diff mercurial/encoding.py @ 15066:24efa83d81cb stable

i18n: calculate terminal columns by width information of each characters

neither number of 'bytes' in any encoding nor 'characters' is
appropriate to calculate terminal columns for specified string.

this patch modifies MBTextWrapper for:

  - overriding '_wrap_chunks()' to make it use not built-in 'len()'
    but 'encoding.colwidth()' for columns of string

  - fixing '_cutdown()' to make it use 'encoding.colwidth()' instead
    of local, similar but incorrect implementation

this patch also modifies 'encoding.py':

  - dividing 'colwith()' into 2 pieces: one for calculation columns of
    specified UNICODE string, and another for rest part of original
    one. the former is used from MBTextWrapper in 'util.py'.

  - preventing 'colwidth()' from evaluating HGENCODINGAMBIGUOUS
    configuration per each invocation: 'unicodedata.east_asian_width'
    checking is kept intact for reducing startup cost.

--- a/mercurial/encoding.py	Sat Aug 06 23:52:20 2011 +0200
+++ b/mercurial/encoding.py	Sat Aug 27 04:56:12 2011 +0900
@@ -135,16 +135,17 @@
         raise error.Abort("%s, please check your locale settings" % k)
 
 # How to treat ambiguous-width characters. Set to 'wide' to treat as wide.
-ambiguous = os.environ.get("HGENCODINGAMBIGUOUS", "narrow")
+wide = (os.environ.get("HGENCODINGAMBIGUOUS", "narrow") == "wide"
+        and "WFA" or "WF")
 
 def colwidth(s):
     "Find the column width of a UTF-8 string for display"
-    d = s.decode(encoding, 'replace')
+    return ucolwidth(s.decode(encoding, 'replace'))
+
+def ucolwidth(d):
+    "Find the column width of a Unicode string for display"
     eaw = getattr(unicodedata, 'east_asian_width', None)
     if eaw is not None:
-        wide = "WF"
-        if ambiguous == "wide":
-            wide = "WFA"
         return sum([eaw(c) in wide and 2 or 1 for c in d])
     return len(d)