phase: 126_pdf_support
All gates verified green — no code changes were needed on this pass. Final report: ## Phase 126 — PDF support: final verification pass **Verified (all tasks 01–05 already complete in working tree):** - `pymupdf` dep in `pyproject.toml`/`uv.lock`; `.env.example` documents the `pdf` token - `app/rag/pdf.py` (text + image extraction, MIME mapping), page-aware `_chunk_pdf`, importer `_index_pdf_file` + embedded-image pass, archives covered via extension walk **Test / lint / coverage results:** - `uv run pytest` → 2997 passed - `uv run pytest tests/e2e/test_pdf_support.py -v --no-cov` (isolation) → 6 passed - `uv run pytest --cov=app --cov-report=term-missing` → TOTAL **99%** (>90% gate), 2997 passed - `uv run ruff check . && uv run pyright` → clean (0 errors) **Completion criteria:** 1. PDF → doc with text/chunks/embedding/summary — ✅ (integration + E2E Sources-page tests) 2. `BOR_IMAGES=true`: embedded images → standalone image docs — ✅ (integration + E2E chat-chip test) 3. `BOR_IMAGES=false`: images skipped, text indexed — ✅ (both suites) 4. PDF renders as extracted text in viewer — ✅ (E2E) 5. Test/coverage/lint gates — ✅ (above) 6. Commit + phase move — harness handles (per protocol, no `git` on this pass) **Decisions:** none new; inline `[Embedded image: …]` placeholders were a documented task-04 deviation (simplified spec wins) — not a defect. No defects found; repo left functional with changes in the working tree. **Next pending phase:** none — `todo/` is empty once 126 is moved.
This commit is contained in:
@@ -61,6 +61,7 @@ dependencies = [
|
||||
{ name = "psycopg", extra = ["binary"] },
|
||||
{ name = "pydantic" },
|
||||
{ name = "pydantic-settings" },
|
||||
{ name = "pymupdf" },
|
||||
{ name = "python-dotenv" },
|
||||
{ name = "python-multipart" },
|
||||
{ name = "sqlalchemy" },
|
||||
@@ -88,6 +89,7 @@ requires-dist = [
|
||||
{ name = "psycopg", extras = ["binary"], specifier = ">=3.1,<4.0" },
|
||||
{ name = "pydantic", specifier = ">=2.7,<3.0" },
|
||||
{ name = "pydantic-settings", specifier = ">=2.3,<3.0" },
|
||||
{ name = "pymupdf", specifier = ">=1.24,<2.0" },
|
||||
{ name = "python-dotenv", specifier = ">=1.0,<2.0" },
|
||||
{ name = "python-multipart", specifier = ">=0.0.9,<0.1" },
|
||||
{ name = "sqlalchemy", specifier = ">=2.0,<2.1" },
|
||||
@@ -846,6 +848,24 @@ wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/71/46/17f022dd3e953bf20a04a028a21ec746d942f8d2af30fa0f124fa0e6a684/pygments-2.21.0-py3-none-any.whl", hash = "sha256:2363c69b61c4a97c838da3b130dcd6468f4848992b21a82f2a63ec34377137d9", size = 1250147, upload-time = "2026-08-17T08:02:44.912Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "pymupdf"
|
||||
version = "1.28.2"
|
||||
source = { registry = "https://pypi.org/simple" }
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/a3/fb/b6761fa2d5266f2cdb24c3b91f4023070ab7848381417678e7a289a1d52a/pymupdf-1.28.2.tar.gz", hash = "sha256:5e0be7908a715aa20333caddd73f1d6f01e4cd0c26e869fa2dd0b7f344da2249", size = 87903557, upload-time = "2026-08-06T21:43:23.321Z" }
|
||||
wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/b4/51/550c9a75c4ff3245cb4ecb7bb95cbe2ab7374230b8e2b7a1f7259444150b/pymupdf-1.28.2-cp310-abi3-macosx_10_15_x86_64.whl", hash = "sha256:5fc315b425ff1f7afdd1ea2f348205cb19b806767daae7ce4d64115799c2bae1", size = 24645079, upload-time = "2026-08-06T21:37:25.001Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/fa/01/3591f781b417b382a8487a2356e927acfe858b1043bab0ec47f6805bb109/pymupdf-1.28.2-cp310-abi3-macosx_11_0_arm64.whl", hash = "sha256:7113846b35dbf0a033f088e4f4fb543dabeb4b0b12c112966a1ca1ee2d5eacae", size = 23875605, upload-time = "2026-08-06T21:37:40.369Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/d2/86/4a68f080b71b46802178346af46486e1697508e760855ff5f3b218a6dff7/pymupdf-1.28.2-cp310-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:3050a233dde1211efe89ada74e2add6238436434159f46097a1423aad2842545", size = 25095554, upload-time = "2026-08-06T21:37:58.485Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/c7/06/dace3e27af26690cb20bead80dbac42941b0841eb689b8aabbd67dde16f0/pymupdf-1.28.2-cp310-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:397d6715c1f0df7548a92d0afd8ce370fc48fa47aeefac16be2bc04a16a8227f", size = 25762500, upload-time = "2026-08-06T21:38:17.438Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/e5/61/4146dfa1d8172a1ce8d59f0eed94896ddefb8deb2274534d0522fbb8abf5/pymupdf-1.28.2-cp310-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:f89fb2d86d07d643a269f17a093105057e20c79c1d06c103b53600067b6d2b01", size = 25986309, upload-time = "2026-08-06T21:38:35.472Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/52/60/1fb6e64676f7500ebe89054b9e5bbbe14d3101c92d5f1a40ac9a35227673/pymupdf-1.28.2-cp310-abi3-win32.whl", hash = "sha256:530ef543a3885b3b81cb72a854e7c5a625a9233201221132bb6c31698c6a2bdb", size = 18525353, upload-time = "2026-08-06T21:38:47.697Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/4a/61/d563bbccba262f9dd6d2d35ccb72593648184d886188efb12d9ce8f34dd6/pymupdf-1.28.2-cp310-abi3-win_amd64.whl", hash = "sha256:ebd244918798502d7b4504c90410d1711a4d7675a32584ca30f1bab419ecbffe", size = 19826532, upload-time = "2026-08-06T21:39:00.213Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/e2/93/08f404a1f0155fe24137cf2d3aabd3e2b4b08c62053ed89c60f2611be3e9/pymupdf-1.28.2-cp310-abi3-win_arm64.whl", hash = "sha256:ffe91a24edc75c80da2a4b62f50fc0f54632d34fc8fe4cbc48e5c7ff07cf8fb4", size = 19759252, upload-time = "2026-08-06T21:39:12.937Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/58/8c/d897dcd32a25b58186c968b15ce4324ca029e9d96460de12325314e390be/pymupdf-1.28.2-cp313-abi3-pyemscripten_2025_0_wasm32.whl", hash = "sha256:2e1b574c0fd2cb238021033fd3c0f9c4388816638df064e4bfb56d9d81736dc8", size = 18399403, upload-time = "2026-08-06T21:39:25.008Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/f6/f1/de34a1c53fe2bf8c6e71db84b0ced782d408970c9810d2b456a2ae96814c/pymupdf-1.28.2-cp314-cp314t-manylinux_2_28_x86_64.whl", hash = "sha256:fd481ed48bef56305c41fb7e05a055c03345c899c7b101dad086258b438f8168", size = 25802333, upload-time = "2026-08-06T21:39:41.426Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "pyright"
|
||||
version = "1.1.411"
|
||||
|
||||
Reference in New Issue
Block a user