Linguifex

Module:headword: Difference between revisions

← Older edit
No edit summary
Tag: Reverted
No edit summary
 
(9 intermediate revisions by the same user not shown)
Line 2: Line 2:


-- Named constants for all modules used, to make it easier to swap out sandbox versions.
-- Named constants for all modules used, to make it easier to swap out sandbox versions.
local debug_track_module = "Module:debug/track"
local en_utilities_module = "Module:en-utilities"
local en_utilities_module = "Module:en-utilities"
local gender_and_number_module = "Module:getn"
local gender_and_number_module = "Module:gender and number"
local headword_data_module = "Module:headword/data"
local headword_data_module = "Module:headword/data"
local headword_page_module = "Module:headword/page"
local headword_page_module = "Module:headword/page"
Line 37: Line 38:
--[==[
--[==[
Loaders for functions in other modules, which overwrite themselves with the target function when called. This ensures modules are only loaded when needed, retains the speed/convenience of locally-declared pre-loaded functions, and has no overhead after the first call, since the target functions are called directly in any subsequent calls.]==]
Loaders for functions in other modules, which overwrite themselves with the target function when called. This ensures modules are only loaded when needed, retains the speed/convenience of locally-declared pre-loaded functions, and has no overhead after the first call, since the target functions are called directly in any subsequent calls.]==]
local function debug_track(...)
debug_track = require(debug_track_module)
return debug_track(...)
end
local function encode_entities(...)
local function encode_entities(...)
encode_entities = require(string_utilities_module).encode_entities
encode_entities = require(string_utilities_module).encode_entities
Line 174: Line 180:
-- If set to true, categories always appear, even in non-mainspace pages
-- If set to true, categories always appear, even in non-mainspace pages
local test_force_categories = false
local test_force_categories = false
-- Add a tracking category to track entries with certain (unusually undesirable) properties. `track_id` is an identifier
-- for the particular property being tracked and goes into the tracking page. Specifically, this adds a link in the
-- page text to [[Wiktionary:Tracking/headword/TRACK_ID]], meaning you can find all entries with the `track_id` property
-- by visiting [[Special:WhatLinksHere/Wiktionary:Tracking/headword/TRACK_ID]].
--
-- If `lang` (a language object) is given, an additional tracking page [[Wiktionary:Tracking/headword/TRACK_ID/CODE]] is
-- linked to where CODE is the language code of `lang`, and you can find all entries in the combination of `track_id`
-- and `lang` by visiting [[Special:WhatLinksHere/Wiktionary:Tracking/headword/TRACK_ID/CODE]]. This makes it possible to
-- isolate only the entries with a specific tracking property that are in a given language. Note that if `lang`
-- references at etymology-only language, both that language's code and its full parent's code are tracked.
local function track(track_id, lang)
local tracking_page = "headword/" .. track_id
if lang and lang:hasType("etymology-only") then
debug_track{tracking_page, tracking_page .. "/" .. lang:getCode(),
tracking_page .. "/" .. lang:getFullCode()}
elseif lang then
debug_track{tracking_page, tracking_page .. "/" .. lang:getCode()}
else
debug_track(tracking_page)
end
return true
end




Line 363: Line 392:
else
else
head_parts = concat(head_parts)
head_parts = concat(head_parts)
end
if has_manual_translits then
-- [[Special:WhatLinksHere/Wiktionary:Tracking/headword/manual-tr]]
-- [[Special:WhatLinksHere/Wiktionary:Tracking/headword/manual-tr/LANGCODE]]
track("manual-tr", data.lang)
end
end


Line 401: Line 436:
if not saw_translit_page and data.lang:hasType("etymology-only") then
if not saw_translit_page and data.lang:hasType("etymology-only") then
langname = data.lang:getFullName()
langname = data.lang:getFullName()
transliteration_page = new_title(langname .. " transliteration")
transliteration_page = new_title(langname .. " transliteration", "Wiktionary")


if transliteration_page and transliteration_page:getContent() then
if transliteration_page and transliteration_page:getContent() then
translits_formatted = " [[" .. langname .. " transliteration|•]]" .. translits_formatted
translits_formatted = " [[Wiktionary:" .. langname .. " transliteration|•]]" .. translits_formatted
end
end
end
end
Line 468: Line 503:
-- right into the 'data' table to disable inflection links of the entire headword
-- right into the 'data' table to disable inflection links of the entire headword
-- when inflected forms aren't entry-worthy, e.g.: in Vulgar Latin
-- when inflected forms aren't entry-worthy, e.g.: in Vulgar Latin
local nolinkinfl = part.face == "hypothetical" or part.nolinkinfl or data.nolinkinfl
local nolinkinfl = part.face == "hypothetical" or (part.nolink and track("nolink") or part.nolinkinfl) or (
data.nolink and track("nolink") or data.nolinkinfl)


local formatted
local formatted
Line 584: Line 620:
local title = mw.title.new(stripped_physical_term)
local title = mw.title.new(stripped_physical_term)
if title and not title:getContent() then
if title and not title:getContent() then
insert(data.categories, data.lang:getFullName() .. " " .. plpos .. " with red links in their headword lines")
return true
return true
end
end
Line 753: Line 788:
-- that.
-- that.
if tbl == true then
if tbl == true then
if page.raw_defaultsort ~= sortkey then
insert(lang_cats, lang:getFullName() .. " terms with non-redundant non-automated sortkeys")
end
return
return
end
end
Line 765: Line 797:
different = true
different = true
end
end
end
if redundant then
insert(lang_cats, lang:getFullName() .. " terms with redundant sortkeys")
end
if different then
insert(lang_cats, lang:getFullName() .. " terms with non-redundant non-automated sortkeys")
end
end
return sortkey
return sortkey
Line 782: Line 808:
if tbl then
if tbl then
sortkey = handle_raw_sortkeys(tbl, sortkey, page, lang, lang_cats)
sortkey = handle_raw_sortkeys(tbl, sortkey, page, lang, lang_cats)
insert(lang_cats, canonical .. " entries with topic categories using raw markup")
end
end
tbl = page.wikitext_langname_cat[canonical]
tbl = page.wikitext_langname_cat[canonical]
if tbl then
if tbl then
handle_raw_sortkeys(tbl, sortkey, page, lang, lang_cats)
handle_raw_sortkeys(tbl, sortkey, page, lang, lang_cats)
insert(lang_cats, canonical .. " entries with language name categories using raw markup")
end
if get_current_L2() ~= canonical then
insert(lang_cats, canonical .. " entries with incorrect language header")
end
end
end
end
Line 888: Line 909:
local escaped_langname = pattern_escape(full_langname)
local escaped_langname = pattern_escape(full_langname)
local matches_lang_pattern = "^" .. escaped_langname .. " "
local matches_lang_pattern = "^" .. escaped_langname .. " "
for _, cat in ipairs(data.categories) do
-- Does the category begin with the language name? If not, tag it with a tracking category.
if not cat:find(matches_lang_pattern) then
-- [[Special:WhatLinksHere/Wiktionary:Tracking/headword/no lang category]]
-- [[Special:WhatLinksHere/Wiktionary:Tracking/headword/no lang category/LANGCODE]]
track("no lang category", data.lang)
end
end


-- If `pos_category` not given, try to infer it from the first specified category. If this doesn't work, we
-- If `pos_category` not given, try to infer it from the first specified category. If this doesn't work, we
Line 918: Line 947:
-- add an appropriate category.
-- add an appropriate category.
local postype = export.pos_lemma_or_nonlemma(data.pos_category)
local postype = export.pos_lemma_or_nonlemma(data.pos_category)
local main_cat = data.lang:getMainCategoryName()
    local main_cat = data.lang:getMainCategoryName()
if not postype then
    if not postype then
elseif not data.noposcat then
    elseif not data.noposcat then
if postype:match("^lemma") and main_cat ~= "lemma" then
        if postype:match("^lemma") and main_cat ~= "lemma" then
postype = main_cat
            postype = main_cat
end
        end
insert(data.categories, 1, full_langname .. " " .. postype .. "s")
        insert(data.categories, 1, full_langname .. " " .. postype .. "s")
end
    end
   
    insert(data.categories, 1, "Contionary")


-- EXPERIMENTAL: see [[Wiktionary:Beer parlour/2024/June#Decluttering the altform mess]]
-- EXPERIMENTAL: see [[Wiktionary:Beer parlour/2024/June#Decluttering the altform mess]]
Line 961: Line 992:
end
end


if is_reconstructed then
if is_reconstructed and not data.lang:hasType("conlang") then
default_head = "*" .. default_head
default_head = "*" .. default_head
end
end
Line 1,014: Line 1,045:


local auto_sc = data.lang:findBestScript(head.term)
local auto_sc = data.lang:findBestScript(head.term)
if (
auto_sc:getCode() == "None" and
find_best_script_without_lang(head.term):getCode() ~= "None"
) then
insert(data.categories, full_langname .. " terms in nonstandard scripts")
end
if not (head.sc or data.sc) then -- No script code given, so use autodetected script.
if not (head.sc or data.sc) then -- No script code given, so use autodetected script.
head.sc = auto_sc
head.sc = auto_sc
Line 1,025: Line 1,050:
if not head.sc then -- Overall script code given.
if not head.sc then -- Overall script code given.
head.sc = data.sc
head.sc = data.sc
end
-- Track uses of sc parameter.
if head.sc:getCode() == auto_sc:getCode() then
if not data.no_script_code_cat then
insert(data.categories, full_langname .. " terms with redundant script codes")
end
else
if not data.no_script_code_cat then
insert(data.categories, full_langname .. " terms with non-redundant manual script codes")
end
end
end
end
end
Line 1,072: Line 1,087:
if automated_tr then
if automated_tr then
local manual_tr = head.tr
local manual_tr = head.tr
if manual_tr then
if remove_links(manual_tr) == remove_links(automated_tr) then
insert(data.categories, full_langname .. " terms with redundant transliterations")
else
insert(data.categories, full_langname .. " terms with non-redundant manual transliterations")
end
end


if not manual_tr then
if not manual_tr then
Line 1,167: Line 1,174:


------------ 9. Insert additional categories. ------------
------------ 9. Insert additional categories. ------------
if data.force_cat_output then
-- [[Special:WhatLinksHere/Wiktionary:Tracking/headword/force cat output]]
track("force cat output")
end


if has_redundant_head_param then
if has_redundant_head_param then
Line 1,413: Line 1,425:
insert(data.categories, full_langname .. " terms spelled with " .. character)
insert(data.categories, full_langname .. " terms spelled with " .. character)
end
end
end
end
if data.heads[1].sc:isSystem("alphabet") then
local pagename, i = page.pagename:ulower(), 2
while umatch(pagename, "(%a)" .. ("%1"):rep(i)) do
i = i + 1
insert(data.categories, full_langname .. " terms with " .. i .. " consecutive instances of the same letter")
end
end
end
end
Line 1,430: Line 1,434:
and is_palindrome(page.pagename, data.lang, data.heads[1].sc) then
and is_palindrome(page.pagename, data.lang, data.heads[1].sc) then
insert(data.categories, full_langname .. " palindromes")
insert(data.categories, full_langname .. " palindromes")
end
if namespace == "" and not lang_reconstructed then
for _, head in ipairs(data.heads) do
if page.full_raw_pagename ~= get_link_page(remove_links(head.term), data.lang, head.sc) then
-- [[Special:WhatLinksHere/Wiktionary:Tracking/headword/pagename spelling mismatch]]
-- [[Special:WhatLinksHere/Wiktionary:Tracking/headword/pagename spelling mismatch/LANGCODE]]
track("pagename spelling mismatch", data.lang)
break
end
end
end
end


Retrieved from "https://linguifex.com/wiki/Module:headword"