Strip numbers from wordlists.

Many wordlists have format "NNNNNN<tab>some-term". We try to
detect lines of this format and will parse them to get the term
(removing numbers and whitespaces).

diceware/wordlist.py

@@ -100,6 +100,9 @@ def get_signed_wordlist(file_descriptor):
             break
         if line.startswith('- '):
             line = line[2:]
+        match = RE_NUMBERED_WORDLIST_ENTRY.match(line)
+        if match:
+            line = match.groups()[0]
         if not line:
             continue
         result += [line, ]

tests/test_wordlist.py

@@ -67,8 +67,8 @@ class Test_GetSignedWordList(object):
         with open(wlist_path, 'r') as fd:
             result = get_signed_wordlist(fd)
         assert len(result) == 7776
-        assert "11111\ta" == result[0]
-        assert "66666\t@" == result[-1]
+        assert "a" == result[0]
+        assert "@" == result[-1]
 
 
 class TestWordlistModule(object):