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

Side by Side Diff: src/org/adblockplus/brazil/RequestHandler.java

Issue 6612583456964608: Convert injected selectors to the site charset (Closed)
Patch Set: Created Nov. 19, 2013, 7:39 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
« no previous file with comments | « no previous file | 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 <http://adblockplus.org/>, 2 * This file is part of Adblock Plus <http://adblockplus.org/>,
3 * Copyright (C) 2006-2013 Eyeo GmbH 3 * Copyright (C) 2006-2013 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 package org.adblockplus.brazil; 18 package org.adblockplus.brazil;
19 19
20 import java.io.EOFException; 20 import java.io.EOFException;
21 import java.io.FilterInputStream; 21 import java.io.FilterInputStream;
22 import java.io.FilterOutputStream; 22 import java.io.FilterOutputStream;
23 import java.io.IOException; 23 import java.io.IOException;
24 import java.io.InterruptedIOException; 24 import java.io.InterruptedIOException;
25 import java.io.OutputStream; 25 import java.io.OutputStream;
26 import java.net.ConnectException; 26 import java.net.ConnectException;
27 import java.net.MalformedURLException; 27 import java.net.MalformedURLException;
28 import java.net.URL; 28 import java.net.URL;
29 import java.net.UnknownHostException; 29 import java.net.UnknownHostException;
30 import java.nio.charset.Charset;
30 import java.util.List; 31 import java.util.List;
32 import java.util.regex.Matcher;
31 import java.util.regex.Pattern; 33 import java.util.regex.Pattern;
32 import java.util.zip.GZIPInputStream; 34 import java.util.zip.GZIPInputStream;
33 import java.util.zip.InflaterInputStream; 35 import java.util.zip.InflaterInputStream;
34 36
35 import org.adblockplus.ChunkedOutputStream; 37 import org.adblockplus.ChunkedOutputStream;
36 import org.adblockplus.android.AdblockPlus; 38 import org.adblockplus.android.AdblockPlus;
37 import org.apache.commons.lang.StringUtils; 39 import org.apache.commons.lang.StringUtils;
38 import org.literateprograms.BoyerMoore; 40 import org.literateprograms.BoyerMoore;
39 41
40 import sunlabs.brazil.server.Request; 42 import sunlabs.brazil.server.Request;
(...skipping 227 matching lines...) Expand 10 before | Expand all | Expand 10 after
268 // Use chunked encoding when injecting filters in page 270 // Use chunked encoding when injecting filters in page
269 if (out == null) 271 if (out == null)
270 { 272 {
271 request.responseHeaders.remove("Content-Length"); 273 request.responseHeaders.remove("Content-Length");
272 request.responseHeaders.remove("Content-Encoding"); 274 request.responseHeaders.remove("Content-Encoding");
273 out = new ChunkedOutputStream(request.out); 275 out = new ChunkedOutputStream(request.out);
274 request.responseHeaders.add("Transfer-Encoding", "chunked"); 276 request.responseHeaders.add("Transfer-Encoding", "chunked");
275 size = Integer.MAX_VALUE; 277 size = Integer.MAX_VALUE;
276 } 278 }
277 279
280 String charsetName = "utf-8";
281 final String contentType = request.responseHeaders.get("Content-Type");
282 if (contentType != null)
283 {
284 final Matcher matcher = Pattern.compile("charset=([^;]*)").matcher(con tentType);
285 if (matcher.matches())
286 {
287 try
288 {
289 final String extractedCharsetName = matcher.group(0);
290 Charset.forName(extractedCharsetName);
291 charsetName = extractedCharsetName;
292 }
293 catch (IllegalArgumentException e)
294 {
295 Log.e(prefix, "Unsupported site charset, falling back to " + chars etName, e);
296 }
297 }
298 }
299
278 request.sendHeaders(-1, null, -1); 300 request.sendHeaders(-1, null, -1);
279 301
280 byte[] buf = new byte[Math.min(4096, size)]; 302 byte[] buf = new byte[Math.min(4096, size)];
281 303
282 boolean sent = selectors == null; 304 boolean sent = selectors == null;
283 // TODO Do we need to set encoding here?
284 BoyerMoore matcher = new BoyerMoore("<html".getBytes()); 305 BoyerMoore matcher = new BoyerMoore("<html".getBytes());
285 306
286 while (size > 0) 307 while (size > 0)
287 { 308 {
288 out.flush(); 309 out.flush();
289 310
290 count = in.read(buf, 0, Math.min(buf.length, size)); 311 count = in.read(buf, 0, Math.min(buf.length, size));
291 if (count < 0) 312 if (count < 0)
292 { 313 {
293 break; 314 break;
294 } 315 }
295 size -= count; 316 size -= count;
296 try 317 try
297 { 318 {
298 // Search for <html> tag 319 // Search for <html> tag
299 if (!sent && count > 0) 320 if (!sent && count > 0)
300 { 321 {
301 List<Integer> matches = matcher.match(buf, 0, count); 322 List<Integer> matches = matcher.match(buf, 0, count);
302 if (!matches.isEmpty()) 323 if (!matches.isEmpty())
303 { 324 {
304 // Add filters right before match 325 // Add filters right before match
305 int m = matches.get(0); 326 int m = matches.get(0);
306 out.write(buf, 0, m); 327 out.write(buf, 0, m);
307 out.write("<style type=\"text/css\">\n".getBytes()); 328 out.write("<style type=\"text/css\">\n".getBytes());
308 // TODO Do we need to set encoding here? 329 out.write(StringUtils.join(selectors, ",\r\n").getBytes(charsetN ame));
309 out.write(StringUtils.join(selectors, ",\r\n").getBytes());
310 out.write("{ display: none !important }</style>\n".getBytes()); 330 out.write("{ display: none !important }</style>\n".getBytes());
311 out.write(buf, m, count - m); 331 out.write(buf, m, count - m);
312 sent = true; 332 sent = true;
313 continue; 333 continue;
314 } 334 }
315 } 335 }
316 out.write(buf, 0, count); 336 out.write(buf, 0, count);
317 } 337 }
318 catch (IOException e) 338 catch (IOException e)
319 { 339 {
(...skipping 44 matching lines...) Expand 10 before | Expand all | Expand 10 after
364 request.sendError(500, msg); 384 request.sendError(500, msg);
365 Log.e(prefix, msg, e); 385 Log.e(prefix, msg, e);
366 } 386 }
367 finally 387 finally
368 { 388 {
369 target.close(); 389 target.close();
370 } 390 }
371 return true; 391 return true;
372 } 392 }
373 } 393 }
OLDNEW
« no previous file with comments | « no previous file | no next file » | no next file with comments »

Powered by Google App Engine
This is Rietveld