mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-07-27 20:44:16 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: ParserError EOF inside string (#470) (#472)

Browse Source 
Signed-off-by: guglie <gdguglie@gmail.com>
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
This commit is contained in:
guglie 2024-12-03 11:21:18 +01:00 committed by GitHub
parent a01cedbb69
commit a7e3f713bb
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 os import os
@ -96,7 +97,7 @@ 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), quoting=csv.QUOTE_NONE, sep="\t")
# Display the dataframe (optional) # Display the dataframe (optional)
# _log.info("df: ", df.head()) # _log.info("df: ", df.head())