Package: iso-codes
Version: 0.48-1
The .pot files in iso-codes sometimes use msgids that are not ASCII.
However, the GNU gettext manual says:
Note that the MSGID argument to `gettext' is not subject to
character set conversion. Also, when `gettext' does not find a
translation for MSGID, it returns MSGID unchanged - independently of
the current output character set. It is therefore recommended that all
MSGIDs be US-ASCII strings.
An example problem scenario is if gettext("Åland Islands") returns its
argument (which is UTF-8) in an EUC-JIS locale: the result will be a
corrupted string being sent to the user.
Here is a proposed patch, which causes the msgid to be the ASCII
approximation "Aaland Islands" instead.
2005-09-30 Paul Eggert <[EMAIL PROTECTED]>
* iso2pot.py: Convert msgids to an ASCII approximation if they
are not already ASCII.
diff -pru -I iso-codes- --exclude='*.po' iso-codes-0.48-tmp/iso2pot.py
iso-codes-0.48-fix/iso2pot.py
--- iso-codes-0.48-tmp/iso2pot.py 2004-06-15 13:36:43.000000000 -0700
+++ iso-codes-0.48-fix/iso2pot.py 2005-09-30 14:36:26.000000000 -0700
@@ -8,7 +8,7 @@
from xml.sax import saxutils, make_parser, saxlib, saxexts, ContentHandler
from xml.sax.handler import feature_namespaces
-import sys, os, getopt, urllib2, locale, time
+import sys, os, getopt, urllib2, locale, time, codecs
class printPot(saxutils.DefaultHandler):
def __init__(self, nameslist,comment, ofile):
@@ -21,6 +21,57 @@ class printPot(saxutils.DefaultHandler):
self.ofile = ofile
self.done = {}
+ def asciiize(exc):
+ """Convert to an ASCII approximation of the input.
+ """
+ codepoint2ascii = {
+ 0x00C5 : 'Aa',
+ 0x00DA : 'U',
+ 0x00E1 : 'a',
+ 0x00E2 : 'a',
+ 0x00E4 : 'a',
+ 0x00E5 : 'aa',
+ 0x00E7 : 'c',
+ 0x00E8 : 'e',
+ 0x00E9 : 'e',
+ 0x00EB : 'e',
+ 0x00ED : 'i',
+ 0x00EF : 'i',
+ 0x00C1 : 'A',
+ 0x00F1 : 'n',
+ 0x00F3 : 'o',
+ 0x00F4 : 'o',
+ 0x00F6 : 'o',
+ 0x00F8 : 'o',
+ 0x00FA : 'u',
+ 0x00FD : 'y',
+ 0x0101 : 'a',
+ 0x010D : 'c',
+ 0x011B : 'e',
+ 0x012B : 'i',
+ 0x0141 : 'L',
+ 0x0142 : 'l',
+ 0x0148 : 'n',
+ 0x0151 : 'o',
+ 0x0159 : 'r',
+ 0x015A : 'S',
+ 0x015B : 's',
+ 0x015E : 'S',
+ 0x015F : 's',
+ 0x0161 : 's',
+ 0x0162 : 'T',
+ 0x0163 : 't',
+ 0x016B : 'u',
+ 0x017D : 'Z',
+ }
+ if not isinstance(exc, UnicodeEncodeError):
+ raise TypeError("don't know how to handle %r" % exc)
+ l = []
+ for c in exc.object[exc.start:exc.end]:
+ l.append(codepoint2ascii[ord(c)])
+ return (u''.join(l), exc.end)
+
+ codecs.register_error('iso2pot.asciiize', asciiize)
def startElement(self, name, attrs):
# Get the name attributes
@@ -28,7 +79,7 @@ class printPot(saxutils.DefaultHandler):
n = attrs.get(aname, None)
c = attrs.get(self.comment, None)
if type(n) == unicode:
- n = n.encode('UTF-8')
+ n = n.encode('ascii', 'iso2pot.asciiize')
if type(c) == unicode:
c = c.encode('UTF-8')
if n != None and not self.done.has_key(n):
