kreuzberg 3.10.1__py3-none-any.whl → 3.11.0__py3-none-any.whl

kreuzberg/_config.py

@@ -97,19 +97,21 @@ def parse_ocr_backend_config(
     if not isinstance(backend_config, dict):
         return None
 
-    if backend == "tesseract":
-        # Convert psm integer to PSMMode enum if needed
-        processed_config = backend_config.copy()
-        if "psm" in processed_config and isinstance(processed_config["psm"], int):
-            from kreuzberg._ocr._tesseract import PSMMode  # noqa: PLC0415
-
-            processed_config["psm"] = PSMMode(processed_config["psm"])
-        return TesseractConfig(**processed_config)
-    if backend == "easyocr":
-        return EasyOCRConfig(**backend_config)
-    if backend == "paddleocr":
-        return PaddleOCRConfig(**backend_config)
-    return None
+    match backend:
+        case "tesseract":
+            # Convert psm integer to PSMMode enum if needed
+            processed_config = backend_config.copy()
+            if "psm" in processed_config and isinstance(processed_config["psm"], int):
+                from kreuzberg._ocr._tesseract import PSMMode  # noqa: PLC0415
+
+                processed_config["psm"] = PSMMode(processed_config["psm"])
+            return TesseractConfig(**processed_config)
+        case "easyocr":
+            return EasyOCRConfig(**backend_config)
+        case "paddleocr":
+            return PaddleOCRConfig(**backend_config)
+        case _:
+            return None
 
 
 def build_extraction_config_from_dict(config_dict: dict[str, Any]) -> ExtractionConfig:
@@ -140,7 +142,9 @@ def build_extraction_config_from_dict(config_dict: dict[str, Any]) -> Extraction
         "document_classification_mode",
         "keyword_count",
     }
-    extraction_config.update({field: config_dict[field] for field in basic_fields if field in config_dict})
+    extraction_config = extraction_config | {
+        field: config_dict[field] for field in basic_fields if field in config_dict
+    }
 
     # Handle OCR backend configuration
     ocr_backend = extraction_config.get("ocr_backend")

kreuzberg/_document_classification.py

@@ -62,7 +62,7 @@ def _get_translated_text(result: ExtractionResult) -> str:
         from deep_translator import GoogleTranslator  # noqa: PLC0415
     except ImportError as e:  # pragma: no cover
         raise MissingDependencyError(
-            "The 'deep-translator' library is not installed. Please install it with: pip install 'kreuzberg[auto-classify-document-type]'"
+            "The 'deep-translator' library is not installed. Please install it with: pip install 'kreuzberg[document-classification]'"
         ) from e
 
     try:

kreuzberg/_extractors/_base.py

@@ -116,8 +116,7 @@ class Extractor(ABC):
         quality_score = calculate_quality_score(cleaned_content, dict(result.metadata) if result.metadata else None)
 
         # Add quality metadata
-        enhanced_metadata = dict(result.metadata) if result.metadata else {}
-        enhanced_metadata["quality_score"] = quality_score
+        enhanced_metadata = (dict(result.metadata) if result.metadata else {}) | {"quality_score": quality_score}
 
         # Return enhanced result
         return ExtractionResult(

kreuzberg/_extractors/_image.py

@@ -85,23 +85,24 @@ class ImageExtractor(Extractor):
 
         backend = get_ocr_backend(self.config.ocr_backend)
 
-        if self.config.ocr_backend == "tesseract":
-            config = (
-                self.config.ocr_config if isinstance(self.config.ocr_config, TesseractConfig) else TesseractConfig()
-            )
-            result = backend.process_file_sync(path, **asdict(config))
-        elif self.config.ocr_backend == "paddleocr":
-            paddle_config = (
-                self.config.ocr_config if isinstance(self.config.ocr_config, PaddleOCRConfig) else PaddleOCRConfig()
-            )
-            result = backend.process_file_sync(path, **asdict(paddle_config))
-        elif self.config.ocr_backend == "easyocr":
-            easy_config = (
-                self.config.ocr_config if isinstance(self.config.ocr_config, EasyOCRConfig) else EasyOCRConfig()
-            )
-            result = backend.process_file_sync(path, **asdict(easy_config))
-        else:
-            raise NotImplementedError(f"Sync OCR not implemented for {self.config.ocr_backend}")
+        match self.config.ocr_backend:
+            case "tesseract":
+                config = (
+                    self.config.ocr_config if isinstance(self.config.ocr_config, TesseractConfig) else TesseractConfig()
+                )
+                result = backend.process_file_sync(path, **asdict(config))
+            case "paddleocr":
+                paddle_config = (
+                    self.config.ocr_config if isinstance(self.config.ocr_config, PaddleOCRConfig) else PaddleOCRConfig()
+                )
+                result = backend.process_file_sync(path, **asdict(paddle_config))
+            case "easyocr":
+                easy_config = (
+                    self.config.ocr_config if isinstance(self.config.ocr_config, EasyOCRConfig) else EasyOCRConfig()
+                )
+                result = backend.process_file_sync(path, **asdict(easy_config))
+            case _:
+                raise NotImplementedError(f"Sync OCR not implemented for {self.config.ocr_backend}")
         return self._apply_quality_processing(result)
 
     def _get_extension_from_mime_type(self, mime_type: str) -> str:

kreuzberg/_extractors/_pdf.py

@@ -88,14 +88,12 @@ class PDFExtractor(Extractor):
             # Enhance metadata with table information
             if result.tables:
                 table_summary = generate_table_summary(result.tables)
-                result.metadata.update(
-                    {
-                        "table_count": table_summary["table_count"],
-                        "tables_summary": f"Document contains {table_summary['table_count']} tables "
-                        f"across {table_summary['pages_with_tables']} pages with "
-                        f"{table_summary['total_rows']} total rows",
-                    }
-                )
+                result.metadata = result.metadata | {
+                    "table_count": table_summary["table_count"],
+                    "tables_summary": f"Document contains {table_summary['table_count']} tables "
+                    f"across {table_summary['pages_with_tables']} pages with "
+                    f"{table_summary['total_rows']} total rows",
+                }
 
         return self._apply_quality_processing(result)
 
@@ -153,14 +151,12 @@ class PDFExtractor(Extractor):
         # Enhance metadata with table information
         if tables:
             table_summary = generate_table_summary(tables)
-            result.metadata.update(
-                {
-                    "table_count": table_summary["table_count"],
-                    "tables_summary": f"Document contains {table_summary['table_count']} tables "
-                    f"across {table_summary['pages_with_tables']} pages with "
-                    f"{table_summary['total_rows']} total rows",
-                }
-            )
+            result.metadata = result.metadata | {
+                "table_count": table_summary["table_count"],
+                "tables_summary": f"Document contains {table_summary['table_count']} tables "
+                f"across {table_summary['pages_with_tables']} pages with "
+                f"{table_summary['total_rows']} total rows",
+            }
 
         # Apply quality processing
         return self._apply_quality_processing(result)
@@ -386,23 +382,24 @@ class PDFExtractor(Extractor):
         backend = get_ocr_backend(self.config.ocr_backend)
         paths = [Path(p) for p in image_paths]
 
-        if self.config.ocr_backend == "tesseract":
-            config = (
-                self.config.ocr_config if isinstance(self.config.ocr_config, TesseractConfig) else TesseractConfig()
-            )
-            results = backend.process_batch_sync(paths, **asdict(config))
-        elif self.config.ocr_backend == "paddleocr":
-            paddle_config = (
-                self.config.ocr_config if isinstance(self.config.ocr_config, PaddleOCRConfig) else PaddleOCRConfig()
-            )
-            results = backend.process_batch_sync(paths, **asdict(paddle_config))
-        elif self.config.ocr_backend == "easyocr":
-            easy_config = (
-                self.config.ocr_config if isinstance(self.config.ocr_config, EasyOCRConfig) else EasyOCRConfig()
-            )
-            results = backend.process_batch_sync(paths, **asdict(easy_config))
-        else:
-            raise NotImplementedError(f"Sync OCR not implemented for {self.config.ocr_backend}")
+        match self.config.ocr_backend:
+            case "tesseract":
+                config = (
+                    self.config.ocr_config if isinstance(self.config.ocr_config, TesseractConfig) else TesseractConfig()
+                )
+                results = backend.process_batch_sync(paths, **asdict(config))
+            case "paddleocr":
+                paddle_config = (
+                    self.config.ocr_config if isinstance(self.config.ocr_config, PaddleOCRConfig) else PaddleOCRConfig()
+                )
+                results = backend.process_batch_sync(paths, **asdict(paddle_config))
+            case "easyocr":
+                easy_config = (
+                    self.config.ocr_config if isinstance(self.config.ocr_config, EasyOCRConfig) else EasyOCRConfig()
+                )
+                results = backend.process_batch_sync(paths, **asdict(easy_config))
+            case _:
+                raise NotImplementedError(f"Sync OCR not implemented for {self.config.ocr_backend}")
 
         # Use list comprehension and join for efficient string building
         return "\n\n".join(result.content for result in results)

kreuzberg/_mcp/server.py

@@ -51,7 +51,7 @@ def _create_config_with_overrides(**kwargs: Any) -> ExtractionConfig:
     }
 
     # Override with provided parameters
-    config_dict.update(kwargs)
+    config_dict = config_dict | kwargs
 
     return ExtractionConfig(**config_dict)
 

kreuzberg/_types.py

@@ -349,7 +349,7 @@ class ExtractionConfig:
     """Configuration for language detection. If None, uses default settings."""
     spacy_entity_extraction_config: SpacyEntityExtractionConfig | None = None
     """Configuration for spaCy entity extraction. If None, uses default settings."""
-    auto_detect_document_type: bool = True
+    auto_detect_document_type: bool = False
     """Whether to automatically detect the document type."""
     document_type_confidence_threshold: float = 0.5
     """Confidence threshold for document type detection."""
@@ -398,15 +398,16 @@ class ExtractionConfig:
             return asdict(self.ocr_config)
 
         # Lazy load and cache default configs instead of creating new instances
-        if self.ocr_backend == "tesseract":
-            from kreuzberg._ocr._tesseract import TesseractConfig  # noqa: PLC0415
+        match self.ocr_backend:
+            case "tesseract":
+                from kreuzberg._ocr._tesseract import TesseractConfig  # noqa: PLC0415
 
-            return asdict(TesseractConfig())
-        if self.ocr_backend == "easyocr":
-            from kreuzberg._ocr._easyocr import EasyOCRConfig  # noqa: PLC0415
+                return asdict(TesseractConfig())
+            case "easyocr":
+                from kreuzberg._ocr._easyocr import EasyOCRConfig  # noqa: PLC0415
 
-            return asdict(EasyOCRConfig())
-        # paddleocr
-        from kreuzberg._ocr._paddleocr import PaddleOCRConfig  # noqa: PLC0415
+                return asdict(EasyOCRConfig())
+            case _:  # paddleocr or any other backend
+                from kreuzberg._ocr._paddleocr import PaddleOCRConfig  # noqa: PLC0415
 
-        return asdict(PaddleOCRConfig())
+                return asdict(PaddleOCRConfig())

{kreuzberg-3.10.1.dist-info → kreuzberg-3.11.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: kreuzberg
-Version: 3.10.1
+Version: 3.11.0
 Summary: Document intelligence framework for Python - Extract text, metadata, and structured data from diverse file formats
 Project-URL: documentation, https://kreuzberg.dev
 Project-URL: homepage, https://github.com/Goldziher/kreuzberg
@@ -32,7 +32,7 @@ Requires-Dist: anyio>=4.9.0
 Requires-Dist: chardetng-py>=0.3.5
 Requires-Dist: exceptiongroup>=1.2.2; python_version < '3.11'
 Requires-Dist: html-to-markdown[lxml]>=1.9.0
-Requires-Dist: mcp>=1.12.2
+Requires-Dist: mcp>=1.12.3
 Requires-Dist: msgspec>=0.18.0
 Requires-Dist: playa-pdf>=0.6.4
 Requires-Dist: psutil>=7.0.0
@@ -45,6 +45,7 @@ Requires-Dist: mailparse>=1.0.15; extra == 'additional-extensions'
 Requires-Dist: tomli>=2.0.0; (python_version < '3.11') and extra == 'additional-extensions'
 Provides-Extra: all
 Requires-Dist: click>=8.2.1; extra == 'all'
+Requires-Dist: deep-translator>=1.11.4; extra == 'all'
 Requires-Dist: easyocr>=1.7.2; extra == 'all'
 Requires-Dist: fast-langdetect>=0.3.2; extra == 'all'
 Requires-Dist: gmft>=0.4.2; extra == 'all'
@@ -53,6 +54,7 @@ Requires-Dist: litestar[opentelemetry,standard,structlog]>=2.16.0; extra == 'all
 Requires-Dist: mailparse>=1.0.15; extra == 'all'
 Requires-Dist: paddleocr>=3.1.0; extra == 'all'
 Requires-Dist: paddlepaddle>=3.1.0; extra == 'all'
+Requires-Dist: pandas>=2.3.1; extra == 'all'
 Requires-Dist: playa-pdf[crypto]>=0.6.4; extra == 'all'
 Requires-Dist: rich>=14.1.0; extra == 'all'
 Requires-Dist: semantic-text-splitter>=0.27.0; extra == 'all'
@@ -61,9 +63,6 @@ Requires-Dist: spacy>=3.8.7; extra == 'all'
 Requires-Dist: tomli>=2.0.0; (python_version < '3.11') and extra == 'all'
 Provides-Extra: api
 Requires-Dist: litestar[opentelemetry,standard,structlog]>=2.16.0; extra == 'api'
-Provides-Extra: auto-classify-document-type
-Requires-Dist: deep-translator>=1.11.4; extra == 'auto-classify-document-type'
-Requires-Dist: pandas>=2.3.1; extra == 'auto-classify-document-type'
 Provides-Extra: chunking
 Requires-Dist: semantic-text-splitter>=0.27.0; extra == 'chunking'
 Provides-Extra: cli
@@ -72,6 +71,9 @@ Requires-Dist: rich>=14.1.0; extra == 'cli'
 Requires-Dist: tomli>=2.0.0; (python_version < '3.11') and extra == 'cli'
 Provides-Extra: crypto
 Requires-Dist: playa-pdf[crypto]>=0.6.4; extra == 'crypto'
+Provides-Extra: document-classification
+Requires-Dist: deep-translator>=1.11.4; extra == 'document-classification'
+Requires-Dist: pandas>=2.3.1; extra == 'document-classification'
 Provides-Extra: easyocr
 Requires-Dist: easyocr>=1.7.2; extra == 'easyocr'
 Provides-Extra: entity-extraction

{kreuzberg-3.10.1.dist-info → kreuzberg-3.11.0.dist-info}/RECORD

@@ -1,16 +1,16 @@
 kreuzberg/__init__.py,sha256=0OJ_jNKbS6GxzWC5-EfRCiE80as_ya0-wwyNsTYbxzY,1721
 kreuzberg/__main__.py,sha256=s2qM1nPEkRHAQP-G3P7sf5l6qA_KJeIEHS5LpPz04lg,183
 kreuzberg/_chunker.py,sha256=y4-dX6ILjjBkkC1gkCzXb7v7vbi8844m7vz1gIzbmv4,1952
-kreuzberg/_config.py,sha256=Yptj-wFXsQHxIdG7xd_HYA7bqjaRLq-1Os4nPQwJtl8,13947
+kreuzberg/_config.py,sha256=Au521UiR7vcQs_8_hhoWIfmDDMJIrDM3XZUB_qHfCmo,14035
 kreuzberg/_constants.py,sha256=Bxc8oiN-wHwnWXT9bEiJhTUcu1ygPpra5qHirAif3b4,191
-kreuzberg/_document_classification.py,sha256=SErB5Ji6AyEDhgHYPUQr1xcj8FYo0cWOHqb-utRjgJE,6874
+kreuzberg/_document_classification.py,sha256=qFGmwvUMhnNAvNNJO7E-huPx-Ps-_DWxdNxsozIzgaw,6870
 kreuzberg/_entity_extraction.py,sha256=Oa1T-9mptimpOHtcda-GtrVYH9PFy7DSJj3thJZUD7k,7902
 kreuzberg/_gmft.py,sha256=HdQ7Xpuixxl2Y0jY8C3KfyQEU0mN4yQdqErWCv4TnFY,25573
 kreuzberg/_language_detection.py,sha256=_Ng2aHgPxOHFgd507gVNiIGVmnxxbpgYwsO0bD0yTzg,3315
 kreuzberg/_mime_types.py,sha256=2warRVqfBUNIg8JBg8yP4pRqaMPvwINosHMkJwtH_Fc,8488
 kreuzberg/_playa.py,sha256=_IPrUSWwSfDQlWXOpKlauV0D9MhGrujGP5kmQ0U3L0g,12188
 kreuzberg/_registry.py,sha256=wGSlkS0U1zqruWQCLE95vj4a2mw1yyvf0j6rgz80sJg,3473
-kreuzberg/_types.py,sha256=OiB-W_V3zg5rHCfVOr4x39TZJIsd5-sE_SgPZzokW9k,15318
+kreuzberg/_types.py,sha256=bMaU6VuoqwOpW6ufshA-DWpNw6t9EokjEDEfFsznvdo,15389
 kreuzberg/cli.py,sha256=rJMdHg7FhUxefCrx-sf4c2qVGRXr8Xrpjgfx_DQSKMg,12558
 kreuzberg/exceptions.py,sha256=PTiAZgQwcG9hXbgYg2W7sfxksFhq5_wzOFgZGnTJAoc,2991
 kreuzberg/extraction.py,sha256=Kt1mOxdlOb35yVOdpdhiRPuTgA9BW_TTG9qwCkSxSkc,17332
@@ -18,17 +18,17 @@ kreuzberg/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 kreuzberg/_api/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 kreuzberg/_api/main.py,sha256=8VwxRlIXwnPs7ZYm0saUZsNOjevEAWJQpNreG-X7ZpE,3273
 kreuzberg/_extractors/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-kreuzberg/_extractors/_base.py,sha256=yNVQSECFad-8_MjqpQZ4q0jQoNdzP6-tqw6l3TfgsMc,4418
+kreuzberg/_extractors/_base.py,sha256=H_nwynBX3fozncVjV13c329x5eCLl5r7nyVTLQyDAzI,4396
 kreuzberg/_extractors/_email.py,sha256=Jpr4NFef640uVgNFkR1or-omy8RVt-NOHUYgWRDjyBo,6753
 kreuzberg/_extractors/_html.py,sha256=lOM1Tgrrvd7vpEeFAxC1dp0Tibr6N2FEHCjgFx0FK64,1745
-kreuzberg/_extractors/_image.py,sha256=OmkqR5Cd6bTM_qHEdNHeXa5eK-3KvtLgHX-JE5oZWec,4483
+kreuzberg/_extractors/_image.py,sha256=Iz1JpvGqcYyh9g4zO_bMZG3E9S39KNHFu8PrXDRXeOk,4513
 kreuzberg/_extractors/_pandoc.py,sha256=51k7XISfKaPorhapG7aIeQb94KGsfozxKyT2rwhk9Bk,26553
-kreuzberg/_extractors/_pdf.py,sha256=kvbB9Brz7brUpqMZN1G-CRAFgXn5hlWa6eGKXSAe4Xk,19938
+kreuzberg/_extractors/_pdf.py,sha256=OflyvwEkuFLmw8E3si35MCGH31fvd5o50VdMmu5QRVs,19884
 kreuzberg/_extractors/_presentation.py,sha256=CUlqZl_QCdJdumsZh0BpROkFbvi9uq7yMoIt3bRTUeE,10859
 kreuzberg/_extractors/_spread_sheet.py,sha256=iagiyJsnl-89OP1eqmEv8jWl7gZBJm2x0YOyqBgLasA,13733
 kreuzberg/_extractors/_structured.py,sha256=PbNaXd-_PUPsE0yZkISod_vLBokbWdVTKEPpEmqaEMM,5787
 kreuzberg/_mcp/__init__.py,sha256=8PYV-omC8Rln7Cove8C3rHu3d7sR1FuiwSBG1O7vkAE,92
-kreuzberg/_mcp/server.py,sha256=aAnkRDvr-tDIw-G9CAThVmvR3qOQOowcnWE6BLJg2jg,8723
+kreuzberg/_mcp/server.py,sha256=Dxed80MqZsYCFyYo0QdArpKE4H8DhpKY34fijdzV5uw,8731
 kreuzberg/_ocr/__init__.py,sha256=grshVFwVQl2rMvH1hg1JNlYXjy5-Tdb_rusLD1Cselk,706
 kreuzberg/_ocr/_base.py,sha256=IkONqwG6zxZoVMni1JlYugBoyONahlRny7J2_7Dy69c,3953
 kreuzberg/_ocr/_easyocr.py,sha256=dWfoj5fPIGqJPGTVeZ0W59TrW3DpNwF0bcfgt6FwQUw,17238
@@ -47,8 +47,8 @@ kreuzberg/_utils/_string.py,sha256=bCzO3UO6nXupxvtMWvHqfp1Vd9CTzEH9jmpJXQ7upAU,6
 kreuzberg/_utils/_sync.py,sha256=7LSavBmxVKQUzdjfx9fYRAI9IbJtRw8iGf_Q8B7RX9g,4923
 kreuzberg/_utils/_table.py,sha256=IomrfQBP85DZI8RmQjOVs2Siq7VP9FUTYPaZR4t3yRw,8199
 kreuzberg/_utils/_tmp.py,sha256=hVn-VVijIg2FM7EZJ899gc7wZg-TGoJZoeAcxMX-Cxg,1044
-kreuzberg-3.10.1.dist-info/METADATA,sha256=2idgsCPgaT174AZ7HA8yXZEjPLdiLkEH9-e-IMmvFck,12047
-kreuzberg-3.10.1.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-kreuzberg-3.10.1.dist-info/entry_points.txt,sha256=GplGhFryCP7kyAG_k-Mdahznvo2fwi73qLFg5yQfH_A,91
-kreuzberg-3.10.1.dist-info/licenses/LICENSE,sha256=-8caMvpCK8SgZ5LlRKhGCMtYDEXqTKH9X8pFEhl91_4,1066
-kreuzberg-3.10.1.dist-info/RECORD,,
+kreuzberg-3.11.0.dist-info/METADATA,sha256=pvyRM3TAmXE3TnYaNOZ1chD_IQTgWn254wxnqDsy6EM,12135
+kreuzberg-3.11.0.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+kreuzberg-3.11.0.dist-info/entry_points.txt,sha256=GplGhFryCP7kyAG_k-Mdahznvo2fwi73qLFg5yQfH_A,91
+kreuzberg-3.11.0.dist-info/licenses/LICENSE,sha256=-8caMvpCK8SgZ5LlRKhGCMtYDEXqTKH9X8pFEhl91_4,1066
+kreuzberg-3.11.0.dist-info/RECORD,,