558 

   558 

   559 _utf8len = [0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 2, 2, 3, 4]

   559 _utf8len = [0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 2, 2, 3, 4]

   560 

   560 

   561 

   561 

   562 def getutf8char(s, pos):

   562 def getutf8char(s, pos):

   564     '''get the next full utf-8 character in the given string, starting at pos

   564     '''get the next full utf-8 character in the given string, starting at pos

   565 

   565 

   566     Raises a UnicodeError if the given location does not start a valid

   566     Raises a UnicodeError if the given location does not start a valid

   567     utf-8 character.

   567     utf-8 character.

   568     '''

   568     '''

   577     c.decode("utf-8", _utf8strict)

   577     c.decode("utf-8", _utf8strict)

   578     return c

   578     return c

   579 

   579 

   580 

   580 

   581 def toutf8b(s):

   581 def toutf8b(s):

   583     '''convert a local, possibly-binary string into UTF-8b

   583     '''convert a local, possibly-binary string into UTF-8b

   584 

   584 

   585     This is intended as a generic method to preserve data when working

   585     This is intended as a generic method to preserve data when working

   586     with schemes like JSON and XML that have no provision for

   586     with schemes like JSON and XML that have no provision for

   587     arbitrary byte strings. As Mercurial often doesn't know

   587     arbitrary byte strings. As Mercurial often doesn't know