Module:Headword: Difference between revisions
Tag: Undo |
No edit summary |
||
Line 10: | Line 10: | ||
local toBeTagged = m_data.toBeTagged | local toBeTagged = m_data.toBeTagged | ||
-- If set to true, categories always appear, even in non-mainspace pages | |||
local test_force_categories = false | |||
local function test_script(text, script_code) | local function test_script(text, script_code) | ||
Line 50: | Line 39: | ||
local function preprocess(data) | local spacingPunctuation = "[%s%p]+" | ||
--[[ List of punctuation or spacing characters that are found inside of words. | |||
Used to exclude characters from the regex above. ]] | |||
local wordPunc = "-־׳״'.·*’་•" | |||
local notWordPunc = "[^" .. wordPunc .. "]+" | |||
-- Return true if the given head is multiword according to the algorithm used | |||
-- in full_headword(). | |||
function export.head_is_multiword(head) | |||
for possibleWordBreak in mw.ustring.gmatch(head, spacingPunctuation) do | |||
if mw.ustring.find(possibleWordBreak, notWordPunc) then | |||
return true | |||
end | |||
end | |||
return false | |||
end | |||
-- Add links to a multiword head. | |||
function export.add_multiword_links(head) | |||
local function workaround_to_exclude_chars(s) | |||
return mw.ustring.gsub(s, notWordPunc, "]]%1[[") | |||
end | |||
head = "[[" | |||
.. mw.ustring.gsub( | |||
head, | |||
spacingPunctuation, | |||
workaround_to_exclude_chars | |||
) | |||
.. "]]" | |||
--[=[ | |||
use this when workaround is no longer needed: | |||
head = "[[" | |||
.. mw.ustring.gsub(head, WORDBREAKCHARS, "]]%1[[") | |||
.. "]]" | |||
Remove any empty links, which could have been created above | |||
at the beginning or end of the string. | |||
]=] | |||
head = mw.ustring.gsub(head, "%[%[%]%]", "") | |||
return head | |||
end | |||
local function non_categorizable() | |||
return (title:inNamespace("") and title.text:find("^Unsupported titles/")) | |||
or (title:inNamespace("Appendix") and title.text:find("^Gestures/")) | |||
end | |||
local function preprocess(data, postype) | |||
--[=[ | --[=[ | ||
[[Special:WhatLinksHere/Template:tracking/headword/heads-not-table]] | [[Special:WhatLinksHere/Template:tracking/headword/heads-not-table]] | ||
Line 57: | Line 99: | ||
if type(data.heads) ~= "table" then | if type(data.heads) ~= "table" then | ||
if data.heads then | if data.heads then | ||
require("Module:debug") | require("Module:debug/track")("headword/heads-not-table") | ||
end | end | ||
Line 65: | Line 107: | ||
if type(data.translits) ~= "table" then | if type(data.translits) ~= "table" then | ||
if data.translits then | if data.translits then | ||
require("Module:debug") | require("Module:debug/track")("headword/translits-not-table") | ||
end | end | ||
Line 73: | Line 115: | ||
if type(data.transcriptions) ~= "table" then | if type(data.transcriptions) ~= "table" then | ||
if data.transcriptions then | if data.transcriptions then | ||
require("Module:debug") | require("Module:debug/track")("headword/transcriptions-not-table") | ||
end | end | ||
Line 92: | Line 134: | ||
local default_head | local default_head | ||
if is_reconstructed then | if is_reconstructed then | ||
default_head = require("Module:utilities").plain_gsub(pagename, data.lang:getCanonicalName() .. "/", "") | |||
else | else | ||
default_head = | default_head = subpagename | ||
end | end | ||
local unmodified_default_head = default_head | |||
-- Add links to multi-word page names when appropriate | -- Add links to multi-word page names when appropriate | ||
if data.lang:getCode() ~= "zh" | if data.lang:getCode() ~= "zh" and (not is_reconstructed) and | ||
export.head_is_multiword(default_head) then | |||
default_head = export.add_multiword_links(default_head) | |||
end | end | ||
Line 154: | Line 162: | ||
data.heads[i] = head | data.heads[i] = head | ||
end | end | ||
-- If the first head is multiword (after removing links), maybe insert into "LANG multiword terms" | |||
if not data.nomultiwordcat and postype == "lemma" and not m_data.no_multiword_cat[data.lang:getCode()] then | |||
-- Check for spaces or hyphens, but exclude prefixes and suffixes. | |||
-- Use the pagename, not the head= value, because the latter may have extra | |||
-- junk in it, e.g. superscripted text that throws off the algorithm. | |||
local checkpattern = ".[%s%-፡]." | |||
if m_data.hyphen_not_multiword_sep[data.lang:getCode()] then | |||
-- Exclude hyphens if the data module states that they should for this language | |||
checkpattern = ".[%s፡]." | |||
end | |||
if mw.ustring.find(unmodified_default_head, checkpattern) and not non_categorizable() then | |||
table.insert(data.categories, data.lang:getCanonicalName() .. " multiword terms") | |||
end | |||
end | |||
--[[ Try to detect the script if it was not provided | --[[ Try to detect the script if it was not provided | ||
We use the first headword for this, and assume | We use the first headword for this, and assume | ||
Line 211: | Line 234: | ||
-- Format a headword with transliterations | -- Format a headword with transliterations | ||
local function format_headword(data) | local function format_headword(data) | ||
local m_scriptutils = require("Module:script utilities") | local m_scriptutils = require("Module:script utilities") | ||
Line 217: | Line 239: | ||
-- Need to do it this way because translit[1] might be nil while translit[2] is not | -- Need to do it this way because translit[1] might be nil while translit[2] is not | ||
local has_translits = false | local has_translits = false | ||
local has_manual_translits = false | |||
-- Format the headwords | -- Format the headwords | ||
Line 222: | Line 245: | ||
if data.translits[i] or data.transcriptions[i] then | if data.translits[i] or data.transcriptions[i] then | ||
has_translits = true | has_translits = true | ||
end | |||
if data.translits[i] and data.translits[i].is_manual or data.transcriptions[i] then | |||
has_manual_translits = true | |||
end | end | ||
-- Apply processing to the headword, for formatting links and such | -- Apply processing to the headword, for formatting links and such | ||
if head:find("[[", nil, true) and (not data.sc or data.sc:getCode() ~= "Imag") then | if head:find("[[", nil, true) and (not data.sc or data.sc:getCode() ~= "Imag") then | ||
head = | head = require("Module:links").language_link({term = head, lang = data.lang}, false) | ||
end | end | ||
Line 240: | Line 266: | ||
local translits_formatted = "" | local translits_formatted = "" | ||
if has_manual_translits then | |||
-- [[Special:WhatLinksHere/Template:tracking/headword/has-manual-translit/LANG]] | |||
require("Module:debug/track")("headword/has-manual-translit/" .. data.lang:getCode()) | |||
end | |||
if has_translits then | if has_translits then | ||
-- Format the transliterations | -- Format the transliterations | ||
local translits = data.translits | local translits = data.translits | ||
Line 289: | Line 321: | ||
local function format_genders(data) | local function format_genders(data) | ||
if data.genders and #data.genders > 0 then | if data.genders and #data.genders > 0 then | ||
local | local pos_for_cat | ||
return " " .. | if not data.nogendercat and not m_data.no_gender_cat[data.lang:getCode()] then | ||
local pos_category = data.pos_category:gsub("^reconstructed ", "") | |||
pos_for_cat = m_data.pos_for_gender_number_cat[pos_category] | |||
end | |||
local text, cats = require("Module:gender and number").format_genders(data.genders, data.lang, pos_for_cat) | |||
for _, cat in ipairs(cats) do | |||
table.insert(data.categories, cat) | |||
end | |||
return " " .. text | |||
else | else | ||
return "" | return "" | ||
Line 298: | Line 338: | ||
local function format_inflection_parts(data, parts) | local function format_inflection_parts(data, parts) | ||
for key, part in ipairs(parts) do | for key, part in ipairs(parts) do | ||
if type(part) ~= "table" then | if type(part) ~= "table" then | ||
Line 305: | Line 343: | ||
end | end | ||
local qualifiers | local qualifiers | ||
local reftext | |||
if part.qualifiers and #part.qualifiers > 0 then | if part.qualifiers and #part.qualifiers > 0 then | ||
Line 311: | Line 350: | ||
-- [[Special:WhatLinksHere/Template:tracking/headword/qualifier]] | -- [[Special:WhatLinksHere/Template:tracking/headword/qualifier]] | ||
require("Module:debug") | require("Module:debug/track")("headword/qualifier") | ||
end | |||
if part.refs and #part.refs > 0 then | |||
local refs = {} | |||
for _, ref in ipairs(part.refs) do | |||
if type(ref) ~= "table" then | |||
ref = {text = ref} | |||
end | |||
local refargs | |||
if ref.name or ref.group then | |||
refargs = {name = ref.name, group = ref.group} | |||
end | |||
table.insert(refs, mw.getCurrentFrame():extensionTag("ref", ref.text, refargs)) | |||
end | |||
reftext = table.concat(refs) | |||
end | end | ||
Line 317: | Line 370: | ||
local face = part.hypothetical and "hypothetical" or "bold" | local face = part.hypothetical and "hypothetical" or "bold" | ||
local nolink = part.hypothetical or part.nolink | local nolink = part.hypothetical or part.nolink | ||
if part.label then | |||
-- There should be a better way of italicizing a label. As is, this isn't customizable. | |||
part = "<i>" .. part.label .. "</i>" | |||
else | |||
-- Convert the term into a full link | |||
-- Don't show a transliteration here, the consensus seems to be not to | |||
-- show them in headword lines to avoid clutter. | |||
part = require("Module:links").full_link( | |||
{ | |||
term = not nolink and part.term or nil, | |||
alt = part.alt or (nolink and part.term or nil), | |||
lang = part.lang or data.lang, | |||
sc = part.sc or parts.sc or (not part.lang and data.sc), | |||
id = part.id, | |||
genders = part.genders, | |||
tr = part.translit or (not (parts.enable_auto_translit or data.inflections.enable_auto_translit) and "-" or nil), | |||
ts = part.transcription, | |||
accel = parts.accel or partaccel, | |||
}, | |||
face, | |||
false | |||
) | |||
end | |||
if qualifiers then | |||
part = qualifiers .. part | |||
end | |||
if reftext then | |||
part = part .. reftext | |||
end | |||
parts[key] = part | parts[key] = part | ||
Line 348: | Line 411: | ||
elseif parts.request then | elseif parts.request then | ||
parts_output = " <small>[please provide]</small>" | parts_output = " <small>[please provide]</small>" | ||
.. require("Module:utilities") | .. require("Module:utilities/format_categories")( | ||
{"Requests for inflections in " .. data.lang:getCanonicalName() .. " entries"}, | {"Requests for inflections in " .. data.lang:getCanonicalName() .. " entries"}, | ||
lang, | lang, | ||
nil, | nil, | ||
nil, | nil, | ||
data.force_cat_output, | data.force_cat_output or test_force_categories, | ||
data.sc | data.sc | ||
) | ) | ||
Line 374: | Line 437: | ||
end | end | ||
end | end | ||
-- Return "lemma" if the given POS is a lemma, "non-lemma form" if a non-lemma form, or nil | |||
-- if unknown. The POS passed in must be in its plural form ("nouns", "prefixes", etc.). | |||
-- If you have a POS in its singular form, call pluralize() in [[Module:string utilities]] to | |||
-- pluralize it in a smart fashion that knows when to add '-s' and when to add '-es'. | |||
-- | |||
-- If `best_guess` is given and the POS is in neither the lemma nor non-lemma list, guess | |||
-- based on whether it ends in " forms"; otherwise, return nil. | |||
function export.pos_lemma_or_nonlemma(plpos, best_guess) | |||
-- Is it a lemma category? | |||
if isLemma[plpos] or isLemma[plpos:gsub("^reconstructed ", "")] then | |||
return "lemma" | |||
-- Is it a nonlemma category? | |||
elseif isNonLemma[plpos] | |||
or isNonLemma[plpos:gsub("^reconstructed ", "")] | |||
or isLemma[plpos:gsub("^mutated ", "")] | |||
or isNonLemma[plpos:gsub("^mutated ", "")] then | |||
return "non-lemma form" | |||
elseif best_guess then | |||
return plpos:find(" forms$") and "non-lemma form" or "lemma" | |||
else | |||
return nil | |||
end | |||
end | |||
local function show_headword_line(data) | local function show_headword_line(data) | ||
Line 379: | Line 468: | ||
-- Check the namespace against the language type | -- Check the namespace against the language type | ||
if namespace == "" then | |||
if data.lang:getType() == "reconstructed" then | |||
error("Entries for this language must be placed in the Reconstruction: namespace.") | |||
elseif data.lang:getType() == "appendix-constructed" then | |||
error("Entries for this language must be placed in the Appendix: namespace.") | |||
end | |||
end | |||
local tracking_categories = {} | local tracking_categories = {} | ||
Line 394: | Line 483: | ||
table.insert(data.categories, 1, pos_category) | table.insert(data.categories, 1, pos_category) | ||
end | end | ||
end | |||
if data.sccat and data.sc then | |||
table.insert(data.categories, data.lang:getCanonicalName() .. " " .. data.pos_category | |||
.. " in " .. data.sc:getDisplayForm()) | |||
end | end | ||
-- Is it a lemma category? | -- Is it a lemma category? | ||
local postype = export.pos_lemma_or_nonlemma(data.pos_category) | |||
if not postype then | |||
-- We don't know what this category is, so tag it with a tracking category. | |||
--[=[ | --[=[ | ||
[[Special:WhatLinksHere/Template:tracking/headword/unrecognized pos]] | [[Special:WhatLinksHere/Template:tracking/headword/unrecognized pos]] | ||
]=] | ]=] | ||
table.insert(tracking_categories, "head tracking/unrecognized pos") | table.insert(tracking_categories, "head tracking/unrecognized pos") | ||
require("Module:debug") | require("Module:debug/track"){ | ||
"headword/unrecognized pos", | "headword/unrecognized pos", | ||
"headword/unrecognized pos/lang/" .. data.lang:getCode(), | "headword/unrecognized pos/lang/" .. data.lang:getCode(), | ||
"headword/unrecognized pos/pos/" .. data.pos_category | "headword/unrecognized pos/pos/" .. data.pos_category | ||
} | } | ||
elseif not data.noposcat then | |||
table.insert(data.categories, 1, data.lang:getCanonicalName() .. " " .. postype .. "s") | |||
end | end | ||
-- Preprocess | -- Preprocess | ||
preprocess(data | preprocess(data, postype) | ||
if namespace == "" and data.lang:getType() ~= "reconstructed" then | if namespace == "" and data.lang:getType() ~= "reconstructed" then | ||
local m_links = require("Module:links") | |||
for _, head in ipairs(data.heads) do | for _, head in ipairs(data.heads) do | ||
if title.prefixedText ~= m_links.getLinkPage(m_links.remove_links(head), data.lang) then | if title.prefixedText ~= m_links.getLinkPage(m_links.remove_links(head), data.lang) then | ||
Line 434: | Line 517: | ||
[[Special:WhatLinksHere/Template:tracking/headword/pagename spelling mismatch]] | [[Special:WhatLinksHere/Template:tracking/headword/pagename spelling mismatch]] | ||
]=] | ]=] | ||
require("Module:debug") | require("Module:debug/track"){ | ||
"headword/pagename spelling mismatch", | "headword/pagename spelling mismatch", | ||
"headword/pagename spelling mismatch/" .. data.lang:getCode() | "headword/pagename spelling mismatch/" .. data.lang:getCode() | ||
Line 448: | Line 531: | ||
format_genders(data) .. | format_genders(data) .. | ||
format_inflections(data) .. | format_inflections(data) .. | ||
require("Module:utilities") | require("Module:utilities/format_categories")( | ||
tracking_categories, data.lang, data.sort_key, nil, data.force_cat_output, data.sc | tracking_categories, data.lang, data.sort_key, nil, | ||
data.force_cat_output or test_force_categories, data.sc | |||
) | ) | ||
end | end | ||
Line 470: | Line 554: | ||
-- Track uses of sc parameter | -- Track uses of sc parameter | ||
local best = require("Module:scripts").findBestScript(pagename, data.lang) | local best = require("Module:scripts").findBestScript(pagename, data.lang) | ||
require("Module:debug") | require("Module:debug/track")("headword/sc") | ||
if data.sc:getCode() == best:getCode() then | if data.sc:getCode() == best:getCode() then | ||
require("Module:debug") | require("Module:debug/track")("headword/sc/redundant") | ||
require("Module:debug") | require("Module:debug/track")("headword/sc/redundant/" .. data.sc:getCode()) | ||
else | else | ||
require("Module:debug") | require("Module:debug/track")("headword/sc/needed") | ||
require("Module:debug") | require("Module:debug/track")("headword/sc/needed/" .. data.sc:getCode()) | ||
end | end | ||
end | end | ||
Line 483: | Line 567: | ||
local displayTitle | local displayTitle | ||
-- Assumes that the scripts in "toBeTagged" will never occur in the Reconstruction namespace. | -- Assumes that the scripts in "toBeTagged" will never occur in the Reconstruction namespace. | ||
if namespace == "" and data.sc and toBeTagged[data.sc:getCode()] | -- Avoid tagging ASCII as Hani even when it is tagged as Hani in the | ||
data.sc:getCode() == "Jpan" and (test_script(pagename, "Hira") or test_script(pagename, "Kana")) then | -- headword, as in [[check]]. The check for ASCII might need to be expanded | ||
-- to a check for any Latin characters and whitespace or punctuation. | |||
if (namespace == "" and data.sc and toBeTagged[data.sc:getCode()] | |||
and not pagename:find "^[%z\1-\127]+$") | |||
or (data.sc:getCode() == "Jpan" and (test_script(pagename, "Hira") or test_script(pagename, "Kana"))) then | |||
displayTitle = '<span class="' .. data.sc:getCode() .. '">' .. pagename .. '</span>' | displayTitle = '<span class="' .. data.sc:getCode() .. '">' .. pagename .. '</span>' | ||
elseif namespace == "Reconstruction" then | elseif namespace == "Reconstruction" then | ||
Line 517: | Line 605: | ||
[[Special:WhatLinksHere/Template:tracking/headword/force cat output]] | [[Special:WhatLinksHere/Template:tracking/headword/force cat output]] | ||
]=] | ]=] | ||
require("Module:debug") | require("Module:debug/track")("headword/force cat output") | ||
end | end | ||
Line 526: | Line 614: | ||
-- Were any categories specified? | -- Were any categories specified? | ||
if data.categories and #data.categories > 0 then | if data.categories and #data.categories > 0 then | ||
local lang_name = require("Module:string") | local lang_name = require("Module:string/pattern_escape")(data.lang:getCanonicalName()) | ||
for _, cat in ipairs(data.categories) do | for _, cat in ipairs(data.categories) do | ||
-- Does the category begin with the language name? If not, tag it with a tracking category. | -- Does the category begin with the language name? If not, tag it with a tracking category. | ||
Line 536: | Line 624: | ||
[[Special:WhatLinksHere/Template:tracking/head tracking/no lang category]] | [[Special:WhatLinksHere/Template:tracking/head tracking/no lang category]] | ||
]=] | ]=] | ||
require("Module:debug") | require("Module:debug/track"){ | ||
"headword/no lang category", | "headword/no lang category", | ||
"headword/no lang category/lang/" .. data.lang:getCode() | "headword/no lang category/lang/" .. data.lang:getCode() | ||
Line 564: | Line 652: | ||
if standard then | if standard then | ||
if mw.ustring.len(title.subpageText) ~= 1 and not | if mw.ustring.len(title.subpageText) ~= 1 and not non_categorizable() then | ||
for character in mw.ustring.gmatch(title.subpageText, "([^" .. standard .. "])") do | for character in mw.ustring.gmatch(title.subpageText, "([^" .. standard .. "])") do | ||
local upper = mw.ustring.upper(character) | local upper = mw.ustring.upper(character) | ||
Line 579: | Line 667: | ||
-- Categorise for palindromes | -- Categorise for palindromes | ||
if title.nsText ~= "Reconstruction" | if title.nsText ~= "Reconstruction" and mw.ustring.len(title.subpageText)>2 | ||
and require('Module:palindromes').is_palindrome( | and require('Module:palindromes').is_palindrome( | ||
title.subpageText, data.lang, data.sc | title.subpageText, data.lang, data.sc | ||
Line 585: | Line 673: | ||
table.insert(data.categories, data.lang:getCanonicalName() .. " palindromes") | table.insert(data.categories, data.lang:getCanonicalName() .. " palindromes") | ||
end | end | ||
-- This may add more categories (e.g. gender categories), so make sure it gets | |||
-- evaluated first. | |||
local text = show_headword_line(data) | |||
return | return | ||
text .. | |||
require("Module:utilities") | require("Module:utilities/format_categories")( | ||
data.categories, data.lang, data.sort_key, nil, data.force_cat_output, data.sc | data.categories, data.lang, data.sort_key, nil, | ||
data.force_cat_output or test_force_categories, data.sc | |||
) .. | ) .. | ||
require("Module:utilities") | require("Module:utilities/format_categories")( | ||
tracking_categories, data.lang, data.sort_key, nil, data.force_cat_output, data.sc | tracking_categories, data.lang, data.sort_key, nil, | ||
data.force_cat_output or test_force_categories, data.sc | |||
) | ) | ||
end | end | ||
return export | return export |
Revision as of 00:33, 10 April 2022
- The following documentation is located at Module:Headword/documentation. [edit]
- Useful links: subpage list • transclusions • testcases • sandbox
This module is used to show headword lines, along with any annotations like genders, transliterations and inflections. It's used by the template {{head}}
, via the submodule Module:headword/templates. It's also used by many other headword modules; for a full list, see Category:Headword-line modules. Some of the data used by this module is found in Module:headword/data.
export.head_is_multiword
function export.head_is_multiword(head)
This function lacks documentation. Please add a description of its usages, inputs and outputs, or its difference from similar functions, or make it local to remove it from the function list.
export.add_multiword_links
function export.add_multiword_links(head)
This function lacks documentation. Please add a description of its usages, inputs and outputs, or its difference from similar functions, or make it local to remove it from the function list.
export.pos_lemma_or_nonlemma
function export.pos_lemma_or_nonlemma(plpos, best_guess)
This function lacks documentation. Please add a description of its usages, inputs and outputs, or its difference from similar functions, or make it local to remove it from the function list.
export.full_headword
function export.full_headword(data)
This function lacks documentation. Please add a description of its usages, inputs and outputs, or its difference from similar functions, or make it local to remove it from the function list.
Further explanations for full_headword()
The sole argument, data
, is a table containing the following items (WARNING: they will be destructively modified):
{
lang = language_object,
pagename = nil or "pagename",
heads = { "head1", "head2", "head3", ... } or {
{
term = nil or "head1",
tr = nil or "translit1",
ts = nil or "transcription1",
sc = nil or script_object,
q = nil or {"left_qualifier1", "left_qualifier2", ...},
qq = nil or {"right_qualifier1", "right_qualifier2", ...},
refs = nil or {{text = "ref_text1" or "", name = nil or "ref_name1", group = nil or "ref_group1"}, ...},
separator = nil or "separator",
},
...
},
translits = { [1] = "translit1", [3] = "translit3", ... },
transcriptions = { [2] = "transcription2", [3] = "transcription3", ... },
sc = script_object,
inflections = {
enable_auto_translit = boolean,
{ label = "grammatical_category", "inflected_form1", "inflected_form2", ... },
{ label = "grammatical_category", accel = {form = "tag|tag", lemma = "lémma"}, "inflected_form1", "inflected_form2", ... },
{
label = "grammatical_category",
accel = {
form = "tag|tag",
target = "form_target",
tr = nil or "form_manual_translit",
gender = "gender_spec" or {"gender_spec1", "gender_spec2", ...},
pos = "form_part_of_speech",
lemma = nil or "lémma",
lemma_translit = nil or "lemma_manual_translit",
no_store = boolean,
},
sc = nil or inflection_specific_script_object,
enable_auto_translit = boolean,
"inflected_form1",
{
term = "inflected_form2",
alt = nil or "display_text",
translit = nil or "manual_transliteration",
transcription = nil or "manual_transcription",
gender = {"gender1", "gender2", {spec = "gender3", qualifiers = nil or {"qualifier1", "qualifier2", ... }}},
accel = {form = "tag|tag|tag", lemma = "lemma_of_inflected_form", lemma_translit = "manual_translit" },
lang = nil or term_specific_lang_object,
sc = nil or term_specific_script_object,
id = "sense_id",
q = nil or {"left_qualifier1", "left_qualifier2", ... },
qq = nil or {"right_qualifier1", "right_qualifier2", ... },
refs = nil or {{text = "ref_text1" or "", name = nil or "ref_name1", group = nil or "ref_group1"}, ...},
separator = nil or "separator",
nolink = boolean,
hypothetical = boolean,
},
{
label = "raw_textual_label",
q = nil or {"left_qualifier1", "left_qualifier2", ... },
qq = nil or {"right_qualifier1", "right_qualifier2", ... },
refs = nil or {{text = "ref_text1" or "", name = nil or "ref_name1", group = nil or "ref_group1"}, ...},
separator = nil or "separator",
},
...
},
{ label = "grammatical_category", request = true },
...
},
genders = {
"gender1",
{spec = "gender2", qualifiers = {"qualifier1", "qualifier2", ...}},
...
},
pos_category = "plural_part_of_speech",
categories = { "category1", "category2", ... },
whole_page_categories = { "category1", "category2", ... },
force_cat_output = boolean,
sccat = boolean,
noposcat = boolean,
nogendercat = boolean,
nomultiwordcat = boolean,
nopalindromecat = boolean,
nolink = boolean,
sort_key = "sort_key",
id = "sense_id",
}
Further explanation:
is required and is a language object from Module:languages corresponding to a given language. For example, useLua logo Uses Lua:
to retrieve the object corresponding to Russian.Lua logo Uses Lua:
is optional and allows you to override the pagename used variously in the module (e.g. as the default value when a head is omitted, for setting categories such as palindromes andLua logo Uses Lua: terms spelled with CHAR
, etc.).
is a table listing the heads of the headword. Each element is either a string specifying only the headword itself (old-style), or an object specifying all the properties of the headword (new-style). You cannot mix and match these two styles; all elements should be of one type or the other. If no heads are specified at all (Lua logo Uses Lua:
is omitted or is an empty array), a default head is set based on the assumed pagename (either the actual pagename or the value ofLua logo Uses Lua:
, if set). When using old-style head strings, a given head in the array can beLua logo Uses Lua:
, in which case a default head is set as above. When head objects are used, a given object can have the following properties:Lua logo Uses Lua:
: A string specifying the headword. This can be omitted, in which case a default head is set as above. Explicit headwords are generally used to specify extra diacritics (in languages with such diacritics, e.g. Russian, Arabic, Latin, Ancient Greek, Old English, etc.), or to link individual words of a multiword term, particularly when the words are inflected forms. Note that by default, each word is linked individually to itself, so there is no need to specify links for a term like a golden key can open any door. Some additional notes:Lua logo Uses Lua: - If a headword string contains wikilinks, they are converted into language-section links for the given language (using
Module:links#language_link
, which is also used by{{l}}
). For example, giving
, if the language provided is English, will produce:Lua logo Uses Lua:
. If string is prefixed with * or if any of the links are, then they are interpreted as reconstructed terms and it will create links to the Reconstruction namespace as appropriate.Lua logo Uses Lua: - If the page name contains spaces or punctuation marks (except for punctuation marks that are used inside of words), it is split and each individual word is automatically wikilinked as above.
- If the current page is in the
Reconstruction:
namespace, then an asterisk
will be prepended to the headword to indicate that it is a reconstructed term.Lua logo Uses Lua:
: A string specifying the transliteration of the headword. This is only needed when the headword is in a non-Latin script, and even then only when the automatic transliteration specified using the language's transliteration module is incorrect (or the language has no transliteration module, such as with Persian and Hebrew). For languages with a transliteration module, pass inLua logo Uses Lua:
to suppress the transliteration entirely.Lua logo Uses Lua:
: A string specifying the transcription of the headword. This is only used in a few languages with non-Latin scripts where the spelling is significantly different from the pronunciation, such as Akkadian, Old Persian or Hittite. In cases like this, the transliteration usually reflects the spelling and the transcription reflects the pronunciation. For this reason, transcriptions are displayed between slashes. Transcriptions should NOT be used simply to display IPA pronunciation of a language like Russian or Arabic. Unlike for transliterations, there are no automatic transcription modules.Lua logo Uses Lua:
: An optional script object from Module:scripts corresponding to a given script, specifying the script that the headword is in. If omitted, defaults to the top-levelLua logo Uses Lua:
value. Most of the time, neither the per-headword script nor top-level script need to be specified: If both are omitted, Module:scripts will determine the script(s) using the list of scripts in the language's data file and the characters that are in the headword. Specifically, if there are multiple possible scripts for a language, the script with the largest number of characters in the headword is chosen.Lua logo Uses Lua:
: An optional array specifying one of more qualifiers displayed to the left of the headword. Qualifiers are displayed in italics and with parentheses around them, and are intended to specify relevant properties of the headword, especially when there is more than one headword.Lua logo Uses Lua:
: An optional array specifying one of more qualifiers displayed to the right of the headword, as above.Lua logo Uses Lua:
: An optional array specifying one of more references (i.e. footnotes) for the headword. This is similar to usingLua logo Uses Lua: <ref>...</ref>
to specify a reference/footnote after a given word in the text. Each element of the array is either a string (the text of the reference) or an object of the form
. In this latter format:Lua logo Uses Lua: - [[:{text = "ref_text" or "", name = nil or "ref_name", group = nil or "ref_group"}]]
specifies the reference text (which cannot beLua logo Uses Lua:
; use a blank string when cross-referencing to another reference);Lua logo Uses Lua:
gives an optional name to the reference for cross-reference purposes, if the reference text is non-empty, similarly toLua logo Uses Lua: <ref name="ref_name">ref_text</ref>
; however, if the reference text is empty, it specifies a cross-reference to a previously-named reference, similarly to<ref name="ref_name"/>
;
gives an optional group to the reference for grouping purposes, similarly toLua logo Uses Lua: <ref name="ref_name" group="ref_group">ref_text</ref>
; however, if the reference text is empty, it specifies the group of a cross-reference to a previously-named reference, similarly to<ref name="ref_name" group="ref_group"/>
.
: The separator preceding the headword. If omitted, the default value isLua logo Uses Lua: <i>or</i>
(i.e. the italicized word or surrounded by spaces) for the second and higher headword, and a blank string for the first headword. Use a blank string to request no separator at all.
is an optional table listing the transliterations corresponding to each headword inLua logo Uses Lua:
, when old-style head strings are used; omitting this field is equivalent to setting it to an empty list. If new-style head objects are used, this field must be omitted. The Nth numbered entry should be either a string specifying the transliteration of headword N, or may be omitted, as with theLua logo Uses Lua:
property described above. Note that, if there are multiple headwords, the table inLua logo Uses Lua:
might have entries in the middle of the list that areLua logo Uses Lua:
. A list of this sort cannot be created withLua logo Uses Lua:
, as attempting to insertLua logo Uses Lua:
this way does nothing. Instead, each transliteration must be explicitly assigned using a number as index, e.g.Lua logo Uses Lua:
; here, itemLua logo Uses Lua: - [[:{ [1] = "string", [3] = "string", ... }]]
isLua logo Uses Lua:
, because no value was assigned to it.Lua logo Uses Lua:
is an optional table listing the transcriptions corresponding to each headword inLua logo Uses Lua:
, when old-style head strings are used; omitting this field is equivalent to setting it to an empty list. If new-style head objects are used, this field must be omitted. It is of the same format asLua logo Uses Lua:
, and can have holes in it as needed. The meaning of the transcription field is as described abobe forLua logo Uses Lua:
.Lua logo Uses Lua:
is an optional script object from Module:scripts corresponding to a given script. If specified, this applies equally to all heads specified usingLua logo Uses Lua:
; if you need to specify per-head scripts, use the head object format documented above. Most of the time you can omit this item, and Module:scripts will determine the script(s) as specified above for theLua logo Uses Lua:
headword property.Lua logo Uses Lua:
is a table listing the gender/number specifications for the headwords. This can be omitted for no genders or numbers. Each element is either a string specifying a gender/number spec, or a table of the formLua logo Uses Lua:
. In either case, the accepted values for genders or numbers are given in Module:gender and number; examples areLua logo Uses Lua: - [[:{spec = "gender/number_spec", qualifiers = nil or {"qualifier1", "qualifier2", ...}]]
for masculine,Lua logo Uses Lua:
for feminine animate plural andLua logo Uses Lua:
for noun class 2 in languages such as Swahili that have noun classes. If the format with qualifiers is given, the qualifiers are displayed to the left of the gender/number specification. Categories are automatically added according to the specific genders, e.g.Lua logo Uses Lua: LANG masculine nouns
for the language specified in
if the gender is masculine and the part of speech (see below) isLua logo Uses Lua: nouns
orreconstructed nouns
. To suppress the addition of these categories, specify
.Lua logo Error: no modules specified
is a table listing the inflections to be displayed in the headword entry. The format of this table is somewhat complex and is described below underLua logo Uses Lua: format_inflections
.
is the part-of-speech category for the entry. This is one of theLua logo Uses Lua: lemma
andnonlemma
parts of speech listed in Module:headword/data. It should be in the plural: for example,
. If this item is omitted, the part of speech category must be included in as the first item inLua logo Uses Lua:
.Lua logo Uses Lua:
is a table listing the categories to which the entry containing the headword will be added. The first category should be a part-of-speech category, with the canonical name of the language at the beginning –Lua logo Uses Lua:
– unless the part of speech is given in the fieldLua logo Uses Lua:
.Lua logo Uses Lua:
is a table listing language-agnostic categories to which the page will be added, which it is nevertheless useful for the headword module to handle (e.g. Category:Unsupported titles). Because they are not tied to a language, pages in them should be sorted according to theirLua logo Uses Lua: {{DEFAULTSORT:}}
values for the sake of consistency. Note that some of these - including "Category:Unsupported titles" - are already handled automatically.
is a string specifying a sort key for the categories listed inLua logo Uses Lua:
. Sort keys should usually be omitted, because theLua logo Uses Lua: format_categories
function in Module:utilities will generate a suitable sortkey in most cases. The sortkey is used to ensure that the page is listed in the correct order in the categories to which it belongs.
is a boolean value determining whether or not to link the forms of the entire headword. Not to be confused withLua logo Uses Lua:
, which disables linking only for one of the forms. It is used, for example, by Module:la-headword for reconstructed terms.Lua logo Uses Lua: Examples
A simple example
full_headword{ lang = require("Module:languages").getByCode("en"), -- language code heads = {"book"}, -- headwords inflections = { {label = "plural", "books"} -- inflections }, categories = {"English nouns"}, -- part-of-speech category }
might give (depending on the page it's run on):
<strong class="Latn headword" lang="en">book</strong> (''plural'' <b class="Latn" lang="en">[[books#English|books]]</b>)[[Category:English lemmas|HEADWORD]][[Category:English nouns|HEADWORD]]
which displays as:
- book (plural books)
A fuller example
full_headword{ lang = require("Module:languages").getByCode("de"), heads = {"Hund"}, genders = {"m"}, inflections = { {label = "genitive", "Hundes", "Hunds"}, {label = "plural", "Hunde", {term="Hünde", q="nonstandard"}}, {label = "diminutive", {term = "Hündchen", genders = {"n"}}, {nolink=true, term = "Hündlein", genders = {"n"}} } }, categories = {"German nouns"}, }
might give (depending on the page it's run on):
<strong class="Latn headword" lang="de">Hund</strong> <span class="gender"><abbr title="masculine gender">m</abbr></span> (''genitive'' <b class="Latn" lang="de">[[Hundes#German|Hundes]]</b> ''or'' <b class="Latn" lang="de">[[Hunds#German|Hunds]]</b>, ''plural'' <b class="Latn" lang="de">[[Hunde#German|Hunde]] </b>''or (nonstandard)''<b> [[Hünde#German|Hünde]]</b>, ''diminutive'' <b class="Latn" lang="de">[[Hündchen#German|Hündchen]]</b> <span class="gender"><abbr title="neuter gender">n</abbr></span> ''or'' <b class="Latn" lang="de">Hündlein</b> <span class="gender"><abbr title="neuter gender">n</abbr></span>)[[Category:German lemmas|HEADWORD]][[Category:German nouns|HEADWORD]]
which displays as:
- Hund m (genitive Hundes or Hunds, plural Hunde or (nonstandard) Hünde, diminutive Hündchen n or Hündlein n)
An example in a non-Latin script
This example is in Russian, which has automatic transliteration:
full_headword{ lang = require("Module:languages").getByCode("ru"), heads = {"кни́га"}, genders = {"f-in"}, inflections = { {label = "genitive", "кни́ги"}, {label = "nominative plural", "кни́ги"}, {label = "genitive plural", "книг"} }, categories = {"Russian nouns"}, }
might give (depending on the page it's run on):
<strong class="Cyrl headword" lang="ru">кни́га</strong> [[Wiktionary:Russian transliteration|•]] (<span class="tr" lang=""><span class="tr" lang="">kníga</span></span>) <span class="gender"><abbr title="feminine gender">f</abbr> <abbr title="inanimate">inan</abbr></span> (''genitive'' <b class="Cyrl" lang="ru">[[книги#Russian|кни́ги]]</b>, ''nominative plural'' <b class="Cyrl" lang="ru">[[книги#Russian|кни́ги]]</b>, ''genitive plural'' <b class="Cyrl" lang="ru">[[книг#Russian|книг]]</b>)[[Category:Russian lemmas|HEADWORD]][[Category:Russian nouns|HEADWORD]]
which displays as
Note a few things about the transliteration:
- If the transliteration is specified and non-empty, Module:headword adds some stuff before and after it. For example, if the transliteration is
and the language is Hebrew, producesLua logo Uses Lua: which looks like “• (foo)”.[[Wiktionary:Hebrew transliteration|•]] (<span lang="">foo</span>)
- The bullet linking to a transliteration policy page is only added if the page actually exists.
A fuller example in a non-Latin script
This example is in Russian, with two headwords, each of which requires manual transliteration:
full_headword{ lang = require("Module:languages").getByCode("ru"), heads = { {term = "интервьюе́р", tr = "intɛrvʹjuér"}, {term = "интервью́ер", "intɛrvʹjújer"}, }, genders = {"m-an"}, inflections = { {label = "genitive", "интервьюе́ра", "интервью́ера"}, {label = "nominative plural", "интервьюе́ры", "интервью́еры"}, {label = "genitive plural", "интервьюе́ров", "интервью́еров"}, }, categories = {"Russian nouns"}, }
might give (depending on the page it's run on):
<strong class="Cyrl headword" lang="ru">интервьюе́р</strong> ''or'' <strong class="Cyrl headword" lang="ru">интервью́ер</strong> [[Wiktionary:Russian transliteration|•]] (<span class="tr" lang=""><span class="tr" lang="">intɛrvʹjuér</span> ''or'' <span class="tr" lang="">intɛrvʹjújer</span></span>) <span class="gender"><abbr title="masculine gender">m</abbr> <abbr title="animate">anim</abbr></span> (''genitive'' <b class="Cyrl" lang="ru">[[интервьюера#Russian|интервьюе́ра]]</b> ''or'' <b class="Cyrl" lang="ru">[[интервьюера#Russian|интервью́ера]]</b>, ''nominative plural'' <b class="Cyrl" lang="ru">[[интервьюеры#Russian|интервьюе́ры]]</b> ''or'' <b class="Cyrl" lang="ru">[[интервьюеры#Russian|интервью́еры]]</b>, ''genitive plural'' <b class="Cyrl" lang="ru">[[интервьюеров#Russian|интервьюе́ров]]</b> ''or'' <b class="Cyrl" lang="ru">[[интервьюеров#Russian|интервью́еров]]</b>)[[Category:Russian lemmas|HEADWORD]][[Category:Russian nouns|HEADWORD]]
which displays as
- интервьюе́р or интервью́ер • (intɛrvʹjuér or intɛrvʹjújer) m anim (genitive интервьюе́ра or интервью́ера, nominative plural интервьюе́ры or интервью́еры, genitive plural интервьюе́ров or интервью́еров)
Another fuller example in a non-Latin script
This example is in Arabic, with embedded links in the headword, manual transliteration in an inflection and use of
:Lua logo Uses Lua: full_headword{ lang = require("Module:languages").getByCode("ar"), heads = { {term = "[[غُدّة]] [[بَصَلِيّ|بَصَلِيّة]] [[إحْلِيلِيّ|إحْلِيلِيّة]]", tr = "ḡudda baṣaliyya ʾiḥlīliyya"}, }, genders = {"f"}, inflections = { enable_auto_translit = true, {label = "plural", {term="غُدَد بَصَلِيَّة إِحْلِيلِيَة", translit="ḡudad baṣaliyya ʾiḥlīliyya"}}, }, categories = {"Arabic nouns"}, }
might give (depending on the page it's run on):
<strong class="Arab headword" lang="ar">[[غدة#Arabic|غُدّة]] [[بصلي#Arabic|بَصَلِيّة]] [[إحليلي#Arabic|إحْلِيلِيّة]]</strong> [[Wiktionary:Arabic transliteration|•]] (<span class="tr" lang=""><span class="tr" lang="">ḡudda baṣaliyya ʾiḥlīliyya</span></span>) <span class="gender"><abbr title="feminine gender">f</abbr></span> (''plural'' <b class="Arab" lang="ar">[[غدد بصلية إحليلية#Arabic|غُدَد بَصَلِيَّة إِحْلِيلِيَة]]</b> (<span lang="" class="tr">ḡudad baṣaliyya ʾiḥlīliyya</span>))[[Category:Arabic lemmas|HEADWORD]][[Category:Arabic nouns|HEADWORD]]
which displays as
- غُدّة بَصَلِيّة إحْلِيلِيّة • (ḡudda baṣaliyya ʾiḥlīliyya) f (plural غُدَد بَصَلِيَّة إِحْلِيلِيَة (ḡudad baṣaliyya ʾiḥlīliyya))
Proposed/planned changes
- Checking for invalid genders, given a list of genders that are valid for a particular language.
- If a headword string contains wikilinks, they are converted into language-section links for the given language (using
local export = {}
local m_data = mw.loadData("Module:headword/data")
local title = mw.title.getCurrentTitle()
local isLemma = m_data.lemmas
local isNonLemma = m_data.nonlemmas
local notranslit = m_data.notranslit
local toBeTagged = m_data.toBeTagged
-- If set to true, categories always appear, even in non-mainspace pages
local test_force_categories = false
local function test_script(text, script_code)
if type(text) == "string" and type(script_code) == "string" then
local sc = require("Module:scripts").getByCode(script_code)
local characters
if sc then
characters = sc:getCharacters()
end
local out
if characters then
text = mw.ustring.gsub(text, "%W", "")
out = mw.ustring.find(text, "[" .. characters .. "]")
end
if out then
return true
else
return false
end
else
mw.log("Parameters to test_script were incorrect.")
return nil
end
end
local spacingPunctuation = "[%s%p]+"
--[[ List of punctuation or spacing characters that are found inside of words.
Used to exclude characters from the regex above. ]]
local wordPunc = "-־׳״'.·*’་•"
local notWordPunc = "[^" .. wordPunc .. "]+"
-- Return true if the given head is multiword according to the algorithm used
-- in full_headword().
function export.head_is_multiword(head)
for possibleWordBreak in mw.ustring.gmatch(head, spacingPunctuation) do
if mw.ustring.find(possibleWordBreak, notWordPunc) then
return true
end
end
return false
end
-- Add links to a multiword head.
function export.add_multiword_links(head)
local function workaround_to_exclude_chars(s)
return mw.ustring.gsub(s, notWordPunc, "]]%1[[")
end
head = "[["
.. mw.ustring.gsub(
head,
spacingPunctuation,
workaround_to_exclude_chars
)
.. "]]"
--[=[
use this when workaround is no longer needed:
head = "[["
.. mw.ustring.gsub(head, WORDBREAKCHARS, "]]%1[[")
.. "]]"
Remove any empty links, which could have been created above
at the beginning or end of the string.
]=]
head = mw.ustring.gsub(head, "%[%[%]%]", "")
return head
end
local function non_categorizable()
return (title:inNamespace("") and title.text:find("^Unsupported titles/"))
or (title:inNamespace("Appendix") and title.text:find("^Gestures/"))
end
local function preprocess(data, postype)
--[=[
[[Special:WhatLinksHere/Template:tracking/headword/heads-not-table]]
[[Special:WhatLinksHere/Template:tracking/headword/translits-not-table]]
]=]
if type(data.heads) ~= "table" then
if data.heads then
require("Module:debug/track")("headword/heads-not-table")
end
data.heads = { data.heads }
end
if type(data.translits) ~= "table" then
if data.translits then
require("Module:debug/track")("headword/translits-not-table")
end
data.translits = { data.translits }
end
if type(data.transcriptions) ~= "table" then
if data.transcriptions then
require("Module:debug/track")("headword/transcriptions-not-table")
end
data.transcriptions = { data.transcriptions }
end
if not data.heads or #data.heads == 0 then
data.heads = {""}
end
-- Determine if term is reconstructed
local is_reconstructed = data.lang:getType() == "reconstructed"
or title.nsText == "Reconstruction"
-- Create a default headword.
local subpagename = title.subpageText
local pagename = title.text
local default_head
if is_reconstructed then
default_head = require("Module:utilities").plain_gsub(pagename, data.lang:getCanonicalName() .. "/", "")
else
default_head = subpagename
end
local unmodified_default_head = default_head
-- Add links to multi-word page names when appropriate
if data.lang:getCode() ~= "zh" and (not is_reconstructed) and
export.head_is_multiword(default_head) then
default_head = export.add_multiword_links(default_head)
end
if is_reconstructed then
default_head = "*" .. default_head
end
-- If a head is the empty string "", then replace it with the default
for i, head in ipairs(data.heads) do
if head == "" then
head = default_head
else
if head == default_head and data.lang:getCanonicalName() == "English" then
table.insert(data.categories, data.lang:getCanonicalName() .. " terms with redundant head parameter")
end
end
data.heads[i] = head
end
-- If the first head is multiword (after removing links), maybe insert into "LANG multiword terms"
if not data.nomultiwordcat and postype == "lemma" and not m_data.no_multiword_cat[data.lang:getCode()] then
-- Check for spaces or hyphens, but exclude prefixes and suffixes.
-- Use the pagename, not the head= value, because the latter may have extra
-- junk in it, e.g. superscripted text that throws off the algorithm.
local checkpattern = ".[%s%-፡]."
if m_data.hyphen_not_multiword_sep[data.lang:getCode()] then
-- Exclude hyphens if the data module states that they should for this language
checkpattern = ".[%s፡]."
end
if mw.ustring.find(unmodified_default_head, checkpattern) and not non_categorizable() then
table.insert(data.categories, data.lang:getCanonicalName() .. " multiword terms")
end
end
--[[ Try to detect the script if it was not provided
We use the first headword for this, and assume
that all of them have the same script
This *should* always be true, right? ]]
if not data.sc then
data.sc = require("Module:scripts").findBestScript(data.heads[1], data.lang)
end
for i, val in pairs(data.translits) do
data.translits[i] = {display = val, is_manual = true}
end
-- Make transliterations
for i, head in ipairs(data.heads) do
local translit = data.translits[i]
-- Try to generate a transliteration if necessary
-- Generate it if the script is not Latn or similar, and if no transliteration was provided
if translit and translit.display == "-" then
translit = nil
elseif not translit and not (data.sc:getCode():find("Latn", nil, true) or data.sc:getCode() == "Latinx" or data.sc:getCode() == "None") and (not data.sc or data.sc:getCode() ~= "Imag") then
translit = data.lang:transliterate(require("Module:links").remove_links(head), data.sc)
-- There is still no transliteration?
-- Add the entry to a cleanup category.
if not translit and not notranslit[data.lang:getCode()] then
translit = "<small>transliteration needed</small>"
table.insert(data.categories, "Requests for transliteration of " .. data.lang:getCanonicalName() .. " terms")
end
if translit then
translit = {display = translit, is_manual = false}
end
end
-- Link to the transliteration entry for languages that require this
if translit and data.lang:link_tr() then
translit.display = require("Module:links").full_link{
term = translit.display,
lang = data.lang,
sc = require("Module:scripts").getByCode("Latn"),
tr = "-"
}
end
data.translits[i] = translit
end
if data.id and type(data.id) ~= "string" then
error("The id in the data table should be a string.")
end
end
-- Format a headword with transliterations
local function format_headword(data)
local m_scriptutils = require("Module:script utilities")
-- Are there non-empty transliterations?
-- Need to do it this way because translit[1] might be nil while translit[2] is not
local has_translits = false
local has_manual_translits = false
-- Format the headwords
for i, head in ipairs(data.heads) do
if data.translits[i] or data.transcriptions[i] then
has_translits = true
end
if data.translits[i] and data.translits[i].is_manual or data.transcriptions[i] then
has_manual_translits = true
end
-- Apply processing to the headword, for formatting links and such
if head:find("[[", nil, true) and (not data.sc or data.sc:getCode() ~= "Imag") then
head = require("Module:links").language_link({term = head, lang = data.lang}, false)
end
-- Add language and script wrapper
if i == 1 then
head = m_scriptutils.tag_text(head, data.lang, data.sc, "head", nil, data.id)
else
head = m_scriptutils.tag_text(head, data.lang, data.sc, "head", nil)
end
data.heads[i] = head
end
local translits_formatted = ""
if has_manual_translits then
-- [[Special:WhatLinksHere/Template:tracking/headword/has-manual-translit/LANG]]
require("Module:debug/track")("headword/has-manual-translit/" .. data.lang:getCode())
end
if has_translits then
-- Format the transliterations
local translits = data.translits
local transcriptions = data.transcriptions
if translits then
-- using pairs() instead of ipairs() in case there is a gap
for i, _ in pairs(translits) do
if type(i) == "number" then
translits[i] = m_scriptutils.tag_translit(translits[i].display, data.lang:getCode(), "head", nil, translits[i].is_manual)
end
end
end
if transcriptions then
for i, _ in pairs(transcriptions) do
if type(i) == "number" then
transcriptions[i] = m_scriptutils.tag_transcription(transcriptions[i], data.lang:getCode(), "head")
end
end
end
for i = 1, math.max(#translits, #transcriptions) do
local translits_formatted = {}
table.insert(translits_formatted, translits[i] and translits[i] or "")
table.insert(translits_formatted, (translits[i] and transcriptions[i]) and " " or "")
table.insert(translits_formatted, transcriptions[i] and "/" .. transcriptions[i] .. "/" or "")
data.translits[i] = table.concat(translits_formatted)
end
translits_formatted = " (" .. table.concat(data.translits, " <i>or</i> ") .. ")"
local transliteration_page = mw.title.new(data.lang:getCanonicalName() .. " transliteration", "Wiktionary")
if transliteration_page then
local success, exists = pcall(function () return transliteration_page.exists end)
if success and exists then
translits_formatted = " [[Wiktionary:" .. data.lang:getCanonicalName() .. " transliteration|•]]" .. translits_formatted
end
end
end
return table.concat(data.heads, " <i>or</i> ") .. translits_formatted
end
local function format_genders(data)
if data.genders and #data.genders > 0 then
local pos_for_cat
if not data.nogendercat and not m_data.no_gender_cat[data.lang:getCode()] then
local pos_category = data.pos_category:gsub("^reconstructed ", "")
pos_for_cat = m_data.pos_for_gender_number_cat[pos_category]
end
local text, cats = require("Module:gender and number").format_genders(data.genders, data.lang, pos_for_cat)
for _, cat in ipairs(cats) do
table.insert(data.categories, cat)
end
return " " .. text
else
return ""
end
end
local function format_inflection_parts(data, parts)
for key, part in ipairs(parts) do
if type(part) ~= "table" then
part = {term = part}
end
local qualifiers
local reftext
if part.qualifiers and #part.qualifiers > 0 then
qualifiers = require("Module:qualifier").format_qualifier(part.qualifiers) .. " "
-- [[Special:WhatLinksHere/Template:tracking/headword/qualifier]]
require("Module:debug/track")("headword/qualifier")
end
if part.refs and #part.refs > 0 then
local refs = {}
for _, ref in ipairs(part.refs) do
if type(ref) ~= "table" then
ref = {text = ref}
end
local refargs
if ref.name or ref.group then
refargs = {name = ref.name, group = ref.group}
end
table.insert(refs, mw.getCurrentFrame():extensionTag("ref", ref.text, refargs))
end
reftext = table.concat(refs)
end
local partaccel = part.accel
local face = part.hypothetical and "hypothetical" or "bold"
local nolink = part.hypothetical or part.nolink
if part.label then
-- There should be a better way of italicizing a label. As is, this isn't customizable.
part = "<i>" .. part.label .. "</i>"
else
-- Convert the term into a full link
-- Don't show a transliteration here, the consensus seems to be not to
-- show them in headword lines to avoid clutter.
part = require("Module:links").full_link(
{
term = not nolink and part.term or nil,
alt = part.alt or (nolink and part.term or nil),
lang = part.lang or data.lang,
sc = part.sc or parts.sc or (not part.lang and data.sc),
id = part.id,
genders = part.genders,
tr = part.translit or (not (parts.enable_auto_translit or data.inflections.enable_auto_translit) and "-" or nil),
ts = part.transcription,
accel = parts.accel or partaccel,
},
face,
false
)
end
if qualifiers then
part = qualifiers .. part
end
if reftext then
part = part .. reftext
end
parts[key] = part
end
local parts_output = ""
if #parts > 0 then
parts_output = " " .. table.concat(parts, " <i>or</i> ")
elseif parts.request then
parts_output = " <small>[please provide]</small>"
.. require("Module:utilities/format_categories")(
{"Requests for inflections in " .. data.lang:getCanonicalName() .. " entries"},
lang,
nil,
nil,
data.force_cat_output or test_force_categories,
data.sc
)
end
return "<i>" .. parts.label .. "</i>" .. parts_output
end
-- Format the inflections following the headword
local function format_inflections(data)
if data.inflections and #data.inflections > 0 then
-- Format each inflection individually
for key, infl in ipairs(data.inflections) do
data.inflections[key] = format_inflection_parts(data, infl)
end
return " (" .. table.concat(data.inflections, ", ") .. ")"
else
return ""
end
end
-- Return "lemma" if the given POS is a lemma, "non-lemma form" if a non-lemma form, or nil
-- if unknown. The POS passed in must be in its plural form ("nouns", "prefixes", etc.).
-- If you have a POS in its singular form, call pluralize() in [[Module:string utilities]] to
-- pluralize it in a smart fashion that knows when to add '-s' and when to add '-es'.
--
-- If `best_guess` is given and the POS is in neither the lemma nor non-lemma list, guess
-- based on whether it ends in " forms"; otherwise, return nil.
function export.pos_lemma_or_nonlemma(plpos, best_guess)
-- Is it a lemma category?
if isLemma[plpos] or isLemma[plpos:gsub("^reconstructed ", "")] then
return "lemma"
-- Is it a nonlemma category?
elseif isNonLemma[plpos]
or isNonLemma[plpos:gsub("^reconstructed ", "")]
or isLemma[plpos:gsub("^mutated ", "")]
or isNonLemma[plpos:gsub("^mutated ", "")] then
return "non-lemma form"
elseif best_guess then
return plpos:find(" forms$") and "non-lemma form" or "lemma"
else
return nil
end
end
local function show_headword_line(data)
local namespace = title.nsText
-- Check the namespace against the language type
if namespace == "" then
if data.lang:getType() == "reconstructed" then
error("Entries for this language must be placed in the Reconstruction: namespace.")
elseif data.lang:getType() == "appendix-constructed" then
error("Entries for this language must be placed in the Appendix: namespace.")
end
end
local tracking_categories = {}
if not data.noposcat then
local pos_category = data.lang:getCanonicalName() .. " " .. data.pos_category
if pos_category ~= "Translingual Han characters" then
table.insert(data.categories, 1, pos_category)
end
end
if data.sccat and data.sc then
table.insert(data.categories, data.lang:getCanonicalName() .. " " .. data.pos_category
.. " in " .. data.sc:getDisplayForm())
end
-- Is it a lemma category?
local postype = export.pos_lemma_or_nonlemma(data.pos_category)
if not postype then
-- We don't know what this category is, so tag it with a tracking category.
--[=[
[[Special:WhatLinksHere/Template:tracking/headword/unrecognized pos]]
]=]
table.insert(tracking_categories, "head tracking/unrecognized pos")
require("Module:debug/track"){
"headword/unrecognized pos",
"headword/unrecognized pos/lang/" .. data.lang:getCode(),
"headword/unrecognized pos/pos/" .. data.pos_category
}
elseif not data.noposcat then
table.insert(data.categories, 1, data.lang:getCanonicalName() .. " " .. postype .. "s")
end
-- Preprocess
preprocess(data, postype)
if namespace == "" and data.lang:getType() ~= "reconstructed" then
local m_links = require("Module:links")
for _, head in ipairs(data.heads) do
if title.prefixedText ~= m_links.getLinkPage(m_links.remove_links(head), data.lang) then
--[=[
[[Special:WhatLinksHere/Template:tracking/headword/pagename spelling mismatch]]
]=]
require("Module:debug/track"){
"headword/pagename spelling mismatch",
"headword/pagename spelling mismatch/" .. data.lang:getCode()
}
break
end
end
end
-- Format and return all the gathered information
return
format_headword(data) ..
format_genders(data) ..
format_inflections(data) ..
require("Module:utilities/format_categories")(
tracking_categories, data.lang, data.sort_key, nil,
data.force_cat_output or test_force_categories, data.sc
)
end
function export.full_headword(data)
local tracking_categories = {}
-- Script-tags the topmost header.
local pagename = title.text
local fullPagename = title.fullText
local namespace = title.nsText
if not data.lang or type(data.lang) ~= "table" or not data.lang.getCode then
error("In data, the first argument to full_headword, data.lang should be a language object.")
end
if not data.sc then
data.sc = require("Module:scripts").findBestScript(data.heads and data.heads[1] ~= "" and data.heads[1] or pagename, data.lang)
else
-- Track uses of sc parameter
local best = require("Module:scripts").findBestScript(pagename, data.lang)
require("Module:debug/track")("headword/sc")
if data.sc:getCode() == best:getCode() then
require("Module:debug/track")("headword/sc/redundant")
require("Module:debug/track")("headword/sc/redundant/" .. data.sc:getCode())
else
require("Module:debug/track")("headword/sc/needed")
require("Module:debug/track")("headword/sc/needed/" .. data.sc:getCode())
end
end
local displayTitle
-- Assumes that the scripts in "toBeTagged" will never occur in the Reconstruction namespace.
-- Avoid tagging ASCII as Hani even when it is tagged as Hani in the
-- headword, as in [[check]]. The check for ASCII might need to be expanded
-- to a check for any Latin characters and whitespace or punctuation.
if (namespace == "" and data.sc and toBeTagged[data.sc:getCode()]
and not pagename:find "^[%z\1-\127]+$")
or (data.sc:getCode() == "Jpan" and (test_script(pagename, "Hira") or test_script(pagename, "Kana"))) then
displayTitle = '<span class="' .. data.sc:getCode() .. '">' .. pagename .. '</span>'
elseif namespace == "Reconstruction" then
displayTitle, matched = mw.ustring.gsub(
fullPagename,
"^(Reconstruction:[^/]+/)(.+)$",
function(before, term)
return before ..
require("Module:script utilities").tag_text(
term,
data.lang,
data.sc
)
end
)
if matched == 0 then
displayTitle = nil
end
end
if displayTitle then
local frame = mw.getCurrentFrame()
frame:callParserFunction(
"DISPLAYTITLE",
displayTitle
)
end
if data.force_cat_output then
--[=[
[[Special:WhatLinksHere/Template:tracking/headword/force cat output]]
]=]
require("Module:debug/track")("headword/force cat output")
end
if data.getCanonicalName then
error('The "data" variable supplied to "full_headword" should not be a language object.')
end
-- Were any categories specified?
if data.categories and #data.categories > 0 then
local lang_name = require("Module:string/pattern_escape")(data.lang:getCanonicalName())
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 mw.ustring.find(cat, "^" .. lang_name) then
mw.log(cat, data.lang:getCanonicalName())
table.insert(tracking_categories, "head tracking/no lang category")
--[=[
[[Special:WhatLinksHere/Template:tracking/head tracking/no lang category]]
]=]
require("Module:debug/track"){
"headword/no lang category",
"headword/no lang category/lang/" .. data.lang:getCode()
}
end
end
if not data.pos_category
and mw.ustring.find(data.categories[1], "^" .. data.lang:getCanonicalName())
then
data.pos_category = mw.ustring.gsub(data.categories[1], "^" .. data.lang:getCanonicalName() .. " ", "")
table.remove(data.categories, 1)
end
end
if not data.pos_category then
error(
'No valid part-of-speech categories were found in the list '
.. 'of categories passed to the function "full_headword". '
.. 'The part-of-speech category should consist of a language\'s '
.. 'canonical name plus a part of speech.'
)
end
-- Categorise for unusual characters
local standard = data.lang:getStandardCharacters()
if standard then
if mw.ustring.len(title.subpageText) ~= 1 and not non_categorizable() then
for character in mw.ustring.gmatch(title.subpageText, "([^" .. standard .. "])") do
local upper = mw.ustring.upper(character)
if not mw.ustring.find(upper, "[" .. standard .. "]") then
character = upper
end
table.insert(
data.categories,
data.lang:getCanonicalName() .. " terms spelled with " .. character
)
end
end
end
-- Categorise for palindromes
if title.nsText ~= "Reconstruction" and mw.ustring.len(title.subpageText)>2
and require('Module:palindromes').is_palindrome(
title.subpageText, data.lang, data.sc
) then
table.insert(data.categories, data.lang:getCanonicalName() .. " palindromes")
end
-- This may add more categories (e.g. gender categories), so make sure it gets
-- evaluated first.
local text = show_headword_line(data)
return
text ..
require("Module:utilities/format_categories")(
data.categories, data.lang, data.sort_key, nil,
data.force_cat_output or test_force_categories, data.sc
) ..
require("Module:utilities/format_categories")(
tracking_categories, data.lang, data.sort_key, nil,
data.force_cat_output or test_force_categories, data.sc
)
end
return export