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

word extractor cleans. (#20926)

Browse Source 
Signed-off-by: zhanluxianshen <zhanluxianshen@163.com>
This commit is contained in:
湛露先生
2025-08-08 09:37:51 +08:00
committed by GitHub
parent 6f80fb72cb
commit fd536a943a
1 changed files with 2 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files

19
api/core/rag/extractor/word_extractor.py
View File

@@ -62,7 +62,7 @@ class WordExtractor(BaseExtractor):
def extract(self) -> list[Document]:
"""Load given path as single page."""
content = self.parse_docx(self.file_path, "storage")
content = self.parse_docx(self.file_path)
return [
Document(
page_content=content,
@@ -189,23 +189,8 @@ class WordExtractor(BaseExtractor):
paragraph_content.append(run.text)
return "".join(paragraph_content).strip()
def _parse_paragraph(self, paragraph, image_map):
paragraph_content = []
for run in paragraph.runs:
if run.element.xpath(".//a:blip"):
for blip in run.element.xpath(".//a:blip"):
embed_id = blip.get("{http://schemas.openxmlformats.org/officeDocument/2006/relationships}embed")
if embed_id:
rel_target = run.part.rels[embed_id].target_ref
if rel_target in image_map:
paragraph_content.append(image_map[rel_target])
if run.text.strip():
paragraph_content.append(run.text.strip())
return " ".join(paragraph_content) if paragraph_content else ""
def parse_docx(self, docx_path, image_folder):
def parse_docx(self, docx_path):
doc = DocxDocument(docx_path)
os.makedirs(image_folder, exist_ok=True)
content = []