uriparser.cpp
14.3 KB
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
/* ****************************************************************************
* Copyright 2019 Open Systems Development BV *
* *
* Permission is hereby granted, free of charge, to any person obtaining a *
* copy of this software and associated documentation files (the "Software"), *
* to deal in the Software without restriction, including without limitation *
* the rights to use, copy, modify, merge, publish, distribute, sublicense, *
* and/or sell copies of the Software, and to permit persons to whom the *
* Software is furnished to do so, subject to the following conditions: *
* *
* The above copyright notice and this permission notice shall be included in *
* all copies or substantial portions of the Software. *
* *
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR *
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, *
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL *
* THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER *
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING *
* FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER *
* DEALINGS IN THE SOFTWARE. *
* ***************************************************************************/
#include "uriparser.h"
// std
#include <iostream>
#include <sstream>
#include <utility>
// gnu-c
#include <netdb.h>
// boost
#include <boost/algorithm/string/case_conv.hpp>
#include <boost/algorithm/string/split.hpp>
#include <boost/lexical_cast.hpp>
#include <boost/regex.hpp>
// osdev::components::mqtt
#include "bimap.h"
#include "stringutils.h"
#include "uriutils.h"
// mlogic::common::logger
// #include "mlogic/common/logger/loggerprovider.h"
// #include "mlogic/common/invalidargumentexception.h"
// #include "mlogic/common/nullptrexception.h"
// #include "mlogic/common/systemexception.h"
using namespace osdev::components::mqtt;
namespace {
/**
* @brief Copies an item from the from container to the to container.
* @tparam TFrom The type of the container from which to copy.
* @tparam TTo The type of the container to which to copy.
* @param itemName The name of the item to copy.
* @param from The container from which to copy.
* @param to The cointainer to which to copy.
* @param transformation Apply transformation function to the input. Default no transformation.
*/
template <typename TFrom, typename TTo>
void copyItem(const std::string& itemName, const TFrom& from, TTo& to, const std::function<std::string(const std::string&)>& transformation = std::function<std::string(const std::string&)>())
{
if (transformation) {
to.insert(std::make_pair(itemName, transformation(from[itemName])));
}
else {
to.insert(std::make_pair(itemName, from[itemName]));
}
}
const std::string& getItem(const std::map<std::string, std::string>& source, const std::string& itemName)
{
static const std::string s_empty;
const auto cit = source.find(itemName);
if (cit != source.end()) {
return cit->second;
}
return s_empty;
}
static const boost::bimap<char, std::string>& getReservedCharacterMap()
{
static const auto s_lookupTable = makeBimap<char, std::string>(
{ { ':', percentEncode<':'>() },
{ '/', percentEncode<'/'>() },
{ '?', percentEncode<'?'>() },
{ '#', percentEncode<'#'>() },
{ '[', percentEncode<'['>() },
{ ']', percentEncode<']'>() },
{ '@', percentEncode<'@'>() },
{ '!', percentEncode<'!'>() },
{ '$', percentEncode<'$'>() },
{ '&', percentEncode<'&'>() },
{ '\'', percentEncode<'\''>() },
{ '(', percentEncode<'('>() },
{ ')', percentEncode<')'>() },
{ '*', percentEncode<'*'>() },
{ '+', percentEncode<'+'>() },
{ ',', percentEncode<','>() },
{ ';', percentEncode<';'>() },
{ '=', percentEncode<'='>() },
{ '"', percentEncode<'"'>() },
{ '%', percentEncode<'%'>() },
{ '-', percentEncode<'-'>() },
{ '.', percentEncode<'.'>() },
{ '<', percentEncode<'<'>() },
{ '>', percentEncode<'>'>() },
{ '\\', percentEncode<'\\'>() },
{ '^', percentEncode<'^'>() },
{ '_', percentEncode<'_'>() },
{ '`', percentEncode<'`'>() },
{ '{', percentEncode<'{'>() },
{ '|', percentEncode<'|'>() },
{ '}', percentEncode<'}'>() },
{ '~', percentEncode<'~'>() } });
return s_lookupTable;
}
std::string decode(const std::string& in)
{
static constexpr size_t encodingTokenSize = 3; // example: %20 encodes a space character.
const auto& reservedLookup = getReservedCharacterMap();
std::string out = in;
std::size_t pos = 0;
while ((pos = out.find('%', pos)) != std::string::npos) {
if (pos + encodingTokenSize > out.size()) {
// MLOGIC_COMMON_THROW(InvalidArgumentException, "Invalid encoding at end of string");
}
const auto cit = reservedLookup.right.find(out.substr(pos, 3));
if (reservedLookup.right.end() != cit) {
// string& replace (size_t pos, size_t len, size_t n, char c)
// where n is the number of fill characters (1 in this case).
out.replace(pos, encodingTokenSize, 1, cit->second);
}
++pos;
}
return out;
}
std::string encode(const std::string& in)
{
const auto& reservedLookup = getReservedCharacterMap();
std::string out = in;
for (size_t pos = 0; pos < out.size(); ++pos) {
const auto cit = reservedLookup.left.find(out[pos]);
if (reservedLookup.left.end() != cit) {
out.replace(pos, 1, cit->second);
pos += 2;
}
}
return out;
}
} // anonymous
// static
ParsedUri UriParser::parse(const std::string& uri)
{
// Before turning to regular expressions, the following ibraries were evaluated to achieve this functionality:
// Qt QUrlParser: http://doc.qt.io/qt-4.8/qurl.html
// cpp-netlib: https://github.com/cpp-netlib/uri
// uriparser: http://uriparser.sourceforge.net/
// From the above, cpp-netlib was the most compelling because of its pending standardization for C++(17?).
// However, none of these libraries could handle strings for port service names, so a custom implementation seems necessary.
// As an additional validation step, one of the above libraries could be used after the port service name was replaced (see below).
//
// Split the uri in two stages. First break down the uri in its components: scheme (cannot be empty), authority (cannot be empty), path, query, fragment.
// The path, query and fragment parts are optional. Because the scheme and authority part cannot be empty only a subset of uri's is handled by this function.
// In the second stage the authority is parsed to get the hostname and the port. In order to use an ipv6 host address it must be
// wrapped in brackets. The addresses are not validated whether they are correct. When a open bracket is found the part that is between brackets
// must contain at least two colons. This is enough to discern something that resembles an ipv6 address from the other possibilities.
static const std::string regexUriString(
R"regex(^(?<scheme>[^:/?#]+)://(?<authority>[^/?#]+)(?<path>[^?#]*)(?<q1>\?(?<query>[^#]*))?(?<f1>#(?<fragment>.*))?)regex");
// This regex only checks for non occurrence of the @ symbol since the input is the result from the regexUri where it is already validated that characters "/>#" do not exist
// in the authority part. This regexAuthority uses the if then else construct "(?(?=regex)then|else)" to choose between ipv6 or something else.
static const std::string regexAuthorityString(
R"regex(^((?<user>[^:@]+)(:(?<password>[^@]+))?@)?(?(?=(?<ipv6>\[))\[(?=(.*:){2,}.*)(?<host>[^@]+)\]|(?<host>[^:@]+))(?<p1>:(?<port>[^:@]+))?$)regex");
static boost::regex uriRegex(regexUriString);
boost::cmatch whatUri;
auto uriMatches = boost::regex_match(
uri.c_str(),
whatUri,
uriRegex);
if (!uriMatches)
{
// ErrorLogToFile("UriParser", "Invalid uri: '%1'", uri);
// throw (InvalidArgumentException, "No match for the specified uri.");
}
static boost::regex authorityRegex(regexAuthorityString);
boost::cmatch whatAuthority;
std::string authority = whatUri["authority"];
auto authorityMatches = boost::regex_match(
authority.c_str(),
whatAuthority,
authorityRegex);
if (!authorityMatches)
{
// ErrorToLogFile("UriParser", "Uri contains invalid authority part: %1", authority);
// Throw (InvalidArgumentException, "Uri contains invalid authority part.");
}
static const auto toLower = [](const std::string& in) -> std::string { return boost::to_lower_copy(in); };
ParsedUri parsedUri;
copyItem("scheme", whatUri, parsedUri, toLower);
copyItem("user", whatAuthority, parsedUri, &decode);
copyItem("password", whatAuthority, parsedUri, &decode);
copyItem("ipv6", whatAuthority, parsedUri); // Acts as a flag. Empty means not ipv6, not empty means ipv6 (this is not validated in the parse however!)
copyItem("host", whatAuthority, parsedUri, toLower);
copyItem("port", whatAuthority, parsedUri, toLower);
copyItem("path", whatUri, parsedUri);
copyItem("query", whatUri, parsedUri);
copyItem("fragment", whatUri, parsedUri, &decode);
return parsedUri;
}
// static
ParsedQuery UriParser::parseQuery(const ParsedUri& parsedUri)
{
const auto cit = parsedUri.find("query");
if (parsedUri.end() == cit) {
return {};
}
const auto& queryString = cit->second;
std::vector<std::string> keyValues;
boost::algorithm::split(keyValues, queryString, [](char ch) { return ch == '&'; });
std::map<std::string, std::string> retval;
for (const auto& query : keyValues) {
auto pos = query.find('=');
if (std::string::npos != pos) {
retval[decode(query.substr(0, pos))] = pos + 1 < query.size() ? decode(query.substr(pos + 1)) : "";
}
}
return retval;
}
// static
ParsedPath UriParser::parsePath(const ParsedUri& parsedUri)
{
const auto cit = parsedUri.find("path");
if (parsedUri.end() == cit) {
return {};
}
const auto& pathString = cit->second;
ParsedPath pathElements;
if (!pathString.empty()) {
const auto path = pathString.substr(1);
boost::algorithm::split(pathElements, path, [](char ch) { return ch == '/'; }); // empty string will lead to a single pathElement
std::transform(pathElements.begin(), pathElements.end(), pathElements.begin(), &decode);
}
return pathElements;
}
// static
std::string UriParser::normalize(const std::string& uri)
{
auto parsedUri = parse(uri);
auto& portString = parsedUri["port"];
if (!portString.empty() && !is_numeric(portString)) {
auto portnumber = getPortnumber(portString);
portString = boost::lexical_cast<std::string>(portnumber);
}
return toString(parsedUri);
}
// static
std::string UriParser::toString(const ParsedUri& parsedUri)
{
const auto& schemeString = getItem(parsedUri, "scheme");
const auto& hostString = getItem(parsedUri, "host");
if( schemeString.empty() )
{
// Do something sensible
}
if( hostString.empty() )
{
// Do something sensible.
}
const auto& user = getItem(parsedUri, "user");
const auto& password = getItem(parsedUri, "password");
const auto& portString = getItem(parsedUri, "port");
const auto& pathString = getItem(parsedUri, "path");
const auto& queryString = getItem(parsedUri, "query");
const auto& fragmentString = getItem(parsedUri, "fragment");
// wrap hostname in brackets only if the incoming url uses them
bool ipv6 = !getItem(parsedUri, "ipv6").empty();
std::ostringstream oss;
oss << schemeString << "://";
if (!user.empty()) {
oss << encode(user);
if (!password.empty()) {
oss << ":" << encode(password);
}
oss << "@";
}
if (ipv6) {
oss << '[';
}
oss << hostString;
if (ipv6) {
oss << ']';
}
if (!portString.empty()) {
oss << ':' << portString;
}
if (!pathString.empty()) {
auto pathElements = UriParser::parsePath(parsedUri);
for (const auto& element : pathElements) {
oss << "/" << encode(element);
}
}
if (!queryString.empty()) {
auto queryElements = UriParser::parseQuery(parsedUri);
oss << '?';
for (auto cit = queryElements.cbegin(); queryElements.cend() != cit; ++cit) {
oss << encode(cit->first) << '=' << encode(cit->second);
if (next(cit) != queryElements.cend()) {
oss << '&';
}
}
}
if (!fragmentString.empty()) {
oss << '#' << encode(fragmentString);
}
return oss.str();
}
// static
int UriParser::getPortnumber(const std::string& service, const std::string& protocolName)
{
const unsigned int bufSize = 1024;
struct servent data;
struct servent* result;
char buf[bufSize]; // contains the strings that data points to
::getservbyname_r(service.c_str(), protocolName.c_str(), &data, buf, bufSize, &result);
if (nullptr == result)
{
// ErrorLogToFile ("UriParser", "Could not determine the portnumber for the specified service: %1 for protocol: %2. Please check the portnumber configuration in /etc/services.", service, protocolName);
// throw (?) (InvalidArgumentException, "Could not determine the portnumber for the specified service and/or protocol.");
}
// htonx functions need -Wold-style-cast disabled
#pragma GCC diagnostic push
#pragma GCC diagnostic ignored "-Wold-style-cast"
return static_cast<int>(ntohs(static_cast<uint16_t>(data.s_port)));
#pragma GCC diagnostic pop
}