diff options
author | Vsevolod Stakhov <vsevolod@highsecure.ru> | 2021-06-28 14:01:25 +0100 |
---|---|---|
committer | Vsevolod Stakhov <vsevolod@highsecure.ru> | 2021-06-28 14:01:40 +0100 |
commit | ee9655827a5d7daef68160c4c969d91e2ff73aa3 (patch) | |
tree | 0a39eaea8a0819d8633426c2b3c11c03b18250db | |
parent | ddda2007228617f8689f815e6a5f944b284ec5b0 (diff) | |
download | rspamd-ee9655827a5d7daef68160c4c969d91e2ff73aa3.tar.gz rspamd-ee9655827a5d7daef68160c4c969d91e2ff73aa3.zip |
[Test] Some fixes to html unit tests
-rw-r--r-- | test/lua/unit/html.lua | 38 |
1 files changed, 10 insertions, 28 deletions
diff --git a/test/lua/unit/html.lua b/test/lua/unit/html.lua index 79d55502e..8582c4edc 100644 --- a/test/lua/unit/html.lua +++ b/test/lua/unit/html.lua @@ -1,31 +1,11 @@ context("HTML processing", function() local rspamd_util = require("rspamd_util") local logger = require("rspamd_logger") - - test("Extract text from HTML", function() - local cases = { + local cases = { -- Entities {[[<html><body>.firebaseapp.com</body></html>]], [[.firebaseapp.com]]}, {[[ -<!DOCTYPE html> -<html lang="en"> - <head> - <meta charset="utf-8"> - <title>title</title> - <link rel="stylesheet" href="style.css"> - <script src="script.js"></script> - </head> - <body> - <!-- page content --> - Hello, world! <b>test</b> - <p>data<> - </P> - <b>stuff</p>? - </body> -</html> - ]], "Hello, world! test\r\ndata\r\nstuff\r\n?"}, - {[[ <?xml version="1.0" encoding="iso-8859-1"?> <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" @@ -42,7 +22,7 @@ context("HTML processing", function() </p> </body> - </html>]], 'Hello, world!\r\n'}, + </html>]], 'Hello, world!\n'}, {[[ <!DOCTYPE html> <html lang="en"> @@ -76,7 +56,7 @@ context("HTML processing", function() </div> </body> </html> - ]], 'Hello, world!\r\ntest\r\ncontent\r\nmore content\r\ncontent inside div\r\n'}, + ]], 'Hello, world!\ntest\ncontent\nmore content\ncontent inside div\n'}, {[[ <html lang="en"> <head> @@ -103,7 +83,7 @@ context("HTML processing", function() </body> </html> - ]], 'content\r\nheada headb\r\ndata1 data2\r\n'}, + ]], 'content\nheada headb\ndata1 data2\n'}, {[[ <html lang="en"> <head> @@ -118,14 +98,16 @@ context("HTML processing", function() </body> </html> ]], 'a b a > b a < b a & b \'a "a"'}, - } + } - for _,c in ipairs(cases) do + for i,c in ipairs(cases) do + test("Extract text from HTML " .. tostring(i), function() local t = rspamd_util.parse_html(c[1]) assert_not_nil(t) assert_equal(c[2], tostring(t), string.format("'%s' doesn't match with '%s'", c[2], t)) - end - end) + + end) + end end) |