Fuzzy matchen in strings

fuzzy-matching.py

#!/usr/bin/env python3

import json
from fuzzysearch import find_near_matches
from fuzzywuzzy import process

json_file = "A152153-pagina5tm20/page/NL-UtHUA_A152153_000005-f.json"

def fuzzy_extract(qs, ls, threshold):
    '''fuzzy matches 'qs' in 'ls' and returns list of 
    tuples of (word,index)
    '''
    for word, _ in process.extractBests(qs, (ls,), score_cutoff=threshold):
        for match in find_near_matches(qs, word, max_l_dist=1):
            match = word[match.start:match.end]
            index = ls.find(match)
            yield (match, index)

def get_page_text(data):
	for text_region in data["PcGts"]["Page"]["TextRegion"]:
		for text_line in text_region["TextLine"]:
			txt = text_line["TextEquiv"]["Unicode"]
			if txt:
				yield(txt)

#############################################

with open(json_file) as f:
	data = json.load(f)

text = " ".join(get_page_text(data))

q = "op heden den"
q = "is voor ons ondergeteekende"
# q = "oud"
q = "wonende"
q = "die ons verklaard heeft, dat op den "
q = "maand des"
q = "middags te"
# q = "uur"
q = "bevallen is van een kind van het "
q = "geslacht, waaraan men goven"

for match,index in fuzzy_extract(q, text, 10):
    print('match: {}\nindex: {}'.format(match, index))