Initial commit

Author: suguru

.travis.yml

@@ -0,0 +1,23 @@
+language: go
+
+go:
+  - 1.4.1
+
+before_install:
+  - sudo pip install codecov
+
+install:
+  - go get golang.org/x/tools/cmd/vet
+  - go get golang.org/x/tools/cmd/cover
+  - go get github.com/golang/lint/golint
+
+before_script:
+  - go get ./...
+  - go vet ./...
+  - golint ./... | xargs -r false
+
+script:
+  - go test -v -coverprofile=coverage.txt -covermode=count
+
+after_success:
+  - codecov

LICENSE

@@ -0,0 +1,5 @@
+Copyright (c) 2015, Suguru Namura
+
+Permission to use, copy, modify, and/or distribute this software for any purpose with or without fee is hereby granted, provided that the above copyright notice and this permission notice appear in all copies.
+
+THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.

LICENSE.tinysegmenter

@@ -0,0 +1,5 @@
+TinySegmenter 0.1 -- Super compact Japanese tokenizer in Javascript
+(c) 2008 Taku Kudo <[email protected]>
+TinySegmenter is freely distributable under the terms of a new BSD licence.
+For details, see http://chasen.org/~taku/software/TinySegmenter/LICENCE.txt
+

README.md

@@ -0,0 +1,56 @@
+NihonGo is japanese utility for Golang
+====
+
+[![Build Status](http://img.shields.io/travis/dogenzaka/nihongo.svg?style=flat)](https://travis-ci.org/dogenzaka/nihongo)
+[![Coverage](http://img.shields.io/codecov/c/github/dogenzaka/nihongo.svg?style=flat)](https://codecov.io/github/dogenzaka/nihongo)
+[![License](http://img.shields.io/badge/license-MIT-red.svg?style=flat)](https://github.com/dogenzaka/nihongo/blob/master/LICENSE)
+
+NihonGo is japanese utility on Go.
+
+```
+go get github.com/dogenzaka/nihongo
+```
+
+Featuers
+--
+
+- Katakana / Hiragana conversion
+- Unicode normalization
+- Detect katakana / hiragana string
+- Simple tokenizer ported TinySegmenter
+
+Examples
+--
+
+```go
+import (
+  "fmt"
+  "github.com/dogenzaka/nihongo"
+)
+
+func TestNormalize() {
+  normalized := nihongo.Normalize("テストﾃｽﾄ＋＝")
+  fmt.Println(normalized) // テストテスト+=
+}
+
+func TestToHiragana() {
+  hira := nihongo.ToHiragana("テストてすと")
+  fmt.Println(hira) // てすとてすと
+}
+
+func TestToKatakana() {
+  kana := nihongo.ToKatakana("テストてすと")
+  fmt.Println(kana) // テストテスト
+}
+
+func TestTokenize() {
+  words := nihongo.Tokenize("私は人間です")
+  fmt.Println(words) // ["私" "は" "人間" "です"]
+}
+
+```
+
+License
+--
+ISC
+

nihong_test.go

@@ -0,0 +1,65 @@
+package nihongo
+
+import (
+	"testing"
+)
+
+func TestNormalize(t *testing.T) {
+
+	norm := Normalize("テストてすと")
+	if norm != "テストてすと" {
+		t.Errorf("Converted strings which should not be converted %v", norm)
+	}
+
+	norm = Normalize("テストﾃｽﾄ／＋")
+	if norm != "テストテスト/+" {
+		t.Errorf("Converted strings which should not be converted %v", norm)
+	}
+
+}
+
+func TestToHiragana(t *testing.T) {
+
+	hira := ToHiragana("テスト")
+	if hira != "てすと" {
+		t.Errorf("Not converted to Hiragana %v", hira)
+	}
+
+	hira = ToHiragana("テスト混合てすと")
+	if hira != "てすと混合てすと" {
+		t.Errorf("Not converted to Hiragana %v", hira)
+	}
+
+	hira = ToHiragana("Englishテスト混合")
+	if hira != "Englishてすと混合" {
+		t.Errorf("Not converted to Hiragana %v", hira)
+	}
+
+	hira = ToHiragana("アイウエオカキクケコサシスセソタチツテトナニヌネノハヒフヘホマミムメモヤユヨラリルレロワヲンガギグゲゴザジズゼゾダヂヅデドバビブベボパピプペポ")
+	if hira != "あいうえおかきくけこさしすせそたちつてとなにぬねのはひふへほまみむめもやゆよらりるれろわをんがぎぐげござじずぜぞだぢづでどばびぶべぼぱぴぷぺぽ" {
+		t.Errorf("Not converted to Hiragana %v", hira)
+	}
+}
+
+func TestToKatakana(t *testing.T) {
+
+	kana := ToKatakana("てすと")
+	if kana != "テスト" {
+		t.Errorf("Not converted to Katakana %v", kana)
+	}
+
+	kana = ToKatakana("てすと混合テスト")
+	if kana != "テスト混合テスト" {
+		t.Errorf("Not converted to Katakana %v", kana)
+	}
+
+	kana = ToKatakana("てすと混合English")
+	if kana != "テスト混合English" {
+		t.Errorf("Not converted to Katakana %v", kana)
+	}
+
+	kana = ToKatakana("あいうえおかきくけこさしすせそたちつてとなにぬねのはひふへほまみむめもやゆよらりるれろわをんがぎぐげござじずぜぞだぢづでどばびぶべぼぱぴぷぺぽ")
+	if kana != "アイウエオカキクケコサシスセソタチツテトナニヌネノハヒフヘホマミムメモヤユヨラリルレロワヲンガギグゲゴザジズゼゾダヂヅデドバビブベボパピプペポ" {
+		t.Errorf("Not converted to Katakana %v", kana)
+	}
+}

nihongo.go

@@ -0,0 +1,63 @@
+package nihongo
+
+import (
+	"bytes"
+	"golang.org/x/text/unicode/norm"
+	"unicode"
+)
+
+// Normalize japanese text which will convert with NFKC normalization.
+// Hankaku-Kana -> Zenkaku-Kana
+// Zenkaku special chars -> Hankaku special chars
+func Normalize(text string) string {
+	return norm.NFKC.String(text)
+}
+
+// ContainsHiragana returns true when text contains hiragana
+func ContainsHiragana(text string) bool {
+	for _, r := range text {
+		if unicode.In(r, unicode.Hiragana) {
+			return true
+		}
+	}
+	return false
+}
+
+// ContainsKatakana returns true when text contains katakana
+func ContainsKatakana(text string) bool {
+	for _, r := range text {
+		if unicode.In(r, unicode.Katakana) {
+			return true
+		}
+	}
+	return false
+}
+
+// ToHiragana converts all katakana text to hiragana.
+// You should normalize text before converting.
+func ToHiragana(text string) string {
+	var buf bytes.Buffer
+	for _, r := range text {
+		if unicode.In(r, unicode.Katakana) {
+			// Convert to hiragana
+			r -= 0x60
+		}
+		buf.WriteRune(r)
+	}
+	return buf.String()
+}
+
+// ToKatakana converts all hiragana text to katakana.
+// You should normalize text before converting.
+func ToKatakana(text string) string {
+	var buf bytes.Buffer
+	//buf := bytes.NewBuffer(make([]byte, len(text)))
+	for _, r := range text {
+		if unicode.In(r, unicode.Hiragana) {
+			// Convert to hiragana
+			r += 0x60
+		}
+		buf.WriteRune(r)
+	}
+	return buf.String()
+}