Skip to content

Commit

Permalink
format
Browse files Browse the repository at this point in the history
  • Loading branch information
@h20y6m
h20y6m committed Aug 15, 2022
1 parent 3d14629 commit 7da25e4
Show file tree
Hide file tree
Showing 2 changed files with 155 additions and 61 deletions.
5 changes: 5 additions & 0 deletions .gitignore
View file
Original file line number Diff line number Diff line change
Expand Up @@ -3,3 +3,8 @@ build/*
*.zip

*.pdf

*.aux
*.hd
*.log
*.out
211 changes: 150 additions & 61 deletions plexpl3.dtx
View file
Original file line number Diff line number Diff line change
Expand Up @@ -118,11 +118,15 @@
%
% \section{expl3の和文文字トークン対応}
%
% \subsection{大文字小文字変換関数の修正}
% \url{https://gist.github.com/zr-tex8r/248ff347172ce16d005897656687a901}
%
% \begin{macro}{\token_if_jachar:NTF}
% \meta{token} \marg{true code} \marg{false code}
%
% Tests if \meta{token} is a jachar token or not.
%
% \begin{macrocode}
%---------------------------------------
%% \token_if_jachar:N <token>
% Tests if <token> is a jachar token or not.
\bool_lazy_or:nnTF
{ \sys_if_engine_ptex_p: }
{ \sys_if_engine_uptex_p: }
Expand All @@ -132,8 +136,10 @@
\prg_new_conditional:Npnn \exp_not:N \token_if_jachar:N ##1
{ p , T , F , TF }
{
% A token is a jachar token if and only if
% its meaning string starts with "kanji ".
% \end{macrocode}
% A token is a jachar token if and only if
% its meaning string starts with ``\verb*|kanji |''.
% \begin{macrocode}
\exp_not:N \str_if_eq:eeTF
{
\exp_not:N \exp_after:wN
Expand All @@ -155,9 +161,12 @@
{ p , T , F , TF }
{ \prg_return_false: }
}

%---------------------------------------
%% Fix for the case-change funcrtions in l3text.
% \end{macrocode}
% \end{macro}
%
% Fix for the case-change funcrtions in \file{l3text}.
%
% \begin{macrocode}
\bool_lazy_or:nnT
{ \sys_if_engine_ptex_p: }
{ \sys_if_engine_uptex_p: }
Expand All @@ -169,8 +178,10 @@
{ \sys_if_engine_luatex_p: }
{ \sys_if_engine_xetex_p: }
{
% The current implementation for pdftex should be employed
% for all non-Unicode engines.
% \end{macrocode}
% The current implementation for pdftex should be employed
% for all non-Unicode engines.
% \begin{macrocode}
\cs_gset:Npn \__text_change_case_char_auxii:nnnN #1#2#3#4
{
\int_compare:nNnTF { `#4 } < { "F0 }
Expand All @@ -187,7 +198,9 @@
{
\int_compare:nNnTF { `#4 } > { "80 } % why not "7F?
{
% Check if the given character token is a jachar.
% \end{macrocode}
% Check if the given character token is a jachar.
% \begin{macrocode}
\token_if_jachar:NTF #4
{ \__text_change_case_char_jachar:nnnN }
{
Expand All @@ -200,15 +213,19 @@
{#1} {#2} {#3} #4
}
}

%---------------------------------------
%% Fix for the case-change funcrtions in l3str.
% \end{macrocode}
%
% Fix for the case-change funcrtions in \file{l3str}.
%
% \begin{macrocode}
\bool_lazy_or:nnF
{ \sys_if_engine_luatex_p: }
{ \sys_if_engine_xetex_p: }
{
% The current implementation for pdftex should be employed
% for all non-Unicode engines.
% \end{macrocode}
% The current implementation for pdftex should be employed
% for all non-Unicode engines.
% \begin{macrocode}
\cs_gset:Npn \__str_change_case_char_UTFviii:nNNN #1#2#3#4
{ \__str_change_case_char_UTFviii:nn {#1} {#2#3#4} }
\cs_gset:Npn \__str_change_case_char_UTFviii:nNNNN #1#2#3#4#5
Expand All @@ -224,7 +241,9 @@
{ \__str_change_case_end:wn }
\int_compare:nNnTF { `#2 } > { "80 }
{
% Check if the given character token is a jachar.
% \end{macrocode}
% Check if the given character token is a jachar.
% \begin{macrocode}
\token_if_jachar:NTF #2
{ \__str_change_case_char_jachar:nN }
{
Expand Down Expand Up @@ -252,11 +271,20 @@
}
% \end{macrocode}
%
% \subsection{文字コード変換関数の修正}
% \url{https://gist.github.com/h20y6m/6449d1d5d29a71620d19f29f881a0549}
%
% \begin{macro}{\__str_encode_if_extended_char_p:n}
% \begin{macro}{\__str_encode_extended_char:n}
% \begin{macrocode}
\cs_new:Npn \__str_encode_if_extended_char_p:n #1 { \c_false_bool }
\cs_new:Npn \__str_encode_extended_char:n #1 { }

% \end{macrocode}
% \end{macro}
% \end{macro}
%
% Patch for UTF-8 encoding function in \file{l3str-convert}.
% \begin{macrocode}
\cs_gset:Npn \__str_encode_utf_viii_char:n #1
{
\if_predicate:w \__str_encode_if_extended_char_p:n {#1}
Expand All @@ -270,10 +298,19 @@
\s__str_stop
\fi:
}

% \end{macrocode}
%
% \begin{macro}{\__str_decode_if_extended_char_p:N}
% \begin{macro}{\__str_decode_extended_char:N}
% \begin{macrocode}
\cs_new:Npn \__str_decode_if_extended_char_p:N #1 { \c_false_bool }
\cs_new:Npn \__str_decode_extended_char:N #1 { }

% \end{macrocode}
% \end{macro}
% \end{macro}
%
% Patch for UTF-8 decoding function in \file{l3str-convert}.
% \begin{macrocode}
\cs_gset:Npn \__str_decode_utf_viii_start:N #1
{
#1
Expand All @@ -300,10 +337,14 @@
\__str_use_none_delimit_by_s_stop:w {"80} {"800} {"10000} {"110000} \s__str_stop
\__str_decode_utf_viii_start:N
}

% \end{macrocode}
%
% \begin{macrocode}
\cs_new_protected:Npn \__ptex_tmp:w { }

% (upTeX only) declare kanji token which has specific kcatcode.
% \end{macrocode}
%
% (up\TeX{} only) declare kanji token which has specific kcatcode.
% \begin{macrocode}
\sys_if_engine_uptex:T
{
\group_begin:
Expand All @@ -320,8 +361,10 @@
\__ptex_tmp:w \c_kcatcode_hangul_token { 19 }
\group_end:
}

% (upTeX only) get kcatcode of token.
% \end{macrocode}
%
% (up\TeX{} only) get kcatcode of token.
% \begin{macrocode}
\sys_if_engine_uptex:T
{
\cs_new:Npn \__ptex_char_kcatcode:N #1
Expand All @@ -345,29 +388,38 @@
\fi:
}
}


% \end{macrocode}
%
% define ptex+utf8 encoding.

%
% ptex+utf8 encode function.
% \begin{macrocode}
\cs_new_protected:cpn { __str_convert_encode_ptex+utf8: }
{
\group_begin:
\cs_set_eq:NN \__str_encode_if_extended_char_p:n \__str_encode_if_kanji_char_p:n
\cs_set_eq:NN \__str_encode_extended_char:n \__str_encode_kanji_char:n
\cs_set_eq:NN \__str_encode_if_extended_char_p:n
\__str_encode_if_kanji_char_p:n
\cs_set_eq:NN \__str_encode_extended_char:n
\__str_encode_kanji_char:n
\use:c { __str_convert_encode_utf8: }
\group_end:
}

% Tests whether the Unicode code point #1 is Japanese character
% \end{macrocode}
%
% Tests whether the Unicode code point \#1 is Japanese character
% \begin{macrocode}
\int_compare:nNnTF { \tex_jis:D "2121 } = { "3000 }
{
% upTeX with unicode
% \end{macrocode}
% up\TeX{} with unicode
% \begin{macrocode}
\prg_new_conditional:Npnn \__str_encode_if_kanji_char:n #1 { p }
{
% NOTE:
% \kcatcode0--\kcatcode127 may not be 15,
% but ASCII (0--127) never be Japanese character.
% \end{macrocode}
% NOTE:
% \verb|\kcatcode0|--\verb|\kcatcode127| may not be 15,
% but ASCII ($0$--$127$) never be Japanese character.
% \begin{macrocode}
\if_int_compare:w #1 < "80 \exp_stop_f:
\prg_return_false:
\else:
Expand All @@ -380,70 +432,98 @@
}
}
{
% pTeX or upTeX with euc/sjis
% \end{macrocode}
% p\TeX{} or up\TeX{} with euc/sjis
% \begin{macrocode}
\prg_new_conditional:Npnn \__str_encode_if_kanji_char:n #1 { p }
{
% If specified Unicode code point cannot convert to internal Kanji code,
% \ucs returns -1.
% \end{macrocode}
% If specified Unicode code point cannot convert to internal Kanji code,
% \cs{ucs} returns $-1$.
% \begin{macrocode}
\if_int_compare:w \tex_ucs:D #1 < 0 \exp_stop_f:
\prg_return_false:
\else:
\if_int_compare:w \tex_kcatcode:D \tex_ucs:D #1 = 15 \exp_stop_f: % upTeX only. pTeX always false.
% \end{macrocode}
% up\TeX{} only. p\TeX{} always false.
% \begin{macrocode}
\if_int_compare:w
\tex_kcatcode:D \tex_ucs:D #1 = 15 \exp_stop_f:
\prg_return_false:
\else:
\prg_return_true:
\fi:
\fi:
}
}

% Generate Japanese character token which has Unicode code point #1.
% \end{macrocode}
%
% Generate Japanese character token which has Unicode code point \#1.
% \begin{macrocode}
\int_compare:nNnTF { \tex_jis:D "2121 } = { "3000 }
{
% upTeX with unicode
% \end{macrocode}
% up\TeX{} with unicode
% \begin{macrocode}
\cs_new:Npn \__str_encode_kanji_char:n #1
{
% \Uchar always generates Latin character token for character
% code 128--255, but Japanese character token are needed,
% so use \Ucharcat instead.
% \end{macrocode}
% \cs{Uchar} always generates Latin character token for character
% code $128$--$255$, but Japanese character token are needed,
% so use \cs{Ucharcat} instead.
% \begin{macrocode}
\if_int_compare:w \tex_kcatcode:D #1 > 15 \exp_stop_f:
\tex_Ucharcat:D #1 \exp_stop_f: \tex_kcatcode:D #1 \exp_stop_f:
\tex_Ucharcat:D
#1 \exp_stop_f: \tex_kcatcode:D #1 \exp_stop_f:
\else:
\tex_Ucharcat:D #1 \exp_stop_f: 18 \exp_stop_f:
\fi:
}
}
{
% pTeX or upTeX with euc/sjis
% \end{macrocode}
% p\TeX{} or up\TeX{} with euc/sjis
% \begin{macrocode}
\cs_new:Npn \__str_encode_kanji_char:n #1
{ \tex_Uchar:D \tex_ucs:D #1 \exp_stop_f: \exp_stop_f: }
}

% \end{macrocode}
%
% ptex+utf8 decode function.
% \begin{macrocode}
\cs_new_protected:cpn { __str_convert_decode_ptex+utf8: }
{
\group_begin:
\cs_set_eq:NN \__str_decode_if_extended_char_p:N \__str_decode_if_kanji_char_p:N
\cs_set_eq:NN \__str_decode_extended_char:N \__str_decode_kanji_char:N
\cs_set_eq:NN \__str_decode_if_extended_char_p:N
\__str_decode_if_kanji_char_p:N
\cs_set_eq:NN \__str_decode_extended_char:N
\__str_decode_kanji_char:N
\use:c { __str_convert_decode_utf8: }
\group_end:
}

% Tests whether the token #1 is Japanese character.
% \end{macrocode}
%
% Tests whether the token \#1 is Japanese character.
% \begin{macrocode}
\int_compare:nNnTF { \tex_jis:D "2121 } = { "3000 }
{
% upTeX with unicode
% \end{macrocode}
% up\TeX{} with unicode
% \begin{macrocode}
\prg_new_conditional:Npnn \__str_decode_if_kanji_char:N #1 { p }
{
\if_int_compare:w \__ptex_char_kcatcode:N #1 > 15 \exp_stop_f:
\if_int_compare:w
\__ptex_char_kcatcode:N #1 > 15 \exp_stop_f:
\prg_return_true:
\else:
\prg_return_false:
\fi:
}
}
{
% pTeX or upTeX with euc/sjis
% \end{macrocode}
% p\TeX{} or up\TeX{} with euc/sjis
% \begin{macrocode}
\prg_new_conditional:Npnn \__str_decode_if_kanji_char:N #1 { p }
{
\if_int_compare:w `#1 < "100 \exp_stop_f:
Expand All @@ -453,23 +533,32 @@
\fi:
}
}

% Convert Japanese character #1 to Unicode code point.
% \end{macrocode}
% Convert Japanese character \#1 to Unicode code point.
% \begin{macrocode}
\int_compare:nNnTF { \tex_jis:D "2121 } = { "3000 }
{
% upTeX with unicode
% \end{macrocode}
% up\TeX{} with unicode
% \begin{macrocode}
\cs_new:Npn \__str_decode_kanji_char:N #1
{ \int_value:w `#1 }
}
{
% pTeX or upTeX with euc/sjis
% \end{macrocode}
% p\TeX{} or up\TeX{} with euc/sjis
% \begin{macrocode}
\cs_new:Npn \__str_decode_kanji_char:N #1
{ \tex_toucs:D `#1 }
}

% \end{macrocode}
%
% alternative encoding name
% \begin{macrocode}
\prop_gput:Nnn \g__str_alias_prop { ptex } { ptex+utf8 }
% \end{macrocode}
% set default encoding to ptex+utf8
% \begin{macrocode}
\prop_gput:Nnn \g__str_alias_prop { default } { ptex+utf8 }
% \end{macrocode}
%
Expand Down

0 comments on commit 7da25e4

Please sign in to comment.