\u5211\u6cd5\u3084\u5730\u65b9\u81ea\u6cbb\u6cd5\u7b49\u306e\u6761\u6587\u306e\u6a5f\u68b0\u5b66\u7fd2\u3092AI\u304c\u3057\u3066\u304f\u308c\u306a\u3044\u306e\u306f\u3001Ngram\u306e\u30d9\u30af\u30c8\u30eb\u5316\u306e\u5f71\u97ff\u306a\u306e\u304b\u5b9a\u304b\u3067\u306a\u3044\u304c\u3001\u3068\u308a\u3042\u3048\u305a\u6761\u6587\u306e\u6f22\u6570\u5b57\u3092\u5909\u63db\u3059\u308b\u30d7\u30ed\u30b0\u30e9\u30e0\u3092\u4f5c\u6210\u3057\u30ca\u30ec\u30c3\u30b8\u30d9\u30fc\u30b9\u306b\u3076\u3061\u8fbc\u3080\u3053\u3068\u306b\u3057\u307e\u3057\u305f\u3002<\/p>\n
php\u306e\u6f22\u6570\u5b57\u5909\u63db\u30d7\u30ed\u30b0\u30e9\u30e0:kanjinum.php\u306f\u4ee5\u4e0b\u3002
\n(Usage:php kanjinum.php \u5211\u6cd5.html > \u5211\u6cd5_\u6f22\u6570\u5b57\u5909\u63db.html)<\/p>\n
\r\n<?php\r\nif (!function_exists('mb_str_split')) {\r\n function mb_str_split($string, $length = 1, $encoding = 'UTF-8') {\r\n $result = [];\r\n $strlen = mb_strlen($string, $encoding);\r\n for ($i = 0; $i < $strlen; $i += $length) {\r\n $result[] = mb_substr($string, $i, $length, $encoding);\r\n }\r\n return $result;\r\n }\r\n}\r\n\r\n\/\/ \u6f22\u6570\u5b57 \u2192 \u6570\u5b57\u5909\u63db\u95a2\u6570\uff08\u7c21\u6613\u7248\uff09\r\nfunction kanjiToNumber($kanji) {\r\n $nums = ['\u3007'=>0, '\u4e00'=>1, '\u4e8c'=>2, '\u4e09'=>3, '\u56db'=>4, '\u4e94'=>5, '\u516d'=>6, '\u4e03'=>7, '\u516b'=>8, '\u4e5d'=>9];\r\n $units = ['\u5341'=>10, '\u767e'=>100, '\u5343'=>1000];\r\n $largeUnits = ['\u4e07'=>10000, '\u5104'=>100000000];\r\n\r\n \/\/ mb_str_split \u306e\u4ee3\u66ff\r\n if (!function_exists('mb_str_split')) {\r\n function mb_str_split($string, $length = 1, $encoding = 'UTF-8') {\r\n $result = [];\r\n $strlen = mb_strlen($string, $encoding);\r\n for ($i = 0; $i < $strlen; $i += $length) {\r\n $result[] = mb_substr($string, $i, $length, $encoding);\r\n }\r\n return $result;\r\n }\r\n }\r\n\r\n $chars = mb_str_split($kanji);\r\n $result = 0;\r\n $section = 0;\r\n $number = 0;\r\n\r\n foreach ($chars as $char) {\r\n if (isset($nums[$char])) {\r\n $number = $nums[$char];\r\n } elseif (isset($units[$char])) {\r\n $unit = $units[$char];\r\n if ($number === 0) $number = 1;\r\n $section += $number * $unit;\r\n $number = 0;\r\n } elseif (isset($largeUnits[$char])) {\r\n $unit = $largeUnits[$char];\r\n if ($number === 0 && $section === 0) $section = 1;\r\n $result += ($section + $number) * $unit;\r\n $section = 0;\r\n $number = 0;\r\n } else {\r\n \/\/ \u672a\u77e5\u306e\u6587\u5b57\u306f\u7121\u8996\r\n }\r\n }\r\n\r\n $result += $section + $number;\r\n return $result;\r\n}\r\n\r\n\/\/ \u30b3\u30de\u30f3\u30c9\u30e9\u30a4\u30f3\u5f15\u6570\u304b\u3089\u30d5\u30a1\u30a4\u30eb\u30d1\u30b9\u53d6\u5f97\r\nif ($argc < 2) {\r\n fwrite(STDERR, \"Usage: php convert.php \\n\");\r\n exit(1);\r\n}\r\n\r\n$filePath = $argv[1];\r\n\r\n\/\/ \u30d5\u30a1\u30a4\u30eb\u5b58\u5728\u30c1\u30a7\u30c3\u30af\r\nif (!file_exists($filePath)) {\r\n fwrite(STDERR, \"Error: File not found - $filePath\\n\");\r\n exit(1);\r\n}\r\n\r\n\/\/ HTML\u30d5\u30a1\u30a4\u30eb\u8aad\u307f\u8fbc\u307f\r\n$html = file_get_contents($filePath);\r\n\r\n\/\/ \u6f22\u6570\u5b57\u3092\u691c\u51fa\u3057\u3066\u5909\u63db\r\n$convertedHtml = preg_replace_callback('\/[\u3007\u4e00\u4e8c\u4e09\u56db\u4e94\u516d\u4e03\u516b\u4e5d\u5341\u767e\u5343\u4e07]+\/u', function($matches) {\r\n return kanjiToNumber($matches[0]);\r\n}, $html);\r\n\r\n\/\/ \u6a19\u6e96\u51fa\u529b\u306b\u8868\u793a\r\necho $convertedHtml;\r\n?>\r\n<\/pre>\n","protected":false},"excerpt":{"rendered":"\u5211\u6cd5\u3084\u5730\u65b9\u81ea\u6cbb\u6cd5\u7b49\u306e\u6761\u6587\u306e\u6a5f\u68b0\u5b66\u7fd2\u3092AI\u304c\u3057\u3066\u304f\u308c\u306a\u3044\u306e\u306f\u3001Ngram\u306e\u30d9\u30af\u30c8\u30eb … \u7d9a\u304d\u3092\u8aad\u3080