--[[--------------------------< A D D _ V A N C _ E R R O R >----------------------------------------------------
Adds a single Vancouver system error message to the template's output regardless of how many error actually exist.
To prevent duplication, added_vanc_errs is nil until an error message is emitted.
]]
local added_vanc_errs; -- flag so we only emit one Vancouver error / category
local function add_vanc_error ()
if not added_vanc_errs then
added_vanc_errs = true; -- note that we've added this category
table.insert( z.message_tail, { set_error( 'vancouver', {}, true ) } );
end
end
--[[--------------------------< I S _ G O O D _ V A N C _ N A M E >--------------------------------------------
For Vancouver Style, author/editor names are supposed to be rendered in Latin (read ASCII) characters. When a name
uses characters that contain diacritical marks, those characters are to converted to the corresponding Latin character.
When a name is written using a non-Latin alphabet or logogram, that name is to be transliterated into Latin characters.
These things are not currently possible in this module so are left to the editor to do.
This test allows |first= and |last= names to contain any of the letters defined in the four Unicode Latin character sets
[http://www.unicode.org/charts/PDF/U0000.pdf C0 Controls and Basic Latin] 0041–005A, 0061–007A
[http://www.unicode.org/charts/PDF/U0080.pdf C1 Controls and Latin-1 Supplement] 00C0–00D6, 00D8–00F6, 00F8–00FF
[http://www.unicode.org/charts/PDF/U0100.pdf Latin Extended-A] 0100–017F
[http://www.unicode.org/charts/PDF/U0180.pdf Latin Extended-B] 0180–01BF, 01C4–024F
|lastn= also allowed to contain hyphens, spaces, and apostrophes. (http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35029/)
|firstn= also allowed to contain hyphens, spaces, apostrophes, and periods
At the time of this writing, I had to write the 'if nil == mw.ustring.find ...' test ouside of the code editor and paste it here
because the code editor gets confused between character insertion point and cursor position.
]]
local function is_good_vanc_name (last, first)
if nil == mw.ustring.find (last, "^[A-Za-zÀ-ÖØ-öø-ƿDŽ-ɏ%-%s%']*$") or nil == mw.ustring.find (first, "^[A-Za-zÀ-ÖØ-öø-ƿDŽ-ɏ%-%s%'%.]*$") then
add_vanc_error ();
return false; -- not a string of latin characters; Vancouver required Romanization
end;
return true;
end
--[[--------------------------< R E D U C E _ T O _ I N I T I A L S >------------------------------------------
Attempts to convert names to initials in support of |name-list-format=vanc.
Names in |firstn= may be separated by spaces or hyphens, or for initials, a period. See http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35062/.
Vancouver style requires family rank designations (Jr, II, III, etc) to be rendered as Jr, 2nd, 3rd, etc. This form is not
currently supported by this code so correctly formed names like Smith JL 2nd are converted to Smith J2. See http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35085/.
This function uses ustring functions because firstname initials may be any of the unicode Latin characters accepted by is_good_vanc_name ().
]]
local function reduce_to_initials(first)
if mw.ustring.match(first, "^%u%u$") then return first end; -- when first contains just two upper-case letters, nothing to do
local initials = {}
local i = 0; -- counter for number of initials
for word in mw.ustring.gmatch(first, "[^%s%.%-]+") do -- names separated by spaces, hyphens, or periods
table.insert(initials, mw.ustring.sub(word,1,1)) -- Vancouver format does not include full stops.
i = i + 1; -- bump the counter
if 2 <= i then break; end -- only two initials allowed in Vancouver system; if 2, quit
end
return table.concat(initials) -- Vancouver format does not include spaces.
end
--[[--------------------------< L I S T _ P E O P L E >-------------------------------------------------------
Formats a list of people (e.g. authors / editors)
]]
local function list_people(control, people, etal, list_name) -- TODO: why is list_name here? not used in this function
local sep;
local namesep;
local format = control.format
local maximum = control.maximum
local lastauthoramp = control.lastauthoramp;
local text = {}
if 'vanc' == format then -- Vancouver-like author/editor name styling?
sep = ','; -- name-list separator between authors is a comma
namesep = ' '; -- last/first separator is a space
else
sep = ';' -- name-list separator between authors is a semicolon
namesep = ', ' -- last/first separator is <comma><space>
end
if sep:sub(-1,-1) ~= " " then sep = sep .. " " end
if is_set (maximum) and maximum < 1 then return "", 0; end -- returned 0 is for EditorCount; not used for authors
for i,person in ipairs(people) do
if is_set(person.last) then
local mask = person.mask
local one
local sep_one = sep;
if is_set (maximum) and i > maximum then
etal = true;
break;
elseif (mask ~= nil) then
local n = tonumber(mask)
if (n ~= nil) then
one = string.rep("—",n)
else
one = mask;
sep_one = " ";
end
else
one = person.last
local first = person.first
if is_set(first) then
if ( "vanc" == format ) then -- if vancouver format
one = one:gsub ('%.', ''); -- remove periods from surnames (http://www.ncbi.nlm.nih.gov/books/NBK7271/box/A35029/)
if not person.corporate and is_good_vanc_name (one, first) then -- and name is all Latin characters; corporate authors not tested
first = reduce_to_initials(first) -- attempt to convert first name(s) to initials
end
end
one = one .. namesep .. first
end
if is_set(person.link) and person.link ~= control.page_name then
one = "[[" .. person.link .. "|" .. one .. "]]" -- link author/editor if this page is not the author's/editor's page
end
end
table.insert( text, one )
table.insert( text, sep_one )
end
end
local count = #text / 2; -- (number of names + number of separators) divided by 2
if count > 0 then
if count > 1 and is_set(lastauthoramp) and not etal then
text[#text-2] = " & "; -- replace last separator with ampersand text
end
text[#text] = nil; -- erase the last separator
end
local result = table.concat(text) -- construct list
if etal and is_set (result) then -- etal may be set by |display-authors=etal but we might not have a last-first list
result = result .. sep .. ' ' .. cfg.messages['et al']; -- we've go a last-first list and etal so add et al.
end
return result, count
end
