File

mod_ogp/test.lua @ 5173:460f78654864

mod_muc_rtbl: also filter messages This was a bit tricky because we don't want to run the JIDs through SHA256 on each message. Took a while to come up with this simple plan of just caching the SHA256 of the JIDs on the occupants. This will leave some dirt in the occupants after unloading the module, but that should be ok; once they cycle the room, the hashes will be gone. This is direly needed, otherwise, there is a tight race between the moderation activities and the actors joining the room.
author Jonas Schäfer <jonas@wielicki.name>
date Tue, 21 Feb 2023 21:37:27 +0100
parent 4255:38da10e4b593
line wrap: on
line source

local html = [[
<meta property="og:title" content="Example 1 A">
<meta property=og:title content="Example 2 B">
<meta property="og:title" content="Example 3 C" >
<meta property="og:title" content="Example 4 D" />
<meta property="og:title" content="Example 5 E"/>
<meta property=og:title content=Example 6 F/>
<meta property="og:title" content= "Example 7 G" />
<meta property="og:title" itemprop="image primaryImageOfPage" content="Example 8 H" />
<meta property='og:title' content='Example 9 I' />
<meta content="Example 10 J" property="og:title" >
<meta content="Example 11 K" property="og:title">
<meta content="Example 12 L" property="og:title"/>
<meta content="Example 13 M" property="og:title" />
<meta content="Example 14 N" property=og:title >
<meta content=Example 15 O property=og:title >
<meta content= "Example 16 P" property="og:title" />
<meta content="Example 17 Q" itemprop="image primaryImageOfPage"  property="og:title" />
<meta content= 'Example 18 R' property='og:title' />
]]



local meta_pattern = [[<meta (.-)/?>]]
for match in html:gmatch(meta_pattern) do
    local property = match:match([[property=%s*["']?(og:.-)["']?%s]])
    if not property then
        property = match:match([[property=["']?(og:.-)["']$]])
    end

    local content = match:match([[content=%s*["'](.-)["']%s]])
    if not content then
        content = match:match([[content=["']?(.-)["']$]])
    end
    if not content then
        content = match:match([[content=(.-) property]])
    end
    if not content then
        content = match:match([[content=(.-)$]])
    end

    print(property, '\t', content, '\t', match .. "|")
end