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: In ragflow/rag/app /naive.py, if there are multiple images in one line, the other images will be lost (#9968)

Browse Source 
### What problem does this PR solve?
https://github.com/infiniflow/ragflow/issues/9966

### 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:
Stephen Hu
2025-09-11 11:08:31 +08:00
committed by GitHub
parent d14d92a900
commit 179091b1a4
1 changed files with 36 additions and 30 deletions
Download Patch File Download Diff File Expand all files Collapse all files

66
rag/app/naive.py
View File

@ -41,37 +41,43 @@ class Docx(DocxParser):
pass
def get_picture(self, document, paragraph):
img = paragraph._element.xpath('.//pic:pic')
if not img:
return None
img = img[0]
embed = img.xpath('.//a:blip/@r:embed')
if not embed:
return None
embed = embed[0]
try:
related_part = document.part.related_parts[embed]
image_blob = related_part.image.blob
except UnrecognizedImageError:
logging.info("Unrecognized image format. Skipping image.")
return None
except UnexpectedEndOfFileError:
logging.info("EOF was unexpectedly encountered while reading an image stream. Skipping image.")
return None
except InvalidImageStreamError:
logging.info("The recognized image stream appears to be corrupted. Skipping image.")
return None
except UnicodeDecodeError:
logging.info("The recognized image stream appears to be corrupted. Skipping image.")
return None
except Exception:
logging.info("The recognized image stream appears to be corrupted. Skipping image.")
return None
try:
image = Image.open(BytesIO(image_blob)).convert('RGB')
return image
except Exception:
imgs = paragraph._element.xpath('.//pic:pic')
if not imgs:
return None
res_img = None
for img in imgs:
embed = img.xpath('.//a:blip/@r:embed')
if not embed:
continue
embed = embed[0]
try:
related_part = document.part.related_parts[embed]
image_blob = related_part.image.blob
except UnrecognizedImageError:
logging.info("Unrecognized image format. Skipping image.")
continue
except UnexpectedEndOfFileError:
logging.info("EOF was unexpectedly encountered while reading an image stream. Skipping image.")
continue
except InvalidImageStreamError:
logging.info("The recognized image stream appears to be corrupted. Skipping image.")
continue
except UnicodeDecodeError:
logging.info("The recognized image stream appears to be corrupted. Skipping image.")
continue
except Exception:
logging.info("The recognized image stream appears to be corrupted. Skipping image.")
continue
try:
image = Image.open(BytesIO(image_blob)).convert('RGB')
if res_img is None:
res_img = image
else:
res_img = concat_img(res_img, image)
except Exception:
continue
return res_img
def __clean(self, line):
line = re.sub(r"\u3000", " ", line).strip()