2014-03-10 07:07:35 +00:00
|
|
|
from __future__ import print_function
|
|
|
|
|
2014-01-21 21:40:13 +00:00
|
|
|
import argparse
|
|
|
|
import re
|
2014-03-08 15:03:25 +00:00
|
|
|
import sys
|
2014-01-24 22:22:00 +00:00
|
|
|
|
|
|
|
# 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
|
2014-04-13 02:28:46 +00:00
|
|
|
codepoint2name[ord('-')] = 'hyphen';
|
2014-01-21 21:40:13 +00:00
|
|
|
|
2014-02-15 11:34:50 +00:00
|
|
|
# add some custom names to map characters that aren't in HTML
|
|
|
|
codepoint2name[ord('.')] = 'dot'
|
2014-02-17 22:06:37 +00:00
|
|
|
codepoint2name[ord(':')] = 'colon'
|
|
|
|
codepoint2name[ord('/')] = 'slash'
|
2014-04-15 11:42:52 +00:00
|
|
|
codepoint2name[ord('%')] = 'percent'
|
2014-04-15 11:50:21 +00:00
|
|
|
codepoint2name[ord('#')] = 'hash'
|
2014-04-15 21:03:55 +00:00
|
|
|
codepoint2name[ord('{')] = 'brace_open'
|
|
|
|
codepoint2name[ord('}')] = 'brace_close'
|
2014-04-27 18:23:46 +00:00
|
|
|
codepoint2name[ord('*')] = 'star'
|
2014-02-15 11:34:50 +00:00
|
|
|
|
2014-01-21 21:40:13 +00:00
|
|
|
# this must match the equivalent function in qstr.c
|
|
|
|
def compute_hash(qstr):
|
2014-03-25 15:27:15 +00:00
|
|
|
hash = 5381
|
2014-01-21 21:40:13 +00:00
|
|
|
for char in qstr:
|
2014-03-25 15:27:15 +00:00
|
|
|
hash = (hash * 33) ^ ord(char)
|
2014-06-06 20:55:27 +00:00
|
|
|
# Make sure that valid hash is never zero, zero means "hash not computed"
|
|
|
|
return (hash & 0xffff) or 1
|
2014-01-21 21:40:13 +00:00
|
|
|
|
|
|
|
def do_work(infiles):
|
|
|
|
# read the qstrs in from the input files
|
2014-01-23 22:22:00 +00:00
|
|
|
qstrs = {}
|
2014-01-21 21:40:13 +00:00
|
|
|
for infile in infiles:
|
|
|
|
with open(infile, 'rt') as f:
|
|
|
|
for line in f:
|
2014-05-02 19:10:47 +00:00
|
|
|
# is this a QSTR line?
|
|
|
|
match = re.match(r'^Q\((.+)\)$', line.strip())
|
|
|
|
if not match:
|
2014-04-13 12:16:51 +00:00
|
|
|
continue
|
2014-01-21 21:40:13 +00:00
|
|
|
|
|
|
|
# get the qstr value
|
|
|
|
qstr = match.group(1)
|
2014-01-23 22:22:00 +00:00
|
|
|
ident = re.sub(r'[^A-Za-z0-9_]', lambda s: "_" + codepoint2name[ord(s.group(0))] + "_", qstr)
|
2014-01-21 21:40:13 +00:00
|
|
|
|
|
|
|
# don't add duplicates
|
2014-01-23 22:22:00 +00:00
|
|
|
if ident in qstrs:
|
2014-01-21 21:40:13 +00:00
|
|
|
continue
|
|
|
|
|
2014-01-24 22:22:00 +00:00
|
|
|
# add the qstr to the list, with order number to retain original order in file
|
2014-04-11 17:36:08 +00:00
|
|
|
qstrs[ident] = (len(qstrs), ident, qstr)
|
2014-01-21 21:40:13 +00:00
|
|
|
|
|
|
|
# process the qstrs, printing out the generated C header file
|
|
|
|
print('// This file was automatically generated by makeqstrdata.py')
|
2014-01-21 23:28:27 +00:00
|
|
|
print('')
|
2014-04-11 17:36:08 +00:00
|
|
|
for order, ident, qstr in sorted(qstrs.values(), key=lambda x: x[0]):
|
2014-01-21 21:40:13 +00:00
|
|
|
qhash = compute_hash(qstr)
|
|
|
|
qlen = len(qstr)
|
2014-01-23 22:22:00 +00:00
|
|
|
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 21:40:13 +00:00
|
|
|
|
|
|
|
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 15:03:25 +00:00
|
|
|
print('exiting with error code', file=sys.stderr)
|
2014-01-21 21:40:13 +00:00
|
|
|
exit(1)
|
|
|
|
|
|
|
|
if __name__ == "__main__":
|
|
|
|
main()
|