def __init__(
self,
stoplist=STOP_WORDS,
minsize=2,
maxsize=None,
renumber=True,
lang=None,
):
"""
:param stoplist: A collection of words to remove from the stream.
This is converted to a frozenset. The default is a list of
common English stop words.
:param minsize: The minimum length of token texts. Tokens with
text smaller than this will be stopped. The default is 2.
:param maxsize: The maximum length of token texts. Tokens with text
larger than this will be stopped. Use None to allow any length.
:param renumber: Change the 'pos' attribute of unstopped tokens
to reflect their position with the stopped words removed.
:param lang: Automatically get a list of stop words for the given
language
"""
stops = set()
if stoplist:
stops.update(stoplist)
if lang:
from whoosh.lang import stopwords_for_language
stops.update(stopwords_for_language(lang))
self.stops = frozenset(stops)
self.min = minsize
self.max = maxsize
self.renumber = renumber
def __init__(self, stoplist=STOP_WORDS, minsize=2, maxsize=None,
renumber=True, lang=None):
"""
:param stoplist: A collection of words to remove from the stream.
This is converted to a frozenset. The default is a list of
common English stop words.
:param minsize: The minimum length of token texts. Tokens with
text smaller than this will be stopped. The default is 2.
:param maxsize: The maximum length of token texts. Tokens with text
larger than this will be stopped. Use None to allow any length.
:param renumber: Change the 'pos' attribute of unstopped tokens
to reflect their position with the stopped words removed.
:param lang: Automatically get a list of stop words for the given
language
"""
stops = set()
if stoplist:
stops.update(stoplist)
if lang:
from whoosh.lang import stopwords_for_language
stops.update(stopwords_for_language(lang))
self.stops = frozenset(stops)
self.min = minsize
self.max = maxsize
self.renumber = renumber
def __init__(self, rtepair, stop=True, lemmatize=False):
self.stop = stop
self.stopwords = lang.stopwords_for_language("pt")
self.negwords = set(['não', 'nunca', 'falhou' 'rejeitou', 'negou', 'sem', 'jamais', 'nada', 'nenhum', 'nem', 'ninguém', 'menos', 'pouco'])
# Try to tokenize so that abbreviations like U.S.and monetary amounts
# like "$23.00" are kept as tokens.
from nltk.tokenize import RegexpTokenizer
tokenizer = RegexpTokenizer('([A-Z]\.)+|\w+|\$[\d\.]+')
#Get the set of word types for text and hypothesis
self.text_tokens = tokenizer.tokenize(rtepair.text)
self.hyp_tokens = tokenizer.tokenize(rtepair.hyp)
self.text_words = set(self.text_tokens)
self.hyp_words = set(self.hyp_tokens)
if lemmatize:
self.text_words = set([lemmatize(token) for token in self.text_tokens])
self.hyp_words = set([lemmatize(token) for token in self.hyp_tokens])
if self.stop:
self.text_words = self.text_words - self.stopwords
self.hyp_words = self.hyp_words - self.stopwords
self._overlap = self.hyp_words & self.text_words
self._hyp_extra = self.hyp_words - self.text_words
self._txt_extra = self.text_words - self.hyp_words
def LanguageAnalyzer(lang,
expression=default_pattern,
gaps=False,
cachesize=50000):
"""Configures a simple analyzer for the given language, with a
LowercaseFilter, StopFilter, and StemFilter.
>>> ana = LanguageAnalyzer("es")
>>> [token.text for token in ana("Por el mar corren las liebres")]
['mar', 'corr', 'liebr']
:param expression: The regular expression pattern to use to extract tokens.
:param gaps: If True, the tokenizer *splits* on the expression, rather
than matching on the expression.
:param cachesize: the maximum number of stemmed words to cache. The larger
this number, the faster stemming will be but the more memory it will
use.
"""
from whoosh.lang import NoStemmer, NoStopWords
from whoosh.lang import stopwords_for_language
# Make the start of the chain
chain = (RegexTokenizer(expression=expression, gaps=gaps)
| LowercaseFilter())
# Add a stop word filter
try:
stoplist = stopwords_for_language(lang)
chain = chain | StopFilter(stoplist=stoplist)
except NoStopWords:
pass
# Add a stemming filter
try:
chain = chain | StemFilter(lang=lang, cachesize=cachesize)
except NoStemmer:
pass
return chain
def LanguageAnalyzer(lang, expression=default_pattern, gaps=False,
cachesize=50000):
"""Configures a simple analyzer for the given language, with a
LowercaseFilter, StopFilter, and StemFilter.
>>> ana = LanguageAnalyzer("es")
>>> [token.text for token in ana("Por el mar corren las liebres")]
['mar', 'corr', 'liebr']
:param expression: The regular expression pattern to use to extract tokens.
:param gaps: If True, the tokenizer *splits* on the expression, rather
than matching on the expression.
:param cachesize: the maximum number of stemmed words to cache. The larger
this number, the faster stemming will be but the more memory it will
use.
"""
from whoosh.lang import NoStemmer, NoStopWords
from whoosh.lang import stopwords_for_language
# Make the start of the chain
chain = (RegexTokenizer(expression=expression, gaps=gaps)
| LowercaseFilter())
# Add a stop word filter
try:
stoplist = stopwords_for_language(lang)
chain = chain | StopFilter(stoplist=stoplist)
except NoStopWords:
pass
# Add a stemming filter
try:
chain = chain | StemFilter(lang=lang, cachesize=cachesize)
except NoStemmer:
pass
return chain
