fix: ParserError EOF inside string (DS4SD#470) (DS4SD#472)

Signed-off-by: guglie <[email protected]>
lucas-morin · Dec 10, 2024 · d1244a5 · d1244a5
1 parent 756005e
commit d1244a5
Showing 1 changed file with 2 additions and 1 deletion.
diff --git a/docling/models/tesseract_ocr_cli_model.py b/docling/models/tesseract_ocr_cli_model.py
@@ -1,3 +1,4 @@
+import csv
 import io
 import logging
 import os
@@ -96,7 +97,7 @@ def _run_tesseract(self, ifilename: str):
         # _log.info(decoded_data)
 
         # 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)
         # _log.info("df: ", df.head())