mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-08-02 15:32:30 +00:00
Code Issues Packages Projects Releases Wiki Activity

removed print statements

Browse Source 
Signed-off-by: Matteo Omenetti <omenetti.matteo@gmail.com>
This commit is contained in:
Matteo Omenetti 2025-01-23 07:38:39 -05:00
parent a59c03b27f
commit 849aa759c7
2 changed files with 7 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

21
docling/models/code_formula_model.py
View File

@ -142,7 +142,7 @@ class CodeFormulaModel(BaseItemAndImageEnrichmentModel):
) )
def _extract_code_language(self, input_string: str) -> Tuple[str, Optional[str]]: def _extract_code_language(self, input_string: str) -> Tuple[str, Optional[str]]:
"""Extracts a programming language from the beginning of a (possibly multi-line) string. """Extracts a programming language from the beginning of a string.
This function checks if the input string starts with a pattern of the form This function checks if the input string starts with a pattern of the form
``<_some_language_>``. If it does, it extracts the language string and returns ``<_some_language_>``. If it does, it extracts the language string and returns
@ -162,12 +162,6 @@ class CodeFormulaModel(BaseItemAndImageEnrichmentModel):
- The second element is the extracted language if a match is found; - The second element is the extracted language if a match is found;
otherwise, `None`. otherwise, `None`.
""" """
# Explanation of the regex:
# ^<_([^>]+)> : match "<_something>" at the start, capturing "something" (Group 1)
# \s* : optional whitespace
# (.*) : capture everything after that in Group 2
#
# We also use re.DOTALL so that the (.*) part can include newlines.
pattern = r"^<_([^>]+)_>\s*(.*)" pattern = r"^<_([^>]+)_>\s*(.*)"
match = re.match(pattern, input_string, flags=re.DOTALL) match = re.match(pattern, input_string, flags=re.DOTALL)
if match: if match:
@ -209,18 +203,17 @@ class CodeFormulaModel(BaseItemAndImageEnrichmentModel):
element_prov = element.prov[0] element_prov = element.prov[0]
expansion_factor = 0.03 # Adjust the expansion percentage as needed expansion_factor = 0.03
bbox = element_prov.bbox bbox = element_prov.bbox
width = bbox.r - bbox.l width = bbox.r - bbox.l
height = bbox.t - bbox.b height = bbox.t - bbox.b
# Create the expanded bounding box
expanded_bbox = BoundingBox( expanded_bbox = BoundingBox(
l=bbox.l - width * expansion_factor, # Expand left l=bbox.l - width * expansion_factor,
t=bbox.t + height * expansion_factor, # Expand top t=bbox.t + height * expansion_factor,
r=bbox.r + width * expansion_factor, # Expand right r=bbox.r + width * expansion_factor,
b=bbox.b - height * expansion_factor, # Expand bottom b=bbox.b - height * expansion_factor,
coord_origin=bbox.coord_origin, # Preserve coordinate origin coord_origin=bbox.coord_origin,
) )
page_ix = element_prov.page_no - 1 page_ix = element_prov.page_no - 1

1
tests/test_code_formula.py
View File

@ -49,7 +49,6 @@ def test_code_and_formula_conversion():
assert len(code_blocks) == 1 assert len(code_blocks) == 1
gt = 'public static void print() {\n System.out.println("Java Code");\n}' gt = 'public static void print() {\n System.out.println("Java Code");\n}'
print(gt)
predicted = code_blocks[0].text.strip() predicted = code_blocks[0].text.strip()
assert predicted == gt, f"mismatch in text {predicted=}, {gt=}" assert predicted == gt, f"mismatch in text {predicted=}, {gt=}"