Archives
/
readability
2
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Fix quotes

Browse Source
pull/471/head
Gijs Kruitbosch 6 years ago
parent 7d03bec52d
commit d9f7bb2965
2 changed files with 60 additions and 60 deletions
Show Stats Download Patch File Download Diff File

4
JSDOMParser.js
Unescape Escape View File

@ -684,7 +684,7 @@
// the attribute value will be HTML escaped.
var val = attr.value;
var quote = (val.indexOf('"') === -1 ? '"' : "'");
arr.push(" " + attr.name + '=' + quote + val + quote);
arr.push(" " + attr.name + "=" + quote + val + quote);
}
if (child.localName in voidElems && !child.childNodes.length) {
@ -963,7 +963,7 @@
strBuf.push(c);
c = this.nextChar();
}
var tag = strBuf.join('');
var tag = strBuf.join("");
if (!tag)
return false;

116
Readability.js
Unescape Escape View File

@ -260,7 +260,7 @@ Readability.prototype = {
_getAllNodesWithTag: function(node, tagNames) {
if (node.querySelectorAll) {
return node.querySelectorAll(tagNames.join(','));
return node.querySelectorAll(tagNames.join(","));
}
return [].concat.apply([], tagNames.map(function(tag) {
var collection = node.getElementsByTagName(tag);
@ -359,7 +359,7 @@ Readability.prototype = {
// If they had an element with id "title" in their HTML
if (typeof curTitle !== "string")
curTitle = origTitle = this._getInnerText(doc.getElementsByTagName('title')[0]);
curTitle = origTitle = this._getInnerText(doc.getElementsByTagName("title")[0]);
} catch (e) {/* ignore exceptions setting the title. */}
var titleHadHierarchicalSeparators = false;
@ -370,18 +370,18 @@ Readability.prototype = {
// If there's a separator in the title, first remove the final part
if ((/ [\|\-\\\/>»] /).test(curTitle)) {
titleHadHierarchicalSeparators = / [\\\/>»] /.test(curTitle);
curTitle = origTitle.replace(/(.*)[\|\-\\\/>»] .*/gi, '$1');
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) {
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')
doc.getElementsByTagName("h1"),
doc.getElementsByTagName("h2")
);
var trimmedTitle = curTitle.trim();
var match = this._someNode(headings, function(heading) {
@ -390,19 +390,19 @@ Readability.prototype = {
// If we don't, let's extract the title out of the original title string.
if (!match) {
curTitle = origTitle.substring(origTitle.lastIndexOf(':') + 1);
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);
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) {
} else if (wordCount(origTitle.substr(0, origTitle.indexOf(":"))) > 5) {
curTitle = origTitle;
}
}
} else if (curTitle.length > 150 || curTitle.length < 15) {
var hOnes = doc.getElementsByTagName('h1');
var hOnes = doc.getElementsByTagName("h1");
if (hOnes.length === 1)
curTitle = this._getInnerText(hOnes[0]);
@ -569,7 +569,7 @@ Readability.prototype = {
// 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');
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) {
@ -599,12 +599,12 @@ Readability.prototype = {
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;
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 iframeCount = paragraph.getElementsByTagName("iframe").length;
var totalCount = imgCount + embedCount + objectCount + iframeCount;
return totalCount === 0 && !this._getInnerText(paragraph, false);
@ -641,34 +641,34 @@ Readability.prototype = {
node.readability = {"contentScore": 0};
switch (node.tagName) {
case 'DIV':
case "DIV":
node.readability.contentScore += 5;
break;
case 'PRE':
case 'TD':
case 'BLOCKQUOTE':
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':
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':
case "H1":
case "H2":
case "H3":
case "H4":
case "H5":
case "H6":
case "TH":
node.readability.contentScore -= 5;
break;
}
@ -817,7 +817,7 @@ Readability.prototype = {
if (p !== null) {
p.appendChild(childNode);
} else if (!this._isWhitespace(childNode)) {
p = doc.createElement('p');
p = doc.createElement("p");
node.replaceChild(p, childNode);
p.appendChild(childNode);
}
@ -853,7 +853,7 @@ Readability.prototype = {
**/
var candidates = [];
this._forEachNode(elementsToScore, function(elementToScore) {
if (!elementToScore.parentNode || typeof(elementToScore.parentNode.tagName) === 'undefined')
if (!elementToScore.parentNode || typeof(elementToScore.parentNode.tagName) === "undefined")
return;
// If this paragraph is less than 25 characters, don't even count it.
@ -872,17 +872,17 @@ Readability.prototype = {
contentScore += 1;
// Add points for any commas within this paragraph.
contentScore += innerText.split(',').length;
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);
// Initialize and score ancestors.
this._forEachNode(ancestors, function(ancestor, level) {
if (!ancestor.tagName || !ancestor.parentNode || typeof(ancestor.parentNode.tagName) === 'undefined')
if (!ancestor.tagName || !ancestor.parentNode || typeof(ancestor.parentNode.tagName) === "undefined")
return;
if (typeof(ancestor.readability) === 'undefined') {
if (typeof(ancestor.readability) === "undefined") {
this._initializeNode(ancestor);
candidates.push(ancestor);
}
@ -913,7 +913,7 @@ Readability.prototype = {
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];
@ -1032,8 +1032,8 @@ Readability.prototype = {
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;
@ -1067,7 +1067,7 @@ Readability.prototype = {
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.');
this.log("Altering sibling:", sibling, "to div.");
sibling = this._setNodeTag(sibling, "DIV");
}
@ -1175,7 +1175,7 @@ Readability.prototype = {
* @return Boolean - whether the input string is a byline.
*/
_isValidByline: function(byline) {
if (typeof byline == 'string' || byline instanceof String) {
if (typeof byline == "string" || byline instanceof String) {
byline = byline.trim();
return (byline.length > 0) && (byline.length < 100);
}
@ -1221,7 +1221,7 @@ Readability.prototype = {
if (content) {
// Convert to lowercase and remove any whitespace
// so we can match below.
name = name.toLowerCase().replace(/\s/g, '');
name = name.toLowerCase().replace(/\s/g, "");
values[name] = content.trim();
}
}
@ -1257,12 +1257,12 @@ Readability.prototype = {
* @param Element
**/
_removeScripts: function(doc) {
this._removeNodes(doc.getElementsByTagName('script'), function(scriptNode) {
this._removeNodes(doc.getElementsByTagName("script"), function(scriptNode) {
scriptNode.nodeValue = "";
scriptNode.removeAttribute('src');
scriptNode.removeAttribute("src");
return true;
});
this._removeNodes(doc.getElementsByTagName('noscript'));
this._removeNodes(doc.getElementsByTagName("noscript"));
},
/**
@ -1329,7 +1329,7 @@ Readability.prototype = {
* @return string
**/
_getInnerText: function(e, normalizeSpaces) {
normalizeSpaces = (typeof normalizeSpaces === 'undefined') ? true : normalizeSpaces;
normalizeSpaces = (typeof normalizeSpaces === "undefined") ? true : normalizeSpaces;
var textContent = e.textContent.trim();
if (normalizeSpaces) {
@ -1358,7 +1358,7 @@ Readability.prototype = {
* @return void
**/
_cleanStyles: function(e) {
if (!e || e.tagName.toLowerCase() === 'svg')
if (!e || e.tagName.toLowerCase() === "svg")
return;
// Remove `style` and deprecated presentational attributes
@ -1367,8 +1367,8 @@ Readability.prototype = {
}
if (this.DEPRECATED_SIZE_ATTRIBUTE_ELEMS.indexOf(e.tagName) !== -1) {
e.removeAttribute('width');
e.removeAttribute('height');
e.removeAttribute("width");
e.removeAttribute("height");
}
var cur = e.firstElementChild;
@ -1414,7 +1414,7 @@ Readability.prototype = {
var weight = 0;
// Look for a special classname
if (typeof(e.className) === 'string' && e.className !== '') {
if (typeof(e.className) === "string" && e.className !== "") {
if (this.REGEXPS.negative.test(e.className))
weight -= 25;
@ -1423,7 +1423,7 @@ Readability.prototype = {
}
// Look for a special ID
if (typeof(e.id) === 'string' && e.id !== '') {
if (typeof(e.id) === "string" && e.id !== "") {
if (this.REGEXPS.negative.test(e.id))
weight -= 25;
@ -1612,7 +1612,7 @@ Readability.prototype = {
return true;
}
if (this._getCharCount(node, ',') < 10) {
if (this._getCharCount(node, ",") < 10) {
// If there are not very many commas, and the number of
// non-paragraph elements is more than paragraphs or other
// ominous signs, remove the element.
@ -1672,7 +1672,7 @@ Readability.prototype = {
**/
_cleanHeaders: function(e) {
for (var headerIndex = 1; headerIndex < 3; headerIndex += 1) {
this._removeNodes(e.getElementsByTagName('h' + headerIndex), function (header) {
this._removeNodes(e.getElementsByTagName("h" + headerIndex), function (header) {
return this._getClassWeight(header) < 0;
});
}

Write Preview
Loading…
Cancel
Save