kreuzberg 3.8.1__py3-none-any.whl → 3.8.2__py3-none-any.whl

kreuzberg/_utils/_quality.py

@@ -3,6 +3,7 @@
 from __future__ import annotations
 
 import re
+from functools import reduce
 from typing import Any
 
 # Pre-compiled patterns for performance
@@ -102,9 +103,8 @@ def clean_extracted_text(text: str) -> str:
     if not text:
         return text
 
-    # Remove script and style content
-    for pattern in _SCRIPT_PATTERNS.values():
-        text = pattern.sub(" ", text)
+    # Remove script and style content using functools.reduce for single pass
+    text = reduce(lambda t, pattern: pattern.sub(" ", t), _SCRIPT_PATTERNS.values(), text)
 
     # Clean OCR artifacts
     text = _clean_ocr_artifacts(text)
@@ -134,10 +134,8 @@ def _calculate_script_penalty(text: str, total_chars: int) -> float:
     if total_chars == 0:
         return 0.0
 
-    script_chars = 0
-    for pattern in _SCRIPT_PATTERNS.values():
-        matches = pattern.findall(text)
-        script_chars += sum(len(match) for match in matches)
+    # Use sum with generator expression for single-pass calculation
+    script_chars = sum(len(match) for pattern in _SCRIPT_PATTERNS.values() for match in pattern.findall(text))
 
     return min(1.0, script_chars / total_chars)
 
@@ -147,10 +145,8 @@ def _calculate_navigation_penalty(text: str, total_chars: int) -> float:
     if total_chars == 0:
         return 0.0
 
-    nav_chars = 0
-    for pattern in _NAVIGATION_PATTERNS.values():
-        matches = pattern.findall(text)
-        nav_chars += sum(len(match) for match in matches)
+    # Use sum with generator expression for single-pass calculation
+    nav_chars = sum(len(match) for pattern in _NAVIGATION_PATTERNS.values() for match in pattern.findall(text))
 
     return min(1.0, nav_chars / total_chars)
 

kreuzberg/_utils/_serialization.py

@@ -2,16 +2,28 @@
 
 from __future__ import annotations
 
-from dataclasses import asdict, is_dataclass
-from enum import Enum
+from dataclasses import is_dataclass
 from typing import Any, TypeVar, cast
 
+import msgspec
 from msgspec import MsgspecError
 from msgspec.msgpack import decode, encode
 
 T = TypeVar("T")
 
 
+# Define dict method names in priority order
+_DICT_METHOD_NAMES = (
+    "to_dict",
+    "as_dict",
+    "dict",
+    "model_dump",
+    "json",
+    "to_list",
+    "tolist",
+)
+
+
 def encode_hook(obj: Any) -> Any:
     """Custom encoder for complex objects."""
     if callable(obj):
@@ -20,22 +32,15 @@ def encode_hook(obj: Any) -> Any:
     if isinstance(obj, Exception):
         return {"message": str(obj), "type": type(obj).__name__}
 
-    for key in (
-        "to_dict",
-        "as_dict",
-        "dict",
-        "model_dump",
-        "json",
-        "to_list",
-        "tolist",
-    ):
-        if hasattr(obj, key):
-            method = getattr(obj, key)  # Cache the attribute lookup
-            if callable(method):
-                return method()
+    # Check for dict-like methods more efficiently using any() with generator
+    for attr_name in _DICT_METHOD_NAMES:
+        method = getattr(obj, attr_name, None)
+        if method is not None and callable(method):
+            return method()
 
     if is_dataclass(obj) and not isinstance(obj, type):
-        return {k: v if not isinstance(v, Enum) else v.value for (k, v) in asdict(obj).items()}
+        # Use msgspec.to_builtins for more efficient conversion
+        return msgspec.to_builtins(obj)
 
     if hasattr(obj, "save") and hasattr(obj, "format"):
         return None

kreuzberg/_utils/_string.py

@@ -28,6 +28,7 @@ _encoding_cache: dict[str, str] = {}
 @lru_cache(maxsize=128)
 def _get_encoding_cache_key(data_hash: str, size: int) -> str:
     """Generate cache key for encoding detection."""
+    # Use string interpolation which is faster than format strings for simple cases
     return f"{data_hash}:{size}"
 
 
@@ -104,25 +105,29 @@ def _calculate_text_confidence(text: str) -> float:
     if not text:
         return 0.0
 
-    # Check for common encoding problems
-    replacement_count = len(_MOJIBAKE_PATTERNS["replacement_chars"].findall(text))
-    control_count = len(_MOJIBAKE_PATTERNS["control_chars"].findall(text))
     total_chars = len(text)
-
     if total_chars == 0:
         return 0.0
 
+    # Check for common encoding problems - compile patterns once
+    replacement_count = len(_MOJIBAKE_PATTERNS["replacement_chars"].findall(text))
+    control_count = len(_MOJIBAKE_PATTERNS["control_chars"].findall(text))
+
     # Penalize replacement and control characters
     penalty = (replacement_count + control_count * 2) / total_chars
 
-    # Bonus for readable character ranges
+    # Bonus for readable character ranges - more efficient counting
+    # Use generator expression with early termination
     readable_chars = sum(1 for c in text if c.isprintable() or c.isspace())
     readability_score = readable_chars / total_chars
 
     # Check for suspicious Cyrillic that might be misencoded Hebrew
     cyrillic_matches = _MOJIBAKE_PATTERNS["hebrew_as_cyrillic"].findall(text)
-    if cyrillic_matches and len("".join(cyrillic_matches)) > total_chars * 0.1:
-        penalty += 0.3  # Heavy penalty for likely mojibake
+    if cyrillic_matches:
+        # Calculate total length more efficiently
+        cyrillic_length = sum(len(match) for match in cyrillic_matches)
+        if cyrillic_length > total_chars * 0.1:
+            penalty += 0.3  # Heavy penalty for likely mojibake
 
     return max(0.0, min(1.0, readability_score - penalty))
 
@@ -164,7 +169,8 @@ def normalize_spaces(text: str) -> str:
 
     # Split by double newlines to preserve paragraph breaks
     paragraphs = text.split("\n\n")
-    normalized_paragraphs = []
+
+    result_paragraphs = []
 
     for paragraph in paragraphs:
         # Use pre-compiled patterns for better performance
@@ -173,10 +179,14 @@ def normalize_spaces(text: str) -> str:
         # Clean up multiple newlines within paragraph (keep single newlines)
         cleaned = _NEWLINES_PATTERN.sub("\n", cleaned)
 
-        # Strip and filter empty lines efficiently
-        lines = [line.strip() for line in cleaned.split("\n") if line.strip()]
+        # Process lines efficiently - manual loop avoids double strip() calls
+        lines = []
+        for line in cleaned.split("\n"):
+            stripped_line = line.strip()
+            if stripped_line:
+                lines.append(stripped_line)
 
         if lines:
-            normalized_paragraphs.append("\n".join(lines))
+            result_paragraphs.append("\n".join(lines))
 
-    return "\n\n".join(normalized_paragraphs)
+    return "\n\n".join(result_paragraphs)

kreuzberg/_utils/_table.py

@@ -3,7 +3,6 @@
 from __future__ import annotations
 
 import csv
-from io import StringIO
 from typing import TYPE_CHECKING, Any
 
 if TYPE_CHECKING:
@@ -23,9 +22,9 @@ def export_table_to_csv(table: TableData, separator: str = ",") -> str:
     if "df" not in table or table["df"] is None:
         return ""
 
-    output = StringIO()
-    table["df"].to_csv(output, sep=separator, index=False, quoting=csv.QUOTE_MINIMAL)
-    return output.getvalue().strip()
+    # Use pandas to_csv() direct string return instead of StringIO
+    csv_output = table["df"].to_csv(sep=separator, index=False, quoting=csv.QUOTE_MINIMAL, lineterminator="\n")
+    return str(csv_output).strip()
 
 
 def export_table_to_tsv(table: TableData) -> str:

kreuzberg/cli.py

@@ -18,7 +18,7 @@ except ImportError as e:
     ) from e
 
 from kreuzberg import __version__, extract_bytes_sync, extract_file_sync
-from kreuzberg._cli_config import build_extraction_config, find_default_config, load_config_from_file
+from kreuzberg._config import build_extraction_config, find_config_file, load_config_from_file
 from kreuzberg.exceptions import KreuzbergError, MissingDependencyError
 
 DEFAULT_MAX_CHARACTERS = 4000
@@ -92,7 +92,7 @@ def _load_config(config: Path | None, verbose: bool) -> dict[str, Any]:
     if config:
         file_config = load_config_from_file(config)
     else:
-        default_config = find_default_config()
+        default_config = find_config_file()
         if default_config:
             try:
                 file_config = load_config_from_file(default_config)
@@ -314,7 +314,7 @@ def extract(  # noqa: PLR0913
 def config(config: Path | None) -> None:
     """Show current configuration."""
     try:
-        config_path = config or find_default_config()
+        config_path = config or find_config_file()
 
         if config_path:
             file_config = load_config_from_file(config_path)

kreuzberg/exceptions.py

@@ -7,6 +7,8 @@ from typing import Any
 class KreuzbergError(Exception):
     """Base exception for all Kreuzberg errors."""
 
+    __slots__ = ("context",)
+
     context: Any
     """The context of the error."""
 
@@ -43,14 +45,20 @@ class KreuzbergError(Exception):
 class ParsingError(KreuzbergError):
     """Raised when a parsing error occurs."""
 
+    __slots__ = ()
+
 
 class ValidationError(KreuzbergError):
     """Raised when a validation error occurs."""
 
+    __slots__ = ()
+
 
 class MissingDependencyError(KreuzbergError):
     """Raised when a dependency is missing."""
 
+    __slots__ = ()
+
     @classmethod
     def create_for_package(
         cls, *, dependency_group: str, functionality: str, package_name: str
@@ -79,3 +87,5 @@ class MissingDependencyError(KreuzbergError):
 
 class OCRError(KreuzbergError):
     """Raised when an OCR error occurs."""
+
+    __slots__ = ()

kreuzberg/extraction.py

@@ -460,8 +460,8 @@ def batch_extract_bytes_sync(
             return (index, error_result)
 
     with ThreadPoolExecutor(max_workers=max_workers) as executor:
-        indexed_contents = list(enumerate(contents))
-        future_to_index = {executor.submit(extract_single, ic): i for i, ic in enumerate(indexed_contents)}
+        # Avoid creating intermediate list, use enumerate directly
+        future_to_index = {executor.submit(extract_single, (i, content)): i for i, content in enumerate(contents)}
 
         results: list[ExtractionResult] = [None] * len(contents)  # type: ignore[list-item]
         for future in as_completed(future_to_index):

kreuzberg-3.8.2.dist-info/METADATA

@@ -0,0 +1,265 @@
+Metadata-Version: 2.4
+Name: kreuzberg
+Version: 3.8.2
+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
+Author-email: Na'aman Hirschfeld <nhirschfed@gmail.com>
+License: MIT
+License-File: LICENSE
+Keywords: async,document-analysis,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
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Information Technology
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Database
+Classifier: Topic :: Multimedia :: Graphics :: Capture :: Scanners
+Classifier: Topic :: Office/Business :: Office Suites
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: Scientific/Engineering :: Information Analysis
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Classifier: Topic :: Text Processing :: General
+Classifier: Typing :: Typed
+Requires-Python: >=3.10
+Requires-Dist: anyio>=4.9.0
+Requires-Dist: chardetng-py>=0.3.4
+Requires-Dist: exceptiongroup>=1.2.2; python_version < '3.11'
+Requires-Dist: html-to-markdown[lxml]>=1.8.0
+Requires-Dist: mcp>=1.11.0
+Requires-Dist: msgspec>=0.18.0
+Requires-Dist: playa-pdf>=0.6.1
+Requires-Dist: psutil>=7.0.0
+Requires-Dist: pypdfium2==4.30.0
+Requires-Dist: python-calamine>=0.3.2
+Requires-Dist: python-pptx>=1.0.2
+Requires-Dist: typing-extensions>=4.14.0; python_version < '3.12'
+Provides-Extra: additional-extensions
+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: easyocr>=1.7.2; extra == 'all'
+Requires-Dist: fast-langdetect>=0.3.2; extra == 'all'
+Requires-Dist: gmft>=0.4.2; extra == 'all'
+Requires-Dist: keybert>=0.9.0; extra == 'all'
+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: rich>=14.0.0; extra == 'all'
+Requires-Dist: semantic-text-splitter>=0.27.0; extra == 'all'
+Requires-Dist: setuptools>=80.9.0; extra == 'all'
+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: chunking
+Requires-Dist: semantic-text-splitter>=0.27.0; extra == 'chunking'
+Provides-Extra: cli
+Requires-Dist: click>=8.2.1; extra == 'cli'
+Requires-Dist: rich>=14.0.0; extra == 'cli'
+Requires-Dist: tomli>=2.0.0; (python_version < '3.11') and extra == 'cli'
+Provides-Extra: easyocr
+Requires-Dist: easyocr>=1.7.2; extra == 'easyocr'
+Provides-Extra: entity-extraction
+Requires-Dist: keybert>=0.9.0; extra == 'entity-extraction'
+Requires-Dist: spacy>=3.8.7; extra == 'entity-extraction'
+Provides-Extra: gmft
+Requires-Dist: gmft>=0.4.2; extra == 'gmft'
+Provides-Extra: langdetect
+Requires-Dist: fast-langdetect>=0.3.2; extra == 'langdetect'
+Provides-Extra: paddleocr
+Requires-Dist: paddleocr>=3.1.0; extra == 'paddleocr'
+Requires-Dist: paddlepaddle>=3.1.0; extra == 'paddleocr'
+Requires-Dist: setuptools>=80.9.0; extra == 'paddleocr'
+Description-Content-Type: text/markdown
+
+# Kreuzberg
+
+[![Discord](https://img.shields.io/badge/Discord-Join%20our%20community-7289da)](https://discord.gg/pXxagNK2zN)
+[![PyPI version](https://badge.fury.io/py/kreuzberg.svg)](https://badge.fury.io/py/kreuzberg)
+[![Documentation](https://img.shields.io/badge/docs-kreuzberg.dev-blue)](https://kreuzberg.dev/)
+[![Benchmarks](https://img.shields.io/badge/benchmarks-fastest%20CPU-orange)](https://benchmarks.kreuzberg.dev/)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
+[![Test Coverage](https://img.shields.io/badge/coverage-95%25-green)](https://github.com/Goldziher/kreuzberg)
+
+**A document intelligence framework for Python.** Extract text, metadata, and structured information from diverse document formats through a unified, extensible API. Built on established open source foundations including Pandoc, PDFium, and Tesseract.
+
+📖 **[Complete Documentation](https://kreuzberg.dev/)**
+
+## Framework Overview
+
+### Document Intelligence Capabilities
+
+- **Text Extraction**: High-fidelity text extraction preserving document structure and formatting
+- **Metadata Extraction**: Comprehensive metadata including author, creation date, language, and document properties
+- **Format Support**: 18 document types including PDF, Microsoft Office, images, HTML, and structured data formats
+- **OCR Integration**: Multiple OCR engines (Tesseract, EasyOCR, PaddleOCR) with automatic fallback
+- **Table Detection**: Structured table extraction with cell-level precision via GMFT integration
+
+### Technical Architecture
+
+- **Performance**: Highest throughput among Python document processing frameworks (30+ docs/second)
+- **Resource Efficiency**: 71MB installation, ~360MB runtime memory footprint
+- **Extensibility**: Plugin architecture for custom extractors via the Extractor base class
+- **API Design**: Synchronous and asynchronous APIs with consistent interfaces
+- **Type Safety**: Complete type annotations throughout the codebase
+
+### Open Source Foundation
+
+Kreuzberg leverages established open source technologies:
+
+- **Pandoc**: Universal document converter for robust format support
+- **PDFium**: Google's PDF rendering engine for accurate PDF processing
+- **Tesseract**: Google's OCR engine for text recognition
+- **Python-docx/pptx**: Native Microsoft Office format support
+
+## Quick Start
+
+### Extract Text with CLI
+
+```bash
+# Extract text from any file to markdown
+uvx kreuzberg extract document.pdf > output.md
+
+# With all features (OCR, table extraction, etc.)
+uvx --from "kreuzberg[all]" kreuzberg extract invoice.pdf --ocr --format markdown
+
+# Extract with rich metadata
+uvx kreuzberg extract report.pdf --show-metadata --format json
+```
+
+### Python Usage
+
+**Async (recommended for web apps):**
+
+```python
+from kreuzberg import extract_file
+
+# In your async function
+result = await extract_file("presentation.pptx")
+print(result.content)
+
+# Rich metadata extraction
+print(f"Title: {result.metadata.title}")
+print(f"Author: {result.metadata.author}")
+print(f"Page count: {result.metadata.page_count}")
+print(f"Created: {result.metadata.created_at}")
+```
+
+**Sync (for scripts and CLI tools):**
+
+```python
+from kreuzberg import extract_file_sync
+
+result = extract_file_sync("report.docx")
+print(result.content)
+
+# Access rich metadata
+print(f"Language: {result.metadata.language}")
+print(f"Word count: {result.metadata.word_count}")
+print(f"Keywords: {result.metadata.keywords}")
+```
+
+### Docker
+
+```bash
+# Run the REST API
+docker run -p 8000:8000 goldziher/kreuzberg
+
+# Extract via API
+curl -X POST -F "file=@document.pdf" http://localhost:8000/extract
+```
+
+📖 **[Installation Guide](https://kreuzberg.dev/getting-started/installation/)** • **[CLI Documentation](https://kreuzberg.dev/cli/)** • **[API Reference](https://kreuzberg.dev/api-reference/)**
+
+## Deployment Options
+
+### 🤖 MCP Server (AI Integration)
+
+**Add to Claude Desktop with one command:**
+
+```bash
+claude mcp add kreuzberg uvx -- --from "kreuzberg[all]" kreuzberg-mcp
+```
+
+**Or configure manually in `claude_desktop_config.json`:**
+
+```json
+{
+  "mcpServers": {
+    "kreuzberg": {
+      "command": "uvx",
+      "args": ["--from", "kreuzberg[all]", "kreuzberg-mcp"]
+    }
+  }
+}
+```
+
+**MCP capabilities:**
+
+- Extract text from PDFs, images, Office docs, and more
+- Full OCR support with multiple engines
+- Table extraction and metadata parsing
+
+📖 **[MCP Documentation](https://kreuzberg.dev/user-guide/mcp-server/)**
+
+## Supported Formats
+
+| Category          | Formats                        |
+| ----------------- | ------------------------------ |
+| **Documents**     | PDF, DOCX, DOC, RTF, TXT, EPUB |
+| **Images**        | JPG, PNG, TIFF, BMP, GIF, WEBP |
+| **Spreadsheets**  | XLSX, XLS, CSV, ODS            |
+| **Presentations** | PPTX, PPT, ODP                 |
+| **Web**           | HTML, XML, MHTML               |
+| **Archives**      | Support via extraction         |
+
+## 📊 Performance Characteristics
+
+[View comprehensive benchmarks](https://benchmarks.kreuzberg.dev/) • [Benchmark methodology](https://github.com/Goldziher/python-text-extraction-libs-benchmarks) • [**Detailed Analysis**](https://kreuzberg.dev/performance-analysis/)
+
+### Technical Specifications
+
+| Metric                       | Kreuzberg Sync | Kreuzberg Async | Benchmarked        |
+| ---------------------------- | -------------- | --------------- | ------------------ |
+| **Throughput (tiny files)**  | 31.78 files/s  | 23.94 files/s   | Highest throughput |
+| **Throughput (small files)** | 8.91 files/s   | 9.31 files/s    | Highest throughput |
+| **Memory footprint**         | 359.8 MB       | 395.2 MB        | Lowest usage       |
+| **Installation size**        | 71 MB          | 71 MB           | Smallest size      |
+| **Success rate**             | 100%           | 100%            | Perfect            |
+| **Supported formats**        | 18             | 18              | Comprehensive      |
+
+### Architecture Advantages
+
+- **Native C extensions**: Built on PDFium and Tesseract for maximum performance
+- **Async/await support**: True asynchronous processing with intelligent task scheduling
+- **Memory efficiency**: Streaming architecture minimizes memory allocation
+- **Process pooling**: Automatic multiprocessing for CPU-intensive operations
+- **Optimized data flow**: Efficient data handling with minimal transformations
+
+> **Benchmark details**: Tests include PDFs, Word docs, HTML, images, and spreadsheets in multiple languages (English, Hebrew, German, Chinese, Japanese, Korean) on standardized hardware.
+
+## Documentation
+
+### Quick Links
+
+- [Installation Guide](https://kreuzberg.dev/getting-started/installation/) - Setup and dependencies
+- [User Guide](https://kreuzberg.dev/user-guide/) - Comprehensive usage guide
+- [Performance Analysis](https://kreuzberg.dev/performance-analysis/) - Detailed benchmark results
+- [API Reference](https://kreuzberg.dev/api-reference/) - Complete API documentation
+- [Docker Guide](https://kreuzberg.dev/user-guide/docker/) - Container deployment
+- [REST API](https://kreuzberg.dev/user-guide/api-server/) - HTTP endpoints
+- [CLI Guide](https://kreuzberg.dev/cli/) - Command-line usage
+- [OCR Configuration](https://kreuzberg.dev/user-guide/ocr-configuration/) - OCR engine setup
+
+## License
+
+MIT License - see [LICENSE](LICENSE) for details.

kreuzberg-3.8.2.dist-info/RECORD

@@ -0,0 +1,53 @@
+kreuzberg/__init__.py,sha256=0OJ_jNKbS6GxzWC5-EfRCiE80as_ya0-wwyNsTYbxzY,1721
+kreuzberg/__main__.py,sha256=s2qM1nPEkRHAQP-G3P7sf5l6qA_KJeIEHS5LpPz04lg,183
+kreuzberg/_chunker.py,sha256=2eHSRHcZdJ2ZjR3in49y3o9tPl5HMO3vkbnMqaVCbHI,1887
+kreuzberg/_config.py,sha256=_9JU88ChId8dWUjZ13ueo9_JoFekkyzuv7rZpFkrPZk,12966
+kreuzberg/_constants.py,sha256=Bxc8oiN-wHwnWXT9bEiJhTUcu1ygPpra5qHirAif3b4,191
+kreuzberg/_entity_extraction.py,sha256=woNxARG27Z3T_l6w6N-dbt1PPe1IHptFMOZY_6etv54,7819
+kreuzberg/_gmft.py,sha256=Q46CyBxRxY_oDGpSuXMOJ7qfR9LwuCKXnrl60wcPvU4,25286
+kreuzberg/_language_detection.py,sha256=eEfj4tsh91SfB2_zQIdY-qD7TlPcppaFm0SqQmETS6Y,3295
+kreuzberg/_mime_types.py,sha256=OhJ6gEyyLHjyvRtkk37zyLFBsRcSd_QybBaV8TxinIg,8471
+kreuzberg/_playa.py,sha256=9z4If0WHxbYQxfb8xT7T96L9Du2Fj3Ar5-rF0OHHiMM,11877
+kreuzberg/_registry.py,sha256=wGSlkS0U1zqruWQCLE95vj4a2mw1yyvf0j6rgz80sJg,3473
+kreuzberg/_types.py,sha256=GisvL0ps2LCc0heKopFwSyrEbzH3WpDxaeev4vn59X4,14257
+kreuzberg/cli.py,sha256=vTGS2TJlFTNMWp5LwZd3G2SS8u0m6bhQkH9n6a1oOoM,12439
+kreuzberg/exceptions.py,sha256=PTiAZgQwcG9hXbgYg2W7sfxksFhq5_wzOFgZGnTJAoc,2991
+kreuzberg/extraction.py,sha256=UmeEVN-eSile4HMxP0iqG9092BrsH5_zSZNVHhwy0ko,16993
+kreuzberg/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+kreuzberg/_api/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+kreuzberg/_api/main.py,sha256=g3kqXUfSie2pcw3-EWOM4TAoJUqM7yj2e-cBQJ_bmYc,3253
+kreuzberg/_extractors/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+kreuzberg/_extractors/_base.py,sha256=yNVQSECFad-8_MjqpQZ4q0jQoNdzP6-tqw6l3TfgsMc,4418
+kreuzberg/_extractors/_email.py,sha256=6-Mk1TRXPyy9ylWKCpgdrogyzhiFnJOTuTRld1ghO8I,5695
+kreuzberg/_extractors/_html.py,sha256=lOM1Tgrrvd7vpEeFAxC1dp0Tibr6N2FEHCjgFx0FK64,1745
+kreuzberg/_extractors/_image.py,sha256=eZ7mR4F-mTwYwUzd70xrY7SZYZrNiDxnP5bYDY5P75U,4455
+kreuzberg/_extractors/_pandoc.py,sha256=51k7XISfKaPorhapG7aIeQb94KGsfozxKyT2rwhk9Bk,26553
+kreuzberg/_extractors/_pdf.py,sha256=d-hG_mhAMj22bQ35YuP2nq017z27_2Pp08r1qyHxlYI,16676
+kreuzberg/_extractors/_presentation.py,sha256=CUlqZl_QCdJdumsZh0BpROkFbvi9uq7yMoIt3bRTUeE,10859
+kreuzberg/_extractors/_spread_sheet.py,sha256=vPxEDAyH-gDoVXSg-A0guOjOfaWIuRI3i2NU8xPwhK8,13695
+kreuzberg/_extractors/_structured.py,sha256=d0x6EyRimr8eWmr1qPb7HRWnrbKBuD-GpIrZd8XJp0o,5824
+kreuzberg/_mcp/__init__.py,sha256=8PYV-omC8Rln7Cove8C3rHu3d7sR1FuiwSBG1O7vkAE,92
+kreuzberg/_mcp/server.py,sha256=Ab0w7kR3m7_L1cfhYHiC8HqDL282vt4uBYwYc9w9E08,8703
+kreuzberg/_ocr/__init__.py,sha256=grshVFwVQl2rMvH1hg1JNlYXjy5-Tdb_rusLD1Cselk,706
+kreuzberg/_ocr/_base.py,sha256=CUzYMsJjCqCmHzWckmDeIB2L5hd261xrPrK8Ql-Gdm0,3876
+kreuzberg/_ocr/_easyocr.py,sha256=c2ndpDlIHvAI2WyvQUXLQ1hb6XynKeKARsXQcQ3ntJ0,17110
+kreuzberg/_ocr/_paddleocr.py,sha256=fab8a-3cvDgnt97qF-Km9ZfmkacFeKD_g15O8HXYRVc,17492
+kreuzberg/_ocr/_tesseract.py,sha256=r1g_PCAXgJbZ0RPGn4aSxctZ0F9lLvI3zLGLEPAnviI,31455
+kreuzberg/_utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+kreuzberg/_utils/_cache.py,sha256=H2d6JOiTTAoJx5HPJoToCk4ik-ztTRNEJRrHgcSUTLs,15249
+kreuzberg/_utils/_device.py,sha256=PC8YUPE95pzOyU7sU_icqNZpSfi6HZlEFfmWcV1Uees,10226
+kreuzberg/_utils/_document_cache.py,sha256=z8irioKsOu8xve1YgHatm__wIFvs9I1gDK3tLNsNyqM,6926
+kreuzberg/_utils/_errors.py,sha256=UsktQ_p7eOj9crPsFDg8HgRSE5-IpuFC7y1e6dDI_fY,6503
+kreuzberg/_utils/_pdf_lock.py,sha256=nqxAYCNlfWDrJtP4ZNu57st1YnkDl-gYXdr0q8nv0kA,1961
+kreuzberg/_utils/_process_pool.py,sha256=4BqhmRspwMyPT2EBfTu_rrn7v722wlMLD8qlYvYsc00,8621
+kreuzberg/_utils/_quality.py,sha256=-nKzj5n7yJDYrvl556oq2T5S5oKMEOrjpcRMlZ00Jqo,7668
+kreuzberg/_utils/_serialization.py,sha256=cqqxqN2cmtndBhIr4v2wqiMwnNadnKhvuN7EUj3i18M,2290
+kreuzberg/_utils/_string.py,sha256=bCzO3UO6nXupxvtMWvHqfp1Vd9CTzEH9jmpJXQ7upAU,6800
+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-3.8.2.dist-info/METADATA,sha256=RiP64og5wOaf9gPZ7CwOsNYYx9GBnVMg8orgqZdncKA,11466
+kreuzberg-3.8.2.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+kreuzberg-3.8.2.dist-info/entry_points.txt,sha256=GplGhFryCP7kyAG_k-Mdahznvo2fwi73qLFg5yQfH_A,91
+kreuzberg-3.8.2.dist-info/licenses/LICENSE,sha256=-8caMvpCK8SgZ5LlRKhGCMtYDEXqTKH9X8pFEhl91_4,1066
+kreuzberg-3.8.2.dist-info/RECORD,,