feat: v1.7

.pre-commit-config.yaml

@@ -21,7 +21,7 @@ repos:
       - id: check-case-conflict
       - id: detect-private-key
   - repo: https://github.com/rbubley/mirrors-prettier
-    rev: "v3.4.2"
+    rev: "v3.5.1"
     hooks:
       - id: prettier
         exclude: ^tests|^.idea|^migrations|^.git
@@ -30,13 +30,13 @@ repos:
     hooks:
       - id: pyproject-fmt
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.9.3
+    rev: v0.9.6
     hooks:
       - id: ruff
         args: [--fix]
       - id: ruff-format
   - repo: https://github.com/codespell-project/codespell
-    rev: v2.4.0
+    rev: v2.4.1
     hooks:
       - id: codespell
         exclude: ^tests|^scripts|^kreuzberg/_tesseract

kreuzberg/_extractors.py

@@ -106,8 +106,8 @@ async def extract_pdf(file_path_or_contents: Path | bytes, force_ocr: bool = Fal
     if isinstance(file_path_or_contents, bytes):
         with NamedTemporaryFile(suffix=".pdf", delete=False) as pdf_file:
             try:
-                pdf_file.write(file_path_or_contents)
                 file_path = Path(pdf_file.name)
+                await AsyncPath(file_path).write_bytes(file_path_or_contents)
 
                 if not force_ocr and (content := await extract_pdf_with_pdfium2(file_path)):
                     return normalize_spaces(content)

kreuzberg/_pandoc.py

@@ -1,9 +1,9 @@
 from __future__ import annotations
 
-import json
 import subprocess
 from asyncio import gather
 from dataclasses import dataclass
+from json import JSONDecodeError, loads
 from tempfile import NamedTemporaryFile
 from typing import TYPE_CHECKING, Any, Final, Literal, TypedDict, cast
 
@@ -344,10 +344,10 @@ async def _handle_extract_metadata(input_file: str | PathLike[str], *, mime_type
                     "Failed to extract file data", context={"file": str(input_file), "error": result.stderr.decode()}
                 )
 
-            json_data = json.loads(await AsyncPath(metadata_file.name).read_text("utf-8"))
+            json_data = loads(await AsyncPath(metadata_file.name).read_text("utf-8"))
             return _extract_metadata(json_data)
 
-        except (RuntimeError, OSError, json.JSONDecodeError) as e:
+        except (RuntimeError, OSError, JSONDecodeError) as e:
             raise ParsingError("Failed to extract file data", context={"file": str(input_file)}) from e
 
         finally:

kreuzberg/extraction.py

@@ -79,7 +79,7 @@ async def extract_bytes(content: bytes, mime_type: str, force_ocr: bool = False)
     if mime_type in IMAGE_MIME_TYPES or any(mime_type.startswith(value) for value in IMAGE_MIME_TYPES):
         with NamedTemporaryFile(suffix=IMAGE_MIME_TYPE_EXT_MAP[mime_type], delete=False) as temp_file:
             try:
-                temp_file.write(content)
+                await AsyncPath(temp_file.name).write_bytes(content)
                 return ExtractionResult(
                     content=await process_image_with_tesseract(temp_file.name), mime_type=PLAIN_TEXT_MIME_TYPE
                 )

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "kreuzberg"
-version = "1.6.0"
+version = "1.7.0"
 description = "A text extraction library supporting PDFs, images, office documents and more"
 readme = "README.md"
 keywords = [
@@ -36,28 +36,28 @@ classifiers = [
 ]
 
 dependencies = [
-  "anyio>=4.8.0",
-  "charset-normalizer>=3.4.1",
-  "html-to-markdown>=1.2.0",
-  "pypdfium2>=4.30.1",
-  "python-pptx>=1.0.2",
-  "typing-extensions>=4.12.2; python_version<'3.10'",
-  "xlsx2csv>=0.8.4",
+    "anyio>=4.8.0",
+    "charset-normalizer>=3.4.1",
+    "html-to-markdown>=1.2.0",
+    "pypdfium2>=4.30.1",
+    "python-pptx>=1.0.2",
+    "typing-extensions>=4.12.2",
+    "xlsx2csv>=0.8.4",
 ]
 urls.homepage = "https://github.com/Goldziher/kreuzberg"
 
 [dependency-groups]
 dev = [
-  "covdefaults>=2.3.0",
-  "mypy>=1.15.0",
-  "pre-commit>=4.1.0",
-  "pytest>=8.3.4",
-  "pytest-asyncio>=0.25.3",
-  "pytest-cov>=6.0.0",
-  "pytest-mock>=3.14.0",
-  "pytest-timeout>=2.3.1",
-  "python-dotenv>=1.0.1",
-  "ruff>=0.9.5",
+    "covdefaults>=2.3.0",
+    "mypy>=1.15.0",
+    "pre-commit>=4.1.0",
+    "pytest>=8.3.4",
+    "pytest-asyncio>=0.25.3",
+    "pytest-cov>=6.0.0",
+    "pytest-mock>=3.14.0",
+    "pytest-timeout>=2.3.1",
+    "python-dotenv>=1.0.1",
+    "ruff>=0.9.6",
 ]
 
 [tool.setuptools.packages.find]