Module:CanonicalForms

Documentation for this module may be created at Module:CanonicalForms/doc
-- Module:CanonicalForms
-- Normalizes strings by removing wiki markup and mapping them to canonical values.
-- Mapping tables include:
--   * canonical: Standard display value.
--   * synonyms: Synonyms (case-insensitive) mapped to canonical.
--   * [optional] css: Associated CSS class.
--   * [optional] category: Auto-assignment category.
--
-- Example:
--   local mapping = {
--     { canonical = "gTLD", synonyms = {"gtld", "generic", "tld"} },
--     { canonical = "ccTLD", synonyms = {"cctld", "country", "cc"} }
--   }
--   local canonical, css, category = require('Module:CanonicalForms').normalize(inputString, mapping)

local CanonicalForms = {}

--- Normalize an input string.
-- Removes wiki markup and converts input to lowercase.
-- Checks mappingTable for a matching synonym and returns the corresponding canonical value.
-- @param input String to normalize.
-- @param mappingTable Array of mapping groups with 'canonical', 'synonyms', and optional 'css' and 'category'.
-- @return canonical Matched value, or cleaned input if no match.
-- @return css Optional CSS class.
-- @return category Optional category string.
function CanonicalForms.normalize(input, mappingTable)
    if not input or input == "" then
        return nil, nil, nil
    end

    -- Remove wiki-link markup; eg. "[[Brand TLD]]" to "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