pengjunjie/ragflow
1
0
Fork 1
mirror of https://github.com/infiniflow/ragflow.git synced 2025-12-08 20:42:30 +08:00
Code Issues Packages Projects Releases Wiki Activity

Fix parser_config access for layout_recognize in presentation.py (#8492)

Browse Source 
### What problem does this PR solve?
This PR addresses an issue in the presentation parser where the
`layout_recognize` configuration was incorrectly retrieved from
`kwargs.get("layout_recognize", "DeepDOC")`. Instead, it should be
sourced from the `parser_config` parameter, specifically
`parser_config.get("layout_recognize", "DeepDOC")`.

This mismatch could cause the parser to default to the "DeepDOC" layout
recognizer, ignoring any alternative recognition method specified in the
parser configuration. As a result, PDF document parsing might use an
incorrect recognition engine.

The fix ensures the presentation parser consistently uses the
`layout_recognize` setting from `parser_config`, aligning with the
configuration access patterns used elsewhere in the codebase.

### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
This commit is contained in:
Tuan Le
2025-06-26 10:54:43 +07:00
committed by GitHub
parent f09ca8e795
commit 6b1221d2f6
1 changed files with 4 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
rag/app/presentation.py
View File

@ -98,12 +98,14 @@ class PlainPdf(PlainParser):
def chunk(filename, binary=None, from_page=0, to_page=100000, def chunk(filename, binary=None, from_page=0, to_page=100000,
lang="Chinese", callback=None, **kwargs): lang="Chinese", callback=None, parser_config=None, **kwargs):
""" """
The supported file formats are pdf, pptx. The supported file formats are pdf, pptx.
Every page will be treated as a chunk. And the thumbnail of every page will be stored. Every page will be treated as a chunk. And the thumbnail of every page will be stored.
PPT file will be parsed by using this method automatically, setting-up for every PPT file is not necessary. PPT file will be parsed by using this method automatically, setting-up for every PPT file is not necessary.
""" """
if parser_config is None:
parser_config = {}
eng = lang.lower() == "english" eng = lang.lower() == "english"
doc = { doc = {
"docnm_kwd": filename, "docnm_kwd": filename,
@ -126,7 +128,7 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
res.append(d) res.append(d)
return res return res
elif re.search(r"\.pdf$", filename, re.IGNORECASE): elif re.search(r"\.pdf$", filename, re.IGNORECASE):
layout_recognizer = kwargs.get("layout_recognize", "DeepDOC") layout_recognizer = parser_config.get("layout_recognize", "DeepDOC")
if layout_recognizer == "DeepDOC": if layout_recognizer == "DeepDOC":
pdf_parser = Pdf() pdf_parser = Pdf()
sections = pdf_parser(filename, binary, from_page=from_page, to_page=to_page, callback=callback) sections = pdf_parser(filename, binary, from_page=from_page, to_page=to_page, callback=callback)