ragflow

testdata

fix(parser): preserve PaddleOCR PDF highlight positions (#21205 )

2026-10-20 15:46:31 +08:00

align_test.go

feat(parser): emit structured TableData instead of HTML for tables (#20741 )

2026-10-10 19:52:57 +08:00

audio_parser_test.go

refactor(parser): drop ParseResult.OutputFormat/Markdown, gate on Produced() (#21414 )

2026-10-23 19:11:10 +08:00

audio_parser.go

refactor(parser): drop ParseResult.OutputFormat/Markdown, gate on Produced() (#21414 )

2026-10-23 19:11:10 +08:00

csv_parser_test.go

feat(parser): add media references for on-demand image materialization (#21561 )

2026-10-28 19:47:53 +08:00

csv_parser.go

feat(parser): add media references for on-demand image materialization (#21561 )

2026-10-28 19:47:53 +08:00

delimiter.go

refactor(ingestion): migrate general parser and chunker contract (#19611 )

2026-09-15 15:51:29 +08:00

doc_element_text_test.go

refactor(parser): collapse docElementText into docxElementText (#19135 )

2026-09-03 16:42:49 +08:00

doc_flatten_test.go

Fix(parser): raise legacy .doc parsing fidelity via structured IR (#18192 )

2026-09-02 12:13:37 +08:00

doc_flatten.go

refactor(parser): collapse docElementText into docxElementText (#19135 )

2026-09-03 16:42:49 +08:00

doc_item_positions_test.go

refactor(parser): unify PDF JSON post-processing (#21228 )

2026-10-21 17:46:25 +08:00

doc_item_test.go

refactor(ingestion): remove all ck_type tombstones (#21317 )

2026-10-22 14:34:28 +08:00

doc_item.go

feat(parser): add media references for on-demand image materialization (#21561 )

2026-10-28 19:47:53 +08:00

doc_parser_doc_table_test.go

refactor(parser): drop ParseResult.OutputFormat/Markdown, gate on Produced() (#21414 )

2026-10-23 19:11:10 +08:00

doc_parser_options_test.go

fix(parser): support remove_toc and remove_header_footer in DOCParser (#21988 )

2026-11-09 10:38:19 +08:00

doc_parser_synth_test.go

refactor(parser): drop ParseResult.OutputFormat/Markdown, gate on Produced() (#21414 )

2026-10-23 19:11:10 +08:00

doc_parser.go

fix(parser): support remove_toc and remove_header_footer in DOCParser (#21988 )

2026-11-09 10:38:19 +08:00

doc_text_empty_test.go

refactor(parser): move native PDF/Office extraction into deepdoc facade (#20273 )

2026-09-29 17:26:27 +08:00

doc_text_select_test.go

fix(parser): prefer structured IR over flatter views for .doc (#19147 )

2026-09-02 21:29:00 +08:00

docx_caption_cgo_test.go

Upgrade office_oxide to v0.1.16 and drop temporary caption/table fixes (#21978 )

2026-11-05 12:38:55 +08:00

docx_caption_test.go

Upgrade office_oxide to v0.1.16 and drop temporary caption/table fixes (#21978 )

2026-11-05 12:38:55 +08:00

docx_extract_test.go

fix(parser): detect Office content before selecting Go parsers (#21909 )

2026-11-03 17:38:56 +08:00

docx_ir_caption_style_test.go

Upgrade office_oxide to v0.1.16 and drop temporary caption/table fixes (#21978 )

2026-11-05 12:38:55 +08:00

docx_ir_test.go

fix(parser): preserve Office table cell spans (#22012 )

2026-11-05 15:41:17 +08:00

docx_ir.go

fix(parser): preserve Office table cell spans (#22012 )

2026-11-05 15:41:17 +08:00

docx_parser_cgo_test.go

refactor(parser): drop ParseResult.OutputFormat/Markdown, gate on Produced() (#21414 )

2026-10-23 19:11:10 +08:00

docx_parser_test.go

feat(parser): hand off Office images as media refs (#21700 )

2026-10-30 16:48:51 +08:00

docx_parser.go

Upgrade office_oxide to v0.1.16 and drop temporary caption/table fixes (#21978 )

2026-11-05 12:38:55 +08:00

docx_postprocess_test.go

fix: honor parser params and image VLM system_prompt in Go ingestion (#17334 )

2026-07-24 14:42:26 +08:00

docx_postprocess.go

fix: honor parser params and image VLM system_prompt in Go ingestion (#17334 )

2026-07-24 14:42:26 +08:00

email_parser_test.go

fix(parser): parse email attachments whose names are RFC 2047 encoded (#21361 )

2026-10-29 20:33:26 +08:00

email_parser.go

fix(parser): detect Office content before selecting Go parsers (#21909 )

2026-11-03 17:38:56 +08:00

epub_parser_test.go

feat(media): harden run media cache lifecycle and limits (#21694 )

2026-10-30 12:41:23 +08:00

epub_parser.go

feat(parser): hand off Office images as media refs (#21700 )

2026-10-30 16:48:51 +08:00

fetch_image.go

feat(parser): hand off Markdown and HTML remote images as media refs (#21764 )

2026-11-02 11:59:01 +08:00

html_charset_test.go

refactor(parser): type ParseResult.JSON as []DocItem boundary adapter (#20998 )

2026-10-15 20:15:40 +08:00

html_media_test.go

feat(parser): hand off Markdown and HTML remote images as media refs (#21764 )

2026-11-02 11:59:01 +08:00

html_parser_align_test.go

refactor(ingestion): remove all ck_type tombstones (#21317 )

2026-10-22 14:34:28 +08:00

html_parser_test.go

fix(parser): leave out the content of <template> elements (#21284 )

2026-10-22 14:38:16 +08:00

html_parser_unified_test.go

refactor(parser): type ParseResult.JSON as []DocItem boundary adapter (#20998 )

2026-10-15 20:15:40 +08:00

html_parser.go

feat(parser): hand off Markdown and HTML remote images as media refs (#21764 )

2026-11-02 11:59:01 +08:00

html_postprocess.go

fix: honor parser params and image VLM system_prompt in Go ingestion (#17334 )

2026-07-24 14:42:26 +08:00

html_remote_media_test.go

fix(parser): detect Office content before selecting Go parsers (#21909 )

2026-11-03 17:38:56 +08:00

image_media_test.go

fix(parser): drop hard image edge/pixel limit, add opt-in raster byte ceiling (#20745 )

2026-10-10 19:54:28 +08:00

image_media.go

feat(parser): add media references for on-demand image materialization (#21561 )

2026-10-28 19:47:53 +08:00

image_payload_test.go

feat(parser): add media references for on-demand image materialization (#21561 )

2026-10-28 19:47:53 +08:00

json_parser_test.go

fix(parser): keep JSON numbers and <, >, & as written in JSON items (#21101 )

2026-10-19 15:24:03 +08:00

json_parser.go

feat(parser): add media references for on-demand image materialization (#21561 )

2026-10-28 19:47:53 +08:00

markdown_media_test.go

fix(parser): detect Office content before selecting Go parsers (#21909 )

2026-11-03 17:38:56 +08:00

markdown_parser_test.go

fix(parser): keep the paragraphs of a Markdown blockquote apart (#21347 )

2026-11-05 17:27:45 +08:00

markdown_parser.go

fix(parser): keep the paragraphs of a Markdown blockquote apart (#21347 )

2026-11-05 17:27:45 +08:00

media_budget_test.go

feat(media): harden run media cache lifecycle and limits (#21694 )

2026-10-30 12:41:23 +08:00

office_image_fixture_cgo_test.go

feat(parser): hand off Office images as media refs (#21700 )

2026-10-30 16:48:51 +08:00

office_media_test.go

fix(parser): detect Office content before selecting Go parsers (#21909 )

2026-11-03 17:38:56 +08:00

office_media.go

feat(parser): hand off Office images as media refs (#21700 )

2026-10-30 16:48:51 +08:00

office_parsers_nocgo_test.go

fix: Go ingestion migration batch 5 (Parser 1.1/1.7/2.11, Chunker 1.7/1.8/2.6/2.7, Tokenizer 6x fixes) (#17419 )

2026-07-28 11:12:52 +08:00

office_parsers.go

refactor(parser): move native PDF/Office extraction into deepdoc facade (#20273 )

2026-09-29 17:26:27 +08:00

office_routes_cgo_test.go

fix(parser): detect Office content before selecting Go parsers (#21909 )

2026-11-03 17:38:56 +08:00

office_table_render_test.go

feat(parser): hand off Office images as media refs (#21700 )

2026-10-30 16:48:51 +08:00

office_table_render.go

feat(parser): hand off Office images as media refs (#21700 )

2026-10-30 16:48:51 +08:00

office_text_only_test.go

fix(parser): detect Office content before selecting Go parsers (#21909 )

2026-11-03 17:38:56 +08:00

office_try_parse_test.go

fix(parser): detect Office content before selecting Go parsers (#21909 )

2026-11-03 17:38:56 +08:00

office_try_parse.go

fix(parser): detect Office content before selecting Go parsers (#21909 )

2026-11-03 17:38:56 +08:00

parse_result_produced_test.go

refactor(parser): drop ParseResult.OutputFormat/Markdown, gate on Produced() (#21414 )

2026-10-23 19:11:10 +08:00

parse_result_test.go

refactor(parser): drop ParseResult.OutputFormat/Markdown, gate on Produced() (#21414 )

2026-10-23 19:11:10 +08:00

parse_result.go

fix(parser): detect Office content before selecting Go parsers (#21909 )

2026-11-03 17:38:56 +08:00

parse_with_result_test.go

fix(parser): detect Office content before selecting Go parsers (#21909 )

2026-11-03 17:38:56 +08:00

parser_selection_test.go

fix(parser): detect Office content before selecting Go parsers (#21909 )

2026-11-03 17:38:56 +08:00

parser_type.go

fix(parser): detect Office content before selecting Go parsers (#21909 )

2026-11-03 17:38:56 +08:00

pdf_analyzer_dispatch_entry_test.go

fix(parser): preserve PaddleOCR PDF highlight positions (#21205 )

2026-10-20 15:46:31 +08:00

pdf_analyzer_dispatch_register_test.go

fix(parser): preserve PaddleOCR PDF highlight positions (#21205 )

2026-10-20 15:46:31 +08:00

pdf_analyzer_dispatch_test.go

refactor(parser): remove dead output_format readers (#21336 )

2026-10-22 17:40:41 +08:00

pdf_markdown_to_result_test.go

refactor(parser): drop ParseResult.OutputFormat/Markdown, gate on Produced() (#21414 )

2026-10-23 19:11:10 +08:00

pdf_outline_cgo_test.go

fix(parser): read PDF bookmarks into remote parse results (#21499 )

2026-10-28 15:28:30 +08:00

pdf_outline_cgo.go

fix(parser): read PDF bookmarks into remote parse results (#21499 )

2026-10-28 15:28:30 +08:00

pdf_outline_nocgo.go

fix(parser): read PDF bookmarks into remote parse results (#21499 )

2026-10-28 15:28:30 +08:00

pdf_outline_test.go

fix(parser): read PDF bookmarks into remote parse results (#21499 )

2026-10-28 15:28:30 +08:00

pdf_outline.go

fix(parser): read PDF bookmarks into remote parse results (#21499 )

2026-10-28 15:28:30 +08:00

pdf_parser_cgo_test.go

refactor(parser): drop ParseResult.OutputFormat/Markdown, gate on Produced() (#21414 )

2026-10-23 19:11:10 +08:00

pdf_parser_common_test.go

feat(go): MonkeyOCR PDF dispatch on Go ingestion path (#20469 )

2026-11-03 12:33:27 +08:00

pdf_parser_common.go

feat(go): MonkeyOCR PDF dispatch on Go ingestion path (#20469 )

2026-11-03 12:33:27 +08:00

pdf_parser_docling_test.go

fix(parser): emit Docling page positions and real page_count (#21330 )

2026-10-28 09:55:28 +08:00

pdf_parser_docling.go

fix(parser): honour the pipeline context in SoMark and Docling PDF calls (#21536 )

2026-10-28 15:52:16 +08:00

pdf_parser_fixture_cgo_test.go

refactor(parser): drop ParseResult.OutputFormat/Markdown, gate on Produced() (#21414 )

2026-10-23 19:11:10 +08:00

pdf_parser_is_method_test.go

fix(parser): drop EE-specific references from OSS parse-method comment (#21674 )

2026-10-29 15:30:34 +08:00

pdf_parser_mineru_poll_test.go

fix(parser): stop MinerU polling when the run is cancelled (#21571 )

2026-10-29 20:37:00 +08:00

pdf_parser_mineru_test.go

feat(parser): parse MinerU 4 output and verify the endpoint (#21625 )

2026-10-29 18:45:54 +08:00

pdf_parser_mineru.go

fix(parser): stop MinerU polling when the run is cancelled (#21571 )

2026-10-29 20:37:00 +08:00

pdf_parser_nocgo_test.go

refactor(parser): drop ParseResult.OutputFormat/Markdown, gate on Produced() (#21414 )

2026-10-23 19:11:10 +08:00

pdf_parser_opendataloader_cgo_test.go

fix(parser): carry OpenDataLoader PDF positions through to parse items (#21450 )

2026-10-28 10:44:39 +08:00

pdf_parser_opendataloader_cgo.go

fix(parser): carry OpenDataLoader PDF positions through to parse items (#21450 )

2026-10-28 10:44:39 +08:00

pdf_parser_opendataloader_nocgo_test.go

fix(parser): carry OpenDataLoader PDF positions through to parse items (#21450 )

2026-10-28 10:44:39 +08:00

pdf_parser_opendataloader_nocgo.go

fix(parser): carry OpenDataLoader PDF positions through to parse items (#21450 )

2026-10-28 10:44:39 +08:00

pdf_parser_opendataloader_positions_test.go

fix(parser): carry OpenDataLoader PDF positions through to parse items (#21450 )

2026-10-28 10:44:39 +08:00

pdf_parser_opendataloader_test.go

fix(parser): apply the OpenDataLoader request timeout (#21527 )

2026-10-28 12:44:02 +08:00

pdf_parser_opendataloader.go

fix(parser): apply the OpenDataLoader request timeout (#21527 )

2026-10-28 12:44:02 +08:00

pdf_parser_paddleocr_cgo_test.go

feat(parser): add MiniCPM-OCR as a PDF parser (#21785 )

2026-11-06 14:29:41 +08:00

pdf_parser_paddleocr_cgo.go

fix(parser): preserve PaddleOCR PDF highlight positions (#21205 )

2026-10-20 15:46:31 +08:00

pdf_parser_paddleocr_nocgo_test.go

feat(parser): add MiniCPM-OCR as a PDF parser (#21785 )

2026-11-06 14:29:41 +08:00

pdf_parser_paddleocr_nocgo.go

fix(parser): preserve PaddleOCR PDF highlight positions (#21205 )

2026-10-20 15:46:31 +08:00

pdf_parser_paddleocr_test.go

feat(parser): add MiniCPM-OCR as a PDF parser (#21785 )

2026-11-06 14:29:41 +08:00

pdf_parser_paddleocr.go

feat(parser): add MiniCPM-OCR as a PDF parser (#21785 )

2026-11-06 14:29:41 +08:00

pdf_parser_pages_e2e_test.go

feat: parser pages range and parse type validation for dataset/document (#17293 )

2026-07-23 19:57:27 +08:00

pdf_parser_pages_test.go

refactor(parser): remove dead output_format readers (#21336 )

2026-10-22 17:40:41 +08:00

pdf_parser_remote_common.go

fix(parser): carry OpenDataLoader PDF positions through to parse items (#21450 )

2026-10-28 10:44:39 +08:00

pdf_parser_remote_ctx_test.go

fix(parser): honour the pipeline context in SoMark and Docling PDF calls (#21536 )

2026-10-28 15:52:16 +08:00

pdf_parser_somark_test.go

fix: SoMark web page is missing (#21710 )

2026-11-02 12:05:44 +08:00

pdf_parser_somark.go

fix: SoMark web page is missing (#21710 )

2026-11-02 12:05:44 +08:00

pdf_parser_table_contract_test.go

feat(media): harden run media cache lifecycle and limits (#21694 )

2026-10-30 12:41:23 +08:00

pdf_parser_tcadp_test.go

refactor(parser): drop ParseResult.OutputFormat/Markdown, gate on Produced() (#21414 )

2026-10-23 19:11:10 +08:00

pdf_parser_tcadp.go

refactor(parser): remove dead output_format readers (#21336 )

2026-10-22 17:40:41 +08:00

pdf_parser_tenant_config_test.go

fix(parser): use selected tenant SoMark and OpenDataLoader instances (#21112 )

2026-10-20 13:39:49 +08:00

pdf_positions_test.go

fix(chunker): preserve list-form PDF positions in title chunkers (#21258 )

2026-10-21 18:41:31 +08:00

pdf_positions.go

fix(chunker): preserve list-form PDF positions in title chunkers (#21258 )

2026-10-21 18:41:31 +08:00

pdf_postprocess_measure_test.go

test(parser): pin figure-aware reading order in PDF post-process (#18178 )

2026-08-12 20:28:23 +08:00

pdf_postprocess_test.go

fix(parser): move PDF TOC and header/footer removal to box level (#19779 )

2026-09-18 11:29:28 +08:00

pdf_postprocess.go

refactor(parser): remove dead output_format readers (#21336 )

2026-10-22 17:40:41 +08:00

pdf_result_normalize_markdown_test.go

feat(parser): hand off Markdown and HTML remote images as media refs (#21764 )

2026-11-02 11:59:01 +08:00

pdf_result_test.go

feat(parser): hand off Markdown and HTML remote images as media refs (#21764 )

2026-11-02 11:59:01 +08:00

pdf_result.go

fix(parser): keep PaddleOCR figure regions as media items (#21452 )

2026-10-29 20:21:45 +08:00

pdf_table_no_html_text_test.go

feat(parser): hand off Office images as media refs (#21700 )

2026-10-30 16:48:51 +08:00

picture_parser_test.go

refactor(parser): drop ParseResult.OutputFormat/Markdown, gate on Produced() (#21414 )

2026-10-23 19:11:10 +08:00

picture_parser.go

feat(media): harden run media cache lifecycle and limits (#21694 )

2026-10-30 12:41:23 +08:00

ppt_parser_cgo_test.go

fix(parser): detect Office content before selecting Go parsers (#21909 )

2026-11-03 17:38:56 +08:00

ppt_parser.go

refactor(parser): move native PDF/Office extraction into deepdoc facade (#20273 )

2026-09-29 17:26:27 +08:00

pptx_ir_test.go

feat(parser): hand off Office images as media refs (#21700 )

2026-10-30 16:48:51 +08:00

pptx_ir.go

feat(parser): hand off Office images as media refs (#21700 )

2026-10-30 16:48:51 +08:00

pptx_parser.go

fix(parser): detect Office content before selecting Go parsers (#21909 )

2026-11-03 17:38:56 +08:00

producer_audit_test.go

refactor(parser): drop ParseResult.OutputFormat/Markdown, gate on Produced() (#21414 )

2026-10-23 19:11:10 +08:00

rechunk_singlereturn_test.go

refactor(parser): remove dead ParseResult.Text field and text output path (#21334 )

2026-10-22 16:23:48 +08:00

ssrf_test_helper_test.go

Fix: honor ALLOW_ANY_HOST (#21949 )

2026-11-04 15:49:55 +08:00

table_regression_test.go

Upgrade office_oxide to v0.1.16 and drop temporary caption/table fixes (#21978 )

2026-11-05 12:38:55 +08:00

table_structure_test.go

fix(parser): preserve Office table cell spans (#22012 )

2026-11-05 15:41:17 +08:00

tcadp_common_test.go

fix(parser): scope TCADP bearer token to API server host only (#17672 )

2026-09-21 13:15:41 +08:00

tcadp_common.go

refactor(parser): remove dead output_format readers (#21336 )

2026-10-22 17:40:41 +08:00

text_parser.go

feat(parser): add media references for on-demand image materialization (#21561 )

2026-10-28 19:47:53 +08:00

text_toc_test.go

fix(parser): recognize a Table of Contents heading when removing a TOC (#21331 )

2026-10-28 21:29:49 +08:00

text_toc.go

fix(parser): recognize a Table of Contents heading when removing a TOC (#21331 )

2026-10-28 21:29:49 +08:00

xls_parser_test.go

fix(parser): detect Office content before selecting Go parsers (#21909 )

2026-11-03 17:38:56 +08:00

xls_parser.go

fix(parser): detect Office content before selecting Go parsers (#21909 )

2026-11-03 17:38:56 +08:00

xls_tcadp_test.go

refactor(parser): drop ParseResult.OutputFormat/Markdown, gate on Produced() (#21414 )

2026-10-23 19:11:10 +08:00

xlsx_media_test.go

fix(parser): detect Office content before selecting Go parsers (#21909 )

2026-11-03 17:38:56 +08:00

xlsx_normalize_test.go

refactor(ingestion): migrate general parser and chunker contract (#19611 )

2026-09-15 15:51:29 +08:00

xlsx_normalize.go

fix(parser): recover invalid XLSX sheet names (#19264 )

2026-09-04 18:51:27 +08:00

xlsx_parse_method_test.go

feat(parser): hand off Office images as media refs (#21700 )

2026-10-30 16:48:51 +08:00

xlsx_parser.go

feat(parser): hand off Office images as media refs (#21700 )

2026-10-30 16:48:51 +08:00