Author: andar
Revision: 5251
Log:
Fix showing non-utf8 encoded torrents in add torrent dialog -- this
adds an additional dependency on chardet.
Diff:
Modified: branches/1.1.0_RC/ChangeLog
===================================================================
--- branches/1.1.0_RC/ChangeLog 2009-05-09 03:42:39 UTC (rev 5250)
+++ branches/1.1.0_RC/ChangeLog 2009-05-09 17:46:13 UTC (rev 5251)
@@ -5,6 +5,8 @@
==== GtkUI ====
* Fix high cpu usage when displaying speeds in titlebar
+ * Fix showing non-utf8 encoded torrents in add torrent dialog -- this adds
+ an additional dependency on chardet.
==== WebUI ====
* Fix starting when -l option is used
Modified: branches/1.1.0_RC/README
===================================================================
--- branches/1.1.0_RC/README 2009-05-09 03:42:39 UTC (rev 5250)
+++ branches/1.1.0_RC/README 2009-05-09 17:46:13 UTC (rev 5251)
@@ -41,7 +41,8 @@
python-gtk2 python-notify librsvg2-common python-xdg python-support \
subversion libboost-dev libboost-python-dev libboost-iostreams-dev \
libboost-thread-dev libboost-date-time-dev libboost-filesystem-dev \
- libboost-serialization-dev libssl-dev zlib1g-dev python-setuptools
+ libboost-serialization-dev libssl-dev zlib1g-dev python-setuptools \
+ python-chardet
The names of the packages may vary depending on your OS / distro.
Modified: branches/1.1.0_RC/deluge/ui/common.py
===================================================================
--- branches/1.1.0_RC/deluge/ui/common.py 2009-05-09 03:42:39 UTC (rev
5250)
+++ branches/1.1.0_RC/deluge/ui/common.py 2009-05-09 17:46:13 UTC (rev
5251)
@@ -1,9 +1,9 @@
-#!/usr/bin/env python
# -*- coding: utf-8 -*-
#
# deluge/ui/common.py
#
# Copyright (C) Damien Churchill 2008 <[email protected]>
+# Copyright (C) Andrew Resch 2009 <[email protected]>
#
# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
@@ -32,9 +32,6 @@
# statement from all source files in the program, then also delete it here.
#
-#
-
-
import os
try:
from hashlib import sha1 as sha
@@ -46,6 +43,28 @@
from deluge.log import LOG as log
import deluge.configmanager
+def decode_string(s, encoding="utf8"):
+ """
+ Decodes a string and re-encodes it in utf8. If it cannot decode using
+ `:param:encoding` then it will try to detect the string encoding and
+ decode it.
+
+ :param s: str to decode
+ :param encoding: str, the encoding to use in the decoding
+
+ """
+
+ try:
+ s = s.decode(encoding).encode("utf8")
+ except UnicodeDecodeError:
+ try:
+ import chardet
+ except ImportError:
+ s = s.decode(encoding, "replace").encode("utf8")
+ else:
+ s = s.decode(chardet.detect(s)["encoding"]).encode("utf8")
+ return s
+
class TorrentInfo(object):
def __init__(self, filename):
# Get the torrent data from the torrent file
@@ -65,29 +84,31 @@
elif "codepage" in self.__m_metadata:
self.encoding = str(self.__m_metadata["codepage"])
+ self.__m_name = decode_string(self.__m_metadata["info"]["name"])
+
# Get list of files from torrent info
self.__m_files = []
if self.__m_metadata["info"].has_key("files"):
prefix = ""
if len(self.__m_metadata["info"]["files"]) > 1:
- prefix =
self.__m_metadata["info"]["name"].decode(self.encoding,
"replace").encode("utf8")
+ prefix = self.__m_name
for f in self.__m_metadata["info"]["files"]:
self.__m_files.append({
- 'path': os.path.join(prefix,
*f["path"]).decode(self.encoding, "replace").encode("utf8"),
+ 'path': decode_string(os.path.join(prefix, *f["path"])),
'size': f["length"],
'download': True
})
else:
self.__m_files.append({
- "path":
self.__m_metadata["info"]["name"].decode(self.encoding,
"replace").encode("utf8"),
+ "path": self.__m_name,
"size": self.__m_metadata["info"]["length"],
"download": True
})
@property
def name(self):
- return self.__m_metadata["info"]["name"].decode(self.encoding,
"replace").encode("utf8")
+ return self.__m_name
@property
def info_hash(self):
Modified: trunk/README
===================================================================
--- trunk/README 2009-05-09 03:42:39 UTC (rev 5250)
+++ trunk/README 2009-05-09 17:46:13 UTC (rev 5251)
@@ -54,6 +54,7 @@
pygtk >= 2.10
librsvg
xdg-utils
+ chardet
Web:
mako
Modified: trunk/deluge/ui/common.py
===================================================================
--- trunk/deluge/ui/common.py 2009-05-09 03:42:39 UTC (rev 5250)
+++ trunk/deluge/ui/common.py 2009-05-09 17:46:13 UTC (rev 5251)
@@ -1,9 +1,9 @@
-#!/usr/bin/env python
# -*- coding: utf-8 -*-
#
# deluge/ui/common.py
#
# Copyright (C) Damien Churchill 2008 <[email protected]>
+# Copyright (C) Andrew Resch 2009 <[email protected]>
#
# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
@@ -24,18 +24,39 @@
import os
import sys
+import urlparse
try:
from hashlib import sha1 as sha
except ImportError:
from sha import sha
-import urlparse
-
from deluge import bencode
from deluge.log import LOG as log
import deluge.configmanager
+def decode_string(s, encoding="utf8"):
+ """
+ Decodes a string and re-encodes it in utf8. If it cannot decode using
+ `:param:encoding` then it will try to detect the string encoding and
+ decode it.
+
+ :param s: str to decode
+ :param encoding: str, the encoding to use in the decoding
+
+ """
+
+ try:
+ s = s.decode(encoding).encode("utf8")
+ except UnicodeDecodeError:
+ try:
+ import chardet
+ except ImportError:
+ s = s.decode(encoding, "replace").encode("utf8")
+ else:
+ s = s.decode(chardet.detect(s)["encoding"]).encode("utf8")
+ return s
+
class TorrentInfo(object):
def __init__(self, filename):
# Get the torrent data from the torrent file
@@ -52,16 +73,22 @@
self.encoding = "UTF-8"
if "encoding" in self.__m_metadata:
self.encoding = self.__m_metadata["encoding"]
+ elif "codepage" in self.__m_metadata:
+ self.encoding = str(self.__m_metadata["codepage"])
+ # We try to decode based on the encoding found and if we can't, we try
+ # to detect the encoding and decode that
+ self.__m_name = decode_string(self.__m_metadata["info"]["name"],
self.encoding)
+
# Get list of files from torrent info
paths = {}
if self.__m_metadata["info"].has_key("files"):
prefix = ""
if len(self.__m_metadata["info"]["files"]) > 1:
- prefix =
self.__m_metadata["info"]["name"].decode(self.encoding,
"replace").encode("utf8")
+ prefix = self.__m_name
for index, f in enumerate(self.__m_metadata["info"]["files"]):
- path = os.path.join(prefix, *f["path"]).decode(self.encoding,
"replace").encode("utf8")
+ path = decode_string(os.path.join(prefix, *f["path"]))
f["index"] = index
paths[path] = f
@@ -75,24 +102,24 @@
self.__m_files_tree = file_tree.get_tree()
else:
self.__m_files_tree = {
- self.__m_metadata["info"]["name"].decode(self.encoding,
"replace").encode("utf8"): (self.__m_metadata["info"]["length"], True)
+ self.__m_name: (self.__m_metadata["info"]["length"], True)
}
self.__m_files = []
if self.__m_metadata["info"].has_key("files"):
prefix = ""
if len(self.__m_metadata["info"]["files"]) > 1:
- prefix =
self.__m_metadata["info"]["name"].decode(self.encoding,
"replace").encode("utf8")
+ prefix = self.__m_name
for f in self.__m_metadata["info"]["files"]:
self.__m_files.append({
- 'path': os.path.join(prefix,
*f["path"]).decode(self.encoding, "replace").encode("utf8"),
+ 'path': decode_string(os.path.join(prefix, *f["path"])),
'size': f["length"],
'download': True
})
else:
self.__m_files.append({
- "path":
self.__m_metadata["info"]["name"].decode(self.encoding,
"replace").encode("utf8"),
+ "path": self.__m_name,
"size": self.__m_metadata["info"]["length"],
"download": True
})
@@ -108,7 +135,7 @@
@property
def name(self):
- return
self.__m_metadata["info"]["name"].decode(self.encoding).encode("utf8")
+ return self.__m_name
@property
def info_hash(self):
--~--~---------~--~----~------------~-------~--~----~
You received this message because you are subscribed to the Google Groups
"deluge-commit" group.
To post to this group, send email to [email protected]
To unsubscribe from this group, send email to
[email protected]
For more options, visit this group at
http://groups.google.com/group/deluge-commit?hl=en
-~----------~----~----~----~------~----~------~--~---
