Php 从文本字符串创建关键字-西里尔文的编码问题
我正在搜索一个可以从文本字符串自动创建关键字的代码。下面的代码可以很好地处理拉丁字符,但如果我尝试将其与俄语(西里尔文)一起使用,结果就是逗号之间有空格 我不确定问题出在哪里,但我相信这与编码有关。我试着用这个编码字符串Php 从文本字符串创建关键字-西里尔文的编码问题,php,regex,preg-replace,preg-match-all,Php,Regex,Preg Replace,Preg Match All,我正在搜索一个可以从文本字符串自动创建关键字的代码。下面的代码可以很好地处理拉丁字符,但如果我尝试将其与俄语(西里尔文)一起使用,结果就是逗号之间有空格 我不确定问题出在哪里,但我相信这与编码有关。我试着用这个编码字符串 $string = preg_replace('/\s\s+/i', '', mb_strtolower(utf8_encode($string))); 但是没有运气。结果是一样的 另外,我在$stopwords变量中只包含俄语单词 $stopWords = array('у
$string = preg_replace('/\s\s+/i', '', mb_strtolower(utf8_encode($string)));
但是没有运气。结果是一样的
另外,我在$stopwords变量中只包含俄语单词
$stopWords = array('у','ни','на','да','и','нет','были','уже','лет','в','что','их','до','сих','пор','из','но','бы','чтобы','вы','была','было','мы','к','от','с','так','как','не','есть','ее','нам','для','вас','о','них','без');
这是原始代码
function extractCommonWords($string){
$stopWords = array('i','a','about','an','and','are','as','at','be','by','com','de','en','for','from','how','in','is','it','la','of','on','or','that','the','this','to','was','what','when','where','who','will','with','und','the','www');
$string = preg_replace('/\s\s+/i', '', $string); // replace whitespace
$string = trim($string); // trim the string
$string = preg_replace('/[^a-zA-Z0-9 -]/', '', $string); // only take alphanumerical characters, but keep the spaces and dashes too…
$string = strtolower($string); // make it lowercase
preg_match_all('/\b.*?\b/i', $string, $matchWords);
$matchWords = $matchWords[0];
foreach ( $matchWords as $key=>$item ) {
if ( $item == '' || in_array(strtolower($item), $stopWords) || strlen($item) <= 3 ) {
unset($matchWords[$key]);
}
}
$wordCountArr = array();
if ( is_array($matchWords) ) {
foreach ( $matchWords as $key => $val ) {
$val = strtolower($val);
if ( isset($wordCountArr[$val]) ) {
$wordCountArr[$val]++;
} else {
$wordCountArr[$val] = 1;
}
}
}
arsort($wordCountArr);
$wordCountArr = array_slice($wordCountArr, 0, 10);
return $wordCountArr;}
函数提取常用词($string){
$stopWords=array('i','a','about','an','and','are','as','at','be','by','com','de','en','for','from','how','in','is','it','la','of','on','or','that','the','this','to','was','what','who','will','with','und the','www';
$string=preg_replace('/\s\s+/i','$string);//替换空白
$string=trim($string);//修剪字符串
$string=preg_replace('/[^a-zA-Z0-9-]/',''$string);//只接受字母数字字符,但也保留空格和破折号…
$string=strtolower($string);//使其小写
preg_match_all('/\b.*?\b/i',$string,$matchWords);
$matchWords=$matchWords[0];
foreach($key=>$item的匹配词){
如果($item==''| |在_数组中(strtolower($item),$stopWords)| | strlen($item)$val){
$val=strtolower($val);
如果(isset($wordCountArr[$val])){
$wordCountArr[$val]++;
}否则{
$wordCountArr[$val]=1;
}
}
}
arsort($wordCountArr);
$wordCountArr=array\u片($wordCountArr,0,10);
返回$wordCountArr;}
任何帮助都将不胜感激。西里尔字符由以下正则表达式匹配并从字符串中删除:
$string = preg_replace('/[^a-zA-Z0-9 -]/', '', $string);
要避免它,请与\w
匹配。但是您需要使用for\w
和friends来匹配其他脚本(包括西里尔文)中的字母
还有一件事,regex
/\b.*?\b/i
是错误的,原因有几个。但是如果你仔细想想,它可能会匹配同一个边界两次
无论如何,我相信您不需要从字符串中删除不需要的字符。你只是在试图提取单词。您可以简单地使用1个正则表达式来匹配它们 用于匹配单词的正则表达式(使用Unicode脚本,包括西里尔文)
代码
function extractCommonWords($string){
$stopWords = array('i','a','about','an','and','are','as','at','be','by','com','de','en','for','from','how','in','is','it','la','of','on','or','that','the','this','to','was','what','when','where','who','will','with','und','the','www');
$string = strtolower($string);
preg_match_all('/\w+/u', $string, $matchWords);
$matchWords = $matchWords[0];
foreach ( $matchWords as $key=>$item ) {
if ( $item == '' || in_array(strtolower($item), $stopWords) || strlen($item) <= 3 ) {
unset($matchWords[$key]);
}
}
$wordCountArr = array();
if ( is_array($matchWords) ) {
foreach ( $matchWords as $key => $val ) {
$val = mb_strtolower($val);
if ( isset($wordCountArr[$val]) ) {
$wordCountArr[$val]++;
} else {
$wordCountArr[$val] = 1;
}
}
}
arsort($wordCountArr);
$wordCountArr = array_slice($wordCountArr, 0, 10);
return $wordCountArr;
}
//for testing purposes
$sc = 'Hello there нам для!';
$result = extractCommonWords($sc);
print_r($result);
函数提取常用词($string){
$stopWords=array('i','a','about','an','and','are','as','at','be','by','com','de','en','for','from','how','in','is','it','la','of','on','or','that','the','this','to','was','what','who','will','with','und the','www';
$string=strtolower($string);
preg_match_all('/\w+/u',$string,$matchWords);
$matchWords=$matchWords[0];
foreach($key=>$item的匹配词){
如果($item==''| |在_数组中(strtolower($item),$stopWords)| | strlen($item)$val){
$val=mb_strtolower($val);
如果(isset($wordCountArr[$val])){
$wordCountArr[$val]++;
}否则{
$wordCountArr[$val]=1;
}
}
}
arsort($wordCountArr);
$wordCountArr=array\u片($wordCountArr,0,10);
返回$wordCountArr;
}
//用于测试目的
$sc=‘你好!’这里有人吗;
$result=extractedcommonwords($sc);
打印(结果);
*免责声明:我甚至没有阅读代码的其余部分。我只是指出问题所在
你说得绝对正确。。。这很有魅力。谢谢,还有一件事。您知道如何排除少于5个字符的单词吗?
'/\b\w{5,}/u'
。。。看见\b
是一个(不需要它,但如果你在那里使用它会更有效)啊,那很简单。你是救命恩人。。。我正要写一个单独的脚本来捕捉只有5个以上字符的单词。但这很容易。我需要学习regex。谢谢Mariano。如果你想学习regex,只需阅读我链接到的教程中的几页。干杯
preg_match_all('/\w+/u', $string, $matchWords);
function extractCommonWords($string){
$stopWords = array('i','a','about','an','and','are','as','at','be','by','com','de','en','for','from','how','in','is','it','la','of','on','or','that','the','this','to','was','what','when','where','who','will','with','und','the','www');
$string = strtolower($string);
preg_match_all('/\w+/u', $string, $matchWords);
$matchWords = $matchWords[0];
foreach ( $matchWords as $key=>$item ) {
if ( $item == '' || in_array(strtolower($item), $stopWords) || strlen($item) <= 3 ) {
unset($matchWords[$key]);
}
}
$wordCountArr = array();
if ( is_array($matchWords) ) {
foreach ( $matchWords as $key => $val ) {
$val = mb_strtolower($val);
if ( isset($wordCountArr[$val]) ) {
$wordCountArr[$val]++;
} else {
$wordCountArr[$val] = 1;
}
}
}
arsort($wordCountArr);
$wordCountArr = array_slice($wordCountArr, 0, 10);
return $wordCountArr;
}
//for testing purposes
$sc = 'Hello there нам для!';
$result = extractCommonWords($sc);
print_r($result);