From e1770cf3b0fd5eff3e69a8ec28c15018084eae73 Mon Sep 17 00:00:00 2001 From: Nathan Reiner Date: Thu, 6 Jul 2023 11:51:21 +0200 Subject: add extractors for docx, pptx, pdf, etc. --- src/text/pdf.rs | 5 +++++ 1 file changed, 5 insertions(+) create mode 100644 src/text/pdf.rs (limited to 'src/text/pdf.rs') diff --git a/src/text/pdf.rs b/src/text/pdf.rs new file mode 100644 index 0000000..efa441f --- /dev/null +++ b/src/text/pdf.rs @@ -0,0 +1,5 @@ +use crate::extractors::pdf; + +pub fn get_text(path : &str) -> String { + pdf::pdf2text(path).ok().unwrap_or_else(|| "".to_string()) +} -- cgit v1.2.3-70-g09d2