code cleanup

requirements.txt

@@ -1,118 +1,20 @@
-aiohappyeyeballs==2.7.1
-aiohttp==3.14.3
-aiosignal==1.4.0
-aistudio_sdk==0.3.9
-annotated-doc==0.0.5
-annotated-types==0.8.0
-anyio==4.14.2
-attrs==26.1.0
-bce-python-sdk==0.9.76
-beautifulsoup4==4.15.0
-cachetools==7.1.7
-certifi==2026.7.22
-chardet==7.4.3
-charset-normalizer==3.4.9
-click==8.4.2
-colorlog==6.12.0
-crc32c==2.8
-cssselect==1.5.0
-cssutils==2.15.0
-diskcache==5.6.3
-distro==1.9.0
-docling==2.117.0
-einops==0.8.2
-encutils==1.0.0
-et_xmlfile==2.0.0
-filelock==3.32.2
-filetype==1.2.0
-frozenlist==1.8.0
-fsspec==2026.7.0
-ftfy==6.3.1
-future==1.0.0
-h11==0.16.0
-hf-xet==1.5.2
-httpcore==1.0.9
-httpx==0.28.1
-huggingface_hub==1.26.0
-idna==3.18
-imagesize==2.0.0
-iniconfig==2.3.0
-Jinja2==3.1.6
-jiter==0.16.0
-joblib==1.5.3
-latex2mathml==3.81.0
-llama_cpp_python==0.3.34
-lxml==6.1.1
-markdown-it-py==4.2.0
-MarkupSafe==3.0.3
-mdurl==0.1.2
-modelscope==1.39.0
-modelscope-hub==0.2.0
-more-itertools==11.1.0
-mpmath==1.3.0
-multidict==6.7.1
-narwhals==2.24.0
-networkx==3.6.1
-numpy==2.3.5
-openai==2.53.0
-opencv-contrib-python==4.10.0.84
-opencv-python-headless==4.11.0.86
-openpyxl==3.1.5
-opt-einsum==3.3.0
-packaging==26.2
-paddleocr==3.7.0
+# Core
+typer>=0.15
+opencv-python-headless>=4.11
+numpy>=1.24,<2.4
+PyYAML>=6.0
+Pillow>=11.0
+requests>=2.32
+beautifulsoup4>=4.12
+
+# OCR engines
+paddlex>=3.2,<3.4
 paddlepaddle==3.2.2
-paddlex==3.7.2
-pandas==3.0.5
-pdftext==0.7.1
-pillow==10.4.0
-platformdirs==4.11.0
-pluggy==1.6.0
-premailer==3.10.0
-prettytable==3.18.0
-propcache==0.5.2
-protobuf==7.35.1
-psutil==7.2.2
-py-cpuinfo==9.0.0
-pyclipper==1.4.0
-pycryptodome==3.23.0
-pydantic==2.13.4
-pydantic-settings==2.14.2
-pydantic_core==2.46.4
-Pygments==2.20.0
-pypdfium2==5.10.1
-pytest==9.1.1
-python-bidi==0.6.11
-python-dateutil==2.9.0.post0
-python-dotenv==1.2.2
-PyYAML==6.0.2
-regex==2026.7.19
-requests==2.34.2
-rich==15.0.0
-ruamel.yaml==0.19.1
-ruff==0.16.1
-safetensors==0.8.0
-scikit-learn==1.9.0
-scipy==1.18.0
-sentencepiece==0.2.2
-setuptools==83.0.0
-shapely==2.1.2
-shellingham==1.5.4
-six==1.17.0
-sniffio==1.3.1
-soupsieve==2.9.1
-surya-ocr==0.22.1
-sympy==1.14.0
-threadpoolctl==3.6.0
-tiktoken==0.13.0
-tokenizers==0.22.2
-torch==2.13.0+cpu
-tqdm==4.70.0
-transformers==5.14.1
-typer==0.27.0
-typing-inspection==0.4.2
-typing_extensions==4.16.0
-ujson==5.13.0
-urllib3==2.7.0
-wcwidth==0.8.2
-yarl==1.24.5
+surya-ocr>=0.12
+
+# LLM corrector (--fix-by-llm)
+llama-cpp-python>=0.3
+
+# Dev
+pytest>=8.0
+ruff>=0.9

src/latex/__init__.py

@@ -1,3 +0,0 @@
-from src.latex.json_to_latex import json_to_html, json_to_latex, multi_json_to_latex
-
-__all__ = ["json_to_html", "json_to_latex", "multi_json_to_latex"]

src/split/slicer.py

@@ -267,20 +267,6 @@ def denoise_image(image: np.ndarray) -> np.ndarray:
     return cv2.fastNlMeansDenoisingColored(image, None, 10, 10, 7, 21)
 
 
-def binarize_image(image: np.ndarray) -> np.ndarray:
-    """Адаптивная бинаризация для неравномерной подсветки."""
-    gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
-    binary = cv2.adaptiveThreshold(gray, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C,
-                                    cv2.THRESH_BINARY, 31, 10)
-    return cv2.cvtColor(binary, cv2.COLOR_GRAY2BGR)
-
-
-def upscale_image(image: np.ndarray, factor: int = 2) -> np.ndarray:
-    """Увеличение для мелкого текста (бикубическая интерполяция)."""
-    h, w = image.shape[:2]
-    return cv2.resize(image, (w * factor, h * factor), interpolation=cv2.INTER_CUBIC)
-
-
 def process_image(
     input_path: Path,
     rows: int | None = None,