diff options
Diffstat (limited to 'Master/texmf-dist/tex/latex/l3kernel/expl3-code.tex')
-rw-r--r-- | Master/texmf-dist/tex/latex/l3kernel/expl3-code.tex | 1422 |
1 files changed, 1370 insertions, 52 deletions
diff --git a/Master/texmf-dist/tex/latex/l3kernel/expl3-code.tex b/Master/texmf-dist/tex/latex/l3kernel/expl3-code.tex index dbdc37c17f5..d4f199159cc 100644 --- a/Master/texmf-dist/tex/latex/l3kernel/expl3-code.tex +++ b/Master/texmf-dist/tex/latex/l3kernel/expl3-code.tex @@ -40,6 +40,7 @@ %% l3fp-random.dtx (with options: `package') %% l3fparray.dtx (with options: `package') %% l3sort.dtx (with options: `package') +%% l3str-convert.dtx (with options: `package') %% l3tl-analysis.dtx (with options: `package') %% l3regex.dtx (with options: `package') %% l3box.dtx (with options: `package') @@ -64,7 +65,7 @@ %% and all files in that bundle must be distributed together. %% %% File: expl3.dtx -\def\ExplFileDate{2019-05-28}% +\def\ExplFileDate{2019-07-01}% \begingroup \def\next{\endgroup}% \expandafter\ifx\csname PackageError\endcsname\relax @@ -2189,6 +2190,7 @@ \cs_set:Npn \use_ii:nnnn #1#2#3#4 {#2} \cs_set:Npn \use_iii:nnnn #1#2#3#4 {#3} \cs_set:Npn \use_iv:nnnn #1#2#3#4 {#4} +\cs_set:Npn \use_ii_i:nn #1#2 { #2 #1 } \cs_set:Npn \use_none_delimit_by_q_nil:w #1 \q_nil { } \cs_set:Npn \use_none_delimit_by_q_stop:w #1 \q_stop { } \cs_set:Npn \use_none_delimit_by_q_recursion_stop:w #1 \q_recursion_stop { } @@ -9348,7 +9350,7 @@ } } %% File: l3msg.dtx -\tl_new:N \l__msg_tmp_tl +\tl_new:N \l__msg_internal_tl \str_new:N \l__msg_name_str \str_new:N \l__msg_text_str \tl_const:Nn \c__msg_text_prefix_tl { msg~text~>~ } @@ -9435,22 +9437,35 @@ \c_space_tl \msg_line_number: } -\cs_new_protected:Npn \__msg_interrupt:Nnnn #1#2#3#4 +\cs_new_protected:Npn \__msg_interrupt:NnnnN #1#2#3#4#5 { \str_set:Nx \l__msg_text_str { #1 {#2} } \str_set:Nx \l__msg_name_str { \msg_module_name:n {#2} } - \tl_if_empty:nTF {#4} + \cs_if_eq:cNTF + { \c__msg_more_text_prefix_tl #2 / #3 } + \__msg_no_more_text:nnnn { - \__msg_interrupt_wrap:nnn {#3} + \__msg_interrupt_wrap:nnn + { \use:c { \c__msg_text_prefix_tl #2 / #3 } #4 } { \c__msg_continue_text_tl } - { \c__msg_no_info_text_tl } + { + \c__msg_no_info_text_tl + \tl_if_empty:NF #5 + { \\ \\ #5 } + } } { - \__msg_interrupt_wrap:nnn {#3} + \__msg_interrupt_wrap:nnn + { \use:c { \c__msg_text_prefix_tl #2 / #3 } #4 } { \c__msg_help_text_tl } - {#4} + { + \use:c { \c__msg_more_text_prefix_tl #2 / #3 } #4 + \tl_if_empty:NF #5 + { \\ \\ #5 } + } } } +\cs_new:Npn \__msg_no_more_text:nnnn #1#2#3#4 { } \cs_new_protected:Npn \__msg_interrupt_wrap:nnn #1#2#3 { \iow_wrap:nnnN { \\ #3 } { } { } \__msg_interrupt_more_text:n @@ -9468,13 +9483,13 @@ { ~ } } { } \__msg_interrupt_text:n - \iow_wrap:nnnN { \l__msg_tmp_tl \\ \\ #2 } { } { } + \iow_wrap:nnnN { \l__msg_internal_tl \\ \\ #2 } { } { } \__msg_interrupt:n } \cs_new_protected:Npn \__msg_interrupt_text:n #1 { \group_end: - \tl_set:Nn \l__msg_tmp_tl {#1} + \tl_set:Nn \l__msg_internal_tl {#1} } \cs_new_protected:Npn \__msg_interrupt_more_text:n #1 { \exp_args:Nx \tex_errhelp:D { #1 \iow_newline: } } @@ -9600,41 +9615,32 @@ } \__msg_class_new:nn { fatal } { - \__msg_interrupt:Nnnn - \msg_fatal_text:n - {#1} - { \use:c { \c__msg_text_prefix_tl #1 / #2 } {#3} {#4} {#5} {#6} } - { \c__msg_fatal_text_tl } - \tex_end:D + \__msg_interrupt:NnnnN + \msg_fatal_text:n {#1} {#2} + { {#3} {#4} {#5} {#6} } + \c__msg_fatal_text_tl + \__msg_fatal_exit: + } + \cs_new_protected:Npn \__msg_fatal_exit: + { + \tex_batchmode:D + \tex_read:D -1 to \l__msg_internal_tl } \__msg_class_new:nn { critical } { - \__msg_interrupt:Nnnn - \msg_critical_text:n - {#1} - { \use:c { \c__msg_text_prefix_tl #1 / #2 } {#3} {#4} {#5} {#6} } - { \c__msg_critical_text_tl } + \__msg_interrupt:NnnnN + \msg_critical_text:n {#1} {#2} + { {#3} {#4} {#5} {#6} } + \c__msg_critical_text_tl \tex_endinput:D } \__msg_class_new:nn { error } { - \__msg_error:cnnnnn - { \c__msg_more_text_prefix_tl #1 / #2 } - {#3} {#4} {#5} {#6} - { - \__msg_interrupt:Nnnn - \msg_error_text:n - {#1} - { \use:c { \c__msg_text_prefix_tl #1 / #2 } {#3} {#4} {#5} {#6} } - } - } - \cs_new_protected:Npn \__msg_error:cnnnnn #1#2#3#4#5#6 - { - \cs_if_eq:cNTF {#1} \__msg_no_more_text:nnnn - { #6 { } } - { #6 { \use:c {#1} {#2} {#3} {#4} {#5} } } + \__msg_interrupt:NnnnN + \msg_error_text:n {#1} {#2} + { {#3} {#4} {#5} {#6} } + \c_empty_tl } - \cs_new:Npn \__msg_no_more_text:nnnn #1#2#3#4 { } \__msg_class_new:nn { warning } { \str_set:Nx \l__msg_text_str { \msg_warning_text:n {#1} } @@ -9710,13 +9716,13 @@ { \tl_if_empty:nF {#1} { \exp_args:No \iow_term:n { \use_none:n #1 } } - \tl_set:Nn \l__msg_tmp_tl {#2} + \tl_set:Nn \l__msg_internal_tl {#2} \__kernel_iow_with:Nnn \tex_newlinechar:D { 10 } { \__kernel_iow_with:Nnn \tex_errorcontextlines:D { -1 } { \tex_showtokens:D \exp_after:wN \exp_after:wN \exp_after:wN - { \exp_after:wN \l__msg_tmp_tl } + { \exp_after:wN \l__msg_internal_tl } } } } @@ -12154,7 +12160,8 @@ { \__keys_property_find:n {#1} \cs_if_exist:cTF { \c__keys_props_root_tl \l__keys_property_tl } - { \__keys_define_code:n {#2} } + { \__keys_define_code:n {#2} + } { \tl_if_empty:NF \l__keys_property_tl { @@ -12183,7 +12190,7 @@ { \tl_if_empty:NF \l__keys_module_tl { \l__keys_module_tl / } - #1 + \tl_trim_spaces:n {#1} } \tl_set:Nn \l__keys_property_tl { . #2 } } @@ -12992,7 +12999,28 @@ } } \cs_new:Npn \__keys_trim_spaces:n #1 - { \tl_trim_spaces:o { \tl_to_str:n {#1} } } + { + \exp_after:wN \__keys_trim_spaces_auxi:w \tl_to_str:n {#1} + / \q_nil \q_stop + + } +\cs_new:Npn \__keys_trim_spaces_auxi:w #1 / #2 \q_stop + { + \quark_if_nil:nTF {#2} + { \tl_trim_spaces:n {#1} } + { \__keys_trim_spaces_auxii:w #1 / #2 } + } +\cs_new:Npn \__keys_trim_spaces_auxii:w #1 / #2 / \q_nil + { + \tl_trim_spaces:n {#1} + \__keys_trim_spaces_auxiii:w #2 / \q_recursion_tail / \q_recursion_stop + } +\cs_set:Npn \__keys_trim_spaces_auxiii:w #1 / + { + \quark_if_recursion_tail_stop:n {#1} + \tl_trim_spaces:n { / #1 } + \__keys_trim_spaces_auxiii:w + } \prg_new_conditional:Npnn \keys_if_exist:nn #1#2 { p , T , F , TF } { \cs_if_exist:cTF @@ -20040,6 +20068,1296 @@ \iow_char:N\\sort_return_swapped: ~multiple~times.~ Exactly~one~of~these~should~be~called. } +%% File: l3str-convert.dtx +\cs_new_protected:Npn \__str_tmp:w { } +\tl_new:N \l__str_internal_tl +\int_new:N \l__str_internal_int +\tl_new:N \g__str_result_tl +\int_const:Nn \c__str_replacement_char_int { "FFFD } +\int_const:Nn \c__str_max_byte_int { 255 } +\prop_new:N \g__str_alias_prop +\prop_gput:Nnn \g__str_alias_prop { latin1 } { iso88591 } +\prop_gput:Nnn \g__str_alias_prop { latin2 } { iso88592 } +\prop_gput:Nnn \g__str_alias_prop { latin3 } { iso88593 } +\prop_gput:Nnn \g__str_alias_prop { latin4 } { iso88594 } +\prop_gput:Nnn \g__str_alias_prop { latin5 } { iso88599 } +\prop_gput:Nnn \g__str_alias_prop { latin6 } { iso885910 } +\prop_gput:Nnn \g__str_alias_prop { latin7 } { iso885913 } +\prop_gput:Nnn \g__str_alias_prop { latin8 } { iso885914 } +\prop_gput:Nnn \g__str_alias_prop { latin9 } { iso885915 } +\prop_gput:Nnn \g__str_alias_prop { latin10 } { iso885916 } +\prop_gput:Nnn \g__str_alias_prop { utf16le } { utf16 } +\prop_gput:Nnn \g__str_alias_prop { utf16be } { utf16 } +\prop_gput:Nnn \g__str_alias_prop { utf32le } { utf32 } +\prop_gput:Nnn \g__str_alias_prop { utf32be } { utf32 } +\prop_gput:Nnn \g__str_alias_prop { hexadecimal } { hex } +\bool_new:N \g__str_error_bool +\flag_new:n { str_byte } +\flag_new:n { str_error } +\prg_new_conditional:Npnn \__str_if_contains_char:NN #1#2 { T , TF } + { + \exp_after:wN \__str_if_contains_char_aux:NN \exp_after:wN #2 + #1 { \prg_break:n { ? \fi: } } + \prg_break_point: + \prg_return_false: + } +\prg_new_conditional:Npnn \__str_if_contains_char:nN #1#2 { TF } + { + \__str_if_contains_char_aux:NN #2 #1 { \prg_break:n { ? \fi: } } + \prg_break_point: + \prg_return_false: + } +\cs_new:Npn \__str_if_contains_char_aux:NN #1#2 + { + \if_charcode:w #1 #2 + \exp_after:wN \__str_if_contains_char_true: + \fi: + \__str_if_contains_char_aux:NN #1 + } +\cs_new:Npn \__str_if_contains_char_true: + { \prg_break:n { \prg_return_true: \use_none:n } } +\prg_new_conditional:Npnn \__str_octal_use:N #1 { TF } + { + \if_int_compare:w 1 < '1 \token_to_str:N #1 \exp_stop_f: + #1 \prg_return_true: + \else: + \prg_return_false: + \fi: + } +\prg_new_conditional:Npnn \__str_hexadecimal_use:N #1 { TF } + { + \if_int_compare:w 1 < "1 \token_to_str:N #1 \exp_stop_f: + #1 \prg_return_true: + \else: + \if_case:w \int_eval:n { \exp_after:wN ` \token_to_str:N #1 - `a } + A + \or: B + \or: C + \or: D + \or: E + \or: F + \else: + \prg_return_false: + \exp_after:wN \use_none:n + \fi: + \prg_return_true: + \fi: + } +\group_begin: + \tl_set:Nx \l__str_internal_tl { \tl_to_str:n { 0123456789ABCDEF } } + \tl_map_inline:Nn \l__str_internal_tl + { + \tl_map_inline:Nn \l__str_internal_tl + { + \tl_const:cx { c__str_byte_ \int_eval:n {"#1##1} _tl } + { \char_generate:nn { "#1##1 } { 12 } #1 ##1 } + } + } +\group_end: +\tl_const:cn { c__str_byte_-1_tl } { { } \use_none:n { } } +\cs_new:Npn \__str_output_byte:n #1 + { \__str_output_byte:w #1 \__str_output_end: } +\cs_new:Npn \__str_output_byte:w + { + \exp_after:wN \exp_after:wN + \exp_after:wN \use_i:nnn + \cs:w c__str_byte_ \int_eval:w + } +\cs_new:Npn \__str_output_hexadecimal:n #1 + { + \exp_after:wN \exp_after:wN + \exp_after:wN \use_none:n + \cs:w c__str_byte_ \int_eval:n {#1} _tl \cs_end: + } +\cs_new:Npn \__str_output_end: + { \scan_stop: _tl \cs_end: } +\cs_new:Npn \__str_output_byte_pair_be:n #1 + { + \exp_args:Nf \__str_output_byte_pair:nnN + { \int_div_truncate:nn { #1 } { "100 } } {#1} \use:nn + } +\cs_new:Npn \__str_output_byte_pair_le:n #1 + { + \exp_args:Nf \__str_output_byte_pair:nnN + { \int_div_truncate:nn { #1 } { "100 } } {#1} \use_ii_i:nn + } +\cs_new:Npn \__str_output_byte_pair:nnN #1#2#3 + { + #3 + { \__str_output_byte:n { #1 } } + { \__str_output_byte:n { #2 - #1 * "100 } } + } +\cs_new_protected:Npn \__str_convert_gmap:N #1 + { + \tl_gset:Nx \g__str_result_tl + { + \exp_after:wN \__str_convert_gmap_loop:NN + \exp_after:wN #1 + \g__str_result_tl { ? \prg_break: } + \prg_break_point: + } + } +\cs_new:Npn \__str_convert_gmap_loop:NN #1#2 + { + \use_none:n #2 + #1#2 + \__str_convert_gmap_loop:NN #1 + } +\cs_new_protected:Npn \__str_convert_gmap_internal:N #1 + { + \tl_gset:Nx \g__str_result_tl + { + \exp_after:wN \__str_convert_gmap_internal_loop:Nww + \exp_after:wN #1 + \g__str_result_tl \s__tl \q_stop \prg_break: \s__tl + \prg_break_point: + } + } +\cs_new:Npn \__str_convert_gmap_internal_loop:Nww #1 #2 \s__tl #3 \s__tl + { + \use_none_delimit_by_q_stop:w #3 \q_stop + #1 {#3} + \__str_convert_gmap_internal_loop:Nww #1 + } +\cs_new_protected:Npn \__str_if_flag_error:nnx #1 + { + \flag_if_raised:nTF {#1} + { \__kernel_msg_error:nnx { str } } + { \use_none:nn } + } +\cs_new_protected:Npn \__str_if_flag_no_error:nnx #1#2#3 + { \flag_if_raised:nT {#1} { \bool_gset_true:N \g__str_error_bool } } +\cs_new:Npn \__str_if_flag_times:nT #1#2 + { \flag_if_raised:nT {#1} { #2~(x \flag_height:n {#1} ) } } +\cs_new_protected:Npn \str_set_convert:Nnnn + { \__str_convert:nNNnnn { } \tl_set_eq:NN } +\cs_new_protected:Npn \str_gset_convert:Nnnn + { \__str_convert:nNNnnn { } \tl_gset_eq:NN } +\prg_new_protected_conditional:Npnn + \str_set_convert:Nnnn #1#2#3#4 { T , F , TF } + { + \bool_gset_false:N \g__str_error_bool + \__str_convert:nNNnnn + { \cs_set_eq:NN \__str_if_flag_error:nnx \__str_if_flag_no_error:nnx } + \tl_set_eq:NN #1 {#2} {#3} {#4} + \bool_if:NTF \g__str_error_bool \prg_return_false: \prg_return_true: + } +\prg_new_protected_conditional:Npnn + \str_gset_convert:Nnnn #1#2#3#4 { T , F , TF } + { + \bool_gset_false:N \g__str_error_bool + \__str_convert:nNNnnn + { \cs_set_eq:NN \__str_if_flag_error:nnx \__str_if_flag_no_error:nnx } + \tl_gset_eq:NN #1 {#2} {#3} {#4} + \bool_if:NTF \g__str_error_bool \prg_return_false: \prg_return_true: + } +\cs_new_protected:Npn \__str_convert:nNNnnn #1#2#3#4#5#6 + { + \group_begin: + #1 + \tl_gset:Nx \g__str_result_tl { \__kernel_str_to_other_fast:n {#4} } + \exp_after:wN \__str_convert:wwwnn + \tl_to_str:n {#5} /// \q_stop + { decode } { unescape } + \prg_do_nothing: + \__str_convert_decode_: + \exp_after:wN \__str_convert:wwwnn + \tl_to_str:n {#6} /// \q_stop + { encode } { escape } + \use_ii_i:nn + \__str_convert_encode_: + \group_end: + #2 #3 \g__str_result_tl + } +\cs_new_protected:Npn \__str_convert:wwwnn + #1 / #2 // #3 \q_stop #4#5 + { + \__str_convert:nnn {enc} {#4} {#1} + \__str_convert:nnn {esc} {#5} {#2} + \exp_args:Ncc \__str_convert:NNnNN + { __str_convert_#4_#1: } { __str_convert_#5_#2: } {#2} + } +\cs_new_protected:Npn \__str_convert:NNnNN #1#2#3#4#5 + { + \if_meaning:w #1 #5 + \tl_if_empty:nF {#3} + { \__kernel_msg_error:nnx { str } { native-escaping } {#3} } + #1 + \else: + #4 #2 #1 + \fi: + } +\cs_new_protected:Npn \__str_convert:nnn #1#2#3 + { + \cs_if_exist:cF { __str_convert_#2_#3: } + { + \exp_args:Nx \__str_convert:nnnn + { \__str_convert_lowercase_alphanum:n {#3} } + {#1} {#2} {#3} + } + } +\cs_new_protected:Npn \__str_convert:nnnn #1#2#3#4 + { + \cs_if_exist:cF { __str_convert_#3_#1: } + { + \prop_get:NnNF \g__str_alias_prop {#1} \l__str_internal_tl + { \tl_set:Nn \l__str_internal_tl {#1} } + \cs_if_exist:cF { __str_convert_#3_ \l__str_internal_tl : } + { + \file_if_exist:nTF { l3str-#2- \l__str_internal_tl .def } + { + \group_begin: + \__str_load_catcodes: + \file_input:n { l3str-#2- \l__str_internal_tl .def } + \group_end: + } + { + \tl_clear:N \l__str_internal_tl + \__kernel_msg_error:nnxx { str } { unknown-#2 } {#4} {#1} + } + } + \cs_if_exist:cF { __str_convert_#3_#1: } + { + \cs_gset_eq:cc { __str_convert_#3_#1: } + { __str_convert_#3_ \l__str_internal_tl : } + } + } + \cs_gset_eq:cc { __str_convert_#3_#4: } { __str_convert_#3_#1: } + } +\cs_new:Npn \__str_convert_lowercase_alphanum:n #1 + { + \exp_after:wN \__str_convert_lowercase_alphanum_loop:N + \tl_to_str:n {#1} { ? \prg_break: } + \prg_break_point: + } +\cs_new:Npn \__str_convert_lowercase_alphanum_loop:N #1 + { + \use_none:n #1 + \if_int_compare:w `#1 > `Z \exp_stop_f: + \if_int_compare:w `#1 > `z \exp_stop_f: \else: + \if_int_compare:w `#1 < `a \exp_stop_f: \else: + #1 + \fi: + \fi: + \else: + \if_int_compare:w `#1 < `A \exp_stop_f: + \if_int_compare:w 1 < 1#1 \exp_stop_f: + #1 + \fi: + \else: + \__str_output_byte:n { `#1 + `a - `A } + \fi: + \fi: + \__str_convert_lowercase_alphanum_loop:N + } +\cs_new_protected:Npn \__str_load_catcodes: + { + \char_set_catcode_escape:N \\ + \char_set_catcode_group_begin:N \{ + \char_set_catcode_group_end:N \} + \char_set_catcode_math_toggle:N \$ + \char_set_catcode_alignment:N \& + \char_set_catcode_parameter:N \# + \char_set_catcode_math_superscript:N \^ + \char_set_catcode_ignore:N \ % + \char_set_catcode_space:N \~ + \tl_map_function:nN { abcdefghijklmnopqrstuvwxyz_:ABCDEFILNPSTUX } + \char_set_catcode_letter:N + \tl_map_function:nN { 0123456789"'?*+-.(),`!/<>[];= } + \char_set_catcode_other:N + \char_set_catcode_comment:N \% + \int_set:Nn \tex_endlinechar:D {32} + } +\bool_lazy_any:nTF + { + \sys_if_engine_luatex_p: + \sys_if_engine_xetex_p: + } + { + \cs_new:Npn \__str_filter_bytes:n #1 + { + \__str_filter_bytes_aux:N #1 + { ? \prg_break: } + \prg_break_point: + } + \cs_new:Npn \__str_filter_bytes_aux:N #1 + { + \use_none:n #1 + \if_int_compare:w `#1 < 256 \exp_stop_f: + #1 + \else: + \flag_raise:n { str_byte } + \fi: + \__str_filter_bytes_aux:N + } + } + { \cs_new_eq:NN \__str_filter_bytes:n \use:n } +\bool_lazy_any:nTF + { + \sys_if_engine_luatex_p: + \sys_if_engine_xetex_p: + } + { + \cs_new_protected:Npn \__str_convert_unescape_: + { + \flag_clear:n { str_byte } + \tl_gset:Nx \g__str_result_tl + { \exp_args:No \__str_filter_bytes:n \g__str_result_tl } + \__str_if_flag_error:nnx { str_byte } { non-byte } { bytes } + } + } + { \cs_new_protected:Npn \__str_convert_unescape_: { } } +\cs_new_eq:NN \__str_convert_unescape_bytes: \__str_convert_unescape_: +\cs_new_protected:Npn \__str_convert_escape_: { } +\cs_new_eq:NN \__str_convert_escape_bytes: \__str_convert_escape_: +\cs_new_protected:Npn \__str_convert_decode_: + { \__str_convert_gmap:N \__str_decode_native_char:N } +\cs_new:Npn \__str_decode_native_char:N #1 + { #1 \s__tl \int_value:w `#1 \s__tl } +\bool_lazy_any:nTF + { + \sys_if_engine_luatex_p: + \sys_if_engine_xetex_p: + } + { + \cs_new_protected:Npn \__str_convert_encode_: + { \__str_convert_gmap_internal:N \__str_encode_native_char:n } + \cs_new:Npn \__str_encode_native_char:n #1 + { \char_generate:nn {#1} {12} } + } + { + \cs_new_protected:Npn \__str_convert_encode_: + { + \flag_clear:n { str_error } + \__str_convert_gmap_internal:N \__str_encode_native_char:n + \__str_if_flag_error:nnx { str_error } + { native-overflow } { } + } + \cs_new:Npn \__str_encode_native_char:n #1 + { + \if_int_compare:w #1 > \c__str_max_byte_int + \flag_raise:n { str_error } + ? + \else: + \char_generate:nn {#1} {12} + \fi: + } + \__kernel_msg_new:nnnn { str } { native-overflow } + { Character~code~too~large~for~this~engine. } + { + This~engine~only~support~8-bit~characters:~ + valid~character~codes~are~in~the~range~[0,255].~ + To~manipulate~arbitrary~Unicode,~use~LuaTeX~or~XeTeX. + } + } +\cs_new_protected:Npn \__str_convert_decode_clist: + { + \clist_gset:No \g__str_result_tl \g__str_result_tl + \tl_gset:Nx \g__str_result_tl + { + \exp_args:No \clist_map_function:nN + \g__str_result_tl \__str_decode_clist_char:n + } + } +\cs_new:Npn \__str_decode_clist_char:n #1 + { #1 \s__tl \int_eval:n {#1} \s__tl } +\cs_new_protected:Npn \__str_convert_encode_clist: + { + \__str_convert_gmap_internal:N \__str_encode_clist_char:n + \tl_gset:Nx \g__str_result_tl { \tl_tail:N \g__str_result_tl } + } +\cs_new:Npn \__str_encode_clist_char:n #1 { , #1 } +\cs_new_protected:Npn \str_declare_eight_bit_encoding:nnn #1#2#3 + { + \tl_set:Nn \l__str_internal_tl {#1} + \cs_new_protected:cpn { __str_convert_decode_#1: } + { \__str_convert_decode_eight_bit:n {#1} } + \cs_new_protected:cpn { __str_convert_encode_#1: } + { \__str_convert_encode_eight_bit:n {#1} } + \tl_const:cn { c__str_encoding_#1_tl } {#2} + \tl_const:cn { c__str_encoding_#1_missing_tl } {#3} + } +\cs_new_protected:Npn \__str_convert_decode_eight_bit:n #1 + { + \group_begin: + \int_zero:N \l__str_internal_int + \exp_last_unbraced:Nx \__str_decode_eight_bit_load:nn + { \tl_use:c { c__str_encoding_#1_tl } } + { \q_stop \prg_break: } { } + \prg_break_point: + \exp_last_unbraced:Nx \__str_decode_eight_bit_load_missing:n + { \tl_use:c { c__str_encoding_#1_missing_tl } } + { \q_stop \prg_break: } + \prg_break_point: + \flag_clear:n { str_error } + \__str_convert_gmap:N \__str_decode_eight_bit_char:N + \__str_if_flag_error:nnx { str_error } { decode-8-bit } {#1} + \group_end: + } +\cs_new_protected:Npn \__str_decode_eight_bit_load:nn #1#2 + { + \use_none_delimit_by_q_stop:w #1 \q_stop + \tex_dimen:D "#1 = \l__str_internal_int sp \scan_stop: + \tex_skip:D \l__str_internal_int = "#1 sp \scan_stop: + \tex_toks:D \l__str_internal_int \exp_after:wN { \int_value:w "#2 } + \int_incr:N \l__str_internal_int + \__str_decode_eight_bit_load:nn + } +\cs_new_protected:Npn \__str_decode_eight_bit_load_missing:n #1 + { + \use_none_delimit_by_q_stop:w #1 \q_stop + \tex_dimen:D "#1 = \l__str_internal_int sp \scan_stop: + \tex_skip:D \l__str_internal_int = "#1 sp \scan_stop: + \tex_toks:D \l__str_internal_int \exp_after:wN + { \int_use:N \c__str_replacement_char_int } + \int_incr:N \l__str_internal_int + \__str_decode_eight_bit_load_missing:n + } +\cs_new:Npn \__str_decode_eight_bit_char:N #1 + { + #1 \s__tl + \if_int_compare:w \tex_dimen:D `#1 < \l__str_internal_int + \if_int_compare:w \tex_skip:D \tex_dimen:D `#1 = `#1 \exp_stop_f: + \tex_the:D \tex_toks:D \tex_dimen:D + \fi: + \fi: + \int_value:w `#1 \s__tl + } +\cs_new_protected:Npn \__str_convert_encode_eight_bit:n #1 + { + \group_begin: + \int_zero:N \l__str_internal_int + \exp_last_unbraced:Nx \__str_encode_eight_bit_load:nn + { \tl_use:c { c__str_encoding_#1_tl } } + { \q_stop \prg_break: } { } + \prg_break_point: + \flag_clear:n { str_error } + \__str_convert_gmap_internal:N \__str_encode_eight_bit_char:n + \__str_if_flag_error:nnx { str_error } { encode-8-bit } {#1} + \group_end: + } +\cs_new_protected:Npn \__str_encode_eight_bit_load:nn #1#2 + { + \use_none_delimit_by_q_stop:w #1 \q_stop + \tex_dimen:D "#2 = \l__str_internal_int sp \scan_stop: + \tex_skip:D \l__str_internal_int = "#2 sp \scan_stop: + \exp_args:NNf \tex_toks:D \l__str_internal_int + { \__str_output_byte:n { "#1 } } + \int_incr:N \l__str_internal_int + \__str_encode_eight_bit_load:nn + } +\cs_new:Npn \__str_encode_eight_bit_char:n #1 + { + \if_int_compare:w #1 > \c_max_register_int + \flag_raise:n { str_error } + \else: + \if_int_compare:w \tex_dimen:D #1 < \l__str_internal_int + \if_int_compare:w \tex_skip:D \tex_dimen:D #1 = #1 \exp_stop_f: + \tex_the:D \tex_toks:D \tex_dimen:D #1 \exp_stop_f: + \exp_after:wN \exp_after:wN \exp_after:wN \use_none:nn + \fi: + \fi: + \__str_encode_eight_bit_char_aux:n {#1} + \fi: + } +\cs_new:Npn \__str_encode_eight_bit_char_aux:n #1 + { + \if_int_compare:w #1 > \c__str_max_byte_int + \flag_raise:n { str_error } + \else: + \__str_output_byte:n {#1} + \fi: + } +\__kernel_msg_new:nnn { str } { unknown-esc } + { Escaping~scheme~'#1'~(filtered:~'#2')~unknown. } +\__kernel_msg_new:nnn { str } { unknown-enc } + { Encoding~scheme~'#1'~(filtered:~'#2')~unknown. } +\__kernel_msg_new:nnnn { str } { native-escaping } + { The~'native'~encoding~scheme~does~not~support~any~escaping. } + { + Since~native~strings~do~not~consist~in~bytes,~ + none~of~the~escaping~methods~make~sense.~ + The~specified~escaping,~'#1',~will be ignored. + } +\__kernel_msg_new:nnn { str } { file-not-found } + { File~'l3str-#1.def'~not~found. } +\bool_lazy_any:nT + { + \sys_if_engine_luatex_p: + \sys_if_engine_xetex_p: + } + { + \__kernel_msg_new:nnnn { str } { non-byte } + { String~invalid~in~escaping~'#1':~it~may~only~contain~bytes. } + { + Some~characters~in~the~string~you~asked~to~convert~are~not~ + 8-bit~characters.~Perhaps~the~string~is~a~'native'~Unicode~string?~ + If~it~is,~try~using\\ + \\ + \iow_indent:n + { + \iow_char:N\\str_set_convert:Nnnn \\ + \ \ <str~var>~\{~<string>~\}~\{~native~\}~\{~<target~encoding>~\} + } + } + } +\__kernel_msg_new:nnnn { str } { decode-8-bit } + { Invalid~string~in~encoding~'#1'. } + { + LaTeX~came~across~a~byte~which~is~not~defined~to~represent~ + any~character~in~the~encoding~'#1'. + } +\__kernel_msg_new:nnnn { str } { encode-8-bit } + { Unicode~string~cannot~be~converted~to~encoding~'#1'. } + { + The~encoding~'#1'~only~contains~a~subset~of~all~Unicode~characters.~ + LaTeX~was~asked~to~convert~a~string~to~that~encoding,~but~that~ + string~contains~a~character~that~'#1'~does~not~support. + } +\cs_new_protected:Npn \__str_convert_unescape_hex: + { + \group_begin: + \flag_clear:n { str_error } + \int_set:Nn \tex_escapechar:D { 92 } + \tl_gset:Nx \g__str_result_tl + { + \__str_output_byte:w " + \exp_last_unbraced:Nf \__str_unescape_hex_auxi:N + { \tl_to_str:N \g__str_result_tl } + 0 { ? 0 - 1 \prg_break: } + \prg_break_point: + \__str_output_end: + } + \__str_if_flag_error:nnx { str_error } { unescape-hex } { } + \group_end: + } +\cs_new:Npn \__str_unescape_hex_auxi:N #1 + { + \use_none:n #1 + \__str_hexadecimal_use:NTF #1 + { \__str_unescape_hex_auxii:N } + { + \flag_raise:n { str_error } + \__str_unescape_hex_auxi:N + } + } +\cs_new:Npn \__str_unescape_hex_auxii:N #1 + { + \use_none:n #1 + \__str_hexadecimal_use:NTF #1 + { + \__str_output_end: + \__str_output_byte:w " \__str_unescape_hex_auxi:N + } + { + \flag_raise:n { str_error } + \__str_unescape_hex_auxii:N + } + } +\__kernel_msg_new:nnnn { str } { unescape-hex } + { String~invalid~in~escaping~'hex':~only~hexadecimal~digits~allowed. } + { + Some~characters~in~the~string~you~asked~to~convert~are~not~ + hexadecimal~digits~(0-9,~A-F,~a-f)~nor~spaces. + } +\cs_set_protected:Npn \__str_tmp:w #1#2#3 + { + \cs_new_protected:cpn { __str_convert_unescape_#2: } + { + \group_begin: + \flag_clear:n { str_byte } + \flag_clear:n { str_error } + \int_set:Nn \tex_escapechar:D { 92 } + \tl_gset:Nx \g__str_result_tl + { + \exp_after:wN #3 \g__str_result_tl + #1 ? { ? \prg_break: } + \prg_break_point: + } + \__str_if_flag_error:nnx { str_byte } { non-byte } { #2 } + \__str_if_flag_error:nnx { str_error } { unescape-#2 } { } + \group_end: + } + \cs_new:Npn #3 ##1#1##2##3 + { + \__str_filter_bytes:n {##1} + \use_none:n ##3 + \__str_output_byte:w " + \__str_hexadecimal_use:NTF ##2 + { + \__str_hexadecimal_use:NTF ##3 + { } + { + \flag_raise:n { str_error } + * 0 + `#1 \use_i:nn + } + } + { + \flag_raise:n { str_error } + 0 + `#1 \use_i:nn + } + \__str_output_end: + \use_i:nnn #3 ##2##3 + } + \__kernel_msg_new:nnnn { str } { unescape-#2 } + { String~invalid~in~escaping~'#2'. } + { + LaTeX~came~across~the~escape~character~'#1'~not~followed~by~ + two~hexadecimal~digits.~This~is~invalid~in~the~escaping~'#2'. + } + } +\exp_after:wN \__str_tmp:w \c_hash_str { name } + \__str_unescape_name_loop:wNN +\exp_after:wN \__str_tmp:w \c_percent_str { url } + \__str_unescape_url_loop:wNN +\group_begin: + \char_set_catcode_other:N \^^J + \char_set_catcode_other:N \^^M + \cs_set_protected:Npn \__str_tmp:w #1 + { + \cs_new_protected:Npn \__str_convert_unescape_string: + { + \group_begin: + \flag_clear:n { str_byte } + \flag_clear:n { str_error } + \int_set:Nn \tex_escapechar:D { 92 } + \tl_gset:Nx \g__str_result_tl + { + \exp_after:wN \__str_unescape_string_newlines:wN + \g__str_result_tl \prg_break: ^^M ? + \prg_break_point: + } + \tl_gset:Nx \g__str_result_tl + { + \exp_after:wN \__str_unescape_string_loop:wNNN + \g__str_result_tl #1 ?? { ? \prg_break: } + \prg_break_point: + } + \__str_if_flag_error:nnx { str_byte } { non-byte } { string } + \__str_if_flag_error:nnx { str_error } { unescape-string } { } + \group_end: + } + } + \exp_args:No \__str_tmp:w { \c_backslash_str } + \exp_last_unbraced:NNNNo + \cs_new:Npn \__str_unescape_string_loop:wNNN #1 \c_backslash_str #2#3#4 + { + \__str_filter_bytes:n {#1} + \use_none:n #4 + \__str_output_byte:w ' + \__str_octal_use:NTF #2 + { + \__str_octal_use:NTF #3 + { + \__str_octal_use:NTF #4 + { + \if_int_compare:w #2 > 3 \exp_stop_f: + - 256 + \fi: + \__str_unescape_string_repeat:NNNNNN + } + { \__str_unescape_string_repeat:NNNNNN ? } + } + { \__str_unescape_string_repeat:NNNNNN ?? } + } + { + \str_case_e:nnF {#2} + { + { \c_backslash_str } { 134 } + { ( } { 50 } + { ) } { 51 } + { r } { 15 } + { f } { 14 } + { n } { 12 } + { t } { 11 } + { b } { 10 } + { ^^J } { 0 - 1 } + } + { + \flag_raise:n { str_error } + 0 - 1 \use_i:nn + } + } + \__str_output_end: + \use_i:nn \__str_unescape_string_loop:wNNN #2#3#4 + } + \cs_new:Npn \__str_unescape_string_repeat:NNNNNN #1#2#3#4#5#6 + { \__str_output_end: \__str_unescape_string_loop:wNNN } + \cs_new:Npn \__str_unescape_string_newlines:wN #1 ^^M #2 + { + #1 + \if_charcode:w ^^J #2 \else: ^^J \fi: + \__str_unescape_string_newlines:wN #2 + } + \__kernel_msg_new:nnnn { str } { unescape-string } + { String~invalid~in~escaping~'string'. } + { + LaTeX~came~across~an~escape~character~'\c_backslash_str'~ + not~followed~by~any~of:~'n',~'r',~'t',~'b',~'f',~'(',~')',~ + '\c_backslash_str',~one~to~three~octal~digits,~or~the~end~ + of~a~line. + } +\group_end: +\cs_new_protected:Npn \__str_convert_escape_hex: + { \__str_convert_gmap:N \__str_escape_hex_char:N } +\cs_new:Npn \__str_escape_hex_char:N #1 + { \__str_output_hexadecimal:n { `#1 } } +\str_const:Nn \c__str_escape_name_not_str { ! " $ & ' } %$ +\str_const:Nn \c__str_escape_name_str { {}/<>[] } +\cs_new_protected:Npn \__str_convert_escape_name: + { \__str_convert_gmap:N \__str_escape_name_char:N } +\cs_new:Npn \__str_escape_name_char:N #1 + { + \__str_if_escape_name:NTF #1 {#1} + { \c_hash_str \__str_output_hexadecimal:n {`#1} } + } +\prg_new_conditional:Npnn \__str_if_escape_name:N #1 { TF } + { + \if_int_compare:w `#1 < "2A \exp_stop_f: + \__str_if_contains_char:NNTF \c__str_escape_name_not_str #1 + \prg_return_true: \prg_return_false: + \else: + \if_int_compare:w `#1 > "7E \exp_stop_f: + \prg_return_false: + \else: + \__str_if_contains_char:NNTF \c__str_escape_name_str #1 + \prg_return_false: \prg_return_true: + \fi: + \fi: + } +\str_const:Nx \c__str_escape_string_str + { \c_backslash_str ( ) } +\cs_new_protected:Npn \__str_convert_escape_string: + { \__str_convert_gmap:N \__str_escape_string_char:N } +\cs_new:Npn \__str_escape_string_char:N #1 + { + \__str_if_escape_string:NTF #1 + { + \__str_if_contains_char:NNT + \c__str_escape_string_str #1 + { \c_backslash_str } + #1 + } + { + \c_backslash_str + \int_div_truncate:nn {`#1} {64} + \int_mod:nn { \int_div_truncate:nn {`#1} { 8 } } { 8 } + \int_mod:nn {`#1} { 8 } + } + } +\prg_new_conditional:Npnn \__str_if_escape_string:N #1 { TF } + { + \if_int_compare:w `#1 < "21 \exp_stop_f: + \prg_return_false: + \else: + \if_int_compare:w `#1 > "7E \exp_stop_f: + \prg_return_false: + \else: + \prg_return_true: + \fi: + \fi: + } +\cs_new_protected:Npn \__str_convert_escape_url: + { \__str_convert_gmap:N \__str_escape_url_char:N } +\cs_new:Npn \__str_escape_url_char:N #1 + { + \__str_if_escape_url:NTF #1 {#1} + { \c_percent_str \__str_output_hexadecimal:n { `#1 } } + } +\prg_new_conditional:Npnn \__str_if_escape_url:N #1 { TF } + { + \if_int_compare:w `#1 < "41 \exp_stop_f: + \__str_if_contains_char:nNTF { "-.<> } #1 + \prg_return_true: \prg_return_false: + \else: + \if_int_compare:w `#1 > "7E \exp_stop_f: + \prg_return_false: + \else: + \__str_if_contains_char:nNTF { [ ] } #1 + \prg_return_false: \prg_return_true: + \fi: + \fi: + } +\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 ; - 1 + 0 * ; + { 128 } { 0 } + { 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 - 2 ) } + } +\flag_clear_new:n { str_missing } +\flag_clear_new:n { str_extra } +\flag_clear_new:n { str_overlong } +\flag_clear_new:n { str_overflow } +\__kernel_msg_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:n { `#1 - "C0 } \exp_after:wN + \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:n { #1 * "40 + `#3 - "80 } \exp_after:wN + \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:n { #1 - #4 } \exp_after:wN + \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: + } +\group_begin: + \char_set_catcode_other:N \^^fe + \char_set_catcode_other:N \^^ff + \cs_new_protected:cpn { __str_convert_encode_utf16: } + { + \__str_encode_utf_xvi_aux:N \__str_output_byte_pair_be:n + \tl_gput_left:Nx \g__str_result_tl { ^^fe ^^ff } + } + \cs_new_protected:cpn { __str_convert_encode_utf16be: } + { \__str_encode_utf_xvi_aux:N \__str_output_byte_pair_be:n } + \cs_new_protected:cpn { __str_convert_encode_utf16le: } + { \__str_encode_utf_xvi_aux:N \__str_output_byte_pair_le:n } + \cs_new_protected:Npn \__str_encode_utf_xvi_aux:N #1 + { + \flag_clear:n { str_error } + \cs_set_eq:NN \__str_tmp:w #1 + \__str_convert_gmap_internal:N \__str_encode_utf_xvi_char:n + \__str_if_flag_error:nnx { str_error } { utf16-encode } { } + } + \cs_new:Npn \__str_encode_utf_xvi_char:n #1 + { + \if_int_compare:w #1 < "D800 \exp_stop_f: + \__str_tmp:w {#1} + \else: + \if_int_compare:w #1 < "10000 \exp_stop_f: + \if_int_compare:w #1 < "E000 \exp_stop_f: + \flag_raise:n { str_error } + \__str_tmp:w { \c__str_replacement_char_int } + \else: + \__str_tmp:w {#1} + \fi: + \else: + \exp_args:Nf \__str_tmp:w { \int_div_truncate:nn {#1} {"400} + "D7C0 } + \exp_args:Nf \__str_tmp:w { \int_mod:nn {#1} {"400} + "DC00 } + \fi: + \fi: + } + \flag_clear_new:n { str_missing } + \flag_clear_new:n { str_extra } + \flag_clear_new:n { str_end } + \__kernel_msg_new:nnnn { str } { utf16-encode } + { Unicode~string~cannot~be~expressed~in~UTF-16:~surrogate. } + { + Surrogate~code~points~(in~the~range~[U+D800,~U+DFFF])~ + can~be~expressed~in~the~UTF-8~and~UTF-32~encodings,~ + but~not~in~the~UTF-16~encoding. + } + \__kernel_msg_new:nnnn { str } { utf16-decode } + { + Invalid~UTF-16~string: + \exp_last_unbraced:Nf \use_none:n + { + \__str_if_flag_times:nT { str_missing } { ,~missing~trail~surrogate } + \__str_if_flag_times:nT { str_extra } { ,~extra~trail~surrogate } + \__str_if_flag_times:nT { str_end } { ,~odd~number~of~bytes } + } + . + } + { + In~the~UTF-16~encoding,~each~Unicode~character~is~encoded~as~ + 2~or~4~bytes: \\ + \iow_indent:n + { + Code~point~in~[U+0000,~U+D7FF]:~two~bytes \\ + Code~point~in~[U+D800,~U+DFFF]:~illegal \\ + Code~point~in~[U+E000,~U+FFFF]:~two~bytes \\ + Code~point~in~[U+10000,~U+10FFFF]:~ + a~lead~surrogate~and~a~trail~surrogate \\ + } + Lead~surrogates~are~pairs~of~bytes~in~the~range~[0xD800,~0xDBFF],~ + and~trail~surrogates~are~in~the~range~[0xDC00,~0xDFFF]. + \flag_if_raised:nT { str_missing } + { + \\\\ + A~lead~surrogate~was~not~followed~by~a~trail~surrogate. + } + \flag_if_raised:nT { str_extra } + { + \\\\ + LaTeX~came~across~a~trail~surrogate~when~it~was~not~expected. + } + \flag_if_raised:nT { str_end } + { + \\\\ + The~string~contained~an~odd~number~of~bytes.~This~is~invalid:~ + the~basic~code~unit~for~UTF-16~is~16~bits~(2~bytes). + } + } + \cs_new_protected:cpn { __str_convert_decode_utf16be: } + { \__str_decode_utf_xvi:Nw 1 \g__str_result_tl \s_stop } + \cs_new_protected:cpn { __str_convert_decode_utf16le: } + { \__str_decode_utf_xvi:Nw 2 \g__str_result_tl \s_stop } + \cs_new_protected:cpn { __str_convert_decode_utf16: } + { + \exp_after:wN \__str_decode_utf_xvi_bom:NN + \g__str_result_tl \s_stop \s_stop \s_stop + } + \cs_new_protected:Npn \__str_decode_utf_xvi_bom:NN #1#2 + { + \str_if_eq:nnTF { #1#2 } { ^^ff ^^fe } + { \__str_decode_utf_xvi:Nw 2 } + { + \str_if_eq:nnTF { #1#2 } { ^^fe ^^ff } + { \__str_decode_utf_xvi:Nw 1 } + { \__str_decode_utf_xvi:Nw 1 #1#2 } + } + } + \cs_new_protected:Npn \__str_decode_utf_xvi:Nw #1#2 \s_stop + { + \flag_clear:n { str_error } + \flag_clear:n { str_missing } + \flag_clear:n { str_extra } + \flag_clear:n { str_end } + \cs_set:Npn \__str_tmp:w ##1 ##2 { ` ## #1 } + \tl_gset:Nx \g__str_result_tl + { + \exp_after:wN \__str_decode_utf_xvi_pair:NN + #2 \q_nil \q_nil + \prg_break_point: + } + \__str_if_flag_error:nnx { str_error } { utf16-decode } { } + } + \cs_new:Npn \__str_decode_utf_xvi_pair:NN #1#2 + { + \if_meaning:w \q_nil #2 + \__str_decode_utf_xvi_pair_end:Nw #1 + \fi: + \if_case:w + \int_eval:n { ( \__str_tmp:w #1#2 - "D6 ) / 4 } \scan_stop: + \or: \exp_after:wN \__str_decode_utf_xvi_quad:NNwNN + \or: \exp_after:wN \__str_decode_utf_xvi_extra:NNw + \fi: + #1#2 \s__tl + \int_eval:n { "100 * \__str_tmp:w #1#2 + \__str_tmp:w #2#1 } \s__tl + \__str_decode_utf_xvi_pair:NN + } + \cs_new:Npn \__str_decode_utf_xvi_quad:NNwNN + #1#2 #3 \__str_decode_utf_xvi_pair:NN #4#5 + { + \if_meaning:w \q_nil #5 + \__str_decode_utf_xvi_error:nNN { missing } #1#2 + \__str_decode_utf_xvi_pair_end:Nw #4 + \fi: + \if_int_compare:w + \if_int_compare:w \__str_tmp:w #4#5 < "DC \exp_stop_f: + 0 = 1 + \else: + \__str_tmp:w #4#5 < "E0 + \fi: + \exp_stop_f: + #1 #2 #4 #5 \s__tl + \int_eval:n + { + ( "100 * \__str_tmp:w #1#2 + \__str_tmp:w #2#1 - "D7F7 ) * "400 + + "100 * \__str_tmp:w #4#5 + \__str_tmp:w #5#4 + } + \s__tl + \exp_after:wN \use_i:nnn + \else: + \__str_decode_utf_xvi_error:nNN { missing } #1#2 + \fi: + \__str_decode_utf_xvi_pair:NN #4#5 + } + \cs_new:Npn \__str_decode_utf_xvi_pair_end:Nw #1 \fi: + { + \fi: + \if_meaning:w \q_nil #1 + \else: + \__str_decode_utf_xvi_error:nNN { end } #1 \prg_do_nothing: + \fi: + \prg_break: + } + \cs_new:Npn \__str_decode_utf_xvi_extra:NNw #1#2 \s__tl #3 \s__tl + { \__str_decode_utf_xvi_error:nNN { extra } #1#2 } + \cs_new:Npn \__str_decode_utf_xvi_error:nNN #1#2#3 + { + \flag_raise:n { str_error } + \flag_raise:n { str_#1 } + #2 #3 \s__tl + \int_use:N \c__str_replacement_char_int \s__tl + } +\group_end: +\group_begin: + \char_set_catcode_other:N \^^00 + \char_set_catcode_other:N \^^fe + \char_set_catcode_other:N \^^ff + \cs_new_protected:cpn { __str_convert_encode_utf32: } + { + \__str_convert_gmap_internal:N \__str_encode_utf_xxxii_be:n + \tl_gput_left:Nx \g__str_result_tl { ^^00 ^^00 ^^fe ^^ff } + } + \cs_new_protected:cpn { __str_convert_encode_utf32be: } + { \__str_convert_gmap_internal:N \__str_encode_utf_xxxii_be:n } + \cs_new_protected:cpn { __str_convert_encode_utf32le: } + { \__str_convert_gmap_internal:N \__str_encode_utf_xxxii_le:n } + \cs_new:Npn \__str_encode_utf_xxxii_be:n #1 + { + \exp_args:Nf \__str_encode_utf_xxxii_be_aux:nn + { \int_div_truncate:nn {#1} { "100 } } {#1} + } + \cs_new:Npn \__str_encode_utf_xxxii_be_aux:nn #1#2 + { + ^^00 + \__str_output_byte_pair_be:n {#1} + \__str_output_byte:n { #2 - #1 * "100 } + } + \cs_new:Npn \__str_encode_utf_xxxii_le:n #1 + { + \exp_args:Nf \__str_encode_utf_xxxii_le_aux:nn + { \int_div_truncate:nn {#1} { "100 } } {#1} + } + \cs_new:Npn \__str_encode_utf_xxxii_le_aux:nn #1#2 + { + \__str_output_byte:n { #2 - #1 * "100 } + \__str_output_byte_pair_le:n {#1} + ^^00 + } + \flag_clear_new:n { str_overflow } + \flag_clear_new:n { str_end } + \__kernel_msg_new:nnnn { str } { utf32-decode } + { + Invalid~UTF-32~string: + \exp_last_unbraced:Nf \use_none:n + { + \__str_if_flag_times:nT { str_overflow } { ,~code~point~too~large } + \__str_if_flag_times:nT { str_end } { ,~truncated~string } + } + . + } + { + In~the~UTF-32~encoding,~every~Unicode~character~ + (in~the~range~[U+0000,~U+10FFFF])~is~encoded~as~4~bytes. + \flag_if_raised:nT { str_overflow } + { + \\\\ + LaTeX~came~across~a~code~point~larger~than~1114111,~ + the~maximum~code~point~defined~by~Unicode.~ + Perhaps~the~string~was~not~encoded~in~the~UTF-32~encoding? + } + \flag_if_raised:nT { str_end } + { + \\\\ + The~length~of~the~string~is~not~a~multiple~of~4.~ + Perhaps~the~string~was~truncated? + } + } + \cs_new_protected:cpn { __str_convert_decode_utf32be: } + { \__str_decode_utf_xxxii:Nw 1 \g__str_result_tl \s_stop } + \cs_new_protected:cpn { __str_convert_decode_utf32le: } + { \__str_decode_utf_xxxii:Nw 2 \g__str_result_tl \s_stop } + \cs_new_protected:cpn { __str_convert_decode_utf32: } + { + \exp_after:wN \__str_decode_utf_xxxii_bom:NNNN \g__str_result_tl + \s_stop \s_stop \s_stop \s_stop \s_stop + } + \cs_new_protected:Npn \__str_decode_utf_xxxii_bom:NNNN #1#2#3#4 + { + \str_if_eq:nnTF { #1#2#3#4 } { ^^ff ^^fe ^^00 ^^00 } + { \__str_decode_utf_xxxii:Nw 2 } + { + \str_if_eq:nnTF { #1#2#3#4 } { ^^00 ^^00 ^^fe ^^ff } + { \__str_decode_utf_xxxii:Nw 1 } + { \__str_decode_utf_xxxii:Nw 1 #1#2#3#4 } + } + } + \cs_new_protected:Npn \__str_decode_utf_xxxii:Nw #1#2 \s_stop + { + \flag_clear:n { str_overflow } + \flag_clear:n { str_end } + \flag_clear:n { str_error } + \cs_set:Npn \__str_tmp:w ##1 ##2 { ` ## #1 } + \tl_gset:Nx \g__str_result_tl + { + \exp_after:wN \__str_decode_utf_xxxii_loop:NNNN + #2 \s_stop \s_stop \s_stop \s_stop + \prg_break_point: + } + \__str_if_flag_error:nnx { str_error } { utf32-decode } { } + } + \cs_new:Npn \__str_decode_utf_xxxii_loop:NNNN #1#2#3#4 + { + \if_meaning:w \s_stop #4 + \exp_after:wN \__str_decode_utf_xxxii_end:w + \fi: + #1#2#3#4 \s__tl + \if_int_compare:w \__str_tmp:w #1#4 > 0 \exp_stop_f: + \flag_raise:n { str_overflow } + \flag_raise:n { str_error } + \int_use:N \c__str_replacement_char_int + \else: + \if_int_compare:w \__str_tmp:w #2#3 > 16 \exp_stop_f: + \flag_raise:n { str_overflow } + \flag_raise:n { str_error } + \int_use:N \c__str_replacement_char_int + \else: + \int_eval:n + { \__str_tmp:w #2#3*"10000 + \__str_tmp:w #3#2*"100 + \__str_tmp:w #4#1 } + \fi: + \fi: + \s__tl + \__str_decode_utf_xxxii_loop:NNNN + } + \cs_new:Npn \__str_decode_utf_xxxii_end:w #1 \s_stop + { + \tl_if_empty:nF {#1} + { + \flag_raise:n { str_end } + \flag_raise:n { str_error } + #1 \s__tl + \int_use:N \c__str_replacement_char_int \s__tl + } + \prg_break: + } +\group_end: %% File: l3tl-analysis.dtx \scan_new:N \s__tl \cs_new_eq:NN \l__tl_analysis_token ? @@ -24147,7 +25465,7 @@ \tex_kern:D -\l__box_left_new_dim \hbox:n { - \driver_box_use_rotate:Nn + \__box_backend_rotate:Nn \l__box_internal_box \l__box_angle_fp } @@ -24416,7 +25734,7 @@ { \hbox_set:Nn \l__box_internal_box { - \driver_box_use_scale:Nnn + \__box_backend_scale:Nnn #1 \l__box_scale_x_fp \l__box_scale_y_fp @@ -24454,7 +25772,7 @@ \cs_new_eq:NN \color_group_end: \group_end: \cs_new_protected:Npn \color_ensure_current: { - \driver_color_pickup:N \l__color_current_tl + \__color_backend_pickup:N \l__color_current_tl \__color_select:V \l__color_current_tl } \cs_new_protected:Npn \__color_select:n #1 @@ -24463,13 +25781,13 @@ \cs_new_protected:Npn \__color_select:w #1 ~ #2 \q_stop { \use:c { __color_select_ #1 :w } #2 \q_stop } \cs_new_protected:Npn \__color_select_cmyk:w #1 ~ #2 ~ #3 ~ #4 \q_stop - { \driver_color_cmyk:nnnn {#1} {#2} {#3} {#4} } + { \__color_backend_cmyk:nnnn {#1} {#2} {#3} {#4} } \cs_new_protected:Npn \__color_select_gray:w #1 \q_stop - { \driver_color_gray:n {#1} } + { \__color_backend_gray:n {#1} } \cs_new_protected:Npn \__color_select_rgb:w #1 ~ #2 ~ #3 \q_stop - { \driver_color_rgb:nnn {#1} {#2} {#3} } + { \__color_backend_rgb:nnn {#1} {#2} {#3} } \cs_new_protected:Npn \__color_select_spot:w #1 ~ #2 \q_stop - { \driver_color_spot:nn {#1} {#2} } + { \__color_backend_spot:nn {#1} {#2} } \tl_new:N \l__color_current_tl \tl_set:Nn \l__color_current_tl { gray~0 } %% File: l3coffins.dtx @@ -25332,7 +26650,7 @@ \cs_generate_variant:Nn \coffin_attach:NnnNnnnn { c , Nnnc , cnnc } \cs_new_protected:Npn \coffin_gattach:NnnNnnnn #1#2#3#4#5#6#7#8 { - \__coffin_gattach:NnnNnnnnN #1 {#2} {#3} #4 {#5} {#6} {#7} {#8} + \__coffin_attach:NnnNnnnnN #1 {#2} {#3} #4 {#5} {#6} {#7} {#8} \coffin_gset_eq:NN } \cs_generate_variant:Nn \coffin_gattach:NnnNnnnn { c , Nnnc , cnnc } @@ -25897,10 +27215,10 @@ \fi: } \cs_new_protected:Npn \box_clip:N #1 - { \hbox_set:Nn #1 { \driver_box_use_clip:N #1 } } + { \hbox_set:Nn #1 { \__box_backend_clip:N #1 } } \cs_generate_variant:Nn \box_clip:N { c } \cs_new_protected:Npn \box_gclip:N #1 - { \hbox_gset:Nn #1 { \driver_box_use_clip:N #1 } } + { \hbox_gset:Nn #1 { \__box_backend_clip:N #1 } } \cs_generate_variant:Nn \box_gclip:N { c } \cs_new_protected:Npn \box_set_trim:Nnnnn #1#2#3#4#5 { \__box_set_trim:NnnnnN #1 {#2} {#3} {#4} {#5} \box_set_eq:NN } |