state_to_code.py

#!/usr/bin/env python

from __future__ import unicode_literals

import sys
import codecs
import re
import codecs

statecodes = (
    ("alabama", "al"), ("alaska", "ak"), ("arizona", "az"), ("arkansas", "ar"),
    ("california", "ca"), ("colorado", "co"), ("connecticut", "ct"),
    ("delaware", "de"), ("district of columbia", "dc"), ("florida", "fl"),
    ("georgia", "ga"), ("hawaii", "hi"), ("idaho", "id"), ("illinois", "il"),
    ("indiana", "in"),  ("kansas", "ks"), ("oklahoma", "ok"), ("kentucky", "ky"),
    ("louisiana", "la"), ("maine", "me"), ("maryland", "md"), ("wisconsin", "wi"),
    ("massachusetts", "ma"), ("michigan", "mi"), ("minnesota", "mn"),
    ("mississippi", "ms"), ("missouri", "mo"), ("montana", "mt"),
    ("nebraska", "ne"), ("nevada", "nv"), ("new hampshire", "nh"),
    ("new jersey", "nj"), ("new mexico", "nm"), ("new york", "ny"),
    ("north carolina", "nc"), ("north dakota", "nd"), ("ohio", "oh"),
    ("iowa", "ia"), ("oregon", "or"), ("pennsylvania", "pa"), ("wyoming", "wy"),
    ("rhode island", "ri"), ("south carolina", "sc"), ("south dakota", "sd"),
    ("tennessee", "tn"), ("texas", "tx"), ("utah", "ut"), ("vermont", "vt"),
    ("west virginia", "wv"), ("virginia", "va"), ("washington", "wa"),
)

re_map = [(re.compile(state,  re.IGNORECASE), code)
          for state, code in statecodes]

with codecs.open(sys.argv[1], encoding='utf-8') as inf:
    text = inf.read()

for re_state, code in re_map:
    text = re_state.sub(code, text)

with codecs.open(sys.argv[1], mode='wb', encoding='utf-8') as outf:
    outf.write(text)