UTF-8 입력이 예상되는 아래 코드 줄을 사용할 수 있습니다.
$chr_map = array(
// Windows codepage 1252
"\xC2\x82" => "'", // U+0082⇒U+201A single low-9 quotation mark
"\xC2\x84" => '"', // U+0084⇒U+201E double low-9 quotation mark
"\xC2\x8B" => "'", // U+008B⇒U+2039 single left-pointing angle quotation mark
"\xC2\x91" => "'", // U+0091⇒U+2018 left single quotation mark
"\xC2\x92" => "'", // U+0092⇒U+2019 right single quotation mark
"\xC2\x93" => '"', // U+0093⇒U+201C left double quotation mark
"\xC2\x94" => '"', // U+0094⇒U+201D right double quotation mark
"\xC2\x9B" => "'", // U+009B⇒U+203A single right-pointing angle quotation mark
// Regular Unicode // U+0022 quotation mark (")
// U+0027 apostrophe (')
"\xC2\xAB" => '"', // U+00AB left-pointing double angle quotation mark
"\xC2\xBB" => '"', // U+00BB right-pointing double angle quotation mark
"\xE2\x80\x98" => "'", // U+2018 left single quotation mark
"\xE2\x80\x99" => "'", // U+2019 right single quotation mark
"\xE2\x80\x9A" => "'", // U+201A single low-9 quotation mark
"\xE2\x80\x9B" => "'", // U+201B single high-reversed-9 quotation mark
"\xE2\x80\x9C" => '"', // U+201C left double quotation mark
"\xE2\x80\x9D" => '"', // U+201D right double quotation mark
"\xE2\x80\x9E" => '"', // U+201E double low-9 quotation mark
"\xE2\x80\x9F" => '"', // U+201F double high-reversed-9 quotation mark
"\xE2\x80\xB9" => "'", // U+2039 single left-pointing angle quotation mark
"\xE2\x80\xBA" => "'", // U+203A single right-pointing angle quotation mark
);
$char_val = array_keys ($chr_map); // but: for efficiency you should
$rpl = array_values($chr_map); // pre-calculate these two arrays
$str = str_replace($char_val, $rpl, html_entity_decode($str, ENT_QUOTES, "UTF-8")); 설명
모든 유니코드 문자는 정확히 하나의 "일반 범주"에 속합니다.
이 중 인용 문자를 포함할 수 있는 것은 -
Ps "Punctuation, Open" Pe "Punctuation, Close" Pi "Punctuation, Initial quote (might behave like Ps or Pe depending on its usage)" Pf "Punctuation, Final quote (might behave like Ps or Pe depending on its usage)" Po "Punctuation, Other"
사용자가 UTF-8로 인코딩된 입력에 대해 확신하지 못하는 경우 다른 작업을 수행하기 전에 아래 코드를 배치할 수 있습니다. -
if ( !preg_match('/^\\X*$/u', $str)) {
$str = utf8_encode($str);
} 데이터를 0x80-0x9F 범위에서 정규화해야 하는 경우 아래 코드를 사용할 수 있습니다. -
$normalization_map = array( "\xC2\x80" => "\xE2\x82\xAC", // U+20AC Euro sign "\xC2\x82" => "\xE2\x80\x9A", // U+201A single low-9 quotation mark "\xC2\x83" => "\xC6\x92", // U+0192 latin small letter f with hook "\xC2\x84" => "\xE2\x80\x9E", // U+201E double low-9 quotation mark "\xC2\x85" => "\xE2\x80\xA6", // U+2026 horizontal ellipsis "\xC2\x86" => "\xE2\x80\xA0", // U+2020 dagger "\xC2\x87" => "\xE2\x80\xA1", // U+2021 double dagger "\xC2\x88" => "\xCB\x86", // U+02C6 modifier letter circumflex accent "\xC2\x89" => "\xE2\x80\xB0", // U+2030 per mille sign "\xC2\x8A" => "\xC5\xA0", // U+0160 latin capital letter s with caron "\xC2\x8B" => "\xE2\x80\xB9", // U+2039 single left-pointing angle quotation mark "\xC2\x8C" => "\xC5\x92", // U+0152 latin capital ligature oe "\xC2\x8E" => "\xC5\xBD", // U+017D latin capital letter z with caron "\xC2\x91" => "\xE2\x80\x98", // U+2018 left single quotation mark "\xC2\x92" => "\xE2\x80\x99", // U+2019 right single quotation mark "\xC2\x93" => "\xE2\x80\x9C", // U+201C left double quotation mark "\xC2\x94" => "\xE2\x80\x9D", // U+201D right double quotation mark "\xC2\x95" => "\xE2\x80\xA2", // U+2022 bullet "\xC2\x96" => "\xE2\x80\x93", // U+2013 en dash "\xC2\x97" => "\xE2\x80\x94", // U+2014 em dash "\xC2\x98" => "\xCB\x9C", // U+02DC small tilde "\xC2\x99" => "\xE2\x84\xA2", // U+2122 trade mark sign "\xC2\x9A" => "\xC5\xA1", // U+0161 latin small letter s with caron "\xC2\x9B" => "\xE2\x80\xBA", // U+203A single right-pointing angle quotation mark "\xC2\x9C" => "\xC5\x93", // U+0153 latin small ligature oe "\xC2\x9E" => "\xC5\xBE", // U+017E latin small letter z with caron "\xC2\x9F" => "\xC5\xB8", // U+0178 latin capital letter y with diaeresis ); $chr = array_keys ($normalization_map); // but: for efficiency you should $rpl = array_values($normalization_map); // pre-calculate these two arrays $str = str_replace($chr, $rpl, $str);