Convert numbered pinyin to pinyin with tone marks

Question

Are there any scripts, libraries, or programs using Python, or BASH tools (e.g. awk, perl, sed) which can correc

Answer 1

I ported the code from dani_l to Kotlin (the code in java should be quite similar). It goes :

import java.util.regex.Pattern
val pinyinToneMarks = mapOf(
    'a' to "āáǎà",
    'e' to "ēéěè",
    'i' to "īíǐì",
    'o' to  "ōóǒò",
    'u' to "ūúǔù",
    'ü' to "ǖǘǚǜ",
    'A' to  "ĀÁǍÀ",
    'E' to "ĒÉĚÈ",
    'I' to "ĪÍǏÌ",
    'O' to "ŌÓǑÒ",
    'U' to "ŪÚǓÙ",
    'Ü' to  "ǕǗǙǛ"
)

fun toPinyin(asciiPinyin: String) :String {
  val pattern = Pattern.compile("([aeiouüvÜ]{1,3})(n?g?r?)([012345])")!!
  val matcher = pattern.matcher(asciiPinyin)
  val s = StringBuilder()
  var start = 0
  while (matcher.find(start)) {
      s.append(asciiPinyin, start, matcher.start(1))
      val tone = Integer.parseInt(matcher.group(3)!!) % 5
      val r = matcher.group(1)!!.replace("v", "ü").replace("V", "Ü")
      // for multple vowels, use first one if it is a/e/o, otherwise use second one
      val pos = if (r.length >1 && r[0].toString() !in "aeoAEO") 1 else 0
      if (tone != 0) s.append(r, 0, pos).append(pinyinToneMarks[r[pos]]!![tone - 1]).append(r, pos + 1, r.length)
      else s.append(r)
      s.append(matcher.group(2))
      start = matcher.end(3)
  }
  if (start != asciiPinyin.length) s.append(asciiPinyin, start, asciiPinyin.length)
  return s.toString()
}

fun test() = print(toPinyin("Ni3 hao3 ma0?"))