text to unicode subscript / superscript

h2so4.py

# -*- coding: utf-8
from __future__ import unicode_literals
import warnings
import unicodedata

def build_lookup(macro, micro):
    assert len(macro) == len(micro), (len(macro), len(micro))
    output = {}
    for pair in zip(macro, micro):
        if pair[1] != ' ':
            output[pair[0]] = pair[1]
    return output

def translate(macro, trans):
    output = []
    for char in macro:
        try:
            output.append(trans[char])
        except KeyError:  # wrong type of error
            output.append(char)
            cat = unicodedata.category(char)
            if cat in ['Zs']:
                continue
            warnings.warn('{!r} not available as (sub|super)script'.format(char))
    return ''.join(output)

n_num = "0123456789+-=()"
u_num = "⁰¹²³⁴⁵⁶⁷⁸⁹⁺⁻⁼⁽⁾"
d_num = "₀₁₂₃₄₅₆₇₈₉₊₋₌₍₎"
n_low = "abcdefghijklmnopqrstuvwxyz"
u_low = "ᵃᵇᶜᵈᵉᶠᵍʰⁱʲᵏˡᵐⁿᵒᵖ ʳˢᵗᵘᵛʷˣʸᶻ"
d_low = "ₐ   ₑ  ₕᵢⱼₖₗₘₙₒₚ ᵣₛₜᵤᵥ ₓ  "
n_hi =  "ABCDEFGHIJKLMNOPQRSTUVWXYZ"
u_hi =  "ᴬᴮ ᴰᴱ ᴳᴴᴵᴶᴷᴸᴹᴺᴼᴾ ᴿ ᵀᵁⱽᵂ   "
d_hi =  "                          "
# n_grk="αβγδεζηθικλμνξοπρςστυφχψωɸ"
# u_grk="ᵅᵝᵞᵟᵋ  ᶿᶥ            ᵠᵡ  ᶲ"
# d_grk=" ᵦᵧ             ᵨ    ᵩᵪ   "

n = n_num+n_low+n_hi
u = u_num+u_low+u_hi
d = d_num+d_low+d_hi

utrans = build_lookup(n, u)
dtrans = build_lookup(n, d)

def sub(s):
    return translate(s, dtrans)

def sup(s):
    return translate(s, utrans)

if __name__ == '__main__':
    print sup('hello world')
    print sub('hello world')
    print sup('HELLO WORLD')
    print sub('HELLO WORLD')