classifyre-cli 0.6.10__tar.gz → 0.6.11__tar.gz

classifyre_cli-0.6.11/.turbo/turbo-build.log

@@ -0,0 +1,3 @@
+$ uv sync
+Resolved 324 packages in 202ms
+Checked 51 packages in 0.91ms

{classifyre_cli-0.6.10 → classifyre_cli-0.6.11}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: classifyre-cli
-Version: 0.6.10
+Version: 0.6.11
 Summary: Classifyre CLI — scan and classify unstructured data sources
 License: MIT
 Keywords: data,ingestion,metadata,pii,secrets,unstructured

{classifyre_cli-0.6.10 → classifyre_cli-0.6.11}/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@classifyre/cli",
-  "version": "0.6.10",
+  "version": "0.6.11",
   "private": true,
   "scripts": {
     "build": "uv sync",

{classifyre_cli-0.6.10 → classifyre_cli-0.6.11}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "classifyre-cli"
-version = "0.6.10"
+version = "0.6.11"
 description = "Classifyre CLI — scan and classify unstructured data sources"
 readme = "README.md"
 # Upper bound is load-bearing: onnxruntime publishes no cp315 wheels (notably
@@ -483,6 +483,21 @@ package = true
 # distribution declared by our video and OCR groups. Installing both would
 # overwrite the same cv2 namespace and add GUI libraries to CPU-only containers.
 exclude-dependencies = ["opencv-python"]
+# Two transitive dependencies whose latest release breaks the package that
+# pulls it in, while that package's own requirement still allows it. Both
+# failures were silent in a scan: images and scans came back with no text, and
+# every audio and video file failed. Lift a bound when its consumer catches up.
+constraint-dependencies = [
+    # faster-whisper 1.2.1 (its latest) decodes with
+    # av.open(..., metadata_errors="ignore"), and so does utils/transcription.py.
+    # PyAV 19 removed the argument: every transcription raised TypeError.
+    "av>=11,<19",
+    # Docling (through 2.135) imports rapidocr.utils.model_resolver.PP_OCRV6_LANGS
+    # while building its RapidOCR engine. rapidocr 3.10.0 no longer has it;
+    # Docling catches the ImportError, logs "No OCR engine found" and converts
+    # every image and scanned PDF to an empty document.
+    "rapidocr>=3.9.1,<3.10",
+]
 # Every platform we ship must resolve to versions with
 # usable wheels. Without this, uv happily locks versions that are missing a
 # platform — e.g. deltalake 1.6.1 published no win_amd64 wheel, which broke the

{classifyre_cli-0.6.10 → classifyre_cli-0.6.11}/src/detectors/custom_detector/results.py

@@ -215,9 +215,7 @@ class FindingMapper:
         # Overlong keys are hashed, never truncated: truncation collides
         # ("row-111..." vs "row-111..." with a different tail become one
         # finding), and the API applies the same hash, so both sides agree.
-        identity_key = (
-            _identity_key(str(identity)) if identity not in (None, "") else None
-        )
+        identity_key = _identity_key(str(identity)) if identity not in (None, "") else None
         if identity_key is not None:
             metadata["identity"] = identity_key
 
@@ -263,4 +261,4 @@ class FindingMapper:
         return kept or None
 
 
-__all__ = ["RUNNER", "FindingMapper", "bound_severity", "_identity_key"]
+__all__ = ["RUNNER", "FindingMapper", "_identity_key", "bound_severity"]

{classifyre_cli-0.6.10 → classifyre_cli-0.6.11}/src/utils/file_parser.py

@@ -466,9 +466,15 @@ class _DoclingState:
         # sync itself failed (transient: network blip, registry timeout). A
         # genuine broken package fails on the retry too and is cached then.
         self.install_retry_remaining: int = 1
+        # Whether Docling resolved an OCR engine, asked once per process.
+        self.ocr_engine_checked: bool = False
+        self.ocr_engine_error: str | None = None
+        self.ocr_engine_failures: int = 0
 
 
 _docling_state = _DoclingState()
+# How often building the OCR engine may fail before the failure is taken as settled.
+_OCR_ENGINE_ATTEMPTS = 2
 _docling_lock = threading.Lock()
 # Limits concurrent converter.convert() calls to prevent OOM. The docling
 # StandardPdfPipeline alone holds ~1 GB of model weights; additional working
@@ -538,6 +544,71 @@ def _reset_docling_singleton() -> None:
         _docling_state.error = None
         _docling_state.attempted = False
         _docling_state.install_retry_remaining = 1
+        _docling_state.ocr_engine_checked = False
+        _docling_state.ocr_engine_error = None
+        _docling_state.ocr_engine_failures = 0
+
+
+def _docling_ocr_engine_error() -> str | None:
+    """Why Docling cannot read pixels in this environment, or None when it can.
+
+    Docling picks its OCR engine by trying each one and catching ImportError.
+    When none constructs it logs "No OCR engine found" and carries on: every
+    image and every scanned PDF then converts to an empty document, with no
+    error for the caller to see. That is how rapidocr 3.10.0 (which dropped a
+    name Docling imports) turned a whole drive of photographs and scans into
+    "extraction completed, no text" instead of a failure.
+
+    So the same selection is run once here and its outcome kept. The answer
+    contains "unavailable" on purpose: iter_file_pages reports such an error as
+    ENGINE_UNAVAILABLE, which a scan counts as missing coverage and retries,
+    rather than as an empty file.
+    """
+    if _docling_state.ocr_engine_checked:
+        return _docling_state.ocr_engine_error
+    with _docling_lock:
+        if _docling_state.ocr_engine_checked:
+            return _docling_state.ocr_engine_error
+        import importlib
+
+        try:
+            accelerator = importlib.import_module("docling.datamodel.accelerator_options")
+            options = importlib.import_module("docling.datamodel.pipeline_options")
+            auto = importlib.import_module("docling.models.stages.ocr.auto_ocr_model")
+            build = auto.OcrAutoModel
+            auto_options = options.OcrAutoOptions
+            accelerator_options = accelerator.AcceleratorOptions
+        except Exception:
+            # A Docling laid out differently from the one this was written
+            # against: nothing to ask, so do not second-guess it.
+            _docling_state.ocr_engine_checked = True
+            return None
+        try:
+            model = build(
+                enabled=True,
+                artifacts_path=None,
+                options=auto_options(),
+                accelerator_options=accelerator_options(),
+            )
+        except Exception as exc:
+            # Building an engine can fail for a reason that passes (its model
+            # files are fetched on first use), so this answer is kept only
+            # once it has been given twice.
+            _docling_state.ocr_engine_failures += 1
+            if _docling_state.ocr_engine_failures >= _OCR_ENGINE_ATTEMPTS:
+                _docling_state.ocr_engine_error = f"OCR engine unavailable: {exc}"
+                _docling_state.ocr_engine_checked = True
+            return f"OCR engine unavailable: {exc}"
+        error: str | None = None
+        # Absent attribute (a later Docling) reads as "resolved".
+        if getattr(model, "_engine", model) is None:
+            error = (
+                "OCR engine unavailable: Docling found no usable OCR engine "
+                "(see the 'cannot be used because' lines it logged above)"
+            )
+        _docling_state.ocr_engine_error = error
+        _docling_state.ocr_engine_checked = True
+        return error
 
 
 def _require_file_processing(module_name: str) -> object:
@@ -1004,6 +1075,12 @@ def _extract_docling_markdown(
         return "", error
     if converter is None:
         return "", "Docling converter unavailable"
+    # Pixels need an OCR engine; the document formats Docling parses natively
+    # (pptx, odt, msg) do not, and must keep working without one.
+    if _normalize_mime_type(mime_type).startswith("image/") or mime_type == "application/pdf":
+        engine_error = _docling_ocr_engine_error()
+        if engine_error:
+            return "", engine_error
 
     temp_fname = _temp_file_name(file_name, mime_type)
     try:

{classifyre_cli-0.6.10 → classifyre_cli-0.6.11}/tests/utils/test_file_parser.py

@@ -473,6 +473,96 @@ class TestDoclingConverterSingleton:
         assert text1 == text2 == "ocr output"
         assert len(init_count) == 1, "DocumentConverter() must not be re-instantiated per file"
 
+    def _install_fake_ocr_selection(
+        self,
+        monkeypatch: pytest.MonkeyPatch,
+        *,
+        engine: object | None,
+        raises: Exception | None = None,
+    ) -> list[int]:
+        """Inject the Docling modules the OCR-engine check asks, on top of the fake converter.
+
+        `engine` is what Docling's automatic selection ends up with: None is
+        the state it logs as "No OCR engine found" and then ignores.
+        """
+        selections: list[int] = []
+
+        class FakeAutoModel:
+            def __init__(self, **_kwargs: Any) -> None:
+                selections.append(1)
+                if raises is not None:
+                    raise raises
+                self._engine = engine
+
+        modules = {
+            "docling.datamodel": {},
+            "docling.datamodel.accelerator_options": {"AcceleratorOptions": object},
+            "docling.datamodel.pipeline_options": {"OcrAutoOptions": object},
+            "docling.models": {},
+            "docling.models.stages": {},
+            "docling.models.stages.ocr": {},
+            "docling.models.stages.ocr.auto_ocr_model": {"OcrAutoModel": FakeAutoModel},
+        }
+        for name, attributes in modules.items():
+            module = ModuleType(name)
+            for attribute, value in attributes.items():
+                setattr(module, attribute, value)
+            monkeypatch.setitem(sys.modules, name, module)
+        return selections
+
+    def test_image_without_an_ocr_engine_is_engine_unavailable(
+        self, monkeypatch: pytest.MonkeyPatch
+    ) -> None:
+        """Docling converting pixels with no engine is missing coverage, not an empty file."""
+        self._install_fake_docling(monkeypatch, [])
+        self._install_fake_ocr_selection(monkeypatch, engine=None)
+
+        text, error = extract_text(png_stub(), "image/png", file_name="whiteboard.png")
+        assert text == ""
+        assert error is not None and "OCR engine unavailable" in error
+
+        with pytest.raises(TextExtractionCoverageError) as raised:
+            list(iter_file_pages(png_stub(), "image/png", file_name="whiteboard.png"))
+        assert raised.value.code == TextExtractionCoverageCode.ENGINE_UNAVAILABLE
+
+    def test_ocr_engine_that_fails_to_build_is_engine_unavailable(
+        self, monkeypatch: pytest.MonkeyPatch
+    ) -> None:
+        self._install_fake_docling(monkeypatch, [])
+        selections = self._install_fake_ocr_selection(
+            monkeypatch, engine=None, raises=ImportError("rapidocr does not expose PP_OCRV6_LANGS")
+        )
+
+        for name in ("scan-1.png", "scan-2.png", "scan-3.png"):
+            _text, error = extract_text(png_stub(), "image/png", file_name=name)
+            assert error == "OCR engine unavailable: rapidocr does not expose PP_OCRV6_LANGS"
+        # Tried again once, in case the first failure was a download that did
+        # not finish, and then no more: every further image costs nothing.
+        assert len(selections) == 2
+
+    def test_ocr_engine_is_asked_once(self, monkeypatch: pytest.MonkeyPatch) -> None:
+        self._install_fake_docling(monkeypatch, [])
+        selections = self._install_fake_ocr_selection(monkeypatch, engine=object())
+
+        text1, error1 = extract_text(png_stub(), "image/png", file_name="a.png")
+        text2, error2 = extract_text(png_stub(), "image/png", file_name="b.png")
+
+        assert (text1, error1) == (text2, error2) == ("ocr output", None)
+        assert len(selections) == 1, "the engine selection loads models: once per process"
+
+    def test_native_document_formats_do_not_need_an_ocr_engine(
+        self, monkeypatch: pytest.MonkeyPatch
+    ) -> None:
+        """An .odt has no pixels to read; a missing OCR engine must not cost its text."""
+        self._install_fake_docling(monkeypatch, [])
+        selections = self._install_fake_ocr_selection(monkeypatch, engine=None)
+
+        text, error = extract_text(
+            b"odt-bytes", "application/vnd.oasis.opendocument.text", file_name="doc.odt"
+        )
+        assert (text, error) == ("ocr output", None)
+        assert selections == []
+
 
 # ---------------------------------------------------------------------------
 # parse_file

{classifyre_cli-0.6.10 → classifyre_cli-0.6.11}/uv.lock

@@ -23,6 +23,10 @@ required-markers = [
 ]
 
 [manifest]
+constraints = [
+    { name = "av", specifier = ">=11,<19" },
+    { name = "rapidocr", specifier = ">=3.9.1,<3.10" },
+]
 excludes = ["opencv-python"]
 
 [[package]]
@@ -337,28 +341,28 @@ wheels = [
 
 [[package]]
 name = "av"
-version = "19.0.1"
-source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/90/bc/a2a40e503250fe5d4174471911828f31658864eb69a8a7cb960c715e17b7/av-19.0.1.tar.gz", hash = "sha256:08674930eaf1af78a3ed8f93d3ba49383323b3a867e84349d9c399e36f7497da", size = 4274648, upload-time = "2026-10-03T01:48:28.575Z" }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/ec/2f/f4d219b2c72fea88bcbaea23de5b7f864ebecd348586fd2fe69f7f657147/av-19.0.1-cp312-abi3-macosx_11_0_x86_64.whl", hash = "sha256:2bd44ef4c09bb04aa6100d4c6191ddedaffef6af757ac55d5b4dc90915859299", size = 22625494, upload-time = "2026-10-03T01:47:21.866Z" },
-    { url = "https://files.pythonhosted.org/packages/ff/75/db37bb43a12a317cc0c0b96ddabc7896f582503b377e0803d4d721969522/av-19.0.1-cp312-abi3-macosx_14_0_arm64.whl", hash = "sha256:29d85e4ee36bf8f475dad07d4f4417c07bba62535f6a7179429c357e0ca8fb0f", size = 18439188, upload-time = "2026-10-03T01:47:25.541Z" },
-    { url = "https://files.pythonhosted.org/packages/10/4b/61f138fcf21e7bb50655ed21dd7fdc7a296baf72ea3c7ad8e89cb00b69c1/av-19.0.1-cp312-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:437d4c0d5a7d771f2c3af84cd28e6aac6e173851116c60b53e81dbf1eebe4eab", size = 32676941, upload-time = "2026-10-03T01:47:29.237Z" },
-    { url = "https://files.pythonhosted.org/packages/c8/97/5fb45934ac64e8afc2c6869a7dcb8cb2af1ddab09a725367548856cbb59f/av-19.0.1-cp312-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:1bea5b6134209305199bce7627ac3d33964de2cf2b09c77d08e7f67cf8bd4170", size = 34983451, upload-time = "2026-10-03T01:47:32.895Z" },
-    { url = "https://files.pythonhosted.org/packages/66/f2/6eee1b99ac492fa1965d6fd466ef8b644ca296b4f1dfa8c8225ab340b139/av-19.0.1-cp312-abi3-manylinux_2_31_armv7l.whl", hash = "sha256:1de938ec0134ad88f795dfe0a2dfc2d59e9ecea39a20158d37961279a3483612", size = 41660680, upload-time = "2026-10-03T01:47:36.903Z" },
-    { url = "https://files.pythonhosted.org/packages/11/be/e4ddd0197d02a3114402f3ffde541f6c4edecd24d670bea0da1eb6f15fb2/av-19.0.1-cp312-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:bcd0af218ecbeddbb1b0c56c4278043a3d97b87f3b8e33f6f92d452c744b1b08", size = 33748455, upload-time = "2026-10-03T01:47:40.541Z" },
-    { url = "https://files.pythonhosted.org/packages/7a/41/b9af863f635f64abaf5eb734521306487fc79447f5d55d792339a81c8a4d/av-19.0.1-cp312-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:935a6b6386a6994964e324eb02af4dab01eedbcbbde23b4b21bf1dc59b004244", size = 36008899, upload-time = "2026-10-03T01:47:44.13Z" },
-    { url = "https://files.pythonhosted.org/packages/e6/dc/a87a5a5e3ac462734f9befd8bad1447301e5802d8c111e22bf708fba7af3/av-19.0.1-cp312-abi3-win_amd64.whl", hash = "sha256:906fc3db09288319a75ea23ffefb59961c7dbe0d1c074601507a89de7d8593d8", size = 28149519, upload-time = "2026-10-03T01:47:47.372Z" },
-    { url = "https://files.pythonhosted.org/packages/a5/78/16864f1aa2c3ac5017f15132b85c6d3c74bb85caca8c45ce836ad30dfe20/av-19.0.1-cp312-abi3-win_arm64.whl", hash = "sha256:e9e1b0cae6cebd2adc2c5c6691fc890112f8f6c846b76a9135307617db1e32e9", size = 20706822, upload-time = "2026-10-03T01:47:50.72Z" },
-    { url = "https://files.pythonhosted.org/packages/78/4a/b5d7614856af72d7c18b926dda43bd227844b0b42d64e7c478b080f8d9c1/av-19.0.1-cp314-cp314t-macosx_11_0_x86_64.whl", hash = "sha256:3ef376ab828730f50b635e3541f305503adad713cb4c3eadb5ad0e4c6a6f4a72", size = 22909764, upload-time = "2026-10-03T01:47:54.032Z" },
-    { url = "https://files.pythonhosted.org/packages/b6/c9/50b2dedd4314a0ba0d78d7a7a52f7b073bc3377e5152e51d9d5627c5bcf4/av-19.0.1-cp314-cp314t-macosx_14_0_arm64.whl", hash = "sha256:17f2e42a1c969c78c616fe58bc69641a9df404c1ac2f01b50c1ddc22e5c31f69", size = 18718945, upload-time = "2026-10-03T01:47:58.396Z" },
-    { url = "https://files.pythonhosted.org/packages/ef/a5/eb2b6aadbda16ee676c76e43012709f0cdfe09c35bc9ad4ffb5099827e72/av-19.0.1-cp314-cp314t-manylinux_2_28_aarch64.whl", hash = "sha256:aafd294abd0e5c23e6c813b10fb4792cf1dd1002c1aead0292d195cda2ca154e", size = 36470355, upload-time = "2026-10-03T01:48:01.686Z" },
-    { url = "https://files.pythonhosted.org/packages/c1/f0/25e7d21cc29e949118bdac6efe0ef5c5020fc4273a3ea237989728ebe816/av-19.0.1-cp314-cp314t-manylinux_2_28_x86_64.whl", hash = "sha256:400ba5234865dc370c442658efff0672c64dcad2de26a2a7c900abf16ffd9f68", size = 38457564, upload-time = "2026-10-03T01:48:05.61Z" },
-    { url = "https://files.pythonhosted.org/packages/3f/09/77fec7c8de49fb815d55de1dfac21b39fb9e6915cbd8dcd945538ebb6f44/av-19.0.1-cp314-cp314t-manylinux_2_31_armv7l.whl", hash = "sha256:5e527b9d2d23c096d2b488e19a40ceba3654ea84a3cecee1c1b46c70ceaceae2", size = 43462245, upload-time = "2026-10-03T01:48:10.674Z" },
-    { url = "https://files.pythonhosted.org/packages/8c/1d/bb0281ada4203c5d85f7e8b045de2cadc89c3b5d0ed5705298f7a9288b1f/av-19.0.1-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:79136e62d4bc93db81fb63d6dd0060e86259426c071ca5157b1abe8c815c40b7", size = 37339005, upload-time = "2026-10-03T01:48:14.805Z" },
-    { url = "https://files.pythonhosted.org/packages/0a/84/19a9d37d7546a3879d759a8957b2513a029cafb81f60218c496b1ce9d5a8/av-19.0.1-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:330f91c704aa822b96d9aa21382c0eb41a68531d388078d724d334faa460cbcc", size = 39466754, upload-time = "2026-10-03T01:48:18.988Z" },
-    { url = "https://files.pythonhosted.org/packages/30/c4/39d4e2b778f1e86672671e25c3fd38e8d59d59b6f65c5cd13d7fae3d88a3/av-19.0.1-cp314-cp314t-win_amd64.whl", hash = "sha256:8289295bfd2a438f2cf83c3ab426964055e441f1500410a842e7a767bdc8e51e", size = 29063526, upload-time = "2026-10-03T01:48:22.724Z" },
-    { url = "https://files.pythonhosted.org/packages/f4/7d/a20ff44c1445c09a93985418f6997e5823635848e955a7953339636a9829/av-19.0.1-cp314-cp314t-win_arm64.whl", hash = "sha256:e1f70b1bda35588aff5fc526500376afe143e33cfce5d7e30d368170c38717db", size = 21915698, upload-time = "2026-10-03T01:48:26.386Z" },
+version = "18.1.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/8d/f4/f22114d30d3435e38c6af2b4870f37b864403dca6ae7af747a289ce0a18e/av-18.1.0.tar.gz", hash = "sha256:47bfc286e1bc9de7ab4681fc2b575cd2460a66919d31ffe1bd5aa54fae531a28", size = 4451061, upload-time = "2026-08-12T22:28:18.761Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/05/d4/d7cdc8bff143c17a6d35924375ae28dd692cacde38700a7d419fde54f44a/av-18.1.0-cp311-abi3-macosx_11_0_x86_64.whl", hash = "sha256:ae75d8bb6467895ed1f8572ededf7ffa49eac07f6e483222f5d7d62a41d12f04", size = 22546147, upload-time = "2026-08-12T22:27:11.851Z" },
+    { url = "https://files.pythonhosted.org/packages/3f/c9/37a619297492256b77d5ed906e7d8166c10a26ed251dccf1ae03ab19bff6/av-18.1.0-cp311-abi3-macosx_14_0_arm64.whl", hash = "sha256:b30a4e8d934558e19602b68998a4d9ac9f250fa0dacef216f7e8e40153b13316", size = 18217603, upload-time = "2026-08-12T22:27:14.713Z" },
+    { url = "https://files.pythonhosted.org/packages/d9/84/2464ffb64c08c5ce8b522c8e74594714414e3b0575267652c5c51c0574b9/av-18.1.0-cp311-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:6fc837cc51adf80331ac850779cd53b5d4c4460b0ebe9057a02a921c6736f19d", size = 33640142, upload-time = "2026-08-12T22:27:17.835Z" },
+    { url = "https://files.pythonhosted.org/packages/27/3a/204dbfc3e08eb4cdc6e6ff57be02150bc44523ebdb50182d10025792ebd9/av-18.1.0-cp311-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:8a032e8d8ebc73dec079364b9b4a6837638a2d106e8472314e685ffbf163e700", size = 35786210, upload-time = "2026-08-12T22:27:20.984Z" },
+    { url = "https://files.pythonhosted.org/packages/e1/99/b0d04ec553ff9a7e00455458dfa3a39c8a8f627b273056b4e5fe57d590de/av-18.1.0-cp311-abi3-manylinux_2_31_armv7l.whl", hash = "sha256:3c8b1f8b46f99d52e2d8b0ed5d0cdadf172d24794d46e2077b16e44ed08e26ff", size = 39379798, upload-time = "2026-08-12T22:27:24.432Z" },
+    { url = "https://files.pythonhosted.org/packages/56/b1/e00d4feae59160149df6126585e726fdc6300798fd40c5dd324879e81f68/av-18.1.0-cp311-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:ab5ac081bc9eaf54109120d4e56284674fecfbe520d9aa1707c7fa911ec5f4d2", size = 34690321, upload-time = "2026-08-12T22:27:27.769Z" },
+    { url = "https://files.pythonhosted.org/packages/dc/94/836fa987e3084d11a21489f11357fb24843ef3aa8faf74ddddfc603d5062/av-18.1.0-cp311-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:191224788d87af06c31784a395bb73f14b72f33d7f4871ace0157de2abdc6276", size = 36859932, upload-time = "2026-08-12T22:27:31.403Z" },
+    { url = "https://files.pythonhosted.org/packages/33/b4/76ba21e46704f632004276b85289a1582e95f5eff760436d6149875a1881/av-18.1.0-cp311-abi3-win_amd64.whl", hash = "sha256:ea1480b7a8d5405cb5f382b344731bf125fd2c1c6fae3964f6c48595628387ff", size = 27595679, upload-time = "2026-08-12T22:27:35.177Z" },
+    { url = "https://files.pythonhosted.org/packages/4f/ad/a3135884c5753b09773176b97201ae602f67ad14206c395ff838d66bf9b0/av-18.1.0-cp311-abi3-win_arm64.whl", hash = "sha256:5509ec12aaa19fd6601de13cfa6f4cdad450da07982118510592875d970454d6", size = 20257584, upload-time = "2026-08-12T22:27:38.472Z" },
+    { url = "https://files.pythonhosted.org/packages/4f/5b/4a756265d7fb164336c8d377bca21c39cfa2c178be23cedee840a69b59c5/av-18.1.0-cp314-cp314t-macosx_11_0_x86_64.whl", hash = "sha256:b36b0bae9e4c62f9487c99481ec15e4e3870fcc868522cd6d18fc2d6bfa04f01", size = 22795654, upload-time = "2026-08-12T22:27:42.016Z" },
+    { url = "https://files.pythonhosted.org/packages/d5/cc/1bc841462114a1adf4f7d87456ab78a6972e23271e71865fcd2bbd0e7360/av-18.1.0-cp314-cp314t-macosx_14_0_arm64.whl", hash = "sha256:025f84494cb23278498f03b0d8117d3e47a1cbc9c44b97eb31875cf02251e46b", size = 18435735, upload-time = "2026-08-12T22:27:45.787Z" },
+    { url = "https://files.pythonhosted.org/packages/b8/20/005500ed17a2e62a5e4bb94aa3786942560ec2f55ec1895ebf174c87abef/av-18.1.0-cp314-cp314t-manylinux_2_28_aarch64.whl", hash = "sha256:08a9ae288299cfcbf739dba4ad0c53b9b71f45184303dd45947920d022fed695", size = 37090807, upload-time = "2026-08-12T22:27:50.14Z" },
+    { url = "https://files.pythonhosted.org/packages/5c/f7/11e7f6d848d3690c31ca4f8578167393e619177f1493ccc93b9400852d4e/av-18.1.0-cp314-cp314t-manylinux_2_28_x86_64.whl", hash = "sha256:cf8a17466bef07765dbdecc9e66ed9b25d20b4e14f654fbf35345a58ac45fa0c", size = 38976836, upload-time = "2026-08-12T22:27:54.565Z" },
+    { url = "https://files.pythonhosted.org/packages/c3/63/b271473b24e806062d31191e40c6d65545e9cf59f80f044eba56dcbba0f4/av-18.1.0-cp314-cp314t-manylinux_2_31_armv7l.whl", hash = "sha256:d49a5c542dfdc00f43c6cdb6cc41dac1781ee206fe180b56aa7433dfa816dfae", size = 40896630, upload-time = "2026-08-12T22:27:59.118Z" },
+    { url = "https://files.pythonhosted.org/packages/6b/9f/2ab7fa292a947ad3466ed8e655eefa3b82f535d7ea598c297b4471a937c4/av-18.1.0-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:5548b79e2bf1f59b3e9aedc918a72d9dc45b9adaac10ff9470d5dbdda0002e47", size = 37895673, upload-time = "2026-08-12T22:28:03.98Z" },
+    { url = "https://files.pythonhosted.org/packages/e9/d8/04507c57249b399c3e4f23f01d221532f357338b5316fd2858fbd343127d/av-18.1.0-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:e7ea063f6690193ea335a1d592d6e0274350d45e2ed6af83ee107cb90cbfd84f", size = 39992431, upload-time = "2026-08-12T22:28:08.736Z" },
+    { url = "https://files.pythonhosted.org/packages/d6/d6/bc4b95bea9c2353a7e4d62a3fcfad9adcf0f881741c6ce01ee179d539ce3/av-18.1.0-cp314-cp314t-win_amd64.whl", hash = "sha256:e4d48b9f12cad009cc72fe4f4099107de5e819c95f82767f4fd01a01481c0661", size = 28497798, upload-time = "2026-08-12T22:28:13.003Z" },
+    { url = "https://files.pythonhosted.org/packages/c1/d2/0c277a46f12647c1833f40496e132fb6001e0d19e6144b5ea30896461feb/av-18.1.0-cp314-cp314t-win_arm64.whl", hash = "sha256:5cd9085028902c9880622bd37a12fd4b33060f06a52311f6f4867ca9f29a2c3b", size = 21421979, upload-time = "2026-08-12T22:28:16.48Z" },
 ]
 
 [[package]]
@@ -857,7 +861,7 @@ wheels = [
 
 [[package]]
 name = "classifyre-cli"
-version = "0.6.10"
+version = "0.6.11"
 source = { editable = "." }
 dependencies = [
     { name = "beautifulsoup4" },
@@ -1398,7 +1402,7 @@ youtube = [
 
 [[package]]
 name = "classifyre-schemas"
-version = "0.6.10"
+version = "0.6.11"
 source = { editable = "../../packages/schemas" }
 dependencies = [
     { name = "fastjsonschema" },
@@ -4326,6 +4330,7 @@ source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "pillow" },
 ]
+sdist = { url = "https://files.pythonhosted.org/packages/44/c1/82145984920ca055675af2c2795bd30da6f7461215c41f3c1eacb3d66353/pillow_heif-1.8.1.tar.gz", hash = "sha256:521ebffb8a181d56c3904e5a61f20903edee0d9d3275967b8fb345f866215c06", size = 17395786, upload-time = "2026-10-11T13:18:19.2Z" }
 wheels = [
     { url = "https://files.pythonhosted.org/packages/f9/21/276668287678aad18c8fff15146b4965067c477358dbd6250e4ee08d7ff6/pillow_heif-1.8.1-cp312-cp312-macosx_10_15_x86_64.whl", hash = "sha256:a8e7edf5d30cf10a3d062c28d4ff19baf7e4e0a3c20fb5e4e63d690d67b0bbd4", size = 4815635, upload-time = "2026-10-11T11:16:39.416Z" },
     { url = "https://files.pythonhosted.org/packages/16/a2/53ad321b6d202cd159be3914bccb0eabaa48fa7b4fc630feb31323eccb9d/pillow_heif-1.8.1-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:1c60f323daf9df728858e469e0d95010727a32ee3e6c8e9658809a070fb93f69", size = 4311517, upload-time = "2026-10-11T11:16:41.16Z" },
@@ -5538,13 +5543,12 @@ wheels = [
 
 [[package]]
 name = "rapidocr"
-version = "3.10.0"
+version = "3.9.2"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "colorlog" },
     { name = "numpy" },
     { name = "omegaconf" },
-    { name = "opencv-python-headless" },
     { name = "pillow" },
     { name = "pyclipper" },
     { name = "pyyaml" },
@@ -5554,7 +5558,7 @@ dependencies = [
     { name = "tqdm" },
 ]
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/59/07/203065283bba0c5e9c10af3602dc25ab3e59ee54dc2d1d22c8faeabf5ed8/rapidocr-3.10.0-py3-none-any.whl", hash = "sha256:2fc34e26cd0f48514804a94f8832283039c7334076bff60768b1fed9ad068050", size = 27288134, upload-time = "2026-10-08T15:07:45.98Z" },
+    { url = "https://files.pythonhosted.org/packages/55/ed/0ee9b9281986974be9d2406ae0134c8d7c91d2fc613f16ffda9701eeda6f/rapidocr-3.9.2-py3-none-any.whl", hash = "sha256:04d6b8d151f823d930bd91910555f57bea897c0c44fa6794267b94cf9c1ef9a0", size = 27275208, upload-time = "2026-07-21T10:59:01.599Z" },
 ]
 
 [[package]]

classifyre_cli-0.6.10/.turbo/turbo-build.log

@@ -1,3 +0,0 @@
-$ uv sync
-Resolved 324 packages in 232ms
-Checked 51 packages in 4ms