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    if not value:
51        return "0";
52    assert(value[0] == "U")
53    assert(value[1] == "+")
54    return "0x" + value[2:]
55
56
57def offset_table_entry(offset):
58    return "    &staticEntityTable[%s]," % offset
59
60
61program_name = os.path.basename(__file__)
62if len(sys.argv) < 4 or sys.argv[1] != "-o":
63    # Python 3, change to: print("Usage: %s -o OUTPUT_FILE INPUT_FILE" % program_name, file=sys.stderr)
64    sys.stderr.write("Usage: %s -o OUTPUT_FILE INPUT_FILE\n" % program_name)
65    exit(1)
66
67output_path = sys.argv[2]
68input_path = sys.argv[3]
69
70html_entity_names_file = open(input_path)
71entries = list(csv.reader(html_entity_names_file))
72html_entity_names_file.close()
73
74entries.sort(key = lambda entry: entry[ENTITY])
75entity_count = len(entries)
76
77output_file = open(output_path, "w")
78
79output_file.write("""/*
80 * Copyright (C) 2010 Google, Inc. All Rights Reserved.
81 *
82 * Redistribution and use in source and binary forms, with or without
83 * modification, are permitted provided that the following conditions
84 * are met:
85 * 1. Redistributions of source code must retain the above copyright
86 *    notice, this list of conditions and the following disclaimer.
87 * 2. Redistributions in binary form must reproduce the above copyright
88 *    notice, this list of conditions and the following disclaimer in the
89 *    documentation and/or other materials provided with the distribution.
90 *
91 * THIS SOFTWARE IS PROVIDED BY APPLE INC. ``AS IS'' AND ANY
92 * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
93 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
94 * PURPOSE ARE DISCLAIMED.  IN NO EVENT SHALL APPLE INC. OR
95 * CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
96 * EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
97 * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
98 * PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY
99 * OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
100 * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
101 * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. 
102 */
103
104// THIS FILE IS GENERATED BY WebCore/html/parser/create-html-entity-table
105// DO NOT EDIT (unless you are a ninja)!
106
107#include "config.h"
108#include "HTMLEntityTable.h"
109
110namespace WebCore {
111
112namespace {
113""")
114
115for entry in entries:
116    output_file.write("static const UChar %s[] = %s;\n" % (
117        convert_entity_to_cpp_name(entry[ENTITY]),
118        convert_entity_to_uchar_array(entry[ENTITY])))
119
120output_file.write("""
121static const HTMLEntityTableEntry staticEntityTable[%s] = {\n""" % entity_count)
122
123index = {}
124offset = 0
125for entry in entries:
126    letter = entry[ENTITY][0]
127    if letter not in index:
128        index[letter] = offset
129    values = entry[VALUE].split(' ')
130    assert len(values) <= 2, values
131    output_file.write('    { %s, %s, %s, %s },\n' % (
132        convert_entity_to_cpp_name(entry[ENTITY]),
133        len(entry[ENTITY]),
134        convert_value_to_int(values[0]),
135        convert_value_to_int(values[1] if len(values) >= 2 else "")))
136    offset += 1
137
138output_file.write("""};
139
140""")
141
142output_file.write("static const HTMLEntityTableEntry* uppercaseOffset[] = {\n")
143for letter in string.ascii_uppercase:
144    output_file.write("%s\n" % offset_table_entry(index[letter]))
145output_file.write("%s\n" % offset_table_entry(index['a']))
146output_file.write("""};
147
148static const HTMLEntityTableEntry* lowercaseOffset[] = {\n""")
149for letter in string.ascii_lowercase:
150    output_file.write("%s\n" % offset_table_entry(index[letter]))
151output_file.write("%s\n" % offset_table_entry(entity_count))
152output_file.write("""};
153
154}
155
156const HTMLEntityTableEntry* HTMLEntityTable::firstEntryStartingWith(UChar c)
157{
158    if (c >= 'A' && c <= 'Z')
159        return uppercaseOffset[c - 'A'];
160    if (c >= 'a' && c <= 'z')
161        return lowercaseOffset[c - 'a'];
162    return 0;
163}
164
165const HTMLEntityTableEntry* HTMLEntityTable::lastEntryStartingWith(UChar c)
166{
167    if (c >= 'A' && c <= 'Z')
168        return uppercaseOffset[c - 'A' + 1] - 1;
169    if (c >= 'a' && c <= 'z')
170        return lowercaseOffset[c - 'a' + 1] - 1;
171    return 0;
172}
173
174const HTMLEntityTableEntry* HTMLEntityTable::firstEntry()
175{
176    return &staticEntityTable[0];
177}
178
179const HTMLEntityTableEntry* HTMLEntityTable::lastEntry()
180{
181    return &staticEntityTable[%s - 1];
182}
183
184}
185""" % entity_count)
186