from pprint import pprint
from diffengine.difference import sequence_matcher
from diffengine.tokenization import wikitext_split
for op in sequence_matcher.diff([], wikitext_split.tokenize("Foo bar derp.")):
pprint(op)
from pprint import pprint
from diffengine.engines import hierarchical_matcher
from diffengine.tokenization import wikitext_split
input = "Foo bar derp."
tokens = wikitext_split.tokenize(input)
print(tokens)
for cluster in hierarchical_matcher.cluster(tokens, wikitext_split):
pprint(cluster)
print("-----------------------")
input = """
This is a sentence. This is the end.
This is another paragraph.
"""
tokens = wikitext_split.tokenize(input)
print(tokens)
for cluster in hierarchical_matcher.cluster(tokens, wikitext_split):
pprint(cluster)
print("-----------------------")
input = """
This is a sentence. This is the end.
from pprint import pprint
from diffengine.difference import hierarchical_matcher
from diffengine.tokenization import wikitext_split
tokens1 = wikitext_split.tokenize("Foo bar derp.")
print(tokens1)
for i, op in enumerate(hierarchical_matcher.diff([], tokens1)):
print("#{0}: {1}".format(i+1, repr(op)))
print("-----------------------")
tokens2 = wikitext_split.tokenize("Foo bar derp. Foo bar derp.")
print(tokens2)
for i, op in enumerate(hierarchical_matcher.diff(tokens1, tokens2)):
print("#{0}: {1}".format(i+1, repr(op)))
print("-----------------------")
tokens3 = wikitext_split.tokenize("Foo bar derp. Foo this is a bar derp.")
print(tokens3)
for i, op in enumerate(hierarchical_matcher.diff(tokens2, tokens3)):
print("#{0}: {1}".format(i+1, repr(op)))