Mercurial > public > mercurial-scm > hg
annotate mercurial/encoding.py @ 11297:d320e70442a5
replace Python standard textwrap by MBCS sensitive one for i18n text
Mercurial has problem around text wrapping/filling in MBCS encoding
environment, because standard 'textwrap' module of Python can not
treat it correctly. It splits byte sequence for one character into two
lines.
According to unicode specification, "east asian width" classifies
characters into:
W(ide), N(arrow), F(ull-width), H(alf-width), A(mbiguous)
W/N/F/H can be always recognized as 2/1/2/1 bytes in byte sequence,
but 'A' can not. Size of 'A' depends on language in which it is used.
Unicode specification says:
If the context(= language) cannot be established reliably they
should be treated as narrow characters by default
but many of class 'A' characters are full-width, at least, in Japanese
environment.
So, this patch treats class 'A' characters as full-width always for
safety wrapping.
This patch focuses only on MBCS safe-ness, not on writing/printing
rule strict wrapping for each languages
MBCS sensitive textwrap class is originally implemented
by ITO Nobuaki <daydream.trippers@gmail.com>.
author | FUJIWARA Katsunori <foozy@lares.dti.ne.jp> |
---|---|
date | Sun, 06 Jun 2010 17:20:10 +0900 |
parents | 08a0f04b56bd |
children | 2be70ca17311 |
rev | line source |
---|---|
8226
8b2cd04a6e97
put license and copyright info into comment blocks
Martin Geisler <mg@lazybytes.net>
parents:
8225
diff
changeset
|
1 # encoding.py - character transcoding support for Mercurial |
8b2cd04a6e97
put license and copyright info into comment blocks
Martin Geisler <mg@lazybytes.net>
parents:
8225
diff
changeset
|
2 # |
8b2cd04a6e97
put license and copyright info into comment blocks
Martin Geisler <mg@lazybytes.net>
parents:
8225
diff
changeset
|
3 # Copyright 2005-2009 Matt Mackall <mpm@selenic.com> and others |
8b2cd04a6e97
put license and copyright info into comment blocks
Martin Geisler <mg@lazybytes.net>
parents:
8225
diff
changeset
|
4 # |
8b2cd04a6e97
put license and copyright info into comment blocks
Martin Geisler <mg@lazybytes.net>
parents:
8225
diff
changeset
|
5 # This software may be used and distributed according to the terms of the |
10263 | 6 # GNU General Public License version 2 or any later version. |
7948
de377b1a9a84
move encoding bits from util to encoding
Matt Mackall <mpm@selenic.com>
parents:
diff
changeset
|
7 |
8312
b87a50b7125c
separate import lines from mercurial and general python modules
Simon Heimberg <simohe@besonet.ch>
parents:
8226
diff
changeset
|
8 import error |
b87a50b7125c
separate import lines from mercurial and general python modules
Simon Heimberg <simohe@besonet.ch>
parents:
8226
diff
changeset
|
9 import sys, unicodedata, locale, os |
7948
de377b1a9a84
move encoding bits from util to encoding
Matt Mackall <mpm@selenic.com>
parents:
diff
changeset
|
10 |
de377b1a9a84
move encoding bits from util to encoding
Matt Mackall <mpm@selenic.com>
parents:
diff
changeset
|
11 _encodingfixup = {'646': 'ascii', 'ANSI_X3.4-1968': 'ascii'} |
de377b1a9a84
move encoding bits from util to encoding
Matt Mackall <mpm@selenic.com>
parents:
diff
changeset
|
12 |
de377b1a9a84
move encoding bits from util to encoding
Matt Mackall <mpm@selenic.com>
parents:
diff
changeset
|
13 try: |
de377b1a9a84
move encoding bits from util to encoding
Matt Mackall <mpm@selenic.com>
parents:
diff
changeset
|
14 encoding = os.environ.get("HGENCODING") |
de377b1a9a84
move encoding bits from util to encoding
Matt Mackall <mpm@selenic.com>
parents:
diff
changeset
|
15 if sys.platform == 'darwin' and not encoding: |
de377b1a9a84
move encoding bits from util to encoding
Matt Mackall <mpm@selenic.com>
parents:
diff
changeset
|
16 # On darwin, getpreferredencoding ignores the locale environment and |
de377b1a9a84
move encoding bits from util to encoding
Matt Mackall <mpm@selenic.com>
parents:
diff
changeset
|
17 # always returns mac-roman. We override this if the environment is |
de377b1a9a84
move encoding bits from util to encoding
Matt Mackall <mpm@selenic.com>
parents:
diff
changeset
|
18 # not C (has been customized by the user). |
9574
9e9f63d5c456
encoding: fix issue with non-standard UTF-8 CTYPE on OS X
Dirkjan Ochtman <dirkjan@ochtman.nl>
parents:
8312
diff
changeset
|
19 lc = locale.setlocale(locale.LC_CTYPE, '') |
9e9f63d5c456
encoding: fix issue with non-standard UTF-8 CTYPE on OS X
Dirkjan Ochtman <dirkjan@ochtman.nl>
parents:
8312
diff
changeset
|
20 if lc == 'UTF-8': |
9e9f63d5c456
encoding: fix issue with non-standard UTF-8 CTYPE on OS X
Dirkjan Ochtman <dirkjan@ochtman.nl>
parents:
8312
diff
changeset
|
21 locale.setlocale(locale.LC_CTYPE, 'en_US.UTF-8') |
7948
de377b1a9a84
move encoding bits from util to encoding
Matt Mackall <mpm@selenic.com>
parents:
diff
changeset
|
22 encoding = locale.getlocale()[1] |
de377b1a9a84
move encoding bits from util to encoding
Matt Mackall <mpm@selenic.com>
parents:
diff
changeset
|
23 if not encoding: |
de377b1a9a84
move encoding bits from util to encoding
Matt Mackall <mpm@selenic.com>
parents:
diff
changeset
|
24 encoding = locale.getpreferredencoding() or 'ascii' |
de377b1a9a84
move encoding bits from util to encoding
Matt Mackall <mpm@selenic.com>
parents:
diff
changeset
|
25 encoding = _encodingfixup.get(encoding, encoding) |
de377b1a9a84
move encoding bits from util to encoding
Matt Mackall <mpm@selenic.com>
parents:
diff
changeset
|
26 except locale.Error: |
de377b1a9a84
move encoding bits from util to encoding
Matt Mackall <mpm@selenic.com>
parents:
diff
changeset
|
27 encoding = 'ascii' |
de377b1a9a84
move encoding bits from util to encoding
Matt Mackall <mpm@selenic.com>
parents:
diff
changeset
|
28 encodingmode = os.environ.get("HGENCODINGMODE", "strict") |
de377b1a9a84
move encoding bits from util to encoding
Matt Mackall <mpm@selenic.com>
parents:
diff
changeset
|
29 fallbackencoding = 'ISO-8859-1' |
de377b1a9a84
move encoding bits from util to encoding
Matt Mackall <mpm@selenic.com>
parents:
diff
changeset
|
30 |
de377b1a9a84
move encoding bits from util to encoding
Matt Mackall <mpm@selenic.com>
parents:
diff
changeset
|
31 def tolocal(s): |
de377b1a9a84
move encoding bits from util to encoding
Matt Mackall <mpm@selenic.com>
parents:
diff
changeset
|
32 """ |
de377b1a9a84
move encoding bits from util to encoding
Matt Mackall <mpm@selenic.com>
parents:
diff
changeset
|
33 Convert a string from internal UTF-8 to local encoding |
de377b1a9a84
move encoding bits from util to encoding
Matt Mackall <mpm@selenic.com>
parents:
diff
changeset
|
34 |
de377b1a9a84
move encoding bits from util to encoding
Matt Mackall <mpm@selenic.com>
parents:
diff
changeset
|
35 All internal strings should be UTF-8 but some repos before the |
de377b1a9a84
move encoding bits from util to encoding
Matt Mackall <mpm@selenic.com>
parents:
diff
changeset
|
36 implementation of locale support may contain latin1 or possibly |
de377b1a9a84
move encoding bits from util to encoding
Matt Mackall <mpm@selenic.com>
parents:
diff
changeset
|
37 other character sets. We attempt to decode everything strictly |
de377b1a9a84
move encoding bits from util to encoding
Matt Mackall <mpm@selenic.com>
parents:
diff
changeset
|
38 using UTF-8, then Latin-1, and failing that, we use UTF-8 and |
de377b1a9a84
move encoding bits from util to encoding
Matt Mackall <mpm@selenic.com>
parents:
diff
changeset
|
39 replace unknown characters. |
de377b1a9a84
move encoding bits from util to encoding
Matt Mackall <mpm@selenic.com>
parents:
diff
changeset
|
40 """ |
de377b1a9a84
move encoding bits from util to encoding
Matt Mackall <mpm@selenic.com>
parents:
diff
changeset
|
41 for e in ('UTF-8', fallbackencoding): |
de377b1a9a84
move encoding bits from util to encoding
Matt Mackall <mpm@selenic.com>
parents:
diff
changeset
|
42 try: |
de377b1a9a84
move encoding bits from util to encoding
Matt Mackall <mpm@selenic.com>
parents:
diff
changeset
|
43 u = s.decode(e) # attempt strict decoding |
de377b1a9a84
move encoding bits from util to encoding
Matt Mackall <mpm@selenic.com>
parents:
diff
changeset
|
44 return u.encode(encoding, "replace") |
de377b1a9a84
move encoding bits from util to encoding
Matt Mackall <mpm@selenic.com>
parents:
diff
changeset
|
45 except LookupError, k: |
de377b1a9a84
move encoding bits from util to encoding
Matt Mackall <mpm@selenic.com>
parents:
diff
changeset
|
46 raise error.Abort("%s, please check your locale settings" % k) |
de377b1a9a84
move encoding bits from util to encoding
Matt Mackall <mpm@selenic.com>
parents:
diff
changeset
|
47 except UnicodeDecodeError: |
de377b1a9a84
move encoding bits from util to encoding
Matt Mackall <mpm@selenic.com>
parents:
diff
changeset
|
48 pass |
de377b1a9a84
move encoding bits from util to encoding
Matt Mackall <mpm@selenic.com>
parents:
diff
changeset
|
49 u = s.decode("utf-8", "replace") # last ditch |
de377b1a9a84
move encoding bits from util to encoding
Matt Mackall <mpm@selenic.com>
parents:
diff
changeset
|
50 return u.encode(encoding, "replace") |
de377b1a9a84
move encoding bits from util to encoding
Matt Mackall <mpm@selenic.com>
parents:
diff
changeset
|
51 |
de377b1a9a84
move encoding bits from util to encoding
Matt Mackall <mpm@selenic.com>
parents:
diff
changeset
|
52 def fromlocal(s): |
de377b1a9a84
move encoding bits from util to encoding
Matt Mackall <mpm@selenic.com>
parents:
diff
changeset
|
53 """ |
de377b1a9a84
move encoding bits from util to encoding
Matt Mackall <mpm@selenic.com>
parents:
diff
changeset
|
54 Convert a string from the local character encoding to UTF-8 |
de377b1a9a84
move encoding bits from util to encoding
Matt Mackall <mpm@selenic.com>
parents:
diff
changeset
|
55 |
de377b1a9a84
move encoding bits from util to encoding
Matt Mackall <mpm@selenic.com>
parents:
diff
changeset
|
56 We attempt to decode strings using the encoding mode set by |
de377b1a9a84
move encoding bits from util to encoding
Matt Mackall <mpm@selenic.com>
parents:
diff
changeset
|
57 HGENCODINGMODE, which defaults to 'strict'. In this mode, unknown |
de377b1a9a84
move encoding bits from util to encoding
Matt Mackall <mpm@selenic.com>
parents:
diff
changeset
|
58 characters will cause an error message. Other modes include |
de377b1a9a84
move encoding bits from util to encoding
Matt Mackall <mpm@selenic.com>
parents:
diff
changeset
|
59 'replace', which replaces unknown characters with a special |
de377b1a9a84
move encoding bits from util to encoding
Matt Mackall <mpm@selenic.com>
parents:
diff
changeset
|
60 Unicode character, and 'ignore', which drops the character. |
de377b1a9a84
move encoding bits from util to encoding
Matt Mackall <mpm@selenic.com>
parents:
diff
changeset
|
61 """ |
de377b1a9a84
move encoding bits from util to encoding
Matt Mackall <mpm@selenic.com>
parents:
diff
changeset
|
62 try: |
de377b1a9a84
move encoding bits from util to encoding
Matt Mackall <mpm@selenic.com>
parents:
diff
changeset
|
63 return s.decode(encoding, encodingmode).encode("utf-8") |
de377b1a9a84
move encoding bits from util to encoding
Matt Mackall <mpm@selenic.com>
parents:
diff
changeset
|
64 except UnicodeDecodeError, inst: |
10282
08a0f04b56bd
many, many trivial check-code fixups
Matt Mackall <mpm@selenic.com>
parents:
10263
diff
changeset
|
65 sub = s[max(0, inst.start - 10):inst.start + 10] |
7948
de377b1a9a84
move encoding bits from util to encoding
Matt Mackall <mpm@selenic.com>
parents:
diff
changeset
|
66 raise error.Abort("decoding near '%s': %s!" % (sub, inst)) |
de377b1a9a84
move encoding bits from util to encoding
Matt Mackall <mpm@selenic.com>
parents:
diff
changeset
|
67 except LookupError, k: |
de377b1a9a84
move encoding bits from util to encoding
Matt Mackall <mpm@selenic.com>
parents:
diff
changeset
|
68 raise error.Abort("%s, please check your locale settings" % k) |
de377b1a9a84
move encoding bits from util to encoding
Matt Mackall <mpm@selenic.com>
parents:
diff
changeset
|
69 |
de377b1a9a84
move encoding bits from util to encoding
Matt Mackall <mpm@selenic.com>
parents:
diff
changeset
|
70 def colwidth(s): |
de377b1a9a84
move encoding bits from util to encoding
Matt Mackall <mpm@selenic.com>
parents:
diff
changeset
|
71 "Find the column width of a UTF-8 string for display" |
de377b1a9a84
move encoding bits from util to encoding
Matt Mackall <mpm@selenic.com>
parents:
diff
changeset
|
72 d = s.decode(encoding, 'replace') |
de377b1a9a84
move encoding bits from util to encoding
Matt Mackall <mpm@selenic.com>
parents:
diff
changeset
|
73 if hasattr(unicodedata, 'east_asian_width'): |
de377b1a9a84
move encoding bits from util to encoding
Matt Mackall <mpm@selenic.com>
parents:
diff
changeset
|
74 w = unicodedata.east_asian_width |
11297
d320e70442a5
replace Python standard textwrap by MBCS sensitive one for i18n text
FUJIWARA Katsunori <foozy@lares.dti.ne.jp>
parents:
10282
diff
changeset
|
75 return sum([w(c) in 'WFA' and 2 or 1 for c in d]) |
7948
de377b1a9a84
move encoding bits from util to encoding
Matt Mackall <mpm@selenic.com>
parents:
diff
changeset
|
76 return len(d) |
de377b1a9a84
move encoding bits from util to encoding
Matt Mackall <mpm@selenic.com>
parents:
diff
changeset
|
77 |