Module:he-utilities
- The following documentation is located at Module:he-utilities/documentation. [edit] Categories were auto-generated by Module:module categorization. [edit]
- Useful links: subpage list • links • transclusions • testcases • sandbox
Some utilities for use in other Hebrew modules.
local export = {}
local m_str_utils = require("Module:string utilities")
local catfix = require("Module:utilities").catfix
local codepoint = m_str_utils.codepoint
local gsub = m_str_utils.gsub
local u = m_str_utils.char
local export = {}
local sc = require("Module:scripts").getByCode("Hebr")
local lang = require("Module:languages").getByCode("he")
local m_utilities = require("Module:utilities")
local m_links = require("Module:links")
local m_headword = require("Module:headword")
local rsplit = mw.text.split
-- A wrapper function allowing the contents of this module to be called from
-- templates. For example, '{{#invoke:he-utilities|main|otSofit|כ}}' produces
-- 'ך', as does '{{#invoke:he-utilities|main|letters|kafSofit}}'.
function export.main(frame)
if type(export[frame.args[1]]) == 'function' then
return export[frame.args[1]](frame.args[2])
else
return export[frame.args[1]][frame.args[2]]
end
end
-- A mapping from strings containing letter-names, e.g. "alef", to strings
-- containing letters, e.g. "\215\144". (The latter is a UTF-8-encoded string
-- containing the single Unicode character U+05D0 HEBREW LETTER ALEF.)
export.letters = {}
for i, name in ipairs({ 'alef', 'bet', 'gimel', 'dalet', 'hei', 'vav', 'zayen',
'khet', 'tet', 'yud', 'kafSofit', 'kaf', 'lamed',
'memSofit', 'mem', 'nunSofit', 'nun', 'samekh', 'ayin',
'peiSofit', 'pei', 'tsadiSofit', 'tsadi', 'kuf', 'resh',
'shin', 'tav' }) do
export.letters[name] = u(0x05D0 + i - 1)
end
export.letters.sin = export.letters.shin
-- Same as previous, but for vowels instead of letters. (It also includes a few
-- marks and diacritics that aren't quite "vowels", but are in the same sequence
-- of Unicode characters.)
export.vowels = {}
for i, name in ipairs({ 'shva', 'khatafSegol', 'khatafPatakh', 'khatafKamats',
'khirik', 'tseirei', 'segol', 'patakh', 'kamats',
'kholam', 'ignoreMe', 'kubuts', 'dagesh', 'meteg',
'makaf', 'rafe', 'pasek', 'shinDot', 'sinDot',
'sofPasuk', 'upperDot' }) do
export.vowels[name] = u(0x05B0 + i - 1)
end
export.vowels.ignoreMe = nil
export.vowels.mapik = export.vowels.dagesh
-- If letter is kaf, mem, nun, pei, or tsadi, returns kaf sofit, mem sofit,
-- etc., respectively; otherwise, just returns letter.
function export.otSofit(letter)
if letter == export.letters.kaf or letter == export.letters.mem
or letter == export.letters.nun or letter == export.letters.pei
or letter == export.letters.tsadi then
return u(codepoint(letter) - 1)
else
return letter
end
end
-- Same as previous, except that if letter is kaf or kaf sofit, also tacks on
-- a sh'va (since kaf sofit is written with a sh'va when it has no other vowel).
function export.otSofitShva(letter)
letter = export.otSofit(letter)
if letter == export.letters.kafSofit then
return letter .. export.vowels.shva
else
return letter
end
end
-- If letter is kaf sofit, mem sofit, etc., returns kaf, mem, etc.; otherwise,
-- just returns letter.
function export.otLoSofit(letter)
if letter == export.letters.kafSofit or letter == export.letters.memSofit
or letter == export.letters.nunSofit or letter == export.letters.peiSofit
or letter == export.letters.tsadiSofit then
return u(codepoint(letter) + 1)
else
return letter
end
end
-- If letter is bet, gimel, dalet, kaf, pei, or tav, returns letter plus a
-- dagesh; otherwise, just returns letter.
function export.dageshKal(letter)
if letter == export.letters.bet or letter == export.letters.gimel
or letter == export.letters.dalet or letter == export.letters.kaf
or letter == export.letters.pei or letter == export.letters.tav then
return letter .. export.vowels.dagesh
else
return letter
end
end
-- If letter is shin plus a shin or sin dot, returns shin (without the dot);
-- otherwise, just returns letter.
function export.dotlessShin(letter)
if letter == export.letters.shin .. export.letters.shinDot
or letter == export.letters.sin .. export.letters.sinDot then
return export.letters.shin
else
return letter
end
end
local letters = "[א-ת]"
local modifiers = "[ּׁׂׄ]?"
local separators = "[-־ %.,!|]?"
local regex = "(" .. letters .. modifiers .. ")" .. separators
local medial_radicals = {
["א"] = true,
["ב"] = true,
["ג"] = true,
["ד"] = true,
["ה"] = true,
["הּ"] = false,
["ו"] = true,
["ז"] = true,
["ח"] = true,
["ט"] = true,
["י"] = true,
["כ"] = true,
["ל"] = true,
["מ"] = true,
["נ"] = true,
["ס"] = true,
["ע"] = true,
["פ"] = true,
["צ"] = true,
["ק"] = true,
["ר"] = true,
["שׁ"] = true,
["שׂ"] = true,
["ת"] = true,
}
local initial_radicals = medial_radicals
local final_radicals = {
["א"] = true,
["ב"] = true,
["ג"] = true,
["ד"] = true,
["ה"] = true,
["הּ"] = true,
["ו"] = false,
["ז"] = true,
["ח"] = true,
["ט"] = true,
["י"] = false,
["ך"] = true,
["ל"] = true,
["ם"] = true,
["ן"] = true,
["ס"] = true,
["ע"] = true,
["ף"] = true,
["ץ"] = true,
["ק"] = true,
["ר"] = true,
["שׁ"] = true,
["שׂ"] = true,
["ת"] = true,
}
local radical_romanizations = {
["א"] = "ʾ",
["ב"] = "b",
["ג"] = "g",
["ד"] = "d",
["ה"] = "h",
["ו"] = "w",
["ז"] = "z",
["ח"] = "kh",
["ט"] = "ṭ",
["י"] = "y",
["[כך]"] = "k",
["ל"] = "l",
["[מם]"] = "m",
["[נן]"] = "n",
["ס"] = "s",
["ע"] = "ʿ",
["[פף]"] = "p",
["[ץצ]"] = "ts",
["ק"] = "q",
["ר"] = "r",
["שׁ"] = "sh",
["שׂ"] = "s",
["ת"] = "t",
}
local function transliterate_root(root_string)
local romanized_root = root_string:gsub("־", "-")
for k, v in pairs(radical_romanizations) do
romanized_root = gsub(romanized_root, k, v)
end
return romanized_root
end
function export.plain_root(frame)
local radicals = {}
local len = 0
local subber = function(radical)
table.insert(radicals, radical)
len = len + 1
return ""
end
local scraps = gsub(frame.args[1], regex, subber)
if scraps ~= "" then
error("Unrecognized characters in root.")
end
if len < 2 then
error("Root must have at least two radicals.")
end
for i, radical in ipairs(radicals) do
if i == 1 then -- initial
if not initial_radicals[radical] then
error("Unrecognized initial radical " .. radical .. ".")
end
elseif i == len then -- final
if not final_radicals[radical] then
error("Unrecognized final radical " .. radical .. ".")
end
else -- medial
if not medial_radicals[radical] then
error("Unrecognized medial radical " .. radical .. ".")
end
end
end
return table.concat(radicals, "־")
end
function export.romanized_root(frame)
local root = export.plain_root(frame)
return transliterate_root(root)
end
function export.catfix()
return catfix(lang, sc)
end
local function link(term, alt, tr, id)
if term == "" or term == "—" then
return term
else
return m_links.full_link({
term = term,
alt = alt,
tr = tr,
lang = lang,
id = id,
})
end
end
local function validateRoot(rootTable, joined_root)
if type(rootTable) ~= "table" then
error("rootTable is not a table", 2)
end
local len = #rootTable
if len < 2 then
error("Root must have at least two radicals.")
end
for i, radical in ipairs(rootTable) do
if i == 1 then -- initial
if not initial_radicals[radical] then
error("Unrecognized initial radical " .. radical .. " in " .. joined_root)
end
elseif i == #rootTable then -- final
if not final_radicals[radical] then
error("Unrecognized final radical " .. radical .. " in " .. joined_root)
end
else -- medial
if not medial_radicals[radical] then
error("Unrecognized medial radical " .. radical .. " in " .. joined_root)
end
end
end
end
function export.root(frame)
local output = {}
local categories = {}
local title = mw.title.getCurrentTitle()
local fulltitle = title.fullText
local namespace = title.nsText
local params = {
[1] = { list = true },
["nocat"] = { type = "boolean" },
["plain"] = { type = "boolean" },
["notext"] = { type = "boolean" },
["sense"] = {}
}
local args = require("Module:parameters").process(frame:getParent().args, params)
local rootLetters = {}
local roots = args[1]
local roots_len = #roots
if #roots == 0 and namespace == "Template" then
table.insert(rootLetters, { "כ", "ת", "ב" })
elseif roots then
for _, root in ipairs(roots) do
table.insert(rootLetters, rsplit(root, "־"))
end
else
table.insert(rootLetters, rsplit(fulltitle, "־"))
end
local joined_roots = {}
for i, rootLetter in ipairs(rootLetters) do
table.insert(joined_roots, table.concat(rootLetter, "־"))
validateRoot(rootLetter, joined_roots[i])
end
local sense = args["sense"]
local sense_formatted = ""
if sense ~= nil then
sense_formatted = " (" .. sense .. ") "
end
if fulltitle == joined_roots[1] then
if roots_len > 1 then
error("There should be only one root.")
end
table.insert(output,
m_headword.full_headword({ lang = lang, pos_category = "roots", categories = {}, heads = { fulltitle }, nomultiwordcat = true }))
if args["nocat"] then
return table.concat(output)
else
return table.concat(output) .. table.concat(categories)
end
else
local link_texts = {}
local term_counts = {}
for i, joined_root in ipairs(joined_roots) do
table.insert(link_texts,
link(joined_root, joined_root .. sense_formatted, transliterate_root(joined_root), sense))
table.insert(
categories,
m_utilities.format_categories(
{ lang:getCanonicalName() .. " terms belonging to the root " .. joined_root .. sense_formatted },
lang)
)
table.insert(term_counts,
mw.site.stats.pagesInCategory(
lang:getCanonicalName() .. " terms belonging to the root " .. joined_root .. sense_formatted, "pages")
)
end
if args["nocat"] or args["plain"] then
return table.concat(link_texts, ", ")
else
local link_text_output = ""
for i, link_text in ipairs(link_texts) do
link_text_output = link_text_output .. '<tr><td>' ..
link_text ..
"</td></tr><tr><td>[[:Category:" ..
lang:getCanonicalName() ..
" terms belonging to the root " ..
joined_roots[i] ..
sense_formatted ..
"|" ..
term_counts[i] ..
" term" .. (term_counts[i] == 1 and "" or "s") .. "]]</td></tr>"
end
return
'<table class="wikitable" style="float: right; clear: right; text-align: center;"><tr><th>[[w:Semitic root|Root' ..
(#term_counts == 1 and "" or "s") .. ']]</th></tr>' .. link_text_output ..
'</table>' .. table.concat(categories)
end
end
end
return export