I need to convert one
into 1
, two
into 2
and so on.
Is there a way to do this with a library or a class or anythi
Make use of the python package : WordToDigits
pip install wordtodigits
It can find numbers present in word form in a sentence and then convert them to the proper numeric format. Also takes care of the decimal part, if present. The word representation of numbers could be anywhere in the passage.
https://pypi.org/project/wordtodigits/
Quick and dirty Java port of e_h's C# implementation (above). Note that both return double, not int.
public class Text2Double {
public double Text2Double(String text) {
String[] units = new String[]{
"zero", "one", "two", "three", "four", "five", "six", "seven", "eight",
"nine", "ten", "eleven", "twelve", "thirteen", "fourteen", "fifteen",
"sixteen", "seventeen", "eighteen", "nineteen",
};
String[] tens = new String[]{"", "", "twenty", "thirty", "forty", "fifty", "sixty", "seventy", "eighty", "ninety"};
String[] scales = new String[]{"hundred", "thousand", "million", "billion", "trillion"};
Map<String, ScaleIncrementPair> numWord = new LinkedHashMap<>();
numWord.put("and", new ScaleIncrementPair(1, 0));
for (int i = 0; i < units.length; i++) {
numWord.put(units[i], new ScaleIncrementPair(1, i));
}
for (int i = 1; i < tens.length; i++) {
numWord.put(tens[i], new ScaleIncrementPair(1, i * 10));
}
for (int i = 0; i < scales.length; i++) {
if (i == 0)
numWord.put(scales[i], new ScaleIncrementPair(100, 0));
else
numWord.put(scales[i], new ScaleIncrementPair(Math.pow(10, (i * 3)), 0));
}
double current = 0;
double result = 0;
for(String word : text.split("[ -]"))
{
ScaleIncrementPair scaleIncrement = numWord.get(word);
current = current * scaleIncrement.scale + scaleIncrement.increment;
if (scaleIncrement.scale > 100) {
result += current;
current = 0;
}
}
return result + current;
}
}
public class ScaleIncrementPair
{
public double scale;
public int increment;
public ScaleIncrementPair(double s, int i)
{
scale = s;
increment = i;
}
}
If anyone is interested, I hacked up a version that maintains the rest of the string (though it may have bugs, haven't tested it too much).
def text2int (textnum, numwords={}):
if not numwords:
units = [
"zero", "one", "two", "three", "four", "five", "six", "seven", "eight",
"nine", "ten", "eleven", "twelve", "thirteen", "fourteen", "fifteen",
"sixteen", "seventeen", "eighteen", "nineteen",
]
tens = ["", "", "twenty", "thirty", "forty", "fifty", "sixty", "seventy", "eighty", "ninety"]
scales = ["hundred", "thousand", "million", "billion", "trillion"]
numwords["and"] = (1, 0)
for idx, word in enumerate(units): numwords[word] = (1, idx)
for idx, word in enumerate(tens): numwords[word] = (1, idx * 10)
for idx, word in enumerate(scales): numwords[word] = (10 ** (idx * 3 or 2), 0)
ordinal_words = {'first':1, 'second':2, 'third':3, 'fifth':5, 'eighth':8, 'ninth':9, 'twelfth':12}
ordinal_endings = [('ieth', 'y'), ('th', '')]
textnum = textnum.replace('-', ' ')
current = result = 0
curstring = ""
onnumber = False
for word in textnum.split():
if word in ordinal_words:
scale, increment = (1, ordinal_words[word])
current = current * scale + increment
if scale > 100:
result += current
current = 0
onnumber = True
else:
for ending, replacement in ordinal_endings:
if word.endswith(ending):
word = "%s%s" % (word[:-len(ending)], replacement)
if word not in numwords:
if onnumber:
curstring += repr(result + current) + " "
curstring += word + " "
result = current = 0
onnumber = False
else:
scale, increment = numwords[word]
current = current * scale + increment
if scale > 100:
result += current
current = 0
onnumber = True
if onnumber:
curstring += repr(result + current)
return curstring
Example:
>>> text2int("I want fifty five hot dogs for two hundred dollars.")
I want 55 hot dogs for 200 dollars.
There could be issues if you have, say, "$200". But, this was really rough.
This is the c# implementation of the code in 1st answer:
public static double ConvertTextToNumber(string text)
{
string[] units = new string[] {
"zero", "one", "two", "three", "four", "five", "six", "seven", "eight",
"nine", "ten", "eleven", "twelve", "thirteen", "fourteen", "fifteen",
"sixteen", "seventeen", "eighteen", "nineteen",
};
string[] tens = new string[] {"", "", "twenty", "thirty", "forty", "fifty", "sixty", "seventy", "eighty", "ninety"};
string[] scales = new string[] { "hundred", "thousand", "million", "billion", "trillion" };
Dictionary<string, ScaleIncrementPair> numWord = new Dictionary<string, ScaleIncrementPair>();
numWord.Add("and", new ScaleIncrementPair(1, 0));
for (int i = 0; i < units.Length; i++)
{
numWord.Add(units[i], new ScaleIncrementPair(1, i));
}
for (int i = 1; i < tens.Length; i++)
{
numWord.Add(tens[i], new ScaleIncrementPair(1, i * 10));
}
for (int i = 0; i < scales.Length; i++)
{
if(i == 0)
numWord.Add(scales[i], new ScaleIncrementPair(100, 0));
else
numWord.Add(scales[i], new ScaleIncrementPair(Math.Pow(10, (i*3)), 0));
}
double current = 0;
double result = 0;
foreach (var word in text.Split(new char[] { ' ', '-', '—'}))
{
ScaleIncrementPair scaleIncrement = numWord[word];
current = current * scaleIncrement.scale + scaleIncrement.increment;
if (scaleIncrement.scale > 100)
{
result += current;
current = 0;
}
}
return result + current;
}
public struct ScaleIncrementPair
{
public double scale;
public int increment;
public ScaleIncrementPair(double s, int i)
{
scale = s;
increment = i;
}
}
The majority of this code is to set up the numwords dict, which is only done on the first call.
def text2int(textnum, numwords={}):
if not numwords:
units = [
"zero", "one", "two", "three", "four", "five", "six", "seven", "eight",
"nine", "ten", "eleven", "twelve", "thirteen", "fourteen", "fifteen",
"sixteen", "seventeen", "eighteen", "nineteen",
]
tens = ["", "", "twenty", "thirty", "forty", "fifty", "sixty", "seventy", "eighty", "ninety"]
scales = ["hundred", "thousand", "million", "billion", "trillion"]
numwords["and"] = (1, 0)
for idx, word in enumerate(units): numwords[word] = (1, idx)
for idx, word in enumerate(tens): numwords[word] = (1, idx * 10)
for idx, word in enumerate(scales): numwords[word] = (10 ** (idx * 3 or 2), 0)
current = result = 0
for word in textnum.split():
if word not in numwords:
raise Exception("Illegal word: " + word)
scale, increment = numwords[word]
current = current * scale + increment
if scale > 100:
result += current
current = 0
return result + current
print text2int("seven billion one hundred million thirty one thousand three hundred thirty seven")
#7100031337
Made change so that text2int(scale) will return correct conversion. Eg, text2int("hundred") => 100.
import re
numwords = {}
def text2int(textnum):
if not numwords:
units = [ "zero", "one", "two", "three", "four", "five", "six",
"seven", "eight", "nine", "ten", "eleven", "twelve",
"thirteen", "fourteen", "fifteen", "sixteen", "seventeen",
"eighteen", "nineteen"]
tens = ["", "", "twenty", "thirty", "forty", "fifty", "sixty",
"seventy", "eighty", "ninety"]
scales = ["hundred", "thousand", "million", "billion", "trillion",
'quadrillion', 'quintillion', 'sexillion', 'septillion',
'octillion', 'nonillion', 'decillion' ]
numwords["and"] = (1, 0)
for idx, word in enumerate(units): numwords[word] = (1, idx)
for idx, word in enumerate(tens): numwords[word] = (1, idx * 10)
for idx, word in enumerate(scales): numwords[word] = (10 ** (idx * 3 or 2), 0)
ordinal_words = {'first':1, 'second':2, 'third':3, 'fifth':5,
'eighth':8, 'ninth':9, 'twelfth':12}
ordinal_endings = [('ieth', 'y'), ('th', '')]
current = result = 0
tokens = re.split(r"[\s-]+", textnum)
for word in tokens:
if word in ordinal_words:
scale, increment = (1, ordinal_words[word])
else:
for ending, replacement in ordinal_endings:
if word.endswith(ending):
word = "%s%s" % (word[:-len(ending)], replacement)
if word not in numwords:
raise Exception("Illegal word: " + word)
scale, increment = numwords[word]
if scale > 1:
current = max(1, current)
current = current * scale + increment
if scale > 100:
result += current
current = 0
return result + current