kreuzberg 3.9.0__tar.gz → 3.9.1__tar.gz

{kreuzberg-3.9.0 → kreuzberg-3.9.1}/.pre-commit-config.yaml

@@ -53,7 +53,7 @@ repos:
     hooks:
       - id: pyproject-fmt
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.12.3
+    rev: v0.12.5
     hooks:
       - id: ruff
         args: ["--fix", "--unsafe-fixes"]

{kreuzberg-3.9.0 → kreuzberg-3.9.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: kreuzberg
-Version: 3.9.0
+Version: 3.9.1
 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
@@ -29,12 +29,12 @@ 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: chardetng-py>=0.3.5
 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: html-to-markdown[lxml]>=1.9.0
+Requires-Dist: mcp>=1.12.2
 Requires-Dist: msgspec>=0.18.0
-Requires-Dist: playa-pdf>=0.6.1
+Requires-Dist: playa-pdf>=0.6.4
 Requires-Dist: psutil>=7.0.0
 Requires-Dist: pypdfium2==4.30.0
 Requires-Dist: python-calamine>=0.3.2
@@ -53,7 +53,7 @@ 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: rich>=14.0.0; extra == 'all'
+Requires-Dist: rich>=14.1.0; 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'
@@ -67,7 +67,7 @@ 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: rich>=14.1.0; 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'
@@ -130,14 +130,14 @@ Kreuzberg leverages established open source technologies:
 ### Extract Text with CLI
 
 ```bash
-# Extract text from any file to markdown
-uvx kreuzberg extract document.pdf > output.md
+# Extract text from any file to text format
+uvx kreuzberg extract document.pdf > output.txt
 
 # With all features (OCR, table extraction, etc.)
-uvx --from "kreuzberg[all]" kreuzberg extract invoice.pdf --ocr --format markdown
+uvx --from "kreuzberg[all]" kreuzberg extract invoice.pdf --ocr-backend tesseract --output-format text
 
 # Extract with rich metadata
-uvx kreuzberg extract report.pdf --show-metadata --format json
+uvx kreuzberg extract report.pdf --show-metadata --output-format json
 ```
 
 ### Python Usage

{kreuzberg-3.9.0 → kreuzberg-3.9.1}/README.md

@@ -44,14 +44,14 @@ Kreuzberg leverages established open source technologies:
 ### Extract Text with CLI
 
 ```bash
-# Extract text from any file to markdown
-uvx kreuzberg extract document.pdf > output.md
+# Extract text from any file to text format
+uvx kreuzberg extract document.pdf > output.txt
 
 # With all features (OCR, table extraction, etc.)
-uvx --from "kreuzberg[all]" kreuzberg extract invoice.pdf --ocr --format markdown
+uvx --from "kreuzberg[all]" kreuzberg extract invoice.pdf --ocr-backend tesseract --output-format text
 
 # Extract with rich metadata
-uvx kreuzberg extract report.pdf --show-metadata --format json
+uvx kreuzberg extract report.pdf --show-metadata --output-format json
 ```
 
 ### Python Usage

{kreuzberg-3.9.0 → kreuzberg-3.9.1}/pyproject.toml

@@ -5,7 +5,7 @@ requires = [ "hatchling" ]
 
 [project]
 name = "kreuzberg"
-version = "3.9.0"
+version = "3.9.1"
 description = "Document intelligence framework for Python - Extract text, metadata, and structured data from diverse file formats"
 readme = "README.md"
 keywords = [
@@ -58,12 +58,12 @@ classifiers = [
 
 dependencies = [
   "anyio>=4.9.0",
-  "chardetng-py>=0.3.4",
+  "chardetng-py>=0.3.5",
   "exceptiongroup>=1.2.2; python_version<'3.11'",
-  "html-to-markdown[lxml]>=1.8.0",
-  "mcp>=1.11.0",
+  "html-to-markdown[lxml]>=1.9.0",
+  "mcp>=1.12.2",
   "msgspec>=0.18.0",
-  "playa-pdf>=0.6.1",                                 # pinned due to breaking changes in 0.5.0
+  "playa-pdf>=0.6.4",                                 # pinned due to breaking changes in 0.5.0
   "psutil>=7.0.0",
   "pypdfium2==4.30.0",                                # pinned due to bug in 4.30.1, until v5 is stable
   "python-calamine>=0.3.2",
@@ -88,7 +88,7 @@ optional-dependencies.auto-classify-document-type = [
 optional-dependencies.chunking = [ "semantic-text-splitter>=0.27.0" ]
 optional-dependencies.cli = [
   "click>=8.2.1",
-  "rich>=14.0.0",
+  "rich>=14.1.0",
   "tomli>=2.0.0; python_version<'3.11'",
 ]
 optional-dependencies.easyocr = [ "easyocr>=1.7.2" ]
@@ -115,7 +115,7 @@ dev = [
   "pytest-cov>=6.2.1",
   "pytest-mock>=3.14.0",
   "pytest-timeout>=2.4.0",
-  "ruff>=0.12.1",
+  "ruff>=0.12.5",
   "trio>=0.30.0",
   "uv-bump",
 ]
@@ -216,7 +216,13 @@ max_supported_python = "3.13"
 [tool.pytest.ini_options]
 timeout = 300
 testpaths = [ "tests" ]
-norecursedirs = [ "benchmarks", "python-text-extraction-libs-benchmarks", "dist", "build", "*.egg" ]
+norecursedirs = [
+  "benchmarks",
+  "python-text-extraction-libs-benchmarks",
+  "dist",
+  "build",
+  "*.egg",
+]
 filterwarnings = [
   "ignore:Exception ignored in:pytest.PytestUnraisableExceptionWarning",
   "ignore:pkg_resources is deprecated as an API:DeprecationWarning",