view mod_ogp/test.lua @ 5536:96dec7681af8

mod_firewall: Update user marks to store instantly via map store The original approach was to keep marks in memory only, and persist them at shutdown. That saves I/O, at the cost of potentially losing marks on an unclean shutdown. This change persists marks instantly, which may have some performance overhead but should be more "correct". It also splits the marking/unmarking into an event which may be watched or even fired by other modules.
author Matthew Wild <mwild1@gmail.com>
date Thu, 08 Jun 2023 16:20:42 +0100
parents 38da10e4b593
children
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