diff options
| author | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-04-10 21:30:40 +0000 |
|---|---|---|
| committer | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-04-10 21:30:40 +0000 |
| commit | 133a45c109da5310add55824db21af5239951f93 (patch) | |
| tree | ba6ac4c0a950a0dda56451944315d66409923918 /test/lua/unit/html.lua | |
| parent | Initial commit. (diff) | |
| download | rspamd-133a45c109da5310add55824db21af5239951f93.tar.xz rspamd-133a45c109da5310add55824db21af5239951f93.zip | |
Adding upstream version 3.8.1.upstream/3.8.1upstream
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'test/lua/unit/html.lua')
| -rw-r--r-- | test/lua/unit/html.lua | 113 |
1 files changed, 113 insertions, 0 deletions
diff --git a/test/lua/unit/html.lua b/test/lua/unit/html.lua new file mode 100644 index 0000000..81c52ec --- /dev/null +++ b/test/lua/unit/html.lua @@ -0,0 +1,113 @@ +context("HTML processing", function() + local rspamd_util = require("rspamd_util") + local logger = require("rspamd_logger") + local cases = { + -- Entities + {[[<html><body>.firebaseapp.com</body></html>]], + [[.firebaseapp.com]]}, + {[[ +<?xml version="1.0" encoding="iso-8859-1"?> + <!DOCTYPE html + PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" + "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"> + <html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en"> + <head> + <title> + Wikibooks + </title> + </head> + <body> + <p> + Hello, world! + + </p> + </body> + </html>]], 'Hello, world!\n'}, + {[[ +<!DOCTYPE html> +<html lang="en"> + <head> + <meta charset="utf-8"> + <title>title</title> + <link rel="stylesheet" href="style.css"> + <script src="script.js"></script> + <style><!-- +- -a -a -a -- --- - + --></head> + <body> + <!-- page content --> + Hello, world! + </body> +</html> + ]], 'Hello, world!'}, + {[[ +<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!<br>test</br><br>content</hr>more content<br> + <div> + content inside div + </div> + </body> +</html> + ]], 'Hello, world!\ntest\ncontentmore content\ncontent inside div\n'}, + {[[ +<html lang="en"> + <head> + <meta charset="utf-8"> + <title>title</title> + <link rel="stylesheet" href="style.css"> + <script src="script.js"></script> + </head> + <body> + <!-- tabular content --> + <table> + content + </table> + <table> + <tr> + <th>heada</th> + <th>headb</th> + </tr> + <tr> + <td>data1</td> + <td>data2</td> + </tr> + </table> + + </body> +</html> + ]], 'content\nheada headb\ndata1 data2\n'}, + {[[ +<html lang="en"> + <head> + <meta charset="utf-8"> + <title>title</title> + <link rel="stylesheet" href="style.css"> + <script src="script.js"></script> + </head> + <body> + <!-- escape content --> + a b a > b a < b a & b 'a "a" + </body> +</html> + ]], 'a b a > b a < b a & b \'a "a"'}, + } + + 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) |