1 files changed, 45 insertions, 14 deletions
diff --git a/generate_reference.py b/generate_reference.py
index edc4703..e182205 100755
--- a/generate_reference.py
+++ b/generate_reference.py
@@ -1,4 +1,5 @@
 #!/usr/bin/env python3
+# -*- coding: utf-8 -*-
 
 import collections
 import logging
@@ -91,15 +92,38 @@ TranslDict = collections.OrderedDict([
 CZ_BOOKS = tuple(TranslDict.keys())
 EN_BOOKS = tuple(TranslDict.values())
 
-BIBLE_REF_PARSE_RE = re.compile(r'(%s)?\s*([0-9]+),([0-9—.-]+)'
-                                % '|'.join(CZ_BOOKS))
-SPLIT_VERSE_RE = re.compile('[—.-]')
-
+BIBLE_REF_PARSE_RE = re.compile(r'''
+    (%s)?  # Name of the Bible book (optional)
+    \s*([0-9]+),  # chapter number separated by whitespace
+    ([0-9—.-]+)   # verse number(s) separated by (optional) comma
+''' % '|'.join(CZ_BOOKS), flags=re.VERBOSE)
+ONLY_VERSE_PARSE_RE = re.compile(r'''
+    v\.\s+       # abbreviation of "verš" (verse)
+    ([0-9—.-]+)  # verse number(s) separated by (optional) comma
+''', flags=re.VERBOSE)
+SPLIT_VERSE_RE = re.compile('''
+    (\d+)
+    [—.-]
+    (\d+)
+''', flags=re.VERBOSE)
+
+
+def verse_interval(verse):
+    match = SPLIT_VERSE_RE.search(verse)
+    logging.debug('match = %s', match)
+    if match:
+        matches = match.groups()
+        verse = int(match.group(1))
+        next_verse = int(match.group(2))
+        logging.debug('verse, next_verse = %s, %s', verse, next_verse)
+        return (verse, next_verse)
+    else:
+        return (int(verse),)
 
 def parse_notes_test(instr):
     logging.debug('%s\ninstr = %s', '-' * 30, instr)
     matches = BIBLE_REF_PARSE_RE.findall(instr)
-    logging.debug('matches = %s', matches)
+    logging.debug('BIBLE_REF_PARSE_RE matches = %s', matches)
     out_list = []
     book = None
 
@@ -109,16 +133,23 @@ def parse_notes_test(instr):
             book = match[0]
         elif book is None:
             book = ''
-        chapter = int(match[1])
-        verse = match[2]
-        if SPLIT_VERSE_RE.search(verse):
-            verse_split = SPLIT_VERSE_RE.split(verse)
-            verse = int(verse_split[0])
-            next_verse = int(verse_split[1])
-            logging.debug('verse, next_verse = %s, %s', verse, next_verse)
-            out_list.append((book, chapter, verse, next_verse))
+        logging.debug('match[1] = %s', match[1])
+        if match[1]:
+            chapter = int(match[1].rstrip(','))
         else:
-            out_list.append((book, chapter, int(verse)))
+            chapter = 0
+        logging.debug('match[2] = %s', match[2])
+        verse = match[2]
+        out_list.append((book, chapter) + verse_interval(match[2]))
+    matches = ONLY_VERSE_PARSE_RE.findall(instr)
+    logging.debug('ONLY_VERSE_PARSE_RE matches = %s', matches)
+
+    for match in matches:
+        logging.debug('match = %s', match)
+        if match:
+            out = ('', 0) + verse_interval(match)
+            out_list.append(out)
+
     return tuple(out_list)