Allow the user to specify the fallback encoding for the changelog
Example: use EUC-JP instead of ISO-8859-1:
[ui]
fallbackencoding = EUC-JP
--- a/doc/hgrc.5.txt
+++ b/doc/hgrc.5.txt
@@ -388,6 +388,9 @@ ui::
Print debugging information. True or False. Default is False.
editor;;
The editor to use during a commit. Default is $EDITOR or "vi".
+ fallbackencoding;;
+ Encoding to try if it's not possible to decode the changelog using
+ UTF-8. Default is ISO-8859-1.
ignore;;
A file to read per-user ignore patterns from. This file should be in
the same format as a repository-wide .hgignore file. This option
--- a/mercurial/localrepo.py
+++ b/mercurial/localrepo.py
@@ -72,6 +72,10 @@ class localrepository(repo.repository):
self.manifest = manifest.manifest(self.sopener, v)
self.changelog = changelog.changelog(self.sopener, v)
+ fallback = self.ui.config('ui', 'fallbackencoding')
+ if fallback:
+ util._fallbackencoding = fallback
+
# the changelog might not have the inline index flag
# on. If the format of the changelog is the same as found in
# .hgrc, apply any flags found in the .hgrc as well.
--- a/mercurial/util.py
+++ b/mercurial/util.py
@@ -19,6 +19,7 @@ demandload(globals(), "os threading time
_encoding = os.environ.get("HGENCODING") or locale.getpreferredencoding()
_encodingmode = os.environ.get("HGENCODINGMODE", "strict")
+_fallbackencoding = 'ISO-8859-1'
def tolocal(s):
"""
@@ -30,7 +31,7 @@ def tolocal(s):
using UTF-8, then Latin-1, and failing that, we use UTF-8 and
replace unknown characters.
"""
- for e in "utf-8 latin1".split():
+ for e in ('UTF-8', _fallbackencoding):
try:
u = s.decode(e) # attempt strict decoding
return u.encode(_encoding, "replace")
index d050be8ebfef9771e5e1dffdd1cb98be3a51765a..7b1a00d39063a15a9f92d6cb3d253117063b4a26
GIT binary patch
literal 530
zc$@(e0`2`sM=>x$T4*^jL0KkKStSe@vj6}S|NsA+<Pv?lfASR&qBMW^PaH(70L)Q(
zhVBu_pmvz8Yep~udSx>SN>kDXnhgLwKxp*_hDLw^h#BfY0002fKn)sc<vl_vlL?a&
zC#I%`fuI4jng9R*0000D00002Qc4db4F-clN2q9I8W{}@00E!|nFAm_MuvuiMoj^U
z<CU*McetgPDAy4$?HO%$s48#pz<`u0RDod}DGI&t+SrRakn14PL0Uuyt96PAC&=+K
zkcbgb&*2@+$A>KlgvdeSGQB8BHtlA*j4y7!8C~dxu3oj9G2XKsg_Urpan?~t=zO;a
zT_o;E1t&SQ7!2r`^i?cIYB|*Fh%p@yC2mlx;4(O|jR`SCk+zYP(GH{?L^}$l6%MY^
z(hQ(S%d2}mw;GF}14W?I7(t`3J5ZE|$45v>LxBuLD9U=)H&aSZq+wUevS!iy>0AF`
z6w^ZbSXa1&o>6C5+aWX~gp$`Gj1tTk0H=tStY8Hz^3~~&M0`oJjRU5}+@%11a7cbS
zV>a|s>@*Nb227Lg9l#uXn;{-*?kw3#FFOpkMz!Ec#FYdiz9o&dDuK9CF3}%}iNMMg
z$af(s7}9$*3Kl{&_tpVVF!>yk&hn>K3G)x%$*6iC#L#K9KAa-WCeuQG+y@4Ro&#fq
UprIU>zJH6kBAh5l5{3*}fcePY6951J
--- a/tests/test-encoding
+++ b/tests/test-encoding
@@ -47,3 +47,8 @@ echo % latin-1
HGENCODING=latin-1 hg branches
echo % utf-8
HGENCODING=utf-8 hg branches
+
+echo '[ui]' >> .hg/hgrc
+echo 'fallbackencoding = euc-jp' >> .hg/hgrc
+echo % utf-8
+HGENCODING=utf-8 hg log
--- a/tests/test-encoding.out
+++ b/tests/test-encoding.out
@@ -1,7 +1,7 @@
adding changesets
adding manifests
adding file changes
-added 1 changesets with 1 changes to 1 files
+added 2 changesets with 2 changes to 1 files
(run 'hg update' to get a working copy)
1 files updated, 0 files merged, 0 files removed, 0 files unresolved
% should fail with encoding error
@@ -15,104 +15,153 @@ transaction abort!
rollback completed
% these should work
% ascii
-changeset: 4:d8a5d9eaf41e
+changeset: 5:e4ed49b8a8f0
branch: ?
tag: tip
user: test
date: Thu Jan 01 00:00:00 1970 +0000
summary: latin1 branch
-changeset: 3:5edfc7acb541
+changeset: 4:a02ca5a58e99
user: test
date: Thu Jan 01 00:00:00 1970 +0000
-summary: Added tag ? for changeset 91878608adb3
+summary: Added tag ? for changeset d47908dab82f
-changeset: 2:91878608adb3
+changeset: 3:d47908dab82f
tag: ?
user: test
date: Thu Jan 01 00:00:00 1970 +0000
summary: utf-8 e' encoded: ?
-changeset: 1:6355cacf842e
+changeset: 2:9db1985f3097
user: test
date: Thu Jan 01 00:00:00 1970 +0000
summary: latin-1 e' encoded: ?
+changeset: 1:af6e0db4427c
+user: test
+date: Thu Jan 01 00:00:00 1970 +0000
+summary: euc-jp: ?????? = u'\u65e5\u672c\u8a9e'
+
changeset: 0:60aad1dd20a9
user: test
date: Thu Jan 01 00:00:00 1970 +0000
summary: latin-1 e': ?
% latin-1
-changeset: 4:d8a5d9eaf41e
+changeset: 5:e4ed49b8a8f0
branch: é
tag: tip
user: test
date: Thu Jan 01 00:00:00 1970 +0000
summary: latin1 branch
-changeset: 3:5edfc7acb541
+changeset: 4:a02ca5a58e99
user: test
date: Thu Jan 01 00:00:00 1970 +0000
-summary: Added tag é for changeset 91878608adb3
+summary: Added tag é for changeset d47908dab82f
-changeset: 2:91878608adb3
+changeset: 3:d47908dab82f
tag: é
user: test
date: Thu Jan 01 00:00:00 1970 +0000
summary: utf-8 e' encoded: é
-changeset: 1:6355cacf842e
+changeset: 2:9db1985f3097
user: test
date: Thu Jan 01 00:00:00 1970 +0000
summary: latin-1 e' encoded: é
+changeset: 1:af6e0db4427c
+user: test
+date: Thu Jan 01 00:00:00 1970 +0000
+summary: euc-jp: ÆüËܸì = u'\u65e5\u672c\u8a9e'
+
changeset: 0:60aad1dd20a9
user: test
date: Thu Jan 01 00:00:00 1970 +0000
summary: latin-1 e': é
% utf-8
-changeset: 4:d8a5d9eaf41e
+changeset: 5:e4ed49b8a8f0
branch: é
tag: tip
user: test
date: Thu Jan 01 00:00:00 1970 +0000
summary: latin1 branch
-changeset: 3:5edfc7acb541
+changeset: 4:a02ca5a58e99
user: test
date: Thu Jan 01 00:00:00 1970 +0000
-summary: Added tag é for changeset 91878608adb3
+summary: Added tag é for changeset d47908dab82f
-changeset: 2:91878608adb3
+changeset: 3:d47908dab82f
tag: é
user: test
date: Thu Jan 01 00:00:00 1970 +0000
summary: utf-8 e' encoded: é
-changeset: 1:6355cacf842e
+changeset: 2:9db1985f3097
user: test
date: Thu Jan 01 00:00:00 1970 +0000
summary: latin-1 e' encoded: é
+changeset: 1:af6e0db4427c
+user: test
+date: Thu Jan 01 00:00:00 1970 +0000
+summary: euc-jp: ÆüËܸì = u'\u65e5\u672c\u8a9e'
+
changeset: 0:60aad1dd20a9
user: test
date: Thu Jan 01 00:00:00 1970 +0000
summary: latin-1 e': é
% ascii
-tip 4:d8a5d9eaf41e
-? 2:91878608adb3
+tip 5:e4ed49b8a8f0
+? 3:d47908dab82f
% latin-1
-tip 4:d8a5d9eaf41e
-é 2:91878608adb3
+tip 5:e4ed49b8a8f0
+é 3:d47908dab82f
+% utf-8
+tip 5:e4ed49b8a8f0
+é 3:d47908dab82f
+% ascii
+? 5:e4ed49b8a8f0
+% latin-1
+é 5:e4ed49b8a8f0
+% utf-8
+é 5:e4ed49b8a8f0
% utf-8
-tip 4:d8a5d9eaf41e
-é 2:91878608adb3
-% ascii
-? 4:d8a5d9eaf41e
-% latin-1
-é 4:d8a5d9eaf41e
-% utf-8
-é 4:d8a5d9eaf41e
+changeset: 5:e4ed49b8a8f0
+branch: é
+tag: tip
+user: test
+date: Thu Jan 01 00:00:00 1970 +0000
+summary: latin1 branch
+
+changeset: 4:a02ca5a58e99
+user: test
+date: Thu Jan 01 00:00:00 1970 +0000
+summary: Added tag é for changeset d47908dab82f
+
+changeset: 3:d47908dab82f
+tag: é
+user: test
+date: Thu Jan 01 00:00:00 1970 +0000
+summary: utf-8 e' encoded: é
+
+changeset: 2:9db1985f3097
+user: test
+date: Thu Jan 01 00:00:00 1970 +0000
+summary: latin-1 e' encoded: é
+
+changeset: 1:af6e0db4427c
+user: test
+date: Thu Jan 01 00:00:00 1970 +0000
+summary: euc-jp: 日本語 = u'\u65e5\u672c\u8a9e'
+
+changeset: 0:60aad1dd20a9
+user: test
+date: Thu Jan 01 00:00:00 1970 +0000
+summary: latin-1 e': �
+