Module:CanonicalForms

Documentation for this module may be created at Module:CanonicalForms/doc

-- Module:CanonicalForms
-- Provides normalization functions by stripping wiki-link markup and mapping input to canonical values.
-- Templates supply mapping tables, each containing:
--   • canonical: The standard display value.
--   • synonyms:  Case-insensitive alternatives mapping to the canonical value.
--   • [optional] css: An associated CSS class.
--   • [optional] category: A category string for auto-assignment.
--
-- The normalize function removes wiki markup, converts input to lowercase, 
-- and matches it against provided synonyms, returning the canonical value, css, and category if applicable.
--
-- Example usage:
--   local mapping = {
--     { canonical = "gTLD", synonyms = {"generic", "gtld", "tld"} },
--     { canonical = "ccTLD", synonyms = {"cctld", "country", "cc"} }
--   }
--   local canonical, css, category = require('Module:CanonicalForms').normalize(inputString, mapping)

local CanonicalForms = {}

--- Normalizes an input string based on a mapping table.
-- Strips wiki-link markup, converts to lowercase, and returns the canonical value.
-- @param input The input string to normalize.
-- @param mappingTable An array of mapping groups.
-- @return canonical The matched canonical value, or the cleaned input if no match is found.
-- @return css (optional) An associated CSS class if available.
-- @return category (optional) An associated category string if available.
function CanonicalForms.normalize(input, mappingTable)
    if not input or input == "" then
        return nil, nil, nil
    end

    -- Remove wiki-link markup: [[Brand TLD]] → "Brand TLD"
    local cleanInput = input:gsub("%[%[([^|%]]+)|?[^%]]*%]%]", "%1"):lower()

    for _, group in ipairs(mappingTable) do
        for _, syn in ipairs(group.synonyms or {}) do
            if cleanInput == syn:lower() then
                return group.canonical, group.css, group.category
            end
        end
    end

    return cleanInput, nil, nil
end

return CanonicalForms

Generic Top-level Domain

Country code top-level domain. Determined by "ISO 3166-1: Codes for the representation of names of countries and their subdivisions — Part 1: Country codes".

Top-Level Domain