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

Make summarization work for text/plain content #531

Merged
merged 1 commit into from
Oct 30, 2023
Merged

Make summarization work for text/plain content #531

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
19 changes: 15 additions & 4 deletions src/utils/get-core-content-text.mjs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,6 +15,9 @@ const adapters = {
}

function findLargestElement(e) {
if (!e) {
return null
}
let maxArea = 0
let largestElement = null
const limitedArea = 0.8 * getArea(e)
Expand Down Expand Up @@ -50,14 +53,22 @@ export function getCoreContentText() {
console.log(largestElement)
console.log(secondLargestElement)

if (!largestElement) return
function getTextFrom(e) {
return e.innerText || e.textContent
}

let ret
if (secondLargestElement && getArea(secondLargestElement) > 0.5 * getArea(largestElement)) {
ret = secondLargestElement.innerText || secondLargestElement.textContent
if (!largestElement) {
ret = getTextFrom(document.body)
console.log('use document.body')
} else if (
secondLargestElement &&
getArea(secondLargestElement) > 0.5 * getArea(largestElement)
) {
ret = getTextFrom(secondLargestElement)
console.log('use second')
} else {
ret = largestElement.innerText || largestElement.textContent
ret = getTextFrom(largestElement)
console.log('use first')
}
return ret.trim().replaceAll(' ', '').replaceAll('\n\n', '').replaceAll(',,', '')
Expand Down