zlei6/ragflow
1
0
Fork 0
mirror of https://github.com/infiniflow/ragflow.git synced 2026-07-27 10:52:03 +08:00
Code Issues Packages Projects Releases Wiki Activity

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

Browse Source
This commit is contained in:
Wang Qi
2026-07-03 12:53:39 +08:00
committed by GitHub
parent 19fcb4a981
commit 6a4b9be426
588 changed files with 11123 additions and 15412 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
deepdoc/parser/ppt_parser.py
View File

@@ -27,23 +27,20 @@ class RAGFlowPptParser:
def __sort_shapes(self, shapes):
cache_key = id(shapes)
if cache_key not in self._shape_cache:
self._shape_cache[cache_key] = sorted(
shapes,
key=lambda x: ((x.top if x.top is not None else 0) // 10, x.left if x.left is not None else 0)
)
self._shape_cache[cache_key] = sorted(shapes, key=lambda x: ((x.top if x.top is not None else 0) // 10, x.left if x.left is not None else 0))
return self._shape_cache[cache_key]
def __get_bulleted_text(self, paragraph):
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}"
return f"{' ' * paragraph.level}.{paragraph.text}"
else:
return paragraph.text
def __extract(self, shape):
try:
# First try to get text content
if hasattr(shape, 'has_text_frame') and shape.has_text_frame:
if hasattr(shape, "has_text_frame") and shape.has_text_frame:
text_frame = shape.text_frame
texts = []
for paragraph in text_frame.paragraphs:
@@ -56,7 +53,7 @@ class RAGFlowPptParser:
shape_type = shape.shape_type
except NotImplementedError:
# If shape_type is not available, try to get text content
if hasattr(shape, 'text'):
if hasattr(shape, "text"):
return shape.text.strip()
return ""
@@ -65,8 +62,7 @@ class RAGFlowPptParser:
tb = shape.table
rows = []
for i in range(1, len(tb.rows)):
rows.append("; ".join([tb.cell(
0, j).text + ": " + tb.cell(i, j).text for j in range(len(tb.columns)) if tb.cell(i, j)]))
rows.append("; ".join([tb.cell(0, j).text + ": " + tb.cell(i, j).text for j in range(len(tb.columns)) if tb.cell(i, j)]))
return "\n".join(rows)
# Handle group shape
@@ -85,9 +81,7 @@ class RAGFlowPptParser:
return ""
def __call__(self, fnm, from_page, to_page, callback=None):
ppt = Presentation(fnm) if isinstance(
fnm, str) else Presentation(
BytesIO(fnm))
ppt = Presentation(fnm) if isinstance(fnm, str) else Presentation(BytesIO(fnm))
txts = []
self.total_page = len(ppt.slides)
for i, slide in enumerate(ppt.slides):