%% %% This is file `l3str-convert.sty', %% generated with the docstrip utility. %% %% The original source files were: %% %% l3str-convert.dtx (with options: `package') %% %% Copyright (C) 2011-2016 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. %% %% File: l3str-convert.dtx Copyright (C) 2013-2017 The LaTeX3 Project \RequirePackage{expl3} \GetIdInfo$Id: l3str-convert.dtx 6969 2017-02-20 18:32:23Z bruno $ {L3 Experimental string encoding conversions} \ProvidesExplPackage {\ExplFileName}{\ExplFileDate}{\ExplFileVersion}{\ExplFileDescription} \RequirePackage{l3tl-analysis,l3tl-build} \cs_if_exist:NF \use_ii_i:nn { \cs_new:Npn \use_ii_i:nn #1#2 { #2 #1 } } \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 } \int_const:Nn \c__str_ascii_min_int { 0 } \int_const:Nn \c__str_ascii_max_control_int { 31 } \int_const:Nn \c__str_ascii_max_int { 127 } \int_const:Nn \c__str_ascii_lower_int { `a - `A } \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 } \group_begin: \char_set_lccode:nn { `\* } { `\ } \char_set_lccode:nn { `\A } { `\A } \tex_lowercase:D { \group_end: \cs_new_protected:Npn \__str_gset_other:Nn #1#2 { \tl_gset:Nx #1 { \exp_after:wN \__str_gset_other_loop:w \tl_to_str:n {#2} ~ % A ~ A ~ A ~ A ~ A ~ A ~ A ~ A ~ A ~ \q_stop } } \cs_new:Npn \__str_gset_other_loop:w #1 ~ #2 ~ #3 ~ #4 ~ #5 ~ #6 ~ #7 ~ #8 ~ #9 ~ { \if_meaning:w A #9 \__str_gset_other_end:w \fi: #1 * #2 * #3 * #4 * #5 * #6 * #7 * #8 * #9 \__str_gset_other_loop:w * } \cs_new:Npn \__str_gset_other_end:w \fi: #1 * A #2 \q_stop { \fi: #1 } } \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:w \exp_after:wN ` \token_to_str:N #1 - `a \__int_eval_end: 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_value:w \__int_eval:w } \cs_new:Npn \__str_output_hexadecimal:n #1 { \__str_output_hexadecimal:w #1 \__str_output_end: } \cs_new:Npn \__str_output_hexadecimal:w { \exp_after:wN \exp_after:wN \exp_after:wN \use_none:n \cs:w c__str_byte_ \__int_value:w \__int_eval:w } \cs_new:Npn \__str_output_end: { \__int_eval_end: _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} { \__msg_kernel_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 \__str_gset_other:Nn \g__str_result_tl {#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} { \__msg_kernel_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 \__msg_kernel_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 + \c__str_ascii_lower_int } \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 } \group_begin: \char_set_catcode_other:n { 0 } \bool_lazy_any:nTF { \sys_if_engine_luatex_p: \sys_if_engine_xetex_p: } { \cs_new_protected:Npn \__str_convert_encode_: { \__tl_gbuild_x:Nw \g__str_result_tl \exp_after:wN \__str_encode_native_loop:w \g__str_result_tl \s__tl { \q_stop \__prg_break: } \s__tl \__prg_break_point: \__tl_build_end: } \cs_new_protected:Npn \__str_encode_native_loop:w #1 \s__tl #2 \s__tl { \use_none_delimit_by_q_stop:w #2 \q_stop \exp_args:Nx \__tl_build_one:n { \char_generate:nn {#2} {12} } \__str_encode_native_loop:w } } { \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 } { pdfTeX-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: \__str_output_byte:n {#1} \fi: } \__msg_kernel_new:nnnn { str } { pdfTeX-native-overflow } { Character~code~too~large~for~pdfTeX. } { The~pdfTeX~engine~only~supports~8-bit~characters:~ valid~character~codes~are~in~the~range~[0,255].~ To~manipulate~arbitrary~Unicode,~use~LuaTeX~or~XeTeX. } } \group_end: \cs_new_protected:Npn \__str_convert_decode_clist: { \clist_set: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: } \__msg_kernel_new:nnn { str } { unknown-esc } { Escaping~scheme~'#1'~(filtered:~'#2')~unknown. } \__msg_kernel_new:nnn { str } { unknown-enc } { Encoding~scheme~'#1'~(filtered:~'#2')~unknown. } \__msg_kernel_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. } \__msg_kernel_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: } { \__msg_kernel_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 \\ \ \ ~\{~~\}~\{~native~\}~\{~~\} } } } \__msg_kernel_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'. } \__msg_kernel_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. } %% %% %% End of file `l3str-convert.sty'.