def test_apply():
def visit(q):
if isinstance(q, (Term, Variations, FuzzyTerm)):
q.text = q.text.upper()
return q
return q.apply(visit)
before = And([Not(Term("a", u("b"))), Variations("a", u("c")),
Not(FuzzyTerm("a", u("d")))])
after = visit(before)
assert_equal(after, And([Not(Term("a", u("B"))), Variations("a", u("C")),
Not(FuzzyTerm("a", u("D")))]))
def term2var(q):
if isinstance(q, Term):
return Variations(q.fieldname, q.text)
else:
return q.apply(term2var)
q = And([Term("f", "alfa"), Or([Term("f", "bravo"),
Not(Term("f", "charlie"))])])
q = term2var(q)
assert_equal(q, And([Variations('f', 'alfa'),
Or([Variations('f', 'bravo'),
Not(Variations('f', 'charlie'))])]))
def queryCategoryGenerator(busqueda):
trozos = busqueda
query = None
for p in trozos:
if (query is None):
query = FuzzyTerm("categoria", p, maxdist=2)
else:
query = query | FuzzyTerm("categoria", p, maxdist=2)
return query
def querySearchGenerator(busqueda):
trozos = busqueda.split(" ")
query = None
for p in trozos:
if (query is None):
query = FuzzyTerm("titulo", p, maxdist=int(
len(p) / 4)) | FuzzyTerm(
"descripcion", p, maxdist=int(len(p) / 4))
else:
query = query | FuzzyTerm("titulo", p, maxdist=int(
len(p) / 4)) | FuzzyTerm(
"descripcion", p, maxdist=int(len(p) / 4))
return query
def busqueda_noticia(request):
form = NoticiaBusquedaForm()
noticias = None
if request.method == 'POST':
form = NoticiaBusquedaForm(request.POST)
if form.is_valid():
noticias = Noticia.objects.all()
keywords = form.cleaned_data['keywords']
ix = open_dir(dirindex)
with ix.searcher() as searcher:
temas = keywords.split()
for x in temas:
query = FuzzyTerm('titulo', x)
#Si no funciona bien, hacerlo con Term
noticias = noticias & searcher.search(query)
else:
form = NoticiaBusquedaForm()
return render(request, 'busqueda_noticias.html', {
'form': form,
'noticias': noticias
})
def search_doc(self,
word,
docTypes,
numPage=1,
numByPage=10,
showNumResults=False):
"""
Return a list of docs that contains given word and that matches
given type.
"""
indexSchema = IndexSchema()
# Retrieves the fields to search from the doctypes schema
fieldsToSearch = []
for docType in docTypes:
docType = docType.lower()
try:
schema = indexSchema.doctypesSchema[docType]
fieldsToSearch = fieldsToSearch + schema
except:
logger.warning("Schema not found for %s" % docType)
# By default we search "content" (for BC) and "tags"
fields = ['content', 'tags'] + fieldsToSearch
logger.info("Search will be performed on fields %s" % fields)
# Creates the query parser.
# MultifieldParser allows search on multiple fields.
# We use a custom FuzzyTerm class to set the Levenstein distance to 2
parser = MultifieldParser(fields,
schema=indexSchema.schema,
termclass=CustomFuzzyTerm)
query = parser.parse(word)
# Creates a filter on the doctype field
doctypeFilterMatcher = []
for docType in docTypes:
term = FuzzyTerm("docType", unicode(docType.lower()), 1.0, 2)
doctypeFilterMatcher.append(term)
docTypeFilter = Or(doctypeFilterMatcher)
# Processes the search (request the index, Whoosh magic)
with indexSchema.index.searcher() as searcher:
results = searcher.search_page(query,
numPage,
pagelen=numByPage,
filter=docTypeFilter)
resultsID = [result["docId"] for result in results]
logger.info("Results: %s" % resultsID)
# Ensures BC if the number of results is not requested
if showNumResults:
return {'ids': resultsID, 'numResults': len(results)}
else:
return {'ids': resultsID}
def test_fuzzyterm():
schema = fields.Schema(id=fields.STORED, f=fields.TEXT)
ix = RamStorage().create_index(schema)
w = ix.writer()
w.add_document(id=1, f=u("alfa bravo charlie delta"))
w.add_document(id=2, f=u("bravo charlie delta echo"))
w.add_document(id=3, f=u("charlie delta echo foxtrot"))
w.add_document(id=4, f=u("delta echo foxtrot golf"))
w.commit()
with ix.searcher() as s:
q = FuzzyTerm("f", "brave")
assert_equal([d["id"] for d in s.search(q)], [1, 2])
def queryCategoryGenerator(busqueda):
trozos = []
for b in busqueda:
t = []
if " " in b:
t = b.split(" ")
trozos = trozos + t
elif "/" in b:
t = b.split("/")
trozos = trozos + t
trozos.append(b)
query = None
for p in trozos:
if (query is None):
query = FuzzyTerm("categoria", p, maxdist=2)
else:
query = query | FuzzyTerm("categoria", p, maxdist=2)
return query
def test_query_copy_hash():
def do(q1, q2):
q1a = copy.deepcopy(q1)
assert_equal(q1, q1a)
assert_equal(hash(q1), hash(q1a))
assert_not_equal(q1, q2)
do(Term("a", u("b"), boost=1.1), Term("a", u("b"), boost=1.5))
do(And([Term("a", u("b")), Term("c", u("d"))], boost=1.1),
And([Term("a", u("b")), Term("c", u("d"))], boost=1.5))
do(Or([Term("a", u("b"), boost=1.1), Term("c", u("d"))]),
Or([Term("a", u("b"), boost=1.8), Term("c", u("d"))], boost=1.5))
do(DisjunctionMax([Term("a", u("b"), boost=1.8), Term("c", u("d"))]),
DisjunctionMax([Term("a", u("b"), boost=1.1), Term("c", u("d"))],
boost=1.5))
do(Not(Term("a", u("b"), boost=1.1)), Not(Term("a", u("b"), boost=1.5)))
do(Prefix("a", u("b"), boost=1.1), Prefix("a", u("b"), boost=1.5))
do(Wildcard("a", u("b*x?"), boost=1.1), Wildcard("a", u("b*x?"),
boost=1.5))
do(FuzzyTerm("a", u("b"), constantscore=True),
FuzzyTerm("a", u("b"), constantscore=False))
do(FuzzyTerm("a", u("b"), boost=1.1), FuzzyTerm("a", u("b"), boost=1.5))
do(TermRange("a", u("b"), u("c")), TermRange("a", u("b"), u("d")))
do(TermRange("a", None, u("c")), TermRange("a", None, None))
do(TermRange("a", u("b"), u("c"), boost=1.1),
TermRange("a", u("b"), u("c"), boost=1.5))
do(TermRange("a", u("b"), u("c"), constantscore=True),
TermRange("a", u("b"), u("c"), constantscore=False))
do(NumericRange("a", 1, 5), NumericRange("a", 1, 6))
do(NumericRange("a", None, 5), NumericRange("a", None, None))
do(NumericRange("a", 3, 6, boost=1.1), NumericRange("a", 3, 6, boost=1.5))
do(NumericRange("a", 3, 6, constantscore=True),
NumericRange("a", 3, 6, constantscore=False))
# do(DateRange)
do(Variations("a", u("render")), Variations("a", u("renders")))
do(Variations("a", u("render"), boost=1.1),
Variations("a", u("renders"), boost=1.5))
do(Phrase("a", [u("b"), u("c"), u("d")]),
Phrase("a", [u("b"), u("c"), u("e")]))
do(Phrase("a", [u("b"), u("c"), u("d")], boost=1.1),
Phrase("a", [u("b"), u("c"), u("d")], boost=1.5))
do(Phrase("a", [u("b"), u("c"), u("d")], slop=1),
Phrase("a", [u("b"), u("c"), u("d")], slop=2))
# do(Ordered)
do(Every(), Every("a"))
do(Every("a"), Every("b"))
do(Every("a", boost=1.1), Every("a", boost=1.5))
do(NullQuery, Term("a", u("b")))
do(ConstantScoreQuery(Term("a", u("b"))),
ConstantScoreQuery(Term("a", u("c"))))
do(ConstantScoreQuery(Term("a", u("b")), score=2.0),
ConstantScoreQuery(Term("a", u("c")), score=2.1))
do(Require(Term("a", u("b")), Term("c", u("d"))),
Require(Term("a", u("b"), boost=1.1), Term("c", u("d"))))
# do(Require)
# do(AndMaybe)
# do(AndNot)
# do(Otherwise)
do(SpanFirst(Term("a", u("b")), limit=1), SpanFirst(Term("a", u("b")),
limit=2))
do(SpanNear(Term("a", u("b")), Term("c", u("d"))),
SpanNear(Term("a", u("b")), Term("c", u("e"))))
do(SpanNear(Term("a", u("b")), Term("c", u("d")), slop=1),
SpanNear(Term("a", u("b")), Term("c", u("d")), slop=2))
do(SpanNear(Term("a", u("b")), Term("c", u("d")), mindist=1),
SpanNear(Term("a", u("b")), Term("c", u("d")), mindist=2))
do(SpanNear(Term("a", u("b")), Term("c", u("d")), ordered=True),
SpanNear(Term("a", u("b")), Term("c", u("d")), ordered=False))
do(SpanNot(Term("a", u("b")), Term("a", u("c"))),
SpanNot(Term("a", u("b")), Term("a", u("d"))))
do(SpanOr([Term("a", u("b")), Term("a", u("c")), Term("a", u("d"))]),
SpanOr([Term("a", u("b")), Term("a", u("c")), Term("a", u("e"))]))
do(SpanContains(Term("a", u("b")), Term("a", u("c"))),
SpanContains(Term("a", u("b")), Term("a", u("d"))))
def __init__(self, fieldname, text, boost=1.0, maxdist=1):
FuzzyTerm.__init__(self, fieldname, text, 1.0, 2)
def search_doc(directory,
word,
doc_types,
num_page=1,
num_by_page=10,
show_num_results=True):
"""
* -------------{Function}---------------
* Returns a list of docs that contains a given set of words that matches a g
* -------------{returns}----------------
* {set} query results . . .
* -------------{params}-----------------
* : directory -> path of the index
* : word -> words to query
* : doc_types -> type of doc to search
* : num_page -> number of pages to search
* : show_num_results -> number of results to return
"""
index_schema = load_index(directory)
doctypes_schema = load_doctypes_schema(directory)
# Retrieves the fields to search from the doctypes schema
fields_to_search = []
for doc_type in doc_types:
doc_type = doc_type.lower()
try:
schema = doctypes_schema[doc_type]
fields_to_search = fields_to_search + schema
except:
logger.warning(
"Schema not found for {doc_type}".format(doc_type=doc_type))
# By default we search "content" (for BC) and "tags"
fields = ["content", "tags"] + fields_to_search
logger.info(
"search will be performed on fields {fields}".format(fields=fields))
# Creates the query parser
# MultifieldParser allows search on multiple fields
# We use custom FuzzyTerm class to set the Leveshtein distance to 2
parser = MultifieldParser(fields,
schema=doctypes_schema,
termclass=CustomFuzzyTerm)
query = parser.parse(word)
# Creates a filter on the doctype field
doctype_filter_matcher = []
for doc_type in doc_types:
term = FuzzyTerm("doc_type", doc_type.lower(), 1.0, 2)
doctype_filter_matcher.append(term)
doc_type_filter = Or(doctype_filter_matcher)
# Processes the search(request the index, whoosh magic)
with index_schema.searcher() as searcher:
results = searcher.search_page(query,
num_page,
pagelen=num_by_page,
filter=doc_type_filter)
results_id = [result["doc_id"] for result in results]
logger.info("Results: {results_id}".format(results_id=results_id))
# Ensures BC if the number of results is not requested
if show_num_results:
return {"ids": results_id, "num_results": len(results)}
else:
return {"ids": results_id}
def __init__(self, fieldname, text, boost=1.0, maxdist=1):
FuzzyTerm.__init__(self, fieldname, text, 1.0, 2)
'''
Created on Oct 27, 2014
@author: Cassie
'''
from whoosh import index
from whoosh.qparser import QueryParser
from whoosh.query import And, Term, Not, FuzzyTerm, Phrase
ix = index.open_dir("index")
q1 = And([
Term("city_text", u"greek"),
Term("city_text", u"roman"),
Not(Term("city_text", u"persian"))
])
q2 = FuzzyTerm("city_text", u"shakespeare")
q3 = Phrase("city_text", [u"located", u"below", u"sea", u"level"], slop=10)
with ix.searcher() as s:
results = s.search(q2, limit=None)
for a in results:
print a['city_name']
def fuzzy_term(q, dist, field):
if len(q) <= 3:
return Term(field, q)
return FuzzyTerm(field, q, maxdist=dist, prefixlength=1)
def perform_search(self, sentence):
with self._searcher() as s:
tokens = sentence.split()
tokens = [token for token in tokens if token != REPLACED]
print('tokens=', tokens)
exact_and_match = And([Term(TEXT_FIELD, t) for t in tokens],
boost=.5)
exact_or_match = Or([Term(TEXT_FIELD, t) for t in tokens],
boost=.5,
scale=0.9)
# Added variability of maxdist based on word length
fuzzy_or_match = Or([
FuzzyTerm(TEXT_FIELD,
t,
prefixlength=1,
maxdist=1 if len(t) < 8 else 2)
for t in tokens if len(t) >= 4
],
boost=.2,
scale=0.9)
if len(tokens) > 1:
# add bigrams if there are any
bigrams = ['_'.join(b) for b in find_ngrams(tokens, 2)]
bigram_fuzzy_or_match = Or([
FuzzyTerm(BIGRAMS_FIELD,
b,
prefixlength=3,
maxdist=2 if len(b) < 8 else 3) for b in bigrams
],
scale=0.9)
else:
bigram_fuzzy_or_match = None
non_brand_or_match = Or(
[Term(NONBRAND_TEXT_FIELD, t) for t in tokens])
# q = exact_and_match \
# | exact_or_match \
# | fuzzy_or_match
# my_match = Or([Term(f, token) for token in tokens], boost=1)
# q = my_match
#
# q = Or([FuzzyTerm(f, token, prefixlength=2) for token in tokens if len(token) >= 3], boost=1.0,
# scale=0.9)
q = exact_and_match | exact_or_match | fuzzy_or_match | non_brand_or_match
if bigram_fuzzy_or_match:
q = q | bigram_fuzzy_or_match
print(q)
search_results = self.get_search_results(self._index, s, q)
for x in search_results:
print(x, x.score)
if search_results:
score, text, matched = search_results[0].items()
return text, list(set(matched))
else:
return None, None
def fuzzy_term(q: str, dist: int, field: str) -> Term:
if len(q) <= 3:
return Term(field, q)
return FuzzyTerm(field, q, maxdist=dist, prefixlength=1)
def search(self, query):
with self.index.searcher() as searcher:
terms = [FuzzyTerm("content", word, maxdist=2) for word in query]
search_query = Or(terms)
results = searcher.search(search_query)
return [result["filename"] for result in results]
