Jump to content

Module:CodeToText: 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
25,057 edits
// via Wikitext Extension for VSCode
// via Wikitext Extension for VSCode
 
(6 intermediate revisions by the same user not shown)
Line 1: Line 1:
-- Module:TranscludeModuleCode
--[[
-- Extracts a snippet of content from a specified page using either:
* Name: CodeToText
-- 1. A defined line range (from/to parameters)
* Author: Mark W. Datysgeld
-- 2. Hook markers like emojis (hook parameter)
* Description: Utility for extracting content snippets from wiki pages using emoji hook markers placed at the beginning and end of desired content sections
--
* Notes: Example usage: {{#invoke:CodeToText|showSnippet|page=Module:Example|hook=⭐}}; Supports emoji hooks like 🪝, 📌, 🔖, ⭐ for both inline and block content extraction
-- The module finds content between matching instances of the same hook,
]]
-- either on different lines or within the same line. Any emoji can be used
-- as a hook (🪝, 📌, 🔖, 🏷️, 🚩, ⭐, etc.) - just place the same emoji at
-- the beginning and end of the content you want to extract.
--
-- Example:
--  {{#invoke:TranscludeModuleCode|showSnippet|page=Module:Example|hook=⭐}}


local p = {}
local p = {}
-- Cache for previously extracted snippets (persists during a single page render)
local snippetCache = {}
-- Helper function to create a cache key from parameters
local function createCacheKey(pageName, hook, fromLine, toLine)
    if hook then
        return pageName .. "|hook=" .. hook
    else
        return pageName .. "|from=" .. tostring(fromLine) .. "|to=" .. tostring(toLine)
    end
end


function p.showSnippet(frame)
function p.showSnippet(frame)
Line 31: Line 13:
         return "Error: 'page' parameter is required"
         return "Error: 'page' parameter is required"
     end
     end
   
 
     local hook = frame.args.hook
     local hook = frame.args.hook
      
     if not hook then
    -- Fallback to line numbers if hook isn't provided
         return "Error: 'hook' parameter is required"
    local fromLine = tonumber(frame.args.from) or 1
    local toLine  = tonumber(frame.args.to)  or fromLine
   
    -- Check cache first for previously extracted snippets
    local cacheKey = createCacheKey(pageName, hook, fromLine, toLine)
    if snippetCache[cacheKey] then
         return snippetCache[cacheKey]
     end
     end


Line 54: Line 29:
     end
     end


    local result
     -- Try inline hooks first
   
    local inlineSnippet = content:match(hook .. "(.-)" .. hook)
     -- If hook is provided, use it to extract the snippet
     if inlineSnippet then
    if hook then
         return inlineSnippet
        -- First, check for inline hooks (hooks on the same line)
        -- This is more efficient than splitting into lines first
        local inlinePattern = hook .. "(.-)" .. hook
        local inlineMatch = content:match(inlinePattern)
       
        if inlineMatch then
            -- We found inline hooks - use the content between them
            result = inlineMatch
        else
            -- Look for hooks on different lines
            local lines = {}
            local lineCount = 0
            local hookPositions = {}
           
            -- Find all instances of the hook and count lines
            local lineNumber = 0
            for line in content:gmatch("[^\r\n]+") do
                lineNumber = lineNumber + 1
                lineCount = lineNumber
               
                if line:find(hook, 1, true) then
                    table.insert(hookPositions, lineNumber)
                end
               
                -- Store all lines for later use
                lines[lineNumber] = line
            end
           
            if #hookPositions < 2 then
                return "Error: Need at least 2 instances of hook '" .. hook .. "' in '" .. pageName .. "'"
            end
           
            -- Extract content between first two hook instances (excluding the hook lines)
            local startLine = hookPositions[1]
            local endLine = hookPositions[2]
           
            -- Always exclude the hook lines
            local startIndex = startLine + 1
            local endIndex = endLine - 1
           
            -- Pre-allocate snippet table with known size
            local snippetSize = math.max(0, endIndex - startIndex + 1)
            local snippet = {}
           
            if snippetSize > 0 then
                for i = 1, snippetSize do
                    snippet[i] = lines[startIndex + i - 1]
                end
                result = table.concat(snippet, "\n")
            else
                result = ""
            end
        end
     else
        -- Fallback to line number-based extraction
        -- For line-based extraction, we can be more efficient by only processing the needed lines
        local lineNumber = 0
        local snippet = {}
        local snippetIndex = 0
       
        -- Only process lines up to toLine
        for line in content:gmatch("[^\r\n]+") do
            lineNumber = lineNumber + 1
           
            -- Skip lines before fromLine
            if lineNumber >= fromLine then
                -- Stop once we've reached toLine
                if lineNumber > toLine then
                    break
                end
               
                snippetIndex = snippetIndex + 1
                snippet[snippetIndex] = line
            end
         end
       
        result = table.concat(snippet, "\n")
     end
     end
      
 
     -- Cache the result before returning
     -- Find block hooks
     snippetCache[cacheKey] = result
    local s, e = content:find(hook, 1, true)
     return result
    if not s then
        return "Error: Need at least 2 instances of hook '" .. hook .. "' in '" .. pageName .. "'"
    end
 
    local s2, e2 = content:find(hook, e + 1, true)
    if not s2 then
        return "Error: Need at least 2 instances of hook '" .. hook .. "' in '" .. pageName .. "'"
    end
 
     -- Extract text between the two hooks, excluding the hook lines
     local snippet = content:sub(e + 1, s2 - 1)
 
    -- Trim leading and trailing newlines
    if snippet:sub(1,1) == "\n" then
        snippet = snippet:sub(2)
    end
    if snippet:sub(-1) == "\n" then
        snippet = snippet:sub(1, -2)
    end
 
     return snippet
end
end


return p
return p

Latest revision as of 02:56, 25 August 2025

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

--[[
* Name: CodeToText
* Author: Mark W. Datysgeld
* Description: Utility for extracting content snippets from wiki pages using emoji hook markers placed at the beginning and end of desired content sections
* Notes: Example usage: {{#invoke:CodeToText|showSnippet|page=Module:Example|hook=⭐}}; Supports emoji hooks like 🪝, 📌, 🔖, ⭐ for both inline and block content extraction
]]

local p = {}

function p.showSnippet(frame)
    local pageName = frame.args.page
    if not pageName then
        return "Error: 'page' parameter is required"
    end

    local hook = frame.args.hook
    if not hook then
        return "Error: 'hook' parameter is required"
    end

    local titleObj = mw.title.new(pageName)
    if not titleObj then
        return "Failed to create mw.title object for '" .. pageName .. "'"
    end

    local content = titleObj:getContent()
    if not content then
        return "No content for '" .. pageName .. "'"
    end

    -- Try inline hooks first
    local inlineSnippet = content:match(hook .. "(.-)" .. hook)
    if inlineSnippet then
        return inlineSnippet
    end

    -- Find block hooks
    local s, e = content:find(hook, 1, true)
    if not s then
        return "Error: Need at least 2 instances of hook '" .. hook .. "' in '" .. pageName .. "'"
    end

    local s2, e2 = content:find(hook, e + 1, true)
    if not s2 then
        return "Error: Need at least 2 instances of hook '" .. hook .. "' in '" .. pageName .. "'"
    end

    -- Extract text between the two hooks, excluding the hook lines
    local snippet = content:sub(e + 1, s2 - 1)

    -- Trim leading and trailing newlines
    if snippet:sub(1,1) == "\n" then
        snippet = snippet:sub(2)
    end
    if snippet:sub(-1) == "\n" then
        snippet = snippet:sub(1, -2)
    end

    return snippet
end

return p
Retrieved from "https://staging.icannwiki.org/index.php?title=Module:CodeToText&oldid=1387972"