| 1 |
#! /usr/bin/env python |
| 2 |
|
| 3 |
# Copyright (C) 2016 Apple Inc. All rights reserved. |
| 4 |
# |
| 5 |
# Redistribution and use in source and binary forms, with or without |
| 6 |
# modification, are permitted provided that the following conditions |
| 7 |
# are met: |
| 8 |
# |
| 9 |
# 1. Redistributions of source code must retain the above copyright |
| 10 |
# notice, this list of conditions and the following disclaimer. |
| 11 |
# 2. Redistributions in binary form must reproduce the above copyright |
| 12 |
# notice, this list of conditions and the following disclaimer in the |
| 13 |
# documentation and/or other materials provided with the distribution. |
| 14 |
# |
| 15 |
# THIS SOFTWARE IS PROVIDED BY APPLE AND ITS CONTRIBUTORS "AS IS" AND ANY |
| 16 |
# EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED |
| 17 |
# WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE |
| 18 |
# DISCLAIMED. IN NO EVENT SHALL APPLE OR ITS CONTRIBUTORS BE LIABLE FOR ANY |
| 19 |
# DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES |
| 20 |
# (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; |
| 21 |
# LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND |
| 22 |
# ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT |
| 23 |
# (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF |
| 24 |
# THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. |
| 25 |
|
| 26 |
# This tool processes the Unicode Character Database file CaseFolding.txt to create |
| 27 |
# canonicalization table as decribed in ECMAScript 6 standard in section |
| 28 |
# "21.2.2.8.2 Runtime Semantics: Canonicalize()", step 2. |
| 29 |
|
| 30 |
import optparse |
| 31 |
import os |
| 32 |
import re |
| 33 |
import sys |
| 34 |
|
| 35 |
header = """/* |
| 36 |
* Copyright (C) 2016 Apple Inc. All rights reserved. |
| 37 |
* |
| 38 |
* Redistribution and use in source and binary forms, with or without |
| 39 |
* modification, are permitted provided that the following conditions |
| 40 |
* are met: |
| 41 |
* |
| 42 |
* 1. Redistributions of source code must retain the above copyright |
| 43 |
* notice, this list of conditions and the following disclaimer. |
| 44 |
* 2. Redistributions in binary form must reproduce the above copyright |
| 45 |
* notice, this list of conditions and the following disclaimer in the |
| 46 |
* documentation and/or other materials provided with the distribution. |
| 47 |
* |
| 48 |
* THIS SOFTWARE IS PROVIDED BY APPLE AND ITS CONTRIBUTORS "AS IS" AND ANY |
| 49 |
* EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED |
| 50 |
* WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE |
| 51 |
* DISCLAIMED. IN NO EVENT SHALL APPLE OR ITS CONTRIBUTORS BE LIABLE FOR ANY |
| 52 |
* DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES |
| 53 |
* (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; |
| 54 |
* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND |
| 55 |
* ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT |
| 56 |
* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF |
| 57 |
* THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. |
| 58 |
*/ |
| 59 |
|
| 60 |
// DO NO EDIT! - This file was generated by generateYarrCanonicalizeUnicode |
| 61 |
|
| 62 |
#include "config.h" |
| 63 |
#include "YarrCanonicalize.h" |
| 64 |
|
| 65 |
namespace JSC { namespace Yarr { |
| 66 |
|
| 67 |
""" |
| 68 |
|
| 69 |
footer = """} } // JSC::Yarr |
| 70 |
""" |
| 71 |
|
| 72 |
MaxUnicode = 0x10ffff |
| 73 |
commonAndSimpleLinesRE = re.compile(r"(?P<code>[0-9A-F]+)\s*;\s*[CS]\s*;\s*(?P<mapping>[0-9A-F]+)", re.IGNORECASE) |
| 74 |
|
| 75 |
def openOrExit(path, mode): |
| 76 |
try: |
| 77 |
dirname = os.path.dirname(path) |
| 78 |
if not os.path.isdir(dirname): |
| 79 |
os.makedirs(dirname) |
| 80 |
if sys.version_info.major >= 3: |
| 81 |
return open(path, mode, encoding="UTF-8") |
| 82 |
else: |
| 83 |
return open(path, mode) |
| 84 |
except IOError as e: |
| 85 |
print("I/O error opening {0}, ({1}): {2}".format(path, e.errno, e.strerror)) |
| 86 |
exit(1) |
| 87 |
|
| 88 |
class Canonicalize: |
| 89 |
def __init__(self): |
| 90 |
self.canonicalGroups = {}; |
| 91 |
|
| 92 |
def addMapping(self, code, mapping): |
| 93 |
if mapping not in self.canonicalGroups: |
| 94 |
self.canonicalGroups[mapping] = [] |
| 95 |
self.canonicalGroups[mapping].append(code) |
| 96 |
|
| 97 |
def readCaseFolding(self, file): |
| 98 |
codesSeen = set() |
| 99 |
for line in file: |
| 100 |
line = line.split('#', 1)[0] |
| 101 |
line = line.rstrip() |
| 102 |
if (not len(line)): |
| 103 |
continue |
| 104 |
|
| 105 |
fields = commonAndSimpleLinesRE.match(line) |
| 106 |
if (not fields): |
| 107 |
continue |
| 108 |
|
| 109 |
code = int(fields.group('code'), 16) |
| 110 |
mapping = int(fields.group('mapping'), 16) |
| 111 |
|
| 112 |
codesSeen.add(code) |
| 113 |
self.addMapping(code, mapping) |
| 114 |
|
| 115 |
for i in range(MaxUnicode + 1): |
| 116 |
if i in codesSeen: |
| 117 |
continue; |
| 118 |
|
| 119 |
self.addMapping(i, i) |
| 120 |
|
| 121 |
def createTables(self, file): |
| 122 |
typeInfo = [""] * (MaxUnicode + 1) |
| 123 |
characterSets = [] |
| 124 |
|
| 125 |
for mapping in sorted(self.canonicalGroups.keys()): |
| 126 |
characters = self.canonicalGroups[mapping] |
| 127 |
if len(characters) == 1: |
| 128 |
typeInfo[characters[0]] = "CanonicalizeUnique:0" |
| 129 |
else: |
| 130 |
characters.sort() |
| 131 |
if len(characters) > 2: |
| 132 |
for ch in characters: |
| 133 |
typeInfo[ch] = "CanonicalizeSet:%d" % len(characterSets) |
| 134 |
characterSets.append(characters) |
| 135 |
else: |
| 136 |
low = characters[0] |
| 137 |
high = characters[1] |
| 138 |
delta = high - low |
| 139 |
if delta == 1: |
| 140 |
type = "CanonicalizeAlternatingUnaligned:0" if low & 1 else "CanonicalizeAlternatingAligned:0" |
| 141 |
typeInfo[low] = type |
| 142 |
typeInfo[high] = type |
| 143 |
else: |
| 144 |
typeInfo[low] = "CanonicalizeRangeLo:%d" % delta |
| 145 |
typeInfo[high] = "CanonicalizeRangeHi:%d" % delta |
| 146 |
|
| 147 |
rangeInfo = [] |
| 148 |
end = 0 |
| 149 |
while end <= MaxUnicode: |
| 150 |
begin = end |
| 151 |
type = typeInfo[end] |
| 152 |
while end < MaxUnicode and typeInfo[end + 1] == type: |
| 153 |
end = end + 1 |
| 154 |
rangeInfo.append({"begin": begin, "end": end, "type": type}) |
| 155 |
end = end + 1 |
| 156 |
|
| 157 |
for i in range(len(characterSets)): |
| 158 |
characters = "" |
| 159 |
cur_set = characterSets[i] |
| 160 |
for ch in cur_set: |
| 161 |
characters = characters + "0x{character:04x}, ".format(character=ch) |
| 162 |
file.write("const UChar32 unicodeCharacterSet{index:d}[] = {{ {characters}0 }};\n".format(index=i, characters=characters)) |
| 163 |
|
| 164 |
file.write("\n") |
| 165 |
file.write("static const size_t UNICODE_CANONICALIZATION_SETS = {setCount:d};\n".format(setCount=len(characterSets))) |
| 166 |
file.write("const UChar32* const unicodeCharacterSetInfo[UNICODE_CANONICALIZATION_SETS] = {\n") |
| 167 |
|
| 168 |
for i in range(len(characterSets)): |
| 169 |
file.write(" unicodeCharacterSet{setNumber:d},\n".format(setNumber=i)) |
| 170 |
|
| 171 |
file.write("};\n") |
| 172 |
file.write("\n") |
| 173 |
file.write("const size_t UNICODE_CANONICALIZATION_RANGES = {rangeCount:d};\n".format(rangeCount=len(rangeInfo))) |
| 174 |
file.write("const CanonicalizationRange unicodeRangeInfo[UNICODE_CANONICALIZATION_RANGES] = {\n") |
| 175 |
|
| 176 |
for info in rangeInfo: |
| 177 |
typeAndValue = info["type"].split(":") |
| 178 |
file.write(" {{ 0x{begin:04x}, 0x{end:04x}, 0x{value:04x}, {type} }},\n".format(begin=info["begin"], end=info["end"], value=int(typeAndValue[1]), type=typeAndValue[0])) |
| 179 |
|
| 180 |
file.write("};\n") |
| 181 |
file.write("\n") |
| 182 |
|
| 183 |
|
| 184 |
if __name__ == "__main__": |
| 185 |
parser = optparse.OptionParser(usage = "usage: %prog <CaseFolding.txt> <YarrCanonicalizeUnicode.h>") |
| 186 |
(options, args) = parser.parse_args() |
| 187 |
|
| 188 |
if len(args) != 2: |
| 189 |
parser.error("<CaseFolding.txt> <YarrCanonicalizeUnicode.h>") |
| 190 |
|
| 191 |
caseFoldingTxtPath = args[0] |
| 192 |
canonicalizeHPath = args[1] |
| 193 |
caseFoldingTxtFile = openOrExit(caseFoldingTxtPath, "r") |
| 194 |
canonicalizeHFile = openOrExit(canonicalizeHPath, "w") |
| 195 |
|
| 196 |
canonicalize = Canonicalize() |
| 197 |
canonicalize.readCaseFolding(caseFoldingTxtFile) |
| 198 |
|
| 199 |
canonicalizeHFile.write(header); |
| 200 |
canonicalize.createTables(canonicalizeHFile) |
| 201 |
canonicalizeHFile.write(footer); |
| 202 |
|
| 203 |
caseFoldingTxtFile.close() |
| 204 |
canonicalizeHFile.close() |
| 205 |
|
| 206 |
exit(0) |