mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-07-26 20:14:47 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fix garbage regex

Browse Source 
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
This commit is contained in:
Christoph Auer 2025-05-06 15:30:16 +02:00
parent 95d2f5fd92
commit a8a8b8e0f9
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
docling/models/page_preprocessing_model.py
View File

@ -28,8 +28,8 @@ class PagePreprocessingModel(BasePageModel):
self.SLASH_G_RE = re.compile(r"(?:/G\d+){2,}") self.SLASH_G_RE = re.compile(r"(?:/G\d+){2,}")
self.FRAG_RE = re.compile(r"\b[A-Za-z](?:/[a-z]{1,3}\.[a-z]{1,3}){2,}\b") self.FRAG_RE = re.compile(r"\b[A-Za-z](?:/[a-z]{1,3}\.[a-z]{1,3}){2,}\b")
self.SLASH_NUMBER_GARBAGE_RE = re.compile( self.SLASH_NUMBER_GARBAGE_RE = re.compile(
r"(?:/\w+\s+){5,}" r"(?:/\w+\s*){2,}"
) # Five or more "/token " sequences ) # Two or more "/token " sequences
def __call__( def __call__(
self, conv_res: ConversionResult, page_batch: Iterable[Page] self, conv_res: ConversionResult, page_batch: Iterable[Page]