shell2python

gistfile1.txt

Shell:

cat *.xml | sed 's/\([A-Z][[:alpha:]]\{0,\}\. [A-Z]\)/| \1/g' | tr '|' '\n' | sed 's/^\( .\{25\}\).*$/\1/g'

 Cn. Octauii praecidi capu
 P. Crassi 
 Sp. Albinus, homines cons
 M. Antonii, omnium eloque
 C. Caesaris, in quo mihi 
 C. Marius tum, cum Cimbri
 Tib. Graccho legum auctor
 C. Drusi domum compleri a
 Cn. Aufidius praetorius e
 M. Crassus, sed aliud mol

Python:

>>> regex = re.compile("[A-Z]'?\w{0,4}\. [A-Z]{0,}\w{0,}");
>>> regex.findall(text)
['Cn. Octauii', 'P. Crassi', 'Sp. Albinus', 'M. Antonii', 'C. Caesaris', 'C. Marius', 'Tib. Graccho', 'C. Drusi', 'Cn. Aufidius', 'M. Crassus']

PythonRegex.Com:

>>> regex = re.compile("([A-Z]'?\w{0,4}\. \b[A-Z]{0,}\b\w{0,}(\. )?(\b[A-Z]{0,}\b\w{0,})?)",re.UNICODE)
>>> r = regex.search(string)
>>> r
<_sre.SRE_Match object at 0xf5896972b7d36f08>
>>> regex.match(string)
None

# List the groups found
>>> r.groups()
(u'M. Tullius', None, u'')

# List the named dictionary objects found
>>> r.groupdict()
{}

# Run findall
>>> regex.findall(string)
[(u'M. Tullius', u'', u''), (u'Mer. Caio', u'', u''), (u'F. P. totalia', u'. ', u'totalia'), (u'Ga. Cesar', u'', u''), (u"M'. C. Memento", u'. ', u'Memento'), (u'M. Metello', u'', u''), (u'Q. Verrem', u'', u''), (u'M. Metellum', u'', u''), (u'M. Metellum', u'', u''), (u'Q. Metellum', u'', u''), (u'L. Metellus', u'', u''), (u"M'. Glabrionem", u'', u''), (u'M. Caesonius', u'', u''), (u'Q. Manlium', u'', u''), (u'Q. Cornificium', u'', u''), (u'P. Sulpicius', u'', u''), (u'M. Crepereius', u'', u''), (u'L. Cassius', u'', u''), (u'Cn. Tremellius', u'', u''), (u'M. Metelli', u'', u''), (u'Cn. Pompeius', u'', u''), (u'M. Metellum', u'', u'')]

# Run timeit test
>>> setup = ur"import re; regex =re.compile("([A-Z]'?\w{0,4}\. \b[A-Z]{0,}\b\w{0,}(\. )?(\ ...
>>> t = timeit.Timer('regex.search(string)',setup)
>>> t.timeit(10000)
6.82871484756

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# caio begotti <caio1982@gmail.com>
# this is under public domain

# reference: https://gist.github.com/2307114
# double-check: http://en.wiktionary.org/wiki/Appendix:Roman_praenomina

import codecs
import glob
import re

praenomina = []
for file in glob.glob('./*.xml'):
    content = codecs.open(file, "r", "utf8")
    text = content.read()
    regex = re.compile("[A-Z]'?\w{0,4}\. [A-Z]{0,}\w{0,}")
    for entry in regex.findall(text):
        praenomina.append(entry)

praenomina = sorted(set(praenomina))
for entry in praenomina:
    print entry.lower()

print len(praenomina)