makeqstrdata.py 3.03 KB
Newer Older
1
2
from __future__ import print_function

3
4
import argparse
import re
5
import sys
6
7
8
9
10
11
12

# 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
13

14
15
# add some custom names to map characters that aren't in HTML
codepoint2name[ord('.')] = 'dot'
16
17
codepoint2name[ord(':')] = 'colon'
codepoint2name[ord('/')] = 'slash'
18

19
20
# this must match the equivalent function in qstr.c
def compute_hash(qstr):
21
    hash = 5381
22
    for char in qstr:
23
        hash = (hash * 33) ^ ord(char)
24
25
26
27
    return hash & 0xffff

def do_work(infiles):
    # read the qstrs in from the input files
28
    qstrs = {}
29
    cpp_header_blocks = 3
30
31
32
33
34
35
36
37
38
39
40
    for infile in infiles:
        with open(infile, 'rt') as f:
            line_number = 0
            for line in f:
                line_number += 1
                line = line.strip()

                # ignore blank lines and comments
                if len(line) == 0 or line.startswith('//'):
                    continue

41
42
43
44
45
46
47
48
                # We'll have 3 line-number lines for py/qstrdefs.h - initial, leaving it to
                # go into other headers, and returning to it.
                if line.startswith('# ') and 'py/qstrdefs.h' in line:
                    cpp_header_blocks -= 1
                    continue
                if cpp_header_blocks != 0:
                    continue

49
                # verify line is of the correct form
50
                match = re.match(r'Q\((.+)\)$', line)
51
                if not match:
52
                    print('({}:{}) bad qstr format, got {}'.format(infile, line_number, line), file=sys.stderr)
53
54
55
56
                    return False

                # get the qstr value
                qstr = match.group(1)
57
                ident = re.sub(r'[^A-Za-z0-9_]', lambda s: "_" + codepoint2name[ord(s.group(0))] + "_", qstr)
58
59

                # don't add duplicates
60
                if ident in qstrs:
61
62
                    continue

63
                # add the qstr to the list, with order number to retain original order in file
64
                qstrs[ident] = (len(qstrs), ident, qstr)
65
66
67

    # process the qstrs, printing out the generated C header file
    print('// This file was automatically generated by makeqstrdata.py')
68
    print('')
69
    for order, ident, qstr in sorted(qstrs.values(), key=lambda x: x[0]):
70
71
        qhash = compute_hash(qstr)
        qlen = len(qstr)
72
        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))
73
74
75
76
77
78
79
80
81
82

    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:
83
        print('exiting with error code', file=sys.stderr)
84
85
86
87
        exit(1)

if __name__ == "__main__":
    main()