PHP intercepts HTML strings automatically complement HTML tags

The code is as follows

Copy Code

/** * Interception of HTML, and automatic completion of the full closure * @param $html * @param $length * @param $end */ function subhtml ($html, $length) { $result = '; $tagStack = Array (); $len = 0; $contents = Preg_split ("~ (<[^>]+?>) ~si", $html, -1,preg_split_no_empty| Preg_split_delim_capture); foreach ($contents as $tag) { if (Trim ($tag) = = "") &nbsp; Continue if (Preg_match ("~<" ([a-z0-9]+) [^/>]*?/>~si, $tag)) { $result. = $tag; }else if (Preg_match ("~</" ([a-z0-9]+) [^/>]*?>~si, $tag, $match)) { if ($tagStack [count ($tagStack)-1] = = $match [1]) { Array_pop ($tagStack); $result. = $tag; } }else if (Preg_match ("~<" ([a-z0-9]+) [^/>]*?>~si, $tag, $match)) { Array_push ($tagStack, $match [1]); $result. = $tag; }else if (Preg_match ("~<!--. *?-->~si", $tag)) { $result. = $tag; }else{ if ($len + mstrlen ($tag) < $length) { $result. = $tag; $len + + Mstrlen ($tag); }else { $str = msubstr ($tag, 0, $length-$len + 1); $result. = $str; Break } } } while (!empty ($tagStack)) { $result. = ' </'. Array_pop ($tagStack). ' > '; } return&nbsp; $result; } /** * Intercept Chinese strings * @param $string string * @param $start starting position * @param $length length * @param $charset &nbsp; Coding * @param $dot Additional strings */ function Msubstr ($string, $start, $length, $dot = ', $charset = ' UTF-8 ') { $string = Str_replace (' &amp; ', ' &quot; ', ' &lt; ', ' &gt; ', ' &nbsp; '), Array (' & ', ' "', ', ', ' < ', ' > ', '), $string); if (strlen ($string) <= $length) { return $string; } if (Strtolower ($charset) = = ' Utf-8 ') { $n = $tn = $noc = 0; while ($n < strlen ($string)) { $t = Ord ($string [$n]); if ($t = = 9 | | $t = 10 | | (<= $t && $t <= 126)) { $tn = 1; $n + +; } elseif (194 <= $t && $t <= 223) { $tn = 2; $n + 2; } elseif (224 <= $t && $t <= 239) { $tn = 3; $n + 3; ElseIf (<= $t && $t <= 247) { $tn = 4; $n + 4; } elseif (248 <= $t && $t <= 251) { $tn = 5; $n + 5; } elseif ($t = = 252 | | $t = = 253) { $tn = 6; $n + 6; } else { $n + +; } $noc + +; if ($noc >= $length) { Break } } if ($noc > $length) { $n-= $tn; } $strcut = substr ($string, 0, $n); } else { for ($i = 0; $i < $length; $i + +) { $strcut. = Ord ($string [$i]) > 127? $string [$i]. $string [+ + $i]: $string [$i]; } } return $strcut. $dot; } /** * Get the length of the string, including Chinese and English. */ function Mstrlen ($str, $charset = ' UTF-8 ') { if (function_exists (' mb_substr ')) { $length =mb_strlen ($str, $charset); } elseif (Function_exists (' iconv_substr ')) { $length =iconv_strlen ($str, $charset); } else { Preg_match_all ("/[x01-x7f]|[ xc2-xdf][x80-xbf]|xe0[xa0-xbf][x80-xbf]| [Xe1-xef] [X80-XBF] [x80-xbf]|xf0[x90-xbf][x80-xbf][x80-xbf]| [Xf1-xf7] [X80-XBF] [X80-XBF] [x80-xbf]/", $text, $ar);&nbsp; $length =count ($ar [0]); } return $length; }

Instance

The code is as follows

Copy Code

* @param the HTML $str to intercept * Number of @param intercepted $num * Do @param need to add more $more * @return Intercept string */ function phpos_chsubstr_ahtml ($str, $num, $more =false) { $leng =strlen ($STR); if ($num >= $leng) return $str; $word = 0; $i = 0; /** string Pointer **/ $stag =array (Array ()); /** Store the start HTML logo **/ $etag =array (Array ()); /** storage End-HTML flag **/ $SP = 0; $EP = 0; while ($word!= $num) { if (Ord ($str [$i]) >128) { $re. =substr ($str, $i, 3); $i +=3; $word + +; } else if ($str [$i]== ' < ') { if ($str [$i +1] = = '! ') { $i + +; Continue } if ($str [$i +1]== '/') { $ptag =& $etag; $k =& $ep; $i +=2; } Else { $ptag =& $stag; $i +=1; $k =& $sp; } for (; $i < $leng; $i + +) { if ($str [$i] = = ") { $ptag [$k] = implode (', $ptag [$k]); $k + +; Break } if ($str [$i]!= ' > ') { $ptag [$k][]= $str [$i]; Continue } Else { $ptag [$k] = implode (', $ptag [$k]); $k + +; Break } } $i + +; Continue } Else { $re. =substr ($str, $i, 1); $word + +; $i + +; } } foreach ($etag as $val) { $key 1=array_search ($val, $stag); if ($key 1!== false) unset ($stag [$key]); } foreach ($stag as $key => $val) { if (In_array ($val, Array (' BR ', ' img ')) unset ($stag [$key 1]); } Array_reverse ($stag); $ends = ' </'. Implode (' ></', $stag). ' > '; $re = substr ($str, 0, $i). $ends; if ($more) $re. = ' ... '; return $re; }

PHP intercepts the string, generates the article summary
We often need to display the previous part of the article when we write a blog, but we are afraid of improper truncation to break the closed tag to cause the entire document structure to break

The code is as follows

Copy Code

function Text_zhaiyao ($text, $length) {//Article Digest generating functions $test: Content $length: summary length Global $Briefing _length; Mb_regex_encoding ("UTF-8"); if (Mb_strlen ($text) <= $length) return $text; $Foremost = mb_substr ($text, 0, $length); $re = "< (/?) (p| div| F12 F22 h3| h4| h5| h6| address| pre| table|tr| td|th| Input| Select| textarea| Object| a| ul| ol| li| base| meta| link|hr|br| param| Img| area| Input| SPAN) [^>]*]; $Single = "/base| meta| link|hr|br| param| Img| area| Input|br/i "; $Stack = Array (); $posStack = Array (); Mb_ereg_search_init ($Foremost, $re, ' I '); while ($pos = Mb_ereg_search_pos ()) { $match = Mb_ereg_search_getregs (); /* [child-matching formulation]: $matche [1]: A "/" charactor indicating whether current ' <...> ' friction is Closing part $matche [2]: Element Name. $matche [3]: Right > A "<...>" friction */ if ($match [1]== "") { $Elem = $match [2]; if (Mb_eregi ($Single, $Elem) && $match [3]!= "") { Continue }