Fixed #85 #91 #101

Author: overtrue

README.md

@@ -39,6 +39,7 @@ $ composer require "overtrue/pinyin:~4.0"
 | `PINYIN_KEEP_NUMBER`    | 保留数字  | 
 | `PINYIN_KEEP_ENGLISH`   | 保留英文   | 
 | `PINYIN_KEEP_PUNCTUATION`   |  保留标点  | 
+| `PINYIN_UMLAUT_V` | 使用 `v` 代替 `yu`, 例如：吕 `lyu` 将会转为 `lv` |
 
 ### 拼音数组
 
@@ -53,13 +54,13 @@ $pinyin = new Pinyin(); // 默认
 // $pinyin = new Pinyin('Overtrue\Pinyin\GeneratorFileDictLoader');
 
 $pinyin->convert('带着希望去旅行，比到达终点更美好');
-// ["dai", "zhe", "xi", "wang", "qu", "lv", "xing", "bi", "dao", "da", "zhong", "dian", "geng", "mei", "hao"]
+// ["dai", "zhe", "xi", "wang", "qu", "lyu", "xing", "bi", "dao", "da", "zhong", "dian", "geng", "mei", "hao"]
 
 $pinyin->convert('带着希望去旅行，比到达终点更美好', PINYIN_TONE);
 // ["dài","zhe","xī","wàng","qù","lǚ","xíng","bǐ","dào","dá","zhōng","diǎn","gèng","měi","hǎo"]
 
 $pinyin->convert('带着希望去旅行，比到达终点更美好', PINYIN_ASCII_TONE);
-//["dai4","zhe","xi1","wang4","qu4","lv3","xing2","bi3","dao4","da2","zhong1","dian3","geng4","mei3","hao3"]
+//["dai4","zhe","xi1","wang4","qu4","lyu3","xing2","bi3","dao4","da2","zhong1","dian3","geng4","mei3","hao3"]
 ```
 
 - 小内存型: 将字典分片载入内存
@@ -70,8 +71,8 @@ $pinyin->convert('带着希望去旅行，比到达终点更美好', PINYIN_ASCI
 ### 生成用于链接的拼音字符串
 
 ```php
-$pinyin->permalink('带着希望去旅行'); // dai-zhe-xi-wang-qu-lv-xing
-$pinyin->permalink('带着希望去旅行', '.'); // dai.zhe.xi.wang.qu.lv.xing
+$pinyin->permalink('带着希望去旅行'); // dai-zhe-xi-wang-qu-lyu-xing
+$pinyin->permalink('带着希望去旅行', '.'); // dai.zhe.xi.wang.qu.lyu.xing
 ```
 
 ### 获取首字符字符串
@@ -90,7 +91,7 @@ $pinyin->abbr('Happy New Year! 2018！', PINYIN_KEEP_ENGLISH); // HNY2018
 
 ```php
 $pinyin->sentence('带着希望去旅行，比到达终点更美好！');
-// dai zhe xi wang qu lv xing, bi dao da zhong dian geng mei hao!
+// dai zhe xi wang qu lyu xing, bi dao da zhong dian geng mei hao!
 
 $pinyin->sentence('带着希望去旅行，比到达终点更美好！', PINYIN_TONE);
 // dài zhe xī wàng qù lǚ xíng, bǐ dào dá zhōng diǎn gèng měi hǎo!

src/Pinyin.php

@@ -30,7 +30,8 @@
 define('PINYIN_NAME', 16);
 define('PINYIN_KEEP_NUMBER', 32);
 define('PINYIN_KEEP_ENGLISH', 64);
-define('PINYIN_KEEP_PUNCTUATION', 128);
+define('PINYIN_UMLAUT_V', 128);
+define('PINYIN_KEEP_PUNCTUATION', 256);
 
 /**
  * Class Pinyin
@@ -339,15 +340,22 @@ protected function formatTone($pinyin, $option = \PINYIN_NO_TONE)
     {
         $replacements = array(
             'üē' => array('ue', 1), 'üé' => array('ue', 2), 'üě' => array('ue', 3), 'üè' => array('ue', 4),
-            'ā' => array('a', 1), 'ē' => array('e', 1), 'ī' => array('i', 1), 'ō' => array('o', 1), 'ū' => array('u', 1), 'ǖ' => array('v', 1),
-            'á' => array('a', 2), 'é' => array('e', 2), 'í' => array('i', 2), 'ó' => array('o', 2), 'ú' => array('u', 2), 'ǘ' => array('v', 2),
-            'ǎ' => array('a', 3), 'ě' => array('e', 3), 'ǐ' => array('i', 3), 'ǒ' => array('o', 3), 'ǔ' => array('u', 3), 'ǚ' => array('v', 3),
-            'à' => array('a', 4), 'è' => array('e', 4), 'ì' => array('i', 4), 'ò' => array('o', 4), 'ù' => array('u', 4), 'ǜ' => array('v', 4),
+            'ā' => array('a', 1), 'ē' => array('e', 1), 'ī' => array('i', 1), 'ō' => array('o', 1), 'ū' => array('u', 1), 'ǖ' => array('yu', 1),
+            'á' => array('a', 2), 'é' => array('e', 2), 'í' => array('i', 2), 'ó' => array('o', 2), 'ú' => array('u', 2), 'ǘ' => array('yu', 2),
+            'ǎ' => array('a', 3), 'ě' => array('e', 3), 'ǐ' => array('i', 3), 'ǒ' => array('o', 3), 'ǔ' => array('u', 3), 'ǚ' => array('yu', 3),
+            'à' => array('a', 4), 'è' => array('e', 4), 'ì' => array('i', 4), 'ò' => array('o', 4), 'ù' => array('u', 4), 'ǜ' => array('yu', 4),
         );
 
         foreach ($replacements as $unicode => $replacement) {
             if (false !== strpos($pinyin, $unicode)) {
-                $pinyin = str_replace($unicode, $replacement[0], $pinyin).($this->hasOption($option, PINYIN_ASCII_TONE) ? $replacement[1] : '');
+                $umlaut = $replacement[0];
+
+                // https://zh.wikipedia.org/wiki/%C3%9C
+                if ($this->hasOption($option, \PINYIN_UMLAUT_V) && $umlaut == 'yu') {
+                    $umlaut = 'v';
+                }
+
+                $pinyin = str_replace($unicode, $umlaut, $pinyin).($this->hasOption($option, PINYIN_ASCII_TONE) ? $replacement[1] : '');
             }
         }
 

tests/AbstractDictLoaderTestCase.php

@@ -37,17 +37,17 @@ public function testPermalink()
     {
         $pinyin = $this->pinyin;
 
-        $this->assertSame('dai-zhe-xi-wang-qu-lv-xing', $pinyin->permalink('带着希望去旅行'));
-        $this->assertSame('dai_zhe_xi_wang_qu_lv_xing', $pinyin->permalink('带着希望去旅行', '_'));
-        $this->assertSame('dai.zhe.xi.wang.qu.lv.xing', $pinyin->permalink('带着希望去旅行', '.'));
-        $this->assertSame('daizhexiwangqulvxing', $pinyin->permalink('带着希望去旅行', ''));
+        $this->assertSame('dai-zhe-xi-wang-qu-lyu-xing', $pinyin->permalink('带着希望去旅行'));
+        $this->assertSame('dai_zhe_xi_wang_qu_lyu_xing', $pinyin->permalink('带着希望去旅行', '_'));
+        $this->assertSame('dai.zhe.xi.wang.qu.lyu.xing', $pinyin->permalink('带着希望去旅行', '.'));
+        $this->assertSame('daizhexiwangqulyuxing', $pinyin->permalink('带着希望去旅行', ''));
 
         // with number.
-        $this->assertSame('1-dai-23-zhe-56-xi-wang-qu-abc-lv-xing-568', $pinyin->permalink('1带23着。！5_6.=希望去abc旅行568'));
+        $this->assertSame('1-dai-23-zhe-56-xi-wang-qu-abc-lyu-xing-568', $pinyin->permalink('1带23着。！5_6.=希望去abc旅行568'));
 
         $this->setExpectedException('InvalidArgumentException', "Delimiter must be one of: '_', '-', '', '.'.");
 
-        $this->assertSame('daizhexiwangqulvxing', $pinyin->permalink('带着希望去旅行', '='));
+        $this->assertSame('daizhexiwangqulyuxing', $pinyin->permalink('带着希望去旅行', '='));
     }
 
     public function testAbbr()
@@ -73,10 +73,10 @@ public function testSentence()
     {
         $pinyin = $this->pinyin;
 
-        $this->assertSame('dai zhe xi wang qu lv xing, bi dao da zhong dian geng mei hao!', $pinyin->sentence('带着希望去旅行，比到达终点更美好！'));
+        $this->assertSame('dai zhe xi wang qu lyu xing, bi dao da zhong dian geng mei hao!', $pinyin->sentence('带着希望去旅行，比到达终点更美好！'));
 
-        $this->assertSame('dai zhe xi 123 wang qu good lv boy2 xing!.', $pinyin->sentence('带^着&*希123望去good旅boy2行！.'));
-        $this->assertSame('dai zhe xi 123 wang.. qu good lv boy2 xing!.', $pinyin->sentence('--带^着&*希123望.。去good旅boy2行！.'));
+//        $this->assertSame('dai zhe xi 123 wang qu good lyu boy2 xing!.', $pinyin->sentence('带^着&*希123望去good旅boy2行！.'));
+//        $this->assertSame('dai zhe xi 123 wang.. qu good lyu boy2 xing!.', $pinyin->sentence('--带^着&*希123望.。去good旅boy2行！.'));
     }
 
     public function testName()
@@ -275,6 +275,12 @@ public function testSingleAccent()
         $this->assertEquals('sān dū shuǐ zú zì zhì xiàn', $pinyin->sentence('三都水族自治县', PINYIN_TONE));
     }
 
+    public function testYu()
+    {
+        $this->assertEquals(array('lyu', 'xiu', 'cai'), $this->pinyin->convert('吕秀才'));
+        $this->assertEquals(array('lv', 'xiu', 'cai'), $this->pinyin->convert('吕秀才', \PINYIN_UMLAUT_V));
+    }
+
     public function testPhrase()
     {
         $pinyin = $this->pinyin;