forked from firebase/firebase-ios-sdk
- Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathbinary_to_array.py
executable file
·313 lines (261 loc) · 9.72 KB
/
binary_to_array.py
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
#!/usr/bin/env python2
# Copyright 2018 Google LLC
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
"""Utility to convert binary data into a C/C++ array.
Usage: %s --input=input_file.bin [--output_source=output_source.cc]
[--output_header=output_header.h] [--cpp_namespace=namespace]
[--header_guard=HEADER_GUARD_TEXT] [--array=array_c_identifier]
[--array_size=array_size_c_identifier] [--filename=override_filename]
[--filename_identifier=filename_c_identifier]
By default, the output source file will be named the same as the input file,
but with .cc as the extension; the output header file will be named the
same as the input file but with .h as the extension.
By default, the data will be in an array named $NAME_data and the size will
be in a constant named $NAME_length, and the filename will be stored in
$NAME_filename. In all these cases, $NAME is the input filename (sans path and
extension) with runs of non-alphanumeric characters changed to underscores. The
header guard will be generated from the output header filename in a similar way.
By default, the data will be placed in the root namespace. If the data is placed
in the root namespace, it will be declared as a C array (using extern "C" if
compiled in C++ mode).
The actual size of $NAME_data is $NAME_length + 1, where it contains an extra
0x00 at the end. When data is actually text, $NAME_data can be used as a valid C
string directly.
"""
fromosimportpath
fromreimportsub
importargparse
importlogging
importos
arg_parser=argparse.ArgumentParser()
arg_parser.add_argument("input",
help="Input file containing binary data to embed.")
arg_parser.add_argument("--output_source",
help="Output source file, defining the array data.")
arg_parser.add_argument("--output_header",
help="Output header file, declaring the array data.")
arg_parser.add_argument("--array", help="Identifier for the array.")
arg_parser.add_argument("--array_size", help="Identifier for the array size.")
arg_parser.add_argument("--filename", help="Override file name in code.")
arg_parser.add_argument("--filename_identifier",
help="Where to put the filename.")
arg_parser.add_argument("--header_guard",
help="Header guard to #define in the output header.")
arg_parser.add_argument("--cpp_namespace",
help="C++ namespace to use. "
"If blank, will generate a C array.")
# How many hex bytes to display in a line. Each "0x00, " takes 6 characters, so
# a width of 12 lets us fit within 80 characters.
WIDTH=12
defheader(header_guard, namespaces, array_name, array_size_name, fileid):
"""Return a C/C++ header for the given array.
Args:
header_guard: Name of the HEADER_GUARD to define.
namespaces: List of namespaces, outer to inner.
array_name: Name of the array.
array_size_name: Name of the array size constant.
fileid: Name of the identifier containing the file name.
Returns:
A list of strings containing the C/C++ header file, line-by-line.
"""
data= []
data.extend([
"// Copyright 2019 Google Inc. All Rights Reserved.",
"",
"#ifndef %s"%header_guard,
"#define %s"%header_guard,
"",
"#include <cstdlib>",
""
])
ifnamespaces:
data.extend([
"namespace %s {"%nsfornsinnamespaces
])
else:
data.extend([
"#if defined(__cplusplus)",
"extern \"C\" {",
"#endif // defined(__cplusplus)"])
data.extend([
"",
"extern const size_t %s;"%array_size_name,
"extern const unsigned char %s[];"%array_name,
"extern const char %s[];"%fileid,
])
data.extend([
""
])
ifnamespaces:
data.extend([
"} // namespace %s"%nsfornsinreversed(namespaces)
])
else:
data.extend([
"#if defined(__cplusplus)",
"} // extern \"C\"",
"#endif // defined(__cplusplus)"
])
data.extend([
"",
"#endif // %s"%header_guard,
""
])
returndata
defsource(namespaces, array_name, array_size_name, fileid, filename,
input_bytes, include_name):
"""Return a C/C++ source file for the given array.
Args:
namespaces: List of namespaces, outer to inner.
array_name: Name of the array.
array_size_name: Name of the array size constant.
fileid: Name of the identifier containing the filename.
filename: The original data filename itself.
input_bytes: Binary data to put into the array.
include_name: Name of the corresponding header file to include.
Returns:
A string containing the C/C++ source file.
"""
ifos.name=='nt':
# Force forward slashes on Windows
include_name=include_name.replace('\\', '/')
data= []
data.extend([
"// Copyright 2019 Google Inc. All Rights Reserved.",
"",
"#include \"%s\""%include_name,
"",
"#include <cstdlib>",
""
])
ifnamespaces:
data.extend([
"namespace %s {"%nsfornsinnamespaces
])
else:
data.extend([
"#if defined(__cplusplus)",
"extern \"C\" {",
"#endif // defined(__cplusplus)"])
data.extend([
"",
"extern const size_t %s;"%array_size_name,
"extern const char %s[];"%fileid,
"extern const unsigned char %s[];"%array_name, "",
"const unsigned char %s[] = {"%array_name
])
length=len(input_bytes)
line=""
foridxinrange(0, length):
ifidx%WIDTH==0:
line+=" "
else:
line+=" "
line+="0x%02x,"%input_bytes[idx]
ifidx%WIDTH==WIDTH-1:
data.append(line)
line=""
data.append(line)
data.append(" 0x00 // Extra \\0 to make it a C string")
data.extend([
"};",
"",
"const size_t %s ="%array_size_name,
" sizeof(%s) - 1;"%array_name,
"",
"const char %s[] = \"%s\";"% (fileid, filename),
"",
])
ifnamespaces:
data.extend([
"} // namespace %s"%nsfornsinnamespaces
][::-1]) # close namespaces in reverse order
else:
data.extend([
"#if defined(__cplusplus)",
"} // extern \"C\"",
"#endif // defined(__cplusplus)"
])
data.extend([
""
])
returndata
def_get_repo_root():
"""Returns the root of the source repository.
"""
scripts_dir=os.path.abspath(os.path.dirname(__file__))
assertos.path.basename(scripts_dir) =='scripts'
root_dir=os.path.dirname(scripts_dir)
assertos.path.isdir(os.path.join(root_dir, '.github'))
returnroot_dir
defmain():
"""Read an binary input file and output to a C/C++ source file as an array.
"""
args=arg_parser.parse_args()
input_file=args.input
input_file_base=os.path.splitext(args.input)[0]
output_source=args.output_source
ifnotoutput_source:
output_source=input_file_base+".cc"
logging.debug("Using default --output_source='%s'", output_source)
output_header=args.output_header
ifnotoutput_header:
output_header=input_file_base+".h"
logging.debug("Using default --output_header='%s'", output_header)
root_dir=_get_repo_root()
absolute_dir=path.dirname(output_header)
relative_dir=path.relpath(absolute_dir, root_dir)
relative_header_path=path.join(relative_dir, path.basename(output_header))
identifier_base=sub("[^0-9a-zA-Z]+", "_", path.basename(input_file_base))
array_name=args.array
ifnotarray_name:
array_name=identifier_base+"_data"
logging.debug("Using default --array='%s'", array_name)
array_size_name=args.array_size
ifnotarray_size_name:
array_size_name=identifier_base+"_size"
logging.debug("Using default --array_size='%s'", array_size_name)
fileid=args.filename_identifier
ifnotfileid:
fileid=identifier_base+"_filename"
logging.debug("Using default --filename_identifier='%s'", fileid)
filename=args.filename
iffilenameisNone: # but not if it's the empty string
filename=path.basename(input_file)
logging.debug("Using default --filename='%s'", filename)
header_guard=args.header_guard
ifnotheader_guard:
header_guard=sub("[^0-9a-zA-Z]+", "_", relative_header_path).upper() +'_'
# Avoid double underscores to stay compliant with the Standard.
header_guard=sub("[_]+", "_", header_guard)
logging.debug("Using default --header_guard='%s'", header_guard)
namespace=args.cpp_namespace
namespaces=namespace.split("::") ifnamespaceelse []
withopen(input_file, "rb") asinfile:
input_bytes=bytearray(infile.read())
logging.debug("Read %d bytes from %s", len(input_bytes), input_file)
header_text="\n".join(header(header_guard, namespaces, array_name,
array_size_name, fileid))
source_text="\n".join(source(namespaces, array_name, array_size_name,
fileid, filename, input_bytes,
relative_header_path))
withopen(output_header, "w") ashdr:
hdr.write(header_text)
logging.debug("Wrote header file %s", output_header)
withopen(output_source, "w") assrc:
src.write(source_text)
logging.debug("Wrote source file %s", output_source)
if__name__=="__main__":
main()