--- @module
local p = {}
local maintenance_categories = {
incorrectly_formatted = "[[Category:Pages using infobox television episode with incorrectly formatted values|%s]]",
unlinked_values = "[[Category:Pages using infobox television episode with unlinked values|%s]]",
image_values_without_an_image = "[[Category:Pages using infobox television episode with image-related values without an image]]",
unnecessary_title_parameter = "[[Category:Pages using infobox television episode with unnecessary title parameter]]",
non_matching_title = "[[Category:Pages using infobox television episode with non-matching title]]",
flag_icon = "[[Category:Pages using infobox television with flag icon]]",
dates_incorrectly_formatted = "[[Category:Pages using infobox television episode with nonstandard dates]]",
manual_display_title = "[[Category:Pages using infobox television episode with unnecessary manual displaytitle]]",
list_markup = "[[Category:Pages using infobox television episode with unnecessary list markup]]",
}
--- Returns the text after removing line breaks (<br> tags) and additional spaces as a result.
---
--- @param text string
--- @return string
local function get_name_with_br_fixes(text)
local title, _ = string.gsub(text, "<br%s?/?>", "")
title, _ = string.gsub(title, " ", " ")
return title
end
--- Returns the page name after replacing quotation marks for single quotes and fixing it to use the
--- "Space+single" and "Single+space" templates if a leading or trailing apostrophe or quotation mark is used.
---
--- Note: per [[MOS:QWQ]] an episode title with quotation marks should be replaced with single quotes.
---
--- @param frame table
--- @param article_title string
--- @return string
local function get_page_name_with_apostrophe_quotation_fixes(frame, article_title)
local page_name, _ = string.gsub(article_title, '"', "'")
local left_side_template = frame:expandTemplate{title = "Space+single"}
local right_side_template = frame:expandTemplate{title = "Single+space"}
page_name, _ = string.gsub(string.gsub(page_name, "^'", left_side_template), "'$", right_side_template)
return page_name
end
--- Returns the series link.
---
--- @param series string
--- @return string
local function get_series_link(series)
local delink = require("Module:Delink")._delink
return delink({series, wikilinks = "target"})
end
--- Returns two strings:
---- The series name after de-linking it and escaping "-".
---- The series name after de-linking it.
---
--- @param series string
--- @return string, string
local function get_series_name(series)
local delink = require("Module:Delink")._delink
local series_name = delink({series})
-- Escape the character "-" as it is needed for string.find() to work.
local _
local series_name_escaped, _ = string.gsub(series_name, "-", "%%-")
return series_name_escaped, series_name
end
--- Returns a table consisting of the episode's title parts.
---
--- The return table's properties:
--- - title - The episode's title.
--- - disambiguation - the disambiguation text without parentheses.
---
--- Note: could potentially be moved to an outside module for other template and module uses.
---
--- @param text string
--- @return table<string, string | nil>
local function get_title_parts(text)
local title, disambiguation = string.match(text, "^(.+) (%b())$")
local titleString = title -- TODO: needed until https://github.com/Benjamin-Dobell/IntelliJ-Luanalysis/issues/63 is resolved.
if not title or type(title) ~= "string" then
titleString = text
end
---@type table<string, string | nil>
local title_parts = {title = --[[---@not number | nil]] titleString, disambiguation = nil}
if not disambiguation or type(disambiguation) ~= "string" then
return title_parts
end
-- Remove outside parentheses from names which use parentheses as part of the name such as "episode (Randall and Hopkirk (Deceased))".
disambiguation = string.sub(--[[---@not number | nil]] disambiguation, 2, -2)
title_parts.disambiguation = --[[---@not number]] disambiguation
return title_parts
end
--- Returns the title used in the {{Lowercase title}} template and an optional maintenance category.
---
--- @param page_text string
--- @param args table
--- @param title_parts table
--- @return string | nil
local function get_lowercase_template_status(page_text, args, title_parts)
local lowercase_template = string.match(page_text, "{{[Ll]owercase title.-}}")
if lowercase_template then
local lowercase_title, _ = string.gsub(title_parts.title,"^%u", string.lower)
if args.title then
if args.title == lowercase_title then
return maintenance_categories.unnecessary_title_parameter
else
return maintenance_categories.non_matching_title
end
return ""
end
return lowercase_title
end
return nil
end
--- Returns the title used in the {{Correct title}} template and an optional maintenance category.
---
--- @param page_text string
--- @param args table
--- @param return_category boolean
--- @return string | nil
local function get_correct_title_value(page_text, args, return_category)
local correct_title_template_pattern = "{{[Cc]orrect title|title=(.*)|reason=.-}}"
local correct_title = string.match(page_text, correct_title_template_pattern)
if not correct_title then
correct_title_template_pattern = "{{[Cc]orrect title|(.*)|reason=.-}}"
correct_title = string.match(page_text, correct_title_template_pattern)
end
if not correct_title and type(correct_title) ~= "string" then
return nil
end
local correct_title_title_parts = get_title_parts(correct_title)
if not correct_title_title_parts.disambiguation then
-- If the correct title value has no disambiguation, check if the title used in the infobox is the same as the title used for the correct title value.
if return_category and args.title then
if args.title == correct_title_title_parts.title then
return maintenance_categories.unnecessary_title_parameter
else
return maintenance_categories.non_matching_title
end
end
return correct_title_title_parts.title
end
local series_name_escaped, _ = get_series_name(args.series)
if series_name_escaped ~= "" and (correct_title_title_parts.disambiguation == series_name_escaped or string.find(correct_title_title_parts.disambiguation, series_name_escaped)) then
if return_category and args.title then
if args.title == correct_title_title_parts.title then
return maintenance_categories.unnecessary_title_parameter
else
return maintenance_categories.non_matching_title
end
end
return correct_title_title_parts.title
end
-- Can't determine if the text in parentheses is disambiguation or part of the title since |series= isn't used.
if return_category then
return ""
end
return correct_title
end
--- Returns the display title text used in either the {{DISPLAYTITLE}} or {{Italic title}} templates.
---
--- @param page_text string
--- @param article_title string
--- @return string | nil
local function get_display_title_text(page_text, article_title)
local title_modification = string.match(page_text, "{{DISPLAYTITLE:(.-)}}")
if title_modification and type(title_modification) == "string" then
return --[[---@not number | nil]] title_modification
end
title_modification = string.match(page_text, "{{Italic title|string=(.-)}}")
if title_modification and type(title_modification) == "string" then
local italic_title_text, _ = string.gsub(article_title, --[[---@not number | nil]] title_modification, "''" .. title_modification .. "''")
return italic_title_text
end
return nil
end
--- Returns a maintenance category if the italic_title value is not "no".
---
--- Infobox parameters checked:
--- - |italic_title=
---
--- @param args table
--- @return string
local function is_italic_title_valid_value(args)
if args.italic_title and args.italic_title ~= "no" then
return string.format(maintenance_categories.incorrectly_formatted, "italic_title")
end
return ""
end
--- Returns a maintenance category if the date is not formatted correctly with a {{Start date}} template.
---
--- Infobox parameters checked:
--- - |airdate=
--- - |released=
--- - |airdate_overall=
---
--- @param start_date string
--- @return string
local function are_dates_formatted_correctly(start_date)
if start_date and not string.find(start_date, "dtstart") then
return maintenance_categories.dates_incorrectly_formatted
end
return ""
end
--- Returns a maintenance category if list markup is used. The infobox can handle list markup correctly.
---
--- Note: the code here is temporarily checking only the parameters which have been converted
--- to use the plainlist class directly. Once current uses will be converted, the function will check all parameters
--- for incorrect usage.
---
--- Infobox parameters checked:
--- - Parameters listed below.
---
--- Currently checks for the following list markup:
--- - <br> tags - per [[MOS:NOBR]].
--- - <li> tags.
--- - "plainlist" class.
--- - "hlist" class.
---
--- @param args table
--- @return string
local function uses_list_markup(args)
local invalid_tags = {
["br"] = "<[bB][rR]%s?/?>",
["li"] = "<li>",
["plainlist"] = "plainlist",
["hlist"] = "hlist",
}
---@type table<string, boolean>
local parameters = {
director = true,
writer = true,
story = true,
teleplay = true,
narrator = true,
presenter = true,
producer = true,
music = true,
photographer = true,
editor = true,
production = true,
airdate = true,
guests = true,
commentary = true,
}
for parameter_name, _ in pairs(parameters) do
for _, list_pattern in pairs(invalid_tags) do
local parameter_value = args[parameter_name]
if parameter_value and string.find(parameter_value, list_pattern) then
return maintenance_categories.list_markup
end
end
end
return ""
end
--- Returns a maintenance category if a flag icon is used.
---
--- All of the infobox values are checked.
---
--- @param args table
--- @return string
local function has_flag_icon(args)
for _, value in pairs(args) do
if string.find(value, "flagicon") then
return maintenance_categories.flag_icon
end
end
return ""
end
--- Returns a maintenance category if the values are linked.
---
--- Infobox parameters checked:
--- - |episode=
--- - |season=
--- - |series_no=
--- - |episode_list=
---
--- The function currently checks if the following values are present:
--- - ]] - links.
---
--- @param args table
--- @return string
local function are_values_linked(args)
local parameters = {
episode = args.episode,
season = args.season,
series_no = args.series_no,
episode_list = args.episode_list,
}
for key, value in pairs(parameters) do
if string.find(value, "]]", 1, true) then
return string.format(maintenance_categories.incorrectly_formatted, key)
end
end
return ""
end
--- Returns a maintenance category if the values are formatted.
---
--- Most of the infobox values are checked. Not included are:
--- - |title= - is handled in is_infobox_title_equal_to_article_title()
--- - |series= - is handled in are_values_links_only()
--- - |next= - is handled in are_values_links_only()
--- - |prev= is handled in are_values_links_only()
--- - |rtitle=
--- - |rprev=
--- - |rnext=
--- - |image_alt=
--- - |alt=
--- - |caption=
--- - |based_on=
--- - |music=
--- - |guests=
---
--- The function currently checks if the following values are present:
--- - '' - italics or bold.
---
--- @param args table
--- @return string
local function are_values_formatted(args)
---@type table<string, boolean>
local ignore_parameters = {
title = true,
series = true,
prev = true,
next = true,
rtitle = true,
rprev = true,
rnext = true,
image_alt = true,
alt = true,
caption = true,
based_on = true,
music = true,
guests = true,
}
for key, value in pairs(args) do
if not ignore_parameters[key] and string.find(value, "''", 1, true) then
return string.format(maintenance_categories.incorrectly_formatted, key)
end
end
return ""
end
--- Returns a maintenance category if the values use additional overall numbering.
---
--- Infobox parameters checked:
--- - |episode=
--- - |season=
--- - |series_no=
---
--- The function currently checks if the following values are present:
--- - overall - unsupported series overall numbering.
---
--- @param args table
--- @return string
local function are_values_using_overall(args)
local parameters = {
episode = args.episode,
season = args.season,
series_no = args.series_no,
}
for key, value in pairs(parameters) do
if string.find(value, "overall") then
return string.format(maintenance_categories.incorrectly_formatted, key)
end
end
return ""
end
--- Returns a maintenance category if the values are unlinked and if additional characters are found in the text.
---
--- Infobox parameters checked:
--- - |series=
--- - |prev=
--- - |next=
---
--- The function currently checks if a value is unlinked or if there is any additional character
--- before or after the linked text.
---
--- @param args table
--- @return string
local function are_values_links_only(args)
local parameters = {
series = args.series,
prev = args.prev,
next = args.next,
}
for key, value in pairs(parameters) do
-- Check whether the values are linked.
if not string.find(value, "%[%[.*%]%]") then
return string.format(maintenance_categories.unlinked_values, key)
end
-- Check whether the values have anything before or after link brackets.
if string.gsub(value, "(%[%[.*%]%])", "") ~= "" then
return string.format(maintenance_categories.incorrectly_formatted, key)
end
end
return ""
end
--- Returns a maintenance category if the |image= value includes the "File:" or "Image:" prefix.
---
--- Infobox parameters checked:
--- - |image=
---
--- @param image string
--- @return string
local function is_image_using_incorrect_syntax(image)
if not image then
return ""
end
if string.find(image, "[Ff]ile:") or string.find(image, "[Ii]mage:") then
return string.format(maintenance_categories.incorrectly_formatted, "image")
end
return ""
end
--- Returns a maintenance category if the |image_size= value includes "px".
---
--- Infobox parameters checked:
--- - |image_size=
---
--- @param image_size string
--- @return string
local function is_image_size_using_px(image_size)
if image_size and string.find(image_size, "px") then
return string.format(maintenance_categories.incorrectly_formatted, "image_size")
end
return ""
end
--- Returns a maintenance category if there is no image file while image auxiliary values are present.
---
--- Infobox parameters checked:
--- - |image=
--- - |image_size=
--- - |image_upright=
--- - |image_alt=
--- - |alt=
--- - |caption=
---
--- @param args table
--- @return string
local function are_image_auxiliary_values_used_for_no_image(args)
if args.image then
return ""
end
if args.image_size or args.image_upright or args.image_alt or args.alt or args.caption then
return maintenance_categories.image_values_without_an_image
end
return ""
end
--- Returns a maintenance category if the infobox title is equal to the article title.
---
--- Infobox parameters checked:
--- - |title=
--- - |series=
--- - |italic_title
---
--- The function currently checks if the infobox title is equal to the article title while ignoring styling such as:
--- - Nowrap spans.
--- - Line breaks.
--- - Leading and trailing apostrophe spaces.
---
--- A return value can be one of three options:
--- - The value of maintenance_categories.non_matching_title - when the args.title does not match the article title.
--- - The value of maintenance_categories.unnecessary_title_parameter - when the args.title matches the article title.
--- - An empty string - when args.title isn't used or the args.title uses an allowed modification
--- (such as a nowrap template) while the rest of the args.title matchs the article title.
---
--- Testing parameters:
--- - |page_test= - a real Wikipedia page to read the content of the page.
--- - |page_title_test= - the title of the page being checked.
---
--- @param frame table
--- @param args table
--- @return string
local function is_infobox_title_equal_to_article_title(frame, args)
if not args.title then
return ""
end
local page_text
if args.page_test then
page_text = mw.title.new(args.page_test):getContent()
else
page_text = mw.title.getCurrentTitle():getContent()
end
-- Check if the article is using a {{Correct title}} template.
local correct_title = get_correct_title_value(page_text, args, true)
if correct_title then
return correct_title
end
local article_title = args.page_title_test
if not args.page_title_test then
article_title = mw.title.getCurrentTitle().text
end
local title_parts = get_title_parts(article_title)
-- Check if the article is using a {{Lowercase title}} template.
local lowercase_title = get_lowercase_template_status(page_text, args, title_parts)
if lowercase_title then
return lowercase_title
end
if title_parts.disambiguation then
local series_name_escaped, _ = get_series_name(args.series)
series_name_escaped = get_name_with_br_fixes(series_name_escaped)
if series_name_escaped ~= "" and (title_parts.disambiguation == series_name_escaped or string.find(title_parts.disambiguation, series_name_escaped)) then
-- Remove disambiguation.
article_title = title_parts.title
end
end
if args.italic_title then
-- Check if the article is using a {{DISPLAYTITLE}} or {{Italic title}} template.
local title_modification = get_display_title_text(page_text, article_title)
if title_modification then
if title_modification == args.title then
return maintenance_categories.unnecessary_title_parameter
else
return maintenance_categories.non_matching_title
end
end
end
local page_name = get_page_name_with_apostrophe_quotation_fixes(frame, article_title)
-- Remove nowrap span.
if string.find(args.title, "nowrap") then
local title = frame:expandTemplate{title = "Strip tags", args = {args.title}}
if title == page_name then
return ""
end
return maintenance_categories.non_matching_title
end
-- Remove line breaks and additional spaces as a result.
if string.find(args.title, "<br%s?/?>") then
local title = get_name_with_br_fixes(args.title)
if title == page_name then
return ""
end
return maintenance_categories.non_matching_title
end
if args.title == page_name then
return maintenance_categories.unnecessary_title_parameter
end
-- Article and infobox titles do not match.
return maintenance_categories.non_matching_title
end
--- Returns the relevant maintenance categories based on the {{Infobox television episode}} values validated.
---
--- @param frame table
--- @return string
function p.validate_values(frame)
local getArgs = require("Module:Arguments").getArgs
local args = getArgs(frame)
---@type string[]
local categories = {}
table.insert(categories, is_infobox_title_equal_to_article_title(frame, args))
table.insert(categories, are_image_auxiliary_values_used_for_no_image(args))
table.insert(categories, is_image_using_incorrect_syntax(args.image))
table.insert(categories, is_image_size_using_px(args.image_size))
table.insert(categories, are_values_links_only(args))
table.insert(categories, are_values_using_overall(args))
table.insert(categories, are_values_formatted(args))
table.insert(categories, are_values_linked(args))
table.insert(categories, has_flag_icon(args))
table.insert(categories, uses_list_markup(args))
table.insert(categories, are_dates_formatted_correctly(args.airdate or args.released))
table.insert(categories, is_italic_title_valid_value(args))
return table.concat(categories)
end
--- Returns an {{Italic dab2}} instance if title qualifies. Also returns a maintenance category if conditions are met.
---
--- The article's title is italicized if the series name is included in the article's title disambiguation.
--- No italicization happens if one of the following conditions is met:
---
--- - |italic_title= is set to "no".
--- - The article's title does not use disambiguation.
--- - No |series= value is set.
--- - The article's disambiguation is not equal or does not include the series name.
---
--- The page is added to a maintenance category if the title is italicized and there is already an
--- {{Italic dab}}, {{Italic title}} or {{DISPLAYTITLE}} template.
---
--- Infobox parameters checked:
--- - |series=
--- - |italic_title=
---
--- Testing parameters:
--- - |page_test= - a real Wikipedia page to read the content of the page.
--- - |page_title_test= - the title of the page being checked.
---
--- @param frame table
--- @return string, string
function p.italic_title(frame)
local getArgs = require("Module:Arguments").getArgs
local args = getArgs(frame)
local page_text
if args.page_test then
page_text = mw.title.new(args.page_test):getContent()
else
page_text = mw.title.getCurrentTitle():getContent()
end
local maintenance_category = ""
-- In case the page does not need to be italicized or can't be automatically done, a "no" value will disable both
-- the italicization and the error handling.
if args.italic_title == "no" then
return "", maintenance_category
end
local article_title = args.page_title_test
if not args.page_title_test then
article_title = mw.title.getCurrentTitle().text
end
-- Check if the page already has an {{Italic dab}}, {{Italic title}} or {{DISPLAYTITLE}} template.
local has_italic_dab, _ = string.find(page_text, "{{[Ii]talic dab")
local has_italic_title, _ = string.find(page_text, "{{[Ii]talic title")
local has_display_title, _ = string.find(page_text, "{{DISPLAYTITLE")
if has_italic_dab or has_italic_title or has_display_title then
maintenance_category = maintenance_categories.manual_display_title
end
local title_parts = get_title_parts(article_title)
-- The title is not italicized if the title does not use disambiguation or if the series parameter isn't used.
if not title_parts.disambiguation or not args.series then
return "", maintenance_category
end
local series_name_escaped, series_name = get_series_name(args.series)
series_name_escaped = get_name_with_br_fixes(series_name_escaped)
series_name = get_name_with_br_fixes(series_name)
-- Check if the disambiguation equals the series name or if the series name can be found in the disambiguation.
local italic_dab
if title_parts.disambiguation == series_name then
italic_dab = frame:expandTemplate{title = "Italic dab2"}
elseif string.find(title_parts.disambiguation, series_name_escaped) then
italic_dab = frame:expandTemplate{title = "Italic dab2", args = {string = series_name}}
else
return "", maintenance_category
end
if args.page_title_test and italic_dab then
italic_dab = "italic_dab"
end
return italic_dab, maintenance_category
end
--- Returns a formatted title string.
---
--- @param rtitle string
--- @return string
local function create_title_with_rtitle_value(rtitle)
local title_pattern = '"(.*)" and "(.*)"'
if string.find(rtitle, title_pattern) then
local episode1, episode2 = string.match(rtitle, title_pattern)
local title_format = "\"'''%s'''\" and \"'''%s'''\""
return string.format(title_format, episode1, episode2)
end
local title_pattern_br = '"(.*)" and%s?<br%s?/?>%s?"(.*)"'
if string.find(rtitle, title_pattern_br) then
local episode1, episode2 = string.match(rtitle, title_pattern_br)
local title_format = "\"'''%s'''\" and<br/> \"'''%s'''\""
return string.format(title_format, episode1, episode2)
end
return string.format("'''%s'''", rtitle)
end
--- Returns the text used for the |above= field of the infobox.
---
--- Infobox parameters checked:
--- - |rtitle=
--- - |title=
--- - |series=
---
--- Testing parameters:
--- - |page_test= - a real Wikipedia page to read the content of the page.
--- - |page_title_test= - the title of the page being checked.
---
--- @param frame table
--- @return string
function p.above_title(frame)
local getArgs = require("Module:Arguments").getArgs
local args = getArgs(frame)
if args.rtitle then
return create_title_with_rtitle_value(args.rtitle)
end
local page
if args.page_test then
page = mw.title.new(args.page_test)
else
page = mw.title.getCurrentTitle()
end
local page_text = page:getContent()
local article_title = args.page_title_test
if not args.page_title_test then
article_title = page.text
end
local title_format = "\"'''%s'''\""
local correct_title = get_correct_title_value(page_text, args, false)
if correct_title then
return string.format(title_format, correct_title)
end
local title_parts = get_title_parts(article_title)
local lowercase_title = get_lowercase_template_status(page_text, args, title_parts)
if lowercase_title then
return string.format(title_format, lowercase_title)
end
if args.italic_title and not args.rtitle then
local title_modification = get_display_title_text(page_text, article_title)
if title_modification then
return string.format(title_format, title_modification)
end
end
if args.title then
return string.format(title_format, args.title)
end
local series_name_escaped, _ = get_series_name(args.series)
if not title_parts.disambiguation or (series_name_escaped ~= "" and (title_parts.disambiguation == series_name_escaped or string.find(title_parts.disambiguation, series_name_escaped))) then
return string.format(title_format, get_page_name_with_apostrophe_quotation_fixes(frame, title_parts.title))
end
return string.format(title_format, get_page_name_with_apostrophe_quotation_fixes(frame, article_title))
end
--- Returns a list of episodes link if not formatted, otherwise returns the text used for args.episode_list.
---
--- Infobox parameters checked:
--- - |episode_list=
--- - |series=
---
--- @param frame table
--- @return string
function p.episode_list(frame)
local getArgs = require("Module:Arguments").getArgs
---@type table<string, string>
local args = getArgs(frame)
if args.episode_list then
for _, v in pairs({"]]", "''"}) do
if string.find(args.episode_list, v) then
return args.episode_list
end
end
if string.find(args.episode_list, "[Ss]toryline") then
return "[[" .. args.episode_list .. "|Storylines]]"
end
return "[[" .. args.episode_list .. "|List of episodes]]"
end
if args.series then
local series_name = get_series_link(args.series)
local list_of_episodes = "List of " .. series_name .. " episodes"
if mw.title.new(list_of_episodes):getContent() then
return "[[" .. list_of_episodes .. "|List of episodes]]"
end
end
end
--- Returns the relevant maintenance categories based on the {{Infobox television crossover episode}} values validated.
---
--- @param frame table
--- @return string
function p.validate_values_crossover(frame)
local getArgs = require("Module:Arguments").getArgs
local args = getArgs(frame)
---@type string[]
local categories = {}
table.insert(categories, are_image_auxiliary_values_used_for_no_image(args))
table.insert(categories, is_image_using_incorrect_syntax(args.image))
table.insert(categories, is_image_size_using_px(args.image_size))
table.insert(categories, has_flag_icon(args))
table.insert(categories, are_dates_formatted_correctly(args.airdate_overall))
for i = 1, 5 do
if not args["series" .. i] then
break
end
local nested_args = {
series = args["series" .. i],
episode = args["episode_no" .. i],
season = args["season" .. i],
airdate = args["airdate" .. i],
prev = args["prev" .. i],
next = args["next" .. i],
episode_list = args["episode_list" .. i],
}
table.insert(categories, are_values_links_only(nested_args))
table.insert(categories, are_values_using_overall(nested_args))
table.insert(categories, are_values_formatted(nested_args))
table.insert(categories, are_values_linked(nested_args))
table.insert(categories, are_dates_formatted_correctly(nested_args.airdate))
end
return table.concat(categories, "")
end
return p
