{"id":672,"date":"2023-03-23T14:37:57","date_gmt":"2023-03-23T06:37:57","guid":{"rendered":"http:\/\/www.inhhh.com\/blog\/?p=672"},"modified":"2023-03-23T14:37:57","modified_gmt":"2023-03-23T06:37:57","slug":"cunicode-%e5%92%8c-utf-8-%e7%9a%84%e8%bd%ac%e6%8d%a2","status":"publish","type":"post","link":"http:\/\/www.inhhh.com\/blog\/?p=672","title":{"rendered":"C++Unicode \u548c UTF-8 \u7684\u8f6c\u6362"},"content":{"rendered":"\n<p>\u4ee3\u7801\u6458\u6284\u4e8e Stack Overflow<\/p>\n\n\n\n<p>\u8fde\u63a5\uff1ahttps:\/\/stackoverflow.com\/questions\/12015571\/how-to-print-unicode-character-in-c<\/p>\n\n\n\n<p>\u6211\u4e00\u5f00\u59cb\u7684\u9700\u6c42\u662f\u9700\u8981\u5728\u63a7\u5236\u53f0\u6253\u5370\u8fdb\u5ea6\uff0c\u7528\u8fde\u7eed\u7684\u5b9e\u5fc3\u6b63\u65b9\u5f62\u6765\u6a21\u62df\u8fdb\u5ea6\uff0c\u6240\u4ee5\u5c31\u60f3\u6253\u5370\u6b63\u65b9\u5f62\uff082588\uff09\uff0c\u6240\u4ee5\u5c31\u627e\u5230\u4e86\u8fd9\u4e2a\u5e16\u5b50\uff0c\u987a\u4fbf\u9644\u4e0a\u6253\u5370\u5b9e\u5fc3\u6b63\u65b9\u5f62\u7684\u4ee3\u7801\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>std::cout &lt;&lt; \"\\u2588\" &lt;&lt; std::endl;<\/code><\/pre>\n\n\n\n<p>\u4ee5\u4e0b\u662f\u4e00\u4e9b\u8f6c\u6362\u4ee3\u7801\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>\r\n#include &lt;iostream>\n\nusing namespace std;\n\n\nint utf8_to_unicode(string utf8_code);\nstring unicode_to_utf8(int unicode);\n\n\nint main() {\n    cout &lt;&lt; unicode_to_utf8(36) &lt;&lt; '\\t';\n    cout &lt;&lt; unicode_to_utf8(162) &lt;&lt; '\\t';\n    cout &lt;&lt; unicode_to_utf8(8364) &lt;&lt; '\\t';\n    cout &lt;&lt; unicode_to_utf8(128578) &lt;&lt; endl;\n\n    cout &lt;&lt; unicode_to_utf8(0x24) &lt;&lt; '\\t';\n    cout &lt;&lt; unicode_to_utf8(0xa2) &lt;&lt; '\\t';\n    cout &lt;&lt; unicode_to_utf8(0x20ac) &lt;&lt; '\\t';\n    cout &lt;&lt; unicode_to_utf8(0x1f642) &lt;&lt; endl;\n\n    cout &lt;&lt; utf8_to_unicode(\"$\") &lt;&lt; '\\t';\n    cout &lt;&lt; utf8_to_unicode(\"\u00a2\") &lt;&lt; '\\t';\n    cout &lt;&lt; utf8_to_unicode(\"\u20ac\") &lt;&lt; '\\t';\n    cout &lt;&lt; utf8_to_unicode(\"?\") &lt;&lt; endl;\n\n    cout &lt;&lt; utf8_to_unicode(\"\\x24\") &lt;&lt; '\\t';\n    cout &lt;&lt; utf8_to_unicode(\"\\xc2\\xa2\") &lt;&lt; '\\t';\n    cout &lt;&lt; utf8_to_unicode(\"\\xe2\\x82\\xac\") &lt;&lt; '\\t';\n    cout &lt;&lt; utf8_to_unicode(\"\\xf0\\x9f\\x99\\x82\") &lt;&lt; endl;\n\n    return 0;\n}\n\nint utf8_to_unicode(string utf8_code) {\n    unsigned utf8_size = utf8_code.length();\n    int unicode = 0;\n\n    for (unsigned p = 0; p &lt; utf8_size; ++p) {\n        int bit_count = (p ? 6 : 8 - utf8_size - (utf8_size == 1 ? 0 : 1)),\n            shift = (p &lt; utf8_size - 1 ? (6 * (utf8_size - p - 1)) : 0);\n\n        for (int k = 0; k &lt; bit_count; ++k)\n            unicode += ((utf8_code&#91;p] &amp; (1 &lt;&lt; k)) &lt;&lt; shift);\n    }\n\n    return unicode;\n}\n\nstring unicode_to_utf8(int unicode) {\n    string s;\n\n    if (unicode >= 0 and unicode &lt;= 0x7f) { \/\/ 7F(16) = 127(10)\n        s = static_cast&lt;char>(unicode);\n\n        return s;\n    } else if (unicode &lt;= 0x7ff) { \/\/ 7FF(16) = 2047(10)\n        unsigned char c1 = 192, c2 = 128;\n\n        for (int k = 0; k &lt; 11; ++k) {\n            if (k &lt; 6)  c2 |= (unicode % 64) &amp; (1 &lt;&lt; k);\n            else c1 |= (unicode >> 6) &amp; (1 &lt;&lt; (k - 6));\n        }\n\n        s = c1;    s += c2;\n\n        return s;\n    } else if (unicode &lt;= 0xffff) { \/\/ FFFF(16) = 65535(10)\n        unsigned char c1 = 224, c2 = 128, c3 = 128;\n\n        for (int k = 0; k &lt; 16; ++k) {\n            if (k &lt; 6)  c3 |= (unicode % 64) &amp; (1 &lt;&lt; k);\n            else if (k &lt; 12) c2 |= (unicode >> 6) &amp; (1 &lt;&lt; (k - 6));\n            else c1 |= (unicode >> 12) &amp; (1 &lt;&lt; (k - 12));\n        }\n\n        s = c1;    s += c2;    s += c3;\n\n        return s;\n    } else if (unicode &lt;= 0x1fffff) { \/\/ 1FFFFF(16) = 2097151(10)\n        unsigned char c1 = 240, c2 = 128, c3 = 128, c4 = 128;\n\n        for (int k = 0; k &lt; 21; ++k) {\n            if (k &lt; 6)  c4 |= (unicode % 64) &amp; (1 &lt;&lt; k);\n            else if (k &lt; 12) c3 |= (unicode >> 6) &amp; (1 &lt;&lt; (k - 6));\n            else if (k &lt; 18) c2 |= (unicode >> 12) &amp; (1 &lt;&lt; (k - 12));\n            else c1 |= (unicode >> 18) &amp; (1 &lt;&lt; (k - 18));\n        }\n\n        s = c1;    s += c2;    s += c3;    s += c4;\n\n        return s;\n    } else if (unicode &lt;= 0x3ffffff) { \/\/ 3FFFFFF(16) = 67108863(10)\n        ;  \/\/ actually, there are no 5-bytes unicodes\n    } else if (unicode &lt;= 0x7fffffff) { \/\/ 7FFFFFFF(16) = 2147483647(10)\n        ;  \/\/ actually, there are no 6-bytes unicodes\n    } else  ; \/\/ incorrect unicode (&lt; 0 or > 2147483647)\n\n    return \"\";\n}\r\n<\/code><\/pre>\n","protected":false},"excerpt":{"rendered":"<p>\u4ee3\u7801\u6458\u6284\u4e8e Stack Overflow \u8fde\u63a5\uff1ahttps:\/\/stackoverflow.com\/quest<\/p>\n<div class=\"more-link\">\n\t\t\t\t <a href=\"http:\/\/www.inhhh.com\/blog\/?p=672\" class=\"link-btn theme-btn\"><span>Read More <\/span> <i class=\"fa fa-caret-right\"><\/i><\/a>\n\t\t\t<\/div>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[],"class_list":["post-672","post","type-post","status-publish","format-standard","hentry","category-uncategorized"],"_links":{"self":[{"href":"http:\/\/www.inhhh.com\/blog\/index.php?rest_route=\/wp\/v2\/posts\/672","targetHints":{"allow":["GET"]}}],"collection":[{"href":"http:\/\/www.inhhh.com\/blog\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/www.inhhh.com\/blog\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/www.inhhh.com\/blog\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"http:\/\/www.inhhh.com\/blog\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=672"}],"version-history":[{"count":1,"href":"http:\/\/www.inhhh.com\/blog\/index.php?rest_route=\/wp\/v2\/posts\/672\/revisions"}],"predecessor-version":[{"id":673,"href":"http:\/\/www.inhhh.com\/blog\/index.php?rest_route=\/wp\/v2\/posts\/672\/revisions\/673"}],"wp:attachment":[{"href":"http:\/\/www.inhhh.com\/blog\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=672"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/www.inhhh.com\/blog\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=672"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/www.inhhh.com\/blog\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=672"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}