%%
%% This is file `l3str-enc-utf8.def',
%% generated with the docstrip utility.
%%
%% The original source files were:
%%
%% l3str-convert.dtx  (with options: `utf8')
%% 
%% EXPERIMENTAL CODE
%% 
%% Do not distribute this file without also distributing the
%% source files specified above.
%% 
%% Do not distribute a modified version of this file.
%% 
%% File: l3str-convert.dtx Copyright (C) 2013-2016 The LaTeX3 Project
%%
%% It may be distributed and/or modified under the conditions of the
%% LaTeX Project Public License (LPPL), either version 1.3c of this
%% license or (at your option) any later version.  The latest version
%% of this license is in the file
%%
%%    http://www.latex-project.org/lppl.txt
%%
%% This file is part of the "l3experimental bundle" (The Work in LPPL)
%% and all files in that bundle must be distributed together.
%%
%% The released version of this bundle is available from CTAN.
%%
%% -----------------------------------------------------------------------
%%
%% The development version of the bundle can be found at
%%
%%    http://www.latex-project.org/svnroot/experimental/trunk/
%%
%% for those people who are interested.
%%
%%%%%%%%%%%
%% NOTE: %%
%%%%%%%%%%%
%%
%%   Snapshots taken from the repository represent work in progress and may
%%   not work or may contain conflicting material!  We therefore ask
%%   people _not_ to put them into distributions, archives, etc. without
%%   prior consultation with the LaTeX3 Project.
%%
%% -----------------------------------------------------------------------
\cs_new_protected:cpn { __str_convert_encode_utf8: }
  { \__str_convert_gmap_internal:N \__str_encode_utf_viii_char:n }
\cs_new:Npn \__str_encode_utf_viii_char:n #1
  {
    \__str_encode_utf_viii_loop:wwnnw #1 ; \c_minus_one + \c_zero * ;
      { 128 } { \c_zero }
      {  32 } {     192 }
      {  16 } {     224 }
      {   8 } {     240 }
    \q_stop
  }
\cs_new:Npn \__str_encode_utf_viii_loop:wwnnw #1; #2; #3#4 #5 \q_stop
  {
    \if_int_compare:w #1 < #3 \exp_stop_f:
      \__str_output_byte:n { #1 + #4 }
      \exp_after:wN \use_none_delimit_by_q_stop:w
    \fi:
    \exp_after:wN \__str_encode_utf_viii_loop:wwnnw
      \__int_value:w \int_div_truncate:nn {#1} {64} ; #1 ;
      #5 \q_stop
    \__str_output_byte:n { #2 - 64 * ( #1 - \c_two ) }
  }
\flag_clear_new:n { str_missing }
\flag_clear_new:n { str_extra }
\flag_clear_new:n { str_overlong }
\flag_clear_new:n { str_overflow }
\__msg_kernel_new:nnnn { str } { utf8-decode }
  {
    Invalid~UTF-8~string: \exp_last_unbraced:Nf \use_none:n
    \__str_if_flag_times:nT { str_missing }  { ,~missing~continuation~byte }
    \__str_if_flag_times:nT { str_extra }    { ,~extra~continuation~byte }
    \__str_if_flag_times:nT { str_overlong } { ,~overlong~form }
    \__str_if_flag_times:nT { str_overflow } { ,~code~point~too~large }
    .
  }
  {
    In~the~UTF-8~encoding,~each~Unicode~character~consists~in~
    1~to~4~bytes,~with~the~following~bit~pattern: \\
    \iow_indent:n
      {
        Code~point~\ \ \ \ <~128:~0xxxxxxx \\
        Code~point~\ \ \  <~2048:~110xxxxx~10xxxxxx \\
        Code~point~\ \   <~65536:~1110xxxx~10xxxxxx~10xxxxxx \\
        Code~point~    <~1114112:~11110xxx~10xxxxxx~10xxxxxx~10xxxxxx \\
      }
    Bytes~of~the~form~10xxxxxx~are~called~continuation~bytes.
    \flag_if_raised:nT { str_missing }
      {
        \\\\
        A~leading~byte~(in~the~range~[192,255])~was~not~followed~by~
        the~appropriate~number~of~continuation~bytes.
      }
    \flag_if_raised:nT { str_extra }
      {
        \\\\
        LaTeX~came~across~a~continuation~byte~when~it~was~not~expected.
      }
    \flag_if_raised:nT { str_overlong }
      {
        \\\\
        Every~Unicode~code~point~must~be~expressed~in~the~shortest~
        possible~form.~For~instance,~'0xC0'~'0x83'~is~not~a~valid~
        representation~for~the~code~point~3.
      }
    \flag_if_raised:nT { str_overflow }
      {
        \\\\
        Unicode~limits~code~points~to~the~range~[0,1114111].
      }
  }
\cs_new_protected:cpn { __str_convert_decode_utf8: }
  {
    \flag_clear:n { str_error }
    \flag_clear:n { str_missing }
    \flag_clear:n { str_extra }
    \flag_clear:n { str_overlong }
    \flag_clear:n { str_overflow }
    \tl_gset:Nx \g__str_result_tl
      {
        \exp_after:wN \__str_decode_utf_viii_start:N \g__str_result_tl
          { \__prg_break: \__str_decode_utf_viii_end: }
        \__prg_break_point:
      }
    \__str_if_flag_error:nnx { str_error } { utf8-decode } { }
  }
\cs_new:Npn \__str_decode_utf_viii_start:N #1
  {
    #1
    \if_int_compare:w `#1 < "C0 \exp_stop_f:
      \s__tl
      \if_int_compare:w `#1 < "80 \exp_stop_f:
        \__int_value:w `#1
      \else:
        \flag_raise:n { str_extra }
        \flag_raise:n { str_error }
        \int_use:N \c__str_replacement_char_int
      \fi:
    \else:
      \exp_after:wN \__str_decode_utf_viii_continuation:wwN
      \__int_value:w \__int_eval:w `#1 - "C0 \exp_after:wN \__int_eval_end:
    \fi:
    \s__tl
    \use_none_delimit_by_q_stop:w {"80} {"800} {"10000} {"110000} \q_stop
    \__str_decode_utf_viii_start:N
  }
\cs_new:Npn \__str_decode_utf_viii_continuation:wwN
    #1 \s__tl #2 \__str_decode_utf_viii_start:N #3
  {
    \use_none:n #3
    \if_int_compare:w `#3 <
          \if_int_compare:w `#3 < "80 \exp_stop_f: - \fi:
          "C0 \exp_stop_f:
      #3
      \exp_after:wN \__str_decode_utf_viii_aux:wNnnwN
      \__int_value:w \__int_eval:w
        #1 * "40 + `#3 - "80
      \exp_after:wN \__int_eval_end:
    \else:
      \s__tl
      \flag_raise:n { str_missing }
      \flag_raise:n { str_error }
      \int_use:N \c__str_replacement_char_int
    \fi:
    \s__tl
    #2
    \__str_decode_utf_viii_start:N #3
  }
\cs_new:Npn \__str_decode_utf_viii_aux:wNnnwN
    #1 \s__tl #2#3#4 #5 \__str_decode_utf_viii_start:N #6
  {
    \if_int_compare:w #1 < #4 \exp_stop_f:
      \s__tl
      \if_int_compare:w #1 < #3 \exp_stop_f:
        \flag_raise:n { str_overlong }
        \flag_raise:n { str_error }
        \int_use:N \c__str_replacement_char_int
      \else:
        #1
      \fi:
    \else:
      \if_meaning:w \q_stop #5
        \__str_decode_utf_viii_overflow:w #1
      \fi:
      \exp_after:wN \__str_decode_utf_viii_continuation:wwN
      \__int_value:w \__int_eval:w #1 - #4 \exp_after:wN \__int_eval_end:
    \fi:
    \s__tl
    #2 {#4} #5
    \__str_decode_utf_viii_start:N
  }
\cs_new:Npn \__str_decode_utf_viii_overflow:w #1 \fi: #2 \fi:
  {
    \fi: \fi:
    \flag_raise:n { str_overflow }
    \flag_raise:n { str_error }
    \int_use:N \c__str_replacement_char_int
  }
\cs_new:Npn \__str_decode_utf_viii_end:
  {
    \s__tl
    \flag_raise:n { str_missing }
    \flag_raise:n { str_error }
    \int_use:N \c__str_replacement_char_int \s__tl
    \__prg_break:
  }
%% 
%%
%% End of file `l3str-enc-utf8.def'.