summaryrefslogtreecommitdiffstats
path: root/toolkit/components/reader/ReaderMode.jsm
blob: b9b31e29fa35f50f07a1abb71b22f8dfc426ae9f (plain)
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
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
// -*- indent-tabs-mode: nil; js-indent-level: 2 -*-
/* 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/. */
"use strict";

this.EXPORTED_SYMBOLS = ["ReaderMode"];

const { classes: Cc, interfaces: Ci, utils: Cu } = Components;

// Class names to preserve in the readerized output. We preserve these class
// names so that rules in aboutReader.css can match them.
const CLASSES_TO_PRESERVE = [
  "caption",
  "hidden",
  "invisble",
  "sr-only",
  "visually-hidden",
  "visuallyhidden",
  "wp-caption",
  "wp-caption-text",
];

Cu.import("resource://gre/modules/Services.jsm");
Cu.import("resource://gre/modules/XPCOMUtils.jsm");

Cu.importGlobalProperties(["XMLHttpRequest"]);

XPCOMUtils.defineLazyModuleGetter(this, "CommonUtils", "resource://services-common/utils.js");
XPCOMUtils.defineLazyModuleGetter(this, "EventDispatcher", "resource://gre/modules/Messaging.jsm");
XPCOMUtils.defineLazyModuleGetter(this, "OS", "resource://gre/modules/osfile.jsm");
XPCOMUtils.defineLazyModuleGetter(this, "ReaderWorker", "resource://gre/modules/reader/ReaderWorker.jsm");
XPCOMUtils.defineLazyModuleGetter(this, "Readerable", "resource://gre/modules/Readerable.jsm");

this.ReaderMode = {
  // Version of the cache schema.
  CACHE_VERSION: 1,

  DEBUG: 0,

  /**
   * Enter the reader mode by going forward one step in history if applicable,
   * if not, append the about:reader page in the history instead.
   */
  enterReaderMode(docShell, win) {
    let url = win.document.location.href;
    let readerURL = "about:reader?url=" + encodeURIComponent(url);
    let webNav = docShell.QueryInterface(Ci.nsIWebNavigation);
    let sh = webNav.sessionHistory;
    if (webNav.canGoForward) {
      let forwardEntry = sh.getEntryAtIndex(sh.index + 1, false);
      let forwardURL = forwardEntry.URI.spec;
      if (forwardURL && (forwardURL == readerURL || !readerURL)) {
        webNav.goForward();
        return;
      }
    }

    win.document.location = readerURL;
  },

  /**
   * Exit the reader mode by going back one step in history if applicable,
   * if not, append the original page in the history instead.
   */
  leaveReaderMode(docShell, win) {
    let url = win.document.location.href;
    let originalURL = this.getOriginalUrl(url);
    let webNav = docShell.QueryInterface(Ci.nsIWebNavigation);
    let sh = webNav.sessionHistory;
    if (webNav.canGoBack) {
      let prevEntry = sh.getEntryAtIndex(sh.index - 1, false);
      let prevURL = prevEntry.URI.spec;
      if (prevURL && (prevURL == originalURL || !originalURL)) {
        webNav.goBack();
        return;
      }
    }

    win.document.location = originalURL;
  },

  /**
   * Returns original URL from an about:reader URL.
   *
   * @param url An about:reader URL.
   * @return The original URL for the article, or null if we did not find
   *         a properly formatted about:reader URL.
   */
  getOriginalUrl(url) {
    if (!url.startsWith("about:reader?")) {
      return null;
    }

    let outerHash = "";
    try {
      let uriObj = Services.io.newURI(url);
      url = uriObj.specIgnoringRef;
      outerHash = uriObj.ref;
    } catch (ex) { /* ignore, use the raw string */ }

    let searchParams = new URLSearchParams(url.substring("about:reader?".length));
    if (!searchParams.has("url")) {
      return null;
    }
    let originalUrl = searchParams.get("url");
    if (outerHash) {
      try {
        let uriObj = Services.io.newURI(originalUrl);
        uriObj = Services.io.newURI("#" + outerHash, null, uriObj);
        originalUrl = uriObj.spec;
      } catch (ex) {}
    }
    return originalUrl;
  },

  getOriginalUrlObjectForDisplay(url) {
    let originalUrl = this.getOriginalUrl(url);
    if (originalUrl) {
      let uriObj;
      try {
        uriObj = Services.uriFixup.createFixupURI(originalUrl, Services.uriFixup.FIXUP_FLAG_NONE);
      } catch (ex) {
        return null;
      }
      try {
        return Services.uriFixup.createExposableURI(uriObj);
      } catch (ex) {
        return null;
      }
    }
    return null;
  },

  /**
   * Gets an article from a loaded browser's document. This method will not attempt
   * to parse certain URIs (e.g. about: URIs).
   *
   * @param doc A document to parse.
   * @return {Promise}
   * @resolves JS object representing the article, or null if no article is found.
   */
  parseDocument(doc) {
    if (!Readerable.shouldCheckUri(doc.documentURIObject) ||
        !Readerable.shouldCheckUri(doc.baseURIObject, true)) {
      this.log("Reader mode disabled for URI");
      return null;
    }

    return this._readerParse(doc);
  },

  /**
   * Downloads and parses a document from a URL.
   *
   * @param url URL to download and parse.
   * @return {Promise}
   * @resolves JS object representing the article, or null if no article is found.
   */
  async downloadAndParseDocument(url) {
    let doc = await this._downloadDocument(url);
    if (!doc) {
      return null;
    }
    if (!Readerable.shouldCheckUri(doc.documentURIObject) ||
        !Readerable.shouldCheckUri(doc.baseURIObject, true)) {
      this.log("Reader mode disabled for URI");
      return null;
    }

    return await this._readerParse(doc);
  },

  _downloadDocument(url) {
    try {
      if (!Readerable.shouldCheckUri(Services.io.newURI(url))) {
        return null;
      }
    } catch (ex) {
      Cu.reportError(new Error(`Couldn't create URI from ${url} to download: ${ex}`));
      return null;
    }
    return new Promise((resolve, reject) => {
      let xhr = new XMLHttpRequest();
      xhr.open("GET", url, true);
      xhr.onerror = evt => reject(evt.error);
      xhr.responseType = "document";
      xhr.onload = evt => {
        if (xhr.status !== 200) {
          reject("Reader mode XHR failed with status: " + xhr.status);
          return;
        }

        let doc = xhr.responseXML;
        if (!doc) {
          reject("Reader mode XHR didn't return a document");
          return;
        }

        // Manually follow a meta refresh tag if one exists.
        let meta = doc.querySelector("meta[http-equiv=refresh]");
        if (meta) {
          let content = meta.getAttribute("content");
          if (content) {
            let urlIndex = content.toUpperCase().indexOf("URL=");
            if (urlIndex > -1) {
              let baseURI = Services.io.newURI(url);
              let newURI = Services.io.newURI(content.substring(urlIndex + 4), null, baseURI);
              let newURL = newURI.spec;
              let ssm = Services.scriptSecurityManager;
              let flags = ssm.LOAD_IS_AUTOMATIC_DOCUMENT_REPLACEMENT |
                          ssm.DISALLOW_INHERIT_PRINCIPAL;
              try {
                ssm.checkLoadURIStrWithPrincipal(doc.nodePrincipal, newURL, flags);
              } catch (ex) {
                let errorMsg = "Reader mode disallowed meta refresh (reason: " + ex + ").";

                if (Services.prefs.getBoolPref("reader.errors.includeURLs"))
                  errorMsg += " Refresh target URI: '" + newURL + "'.";
                reject(errorMsg);
                return;
              }
              // Otherwise, pass an object indicating our new URL:
              if (!baseURI.equalsExceptRef(newURI)) {
                reject({newURL});
                return;
              }
            }
          }
        }
        let responseURL = xhr.responseURL;
        let givenURL = url;
        // Convert these to real URIs to make sure the escaping (or lack
        // thereof) is identical:
        try {
          responseURL = Services.io.newURI(responseURL).specIgnoringRef;
        } catch (ex) { /* Ignore errors - we'll use what we had before */ }
        try {
          givenURL = Services.io.newURI(givenURL).specIgnoringRef;
        } catch (ex) { /* Ignore errors - we'll use what we had before */ }

        if (responseURL != givenURL) {
          // We were redirected without a meta refresh tag.
          // Force redirect to the correct place:
          reject({newURL: xhr.responseURL});
          return;
        }
        resolve(doc);
      };
      xhr.send();
    });
  },


  /**
   * Retrieves an article from the cache given an article URI.
   *
   * @param url The article URL.
   * @return {Promise}
   * @resolves JS object representing the article, or null if no article is found.
   * @rejects OS.File.Error
   */
  async getArticleFromCache(url) {
    let path = this._toHashedPath(url);
    try {
      let array = await OS.File.read(path);
      return JSON.parse(new TextDecoder().decode(array));
    } catch (e) {
      if (!(e instanceof OS.File.Error) || !e.becauseNoSuchFile)
        throw e;
      return null;
    }
  },

  /**
   * Stores an article in the cache.
   *
   * @param article JS object representing article.
   * @return {Promise}
   * @resolves When the article is stored.
   * @rejects OS.File.Error
   */
  async storeArticleInCache(article) {
    let array = new TextEncoder().encode(JSON.stringify(article));
    let path = this._toHashedPath(article.url);
    await this._ensureCacheDir();
    return OS.File.writeAtomic(path, array, { tmpPath: path + ".tmp" })
      .then(success => {
        OS.File.stat(path).then(info => {
          return EventDispatcher.instance.sendRequest({
            type: "Reader:AddedToCache",
            url: article.url,
            size: info.size,
            path: path,
          });
        });
      });
  },

  /**
   * Removes an article from the cache given an article URI.
   *
   * @param url The article URL.
   * @return {Promise}
   * @resolves When the article is removed.
   * @rejects OS.File.Error
   */
  async removeArticleFromCache(url) {
    let path = this._toHashedPath(url);
    await OS.File.remove(path);
  },

  log(msg) {
    if (this.DEBUG)
      dump("Reader: " + msg);
  },

  /**
   * Attempts to parse a document into an article. Heavy lifting happens
   * in readerWorker.js.
   *
   * @param doc The document to parse.
   * @return {Promise}
   * @resolves JS object representing the article, or null if no article is found.
   */
  async _readerParse(doc) {
    if (this.parseNodeLimit) {
      let numTags = doc.getElementsByTagName("*").length;
      if (numTags > this.parseNodeLimit) {
        this.log("Aborting parse for " + doc.baseURIObject.spec + "; " + numTags + " elements found");
        return null;
      }
    }

    // Fetch this here before we send `doc` off to the worker thread, as later on the
    // document might be nuked but we will still want the URI.
    let {documentURI} = doc;

    let uriParam = {
      spec: doc.baseURIObject.spec,
      host: doc.baseURIObject.host,
      prePath: doc.baseURIObject.prePath,
      scheme: doc.baseURIObject.scheme,
      pathBase: Services.io.newURI(".", null, doc.baseURIObject).spec
    };

    let langAttributes = {
      charset: doc.characterSet,
      lang: doc.documentElement.lang
    };

    let serializer = Cc["@mozilla.org/xmlextras/xmlserializer;1"].
                     createInstance(Ci.nsIDOMSerializer);
    let serializedDoc = serializer.serializeToString(doc);

    let options = {
      classesToPreserve: CLASSES_TO_PRESERVE,
    };

    let article = null;
    try {
      article = await ReaderWorker.post("parseDocument", [uriParam, serializedDoc, options]);
    } catch (e) {
      Cu.reportError("Error in ReaderWorker: " + e);
    }

    // Explicitly null out doc to make it clear it might not be available from this
    // point on.
    doc = null;

    if (!article) {
      this.log("Worker did not return an article");
      return null;
    }

    // Readability returns a URI object based on the baseURI, but we only care
    // about the original document's URL from now on. This also avoids spoofing
    // attempts where the baseURI doesn't match the domain of the documentURI
    article.url = documentURI;
    delete article.uri;

    let flags = Ci.nsIDocumentEncoder.OutputSelectionOnly | Ci.nsIDocumentEncoder.OutputAbsoluteLinks;
    article.title = Cc["@mozilla.org/parserutils;1"].getService(Ci.nsIParserUtils)
                                                    .convertToPlainText(article.title, flags, 0);

    await this._assignLanguage(article, langAttributes);
    this._maybeAssignTextDirection(article);

    this._assignReadTime(article);

    return article;
  },

  get _cryptoHash() {
    delete this._cryptoHash;
    return this._cryptoHash = Cc["@mozilla.org/security/hash;1"].createInstance(Ci.nsICryptoHash);
  },

  get _unicodeConverter() {
    delete this._unicodeConverter;
    this._unicodeConverter = Cc["@mozilla.org/intl/scriptableunicodeconverter"]
                              .createInstance(Ci.nsIScriptableUnicodeConverter);
    this._unicodeConverter.charset = "utf8";
    return this._unicodeConverter;
  },

  /**
   * Calculate the hashed path for a stripped article URL.
   *
   * @param url The article URL. This should have referrers removed.
   * @return The file path to the cached article.
   */
  _toHashedPath(url) {
    let value = this._unicodeConverter.convertToByteArray(url);
    this._cryptoHash.init(this._cryptoHash.MD5);
    this._cryptoHash.update(value, value.length);

    let hash = CommonUtils.encodeBase32(this._cryptoHash.finish(false));
    let fileName = hash.substring(0, hash.indexOf("=")) + ".json";
    return OS.Path.join(OS.Constants.Path.profileDir, "readercache", fileName);
  },

  /**
   * Ensures the cache directory exists.
   *
   * @return Promise
   * @resolves When the cache directory exists.
   * @rejects OS.File.Error
   */
  _ensureCacheDir() {
    let dir = OS.Path.join(OS.Constants.Path.profileDir, "readercache");
    return OS.File.exists(dir).then(exists => {
      if (!exists) {
        return OS.File.makeDir(dir);
      }
      return undefined;
    });
  },

  /**
   * Sets a global language string value if possible. If langauge detection is
   * available, use that. Otherwise, revert to a simpler mechanism using the
   * document's lang attribute or charset.
   *
   * @return Promise
   * @resolves when the language is detected
   */
  _assignLanguage(article, attributes) {
    try {
      Cu.import("resource://modules/translation/LanguageDetector.jsm");
      return LanguageDetector.detectLanguage(article.textContent).then(result => {
        article.language = result.confident ? result.language : null;
      });
    } catch(ex) {
      return new Promise((resolve) => {
        resolve(this._assignSimpleLanguage(attributes));
      }).then(result => {
        article.language = result;
      });
    }
  },

  _assignSimpleLanguage(attributes) {
    var lang = attributes.lang.substring(0,2);
    if (lang) {
      return lang;
    }

    // If there is no lang attribute, try the charset.
    // We can only use this for charsets that are specific to one language.
    const charsetLang = new Map([
      [ "us-ascii",    "en" ],
      [ "iso-8859-6",  "ar" ],
      [ "iso-8859-7",  "el" ],
      [ "iso-8859-8",  "he" ],
      [ "iso-8859-9",  "tr" ],
      [ "iso-8859-11", "th" ],
      [ "jis_x0201",   "ja" ],
      [ "shift_jis",   "ja" ],
      [ "euc-jp",      "ja" ]
    ]);

    return charsetLang.get(attributes.charset);
  },

  _maybeAssignTextDirection(article) {
    // TODO: Remove the hardcoded language codes below once bug 1320265 is resolved.
    if (!article.dir && ["ar", "fa", "he", "ug", "ur"].includes(article.language)) {
      article.dir = "rtl";
    }
  },

  /**
   * Assigns the estimated reading time range of the article to the article object.
   *
   * @param article the article object to assign the reading time estimate to.
   */
  _assignReadTime(article) {
    let lang = article.language || "en";
    const readingSpeed = this._getReadingSpeedForLanguage(lang);
    const charactersPerMinuteLow = readingSpeed.cpm - readingSpeed.variance;
    const charactersPerMinuteHigh = readingSpeed.cpm + readingSpeed.variance;
    const length = article.length;

    article.readingTimeMinsSlow = Math.ceil(length / charactersPerMinuteLow);
    article.readingTimeMinsFast  = Math.ceil(length / charactersPerMinuteHigh);
  },

  /**
   * Returns the reading speed of a selection of languages with likely variance.
   *
   * Reading speed estimated from a study done on reading speeds in various languages.
   * study can be found here: http://iovs.arvojournals.org/article.aspx?articleid=2166061
   *
   * @return object with characters per minute and variance. Defaults to English
   *         if no suitable language is found in the collection.
   */
  _getReadingSpeedForLanguage(lang) {
    const readingSpeed = new Map([
      [ "en", {cpm: 987,  variance: 118 } ],
      [ "ar", {cpm: 612,  variance: 88 } ],
      [ "de", {cpm: 920,  variance: 86 } ],
      [ "es", {cpm: 1025, variance: 127 } ],
      [ "fi", {cpm: 1078, variance: 121 } ],
      [ "fr", {cpm: 998,  variance: 126 } ],
      [ "he", {cpm: 833,  variance: 130 } ],
      [ "it", {cpm: 950,  variance: 140 } ],
      [ "jw", {cpm: 357,  variance: 56 } ],
      [ "nl", {cpm: 978,  variance: 143 } ],
      [ "pl", {cpm: 916,  variance: 126 } ],
      [ "pt", {cpm: 913,  variance: 145 } ],
      [ "ru", {cpm: 986,  variance: 175 } ],
      [ "sk", {cpm: 885,  variance: 145 } ],
      [ "sv", {cpm: 917,  variance: 156 } ],
      [ "tr", {cpm: 1054, variance: 156 } ],
      [ "zh", {cpm: 255,  variance: 29 } ],
    ]);

    return readingSpeed.get(lang) || readingSpeed.get("en");
  },
};

// Don't try to parse the page if it has too many elements (for memory and
// performance reasons)
XPCOMUtils.defineLazyPreferenceGetter(
  ReaderMode, "parseNodeLimit", "reader.parse-node-limit", 0);