Skip to content

A fast, helpful, and open-source document parser

remove some comments

Logan Markewich9d13385f4e58
diff --git a/src/processing/bbox.ts b/src/processing/bbox.ts
index e5746c8..2ef15be 100644
--- a/src/processing/bbox.ts
+++ b/src/processing/bbox.ts
@@ -39,8 +39,6 @@ const MIN_RENDERED_AREA = 200;
/**
* Filters images that should not be OCR'd based on various criteria.
* Returns the filtered array of images that should be processed.
- *
- * Ported from llamaparse's filterImagesForOCR function.
*/
export function filterImagesForOCR(
images: Image[],
diff --git a/src/processing/cleanText.ts b/src/processing/cleanText.ts
index aec9a31..551ec6e 100644
--- a/src/processing/cleanText.ts
+++ b/src/processing/cleanText.ts
@@ -7,8 +7,6 @@ import { ParsedPage, LiteParseConfig } from '../core/types.js';
* - Top margin (empty lines at start)
* - Bottom margin (empty lines at end)
* - Right margin (trailing whitespace on each line)
- *
- * Ported from llamaparse's detectAndRemoveMargin function.
*/
function detectAndRemoveMarginOnPage(page: ParsedPage): void {
const lines = page.text.split('\n');
diff --git a/src/vendor/pdfjs/README.md b/src/vendor/pdfjs/README.md
index cf6ead9..e69de29 100644
--- a/src/vendor/pdfjs/README.md
+++ b/src/vendor/pdfjs/README.md
@@ -1,5 +0,0 @@
-
-
-This is the llamaParse Forked version.
-
-use generic (not legacy build) from https://github.com/run-llama/llama-pdf-js-fork
\ No newline at end of file