Module:eu-pron/new
- The following documentation is located at Module:eu-pron/new/documentation. [edit] Categories were auto-generated by Module:module categorization. [edit]
- Useful links: root page • root page’s subpages • links • transclusions • testcases • sandbox
This module is not to be directly used. It is used by Template:eu-pr, see there for usage.
--Based on Module:es-pronunc by Benwing2.
local export = {}
local m_IPA = require("Module:IPA")
local m_table = require("Module:table")
local put_module = "Module:parse utilities"
local force_cat = false -- for testing
local lang = require("Module:languages").getByCode("eu")
local u = mw.ustring.char
local rfind = mw.ustring.find
local rsubn = mw.ustring.gsub
local rmatch = mw.ustring.match
local rsplit = mw.text.split
local ulower = mw.ustring.lower
local uupper = mw.ustring.upper
local usub = mw.ustring.sub
local ulen = mw.ustring.len
local unfd = mw.ustring.toNFD
local unfc = mw.ustring.toNFC
local TILDE = u(0x0303) -- tilde = ̃
local SYLDIV = u(0xFFF0) -- used to represent a user-specific syllable divider (.) so we won't change it
local vowel = "aeiouAEIOU" -- vowel; include y so we get single-word y correct and for syllabifying from spelling
local V = "[" .. vowel .. "]" -- vowel class
local W = "[wʝ]" -- glides, used in a few loanwords
local sylsep = "%-." .. SYLDIV -- hyphen included for syllabifying from spelling
local sylsep_c = "[" .. sylsep .. "]"
local wordsep = "# "
local separator = sylsep .. wordsep
local separator_c = "[" .. separator .. "]"
local C = "[^" .. vowel .. separator .. "]" -- consonant class including h
-- version of rsubn() that discards all but the first return value
local function rsub(term, foo, bar)
local retval = rsubn(term, foo, bar)
return retval
end
-- version of rsubn() that returns a 2nd argument boolean indicating whether
-- a substitution was made.
local function rsubb(term, foo, bar)
local retval, nsubs = rsubn(term, foo, bar)
return retval, nsubs > 0
end
-- apply rsub() repeatedly until no change
local function rsub_repeatedly(term, foo, bar)
while true do
local new_term = rsub(term, foo, bar)
if new_term == term then
return term
end
term = new_term
end
end
local function decompose(text)
-- decompose everything but ñ and ü
text = unfd(text)
text = rsub(text, ".[" .. TILDE .. "]", {
["n" .. TILDE] = "ñ",
["N" .. TILDE] = "Ñ",
})
return text
end
local function split_on_comma(term)
if term:find(",%s") then
return require(put_module).split_on_comma(term)
else
return rsplit(term, ",")
end
end
-- Remove any HTML from the formatted text and resolve links, since the extra characters don't contribute to the
-- displayed length.
local function convert_to_raw_text(text)
text = rsub(text, "<.->", "")
if text:find("%[%[") then
text = require("Module:links").remove_links(text)
end
return text
end
-- Return the approximate displayed length in characters.
local function textual_len(text)
return ulen(convert_to_raw_text(text))
end
local function construct_default_differences(dialect)
if dialect == "gipuzkoan" then
return {
northern_different = false,
j_different = false,
need_bisc = false,
}
end
return nil
end
-- Main syllable-division algorithm
local function syllabify_from_spelling_or_pronun(text)
text = rsub_repeatedly(text, "(" .. V .. ")(" .. C .. W .. "?" .. V .. ")", "%1.%2")
text = rsub_repeatedly(text, "(" .. V .. C .. ")(" .. C .. V .. ")", "%1.%2")
text = rsub_repeatedly(text, "(" .. V .. C .. ")(" .. C .. C .. V .. ")", "%1.%2")
text = rsub_repeatedly(text, "(" .. V .. C .. C .. ")(" .. C .. C .. V .. ")", "%1.%2")
text = rsub(text, "([pfbktdɡg])%.([lrɾ])", ".%1%2") --the first "ɡ" is the IPA one; the second "g" is the regular one
text = rsub_repeatedly(text, "(" .. C .. ")%.s(" .. C .. ")", "%1s.%2")
-- %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
text = rsub_repeatedly(text, "([ae]" .. ")ui", "%1u.i")
text = rsub_repeatedly(text, "([aeiou]" .. ")([aeo])", "%1.%2")
text = rsub_repeatedly(text, "ii", "i.i")
text = rsub_repeatedly(text, "([iou]" .. ")u", "%1.u")
return text
end
local function syllabify_from_spelling(text)
text = decompose(text)
-- start at FFF1 because FFF0 is used for SYLDIV
-- Temporary replacements for characters we want treated as default consonants. The C and related consonant regexes
-- treat all unknown characters as consonants.
local TEMP_tz = u(0xFFF1)
local TEMP_ts = u(0xFFF2)
local TEMP_tx = u(0xFFF3)
local TEMP_tx_CAPS = u(0xFFF4)
local TEMP_ll = u(0xFFF5)
local TEMP_ll_CAPS = u(0xFFF6)
local TEMP_dd = u(0xFFF7)
local TEMP_dd_CAPS = u(0xFFF8)
local TEMP_tt = u(0xFFF9)
local TEMP_tt_CAPS = u(0xFFFA)
local TEMP_rr = u(0xFFB)
-- Change user-specified . into SYLDIV so we don't shuffle it around when dividing into syllables.
text = text:gsub("%.", SYLDIV)
-- handle digraphs
text = rsub(text, "tz", TEMP_tz)
text = rsub(text, "ts", TEMP_ts)
text = rsub(text, "tx", TEMP_tx)
text = rsub(text, "Tx", TEMP_tx_CAPS)
text = rsub(text, "ll", TEMP_ll)
text = rsub(text, "Ll", TEMP_ll_CAPS)
text = rsub(text, "tt", TEMP_tt)
text = rsub(text, "Tt", TEMP_tt_CAPS)
text = rsub(text, "dd", TEMP_dd)
text = rsub(text, "Dd", TEMP_dd_CAPS)
text = rsub(text, "rr", TEMP_rr)
text = syllabify_from_spelling_or_pronun(text)
text = text:gsub(SYLDIV, ".")
text = text:gsub(TEMP_tz, "tz")
text = text:gsub(TEMP_ts, "ts")
text = text:gsub(TEMP_tx, "tx")
text = text:gsub(TEMP_tx_CAPS, "Tx")
text = text:gsub(TEMP_ll, "ll")
text = text:gsub(TEMP_ll_CAPS, "Ll")
text = text:gsub(TEMP_tt, "tt")
text = text:gsub(TEMP_tt_CAPS, "Tt")
text = text:gsub(TEMP_dd, "dd")
text = text:gsub(TEMP_dd_CAPS, "Dd")
text = text:gsub(TEMP_rr, "rr")
text = unfc(text)
return text
end
-- Generate the IPA of a given respelling, where a respelling is the representation of the pronunciation of a given
function export.IPA(text, dialect, phonetic)
local northern = dialect == "northern"
local southern = dialect == "gipuzkoan" or dialect == "navarrese" or dialect == "biscayan"
local nav = dialect == "navarrese"
local bisc = dialect == "biscayan"
local northern_different = false
local j_different = false
local need_bisc = false
local J = ""
local N = ""
-- start at FFF1 because FFF0 is used for SYLDIV
local TEMP_Y = u(0xFFF1)
local TEMP_W = u(0xFFF2)
--function that gets the last two syllables (used for generating the correct rhymes)
local function extract_last_syllables(text)
local words = rsplit(text, " ")
if #words > 1 then --no rhymes are generated when there are multiple words
return ""
end
text = rsub(text, "([aeou])i", "%1")
text = rsub(text, "([ae])u", "%1")
local length = string.len(text)
local rhyme = ""
local count = -1
local syl = 0
while count > -length do
if string.find("aeiou", string.sub(text,count,count)) then
rhyme = string.sub(text,count,-1)
syl = syl + 1
if syl == 2 then
return rhyme
end
end
count = count - 1
end
return rhyme
end
text = ulower(text or mw.title.getCurrentTitle().text)
-- decompose everything but ñ and ü
text = decompose(text)
-- convert commas and en/en dashes to IPA foot boundaries
text = rsub(text, "%s*[,–—]%s*", " | ")
-- question mark or exclamation point in the middle of a sentence -> IPA foot boundary
text = rsub(text, "([^%s])%s*[!?]%s*([^%s])", "%1 | %2")
-- canonicalize multiple spaces and remove leading and trailing spaces
local function canon_spaces(text)
text = rsub(text, "%s+", " ")
text = rsub(text, "^ ", "")
text = rsub(text, " $", "")
return text
end
text = canon_spaces(text)
-- Convert hyphens to spaces, to handle [[Austria-Hungría]], [[franco-italiano]], etc.
text = rsub(text, "%-", " ")
-- canonicalize multiple spaces again, which may have been introduced by hyphens
text = canon_spaces(text)
-- now eliminate punctuation
text = rsub(text, "[!?']", "")
-- put # at word beginning and end and double ## at text/foot boundary beginning/end
text = rsub(text, " | ", "# | #")
text = "##" .. rsub(text, " ", "# #") .. "##"
--determining whether "h" denotes a phoneme, or the lack of palatalization, palatalization when needed
text = rsub(text, "nh", "N")
text = rsub(text, "lh", "L")
text = rsub(text, "([aeo])il([# .h]*[aeiou])", (northern and "%1ił%2" or "%1ĺ%2"))
text = rsub(text, "([aeo])in([# .h]*[aeiou])", (northern and "%1iň%2" or "%1ń%2"))
text = rsub(text, "uin([# .h]*[aeiou])", (northern and "uiň%1" or "uiń%1"))
text = rsub(text, "uil([# .h]*[aeiou])", (northern and "uił%1" or "uiĺ%1"))
text = rsub(text, "il([# .h]*[aeiou])", (northern and "ił%1" or "iĺ%1"))
text = rsub(text, "in([# .h]*[aeiou])", (northern and "iň%1" or "iń%1"))
if text:find("[łňńĺh]") then
northern_different = true
end
if extract_last_syllables(text):find("[łňńĺh]") then
N = "N"
end
text = rsub(text, "ĺ", "ʎ")
text = rsub(text, "ń", "ɲ")
text = rsub(text, "N", "n")
text = rsub(text, "L", "l")
text = rsub(text, "ň", "n")
text = rsub(text, "ł", "l")
--c, g, q
text = rsub(text, "ng([^aeiouüwhlr])", "n%1") -- [[Bangkok]], [[angstrom]], etc.
text = rsub(text, "q", "k") -- [[quark]], [[Qatar]], [[burqa]], [[Iraq]], etc.
text = rsub(text, "c", "k") -- [[campus]], etc.
--alphabet-to-phoneme
text = rsub(text, "aje#", "aʒe#") -- final -aje is pronounced /aʒe/ in the North and /axe/ in the South, regardless of how native j is pronounced
text = rsub(text, "ihoa", "iχoa") -- the <h> in conjugated forms of joan is pronounced in the South
text = rsub(text, "zh", "ź")
text = rsub(text, "tx", "C") --not the real sound
text = rsub(text, "tz", "Ś") --not the real sound
text = rsub(text, "ts", "S") --not the real sound
text = rsubb(text, "ll", "ʎ")
text = rsubb(text, "dd", "ɟ")
text = rsubb(text, "tt", "c")
text = rsub(text, "x", "ʃ")
text = rsub(text, "#p([st])", "#%1") -- [[psicologia]], [[pterodaktilo]]
text = rsub(text, "[gñrvz]",
{ ["g"] = "ɡ", ["ñ"] = "ɲ", ["v"] = "b", ["z"] = "ś" })
if text:find("ś") or text:find("S") then
need_bisc = true
end
--/x/~/j/~/ʒ/ sounds
if text:find("[yj]") then
northern_different = true
j_different = true
end
if extract_last_syllables(text):find("[yj]") then
J = "J"
end
if text:find("ʒ") or text:find("χ") then
northern_different = true
end
if extract_last_syllables(text):find("ʒ") then
N = "N"
end
if text:find("kh") then
northern_different = true
end
if extract_last_syllables(text):find("kh") then
N = "N"
end
if text:find("ź") then
northern_different = true
end
if extract_last_syllables(text):find("ź") then
N = "N"
end
text = rsubb(text, "j", (northern and "ɟ" or "x"))
text = rsubb(text, "y", (northern and "ɟ" or "j")) -- <y> is used for words which always have a palatal
text = rsubb(text, "kh", (northern and "k" or "χ"))
text = rsubb(text, "ź", (northern and "ʒ" or "ʃ"))
-- trilled r (in all cases except between vowels)
text = rsub(text, "([aeiou])r([aeiou])", "%1ɾ%2")
text = rsub(text, "([aeiou])r([aeiou])", "%1ɾ%2") -- it has to be applied twice in order to handle VrVrV sequences
text = rsub(text, "rr", "r")
text = rsub(text, "n([# .]*[bpm])", "m%1")
-- lack of /h/ in Southern dialects
text = rsub(text, "aha", (northern and "aha" or "a"))
text = rsub(text, "ehe", (northern and "ehe" or "e"))
text = rsub(text, "ihi", (northern and "ihi" or "i"))
text = rsub(text, "oho", (northern and "oho" or "o"))
text = rsub(text, "uhu", (northern and "uhu" or "u"))
text = rsub(text, "h", (northern and "h" or ""))
text = rsub(text, "n([# .]*[bpm])", "m%1")
-- handle i/u between vowels
text = rsub_repeatedly(text, "ui", "U") --this dipthong requires special treatment
local vowel_to_glide = { ["i"] = "i.", ["u"] = "u." }
text = rsub_repeatedly(text, "(" .. V .. "*)([iu])(" .. V .. ")",
function(v1, iu, v2)
return v1 .. vowel_to_glide[iu] .. v2
end
)
text = rsub_repeatedly(text, "U", "ui")
--syllable division
text = syllabify_from_spelling_or_pronun(text)
--dialectal differences
if nav then
text = rsub(text, "x", "j")
elseif bisc then --fake symbols, to be replaced later
text = rsub(text, "x", "đ")
text = rsub(text, "j", "đ")
text = rsub(text, "ś", "s")
text = rsub(text, "S", "Ś")
end
text = rsubb(text, "ʒ", (southern and "x" or "ʒ"))
text = rsubb(text, "χ", (southern and "x" or "h"))
--phonetic transcription
if phonetic then
-- θ, s, f before voiced consonants
local voiced = "mnɲbdɟɡʎljđ"
local r = "ɾr"
local tovoiced = {
["s"] = "z̺",
["ś"] = "z̻",
}
local function voice(sound, following)
return tovoiced[sound] .. following
end
text = rsub(text, "([sś])(" .. separator_c .. "*[" .. voiced .. r .. "])", voice)
-- fricative vs. stop allophones; first convert stops to fricatives, then back to stops
-- after nasals and sometimes after l
local stop_to_fricative = {["b"] = "β", ["d"] = "ð", ["ɡ"] = "ɣ"}
local fricative_to_stop = {["β"] = "b", ["ð"] = "d", ["ɣ"] = "ɡ"}
text = rsub(text, "[bdɡ]", stop_to_fricative)
text = rsub(text, "([mnɲ]" .. separator_c .. "*)([βɣ])",
function(nasal, fricative) return nasal .. fricative_to_stop[fricative] end
)
text = rsub(text, "([lʎmnɲ]" .. separator_c .. "*)([ð])",
function(nasal_l, fricative) return nasal_l .. fricative_to_stop[fricative] end
)
text = rsub(text, "##β", "##b")
text = rsub(text, "##ð", "##d")
text = rsub(text, "##ɣ", "##ɡ")
text = rsub(text, "[td]", {["t"] = "t̪", ["d"] = "d̪"})
-- nasal assimilation before consonants
local labiodental, dentialveolar, alveolopalatal, palatal, velar = "ɱ", "n̪", "nʲ", "ɲ", "ŋ"
local nasal_assimilation = {
["f"] = labiodental,
["t"] = dentialveolar, ["d"] = dentialveolar,
["C"] = alveolopalatal,
["ʃ"] = alveolopalatal,
["đ"] = alveolopalatal,
["ɟ"] = palatal, ["c"] = palatal, ["ʎ"] = palatal, ["j"] = palatal,
["k"] = velar, ["x"] = velar, ["ɡ"] = velar,
}
text = rsub(text, "n(" .. separator_c .. "*)(.)",
function(stress, following)
return (nasal_assimilation[following] or "n") .. stress .. following
end
)
-- lateral assimilation before consonants
text = rsub(text, "l(" .. separator_c .. "*)(.)",
function(stress, following)
local l = "l"
if following == "t" or following == "d" then
-- dentialveolar
l = "l̪"
elseif following == "C" or following == "ʃ" or following == "đ" then
-- alveolopalatal
l = "lʲ"
elseif following == "ɟ" or following == "c" or following == "j" then
-- alveolopalatal
l = "ʎ"
end
return l .. stress .. following
end)
-- voiced fricatives are actually approximants
text = rsub(text, "([βðɣ])", "%1̞")
--nasalization of vowels
text = rsub(text, "([aeou])i([mnɲ])", "%1" .. TILDE .. "i" .. TILDE .. "%2")
text = rsub(text, "([ae])u([mnɲ])", "%1" .. TILDE .. "u" .. TILDE .. "%2")
text = rsub(text, "([aeiou])([mnɲ])", "%1" .. TILDE .. "%2")
end
--semivowels
text = rsub(text, "([aeou])" .. TILDE .. "([i])", "%1" .. TILDE .. "%2̯")
text = rsub(text, "([ae])" .. TILDE .. "([u])", "%1" .. TILDE .. "%2̯")
text = rsub(text, "([aeou][i])", "%1̯")
text = rsub(text, "([ae][u])", "%1̯")
text = rsub(text, "u̯i̯", "u̯i") --correct the mistake appeareing in words with aui, eui
-- convert fake symbols to real ones
local final_conversions = {
["S"] = "t͡s̺",
["Ś"] = "t͡s̻",
["s"] = "s̺",
["ś"] = "s̻",
["C"] = "t͡ʃ",
["X"] = "x",
["đ"] = "d͡ʒ",
["ʝ"] = "j"
}
text = rsub(text, "[SŚsśCXđʝ]", final_conversions)
-- remove # symbols at word and text boundaries
text = rsub(text, "#", "")
text = mw.ustring.toNFC(text)
--add technical characters to the end of the rhyme in order to parse the rhymes correctly
text = text .. J .. N
local differences = nil
if dialect == "gipuzkoan" then
differences = {
northern_different = northern_different,
need_bisc = need_bisc,
j_different = j_different,
}
end
local ret = {
text = text,
differences = differences,
}
return ret
end
function export.IPA_string(frame)
local iparams = {
[1] = {},
["style"] = {required = true},
["phonetic"] = {type = "boolean"},
}
local iargs = require("Module:parameters").process(frame.args, iparams)
local retval = export.IPA(iargs[1], iargs.style, iargs.phonetic)
return retval.text
end
-- Generate all relevant dialect pronunciations and group into styles.
local function express_all_styles(style_spec, dodialect)
local ret = {
pronun = {},
expressed_styles = {},
}
local need_bisc
local function express_style(hidden_tag, tag, representative_dialect, matching_styles)
matching_styles = matching_styles or representative_dialect
-- If style specified, make sure it matches the requested style.
local style_matches
if not style_spec then
style_matches = true
else
local style_parts = rsplit(matching_styles, "%-")
local or_styles = rsplit(style_spec, "%s*,%s*")
for _, or_style in ipairs(or_styles) do
local and_styles = rsplit(or_style, "%s*%+%s*")
local and_matches = true
for _, and_style in ipairs(and_styles) do
local negate
if and_style:find("^%-") then
and_style = and_style:gsub("^%-", "")
negate = true
end
local this_style_matches = false
for _, part in ipairs(style_parts) do
if part == and_style then
this_style_matches = true
break
end
end
if negate then
this_style_matches = not this_style_matches
end
if not this_style_matches then
and_matches = false
end
end
if and_matches then
style_matches = true
break
end
end
end
if not style_matches then
return
end
-- Fetch the representative dialect's pronunciation if not already present.
if not ret.pronun[representative_dialect] then
dodialect(ret, representative_dialect)
end
-- Insert the new style into the style group, creating the group if necessary.
local new_style = {
tag = tag,
pronun = ret.pronun[representative_dialect],
}
for _, hidden_tag_style in ipairs(ret.expressed_styles) do
if hidden_tag_style.tag == hidden_tag then
table.insert(hidden_tag_style.styles, new_style)
return
end
end
table.insert(ret.expressed_styles, {
tag = hidden_tag,
styles = {new_style},
})
end
-- For each type of difference, figure out if the difference exists in any of the given respellings. We do this by
-- generating the pronunciation for the dialect "gipuzkoan", for each respelling. In the process of
-- generating the pronunciation for a given respelling, it computes how the other dialects for that respelling
-- differ. Then we take the union of these differences across the respellings.
dodialect(ret, "gipuzkoan")
local differences = {}
for _, difftype in ipairs { "northern_different", "j_different", "need_bisc"} do
for _, pronun in ipairs(ret.pronun["gipuzkoan"]) do
if pronun.differences[difftype] then
differences[difftype] = true
end
end
end
local northern_different = differences.northern_different
local j_different = differences.j_different
need_bisc = differences.need_bisc
-- Now, based on the observed differences, figure out how to combine the individual dialects into styles and style groups.
if northern_different then
express_style("Navarro-Lapurdian","Navarro-Lapurdian","northern")
if j_different then
express_style("Southern","Gipuzkoan","gipuzkoan")
express_style("Southern","Biscayan","biscayan")
express_style("Southern","Navarrese","navarrese")
else
if need_bisc then
express_style("Southern","Gipuzkoan, Navarrese","gipuzkoan")
express_style("Southern","Biscayan","biscayan")
else
express_style("Southern","Southern","gipuzkoan")
end
end
else
if j_different then
express_style("Navarro-Lapurdian","Navarro-Lapurdian","northern")
express_style("Southern","Gipuzkoan","gipuzkoan")
express_style("Southern","Biscayan","biscayan")
express_style("Southern","Navarrese","navarrese")
elseif need_bisc then
express_style(false,"most dialects","gipuzkoan")
express_style(false,"Biscayan","biscayan")
else
express_style(false,false,"gipuzkoan")
end
end
return ret
end
local function format_all_styles(expressed_styles, format_style)
for i, style_group in ipairs(expressed_styles) do
if #style_group.styles == 1 then
style_group.formatted, style_group.formatted_len =
format_style(style_group.styles[1].tag, style_group.styles[1], i == 1)
else
style_group.formatted, style_group.formatted_len =
format_style(style_group.tag, style_group.styles[1], i == 1)
for j, style in ipairs(style_group.styles) do
style.formatted, style.formatted_len =
format_style(style.tag, style, i == 1 and j == 1)
end
end
end
local maxlen = 0
for i, style_group in ipairs(expressed_styles) do
local this_len = style_group.formatted_len
if #style_group.styles > 1 then
for _, style in ipairs(style_group.styles) do
this_len = math.max(this_len, style.formatted_len)
end
end
maxlen = math.max(maxlen, this_len)
end
local lines = {}
local need_major_hack = false
for i, style_group in ipairs(expressed_styles) do
if #style_group.styles == 1 then
table.insert(lines, style_group.formatted)
need_major_hack = false
else
local inline = '\n<div class="vsShow" style="display:none">\n' .. style_group.formatted .. "</div>"
local full_prons = {}
for _, style in ipairs(style_group.styles) do
table.insert(full_prons, style.formatted)
end
local full = '\n<div class="vsHide">\n' .. table.concat(full_prons, "\n") .. "</div>"
local em_length = math.floor(maxlen * 0.68) -- from [[Module:grc-pronunciation]]
table.insert(lines, '<div class="vsSwitcher" data-toggle-category="pronunciations" style="width: ' .. em_length .. 'em; max-width:100%;"><span class="vsToggleElement" style="float: right;"> </span>' .. inline .. full .. "</div>")
need_major_hack = true
end
end
-- major hack to get bullets working on the next line after a div box
return table.concat(lines, "\n") .. (need_major_hack and "\n<span></span>" or "")
end
local function dodialect_pronun(args, ret, dialect)
ret.pronun[dialect] = {}
for i, term in ipairs(args.terms) do
local phonemic, phonetic, differences
if term.raw then
phonemic = term.raw_phonemic
phonetic = term.raw_phonetic
differences = construct_default_differences(dialect)
else
phonemic = export.IPA(term.term, dialect, false)
phonetic = export.IPA(term.term, dialect, true)
differences = phonemic.differences
phonemic = phonemic.text
phonetic = phonetic.text
end
local refs
if not term.ref then
refs = nil
else
refs = {}
for _, refspec in ipairs(term.ref) do
local this_refs = require("Module:references").parse_references(refspec)
for _, this_ref in ipairs(this_refs) do
table.insert(refs, this_ref)
end
end
end
ret.pronun[dialect][i] = {
raw = term.raw,
phonemic = phonemic,
phonetic = phonetic,
refs = refs,
q = term.q,
qq = term.qq,
a = term.a,
aa = term.aa,
differences = differences,
}
end
end
local function generate_pronun(args)
local function remove_technical_chars(text)
return rsub(text, "([JN])", "")
end
local function this_dodialect_pronun(ret, dialect)
dodialect_pronun(args, ret, dialect)
end
local ret = express_all_styles(args.style, this_dodialect_pronun)
local function format_style(tag, expressed_style, is_first)
local pronunciations = {}
local formatted_pronuns = {}
local function ins(formatted_part)
table.insert(formatted_pronuns, formatted_part)
end
-- Loop through each pronunciation. For each one, add the phonemic and phonetic versions to `pronunciations`,
-- for formatting by [[Module:IPA]], and also create an approximation of the formatted version so that we can
-- compute the appropriate width of the HTML switcher div box that holds the different per-dialect variants.
-- NOTE: The code below constructs the formatted approximation out-of-order in some cases but that doesn't
-- currently matter because we assume all characters have the same width. If we change the width computation
-- in a way that requires the correct order, we need changes to the code below.
for j, pronun in ipairs(expressed_style.pronun) do
-- Add tag to left qualifiers if first one
-- FIXME: Consider using accent qualifier for the tag instead.
local qs = pronun.q
if j == 1 and tag then
if qs then
qs = m_table.deepcopy(qs)
table.insert(qs, tag)
else
qs = {tag}
end
end
local first_pronun = #pronunciations + 1
if not pronun.phonemic and not pronun.phonetic then
error("Internal error: Saw neither phonemic nor phonetic pronunciation")
end
if pronun.phonemic then -- missing if 'raw:[...]' given
-- don't display syllable division markers in phonemic
local slash_pron = "/" .. remove_technical_chars(pronun.phonemic:gsub("%.", "")) .. "/"
table.insert(pronunciations, {
pron = slash_pron,
})
ins(slash_pron)
end
if pronun.phonetic then -- missing if 'raw:/.../' given
local bracket_pron = "[" .. remove_technical_chars(pronun.phonetic) .. "]"
table.insert(pronunciations, {
pron = bracket_pron,
})
ins(bracket_pron)
end
local last_pronun = #pronunciations
if qs then
pronunciations[first_pronun].q = qs
end
if pronun.a then
pronunciations[first_pronun].a = pronun.a
end
if j > 1 then
pronunciations[first_pronun].separator = ", "
ins(", ")
end
if pronun.qq then
pronunciations[last_pronun].qq = pronun.qq
end
if pronun.aa then
pronunciations[last_pronun].aa = pronun.aa
end
if qs or pronun.qq or pronun.a or pronun.aa then
-- Note: This inserts the actual formatted qualifier text, including HTML and such, but the later call
-- to textual_len() removes all HTML and reduces links.
ins(require("Module:pron qualifier").format_qualifiers {
lang = lang,
text = "",
q = qs,
qq = pronun.qq,
a = pronun.a,
aa = pronun.aa,
})
end
if pronun.refs then
pronunciations[last_pronun].refs = pronun.refs
-- Approximate the reference using a footnote notation. This will be slightly inaccurate if there are
-- more than nine references but that is rare.
ins(string.rep("[1]", #pronun.refs))
end
if first_pronun ~= last_pronun then
pronunciations[last_pronun].separator = " "
ins(" ")
end
end
local bullet = string.rep("*", args.bullets) .. " "
-- Here we construct the formatted line in `formatted`, and also try to construct the equivalent without HTML
-- and wiki markup in `formatted_for_len`, so we can compute the approximate textual length for use in sizing
-- the toggle box with the "more" button on the right.
local pre = is_first and args.pre and args.pre .. " " or ""
local post = is_first and args.post and " " .. args.post or ""
local formatted = bullet .. pre .. m_IPA.format_IPA_full { lang = lang, items = pronunciations, separator = "" } .. post
local formatted_for_len = bullet .. pre .. "IPA(key): " .. table.concat(formatted_pronuns) .. post
return formatted, textual_len(formatted_for_len)
end
ret.text = format_all_styles(ret.expressed_styles, format_style)
return ret
end
local function parse_respelling(respelling, pagename, parse_err)
local raw_respelling = respelling:match("^raw:(.*)$")
if raw_respelling then
local raw_phonemic, raw_phonetic = raw_respelling:match("^/(.*)/ %[(.*)%]$")
if not raw_phonemic then
raw_phonemic = raw_respelling:match("^/(.*)/$")
end
if not raw_phonemic then
raw_phonetic = raw_respelling:match("^%[(.*)%]$")
end
if not raw_phonemic and not raw_phonetic then
parse_err(("Unable to parse raw respelling '%s', should be one of /.../, [...] or /.../ [...]")
:format(raw_respelling))
end
return {
raw = true,
raw_phonemic = raw_phonemic,
raw_phonetic = raw_phonetic,
}
end
if respelling == "+" then
respelling = pagename
end
return {term = respelling}
end
-- Return the number of syllables of a phonemic representation, which should have syllable dividers in it but no
-- hyphens.
local function get_num_syl_from_phonemic(phonemic)
-- Maybe we should just count vowels instead of the below code.
phonemic = rsub(phonemic, "|", " ") -- remove IPA foot boundaries
local words = rsplit(phonemic, " +")
for i, word in ipairs(words) do
-- IPA stress marks are syllable divisions if between characters; otherwise just remove.
word = rsub(word, "(.)[ˌˈ](.)", "%1.%2")
word = rsub(word, "[ˌˈ]", "")
words[i] = word
end
-- There should be a syllable boundary between words.
phonemic = table.concat(words, ".")
return ulen(rsub(phonemic, "[^.]", "")) + 1
end
-- Take the last two syllables for the ryhme, unless the word has a single syllable
local function convert_phonemic_to_rhyme(phonemic)
local syllables = rsplit(phonemic, "%.")
local rh = ""
if #syllables > 1 then
rh = table.concat(syllables, ".", #syllables - 1, #syllables)
else
rh = phonemic
end
return rsub(rh, "^[^" .. vowel .. "]*", ""):gsub("%.", ""):gsub("͡", "")
end
local function split_syllabified_spelling(spelling)
return rsplit(spelling, "%.")
end
-- "Align" syllabification to original spelling by matching character-by-character, allowing for extra syllable and
-- accent markers in the syllabification. If we encounter an extra syllable marker (.), we allow and keep it. If we
-- encounter an extra accent marker in the syllabification, we drop it. In any other case, we return nil indicating
-- the alignment failed.
local function align_syllabification_to_spelling(syllab, spelling)
local result = {}
local syll_chars = rsplit(decompose(syllab), "")
local spelling_chars = rsplit(decompose(spelling), "")
local i = 1
local j = 1
while i <= #syll_chars or j <= #spelling_chars do
local ci = syll_chars[i]
local cj = spelling_chars[j]
if ci == cj then
table.insert(result, ci)
i = i + 1
j = j + 1
elseif ci == "." then
table.insert(result, ci)
i = i + 1
elseif ci == AC or ci == GR or ci == CFLEX then
-- skip character
i = i + 1
else
-- non-matching character
return nil
end
end
if i <= #syll_chars or j <= #spelling_chars then
-- left-over characters on one side or the other
return nil
end
return unfc(table.concat(result))
end
local function generate_hyph_obj(term)
return {syllabification = term, hyph = split_syllabified_spelling(term)}
end
-- Word should already be decomposed.
local function word_has_vowels(word)
return rfind(word, V)
end
local function all_words_have_vowels(term)
local words = rsplit(decompose(term), "[ %-]")
for i, word in ipairs(words) do
-- Allow empty word; this occurs with prefixes and suffixes.
if word ~= "" and not word_has_vowels(word) then
return false
end
end
return true
end
local function should_generate_rhyme_from_respelling(term)
local words = rsplit(decompose(term), " +")
return #words == 1 and -- no if multiple words
not words[1]:find(".%-.") and -- no if word is composed of hyphenated parts (e.g. [[Austria-Hungría]])
not words[1]:find("%-$") and -- no if word is a prefix
not (words[1]:find("^%-") and words[1]:find(CFLEX)) and -- no if word is an unstressed suffix
word_has_vowels(words[1]) -- no if word has no vowels (e.g. a single letter)
end
local function should_generate_rhyme_from_ipa(ipa)
return not ipa:find("%s") and word_has_vowels(decompose(ipa))
end
local function dodialect_specified_rhymes(rhymes, hyphs, parsed_respellings, rhyme_ret, dialect)
rhyme_ret.pronun[dialect] = {}
for _, rhyme in ipairs(rhymes) do
local num_syl = rhyme.num_syl
local no_num_syl = false
-- If user explicitly gave the rhyme but didn't explicitly specify the number of syllables, try to take it from
-- the hyphenation.
if not num_syl then
num_syl = {}
for _, hyph in ipairs(hyphs) do
if should_generate_rhyme_from_respelling(hyph.syllabification) then
local this_num_syl = 1 + ulen(rsub(hyph.syllabification, "[^.]", ""))
m_table.insertIfNot(num_syl, this_num_syl)
else
no_num_syl = true
break
end
end
if no_num_syl or #num_syl == 0 then
num_syl = nil
end
end
-- If that fails and term is single-word, try to take it from the phonemic.
if not no_num_syl and not num_syl then
for _, parsed in ipairs(parsed_respellings) do
for dialect, pronun in pairs(parsed.pronun.pronun[dialect]) do
-- Check that pronun.phonemic exists (it may not if raw phonetic-only pronun is given).
if pronun.phonemic then
if not should_generate_rhyme_from_ipa(pronun.phonemic) then
no_num_syl = true
break
end
-- Count number of syllables by looking at syllable boundaries (including stress marks).
local this_num_syl = get_num_syl_from_phonemic(pronun.phonemic)
m_table.insertIfNot(num_syl, this_num_syl)
end
end
if no_num_syl then
break
end
end
if no_num_syl or #num_syl == 0 then
num_syl = nil
end
end
table.insert(rhyme_ret.pronun[dialect], {
rhyme = rhyme.rhyme,
num_syl = num_syl,
qualifiers = rhyme.qualifiers,
differences = construct_default_differences(dialect),
})
end
end
local function parse_pron_modifier(arg, put, parse_err, generate_obj, param_mods, no_split_on_comma)
local retval = {}
if arg:find("<") then
if not put then
put = require(put_module)
end
local function get_valid_prefixes()
local valid_prefixes = {}
for param_mod, _ in pairs(param_mods) do
table.insert(valid_prefixes, param_mod)
end
table.insert(valid_prefixes, "q")
table.insert(valid_prefixes, "qq")
table.insert(valid_prefixes, "a")
table.insert(valid_prefixes, "aa")
table.sort(valid_prefixes)
return valid_prefixes
end
local segments = put.parse_balanced_segment_run(arg, "<", ">")
local comma_separated_groups =
no_split_on_comma and {segments} or put.split_alternating_runs_on_comma(segments)
for _, group in ipairs(comma_separated_groups) do
local obj = generate_obj(group[1])
for j = 2, #group - 1, 2 do
if group[j + 1] ~= "" then
parse_err("Extraneous text '" .. group[j + 1] .. "' after modifier")
end
local modtext = group[j]:match("^<(.*)>$")
if not modtext then
parse_err("Internal error: Modifier '" .. group[j] .. "' isn't surrounded by angle brackets")
end
local prefix, val = modtext:match("^([a-z]+):(.*)$")
if not prefix then
local valid_prefixes = get_valid_prefixes()
for i, valid_prefix in ipairs(valid_prefixes) do
valid_prefixes[i] = "'" .. valid_prefix .. ":'"
end
parse_err("Modifier " .. group[j] .. " lacks a prefix, should begin with one of " ..
m_table.serialCommaJoin(valid_prefixes))
end
if prefix == "q" or prefix == "qq" or prefix == "a" or prefix == "aa" then
if not obj[prefix] then
obj[prefix] = {}
end
table.insert(obj[prefix], val)
elseif param_mods[prefix] then
local key = param_mods[prefix].item_dest or prefix
if obj[key] then
parse_err("Modifier '" .. prefix .. "' specified more than once")
end
local convert = param_mods[prefix].convert
if convert then
obj[key] = convert(val)
else
obj[key] = val
end
else
local valid_prefixes = get_valid_prefixes()
for i, valid_prefix in ipairs(valid_prefixes) do
valid_prefixes[i] = "'" .. valid_prefix .. "'"
end
parse_err("Unrecognized prefix '" .. prefix .. "' in modifier " .. group[j]
.. ", should be " .. m_table.serialCommaJoin(valid_prefixes))
end
end
table.insert(retval, obj)
end
elseif no_split_on_comma then
table.insert(retval, generate_obj(arg))
else
for _, term in ipairs(split_on_comma(arg)) do
table.insert(retval, generate_obj(term))
end
end
return retval
end
local function parse_rhyme(arg, put, parse_err)
local function generate_obj(term)
return {rhyme = term}
end
local param_mods = {
s = {
item_dest = "num_syl",
convert = function(arg)
local nsyls = rsplit(arg, ",")
for i, nsyl in ipairs(nsyls) do
if not nsyl:find("^[0-9]+$") then
parse_err("Number of syllables '" .. nsyl .. "' should be numeric")
end
nsyls[i] = tonumber(nsyl)
end
return nsyls
end,
},
}
return parse_pron_modifier(arg, put, parse_err, generate_obj, param_mods)
end
local function parse_hyph(arg, put, parse_err)
-- None other than qualifiers
local param_mods = {}
return parse_pron_modifier(arg, put, parse_err, generate_hyph_obj, param_mods)
end
local function parse_homophone(arg, put, parse_err)
local function generate_obj(term)
return {term = term}
end
local param_mods = {
t = {
-- We need to store the <t:...> inline modifier into the "gloss" key of the parsed term,
-- because that is what [[Module:links]] (called from [[Module:homophones]]) expects.
item_dest = "gloss",
},
gloss = {},
pos = {},
alt = {},
lit = {},
id = {},
g = {
-- We need to store the <g:...> inline modifier into the "genders" key of the parsed term,
-- because that is what [[Module:links]] (called from [[Module:homophones]]) expects.
item_dest = "genders",
convert = function(arg)
return rsplit(arg, ",")
end,
},
}
return parse_pron_modifier(arg, put, parse_err, generate_obj, param_mods)
end
local function generate_audio_obj(arg)
local file, gloss
if arg:find("#") then
file, gloss = arg:match("^(.-)%s*#%s*(.*)$")
else
file, gloss = arg:match("^(.-)%s*;%s*(.*)$")
end
file = file or arg
return {file = file, gloss = gloss}
end
local function parse_audio(arg, put, parse_err)
-- None other than qualifiers
local param_mods = {}
-- Don't split on comma because some filenames have embedded commas not followed by a space
-- (typically followed by an underscore).
return parse_pron_modifier(arg, put, parse_err, generate_audio_obj, param_mods, "no split on comma")
end
-- External entry point for {{es-pr}}.
function export.show_pr(frame)
local params = {
[1] = {list = true},
["rhyme"] = {},
["hyph"] = {},
["hmp"] = {},
["audio"] = {list = true},
["pagename"] = {},
}
local parargs = frame:getParent().args
local args = require("Module:parameters").process(parargs, params)
local pagename = args.pagename or mw.title.getCurrentTitle().subpageText
-- Parse the arguments.
local function remove_technical_chars(text)
return rsub(text, "([JN])", "")
end
local respellings = #args[1] > 0 and args[1] or {"+"}
local parsed_respellings = {}
local function overall_parse_err(msg, arg, val)
error(msg .. ": " .. arg .. "= " .. val)
end
local overall_rhyme = args.rhyme and
parse_rhyme(args.rhyme, nil, function(msg) overall_parse_err(msg, "rhyme", args.rhyme) end) or nil
local overall_hyph = args.hyph and
parse_hyph(args.hyph, nil, function(msg) overall_parse_err(msg, "hyph", args.hyph) end) or nil
local overall_hmp = args.hmp and
parse_homophone(args.hmp, nil, function(msg) overall_parse_err(msg, "hmp", args.hmp) end) or nil
local overall_audio
if args.audio then
overall_audio = {}
for _, audio in ipairs(args.audio) do
local parsed_audio = parse_audio(audio, nil, function(msg) overall_parse_err(msg, "audio", audio) end)
if #parsed_audio > 1 then
error("Internal error: Saw more than one object returned from parse_audio")
end
table.insert(overall_audio, parsed_audio[1])
end
end
local put
for i, respelling in ipairs(respellings) do
local function parse_err(msg)
error(msg .. ": " .. i .. "= " .. respelling)
end
if respelling:find("<") then
if not put then
put = require(put_module)
end
local param_mods = {
pre = {},
post = {},
style = {},
bullets = {
convert = function(arg)
if not arg:find("^[0-9]+$") then
parse_err("Modifier 'bullets' should have a number as argument, but saw '" .. arg .. "'")
end
return tonumber(arg)
end,
},
rhyme = {
insert = true,
flatten = true,
convert = function(arg) return parse_rhyme(arg, put, parse_err) end,
},
hyph = {
insert = true,
flatten = true,
convert = function(arg) return parse_hyph(arg, put, parse_err) end,
},
hmp = {
insert = true,
flatten = true,
convert = function(arg) return parse_homophone(arg, put, parse_err) end,
},
audio = {
insert = true,
flatten = true,
convert = function(arg) return parse_audio(arg, put, parse_err) end,
},
}
local function get_valid_prefixes()
local valid_prefixes = {}
for param_mod, _ in pairs(param_mods) do
table.insert(valid_prefixes, param_mod)
end
table.insert(valid_prefixes, "ref")
table.insert(valid_prefixes, "q")
table.insert(valid_prefixes, "qq")
table.insert(valid_prefixes, "a")
table.insert(valid_prefixes, "aa")
table.sort(valid_prefixes)
return valid_prefixes
end
local segments = put.parse_balanced_segment_run(respelling, "<", ">")
local comma_separated_groups = put.split_alternating_runs_on_comma(segments, ",")
local parsed = {terms = {}, audio = {}, rhyme = {}, hyph = {}, hmp = {}}
for j, group in ipairs(comma_separated_groups) do
local termobj = parse_respelling(group[1], pagename, parse_err)
for k = 2, #group - 1, 2 do
if group[k + 1] ~= "" then
parse_err("Extraneous text '" .. group[k + 1] .. "' after modifier")
end
local modtext = group[k]:match("^<(.*)>$")
if not modtext then
parse_err("Internal error: Modifier '" .. group[k] .. "' isn't surrounded by angle brackets")
end
local prefix, arg = modtext:match("^([a-z]+):(.*)$")
if not prefix then
local valid_prefixes = get_valid_prefixes()
for i, valid_prefix in ipairs(valid_prefixes) do
valid_prefixes[i] = "'" .. valid_prefix .. ":'"
end
parse_err("Modifier " .. group[k] .. " lacks a prefix, should begin with one of " ..
m_table.serialCommaJoin(valid_prefixes))
end
if prefix == "ref" or prefix == "q" or prefix == "qq" or prefix == "a" or prefix == "aa" then
if not termobj[prefix] then
termobj[prefix] = {}
end
table.insert(termobj[prefix], arg)
elseif param_mods[prefix] then
if j < #comma_separated_groups then
parse_err("Modifier '" .. prefix .. "' should occur after the last comma-separated term")
end
if not param_mods[prefix].insert and parsed[prefix] then
parse_err("Modifier '" .. prefix .. "' occurs twice, second occurrence " .. group[k])
end
local converted
if param_mods[prefix].convert then
converted = param_mods[prefix].convert(arg)
else
converted = arg
end
if param_mods[prefix].insert then
if param_mods[prefix].flatten then
for _, obj in ipairs(converted) do
table.insert(parsed[prefix], obj)
end
else
table.insert(parsed[prefix], converted)
end
else
parsed[prefix] = converted
end
else
local valid_prefixes = get_valid_prefixes()
for i, valid_prefix in ipairs(valid_prefixes) do
valid_prefixes[i] = "'" .. valid_prefix .. "'"
end
parse_err("Unrecognized prefix '" .. prefix .. "' in modifier " .. group[k]
.. ", should be " .. m_table.serialCommaJoin(valid_prefixes))
end
end
table.insert(parsed.terms, termobj)
end
if not parsed.bullets then
parsed.bullets = 1
end
table.insert(parsed_respellings, parsed)
else
local termobjs = {}
for _, term in ipairs(split_on_comma(respelling)) do
table.insert(termobjs, parse_respelling(term, pagename, parse_err))
end
table.insert(parsed_respellings, {
terms = termobjs,
audio = {},
rhyme = {},
hyph = {},
hmp = {},
bullets = 1,
})
end
end
if overall_hyph then
local hyphs = {}
for _, hyph in ipairs(overall_hyph) do
if hyph.syllabification == "+" then
hyph.syllabification = syllabify_from_spelling(pagename)
hyph.hyph = split_syllabified_spelling(hyph.syllabification)
elseif hyph.syllabification == "-" then
overall_hyph = {}
break
end
end
end
-- Loop over individual respellings, processing each.
for _, parsed in ipairs(parsed_respellings) do
parsed.pronun = generate_pronun(parsed)
local no_auto_rhyme = false
for _, term in ipairs(parsed.terms) do
if term.raw then
if not should_generate_rhyme_from_ipa(term.raw_phonemic or term.raw_phonetic) then
no_auto_rhyme = true
break
end
elseif not should_generate_rhyme_from_respelling(term.term) then
no_auto_rhyme = true
break
end
end
if #parsed.hyph == 0 then
if not overall_hyph and all_words_have_vowels(pagename) then
for _, term in ipairs(parsed.terms) do
if not term.raw then
local syllabification = syllabify_from_spelling(term.term)
local aligned_syll = align_syllabification_to_spelling(syllabification, pagename)
if aligned_syll then
m_table.insertIfNot(parsed.hyph, generate_hyph_obj(aligned_syll))
end
end
end
end
else
for _, hyph in ipairs(parsed.hyph) do
if hyph.syllabification == "+" then
hyph.syllabification = syllabify_from_spelling(pagename)
hyph.hyph = split_syllabified_spelling(hyph.syllabification)
elseif hyph.syllabification == "-" then
parsed.hyph = {}
break
end
end
end
-- Generate the rhymes.
local function dodialect_rhymes_from_pronun(rhyme_ret, dialect)
rhyme_ret.pronun[dialect] = {}
-- It's possible the pronunciation for a passed-in dialect was never generated. This happens e.g. with
-- {{es-pr|cebolla<style:seseo>}}. The initial call to generate_pronun() fails to generate a pronunciation
-- for the dialect 'distinction-yeismo' because the pronunciation of 'cebolla' differs between distincion
-- and seseo and so the seseo style restriction rules out generation of pronunciation for distincion
-- dialects (other than 'gipuzkoan', which always gets generated so as to determine on which axes
-- the dialects differ). However, when generating the rhyme, it is based only on -olla, whose pronunciation
-- does not differ between distincion and seseo, but does differ between lleismo and yeismo, so it needs to
-- generate a yeismo-specific rhyme, and 'distincion-yeismo' is the representative dialect for yeismo in the
-- situation where distincion and seseo do not have distinct results (based on the following line in
-- express_all_styles()):
-- express_style(false, "most of Spain and Latin America", "distincion-yeismo", "distincion-seseo-yeismo")
-- In this case we need to generate the missing overall pronunciation ourselves since we need it to generate
-- the dialect-specific rhyme pronunciation.
if not parsed.pronun.pronun[dialect] then
dodialect_pronun(parsed, parsed.pronun, dialect)
end
for _, pronun in ipairs(parsed.pronun.pronun[dialect]) do
-- We should have already excluded multiword terms and terms without vowels from rhyme generation (see
-- `no_auto_rhyme` below). But make sure to check that pronun.phonemic exists (it may not if raw
-- phonetic-only pronun is given).
if pronun.phonemic then
-- Count number of syllables by looking at syllable boundaries (including stress marks).
local num_syl = get_num_syl_from_phonemic(pronun.phonemic)
-- Get the rhyme by truncating everything up through the last stress mark + any following
-- consonants, and remove syllable boundary markers.
local rhyme = convert_phonemic_to_rhyme(pronun.phonemic)
local saw_already = false
for _, existing in ipairs(rhyme_ret.pronun[dialect]) do
if existing.rhyme == rhyme then
saw_already = true
-- We already saw this rhyme but possibly with a different number of syllables,
-- e.g. if the user specified two pronunciations 'biología' (4 syllables) and
-- 'bi.ología' (5 syllables), both of which have the same rhyme /ia/.
m_table.insertIfNot(existing.num_syl, num_syl)
break
end
end
if not saw_already then
local rh2 = rsub(rhyme, "ts̻", "")
local rhyme_diffs = nil
if dialect == "gipuzkoan" then
rhyme_diffs = {}
if rfind(rh2,"s̻") then
rhyme_diffs.need_bisc = true
end
if rfind(rhyme,"ts̺") then
rhyme_diffs.need_bisc = true
end
if rfind(rhyme,"J") then
rhyme_diffs.j_different = true
end
if rfind(rhyme,"N") then
rhyme_diffs.northern_different = true
end
end
table.insert(rhyme_ret.pronun[dialect], {
rhyme = remove_technical_chars(rhyme),
num_syl = {num_syl},
differences = rhyme_diffs,
})
end
end
end
end
if #parsed.rhyme == 0 then
if overall_rhyme or no_auto_rhyme then
parsed.rhyme = nil
else
parsed.rhyme = express_all_styles(parsed.style, dodialect_rhymes_from_pronun)
end
else
local no_rhyme = false
for _, rhyme in ipairs(parsed.rhyme) do
if rhyme.rhyme == "-" then
no_rhyme = true
break
end
end
if no_rhyme then
parsed.rhyme = nil
else
local function this_dodialect(rhyme_ret, dialect)
return dodialect_specified_rhymes(parsed.rhyme, parsed.hyph, {parsed}, rhyme_ret, dialect)
end
parsed.rhyme = express_all_styles(parsed.style, this_dodialect)
end
end
end
if overall_rhyme then
local no_overall_rhyme = false
for _, orhyme in ipairs(overall_rhyme) do
if orhyme.rhyme == "-" then
no_overall_rhyme = true
break
end
end
if no_overall_rhyme then
overall_rhyme = nil
else
local all_hyphs
if overall_hyph then
all_hyphs = overall_hyph
else
all_hyphs = {}
for _, parsed in ipairs(parsed_respellings) do
for _, hyph in ipairs(parsed.hyph) do
m_table.insertIfNot(all_hyphs, hyph)
end
end
end
local function dodialect_overall_rhyme(rhyme_ret, dialect)
return dodialect_specified_rhymes(overall_rhyme, all_hyphs, parsed_respellings, rhyme_ret, dialect)
end
overall_rhyme = express_all_styles(parsed.style, dodialect_overall_rhyme)
end
end
-- If all sets of pronunciations have the same rhymes, display them only once at the bottom.
-- Otherwise, display rhymes beneath each set, indented.
local first_rhyme_ret
local all_rhyme_sets_eq = true
for j, parsed in ipairs(parsed_respellings) do
if j == 1 then
first_rhyme_ret = parsed.rhyme
elseif not m_table.deepEquals(first_rhyme_ret, parsed.rhyme) then
all_rhyme_sets_eq = false
break
end
end
local function format_rhyme(rhyme_ret, num_bullets)
local function format_rhyme_style(tag, expressed_style, is_first)
local pronunciations = {}
local rhymes = {}
for _, pronun in ipairs(expressed_style.pronun) do
table.insert(rhymes, pronun)
end
local data = {
lang = lang,
rhymes = rhymes,
qualifiers = tag and {tag} or nil,
force_cat = force_cat,
}
local bullet = string.rep("*", num_bullets) .. " "
local formatted = bullet .. require("Module:rhymes").format_rhymes(data)
local formatted_for_len_parts = {}
table.insert(formatted_for_len_parts, bullet .. "Rhymes: " .. (tag and "(" .. tag .. ") " or ""))
for j, pronun in ipairs(expressed_style.pronun) do
if j > 1 then
table.insert(formatted_for_len_parts, ", ")
end
if pronun.qualifiers then
table.insert(formatted_for_len_parts, "(" .. table.concat(pronun.qualifiers, ", ") .. ") ")
end
table.insert(formatted_for_len_parts, "-" .. pronun.rhyme)
end
return formatted, textual_len(table.concat(formatted_for_len_parts))
end
return format_all_styles(rhyme_ret.expressed_styles, format_rhyme_style)
end
-- If all sets of pronunciations have the same hyphenations, display them only once at the bottom.
-- Otherwise, display hyphenations beneath each set, indented.
local first_hyphs
local all_hyph_sets_eq = true
for j, parsed in ipairs(parsed_respellings) do
if j == 1 then
first_hyphs = parsed.hyph
elseif not m_table.deepEquals(first_hyphs, parsed.hyph) then
all_hyph_sets_eq = false
break
end
end
local function format_hyphenations(hyphs, num_bullets)
local hyphtext = require("Module:hyphenation").format_hyphenations { lang = lang, hyphs = hyphs}
return string.rep("*", num_bullets) .. " " .. hyphtext
end
-- If all sets of pronunciations have the same homophones, display them only once at the bottom.
-- Otherwise, display homophones beneath each set, indented.
local first_hmps
local all_hmp_sets_eq = true
for j, parsed in ipairs(parsed_respellings) do
if j == 1 then
first_hmps = parsed.hmp
elseif not m_table.deepEquals(first_hmps, parsed.hmp) then
all_hmp_sets_eq = false
break
end
end
local function format_homophones(hmps, num_bullets)
local hmptext = require("Module:homophones").format_homophones { lang = lang, homophones = hmps }
return string.rep("*", num_bullets) .. " " .. hmptext
end
local function format_audio(audios, num_bullets)
local ret = {}
for i, audio in ipairs(audios) do
local text = require("Module:audio").format_audio {
lang = lang,
file = audio.file,
caption = audio.gloss,
q = audio.q,
qq = audio.qq,
a = audio.a,
aa = audio.aa,
}
table.insert(ret, string.rep("*", num_bullets) .. " " .. text)
end
return table.concat(ret, "\n")
end
local textparts = {}
local min_num_bullets = 9999
for j, parsed in ipairs(parsed_respellings) do
if parsed.bullets < min_num_bullets then
min_num_bullets = parsed.bullets
end
if j > 1 then
table.insert(textparts, "\n")
end
table.insert(textparts, parsed.pronun.text)
if #parsed.audio > 0 then
table.insert(textparts, "\n")
-- If only one pronunciation set, add the audio with the same number of bullets, otherwise
-- indent audio by one more bullet.
table.insert(textparts, format_audio(parsed.audio,
#parsed_respellings == 1 and parsed.bullets or parsed.bullets + 1))
end
if not all_rhyme_sets_eq and parsed.rhyme then
table.insert(textparts, "\n")
table.insert(textparts, format_rhyme(parsed.rhyme, parsed.bullets + 1))
end
if not all_hyph_sets_eq and #parsed.hyph > 0 then
table.insert(textparts, "\n")
table.insert(textparts, format_hyphenations(parsed.hyph, parsed.bullets + 1))
end
if not all_hmp_sets_eq and #parsed.hmp > 0 then
table.insert(textparts, "\n")
table.insert(textparts, format_homophones(parsed.hmp, parsed.bullets + 1))
end
end
if overall_audio and #overall_audio > 0 then
table.insert(textparts, "\n")
table.insert(textparts, format_audio(overall_audio, min_num_bullets))
end
if all_rhyme_sets_eq and first_rhyme_ret then
table.insert(textparts, "\n")
table.insert(textparts, format_rhyme(first_rhyme_ret, min_num_bullets))
end
if overall_rhyme then
table.insert(textparts, "\n")
table.insert(textparts, format_rhyme(overall_rhyme, min_num_bullets))
end
if all_hyph_sets_eq and #first_hyphs > 0 then
table.insert(textparts, "\n")
table.insert(textparts, format_hyphenations(first_hyphs, min_num_bullets))
end
if overall_hyph and #overall_hyph > 0 then
table.insert(textparts, "\n")
table.insert(textparts, format_hyphenations(overall_hyph, min_num_bullets))
end
if all_hmp_sets_eq and #first_hmps > 0 then
table.insert(textparts, "\n")
table.insert(textparts, format_homophones(first_hmps, min_num_bullets))
end
if overall_hmp and #overall_hmp > 0 then
table.insert(textparts, "\n")
table.insert(textparts, format_homophones(overall_hmp, min_num_bullets))
end
return table.concat(textparts)
end
return export