aboutsummaryrefslogtreecommitdiffstats
path: root/epubgrep.py
diff options
context:
space:
mode:
authorMatěj Cepl <mcepl@cepl.eu>2021-05-09 10:49:02 +0200
committerMatěj Cepl <mcepl@cepl.eu>2021-05-09 10:52:18 +0200
commit5f8b8cdbd7c5706d00c86e098660f65586a282c8 (patch)
treeaa763c6ea074f96871113e647adb2c8d296a3cb0 /epubgrep.py
parente34704aada1840fa2b8c8629e15ed99dcd000374 (diff)
downloadepubgrep-5f8b8cdbd7c5706d00c86e098660f65586a282c8.tar.gz
When searching through metadata, search through tags as well.
Diffstat (limited to 'epubgrep.py')
-rwxr-xr-xepubgrep.py48
1 files changed, 33 insertions, 15 deletions
diff --git a/epubgrep.py b/epubgrep.py
index c66a326..189e8b7 100755
--- a/epubgrep.py
+++ b/epubgrep.py
@@ -12,7 +12,7 @@ from typing import Any, Dict, List, Optional, Tuple
import epub_meta
logging.basicConfig(format='%(levelname)s:%(funcName)s:%(message)s',
- level=logging.DEBUG)
+ level=logging.INFO)
log = logging.getLogger('epubgrep')
@@ -85,18 +85,35 @@ def _singleline_search(inf, sought_RE, out_title, filename, counting,
return count, out
-def _description_search(mdata: dict, sre: re.Pattern, fname: str,
+def _metadata_search(mdata: dict, sre: re.Pattern, fname: str,
col: bool) -> str:
+ """
+ Search through metadata, not text.
+
+ :param: mdata: complete metadata to search through
+ :param: sre: re.Pattern to search
+ :param: fname: filename of the book
+ :param: col: should we colorize the output
+ """
out = ''
- decoded_line = mdata['description']
- if decoded_line is None:
- return out
+ decoded_line = mdata.get('description')
+ tags = mdata.get('subject')
- res = sre.search(decoded_line)
- if res:
- title = '\n{}'.format(fname)
- out += title + '\n'
- out += _colorize_found(decoded_line, res, col)
+ if decoded_line:
+ res = sre.search(decoded_line)
+ if res:
+ title = f'\n{fname}'
+ out += title + '\n'
+ out += _colorize_found(decoded_line, res, col)
+ title = ''
+ if tags:
+ for tag in tags:
+ res = sre.search(tag)
+ if res:
+ if not title:
+ title = f'\n{fname}'
+ out += f'{title}\n'
+ out += _colorize_found(tag, res, col)
return out
@@ -120,8 +137,8 @@ def grep_book(filename: str, opts: argparse.Namespace,
book = zipfile.ZipFile(filename)
printed_booktitle = False
- if opts.description:
- return _description_search(metadata, sought_RE, filename, opts.color)
+ if opts.metadata:
+ return _metadata_search(metadata, sought_RE, filename, opts.color)
for zif in book.infolist():
with book.open(zif) as inf:
@@ -166,10 +183,11 @@ def main():
help="just counts of found patterns")
parser.add_argument('-C', '--weighted-count',
action='store_true',
- help="counts of found patterns as a proportion of whole text")
- parser.add_argument('-d', '--description',
+ help="counts of found patterns " +
+ "as a proportion of whole text")
+ parser.add_argument('-d', '--metadata',
action='store_true',
- help="search just in descriptions")
+ help="search just in metadata")
parser.add_argument('-i', '--ignore-case',
action='store_true',
help="make search case insensitive")