|
-- Get localization data
-- Local aliases of the file namespace
local d = require("Module:Excerpt/l10n")
local fileNamespaces = {
"[Ff]ile",
"[Ii]mage"
}
local captionParams = {
"[^=|]*[Cc]aption[^=|]*",
"[^=|]*[Ll]egend[^=|]*"
}
-- Local category to track content pages with broken excerpts (may be empty, don't include the "Category:" prefix)
local brokenCategory = "Articles with broken excerpts"
-- The module keeps all inline templates except these ones
local unwantedInlineTemplates = {"[Ee]fn", "[Ee]fn%-[lu][arg]", "[Ee]l[mn]", "[Rr]p?", "[Ss]fn[bmp]", "[Ss]f[bn]", "[Nn]ote[Tt]ag", "#[Tt]ag:%s*[Rr]ef", "[Rr]efn?",
"[CcDd]n", "[Cc]itation[%- _]needed", "[Dd]isambiguation needed", "[Ff]eatured article", "[Gg]ood article",
"[Dd]ISPLAYTITLE", "[Ss]hort[ _]+description", "[Cc]itation", "[Cc]ite[%- _]+[%w_%s]-", "[Cc]oor[%w_%s]-",
"[Uu]?n?[Rr]eliable source[%?%w_%s]-", "[Rr]s%??", "[Vv]c", "[Vv]erify credibility", "[Bb]y[ _]*[Ww]ho[m]*%??", "[Ww]ikisource[ -_]*multi", "[Ii]nflation[ _/-]*[Ff]n",
"[Bb]iblesource",
-- aliases for Clarification needed
"[Cc]f[ny]", "[Cc]larification[ _]+inline", "[Cc]larification[%- _]*needed", "[Cc]larification", "[Cc]larify%-inline", "[Cc]larify%-?me",
"[Cc]larify[ _]+inline", "[Cc]larify", "[Cc]LARIFY", "[Cc]onfusing%-inline", "[Cc]onfusing%-short", "[Ee]xplainme", "[Hh]uh[ _]*%??", "[Ww]hat%?",
"[Ii]nline[ _]+[Uu]nclear", "[Ii]n[ _]+what[ _]+sense", "[Oo]bscure", "[Pp]lease[ _]+clarify", "[Uu]nclear[ _]+inline", "[Ww]hat's[ _]+this%?",
"[Gg]eoQuelle", "[Nn]eed[s]+[%- _]+[Ii][Pp][Aa]", "[Ii]PA needed",
-- aliases for Clarification needed lead
"[Cc]itation needed %(?lea?de?%)?", "[Cc]nl", "[Ff]act %(?lea?de?%)?", "[Ll]ead citation needed", "[Nn]ot in body", "[Nn]ot verified in body",
-- Primary source etc.
"[Pp]s[ci]", "[Nn]psn", "[Nn]on%-primary[ _]+source[ _]+needed", "[Ss]elf%-published[%w_%s]-", "[Uu]ser%-generated[%w_%s]-",
"[Pp]rimary source[%w_%s]-", "[Ss]econdary source[%w_%s]-", "[Tt]ertiary source[%w_%s]-", "[Tt]hird%-party[%w_%s]-",
-- aliases for Disambiguation (page) and similar
"[Bb]egriffsklärung", "[Dd][Aa][Bb]", "[Dd]big", "[%w_%s]-%f[%w][Dd]isam[%w_%s]-", "[Hh][Nn][Dd][Ii][Ss]",
-- aliases for Failed verification
"[Bb]adref", "[Ff]aile?[ds] ?[rv][%w_%s]-", "[Ff][Vv]", "[Nn][Ii]?[Cc][Gg]", "[Nn]ot ?in ?[crs][%w_%s]-", "[Nn]ot specifically in source",
"[Vv]erification[%- _]failed",
-- aliases for When
"[Aa]s[ _]+of[ _]+when%??", "[Aa]s[ _%-]+of%??", "[Cc]larify date", "[Dd]ate[ _]*needed", "[Nn]eeds?[ _]+date", "[Rr]ecently", "[Ss]ince[ _]+when%??",
"[Ww]HEN", "[Ww]hen%??",
-- aliases for Update
"[Nn]ot[ _]*up[ _]*to[ _]*date","[Oo]u?[Tt][Dd]","[Oo]ut[%- _]*o?f?[%- _]*dated?", "[Uu]pdate", "[Uu]pdate[ _]+sect", "[Uu]pdate[ _]+Watch",
-- aliases for Pronunciation needed
"[Pp]ronunciation%??[%- _]*n?e?e?d?e?d?", "[Pp]ronounce", "[Rr]equested[%- _]*pronunciation", "[Rr]e?q?pron", "[Nn]eeds[%- _]*pronunciation",
-- Chart, including Chart/start etc.
"[Cc]hart", "[Cc]hart/[%w_%s]-",
-- Cref and others
"[Cc]ref2?", "[Cc]note",
-- Explain and others
"[Ee]xplain", "[Ff]urther[ ]*explanation[ ]*needed", "[Ee]laboration[ ]*needed", "[Ee]xplanation[ ]*needed",
-- TOC templates
"[Cc][Oo][Mm][Pp][Aa][Cc][Tt][ _]*[Tt][Oo][Cc][8]*[5]*", "[Tt][Oo][Cc]", "09[Aa][Zz]", "[Tt][Oo][Cc][ ]*[Cc][Oo][Mm][Pp][Aa][Cc][Tt]", "[Tt][Oo][Cc][ ]*[Ss][Mm][Aa][Ll][Ll]", "[Cc][Oo][Mm][Pp][Aa][Cc][Tt][ _]*[Aa][Ll][Pp][Hh][Aa][Bb][Ee][Tt][Ii][Cc][ _]*[Tt][Oo][Cc]",
"DEFAULTSORT:.-",
"[Oo]ne[ _]+source"
}
-- The module removes all block templates except these ones
local wantedBlockTemplates = {
"[Hh]istorical populations"
}
local p = {}
local function striptemplate(t)
-- If template is unwanted then return "" (gsub will replace by nothing), else return nil (gsub will keep existing string)
if matchany(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
-- Check image for suitability
local function checkimage(image)
local page = matchany(image, "", d.fileNamespaces, "%s*:[^|%]]*") -- match File:(name) or Image:(name)
if not page then return false end
local startre = ""
if start then startre = "^" end -- a true flag restricts search to start of string
local image = matchany(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
capture_from = 1
while capture_from < mw.ustring.len(text) do
local position, caption = matchany(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"
image = mw.ustring.match(image, "^[^}|\n]*") -- remove later arguments
token = "[[" -- Add File: unless name already begins File: or Image:
if not matchany(image, "^", d.fileNamespaces, "%s*:") then
token = token .. "File:"
end
-- Help gsub convert imagemaps into standard images
local function convertImagemap(imagemap)
local image = matchany(imagemap, "[>\n]%s*", d.fileNamespaces, "[^\n]*")
if image then
return "<!--imagemap-->[[" .. mw.ustring.gsub(image, "[>\n]%s*", "", 1) .. "]]"
if token then -- found a template which is not the prefix to a line of text
if leadstart then -- lead has already started, so keep the template within the text, unless it's a whole line (navbox etc.)
if not filesOnly and not startLine then t = t .. token end
elseif matchany(token, "{{%s*", d.wantedBlockTemplates, "%s*%f[|}]") then
t = t .. token -- keep wanted block templates
end
if text == "" and d.brokenCategory and d.brokenCategory ~= "" and mw.title.getCurrentTitle().isContentPage then
return "[[Category:" .. d.brokenCategory .. "]]"
else
return frame:preprocess(text)
| 