create-html-entity-table revision cad810f21b803229eb11403f9209855525a25d57 
1#!/usr/bin/env python
2# Copyright (c) 2010 Google Inc. All rights reserved.
3#
4# Redistribution and use in source and binary forms, with or without
5# modification, are permitted provided that the following conditions are
6# met:
7# 
8#     * Redistributions of source code must retain the above copyright
9# notice, this list of conditions and the following disclaimer.
10#     * Redistributions in binary form must reproduce the above
11# copyright notice, this list of conditions and the following disclaimer
12# in the documentation and/or other materials provided with the
13# distribution.
14#     * Neither the name of Google Inc. nor the names of its
15# contributors may be used to endorse or promote products derived from
16# this software without specific prior written permission.
17# 
18# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
19# "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
20# LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
21# A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
22# OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
23# SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
24# LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
25# DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
26# THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
27# (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
28# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
29
30import csv
31import os.path
32import string
33import sys
34
35ENTITY = 0
36VALUE = 1
37
38def convert_entity_to_cpp_name(entity):
39    postfix = "EntityName"
40    if entity[-1] == ";":
41        return "%sSemicolon%s" % (entity[:-1], postfix)
42    return "%s%s" % (entity, postfix)
43
44
45def convert_entity_to_uchar_array(entity):
46    return "{'%s'}" % "', '".join(entity)
47
48
49def convert_value_to_int(value):
50    assert(value[0] == "U")
51    assert(value[1] == "+")
52    return "0x" + value[2:]
53
54
55def offset_table_entry(offset):
56    return "    &staticEntityTable[%s]," % offset
57
58
59program_name = os.path.basename(__file__)
60if len(sys.argv) < 4 or sys.argv[1] != "-o":
61    print >> sys.stderr, "Usage: %s -o OUTPUT_FILE INPUT_FILE" % program_name
62    exit(1)
63
64output_path = sys.argv[2]
65input_path = sys.argv[3]
66
67html_entity_names_file = open(input_path)
68entries = list(csv.reader(html_entity_names_file))
69html_entity_names_file.close()
70
71entries.sort(lambda a, b: cmp(a[ENTITY], b[ENTITY]))
72entity_count = len(entries)
73
74output_file = open(output_path, "w")
75
76print >> output_file, """/*
77 * Copyright (C) 2010 Google, Inc. All Rights Reserved.
78 *
79 * Redistribution and use in source and binary forms, with or without
80 * modification, are permitted provided that the following conditions
81 * are met:
82 * 1. Redistributions of source code must retain the above copyright
83 *    notice, this list of conditions and the following disclaimer.
84 * 2. Redistributions in binary form must reproduce the above copyright
85 *    notice, this list of conditions and the following disclaimer in the
86 *    documentation and/or other materials provided with the distribution.
87 *
88 * THIS SOFTWARE IS PROVIDED BY APPLE INC. ``AS IS'' AND ANY
89 * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
90 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
91 * PURPOSE ARE DISCLAIMED.  IN NO EVENT SHALL APPLE INC. OR
92 * CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
93 * EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
94 * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
95 * PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY
96 * OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
97 * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
98 * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. 
99 */
100
101// THIS FILE IS GENERATED BY WebCore/html/parser/create-html-entity-table
102// DO NOT EDIT (unless you are a ninja)!
103
104#include "config.h"
105#include "HTMLEntityTable.h"
106
107namespace WebCore {
108
109namespace {
110"""
111
112for entry in entries:
113    print >> output_file, "const UChar %sEntityName[] = %s;" % (
114        convert_entity_to_cpp_name(entry[ENTITY]),
115        convert_entity_to_uchar_array(entry[ENTITY]))
116
117print >> output_file, """
118HTMLEntityTableEntry staticEntityTable[%s] = {""" % entity_count
119
120index = {}
121offset = 0
122for entry in entries:
123    letter = entry[ENTITY][0]
124    if not index.get(letter):
125        index[letter] = offset
126    print >> output_file, '    { %sEntityName, %s, %s },' % (
127        convert_entity_to_cpp_name(entry[ENTITY]),
128        len(entry[ENTITY]),
129        convert_value_to_int(entry[VALUE]))
130    offset += 1
131
132print >> output_file, """};
133"""
134
135print >> output_file, "const HTMLEntityTableEntry* uppercaseOffset[] = {"
136for letter in string.uppercase:
137    print >> output_file, offset_table_entry(index[letter])
138print >> output_file, offset_table_entry(index['a'])
139print >> output_file, """};
140
141const HTMLEntityTableEntry* lowercaseOffset[] = {"""
142for letter in string.lowercase:
143    print >> output_file, offset_table_entry(index[letter])
144print >> output_file, offset_table_entry(entity_count)
145print >> output_file, """};
146
147}
148
149const HTMLEntityTableEntry* HTMLEntityTable::firstEntryStartingWith(UChar c)
150{
151    if (c >= 'A' && c <= 'Z')
152        return uppercaseOffset[c - 'A'];
153    if (c >= 'a' && c <= 'z')
154        return lowercaseOffset[c - 'a'];
155    return 0;
156}
157
158const HTMLEntityTableEntry* HTMLEntityTable::lastEntryStartingWith(UChar c)
159{
160    if (c >= 'A' && c <= 'Z')
161        return uppercaseOffset[c - 'A' + 1] - 1;
162    if (c >= 'a' && c <= 'z')
163        return lowercaseOffset[c - 'a' + 1] - 1;
164    return 0;
165}
166
167const HTMLEntityTableEntry* HTMLEntityTable::firstEntry()
168{
169    return &staticEntityTable[0];
170}
171
172const HTMLEntityTableEntry* HTMLEntityTable::lastEntry()
173{
174    return &staticEntityTable[%s - 1];
175}
176
177}
178""" % entity_count
179