diff options
| -rwxr-xr-x | epubgrep.py | 73 |
1 files changed, 50 insertions, 23 deletions
diff --git a/epubgrep.py b/epubgrep.py index 78728d7..9118787 100755 --- a/epubgrep.py +++ b/epubgrep.py @@ -15,18 +15,19 @@ log = logging.getLogger('epubgrep') def get_chapter_title(mdata: List[Dict[str, Any]], fname: str) -> Optional[Tuple[str, int]]: - found_list = [(x['title'], x['index']) for x in mdata if x['src'] == fname] - log.debug('found_list = %s', found_list) - if len(found_list) > 0: - chap_title = found_list[0][0].strip(' \t.0123456789') - return chap_title, found_list[0][1] - else: - return ('Unknown', 0) + if mdata is not None: + found_list = [(x['title'], x['index']) for x in mdata if x['src'] == fname] + if len(found_list) > 0: + chap_title = found_list[0][0].strip(' \t.0123456789') + return chap_title, found_list[0][1] + else: + return ('Unknown', 0) -def grep_book(filename: str, pattern: str, flags: int): +def grep_book(filename: str, pattern: str, flags: int, counting: bool=False, color: bool=False): assert os.path.isfile(filename), "{} is not EPub file.".format(filename) - sought_RE = re.compile(pattern, flags) + sought_RE = re.compile('(' + pattern + ')', flags) + count = 0 mline = flags & re.M == re.M @@ -43,37 +44,62 @@ def grep_book(filename: str, pattern: str, flags: int): if not printed_booktitle: print('{}'.format(filename)) printed_booktitle = True - chap_info = get_chapter_title(metadata.toc, zif.filename) - print("{}. {}:\n".format(chap_info[1], chap_info[0])) - print('{}\n'.format(res.group(0))) + if counting: + count += 1 + else: + chap_info = get_chapter_title(metadata.toc, zif.filename) + print("{}. {}:\n".format(chap_info[1], chap_info[0])) + print('{}\n'.format(res.group(0))) else: printed_title = False for line in inf: decoded_line = line.decode(errors='replace').strip() - if sought_RE.search(decoded_line): + res = sought_RE.search(decoded_line) + if res: if not printed_booktitle: print('{}'.format(filename)) printed_booktitle = True - if not printed_title: - chap_info = get_chapter_title(metadata.toc, - zif.filename) - print("{}. {}:\n".format(chap_info[1], chap_info[0])) - printed_title = True - print(decoded_line) + if counting: + count += 1 + else: + if not printed_title: + chap_info = get_chapter_title(metadata.toc, + zif.filename) + if chap_info is not None: + print("{}. {}:\n".format(chap_info[1], chap_info[0])) + printed_title = True + # https://stackoverflow.com/a/33206814 + # print("\033[31;1;4mHello\033[0m") + if color: + found_line = decoded_line.replace( + res.group(1), + "\033[31;1m" + res.group(1) + "\033[31;0m") + print('{}\n'.format(found_line)) + else: + print(decoded_line) + + if count > 0: + print('Found: {}'.format(count)) if __name__ == "__main__": parser = argparse.ArgumentParser(description='Grep through EPub book') parser.add_argument('pattern') - parser.add_argument('filename') + parser.add_argument('files', nargs='+') + parser.add_argument('-c', '--count', + action='store_true', + help="just counts of found patterns") parser.add_argument('-i', '--ignore-case', action='store_true', help="make search case insensitive") + parser.add_argument('-o', '--color', '--colour', + action='store_true', + help="make search case insensitive") parser.add_argument('-m', '--multi-line', action='store_true', help="make search multi line") args = parser.parse_args() - log.debug('args = %s', args) + # log.debug('args = %s', args) search_flags = 0 if args.ignore_case: @@ -82,5 +108,6 @@ if __name__ == "__main__": if args.multi_line: search_flags |= re.M | re.S - book_fname = os.path.realpath(args.filename) - grep_book(book_fname, args.pattern, search_flags) + for filename in args.files: + book_fname = os.path.realpath(filename) + grep_book(book_fname, args.pattern, search_flags, args.count, args.color) |