forgejo/golang-github-blevesearch-bleve
1
0
Fork 0
Code Issues Activity

Adding upstream version 2.5.1.

Browse source 
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
Download patch file Download diff file Expand all files Collapse all files

60
analysis/lang/pl/analyzer_pl.go Normal file
View file

@ -0,0 +1,60 @@
// Copyright (c) 2018 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 pl
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 = "pl"
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
}
stopPlFilter, err := cache.TokenFilterNamed(StopName)
if err != nil {
return nil, err
}
stemmerPlFilter, err := cache.TokenFilterNamed(SnowballStemmerName)
if err != nil {
return nil, err
}
rv := analysis.DefaultAnalyzer{
Tokenizer: tokenizer,
TokenFilters: []analysis.TokenFilter{
toLowerFilter,
stopPlFilter,
stemmerPlFilter,
},
}
return &rv, nil
}
func init() {
err := registry.RegisterAnalyzer(AnalyzerName, AnalyzerConstructor)
if err != nil {
panic(err)
}
}

149
analysis/lang/pl/analyzer_pl_test.go Normal file
View file

@ -0,0 +1,149 @@
// Copyright (c) 2018 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 pl
import (
"reflect"
"testing"
"github.com/blevesearch/bleve/v2/analysis"
"github.com/blevesearch/bleve/v2/registry"
)
func TestPolishAnalyzer(t *testing.T) {
tests := []struct {
input []byte
output analysis.TokenStream
}{
// stemming
{
input: []byte("śmiało"),
output: analysis.TokenStream{
&analysis.Token{
Term: []byte("śmieć"),
},
},
},
{
input: []byte("przypadku"),
output: analysis.TokenStream{
&analysis.Token{
Term: []byte("przypadek"),
},
},
},
// stop word
{
input: []byte("według"),
output: analysis.TokenStream{},
},
// digits safe
{
input: []byte("text 1000"),
output: analysis.TokenStream{
&analysis.Token{
Term: []byte("text"),
},
&analysis.Token{
Term: []byte("1000"),
},
},
},
{
input: []byte("badawczego było opracowanie kompendium które przystępny sposób prezentowało niespecjalistom zakresu kryptografii kwantowej wykorzystanie technik kwantowych do bezpiecznego przesyłu przetwarzania informacji"),
output: analysis.TokenStream{
&analysis.Token{
Term: []byte("badawczy"),
},
&analysis.Token{
Term: []byte("opracować"),
},
&analysis.Token{
Term: []byte("kompendium"),
},
&analysis.Token{
Term: []byte("przystyć"),
},
&analysis.Token{
Term: []byte("prezentować"),
},
&analysis.Token{
Term: []byte("niespecjalista"),
},
&analysis.Token{
Term: []byte("zakres"),
},
&analysis.Token{
Term: []byte("kryptografia"),
},
&analysis.Token{
Term: []byte("kwantowy"),
},
&analysis.Token{
Term: []byte("wykorzyseć"),
},
&analysis.Token{
Term: []byte("technika"),
},
&analysis.Token{
Term: []byte("kwantowy"),
},
&analysis.Token{
Term: []byte("bezpieczny"),
},
&analysis.Token{
Term: []byte("przesył"),
},
&analysis.Token{
Term: []byte("przetwarzać"),
},
&analysis.Token{
Term: []byte("informacja"),
},
},
},
{
input: []byte("Ale ta wiedza była utrzymywana w tajemnicy"),
output: analysis.TokenStream{
&analysis.Token{
Term: []byte("wiedza"),
},
&analysis.Token{
Term: []byte("utrzymywać"),
},
&analysis.Token{
Term: []byte("tajemnik"),
},
},
},
}
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)
}
}
}
}

58
analysis/lang/pl/stemmer_pl.go Normal file
View file

@ -0,0 +1,58 @@
// Copyright (c) 2018 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 pl
import (
"github.com/blevesearch/bleve/v2/analysis"
"github.com/blevesearch/bleve/v2/analysis/lang/pl/stempel"
"github.com/blevesearch/bleve/v2/registry"
)
const SnowballStemmerName = "stemmer_pl"
type PolishStemmerFilter struct {
trie stempel.Trie
}
func NewPolishStemmerFilter() (*PolishStemmerFilter, error) {
trie, err := stempel.LoadTrie()
if err != nil {
return nil, err
}
return &PolishStemmerFilter{
trie: trie,
}, nil
}
func (s *PolishStemmerFilter) Filter(input analysis.TokenStream) analysis.TokenStream {
for _, token := range input {
buff := []rune(string(token.Term))
diff := s.trie.GetLastOnPath(buff)
buff = stempel.Diff(buff, diff)
token.Term = []byte(string(buff))
}
return input
}
func PolishStemmerFilterConstructor(config map[string]interface{}, cache *registry.Cache) (analysis.TokenFilter, error) {
return NewPolishStemmerFilter()
}
func init() {
err := registry.RegisterTokenFilter(SnowballStemmerName, PolishStemmerFilterConstructor)
if err != nil {
panic(err)
}
}

67
analysis/lang/pl/stemmer_pl_test.go Normal file
View file

@ -0,0 +1,67 @@
// Copyright (c) 2018 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 pl
import (
"reflect"
"testing"
"github.com/blevesearch/bleve/v2/analysis"
"github.com/blevesearch/bleve/v2/registry"
)
func TestPolishStemmer(t *testing.T) {
tests := []struct {
input analysis.TokenStream
output analysis.TokenStream
}{
{
input: analysis.TokenStream{
&analysis.Token{
Term: []byte("utrzymywana"),
},
},
output: analysis.TokenStream{
&analysis.Token{
Term: []byte("utrzymywać"),
},
},
},
{
input: analysis.TokenStream{
&analysis.Token{
Term: []byte("tajemnicy"),
},
},
output: analysis.TokenStream{
&analysis.Token{
Term: []byte("tajemnik"),
},
},
},
}
cache := registry.NewCache()
filter, err := cache.TokenFilterNamed(SnowballStemmerName)
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)
}
}
}

202
analysis/lang/pl/stempel/LICENSE Normal file
View file

@ -0,0 +1,202 @@
Apache License
Version 2.0, January 2004
http://www.apache.org/licenses/
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
1. Definitions.
"License" shall mean the terms and conditions for use, reproduction,
and distribution as defined by Sections 1 through 9 of this document.
"Licensor" shall mean the copyright owner or entity authorized by
the copyright owner that is granting the License.
"Legal Entity" shall mean the union of the acting entity and all
other entities that control, are controlled by, or are under common
control with that entity. For the purposes of this definition,
"control" means (i) the power, direct or indirect, to cause the
direction or management of such entity, whether by contract or
otherwise, or (ii) ownership of fifty percent (50%) or more of the
outstanding shares, or (iii) beneficial ownership of such entity.
"You" (or "Your") shall mean an individual or Legal Entity
exercising permissions granted by this License.
"Source" form shall mean the preferred form for making modifications,
including but not limited to software source code, documentation
source, and configuration files.
"Object" form shall mean any form resulting from mechanical
transformation or translation of a Source form, including but
not limited to compiled object code, generated documentation,
and conversions to other media types.
"Work" shall mean the work of authorship, whether in Source or
Object form, made available under the License, as indicated by a
copyright notice that is included in or attached to the work
(an example is provided in the Appendix below).
"Derivative Works" shall mean any work, whether in Source or Object
form, that is based on (or derived from) the Work and for which the
editorial revisions, annotations, elaborations, or other modifications
represent, as a whole, an original work of authorship. For the purposes
of this License, Derivative Works shall not include works that remain
separable from, or merely link (or bind by name) to the interfaces of,
the Work and Derivative Works thereof.
"Contribution" shall mean any work of authorship, including
the original version of the Work and any modifications or additions
to that Work or Derivative Works thereof, that is intentionally
submitted to Licensor for inclusion in the Work by the copyright owner
or by an individual or Legal Entity authorized to submit on behalf of
the copyright owner. For the purposes of this definition, "submitted"
means any form of electronic, verbal, or written communication sent
to the Licensor or its representatives, including but not limited to
communication on electronic mailing lists, source code control systems,
and issue tracking systems that are managed by, or on behalf of, the
Licensor for the purpose of discussing and improving the Work, but
excluding communication that is conspicuously marked or otherwise
designated in writing by the copyright owner as "Not a Contribution."
"Contributor" shall mean Licensor and any individual or Legal Entity
on behalf of whom a Contribution has been received by Licensor and
subsequently incorporated within the Work.
2. Grant of Copyright License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
copyright license to reproduce, prepare Derivative Works of,
publicly display, publicly perform, sublicense, and distribute the
Work and such Derivative Works in Source or Object form.
3. Grant of Patent License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
(except as stated in this section) patent license to make, have made,
use, offer to sell, sell, import, and otherwise transfer the Work,
where such license applies only to those patent claims licensable
by such Contributor that are necessarily infringed by their
Contribution(s) alone or by combination of their Contribution(s)
with the Work to which such Contribution(s) was submitted. If You
institute patent litigation against any entity (including a
cross-claim or counterclaim in a lawsuit) alleging that the Work
or a Contribution incorporated within the Work constitutes direct
or contributory patent infringement, then any patent licenses
granted to You under this License for that Work shall terminate
as of the date such litigation is filed.
4. Redistribution. You may reproduce and distribute copies of the
Work or Derivative Works thereof in any medium, with or without
modifications, and in Source or Object form, provided that You
meet the following conditions:
(a) You must give any other recipients of the Work or
Derivative Works a copy of this License; and
(b) You must cause any modified files to carry prominent notices
stating that You changed the files; and
(c) You must retain, in the Source form of any Derivative Works
that You distribute, all copyright, patent, trademark, and
attribution notices from the Source form of the Work,
excluding those notices that do not pertain to any part of
the Derivative Works; and
(d) If the Work includes a "NOTICE" text file as part of its
distribution, then any Derivative Works that You distribute must
include a readable copy of the attribution notices contained
within such NOTICE file, excluding those notices that do not
pertain to any part of the Derivative Works, in at least one
of the following places: within a NOTICE text file distributed
as part of the Derivative Works; within the Source form or
documentation, if provided along with the Derivative Works; or,
within a display generated by the Derivative Works, if and
wherever such third-party notices normally appear. The contents
of the NOTICE file are for informational purposes only and
do not modify the License. You may add Your own attribution
notices within Derivative Works that You distribute, alongside
or as an addendum to the NOTICE text from the Work, provided
that such additional attribution notices cannot be construed
as modifying the License.
You may add Your own copyright statement to Your modifications and
may provide additional or different license terms and conditions
for use, reproduction, or distribution of Your modifications, or
for any such Derivative Works as a whole, provided Your use,
reproduction, and distribution of the Work otherwise complies with
the conditions stated in this License.
5. Submission of Contributions. Unless You explicitly state otherwise,
any Contribution intentionally submitted for inclusion in the Work
by You to the Licensor shall be under the terms and conditions of
this License, without any additional terms or conditions.
Notwithstanding the above, nothing herein shall supersede or modify
the terms of any separate license agreement you may have executed
with Licensor regarding such Contributions.
6. Trademarks. This License does not grant permission to use the trade
names, trademarks, service marks, or product names of the Licensor,
except as required for reasonable and customary use in describing the
origin of the Work and reproducing the content of the NOTICE file.
7. Disclaimer of Warranty. Unless required by applicable law or
agreed to in writing, Licensor provides the Work (and each
Contributor provides its Contributions) on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
implied, including, without limitation, any warranties or conditions
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
PARTICULAR PURPOSE. You are solely responsible for determining the
appropriateness of using or redistributing the Work and assume any
risks associated with Your exercise of permissions under this License.
8. Limitation of Liability. In no event and under no legal theory,
whether in tort (including negligence), contract, or otherwise,
unless required by applicable law (such as deliberate and grossly
negligent acts) or agreed to in writing, shall any Contributor be
liable to You for damages, including any direct, indirect, special,
incidental, or consequential damages of any character arising as a
result of this License or out of the use or inability to use the
Work (including but not limited to damages for loss of goodwill,
work stoppage, computer failure or malfunction, or any and all
other commercial damages or losses), even if such Contributor
has been advised of the possibility of such damages.
9. Accepting Warranty or Additional Liability. While redistributing
the Work or Derivative Works thereof, You may choose to offer,
and charge a fee for, acceptance of support, warranty, indemnity,
or other liability obligations and/or rights consistent with this
License. However, in accepting such obligations, You may act only
on Your own behalf and on Your sole responsibility, not on behalf
of any other Contributor, and only if You agree to indemnify,
defend, and hold each Contributor harmless for any liability
incurred by, or claims asserted against, such Contributor by reason
of your accepting any such warranty or additional liability.
END OF TERMS AND CONDITIONS
APPENDIX: How to apply the Apache License to your work.
To apply the Apache License to your work, attach the following
boilerplate notice, with the fields enclosed by brackets "[]"
replaced with your own identifying information. (Don't include
the brackets!) The text should be enclosed in the appropriate
comment syntax for the file format. We also recommend that a
file or class name and description of purpose be included on the
same "printed page" as the copyright notice for easier
identification within third-party archives.
Copyright [yyyy] [name of copyright owner]
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.

53
analysis/lang/pl/stempel/cell.go Normal file
View file

@ -0,0 +1,53 @@
// Copyright (c) 2018 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 stempel
import (
"fmt"
"github.com/blevesearch/stempel/javadata"
)
type cell struct {
ref int32
cmd int32
}
func (c *cell) String() string {
return fmt.Sprintf("ref(%d) cmd(%d)", c.ref, c.cmd)
}
func newCell(r *javadata.Reader) (*cell, error) {
cmd, err := r.ReadInt32()
if err != nil {
return nil, fmt.Errorf("error reading cell cmd: %v", err)
}
_, err = r.ReadInt32()
if err != nil {
return nil, fmt.Errorf("error reading cell cnt: %v", err)
}
ref, err := r.ReadInt32()
if err != nil {
return nil, fmt.Errorf("error reading cell ref: %v", err)
}
_, err = r.ReadInt32()
if err != nil {
return nil, fmt.Errorf("error reading cell skip: %v", err)
}
return &cell{
cmd: cmd,
ref: ref,
}, nil
}

64
analysis/lang/pl/stempel/diff.go Normal file
View file

@ -0,0 +1,64 @@
// Copyright (c) 2018 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 stempel
// Diff transforms the dest rune slice following the rules described
// in the diff command rune slice.
func Diff(dest, diff []rune) []rune {
if len(diff) == 0 {
return dest
}
pos := len(dest) - 1
if pos < 0 {
return dest
}
for i := 0; i < len(diff)/2; i++ {
cmd := diff[2*i]
param := diff[2*i+1]
parNum := int(param - 'a' + 1)
switch cmd {
case '-':
pos = pos - parNum + 1
case 'R':
if pos < 0 || pos >= len(dest) {
// out of bounds, just return
return dest
}
dest[pos] = param
case 'D':
o := pos
pos -= parNum - 1
if pos < 0 || pos >= len(dest) {
// out of bounds, just return
return dest
}
dest = append(dest[:pos], dest[o+1:]...)
case 'I':
pos++
if pos < 0 || pos > len(dest) {
// out of bounds, just return
return dest
}
dest = append(dest, 0)
copy(dest[pos+1:], dest[pos:])
dest[pos] = param
}
pos--
}
return dest
}

144
analysis/lang/pl/stempel/diff_test.go Normal file
View file

@ -0,0 +1,144 @@
// Copyright (c) 2018 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 stempel
import (
"fmt"
"reflect"
"testing"
)
func TestDiff(t *testing.T) {
tests := []struct {
in []rune
cmd []rune
out []rune
}{
// test delete, this command deletes N chars backwards from the current pos
// the current pos starts at the end of the string
// if you try to delete a negative number of chars or more chars than there
// are, you will get the buffer at that time
{
in: []rune{'h', 'e', 'l', 'l', 'o'},
// delete 1
cmd: []rune{'D', 'a'},
out: []rune{'h', 'e', 'l', 'l'},
},
{
in: []rune{'h', 'e', 'l', 'l', 'o'},
// delete 2
cmd: []rune{'D', 'a' + 1},
out: []rune{'h', 'e', 'l'},
},
{
in: []rune{'h', 'e', 'l', 'l', 'o'},
// delete 3
cmd: []rune{'D', 'a' + 2},
out: []rune{'h', 'e'},
},
{
in: []rune{'h', 'e', 'l', 'l', 'o'},
// delete 4
cmd: []rune{'D', 'a' + 3},
out: []rune{'h'},
},
{
in: []rune{'h', 'e', 'l', 'l', 'o'},
// delete 5
cmd: []rune{'D', 'a' + 4},
out: []rune{},
},
{
in: []rune{'h', 'e', 'l', 'l', 'o'},
// delete 6 (invalid, return buffer at that point)
cmd: []rune{'D', 'a' + 5},
out: []rune{'h', 'e', 'l', 'l', 'o'},
},
{
in: []rune{'h', 'e', 'l', 'l', 'o'},
// delete -1
cmd: []rune{'D', 'a' - 1},
out: []rune{'h', 'e', 'l', 'l', 'o'},
},
// delete one char twice
{
in: []rune{'h', 'e', 'l', 'l', 'o'},
// delete 1, delete 1
cmd: []rune{'D', 'a', 'D', 'a'},
out: []rune{'h', 'e', 'l'},
},
// test insert
{
in: []rune{'h', 'e', 'l', 'l', 'o'},
// insert 'p'
cmd: []rune{'I', 'p'},
out: []rune{'h', 'e', 'l', 'l', 'o', 'p'},
},
// insert twice
{
in: []rune{'h'},
// insert 'l', insert 'e'
// NOTE how the cursor moves backwards, so we have to insert in reverse
cmd: []rune{'I', 'l', 'I', 'e'},
out: []rune{'h', 'e', 'l'},
},
// test replace
{
in: []rune{'h', 'e', 'l', 'l', 'o'},
// replace with 'y'
cmd: []rune{'R', 'y'},
out: []rune{'h', 'e', 'l', 'l', 'y'},
},
// test replace again
{
in: []rune{'h', 'e', 'l', 'l', 'o'},
// replace with 'y', then replace with 'x'
// NOTE how the cursor moves backwards as we replace
cmd: []rune{'R', 'y', 'R', 'x'},
out: []rune{'h', 'e', 'l', 'x', 'y'},
},
// test skip, then replace
{
in: []rune{'h', 'e', 'l', 'l', 'o'},
// skip 1, then replace with 'y'
cmd: []rune{'-', 'a', 'R', 'y'},
out: []rune{'h', 'e', 'l', 'y', 'o'},
},
// test skip 2, then replace
{
in: []rune{'h', 'e', 'l', 'l', 'o'},
// skip 1, then replace with 'y'
cmd: []rune{'-', 'a' + 1, 'R', 'y'},
out: []rune{'h', 'e', 'y', 'l', 'o'},
},
// test skip 2, then replace
{
in: []rune{'h', 'e', 'l', 'l', 'o'},
// skip 5 (too far), then replace with 'y'
// get original
cmd: []rune{'-', 'a' + 4, 'R', 'y'},
out: []rune{'h', 'e', 'l', 'l', 'o'},
},
}
for _, test := range tests {
t.Run(fmt.Sprintf("%s-'%s'", string(test.in), string(test.cmd)), func(t *testing.T) {
got := Diff(test.in, test.cmd)
if !reflect.DeepEqual(test.out, got) {
t.Errorf("expected %v, got %v", test.out, got)
}
})
}
}

71
analysis/lang/pl/stempel/file.go Normal file
View file

@ -0,0 +1,71 @@
// Copyright (c) 2018 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 stempel
import (
"bytes"
_ "embed"
"github.com/blevesearch/stempel/javadata"
"io"
"os"
"strings"
)
//go:embed pl/stemmer_20000.tbl
var stempelFile []byte
// Trie is the external interface to work with the stempel trie
type Trie interface {
GetLastOnPath([]rune) []rune
}
// Open attempts to open a file at the specified path, and use it to
// build a Trie
func Open(path string) (Trie, error) {
f, err := os.Open(path)
if err != nil {
return nil, err
}
return buildTrieFromReader(f)
}
// LoadTrie load trie from embed file
func LoadTrie() (Trie, error) {
return buildTrieFromReader(bytes.NewReader(stempelFile))
}
// buildTrieFromReader build trie from io.Reader
func buildTrieFromReader(f io.Reader) (Trie, error) {
r := javadata.NewReader(f)
method, err := r.ReadUTF()
if err != nil {
return nil, err
}
var rv Trie
if strings.Contains(method, "M") {
rv, err = newMultiTrie(r)
if err != nil {
return nil, err
}
} else {
rv, err = newTrie(r)
if err != nil {
return nil, err
}
}
return rv, nil
}

91
analysis/lang/pl/stempel/file_test.go Normal file
View file

@ -0,0 +1,91 @@
// Copyright (c) 2018 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 stempel
import (
"bufio"
"compress/gzip"
"os"
"strings"
"testing"
"golang.org/x/text/encoding/charmap"
)
func TestEmpty(t *testing.T) {
trie, err := Open("pl/stemmer_20000.tbl")
if err != nil {
t.Fatal(err)
}
buff := []rune("")
diff := trie.GetLastOnPath(buff)
if len(diff) > 0 {
t.Fatalf("expected empty diff, got %v", diff)
}
buff = Diff(buff, diff)
if len(buff) > 0 {
t.Fatalf("expected empty buff, got %v", buff)
}
}
// TestStem only tests that we can successfully stem everything in the
// dictionary without crashing. It does not attempt to assert correct output.
func TestStem(t *testing.T) {
trie, err := Open("pl/stemmer_20000.tbl")
if err != nil {
t.Fatal(err)
}
wordFileGz, err := os.Open("pl/pl_PL.dic.gz")
if err != nil {
t.Fatal(err)
}
defer func() {
cerr := wordFileGz.Close()
if cerr != nil {
t.Fatal(cerr)
}
}()
wordFile, err := gzip.NewReader(wordFileGz)
if err != nil {
t.Fatal(err)
}
defer func() {
cerr := wordFile.Close()
if cerr != nil {
t.Fatal(cerr)
}
}()
cr := charmap.ISO8859_2.NewDecoder().Reader(wordFile)
scanner := bufio.NewScanner(cr)
for scanner.Scan() {
before := scanner.Text()
hasSlash := strings.Index(before, "/")
if hasSlash > 0 {
before = before[0:hasSlash]
}
buff := []rune(before)
diff := trie.GetLastOnPath(buff)
_ = Diff(buff, diff)
}
if err := scanner.Err(); err != nil {
t.Fatal(err)
}
}

35
analysis/lang/pl/stempel/fuzz.go Normal file
View file

@ -0,0 +1,35 @@
// Copyright (c) 2018 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.
//go:build gofuzz
// +build gofuzz
package stempel
var fuzzTrie Trie
func init() {
var err error
fuzzTrie, err = Open("pl/stemmer_20000.tbl")
if err != nil {
panic(err)
}
}
func Fuzz(data []byte) int {
inRunes := []rune(string(data))
diff := fuzzTrie.GetLastOnPath(inRunes)
_ = Diff(inRunes, diff)
return 1
}

3
analysis/lang/pl/stempel/javadata/README.md Normal file
View file

@ -0,0 +1,3 @@
# javadata
Go library to read data written with java.io.DataOutput

34
analysis/lang/pl/stempel/javadata/fuzz.go Normal file
View file

@ -0,0 +1,34 @@
// Copyright (c) 2018 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.
//go:build gofuzz
// +build gofuzz
package javadata
import "bytes"
func Fuzz(data []byte) int {
br := bytes.NewReader(data)
jdr := NewReader(br)
var err error
for err == nil {
_, err = jdr.ReadUTF()
}
if err != nil {
return 0
}
return 1
}

135
analysis/lang/pl/stempel/javadata/input.go Normal file
View file

@ -0,0 +1,135 @@
// Copyright (c) 2018 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 javadata
import (
"bufio"
"encoding/binary"
"fmt"
"io"
)
// ErrMalformedInput returned when malformed input is encountered
var ErrMalformedInput = fmt.Errorf("malformed input")
// Reader knows how to read java serialized data
type Reader struct {
r *bufio.Reader
}
// NewReader creates a new java data input reader
func NewReader(r io.Reader) *Reader {
return &Reader{r: bufio.NewReader(r)}
}
// ReadBool attempts to reads a bool from the stream
func (r *Reader) ReadBool() (bool, error) {
b, err := r.r.ReadByte()
if err != nil {
return false, err
}
return b != 0, nil
}
// ReadInt32 attempts to reads a signed 32-bit integer from the stream
func (r *Reader) ReadInt32() (rv int32, err error) {
err = binary.Read(r.r, binary.BigEndian, &rv)
return
}
// ReadUint16 attempts to reads a unsigned 16-bit integer from the stream
func (r *Reader) ReadUint16() (rv uint16, err error) {
err = binary.Read(r.r, binary.BigEndian, &rv)
return
}
// ReadCharAsRune attempts to read a java two byte char and return it as a rune
func (r *Reader) ReadCharAsRune() (rv rune, err error) {
var char uint16
err = binary.Read(r.r, binary.BigEndian, &char)
rv = rune(char)
return
}
// ReadUTF attempts to reads a UTF-encoded string from the stream
// this method follows the specific alternate encoding desribed here:
// https://docs.oracle.com/javase/7/docs/api/java/io/DataInput.html
func (r *Reader) ReadUTF() (string, error) {
utfLen, err := r.ReadUint16()
if err != nil {
return "", err
}
bytes := make([]byte, utfLen)
runes := make([]rune, utfLen)
_, err = io.ReadFull(r.r, bytes)
if err != nil {
return "", err
}
var count uint16
var runeCount uint16
// handle simple case of all ascii
for count < utfLen {
c := bytes[count]
if bytes[count] > 127 {
break
}
count++
runes[runeCount] = rune(c)
runeCount++
}
// handle rest
for count < utfLen {
c := bytes[count]
switch bytes[count] >> 4 {
case 0, 1, 2, 3, 4, 5, 6, 7, 8:
/* 0xxxxxxx*/
count++
runes[runeCount] = rune(c)
runeCount++
case 12, 13:
/* 110x xxxx 10xx xxxx*/
count += 2
if count > utfLen {
return "", ErrMalformedInput
}
char2 := rune(bytes[count-1])
if (char2 & 0xC0) != 0x80 {
return "", ErrMalformedInput
}
runes[runeCount] = (rune(c)&0x1F)<<6 | char2&0x3F
runeCount++
case 14:
/* 1110 xxxx 10xx xxxx 10xx xxxx */
count += 3
if count > utfLen {
return "", ErrMalformedInput
}
char2 := rune(bytes[count-2])
char3 := rune(bytes[count-1])
if ((char2 & 0xC0) != 0x80) || ((char3 & 0xC0) != 0x80) {
return "", ErrMalformedInput
}
runes[runeCount] = ((rune(c)&0x0F)<<12 | (char2&0x3F)<<6 | (char3&0x3F)<<0)
runeCount++
default:
/* 10xx xxxx, 1111 xxxx */
return "", ErrMalformedInput
}
}
return string(runes[0:runeCount]), nil
}

249
analysis/lang/pl/stempel/javadata/input_test.go Normal file
View file

@ -0,0 +1,249 @@
// Copyright (c) 2018 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 javadata
import (
"bytes"
"io"
"testing"
)
func TestReadBool(t *testing.T) {
tests := []struct {
in []byte
out bool
err error
}{
{
in: []byte{0},
out: false,
},
{
in: []byte{1},
out: true,
},
{
in: []byte{27},
out: true,
},
{
in: []byte{},
err: io.EOF,
},
}
for _, test := range tests {
t.Run(string(test.in), func(t *testing.T) {
sr := bytes.NewReader(test.in)
dr := NewReader(sr)
actual, err := dr.ReadBool()
if err != test.err {
t.Error(err)
}
if actual != test.out {
t.Errorf("expected %t, got %t", test.out, actual)
}
})
}
}
func TestReadUint16(t *testing.T) {
tests := []struct {
in []byte
out uint16
err error
}{
{
in: []byte{0, 0},
out: 0,
},
{
in: []byte{0, 1},
out: 1,
},
{
in: []byte{1, 0},
out: 256,
},
{
in: []byte{},
err: io.EOF,
},
}
for _, test := range tests {
t.Run(string(test.in), func(t *testing.T) {
sr := bytes.NewReader(test.in)
dr := NewReader(sr)
actual, err := dr.ReadUint16()
if err != test.err {
t.Error(err)
}
if actual != test.out {
t.Errorf("expected %d, got %d", test.out, actual)
}
})
}
}
func TestReadInt32(t *testing.T) {
tests := []struct {
in []byte
out int32
err error
}{
{
in: []byte{0, 0, 0, 0},
out: 0,
},
{
in: []byte{0, 0, 0, 1},
out: 1,
},
{
in: []byte{0, 0, 1, 0},
out: 256,
},
{
in: []byte{0, 1, 0, 0},
out: 65536,
},
{
in: []byte{},
err: io.EOF,
},
}
for _, test := range tests {
t.Run(string(test.in), func(t *testing.T) {
sr := bytes.NewReader(test.in)
dr := NewReader(sr)
actual, err := dr.ReadInt32()
if err != test.err {
t.Error(err)
}
if actual != test.out {
t.Errorf("expected %d, got %d", test.out, actual)
}
})
}
}
func TestReadUTF(t *testing.T) {
tests := []struct {
in []byte
out string
err error
}{
{
in: []byte{0, 3, 'c', 'a', 't'},
out: "cat",
},
{
in: []byte{0, 2, 0xc2, 0xa3},
out: "£",
},
{
in: []byte{0, 3, 0xe3, 0x85, 0x85},
out: "ㅅ",
},
{
in: []byte{0, 6, 0xe3, 0x85, 0x85, 'c', 'a', 't'},
out: "ㅅcat",
},
{
in: []byte{},
err: io.EOF,
},
{
in: []byte{0, 3},
err: io.EOF,
},
{
in: []byte{0, 1, 0xc2},
err: ErrMalformedInput,
},
{
in: []byte{0, 2, 0xc2, 0xc3},
err: ErrMalformedInput,
},
{
in: []byte{0, 2, 0xe3, 0x85},
err: ErrMalformedInput,
},
{
in: []byte{0, 3, 0xe3, 0xc5, 0x85},
err: ErrMalformedInput,
},
{
in: []byte{0, 1, 0xff},
err: ErrMalformedInput,
},
{
in: []byte{0x0, 0x05, 0x44, 0x61, 0x52, 0xc4, 0x87},
out: "DaRć",
},
}
for _, test := range tests {
t.Run(string(test.in), func(t *testing.T) {
sr := bytes.NewReader(test.in)
dr := NewReader(sr)
actual, err := dr.ReadUTF()
if err != test.err {
t.Error(err)
}
if actual != test.out {
t.Errorf("expected %s, got %s", test.out, actual)
}
})
}
}
// func TestFile(t *testing.T) {
// f, err := os.Open("stemmer_20000.tbl")
// if err != nil {
// t.Fatal(err)
// }
// r := NewReader(f)
// reversed, err := r.ReadBool()
// if err != nil {
// t.Fatal(err)
// }
// log.Printf("reversed: %t", reversed)
// root, err := r.ReadInt32()
// if err != nil {
// t.Fatal(err)
// }
// log.Printf("root: %d", root)
// n, err := r.ReadInt32()
// if err != nil {
// t.Fatal(err)
// }
// log.Printf("n is %d", n)
// // for n > 0 {
// // utf, err := r.ReadUTF()
// // if err != nil {
// // t.Error(err)
// // }
// // log.Printf("read: %s", utf)
// // n--
// // }
// }

140
analysis/lang/pl/stempel/multi_trie.go Normal file
View file

@ -0,0 +1,140 @@
// Copyright (c) 2018 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 stempel
import (
"fmt"
"github.com/blevesearch/stempel/javadata"
)
// multiTrie represents a trie of tries. When using the multiTrie, each trie
// is consulted consecutively to find commands to perform on the input. Thus
// a multiTrie with seven tries might have up to seven groups of commands to
// perform on the input.
type multiTrie struct {
tries []*trie
by int32
forward bool
}
func newMultiTrie(r *javadata.Reader) (rv *multiTrie, err error) {
rv = &multiTrie{}
rv.forward, err = r.ReadBool()
if err != nil {
return nil, err
}
rv.by, err = r.ReadInt32()
if err != nil {
return nil, err
}
nTries, err := r.ReadInt32()
if err != nil {
return nil, err
}
for nTries > 0 {
trie, err := newTrie(r)
if err != nil {
return nil, err
}
rv.tries = append(rv.tries, trie)
nTries--
}
return rv, nil
}
const eom = rune('*')
func (t *multiTrie) GetLastOnPath(key []rune) []rune {
var rv []rune
lastKey := key
p := make([][]rune, len(t.tries))
lastR := ' '
for i := 0; i < len(t.tries); i++ {
r := t.tries[i].GetLastOnPath(lastKey)
if len(r) == 0 || len(r) == 1 && r[0] == eom {
return rv
}
if cannotFollow(lastR, r[0]) {
return rv
}
lastR = r[len(r)-2]
p[i] = r
if p[i][0] == '-' {
if i > 0 {
var err error
key, err = t.skip(key, lengthPP(p[i-1]))
if err != nil {
return rv
}
}
var err error
key, err = t.skip(key, lengthPP(p[i]))
if err != nil {
return rv
}
}
rv = append(rv, r...)
if len(key) != 0 {
lastKey = key
}
}
return rv
}
func cannotFollow(after, goes rune) bool {
switch after {
case '-', 'D':
return after == goes
}
return false
}
var errIndexOutOfBounds = fmt.Errorf("index out of bounds")
func (t *multiTrie) skip(in []rune, count int) ([]rune, error) {
if count > len(in) {
return nil, errIndexOutOfBounds
}
if t.forward {
return in[count:], nil
}
return in[0 : len(in)-count], nil
}
func lengthPP(cmd []rune) int {
rv := 0
for i := 0; i < len(cmd); i++ {
switch cmd[i] {
case '-', 'D':
i++
rv += int(cmd[i] - rune('a') + 1)
case 'R':
i++
rv++
fallthrough
case 'I':
}
}
return rv
}
func (t *multiTrie) String() string {
rv := ""
for i, trie := range t.tries {
rv += fmt.Sprintf("trie %d\n\n %v\n--------\n", i, trie)
}
return rv
}

BIN
analysis/lang/pl/stempel/pl/pl_PL.dic.gz Normal file
View file

Binary file not shown.

BIN
analysis/lang/pl/stempel/pl/stemmer_20000.tbl Normal file
View file

Binary file not shown.

80
analysis/lang/pl/stempel/row.go Normal file
View file

@ -0,0 +1,80 @@
// Copyright (c) 2018 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 stempel
import (
"fmt"
"github.com/blevesearch/stempel/javadata"
)
type row struct {
cells map[rune]*cell
}
func (r *row) String() string {
rv := ""
for k, v := range r.cells {
rv += fmt.Sprintf("[%s:%v]\n", string(k), v)
}
return rv
}
func newRow(r *javadata.Reader) (*row, error) {
rv := &row{
cells: make(map[rune]*cell),
}
nCells, err := r.ReadInt32()
if err != nil {
return nil, fmt.Errorf("error reading num cells: %v", err)
}
for nCells > 0 {
c, err := r.ReadCharAsRune()
if err != nil {
return nil, fmt.Errorf("error reading cell char: %v", err)
}
cell, err := newCell(r)
if err != nil {
return nil, fmt.Errorf("error reading cell: %v", err)
}
rv.cells[c] = cell
nCells--
}
return rv, nil
}
func (r *row) getCmd(way rune) int32 {
c := r.at(way)
if c != nil {
return c.cmd
}
return -1
}
func (r *row) getRef(way rune) int32 {
c := r.at(way)
if c != nil {
return c.ref
}
return -1
}
func (r *row) at(c rune) *cell {
return r.cells[c]
}

48
analysis/lang/pl/stempel/strenum.go Normal file
View file

@ -0,0 +1,48 @@
// Copyright (c) 2018 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 stempel
import (
"io"
)
type strEnum struct {
r []rune
from int
by int
}
func newStrEnum(s []rune, up bool) *strEnum {
rv := &strEnum{
r: s,
}
if up {
rv.from = 0
rv.by = 1
} else {
rv.from = len(s) - 1
rv.by = -1
}
return rv
}
func (s *strEnum) next() (rune, error) {
if s.from < 0 || s.from >= len(s.r) {
return 0, io.EOF
}
rv := s.r[s.from]
s.from += s.by
return rv, nil
}

61
analysis/lang/pl/stempel/strenum_test.go Normal file
View file

@ -0,0 +1,61 @@
// Copyright (c) 2018 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 stempel
import (
"fmt"
"io"
"reflect"
"testing"
)
func TestStrenumNext(t *testing.T) {
tests := []struct {
in []rune
up bool
expect []rune
}{
{
in: []rune{'h', 'e', 'l', 'l', 'o'},
up: true,
expect: []rune{'h', 'e', 'l', 'l', 'o'},
},
{
in: []rune{'h', 'e', 'l', 'l', 'o'},
up: false,
expect: []rune{'o', 'l', 'l', 'e', 'h'},
},
}
for _, test := range tests {
t.Run(fmt.Sprintf("%s-up-%t", string(test.in), test.up), func(t *testing.T) {
strenum := newStrEnum(test.in, test.up)
var got []rune
next, err := strenum.next()
for err == nil {
got = append(got, next)
next, err = strenum.next()
}
if err != io.EOF {
t.Errorf("next got err: %v", err)
}
if !reflect.DeepEqual(got, test.expect) {
t.Errorf("expected %v, got %v", test.expect, got)
}
})
}
}

132
analysis/lang/pl/stempel/trie.go Normal file
View file

@ -0,0 +1,132 @@
// Copyright (c) 2018 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 stempel
import (
"fmt"
"github.com/blevesearch/stempel/javadata"
)
// trie represents the internal trie structure
type trie struct {
rows []*row
cmds []string
root int32
forward bool
}
func newTrie(r *javadata.Reader) (rv *trie, err error) {
rv = &trie{}
rv.forward, err = r.ReadBool()
if err != nil {
return nil, fmt.Errorf("error reading trie forward: %v", err)
}
rv.root, err = r.ReadInt32()
if err != nil {
return nil, fmt.Errorf("error reading trie root: %v", err)
}
// commands
nCommands, err := r.ReadInt32()
if err != nil {
return nil, fmt.Errorf("error reading trie num commands: %v", err)
}
for nCommands > 0 {
utfCommand, nerr := r.ReadUTF()
if nerr != nil {
return nil, fmt.Errorf("error reading trie command utf: %v", nerr)
}
rv.cmds = append(rv.cmds, utfCommand)
nCommands--
}
// rows
nRows, err := r.ReadInt32()
if err != nil {
return nil, fmt.Errorf("error reading trie num rows: %v", err)
}
for nRows > 0 {
row, err := newRow(r)
if err != nil {
return nil, fmt.Errorf("error reading trie row: %v", err)
}
rv.rows = append(rv.rows, row)
nRows--
}
return rv, nil
}
func (t *trie) getRow(i int) *row {
if i < 0 || i >= len(t.rows) {
return nil
}
return t.rows[i]
}
func (t *trie) GetLastOnPath(key []rune) []rune {
now := t.getRow(int(t.root))
var last []rune
var w int32
e := newStrEnum(key, t.forward)
// walk over each rune
// if rune has row in the table, note the cmd (as last)
// if rune has row in table, see if it transitions to another row
// if it does, move to that row and next char on next loop itr
// if it does not, return the last cmd
// if you get to end of string and there is command in row use it
// or return last
for i := 0; i < len(key)-1; i++ {
r, err := e.next()
if err != nil {
return last
}
w = now.getCmd(r)
if w >= 0 {
last = []rune(t.cmds[w])
}
w = now.getRef(r)
if w >= 0 {
now = t.getRow(int(w))
} else {
return last
}
}
r, err := e.next()
if err != nil {
return last
}
w = now.getCmd(r)
if err != nil {
return last
}
if w >= 0 {
return []rune(t.cmds[w])
}
return last
}
func (t *trie) String() string {
rv := ""
for _, cmd := range t.cmds {
rv += fmt.Sprintf("cmd: %s\n", string(cmd))
}
for _, row := range t.rows {
rv += fmt.Sprintf("row: %v\n", row)
}
return rv
}

36
analysis/lang/pl/stop_filter_pl.go Normal file
View file

@ -0,0 +1,36 @@
// Copyright (c) 2018 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 pl
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)
}
}

368
analysis/lang/pl/stop_words_pl.go Normal file
View file

@ -0,0 +1,368 @@
package pl
import (
"github.com/blevesearch/bleve/v2/analysis"
"github.com/blevesearch/bleve/v2/registry"
)
const StopName = "stop_pl"
// 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 PolishStopWords = []byte(` | From https://github.com/stopwords-iso/stopwords-pl/tree/master
| The MIT License (MIT)
| See https://github.com/stopwords-iso/stopwords-pl/blob/master/LICENSE
| - Encoding was converted to UTF-8.
| - This notice was added.
| - english text is auto-translate
|
| NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
| a polish stop word list. comments begin with vertical bar. each stop
| word is at the start of a line.
a | and
aby | to
ach | ah
acz | although
aczkolwiek | although
aj | ay
albo | or
ale | but
ależ | but
ani | or
aż | until
bardziej | more
bardzo | very
bez | without
bo | because
bowiem | because
by | by
byli | were
bym | i would
bynajmniej | not at all
być | to be
był | was
była | was
było | was
były | were
będzie | will be
będą | they will
cali | inches
cała | whole
cały | whole
chce | i want
choć | though
ci | you
ciebie | you
cię | you
co | what
cokolwiek | whatever
coraz | getting
coś | something
czasami | sometimes
czasem | sometimes
czemu | why
czy | whether
czyli | that is
często | often
daleko | far
dla | for
dlaczego | why
dlatego | which is why
do | down
dobrze | all right
dokąd | where
dość | enough
dr | dr
dużo | a lot
dwa | two
dwaj | two
dwie | two
dwoje | two
dzisiaj | today
dziś | today
gdy | when
gdyby | if
gdyż | because
gdzie | where
gdziekolwiek | wherever
gdzieś | somewhere
go | him
godz | time
hab | hab
i | and
ich | their
ii | ii
iii | iii
ile | how much
im | them
inna | different
inne | other
inny | other
innych | other
inż | eng
iv | iv
ix | ix
iż | that
ja | i
jak | how
jakaś | some
jakby | as if
jaki | what
jakichś | some
jakie | what
jakiś | some
jakiż | what
jakkolwiek | however
jako | as
jakoś | somehow
je | them
jeden | one
jedna | one
jednak | but
jednakże | however
jedno | one
jednym | one
jedynie | only
jego | his
jej | her
jemu | him
jest | is
jestem | i am
jeszcze | still
jeśli | if
jeżeli | if
już | already
ją | i
każdy | everyone
kiedy | when
kierunku | direction
kilka | several
kilku | several
kimś | someone
kto | who
ktokolwiek | anyone
ktoś | someone
która | which
które | which
którego | whose
której | which
który | which
których | which
którym | which
którzy | who
ku | to
lat | years
lecz | but
lub | or
ma | has
mają | may
mam | i have
mamy | we have
mało | little
mgr | msc
mi | to me
miał | had
mimo | despite
między | between
mnie | me
mną | me
mogą | they can
moi | my
moim | my
moja | my
moje | my
może | maybe
możliwe | that's possible
można | you can
mu | him
musi | has to
my | we
mój | my
na | on
nad | above
nam | u.s
nami | us
nas | us
nasi | our
nasz | our
nasza | our
nasze | our
naszego | our
naszych | ours
natomiast | whereas
natychmiast | immediately
nawet | even
nic | nothing
nich | them
nie | no
niech | let
niego | him
niej | her
niemu | not him
nigdy | never
nim | him
nimi | them
nią | her
niż | than
no | yeah
nowe | new
np | e.g.
nr | no
o | about
o.o. | o.o.
obok | near
od | from
ok | approx
około | about
on | he
ona | she
one | they
oni | they
ono | it
oraz | and
oto | here
owszem | yes
pan | mr
pana | mr
pani | you
pl | pl
po | after
pod | under
podczas | while
pomimo | despite
ponad | above
ponieważ | because
powinien | should
powinna | she should
powinni | they should
powinno | should
poza | apart from
prawie | almost
prof | prof
przecież | yet
przed | before
przede | above
przedtem | before
przez | by
przy | by
raz | once
razie | case
roku | year
również | also
sam | alone
sama | alone
się | myself
skąd | from where
sobie | myself
sobą | myself
sposób | way
swoje | own
są | are
ta | this
tak | yes
taka | such
taki | such
takich | such
takie | such
także | too
tam | over there
te | these
tego | this
tej | this one
tel | phone
temu | ago
ten | this
teraz | now
też | too
to | this
tobie | you
tobą | you
toteż | this as well
totobą | you
trzeba | it's necessary to
tu | here
tutaj | here
twoi | yours
twoim | yours
twoja | your
twoje | your
twym | your
twój | your
ty | you
tych | these
tylko | just
tym | this
tys | thousand
tzw | so-called
tę | these
u | at
ul | st
vi | vi
vii | vii
viii | viii
vol | vol
w | in
wam | you
wami | you
was | mustache
wasi | yours
wasz | yours
wasza | yours
wasze | yours
we | in
według | according to
wie | knows
wiele | many
wielu | many
więc | so
więcej | more
wszyscy | all
wszystkich | everyone
wszystkie | all
wszystkim | everyone
wszystko | all
wtedy | then
www | www
wy | you
właśnie | exactly
wśród | among
xi | x.x
xii | xii
xiii | xii
xiv | xiv
xv | xv
z | with
za | behind
zapewne | probably
zawsze | always
zaś | and
ze | that
zeznowu | testify
znowu | again
znów | again
został | left
zł | zloty
żaden | no
żadna | none
żadne | none
żadnych | none
że | that
żeby | to
`)
func TokenMapConstructor(config map[string]interface{}, cache *registry.Cache) (analysis.TokenMap, error) {
rv := analysis.NewTokenMap()
err := rv.LoadBytes(PolishStopWords)
return rv, err
}
func init() {
err := registry.RegisterTokenMap(StopName, TokenMapConstructor)
if err != nil {
panic(err)
}
}