1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
|
#!/usr/bin/env python3
import argparse
import concurrent.futures
import logging
import os.path
import re
import sys
import zipfile
from typing import Any, Dict, List, Optional, Tuple
import epub_meta
logging.basicConfig(format='%(levelname)s:%(funcName)s:%(message)s',
level=logging.INFO)
log = logging.getLogger('epubgrep')
def get_chapter_title(mdata: List[Dict[str, Any]], fname: str) -> Optional[Tuple[str, int]]:
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, counting: bool=False, color: bool=False):
assert os.path.isfile(filename), "{} is not EPub file.".format(filename)
sought_RE = re.compile('(' + pattern + ')', flags)
count = 0
out_title = ''
out = ''
mline = flags & re.M == re.M
try:
metadata = epub_meta.get_epub_metadata(filename)
except epub_meta.EPubException:
log.exception('Failed to open {}'.format(filename))
book = zipfile.ZipFile(filename)
printed_booktitle = False
for zif in book.infolist():
with book.open(zif) as inf:
if mline:
decoded_str = inf.read().decode(errors='replace')
res = sought_RE.search(decoded_str)
if res:
if not printed_booktitle:
out += '{}\n'.format(filename)
printed_booktitle = True
if counting:
count += 1
else:
chap_info = get_chapter_title(metadata.toc,
zif.filename)
out += "{}. {}:\n\n".format(chap_info[1], chap_info[0])
out += '{}\n\n'.format(res.group(0))
else:
printed_title = False
for line in inf:
decoded_line = line.decode(errors='replace').strip()
res = sought_RE.search(decoded_line)
if res:
if not out_title:
out_title = '{}'.format(filename)
if counting:
count += 1
else:
if not printed_booktitle:
out += out_title + '\n'
printed_booktitle = True
if not printed_title:
chap_info = get_chapter_title(metadata.toc,
zif.filename)
if chap_info is not None:
out += "{}. {}:\n\n".format(chap_info[1],
chap_info[0])
printed_title = True
# https://stackoverflow.com/a/33206814
# print("\033[31;1;4mHello\033[0m")
if not counting:
if color:
found_line = decoded_line.replace(
res.group(1),
"\033[31;1m" + res.group(1) + "\033[31;0m")
out += '{}\n'.format(found_line)
else:
out += decoded_line + '\n'
if count > 0:
out += '{:02d}:{}'.format(count, out_title)
return out
if __name__ == "__main__":
parser = argparse.ArgumentParser(description='Grep through EPub book')
parser.add_argument('pattern')
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_false',
help="Do NOT mark found patterns with color")
parser.add_argument('-m', '--multi-line',
action='store_true',
help="make search multi line")
args = parser.parse_args()
# log.debug('args = %s', args)
search_flags = 0
if args.ignore_case:
search_flags |= re.I
if args.multi_line:
search_flags |= re.M | re.S
with concurrent.futures.ProcessPoolExecutor() as executor:
fut_to_fname = {executor.submit(grep_book,
os.path.realpath(filename),
args.pattern, search_flags,
args.count, args.color):
filename for filename in args.files}
for future in concurrent.futures.as_completed(fut_to_fname):
fname = fut_to_fname[future]
try:
data = future.result()
if data:
data = data.rstrip()
if len(data) > 0:
print(data)
except (BrokenPipeError, KeyboardInterrupt):
sys.exit()
|
