issue_comments: 623806533
This data as json
| html_url | issue_url | id | node_id | user | created_at | updated_at | author_association | body | reactions | issue | performed_via_github_app |
|---|---|---|---|---|---|---|---|---|---|---|---|
| https://github.com/dogsheep/dogsheep-photos/issues/16#issuecomment-623806533 | https://api.github.com/repos/dogsheep/dogsheep-photos/issues/16 | 623806533 | MDEyOklzc3VlQ29tbWVudDYyMzgwNjUzMw== | 9599 | 2020-05-05T02:50:16Z | 2020-05-05T02:50:16Z | MEMBER | I figured there must be a separate database that Photos uses to store the text of the identified labels. I used "Open Files and Ports" in Activity Monitor against the Photos app to try and spot candidates... and found `/Users/simon/Pictures/Photos Library.photoslibrary/database/search/psi.sqlite` - a 53MB SQLite database file. <img width="1365" alt="Item-0_and_Item-0_and_Item-0_and_Item-0" src="https://user-images.githubusercontent.com/9599/81031213-61ea0800-8e40-11ea-8237-cfce4a5128e0.png"> Here's the schema of that file: ``` $ sqlite3 psi.sqlite .schema CREATE TABLE word_embedding(word TEXT, extended_word TEXT, score DOUBLE); CREATE INDEX word_embedding_index ON word_embedding(word); CREATE VIRTUAL TABLE word_embedding_prefix USING fts5(extended_word) /* word_embedding_prefix(extended_word) */; CREATE TABLE IF NOT EXISTS 'word_embedding_prefix_data'(id INTEGER PRIMARY KEY, block BLOB); CREATE TABLE IF NOT EXISTS 'word_embedding_prefix_idx'(segid, term, pgno, PRIMARY KEY(segid, term)) WITHOUT ROWID; CREATE TABLE IF NOT EXISTS 'word_embedding_prefix_content'(id INTEGER PRIMARY KEY, c0); CREATE TABLE IF NOT EXISTS 'word_embedding_prefix_docsize'(id INTEGER PRIMARY KEY, sz BLOB); CREATE TABLE IF NOT EXISTS 'word_embedding_prefix_config'(k PRIMARY KEY, v) WITHOUT ROWID; CREATE TABLE groups(category INT2, owning_groupid INT, content_string TEXT, normalized_string TEXT, lookup_identifier TEXT, token_ranges_0 INT8, token_ranges_1 INT8, UNIQUE(category, owning_groupid, content_string, lookup_identifier, token_ranges_0, token_ranges_1)); CREATE TABLE assets(uuid_0 INT, uuid_1 INT, creationDate INT, UNIQUE(uuid_0, uuid_1)); CREATE TABLE ga(groupid INT, assetid INT, PRIMARY KEY(groupid, assetid)); CREATE TABLE collections(uuid_0 INT, uuid_1 INT, startDate INT, endDate INT, title TEXT, subtitle TEXT, keyAssetUUID_0 INT, keyAssetUUID_1 INT, typeAndNumberOfAssets INT32, sortDate DOUBLE, UNIQUE(uuid_0, uuid_1)); CREATE TABLE gc(groupid INT, collectionid INT, PRIMARY KEY(groupid, collectionid)); CREATE VIRTUAL TABLE prefix USING fts5(content='groups', normalized_string, category UNINDEXED, tokenize = 'PSITokenizer'); CREATE TABLE IF NOT EXISTS 'prefix_data'(id INTEGER PRIMARY KEY, block BLOB); CREATE TABLE IF NOT EXISTS 'prefix_idx'(segid, term, pgno, PRIMARY KEY(segid, term)) WITHOUT ROWID; CREATE TABLE IF NOT EXISTS 'prefix_docsize'(id INTEGER PRIMARY KEY, sz BLOB); CREATE TABLE IF NOT EXISTS 'prefix_config'(k PRIMARY KEY, v) WITHOUT ROWID; CREATE TABLE lookup(identifier TEXT PRIMARY KEY, category INT2); CREATE TRIGGER trigger_groups_insert AFTER INSERT ON groups BEGIN INSERT INTO prefix(rowid, normalized_string, category) VALUES (new.rowid, new.normalized_string, new.category); END; CREATE TRIGGER trigger_groups_delete AFTER DELETE ON groups BEGIN INSERT INTO prefix(prefix, rowid, normalized_string, category) VALUES('delete', old.rowid, old.normalized_string, old.category); END; CREATE INDEX group_pk ON groups(category, content_string, normalized_string, lookup_identifier); CREATE INDEX asset_pk ON assets(uuid_0, uuid_1); CREATE INDEX ga_assetid ON ga(assetid, groupid); CREATE INDEX collection_pk ON collections(uuid_0, uuid_1); CREATE INDEX gc_collectionid ON gc(collectionid); ``` | {"total_count": 0, "+1": 0, "-1": 0, "laugh": 0, "hooray": 0, "confused": 0, "heart": 0, "rocket": 0, "eyes": 0} | 612287234 |