[FIX] Date parser improved for Europresse corpus.

7dae83bd · Administrator · 4a641c04 · 7dae83bd
Commit 7dae83bd authored Jan 07, 2015 by Administrator
Hide whitespace changes
Inline Side-by-side

Showing with 1 addition and 1 deletion

EuropressFileParser.py parsing/FileParsers/EuropressFileParser.py +1 -1

No files found.
--- a/parsing/FileParsers/EuropressFileParser.py
+++ b/parsing/FileParsers/EuropressFileParser.py
@@ -54,7 +54,7 @@ class EuropressFileParser(FileParser):
                   if isinstance(text, bytes):
                       text = text.decode(encoding)

-                   format_date_fr = re.compile('\d+\s*\w+\s+\d{4}', re.UNICODE)
+                   format_date_fr = re.compile('\d*\s*\w+\s+\d{4}', re.UNICODE)
                   test_date_fr = format_date_fr.match(text)
                   
                   format_date_en = re.compile('\w+\s+\d+,\s+\d{4}', re.UNICODE)