changeset 3640:e54b2e843990

Xapian indexing: remove crappy num regex from WikiAnalyzer
author Thomas Waldmann <tw AT waldmann-edv DOT de>
date Sat, 24 May 2008 23:17:45 +0200
parents 776b338ccc2d
children 00af8e564f96
files MoinMoin/search/Xapian.py
diffstat 1 files changed, 0 insertions(+), 6 deletions(-) [+]
line wrap: on
line diff
--- a/MoinMoin/search/Xapian.py	Sat May 24 00:23:45 2008 +0200
+++ b/MoinMoin/search/Xapian.py	Sat May 24 23:17:45 2008 +0200
@@ -81,7 +81,6 @@
         r"(?P<company>\w+[&@]\w+)|" + # company names like AT&T and Excite@Home.
         r"(?P<email>\w+([.-]\w+)*@\w+([.-]\w+)*)|" +    # email addresses
         r"(?P<hostname>\w+(\.\w+)+)|" +                 # hostnames
-        r"(?P<num>(\w+[-/.,])*\w*\d\w*([-/.,]\w+)*)|" + # version numbers
         r"(?P<acronym>(\w\.)+)|" +          # acronyms: U.S.A., I.B.M., etc.
         r"(?P<word>\w+)",                   # words (including WikiWords)
         re.U)
@@ -138,11 +137,6 @@
                     for word in self.dot_re.split(m.group("hostname")):
                         yield (enc(word), m.start() + displ)
                         displ += len(word) + 1
-                elif m.group("num"):
-                    displ = 0
-                    for word in self.dot_re.split(m.group("num")):
-                        yield (enc(word), m.start() + displ)
-                        displ += len(word) + 1
                 elif m.group("word"):
                     word = m.group("word")
                     yield (enc(word), m.start())