Mos\TextFilter\TTextUtilities

Complexity

Total Complexity

11

Size/Duplication

Total Lines	177
Duplicated Lines	0 %

Coupling/Cohesion

Components	0
Dependencies	0

Test Coverage

Coverage

29.55%

Importance

Changes	4
Bugs	0	Features	2

5 Methods

Rating	Name	Duplication	Size	Complexity
A	getUntilStop()	0	8	2
A	getUntilMore()	0	9	2
A	wrapElementWithStartEnd()	0	9	1
A	wrapElementContentWithStartEnd()	0	9	1
B	createToc()	0	24	5

<?php

namespace Mos\TextFilter;

/**
 * Utilities when working with text.
 *
 */
trait TTextUtilities
{
    /**
     * Get text until <!--stop--> or all text.
     *
     * @param string $text with content
     *
     * @return string with text
     */
    public function getUntilStop($text)
    {
        $pos = stripos($text, "<!--stop-->");
        if ($pos) {
            $text = substr($text, 0, $pos);
        }
        return $text;
    }



    /**
     * Get text until <!--more--> or all text.
     *
     * @param string $text with content
     *
     * @return array with text and boolean if more was detected.
     */
    public function getUntilMore($text)
    {
        $pos = stripos($text, "<!--more-->");
        $hasMore = $pos;
        if ($pos) {
            $text = substr($text, 0, $pos);
        }
        return [$text, $hasMore];
    }



    /**
     * Wrap HTML element with with start and end.
     *
     * @param string  $text  with content
     * @param string  $tag   HTML tag to search for
     * @param string  $start wrap start part
     * @param string  $end   wrap end part
     * @param number  $count hits to search for
     *
     * @return array with text and boolean if more was detected.
     */
    public function wrapElementWithStartEnd($text, $tag, $start, $end, $count)
    {
        return preg_replace(
            "#(<$tag>)(.*?)(</$tag>)#",
            "$start$1$2$3$end</a>",
            $text,
            $count
        );
    }



    /**
    * Wrap content of a HTML element with start and end.
     *
     * @param string  $text  with content
     * @param string  $tag   HTML tag to search for
     * @param string  $start wrap start part
     * @param string  $end   wrap end part
     * @param number  $count hits to search for
     *
     * @return array with text and boolean if more was detected.
     */
    public function wrapElementContentWithStartEnd($text, $tag, $start, $end, $count)
    {
        return preg_replace(
            "#(<$tag>)(.*?)(</$tag>)#",
            "$1$start$2$end$3</a>",
            $text,
            $count
        );
    }



    /**
     * Create a TOC of HTML headings from and to a certain level.
     *
     * @param string  $text  with content
     * @param integer $start level of headings to use for toc.
     * @param integer $stop  level of headings to use for toc.
     *
     * @return array with entries to generate a TOC.
     */
    public function createToc($text, $start = 2, $stop = 4)
    {
        $level = "$start-$stop";
        $pattern = "/<(h[$level])([^>]*)>(.*)<\/h[$level]>/";
        preg_match_all($pattern, $text, $matches, PREG_SET_ORDER);

        $toc = [];
        foreach ($matches as $val) {

The expression $matches of type null|array<integer,array<integer,string>> is not guaranteed to be traversable. How about adding an additional type check?

            preg_match("/id=['\"]([^>\"']+)/", $val[2], $id);
            $id = isset($id[1]) ? $id[1] : null;
            var_dump($matches[1]);

var_dump($matches[1]); looks like debug code. Are you sure you do not want to remove it? This might expose sensitive data.

            $toc[] = [
                "level" => isset($val[1])
                    ? $val[1]
                    : null,
                "title" => isset($val[3])
                    ? $val[3]
                    : null,
                "id" => $id,
            ];
        }

        return $toc;
    }



    /**
     * Get content as pure text.
     *
     * @return string with the pure text.
     */
/*    public function GetPureText() {
      return preg_replace('/\s+/', ' ', strip_tags($this->GetFilteredData()));
    }
*/



    /**
     * Returns the excerpt of the text with at most the specified amount of characters.
     *
     * @param int $chars the number of characters to return.
     * @param boolean $hard do a hard break at exactly $chars characters or find closest space.
     * @return string as the excerpt.
     */
/*    public function GetExcerpt($chars=139, $hard=false) {
      if(!isset($this->data['data_filtered'])) {
        return null;
      }
      $excerpt = strip_tags($this->data['data_filtered']);

      if(strlen($excerpt) > $chars) {
        $excerpt   = substr($excerpt, 0, $chars-1);
      }

      if(!$hard) {
        $lastSpace = strrpos($excerpt, ' ');
        $excerpt   = substr($excerpt, 0, $lastSpace);
      }

      return $excerpt;
    }
    
    
    /**
     * Returns the first paragraph ot the text.
     * 
     * @return string as the first paragraph.
     */
/*    public function GetFirstParagraph() {
      if(!isset($this->data['data_filtered'])) {
        return null;
      }
      $excerpt = $this->data['data_filtered'];

      $firstPara = strpos($excerpt, '</p>');
      $excerpt   = substr($excerpt, 0, $firstPara + 4);

      return $excerpt;
    }
*/
}