extern/pdf-to-markdown
1
0
Fork 0
mirror of https://github.com/jzillmann/pdf-to-markdown.git synced 2025-06-21 01:58:01 +02:00
Code Issues Packages Projects Releases Wiki Activity

remove width and height from removing repetitive items to increase accuracy

Browse Source
This commit is contained in:
Johannes Zillmann 2017-02-03 12:37:39 +01:00
parent 91087d550b
commit 12f6105d90
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
src/javascript/models/transformations/RemoveRepetitiveElements.jsx
View File

@ -21,7 +21,7 @@ function hashCodeIgnoringNumbers(string) {
function combineCoordinates(textItem) {
var hashCode = hashCodeIgnoringNumbers(textItem.text);
return `${textItem.x}-${textItem.y}-${textItem.width}-${textItem.height}-${hashCode}`;
return `${textItem.x}-${textItem.y}-${hashCode}`;
}
// Remove elements with similar content on same page positions, like page numbers, licenes information, etc...
@ -37,7 +37,7 @@ export default class RemoveRepetitiveElements extends Transformation {
transform(pages:PdfPage[]) {
//build repetition counts for every element
var repetitionCounts = {};
const repetitionCounts = {};
pages.forEach(pdfPage => {
pdfPage.textItems.forEach(textItem => {
var combinedCoordinates = combineCoordinates(textItem);