Not logged in.  Login/Logout/Register | List snippets | | Create snippet | Upload image | Upload data

131
LINES

< > BotCompany Repo | #1013121 // parseEnglishNumbers

JavaX fragment (include)

static final String[] DIGITS = {"one", "two", "three", "four", "five", "six", "seven", "eight", "nine"};
static final String[] TENS = {null, "twenty", "thirty", "forty", "fifty", "sixty", "seventy", "eighty", "ninety"};
static final String[] TEENS = {"ten", "eleven", "twelve", "thirteen", "fourteen", "fifteen", "sixteen", "seventeen", "eighteen", "nineteen"};
static final String[] MAGNITUDES = {"hundred", "thousand", "million", "point"};
static final String[] ZERO = {"zero", "oh"};

static S parseEnglishNumbers(S input) {
  if (empty(input)) ret input;
  input = trim(simpleSpaces(lower(input)));
  String result = "";
  String[] decimal = input.split(MAGNITUDES[3]);
  String[] millions = decimal[0].split(MAGNITUDES[2]);

  for (int i = 0; i < millions.length; i++) {
    String[] thousands = millions[i].split(MAGNITUDES[1]);

    for (int j = 0; j < thousands.length; j++) {
        int[] triplet = {0, 0, 0};
        StringTokenizer set = new StringTokenizer(thousands[j]);

        if (set.countTokens() == 1) { //If there is only one token given in triplet
            String uno = set.nextToken();
            triplet[0] = 0;
            for (int k = 0; k < DIGITS.length; k++) {
                if (uno.equals(DIGITS[k])) {
                    triplet[1] = 0;
                    triplet[2] = k + 1;
                }
                if (uno.equals(TENS[k])) {
                    triplet[1] = k + 1;
                    triplet[2] = 0;
                }
                if (uno.equals(TEENS[k])) triplet[2] = k+10;
            }
        }


        else if (set.countTokens() == 2) {  //If there are two tokens given in triplet
            String uno = set.nextToken();
            String dos = set.nextToken();
            if (dos.equals(MAGNITUDES[0])) {  //If one of the two tokens is "hundred"
                for (int k = 0; k < DIGITS.length; k++) {
                    if (uno.equals(DIGITS[k])) {
                        triplet[0] = k + 1;
                        triplet[1] = 0;
                        triplet[2] = 0;
                    }
                }
            }
            else {
                triplet[0] = 0;
                for (int k = 0; k < DIGITS.length; k++) {
                    if (uno.equals(TENS[k])) {
                        triplet[1] = k + 1;
                    }
                    if (dos.equals(DIGITS[k])) {
                        triplet[2] = k + 1;
                    }
                }
            }
        }

        else if (set.countTokens() == 3) {  //If there are three tokens given in triplet
            String uno = set.nextToken();
            String dos = set.nextToken();
            String tres = set.nextToken();
            for (int k = 0; k < DIGITS.length; k++) {
                if (uno.equals(DIGITS[k])) {
                    triplet[0] = k + 1;
                }
                if (tres.equals(DIGITS[k])) {
                    triplet[1] = 0;
                    triplet[2] = k + 1;
                }
                if (tres.equals(TENS[k])) {
                    triplet[1] = k + 1;
                    triplet[2] = 0;
                }
            }
        }

        else if (set.countTokens() == 4) {  //If there are four tokens given in triplet
            String uno = set.nextToken();
            String dos = set.nextToken();
            String tres = set.nextToken();
            String cuatro = set.nextToken();
            for (int k = 0; k < DIGITS.length; k++) {
                if (uno.equals(DIGITS[k])) {
                    triplet[0] = k + 1;
                }
                if (cuatro.equals(DIGITS[k])) {
                    triplet[2] = k + 1;
                }
                if (tres.equals(TENS[k])) {
                    triplet[1] = k + 1;
                }
            }
        }
        else {
            triplet[0] = 0;
            triplet[1] = 0;
            triplet[2] = 0;
        }

        result = result + Integer.toString(triplet[0]) + Integer.toString(triplet[1]) + Integer.toString(triplet[2]);
    }
  }
  
  if (decimal.length > 1) {  //The number is a decimal
    StringTokenizer decimalDigits = new StringTokenizer(decimal[1]);
    result = result + ".";
    System.out.println(decimalDigits.countTokens() + " decimal digits");
    while (decimalDigits.hasMoreTokens()) {
        String w = decimalDigits.nextToken();
        System.out.println(w);

        if (w.equals(ZERO[0]) || w.equals(ZERO[1])) {
            result = result + "0";
        }
        for (int j = 0; j < DIGITS.length; j++) {
            if (w.equals(DIGITS[j])) {
                result = result + Integer.toString(j + 1);
            }   
        }

    }
  }

  while (startsWith(result, "0") && !startsWith(result, "0.")) result = dropFirst(result);
  ret result;
}

Author comment

From https://stackoverflow.com/questions/4062022/how-to-convert-words-to-a-number

download  show line numbers  debug dex  old transpilations   

Travelled to 15 computer(s): aoiabmzegqzx, bhatertpkbcr, cbybwowwnfue, cfunsshuasjs, gwrvuhgaqvyk, ishqpsrjomds, lnbujpyubztb, lpdgvwnxivlt, mqqgnosmbjvj, pyentgdyhuwx, pzhvpgtvlbxg, tslmcundralx, tvejysmllsmz, vouqrxazstgt, whxojlpjdney

No comments. add comment

Snippet ID: #1013121
Snippet name: parseEnglishNumbers
Eternal ID of this version: #1013121/6
Text MD5: 172463a74b7e68535a189b5b2a12e33b
Author: stefan
Category: javax / a.i.
Type: JavaX fragment (include)
Public (visible to everyone): Yes
Archived (hidden from active list): No
Created/modified: 2019-03-21 00:54:06
Source code size: 4913 bytes / 131 lines
Pitched / IR pitched: No / No
Views / Downloads: 344 / 428
Version history: 5 change(s)
Referenced in: [show references]