urlmatch.c 18.1 KB
Newer Older
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
#include "cache.h"
#include "urlmatch.h"

#define URL_ALPHA "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz"
#define URL_DIGIT "0123456789"
#define URL_ALPHADIGIT URL_ALPHA URL_DIGIT
#define URL_SCHEME_CHARS URL_ALPHADIGIT "+.-"
#define URL_HOST_CHARS URL_ALPHADIGIT ".-[:]" /* IPv6 literals need [:] */
#define URL_UNSAFE_CHARS " <>\"%{}|\\^`" /* plus 0x00-0x1F,0x7F-0xFF */
#define URL_GEN_RESERVED ":/?#[]@"
#define URL_SUB_RESERVED "!$&'()*+,;="
#define URL_RESERVED URL_GEN_RESERVED URL_SUB_RESERVED /* only allowed delims */

static int append_normalized_escapes(struct strbuf *buf,
				     const char *from,
				     size_t from_len,
				     const char *esc_extra,
				     const char *esc_ok)
{
	/*
	 * Append to strbuf 'buf' characters from string 'from' with length
	 * 'from_len' while unescaping characters that do not need to be escaped
	 * and escaping characters that do.  The set of characters to escape
	 * (the complement of which is unescaped) starts out as the RFC 3986
	 * unsafe characters (0x00-0x1F,0x7F-0xFF," <>\"#%{}|\\^`").  If
	 * 'esc_extra' is not NULL, those additional characters will also always
	 * be escaped.  If 'esc_ok' is not NULL, those characters will be left
	 * escaped if found that way, but will not be unescaped otherwise (used
	 * for delimiters).  If a %-escape sequence is encountered that is not
	 * followed by 2 hexadecimal digits, the sequence is invalid and
	 * false (0) will be returned.  Otherwise true (1) will be returned for
	 * success.
	 *
	 * Note that all %-escape sequences will be normalized to UPPERCASE
	 * as indicated in RFC 3986.  Unless included in esc_extra or esc_ok
	 * alphanumerics and "-._~" will always be unescaped as per RFC 3986.
	 */

	while (from_len) {
		int ch = *from++;
		int was_esc = 0;

		from_len--;
		if (ch == '%') {
45
			if (from_len < 2)
46
				return 0;
47 48 49 50
			ch = hex2chr(from);
			if (ch < 0)
				return 0;
			from += 2;
51 52 53 54 55 56 57 58 59 60 61 62 63 64 65
			from_len -= 2;
			was_esc = 1;
		}
		if ((unsigned char)ch <= 0x1F || (unsigned char)ch >= 0x7F ||
		    strchr(URL_UNSAFE_CHARS, ch) ||
		    (esc_extra && strchr(esc_extra, ch)) ||
		    (was_esc && strchr(esc_ok, ch)))
			strbuf_addf(buf, "%%%02X", (unsigned char)ch);
		else
			strbuf_addch(buf, ch);
	}

	return 1;
}

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
static const char *end_of_token(const char *s, int c, size_t n)
{
	const char *next = memchr(s, c, n);
	if (!next)
		next = s + n;
	return next;
}

static int match_host(const struct url_info *url_info,
		      const struct url_info *pattern_info)
{
	const char *url = url_info->url + url_info->host_off;
	const char *pat = pattern_info->url + pattern_info->host_off;
	int url_len = url_info->host_len;
	int pat_len = pattern_info->host_len;

	while (url_len && pat_len) {
		const char *url_next = end_of_token(url, '.', url_len);
		const char *pat_next = end_of_token(pat, '.', pat_len);

		if (pat_next == pat + 1 && pat[0] == '*')
			/* wildcard matches anything */
			;
		else if ((pat_next - pat) == (url_next - url) &&
			 !memcmp(url, pat, url_next - url))
			/* the components are the same */
			;
		else
			return 0; /* found an unmatch */

		if (url_next < url + url_len)
			url_next++;
		url_len -= url_next - url;
		url = url_next;
		if (pat_next < pat + pat_len)
			pat_next++;
		pat_len -= pat_next - pat;
		pat = pat_next;
	}

	return (!url_len && !pat_len);
}

109
static char *url_normalize_1(const char *url, struct url_info *out_info, char allow_globs)
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
{
	/*
	 * Normalize NUL-terminated url using the following rules:
	 *
	 * 1. Case-insensitive parts of url will be converted to lower case
	 * 2. %-encoded characters that do not need to be will be unencoded
	 * 3. Characters that are not %-encoded and must be will be encoded
	 * 4. All %-encodings will be converted to upper case hexadecimal
	 * 5. Leading 0s are removed from port numbers
	 * 6. If the default port for the scheme is given it will be removed
	 * 7. A path part (including empty) not starting with '/' has one added
	 * 8. Any dot segments (. or ..) in the path are resolved and removed
	 * 9. IPv6 host literals are allowed (but not normalized or validated)
	 *
	 * The rules are based on information in RFC 3986.
	 *
	 * Please note this function requires a full URL including a scheme
	 * and host part (except for file: URLs which may have an empty host).
	 *
	 * The return value is a newly allocated string that must be freed
	 * or NULL if the url is not valid.
	 *
	 * If out_info is non-NULL, the url and err fields therein will always
	 * be set.  If a non-NULL value is returned, it will be stored in
	 * out_info->url as well, out_info->err will be set to NULL and the
	 * other fields of *out_info will also be filled in.  If a NULL value
	 * is returned, NULL will be stored in out_info->url and out_info->err
	 * will be set to a brief, translated, error message, but no other
	 * fields will be filled in.
	 *
	 * This is NOT a URL validation function.  Full URL validation is NOT
	 * performed.  Some invalid host names are passed through this function
	 * undetected.  However, most all other problems that make a URL invalid
	 * will be detected (including a missing host for non file: URLs).
	 */

	size_t url_len = strlen(url);
	struct strbuf norm;
	size_t spanned;
	size_t scheme_len, user_off=0, user_len=0, passwd_off=0, passwd_len=0;
150
	size_t host_off=0, host_len=0, port_off=0, port_len=0, path_off, path_len, result_len;
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
	const char *slash_ptr, *at_ptr, *colon_ptr, *path_start;
	char *result;

	/*
	 * Copy lowercased scheme and :// suffix, %-escapes are not allowed
	 * First character of scheme must be URL_ALPHA
	 */
	spanned = strspn(url, URL_SCHEME_CHARS);
	if (!spanned || !isalpha(url[0]) || spanned + 3 > url_len ||
	    url[spanned] != ':' || url[spanned+1] != '/' || url[spanned+2] != '/') {
		if (out_info) {
			out_info->url = NULL;
			out_info->err = _("invalid URL scheme name or missing '://' suffix");
		}
		return NULL; /* Bad scheme and/or missing "://" part */
	}
	strbuf_init(&norm, url_len);
	scheme_len = spanned;
	spanned += 3;
	url_len -= spanned;
	while (spanned--)
		strbuf_addch(&norm, tolower(*url++));


	/*
	 * Copy any username:password if present normalizing %-escapes
	 */
	at_ptr = strchr(url, '@');
	slash_ptr = url + strcspn(url, "/?#");
	if (at_ptr && at_ptr < slash_ptr) {
		user_off = norm.len;
		if (at_ptr > url) {
			if (!append_normalized_escapes(&norm, url, at_ptr - url,
						       "", URL_RESERVED)) {
				if (out_info) {
					out_info->url = NULL;
					out_info->err = _("invalid %XX escape sequence");
				}
				strbuf_release(&norm);
				return NULL;
			}
			colon_ptr = strchr(norm.buf + scheme_len + 3, ':');
			if (colon_ptr) {
				passwd_off = (colon_ptr + 1) - norm.buf;
				passwd_len = norm.len - passwd_off;
				user_len = (passwd_off - 1) - (scheme_len + 3);
			} else {
				user_len = norm.len - (scheme_len + 3);
			}
		}
		strbuf_addch(&norm, '@');
		url_len -= (++at_ptr - url);
		url = at_ptr;
	}


	/*
	 * Copy the host part excluding any port part, no %-escapes allowed
	 */
	if (!url_len || strchr(":/?#", *url)) {
		/* Missing host invalid for all URL schemes except file */
		if (strncmp(norm.buf, "file:", 5)) {
			if (out_info) {
				out_info->url = NULL;
				out_info->err = _("missing host and scheme is not 'file:'");
			}
			strbuf_release(&norm);
			return NULL;
		}
	} else {
		host_off = norm.len;
	}
	colon_ptr = slash_ptr - 1;
	while (colon_ptr > url && *colon_ptr != ':' && *colon_ptr != ']')
		colon_ptr--;
	if (*colon_ptr != ':') {
		colon_ptr = slash_ptr;
	} else if (!host_off && colon_ptr < slash_ptr && colon_ptr + 1 != slash_ptr) {
		/* file: URLs may not have a port number */
		if (out_info) {
			out_info->url = NULL;
			out_info->err = _("a 'file:' URL may not have a port number");
		}
		strbuf_release(&norm);
		return NULL;
	}
237 238 239 240 241 242

	if (allow_globs)
		spanned = strspn(url, URL_HOST_CHARS "*");
	else
		spanned = strspn(url, URL_HOST_CHARS);

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
	if (spanned < colon_ptr - url) {
		/* Host name has invalid characters */
		if (out_info) {
			out_info->url = NULL;
			out_info->err = _("invalid characters in host name");
		}
		strbuf_release(&norm);
		return NULL;
	}
	while (url < colon_ptr) {
		strbuf_addch(&norm, tolower(*url++));
		url_len--;
	}


	/*
	 * Check the port part and copy if not the default (after removing any
	 * leading 0s); no %-escapes allowed
	 */
	if (colon_ptr < slash_ptr) {
		/* skip the ':' and leading 0s but not the last one if all 0s */
		url++;
		url += strspn(url, "0");
		if (url == slash_ptr && url[-1] == '0')
			url--;
		if (url == slash_ptr) {
			/* Skip ":" port with no number, it's same as default */
		} else if (slash_ptr - url == 2 &&
			   !strncmp(norm.buf, "http:", 5) &&
			   !strncmp(url, "80", 2)) {
			/* Skip http :80 as it's the default */
		} else if (slash_ptr - url == 3 &&
			   !strncmp(norm.buf, "https:", 6) &&
			   !strncmp(url, "443", 3)) {
			/* Skip https :443 as it's the default */
		} else {
			/*
			 * Port number must be all digits with leading 0s removed
			 * and since all the protocols we deal with have a 16-bit
			 * port number it must also be in the range 1..65535
			 * 0 is not allowed because that means "next available"
			 * on just about every system and therefore cannot be used
			 */
			unsigned long pnum = 0;
			spanned = strspn(url, URL_DIGIT);
			if (spanned < slash_ptr - url) {
				/* port number has invalid characters */
				if (out_info) {
					out_info->url = NULL;
					out_info->err = _("invalid port number");
				}
				strbuf_release(&norm);
				return NULL;
			}
			if (slash_ptr - url <= 5)
				pnum = strtoul(url, NULL, 10);
			if (pnum == 0 || pnum > 65535) {
				/* port number not in range 1..65535 */
				if (out_info) {
					out_info->url = NULL;
					out_info->err = _("invalid port number");
				}
				strbuf_release(&norm);
				return NULL;
			}
			strbuf_addch(&norm, ':');
309
			port_off = norm.len;
310 311 312 313 314 315 316
			strbuf_add(&norm, url, slash_ptr - url);
			port_len = slash_ptr - url;
		}
		url_len -= slash_ptr - colon_ptr;
		url = slash_ptr;
	}
	if (host_off)
317
		host_len = norm.len - host_off - (port_len ? port_len + 1 : 0);
318 319 320 321 322 323 324 325 326 327 328 329 330 331 332


	/*
	 * Now copy the path resolving any . and .. segments being careful not
	 * to corrupt the URL by unescaping any delimiters, but do add an
	 * initial '/' if it's missing and do normalize any %-escape sequences.
	 */
	path_off = norm.len;
	path_start = norm.buf + path_off;
	strbuf_addch(&norm, '/');
	if (*url == '/') {
		url++;
		url_len--;
	}
	for (;;) {
333 334
		const char *seg_start;
		size_t seg_start_off = norm.len;
335 336
		const char *next_slash = url + strcspn(url, "/?#");
		int skip_add_slash = 0;
337

338 339 340 341 342 343 344 345 346 347 348 349 350
		/*
		 * RFC 3689 indicates that any . or .. segments should be
		 * unescaped before being checked for.
		 */
		if (!append_normalized_escapes(&norm, url, next_slash - url, "",
					       URL_RESERVED)) {
			if (out_info) {
				out_info->url = NULL;
				out_info->err = _("invalid %XX escape sequence");
			}
			strbuf_release(&norm);
			return NULL;
		}
351 352

		seg_start = norm.buf + seg_start_off;
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
		if (!strcmp(seg_start, ".")) {
			/* ignore a . segment; be careful not to remove initial '/' */
			if (seg_start == path_start + 1) {
				strbuf_setlen(&norm, norm.len - 1);
				skip_add_slash = 1;
			} else {
				strbuf_setlen(&norm, norm.len - 2);
			}
		} else if (!strcmp(seg_start, "..")) {
			/*
			 * ignore a .. segment and remove the previous segment;
			 * be careful not to remove initial '/' from path
			 */
			const char *prev_slash = norm.buf + norm.len - 3;
			if (prev_slash == path_start) {
				/* invalid .. because no previous segment to remove */
				if (out_info) {
					out_info->url = NULL;
					out_info->err = _("invalid '..' path segment");
				}
				strbuf_release(&norm);
				return NULL;
			}
			while (*--prev_slash != '/') {}
			if (prev_slash == path_start) {
				strbuf_setlen(&norm, prev_slash - norm.buf + 1);
				skip_add_slash = 1;
			} else {
				strbuf_setlen(&norm, prev_slash - norm.buf);
			}
		}
		url_len -= next_slash - url;
		url = next_slash;
		/* if the next char is not '/' done with the path */
		if (*url != '/')
			break;
		url++;
		url_len--;
		if (!skip_add_slash)
			strbuf_addch(&norm, '/');
	}
	path_len = norm.len - path_off;


	/*
	 * Now simply copy the rest, if any, only normalizing %-escapes and
	 * being careful not to corrupt the URL by unescaping any delimiters.
	 */
	if (*url) {
		if (!append_normalized_escapes(&norm, url, url_len, "", URL_RESERVED)) {
			if (out_info) {
				out_info->url = NULL;
				out_info->err = _("invalid %XX escape sequence");
			}
			strbuf_release(&norm);
			return NULL;
		}
	}


	result = strbuf_detach(&norm, &result_len);
	if (out_info) {
		out_info->url = result;
		out_info->err = NULL;
		out_info->url_len = result_len;
		out_info->scheme_len = scheme_len;
		out_info->user_off = user_off;
		out_info->user_len = user_len;
		out_info->passwd_off = passwd_off;
		out_info->passwd_len = passwd_len;
		out_info->host_off = host_off;
		out_info->host_len = host_len;
425
		out_info->port_off = port_off;
426 427 428 429 430 431 432
		out_info->port_len = port_len;
		out_info->path_off = path_off;
		out_info->path_len = path_len;
	}
	return result;
}

433 434 435 436 437
char *url_normalize(const char *url, struct url_info *out_info)
{
	return url_normalize_1(url, out_info, 0);
}

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
static size_t url_match_prefix(const char *url,
			       const char *url_prefix,
			       size_t url_prefix_len)
{
	/*
	 * url_prefix matches url if url_prefix is an exact match for url or it
	 * is a prefix of url and the match ends on a path component boundary.
	 * Both url and url_prefix are considered to have an implicit '/' on the
	 * end for matching purposes if they do not already.
	 *
	 * url must be NUL terminated.  url_prefix_len is the length of
	 * url_prefix which need not be NUL terminated.
	 *
	 * The return value is the length of the match in characters (including
	 * the final '/' even if it's implicit) or 0 for no match.
	 *
	 * Passing NULL as url and/or url_prefix will always cause 0 to be
	 * returned without causing any faults.
	 */
	if (!url || !url_prefix)
		return 0;
	if (!url_prefix_len || (url_prefix_len == 1 && *url_prefix == '/'))
		return (!*url || *url == '/') ? 1 : 0;
	if (url_prefix[url_prefix_len - 1] == '/')
		url_prefix_len--;
	if (strncmp(url, url_prefix, url_prefix_len))
		return 0;
	if ((strlen(url) == url_prefix_len) || (url[url_prefix_len] == '/'))
		return url_prefix_len + 1;
	return 0;
}

470 471
static int match_urls(const struct url_info *url,
		      const struct url_info *url_prefix,
472
		      struct urlmatch_item *match)
473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490
{
	/*
	 * url_prefix matches url if the scheme, host and port of url_prefix
	 * are the same as those of url and the path portion of url_prefix
	 * is the same as the path portion of url or it is a prefix that
	 * matches at a '/' boundary.  If url_prefix contains a user name,
	 * that must also exactly match the user name in url.
	 *
	 * If the user, host, port and path match in this fashion, the returned
	 * value is the length of the path match including any implicit
	 * final '/'.  For example, "http://me@example.com/path" is matched by
	 * "http://example.com" with a path length of 1.
	 *
	 * If there is a match and exactusermatch is not NULL, then
	 * *exactusermatch will be set to true if both url and url_prefix
	 * contained a user name or false if url_prefix did not have a
	 * user name.  If there is no match *exactusermatch is left untouched.
	 */
491 492
	char usermatched = 0;
	size_t pathmatchlen;
493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511

	if (!url || !url_prefix || !url->url || !url_prefix->url)
		return 0;

	/* check the scheme */
	if (url_prefix->scheme_len != url->scheme_len ||
	    strncmp(url->url, url_prefix->url, url->scheme_len))
		return 0; /* schemes do not match */

	/* check the user name if url_prefix has one */
	if (url_prefix->user_off) {
		if (!url->user_off || url->user_len != url_prefix->user_len ||
		    strncmp(url->url + url->user_off,
			    url_prefix->url + url_prefix->user_off,
			    url->user_len))
			return 0; /* url_prefix has a user but it's not a match */
		usermatched = 1;
	}

512
	/* check the host */
513
	if (!match_host(url, url_prefix))
514 515 516 517 518 519 520
		return 0; /* host names do not match */

	/* check the port */
	if (url_prefix->port_len != url->port_len ||
	    strncmp(url->url + url->port_off,
		    url_prefix->url + url_prefix->port_off, url->port_len))
		return 0; /* ports do not match */
521 522 523 524 525 526

	/* check the path */
	pathmatchlen = url_match_prefix(
		url->url + url->path_off,
		url_prefix->url + url_prefix->path_off,
		url_prefix->url_len - url_prefix->path_off);
527 528
	if (!pathmatchlen)
		return 0; /* paths do not match */
529

530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548
	if (match) {
		match->hostmatch_len = url_prefix->host_len;
		match->pathmatch_len = pathmatchlen;
		match->user_matched = usermatched;
	}

	return 1;
}

static int cmp_matches(const struct urlmatch_item *a,
		       const struct urlmatch_item *b)
{
	if (a->hostmatch_len != b->hostmatch_len)
		return a->hostmatch_len < b->hostmatch_len ? -1 : 1;
	if (a->pathmatch_len != b->pathmatch_len)
		return a->pathmatch_len < b->pathmatch_len ? -1 : 1;
	if (a->user_matched != b->user_matched)
		return b->user_matched ? -1 : 1;
	return 0;
549
}
550 551 552 553 554

int urlmatch_config_entry(const char *var, const char *value, void *cb)
{
	struct string_list_item *item;
	struct urlmatch_config *collect = cb;
555
	struct urlmatch_item matched = {0};
556 557 558 559 560
	struct url_info *url = &collect->url;
	const char *key, *dot;
	struct strbuf synthkey = STRBUF_INIT;
	int retval;

561
	if (!skip_prefix(var, collect->section, &key) || *(key++) != '.') {
562 563 564 565 566 567 568 569 570 571
		if (collect->cascade_fn)
			return collect->cascade_fn(var, value, cb);
		return 0; /* not interested */
	}
	dot = strrchr(key, '.');
	if (dot) {
		char *config_url, *norm_url;
		struct url_info norm_info;

		config_url = xmemdupz(key, dot - key);
572
		norm_url = url_normalize_1(config_url, &norm_info, 1);
573 574 575
		free(config_url);
		if (!norm_url)
			return 0;
576
		retval = match_urls(url, &norm_info, &matched);
577
		free(norm_url);
578
		if (!retval)
579 580 581 582 583 584 585 586 587
			return 0;
		key = dot + 1;
	}

	if (collect->key && strcmp(key, collect->key))
		return 0;

	item = string_list_insert(&collect->vars, key);
	if (!item->util) {
588
		item->util = xcalloc(1, sizeof(matched));
589
	} else {
590 591 592 593 594
		if (cmp_matches(&matched, item->util) < 0)
			 /*
			  * Our match is worse than the old one,
			  * we cannot use it.
			  */
595 596 597 598
			return 0;
		/* Otherwise, replace it with this one. */
	}

599
	memcpy(item->util, &matched, sizeof(matched));
600 601 602 603 604 605 606 607
	strbuf_addstr(&synthkey, collect->section);
	strbuf_addch(&synthkey, '.');
	strbuf_addstr(&synthkey, key);
	retval = collect->collect_fn(synthkey.buf, value, collect->cb);

	strbuf_release(&synthkey);
	return retval;
}