aboutsummaryrefslogtreecommitdiffhomepage
path: root/application/http/HttpUtils.php
blob: ed1002b04770b1e5628581c8f9046b96c5cc950c (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
<?php

use Shaarli\Http\Url;

/**
 * GET an HTTP URL to retrieve its content
 * Uses the cURL library or a fallback method
 *
 * @param string          $url                URL to get (http://...)
 * @param int             $timeout            network timeout (in seconds)
 * @param int             $maxBytes           maximum downloaded bytes (default: 4 MiB)
 * @param callable|string $curlHeaderFunction Optional callback called during the download of headers
 *                                            (CURLOPT_HEADERFUNCTION)
 * @param callable|string $curlWriteFunction  Optional callback called during the download (cURL CURLOPT_WRITEFUNCTION).
 *                                            Can be used to add download conditions on the
 *                                            headers (response code, content type, etc.).
 *
 * @return array HTTP response headers, downloaded content
 *
 * Output format:
 *  [0] = associative array containing HTTP response headers
 *  [1] = URL content (downloaded data)
 *
 * Example:
 *  list($headers, $data) = get_http_response('http://sebauvage.net/');
 *  if (strpos($headers[0], '200 OK') !== false) {
 *      echo 'Data type: '.htmlspecialchars($headers['Content-Type']);
 *  } else {
 *      echo 'There was an error: '.htmlspecialchars($headers[0]);
 *  }
 *
 * @see https://secure.php.net/manual/en/ref.curl.php
 * @see https://secure.php.net/manual/en/functions.anonymous.php
 * @see https://secure.php.net/manual/en/function.preg-split.php
 * @see https://secure.php.net/manual/en/function.explode.php
 * @see http://stackoverflow.com/q/17641073
 * @see http://stackoverflow.com/q/9183178
 * @see http://stackoverflow.com/q/1462720
 */
function get_http_response(
    $url,
    $timeout = 30,
    $maxBytes = 4194304,
    $curlHeaderFunction = null,
    $curlWriteFunction = null
) {
    $urlObj = new Url($url);
    $cleanUrl = $urlObj->idnToAscii();

    if (!filter_var($cleanUrl, FILTER_VALIDATE_URL) || !$urlObj->isHttp()) {
        return array(array(0 => 'Invalid HTTP UrlUtils'), false);
    }

    $userAgent =
        'Mozilla/5.0 (X11; Fedora; Linux x86_64; rv:45.0)'
        . ' Gecko/20100101 Firefox/45.0';
    $acceptLanguage =
        substr(setlocale(LC_COLLATE, 0), 0, 2) . ',en-US;q=0.7,en;q=0.3';
    $maxRedirs = 3;

    if (!function_exists('curl_init')) {
        return get_http_response_fallback(
            $cleanUrl,
            $timeout,
            $maxBytes,
            $userAgent,
            $acceptLanguage,
            $maxRedirs
        );
    }

    $ch = curl_init($cleanUrl);
    if ($ch === false) {
        return array(array(0 => 'curl_init() error'), false);
    }

    // General cURL settings
    curl_setopt($ch, CURLOPT_AUTOREFERER, true);
    curl_setopt($ch, CURLOPT_FOLLOWLOCATION, true);
    // Default header download if the $curlHeaderFunction is not defined
    curl_setopt($ch, CURLOPT_HEADER, !is_callable($curlHeaderFunction));
    curl_setopt(
        $ch,
        CURLOPT_HTTPHEADER,
        array('Accept-Language: ' . $acceptLanguage)
    );
    curl_setopt($ch, CURLOPT_MAXREDIRS, $maxRedirs);
    curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
    curl_setopt($ch, CURLOPT_TIMEOUT, $timeout);
    curl_setopt($ch, CURLOPT_USERAGENT, $userAgent);

    // Max download size management
    curl_setopt($ch, CURLOPT_BUFFERSIZE, 1024*16);
    curl_setopt($ch, CURLOPT_NOPROGRESS, false);
    if (is_callable($curlHeaderFunction)) {
        curl_setopt($ch, CURLOPT_HEADERFUNCTION, $curlHeaderFunction);
    }
    if (is_callable($curlWriteFunction)) {
        curl_setopt($ch, CURLOPT_WRITEFUNCTION, $curlWriteFunction);
    }
    curl_setopt(
        $ch,
        CURLOPT_PROGRESSFUNCTION,
        function ($arg0, $arg1, $arg2, $arg3, $arg4) use ($maxBytes) {
            $downloaded = $arg2;

            // Non-zero return stops downloading
            return ($downloaded > $maxBytes) ? 1 : 0;
        }
    );

    $response = curl_exec($ch);
    $errorNo = curl_errno($ch);
    $errorStr = curl_error($ch);
    $headSize = curl_getinfo($ch, CURLINFO_HEADER_SIZE);
    curl_close($ch);

    if ($response === false) {
        if ($errorNo == CURLE_COULDNT_RESOLVE_HOST) {
            /*
             * Workaround to match fallback method behaviour
             * Removing this would require updating
             * GetHttpUrlTest::testGetInvalidRemoteUrl()
             */
            return array(false, false);
        }
        return array(array(0 => 'curl_exec() error: ' . $errorStr), false);
    }

    // Formatting output like the fallback method
    $rawHeaders = substr($response, 0, $headSize);

    // Keep only headers from latest redirection
    $rawHeadersArrayRedirs = explode("\r\n\r\n", trim($rawHeaders));
    $rawHeadersLastRedir = end($rawHeadersArrayRedirs);

    $content = substr($response, $headSize);
    $headers = array();
    foreach (preg_split('~[\r\n]+~', $rawHeadersLastRedir) as $line) {
        if (empty($line) || ctype_space($line)) {
            continue;
        }
        $splitLine = explode(': ', $line, 2);
        if (count($splitLine) > 1) {
            $key = $splitLine[0];
            $value = $splitLine[1];
            if (array_key_exists($key, $headers)) {
                if (!is_array($headers[$key])) {
                    $headers[$key] = array(0 => $headers[$key]);
                }
                $headers[$key][] = $value;
            } else {
                $headers[$key] = $value;
            }
        } else {
            $headers[] = $splitLine[0];
        }
    }

    return array($headers, $content);
}

/**
 * GET an HTTP URL to retrieve its content (fallback method)
 *
 * @param string $cleanUrl       URL to get (http://... valid and in ASCII form)
 * @param int    $timeout        network timeout (in seconds)
 * @param int    $maxBytes       maximum downloaded bytes
 * @param string $userAgent      "User-Agent" header
 * @param string $acceptLanguage "Accept-Language" header
 * @param int    $maxRedr        maximum amount of redirections followed
 *
 * @return array HTTP response headers, downloaded content
 *
 * Output format:
 *  [0] = associative array containing HTTP response headers
 *  [1] = URL content (downloaded data)
 *
 * @see http://php.net/manual/en/function.file-get-contents.php
 * @see http://php.net/manual/en/function.stream-context-create.php
 * @see http://php.net/manual/en/function.get-headers.php
 */
function get_http_response_fallback(
    $cleanUrl,
    $timeout,
    $maxBytes,
    $userAgent,
    $acceptLanguage,
    $maxRedr
) {
    $options = array(
        'http' => array(
            'method' => 'GET',
            'timeout' => $timeout,
            'user_agent' => $userAgent,
            'header' => "Accept: */*\r\n"
                . 'Accept-Language: ' . $acceptLanguage
        )
    );

    stream_context_set_default($options);
    list($headers, $finalUrl) = get_redirected_headers($cleanUrl, $maxRedr);
    if (! $headers || strpos($headers[0], '200 OK') === false) {
        $options['http']['request_fulluri'] = true;
        stream_context_set_default($options);
        list($headers, $finalUrl) = get_redirected_headers($cleanUrl, $maxRedr);
    }

    if (! $headers) {
        return array($headers, false);
    }

    try {
        // TODO: catch Exception in calling code (thumbnailer)
        $context = stream_context_create($options);
        $content = file_get_contents($finalUrl, false, $context, -1, $maxBytes);
    } catch (Exception $exc) {
        return array(array(0 => 'HTTP Error'), $exc->getMessage());
    }

    return array($headers, $content);
}

/**
 * Retrieve HTTP headers, following n redirections (temporary and permanent ones).
 *
 * @param string $url              initial URL to reach.
 * @param int    $redirectionLimit max redirection follow.
 *
 * @return array HTTP headers, or false if it failed.
 */
function get_redirected_headers($url, $redirectionLimit = 3)
{
    $headers = get_headers($url, 1);
    if (!empty($headers['location']) && empty($headers['Location'])) {
        $headers['Location'] = $headers['location'];
    }

    // Headers found, redirection found, and limit not reached.
    if ($redirectionLimit-- > 0
        && !empty($headers)
        && (strpos($headers[0], '301') !== false || strpos($headers[0], '302') !== false)
        && !empty($headers['Location'])) {
        $redirection = is_array($headers['Location']) ? end($headers['Location']) : $headers['Location'];
        if ($redirection != $url) {
            $redirection = getAbsoluteUrl($url, $redirection);
            return get_redirected_headers($redirection, $redirectionLimit);
        }
    }

    return array($headers, $url);
}

/**
 * Get an absolute URL from a complete one, and another absolute/relative URL.
 *
 * @param string $originalUrl The original complete URL.
 * @param string $newUrl      The new one, absolute or relative.
 *
 * @return string Final URL:
 *   - $newUrl if it was already an absolute URL.
 *   - if it was relative, absolute URL from $originalUrl path.
 */
function getAbsoluteUrl($originalUrl, $newUrl)
{
    $newScheme = parse_url($newUrl, PHP_URL_SCHEME);
    // Already an absolute URL.
    if (!empty($newScheme)) {
        return $newUrl;
    }

    $parts = parse_url($originalUrl);
    $final = $parts['scheme'] .'://'. $parts['host'];
    $final .= (!empty($parts['port'])) ? $parts['port'] : '';
    $final .= '/';
    if ($newUrl[0] != '/') {
        $final .= substr(ltrim($parts['path'], '/'), 0, strrpos($parts['path'], '/'));
    }
    $final .= ltrim($newUrl, '/');
    return $final;
}

/**
 * Returns the server's base URL: scheme://domain.tld[:port]
 *
 * @param array $server the $_SERVER array
 *
 * @return string the server's base URL
 *
 * @see http://www.ietf.org/rfc/rfc7239.txt
 * @see http://www.ietf.org/rfc/rfc6648.txt
 * @see http://stackoverflow.com/a/3561399
 * @see http://stackoverflow.com/q/452375
 */
function server_url($server)
{
    $scheme = 'http';
    $port = '';

    // Shaarli is served behind a proxy
    if (isset($server['HTTP_X_FORWARDED_PROTO'])) {
        // Keep forwarded scheme
        if (strpos($server['HTTP_X_FORWARDED_PROTO'], ',') !== false) {
            $schemes = explode(',', $server['HTTP_X_FORWARDED_PROTO']);
            $scheme = trim($schemes[0]);
        } else {
            $scheme = $server['HTTP_X_FORWARDED_PROTO'];
        }

        if (isset($server['HTTP_X_FORWARDED_PORT'])) {
            // Keep forwarded port
            if (strpos($server['HTTP_X_FORWARDED_PORT'], ',') !== false) {
                $ports = explode(',', $server['HTTP_X_FORWARDED_PORT']);
                $port = trim($ports[0]);
            } else {
                $port = $server['HTTP_X_FORWARDED_PORT'];
            }

            // This is a workaround for proxies that don't forward the scheme properly.
            // Connecting over port 443 has to be in HTTPS.
            // See https://github.com/shaarli/Shaarli/issues/1022
            if ($port == '443') {
                $scheme = 'https';
            }

            if (($scheme == 'http' && $port != '80')
                || ($scheme == 'https' && $port != '443')
            ) {
                $port = ':' . $port;
            } else {
                $port = '';
            }
        }

        if (isset($server['HTTP_X_FORWARDED_HOST'])) {
            // Keep forwarded host
            if (strpos($server['HTTP_X_FORWARDED_HOST'], ',') !== false) {
                $hosts = explode(',', $server['HTTP_X_FORWARDED_HOST']);
                $host = trim($hosts[0]);
            } else {
                $host = $server['HTTP_X_FORWARDED_HOST'];
            }
        } else {
            $host = $server['SERVER_NAME'];
        }

        return $scheme.'://'.$host.$port;
    }

    // SSL detection
    if ((! empty($server['HTTPS']) && strtolower($server['HTTPS']) == 'on')
        || (isset($server['SERVER_PORT']) && $server['SERVER_PORT'] == '443')) {
        $scheme = 'https';
    }

    // Do not append standard port values
    if (($scheme == 'http' && $server['SERVER_PORT'] != '80')
        || ($scheme == 'https' && $server['SERVER_PORT'] != '443')) {
        $port = ':'.$server['SERVER_PORT'];
    }

    return $scheme.'://'.$server['SERVER_NAME'].$port;
}

/**
 * Returns the absolute URL of the current script, without the query
 *
 * If the resource is "index.php", then it is removed (for better-looking URLs)
 *
 * @param array $server the $_SERVER array
 *
 * @return string the absolute URL of the current script, without the query
 */
function index_url($server)
{
    if (defined('SHAARLI_ROOT_URL') && null !== SHAARLI_ROOT_URL) {
        return rtrim(SHAARLI_ROOT_URL, '/') . '/';
    }

    $scriptname = !empty($server['SCRIPT_NAME']) ? $server['SCRIPT_NAME'] : '/';
    if (endsWith($scriptname, 'index.php')) {
        $scriptname = substr($scriptname, 0, -9);
    }
    return server_url($server) . $scriptname;
}

/**
 * Returns the absolute URL of the current script, with current route and query
 *
 * If the resource is "index.php", then it is removed (for better-looking URLs)
 *
 * @param array $server the $_SERVER array
 *
 * @return string the absolute URL of the current script, with the query
 */
function page_url($server)
{
    $scriptname = $server['SCRIPT_NAME'] ?? '';
    if (endsWith($scriptname, 'index.php')) {
        $scriptname = substr($scriptname, 0, -9);
    }

    $route = preg_replace('@^' . $scriptname . '@', '', $server['REQUEST_URI'] ?? '');
    if (! empty($server['QUERY_STRING'])) {
        return index_url($server) . $route . '?' . $server['QUERY_STRING'];
    }

    return index_url($server) . $route;
}

/**
 * Retrieve the initial IP forwarded by the reverse proxy.
 *
 * Inspired from: https://github.com/zendframework/zend-http/blob/master/src/PhpEnvironment/RemoteAddress.php
 *
 * @param array $server     $_SERVER array which contains HTTP headers.
 * @param array $trustedIps List of trusted IP from the configuration.
 *
 * @return string|bool The forwarded IP, or false if none could be extracted.
 */
function getIpAddressFromProxy($server, $trustedIps)
{
    $forwardedIpHeader = 'HTTP_X_FORWARDED_FOR';
    if (empty($server[$forwardedIpHeader])) {
        return false;
    }

    $ips = preg_split('/\s*,\s*/', $server[$forwardedIpHeader]);
    $ips = array_diff($ips, $trustedIps);
    if (empty($ips)) {
        return false;
    }

    return array_pop($ips);
}


/**
 * Return an identifier based on the advertised client IP address(es)
 *
 * This aims at preventing session hijacking from users behind the same proxy
 * by relying on HTTP headers.
 *
 * See:
 * - https://secure.php.net/manual/en/reserved.variables.server.php
 * - https://stackoverflow.com/questions/3003145/how-to-get-the-client-ip-address-in-php
 * - https://stackoverflow.com/questions/12233406/preventing-session-hijacking
 * - https://stackoverflow.com/questions/21354859/trusting-x-forwarded-for-to-identify-a-visitor
 *
 * @param array $server The $_SERVER array
 *
 * @return string An identifier based on client IP address information
 */
function client_ip_id($server)
{
    $ip = $server['REMOTE_ADDR'];

    if (isset($server['HTTP_X_FORWARDED_FOR'])) {
        $ip = $ip . '_' . $server['HTTP_X_FORWARDED_FOR'];
    }
    if (isset($server['HTTP_CLIENT_IP'])) {
        $ip = $ip . '_' . $server['HTTP_CLIENT_IP'];
    }
    return $ip;
}


/**
 * Returns true if Shaarli's currently browsed in HTTPS.
 * Supports reverse proxies (if the headers are correctly set).
 *
 * @param array $server $_SERVER.
 *
 * @return bool true if HTTPS, false otherwise.
 */
function is_https($server)
{

    if (isset($server['HTTP_X_FORWARDED_PORT'])) {
        // Keep forwarded port
        if (strpos($server['HTTP_X_FORWARDED_PORT'], ',') !== false) {
            $ports = explode(',', $server['HTTP_X_FORWARDED_PORT']);
            $port = trim($ports[0]);
        } else {
            $port = $server['HTTP_X_FORWARDED_PORT'];
        }

        if ($port == '443') {
            return true;
        }
    }

    return ! empty($server['HTTPS']);
}

/**
 * Get cURL callback function for CURLOPT_WRITEFUNCTION
 *
 * @param string $charset     to extract from the downloaded page (reference)
 * @param string $curlGetInfo Optionally overrides curl_getinfo function
 *
 * @return Closure
 */
function get_curl_header_callback(
    &$charset,
    $curlGetInfo = 'curl_getinfo'
) {
    $isRedirected = false;

    return function ($ch, $data) use ($curlGetInfo, &$charset, &$isRedirected) {
        $responseCode = $curlGetInfo($ch, CURLINFO_RESPONSE_CODE);
        $chunkLength = strlen($data);
        if (!empty($responseCode) && in_array($responseCode, [301, 302])) {
            $isRedirected = true;
            return $chunkLength;
        }
        if (!empty($responseCode) && $responseCode !== 200) {
            return false;
        }
        // After a redirection, the content type will keep the previous request value
        // until it finds the next content-type header.
        if (! $isRedirected || strpos(strtolower($data), 'content-type') !== false) {
            $contentType = $curlGetInfo($ch, CURLINFO_CONTENT_TYPE);
        }
        if (!empty($contentType) && strpos($contentType, 'text/html') === false) {
            return false;
        }
        if (!empty($contentType) && empty($charset)) {
            $charset = header_extract_charset($contentType);
        }

        return $chunkLength;
    };
}

/**
 * Get cURL callback function for CURLOPT_WRITEFUNCTION
 *
 * @param string $charset     to extract from the downloaded page (reference)
 * @param string $title       to extract from the downloaded page (reference)
 * @param string $description to extract from the downloaded page (reference)
 * @param string $keywords    to extract from the downloaded page (reference)
 * @param bool   $retrieveDescription Automatically tries to retrieve description and keywords from HTML content
 * @param string $curlGetInfo Optionally overrides curl_getinfo function
 *
 * @return Closure
 */
function get_curl_download_callback(
    &$charset,
    &$title,
    &$description,
    &$keywords,
    $retrieveDescription,
    $tagsSeparator
) {
    $currentChunk = 0;
    $foundChunk = null;

    /**
     * cURL callback function for CURLOPT_WRITEFUNCTION (called during the download).
     *
     * While downloading the remote page, we check that the HTTP code is 200 and content type is 'html/text'
     * Then we extract the title and the charset and stop the download when it's done.
     *
     * @param resource $ch   cURL resource
     * @param string   $data chunk of data being downloaded
     *
     * @return int|bool length of $data or false if we need to stop the download
     */
    return function ($ch, $data) use (
        $retrieveDescription,
        $tagsSeparator,
        &$charset,
        &$title,
        &$description,
        &$keywords,
        &$currentChunk,
        &$foundChunk
    ) {
        $chunkLength = strlen($data);
        $currentChunk++;

        if (empty($charset)) {
            $charset = html_extract_charset($data);
        }
        if (empty($title)) {
            $title = html_extract_title($data);
            $foundChunk = ! empty($title) ? $currentChunk : $foundChunk;
        }
        if (empty($title)) {
            $title = html_extract_tag('title', $data);
            $foundChunk = ! empty($title) ? $currentChunk : $foundChunk;
        }
        if ($retrieveDescription && empty($description)) {
            $description = html_extract_tag('description', $data);
            $foundChunk = ! empty($description) ? $currentChunk : $foundChunk;
        }
        if ($retrieveDescription && empty($keywords)) {
            $keywords = html_extract_tag('keywords', $data);
            if (! empty($keywords)) {
                $foundChunk = $currentChunk;
                // Keywords use the format tag1, tag2 multiple words, tag
                // So we split the result with `,`, then if a tag contains the separator we replace it by `-`.
                $keywords = tags_array2str(array_map(function(string $keyword) use ($tagsSeparator): string {
                    return tags_array2str(tags_str2array($keyword, $tagsSeparator), '-');
                }, tags_str2array($keywords, ',')), $tagsSeparator);
            }
        }

        // We got everything we want, stop the download.
        // If we already found either the title, description or keywords,
        // it's highly unlikely that we'll found the other metas further than
        // in the same chunk of data or the next one. So we also stop the download after that.
        if ((!empty($responseCode) && !empty($contentType) && !empty($charset)) && $foundChunk !== null
            && (! $retrieveDescription
                || $foundChunk < $currentChunk
                || (!empty($title) && !empty($description) && !empty($keywords))
            )
        ) {
            return false;
        }

        return $chunkLength;
    };
}