diff options
Diffstat (limited to 'py/makeqstrdata.py')
| -rw-r--r-- | py/makeqstrdata.py | 22 |
1 files changed, 15 insertions, 7 deletions
diff --git a/py/makeqstrdata.py b/py/makeqstrdata.py index c4b7be42e7..c5ad708e89 100644 --- a/py/makeqstrdata.py +++ b/py/makeqstrdata.py @@ -1,6 +1,13 @@ import argparse import re +# 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 + # this must match the equivalent function in qstr.c def compute_hash(qstr): hash = 0 @@ -10,7 +17,7 @@ def compute_hash(qstr): def do_work(infiles): # read the qstrs in from the input files - qstrs = [] + qstrs = {} for infile in infiles: with open(infile, 'rt') as f: line_number = 0 @@ -23,28 +30,29 @@ def do_work(infiles): continue # verify line is of the correct form - match = re.match(r'Q\(([0-9A-Za-z_]+)\)$', line) + match = re.match(r'Q\((.+)\)$', line) if not match: print('({}:{}) bad qstr format, got {}'.format(infile, line_number, line)) return False # get the qstr value qstr = match.group(1) + ident = re.sub(r'[^A-Za-z0-9_]', lambda s: "_" + codepoint2name[ord(s.group(0))] + "_", qstr) # don't add duplicates - if qstr in qstrs: + if ident in qstrs: continue - # add the qstr to the list - qstrs.append(qstr) + # add the qstr to the list, with order number to retain original order in file + qstrs[ident] = (len(qstrs), ident, qstr) # process the qstrs, printing out the generated C header file print('// This file was automatically generated by makeqstrdata.py') print('') - for qstr in qstrs: + for order, ident, qstr in sorted(qstrs.values(), key=lambda x: x[0]): qhash = compute_hash(qstr) qlen = len(qstr) - print('Q({}, (const byte*)"\\x{:02x}\\x{:02x}\\x{:02x}\\x{:02x}" "{}")'.format(qstr, qhash & 0xff, (qhash >> 8) & 0xff, qlen & 0xff, (qlen >> 8) & 0xff, qstr)) + 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)) return True |