{"id":207898,"date":"2025-07-08T08:23:19","date_gmt":"2025-07-08T00:23:19","guid":{"rendered":"https:\/\/server.hk\/cnblog\/207898\/"},"modified":"2025-07-08T08:23:19","modified_gmt":"2025-07-08T00:23:19","slug":"%e4%bd%bf%e7%94%a8-bufio-newscanner-%e9%80%90%e8%a1%8c%e8%af%bb%e5%8f%96%e6%96%87%e4%bb%b6%e6%97%b6%e5%87%ba%e7%8e%b0%e6%80%a7%e8%83%bd%e9%97%ae%e9%a2%98","status":"publish","type":"post","link":"https:\/\/server.hk\/cnblog\/207898\/","title":{"rendered":"\u4f7f\u7528 bufio.NewScanner \u9010\u884c\u8bfb\u53d6\u6587\u4ef6\u65f6\u51fa\u73b0\u6027\u80fd\u95ee\u9898"},"content":{"rendered":"<p><b><\/b> <\/p>\n<p>\u5f53\u524d\u4f4d\u7f6e\uff1a <span>&gt;<\/span> <span>&gt;<\/span> <span>&gt;<\/span> <span>&gt;<\/span> <span>\u4f7f\u7528 bufio.NewScanner \u9010\u884c\u8bfb\u53d6\u6587\u4ef6\u65f6\u51fa\u73b0\u6027\u80fd\u95ee\u9898<\/span><\/p>\n<p><span>\u6765\u6e90\uff1astackoverflow<\/span><br \/>\n<span>2024-04-26 15:54:35<\/span><br \/>\n<span><i><\/i>0\u6d4f\u89c8<\/span><br \/>\n<span style=\"cursor: pointer\"><i><\/i>\u6536\u85cf<\/span> <\/p>\n<p>\u672c\u7bc7\u6587\u7ae0\u5411\u5927\u5bb6\u4ecb\u7ecd\u300a\u4f7f\u7528 bufio.NewScanner \u9010\u884c\u8bfb\u53d6\u6587\u4ef6\u65f6\u51fa\u73b0\u6027\u80fd\u95ee\u9898\u300b\uff0c\u4e3b\u8981\u5305\u62ec\uff0c\u5177\u6709\u4e00\u5b9a\u7684\u53c2\u8003\u4ef7\u503c\uff0c\u9700\u8981\u7684\u670b\u53cb\u53ef\u4ee5\u53c2\u8003\u4e00\u4e0b\u3002<\/p>\n<p> \u95ee\u9898\u5185\u5bb9<br \/>\n <\/p>\n<p>\u6211\u6b63\u5728\u5b66\u4e60\u5982\u4f55\u5728 go \u4e2d\u6709\u6548\u5730\u8bfb\u53d6\u975e\u5e38\u5927\u7684\u6587\u4ef6\u3002\u6211\u5c1d\u8bd5\u8fc7 <code>bufio.newscanner<\/code> \u548c <code>bufio.newreader<\/code> \u4e0e <code>readstring('\\n')<\/code> \u3002\u5728\u8fd9\u4e24\u4e2a\u9009\u9879\u4e2d\uff0c<code>newscanner<\/code> \u4f3c\u4e4e\u59cb\u7ec8\u66f4\u5feb (2:1)\u3002<\/p>\n<p>\u5bf9\u4e8e <code>newscanner<\/code>\uff0c\u6211\u53d1\u73b0\u9010\u884c\u8bfb\u53d6\u6587\u4ef6\u6bd4\u8fd0\u884c unix cat \u547d\u4ee4\u8bfb\u53d6\u6587\u4ef6\u82b1\u8d39\u66f4\u591a\u65f6\u95f4\u3002<\/p>\n<p>\u6211\u6d4b\u91cf\u4e86\u8fd0\u884c\u6b64\u4ee3\u7801\u9700\u8981\u591a\u957f\u65f6\u95f4\uff1a<\/p>\n<pre>package main\n\nimport (\n    \"bufio\"\n    \"fmt\"\n    \"os\"\n)\n\nfunc main() {\n\n     file, _ := os.open(\"test\")\n     scanner := bufio.newscanner(file)\n     for scanner.scan() {\n        fmt.println(scanner.text())\n     }\n\n}\n<\/pre>\n<p>\u5f53\u60a8\u4e0e\u5e38\u89c4 unix <code>cat<\/code> \u8f93\u51fa\u8fdb\u884c\u6bd4\u8f83\u65f6\uff0c\u6211\u5f97\u5230\u4ee5\u4e0b\u7ed3\u679c\uff1a<\/p>\n<pre>$ time .\/parser3 &gt; \/dev\/null\n       19.13 real        13.81 user         5.94 sys\n$ time cat test &gt; \/dev\/null\n        0.83 real         0.08 user         0.74 sys<\/pre>\n<p>\u591a\u6b21\u6267\u884c\u7684\u65f6\u95f4\u5dee\u662f\u4e00\u81f4\u7684\u3002<\/p>\n<p>\u6211\u77e5\u9053\u626b\u63cf <code>'\\n'<\/code> \u4f1a\u589e\u52a0\u5f00\u9500\uff0c\u800c\u4e0d\u662f\u50cf cat \u90a3\u6837\u53ea\u662f\u5c06\u6570\u636e\u4ece\u8f93\u5165\u590d\u5236\u5230\u8f93\u51fa\u3002<\/p>\n<p>\u4f46\u662f\u770b\u5230 <code>cat<\/code> \u548c\u6b64\u4ee3\u7801\u7247\u6bb5\u4e4b\u95f4\u7684\u533a\u522b\uff0c\u6211\u95ee\u81ea\u5df1\u8fd9\u662f\u5426\u662f\u5728 go \u4e2d\u9010\u884c\u8bfb\u53d6\u6587\u4ef6\u7684\u6700\u6709\u6548\u65b9\u6cd5\u3002<\/p>\n<p> <\/p>\n<h2>\u89e3\u51b3\u65b9\u6848<\/h2>\n<p> <\/p>\n<p>\u6839\u636e muffintop \u7684\u8bc4\u8bba\uff0c\u8fd9\u662f\u63d0\u9ad8\u901f\u5ea6\u7684\u4ee3\u7801\u7247\u6bb5\u3002\u6027\u80fd\u635f\u5931\u4e0e scanner \u7684\u4f7f\u7528\u65e0\u5173\uff0c\u800c\u662f\u4e0e\u4ee5\u4e0b\u4e8b\u5b9e\u6709\u5173\uff1a<\/p>\n<ol>\n<li>\u5728\u8f93\u51fa\u4e2d\u4e0d\u4f7f\u7528\u7f13\u51b2<\/li>\n<li>\u4f7f\u7528 <code>scanner.text()<\/code>\uff08\u5206\u914d\u5b57\u7b26\u4e32\uff09\u800c\u4e0d\u662f <code>scanner.bytes()<\/code><\/li>\n<\/ol>\n<p><strong>\u6dfb\u52a0\u8f93\u51fa\u7f13\u51b2\u7684\u6027\u80fd\uff1a<\/strong><\/p>\n<pre>package main\n\nimport (\n    \"bufio\"\n    \"fmt\"\n    \"os\"\n)\n\nfunc main() {\n\n     file, _ := os.open(\"test\")\n     w := bufio.newwriter(os.stdout) \n     scanner := bufio.newscanner(file)\n     for scanner.scan() {\n        fmt.fprintln(w, scanner.text())\n     }\n\n}\n<\/pre>\n<p>\u4e0a\u8ff0\u89e3\u51b3\u65b9\u6848\u4f7f\u7528\u8f93\u51fa\u7f13\u51b2\uff0c\u9700\u8981 6.6 \u79d2\uff0c\u800c\u539f\u6765\u9700\u8981 19.1 \u79d2<\/p>\n<p><strong>\u6dfb\u52a0\u8f93\u51fa\u7f13\u51b2\u5e76\u4f7f\u7528 <code>.bytes()<\/code> \u800c\u4e0d\u662f <code>.text()<\/code> \u8f93\u51fa\u7684\u6027\u80fd\uff1a<\/strong><\/p>\n<pre>package main\n\nimport (\n    \"bufio\"\n    \"fmt\"\n    \"os\"\n)\n\nfunc main() {\n\n     file, _ := os.open(\"test\")\n     w := bufio.newwriter(os.stdout) \n     scanner := bufio.newscanner(file)\n     for scanner.scan() {\n        w.write(scanner.bytes()); w.writebyte('\\n')\n     }\n\n}\n<\/pre>\n<p>\u4e0a\u8ff0\u89e3\u51b3\u65b9\u6848\u4f7f\u7528\u8f93\u51fa\u7f13\u51b2\u5e76\u4ece\u626b\u63cf\u4eea\u8f93\u51fa\u5b57\u8282\uff0c\u9700\u8981 2.2 \u79d2\uff0c\u800c\u539f\u6765\u9700\u8981 19.1 \u79d2\u3002<\/p>\n<p>\u9996\u5148\u8003\u8651\u60a8\u5c06\u8bfb\u53d6 csv\u3001json \u7684\u6570\u636e\u7c7b\u578b\uff0c\u4ee5\u53ca\u8bfb\u53d6\u7684\u7cfb\u7edf\u5c06\u4f1a\u9605\u8bfb\u5b83\uff0c\u4e3a\u4ec0\u4e48\uff1f\u5fc5\u987b\u8003\u8651\u6240\u6709\u8fd9\u4e9b\u7ec6\u8282\u3002\u6ca1\u6709\u4e00\u79cd\u65b9\u6cd5\u9002\u5408\u6240\u6709\u60c5\u51b5\uff0c\u6700\u597d\u7684\u5f00\u53d1\u4eba\u5458\u77e5\u9053\u5982\u4f55\u4f7f\u7528 <code>right \u5de5\u5177 <\/code> \u6765\u5b8c\u6210 <code>job<\/code>\u3002\u5982\u679c\u4e0d\u77e5\u9053\u5185\u5b58\u9650\u5236\u3001\u6570\u636e\u7b49\uff0c\u5c31\u4e0d\u6e05\u695a\u3002\u6211\u4eec\u4f1a\u4ece\u670d\u52a1\u5668\u8bfb\u53d6\u5927\u91cf json \u5417\uff1f\u6216\u8005\u6211\u4eec\u4f1a\u89e3\u6790\u4e00\u4e2a\u5c0f\u6587\u672c\u6587\u4ef6\uff0c\u901a\u5e38\u6bcf\u4e2a\u51fd\u6570\u90fd\u6709\u4e00\u4e2a\u76ee\u7684\u3002\u4e0d\u8981\u517b\u6210\u8ba4\u4e3a\u4e00\u79cd\u65b9\u6cd5\u6bd4\u53e6\u4e00\u79cd\u65b9\u6cd5\u66f4\u597d\u6216\u66f4\u5dee\u7684\u4e60\u60ef\uff0c\u4ece\u800c\u9650\u5236\u4f60\u7684\u5b66\u4e60\u548c\u6280\u80fd\u3002<\/p>\n<h3>\u8bfb\u53d6\u6587\u4ef6\u7684\u65b9\u6cd5\u3002<\/h3>\n<ul>\n<li>\u6587\u6863\u89e3\u6790<\/li>\n<li>\u4ece\u6587\u4ef6\u4e2d\u8bfb\u53d6\u6240\u6709\u6570\u636e\u5e76\u5c06\u5176\u8f6c\u6362\u4e3a\u5bf9\u8c61\u3002<\/li>\n<\/ul>\n<ul>\n<li>\u6d41\u89e3\u6790<\/li>\n<li>\u4e00\u6b21\u8bfb\u53d6\u4e00\u4e2a\u5143\u7d20\uff0c\u7136\u540e\u8f6c\u5230\u4e0b\u4e00\u4e2a\u5143\u7d20\u3002<\/li>\n<\/ul>\n<p>\u67d0\u4e9b\u65b9\u6cd5\u53ef\u80fd\u4f1a\u66f4\u5feb\uff0c\u4f46\u5b83\u5c06\u6574\u4e2a\u6587\u4ef6\u8bfb\u53d6\u5230\u5185\u5b58\u4e2d\uff0c\u5982\u679c\u60a8\u7684\u6587\u4ef6\u592a\u5927\u600e\u4e48\u529e\uff1f<\/p>\n<p>\u6216\u8005\u5982\u679c\u60a8\u7684\u6587\u4ef6\u4e0d\u662f\u90a3\u4e48\u5927\uff0c\u8981\u67e5\u627e\u91cd\u590d\u7684\u540d\u79f0\u600e\u4e48\u529e\uff1f\u5982\u679c\u60a8\u9010\u884c\u626b\u63cf\u6587\u4ef6\uff0c \u4e5f\u8bb8\u5982\u679c\u60a8\u6b63\u5728\u641c\u7d22\u591a\u4e2a\u9879\u76ee\uff0c\u9010\u884c\u9605\u8bfb\u662f\u6700\u597d\u7684\u65b9\u6cd5\u5417\uff1f<\/p>\n<p>\u4f60\u5e94\u8be5\u770b\u770b\u8fd9\u7bc7\u6587\u7ae0\u3002\u7279\u522b\u611f\u8c22@schwern\uff0c\u4ed6\u5df2\u7ecf\u5728\u8fd9\u91cc\u56de\u7b54\u4e86\u60a8\u7684\u95ee\u9898\u3002\u4f7f\u7528\u5b57\u8282\u548c\u626b\u63cf\u4eea\u7a0d\u5fae\u5feb\u4e00\u4e9b\u3002\u8bf7\u53c2\u9605\uff1a<\/p>\n<pre>I found that using scanner.Bytes() instead of scanner.Text() improves speed\n slightly on my machine.  bufio's scanner.Bytes() method \ndoesn't allocate any additional memory, whereas Text() creates a string from its buffer.<\/pre>\n<p>\u5230\u8fd9\u91cc\uff0c\u6211\u4eec\u4e5f\u5c31\u8bb2\u5b8c\u4e86\u300a\u4f7f\u7528 bufio.NewScanner \u9010\u884c\u8bfb\u53d6\u6587\u4ef6\u65f6\u51fa\u73b0\u6027\u80fd\u95ee\u9898\u300b\u7684\u5185\u5bb9\u4e86\u3002\u4e2a\u4eba\u8ba4\u4e3a\uff0c\u57fa\u7840\u77e5\u8bc6\u7684\u5b66\u4e60\u548c\u5de9\u56fa\uff0c\u662f\u4e3a\u4e86\u66f4\u597d\u7684\u5c06\u5176\u8fd0\u7528\u5230\u9879\u76ee\u4e2d\uff0c\u6b22\u8fce\u5173\u6ce8\u516c\u4f17\u53f7\uff0c\u5e26\u4f60\u4e86\u89e3\u66f4\u591a\u5173\u4e8e\u7684\u77e5\u8bc6\u70b9\uff01<\/p>\n","protected":false},"excerpt":{"rendered":"<p>\u5f53\u524d\u4f4d\u7f6e\uff1a &gt; &gt; &#46;&#46;&#46;<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[4925],"tags":[],"class_list":["post-207898","post","type-post","status-publish","format-standard","hentry","category-4925"],"_links":{"self":[{"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/posts\/207898","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/comments?post=207898"}],"version-history":[{"count":0,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/posts\/207898\/revisions"}],"wp:attachment":[{"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/media?parent=207898"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/categories?post=207898"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/tags?post=207898"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}