1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
|
from __future__ import print_function
from __future__ import unicode_literals
from builtins import str, bytes, dict, int
import os
import sys
sys.path.insert(0, os.path.join(os.path.dirname(__file__), "..", ".."))
from pattern.search import search, match
from pattern.en import parsetree
# This example demonstrates an interesting search pattern that mines for comparisons.
# Notice the use of the constraint "be".
# If the output from the parser includes word lemmas (e.g., "doing" => "do")
# these will also be matched. Using "be" then matches "is", "being", "are", ...
# and if underspecification is used "could be", "will be", "definitely was", ...
p = "NP be ADJP|ADVP than NP"
for s in (
"the turtle was faster than the hare",
"Arnold Schwarzenegger is more dangerous than Dolph Lundgren"):
t = parsetree(s, lemmata=True) # parse lemmas
m = search(p, t)
if m:
# Constituents for the given constraint indices:
# 0 = NP, 2 = ADJP|ADVP, 4 = NP
print(m[0].constituents(constraint=[0, 2, 4]))
print("")
p = "NP be ADJP|ADVP than NP"
t = parsetree("the turtle was faster than the hare", lemmata=True)
m = match(p, t)
print(t)
print("")
for w in m.words:
print("%s\t=> %s" % (w, m.constraint(w)))
|
