Issue #22165: SimpleHTTPRequestHandler now supports undecodable file names.

This commit is contained in:
Serhiy Storchaka 2014-08-17 08:22:11 +03:00
parent 402df0975c
commit cb5bc408ad
3 changed files with 36 additions and 4 deletions

View file

@ -747,7 +747,12 @@ class SimpleHTTPRequestHandler(BaseHTTPRequestHandler):
return None
list.sort(key=lambda a: a.lower())
r = []
displaypath = html.escape(urllib.parse.unquote(self.path))
try:
displaypath = urllib.parse.unquote(self.path,
errors='surrogatepass')
except UnicodeDecodeError:
displaypath = urllib.parse.unquote(path)
displaypath = html.escape(displaypath)
enc = sys.getfilesystemencoding()
title = 'Directory listing for %s' % displaypath
r.append('<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01//EN" '
@ -769,9 +774,11 @@ class SimpleHTTPRequestHandler(BaseHTTPRequestHandler):
displayname = name + "@"
# Note: a link to a directory displays with @ and links with /
r.append('<li><a href="%s">%s</a></li>'
% (urllib.parse.quote(linkname), html.escape(displayname)))
% (urllib.parse.quote(linkname,
errors='surrogatepass'),
html.escape(displayname)))
r.append('</ul>\n<hr>\n</body>\n</html>\n')
encoded = '\n'.join(r).encode(enc)
encoded = '\n'.join(r).encode(enc, 'surrogateescape')
f = io.BytesIO()
f.write(encoded)
f.seek(0)
@ -794,7 +801,11 @@ class SimpleHTTPRequestHandler(BaseHTTPRequestHandler):
path = path.split('#',1)[0]
# Don't forget explicit trailing slash when normalizing. Issue17324
trailing_slash = path.rstrip().endswith('/')
path = posixpath.normpath(urllib.parse.unquote(path))
try:
path = urllib.parse.unquote(path, errors='surrogatepass')
except UnicodeDecodeError:
path = urllib.parse.unquote(path)
path = posixpath.normpath(path)
words = path.split('/')
words = filter(None, words)
path = os.getcwd()