view mod_ogp/test.lua @ 5119:048e339706ba

mod_rest: Remove manual reference expansion in schema This hack was originally added to reduce the number of definitions of common attributes (type, to, from etc) and payloads (e.g. delay). This predated pointers and references, and until now was needed because parsing picked out the correct stanza kind from the schema, which broke internal references. Removing this hack paves the way for allowing the schema to be configured or customized more easily.
author Kim Alvefur <zash@zash.se>
date Tue, 20 Dec 2022 21:48:28 +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