IRCScraper::processChannelMessages() - Code Metrics - NNTmux/newznab-tmux - Measure and Improve Code Quality continuously with Scrutinizer

IRCScraper::processChannelMessages() F
last analyzed 2026-01-22 09:47 UTC

↳ Parent: IRCScraper

Complexity

Conditions	34
Paths	1692

Size

Total Lines	88
Code Lines	59

Duplication

Lines	0
Ratio	0 %

Importance

Changes

Metric	Value
eloc	59
dl	0
loc	88
rs	0
c	0
b	0
f	0
cc	34
nc	1692
nop	0

How to fix Long Method Complexity

<?php

namespace App\Services;

use App\Facades\Search;
use App\Models\Predb;
use App\Models\UsenetGroup;
use Illuminate\Support\Carbon;
use Illuminate\Support\Facades\DB;

/**
 * Class IRCScraper.
 */
class IRCScraper extends IRCClient
{
    /**
     * Regex to ignore categories.
     */
    protected string|false $_categoryIgnoreRegex = false;

    /**
     * Array of current pre info.
     */
    protected array $_curPre;

    /**
     * List of groups and their id's.
     */
    protected array $_groupList;

    /**
     * Array of ignored channels.
     */
    protected array $_ignoredChannels;

    /**
     * Is this pre nuked or un nuked?
     */
    protected bool $_nuked;

    protected $_oldPre;

    /**
     * Run this in silent mode (no text output).
     */
    protected bool $_silent;

    /**
     * Regex to ignore PRE titles.
     */
    protected string|false $_titleIgnoreRegex = false;

    /**
     * Construct.
     *
     * @param  bool  $silent  Run this in silent mode (no text output).
     * @param  bool  $debug  Turn on debug? Shows sent/received socket buffer messages.
     *
     * @throws \Exception
     */
    public function __construct(bool $silent, bool $debug)
    {
        if (config('irc_settings.scrape_irc_source_ignore')) {
            try {
                $ignored = unserialize(
                    (string) config('irc_settings.scrape_irc_source_ignore'),
                    ['allowed_classes' => false]
                );
                $this->_ignoredChannels = is_array($ignored) ? $ignored : [];
            } catch (\ValueError $e) {
                $this->_ignoredChannels = [];
            }
        } else {
            $this->_ignoredChannels = [
                '#a.b.cd.image' => false,
                '#a.b.console.ps3' => false,
                '#a.b.dvd' => false,
                '#a.b.erotica' => false,
                '#a.b.flac' => false,
                '#a.b.foreign' => false,
                '#a.b.games.nintendods' => false,
                '#a.b.inner-sanctum' => false,
                '#a.b.moovee' => false,
                '#a.b.movies.divx' => false,
                '#a.b.sony.psp' => false,
                '#a.b.sounds.mp3.complete_cd' => false,
                '#a.b.teevee' => false,
                '#a.b.games.wii' => false,
                '#a.b.warez' => false,
                '#a.b.games.xbox360' => false,
                '#pre@corrupt' => false,
                '#scnzb' => false,
                '#tvnzb' => false,
                'srrdb' => false,
            ];
        }

        if (config('irc_settings.scrape_irc_category_ignore') !== '') {
            $this->_categoryIgnoreRegex = (string) config('irc_settings.scrape_irc_category_ignore');
        }

        if (config('irc_settings.scrape_irc_title_ignore') !== '') {
            $this->_titleIgnoreRegex = (string) config('irc_settings.scrape_irc_title_ignore');
        }

        $this->_groupList = [];
        $this->_silent = $silent;
        $this->_debug = $debug;
        $this->_resetPreVariables();
        $this->_startScraping();
    }

    /**
     * Main method for scraping.
     */
    protected function _startScraping(): void
    {
        // Connect to IRC.
        if ($this->connect((string) config('irc_settings.scrape_irc_server'), (int) config('irc_settings.scrape_irc_port'), (bool) config('irc_settings.scrape_irc_tls')) === false) {
            exit(

                'Error connecting to ('.
                config('irc_settings.scrape_irc_server').
                ':'.
                config('irc_settings.scrape_irc_port').
                '). Please verify your server information and try again.'.
                PHP_EOL
            );
        }

        // Normalize password to ?string
        $password = config('irc_settings.scrape_irc_password');
        $password = ($password === false || $password === '' || $password === null) ? null : (string) $password;

        // Login to IRC. Note parameter order: nick, user, real, pass.
        if ($this->login((string) config('irc_settings.scrape_irc_nickname'), (string) config('irc_settings.scrape_irc_username'), (string) config('irc_settings.scrape_irc_realname'), $password) === false) {
            exit(

                'Error logging in to: ('.
                config('irc_settings.scrape_irc_server').':'.config('irc_settings.scrape_irc_port').') nickname: ('.config('irc_settings.scrape_irc_nickname').
                '). Verify your connection information, you might also be banned from this server or there might have been a connection issue.'.
                PHP_EOL
            );
        }

        // Join channels.
        $channelsCfg = config('irc_settings.scrape_irc_channels');
        if ($channelsCfg) {
            try {
                $channels = unserialize((string) $channelsCfg, ['allowed_classes' => false]);
            } catch (\ValueError $e) {
                $channels = ['#PreNNTmux' => null];
            }
            if (! is_array($channels)) {
                $channels = ['#PreNNTmux' => null];
            }
        } else {
            $channels = ['#PreNNTmux' => null];
        }
        $this->joinChannels($channels);

        if (! $this->_silent) {
            echo '['.
                date('r').
                '] [Scraping of IRC channels for ('.
                config('irc_settings.scrape_irc_server').
                ':'.
                config('irc_settings.scrape_irc_port').
                ') ('.
                config('irc_settings.scrape_irc_nickname').
                ') started.]'.
                PHP_EOL;
        }

        // Scan incoming IRC messages.
        $this->readIncoming();
    }

    /**
     * Process bot messages, insert/update PREs.
     *
     * @throws \Exception
     */
    protected function processChannelMessages(): void
    {
        if ($this->_debug && ! $this->_silent) {
            echo '[DEBUG] Processing message: '.$this->_channelData['message'].PHP_EOL;
        }

        if (preg_match(
            '/^(NEW|UPD|NUK): \[DT: (?P<time>.+?)\]\s?\[TT: (?P<title>.+?)\]\s?\[SC: (?P<source>.+?)\]\s?\[CT: (?P<category>.+?)\]\s?\[RQ: (?P<req>.+?)\]'.
            '\s?\[SZ: (?P<size>.+?)\]\s?\[FL: (?P<files>.+?)\]\s?(\[FN: (?P<filename>.+?)\]\s?)?(\[(?P<nuked>(UN|MOD|RE|OLD)?NUKED?): (?P<reason>.+?)\])?$/i',
            $this->_channelData['message'],
            $hits
        )) {
            if ($this->_debug && ! $this->_silent) {
                echo '[DEBUG] Regex matched! Title: '.$hits['title'].' | Source: '.$hits['source'].' | Category: '.$hits['category'].PHP_EOL;
            }

            if (isset($this->_ignoredChannels[$hits['source']]) && $this->_ignoredChannels[$hits['source']] === true) {
                if ($this->_debug && ! $this->_silent) {
                    echo '[DEBUG] Source '.$hits['source'].' is ignored, skipping...'.PHP_EOL;
                }

                return;
            }

            if ($this->_categoryIgnoreRegex !== false && preg_match((string) $this->_categoryIgnoreRegex, $hits['category'])) {
                if ($this->_debug && ! $this->_silent) {
                    echo '[DEBUG] Category '.$hits['category'].' is ignored by regex, skipping...'.PHP_EOL;
                }

                return;
            }

            if ($this->_titleIgnoreRegex !== false && preg_match((string) $this->_titleIgnoreRegex, $hits['title'])) {
                if ($this->_debug && ! $this->_silent) {
                    echo '[DEBUG] Title '.$hits['title'].' is ignored by regex, skipping...'.PHP_EOL;
                }

                return;
            }

            $utime = Carbon::createFromTimeString($hits['time'], 'UTC')->timestamp;

            $this->_curPre['predate'] = 'FROM_UNIXTIME('.$utime.')';
            $this->_curPre['title'] = $hits['title'];
            $this->_curPre['source'] = $hits['source'];
            if ($hits['category'] !== 'N/A') {
                $this->_curPre['category'] = $hits['category'];
            }
            if ($hits['req'] !== 'N/A' && preg_match('/^(?P<req>\d+):(?P<group>.+)$/i', $hits['req'], $matches2)) {
                $this->_curPre['reqid'] = $matches2['req'];
                $this->_curPre['group_id'] = $this->_getGroupID($matches2['group']);
            }
            if ($hits['size'] !== 'N/A') {
                $this->_curPre['size'] = $hits['size'];
            }
            if ($hits['files'] !== 'N/A') {
                $this->_curPre['files'] = substr($hits['files'], 0, 50);
            }

            if (isset($hits['filename']) && $hits['filename'] !== 'N/A') {
                $this->_curPre['filename'] = $hits['filename'];
            }

            if (isset($hits['nuked'])) {
                switch ($hits['nuked']) {
                    case 'NUKED':
                        $this->_curPre['nuked'] = Predb::PRE_NUKED;
                        break;
                    case 'UNNUKED':
                        $this->_curPre['nuked'] = Predb::PRE_UNNUKED;
                        break;
                    case 'MODNUKED':
                        $this->_curPre['nuked'] = Predb::PRE_MODNUKE;
                        break;
                    case 'RENUKED':
                        $this->_curPre['nuked'] = Predb::PRE_RENUKED;
                        break;
                    case 'OLDNUKE':
                        $this->_curPre['nuked'] = Predb::PRE_OLDNUKE;
                        break;
                }
                $this->_curPre['reason'] = (isset($hits['reason']) ? substr($hits['reason'], 0, 255) : '');
                $this->_nuked = true; // flag for output
            }
            $this->_checkForDupe();
        } else {
            if ($this->_debug && ! $this->_silent) {
                echo '[DEBUG] Message did not match PRE regex pattern'.PHP_EOL;
            }
        }
    }

    /**
     * Check if we already have the PRE, update if we have it, insert if not.
     *
     * @throws \Exception
     */
    protected function _checkForDupe(): void
    {
        $this->_oldPre = Predb::query()->where('title', $this->_curPre['title'])->select(['category', 'size'])->first();
        if ($this->_oldPre === null) {
            if ($this->_debug && ! $this->_silent) {
                echo '[DEBUG] New PRE found, inserting: '.$this->_curPre['title'].PHP_EOL;
            }
            $this->_insertNewPre();
        } else {
            if ($this->_debug && ! $this->_silent) {
                echo '[DEBUG] PRE already exists, updating: '.$this->_curPre['title'].PHP_EOL;
            }
            $this->_updatePre();
        }
        $this->_resetPreVariables();
    }

    /**
     * Insert new PRE into the DB.
     *
     *
     * @throws \Exception
     */
    protected function _insertNewPre(): void
    {
        // Check if title is empty first
        if (empty($this->_curPre['title'])) {
            if ($this->_debug && ! $this->_silent) {
                echo '[DEBUG] PRE title is empty, skipping insert'.PHP_EOL;
            }

            return;
        }

        // Double-check database to ensure we don't have stale search index data
        $existingPre = Predb::query()->where('title', $this->_curPre['title'])->first();
        if ($existingPre !== null) {
            if ($this->_debug && ! $this->_silent) {
                echo '[DEBUG] PRE already exists in database (ID: '.$existingPre->id.'), skipping insert'.PHP_EOL;
            }

            return;
        }

        if ($this->_debug && ! $this->_silent) {
            echo '[DEBUG] PRE not in database, proceeding with insert...'.PHP_EOL;
        }

        $query = 'INSERT INTO predb (';

        $query .= (! empty($this->_curPre['size']) ? 'size, ' : '');
        $query .= (! empty($this->_curPre['category']) ? 'category, ' : '');
        $query .= (! empty($this->_curPre['source']) ? 'source, ' : '');
        $query .= (! empty($this->_curPre['reason']) ? 'nukereason, ' : '');
        $query .= (! empty($this->_curPre['files']) ? 'files, ' : '');
        $query .= (! empty($this->_curPre['reqid']) ? 'requestid, ' : '');
        $query .= (! empty($this->_curPre['group_id']) ? 'groups_id, ' : '');
        $query .= (! empty($this->_curPre['nuked']) ? 'nuked, ' : '');
        $query .= (! empty($this->_curPre['filename']) ? 'filename, ' : '');

        $query .= 'predate, title) VALUES (';

        $query .= (! empty($this->_curPre['size']) ? escapeString($this->_curPre['size']).', ' : '');
        $query .= (! empty($this->_curPre['category']) ? escapeString($this->_curPre['category']).', ' : '');
        $query .= (! empty($this->_curPre['source']) ? escapeString($this->_curPre['source']).', ' : '');
        $query .= (! empty($this->_curPre['reason']) ? escapeString($this->_curPre['reason']).', ' : '');
        $query .= (! empty($this->_curPre['files']) ? escapeString($this->_curPre['files']).', ' : '');
        $query .= (! empty($this->_curPre['reqid']) ? $this->_curPre['reqid'].', ' : '');
        $query .= (! empty($this->_curPre['group_id']) ? $this->_curPre['group_id'].', ' : '');
        $query .= (! empty($this->_curPre['nuked']) ? $this->_curPre['nuked'].', ' : '');
        $query .= (! empty($this->_curPre['filename']) ? escapeString($this->_curPre['filename']).', ' : '');
        $query .= (! empty($this->_curPre['predate']) ? $this->_curPre['predate'].', ' : 'NOW(), ');

        $query .= '%s)';

        if ($this->_debug && ! $this->_silent) {
            echo '[DEBUG] Executing SQL: '.substr($query, 0, 100).'...'.PHP_EOL;
        }

        try {
            DB::insert(
                sprintf(
                    $query,
                    escapeString($this->_curPre['title'])
                )
            );

            $lastId = DB::connection()->getPdo()->lastInsertId();

            if ($this->_debug && ! $this->_silent) {
                echo '[DEBUG] Successfully inserted PRE with ID: '.$lastId.PHP_EOL;
            }

            $parameters = [
                'id' => $lastId,
                'title' => $this->_curPre['title'],
                'filename' => $this->_curPre['filename'] ?? null,
                'source' => $this->_curPre['source'] ?? null,
            ];

            Search::insertPredb($parameters);

            $this->_doEcho(true);
        } catch (\Exception $e) {
            if ($this->_debug && ! $this->_silent) {
                echo '[DEBUG] ERROR inserting PRE: '.$e->getMessage().PHP_EOL;
            }
        }
    }

    /**
     * Updates PRE data in the DB.
     *
     *
     * @throws \Exception
     */
    protected function _updatePre(): void
    {
        if (empty($this->_curPre['title'])) {
            return;
        }

        $query = 'UPDATE predb SET ';

        $query .= (! empty($this->_curPre['size']) ? 'size = '.escapeString($this->_curPre['size']).', ' : '');
        $query .= (! empty($this->_curPre['source']) ? 'source = '.escapeString($this->_curPre['source']).', ' : '');
        $query .= (! empty($this->_curPre['files']) ? 'files = '.escapeString($this->_curPre['files']).', ' : '');
        $query .= (! empty($this->_curPre['reason']) ? 'nukereason = '.escapeString($this->_curPre['reason']).', ' : '');
        $query .= (! empty($this->_curPre['reqid']) ? 'requestid = '.$this->_curPre['reqid'].', ' : '');
        $query .= (! empty($this->_curPre['group_id']) ? 'groups_id = '.$this->_curPre['group_id'].', ' : '');
        $query .= (! empty($this->_curPre['predate']) ? 'predate = '.$this->_curPre['predate'].', ' : '');
        $query .= (! empty($this->_curPre['nuked']) ? 'nuked = '.$this->_curPre['nuked'].', ' : '');
        $query .= (! empty($this->_curPre['filename']) ? 'filename = '.escapeString($this->_curPre['filename']).', ' : '');
        $query .= (
            (empty($this->_oldPre['category']) && ! empty($this->_curPre['category']))
                ? 'category = '.escapeString($this->_curPre['category']).', '
                : ''
        );

        if ($query === 'UPDATE predb SET ') {
            return;
        }

        $query .= 'title = '.escapeString($this->_curPre['title']);
        $query .= ' WHERE title = '.escapeString($this->_curPre['title']);

        // Execute the update and then fetch the affected row ID by title.
        DB::update($query);

        // Look up the predb row ID by title for indexing backends.
        $predbId = Predb::query()->where('title', $this->_curPre['title'])->value('id');

        if (! empty($predbId)) {
            $parameters = [
                'id' => $predbId,
                'title' => $this->_curPre['title'],
                'filename' => $this->_curPre['filename'] ?? null,
                'source' => $this->_curPre['source'] ?? null,
            ];

            Search::updatePreDb($parameters);
        }

        $this->_doEcho(false);
    }

    /**
     * Echo new or update pre to CLI.
     */
    protected function _doEcho(bool $new = true): void
    {
        if (! $this->_silent) {
            $nukeString = '';
            if ($this->_nuked !== false) {
                switch ((int) $this->_curPre['nuked']) {
                    case Predb::PRE_NUKED:
                        $nukeString = '[ NUKED ] ';
                        break;
                    case Predb::PRE_UNNUKED:
                        $nukeString = '[UNNUKED] ';
                        break;
                    case Predb::PRE_MODNUKE:
                        $nukeString = '[MODNUKE] ';
                        break;
                    case Predb::PRE_OLDNUKE:
                        $nukeString = '[OLDNUKE] ';
                        break;
                    case Predb::PRE_RENUKED:
                        $nukeString = '[RENUKED] ';
                        break;
                    default:
                        break;
                }
                $nukeString .= '['.($this->_curPre['reason'] ?? '').'] ';
            }

            echo '['.
                date('r').
                ($new ? '] [ Added Pre ] [' : '] [Updated Pre] [').
                ($this->_curPre['source'] ?? '').
                '] '.
                $nukeString.
                '['.
                $this->_curPre['title'].
                ']'.
                (
                    ! empty($this->_curPre['category'])
                    ? ' ['.$this->_curPre['category'].']'
                    : (
                        ! empty($this->_oldPre['category'])
                        ? ' ['.$this->_oldPre['category'].']'
                        : ''
                    )
                ).
                (! empty($this->_curPre['size']) ? ' ['.$this->_curPre['size'].']' : '').
                PHP_EOL;
        }
    }

    /**
     * Get a group id for a group name.
     */
    protected function _getGroupID(string $groupName): mixed
    {
        if (! isset($this->_groupList[$groupName])) {
            $group = UsenetGroup::query()->where('name', $groupName)->first(['id']);
            $this->_groupList[$groupName] = $group !== null ? $group['id'] : '';
        }

        return $this->_groupList[$groupName];
    }

    /**
     * After updating or inserting new PRE, reset these.
     */
    protected function _resetPreVariables(): void
    {
        $this->_nuked = false;
        $this->_oldPre = [];
        $this->_curPre =
            [
                'title' => '',
                'size' => '',
                'predate' => '',
                'category' => '',
                'source' => '',
                'group_id' => '',
                'reqid' => '',
                'nuked' => '',
                'reason' => '',
                'files' => '',
                'filename' => '',
            ];
    }
}


1			<?php
2
3			namespace App\Services;
4
5			use App\Facades\Search;
6			use App\Models\Predb;
7			use App\Models\UsenetGroup;
8			use Illuminate\Support\Carbon;
9			use Illuminate\Support\Facades\DB;
10
11			/**
12			* Class IRCScraper.
13			*/
14			class IRCScraper extends IRCClient
15			{
16			/**
17			* Regex to ignore categories.
18			*/
19			protected string\|false $_categoryIgnoreRegex = false;
20
21			/**
22			* Array of current pre info.
23			*/
24			protected array $_curPre;
25
26			/**
27			* List of groups and their id's.
28			*/
29			protected array $_groupList;
30
31			/**
32			* Array of ignored channels.
33			*/
34			protected array $_ignoredChannels;
35
36			/**
37			* Is this pre nuked or un nuked?
38			*/
39			protected bool $_nuked;
40
41			protected $_oldPre;
42
43			/**
44			* Run this in silent mode (no text output).
45			*/
46			protected bool $_silent;
47
48			/**
49			* Regex to ignore PRE titles.
50			*/
51			protected string\|false $_titleIgnoreRegex = false;
52
53			/**
54			* Construct.
55			*
56			* @param bool $silent Run this in silent mode (no text output).
57			* @param bool $debug Turn on debug? Shows sent/received socket buffer messages.
58			*
59			* @throws \Exception
60			*/
61			public function __construct(bool $silent, bool $debug)
62			{
63			if (config('irc_settings.scrape_irc_source_ignore')) {
64			try {
65			$ignored = unserialize(
66			(string) config('irc_settings.scrape_irc_source_ignore'),
67			['allowed_classes' => false]
68			);
69			$this->_ignoredChannels = is_array($ignored) ? $ignored : [];
70			} catch (\ValueError $e) {
71			$this->_ignoredChannels = [];
72			}
73			} else {
74			$this->_ignoredChannels = [
75			'#a.b.cd.image' => false,
76			'#a.b.console.ps3' => false,
77			'#a.b.dvd' => false,
78			'#a.b.erotica' => false,
79			'#a.b.flac' => false,
80			'#a.b.foreign' => false,
81			'#a.b.games.nintendods' => false,
82			'#a.b.inner-sanctum' => false,
83			'#a.b.moovee' => false,
84			'#a.b.movies.divx' => false,
85			'#a.b.sony.psp' => false,
86			'#a.b.sounds.mp3.complete_cd' => false,
87			'#a.b.teevee' => false,
88			'#a.b.games.wii' => false,
89			'#a.b.warez' => false,
90			'#a.b.games.xbox360' => false,
91			'#pre@corrupt' => false,
92			'#scnzb' => false,
93			'#tvnzb' => false,
94			'srrdb' => false,
95			];
96			}
97
98			if (config('irc_settings.scrape_irc_category_ignore') !== '') {
99			$this->_categoryIgnoreRegex = (string) config('irc_settings.scrape_irc_category_ignore');
100			}
101
102			if (config('irc_settings.scrape_irc_title_ignore') !== '') {
103			$this->_titleIgnoreRegex = (string) config('irc_settings.scrape_irc_title_ignore');
104			}
105
106			$this->_groupList = [];
107			$this->_silent = $silent;
108			$this->_debug = $debug;
109			$this->_resetPreVariables();
110			$this->_startScraping();
111			}
112
113			/**
114			* Main method for scraping.
115			*/
116			protected function _startScraping(): void
117			{
118			// Connect to IRC.
119			if ($this->connect((string) config('irc_settings.scrape_irc_server'), (int) config('irc_settings.scrape_irc_port'), (bool) config('irc_settings.scrape_irc_tls')) === false) {
120			exit(
			0 ignored issues – show Best Practice introduced 2018-03-13 23:59 UTC by Report Bug Copy Issue Report Using `exit` here is not recommended. In general, usage of exit should be done with care and only when running in a scripting context like a CLI script. Loading history...
121			'Error connecting to ('.
122			config('irc_settings.scrape_irc_server').
123			':'.
124			config('irc_settings.scrape_irc_port').
125			'). Please verify your server information and try again.'.
126			PHP_EOL
127			);
128			}
129
130			// Normalize password to ?string
131			$password = config('irc_settings.scrape_irc_password');
132			$password = ($password === false \|\| $password === '' \|\| $password === null) ? null : (string) $password;
133
134			// Login to IRC. Note parameter order: nick, user, real, pass.
135			if ($this->login((string) config('irc_settings.scrape_irc_nickname'), (string) config('irc_settings.scrape_irc_username'), (string) config('irc_settings.scrape_irc_realname'), $password) === false) {
136			exit(
			0 ignored issues – show Best Practice introduced 2025-12-23 12:50 UTC by Report Bug Copy Issue Report Using `exit` here is not recommended. In general, usage of exit should be done with care and only when running in a scripting context like a CLI script. Loading history...
137			'Error logging in to: ('.
138			config('irc_settings.scrape_irc_server').':'.config('irc_settings.scrape_irc_port').') nickname: ('.config('irc_settings.scrape_irc_nickname').
139			'). Verify your connection information, you might also be banned from this server or there might have been a connection issue.'.
140			PHP_EOL
141			);
142			}
143
144			// Join channels.
145			$channelsCfg = config('irc_settings.scrape_irc_channels');
146			if ($channelsCfg) {
147			try {
148			$channels = unserialize((string) $channelsCfg, ['allowed_classes' => false]);
149			} catch (\ValueError $e) {
150			$channels = ['#PreNNTmux' => null];
151			}
152			if (! is_array($channels)) {
153			$channels = ['#PreNNTmux' => null];
154			}
155			} else {
156			$channels = ['#PreNNTmux' => null];
157			}
158			$this->joinChannels($channels);
159
160			if (! $this->_silent) {
161			echo '['.
162			date('r').
163			'] [Scraping of IRC channels for ('.
164			config('irc_settings.scrape_irc_server').
165			':'.
166			config('irc_settings.scrape_irc_port').
167			') ('.
168			config('irc_settings.scrape_irc_nickname').
169			') started.]'.
170			PHP_EOL;
171			}
172
173			// Scan incoming IRC messages.
174			$this->readIncoming();
175			}
176
177			/**
178			* Process bot messages, insert/update PREs.
179			*
180			* @throws \Exception
181			*/
182			protected function processChannelMessages(): void
183			{
184			if ($this->_debug && ! $this->_silent) {
185			echo '[DEBUG] Processing message: '.$this->_channelData['message'].PHP_EOL;
186			}
187
188			if (preg_match(
189			'/^(NEW\|UPD\|NUK): \[DT: (?P<time>.+?)\]\s?\[TT: (?P<title>.+?)\]\s?\[SC: (?P<source>.+?)\]\s?\[CT: (?P<category>.+?)\]\s?\[RQ: (?P<req>.+?)\]'.
190			'\s?\[SZ: (?P<size>.+?)\]\s?\[FL: (?P<files>.+?)\]\s?(\[FN: (?P<filename>.+?)\]\s?)?(\[(?P<nuked>(UN\|MOD\|RE\|OLD)?NUKED?): (?P<reason>.+?)\])?$/i',
191			$this->_channelData['message'],
192			$hits
193			)) {
194			if ($this->_debug && ! $this->_silent) {
195			echo '[DEBUG] Regex matched! Title: '.$hits['title'].' \| Source: '.$hits['source'].' \| Category: '.$hits['category'].PHP_EOL;
196			}
197
198			if (isset($this->_ignoredChannels[$hits['source']]) && $this->_ignoredChannels[$hits['source']] === true) {
199			if ($this->_debug && ! $this->_silent) {
200			echo '[DEBUG] Source '.$hits['source'].' is ignored, skipping...'.PHP_EOL;
201			}
202
203			return;
204			}
205
206			if ($this->_categoryIgnoreRegex !== false && preg_match((string) $this->_categoryIgnoreRegex, $hits['category'])) {
207			if ($this->_debug && ! $this->_silent) {
208			echo '[DEBUG] Category '.$hits['category'].' is ignored by regex, skipping...'.PHP_EOL;
209			}
210
211			return;
212			}
213
214			if ($this->_titleIgnoreRegex !== false && preg_match((string) $this->_titleIgnoreRegex, $hits['title'])) {
215			if ($this->_debug && ! $this->_silent) {
216			echo '[DEBUG] Title '.$hits['title'].' is ignored by regex, skipping...'.PHP_EOL;
217			}
218
219			return;
220			}
221
222			$utime = Carbon::createFromTimeString($hits['time'], 'UTC')->timestamp;
223
224			$this->_curPre['predate'] = 'FROM_UNIXTIME('.$utime.')';
225			$this->_curPre['title'] = $hits['title'];
226			$this->_curPre['source'] = $hits['source'];
227			if ($hits['category'] !== 'N/A') {
228			$this->_curPre['category'] = $hits['category'];
229			}
230			if ($hits['req'] !== 'N/A' && preg_match('/^(?P<req>\d+):(?P<group>.+)$/i', $hits['req'], $matches2)) {
231			$this->_curPre['reqid'] = $matches2['req'];
232			$this->_curPre['group_id'] = $this->_getGroupID($matches2['group']);
233			}
234			if ($hits['size'] !== 'N/A') {
235			$this->_curPre['size'] = $hits['size'];
236			}
237			if ($hits['files'] !== 'N/A') {
238			$this->_curPre['files'] = substr($hits['files'], 0, 50);
239			}
240
241			if (isset($hits['filename']) && $hits['filename'] !== 'N/A') {
242			$this->_curPre['filename'] = $hits['filename'];
243			}
244
245			if (isset($hits['nuked'])) {
246			switch ($hits['nuked']) {
247			case 'NUKED':
248			$this->_curPre['nuked'] = Predb::PRE_NUKED;
249			break;
250			case 'UNNUKED':
251			$this->_curPre['nuked'] = Predb::PRE_UNNUKED;
252			break;
253			case 'MODNUKED':
254			$this->_curPre['nuked'] = Predb::PRE_MODNUKE;
255			break;
256			case 'RENUKED':
257			$this->_curPre['nuked'] = Predb::PRE_RENUKED;
258			break;
259			case 'OLDNUKE':
260			$this->_curPre['nuked'] = Predb::PRE_OLDNUKE;
261			break;
262			}
263			$this->_curPre['reason'] = (isset($hits['reason']) ? substr($hits['reason'], 0, 255) : '');
264			$this->_nuked = true; // flag for output
265			}
266			$this->_checkForDupe();
267			} else {
268			if ($this->_debug && ! $this->_silent) {
269			echo '[DEBUG] Message did not match PRE regex pattern'.PHP_EOL;
270			}
271			}
272			}
273
274			/**
275			* Check if we already have the PRE, update if we have it, insert if not.
276			*
277			* @throws \Exception
278			*/
279			protected function _checkForDupe(): void
280			{
281			$this->_oldPre = Predb::query()->where('title', $this->_curPre['title'])->select(['category', 'size'])->first();
282			if ($this->_oldPre === null) {
283			if ($this->_debug && ! $this->_silent) {
284			echo '[DEBUG] New PRE found, inserting: '.$this->_curPre['title'].PHP_EOL;
285			}
286			$this->_insertNewPre();
287			} else {
288			if ($this->_debug && ! $this->_silent) {
289			echo '[DEBUG] PRE already exists, updating: '.$this->_curPre['title'].PHP_EOL;
290			}
291			$this->_updatePre();
292			}
293			$this->_resetPreVariables();
294			}
295
296			/**
297			* Insert new PRE into the DB.
298			*
299			*
300			* @throws \Exception
301			*/
302			protected function _insertNewPre(): void
303			{
304			// Check if title is empty first
305			if (empty($this->_curPre['title'])) {
306			if ($this->_debug && ! $this->_silent) {
307			echo '[DEBUG] PRE title is empty, skipping insert'.PHP_EOL;
308			}
309
310			return;
311			}
312
313			// Double-check database to ensure we don't have stale search index data
314			$existingPre = Predb::query()->where('title', $this->_curPre['title'])->first();
315			if ($existingPre !== null) {
316			if ($this->_debug && ! $this->_silent) {
317			echo '[DEBUG] PRE already exists in database (ID: '.$existingPre->id.'), skipping insert'.PHP_EOL;
318			}
319
320			return;
321			}
322
323			if ($this->_debug && ! $this->_silent) {
324			echo '[DEBUG] PRE not in database, proceeding with insert...'.PHP_EOL;
325			}
326
327			$query = 'INSERT INTO predb (';
328
329			$query .= (! empty($this->_curPre['size']) ? 'size, ' : '');
330			$query .= (! empty($this->_curPre['category']) ? 'category, ' : '');
331			$query .= (! empty($this->_curPre['source']) ? 'source, ' : '');
332			$query .= (! empty($this->_curPre['reason']) ? 'nukereason, ' : '');
333			$query .= (! empty($this->_curPre['files']) ? 'files, ' : '');
334			$query .= (! empty($this->_curPre['reqid']) ? 'requestid, ' : '');
335			$query .= (! empty($this->_curPre['group_id']) ? 'groups_id, ' : '');
336			$query .= (! empty($this->_curPre['nuked']) ? 'nuked, ' : '');
337			$query .= (! empty($this->_curPre['filename']) ? 'filename, ' : '');
338
339			$query .= 'predate, title) VALUES (';
340
341			$query .= (! empty($this->_curPre['size']) ? escapeString($this->_curPre['size']).', ' : '');
342			$query .= (! empty($this->_curPre['category']) ? escapeString($this->_curPre['category']).', ' : '');
343			$query .= (! empty($this->_curPre['source']) ? escapeString($this->_curPre['source']).', ' : '');
344			$query .= (! empty($this->_curPre['reason']) ? escapeString($this->_curPre['reason']).', ' : '');
345			$query .= (! empty($this->_curPre['files']) ? escapeString($this->_curPre['files']).', ' : '');
346			$query .= (! empty($this->_curPre['reqid']) ? $this->_curPre['reqid'].', ' : '');
347			$query .= (! empty($this->_curPre['group_id']) ? $this->_curPre['group_id'].', ' : '');
348			$query .= (! empty($this->_curPre['nuked']) ? $this->_curPre['nuked'].', ' : '');
349			$query .= (! empty($this->_curPre['filename']) ? escapeString($this->_curPre['filename']).', ' : '');
350			$query .= (! empty($this->_curPre['predate']) ? $this->_curPre['predate'].', ' : 'NOW(), ');
351
352			$query .= '%s)';
353
354			if ($this->_debug && ! $this->_silent) {
355			echo '[DEBUG] Executing SQL: '.substr($query, 0, 100).'...'.PHP_EOL;
356			}
357
358			try {
359			DB::insert(
360			sprintf(
361			$query,
362			escapeString($this->_curPre['title'])
363			)
364			);
365
366			$lastId = DB::connection()->getPdo()->lastInsertId();
367
368			if ($this->_debug && ! $this->_silent) {
369			echo '[DEBUG] Successfully inserted PRE with ID: '.$lastId.PHP_EOL;
370			}
371
372			$parameters = [
373			'id' => $lastId,
374			'title' => $this->_curPre['title'],
375			'filename' => $this->_curPre['filename'] ?? null,
376			'source' => $this->_curPre['source'] ?? null,
377			];
378
379			Search::insertPredb($parameters);
380
381			$this->_doEcho(true);
382			} catch (\Exception $e) {
383			if ($this->_debug && ! $this->_silent) {
384			echo '[DEBUG] ERROR inserting PRE: '.$e->getMessage().PHP_EOL;
385			}
386			}
387			}
388
389			/**
390			* Updates PRE data in the DB.
391			*
392			*
393			* @throws \Exception
394			*/
395			protected function _updatePre(): void
396			{
397			if (empty($this->_curPre['title'])) {
398			return;
399			}
400
401			$query = 'UPDATE predb SET ';
402
403			$query .= (! empty($this->_curPre['size']) ? 'size = '.escapeString($this->_curPre['size']).', ' : '');
404			$query .= (! empty($this->_curPre['source']) ? 'source = '.escapeString($this->_curPre['source']).', ' : '');
405			$query .= (! empty($this->_curPre['files']) ? 'files = '.escapeString($this->_curPre['files']).', ' : '');
406			$query .= (! empty($this->_curPre['reason']) ? 'nukereason = '.escapeString($this->_curPre['reason']).', ' : '');
407			$query .= (! empty($this->_curPre['reqid']) ? 'requestid = '.$this->_curPre['reqid'].', ' : '');
408			$query .= (! empty($this->_curPre['group_id']) ? 'groups_id = '.$this->_curPre['group_id'].', ' : '');
409			$query .= (! empty($this->_curPre['predate']) ? 'predate = '.$this->_curPre['predate'].', ' : '');
410			$query .= (! empty($this->_curPre['nuked']) ? 'nuked = '.$this->_curPre['nuked'].', ' : '');
411			$query .= (! empty($this->_curPre['filename']) ? 'filename = '.escapeString($this->_curPre['filename']).', ' : '');
412			$query .= (
413			(empty($this->_oldPre['category']) && ! empty($this->_curPre['category']))
414			? 'category = '.escapeString($this->_curPre['category']).', '
415			: ''
416			);
417
418			if ($query === 'UPDATE predb SET ') {
419			return;
420			}
421
422			$query .= 'title = '.escapeString($this->_curPre['title']);
423			$query .= ' WHERE title = '.escapeString($this->_curPre['title']);
424
425			// Execute the update and then fetch the affected row ID by title.
426			DB::update($query);
427
428			// Look up the predb row ID by title for indexing backends.
429			$predbId = Predb::query()->where('title', $this->_curPre['title'])->value('id');
430
431			if (! empty($predbId)) {
432			$parameters = [
433			'id' => $predbId,
434			'title' => $this->_curPre['title'],
435			'filename' => $this->_curPre['filename'] ?? null,
436			'source' => $this->_curPre['source'] ?? null,
437			];
438
439			Search::updatePreDb($parameters);
440			}
441
442			$this->_doEcho(false);
443			}
444
445			/**
446			* Echo new or update pre to CLI.
447			*/
448			protected function _doEcho(bool $new = true): void
449			{
450			if (! $this->_silent) {
451			$nukeString = '';
452			if ($this->_nuked !== false) {
453			switch ((int) $this->_curPre['nuked']) {
454			case Predb::PRE_NUKED:
455			$nukeString = '[ NUKED ] ';
456			break;
457			case Predb::PRE_UNNUKED:
458			$nukeString = '[UNNUKED] ';
459			break;
460			case Predb::PRE_MODNUKE:
461			$nukeString = '[MODNUKE] ';
462			break;
463			case Predb::PRE_OLDNUKE:
464			$nukeString = '[OLDNUKE] ';
465			break;
466			case Predb::PRE_RENUKED:
467			$nukeString = '[RENUKED] ';
468			break;
469			default:
470			break;
471			}
472			$nukeString .= '['.($this->_curPre['reason'] ?? '').'] ';
473			}
474
475			echo '['.
476			date('r').
477			($new ? '] [ Added Pre ] [' : '] [Updated Pre] [').
478			($this->_curPre['source'] ?? '').
479			'] '.
480			$nukeString.
481			'['.
482			$this->_curPre['title'].
483			']'.
484			(
485			! empty($this->_curPre['category'])
486			? ' ['.$this->_curPre['category'].']'
487			: (
488			! empty($this->_oldPre['category'])
489			? ' ['.$this->_oldPre['category'].']'
490			: ''
491			)
492			).
493			(! empty($this->_curPre['size']) ? ' ['.$this->_curPre['size'].']' : '').
494			PHP_EOL;
495			}
496			}
497
498			/**
499			* Get a group id for a group name.
500			*/
501			protected function _getGroupID(string $groupName): mixed
502			{
503			if (! isset($this->_groupList[$groupName])) {
504			$group = UsenetGroup::query()->where('name', $groupName)->first(['id']);
505			$this->_groupList[$groupName] = $group !== null ? $group['id'] : '';
506			}
507
508			return $this->_groupList[$groupName];
509			}
510
511			/**
512			* After updating or inserting new PRE, reset these.
513			*/
514			protected function _resetPreVariables(): void
515			{
516			$this->_nuked = false;
517			$this->_oldPre = [];
518			$this->_curPre =
519			[
520			'title' => '',
521			'size' => '',
522			'predate' => '',
523			'category' => '',
524			'source' => '',
525			'group_id' => '',
526			'reqid' => '',
527			'nuked' => '',
528			'reason' => '',
529			'files' => '',
530			'filename' => '',
531			];
532			}
533			}
534

NNTmux / newznab-tmux

IRCScraper::processChannelMessages() F last analyzed 2026-01-22 09:47 UTC

Complexity

Size

Duplication

Importance

How to fix Long Method Complexity

Long Method

Duplication Side-by-Side

Filter issues like

IRCScraper::processChannelMessages() F
last analyzed 2026-01-22 09:47 UTC