[Pywikipedia-l] SVN: [6305] trunk/pywikipedia/fixes.py

[wikipedian at svn.wikimedia.org]

Revision: 6305
Author:   wikipedian
Date:     2009-01-27 19:58:05 +0000 (Tue, 27 Jan 2009)

Log Message:
-----------
fix ISBNs which have minus signs, em dashes, etc. as separators.

Modified Paths:
--------------
    trunk/pywikipedia/fixes.py

Modified: trunk/pywikipedia/fixes.py
===================================================================
--- trunk/pywikipedia/fixes.py	2009-01-27 13:57:16 UTC (rev 6304)
+++ trunk/pywikipedia/fixes.py	2009-01-27 19:58:05 UTC (rev 6305)
@@ -388,12 +388,12 @@
             (r'ISBN: (\d+)', r'ISBN \1'),
             # superfluous word "number"
             (r'ISBN( number| no\.?| No\.?|-Nummer|-Nr\.):? (\d+)', r'ISBN \2'),
-            # Spaces, dashes, or dots instead of hyphens as separators,
-            # or spaces between digits and separators.
+            # Space, minus, dot,  hypen, en dash, em dash, etc. instead of
+            # hyphen-minus as separator, or spaces between digits and separators.
             # Note that these regular expressions also match valid ISBNs, but
             # these won't be changed.
-            (r'ISBN (978|979) *[\- –\.] *(\d+) *[\- –\.] *(\d+) *[\- –\.] *(\d+) *[\- –\.] *(\d)(?!\d)', r'ISBN \1-\2-\3-\4-\5'), # ISBN-13
-            (r'ISBN (\d+) *[\- –\.] *(\d+) *[\- –\.] *(\d+) *[\- –\.] *(\d|X|x)(?!\d)', r'ISBN \1-\2-\3-\4'), # ISBN-10
+            (ur'ISBN (978|979) *[\- −\.‐-―] *(\d+) *[\- −\.‐-―] *(\d+) *[\- −\.‐-―] *(\d+) *[\- −\.‐-―] *(\d)(?!\d)', r'ISBN \1-\2-\3-\4-\5'), # ISBN-13
+            (ur'ISBN (\d+) *[\- −\.‐-―] *(\d+) *[\- −\.‐-―] *(\d+) *[\- −\.‐-―] *(\d|X|x)(?!\d)', r'ISBN \1-\2-\3-\4'), # ISBN-10
             # missing space before ISBN-10 or before ISBN-13,
             # or non-breaking space.
             (r'ISBN(| | )((\d(-?)){12}\d|(\d(-?)){9}[\dXx])', r'ISBN \2'),