commit d09def36d52af3e087433eb67c49da633436c602
author Georg Brandl <georg@python.org> Thu Mar 09 13:27:14 2006 +0000
committer Georg Brandl <georg@python.org> Thu Mar 09 13:27:14 2006 +0000
tree f9498fe321b3156583d269362e26ef6523b18ec0
parent 8f4b4db676c10239543dd4bbdf99dacdd6468bd4

Bug #1442874: handle "<!>", the empty SGML comment

Lib/markupbase.py

diff --git a/Lib/markupbase.py b/Lib/markupbase.py
index 3d00a74..85b07a2 100644
--- a/Lib/markupbase.py
+++ b/Lib/markupbase.py
@@ -76,13 +76,16 @@
         rawdata = self.rawdata
         j = i + 2
         assert rawdata[i:j] == "<!", "unexpected call to parse_declaration"
+        if rawdata[j:j+1] == ">":
+            # the empty comment <!>
+            return j + 1
         if rawdata[j:j+1] in ("-", ""):
             # Start of comment followed by buffer boundary,
             # or just a buffer boundary.
             return -1
         # A simple, practical version could look like: ((name|stringlit) S*) + '>'
         n = len(rawdata)
-        if rawdata[j:j+1] == '--': #comment
+        if rawdata[j:j+2] == '--': #comment
             # Locate --.*-- as the body of the comment
             return self.parse_comment(i)
         elif rawdata[j] == '[': #marked section

Lib/test/test_htmlparser.py

diff --git a/Lib/test/test_htmlparser.py b/Lib/test/test_htmlparser.py
index 4cb87df..54b90cd 100755
--- a/Lib/test/test_htmlparser.py
+++ b/Lib/test/test_htmlparser.py
@@ -115,7 +115,7 @@
 <Img sRc='Bar' isMAP>sample
 text
 &#x201C;
-<!--comment2a-- --comment2b-->
+<!--comment2a-- --comment2b--><!>
 </Html>
 """, [
     ("data", "\n"),