Print also the filename of the EPub where the line was found.

1 files changed, 16 insertions, 4 deletions

diff --git a/epubgrep.py b/epubgrep.py
index 578c20b..f2da727 100755
--- a/epubgrep.py
+++ b/epubgrep.py
@@ -1,5 +1,6 @@
 #!/usr/bin/env python3
 import argparse
+import logging
 import os.path
 import re
 import zipfile
@@ -8,8 +9,14 @@ from typing import Any, Dict, List, Optional, Tuple
 
 import epub_meta
 
-def get_chapter_title(mdata:List[Dict[str, Any]], fname:str) -> Optional[Tuple[str, int]]:
+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]]:
     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]
@@ -17,26 +24,31 @@ def get_chapter_title(mdata:List[Dict[str, Any]], fname:str) -> Optional[Tuple[s
         return ('Unknown', 0)
 
 
-def grep_book(filename:str, pattern:str, flags:int):
+def grep_book(filename: str, pattern: str, flags: int):
     assert os.path.isfile(filename), "{} is not EPub file.".format(filename)
     sought_RE = re.compile(pattern, flags)
 
     metadata = epub_meta.get_epub_metadata(filename)
     book = zipfile.ZipFile(filename)
+    printed_booktitle = False
 
     for zif in book.infolist():
         with book.open(zif) as inf:
             printed_title = False
             for line in inf:
-                decoded_line = line.decode()
+                decoded_line = line.decode(errors='replace').strip()
                 if sought_RE.search(decoded_line):
+                    if not printed_booktitle:
+                        print('{}'.format(filename))
+                        printed_booktitle = True
                     if not printed_title:
                         chap_info = get_chapter_title(metadata.toc,
-                                                          zif.filename)
+                                                      zif.filename)
                         print("{}. {}:\n".format(chap_info[1], chap_info[0]))
                         printed_title = True
                     print(decoded_line)
 
+
 if __name__ == "__main__":
     parser = argparse.ArgumentParser(description='Grep through EPub book')
     parser.add_argument('pattern')