ICANNWiki

Module:CanonicalForms: Difference between revisions

← Older edit
MarkWD (talk | contribs)
Bureaucrats, Check users, Interface administrators, Administrators (Semantic MediaWiki), Curators (Semantic MediaWiki), Editors (Semantic MediaWiki), steward, Suppressors, Administrators, Temporary account IP viewers
25,069 edits
// via Wikitext Extension for VSCode
// via Wikitext Extension for VSCode
 
(2 intermediate revisions by the same user not shown)
Line 1: Line 1:
-- Module:CanonicalForms
--[[
-- Normalizes strings by removing wiki markup and mapping to canonical values.
* Name: CanonicalForms
-- Mapping tables:
* Author: Mark W. Datysgeld
--  * canonical: Display value
* Description: Text normalization utility that removes wiki markup and maps user input to canonical values using configurable lookup tables
--  * synonyms: Case-insensitive terms mapped to canonical
* Notes: Example usage: local mapping = { { canonical = "gTLD", synonyms = {"generic", "g"} }, { canonical = "ccTLD", synonyms = {"country", "cc"} } }; local canonical, css, category = require('Module:CanonicalForms').normalize(inputString, mapping)
--  * [optional] css: 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 = {}
local CanonicalForms = {}


--- Normalize an input string.
-- Normalize an input string
-- Removes wiki markup, converts to lowercase, and maps to canonical form.
-- Removes wiki markup, converts to lowercase, and maps to canonical form
-- @param input String to normalize.
-- @param mappingTable Mapping groups with 'canonical', 'synonyms', and optional 'css'/'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)
function CanonicalForms.normalize(input, mappingTable)
     if not input or input == "" then
     if not input or input == "" then
Line 28: Line 15:
     end
     end


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


Line 35: Line 22:
         local lookupCache = {}
         local lookupCache = {}
         for _, group in ipairs(mappingTable) do
         for _, group in ipairs(mappingTable) do
            -- Add the canonical form itself to the lookup (in lowercase)
            lookupCache[group.canonical:lower()] = group
           
            -- Add all synonyms to the lookup
             for _, syn in ipairs(group.synonyms or {}) do
             for _, syn in ipairs(group.synonyms or {}) do
                 lookupCache[syn:lower()] = group
                 lookupCache[syn:lower()] = group
Retrieved from "https://staging.icannwiki.org/Module:CanonicalForms"