From ca94ff3410ee2536bffd101d9851f8a57bde80e7 Mon Sep 17 00:00:00 2001 From: Matteo-Omenetti Date: Mon, 10 Mar 2025 11:32:59 +0100 Subject: [PATCH] new version code formula model Signed-off-by: Matteo-Omenetti --- docling/models/code_formula_model.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/docling/models/code_formula_model.py b/docling/models/code_formula_model.py index 1a0f0bf0..3694ecbe 100644 --- a/docling/models/code_formula_model.py +++ b/docling/models/code_formula_model.py @@ -124,7 +124,7 @@ class CodeFormulaModel(BaseItemAndImageEnrichmentModel): repo_id="ds4sd/CodeFormula", force_download=force, local_dir=local_dir, - revision="v1.0.1", + revision="v1.0.2", ) return Path(download_path) @@ -175,7 +175,7 @@ class CodeFormulaModel(BaseItemAndImageEnrichmentModel): - The second element is the extracted language if a match is found; otherwise, `None`. """ - pattern = r"^<_([^>]+)_>\s*(.*)" + pattern = r"^<_([^_>]+)_>\s(.*)" match = re.match(pattern, input_string, flags=re.DOTALL) if match: language = str(match.group(1)) # the captured programming language