Rietveld Code Review Tool
Help | Bug tracker | Discussion group | Source code

Delta Between Two Patch Sets: compiled/subscription/DownloadableSubscription.cpp

Issue 29606600: Issue 5146 - Implement DownloadableSubscription parsing in C++ (Closed) Base URL: https://hg.adblockplus.org/adblockpluscore/
Left Patch Set: Improved logic for Process() Created Dec. 5, 2017, 7:16 a.m.
Right Patch Set: Removed Md5sum and associated code Created Aug. 14, 2018, 12:38 p.m.
Left:
Right:
Use n/p to move between diff chunks; N/P to move between comments.
Jump to:
Left: Side by side diff | Download
Right: Side by side diff | Download
« no previous file with change/comment | « compiled/subscription/DownloadableSubscription.h ('k') | compiled/subscription/Subscription.h » ('j') | no next file with change/comment »
Toggle Intra-line Diffs ('i') | Expand Comments ('e') | Collapse Comments ('c') | Show Comments Hide Comments ('s')
LEFTRIGHT
1 /* 1 /*
2 * This file is part of Adblock Plus <https://adblockplus.org/>, 2 * This file is part of Adblock Plus <https://adblockplus.org/>,
3 * Copyright (C) 2006-present eyeo GmbH 3 * Copyright (C) 2006-present eyeo GmbH
4 * 4 *
5 * Adblock Plus is free software: you can redistribute it and/or modify 5 * Adblock Plus is free software: you can redistribute it and/or modify
6 * it under the terms of the GNU General Public License version 3 as 6 * it under the terms of the GNU General Public License version 3 as
7 * published by the Free Software Foundation. 7 * published by the Free Software Foundation.
8 * 8 *
9 * Adblock Plus is distributed in the hope that it will be useful, 9 * Adblock Plus is distributed in the hope that it will be useful,
10 * but WITHOUT ANY WARRANTY; without even the implied warranty of 10 * but WITHOUT ANY WARRANTY; without even the implied warranty of
11 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 11 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
12 * GNU General Public License for more details. 12 * GNU General Public License for more details.
13 * 13 *
14 * You should have received a copy of the GNU General Public License 14 * You should have received a copy of the GNU General Public License
15 * along with Adblock Plus. If not, see <http://www.gnu.org/licenses/>. 15 * along with Adblock Plus. If not, see <http://www.gnu.org/licenses/>.
16 */ 16 */
17 17
18 #include <cwctype> 18 #include <cwctype>
19 #include <limits> 19 #include <limits>
20 20
21 #include "DownloadableSubscription.h" 21 #include "DownloadableSubscription.h"
22 #include "../Base64.h"
23 #include "../FilterNotifier.h" 22 #include "../FilterNotifier.h"
24 #include "../StringScanner.h" 23 #include "../StringScanner.h"
25 #include "../filter/CommentFilter.h" 24 #include "../filter/CommentFilter.h"
25
26 ABP_NS_USING
26 27
27 namespace { 28 namespace {
28 constexpr int MILLIS_IN_HOUR = 60 * 60 * 1000; 29 constexpr int MILLIS_IN_HOUR = 60 * 60 * 1000;
29 constexpr int MILLIS_IN_DAY = 24 * MILLIS_IN_HOUR; 30 constexpr int MILLIS_IN_DAY = 24 * MILLIS_IN_HOUR;
30 // limits 31 // limits
31 constexpr int64_t MAX_HOUR = std::numeric_limits<int64_t>::max() / MILLIS_IN_H OUR; 32 constexpr int64_t MAX_HOUR = std::numeric_limits<int64_t>::max() / MILLIS_IN_H OUR;
32 constexpr int64_t MAX_DAY = std::numeric_limits<int64_t>::max() / MILLIS_IN_DA Y; 33 constexpr int64_t MAX_DAY = std::numeric_limits<int64_t>::max() / MILLIS_IN_DA Y;
33 34
34 typedef std::pair<DependentString, DependentString> Param; 35 typedef std::pair<DependentString, DependentString> Param;
35 36
(...skipping 50 matching lines...) Expand 10 before | Expand all | Expand 10 after
86 } 87 }
87 88
88 DownloadableSubscription_Parser::DownloadableSubscription_Parser() 89 DownloadableSubscription_Parser::DownloadableSubscription_Parser()
89 : mFirstLine(true) 90 : mFirstLine(true)
90 { 91 {
91 annotate_address(this, "DownloadableSubscription_Parser"); 92 annotate_address(this, "DownloadableSubscription_Parser");
92 } 93 }
93 94
94 namespace { 95 namespace {
95 const DependentString ADBLOCK_HEADER(u"[Adblock"_str); 96 const DependentString ADBLOCK_HEADER(u"[Adblock"_str);
96
97 // Only check for trailing base64 padding. There should be at most 2 '='.
98 // In that case return a truncated string.
99 DependentString CleanUpChecksum(const String& checksum)
100 {
101 const auto len = checksum.length();
102 if ((len > 22 && len <= 24) &&
103 (checksum[22] == u'=' && (len == 23 || checksum[23] == u'=')))
104 return DependentString(checksum, 0, 22);
105 return DependentString(checksum);
106 }
107 } 97 }
108 98
109 void DownloadableSubscription_Parser::Process(const String& line) 99 void DownloadableSubscription_Parser::Process(const String& line)
110 { 100 {
111 bool isHeader = false; 101 bool isHeader = false;
112 bool doChecksum = true;
113 isHeader = line.find(ADBLOCK_HEADER) != String::npos; 102 isHeader = line.find(ADBLOCK_HEADER) != String::npos;
114 if (!isHeader) 103 if (!isHeader)
115 { 104 {
116 auto param = ParseParam(line); 105 auto param = ParseParam(line);
117 if (param.first.is_invalid()) 106 if (param.first.is_invalid())
118 mFiltersText.emplace_back(line); 107 mFiltersText.emplace_back(line);
119 else 108 else
120 { 109 mParams[param.first] = param.second;
121 if (param.first == u"checksum"_str)
122 {
123 mParams[param.first] = CleanUpChecksum(param.second);
124 doChecksum = false;
125 }
126 else
127 mParams[param.first] = param.second;
128 }
129 }
130 // Checksum is an MD5 checksum (base64-encoded without the trailing "=") of
131 // all lines in UTF-8 without the checksum line, joined with "\n".
132 if (doChecksum)
133 {
134 if (!mFirstLine)
135 mChecksum.Update((const uint8_t*)"\n", 1);
136 else
137 mFirstLine = false;
138 mChecksum.Update(line);
139 } 110 }
140 } 111 }
141 112
142 int64_t DownloadableSubscription_Parser::ParseExpires(const String& expires) 113 int64_t DownloadableSubscription_Parser::ParseExpires(const String& expires)
143 { 114 {
144 bool isHour = false; 115 bool isHour = false;
145 StringScanner scanner(expires); 116 StringScanner scanner(expires);
146 String::size_type numStart = 0; 117 String::size_type numStart = 0;
147 String::size_type numLen = 0; 118 String::size_type numLen = 0;
148 while(!scanner.done()) 119 while(!scanner.done())
(...skipping 12 matching lines...) Expand all
161 } 132 }
162 else 133 else
163 { 134 {
164 if (numLen) 135 if (numLen)
165 scanner.back(); 136 scanner.back();
166 break; 137 break;
167 } 138 }
168 } 139 }
169 140
170 DependentString numStr(expires, numStart, numLen); 141 DependentString numStr(expires, numStart, numLen);
171 int64_t num = numStr.toInt<int64_t>(); 142 int64_t num = lexical_cast<int64_t>(numStr);
172 if (num == 0) 143 if (num == 0)
173 return 0; 144 return 0;
174 145
175 while (!scanner.done()) 146 while (!scanner.done())
176 { 147 {
177 auto ch = scanner.next(); 148 auto ch = scanner.next();
178 if (std::iswspace(ch)) 149 if (std::iswspace(ch))
179 continue; 150 continue;
180 151
181 if (ch == u'h') 152 if (ch == u'h')
182 isHour = true; 153 isHour = true;
183 154
184 // assume we are done here. The rest is ignored. 155 // assume we are done here. The rest is ignored.
185 break; 156 break;
186 } 157 }
187 // check for overflow. 158 // check for overflow.
188 if ((isHour && (num > MAX_HOUR)) || (num > MAX_DAY)) 159 if ((isHour && (num > MAX_HOUR)) || (num > MAX_DAY))
189 return 0; 160 return 0;
190 161
191 num *= isHour ? MILLIS_IN_HOUR : MILLIS_IN_DAY; 162 num *= isHour ? MILLIS_IN_HOUR : MILLIS_IN_DAY;
192 return num; 163 return num;
193 } 164 }
194 165
195 bool DownloadableSubscription_Parser::VerifyChecksum()
196 {
197 if (!mParams.find(u"checksum"_str))
198 return true;
199
200 if (mB64Checksum.is_invalid())
201 {
202 uint8_t checksum[MD5::CHECKSUM_LENGTH];
203 mChecksum.Final(checksum);
204 mB64Checksum = ToBase64(checksum, MD5::CHECKSUM_LENGTH);
205 }
206 return (mParams[u"checksum"_str] == mB64Checksum);
207 }
208
209 int64_t DownloadableSubscription_Parser::Finalize(DownloadableSubscription& subs cription) 166 int64_t DownloadableSubscription_Parser::Finalize(DownloadableSubscription& subs cription)
210 { 167 {
211 if (mB64Checksum.is_invalid())
212 VerifyChecksum(); // here we ignore the checksum, but we calculate it.
213
214 auto entry = mParams.find(u"title"_str); 168 auto entry = mParams.find(u"title"_str);
215 if (entry) 169 if (entry)
216 { 170 {
217 subscription.SetTitle(entry->second); 171 subscription.SetTitle(entry->second);
218 subscription.SetFixedTitle(true); 172 subscription.SetFixedTitle(true);
219 } 173 }
220 else 174 else
221 subscription.SetFixedTitle(false); 175 subscription.SetFixedTitle(false);
222 176
223 int32_t version = 0; 177 int32_t version = 0;
224 entry = mParams.find(u"version"_str); 178 entry = mParams.find(u"version"_str);
225 if (entry) 179 if (entry)
226 version = entry->second.toInt<int32_t>(); 180 version = lexical_cast<int32_t>(entry->second);
227 subscription.SetDataRevision(version); 181 subscription.SetDataRevision(version);
228 182
229 int64_t expires = 0; 183 int64_t expires = 0;
230 entry = mParams.find(u"expires"_str); 184 entry = mParams.find(u"expires"_str);
231 if (entry) 185 if (entry)
232 expires = ParseExpires(entry->second); 186 expires = ParseExpires(entry->second);
233 187
234 FilterNotifier::SubscriptionChange( 188 FilterNotifier::SubscriptionChange(
235 FilterNotifier::Topic::SUBSCRIPTION_BEFORE_FILTERS_REPLACED, 189 FilterNotifier::Topic::SUBSCRIPTION_BEFORE_FILTERS_REPLACED,
236 subscription); 190 subscription);
(...skipping 25 matching lines...) Expand all
262 return emptyString; 216 return emptyString;
263 } 217 }
264 218
265 const String& DownloadableSubscription_Parser::GetHomepage() const 219 const String& DownloadableSubscription_Parser::GetHomepage() const
266 { 220 {
267 auto entry = mParams.find(u"homepage"_str); 221 auto entry = mParams.find(u"homepage"_str);
268 if (entry) 222 if (entry)
269 return entry->second; 223 return entry->second;
270 return emptyString; 224 return emptyString;
271 } 225 }
226
227 ABP_NS_USING
272 228
273 DownloadableSubscription::DownloadableSubscription(const String& id) 229 DownloadableSubscription::DownloadableSubscription(const String& id)
274 : Subscription(classType, id), mFixedTitle(false), mLastCheck(0), 230 : Subscription(classType, id), mFixedTitle(false), mLastCheck(0),
275 mHardExpiration(0), mSoftExpiration(0), mLastDownload(0), mLastSuccess(0), 231 mHardExpiration(0), mSoftExpiration(0), mLastDownload(0), mLastSuccess(0),
276 mErrorCount(0), mDataRevision(0), mDownloadCount(0) 232 mErrorCount(0), mDataRevision(0), mDownloadCount(0)
277 { 233 {
278 SetTitle(id); 234 SetTitle(id);
279 } 235 }
280 236
281 DownloadableSubscription_Parser* DownloadableSubscription::ParseDownload() 237 DownloadableSubscription_Parser* DownloadableSubscription::ParseDownload()
282 { 238 {
283 return new DownloadableSubscription_Parser(); 239 return new DownloadableSubscription_Parser();
284 } 240 }
285 241
286 OwnedString DownloadableSubscription::Serialize() const 242 OwnedString DownloadableSubscription::Serialize() const
287 { 243 {
288 OwnedString result(Subscription::Serialize()); 244 OwnedString result(Subscription::Serialize());
289 if (mFixedTitle) 245 if (mFixedTitle)
290 result.append(u"fixedTitle=true\n"_str); 246 result.append(ABP_TEXT("fixedTitle=true\n"_str));
291 if (!mHomepage.empty()) 247 if (!mHomepage.empty())
292 { 248 {
293 result.append(u"homepage="_str); 249 result.append(ABP_TEXT("homepage="_str));
294 result.append(mHomepage); 250 result.append(mHomepage);
295 result.append(u'\n'); 251 result.append(ABP_TEXT('\n'));
296 } 252 }
297 if (mLastCheck) 253 if (mLastCheck)
298 { 254 {
299 result.append(u"lastCheck="_str); 255 result.append(ABP_TEXT("lastCheck="_str));
300 result.append(mLastCheck); 256 result.append(mLastCheck);
301 result.append(u'\n'); 257 result.append(ABP_TEXT('\n'));
302 } 258 }
303 if (mHardExpiration) 259 if (mHardExpiration)
304 { 260 {
305 result.append(u"expires="_str); 261 result.append(ABP_TEXT("expires="_str));
306 result.append(mHardExpiration); 262 result.append(mHardExpiration);
307 result.append(u'\n'); 263 result.append(ABP_TEXT('\n'));
308 } 264 }
309 if (mSoftExpiration) 265 if (mSoftExpiration)
310 { 266 {
311 result.append(u"softExpiration="_str); 267 result.append(ABP_TEXT("softExpiration="_str));
312 result.append(mSoftExpiration); 268 result.append(mSoftExpiration);
313 result.append(u'\n'); 269 result.append(ABP_TEXT('\n'));
314 } 270 }
315 if (mLastDownload) 271 if (mLastDownload)
316 { 272 {
317 result.append(u"lastDownload="_str); 273 result.append(ABP_TEXT("lastDownload="_str));
318 result.append(mLastDownload); 274 result.append(mLastDownload);
319 result.append(u'\n'); 275 result.append(ABP_TEXT('\n'));
320 } 276 }
321 if (!mDownloadStatus.empty()) 277 if (!mDownloadStatus.empty())
322 { 278 {
323 result.append(u"downloadStatus="_str); 279 result.append(ABP_TEXT("downloadStatus="_str));
324 result.append(mDownloadStatus); 280 result.append(mDownloadStatus);
325 result.append(u'\n'); 281 result.append(ABP_TEXT('\n'));
326 } 282 }
327 if (mLastSuccess) 283 if (mLastSuccess)
328 { 284 {
329 result.append(u"lastSuccess="_str); 285 result.append(ABP_TEXT("lastSuccess="_str));
330 result.append(mLastSuccess); 286 result.append(mLastSuccess);
331 result.append(u'\n'); 287 result.append(ABP_TEXT('\n'));
332 } 288 }
333 if (mErrorCount) 289 if (mErrorCount)
334 { 290 {
335 result.append(u"errors="_str); 291 result.append(ABP_TEXT("errors="_str));
336 result.append(mErrorCount); 292 result.append(mErrorCount);
337 result.append(u'\n'); 293 result.append(ABP_TEXT('\n'));
338 } 294 }
339 if (mDataRevision) 295 if (mDataRevision)
340 { 296 {
341 result.append(u"version="_str); 297 result.append(ABP_TEXT("version="_str));
342 result.append(mDataRevision); 298 result.append(mDataRevision);
343 result.append(u'\n'); 299 result.append(ABP_TEXT('\n'));
344 } 300 }
345 if (!mRequiredVersion.empty()) 301 if (!mRequiredVersion.empty())
346 { 302 {
347 result.append(u"requiredVersion="_str); 303 result.append(ABP_TEXT("requiredVersion="_str));
348 result.append(mRequiredVersion); 304 result.append(mRequiredVersion);
349 result.append(u'\n'); 305 result.append(ABP_TEXT('\n'));
350 } 306 }
351 if (mDownloadCount) 307 if (mDownloadCount)
352 { 308 {
353 result.append(u"downloadCount="_str); 309 result.append(ABP_TEXT("downloadCount="_str));
354 result.append(mDownloadCount); 310 result.append(mDownloadCount);
355 result.append(u'\n'); 311 result.append(ABP_TEXT('\n'));
356 } 312 }
357 return result; 313 return result;
358 } 314 }
LEFTRIGHT

Powered by Google App Engine
This is Rietveld