-----------------------------------------------------------------------
-- Character set converter for SciTE Exporter
-- Version 1.0.1, 20070805
--
-- Copyright 2006-2007 by Kein-Hong Man <khman@users.sf.net>
-- All Rights Reserved
--
-- Permission to use, copy, modify, and distribute this software and
-- its documentation for any purpose and without fee is hereby granted,
-- provided that the above copyright notice appear in all copies and
-- that both that copyright notice and this permission notice appear
-- in supporting documentation.
--
-- KEIN-HONG MAN DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS SOFTWARE,
-- INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS, IN
-- NO EVENT SHALL KEIN-HONG MAN BE LIABLE FOR ANY SPECIAL, INDIRECT OR
-- CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS
-- OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT,
-- NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION
-- WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
--
-----------------------------------------------------------------------
-- USAGE
-- * First, initialize the charset converter, then the converter
--   function is used within the exporter.
-- * The default is a pass-through, equivalent to "iso-8859-1"
-- * Currently implemented charsets are:
--     iso-8859-1       alias: default
--     windows-1252     alias: cp1252
-- * Used by UTF-8 targets only: ABW, SXW, ODT
-----------------------------------------------------------------------

-----------------------------------------------------------------------
-- a simple check to alert of non-existence of exportutil library
-----------------------------------------------------------------------
if not exportutil then error("SciTE_ExportCharset: exportutil not defined") end

-----------------------------------------------------------------------
-- exportutil.CharsetFromSet
--
-- Sets the character set of the source.
-----------------------------------------------------------------------
function exportutil.CharsetFromSet(charset)
  local aliases = {
    ["default"] = "iso-8859-1",
    ["cp1252"] = "windows-1252",
  }
  ---------------------------------------------------------------
  local windows_1252 = {
    -- Data from apr-iconv.
    -- 0xFFFE encodings changed to a question mark instead.
    -- Source value: 0x80
    -- 0x20AC, 0xFFFE, 0x201A, 0x0192, 0x201E, 0x2026, 0x2020, 0x2021,
    -- 0x02C6, 0x2030, 0x0160, 0x2039, 0x0152, 0xFFFE, 0x017D, 0xFFFE,
    8364, 63, 8218, 402, 8222, 8230, 8224, 8225,
    710, 8240, 352, 8249, 338, 63, 381, 63,
    -- Source value: 0x90
    -- 0xFFFE, 0x2018, 0x2019, 0x201C, 0x201D, 0x2022, 0x2013, 0x2014,
    -- 0x02DC, 0x2122, 0x0161, 0x203A, 0x0153, 0xFFFE, 0x017E, 0x0178,
    63, 8216, 8217, 8220, 8221, 8226, 8211, 8212,
    732, 8482, 353, 8250, 339, 63, 382, 376,
  }
  local converters = {
    -------------------------------------------------------------
    ["iso-8859-1"] =
      function(c)
        return c
      end,
    -------------------------------------------------------------
    ["windows-1252"] =
      function(c)
        if c < 128 or c >= 160 then return c end
        return windows_1252[c - 127]
      end,
    -------------------------------------------------------------
  }
  -- check source charset, optionally lookup alias
  if not converters[charset] then
    charset = aliases[charset]
  end
  -- set converter function
  if converters[charset] then
    exportutil.CharsetToUTF8 = converters[charset]
  else
    error("exportutil.CharsetFromSet: unrecognized charset "..charset)
  end
end

-----------------------------------------------------------------------
-- exportutil.CharsetToUTF8
--
-- Converts an 8-bit character value to a UTF-8 value.
-----------------------------------------------------------------------
exportutil.CharsetFromSet("default")     -- initializes the function
-- function exportutil.CharsetToUTF8(c)
-- this is the default translator, a pass-through (or iso-8859-1)

-- end of script