Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Clean up byline validation #905

Merged
merged 2 commits into from
Sep 26, 2024
Merged

Clean up byline validation #905

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
110c4ad
Clean up byline validation
JKingweb Aug 22, 2024
4128287
Make clearer that byline validity only cares about text length
JKingweb Aug 22, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
57 changes: 22 additions & 35 deletions Readability.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -978,27 +978,25 @@ Readability.prototype = {
return 1 - distanceB;
},

_checkByline(node, matchString) {
if (this._articleByline || this._metadata.byline) {
return false;
}

if (node.getAttribute !== undefined) {
var rel = node.getAttribute("rel");
var itemprop = node.getAttribute("itemprop");
}
/**
* Checks whether an element node contains a valid byline
*
* @param node {Element}
* @param matchString {string}
* @return boolean
*/
_isValidByline(node, matchString) {
var rel = node.getAttribute("rel");
var itemprop = node.getAttribute("itemprop");
var bylineLength = node.textContent.trim().length;

if (
return (
(rel === "author" ||
(itemprop && itemprop.includes("author")) ||
this.REGEXPS.byline.test(matchString)) &&
this._isValidByline(node.textContent)
) {
this._articleByline = node.textContent.trim();
return true;
}

return false;
!!bylineLength &&
bylineLength < 100
);
},

_getNodeAncestors(node, maxDepth) {
Expand Down Expand Up @@ -1073,8 +1071,13 @@ Readability.prototype = {
continue;
}

// Check to see if this node is a byline, and remove it if it is.
if (this._checkByline(node, matchString)) {
// If we don't have a byline yet check to see if this node is a byline; if it is store the byline and remove the node.
if (
!this._articleByline &&
!this._metadata.byline &&
this._isValidByline(node, matchString)
) {
this._articleByline = node.textContent.trim();
node = this._removeAndGetNext(node);
continue;
}
Expand Down Expand Up @@ -1573,22 +1576,6 @@ Readability.prototype = {
}
},

/**
* 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.
*
* @param possibleByline {string} - a string to check whether its a byline.
* @return Boolean - whether the input string is a byline.
*/
_isValidByline(byline) {
if (typeof byline == "string" || byline instanceof String) {
byline = byline.trim();
return !!byline.length && byline.length < 100;
}
return false;
},

/**
* Converts some of the common HTML entities in string to their corresponding characters.
*
Expand Down