2014-03-10 03:07:35 -04:00
|
|
|
from __future__ import print_function
|
|
|
|
|
2014-01-21 16:40:13 -05:00
|
|
|
import argparse
|
|
|
|
import re
|
2014-03-08 10:03:25 -05:00
|
|
|
import sys
|
2014-01-24 17:22:00 -05:00
|
|
|
|
|
|
|
# codepoint2name is different in Python 2 to Python 3
|
|
|
|
import platform
|
|
|
|
if platform.python_version_tuple()[0] == '2':
|
|
|
|
from htmlentitydefs import codepoint2name
|
|
|
|
elif platform.python_version_tuple()[0] == '3':
|
|
|
|
from html.entities import codepoint2name
|
2014-04-12 22:28:46 -04:00
|
|
|
codepoint2name[ord('-')] = 'hyphen';
|
2014-01-21 16:40:13 -05:00
|
|
|
|
2014-02-15 06:34:50 -05:00
|
|
|
# add some custom names to map characters that aren't in HTML
|
|
|
|
codepoint2name[ord('.')] = 'dot'
|
2014-02-17 17:06:37 -05:00
|
|
|
codepoint2name[ord(':')] = 'colon'
|
|
|
|
codepoint2name[ord('/')] = 'slash'
|
2014-04-15 07:42:52 -04:00
|
|
|
codepoint2name[ord('%')] = 'percent'
|
2014-02-15 06:34:50 -05:00
|
|
|
|
2014-01-21 16:40:13 -05:00
|
|
|
# this must match the equivalent function in qstr.c
|
|
|
|
def compute_hash(qstr):
|
2014-03-25 11:27:15 -04:00
|
|
|
hash = 5381
|
2014-01-21 16:40:13 -05:00
|
|
|
for char in qstr:
|
2014-03-25 11:27:15 -04:00
|
|
|
hash = (hash * 33) ^ ord(char)
|
2014-01-21 16:40:13 -05:00
|
|
|
return hash & 0xffff
|
|
|
|
|
2014-04-13 08:16:51 -04:00
|
|
|
# given a list of (name,regex) pairs, find the first one that matches the given line
|
2014-04-14 18:38:37 -04:00
|
|
|
def re_match_first(regexs, line):
|
2014-04-13 08:16:51 -04:00
|
|
|
for name, regex in regexs:
|
|
|
|
match = re.match(regex, line)
|
|
|
|
if match:
|
|
|
|
return name, match
|
|
|
|
return None, None
|
|
|
|
|
2014-04-14 18:38:37 -04:00
|
|
|
# regexs to recognise lines that the CPP emits
|
|
|
|
# use a list so that matching order is honoured
|
|
|
|
cpp_regexs = [
|
|
|
|
('qstr', r'Q\((.+)\)$'),
|
|
|
|
('cdecl', r'(typedef|extern) [A-Za-z0-9_* ]+;$')
|
|
|
|
]
|
|
|
|
|
2014-01-21 16:40:13 -05:00
|
|
|
def do_work(infiles):
|
|
|
|
# read the qstrs in from the input files
|
2014-01-23 17:22:00 -05:00
|
|
|
qstrs = {}
|
2014-01-21 16:40:13 -05:00
|
|
|
for infile in infiles:
|
|
|
|
with open(infile, 'rt') as f:
|
|
|
|
line_number = 0
|
|
|
|
for line in f:
|
|
|
|
line_number += 1
|
|
|
|
line = line.strip()
|
|
|
|
|
2014-04-13 08:16:51 -04:00
|
|
|
# ignore blank lines, comments and preprocessor directives
|
|
|
|
if len(line) == 0 or line.startswith('//') or line.startswith('#'):
|
2014-01-21 16:40:13 -05:00
|
|
|
continue
|
|
|
|
|
2014-04-13 08:16:51 -04:00
|
|
|
# work out what kind of line it is
|
2014-04-14 18:38:37 -04:00
|
|
|
match_kind, match = re_match_first(cpp_regexs, line)
|
2014-04-13 08:16:51 -04:00
|
|
|
if match_kind is None:
|
|
|
|
# unknown line format
|
2014-03-08 10:03:25 -05:00
|
|
|
print('({}:{}) bad qstr format, got {}'.format(infile, line_number, line), file=sys.stderr)
|
2014-01-21 16:40:13 -05:00
|
|
|
return False
|
2014-04-13 08:16:51 -04:00
|
|
|
elif match_kind != 'qstr':
|
|
|
|
# not a line with a qstr
|
|
|
|
continue
|
2014-01-21 16:40:13 -05:00
|
|
|
|
|
|
|
# get the qstr value
|
|
|
|
qstr = match.group(1)
|
2014-01-23 17:22:00 -05:00
|
|
|
ident = re.sub(r'[^A-Za-z0-9_]', lambda s: "_" + codepoint2name[ord(s.group(0))] + "_", qstr)
|
2014-01-21 16:40:13 -05:00
|
|
|
|
|
|
|
# don't add duplicates
|
2014-01-23 17:22:00 -05:00
|
|
|
if ident in qstrs:
|
2014-01-21 16:40:13 -05:00
|
|
|
continue
|
|
|
|
|
2014-01-24 17:22:00 -05:00
|
|
|
# add the qstr to the list, with order number to retain original order in file
|
2014-04-11 13:36:08 -04:00
|
|
|
qstrs[ident] = (len(qstrs), ident, qstr)
|
2014-01-21 16:40:13 -05:00
|
|
|
|
|
|
|
# process the qstrs, printing out the generated C header file
|
|
|
|
print('// This file was automatically generated by makeqstrdata.py')
|
2014-01-21 18:28:27 -05:00
|
|
|
print('')
|
2014-04-11 13:36:08 -04:00
|
|
|
for order, ident, qstr in sorted(qstrs.values(), key=lambda x: x[0]):
|
2014-01-21 16:40:13 -05:00
|
|
|
qhash = compute_hash(qstr)
|
|
|
|
qlen = len(qstr)
|
2014-01-23 17:22:00 -05:00
|
|
|
print('Q({}, (const byte*)"\\x{:02x}\\x{:02x}\\x{:02x}\\x{:02x}" "{}")'.format(ident, qhash & 0xff, (qhash >> 8) & 0xff, qlen & 0xff, (qlen >> 8) & 0xff, qstr))
|
2014-01-21 16:40:13 -05:00
|
|
|
|
|
|
|
return True
|
|
|
|
|
|
|
|
def main():
|
|
|
|
arg_parser = argparse.ArgumentParser(description='Process raw qstr file and output qstr data with length, hash and data bytes')
|
|
|
|
arg_parser.add_argument('files', nargs='+', help='input file(s)')
|
|
|
|
args = arg_parser.parse_args()
|
|
|
|
|
|
|
|
result = do_work(args.files)
|
|
|
|
if not result:
|
2014-03-08 10:03:25 -05:00
|
|
|
print('exiting with error code', file=sys.stderr)
|
2014-01-21 16:40:13 -05:00
|
|
|
exit(1)
|
|
|
|
|
|
|
|
if __name__ == "__main__":
|
|
|
|
main()
|