Fixed content_types handling of content sniffing so that html can still be

recognized when formal doctype dtd declarations are used. We will need to revisit this sometime - we are probably asking for trouble by trying to make too many things automatic as far as content-type detection...

Fixed content_types handling of content sniffing so that html can still be
recognized when formal doctype dtd declarations are used. We will need to revisit this sometime - we are probably asking for trouble by trying to make too many things automatic as far as content-type detection...
a4036ced · e7d87a92 · a4036ced
Commit a4036ced authored Nov 01, 1999 by
Hide whitespace changes
Inline Side-by-side

Showing with 8 additions and 4 deletions

lib/python/OFS/content_types.py lib/python/OFS/content_types.py +8 -4

No files found.
--- a/lib/python/OFS/content_types.py
+++ b/lib/python/OFS/content_types.py
@@ -83,7 +83,7 @@
 # 
 ##############################################################################
 """A utility module for content-type handling."""
-__version__='$Revision: 1.7 $'[11:-2]
+__version__='$Revision: 1.8 $'[11:-2]

 src="""
 htm, html: text/html
@@ -101,7 +101,7 @@ tar: application/x-tar
 zip: application/x-zip
 """

-from string import split, strip, lower
+from string import split, strip, lower, find
 import ts_regex, mimetypes

 content_type={}
@@ -113,9 +113,13 @@ for l in filter(lambda s: s and s[:1] != '#', map(strip, split(src,'\n'))):


 find_binary=ts_regex.compile('[\0-\7]').search
-html_re=ts_regex.compile('<html>', ts_regex.casefold)
+
 def text_type(s):
-    return "text/" + (html_re.search(s) >= 0 and 'html' or 'plain')
+    # Yuk. See if we can figure out the type by content.
+    if (lower(strip(s)[:6]) == '<html>' or find(s, '</') > 0):
+        return 'text/html'
+    return 'text/plain'
+


 # This gives us a hook to add content types that