To_Title_Case.lua

--[[

NoteCase Pro script

   See http://www.notecasepro.com/

SCRIPT NAME: Change Case — To Title Case

   v. 1.0.2 


PURPOSE: The Change Case — To Title Case script converts English language selected text to Title Case, that is all words have their first character capitalized, excepting articles, conjunctions, and (particular) prepositions. 

This script presently produces title case in the English language only. For other languages, edit this script's "smallwords" table.

This script's output should not be trusted without review. The script does not respect the four exceptions specified for capitalization in the MLA style rules: 

* When one of these words starts a title;
* When one of these words ends a title;
* When one of these words comes after a colon, as in a subtitle; and 
* When a quotation is part of a title, follow the capitalization used in the quote.

Also, 

[i] the MLA list of words to be lower-cased in title case includes words used as both prepositions and nouns (only the latter should be capitalized in title case) and a complete list of English prepositions (all of which should be lower-cased in title case) is impossible to generate for that reason. See http://www.englishclub.com/download/PDF/EnglishClub-English-Prepositions-List.pdf.

[ii] the script does not correctly handle the case of punctuation within a word. Characters after such punctuation will be upper cased.  


RIGHTS: Derived in large part from code by Duncan Cross licensed under the MIT license. http://punchtheair.blogspot.com/, in turn derived from javascript code by David Gouch licensed under the MIT license, https://github.com/gouch/to-title-case. 

Copyright © 2015 Duncan Cross

Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the "Software"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions:

The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software.

THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

Adapted for use in NoteCase Pro by Paul E. Merrell, this script's author, who hereby waives all of his copyright and related or neighboring rights to this script, pursuant to the Creative Commons CC0 Universal relinquishment of rights found at http://creativecommons.org/publicdomain/zero/1.0/


CHANGE LOG:

v. 1.0.2

* Added check to see if language setting is English and if not, throw a choice message box on whether to proceed.

v. 1.0.1

* Fix: script did not work when string was all caps. Work-around is to convert string to all lower case before applying title case function.

* Fix: now aborts with error message if string includes either unordered list or A element markup.


TODO:

* find and fix bug that stops script from correctly processing strings that are all upper case. See work-around in second line of first function that converts the string to lower case before other processing   
--]]

-- loads functions

local function titlecase(title)
  local title = utf8ex.lower(title)
  return utf8ex.gsub(title, "()([%w&`'''\".@:/{%(%[<>_]+)(-? *)()", 

  --return utf8ex.gsub(title, "()([%w&`'''\"".@:/{%(%[<>_]+)(-? *)()",
   function(index, nonspace, space, endpos)
     local low = nonspace:lower();
     if (index > 1) and (title:sub(index-2,index-2) ~= ':')
           and (endpos < #title) and smallwords[low] then
       return low .. space;
     elseif title:sub(index-1, index+1):match("['\"_{%(%[]/)") then
       return nonspace:sub(1,1) .. nonspace:sub(2,2):upper()
          .. nonspace:sub(3) .. space;
     elseif nonspace:sub(2):match("[A-Z&]")
           or nonspace:sub(2):match("%w[%._]%w") then
       return nonspace .. space;
     end
     return nonspace:sub(1,1):upper() .. nonspace:sub(2) .. space;
   end);
end -- function titlecase


local function Test_String_For_Substrings(s)
  for i, v in ipairs(tQueries) do
    if utf8ex.find(s, v) == nil then
      return 0
    else
      return 1
    end -- if string.find
  end -- for i,
end -- function

local function Get_Selected_Note_Content(nDocID, strNoteID, nIsHtml)

  local nSelFrom, nSelTo = Nc_Note_SelectionRange_Get(nDocID, strNoteID)
  assert(nSelFrom ~= nSelTo, [[
ERROR: Text must be selected 
in the Note Pane when using 
this script. Aborting execution.]])

  -- get selected content in desired format
  local strContent = Nc_Note_Content_Get(nDocID, strNoteID, nIsHtml, nSelFrom, nSelTo)

  return strContent, nSelFrom, nSelTo

end -- function GetSelected

-- function replaces content in note
local function Replace_Selected_Note_Content(nDocID, strNoteID, strContent, nIsHtml, nSelFrom, nSelTo)

  -- makes sure nSelFrom is <= nSelTo
if nSelFrom > nSelTo then nSelFrom, nSelTo = nSelTo, nSelFrom end

  -- replace the selected content in the note 
  Nc_Note_Content_Set(nDocID, strNoteID, strContent, nIsHtml, nSelFrom, nSelTo)

  -- get the character count of the new string
  local nCount = Nc_String_CharacterCount_Get(strContent)

  -- calculate new cursor offset
  local nCursorPos = nSelFrom + nCount 

  -- remove selection highlighting and set the cursor position immediately after the inserted new string
  Nc_Note_SelectionRange_Set(nDocID, strNoteID, nCursorPos, nCursorPos)

  return

end -- function


-- begins script

-- throws choice message box if program's current language setting is not English
local strLanguage = Nc_Config_Language_Get()
if strLanguage ~= "en" then
  local strText = [[
CAUTION: This script is designed
for English text only. It will 
damage text in any other language.

Proceed?]]
  local nChoice = Nc_GUI_MessageBox(strText, 1, 0, "Caution")
  if nChoice == 	3 then
		  return 
		end
end

-- get IDs for current document/note
local nDocID = Nc_Doc_ID_GetCur()
local strNoteID = Nc_Note_ID_GetCur(nDocID)

-- gets selection
local strContent, nSelFrom, nSelTo = Get_Selected_Note_Content(nDocID, strNoteID, 1)
if strContent == "" then 
  Nc_GUI_InfoBox("ERROR: Text must be selected. Terminating script prematurely.", "ERROR", 1)
end  

-- array of substrings function will test for
tQueries = { 
"<A ", 
"</A>",
"<a ",
"</a>",
"<UL>",
"</UL>",
"<LI>",
"</LI>"}

-- tests string for A and list elements
local nMatch = Test_String_For_Substrings(strContent)
assert(nMatch ~= 1, "ERROR: Selection includes hyperlink or\r\nbullet list markup. This script cannot\r\nprocess text containing those types of markup.") 

-- table of lower case words
smallwords = {
		["a"]=1,
		["aboard"]=1,
		["about"]=1,
		["above"]=1,
		["according to"]=1,
		["across"]=1,
		["after"]=1,
		["against"]=1,
		["ahead of"]=1,
		["à la"]=1, 
		["along"]=1,
		["alongside"]=1,
		["along with"]=1,
		["amid"]=1,
		["amidst"]=1,
		["among"]=1,
		["amongst"]=1,
		["and"]=1, 
		["anti"]=1,
		["apart from"]=1,
		["around"]=1,
		["as"]=1, 
		["as for"]=1,
		["as per"]=1,
		["as to"]=1,
		["aside from"]=1,
		["astride"]=1,
		["as well as"]=1,
		["at"]=1,
		["atop"]=1,
		["away from"]=1,
		["because of"]=1,
		["barring"]=1,
		["before"]=1,
		["behind"]=1,
		["beneath"]=1,
		["below"]=1,
		["beside"]=1,
		["besides"]=1, 
		["between"]=1,
		["betwixt"]=1,
		["beyond"]=1,
		["but"]=1, 
		["but for"]=1,
		["by"]=1,
		["by means of"]=1, 
		["circa"]=1,
		["close to"]=1,
		["concerning"]=1,
		["considering"]=1,
		["contrary to"]=1,
		["counting"]=1,
		["cum"]=1,
		["depending on"]=1,
		["despite"]=1,
		["down"]=1,
		["due to"]=1,
		["during"]=1,
		["en"]=1, 
		["except"]=1,
		["except for"]=1,
		["excepting"]=1,
		["excluding"]=1,
		["following"]=1,
		["for"]=1, 
		["forward of"]=1,
		["from"]=1,
		["further to"]=1,
		["given"]=1,
		["if"]=1,
		["in"]=1, 
		["in addition to"]=1,
		["inbetween"]=1,
		["in case of"]=1,
		["in face of"]=1,
		["in favor of"]=1,
		["in favour of"]=1,
		["in front of"]=1,
		["including"]=1,
		["in lieu of"]=1,
		["in spite of"]=1,
		["instead of"]=1,
		["inside"]=1,
		["into"]=1,
		["in view of"]=1,
		["irrespective of"]=1,
		["like"]=1, 
		["minus"]=1,
		["near"]=1,
		["near to"]=1,
		["next to"]=1,
		["notwithstanding"]=1,
		["of"]=1,
		["off"]=1,
		["on"]=1,
		["on account of"]=1,
		["on behalf of"]=1,
		["on board"]=1,
		["onto"]=1,
		["on to"]=1,
		["on top of"]=1,
		["opposite"]=1,
		["opposite to"]=1,
		["other than"]=1,
		["out of"]=1,
		["out from"]=1,
		["outside"]=1,
		["outside of"]=1,
		["owing to"]=1,
		["over"]=1,
		["past"]=1,
		["pending"]=1,
		["per"]=1,
		["plus"]=1,
		["preparatory to"]=1,
		["prior to"]=1,
		["re"]=1,
		["regarding"]=1,		
		["regardless of"]=1,
		["respecting"]=1,
		["save for"]=1,
		["since"]=1,
		["than"]=1,
		["thanks to"]=1,
		["the"]=1,
		["through"]=1,
		["thru"]=1,
		["throughout"]=1,
		["til"]=1,
		["to"]=1,
		["together with"]=1,
		["touching"]=1,
		["toward"]=1,
		["towards"]=1, 
		["under"]=1,
		["unlike"]=1,
		["until"]=1,
		["up"]=1,		
		["up against"]=1,
		["upon"]=1,
		["up to"]=1,
		["up until"]=1,
		["versus"]=1,
		["vs."]=1, 
		["v."]=1, 
		["via"]=1,
		["vis-à-vis"]=1,
		["with"]=1,
		["within"]=1,
		["without"]=1,
		["with reference to"]=1,
		["with regard to"]=1,
		["worth"]=1
		}

-- converts string to title case
local strTitleCase = titlecase(strContent)

-- replaces string in note
Replace_Selected_Note_Content(nDocID, strNoteID, strTitleCase, 1, nSelFrom, nSelTo)