From f2bd10e31bfaa5590aa823a4bdf0722cd4094917 Mon Sep 17 00:00:00 2001
From: calvin <calvin@e7d03fd6-7b0d-0410-9947-9c21f3af8025>
Date: Sat, 28 Oct 2000 16:15:56 +0000
Subject: [PATCH] fix tag parsing

git-svn-id: https://linkchecker.svn.sourceforge.net/svnroot/linkchecker/trunk/linkchecker@180 e7d03fd6-7b0d-0410-9947-9c21f3af8025
---
 FAQ                  |  4 ++--
 debian/changelog     |  6 ++++--
 linkcheck/UrlData.py | 32 ++++++++++++++++----------------
 3 files changed, 22 insertions(+), 20 deletions(-)

diff --git a/FAQ b/FAQ
index 8fce930d..dcf63a80 100644
--- a/FAQ
+++ b/FAQ
@@ -1,11 +1,11 @@
 Q: The link "mailto:john@company.com?subject=Hello John" is reported
    as an error.
 A: You have to quote special characters (e.g. spaces) in the subject field.
-   The correct link should be "mailto:...?subject=Hello%20John!"
+   The correct link should be "mailto:...?subject=Hello%20John"
    Unfortunately browsers like IE and Netscape do not enforce this.
 
 
 Q: I have a pretty large site to check. How can I restrict link checking
-   to only check my own pages?
+   to check only my own pages?
 A: Look at the options --intern, --extern, --strict and --recursion-level.
 
diff --git a/debian/changelog b/debian/changelog
index f51329f4..d66e20d9 100644
--- a/debian/changelog
+++ b/debian/changelog
@@ -3,11 +3,13 @@ linkchecker (1.2.6) unstable; urgency=low
   * made a FAQ
   * configuration changes: distutils are now required; because of that
     we have no more .tmpl files
-  * correct db name in create.sql
+  * fix db name in create.sql
   * added timeoutsocket.py to supply a timeout for socket.connect()
     calls
+  * fix tag parsing when a quoted tag attribute value contains a >
+    character
 
- -- Bastian Kleineidam <calvin@users.sourceforge.net>  Mon, 16 Oct 2000 14:55:51 +0200
+ -- Bastian Kleineidam <calvin@users.sourceforge.net>  Sat, 28 Oct 2000 17:52:53 +0200
 
 linkchecker (1.2.5) unstable; urgency=low
 
diff --git a/linkcheck/UrlData.py b/linkcheck/UrlData.py
index 7644d301..ed67b1ca 100644
--- a/linkcheck/UrlData.py
+++ b/linkcheck/UrlData.py
@@ -33,22 +33,22 @@ except ImportError:
     pass
 
 _linkMatcher = r"""
-    (?i)          # case insensitive
-    <             # open tag
-    \s*           # whitespace
-    %s            # tag name
-    \s+           # whitespace
-    [^>]*?        # skip leading attributes
-    %s            # attrib name
-    \s*           # whitespace
-    =             # equal sign
-    \s*           # whitespace
-    (?P<value>    # attribute value
-     ".*?" |      # in double quotes
-     '.*?' |      # in single quotes
-     [^\s>]+)     # unquoted
-    [^>]*         # skip trailing attributes
-    >             # close tag
+    (?i)           # case insensitive
+    <              # open tag
+    \s*            # whitespace
+    %s             # tag name
+    \s+            # whitespace
+    [^>]*?         # skip leading attributes
+    %s             # attrib name
+    \s*            # whitespace
+    =              # equal sign
+    \s*            # whitespace
+    (?P<value>     # attribute value
+     ".*?" |       # in double quotes
+     '.*?' |       # in single quotes
+     [^\s>]+)      # unquoted
+    ([^">]|".*?")* # skip trailing attributes
+    >              # close tag
     """
 
 LinkPatterns = (