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
|
/*
* SRT - Secure, Reliable, Transport
* Copyright (c) 2018 Haivision Systems Inc.
*
* This Source Code Form is subject to the terms of the Mozilla Public
* License, v. 2.0. If a copy of the MPL was not distributed with this
* file, You can obtain one at http://mozilla.org/MPL/2.0/.
*
*/
// STL includes
#include <algorithm>
#include <map>
#include <string>
#include "uriparser.hpp"
#ifdef TEST
#define TEST1 1
#endif
#ifdef TEST1
#include <iostream>
#endif
using namespace std;
map<string, UriParser::Type> g_types;
// Map construction using the initializer list is only available starting from C++11.
// This dummy structure is used instead.
struct UriParserInit
{
UriParserInit()
{
g_types["file"] = UriParser::FILE;
g_types["udp"] = UriParser::UDP;
g_types["tcp"] = UriParser::TCP;
g_types["srt"] = UriParser::SRT;
g_types["rtmp"] = UriParser::RTMP;
g_types["http"] = UriParser::HTTP;
g_types["rtp"] = UriParser::RTP;
g_types[""] = UriParser::UNKNOWN;
}
} g_uriparser_init;
UriParser::UriParser(const string& strUrl, DefaultExpect exp)
: m_uriType(UNKNOWN)
{
m_expect = exp;
Parse(strUrl, exp);
}
UriParser::~UriParser(void)
{
}
string UriParser::makeUri()
{
// Reassemble parts into the URI
string prefix = "";
if (m_proto != "")
{
prefix = m_proto + "://";
}
std::ostringstream out;
out << prefix << m_host;
if ((m_port == "" || m_port == "0") && m_expect == EXPECT_FILE)
{
// Do not add port
}
else
{
out << ":" << m_port;
}
if (m_path != "")
{
if (m_path[0] != '/')
out << "/";
out << m_path;
}
if (!m_mapQuery.empty())
{
out << "?";
query_it i = m_mapQuery.begin();
for (;;)
{
out << i->first << "=" << i->second;
++i;
if (i == m_mapQuery.end())
break;
out << "&";
}
}
m_origUri = out.str();
return m_origUri;
}
string UriParser::proto(void) const
{
return m_proto;
}
UriParser::Type UriParser::type() const
{
return m_uriType;
}
string UriParser::host(void) const
{
return m_host;
}
string UriParser::port(void) const
{
return m_port;
}
unsigned short int UriParser::portno(void) const
{
// This returns port in numeric version. Fallback to 0.
try
{
int i = atoi(m_port.c_str());
if ( i <= 0 || i > 65535 )
return 0;
return i;
}
catch (...)
{
return 0;
}
}
string UriParser::path(void) const
{
return m_path;
}
string UriParser::queryValue(const string& strKey) const
{
return m_mapQuery.at(strKey);
}
// NOTE: handles percent encoded single byte ASCII / Latin-1 characters but not unicode characters and encodings
static string url_decode(const string& str)
{
string ret;
ret.reserve(str.size());
size_t end_idx = 0;
for (;;)
{
size_t idx = str.find('%', end_idx);
if (idx == string::npos)
break;
if (idx + 2 >= str.size()) // bad percent encoding at the end
break;
ret += str.substr(end_idx, idx - end_idx);
// make a "string" out of only two characters following %
char tmp[3] = { str[idx+1], str[idx+2], '\0' };
char* endptr = 0;
unsigned val = strtoul(tmp, &endptr, 16);
if (endptr != &tmp[2])
{
// Processing was not correct. Skip these and proceed.
ret += str[idx];
end_idx = idx + 1;
}
else
{
ret += char(val);
end_idx = idx + 3;
}
// And again search anew since end_idx.
}
// Copy the rest of the string that wasn't processed.
ret += str.substr(end_idx, str.size() - end_idx);
return ret;
}
void UriParser::Parse(const string& strUrl, DefaultExpect exp)
{
int iQueryStart = -1;
size_t idx = strUrl.find("?");
if (idx != string::npos)
{
m_host = strUrl.substr(0, idx);
iQueryStart = (int)(idx + 1);
}
else
{
m_host = strUrl;
}
idx = m_host.find("://");
if (idx != string::npos)
{
m_proto = m_host.substr(0, idx);
transform(m_proto.begin(), m_proto.end(), m_proto.begin(), [](char c){ return tolower(c); });
m_host = m_host.substr(idx + 3, m_host.size() - (idx + 3));
}
// Handle the IPv6 specification in square brackets.
// This actually handles anything specified in [] so potentially
// you can also specify the usual hostname here as well. If the
// whole host results to have [] at edge positions, they are stripped,
// otherwise they remain. In both cases the search for the colon
// separating the port specification starts only after ].
const size_t i6pos = m_host.find("[");
size_t i6end = string::npos;
// Search for the "path" part only behind the closed bracket,
// if both open and close brackets were found
size_t path_since = 0;
if (i6pos != string::npos)
{
i6end = m_host.find("]", i6pos);
if (i6end != string::npos)
path_since = i6end;
}
idx = m_host.find("/", path_since);
if (idx != string::npos)
{
m_path = m_host.substr(idx, m_host.size() - idx);
m_host = m_host.substr(0, idx);
}
// Check special things in the HOST entry.
size_t atp = m_host.find('@');
if (atp != string::npos)
{
string realhost = m_host.substr(atp+1);
string prehost;
if ( atp > 0 )
{
prehost = m_host.substr(0, atp-0);
size_t colon = prehost.find(':');
if ( colon != string::npos )
{
string pw = prehost.substr(colon+1);
string user;
if ( colon > 0 )
user = prehost.substr(0, colon-0);
m_mapQuery["user"] = user;
m_mapQuery["password"] = pw;
}
else
{
m_mapQuery["user"] = prehost;
}
}
else
{
m_mapQuery["multicast"] = "1";
}
m_host = realhost;
}
bool stripbrackets = false;
size_t hostend = 0;
if (i6pos != string::npos)
{
// IPv6 IP address. Find the terminating ]
hostend = m_host.find("]", i6pos);
idx = m_host.rfind(":");
if (hostend != string::npos)
{
// Found the end. But not necessarily it was
// at the beginning. If it was at the beginning,
// strip them from the host name.
size_t lasthost = idx;
if (idx != string::npos && idx < hostend)
{
idx = string::npos;
lasthost = m_host.size();
}
if (i6pos == 0 && hostend == lasthost - 1)
{
stripbrackets = true;
}
}
}
else
{
idx = m_host.rfind(":");
}
if (idx != string::npos)
{
m_port = m_host.substr(idx + 1, m_host.size() - (idx + 1));
// Extract host WITHOUT stripping brackets
m_host = m_host.substr(0, idx);
}
if (stripbrackets)
{
if (!hostend)
hostend = m_host.size() - 1;
m_host = m_host.substr(1, hostend - 1);
}
if ( m_port == "" && m_host != "" )
{
// Check if the host-but-no-port has specified
// a single integer number. If so
// We need to use C86 strtol, cannot use C++11
const char* beg = m_host.c_str();
const char* end = m_host.c_str() + m_host.size();
char* eos = 0;
long val = strtol(beg, &eos, 10);
if ( val > 0 && eos == end )
{
m_port = m_host;
m_host = "";
}
}
string strQueryPair;
while (iQueryStart > -1)
{
idx = strUrl.find("&", iQueryStart);
if (idx != string::npos)
{
strQueryPair = strUrl.substr(iQueryStart, idx - iQueryStart);
iQueryStart = (int)(idx + 1);
}
else
{
strQueryPair = strUrl.substr(iQueryStart, strUrl.size() - iQueryStart);
iQueryStart = (int)idx;
}
idx = strQueryPair.find("=");
if (idx != string::npos)
{
m_mapQuery[url_decode(strQueryPair.substr(0, idx))] = url_decode(strQueryPair.substr(idx + 1, strQueryPair.size() - (idx + 1)));
}
}
if (m_proto == "file")
{
if ( m_path.size() > 3 && m_path.substr(0, 3) == "/./" )
m_path = m_path.substr(3);
}
// Post-parse fixes
// Treat empty protocol as a file. In this case, merge the host and path.
if (exp == EXPECT_FILE && m_proto == "" && m_port == "")
{
m_proto = "file";
m_path = m_host + m_path;
m_host = "";
}
const auto proto_it = g_types.find(m_proto);
// Default-constructed UNKNOWN will be used if not found.
if (proto_it != g_types.end())
{
m_uriType = proto_it->second;
}
m_origUri = strUrl;
}
#ifdef TEST
#include <vector>
using namespace std;
int main( int argc, char** argv )
{
if ( argc < 2 )
{
return 0;
}
UriParser parser (argv[1], UriParser::EXPECT_HOST);
std::vector<std::string> args;
if (argc > 2)
{
copy(argv+2, argv+argc, back_inserter(args));
}
(void)argc;
cout << "PARSING URL: " << argv[1] << endl;
cout << "SCHEME INDEX: " << int(parser.type()) << endl;
cout << "PROTOCOL: " << parser.proto() << endl;
cout << "HOST: " << parser.host() << endl;
cout << "PORT (string): " << parser.port() << endl;
cout << "PORT (numeric): " << parser.portno() << endl;
cout << "PATH: " << parser.path() << endl;
cout << "PARAMETERS:\n";
for (auto& p: parser.parameters())
{
cout << "\t" << p.first << " = " << p.second << endl;
}
if (!args.empty())
{
for (string& s: args)
{
vector<string> keyval;
Split(s, '=', back_inserter(keyval));
if (keyval.size() < 2)
keyval.push_back("");
parser[keyval[0]] = keyval[1];
}
cout << "REASSEMBLED: " << parser.makeUri() << endl;
}
return 0;
}
#endif
|