Attached below is a patch to add UTF-8 support to jack 3.1.1.
I've tested this in a Latin1 and UTF-8 locale with OGG; MP3
hasn't been tested.
--
Martin Michlmayr
http://www.cyrius.com/
diff -urN site-packages.orig/jack_config.py site-packages/jack_config.py
--- site-packages.orig/jack_config.py 2005-04-22 21:31:37.000000000 +0100
+++ site-packages/jack_config.py 2005-04-23 00:16:38.000000000 +0100
@@ -177,15 +177,13 @@
'type': types.StringType,
'val': "",
'usage': "convert file names using a python method",
- 'doc': r"""an example which converts to lowercase, even with non-ascii
charsets (you have to specify the charset):
".decode(charset).lower().encode(charset)" """,
+ 'doc': r"""an example which converts to lowercase, even with non-ascii
charsets: ".lower()" """,
'long': 'AUTO',
},
'charset': {
'type': types.StringType,
- 'val': "latin-1",
- 'usage': "charset of freedb data",
- 'doc': "examples: latin-1 ascii, utf-8, ...",
- 'long': 'AUTO',
+ 'val': "utf-8",
+ # for backwards compatibility only; now ignored.
},
'unusable_chars': {
'type': types.ListType,
Binary files site-packages.orig/jack_config.pyc and
site-packages/jack_config.pyc differ
diff -urN site-packages.orig/jack_display.py site-packages/jack_display.py
--- site-packages.orig/jack_display.py 2005-04-22 21:31:37.000000000 +0100
+++ site-packages/jack_display.py 2005-04-22 22:50:51.000000000 +0100
@@ -63,9 +63,9 @@
if jack_freedb.names_available:
jack_term.tmod.extra_lines = jack_term.tmod.extra_lines + 1
if jack_term.term_type == "curses":
- discname = jack_tag.track_names[0][0] + " - " +
jack_tag.track_names[0][1]
+ discname = jack_tag.locale_names[0][0] + " - " +
jack_tag.locale_names[0][1]
else:
- options_string = center_line(jack_tag.track_names[0][0] + " - " +
jack_tag.track_names[0][1], fill = "- ", fill_r = " -", width =
jack_term.size_x) + "\n" + center_line(options_string, fill = " ", fill_r = "
", width = jack_term.size_x)
+ options_string = center_line(jack_tag.locale_names[0][0] + " - " +
jack_tag.locale_names[0][1], fill = "- ", fill_r = " -", width =
jack_term.size_x) + "\n" + center_line(options_string, fill = " ", fill_r = "
", width = jack_term.size_x)
def sig_handler(sig, frame):
"signal handler and general cleanup procedure"
Binary files site-packages.orig/jack_display.pyc and
site-packages/jack_display.pyc differ
diff -urN site-packages.orig/jack_freedb.py site-packages/jack_freedb.py
--- site-packages.orig/jack_freedb.py 2005-04-22 21:31:37.000000000 +0100
+++ site-packages/jack_freedb.py 2005-04-23 01:03:12.000000000 +0100
@@ -20,6 +20,8 @@
import string
import sys
import os
+import locale
+import codecs
import jack_playorder
import jack_functions
@@ -53,9 +55,9 @@
global names_available, dir_created
freedb_rename = 0
if warn == None:
- err, track_names, cd_id, revision =
freedb_names(freedb_id(all_tracks), all_tracks, freedb_form_file, verb = verb)
+ err, track_names, locale_names, cd_id, revision =
freedb_names(freedb_id(all_tracks), all_tracks, freedb_form_file, verb = verb)
else:
- err, track_names, cd_id, revision =
freedb_names(freedb_id(all_tracks), all_tracks, freedb_form_file, verb = verb,
warn = warn)
+ err, track_names, locale_names, cd_id, revision =
freedb_names(freedb_id(all_tracks), all_tracks, freedb_form_file, verb = verb,
warn = warn)
if (not err) and dirs:
freedb_rename = 1
@@ -83,7 +85,7 @@
names_available = 1
else:
freedb_rename = 0
- return err, track_names, freedb_rename, revision
+ return err, track_names, locale_names, freedb_rename, revision
#/ end of interpret_db_file /#
def local_freedb(cd_id, freedb_dir, outfile = "/tmp/testfilefreedb"):
@@ -214,7 +216,7 @@
qs = qs + `i[START] + MSF_OFFSET` + " "
qs = qs + `(MSF_OFFSET + tracks[-1][START] + tracks[-1][LEN]) /
CDDA_BLOCKS_PER_SECOND`
hello = "hello=" + cf['_username'] + " " + cf['_hostname'] + " " +
freedb_servers[cf['_freedb_server']]['id']
- qs = urllib.quote_plus(qs + "&" + hello + "&proto=3", "=&")
+ qs = urllib.quote_plus(qs + "&" + hello + "&proto=6", "=&")
url = "http://"; + freedb_servers[cf['_freedb_server']]['host'] +
"/~cddb/cddb.cgi?" + qs
if cf['_cont_failed_query']:
try:
@@ -227,8 +229,8 @@
f = urllib2.urlopen(url)
buf = f.readline()
if buf and buf[0:1] == "2":
- if buf[0:3] == "211": # Found inexact matches, list follows
- print "Found inexact matches. Choose one:"
+ if buf[0:3] in ("210", "211"): # Found inexact or multiple exact
matches, list follows
+ print "Found the following matches. Choose one:"
num = 1
matches = []
while 1:
@@ -278,7 +280,7 @@
error(buf + f.read() + " --don't know what to do, aborting
query.")
cmd = "cmd=cddb read " + freedb_cat + " " + cd_id
- url = "http://"; + freedb_servers[cf['_freedb_server']]['host'] +
"/~cddb/cddb.cgi?" + urllib.quote_plus(cmd + "&" + hello + "&proto=3", "=&")
+ url = "http://"; + freedb_servers[cf['_freedb_server']]['host'] +
"/~cddb/cddb.cgi?" + urllib.quote_plus(cmd + "&" + hello + "&proto=6", "=&")
f = urllib2.urlopen(url)
buf = f.readline()
if buf and buf[0:3] == "210": # entry follows
@@ -319,6 +321,10 @@
line = f.readline()
if not line:
break
+ try:
+ line = unicode(line, "utf-8")
+ except UnicodeDecodeError:
+ line = unicode(line, "latin-1")
line = string.replace(line, "\n", "") # cannot use rstrip, we need
trailing
# spaces
line = string.replace(line, "\r", "") # I consider "\r"s as bugs in
db info
@@ -591,8 +597,11 @@
else:
print "Warning: track %i (starting at 0) has no EXTT entry." %
i
- # clean up a bit:
+ locale_names = []
+ # clean up a bit and create names for the appropriate locale:
+ # FIXME: this for loop doesn't actually change the variable names at all!
for i in names:
+ t = []
for j in [0, 1]:
if i[j]:
i[j] = string.strip(i[j])
@@ -602,7 +611,10 @@
i[j] = i[j][1:-1]
while i[j][0] == '"' and string.find(i[j][1:], '"') != -1:
i[j] = string.replace(i[j][1:], '"', '', 1)
- return err, names, read_id, revision
+ x = i[j].encode(locale.getpreferredencoding(), "replace")
+ t.append(x)
+ locale_names.append(t)
+ return err, names, locale_names, read_id, revision
def choose_cat(cat = ["blues", "classical", "country", "data", "folk", "jazz",
"misc", "newage", "reggae", "rock", "soundtrack"]):
print "choose a category:"
@@ -634,7 +646,7 @@
import httplib
hello = "hello=" + cf['_username'] + " " + cf['_hostname'] + " " +
prog_name + " " + prog_version
print "Info: querying categories..."
- url = "http://"; + freedb_servers[cf['_freedb_server']]['host'] +
"/~cddb/cddb.cgi?" + urllib.quote_plus("cmd=cddb lscat" + "&" + hello +
"&proto=3", "=&")
+ url = "http://"; + freedb_servers[cf['_freedb_server']]['host'] +
"/~cddb/cddb.cgi?" + urllib.quote_plus("cmd=cddb lscat" + "&" + hello +
"&proto=6", "=&")
f = urllib2.urlopen(url)
buf = f.readline()
if buf[0:3] == "500":
@@ -697,12 +709,20 @@
h.putheader('User-Email', email)
#h.putheader('Submit-Mode', 'test')
h.putheader('Submit-Mode', 'submit')
- h.putheader('Charset', 'ISO-8859-1')
+ h.putheader('Charset', 'UTF-8')
h.putheader('X-Cddbd-Note', 'Problems submitting with ' + prog_name + '?
Visit jack.sf.net.')
h.putheader('Content-Length', str(jack_utils.filesize(file)))
h.endheaders()
- f = open(file, "r")
- h.send(f.read())
+ # The user just wrote the file with a text editor so we assume that it
+ # is in their locale.
+ f = codecs.open(file, "r", locale.getpreferredencoding())
+ try:
+ text = f.read()
+ except UnicodeDecodeError:
+ print "The freedb file does not match your current locale. Please
convert it"
+ print "to " + locale.getpreferredencoding() + " manually."
+ sys.exit(1)
+ h.send(text.encode("utf-8"))
f.close()
print
Binary files site-packages.orig/jack_freedb.pyc and
site-packages/jack_freedb.pyc differ
diff -urN site-packages.orig/jack_init.py site-packages/jack_init.py
--- site-packages.orig/jack_init.py 2005-04-22 21:31:37.000000000 +0100
+++ site-packages/jack_init.py 2005-04-23 00:48:31.000000000 +0100
@@ -78,4 +78,3 @@
pyid3lib = dummy_pyid3()
-os.environ['LC_ALL'] = "C"
Binary files site-packages.orig/jack_init.pyc and site-packages/jack_init.pyc
differ
diff -urN site-packages.orig/jack_prepare.py site-packages/jack_prepare.py
--- site-packages.orig/jack_prepare.py 2005-04-22 21:31:37.000000000 +0100
+++ site-packages/jack_prepare.py 2005-04-22 22:34:31.000000000 +0100
@@ -106,7 +106,7 @@
unique_dirs.append(jack_dirs[i])
for i in unique_dirs:
jack_ripstuff.all_tracks, dummy, track1_offset =
jack_functions.cdrdao_gettoc(os.path.join(i, cf['_toc_file']))
- err, jack_tag.track_names, cd_id, revision =
freedb_names(jack_freedb.freedb_id(jack_ripstuff.all_tracks),
jack_ripstuff.all_tracks, os.path.join(i, cf['_freedb_form_file']), verb = 0,
warn = 0)
+ err, jack_tag.track_names, jack_tag.locale_names, cd_id,
revision = freedb_names(jack_freedb.freedb_id(jack_ripstuff.all_tracks),
jack_ripstuff.all_tracks, os.path.join(i, cf['_freedb_form_file']), verb = 0,
warn = 0)
if err or cf['_force']:# this means freedb data is not
there yet
info("matching dir found: %d" % i)
pid = os.fork()
@@ -465,7 +465,7 @@
if not is_submittable:
error("can't submit in current state, please fix jack.freedb")
- err, jack_tag.track_names, cd_id, revision =
jack_freedb.freedb_names(jack_freedb.freedb_id(jack_ripstuff.all_tracks),
jack_ripstuff.all_tracks, cf['_freedb_form_file'])
+ err, jack_tag.track_names, jack_tag.locale_names, cd_id, revision =
jack_freedb.freedb_names(jack_freedb.freedb_id(jack_ripstuff.all_tracks),
jack_ripstuff.all_tracks, cf['_freedb_form_file'])
if err:
error("invalid freedb file")
else:
@@ -492,11 +492,11 @@
jack_utils.ex_edit(cf['_freedb_form_file'])
if cf['_query_on_start']:
- err, jack_tag.track_names, freedb_rename, revision =
jack_freedb.interpret_db_file(jack_ripstuff.all_tracks,
cf['_freedb_form_file'], verb = cf['_query_on_start'], dirs = 1)
+ err, jack_tag.track_names, jack_tag.locale_names, freedb_rename,
revision = jack_freedb.interpret_db_file(jack_ripstuff.all_tracks,
cf['_freedb_form_file'], verb = cf['_query_on_start'], dirs = 1)
if err:
error("query on start failed to give a good freedb file,
aborting.")
else:
- err, jack_tag.track_names, freedb_rename, revision =
jack_freedb.interpret_db_file(jack_ripstuff.all_tracks,
cf['_freedb_form_file'], verb = cf['_query_on_start'], warn =
cf['_query_on_start'])
+ err, jack_tag.track_names, jack_tag.locale_names, freedb_rename,
revision = jack_freedb.interpret_db_file(jack_ripstuff.all_tracks,
cf['_freedb_form_file'], verb = cf['_query_on_start'], warn =
cf['_query_on_start'])
return freedb_rename
def undo_rename(status, todo):
Binary files site-packages.orig/jack_prepare.pyc and
site-packages/jack_prepare.pyc differ
diff -urN site-packages.orig/jack_ripstuff.py site-packages/jack_ripstuff.py
--- site-packages.orig/jack_ripstuff.py 2005-04-22 21:31:37.000000000 +0100
+++ site-packages/jack_ripstuff.py 2005-04-22 22:28:03.000000000 +0100
@@ -18,6 +18,8 @@
import jack_freedb
+import locale
+
from jack_globals import *
all_tracks_orig = []
@@ -66,7 +68,8 @@
tmp = tmp + track_names[i[NUM]][0] + " - " +
track_names[i[NUM]][1]
else:
tmp = tmp + track_names[i[NUM]][1]
- printable_names[i[NUM]] = tmp + "." * (max_name_len - len(tmp))
+ p_tmp = tmp.encode(locale.getpreferredencoding(), "replace")
+ printable_names[i[NUM]] = p_tmp + "." * (max_name_len - len(tmp))
else:
if cf['_show_time']:
printable_names[i[NUM]] = ("%02i " % i[NUM]) + len_tmp + "." *
(max_name_len - len(i[NAME]) - 6)
Binary files site-packages.orig/jack_ripstuff.pyc and
site-packages/jack_ripstuff.pyc differ
Binary files site-packages.orig/jack_t_curses.pyc and
site-packages/jack_t_curses.pyc differ
diff -urN site-packages.orig/jack_tag.py site-packages/jack_tag.py
--- site-packages.orig/jack_tag.py 2005-04-22 21:31:37.000000000 +0100
+++ site-packages/jack_tag.py 2005-04-23 00:21:39.000000000 +0100
@@ -18,6 +18,7 @@
import string
import os, sys
+import locale
import jack_functions
import jack_ripstuff
@@ -33,6 +34,7 @@
from jack_globals import *
track_names = None
+locale_names = None
genretxt = None
a_artist = None
@@ -57,6 +59,8 @@
if jack_freedb.names_available:
a_artist = track_names[0][0]
a_title = track_names[0][1]
+ p_artist = locale_names[0][0]
+ p_title = locale_names[0][1]
if cf['_set_id3tag'] or freedb_rename:
jack_m3u.init()
@@ -135,13 +139,14 @@
vf = ogg.vorbis.VorbisFile(mp3name)
oggi = vf.comment()
oggi.clear()
- oggi.add_tag('ALBUM',
a_title.decode(cf['_charset']).encode('utf-8'))
+ oggi.add_tag('ALBUM', a_title.encode("utf-8"))
+
oggi.add_tag('TRACKNUMBER', `i[NUM]`)
- oggi.add_tag('TITLE',
t_name.decode(cf['_charset']).encode('utf-8'))
+ oggi.add_tag('TITLE', t_name.encode("utf-8"))
if t_artist:
- oggi.add_tag('ARTIST',
t_artist.decode(cf['_charset']).encode('utf-8'))
+ oggi.add_tag('ARTIST', t_artist.encode("utf-8"))
else:
- oggi.add_tag('ARTIST',
a_artist.decode(cf['_charset']).encode('utf-8'))
+ oggi.add_tag('ARTIST', a_artist.encode("utf-8"))
if cf['_id3_genre'] != -1:
oggi.add_tag('GENRE', id3genres[cf['_id3_genre']])
if cf['_id3_year'] != -1:
@@ -158,35 +163,41 @@
exec("newname = newname" + cf['_char_filter'])
for char_i in range(len(cf['_unusable_chars'])):
newname = string.replace(newname,
cf['_unusable_chars'][char_i], cf['_replacement_chars'][char_i])
+ oldname = i[NAME]
+ i[NAME] = unicode(i[NAME], "utf-8")
if i[NAME] != newname:
+ p_newname = newname.encode(locale.getpreferredencoding(),
"replace")
+ newname = newname.encode("utf-8", "replace")
+ p_mp3name = mp3name.encode(locale.getpreferredencoding(),
"replace")
+ p_wavname = wavname.encode(locale.getpreferredencoding(),
"replace")
ok = 1
if os.path.exists(newname + ext):
ok = 0
- print 'NOT renaming "' + mp3name + '" to "' + newname
+ ext + '" because dest. exists.'
+ print 'NOT renaming "' + p_mp3name + '" to "' +
p_newname + ext + '" because dest. exists.'
if cf['_keep_wavs']:
- print 'NOT renaming "' + wavname + '" to "' +
newname + ".wav" + '" because dest. exists.'
+ print 'NOT renaming "' + p_wavname + '" to "' +
p_newname + ".wav" + '" because dest. exists.'
elif cf['_keep_wavs'] and os.path.exists(newname + ".wav"):
ok = 0
- print 'NOT renaming "' + wavname + '" to "' + newname
+ ".wav" + '" because dest. exists.'
- print 'NOT renaming "' + mp3name + '" to "' + newname
+ ext + '" because WAV dest. exists.'
+ print 'NOT renaming "' + p_wavname + '" to "' +
p_newname + ".wav" + '" because dest. exists.'
+ print 'NOT renaming "' + p_mp3name + '" to "' +
p_newname + ext + '" because WAV dest. exists.'
if ok:
if not cf['_only_dae']:
try:
os.rename(mp3name, newname + ext)
except OSError:
- error('Cannot rename "%s" to "%s" (Filename is
too long or has unusable characters)' % (mp3name, newname + ext))
+ error('Cannot rename "%s" to "%s" (Filename is
too long or has unusable characters)' % (p_mp3name, p_newname + ext))
jack_m3u.add(newname + ext)
if cf['_keep_wavs']:
os.rename(wavname, newname + ".wav")
jack_m3u.add_wav(newname + ".wav")
- jack_functions.progress(i[NUM], "ren", "%s-->%s" %
(i[NAME], newname))
+ jack_functions.progress(i[NUM], "ren", "%s-->%s" %
(oldname, newname))
elif cf['_silent_mode']:
jack_functions.progress(i[NUM], "err", "while renaming
track")
print
if not cf['_silent_mode']:
if jack_freedb.names_available:
- print "Done with \"" + a_artist+ " - " + a_title + "\"."
+ print "Done with \"" + p_artist+ " - " + p_title + "\"."
else:
print "All done.",
if cf['_set_id3tag'] and cf['_id3_year'] != -1:
Binary files site-packages.orig/jack_tag.pyc and site-packages/jack_tag.pyc
differ
diff -urN site-packages.orig/jack_utils.py site-packages/jack_utils.py
--- site-packages.orig/jack_utils.py 2005-04-22 21:31:37.000000000 +0100
+++ site-packages/jack_utils.py 2005-04-23 00:08:02.000000000 +0100
@@ -167,6 +167,7 @@
for i in dirs:
replace_list = (("%a", names[0][0]), ("%l", names[0][1]), ("%y",
`cf['_id3_year']`), ("%g", cf['_id3_genre_txt']))
x = jack_misc.multi_replace(i, replace_list, unusable_charmap)
+ x = x.encode("utf-8", "replace")
exec("x = x" + cf['_char_filter'])
dirs2.append(x)
if cf['_append_year'] and len(`cf['_id3_year']`) == 4: # Y10K bug!
Binary files site-packages.orig/jack_utils.pyc and site-packages/jack_utils.pyc
differ
diff -urN site-packages.orig/jack_workers.py site-packages/jack_workers.py
--- site-packages.orig/jack_workers.py 2005-04-22 21:31:37.000000000 +0100
+++ site-packages/jack_workers.py 2005-04-22 22:50:29.000000000 +0100
@@ -55,7 +55,7 @@
default_signals()
if nice_value:
os.nice(nice_value)
- os.execvp(args[0], args)
+ os.execvp(args[0], [a.encode("utf-8", "replace") for a in args])
else:
data['pid'] = pid
if os.uname()[0] == "Linux":
Binary files site-packages.orig/jack_workers.pyc and
site-packages/jack_workers.pyc differ
--- /usr/bin/jack 2005-04-01 02:54:08.000000000 +0100
+++ ./jack-3.1 2005-04-22 22:45:04.000000000 +0100
@@ -149,7 +149,7 @@
### (10) update freedb dbfile
if cf['_update_freedb']:
if not jack_tag.track_names:
- err, jack_tag.track_names, freedb_rename, revision =
jack_freedb.interpret_db_file(jack_ripstuff.all_tracks,
cf['_freedb_form_file'], verb = 1, dirs = 0)
+ err, jack_tag.track_names, jack_tag.locale_names, freedb_rename,
revision = jack_freedb.interpret_db_file(jack_ripstuff.all_tracks,
cf['_freedb_form_file'], verb = 1, dirs = 0)
jack_freedb.freedb_template(jack_ripstuff.all_tracks,
jack_tag.track_names, revision + 1)
jack_utils.ex_edit(cf['_freedb_form_file'])
info("now submit your changes if you like, using the option --submit (via
http POST). Don't forget to activate your changes locally with -R")
@@ -242,7 +242,7 @@
jack_display.exit()
if cf['_query_when_ready'] or cf['_read_freedb_file'] or cf['_query_on_start']:
- err, jack_tag.track_names, freedb_rename, revision =
jack_freedb.interpret_db_file(jack_ripstuff.all_tracks,
cf['_freedb_form_file'], verb = 1, dirs = 1)
+ err, jack_tag.track_names, jack_tag.locale_names, freedb_rename, revision
= jack_freedb.interpret_db_file(jack_ripstuff.all_tracks,
cf['_freedb_form_file'], verb = 1, dirs = 1)
if err:
error("could not read freedb file")
