Migrate to dep (#3972)
* Update makefile to use dep * Migrate to dep * Fix some deps * Try to find a better version for golang.org/x/net * Try to find a better version for golang.org/x/oauth2
This commit is contained in:
Antoine GIRARD
Lauris BH
parent
d7fd9bf7bb
commit
3f3383dc0a
281 changed files with 12024 additions and 32676 deletions
92
vendor/github.com/blevesearch/segment/README.md
generated
vendored
92
vendor/github.com/blevesearch/segment/README.md
generated
vendored
|
|
@ -1,92 +0,0 @@
|
|||
# segment
|
||||
|
||||
A Go library for performing Unicode Text Segmentation
|
||||
as described in [Unicode Standard Annex #29](http://www.unicode.org/reports/tr29/)
|
||||
|
||||
## Features
|
||||
|
||||
* Currently only segmentation at Word Boundaries is supported.
|
||||
|
||||
## License
|
||||
|
||||
Apache License Version 2.0
|
||||
|
||||
## Usage
|
||||
|
||||
The functionality is exposed in two ways:
|
||||
|
||||
1. You can use a bufio.Scanner with the SplitWords implementation of SplitFunc.
|
||||
The SplitWords function will identify the appropriate word boundaries in the input
|
||||
text and the Scanner will return tokens at the appropriate place.
|
||||
|
||||
scanner := bufio.NewScanner(...)
|
||||
scanner.Split(segment.SplitWords)
|
||||
for scanner.Scan() {
|
||||
tokenBytes := scanner.Bytes()
|
||||
}
|
||||
if err := scanner.Err(); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
|
||||
2. Sometimes you would also like information returned about the type of token.
|
||||
To do this we have introduce a new type named Segmenter. It works just like Scanner
|
||||
but additionally a token type is returned.
|
||||
|
||||
segmenter := segment.NewWordSegmenter(...)
|
||||
for segmenter.Segment() {
|
||||
tokenBytes := segmenter.Bytes())
|
||||
tokenType := segmenter.Type()
|
||||
}
|
||||
if err := segmenter.Err(); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
|
||||
## Choosing Implementation
|
||||
|
||||
By default segment does NOT use the fastest runtime implementation. The reason is that it adds approximately 5s to compilation time and may require more than 1GB of ram on the machine performing compilation.
|
||||
|
||||
However, you can choose to build with the fastest runtime implementation by passing the build tag as follows:
|
||||
|
||||
-tags 'prod'
|
||||
|
||||
## Generating Code
|
||||
|
||||
Several components in this package are generated.
|
||||
|
||||
1. Several Ragel rules files are generated from Unicode properties files.
|
||||
2. Ragel machine is generated from the Ragel rules.
|
||||
3. Test tables are generated from the Unicode test files.
|
||||
|
||||
All of these can be generated by running:
|
||||
|
||||
go generate
|
||||
|
||||
## Fuzzing
|
||||
|
||||
There is support for fuzzing the segment library with [go-fuzz](https://github.com/dvyukov/go-fuzz).
|
||||
|
||||
1. Install go-fuzz if you haven't already:
|
||||
|
||||
go get github.com/dvyukov/go-fuzz/go-fuzz
|
||||
go get github.com/dvyukov/go-fuzz/go-fuzz-build
|
||||
|
||||
2. Build the package with go-fuzz:
|
||||
|
||||
go-fuzz-build github.com/blevesearch/segment
|
||||
|
||||
3. Convert the Unicode provided test cases into the initial corpus for go-fuzz:
|
||||
|
||||
go test -v -run=TestGenerateWordSegmentFuzz -tags gofuzz_generate
|
||||
|
||||
4. Run go-fuzz:
|
||||
|
||||
go-fuzz -bin=segment-fuzz.zip -workdir=workdir
|
||||
|
||||
## Status
|
||||
|
||||
|
||||
[](https://travis-ci.org/blevesearch/segment)
|
||||
|
||||
[](https://coveralls.io/r/blevesearch/segment?branch=master)
|
||||
|
||||
[](https://godoc.org/github.com/blevesearch/segment)
|
||||
285
vendor/github.com/blevesearch/segment/segment_words.rl
generated
vendored
285
vendor/github.com/blevesearch/segment/segment_words.rl
generated
vendored
|
|
@ -1,285 +0,0 @@
|
|||
// 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.
|
||||
|
||||
// +build BUILDTAGS
|
||||
|
||||
package segment
|
||||
|
||||
import (
|
||||
"fmt"
|
||||
"unicode/utf8"
|
||||
)
|
||||
|
||||
var RagelFlags = "RAGELFLAGS"
|
||||
|
||||
var ParseError = fmt.Errorf("unicode word segmentation parse error")
|
||||
|
||||
// Word Types
|
||||
const (
|
||||
None = iota
|
||||
Number
|
||||
Letter
|
||||
Kana
|
||||
Ideo
|
||||
)
|
||||
|
||||
%%{
|
||||
machine s;
|
||||
write data;
|
||||
}%%
|
||||
|
||||
func segmentWords(data []byte, maxTokens int, atEOF bool, val [][]byte, types []int) ([][]byte, []int, int, error) {
|
||||
cs, p, pe := 0, 0, len(data)
|
||||
cap := maxTokens
|
||||
if cap < 0 {
|
||||
cap = 1000
|
||||
}
|
||||
if val == nil {
|
||||
val = make([][]byte, 0, cap)
|
||||
}
|
||||
if types == nil {
|
||||
types = make([]int, 0, cap)
|
||||
}
|
||||
|
||||
// added for scanner
|
||||
ts := 0
|
||||
te := 0
|
||||
act := 0
|
||||
eof := pe
|
||||
_ = ts // compiler not happy
|
||||
_ = te
|
||||
_ = act
|
||||
|
||||
// our state
|
||||
startPos := 0
|
||||
endPos := 0
|
||||
totalConsumed := 0
|
||||
%%{
|
||||
|
||||
include SCRIPTS "ragel/uscript.rl";
|
||||
include WB "ragel/uwb.rl";
|
||||
|
||||
action startToken {
|
||||
startPos = p
|
||||
}
|
||||
|
||||
action endToken {
|
||||
endPos = p
|
||||
}
|
||||
|
||||
action finishNumericToken {
|
||||
if !atEOF {
|
||||
return val, types, totalConsumed, nil
|
||||
}
|
||||
|
||||
val = append(val, data[startPos:endPos+1])
|
||||
types = append(types, Number)
|
||||
totalConsumed = endPos+1
|
||||
if maxTokens > 0 && len(val) >= maxTokens {
|
||||
return val, types, totalConsumed, nil
|
||||
}
|
||||
}
|
||||
|
||||
action finishHangulToken {
|
||||
if endPos+1 == pe && !atEOF {
|
||||
return val, types, totalConsumed, nil
|
||||
} else if dr, size := utf8.DecodeRune(data[endPos+1:]); dr == utf8.RuneError && size == 1 {
|
||||
return val, types, totalConsumed, nil
|
||||
}
|
||||
|
||||
val = append(val, data[startPos:endPos+1])
|
||||
types = append(types, Letter)
|
||||
totalConsumed = endPos+1
|
||||
if maxTokens > 0 && len(val) >= maxTokens {
|
||||
return val, types, totalConsumed, nil
|
||||
}
|
||||
}
|
||||
|
||||
action finishKatakanaToken {
|
||||
if endPos+1 == pe && !atEOF {
|
||||
return val, types, totalConsumed, nil
|
||||
} else if dr, size := utf8.DecodeRune(data[endPos+1:]); dr == utf8.RuneError && size == 1 {
|
||||
return val, types, totalConsumed, nil
|
||||
}
|
||||
|
||||
val = append(val, data[startPos:endPos+1])
|
||||
types = append(types, Ideo)
|
||||
totalConsumed = endPos+1
|
||||
if maxTokens > 0 && len(val) >= maxTokens {
|
||||
return val, types, totalConsumed, nil
|
||||
}
|
||||
}
|
||||
|
||||
action finishWordToken {
|
||||
if !atEOF {
|
||||
return val, types, totalConsumed, nil
|
||||
}
|
||||
val = append(val, data[startPos:endPos+1])
|
||||
types = append(types, Letter)
|
||||
totalConsumed = endPos+1
|
||||
if maxTokens > 0 && len(val) >= maxTokens {
|
||||
return val, types, totalConsumed, nil
|
||||
}
|
||||
}
|
||||
|
||||
action finishHanToken {
|
||||
if endPos+1 == pe && !atEOF {
|
||||
return val, types, totalConsumed, nil
|
||||
} else if dr, size := utf8.DecodeRune(data[endPos+1:]); dr == utf8.RuneError && size == 1 {
|
||||
return val, types, totalConsumed, nil
|
||||
}
|
||||
|
||||
val = append(val, data[startPos:endPos+1])
|
||||
types = append(types, Ideo)
|
||||
totalConsumed = endPos+1
|
||||
if maxTokens > 0 && len(val) >= maxTokens {
|
||||
return val, types, totalConsumed, nil
|
||||
}
|
||||
}
|
||||
|
||||
action finishHiraganaToken {
|
||||
if endPos+1 == pe && !atEOF {
|
||||
return val, types, totalConsumed, nil
|
||||
} else if dr, size := utf8.DecodeRune(data[endPos+1:]); dr == utf8.RuneError && size == 1 {
|
||||
return val, types, totalConsumed, nil
|
||||
}
|
||||
|
||||
val = append(val, data[startPos:endPos+1])
|
||||
types = append(types, Ideo)
|
||||
totalConsumed = endPos+1
|
||||
if maxTokens > 0 && len(val) >= maxTokens {
|
||||
return val, types, totalConsumed, nil
|
||||
}
|
||||
}
|
||||
|
||||
action finishNoneToken {
|
||||
lastPos := startPos
|
||||
for lastPos <= endPos {
|
||||
_, size := utf8.DecodeRune(data[lastPos:])
|
||||
lastPos += size
|
||||
}
|
||||
endPos = lastPos -1
|
||||
p = endPos
|
||||
|
||||
if endPos+1 == pe && !atEOF {
|
||||
return val, types, totalConsumed, nil
|
||||
} else if dr, size := utf8.DecodeRune(data[endPos+1:]); dr == utf8.RuneError && size == 1 {
|
||||
return val, types, totalConsumed, nil
|
||||
}
|
||||
// otherwise, consume this as well
|
||||
val = append(val, data[startPos:endPos+1])
|
||||
types = append(types, None)
|
||||
totalConsumed = endPos+1
|
||||
if maxTokens > 0 && len(val) >= maxTokens {
|
||||
return val, types, totalConsumed, nil
|
||||
}
|
||||
}
|
||||
|
||||
HangulEx = Hangul ( Extend | Format )*;
|
||||
HebrewOrALetterEx = ( Hebrew_Letter | ALetter ) ( Extend | Format )*;
|
||||
NumericEx = Numeric ( Extend | Format )*;
|
||||
KatakanaEx = Katakana ( Extend | Format )*;
|
||||
MidLetterEx = ( MidLetter | MidNumLet | Single_Quote ) ( Extend | Format )*;
|
||||
MidNumericEx = ( MidNum | MidNumLet | Single_Quote ) ( Extend | Format )*;
|
||||
ExtendNumLetEx = ExtendNumLet ( Extend | Format )*;
|
||||
HanEx = Han ( Extend | Format )*;
|
||||
HiraganaEx = Hiragana ( Extend | Format )*;
|
||||
SingleQuoteEx = Single_Quote ( Extend | Format )*;
|
||||
DoubleQuoteEx = Double_Quote ( Extend | Format )*;
|
||||
HebrewLetterEx = Hebrew_Letter ( Extend | Format )*;
|
||||
RegionalIndicatorEx = Regional_Indicator ( Extend | Format )*;
|
||||
NLCRLF = Newline | CR | LF;
|
||||
OtherEx = ^(NLCRLF) ( Extend | Format )* ;
|
||||
|
||||
# UAX#29 WB8. Numeric × Numeric
|
||||
# WB11. Numeric (MidNum | MidNumLet | Single_Quote) × Numeric
|
||||
# WB12. Numeric × (MidNum | MidNumLet | Single_Quote) Numeric
|
||||
# WB13a. (ALetter | Hebrew_Letter | Numeric | Katakana | ExtendNumLet) × ExtendNumLet
|
||||
# WB13b. ExtendNumLet × (ALetter | Hebrew_Letter | Numeric | Katakana)
|
||||
#
|
||||
WordNumeric = ( ( ExtendNumLetEx )* NumericEx ( ( ( ExtendNumLetEx )* | MidNumericEx ) NumericEx )* ( ExtendNumLetEx )* ) >startToken @endToken;
|
||||
|
||||
# subset of the below for typing purposes only!
|
||||
WordHangul = ( HangulEx )+ >startToken @endToken;
|
||||
WordKatakana = ( KatakanaEx )+ >startToken @endToken;
|
||||
|
||||
# UAX#29 WB5. (ALetter | Hebrew_Letter) × (ALetter | Hebrew_Letter)
|
||||
# WB6. (ALetter | Hebrew_Letter) × (MidLetter | MidNumLet | Single_Quote) (ALetter | Hebrew_Letter)
|
||||
# WB7. (ALetter | Hebrew_Letter) (MidLetter | MidNumLet | Single_Quote) × (ALetter | Hebrew_Letter)
|
||||
# WB7a. Hebrew_Letter × Single_Quote
|
||||
# WB7b. Hebrew_Letter × Double_Quote Hebrew_Letter
|
||||
# WB7c. Hebrew_Letter Double_Quote × Hebrew_Letter
|
||||
# WB9. (ALetter | Hebrew_Letter) × Numeric
|
||||
# WB10. Numeric × (ALetter | Hebrew_Letter)
|
||||
# WB13. Katakana × Katakana
|
||||
# WB13a. (ALetter | Hebrew_Letter | Numeric | Katakana | ExtendNumLet) × ExtendNumLet
|
||||
# WB13b. ExtendNumLet × (ALetter | Hebrew_Letter | Numeric | Katakana)
|
||||
#
|
||||
# Marty -deviated here to allow for (ExtendNumLetEx x ExtendNumLetEx) part of 13a
|
||||
#
|
||||
Word = ( ( ExtendNumLetEx )* ( KatakanaEx ( ( ExtendNumLetEx )* KatakanaEx )*
|
||||
| ( HebrewLetterEx ( SingleQuoteEx | DoubleQuoteEx HebrewLetterEx )
|
||||
| NumericEx ( ( ( ExtendNumLetEx )* | MidNumericEx ) NumericEx )*
|
||||
| HebrewOrALetterEx ( ( ( ExtendNumLetEx )* | MidLetterEx ) HebrewOrALetterEx )*
|
||||
|ExtendNumLetEx
|
||||
)+
|
||||
)
|
||||
(
|
||||
( ExtendNumLetEx )+ ( KatakanaEx ( ( ExtendNumLetEx )* KatakanaEx )*
|
||||
| ( HebrewLetterEx ( SingleQuoteEx | DoubleQuoteEx HebrewLetterEx )
|
||||
| NumericEx ( ( ( ExtendNumLetEx )* | MidNumericEx ) NumericEx )*
|
||||
| HebrewOrALetterEx ( ( ( ExtendNumLetEx )* | MidLetterEx ) HebrewOrALetterEx )*
|
||||
)+
|
||||
)
|
||||
)* ExtendNumLetEx*) >startToken @endToken;
|
||||
|
||||
# UAX#29 WB14. Any ÷ Any
|
||||
WordHan = HanEx >startToken @endToken;
|
||||
WordHiragana = HiraganaEx >startToken @endToken;
|
||||
|
||||
WordExt = ( ( Extend | Format )* ) >startToken @endToken; # maybe plus not star
|
||||
|
||||
WordCRLF = (CR LF) >startToken @endToken;
|
||||
|
||||
WordCR = CR >startToken @endToken;
|
||||
|
||||
WordLF = LF >startToken @endToken;
|
||||
|
||||
WordNL = Newline >startToken @endToken;
|
||||
|
||||
WordRegional = (RegionalIndicatorEx+) >startToken @endToken;
|
||||
|
||||
Other = OtherEx >startToken @endToken;
|
||||
|
||||
main := |*
|
||||
WordNumeric => finishNumericToken;
|
||||
WordHangul => finishHangulToken;
|
||||
WordKatakana => finishKatakanaToken;
|
||||
Word => finishWordToken;
|
||||
WordHan => finishHanToken;
|
||||
WordHiragana => finishHiraganaToken;
|
||||
WordRegional =>finishNoneToken;
|
||||
WordCRLF => finishNoneToken;
|
||||
WordCR => finishNoneToken;
|
||||
WordLF => finishNoneToken;
|
||||
WordNL => finishNoneToken;
|
||||
WordExt => finishNoneToken;
|
||||
Other => finishNoneToken;
|
||||
*|;
|
||||
|
||||
write init;
|
||||
write exec;
|
||||
}%%
|
||||
|
||||
if cs < s_first_final {
|
||||
return val, types, totalConsumed, ParseError
|
||||
}
|
||||
|
||||
return val, types, totalConsumed, nil
|
||||
}
|
||||
Loading…
Add table
Add a link
Reference in a new issue