Module:CanonicalForms: Difference between revisions

(One intermediate revision by the same user not shown)

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 (automatically included in case-insensitive matching)~~

* Description: Text normalization utility that removes wiki markup and maps user input to canonical values using configurable lookup tables

~~-- * synonyms: Additional 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 = {"generic", "~~tld~~"} },

-- { canonical = "ccTLD", synonyms = {"country", "cc"} }

-- }

-- local canonical, css, category = require('Module:CanonicalForms').normalize(inputString, mapping)

--

~~-- Note: The canonical value itself is automatically included in case-insensitive matching.~~

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)

if not input or input == "" then

Line 30:

Line 15:

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()

@@ 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 (automatically included in case-insensitive matching)
+* Description: Text normalization utility that removes wiki markup and maps user input to canonical values using configurable lookup tables
---   * synonyms: Additional 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 = {"generic", "tld"} },
---     { canonical = "ccTLD", synonyms = {"country", "cc"} }
---   }
---   local canonical, css, category = require('Module:CanonicalForms').normalize(inputString, mapping)
---
--- Note: The canonical value itself is automatically included in case-insensitive matching.
 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)
      if not input or input == "" then
@@ Line 30: / Line 15: @@
      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()