summaryrefslogtreecommitdiff
path: root/tools/js2c.py
blob: 69ec8a83c4b00338b7c365749c79b72d4fb833b0 (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
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
#!/usr/bin/env python
#
# Copyright 2006-2008 the V8 project authors. 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 is a utility for converting JavaScript source code into C-style
# char arrays. It is used for embedded JavaScript code in the V8
# library.

import os
from os.path import dirname
import re
import sys
import string

sys.path.append(dirname(__file__) + "/../deps/v8/tools");
import jsmin


def ToCArray(filename, lines):
  result = []
  row = 1
  col = 0
  for chr in lines:
    col += 1
    if chr == "\n" or chr == "\r":
      row += 1
      col = 0

    value = ord(chr)

    if value >= 128:
      print 'non-ascii value ' + filename + ':' + str(row) + ':' + str(col)
      sys.exit(1);

    result.append(str(value))
  result.append("0")
  return ", ".join(result)


def CompressScript(lines, do_jsmin):
  # If we're not expecting this code to be user visible, we can run it through
  # a more aggressive minifier.
  if do_jsmin:
    minifier = JavaScriptMinifier()
    return minifier.JSMinify(lines)

  # Remove stuff from the source that we don't want to appear when
  # people print the source code using Function.prototype.toString().
  # Note that we could easily compress the scripts mode but don't
  # since we want it to remain readable.
  #lines = re.sub('//.*\n', '\n', lines) # end-of-line comments
  #lines = re.sub(re.compile(r'/\*.*?\*/', re.DOTALL), '', lines) # comments.
  #lines = re.sub('\s+\n+', '\n', lines) # trailing whitespace
  return lines


def ReadFile(filename):
  file = open(filename, "rt")
  try:
    lines = file.read()
  finally:
    file.close()
  return lines


def ReadLines(filename):
  result = []
  for line in open(filename, "rt"):
    if '#' in line:
      line = line[:line.index('#')]
    line = line.strip()
    if len(line) > 0:
      result.append(line)
  return result


def LoadConfigFrom(name):
  import ConfigParser
  config = ConfigParser.ConfigParser()
  config.read(name)
  return config


def ParseValue(string):
  string = string.strip()
  if string.startswith('[') and string.endswith(']'):
    return string.lstrip('[').rstrip(']').split()
  else:
    return string


def ExpandConstants(lines, constants):
  for key, value in constants.items():
    lines = lines.replace(key, str(value))
  return lines


def ExpandMacros(lines, macros):
  for name, macro in macros.items():
    start = lines.find(name + '(', 0)
    while start != -1:
      # Scan over the arguments
      assert lines[start + len(name)] == '('
      height = 1
      end = start + len(name) + 1
      last_match = end
      arg_index = 0
      mapping = { }
      def add_arg(str):
        # Remember to expand recursively in the arguments
        replacement = ExpandMacros(str.strip(), macros)
        mapping[macro.args[arg_index]] = replacement
      while end < len(lines) and height > 0:
        # We don't count commas at higher nesting levels.
        if lines[end] == ',' and height == 1:
          add_arg(lines[last_match:end])
          last_match = end + 1
        elif lines[end] in ['(', '{', '[']:
          height = height + 1
        elif lines[end] in [')', '}', ']']:
          height = height - 1
        end = end + 1
      # Remember to add the last match.
      add_arg(lines[last_match:end-1])
      result = macro.expand(mapping)
      # Replace the occurrence of the macro with the expansion
      lines = lines[:start] + result + lines[end:]
      start = lines.find(name + '(', end)
  return lines

class TextMacro:
  def __init__(self, args, body):
    self.args = args
    self.body = body
  def expand(self, mapping):
    result = self.body
    for key, value in mapping.items():
        result = result.replace(key, value)
    return result

class PythonMacro:
  def __init__(self, args, fun):
    self.args = args
    self.fun = fun
  def expand(self, mapping):
    args = []
    for arg in self.args:
      args.append(mapping[arg])
    return str(self.fun(*args))

CONST_PATTERN = re.compile('^const\s+([a-zA-Z0-9_]+)\s*=\s*([^;]*);$')
MACRO_PATTERN = re.compile('^macro\s+([a-zA-Z0-9_]+)\s*\(([^)]*)\)\s*=\s*([^;]*);$')
PYTHON_MACRO_PATTERN = re.compile('^python\s+macro\s+([a-zA-Z0-9_]+)\s*\(([^)]*)\)\s*=\s*([^;]*);$')

def ReadMacros(lines):
  constants = { }
  macros = { }
  for line in lines:
    hash = line.find('#')
    if hash != -1: line = line[:hash]
    line = line.strip()
    if len(line) is 0: continue
    const_match = CONST_PATTERN.match(line)
    if const_match:
      name = const_match.group(1)
      value = const_match.group(2).strip()
      constants[name] = value
    else:
      macro_match = MACRO_PATTERN.match(line)
      if macro_match:
        name = macro_match.group(1)
        args = map(string.strip, macro_match.group(2).split(','))
        body = macro_match.group(3).strip()
        macros[name] = TextMacro(args, body)
      else:
        python_match = PYTHON_MACRO_PATTERN.match(line)
        if python_match:
          name = python_match.group(1)
          args = map(string.strip, python_match.group(2).split(','))
          body = python_match.group(3).strip()
          fun = eval("lambda " + ",".join(args) + ': ' + body)
          macros[name] = PythonMacro(args, fun)
        else:
          raise ("Illegal line: " + line)
  return (constants, macros)


HEADER_TEMPLATE = """\
#ifndef node_natives_h
#define node_natives_h
namespace node {

%(source_lines)s\

struct _native {
  const char* name;
  const char* source;
  size_t source_len;
};

static const struct _native natives[] = {

%(native_lines)s\

  { NULL, NULL } /* sentinel */

};

}
#endif
"""


NATIVE_DECLARATION = """\
  { "%(id)s", %(id)s_native, sizeof(%(id)s_native)-1 },
"""

SOURCE_DECLARATION = """\
  const char %(id)s_native[] = { %(data)s };
"""


GET_DELAY_INDEX_CASE = """\
    if (strcmp(name, "%(id)s") == 0) return %(i)i;
"""


GET_DELAY_SCRIPT_SOURCE_CASE = """\
    if (index == %(i)i) return Vector<const char>(%(id)s, %(length)i);
"""


GET_DELAY_SCRIPT_NAME_CASE = """\
    if (index == %(i)i) return Vector<const char>("%(name)s", %(length)i);
"""

def JS2C(source, target):
  ids = []
  delay_ids = []
  modules = []
  # Locate the macros file name.
  consts = {}
  macros = {}

  for s in source:
    if 'macros.py' == (os.path.split(str(s))[1]):
      (consts, macros) = ReadMacros(ReadLines(str(s)))
    else:
      modules.append(s)

  # Build source code lines
  source_lines = [ ]
  source_lines_empty = []

  native_lines = []

  for s in modules:
    delay = str(s).endswith('-delay.js')
    lines = ReadFile(str(s))
    do_jsmin = lines.find('// jsminify this file, js2c: jsmin') != -1

    lines = ExpandConstants(lines, consts)
    lines = ExpandMacros(lines, macros)
    lines = CompressScript(lines, do_jsmin)
    data = ToCArray(s, lines)
    id = os.path.basename(str(s)).split('.')[0]
    if delay: id = id[:-6]
    if delay:
      delay_ids.append((id, len(lines)))
    else:
      ids.append((id, len(lines)))
    source_lines.append(SOURCE_DECLARATION % { 'id': id, 'data': data })
    source_lines_empty.append(SOURCE_DECLARATION % { 'id': id, 'data': 0 })
    native_lines.append(NATIVE_DECLARATION % { 'id': id })
  
  # Build delay support functions
  get_index_cases = [ ]
  get_script_source_cases = [ ]
  get_script_name_cases = [ ]

  i = 0
  for (id, length) in delay_ids:
    native_name = "native %s.js" % id
    get_index_cases.append(GET_DELAY_INDEX_CASE % { 'id': id, 'i': i })
    get_script_source_cases.append(GET_DELAY_SCRIPT_SOURCE_CASE % {
      'id': id,
      'length': length,
      'i': i
    })
    get_script_name_cases.append(GET_DELAY_SCRIPT_NAME_CASE % {
      'name': native_name,
      'length': len(native_name),
      'i': i
    });
    i = i + 1

  for (id, length) in ids:
    native_name = "native %s.js" % id
    get_index_cases.append(GET_DELAY_INDEX_CASE % { 'id': id, 'i': i })
    get_script_source_cases.append(GET_DELAY_SCRIPT_SOURCE_CASE % {
      'id': id,
      'length': length,
      'i': i
    })
    get_script_name_cases.append(GET_DELAY_SCRIPT_NAME_CASE % {
      'name': native_name,
      'length': len(native_name),
      'i': i
    });
    i = i + 1

  # Emit result
  output = open(str(target[0]), "w")
  output.write(HEADER_TEMPLATE % {
    'builtin_count': len(ids) + len(delay_ids),
    'delay_count': len(delay_ids),
    'source_lines': "\n".join(source_lines),
    'native_lines': "\n".join(native_lines),
    'get_index_cases': "".join(get_index_cases),
    'get_script_source_cases': "".join(get_script_source_cases),
    'get_script_name_cases': "".join(get_script_name_cases)
  })
  output.close()

  if len(target) > 1:
    output = open(str(target[1]), "w")
    output.write(HEADER_TEMPLATE % {
      'builtin_count': len(ids) + len(delay_ids),
      'delay_count': len(delay_ids),
      'source_lines': "\n".join(source_lines_empty),
      'get_index_cases': "".join(get_index_cases),
      'get_script_source_cases': "".join(get_script_source_cases),
      'get_script_name_cases': "".join(get_script_name_cases)
    })
    output.close()

def main():
  natives = sys.argv[1]
  source_files = sys.argv[2:]
  JS2C(source_files, [natives])

if __name__ == "__main__":
  main()