文字差异如何体现对比效果？
- 内容介绍
- 文章标签
- 相关推荐
本文共计1608个文字，预计阅读时间需要7分钟。
php
127: if ($value==192 || $value==223) $split=2;
elseif ($value==224 || $value==239) $split=3;elseif ($value==240 || $value==247) $split=4;else $split=1;$key=NULL;for ($j=0; $j < $split; $j++, $i++) { $key[]='';} html_diff.class.php
127){
if($value >= 192 && $value <= 223)
$split = 2;
elseif($value >= 224 && $value <= 239)
$split = 3;
elseif($value >= 240 && $value <= 247)
$split = 4;
} else {
$split = 1;
}
$key = NULL;
for ( $j = 0; $j < $split; ++$j, ++$i ) {
$key .= $str[$i];
}
$array[] = $key;
//array_push( $array, $key );
}
return $array;
}
function isHanz($str) {
return preg_match("/[\\x{7F}-\\x{FF}]/",$str);
/*for ( $i = 0; $i < strlen($str);++$i ){
$value = ord($str[$i]);
if($value > 127){
return true;
}
}
return false;*/
}
/**
* 从某索引取到另外一个索引
* 不包含end_offset
*
*/
function array_slice_byoffset(&$arr,$start_offset,$end_offset,$preserve_keys = false) {
return array_slice($arr,$start_offset,$end_offset - $start_offset,preserve_keys);
/*
$result = array();
foreach($arr as $k => $v) {
if ($k >= $start_offset && $k < $end_offset) {
if ($preserve_keys) {
$result[$k] = $v;
} else {
$result[] = $v;
}
}
}
return $result;
*/
}
function preg_match_array($pattern_array,$subject) {
$result = 0;
foreach($pattern_array as $v) {
$result |= preg_match('/'.$v.'/',$subject);
}
return $result;
}
define('MODE_CHARACTER',1);
define('MODE_TAG',2);
define('MODE_WHITESPACE',3);
define('ACTION_EQUAL',1);
define('ACTION_DELETE',2);
define('ACTION_INSERT',3);
define('ACTION_NONE',4);
define('ACTION_REPLACE',5);
class html_diff {
private $specialCaseOpeningTags,$specialCaseClosingTags;
private $content,$wordIndices;
private $oldWords,$newWords;
public function html_diff() {
$this->specialCaseOpeningTags = array( "
a
ab
c' * diff result: '
ab
c
' * this still doesn't guarantee valid HTML (hint: think about diffing a text containing ins or * del tags), but handles correctly more cases than the earlier version. * * P.S.: Spare a thought for people who write HTML browsers. They live in this ... every day. * @param $tag string * @param $cssClass string * @param $words mixed */ private function InsertTag($tag, $cssClass, $words) { while (true) { if (count($words) == 0) { break; } //$nonTags = $this->ExtractConsecutiveWords($words, x => !this.IsTag(x)); $nonTags = $this->ExtractConsecutiveWords($words, false); $specialCaseTagInjection = ''; $specialCaseTagInjectionIsBefore = false; if (count($nonTags) != 0) { $text = $this->WrapText(implode('', $nonTags), $tag, $cssClass); $this->content[] = $text; } else { // Check if strong tag //if ($this->specialCaseOpeningTags.FirstOrDefault(x => Regex.IsMatch($words[0], x)) != null) { if (!!preg_match_array($this->specialCaseOpeningTags,$words[0]) ) { $specialCaseTagInjection = ' '; // words.RemoveAt(0); if ($tag == 'del') array_shift($words); //delete 0 } else if (in_array($words[0],$this->specialCaseClosingTags)) { $specialCaseTagInjection = ''; $specialCaseTagInjectionIsBefore = true; if ($tag == "del") array_shift($words); //delete 0 } } if (count($words) == 0 && strlen($specialCaseTagInjection) == 0) { break; } if ($specialCaseTagInjectionIsBefore) { $this->content[] = $specialCaseTagInjection . implode('', $this->ExtractConsecutiveWords($words, true)); } else { $this->content[] = implode('', $this->ExtractConsecutiveWords($words, true)) . $specialCaseTagInjection; } } } private function WrapText($text, $tagName, $cssClass) { return sprintf("<%s class='%s'>%s ", $tagName, $cssClass, $text ,$tagName); } private function ExtractConsecutiveWords(&$words, $condition) { $indexOfFirstTag = false; for ($i = 0; $i < count($words); $i++) { $word = $words[$i]; if ($condition ? !$this->IsTag($word) : !!$this->IsTag($word)) { $indexOfFirstTag = $i; break; } } //print_r($indexOfFirstTag); if ($indexOfFirstTag !== false) { //var items = words.Where((s, pos) => pos >= 0 && pos < indexOfFirstTag).ToArray(); $items = array_slice_byoffset($words,0,$indexOfFirstTag); if ($indexOfFirstTag > 0) { //$words.RemoveRange(0, $indexOfFirstTag); array_splice($words,0,$indexOfFirstTag); } //print_r($words); return $items; } else { //$items = $words.Where((s, pos) => pos >= 0 && pos <= words.Count).ToArray(); $items = $words; //words.RemoveRange(0, words.Count); $words = array(); return $items; } } private function IsTag($item) { $isTag = $this->IsOpeningTag($item) || $this->IsClosingTag($item); return $isTag; } private function IsOpeningTag($item) { return preg_match("/^\\s*<[^>]+>\\s*$/",$item) > 0; } private function IsClosingTag($item) { return preg_match("/^\\s*<\\/[^>]+>\\s*$/",$item) > 0; } private function Operations() { $positionInOld = 0; $positionInNew = 0; //List本文共计1608个文字，预计阅读时间需要7分钟。
php
127: if ($value==192 || $value==223) $split=2;
elseif ($value==224 || $value==239) $split=3;elseif ($value==240 || $value==247) $split=4;else $split=1;$key=NULL;for ($j=0; $j < $split; $j++, $i++) { $key[]='';} html_diff.class.php
127){
if($value >= 192 && $value <= 223)
$split = 2;
elseif($value >= 224 && $value <= 239)
$split = 3;
elseif($value >= 240 && $value <= 247)
$split = 4;
} else {
$split = 1;
}
$key = NULL;
for ( $j = 0; $j < $split; ++$j, ++$i ) {
$key .= $str[$i];
}
$array[] = $key;
//array_push( $array, $key );
}
return $array;
}
function isHanz($str) {
return preg_match("/[\\x{7F}-\\x{FF}]/",$str);
/*for ( $i = 0; $i < strlen($str);++$i ){
$value = ord($str[$i]);
if($value > 127){
return true;
}
}
return false;*/
}
/**
* 从某索引取到另外一个索引
* 不包含end_offset
*
*/
function array_slice_byoffset(&$arr,$start_offset,$end_offset,$preserve_keys = false) {
return array_slice($arr,$start_offset,$end_offset - $start_offset,preserve_keys);
/*
$result = array();
foreach($arr as $k => $v) {
if ($k >= $start_offset && $k < $end_offset) {
if ($preserve_keys) {
$result[$k] = $v;
} else {
$result[] = $v;
}
}
}
return $result;
*/
}
function preg_match_array($pattern_array,$subject) {
$result = 0;
foreach($pattern_array as $v) {
$result |= preg_match('/'.$v.'/',$subject);
}
return $result;
}
define('MODE_CHARACTER',1);
define('MODE_TAG',2);
define('MODE_WHITESPACE',3);
define('ACTION_EQUAL',1);
define('ACTION_DELETE',2);
define('ACTION_INSERT',3);
define('ACTION_NONE',4);
define('ACTION_REPLACE',5);
class html_diff {
private $specialCaseOpeningTags,$specialCaseClosingTags;
private $content,$wordIndices;
private $oldWords,$newWords;
public function html_diff() {
$this->specialCaseOpeningTags = array( "
a
ab
c' * diff result: '
ab
c
' * this still doesn't guarantee valid HTML (hint: think about diffing a text containing ins or * del tags), but handles correctly more cases than the earlier version. * * P.S.: Spare a thought for people who write HTML browsers. They live in this ... every day. * @param $tag string * @param $cssClass string * @param $words mixed */ private function InsertTag($tag, $cssClass, $words) { while (true) { if (count($words) == 0) { break; } //$nonTags = $this->ExtractConsecutiveWords($words, x => !this.IsTag(x)); $nonTags = $this->ExtractConsecutiveWords($words, false); $specialCaseTagInjection = ''; $specialCaseTagInjectionIsBefore = false; if (count($nonTags) != 0) { $text = $this->WrapText(implode('', $nonTags), $tag, $cssClass); $this->content[] = $text; } else { // Check if strong tag //if ($this->specialCaseOpeningTags.FirstOrDefault(x => Regex.IsMatch($words[0], x)) != null) { if (!!preg_match_array($this->specialCaseOpeningTags,$words[0]) ) { $specialCaseTagInjection = ' '; // words.RemoveAt(0); if ($tag == 'del') array_shift($words); //delete 0 } else if (in_array($words[0],$this->specialCaseClosingTags)) { $specialCaseTagInjection = ''; $specialCaseTagInjectionIsBefore = true; if ($tag == "del") array_shift($words); //delete 0 } } if (count($words) == 0 && strlen($specialCaseTagInjection) == 0) { break; } if ($specialCaseTagInjectionIsBefore) { $this->content[] = $specialCaseTagInjection . implode('', $this->ExtractConsecutiveWords($words, true)); } else { $this->content[] = implode('', $this->ExtractConsecutiveWords($words, true)) . $specialCaseTagInjection; } } } private function WrapText($text, $tagName, $cssClass) { return sprintf("<%s class='%s'>%s ", $tagName, $cssClass, $text ,$tagName); } private function ExtractConsecutiveWords(&$words, $condition) { $indexOfFirstTag = false; for ($i = 0; $i < count($words); $i++) { $word = $words[$i]; if ($condition ? !$this->IsTag($word) : !!$this->IsTag($word)) { $indexOfFirstTag = $i; break; } } //print_r($indexOfFirstTag); if ($indexOfFirstTag !== false) { //var items = words.Where((s, pos) => pos >= 0 && pos < indexOfFirstTag).ToArray(); $items = array_slice_byoffset($words,0,$indexOfFirstTag); if ($indexOfFirstTag > 0) { //$words.RemoveRange(0, $indexOfFirstTag); array_splice($words,0,$indexOfFirstTag); } //print_r($words); return $items; } else { //$items = $words.Where((s, pos) => pos >= 0 && pos <= words.Count).ToArray(); $items = $words; //words.RemoveRange(0, words.Count); $words = array(); return $items; } } private function IsTag($item) { $isTag = $this->IsOpeningTag($item) || $this->IsClosingTag($item); return $isTag; } private function IsOpeningTag($item) { return preg_match("/^\\s*<[^>]+>\\s*$/",$item) > 0; } private function IsClosingTag($item) { return preg_match("/^\\s*<\\/[^>]+>\\s*$/",$item) > 0; } private function Operations() { $positionInOld = 0; $positionInNew = 0; //List