1 # Copyright (C) 2010 Apple Inc. All rights reserved.

     2 # 

     3 # Redistribution and use in source and binary forms, with or without

     4 # modification, are permitted provided that the following conditions

     5 # are met:

     6 # 1. Redistributions of source code must retain the above copyright

     7 #    notice, this list of conditions and the following disclaimer.

     8 # 2. Redistributions in binary form must reproduce the above copyright

     9 #    notice, this list of conditions and the following disclaimer in the

    10 #    documentation and/or other materials provided with the distribution.

    11 # 

    12 # THIS SOFTWARE IS PROVIDED BY APPLE INC. ``AS IS'' AND ANY

    13 # EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE

    14 # IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR

    15 # PURPOSE ARE DISCLAIMED.  IN NO EVENT SHALL APPLE INC. OR

    16 # CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,

    17 # EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,

    18 # PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR

    19 # PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY

    20 # OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT

    21 # (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE

    22 # OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. 

    23 

    24 types = {

    25     "wordchar": { "UseTable" : True, "data": ['_', ('0','9'), ('A', 'Z'), ('a','z')]},

    26     "nonwordchar": { "UseTable" : True, "Inverse": "wordchar", "data": ['`', (0, ord('0') - 1), (ord('9') + 1, ord('A') - 1), (ord('Z') + 1, ord('_') - 1), (ord('z') + 1, 0xffff)]},

    27     "newline": { "UseTable" : False, "data": ['\n', '\r', 0x2028, 0x2029]},

    28     "spaces": { "UseTable" : True, "data": [' ', ('\t', '\r'), 0xa0, 0x1680, 0x180e, 0x2028, 0x2029, 0x202f, 0x205f, 0x3000, (0x2000, 0x200a)]},

    29     "nonspaces": { "UseTable" : True, "Inverse": "spaces", "data": [(0, ord('\t') - 1), (ord('\r') + 1, ord(' ') - 1), (ord(' ') + 1, 0x009f), (0x00a1, 0x167f), (0x1681, 0x180d), (0x180f, 0x1fff), (0x200b, 0x2027), (0x202a, 0x202e), (0x2030, 0x205e), (0x2060, 0x2fff), (0x3001, 0xffff)]},

    30     "digits": { "UseTable" : False, "data": [('0', '9')]},

    31     "nondigits": { "UseTable" : False, "Inverse": "digits", "data": [(0, ord('0') - 1), (ord('9') + 1, 0xffff)] }

    32 }

    33 entriesPerLine = 50

    34 arrays = "";

    35 functions = "";

    36 

    37 for name, classes in types.items():

    38     ranges = [];

    39     size = 0;

    40     for _class in classes["data"]:

    41         if type(_class) == str:

    42             ranges.append((ord(_class), ord(_class)))

    43         elif type(_class) == int:

    44             ranges.append((_class, _class))

    45         else:

    46             (min, max) = _class;

    47             if type(min) == str:

    48                 min = ord(min)

    49             if type(max) == str:

    50                 max = ord(max)

    51             if max > 0x7f and min <= 0x7f:

    52                 ranges.append((min, 0x7f))

    53                 min = 0x80

    54             ranges.append((min,max))

    55     ranges.sort();

    56     

    57     if classes["UseTable"] and (not "Inverse" in classes):

    58         array = ("static const char _%sData[65536] = {\n" % name);

    59         i = 0

    60         for (min,max) in ranges:

    61             while i < min:

    62                 i = i + 1

    63                 array += ('0,')

    64                 if (i % entriesPerLine == 0) and (i != 0):

    65                     array += ('\n')

    66             while i <= max:

    67                 i = i + 1

    68                 if (i == 65536):

    69                     array += ("1")

    70                 else:

    71                     array += ('1,')

    72                 if (i % entriesPerLine == 0) and (i != 0):

    73                     array += ('\n')

    74         while i < 0xffff:

    75             array += ("0,")

    76             i = i + 1;

    77             if (i % entriesPerLine == 0) and (i != 0):

    78                 array += ('\n')

    79         if i == 0xffff:

    80             array += ("0")

    81         array += ("\n};\n\n");

    82         arrays += array

    83     

    84     # Generate createFunction:

    85     function = "";

    86     function += ("CharacterClass* %sCreate()\n" % name)

    87     function += ("{\n")

    88     if classes["UseTable"]:

    89         if "Inverse" in classes:

    90             function += ("    CharacterClass* characterClass = new CharacterClass(CharacterClassTable::create(_%sData, true));\n" % (classes["Inverse"]))

    91         else:

    92             function += ("    CharacterClass* characterClass = new CharacterClass(CharacterClassTable::create(_%sData, false));\n" % (name))

    93     else:

    94         function += ("    CharacterClass* characterClass = new CharacterClass(0);\n")

    95     for (min, max) in ranges:

    96         if (min == max):

    97             if (min > 127):

    98                 function += ("    characterClass->m_matchesUnicode.append(0x%04x);\n" % min)

    99             else:

   100                 function += ("    characterClass->m_matches.append(0x%02x);\n" % min)

   101             continue

   102         if (min > 127) or (max > 127):

   103             function += ("    characterClass->m_rangesUnicode.append(CharacterRange(0x%04x, 0x%04x));\n" % (min, max))

   104         else:

   105             function += ("    characterClass->m_ranges.append(CharacterRange(0x%02x, 0x%02x));\n" % (min, max))

   106     function += ("    return characterClass;\n")

   107     function += ("}\n\n")

   108     functions += function

   109 

   110 print(arrays)

   111 print(functions)

   112