def get_words(self, unit):
"""Return list of word pairs for an unit."""
words = set()
source_language = unit.translation.component.project.source_language
# Filters stop words for a language
try:
stopfilter = StopFilter(lang=source_language.base_code)
except NoStopWords:
stopfilter = StopFilter()
# Prepare analyzers
# - simple analyzer just splits words based on regexp
# - language analyzer if available (it is for English)
analyzers = [
SimpleAnalyzer(expression=SPLIT_RE, gaps=True) | stopfilter,
LanguageAnalyzer(source_language.base_code),
]
# Add ngram analyzer for languages like Chinese or Japanese
if source_language.uses_ngram():
analyzers.append(NgramAnalyzer(4))
# Extract words from all plurals and from context
flags = unit.all_flags
for text in unit.get_source_plurals() + [unit.context]:
text = strip_string(text, flags).lower()
for analyzer in analyzers:
# Some Whoosh analyzers break on unicode
try:
words.update(token.text for token in analyzer(text))
except (UnicodeDecodeError, IndexError) as error:
report_error(error)
if len(words) > 1000:
break
if len(words) > 1000:
break
if '' in words:
words.remove('')
if not words:
# No extracted words, no dictionary
return self.none()
# Build the query for fetching the words
# We want case insensitive lookup
return self.filter(
project=unit.translation.component.project,
language=unit.translation.language,
source__iregex=r'(^|[ \t\n\r\f\v])({0})($|[ \t\n\r\f\v])'.format(
'|'.join(re_escape(word) for word in islice(words, 1000))),
)
def ChineseAnalyzer(expression=default_pattern,
stoplist=None,
minsize=2,
maxsize=None,
gaps=False,
stemfn=stem,
ignore=None,
cachesize=50000):
"""Composes a RegexTokenizer with a lower case filter, an optional stop
filter, and a stemming filter.
用小写过滤器、可选的停止停用词过滤器和词干过滤器组成生成器。
>>> ana = ChineseAnalyzer()
>>> [token.text for token in ana("Testing is testing and testing")]
["test", "test", "test"]
:param expression: 用于提取 token 令牌的正则表达式
:param stoplist: 一个停用词列表。 设置为 None 标识禁用停用词过滤功能。
:param minsize: 单词最小长度，小于它的单词将被从流中删除。
:param maxsize: 单词最大长度，大于它的单词将被从流中删除。
:param gaps: 如果为 True, tokenizer 令牌解析器将会分割正则表达式，而非匹配正则表达式
:param ignore: 一组忽略的单词。
:param cachesize: 缓存词干词的最大数目。 这个数字越大，词干生成的速度就越快，但占用的内存就越多。
使用 None 表示无缓存，使用 -1 表示无限缓存。
"""
ret = ChineseTokenizer(expression=expression, gaps=gaps)
chain = ret | LowercaseFilter()
if stoplist is not None:
chain = chain | StopFilter(
stoplist=stoplist, minsize=minsize, maxsize=maxsize)
return chain | StemFilter(
stemfn=stemfn, ignore=ignore, cachesize=cachesize)
def FancyAnalyzer(expression=r"\s+",
stoplist=STOP_WORDS,
minsize=2,
maxsize=None,
gaps=True,
splitwords=True,
splitnums=True,
mergewords=False,
mergenums=False):
"""Composes a RegexTokenizer with an IntraWordFilter, LowercaseFilter, and
StopFilter.
>>> ana = FancyAnalyzer()
>>> [token.text for token in ana("Should I call getInt or get_real?")]
["should", "call", "getInt", "get", "int", "get_real", "get", "real"]
:param expression: The regular expression pattern to use to extract tokens.
:param stoplist: A list of stop words. Set this to None to disable
the stop word filter.
:param minsize: Words smaller than this are removed from the stream.
:param maxsize: Words longer that this are removed from the stream.
:param gaps: If True, the tokenizer *splits* on the expression, rather
than matching on the expression.
"""
return (RegexTokenizer(expression=expression, gaps=gaps)
| IntraWordFilter(splitwords=splitwords,
splitnums=splitnums,
mergewords=mergewords,
mergenums=mergenums)
| LowercaseFilter()
| StopFilter(stoplist=stoplist, minsize=minsize))
def StemmingAnalyzer(expression=default_pattern,
stoplist=STOP_WORDS,
minsize=2,
maxsize=None,
gaps=False,
stemfn=stem,
ignore=None,
cachesize=50000):
"""Composes a RegexTokenizer with a lower case filter, an optional stop
filter, and a stemming filter.
>>> ana = StemmingAnalyzer()
>>> [token.text for token in ana("Testing is testing and testing")]
["test", "test", "test"]
:param expression: The regular expression pattern to use to extract tokens.
:param stoplist: A list of stop words. Set this to None to disable
the stop word filter.
:param minsize: Words smaller than this are removed from the stream.
:param maxsize: Words longer that this are removed from the stream.
:param gaps: If True, the tokenizer *splits* on the expression, rather
than matching on the expression.
:param ignore: a set of words to not stem.
: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. Use None for no cache, or -1 for an unbounded cache.
"""
ret = RegexTokenizer(expression=expression, gaps=gaps)
chain = ret | LowercaseFilter()
if stoplist is not None:
chain = chain | StopFilter(
stoplist=stoplist, minsize=minsize, maxsize=maxsize)
return chain | StemFilter(
stemfn=stemfn, ignore=ignore, cachesize=cachesize)
def StandardAnalyzer(expression=default_pattern,
stoplist=STOP_WORDS,
minsize=2,
maxsize=None,
gaps=False):
"""Composes a RegexTokenizer with a LowercaseFilter and optional
StopFilter.
>>> ana = StandardAnalyzer()
>>> [token.text for token in ana("Testing is testing and testing")]
["testing", "testing", "testing"]
:param expression: The regular expression pattern to use to extract tokens.
:param stoplist: A list of stop words. Set this to None to disable
the stop word filter.
:param minsize: Words smaller than this are removed from the stream.
:param maxsize: Words longer that this are removed from the stream.
:param gaps: If True, the tokenizer *splits* on the expression, rather
than matching on the expression.
"""
ret = RegexTokenizer(expression=expression, gaps=gaps)
chain = ret | LowercaseFilter()
if stoplist is not None:
chain = chain | StopFilter(
stoplist=stoplist, minsize=minsize, maxsize=maxsize)
return chain
def stop(text):
stopper = StopFilter()
tokenizer = SimpleAnalyzer()
tokens = tokenizer(text)
result = []
for token in stopper(tokens):
result.append(repr(token.text))
return ' '.join(result)
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']
The list of available languages is in `whoosh.lang.languages`.
You can use :func:`whoosh.lang.has_stemmer` and
:func:`whoosh.lang.has_stopwords` to check if a given language has a
stemming function and/or stop word list available.
: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
# Make the start of the chain
chain = (RegexTokenizer(expression=expression, gaps=gaps)
| LowercaseFilter())
# Add a stop word filter
try:
chain = chain | StopFilter(lang=lang)
except NoStopWords:
pass
# Add a stemming filter
try:
chain = chain | StemFilter(lang=lang, cachesize=cachesize)
except NoStemmer:
pass
return chain
def get_terms(self, unit):
"""Return list of term pairs for an unit."""
words = set()
source_language = unit.translation.component.project.source_language
# Filters stop words for a language
try:
stopfilter = StopFilter(lang=source_language.base_code)
except NoStopWords:
stopfilter = StopFilter()
# Prepare analyzers
# - basic simple analyzer to split on non-word chars
# - simple analyzer just splits words based on regexp to catch in word dashes
# - language analyzer if available (it is for English)
analyzers = [
SimpleAnalyzer() | stopfilter,
SimpleAnalyzer(expression=SPLIT_RE, gaps=True) | stopfilter,
LanguageAnalyzer(source_language.base_code),
]
# Add ngram analyzer for languages like Chinese or Japanese
if source_language.uses_ngram():
analyzers.append(NgramAnalyzer(4))
# Extract words from all plurals and from context
flags = unit.all_flags
for text in unit.get_source_plurals() + [unit.context]:
text = strip_string(text, flags).lower()
for analyzer in analyzers:
# Some Whoosh analyzers break on unicode
try:
words.update(token.text for token in analyzer(text))
except (UnicodeDecodeError, IndexError):
report_error(cause="Term words parsing")
if len(words) > 1000:
break
if len(words) > 1000:
break
if "" in words:
words.remove("")
if not words:
# No extracted words, no glossary
return self.none()
# Build the query for fetching the words
# We want case insensitive lookup
words = islice(words, 1000)
if settings.DATABASES["default"][
"ENGINE"] == "django.db.backends.postgresql":
# Use regex as that is utilizing pg_trgm index
results = self.filter(
source__iregex=r"(^|[ \t\n\r\f\v])({0})($|[ \t\n\r\f\v])".
format("|".join(re_escape(word) for word in words)), )
else:
# MySQL
results = self.filter(
reduce(
lambda x, y: x | y,
(models.Q(source__search=word) for word in words),
), )
return results.for_project(unit.translation.component.project).filter(
language=unit.translation.language)
def get_words(self, unit):
"""Return list of word pairs for an unit."""
words = set()
source_language = unit.translation.component.project.source_language
# Filters stop words for a language
try:
stopfilter = StopFilter(lang=source_language.base_code)
except NoStopWords:
stopfilter = StopFilter()
# Prepare analyzers
# - simple analyzer just splits words based on regexp
# - language analyzer if available (it is for English)
analyzers = [
SimpleAnalyzer(expression=SPLIT_RE, gaps=True) | stopfilter,
LanguageAnalyzer(source_language.base_code),
]
# Add ngram analyzer for languages like Chinese or Japanese
if source_language.uses_ngram():
analyzers.append(NgramAnalyzer(4))
# Extract words from all plurals and from context
flags = unit.all_flags
for text in unit.get_source_plurals() + [unit.context]:
text = strip_string(text, flags).lower()
for analyzer in analyzers:
# Some Whoosh analyzers break on unicode
try:
words.update(token.text for token in analyzer(text))
except (UnicodeDecodeError, IndexError) as error:
report_error(error)
if len(words) > 1000:
break
if len(words) > 1000:
break
if "" in words:
words.remove("")
if not words:
# No extracted words, no dictionary
return self.none()
# Build the query for fetching the words
# We want case insensitive lookup
words = islice(words, 1000)
if settings.DATABASES["default"][
"ENGINE"] == "django.db.backends.postgresql":
results = self.filter(source__search=reduce(
lambda x, y: x | y, (SearchQuery(word) for word in words)), )
else:
# MySQL
results = self.filter(
reduce(
lambda x, y: x | y,
(models.Q(source__search=word) for word in words),
), )
return results.filter(
project=unit.translation.component.project,
language=unit.translation.language,
)
