estel/dify
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

Fix: the pict type picture was not processed in the docx (#19305)

Browse Source 
Co-authored-by: zqgame <zqgame@zqgame.local>
This commit is contained in:
helojo
2025-07-17 22:53:35 +08:00
committed by GitHub
parent 7a69b57823
commit e7d80bf7bf
1 changed files with 30 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

30
api/core/rag/extractor/word_extractor.py
View File

@@ -238,9 +238,11 @@ class WordExtractor(BaseExtractor):
paragraph_content = [] paragraph_content = []
for run in paragraph.runs: for run in paragraph.runs:
if hasattr(run.element, "tag") and isinstance(run.element.tag, str) and run.element.tag.endswith("r"): if hasattr(run.element, "tag") and isinstance(run.element.tag, str) and run.element.tag.endswith("r"):
# Process drawing type images
drawing_elements = run.element.findall( drawing_elements = run.element.findall(
".//{http://schemas.openxmlformats.org/wordprocessingml/2006/main}drawing" ".//{http://schemas.openxmlformats.org/wordprocessingml/2006/main}drawing"
) )
has_drawing = False
for drawing in drawing_elements: for drawing in drawing_elements:
blip_elements = drawing.findall( blip_elements = drawing.findall(
".//{http://schemas.openxmlformats.org/drawingml/2006/main}blip" ".//{http://schemas.openxmlformats.org/drawingml/2006/main}blip"
@@ -252,6 +254,34 @@ class WordExtractor(BaseExtractor):
if embed_id: if embed_id:
image_part = doc.part.related_parts.get(embed_id) image_part = doc.part.related_parts.get(embed_id)
if image_part in image_map: if image_part in image_map:
has_drawing = True
paragraph_content.append(image_map[image_part])
# Process pict type images
shape_elements = run.element.findall(
".//{http://schemas.openxmlformats.org/wordprocessingml/2006/main}pict"
)
for shape in shape_elements:
# Find image data in VML
shape_image = shape.find(
".//{http://schemas.openxmlformats.org/wordprocessingml/2006/main}binData"
)
if shape_image is not None and shape_image.text:
image_id = shape_image.get(
"{http://schemas.openxmlformats.org/officeDocument/2006/relationships}id"
)
if image_id and image_id in doc.part.rels:
image_part = doc.part.rels[image_id].target_part
if image_part in image_map and not has_drawing:
paragraph_content.append(image_map[image_part])
# Find imagedata element in VML
image_data = shape.find(".//{urn:schemas-microsoft-com:vml}imagedata")
if image_data is not None:
image_id = image_data.get("id") or image_data.get(
"{http://schemas.openxmlformats.org/officeDocument/2006/relationships}id"
)
if image_id and image_id in doc.part.rels:
image_part = doc.part.rels[image_id].target_part
if image_part in image_map and not has_drawing:
paragraph_content.append(image_map[image_part]) paragraph_content.append(image_map[image_part])
if run.text.strip(): if run.text.strip():
paragraph_content.append(run.text.strip()) paragraph_content.append(run.text.strip())