From d77380f024e95852d14e8fa4386609381c654f1a Mon Sep 17 00:00:00 2001 From: Stephen Hu Date: Mon, 24 Mar 2025 09:31:31 +0800 Subject: [PATCH] Feat: support pic base bullet for PPT (#6406) ### What problem does this PR solve? support pic base bullet for PPT modify one mistake in document ### Type of change - [x] New Feature (non-breaking change which adds functionality) --- deepdoc/parser/ppt_parser.py | 2 +- docs/references/http_api_reference.md | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/deepdoc/parser/ppt_parser.py b/deepdoc/parser/ppt_parser.py index 5cbd1330f..8757e3090 100644 --- a/deepdoc/parser/ppt_parser.py +++ b/deepdoc/parser/ppt_parser.py @@ -24,7 +24,7 @@ class RAGFlowPptParser: super().__init__() def __get_bulleted_text(self, paragraph): - is_bulleted = bool(paragraph._p.xpath("./a:pPr/a:buChar")) or bool(bool(paragraph._p.xpath("./a:pPr/a:buAutoNum")) ) + is_bulleted = bool(paragraph._p.xpath("./a:pPr/a:buChar")) or bool(paragraph._p.xpath("./a:pPr/a:buAutoNum")) or bool(paragraph._p.xpath("./a:pPr/a:buBlip")) if is_bulleted: return f"{' '* paragraph.level}.{paragraph.text}" else: diff --git a/docs/references/http_api_reference.md b/docs/references/http_api_reference.md index bde246048..908afe2bb 100644 --- a/docs/references/http_api_reference.md +++ b/docs/references/http_api_reference.md @@ -1149,7 +1149,7 @@ curl --request GET \ - `dataset_id`: (*Path parameter*) The associated dataset ID. -- `document_ids`: (*Path parameter*) +- `document_id`: (*Path parameter*) The associated document ID. - `keywords`(*Filter parameter*), `string` The keywords used to match chunk content.