Created
November 24, 2016 23:27
-
-
Save IevaZarina/fdf0b2de25402b537ba57341ba8c95dd to your computer and use it in GitHub Desktop.
Simple test case for aho-corasick automata for keyword search.
This file contains 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
import ahocorasick as ahc | |
keywords = [ | |
('he', 1), | |
('she', 1), | |
('hers', 1), | |
('her', 1) | |
] | |
text = [ | |
'he is here', | |
'this is she', | |
'this is hers ', | |
'her bag is big' | |
] | |
def make_aho_automaton(keywords): | |
A = ahc.Automaton() # initialize | |
for (key, cat) in keywords: | |
A.add_word(key, (cat, key)) # add keys and categories to the trie struncture | |
A.make_automaton() # generate automaton | |
return A | |
A = make_aho_automaton(keywords) | |
def find_keywords(line, A): | |
found_keywords = [] | |
for end_index, (cat, keyw) in A.iter(line): | |
found_keywords.append(keyw) | |
return found_keywords | |
print '------ no padding ---------' | |
new_text = [] | |
for line in text: | |
print line, ':', find_keywords(line, A) | |
print '------ with padding --------' | |
keywords = [ | |
(' he ', 1), | |
(' she ', 1), | |
(' hers ', 1), | |
(' her ', 1) | |
] | |
text = [ | |
' he is here ', | |
' this is she ', | |
' this is hers ', | |
' her bag is big ' | |
] | |
A_spaces = make_aho_automaton(keywords) | |
for line in text: | |
print line, ':', find_keywords(line, A_spaces) | |
print '------ repalacing/removing found keywords ---------' | |
def find_keyword_locations(line, A): | |
line_indices = [False for x in line] | |
for end_index, (cat, keyw) in A.iter(line): | |
start_index = end_index - len(keyw) + 2 # start index after first space | |
for i in range(start_index, end_index): # end index excluding last space | |
line_indices[i] = True | |
return line_indices | |
new_text_removed = [] | |
new_text_replaced = [] | |
for line in text: | |
line_indices = find_keyword_locations(line, A_spaces) | |
line = list(line) # split string into list | |
new_line = "".join([line[i] if not x else '' for i, x in enumerate(line_indices)]) | |
new_text_removed.append(new_line) | |
new_line = "".join([line[i] if not x else '-' for i, x in enumerate(line_indices)]) | |
new_text_replaced.append(new_line) | |
print text | |
print new_text_removed | |
print new_text_replaced |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment