mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-08-02 07:22:14 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: tesseract_ocr_cli csv parsing fails when text contains single quotes

Browse Source
This commit is contained in:
Gaspard Petit 2024-12-02 01:59:17 -05:00
parent 8ccb3c6db6
commit 2f6f6c1b41
1 changed files with 2 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
docling/models/tesseract_ocr_cli_model.py
View File

@ -1,3 +1,4 @@
import csv
import io import io
import logging import logging
import tempfile import tempfile
@ -95,7 +96,7 @@ class TesseractOcrCliModel(BaseOcrModel):
# _log.info(decoded_data) # _log.info(decoded_data)
# Read the TSV file generated by Tesseract # Read the TSV file generated by Tesseract
df = pd.read_csv(io.StringIO(decoded_data), sep="\t") df = pd.read_csv(io.StringIO(decoded_data), sep="\t", quoting=csv.QUOTE_NONE)
# Display the dataframe (optional) # Display the dataframe (optional)
# _log.info("df: ", df.head()) # _log.info("df: ", df.head())