require('strict');
local lang_obj = mw.language.getContentLanguage(); -- language object for number formatting appropriate to local language
--[[--------------------------< I 1 8 N _ T >------------------------------------------------------------------
An associative table of static text used in this module for use when translating this module to other languages.
The values $1 and $2 are replaced with values as stated in the associated message comment
]]
local i18n_t = {
-- non-fatal error messaging
['markup removed'] = '标记已移除，无法链接', -- error message
-- fatal error messaging
['fatal_no_article'] = '错误：页面$1未創建', -- $1 is page name
['fatal_no_sections'] = '错误：页面$1未分章节', -- $1 is page name
['fatal_redirect'] = '错误：页面$1是重定向', -- $1 is page name
['help link'] = '（[[$1|帮助]]）', -- help text wikilink for all error messages; $1 is calling template's name
['error category'] = '[[Category:有$1错误的页面]]', -- $1 is calling template's name; comment out this line, to suppress error category
['table caption'] = '[[$1]]各章节大小（共$2个章节）', -- caption; $1 is page name; $2 is number of sections
['section_name'] = '章节标题', -- column headings; left to right
['byte_count'] = '字节数',
['prose_size'] = '<abbr title="两汉字或一西文单词计为一词，粗略值">正文词数</abbr>',
['section_header'] = '标题', -- column headings; left to right
['section_total'] = '合计',
['top'] = nil, -- for the unnamed lede section; use this only when this module does not get correct string from MediaWiki:Vector-toc-beginning
['total'] = '总计', -- footer
['yesno'] = {
['yes'] = true,
['y'] = true,
['true'] = true,
['t'] = true,
['1'] = true,
['no'] = false,
['n'] = false,
['false'] = false,
['f'] = false,
['0'] = false
}
}
local section_top = i18n_t.top or -- i18n_t.top rarely needed
mw.message.new('vector-toc-beginning') -- lead section doesn't have a heading, get the interface message for 'top'
:inLanguage(lang_obj:getCode()) -- in the current wiki's content language
:plain(); -- and make sure we have a string
local noprose_sections = { -- Sections to exclude when calculating prose size
'References', '參考', '参考', '參考資料', '参考资料', '參考文獻', '参考文献',
'See also', '參見', '参见', '另見', '另见',
'External links', '外部連結', '外部链接',
'Further reading', '擴展閱讀', '扩展阅读',
};
--[[--------------------------< E R R O R _ M S G _ M A K E >--------------------------------------------------
common function to emit both fatal and non-fatal error messages
template_name used in error message help text link and error category link fetched from MediaWiki
error category emitted only for transclusions in the Talk namespace; only when i18n_t['error category'] has a
value; only when we have not already emitted the category link.
]]
local err_cat_added; -- page-scope boolean flag; true when error cat link has been emmitted; nil else
local function error_msg_make(template_name, msg, args_t, fatal)
local err_cat = ''; -- empty string for concatenation
if not err_cat_added and i18n_t['error category'] and 1 == mw.title.getCurrentTitle().namespace then
err_cat = mw.message.newRawMessage(i18n_t['error category'], { template_name }):plain(); -- create error category wikilink
err_cat_added = true; -- we will do this only once
end
local err_msg = table.concat({
fatal and '' or ' ', -- no space before fatal error messages
fatal and '<span style="font-size:100%;" class="error">' or '<span style="color:#d33">', -- select fatal/non-fatal styling
mw.message.newRawMessage(msg, args_t):plain(), -- compose the message
' ', -- insert a space between the message and the help link
mw.message.newRawMessage(i18n_t['help link'], { template_name }):plain(), -- add the help link
'</span>', -- and done with styling
err_cat -- if not yet emitted, append error cat link
});
return err_msg;
end
--[[--------------------------< FIND_STRING_IN >--------------------------------
Function returns True if the string `str` is found in the table `tbl`, False if not
]]
local function find_string_in(tbl, str)
for _, element in ipairs(tbl) do
if (element == str) then
return true
end
end
return false
end
--[[--------------------------< PROSESIZE_GET >--------------------------------
Function returns the prose size of a wikitext.
The prosesize is returned as the number of bytes of readable prose, as well as the number of words
]]
local function prosesize_get(wikitext)
-- Remove comments
local text = wikitext:gsub("<!%-%-.-%-%->", "")
local wordcount;
local _;
-- Remove refs and their contents
text = text:gsub("<ref[^>]-/>", "")
text = text:gsub("<ref.->.-</ref>", "")
-- Remove tables {|
text = text:gsub("{|.-|}", "")
-- Remove templates {{...}}
-- First, let's remove single brackets that might confused the below code
text = text:gsub("([^{]){([^{])", "%1%2")
text = text:gsub("([^}])}([^}])", "%1%2")
-- recursive removal is tricky, so this handles most cases
local n = 1
while n > 0 do -- stop when nothing more was removed
text, n = text:gsub("{{[^{}]-}}", "") -- remove the innermost templates
end
-- Remove files/images [[File:...]] or [[Image:...]]
text = text:gsub("%[%[(File|Image):.-%]%]", "")
-- Remove links but keep display text [[link|display]]
text = text:gsub("%[%[[^|%]]-|", "[[") -- strip leading [[foo|
text = text:gsub("%[%[(.-)%]%]", "%1") -- [[bar]] -> bar
-- Remove html tags (but not their contents unless self-closing)
text = text:gsub("<.->", "")
-- Remove headings markup (=== heading ===)
text = text:gsub("=+.-=+", "")
-- Remove formatting markup (''italic'', '''bold''', etc.)
text = text:gsub("''+", "")
-- Remove list lines (*, #, ;, :)
local cleaned_lines = {}
for line in text:gmatch("[^\n]+") do
if not line:match("^%s*[%*#;:]") then
table.insert(cleaned_lines, line)
end
end
text = table.concat(cleaned_lines, "\n")
-- Remove now-empty parentheses
-- text = text:gsub("%(%)", "")
-- Collapse whitespace
text = text:gsub("%s+", " ")
-- Trim
text = text:match("^%s*(.-)%s*$")
text = mw.ustring.gsub(text, "[一-鿿][一-鿿]", "a ") -- \u4E00-\u9FFF
-- Count the number of words
_, wordcount = text:gsub("%S+", "")
-- Return byte length and number of words
return #text, wordcount
end
--[[--------------------------< R E D L I N K _ T E M P L A T E _ R E M O V E >--------------------------------
Following a preprocessing of the section heading, any templates not known to the local wiki will have been converted
to a template-space redlink to the unknown template-name in the locally named template namespace. These redlinks
must be removed and the section name marked as modified so that the section heading link can be suppressed.
returns section name and boolean true if redlinks were replaced; boolean false else
]]
local function redlink_template_remove(section_name)
local redlink_pattern = '%[%[:' .. mw.site.namespaces[10]["name"] .. ':.-%]%]'; -- fetch template names space name in the wiki's local language
local count;
section_name, count = section_name:gsub(redlink_pattern, '[...]'); -- replace unknown-template redlinks with bracketed ellipses
return section_name, 0 < count;
end
--[[--------------------------< A N C H O R S _ R E M O V E >--------------------------------------------------
remove html markup that looks like an anchor. There appear to be two general forms:
<span class="anchor" id="Foo"></span>
<span id="Foo"></span>
multiple anchor spans are allowed
Because anchor markup is allowed in section headings, does not set the modified flag on return
]]
local function anchors_remove(section_name)
local patterns = {
'<span +[^>]*class *= *"anchor"[^>]*></span>', -- don't care about the id= or any other attribute here if we have the anchor class
'<span +%f[%a]id *= *".-" *></span>', -- here the span must have only the id= attribute
}
for _, pattern in ipairs(patterns) do
section_name = section_name:gsub(pattern, ''); -- remove all anchor spans
end
return section_name;
end
--[[--------------------------< R E F S _ R E M O V E >--------------------------------------------------------
remove wikitext reference markup. done this way because we later preprocess the section name to render any templates
that are present in the section name (there shouldn't be but that doesn't stop editors from including them).
preprocessing a section name with reference markup causes MediaWiki to create a reflist; a side effect that we
don't want.
returns modified section name and boolean true when references have been removed; unmodified section name and false else.
]]
local function refs_remove(section_name)
local name; -- modified (or unmodified) section name
local markup_removed; -- boolean true when reference markup has been removed
local count;
name, count = section_name:gsub('<ref.-/>', ''); -- remove self-closed <ref with attributes /> tags
markup_removed = 0 < count; -- count not zero, set <markup_removed> true
name, count = name:gsub('<ref.->.-</ref>', ''); -- remove remaining ref tags and content (if any)
return name, markup_removed or (0 < count)
end
--[[--------------------------< S T R I P M A R K E R S _ R E M O V E >----------------------------------------
remove stripmarkers from preprocessed section names. it may be best to preserve <nowiki/> tags before section name
is preprocessed to prevent '<nowiki/>'' from being interpreted as ''' bold markup. It is not possible to do that
here because all nowiki strip markers are only identifiable by the numbers.
returns modified section name and boolean true when stripmarkers have been removed; unmodified section name and false else.
]]
local function stripmarkers_remove(section_name)
local count;
section_name, count = section_name:gsub('\127[^\127]*UNIQ%-%-%a+%-[%x]+%-QINU[^\127]*\127', '');
return section_name, (0 < count);
end
--[=[-------------------------< R E M O V E _ W I K I _ L I N K >----------------------------------------------
Gets the display text from a wikilink like [[A|B]] or [[B]] gives B
The str:gsub() returns either A|B from a [[A|B]] or B from [[B]] or B from B (no wikilink markup).
In l(), l:gsub() removes the link and pipe (if they exist); the second :gsub() trims white space from the label
if str was wrapped in wikilink markup. Presumably, this is because without wikimarkup in str, there is no match
in the initial gsub, the replacement function l() doesn't get called.
]=]
local function remove_wiki_link(str)
return (str:gsub("%[%[([^%[%]]*)%]%]", function(l)
return l:gsub("^[^|]*|(.*)$", "%1"):gsub("^%s*(.-)%s*$", "%1");
end));
end
--[[--------------------------< R E M O V E _ C O N T A I N E R >----------------------------------------------
Inspired from above, removes everything between < & >
Used to remove html containers from headings to fix breaking section links, but legitimate text within < & > are removed too
returns text and boolean true if modified; text and boolean false else
]]
local function remove_container(str)
local count;
str, count = str:gsub("<([^>]*)>", function(l)
return l:gsub("^%s*(.-)%s*$", "");
end);
return str, 0 < count
end
--[=[-------------------------< M A K E _ W I K I L I N K >----------------------------------------------------
Makes a wikilink; when both link and display text is provided, returns a wikilink in the form [[L|D]]; if only
link is provided, returns a wikilink in the form [[L]]; if neither are provided or link is omitted, returns an
empty string.
]=]
local function make_wikilink(link, display)
if link and ('' ~= link) then
if display and ('' ~= display) then
return table.concat({ '[[', link, '|', display, ']]' });
else
return table.concat({ '[[', link, ']]' });
end
end
return display or ''; -- link not set so return the display text
end
--[[--------------------------< S E C T I O N _ D A T A _ G E T >----------------------------------------------
Read article content and fill associative arrays in sequence <sections_t>. The associative arrays hold section
name, its starting location within content, section size, and section level (2 (==), 3 (===), etc). Modifies and
returns <total> (article size) and <max> (longest section).
]]
local function section_data_get(content, total, max, total_prose, max_prose, sections_t, getprose)
local s, e, name, _;
----------< M A X _ U P D A T E >----------
local function max_update(max, sec_size, sec_i) -- local function to update max and its index
if max < sec_size then -- new section is longer
return sec_size, sec_i; -- update and done
end
return max; -- no update
end
-------------------------------------------
while (1) do -- done this way because some articles reuse section names
s, e, name = string.find(content, '\n==+ *(.-) *==+', e); -- get start, end, and section name beginning at end of last find; newline must precede '==' heading markup
if s then
table.insert(sections_t, { ['name'] = name, ['start'] = s }); -- save section name and start location of this find
else
break;
end
end
for i, section_t in ipairs(sections_t) do
if 1 ~= i then -- i==1 is the lead section; already accounted for
local escaped_section_name = section_t.name:gsub('[%(%)%.%%%+%-%*%?%[%^%$%]]', '%%%0'); -- escape lua patterns in section name
local pattern = '(==+ *' .. escaped_section_name .. ' *==+.-)==+'; -- make a pattern to get the content of a section
local section_content = string.match(content, pattern, section_t.start); -- get the content beginning at the string.find() start location
if section_content then
section_t.size = #section_content; -- get a count of the bytes in the section
total = total + section_t.size;
max = max_update(max, section_t.size, i); -- keep track of largest count
if getprose then
if find_string_in(noprose_sections, escaped_section_name) then
section_t.prosesize = 0;
else
_, section_t.prosesize = prosesize_get(section_content);
end
total_prose = total_prose + section_t.prosesize;
max_prose = max_update(max_prose, section_t.prosesize, i); -- keep track of largest count
end
else -- probably the last section (no proper header follows this section name)
pattern = '(==+ *' .. escaped_section_name .. ' *==+.+)'; -- make a new pattern
section_content = string.match(content, pattern, section_t.start); -- try to get content
if section_content then
section_t.size = #section_content; -- get a count of the bytes in the section
total = total + section_t.size;
max = max_update(max, section_t.size, i); -- keep track of largest count
if getprose then
if find_string_in(noprose_sections, escaped_section_name) then
section_t.prosesize = 0;
else
_, section_t.prosesize = prosesize_get(section_content);
end
total_prose = total_prose + section_t.prosesize;
max_prose = max_update(max_prose, section_t.prosesize, i); -- keep track of largest count
end
else
section_t.size = '—'; -- no content so show that
section_t.prosesize = '-';
end
end
local _;
_, section_t.level = section_content:find('^=+'); -- should always be the first n characters of section content
end
end
return total, max, total_prose, max_prose;
end
--[[--------------------------< A R T I C L E _ C O N T E N T _ G E T >----------------------------------------
Common function to fetch the <article> content. Also fetches byte count for lead section because that section
is different from all others
On success, returns unparsed article content, lead section byte count, and nil message. On error, returns nil
content, nil lead section byte count, and fatal error message
]]
local function article_content_get(article, template_name, getprose)
local _, section_content_prose;
local title_obj = mw.title.new(article)
local content = title_obj:getContent(); -- get unparsed wikitext from the article
if not content then
return nil, nil, nil, error_msg_make(template_name, i18n_t['fatal_no_article'], { article }, true); -- emit fatal error message and abandon
end
if title_obj.isRedirect then -- redirects don't have sections
return nil, nil, nil, error_msg_make(template_name, i18n_t['fatal_redirect'], { article }, true); -- emit fatal error message and abandon
end
local section_content = content:match('(.-)===*'); -- get the lead section
if not section_content then
return nil, nil, nil, error_msg_make(template_name, i18n_t['fatal_no_sections'], { article }, true); -- emit fatal error message and abandon
end
if getprose then
_, section_content_prose = prosesize_get(section_content)
end
return content, #section_content, section_content_prose, nil; -- return the contnet and length of the lead section and nil for error message
end
--[[--------------------------< S I Z E >----------------------------------------------------------------------
module entry point
créer une liste liée au wikilien des sections de <nom de l'article> et de leur taille en octets dans un wikitable triable.
{{#invoke:Section sizes|size|<article name>}}
]]
local function size(frame)
local template_name = frame:getParent():getTitle(); -- get template name for use in error messaging and category name
local section_info_t = {}; -- table to hold section names and sizes
local section_content; -- section content used for counting
local totcount = {};
local totcount_prose = {};
local lastlevel;
local maxlevels;
local levelcounts = {};
local levelcounts_prose = {};
local upperlevel;
local highlight;
local highlighttot;
local highlight_prose;
local highlighttot_prose;
local total; -- sum of all byte counts
local max; -- largest section so far encountered
local total_prose;
local max_prose;
local totmax; -- largest section so far encountered (section total)
local totmax_prose; -- largest section so far encountered (section total)
local _; -- dummy for using gsub to count bytes
local wl_name; -- anchor and display portion for wikilinks in rendered list
local getprose = i18n_t.yesno[frame.args.getprose or 'true']; -- boolean false when |_getprose=no; true else
getprose = getprose == nil and true or
getprose -- can't do "or true" because then it will turn false values true
local content, sec_0_count, sec_0_count_prose, msg =
article_content_get(frame.args[1], template_name, getprose); -- get the article content with lead section byte count because lead is different from all others
if msg then -- is something wrong
return msg; -- emit message and abandon
end
total = sec_0_count;
max = sec_0_count;
total_prose = sec_0_count_prose;
max_prose = sec_0_count_prose;
-- sequence of associative arrays with section name, starting location, size, and level
local sections_t = { { ['level'] = 2, ['name'] = section_top, ['size'] = sec_0_count, ['start'] = 1, ['prosesize'] = sec_0_count_prose } }; -- init with lead info
total, max, total_prose, max_prose = section_data_get(content, total, max, total_prose, max_prose, sections_t,
getprose); -- fill <sections_t> arrays for all sections except the lead
totmax = 0;
totmax_prose = 0;
lastlevel = 0;
maxlevels = 7;
for j = 1, maxlevels do
levelcounts[j] = 0;
levelcounts_prose[j] = 0;
end
local level, size, prosesize;
for i = #sections_t, 1, -1 do
level = sections_t[i].level;
size = sections_t[i].size;
prosesize = sections_t[i].prosesize or 0;
if level < lastlevel then -- reset all
totcount[i] = levelcounts[level] + size;
totcount_prose[i] = levelcounts_prose[level] + prosesize;
for j = level, maxlevels do
levelcounts[j] = 0;
levelcounts_prose[j] = 0;
end
end
if level >= lastlevel then
totcount[i] = size;
totcount_prose[i] = prosesize;
end
if level > 0 then
upperlevel = level - 1;
levelcounts[upperlevel] = levelcounts[upperlevel] + totcount[i];
levelcounts_prose[upperlevel] = levelcounts_prose[upperlevel] + totcount_prose[i];
end
lastlevel = level;
if totcount[i] > totmax then
totmax = totcount[i];
end
if totcount_prose[i] > totmax_prose then
totmax_prose = totcount_prose[i];
end
end
for i, section_t in ipairs(sections_t) do
level = section_t.level;
size = section_t.size;
prosesize = section_t.prosesize;
if size == max then
highlight = 'background:#f00;color:#000;"|';
else
local proportion = size /
max -- get value of "how much of the max" the count is
local gb = 250 -
math.floor(250 * proportion) -- approach #f8f9fa [r=248,g=249,b=250] (default wikitable cell color) for small bytecounts
highlight = string.format('background:#F8%02X%02X;color:#000;"|', gb, gb) -- shade the bg as r: 248, g: gb, and b: gb
end
if getprose then
if prosesize == max_prose then
highlight_prose = 'background:#008000;color:#fff;"|';
else
local proportion = prosesize /
max_prose -- get value of "how much of the max" the count is
local gb = 250 -
math.floor(250 * proportion) -- approach #f8f9fa [r=248,g=249,b=250] (default wikitable cell color) for small bytecounts
highlight_prose = string.format('background:#%02XF8%02X;color:#000;"|', gb, gb) -- shade the bg as r: 248, g: gb, and b: gb
end
end
highlighttot = ''; -- start the style declaration
if totcount[i] == totmax then
highlighttot = highlighttot .. 'background:#f00;color:#000;';
else
local proportion = totcount[i] /
totmax -- get value of "how much of the max" the count is
local gb = 250 -
math.floor(250 * proportion) -- approach #f8f9fa [r=248,g=249,b=250] (default wikitable cell color) for small bytecounts
highlighttot = highlighttot ..
string.format('background:#F8%02X%02X;color:#000;', gb, gb) -- shade the bg as r: 248, g: gb, and b: gb
end
if getprose then
highlighttot_prose = ''; -- start the style declaration
if totcount_prose[i] == totmax_prose then
highlighttot_prose = highlighttot_prose .. 'background:#008000;color:#fff;';
else
local proportion = totcount_prose[i] /
totmax_prose -- get value of "how much of the max" the count is
local gb = 250 -
math.floor(250 * proportion) -- approach #f8f9fa [r=248,g=249,b=250] (default wikitable cell color) for small bytecounts
highlighttot_prose = highlighttot_prose ..
string.format('background:#%02XF8%02X;color:#000;', gb, gb) -- shade the bg as r: 248, g: gb, and b: gb
end
end
if level == 2 then
highlighttot = highlighttot .. 'font-weight:bold;'; -- if main section, make it bold
elseif totcount[i] == size then
highlighttot = 'color:transparent;'; -- hide totals for subsections with no subsubsections, values required for proper sorting
end
highlighttot = highlighttot .. '"|'; -- close the style declaration
if getprose then
if level == 2 then
highlighttot_prose = highlighttot_prose .. 'font-weight:bold;'; -- if main section, make it bold
elseif totcount_prose[i] == prosesize then
highlighttot_prose = 'color:transparent;'; -- hide totals for subsections with no subsubsections, values required for proper sorting
end
highlighttot_prose = highlighttot_prose .. '"|'; -- close the style declaration
end
level = (2 < level) and ((level - 2) * 1.6) or nil; -- remove offset and mult by 1.6em (same indent as ':' markup which doesn't work in a table)
local markup_removed; -- temp flag to note that the section heading has been modified (references and html-like markup stripped, etc)
local modified = false; -- flag to select section heading styling; false: wikilink; true: plain text with error message
wl_name, modified = refs_remove(section_t.name); -- remove all references
wl_name = remove_wiki_link(wl_name); -- remove all wikilinks
wl_name = wl_name:gsub('<nowiki/>', '__sss_nowiki/__'); -- replace <nowiki/> tag with special secret symbol
wl_name = frame:preprocess(wl_name); -- render to html
wl_name, markup_removed = redlink_template_remove(wl_name); -- remove redlink template wikilinks created by preprocessing of unknown templates
modified = modified or markup_removed; -- update <modified>
wl_name = anchors_remove(wl_name); -- remove known anchor markup; these allowed in section heading so do not bump <modified>
wl_name = wl_name:gsub('__sss_nowiki/__', '<nowiki/>'); -- replace special secret symbol with <nowiki/> tag
wl_name, markup_removed = stripmarkers_remove(wl_name); -- remove any strip markers resulting from preprocessing
modified = modified or markup_removed; -- update <modified>
wl_name = wl_name:gsub('</?i>', '\'\''); -- italic markup has been converted to html; unconvert so remove_container() doesn't remove inappropriately
wl_name = wl_name:gsub('</?b>', '\'\'\''); -- bold markup has been converted to html; unconvert so remove_container() doesn't remove inappropriately
wl_name, markup_removed = remove_container(wl_name); -- remove html containers from section headings so that we can link to the section
modified = modified or markup_removed; -- update <modified>
wl_name = wl_name:gsub('[%[%]]', { ['['] = '[', [']'] = ']' }); -- replace '[' and ']' characters with html entities so that wikilinked section names work
wl_name = mw.text.trim(wl_name); -- trim leading/trailing white space if any because white space buggers up url anchor links
local heading_text;
if modified then
heading_text = table.concat({ -- modified headings are rendered in plain text with an error message
wl_name, -- plain text section name
error_msg_make(template_name, i18n_t['markup removed'], {}), -- error message with help link
}); -- close help link
else
heading_text = make_wikilink(frame.args[1] .. '#' .. wl_name:gsub("''+", ''), wl_name); -- unmodified rendered as is
end
table.insert(section_info_t,
table.concat({ -- build most of a table row here because here we have heading information that we won't have later
level and '<span style="margin-left:' .. level .. 'em">' or '', -- indent per heading level (number of '=' in heading markup)
heading_text, -- section link remove any bold/italic markup from the link part of the wikilink; leave the markup in the display
level and '</span>' or '', -- close the span if opened
'||style="text-align:right;', -- table column separator and right align byte count column
highlight,
lang_obj:formatNum(size), -- commafied byte count for section
'||style="text-align:right;', -- table column separator and right align section total column
highlighttot,
lang_obj:formatNum(totcount[i]), -- section total count!!
}) .. (getprose and table.concat({
'||style="text-align:right;', -- table column separator and right align byte count column
highlight_prose,
lang_obj:formatNum(prosesize), -- section prose size
'||style="text-align:right;', -- table column separator and right align byte count column
highlighttot_prose,
lang_obj:formatNum(totcount_prose[i]), -- section prose size total
}) or ''));
end
local out = {}; -- make a sortable wikitable for output
table.insert(out,
string.format('{| class="wikitable sortable" style="%s"\n|+%s', -- output caption and column headings
frame.args.style or '', -- value for style= attribute
mw.message.newRawMessage(i18n_t['table caption'], { frame.args[1], #section_info_t }):plain()
));
table.insert(out, table.concat({ -- column headings
'\n! rowspan=2|',
i18n_t.section_name,
'!! colspan=2|',
i18n_t.byte_count,
}));
if getprose then
table.insert(out, table.concat({
'!! colspan=2|',
i18n_t.prose_size,
}));
end
table.insert(out, table.concat({ -- new header column
'\n|-',
'\n!',
i18n_t.section_header,
'!!',
i18n_t.section_total,
}));
if getprose then
table.insert(out, table.concat({
'!!',
i18n_t.section_header,
'!!',
i18n_t.section_total,
}));
end
table.insert(out, '\n|-\n|'); -- first row pipe
table.insert(out, table.concat(section_info_t, '\n|-\n|')); -- section rows with leading pipes (except first row already done)
table.insert(out,
table.concat({ -- total number of bytes; heading markup so that sorting doesn't move this row from the bottom to top
'\n|-\n!scope=row|',
i18n_t.total, -- footer label
'\n!style="text-align:right"|',
lang_obj:formatNum(total), -- byte count sum; TODO: to columns, should be two separate sums; test for equality?
'\n!style="text-align:right"|',
lang_obj:formatNum(total), -- section size sum; TODO: to columns, should be two separate sums; test for equality?
}));
if getprose then
table.insert(out, table.concat({
'\n!style="text-align:right"|',
lang_obj:formatNum(total_prose), -- section size sum; TODO: to columns, should be two separate sums; test for equality?
'\n!style="text-align:right"|',
lang_obj:formatNum(total_prose), -- section size sum; TODO: to columns, should be two separate sums; test for equality?
}));
end
table.insert(out, '\n|}'); -- close the wikitable
local result = table.concat(out);
return result; -- because gsub returns string and number of replacements
end
--[[--------------------------< S E C T I O N _ S I Z E _ G E T >----------------------------------------------
return the length of the specified section of the specified article.
parameters:
{{{1}}} – article title (required)
{{{2}}} – section name or one of three keywords. keywords use leading underscores to minimize confusion with
section names 'Lead' (the metal) and 'Max' (a proper name), etc.
<section name> – returns the length of the named section; section name comparisons are case insensitve.
keywords:
_lead – returns the length of the lead (unnamed section)
_max – returns the length of the longest section
_total – returns the article length
{{{3}}} – supports one keyword
_all – requires named section in {{{2}}}; not supported for keywords; returns size of the named section plus
the lengths of its subsections
|_nosep= – accepts one value 'yes'; renders section size without thousands separator; ignored when |_pct= set;
default is commafied
|_pct= – accepts one value 'yes'; function returns size specified by name or keyword as a percentage of _total
rounded to two decimals; appends '%' symbol; _total as a percentage of _total allowed but why?
returns nil when there is no keyword match and no <section name> match
{{#invoke:section sizes|section_length|<article title>|<_lead|_max|_total|section name>|_all}}
]]
local function section_size_get(frame)
local args_t = require("Module:Arguments").getArgs(frame);
local template_name = frame:getParent():getTitle(); -- get template name for use in error messaging and category name
local nosep = i18n_t.yesno[args_t._nosep or 'false'] or false; -- boolean true when |_nosep=yes; false else
local pct = i18n_t.yesno[args_t._pct or 'false'] or false; -- boolean true when |_pct=yes; false else
local getprose = false -- fetching prose is only used by size(), not section_size_get()
local content, sec_0_count, sec_0_count_prose, msg =
article_content_get(args_t[1], template_name, getprose); -- get the article content with lead section byte count in <count_t> because lead is different from all others
if msg then -- is something wrong
return msg; -- emit message and abandon
end
local total = sec_0_count; -- initialize with length of the lead
local max = sec_0_count;
local total_prose = sec_0_count_prose;
local max_prose = sec_0_count_prose;
----------< R E T V A L >----------
local function retval(size) -- local function to select return value format according to |pct=
return pct and string.format("%2.2f%%", 100 * (size / total)) or -- return the percentage
lang_obj:formatNum(size, { noCommafy = nosep }); -- return the size
end
-----------------------------------
-- sequence of associative arrays with section name, starting location, size, and level
local sections_t = { { ['level'] = 2, ['name'] = section_top, ['size'] = sec_0_count, ['start'] = 1 } }; -- init with lead info
total, max = section_data_get(content, total, max, total_prose, max_prose, sections_t, getprose);
if '_lead' == args_t[2] then -- {{{2}}} has '_lead' keyword; lead section is handled differently from all other sections
return retval(sec_0_count); -- return selected output form and done
elseif '_max' == args_t[2] then -- when {{{2}}} has '_max' keyword
return retval(max); -- return selected output form and done
elseif '_total' == args_t[2] then -- when {{{2}}} has '_total' keyword
return retval(total); -- return the article's total length and done; pct possible, but why?
elseif args_t[2] then -- if set, it should be a section name
local target_section_name = args_t[2]:lower(); -- get it and force lower case for comparison
local section_level;
local section_size = 0;
for i, section_t in ipairs(sections_t) do -- loop through <section_t.name> looking for a match; TODO: is there a better way to do this?
if not section_level then -- not yet found a match
if section_t.name:lower() == target_section_name then -- force lower case for comparison
if '_all' == args_t[3] then -- when {{{3}}} has '_all' keyword
section_level = section_t.level; -- found it so initialize these; this one is a flag to know that we found the target section
section_size = section_t.size; -- init
else
return retval(section_t.size); -- return selected output form and done
end
end
elseif section_level < section_t.level then -- here when we found the section, '_all' keyword present
section_size = section_size + section_t.size; -- this section level greater than target's, so add in the subsection's size
else -- here when we found the section, '_all' keyword present
return retval(section_size); -- return selected output form and done
end
end
else -- here when {{{3}}} has nothing
return nil; -- so return nothing
end
end
--[[--------------------------< E X P O R T E D F U N C T I O N S >------------------------------------------
]]
return
{
size = size,
section_size_get = section_size_get,
}
