pinyin

README

go-pinyin

汉语拼音转换工具 Go 版。

Installation

go get -u github.com/mozillazg/go-pinyin

install CLI tool:

go get -u github.com/mozillazg/go-pinyin/cmd/pinyin
$ pinyin 中国人
zhōng guó rén

Documentation

API documentation can be found here: https://godoc.org/github.com/mozillazg/go-pinyin

Usage

package main

import (
	"fmt"
	"github.com/mozillazg/go-pinyin"
)

func main() {
	hans := "中国人"

	// 默认
	a := pinyin.NewArgs()
	fmt.Println(pinyin.Pinyin(hans, a))
	// [[zhong] [guo] [ren]]

	// 包含声调
	a.Style = pinyin.Tone
	fmt.Println(pinyin.Pinyin(hans, a))
	// [[zhōng] [guó] [rén]]

	// 声调用数字表示
	a.Style = pinyin.Tone2
	fmt.Println(pinyin.Pinyin(hans, a))
	// [[zho1ng] [guo2] [re2n]]

	// 开启多音字模式
	a = pinyin.NewArgs()
	a.Heteronym = true
	fmt.Println(pinyin.Pinyin(hans, a))
	// [[zhong zhong] [guo] [ren]]
	a.Style = pinyin.Tone2
	fmt.Println(pinyin.Pinyin(hans, a))
	// [[zho1ng zho4ng] [guo2] [re2n]]

	fmt.Println(pinyin.LazyPinyin(hans, pinyin.NewArgs()))
	// [zhong guo ren]

	fmt.Println(pinyin.Convert(hans, nil))
	// [[zhong] [guo] [ren]]

	fmt.Println(pinyin.LazyConvert(hans, nil))
	// [zhong guo ren]

	// 段落转换，支持完整支持多音字，保留符号
	fmt.Println(pinyin.Paragraph("交给团长，告诉他我们给予期望。前线的供给一定要能自给自足！"))
	// jiao gei tuan zhang, gao su ta wo men ji yu qi wang. qian xian de gong ji yi ding yao neng zi ji zi zu!
}

Related Projects

• hotoo/pinyin: 汉语拼音转换工具 Node.js/JavaScript 版。
• mozillazg/python-pinyin: 汉语拼音转换工具 Python 版。
• mozillazg/rust-pinyin: 汉语拼音转换工具 Rust 版。

pinyin data

• 使用 pinyin-data 的拼音数据

License

Under the MIT License.

Documentation

Overview

Package pinyin : 汉语拼音转换工具.

Usage

package main

import (
	"fmt"
	"github.com/mozillazg/go-pinyin"
)

func main() {
	hans := "中国人"
	// 默认
	a := pinyin.NewArgs()
	fmt.Println(pinyin.Pinyin(hans, a))
	// [[zhong] [guo] [ren]]

	// 包含声调
	a.Style = pinyin.Tone
	fmt.Println(pinyin.Pinyin(hans, a))
	// [[zhōng] [guó] [rén]]

	// 声调用数字表示
	a.Style = pinyin.Tone2
	fmt.Println(pinyin.Pinyin(hans, a))
	// [[zho1ng] [guo2] [re2n]]

	// 开启多音字模式
	a = pinyin.NewArgs()
	a.Heteronym = true
	fmt.Println(pinyin.Pinyin(hans, a))
	// [[zhong zhong] [guo] [ren]]
	a.Style = pinyin.Tone2
	fmt.Println(pinyin.Pinyin(hans, a))
	// [[zho1ng zho4ng] [guo2] [re2n]]
}

Index

• Constants
• Variables
• func Convert(s string, a *Args) [][]string
• func LazyConvert(s string, a *Args) []string
• func LazyPinyin(s string, a Args) []string
• func Paragraph(p string) (s string)
• func Pinyin(s string, a Args) [][]string
• func SinglePinyin(r rune, a Args) []string
• func Slug(s string, a Args) string
• type Args
  • func NewArgs() Args

Examples

• Convert
• LazyPinyin
• Paragraph
• Pinyin (Default)
• Pinyin (FallbackCustom1)
• Pinyin (FallbackCustom2)
• Pinyin (Finals)
• Pinyin (FinalsTone)
• Pinyin (FinalsTone2)
• Pinyin (FirstLetter)
• Pinyin (Heteronym)
• Pinyin (Initials)
• Pinyin (Normal)
• Pinyin (Tone)
• Pinyin (Tone2)
• Slug

Constants

const (
	Version   = "0.16.0"
	Author    = "mozillazg, 闲耘"
	License   = "MIT"
	Copyright = "Copyright (c) 2016 mozillazg, 闲耘"
)

Meta

const (
	Normal      = 0 // 普通风格，不带声调（默认风格）。如： zhong guo
	Tone        = 1 // 声调风格1，拼音声调在韵母第一个字母上。如： zhōng guó
	Tone2       = 2 // 声调风格2，即拼音声调在各个韵母之后，用数字 [1-4] 进行表示。如： zho1ng guo2
	Tone3       = 8 // 声调风格3，即拼音声调在各个拼音之后，用数字 [1-4] 进行表示。如： zhong1 guo2
	Initials    = 3 // 声母风格，只返回各个拼音的声母部分。如： zh g
	FirstLetter = 4 // 首字母风格，只返回拼音的首字母部分。如： z g
	Finals      = 5 // 韵母风格，只返回各个拼音的韵母部分，不带声调。如： ong uo
	FinalsTone  = 6 // 韵母风格1，带声调，声调在韵母第一个字母上。如： ōng uó
	FinalsTone2 = 7 // 韵母风格2，带声调，声调在各个韵母之后，用数字 [1-4] 进行表示。如： o1ng uo2
	FinalsTone3 = 9 // 韵母风格3，带声调，声调在各个拼音之后，用数字 [1-4] 进行表示。如： ong1 uo2
)

拼音风格(推荐)

const (
	NORMAL       = Normal
	TONE         = Tone
	TONE2        = Tone2
	INITIALS     = Initials
	FIRST_LETTER = FirstLetter
	FINALS       = Finals
	FINALS_TONE  = FinalsTone
	FINALS_TONE2 = FinalsTone2
)

拼音风格(兼容之前的版本)

Variables

var Fallback = func(r rune, a Args) []string {
	return []string{}
}

Fallback 默认配置: 如何处理没有拼音的字符(忽略这个字符)

var Heteronym = false

Heteronym 默认配置：是否启用多音字模式

var PinyinDict = map[int]string{}/* 41451 elements not displayed */

PinyinDict is data map Warning: Auto-generated file, don't edit.

var Separator = "-"

Separator 默认配置： `Slug` 中 Join 所用的分隔符

var Style = Normal

Style 默认配置：风格

Functions

func Convert

func Convert(s string, a *Args) [][]string

Convert 跟 Pinyin 的唯一区别就是 a 参数可以是 nil

Example

hans := "中国人"
fmt.Println("default:", pinyin.Convert(hans, nil))

Output:

default: [[zhong] [guo] [ren]]

func LazyConvert

func LazyConvert(s string, a *Args) []string

LazyConvert 跟 LazyPinyin 的唯一区别就是 a 参数可以是 nil

func LazyPinyin

func LazyPinyin(s string, a Args) []string

LazyPinyin 汉字转拼音，与 `Pinyin` 的区别是： 返回值类型不同，并且不支持多音字模式，每个汉字只取第一个音.

Example

hans := "中国人"
a := pinyin.NewArgs()
fmt.Println(pinyin.LazyPinyin(hans, a))

Output:

[zhong guo ren]

func Paragraph

func Paragraph(p string) (s string)

Paragraph convert a Chinese paragraph into pinyin, including letters, numbers, symbols

Example

hans := "人民银行旁边一行人abc字母【路牌】，平行宇宙发行股票。"
fmt.Println(pinyin.Paragraph(hans))

Output:

ren min yin xing pang bian yi xing ren abc zi mu [lu pai], ping xing yu zhou fa xing gu piao.

func Pinyin

func Pinyin(s string, a Args) [][]string

Pinyin 汉字转拼音，支持多音字模式.

Example (Default)

hans := "中国人"
a := pinyin.NewArgs()
fmt.Println("default:", pinyin.Pinyin(hans, a))

Output:

default: [[zhong] [guo] [ren]]

Example (FallbackCustom1)

hans := "中国人abc"
a := pinyin.NewArgs()
a.Fallback = func(r rune, a pinyin.Args) []string {
	return []string{string(r + 1)}
}
fmt.Println(pinyin.Pinyin(hans, a))

Output:

[[zhong] [guo] [ren] [b] [c] [d]]

Example (FallbackCustom2)

hans := "中国人アイウ"
a := pinyin.NewArgs()
a.Fallback = func(r rune, a pinyin.Args) []string {
	data := map[rune][]string{
		'ア': {"a"},
		'イ': {"i"},
		'ウ': {"u"},
	}
	s, ok := data[r]
	if ok {
		return s
	} else {
		return []string{}
	}
}
fmt.Println(pinyin.Pinyin(hans, a))

Output:

[[zhong] [guo] [ren] [a] [i] [u]]

Example (Finals)

hans := "中国人"
a := pinyin.NewArgs()
a.Style = pinyin.Finals
fmt.Println(pinyin.Pinyin(hans, a))

Output:

[[ong] [uo] [en]]

Example (FinalsTone)

hans := "中国人"
a := pinyin.NewArgs()
a.Style = pinyin.FinalsTone
fmt.Println(pinyin.Pinyin(hans, a))

Output:

[[ōng] [uó] [én]]

Example (FinalsTone2)

hans := "中国人"
a := pinyin.NewArgs()
a.Style = pinyin.FinalsTone2
fmt.Println(pinyin.Pinyin(hans, a))

Output:

[[o1ng] [uo2] [e2n]]

Example (FirstLetter)

hans := "中国人"
a := pinyin.NewArgs()
a.Style = pinyin.FirstLetter
fmt.Println(pinyin.Pinyin(hans, a))

Output:

[[z] [g] [r]]

Example (Heteronym)

hans := "中国人"
a := pinyin.NewArgs()
a.Heteronym = true
a.Style = pinyin.Tone2
fmt.Println(pinyin.Pinyin(hans, a))

Output:

[[zho1ng zho4ng] [guo2] [re2n]]

Example (Initials)

hans := "中国人"
a := pinyin.NewArgs()
a.Style = pinyin.Initials
fmt.Println("Initials:", pinyin.Pinyin(hans, a))

Output:

Initials: [[zh] [g] [r]]

Example (Normal)

hans := "中国人"
a := pinyin.NewArgs()
a.Style = pinyin.Normal
fmt.Println("Normal:", pinyin.Pinyin(hans, a))

Output:

Normal: [[zhong] [guo] [ren]]

Example (Tone)

hans := "中国人"
a := pinyin.NewArgs()
a.Style = pinyin.Tone
fmt.Println("Tone:", pinyin.Pinyin(hans, a))

Output:

Tone: [[zhōng] [guó] [rén]]

Example (Tone2)

hans := "中国人"
a := pinyin.NewArgs()
a.Style = pinyin.Tone2
fmt.Println("Tone2:", pinyin.Pinyin(hans, a))

Output:

Tone2: [[zho1ng] [guo2] [re2n]]

func SinglePinyin

func SinglePinyin(r rune, a Args) []string

SinglePinyin 把单个 `rune` 类型的汉字转换为拼音.

func Slug

func Slug(s string, a Args) string

Slug join `LazyPinyin` 的返回值. 建议改用 https://github.com/mozillazg/go-slugify

Example

hans := "中国人"
a := pinyin.NewArgs()
fmt.Println(pinyin.Slug(hans, a))

Output:

zhong-guo-ren

Types

type Args

type Args struct {
	Style     int    // 拼音风格（默认： Normal)
	Heteronym bool   // 是否启用多音字模式（默认：禁用）
	Separator string // Slug 中使用的分隔符（默认：-)

	// 处理没有拼音的字符（默认忽略没有拼音的字符）
	// 函数返回的 slice 的长度为0 则表示忽略这个字符
	Fallback func(r rune, a Args) []string
}

Args 配置信息

func NewArgs

func NewArgs() Args

NewArgs 返回包含默认配置的 `Args`