fix(tagging): Tag output images tags each image, not its prompt (#379, PR 1)
The native "Tag output images" job now runs the image-tags loop over every still image the output folders list, linked or not: each image gets its own model tags (at most "Suggestions per image") in its image tag set, and its bytes are marked auto-tagged in a new media_image_autotags table. No prompt tag or prompt text is written. - database/autotag_schema.py: one forward-only WITHOUT ROWID table, optional in old backups, refused without the annotation group. - add_image_tags/replace_image_tags take mark_autotagged; autotag_state and autotagged_locators read the marks through the one current-record rule. - "Skip already tagged" skips images whose current bytes are marked, counted in a stat-only pre-pass; hand tags do not count. - The review counts images and estimates the time (WD14 on CPU or CUDA). - System > Auto-tagging review rows and copy, D134 and the Auto-tagging contract follow. Part of #379
This commit is contained in:
Vito Sansevero
@@ -33,7 +33,7 @@ test.afterEach(async ({ page, request, browserName }) => {
|
||||
const PREVIEW_URL = '/prompt_manager/autotag/batch/preview';
|
||||
const MODEL_OPTIONS = ['WD14 SwinV2 · ~400 MB', 'WD14 ViT · ~400 MB', 'GGUF JoyCaption · ~4.5 GB', 'HuggingFace JoyCaption · ~16 GB'];
|
||||
const SUGGESTIONS = 'From 1 to 100: the most suggestions Generate shows for one image.';
|
||||
const BATCH = 'Add tags to each prompt from its linked output images with the model above. Review the scope first.';
|
||||
const BATCH = 'Tag each output image from its own pixels with the model above. Prompts are not changed. Review the scope first.';
|
||||
|
||||
/** Runs in the page: Auto-tagging's surface under `mainSelector`: rows, field, actions, operation, geometry and tokens. */
|
||||
function measureTagging(mainSelector) {
|
||||
@@ -272,11 +272,19 @@ function measureReview() {
|
||||
}
|
||||
|
||||
const number = value => value.toLocaleString('en-US');
|
||||
/** DEC11 (#379): the Time row the preview's estimate reads as (WD14 on the test server's processor). */
|
||||
function timeRow(plan) {
|
||||
const minutes = Math.max(1, Math.ceil(plan.estimate_seconds / 60));
|
||||
const text = minutes < 90 ? `about ${minutes} min`
|
||||
: `about ${Math.floor(minutes / 60)} h${minutes % 60 ? ` ${minutes % 60} min` : ''}`;
|
||||
return `${text} on a processor; a graphics card can be faster.`;
|
||||
}
|
||||
|
||||
/**
|
||||
* D134: the server's batch preview in the concept's review: "Review tag output images" with "Tag output images" as its
|
||||
* `h3`, the model, policy, counts and settings in the concept's `dl.meta-grid` (Backup in the concept's wording), the
|
||||
* upper-bound sentence in the concept's `p.small`, the D55 backup box and Cancel / "Start tagging".
|
||||
* D134 (#379): the server's batch preview in the concept's review: "Review tag output images" with "Tag output images"
|
||||
* as its `h3`, the model, policy, image counts, time estimate and settings in the concept's `dl.meta-grid` (Backup in
|
||||
* the concept's wording), the estimate sentence in the concept's `p.small`, the D55 backup box and Cancel / "Start
|
||||
* tagging".
|
||||
*/
|
||||
function mapBatchConcept(reference, plan) {
|
||||
const [cancel, start] = reference.actions.buttons;
|
||||
@@ -286,13 +294,14 @@ function mapBatchConcept(reference, plan) {
|
||||
tree: ['h3', 'dl.meta-grid', 'p.small', 'div.notice', 'div.dialog-actions'],
|
||||
heading: { ...reference.heading, text: 'Tag output images' },
|
||||
grid: { ...reference.grid, rows: [['Model', 'WD14 SwinV2 · ~400 MB'], ['Existing tags', 'Merge with existing'],
|
||||
['Images linked', number(plan.images)], ['Prompts', number(plan.prompts)], ['Already tagged', number(plan.already_tagged)],
|
||||
['Prompts to tag', `up to ${number(plan.to_tag)}`], ['Settings', 'General 0.35 · Character 0.85'],
|
||||
['Images', number(plan.images)], ['Already auto-tagged', number(plan.already_tagged)],
|
||||
['Images to tag', `about ${number(plan.to_tag)}`], ['Time', timeRow(plan)],
|
||||
['Settings', `General 0.35 · Character 0.85 · up to ${number(plan.suggestion_limit)} tags per image`],
|
||||
['Backup', 'Create and verify before changes']] },
|
||||
backup: { tree: ['div', 'div.row-actions'], text: [['h3', 'Back up the database first (recommended)'],
|
||||
['p', 'Downloads a copy of the prompts database before this operation changes any records.']], buttons: ['Back up now'] },
|
||||
note: { ...reference.note, text: 'Nothing is written until you start. Missing files and files outside the output folders '
|
||||
+ 'are counted, so the prompts to tag are an upper bound; Activity reports what was tagged.' },
|
||||
note: { ...reference.note, text: 'Nothing is written until you start. The number to tag is an estimate: images changed '
|
||||
+ 'since they were tagged are tagged again, and missing files are skipped. Activity reports what was tagged.' },
|
||||
actions: { ...reference.actions, buttons: [cancel, { ...start, text: 'Start tagging' }] },
|
||||
};
|
||||
}
|
||||
@@ -308,8 +317,8 @@ async function conceptReview(page, theme) {
|
||||
|
||||
async function productionReview(page, theme) {
|
||||
await productionTagging(page, theme);
|
||||
// Every concept-fixture prompt with an image is already tagged, so under the saved Skip there is nothing to start
|
||||
// (the Cancel-only review). Merge reviews a batch with work: the full review the concept's shell is compared with.
|
||||
// Merge reviews every listed still image (#379): a batch with work, the full review the concept's shell is compared
|
||||
// with.
|
||||
await page.locator('#workspace-main #tag-existing').selectOption('merge');
|
||||
const answer = page.waitForResponse(response => response.url().endsWith(PREVIEW_URL));
|
||||
await page.locator('#workspace-main .operation').getByRole('button', { name: 'Review', exact: true }).click();
|
||||
@@ -326,8 +335,9 @@ for (const theme of THEMES) for (const [width, height] of SIZES) {
|
||||
expect(concept.tree).toEqual(['p.demo-note', 'h3', 'dl.meta-grid', 'p.small', 'div.dialog-actions']);
|
||||
await page.screenshot({ path: testInfo.outputPath(`concept-plan-review-${theme}-${width}.png`) });
|
||||
const { plan, production } = await productionReview(page, theme);
|
||||
// Under Merge every prompt with a linked image is tagged again: the batch has work to review.
|
||||
// Under Merge every listed still image is tagged again: the batch has work to review.
|
||||
expect(plan.to_tag).toBeGreaterThan(0);
|
||||
expect(plan.estimate_device).toBe('cpu');
|
||||
await page.screenshot({ path: testInfo.outputPath(`production-tagging-review-${theme}-${width}.png`) });
|
||||
expect(diffInventory(mapBatchConcept(concept, plan), production)).toEqual([]);
|
||||
});
|
||||
@@ -372,9 +382,17 @@ test('tag output images review comparison detects mutations', async ({ page }) =
|
||||
const expected = mapBatchConcept(concept, plan);
|
||||
const paths = async () => diffInventory(expected, await page.evaluate(measureReview)).map(item => item.path);
|
||||
expect(await paths()).toEqual([]);
|
||||
await page.evaluate(() => { document.querySelectorAll('dialog#modal[open] dl.meta-grid dt')[5].textContent = 'To tag'; });
|
||||
expect(await paths()).toEqual(['grid.rows.5.0']);
|
||||
await page.evaluate(() => { document.querySelectorAll('dialog#modal[open] dl.meta-grid dt')[5].textContent = 'Prompts to tag'; });
|
||||
// Every label of the grid is compared (#379's rows included): a changed one is named by its row.
|
||||
for (const [index, [term]] of expected.grid.rows.entries()) {
|
||||
await page.evaluate(([at, label]) => {
|
||||
document.querySelectorAll('dialog#modal[open] dl.meta-grid dt')[at].textContent = label;
|
||||
}, [index, `${term}!`]);
|
||||
expect(await paths()).toEqual([`grid.rows.${index}.0`]);
|
||||
await page.evaluate(([at, label]) => {
|
||||
document.querySelectorAll('dialog#modal[open] dl.meta-grid dt')[at].textContent = label;
|
||||
}, [index, term]);
|
||||
}
|
||||
expect(await paths()).toEqual([]);
|
||||
const undoGrid = await mutate(page, { css: 'dialog#modal dl.meta-grid { column-gap: 3px; }' });
|
||||
expect(await paths()).toEqual(expect.arrayContaining(['grid.columnGap']));
|
||||
await undoGrid();
|
||||
|
||||
@@ -315,22 +315,28 @@ test('Preview tagging review without a selection toasts the D115 sentence', asyn
|
||||
await expect(tagDialog(page)).toHaveCount(0);
|
||||
});
|
||||
|
||||
test('Tag output images reviews the scope and starts a batch job', async ({ page, request }) => {
|
||||
test('Tag output images reviews the images, tags each one and never a prompt (#379)', async ({ page, request }) => {
|
||||
const before = await serverJson(request, '/__test__/tagging/snapshot');
|
||||
await openTagging(page);
|
||||
// The fixture's one prompt is already tagged: under Merge it is tagged again with what its images give.
|
||||
await page.locator('#tag-existing').selectOption('merge');
|
||||
// The saved policy is Skip: no image is auto-tagged yet, so every listed still image is to tag.
|
||||
const previewed = page.waitForResponse(item => new URL(item.url()).pathname === PREVIEW_URL);
|
||||
await reviewButton(page).click();
|
||||
const answer = await previewed;
|
||||
expect(answer.request().postDataJSON()).toEqual({ model_type: 'wd14-swinv2', existing: 'merge' });
|
||||
expect(answer.request().postDataJSON()).toEqual({ model_type: 'wd14-swinv2', existing: 'skip' });
|
||||
const plan = await answer.json();
|
||||
// Four still images (two linked, a copy, an unlinked one); the video is not a target.
|
||||
expect([plan.images, plan.already_tagged, plan.to_tag]).toEqual([4, 0, 4]);
|
||||
expect(plan.prompts).toBeUndefined();
|
||||
await expect(dialog(page).locator('#modal-title')).toHaveText('Review tag output images');
|
||||
await expect(dialog(page).locator('#modal-body > h3')).toHaveText('Tag output images');
|
||||
expect(await gridOf(page)).toEqual([['Model', 'WD14 SwinV2 · ~400 MB'], ['Existing tags', 'Merge with existing'],
|
||||
['Images linked', String(plan.images)], ['Prompts', String(plan.prompts)], ['Already tagged', String(plan.already_tagged)],
|
||||
['Prompts to tag', `up to ${plan.to_tag}`], ['Settings', 'General 0.35 · Character 0.85'],
|
||||
expect(await gridOf(page)).toEqual([['Model', 'WD14 SwinV2 · ~400 MB'], ['Existing tags', 'Skip already tagged'],
|
||||
['Images', '4'], ['Already auto-tagged', '0'], ['Images to tag', 'about 4'],
|
||||
['Time', 'about 1 min on a processor; a graphics card can be faster.'],
|
||||
['Settings', `General 0.35 · Character 0.85 · up to ${plan.suggestion_limit} tags per image`],
|
||||
['Backup', 'Create and verify before changes']]);
|
||||
await expect(dialog(page).locator('#modal-body > p.small')).toHaveText('Nothing is written until you start. The number to '
|
||||
+ 'tag is an estimate: images changed since they were tagged are tagged again, and missing files are skipped. '
|
||||
+ 'Activity reports what was tagged.');
|
||||
await expect(dialog(page).locator('#modal-body > .notice h3')).toHaveText('Back up the database first (recommended)');
|
||||
// The review wrote nothing.
|
||||
expect(await serverJson(request, '/__test__/tagging/snapshot')).toEqual(before);
|
||||
@@ -338,15 +344,23 @@ test('Tag output images reviews the scope and starts a batch job', async ({ page
|
||||
const started = page.waitForResponse(item => new URL(item.url()).pathname === '/prompt_manager/jobs/autotag');
|
||||
await dialog(page).getByRole('button', { name: 'Start tagging', exact: true }).click();
|
||||
const start = await started;
|
||||
expect(start.request().postDataJSON()).toEqual({ model_type: 'wd14-swinv2', existing: 'merge',
|
||||
expect(start.request().postDataJSON()).toEqual({ model_type: 'wd14-swinv2', existing: 'skip',
|
||||
options: { general_threshold: 0.35, character_threshold: 0.85 } });
|
||||
const { job } = await start.json();
|
||||
await expect(page).toHaveURL(`${workspace}#/activity/${job.id}`);
|
||||
await expect(page.locator('#workspace-main h1')).toHaveText('Tag output images');
|
||||
const finished = await ended(request, job.id);
|
||||
expect(finished.state).toBe('finished');
|
||||
const after = await serverJson(request, '/__test__/tagging/snapshot');
|
||||
expect(after.prompt_tags.length).toBeGreaterThan(before.prompt_tags.length);
|
||||
expect(finished.status_line).toBe('Tagged 4 images');
|
||||
// Each image got its own tags; no prompt, pair or link row changed.
|
||||
expect(await serverJson(request, '/__test__/tagging/snapshot')).toEqual(before);
|
||||
|
||||
// Under Skip every image is now auto-tagged: nothing to start.
|
||||
await openTagging(page);
|
||||
await reviewButton(page).click();
|
||||
await expect(dialog(page).locator('#modal-body > p.small')).toHaveText('Every output image is already auto-tagged.');
|
||||
expect((await gridOf(page)).slice(2, 5)).toEqual([['Images', '4'], ['Already auto-tagged', '4'], ['Images to tag', 'about 0']]);
|
||||
await expect(dialog(page).locator('.dialog-actions button')).toHaveText(['Cancel']);
|
||||
});
|
||||
|
||||
test('Replace after review shows only Cancel with the reason', async ({ page, request }) => {
|
||||
@@ -355,18 +369,13 @@ test('Replace after review shows only Cancel with the reason', async ({ page, re
|
||||
await page.locator('#tag-existing').selectOption('replace_after_review');
|
||||
await reviewButton(page).click();
|
||||
await expect(dialog(page).locator('#modal-title')).toHaveText('Review tag output images');
|
||||
expect((await gridOf(page)).map(([term]) => term)).toEqual(['Model', 'Existing tags', 'Images linked', 'Prompts', 'Already tagged',
|
||||
'Prompts to tag', 'Settings', 'Backup']);
|
||||
expect((await gridOf(page)).map(([term]) => term)).toEqual(['Model', 'Existing tags', 'Images', 'Already auto-tagged',
|
||||
'Images to tag', 'Time', 'Settings', 'Backup']);
|
||||
await expect(dialog(page).locator('#modal-body > p.small')).toHaveText('Replacing tags needs a review of each image. '
|
||||
+ 'Use Preview tagging review, or choose Skip or Merge for a batch run.');
|
||||
await expect(dialog(page).locator('.dialog-actions button')).toHaveText(['Cancel']);
|
||||
await dialog(page).getByRole('button', { name: 'Cancel', exact: true }).click();
|
||||
await expect(dialog(page)).toHaveCount(0);
|
||||
// Under Skip the fixture's only prompt is already tagged: nothing to start either.
|
||||
await page.locator('#tag-existing').selectOption('skip');
|
||||
await reviewButton(page).click();
|
||||
await expect(dialog(page).locator('#modal-body > p.small')).toHaveText('Every prompt with an output image is already tagged.');
|
||||
await expect(dialog(page).locator('.dialog-actions button')).toHaveText(['Cancel']);
|
||||
expect(await serverJson(request, '/__test__/tagging/snapshot')).toEqual(before);
|
||||
expect((await serverJson(request, '/prompt_manager/jobs')).jobs.filter(item => item.kind === 'autotag')).toEqual([]);
|
||||
});
|
||||
|
||||
@@ -360,19 +360,23 @@ test('Preview tagging review opens the Tag image dialog with the section’s val
|
||||
} finally { scope.dispose(); dom.restore(); }
|
||||
});
|
||||
|
||||
const PLAN = { images: 3, prompts: 2, already_tagged: 1, to_tag: 1,
|
||||
const PLAN = { images: 3, already_tagged: 1, to_tag: 2, estimate_seconds: 3.2, estimate_device: 'cpu', suggestion_limit: 10,
|
||||
model: { type: 'wd14-swinv2', label: 'WD14 SwinV2', size_label: '~400 MB', downloaded: true }, existing: 'skip',
|
||||
review_required: false, backup: { policy: 'on' }, disk: { free_bytes: 10 * 2 ** 30, required_bytes: 2 ** 20, sufficient: true } };
|
||||
|
||||
test('the batch review grid, body and Cancel-only reasons (D134, CUJ 4–5)', async () => {
|
||||
const { batchGrid, batchBody, batchCloseNote, existingLabel, REPLACE_NOTE, NOTHING_TO_TAG, NO_LINKED_IMAGES } = await tagging;
|
||||
test('the batch review grid, body and Cancel-only reasons (D134, #379, CUJ 4–5)', async () => {
|
||||
const { batchGrid, batchBody, batchCloseNote, existingLabel, REPLACE_NOTE, NOTHING_TO_TAG, NO_IMAGES } = await tagging;
|
||||
assert.deepEqual(batchGrid(PLAN, HOST), [['Model', 'WD14 SwinV2 · ~400 MB'], ['Existing tags', 'Skip already tagged'],
|
||||
['Images linked', '3'], ['Prompts', '2'], ['Already tagged', '1'], ['Prompts to tag', 'up to 1'],
|
||||
['Settings', 'General 0.35 · Character 0.85'], ['Backup', 'Create and verify before changes']]);
|
||||
['Images', '3'], ['Already auto-tagged', '1'], ['Images to tag', 'about 2'],
|
||||
['Time', 'about 1 min on a processor; a graphics card can be faster.'],
|
||||
['Settings', 'General 0.35 · Character 0.85 · up to 10 tags per image'], ['Backup', 'Create and verify before changes']]);
|
||||
const llm = { ...HOST, autotag_model_type: 'gguf' };
|
||||
assert.deepEqual(batchGrid({ ...PLAN, model: { type: 'gguf' }, backup: { policy: 'off' } }, llm).slice(-2),
|
||||
[['Settings', 'Template of 27 characters'], ['Backup', 'No safety backup (the policy is off)']]);
|
||||
assert.deepEqual(batchGrid({ ...PLAN, model: { type: 'gguf' }, backup: { policy: 'off' }, estimate_seconds: null,
|
||||
estimate_device: null, suggestion_limit: 4 }, llm).slice(-3),
|
||||
[['Time', 'Language-model engines take longer per image. Activity shows the time left once tagging starts.'],
|
||||
['Settings', 'Template of 27 characters · up to 4 tags per image'], ['Backup', 'No safety backup (the policy is off)']]);
|
||||
assert.equal(batchGrid({}, HOST)[2][1], '0');
|
||||
assert.equal(batchGrid({}, HOST)[6][1], 'General 0.35 · Character 0.85');
|
||||
assert.equal(existingLabel('odd'), 'odd');
|
||||
assert.deepEqual(batchBody(HOST), { model_type: 'wd14-swinv2', existing: 'skip',
|
||||
options: { general_threshold: 0.35, character_threshold: 0.85 } });
|
||||
@@ -385,9 +389,31 @@ test('the batch review grid, body and Cancel-only reasons (D134, CUJ 4–5)', as
|
||||
assert.equal(batchCloseNote({ ...PLAN, model: { ...PLAN.model, downloaded: false } }), 'WD14 SwinV2 is not downloaded. Download it first.');
|
||||
assert.equal(batchCloseNote({ ...PLAN, disk: { free_bytes: 2 ** 20, required_bytes: 2 ** 21, sufficient: false } }),
|
||||
'Not enough free disk space: the safety backup needs about 2.0 MB and 1.0 MB is free. Nothing is written until there is room.');
|
||||
assert.equal(batchCloseNote({ ...PLAN, prompts: 0, to_tag: 0 }), NO_LINKED_IMAGES);
|
||||
assert.equal(batchCloseNote({ ...PLAN, images: 0, to_tag: 0 }), NO_IMAGES);
|
||||
assert.equal(batchCloseNote({ ...PLAN, images: undefined }), NO_IMAGES);
|
||||
assert.equal(NO_IMAGES, 'The output folders contain no images to tag.');
|
||||
assert.equal(batchCloseNote({ ...PLAN, to_tag: 0 }), NOTHING_TO_TAG);
|
||||
assert.equal(NOTHING_TO_TAG, 'Every prompt with an output image is already tagged.');
|
||||
assert.equal(NOTHING_TO_TAG, 'Every output image is already auto-tagged.');
|
||||
});
|
||||
|
||||
test('the review Time row (DEC11, #379): minutes, hours and the engine it runs on', async () => {
|
||||
const { durationText, timeText, TIME_UNKNOWN } = await tagging;
|
||||
assert.equal(durationText(1), 'about 1 min');
|
||||
assert.equal(durationText(0), 'about 1 min');
|
||||
assert.equal(durationText(89), 'about 89 min');
|
||||
assert.equal(durationText(90), 'about 1 h 30 min');
|
||||
assert.equal(durationText(120), 'about 2 h');
|
||||
assert.equal(durationText(631), 'about 10 h 31 min');
|
||||
assert.equal(durationText(Number.NaN), 'about 1 min');
|
||||
// 23,645 images at 1.6 s on a processor (the design's CUJ 1).
|
||||
assert.equal(timeText({ estimate_seconds: 37832, estimate_device: 'cpu' }),
|
||||
'about 10 h 31 min on a processor; a graphics card can be faster.');
|
||||
assert.equal(timeText({ estimate_seconds: 59, estimate_device: 'gpu' }), 'about 1 min on the graphics card.');
|
||||
assert.equal(timeText({ estimate_seconds: 0, estimate_device: 'cpu' }), 'about 1 min on a processor; a graphics card can be faster.');
|
||||
for (const plan of [{ estimate_seconds: null }, {}, { estimate_seconds: -1 }, { estimate_seconds: Infinity }, null]) {
|
||||
assert.equal(timeText(plan), TIME_UNKNOWN);
|
||||
}
|
||||
assert.equal(TIME_UNKNOWN, 'Language-model engines take longer per image. Activity shows the time left once tagging starts.');
|
||||
});
|
||||
|
||||
test('showBatchPlan opens the review with the backup box, or the Cancel-only review', async () => {
|
||||
|
||||
@@ -35,6 +35,8 @@ REVIEW_TABLES = (
|
||||
"media_review_items",
|
||||
"media_review_metadata",
|
||||
)
|
||||
# The auto-tag marks (#379) cite annotation bytes too; an old backup lacks them.
|
||||
CITING_TABLES = REVIEW_TABLES + ("media_image_autotags",)
|
||||
# The exact DDL the plan pins; the module must produce precisely these objects.
|
||||
DDL = {
|
||||
METADATA: (
|
||||
@@ -214,7 +216,7 @@ class AnnotationSchemaTests(unittest.TestCase):
|
||||
"""
|
||||
with closing(sqlite3.connect(path)) as raw, raw:
|
||||
raw.execute("PRAGMA foreign_keys=OFF")
|
||||
for table in REVIEW_TABLES + tuple(reversed(TABLES)):
|
||||
for table in CITING_TABLES + tuple(reversed(TABLES)):
|
||||
raw.execute(f"DROP TABLE {table}")
|
||||
|
||||
def test_fresh_install_and_reopen_is_idempotent(self):
|
||||
|
||||
@@ -561,6 +561,142 @@ class CurrentImageTagsTests(AnnotationTestCase):
|
||||
)
|
||||
|
||||
|
||||
class AutotagMarkTests(AnnotationTestCase):
|
||||
"""The auto-tagged mark (#379): per byte record, written with the tags."""
|
||||
|
||||
def marked(self):
|
||||
conn = self.db.model.get_connection()
|
||||
return sorted(
|
||||
row[0] for row in conn.execute("SELECT * FROM media_image_autotags")
|
||||
)
|
||||
|
||||
def byte_id(self, loc, digest=DIGEST_A):
|
||||
conn = self.db.model.get_connection()
|
||||
return conn.execute(
|
||||
"SELECT b.id FROM media_annotation_bytes b JOIN media_annotation_files f "
|
||||
"ON f.id=b.file_id WHERE f.locator=? AND b.sha256=?",
|
||||
(loc, digest),
|
||||
).fetchone()[0]
|
||||
|
||||
def test_hand_tags_never_mark(self):
|
||||
loc = self.locator("a.png")
|
||||
self.replace(loc, tags=["keeper"])
|
||||
self.add(loc, tags=["more"])
|
||||
self.assertEqual(self.marked(), [])
|
||||
self.assertEqual(self.db.autotag_state({loc: (SIZE, MTIME)}), {loc: False})
|
||||
self.assertEqual(self.db.autotagged_locators(), set())
|
||||
|
||||
def test_model_union_marks_including_replayed_and_empty_results(self):
|
||||
loc = self.locator("a.png")
|
||||
receipt = self.add(loc, tags=["bird"], mark_autotagged=True)
|
||||
self.assertEqual((receipt["added"], receipt["replayed"]), (1, False))
|
||||
self.assertEqual(self.marked(), [self.byte_id(loc)])
|
||||
# A replayed union and an empty result still mark (idempotently).
|
||||
other = self.locator("b.png")
|
||||
self.replace(other, DIGEST_B, ["keeper"])
|
||||
replayed = self.add(other, DIGEST_B, ["KEEPER"], mark_autotagged=True)
|
||||
self.assertTrue(replayed["replayed"])
|
||||
empty = self.locator("c.png")
|
||||
nothing = self.add(empty, tags=[], mark_autotagged=True)
|
||||
self.assertEqual((nothing["tags"], nothing["added"]), ([], 0))
|
||||
self.add(empty, tags=[], mark_autotagged=True)
|
||||
self.assertEqual(
|
||||
self.marked(),
|
||||
sorted(
|
||||
[self.byte_id(loc), self.byte_id(other, DIGEST_B), self.byte_id(empty)]
|
||||
),
|
||||
)
|
||||
self.assertEqual(
|
||||
self.db.autotag_state(
|
||||
{loc: (SIZE, MTIME), other: (SIZE, MTIME), empty: (SIZE, MTIME)}
|
||||
),
|
||||
{loc: True, other: True, empty: True},
|
||||
)
|
||||
self.schema_clean()
|
||||
|
||||
def test_empty_union_without_mark_is_refused(self):
|
||||
with self.assertRaises(ValueError):
|
||||
self.add(self.locator("a.png"), tags=[])
|
||||
self.assertEqual(self.counts()["media_annotation_files"], 0)
|
||||
|
||||
def test_tag_limit_union_writes_no_tag_and_no_mark(self):
|
||||
loc = self.locator("a.png")
|
||||
self.replace(loc, tags=[f"t{i}" for i in range(100)])
|
||||
before = self.rows(*ANNOTATION_TABLES, "tags")
|
||||
with self.assertRaises(AnnotationCommandError) as ctx:
|
||||
self.add(loc, tags=["one more"], mark_autotagged=True)
|
||||
self.assertEqual(ctx.exception.code, "tag-limit")
|
||||
self.assertEqual(self.rows(*ANNOTATION_TABLES, "tags"), before)
|
||||
self.assertEqual(self.marked(), [])
|
||||
|
||||
def test_replace_marks_on_saved_and_replayed_receipts_not_on_conflict(self):
|
||||
loc = self.locator("a.png")
|
||||
saved = self.replace(loc, tags=["a"], mark_autotagged=True)
|
||||
self.assertFalse(saved["replayed"])
|
||||
self.assertEqual(self.marked(), [self.byte_id(loc)])
|
||||
other = self.locator("b.png")
|
||||
self.replace(other, DIGEST_B, ["x"])
|
||||
replayed = self.replace(
|
||||
other, DIGEST_B, ["x"], revision=1, mark_autotagged=True
|
||||
)
|
||||
self.assertTrue(replayed["replayed"])
|
||||
third = self.locator("c.png")
|
||||
self.replace(third, tags=["y"])
|
||||
with self.assertRaises(AnnotationCommandError):
|
||||
self.replace(third, tags=["z"], revision=5, mark_autotagged=True)
|
||||
self.assertEqual(
|
||||
self.marked(), sorted([self.byte_id(loc), self.byte_id(other, DIGEST_B)])
|
||||
)
|
||||
|
||||
def test_mark_follows_the_bytes_not_the_file(self):
|
||||
loc = self.locator("a.png")
|
||||
self.add(loc, tags=["bird"], mark_autotagged=True)
|
||||
# The file's bytes changed: the new record is current and unmarked.
|
||||
self.replace(loc, DIGEST_B, ["hand"], mtime_ns=MTIME + 1)
|
||||
self.assertEqual(self.db.autotag_state({loc: (SIZE, MTIME + 1)}), {loc: False})
|
||||
self.assertEqual(self.db.autotag_state({loc: (SIZE, MTIME)}), {loc: True})
|
||||
# The review's estimate counts any marked record of the locator.
|
||||
self.assertEqual(self.db.autotagged_locators(), {loc})
|
||||
missing = self.locator("none.png")
|
||||
self.assertEqual(self.db.autotag_state({missing: (1, 1)}), {missing: False})
|
||||
|
||||
def test_state_and_tags_choose_the_same_current_record(self):
|
||||
loc = self.locator("a.png")
|
||||
# Two records with the same verified fingerprint: the newest wins.
|
||||
self.replace(loc, DIGEST_A, ["old bytes"])
|
||||
with patch.object(
|
||||
annotations_module, "utc_now_iso", return_value="2099-01-01T00:00:00"
|
||||
):
|
||||
self.add(loc, DIGEST_B, ["new bytes"], mark_autotagged=True)
|
||||
stats = {loc: (SIZE, MTIME)}
|
||||
self.assertEqual(self.db.current_image_tags(stats), {loc: ["new bytes"]})
|
||||
self.assertEqual(self.db.autotag_state(stats), {loc: True})
|
||||
with patch.object(
|
||||
annotations_module, "utc_now_iso", return_value="2199-01-01T00:00:00"
|
||||
):
|
||||
self.add(loc, DIGEST_A, ["older bytes again"])
|
||||
self.assertEqual(
|
||||
self.db.current_image_tags(stats), {loc: ["old bytes", "older bytes again"]}
|
||||
)
|
||||
self.assertEqual(self.db.autotag_state(stats), {loc: False})
|
||||
|
||||
def test_marks_never_touch_prompt_rows(self):
|
||||
conn = self.db.model.get_connection()
|
||||
prompt_id = self.db.save_prompt("a beach", tags=["beach"])
|
||||
before = [
|
||||
[tuple(row) for row in conn.execute(f"SELECT * FROM {table} ORDER BY 1")]
|
||||
for table in ("prompts", "prompt_tags")
|
||||
]
|
||||
self.add(self.locator("a.png"), tags=["bird"], mark_autotagged=True)
|
||||
self.replace(self.locator("b.png"), DIGEST_B, ["waves"], mark_autotagged=True)
|
||||
after = [
|
||||
[tuple(row) for row in conn.execute(f"SELECT * FROM {table} ORDER BY 1")]
|
||||
for table in ("prompts", "prompt_tags")
|
||||
]
|
||||
self.assertIsNotNone(prompt_id)
|
||||
self.assertEqual(after, before)
|
||||
|
||||
|
||||
class AnnotationIsolationTests(AnnotationTestCase):
|
||||
def test_cascade_from_vocabulary_delete_keeps_byte_records(self):
|
||||
loc = self.locator("a.png")
|
||||
|
||||
+9
-163
@@ -1893,13 +1893,15 @@ class TestTagOutputImagesPreview(BatchJobTestCase):
|
||||
self.assertEqual(self.service.generate_calls, [])
|
||||
self.assertEqual(self.service.load_calls, [])
|
||||
|
||||
async def test_preview_counts_skip_and_merge(self):
|
||||
async def test_preview_counts_listed_still_images_not_prompts(self):
|
||||
self._seed()
|
||||
skip = await (await self._preview(existing="skip")).json()
|
||||
# t, f1, f2 and m are listed; gone.png is missing, o.png is outside.
|
||||
self.assertEqual(
|
||||
{k: skip[k] for k in ("images", "prompts", "already_tagged", "to_tag")},
|
||||
{"images": 6, "prompts": 5, "already_tagged": 1, "to_tag": 4},
|
||||
{k: skip[k] for k in ("images", "already_tagged", "to_tag")},
|
||||
{"images": 4, "already_tagged": 0, "to_tag": 4},
|
||||
)
|
||||
self.assertNotIn("prompts", skip)
|
||||
self.assertEqual(
|
||||
skip["model"],
|
||||
{
|
||||
@@ -1916,7 +1918,7 @@ class TestTagOutputImagesPreview(BatchJobTestCase):
|
||||
set(skip["disk"]), {"free_bytes", "required_bytes", "sufficient"}
|
||||
)
|
||||
merge = await (await self._preview(existing="merge")).json()
|
||||
self.assertEqual(merge["to_tag"], 5)
|
||||
self.assertEqual(merge["to_tag"], 4)
|
||||
leaked = [s for s in _strings(skip) if _absolute(s)]
|
||||
self.assertEqual(leaked, [])
|
||||
|
||||
@@ -1924,7 +1926,7 @@ class TestTagOutputImagesPreview(BatchJobTestCase):
|
||||
self._seed()
|
||||
data = await (await self._preview(existing="replace_after_review")).json()
|
||||
self.assertTrue(data["review_required"])
|
||||
self.assertEqual(data["prompts"], 5)
|
||||
self.assertEqual(data["images"], 4)
|
||||
|
||||
async def test_preview_refuses_bad_bodies(self):
|
||||
for body in (
|
||||
@@ -1979,119 +1981,6 @@ class TestTagOutputImagesJob(BatchJobTestCase):
|
||||
"WD14 ViT is not downloaded. Download it in System › Auto-tagging.",
|
||||
)
|
||||
|
||||
async def test_job_writes_what_legacy_writes(self):
|
||||
ids = self._seed()
|
||||
await self._run_job(existing="skip")
|
||||
native = {name: sorted(self._tags(pid)) for name, pid in ids.items()}
|
||||
# The same library through the legacy batch, in a fresh database.
|
||||
for name, pid in ids.items():
|
||||
self.api.db.update_prompt_metadata(
|
||||
pid,
|
||||
tags=(
|
||||
["existing"]
|
||||
if name == "tagged"
|
||||
else (["auto-scanned"] if name == "marked" else [])
|
||||
),
|
||||
)
|
||||
resp = await self.client.post(
|
||||
"/prompt_manager/autotag/start?model_type=wd14-vit&skip_tagged=true"
|
||||
)
|
||||
self.assertEqual(self._sse_events(await resp.text())[-1]["type"], "complete")
|
||||
legacy = {name: sorted(self._tags(pid)) for name, pid in ids.items()}
|
||||
self.assertEqual(native, legacy)
|
||||
self.assertEqual(native["tagged"], ["existing"])
|
||||
self.assertEqual(native["fresh"], ["1girl", "smile"])
|
||||
|
||||
async def test_job_outcomes_follow_the_mapping(self):
|
||||
ids = self._seed()
|
||||
self.api.db.update_prompt_metadata(
|
||||
ids["marked"], tags=["auto-scanned", "1girl", "smile"]
|
||||
)
|
||||
|
||||
def details(job):
|
||||
return {
|
||||
group: sorted(row["detail"] for row in rows)
|
||||
for group, rows in job.outcomes.items()
|
||||
}
|
||||
|
||||
merged = await self._run_job(existing="merge")
|
||||
self.assertEqual(merged.state, "finished")
|
||||
self.assertEqual(
|
||||
details(merged),
|
||||
{
|
||||
"tagged": ["Added 2 tags", "Added 2 tags"],
|
||||
"unchanged": ["No new tags"],
|
||||
"skipped": [
|
||||
"File not found",
|
||||
"Outside the output folders",
|
||||
"Prompt handled by another image",
|
||||
],
|
||||
"errors": [],
|
||||
},
|
||||
)
|
||||
self.assertEqual(merged.status_line, "Tagged 2 prompts")
|
||||
|
||||
skipped = await self._run_job(existing="skip")
|
||||
self.assertEqual(details(skipped)["tagged"], [])
|
||||
self.assertEqual(details(skipped)["skipped"].count("Prompt already tagged"), 3)
|
||||
self.assertEqual(skipped.status_line, "Tagged 0 prompts")
|
||||
|
||||
async def test_tagging_errors_are_fixed_strings(self):
|
||||
self._seed()
|
||||
self.service.generate_error = RuntimeError("/srv/secret/model exploded")
|
||||
job = await self._run_job(existing="merge")
|
||||
self.assertTrue(job.outcomes["errors"])
|
||||
self.assertEqual(
|
||||
{r["detail"] for r in job.outcomes["errors"]}, {"Tagging failed"}
|
||||
)
|
||||
self.assertNotIn("/srv/secret", json.dumps(job.report()))
|
||||
|
||||
async def test_job_progress_is_determinate(self):
|
||||
self._seed()
|
||||
seen = []
|
||||
original = self.service.generate_tags
|
||||
|
||||
def generate(*args, **kwargs):
|
||||
job = self.api._jobs.active("autotag")
|
||||
seen.append((job.processed, job.total))
|
||||
return original(*args, **kwargs)
|
||||
|
||||
self.service.generate_tags = generate
|
||||
job = await self._run_job(existing="merge")
|
||||
self.assertEqual((job.processed, job.total, job.progress), (6, 6, 100))
|
||||
self.assertTrue(all(total == 6 for _p, total in seen[1:]), seen)
|
||||
self.assertTrue(job.cancellable)
|
||||
|
||||
async def test_job_cancel_stops_before_the_next_image_and_keeps_writes(self):
|
||||
ids = self._seed()
|
||||
started = threading.Event()
|
||||
proceed = threading.Event()
|
||||
calls = []
|
||||
|
||||
def slow(image_path, **kwargs):
|
||||
calls.append(image_path)
|
||||
started.set()
|
||||
proceed.wait(30)
|
||||
return ["slow"]
|
||||
|
||||
self.service.generate_tags = slow
|
||||
resp = await self._start_job(existing="merge")
|
||||
job = self.api._jobs.get((await resp.json())["job"]["id"])
|
||||
try:
|
||||
await asyncio.get_running_loop().run_in_executor(None, started.wait, 30)
|
||||
cancel = await self.client.post(f"/prompt_manager/jobs/{job.id}/cancel")
|
||||
self.assertTrue((await cancel.json())["cancellation_requested"])
|
||||
finally:
|
||||
proceed.set()
|
||||
await asyncio.wait_for(asyncio.shield(job.task), 30)
|
||||
self.assertEqual(job.state, "cancelled")
|
||||
self.assertEqual(job.status_line, "Cancelled. Tags already added were kept.")
|
||||
self.assertEqual(len(calls), 1)
|
||||
tagged = [n for n, pid in ids.items() if "slow" in self._tags(pid)]
|
||||
self.assertEqual(len(tagged), 1)
|
||||
self.assertIsNone(model_gate.holder())
|
||||
self.assertEqual(self.service.unload_calls, 0)
|
||||
|
||||
async def test_job_refused_while_legacy_batch_holds(self):
|
||||
async with self.api._jobs.hold(
|
||||
"autotag", "Tag output images (legacy page)", admission="records"
|
||||
@@ -2103,41 +1992,6 @@ class TestTagOutputImagesJob(BatchJobTestCase):
|
||||
self.assertEqual(data["running"]["title"], "Tag output images (legacy page)")
|
||||
self.assertIsNone(model_gate.holder())
|
||||
|
||||
async def test_legacy_refused_while_job_runs(self):
|
||||
self._seed()
|
||||
started, proceed = threading.Event(), threading.Event()
|
||||
|
||||
def slow(image_path, **kwargs):
|
||||
started.set()
|
||||
proceed.wait(30)
|
||||
return ["slow"]
|
||||
|
||||
self.service.generate_tags = slow
|
||||
resp = await self._start_job(existing="merge")
|
||||
job = self.api._jobs.get((await resp.json())["job"]["id"])
|
||||
try:
|
||||
await asyncio.get_running_loop().run_in_executor(None, started.wait, 30)
|
||||
self.assertTrue(model_gate.holder().startswith("autotag-job:"))
|
||||
legacy = await self.client.post("/prompt_manager/autotag/start")
|
||||
# Both legacy pages read a stream: the refusal is one error frame
|
||||
# that names the running job.
|
||||
self.assertEqual(legacy.status, 200)
|
||||
self.assertEqual(
|
||||
self._sse_events(await legacy.text()),
|
||||
[
|
||||
{
|
||||
"type": "error",
|
||||
"status": "error",
|
||||
"message": "Tag output images already running",
|
||||
}
|
||||
],
|
||||
)
|
||||
unload = await self.client.post("/prompt_manager/autotag/unload")
|
||||
self.assertEqual((await unload.json())["operation"], "Tag output images")
|
||||
finally:
|
||||
proceed.set()
|
||||
await asyncio.wait_for(asyncio.shield(job.task), 30)
|
||||
|
||||
async def test_job_releases_gate_when_start_is_refused(self):
|
||||
class Running:
|
||||
id = "other"
|
||||
@@ -2185,7 +2039,7 @@ class TestTagOutputImagesJob(BatchJobTestCase):
|
||||
("database folder", "the safety backup", 10, 1),
|
||||
10,
|
||||
)
|
||||
with patch("py.api.autotag_routes.disk_plan", return_value=short):
|
||||
with patch("py.api.image_tag_jobs.disk_plan", return_value=short):
|
||||
resp = await self._start_job()
|
||||
data = await resp.json()
|
||||
self.assertEqual(resp.status, 507)
|
||||
@@ -2203,14 +2057,6 @@ class TestTagOutputImagesJob(BatchJobTestCase):
|
||||
inside = [row for row in rows if row["root_index"] == 0]
|
||||
self.assertTrue(inside)
|
||||
|
||||
async def test_native_batch_leaves_custom_prompt_unchanged(self):
|
||||
self._seed()
|
||||
self.service.custom_prompt = "legacy page prompt"
|
||||
await self._run_job(existing="merge", model_type="gguf")
|
||||
self.assertEqual(self.service.custom_prompt, "legacy page prompt")
|
||||
prompts = {call[1] for call in self.service.generate_calls}
|
||||
self.assertEqual(prompts, {"Tags please."})
|
||||
|
||||
|
||||
# The legacy batch's per-image frames over BatchJobTestCase's library, newest
|
||||
# first, with every throttle check passing (pinned from main's generator).
|
||||
@@ -2342,7 +2188,7 @@ class TestTagOutputImagesEdges(BatchJobTestCase):
|
||||
async def test_unexpected_error_fails_the_job_with_a_reason(self):
|
||||
self._seed()
|
||||
with patch.object(
|
||||
self.api.db, "autotag_batch_candidates", side_effect=[[], RuntimeError("x")]
|
||||
self.api, "_autotag_prepass", side_effect=RuntimeError("/srv/x")
|
||||
):
|
||||
job = await self._run_job(existing="merge")
|
||||
self.assertEqual(job.state, "failed")
|
||||
|
||||
@@ -0,0 +1,634 @@
|
||||
"""Tag output images tags each image, never its prompt (#379, PR 1).
|
||||
|
||||
``POST /prompt_manager/jobs/autotag`` runs the ``image-tags`` loop over every
|
||||
still image the output folders list, linked to a prompt or not: each image
|
||||
gets its own model tags in its image tag set and is marked auto-tagged.
|
||||
"Skip already tagged" skips images whose current bytes are marked, counted
|
||||
before the loop without opening them. Prompt tags and prompt text never
|
||||
change. No real model is loaded: the engine is a fake that answers per image.
|
||||
"""
|
||||
|
||||
import asyncio
|
||||
import json
|
||||
import ntpath
|
||||
import os
|
||||
import posixpath
|
||||
import re
|
||||
import sqlite3
|
||||
import threading
|
||||
from pathlib import Path
|
||||
from unittest.mock import patch
|
||||
|
||||
try:
|
||||
from test_api_images import make_png
|
||||
from test_image_tag_jobs import HookedTagger, ImageTagJobTestCase
|
||||
except ImportError:
|
||||
from tests.test_api_images import make_png
|
||||
from tests.test_image_tag_jobs import HookedTagger, ImageTagJobTestCase
|
||||
|
||||
from database.execution_history_schema import rotate_history_epoch
|
||||
from py import model_gate
|
||||
from py.api import admin as admin_module
|
||||
from py.api import image_tag_jobs as jobs_module
|
||||
from py.config import PromptManagerConfig
|
||||
from utils.hashing import generate_prompt_hash
|
||||
|
||||
JOB = "/prompt_manager/jobs/autotag"
|
||||
PREVIEW = "/prompt_manager/autotag/batch/preview"
|
||||
WAIT = 30.0
|
||||
WD14 = {"general_threshold": 0.35, "character_threshold": 0.85}
|
||||
CANCELLED = "Cancelled. Tags already added were kept."
|
||||
_DRIVE = re.compile(r"^[A-Za-z]:[\\/]")
|
||||
|
||||
|
||||
class PerImageTagger(HookedTagger):
|
||||
"""Answers each image from its own bytes: ``by_bytes`` maps exact file
|
||||
contents to the names the "model" sees; any other image gets SCORED."""
|
||||
|
||||
def __init__(self):
|
||||
super().__init__()
|
||||
self.by_bytes = {}
|
||||
|
||||
def generate_tag_suggestions(self, image_path, **kwargs):
|
||||
result = super().generate_tag_suggestions(image_path, **kwargs)
|
||||
names = self.by_bytes.get(self.read_bytes[-1])
|
||||
if names is None:
|
||||
return result
|
||||
return [(name, 0.9) for name in names][: kwargs["limit"]]
|
||||
|
||||
|
||||
def _strings(value):
|
||||
if isinstance(value, str):
|
||||
yield value
|
||||
elif isinstance(value, dict):
|
||||
for item in value.values():
|
||||
yield from _strings(item)
|
||||
elif isinstance(value, (list, tuple)):
|
||||
for item in value:
|
||||
yield from _strings(item)
|
||||
|
||||
|
||||
def _absolute(text):
|
||||
return posixpath.isabs(text) or ntpath.isabs(text) or bool(_DRIVE.match(text))
|
||||
|
||||
|
||||
class BatchTestCase(ImageTagJobTestCase):
|
||||
async def get_application(self):
|
||||
app = await super().get_application()
|
||||
self.tagger = PerImageTagger()
|
||||
patcher = patch("py.autotag.get_autotag_service", return_value=self.tagger)
|
||||
patcher.start()
|
||||
self.addCleanup(patcher.stop)
|
||||
backup = PromptManagerConfig.SAFETY_BACKUP
|
||||
self.addCleanup(setattr, PromptManagerConfig, "SAFETY_BACKUP", backup)
|
||||
PromptManagerConfig.SAFETY_BACKUP = False
|
||||
return app
|
||||
|
||||
# -- helpers ---------------------------------------------------------
|
||||
|
||||
def image(self, name, color, sees=None):
|
||||
path = make_png(self.output_dir / name, size=(8, 6), color=color)
|
||||
if sees is not None:
|
||||
self.tagger.by_bytes[path.read_bytes()] = list(sees)
|
||||
return path
|
||||
|
||||
async def relist(self):
|
||||
"""Walk the output folder again (a cached listing is used as it is)."""
|
||||
await self.api._listing(self.output_dir, fresh=True)
|
||||
|
||||
def prompt(self, text, tags=()):
|
||||
return self.api.db.save_prompt(
|
||||
text=text,
|
||||
category=None,
|
||||
tags=list(tags),
|
||||
rating=None,
|
||||
prompt_hash=generate_prompt_hash(text),
|
||||
)
|
||||
|
||||
def link(self, prompt_id, path):
|
||||
return self.api.db.link_image_to_prompt(prompt_id, str(path))
|
||||
|
||||
def prompt_rows(self):
|
||||
conn = sqlite3.connect(self._temp_db.name)
|
||||
try:
|
||||
return {
|
||||
table: conn.execute(f"SELECT * FROM {table} ORDER BY 1,2").fetchall()
|
||||
for table in ("prompts", "prompt_tags")
|
||||
}
|
||||
finally:
|
||||
conn.close()
|
||||
|
||||
def marked(self):
|
||||
conn = sqlite3.connect(self._temp_db.name)
|
||||
try:
|
||||
return {
|
||||
row[0]
|
||||
for row in conn.execute(
|
||||
"SELECT f.locator FROM media_image_autotags m JOIN "
|
||||
"media_annotation_bytes b ON b.id=m.byte_id JOIN "
|
||||
"media_annotation_files f ON f.id=b.file_id"
|
||||
)
|
||||
}
|
||||
finally:
|
||||
conn.close()
|
||||
|
||||
async def preview(self, existing="skip", model_type="wd14-vit"):
|
||||
response = await self.client.post(
|
||||
PREVIEW, json={"model_type": model_type, "existing": existing}
|
||||
)
|
||||
return response.status, await self.json_of(response)
|
||||
|
||||
async def start_batch(self, existing="skip", model_type="wd14-vit", options=None):
|
||||
if options is None:
|
||||
options = (
|
||||
dict(WD14)
|
||||
if model_type.startswith("wd14")
|
||||
else {"instructions": "Tags please."}
|
||||
)
|
||||
response = await self.client.post(
|
||||
JOB,
|
||||
json={"model_type": model_type, "existing": existing, "options": options},
|
||||
)
|
||||
return response.status, await self.json_of(response)
|
||||
|
||||
async def run_batch(self, **kwargs):
|
||||
status, data = await self.start_batch(**kwargs)
|
||||
self.assertEqual(status, 202, data)
|
||||
job = self.api._jobs.get(data["job"]["id"])
|
||||
await asyncio.wait_for(asyncio.shield(job.task), WAIT)
|
||||
return job
|
||||
|
||||
|
||||
class TestPerImageWrites(BatchTestCase):
|
||||
async def test_two_images_of_one_prompt_get_their_own_tags_and_no_prompt_changes(
|
||||
self,
|
||||
):
|
||||
prompt_id = self.prompt("a girl at the beach", tags=["beach"])
|
||||
a = self.image("a.png", (10, 20, 30), sees=["1girl", "bird"])
|
||||
b = self.image("b.png", (40, 50, 60), sees=["1girl", "waves"])
|
||||
self.link(prompt_id, a)
|
||||
self.link(prompt_id, b)
|
||||
before = self.prompt_rows()
|
||||
|
||||
job = await self.run_batch(existing="skip")
|
||||
|
||||
self.assertEqual(job.state, "finished", job.status_line)
|
||||
self.assertEqual(self.stored("a.png")["tags"], ["1girl", "bird"])
|
||||
self.assertEqual(self.stored("b.png")["tags"], ["1girl", "waves"])
|
||||
self.assertEqual(self.prompt_rows(), before)
|
||||
self.assertEqual(self.api.db.get_prompt_by_id(prompt_id)["tags"], ["beach"])
|
||||
self.assertEqual(self.marked(), {self.locator("a.png"), self.locator("b.png")})
|
||||
self.assertEqual(
|
||||
job.counters, {"tagged": 2, "unchanged": 0, "skipped": 0, "errors": 0}
|
||||
)
|
||||
self.assertEqual(job.status_line, "Tagged 2 images")
|
||||
self.assertEqual((job.processed, job.total, job.progress), (2, 2, 100))
|
||||
self.assertEqual(job.scope["images"], 2)
|
||||
# Inference read the private captures, one per image.
|
||||
self.assertEqual(len(self.tagger.calls), 2)
|
||||
|
||||
async def test_unlinked_images_are_tagged_and_videos_are_not_targets(self):
|
||||
self.image("free.png", (1, 2, 3), sees=["tree"])
|
||||
(self.output_dir / "clip.mp4").write_bytes(b"\x00\x00\x00\x18ftypmp42" * 8)
|
||||
|
||||
job = await self.run_batch()
|
||||
|
||||
self.assertEqual(self.stored("free.png")["tags"], ["tree"])
|
||||
self.assertEqual(job.total, 1)
|
||||
self.assertEqual(job.status_line, "Tagged 1 image")
|
||||
rows = [row["path"] for rows in job.outcomes.values() for row in rows]
|
||||
self.assertNotIn("clip.mp4", rows)
|
||||
|
||||
async def test_hand_tags_do_not_block_a_skip_run(self):
|
||||
path = self.image("c.png", (7, 7, 7), sees=["bird"])
|
||||
self.saved_set("c.png", path.read_bytes(), ["keeper"])
|
||||
|
||||
job = await self.run_batch(existing="skip")
|
||||
|
||||
self.assertEqual(self.stored("c.png")["tags"], ["keeper", "bird"])
|
||||
self.assertEqual(job.counters["tagged"], 1)
|
||||
|
||||
async def test_skip_counts_marked_images_without_opening_them_and_merge_retags(
|
||||
self,
|
||||
):
|
||||
self.image("a.png", (1, 1, 1), sees=["bird"])
|
||||
self.image("b.png", (2, 2, 2), sees=["cat"])
|
||||
first = await self.run_batch()
|
||||
self.assertEqual(first.counters["tagged"], 2)
|
||||
self.tagger.calls.clear()
|
||||
|
||||
captures = []
|
||||
store = self.api._capture_store()
|
||||
real_capture = store.capture
|
||||
|
||||
def spy(*args, **kwargs):
|
||||
captures.append(args)
|
||||
return real_capture(*args, **kwargs)
|
||||
|
||||
with patch.object(store, "capture", side_effect=spy):
|
||||
skipped = await self.run_batch(existing="skip")
|
||||
self.assertEqual(captures, [])
|
||||
self.assertEqual(self.tagger.calls, [])
|
||||
self.assertEqual(
|
||||
skipped.counters, {"tagged": 0, "unchanged": 0, "skipped": 2, "errors": 0}
|
||||
)
|
||||
self.assertEqual(
|
||||
sorted(self.rows(skipped, "skipped")),
|
||||
[("a.png", "Already auto-tagged"), ("b.png", "Already auto-tagged")],
|
||||
)
|
||||
self.assertFalse(any("Already auto-tagged" in line for line in skipped.log))
|
||||
self.assertEqual((skipped.processed, skipped.total), (2, 2))
|
||||
self.assertEqual(skipped.status_line, "Tagged 0 images")
|
||||
|
||||
self.tagger.by_bytes[(self.output_dir / "a.png").read_bytes()] = ["bird", "sky"]
|
||||
merged = await self.run_batch(existing="merge")
|
||||
self.assertEqual(len(self.tagger.calls), 2)
|
||||
self.assertEqual(self.stored("a.png")["tags"], ["bird", "sky"])
|
||||
self.assertEqual(self.rows(merged, "tagged"), [("a.png", "Added 1 tag")])
|
||||
self.assertEqual(self.rows(merged, "unchanged"), [("b.png", "No new tags")])
|
||||
|
||||
async def test_changed_bytes_are_tagged_again(self):
|
||||
self.image("a.png", (1, 1, 1), sees=["bird"])
|
||||
await self.run_batch()
|
||||
self.image("a.png", (9, 9, 9), sees=["cat"])
|
||||
job = await self.run_batch(existing="skip")
|
||||
self.assertEqual(self.rows(job, "tagged"), [("a.png", "Added 1 tag")])
|
||||
self.assertEqual(self.stored("a.png")["tags"], ["cat"])
|
||||
|
||||
async def test_an_image_with_no_model_tags_is_marked_and_skipped_next_time(self):
|
||||
self.image("plain.png", (3, 3, 3), sees=[])
|
||||
job = await self.run_batch()
|
||||
self.assertEqual(self.rows(job, "unchanged"), [("plain.png", "No new tags")])
|
||||
self.assertEqual(self.marked(), {self.locator("plain.png")})
|
||||
again = await self.run_batch()
|
||||
self.assertEqual(
|
||||
self.rows(again, "skipped"), [("plain.png", "Already auto-tagged")]
|
||||
)
|
||||
|
||||
async def test_unsupported_still_is_marked_and_skipped_by_the_next_run(self):
|
||||
(self.output_dir / "broken.png").write_bytes(b"not an image")
|
||||
job = await self.run_batch()
|
||||
self.assertEqual(
|
||||
self.rows(job, "skipped"), [("broken.png", "Not a supported still image")]
|
||||
)
|
||||
self.assertEqual(self.marked(), {self.locator("broken.png")})
|
||||
again = await self.run_batch()
|
||||
self.assertEqual(
|
||||
self.rows(again, "skipped"), [("broken.png", "Already auto-tagged")]
|
||||
)
|
||||
self.assertEqual(self.tagger.calls, [])
|
||||
|
||||
async def test_too_large_is_skipped_before_any_copy(self):
|
||||
self.image("big.png", (5, 5, 5))
|
||||
self.api._capture_store().max_file = 16
|
||||
store = self.api._capture_store()
|
||||
with patch.object(store, "capture", side_effect=AssertionError("copied")):
|
||||
job = await self.run_batch()
|
||||
self.assertEqual(
|
||||
self.rows(job, "skipped"), [("big.png", "Too large to verify")]
|
||||
)
|
||||
self.assertEqual(self.marked(), set())
|
||||
|
||||
async def test_overlapping_roots_list_a_file_once(self):
|
||||
self.image("sub/a.png", (4, 4, 4), sees=["bird"])
|
||||
sub = self.output_dir / "sub"
|
||||
self.api._get_all_output_dirs = lambda: [self.output_dir, sub]
|
||||
job = await self.run_batch()
|
||||
self.assertEqual(job.total, 1)
|
||||
self.assertEqual(len(self.tagger.calls), 1)
|
||||
self.assertEqual(self.rows(job, "tagged"), [("sub/a.png", "Added 1 tag")])
|
||||
status, data = await self.preview()
|
||||
self.assertEqual((status, data["images"]), (200, 1))
|
||||
|
||||
async def test_rows_log_and_status_carry_no_absolute_paths(self):
|
||||
self.image("a.png", (1, 1, 1))
|
||||
(self.output_dir / "broken.png").write_bytes(b"not an image")
|
||||
job = await self.run_batch()
|
||||
leaked = [s for s in _strings(job.report()) if _absolute(s)]
|
||||
self.assertEqual(leaked, [])
|
||||
self.assertNotIn(str(self.output_dir), json.dumps(job.report()))
|
||||
|
||||
|
||||
class TestBatchLifecycle(BatchTestCase):
|
||||
async def test_cancel_after_one_image_keeps_it_and_the_rerun_skips_it(self):
|
||||
for n in range(3):
|
||||
self.image(f"{n}.png", (n, n, n), sees=[f"t{n}"])
|
||||
entered, proceed = threading.Event(), threading.Event()
|
||||
self.tagger.block = (entered, proceed)
|
||||
status, data = await self.start_batch()
|
||||
self.assertEqual(status, 202, data)
|
||||
job = self.api._jobs.get(data["job"]["id"])
|
||||
try:
|
||||
await self.wait_for(entered)
|
||||
cancel = await self.client.post(f"/prompt_manager/jobs/{job.id}/cancel")
|
||||
self.assertEqual(cancel.status, 200)
|
||||
finally:
|
||||
self.tagger.block = None
|
||||
proceed.set()
|
||||
await asyncio.wait_for(asyncio.shield(job.task), WAIT)
|
||||
self.assertEqual(job.state, "cancelled")
|
||||
self.assertEqual(job.status_line, CANCELLED)
|
||||
self.assertEqual(job.counters["tagged"], 1)
|
||||
self.assertEqual(len(self.marked()), 1)
|
||||
self.assertIsNone(model_gate.holder())
|
||||
|
||||
lines = []
|
||||
real_update = type(job).update
|
||||
|
||||
def spy(self_job, **kwargs):
|
||||
if kwargs.get("status_line"):
|
||||
lines.append(kwargs["status_line"])
|
||||
return real_update(self_job, **kwargs)
|
||||
|
||||
with patch.object(type(job), "update", spy):
|
||||
rerun = await self.run_batch()
|
||||
self.assertEqual(rerun.counters["skipped"], 1)
|
||||
self.assertEqual(rerun.counters["tagged"], 2)
|
||||
self.assertIn("Processing file 2 of 3", lines)
|
||||
self.assertIn("Processing file 3 of 3", lines)
|
||||
self.assertNotIn("Processing file 1 of 3", lines)
|
||||
self.assertEqual((rerun.processed, rerun.total), (3, 3))
|
||||
|
||||
async def test_cancel_in_each_phase_writes_nothing(self):
|
||||
self.image("a.png", (1, 1, 1))
|
||||
for phase in (
|
||||
"_safety_backup_step",
|
||||
"_prepare_tagging_model",
|
||||
"_autotag_targets",
|
||||
):
|
||||
with self.subTest(phase):
|
||||
real = getattr(self.api, phase)
|
||||
|
||||
async def cancelling(*args, _real=real, **kwargs):
|
||||
result = await _real(*args, **kwargs)
|
||||
self.api._jobs.active("autotag").cancelled = True
|
||||
return result
|
||||
|
||||
with patch.object(self.api, phase, side_effect=cancelling):
|
||||
job = await self.run_batch()
|
||||
self.assertEqual(job.state, "cancelled")
|
||||
self.assertEqual(job.status_line, CANCELLED)
|
||||
self.assertEqual(self.marked(), set())
|
||||
self.assertEqual(self.tagger.calls, [])
|
||||
self.assertIsNone(model_gate.holder())
|
||||
|
||||
async def test_restore_mid_run_fails_the_job(self):
|
||||
self.image("a.png", (1, 1, 1))
|
||||
self.image("b.png", (2, 2, 2))
|
||||
|
||||
def restore(_path):
|
||||
conn = sqlite3.connect(self._temp_db.name)
|
||||
try:
|
||||
rotate_history_epoch(conn)
|
||||
finally:
|
||||
conn.close()
|
||||
|
||||
self.tagger.on_generate = restore
|
||||
job = await self.run_batch()
|
||||
self.assertEqual(job.state, "failed")
|
||||
self.assertEqual(
|
||||
job.status_line, "Prompt storage was restored; start the job again."
|
||||
)
|
||||
|
||||
async def test_listing_error_fails_the_job(self):
|
||||
self.image("a.png", (1, 1, 1))
|
||||
with patch.object(
|
||||
self.api, "_get_gallery_files", side_effect=OSError("/secret/out")
|
||||
):
|
||||
job = await self.run_batch()
|
||||
self.assertEqual(job.state, "failed")
|
||||
self.assertEqual(
|
||||
job.status_line, "The output folders could not be listed. Try again."
|
||||
)
|
||||
self.assertNotIn("/secret", json.dumps(job.report()))
|
||||
|
||||
async def test_model_that_cannot_load_fails_the_job(self):
|
||||
self.image("a.png", (1, 1, 1))
|
||||
self.tagger.load_error = RuntimeError("no CUDA")
|
||||
job = await self.run_batch()
|
||||
self.assertEqual(job.state, "failed")
|
||||
self.assertEqual(
|
||||
job.status_line, "Auto-tagging failed. Check server logs for details."
|
||||
)
|
||||
self.assertIsNone(model_gate.holder())
|
||||
|
||||
async def test_zero_targets_finish_with_tagged_zero(self):
|
||||
job = await self.run_batch()
|
||||
self.assertEqual(job.state, "finished")
|
||||
self.assertEqual(job.status_line, "Tagged 0 images")
|
||||
self.assertEqual((job.processed, job.total), (0, 0))
|
||||
|
||||
async def test_runner_unloads_after_a_cancel_when_not_kept_in_memory(self):
|
||||
self.image("a.png", (1, 1, 1))
|
||||
owner = model_gate.new_owner("legacy-batch")
|
||||
self.assertTrue(model_gate.try_acquire(owner))
|
||||
run = jobs_module.AutotagRun(
|
||||
model_type="wd14-vit",
|
||||
existing="skip",
|
||||
options={**WD14, "use_gpu": True, "suggestion_limit": 10},
|
||||
keep_in_memory=False,
|
||||
backup_on=False,
|
||||
owner=owner,
|
||||
)
|
||||
|
||||
from py.api.jobs import AUTOTAG_GROUP_NAMES, Job as RealJob
|
||||
|
||||
job = RealJob(
|
||||
"autotag",
|
||||
"Tag output images",
|
||||
admission="records",
|
||||
groups=AUTOTAG_GROUP_NAMES,
|
||||
)
|
||||
real_targets = self.api._autotag_targets
|
||||
|
||||
async def cancel_after_listing():
|
||||
targets = await real_targets()
|
||||
job.cancelled = True
|
||||
return targets
|
||||
|
||||
with patch.object(
|
||||
self.api, "_autotag_targets", side_effect=cancel_after_listing
|
||||
):
|
||||
await self.api._run_autotag_batch(run, job)
|
||||
self.assertEqual(job.state, "cancelled")
|
||||
self.assertEqual(self.tagger.unload_calls, 1)
|
||||
self.assertIsNone(model_gate.holder())
|
||||
|
||||
async def test_time_left_uses_the_models_rate_only(self):
|
||||
for n in range(4):
|
||||
self.image(f"{n}.png", (n, n, n))
|
||||
await self.run_batch()
|
||||
for n in range(4, 8):
|
||||
self.image(f"{n}.png", (n, n, n))
|
||||
await self.relist()
|
||||
calls = []
|
||||
real = jobs_module._time_left
|
||||
|
||||
def spy(*args):
|
||||
calls.append(args)
|
||||
return real(*args)
|
||||
|
||||
with patch.object(jobs_module, "_time_left", side_effect=spy):
|
||||
job = await self.run_batch()
|
||||
self.assertEqual(job.counters["skipped"], 4)
|
||||
# (done, total, batches, elapsed): over the 4 images the model runs on.
|
||||
self.assertEqual(
|
||||
[(c[0], c[1], c[2]) for c in calls], [(n, 4, n) for n in range(4)]
|
||||
)
|
||||
# The shared D56 text is unchanged.
|
||||
self.assertEqual(admin_module._time_left(5, 10, 5, 300), " · about 5 min left")
|
||||
|
||||
|
||||
class TestStartRefusals(BatchTestCase):
|
||||
async def test_unavailable_model_and_bad_bodies(self):
|
||||
self.tagger.downloaded["wd14-vit"] = False
|
||||
status, data = await self.start_batch()
|
||||
self.assertEqual((status, data["code"]), (409, "model-unavailable"))
|
||||
status, data = await self.start_batch(existing="replace_after_review")
|
||||
self.assertEqual((status, data["code"]), (400, "review-required"))
|
||||
status, _data = await self.start_batch(options={**WD14, "suggestion_limit": 3})
|
||||
self.assertEqual(status, 400)
|
||||
self.assertEqual(self.api._jobs.list(), [])
|
||||
self.assertIsNone(model_gate.holder())
|
||||
|
||||
async def test_model_busy_when_the_gate_is_held(self):
|
||||
owner = model_gate.new_owner("image-annotations")
|
||||
self.assertTrue(model_gate.try_acquire(owner))
|
||||
try:
|
||||
status, data = await self.start_batch()
|
||||
finally:
|
||||
model_gate.release(owner)
|
||||
self.assertEqual((status, data["code"]), (409, "model-busy"))
|
||||
|
||||
|
||||
class TestBatchBeside(BatchTestCase):
|
||||
async def test_legacy_batch_and_unload_are_refused_while_the_job_runs(self):
|
||||
self.image("a.png", (1, 1, 1))
|
||||
entered, proceed = threading.Event(), threading.Event()
|
||||
self.tagger.block = (entered, proceed)
|
||||
status, data = await self.start_batch()
|
||||
self.assertEqual(status, 202, data)
|
||||
job = self.api._jobs.get(data["job"]["id"])
|
||||
try:
|
||||
await self.wait_for(entered)
|
||||
self.assertTrue(model_gate.holder().startswith("autotag-job:"))
|
||||
legacy = await self.client.post("/prompt_manager/autotag/start")
|
||||
self.assertEqual(legacy.status, 200)
|
||||
frames = [
|
||||
json.loads(line[len("data: ") :])
|
||||
for line in (await legacy.text()).splitlines()
|
||||
if line.startswith("data: ")
|
||||
]
|
||||
self.assertEqual(
|
||||
frames,
|
||||
[
|
||||
{
|
||||
"type": "error",
|
||||
"status": "error",
|
||||
"message": "Tag output images already running",
|
||||
}
|
||||
],
|
||||
)
|
||||
unload = await self.client.post("/prompt_manager/autotag/unload")
|
||||
self.assertEqual((await unload.json())["operation"], "Tag output images")
|
||||
finally:
|
||||
self.tagger.block = None
|
||||
proceed.set()
|
||||
await asyncio.wait_for(asyncio.shield(job.task), WAIT)
|
||||
self.assertEqual(job.state, "finished")
|
||||
|
||||
async def test_language_model_batch_passes_instructions_per_call(self):
|
||||
self.image("a.png", (1, 1, 1))
|
||||
job = await self.run_batch(model_type="gguf")
|
||||
self.assertEqual(job.state, "finished", job.status_line)
|
||||
self.assertEqual(self.tagger.calls[0]["prompt"], "Tags please.")
|
||||
self.assertEqual(self.tagger.custom_prompt, "legacy prompt")
|
||||
|
||||
async def test_inference_errors_are_fixed_strings_and_not_marked(self):
|
||||
self.image("a.png", (1, 1, 1))
|
||||
|
||||
def explode(_path):
|
||||
raise RuntimeError("/srv/secret/model exploded")
|
||||
|
||||
self.tagger.on_generate = explode
|
||||
job = await self.run_batch()
|
||||
self.assertEqual(
|
||||
self.rows(job, "errors"),
|
||||
[("a.png", "Auto-tagging failed. Check server logs for details.")],
|
||||
)
|
||||
self.assertNotIn("/srv/secret", json.dumps(job.report()))
|
||||
self.assertEqual(self.marked(), set())
|
||||
|
||||
|
||||
class TestPreview(BatchTestCase):
|
||||
async def test_preview_counts_images_and_estimates_time(self):
|
||||
prompt_id = self.prompt("p")
|
||||
a = self.image("a.png", (1, 1, 1))
|
||||
self.image("b.png", (2, 2, 2))
|
||||
self.image("c.png", (3, 3, 3))
|
||||
self.link(prompt_id, a)
|
||||
(self.output_dir / "clip.mp4").write_bytes(b"\x00\x00\x00\x18ftypmp42" * 8)
|
||||
status, fresh = await self.preview()
|
||||
self.assertEqual(status, 200, fresh)
|
||||
self.assertEqual(
|
||||
{k: fresh[k] for k in ("images", "already_tagged", "to_tag")},
|
||||
{"images": 3, "already_tagged": 0, "to_tag": 3},
|
||||
)
|
||||
self.assertNotIn("prompts", fresh)
|
||||
self.assertEqual(fresh["suggestion_limit"], 10)
|
||||
self.assertEqual(fresh["estimate_device"], "cpu")
|
||||
self.assertAlmostEqual(fresh["estimate_seconds"], 3 * 1.6)
|
||||
|
||||
self.tagger.block = None
|
||||
await self.run_batch()
|
||||
self.image("d.png", (4, 4, 4))
|
||||
await self.relist()
|
||||
skip = (await self.preview("skip"))[1]
|
||||
self.assertEqual(
|
||||
{k: skip[k] for k in ("images", "already_tagged", "to_tag")},
|
||||
{"images": 4, "already_tagged": 3, "to_tag": 1},
|
||||
)
|
||||
merge = (await self.preview("merge"))[1]
|
||||
self.assertEqual(merge["to_tag"], 4)
|
||||
for model_type in ("gguf", "hf"):
|
||||
llm = (await self.preview(model_type=model_type))[1]
|
||||
self.assertIsNone(llm["estimate_seconds"])
|
||||
self.assertIsNone(llm["estimate_device"])
|
||||
self.assertEqual([s for s in _strings(skip) if _absolute(s)], [])
|
||||
|
||||
async def test_preview_uses_the_graphics_card_rate_when_wd14_runs_on_cuda(self):
|
||||
self.image("a.png", (1, 1, 1))
|
||||
self.tagger.wd14_device = lambda: "gpu"
|
||||
data = (await self.preview())[1]
|
||||
self.assertEqual(data["estimate_device"], "gpu")
|
||||
from py.tagging_defaults import WD14_GPU_SECONDS_PER_IMAGE
|
||||
|
||||
self.assertAlmostEqual(data["estimate_seconds"], WD14_GPU_SECONDS_PER_IMAGE)
|
||||
|
||||
async def test_preview_writes_nothing_and_opens_no_media_file(self):
|
||||
self.image("a.png", (1, 1, 1))
|
||||
await self.run_batch()
|
||||
self.image("b.png", (2, 2, 2))
|
||||
await self.relist() # the listing, primed
|
||||
files = [self._temp_db.name + suffix for suffix in ("", "-wal")]
|
||||
before = [Path(f).read_bytes() if os.path.exists(f) else None for f in files]
|
||||
media = str(self.output_dir)
|
||||
real_open, real_stat = open, os.stat
|
||||
|
||||
def guarded_open(file, *args, **kwargs):
|
||||
if str(file).startswith(media):
|
||||
raise AssertionError(f"opened {file}")
|
||||
return real_open(file, *args, **kwargs)
|
||||
|
||||
def guarded_stat(path, *args, **kwargs):
|
||||
if str(path).startswith(media) and str(path) != media:
|
||||
raise AssertionError(f"stat {path}")
|
||||
return real_stat(path, *args, **kwargs)
|
||||
|
||||
with patch("builtins.open", guarded_open), patch("os.stat", guarded_stat):
|
||||
status, data = await self.preview()
|
||||
self.assertEqual(status, 200, data)
|
||||
after = [Path(f).read_bytes() if os.path.exists(f) else None for f in files]
|
||||
self.assertEqual(after, before)
|
||||
self.assertEqual(data["to_tag"], 1)
|
||||
self.assertEqual(self.tagger.calls[1:], [])
|
||||
@@ -884,3 +884,29 @@ class TestImageConversion(EngineTestCase):
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
|
||||
|
||||
class TestWd14Device(EngineTestCase):
|
||||
"""Where WD14 runs, for the Tag output images estimate (#379)."""
|
||||
|
||||
def test_loaded_session_answers_from_its_first_provider(self):
|
||||
cpu = FakeOnnxSession([0.5] * len(WD14_TAGS))
|
||||
service = self._service(("wd14", (cpu, WD14_TAGS)))
|
||||
_touch_model_files(self.models_dir, "wd14-vit")
|
||||
service.load_model("wd14-vit")
|
||||
self.assertEqual(service.wd14_device(), "cpu")
|
||||
cpu.get_providers = lambda: ["CUDAExecutionProvider", "CPUExecutionProvider"]
|
||||
self.assertEqual(service.wd14_device(), "gpu")
|
||||
|
||||
def test_without_a_session_the_available_providers_answer(self):
|
||||
service = self._service(None)
|
||||
fake = types.SimpleNamespace(
|
||||
get_available_providers=lambda: ["CUDAExecutionProvider"]
|
||||
)
|
||||
with patch.dict(sys.modules, {"onnxruntime": fake}):
|
||||
self.assertEqual(service.wd14_device(), "gpu")
|
||||
fake.get_available_providers = lambda: ["CPUExecutionProvider"]
|
||||
with patch.dict(sys.modules, {"onnxruntime": fake}):
|
||||
self.assertEqual(service.wd14_device(), "cpu")
|
||||
with patch.dict(sys.modules, {"onnxruntime": None}):
|
||||
self.assertEqual(service.wd14_device(), "cpu")
|
||||
|
||||
@@ -0,0 +1,318 @@
|
||||
"""Auto-tagged marks schema group (#379): install, validation and restore."""
|
||||
|
||||
import hashlib
|
||||
import re
|
||||
import shutil
|
||||
import sqlite3
|
||||
import tempfile
|
||||
import unittest
|
||||
from contextlib import closing
|
||||
from pathlib import Path
|
||||
|
||||
try:
|
||||
from tests.open_handles import assert_closed
|
||||
except ImportError: # discovered with tests/ as the top-level directory
|
||||
from open_handles import assert_closed
|
||||
|
||||
from database.models import PromptModel
|
||||
|
||||
try: # guarded so a missing module fails assertions, not test loading
|
||||
from database.autotag_schema import (
|
||||
AUTOTAG_TABLE,
|
||||
autotag_schema_error,
|
||||
autotag_without_annotations_error,
|
||||
migrate_autotag_state,
|
||||
)
|
||||
except ImportError:
|
||||
AUTOTAG_TABLE = None
|
||||
autotag_schema_error = None
|
||||
autotag_without_annotations_error = None
|
||||
migrate_autotag_state = None
|
||||
|
||||
TABLE = "media_image_autotags"
|
||||
DDL = (
|
||||
f"CREATE TABLE {TABLE} (byte_id TEXT PRIMARY KEY "
|
||||
"REFERENCES media_annotation_bytes(id) ON DELETE CASCADE) WITHOUT ROWID"
|
||||
)
|
||||
ANNOTATION_TABLES = (
|
||||
"media_annotation_metadata",
|
||||
"media_annotation_files",
|
||||
"media_annotation_bytes",
|
||||
"media_image_tags",
|
||||
)
|
||||
REVIEW_TABLES = (
|
||||
"media_review_metadata",
|
||||
"media_review_items",
|
||||
"media_review_decisions",
|
||||
)
|
||||
FILE_ID = "0f8e4b2a-1c3d-4e5f-8a9b-0c1d2e3f4a5b"
|
||||
BYTE_ID = "6a1b2c3d-4e5f-4a6b-8c9d-0e1f2a3b4c5d"
|
||||
OTHER_ID = "7b2c3d4e-5f6a-4b7c-9d0e-1f2a3b4c5d6e"
|
||||
DIGEST = hashlib.sha256(b"img").hexdigest()
|
||||
NOW = "2026-10-27T00:00:00.000000+00:00"
|
||||
NEEDS_ANNOTATIONS = "Image auto-tag marks need the image annotation tables"
|
||||
INVALID_VALUES = "Image auto-tag marks contain invalid values"
|
||||
INVALID_SCHEMA = "Image auto-tag marks have an invalid schema"
|
||||
|
||||
|
||||
def _compact(sql):
|
||||
return re.sub(r"\s+", "", sql or "").lower()
|
||||
|
||||
|
||||
def catalog(conn):
|
||||
return {
|
||||
(kind, name, _compact(sql))
|
||||
for kind, name, sql in conn.execute(
|
||||
"SELECT type,name,sql FROM sqlite_master WHERE name=? OR tbl_name=?",
|
||||
(TABLE, TABLE),
|
||||
)
|
||||
}
|
||||
|
||||
|
||||
def marks(conn):
|
||||
return [tuple(row) for row in conn.execute(f"SELECT byte_id FROM {TABLE}")]
|
||||
|
||||
|
||||
def insert_byte(conn, file_id=FILE_ID, byte_id=BYTE_ID, locator="/out/img.png"):
|
||||
conn.execute(
|
||||
"INSERT INTO media_annotation_files VALUES(?,?,?)", (file_id, locator, NOW)
|
||||
)
|
||||
conn.execute(
|
||||
"INSERT INTO media_annotation_bytes VALUES(?,?,?,?,?,?,?,0)",
|
||||
(byte_id, file_id, DIGEST, 3, 1_700_000_000_000_000_000, NOW, NOW),
|
||||
)
|
||||
|
||||
|
||||
class AutotagSchemaTests(unittest.TestCase):
|
||||
def setUp(self):
|
||||
self.temp = tempfile.TemporaryDirectory()
|
||||
self.addCleanup(self.temp.cleanup)
|
||||
self.addCleanup(assert_closed, self, self.temp.name)
|
||||
self.addCleanup(PromptModel.reset_schema_cache)
|
||||
self.models = []
|
||||
self.addCleanup(self.close_models)
|
||||
self.path = str(Path(self.temp.name) / "live.db")
|
||||
|
||||
def close_models(self):
|
||||
for model in self.models:
|
||||
model.close_all()
|
||||
|
||||
def model(self, path=None):
|
||||
model = PromptModel(path or self.path)
|
||||
self.models.append(model)
|
||||
return model
|
||||
|
||||
def require_module(self):
|
||||
self.assertIsNotNone(
|
||||
autotag_schema_error, "database.autotag_schema is not implemented"
|
||||
)
|
||||
|
||||
def raw(self, path, *statements, foreign_keys=False):
|
||||
with closing(sqlite3.connect(path)) as raw, raw:
|
||||
raw.execute(f"PRAGMA foreign_keys={'ON' if foreign_keys else 'OFF'}")
|
||||
for statement in statements:
|
||||
if isinstance(statement, tuple):
|
||||
raw.execute(*statement)
|
||||
else:
|
||||
raw.execute(statement)
|
||||
|
||||
def closed_current(self, name="current.db", *, with_mark=True):
|
||||
"""A closed, current database with one byte record (and its mark)."""
|
||||
path = str(Path(self.temp.name) / name)
|
||||
model = self.model(path)
|
||||
with model.get_connection() as conn:
|
||||
insert_byte(conn)
|
||||
if with_mark:
|
||||
conn.execute(f"INSERT INTO {TABLE} VALUES(?)", (BYTE_ID,))
|
||||
model.close_all()
|
||||
return path
|
||||
|
||||
def test_fresh_install_has_exactly_the_pinned_table(self):
|
||||
self.require_module()
|
||||
self.assertEqual(AUTOTAG_TABLE, TABLE)
|
||||
model = self.model()
|
||||
with model.get_connection() as conn:
|
||||
# WITHOUT ROWID with a primary key: no sqlite_autoindex row.
|
||||
self.assertEqual(catalog(conn), {("table", TABLE, _compact(DDL))})
|
||||
self.assertEqual(
|
||||
[tuple(row) for row in conn.execute(f"PRAGMA table_info({TABLE})")],
|
||||
[(0, "byte_id", "TEXT", 1, None, 1)],
|
||||
)
|
||||
self.assertIsNone(autotag_schema_error(conn, allow_missing=False))
|
||||
self.assertEqual(marks(conn), [])
|
||||
self.assertEqual(
|
||||
PromptModel.verify_database_file(self.path, require_library_state=True),
|
||||
(True, "ok"),
|
||||
)
|
||||
|
||||
def test_reopen_and_rerun_are_idempotent(self):
|
||||
self.require_module()
|
||||
path = self.closed_current()
|
||||
for _ in range(2):
|
||||
PromptModel.reset_schema_cache()
|
||||
model = self.model(path)
|
||||
with model.get_connection() as conn:
|
||||
migrate_autotag_state(conn)
|
||||
self.assertEqual(marks(conn), [(BYTE_ID,)])
|
||||
self.assertEqual(catalog(conn), {("table", TABLE, _compact(DDL))})
|
||||
model.close_all()
|
||||
|
||||
def test_old_database_without_the_table_gains_it_and_keeps_its_rows(self):
|
||||
self.require_module()
|
||||
path = self.closed_current(with_mark=False)
|
||||
self.raw(path, f"DROP TABLE {TABLE}")
|
||||
with closing(sqlite3.connect(path)) as raw:
|
||||
before = raw.execute("SELECT * FROM media_annotation_bytes").fetchall()
|
||||
self.assertIsNone(autotag_schema_error(raw))
|
||||
self.assertEqual(
|
||||
autotag_schema_error(raw, allow_missing=False),
|
||||
"Missing image auto-tag marks schema",
|
||||
)
|
||||
self.assertTrue(PromptModel.verify_database_file(path)[0])
|
||||
self.assertEqual(
|
||||
PromptModel.verify_database_file(path, require_library_state=True),
|
||||
(False, "Missing image auto-tag marks schema"),
|
||||
)
|
||||
PromptModel.reset_schema_cache()
|
||||
model = self.model(path)
|
||||
with model.get_connection() as conn:
|
||||
self.assertEqual(catalog(conn), {("table", TABLE, _compact(DDL))})
|
||||
self.assertEqual(
|
||||
[
|
||||
tuple(row)
|
||||
for row in conn.execute("SELECT * FROM media_annotation_bytes")
|
||||
],
|
||||
before,
|
||||
)
|
||||
model.close_all()
|
||||
|
||||
def test_table_without_annotation_group_is_refused(self):
|
||||
self.require_module()
|
||||
path = self.closed_current(with_mark=False)
|
||||
self.raw(
|
||||
path,
|
||||
*(
|
||||
f"DROP TABLE {t}"
|
||||
for t in REVIEW_TABLES + tuple(reversed(ANNOTATION_TABLES))
|
||||
),
|
||||
)
|
||||
with closing(sqlite3.connect(path)) as raw:
|
||||
self.assertEqual(autotag_without_annotations_error(raw), NEEDS_ANNOTATIONS)
|
||||
for allow_missing in (True, False):
|
||||
self.assertEqual(
|
||||
autotag_schema_error(raw, allow_missing=allow_missing),
|
||||
NEEDS_ANNOTATIONS,
|
||||
)
|
||||
self.assertEqual(
|
||||
PromptModel.verify_database_file(path), (False, NEEDS_ANNOTATIONS)
|
||||
)
|
||||
PromptModel.reset_schema_cache()
|
||||
with self.assertRaises(sqlite3.DatabaseError) as raised:
|
||||
self.model(path)
|
||||
self.assertIn(NEEDS_ANNOTATIONS, str(raised.exception))
|
||||
|
||||
def test_invalid_values_are_refused_without_repair(self):
|
||||
self.require_module()
|
||||
cases = {
|
||||
"not-a-uuid": (f"INSERT INTO {TABLE} VALUES('not-a-uuid')",),
|
||||
"upper-uuid": ((f"INSERT INTO {TABLE} VALUES(?)", (OTHER_ID.upper(),)),),
|
||||
"dangling": ((f"INSERT INTO {TABLE} VALUES(?)", (OTHER_ID,)),),
|
||||
}
|
||||
for name, statements in cases.items():
|
||||
with self.subTest(name):
|
||||
path = self.closed_current(f"{name}.db", with_mark=False)
|
||||
self.raw(path, *statements)
|
||||
with closing(sqlite3.connect(path)) as raw:
|
||||
self.assertEqual(autotag_schema_error(raw), INVALID_VALUES)
|
||||
before = marks(raw)
|
||||
self.assertEqual(
|
||||
PromptModel.verify_database_file(path), (False, INVALID_VALUES)
|
||||
)
|
||||
PromptModel.reset_schema_cache()
|
||||
with self.assertRaises(sqlite3.DatabaseError):
|
||||
self.model(path)
|
||||
with closing(sqlite3.connect(path)) as raw:
|
||||
self.assertEqual(marks(raw), before)
|
||||
|
||||
def test_altered_definitions_are_refused(self):
|
||||
self.require_module()
|
||||
cases = {
|
||||
"rowid": f"CREATE TABLE {TABLE} (byte_id TEXT PRIMARY KEY "
|
||||
"REFERENCES media_annotation_bytes(id) ON DELETE CASCADE)",
|
||||
"restrict": f"CREATE TABLE {TABLE} (byte_id TEXT PRIMARY KEY "
|
||||
"REFERENCES media_annotation_bytes(id) ON DELETE RESTRICT) WITHOUT ROWID",
|
||||
"extra column": f"CREATE TABLE {TABLE} (byte_id TEXT PRIMARY KEY "
|
||||
"REFERENCES media_annotation_bytes(id) ON DELETE CASCADE, engine TEXT) "
|
||||
"WITHOUT ROWID",
|
||||
}
|
||||
for name, ddl in cases.items():
|
||||
with self.subTest(name):
|
||||
path = self.closed_current(f"{name}.db", with_mark=False)
|
||||
self.raw(path, f"DROP TABLE {TABLE}", ddl)
|
||||
with closing(sqlite3.connect(path)) as raw:
|
||||
self.assertEqual(autotag_schema_error(raw), INVALID_SCHEMA)
|
||||
self.assertFalse(PromptModel.verify_database_file(path)[0])
|
||||
path = self.closed_current("index.db", with_mark=False)
|
||||
self.raw(path, f"CREATE INDEX idx_extra ON {TABLE}(byte_id)")
|
||||
with closing(sqlite3.connect(path)) as raw:
|
||||
self.assertEqual(autotag_schema_error(raw), INVALID_SCHEMA)
|
||||
|
||||
def test_deleting_the_byte_record_cascades_to_its_mark(self):
|
||||
self.require_module()
|
||||
model = self.model()
|
||||
with model.get_connection() as conn:
|
||||
insert_byte(conn)
|
||||
conn.execute(f"INSERT INTO {TABLE} VALUES(?)", (BYTE_ID,))
|
||||
conn.execute(f"INSERT OR IGNORE INTO {TABLE} VALUES(?)", (BYTE_ID,))
|
||||
self.assertEqual(marks(conn), [(BYTE_ID,)])
|
||||
conn.execute("DELETE FROM media_annotation_files")
|
||||
self.assertEqual(marks(conn), [])
|
||||
|
||||
def test_restore_of_a_pre_change_backup_migrates(self):
|
||||
self.require_module()
|
||||
src = self.closed_current("backup.db", with_mark=False)
|
||||
self.raw(src, f"DROP TABLE {TABLE}")
|
||||
live = self.model()
|
||||
live.restore_from_file(src)
|
||||
with closing(sqlite3.connect(self.path)) as raw:
|
||||
self.assertEqual(catalog(raw), {("table", TABLE, _compact(DDL))})
|
||||
self.assertEqual(
|
||||
raw.execute("SELECT id FROM media_annotation_bytes").fetchall(),
|
||||
[(BYTE_ID,)],
|
||||
)
|
||||
self.assertEqual(
|
||||
PromptModel.verify_database_file(self.path, require_library_state=True),
|
||||
(True, "ok"),
|
||||
)
|
||||
with closing(sqlite3.connect(src)) as raw: # the source is untouched
|
||||
self.assertEqual(catalog(raw), set())
|
||||
|
||||
def test_install_failure_rolls_back(self):
|
||||
self.require_module()
|
||||
src = self.closed_current("copy.db", with_mark=False)
|
||||
self.raw(src, f"DROP TABLE {TABLE}")
|
||||
path = str(Path(self.temp.name) / "rollback.db")
|
||||
shutil.copyfile(src, path)
|
||||
with closing(sqlite3.connect(path)) as raw:
|
||||
raw.execute("BEGIN")
|
||||
raw.execute("CREATE TABLE marker(x)")
|
||||
# An invalid group already present: nothing created, outer work kept.
|
||||
raw.execute(f"CREATE TABLE {TABLE}(byte_id TEXT)")
|
||||
with self.assertRaises(sqlite3.DatabaseError):
|
||||
migrate_autotag_state(raw)
|
||||
self.assertEqual(
|
||||
raw.execute(
|
||||
f"SELECT sql FROM sqlite_master WHERE name='{TABLE}'"
|
||||
).fetchone()[0],
|
||||
f"CREATE TABLE {TABLE}(byte_id TEXT)",
|
||||
)
|
||||
self.assertIsNotNone(
|
||||
raw.execute(
|
||||
"SELECT 1 FROM sqlite_master WHERE name='marker'"
|
||||
).fetchone()
|
||||
)
|
||||
raw.rollback()
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
@@ -468,6 +468,7 @@ class TestRestoreFromFile(BackupTestCase):
|
||||
|
||||
def test_restore_old_backup_without_annotations(self):
|
||||
tables = (
|
||||
"media_image_autotags",
|
||||
"media_review_decisions",
|
||||
"media_review_items",
|
||||
"media_review_metadata",
|
||||
|
||||
@@ -371,7 +371,10 @@ class ReviewSchemaTests(unittest.TestCase):
|
||||
self.require_module()
|
||||
for label, dropped in (
|
||||
("annotations only", TABLES),
|
||||
("predates annotations", ANNOTATION_TABLES + TABLES),
|
||||
(
|
||||
"predates annotations",
|
||||
("media_image_autotags",) + ANNOTATION_TABLES + TABLES,
|
||||
),
|
||||
):
|
||||
with self.subTest(label):
|
||||
path = str(Path(self.temp.name) / f"{label.replace(' ', '-')}.db")
|
||||
|
||||
Reference in New Issue
Block a user