PYTHON

pinyin to pinyin numbers python

PinyinToneMark = {
    0: "aoeiuvu00fc",
    1: "u0101u014du0113u012bu016bu01d6u01d6",
    2: "u00e1u00f3u00e9u00edu00fau01d8u01d8",
    3: "u01ceu01d2u011bu01d0u01d4u01dau01da",
    4: "u00e0u00f2u00e8u00ecu00f9u01dcu01dc",
}

def decode_pinyin(s):
    s = s.lower()
    r = ""
    t = ""
    for c in s:
        if c >= 'a' and c <= 'z':
            t += c
        elif c == ':':
            assert t[-1] == 'u'
            t = t[:-1] + "u00fc"
        else:
            if c >= '0' and c <= '5':
                tone = int(c) % 5
                if tone != 0:
                    m = re.search("[aoeiuvu00fc]+", t)
                    if m is None:
                        t += c
                    elif len(m.group(0)) == 1:
                        t = t[:m.start(0)] + PinyinToneMark[tone][PinyinToneMark[0].index(m.group(0))] + t[m.end(0):]
                    else:
                        if 'a' in t:
                            t = t.replace("a", PinyinToneMark[tone][0])
                        elif 'o' in t:
                            t = t.replace("o", PinyinToneMark[tone][1])
                        elif 'e' in t:
                            t = t.replace("e", PinyinToneMark[tone][2])
                        elif t.endswith("ui"):
                            t = t.replace("i", PinyinToneMark[tone][3])
                        elif t.endswith("iu"):
                            t = t.replace("u", PinyinToneMark[tone][4])
                        else:
                            t += "!"
            r += t
            t = ""
    r += t
    return r