,IC_kwDOJHON9s5XLNid,9599,simonw,2023-03-09T18:20:56Z,2023-03-09T18:20:56Z,MEMBER,"In terms of the UI: I'm tempted to say that the default behaviour is for it to run until it sees a note that it already knows about AND that has matching update/created dates, and then stop.
You can do a full import again ignoring that logic with `apple-notes-to-sqlite notes.db --full`.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1616429236,Support incremental updates,
https://github.com/dogsheep/apple-notes-to-sqlite/issues/4#issuecomment-1462554175,https://api.github.com/repos/dogsheep/apple-notes-to-sqlite/issues/4,1462554175,IC_kwDOJHON9s5XLM4_,9599,simonw,2023-03-09T18:19:34Z,2023-03-09T18:19:34Z,MEMBER,It looks like the iteration order is most-recently-modified-first - I tried editing a note a bit further back in my notes app and it was the first one output by `apple-notes-to-sqlite --dump`.,"{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1616429236,Support incremental updates,
https://github.com/dogsheep/apple-notes-to-sqlite/issues/2#issuecomment-1461285545,https://api.github.com/repos/dogsheep/apple-notes-to-sqlite/issues/2,1461285545,IC_kwDOJHON9s5XGXKp,9599,simonw,2023-03-09T05:06:24Z,2023-03-09T05:06:24Z,MEMBER,"OK, this works!","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1616354999,First working version,
https://github.com/dogsheep/apple-notes-to-sqlite/issues/2#issuecomment-1461262577,https://api.github.com/repos/dogsheep/apple-notes-to-sqlite/issues/2,1461262577,IC_kwDOJHON9s5XGRjx,9599,simonw,2023-03-09T04:30:00Z,2023-03-09T04:30:00Z,MEMBER,It doesn't have tests yet. I guess I'll need to mock `subprocess` to test this.,"{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1616354999,First working version,
https://github.com/dogsheep/apple-notes-to-sqlite/issues/2#issuecomment-1461260978,https://api.github.com/repos/dogsheep/apple-notes-to-sqlite/issues/2,1461260978,IC_kwDOJHON9s5XGRKy,9599,simonw,2023-03-09T04:27:18Z,2023-03-09T04:27:18Z,MEMBER,"Before that conversion:
Monday, March 6, 2023 at 11:55:15 AM
After:
2023-03-06T11:55:15","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1616354999,First working version,
https://github.com/dogsheep/apple-notes-to-sqlite/issues/2#issuecomment-1461259490,https://api.github.com/repos/dogsheep/apple-notes-to-sqlite/issues/2,1461259490,IC_kwDOJHON9s5XGQzi,9599,simonw,2023-03-09T04:24:27Z,2023-03-09T04:24:27Z,MEMBER,"Converting AppleScript date strings to ISO format is hard!
https://forum.latenightsw.com/t/formatting-dates/841 has a recipe I'll try:
set todayISO to (todayDate as «class isot» as string)
Not clear to me how timezones work here. I'm going to ignore them for the moment.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1616354999,First working version,
https://github.com/dogsheep/apple-notes-to-sqlite/issues/2#issuecomment-1461234591,https://api.github.com/repos/dogsheep/apple-notes-to-sqlite/issues/2,1461234591,IC_kwDOJHON9s5XGKuf,9599,simonw,2023-03-09T03:56:45Z,2023-03-09T03:56:45Z,MEMBER,"My prototype showed that images embedded in notes come out in the HTML export as bas64 image URLs, which is neat.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1616354999,First working version,
https://github.com/dogsheep/apple-notes-to-sqlite/issues/2#issuecomment-1461234311,https://api.github.com/repos/dogsheep/apple-notes-to-sqlite/issues/2,1461234311,IC_kwDOJHON9s5XGKqH,9599,simonw,2023-03-09T03:56:24Z,2023-03-09T03:56:24Z,MEMBER,"I opened the ""Script Editor"" app on my computer, used Window -> Library to open the Library panel, then clicked on the Notes app there. I got this:
So the notes object has these properties:
- name (text) : the name of the note (normally the first line of the body)
- id (text, r/o) : the unique identifier of the note
- container ([folder](applewebdata://621FA8D9-C995-4081-B3B3-149B0EA04C7F#Notes-Suite.folder), r/o) : the folder of the note
- body (text) : the HTML content of the note
- plaintext (text, r/o) : the plaintext content of the note
- creation date (date, r/o) : the creation date of the note
- modification date (date, r/o) : the modification date of the note
- password protected (boolean, r/o) : Is the note password protected?
- shared (boolean, r/o) : Is the note shared?
I'm going to ignore the concept of attachments for the moment.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1616354999,First working version,
https://github.com/dogsheep/apple-notes-to-sqlite/issues/2#issuecomment-1461232709,https://api.github.com/repos/dogsheep/apple-notes-to-sqlite/issues/2,1461232709,IC_kwDOJHON9s5XGKRF,9599,simonw,2023-03-09T03:54:28Z,2023-03-09T03:54:28Z,MEMBER,"I think the AppleScript I want to pass to `osascript` looks like this:
```applescript
tell application ""Notes""
repeat with eachNote in every note
set noteId to the id of eachNote
set noteTitle to the name of eachNote
set noteBody to the body of eachNote
log ""------------------------"" & ""\n""
log noteId & ""\n""
log noteTitle & ""\n\n""
log noteBody & ""\n""
end repeat
end tell
```
But there are a few more properties I'd like to get - created and updated date for example.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1616354999,First working version,
https://github.com/dogsheep/apple-notes-to-sqlite/issues/1#issuecomment-1461230436,https://api.github.com/repos/dogsheep/apple-notes-to-sqlite/issues/1,1461230436,IC_kwDOJHON9s5XGJtk,9599,simonw,2023-03-09T03:51:52Z,2023-03-09T03:51:52Z,MEMBER,This did the job! Next step is to turn that into a Python script.,"{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1616347574,Initial proof of concept with ChatGPT,
https://github.com/dogsheep/apple-notes-to-sqlite/issues/1#issuecomment-1461230197,https://api.github.com/repos/dogsheep/apple-notes-to-sqlite/issues/1,1461230197,IC_kwDOJHON9s5XGJp1,9599,simonw,2023-03-09T03:51:36Z,2023-03-09T03:51:36Z,MEMBER,"After a few more rounds I got to this script, which outputs them to a `/tmp/notes.txt` file:
```zsh
#!/bin/zsh
osascript -e '
set notesFile to ""/tmp/notes.txt""
set fileRef to open for access notesFile with write permission
tell application ""Notes""
repeat with eachNote in every note
set noteId to the id of eachNote
set noteTitle to the name of eachNote
set noteBody to the body of eachNote
write ""------------------------"" & ""\n"" to fileRef
write noteId & ""\n"" to fileRef
write noteTitle & ""\n\n"" to fileRef
write noteBody & ""\n"" to fileRef
end repeat
end tell
close access fileRef'
```
Then I wrote this little Python script to load them into a database:
```python
import sqlite_utils
split = b""------------------------\n""
s = open(""/tmp/notes.txt"", ""rb"").read()
notes = [n.decode(""mac_roman"") for n in s.split(split) if n]
cleaned_notes = [{
""id"": n.split(""\n"")[0],
""title"": n.split(""\n"")[1],
""body"": ""\n"".join(n.split(""\n"")[2:]).strip()
} for n in notes]
db = sqlite_utils.Database(""/tmp/notes.db"")
db[""notes""].insert_all(cleaned_notes)
```","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1616347574,Initial proof of concept with ChatGPT,
https://github.com/dogsheep/apple-notes-to-sqlite/issues/1#issuecomment-1461226402,https://api.github.com/repos/dogsheep/apple-notes-to-sqlite/issues/1,1461226402,IC_kwDOJHON9s5XGIui,9599,simonw,2023-03-09T03:47:11Z,2023-03-09T03:47:11Z,MEMBER,"Me:
> Write applescript to loop through all of my Apple Notes and output their contents
ChatGPT:
```applescript
tell application ""Notes""
repeat with eachNote in every note
set noteTitle to the name of eachNote
set noteBody to the body of eachNote
display dialog noteTitle & return & return & noteBody
end repeat
end tell
```
Me:
> How can I turn that into a zsh script which will output the results to my terminal
ChatGPT:
```zsh
#!/usr/bin/zsh
osascript -e 'tell application ""Notes""
repeat with eachNote in every note
set noteTitle to the name of eachNote
set noteBody to the body of eachNote
set output to noteTitle & ""\n"" & noteBody & ""\n""
display dialog output
log output
end repeat
end tell'
```
I had to change that first line to `#!/bin/zsh` - then when I ran it it spammed my screen with dialog boxes.
Me:
> I want to log the notes contents to the terminal, not display it in a dialog
ChatGPT:
```zsh
#!/bin/zsh
osascript -e 'tell application ""Notes""
repeat with eachNote in every note
set noteTitle to the name of eachNote
set noteBody to the body of eachNote
set output to noteTitle & ""\n"" & noteBody & ""\n""
log output
end repeat
end tell'
```
This really helps!","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1616347574,Initial proof of concept with ChatGPT,
https://github.com/simonw/datasette/pull/1999#issuecomment-1461161256,https://api.github.com/repos/simonw/datasette/issues/1999,1461161256,IC_kwDOBm6k_c5XF40o,9599,simonw,2023-03-09T02:10:07Z,2023-03-09T02:10:07Z,OWNER,"Just ran into a `no such table: columns` error - which I think is because my new view code sometimes bypasses calling this method (currently done in `BaseView.dispatch_request()`):
https://github.com/simonw/datasette/blob/96e94f9b7b2db53865e61390bcce6761727f26d8/datasette/views/base.py#L101-L103","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1551694938,?_extra= support (draft),
https://github.com/simonw/datasette/pull/1999#issuecomment-1461148579,https://api.github.com/repos/simonw/datasette/issues/1999,1461148579,IC_kwDOBm6k_c5XF1uj,9599,simonw,2023-03-09T01:54:10Z,2023-03-09T01:55:33Z,OWNER,Or... I could temporarily build a quick additional `CannedQueryView` subclass that just does the necessary bits to get the existing code to work. I'm going to try that.,"{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1551694938,?_extra= support (draft),
https://github.com/simonw/datasette/pull/1999#issuecomment-1461148254,https://api.github.com/repos/simonw/datasette/issues/1999,1461148254,IC_kwDOBm6k_c5XF1pe,9599,simonw,2023-03-09T01:53:41Z,2023-03-09T01:53:41Z,OWNER,"Solving this is proving difficult: https://github.com/simonw/datasette/blob/96e94f9b7b2db53865e61390bcce6761727f26d8/datasette/views/table.py#L1500-L1503
The problem is that calling `.data()` on `QueryView` only works here because we expect to ourselves be inside a `.data()` method, with all of the existing magic that knows how to render things that are returned by that.
So I may need to substantially re-engineer how `QueryView` works in order to get this to work.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1551694938,?_extra= support (draft),
https://github.com/simonw/datasette/pull/1999#issuecomment-1461075648,https://api.github.com/repos/simonw/datasette/issues/1999,1461075648,IC_kwDOBm6k_c5XFj7A,9599,simonw,2023-03-09T00:24:22Z,2023-03-09T00:24:22Z,OWNER,`127.0.0.1:8001/fixtures/neighborhood_search` fails because the forwarding to a canned query does not yet work.,"{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1551694938,?_extra= support (draft),
https://github.com/simonw/datasette/pull/1999#issuecomment-1461074526,https://api.github.com/repos/simonw/datasette/issues/1999,1461074526,IC_kwDOBm6k_c5XFjpe,9599,simonw,2023-03-09T00:23:06Z,2023-03-09T00:23:06Z,OWNER," pytest tests/test_table_html.py
Currently 44 failed, 24 passed in 7.53s
Failures here: https://gist.github.com/simonw/df0a52cd7d820b776dc3dfc50e7cb778","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1551694938,?_extra= support (draft),
https://github.com/simonw/datasette/pull/1999#issuecomment-1461070937,https://api.github.com/repos/simonw/datasette/issues/1999,1461070937,IC_kwDOBm6k_c5XFixZ,9599,simonw,2023-03-09T00:18:52Z,2023-03-09T00:19:36Z,OWNER,"I managed to get HTML view working! I did it by continuing to add more things to the extras and the `_html` bundle until the page loaded for me:
```diff
async def extra_extras():
""Available ?_extra= blocks""
return {
@@ -1981,6 +2053,14 @@ async def extra_extras():
""query"",
""display_columns"",
""display_rows"",
+ ""database"",
+ ""table"",
+ ""database_color"",
+ ""table_actions"",
+ ""filters"",
+ ""renderers"",
+ ""custom_table_templates"",
+ ""sorted_facet_results"",
]
}
@@ -2006,6 +2086,14 @@ async def extra_extras():
extra_query,
extra_metadata,
extra_extras,
+ extra_database,
+ extra_table,
+ extra_database_color,
+ extra_table_actions,
+ extra_filters,
+ extra_renderers,
+ extra_custom_table_templates,
+ extra_sorted_facet_results,
)
```
I'll probably refactor this into something cleaner, and maybe but a bunch of them in a `""html""` dictionary and update the templates to use `{{ html.filters }}` or similar. Will look at that once the tests are passing.
","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1551694938,?_extra= support (draft),
https://github.com/simonw/datasette/pull/1999#issuecomment-1461047607,https://api.github.com/repos/simonw/datasette/issues/1999,1461047607,IC_kwDOBm6k_c5XFdE3,9599,simonw,2023-03-08T23:51:46Z,2023-03-08T23:51:46Z,OWNER,"This feels quite nice:
","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1551694938,?_extra= support (draft),
https://github.com/simonw/datasette/pull/1999#issuecomment-1461044477,https://api.github.com/repos/simonw/datasette/issues/1999,1461044477,IC_kwDOBm6k_c5XFcT9,9599,simonw,2023-03-08T23:47:26Z,2023-03-08T23:47:26Z,OWNER,"I want to package together all of the extras that are needed for the HTML format. A few options for doing that:
- Introduce `?_extra=_html` where the leading underscore indicates that this is a ""bundle"" of extras, then define a bundle that's everything needed for the HTML renderer
- Have some other mechanism whereby different renderers can request a bundle of extras.
I'm leaning towards the first option. I'll try that and see what it looks like.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1551694938,?_extra= support (draft),
https://github.com/simonw/datasette/pull/1999#issuecomment-1461023559,https://api.github.com/repos/simonw/datasette/issues/1999,1461023559,IC_kwDOBm6k_c5XFXNH,9599,simonw,2023-03-08T23:23:02Z,2023-03-08T23:23:02Z,OWNER,"To get this unblocked, I'm going to allow myself to pass non-JSON-serializable objects to the HTML template version of things. If I can get that working (and get the existing tests to pass) I can consider a later change that makes those JSON serializable - or admit that it's OK for the templates to have non-JSON data passed to them and figure out how best to document those variables independently from the JSON documentation.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1551694938,?_extra= support (draft),
https://github.com/simonw/datasette/pull/1999#issuecomment-1461002039,https://api.github.com/repos/simonw/datasette/issues/1999,1461002039,IC_kwDOBm6k_c5XFR83,9599,simonw,2023-03-08T22:58:16Z,2023-03-08T23:02:09Z,OWNER,"The reason for that `Row` thing is that it allows custom templates that do things like this:
https://docs.datasette.io/en/stable/changelog.html#easier-custom-templates-for-table-rows
```html+jinja
{% for row in display_rows %}
{{ row[""title""] }}
{{ row[""description""] }}
Category: {{ row.display(""category_id"") }}
{% endfor %}
```
Is that a good design? the `.display()` thing feels weird - I wonder if anyone has ever actually used that.
It's documented here: https://docs.datasette.io/en/0.64.2/custom_templates.html#custom-templates
> If you want to output the rendered HTML version of a column, including any links to foreign keys, you can use `{{ row.display(""column_name"") }}`.
I can't see any examples of anyone using it in this code search: https://cs.github.com/?scopeName=All+repos&scope=&q=datasette+row.display
It is however useful to have some kind of abstraction layer here that insulates the SQLite `Row` object, since having an extra layer will help if Datasette ever grows support for alternative database backends such as DuckDB or PostgreSQL.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1551694938,?_extra= support (draft),
https://github.com/simonw/datasette/pull/1999#issuecomment-1460988975,https://api.github.com/repos/simonw/datasette/issues/1999,1460988975,IC_kwDOBm6k_c5XFOwv,9599,simonw,2023-03-08T22:42:57Z,2023-03-08T22:42:57Z,OWNER,"Aside idea: it might be interesting if there were ""lazy"" template variables available in the context: things that are not actually executed unless a template author requests them.
Imagine if `metadata` was a lazy template reference, such that custom templates that don't display any metadata don't trigger it to be resolved (which might involve additional database queries some day).","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1551694938,?_extra= support (draft),
https://github.com/simonw/datasette/pull/1999#issuecomment-1460986533,https://api.github.com/repos/simonw/datasette/issues/1999,1460986533,IC_kwDOBm6k_c5XFOKl,9599,simonw,2023-03-08T22:40:28Z,2023-03-08T22:40:28Z,OWNER,"Figuring out what to do with `display_columns_and_rows()` is hard. That returns rows as this special kind of object, which is designed to be accessed from the HTML templates:
https://github.com/simonw/datasette/blob/96e94f9b7b2db53865e61390bcce6761727f26d8/datasette/views/table.py#L45-L71","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1551694938,?_extra= support (draft),
https://github.com/simonw/datasette/pull/1999#issuecomment-1460970807,https://api.github.com/repos/simonw/datasette/issues/1999,1460970807,IC_kwDOBm6k_c5XFKU3,9599,simonw,2023-03-08T22:31:49Z,2023-03-08T22:33:03Z,OWNER,"For the HTML version, I need to decide where all of the stuff that happens in `async def extra_template()` is going to live.
I think it's another one of those extra functions, triggered for `?_extra=context`.
https://github.com/simonw/datasette/blob/96e94f9b7b2db53865e61390bcce6761727f26d8/datasette/views/table.py#L813-L912","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1551694938,?_extra= support (draft),
https://github.com/simonw/datasette/pull/1999#issuecomment-1460943097,https://api.github.com/repos/simonw/datasette/issues/1999,1460943097,IC_kwDOBm6k_c5XFDj5,9599,simonw,2023-03-08T22:09:24Z,2023-03-08T22:09:47Z,OWNER,"The ease with which I added that `?_extra=query` feature in https://github.com/simonw/datasette/pull/1999/commits/96e94f9b7b2db53865e61390bcce6761727f26d8 made me feel really confident that this architecture is going in the right direction.
```diff
diff --git a/datasette/views/table.py b/datasette/views/table.py
index 8d3bb2c930..3e1db9c85f 100644
--- a/datasette/views/table.py
+++ b/datasette/views/table.py
@@ -1913,6 +1913,13 @@ async def extra_request():
""args"": request.args._data,
}
+ async def extra_query():
+ ""Details of the underlying SQL query""
+ return {
+ ""sql"": sql,
+ ""params"": params,
+ }
+
async def extra_extras():
""Available ?_extra= blocks""
return {
@@ -1938,6 +1945,7 @@ async def extra_extras():
extra_primary_keys,
extra_debug,
extra_request,
+ extra_query,
extra_extras,
)
```","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1551694938,?_extra= support (draft),
https://github.com/simonw/datasette/pull/1999#issuecomment-1460916405,https://api.github.com/repos/simonw/datasette/issues/1999,1460916405,IC_kwDOBm6k_c5XE9C1,9599,simonw,2023-03-08T21:43:27Z,2023-03-08T21:43:27Z,OWNER,"Just noticed that `_json=colname` is not working, and that's because it's handled by the renderer here:
https://github.com/simonw/datasette/blob/56b0758a5fbf85d01ff80a40c9b028469d7bb65f/datasette/renderer.py#L29-L40
But that's not currently being called by my new code.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1551694938,?_extra= support (draft),
https://github.com/simonw/datasette/pull/1999#issuecomment-1460907148,https://api.github.com/repos/simonw/datasette/issues/1999,1460907148,IC_kwDOBm6k_c5XE6yM,9599,simonw,2023-03-08T21:34:30Z,2023-03-08T21:34:30Z,OWNER,"I'm going to hold off on that refactor until later, when I have tests to show me if the refactor works or not.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1551694938,?_extra= support (draft),
https://github.com/simonw/datasette/pull/1999#issuecomment-1460906741,https://api.github.com/repos/simonw/datasette/issues/1999,1460906741,IC_kwDOBm6k_c5XE6r1,9599,simonw,2023-03-08T21:34:08Z,2023-03-08T21:34:08Z,OWNER,"So maybe I can refactor it to look a bit more like this:
https://github.com/simonw/datasette/blob/db1a88f4e17a1f50bdaa681e8beddb2276503e7c/datasette/views/table.py#L1602-L1604
One thing that's useful here is that `is_view` is handled early, like this:
https://github.com/simonw/datasette/blob/db1a88f4e17a1f50bdaa681e8beddb2276503e7c/datasette/views/table.py#L466-L472
So if I omit the `is_view` bit from the extracted function I can simplify more.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1551694938,?_extra= support (draft),
https://github.com/simonw/datasette/pull/1999#issuecomment-1460905469,https://api.github.com/repos/simonw/datasette/issues/1999,1460905469,IC_kwDOBm6k_c5XE6X9,9599,simonw,2023-03-08T21:32:56Z,2023-03-08T21:32:56Z,OWNER,"I'd really like to extract this ugly logic out into a helper function:
https://github.com/simonw/datasette/blob/db1a88f4e17a1f50bdaa681e8beddb2276503e7c/datasette/views/table.py#L1617-L1684
I copied it in and asked ChatGPT to ""List all of the variable that are either modified or assigned to by the above code"":
> Modified variables:
>
> offset
> where_clauses
> params
> order_by
>
> Assigned variables:
>
> sort_value
> next_by_pk_clauses
> order_by (when sort or sort_desc is not None)
Then I asked which variables were used as inputs, and argued with it a bit about whether it should be counting functions. Eventually got to this:
> My apologies for the oversight. Here are the variables needed as input by the above code, excluding any functions:
>
> _next
> is_view
> sort
> sort_desc
> use_rowid
> pks
> order_by
Note that `use_rowid` is actually defined earlier in terms of two of those other variables: https://github.com/simonw/datasette/blob/db1a88f4e17a1f50bdaa681e8beddb2276503e7c/datasette/views/table.py#L1540","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1551694938,?_extra= support (draft),
https://github.com/simonw/datasette/issues/2036#issuecomment-1460866243,https://api.github.com/repos/simonw/datasette/issues/2036,1460866243,IC_kwDOBm6k_c5XEwzD,9599,simonw,2023-03-08T20:57:34Z,2023-03-08T20:57:34Z,OWNER,This fix is released in 0.64.2 https://docs.datasette.io/en/stable/changelog.html#v0-64-2,"{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1615862295,"`publish cloudrun` reuses image tags, which can lead to very surprising deploy problems",
https://github.com/simonw/datasette/issues/2036#issuecomment-1460848869,https://api.github.com/repos/simonw/datasette/issues/2036,1460848869,IC_kwDOBm6k_c5XEsjl,9599,simonw,2023-03-08T20:40:55Z,2023-03-08T20:40:55Z,OWNER,"Here's the https://latest.datasette.io/ deployment that just went out, further demonstrating that this change is working correctly:
","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1615862295,"`publish cloudrun` reuses image tags, which can lead to very surprising deploy problems",
https://github.com/simonw/datasette/issues/2037#issuecomment-1460840620,https://api.github.com/repos/simonw/datasette/issues/2037,1460840620,IC_kwDOBm6k_c5XEqis,9599,simonw,2023-03-08T20:33:00Z,2023-03-08T20:33:00Z,OWNER,Got the same failure again for a recent commit: https://github.com/simonw/datasette/actions/runs/4368239376/jobs/7640567282,"{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1615891776,Test failure: FAILED tests/test_cli.py::test_install_requirements - FileNotFoundError,
https://github.com/simonw/datasette/issues/2037#issuecomment-1460838797,https://api.github.com/repos/simonw/datasette/issues/2037,1460838797,IC_kwDOBm6k_c5XEqGN,9599,simonw,2023-03-08T20:31:15Z,2023-03-08T20:31:15Z,OWNER,"It's this test here:
https://github.com/simonw/datasette/blob/1ad92a1d87d79084ebe524ed186c900ff042328c/tests/test_cli.py#L181-L189
Added in:
- #2033 ","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1615891776,Test failure: FAILED tests/test_cli.py::test_install_requirements - FileNotFoundError,
https://github.com/simonw/datasette/issues/2037#issuecomment-1460838109,https://api.github.com/repos/simonw/datasette/issues/2037,1460838109,IC_kwDOBm6k_c5XEp7d,9599,simonw,2023-03-08T20:30:36Z,2023-03-08T20:30:36Z,OWNER,Instead of using `isolated_filesystem()` I could use a `tmpdir` fixture instead.,"{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1615891776,Test failure: FAILED tests/test_cli.py::test_install_requirements - FileNotFoundError,
https://github.com/simonw/datasette/issues/2036#issuecomment-1460827178,https://api.github.com/repos/simonw/datasette/issues/2036,1460827178,IC_kwDOBm6k_c5XEnQq,9599,simonw,2023-03-08T20:25:10Z,2023-03-08T20:25:10Z,OWNER,"https://console.cloud.google.com/run/detail/us-central1/new-service/revisions?project=datasette-222320 confirms that the image deployed is:
Compared to https://console.cloud.google.com/run/detail/us-central1/datasette-io/revisions?project=datasette-222320 which shows that `datasette.io` is running:
","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1615862295,"`publish cloudrun` reuses image tags, which can lead to very surprising deploy problems",
https://github.com/simonw/datasette/issues/2036#issuecomment-1460816528,https://api.github.com/repos/simonw/datasette/issues/2036,1460816528,IC_kwDOBm6k_c5XEkqQ,9599,simonw,2023-03-08T20:22:50Z,2023-03-08T20:23:20Z,OWNER,"Testing this manually:
```
% datasette publish cloudrun content.db --service new-service
Creating temporary tarball archive of 2 file(s) totalling 13.8 MiB before compression.
Uploading tarball of [.] to [gs://datasette-222320_cloudbuild/source/1678306859.271661-805303f364144b6094cc9c8532ab5133.tgz]
Created [https://cloudbuild.googleapis.com/v1/projects/datasette-222320/locations/global/builds/290f41a4-e29a-443c-a1e5-c54513c6143d].
Logs are available at [ https://console.cloud.google.com/cloud-build/builds/290f41a4-e29a-443c-a1e5-c54513c6143d?project=99025868001 ].
---- REMOTE BUILD OUTPUT ----
starting build ""290f41a4-e29a-443c-a1e5-c54513c6143d""
FETCHSOURCE
Fetching storage object: gs://datasette-222320_cloudbuild/source/1678306859.271661-805303f364144b6094cc9c8532ab5133.tgz#1678306862810483
Copying gs://datasette-222320_cloudbuild/source/1678306859.271661-805303f364144b6094cc9c8532ab5133.tgz#1678306862810483...
/ [1 files][ 3.9 MiB/ 3.9 MiB]
Operation completed over 1 objects/3.9 MiB.
BUILD
Already have image (with digest): gcr.io/cloud-builders/docker
Sending build context to Docker daemon 14.52MB
Step 1/9 : FROM python:3.11.0-slim-bullseye
...
Installing collected packages: rfc3986, typing-extensions, sniffio, PyYAML, python-multipart, pluggy, pint, mergedeep, MarkupSafe, itsdangerous, idna, hupper, h11, click, certifi, asgiref, aiofiles, uvicorn, Jinja2, janus, click-default-group-wheel, asgi-csrf, anyio, httpcore, httpx, datasette
Successfully installed Jinja2-3.1.2 MarkupSafe-2.1.2 PyYAML-6.0 aiofiles-23.1.0 anyio-3.6.2 asgi-csrf-0.9 asgiref-3.6.0 certifi-2022.12.7 click-8.1.3 click-default-group-wheel-1.2.2 datasette-0.64.1 h11-0.14.0 httpcore-0.16.3 httpx-0.23.3 hupper-1.11 idna-3.4 itsdangerous-2.1.2 janus-1.0.0 mergedeep-1.3.4 pint-0.20.1 pluggy-1.0.0 python-multipart-0.0.6 rfc3986-1.5.0 sniffio-1.3.0 typing-extensions-4.5.0 uvicorn-0.20.0
WARNING: Running pip as the 'root' user can result in broken permissions and conflicting behaviour with the system package manager. It is recommended to use a virtual environment instead: https://pip.pypa.io/warnings/venv
[notice] A new release of pip available: 22.3 -> 23.0.1
[notice] To update, run: pip install --upgrade pip
Removing intermediate container 8ccebfebebc9
---> b972c85b38bb
...
Successfully built 606b7c286d7f
Successfully tagged gcr.io/datasette-222320/datasette-new-service:latest
PUSH
Pushing gcr.io/datasette-222320/datasette-new-service
The push refers to repository [gcr.io/datasette-222320/datasette-new-service]
667b1dc69e5e: Preparing
...
d8ddfcff216f: Pushed
latest: digest: sha256:452daffb2d3d7a8579c2ab39854be285155252c9428b4c1c50caac6a3a269e3f size: 2004
DONE
---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
ID CREATE_TIME DURATION SOURCE IMAGES STATUS
290f41a4-e29a-443c-a1e5-c54513c6143d 2023-03-08T20:21:03+00:00 39S gs://datasette-222320_cloudbuild/source/1678306859.271661-805303f364144b6094cc9c8532ab5133.tgz gcr.io/datasette-222320/datasette-new-service (+1 more) SUCCESS
Deploying container to Cloud Run service [new-service] in project [datasette-222320] region [us-central1]
✓ Deploying new service... Done.
✓ Creating Revision...
✓ Routing traffic...
✓ Setting IAM Policy...
Done.
Service [new-service] revision [new-service-00001-zon] has been deployed and is serving 100 percent of traffic.
Service URL: https://new-service-j7hipcg4aq-uc.a.run.app
```
https://new-service-j7hipcg4aq-uc.a.run.app/ was deployed successfully.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1615862295,"`publish cloudrun` reuses image tags, which can lead to very surprising deploy problems",
https://github.com/simonw/datasette/issues/2036#issuecomment-1460810523,https://api.github.com/repos/simonw/datasette/issues/2036,1460810523,IC_kwDOBm6k_c5XEjMb,9599,simonw,2023-03-08T20:17:01Z,2023-03-08T20:17:01Z,OWNER,"I'm going to solve this by using the service name in that `image_id` instead:
```python
image_id = f""gcr.io/{project}/{service_name}""
```
This is a nasty bug, so I'm going to backport it to a `0.64.2` release as well.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1615862295,"`publish cloudrun` reuses image tags, which can lead to very surprising deploy problems",
https://github.com/simonw/datasette/issues/2036#issuecomment-1460809643,https://api.github.com/repos/simonw/datasette/issues/2036,1460809643,IC_kwDOBm6k_c5XEi-r,9599,simonw,2023-03-08T20:16:10Z,2023-03-08T20:16:10Z,OWNER,"I think the code at fault is here:
https://github.com/simonw/datasette/blob/1ad92a1d87d79084ebe524ed186c900ff042328c/datasette/publish/cloudrun.py#L176-L182
That name ends up defaulting to `datasette` - so multiple different projects may end up deploying to the same `image_id`.
What I think happened in the `datasette.io` bug is that this workflow: https://github.com/simonw/simonwillisonblog-backup/blob/bfb573e96d8622ab52b22fdcd54724fe6e59fd24/.github/workflows/backup.yml and this workflow: https://github.com/simonw/datasette.io/blob/4676db5bf4a3fc9f792ee270ec0c59eb902cd2c3/.github/workflows/deploy.yml both happened to run at the exact same time.
And so the image that was pushed to `gcr.io/datasette-222320/datasette:latest` by the `simonw/simonwillisonblog-backup` action was then deployed by the `simonw/datasette.io/` action, which broke the site.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1615862295,"`publish cloudrun` reuses image tags, which can lead to very surprising deploy problems",
https://github.com/simonw/datasette/issues/2035#issuecomment-1460808028,https://api.github.com/repos/simonw/datasette/issues/2035,1460808028,IC_kwDOBm6k_c5XEilc,1176293,ar-jan,2023-03-08T20:14:47Z,2023-03-08T20:14:47Z,NONE,"+1, I have been wishing for this feature (also for use with template-sql). It was requested before here #1304.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1615692818,Potential feature: special support for `?a=1&a=2` on the query page,
https://github.com/simonw/datasette/pull/1999#issuecomment-1460760116,https://api.github.com/repos/simonw/datasette/issues/1999,1460760116,IC_kwDOBm6k_c5XEW40,9599,simonw,2023-03-08T19:48:52Z,2023-03-08T19:48:52Z,OWNER,"I'm trying to get `http://127.0.0.1:8001/fixtures/compound_three_primary_keys?_next=a,d,v` to return the correct results.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1551694938,?_extra= support (draft),
https://github.com/simonw/datasette/pull/1999#issuecomment-1460759358,https://api.github.com/repos/simonw/datasette/issues/1999,1460759358,IC_kwDOBm6k_c5XEWs-,9599,simonw,2023-03-08T19:48:13Z,2023-03-20T18:47:12Z,OWNER,"Breaking this down into smaller steps:
- [x] Get `?_next=` working
- [x] Implement extensions - so `.json` is needed again for the JSON version, and anything without an extension is passed through a new code path for HTML
- [ ] That HTML view should only access JSON data, which can be seen by using `.context` - this will require a lot of updates to templates (it may be necessary to still provide access to some helper functions though). This will form the basis of the ambition to fully document the template context.
- [ ] Get a bunch of the existing table HTML and JSON tests to pass
- [ ] Use those tests to refactor the nasty `_next` code, see https://github.com/simonw/datasette/pull/1999#issuecomment-1460905469
- [ ] Figure out how the [register_output_renderer(datasette)](https://docs.datasette.io/en/stable/plugin_hooks.html#register-output-renderer-datasette) plugin hook should work","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1551694938,?_extra= support (draft),
https://github.com/simonw/datasette/issues/2035#issuecomment-1460682625,https://api.github.com/repos/simonw/datasette/issues/2035,1460682625,IC_kwDOBm6k_c5XED-B,9599,simonw,2023-03-08T18:40:57Z,2023-03-08T18:40:57Z,OWNER,Pushed that prototype to a branch: https://github.com/simonw/datasette/commit/0fe844e9adb006a0138e83102ced1329d9155c59 / https://github.com/simonw/datasette/compare/sql-list-parameters,"{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1615692818,Potential feature: special support for `?a=1&a=2` on the query page,
https://github.com/simonw/datasette/issues/2035#issuecomment-1460679434,https://api.github.com/repos/simonw/datasette/issues/2035,1460679434,IC_kwDOBm6k_c5XEDMK,9599,simonw,2023-03-08T18:39:35Z,2023-03-08T18:39:35Z,OWNER,"I should consider the existing design of magic parameters here: https://docs.datasette.io/en/stable/sql_queries.html#magic-parameters
- `_actor_*`
- `_header_*`
- `_cookie_`
- `_now_epoch`
- `_now_date_utc`
- `_now_datetime_utc`
- `_random_chars_*`
Should this new `id__list` syntax look more like those magic parameters, or is it OK to use `name__magic` syntax here instead?","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1615692818,Potential feature: special support for `?a=1&a=2` on the query page,
https://github.com/simonw/datasette/issues/2035#issuecomment-1460668431,https://api.github.com/repos/simonw/datasette/issues/2035,1460668431,IC_kwDOBm6k_c5XEAgP,9599,simonw,2023-03-08T18:35:34Z,2023-03-08T18:35:34Z,OWNER,"To implement this properly need to do the following:
- Get the page to display multiple `id: [ text input here ]` fields such that re-submission works
- Figure out how this should work for canned queries and for writable canned queries
- Tests that cover queries, canned queries, writable canned queries
And a bonus feature: what if the Datasette UI layer spotted `:id__list` parameters and used them to add a bit of JavaScript that allowed users to click a `+` button next to an `id` form field to add another one?
Also, when a page is re-displayed for on of these queries it could potentially add an extra form field allowing people to add another value.
Though this has an annoying problem: how to tell the difference between an additional `id` input field that the user chose not to populate, v.s. one that is supposed to represent an empty string?
Maybe only support multiple `id` fields for users with JavaScript in order to avoid this problem.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1615692818,Potential feature: special support for `?a=1&a=2` on the query page,
https://github.com/simonw/datasette/issues/2035#issuecomment-1460664619,https://api.github.com/repos/simonw/datasette/issues/2035,1460664619,IC_kwDOBm6k_c5XD_kr,9599,simonw,2023-03-08T18:32:29Z,2023-03-08T18:32:29Z,OWNER,"Got a prototype working:
```diff
diff --git a/datasette/views/database.py b/datasette/views/database.py
index 8d289105..6f9d8a44 100644
--- a/datasette/views/database.py
+++ b/datasette/views/database.py
@@ -226,6 +226,12 @@ class QueryView(DataView):
):
db = await self.ds.resolve_database(request)
database = db.name
+ # Disallow x__list query string parameters
+ invalid_params = [k for k in request.args if k.endswith(""__list"")]
+ if invalid_params:
+ raise DatasetteError(
+ ""Invalid query string parameters: {}"".format("", "".join(invalid_params))
+ )
params = {key: request.args.get(key) for key in request.args}
if ""sql"" in params:
params.pop(""sql"")
@@ -258,6 +264,11 @@ class QueryView(DataView):
for named_parameter in named_parameters
if not named_parameter.startswith(""_"")
}
+ # Handle any __list parameters
+ for named_parameter in named_parameters:
+ if named_parameter.endswith(""__list""):
+ list_values = request.args.getlist(named_parameter[:-6])
+ params[named_parameter] = json.dumps(list_values)
# Set to blank string if missing from params
for named_parameter in named_parameters:
```
This isn't yet doing the right thing on form re-submission: it breaks because it attempts to pass through the `?id__list=` invalid parameter. But I did manage to get it to do this through careful editing of the URL:
That was this URL: `http://127.0.0.1:8034/content?sql=select+%3Aid__list%2C*+from+releases+where+id+in+(select+value+from+json_each(%3Aid__list))&id=62642726&id=18402901&id=38714866`","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1615692818,Potential feature: special support for `?a=1&a=2` on the query page,
https://github.com/simonw/datasette/issues/2035#issuecomment-1460659382,https://api.github.com/repos/simonw/datasette/issues/2035,1460659382,IC_kwDOBm6k_c5XD-S2,9599,simonw,2023-03-08T18:28:00Z,2023-03-08T18:28:00Z,OWNER,"Also: `datasette-explain` may need to be updated to understand how to handle this:
`ERROR: conn=, sql = 'explain select * from releases where id in (select id from json_each(:id__list))', params = None: You did not supply a value for binding parameter :id__list.`
","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1615692818,Potential feature: special support for `?a=1&a=2` on the query page,
https://github.com/simonw/datasette/issues/2035#issuecomment-1460654136,https://api.github.com/repos/simonw/datasette/issues/2035,1460654136,IC_kwDOBm6k_c5XD9A4,9599,simonw,2023-03-08T18:25:46Z,2023-03-08T18:25:46Z,OWNER,"Trickiest part of the implementation here is that it needs to know to output three `id` HTML form fields on the page, such that their values are persisted when the form is submitted a second time.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1615692818,Potential feature: special support for `?a=1&a=2` on the query page,
https://github.com/simonw/datasette/issues/2035#issuecomment-1460639749,https://api.github.com/repos/simonw/datasette/issues/2035,1460639749,IC_kwDOBm6k_c5XD5gF,9599,simonw,2023-03-08T18:17:31Z,2023-03-08T18:17:31Z,OWNER,"Since we are pre-1.0 it's still OK to implement a feature that disallows `?id__list=` in the URL, but allows `:id__list` in SQL queries to reference the JSON list of parameters.
So I'm going to prototype this as the `:id__list` feature and see how it feels.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1615692818,Potential feature: special support for `?a=1&a=2` on the query page,
https://github.com/simonw/datasette/issues/2035#issuecomment-1460637906,https://api.github.com/repos/simonw/datasette/issues/2035,1460637906,IC_kwDOBm6k_c5XD5DS,9599,simonw,2023-03-08T18:16:31Z,2023-03-08T18:16:31Z,OWNER,"I'm pretty sold on this as a feature now. The main question I have is which of these options to implement:
1. `?id=1&?id=2` results in `:id` in the query being `[""1"", ""2""]` - no additional syntax required
2. `:id` in the query continues to reference just the first of those parameters - but `:id__list` (or some other custom syntax) instead gets `[""1"", ""2""]` - or, if the URL is `?id=1` - gets `[""1""]`
Actually on writing these out I realize that option 2 is the ONLY valid option. It's no good building a query that works against a JSON list if the user might pass just a single ID, `?id=1`, resulting in their query breaking.","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",1615692818,Potential feature: special support for `?a=1&a=2` on the query page,
https://github.com/simonw/datasette/issues/2035#issuecomment-1460632758,https://api.github.com/repos/simonw/datasette/issues/2035,1460632758,IC_kwDOBm6k_c5XD3y2,9599,simonw,2023-03-08T18:13:49Z,2023-03-08T18:13:49Z,OWNER,"https://github.com/rclement/datasette-dashboards/issues/54 makes the excellent point that the `