KMS/ragflow
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

Fix:#3230 When parsing a docx file using the Book parsing method, to_page is always -1, resulting in a block count of 0 even if parsing is successful (#3249)

Browse Source 
### What problem does this PR solve?

When parsing a docx file using the Book parsing method, to_page is
always -1, resulting in a block count of 0 even if parsing is successful

Fix:#3230

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)

Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
This commit is contained in:
kuschzzp 2024-11-08 09:21:42 +08:00 committed by GitHub
parent 7c0d28b62d
commit 9c6cc20356
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
api/db/db_models.py
View File

@ -840,7 +840,7 @@ class Task(DataBaseModel):
doc_id = CharField(max_length=32, null=False, index=True)
from_page = IntegerField(default=0)
to_page = IntegerField(default=-1)
to_page = IntegerField(default=100000000)
begin_at = DateTimeField(null=True, index=True)
process_duation = FloatField(default=0)

4
deepdoc/parser/docx_parser.py
View File

@ -110,7 +110,7 @@ class RAGFlowDocxParser:
return lines
return ["\n".join(lines)]
def __call__(self, fnm, from_page=0, to_page=100000):
def __call__(self, fnm, from_page=0, to_page=100000000):
self.doc = Document(fnm) if isinstance(
fnm, str) else Document(BytesIO(fnm))
pn = 0 # parsed page
@ -130,7 +130,7 @@ class RAGFlowDocxParser:
if 'lastRenderedPageBreak' in run._element.xml:
pn += 1
secs.append(("".join(runs_within_single_paragraph), p.style.name)) # then concat run.text as part of the paragraph
secs.append(("".join(runs_within_single_paragraph), p.style.name if hasattr(p.style, 'name') else '')) # then concat run.text as part of the paragraph
tbls = [self.__extract_table_content(tb) for tb in self.doc.tables]
return secs, tbls