mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-07-27 04:24:45 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge 990ecac0bc into 1985841a19

Browse Source
This commit is contained in:
mohammed ahmed 2025-07-25 13:01:36 +02:00 committed by GitHub
commit 5512174826
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 4 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
docling/models/tesseract_ocr_cli_model.py
View File

@ -320,6 +320,8 @@ class TesseractOcrCliModel(BaseOcrModel):
def _parse_orientation(df_osd: pd.DataFrame) -> int: def _parse_orientation(df_osd: pd.DataFrame) -> int:
orientations = df_osd.loc[df_osd["key"] == "Orientation in degrees"].value.tolist() # For strictly optimal performance with invariant dataframe format:
orientation = parse_tesseract_orientation(orientations[0].strip()) mask = df_osd["key"].to_numpy() == "Orientation in degrees"
orientation_val = df_osd["value"].to_numpy()[mask][0]
orientation = parse_tesseract_orientation(orientation_val.strip())
return orientation return orientation