' + html + '
', []);
-
+
if (os.EOL === '\r\n') {
- expectedMd = expectedMd.replace(/\r\n/g, '\n')
- actualMd = actualMd.replace(/\r\n/g, '\n')
+ expectedMd = expectedMd.replace(/\r\n/g, '\n');
+ actualMd = actualMd.replace(/\r\n/g, '\n');
}
if (actualMd !== expectedMd) {
@@ -60,9 +62,9 @@ describe('EnexToMd', function() {
expect(false).toBe(true);
// return;
} else {
- expect(true).toBe(true)
+ expect(true).toBe(true);
}
}
}));
-});
\ No newline at end of file
+});
diff --git a/CliClient/tests/HtmlToMd.js b/CliClient/tests/HtmlToMd.js
index 8e48e4989..156697085 100644
--- a/CliClient/tests/HtmlToMd.js
+++ b/CliClient/tests/HtmlToMd.js
@@ -1,3 +1,5 @@
+/* eslint-disable no-unused-vars */
+
require('app-module-path').addPath(__dirname);
const os = require('os');
@@ -29,7 +31,7 @@ describe('HtmlToMd', function() {
const basePath = __dirname + '/html_to_md';
const files = await shim.fsDriver().readDirStats(basePath);
const htmlToMd = new HtmlToMd();
-
+
for (let i = 0; i < files.length; i++) {
const htmlFilename = files[i].path;
if (htmlFilename.indexOf('.html') < 0) continue;
@@ -39,14 +41,14 @@ describe('HtmlToMd', function() {
// if (htmlFilename !== 'mathjax_block.html') continue;
- const htmlToMdOptions = {}
+ const htmlToMdOptions = {};
if (htmlFilename === 'anchor_local.html') {
// Normally the list of anchor names in the document are retrieved from the HTML code
// This is straightforward when the document is still in DOM format, as with the clipper,
// but otherwise it would need to be somehow parsed out from the HTML. Here we just
// hard code the anchors that we know are in the file.
- htmlToMdOptions.anchorNames = ['first', 'second']
+ htmlToMdOptions.anchorNames = ['first', 'second'];
}
const html = await shim.fsDriver().readFile(htmlPath);
@@ -55,8 +57,8 @@ describe('HtmlToMd', function() {
let actualMd = await htmlToMd.parse('' + html + '
', htmlToMdOptions);
if (os.EOL === '\r\n') {
- expectedMd = expectedMd.replace(/\r\n/g, '\n')
- actualMd = actualMd.replace(/\r\n/g, '\n')
+ expectedMd = expectedMd.replace(/\r\n/g, '\n');
+ actualMd = actualMd.replace(/\r\n/g, '\n');
}
if (actualMd !== expectedMd) {
@@ -74,9 +76,9 @@ describe('HtmlToMd', function() {
expect(false).toBe(true);
// return;
} else {
- expect(true).toBe(true)
+ expect(true).toBe(true);
}
}
}));
-});
\ No newline at end of file
+});
diff --git a/CliClient/tests/StringUtils.js b/CliClient/tests/StringUtils.js
index a4a477a3a..0e37dbd4d 100644
--- a/CliClient/tests/StringUtils.js
+++ b/CliClient/tests/StringUtils.js
@@ -1,3 +1,5 @@
+/* eslint-disable no-unused-vars */
+
require('app-module-path').addPath(__dirname);
const { time } = require('lib/time-utils.js');
@@ -42,4 +44,4 @@ describe('StringUtils', function() {
done();
});
-});
\ No newline at end of file
+});
diff --git a/CliClient/tests/TaskQueue.js b/CliClient/tests/TaskQueue.js
index f2ddd6af2..a1fad3bea 100644
--- a/CliClient/tests/TaskQueue.js
+++ b/CliClient/tests/TaskQueue.js
@@ -1,3 +1,5 @@
+/* eslint-disable no-unused-vars */
+
require('app-module-path').addPath(__dirname);
const { asyncTest, fileContentEqual, setupDatabase, revisionService, setupDatabaseAndSynchronizer, db, synchronizer, fileApi, sleep, clearDatabase, switchClient, syncTargetId, objectsEqual, checkThrowAsync } = require('test-utils.js');
@@ -54,4 +56,4 @@ describe('TaskQueue', function() {
expect(results[1].error.message).toBe('e');
}));
-});
\ No newline at end of file
+});
diff --git a/CliClient/tests/encryption.js b/CliClient/tests/encryption.js
index 1603abdbb..e914e6afa 100644
--- a/CliClient/tests/encryption.js
+++ b/CliClient/tests/encryption.js
@@ -1,3 +1,5 @@
+/* eslint-disable no-unused-vars */
+
require('app-module-path').addPath(__dirname);
const { time } = require('lib/time-utils.js');
@@ -116,7 +118,7 @@ describe('Encryption', function() {
await service.loadMasterKey(masterKey, '123456', true);
let cipherText = await service.encryptString('some secret');
- cipherText += "ABCDEFGHIJ";
+ cipherText += 'ABCDEFGHIJ';
let hasThrown = await checkThrowAsync(async () => await service.decryptString(cipherText));
@@ -147,8 +149,8 @@ describe('Encryption', function() {
// Check that encrypted data is there
expect(!!deserialized.encryption_cipher_text).toBe(true);
- encryptedNote = await Note.save(deserialized);
- decryptedNote = await Note.decrypt(encryptedNote);
+ const encryptedNote = await Note.save(deserialized);
+ const decryptedNote = await Note.decrypt(encryptedNote);
expect(decryptedNote.title).toBe(note.title);
expect(decryptedNote.body).toBe(note.body);
@@ -176,4 +178,4 @@ describe('Encryption', function() {
done();
});
-});
\ No newline at end of file
+});
diff --git a/CliClient/tests/htmlUtils.js b/CliClient/tests/htmlUtils.js
index 10be8dd62..145b76963 100644
--- a/CliClient/tests/htmlUtils.js
+++ b/CliClient/tests/htmlUtils.js
@@ -1,3 +1,5 @@
+/* eslint-disable no-unused-vars */
+
require('app-module-path').addPath(__dirname);
const { time } = require('lib/time-utils.js');
@@ -46,8 +48,8 @@ describe('htmlUtils', function() {
return function(src) {
i++;
return urls[i];
- }
- }
+ };
+ };
for (let i = 0; i < testCases.length; i++) {
const md = testCases[i][0];
@@ -102,4 +104,4 @@ describe('htmlUtils', function() {
done();
});
-});
\ No newline at end of file
+});
diff --git a/CliClient/tests/markdownUtils.js b/CliClient/tests/markdownUtils.js
index 9203b19ed..ef9c07360 100644
--- a/CliClient/tests/markdownUtils.js
+++ b/CliClient/tests/markdownUtils.js
@@ -1,3 +1,5 @@
+/* eslint-disable no-unused-vars */
+
require('app-module-path').addPath(__dirname);
const { time } = require('lib/time-utils.js');
@@ -52,4 +54,4 @@ describe('markdownUtils', function() {
done();
});
-});
\ No newline at end of file
+});
diff --git a/CliClient/tests/models_BaseItem.js b/CliClient/tests/models_BaseItem.js
index 9c274e0ff..9f0cc84c5 100644
--- a/CliClient/tests/models_BaseItem.js
+++ b/CliClient/tests/models_BaseItem.js
@@ -1,3 +1,5 @@
+/* eslint-disable no-unused-vars */
+
require('app-module-path').addPath(__dirname);
const { time } = require('lib/time-utils.js');
@@ -38,29 +40,29 @@ describe('models_BaseItem', function() {
// This is to handle the case where a property is removed from a BaseItem table - in that case files in
// the sync target will still have the old property but we don't need it locally.
it('should ignore properties that are present in sync file but not in database when serialising', asyncTest(async () => {
- let folder = await Folder.save({ title: "folder1" });
-
+ let folder = await Folder.save({ title: 'folder1' });
+
let serialized = await Folder.serialize(folder);
- serialized += "\nignore_me: true"
+ serialized += '\nignore_me: true';
let unserialized = await Folder.unserialize(serialized);
expect('ignore_me' in unserialized).toBe(false);
}));
-
+
it('should not modify title when unserializing', asyncTest(async () => {
- let folder1 = await Folder.save({ title: "" });
- let folder2 = await Folder.save({ title: "folder1" });
-
- let serialized1 = await Folder.serialize(folder1);
- let unserialized1 = await Folder.unserialize(serialized1);
-
- expect(unserialized1.title).toBe(folder1.title);
-
- let serialized2 = await Folder.serialize(folder2);
- let unserialized2 = await Folder.unserialize(serialized2);
-
- expect(unserialized2.title).toBe(folder2.title);
+ let folder1 = await Folder.save({ title: '' });
+ let folder2 = await Folder.save({ title: 'folder1' });
+
+ let serialized1 = await Folder.serialize(folder1);
+ let unserialized1 = await Folder.unserialize(serialized1);
+
+ expect(unserialized1.title).toBe(folder1.title);
+
+ let serialized2 = await Folder.serialize(folder2);
+ let unserialized2 = await Folder.unserialize(serialized2);
+
+ expect(unserialized2.title).toBe(folder2.title);
}));
-});
\ No newline at end of file
+});
diff --git a/CliClient/tests/models_Folder.js b/CliClient/tests/models_Folder.js
index c43cdee11..846fe6d88 100644
--- a/CliClient/tests/models_Folder.js
+++ b/CliClient/tests/models_Folder.js
@@ -1,3 +1,5 @@
+/* eslint-disable no-unused-vars */
+
require('app-module-path').addPath(__dirname);
const { time } = require('lib/time-utils.js');
@@ -26,10 +28,10 @@ describe('models_Folder', function() {
});
it('should tell if a notebook can be nested under another one', asyncTest(async () => {
- let f1 = await Folder.save({ title: "folder1" });
- let f2 = await Folder.save({ title: "folder2", parent_id: f1.id });
- let f3 = await Folder.save({ title: "folder3", parent_id: f2.id });
- let f4 = await Folder.save({ title: "folder4" });
+ let f1 = await Folder.save({ title: 'folder1' });
+ let f2 = await Folder.save({ title: 'folder2', parent_id: f1.id });
+ let f3 = await Folder.save({ title: 'folder3', parent_id: f2.id });
+ let f4 = await Folder.save({ title: 'folder4' });
expect(await Folder.canNestUnder(f1.id, f2.id)).toBe(false);
expect(await Folder.canNestUnder(f2.id, f2.id)).toBe(false);
@@ -42,8 +44,8 @@ describe('models_Folder', function() {
}));
it('should recursively delete notes and sub-notebooks', asyncTest(async () => {
- let f1 = await Folder.save({ title: "folder1" });
- let f2 = await Folder.save({ title: "folder2", parent_id: f1.id });
+ let f1 = await Folder.save({ title: 'folder1' });
+ let f2 = await Folder.save({ title: 'folder2', parent_id: f1.id });
let n1 = await Note.save({ title: 'note1', parent_id: f2.id });
await Folder.delete(f1.id);
@@ -55,9 +57,9 @@ describe('models_Folder', function() {
it('should sort by last modified, based on content', asyncTest(async () => {
let folders;
- let f1 = await Folder.save({ title: "folder1" }); await sleep(0.1);
- let f2 = await Folder.save({ title: "folder2" }); await sleep(0.1);
- let f3 = await Folder.save({ title: "folder3" }); await sleep(0.1);
+ let f1 = await Folder.save({ title: 'folder1' }); await sleep(0.1);
+ let f2 = await Folder.save({ title: 'folder2' }); await sleep(0.1);
+ let f3 = await Folder.save({ title: 'folder3' }); await sleep(0.1);
let n1 = await Note.save({ title: 'note1', parent_id: f2.id });
folders = await Folder.orderByLastModified(await Folder.all(), 'desc');
@@ -89,9 +91,9 @@ describe('models_Folder', function() {
it('should sort by last modified, based on content (sub-folders too)', asyncTest(async () => {
let folders;
- let f1 = await Folder.save({ title: "folder1" }); await sleep(0.1);
- let f2 = await Folder.save({ title: "folder2" }); await sleep(0.1);
- let f3 = await Folder.save({ title: "folder3", parent_id: f1.id }); await sleep(0.1);
+ let f1 = await Folder.save({ title: 'folder1' }); await sleep(0.1);
+ let f2 = await Folder.save({ title: 'folder2' }); await sleep(0.1);
+ let f3 = await Folder.save({ title: 'folder3', parent_id: f1.id }); await sleep(0.1);
let n1 = await Note.save({ title: 'note1', parent_id: f3.id });
folders = await Folder.orderByLastModified(await Folder.all(), 'desc');
@@ -100,7 +102,7 @@ describe('models_Folder', function() {
expect(folders[1].id).toBe(f3.id);
expect(folders[2].id).toBe(f2.id);
- let n2 = await Note.save({ title: 'note2', parent_id: f2.id });
+ let n2 = await Note.save({ title: 'note2', parent_id: f2.id });
folders = await Folder.orderByLastModified(await Folder.all(), 'desc');
expect(folders[0].id).toBe(f2.id);
@@ -108,13 +110,13 @@ describe('models_Folder', function() {
expect(folders[2].id).toBe(f3.id);
await Note.save({ id: n1.id, title: 'note1 MOD' });
-
+
folders = await Folder.orderByLastModified(await Folder.all(), 'desc');
expect(folders[0].id).toBe(f1.id);
expect(folders[1].id).toBe(f3.id);
expect(folders[2].id).toBe(f2.id);
- let f4 = await Folder.save({ title: "folder4", parent_id: f1.id }); await sleep(0.1);
+ let f4 = await Folder.save({ title: 'folder4', parent_id: f1.id }); await sleep(0.1);
let n3 = await Note.save({ title: 'note3', parent_id: f4.id });
folders = await Folder.orderByLastModified(await Folder.all(), 'desc');
@@ -125,4 +127,4 @@ describe('models_Folder', function() {
expect(folders[3].id).toBe(f2.id);
}));
-});
\ No newline at end of file
+});
diff --git a/CliClient/tests/models_ItemChange.js b/CliClient/tests/models_ItemChange.js
index fbcf1b72a..760097209 100644
--- a/CliClient/tests/models_ItemChange.js
+++ b/CliClient/tests/models_ItemChange.js
@@ -1,3 +1,5 @@
+/* eslint-disable no-unused-vars */
+
require('app-module-path').addPath(__dirname);
const { time } = require('lib/time-utils.js');
@@ -25,7 +27,7 @@ describe('models_ItemChange', function() {
});
it('should delete old changes that have been processed', asyncTest(async () => {
- const n1 = await Note.save({ title: "abcd efgh" }); // 3
+ const n1 = await Note.save({ title: 'abcd efgh' }); // 3
await ItemChange.waitForAllSaved();
@@ -48,4 +50,4 @@ describe('models_ItemChange', function() {
expect(await ItemChange.lastChangeId()).toBe(0);
}));
-});
\ No newline at end of file
+});
diff --git a/CliClient/tests/models_Note.js b/CliClient/tests/models_Note.js
index 876b337b3..247a55d5d 100644
--- a/CliClient/tests/models_Note.js
+++ b/CliClient/tests/models_Note.js
@@ -1,3 +1,5 @@
+/* eslint-disable no-unused-vars */
+
require('app-module-path').addPath(__dirname);
const { time } = require('lib/time-utils.js');
@@ -21,7 +23,7 @@ describe('models_Note', function() {
});
it('should find resource and note IDs', asyncTest(async () => {
- let folder1 = await Folder.save({ title: "folder1" });
+ let folder1 = await Folder.save({ title: 'folder1' });
let note1 = await Note.save({ title: 'ma note', parent_id: folder1.id });
let note2 = await Note.save({ title: 'ma deuxième note', body: 'Lien vers première note : ' + Note.markdownTag(note1), parent_id: folder1.id });
@@ -67,7 +69,7 @@ describe('models_Note', function() {
}));
it('should change the type of notes', asyncTest(async () => {
- let folder1 = await Folder.save({ title: "folder1" });
+ let folder1 = await Folder.save({ title: 'folder1' });
let note1 = await Note.save({ title: 'ma note', parent_id: folder1.id });
note1 = await Note.load(note1.id);
@@ -86,9 +88,9 @@ describe('models_Note', function() {
expect(changedNote === note1).toBe(false);
expect(!!changedNote.is_todo).toBe(false);
}));
-
+
it('should serialize and unserialize without modifying data', asyncTest(async () => {
- let folder1 = await Folder.save({ title: "folder1"});
+ let folder1 = await Folder.save({ title: 'folder1'});
const testCases = [
[ {title: '', body:'Body and no title\nSecond line\nThird Line', parent_id: folder1.id},
'', 'Body and no title\nSecond line\nThird Line'],
@@ -96,22 +98,22 @@ describe('models_Note', function() {
'Note title', 'Body and title'],
[ {title: 'Title and no body', body:'', parent_id: folder1.id},
'Title and no body', ''],
- ]
-
+ ];
+
for (let i = 0; i < testCases.length; i++) {
const t = testCases[i];
-
+
const input = t[0];
const expectedTitle = t[1];
const expectedBody = t[1];
-
+
let note1 = await Note.save(input);
let serialized = await Note.serialize(note1);
- let unserialized = await Note.unserialize( serialized);
-
+ let unserialized = await Note.unserialize(serialized);
+
expect(unserialized.title).toBe(input.title);
expect(unserialized.body).toBe(input.body);
}
}));
-});
\ No newline at end of file
+});
diff --git a/CliClient/tests/models_Resource.js b/CliClient/tests/models_Resource.js
index 64ae22305..a344eb130 100644
--- a/CliClient/tests/models_Resource.js
+++ b/CliClient/tests/models_Resource.js
@@ -1,3 +1,5 @@
+/* eslint-disable no-unused-vars, require-atomic-updates */
+
require('app-module-path').addPath(__dirname);
const { time } = require('lib/time-utils.js');
@@ -25,7 +27,7 @@ describe('models_Resource', function() {
});
it('should have a "done" fetch_status when created locally', asyncTest(async () => {
- let folder1 = await Folder.save({ title: "folder1" });
+ let folder1 = await Folder.save({ title: 'folder1' });
let note1 = await Note.save({ title: 'ma note', parent_id: folder1.id });
await shim.attachFileToNote(note1, testImagePath);
let resource1 = (await Resource.all())[0];
@@ -34,7 +36,7 @@ describe('models_Resource', function() {
}));
it('should have a default local state', asyncTest(async () => {
- let folder1 = await Folder.save({ title: "folder1" });
+ let folder1 = await Folder.save({ title: 'folder1' });
let note1 = await Note.save({ title: 'ma note', parent_id: folder1.id });
await shim.attachFileToNote(note1, testImagePath);
let resource1 = (await Resource.all())[0];
@@ -45,7 +47,7 @@ describe('models_Resource', function() {
}));
it('should save and delete local state', asyncTest(async () => {
- let folder1 = await Folder.save({ title: "folder1" });
+ let folder1 = await Folder.save({ title: 'folder1' });
let note1 = await Note.save({ title: 'ma note', parent_id: folder1.id });
await shim.attachFileToNote(note1, testImagePath);
let resource1 = (await Resource.all())[0];
@@ -61,7 +63,7 @@ describe('models_Resource', function() {
}));
it('should resize the resource if the image is below the required dimensions', asyncTest(async () => {
- let folder1 = await Folder.save({ title: "folder1" });
+ let folder1 = await Folder.save({ title: 'folder1' });
let note1 = await Note.save({ title: 'ma note', parent_id: folder1.id });
const previousMax = Resource.IMAGE_MAX_DIMENSION;
Resource.IMAGE_MAX_DIMENSION = 5;
@@ -76,7 +78,7 @@ describe('models_Resource', function() {
}));
it('should not resize the resource if the image is below the required dimensions', asyncTest(async () => {
- let folder1 = await Folder.save({ title: "folder1" });
+ let folder1 = await Folder.save({ title: 'folder1' });
let note1 = await Note.save({ title: 'ma note', parent_id: folder1.id });
await shim.attachFileToNote(note1, testImagePath);
let resource1 = (await Resource.all())[0];
@@ -87,4 +89,4 @@ describe('models_Resource', function() {
expect(originalStat.size).toBe(newStat.size);
}));
-});
\ No newline at end of file
+});
diff --git a/CliClient/tests/models_Revision.js b/CliClient/tests/models_Revision.js
index 9a45ef95c..7bb293765 100644
--- a/CliClient/tests/models_Revision.js
+++ b/CliClient/tests/models_Revision.js
@@ -1,3 +1,5 @@
+/* eslint-disable no-unused-vars */
+
require('app-module-path').addPath(__dirname);
const { time } = require('lib/time-utils.js');
@@ -41,7 +43,7 @@ describe('models_Revision', function() {
const newObject = {
one: '123',
three: '999',
- }
+ };
const patch = Revision.createObjectPatch(oldObject, newObject);
const merged = Revision.applyObjectPatch(oldObject, patch);
@@ -82,16 +84,16 @@ describe('models_Revision', function() {
-
+x
%5D Check `,
- expected: [-1, +1],
- },
- {
- patch: `@@ -1022,56 +1022,415 @@
+ expected: [-1, +1],
+ },
+ {
+ patch: `@@ -1022,56 +1022,415 @@
.%0A%0A#
- How to view a note history%0A%0AWhile all the apps
+%C2%A0How does it work?%0A%0AAll the apps save a version of the modified notes every 10 minutes.
%0A%0A# `,
- expected: [-(19+27+2), 17+67+4],
- },
+ expected: [-(19+27+2), 17+67+4],
+ },
];
for (const test of tests) {
@@ -101,4 +103,4 @@ describe('models_Revision', function() {
}
}));
-});
\ No newline at end of file
+});
diff --git a/CliClient/tests/models_Setting.js b/CliClient/tests/models_Setting.js
index 53cce0439..a1a7de0c2 100644
--- a/CliClient/tests/models_Setting.js
+++ b/CliClient/tests/models_Setting.js
@@ -1,3 +1,5 @@
+/* eslint-disable no-unused-vars */
+
require('app-module-path').addPath(__dirname);
const { time } = require('lib/time-utils.js');
@@ -18,7 +20,7 @@ describe('models_Setting', function() {
const settings = {
'sync.5.path': 'http://example.com',
'sync.5.username': 'testing',
- }
+ };
let output = Setting.subValues('sync.5', settings);
expect(output['path']).toBe('http://example.com');
@@ -29,4 +31,4 @@ describe('models_Setting', function() {
expect('username' in output).toBe(false);
}));
-});
\ No newline at end of file
+});
diff --git a/CliClient/tests/models_Tag.js b/CliClient/tests/models_Tag.js
index cf136e631..a959d1674 100644
--- a/CliClient/tests/models_Tag.js
+++ b/CliClient/tests/models_Tag.js
@@ -1,3 +1,5 @@
+/* eslint-disable no-unused-vars */
+
require('app-module-path').addPath(__dirname);
const { time } = require('lib/time-utils.js');
@@ -22,7 +24,7 @@ describe('models_Tag', function() {
});
it('should add tags by title', asyncTest(async () => {
- let folder1 = await Folder.save({ title: "folder1" });
+ let folder1 = await Folder.save({ title: 'folder1' });
let note1 = await Note.save({ title: 'ma note', parent_id: folder1.id });
await Tag.setNoteTagsByTitles(note1.id, ['un', 'deux']);
@@ -32,7 +34,7 @@ describe('models_Tag', function() {
}));
it('should not allow renaming tag to existing tag names', asyncTest(async () => {
- let folder1 = await Folder.save({ title: "folder1" });
+ let folder1 = await Folder.save({ title: 'folder1' });
let note1 = await Note.save({ title: 'ma note', parent_id: folder1.id });
await Tag.setNoteTagsByTitles(note1.id, ['un', 'deux']);
@@ -44,7 +46,7 @@ describe('models_Tag', function() {
}));
it('should not return tags without notes', asyncTest(async () => {
- let folder1 = await Folder.save({ title: "folder1" });
+ let folder1 = await Folder.save({ title: 'folder1' });
let note1 = await Note.save({ title: 'ma note', parent_id: folder1.id });
await Tag.setNoteTagsByTitles(note1.id, ['un']);
@@ -57,4 +59,4 @@ describe('models_Tag', function() {
expect(tags.length).toBe(0);
}));
-});
\ No newline at end of file
+});
diff --git a/CliClient/tests/pathUtils.js b/CliClient/tests/pathUtils.js
index dba746026..fce59209a 100644
--- a/CliClient/tests/pathUtils.js
+++ b/CliClient/tests/pathUtils.js
@@ -1,3 +1,5 @@
+/* eslint-disable no-unused-vars */
+
require('app-module-path').addPath(__dirname);
const { extractExecutablePath, quotePath, unquotePath, friendlySafeFilename, toFileProtocolPath} = require('lib/path-utils.js');
@@ -50,7 +52,7 @@ describe('pathUtils', function() {
const t = testCases[i];
expect(quotePath(t[0])).toBe(t[1]);
expect(unquotePath(quotePath(t[0]))).toBe(t[0]);
- }
+ }
done();
});
@@ -68,7 +70,7 @@ describe('pathUtils', function() {
for (let i = 0; i < testCases.length; i++) {
const t = testCases[i];
expect(extractExecutablePath(t[0])).toBe(t[1]);
- }
+ }
done();
});
@@ -77,7 +79,7 @@ describe('pathUtils', function() {
const testCases_win32 = [
['C:\\handle\\space test', 'file:///C:/handle/space+test'],
['C:\\escapeplus\\+', 'file:///C:/escapeplus/%2B'],
- ['C:\\handle\\single quote\'', 'file:///C:/handle/single+quote%27'],
+ ['C:\\handle\\single quote\'', 'file:///C:/handle/single+quote%27'],
];
const testCases_unixlike = [
['/handle/space test', 'file:///handle/space+test'],
@@ -88,13 +90,13 @@ describe('pathUtils', function() {
for (let i = 0; i < testCases_win32.length; i++) {
const t = testCases_win32[i];
expect(toFileProtocolPath(t[0], 'win32')).toBe(t[1]);
- }
+ }
for (let i = 0; i < testCases_unixlike.length; i++) {
const t = testCases_unixlike[i];
expect(toFileProtocolPath(t[0], 'linux')).toBe(t[1]);
- }
+ }
done();
});
-});
\ No newline at end of file
+});
diff --git a/CliClient/tests/services_InteropService.js b/CliClient/tests/services_InteropService.js
index bb9bd88f1..3a7bd0532 100644
--- a/CliClient/tests/services_InteropService.js
+++ b/CliClient/tests/services_InteropService.js
@@ -1,3 +1,5 @@
+/* eslint-disable no-unused-vars */
+
require('app-module-path').addPath(__dirname);
const { time } = require('lib/time-utils.js');
@@ -44,7 +46,7 @@ describe('services_InteropService', function() {
it('should export and import folders', asyncTest(async () => {
const service = new InteropService();
- let folder1 = await Folder.save({ title: "folder1" });
+ let folder1 = await Folder.save({ title: 'folder1' });
folder1 = await Folder.load(folder1.id);
const filePath = exportDir() + '/test.jex';
@@ -79,7 +81,7 @@ describe('services_InteropService', function() {
it('should export and import folders and notes', asyncTest(async () => {
const service = new InteropService();
- let folder1 = await Folder.save({ title: "folder1" });
+ let folder1 = await Folder.save({ title: 'folder1' });
let note1 = await Note.save({ title: 'ma note', parent_id: folder1.id });
note1 = await Note.load(note1.id);
const filePath = exportDir() + '/test.jex';
@@ -118,7 +120,7 @@ describe('services_InteropService', function() {
it('should export and import notes to specific folder', asyncTest(async () => {
const service = new InteropService();
- let folder1 = await Folder.save({ title: "folder1" });
+ let folder1 = await Folder.save({ title: 'folder1' });
let note1 = await Note.save({ title: 'ma note', parent_id: folder1.id });
note1 = await Note.load(note1.id);
const filePath = exportDir() + '/test.jex';
@@ -138,7 +140,7 @@ describe('services_InteropService', function() {
it('should export and import tags', asyncTest(async () => {
const service = new InteropService();
const filePath = exportDir() + '/test.jex';
- let folder1 = await Folder.save({ title: "folder1" });
+ let folder1 = await Folder.save({ title: 'folder1' });
let note1 = await Note.save({ title: 'ma note', parent_id: folder1.id });
let tag1 = await Tag.save({ title: 'mon tag' });
tag1 = await Tag.load(tag1.id);
@@ -178,7 +180,7 @@ describe('services_InteropService', function() {
it('should export and import resources', asyncTest(async () => {
const service = new InteropService();
const filePath = exportDir() + '/test.jex';
- let folder1 = await Folder.save({ title: "folder1" });
+ let folder1 = await Folder.save({ title: 'folder1' });
let note1 = await Note.save({ title: 'ma note', parent_id: folder1.id });
await shim.attachFileToNote(note1, __dirname + '/../tests/support/photo.jpg');
note1 = await Note.load(note1.id);
@@ -186,7 +188,7 @@ describe('services_InteropService', function() {
let resource1 = await Resource.load(resourceIds[0]);
await service.export({ path: filePath });
-
+
await Note.delete(note1.id);
await service.import({ path: filePath });
@@ -214,11 +216,11 @@ describe('services_InteropService', function() {
it('should export and import single notes', asyncTest(async () => {
const service = new InteropService();
const filePath = exportDir() + '/test.jex';
- let folder1 = await Folder.save({ title: "folder1" });
+ let folder1 = await Folder.save({ title: 'folder1' });
let note1 = await Note.save({ title: 'ma note', parent_id: folder1.id });
await service.export({ path: filePath, sourceNoteIds: [note1.id] });
-
+
await Note.delete(note1.id);
await Folder.delete(folder1.id);
@@ -234,11 +236,11 @@ describe('services_InteropService', function() {
it('should export and import single folders', asyncTest(async () => {
const service = new InteropService();
const filePath = exportDir() + '/test.jex';
- let folder1 = await Folder.save({ title: "folder1" });
+ let folder1 = await Folder.save({ title: 'folder1' });
let note1 = await Note.save({ title: 'ma note', parent_id: folder1.id });
await service.export({ path: filePath, sourceFolderIds: [folder1.id] });
-
+
await Note.delete(note1.id);
await Folder.delete(folder1.id);
@@ -252,17 +254,17 @@ describe('services_InteropService', function() {
}));
it('should export and import folder and its sub-folders', asyncTest(async () => {
-
+
const service = new InteropService();
const filePath = exportDir() + '/test.jex';
- let folder1 = await Folder.save({ title: "folder1" });
- let folder2 = await Folder.save({ title: "folder2", parent_id: folder1.id });
- let folder3 = await Folder.save({ title: "folder3", parent_id: folder2.id });
- let folder4 = await Folder.save({ title: "folder4", parent_id: folder2.id });
+ let folder1 = await Folder.save({ title: 'folder1' });
+ let folder2 = await Folder.save({ title: 'folder2', parent_id: folder1.id });
+ let folder3 = await Folder.save({ title: 'folder3', parent_id: folder2.id });
+ let folder4 = await Folder.save({ title: 'folder4', parent_id: folder2.id });
let note1 = await Note.save({ title: 'ma note', parent_id: folder4.id });
await service.export({ path: filePath, sourceFolderIds: [folder1.id] });
-
+
await Note.delete(note1.id);
await Folder.delete(folder1.id);
await Folder.delete(folder2.id);
@@ -273,7 +275,7 @@ describe('services_InteropService', function() {
expect(await Note.count()).toBe(1);
expect(await Folder.count()).toBe(4);
-
+
let folder1_2 = await Folder.loadByTitle('folder1');
let folder2_2 = await Folder.loadByTitle('folder2');
let folder3_2 = await Folder.loadByTitle('folder3');
@@ -289,12 +291,12 @@ describe('services_InteropService', function() {
it('should export and import links to notes', asyncTest(async () => {
const service = new InteropService();
const filePath = exportDir() + '/test.jex';
- let folder1 = await Folder.save({ title: "folder1" });
+ let folder1 = await Folder.save({ title: 'folder1' });
let note1 = await Note.save({ title: 'ma note', parent_id: folder1.id });
let note2 = await Note.save({ title: 'ma deuxième note', body: 'Lien vers première note : ' + Note.markdownTag(note1), parent_id: folder1.id });
await service.export({ path: filePath, sourceFolderIds: [folder1.id] });
-
+
await Note.delete(note1.id);
await Note.delete(note2.id);
await Folder.delete(folder1.id);
@@ -322,7 +324,7 @@ describe('services_InteropService', function() {
// verify that the json files exist and can be parsed
const items = [folder1, note1];
for (let i = 0; i < items.length; i++) {
- const jsonFile = filePath + '/' + items[i].id + '.json';
+ const jsonFile = filePath + '/' + items[i].id + '.json';
let json = await fs.readFile(jsonFile, 'utf-8');
let obj = JSON.parse(json);
expect(obj.id).toBe(items[i].id);
@@ -357,4 +359,4 @@ describe('services_InteropService', function() {
expect(await shim.fsDriver().exists(outDir + '/ジョプリン/ジョプリン.md')).toBe(true);
}));
-});
\ No newline at end of file
+});
diff --git a/CliClient/tests/services_KvStore.js b/CliClient/tests/services_KvStore.js
index 617ce9797..5c1e461f3 100644
--- a/CliClient/tests/services_KvStore.js
+++ b/CliClient/tests/services_KvStore.js
@@ -1,3 +1,5 @@
+/* eslint-disable no-unused-vars */
+
require('app-module-path').addPath(__dirname);
const { asyncTest, fileContentEqual, setupDatabase, revisionService, setupDatabaseAndSynchronizer, db, synchronizer, fileApi, sleep, clearDatabase, switchClient, syncTargetId, objectsEqual, checkThrowAsync } = require('test-utils.js');
@@ -104,4 +106,4 @@ describe('services_KvStore', function() {
expect(numbers[1]).toBe(2);
}));
-});
\ No newline at end of file
+});
diff --git a/CliClient/tests/services_ResourceService.js b/CliClient/tests/services_ResourceService.js
index a486e733d..688f17e76 100644
--- a/CliClient/tests/services_ResourceService.js
+++ b/CliClient/tests/services_ResourceService.js
@@ -1,3 +1,5 @@
+/* eslint-disable no-unused-vars */
+
require('app-module-path').addPath(__dirname);
const { time } = require('lib/time-utils.js');
@@ -46,7 +48,7 @@ describe('services_ResourceService', function() {
it('should delete orphaned resources', asyncTest(async () => {
const service = new ResourceService();
- let folder1 = await Folder.save({ title: "folder1" });
+ let folder1 = await Folder.save({ title: 'folder1' });
let note1 = await Note.save({ title: 'ma note', parent_id: folder1.id });
note1 = await shim.attachFileToNote(note1, __dirname + '/../tests/support/photo.jpg');
let resource1 = (await Resource.all())[0];
@@ -77,7 +79,7 @@ describe('services_ResourceService', function() {
it('should not delete resource if still associated with at least one note', asyncTest(async () => {
const service = new ResourceService();
- let folder1 = await Folder.save({ title: "folder1" });
+ let folder1 = await Folder.save({ title: 'folder1' });
let note1 = await Note.save({ title: 'ma note', parent_id: folder1.id });
let note2 = await Note.save({ title: 'ma deuxième note', parent_id: folder1.id });
note1 = await shim.attachFileToNote(note1, __dirname + '/../tests/support/photo.jpg');
@@ -86,9 +88,9 @@ describe('services_ResourceService', function() {
await service.indexNoteResources();
await Note.delete(note1.id);
-
+
await service.indexNoteResources();
-
+
await Note.save({ id: note2.id, body: Resource.markdownTag(resource1) });
await service.indexNoteResources();
@@ -111,7 +113,7 @@ describe('services_ResourceService', function() {
it('should not delete resource if it is used in an IMG tag', asyncTest(async () => {
const service = new ResourceService();
- let folder1 = await Folder.save({ title: "folder1" });
+ let folder1 = await Folder.save({ title: 'folder1' });
let note1 = await Note.save({ title: 'ma note', parent_id: folder1.id });
note1 = await shim.attachFileToNote(note1, __dirname + '/../tests/support/photo.jpg');
let resource1 = (await Resource.all())[0];
@@ -119,9 +121,9 @@ describe('services_ResourceService', function() {
await service.indexNoteResources();
await Note.save({ id: note1.id, body: 'This is HTML: nodes which have
node(s) and append them into the `nodes` variable. - // Some articles' DOM structures might look like - //
node(s) and append them into the `nodes` variable. - // Some articles' DOM structures might look like - //
- // Sentences
- //
- // Sentences
- //
- var brNodes = doc.querySelectorAll("div > br");
- if (brNodes.length) {
- var set = new Set(nodes);
- [].forEach.call(brNodes, function(node) {
- set.add(node.parentNode);
- });
- nodes = Array.from(set);
- }
+ // Get - //
- // Sentences
- //
nodes which have
node(s) and append them into the `nodes` variable. + // Some articles' DOM structures might look like + //![]()
uri in the given element to an absolute URI,
* ignoring #ref URIs.
*
* @param Element
* @return void
*/
- _fixRelativeUris: function(articleContent) {
- var baseURI = this._doc.baseURI;
- var documentURI = this._doc.documentURI;
- function toAbsoluteURI(uri) {
- // Leave hash links alone if the base URI matches the document URI:
- if (baseURI == documentURI && uri.charAt(0) == "#") {
- return uri;
- }
- // Otherwise, resolve against base URI:
- try {
- return new URL(uri, baseURI).href;
- } catch (ex) {
- // Something went wrong, just return the original:
- }
- return uri;
- }
+ _fixRelativeUris: function(articleContent) {
+ var baseURI = this._doc.baseURI;
+ var documentURI = this._doc.documentURI;
+ function toAbsoluteURI(uri) {
+ // Leave hash links alone if the base URI matches the document URI:
+ if (baseURI == documentURI && uri.charAt(0) == '#') {
+ return uri;
+ }
+ // Otherwise, resolve against base URI:
+ try {
+ return new URL(uri, baseURI).href;
+ } catch (ex) {
+ // Something went wrong, just return the original:
+ }
+ return uri;
+ }
- var links = this._getAllNodesWithTag(articleContent, ["a"]);
- this._forEachNode(links, function(link) {
- var href = link.getAttribute("href");
- if (href) {
- // Replace links with javascript: URIs with text content, since
- // they won't work after scripts have been removed from the page.
- if (href.indexOf("javascript:") === 0) {
- var text = this._doc.createTextNode(link.textContent);
- link.parentNode.replaceChild(text, link);
- } else {
- link.setAttribute("href", toAbsoluteURI(href));
- }
- }
- });
+ var links = this._getAllNodesWithTag(articleContent, ['a']);
+ this._forEachNode(links, function(link) {
+ var href = link.getAttribute('href');
+ if (href) {
+ // Replace links with javascript: URIs with text content, since
+ // they won't work after scripts have been removed from the page.
+ if (href.indexOf('javascript:') === 0) {
+ var text = this._doc.createTextNode(link.textContent);
+ link.parentNode.replaceChild(text, link);
+ } else {
+ link.setAttribute('href', toAbsoluteURI(href));
+ }
+ }
+ });
- var imgs = this._getAllNodesWithTag(articleContent, ["img"]);
- this._forEachNode(imgs, function(img) {
- var src = img.getAttribute("src");
- if (src) {
- img.setAttribute("src", toAbsoluteURI(src));
- }
- });
- },
+ var imgs = this._getAllNodesWithTag(articleContent, ['img']);
+ this._forEachNode(imgs, function(img) {
+ var src = img.getAttribute('src');
+ if (src) {
+ img.setAttribute('src', toAbsoluteURI(src));
+ }
+ });
+ },
- /**
+ /**
* Get the article title as an H1.
*
* @return void
**/
- _getArticleTitle: function() {
- var doc = this._doc;
- var curTitle = "";
- var origTitle = "";
+ _getArticleTitle: function() {
+ var doc = this._doc;
+ var curTitle = '';
+ var origTitle = '';
- try {
- curTitle = origTitle = doc.title.trim();
+ try {
+ curTitle = origTitle = doc.title.trim();
- // If they had an element with id "title" in their HTML
- if (typeof curTitle !== "string")
- curTitle = origTitle = this._getInnerText(doc.getElementsByTagName("title")[0]);
- } catch (e) {/* ignore exceptions setting the title. */}
+ // If they had an element with id "title" in their HTML
+ if (typeof curTitle !== 'string')
+ curTitle = origTitle = this._getInnerText(doc.getElementsByTagName('title')[0]);
+ } catch (e) {/* ignore exceptions setting the title. */}
- var titleHadHierarchicalSeparators = false;
- function wordCount(str) {
- return str.split(/\s+/).length;
- }
+ var titleHadHierarchicalSeparators = false;
+ function wordCount(str) {
+ return str.split(/\s+/).length;
+ }
- // If there's a separator in the title, first remove the final part
- if ((/ [\|\-\\\/>»] /).test(curTitle)) {
- titleHadHierarchicalSeparators = / [\\\/>»] /.test(curTitle);
- curTitle = origTitle.replace(/(.*)[\|\-\\\/>»] .*/gi, "$1");
+ // If there's a separator in the title, first remove the final part
+ if ((/ [\|\-\\\/>»] /).test(curTitle)) {
+ titleHadHierarchicalSeparators = / [\\\/>»] /.test(curTitle);
+ curTitle = origTitle.replace(/(.*)[\|\-\\\/>»] .*/gi, '$1');
- // If the resulting title is too short (3 words or fewer), remove
- // the first part instead:
- if (wordCount(curTitle) < 3)
- curTitle = origTitle.replace(/[^\|\-\\\/>»]*[\|\-\\\/>»](.*)/gi, "$1");
- } else if (curTitle.indexOf(": ") !== -1) {
- // Check if we have an heading containing this exact string, so we
- // could assume it's the full title.
- var headings = this._concatNodeLists(
- doc.getElementsByTagName("h1"),
- doc.getElementsByTagName("h2")
- );
- var trimmedTitle = curTitle.trim();
- var match = this._someNode(headings, function(heading) {
- return heading.textContent.trim() === trimmedTitle;
- });
+ // If the resulting title is too short (3 words or fewer), remove
+ // the first part instead:
+ if (wordCount(curTitle) < 3)
+ curTitle = origTitle.replace(/[^\|\-\\\/>»]*[\|\-\\\/>»](.*)/gi, '$1');
+ } else if (curTitle.indexOf(': ') !== -1) {
+ // Check if we have an heading containing this exact string, so we
+ // could assume it's the full title.
+ var headings = this._concatNodeLists(
+ doc.getElementsByTagName('h1'),
+ doc.getElementsByTagName('h2')
+ );
+ var trimmedTitle = curTitle.trim();
+ var match = this._someNode(headings, function(heading) {
+ return heading.textContent.trim() === trimmedTitle;
+ });
- // If we don't, let's extract the title out of the original title string.
- if (!match) {
- curTitle = origTitle.substring(origTitle.lastIndexOf(":") + 1);
+ // If we don't, let's extract the title out of the original title string.
+ if (!match) {
+ curTitle = origTitle.substring(origTitle.lastIndexOf(':') + 1);
- // If the title is now too short, try the first colon instead:
- if (wordCount(curTitle) < 3) {
- curTitle = origTitle.substring(origTitle.indexOf(":") + 1);
- // But if we have too many words before the colon there's something weird
- // with the titles and the H tags so let's just use the original title instead
- } else if (wordCount(origTitle.substr(0, origTitle.indexOf(":"))) > 5) {
- curTitle = origTitle;
- }
- }
- } else if (curTitle.length > 150 || curTitle.length < 15) {
- var hOnes = doc.getElementsByTagName("h1");
+ // If the title is now too short, try the first colon instead:
+ if (wordCount(curTitle) < 3) {
+ curTitle = origTitle.substring(origTitle.indexOf(':') + 1);
+ // But if we have too many words before the colon there's something weird
+ // with the titles and the H tags so let's just use the original title instead
+ } else if (wordCount(origTitle.substr(0, origTitle.indexOf(':'))) > 5) {
+ curTitle = origTitle;
+ }
+ }
+ } else if (curTitle.length > 150 || curTitle.length < 15) {
+ var hOnes = doc.getElementsByTagName('h1');
- if (hOnes.length === 1)
- curTitle = this._getInnerText(hOnes[0]);
- }
+ if (hOnes.length === 1)
+ curTitle = this._getInnerText(hOnes[0]);
+ }
- curTitle = curTitle.trim().replace(this.REGEXPS.normalize, " ");
- // If we now have 4 words or fewer as our title, and either no
- // 'hierarchical' separators (\, /, > or ») were found in the original
- // title or we decreased the number of words by more than 1 word, use
- // the original title.
- var curTitleWordCount = wordCount(curTitle);
- if (curTitleWordCount <= 4 &&
+ curTitle = curTitle.trim().replace(this.REGEXPS.normalize, ' ');
+ // If we now have 4 words or fewer as our title, and either no
+ // 'hierarchical' separators (\, /, > or ») were found in the original
+ // title or we decreased the number of words by more than 1 word, use
+ // the original title.
+ var curTitleWordCount = wordCount(curTitle);
+ if (curTitleWordCount <= 4 &&
(!titleHadHierarchicalSeparators ||
- curTitleWordCount != wordCount(origTitle.replace(/[\|\-\\\/>»]+/g, "")) - 1)) {
- curTitle = origTitle;
- }
+ curTitleWordCount != wordCount(origTitle.replace(/[\|\-\\\/>»]+/g, '')) - 1)) {
+ curTitle = origTitle;
+ }
- return curTitle;
- },
+ return curTitle;
+ },
- /**
+ /**
* Prepare the HTML document for readability to scrape it.
* This includes things like stripping javascript, CSS, and handling terrible markup.
*
* @return void
**/
- _prepDocument: function() {
- var doc = this._doc;
+ _prepDocument: function() {
+ var doc = this._doc;
- // Remove all style tags in head
- this._removeNodes(doc.getElementsByTagName("style"));
+ // Remove all style tags in head
+ this._removeNodes(doc.getElementsByTagName('style'));
- if (doc.body) {
- this._replaceBrs(doc.body);
- }
+ if (doc.body) {
+ this._replaceBrs(doc.body);
+ }
- this._replaceNodeTags(doc.getElementsByTagName("font"), "SPAN");
- },
+ this._replaceNodeTags(doc.getElementsByTagName('font'), 'SPAN');
+ },
- /**
+ /**
* Finds the next element, starting from the given node, and ignoring
* whitespace in between. If the given node is an element, the same node is
* returned.
*/
- _nextElement: function (node) {
- var next = node;
- while (next
+ _nextElement: function (node) {
+ var next = node;
+ while (next
&& (next.nodeType != this.ELEMENT_NODE)
&& this.REGEXPS.whitespace.test(next.textContent)) {
- next = next.nextSibling;
- }
- return next;
- },
+ next = next.nextSibling;
+ }
+ return next;
+ },
- /**
+ /**
* Replaces 2 or more successive
elements with a single
elements have been found and replaced with a - //
node(s) and append them into the `nodes` variable. + // Some articles' DOM structures might look like + //
+ // Sentences
+ //
+ // Sentences
+ //
+ var brNodes = doc.querySelectorAll('div > br');
+ if (brNodes.length) {
+ var set = new Set(nodes);
+ [].forEach.call(brNodes, function(node) {
+ set.add(node.parentNode);
+ });
+ nodes = Array.from(set);
+ }
- var score = 0;
- // This is a little cheeky, we use the accumulator 'score' to decide what to return from
- // this callback:
- return [].some.call(nodes, function(node) {
- if (!isVisible(node))
- return false;
+ var score = 0;
+ // This is a little cheeky, we use the accumulator 'score' to decide what to return from
+ // this callback:
+ return [].some.call(nodes, function(node) {
+ if (!isVisible(node))
+ return false;
- var matchString = node.className + " " + node.id;
- if (REGEXPS.unlikelyCandidates.test(matchString) &&
+ var matchString = node.className + ' ' + node.id;
+ if (REGEXPS.unlikelyCandidates.test(matchString) &&
!REGEXPS.okMaybeItsACandidate.test(matchString)) {
- return false;
- }
+ return false;
+ }
- if (node.matches("li p")) {
- return false;
- }
+ if (node.matches('li p')) {
+ return false;
+ }
- var textContentLength = node.textContent.trim().length;
- if (textContentLength < 140) {
- return false;
- }
+ var textContentLength = node.textContent.trim().length;
+ if (textContentLength < 140) {
+ return false;
+ }
- score += Math.sqrt(textContentLength - 140);
+ score += Math.sqrt(textContentLength - 140);
- if (score > 20) {
- return true;
- }
- return false;
- });
+ if (score > 20) {
+ return true;
+ }
+ return false;
+ });
}
-if (typeof exports === "object") {
- exports.isProbablyReaderable = isProbablyReaderable;
+if (typeof exports === 'object') {
+ exports.isProbablyReaderable = isProbablyReaderable;
}
diff --git a/Clipper/joplin-webclipper/content_scripts/Readability.js b/Clipper/joplin-webclipper/content_scripts/Readability.js
index f3eef238b..db5ab6ce0 100644
--- a/Clipper/joplin-webclipper/content_scripts/Readability.js
+++ b/Clipper/joplin-webclipper/content_scripts/Readability.js
@@ -28,147 +28,147 @@
* @param {Object} options The options object.
*/
function Readability(doc, options) {
- // In some older versions, people passed a URI as the first argument. Cope:
- if (options && options.documentElement) {
- doc = options;
- options = arguments[2];
- } else if (!doc || !doc.documentElement) {
- throw new Error("First argument to Readability constructor should be a document object.");
- }
- options = options || {};
+ // In some older versions, people passed a URI as the first argument. Cope:
+ if (options && options.documentElement) {
+ doc = options;
+ options = arguments[2];
+ } else if (!doc || !doc.documentElement) {
+ throw new Error('First argument to Readability constructor should be a document object.');
+ }
+ options = options || {};
- this._doc = doc;
- this._articleTitle = null;
- this._articleByline = null;
- this._articleDir = null;
- this._articleSiteName = null;
- this._attempts = [];
+ this._doc = doc;
+ this._articleTitle = null;
+ this._articleByline = null;
+ this._articleDir = null;
+ this._articleSiteName = null;
+ this._attempts = [];
- // Configurable options
- this._debug = !!options.debug;
- this._maxElemsToParse = options.maxElemsToParse || this.DEFAULT_MAX_ELEMS_TO_PARSE;
- this._nbTopCandidates = options.nbTopCandidates || this.DEFAULT_N_TOP_CANDIDATES;
- this._charThreshold = options.charThreshold || this.DEFAULT_CHAR_THRESHOLD;
- this._classesToPreserve = this.CLASSES_TO_PRESERVE.concat(options.classesToPreserve || []);
+ // Configurable options
+ this._debug = !!options.debug;
+ this._maxElemsToParse = options.maxElemsToParse || this.DEFAULT_MAX_ELEMS_TO_PARSE;
+ this._nbTopCandidates = options.nbTopCandidates || this.DEFAULT_N_TOP_CANDIDATES;
+ this._charThreshold = options.charThreshold || this.DEFAULT_CHAR_THRESHOLD;
+ this._classesToPreserve = this.CLASSES_TO_PRESERVE.concat(options.classesToPreserve || []);
- // Start with all flags set
- this._flags = this.FLAG_STRIP_UNLIKELYS |
+ // Start with all flags set
+ this._flags = this.FLAG_STRIP_UNLIKELYS |
this.FLAG_WEIGHT_CLASSES |
this.FLAG_CLEAN_CONDITIONALLY;
- var logEl;
+ var logEl;
- // Control whether log messages are sent to the console
- if (this._debug) {
- logEl = function(e) {
- var rv = e.nodeName + " ";
- if (e.nodeType == e.TEXT_NODE) {
- return rv + '("' + e.textContent + '")';
- }
- var classDesc = e.className && ("." + e.className.replace(/ /g, "."));
- var elDesc = "";
- if (e.id)
- elDesc = "(#" + e.id + classDesc + ")";
- else if (classDesc)
- elDesc = "(" + classDesc + ")";
- return rv + elDesc;
- };
- this.log = function () {
- if (typeof dump !== "undefined") {
- var msg = Array.prototype.map.call(arguments, function(x) {
- return (x && x.nodeName) ? logEl(x) : x;
- }).join(" ");
- dump("Reader: (Readability) " + msg + "\n");
- } else if (typeof console !== "undefined") {
- var args = ["Reader: (Readability) "].concat(arguments);
- console.log.apply(console, args);
- }
- };
- } else {
- this.log = function () {};
- }
+ // Control whether log messages are sent to the console
+ if (this._debug) {
+ logEl = function(e) {
+ var rv = e.nodeName + ' ';
+ if (e.nodeType == e.TEXT_NODE) {
+ return rv + '("' + e.textContent + '")';
+ }
+ var classDesc = e.className && ('.' + e.className.replace(/ /g, '.'));
+ var elDesc = '';
+ if (e.id)
+ elDesc = '(#' + e.id + classDesc + ')';
+ else if (classDesc)
+ elDesc = '(' + classDesc + ')';
+ return rv + elDesc;
+ };
+ this.log = function () {
+ if (typeof dump !== 'undefined') {
+ var msg = Array.prototype.map.call(arguments, function(x) {
+ return (x && x.nodeName) ? logEl(x) : x;
+ }).join(' ');
+ dump('Reader: (Readability) ' + msg + '\n');
+ } else if (typeof console !== 'undefined') {
+ var args = ['Reader: (Readability) '].concat(arguments);
+ console.log.apply(console, args);
+ }
+ };
+ } else {
+ this.log = function () {};
+ }
}
Readability.prototype = {
- FLAG_STRIP_UNLIKELYS: 0x1,
- FLAG_WEIGHT_CLASSES: 0x2,
- FLAG_CLEAN_CONDITIONALLY: 0x4,
+ FLAG_STRIP_UNLIKELYS: 0x1,
+ FLAG_WEIGHT_CLASSES: 0x2,
+ FLAG_CLEAN_CONDITIONALLY: 0x4,
- // https://developer.mozilla.org/en-US/docs/Web/API/Node/nodeType
- ELEMENT_NODE: 1,
- TEXT_NODE: 3,
+ // https://developer.mozilla.org/en-US/docs/Web/API/Node/nodeType
+ ELEMENT_NODE: 1,
+ TEXT_NODE: 3,
- // Max number of nodes supported by this parser. Default: 0 (no limit)
- DEFAULT_MAX_ELEMS_TO_PARSE: 0,
+ // Max number of nodes supported by this parser. Default: 0 (no limit)
+ DEFAULT_MAX_ELEMS_TO_PARSE: 0,
- // The number of top candidates to consider when analysing how
- // tight the competition is among candidates.
- DEFAULT_N_TOP_CANDIDATES: 5,
+ // The number of top candidates to consider when analysing how
+ // tight the competition is among candidates.
+ DEFAULT_N_TOP_CANDIDATES: 5,
- // Element tags to score by default.
- DEFAULT_TAGS_TO_SCORE: "section,h2,h3,h4,h5,h6,p,td,pre".toUpperCase().split(","),
+ // Element tags to score by default.
+ DEFAULT_TAGS_TO_SCORE: 'section,h2,h3,h4,h5,h6,p,td,pre'.toUpperCase().split(','),
- // The default number of chars an article must have in order to return a result
- DEFAULT_CHAR_THRESHOLD: 500,
+ // The default number of chars an article must have in order to return a result
+ DEFAULT_CHAR_THRESHOLD: 500,
- // All of the regular expressions in use within readability.
- // Defined up here so we don't instantiate them repeatedly in loops.
- REGEXPS: {
- // NOTE: These two regular expressions are duplicated in
- // Readability-readerable.js. Please keep both copies in sync.
- unlikelyCandidates: /-ad-|ai2html|banner|breadcrumbs|combx|comment|community|cover-wrap|disqus|extra|foot|gdpr|header|legends|menu|related|remark|replies|rss|shoutbox|sidebar|skyscraper|social|sponsor|supplemental|ad-break|agegate|pagination|pager|popup|yom-remote/i,
- okMaybeItsACandidate: /and|article|body|column|main|shadow/i,
+ // All of the regular expressions in use within readability.
+ // Defined up here so we don't instantiate them repeatedly in loops.
+ REGEXPS: {
+ // NOTE: These two regular expressions are duplicated in
+ // Readability-readerable.js. Please keep both copies in sync.
+ unlikelyCandidates: /-ad-|ai2html|banner|breadcrumbs|combx|comment|community|cover-wrap|disqus|extra|foot|gdpr|header|legends|menu|related|remark|replies|rss|shoutbox|sidebar|skyscraper|social|sponsor|supplemental|ad-break|agegate|pagination|pager|popup|yom-remote/i,
+ okMaybeItsACandidate: /and|article|body|column|main|shadow/i,
- positive: /article|body|content|entry|hentry|h-entry|main|page|pagination|post|text|blog|story/i,
- negative: /hidden|^hid$| hid$| hid |^hid |banner|combx|comment|com-|contact|foot|footer|footnote|gdpr|masthead|media|meta|outbrain|promo|related|scroll|share|shoutbox|sidebar|skyscraper|sponsor|shopping|tags|tool|widget/i,
- extraneous: /print|archive|comment|discuss|e[\-]?mail|share|reply|all|login|sign|single|utility/i,
- byline: /byline|author|dateline|writtenby|p-author/i,
- replaceFonts: /<(\/?)font[^>]*>/gi,
- normalize: /\s{2,}/g,
- videos: /\/\/(www\.)?((dailymotion|youtube|youtube-nocookie|player\.vimeo|v\.qq)\.com|(archive|upload\.wikimedia)\.org|player\.twitch\.tv)/i,
- nextLink: /(next|weiter|continue|>([^\|]|$)|»([^\|]|$))/i,
- prevLink: /(prev|earl|old|new|<|«)/i,
- whitespace: /^\s*$/,
- hasContent: /\S$/,
- },
+ positive: /article|body|content|entry|hentry|h-entry|main|page|pagination|post|text|blog|story/i,
+ negative: /hidden|^hid$| hid$| hid |^hid |banner|combx|comment|com-|contact|foot|footer|footnote|gdpr|masthead|media|meta|outbrain|promo|related|scroll|share|shoutbox|sidebar|skyscraper|sponsor|shopping|tags|tool|widget/i,
+ extraneous: /print|archive|comment|discuss|e[\-]?mail|share|reply|all|login|sign|single|utility/i,
+ byline: /byline|author|dateline|writtenby|p-author/i,
+ replaceFonts: /<(\/?)font[^>]*>/gi,
+ normalize: /\s{2,}/g,
+ videos: /\/\/(www\.)?((dailymotion|youtube|youtube-nocookie|player\.vimeo|v\.qq)\.com|(archive|upload\.wikimedia)\.org|player\.twitch\.tv)/i,
+ nextLink: /(next|weiter|continue|>([^\|]|$)|»([^\|]|$))/i,
+ prevLink: /(prev|earl|old|new|<|«)/i,
+ whitespace: /^\s*$/,
+ hasContent: /\S$/,
+ },
- DIV_TO_P_ELEMS: [ "A", "BLOCKQUOTE", "DL", "DIV", "IMG", "OL", "P", "PRE", "TABLE", "UL", "SELECT" ],
+ DIV_TO_P_ELEMS: [ 'A', 'BLOCKQUOTE', 'DL', 'DIV', 'IMG', 'OL', 'P', 'PRE', 'TABLE', 'UL', 'SELECT' ],
- ALTER_TO_DIV_EXCEPTIONS: ["DIV", "ARTICLE", "SECTION", "P"],
+ ALTER_TO_DIV_EXCEPTIONS: ['DIV', 'ARTICLE', 'SECTION', 'P'],
- PRESENTATIONAL_ATTRIBUTES: [ "align", "background", "bgcolor", "border", "cellpadding", "cellspacing", "frame", "hspace", "rules", "style", "valign", "vspace" ],
+ PRESENTATIONAL_ATTRIBUTES: [ 'align', 'background', 'bgcolor', 'border', 'cellpadding', 'cellspacing', 'frame', 'hspace', 'rules', 'style', 'valign', 'vspace' ],
- DEPRECATED_SIZE_ATTRIBUTE_ELEMS: [ "TABLE", "TH", "TD", "HR", "PRE" ],
+ DEPRECATED_SIZE_ATTRIBUTE_ELEMS: [ 'TABLE', 'TH', 'TD', 'HR', 'PRE' ],
- // The commented out elements qualify as phrasing content but tend to be
- // removed by readability when put into paragraphs, so we ignore them here.
- PHRASING_ELEMS: [
- // "CANVAS", "IFRAME", "SVG", "VIDEO",
- "ABBR", "AUDIO", "B", "BDO", "BR", "BUTTON", "CITE", "CODE", "DATA",
- "DATALIST", "DFN", "EM", "EMBED", "I", "IMG", "INPUT", "KBD", "LABEL",
- "MARK", "MATH", "METER", "NOSCRIPT", "OBJECT", "OUTPUT", "PROGRESS", "Q",
- "RUBY", "SAMP", "SCRIPT", "SELECT", "SMALL", "SPAN", "STRONG", "SUB",
- "SUP", "TEXTAREA", "TIME", "VAR", "WBR"
- ],
+ // The commented out elements qualify as phrasing content but tend to be
+ // removed by readability when put into paragraphs, so we ignore them here.
+ PHRASING_ELEMS: [
+ // "CANVAS", "IFRAME", "SVG", "VIDEO",
+ 'ABBR', 'AUDIO', 'B', 'BDO', 'BR', 'BUTTON', 'CITE', 'CODE', 'DATA',
+ 'DATALIST', 'DFN', 'EM', 'EMBED', 'I', 'IMG', 'INPUT', 'KBD', 'LABEL',
+ 'MARK', 'MATH', 'METER', 'NOSCRIPT', 'OBJECT', 'OUTPUT', 'PROGRESS', 'Q',
+ 'RUBY', 'SAMP', 'SCRIPT', 'SELECT', 'SMALL', 'SPAN', 'STRONG', 'SUB',
+ 'SUP', 'TEXTAREA', 'TIME', 'VAR', 'WBR',
+ ],
- // These are the classes that readability sets itself.
- CLASSES_TO_PRESERVE: [ "page" ],
+ // These are the classes that readability sets itself.
+ CLASSES_TO_PRESERVE: [ 'page' ],
- /**
+ /**
* Run any post-process modifications to article content as necessary.
*
* @param Element
* @return void
**/
- _postProcessContent: function(articleContent) {
- // Readability cannot open relative uris so we convert them to absolute uris.
- this._fixRelativeUris(articleContent);
+ _postProcessContent: function(articleContent) {
+ // Readability cannot open relative uris so we convert them to absolute uris.
+ this._fixRelativeUris(articleContent);
- // Remove classes.
- this._cleanClasses(articleContent);
- },
+ // Remove classes.
+ this._cleanClasses(articleContent);
+ },
- /**
+ /**
* Iterates over a NodeList, calls `filterFn` for each node and removes node
* if function returned `true`.
*
@@ -178,33 +178,33 @@ Readability.prototype = {
* @param Function filterFn the function to use as a filter
* @return void
*/
- _removeNodes: function(nodeList, filterFn) {
- for (var i = nodeList.length - 1; i >= 0; i--) {
- var node = nodeList[i];
- var parentNode = node.parentNode;
- if (parentNode) {
- if (!filterFn || filterFn.call(this, node, i, nodeList)) {
- parentNode.removeChild(node);
- }
- }
- }
- },
+ _removeNodes: function(nodeList, filterFn) {
+ for (var i = nodeList.length - 1; i >= 0; i--) {
+ var node = nodeList[i];
+ var parentNode = node.parentNode;
+ if (parentNode) {
+ if (!filterFn || filterFn.call(this, node, i, nodeList)) {
+ parentNode.removeChild(node);
+ }
+ }
+ }
+ },
- /**
+ /**
* Iterates over a NodeList, and calls _setNodeTag for each node.
*
* @param NodeList nodeList The nodes to operate on
* @param String newTagName the new tag name to use
* @return void
*/
- _replaceNodeTags: function(nodeList, newTagName) {
- for (var i = nodeList.length - 1; i >= 0; i--) {
- var node = nodeList[i];
- this._setNodeTag(node, newTagName);
- }
- },
+ _replaceNodeTags: function(nodeList, newTagName) {
+ for (var i = nodeList.length - 1; i >= 0; i--) {
+ var node = nodeList[i];
+ this._setNodeTag(node, newTagName);
+ }
+ },
- /**
+ /**
* Iterate over a NodeList, which doesn't natively fully implement the Array
* interface.
*
@@ -215,11 +215,11 @@ Readability.prototype = {
* @param Function fn The iterate function.
* @return void
*/
- _forEachNode: function(nodeList, fn) {
- Array.prototype.forEach.call(nodeList, fn, this);
- },
+ _forEachNode: function(nodeList, fn) {
+ Array.prototype.forEach.call(nodeList, fn, this);
+ },
- /**
+ /**
* Iterate over a NodeList, return true if any of the provided iterate
* function calls returns true, false otherwise.
*
@@ -230,11 +230,11 @@ Readability.prototype = {
* @param Function fn The iterate function.
* @return Boolean
*/
- _someNode: function(nodeList, fn) {
- return Array.prototype.some.call(nodeList, fn, this);
- },
+ _someNode: function(nodeList, fn) {
+ return Array.prototype.some.call(nodeList, fn, this);
+ },
- /**
+ /**
* Iterate over a NodeList, return true if all of the provided iterate
* function calls return true, false otherwise.
*
@@ -245,36 +245,36 @@ Readability.prototype = {
* @param Function fn The iterate function.
* @return Boolean
*/
- _everyNode: function(nodeList, fn) {
- return Array.prototype.every.call(nodeList, fn, this);
- },
+ _everyNode: function(nodeList, fn) {
+ return Array.prototype.every.call(nodeList, fn, this);
+ },
- /**
+ /**
* Concat all nodelists passed as arguments.
*
* @return ...NodeList
* @return Array
*/
- _concatNodeLists: function() {
- var slice = Array.prototype.slice;
- var args = slice.call(arguments);
- var nodeLists = args.map(function(list) {
- return slice.call(list);
- });
- return Array.prototype.concat.apply([], nodeLists);
- },
+ _concatNodeLists: function() {
+ var slice = Array.prototype.slice;
+ var args = slice.call(arguments);
+ var nodeLists = args.map(function(list) {
+ return slice.call(list);
+ });
+ return Array.prototype.concat.apply([], nodeLists);
+ },
- _getAllNodesWithTag: function(node, tagNames) {
- if (node.querySelectorAll) {
- return node.querySelectorAll(tagNames.join(","));
- }
- return [].concat.apply([], tagNames.map(function(tag) {
- var collection = node.getElementsByTagName(tag);
- return Array.isArray(collection) ? collection : Array.from(collection);
- }));
- },
+ _getAllNodesWithTag: function(node, tagNames) {
+ if (node.querySelectorAll) {
+ return node.querySelectorAll(tagNames.join(','));
+ }
+ return [].concat.apply([], tagNames.map(function(tag) {
+ var collection = node.getElementsByTagName(tag);
+ return Array.isArray(collection) ? collection : Array.from(collection);
+ }));
+ },
- /**
+ /**
* Removes the class="" attribute from every element in the given
* subtree, except those that match CLASSES_TO_PRESERVE and
* the classesToPreserve array from the options object.
@@ -282,921 +282,921 @@ Readability.prototype = {
* @param Element
* @return void
*/
- _cleanClasses: function(node) {
- var classesToPreserve = this._classesToPreserve;
- var className = (node.getAttribute("class") || "")
- .split(/\s+/)
- .filter(function(cls) {
- return classesToPreserve.indexOf(cls) != -1;
- })
- .join(" ");
+ _cleanClasses: function(node) {
+ var classesToPreserve = this._classesToPreserve;
+ var className = (node.getAttribute('class') || '')
+ .split(/\s+/)
+ .filter(function(cls) {
+ return classesToPreserve.indexOf(cls) != -1;
+ })
+ .join(' ');
- if (className) {
- node.setAttribute("class", className);
- } else {
- node.removeAttribute("class");
- }
+ if (className) {
+ node.setAttribute('class', className);
+ } else {
+ node.removeAttribute('class');
+ }
- for (node = node.firstElementChild; node; node = node.nextElementSibling) {
- this._cleanClasses(node);
- }
- },
+ for (node = node.firstElementChild; node; node = node.nextElementSibling) {
+ this._cleanClasses(node);
+ }
+ },
- /**
+ /**
* Converts each and + //
+ // Sentences
+ //
elements with a single
.
* Whitespace between
elements are ignored. For example:
*
foo
bar
abc
* will become:
* bar
abc
foo
bar
*/
- _replaceBrs: function (elem) {
- this._forEachNode(this._getAllNodesWithTag(elem, ["br"]), function(br) {
- var next = br.nextSibling;
+ _replaceBrs: function (elem) {
+ this._forEachNode(this._getAllNodesWithTag(elem, ['br']), function(br) {
+ var next = br.nextSibling;
- // Whether 2 or more bar
abc
elements have been found and replaced with a - //
block.
- var replaced = false;
+ // Whether 2 or more
elements have been found and replaced with a
+ //
block.
+ var replaced = false;
- // If we find a
chain, remove the
s until we hit another element
- // or non-whitespace. This leaves behind the first
in the chain
- // (which will be replaced with a
later).
- while ((next = this._nextElement(next)) && (next.tagName == "BR")) {
- replaced = true;
- var brSibling = next.nextSibling;
- next.parentNode.removeChild(next);
- next = brSibling;
- }
+ // If we find a
chain, remove the
s until we hit another element
+ // or non-whitespace. This leaves behind the first
in the chain
+ // (which will be replaced with a
later).
+ while ((next = this._nextElement(next)) && (next.tagName == 'BR')) {
+ replaced = true;
+ var brSibling = next.nextSibling;
+ next.parentNode.removeChild(next);
+ next = brSibling;
+ }
- // If we removed a
chain, replace the remaining
with a
. Add - // all sibling nodes as children of the
until we hit another
- // chain.
- if (replaced) {
- var p = this._doc.createElement("p");
- br.parentNode.replaceChild(p, br);
+ // If we removed a
chain, replace the remaining
with a
. Add + // all sibling nodes as children of the
until we hit another
+ // chain.
+ if (replaced) {
+ var p = this._doc.createElement('p');
+ br.parentNode.replaceChild(p, br);
- next = p.nextSibling;
- while (next) {
- // If we've hit another
, we're done adding children to this
.
- if (next.tagName == "BR") {
- var nextElem = this._nextElement(next.nextSibling);
- if (nextElem && nextElem.tagName == "BR")
- break;
- }
+ next = p.nextSibling;
+ while (next) {
+ // If we've hit another
, we're done adding children to this
. + if (next.tagName == 'BR') { + var nextElem = this._nextElement(next.nextSibling); + if (nextElem && nextElem.tagName == 'BR') + break; + } - if (!this._isPhrasingContent(next)) - break; + if (!this._isPhrasingContent(next)) + break; - // Otherwise, make this node a child of the new
. - var sibling = next.nextSibling; - p.appendChild(next); - next = sibling; - } + // Otherwise, make this node a child of the new
. + var sibling = next.nextSibling; + p.appendChild(next); + next = sibling; + } - while (p.lastChild && this._isWhitespace(p.lastChild)) { - p.removeChild(p.lastChild); - } + while (p.lastChild && this._isWhitespace(p.lastChild)) { + p.removeChild(p.lastChild); + } - if (p.parentNode.tagName === "P") - this._setNodeTag(p.parentNode, "DIV"); - } - }); - }, + if (p.parentNode.tagName === 'P') + this._setNodeTag(p.parentNode, 'DIV'); + } + }); + }, - _setNodeTag: function (node, tag) { - this.log("_setNodeTag", node, tag); - if (node.__JSDOMParser__) { - node.localName = tag.toLowerCase(); - node.tagName = tag.toUpperCase(); - return node; - } + _setNodeTag: function (node, tag) { + this.log('_setNodeTag', node, tag); + if (node.__JSDOMParser__) { + node.localName = tag.toLowerCase(); + node.tagName = tag.toUpperCase(); + return node; + } - var replacement = node.ownerDocument.createElement(tag); - while (node.firstChild) { - replacement.appendChild(node.firstChild); - } - node.parentNode.replaceChild(replacement, node); - if (node.readability) - replacement.readability = node.readability; + var replacement = node.ownerDocument.createElement(tag); + while (node.firstChild) { + replacement.appendChild(node.firstChild); + } + node.parentNode.replaceChild(replacement, node); + if (node.readability) + replacement.readability = node.readability; - for (var i = 0; i < node.attributes.length; i++) { - try { - replacement.setAttribute(node.attributes[i].name, node.attributes[i].value); - } catch (ex) { - /* it's possible for setAttribute() to throw if the attribute name + for (var i = 0; i < node.attributes.length; i++) { + try { + replacement.setAttribute(node.attributes[i].name, node.attributes[i].value); + } catch (ex) { + /* it's possible for setAttribute() to throw if the attribute name * isn't a valid XML Name. Such attributes can however be parsed from * source in HTML docs, see https://github.com/whatwg/html/issues/4275, * so we can hit them here and then throw. We don't care about such * attributes so we ignore them. */ - } - } - return replacement; - }, + } + } + return replacement; + }, - /** + /** * Prepare the article node for display. Clean out any inline styles, * iframes, forms, strip extraneous
tags, etc. * * @param Element * @return void **/ - _prepArticle: function(articleContent) { - this._cleanStyles(articleContent); + _prepArticle: function(articleContent) { + this._cleanStyles(articleContent); - // Check for data tables before we continue, to avoid removing items in - // those tables, which will often be isolated even though they're - // visually linked to other content-ful elements (text, images, etc.). - this._markDataTables(articleContent); + // Check for data tables before we continue, to avoid removing items in + // those tables, which will often be isolated even though they're + // visually linked to other content-ful elements (text, images, etc.). + this._markDataTables(articleContent); - this._fixLazyImages(articleContent); + this._fixLazyImages(articleContent); - // Clean out junk from the article content - this._cleanConditionally(articleContent, "form"); - this._cleanConditionally(articleContent, "fieldset"); - this._clean(articleContent, "object"); - this._clean(articleContent, "embed"); - this._clean(articleContent, "h1"); - this._clean(articleContent, "footer"); - this._clean(articleContent, "link"); - this._clean(articleContent, "aside"); + // Clean out junk from the article content + this._cleanConditionally(articleContent, 'form'); + this._cleanConditionally(articleContent, 'fieldset'); + this._clean(articleContent, 'object'); + this._clean(articleContent, 'embed'); + this._clean(articleContent, 'h1'); + this._clean(articleContent, 'footer'); + this._clean(articleContent, 'link'); + this._clean(articleContent, 'aside'); - // Clean out elements with little content that have "share" in their id/class combinations from final top candidates, - // which means we don't remove the top candidates even they have "share". + // Clean out elements with little content that have "share" in their id/class combinations from final top candidates, + // which means we don't remove the top candidates even they have "share". - var shareElementThreshold = this.DEFAULT_CHAR_THRESHOLD; + var shareElementThreshold = this.DEFAULT_CHAR_THRESHOLD; - this._forEachNode(articleContent.children, function (topCandidate) { - this._cleanMatchedNodes(topCandidate, function (node, matchString) { - return /share/.test(matchString) && node.textContent.length < shareElementThreshold; - }); - }); + this._forEachNode(articleContent.children, function (topCandidate) { + this._cleanMatchedNodes(topCandidate, function (node, matchString) { + return /share/.test(matchString) && node.textContent.length < shareElementThreshold; + }); + }); - // If there is only one h2 and its text content substantially equals article title, - // they are probably using it as a header and not a subheader, - // so remove it since we already extract the title separately. - var h2 = articleContent.getElementsByTagName("h2"); - if (h2.length === 1) { - var lengthSimilarRate = (h2[0].textContent.length - this._articleTitle.length) / this._articleTitle.length; - if (Math.abs(lengthSimilarRate) < 0.5) { - var titlesMatch = false; - if (lengthSimilarRate > 0) { - titlesMatch = h2[0].textContent.includes(this._articleTitle); - } else { - titlesMatch = this._articleTitle.includes(h2[0].textContent); - } - if (titlesMatch) { - this._clean(articleContent, "h2"); - } - } - } + // If there is only one h2 and its text content substantially equals article title, + // they are probably using it as a header and not a subheader, + // so remove it since we already extract the title separately. + var h2 = articleContent.getElementsByTagName('h2'); + if (h2.length === 1) { + var lengthSimilarRate = (h2[0].textContent.length - this._articleTitle.length) / this._articleTitle.length; + if (Math.abs(lengthSimilarRate) < 0.5) { + var titlesMatch = false; + if (lengthSimilarRate > 0) { + titlesMatch = h2[0].textContent.includes(this._articleTitle); + } else { + titlesMatch = this._articleTitle.includes(h2[0].textContent); + } + if (titlesMatch) { + this._clean(articleContent, 'h2'); + } + } + } - this._clean(articleContent, "iframe"); - this._clean(articleContent, "input"); - this._clean(articleContent, "textarea"); - this._clean(articleContent, "select"); - this._clean(articleContent, "button"); - this._cleanHeaders(articleContent); + this._clean(articleContent, 'iframe'); + this._clean(articleContent, 'input'); + this._clean(articleContent, 'textarea'); + this._clean(articleContent, 'select'); + this._clean(articleContent, 'button'); + this._cleanHeaders(articleContent); - // Do these last as the previous stuff may have removed junk - // that will affect these - this._cleanConditionally(articleContent, "table"); - this._cleanConditionally(articleContent, "ul"); - this._cleanConditionally(articleContent, "div"); + // Do these last as the previous stuff may have removed junk + // that will affect these + this._cleanConditionally(articleContent, 'table'); + this._cleanConditionally(articleContent, 'ul'); + this._cleanConditionally(articleContent, 'div'); - // Remove extra paragraphs - this._removeNodes(articleContent.getElementsByTagName("p"), function (paragraph) { - var imgCount = paragraph.getElementsByTagName("img").length; - var embedCount = paragraph.getElementsByTagName("embed").length; - var objectCount = paragraph.getElementsByTagName("object").length; - // At this point, nasty iframes have been removed, only remain embedded video ones. - var iframeCount = paragraph.getElementsByTagName("iframe").length; - var totalCount = imgCount + embedCount + objectCount + iframeCount; + // Remove extra paragraphs + this._removeNodes(articleContent.getElementsByTagName('p'), function (paragraph) { + var imgCount = paragraph.getElementsByTagName('img').length; + var embedCount = paragraph.getElementsByTagName('embed').length; + var objectCount = paragraph.getElementsByTagName('object').length; + // At this point, nasty iframes have been removed, only remain embedded video ones. + var iframeCount = paragraph.getElementsByTagName('iframe').length; + var totalCount = imgCount + embedCount + objectCount + iframeCount; - return totalCount === 0 && !this._getInnerText(paragraph, false); - }); + return totalCount === 0 && !this._getInnerText(paragraph, false); + }); - this._forEachNode(this._getAllNodesWithTag(articleContent, ["br"]), function(br) { - var next = this._nextElement(br.nextSibling); - if (next && next.tagName == "P") - br.parentNode.removeChild(br); - }); + this._forEachNode(this._getAllNodesWithTag(articleContent, ['br']), function(br) { + var next = this._nextElement(br.nextSibling); + if (next && next.tagName == 'P') + br.parentNode.removeChild(br); + }); - // Remove single-cell tables - this._forEachNode(this._getAllNodesWithTag(articleContent, ["table"]), function(table) { - var tbody = this._hasSingleTagInsideElement(table, "TBODY") ? table.firstElementChild : table; - if (this._hasSingleTagInsideElement(tbody, "TR")) { - var row = tbody.firstElementChild; - if (this._hasSingleTagInsideElement(row, "TD")) { - var cell = row.firstElementChild; - cell = this._setNodeTag(cell, this._everyNode(cell.childNodes, this._isPhrasingContent) ? "P" : "DIV"); - table.parentNode.replaceChild(cell, table); - } - } - }); - }, + // Remove single-cell tables + this._forEachNode(this._getAllNodesWithTag(articleContent, ['table']), function(table) { + var tbody = this._hasSingleTagInsideElement(table, 'TBODY') ? table.firstElementChild : table; + if (this._hasSingleTagInsideElement(tbody, 'TR')) { + var row = tbody.firstElementChild; + if (this._hasSingleTagInsideElement(row, 'TD')) { + var cell = row.firstElementChild; + cell = this._setNodeTag(cell, this._everyNode(cell.childNodes, this._isPhrasingContent) ? 'P' : 'DIV'); + table.parentNode.replaceChild(cell, table); + } + } + }); + }, - /** + /** * Initialize a node with the readability object. Also checks the * className/id for special names to add to its score. * * @param Element * @return void **/ - _initializeNode: function(node) { - node.readability = {"contentScore": 0}; + _initializeNode: function(node) { + node.readability = {'contentScore': 0}; - switch (node.tagName) { - case "DIV": - node.readability.contentScore += 5; - break; + switch (node.tagName) { + case 'DIV': + node.readability.contentScore += 5; + break; - case "PRE": - case "TD": - case "BLOCKQUOTE": - node.readability.contentScore += 3; - break; + case 'PRE': + case 'TD': + case 'BLOCKQUOTE': + node.readability.contentScore += 3; + break; - case "ADDRESS": - case "OL": - case "UL": - case "DL": - case "DD": - case "DT": - case "LI": - case "FORM": - node.readability.contentScore -= 3; - break; + case 'ADDRESS': + case 'OL': + case 'UL': + case 'DL': + case 'DD': + case 'DT': + case 'LI': + case 'FORM': + node.readability.contentScore -= 3; + break; - case "H1": - case "H2": - case "H3": - case "H4": - case "H5": - case "H6": - case "TH": - node.readability.contentScore -= 5; - break; - } + case 'H1': + case 'H2': + case 'H3': + case 'H4': + case 'H5': + case 'H6': + case 'TH': + node.readability.contentScore -= 5; + break; + } - node.readability.contentScore += this._getClassWeight(node); - }, + node.readability.contentScore += this._getClassWeight(node); + }, - _removeAndGetNext: function(node) { - var nextNode = this._getNextNode(node, true); - node.parentNode.removeChild(node); - return nextNode; - }, + _removeAndGetNext: function(node) { + var nextNode = this._getNextNode(node, true); + node.parentNode.removeChild(node); + return nextNode; + }, - /** + /** * Traverse the DOM from node to node, starting at the node passed in. * Pass true for the second parameter to indicate this node itself * (and its kids) are going away, and we want the next node over. * * Calling this in a loop will traverse the DOM depth-first. */ - _getNextNode: function(node, ignoreSelfAndKids) { - // First check for kids if those aren't being ignored - if (!ignoreSelfAndKids && node.firstElementChild) { - return node.firstElementChild; - } - // Then for siblings... - if (node.nextElementSibling) { - return node.nextElementSibling; - } - // And finally, move up the parent chain *and* find a sibling - // (because this is depth-first traversal, we will have already - // seen the parent nodes themselves). - do { - node = node.parentNode; - } while (node && !node.nextElementSibling); - return node && node.nextElementSibling; - }, + _getNextNode: function(node, ignoreSelfAndKids) { + // First check for kids if those aren't being ignored + if (!ignoreSelfAndKids && node.firstElementChild) { + return node.firstElementChild; + } + // Then for siblings... + if (node.nextElementSibling) { + return node.nextElementSibling; + } + // And finally, move up the parent chain *and* find a sibling + // (because this is depth-first traversal, we will have already + // seen the parent nodes themselves). + do { + node = node.parentNode; + } while (node && !node.nextElementSibling); + return node && node.nextElementSibling; + }, - _checkByline: function(node, matchString) { - if (this._articleByline) { - return false; - } + _checkByline: function(node, matchString) { + if (this._articleByline) { + return false; + } - if (node.getAttribute !== undefined) { - var rel = node.getAttribute("rel"); - var itemprop = node.getAttribute("itemprop"); - } + if (node.getAttribute !== undefined) { + var rel = node.getAttribute('rel'); + var itemprop = node.getAttribute('itemprop'); + } - if ((rel === "author" || (itemprop && itemprop.indexOf("author") !== -1) || this.REGEXPS.byline.test(matchString)) && this._isValidByline(node.textContent)) { - this._articleByline = node.textContent.trim(); - return true; - } + if ((rel === 'author' || (itemprop && itemprop.indexOf('author') !== -1) || this.REGEXPS.byline.test(matchString)) && this._isValidByline(node.textContent)) { + this._articleByline = node.textContent.trim(); + return true; + } - return false; - }, + return false; + }, - _getNodeAncestors: function(node, maxDepth) { - maxDepth = maxDepth || 0; - var i = 0, ancestors = []; - while (node.parentNode) { - ancestors.push(node.parentNode); - if (maxDepth && ++i === maxDepth) - break; - node = node.parentNode; - } - return ancestors; - }, + _getNodeAncestors: function(node, maxDepth) { + maxDepth = maxDepth || 0; + var i = 0, ancestors = []; + while (node.parentNode) { + ancestors.push(node.parentNode); + if (maxDepth && ++i === maxDepth) + break; + node = node.parentNode; + } + return ancestors; + }, - /*** + /*** * grabArticle - Using a variety of metrics (content score, classname, element types), find the content that is * most likely to be the stuff a user wants to read. Then return it wrapped up in a div. * * @param page a document to run upon. Needs to be a full document, complete with body. * @return Element **/ - _grabArticle: function (page) { - this.log("**** grabArticle ****"); - var doc = this._doc; - var isPaging = (page !== null ? true: false); - page = page ? page : this._doc.body; + _grabArticle: function (page) { + this.log('**** grabArticle ****'); + var doc = this._doc; + var isPaging = (page !== null ? true: false); + page = page ? page : this._doc.body; - // We can't grab an article if we don't have a page! - if (!page) { - this.log("No body found in document. Abort."); - return null; - } + // We can't grab an article if we don't have a page! + if (!page) { + this.log('No body found in document. Abort.'); + return null; + } - var pageCacheHtml = page.innerHTML; + var pageCacheHtml = page.innerHTML; - while (true) { - var stripUnlikelyCandidates = this._flagIsActive(this.FLAG_STRIP_UNLIKELYS); + while (true) { + var stripUnlikelyCandidates = this._flagIsActive(this.FLAG_STRIP_UNLIKELYS); - // First, node prepping. Trash nodes that look cruddy (like ones with the - // class name "comment", etc), and turn divs into P tags where they have been - // used inappropriately (as in, where they contain no other block level elements.) - var elementsToScore = []; - var node = this._doc.documentElement; + // First, node prepping. Trash nodes that look cruddy (like ones with the + // class name "comment", etc), and turn divs into P tags where they have been + // used inappropriately (as in, where they contain no other block level elements.) + var elementsToScore = []; + var node = this._doc.documentElement; - while (node) { - var matchString = node.className + " " + node.id; + while (node) { + var matchString = node.className + ' ' + node.id; - if (!this._isProbablyVisible(node)) { - this.log("Removing hidden node - " + matchString); - node = this._removeAndGetNext(node); - continue; - } + if (!this._isProbablyVisible(node)) { + this.log('Removing hidden node - ' + matchString); + node = this._removeAndGetNext(node); + continue; + } - // Check to see if this node is a byline, and remove it if it is. - if (this._checkByline(node, matchString)) { - node = this._removeAndGetNext(node); - continue; - } + // Check to see if this node is a byline, and remove it if it is. + if (this._checkByline(node, matchString)) { + node = this._removeAndGetNext(node); + continue; + } - // Remove unlikely candidates - if (stripUnlikelyCandidates) { - if (this.REGEXPS.unlikelyCandidates.test(matchString) && + // Remove unlikely candidates + if (stripUnlikelyCandidates) { + if (this.REGEXPS.unlikelyCandidates.test(matchString) && !this.REGEXPS.okMaybeItsACandidate.test(matchString) && - !this._hasAncestorTag(node, "table") && - node.tagName !== "BODY" && - node.tagName !== "A") { - this.log("Removing unlikely candidate - " + matchString); - node = this._removeAndGetNext(node); - continue; - } - } + !this._hasAncestorTag(node, 'table') && + node.tagName !== 'BODY' && + node.tagName !== 'A') { + this.log('Removing unlikely candidate - ' + matchString); + node = this._removeAndGetNext(node); + continue; + } + } - // Remove DIV, SECTION, and HEADER nodes without any content(e.g. text, image, video, or iframe). - if ((node.tagName === "DIV" || node.tagName === "SECTION" || node.tagName === "HEADER" || - node.tagName === "H1" || node.tagName === "H2" || node.tagName === "H3" || - node.tagName === "H4" || node.tagName === "H5" || node.tagName === "H6") && + // Remove DIV, SECTION, and HEADER nodes without any content(e.g. text, image, video, or iframe). + if ((node.tagName === 'DIV' || node.tagName === 'SECTION' || node.tagName === 'HEADER' || + node.tagName === 'H1' || node.tagName === 'H2' || node.tagName === 'H3' || + node.tagName === 'H4' || node.tagName === 'H5' || node.tagName === 'H6') && this._isElementWithoutContent(node)) { - node = this._removeAndGetNext(node); - continue; - } + node = this._removeAndGetNext(node); + continue; + } - if (this.DEFAULT_TAGS_TO_SCORE.indexOf(node.tagName) !== -1) { - elementsToScore.push(node); - } + if (this.DEFAULT_TAGS_TO_SCORE.indexOf(node.tagName) !== -1) { + elementsToScore.push(node); + } - // Turn all divs that don't have children block level elements into p's - if (node.tagName === "DIV") { - // Put phrasing content into paragraphs. - var p = null; - var childNode = node.firstChild; - while (childNode) { - var nextSibling = childNode.nextSibling; - if (this._isPhrasingContent(childNode)) { - if (p !== null) { - p.appendChild(childNode); - } else if (!this._isWhitespace(childNode)) { - p = doc.createElement("p"); - node.replaceChild(p, childNode); - p.appendChild(childNode); - } - } else if (p !== null) { - while (p.lastChild && this._isWhitespace(p.lastChild)) { - p.removeChild(p.lastChild); - } - p = null; - } - childNode = nextSibling; - } + // Turn all divs that don't have children block level elements into p's + if (node.tagName === 'DIV') { + // Put phrasing content into paragraphs. + var p = null; + var childNode = node.firstChild; + while (childNode) { + var nextSibling = childNode.nextSibling; + if (this._isPhrasingContent(childNode)) { + if (p !== null) { + p.appendChild(childNode); + } else if (!this._isWhitespace(childNode)) { + p = doc.createElement('p'); + node.replaceChild(p, childNode); + p.appendChild(childNode); + } + } else if (p !== null) { + while (p.lastChild && this._isWhitespace(p.lastChild)) { + p.removeChild(p.lastChild); + } + p = null; + } + childNode = nextSibling; + } - // Sites like http://mobile.slate.com encloses each paragraph with a DIV - // element. DIVs with only a P element inside and no text content can be - // safely converted into plain P elements to avoid confusing the scoring - // algorithm with DIVs with are, in practice, paragraphs. - if (this._hasSingleTagInsideElement(node, "P") && this._getLinkDensity(node) < 0.25) { - var newNode = node.children[0]; - node.parentNode.replaceChild(newNode, node); - node = newNode; - elementsToScore.push(node); - } else if (!this._hasChildBlockElement(node)) { - node = this._setNodeTag(node, "P"); - elementsToScore.push(node); - } - } - node = this._getNextNode(node); - } + // Sites like http://mobile.slate.com encloses each paragraph with a DIV + // element. DIVs with only a P element inside and no text content can be + // safely converted into plain P elements to avoid confusing the scoring + // algorithm with DIVs with are, in practice, paragraphs. + if (this._hasSingleTagInsideElement(node, 'P') && this._getLinkDensity(node) < 0.25) { + var newNode = node.children[0]; + node.parentNode.replaceChild(newNode, node); + node = newNode; + elementsToScore.push(node); + } else if (!this._hasChildBlockElement(node)) { + node = this._setNodeTag(node, 'P'); + elementsToScore.push(node); + } + } + node = this._getNextNode(node); + } - /** + /** * Loop through all paragraphs, and assign a score to them based on how content-y they look. * Then add their score to their parent node. * * A score is determined by things like number of commas, class names, etc. Maybe eventually link density. **/ - var candidates = []; - this._forEachNode(elementsToScore, function(elementToScore) { - if (!elementToScore.parentNode || typeof(elementToScore.parentNode.tagName) === "undefined") - return; + var candidates = []; + this._forEachNode(elementsToScore, function(elementToScore) { + if (!elementToScore.parentNode || typeof(elementToScore.parentNode.tagName) === 'undefined') + return; - // If this paragraph is less than 25 characters, don't even count it. - var innerText = this._getInnerText(elementToScore); - if (innerText.length < 25) - return; + // If this paragraph is less than 25 characters, don't even count it. + var innerText = this._getInnerText(elementToScore); + if (innerText.length < 25) + return; - // Exclude nodes with no ancestor. - var ancestors = this._getNodeAncestors(elementToScore, 3); - if (ancestors.length === 0) - return; + // Exclude nodes with no ancestor. + var ancestors = this._getNodeAncestors(elementToScore, 3); + if (ancestors.length === 0) + return; - var contentScore = 0; + var contentScore = 0; - // Add a point for the paragraph itself as a base. - contentScore += 1; + // Add a point for the paragraph itself as a base. + contentScore += 1; - // Add points for any commas within this paragraph. - contentScore += innerText.split(",").length; + // Add points for any commas within this paragraph. + contentScore += innerText.split(',').length; - // For every 100 characters in this paragraph, add another point. Up to 3 points. - contentScore += Math.min(Math.floor(innerText.length / 100), 3); + // For every 100 characters in this paragraph, add another point. Up to 3 points. + contentScore += Math.min(Math.floor(innerText.length / 100), 3); - // Initialize and score ancestors. - this._forEachNode(ancestors, function(ancestor, level) { - if (!ancestor.tagName || !ancestor.parentNode || typeof(ancestor.parentNode.tagName) === "undefined") - return; + // Initialize and score ancestors. + this._forEachNode(ancestors, function(ancestor, level) { + if (!ancestor.tagName || !ancestor.parentNode || typeof(ancestor.parentNode.tagName) === 'undefined') + return; - if (typeof(ancestor.readability) === "undefined") { - this._initializeNode(ancestor); - candidates.push(ancestor); - } + if (typeof(ancestor.readability) === 'undefined') { + this._initializeNode(ancestor); + candidates.push(ancestor); + } - // Node score divider: - // - parent: 1 (no division) - // - grandparent: 2 - // - great grandparent+: ancestor level * 3 - if (level === 0) - var scoreDivider = 1; - else if (level === 1) - scoreDivider = 2; - else - scoreDivider = level * 3; - ancestor.readability.contentScore += contentScore / scoreDivider; - }); - }); + // Node score divider: + // - parent: 1 (no division) + // - grandparent: 2 + // - great grandparent+: ancestor level * 3 + if (level === 0) + var scoreDivider = 1; + else if (level === 1) + scoreDivider = 2; + else + scoreDivider = level * 3; + ancestor.readability.contentScore += contentScore / scoreDivider; + }); + }); - // After we've calculated scores, loop through all of the possible - // candidate nodes we found and find the one with the highest score. - var topCandidates = []; - for (var c = 0, cl = candidates.length; c < cl; c += 1) { - var candidate = candidates[c]; + // After we've calculated scores, loop through all of the possible + // candidate nodes we found and find the one with the highest score. + var topCandidates = []; + for (var c = 0, cl = candidates.length; c < cl; c += 1) { + var candidate = candidates[c]; - // Scale the final candidates score based on link density. Good content - // should have a relatively small link density (5% or less) and be mostly - // unaffected by this operation. - var candidateScore = candidate.readability.contentScore * (1 - this._getLinkDensity(candidate)); - candidate.readability.contentScore = candidateScore; + // Scale the final candidates score based on link density. Good content + // should have a relatively small link density (5% or less) and be mostly + // unaffected by this operation. + var candidateScore = candidate.readability.contentScore * (1 - this._getLinkDensity(candidate)); + candidate.readability.contentScore = candidateScore; - this.log("Candidate:", candidate, "with score " + candidateScore); + this.log('Candidate:', candidate, 'with score ' + candidateScore); - for (var t = 0; t < this._nbTopCandidates; t++) { - var aTopCandidate = topCandidates[t]; + for (var t = 0; t < this._nbTopCandidates; t++) { + var aTopCandidate = topCandidates[t]; - if (!aTopCandidate || candidateScore > aTopCandidate.readability.contentScore) { - topCandidates.splice(t, 0, candidate); - if (topCandidates.length > this._nbTopCandidates) - topCandidates.pop(); - break; - } - } - } + if (!aTopCandidate || candidateScore > aTopCandidate.readability.contentScore) { + topCandidates.splice(t, 0, candidate); + if (topCandidates.length > this._nbTopCandidates) + topCandidates.pop(); + break; + } + } + } - var topCandidate = topCandidates[0] || null; - var neededToCreateTopCandidate = false; - var parentOfTopCandidate; + var topCandidate = topCandidates[0] || null; + var neededToCreateTopCandidate = false; + var parentOfTopCandidate; - // If we still have no top candidate, just use the body as a last resort. - // We also have to copy the body node so it is something we can modify. - if (topCandidate === null || topCandidate.tagName === "BODY") { - // Move all of the page's children into topCandidate - topCandidate = doc.createElement("DIV"); - neededToCreateTopCandidate = true; - // Move everything (not just elements, also text nodes etc.) into the container - // so we even include text directly in the body: - var kids = page.childNodes; - while (kids.length) { - this.log("Moving child out:", kids[0]); - topCandidate.appendChild(kids[0]); - } + // If we still have no top candidate, just use the body as a last resort. + // We also have to copy the body node so it is something we can modify. + if (topCandidate === null || topCandidate.tagName === 'BODY') { + // Move all of the page's children into topCandidate + topCandidate = doc.createElement('DIV'); + neededToCreateTopCandidate = true; + // Move everything (not just elements, also text nodes etc.) into the container + // so we even include text directly in the body: + var kids = page.childNodes; + while (kids.length) { + this.log('Moving child out:', kids[0]); + topCandidate.appendChild(kids[0]); + } - page.appendChild(topCandidate); + page.appendChild(topCandidate); - this._initializeNode(topCandidate); - } else if (topCandidate) { - // Find a better top candidate node if it contains (at least three) nodes which belong to `topCandidates` array - // and whose scores are quite closed with current `topCandidate` node. - var alternativeCandidateAncestors = []; - for (var i = 1; i < topCandidates.length; i++) { - if (topCandidates[i].readability.contentScore / topCandidate.readability.contentScore >= 0.75) { - alternativeCandidateAncestors.push(this._getNodeAncestors(topCandidates[i])); - } - } - var MINIMUM_TOPCANDIDATES = 3; - if (alternativeCandidateAncestors.length >= MINIMUM_TOPCANDIDATES) { - parentOfTopCandidate = topCandidate.parentNode; - while (parentOfTopCandidate.tagName !== "BODY") { - var listsContainingThisAncestor = 0; - for (var ancestorIndex = 0; ancestorIndex < alternativeCandidateAncestors.length && listsContainingThisAncestor < MINIMUM_TOPCANDIDATES; ancestorIndex++) { - listsContainingThisAncestor += Number(alternativeCandidateAncestors[ancestorIndex].includes(parentOfTopCandidate)); - } - if (listsContainingThisAncestor >= MINIMUM_TOPCANDIDATES) { - topCandidate = parentOfTopCandidate; - break; - } - parentOfTopCandidate = parentOfTopCandidate.parentNode; - } - } - if (!topCandidate.readability) { - this._initializeNode(topCandidate); - } + this._initializeNode(topCandidate); + } else if (topCandidate) { + // Find a better top candidate node if it contains (at least three) nodes which belong to `topCandidates` array + // and whose scores are quite closed with current `topCandidate` node. + var alternativeCandidateAncestors = []; + for (var i = 1; i < topCandidates.length; i++) { + if (topCandidates[i].readability.contentScore / topCandidate.readability.contentScore >= 0.75) { + alternativeCandidateAncestors.push(this._getNodeAncestors(topCandidates[i])); + } + } + var MINIMUM_TOPCANDIDATES = 3; + if (alternativeCandidateAncestors.length >= MINIMUM_TOPCANDIDATES) { + parentOfTopCandidate = topCandidate.parentNode; + while (parentOfTopCandidate.tagName !== 'BODY') { + var listsContainingThisAncestor = 0; + for (var ancestorIndex = 0; ancestorIndex < alternativeCandidateAncestors.length && listsContainingThisAncestor < MINIMUM_TOPCANDIDATES; ancestorIndex++) { + listsContainingThisAncestor += Number(alternativeCandidateAncestors[ancestorIndex].includes(parentOfTopCandidate)); + } + if (listsContainingThisAncestor >= MINIMUM_TOPCANDIDATES) { + topCandidate = parentOfTopCandidate; + break; + } + parentOfTopCandidate = parentOfTopCandidate.parentNode; + } + } + if (!topCandidate.readability) { + this._initializeNode(topCandidate); + } - // Because of our bonus system, parents of candidates might have scores - // themselves. They get half of the node. There won't be nodes with higher - // scores than our topCandidate, but if we see the score going *up* in the first - // few steps up the tree, that's a decent sign that there might be more content - // lurking in other places that we want to unify in. The sibling stuff - // below does some of that - but only if we've looked high enough up the DOM - // tree. - parentOfTopCandidate = topCandidate.parentNode; - var lastScore = topCandidate.readability.contentScore; - // The scores shouldn't get too low. - var scoreThreshold = lastScore / 3; - while (parentOfTopCandidate.tagName !== "BODY") { - if (!parentOfTopCandidate.readability) { - parentOfTopCandidate = parentOfTopCandidate.parentNode; - continue; - } - var parentScore = parentOfTopCandidate.readability.contentScore; - if (parentScore < scoreThreshold) - break; - if (parentScore > lastScore) { - // Alright! We found a better parent to use. - topCandidate = parentOfTopCandidate; - break; - } - lastScore = parentOfTopCandidate.readability.contentScore; - parentOfTopCandidate = parentOfTopCandidate.parentNode; - } + // Because of our bonus system, parents of candidates might have scores + // themselves. They get half of the node. There won't be nodes with higher + // scores than our topCandidate, but if we see the score going *up* in the first + // few steps up the tree, that's a decent sign that there might be more content + // lurking in other places that we want to unify in. The sibling stuff + // below does some of that - but only if we've looked high enough up the DOM + // tree. + parentOfTopCandidate = topCandidate.parentNode; + var lastScore = topCandidate.readability.contentScore; + // The scores shouldn't get too low. + var scoreThreshold = lastScore / 3; + while (parentOfTopCandidate.tagName !== 'BODY') { + if (!parentOfTopCandidate.readability) { + parentOfTopCandidate = parentOfTopCandidate.parentNode; + continue; + } + var parentScore = parentOfTopCandidate.readability.contentScore; + if (parentScore < scoreThreshold) + break; + if (parentScore > lastScore) { + // Alright! We found a better parent to use. + topCandidate = parentOfTopCandidate; + break; + } + lastScore = parentOfTopCandidate.readability.contentScore; + parentOfTopCandidate = parentOfTopCandidate.parentNode; + } - // If the top candidate is the only child, use parent instead. This will help sibling - // joining logic when adjacent content is actually located in parent's sibling node. - parentOfTopCandidate = topCandidate.parentNode; - while (parentOfTopCandidate.tagName != "BODY" && parentOfTopCandidate.children.length == 1) { - topCandidate = parentOfTopCandidate; - parentOfTopCandidate = topCandidate.parentNode; - } - if (!topCandidate.readability) { - this._initializeNode(topCandidate); - } - } + // If the top candidate is the only child, use parent instead. This will help sibling + // joining logic when adjacent content is actually located in parent's sibling node. + parentOfTopCandidate = topCandidate.parentNode; + while (parentOfTopCandidate.tagName != 'BODY' && parentOfTopCandidate.children.length == 1) { + topCandidate = parentOfTopCandidate; + parentOfTopCandidate = topCandidate.parentNode; + } + if (!topCandidate.readability) { + this._initializeNode(topCandidate); + } + } - // Now that we have the top candidate, look through its siblings for content - // that might also be related. Things like preambles, content split by ads - // that we removed, etc. - var articleContent = doc.createElement("DIV"); - if (isPaging) - articleContent.id = "readability-content"; + // Now that we have the top candidate, look through its siblings for content + // that might also be related. Things like preambles, content split by ads + // that we removed, etc. + var articleContent = doc.createElement('DIV'); + if (isPaging) + articleContent.id = 'readability-content'; - var siblingScoreThreshold = Math.max(10, topCandidate.readability.contentScore * 0.2); - // Keep potential top candidate's parent node to try to get text direction of it later. - parentOfTopCandidate = topCandidate.parentNode; - var siblings = parentOfTopCandidate.children; + var siblingScoreThreshold = Math.max(10, topCandidate.readability.contentScore * 0.2); + // Keep potential top candidate's parent node to try to get text direction of it later. + parentOfTopCandidate = topCandidate.parentNode; + var siblings = parentOfTopCandidate.children; - for (var s = 0, sl = siblings.length; s < sl; s++) { - var sibling = siblings[s]; - var append = false; + for (var s = 0, sl = siblings.length; s < sl; s++) { + var sibling = siblings[s]; + var append = false; - this.log("Looking at sibling node:", sibling, sibling.readability ? ("with score " + sibling.readability.contentScore) : ""); - this.log("Sibling has score", sibling.readability ? sibling.readability.contentScore : "Unknown"); + this.log('Looking at sibling node:', sibling, sibling.readability ? ('with score ' + sibling.readability.contentScore) : ''); + this.log('Sibling has score', sibling.readability ? sibling.readability.contentScore : 'Unknown'); - if (sibling === topCandidate) { - append = true; - } else { - var contentBonus = 0; + if (sibling === topCandidate) { + append = true; + } else { + var contentBonus = 0; - // Give a bonus if sibling nodes and top candidates have the example same classname - if (sibling.className === topCandidate.className && topCandidate.className !== "") - contentBonus += topCandidate.readability.contentScore * 0.2; + // Give a bonus if sibling nodes and top candidates have the example same classname + if (sibling.className === topCandidate.className && topCandidate.className !== '') + contentBonus += topCandidate.readability.contentScore * 0.2; - if (sibling.readability && + if (sibling.readability && ((sibling.readability.contentScore + contentBonus) >= siblingScoreThreshold)) { - append = true; - } else if (sibling.nodeName === "P") { - var linkDensity = this._getLinkDensity(sibling); - var nodeContent = this._getInnerText(sibling); - var nodeLength = nodeContent.length; + append = true; + } else if (sibling.nodeName === 'P') { + var linkDensity = this._getLinkDensity(sibling); + var nodeContent = this._getInnerText(sibling); + var nodeLength = nodeContent.length; - if (nodeLength > 80 && linkDensity < 0.25) { - append = true; - } else if (nodeLength < 80 && nodeLength > 0 && linkDensity === 0 && + if (nodeLength > 80 && linkDensity < 0.25) { + append = true; + } else if (nodeLength < 80 && nodeLength > 0 && linkDensity === 0 && nodeContent.search(/\.( |$)/) !== -1) { - append = true; - } - } - } + append = true; + } + } + } - if (append) { - this.log("Appending node:", sibling); + if (append) { + this.log('Appending node:', sibling); - if (this.ALTER_TO_DIV_EXCEPTIONS.indexOf(sibling.nodeName) === -1) { - // We have a node that isn't a common block level element, like a form or td tag. - // Turn it into a div so it doesn't get filtered out later by accident. - this.log("Altering sibling:", sibling, "to div."); + if (this.ALTER_TO_DIV_EXCEPTIONS.indexOf(sibling.nodeName) === -1) { + // We have a node that isn't a common block level element, like a form or td tag. + // Turn it into a div so it doesn't get filtered out later by accident. + this.log('Altering sibling:', sibling, 'to div.'); - sibling = this._setNodeTag(sibling, "DIV"); - } + sibling = this._setNodeTag(sibling, 'DIV'); + } - articleContent.appendChild(sibling); - // siblings is a reference to the children array, and - // sibling is removed from the array when we call appendChild(). - // As a result, we must revisit this index since the nodes - // have been shifted. - s -= 1; - sl -= 1; - } - } + articleContent.appendChild(sibling); + // siblings is a reference to the children array, and + // sibling is removed from the array when we call appendChild(). + // As a result, we must revisit this index since the nodes + // have been shifted. + s -= 1; + sl -= 1; + } + } - if (this._debug) - this.log("Article content pre-prep: " + articleContent.innerHTML); - // So we have all of the content that we need. Now we clean it up for presentation. - this._prepArticle(articleContent); - if (this._debug) - this.log("Article content post-prep: " + articleContent.innerHTML); + if (this._debug) + this.log('Article content pre-prep: ' + articleContent.innerHTML); + // So we have all of the content that we need. Now we clean it up for presentation. + this._prepArticle(articleContent); + if (this._debug) + this.log('Article content post-prep: ' + articleContent.innerHTML); - if (neededToCreateTopCandidate) { - // We already created a fake div thing, and there wouldn't have been any siblings left - // for the previous loop, so there's no point trying to create a new div, and then - // move all the children over. Just assign IDs and class names here. No need to append - // because that already happened anyway. - topCandidate.id = "readability-page-1"; - topCandidate.className = "page"; - } else { - var div = doc.createElement("DIV"); - div.id = "readability-page-1"; - div.className = "page"; - var children = articleContent.childNodes; - while (children.length) { - div.appendChild(children[0]); - } - articleContent.appendChild(div); - } + if (neededToCreateTopCandidate) { + // We already created a fake div thing, and there wouldn't have been any siblings left + // for the previous loop, so there's no point trying to create a new div, and then + // move all the children over. Just assign IDs and class names here. No need to append + // because that already happened anyway. + topCandidate.id = 'readability-page-1'; + topCandidate.className = 'page'; + } else { + var div = doc.createElement('DIV'); + div.id = 'readability-page-1'; + div.className = 'page'; + var children = articleContent.childNodes; + while (children.length) { + div.appendChild(children[0]); + } + articleContent.appendChild(div); + } - if (this._debug) - this.log("Article content after paging: " + articleContent.innerHTML); + if (this._debug) + this.log('Article content after paging: ' + articleContent.innerHTML); - var parseSuccessful = true; + var parseSuccessful = true; - // Now that we've gone through the full algorithm, check to see if - // we got any meaningful content. If we didn't, we may need to re-run - // grabArticle with different flags set. This gives us a higher likelihood of - // finding the content, and the sieve approach gives us a higher likelihood of - // finding the -right- content. - var textLength = this._getInnerText(articleContent, true).length; - if (textLength < this._charThreshold) { - parseSuccessful = false; - page.innerHTML = pageCacheHtml; + // Now that we've gone through the full algorithm, check to see if + // we got any meaningful content. If we didn't, we may need to re-run + // grabArticle with different flags set. This gives us a higher likelihood of + // finding the content, and the sieve approach gives us a higher likelihood of + // finding the -right- content. + var textLength = this._getInnerText(articleContent, true).length; + if (textLength < this._charThreshold) { + parseSuccessful = false; + page.innerHTML = pageCacheHtml; - if (this._flagIsActive(this.FLAG_STRIP_UNLIKELYS)) { - this._removeFlag(this.FLAG_STRIP_UNLIKELYS); - this._attempts.push({articleContent: articleContent, textLength: textLength}); - } else if (this._flagIsActive(this.FLAG_WEIGHT_CLASSES)) { - this._removeFlag(this.FLAG_WEIGHT_CLASSES); - this._attempts.push({articleContent: articleContent, textLength: textLength}); - } else if (this._flagIsActive(this.FLAG_CLEAN_CONDITIONALLY)) { - this._removeFlag(this.FLAG_CLEAN_CONDITIONALLY); - this._attempts.push({articleContent: articleContent, textLength: textLength}); - } else { - this._attempts.push({articleContent: articleContent, textLength: textLength}); - // No luck after removing flags, just return the longest text we found during the different loops - this._attempts.sort(function (a, b) { - return b.textLength - a.textLength; - }); + if (this._flagIsActive(this.FLAG_STRIP_UNLIKELYS)) { + this._removeFlag(this.FLAG_STRIP_UNLIKELYS); + this._attempts.push({articleContent: articleContent, textLength: textLength}); + } else if (this._flagIsActive(this.FLAG_WEIGHT_CLASSES)) { + this._removeFlag(this.FLAG_WEIGHT_CLASSES); + this._attempts.push({articleContent: articleContent, textLength: textLength}); + } else if (this._flagIsActive(this.FLAG_CLEAN_CONDITIONALLY)) { + this._removeFlag(this.FLAG_CLEAN_CONDITIONALLY); + this._attempts.push({articleContent: articleContent, textLength: textLength}); + } else { + this._attempts.push({articleContent: articleContent, textLength: textLength}); + // No luck after removing flags, just return the longest text we found during the different loops + this._attempts.sort(function (a, b) { + return b.textLength - a.textLength; + }); - // But first check if we actually have something - if (!this._attempts[0].textLength) { - return null; - } + // But first check if we actually have something + if (!this._attempts[0].textLength) { + return null; + } - articleContent = this._attempts[0].articleContent; - parseSuccessful = true; - } - } + articleContent = this._attempts[0].articleContent; + parseSuccessful = true; + } + } - if (parseSuccessful) { - // Find out text direction from ancestors of final top candidate. - var ancestors = [parentOfTopCandidate, topCandidate].concat(this._getNodeAncestors(parentOfTopCandidate)); - this._someNode(ancestors, function(ancestor) { - if (!ancestor.tagName) - return false; - var articleDir = ancestor.getAttribute("dir"); - if (articleDir) { - this._articleDir = articleDir; - return true; - } - return false; - }); - return articleContent; - } - } - }, + if (parseSuccessful) { + // Find out text direction from ancestors of final top candidate. + var ancestors = [parentOfTopCandidate, topCandidate].concat(this._getNodeAncestors(parentOfTopCandidate)); + this._someNode(ancestors, function(ancestor) { + if (!ancestor.tagName) + return false; + var articleDir = ancestor.getAttribute('dir'); + if (articleDir) { + this._articleDir = articleDir; + return true; + } + return false; + }); + return articleContent; + } + } + }, - /** + /** * Check whether the input string could be a byline. * This verifies that the input is a string, and that the length * is less than 100 chars. @@ -1204,112 +1204,112 @@ Readability.prototype = { * @param possibleByline {string} - a string to check whether its a byline. * @return Boolean - whether the input string is a byline. */ - _isValidByline: function(byline) { - if (typeof byline == "string" || byline instanceof String) { - byline = byline.trim(); - return (byline.length > 0) && (byline.length < 100); - } - return false; - }, + _isValidByline: function(byline) { + if (typeof byline == 'string' || byline instanceof String) { + byline = byline.trim(); + return (byline.length > 0) && (byline.length < 100); + } + return false; + }, - /** + /** * Attempts to get excerpt and byline metadata for the article. * * @return Object with optional "excerpt" and "byline" properties */ - _getArticleMetadata: function() { - var metadata = {}; - var values = {}; - var metaElements = this._doc.getElementsByTagName("meta"); + _getArticleMetadata: function() { + var metadata = {}; + var values = {}; + var metaElements = this._doc.getElementsByTagName('meta'); - // property is a space-separated list of values - var propertyPattern = /\s*(dc|dcterm|og|twitter)\s*:\s*(author|creator|description|title|site_name)\s*/gi; + // property is a space-separated list of values + var propertyPattern = /\s*(dc|dcterm|og|twitter)\s*:\s*(author|creator|description|title|site_name)\s*/gi; - // name is a single value - var namePattern = /^\s*(?:(dc|dcterm|og|twitter|weibo:(article|webpage))\s*[\.:]\s*)?(author|creator|description|title|site_name)\s*$/i; + // name is a single value + var namePattern = /^\s*(?:(dc|dcterm|og|twitter|weibo:(article|webpage))\s*[\.:]\s*)?(author|creator|description|title|site_name)\s*$/i; - // Find description tags. - this._forEachNode(metaElements, function(element) { - var elementName = element.getAttribute("name"); - var elementProperty = element.getAttribute("property"); - var content = element.getAttribute("content"); - if (!content) { - return; - } - var matches = null; - var name = null; + // Find description tags. + this._forEachNode(metaElements, function(element) { + var elementName = element.getAttribute('name'); + var elementProperty = element.getAttribute('property'); + var content = element.getAttribute('content'); + if (!content) { + return; + } + var matches = null; + var name = null; - if (elementProperty) { - matches = elementProperty.match(propertyPattern); - if (matches) { - for (var i = matches.length - 1; i >= 0; i--) { - // Convert to lowercase, and remove any whitespace - // so we can match below. - name = matches[i].toLowerCase().replace(/\s/g, ""); - // multiple authors - values[name] = content.trim(); - } - } - } - if (!matches && elementName && namePattern.test(elementName)) { - name = elementName; - if (content) { - // Convert to lowercase, remove any whitespace, and convert dots - // to colons so we can match below. - name = name.toLowerCase().replace(/\s/g, "").replace(/\./g, ":"); - values[name] = content.trim(); - } - } - }); + if (elementProperty) { + matches = elementProperty.match(propertyPattern); + if (matches) { + for (var i = matches.length - 1; i >= 0; i--) { + // Convert to lowercase, and remove any whitespace + // so we can match below. + name = matches[i].toLowerCase().replace(/\s/g, ''); + // multiple authors + values[name] = content.trim(); + } + } + } + if (!matches && elementName && namePattern.test(elementName)) { + name = elementName; + if (content) { + // Convert to lowercase, remove any whitespace, and convert dots + // to colons so we can match below. + name = name.toLowerCase().replace(/\s/g, '').replace(/\./g, ':'); + values[name] = content.trim(); + } + } + }); - // get title - metadata.title = values["dc:title"] || - values["dcterm:title"] || - values["og:title"] || - values["weibo:article:title"] || - values["weibo:webpage:title"] || - values["title"] || - values["twitter:title"]; + // get title + metadata.title = values['dc:title'] || + values['dcterm:title'] || + values['og:title'] || + values['weibo:article:title'] || + values['weibo:webpage:title'] || + values['title'] || + values['twitter:title']; - if (!metadata.title) { - metadata.title = this._getArticleTitle(); - } + if (!metadata.title) { + metadata.title = this._getArticleTitle(); + } - // get author - metadata.byline = values["dc:creator"] || - values["dcterm:creator"] || - values["author"]; + // get author + metadata.byline = values['dc:creator'] || + values['dcterm:creator'] || + values['author']; - // get description - metadata.excerpt = values["dc:description"] || - values["dcterm:description"] || - values["og:description"] || - values["weibo:article:description"] || - values["weibo:webpage:description"] || - values["description"] || - values["twitter:description"]; + // get description + metadata.excerpt = values['dc:description'] || + values['dcterm:description'] || + values['og:description'] || + values['weibo:article:description'] || + values['weibo:webpage:description'] || + values['description'] || + values['twitter:description']; - // get site name - metadata.siteName = values["og:site_name"]; + // get site name + metadata.siteName = values['og:site_name']; - return metadata; - }, + return metadata; + }, - /** + /** * Removes script tags from the document. * * @param Element **/ - _removeScripts: function(doc) { - this._removeNodes(doc.getElementsByTagName("script"), function(scriptNode) { - scriptNode.nodeValue = ""; - scriptNode.removeAttribute("src"); - return true; - }); - this._removeNodes(doc.getElementsByTagName("noscript")); - }, + _removeScripts: function(doc) { + this._removeNodes(doc.getElementsByTagName('script'), function(scriptNode) { + scriptNode.nodeValue = ''; + scriptNode.removeAttribute('src'); + return true; + }); + this._removeNodes(doc.getElementsByTagName('noscript')); + }, - /** + /** * Check if this node has only whitespace and a single element with given tag * Returns false if the DIV node contains non-empty text nodes * or if it contains no element with given tag or more than 1 element. @@ -1317,54 +1317,54 @@ Readability.prototype = { * @param Element * @param string tag of child element **/ - _hasSingleTagInsideElement: function(element, tag) { - // There should be exactly 1 element child with given tag - if (element.children.length != 1 || element.children[0].tagName !== tag) { - return false; - } + _hasSingleTagInsideElement: function(element, tag) { + // There should be exactly 1 element child with given tag + if (element.children.length != 1 || element.children[0].tagName !== tag) { + return false; + } - // And there should be no text nodes with real content - return !this._someNode(element.childNodes, function(node) { - return node.nodeType === this.TEXT_NODE && + // And there should be no text nodes with real content + return !this._someNode(element.childNodes, function(node) { + return node.nodeType === this.TEXT_NODE && this.REGEXPS.hasContent.test(node.textContent); - }); - }, + }); + }, - _isElementWithoutContent: function(node) { - return node.nodeType === this.ELEMENT_NODE && + _isElementWithoutContent: function(node) { + return node.nodeType === this.ELEMENT_NODE && node.textContent.trim().length == 0 && (node.children.length == 0 || - node.children.length == node.getElementsByTagName("br").length + node.getElementsByTagName("hr").length); - }, + node.children.length == node.getElementsByTagName('br').length + node.getElementsByTagName('hr').length); + }, - /** + /** * Determine whether element has any children block level elements. * * @param Element */ - _hasChildBlockElement: function (element) { - return this._someNode(element.childNodes, function(node) { - return this.DIV_TO_P_ELEMS.indexOf(node.tagName) !== -1 || + _hasChildBlockElement: function (element) { + return this._someNode(element.childNodes, function(node) { + return this.DIV_TO_P_ELEMS.indexOf(node.tagName) !== -1 || this._hasChildBlockElement(node); - }); - }, + }); + }, - /*** + /*** * Determine if a node qualifies as phrasing content. * https://developer.mozilla.org/en-US/docs/Web/Guide/HTML/Content_categories#Phrasing_content **/ - _isPhrasingContent: function(node) { - return node.nodeType === this.TEXT_NODE || this.PHRASING_ELEMS.indexOf(node.tagName) !== -1 || - ((node.tagName === "A" || node.tagName === "DEL" || node.tagName === "INS") && + _isPhrasingContent: function(node) { + return node.nodeType === this.TEXT_NODE || this.PHRASING_ELEMS.indexOf(node.tagName) !== -1 || + ((node.tagName === 'A' || node.tagName === 'DEL' || node.tagName === 'INS') && this._everyNode(node.childNodes, this._isPhrasingContent)); - }, + }, - _isWhitespace: function(node) { - return (node.nodeType === this.TEXT_NODE && node.textContent.trim().length === 0) || - (node.nodeType === this.ELEMENT_NODE && node.tagName === "BR"); - }, + _isWhitespace: function(node) { + return (node.nodeType === this.TEXT_NODE && node.textContent.trim().length === 0) || + (node.nodeType === this.ELEMENT_NODE && node.tagName === 'BR'); + }, - /** + /** * Get the inner text of a node - cross browser compatibly. * This also strips out any excess whitespace to be found. * @@ -1372,113 +1372,113 @@ Readability.prototype = { * @param Boolean normalizeSpaces (default: true) * @return string **/ - _getInnerText: function(e, normalizeSpaces) { - normalizeSpaces = (typeof normalizeSpaces === "undefined") ? true : normalizeSpaces; - var textContent = e.textContent.trim(); + _getInnerText: function(e, normalizeSpaces) { + normalizeSpaces = (typeof normalizeSpaces === 'undefined') ? true : normalizeSpaces; + var textContent = e.textContent.trim(); - if (normalizeSpaces) { - return textContent.replace(this.REGEXPS.normalize, " "); - } - return textContent; - }, + if (normalizeSpaces) { + return textContent.replace(this.REGEXPS.normalize, ' '); + } + return textContent; + }, - /** + /** * Get the number of times a string s appears in the node e. * * @param Element * @param string - what to split on. Default is "," * @return number (integer) **/ - _getCharCount: function(e, s) { - s = s || ","; - return this._getInnerText(e).split(s).length - 1; - }, + _getCharCount: function(e, s) { + s = s || ','; + return this._getInnerText(e).split(s).length - 1; + }, - /** + /** * Remove the style attribute on every e and under. * TODO: Test if getElementsByTagName(*) is faster. * * @param Element * @return void **/ - _cleanStyles: function(e) { - if (!e || e.tagName.toLowerCase() === "svg") - return; + _cleanStyles: function(e) { + if (!e || e.tagName.toLowerCase() === 'svg') + return; - // Remove `style` and deprecated presentational attributes - for (var i = 0; i < this.PRESENTATIONAL_ATTRIBUTES.length; i++) { - e.removeAttribute(this.PRESENTATIONAL_ATTRIBUTES[i]); - } + // Remove `style` and deprecated presentational attributes + for (var i = 0; i < this.PRESENTATIONAL_ATTRIBUTES.length; i++) { + e.removeAttribute(this.PRESENTATIONAL_ATTRIBUTES[i]); + } - if (this.DEPRECATED_SIZE_ATTRIBUTE_ELEMS.indexOf(e.tagName) !== -1) { - e.removeAttribute("width"); - e.removeAttribute("height"); - } + if (this.DEPRECATED_SIZE_ATTRIBUTE_ELEMS.indexOf(e.tagName) !== -1) { + e.removeAttribute('width'); + e.removeAttribute('height'); + } - var cur = e.firstElementChild; - while (cur !== null) { - this._cleanStyles(cur); - cur = cur.nextElementSibling; - } - }, + var cur = e.firstElementChild; + while (cur !== null) { + this._cleanStyles(cur); + cur = cur.nextElementSibling; + } + }, - /** + /** * Get the density of links as a percentage of the content * This is the amount of text that is inside a link divided by the total text in the node. * * @param Element * @return number (float) **/ - _getLinkDensity: function(element) { - var textLength = this._getInnerText(element).length; - if (textLength === 0) - return 0; + _getLinkDensity: function(element) { + var textLength = this._getInnerText(element).length; + if (textLength === 0) + return 0; - var linkLength = 0; + var linkLength = 0; - // XXX implement _reduceNodeList? - this._forEachNode(element.getElementsByTagName("a"), function(linkNode) { - linkLength += this._getInnerText(linkNode).length; - }); + // XXX implement _reduceNodeList? + this._forEachNode(element.getElementsByTagName('a'), function(linkNode) { + linkLength += this._getInnerText(linkNode).length; + }); - return linkLength / textLength; - }, + return linkLength / textLength; + }, - /** + /** * Get an elements class/id weight. Uses regular expressions to tell if this * element looks good or bad. * * @param Element * @return number (Integer) **/ - _getClassWeight: function(e) { - if (!this._flagIsActive(this.FLAG_WEIGHT_CLASSES)) - return 0; + _getClassWeight: function(e) { + if (!this._flagIsActive(this.FLAG_WEIGHT_CLASSES)) + return 0; - var weight = 0; + var weight = 0; - // Look for a special classname - if (typeof(e.className) === "string" && e.className !== "") { - if (this.REGEXPS.negative.test(e.className)) - weight -= 25; + // Look for a special classname + if (typeof(e.className) === 'string' && e.className !== '') { + if (this.REGEXPS.negative.test(e.className)) + weight -= 25; - if (this.REGEXPS.positive.test(e.className)) - weight += 25; - } + if (this.REGEXPS.positive.test(e.className)) + weight += 25; + } - // Look for a special ID - if (typeof(e.id) === "string" && e.id !== "") { - if (this.REGEXPS.negative.test(e.id)) - weight -= 25; + // Look for a special ID + if (typeof(e.id) === 'string' && e.id !== '') { + if (this.REGEXPS.negative.test(e.id)) + weight -= 25; - if (this.REGEXPS.positive.test(e.id)) - weight += 25; - } + if (this.REGEXPS.positive.test(e.id)) + weight += 25; + } - return weight; - }, + return weight; + }, - /** + /** * Clean a node of all elements of type "tag". * (Unless it's a youtube/vimeo video. People love movies.) * @@ -1486,30 +1486,30 @@ Readability.prototype = { * @param string tag to clean * @return void **/ - _clean: function(e, tag) { - var isEmbed = ["object", "embed", "iframe"].indexOf(tag) !== -1; + _clean: function(e, tag) { + var isEmbed = ['object', 'embed', 'iframe'].indexOf(tag) !== -1; - this._removeNodes(e.getElementsByTagName(tag), function(element) { - // Allow youtube and vimeo videos through as people usually want to see those. - if (isEmbed) { - // First, check the elements attributes to see if any of them contain youtube or vimeo - for (var i = 0; i < element.attributes.length; i++) { - if (this.REGEXPS.videos.test(element.attributes[i].value)) { - return false; - } - } + this._removeNodes(e.getElementsByTagName(tag), function(element) { + // Allow youtube and vimeo videos through as people usually want to see those. + if (isEmbed) { + // First, check the elements attributes to see if any of them contain youtube or vimeo + for (var i = 0; i < element.attributes.length; i++) { + if (this.REGEXPS.videos.test(element.attributes[i].value)) { + return false; + } + } - // For embed with