summaryrefslogtreecommitdiffstats
path: root/chromium/third_party/WebKit/Source/core/html/parser/create-html-entity-table
blob: 587e8a8f5d11d027abb3826782953a3f8d58814f (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
#!/usr/bin/env python
# Copyright (c) 2010 Google Inc. All rights reserved.
#
# Redistribution and use in source and binary forms, with or without
# modification, are permitted provided that the following conditions are
# met:
# 
#     * Redistributions of source code must retain the above copyright
# notice, this list of conditions and the following disclaimer.
#     * Redistributions in binary form must reproduce the above
# copyright notice, this list of conditions and the following disclaimer
# in the documentation and/or other materials provided with the
# distribution.
#     * Neither the name of Google Inc. nor the names of its
# contributors may be used to endorse or promote products derived from
# this software without specific prior written permission.
# 
# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
# "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
# LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
# A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
# OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
# SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
# LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
# DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
# THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
# (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

"""This python script creates the raw data that is our entity
database. The representation is one string database containing all
strings we could need, and then a mapping from offset+length -> entity
data. That is compact, easy to use and efficient."""

import csv
import os.path
import string
import sys

ENTITY = 0
VALUE = 1

def convert_value_to_int(value):
    if not value:
        return "0";
    assert(value[0] == "U")
    assert(value[1] == "+")
    return "0x" + value[2:]


def offset_table_entry(offset):
    return "    &staticEntityTable[%s]," % offset


program_name = os.path.basename(__file__)
if len(sys.argv) < 4 or sys.argv[1] != "-o":
    # Python 3, change to: print("Usage: %s -o OUTPUT_FILE INPUT_FILE" % program_name, file=sys.stderr)
    sys.stderr.write("Usage: %s -o OUTPUT_FILE INPUT_FILE\n" % program_name)
    exit(1)

output_path = sys.argv[2]
input_path = sys.argv[3]

with open(input_path) as html_entity_names_file:
    entries = list(csv.reader(html_entity_names_file))

entries.sort(key = lambda entry: entry[ENTITY])
entity_count = len(entries)

output_file = open(output_path, "w")

output_file.write("""/*
 * Copyright (C) 2010 Google, Inc. All Rights Reserved.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions
 * are met:
 * 1. Redistributions of source code must retain the above copyright
 *    notice, this list of conditions and the following disclaimer.
 * 2. Redistributions in binary form must reproduce the above copyright
 *    notice, this list of conditions and the following disclaimer in the
 *    documentation and/or other materials provided with the distribution.
 *
 * THIS SOFTWARE IS PROVIDED BY APPLE INC. ``AS IS'' AND ANY
 * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
 * PURPOSE ARE DISCLAIMED.  IN NO EVENT SHALL APPLE INC. OR
 * CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
 * EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
 * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
 * PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY
 * OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
 * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
 * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. 
 */

// THIS FILE IS GENERATED BY core/html/parser/create-html-entity-table
// DO NOT EDIT (unless you are a ninja)!

#include "config.h"
#include "core/html/parser/HTMLEntityTable.h"

namespace WebCore {

namespace {
""")

assert len(entries) > 0, "Code assumes a non-empty entity array."
def check_ascii(entity_string):
    for c in entity_string:
        code = ord(c)
        assert 0 <= code <= 127, (c + " is not ASCII. Need to change type " +
                                  "of storage from LChar to UChar to support " +
                                  "this entity.")

output_file.write("static const LChar staticEntityStringStorage[] = {\n")
output_file.write("'")
all_data = ""
entity_offset = 0
first_output = True
saved_by_reusing = 0
for entry in entries:
    check_ascii(entry[ENTITY])
    # Reuse substrings from earlier entries. This saves 1-2000
    # characters, but it's O(n^2) and not very smart. The optimal
    # solution has to solve the "Shortest Common Superstring" problem
    # and that is NP-Complete or worse.
    #
    # This would be even more efficient if we didn't store the
    # semi-colon in the array but as a bit in the entry.
    entity = entry[ENTITY]
    already_existing_offset = all_data.find(entity)
    if already_existing_offset != -1:
        # Reusing space.
        this_offset = already_existing_offset
        saved_by_reusing += len(entity)
    else:
        if not first_output:
            output_file.write(",\n'")
        first_output = False

        # Try the end of the string and see if we can reuse that to
        # fit the start of the new entity.
        data_to_add = entity
        this_offset = entity_offset
        for truncated_len in range(len(entity) - 1, 0, -1):
            if all_data.endswith(entity[:truncated_len]):
                data_to_add = entity[truncated_len:]
                this_offset = entity_offset - truncated_len
                saved_by_reusing += truncated_len
                break

        output_file.write("', '".join(data_to_add))
        all_data += data_to_add
        output_file.write("'")
        entity_offset += len(data_to_add)
    assert len(entry) == 2, "We will use slot [2] in the list for the offset."
    assert this_offset < 32768 # Stored in a 16 bit short.
    entry.append(this_offset)

output_file.write("};\n")

index = {}
for offset, entry in enumerate(entries):
    starting_letter = entry[ENTITY][0]
    if starting_letter not in index:
        index[starting_letter] = offset

output_file.write("""
static const HTMLEntityTableEntry staticEntityTable[%s] = {\n""" % entity_count)

for entry in entries:
    values = entry[VALUE].split(' ')
    assert len(values) <= 2, values
    output_file.write('    { %s, %s, %s, %s }, // &%s\n' % (
        convert_value_to_int(values[0]),
        convert_value_to_int(values[1] if len(values) >= 2 else ""),
        entry[2],
        len(entry[ENTITY]),
        entry[ENTITY],
        ))

output_file.write("""};

""")

output_file.write("""
}
""")

output_file.write("static const short uppercaseOffset[] = {\n")
for letter in string.ascii_uppercase:
    output_file.write("%d,\n" % index[letter])
output_file.write("%d\n" % index['a'])
output_file.write("""};

static const short lowercaseOffset[] = {\n""")
for letter in string.ascii_lowercase:
    output_file.write("%d,\n" % index[letter])
output_file.write("%d\n" % entity_count)
output_file.write("""};

const LChar* HTMLEntityTable::entityString(const HTMLEntityTableEntry& entry)
{
    return staticEntityStringStorage + entry.entityOffset;
}

LChar HTMLEntityTableEntry::lastCharacter() const
{
    return HTMLEntityTable::entityString(*this)[length - 1];
}

const HTMLEntityTableEntry* HTMLEntityTable::firstEntryStartingWith(UChar c)
{
    if (c >= 'A' && c <= 'Z')
        return &staticEntityTable[uppercaseOffset[c - 'A']];
    if (c >= 'a' && c <= 'z')
        return &staticEntityTable[lowercaseOffset[c - 'a']];
    return 0;
}

const HTMLEntityTableEntry* HTMLEntityTable::lastEntryStartingWith(UChar c)
{
    if (c >= 'A' && c <= 'Z')
        return &staticEntityTable[uppercaseOffset[c - 'A' + 1]] - 1;
    if (c >= 'a' && c <= 'z')
        return &staticEntityTable[lowercaseOffset[c - 'a' + 1]] - 1;
    return 0;
}

const HTMLEntityTableEntry* HTMLEntityTable::firstEntry()
{
    return &staticEntityTable[0];
}

const HTMLEntityTableEntry* HTMLEntityTable::lastEntry()
{
    return &staticEntityTable[%s - 1];
}

}
""" % entity_count)