%PDF-
%PDF-
Mini Shell
Mini Shell
%%
%% This is file `l3regex.sty',
%% generated with the docstrip utility.
%%
%% The original source files were:
%%
%% l3regex.dtx (with options: `package')
%%
%% 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: l3regex.dtx Copyright (C) 2011-2013 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.
%%
%% -----------------------------------------------------------------------
\RequirePackage{expl3}
\GetIdInfo$Id: l3regex.dtx 4455 2013-01-22 20:38:19Z bruno $
{L3 Experimental regular expressions}
\ProvidesExplPackage
{\ExplFileName}{\ExplFileDate}{\ExplFileVersion}{\ExplFileDescription}
\RequirePackage{l3tl-build, l3tl-analysis, l3flag, l3str, l3str-convert}
\cs_generate_variant:Nn \tl_to_str:n { V }
\cs_new:Npn \__regex_tmp:w { }
\tl_new:N \l__regex_internal_a_tl
\tl_new:N \l__regex_internal_b_tl
\int_new:N \l__regex_internal_a_int
\int_new:N \l__regex_internal_b_int
\int_new:N \l__regex_internal_c_int
\bool_new:N \l__regex_internal_bool
\seq_new:N \l__regex_internal_seq
\tl_new:N \g__regex_internal_tl
\tl_const:Nn \c__regex_no_match_regex
{
\__regex_branch:n
{ \__regex_class:NnnnN \c_true_bool { } { 1 } { 0 } \c_true_bool }
}
\int_new:N \l__regex_balance_int
\cs_new_protected:Npn \__regex_break_true:w
#1 \__regex_break_point:TF #2 #3 {#2}
\cs_new_protected:Npn \__regex_break_point:TF #1 #2 { #2 }
\cs_new_protected:Npn \__regex_item_reverse:n #1
{
#1
\__regex_break_point:TF { } \__regex_break_true:w
}
\cs_new_protected:Npn \__regex_item_caseful_equal:n #1
{
\if_int_compare:w #1 = \l__regex_current_char_int
\exp_after:wN \__regex_break_true:w
\fi:
}
\cs_new_protected:Npn \__regex_item_caseful_range:nn #1 #2
{
\reverse_if:N \if_int_compare:w #1 > \l__regex_current_char_int
\reverse_if:N \if_int_compare:w #2 < \l__regex_current_char_int
\exp_after:wN \exp_after:wN \exp_after:wN \__regex_break_true:w
\fi:
\fi:
}
\cs_new_protected:Npn \__regex_item_caseless_equal:n #1
{
\if_int_compare:w #1 = \l__regex_current_char_int
\exp_after:wN \__regex_break_true:w
\fi:
\if_int_compare:w \l__regex_case_changed_char_int = \c_max_int
\__regex_compute_case_changed_char:
\fi:
\if_int_compare:w #1 = \l__regex_case_changed_char_int
\exp_after:wN \__regex_break_true:w
\fi:
}
\cs_new_protected:Npn \__regex_item_caseless_range:nn #1 #2
{
\reverse_if:N \if_int_compare:w #1 > \l__regex_current_char_int
\reverse_if:N \if_int_compare:w #2 < \l__regex_current_char_int
\exp_after:wN \exp_after:wN \exp_after:wN \__regex_break_true:w
\fi:
\fi:
\if_int_compare:w \l__regex_case_changed_char_int = \c_max_int
\__regex_compute_case_changed_char:
\fi:
\reverse_if:N \if_int_compare:w #1 > \l__regex_case_changed_char_int
\reverse_if:N \if_int_compare:w #2 < \l__regex_case_changed_char_int
\exp_after:wN \exp_after:wN \exp_after:wN \__regex_break_true:w
\fi:
\fi:
}
\cs_new_protected_nopar:Npn \__regex_compute_case_changed_char:
{
\int_set_eq:NN \l__regex_case_changed_char_int \l__regex_current_char_int
\if_int_compare:w \l__regex_current_char_int < \c_ninety_one
\if_int_compare:w \l__regex_current_char_int < \c_sixty_five
\else:
\int_add:Nn \l__regex_case_changed_char_int { \c_thirty_two }
\fi:
\else:
\if_int_compare:w \l__regex_current_char_int < \c_one_hundred_twenty_three
\if_int_compare:w \l__regex_current_char_int < \c_ninety_seven
\else:
\int_sub:Nn \l__regex_case_changed_char_int { \c_thirty_two }
\fi:
\fi:
\fi:
}
\cs_new_eq:NN \__regex_item_equal:n ?
\cs_new_eq:NN \__regex_item_range:nn ?
\cs_new_protected:Npn \__regex_item_catcode:
{
"
\if_case:w \l__regex_current_catcode_int
1 \or: 4 \or: 10 \or: 40
\or: 100 \or: \or: 1000 \or: 4000
\or: 10000 \or: \or: 100000 \or: 400000
\or: 1000000 \or: 4000000 \else: 1*\c_zero
\fi:
}
\cs_new_protected:Npn \__regex_item_catcode:nT #1
{
\if_int_odd:w \__int_eval:w #1 / \__regex_item_catcode: \__int_eval_end:
\exp_after:wN \use:n
\else:
\exp_after:wN \use_none:n
\fi:
}
\cs_new_protected:Npn \__regex_item_catcode_reverse:nT #1#2
{ \__regex_item_catcode:nT {#1} { \__regex_item_reverse:n {#2} } }
\cs_new_protected:Npn \__regex_item_exact:nn #1#2
{
\if_int_compare:w #1 = \l__regex_current_catcode_int
\if_int_compare:w #2 = \l__regex_current_char_int
\exp_after:wN \exp_after:wN \exp_after:wN \__regex_break_true:w
\fi:
\fi:
}
\cs_new_protected:Npn \__regex_item_exact_cs:c #1
{
\int_compare:nNnTF \l__regex_current_catcode_int = \c_zero
{
\str_if_eq_x:nnTF
{
\exp_after:wN \exp_after:wN \exp_after:wN \cs_to_str:N
\tex_the:D \tex_toks:D \l__regex_current_pos_int
}
{ #1 }
{ \__regex_break_true:w } { }
}
{ }
}
\cs_new_protected:Npn \__regex_item_cs:n #1
{
\int_compare:nNnT \l__regex_current_catcode_int = \c_zero
{
\group_begin:
\__regex_single_match:
\__regex_disable_submatches:
\__regex_build_for_cs:n {#1}
\bool_set_eq:NN \l__regex_saved_success_bool \g__regex_success_bool
\exp_args:Nx \__regex_match:n
{
\exp_after:wN \exp_after:wN
\exp_after:wN \cs_to_str:N
\tex_the:D \tex_toks:D \l__regex_current_pos_int
}
\if_meaning:w \c_true_bool \g__regex_success_bool
\group_insert_after:N \__regex_break_true:w
\fi:
\bool_gset_eq:NN \g__regex_success_bool \l__regex_saved_success_bool
\group_end:
}
}
\cs_new_protected_nopar:Npn \__regex_prop_d:
{ \__regex_item_caseful_range:nn \c_forty_eight { 57 } } % 0--9
\cs_new_protected_nopar:Npn \__regex_prop_h:
{
\__regex_item_caseful_equal:n \c_thirty_two % space
\__regex_item_caseful_equal:n \c_nine % tab
}
\cs_new_protected_nopar:Npn \__regex_prop_s:
{
\__regex_item_caseful_equal:n \c_thirty_two % space
\__regex_item_caseful_equal:n \c_nine % tab
\__regex_item_caseful_equal:n \c_ten % lf
\__regex_item_caseful_equal:n \c_twelve % ff
\__regex_item_caseful_equal:n \c_thirteen % cr
}
\cs_new_protected_nopar:Npn \__regex_prop_v:
{ \__regex_item_caseful_range:nn \c_ten \c_thirteen } % lf, vtab, ff, cr
\cs_new_protected_nopar:Npn \__regex_prop_w:
{
\__regex_item_caseful_range:nn \c_ninety_seven { 122 } % a--z
\__regex_item_caseful_range:nn \c_sixty_five { 90 } % A--Z
\__regex_item_caseful_range:nn \c_forty_eight { 57 } % 0--9
\__regex_item_caseful_equal:n { 95 } % _
}
\cs_new_protected_nopar:Npn \__regex_prop_N:
{ \__regex_item_reverse:n { \__regex_item_caseful_equal:n \c_ten } }
\cs_new_protected_nopar:Npn \__regex_posix_alnum:
{ \__regex_posix_alpha: \__regex_posix_digit: }
\cs_new_protected_nopar:Npn \__regex_posix_alpha:
{ \__regex_posix_lower: \__regex_posix_upper: }
\cs_new_protected_nopar:Npn \__regex_posix_ascii:
{ \__regex_item_caseful_range:nn \c_zero \c_one_hundred_twenty_seven }
\cs_new_eq:NN \__regex_posix_blank: \__regex_prop_h:
\cs_new_protected_nopar:Npn \__regex_posix_cntrl:
{
\__regex_item_caseful_range:nn \c_zero { 31 }
\__regex_item_caseful_equal:n \c_one_hundred_twenty_seven
}
\cs_new_eq:NN \__regex_posix_digit: \__regex_prop_d:
\cs_new_protected_nopar:Npn \__regex_posix_graph:
{ \__regex_item_caseful_range:nn { 33 } { 126 } }
\cs_new_protected_nopar:Npn \__regex_posix_lower:
{ \__regex_item_caseful_range:nn \c_ninety_seven { 122 } }
\cs_new_protected_nopar:Npn \__regex_posix_print:
{ \__regex_item_caseful_range:nn \c_thirty_two { 126 } }
\cs_new_protected_nopar:Npn \__regex_posix_punct:
{
\__regex_item_caseful_range:nn { 33 } { 47 }
\__regex_item_caseful_range:nn { 58 } { 64 }
\__regex_item_caseful_range:nn { 91 } { 96 }
\__regex_item_caseful_range:nn { 123 } { 126 }
}
\cs_new_protected_nopar:Npn \__regex_posix_space:
{
\__regex_item_caseful_equal:n \c_thirty_two
\__regex_item_caseful_range:nn \c_nine \c_thirteen
}
\cs_new_protected_nopar:Npn \__regex_posix_upper:
{ \__regex_item_caseful_range:nn \c_sixty_five { 90 } }
\cs_new_eq:NN \__regex_posix_word: \__regex_prop_w:
\cs_new_protected_nopar:Npn \__regex_posix_xdigit:
{
\__regex_posix_digit:
\__regex_item_caseful_range:nn \c_sixty_five { 70 }
\__regex_item_caseful_range:nn \c_ninety_seven { 102 }
}
\cs_new_protected:Npn \__regex_escape_use:nnnn #1#2#3#4
{
\__tl_build:Nw \l__regex_internal_a_tl
\cs_set_nopar:Npn \__regex_escape_unescaped:N ##1 { #1 }
\cs_set_nopar:Npn \__regex_escape_escaped:N ##1 { #2 }
\cs_set_nopar:Npn \__regex_escape_raw:N ##1 { #3 }
\int_set:Nn \tex_escapechar:D { 92 }
\__str_gset_other:Nn \g__regex_internal_tl { #4 }
\tl_set:Nx \l__regex_internal_b_tl
{
\exp_after:wN \__regex_escape_loop:N \g__regex_internal_tl
{ break } \__prg_break_point:
}
\__tl_build_one:o \l__regex_internal_b_tl
\__tl_build_end:
\l__regex_internal_a_tl
}
\cs_new:Npn \__regex_escape_loop:N #1
{
\cs_if_exist_use:cF { __regex_escape_\token_to_str:N #1:w }
{ \__regex_escape_unescaped:N #1 }
\__regex_escape_loop:N
}
\cs_new_nopar:cpn { __regex_escape_ \c_backslash_str :w }
\__regex_escape_loop:N #1
{
\cs_if_exist_use:cF { __regex_escape_/\token_to_str:N #1:w }
{ \__regex_escape_escaped:N #1 }
\__regex_escape_loop:N
}
\cs_new_eq:NN \__regex_escape_unescaped:N ?
\cs_new_eq:NN \__regex_escape_escaped:N ?
\cs_new_eq:NN \__regex_escape_raw:N ?
\cs_new_eq:NN \__regex_escape_break:w \__prg_break:
\cs_new_nopar:cpn { __regex_escape_/break:w }
{
\if_false: { \fi: }
\__msg_kernel_error:nn { regex } { trailing-backslash }
\exp_after:wN \use_none:n \exp_after:wN { \if_false: } \fi:
}
\cs_new_nopar:cpn { __regex_escape_~:w } { }
\cs_new_nopar:cpx { __regex_escape_/a:w }
{ \exp_not:N \__regex_escape_raw:N \iow_char:N \^^G }
\cs_new_nopar:cpx { __regex_escape_/t:w }
{ \exp_not:N \__regex_escape_raw:N \iow_char:N \^^I }
\cs_new_nopar:cpx { __regex_escape_/n:w }
{ \exp_not:N \__regex_escape_raw:N \iow_char:N \^^J }
\cs_new_nopar:cpx { __regex_escape_/f:w }
{ \exp_not:N \__regex_escape_raw:N \iow_char:N \^^L }
\cs_new_nopar:cpx { __regex_escape_/r:w }
{ \exp_not:N \__regex_escape_raw:N \iow_char:N \^^M }
\cs_new_nopar:cpx { __regex_escape_/e:w }
{ \exp_not:N \__regex_escape_raw:N \iow_char:N \^^[ }
\cs_new:cpn { __regex_escape_/x:w } \__regex_escape_loop:N
{
\exp_after:wN \__regex_escape_x_end:w
\__int_value:w "0 \__regex_escape_x_test:N
}
\cs_new:Npn \__regex_escape_x_end:w #1 ;
{
\int_compare:nNnTF {#1} < \c_two_hundred_fifty_six
{
\exp_last_unbraced:Nf \__regex_escape_raw:N
{ \__str_output_byte:n {#1} }
}
{ \__regex_escape_x_large:n {#1} }
}
\group_begin:
\char_set_catcode_other:n { 0 }
\cs_new:Npn \__regex_escape_x_large:n #1
{
\if_false: { \fi: }
\__tl_build_one:o \l__regex_internal_b_tl
\int_compare:nNnTF {#1} > \c_max_char_int
{
\__msg_kernel_error:nnx { regex } { x-overflow } {#1}
\tl_set:Nx \l__regex_internal_b_tl
{ \if_false: } \fi:
}
{
\char_set_lccode:nn { \c_zero } {#1}
\tl_to_lowercase:n
{
\tl_set:Nx \l__regex_internal_b_tl
{ \if_false: } \fi:
\__regex_escape_raw:N ^^@
}
}
}
\group_end:
\cs_new:Npn \__regex_escape_x_test:N #1
{
\str_if_eq_x:nnTF {#1} { break } { ; }
{
\if_charcode:w \c_space_token #1
\exp_after:wN \__regex_escape_x_test:N
\else:
\exp_after:wN \__regex_escape_x_test_two:N
\exp_after:wN #1
\fi:
}
}
\cs_new:Npn \__regex_escape_x_test_two:N #1
{
\if_charcode:w \c_left_brace_str #1
\exp_after:wN \__regex_escape_x_loop:N
\else:
\__str_hexadecimal_use:NTF #1
{ \exp_after:wN \__regex_escape_x:N }
{ ; \exp_after:wN \__regex_escape_loop:N \exp_after:wN #1 }
\fi:
}
\cs_new:Npn \__regex_escape_x:N #1
{
\str_if_eq_x:nnTF {#1} { break } { ; }
{
\__str_hexadecimal_use:NTF #1
{ ; \__regex_escape_loop:N }
{ ; \__regex_escape_loop:N #1 }
}
}
\cs_new:Npn \__regex_escape_x_loop:N #1
{
\__str_hexadecimal_use:NTF #1
{ \__regex_escape_x_loop:N }
{
\token_if_eq_charcode:NNTF \c_space_token #1
{ \__regex_escape_x_loop:N }
{
;
\exp_after:wN \token_if_eq_charcode:NNTF \c_right_brace_str #1
{ \__regex_escape_loop:N }
{
\if_false: { \fi: }
\__tl_build_one:o \l__regex_internal_b_tl
\__msg_kernel_error:nn { regex } { x-missing-rbrace } {#1}
\tl_set:Nx \l__regex_internal_b_tl
{ \if_false: } \fi: \__regex_escape_loop:N #1
}
}
}
}
\prg_new_conditional:Npnn \__regex_char_if_special:N #1 { TF }
{
\if_int_compare:w `#1 < \c_ninety_one
\if_int_compare:w `#1 < \c_fifty_eight
\if_int_compare:w `#1 < \c_forty_eight
\if_int_compare:w `#1 < \c_thirty_two
\prg_return_false: \else: \prg_return_true: \fi:
\else: \prg_return_false: \fi:
\else:
\if_int_compare:w `#1 < \c_sixty_five
\prg_return_true: \else: \prg_return_false: \fi:
\fi:
\else:
\if_int_compare:w `#1 < \c_one_hundred_twenty_three
\if_int_compare:w `#1 < \c_ninety_seven
\prg_return_true: \else: \prg_return_false: \fi:
\else:
\if_int_compare:w `#1 < \c_one_hundred_twenty_seven
\prg_return_true: \else: \prg_return_false: \fi:
\fi:
\fi:
}
\prg_new_conditional:Npnn \__regex_char_if_alphanumeric:N #1 { TF }
{
\if_int_compare:w `#1 < \c_ninety_one
\if_int_compare:w `#1 < \c_fifty_eight
\if_int_compare:w `#1 < \c_forty_eight
\prg_return_false: \else: \prg_return_true: \fi:
\else:
\if_int_compare:w `#1 < \c_sixty_five
\prg_return_false: \else: \prg_return_true: \fi:
\fi:
\else:
\if_int_compare:w `#1 < \c_one_hundred_twenty_three
\if_int_compare:w `#1 < \c_ninety_seven
\prg_return_false: \else: \prg_return_true: \fi:
\else:
\prg_return_false:
\fi:
\fi:
}
\int_new:N \l__regex_group_level_int
\int_new:N \l__regex_mode_int
\int_new:N \l__regex_catcodes_int
\int_new:N \l__regex_default_catcodes_int
\bool_new:N \l__regex_catcodes_bool
\int_const:Nn \c__regex_catcode_C_int { "1 }
\int_const:Nn \c__regex_catcode_B_int { "4 }
\int_const:Nn \c__regex_catcode_E_int { "10 }
\int_const:Nn \c__regex_catcode_M_int { "40 }
\int_const:Nn \c__regex_catcode_T_int { "100 }
\int_const:Nn \c__regex_catcode_P_int { "1000 }
\int_const:Nn \c__regex_catcode_U_int { "4000 }
\int_const:Nn \c__regex_catcode_D_int { "10000 }
\int_const:Nn \c__regex_catcode_S_int { "100000 }
\int_const:Nn \c__regex_catcode_L_int { "400000 }
\int_const:Nn \c__regex_catcode_O_int { "1000000 }
\int_const:Nn \c__regex_catcode_A_int { "4000000 }
\int_const:Nn \c__regex_all_catcodes_int { "5515155 }
\cs_new_eq:NN \l__regex_internal_regex \c__regex_no_match_regex
\seq_new:N \l__regex_show_prefix_seq
\int_new:N \l__regex_show_lines_int
\cs_new_protected:Npn \__regex_get_digits:NTFw #1#2#3#4#5
{
\__regex_if_raw_digit:NNTF #4 #5
{ #1 = #5 \__regex_get_digits_loop:nw {#2} }
{ #3 #4 #5 }
}
\cs_new:Npn \__regex_get_digits_loop:nw #1#2#3
{
\__regex_if_raw_digit:NNTF #2 #3
{ #3 \__regex_get_digits_loop:nw {#1} }
{ \scan_stop: #1 #2 #3 }
}
\prg_new_conditional:Npnn \__regex_if_raw_digit:NN #1#2 { TF }
{
\if_meaning:w \__regex_compile_raw:N #1
\if_int_compare:w \c_one < 1 #2 \exp_stop_f:
\prg_return_true:
\else:
\prg_return_false:
\fi:
\else:
\prg_return_false:
\fi:
}
\cs_new_nopar:Npn \__regex_if_in_class:TF
{
\if_int_odd:w \l__regex_mode_int
\exp_after:wN \use_i:nn
\else:
\exp_after:wN \use_ii:nn
\fi:
}
\cs_new_nopar:Npn \__regex_if_in_cs:TF
{
\if_int_odd:w \l__regex_mode_int
\exp_after:wN \use_ii:nn
\else:
\if_int_compare:w \l__regex_mode_int < \c_zero
\exp_after:wN \exp_after:wN \exp_after:wN \use_i:nn
\else:
\exp_after:wN \exp_after:wN \exp_after:wN \use_ii:nn
\fi:
\fi:
}
\cs_new_nopar:Npn \__regex_if_in_class_or_catcode:TF
{
\if_int_odd:w \l__regex_mode_int
\exp_after:wN \use_i:nn
\else:
\if_int_compare:w \l__regex_mode_int > \c_zero
\exp_after:wN \exp_after:wN \exp_after:wN \use_i:nn
\else:
\exp_after:wN \exp_after:wN \exp_after:wN \use_ii:nn
\fi:
\fi:
}
\cs_new_nopar:Npn \__regex_if_within_catcode:TF
{
\if_int_compare:w \l__regex_mode_int > \c_zero
\exp_after:wN \use_i:nn
\else:
\exp_after:wN \use_ii:nn
\fi:
}
\cs_new_protected:Npn \__regex_chk_c_allowed:T
{
\if_int_compare:w \l__regex_mode_int = \c_zero
\exp_after:wN \use:n
\else:
\if_int_compare:w \l__regex_mode_int = \c_three
\exp_after:wN \exp_after:wN \exp_after:wN \use:n
\else:
\__msg_kernel_error:nn { regex } { c-bad-mode }
\exp_after:wN \exp_after:wN \exp_after:wN \use_none:n
\fi:
\fi:
}
\cs_new_protected:Npn \__regex_mode_quit_c:
{
\if_int_compare:w \l__regex_mode_int = \c_two
\l__regex_mode_int = \c_zero
\else:
\if_int_compare:w \l__regex_mode_int = \c_six
\l__regex_mode_int = \c_three
\fi:
\fi:
}
\cs_new_protected_nopar:Npn \__regex_compile:w
{
\__tl_build_x:Nw \l__regex_internal_regex
\int_zero:N \l__regex_group_level_int
\int_set_eq:NN \l__regex_default_catcodes_int \c__regex_all_catcodes_int
\int_set_eq:NN \l__regex_catcodes_int \l__regex_default_catcodes_int
\cs_set_nopar:Npn \__regex_item_equal:n { \__regex_item_caseful_equal:n }
\cs_set_nopar:Npn \__regex_item_range:nn { \__regex_item_caseful_range:nn }
\__tl_build_one:n { \__regex_branch:n { \if_false: } \fi: }
}
\cs_new_protected_nopar:Npn \__regex_compile_end:
{
\__regex_if_in_class:TF
{
\__msg_kernel_error:nn { regex } { missing-rbrack }
\use:c { __regex_compile_]: }
\prg_do_nothing: \prg_do_nothing:
}
{ }
\if_int_compare:w \l__regex_group_level_int > \c_zero
\__msg_kernel_error:nnx { regex } { missing-rparen }
{ \int_use:N \l__regex_group_level_int }
\prg_replicate:nn
{ \l__regex_group_level_int }
{
\__tl_build_one:n
{
\if_false: { \fi: }
\if_false: { \fi: } { 1 } { 0 } \c_true_bool
}
\__tl_build_end:
\__tl_build_one:o \l__regex_internal_regex
}
\fi:
\__tl_build_one:n { \if_false: { \fi: } }
\__tl_build_end:
}
\cs_new_protected:Npn \__regex_compile:n #1
{
\__regex_compile:w
\int_set:Nn \tex_escapechar:D { 92 }
\int_set_eq:NN \l__regex_mode_int \c_zero
\__regex_escape_use:nnnn
{
\__regex_char_if_special:NTF ##1
\__regex_compile_special:N \__regex_compile_raw:N ##1
}
{
\__regex_char_if_alphanumeric:NTF ##1
\__regex_compile_escaped:N \__regex_compile_raw:N ##1
}
{ \__regex_compile_raw:N ##1 }
{ #1 }
\prg_do_nothing: \prg_do_nothing:
\prg_do_nothing: \prg_do_nothing:
\int_compare:nNnT \l__regex_mode_int < \c_zero
{
\__msg_kernel_error:nn { regex } { c-missing-rbrace }
\__regex_compile_end:
\__regex_compile_one:x
{ \__regex_item_cs:n { \exp_not:o \l__regex_internal_regex } }
\prg_do_nothing: \prg_do_nothing:
\prg_do_nothing: \prg_do_nothing:
}
\__regex_compile_end:
}
\cs_new_protected:Npn \__regex_compile_special:N #1
{
\cs_if_exist_use:cF { __regex_compile_#1: }
{ \__regex_compile_raw:N #1 }
}
\cs_new_protected:Npn \__regex_compile_escaped:N #1
{
\cs_if_exist_use:cF { __regex_compile_/#1: }
{ \__regex_compile_raw:N #1 }
}
\cs_new_protected:Npn \__regex_compile_one:x #1
{
\__regex_mode_quit_c:
\__regex_if_in_class:TF { }
{
\__tl_build_one:n
{ \__regex_class:NnnnN \c_true_bool { \if_false: } \fi: }
}
\__tl_build_one:x
{
\if_int_compare:w \l__regex_catcodes_int < \c__regex_all_catcodes_int
\__regex_item_catcode:nT { \int_use:N \l__regex_catcodes_int }
{ \exp_not:N \exp_not:n {#1} }
\else:
\exp_not:N \exp_not:n {#1}
\fi:
}
\int_set_eq:NN \l__regex_catcodes_int \l__regex_default_catcodes_int
\__regex_if_in_class:TF { } { \__regex_compile_quantifier:w }
}
\cs_new_protected:Npn \__regex_compile_abort_tokens:n #1
{
\use:x
{
\exp_args:No \tl_map_function:nN { \tl_to_str:n {#1} }
\__regex_compile_raw:N
}
}
\cs_generate_variant:Nn \__regex_compile_abort_tokens:n { x }
\cs_new_protected:Npn \__regex_compile_quantifier:w #1#2
{
\token_if_eq_meaning:NNTF #1 \__regex_compile_special:N
{
\cs_if_exist_use:cF { __regex_compile_quantifier_#2:w }
{ \__regex_compile_quantifier_none: #1 #2 }
}
{ \__regex_compile_quantifier_none: #1 #2 }
}
\cs_new_protected:Npn \__regex_compile_quantifier_none:
{ \__tl_build_one:n { \if_false: { \fi: } { 1 } { 0 } \c_false_bool } }
\cs_new_protected:Npn \__regex_compile_quantifier_abort:xNN #1#2#3
{
\__regex_compile_quantifier_none:
\__msg_kernel_warning:nnxx { regex } { invalid-quantifier } {#1} {#3}
\__regex_compile_abort_tokens:x {#1}
#2 #3
}
\cs_new_protected:Npn \__regex_compile_quantifier_lazyness:nnNN #1#2#3#4
{
\str_if_eq:nnTF { #3 #4 } { \__regex_compile_special:N ? }
{ \__tl_build_one:n { \if_false: { \fi: } { #1 } { #2 } \c_true_bool } }
{
\__tl_build_one:n { \if_false: { \fi: } { #1 } { #2 } \c_false_bool }
#3 #4
}
}
\cs_new_protected_nopar:cpn { __regex_compile_quantifier_?:w }
{ \__regex_compile_quantifier_lazyness:nnNN { 0 } { 1 } }
\cs_new_protected_nopar:cpn { __regex_compile_quantifier_*:w }
{ \__regex_compile_quantifier_lazyness:nnNN { 0 } { -1 } }
\cs_new_protected_nopar:cpn { __regex_compile_quantifier_+:w }
{ \__regex_compile_quantifier_lazyness:nnNN { 1 } { -1 } }
\cs_new_protected:cpn { __regex_compile_quantifier_ \c_left_brace_str :w }
{
\__regex_get_digits:NTFw \l__regex_internal_a_int
{ \__regex_compile_quantifier_braced_auxi:w }
{ \__regex_compile_quantifier_abort:xNN { \c_left_brace_str } }
}
\cs_new_protected:Npn \__regex_compile_quantifier_braced_auxi:w #1#2
{
\str_case_x:nnn { #1 #2 }
{
{ \__regex_compile_special:N \c_right_brace_str }
{
\exp_args:No \__regex_compile_quantifier_lazyness:nnNN
{ \int_use:N \l__regex_internal_a_int } { 0 }
}
{ \__regex_compile_special:N , }
{
\__regex_get_digits:NTFw \l__regex_internal_b_int
{ \__regex_compile_quantifier_braced_auxiii:w }
{ \__regex_compile_quantifier_braced_auxii:w }
}
}
{
\__regex_compile_quantifier_abort:xNN
{ \c_left_brace_str \int_use:N \l__regex_internal_a_int }
#1 #2
}
}
\cs_new_protected:Npn \__regex_compile_quantifier_braced_auxii:w #1#2
{
\str_if_eq_x:nnTF
{ #1 #2 } { \__regex_compile_special:N \c_right_brace_str }
{
\exp_args:No \__regex_compile_quantifier_lazyness:nnNN
{ \int_use:N \l__regex_internal_a_int } { -1 }
}
{
\__regex_compile_quantifier_abort:xNN
{ \c_left_brace_str \int_use:N \l__regex_internal_a_int , }
#1 #2
}
}
\cs_new_protected:Npn \__regex_compile_quantifier_braced_auxiii:w #1#2
{
\str_if_eq_x:nnTF
{ #1 #2 } { \__regex_compile_special:N \c_right_brace_str }
{
\if_int_compare:w \l__regex_internal_a_int > \l__regex_internal_b_int
\__msg_kernel_error:nnxx { regex } { backwards-quantifier }
{ \int_use:N \l__regex_internal_a_int }
{ \int_use:N \l__regex_internal_b_int }
\int_zero:N \l__regex_internal_b_int
\else:
\int_sub:Nn \l__regex_internal_b_int \l__regex_internal_a_int
\fi:
\exp_args:Noo \__regex_compile_quantifier_lazyness:nnNN
{ \int_use:N \l__regex_internal_a_int }
{ \int_use:N \l__regex_internal_b_int }
}
{
\__regex_compile_quantifier_abort:xNN
{
\c_left_brace_str
\int_use:N \l__regex_internal_a_int ,
\int_use:N \l__regex_internal_b_int
}
#1 #2
}
}
\cs_new_protected:Npn \__regex_compile_raw_error:N #1
{
\__msg_kernel_error:nnx { regex } { bad-escape } {#1}
\__regex_compile_raw:N #1
}
\cs_new_protected:Npn \__regex_compile_raw:N #1#2#3
{
\__regex_if_in_class:TF
{
\str_if_eq:nnTF {#2#3} { \__regex_compile_special:N - }
{ \__regex_compile_range:Nw #1 }
{
\__regex_compile_one:x
{ \__regex_item_equal:n { \__int_value:w `#1 ~ } }
#2 #3
}
}
{
\__regex_compile_one:x
{ \__regex_item_equal:n { \__int_value:w `#1 ~ } }
#2 #3
}
}
\prg_new_protected_conditional:Npnn \__regex_if_end_range:NN #1#2 { TF }
{
\if_meaning:w \__regex_compile_raw:N #1
\prg_return_true:
\else:
\if_meaning:w \__regex_compile_special:N #1
\if_charcode:w ] #2
\prg_return_false:
\else:
\prg_return_true:
\fi:
\else:
\prg_return_false:
\fi:
\fi:
}
\cs_new_protected:Npn \__regex_compile_range:Nw #1#2#3
{
\__regex_if_end_range:NNTF #2 #3
{
\if_int_compare:w `#1 > `#3 \exp_stop_f:
\__msg_kernel_error:nnxx { regex } { range-backwards } {#1} {#3}
\else:
\__tl_build_one:x
{
\if_int_compare:w `#1 = `#3 \exp_stop_f:
\__regex_item_equal:n
\else:
\__regex_item_range:nn { \__int_value:w `#1 ~ }
\fi:
{ \__int_value:w `#3 ~ }
}
\fi:
}
{
\__msg_kernel_warning:nnxx { regex } { range-missing-end }
{#1} { \c_backslash_str #3 }
\__tl_build_one:x
{
\__regex_item_equal:n { \__int_value:w `#1 ~ }
\__regex_item_equal:n { \__int_value:w `- ~ }
}
#2#3
}
}
\cs_new_protected_nopar:cpx { __regex_compile_.: }
{
\exp_not:N \__regex_if_in_class:TF
{ \__regex_compile_raw:N . }
{ \__regex_compile_one:x \exp_not:c { __regex_prop_.: } }
}
\cs_new_protected_nopar:cpn { __regex_prop_.: }
{
\if_int_compare:w \l__regex_current_char_int > - \c_two
\exp_after:wN \__regex_break_true:w
\fi:
}
\cs_set_protected:Npn \__regex_tmp:w #1#2
{
\cs_new_protected_nopar:cpx { __regex_compile_/#1: }
{ \__regex_compile_one:x \exp_not:c { __regex_prop_#1: } }
\cs_new_protected_nopar:cpx { __regex_compile_/#2: }
{
\__regex_compile_one:x
{ \__regex_item_reverse:n \exp_not:c { __regex_prop_#1: } }
}
}
\__regex_tmp:w d D
\__regex_tmp:w h H
\__regex_tmp:w s S
\__regex_tmp:w v V
\__regex_tmp:w w W
\cs_new_protected_nopar:cpn { __regex_compile_/N: }
{ \__regex_compile_one:x \__regex_prop_N: }
\cs_new_protected:Npn \__regex_compile_anchor:NF #1#2
{
\__regex_if_in_class_or_catcode:TF {#2}
{
\__tl_build_one:n
{ \__regex_assertion:Nn \c_true_bool { \__regex_anchor:N #1 } }
}
}
\cs_set_protected:Npn \__regex_tmp:w #1#2
{
\cs_new_protected_nopar:cpn { __regex_compile_/#1: }
{ \__regex_compile_anchor:NF #2 { \__regex_compile_raw_error:N #1 } }
}
\__regex_tmp:w A \l__regex_min_pos_int
\__regex_tmp:w G \l__regex_start_pos_int
\__regex_tmp:w Z \l__regex_max_pos_int
\__regex_tmp:w z \l__regex_max_pos_int
\cs_set_protected:Npn \__regex_tmp:w #1#2
{
\cs_new_protected_nopar:cpn { __regex_compile_#1: }
{ \__regex_compile_anchor:NF #2 { \__regex_compile_raw:N #1 } }
}
\exp_args:Nx \__regex_tmp:w { \iow_char:N \^ } \l__regex_min_pos_int
\exp_args:Nx \__regex_tmp:w { \iow_char:N \$ } \l__regex_max_pos_int
\cs_new_protected_nopar:cpn { __regex_compile_/b: }
{
\__regex_if_in_class_or_catcode:TF
{ \__regex_compile_raw_error:N b }
{
\__tl_build_one:n
{ \__regex_assertion:Nn \c_true_bool { \__regex_b_test: } }
}
}
\cs_new_protected_nopar:cpn { __regex_compile_/B: }
{
\__regex_if_in_class_or_catcode:TF
{ \__regex_compile_raw_error:N B }
{
\__tl_build_one:n
{ \__regex_assertion:Nn \c_false_bool { \__regex_b_test: } }
}
}
\cs_new_protected:cpn { __regex_compile_]: }
{
\__regex_if_in_class:TF
{
\if_int_compare:w \l__regex_mode_int > \c_sixteen
\__tl_build_one:n { \if_false: { \fi: } }
\fi:
\tex_advance:D \l__regex_mode_int - \c_fifteen
\tex_divide:D \l__regex_mode_int \c_thirteen
\if_int_odd:w \l__regex_mode_int \else:
\exp_after:wN \__regex_compile_quantifier:w
\fi:
}
{ \__regex_compile_raw:N ] }
}
\cs_new_protected_nopar:cpn { __regex_compile_[: }
{
\__regex_if_in_class:TF
{ \__regex_compile_class_posix_test:w }
{
\__regex_if_within_catcode:TF
{
\exp_after:wN \__regex_compile_class_catcode:w
\int_use:N \l__regex_catcodes_int ;
}
{ \__regex_compile_class_normal:w }
}
}
\cs_new_protected_nopar:Npn \__regex_compile_class_normal:w
{
\__regex_compile_class:TFNN
{ \__regex_class:NnnnN \c_true_bool }
{ \__regex_class:NnnnN \c_false_bool }
}
\cs_new_protected:Npn \__regex_compile_class_catcode:w #1;
{
\if_int_compare:w \l__regex_mode_int = \c_two
\__tl_build_one:n
{ \__regex_class:NnnnN \c_true_bool { \if_false: } \fi: }
\fi:
\int_set_eq:NN \l__regex_catcodes_int \l__regex_default_catcodes_int
\__regex_compile_class:TFNN
{ \__regex_item_catcode:nT {#1} }
{ \__regex_item_catcode_reverse:nT {#1} }
}
\cs_new_protected:Npn \__regex_compile_class:TFNN #1#2#3#4
{
\l__regex_mode_int = \__int_value:w \l__regex_mode_int 3 \exp_stop_f:
\str_if_eq:nnTF { #3 #4 } { \__regex_compile_special:N ^ }
{
\__tl_build_one:n { #2 { \if_false: } \fi: }
\__regex_compile_class:NN
}
{
\__tl_build_one:n { #1 { \if_false: } \fi: }
\__regex_compile_class:NN #3 #4
}
}
\cs_new_protected:Npn \__regex_compile_class:NN #1#2
{
\token_if_eq_charcode:NNTF #2 ]
{ \__regex_compile_raw:N #2 }
{ #1 #2 }
}
\cs_new_protected:Npn \__regex_compile_class_posix_test:w #1#2
{
\token_if_eq_meaning:NNT \__regex_compile_special:N #1
{
\str_case:nnn { #2 }
{
: { \__regex_compile_class_posix:NNNNw }
= { \__msg_kernel_warning:nnx { regex } { posix-unsupported } { = } }
. { \__msg_kernel_warning:nnx { regex } { posix-unsupported } { . } }
}
{ }
}
\__regex_compile_raw:N [ #1 #2
}
\cs_new_protected:Npn \__regex_compile_class_posix:NNNNw #1#2#3#4#5#6
{
\str_if_eq:nnTF { #5 #6 } { \__regex_compile_special:N ^ }
{
\bool_set_false:N \l__regex_internal_bool
\tl_set:Nx \l__regex_internal_a_tl { \if_false: } \fi:
\__regex_compile_class_posix_loop:w
}
{
\bool_set_true:N \l__regex_internal_bool
\tl_set:Nx \l__regex_internal_a_tl { \if_false: } \fi:
\__regex_compile_class_posix_loop:w #5 #6
}
}
\cs_new:Npn \__regex_compile_class_posix_loop:w #1#2
{
\token_if_eq_meaning:NNTF \__regex_compile_raw:N #1
{ #2 \__regex_compile_class_posix_loop:w }
{ \if_false: { \fi: } \__regex_compile_class_posix_end:w #1 #2 }
}
\cs_new_protected:Npn \__regex_compile_class_posix_end:w #1#2#3#4
{
\str_if_eq:nnTF { #1 #2 #3 #4 }
{ \__regex_compile_special:N : \__regex_compile_special:N ] }
{
\cs_if_exist:cTF { __regex_posix_ \l__regex_internal_a_tl : }
{
\__regex_compile_one:x
{
\bool_if:NF \l__regex_internal_bool \__regex_item_reverse:n
\exp_not:c { __regex_posix_ \l__regex_internal_a_tl : }
}
}
{
\__msg_kernel_warning:nnx { regex } { posix-unknown }
{ \l__regex_internal_a_tl }
\__regex_compile_abort_tokens:x
{
[: \bool_if:NF \l__regex_internal_bool { ^ }
\l__regex_internal_a_tl :]
}
}
}
{
\__msg_kernel_error:nnxx { regex } { posix-missing-close }
{ [: \l__regex_internal_a_tl } { #2 #4 }
\__regex_compile_abort_tokens:x { [: \l__regex_internal_a_tl }
#1 #2 #3 #4
}
}
\cs_new_protected:Npn \__regex_compile_group_begin:N #1
{
\__tl_build_one:n { #1 { \if_false: } \fi: }
\__regex_mode_quit_c:
\__tl_build:Nw \l__regex_internal_regex
\int_set_eq:NN \l__regex_default_catcodes_int \l__regex_catcodes_int
\int_incr:N \l__regex_group_level_int
\__tl_build_one:n { \__regex_branch:n { \if_false: } \fi: }
}
\cs_new_protected:Npn \__regex_compile_group_end:
{
\if_int_compare:w \l__regex_group_level_int > \c_zero
\__tl_build_one:n { \if_false: { \fi: } }
\__tl_build_end:
\int_set_eq:NN \l__regex_catcodes_int \l__regex_default_catcodes_int
\__tl_build_one:o \l__regex_internal_regex
\exp_after:wN \__regex_compile_quantifier:w
\else:
\__msg_kernel_warning:nn { regex } { extra-rparen }
\exp_after:wN \__regex_compile_raw:N \exp_after:wN )
\fi:
}
\cs_new_protected_nopar:cpn { __regex_compile_(: }
{
\__regex_if_in_class:TF { \__regex_compile_raw:N ( }
{ \__regex_compile_lparen:w }
}
\cs_new_protected:Npn \__regex_compile_lparen:w #1#2#3#4
{
\str_if_eq:nnTF { #1 #2 } { \__regex_compile_special:N ? }
{
\cs_if_exist_use:cF
{ __regex_compile_special_group_\token_to_str:N #4 :w }
{
\__msg_kernel_warning:nnx { regex } { special-group-unknown }
{ (? \token_to_str:N #4 }
\__regex_compile_group_begin:N \__regex_group:nnnN
\__regex_compile_raw:N ? #3 #4
}
}
{
\__regex_compile_group_begin:N \__regex_group:nnnN
#1 #2 #3 #4
}
}
\cs_new_protected_nopar:cpn { __regex_compile_|: }
{
\__regex_if_in_class:TF { \__regex_compile_raw:N | }
{
\__tl_build_one:n
{ \if_false: { \fi: } \__regex_branch:n { \if_false: } \fi: }
}
}
\cs_new_protected_nopar:cpn { __regex_compile_): }
{
\__regex_if_in_class:TF { \__regex_compile_raw:N ) }
{ \__regex_compile_group_end: }
}
\cs_new_protected_nopar:cpn { __regex_compile_special_group_::w }
{ \__regex_compile_group_begin:N \__regex_group_no_capture:nnnN }
\cs_new_protected_nopar:cpn { __regex_compile_special_group_|:w }
{ \__regex_compile_group_begin:N \__regex_group_resetting:nnnN }
\cs_new_protected:Npn \__regex_compile_special_group_i:w #1#2
{
\str_if_eq:nnTF { #1 #2 } { \__regex_compile_special:N ) }
{
\cs_set_nopar:Npn \__regex_item_equal:n { \__regex_item_caseless_equal:n }
\cs_set_nopar:Npn \__regex_item_range:nn { \__regex_item_caseless_range:nn }
}
{
\__msg_kernel_warning:nnx { regex } { unknown-option } { (?i #2 }
\__regex_compile_raw:N (
\__regex_compile_raw:N ?
\__regex_compile_raw:N i
#1 #2
}
}
\cs_new_protected_nopar:cpn { __regex_compile_special_group_-:w } #1#2#3#4
{
\str_if_eq:nnTF { #1 #2 #3 #4 }
{ \__regex_compile_raw:N i \__regex_compile_special:N ) }
{
\cs_set_nopar:Npn \__regex_item_equal:n { \__regex_item_caseful_equal:n }
\cs_set_nopar:Npn \__regex_item_range:nn { \__regex_item_caseful_range:nn }
}
{
\__msg_kernel_warning:nnx { regex } { unknown-option } { (?-#2#4 }
\__regex_compile_raw:N (
\__regex_compile_raw:N ?
\__regex_compile_raw:N -
#1 #2 #3 #4
}
}
\cs_new_protected:cpn { __regex_compile_/c: }
{ \__regex_chk_c_allowed:T { \__regex_compile_c_test:NN } }
\cs_new_protected:Npn \__regex_compile_c_test:NN #1#2
{
\token_if_eq_meaning:NNTF #1 \__regex_compile_raw:N
{
\int_if_exist:cTF { c__regex_catcode_#2_int }
{
\int_set_eq:Nc \l__regex_catcodes_int { c__regex_catcode_#2_int }
\l__regex_mode_int
= \if_case:w \l__regex_mode_int \c_two \else: \c_six \fi:
}
}
{ \cs_if_exist_use:cF { __regex_compile_c_#2:w } }
{
\__msg_kernel_error:nnx { regex } { c-missing-category } {#2}
#1 #2
}
}
\cs_new_protected:cpn { __regex_compile_c_[:w } #1#2
{
\l__regex_mode_int
= \if_case:w \l__regex_mode_int \c_two \else: \c_six \fi:
\int_zero:N \l__regex_catcodes_int
\str_if_eq:nnTF { #1 #2 } { \__regex_compile_special:N ^ }
{
\bool_set_false:N \l__regex_catcodes_bool
\__regex_compile_c_lbrack_loop:NN
}
{
\bool_set_true:N \l__regex_catcodes_bool
\__regex_compile_c_lbrack_loop:NN
#1 #2
}
}
\cs_new_protected:Npn \__regex_compile_c_lbrack_loop:NN #1#2
{
\token_if_eq_meaning:NNTF #1 \__regex_compile_raw:N
{
\int_if_exist:cTF { c__regex_catcode_#2_int }
{
\exp_args:Nc \__regex_compile_c_lbrack_add:N
{ c__regex_catcode_#2_int }
\__regex_compile_c_lbrack_loop:NN
}
}
{
\token_if_eq_charcode:NNTF #2 ]
{ \__regex_compile_c_lbrack_end: }
}
{
\__msg_kernel_error:nnx { regex } { c-missing-rbrack } {#2}
\__regex_compile_c_lbrack_end:
#1 #2
}
}
\cs_new_protected:Npn \__regex_compile_c_lbrack_add:N #1
{
\if_int_odd:w \__int_eval:w \l__regex_catcodes_int / #1 \__int_eval_end:
\else:
\tex_advance:D \l__regex_catcodes_int #1
\fi:
}
\cs_new_protected_nopar:Npn \__regex_compile_c_lbrack_end:
{
\if_meaning:w \c_false_bool \l__regex_catcodes_bool
\int_set:Nn \l__regex_catcodes_int
{ \c__regex_all_catcodes_int - \l__regex_catcodes_int }
\fi:
}
\cs_new_protected_nopar:cpn { __regex_compile_c_ \c_left_brace_str :w }
{
\__regex_compile:w
\__regex_disable_submatches:
\l__regex_mode_int
= - \if_case:w \l__regex_mode_int \c_two \else: \c_six \fi:
}
\cs_new_protected:cpn { __regex_compile_ \c_right_brace_str : }
{
\__regex_if_in_cs:TF
{
\__regex_compile_end:
\__regex_compile_one:x
{ \__regex_item_cs:n { \exp_not:o \l__regex_internal_regex } }
}
{ \exp_after:wN \__regex_compile_raw:N \c_right_brace_str }
}
\cs_new_protected:cpn { __regex_compile_/u: } #1#2
{
\__regex_if_in_class_or_catcode:TF
{ \__regex_compile_raw_error:N u #1 #2 }
{
\str_if_eq_x:nnTF {#1#2} { \__regex_compile_special:N \c_left_brace_str }
{
\tl_set:Nx \l__regex_internal_a_tl { \if_false: } \fi:
\__regex_compile_u_loop:NN
}
{
\__msg_kernel_error:nn { regex } { u-missing-lbrace }
\__regex_compile_raw:N u #1 #2
}
}
}
\cs_new:Npn \__regex_compile_u_loop:NN #1#2
{
\token_if_eq_meaning:NNTF #1 \__regex_compile_raw:N
{ #2 \__regex_compile_u_loop:NN }
{
\token_if_eq_meaning:NNTF #1 \__regex_compile_special:N
{
\exp_after:wN \token_if_eq_charcode:NNTF \c_right_brace_str #2
{ \if_false: { \fi: } \__regex_compile_u_end: }
{ #2 \__regex_compile_u_loop:NN }
}
{
\if_false: { \fi: }
\__msg_kernel_error:nnx { regex } { u-missing-rbrace } {#2}
\__regex_compile_u_end:
#1 #2
}
}
}
\cs_new_protected:Npn \__regex_compile_u_end:
{
\tl_set:Nv \l__regex_internal_a_tl { \l__regex_internal_a_tl }
\if_int_compare:w \l__regex_mode_int = \c_zero
\__regex_compile_u_not_cs:
\else:
\__regex_compile_u_in_cs:
\fi:
}
\cs_new_protected:Npn \__regex_compile_u_in_cs:
{
\exp_args:NNo \__str_gset_other:Nn \g__regex_internal_tl
{ \l__regex_internal_a_tl }
\__tl_build_one:x
{
\tl_map_function:NN \g__regex_internal_tl
\__regex_compile_u_in_cs_aux:n
}
}
\cs_new:Npn \__regex_compile_u_in_cs_aux:n #1
{
\__regex_class:NnnnN \c_true_bool
{ \__regex_item_caseful_equal:n { \__int_value:w `#1 } }
{ 1 } { 0 } \c_false_bool
}
\cs_new_protected:Npn \__regex_compile_u_not_cs:
{
\exp_args:No \__tl_analysis_map_inline:nn { \l__regex_internal_a_tl }
{
\__tl_build_one:n
{
\__regex_class:NnnnN \c_true_bool
{
\if_int_compare:w "##2 = \c_zero
\__regex_item_exact_cs:c { \exp_after:wN \cs_to_str:N ##1 }
\else:
\__regex_item_exact:nn { \__int_value:w "##2 } { ##3 }
\fi:
}
{ 1 } { 0 } \c_false_bool
}
}
}
\cs_new_protected_nopar:cpn { __regex_compile_/K: }
{
\int_compare:nNnTF \l__regex_mode_int = \c_zero
{ \__tl_build_one:n { \__regex_command_K: } }
{ \__regex_compile_raw_error:N K }
}
\cs_new_protected:Npn \__regex_show:Nx #1#2
{
\__tl_build:Nw \l__regex_internal_a_tl
\cs_set_protected_nopar:Npn \__regex_branch:n
{
\seq_pop_right:NN \l__regex_show_prefix_seq \l__regex_internal_a_tl
\__regex_show_one:n { +-branch }
\seq_put_right:No \l__regex_show_prefix_seq \l__regex_internal_a_tl
\use:n
}
\cs_set_protected_nopar:Npn \__regex_group:nnnN
{ \__regex_show_group_aux:nnnnN { } }
\cs_set_protected_nopar:Npn \__regex_group_no_capture:nnnN
{ \__regex_show_group_aux:nnnnN { ~(no~capture) } }
\cs_set_protected_nopar:Npn \__regex_group_resetting:nnnN
{ \__regex_show_group_aux:nnnnN { ~(resetting) } }
\cs_set_eq:NN \__regex_class:NnnnN \__regex_show_class:NnnnN
\cs_set_protected_nopar:Npn \__regex_command_K:
{ \__regex_show_one:n { reset~match~start~(\iow_char:N\\K) } }
\cs_set_protected:Npn \__regex_assertion:Nn ##1##2
{ \__regex_show_one:n { \bool_if:NF ##1 { negative~ } assertion:~##2 } }
\cs_set_nopar:Npn \__regex_b_test: { word~boundary }
\cs_set_eq:NN \__regex_anchor:N \__regex_show_anchor_to_str:N
\cs_set_protected:Npn \__regex_item_caseful_equal:n ##1
{ \__regex_show_one:n { char~code~\int_eval:n{##1} } }
\cs_set_protected:Npn \__regex_item_caseful_range:nn ##1##2
{ \__regex_show_one:n { range~[\int_eval:n{##1}, \int_eval:n{##2}] } }
\cs_set_protected:Npn \__regex_item_caseless_equal:n ##1
{ \__regex_show_one:n { char~code~\int_eval:n{##1}~(caseless) } }
\cs_set_protected:Npn \__regex_item_caseless_range:nn ##1##2
{
\__regex_show_one:n
{ Range~[\int_eval:n{##1}, \int_eval:n{##2}]~(caseless) }
}
\cs_set_protected:Npn \__regex_item_catcode:nT
{ \__regex_show_item_catcode:NnT \c_true_bool }
\cs_set_protected:Npn \__regex_item_catcode_reverse:nT
{ \__regex_show_item_catcode:NnT \c_false_bool }
\cs_set_protected:Npn \__regex_item_reverse:n
{ \__regex_show_scope:nn { Reversed~match } }
\cs_set_protected:Npn \__regex_item_exact:nn ##1##2
{ \__regex_show_one:n { char~##2,~catcode~##1 } }
\cs_set_protected:Npn \__regex_item_exact_cs:c ##1
{ \__regex_show_one:n { control~sequence~\iow_char:N\\##1 } }
\cs_set_protected:Npn \__regex_item_cs:n
{ \__regex_show_scope:nn { control~sequence } }
\cs_set:cpn { __regex_prop_.: } { \__regex_show_one:n { any~token } }
\seq_clear:N \l__regex_show_prefix_seq
\__regex_show_push:n { ~ }
#1
\__tl_build_end:
\__msg_show_variable:n { >~Compiled~regex~#2: \l__regex_internal_a_tl }
}
\cs_new_protected:Npn \__regex_show_one:n #1
{
\int_incr:N \l__regex_show_lines_int
\__tl_build_one:x
{
\exp_not:N \\
\seq_map_function:NN \l__regex_show_prefix_seq \use:n
#1
}
}
\cs_new_protected:Npn \__regex_show_push:n #1
{ \seq_put_right:Nx \l__regex_show_prefix_seq { #1 ~ } }
\cs_new_protected:Npn \__regex_show_pop:
{ \seq_pop_right:NN \l__regex_show_prefix_seq \l__regex_internal_a_tl }
\cs_new_protected:Npn \__regex_show_scope:nn #1#2
{
\__regex_show_one:n {#1}
\__regex_show_push:n { ~ }
#2
\__regex_show_pop:
}
\cs_new_protected:Npn \__regex_show_group_aux:nnnnN #1#2#3#4#5
{
\__regex_show_one:n { ,-group~begin #1 }
\__regex_show_push:n { | }
\use_ii:nn #2
\__regex_show_pop:
\__regex_show_one:n
{ `-group~end \__regex_msg_repeated:nnN {#3} {#4} #5 }
}
\cs_set:Npn \__regex_show_class:NnnnN #1#2#3#4#5
{
\__tl_build:Nw \l__regex_internal_a_tl
\int_zero:N \l__regex_show_lines_int
\__regex_show_push:n {~}
#2
\exp_last_unbraced:Nf
\int_case:nnn { \l__regex_show_lines_int }
{
{0}
{
\__tl_build_end:
\__regex_show_one:n { \bool_if:NTF #1 { Fail } { Pass } }
}
{1}
{
\__tl_build_end:
\bool_if:NTF #1
{
#2
\__tl_build_one:n { \__regex_msg_repeated:nnN {#3} {#4} #5 }
}
{
\__regex_show_one:n
{ Don't~match~\__regex_msg_repeated:nnN {#3} {#4} #5 }
\__tl_build_one:o \l__regex_internal_a_tl
}
}
}
{
\__tl_build_end:
\__regex_show_one:n
{
\bool_if:NTF #1 { M } { Don't~m } atch
\__regex_msg_repeated:nnN {#3} {#4} #5
}
\__tl_build_one:o \l__regex_internal_a_tl
}
}
\cs_new:Npn \__regex_show_anchor_to_str:N #1
{
anchor~at~
\str_case:nnn { #1 }
{
{ \l__regex_min_pos_int } { start~(\iow_char:N\\A) }
{ \l__regex_start_pos_int } { start~of~match~(\iow_char:N\\G) }
{ \l__regex_max_pos_int } { end~(\iow_char:N\\Z) }
}
{ <error:~'#1'~not~recognized> }
}
\cs_new_protected:Npn \__regex_show_item_catcode:NnT #1#2
{
\seq_set_split:Nnn \l__regex_internal_seq { } { CBEMTPUDSLOA }
\seq_set_filter:NNn \l__regex_internal_seq \l__regex_internal_seq
{ \int_if_odd_p:n { #2 / \int_use:c { c__regex_catcode_##1_int } } }
\__regex_show_scope:nn
{
categories~
\seq_map_function:NN \l__regex_internal_seq \use:n
, ~
\bool_if:NF #1 { negative~ } class
}
}
\int_new:N \l__regex_min_state_int
\int_new:N \l__regex_max_state_int
\int_new:N \l__regex_left_state_int
\int_new:N \l__regex_right_state_int
\seq_new:N \l__regex_left_state_seq
\seq_new:N \l__regex_right_state_seq
\int_new:N \l__regex_capturing_group_int
\cs_new_protected:Npn \__regex_build:n #1
{
\__regex_compile:n {#1}
\__regex_build:N \l__regex_internal_regex
}
\cs_new_protected:Npn \__regex_build:N #1
{
\int_set:Nn \tex_escapechar:D { 92 }
\int_zero:N \l__regex_capturing_group_int
\int_set_eq:NN \l__regex_max_state_int \l__regex_min_state_int
\__regex_build_new_state:
\__regex_build_new_state:
\__regex_toks_put_right:Nn \l__regex_left_state_int
{ \__regex_action_start_wildcard: }
\__regex_group:nnnN {#1} { 1 } { 0 } \c_false_bool
\__regex_toks_put_right:Nn \l__regex_right_state_int
{ \__regex_action_success: }
}
\cs_new_protected:Npn \__regex_build_for_cs:n #1
{
\int_set_eq:NN \l__regex_max_state_int \l__regex_min_state_int
\__regex_build_new_state:
\__regex_build_new_state:
\__regex_push_lr_states:
#1
\__regex_pop_lr_states:
\__regex_toks_put_right:Nn \l__regex_right_state_int
{
\if_int_compare:w \l__regex_current_pos_int = \l__regex_max_pos_int
\exp_after:wN \__regex_action_success:
\fi:
}
}
\cs_new_protected_nopar:Npn \__regex_push_lr_states:
{
\seq_push:No \l__regex_left_state_seq
{ \int_use:N \l__regex_left_state_int }
\seq_push:No \l__regex_right_state_seq
{ \int_use:N \l__regex_right_state_int }
}
\cs_new_protected_nopar:Npn \__regex_pop_lr_states:
{
\seq_pop:NN \l__regex_left_state_seq \l__regex_internal_a_tl
\int_set:Nn \l__regex_left_state_int \l__regex_internal_a_tl
\seq_pop:NN \l__regex_right_state_seq \l__regex_internal_a_tl
\int_set:Nn \l__regex_right_state_int \l__regex_internal_a_tl
}
\cs_new_protected:Npn \__regex_toks_put_left:Nx #1#2
{
\cs_set_nopar:Npx \__regex_tmp:w { #2 }
\tex_toks:D #1 \exp_after:wN \exp_after:wN \exp_after:wN
{ \exp_after:wN \__regex_tmp:w \tex_the:D \tex_toks:D #1 }
}
\cs_new_protected:Npn \__regex_toks_put_right:Nx #1#2
{
\cs_set_nopar:Npx \__regex_tmp:w {#2}
\tex_toks:D #1 \exp_after:wN
{ \tex_the:D \tex_toks:D \exp_after:wN #1 \__regex_tmp:w }
}
\cs_new_protected:Npn \__regex_toks_put_right:Nn #1#2
{ \tex_toks:D #1 \exp_after:wN { \tex_the:D \tex_toks:D #1 #2 } }
\cs_new_protected:Npn \__regex_build_transition_left:NNN #1#2#3
{ \__regex_toks_put_left:Nx #2 { #1 { \int_eval:n { #3 - #2 } } } }
\cs_new_protected:Npn \__regex_build_transition_right:nNn #1#2#3
{ \__regex_toks_put_right:Nx #2 { #1 { \int_eval:n { #3 - #2 } } } }
\cs_new_protected_nopar:Npn \__regex_build_new_state:
{
\tex_toks:D \l__regex_max_state_int { }
\int_set_eq:NN \l__regex_left_state_int \l__regex_right_state_int
\int_set_eq:NN \l__regex_right_state_int \l__regex_max_state_int
\int_incr:N \l__regex_max_state_int
}
\cs_new_protected:Npn \__regex_build_transitions_lazyness:NNNNN #1#2#3#4#5
{
\__regex_build_new_state:
\__regex_toks_put_right:Nx \l__regex_left_state_int
{
\if_meaning:w \c_true_bool #1
#2 { \int_eval:n { #3 - \l__regex_left_state_int } }
#4 { \int_eval:n { #5 - \l__regex_left_state_int } }
\else:
#4 { \int_eval:n { #5 - \l__regex_left_state_int } }
#2 { \int_eval:n { #3 - \l__regex_left_state_int } }
\fi:
}
}
\cs_new_protected:Npn \__regex_class:NnnnN #1#2#3#4#5
{
\cs_set_nopar:Npx \__regex_tests_action_cost:n ##1
{
\exp_not:n { \exp_not:n {#2} }
\bool_if:NTF #1
{ \__regex_break_point:TF { \__regex_action_cost:n {##1} } { } }
{ \__regex_break_point:TF { } { \__regex_action_cost:n {##1} } }
}
\if_case:w - #4 \exp_stop_f:
\__regex_class_repeat:n {#3}
\or: \__regex_class_repeat:nN {#3} #5
\else: \__regex_class_repeat:nnN {#3} {#4} #5
\fi:
}
\cs_new:Npn \__regex_tests_action_cost:n { \__regex_action_cost:n }
\cs_new_protected:Npn \__regex_class_repeat:n #1
{
\prg_replicate:nn {#1}
{
\__regex_build_new_state:
\__regex_build_transition_right:nNn \__regex_tests_action_cost:n
\l__regex_left_state_int \l__regex_right_state_int
}
}
\cs_new_protected:Npn \__regex_class_repeat:nN #1#2
{
\if_int_compare:w #1 = \c_zero
\__regex_build_transitions_lazyness:NNNNN #2
\__regex_action_free:n \l__regex_right_state_int
\__regex_tests_action_cost:n \l__regex_left_state_int
\else:
\__regex_class_repeat:n {#1}
\int_set_eq:NN \l__regex_internal_a_int \l__regex_left_state_int
\__regex_build_transitions_lazyness:NNNNN #2
\__regex_action_free:n \l__regex_right_state_int
\__regex_action_free:n \l__regex_internal_a_int
\fi:
}
\cs_new_protected:Npn \__regex_class_repeat:nnN #1#2#3
{
\__regex_class_repeat:n {#1}
\int_set:Nn \l__regex_internal_a_int
{ \l__regex_max_state_int + #2 - \c_one }
\prg_replicate:nn { #2 }
{
\__regex_build_transitions_lazyness:NNNNN #3
\__regex_action_free:n \l__regex_internal_a_int
\__regex_tests_action_cost:n \l__regex_right_state_int
}
}
\cs_new_protected:Npn \__regex_group_aux:nnnnN #1#2#3#4#5
{
\if_int_compare:w #3 = \c_zero
\__regex_build_new_state:
\__regex_build_transition_right:nNn \__regex_action_free_group:n
\l__regex_left_state_int \l__regex_right_state_int
\fi:
\__regex_build_new_state:
\__regex_push_lr_states:
#2
\__regex_pop_lr_states:
\if_case:w - #4 \exp_stop_f:
\__regex_group_repeat:nn {#1} {#3}
\or: \__regex_group_repeat:nnN {#1} {#3} #5
\else: \__regex_group_repeat:nnnN {#1} {#3} {#4} #5
\fi:
}
\cs_new_protected:Npn \__regex_group:nnnN #1
{
\exp_args:No \__regex_group_aux:nnnnN
{ \int_use:N \l__regex_capturing_group_int }
{
\int_incr:N \l__regex_capturing_group_int
#1
}
}
\cs_new_protected_nopar:Npn \__regex_group_no_capture:nnnN
{ \__regex_group_aux:nnnnN { -1 } }
\cs_new_protected:Npn \__regex_group_resetting:nnnN #1
{
\__regex_group_aux:nnnnN { -1 }
{
\exp_args:Noo \__regex_group_resetting_loop:nnNn
{ \int_use:N \l__regex_capturing_group_int }
{ \int_use:N \l__regex_capturing_group_int }
#1
{ ?? \__prg_break:n } { }
\__prg_break_point:
}
}
\cs_new_protected:Npn \__regex_group_resetting_loop:nnNn #1#2#3#4
{
\use_none:nn #3 { \int_set:Nn \l__regex_capturing_group_int {#1} }
\int_set:Nn \l__regex_capturing_group_int {#2}
#3 {#4}
\exp_args:Nf \__regex_group_resetting_loop:nnNn
{ \int_max:nn {#1} { \l__regex_capturing_group_int } }
{#2}
}
\cs_new_protected:Npn \__regex_branch:n #1
{
\__regex_build_new_state:
\seq_get:NN \l__regex_left_state_seq \l__regex_internal_a_tl
\int_set:Nn \l__regex_left_state_int \l__regex_internal_a_tl
\__regex_build_transition_right:nNn \__regex_action_free:n
\l__regex_left_state_int \l__regex_right_state_int
#1
\seq_get:NN \l__regex_right_state_seq \l__regex_internal_a_tl
\__regex_build_transition_right:nNn \__regex_action_free:n
\l__regex_right_state_int \l__regex_internal_a_tl
}
\cs_new_protected:Npn \__regex_group_repeat:nn #1#2
{
\if_int_compare:w #2 = \c_zero
\int_set:Nn \l__regex_max_state_int
{ \l__regex_left_state_int - \c_one }
\__regex_build_new_state:
\else:
\__regex_group_repeat_aux:n {#2}
\__regex_group_submatches:nNN {#1}
\l__regex_internal_a_int \l__regex_right_state_int
\__regex_build_new_state:
\fi:
}
\cs_new_protected:Npn \__regex_group_submatches:nNN #1#2#3
{
\if_int_compare:w #1 > \c_minus_one
\__regex_toks_put_left:Nx #2 { \__regex_action_submatch:n { #1 < } }
\__regex_toks_put_left:Nx #3 { \__regex_action_submatch:n { #1 > } }
\fi:
}
\cs_new_protected:Npn \__regex_group_repeat_aux:n #1
{
\__regex_build_transition_right:nNn \__regex_action_free:n
\l__regex_right_state_int \l__regex_max_state_int
\int_set_eq:NN \l__regex_internal_a_int \l__regex_left_state_int
\int_set_eq:NN \l__regex_internal_b_int \l__regex_max_state_int
\if_int_compare:w \__int_eval:w #1 > \c_one
\int_set:Nn \l__regex_internal_c_int
{
( #1 - \c_one )
* ( \l__regex_internal_b_int - \l__regex_internal_a_int )
}
\tex_advance:D \l__regex_right_state_int \l__regex_internal_c_int
\tex_advance:D \l__regex_max_state_int \l__regex_internal_c_int
\prg_replicate:nn \l__regex_internal_c_int
{
\tex_toks:D \l__regex_internal_b_int
= \tex_toks:D \l__regex_internal_a_int
\tex_advance:D \l__regex_internal_a_int \c_one
\tex_advance:D \l__regex_internal_b_int \c_one
}
\fi:
}
\cs_new_protected:Npn \__regex_group_repeat:nnN #1#2#3
{
\if_int_compare:w #2 = \c_zero
\__regex_group_submatches:nNN {#1}
\l__regex_left_state_int \l__regex_right_state_int
\int_set:Nn \l__regex_internal_a_int
{ \l__regex_left_state_int - \c_one }
\__regex_build_transition_right:nNn \__regex_action_free:n
\l__regex_right_state_int \l__regex_internal_a_int
\__regex_build_new_state:
\if_meaning:w \c_true_bool #3
\__regex_build_transition_left:NNN \__regex_action_free:n
\l__regex_internal_a_int \l__regex_right_state_int
\else:
\__regex_build_transition_right:nNn \__regex_action_free:n
\l__regex_internal_a_int \l__regex_right_state_int
\fi:
\else:
\__regex_group_repeat_aux:n {#2}
\__regex_group_submatches:nNN {#1}
\l__regex_internal_a_int \l__regex_right_state_int
\if_meaning:w \c_true_bool #3
\__regex_build_transition_right:nNn \__regex_action_free_group:n
\l__regex_right_state_int \l__regex_internal_a_int
\else:
\__regex_build_transition_left:NNN \__regex_action_free_group:n
\l__regex_right_state_int \l__regex_internal_a_int
\fi:
\__regex_build_new_state:
\fi:
}
\cs_new_protected:Npn \__regex_group_repeat:nnnN #1#2#3#4
{
\__regex_group_submatches:nNN {#1}
\l__regex_left_state_int \l__regex_right_state_int
\__regex_group_repeat_aux:n { #2 + #3 }
\if_meaning:w \c_true_bool #4
\int_set_eq:NN \l__regex_left_state_int \l__regex_max_state_int
\prg_replicate:nn { #3 }
{
\int_sub:Nn \l__regex_left_state_int
{ \l__regex_internal_b_int - \l__regex_internal_a_int }
\__regex_build_transition_left:NNN \__regex_action_free:n
\l__regex_left_state_int \l__regex_max_state_int
}
\else:
\prg_replicate:nn { #3 - \c_one }
{
\int_sub:Nn \l__regex_right_state_int
{ \l__regex_internal_b_int - \l__regex_internal_a_int }
\__regex_build_transition_right:nNn \__regex_action_free:n
\l__regex_right_state_int \l__regex_max_state_int
}
\if_int_compare:w #2 = \c_zero
\int_set:Nn \l__regex_right_state_int
{ \l__regex_left_state_int - \c_one }
\else:
\int_sub:Nn \l__regex_right_state_int
{ \l__regex_internal_b_int - \l__regex_internal_a_int }
\fi:
\__regex_build_transition_right:nNn \__regex_action_free:n
\l__regex_right_state_int \l__regex_max_state_int
\fi:
\__regex_build_new_state:
}
\cs_new_protected:Npn \__regex_assertion:Nn #1#2
{
\__regex_build_new_state:
\__regex_toks_put_right:Nx \l__regex_left_state_int
{
\exp_not:n {#2}
\__regex_break_point:TF
\bool_if:NF #1 { { } }
{
\__regex_action_free:n
{
\int_eval:n
{ \l__regex_right_state_int - \l__regex_left_state_int }
}
}
\bool_if:NT #1 { { } }
}
}
\cs_new_protected:Npn \__regex_anchor:N #1
{
\if_int_compare:w #1 = \l__regex_current_pos_int
\exp_after:wN \__regex_break_true:w
\fi:
}
\cs_new_protected_nopar:Npn \__regex_b_test:
{
\group_begin:
\int_set_eq:NN \l__regex_current_char_int \l__regex_last_char_int
\__regex_prop_w:
\__regex_break_point:TF
{ \group_end: \__regex_item_reverse:n \__regex_prop_w: }
{ \group_end: \__regex_prop_w: }
}
\cs_new_protected_nopar:Npn \__regex_command_K:
{
\__regex_build_new_state:
\__regex_toks_put_right:Nx \l__regex_left_state_int
{
\__regex_action_submatch:n { 0< }
\bool_set_true:N \l__regex_fresh_thread_bool
\__regex_action_free:n
{ \int_eval:n { \l__regex_right_state_int - \l__regex_left_state_int } }
\bool_set_false:N \l__regex_fresh_thread_bool
}
}
\int_new:N \l__regex_min_pos_int
\int_new:N \l__regex_max_pos_int
\int_new:N \l__regex_current_pos_int
\int_new:N \l__regex_start_pos_int
\int_new:N \l__regex_success_pos_int
\int_new:N \l__regex_current_char_int
\int_new:N \l__regex_current_catcode_int
\int_new:N \l__regex_last_char_int
\int_new:N \l__regex_case_changed_char_int
\int_new:N \l__regex_current_state_int
\prop_new:N \l__regex_current_submatches_prop
\prop_new:N \l__regex_success_submatches_prop
\int_new:N \l__regex_step_int
\int_new:N \l__regex_min_active_int
\int_new:N \l__regex_max_active_int
\tl_new:N \l__regex_every_match_tl
\bool_new:N \l__regex_fresh_thread_bool
\bool_new:N \l__regex_empty_success_bool
\cs_new_eq:NN \__regex_if_two_empty_matches:F \use:n
\bool_new:N \g__regex_success_bool
\bool_new:N \l__regex_saved_success_bool
\bool_new:N \l__regex_match_success_bool
\cs_new_protected:Npn \__regex_match:n #1
{
\int_zero:N \l__regex_balance_int
\int_set:Nn \l__regex_current_pos_int { \c_two * \l__regex_max_state_int }
\__regex_query_set:nnn { } { -1 } { -2 }
\int_set_eq:NN \l__regex_min_pos_int \l__regex_current_pos_int
\__tl_analysis_map_inline:nn {#1}
{ \__regex_query_set:nnn {##1} {"##2} {##3} }
\int_set_eq:NN \l__regex_max_pos_int \l__regex_current_pos_int
\__regex_query_set:nnn { } { -1 } { -2 }
\bool_gset_false:N \g__regex_success_bool
\int_step_inline:nnnn
\l__regex_min_state_int \c_one { \l__regex_max_state_int - \c_one }
{ \tex_dimen:D ##1 \c_one sp \scan_stop: }
\int_set_eq:NN \l__regex_min_active_int \l__regex_max_state_int
\int_set_eq:NN \l__regex_step_int \c_zero
\int_set_eq:NN \l__regex_success_pos_int \l__regex_min_pos_int
\int_set:Nn \l__regex_submatch_int
{ \c_two * \l__regex_max_state_int }
\bool_set_false:N \l__regex_empty_success_bool
\__regex_match_once:
}
\cs_new_protected_nopar:Npn \__regex_match_once:
{
\if_meaning:w \c_true_bool \l__regex_empty_success_bool
\cs_set_nopar:Npn \__regex_if_two_empty_matches:F
{ \int_compare:nNnF \l__regex_start_pos_int = \l__regex_current_pos_int }
\else:
\cs_set_eq:NN \__regex_if_two_empty_matches:F \use:n
\fi:
\int_set_eq:NN \l__regex_start_pos_int \l__regex_success_pos_int
\bool_set_false:N \l__regex_match_success_bool
\prop_clear:N \l__regex_current_submatches_prop
\int_set_eq:NN \l__regex_max_active_int \l__regex_min_active_int
\__regex_store_state:n { \l__regex_min_state_int }
\int_set:Nn \l__regex_current_pos_int
{ \l__regex_start_pos_int - \c_one }
\__regex_query_get:
\__regex_match_loop:
\l__regex_every_match_tl
}
\cs_new_protected_nopar:Npn \__regex_single_match:
{
\tl_set:Nn \l__regex_every_match_tl
{ \bool_gset_eq:NN \g__regex_success_bool \l__regex_match_success_bool }
}
\cs_new_protected:Npn \__regex_multi_match:n #1
{
\tl_set:Nn \l__regex_every_match_tl
{
\if_meaning:w \c_true_bool \l__regex_match_success_bool
\bool_gset_true:N \g__regex_success_bool
#1
\exp_after:wN \__regex_match_once:
\fi:
}
}
\cs_new_protected_nopar:Npn \__regex_match_loop:
{
\tex_advance:D \l__regex_step_int \c_two
\int_incr:N \l__regex_current_pos_int
\int_set_eq:NN \l__regex_last_char_int \l__regex_current_char_int
\int_set_eq:NN \l__regex_case_changed_char_int \c_max_int
\__regex_query_get:
\use:x
{
\int_set_eq:NN \l__regex_max_active_int \l__regex_min_active_int
\exp_after:wN \__regex_match_one_active:w
\int_use:N \l__regex_min_active_int ;
}
\__prg_break_point:
\bool_set_false:N \l__regex_fresh_thread_bool %^^A was arg of break_point:n
\if_int_compare:w \l__regex_max_active_int > \l__regex_min_active_int
\if_int_compare:w \l__regex_current_pos_int < \l__regex_max_pos_int
\exp_after:wN \exp_after:wN \exp_after:wN \__regex_match_loop:
\fi:
\fi:
}
\cs_new:Npn \__regex_match_one_active:w #1;
{
\if_int_compare:w #1 < \l__regex_max_active_int
\__regex_use_state_and_submatches:nn
{ \__int_value:w \tex_skip:D #1 }
{ \tex_the:D \tex_toks:D #1 }
\exp_after:wN \__regex_match_one_active:w
\int_use:N \__int_eval:w #1 + \c_one \exp_after:wN ;
\fi:
}
\cs_new_protected:Npn \__regex_query_set:nnn #1#2#3
{
\tex_muskip:D \l__regex_current_pos_int
= \etex_gluetomu:D
#3 sp
plus #2 sp
minus \l__regex_balance_int sp
\scan_stop:
\tex_toks:D \l__regex_current_pos_int {#1}
\int_incr:N \l__regex_current_pos_int
\if_case:w #2 \exp_stop_f:
\or: \int_incr:N \l__regex_balance_int
\or: \int_decr:N \l__regex_balance_int
\fi:
}
\cs_new_protected_nopar:Npn \__regex_query_get:
{
\l__regex_current_char_int
= \etex_mutoglue:D \tex_muskip:D \l__regex_current_pos_int
\l__regex_current_catcode_int = \etex_gluestretch:D
\etex_mutoglue:D \tex_muskip:D \l__regex_current_pos_int
}
\cs_new_protected_nopar:Npn \__regex_use_state:
{
\tex_dimen:D \l__regex_current_state_int
= \l__regex_step_int sp \scan_stop:
\tex_the:D \tex_toks:D \l__regex_current_state_int
\tex_dimen:D \l__regex_current_state_int
= \__int_eval:w \l__regex_step_int + \c_one \__int_eval_end: sp \scan_stop:
}
\cs_new_protected:Npn \__regex_use_state_and_submatches:nn #1 #2
{
\int_set:Nn \l__regex_current_state_int {#1}
\if_int_compare:w \tex_dimen:D \l__regex_current_state_int
< \l__regex_step_int
\tl_set:Nn \l__regex_current_submatches_prop {#2}
\exp_after:wN \__regex_use_state:
\fi:
\scan_stop:
}
\cs_new_protected_nopar:Npn \__regex_action_start_wildcard:
{
\bool_set_true:N \l__regex_fresh_thread_bool
\__regex_action_free:n {1}
\bool_set_false:N \l__regex_fresh_thread_bool
\__regex_action_cost:n {0}
}
\cs_new_protected_nopar:Npn \__regex_action_free:n
{ \__regex_action_free_aux:nn { > \l__regex_step_int \else: } }
\cs_new_protected_nopar:Npn \__regex_action_free_group:n
{ \__regex_action_free_aux:nn { < \l__regex_step_int } }
\cs_new_protected:Npn \__regex_action_free_aux:nn #1#2
{
\use:x
{
\int_add:Nn \l__regex_current_state_int {#2}
\exp_not:n
{
\if_int_compare:w \tex_dimen:D \l__regex_current_state_int #1
\exp_after:wN \__regex_use_state:
\fi:
}
\int_set:Nn \l__regex_current_state_int
{ \int_use:N \l__regex_current_state_int }
\tl_set:Nn \exp_not:N \l__regex_current_submatches_prop
{ \exp_not:o \l__regex_current_submatches_prop }
}
}
\cs_new_protected:Npn \__regex_action_cost:n #1
{
\exp_args:No \__regex_store_state:n
{ \int_use:N \__int_eval:w \l__regex_current_state_int + #1 }
}
\cs_new_protected:Npn \__regex_store_state:n #1
{
\__regex_store_submatches:
\tex_skip:D \l__regex_max_active_int = #1 sp \scan_stop:
\int_incr:N \l__regex_max_active_int
}
\cs_new_protected_nopar:Npn \__regex_store_submatches:
{
\tex_toks:D \l__regex_max_active_int \exp_after:wN
{ \l__regex_current_submatches_prop }
}
\cs_new_protected_nopar:Npn \__regex_disable_submatches:
{
\cs_set_protected_nopar:Npn \__regex_store_submatches: { }
\cs_set_protected:Npn \__regex_action_submatch:n ##1 { }
}
\cs_new_protected:Npn \__regex_action_submatch:n #1
{
\prop_put:Nno \l__regex_current_submatches_prop {#1}
{ \int_use:N \l__regex_current_pos_int }
}
\cs_new_protected_nopar:Npn \__regex_action_success:
{
\__regex_if_two_empty_matches:F
{
\bool_set_true:N \l__regex_match_success_bool
\bool_set_eq:NN \l__regex_empty_success_bool
\l__regex_fresh_thread_bool
\int_set_eq:NN \l__regex_success_pos_int \l__regex_current_pos_int
\prop_set_eq:NN \l__regex_success_submatches_prop
\l__regex_current_submatches_prop
\__prg_break:
}
}
\int_new:N \l__regex_replacement_csnames_int
\tl_new:N \l__regex_balance_tl
\cs_new:Npn \__regex_replacement_balance_one_match:n #1
{ - \__regex_submatch_balance:n {#1} }
\cs_new:Npn \__regex_replacement_do_one_match:n #1
{
\__regex_query_range:nn
{ \etex_glueshrink:D \tex_skip:D #1 }
{ \tex_skip:D #1 }
}
\cs_new:Npn \__regex_replacement_exp_not:N #1 { \exp_not:n {#1} }
\cs_new:Npn \__regex_query_range:nn #1#2
{
\exp_after:wN \__regex_query_range_loop:ww
\int_use:N \__int_eval:w #1 \exp_after:wN ;
\int_use:N \__int_eval:w #2 ;
\__prg_break_point:
}
\cs_new:Npn \__regex_query_range_loop:ww #1 ; #2 ;
{
\if_int_compare:w #1 < #2 \exp_stop_f:
\else:
\exp_after:wN \__prg_break:
\fi:
\tex_the:D \tex_toks:D #1 \exp_stop_f:
\exp_after:wN \__regex_query_range_loop:ww
\int_use:N \__int_eval:w #1 + \c_one ; #2 ;
}
\cs_new:Npn \__regex_query_submatch:n #1
{
\__regex_query_range:nn
{ \tex_skip:D \__int_eval:w #1 }
{ \etex_gluestretch:D \tex_skip:D \__int_eval:w #1 }
}
\cs_new_protected:Npn \__regex_submatch_balance:n #1
{
\etex_glueshrink:D \etex_mutoglue:D \etex_muexpr:D
\tex_muskip:D \etex_gluestretch:D \tex_skip:D #1
- \tex_muskip:D \tex_skip:D #1
\scan_stop:
}
\cs_new_protected:Npn \__regex_replacement:n #1
{
\__tl_build:Nw \l__regex_internal_a_tl
\int_zero:N \l__regex_balance_int
\tl_clear:N \l__regex_balance_tl
\__regex_escape_use:nnnn
{
\if_charcode:w \c_right_brace_str ##1
\__regex_replacement_rbrace:N \else: \__tl_build_one:n \fi: ##1
}
{ \__regex_replacement_escaped:N ##1 }
{ \__tl_build_one:n ##1 }
{#1}
\prg_do_nothing: \prg_do_nothing:
\if_int_compare:w \l__regex_replacement_csnames_int > \c_zero
\__msg_kernel_error:nnx { regex } { replacement-missing-rbrace }
{ \int_use:N \l__regex_replacement_csnames_int }
\__tl_build_one:x
{ \prg_replicate:nn \l__regex_replacement_csnames_int \cs_end: }
\fi:
\cs_gset:Npx \__regex_replacement_balance_one_match:n ##1
{
+ \int_use:N \l__regex_balance_int
\l__regex_balance_tl
- \__regex_submatch_balance:n {##1}
}
\__tl_build_end:
\exp_args:No \__regex_replacement_aux:n \l__regex_internal_a_tl
}
\cs_new_protected:Npn \__regex_replacement_aux:n #1
{
\cs_set:Npn \__regex_replacement_do_one_match:n ##1
{
\__regex_query_range:nn
{ \etex_glueshrink:D \tex_skip:D ##1 }
{ \tex_skip:D ##1 }
#1
}
}
\cs_new_protected:Npn \__regex_replacement_escaped:N #1
{
\cs_if_exist_use:cF { __regex_replacement_#1:w }
{
\if_int_compare:w \c_one < 1#1 \exp_stop_f:
\__regex_replacement_put_submatch:n {#1}
\else:
\__tl_build_one:n #1
\fi:
}
}
\cs_new_protected:Npn \__regex_replacement_put_submatch:n #1
{
\if_int_compare:w #1 < \l__regex_capturing_group_int
\__tl_build_one:n { \__regex_query_submatch:n { #1 + ##1 } }
\if_int_compare:w \l__regex_replacement_csnames_int = \c_zero
\tl_put_right:Nn \l__regex_balance_tl
{ + \__regex_submatch_balance:n { \__int_eval:w #1+##1 \__int_eval_end: } }
\fi:
\fi:
}
\cs_new_protected:Npn \__regex_replacement_g:w #1#2
{
\str_if_eq_x:nnTF { #1#2 } { \__tl_build_one:n \c_left_brace_str }
{
\int_zero:N \l__regex_internal_a_int
\__regex_replacement_g_digits:NN
}
{ \__regex_replacement_error:NNN g #1 #2 }
}
\cs_new_protected:Npn \__regex_replacement_g_digits:NN #1#2
{
\token_if_eq_meaning:NNTF #1 \__tl_build_one:n
{
\if_int_compare:w \c_one < 1#2 \exp_stop_f:
\int_set:Nn \l__regex_internal_a_int
{ \c_ten * \l__regex_internal_a_int + #2 }
\exp_after:wN \use_i:nnn
\exp_after:wN \__regex_replacement_g_digits:NN
\else:
\exp_after:wN \__regex_replacement_error:NNN
\exp_after:wN g
\fi:
}
{
\if_meaning:w \__regex_replacement_rbrace:N #1
\exp_args:No \__regex_replacement_put_submatch:n
{ \int_use:N \l__regex_internal_a_int }
\exp_after:wN \use_none:nn
\else:
\exp_after:wN \__regex_replacement_error:NNN
\exp_after:wN g
\fi:
}
#1 #2
}
\cs_new_protected:Npn \__regex_replacement_c:w #1#2
{
\token_if_eq_meaning:NNTF #1 \__tl_build_one:n
{
\cs_if_exist_use:cF { __regex_replacement_c_#2:w }
{ \__regex_replacement_error:NNN c #1#2 }
}
{ \__regex_replacement_error:NNN c #1#2 }
}
\cs_new_protected_nopar:cpn { __regex_replacement_c_ \c_left_brace_str :w }
{
\if_case:w \l__regex_replacement_csnames_int
\__tl_build_one:n
{ \exp_not:n { \exp_after:wN \__regex_replacement_exp_not:N \cs:w } }
\else:
\__tl_build_one:n { \exp_not:n { \exp_after:wN \tl_to_str:N \cs:w } }
\fi:
\int_incr:N \l__regex_replacement_csnames_int
}
\cs_new_protected:Npn \__regex_replacement_u:w #1#2
{
\str_if_eq_x:nnTF { #1#2 } { \__tl_build_one:n \c_left_brace_str }
{
\if_case:w \l__regex_replacement_csnames_int
\__tl_build_one:n { \exp_not:n { \exp_after:wN \exp_not:V \cs:w } }
\else:
\__tl_build_one:n { \exp_not:n { \exp_after:wN \tl_to_str:V \cs:w } }
\fi:
\int_incr:N \l__regex_replacement_csnames_int
}
{ \__regex_replacement_error:NNN u #1#2 }
}
\cs_new_protected:Npn \__regex_replacement_rbrace:N #1
{
\if_int_compare:w \l__regex_replacement_csnames_int > \c_zero
\__tl_build_one:n \cs_end:
\int_decr:N \l__regex_replacement_csnames_int
\else:
\__tl_build_one:n #1
\fi:
}
\group_begin:
\cs_new_protected:Npn \__regex_replacement_char:nNN #1#2#3
{
\if_meaning:w \prg_do_nothing: #3
\__msg_kernel_error:nn { regex } { replacement-catcode-end }
\else:
\tex_lccode:D \c_zero = `#3 \scan_stop:
\tl_to_lowercase:n { \__tl_build_one:n {#1} }
\fi:
}
\char_set_catcode_active:N \^^@
\cs_new_protected_nopar:Npn \__regex_replacement_c_A:w
{ \__regex_replacement_char:nNN { \exp_not:n { \exp_not:N ^^@ } } }
\char_set_catcode_group_begin:N \^^@
\cs_new_protected_nopar:Npn \__regex_replacement_c_B:w
{
\if_int_compare:w \l__regex_replacement_csnames_int = \c_zero
\int_incr:N \l__regex_balance_int
\fi:
\__regex_replacement_char:nNN
{ \exp_not:n { \exp_after:wN ^^@ \if_false: } \fi: } }
}
\cs_new_protected:Npn \__regex_replacement_c_C:w #1#2
{ \__tl_build_one:n { \exp_not:N \exp_not:N \exp_not:c {#2} } }
\char_set_catcode_math_subscript:N \^^@
\cs_new_protected_nopar:Npn \__regex_replacement_c_D:w
{ \__regex_replacement_char:nNN { ^^@ } }
\char_set_catcode_group_end:N \^^@
\cs_new_protected_nopar:Npn \__regex_replacement_c_E:w
{
\if_int_compare:w \l__regex_replacement_csnames_int = \c_zero
\int_decr:N \l__regex_balance_int
\fi:
\__regex_replacement_char:nNN
{ \exp_not:n { \if_false: { \fi: ^^@ } }
}
\char_set_catcode_letter:N \^^@
\cs_new_protected_nopar:Npn \__regex_replacement_c_L:w
{ \__regex_replacement_char:nNN { ^^@ } }
\char_set_catcode_math_toggle:N \^^@
\cs_new_protected_nopar:Npn \__regex_replacement_c_M:w
{ \__regex_replacement_char:nNN { ^^@ } }
\char_set_catcode_other:N \^^@
\cs_new_protected_nopar:Npn \__regex_replacement_c_O:w
{ \__regex_replacement_char:nNN { ^^@ } }
\char_set_catcode_parameter:N \^^@
\cs_new_protected_nopar:Npn \__regex_replacement_c_P:w
{
\__regex_replacement_char:nNN
{ \exp_not:n { \exp_not:n { ^^@^^@^^@^^@ } } }
}
\cs_new_protected:Npn \__regex_replacement_c_S:w #1#2
{
\if_meaning:w \prg_do_nothing: #2
\__msg_kernel_error:nn { regex } { replacement-catcode-end }
\else:
\if_int_compare:w `#2 = \c_zero
\__msg_kernel_error:nn { regex } { replacement-null-space }
\fi:
\tex_lccode:D 32 = `#2 \scan_stop:
\tl_to_lowercase:n { \__tl_build_one:n {~} }
\fi:
}
\char_set_catcode_alignment:N \^^@
\cs_new_protected_nopar:Npn \__regex_replacement_c_T:w
{ \__regex_replacement_char:nNN { ^^@ } }
\char_set_catcode_math_superscript:N \^^@
\cs_new_protected_nopar:Npn \__regex_replacement_c_U:w
{ \__regex_replacement_char:nNN { ^^@ } }
\group_end:
\cs_new_protected:Npn \__regex_replacement_error:NNN #1#2#3
{
\__msg_kernel_error:nnx { regex } { replacement-#1 } {#3}
#2 #3
}
\cs_new_protected:Npn \regex_new:N #1
{ \cs_new_eq:NN #1 \c__regex_no_match_regex }
\cs_new_protected_nopar:Npn \regex_set:Nn #1#2
{
\__regex_compile:n {#2}
\tl_set_eq:NN #1 \l__regex_internal_regex
}
\cs_new_protected_nopar:Npn \regex_gset:Nn #1#2
{
\__regex_compile:n {#2}
\tl_gset_eq:NN #1 \l__regex_internal_regex
}
\cs_new_protected_nopar:Npn \regex_const:Nn #1#2
{
\__regex_compile:n {#2}
\tl_const:Nx #1 { \exp_not:o \l__regex_internal_regex }
}
\cs_new_protected:Npn \regex_show:n #1
{
\__regex_compile:n {#1}
\__regex_show:Nx \l__regex_internal_regex
{ { \tl_to_str:n {#1} } }
}
\cs_new_protected:Npn \regex_show:N #1
{ \__regex_show:Nx #1 { variable~\token_to_str:N #1 } }
\prg_new_protected_conditional:Npnn \regex_match:nn #1#2 { T , F , TF }
{
\__regex_if_match:nn { \__regex_build:n {#1} } {#2}
\__regex_return:
}
\prg_new_protected_conditional:Npnn \regex_match:Nn #1#2 { T , F , TF }
{
\__regex_if_match:nn { \__regex_build:N #1 } {#2}
\__regex_return:
}
\cs_new_protected:Npn \regex_count:nnN #1
{ \__regex_count:nnN { \__regex_build:n {#1} } }
\cs_new_protected:Npn \regex_count:NnN #1
{ \__regex_count:nnN { \__regex_build:N #1 } }
\cs_set_protected:Npn \__regex_tmp:w #1#2#3
{
\cs_new_protected:Npn #2 ##1 { #1 { \__regex_build:n {##1} } }
\cs_new_protected:Npn #3 ##1 { #1 { \__regex_build:N ##1 } }
\prg_new_protected_conditional:Npnn #2 ##1##2##3 { T , F , TF }
{ #1 { \__regex_build:n {##1} } {##2} ##3 \__regex_return: }
\prg_new_protected_conditional:Npnn #3 ##1##2##3 { T , F , TF }
{ #1 { \__regex_build:N ##1 } {##2} ##3 \__regex_return: }
}
\__regex_tmp:w \__regex_extract_once:nnN
\regex_extract_once:nnN \regex_extract_once:NnN
\__regex_tmp:w \__regex_extract_all:nnN
\regex_extract_all:nnN \regex_extract_all:NnN
\__regex_tmp:w \__regex_replace_once:nnN
\regex_replace_once:nnN \regex_replace_once:NnN
\__regex_tmp:w \__regex_replace_all:nnN
\regex_replace_all:nnN \regex_replace_all:NnN
\__regex_tmp:w \__regex_split:nnN \regex_split:nnN \regex_split:NnN
\int_new:N \l__regex_match_count_int
\flag_new:n { __regex_begin }
\flag_new:n { __regex_end }
\int_new:N \l__regex_submatch_int
\int_new:N \l__regex_zeroth_submatch_int
\cs_new_protected_nopar:Npn \__regex_return:
{
\if_meaning:w \c_true_bool \g__regex_success_bool
\prg_return_true:
\else:
\prg_return_false:
\fi:
}
\cs_new_protected:Npn \__regex_if_match:nn #1#2
{
\group_begin:
\__regex_disable_submatches:
\__regex_single_match:
#1
\__regex_match:n {#2}
\group_end:
}
\cs_new_protected:Npn \__regex_count:nnN #1#2#3
{
\group_begin:
\__regex_disable_submatches:
\int_zero:N \l__regex_match_count_int
\__regex_multi_match:n { \int_incr:N \l__regex_match_count_int }
#1
\__regex_match:n {#2}
\exp_args:NNNo
\group_end:
\int_set:Nn #3 { \int_use:N \l__regex_match_count_int }
}
\cs_new_protected:Npn \__regex_extract_once:nnN #1#2#3
{
\group_begin:
\__regex_single_match:
#1
\__regex_match:n {#2}
\__regex_extract:
\__regex_group_end_extract_seq:N #3
}
\cs_new_protected:Npn \__regex_extract_all:nnN #1#2#3
{
\group_begin:
\__regex_multi_match:n { \__regex_extract: }
#1
\__regex_match:n {#2}
\__regex_group_end_extract_seq:N #3
}
\cs_new_protected:Npn \__regex_split:nnN #1#2#3
{
\group_begin:
\__regex_multi_match:n
{
\if_int_compare:w \l__regex_start_pos_int < \l__regex_success_pos_int
\__regex_extract:
\tex_skip:D \l__regex_zeroth_submatch_int
= \l__regex_start_pos_int sp
plus \tex_skip:D \l__regex_zeroth_submatch_int \scan_stop:
\fi:
}
#1
\__regex_match:n {#2}
\tex_skip:D \l__regex_submatch_int
= \l__regex_start_pos_int sp plus \l__regex_max_pos_int sp \scan_stop:
\int_incr:N \l__regex_submatch_int
\if_meaning:w \c_true_bool \l__regex_empty_success_bool
\if_int_compare:w \l__regex_start_pos_int = \l__regex_max_pos_int
\int_decr:N \l__regex_submatch_int
\fi:
\fi:
\__regex_group_end_extract_seq:N #3
}
\cs_new_protected:Npn \__regex_group_end_extract_seq:N #1
{
\cs_set_eq:NN \__seq_item:n \scan_stop:
\flag_clear:n { __regex_begin }
\flag_clear:n { __regex_end }
\tl_set:Nx \l__regex_internal_a_tl
{
\int_step_function:nnnN
{ \c_two * \l__regex_max_state_int }
\c_one
{ \l__regex_submatch_int - \c_one }
\__regex_extract_seq_aux:n
}
\int_compare:nNnF
{ \flag_height:n { __regex_begin } + \flag_height:n { __regex_end } }
= \c_zero
{
\__msg_kernel_error:nnxxx { regex } { result-unbalanced }
{ splitting~or~extracting~submatches }
{ \flag_height:n { __regex_end } }
{ \flag_height:n { __regex_begin } }
}
\use:x
{
\group_end:
\tl_set:Nn \exp_not:N #1 { \l__regex_internal_a_tl }
}
}
\cs_new:Npn \__regex_extract_seq_aux:n #1
{
\__seq_item:n
{
\exp_after:wN \__regex_extract_seq_aux:ww
\__int_value:w \__regex_submatch_balance:n {#1} ; #1;
}
}
\cs_new:Npn \__regex_extract_seq_aux:ww #1; #2;
{
\if_int_compare:w #1 < \c_zero
\flag_raise:n { __regex_end }
\prg_replicate:nn {-#1} { \exp_not:n { { \if_false: } \fi: } }
\fi:
\__regex_query_submatch:n {#2}
\if_int_compare:w #1 > \c_zero
\flag_raise:n { __regex_begin }
\prg_replicate:nn {#1} { \exp_not:n { \if_false: { \fi: } } }
\fi:
}
\cs_new_protected_nopar:Npn \__regex_extract:
{
\if_meaning:w \c_true_bool \g__regex_success_bool
\int_set_eq:NN \l__regex_zeroth_submatch_int \l__regex_submatch_int
\prg_replicate:nn \l__regex_capturing_group_int
{
\tex_skip:D \l__regex_submatch_int \c_zero sp \scan_stop:
\int_incr:N \l__regex_submatch_int
}
\prop_map_inline:Nn \l__regex_success_submatches_prop
{
\if_int_compare:w ##1 \c_minus_one
\exp_after:wN \__regex_extract_e:wn \__int_value:w
\else:
\exp_after:wN \__regex_extract_b:wn \__int_value:w
\fi:
\__int_eval:w \l__regex_zeroth_submatch_int + ##1 {##2}
}
\tex_skip:D \l__regex_zeroth_submatch_int
= \tex_the:D \tex_skip:D \l__regex_zeroth_submatch_int
minus \l__regex_start_pos_int sp \scan_stop:
\fi:
}
\cs_new_protected:Npn \__regex_extract_b:wn #1 < #2
{
\tex_skip:D #1 = #2 sp
plus \etex_gluestretch:D \tex_skip:D #1 \scan_stop:
}
\cs_new_protected:Npn \__regex_extract_e:wn #1 > #2
{
\tex_skip:D #1
= 1 \tex_skip:D #1 plus #2 sp \scan_stop:
}
\cs_new_protected:Npn \__regex_replace_once:nnN #1#2#3
{
\group_begin:
\__regex_single_match:
#1
\__regex_replacement:n {#2}
\exp_args:No \__regex_match:n { #3 }
\if_meaning:w \c_false_bool \g__regex_success_bool
\group_end:
\else:
\__regex_extract:
\int_set:Nn \l__regex_balance_int
{
\__regex_replacement_balance_one_match:n
{ \l__regex_zeroth_submatch_int }
}
\tl_set:Nx \l__regex_internal_a_tl
{
\__regex_replacement_do_one_match:n { \l__regex_zeroth_submatch_int }
\__regex_query_range:nn
{ \etex_gluestretch:D \tex_skip:D \l__regex_zeroth_submatch_int }
{ \l__regex_max_pos_int }
}
\__regex_group_end_replace:N #3
\fi:
}
\cs_new_protected:Npn \__regex_replace_all:nnN #1#2#3
{
\group_begin:
\__regex_multi_match:n { \__regex_extract: }
#1
\__regex_replacement:n {#2}
\exp_args:No \__regex_match:n {#3}
\int_set:Nn \l__regex_balance_int
{
0
\int_step_function:nnnN
{ \c_two * \l__regex_max_state_int }
\l__regex_capturing_group_int
{ \l__regex_submatch_int - \c_one }
\__regex_replacement_balance_one_match:n
}
\tl_set:Nx \l__regex_internal_a_tl
{
\int_step_function:nnnN
{ \c_two * \l__regex_max_state_int }
\l__regex_capturing_group_int
{ \l__regex_submatch_int - \c_one }
\__regex_replacement_do_one_match:n
\__regex_query_range:nn
\l__regex_start_pos_int \l__regex_max_pos_int
}
\__regex_group_end_replace:N #3
}
\cs_new_protected_nopar:Npn \__regex_group_end_replace:N #1
{
\if_int_compare:w \l__regex_balance_int = \c_zero
\else:
\__msg_kernel_error:nnxxx { regex } { result-unbalanced }
{ replacing }
{ \int_max:nn { - \l__regex_balance_int } { \c_zero } }
{ \int_max:nn { \l__regex_balance_int } { \c_zero } }
\fi:
\use:x
{
\group_end:
\tl_set:Nn \exp_not:N #1
{
\if_int_compare:w \l__regex_balance_int < \c_zero
\prg_replicate:nn { - \l__regex_balance_int }
{ { \if_false: } \fi: }
\fi:
\l__regex_internal_a_tl
\if_int_compare:w \l__regex_balance_int > \c_zero
\prg_replicate:nn { \l__regex_balance_int }
{ \if_false: { \fi: } }
\fi:
}
}
}
\__msg_kernel_new:nnnn { regex } { trailing-backslash }
{ Trailing~escape~character~\iow_char:N\\. }
{
A~regular~expression~or~its~replacement~text~ends~with~
the~escape~character~\iow_char:N\\.~It~will~be~ignored.
}
\__msg_kernel_new:nnnn { regex } { x-missing-rbrace }
{ Missing~closing~brace~in~\iow_char:N\\x~hexadecimal~sequence. }
{
You~wrote~something~like~
`\iow_char:N\\x\{\int_to_hexadecimal:n{#1}'.~
The~closing~brace~is~missing.
}
\__msg_kernel_new:nnnn { regex } { x-overflow }
{ Character~code~'#1'~too~large~in~\iow_char:N\\x~hexadecimal~sequence. }
{
You~wrote~something~like~
`\iow_char:N\\x\{\int_to_hexadecimal:n{#1}\}'.~
The~character~code~'#1'~is~larger~than~\int_use:N \c_max_char_int.
}
\__msg_kernel_new:nnnn { regex } { invalid-quantifier }
{ Braced~quantifier~'#1'~may~not~be~followed~by~'#2'. }
{
The~character~'#2'~is~invalid~in~the~braced~quantifier~'#1'.~
The~only~valid~quantifiers~are~'*',~'?',~'+',~'{<int>}',~
'{<min>,}'~and~'{<min>,<max>}',~followed~or~not~by~'?'.
}
\__msg_kernel_new:nnnn { regex } { missing-rbrack }
{ Missing~right~bracket~inserted~in~regular~expression. }
{
LaTeX~was~given~a~regular~expression~where~a~character~class~
was~started~with~'[',~but~the~matching~']'~is~missing.
}
\__msg_kernel_new:nnnn { regex } { missing-rparen }
{
Missing~right~parenthes\int_compare:nTF{#1=1}{i}{e}s~
inserted~in~regular~expression.
}
{
LaTeX~was~given~a~regular~expression~with~\int_eval:n{#1}~
more~left~parenthes\int_compare:nTF{#1=1}{i}{e}s~than~right~
parenthes\int_compare:nTF{#1=1}{i}{e}s.
}
\__msg_kernel_new:nnnn { regex } { extra-rparen }
{ Extra~right~parenthesis~ignored~in~regular~expression. }
{
LaTeX~came~across~a~closing~parenthesis~when~no~submatch~group~
was~open.~The~parenthesis~will~be~ignored.
}
\__msg_kernel_new:nnnn { regex } { bad-escape }
{
Invalid~escape~\c_backslash_str #1~
\__regex_if_in_cs:TF { within~a~control~sequence. }
{
\__regex_if_in_class:TF
{ in~a~character~class. }
{ following~a~category~test. }
}
}
{
The~escape~sequence~\iow_char:N\\#1~may~not~appear~
\__regex_if_in_cs:TF
{
within~a~control~sequence~test~introduced~by~
\iow_char:N\\c\iow_char:N\{.
}
{
\__regex_if_in_class:TF
{ within~a~character~class~ }
{ following~a~category~test~such~as~\iow_char:N\\cL~ }
because~it~does~not~match~exactly~one~character.
}
}
\__msg_kernel_new:nnnn { regex } { range-missing-end }
{ Invalid~end-point~for~range~'#1-#2'~in~character~class. }
{
The~end-point~'#2'~of~the~range~'#1-#2'~may~not~serve~as~an~
end-point~for~a~range:~alphanumeric~characters~should~not~be~
escaped,~and~non-alphanumeric~characters~should~be~escaped.
}
\__msg_kernel_new:nnnn { regex } { range-backwards }
{ Range~[#1-#2]~out~of~order~in~character~class. }
{
In~ranges~of~characters~[x-y]~appearing~in~character~classes,~
the~first~character~code~must~not~be~larger~than~the~second.~
Here,~#1~has~character~code~\int_eval:n {`#1},~while~#2~has~
character~code~\int_eval:n {`#2}.
}
\__msg_kernel_new:nnnn { regex } { c-bad-mode }
{ Invalid~nested~\iow_char:N\\c~escape~in~regular~expression. }
{
The~\iow_char:N\\c~escape~cannot~be~used~within~
a~control~sequence~test~'\iow_char:N\\c{...}'.~
To~combine~several~category~tests,~use~'\iow_char:N\\c[...]'.
}
\__msg_kernel_new:nnnn { regex } { c-missing-rbrace }
{ Missing~right~brace~inserted~for~\iow_char:N\\c~escape. }
{
LaTeX~was~given~a~regular~expression~where~a~
'\iow_char:N\\c\iow_char:N\{...'~construction~was~not~ended~
with~a~closing~brace~'\iow_char:N\}'.
}
\__msg_kernel_new:nnnn { regex } { c-missing-rbrack }
{ Missing~right~bracket~inserted~for~\iow_char:N\\c~escape. }
{
A~construction~'\iow_char:N\\c[...'~appears~in~a~
regular~expression,~but~the~closing~']'~is~not~present.
}
\__msg_kernel_new:nnnn { regex } { c-missing-category }
{ Invalid~character~'#1'~following~\iow_char:N\\c~escape. }
{
In~regular~expressions,~the~\iow_char:N\\c~escape~sequence~
may~only~be~followed~by~a~left~brace,~a~left~bracket,~or~a~
capital~letter~representing~a~character~category,~namely~
one~of~ABCDELMOPSTU.
}
\__msg_kernel_new:nnnn { regex } { u-missing-lbrace }
{ Missing~left~brace~following~\iow_char:N\\u~escape. }
{
The~\iow_char:N\\u~escape~sequence~must~be~followed~by~
a~brace~group~with~the~name~of~the~variable~to~use.
}
\__msg_kernel_new:nnnn { regex } { u-missing-rbrace }
{ Missing~right~brace~inserted~for~\iow_char:N\\u~escape. }
{
LaTeX~
\str_if_eq_x:nnTF { } {#2}
{ reached~the~end~of~the~string~ }
{ encountered~an~escaped~alphanumeric~character '\iow_char:N\\#2'~ }
when~parsing~the~argument~of~an~'\iow_char:N\\u\iow_char:N\{...\}'~escape.
}
\__msg_kernel_new:nnnn { regex } { posix-unsupported }
{ POSIX~collating~element~'[#1 ~ #1]'~not~supported. }
{
The~[.foo.]~and~[=bar=]~syntaxes~have~a~special~meaning~in~POSIX~
regular~expressions.~This~is~not~supported~by~LaTeX.~Maybe~you~
forgot~to~escape~a~left~bracket~in~a~character~class?
}
\__msg_kernel_new:nnnn { regex } { posix-unknown }
{ POSIX~class~[:#1:]~unknown. }
{
[:#1:]~is~not~among~the~known~POSIX~classes~
[:alnum:],~[:alpha:],~[:ascii:],~[:blank:],~
[:cntrl:],~[:digit:],~[:graph:],~[:lower:],~
[:print:],~[:punct:],~[:space:],~[:upper:],~
[:word:],~and~[:xdigit:].
}
\__msg_kernel_new:nnnn { regex } { posix-missing-close }
{ Missing~closing~':]'~for~POSIX~class. }
{ The~POSIX~syntax~'#1'~must~be~followed~by~':]',~not~'#2'. }
\__msg_kernel_new:nnnn { regex } { result-unbalanced }
{ Missing~brace~inserted~when~#1. }
{
LaTeX~was~asked~to~do~some~regular~expression~operation,~
and~the~resulting~token~list~would~not~have~the~same~number~
of~begin-group~and~end-group~tokens.~Braces~were~inserted:~
#2~left,~#3~right.
}
\__msg_kernel_new:nnnn { regex } { unknown-option }
{ Unknown~option~`#1'~for~regular~expressions. }
{
The~only~available~option~is~'case-insensitive',~toggled~by~
'(?i)'~and~'(?-i)'.
}
\__msg_kernel_new:nnnn { regex } { replacement-c }
{ Misused~\iow_char:N\\c~command~in~a~replacement~text. }
{
In~a~replacement~text,~the~\iow_char:N\\c~escape~sequence~
can~be~followed~by~one~of~the~letters~ABCDELMOPSTU~
or~a~brace~group,~not~by~'#1'.
}
\__msg_kernel_new:nnnn { regex } { replacement-u }
{ Misused~\iow_char:N\\u~command~in~a~replacement~text. }
{
In~a~replacement~text,~the~\iow_char:N\\u~escape~sequence~
must~be~~followed~by~a~brace~group~holding~the~name~of~the~
variable~to~use.
}
\__msg_kernel_new:nnnn { regex } { replacement-g }
{ Missing~brace~for~the~\iow_char:N\\g~construction~in~a~replacement~text. }
{
In~the~replacement~text~for~a~regular~expression~search,~
submatches~are~represented~either~as~\iow_char:N \\g{dd..d},~
or~\\d,~where~`d'~are~single~digits.~Here,~a~brace~is~missing.
}
\__msg_kernel_new:nnnn { regex } { replacement-catcode-end }
{
Missing~character~for~the~\iow_char:N\\c<category><character>~
construction~in~a~replacement~text.
}
{
In~a~replacement~text,~the~\iow_char:N\\c~escape~sequence~
can~be~followed~by~one~of~the~letters~ABCDELMOPSTU~representing~
the~character~category.~Then,~a~character~must~follow.~LaTeX~
reached~the~end~of~the~replacement~when~looking~for~that.
}
\__msg_kernel_new:nnnn { regex } { replacement-null-space }
{ TeX~cannot~build~a~space~token~with~character~code~0. }
{
You~asked~for~a~character~token~with~category~'space',~
and~character~code~0,~for~instance~through~
'\iow_char:N\\cS\iow_char:N\\x00'.~
This~specific~case~is~impossible~and~will~be~replaced~
by~a~normal~space.
}
\__msg_kernel_new:nnnn { regex } { replacement-missing-rbrace }
{ Missing~right~brace~inserted~in~replacement~text. }
{
There~were~\int_use:N \l__regex_replacement_csnames_int \
missing~right~braces.
}
\cs_new:Npn \__regex_msg_repeated:nnN #1#2#3
{
\str_if_eq_x:nnF { #1 #2 } { 1 0 }
{
, ~ repeated ~
\int_case:nnn {#2}
{
{ -1 } { #1~or~more~times,~\bool_if:NTF #3 { lazy } { greedy } }
{ 0 } { #1~times }
}
{
between~#1~and~\int_eval:n {#1+#2}~times,~
\bool_if:NTF #3 { lazy } { greedy }
}
}
}
%%
%%
%% End of file `l3regex.sty'.
Zerion Mini Shell 1.0