Switch from Godep to go vendoring

vendor/github.com/blevesearch/bleve/analysis/language/en/analyzer_en.go

@@ -0,0 +1,58 @@
+//  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 en
+
+import (
+	"github.com/blevesearch/bleve/analysis"
+	"github.com/blevesearch/bleve/registry"
+
+	"github.com/blevesearch/bleve/analysis/token_filters/lower_case_filter"
+	"github.com/blevesearch/bleve/analysis/token_filters/porter"
+	"github.com/blevesearch/bleve/analysis/tokenizers/unicode"
+)
+
+const AnalyzerName = "en"
+
+func AnalyzerConstructor(config map[string]interface{}, cache *registry.Cache) (*analysis.Analyzer, error) {
+	tokenizer, err := cache.TokenizerNamed(unicode.Name)
+	if err != nil {
+		return nil, err
+	}
+	possEnFilter, err := cache.TokenFilterNamed(PossessiveName)
+	if err != nil {
+		return nil, err
+	}
+	toLowerFilter, err := cache.TokenFilterNamed(lower_case_filter.Name)
+	if err != nil {
+		return nil, err
+	}
+	stopEnFilter, err := cache.TokenFilterNamed(StopName)
+	if err != nil {
+		return nil, err
+	}
+	stemmerEnFilter, err := cache.TokenFilterNamed(porter.Name)
+	if err != nil {
+		return nil, err
+	}
+	rv := analysis.Analyzer{
+		Tokenizer: tokenizer,
+		TokenFilters: []analysis.TokenFilter{
+			possEnFilter,
+			toLowerFilter,
+			stopEnFilter,
+			stemmerEnFilter,
+		},
+	}
+	return &rv, nil
+}
+
+func init() {
+	registry.RegisterAnalyzer(AnalyzerName, AnalyzerConstructor)
+}

vendor/github.com/blevesearch/bleve/analysis/language/en/analyzer_en_test.go

@@ -0,0 +1,100 @@
+//  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 en
+
+import (
+	"reflect"
+	"testing"
+
+	"github.com/blevesearch/bleve/analysis"
+	"github.com/blevesearch/bleve/registry"
+)
+
+func TestEnglishAnalyzer(t *testing.T) {
+	tests := []struct {
+		input  []byte
+		output analysis.TokenStream
+	}{
+		// stemming
+		{
+			input: []byte("books"),
+			output: analysis.TokenStream{
+				&analysis.Token{
+					Term:     []byte("book"),
+					Position: 1,
+					Start:    0,
+					End:      5,
+				},
+			},
+		},
+		{
+			input: []byte("book"),
+			output: analysis.TokenStream{
+				&analysis.Token{
+					Term:     []byte("book"),
+					Position: 1,
+					Start:    0,
+					End:      4,
+				},
+			},
+		},
+		// stop word removal
+		{
+			input:  []byte("the"),
+			output: analysis.TokenStream{},
+		},
+		// possessive removal
+		{
+			input: []byte("steven's"),
+			output: analysis.TokenStream{
+				&analysis.Token{
+					Term:     []byte("steven"),
+					Position: 1,
+					Start:    0,
+					End:      8,
+				},
+			},
+		},
+		{
+			input: []byte("steven\u2019s"),
+			output: analysis.TokenStream{
+				&analysis.Token{
+					Term:     []byte("steven"),
+					Position: 1,
+					Start:    0,
+					End:      10,
+				},
+			},
+		},
+		{
+			input: []byte("steven\uFF07s"),
+			output: analysis.TokenStream{
+				&analysis.Token{
+					Term:     []byte("steven"),
+					Position: 1,
+					Start:    0,
+					End:      10,
+				},
+			},
+		},
+	}
+
+	cache := registry.NewCache()
+	analyzer, err := cache.AnalyzerNamed(AnalyzerName)
+	if err != nil {
+		t.Fatal(err)
+	}
+	for _, test := range tests {
+		actual := analyzer.Analyze(test.input)
+		if !reflect.DeepEqual(actual, test.output) {
+			t.Errorf("expected %v, got %v", test.output, actual)
+		}
+	}
+}

vendor/github.com/blevesearch/bleve/analysis/language/en/possessive_filter_en.go

@@ -0,0 +1,57 @@
+//  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 en
+
+import (
+	"bytes"
+
+	"github.com/blevesearch/bleve/analysis"
+	"github.com/blevesearch/bleve/registry"
+)
+
+const PossessiveName = "possessive_en"
+
+const rightSingleQuotationMark = '’'
+const apostrophe = '\''
+const fullWidthApostrophe = '＇'
+
+const apostropheChars = rightSingleQuotationMark + apostrophe + fullWidthApostrophe
+
+type PossessiveFilter struct {
+}
+
+func NewPossessiveFilter() *PossessiveFilter {
+	return &PossessiveFilter{}
+}
+
+func (s *PossessiveFilter) Filter(input analysis.TokenStream) analysis.TokenStream {
+	for _, token := range input {
+		runes := bytes.Runes(token.Term)
+		if len(runes) >= 2 {
+			secondToLastRune := runes[len(runes)-2]
+			lastRune := runes[len(runes)-1]
+			if (secondToLastRune == rightSingleQuotationMark ||
+				secondToLastRune == apostrophe ||
+				secondToLastRune == fullWidthApostrophe) &&
+				(lastRune == 's' || lastRune == 'S') {
+				token.Term = analysis.TruncateRunes(token.Term, 2)
+			}
+		}
+	}
+	return input
+}
+
+func PossessiveFilterConstructor(config map[string]interface{}, cache *registry.Cache) (analysis.TokenFilter, error) {
+	return NewPossessiveFilter(), nil
+}
+
+func init() {
+	registry.RegisterTokenFilter(PossessiveName, PossessiveFilterConstructor)
+}

vendor/github.com/blevesearch/bleve/analysis/language/en/possessive_filter_en_test.go

@@ -0,0 +1,86 @@
+//  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 en
+
+import (
+	"reflect"
+	"testing"
+
+	"github.com/blevesearch/bleve/analysis"
+	"github.com/blevesearch/bleve/registry"
+)
+
+func TestEnglishPossessiveFilter(t *testing.T) {
+	tests := []struct {
+		input  analysis.TokenStream
+		output analysis.TokenStream
+	}{
+		{
+			input: analysis.TokenStream{
+				&analysis.Token{
+					Term: []byte("marty's"),
+				},
+				&analysis.Token{
+					Term: []byte("MARTY'S"),
+				},
+				&analysis.Token{
+					Term: []byte("marty’s"),
+				},
+				&analysis.Token{
+					Term: []byte("MARTY’S"),
+				},
+				&analysis.Token{
+					Term: []byte("marty＇s"),
+				},
+				&analysis.Token{
+					Term: []byte("MARTY＇S"),
+				},
+				&analysis.Token{
+					Term: []byte("m"),
+				},
+			},
+			output: analysis.TokenStream{
+				&analysis.Token{
+					Term: []byte("marty"),
+				},
+				&analysis.Token{
+					Term: []byte("MARTY"),
+				},
+				&analysis.Token{
+					Term: []byte("marty"),
+				},
+				&analysis.Token{
+					Term: []byte("MARTY"),
+				},
+				&analysis.Token{
+					Term: []byte("marty"),
+				},
+				&analysis.Token{
+					Term: []byte("MARTY"),
+				},
+				&analysis.Token{
+					Term: []byte("m"),
+				},
+			},
+		},
+	}
+
+	cache := registry.NewCache()
+	stemmerFilter, err := cache.TokenFilterNamed(PossessiveName)
+	if err != nil {
+		t.Fatal(err)
+	}
+	for _, test := range tests {
+		actual := stemmerFilter.Filter(test.input)
+		if !reflect.DeepEqual(actual, test.output) {
+			t.Errorf("expected %s, got %s", test.output, actual)
+		}
+	}
+}

vendor/github.com/blevesearch/bleve/analysis/language/en/stemmer_en.go

@@ -0,0 +1,28 @@
+//  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.
+
+// +build libstemmer full
+
+package en
+
+import (
+	"github.com/blevesearch/bleve/analysis"
+	"github.com/blevesearch/bleve/analysis/token_filters/stemmer_filter"
+	"github.com/blevesearch/bleve/registry"
+)
+
+const StemmerName = "stemmer_en"
+
+func StemmerFilterConstructor(config map[string]interface{}, cache *registry.Cache) (analysis.TokenFilter, error) {
+	return stemmer_filter.NewStemmerFilter("en")
+}
+
+func init() {
+	registry.RegisterTokenFilter(StemmerName, StemmerFilterConstructor)
+}

vendor/github.com/blevesearch/bleve/analysis/language/en/stemmer_en_test.go

@@ -0,0 +1,72 @@
+//  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.
+
+// +build libstemmer full
+
+package en
+
+import (
+	"reflect"
+	"testing"
+
+	"github.com/blevesearch/bleve/analysis"
+	"github.com/blevesearch/bleve/registry"
+)
+
+func TestEnglishStemmer(t *testing.T) {
+	tests := []struct {
+		input  analysis.TokenStream
+		output analysis.TokenStream
+	}{
+		{
+			input: analysis.TokenStream{
+				&analysis.Token{
+					Term: []byte("walking"),
+				},
+				&analysis.Token{
+					Term: []byte("talked"),
+				},
+				&analysis.Token{
+					Term: []byte("business"),
+				},
+				&analysis.Token{
+					Term:    []byte("protected"),
+					KeyWord: true,
+				},
+			},
+			output: analysis.TokenStream{
+				&analysis.Token{
+					Term: []byte("walk"),
+				},
+				&analysis.Token{
+					Term: []byte("talk"),
+				},
+				&analysis.Token{
+					Term: []byte("busi"),
+				},
+				&analysis.Token{
+					Term:    []byte("protected"),
+					KeyWord: true,
+				},
+			},
+		},
+	}
+
+	cache := registry.NewCache()
+	stemmerFilter, err := cache.TokenFilterNamed(StemmerName)
+	if err != nil {
+		t.Fatal(err)
+	}
+	for _, test := range tests {
+		actual := stemmerFilter.Filter(test.input)
+		if !reflect.DeepEqual(actual, test.output) {
+			t.Errorf("expected %s, got %s", test.output, actual)
+		}
+	}
+}

vendor/github.com/blevesearch/bleve/analysis/language/en/stop_filter_en.go

@@ -0,0 +1,28 @@
+//  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 en
+
+import (
+	"github.com/blevesearch/bleve/analysis"
+	"github.com/blevesearch/bleve/analysis/token_filters/stop_tokens_filter"
+	"github.com/blevesearch/bleve/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_tokens_filter.NewStopTokensFilter(tokenMap), nil
+}
+
+func init() {
+	registry.RegisterTokenFilter(StopName, StopTokenFilterConstructor)
+}

vendor/github.com/blevesearch/bleve/analysis/language/en/stop_words_en.go

@@ -0,0 +1,343 @@
+package en
+
+import (
+	"github.com/blevesearch/bleve/analysis"
+	"github.com/blevesearch/bleve/registry"
+)
+
+const StopName = "stop_en"
+
+// 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 EnglishStopWords = []byte(` | From svn.tartarus.org/snowball/trunk/website/algorithms/english/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"
+ 
+ | An English stop word list. Comments begin with vertical bar. Each stop
+ | word is at the start of a line.
+
+ | Many of the forms below are quite rare (e.g. "yourselves") but included for
+ |  completeness.
+
+           | PRONOUNS FORMS
+             | 1st person sing
+
+i              | subject, always in upper case of course
+
+me             | object
+my             | possessive adjective
+               | the possessive pronoun 'mine' is best suppressed, because of the
+               | sense of coal-mine etc.
+myself         | reflexive
+             | 1st person plural
+we             | subject
+
+| us           | object
+               | care is required here because US = United States. It is usually
+               | safe to remove it if it is in lower case.
+our            | possessive adjective
+ours           | possessive pronoun
+ourselves      | reflexive
+             | second person (archaic 'thou' forms not included)
+you            | subject and object
+your           | possessive adjective
+yours          | possessive pronoun
+yourself       | reflexive (singular)
+yourselves     | reflexive (plural)
+             | third person singular
+he             | subject
+him            | object
+his            | possessive adjective and pronoun
+himself        | reflexive
+
+she            | subject
+her            | object and possessive adjective
+hers           | possessive pronoun
+herself        | reflexive
+
+it             | subject and object
+its            | possessive adjective
+itself         | reflexive
+             | third person plural
+they           | subject
+them           | object
+their          | possessive adjective
+theirs         | possessive pronoun
+themselves     | reflexive
+             | other forms (demonstratives, interrogatives)
+what
+which
+who
+whom
+this
+that
+these
+those
+
+           | VERB FORMS (using F.R. Palmer's nomenclature)
+             | BE
+am             | 1st person, present
+is             | -s form (3rd person, present)
+are            | present
+was            | 1st person, past
+were           | past
+be             | infinitive
+been           | past participle
+being          | -ing form
+             | HAVE
+have           | simple
+has            | -s form
+had            | past
+having         | -ing form
+             | DO
+do             | simple
+does           | -s form
+did            | past
+doing          | -ing form
+
+ | The forms below are, I believe, best omitted, because of the significant
+ | homonym forms:
+
+ |  He made a WILL
+ |  old tin CAN
+ |  merry month of MAY
+ |  a smell of MUST
+ |  fight the good fight with all thy MIGHT
+
+ | would, could, should, ought might however be included
+
+ |          | AUXILIARIES
+ |            | WILL
+ |will
+
+would
+
+ |            | SHALL
+ |shall
+
+should
+
+ |            | CAN
+ |can
+
+could
+
+ |            | MAY
+ |may
+ |might
+ |            | MUST
+ |must
+ |            | OUGHT
+
+ought
+
+           | COMPOUND FORMS, increasingly encountered nowadays in 'formal' writing
+              | pronoun + verb
+
+i'm
+you're
+he's
+she's
+it's
+we're
+they're
+i've
+you've
+we've
+they've
+i'd
+you'd
+he'd
+she'd
+we'd
+they'd
+i'll
+you'll
+he'll
+she'll
+we'll
+they'll
+
+              | verb + negation
+
+isn't
+aren't
+wasn't
+weren't
+hasn't
+haven't
+hadn't
+doesn't
+don't
+didn't
+
+              | auxiliary + negation
+
+won't
+wouldn't
+shan't
+shouldn't
+can't
+cannot
+couldn't
+mustn't
+
+             | miscellaneous forms
+
+let's
+that's
+who's
+what's
+here's
+there's
+when's
+where's
+why's
+how's
+
+              | rarer forms
+
+ | daren't needn't
+
+              | doubtful forms
+
+ | oughtn't mightn't
+
+           | ARTICLES
+a
+an
+the
+
+           | THE REST (Overlap among prepositions, conjunctions, adverbs etc is so
+           | high, that classification is pointless.)
+and
+but
+if
+or
+because
+as
+until
+while
+
+of
+at
+by
+for
+with
+about
+against
+between
+into
+through
+during
+before
+after
+above
+below
+to
+from
+up
+down
+in
+out
+on
+off
+over
+under
+
+again
+further
+then
+once
+
+here
+there
+when
+where
+why
+how
+
+all
+any
+both
+each
+few
+more
+most
+other
+some
+such
+
+no
+nor
+not
+only
+own
+same
+so
+than
+too
+very
+
+ | Just for the record, the following words are among the commonest in English
+
+    | one
+    | every
+    | least
+    | less
+    | many
+    | now
+    | ever
+    | never
+    | say
+    | says
+    | said
+    | also
+    | get
+    | go
+    | goes
+    | just
+    | made
+    | make
+    | put
+    | see
+    | seen
+    | whether
+    | like
+    | well
+    | back
+    | even
+    | still
+    | way
+    | take
+    | since
+    | another
+    | however
+    | two
+    | three
+    | four
+    | five
+    | first
+    | second
+    | new
+    | old
+    | high
+    | long
+`)
+
+func TokenMapConstructor(config map[string]interface{}, cache *registry.Cache) (analysis.TokenMap, error) {
+	rv := analysis.NewTokenMap()
+	err := rv.LoadBytes(EnglishStopWords)
+	return rv, err
+}
+
+func init() {
+	registry.RegisterTokenMap(StopName, TokenMapConstructor)
+}