def from_sentence(cls, sentence, cacheable=True, opts=None):
"""Create PredPatt instance from a sentence (string), which we'll parse and
convert to UD automatically. [English only]
"""
from predpatt import Parser
global _PARSER
if _PARSER is None:
_PARSER = Parser.get_instance(cacheable)
parse = _PARSER(sentence)
return cls(parse, opts=opts)
def from_constituency(cls, parse_string, cacheable=True, opts=None):
"""Create PredPatt instance from a constituency parse, which we'll convert to UD
automatically. [English only]
"""
from predpatt import Parser
global _PARSER
if _PARSER is None:
_PARSER = Parser.get_instance(cacheable)
parse = _PARSER.to_ud(parse_string)
return cls(parse, opts=opts)
* Support multiple sentences?
* Add option to list rules which fired.
* Show calibration score.
"""
import re
from bottle import route, run, template, request
from predpatt import Parser, PredPatt, PredPattOpts
from textwrap import dedent
# TODO eventually we'll want to accept paragraphs as input.
#import nltk
#sent_detector = nltk.data.load('tokenizers/punkt/english.pickle')
parser = Parser.get_instance()
@route('/')
@route('/', method='GET')
def main():
patterns = ''
sentence = 'The quick brown fox jumped over the lazy dog .'
tags = ''
parse = ''
if request.GET.get('sentence', '').strip():
sentence = request.GET.get('sentence', '').strip()
pp_opts = PredPattOpts()
for k, v in sorted(PredPattOpts().__dict__.iteritems()):
print
# To change certain behaviors, you can pass different options for the PredPatt
# instance. For example, to disable expansion of conjunctions and extraction of
# amods, use the following:
from predpatt import PredPattOpts
P = PredPatt.from_sentence(sentence,
opts=PredPattOpts(resolve_amod=0, resolve_conj=0))
print P.pprint(color=1)
print '______________________________________________________________________________'
print
#______________________________________________________________________________
# Bonus material
# Already have a constituency parse? No problem!
P = PredPatt.from_constituency(
'( (S (NP (NNP Chris)) (VP (VBZ loves) (NP (NNP Pat))) (. .)) )')
print P.pprint(track_rule=True, color=True)
print '______________________________________________________________________________'
print
# Using PredPatt's Parser interface
from predpatt import Parser
parser = Parser.get_instance() # Create UD parser instance
parse = parser(sentence) # Parse sentence
print parse.pprint()
def test():
from argparse import ArgumentParser
p = ArgumentParser()
p.add_argument('--filename', default='doc/DOCTEST.md')
args = p.parse_args()
sentences = re.findall(
'^> (.*)\n([\w\W]*?)(?=^>|<END>)',
codecs.open(args.filename, encoding='utf-8').read() + '\n<END>',
re.MULTILINE)
# TODO: Use PredPatt.from_string instead of duplicating code here.
parser = Parser.get_instance()
passed = 0
failed = 0
blank = 0
for s, chunk in sentences:
s = s.strip()
if not s:
continue
# use cached parse listed in doctest chunk.
parse_chunk = re.findall('<\!--parse=([\w\W]+?)-->', chunk)
if parse_chunk:
from predpatt.UDParse import DepTriple, UDParse
[parse_chunk] = parse_chunk
triples = [
DepTriple(r, int(b), int(a)) for r, a, b in re.findall(
'(\S+)\(\S+?/(\d+), \S+?/(\d+)\)', parse_chunk)
]
tokens = s.split()
[tags_chunk] = re.findall('<\!--tags=([\w\W]+?)-->', chunk)
tags = re.findall('\S+/(\S+)', tags_chunk)
parse = UDParse(tokens, tags, triples)
else:
parse = parser(s)
P = PredPatt(parse, ppattopts)
relations = P.pprint(track_rule=True)
tags = ' '.join('%s/%s' % x for x in zip(parse.tokens, parse.tags))
parse = parse.pprint(K=4)
relations = relations.replace('\t', ' ')
relations = '\n'.join(line[4:].rstrip()
for line in relations.split('\n'))
expected = []
chunk = chunk.replace('\t', ' ')
for line in chunk.split('\n'):
if line.startswith(' '):
line = line[4:].rstrip()
expected.append(line)
expected = '\n'.join(expected)
if not expected.strip():
blank += 1
#got = '%s\n%s\n%s' % (tags, parse, relations)
got = relations.strip() or '<empty>'
got = re.sub(r'\s*\[.*\]', '', got)
if expected.strip() == got.strip():
#print colored('pass', 'green')
passed += 1
else:
print()
print(colored('> ' + s, 'yellow'))
print(colored('fail', 'red'))
print('expected:')
for line in expected.split('\n'):
print(' ', colored(line, 'blue'))
print('got:')
for line in got.split('\n'):
print(' ', line)
print()
print(colored(tags, 'magenta'))
print()
print(colored(parse, 'magenta'))
failed += 1
msg = '[doctest] %.f%% (%s/%s) passed' % (passed * 100.0 /
(passed + failed), passed,
passed + failed)
if failed == 0:
print(msg)
else:
print()
print(msg)
print()
if blank:
print('blank:', blank)