pinyin - npm Package Compare versions

Comparing version 3.0.0-alpha.0 to 3.0.0-alpha.1

lib/declare.d.ts

 import { ENUM_PINYIN_STYLE, ENUM_PINYIN_MODE } from "./constant";
+export interface IPinyin {
+    (han: string, options?: IPinyinOptions): string[][];
+    compare: (a: string, b: string) => number;
+    compact: (arr: string[][]) => string[][];
+    STYLE_TONE: ENUM_PINYIN_STYLE;
+    STYLE_TONE2: ENUM_PINYIN_STYLE;
+    STYLE_TO3NE: ENUM_PINYIN_STYLE;
+    STYLE_NORMAL: ENUM_PINYIN_STYLE;
+    STYLE_INITIALS: ENUM_PINYIN_STYLE;
+    STYLE_FIRST_LETTER: ENUM_PINYIN_STYLE;
+    MODE_NORMAL: ENUM_PINYIN_MODE;
+    MODE_SURNAME: ENUM_PINYIN_MODE;
+}
 export declare type IPinyinStyle = "normal" | "tone" | "tone2" | "to3ne" | "initials" | "first_letter" | // 推荐使用小写，和输出的拼音一致
@@ -3,0 +16,0 @@ "NORMAL" | "TONE" | "TONE2" | "TO3NE" | "INITIALS" | "FIRST_LETTER" | // 方便老版本迁移

lib/pinyin.d.ts

@@ -1,15 +0,9 @@
-import type { IPinyinOptions } from "./declare";
-/**
- * 拼音转换入口。
- */
-export declare function pinyin(hans: string, options?: IPinyinOptions): string[][];
+import PinyinBase from "./PinyinBase";
+import type { IPinyinSegment } from "./declare";
+export declare class Pinyin extends PinyinBase {
+    segment(hans: string, segmentType?: IPinyinSegment): string[];
+}
+export declare const pinyin: import("./declare").IPinyin;
 export default pinyin;
-/**
- * 比较两个汉字转成拼音后的排序顺序，可以用作默认的拼音排序算法。
- *
- * @param {String} hanA 汉字字符串 A。
- * @return {String} hanB 汉字字符串 B。
- * @return {Number} 返回 -1，0，或 1。
- */
-export declare function compare(hanA: string, hanB: string): number;
+export declare const compare: (a: string, b: string) => number;
 export { compact } from "./util";

lib/pinyin.js

 "use strict";
-var __importDefault = (this && this.__importDefault) || function (mod) {
-    return (mod && mod.__esModule) ? mod : { "default": mod };
+var __extends = (this && this.__extends) || (function () {
+    var extendStatics = function (d, b) {
+        extendStatics = Object.setPrototypeOf ||
+            ({ __proto__: [] } instanceof Array && function (d, b) { d.__proto__ = b; }) ||
+            function (d, b) { for (var p in b) if (Object.prototype.hasOwnProperty.call(b, p)) d[p] = b[p]; };
+        return extendStatics(d, b);
+    };
+    return function (d, b) {
+        if (typeof b !== "function" && b !== null)
+            throw new TypeError("Class extends value " + String(b) + " is not a constructor or null");
+        extendStatics(d, b);
+        function __() { this.constructor = d; }
+        d.prototype = b === null ? Object.create(b) : (__.prototype = b.prototype, new __());
+    };
+})();
+var __createBinding = (this && this.__createBinding) || (Object.create ? (function(o, m, k, k2) {
+    if (k2 === undefined) k2 = k;
+    var desc = Object.getOwnPropertyDescriptor(m, k);
+    if (!desc || ("get" in desc ? !m.__esModule : desc.writable || desc.configurable)) {
+      desc = { enumerable: true, get: function() { return m[k]; } };
+    }
+    Object.defineProperty(o, k2, desc);
+}) : (function(o, m, k, k2) {
+    if (k2 === undefined) k2 = k;
+    o[k2] = m[k];
+}));
+var __setModuleDefault = (this && this.__setModuleDefault) || (Object.create ? (function(o, v) {
+    Object.defineProperty(o, "default", { enumerable: true, value: v });
+}) : function(o, v) {
+    o["default"] = v;
+});
+var __importStar = (this && this.__importStar) || function (mod) {
+    if (mod && mod.__esModule) return mod;
+    var result = {};
+    if (mod != null) for (var k in mod) if (k !== "default" && Object.prototype.hasOwnProperty.call(mod, k)) __createBinding(result, mod, k);
+    __setModuleDefault(result, mod);
+    return result;
 };
 Object.defineProperty(exports, "__esModule", { value: true });
-exports.compact = exports.compare = exports.pinyin = void 0;
-var dict_zi_1 = __importDefault(require("./data/dict-zi")); // 单个汉字拼音数据。
-var phrases_dict_1 = __importDefault(require("./data/phrases-dict")); // 词组拼音数据。
+exports.compact = exports.compare = exports.pinyin = exports.Pinyin = void 0;
+var PinyinBase_1 = __importStar(require("./PinyinBase"));
 var segment_1 = require("./segment");
-var format_1 = require("./format");
-var surname_1 = __importDefault(require("./data/surname"));
-var compound_surname_1 = __importDefault(require("./data/compound_surname"));
+var Pinyin = /** @class */ (function (_super) {
+    __extends(Pinyin, _super);
+    function Pinyin() {
+        return _super !== null && _super.apply(this, arguments) || this;
+    }
+    Pinyin.prototype.segment = function (hans, segmentType) {
+        return (0, segment_1.segment)(hans, segmentType);
+    };
+    return Pinyin;
+}(PinyinBase_1.default));
+exports.Pinyin = Pinyin;
+exports.pinyin = (0, PinyinBase_1.getPinyinInstance)(new Pinyin());
+exports.default = exports.pinyin;
+exports.compare = exports.pinyin.compare;
 var util_1 = require("./util");
-var constant_1 = require("./constant");
-/**
- * 拼音转换入口。
- */
-function pinyin(hans, options) {
-    if (typeof hans !== "string") {
-        return [];
-    }
-    var opt = (0, util_1.convertUserOptions)(options);
-    var pys;
-    if (opt.mode === constant_1.ENUM_PINYIN_MODE.SURNAME) {
-        pys = surname_pinyin(hans, opt);
-    }
-    else {
-        // 因为分词结果有词性信息，结构不同，处理也不相同，所以需要分别处理。
-        if (opt.segment) {
-            // 分词加词性标注转换。
-            pys = segment_pinyin(hans, opt);
-        }
-        else {
-            // 单字拆分转换。连续的非中文字符作为一个词（原样输出，不转换成拼音）。
-            pys = normal_pinyin(hans, opt);
-        }
-    }
-    if (options === null || options === void 0 ? void 0 : options.compact) {
-        pys = (0, util_1.compact)(pys);
-    }
-    return pys;
-}
-exports.pinyin = pinyin;
-exports.default = pinyin;
-/**
- * 不使用分词算法的拼音转换。
- */
-function normal_pinyin(hans, options) {
-    var pys = [];
-    var nohans = "";
-    for (var i = 0, l = hans.length; i < l; i++) {
-        var words = hans[i];
-        var firstCharCode = words.charCodeAt(0);
-        if (dict_zi_1.default[firstCharCode]) {
-            // 处理前面的“非中文”部分。
-            if (nohans.length > 0) {
-                pys.push([nohans]);
-                nohans = ""; // 重置“非中文”缓存。
-            }
-            pys.push(single_pinyin(words, options));
-        }
-        else {
-            nohans += words;
-        }
-    }
-    // 清理最后的非中文字符串。
-    if (nohans.length > 0) {
-        pys.push([nohans]);
-        nohans = ""; // reset non-chinese words.
-    }
-    return pys;
-}
-/**
- * 单字拼音转换。
- * @param {String} han, 单个汉字
- * @return {Array} 返回拼音列表，多音字会有多个拼音项。
- */
-function single_pinyin(han, options) {
-    if (typeof han !== "string") {
-        return [];
-    }
-    if (han.length !== 1) {
-        return single_pinyin(han.charAt(0), options);
-    }
-    var hanCode = han.charCodeAt(0);
-    if (!dict_zi_1.default[hanCode]) {
-        return [han];
-    }
-    var pys = dict_zi_1.default[hanCode].split(",");
-    if (!options.heteronym) {
-        return [(0, format_1.toFixed)(pys[0], options.style)];
-    }
-    // 临时存储已存在的拼音，避免多音字拼音转换为非注音风格出现重复。
-    var py_cached = {};
-    var pinyins = [];
-    for (var i = 0, l = pys.length; i < l; i++) {
-        var py = (0, format_1.toFixed)(pys[i], options.style);
-        if ((0, util_1.hasKey)(py_cached, py)) {
-            continue;
-        }
-        py_cached[py] = py;
-        pinyins.push(py);
-    }
-    return pinyins;
-}
-/**
- * 将文本分词，并转换成拼音。
- */
-function segment_pinyin(hans, options) {
-    var phrases = (0, segment_1.segment)(hans, options.segment);
-    var pys = [];
-    var nohans = "";
-    for (var i = 0, l = phrases.length; i < l; i++) {
-        var words = phrases[i];
-        var firstCharCode = words.charCodeAt(0);
-        if (dict_zi_1.default[firstCharCode]) {
-            // ends of non-chinese words.
-            if (nohans.length > 0) {
-                pys.push([nohans]);
-                nohans = ""; // reset non-chinese words.
-            }
-            var newPys = words.length === 1
-                ? normal_pinyin(words, options)
-                : phrases_pinyin(words, options);
-            if (options.group) {
-                pys.push(groupPhrases(newPys));
-            }
-            else {
-                pys = pys.concat(newPys);
-            }
-        }
-        else {
-            nohans += words;
-        }
-    }
-    // 清理最后的非中文字符串。
-    if (nohans.length > 0) {
-        pys.push([nohans]);
-        nohans = ""; // reset non-chinese words.
-    }
-    return pys;
-}
-/**
- * 词语注音
- * @param {String} phrases, 指定的词组。
- * @param {Object} options, 选项。
- * @return {Array}
- */
-function phrases_pinyin(phrases, options) {
-    var py = [];
-    if ((0, util_1.hasKey)(phrases_dict_1.default, phrases)) {
-        //! copy pinyin result.
-        phrases_dict_1.default[phrases].forEach(function (item, idx) {
-            py[idx] = [];
-            if (options.heteronym) {
-                item.forEach(function (py_item, py_index) {
-                    py[idx][py_index] = (0, format_1.toFixed)(py_item, options.style);
-                });
-            }
-            else {
-                py[idx][0] = (0, format_1.toFixed)(item[0], options.style);
-            }
-        });
-    }
-    else {
-        for (var i = 0, l = phrases.length; i < l; i++) {
-            py.push(single_pinyin(phrases[i], options));
-        }
-    }
-    return py;
-}
-function groupPhrases(phrases) {
-    if (phrases.length === 1) {
-        return phrases[0];
-    }
-    var grouped = (0, util_1.combo)(phrases);
-    return grouped;
-}
-// 姓名转成拼音
-function surname_pinyin(hans, options) {
-    return compound_surname(hans, options);
-}
-// 复姓处理
-function compound_surname(hans, options) {
-    var len = hans.length;
-    var prefixIndex = 0;
-    var result = [];
-    for (var i = 0; i < len; i++) {
-        var twowords = hans.substring(i, i + 2);
-        if ((0, util_1.hasKey)(compound_surname_1.default, twowords)) {
-            if (prefixIndex <= i - 1) {
-                result = result.concat(single_surname(hans.substring(prefixIndex, i), options));
-            }
-            result = result.concat(compound_surname_1.default[twowords]);
-            i = i + 2;
-            prefixIndex = i;
-        }
-    }
-    // 处理复姓后面剩余的部分。
-    result = result.concat(single_surname(hans.substring(prefixIndex, len), options));
-    return result;
-}
-// 单姓处理
-function single_surname(hans, options) {
-    var result = [];
-    for (var i = 0, l = hans.length; i < l; i++) {
-        var word = hans.charAt(i);
-        if ((0, util_1.hasKey)(surname_1.default, word)) {
-            result = result.concat(surname_1.default[word]);
-        }
-        else {
-            result.push(single_pinyin(word, options));
-        }
-    }
-    return result;
-}
-/**
- * 比较两个汉字转成拼音后的排序顺序，可以用作默认的拼音排序算法。
- *
- * @param {String} hanA 汉字字符串 A。
- * @return {String} hanB 汉字字符串 B。
- * @return {Number} 返回 -1，0，或 1。
- */
-function compare(hanA, hanB) {
-    var pinyinA = pinyin(hanA);
-    var pinyinB = pinyin(hanB);
-    return String(pinyinA).localeCompare(String(pinyinB));
-}
-exports.compare = compare;
-var util_2 = require("./util");
-Object.defineProperty(exports, "compact", { enumerable: true, get: function () { return util_2.compact; } });
+Object.defineProperty(exports, "compact", { enumerable: true, get: function () { return util_1.compact; } });
 //# sourceMappingURL=pinyin.js.map

lib/segment.js

@@ -21,2 +21,3 @@ "use strict";
         if (!nodeRsJiebaLoaded) {
+            nodeRsJiebaLoaded = true;
             (0, jieba_1.load)();
@@ -23,0 +24,0 @@ }

package.json

 {
   "name": "pinyin",
-  "version": "3.0.0-alpha.0",
+  "version": "3.0.0-alpha.1",
   "description": "汉语拼音转换工具。",
-  "main": "lib/pinyin.js",
-  "module": "esm/pinyin.js",
-  "browser": "lib/pinyin.js",
+  "main": "./lib/pinyin.js",
+  "module": "./esm/pinyin.js",
+  "browser": {
+    "./lib/pinyin.js": "./lib/pinyin-web.js",
+    "./esm/pinyin.js": "./esm/pinyin-web.js"
+  },
   "bin": {
@@ -24,3 +27,3 @@ "pinyin": "./bin/pinyin"
     "build": "tsc --downlevelIteration -p tsconfig-es5.json & tsc --downlevelIteration -p tsconfig.json",
-    "doc:build": "dumi build",
+    "doc:build": "rm -rf ./src/.umi && dumi build",
     "doc:deploy": "npm run doc:build && cp CNAME docs-dist/dist && gh-pages -d docs-dist/dist",
@@ -27,0 +30,0 @@ "lint": "eslint ./src/ ./test/",

README.en-US.md

@@ -0,4 +1,3 @@
+# pīnyīn for Han （汉字） (v3)
 
-# pīnyīn for Han （汉字）
-
 ---
@@ -23,3 +22,3 @@
 
-[中文文档](/)
+[中文文档网站](/)
 
@@ -26,0 +25,0 @@ [中文 README](README.md)

README.md

@@ -1,2 +0,2 @@
-# README
+# README (v3)
 
@@ -25,3 +25,3 @@ pīnyīn, 汉字拼音转换工具。
 
-[English Documention](/en-US/)
+[English Documention Site](/en-US/)
 
@@ -50,3 +50,3 @@ [English README](README.en-US.md)
 ```bash
-npm install pinyin --save
+npm install pinyin@v3 --save
 ```
@@ -103,3 +103,54 @@
 
+传入给 pinyin 方法的第二个参数的选项类型。
 
+```typescript
+export interface IPinyinOptions {
+  style?: IPinyinStyle; // 拼音输出形式
+  mode?: IPinyinMode, // 拼音模式
+  // 指定分词库。
+  // 为了兼容老版本，可以使用 boolean 类型指定是否开启分词，默认开启。
+  segment?: IPinyinSegment | boolean;
+  // 是否返回多音字
+  heteronym?: boolean;
+  // 是否分组词组拼音
+  group?: boolean;
+  compact?: boolean;
+}
+```
+
+### IPinyinStyle
+
+输出拼音格式。可以从直接使用以下字符串或数字，也兼容 v2 版本中 `pinyin.STYLE_TONE` 这样的形式。
+
+```
+export type IPinyinStyle =
+  "normal" | "tone" | "tone2" | "to3ne" | "initials" | "first_letter" | // 推荐使用小写，和输出的拼音一致
+  "NORMAL" | "TONE" | "TONE2" | "TO3NE" | "INITIALS" | "FIRST_LETTER" | // 方便老版本迁移
+  0        | 1      | 2       | 5       | 3          | 4;               // 兼容老版本
+```
+
+### IPinyinMode
+
+拼音模式，默认普通模式，可以指定人名模式。
+
+```
+// - NORMAL: 普通模式
+// - SURNAME: 姓氏模式，优先使用姓氏的拼音。
+export type IPinyinMode =
+  "normal" | "surname" |
+  "NORMAL" | "SURNAME";
+```
+
+### IPinyinSegment
+
+分词方式。
+
+- 默认关闭 `false`，
+- 也可以设置为 `true` 开启，Web 版中使用 "segmentit" 分词，Node 版中使用 "nodejieba" 分词。
+- 也可以声明以下字符串来指定分词算法。但目前 Web 版只支持 "segmentit" 分词。
+
+```
+export type IPinyinSegment = "nodejieba" | "segmentit" | "@node-rs/jieba";
+```
+
 ## API
@@ -106,0 +157,0 @@

Fixed alerts

Major refactor

Supply chain risk

Package has recently undergone a major refactor. It may be unstable or indicate significant internal changes. Use caution when updating to versions that include significant changes.

Found 1 instance in 1 package

Improved metrics

Total package byte prevSize

9174476

increased by0.22%

Number of package files

50

increased by31.58%

Lines of code

84369

increased by0.35%

Number of lines in readme file

371

increased by15.94%

Number of medium supply chain risk alerts

0

decreased by-100%

No dependency changes