subversion/libsvn_subr/genctype.py

   1 #!/usr/bin/env python
   2 """getctype.py - Generate the svn_ctype character classification table.
   3 """
   4
   5 import string
   6
   7 # Table of ASCII character names
   8 names = ('nul', 'soh', 'stx', 'etx', 'eot', 'enq', 'ack', 'bel',
   9          'bs',  'ht',  'nl',  'vt',  'np',  'cr',  'so',  'si',
  10          'dle', 'dc1', 'dc2', 'dc3', 'dc4', 'nak', 'syn', 'etb',
  11          'can', 'em',  'sub', 'esc', 'fs',  'gs',  'rs',  'us',
  12          'sp',  '!',   '"',   '#',   '$',   '%',   '&',   '\'',
  13          '(',   ')',   '*',   '+',   ',',   '-',   '.',   '/',
  14          '0',   '1',   '2',   '3',   '4',   '5',   '6',   '7',
  15          '8',   '9',   ':',   ';',   '<',   '=',   '>',   '?',
  16          '@',   'A',   'B',   'C',   'D',   'E',   'F',   'G',
  17          'H',   'I',   'J',   'K',   'L',   'M',   'N',   'O',
  18          'P',   'Q',   'R',   'S',   'T',   'U',   'V',   'W',
  19          'X',   'Y',   'Z',   '[',   '\\',  ']',   '^',   '_',
  20          '`',   'a',   'b',   'c',   'd',   'e',   'f',   'g',
  21          'h',   'i',   'j',   'k',   'l',   'm',   'n',   'o',
  22          'p',   'q',   'r',   's',   't',   'u',   'v',   'w',
  23          'x',   'y',   'z',   '{',   '|',   '}',   '~',   'del')
  24
  25 # All whitespace characters:
  26 #   horizontal tab, vertical tab, new line, form feed, carriage return, space
  27 whitespace = (9, 10, 11, 12, 13, 32)
  28
  29 # Bytes not valid in UTF-8 sequences
  30 utf8_invalid = (0xE0, 0xF0, 0xF8, 0xFC, 0xFE, 0xFF)
  31
  32 print '    /* **** DO NOT EDIT! ****'
  33 print '       This table was generated by genctype.py, make changes there. */'
  34
  35 for c in xrange(256):
  36     bits = []
  37
  38     # Ascii subrange
  39     if c < 128:
  40         bits.append('SVN_CTYPE_ASCII')
  41
  42         if len(names[c]) == 1:
  43             name = string.center(names[c], 3)
  44         else:
  45             name = string.ljust(names[c], 3)
  46
  47         # Control characters
  48         if c < 32 or c == 127:
  49             bits.append('SVN_CTYPE_CNTRL')
  50
  51         # Whitespace characters
  52         if c in whitespace:
  53             bits.append('SVN_CTYPE_SPACE')
  54
  55         # Punctuation marks
  56         if c >= 33 and c < 48 \
  57            or c >= 58 and c < 65 \
  58            or c >= 91 and c < 97 \
  59            or c >= 123 and c < 127:
  60             bits.append('SVN_CTYPE_PUNCT')
  61
  62         # Decimal digits
  63         elif c >= 48 and c < 58:
  64             bits.append('SVN_CTYPE_DIGIT')
  65
  66         # Uppercase letters
  67         elif c >= 65 and c < 91:
  68             bits.append('SVN_CTYPE_UPPER')
  69             # Hexadecimal digits
  70             if c <= 70:
  71                 bits.append('SVN_CTYPE_XALPHA')
  72
  73         # Lowercase letters
  74         elif c >= 97 and c < 123:
  75             bits.append('SVN_CTYPE_LOWER')
  76             # Hexadecimal digits
  77             if c <= 102:
  78                 bits.append('SVN_CTYPE_XALPHA')
  79
  80     # UTF-8 multibyte sequences
  81     else:
  82         name = hex(c)[1:]
  83
  84         # Lead bytes (start of sequence)
  85         if c > 0xC0 and c < 0xFE and c not in utf8_invalid:
  86             bits.append('SVN_CTYPE_UTF8LEAD')
  87
  88         # Continuation bytes
  89         elif (c & 0xC0) == 0x80:
  90             bits.append('SVN_CTYPE_UTF8CONT')
  91
  92     if len(bits) == 0:
  93         flags = '0'
  94     else:
  95         flags = string.join(bits, ' | ')
  96     print '    /* %s */ %s,' % (name, flags)