spaCy/spacy/lemmatizer.py

112 lines
4.0 KiB
Python
Raw Normal View History

# coding: utf8
from __future__ import unicode_literals
from .symbols import POS, NOUN, VERB, ADJ, PUNCT
from .symbols import VerbForm_inf, VerbForm_none, Number_sing, Degree_pos
2014-12-23 07:16:57 +03:00
class Lemmatizer(object):
@classmethod
2017-03-26 15:17:07 +03:00
def load(cls, path, index=None, exc=None, rules=None):
return cls(index or {}, exc or {}, rules or {})
2014-12-23 07:16:57 +03:00
def __init__(self, index=None, exceptions=None, rules=None, lookup=None):
self.index = index if index is not None else {}
self.exc = exceptions if exceptions is not None else {}
self.rules = rules if rules is not None else {}
self.lookup_table = lookup if lookup is not None else {}
2015-08-25 16:46:19 +03:00
def __call__(self, string, univ_pos, morphology=None):
2017-10-12 23:50:43 +03:00
if univ_pos in (NOUN, 'NOUN', 'noun'):
2016-09-27 15:16:22 +03:00
univ_pos = 'noun'
2017-10-12 23:50:43 +03:00
elif univ_pos in (VERB, 'VERB', 'verb'):
2016-09-27 15:16:22 +03:00
univ_pos = 'verb'
2017-10-12 23:50:43 +03:00
elif univ_pos in (ADJ, 'ADJ', 'adj'):
2016-09-27 15:16:22 +03:00
univ_pos = 'adj'
2017-10-12 23:50:43 +03:00
elif univ_pos in (PUNCT, 'PUNCT', 'punct'):
2016-09-27 15:16:22 +03:00
univ_pos = 'punct'
else:
return set([string.lower()])
# See Issue #435 for example of where this logic is requied.
if self.is_base_form(univ_pos, morphology):
return set([string.lower()])
2016-09-27 18:47:05 +03:00
lemmas = lemmatize(string, self.index.get(univ_pos, {}),
self.exc.get(univ_pos, {}),
self.rules.get(univ_pos, []))
2015-09-08 16:38:03 +03:00
return lemmas
2014-12-23 07:16:57 +03:00
def is_base_form(self, univ_pos, morphology=None):
"""
Check whether we're dealing with an uninflected paradigm, so we can
avoid lemmatization entirely.
"""
morphology = {} if morphology is None else morphology
2017-09-06 20:13:24 +03:00
others = [key for key in morphology
if key not in (POS, 'Number', 'POS', 'VerbForm', 'Tense')]
true_morph_key = morphology.get('morph', 0)
2017-03-25 23:56:41 +03:00
if univ_pos == 'noun' and morphology.get('Number') == 'sing':
return True
2017-03-25 23:56:41 +03:00
elif univ_pos == 'verb' and morphology.get('VerbForm') == 'inf':
return True
# This maps 'VBP' to base form -- probably just need 'IS_BASE'
# morphology
elif univ_pos == 'verb' and (morphology.get('VerbForm') == 'fin' and \
2017-09-06 20:13:24 +03:00
morphology.get('Tense') == 'pres' and \
morphology.get('Number') is None and \
not others):
return True
elif univ_pos == 'adj' and morphology.get('Degree') == 'pos':
return True
2017-03-25 23:56:41 +03:00
elif VerbForm_inf in morphology:
return True
elif VerbForm_none in morphology:
return True
elif Number_sing in morphology:
return True
elif Degree_pos in morphology:
return True
else:
return False
2014-12-23 07:16:57 +03:00
def noun(self, string, morphology=None):
return self(string, 'noun', morphology)
2014-12-23 07:16:57 +03:00
def verb(self, string, morphology=None):
return self(string, 'verb', morphology)
2014-12-23 07:16:57 +03:00
def adj(self, string, morphology=None):
return self(string, 'adj', morphology)
def punct(self, string, morphology=None):
return self(string, 'punct', morphology)
def lookup(self, string):
if string in self.lookup_table:
return self.lookup_table[string]
return string
2014-12-23 07:16:57 +03:00
def lemmatize(string, index, exceptions, rules):
string = string.lower()
forms = []
# TODO: Is this correct? See discussion in Issue #435.
#if string in index:
# forms.append(string)
2014-12-23 07:16:57 +03:00
forms.extend(exceptions.get(string, []))
2017-03-01 23:44:17 +03:00
oov_forms = []
2017-10-14 14:32:55 +03:00
if not forms:
for old, new in rules:
if string.endswith(old):
form = string[:len(string) - len(old)] + new
if not form:
pass
elif form in index or not form.isalpha():
forms.append(form)
else:
oov_forms.append(form)
2014-12-23 07:16:57 +03:00
if not forms:
2017-03-01 23:44:17 +03:00
forms.extend(oov_forms)
if not forms:
forms.append(string)
2014-12-23 07:16:57 +03:00
return set(forms)