Module:Excerpt/sandbox: Difference between revisions

Revision as of 22:04, 28 April 2020

Revision as of 22:20, 28 April 2020

Line 1:

-- Get localizationlocalized data

local d = require("Module:Excerpt/i18n")

local p = {}

-- Helper function to debug

-- ReturnReturns blank text, or an error message if requested

local errors

-- Return blank text, or an error message if requested

local function err(text)

if errors then error(text, 2) end

Line 19 ⟶ 20:

end

-- InHelper text,function to match pre..list[1]..postfrom ora pre..list[2]..post orregular ...expressions

-- Like so: match pre..list[1]..post or pre..list[2]..post or ...

local function matchanymatchAny(text, pre, list, post, init)

local match = {}

for i = 1, #list do

Line 30 ⟶ 32:

-- Help gsub to remove unwanted templates and pseudo-templates such as #tag:ref and DEFAULTSORT

local function striptemplatestripTemplate(t)

-- If template is unwanted then return "" (gsub will replace by nothing), else return nil (gsub will keep existing string)

if matchanymatchAny(t, "^{{%s*", d.unwantedInlineTemplates, "%s*%f[|}]") then return "" end

-- If template is wanted but produces an unwanted reference then return the string with |shortref or |ref removed

Line 39 ⟶ 41:

-- If a wanted template has unwanted nested templates, purge them too

noref = mw.ustring.sub(noref, 1, 2) .. mw.ustring.gsub(mw.ustring.sub(noref, 3), "%b{}", striptemplatestripTemplate)

-- Replace {{audio}} by its text parameter: {{Audio|Foo.ogg|Bar}} → Bar

Line 65 ⟶ 67:

-- Check image for suitability

local function checkimagecheckImage(image)

local page = matchanymatchAny(image, "", d.fileNamespaces, "%s*:[^|%]]*") -- match File:(name) or Image:(name)

if not page then return false end

-- Limit to image types: .gif, .jpg, .jpeg, .png, .svg, .tiff, .xcf (exclude .ogg audio etc.)

if not matchanymatchAny(page, "%.", {"[Gg][Ii][Ff]", "[Jj][Pp][Ee]?[Gg]", "[Pp][Nn][Gg]", "[Ss][Vv][Gg]", "[Tt][Ii][Ff][Ff]", "[Xx][Cc][Ff]"}, "%s*$") then

return false

end

Line 77 ⟶ 79:

if desc and desc ~= "" then -- found description on local wiki

if mw.ustring.match(desc, "[Nn]on%-free") then return false end

desc = mw.ustring.gsub(desc, "%b{}", striptemplatestripTemplate) -- remove DEFAULTSORT etc. to avoid side effects of frame:preprocess

elseif not rtitle then

return false

Line 91 ⟶ 93:

-- Attempt to parse [[File:...]] or [[Image:...]], either anywhere (start=false) or at the start only (start=true)

local function parseimageparseImage(text, start)

local startre = ""

if start then startre = "^" end -- a true flag restricts search to start of string

local image = matchanymatchAny(text, startre .. "%[%[%s*", d.fileNamespaces, "%s*:.*") -- [[File: or [[Image: ...

if image then

image = mw.ustring.match(image, "%b[]%s*") -- matching [[...]] to handle wikilinks nested in caption

Line 102 ⟶ 104:

-- Parse a caption, which ends at a | (end of parameter) or } (end of infobox) but may contain nested [..] and {..}

local function parsecaptionparseCaption(caption)

if not caption then return nil end

local len = mw.ustring.len(caption)

Line 124 ⟶ 126:

-- Attempt to construct a [[File:...]] block from {{infobox ... |image= ...}}

local function argimageargImage(text)

local token = nil

local hasNamedArgs = mw.ustring.find(text, "|") and mw.ustring.find(text, "=")

Line 185 ⟶ 187:

capture_from = 1

while capture_from < mw.ustring.len(text) do

local position, caption = matchanymatchAny(text, "|%s*", d.captionParams, "%s*=%s*()([^\n]+)", capture_from)

if caption then

-- extend caption to parse "| caption = Foo {{Template\n on\n multiple lines}} Bar\n"

Line 201 ⟶ 203:

if images[i] then

if not captions[i] then

captions[i] = parsecaptionparseCaption(caption)

end

end

Line 279 ⟶ 281:

for _, index in ipairs(keys) do

local image = images[index]

local token = parseimageparseImage(image, true) -- look for image=[[File:...]] etc.

if not token then

image = mw.ustring.match(image, "^[^}|\n]*") -- remove later arguments

token = "[[" -- Add File: unless name already begins File: or Image:

if not matchanymatchAny(image, "^", d.fileNamespaces, "%s*:") then

token = token .. "File:"

end

Line 302 ⟶ 304:

-- Help gsub convert imagemaps into standard images

local function convertImagemapconvertImageMap(imagemap)

local image = matchanymatchAny(imagemap, "[>\n]%s*", d.fileNamespaces, "[^\n]*")

if image then

return "<!--imagemap-->[[" .. mw.ustring.gsub(image, "[>\n]%s*", "", 1) .. "]]"

Line 312 ⟶ 314:

-- Convert a comma-separated list of numbers or min-max ranges into a list of booleans, e.g. "1,3-5" → {1=true,2=false,3=true,4=true,5=true}

local function numberflagsnumberFlags(str)

local ranges = mw.text.split(str, ",") -- parse ranges, e.g. "1,3-5" → {"1","3-5"}

local flags = {}

Line 362 ⟶ 364:

local allparas = true -- keep all paragraphs?

if options.paraflags then

if type(options.paraflags) ~= "table" then options.paraflags = numberflagsnumberFlags(options.paraflags) end

for _, v in pairs(options.paraflags) do

if v then allparas = false end -- if any para specifically requested, don't keep all

Line 374 ⟶ 376:

local maxfile = 0 -- for efficiency, stop checking images after this many have been found

if options.fileflags then

if type(options.fileflags) ~= "table" then options.fileflags = numberflagsnumberFlags(options.fileflags) end

for k, v in pairs(options.fileflags) do

if v and k > maxfile then maxfile = k end -- set maxfile = highest key in fileflags

Line 400 ⟶ 402:

f = modifyImage(f, "thumb")

f = modifyImage(f, fileargs)

if checkimagecheckImage(f) then filetext = filetext .. f .. "\n" end

end

Line 412 ⟶ 414:

line = mw.ustring.gsub(line, "%b<>", "") -- remove all HTML tags from this line

-- if anything is left, other than an incomplete further template or an image, keep the template: it counts as part of the line

if mw.ustring.find(line, "%S") and not matchanymatchAny(line, "^%s*", { "{{", "%[%[%s*[Ff]ile:", "%[%[%s*[Ii]mage:" }, "") then

token = nil

end

Line 422 ⟶ 424:

if not filesOnly and not startLine then t = t .. token end

elseif matchanymatchAny(token, "{{%s*", d.wantedBlockTemplates, "%s*%f[|}]") then

t = t .. token -- keep wanted block templates

Line 429 ⟶ 431:

elseif files < maxfile then -- discard template, but if we are still collecting images...

local images = argimageargImage(token) or {}

if not images then

local image = parseimageparseImage(token, false) -- look for embedded [[File:...]], |image=, etc.

if image then table.insert(images, image) end

end

for _, image in ipairs(images) do

if files < maxfile and checkimagecheckImage(image) then -- if image is found and qualifies (not a sound file, non-free, etc.)

files = files + 1 -- count the file, whether displaying it or not

if options.fileflags and options.fileflags[files] then -- if displaying this image

Line 446 ⟶ 448:

end

else -- the next token in text is not a template

token = parseimageparseImage(text, true)

if token then -- the next token in text looks like an image

if files < maxfile and checkimagecheckImage(token) then -- if more images are wanted and this is a wanted image

files = files + 1

if options.fileflags and options.fileflags[files] then

Line 514 ⟶ 516:

text = mw.ustring.gsub(text, "<%s*[Rr][Ee][Ff][^>]-/%s*>", "") -- remove refs cited elsewhere

text = mw.ustring.gsub(text, "<%s*[Rr][Ee][Ff].->.-<%s*/%s*[Rr][Ee][Ff]%s*>", "") -- remove refs

text = mw.ustring.gsub(text, "%b{}", striptemplatestripTemplate) -- remove unwanted templates such as references

end

text = mw.ustring.gsub(text, "<%s*[Ss][Cc][Oo][Rr][Ee].->.-<%s*/%s*[Ss][Cc][Oo][Rr][Ee]%s*>", "") -- remove musical scores

text = mw.ustring.gsub(text, "<%s*[Ii][Mm][Aa][Gg][Ee][Mm][Aa][Pp].->.-<%s*/%s*[Ii][Mm][Aa][Gg][Ee][Mm][Aa][Pp]%s*>", convertImagemapconvertImageMap) -- convert imagemaps into standard images

text = mw.ustring.gsub(text, "%s*{{%s*[Tt][Oo][Cc].-}}", "") -- remove most common tables of contents

text = mw.ustring.gsub(text, "%s*__[A-Z]*TOC__", "") -- remove TOC behavior switches

Line 529 ⟶ 531:

-- Parse a ==Section== from a page

local function getsectiongetSection(text, section, mainonly)

local escapedSection = mw.ustring.gsub(mw.uri.decode(section), "([%^%$%(%)%%%.%[%]%*%+%-%?])", "%%%1") -- %26 → & etc, then ^ → %^ etc.

local level, content = mw.ustring.match(text .. "\n", "\n(==+)%s*" .. escapedSection .. "%s*==.-\n(.*)")

Line 544 ⟶ 546:

-- Remove unmatched <tag> or </tag> tags

local function fixtagsfixTags(text, tag)

local startcount = 0

for i in mw.ustring.gmatch(text, "<%s*" .. tag .. "%f[^%w_].->") do startcount = startcount + 1 end

Line 607 ⟶ 609:

section = mw.ustring.match(pagename, ".-#(.*)") -- parse redirect to Page#Section

end

if text and section and section ~= "" then text = getsectiongetSection(text, section) end

end

end

Line 624 ⟶ 626:

pageopts[k] = v

end

pageopts.paraflags = numberflagsnumberFlags(pageopts["paragraphs"] or "") -- parse paragraphs, e.g. "1,3-5" → {"1","3-5"}

pageopts.fileflags = numberflagsnumberFlags(pageopts["files"] or "") -- parse file numbers

if pageopts.more and pageopts.more == "" then pageopts.more = "Read more..." end -- more= is short for this default text

end

Line 670 ⟶ 672:

-- Ensure div tags match

text = fixtagsfixTags(text, "div")

if pageopts.more then text = text .. " '''[[" .. pagename .. "|" .. pageopts.more .. "]]'''" end -- wikilink to article for more info

Line 713 ⟶ 715:

end

if args["section"] then -- check relevant section only

text = getsectiongetSection(text, args["section"], args["sectiononly"])

if not text then return err("No section " .. args["section"] .. " in page " .. page) end

end

Line 739 ⟶ 741:

local options = args -- pick up miscellaneous options: more, errors, fileargs

options.paraflags = numberflagsnumberFlags(args["paragraphs"] or "") -- parse paragraphs, e.g. "1,3-5" → {"1","3-5"}

options.fileflags = numberflagsnumberFlags(args["files"] or "") -- parse file numbers

if options.more and options.more == "" then options.more = "Read more..." end -- more= is short for this default text

Line 801 ⟶ 803:

else

local options = args -- pick up miscellaneous options: more, errors, fileargs

options.paraflags = numberflagsnumberFlags(args.paragraphs or "") -- parse paragraphs, e.g. "1,3-5" → {"1","3-5"}

options.fileflags = numberflagsnumberFlags(args.files or "1") -- parse file numbers

options.nobold=1

options.keepTables = is(args.tables) and args.tables or 1

Line 839 ⟶ 841:

-- Entry points for other Lua modules

function p.getContent(page, frame) return getContent(page, frame) end

function p.getsection(text, section) return getsectiongetSection(text, section) end

function p.parse(text, options, filesOnly) return parse(text, options, filesOnly) end

function p.argimage(text) return argimageargImage(text) end

function p.checkimage(image) return checkimagecheckImage(image) end

function p.parseimage(text, start) return parseimageparseImage(text, start) end

function p.cleanupText(text, options) return cleanupText(text, options) end

function p.main(pagenames, options) return main(pagenames, options) end

function p.numberflags(str) return numberflagsnumberFlags(str) end

return p