From a8a8b8e0f99f44392714cf3bfa139a7555d55ccc Mon Sep 17 00:00:00 2001 From: Christoph Auer Date: Tue, 6 May 2025 15:30:16 +0200 Subject: [PATCH] Fix garbage regex Signed-off-by: Christoph Auer --- docling/models/page_preprocessing_model.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/docling/models/page_preprocessing_model.py b/docling/models/page_preprocessing_model.py index 2088eb2f..6a1dcf19 100644 --- a/docling/models/page_preprocessing_model.py +++ b/docling/models/page_preprocessing_model.py @@ -28,8 +28,8 @@ class PagePreprocessingModel(BasePageModel): 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.SLASH_NUMBER_GARBAGE_RE = re.compile( - r"(?:/\w+\s+){5,}" - ) # Five or more "/token " sequences + r"(?:/\w+\s*){2,}" + ) # Two or more "/token " sequences def __call__( self, conv_res: ConversionResult, page_batch: Iterable[Page]