From 67da99861f5ff0a65016cbc7904d37fb3aa4c013 Mon Sep 17 00:00:00 2001 From: Teddy Wing Date: Sat, 2 Nov 2019 03:42:46 +0100 Subject: get_urls_from_pdf: Test extracted URLs Add a test with a simple text-only PDF with three URLs. Currently I'm getting the following failure, so visibly the order is not necessarily the same as the visible order, and multi-line hyperlinks can be encoded as two link areas: ---- tests::get_urls_from_pdf_extracts_urls_from_pdf stdout ---- thread 'tests::get_urls_from_pdf_extracts_urls_from_pdf' panicked at 'assertion failed: `(left == right)` left: `["http://www.gutenberg.org/ebooks/11", "https://ia800908.us.archive.org/6/items/alicesadventures19033gut/19033-h/images/i002.jpg", "https://science.nasa.gov/news-article/black-hole-image-makes-history"]`, right: `["http://www.gutenberg.org/ebooks/11", "https://science.nasa.gov/news-article/black-hole-image-makes-history", "https://ia800908.us.archive.org/6/items/alicesadventures19033gut/19033-h/images/i002.jpg", "https://ia800908.us.archive.org/6/items/alicesadventures19033gut/19033-h/images/i002.jpg"]`', src/lib.rs:65:9 --- src/lib.rs | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'src') diff --git a/src/lib.rs b/src/lib.rs index 2a59906..c7f6e94 100644 --- a/src/lib.rs +++ b/src/lib.rs @@ -46,3 +46,22 @@ pub fn get_urls_from_pdf>(path: P) -> Result> { Ok(urls) } + + +#[cfg(test)] +mod tests { + use super::*; + + #[test] + fn get_urls_from_pdf_extracts_urls_from_pdf() { + let expected = vec![ + "http://www.gutenberg.org/ebooks/11", + "https://ia800908.us.archive.org/6/items/alicesadventures19033gut/19033-h/images/i002.jpg", + "https://science.nasa.gov/news-article/black-hole-image-makes-history", + ]; + + let urls = get_urls_from_pdf("testdata/Alice's Adventures in Wonderland.pdf"); + + assert_eq!(expected, urls.unwrap()); + } +} -- cgit v1.2.3