{"id":17118,"date":"2023-11-24T01:50:04","date_gmt":"2023-11-23T17:50:04","guid":{"rendered":"https:\/\/www.bookcard.net\/wordpress\/?p=17118"},"modified":"2023-11-24T01:51:59","modified_gmt":"2023-11-23T17:51:59","slug":"unicode_utf8","status":"publish","type":"post","link":"https:\/\/www.bookcard.net\/wordpress\/unicode_utf8\/","title":{"rendered":"UNICODE-UTF8\u8f49\u63db"},"content":{"rendered":"<figure id=\"attachment_17119\" aria-describedby=\"caption-attachment-17119\" style=\"width: 1280px\" class=\"wp-caption alignnone\"><a href=\"https:\/\/www.bookcard.net\/wordpress\/wp-content\/uploads\/2023\/11\/UNICODE_UTF8.jpg\"><img loading=\"lazy\" decoding=\"async\" class=\"size-full wp-image-17119\" src=\"https:\/\/www.bookcard.net\/wordpress\/wp-content\/uploads\/2023\/11\/UNICODE_UTF8.jpg\" alt=\"UNICODE-UTF8\u8f49\u63db\" width=\"1280\" height=\"800\" srcset=\"https:\/\/www.bookcard.net\/wordpress\/wp-content\/uploads\/2023\/11\/UNICODE_UTF8.jpg 1280w, https:\/\/www.bookcard.net\/wordpress\/wp-content\/uploads\/2023\/11\/UNICODE_UTF8-300x188.jpg 300w, https:\/\/www.bookcard.net\/wordpress\/wp-content\/uploads\/2023\/11\/UNICODE_UTF8-768x480.jpg 768w\" sizes=\"auto, (max-width: 1280px) 100vw, 1280px\" \/><\/a><figcaption id=\"caption-attachment-17119\" class=\"wp-caption-text\">UNICODE-UTF8\u8f49\u63db<\/figcaption><\/figure>\n<p>\u4fc2\u96fb\u8166\u767c\u5c55\u521d\u6642.\u5b9a\u7fa9\u5de6\u5957\u300eASCII\u78bc\u300f,\u5f97128\u5b57\u7b26,\u82f1\u6587\u52a0\u6578\u5b57\u7528\u55ae\u5b57\u7bc0BYTE. \u5f8c\u849e\u5404\u570b\u7686\u81ea\u5b9a\u300e\u5b57\u7b26\u7de8\u78bc\u300f,\u300eBIG5\/GB2312\u300f\u7686\u5360\u4e24\u5b57\u7bc0WORD,\u7ed3\u679c\u4fc2\u7de8\u78bc\u91cd\u53e0.\u6240\u4ee5\u5148\u6709\u4e82\u78bc.<\/p>\n<p>UNICODE\u300e\u842c\u570b\u78bc\u300f,\u5404\u570b\u5404\u81ea\u6709\u7368\u7acb\u7de8\u78bc\u6bb5,\u543e\u91cd\u53e0,\u540c\u300eASCII\u78bc\u300f\u517c\u5bb9.<\/p>\n<p>\u300eUNICODE\u300f\u4fc2\u8a2d\u8a08\u4e4b\u521d\u6bcf\u5b57\u7b26\u5360\u300e2 BYTE\u300f\u5373\u300eUSC2\u300f\u5b57\u7b26\u96c6. \u4f46\u4fc2\u300e2 BYTE\u300f\u591f\u652f\u630165535\u5b57\u7b26.\u6240\u4ee5\u5f8c\u849e\u6709\u300eUSC4\u300f\u5360\u300e4 BYTE\u300f.<\/p>\n<p>\u4fc2\u540c\u58f9\u5b57\u7b26\u4e32USC2\u540cUSC4\u6703\u6df7\u5408\u51fa\u73fe.<\/p>\n<p>\u4f46\u4fc2\u300eASCII\u78bc\u300f\u53ea\u9700\u55ae\u5b57\u7bc0\u300e1 BYTE\u300f. \u6240\u4ee5\u767c\u660e\u5de6\u300eUTF-8\u300f\u4ee5\u7bc0\u7d04\u5730\u65b9.<\/p>\n<p>\u300eUTF-8\u300f\u540c\u300eUNICODE\u300f\u6309\u7167\u4e0b\u8868\u4e92\u70ba\u8f49\u6362.<\/p>\n<table>\n<tbody>\n<tr>\n<td width=\"264\">Unicode\u300eUSC2\u300f\u5b57\u7b26\u96c6HEX<\/td>\n<td width=\"289\">\u300eUTF-8\u300fbin<\/td>\n<\/tr>\n<tr>\n<td width=\"264\">0x0000~0x007F<\/td>\n<td width=\"289\">0xxxxxxx<\/td>\n<\/tr>\n<tr>\n<td width=\"264\">0x0080~0x07FF<\/td>\n<td width=\"289\">110xxxxx 10xxxxxx<\/td>\n<\/tr>\n<tr>\n<td width=\"264\">0x0800~0xFFFF<\/td>\n<td width=\"289\">1110xxxx 10xxxxxx 10xxxxxx<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p>\u70ba\u5de6\u4fc2\u540c\u58f9\u5b57\u7b26\u4e32\u300eUSC2\u300f\u540c\u300eUSC4\u300f\u6df7\u5408\u51fa\u73fe.\u4fc2\u300eUSC4\u300f\u5b57\u7b26\u300e\u4f4e16bit\u300f\u540c\u300e\u9ad816bit\u300f\u5206\u5225\u52a0\u524d\u7f00\u6a19\u8a18.<\/p>\n<p>\u300e\u4f4e16bit\u300f\u52a0\u300e0xD800\u300f,\u300e\u9ad816bit\u300f\u52a0\u300e0xDC00\u300f,\u518d\u52a0\u58f9\u5340\u57df0x10000.<\/p>\n<p>\u524d\u7f00\u6a19\u8a18\u300e0xD800\u300f\u300e0xDC00\u300f\u5404\u53606bit,\u5404\u51c0\u4f4e10bit\u52a0\u57cb\u6709\u300e20bit\u300f.\u591f\u652f\u6301 \u300e1048576\u300f\u5b57\u7b26<\/p>\n<table>\n<tbody>\n<tr>\n<td width=\"188\">USC4-\u4f4e16bit\u524d\u7f00\u6a19\u8a18<\/td>\n<td width=\"152\">0xD800<\/td>\n<td width=\"213\">BIN:110110 00000 00000<\/td>\n<\/tr>\n<tr>\n<td width=\"188\">USC4-\u9ad816bit\u524d\u7f00\u6a19\u8a18<\/td>\n<td width=\"152\">0xDC00<\/td>\n<td width=\"213\">BIN:110111 00000 00000<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p>&nbsp;<\/p>\n<table>\n<tbody>\n<tr>\n<td width=\"75\">USC4<\/td>\n<td width=\"85\">\u524d\u7f00\u6a19\u8a18<\/td>\n<td width=\"393\">USC4=\u524d\u7f00\u6a19\u8a18+\u5b57\u7b26<\/td>\n<\/tr>\n<tr>\n<td width=\"75\">\u4f4e16bit<\/td>\n<td width=\"85\">0xD800<\/td>\n<td width=\"393\">BIN:110110 00000 00000 + BIN:xxxxxxxxxx<\/td>\n<\/tr>\n<tr>\n<td width=\"75\">\u9ad816bit<\/td>\n<td width=\"85\">0xDC00<\/td>\n<td width=\"393\">BIN:110111 00000 00000 + BIN:xxxxxxxxxx<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p>utf8 \u8f49 usc4<\/p>\n<table>\n<tbody>\n<tr>\n<td width=\"141\">\u9996\u5b57\u7bc0<\/td>\n<td width=\"412\">value = utf8[sour] &amp; (0xFF &gt;&gt; (bytes + 1));<\/p>\n<p>++sour;<\/td>\n<\/tr>\n<tr>\n<td width=\"141\">\u5c3e\u968f\u5b57\u7bc0<\/td>\n<td width=\"412\">for (int i = 1; i &lt; bytes; ++i) {<\/p>\n<p>value = value &lt;&lt; 6;<\/p>\n<p>value = value | (utf8[sour] &amp; 0x3f);\/\/ \u63d0\u4f4e6bit<\/p>\n<p>++sour;<\/p>\n<p>}<\/td>\n<\/tr>\n<tr>\n<td width=\"141\">\u51cf\u58f9\u5340\u57df<\/td>\n<td width=\"412\">value = value &#8211; 0x10000<\/td>\n<\/tr>\n<tr>\n<td width=\"141\">\u4f4e16bit<\/td>\n<td width=\"412\">unicode[dest] = 0xD800 | ((value &gt;&gt; 10) &amp; 0x3ff );<\/td>\n<\/tr>\n<tr>\n<td width=\"141\">\u9ad816bit<\/td>\n<td width=\"412\">unicode[dest+1] = 0xDC00 | ((value) &amp; 0x3ff);<\/p>\n<p>dest = dest + 2;<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p>utf8 \u8f49 usc2<\/p>\n<table>\n<tbody>\n<tr>\n<td width=\"141\">\u9996\u5b57\u7bc0<\/td>\n<td width=\"412\">value = utf8[sour] &amp; (0xFF &gt;&gt; (bytes + 1));<\/p>\n<p>++sour;<\/td>\n<\/tr>\n<tr>\n<td width=\"141\">\u5c3e\u968f\u5b57\u7bc0<\/td>\n<td width=\"412\">for (int i = 1; i &lt; bytes; ++i) {<\/p>\n<p>value = value &lt;&lt; 6;<\/p>\n<p>value = value | (utf8[sour] &amp; 0x3f);<\/p>\n<p>++sour;<\/p>\n<p>}<\/td>\n<\/tr>\n<tr>\n<td width=\"141\">\u53cd\u8f49\u5b57\u7bc0<\/td>\n<td width=\"412\">v = (value &gt;&gt; 24) &amp; 0xFF;<\/p>\n<p>unicode[dest] = v;<\/p>\n<p>v = (value &gt;&gt; 16) &amp; 0xFF;<\/p>\n<p>if (v != 0) {<\/p>\n<p>unicode[dest] = (unicode[dest] &lt;&lt; 8) + v;<\/p>\n<p>++dest;<\/p>\n<p>}<\/td>\n<\/tr>\n<tr>\n<td width=\"141\">\u53cd\u8f49\u5b57\u7bc0<\/td>\n<td width=\"412\">v = (value &gt;&gt; 8) &amp; 0xFF;<\/p>\n<p>unicode[dest] = v;<\/p>\n<p>v = value &amp; 0xFF;<\/p>\n<p>if (v != 0) {<\/p>\n<p>unicode[dest] = (unicode[dest] &lt;&lt; 8) + v;<\/p>\n<p>++dest;<\/p>\n<p>}<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p>Usc4\u8f49utf8<\/p>\n<table>\n<tbody>\n<tr>\n<td width=\"94\">\u63d0\u53d6\u5b57\u7b26<\/td>\n<td width=\"459\">value = (unicode[sour] &#8211; 0xD800) &lt;&lt; 10 | (unicode[sour + 1] &#8211; 0xDC00);<\/td>\n<\/tr>\n<tr>\n<td width=\"94\">\u52a0\u58f9\u5340\u57df<\/td>\n<td width=\"459\">value = value + 0x10000;<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p>Usc2\u8f49utf8<\/p>\n<table>\n<tbody>\n<tr>\n<td width=\"104\">\u63d0\u53d6\u5b57\u7b26<\/td>\n<td width=\"449\">value = unicode[sour];<\/td>\n<\/tr>\n<tr>\n<td width=\"104\">\u9996\u5b57\u7bc0<\/td>\n<td width=\"449\">utf8[dest] = (0xFF &lt;&lt; (8 &#8211; bytes)) | (value &gt;&gt; ((bytes &#8211; 1) * 6));<\/p>\n<p>++dest;<\/td>\n<\/tr>\n<tr>\n<td width=\"104\">\u5c3e\u968f\u5b57\u7bc0<\/td>\n<td width=\"449\">for (int i = 1; i &lt; bytes; ++i) {<\/p>\n<p>utf8[dest] = 0x80 | (value &gt;&gt; ((bytes &#8211; i &#8211; 1) * 6) &amp; 0x3F);<\/p>\n<p>++dest;<\/p>\n<p>}<\/p>\n<p>++sour;<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p>\u300eUTF-8\u300f\u9996byte,\u524d\u7f00\u6a19\u8a18\u5b57\u7b26\u9577\u5ea6. \u524d\u7f000\u9577\u5ea61, \u524d\u7f00110\u9577\u5ea62, \u524d\u7f001110\u9577\u5ea63. \u4ee5\u6b64\u7c7b\u63a8.\u5c3e\u968fbyte\u524d\u7f00\u7686\u6a19\u8a1801.<\/p>\n<table>\n<tbody>\n<tr>\n<td width=\"425\">\u300eUTF-8\u300fbin<\/td>\n<td width=\"128\">\u9577\u5ea6<\/td>\n<\/tr>\n<tr>\n<td width=\"425\">bin:0xxxxxxx<\/td>\n<td width=\"128\">1<\/td>\n<\/tr>\n<tr>\n<td width=\"425\">bin:110xxxxx 10xxxxxx<\/td>\n<td width=\"128\">2<\/td>\n<\/tr>\n<tr>\n<td width=\"425\">bin:1110xxxx 10xxxxxx 10xxxxxx<\/td>\n<td width=\"128\">3<\/td>\n<\/tr>\n<tr>\n<td width=\"425\">bin:11110xxx 10xxxxxx 10xxxxxx 10xxxxxx<\/td>\n<td width=\"128\">4<\/td>\n<\/tr>\n<tr>\n<td width=\"425\">bin:111110xx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx<\/td>\n<td width=\"128\">5<\/td>\n<\/tr>\n<tr>\n<td width=\"425\">bin:1111110x 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx<\/td>\n<td width=\"128\">6<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p>\u6309\u9996BIT\u7b26\u865f,\u8a08\u7b97UTF8\u5b57\u7b26\u9577\u5ea6,\u8fd4\u56de0\u975eUFT8\u5b57\u7b26.<\/p>\n<table>\n<tbody>\n<tr>\n<td width=\"425\">\u300eUTF-8\u300f\u5b57\u7b26<\/td>\n<td width=\"128\"><\/td>\n<\/tr>\n<tr>\n<td width=\"425\">if ((utf8[0] &amp; 0x80) == 0x00)<\/p>\n<p>return 1;<\/td>\n<td width=\"128\">0xxxxxxx<\/td>\n<\/tr>\n<tr>\n<td width=\"425\">if ((utf8[0] &amp; 0xE0) == 0xC0\u00a0 &amp;&amp;<\/p>\n<p>(utf8[1] &amp; 0xC0) == 0x80)<\/p>\n<p>return 2;<\/td>\n<td width=\"128\">110xxxxx 10xxxxxx<\/td>\n<\/tr>\n<tr>\n<td width=\"425\">if ((utf8[0] &amp; 0xF0) == 0xE0 &amp;&amp;<\/p>\n<p>(utf8[1] &amp; 0xC0) == 0x80 &amp;&amp;<\/p>\n<p>(utf8[2] &amp; 0xC0) == 0x80)<\/p>\n<p>return 3;<\/td>\n<td width=\"128\">1110xxxx<\/p>\n<p>10xxxxxx<\/p>\n<p>10xxxxxx<\/td>\n<\/tr>\n<tr>\n<td width=\"425\">if ((utf8[0] &amp; 0xF8) == 0xF0 &amp;&amp;<\/p>\n<p>(utf8[1] &amp; 0xC0) == 0x80 &amp;&amp;<\/p>\n<p>(utf8[2] &amp; 0xC0) == 0x80 &amp;&amp;<\/p>\n<p>(utf8[3] &amp; 0xC0) == 0x80)<\/p>\n<p>return 4;<\/td>\n<td width=\"128\">11110xxx<\/p>\n<p>10xxxxxx<\/p>\n<p>10xxxxxx<\/p>\n<p>10xxxxxx<\/td>\n<\/tr>\n<tr>\n<td width=\"425\">if ((utf8[0] &amp; 0xFC) == 0xF8 &amp;&amp;<\/p>\n<p>(utf8[1] &amp; 0xC0) == 0x80 &amp;&amp;<\/p>\n<p>(utf8[2] &amp; 0xC0) == 0x80 &amp;&amp;<\/p>\n<p>(utf8[3] &amp; 0xC0) == 0x80 &amp;&amp;<\/p>\n<p>(utf8[4] &amp; 0xC0) == 0x80)<\/p>\n<p>return 5;<\/td>\n<td width=\"128\">111110xx<\/p>\n<p>10xxxxxx<\/p>\n<p>10xxxxxx<\/p>\n<p>10xxxxxx<\/p>\n<p>10xxxxxx<\/td>\n<\/tr>\n<tr>\n<td width=\"425\">if ((utf8[0] &amp; 0xFE) == 0xFC &amp;&amp;<\/p>\n<p>(utf8[1] &amp; 0xC0) == 0x80 &amp;&amp;<\/p>\n<p>(utf8[2] &amp; 0xC0) == 0x80 &amp;&amp;<\/p>\n<p>(utf8[3] &amp; 0xC0) == 0x80 &amp;&amp;<\/p>\n<p>(utf8[4] &amp; 0xC0) == 0x80 &amp;&amp;<\/p>\n<p>(utf8[5] &amp; 0xC0) == 0x80)<\/p>\n<p>return 6;<\/td>\n<td width=\"128\">1111110x<\/p>\n<p>10xxxxxx<\/p>\n<p>10xxxxxx<\/p>\n<p>10xxxxxx<\/p>\n<p>10xxxxxx<\/p>\n<p>10xxxxxx<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p>unicode\u8f49utf8 , ASCII\u78bc\u76f8\u7b49.<\/p>\n<table>\n<tbody>\n<tr>\n<td width=\"553\">\u00a0int UnicodeToUTF8(char * utf8, const wchar_t * unicode)<\/p>\n<p>{<\/p>\n<p>int unicodeLength = 0;<\/p>\n<p>int bytes;<\/p>\n<p>int dest, sour;<\/p>\n<p>DWORD value;<\/p>\n<p>unicodeLength = Unicode_Length(unicode) ;<\/p>\n<p>sour = dest = 0;<\/p>\n<p>while (sour &lt; unicodeLength)<\/p>\n<p>{<\/p>\n<p>bytes = 1;<\/p>\n<p>if (unicode[sour] &gt;= 0xD800 &amp;&amp; unicode[sour + 1] &gt;= 0xDC00)<\/p>\n<p>bytes = 4;<\/p>\n<p>else<\/p>\n<p>if (unicode[sour] &gt;= 0x00 &amp;&amp; unicode[sour] &lt;= 0x7F)<\/p>\n<p>bytes = 1;<\/p>\n<p>else<\/p>\n<p>if (unicode[sour] &gt;= 0x80 &amp;&amp; unicode[sour] &lt;= 0x7FF)<\/p>\n<p>bytes = 2;<\/p>\n<p>else<\/p>\n<p>if (unicode[sour] &gt;= 0x800 &amp;&amp; unicode[sour] &lt;= 0xFFFF)<\/p>\n<p>bytes = 3;<\/p>\n<p>else<\/p>\n<p>if (((unicode[sour + 1] &lt;&lt; 16) | unicode[sour]) &gt;= 0x10000 &amp;&amp;<\/p>\n<p>((unicode[sour + 1] &lt;&lt; 16) | unicode[sour]) &lt;= 0x1FFFFF)<\/p>\n<p>bytes = 4;<\/p>\n<p>else<\/p>\n<p>if (((unicode[sour + 1] &lt;&lt; 16) | unicode[sour]) &gt;= 0x200000 &amp;&amp;<\/p>\n<p>((unicode[sour + 1] &lt;&lt; 16) | unicode[sour]) &lt;= 0x3FFFFFF)<\/p>\n<p>bytes = 5;<\/p>\n<p>else<\/p>\n<p>if (((unicode[sour + 1] &lt;&lt; 16) | unicode[sour]) &gt;= 0x4000000 &amp;&amp;<\/p>\n<p>((unicode[sour + 1] &lt;&lt; 16) | unicode[sour]) &lt;= 0x7FFFFFFF)<\/p>\n<p>bytes = 6;<\/p>\n<p>else<\/p>\n<p>if (((unicode[sour + 1] &lt;&lt; 16) | unicode[sour]) &gt;= 0x80000000)<\/p>\n<p>bytes = 7;<\/p>\n<p>&nbsp;<\/p>\n<p>if (bytes == 1)<\/p>\n<p>{<\/p>\n<p>utf8[dest] = unicode[sour];<\/p>\n<p>++dest;<\/p>\n<p>++sour;<\/p>\n<p>}<\/p>\n<p>else<\/p>\n<p>if (unicode[sour] &gt;= 0xD800 &amp;&amp; unicode[sour + 1] &gt;= 0xDC00)<\/p>\n<p>{<\/p>\n<p>value = (unicode[sour] &#8211; 0xD800) &lt;&lt; 10\u00a0\u00a0 |\u00a0 (unicode[sour + 1] &#8211; 0xDC00);<\/p>\n<p>value = value + 0x10000;<\/p>\n<p>utf8[dest] = (0xFF &lt;&lt; (8 &#8211; bytes)) | (value &gt;&gt; ((bytes &#8211; 1) * 6));<\/p>\n<p>++dest;<\/p>\n<p>for (int i = 1; i &lt; bytes; ++i) {<\/p>\n<p>utf8[dest] = 0x80 | (value &gt;&gt; ((bytes &#8211; i &#8211; 1) * 6) &amp; 0x3F);<\/p>\n<p>++dest;<\/p>\n<p>}<\/p>\n<p>sour = sour + 2;<\/p>\n<p>}<\/p>\n<p>else<\/p>\n<p>if (bytes == 2 || bytes == 3)<\/p>\n<p>{<\/p>\n<p>value = unicode[sour];<\/p>\n<p>utf8[dest] = (0xFF &lt;&lt; (8 &#8211; bytes)) | (value &gt;&gt; ((bytes &#8211; 1) * 6));<\/p>\n<p>++dest;<\/p>\n<p>for (int i = 1; i &lt; bytes; ++i) {<\/p>\n<p>utf8[dest] = 0x80 | (value &gt;&gt; ((bytes &#8211; i &#8211; 1) * 6) &amp; 0x3F);<\/p>\n<p>++dest;<\/p>\n<p>}<\/p>\n<p>++sour;<\/p>\n<p>}<\/p>\n<p>else<\/p>\n<p>if (bytes &gt;= 4)<\/p>\n<p>{<\/p>\n<p>value = (unicode[sour + 1] &lt;&lt; 16) | unicode[sour];<\/p>\n<p>utf8[dest] = (0xFF &lt;&lt; (8 &#8211; bytes)) | (value &gt;&gt; ((bytes &#8211; 1) * 6));<\/p>\n<p>++dest;<\/p>\n<p>for (int i = 1; i &lt; bytes; ++i) {<\/p>\n<p>utf8[dest] = 0x80 | (value &gt;&gt; ((bytes &#8211; i &#8211; 1) * 6) &amp; 0x3F);<\/p>\n<p>++dest;<\/p>\n<p>}<\/p>\n<p>sour = sour + 2;<\/p>\n<p>}<\/p>\n<p>}<\/p>\n<p>utf8[dest] = NULL;<\/p>\n<p>return dest;<\/p>\n<p>}<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p>utf8 \u8f49 unicode<\/p>\n<table>\n<tbody>\n<tr>\n<td width=\"553\">\u00a0int UTF8ToUnicode(wchar_t * unicode, const char* utf8)<\/p>\n<p>{<\/p>\n<p>int utf8Length;<\/p>\n<p>int sour, dest;<\/p>\n<p>int bytes;<\/p>\n<p>dest = sour = 0;<\/p>\n<p>DWORD value;<\/p>\n<p>BYTE v;<\/p>\n<p>utf8Length = strlen(utf8);<\/p>\n<p>while (sour &lt; utf8Length)<\/p>\n<p>{<\/p>\n<p>if ((utf8[sour] &amp; 0x80) == 0x00)<\/p>\n<p>bytes = 1;<\/p>\n<p>else<\/p>\n<p>if ((utf8[sour] &amp; 0xE0) == 0xC0)<\/p>\n<p>bytes = 2;<\/p>\n<p>else<\/p>\n<p>if ((utf8[sour] &amp; 0xF0) == 0xE0)<\/p>\n<p>bytes = 3;<\/p>\n<p>else<\/p>\n<p>if ((utf8[sour] &amp; 0xF8) == 0xF0)<\/p>\n<p>bytes = 4;<\/p>\n<p>else<\/p>\n<p>if ((utf8[sour] &amp; 0xFC) == 0xF8)<\/p>\n<p>bytes = 5;<\/p>\n<p>else<\/p>\n<p>if ((utf8[sour] &amp; 0xFE) == 0xFC)<\/p>\n<p>bytes = 6;<\/p>\n<p>else<\/p>\n<p>bytes = 7;<\/p>\n<p>if (bytes == 1)<\/p>\n<p>{<\/p>\n<p>unicode[dest] = utf8[sour];<\/p>\n<p>++dest;<\/p>\n<p>++sour;<\/p>\n<p>}<\/p>\n<p>else<\/p>\n<p>if (bytes == 2 || bytes == 3)<\/p>\n<p>{<\/p>\n<p>value = utf8[sour] &amp; (0xFF &gt;&gt; (bytes + 1));<\/p>\n<p>++sour;<\/p>\n<p>for (int i = 1; i &lt; bytes; ++i) {<\/p>\n<p>value = value &lt;&lt; 6;<\/p>\n<p>value = value | (utf8[sour] &amp; 0x3f);<\/p>\n<p>++sour;<\/p>\n<p>}<\/p>\n<p>&nbsp;<\/p>\n<p>v = (value &gt;&gt; 24) &amp; 0xFF;<\/p>\n<p>unicode[dest] = v;<\/p>\n<p>v = (value &gt;&gt; 16) &amp; 0xFF;<\/p>\n<p>if (v != 0) {<\/p>\n<p>unicode[dest] = (unicode[dest] &lt;&lt; 8) + v;<\/p>\n<p>++dest;<\/p>\n<p>}<\/p>\n<p>&nbsp;<\/p>\n<p>v = (value &gt;&gt; 8) &amp; 0xFF;<\/p>\n<p>unicode[dest] = v;<\/p>\n<p>v = value &amp; 0xFF;<\/p>\n<p>if (v != 0) {<\/p>\n<p>unicode[dest] = (unicode[dest] &lt;&lt; 8) + v;<\/p>\n<p>++dest;<\/p>\n<p>}<\/p>\n<p>}<\/p>\n<p>else<\/p>\n<p>if (bytes &gt;= 4 )<\/p>\n<p>{<\/p>\n<p>value = utf8[sour] &amp; (0xFF &gt;&gt; (bytes + 1));<\/p>\n<p>++sour;<\/p>\n<p>for (int i = 1; i &lt; bytes; ++i) {<\/p>\n<p>value = value &lt;&lt; 6;<\/p>\n<p>value = value | (utf8[sour] &amp; 0x3f);<\/p>\n<p>++sour;<\/p>\n<p>}<\/p>\n<p>value = value &#8211; 0x10000;<\/p>\n<p>unicode[dest] = 0xD800 | ((value &gt;&gt; 10) &amp; 0x3ff );<\/p>\n<p>unicode[dest+1] = 0xDC00 | ((value) &amp; 0x3ff);<\/p>\n<p>dest = dest + 2;<\/p>\n<p>}<\/p>\n<p>}<\/p>\n<p>&nbsp;<\/p>\n<p>unicode[dest] = NULL;<\/p>\n<p>return dest;<\/p>\n<p>}<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p>&nbsp;<\/p>\n","protected":false},"excerpt":{"rendered":"<p>\u4fc2\u96fb\u8166\u767c\u5c55\u521d\u6642.\u5b9a\u7fa9\u5de6\u5957\u300eASCII\u78bc\u300f,\u5f97128\u5b57\u7b26,\u82f1\u6587\u52a0\u6578\u5b57\u7528\u55ae\u5b57\u7bc0BYTE. \u5f8c\u849e\u5404\u570b\u7686\u81ea\u5b9a\u300e\u5b57\u7b26\u7de8\u78bc &hellip; <\/p>\n<p class=\"link-more\"><a href=\"https:\/\/www.bookcard.net\/wordpress\/unicode_utf8\/\" class=\"more-link\">\u7e7c\u7e8c\u95b1\u8b80 <span class=\"screen-reader-text\">UNICODE-UTF8\u8f49\u63db<\/span><\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[13],"tags":[42],"class_list":["post-17118","post","type-post","status-publish","format-standard","hentry","category-pc","tag-computer","entry"],"amp_enabled":true,"_links":{"self":[{"href":"https:\/\/www.bookcard.net\/wordpress\/wp-json\/wp\/v2\/posts\/17118","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.bookcard.net\/wordpress\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.bookcard.net\/wordpress\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.bookcard.net\/wordpress\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.bookcard.net\/wordpress\/wp-json\/wp\/v2\/comments?post=17118"}],"version-history":[{"count":2,"href":"https:\/\/www.bookcard.net\/wordpress\/wp-json\/wp\/v2\/posts\/17118\/revisions"}],"predecessor-version":[{"id":17122,"href":"https:\/\/www.bookcard.net\/wordpress\/wp-json\/wp\/v2\/posts\/17118\/revisions\/17122"}],"wp:attachment":[{"href":"https:\/\/www.bookcard.net\/wordpress\/wp-json\/wp\/v2\/media?parent=17118"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.bookcard.net\/wordpress\/wp-json\/wp\/v2\/categories?post=17118"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.bookcard.net\/wordpress\/wp-json\/wp\/v2\/tags?post=17118"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}