makeqstrdata.py 3.98 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
codepoint2name[ord('-')] = 'hyphen';
14

15
# add some custom names to map characters that aren't in HTML
16
17
18
codepoint2name[ord(' ')] = 'space'
codepoint2name[ord('\'')] = 'squot'
codepoint2name[ord(',')] = 'comma'
19
codepoint2name[ord('.')] = 'dot'
20
21
codepoint2name[ord(':')] = 'colon'
codepoint2name[ord('/')] = 'slash'
Damien George's avatar
Damien George committed
22
codepoint2name[ord('%')] = 'percent'
23
codepoint2name[ord('#')] = 'hash'
24
25
26
27
codepoint2name[ord('(')] = 'paren_open'
codepoint2name[ord(')')] = 'paren_close'
codepoint2name[ord('[')] = 'bracket_open'
codepoint2name[ord(']')] = 'bracket_close'
28
29
codepoint2name[ord('{')] = 'brace_open'
codepoint2name[ord('}')] = 'brace_close'
30
codepoint2name[ord('*')] = 'star'
31
codepoint2name[ord('!')] = 'bang'
32
codepoint2name[ord('\\')] = 'backslash'
33

34
35
# this must match the equivalent function in qstr.c
def compute_hash(qstr):
36
    hash = 5381
37
    for char in qstr:
38
        hash = (hash * 33) ^ ord(char)
39
40
    # Make sure that valid hash is never zero, zero means "hash not computed"
    return (hash & 0xffff) or 1
41
42
43

def do_work(infiles):
    # read the qstrs in from the input files
44
    qcfgs = {}
45
    qstrs = {}
46
47
48
    for infile in infiles:
        with open(infile, 'rt') as f:
            for line in f:
49
50
51
52
53
54
55
56
57
58
59
60
                line = line.strip()

                # is this a config line?
                match = re.match(r'^QCFG\((.+), (.+)\)', line)
                if match:
                    value = match.group(2)
                    if value[0] == '(' and value[-1] == ')':
                        # strip parenthesis from config value
                        value = value[1:-1]
                    qcfgs[match.group(1)] = value
                    continue

61
                # is this a QSTR line?
62
                match = re.match(r'^Q\((.*)\)$', line)
63
                if not match:
64
                    continue
65
66
67

                # get the qstr value
                qstr = match.group(1)
68
                ident = re.sub(r'[^A-Za-z0-9_]', lambda s: "_" + codepoint2name[ord(s.group(0))] + "_", qstr)
69
70

                # don't add duplicates
71
                if ident in qstrs:
72
73
                    continue

74
                # add the qstr to the list, with order number to retain original order in file
75
                qstrs[ident] = (len(qstrs), ident, qstr)
76

77
78
79
80
81
    # get config variables
    cfg_bytes_len = int(qcfgs['BYTES_IN_LEN'])
    cfg_max_len = 1 << (8 * cfg_bytes_len)

    # print out the starte of the generated C header file
82
    print('// This file was automatically generated by makeqstrdata.py')
83
    print('')
84

85
    # add NULL qstr with no hash or data
86
87
88
    print('QDEF(MP_QSTR_NULL, (const byte*)"\\x00\\x00%s" "")' % ('\\x00' * cfg_bytes_len))

    # go through each qstr and print it out
89
    for order, ident, qstr in sorted(qstrs.values(), key=lambda x: x[0]):
90
        qhash = compute_hash(qstr)
91
92
        # Calculate len of str, taking escapes into account
        qlen = len(qstr.replace("\\\\", "-").replace("\\", ""))
93
        qdata = qstr.replace('"', '\\"')
94
95
96
        if qlen >= cfg_max_len:
            print('qstr is too long:', qstr)
            assert False
97
        qlen_str = ('\\x%02x' * cfg_bytes_len) % tuple(((qlen >> (8 * i)) & 0xff) for i in range(cfg_bytes_len))
98
        print('QDEF(MP_QSTR_%s, (const byte*)"\\x%02x\\x%02x%s" "%s")' % (ident, qhash & 0xff, (qhash >> 8) & 0xff, qlen_str, qdata))
99
100
101
102
103
104
105
106
107
108

    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:
109
        print('exiting with error code', file=sys.stderr)
110
111
112
113
        exit(1)

if __name__ == "__main__":
    main()