unicode 0.9.7 / usr / bin / paracode

#!/usr/bin/python

import sys, unicodedata
from optparse import OptionParser



table_cyrillic = {

'A' : u'\N{CYRILLIC CAPITAL LETTER A}',
'B' : u'\N{CYRILLIC CAPITAL LETTER VE}',
'C' : u'\N{CYRILLIC CAPITAL LETTER ES}',
'E' : u'\N{CYRILLIC CAPITAL LETTER IE}',
'H' : u'\N{CYRILLIC CAPITAL LETTER EN}',
'I' : u'\N{CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I}',
'J' : u'\N{CYRILLIC CAPITAL LETTER JE}',
'K' : u'\N{CYRILLIC CAPITAL LETTER KA}',
'M' : u'\N{CYRILLIC CAPITAL LETTER EM}',
'O' : u'\N{CYRILLIC CAPITAL LETTER O}',
'P' : u'\N{CYRILLIC CAPITAL LETTER ER}',
'S' : u'\N{CYRILLIC CAPITAL LETTER DZE}',
'T' : u'\N{CYRILLIC CAPITAL LETTER TE}',
'X' : u'\N{CYRILLIC CAPITAL LETTER HA}',
'Y' : u'\N{CYRILLIC CAPITAL LETTER U}',

'a' : u'\N{CYRILLIC SMALL LETTER A}',
'c' : u'\N{CYRILLIC SMALL LETTER ES}',
'e' : u'\N{CYRILLIC SMALL LETTER IE}',
'i' : u'\N{CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I}',
'j' : u'\N{CYRILLIC SMALL LETTER JE}',
'o' : u'\N{CYRILLIC SMALL LETTER O}',
'p' : u'\N{CYRILLIC SMALL LETTER ER}',
's' : u'\N{CYRILLIC SMALL LETTER DZE}',
'x' : u'\N{CYRILLIC SMALL LETTER HA}',
'y' : u'\N{CYRILLIC SMALL LETTER U}',

}

table_cyrillic_plus = {
'Y' : u'\N{CYRILLIC CAPITAL LETTER STRAIGHT U}',
'h' : u'\N{CYRILLIC SMALL LETTER SHHA}',
}

table_greek = {
'A' : u'\N{GREEK CAPITAL LETTER ALPHA}',
'B' : u'\N{GREEK CAPITAL LETTER BETA}',
'E' : u'\N{GREEK CAPITAL LETTER EPSILON}',
'H' : u'\N{GREEK CAPITAL LETTER ETA}',
'I' : u'\N{GREEK CAPITAL LETTER IOTA}',
'K' : u'\N{GREEK CAPITAL LETTER KAPPA}',
'M' : u'\N{GREEK CAPITAL LETTER MU}',
'N' : u'\N{GREEK CAPITAL LETTER NU}',
'O' : u'\N{GREEK CAPITAL LETTER OMICRON}',
'P' : u'\N{GREEK CAPITAL LETTER RHO}',
'T' : u'\N{GREEK CAPITAL LETTER TAU}',
'X' : u'\N{GREEK CAPITAL LETTER CHI}',
'Y' : u'\N{GREEK CAPITAL LETTER UPSILON}',
'Z' : u'\N{GREEK CAPITAL LETTER ZETA}',

'o' : u'\N{GREEK SMALL LETTER OMICRON}',
}

table_other = {
'!' : u'\N{LATIN LETTER RETROFLEX CLICK}',

'O' : u'\N{ARMENIAN CAPITAL LETTER OH}',
'S' : u'\N{ARMENIAN CAPITAL LETTER TIWN}',
'o' : u'\N{ARMENIAN SMALL LETTER OH}',
'n' : u'\N{ARMENIAN SMALL LETTER VO}',
}

table_cherokee = {
'A' : u'\N{CHEROKEE LETTER GO}',
'B' : u'\N{CHEROKEE LETTER YV}',
'C' : u'\N{CHEROKEE LETTER TLI}',
'D' : u'\N{CHEROKEE LETTER A}',
'E' : u'\N{CHEROKEE LETTER GV}',
'G' : u'\N{CHEROKEE LETTER NAH}',
'H' : u'\N{CHEROKEE LETTER MI}',
'J' : u'\N{CHEROKEE LETTER GU}',
'K' : u'\N{CHEROKEE LETTER TSO}',
'L' : u'\N{CHEROKEE LETTER TLE}',
'M' : u'\N{CHEROKEE LETTER LU}',
'P' : u'\N{CHEROKEE LETTER TLV}',
'R' : u'\N{CHEROKEE LETTER SV}',
'S' : u'\N{CHEROKEE LETTER DU}',
'T' : u'\N{CHEROKEE LETTER I}',
'V' : u'\N{CHEROKEE LETTER DO}',
'W' : u'\N{CHEROKEE LETTER LA}',
'Y' : u'\N{CHEROKEE LETTER GI}',
'Z' : u'\N{CHEROKEE LETTER NO}',

}

table_mirror = {

'A' : u'\N{FOR ALL}',
'B' : u'\N{CANADIAN SYLLABICS CARRIER KHA}',
'C' : u'\N{LATIN CAPITAL LETTER OPEN O}',
'D' : u'\N{CANADIAN SYLLABICS CARRIER PA}',
'E' : u'\N{LATIN CAPITAL LETTER REVERSED E}',
'F' : u'\N{TURNED CAPITAL F}',
'G' : u'\N{TURNED SANS-SERIF CAPITAL G}',
'H' : u'H',
'I' : u'I',
'J' : u'\N{LATIN SMALL LETTER LONG S}',
'K' : u'\N{LATIN SMALL LETTER TURNED K}', # fixme
'L' : u'\N{TURNED SANS-SERIF CAPITAL L}',
'M' : u'W',
'N' : u'N',
'O' : u'O',
'P' : u'\N{CYRILLIC CAPITAL LETTER KOMI DE}',
'R' : u'\N{CANADIAN SYLLABICS TLHO}',
'S' : u'S',
'T' : u'\N{UP TACK}',
'U' : u'\N{ARMENIAN CAPITAL LETTER VO}',
'V' : u'\N{N-ARY LOGICAL AND}',
'W' : u'M',
'X' : u'X',
'Y' : u'\N{TURNED SANS-SERIF CAPITAL Y}',
'Z' : u'Z',

'a' : u'\N{LATIN SMALL LETTER TURNED A}',
'b' : u'q',
'c' : u'\N{LATIN SMALL LETTER OPEN O}',
'd' : u'p',
'e' : u'\N{LATIN SMALL LETTER SCHWA}',
'f' : u'\N{LATIN SMALL LETTER DOTLESS J WITH STROKE}',
'g' : u'\N{LATIN SMALL LETTER B WITH HOOK}',
'h' : u'\N{LATIN SMALL LETTER TURNED H}',
'i' : u'\N{LATIN SMALL LETTER DOTLESS I}' + u'\N{COMBINING DOT BELOW}',
'j' : u'\N{LATIN SMALL LETTER LONG S}' + u'\N{COMBINING DOT BELOW}',
'k' : u'\N{LATIN SMALL LETTER TURNED K}',
'l' : u'l',
'm' : u'\N{LATIN SMALL LETTER TURNED M}',
'n' : u'u',
'o' : u'o',
'p' : u'd',
'q' : u'b',
'r' : u'\N{LATIN SMALL LETTER TURNED R}',
's' : u's',
't' : u'\N{LATIN SMALL LETTER TURNED T}',
'u' : u'n',
'v' : u'\N{LATIN SMALL LETTER TURNED V}',
'w' : u'\N{LATIN SMALL LETTER TURNED W}',
'x' : u'x',
'y' : u'\N{LATIN SMALL LETTER TURNED Y}',
'z' : u'z',

'0' : '0',
'1' : u'I',
'2' : u'\N{INVERTED QUESTION MARK}\N{COMBINING MACRON}',
'3' : u'\N{LATIN CAPITAL LETTER OPEN E}',
'4' : u'\N{LATIN SMALL LETTER LZ DIGRAPH}',
'6' : '9',
'7' : u'\N{LATIN CAPITAL LETTER L WITH STROKE}',
'8' : '8',
'9' : '6',
',' : "'",
"'" : ',',
'.' : u'\N{DOT ABOVE}',
'?' : u'\N{INVERTED QUESTION MARK}',
'!' : u'\N{INVERTED EXCLAMATION MARK}',


}


tables_names = ['cyrillic', 'cyrillic_plus', 'greek',
'other', 'cherokee']

table_default = table_cyrillic
table_default.update(table_greek)

table_all={}
for t in tables_names:
    table_all.update(globals()['table_'+t])
    
parser = OptionParser(usage="usage: %prog [options]")

parser.add_option("-t", "--tables",
    action="store", default='default', dest="tables", type="string",
    help="""list of tables to use, separated by a plus sign. 
Possible tables are: """+'+'.join(tables_names)+"""  and a special name 'all' to specify 
all these tables joined together. 
There is another table, 'mirror', that is not selected in 'all'.""")

parser.add_option("-r", "--reverse",
      action="count", dest="reverse",
      default=0,
      help="Reverse the text after conversion. Best used with the 'mirror' table.")

(options, args) = parser.parse_args()

if args:
    to_convert = ' '.join(args).decode('utf-8')
else:
    to_convert = None

tables = options.tables.split('+')
tables = ['table_'+x for x in tables]

tables = [globals()[x] for x in tables]

table = {}
for t in tables:
    table.update(t)

def reverse_string(s):
    l = list(s)
    l.reverse()
    r = ''.join(l)
    return r

def do_convert(s, reverse=0):
    if reverse:
        s = reverse_string(s)
    l = unicodedata.normalize('NFKD', s)
    out = []
    for c in l:
        out.append(table.get(c, c))
    out = ''.join(out)
    out = unicodedata.normalize('NFKC', out)
    return out

if not to_convert:
    if options.reverse:
        lines = sys.stdin.readlines()
        lines.reverse()
    else:
        lines = sys.stdin
        
    for line in lines:
        l = line.decode('utf-8')
        out = do_convert(l, options.reverse)
        sys.stdout.write(out.encode('utf-8'))
    
else:
    out = do_convert(to_convert, options.reverse)
    sys.stdout.write(out.encode('utf-8'))
    sys.stdout.write('\n')