|
| 1 | +"""Converts a given string to integer and float |
| 2 | +This works with only Indian system of wording |
| 3 | +
|
| 4 | + * Indian system uses crore, lakh, thousand and not million and billions |
| 5 | +
|
| 6 | +For the part after the decimal example ( .159 ): |
| 7 | + * Digit by digit ( .159 ) -> point one five nine is allowed |
| 8 | + * Anything else will throw an error |
| 9 | +
|
| 10 | +>>> to_int("Five") |
| 11 | +5 |
| 12 | +>>> to_float("Five") |
| 13 | +5.0 |
| 14 | +
|
| 15 | +>>> to_int("One thousand five hundred and two") |
| 16 | +1502 |
| 17 | +>>> to_float("One thousand five hundred and two") |
| 18 | +1502.0 |
| 19 | +
|
| 20 | +>>> to_int( |
| 21 | +... "Ninety nine crore three lakh seventy two thousand and six point one five nine" |
| 22 | +... ) |
| 23 | +990372006 |
| 24 | +
|
| 25 | +>>> to_float( |
| 26 | +... "Ninety nine crore three lakh seventy two thousand and six point one five nine" |
| 27 | +... ) |
| 28 | +990372006.159 |
| 29 | +
|
| 30 | +wikipedia explanation - https://en.wikipedia.org/wiki/Numeral_(linguistics) |
| 31 | +""" |
| 32 | + |
| 33 | + |
| 34 | +def to_int(word: str) -> int: |
| 35 | + if len(word.strip()) > 0: |
| 36 | + units = { |
| 37 | + "zero": 0, |
| 38 | + "one": 1, |
| 39 | + "two": 2, |
| 40 | + "three": 3, |
| 41 | + "four": 4, |
| 42 | + "five": 5, |
| 43 | + "six": 6, |
| 44 | + "seven": 7, |
| 45 | + "eight": 8, |
| 46 | + "nine": 9, |
| 47 | + "eleven": 11, |
| 48 | + "twelve": 12, |
| 49 | + "thirteen": 13, |
| 50 | + "fourteen": 14, |
| 51 | + "fifteen": 15, |
| 52 | + "sixteen": 16, |
| 53 | + "seventeen": 17, |
| 54 | + "eighteen": 18, |
| 55 | + "nineteen": 19, |
| 56 | + } |
| 57 | + |
| 58 | + tens = { |
| 59 | + "ten": 10, |
| 60 | + "twenty": 20, |
| 61 | + "thirty": 30, |
| 62 | + "forty": 40, |
| 63 | + "fifty": 50, |
| 64 | + "sixty": 60, |
| 65 | + "seventy": 70, |
| 66 | + "eighty": 80, |
| 67 | + "ninety": 90, |
| 68 | + } |
| 69 | + |
| 70 | + multipliers = { |
| 71 | + "hundred": 100, |
| 72 | + "thousand": 1_000, |
| 73 | + "lakh": 1_00_000, |
| 74 | + "crore": 1_00_00_000, |
| 75 | + } |
| 76 | + |
| 77 | + if "point" in word: |
| 78 | + word_lst = word.split("point") |
| 79 | + word = "".join(word_lst[:-1]) |
| 80 | + |
| 81 | + words = ( |
| 82 | + word.strip() |
| 83 | + .replace(" and", "") |
| 84 | + .replace("-", "") |
| 85 | + .replace("_", "") |
| 86 | + .lower() |
| 87 | + .split() |
| 88 | + ) |
| 89 | + |
| 90 | + number = 0 |
| 91 | + temp = 0 |
| 92 | + |
| 93 | + for index, word in enumerate(words): |
| 94 | + if index == 0: |
| 95 | + if word in units: |
| 96 | + temp += units[word] |
| 97 | + elif word in tens: |
| 98 | + temp += tens[word] |
| 99 | + else: |
| 100 | + temp += multipliers[word] |
| 101 | + elif index == (len(words) - 1): |
| 102 | + if word in units: |
| 103 | + temp += units[word] |
| 104 | + number += temp |
| 105 | + elif word in tens: |
| 106 | + temp += tens[word] |
| 107 | + number += temp |
| 108 | + else: |
| 109 | + temp *= multipliers[word] |
| 110 | + number += temp |
| 111 | + elif word in units: |
| 112 | + temp += units[word] |
| 113 | + elif word in tens: |
| 114 | + temp += tens[word] |
| 115 | + elif word in multipliers: |
| 116 | + temp *= multipliers[word] |
| 117 | + number += temp |
| 118 | + temp = 0 |
| 119 | + |
| 120 | + if len(words) > 1: |
| 121 | + return number |
| 122 | + else: |
| 123 | + return temp |
| 124 | + else: |
| 125 | + raise ValueError("Empty input is not a valid number in words") |
| 126 | + |
| 127 | + |
| 128 | +def to_float(word: str) -> float: |
| 129 | + units = { |
| 130 | + "zero": 0, |
| 131 | + "one": 1, |
| 132 | + "two": 2, |
| 133 | + "three": 3, |
| 134 | + "four": 4, |
| 135 | + "five": 5, |
| 136 | + "six": 6, |
| 137 | + "seven": 7, |
| 138 | + "eight": 8, |
| 139 | + "nine": 9, |
| 140 | + "eleven": 11, |
| 141 | + "twelve": 12, |
| 142 | + "thirteen": 13, |
| 143 | + "fourteen": 14, |
| 144 | + "fifteen": 15, |
| 145 | + "sixteen": 16, |
| 146 | + "seventeen": 17, |
| 147 | + "eighteen": 18, |
| 148 | + "nineteen": 19, |
| 149 | + } |
| 150 | + |
| 151 | + all_words = ( |
| 152 | + word.strip() |
| 153 | + .replace(" and", "") |
| 154 | + .replace("-", "") |
| 155 | + .replace("_", "") |
| 156 | + .lower() |
| 157 | + .split("point") |
| 158 | + ) |
| 159 | + if len(all_words) > 1: |
| 160 | + word = all_words[0] |
| 161 | + after_point = all_words[1].split() |
| 162 | + |
| 163 | + integer_part = to_int(word) |
| 164 | + |
| 165 | + decimal_part = "" |
| 166 | + for num in after_point: |
| 167 | + if num in units: |
| 168 | + decimal_part += str(units[num]) |
| 169 | + |
| 170 | + str_float = str(integer_part) + str(decimal_part) |
| 171 | + divider = "1" + ("0" * len(after_point)) |
| 172 | + return int(str_float) / int(divider) |
| 173 | + |
| 174 | + else: |
| 175 | + return float(to_int(word)) |
| 176 | + |
| 177 | + |
| 178 | +if __name__ == "__main__": |
| 179 | + import doctest |
| 180 | + |
| 181 | + doctest.testmod() |
| 182 | + # while True: |
| 183 | + # word = input("Enter a number in words (q to quit) :- ").lower().strip() |
| 184 | + # if word == "q": |
| 185 | + # break |
| 186 | + # else: |
| 187 | + # integer = to_int(word) |
| 188 | + # print(f"\nThe number in {type(integer)} --> {integer} ") |
| 189 | + # floater = to_float(word) |
| 190 | + # print(f"\nThe number in {type(floater)} --> {floater} ") |
0 commit comments