Modül:Transcluder

[bullvar_katip]

-- Module:Transcluder is a general-purpose transclusion engine -- Documentation and master version: https://en.wikipedia.org/wiki/Module:Transcluder -- Authors: User:Sophivorus, User:Certes & others -- License: CC-BY-SA-3.0 local p = {} -- Helper function to test for truthy and falsy values -- @todo Somehow internationalize it local function truthy(value) if not value or value or value 0 or value '0' or value 'false' or value 'no' or value 'non' then return false end return true end -- Helper function to match from a list of regular expressions -- Like so: match pre..list[1]..post or pre..list[2]..post or ... local function matchAny(text, pre, list, post, init) local match = {} for i = 1, #list do match = { mw.ustring.match(text, pre .. list .. post, init) } if match[1] then return unpack(match) end end return nil end -- Like matchAny but for Category/File links with less overhead local function matchAnyLink(text, list) local match for _, v in ipairs(list) do match = string.match(text, '%[%[%s*' .. v .. '%s*:.*%]%]') if match then break end end return match end -- Helper function to escape a string for use in regexes local function escapeString(str) return string.gsub(str, '[%^%$%(%)%.%[%]%*%+%-%?%%]', '%%%0') end -- Helper function to remove a string from a text local function removeString(text, str) local pattern = escapeString(str) if #pattern > 9999 then -- strings longer than 10000 bytes can't be put into regexes pattern = escapeString(mw.ustring.sub(str, 1, 999)) .. '.-' .. escapeString(mw.ustring.sub(str, -999)) end return string.gsub(text, pattern, ) end -- Helper function to convert a comma-separated list of numbers or min-max ranges into a list of booleans -- @param flags Comma-separated list of numbers or min-max ranges, for example '1,3-5' -- @return Map from integers to booleans, for example {1=true,2=false,3=true,4=true,5=true} -- @return Boolean indicating whether the flags should be treated as a blacklist or not local function parseFlags(value) local flags = {} local blacklist = false if not value then return nil, false end if type(value) == 'number' then if value if Foo is defined elsewhere if flags and not truthy(flags) then text = string.gsub(text, ']*/%s*>') do text = removeString(text, citation) end end end end return references, text end -- Get the lead section from the given wikitext. -- @param text Required. Wikitext to parse. -- @return Wikitext of the lead section. local function getLead(text) text = string.gsub('\n' .. text, '\n==.*', ) text = mw.text.trim(text) if not text then return throwError('lead-empty') end return text end -- Get the requested sections from the given wikitext. -- @param text Required. Wikitext to parse. -- @param flags Range of sections to return, for example 2 or '1,3-5'. Omit to return all sections. -- @return Sequence of strings containing the wikitext of the requested sections. -- @return Original wikitext minus requested sections. local function getSections(text, flags) local sections = {} local flags, blacklist = parseFlags(flags) local count = 0 local prefix, section, suffix for title in string.gmatch('\n' .. text .. '\n ', '\n +%s*([^=]+)%s* +') do count count + 1 prefix, section, suffix string.match('\n' .. text .. '\n ', '\n +%s*' .. escapeString(title) .. '%s* +(.-)\n ') if not blacklist and ( not flags or flags[count] or matchFlag(title, flags) ) or blacklist and flags and not flags[count] and not matchFlag(title, flags) then sections[title] section else text string.sub(text, 1, prefix) .. string.sub(text, suffix) text string.gsub(text, '\n? $', ) -- remove the trailing \n== end end return sections, text end -- Get the requested section or ') then -- avoid expensive search if possible text = mw.text.trim((text :gsub('.-', ) -- remove text between section tags :gsub('^.-', ) -- remove text before first section tag :gsub('.*', ) -- remove text after last section tag )) if text then return throwError('section-tag-empty', section) end return text end local level, text string.match('\n' .. text .. '\n', '\n( +)%s*' .. escapedSection .. '%s* .-\n(.*)') if not text then return throwError('section-not-found', section) end local nextSection '\n ' .. string.rep('=?', #level - 2) .. '[^=].*' text = string.gsub(text, nextSection, ) -- remove later sections with headings at this level or higher text = mw.text.trim(text) if text == then return throwError('section-empty', section) end return text end -- Replace the first call to each reference defined outside of the text for the full reference, to prevent undefined references -- Then prefix the page title to the reference names to prevent conflicts -- that is, replace for -- also remove reference groups: ]*>.-<%s*/%s*[Rr][Ee][Ff]%s*>') if refBody then -- the ref body was found elsewhere text = mw.ustring.gsub(text, '<%s*[Rr][Ee][Ff][^>]*name%s*=%s*["\']?%s*' .. refName .. '%s*["\']?[^>]*/?%s*>', mw.ustring.gsub(refBody, '%%', '%%%%'), 1) end end end else position = mw.ustring.len(text) end end page = string.gsub(page, '"', ) -- remove any quotation marks from the page title text = mw.ustring.gsub(text, '<%s*[Rr][Ee][Ff][^>]*name%s*=%s*["\']?([^"\'>/]+)["\']?[^>/]*(/?)%s*>', '<ref name="' .. page .. ' %1"%2>') text = mw.ustring.gsub(text, '<%s*[Rr][Ee][Ff]%s*group%s*=%s*["\']?[^"\'>/]+["\']%s*>', ) return text end -- Replace the bold title or synonym near the start of the page by a link to the page local function linkBold(text, page) local lang = mw.language.getContentLanguage local position = mw.ustring.find(text, "" .. lang:ucfirst(page) .. "", 1, true) -- look for "Foo is..." (uc) or "A foo is..." (lc) or mw.ustring.find(text, "" .. lang:lcfirst(page) .. "", 1, true) -- plain search: special characters in page represent themselves if position then local length = mw.ustring.len(page) text = mw.ustring.sub(text, 1, position + 2) .. "" .. mw.ustring.sub(text, position + 3, position + length + 2) .. "" .. mw.ustring.sub(text, position + length + 3, -1) -- link it else -- look for anything unlinked in bold, assumed to be a synonym of the title (e.g. a person's birth name) text = mw.ustring.gsub(text, "(.-'*)", function(a, b) if not mw.ustring.find(b, "%[") and not mw.ustring.find(b, "%{") then -- if not wikilinked or some weird template return "" .. b .. "" -- replace Foo by Foo else return nil -- instruct gsub to make no change end end, 1) -- "end" here terminates the anonymous replacement function(a, b) passed to gsub end return text end -- Remove non-free files. -- @param text Required. Wikitext to clean. -- @return Clean wikitext. local function removeNonFreeFiles(text) local fileNamespaces = getNamespaces('File') local fileName local fileDescription local frame = mw.getCurrentFrame for file in string.gmatch(text, '%b[]') do if matchAnyLink(file, fileNamespaces) then fileName = 'File:' .. string.match(file, '%[%[[^:]-[^]|]+)') fileDescription, fileName = getText(fileName) if fileName then if not fileDescription or fileDescription == then fileDescription = framereprocess -- try Commons end if fileDescription and string.match(fileDescription, '[Nn]on%-free') then text = removeString(text, file) end end end end return text end -- Remove any self links local function removeSelfLinks(text) local lang = mw.language.getContentLanguage local page = escapeString(mw.title.getCurrentTitle.prefixedText) local ucpage = lang:ucfirst(page) local lcpage = lang:lcfirst(page) text = text :gsub('%[%[(' .. ucpage .. ')%]%]', '%1') :gsub('%[%[(' .. lcpage .. ')%]%]', '%1') :gsub('%[%[' .. ucpage .. '|([^]]+)%]%]', '%1') :gsub('%[%[' .. lcpage .. '|([^]]+)%]%]', '%1') return text end -- Remove all wikilinks local function removeLinks(text) text = text :gsub('%[%[[^%]|]+|([^]]+)%]%]', '%1') :gsub('%[%[([^]]+)%]%]', '%1') :gsub('%[[^ ]+ ([^]]+)%]', '%1') :gsub('%[([^]]+)%]', '%1') return text end -- Remove HTML comments local function removeComments(text) text = string.gsub(text, '<!%-%-.-%-%->', ) return text end -- Remove behavior switches, such as __NOTOC__ local function removeBehaviorSwitches(text) text = string.gsub(text, '__[A-Z]+__', ) return text end -- Remove bold text local function removeBold(text) text = string.gsub(text, "'", ) return text end -- Main function for modules local function get(page, options) if not options then options = {} end -- Make sure the page exists if not page then return throwError('no-page') end page = mw.text.trim(page) if page then return throwError('no-page') end local page, hash, section string.match(page, '([^#]+)(#?)(.*)') local text, temp getText(page, options.noFollow) if not temp then return throwError('invalid-title', page) end page temp if not text then return throwError('page-not-found', page) end local full text -- save the full text for fixReferences below -- Get the requested section if truthy(section) then text getSection(text, section) elseif truthy(hash) then text getLead(text) end -- Keep only the requested elements local elements if options.only then if options.only 'sections' then elements = getSections(text, options.sections) end if options.only 'lists' then elements getLists(text, options.lists) end if options.only 'files' then elements = getFiles(text, options.files) end if options.only 'tables' then elements getTables(text, options.tables) end if options.only 'templates' then elements = getTemplates(text, options.templates) end if options.only 'parameters' then elements getParameters(text, options.parameters) end if options.only 'paragraphs' then elements = getParagraphs(text, options.paragraphs) end if options.only 'categories' then elements getCategories(text, options.categories) end if options.only 'references' then elements = getReferences(text, options.references) end text = if elements then for key, element in pairs(elements) do text = text .. '\n' .. element .. '\n' end end end -- Filter the requested elements if options.sections and options.only ~= 'sections' then elements, text = getSections(text, options.sections) end if options.lists and options.only ~= 'lists' then elements, text = getLists(text, options.lists) end if options.files and options.only ~= 'files' then elements, text = getFiles(text, options.files) end if options.tables and options.only ~= 'tables' then elements, text = getTables(text, options.tables) end if options.templates and options.only ~= 'templates' then elements, text = getTemplates(text, options.templates) end if options.parameters and options.only ~= 'parameters' then elements, text = getParameters(text, options.parameters) end if options.paragraphs and options.only ~= 'paragraphs' then elements, text = getParagraphs(text, options.paragraphs) end if options.categories and options.only ~= 'categories' then elements, text = getCategories(text, options.categories) end if options.references and options.only ~= 'references' then elements, text = getReferences(text, options.references) end -- Misc options if truthy(options.fixReferences) then text = fixReferences(text, page, full) end if truthy(options.linkBold) and not truthy(section) then text = linkBold(text, page) end if truthy(options.noBold) then text = removeBold(text) end if truthy(options.noLinks) then text = removeLinks(text) end if truthy(options.noSelfLinks) then text = removeSelfLinks(text) end if truthy(options.noNonFreeFiles) then text = removeNonFreeFiles(text) end if truthy(options.noBehaviorSwitches) then text = removeBehaviorSwitches(text) end if truthy(options.noComments) then text = removeComments(text) end -- Remove multiple newlines left over from removing elements text = string.gsub(text, '\n\n\n+', '\n\n') text = mw.text.trim(text) return text end -- Main invocation function for templates local function main(frame) local args = parseArgs(frame) local page = args[1] local ok, text = pcall(get, page, args) if not ok then return getError(text) end return framereprocess(text) end -- Entry points for templates function p.main(frame) return main(frame) end -- Entry points for modules function p.get(page, options) return get(page, options) end function p.getText(page, noFollow) return getText(page, noFollow) end function p.getLead(text) return getLead(text) end function p.getSection(text, section) return getSection(text, section) end function p.getSections(text, flags) return getSections(text, flags) end function p.getParagraphs(text, flags) return getParagraphs(text, flags) end function p.getParameters(text, flags) return getParameters(text, flags) end function p.getCategories(text, flags) return getCategories(text, flags) end function p.getReferences(text, flags) return getReferences(text, flags) end function p.getTemplates(text, flags) return getTemplates(text, flags) end function p.getTables(text, flags) return getTables(text, flags) end function p.getLists(text, flags) return getLists(text, flags) end function p.getFiles(text, flags) return getFiles(text, flags) end function p.getError(message, value) return getError(message, value) end -- Expose handy methods function p.truthy(value) return truthy(value) end function p.parseArgs(frame) return parseArgs(frame) end function p.matchAny(text, pre, list, post, init) return matchAny(text, pre, list, post, init) end function p.matchFlag(value, flags) return matchFlag(value, flags) end function p.getNamespaces(name) return getNamespaces(name) end function p.removeBold(text) return removeBold(text) end function p.removeLinks(text) return removeLinks(text) end function p.removeSelfLinks(text) return removeSelfLinks(text) end function p.removeNonFreeFiles(text) return removeNonFreeFiles(text) end function p.removeBehaviorSwitches(text) return removeBehaviorSwitches(text) end function p.removeComments(text) return removeComments(text) end return p