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_value_to_int(value):
46    if not value:
47        return "0";
48    assert(value[0] == "U")
49    assert(value[1] == "+")
50    return "0x" + value[2:]
51
52
53def offset_table_entry(offset):
54    return "    &staticEntityTable[%s]," % offset
55
56
57program_name = os.path.basename(__file__)
58if len(sys.argv) < 4 or sys.argv[1] != "-o":
59    # Python 3, change to: print("Usage: %s -o OUTPUT_FILE INPUT_FILE" % program_name, file=sys.stderr)
60    sys.stderr.write("Usage: %s -o OUTPUT_FILE INPUT_FILE\n" % program_name)
61    exit(1)
62
63output_path = sys.argv[2]
64input_path = sys.argv[3]
65
66html_entity_names_file = open(input_path)
67entries = list(csv.reader(html_entity_names_file))
68html_entity_names_file.close()
69
70entries.sort(key = lambda entry: entry[ENTITY])
71entity_count = len(entries)
72
73output_file = open(output_path, "w")
74
75output_file.write("""/*
76 * Copyright (C) 2010 Google, Inc. All Rights Reserved.
77 * Copyright (C) 2013 Apple 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    output_file.write("static const LChar %s[] = \"%s\";\n" % (convert_entity_to_cpp_name(entry[ENTITY]), entry[ENTITY]))
114
115output_file.write("""
116static const HTMLEntityTableEntry staticEntityTable[%s] = {\n""" % entity_count)
117
118index = {}
119offset = 0
120for entry in entries:
121    letter = entry[ENTITY][0]
122    if letter not in index:
123        index[letter] = offset
124    values = entry[VALUE].split(' ')
125    assert len(values) <= 2, values
126    output_file.write('    { %s, %s, %s, %s },\n' % (
127        convert_entity_to_cpp_name(entry[ENTITY]),
128        len(entry[ENTITY]),
129        convert_value_to_int(values[0]),
130        convert_value_to_int(values[1] if len(values) >= 2 else "")))
131    offset += 1
132
133output_file.write("""};
134
135""")
136
137output_file.write("static const HTMLEntityTableEntry* uppercaseOffset[] = {\n")
138for letter in string.ascii_uppercase:
139    output_file.write("%s\n" % offset_table_entry(index[letter]))
140output_file.write("%s\n" % offset_table_entry(index['a']))
141output_file.write("""};
142
143static const HTMLEntityTableEntry* lowercaseOffset[] = {\n""")
144for letter in string.ascii_lowercase:
145    output_file.write("%s\n" % offset_table_entry(index[letter]))
146output_file.write("%s\n" % offset_table_entry(entity_count))
147output_file.write("""};
148
149}
150
151const HTMLEntityTableEntry* HTMLEntityTable::firstEntryStartingWith(UChar c)
152{
153    if (c >= 'A' && c <= 'Z')
154        return uppercaseOffset[c - 'A'];
155    if (c >= 'a' && c <= 'z')
156        return lowercaseOffset[c - 'a'];
157    return 0;
158}
159
160const HTMLEntityTableEntry* HTMLEntityTable::lastEntryStartingWith(UChar c)
161{
162    if (c >= 'A' && c <= 'Z')
163        return uppercaseOffset[c - 'A' + 1] - 1;
164    if (c >= 'a' && c <= 'z')
165        return lowercaseOffset[c - 'a' + 1] - 1;
166    return 0;
167}
168
169const HTMLEntityTableEntry* HTMLEntityTable::firstEntry()
170{
171    return &staticEntityTable[0];
172}
173
174const HTMLEntityTableEntry* HTMLEntityTable::lastEntry()
175{
176    return &staticEntityTable[%s - 1];
177}
178
179}
180""" % entity_count)
181