More simple examples about python-hyperscan HOT 6 CLOSED

import sys

import hyperscan


def parse_patterns(filename):
    patterns = []
    with open(filename) as f:
        for line in f:
            if line.startswith('#'):
                continue
            columns = [chunk.strip() for chunk in line.split('\t')]
            if len(columns) != 3:
                continue
            columns[0] = int(columns[0])
            columns[1] = columns[1].encode()
            patterns.append(columns)
    return patterns


def match_handler(pattern_id, start, end, flags, context):
    pattern_name = context['names'][pattern_id]
    substr = context['input'][start:end]
    print(f'[match] {pattern_name}: `{substr}`')


def main(args):
    if len(args) != 2:
        print(f'usage: {sys.argv[0]} [patterns file] [input]')
        sys.exit(1)
    pattern_filename, input_str = args
    patterns = parse_patterns(pattern_filename)
    db = hyperscan.Database()
    pattern_ids, expressions, names = zip(*patterns)
    db.compile(expressions=expressions, ids=pattern_ids)
    context = {
        'input': input_str,
        'names': {
            pattern_id: names[i]
            for i, pattern_id in enumerate(pattern_ids)
        },
    }
    db.scan(
        input_str,
        match_event_handler=match_handler,
        context=context,
    )

if __name__ == '__main__':
    main(sys.argv[1:])

    db.compile(
        expressions=expressions,
        ids=pattern_ids,
        flags=hyperscan.HS_FLAG_SOM_LEFTMOST,
    )