Module:CanonicalForms: Difference between revisions

(4 intermediate revisions by the same user not shown)

Line 1:

-- ~~Module~~:CanonicalForms

--[[

~~-- Normalizes strings by removing wiki markup and mapping them to canonical values.~~

* Name: CanonicalForms

~~-- Mapping tables include:~~

* Author: Mark W. Datysgeld

-- * ~~canonical~~: ~~Standard display value~~.

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

-- * ~~synonyms~~: ~~Synonyms (case-insensitive) 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: 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.

-- Normalize an input string

-- Removes wiki markup ~~and~~ converts ~~input~~ to lowercase.

-- Removes wiki markup, converts to lowercase, and maps to canonical form

~~-- 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

Line 29:

Line 15:

end

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

-- Remove wiki internal link markup (e.g., "[[Brand TLD]]" → "Brand TLD")

local cleanInput = input:gsub("%[%[([^|%]]+)|?[^%]]*%]%]", "%1"):lower()

for _, group in ipairs(mappingTable) do

-- Create lookup table for faster matching (first call only)

for _, syn in ipairs(group.synonyms or {}) do

if not mappingTable._lookupCache then

~~if cleanInput ==~~ syn:lower() ~~then~~

local lookupCache = {}

~~return group.canonical,~~ group~~.css, group.category~~

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

lookupCache[syn:lower()] = group

end

mappingTable._lookupCache = lookupCache

end

-- Direct lookup via cache

local match = mappingTable._lookupCache[cleanInput]

if match then

return match.canonical, match.css, match.category

end

@@ Line 1: / Line 1: @@
--- Module:CanonicalForms
+--[[
--- Normalizes strings by removing wiki markup and mapping them to canonical values.
+* Name: CanonicalForms
--- Mapping tables include:
+* Author: Mark W. Datysgeld
---   * canonical: Standard display value.
+* Description: Text normalization utility that removes wiki markup and maps user input to canonical values using configurable lookup tables
---   * synonyms: Synonyms (case-insensitive) 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: 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.
+-- Normalize an input string
--- Removes wiki markup and converts input to lowercase.
+-- Removes wiki markup, converts to lowercase, and maps to canonical form
--- 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
@@ Line 29: / Line 15: @@
      end
-     -- Remove wiki-link markup; eg. "[[Brand TLD]]" to "Brand TLD"
+     -- Remove wiki internal link markup (e.g., "[[Brand TLD]]" → "Brand TLD")
      local cleanInput = input:gsub("%[%[([^|%]]+)|?[^%]]*%]%]", "%1"):lower()
-     for _, group in ipairs(mappingTable) do
+     -- Create lookup table for faster matching (first call only)
-        for _, syn in ipairs(group.synonyms or {}) do
+    if not mappingTable._lookupCache then
-            if cleanInput == syn:lower() then
+        local lookupCache = {}
-                return group.canonical, group.css, group.category
+        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
+                lookupCache[syn:lower()] = group
              end
          end
+        mappingTable._lookupCache = lookupCache
+    end
+    -- Direct lookup via cache
+    local match = mappingTable._lookupCache[cleanInput]
+    if match then
+        return match.canonical, match.css, match.category
      end