lc_parse.py

from unicodedata import normalize as ucnorm, category

def lc2geonames(text, PY3):
    if PY3:
        if not isinstance(text, str):
            str(text, 'utf-8')
    else:
        if not isinstance(text, unicode):
            text = unicode(text)
    if '(' in text:
        text = text.replace('Ala.)', ', Alabama')
        text = text.replace('Alaska)', ', Alaska')
        text = text.replace('Ariz.)', ', Arizona')
        text = text.replace('Ark.)', ', Arkansas')
        text = text.replace('Calif.)', ', California')
        text = text.replace('Colo.)', ', Colorado')
        text = text.replace('Conn.)', ', Connecticut')
        text = text.replace('Del.)', ', Delaware')
        text = text.replace('D.C.)', ', District of Columbia')
        text = text.replace('Fla.)', ', Florida')
        text = text.replace('Ga.)', ', Georgia')
        text = text.replace('Hawaii)', ', Hawaii')
        text = text.replace('Idaho)', ', Idaho')
        text = text.replace('Ill.)', ', Illinois')
        text = text.replace('Ind.)', ', Indiana')
        text = text.replace('Iowa)', ', Iowa')
        text = text.replace('Kan.)', ', Kansas')
        text = text.replace('Ky.)', ', Kentucky')
        text = text.replace('La.)', ', Louisiana')
        text = text.replace('Me.)', ', Maine')
        text = text.replace('Md.)', ', Maryland')
        text = text.replace('Mass.)', ', Massachusetts')
        text = text.replace('Mich.)', ', Michigan')
        text = text.replace('Minn.)', ', Minnesota')
        text = text.replace('Miss.)', ', Mississippi')
        text = text.replace('Mo.)', ', Missouri')
        text = text.replace('Mont.)', ', Montana')
        text = text.replace('Neb.)', ', Nebraska')
        text = text.replace('Nev.)', ', Nevada')
        text = text.replace('N.H.)', ', New Hampshire')
        text = text.replace('N.J.)', ', New Jersey')
        text = text.replace('N.M.)', ', New Mexico')
        text = text.replace('N.Y.)', ', New York')
        text = text.replace('N.C.)', ', North Carolina')
        text = text.replace('N.D.)', ', North Dakota')
        text = text.replace('Ohio)', ', Ohio')
        text = text.replace('Okla.)', ', Oklahoma')
        text = text.replace('Or.)', ', Oregon')
        text = text.replace('Pa.)', ', Pennsylvania')
        text = text.replace('R.I.)', ', Rhode Island')
        text = text.replace('S.C.)', ', South Carolina')
        text = text.replace('S.D.)', ', South Dakota')
        text = text.replace('Tenn.)', ', Tennessee')
        text = text.replace('Tex.)', ', Texas')
        text = text.replace('Utah)', ', Utah')
        text = text.replace('Vt.)', ', Vermont')
        text = text.replace('Va.)', ', Virginia')
        text = text.replace('Wash.)', ', Washington')
        text = text.replace('W. Va.)', ', West Virginia')
        text = text.replace('Wis.)', ', Wisconsin')
        text = text.replace('Wyo.)', ', Wyoming')
        text = text.replace(' (', ' ')
        text = text.replace(')', ' ')
        text = text.replace(':', ',')
    return text