1
0
Fork 0

Adding upstream version 2.5.1.

Signed-off-by: Daniel Baumann <daniel@debian.org>
This commit is contained in:
Daniel Baumann 2025-05-19 00:20:02 +02:00
parent c71cb8b61d
commit 982828099e
Signed by: daniel
GPG key ID: FBB4F0E80A80222F
783 changed files with 150650 additions and 0 deletions

View file

@ -0,0 +1,60 @@
// Copyright (c) 2014 Couchbase, Inc.
//
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
//
// http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS IS" BASIS,
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.
package pt
import (
"github.com/blevesearch/bleve/v2/analysis"
"github.com/blevesearch/bleve/v2/registry"
"github.com/blevesearch/bleve/v2/analysis/token/lowercase"
"github.com/blevesearch/bleve/v2/analysis/tokenizer/unicode"
)
const AnalyzerName = "pt"
func AnalyzerConstructor(config map[string]interface{}, cache *registry.Cache) (analysis.Analyzer, error) {
tokenizer, err := cache.TokenizerNamed(unicode.Name)
if err != nil {
return nil, err
}
toLowerFilter, err := cache.TokenFilterNamed(lowercase.Name)
if err != nil {
return nil, err
}
stopPtFilter, err := cache.TokenFilterNamed(StopName)
if err != nil {
return nil, err
}
stemmerPtFilter, err := cache.TokenFilterNamed(LightStemmerName)
if err != nil {
return nil, err
}
rv := analysis.DefaultAnalyzer{
Tokenizer: tokenizer,
TokenFilters: []analysis.TokenFilter{
toLowerFilter,
stopPtFilter,
stemmerPtFilter,
},
}
return &rv, nil
}
func init() {
err := registry.RegisterAnalyzer(AnalyzerName, AnalyzerConstructor)
if err != nil {
panic(err)
}
}

View file

@ -0,0 +1,70 @@
// Copyright (c) 2014 Couchbase, Inc.
//
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
//
// http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS IS" BASIS,
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.
package pt
import (
"reflect"
"testing"
"github.com/blevesearch/bleve/v2/analysis"
"github.com/blevesearch/bleve/v2/registry"
)
func TestPortugueseAnalyzer(t *testing.T) {
tests := []struct {
input []byte
output analysis.TokenStream
}{
// stemming
{
input: []byte("quilométricas"),
output: analysis.TokenStream{
&analysis.Token{
Term: []byte("quilometric"),
},
},
},
{
input: []byte("quilométricos"),
output: analysis.TokenStream{
&analysis.Token{
Term: []byte("quilometric"),
},
},
},
// stop word
{
input: []byte("não"),
output: analysis.TokenStream{},
},
}
cache := registry.NewCache()
analyzer, err := cache.AnalyzerNamed(AnalyzerName)
if err != nil {
t.Fatal(err)
}
for _, test := range tests {
actual := analyzer.Analyze(test.input)
if len(actual) != len(test.output) {
t.Fatalf("expected length: %d, got %d", len(test.output), len(actual))
}
for i, tok := range actual {
if !reflect.DeepEqual(tok.Term, test.output[i].Term) {
t.Errorf("expected term %s (% x) got %s (% x)", test.output[i].Term, test.output[i].Term, tok.Term, tok.Term)
}
}
}
}

View file

@ -0,0 +1,198 @@
// Copyright (c) 2015 Couchbase, Inc.
//
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
//
// http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS IS" BASIS,
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.
package pt
import (
"bytes"
"github.com/blevesearch/bleve/v2/analysis"
"github.com/blevesearch/bleve/v2/registry"
)
const LightStemmerName = "stemmer_pt_light"
type PortugueseLightStemmerFilter struct {
}
func NewPortugueseLightStemmerFilter() *PortugueseLightStemmerFilter {
return &PortugueseLightStemmerFilter{}
}
func (s *PortugueseLightStemmerFilter) Filter(input analysis.TokenStream) analysis.TokenStream {
for _, token := range input {
runes := bytes.Runes(token.Term)
runes = stem(runes)
token.Term = analysis.BuildTermFromRunes(runes)
}
return input
}
func stem(input []rune) []rune {
inputLen := len(input)
if inputLen < 4 {
return input
}
input = removeSuffix(input)
inputLen = len(input)
if inputLen > 3 && input[inputLen-1] == 'a' {
input = normFeminine(input)
inputLen = len(input)
}
if inputLen > 4 {
switch input[inputLen-1] {
case 'e', 'a', 'o':
input = input[0 : inputLen-1]
inputLen = len(input)
}
}
for i := 0; i < inputLen; i++ {
switch input[i] {
case 'à', 'á', 'â', 'ä', 'ã':
input[i] = 'a'
case 'ò', 'ó', 'ô', 'ö', 'õ':
input[i] = 'o'
case 'è', 'é', 'ê', 'ë':
input[i] = 'e'
case 'ù', 'ú', 'û', 'ü':
input[i] = 'u'
case 'ì', 'í', 'î', 'ï':
input[i] = 'i'
case 'ç':
input[i] = 'c'
}
}
return input
}
func removeSuffix(input []rune) []rune {
inputLen := len(input)
if inputLen > 4 && analysis.RunesEndsWith(input, "es") {
switch input[inputLen-3] {
case 'r', 's', 'l', 'z':
return input[0 : inputLen-2]
}
}
if inputLen > 3 && analysis.RunesEndsWith(input, "ns") {
input[inputLen-2] = 'm'
return input[0 : inputLen-1]
}
if inputLen > 4 && (analysis.RunesEndsWith(input, "eis") || analysis.RunesEndsWith(input, "éis")) {
input[inputLen-3] = 'e'
input[inputLen-2] = 'l'
return input[0 : inputLen-1]
}
if inputLen > 4 && analysis.RunesEndsWith(input, "ais") {
input[inputLen-2] = 'l'
return input[0 : inputLen-1]
}
if inputLen > 4 && analysis.RunesEndsWith(input, "óis") {
input[inputLen-3] = 'o'
input[inputLen-2] = 'l'
return input[0 : inputLen-1]
}
if inputLen > 4 && analysis.RunesEndsWith(input, "is") {
input[inputLen-1] = 'l'
return input
}
if inputLen > 3 &&
(analysis.RunesEndsWith(input, "ões") ||
analysis.RunesEndsWith(input, "ães")) {
input = input[0 : inputLen-1]
inputLen = len(input)
input[inputLen-2] = 'ã'
input[inputLen-1] = 'o'
return input
}
if inputLen > 6 && analysis.RunesEndsWith(input, "mente") {
return input[0 : inputLen-5]
}
if inputLen > 3 && input[inputLen-1] == 's' {
return input[0 : inputLen-1]
}
return input
}
func normFeminine(input []rune) []rune {
inputLen := len(input)
if inputLen > 7 &&
(analysis.RunesEndsWith(input, "inha") ||
analysis.RunesEndsWith(input, "iaca") ||
analysis.RunesEndsWith(input, "eira")) {
input[inputLen-1] = 'o'
return input
}
if inputLen > 6 {
if analysis.RunesEndsWith(input, "osa") ||
analysis.RunesEndsWith(input, "ica") ||
analysis.RunesEndsWith(input, "ida") ||
analysis.RunesEndsWith(input, "ada") ||
analysis.RunesEndsWith(input, "iva") ||
analysis.RunesEndsWith(input, "ama") {
input[inputLen-1] = 'o'
return input
}
if analysis.RunesEndsWith(input, "ona") {
input[inputLen-3] = 'ã'
input[inputLen-2] = 'o'
return input[0 : inputLen-1]
}
if analysis.RunesEndsWith(input, "ora") {
return input[0 : inputLen-1]
}
if analysis.RunesEndsWith(input, "esa") {
input[inputLen-3] = 'ê'
return input[0 : inputLen-1]
}
if analysis.RunesEndsWith(input, "na") {
input[inputLen-1] = 'o'
return input
}
}
return input
}
func PortugueseLightStemmerFilterConstructor(config map[string]interface{}, cache *registry.Cache) (analysis.TokenFilter, error) {
return NewPortugueseLightStemmerFilter(), nil
}
func init() {
err := registry.RegisterTokenFilter(LightStemmerName, PortugueseLightStemmerFilterConstructor)
if err != nil {
panic(err)
}
}

View file

@ -0,0 +1,404 @@
// Copyright (c) 2015 Couchbase, Inc.
//
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
//
// http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS IS" BASIS,
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.
package pt
import (
"reflect"
"testing"
"github.com/blevesearch/bleve/v2/analysis"
"github.com/blevesearch/bleve/v2/registry"
)
func TestPortugueseLightStemmer(t *testing.T) {
tests := []struct {
input analysis.TokenStream
output analysis.TokenStream
}{
{
input: analysis.TokenStream{
&analysis.Token{
Term: []byte("doutores"),
},
},
output: analysis.TokenStream{
&analysis.Token{
Term: []byte("doutor"),
},
},
},
{
input: analysis.TokenStream{
&analysis.Token{
Term: []byte("doutor"),
},
},
output: analysis.TokenStream{
&analysis.Token{
Term: []byte("doutor"),
},
},
},
{
input: analysis.TokenStream{
&analysis.Token{
Term: []byte("homens"),
},
},
output: analysis.TokenStream{
&analysis.Token{
Term: []byte("homem"),
},
},
},
{
input: analysis.TokenStream{
&analysis.Token{
Term: []byte("homem"),
},
},
output: analysis.TokenStream{
&analysis.Token{
Term: []byte("homem"),
},
},
},
{
input: analysis.TokenStream{
&analysis.Token{
Term: []byte("papéis"),
},
},
output: analysis.TokenStream{
&analysis.Token{
Term: []byte("papel"),
},
},
},
{
input: analysis.TokenStream{
&analysis.Token{
Term: []byte("papel"),
},
},
output: analysis.TokenStream{
&analysis.Token{
Term: []byte("papel"),
},
},
},
{
input: analysis.TokenStream{
&analysis.Token{
Term: []byte("normais"),
},
},
output: analysis.TokenStream{
&analysis.Token{
Term: []byte("normal"),
},
},
},
{
input: analysis.TokenStream{
&analysis.Token{
Term: []byte("normal"),
},
},
output: analysis.TokenStream{
&analysis.Token{
Term: []byte("normal"),
},
},
},
{
input: analysis.TokenStream{
&analysis.Token{
Term: []byte("lencóis"),
},
},
output: analysis.TokenStream{
&analysis.Token{
Term: []byte("lencol"),
},
},
},
{
input: analysis.TokenStream{
&analysis.Token{
Term: []byte("lencol"),
},
},
output: analysis.TokenStream{
&analysis.Token{
Term: []byte("lencol"),
},
},
},
{
input: analysis.TokenStream{
&analysis.Token{
Term: []byte("barris"),
},
},
output: analysis.TokenStream{
&analysis.Token{
Term: []byte("barril"),
},
},
},
{
input: analysis.TokenStream{
&analysis.Token{
Term: []byte("barril"),
},
},
output: analysis.TokenStream{
&analysis.Token{
Term: []byte("barril"),
},
},
},
{
input: analysis.TokenStream{
&analysis.Token{
Term: []byte("botões"),
},
},
output: analysis.TokenStream{
&analysis.Token{
Term: []byte("bota"),
},
},
},
{
input: analysis.TokenStream{
&analysis.Token{
Term: []byte("botão"),
},
},
output: analysis.TokenStream{
&analysis.Token{
Term: []byte("bota"),
},
},
},
// longer
{
input: analysis.TokenStream{
&analysis.Token{
Term: []byte("o"),
},
&analysis.Token{
Term: []byte("debate"),
},
&analysis.Token{
Term: []byte("político"),
},
&analysis.Token{
Term: []byte("pelo"),
},
&analysis.Token{
Term: []byte("menos"),
},
&analysis.Token{
Term: []byte("o"),
},
&analysis.Token{
Term: []byte("que"),
},
&analysis.Token{
Term: []byte("vem"),
},
&analysis.Token{
Term: []byte("a"),
},
&analysis.Token{
Term: []byte("público"),
},
&analysis.Token{
Term: []byte("parece"),
},
&analysis.Token{
Term: []byte("de"),
},
&analysis.Token{
Term: []byte("modo"),
},
&analysis.Token{
Term: []byte("nada"),
},
&analysis.Token{
Term: []byte("surpreendente"),
},
&analysis.Token{
Term: []byte("restrito"),
},
&analysis.Token{
Term: []byte("a"),
},
&analysis.Token{
Term: []byte("temas"),
},
&analysis.Token{
Term: []byte("menores"),
},
&analysis.Token{
Term: []byte("mas"),
},
&analysis.Token{
Term: []byte("há"),
},
&analysis.Token{
Term: []byte("evidentemente"),
},
&analysis.Token{
Term: []byte("grandes"),
},
&analysis.Token{
Term: []byte("questões"),
},
&analysis.Token{
Term: []byte("em"),
},
&analysis.Token{
Term: []byte("jogo"),
},
&analysis.Token{
Term: []byte("nas"),
},
&analysis.Token{
Term: []byte("eleições"),
},
&analysis.Token{
Term: []byte("que"),
},
&analysis.Token{
Term: []byte("se"),
},
&analysis.Token{
Term: []byte("aproximam"),
},
},
output: analysis.TokenStream{
&analysis.Token{
Term: []byte("o"),
},
&analysis.Token{
Term: []byte("debat"),
},
&analysis.Token{
Term: []byte("politic"),
},
&analysis.Token{
Term: []byte("pelo"),
},
&analysis.Token{
Term: []byte("meno"),
},
&analysis.Token{
Term: []byte("o"),
},
&analysis.Token{
Term: []byte("que"),
},
&analysis.Token{
Term: []byte("vem"),
},
&analysis.Token{
Term: []byte("a"),
},
&analysis.Token{
Term: []byte("public"),
},
&analysis.Token{
Term: []byte("parec"),
},
&analysis.Token{
Term: []byte("de"),
},
&analysis.Token{
Term: []byte("modo"),
},
&analysis.Token{
Term: []byte("nada"),
},
&analysis.Token{
Term: []byte("surpreendent"),
},
&analysis.Token{
Term: []byte("restrit"),
},
&analysis.Token{
Term: []byte("a"),
},
&analysis.Token{
Term: []byte("tema"),
},
&analysis.Token{
Term: []byte("menor"),
},
&analysis.Token{
Term: []byte("mas"),
},
&analysis.Token{
Term: []byte("há"),
},
&analysis.Token{
Term: []byte("evident"),
},
&analysis.Token{
Term: []byte("grand"),
},
&analysis.Token{
Term: []byte("questa"),
},
&analysis.Token{
Term: []byte("em"),
},
&analysis.Token{
Term: []byte("jogo"),
},
&analysis.Token{
Term: []byte("nas"),
},
&analysis.Token{
Term: []byte("eleica"),
},
&analysis.Token{
Term: []byte("que"),
},
&analysis.Token{
Term: []byte("se"),
},
&analysis.Token{
Term: []byte("aproximam"),
},
},
},
}
cache := registry.NewCache()
filter, err := cache.TokenFilterNamed(LightStemmerName)
if err != nil {
t.Fatal(err)
}
for _, test := range tests {
actual := filter.Filter(test.input)
if !reflect.DeepEqual(actual, test.output) {
t.Errorf("expected %s, got %s", test.output[0].Term, actual[0].Term)
}
}
}

View file

@ -0,0 +1,36 @@
// Copyright (c) 2014 Couchbase, Inc.
//
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
//
// http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS IS" BASIS,
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.
package pt
import (
"github.com/blevesearch/bleve/v2/analysis"
"github.com/blevesearch/bleve/v2/analysis/token/stop"
"github.com/blevesearch/bleve/v2/registry"
)
func StopTokenFilterConstructor(config map[string]interface{}, cache *registry.Cache) (analysis.TokenFilter, error) {
tokenMap, err := cache.TokenMapNamed(StopName)
if err != nil {
return nil, err
}
return stop.NewStopTokensFilter(tokenMap), nil
}
func init() {
err := registry.RegisterTokenFilter(StopName, StopTokenFilterConstructor)
if err != nil {
panic(err)
}
}

View file

@ -0,0 +1,280 @@
package pt
import (
"github.com/blevesearch/bleve/v2/analysis"
"github.com/blevesearch/bleve/v2/registry"
)
const StopName = "stop_pt"
// this content was obtained from:
// lucene-4.7.2/analysis/common/src/resources/org/apache/lucene/analysis/snowball/
// ` was changed to ' to allow for literal string
var PortugueseStopWords = []byte(` | From svn.tartarus.org/snowball/trunk/website/algorithms/portuguese/stop.txt
| This file is distributed under the BSD License.
| See http://snowball.tartarus.org/license.php
| Also see http://www.opensource.org/licenses/bsd-license.html
| - Encoding was converted to UTF-8.
| - This notice was added.
|
| NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
| A Portuguese stop word list. Comments begin with vertical bar. Each stop
| word is at the start of a line.
| The following is a ranked list (commonest to rarest) of stopwords
| deriving from a large sample of text.
| Extra words have been added at the end.
de | of, from
a | the; to, at; her
o | the; him
que | who, that
e | and
do | de + o
da | de + a
em | in
um | a
para | for
| é from SER
com | with
não | not, no
uma | a
os | the; them
no | em + o
se | himself etc
na | em + a
por | for
mais | more
as | the; them
dos | de + os
como | as, like
mas | but
| foi from SER
ao | a + o
ele | he
das | de + as
| tem from TER
à | a + a
seu | his
sua | her
ou | or
| ser from SER
quando | when
muito | much
| from HAV
nos | em + os; us
| already, now
| está from EST
eu | I
também | also
| only, just
pelo | per + o
pela | per + a
até | up to
isso | that
ela | he
entre | between
| era from SER
depois | after
sem | without
mesmo | same
aos | a + os
| ter from TER
seus | his
quem | whom
nas | em + as
me | me
esse | that
eles | they
| estão from EST
você | you
| tinha from TER
| foram from SER
essa | that
num | em + um
nem | nor
suas | her
meu | my
às | a + as
minha | my
| têm from TER
numa | em + uma
pelos | per + os
elas | they
| havia from HAV
| seja from SER
qual | which
| será from SER
nós | we
| tenho from TER
lhe | to him, her
deles | of them
essas | those
esses | those
pelas | per + as
este | this
| fosse from SER
dele | of him
| other words. There are many contractions such as naquele = em+aquele,
| mo = me+o, but they are rare.
| Indefinite article plural forms are also rare.
tu | thou
te | thee
vocês | you (plural)
vos | you
lhes | to them
meus | my
minhas
teu | thy
tua
teus
tuas
nosso | our
nossa
nossos
nossas
dela | of her
delas | of them
esta | this
estes | these
estas | these
aquele | that
aquela | that
aqueles | those
aquelas | those
isto | this
aquilo | that
| forms of estar, to be (not including the infinitive):
estou
está
estamos
estão
estive
esteve
estivemos
estiveram
estava
estávamos
estavam
estivera
estivéramos
esteja
estejamos
estejam
estivesse
estivéssemos
estivessem
estiver
estivermos
estiverem
| forms of haver, to have (not including the infinitive):
hei
havemos
hão
houve
houvemos
houveram
houvera
houvéramos
haja
hajamos
hajam
houvesse
houvéssemos
houvessem
houver
houvermos
houverem
houverei
houverá
houveremos
houverão
houveria
houveríamos
houveriam
| forms of ser, to be (not including the infinitive):
sou
somos
são
era
éramos
eram
fui
foi
fomos
foram
fora
fôramos
seja
sejamos
sejam
fosse
fôssemos
fossem
for
formos
forem
serei
será
seremos
serão
seria
seríamos
seriam
| forms of ter, to have (not including the infinitive):
tenho
tem
temos
tém
tinha
tínhamos
tinham
tive
teve
tivemos
tiveram
tivera
tivéramos
tenha
tenhamos
tenham
tivesse
tivéssemos
tivessem
tiver
tivermos
tiverem
terei
terá
teremos
terão
teria
teríamos
teriam
`)
func TokenMapConstructor(config map[string]interface{}, cache *registry.Cache) (analysis.TokenMap, error) {
rv := analysis.NewTokenMap()
err := rv.LoadBytes(PortugueseStopWords)
return rv, err
}
func init() {
err := registry.RegisterTokenMap(StopName, TokenMapConstructor)
if err != nil {
panic(err)
}
}