Chat highlighter

1. CSS

/** Chat-related *************************************************************/

/* SYNTAX % %(chat)% % */

.chat-user { padding: 2px; vertical-align:top; white-space: nowrap; font-weight: bold  }
.chat-time { padding: 2px; vertical-align:top; white-space: nowrap; font: 12px tahoma, arial }
.chat-text { padding: 2px; vertical-align:top;width: 100% }

.chat-u1 { background: #EEFFEE; }	/* green */
.chat-u2 { background: #EEEEFF; }	/* lilac */
.chat-u3 { background: #F8F6C9; }	/* yellow */
.chat-u4 { background: #D6EEFA; }	/* light blue */
.chat-u5 { background: #FFEEEE; }	/* pink */
.chat-u6 { background: #B3B8F4; }	/* blue */
.chat-u7 { background: #F9E8CD; }	/* orange */
.chat-u8 { background: #ECB3D2; }	/* violet */ 	

<?php
/*
    Chat highlighter
    Supports various date-username-message chat log formats (see regexp description below for details)
    Installation: copy to /src/formatter/highlight/chat.php

    Usage:

    % %(chat)
    [12:04:34 01.05.2010] User: Message text by User.
    [13.01.2001 00:00:00] Another User: Message text by Another User. Link in text https://example.com/
    (03:01 AM 10 Jan 1980) Yet Another User: Message text by Yet Another User.
    With
    several lines
    of text!
    (00.00.0000 00:00) <Fourth User> : Message text by Fourth User.
    [00.00.0000 00:00] <Fifth User>: Message text by Fifth User.
    [00:00 00.00.0000] <Sixth User> Message text by Sixth User.
    (00:00 00.00.0000) <Seventh User> Message text by Seventh User.
    and many others including multiline ones
    (00:00:00 13.01.2001) EighthUser: Message text by EighthUser.
    % %
 */

if (!isset($options['type']))        $options['type']    = 'default';
if (!isset($options['user']))        $options['user']    = 0;

// sanitize $text
$text        = htmlspecialchars($text);
$output        = '';

// replace text links to HMTL
$text        = preg_replace('/\b(https?|ftp|file|nntp|telnet):\/\/\S+/u', '<a href="\\0" target="_blank">\\0</a>', $text);
$pattern    = '/^[\[\(]([^\r\n\]\)]*)[\]\)]\s*(&lt;)?([^:\&\r\n]*)(&gt;)?\s*:?((?:(?!^[\[\(]).*(?:\r?\n)*)*)/um';
/*
    Explanation by https://regex101.com/

    Main string parsing rgexp is:
    /^[\[\(]([^\r\n\]\)]*)[\]\)]\s*(&lt;)?([^:\&\r\n]*)(&gt;)?\s*:?((?:(?!^[\[\(]).*(?:\r?\n)*)*)/m
        ^ asserts position at start of a line
        Match a single character present in the list below [\[\(]
        \[ matches the character [ literally (case sensitive)
        \( matches the character ( literally (case sensitive)
    1st Capturing Group ([^\r\n\]\)]*) -- DATE
        Match a single character not present in the list below [^\r\n\]\)]*
        * Quantifier — Matches between zero and unlimited times, as many times as possible, giving back as needed (greedy)
        \r matches a carriage return (ASCII 13)
        \n matches a line-feed (newline) character (ASCII 10)
        \] matches the character ] literally (case sensitive)
        \) matches the character ) literally (case sensitive)
        Match a single character present in the list below [\]\)]
        \] matches the character ] literally (case sensitive)
        \) matches the character ) literally (case sensitive)
        \s* matches any whitespace character (equal to [\r\n\t\f\v ])
        * Quantifier — Matches between zero and unlimited times, as many times as possible, giving back as needed (greedy)
    2nd Capturing Group (&lt;)?
        ? Quantifier — Matches between zero and one times, as many times as possible, giving back as needed (greedy)
        &lt; matches the characters &lt; literally (case sensitive)
    3rd Capturing Group ([^:\&\r\n]*) -- USERNAME
        Match a single character not present in the list below [^:\&\r\n]*
        * Quantifier — Matches between zero and unlimited times, as many times as possible, giving back as needed (greedy)
        : matches the character : literally (case sensitive)
        \& matches the character & literally (case sensitive)
        \r matches a carriage return (ASCII 13)
        \n matches a line-feed (newline) character (ASCII 10)
    4th Capturing Group (&gt;)?
        ? Quantifier — Matches between zero and one times, as many times as possible, giving back as needed (greedy)
        &gt; matches the characters &gt; literally (case sensitive)
        \s* matches any whitespace character (equal to [\r\n\t\f\v ])
        * Quantifier — Matches between zero and unlimited times, as many times as possible, giving back as needed (greedy)
        :? matches the character : literally (case sensitive)
    5th Capturing Group ((?:(?!^[\[\(]).*(?:\r?\n)*)*) -- MESSAGE
    Global pattern flags
        m modifier: multi line. Causes ^ and $ to match the begin/end of each line (not only begin/end of string)

    If you decide to test this $pattern at https://regex101.com/ please add g modifier (it becomes /mg) to make the regexp applied to the whole text.

    This $pattern matches to:
        [12:04:34 01.05.2010] User: Message text by User.
        [13.01.2001 00:00:00] Another User: Message text by Another User. Link in text https://example.com/
        (03:01 AM 10 Jan 1980) Yet Another User: Message text by Yet Another User.
        With
        several lines
        of text!
        (00.00.0000 00:00) <Fourth User> : Message text by Fourth User.
        [00.00.0000 00:00] <Fifth User>: Message text by Fifth User.
        [00:00 00.00.0000] <Sixth User> Message text by Sixth User.
        (00:00 00.00.0000) <Seventh User> Message text by Seventh User.
        and many others including multiline ones
        (00:00:00 13.01.2001) EighthUser: Message text by EighthUser.
        and many others including multiline ones

    Tested with Whatsapp logs.
 */

// split the $text into $matches: $1 - date, $3 - username, $5 - message
preg_match_all($pattern, $text, $matches, PREG_SET_ORDER);

// build the $names array of usernames in chat
$names    = [];
$c        = 1;

foreach($matches as $match)
{
    if (!array_key_exists($match[3], $names))
    {
        $names[$match[3]] = $c++;
    }
}

// HTML output:
//        $1 - date,
//        $3 - username,
//        $5 - message
foreach($matches as $log)
{
    if ($options['type'] == 'div')
    {
        $output .=
            '<div class="chat-u'. $names[$log[3]] .'">' .
                '[' . $log[1] . '] <b>' . $log[3] . '</b>: ' . $log[5] .
            '</div>';
    }
    else
    {
        $output .=
            '<tr class="chat-u'. $names[$log[3]] .'">' .
                '<td class="chat-user">' . $log[3] . '</td>' .
                '<td class="chat-text">' . $log[5] . '</td>' .
                '<td class="chat-time">' . $log[1] . '</td>' .
            '</tr>';
    }
}

// replace \n to <br> to keep multiline messages
$output = str_replace("\n", '<br>', $output);

if ($options['user'])
{
    // prepare alphabetical list of chat participants
    ksort($names);
    $people = '';

    foreach($names as $name => $v)
    {
        $people .= $name . ', ';
    }

    echo '<p><b>' . trim($people, ', ') . ':</b></p>';
}

if ($options['type'] == 'div')
{
    echo '<div>' . $output . '</div>';
}
else
{
    echo '<div><table>' . $output . '</table></div>';
}
	

2. beauty test

Another User, EighthUser, Fifth User, Fourth User, Seventh User, Sixth User, User, Yet Another User:

1. highlight row color tr::hover: ...
2. lighter colors, see styles for info formatter

3. Suggestions

• add more styles
• set output time format as argument
• add other output layouts, e.g. user time \n text