[Pywikipedia-l] SVN: [5416] trunk/pywikipedia

[nicdumz at svn.wikimedia.org]

Revision: 5416
Author:   nicdumz
Date:     2008-05-20 21:34:18 +0000 (Tue, 20 May 2008)

Log Message:
-----------
* Fixing #1967922 "cosmetic_change fails to get title ?"

* Introducing InvalidTitle to be used instead of Error. The problem, if we raise wikipedia.Error, and catch wikipedia.Error, is that we don't really know what we are catching : Error is the baseclass for all our wikipedia defined exceptions, and "except Error:" catches PageNotSaved, NoPage, or whatever other exceptions. It's poor, we don't want to do this :)

Modified Paths:
--------------
    trunk/pywikipedia/cosmetic_changes.py
    trunk/pywikipedia/wikipedia.py

Modified: trunk/pywikipedia/cosmetic_changes.py
===================================================================
--- trunk/pywikipedia/cosmetic_changes.py	2008-05-20 20:22:19 UTC (rev 5415)
+++ trunk/pywikipedia/cosmetic_changes.py	2008-05-20 21:34:18 UTC (rev 5416)
@@ -181,7 +181,10 @@
                 # [[page_title|link_text]]trailing_chars
                 # We only work on namespace 0 because pipes and linktrails work
                 # differently for images and categories.
-                page = wikipedia.Page(self.site, titleWithSection)
+                try:
+                    page = wikipedia.Page(self.site, titleWithSection)
+                except wikipedia.InvalidTitle:
+                    return match.group()
                 if page.namespace() == 0:
                     # Replace underlines by spaces, also multiple underlines
                     titleWithSection = re.sub('_+', ' ', titleWithSection)

Modified: trunk/pywikipedia/wikipedia.py
===================================================================
--- trunk/pywikipedia/wikipedia.py	2008-05-20 20:22:19 UTC (rev 5415)
+++ trunk/pywikipedia/wikipedia.py	2008-05-20 21:34:18 UTC (rev 5416)
@@ -167,6 +167,9 @@
 class IsNotRedirectPage(Error):
     """Page is not a redirect page"""
 
+class InvalidTitle(Error):
+    """Invalid page title"""
+
 class LockedPage(Error):
     """Page is locked"""
 
@@ -328,7 +331,7 @@
             try:
                 t = url2unicode(t, site = insite, site2 = site)
             except UnicodeDecodeError:
-                raise Error(u'Bad page title : %s' % t)
+                raise InvalidTitle(u'Bad page title : %s' % t)
 
             # Normalize unicode string to a NFC (composed) format to allow
             # proper string comparisons. According to
@@ -354,7 +357,7 @@
                 self._namespace = defaultNamespace
 
             if not t:
-                raise Error(u"Invalid title '%s'" % title )
+                raise InvalidTitle(u"Invalid title '%s'" % title )
 
             self._namespace = defaultNamespace
             #
@@ -1069,7 +1072,7 @@
                 output(u"DBG> invalid <li> item in Whatlinkshere: %s" % link)
             try:
                 p = Page(self.site(), title)
-            except Error:
+            except InvalidTitle:
                 output(u"DBG> Whatlinkshere:%s contains invalid link to %s"
                        % (self.title(), title))
                 continue
@@ -1564,7 +1567,7 @@
                 output(
     u"ERROR: link from %s to [[%s:%s]] contains invalid unicode reference?!"
                         % (self.aslink(), newSite, newTitle))
-            except Error:
+            except InvalidTitle:
                 output(
     u"ERROR: link from %s to [[%s:%s]] is improperly formatted?"
                         % (self.aslink(), newSite, newTitle))
@@ -1633,7 +1636,7 @@
             if not self.site().isInterwikiLink(title):
                 try:
                     page = Page(self.site(), title)
-                except Error:
+                except InvalidTitle:
                     output(u"Page %s contains invalid link to [[%s]]."
                            % (self.title(), title))
                     continue
@@ -1740,7 +1743,7 @@
                     continue
                 try:
                     name = Page(self.site(), name).title()
-                except Error:
+                except InvalidTitle:
                     if name.strip():
                         output(
                             u"Page %s contains invalid template name {{%s}}."
@@ -2613,7 +2616,7 @@
         for match in lineR.finditer(titleList):
             try:
                 yield Page(self.site(), match.group('title'))
-            except Error:
+            except InvalidTitle:
                 output(
         u"Image description page %s contains invalid reference to [[%s]]."
                     % (self.title(), match.group('title')))
@@ -3247,7 +3250,7 @@
             site = insite.getSite(code = lang)
             try:
                 result[site] = Page(site, pagetitle, insite = insite)
-            except Error:
+            except InvalidTitle:
                 output(
         u"[getLanguageLinks] Text contains invalid interwiki link [[%s:%s]]."
                            % (lang, pagetitle))