Created
November 3, 2017 06:16
-
-
Save Navdevl/3c13f5b60555ffa906291421eb7e8a73 to your computer and use it in GitHub Desktop.
A way to convert word to number.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| # Credits to https://stackoverflow.com/questions/493174/is-there-a-way-to-convert-number-words-to-integers#38760564 | |
| 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 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment