Merge 9298548 into 2c914c7

README-us_EN.md

@@ -51,8 +51,12 @@ console.log(pinyin("中心", {
 }));                            // [ [ 'zhōng', 'zhòng' ], [ 'xīn' ] ]
 console.log(pinyin("中心", {
   heteronym: true,              // Enable heteronym mode.
-  segment: true                 // Enable Chinese words eegmentation, fix most heteronym problem.
+  segment: true                 // Enable Chinese words segmentation, fix most heteronym problem.
 }));                            // [ [ 'zhōng' ], [ 'xīn' ] ]
+console.log(pinyin("我喜欢你", {
+  segment: true,                // Enable segmentation. Needed for grouping.
+  group: true                   // Group pinyin segments
+}));                            // [ [ [ 'wǒ' ] ], [ [ 'xǐ' ], [ 'huān' ] ], [ [ 'nǐ' ] ] ]
 console.log(pinyin("中心", {
   style: pinyin.STYLE_INITIALS, // Setting pinyin style.
   heteronym: true

README.md

@@ -59,6 +59,10 @@ console.log(pinyin("中心", {
   heteronym: true,              // 启用多音字模式
   segment: true                 // 启用分词，以解决多音字问题。
 }));                            // [ [ 'zhōng' ], [ 'xīn' ] ]
+console.log(pinyin("我喜欢你", {
+  segment: true,                // 启用分词
+  group: true                   // 启用词组
+}));                            // [ [ [ 'wǒ' ] ], [ [ 'xǐ' ], [ 'huān' ] ], [ [ 'nǐ' ] ] ]
 console.log(pinyin("中心", {
   style: pinyin.STYLE_INITIALS, // 设置拼音风格
   heteronym: true

lib/index.js

@@ -34,10 +34,14 @@ class NodePinyin extends Pinyin {
           nohans = ""; // reset non-chinese words.
         }
 
-        if (words.length === 1) {
-          pys = pys.concat(super.convert(words, options));
+        const newPys = words.length === 1
+          ? super.convert(words, options)
+          : this.phrases_pinyin(words, options);
+
+        if (options.group) {
+          pys.push(newPys);
         } else {
-          pys = pys.concat(this.phrases_pinyin(words, options));
+          pys = pys.concat(newPys);
         }
 
       } else {
@@ -47,6 +51,9 @@ class NodePinyin extends Pinyin {
 
     // 清理最后的非中文字符串。
     if(nohans.length > 0){
+      if (options.group) {
+        nohans = [nohans];
+      }
       pys.push([nohans]);
       nohans = ""; // reset non-chinese words.
     }

tests/test.js

@@ -268,3 +268,17 @@ describe("pinyin.compare", function() {
     expect(sortedData).to.eql("排我序要".split(""));
   });
 });
+
+describe("pinyin group", function() {
+  it("groups segments", function () {
+    const han = "我喜欢你";
+    const py = pinyin(han, {segment: true, group: true, heteronym: true});
+    expect(py).to.eql([[["wǒ"]], [["xǐ"], ["huān"]], [["nǐ"]]]);
+  });
+
+  it("groups segments with heteronyms", function() {
+    const han = "我都喜欢";
+    const py = pinyin(han, {segment: true, group: true, heteronym: true});
+    expect(py).to.eql([[["wǒ"]], [["dū", "dōu"]], [["xǐ"], ["huān"]]]);
+  });
+});