kreuzberg 3.20.1__tar.gz → 3.20.2__tar.gz

{kreuzberg-3.20.1 → kreuzberg-3.20.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: kreuzberg
-Version: 3.20.1
+Version: 3.20.2
 Summary: Document intelligence framework for Python - Extract text, metadata, and structured data from diverse file formats
 Keywords: async,document-analysis,document-classification,document-intelligence,document-processing,extensible,information-extraction,mcp,metadata-extraction,model-context-protocol,ocr,pandoc,pdf-extraction,pdfium,plugin-architecture,rag,retrieval-augmented-generation,structured-data,table-extraction,tesseract,text-extraction
 Author: Na'aman Hirschfeld
@@ -28,7 +28,7 @@ Classifier: Typing :: Typed
 Requires-Dist: anyio>=4.11.0
 Requires-Dist: chardetng-py>=0.3.5
 Requires-Dist: exceptiongroup>=1.2.2 ; python_full_version < '3.11'
-Requires-Dist: html-to-markdown>=2.1.0
+Requires-Dist: html-to-markdown>=2.1.2
 Requires-Dist: langcodes>=3.5.0
 Requires-Dist: mcp>=1.17.0
 Requires-Dist: msgspec>=0.18.0

{kreuzberg-3.20.1 → kreuzberg-3.20.2}/kreuzberg/_gmft.py

@@ -193,9 +193,14 @@ async def extract_tables(
                 await run_sync(doc.close)
 
         except ImportError as e:  # pragma: no cover
-            raise MissingDependencyError.create_for_package(
+            error = MissingDependencyError.create_for_package(
                 dependency_group="gmft", functionality="table extraction", package_name="gmft"
-            ) from e
+            )
+            error.context = {
+                "file_path": str(Path(file_path)),
+                "error_message": str(e),
+            }
+            raise error from e
     finally:
         table_cache.mark_complete(**cache_kwargs)
 
@@ -294,9 +299,14 @@ def extract_tables_sync(
             doc.close()  # type: ignore[no-untyped-call]
 
     except ImportError as e:  # pragma: no cover
-        raise MissingDependencyError.create_for_package(
+        error = MissingDependencyError.create_for_package(
             dependency_group="gmft", functionality="table extraction", package_name="gmft"
-        ) from e
+        )
+        error.context = {
+            "file_path": str(Path(file_path)),
+            "error_message": str(e),
+        }
+        raise error from e
 
 
 def _extract_tables_in_process(
@@ -449,6 +459,17 @@ def _extract_tables_isolated(
             return tables
 
         error_info = result
+        if error_info.get("type") == "ImportError":
+            error = MissingDependencyError.create_for_package(
+                dependency_group="gmft", functionality="table extraction", package_name="gmft"
+            )
+            error.context = {
+                "file_path": str(Path(file_path)),
+                "error_message": error_info["error"],
+                "traceback": error_info.get("traceback"),
+            }
+            raise error from ImportError(error_info["error"])
+
         raise ParsingError(
             f"GMFT table extraction failed: {error_info['error']}",
             context={
@@ -536,6 +557,17 @@ async def _extract_tables_isolated_async(
             return tables
 
         error_info = result
+        if error_info.get("type") == "ImportError":
+            error = MissingDependencyError.create_for_package(
+                dependency_group="gmft", functionality="table extraction", package_name="gmft"
+            )
+            error.context = {
+                "file_path": str(Path(file_path)),
+                "error_message": error_info["error"],
+                "traceback": error_info.get("traceback"),
+            }
+            raise error from ImportError(error_info["error"])
+
         raise ParsingError(
             f"GMFT table extraction failed: {error_info['error']}",
             context={

{kreuzberg-3.20.1 → kreuzberg-3.20.2}/kreuzberg/_types.py

@@ -1,6 +1,7 @@
 from __future__ import annotations
 
 import sys
+import warnings
 from collections.abc import Awaitable, Callable, Mapping
 from dataclasses import asdict, dataclass, field
 from enum import Enum
@@ -262,6 +263,15 @@ class PaddleOCRConfig(ConfigDict):
 
 @dataclass(unsafe_hash=True, frozen=True, slots=True)
 class GMFTConfig(ConfigDict):
+    def __post_init__(self) -> None:
+        warnings.warn(
+            "GMFTConfig is deprecated and will be removed in Kreuzberg v4.0. "
+            "Install `kreuzberg[gmft]` only if you still rely on GMFT. "
+            "Future versions use native TATR-based table extraction via TableExtractionConfig.",
+            FutureWarning,
+            stacklevel=2,
+        )
+
     verbosity: int = 0
     """
     Verbosity level for logging.

{kreuzberg-3.20.1 → kreuzberg-3.20.2}/pyproject.toml

@@ -4,7 +4,7 @@ requires = [ "uv-build" ]
 
 [project]
 name = "kreuzberg"
-version = "3.20.1"
+version = "3.20.2"
 description = "Document intelligence framework for Python - Extract text, metadata, and structured data from diverse file formats"
 readme = "README.md"
 keywords = [
@@ -59,7 +59,7 @@ dependencies = [
   "anyio>=4.11.0",
   "chardetng-py>=0.3.5",
   "exceptiongroup>=1.2.2; python_version<'3.11'",
-  "html-to-markdown>=2.1.0",
+  "html-to-markdown>=2.1.2",
   "langcodes>=3.5.0",
   "mcp>=1.17.0",
   "msgspec>=0.18.0",