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

Side by Side Diff: test/abp2blocklist.js

Issue 29426594: Issue 3673 - Merge closely matching rules (Closed) Base URL: https://hg.adblockplus.org/abp2blocklist
Patch Set: Move merge options to constructor and update comments Created May 8, 2017, 11:09 p.m.
Left:
Right:
Use n/p to move between diff chunks; N/P to move between comments.
Jump to:
View unified diff | Download patch
« lib/abp2blocklist.js ('K') | « lib/abp2blocklist.js ('k') | no next file » | no next file with comments »
Toggle Intra-line Diffs ('i') | Expand Comments ('e') | Collapse Comments ('c') | Show Comments Hide Comments ('s')
OLDNEW
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) 2006-2017 eyeo GmbH 3 * Copyright (C) 2006-2017 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 "use strict"; 18 "use strict";
19 19
20 let Filter = require("filterClasses").Filter; 20 let Filter = require("filterClasses").Filter;
21 let ContentBlockerList = require("../lib/abp2blocklist.js").ContentBlockerList; 21 let ContentBlockerList = require("../lib/abp2blocklist.js").ContentBlockerList;
22 22
23 function testRules(test, filters, expected, transformFunction) 23 function testRules(test, filters, expected, transformFunction,
24 {merge = false, exhaustiveMerge = false} = {})
24 { 25 {
25 let blockerList = new ContentBlockerList(); 26 let blockerList = new ContentBlockerList({merge, exhaustiveMerge});
26 for (let filter of filters) 27 for (let filter of filters)
27 blockerList.addFilter(Filter.fromText(filter)); 28 blockerList.addFilter(Filter.fromText(filter));
28 29
29 let rules = blockerList.generateRules(); 30 let rules = blockerList.generateRules();
30 if (transformFunction) 31 if (transformFunction)
31 rules = transformFunction(rules); 32 rules = transformFunction(rules);
32 33
33 test.deepEqual(rules, expected); 34 test.deepEqual(rules, expected);
34 } 35 }
35 36
(...skipping 188 matching lines...) Expand 10 before | Expand all | Expand 10 after
224 }, 225 },
225 226
226 testUnicode: function(test) 227 testUnicode: function(test)
227 { 228 {
228 testRules(test, ["$domain=🐈.cat"], ["xn--zn8h.cat", "www.xn--zn8h.cat"], 229 testRules(test, ["$domain=🐈.cat"], ["xn--zn8h.cat", "www.xn--zn8h.cat"],
229 rules => rules[0]["trigger"]["if-domain"]); 230 rules => rules[0]["trigger"]["if-domain"]);
230 testRules(test, ["🐈$domain=🐈.cat"], []); 231 testRules(test, ["🐈$domain=🐈.cat"], []);
231 testRules(test, ["###🐈"], []); 232 testRules(test, ["###🐈"], []);
232 233
233 test.done(); 234 test.done();
235 },
236
237 testMerging: function(test)
238 {
239 // Single character substitutions, deletions, and insertions.
240 testRules(test, ["/ads", "/adv"], ["^https?://.*/ad[sv]"],
241 rules => rules.map(rule => rule.trigger["url-filter"]),
242 {merge: true});
243 testRules(test, ["/ad", "/ads"], ["^https?://.*/ads?"],
244 rules => rules.map(rule => rule.trigger["url-filter"]),
245 {merge: true});
246 testRules(test, ["/ads", "/ad"], ["^https?://.*/ads?"],
247 rules => rules.map(rule => rule.trigger["url-filter"]),
248 {merge: true});
249 testRules(test, ["/ads", "/adv", "/ad"], ["^https?://.*/ad[sv]?"],
250 rules => rules.map(rule => rule.trigger["url-filter"]),
251 {merge: true});
252 testRules(test, ["/ad", "/ads", "/adv"], ["^https?://.*/ad[sv]?"],
253 rules => rules.map(rule => rule.trigger["url-filter"]),
254 {merge: true});
255 testRules(test, ["/ads", "/ad", "/adv"], ["^https?://.*/ad[sv]?"],
256 rules => rules.map(rule => rule.trigger["url-filter"]),
257 {merge: true});
258 testRules(test, ["/a", "/ad", "/ads", "/adv"],
259 ["^https?://.*/a", "^https?://.*/ad[sv]?"],
260 rules => rules.map(rule => rule.trigger["url-filter"]),
261 {merge: true});
262 testRules(test, ["/ad", "/a", "/ads", "/adv"],
263 ["^https?://.*/a", "^https?://.*/ad[sv]?"],
264 rules => rules.map(rule => rule.trigger["url-filter"]),
265 {merge: true});
266 testRules(test, ["/ads", "/adv", "/ad", "/a"],
267 ["^https?://.*/ad[sv]?", "^https?://.*/a"],
268 rules => rules.map(rule => rule.trigger["url-filter"]),
269 {merge: true});
270 testRules(test, ["/ads", "/adv", "/a", "/ad"],
271 ["^https?://.*/ad[sv]?", "^https?://.*/a"],
272 rules => rules.map(rule => rule.trigger["url-filter"]),
273 {merge: true});
274 testRules(test, ["/ad", "/a", "/ads", "/adv", "/adx"],
275 ["^https?://.*/a", "^https?://.*/ad[svx]?"],
276 rules => rules.map(rule => rule.trigger["url-filter"]),
277 {merge: true});
278 testRules(test, ["/ads", "/a", "/ad", "/adv", "/adx"],
279 ["^https?://.*/ad[svx]?", "^https?://.*/a"],
280 rules => rules.map(rule => rule.trigger["url-filter"]),
281 {merge: true});
282
283 // Multiple character deletions and insertions.
284 testRules(test, ["/ad", "/adxsi"],
285 ["^https?://.*/ad(xsi)?"],
286 rules => rules.map(rule => rule.trigger["url-filter"]),
287 {merge: true});
288 testRules(test, ["/adxsi", "/xsi"],
289 ["^https?://.*/(ad)?xsi"],
290 rules => rules.map(rule => rule.trigger["url-filter"]),
291 {merge: true});
292 testRules(test, ["/adxsi", "/ai"],
293 ["^https?://.*/a(dxs)?i"],
294 rules => rules.map(rule => rule.trigger["url-filter"]),
295 {merge: true});
296
297 // Both single and multiple character edits combined.
298 testRules(test, ["/ad", "/adxsi", "/xsi", "/axsi", "/bxsi"],
299 ["^https?://.*/ad(xsi)?", "^https?://.*/[ab]?xsi"],
300 rules => rules.map(rule => rule.trigger["url-filter"]),
301 {merge: true});
302
303 testRules(test, ["/ads", "/a", "/ad", "/adv", "/adx", "/adxs"],
304 ["^https?://.*/ad[svx]?", "^https?://.*/a(dxs)?"],
305 rules => rules.map(rule => rule.trigger["url-filter"]),
306 {merge: true});
307 testRules(test, ["/adxs", "/a", "/ad", "/ads", "/adv", "/adx"],
308 ["^https?://.*/a(dxs)?", "^https?://.*/ad[svx]?"],
309 rules => rules.map(rule => rule.trigger["url-filter"]),
310 {merge: true});
311 testRules(test, ["/adxs", "/a", "/ads", "/ad", "/adv", "/adx"],
312 ["^https?://.*/a(dxs)?", "^https?://.*/ad[svx]?"],
313 rules => rules.map(rule => rule.trigger["url-filter"]),
314 {merge: true});
315 testRules(test, ["/adxs", "/a", "/ads", "/adv", "/ad", "/adx"],
316 ["^https?://.*/a(dxs)?", "^https?://.*/ad[svx]?"],
317 rules => rules.map(rule => rule.trigger["url-filter"]),
318 {merge: true});
319 testRules(test, ["/adsxi", "/adxs", "/a", "/ads", "/adv", "/ad", "/adx"],
320 ["^https?://.*/a(dsxi)?", "^https?://.*/adxs",
321 "^https?://.*/ad[svx]?"],
322 rules => rules.map(rule => rule.trigger["url-filter"]),
323 {merge: true});
324 testRules(test, ["/adxsi", "/adsxi", "/adxs", "/a", "/ads", "/adv", "/ad",
325 "/adx"],
326 ["^https?://.*/adxsi?", "^https?://.*/a(dsxi)?",
327 "^https?://.*/ad[svx]?"],
328 rules => rules.map(rule => rule.trigger["url-filter"]),
329 {merge: true});
330
331 // Given the 6 rules "ads", "bds", "adv", "bdv", "adx", and "bdx", we want
332 // the 2 rules "ad[svx]" and "bd[svx]", not the 3 rules "[ab]ds", "[ab]dv",
333 // and "[ab]dx"
334 testRules(test, ["/ads", "/bds", "/adv", "/bdv", "/adx", "/bdx"],
335 ["^https?://.*/ad[svx]", "^https?://.*/bd[svx]"],
336 rules => rules.map(rule => rule.trigger["url-filter"]),
337 {merge: true});
338 testRules(test, ["/ads", "/bds", "/adv", "/bdv", "/bdx"],
339 ["^https?://.*/ad[sv]", "^https?://.*/bd[svx]"],
340 rules => rules.map(rule => rule.trigger["url-filter"]),
341 {merge: true});
342
343 // Make sure there's no merge where there are special characters in the
344 // delta.
345 testRules(test, ["/ads?", "/ads"],
346 ["^https?://.*/ads\\?", "^https?://.*/ads"],
347 rules => rules.map(rule => rule.trigger["url-filter"]),
348 {merge: true});
349 testRules(test, ["/ads?", "/ads-"],
350 ["^https?://.*/ads\\?", "^https?://.*/ads-"],
351 rules => rules.map(rule => rule.trigger["url-filter"]),
352 {merge: true});
353 testRules(test, ["/ads?-", "/ads-"],
354 ["^https?://.*/ads\\?-", "^https?://.*/ads-"],
355 rules => rules.map(rule => rule.trigger["url-filter"]),
356 {merge: true});
357
358 // In exhaustive merge, redundant rules should be discarded.
359 testRules(test, ["/ad", "/ads", "/advertisement"],
360 ["^https?://.*/ad"],
361 rules => rules.map(rule => rule.trigger["url-filter"]),
362 {merge: true, exhaustiveMerge: true});
363
364 test.done();
234 } 365 }
235 }; 366 };
OLDNEW
« lib/abp2blocklist.js ('K') | « lib/abp2blocklist.js ('k') | no next file » | no next file with comments »

Powered by Google App Engine
This is Rietveld