From c654151582a77a0b459e3f55b687e43a32d4b67d Mon Sep 17 00:00:00 2001 From: Case Duckworth Date: Thu, 26 Mar 2015 19:46:45 -0700 Subject: Add HAPAX LEGOMENA support & flatten structure The list of hapax legomena for this project is available at /hapax.html. In addition, the directory structure has been further flattened. All assets (javascript, lua, images, fonts) are in /trunk/. One other thing was to update the makefile. It compiles hapax.txt from rivers. --- lua/allwords.lua | 17 --- lua/river.lua | 228 ----------------------------------- lua/sample-writer.lua | 324 -------------------------------------------------- 3 files changed, 569 deletions(-) delete mode 100644 lua/allwords.lua delete mode 100644 lua/river.lua delete mode 100644 lua/sample-writer.lua (limited to 'lua') diff --git a/lua/allwords.lua b/lua/allwords.lua deleted file mode 100644 index b87f08a..0000000 --- a/lua/allwords.lua +++ /dev/null @@ -1,17 +0,0 @@ -function allwords () - local line = io.read() - local pos = 1 - return function () - while line do - local s, e = string.find(line, "%w+", pos) - if s then - pos = e + 1 - return string.sub(line, s, e) - else - line = io.read() - pos = 1 - end - end - return nil - end -end diff --git a/lua/river.lua b/lua/river.lua deleted file mode 100644 index cd867af..0000000 --- a/lua/river.lua +++ /dev/null @@ -1,228 +0,0 @@ --- Pandoc River writer --- it takes out all formatting, leaving only a river of text --- running down the page: one word per line --- vim: fdm=marker --- invoke with: pandoc -t river.lua - -os.setlocale("en_US.UTF-8") - -local function flow(s) - return s:gsub("%s+", "\n") -end - -local function nude(s) - -- Expand contractions - s = s:gsub("'%a+%s", function (x) - if x == "'ll" then - return " will " - elseif x == "'ve" then - return " have " - elseif x == "'re" then - return " are " - else - return x - end - end) - -- Get rid of quotes around words - s = s:gsub('"', ' ') - s = s:gsub("%s+'", ' ') - s = s:gsub("'%s+", ' ') - -- Remove HTML entities - s = s:gsub('&.-;', ' ') - s = s:gsub('%b<>', ' ') - -- Remove end-of-line backslashes - s = s:gsub('%s+\\$', ' ') - -- Remove dashes (not hyphens) - s = s:gsub('%-%-+', ' ') - s = s:gsub('%-%s', ' ') - -- Remove everything that is not letters or numbers - s = s:gsub('[%.!%?:;,%[%]%(%)<>]', ' ') - -- Remove extra spaces - s = s:gsub('%s+', ' ') - return s:lower() -end - --- This function is called once for the whole document. Parameters: --- body is a string, metadata is a table, variables is a table. --- One could use some kind of templating --- system here; this just gives you a simple standalone HTML file. -function Doc(body, metadata, variables) - local buffer = "" - local function add(s) - buffer = buffer .. nude(s) .. "\n" - end - if metadata['title'] then - add(metadata['title']) - end - if metadata['subtitle'] then - add(metadata['subtitle']) - end - -- TODO: epigraph.content, epigraph.attrib, dedication, other metadata? - add(body) - return flow(buffer) -end - --- Remove all formatting {{{ -function Note(s) - return nude(s) -end - -function Blocksep() - return "\n" -end -function Emph(s) - return nude(s) -end - -function Strong(s) - return nude(s) -end - -function Subscript(s) - return nude(s) -end - -function Superscript(s) - return nude(s) -end - -function SmallCaps(s) - return nude(s) -end - -function Strikeout(s) - return nude(s) -end - -function Code(s, attr) - return nude(s) -end - -function CodeBlock(s, attr) - return nude(s) -end - -function InlineMath(s) - return nude(s) -end - -function DisplayMath(s) - return nude(s) -end - -function Span(s, attr) - return nude(s) -end - -function Cite(s) - return nude(s) -end - -function Plain(s) - return nude(s) -end - --- Links only include the link text -function Link(s, src, tit) - return nude(s) -end - --- Images have nothing to give us --- (but add a space just in case) -function Image(s, src, tit) - return "\n" -end - -function CaptionedImage(s, src, tit) - return "\n" -end - -function Str(s) - return nude(s) -end - -function Div(s, attr) - return nude(s) -end - -function Space(s) - return "\n" -end - -function LineBreak() - return "\n" -end - -function Para(s) - return nude(s) -end - -function Header(lev, s, attr) - return nude(s) -end - -function BlockQuote(s) - return nude(s) -end - -function HorizontalRule() - return "\n" -end - -function BulletList(items) - local buffer = "" - for _, item in pairs(items) do - buffer = buffer .. nude(item) .. "\n" - end - return buffer .. "\n" -end - -function OrderedList(items) - local buffer = "" - for _, item in pairs(items) do - buffer = buffer .. nude(item) .. "\n" - end - return buffer .. "\n" -end - -function DefinitionList(items) - local buffer = "" - for _, item in pairs(items) do - for k, v in pairs(item) do - buffer = buffer .. nude(k) .. "\n" .. nude(v) .. "\n" - end - end - return buffer .. "\n" -end - -function Table(caption, aligns, widths, headers, rows) - local buffer = "" - local function add(s) - buffer = buffer .. nude(s) .. "\n" - end - if caption ~= "" then - add(caption) - end - for _,h in pairs(headers) do - add(h) - end - for _, row in pairs(rows) do - for _, cell in pairs(row) do - add(cell) - end - end - return buffer -end --- }}} - --- The following code will produce runtime warnings when you haven't defined --- all of the functions you need for the custom writer, so it's useful --- to include when you're working on a writer. -local meta = {} -meta.__index = - function(_, key) - io.stderr:write(string.format("WARNING: Undefined function '%s'\n",key)) - return function() return "" end - end -setmetatable(_G, meta) - diff --git a/lua/sample-writer.lua b/lua/sample-writer.lua deleted file mode 100644 index a0c3c29..0000000 --- a/lua/sample-writer.lua +++ /dev/null @@ -1,324 +0,0 @@ --- This is a sample custom writer for pandoc. It produces output --- that is very similar to that of pandoc's HTML writer. --- There is one new feature: code blocks marked with class 'dot' --- are piped through graphviz and images are included in the HTML --- output using 'data:' URLs. --- --- Invoke with: pandoc -t sample.lua --- --- Note: you need not have lua installed on your system to use this --- custom writer. However, if you do have lua installed, you can --- use it to test changes to the script. 'lua sample.lua' will --- produce informative error messages if your code contains --- syntax errors. - --- Character escaping -local function escape(s, in_attribute) - return s:gsub("[<>&\"']", - function(x) - if x == '<' then - return '<' - elseif x == '>' then - return '>' - elseif x == '&' then - return '&' - elseif x == '"' then - return '"' - elseif x == "'" then - return ''' - else - return x - end - end) -end - --- Helper function to convert an attributes table into --- a string that can be put into HTML tags. -local function attributes(attr) - local attr_table = {} - for x,y in pairs(attr) do - if y and y ~= "" then - table.insert(attr_table, ' ' .. x .. '="' .. escape(y,true) .. '"') - end - end - return table.concat(attr_table) -end - --- Run cmd on a temporary file containing inp and return result. -local function pipe(cmd, inp) - local tmp = os.tmpname() - local tmph = io.open(tmp, "w") - tmph:write(inp) - tmph:close() - local outh = io.popen(cmd .. " " .. tmp,"r") - local result = outh:read("*all") - outh:close() - os.remove(tmp) - return result -end - --- Table to store footnotes, so they can be included at the end. -local notes = {} - --- Blocksep is used to separate block elements. -function Blocksep() - return "\n\n" -end - --- This function is called once for the whole document. Parameters: --- body is a string, metadata is a table, variables is a table. --- One could use some kind of templating --- system here; this just gives you a simple standalone HTML file. -function Doc(body, metadata, variables) - local buffer = {} - local function add(s) - table.insert(buffer, s) - end - add('') - add('') - add('') - add('' .. (metadata['title'] or '') .. '') - add('') - add('') - if metadata['title'] and metadata['title'] ~= "" then - add('

' .. metadata['title'] .. '

') - end - for _, author in pairs(metadata['author'] or {}) do - add('

' .. author .. '

') - end - if metadata['date'] and metadata['date'] ~= "" then - add('

' .. metadata.date .. '

') - end - add(body) - if #notes > 0 then - add('
    ') - for _,note in pairs(notes) do - add(note) - end - add('
') - end - add('') - add('') - return table.concat(buffer,'\n') -end - --- The functions that follow render corresponding pandoc elements. --- s is always a string, attr is always a table of attributes, and --- items is always an array of strings (the items in a list). --- Comments indicate the types of other variables. - -function Str(s) - return escape(s) -end - -function Space() - return " " -end - -function LineBreak() - return "
" -end - -function Emph(s) - return "" .. s .. "" -end - -function Strong(s) - return "" .. s .. "" -end - -function Subscript(s) - return "" .. s .. "" -end - -function Superscript(s) - return "" .. s .. "" -end - -function SmallCaps(s) - return '' .. s .. '' -end - -function Strikeout(s) - return '' .. s .. '' -end - -function Link(s, src, tit) - return "" .. s .. "" -end - -function Image(s, src, tit) - return "" -end - -function Code(s, attr) - return "" .. escape(s) .. "" -end - -function InlineMath(s) - return "\\(" .. escape(s) .. "\\)" -end - -function DisplayMath(s) - return "\\[" .. escape(s) .. "\\]" -end - -function Note(s) - local num = #notes + 1 - -- insert the back reference right before the final closing tag. - s = string.gsub(s, - '(.*)' .. s .. '') - -- return the footnote reference, linked to the note. - return '' .. num .. '' -end - -function Span(s, attr) - return "" .. s .. "" -end - -function Cite(s) - return "" .. s .. "" -end - -function Plain(s) - return s -end - -function Para(s) - return "

" .. s .. "

" -end - --- lev is an integer, the header level. -function Header(lev, s, attr) - return "" .. s .. "" -end - -function BlockQuote(s) - return "
\n" .. s .. "\n
" -end - -function HorizontalRule() - return "
" -end - -function CodeBlock(s, attr) - -- If code block has class 'dot', pipe the contents through dot - -- and base64, and include the base64-encoded png as a data: URL. - if attr.class and string.match(' ' .. attr.class .. ' ',' dot ') then - local png = pipe("base64", pipe("dot -Tpng", s)) - return '' - -- otherwise treat as code (one could pipe through a highlighter) - else - return "
" .. escape(s) ..
-           "
" - end -end - -function BulletList(items) - local buffer = {} - for _, item in pairs(items) do - table.insert(buffer, "
  • " .. item .. "
  • ") - end - return "" -end - -function OrderedList(items) - local buffer = {} - for _, item in pairs(items) do - table.insert(buffer, "
  • " .. item .. "
  • ") - end - return "
      \n" .. table.concat(buffer, "\n") .. "\n
    " -end - --- Revisit association list STackValue instance. -function DefinitionList(items) - local buffer = {} - for _,item in pairs(items) do - for k, v in pairs(item) do - table.insert(buffer,"
    " .. k .. "
    \n
    " .. - table.concat(v,"
    \n
    ") .. "
    ") - end - end - return "
    \n" .. table.concat(buffer, "\n") .. "\n
    " -end - --- Convert pandoc alignment to something HTML can use. --- align is AlignLeft, AlignRight, AlignCenter, or AlignDefault. -function html_align(align) - if align == 'AlignLeft' then - return 'left' - elseif align == 'AlignRight' then - return 'right' - elseif align == 'AlignCenter' then - return 'center' - else - return 'left' - end -end - --- Caption is a string, aligns is an array of strings, --- widths is an array of floats, headers is an array of --- strings, rows is an array of arrays of strings. -function Table(caption, aligns, widths, headers, rows) - local buffer = {} - local function add(s) - table.insert(buffer, s) - end - add("") - if caption ~= "" then - add("") - end - if widths and widths[1] ~= 0 then - for _, w in pairs(widths) do - add('') - end - end - local header_row = {} - local empty_header = true - for i, h in pairs(headers) do - local align = html_align(aligns[i]) - table.insert(header_row,'') - empty_header = empty_header and h == "" - end - if empty_header then - head = "" - else - add('') - for _,h in pairs(header_row) do - add(h) - end - add('') - end - local class = "even" - for _, row in pairs(rows) do - class = (class == "even" and "odd") or "even" - add('') - for i,c in pairs(row) do - add('') - end - add('') - end - add('\n" .. s .. "" -end - --- The following code will produce runtime warnings when you haven't defined --- all of the functions you need for the custom writer, so it's useful --- to include when you're working on a writer. -local meta = {} -meta.__index = - function(_, key) - io.stderr:write(string.format("WARNING: Undefined function '%s'\n",key)) - return function() return "" end - end -setmetatable(_G, meta) - -- cgit 1.4.1-21-gabe81
    " .. caption .. "
    ' .. h .. '
    ' .. c .. '