GitLab

- Comment out the line that updates det_count in batch_analyze.py
- Add a new OCR model configuration for Chinese (ch_lite) in models_config.yml- Update the Chinese OCR model configuration to use a different recognition model

- Change `bits` to `self._data_bits` for language detection
- This fixes the TypeError when opening PDF files

- Simplify aspect ratio calculation using direct coordinate subtraction
- Remove unnecessary list append operation
- Improve code readability and performance in table rotation detection

- Implement table orientation detection to identify if a table is in portrait mode
- Add rotation logic to turn portrait tables 90 degrees clockwise before OCR
- Update OCR processing to work with potentially rotated images
- Improve text box analysis to determine if a table is rotated

- Update predict_rec.py to check for NaN values in recognition results
- Replace NaN scores with 0.0 to ensure stability and consistency

fix: support page range

feat(model): improve table recognition by merging and filtering tables

- Add functions to calculate IoU, check if tables are inside each other, and merge tables
- Implement table merging for high IoU tables
- Add filtering to remove nested tables that don't overlap but cover a large area
- Update table_res_list and layout_res to reflect these changes

docs: update version number in README files

- Correct version number from 1.3.2 to 1.3.1 in both README.md and README_zh-CN.md
- Update changelog entries for the latest release

Dev

docs(README): update version number and changelog in README files

- Update version number from 1.3.1 to 1.3.2

refactor(ocr): improve OCR score precision to three decimal places

- Update OCR score formatting in batch_analyze.py and pdf_parse_union_core_v2.py
- Change score rounding method to preserve three decimal places
- Enhance accuracy representation without significantly altering the score value

- Update version from1.3.1 to 1.3.2 in both English and Chinese README files
- Keep other content unchanged

Release 1.3.1

Dev

docs: update badges and project URLs- Update PyPI version badge to us…

- Add project URLs in setup.py for better discoverability
- Make consistent changes across README.md and README_zh-CN.md

fix(table): add model path for slanet-plus to resolve RapidTableError

fix(table): add model path for slanet-plus to resolve RapidTableError

- Import os and pathlib modules to handle file paths
- Define the path to the slanet-plus model
- Update RapidTableInput initialization to include the model path

update 1.3.1

- Add support for Python3.11, 3.12, and 3.13
- Replace requirements.txt based installation with editable install

- Update Python version requirements to >=3.10
- Simplify torch installation command- Remove numpy version restriction
- Update CUDA compatibility information
- Adjust environment creation commands across multiple documentation files

- Remove rapid_table from install_requires in setup.py

- Add "3.13" option for Python version
- Remove "3.9" option for Python version
- Update dependency version options:
  - Remove "0.8.x", "0.9.x", "0.10.x"
  - Add "1.1.x", "1.2.x", "1.3.x"

- Update transformers to exclude version 4.51.0 due to compatibility issues- Rapid table version range expanded to >=1.0.5,<2.0.0
- Add separate 'full_old_linux' extras_require for better support of older Linux systems
- Update matplotlib version requirements for different platforms
- Remove platform-specific paddlepaddle versions,

- Add rapid_table==1.0.3 to old_linux specific dependencies
- This version is compatible with Linux systems from 2019 and earlier
- Newer versions of rapid_table depend on onnxruntime, which is not supported on older Linux systems

fix(model): improve VRAM detection and handling

- Refactor VRAM detection logic for better readability and efficiency
- Add fallback mechanism for unknown VRAM sizes
- Improve device checking in get_vram function

fix: image dataset add lang field