PHP 自动套用段落格式标签

Question

这是一个相当基本的问题，但我只找到了三个答案。我想对可能包含也可能不包含其他 html 元素的未格式化内容进行自动段落标记。两个不错的函数是 wordpress wpautop、HTMLPurifier AutoFormat.AutoParagraph 以及最后一些随机的addParagraphsNew。然而，第一个与我的应用程序许可证不兼容，第二个不在段落标签内添加换行符，第三个是不稳定的。

有谁知道商业上合适的许可脚本，允许将具有换行符和双换行符的html内容转换为
和

标签？

我相信 HTMLPurifier 选项可能是我侵入 AutoFormat.AutoParagraph 插件以使其添加换行符的最佳方法，但我希望能稍微简单一些。我知道很懒。

Answer 1

好吧，你可以自己破解它（如果我正确理解你需要什么），

$text = "hello, I am text

and this is another paragraph, please do some cool
stuff with this (this is after a  line break)

last apragrahp...";

$text = str_replace("\r\n","\n",$text);

$paragraphs = preg_split("/[\n]{2,}/",$text);
foreach ($paragraphs as $key => $p) {
    $paragraphs[$key] = "<p>".str_replace("\n","<br />",$paragraphs[$key])."</p>";
}

$text = implode("", $paragraphs);

echo $text;

这实际上会输出：

<p>hello, I am text</p><p>and this is another paragraph, please do some cool<br />stuff with this (this is after a  line break)</p><p>last apragrahp...</p>

注意它现在如何丢失所有换行符等......

Answer 2

这是一个 JavaScript 解决方案，它将向行添加段落标签。它将忽略空行、标题、图像、列表和代码块内的行。

function Add_paragraph_tags(input)
{
    console.log('Adding paragraph tags');
    var lines = input.split("\n");
    line_is_inside_code_block = false;
    line_is_inside_pre_block = false;
    line_is_inside_table = false;
    line_is_inside_comment = false;
    line_is_inside_video = false;
    line_is_inside_css_block = false;

    lines.forEach
    (
            function(line, index)
            {
                    lines[index] = lines[index].replace(/\<h[1-9]\>\<\/h[1-9]\>/,''); //remove instances of <h2></h3>
                    lines[index] = lines[index].replace(/\<(h[1-9]\>)(.*)\<\/h[1-9]\>/,'<$1$2</$1');
                    if(
                            line==''
                            || /^[ |\t]*<h/.test(line)
                            || /^[ |\t]*<a/.test(line)
                            //|| /^[ |\t]*<p/.test(line)
                            || /^[ |\t]*<br/.test(line)
                            || /^[ |\t]*<img/.test(line)
                            || /^[ |\t]*<\/?div/.test(line)
                            || /^[ |\t]*<pre/.test(line)
                            || /^[ |\t]*<code/.test(line)
                            || /^[ |\t]*<table/.test(line)
                            || /^[ |\t]*<iframe/.test(line)
                            || /^[ |\t]*<figure/.test(line)
                            || /^[ |\t]*<figcaption/.test(line)
                            || /^[ |\t]*<li>/.test(line)
                            || /^[ |\t]*<ol>/.test(line)
                            || /^[ |\t]*<\/ol>/.test(line)
                            || /^[ |\t]*<ul>/.test(line)
                            || /^[ |\t]*<\/ul>/.test(line)
                            || /^[ |\t]*<blockquote><p>/.test(line)
                            || /^[ |\t]*<video/.test(line)
                            || /^[ |\t]*<style/.test(line)
                            || /^[ |\t]*<!--/.test(line)
                            || line_is_inside_code_block
                            || line_is_inside_pre_block
                            || line_is_inside_table
                            || line_is_inside_comment
                            || line_is_inside_video
                            || line_is_inside_css_block
                    )
                    {
                            //do nothing
                    }
                    else
                    {
                            lines[index] = '<p>' + line + '</p>';
                            lines[index] = lines[index].replace('<p><blockquote>','<blockquote><p>');
                            lines[index] = lines[index].replace('</blockquote></p>','</p></blockquote>');
                            lines[index] = lines[index].replace(/(\<p\>)+/,'<p>'); //elimlnate multiple p tags
                            lines[index] = lines[index].replace(/(\<\/p\>)+/,'</p>'); //elimlnate multiple closing p tags
                            lines[index] = lines[index].replace(/\<p\>\<\/p\>/,''); //elimlnate <p></p>
                    }

                    /*if(lines[index+1].startsWith('<br'))
                    {
                            lines[index] = lines[index].replace(/\<\/p\>)/,'');
                    }*/

                    if(line.endsWith('</code>'))
                    {
                            line_is_inside_code_block = false;
                    }
                    else if(line.endsWith('</pre>'))
                    {
                            line_is_inside_pre_block = false;
                    }
                    else if(line.endsWith('</table>'))
                    {
                            line_is_inside_table = false;
                    }
                    else if(line.endsWith('-->'))
                    {
                            line_is_inside_comment = false;
                    }
                    else if(line.endsWith('/video>'))
                    {
                            line_is_inside_video = false;
                    }
                    else if(line.endsWith('/style>'))
                    {
                            line_is_inside_css_block = false;
                    }
                    else if(line.startsWith('<code'))
                    {
                            line_is_inside_code_block = true;
                    }
                    else if(line.startsWith('<pre'))
                    {
                            line_is_inside_pre_block = true;
                    }
                    else if(line.startsWith('<table'))
                    {
                            line_is_inside_table = true;
                    }
                    else if(line.startsWith('<!--'))
                    {
                            line_is_inside_comment = true;
                    }
                    else if(line.startsWith('<video'))
                    {
                            line_is_inside_video = true;
                    }
                    else if(line.startsWith('<style'))
                    {
                            line_is_inside_css_block = true;
                    }
            }
    );
    var output = lines.join('\n');
    output = output.replace(/\n\n+/g,'\n\n');
    output = output.replace(/\<\/p\>\n\<br/g,'\n<br');
    output = output.replace(/\<i\>/g,'<em>');
    output = output.replace(/\<\/i\>/g,'</em>');
    return output;
}

$('button').click(
  function() {
var input_text = $('#input').val();
var output_text = Add_paragraph_tags(input_text);
$('#output').val(output_text);
  })

<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery/3.3.1/jquery.min.js"></script>

<textarea id="input">
This line should have paragraph tags.

<pre>This is code and does not need paragraph tags</pre>

<em>This line should have paragraph tags.</em>

<h1>This is a header and it does not need paragraph tags</h1>

<blockquote>This is a blockquote. This line needs a paragraph tag.

Paragraph tags are needed here too.</blockquote>

<ul>
<li>This is a list item. It does not need a paragraph tag</li>
</ul>

</textarea>

<textarea id="output"></textarea>

<button type="button">Add paragraph tags</button>