summaryrefslogtreecommitdiff
path: root/sys/src/cmd/hg/mercurial/encoding.py
diff options
context:
space:
mode:
authorOri Bernstein <ori@eigenstate.org>2021-06-14 00:00:37 +0000
committerOri Bernstein <ori@eigenstate.org>2021-06-14 00:00:37 +0000
commita73a964e51247ed169d322c725a3a18859f109a3 (patch)
tree3f752d117274d444bda44e85609aeac1acf313f3 /sys/src/cmd/hg/mercurial/encoding.py
parente64efe273fcb921a61bf27d33b230c4e64fcd425 (diff)
python, hg: tow outside the environment.
they've served us well, and can ride off into the sunset.
Diffstat (limited to 'sys/src/cmd/hg/mercurial/encoding.py')
-rw-r--r--sys/src/cmd/hg/mercurial/encoding.py75
1 files changed, 0 insertions, 75 deletions
diff --git a/sys/src/cmd/hg/mercurial/encoding.py b/sys/src/cmd/hg/mercurial/encoding.py
deleted file mode 100644
index b286cc865..000000000
--- a/sys/src/cmd/hg/mercurial/encoding.py
+++ /dev/null
@@ -1,75 +0,0 @@
-# encoding.py - character transcoding support for Mercurial
-#
-# Copyright 2005-2009 Matt Mackall <mpm@selenic.com> and others
-#
-# This software may be used and distributed according to the terms of the
-# GNU General Public License version 2, incorporated herein by reference.
-
-import error
-import sys, unicodedata, locale, os
-
-_encodingfixup = {'646': 'ascii', 'ANSI_X3.4-1968': 'ascii'}
-
-try:
- encoding = os.environ.get("HGENCODING")
- if sys.platform == 'darwin' and not encoding:
- # On darwin, getpreferredencoding ignores the locale environment and
- # always returns mac-roman. We override this if the environment is
- # not C (has been customized by the user).
- locale.setlocale(locale.LC_CTYPE, '')
- encoding = locale.getlocale()[1]
- if not encoding:
- encoding = locale.getpreferredencoding() or 'ascii'
- encoding = _encodingfixup.get(encoding, encoding)
-except locale.Error:
- encoding = 'ascii'
-encodingmode = os.environ.get("HGENCODINGMODE", "strict")
-fallbackencoding = 'ISO-8859-1'
-
-def tolocal(s):
- """
- Convert a string from internal UTF-8 to local encoding
-
- All internal strings should be UTF-8 but some repos before the
- implementation of locale support may contain latin1 or possibly
- other character sets. We attempt to decode everything strictly
- using UTF-8, then Latin-1, and failing that, we use UTF-8 and
- replace unknown characters.
- """
- for e in ('UTF-8', fallbackencoding):
- try:
- u = s.decode(e) # attempt strict decoding
- return u.encode(encoding, "replace")
- except LookupError, k:
- raise error.Abort("%s, please check your locale settings" % k)
- except UnicodeDecodeError:
- pass
- u = s.decode("utf-8", "replace") # last ditch
- return u.encode(encoding, "replace")
-
-def fromlocal(s):
- """
- Convert a string from the local character encoding to UTF-8
-
- We attempt to decode strings using the encoding mode set by
- HGENCODINGMODE, which defaults to 'strict'. In this mode, unknown
- characters will cause an error message. Other modes include
- 'replace', which replaces unknown characters with a special
- Unicode character, and 'ignore', which drops the character.
- """
- try:
- return s.decode(encoding, encodingmode).encode("utf-8")
- except UnicodeDecodeError, inst:
- sub = s[max(0, inst.start-10):inst.start+10]
- raise error.Abort("decoding near '%s': %s!" % (sub, inst))
- except LookupError, k:
- raise error.Abort("%s, please check your locale settings" % k)
-
-def colwidth(s):
- "Find the column width of a UTF-8 string for display"
- d = s.decode(encoding, 'replace')
- if hasattr(unicodedata, 'east_asian_width'):
- w = unicodedata.east_asian_width
- return sum([w(c) in 'WF' and 2 or 1 for c in d])
- return len(d)
-