From 47eed3a94f23507894bfa2f2c56f5bac51b82d88 Mon Sep 17 00:00:00 2001 From: Jan Lukas Gernert Date: Sun, 19 Mar 2023 19:54:41 +0100 Subject: [PATCH] add hidden notes test --- .../readability/hidden-nodes/expected.html | 11 +++++++ .../readability/hidden-nodes/source.html | 29 +++++++++++++++++++ src/full_text_parser/readability/tests.rs | 5 ++++ 3 files changed, 45 insertions(+) create mode 100644 resources/tests/readability/hidden-nodes/expected.html create mode 100644 resources/tests/readability/hidden-nodes/source.html diff --git a/resources/tests/readability/hidden-nodes/expected.html b/resources/tests/readability/hidden-nodes/expected.html new file mode 100644 index 0000000..b8695a0 --- /dev/null +++ b/resources/tests/readability/hidden-nodes/expected.html @@ -0,0 +1,11 @@ +
+

+ Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. +

+

+ Secondary header +

+

+ Third header +

+
diff --git a/resources/tests/readability/hidden-nodes/source.html b/resources/tests/readability/hidden-nodes/source.html new file mode 100644 index 0000000..e0699a0 --- /dev/null +++ b/resources/tests/readability/hidden-nodes/source.html @@ -0,0 +1,29 @@ + + + + + + Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt + + + +

+ Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt +

+

+ Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. +

+

+ Secondary header +

+

+ Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. +

+

+ Third header +

+ + + diff --git a/src/full_text_parser/readability/tests.rs b/src/full_text_parser/readability/tests.rs index d8012f5..9c7dfa5 100644 --- a/src/full_text_parser/readability/tests.rs +++ b/src/full_text_parser/readability/tests.rs @@ -231,6 +231,11 @@ async fn herald_sun_1() { run_test("herald-sun-1").await } +#[tokio::test] +async fn hidden_nodes() { + run_test("hidden-nodes").await +} + #[tokio::test] async fn webmd_1() { run_test("webmd-1").await