kanshan/dify
1
0
Fork 0
mirror of https://github.com/langgenius/dify.git synced 2026-02-21 10:24:41 +08:00
Code Issues Actions 4 Packages Projects Releases Wiki Activity

clean rag word_extractor. (#19397)
Some checks failed
Build and Push API & Web / build (api, DIFY_API_IMAGE_NAME, linux/amd64, build-api-amd64) (push) Has been cancelled
Details
Build and Push API & Web / build (api, DIFY_API_IMAGE_NAME, linux/arm64, build-api-arm64) (push) Has been cancelled
Details
Build and Push API & Web / build (web, DIFY_WEB_IMAGE_NAME, linux/amd64, build-web-amd64) (push) Has been cancelled
Details
Build and Push API & Web / build (web, DIFY_WEB_IMAGE_NAME, linux/arm64, build-web-arm64) (push) Has been cancelled
Details
Build and Push API & Web / create-manifest (api, DIFY_API_IMAGE_NAME, merge-api-images) (push) Has been cancelled
Details
Build and Push API & Web / create-manifest (web, DIFY_WEB_IMAGE_NAME, merge-web-images) (push) Has been cancelled
Details

Browse Source 
Signed-off-by: zhanluxianshen <zhanluxianshen@163.com>
This commit is contained in:
湛露先生 2025-05-09 16:39:16 +08:00 committed by GitHub
parent 56cff485d0
commit 1119790b02
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 3 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
api/core/rag/extractor/word_extractor.py
View File

@ -76,8 +76,7 @@ class WordExtractor(BaseExtractor):
parsed = urlparse(url)
return bool(parsed.netloc) and bool(parsed.scheme)
def _extract_images_from_docx(self, doc, image_folder):
os.makedirs(image_folder, exist_ok=True)
def _extract_images_from_docx(self, doc):
image_count = 0
image_map = {}
@ -210,7 +209,7 @@ class WordExtractor(BaseExtractor):
content = []
image_map = self._extract_images_from_docx(doc, image_folder)
image_map = self._extract_images_from_docx(doc)
hyperlinks_url = None
url_pattern = re.compile(r"http://[^\s+]+//|https://[^\s+]+")
@ -225,7 +224,7 @@ class WordExtractor(BaseExtractor):
xml = ElementTree.XML(run.element.xml)
x_child = [c for c in xml.iter() if c is not None]
for x in x_child:
if x_child is None:
if x is None:
continue
if x.tag.endswith("instrText"):
if x.text is None: