Lukas 6ef64fcd1b fix(parser): fail an EPUB with no readable chapter instead of returning nothing (#19814)

2026-09-28 10:19:35 +08:00

..

resume

Refactor: reformat all code for lefthook using ruff and gofmt (#16585)

2026-07-03 12:53:39 +08:00

__init__.py

Feat: support epub parsing (#13650)

2026-03-17 20:14:06 +08:00

docling_parser.py

fix(deepdoc): guard docling crop against missing page images (#17147)

2026-07-24 11:20:06 +08:00

docx_parser.py

refactor(go): default Go cache/queue backend to Kvrocks and fail fast when down (#19804)

2026-09-18 19:16:07 +08:00

epub_parser.py

fix(parser): fail an EPUB with no readable chapter instead of returning nothing (#19814)

2026-09-28 10:19:35 +08:00

excel_parser.py

fix(parser): read the separator a CSV was written with (#19740)

2026-09-28 10:18:11 +08:00

figure_parser.py

fix(figure_parser): accept lang as named parameter on VisionFigureParser (#17280) (#19511)

2026-09-11 11:31:02 +08:00

html_parser.py

fix(parser): decode non-UTF-8 document text (#19253)

2026-09-04 15:40:34 +08:00

json_parser.py

fix(parser): split JSONL records only on newline characters (#20029)

2026-09-24 10:06:20 +08:00

markdown_parser.py

fix(parser): accept longer closing fences during table extraction (#20028)

2026-09-24 10:06:14 +08:00

mineru_parser.py

fix(mineru): upload the PDF once when several page ranges are configured (#19183)

2026-09-16 14:04:27 +08:00

mistral_parser.py

fix(mistral): honor dataset language in figure prompts (#18021)

2026-08-11 20:38:24 +08:00

monkeyocrv2_parser.py

feat(parser): add MonkeyOCRv2-Parsing support (#18887)

2026-09-07 21:12:50 +08:00

opendataloader_parser.py

fix(deepdoc): harden opendataloader table-cell parsing against bad json (#17316)

2026-08-25 19:49:15 +08:00

paddleocr_parser.py

feat(deepdoc): verify PaddleOCR service connectivity in check_installation (#17669)

2026-09-17 12:32:27 +08:00

pdf_parser.py

fix(deepdoc): preserve textless PDF figures for VLM extraction (#19679) (#19688)

2026-09-16 15:25:53 +08:00

ppt_parser.py

fix(parser): keep a one-row slide table instead of dropping it (#19705)

2026-09-16 19:06:15 +08:00

somark_parser.py

fix: update somark.tech to somark.cn/somark.ai with purchase URLs (#16892)

2026-07-16 19:18:05 +08:00

tcadp_parser.py

fix(tcadp): add timeout to HTTP GET request for document download (#18336)

2026-08-17 13:22:21 +08:00

txt_parser.py

fix(rag): unify parser_config delimiter defaults on a single constant (#19058)

2026-09-03 17:16:37 +08:00

utils.py

fix(parser): decode non-UTF-8 document text (#19253)

2026-09-04 15:40:34 +08:00