summaryrefslogtreecommitdiff
path: root/Master/texmf-dist/tex/latex/l3experimental
diff options
context:
space:
mode:
authorKarl Berry <karl@freefriends.org>2011-11-25 00:13:53 +0000
committerKarl Berry <karl@freefriends.org>2011-11-25 00:13:53 +0000
commitffc8e17b8078900ab7932786f99a36a7f3b1166c (patch)
tree4e6b90567c8ee8bff06b06a3868c14b7e9f06eef /Master/texmf-dist/tex/latex/l3experimental
parent3c7032087650de924a1aead943de992a2c689248 (diff)
l3experimental 2966 (19nov11)
git-svn-id: svn://tug.org/texlive/trunk@24655 c570f23f-e606-0410-a88d-b1316a301751
Diffstat (limited to 'Master/texmf-dist/tex/latex/l3experimental')
-rw-r--r--Master/texmf-dist/tex/latex/l3experimental/l3str/l3regex-trace.sty1053
-rw-r--r--Master/texmf-dist/tex/latex/l3experimental/l3str/l3regex.sty1053
-rw-r--r--Master/texmf-dist/tex/latex/l3experimental/l3str/l3str.sty305
-rw-r--r--Master/texmf-dist/tex/latex/l3experimental/xcoffins/xcoffins.sty10
-rw-r--r--Master/texmf-dist/tex/latex/l3experimental/xgalley/l3galley.sty87
-rw-r--r--Master/texmf-dist/tex/latex/l3experimental/xgalley/xgalley.sty7
6 files changed, 1438 insertions, 1077 deletions
diff --git a/Master/texmf-dist/tex/latex/l3experimental/l3str/l3regex-trace.sty b/Master/texmf-dist/tex/latex/l3experimental/l3str/l3regex-trace.sty
index 29045fcdea9..07d568d94e9 100644
--- a/Master/texmf-dist/tex/latex/l3experimental/l3str/l3regex-trace.sty
+++ b/Master/texmf-dist/tex/latex/l3experimental/l3str/l3regex-trace.sty
@@ -46,113 +46,121 @@
%%
%% -----------------------------------------------------------------------
\RequirePackage{expl3}
-\GetIdInfo$Id: l3regex.dtx 2895 2011-10-09 15:58:19Z joseph $
+\GetIdInfo$Id: l3regex.dtx 2943 2011-10-30 15:59:43Z bruno $
{L3 Experimental Regular Expressions}
\ProvidesExplPackage
{\ExplFileName}{\ExplFileDate}{\ExplFileVersion}{\ExplFileDescription}
\RequirePackage{l3str}
+\int_const:Nn \c_forty_eight { 48 }
+\int_const:Nn \c_fifty_eight { 58 }
+\int_const:Nn \c_sixty_five { 65 }
+\int_const:Nn \c_ninety_one { 91 }
+\int_const:Nn \c_ninety_seven { 97 }
+\int_const:Nn \c_one_hundred_twenty_three { 123 }
+\int_const:Nn \c_one_hundred_twenty_seven { 127 }
\cs_new:Npn \regex_tmp:w { }
\tl_new:N \g_regex_tmpa_tl
\tl_new:N \l_regex_tmpa_tl
\tl_new:N \l_regex_tmpb_tl
\int_new:N \l_regex_tmpa_int
-\tl_new:N \l_regex_pattern_str
+\int_new:N \l_regex_tmpb_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
+\seq_new:N \l_regex_group_begin_seq
+\seq_new:N \l_regex_group_end_seq
\int_new:N \l_regex_capturing_group_int
\seq_new:N \l_regex_capturing_group_seq
\tl_new:N \l_regex_one_or_group_tl
-\int_new:N \l_regex_repetition_int
-\bool_new:N \l_regex_look_behind_bool
-\tl_new:N \l_regex_look_behind_str
\cs_new_eq:NN \regex_build_tmp_class:n \use_none:n
\bool_new:N \l_regex_class_bool
\tl_new:N \l_regex_class_tl
\tl_const:Nn \c_regex_d_tl
{
- \regex_item_range:nn {48} {57} % 0--9
+ \regex_item_range:nn { \c_forty_eight } { 57 } % 0--9
}
\tl_const:Nn \c_regex_D_tl
{
- \regex_item_more:n {57} % 9
- \regex_item_range:nn {0} {47} % 0
+ \regex_item_geq:n { \c_fifty_eight } % > `9
+ \regex_item_range:nn { \c_zero } { 47 } % 0
}
\tl_const:Nn \c_regex_h_tl
{
- \regex_item_equal:n {32} % space
- \regex_item_equal:n {9} % tab
+ \regex_item_equal:n { \c_thirty_two } % space
+ \regex_item_equal:n { \c_nine } % tab
}
\tl_const:Nn \c_regex_H_tl
{
- \regex_item_neq:n {32} % space
- \regex_item_neq:n {9} % tab
- \regex_break_true:w
+ \regex_item_geq:n { 33 } % > space
+ \regex_item_range:nn { \c_ten } { 31 } % tab < ... < space
+ \regex_item_range:nn { \c_zero } { \c_eight } % < tab
}
\tl_const:Nn \c_regex_s_tl
{
- \regex_item_equal:n {32} % space
- \regex_item_neq:n {11} % vtab
- \regex_item_range:nn {9} {13} % tab, lf, vtab, ff, cr
+ \regex_item_equal:n { \c_thirty_two } % space
+ \regex_item_range:nn { \c_nine } { \c_ten } % tab, lf
+ \regex_item_range:nn { \c_twelve } { \c_thirteen } % ff, cr
}
\tl_const:Nn \c_regex_S_tl
{
- \regex_item_more:n {32} % > space
- \regex_item_range:nn {14} {31} % tab < ... < space
- \regex_item_range:nn {0} {8} % < tab
- \regex_item_equal:n {11} % vtab
+ \regex_item_geq:n { 33 } % > space
+ \regex_item_range:nn { \c_fourteen } { 31 } % tab < ... < space
+ \regex_item_range:nn { \c_zero } { \c_eight } % < tab
+ \regex_item_equal:n { \c_eleven } % vtab
}
\tl_const:Nn \c_regex_v_tl
{
- \regex_item_range:nn {10} {13} % lf, vtab, ff, cr
+ \regex_item_range:nn { \c_ten } { \c_thirteen } % lf, vtab, ff, cr
}
\tl_const:Nn \c_regex_V_tl
{
- \regex_item_more:n {13} % cr
- \regex_item_range:nn {0} {9} % < lf
+ \regex_item_geq:n { \c_fourteen } % >cr
+ \regex_item_range:nn { \c_zero } { \c_nine } % < lf
}
\tl_const:Nn \c_regex_w_tl
{
- \regex_item_range:nn {97} {122} % a--z
- \regex_item_range:nn {65} {90} % A--Z
- \regex_item_range:nn {48} {57} % 0--9
- \regex_item_equal:n {95} % _
+ \regex_item_range:nn { \c_ninety_seven } { 122 } % a--z
+ \regex_item_range:nn { \c_sixty_five } { 90 } % A--Z
+ \regex_item_range:nn { \c_forty_eight } { 57 } % 0--9
+ \regex_item_equal:n { 95 } % _
}
\tl_const:Nn \c_regex_W_tl
{
- \regex_item_range:nn {0} {47} % <`0
- \regex_item_range:nn {58} {64} % (`9+1)--(`A-1)
- \regex_item_range:nn {91} {94} % (`Z+1)--(`_-1)
- \regex_item_equal:n {96} % `
- \regex_item_more:n {122} % z
+ \regex_item_range:nn { \c_zero } { 47 } % <`0
+ \regex_item_range:nn { \c_fifty_eight } { 64 } % (`9+1)--(`A-1)
+ \regex_item_range:nn { \c_ninety_one } { 94 } % (`Z+1)--(`_-1)
+ \regex_item_equal:n { 96 } % `
+ \regex_item_geq:n { \c_one_hundred_twenty_three } % z
}
\tl_const:Nn \c_regex_N_tl
{
- \regex_item_neq:n {10} % lf
- \regex_break_true:w
+ \regex_item_geq:n { \c_eleven } % > lf
+ \regex_item_range:nn { \c_zero } { \c_nine } % < lf
}
-\tl_new:N \l_regex_query_str
-\int_new:N \l_regex_start_step_int
-\int_new:N \l_regex_current_char_int
+\tl_new:N \l_regex_query_other_str
\int_new:N \l_regex_current_step_int
+\int_new:N \l_regex_start_step_int
+\int_new:N \l_regex_success_step_int
\int_new:N \l_regex_unique_step_int
+\int_new:N \l_regex_current_char_int
+\int_new:N \l_regex_last_char_int
+\int_new:N \l_regex_case_changed_char_int
+\bool_new:N \l_regex_caseless_bool
\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_max_index_int
\tl_new:N \l_regex_every_match_tl
+\bool_new:N \l_regex_success_bool
\cs_new_protected:Npn \regex_last_match_empty_no:F #1 {#1}
\cs_new_protected:Npn \regex_last_match_empty_yes:F
{ \int_compare:nNnF \l_regex_start_step_int = \l_regex_current_step_int }
\cs_new_eq:NN \regex_last_match_empty:F \regex_last_match_empty_no:F
-\bool_new:N \l_regex_success_bool
\bool_new:N \l_regex_success_empty_bool
-\int_new:N \l_regex_success_step_int
-\prop_new:N \l_regex_success_submatches_prop
\bool_new:N \l_regex_fresh_thread_bool
\seq_new:N \g_regex_submatches_seq
\int_new:N \g_regex_match_count_int
+\seq_new:N \g_regex_extract_all_seq
\seq_new:N \g_regex_split_seq
\tl_new:N \l_regex_replacement_tl
\tl_new:N \g_regex_replaced_str
@@ -169,40 +177,43 @@
\tex_toks:D #1 \exp_after:wN
{ \tex_the:D \tex_toks:D \exp_after:wN #1 \regex_tmp:w }
}
-\cs_new_eq:NN \regex_if_tail_stop:N \quark_if_recursion_tail_stop:N
-\cs_new_protected_nopar:Npn \regex_if_tail_error:Nn #1#2
- { \quark_if_recursion_tail_stop_do:Nn #1 { \regex_build_error:n {#2} } }
-\cs_new_protected_nopar:Npn \regex_build_error:n #1
+\cs_new_nopar:Npn \regex_query_substr:NN #1#2
{
- \msg_error:nnxx { regex } { build-error } {\int_eval:n{#1}}
- {
- \prg_case_int:nnn {#1}
- {
- {-999} {File~not~found}
- {-998} {Unsupported~construct}
- {-997} {The~regular~expression~is~too~large~(32768~states).}
- {1} {\iow_char:N\\~at~end~of~pattern }
- {4} {Numbers~out~of~order~in~\iow_char:N\{\iow_char\}~quantifier.}
- {6} {Missing~terminating~\iow_char:N\]~for~character~class }
- {7} {Invalid~escape~sequence~in~character~class}
- {8} {Range~out~of~order~in~character~class}
- {22} {Mismatched~parentheses}
- {34} {Character~value~in~\iow_char:N\\x{...}~sequence~is~too~large}
- }
- { Internal~bug. }
- }
+ \exp_after:wN \regex_query_substr_aux:NN
+ \exp_after:wN #1
+ \exp_after:wN #2
+ \l_regex_query_other_str
+ \q_stop
+ }
+\cs_new:Npn \regex_query_substr_aux:NN #1#2
+ {
+ \str_skip_do:nn {#1}
+ { \str_collect_do:nn { #2 - #1 } { \use_i_delimit_by_q_stop:nw } }
+ }
+\cs_new_protected_nopar:Npn \regex_seq_pop:N #1
+ {
+ \seq_pop:NN #1 \l_regex_tmpa_tl
+ \l_regex_tmpa_tl
+ }
+\cs_new_protected_nopar:Npn \regex_seq_get:N #1
+ {
+ \seq_get:NN #1 \l_regex_tmpa_tl
+ \l_regex_tmpa_tl
}
-\msg_new:nnn { regex } { build-error } { (error~#1): ~ #2 }
-\cs_new_nopar:Npn \regex_break_true:w #1 \regex_break_point:TF #2 #3 {#2}
-\cs_new_nopar:Npn \regex_break_false:w #1 \regex_break_point:TF #2 #3 {#3}
-\cs_new_eq:NN \regex_break_point:TF \use_ii:nn
-\cs_new_nopar:Npn \regex_item_equal:n #1
+\cs_new_protected_nopar:Npn \regex_item_dot:T
+ { \int_compare:nNnF \l_regex_current_char_int = \c_minus_one }
+\cs_new_protected_nopar:Npn \regex_break_true:w
+ #1 \regex_break_point:TF #2 #3 {#2}
+\cs_new_protected_nopar:Npn \regex_break_false:w
+ #1 \regex_break_point:TF #2 #3 {#3}
+\cs_new_protected_nopar:Npn \regex_break_point:TF #1 #2 { #2 }
+\cs_new_protected_nopar:Npn \regex_item_caseful_equal:n #1
{
\if_num:w #1 = \l_regex_current_char_int
\exp_after:wN \regex_break_true:w
\fi:
}
-\cs_new_nopar:Npn \regex_item_range:nn #1 #2
+\cs_new_protected_nopar:Npn \regex_item_caseful_range:nn #1 #2
{
\reverse_if:N \if_num:w #1 > \l_regex_current_char_int
\reverse_if:N \if_num:w #2 < \l_regex_current_char_int
@@ -210,24 +221,60 @@
\fi:
\fi:
}
-\cs_new_nopar:Npn \regex_item_less:n #1
+\cs_new_protected_nopar:Npn \regex_item_caseful_geq:n #1
{
- \if_num:w #1 > \l_regex_current_char_int
+ \reverse_if:N \if_num:w #1 > \l_regex_current_char_int
\exp_after:wN \regex_break_true:w
\fi:
}
-\cs_new_nopar:Npn \regex_item_more:n #1
+\cs_new_protected_nopar:Npn \regex_item_caseless_equal:n #1
{
- \if_num:w #1 < \l_regex_current_char_int
+ \if_num:w #1 = \l_regex_current_char_int
+ \exp_after:wN \regex_break_true:w
+ \fi:
+ \if_num:w #1 = \l_regex_case_changed_char_int
\exp_after:wN \regex_break_true:w
\fi:
}
-\cs_new_nopar:Npn \regex_item_neq:n #1
+\cs_new_protected_nopar:Npn \regex_item_caseless_range:nn #1 #2
{
- \if_num:w #1 = \l_regex_current_char_int
- \exp_after:wN \regex_break_false:w
+ \reverse_if:N \if_num:w #1 > \l_regex_current_char_int
+ \reverse_if:N \if_num:w #2 < \l_regex_current_char_int
+ \exp_after:wN \exp_after:wN \exp_after:wN \regex_break_true:w
+ \fi:
+ \fi:
+ \reverse_if:N \if_num:w #1 > \l_regex_case_changed_char_int
+ \reverse_if:N \if_num: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_item_caseless_geq:n #1
+ {
+ \reverse_if:N \if_num:w #1 > \l_regex_current_char_int
+ \exp_after:wN \regex_break_true:w
+ \fi:
+ \reverse_if:N \if_num:w #1 > \l_regex_case_changed_char_int
+ \exp_after:wN \regex_break_true:w
+ \fi:
+ }
+\cs_new:Npn \regex_item_equal:n { \regex_item_caseful_equal:n }
+\cs_new:Npn \regex_item_range:nn { \regex_item_caseful_range:nn }
+\cs_new:Npn \regex_item_geq:n { \regex_item_caseful_geq:n }
+\cs_new_protected_nopar:Npn \regex_build_caseless:
+ {
+ \bool_set_true:N \l_regex_caseless_bool
+ \cs_set:Npn \regex_item_equal:n { \regex_item_caseless_equal:n }
+ \cs_set:Npn \regex_item_range:nn { \regex_item_caseless_range:nn }
+ \cs_set:Npn \regex_item_geq:n { \regex_item_caseless_geq:n }
+ }
+\cs_new_protected_nopar:Npn \regex_build_caseful:
+ {
+ \bool_set_false:N \l_regex_caseless_bool
+ \cs_set:Npn \regex_item_equal:n { \regex_item_caseful_equal:n }
+ \cs_set:Npn \regex_item_range:nn { \regex_item_caseful_range:nn }
+ \cs_set:Npn \regex_item_geq:n { \regex_item_caseful_geq:n }
+ }
\cs_new_protected:Npn \regex_get_digits:nw #1
{
\tex_afterassignment:D \regex_tmp:w
@@ -235,65 +282,71 @@
{
\exp_not:n {#1}
{ \if_false: } } \fi:
- \regex_get_digits_aux:N
+ \regex_get_digits_aux:NN
}
-\cs_new_nopar:Npn \regex_get_digits_aux:N #1
+\cs_new_nopar:Npn \regex_get_digits_aux:NN #1#2
{
- \if_num:w 9 < 1 \exp_not:N #1 \exp_stop_f:
- \else:
- \if_charcode:w \c_space_token \exp_not:N #1
+ \if_meaning:w \regex_build_raw:N #1
+ \if_charcode:w \c_space_token \exp_not:N #2
\else:
- \regex_get_digits_end:w
+ \if_num:w 9 < 1 \exp_not:N #2 \exp_stop_f:
+ #2
+ \else:
+ \regex_get_digits_end:w #1 #2
+ \fi:
\fi:
+ \else:
+ \regex_get_digits_end:w #1 #2
\fi:
- #1 \regex_get_digits_aux:N
+ \regex_get_digits_aux:NN
}
-\cs_new_nopar:Npn \regex_get_digits_end:w
- \fi: \fi: #1 \regex_get_digits_aux:N
+\cs_new_nopar:Npn \regex_get_digits_end:w #1 \fi: #2 \regex_get_digits_aux:NN
{
- \fi: \fi:
+ \fi: #2
\if_false: { { \fi: } }
#1
}
+\prg_new_conditional:Npnn \regex_token_if_other_digit:N #1 { TF }
+ {
+ \if_num:w \c_nine < 1 \exp_not:N #1 \exp_stop_f:
+ \prg_return_true: \else: \prg_return_false: \fi:
+ }
\prg_new_conditional:Npnn \regex_aux_char_if_special:N #1 { TF }
{
- \if_num:w `#1 < 97 \exp_stop_f:
- \if_num:w `#1 < 58 \exp_stop_f:
- \if_num:w \int_eval:w (`#1 - \c_eight)/\c_sixteen = \c_two
- \prg_return_true:
- \else:
- \prg_return_false:
- \fi:
+ \if_num:w `#1 < \c_ninety_one
+ \if_num:w `#1 < \c_fifty_eight
+ \if_num:w `#1 < \c_forty_eight
+ \if_num:w `#1 < \c_thirty_two
+ \prg_return_false: \else: \prg_return_true: \fi:
+ \else: \prg_return_false: \fi:
\else:
- \if_num:w \int_eval:w `#1 / 26 = \c_three
- \prg_return_false:
- \else:
- \prg_return_true:
- \fi:
+ \if_num:w `#1 < \c_sixty_five
+ \prg_return_true: \else: \prg_return_false: \fi:
\fi:
\else:
- \if_num:w \int_eval:w `#1 / \c_five = 25 \exp_stop_f:
- \prg_return_true:
+ \if_num:w `#1 < \c_one_hundred_twenty_three
+ \if_num:w `#1 < \c_ninety_seven
+ \prg_return_true: \else: \prg_return_false: \fi:
\else:
- \prg_return_false:
+ \if_num:w `#1 < \c_one_hundred_twenty_seven
+ \prg_return_true: \else: \prg_return_false: \fi:
\fi:
\fi:
}
\prg_new_conditional:Npnn \regex_aux_char_if_alphanumeric:N #1 { TF }
{
- \if_num:w `#1 < 91 \exp_stop_f:
- \if_num:w `#1 < 65 \exp_stop_f:
- \if_num:w \c_nine < 1 #1 \exp_stop_f:
- \prg_return_true:
- \else:
- \prg_return_false:
- \fi:
+ \if_num:w `#1 < \c_ninety_one
+ \if_num:w `#1 < \c_fifty_eight
+ \if_num:w `#1 < \c_forty_eight
+ \prg_return_false: \else: \prg_return_true: \fi:
\else:
- \prg_return_true:
+ \if_num:w `#1 < \c_sixty_five
+ \prg_return_false: \else: \prg_return_true: \fi:
\fi:
\else:
- \if_num:w \int_eval:w (`#1-\c_six)/26 = \c_four
- \prg_return_true:
+ \if_num:w `#1 < \c_one_hundred_twenty_three
+ \if_num:w `#1 < \c_ninety_seven
+ \prg_return_false: \else: \prg_return_true: \fi:
\else:
\prg_return_false:
\fi:
@@ -301,8 +354,8 @@
}
\cs_new_protected_nopar:Npn \regex_build_new_state:
{
- \int_compare:nNnTF \l_regex_max_state_int > {32766}
- { \regex_build_error:n {-997} }
+ \int_compare:nNnTF \l_regex_max_state_int > { 32766 }
+ { \msg_error:nn { regex } { -997 } }
{
\int_incr:N \l_regex_max_state_int
\tex_toks:D \l_regex_max_state_int { \s_regex_toks }
@@ -314,15 +367,15 @@
{
\regex_build_new_state:
\regex_toks_put_right:Nx \l_regex_left_state_int
- { #1 { \int_use:N #2 } }
+ { #1 { \int_eval:n { #2 - \l_regex_left_state_int } } }
}
\cs_new_protected_nopar:Npn \regex_build_transitions_aux:NNNN #1#2#3#4
{
\regex_build_new_state:
\regex_toks_put_right:Nx \l_regex_left_state_int
{
- #1 { \int_use:N #2 }
- #3 { \int_use:N #4 }
+ #1 { \int_eval:n { #2 - \l_regex_left_state_int } }
+ #3 { \int_eval:n { #4 - \l_regex_left_state_int } }
}
}
\cs_new_protected:Npn \regex_build:n #1
@@ -363,25 +416,19 @@
\cs_set_eq:NN \regex_build_control:N \regex_build_default_control:N
\cs_set_eq:NN \regex_build_raw:N \regex_build_default_raw:N
\int_set_eq:NN \l_regex_capturing_group_int \c_zero
- \int_zero:N \l_regex_left_state_int
- \int_zero:N \l_regex_right_state_int
\int_zero:N \l_regex_max_state_int
\regex_build_new_state:
\regex_build_new_state:
\regex_toks_put_right:Nx \l_regex_left_state_int
- {
- \regex_action_start_wildcard:nn
- { \int_use:N \l_regex_left_state_int }
- { \int_use:N \l_regex_right_state_int }
- }
+ { \regex_action_start_wildcard:nn {0} {1} }
}
\cs_new_protected_nopar:Npn \regex_build_end:
{
\seq_if_empty:NF \l_regex_capturing_group_seq
{
- \regex_build_error:n {22}
+ \msg_error:nn { regex } {22}
\prg_replicate:nn
- { \seq_length:N \l_regex_capturing_group_seq } % (
+ { \seq_length:N \l_regex_capturing_group_seq }
{ \regex_build_close_aux: \regex_build_group_: }
}
\regex_toks_put_right:Nx \l_regex_right_state_int
@@ -399,7 +446,13 @@
\regex_toks_put_right:Nx \l_regex_left_state_int
{
\exp_not:N \int_compare:nNnT {#1} = \l_regex_current_step_int
- { \regex_action_free:n { \int_use:N \l_regex_right_state_int } }
+ {
+ \regex_action_free:n
+ {
+ \int_eval:n
+ { \l_regex_right_state_int - \l_regex_left_state_int }
+ }
+ }
}
}
\cs_new_protected_nopar:cpn { regex_build_$: } % $
@@ -409,71 +462,72 @@
{
\exp_not:N \int_compare:nNnT
\c_minus_one = \l_regex_current_char_int
- { \regex_action_free:n { \int_use:N \l_regex_right_state_int } }
+ {
+ \regex_action_free:n
+ {
+ \int_eval:n
+ { \l_regex_right_state_int - \l_regex_left_state_int }
+ }
+ }
}
}
\cs_new_eq:Nc \regex_build_Z: { regex_build_$: } %$
\cs_new_eq:Nc \regex_build_z: { regex_build_$: } %$
\cs_new_protected_nopar:Npn \regex_build_b:
{
- \bool_set_true:N \l_regex_look_behind_bool
\regex_build_new_state:
\regex_toks_put_right:Nx \l_regex_left_state_int
{
\exp_not:N \regex_if_word_boundary:TF
- { \regex_action_free:n { \int_use:N \l_regex_right_state_int } }
+ {
+ \regex_action_free:n
+ {
+ \int_eval:n
+ { \l_regex_right_state_int - \l_regex_left_state_int }
+ }
+ }
{ }
}
}
\cs_new_protected_nopar:Npn \regex_build_B:
{
- \bool_set_true:N \l_regex_look_behind_bool
\regex_build_new_state:
\regex_toks_put_right:Nx \l_regex_left_state_int
{
\exp_not:N \regex_if_word_boundary:TF
{ }
- { \regex_action_free:n { \int_use:N \l_regex_right_state_int } }
+ {
+ \regex_action_free:n
+ {
+ \int_eval:n
+ { \l_regex_right_state_int - \l_regex_left_state_int }
+ }
+ }
}
}
\cs_new_protected_nopar:Npn \regex_if_word_boundary:TF
{
- \tl_if_empty:NTF \l_regex_look_behind_str
- { \c_regex_w_tl }
- {
- \group_begin:
- \cs_set_nopar:Npx \regex_tmp:w
- {
- \int_set:Nn \l_regex_current_char_int
- { ` \str_head:N \l_regex_look_behind_str }
- }
- \regex_tmp:w
- \c_regex_w_tl
- \regex_break_point:TF
- { \group_end: \c_regex_W_tl }
- { \group_end: \c_regex_w_tl }
- }
+ \group_begin:
+ \int_set_eq:NN \l_regex_current_char_int \l_regex_last_char_int
+ \c_regex_w_tl
+ \regex_break_point:TF
+ { \group_end: \c_regex_W_tl \regex_item_equal:n { -1 } }
+ { \group_end: \c_regex_w_tl }
\regex_break_point:TF
}
\cs_new_protected_nopar:Npn \regex_build_default_raw:N #1
{
\cs_set:Npx \regex_build_tmp_class:n ##1
{
- \exp_not:n { \exp_not:N \if_num:w }
- \int_value:w `#1 = \l_regex_current_char_int
- \regex_action_cost:n { ##1 }
- \exp_not:n { \exp_not:N \fi: }
+ \regex_item_equal:n { \int_value:w `#1 }
+ \regex_break_point:TF { \regex_action_cost:n { ##1 } } { }
}
\regex_build_one_quantifier:
}
\cs_new_protected_nopar:cpn { regex_build_.: }
{
\cs_set:Npn \regex_build_tmp_class:n ##1
- {
- \exp_not:N \if_num:w \c_minus_one < \l_regex_current_char_int
- \regex_action_cost:n {##1}
- \exp_not:N \fi:
- }
+ { \regex_item_dot:T { \regex_action_cost:n {##1} } }
\regex_build_one_quantifier:
}
\cs_new_protected_nopar:Npn \regex_build_char_type:N #1
@@ -481,9 +535,7 @@
\cs_set:Npn \regex_build_tmp_class:n ##1
{
\exp_not:N #1
- \exp_not:N \regex_break_point:TF
- { \regex_action_cost:n {##1} }
- { }
+ \regex_break_point:TF { \regex_action_cost:n {##1} } { }
}
\regex_build_one_quantifier:
}
@@ -518,16 +570,8 @@
{
\exp_not:o \l_regex_class_tl
\bool_if:NTF \l_regex_class_bool
- {
- \exp_not:N \regex_break_point:TF
- { \regex_action_cost:n {##1} }
- { }
- }
- {
- \exp_not:N \regex_break_point:TF
- { }
- { \regex_action_cost:n {##1} }
- }
+ { \regex_break_point:TF { \regex_action_cost:n {##1} } { } }
+ { \regex_break_point:TF { } { \regex_action_cost:n {##1} } }
}
\regex_build_one_quantifier:
}
@@ -553,7 +597,7 @@
\cs_new_protected_nopar:Npn \regex_class_single:N #1
{
\tl_put_right:Nx \l_regex_class_tl
- { \exp_not:N \regex_item_equal:n { \int_value:w `#1 } }
+ { \regex_item_equal:n { \int_value:w `#1 } }
}
\cs_new_protected_nopar:Npn \regex_class_range:Nw #1#2#3
{
@@ -572,14 +616,14 @@
\cs_new_protected_nopar:Npn \regex_class_range_put:NN #1#2
{
\if_num:w `#1 > `#2 \exp_stop_f:
- \regex_build_error:n {8}
+ \msg_error:nn { regex } {8}
\else:
\tl_put_right:Nx \l_regex_class_tl
{
\if_num:w `#1 = `#2 \exp_stop_f:
- \exp_not:N \regex_item_equal:n
+ \regex_item_equal:n
\else:
- \exp_not:N \regex_item_range:nn { \int_value:w `#1 }
+ \regex_item_range:nn { \int_value:w `#1 }
\fi:
{ \int_value:w `#2 }
}
@@ -651,26 +695,29 @@
\exp_not:N \regex_build_raw:N \c_lbrace_str #1#2
}
}
-\cs_new_protected_nopar:Npn \regex_build_quantifier_lbrace:nnw #1#2#3
+\cs_new_protected_nopar:Npn \regex_build_quantifier_lbrace:nnw #1#2#3#4
{
- \str_if_eq:xxTF { \exp_not:N #3 } { \c_rbrace_str }
+ \str_if_eq:xxTF
+ { \exp_not:n {#3#4} }
+ { \exp_not:N \regex_build_control:N \c_rbrace_str }
{
\tl_if_empty:nTF {#2}
- { \regex_build_quantifier_aux:nnN { {#1} {\c_max_int} } {nn} }
+ { \regex_build_quantifier_aux:nnNN { {#1} } { n* } }
{
\int_compare:nNnT {#1} > {#2}
- { \regex_build_error:n {4} }
- \regex_build_quantifier_aux:nnN { {#1} {#2} } {nn}
+ { \msg_error:nn { regex } {4} }
+ \regex_build_quantifier_aux:nnNN { {#1} {#2} } { nn }
}
}
{
\regex_build_quantifier_end:n { }
\use:x
{
- \exp_not:n { \exp_args:No \tl_map_function:nN }
- { \c_lbrace_str #1 #2 , }
- \regex_build_raw:N
+ \exp_args:No \tl_map_function:nN
+ { \c_lbrace_str #1 , #2 }
+ \regex_build_raw:N
}
+ #3 #4
}
}
\cs_new_protected_nopar:Npn \regex_build_quantifier_end:n #1
@@ -726,71 +773,27 @@
\regex_action_free:n \l_regex_tmpa_int
}
\cs_new_protected_nopar:Npn \regex_build_one_n: #1
- {
- \int_set_eq:NN \l_regex_tmpa_int \l_regex_right_state_int
- \regex_build_new_state:
- \regex_build_new_state:
- \regex_toks_put_right:Nx \l_regex_tmpa_int
- { %^^A safe \if nesting?
- \exp_not:N \if_num:w #1 > \l_regex_repetition_int
- \regex_action_repeat_move:n
- { \int_use:N \l_regex_left_state_int }
- \exp_not:N \else:
- \regex_action_no_repeat_move:n
- { \int_use:N \l_regex_right_state_int }
- \exp_not:N \fi:
- }
- \regex_toks_put_right:Nx \l_regex_left_state_int
- {
- \regex_build_tmp_class:n
- { \int_use:N \l_regex_tmpa_int }
- }
- }
+ { \prg_replicate:nn {#1} { \regex_build_one_: } }
\cs_new_eq:cN { regex_build_one_n?: } \regex_build_one_n:
-\cs_new_protected_nopar:Npn \regex_build_one_nn: #1#2
+\cs_new_protected_nopar:cpx { regex_build_one_n*: } #1
{
- \regex_build_one_nn_aux:nn {#1}
- {
- \exp_not:N \if_num:w #2 > \l_regex_repetition_int
- \regex_action_repeat_copy:n
- { \int_use:N \l_regex_left_state_int }
- \exp_not:N \fi:
- \regex_action_no_repeat_move:n
- { \int_use:N \l_regex_right_state_int }
- }
+ \exp_not:N \prg_replicate:nn {#1} { \exp_not:N \regex_build_one_: }
+ \exp_not:c { regex_build_one_*: }
}
-\cs_new_protected_nopar:cpn { regex_build_one_nn?: } #1#2
+\cs_new_protected_nopar:cpx { regex_build_one_n*?: } #1
{
- \regex_build_one_nn_aux:nn {#1}
- {
- \regex_action_no_repeat_copy:n
- { \int_use:N \l_regex_right_state_int }
- \exp_not:N \if_num:w #2 > \l_regex_repetition_int
- \regex_action_repeat_move:n
- { \int_use:N \l_regex_left_state_int }
- \exp_not:N \fi:
- }
+ \exp_not:N \prg_replicate:nn {#1} { \exp_not:N \regex_build_one_: }
+ \exp_not:c { regex_build_one_*?: }
}
-\cs_new_protected_nopar:Npn \regex_build_one_nn_aux:nn #1#2
+\cs_new_protected_nopar:Npn \regex_build_one_nn_aux:Nnn #1#2#3
{
- \int_set_eq:NN \l_regex_tmpa_int \l_regex_right_state_int
- \regex_build_new_state:
- \regex_build_new_state:
- \regex_toks_put_right:Nx \l_regex_tmpa_int
- {
- \exp_not:N \if_num:w #1 > \l_regex_repetition_int
- \regex_action_repeat_move:n
- { \int_use:N \l_regex_left_state_int }
- \exp_not:N \else:
- #2
- \exp_not:N \fi:
- }
- \regex_toks_put_right:Nx \l_regex_left_state_int
- {
- \regex_build_tmp_class:n
- { \int_use:N \l_regex_tmpa_int }
- }
+ \prg_replicate:nn {#2} { \regex_build_one_: }
+ \prg_replicate:nn {#3-#2} {#1}
}
+\cs_new_protected_nopar:Npx \regex_build_one_nn:
+ { \regex_build_one_nn_aux:Nnn \exp_not:c { regex_build_one_?: } }
+\cs_new_protected_nopar:cpx { regex_build_one_nn?: }
+ { \regex_build_one_nn_aux:Nnn \exp_not:c { regex_build_one_??: } }
\cs_new_protected_nopar:cpn { regex_build_(: } #1#2
{
\str_if_eq:nnTF { #1 #2 } { \regex_build_control:N ? }
@@ -806,10 +809,19 @@
\cs_new_protected_nopar:Npn \regex_build_open_aux:
{
\regex_build_new_state:
- \seq_push:Nx \l_regex_left_state_seq
- { \int_use:N \l_regex_left_state_int }
- \seq_push:Nx \l_regex_right_state_seq
- { \int_use:N \l_regex_right_state_int }
+ \seq_push:Nx \l_regex_group_begin_seq
+ {
+ \int_set:Nn \l_regex_left_state_int
+ { \int_use:N \l_regex_left_state_int }
+ }
+ \bool_if:NTF \l_regex_caseless_bool
+ { \seq_push:Nn \l_regex_group_end_seq { \regex_build_caseless: } }
+ { \seq_push:Nn \l_regex_group_end_seq { \regex_build_caseful: } }
+ \seq_push:Nx \l_regex_group_end_seq
+ {
+ \int_set:Nn \l_regex_right_state_int
+ { \int_use:N \l_regex_right_state_int }
+ }
\regex_build_begin_alternation:
}
\cs_new_protected_nopar:cpn { regex_build_|: }
@@ -820,7 +832,7 @@
\cs_new_protected_nopar:cpn { regex_build_): }
{
\seq_if_empty:NTF \l_regex_capturing_group_seq
- { \regex_build_error:n {22} }
+ { \msg_error:nn { regex } { 22 } }
{
\regex_build_close_aux:
\regex_build_group_quantifier:
@@ -829,30 +841,41 @@
\cs_new_protected_nopar:Npn \regex_build_close_aux:
{
\regex_build_end_alternation:
- \seq_pop:NN \l_regex_left_state_seq \l_regex_tmpa_tl
- \int_set:Nn \l_regex_left_state_int \l_regex_tmpa_tl
- \seq_pop:NN \l_regex_right_state_seq \l_regex_tmpa_tl
- \int_set:Nn \l_regex_right_state_int \l_regex_tmpa_tl
+ \regex_seq_pop:N \l_regex_group_begin_seq
+ \regex_seq_pop:N \l_regex_group_end_seq
+ \regex_seq_pop:N \l_regex_group_end_seq
}
\cs_new_protected_nopar:Npn \regex_build_begin_alternation:
{
\regex_build_new_state:
- \seq_get:NN \l_regex_left_state_seq \l_regex_tmpa_tl
- \int_set:Nn \l_regex_left_state_int \l_regex_tmpa_tl
+ \regex_seq_get:N \l_regex_group_begin_seq
\regex_toks_put_right:Nx \l_regex_left_state_int
- { \regex_action_free:n { \int_use:N \l_regex_right_state_int } }
+ {
+ \regex_action_free:n
+ {
+ \int_eval:n
+ { \l_regex_right_state_int - \l_regex_left_state_int }
+ }
+ }
}
\cs_new_protected_nopar:Npn \regex_build_end_alternation:
{
- \seq_get:NN \l_regex_right_state_seq \l_regex_tmpa_tl
- \regex_toks_put_right:Nx \l_regex_right_state_int
- { \regex_action_free:n { \l_regex_tmpa_tl } }
+ \int_set_eq:NN \l_regex_left_state_int \l_regex_right_state_int
+ \regex_seq_get:N \l_regex_group_end_seq
+ \regex_toks_put_right:Nx \l_regex_left_state_int
+ {
+ \regex_action_free:n
+ {
+ \int_eval:n
+ { \l_regex_right_state_int - \l_regex_left_state_int }
+ }
+ }
}
\cs_new_protected_nopar:Npn \regex_build_special_group:NN #1#2
{
\cs_if_exist_use:cF { regex_build_special_group_\token_to_str:N #2 : }
{
- \regex_build_error:n { -998 }
+ \msg_error:nn { regex } { -998 }
\regex_build_control:N ( % )
\regex_build_raw:N ?
#1 #2
@@ -863,6 +886,40 @@
\seq_push:Nx \l_regex_capturing_group_seq { * }
\regex_build_open_aux:
}
+\cs_new_protected_nopar:Npn \regex_build_special_group_i:
+ {
+ \regex_build_options:NNN +
+ \regex_build_raw:N i
+ }
+\cs_new_protected_nopar:cpn { regex_build_special_group_-: }
+ {
+ \regex_build_options:NNN -
+ }
+\cs_new_protected_nopar:Npn \regex_build_options:NNN #1#2#3
+ {
+ \token_if_eq_meaning:NNTF \regex_build_raw:N #2
+ {
+ \cs_if_exist_use:cF { regex_build_option_#1#3: }
+ { \msg_error:nnx { regex } { unknown-option } { #3 } }
+ \regex_build_options:NNN #1
+ }
+ {
+ \prg_case_str:nnn { #3 }
+ { % (
+ { ) } { }
+ { - } { \regex_build_options:NNN - }
+ }
+ { \msg_error:nnx { regex } { invalid-in-option } { #3 } }
+ }
+ }
+\cs_new_protected_nopar:cpn { regex_build_option_+i: }
+ {
+ \regex_build_caseless:
+ \cs_set_eq:NN \regex_match_loop_case_hook:
+ \regex_match_loop_caseless_hook:
+ }
+\cs_new_protected_nopar:cpn { regex_build_option_-i: }
+ { \regex_build_caseful: }
\cs_new_protected_nopar:Npn \regex_build_group_quantifier:
{
\tl_set:Nn \l_regex_one_or_group_tl { group }
@@ -891,21 +948,33 @@
\int_set_eq:NN \l_regex_tmpa_int \l_regex_left_state_int
\regex_build_new_state:
\tex_toks:D \l_regex_right_state_int = \tex_toks:D \l_regex_tmpa_int
- \use:x
+ \regex_toks_put_left:Nx \l_regex_right_state_int
+ {
+ \int_set:Nn \l_regex_current_state_int
+ { \int_use:N \l_regex_tmpa_int } % ^^A here we lie!
+ }
+ \cs_set:Npx \regex_tmp:w
{
\tex_toks:D \l_regex_tmpa_int
- { \s_regex_toks #1 { \int_use:N \l_regex_right_state_int } }
+ {
+ \s_regex_toks
+ #1 { \int_eval:n { \l_regex_right_state_int - \l_regex_tmpa_int } }
+ }
}
+ \regex_tmp:w
\regex_build_group_submatches:NN
\l_regex_right_state_int \l_regex_left_state_int
- \int_set_eq:NN \l_regex_right_state_int \l_regex_left_state_int
}
\cs_new_protected_nopar:Npn \regex_build_group_qs_aux:NN #1#2
{
\regex_build_group_shift:N \regex_action_free:n
+ \int_set_eq:NN \l_regex_right_state_int \l_regex_left_state_int
\regex_build_transition_aux:NN \regex_action_free:n #1
#2 \l_regex_tmpa_int
- { \regex_action_free:n { \int_use:N \l_regex_right_state_int } }
+ {
+ \regex_action_free:n
+ { \int_eval:n { \l_regex_right_state_int - \l_regex_tmpa_int } }
+ }
}
\cs_new_protected_nopar:cpn { regex_build_group_?: }
{
@@ -945,77 +1014,63 @@
\regex_action_free:n \l_regex_right_state_int
\regex_action_free:n \l_regex_tmpa_int
}
-\cs_new_protected_nopar:Npn \regex_build_group_n: #1
+\cs_new_protected_nopar:Npn \regex_build_group_n_aux:n #1
{
- \regex_build_group_shift:N \regex_action_repeat_move:n
- \regex_build_transition_aux:NN
- \regex_action_free:n \l_regex_tmpa_int
- \use:x
+ \regex_toks_put_right:Nx \l_regex_right_state_int
{
- \tex_toks:D \l_regex_tmpa_int
- {
- \s_regex_toks
- \exp_not:N \if_num:w #1 > \l_regex_repetition_int
- \tex_the:D \tex_toks:D \l_regex_tmpa_int
- \exp_not:N \else:
- \regex_action_no_repeat_move:n
- { \int_use:N \l_regex_right_state_int }
- \exp_not:N \fi:
- }
+ \regex_action_free:n
+ { \int_eval:n { \l_regex_max_state_int - \l_regex_left_state_int } }
}
- }
-\cs_new_eq:cN { regex_build_group_n?: } \regex_build_group_n:
-\cs_new_protected_nopar:Npn \regex_build_group_nn: #1#2
- {
- \regex_build_group_shift:N \regex_action_repeat_move:n
- \regex_build_transition_aux:NN
- \regex_action_free:n \l_regex_tmpa_int
- \use:x
+ \int_set_eq:NN \l_regex_tmpa_int \l_regex_left_state_int
+ \int_set:Nn \l_regex_tmpb_int { \l_regex_max_state_int + \c_one }
+ \int_set:Nn \l_regex_max_state_int
{
- \tex_toks:D \l_regex_tmpa_int
- {
- \s_regex_toks
- \exp_not:N \if_num:w #1 > \l_regex_repetition_int
- \tex_the:D \tex_toks:D \l_regex_tmpa_int
- \exp_not:N \else:
- \exp_not:N \if_num:w #2 > \l_regex_repetition_int
- \tex_the:D \tex_toks:D \l_regex_tmpa_int
- \exp_not:N \fi:
- \regex_action_no_repeat_copy:n
- { \int_use:N \l_regex_right_state_int }
- \exp_not:N \fi:
- }
+ \l_regex_left_state_int - \c_one
+ + #1 * ( \l_regex_max_state_int - \l_regex_left_state_int + \c_one )
+ }
+ \int_until_do:nNnn \l_regex_tmpb_int > \l_regex_max_state_int
+ {
+ \tex_toks:D \l_regex_tmpb_int = \tex_toks:D \l_regex_tmpa_int
+ \int_incr:N \l_regex_tmpa_int
+ \int_incr:N \l_regex_tmpb_int
}
}
-\cs_new_protected_nopar:cpn { regex_build_group_nn?: } #1#2
- {
- \regex_build_group_shift:N \regex_action_repeat_move:n
+\cs_new_protected_nopar:Npn \regex_build_group_n: #1
+ { % ^^A todo: catch case #1 <= 0.
+ \regex_build_group_n_aux:n {#1}
\regex_build_transition_aux:NN
+ \regex_action_free:n \l_regex_right_state_int
+ \regex_build_group_submatches:NN
+ \l_regex_tmpa_int \l_regex_left_state_int
+ }
+\cs_new_eq:cN { regex_build_group_n?: } \regex_build_group_n:
+\cs_new_protected_nopar:cpn { regex_build_group_n*: } #1
+ { % ^^A todo: catch case #1 <= 0.
+ \regex_build_group_n_aux:n {#1}
+ \regex_build_transitions_aux:NNNN
\regex_action_free:n \l_regex_tmpa_int
- \use:x
- {
- \tex_toks:D \l_regex_tmpa_int
- {
- \s_regex_toks
- \exp_not:N \if_num:w #1 > \l_regex_repetition_int
- \tex_the:D \tex_toks:D \l_regex_tmpa_int
- \exp_not:N \else:
- \regex_action_no_repeat_copy:n
- { \int_use:N \l_regex_right_state_int }
- \exp_not:N \if_num:w #2 > \l_regex_repetition_int
- \tex_the:D \tex_toks:D \l_regex_tmpa_int
- \exp_not:N \fi:
- \exp_not:N \fi:
- }
- }
+ \regex_action_free:n \l_regex_right_state_int
+ \regex_build_group_submatches:NN
+ \l_regex_tmpa_int \l_regex_left_state_int
}
-\cs_new_protected:Npn \regex_if_state_free:nT #1
- {
- \if_num:w \tex_dimen:D #1 = \l_regex_unique_step_int
- \exp_after:wN \use_none:n
- \else:
- \exp_after:wN \use:n
- \fi:
+\cs_new_protected_nopar:cpn { regex_build_group_n*?: } #1
+ { % ^^A todo: catch case #1 <= 0.
+ \regex_build_group_n_aux:n {#1}
+ \regex_build_transitions_aux:NNNN
+ \regex_action_free:n \l_regex_right_state_int
+ \regex_action_free:n \l_regex_tmpa_int
+ \regex_build_group_submatches:NN
+ \l_regex_tmpa_int \l_regex_left_state_int
+ }
+\cs_new_protected_nopar:Npn \regex_build_group_nn: #1#2
+ { % ^^A Not Implemented Yet!
+ \msg_expandable_error:n { Quantifier~{m,n}~not~implemented~yet }
+ \use:c { regex_build_group_n*: } {#1}
+ }
+\cs_new_protected_nopar:cpn { regex_build_group_nn?: } #1#2
+ { % ^^A Not Implemented Yet!
+ \msg_expandable_error:n { Quantifier~{m,n}~not~implemented~yet }
+ \use:c { regex_build_group_n*?: } {#1}
}
\cs_new_protected:Npn \regex_store_state:n #1
{
@@ -1023,23 +1078,24 @@
\tex_skip:D \l_regex_max_index_int #1 sp \scan_stop:
\regex_store_submatches:n {#1}
}
-\cs_new_protected_nopar:Npn \regex_state_use_submatches:
+\cs_new_protected_nopar:Npn \regex_state_use_with_submatches:
{ \regex_state_use_aux:n { } }
\cs_new_protected_nopar:Npn \regex_state_use:
{ \regex_state_use_aux:n { \exp_after:wN \regex_state_use_aux_ii:w } }
-\cs_new:Npn \regex_state_use_aux_ii:w #1 \s_regex_toks { }
-\cs_new_protected:Npn \regex_state_use_aux:n #1
- {
- \regex_if_state_free:nT { \l_regex_current_state_int }
- {
- \tex_dimen:D \l_regex_current_state_int
- = \l_regex_unique_step_int sp \scan_stop:
- #1 \tex_the:D \tex_toks:D \l_regex_current_state_int \scan_stop:
- }
+\cs_new_nopar:Npn \regex_state_use_aux_ii:w #1 \s_regex_toks { }
+\cs_new_protected_nopar:Npn \regex_state_use_aux:n #1
+ {
+ \if_num:w \tex_dimen:D \l_regex_current_state_int
+ < \l_regex_unique_step_int
+ \tex_dimen:D \l_regex_current_state_int
+ = \l_regex_unique_step_int sp \scan_stop:
+ #1 \tex_the:D \tex_toks:D \exp_after:wN \l_regex_current_state_int
+ \fi:
+ \scan_stop:
}
\cs_new_protected_nopar:Npn \regex_disable_submatches:
{
- \cs_set_eq:NN \regex_state_use_submatches: \regex_state_use:
+ \cs_set_eq:NN \regex_state_use_with_submatches: \regex_state_use:
\cs_set_eq:NN \regex_store_submatches:n
\regex_protected_use_none:n
\cs_set_eq:NN \regex_action_submatches:n
@@ -1048,55 +1104,73 @@
\cs_new_protected:Npn \regex_protected_use_none:n #1 { }
\cs_new_protected:Npn \regex_store_submatches:n #1
{
- \exp_after:wN \regex_store_submatches_aux:Nw
- \exp_after:wN \l_regex_current_submatches_prop
- \tex_the:D \tex_toks:D #1 \scan_stop: \q_stop
- { #1 }
+ \tex_toks:D #1 \exp_after:wN
+ {
+ \tex_romannumeral:D
+ \exp_after:wN \regex_store_submatches_aux:w
+ \tex_the:D \tex_toks:D #1
+ }
}
-\cs_new_protected:Npn \regex_store_submatches_aux:Nw #1 #2 \s_regex_toks
+\cs_new_protected:Npn \regex_store_submatches_aux:w #1 \s_regex_toks
{
- \exp_args:No \regex_store_submatches_aux_ii:wnnwwn { #1 }
- #2
- \regex_state_submatches:nn { \c_minus_one } { \q_prop }
+ \regex_store_submatches_aux_ii:Nnnw
+ #1
+ \regex_state_submatches:nn \c_minus_one \q_prop
\s_regex_toks
}
-\cs_new_protected:Npn \regex_store_submatches_aux_ii:wnnwwn
- #1 \regex_state_submatches:nn #2#3 #4 \s_regex_toks #5 \q_stop #6
+\cs_new_protected:Npn \regex_store_submatches_aux_ii:Nnnw
+ \regex_state_submatches:nn #1 #2 #3 \s_regex_toks
{
- \tex_toks:D #6 \exp_after:wN
+ \exp_after:wN \c_zero
+ \exp_after:wN \regex_state_submatches:nn \exp_after:wN
{
- \exp_after:wN \regex_state_submatches:nn \exp_after:wN
- { \int_value:w \int_eval:w \l_regex_unique_step_int + \c_one }
- { #1 }
- \regex_state_submatches:nn {#2} {#3}
- \s_regex_toks
- #5
+ \int_value:w \int_eval:w
+ \l_regex_unique_step_int + \c_one
+ \exp_after:wN
}
+ \exp_after:wN { \l_regex_current_submatches_prop }
+ \regex_state_submatches:nn {#1} {#2}
+ \s_regex_toks
}
\cs_new_protected:Npn \regex_state_submatches:nn #1#2
{
\if_num:w #1 = \l_regex_unique_step_int
- \tl_set:Nn \l_regex_current_submatches_prop {#2}
+ \tl_set:Nn \l_regex_current_submatches_prop { #2 }
\fi:
}
\cs_new_protected:Npn \regex_match:n #1
{
- \tl_set:Nx \l_regex_query_str { \tl_to_other_str:n {#1} }
+ \tl_set:Nx \l_regex_query_other_str { \tl_to_other_str:n {#1} }
\regex_match_initial_setup:
\regex_match_once:
}
\cs_new_protected_nopar:Npn \regex_match_once:
{
\regex_match_setup:
- \exp_after:wN \regex_match_once_aux: \l_regex_query_str
+ \exp_after:wN \regex_match_once_aux: \l_regex_query_other_str
\q_recursion_tail \q_recursion_stop
\bool_if:NT \l_regex_success_bool { \l_regex_every_match_tl }
}
\cs_new_protected_nopar:Npn \regex_match_once_aux:
- { \str_skip_do:nn { \l_regex_start_step_int } { \regex_match_loop:N } }
+ {
+ \int_compare:nNnTF \l_regex_start_step_int = \c_zero
+ {
+ \int_set_eq:NN \l_regex_current_char_int \c_minus_one
+ \regex_match_loop:N
+ }
+ {
+ \str_skip_do:nn
+ { \l_regex_start_step_int - \c_one }
+ { \regex_match_once_aux_ii:N }
+ }
+ }
+\cs_new_protected_nopar:Npn \regex_match_once_aux_ii:N #1
+ {
+ \int_set:Nn \l_regex_current_char_int { `#1 }
+ \regex_match_loop:N
+ }
\cs_new_protected_nopar:Npn \regex_match_initial_setup:
{
- \tl_clear:N \l_regex_look_behind_str
\prg_stepwise_inline:nnnn {1} {1} { \l_regex_max_state_int }
{ \tex_dimen:D ##1 \c_minus_one sp \scan_stop: }
\int_set_eq:NN \l_regex_unique_step_int \c_minus_one
@@ -1118,20 +1192,11 @@
\int_zero:N \l_regex_max_index_int
\regex_store_state:n {1}
}
-\cs_new_protected_nopar:Npn \regex_match_loop_setup:
- {
- \int_incr:N \l_regex_current_step_int
- \int_incr:N \l_regex_unique_step_int
- \bool_set_false:N \l_regex_fresh_thread_bool
- }
\cs_new_eq:NN \s_regex_step \scan_stop:
\cs_new:Npn \regex_break_step:w #1 \s_regex_step { }
\cs_new_protected_nopar:Npn \regex_match_loop:N #1
{
- \regex_match_loop_setup:
- \token_if_eq_meaning:NNTF #1 \q_recursion_tail
- { \int_set_eq:NN \l_regex_current_char_int \c_minus_one }
- { \int_set:Nn \l_regex_current_char_int {`#1} }
+ \regex_match_loop_setup:N #1
\cs_set_nopar:Npx \regex_tmp:w
{
\int_zero:N \l_regex_max_index_int
@@ -1145,19 +1210,49 @@
\exp_after:wN \use_none_delimit_by_q_recursion_stop:w
\fi:
\quark_if_recursion_tail_stop:N #1
- \bool_if:NT \l_regex_look_behind_bool
- { \tl_put_left:Nx \l_regex_look_behind_str {#1} }
\regex_match_loop:N
}
\cs_new_nopar:Npn \regex_match_one_index:n #1
{
- \regex_match_one_index_aux:n { \int_value:w \tex_skip:D #1 }
+ \regex_match_one_index_aux:n
+ { \int_value:w \tex_skip:D #1 }
}
\cs_new_protected_nopar:Npn \regex_match_one_index_aux:n #1
{
\int_set:Nn \l_regex_current_state_int {#1}
\prop_clear:N \l_regex_current_submatches_prop
- \regex_state_use_submatches:
+ \regex_state_use_with_submatches:
+ }
+\cs_new_protected_nopar:Npn \regex_match_loop_setup:N #1
+ {
+ \int_incr:N \l_regex_current_step_int
+ \int_incr:N \l_regex_unique_step_int
+ \bool_set_false:N \l_regex_fresh_thread_bool
+ \int_set_eq:NN \l_regex_last_char_int \l_regex_current_char_int
+ \if_meaning:w #1 \q_recursion_tail
+ \int_set_eq:NN \l_regex_current_char_int \c_minus_one
+ \else:
+ \int_set:Nn \l_regex_current_char_int {`#1}
+ \fi:
+ \regex_match_loop_case_hook:
+ }
+\cs_new_protected_nopar:Npn \regex_match_loop_case_hook: { }
+\cs_new_protected_nopar:Npn \regex_match_loop_caseless_hook:
+ {
+ \int_set_eq:NN \l_regex_case_changed_char_int \l_regex_current_char_int
+ \if_num:w \l_regex_current_char_int < \c_ninety_one
+ \if_num: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_num:w \l_regex_current_char_int < \c_one_hundred_twenty_three
+ \if_num: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_protected_nopar:Npn \regex_action_start_wildcard:nn #1#2
{
@@ -1167,7 +1262,10 @@
\regex_action_cost:n {#1}
}
\cs_new_protected_nopar:Npn \regex_action_cost:n #1
- { \regex_store_state:n {#1} }
+ {
+ \exp_args:Nf \regex_store_state:n %^^A optimize!
+ { \int_eval:n { \l_regex_current_state_int + #1 } }
+ }
\cs_new_protected_nopar:Npn \regex_action_success:
{
\regex_last_match_empty:F
@@ -1184,30 +1282,22 @@
}
\cs_new_protected_nopar:Npn \regex_action_free:n #1
{
- \regex_if_state_free:nT {#1}
+ \cs_set_nopar:Npx \regex_tmp:w
{
- \use:x
- {
- \int_set:Nn \l_regex_current_state_int {#1}
- \regex_store_submatches:n { \l_regex_current_state_int }
- \regex_state_use:
- \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 }
- }
+ \int_add:Nn \l_regex_current_state_int {#1}
+ \regex_state_use:
+ \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 }
}
+ \regex_tmp:w
}
\cs_new_protected_nopar:Npn \regex_action_submatch:n #1
{
\prop_put:Nno \l_regex_current_submatches_prop {#1}
{ \int_use:N \l_regex_current_step_int }
- \regex_store_submatches:n { \l_regex_current_state_int }
}
-\cs_new_protected_nopar:Npn \regex_action_repeat_copy:n { \ERROR }
-\cs_new_protected_nopar:Npn \regex_action_repeat_move:n { \ERROR }
-\cs_new_protected_nopar:Npn \regex_action_no_repeat_copy:n { \ERROR }
-\cs_new_protected_nopar:Npn \regex_action_no_repeat_move:n { \ERROR }
\cs_new_protected_nopar:Npn \regex_extract:
{
\seq_gclear:N \g_regex_submatches_seq
@@ -1217,11 +1307,7 @@
\regex_extract_aux:nTF { ##1 }
{
\seq_gput_right:Nx \g_regex_submatches_seq
- {
- \str_from_to:Nnn \l_regex_query_str
- { \l_regex_tmpa_tl }
- { \l_regex_tmpb_tl }
- }
+ { \regex_query_substr:NN \l_regex_tmpa_tl \l_regex_tmpb_tl }
}
{ \seq_gput_right:Nn \g_regex_submatches_seq { } }
}
@@ -1253,9 +1339,13 @@
= \int_use:N \l_regex_max_state_int
\l_regex_capturing_group_int
= \int_use:N \l_regex_capturing_group_int
- \bool_if:NTF \l_regex_look_behind_bool
- { \bool_set_true:N \l_regex_look_behind_bool }
- { \bool_set_false:N \l_regex_look_behind_bool }
+ \token_if_eq_meaning:NNT
+ \regex_match_loop_case_hook:
+ \regex_match_loop_caseless_hook:
+ {
+ \cs_set_eq:NN \regex_match_loop_case_hook:
+ \regex_match_loop_caseless_hook:
+ }
\prg_stepwise_function:nnnN
{1} {1} {\l_regex_max_state_int}
\regex_set_aux:n
@@ -1269,7 +1359,7 @@
\cs_new:Npn \regex_nfa:Nw #1 #2 \regex_nfa_end:
{ \msg_expandable_error:n { Automaton~#1 used~incorrectly. } }
\cs_new_eq:NN \regex_nfa_end: \scan_stop:
-\prg_new_protected_conditional:Npnn \regex_check_nfa:N #1 { TF }
+\prg_new_protected_conditional:Npnn \regex_check_nfa:N #1 { T , TF }
{ \exp_after:wN \regex_check_nfa_aux:Nw #1 \q_stop }
\cs_new:Npn \regex_check_nfa_aux:Nw #1 #2 \q_stop
{
@@ -1280,11 +1370,6 @@
\prg_return_false:
\fi:
}
-\msg_new:nnn { regex } { not-nfa }
- {
- I~was~expecting~a~regular~expression~variable.\\
- Instead,~I~got~#1.
- }
\cs_new_protected_nopar:Npn \regex_use:N #1
{ \exp_after:wN \use_none:nn #1 }
\cs_new_protected:Npn \regex_user_aux:n #1
@@ -1296,7 +1381,7 @@
}
\cs_new_protected_nopar:Npn \regex_return_after_group:
{
- \if_bool:N \l_regex_success_bool
+ \if_meaning:w \c_true_bool \l_regex_success_bool
\group_insert_after:N \prg_return_true:
\else:
\group_insert_after:N \prg_return_false:
@@ -1304,7 +1389,7 @@
}
\cs_new_protected_nopar:Npn \regex_extract_after_group:N #1
{
- \if_bool:N \l_regex_success_bool
+ \if_meaning:w \c_true_bool \l_regex_success_bool
\regex_extract:
\group_insert_after:N \seq_set_eq:NN
\group_insert_after:N #1
@@ -1359,7 +1444,7 @@
}
\cs_new_protected:Npn \regex_count:NnN #1#2#3
{
- \regex_check_nfa:NTF #1
+ \regex_check_nfa:NT #1
{
\regex_user_aux:n
{
@@ -1375,9 +1460,8 @@
\regex_count_after_group:N #3
}
}
- { }
}
-\cs_new_protected:Npn \regex_extract:nnN #1#2#3
+\cs_new_protected:Npn \regex_extract_once:nnN #1#2#3
{
\regex_user_aux:n
{
@@ -1386,7 +1470,8 @@
\regex_extract_after_group:N #3
}
}
-\prg_new_protected_conditional:Npnn \regex_extract:nnN #1#2#3 { T , F , TF }
+\prg_new_protected_conditional:Npnn \regex_extract_once:nnN #1#2#3
+ { T , F , TF }
{
\regex_user_aux:n
{
@@ -1396,9 +1481,9 @@
\regex_return_after_group:
}
}
-\cs_new_protected:Npn \regex_extract:NnN #1#2#3
+\cs_new_protected:Npn \regex_extract_once:NnN #1#2#3
{
- \regex_check_nfa:NTF #1
+ \regex_check_nfa:NT #1
{
\regex_user_aux:n
{
@@ -1407,9 +1492,9 @@
\regex_extract_after_group:N #3
}
}
- { }
}
-\prg_new_protected_conditional:Npnn \regex_extract:NnN #1#2#3 { T , F , TF }
+\prg_new_protected_conditional:Npnn \regex_extract_once:NnN #1#2#3
+ { T , F , TF }
{
\regex_check_nfa:NTF #1
{
@@ -1423,6 +1508,48 @@
}
{ \prg_return_false: }
}
+\cs_new_protected:Npn \regex_extract_all:nnN #1#2#3
+ {
+ \regex_user_aux:n
+ {
+ \seq_gclear:N \g_regex_extract_all_seq
+ \tl_set:Nn \l_regex_every_match_tl { \regex_extract_all_aux: }
+ \regex_build:n {#1}
+ \regex_match:n {#2}
+ \regex_extract_all_after_group:N #3
+ }
+ }
+\cs_new_protected:Npn \regex_extract_all:NnN #1#2#3
+ {
+ \regex_check_nfa:NT #1
+ {
+ \regex_user_aux:n
+ {
+ \seq_gclear:N \g_regex_extract_all_seq
+ \tl_set:Nn \l_regex_every_match_tl { \regex_extract_all_aux: }
+ \regex_use:N #1
+ \regex_match:n {#2}
+ \regex_extract_all_after_group:N #3
+ }
+ }
+ }
+\cs_new_protected_nopar:Npn \regex_extract_all_aux:
+ {
+ \regex_extract:
+ \seq_gconcat:NNN \g_regex_extract_all_seq
+ \g_regex_extract_all_seq \g_regex_submatches_seq
+ \regex_match_once:
+ }
+\cs_new_protected_nopar:Npn \regex_extract_all_after_group:N #1
+ {
+ \seq_if_empty:NF \g_regex_extract_all_seq
+ {
+ \regex_extract:
+ \group_insert_after:N \seq_set_eq:NN
+ \group_insert_after:N #1
+ \group_insert_after:N \g_regex_extract_all_seq
+ }
+ }
\cs_new_protected:Npn \regex_split:nnN #1#2#3
{
\regex_user_aux:n
@@ -1436,7 +1563,7 @@
}
\cs_new_protected:Npn \regex_split:NnN #1#2#3
{
- \regex_check_nfa:NTF #1
+ \regex_check_nfa:NT #1
{
\regex_user_aux:n
{
@@ -1447,7 +1574,6 @@
\regex_split_after_group:N #3
}
}
- { }
}
\cs_new_protected_nopar:Npn \regex_split_aux:
{
@@ -1459,9 +1585,8 @@
{
\seq_gput_left:Nx \g_regex_submatches_seq
{
- \str_from_to:Nnn \l_regex_query_str
- { \int_use:N \l_regex_start_step_int }
- { \l_regex_tmpa_tl }
+ \regex_query_substr:NN
+ \l_regex_start_step_int \l_regex_tmpa_tl
}
}
{ \msg_error:nn { regex } { internal } }
@@ -1480,9 +1605,8 @@
{
\seq_gput_right:Nx \g_regex_split_seq
{
- \str_from_to:Nnn \l_regex_query_str
- { \int_use:N \l_regex_start_step_int }
- { \int_use:N \l_regex_current_step_int }
+ \regex_query_substr:NN
+ \l_regex_start_step_int \l_regex_current_step_int
}
}
\group_insert_after:N \seq_set_eq:NN
@@ -1494,40 +1618,57 @@
\str_aux_escape:NNNn
\prg_do_nothing:
\regex_replacement_escaped:N
- \regex_replacement_raw:N
+ \prg_do_nothing:
{#1}
\tl_set_eq:NN \l_regex_replacement_tl \g_str_result_tl
\tl_set:Nx \l_regex_replacement_tl
{ \l_regex_replacement_tl \prg_do_nothing: }
}
-\cs_new_nopar:Npn \regex_replacement_raw:N { \exp_not:N \prg_do_nothing: }
\cs_new_nopar:Npn \regex_replacement_escaped:N #1
{
- \if_num:w 9 < 1 #1 \exp_stop_f:
- \exp_not:N \regex_replacement_escaped_ii:nN {#1}
- \else:
- #1
- \fi:
+ \regex_token_if_other_digit:NTF #1
+ {
+ \exp_not:n
+ { \exp_not:n { \seq_item:Nn \g_regex_submatches_seq } } {#1}
+ }
+ {
+ \token_if_eq_charcode:NNTF g #1
+ { \exp_not:N \regex_replacement_submatch:w }
+ { #1 }
+ }
}
-\cs_new_nopar:Npn \regex_replacement_escaped_ii:nN #1#2
+\cs_new_nopar:Npn \regex_replacement_submatch:w #1
{
- \regex_token_if_other_digit:NTF #2
- { \regex_replacement_escaped_ii:nN {#1#2} }
- { \exp_not:N \seq_item:Nn \exp_not:N \g_regex_submatches_seq {#1} #2 }
+ \exp_after:wN \token_if_eq_meaning:NNTF \c_lbrace_str #1
+ { \regex_replacement_submatch_aux:nN { } }
+ {
+ \regex_token_if_other_digit:NTF #1
+ { \exp_not:n { \seq_item:Nn \g_regex_submatches_seq } }
+ { \msg_expandable_error:n { \g misused~in~replacement~text. } }
+ #1
+ }
}
-\prg_new_conditional:Npnn \regex_token_if_other_digit:N #1 { TF }
+\cs_new_nopar:Npn \regex_replacement_submatch_aux:nN #1 #2
{
- \if_num:w 9 < 1 \exp_not:N #1 \exp_stop_f:
- \prg_return_true:
- \else:
- \prg_return_false:
- \fi:
+ \regex_token_if_other_digit:NTF #2
+ { \regex_replacement_submatch_aux:nN {#1#2} }
+ {
+ \exp_not:n { \seq_item:Nn \g_regex_submatches_seq } {#1}
+ \exp_after:wN \token_if_eq_meaning:NNF \c_rbrace_str #2
+ {
+ \msg_expandable_error:n { \g misused~in~replacement~text. }
+ #2
+ }
+ }
}
\cs_new_protected_nopar:Npn \regex_replace_after_group:N #1
{
- \group_insert_after:N \tl_set_eq:NN
+ \group_insert_after:N \tl_set:Nx
\group_insert_after:N #1
- \group_insert_after:N \g_regex_replaced_str
+ \group_insert_after:N {
+ \group_insert_after:N \tl_to_str:N
+ \group_insert_after:N \g_regex_replaced_str
+ \group_insert_after:N }
}
\cs_new_protected:Npn \regex_replace_once_aux:Nn #1#2
{
@@ -1539,15 +1680,16 @@
\regex_extract:
\regex_extract_aux:nTF {0}
{
+ \cs_set_nopar:Npn \regex_tmp:w
+ { \str_skip_do:nn { \l_regex_tmpb_tl } { } }
\tl_gset:Nx \g_regex_replaced_str
{
- \str_from_to:Nnn \l_regex_query_str {0} { \l_regex_tmpa_tl }
+ \regex_query_substr:NN \c_zero \l_regex_tmpa_tl
\l_regex_replacement_tl
- \str_from_to:Nnn \l_regex_query_str
- { \l_regex_tmpb_tl } { \c_max_int }
+ \exp_after:wN \regex_tmp:w \l_regex_query_other_str
}
}
- { \tl_gset_eq:NN \g_regex_replaced_str \l_regex_query_str }
+ { \tl_gset_eq:NN \g_regex_replaced_str \l_regex_query_other_str }
\group_end:
}
\cs_new_protected:Npn \regex_replace_once:nnN #1#2#3
@@ -1592,12 +1734,10 @@
\tl_gclear:N \g_regex_replaced_str
#2
\exp_args:No \regex_match:n {#1}
+ \cs_set_nopar:Npn \regex_tmp:w
+ { \str_skip_do:nn { \l_regex_start_step_int } { } }
\tl_gput_right:Nx \g_regex_replaced_str
- {
- \str_from_to:Nnn \l_regex_query_str
- { \int_use:N \l_regex_start_step_int }
- { \c_max_int }
- }
+ { \exp_after:wN \regex_tmp:w \l_regex_query_other_str }
\group_end:
}
\cs_new_protected_nopar:Npn \regex_replace_all_aux:
@@ -1607,9 +1747,8 @@
{
\tl_gput_right:Nx \g_regex_replaced_str
{
- \str_from_to:Nnn \l_regex_query_str
- { \int_use:N \l_regex_start_step_int }
- { \l_regex_tmpa_tl }
+ \regex_query_substr:NN
+ \l_regex_start_step_int \l_regex_tmpa_tl
\l_regex_replacement_tl
}
}
@@ -1632,6 +1771,26 @@
\regex_replacement:n {#2}
}
}
+\msg_new:nnn { regex } { -998 } { Unsupported~construct }
+\msg_new:nnn { regex } { -997 }
+ { The~regular~expression~is~too~large~(32768~states). }
+\msg_new:nnn { regex } { 1 } { \iow_char:N\\~at~end~of~pattern }
+\msg_new:nnn { regex } { 4 }
+ { Numbers~out~of~order~in~\iow_char:N\{\iow_char\}~quantifier. }
+\msg_new:nnn { regex } { 6 }
+ { Missing~terminating~\iow_char:N\]~for~character~class }
+\msg_new:nnn { regex } { 7 }
+ { Invalid~escape~sequence~in~character~class }
+\msg_new:nnn { regex } { 8 }
+ { Range~out~of~order~in~character~class }
+\msg_new:nnn { regex } { 22 } { Mismatched~parentheses }
+\msg_new:nnn { regex } { 34 }
+ { Character~value~in~\iow_char:N\\x{...}~sequence~is~too~large }
+\msg_new:nnn { regex } { not-nfa }
+ {
+ LaTeX~was~expecting~a~regular~expression~variable.\\
+ Instead,~LaTeX~found~'#1'.
+ }
%%
%%
%% End of file `l3regex-trace.sty'.
diff --git a/Master/texmf-dist/tex/latex/l3experimental/l3str/l3regex.sty b/Master/texmf-dist/tex/latex/l3experimental/l3str/l3regex.sty
index 5da00fdd3d0..c57f415bc47 100644
--- a/Master/texmf-dist/tex/latex/l3experimental/l3str/l3regex.sty
+++ b/Master/texmf-dist/tex/latex/l3experimental/l3str/l3regex.sty
@@ -46,113 +46,121 @@
%%
%% -----------------------------------------------------------------------
\RequirePackage{expl3}
-\GetIdInfo$Id: l3regex.dtx 2895 2011-10-09 15:58:19Z joseph $
+\GetIdInfo$Id: l3regex.dtx 2943 2011-10-30 15:59:43Z bruno $
{L3 Experimental Regular Expressions}
\ProvidesExplPackage
{\ExplFileName}{\ExplFileDate}{\ExplFileVersion}{\ExplFileDescription}
\RequirePackage{l3str}
+\int_const:Nn \c_forty_eight { 48 }
+\int_const:Nn \c_fifty_eight { 58 }
+\int_const:Nn \c_sixty_five { 65 }
+\int_const:Nn \c_ninety_one { 91 }
+\int_const:Nn \c_ninety_seven { 97 }
+\int_const:Nn \c_one_hundred_twenty_three { 123 }
+\int_const:Nn \c_one_hundred_twenty_seven { 127 }
\cs_new:Npn \regex_tmp:w { }
\tl_new:N \g_regex_tmpa_tl
\tl_new:N \l_regex_tmpa_tl
\tl_new:N \l_regex_tmpb_tl
\int_new:N \l_regex_tmpa_int
-\tl_new:N \l_regex_pattern_str
+\int_new:N \l_regex_tmpb_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
+\seq_new:N \l_regex_group_begin_seq
+\seq_new:N \l_regex_group_end_seq
\int_new:N \l_regex_capturing_group_int
\seq_new:N \l_regex_capturing_group_seq
\tl_new:N \l_regex_one_or_group_tl
-\int_new:N \l_regex_repetition_int
-\bool_new:N \l_regex_look_behind_bool
-\tl_new:N \l_regex_look_behind_str
\cs_new_eq:NN \regex_build_tmp_class:n \use_none:n
\bool_new:N \l_regex_class_bool
\tl_new:N \l_regex_class_tl
\tl_const:Nn \c_regex_d_tl
{
- \regex_item_range:nn {48} {57} % 0--9
+ \regex_item_range:nn { \c_forty_eight } { 57 } % 0--9
}
\tl_const:Nn \c_regex_D_tl
{
- \regex_item_more:n {57} % 9
- \regex_item_range:nn {0} {47} % 0
+ \regex_item_geq:n { \c_fifty_eight } % > `9
+ \regex_item_range:nn { \c_zero } { 47 } % 0
}
\tl_const:Nn \c_regex_h_tl
{
- \regex_item_equal:n {32} % space
- \regex_item_equal:n {9} % tab
+ \regex_item_equal:n { \c_thirty_two } % space
+ \regex_item_equal:n { \c_nine } % tab
}
\tl_const:Nn \c_regex_H_tl
{
- \regex_item_neq:n {32} % space
- \regex_item_neq:n {9} % tab
- \regex_break_true:w
+ \regex_item_geq:n { 33 } % > space
+ \regex_item_range:nn { \c_ten } { 31 } % tab < ... < space
+ \regex_item_range:nn { \c_zero } { \c_eight } % < tab
}
\tl_const:Nn \c_regex_s_tl
{
- \regex_item_equal:n {32} % space
- \regex_item_neq:n {11} % vtab
- \regex_item_range:nn {9} {13} % tab, lf, vtab, ff, cr
+ \regex_item_equal:n { \c_thirty_two } % space
+ \regex_item_range:nn { \c_nine } { \c_ten } % tab, lf
+ \regex_item_range:nn { \c_twelve } { \c_thirteen } % ff, cr
}
\tl_const:Nn \c_regex_S_tl
{
- \regex_item_more:n {32} % > space
- \regex_item_range:nn {14} {31} % tab < ... < space
- \regex_item_range:nn {0} {8} % < tab
- \regex_item_equal:n {11} % vtab
+ \regex_item_geq:n { 33 } % > space
+ \regex_item_range:nn { \c_fourteen } { 31 } % tab < ... < space
+ \regex_item_range:nn { \c_zero } { \c_eight } % < tab
+ \regex_item_equal:n { \c_eleven } % vtab
}
\tl_const:Nn \c_regex_v_tl
{
- \regex_item_range:nn {10} {13} % lf, vtab, ff, cr
+ \regex_item_range:nn { \c_ten } { \c_thirteen } % lf, vtab, ff, cr
}
\tl_const:Nn \c_regex_V_tl
{
- \regex_item_more:n {13} % cr
- \regex_item_range:nn {0} {9} % < lf
+ \regex_item_geq:n { \c_fourteen } % >cr
+ \regex_item_range:nn { \c_zero } { \c_nine } % < lf
}
\tl_const:Nn \c_regex_w_tl
{
- \regex_item_range:nn {97} {122} % a--z
- \regex_item_range:nn {65} {90} % A--Z
- \regex_item_range:nn {48} {57} % 0--9
- \regex_item_equal:n {95} % _
+ \regex_item_range:nn { \c_ninety_seven } { 122 } % a--z
+ \regex_item_range:nn { \c_sixty_five } { 90 } % A--Z
+ \regex_item_range:nn { \c_forty_eight } { 57 } % 0--9
+ \regex_item_equal:n { 95 } % _
}
\tl_const:Nn \c_regex_W_tl
{
- \regex_item_range:nn {0} {47} % <`0
- \regex_item_range:nn {58} {64} % (`9+1)--(`A-1)
- \regex_item_range:nn {91} {94} % (`Z+1)--(`_-1)
- \regex_item_equal:n {96} % `
- \regex_item_more:n {122} % z
+ \regex_item_range:nn { \c_zero } { 47 } % <`0
+ \regex_item_range:nn { \c_fifty_eight } { 64 } % (`9+1)--(`A-1)
+ \regex_item_range:nn { \c_ninety_one } { 94 } % (`Z+1)--(`_-1)
+ \regex_item_equal:n { 96 } % `
+ \regex_item_geq:n { \c_one_hundred_twenty_three } % z
}
\tl_const:Nn \c_regex_N_tl
{
- \regex_item_neq:n {10} % lf
- \regex_break_true:w
+ \regex_item_geq:n { \c_eleven } % > lf
+ \regex_item_range:nn { \c_zero } { \c_nine } % < lf
}
-\tl_new:N \l_regex_query_str
-\int_new:N \l_regex_start_step_int
-\int_new:N \l_regex_current_char_int
+\tl_new:N \l_regex_query_other_str
\int_new:N \l_regex_current_step_int
+\int_new:N \l_regex_start_step_int
+\int_new:N \l_regex_success_step_int
\int_new:N \l_regex_unique_step_int
+\int_new:N \l_regex_current_char_int
+\int_new:N \l_regex_last_char_int
+\int_new:N \l_regex_case_changed_char_int
+\bool_new:N \l_regex_caseless_bool
\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_max_index_int
\tl_new:N \l_regex_every_match_tl
+\bool_new:N \l_regex_success_bool
\cs_new_protected:Npn \regex_last_match_empty_no:F #1 {#1}
\cs_new_protected:Npn \regex_last_match_empty_yes:F
{ \int_compare:nNnF \l_regex_start_step_int = \l_regex_current_step_int }
\cs_new_eq:NN \regex_last_match_empty:F \regex_last_match_empty_no:F
-\bool_new:N \l_regex_success_bool
\bool_new:N \l_regex_success_empty_bool
-\int_new:N \l_regex_success_step_int
-\prop_new:N \l_regex_success_submatches_prop
\bool_new:N \l_regex_fresh_thread_bool
\seq_new:N \g_regex_submatches_seq
\int_new:N \g_regex_match_count_int
+\seq_new:N \g_regex_extract_all_seq
\seq_new:N \g_regex_split_seq
\tl_new:N \l_regex_replacement_tl
\tl_new:N \g_regex_replaced_str
@@ -169,40 +177,43 @@
\tex_toks:D #1 \exp_after:wN
{ \tex_the:D \tex_toks:D \exp_after:wN #1 \regex_tmp:w }
}
-\cs_new_eq:NN \regex_if_tail_stop:N \quark_if_recursion_tail_stop:N
-\cs_new_protected_nopar:Npn \regex_if_tail_error:Nn #1#2
- { \quark_if_recursion_tail_stop_do:Nn #1 { \regex_build_error:n {#2} } }
-\cs_new_protected_nopar:Npn \regex_build_error:n #1
+\cs_new_nopar:Npn \regex_query_substr:NN #1#2
{
- \msg_error:nnxx { regex } { build-error } {\int_eval:n{#1}}
- {
- \prg_case_int:nnn {#1}
- {
- {-999} {File~not~found}
- {-998} {Unsupported~construct}
- {-997} {The~regular~expression~is~too~large~(32768~states).}
- {1} {\iow_char:N\\~at~end~of~pattern }
- {4} {Numbers~out~of~order~in~\iow_char:N\{\iow_char\}~quantifier.}
- {6} {Missing~terminating~\iow_char:N\]~for~character~class }
- {7} {Invalid~escape~sequence~in~character~class}
- {8} {Range~out~of~order~in~character~class}
- {22} {Mismatched~parentheses}
- {34} {Character~value~in~\iow_char:N\\x{...}~sequence~is~too~large}
- }
- { Internal~bug. }
- }
+ \exp_after:wN \regex_query_substr_aux:NN
+ \exp_after:wN #1
+ \exp_after:wN #2
+ \l_regex_query_other_str
+ \q_stop
+ }
+\cs_new:Npn \regex_query_substr_aux:NN #1#2
+ {
+ \str_skip_do:nn {#1}
+ { \str_collect_do:nn { #2 - #1 } { \use_i_delimit_by_q_stop:nw } }
+ }
+\cs_new_protected_nopar:Npn \regex_seq_pop:N #1
+ {
+ \seq_pop:NN #1 \l_regex_tmpa_tl
+ \l_regex_tmpa_tl
+ }
+\cs_new_protected_nopar:Npn \regex_seq_get:N #1
+ {
+ \seq_get:NN #1 \l_regex_tmpa_tl
+ \l_regex_tmpa_tl
}
-\msg_new:nnn { regex } { build-error } { (error~#1): ~ #2 }
-\cs_new_nopar:Npn \regex_break_true:w #1 \regex_break_point:TF #2 #3 {#2}
-\cs_new_nopar:Npn \regex_break_false:w #1 \regex_break_point:TF #2 #3 {#3}
-\cs_new_eq:NN \regex_break_point:TF \use_ii:nn
-\cs_new_nopar:Npn \regex_item_equal:n #1
+\cs_new_protected_nopar:Npn \regex_item_dot:T
+ { \int_compare:nNnF \l_regex_current_char_int = \c_minus_one }
+\cs_new_protected_nopar:Npn \regex_break_true:w
+ #1 \regex_break_point:TF #2 #3 {#2}
+\cs_new_protected_nopar:Npn \regex_break_false:w
+ #1 \regex_break_point:TF #2 #3 {#3}
+\cs_new_protected_nopar:Npn \regex_break_point:TF #1 #2 { #2 }
+\cs_new_protected_nopar:Npn \regex_item_caseful_equal:n #1
{
\if_num:w #1 = \l_regex_current_char_int
\exp_after:wN \regex_break_true:w
\fi:
}
-\cs_new_nopar:Npn \regex_item_range:nn #1 #2
+\cs_new_protected_nopar:Npn \regex_item_caseful_range:nn #1 #2
{
\reverse_if:N \if_num:w #1 > \l_regex_current_char_int
\reverse_if:N \if_num:w #2 < \l_regex_current_char_int
@@ -210,24 +221,60 @@
\fi:
\fi:
}
-\cs_new_nopar:Npn \regex_item_less:n #1
+\cs_new_protected_nopar:Npn \regex_item_caseful_geq:n #1
{
- \if_num:w #1 > \l_regex_current_char_int
+ \reverse_if:N \if_num:w #1 > \l_regex_current_char_int
\exp_after:wN \regex_break_true:w
\fi:
}
-\cs_new_nopar:Npn \regex_item_more:n #1
+\cs_new_protected_nopar:Npn \regex_item_caseless_equal:n #1
{
- \if_num:w #1 < \l_regex_current_char_int
+ \if_num:w #1 = \l_regex_current_char_int
+ \exp_after:wN \regex_break_true:w
+ \fi:
+ \if_num:w #1 = \l_regex_case_changed_char_int
\exp_after:wN \regex_break_true:w
\fi:
}
-\cs_new_nopar:Npn \regex_item_neq:n #1
+\cs_new_protected_nopar:Npn \regex_item_caseless_range:nn #1 #2
{
- \if_num:w #1 = \l_regex_current_char_int
- \exp_after:wN \regex_break_false:w
+ \reverse_if:N \if_num:w #1 > \l_regex_current_char_int
+ \reverse_if:N \if_num:w #2 < \l_regex_current_char_int
+ \exp_after:wN \exp_after:wN \exp_after:wN \regex_break_true:w
+ \fi:
+ \fi:
+ \reverse_if:N \if_num:w #1 > \l_regex_case_changed_char_int
+ \reverse_if:N \if_num: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_item_caseless_geq:n #1
+ {
+ \reverse_if:N \if_num:w #1 > \l_regex_current_char_int
+ \exp_after:wN \regex_break_true:w
+ \fi:
+ \reverse_if:N \if_num:w #1 > \l_regex_case_changed_char_int
+ \exp_after:wN \regex_break_true:w
+ \fi:
+ }
+\cs_new:Npn \regex_item_equal:n { \regex_item_caseful_equal:n }
+\cs_new:Npn \regex_item_range:nn { \regex_item_caseful_range:nn }
+\cs_new:Npn \regex_item_geq:n { \regex_item_caseful_geq:n }
+\cs_new_protected_nopar:Npn \regex_build_caseless:
+ {
+ \bool_set_true:N \l_regex_caseless_bool
+ \cs_set:Npn \regex_item_equal:n { \regex_item_caseless_equal:n }
+ \cs_set:Npn \regex_item_range:nn { \regex_item_caseless_range:nn }
+ \cs_set:Npn \regex_item_geq:n { \regex_item_caseless_geq:n }
+ }
+\cs_new_protected_nopar:Npn \regex_build_caseful:
+ {
+ \bool_set_false:N \l_regex_caseless_bool
+ \cs_set:Npn \regex_item_equal:n { \regex_item_caseful_equal:n }
+ \cs_set:Npn \regex_item_range:nn { \regex_item_caseful_range:nn }
+ \cs_set:Npn \regex_item_geq:n { \regex_item_caseful_geq:n }
+ }
\cs_new_protected:Npn \regex_get_digits:nw #1
{
\tex_afterassignment:D \regex_tmp:w
@@ -235,65 +282,71 @@
{
\exp_not:n {#1}
{ \if_false: } } \fi:
- \regex_get_digits_aux:N
+ \regex_get_digits_aux:NN
}
-\cs_new_nopar:Npn \regex_get_digits_aux:N #1
+\cs_new_nopar:Npn \regex_get_digits_aux:NN #1#2
{
- \if_num:w 9 < 1 \exp_not:N #1 \exp_stop_f:
- \else:
- \if_charcode:w \c_space_token \exp_not:N #1
+ \if_meaning:w \regex_build_raw:N #1
+ \if_charcode:w \c_space_token \exp_not:N #2
\else:
- \regex_get_digits_end:w
+ \if_num:w 9 < 1 \exp_not:N #2 \exp_stop_f:
+ #2
+ \else:
+ \regex_get_digits_end:w #1 #2
+ \fi:
\fi:
+ \else:
+ \regex_get_digits_end:w #1 #2
\fi:
- #1 \regex_get_digits_aux:N
+ \regex_get_digits_aux:NN
}
-\cs_new_nopar:Npn \regex_get_digits_end:w
- \fi: \fi: #1 \regex_get_digits_aux:N
+\cs_new_nopar:Npn \regex_get_digits_end:w #1 \fi: #2 \regex_get_digits_aux:NN
{
- \fi: \fi:
+ \fi: #2
\if_false: { { \fi: } }
#1
}
+\prg_new_conditional:Npnn \regex_token_if_other_digit:N #1 { TF }
+ {
+ \if_num:w \c_nine < 1 \exp_not:N #1 \exp_stop_f:
+ \prg_return_true: \else: \prg_return_false: \fi:
+ }
\prg_new_conditional:Npnn \regex_aux_char_if_special:N #1 { TF }
{
- \if_num:w `#1 < 97 \exp_stop_f:
- \if_num:w `#1 < 58 \exp_stop_f:
- \if_num:w \int_eval:w (`#1 - \c_eight)/\c_sixteen = \c_two
- \prg_return_true:
- \else:
- \prg_return_false:
- \fi:
+ \if_num:w `#1 < \c_ninety_one
+ \if_num:w `#1 < \c_fifty_eight
+ \if_num:w `#1 < \c_forty_eight
+ \if_num:w `#1 < \c_thirty_two
+ \prg_return_false: \else: \prg_return_true: \fi:
+ \else: \prg_return_false: \fi:
\else:
- \if_num:w \int_eval:w `#1 / 26 = \c_three
- \prg_return_false:
- \else:
- \prg_return_true:
- \fi:
+ \if_num:w `#1 < \c_sixty_five
+ \prg_return_true: \else: \prg_return_false: \fi:
\fi:
\else:
- \if_num:w \int_eval:w `#1 / \c_five = 25 \exp_stop_f:
- \prg_return_true:
+ \if_num:w `#1 < \c_one_hundred_twenty_three
+ \if_num:w `#1 < \c_ninety_seven
+ \prg_return_true: \else: \prg_return_false: \fi:
\else:
- \prg_return_false:
+ \if_num:w `#1 < \c_one_hundred_twenty_seven
+ \prg_return_true: \else: \prg_return_false: \fi:
\fi:
\fi:
}
\prg_new_conditional:Npnn \regex_aux_char_if_alphanumeric:N #1 { TF }
{
- \if_num:w `#1 < 91 \exp_stop_f:
- \if_num:w `#1 < 65 \exp_stop_f:
- \if_num:w \c_nine < 1 #1 \exp_stop_f:
- \prg_return_true:
- \else:
- \prg_return_false:
- \fi:
+ \if_num:w `#1 < \c_ninety_one
+ \if_num:w `#1 < \c_fifty_eight
+ \if_num:w `#1 < \c_forty_eight
+ \prg_return_false: \else: \prg_return_true: \fi:
\else:
- \prg_return_true:
+ \if_num:w `#1 < \c_sixty_five
+ \prg_return_false: \else: \prg_return_true: \fi:
\fi:
\else:
- \if_num:w \int_eval:w (`#1-\c_six)/26 = \c_four
- \prg_return_true:
+ \if_num:w `#1 < \c_one_hundred_twenty_three
+ \if_num:w `#1 < \c_ninety_seven
+ \prg_return_false: \else: \prg_return_true: \fi:
\else:
\prg_return_false:
\fi:
@@ -301,8 +354,8 @@
}
\cs_new_protected_nopar:Npn \regex_build_new_state:
{
- \int_compare:nNnTF \l_regex_max_state_int > {32766}
- { \regex_build_error:n {-997} }
+ \int_compare:nNnTF \l_regex_max_state_int > { 32766 }
+ { \msg_error:nn { regex } { -997 } }
{
\int_incr:N \l_regex_max_state_int
\tex_toks:D \l_regex_max_state_int { \s_regex_toks }
@@ -314,15 +367,15 @@
{
\regex_build_new_state:
\regex_toks_put_right:Nx \l_regex_left_state_int
- { #1 { \int_use:N #2 } }
+ { #1 { \int_eval:n { #2 - \l_regex_left_state_int } } }
}
\cs_new_protected_nopar:Npn \regex_build_transitions_aux:NNNN #1#2#3#4
{
\regex_build_new_state:
\regex_toks_put_right:Nx \l_regex_left_state_int
{
- #1 { \int_use:N #2 }
- #3 { \int_use:N #4 }
+ #1 { \int_eval:n { #2 - \l_regex_left_state_int } }
+ #3 { \int_eval:n { #4 - \l_regex_left_state_int } }
}
}
\cs_new_protected:Npn \regex_build:n #1
@@ -363,25 +416,19 @@
\cs_set_eq:NN \regex_build_control:N \regex_build_default_control:N
\cs_set_eq:NN \regex_build_raw:N \regex_build_default_raw:N
\int_set_eq:NN \l_regex_capturing_group_int \c_zero
- \int_zero:N \l_regex_left_state_int
- \int_zero:N \l_regex_right_state_int
\int_zero:N \l_regex_max_state_int
\regex_build_new_state:
\regex_build_new_state:
\regex_toks_put_right:Nx \l_regex_left_state_int
- {
- \regex_action_start_wildcard:nn
- { \int_use:N \l_regex_left_state_int }
- { \int_use:N \l_regex_right_state_int }
- }
+ { \regex_action_start_wildcard:nn {0} {1} }
}
\cs_new_protected_nopar:Npn \regex_build_end:
{
\seq_if_empty:NF \l_regex_capturing_group_seq
{
- \regex_build_error:n {22}
+ \msg_error:nn { regex } {22}
\prg_replicate:nn
- { \seq_length:N \l_regex_capturing_group_seq } % (
+ { \seq_length:N \l_regex_capturing_group_seq }
{ \regex_build_close_aux: \regex_build_group_: }
}
\regex_toks_put_right:Nx \l_regex_right_state_int
@@ -399,7 +446,13 @@
\regex_toks_put_right:Nx \l_regex_left_state_int
{
\exp_not:N \int_compare:nNnT {#1} = \l_regex_current_step_int
- { \regex_action_free:n { \int_use:N \l_regex_right_state_int } }
+ {
+ \regex_action_free:n
+ {
+ \int_eval:n
+ { \l_regex_right_state_int - \l_regex_left_state_int }
+ }
+ }
}
}
\cs_new_protected_nopar:cpn { regex_build_$: } % $
@@ -409,71 +462,72 @@
{
\exp_not:N \int_compare:nNnT
\c_minus_one = \l_regex_current_char_int
- { \regex_action_free:n { \int_use:N \l_regex_right_state_int } }
+ {
+ \regex_action_free:n
+ {
+ \int_eval:n
+ { \l_regex_right_state_int - \l_regex_left_state_int }
+ }
+ }
}
}
\cs_new_eq:Nc \regex_build_Z: { regex_build_$: } %$
\cs_new_eq:Nc \regex_build_z: { regex_build_$: } %$
\cs_new_protected_nopar:Npn \regex_build_b:
{
- \bool_set_true:N \l_regex_look_behind_bool
\regex_build_new_state:
\regex_toks_put_right:Nx \l_regex_left_state_int
{
\exp_not:N \regex_if_word_boundary:TF
- { \regex_action_free:n { \int_use:N \l_regex_right_state_int } }
+ {
+ \regex_action_free:n
+ {
+ \int_eval:n
+ { \l_regex_right_state_int - \l_regex_left_state_int }
+ }
+ }
{ }
}
}
\cs_new_protected_nopar:Npn \regex_build_B:
{
- \bool_set_true:N \l_regex_look_behind_bool
\regex_build_new_state:
\regex_toks_put_right:Nx \l_regex_left_state_int
{
\exp_not:N \regex_if_word_boundary:TF
{ }
- { \regex_action_free:n { \int_use:N \l_regex_right_state_int } }
+ {
+ \regex_action_free:n
+ {
+ \int_eval:n
+ { \l_regex_right_state_int - \l_regex_left_state_int }
+ }
+ }
}
}
\cs_new_protected_nopar:Npn \regex_if_word_boundary:TF
{
- \tl_if_empty:NTF \l_regex_look_behind_str
- { \c_regex_w_tl }
- {
- \group_begin:
- \cs_set_nopar:Npx \regex_tmp:w
- {
- \int_set:Nn \l_regex_current_char_int
- { ` \str_head:N \l_regex_look_behind_str }
- }
- \regex_tmp:w
- \c_regex_w_tl
- \regex_break_point:TF
- { \group_end: \c_regex_W_tl }
- { \group_end: \c_regex_w_tl }
- }
+ \group_begin:
+ \int_set_eq:NN \l_regex_current_char_int \l_regex_last_char_int
+ \c_regex_w_tl
+ \regex_break_point:TF
+ { \group_end: \c_regex_W_tl \regex_item_equal:n { -1 } }
+ { \group_end: \c_regex_w_tl }
\regex_break_point:TF
}
\cs_new_protected_nopar:Npn \regex_build_default_raw:N #1
{
\cs_set:Npx \regex_build_tmp_class:n ##1
{
- \exp_not:n { \exp_not:N \if_num:w }
- \int_value:w `#1 = \l_regex_current_char_int
- \regex_action_cost:n { ##1 }
- \exp_not:n { \exp_not:N \fi: }
+ \regex_item_equal:n { \int_value:w `#1 }
+ \regex_break_point:TF { \regex_action_cost:n { ##1 } } { }
}
\regex_build_one_quantifier:
}
\cs_new_protected_nopar:cpn { regex_build_.: }
{
\cs_set:Npn \regex_build_tmp_class:n ##1
- {
- \exp_not:N \if_num:w \c_minus_one < \l_regex_current_char_int
- \regex_action_cost:n {##1}
- \exp_not:N \fi:
- }
+ { \regex_item_dot:T { \regex_action_cost:n {##1} } }
\regex_build_one_quantifier:
}
\cs_new_protected_nopar:Npn \regex_build_char_type:N #1
@@ -481,9 +535,7 @@
\cs_set:Npn \regex_build_tmp_class:n ##1
{
\exp_not:N #1
- \exp_not:N \regex_break_point:TF
- { \regex_action_cost:n {##1} }
- { }
+ \regex_break_point:TF { \regex_action_cost:n {##1} } { }
}
\regex_build_one_quantifier:
}
@@ -518,16 +570,8 @@
{
\exp_not:o \l_regex_class_tl
\bool_if:NTF \l_regex_class_bool
- {
- \exp_not:N \regex_break_point:TF
- { \regex_action_cost:n {##1} }
- { }
- }
- {
- \exp_not:N \regex_break_point:TF
- { }
- { \regex_action_cost:n {##1} }
- }
+ { \regex_break_point:TF { \regex_action_cost:n {##1} } { } }
+ { \regex_break_point:TF { } { \regex_action_cost:n {##1} } }
}
\regex_build_one_quantifier:
}
@@ -553,7 +597,7 @@
\cs_new_protected_nopar:Npn \regex_class_single:N #1
{
\tl_put_right:Nx \l_regex_class_tl
- { \exp_not:N \regex_item_equal:n { \int_value:w `#1 } }
+ { \regex_item_equal:n { \int_value:w `#1 } }
}
\cs_new_protected_nopar:Npn \regex_class_range:Nw #1#2#3
{
@@ -572,14 +616,14 @@
\cs_new_protected_nopar:Npn \regex_class_range_put:NN #1#2
{
\if_num:w `#1 > `#2 \exp_stop_f:
- \regex_build_error:n {8}
+ \msg_error:nn { regex } {8}
\else:
\tl_put_right:Nx \l_regex_class_tl
{
\if_num:w `#1 = `#2 \exp_stop_f:
- \exp_not:N \regex_item_equal:n
+ \regex_item_equal:n
\else:
- \exp_not:N \regex_item_range:nn { \int_value:w `#1 }
+ \regex_item_range:nn { \int_value:w `#1 }
\fi:
{ \int_value:w `#2 }
}
@@ -651,26 +695,29 @@
\exp_not:N \regex_build_raw:N \c_lbrace_str #1#2
}
}
-\cs_new_protected_nopar:Npn \regex_build_quantifier_lbrace:nnw #1#2#3
+\cs_new_protected_nopar:Npn \regex_build_quantifier_lbrace:nnw #1#2#3#4
{
- \str_if_eq:xxTF { \exp_not:N #3 } { \c_rbrace_str }
+ \str_if_eq:xxTF
+ { \exp_not:n {#3#4} }
+ { \exp_not:N \regex_build_control:N \c_rbrace_str }
{
\tl_if_empty:nTF {#2}
- { \regex_build_quantifier_aux:nnN { {#1} {\c_max_int} } {nn} }
+ { \regex_build_quantifier_aux:nnNN { {#1} } { n* } }
{
\int_compare:nNnT {#1} > {#2}
- { \regex_build_error:n {4} }
- \regex_build_quantifier_aux:nnN { {#1} {#2} } {nn}
+ { \msg_error:nn { regex } {4} }
+ \regex_build_quantifier_aux:nnNN { {#1} {#2} } { nn }
}
}
{
\regex_build_quantifier_end:n { }
\use:x
{
- \exp_not:n { \exp_args:No \tl_map_function:nN }
- { \c_lbrace_str #1 #2 , }
- \regex_build_raw:N
+ \exp_args:No \tl_map_function:nN
+ { \c_lbrace_str #1 , #2 }
+ \regex_build_raw:N
}
+ #3 #4
}
}
\cs_new_protected_nopar:Npn \regex_build_quantifier_end:n #1
@@ -726,71 +773,27 @@
\regex_action_free:n \l_regex_tmpa_int
}
\cs_new_protected_nopar:Npn \regex_build_one_n: #1
- {
- \int_set_eq:NN \l_regex_tmpa_int \l_regex_right_state_int
- \regex_build_new_state:
- \regex_build_new_state:
- \regex_toks_put_right:Nx \l_regex_tmpa_int
- { %^^A safe \if nesting?
- \exp_not:N \if_num:w #1 > \l_regex_repetition_int
- \regex_action_repeat_move:n
- { \int_use:N \l_regex_left_state_int }
- \exp_not:N \else:
- \regex_action_no_repeat_move:n
- { \int_use:N \l_regex_right_state_int }
- \exp_not:N \fi:
- }
- \regex_toks_put_right:Nx \l_regex_left_state_int
- {
- \regex_build_tmp_class:n
- { \int_use:N \l_regex_tmpa_int }
- }
- }
+ { \prg_replicate:nn {#1} { \regex_build_one_: } }
\cs_new_eq:cN { regex_build_one_n?: } \regex_build_one_n:
-\cs_new_protected_nopar:Npn \regex_build_one_nn: #1#2
+\cs_new_protected_nopar:cpx { regex_build_one_n*: } #1
{
- \regex_build_one_nn_aux:nn {#1}
- {
- \exp_not:N \if_num:w #2 > \l_regex_repetition_int
- \regex_action_repeat_copy:n
- { \int_use:N \l_regex_left_state_int }
- \exp_not:N \fi:
- \regex_action_no_repeat_move:n
- { \int_use:N \l_regex_right_state_int }
- }
+ \exp_not:N \prg_replicate:nn {#1} { \exp_not:N \regex_build_one_: }
+ \exp_not:c { regex_build_one_*: }
}
-\cs_new_protected_nopar:cpn { regex_build_one_nn?: } #1#2
+\cs_new_protected_nopar:cpx { regex_build_one_n*?: } #1
{
- \regex_build_one_nn_aux:nn {#1}
- {
- \regex_action_no_repeat_copy:n
- { \int_use:N \l_regex_right_state_int }
- \exp_not:N \if_num:w #2 > \l_regex_repetition_int
- \regex_action_repeat_move:n
- { \int_use:N \l_regex_left_state_int }
- \exp_not:N \fi:
- }
+ \exp_not:N \prg_replicate:nn {#1} { \exp_not:N \regex_build_one_: }
+ \exp_not:c { regex_build_one_*?: }
}
-\cs_new_protected_nopar:Npn \regex_build_one_nn_aux:nn #1#2
+\cs_new_protected_nopar:Npn \regex_build_one_nn_aux:Nnn #1#2#3
{
- \int_set_eq:NN \l_regex_tmpa_int \l_regex_right_state_int
- \regex_build_new_state:
- \regex_build_new_state:
- \regex_toks_put_right:Nx \l_regex_tmpa_int
- {
- \exp_not:N \if_num:w #1 > \l_regex_repetition_int
- \regex_action_repeat_move:n
- { \int_use:N \l_regex_left_state_int }
- \exp_not:N \else:
- #2
- \exp_not:N \fi:
- }
- \regex_toks_put_right:Nx \l_regex_left_state_int
- {
- \regex_build_tmp_class:n
- { \int_use:N \l_regex_tmpa_int }
- }
+ \prg_replicate:nn {#2} { \regex_build_one_: }
+ \prg_replicate:nn {#3-#2} {#1}
}
+\cs_new_protected_nopar:Npx \regex_build_one_nn:
+ { \regex_build_one_nn_aux:Nnn \exp_not:c { regex_build_one_?: } }
+\cs_new_protected_nopar:cpx { regex_build_one_nn?: }
+ { \regex_build_one_nn_aux:Nnn \exp_not:c { regex_build_one_??: } }
\cs_new_protected_nopar:cpn { regex_build_(: } #1#2
{
\str_if_eq:nnTF { #1 #2 } { \regex_build_control:N ? }
@@ -806,10 +809,19 @@
\cs_new_protected_nopar:Npn \regex_build_open_aux:
{
\regex_build_new_state:
- \seq_push:Nx \l_regex_left_state_seq
- { \int_use:N \l_regex_left_state_int }
- \seq_push:Nx \l_regex_right_state_seq
- { \int_use:N \l_regex_right_state_int }
+ \seq_push:Nx \l_regex_group_begin_seq
+ {
+ \int_set:Nn \l_regex_left_state_int
+ { \int_use:N \l_regex_left_state_int }
+ }
+ \bool_if:NTF \l_regex_caseless_bool
+ { \seq_push:Nn \l_regex_group_end_seq { \regex_build_caseless: } }
+ { \seq_push:Nn \l_regex_group_end_seq { \regex_build_caseful: } }
+ \seq_push:Nx \l_regex_group_end_seq
+ {
+ \int_set:Nn \l_regex_right_state_int
+ { \int_use:N \l_regex_right_state_int }
+ }
\regex_build_begin_alternation:
}
\cs_new_protected_nopar:cpn { regex_build_|: }
@@ -820,7 +832,7 @@
\cs_new_protected_nopar:cpn { regex_build_): }
{
\seq_if_empty:NTF \l_regex_capturing_group_seq
- { \regex_build_error:n {22} }
+ { \msg_error:nn { regex } { 22 } }
{
\regex_build_close_aux:
\regex_build_group_quantifier:
@@ -829,30 +841,41 @@
\cs_new_protected_nopar:Npn \regex_build_close_aux:
{
\regex_build_end_alternation:
- \seq_pop:NN \l_regex_left_state_seq \l_regex_tmpa_tl
- \int_set:Nn \l_regex_left_state_int \l_regex_tmpa_tl
- \seq_pop:NN \l_regex_right_state_seq \l_regex_tmpa_tl
- \int_set:Nn \l_regex_right_state_int \l_regex_tmpa_tl
+ \regex_seq_pop:N \l_regex_group_begin_seq
+ \regex_seq_pop:N \l_regex_group_end_seq
+ \regex_seq_pop:N \l_regex_group_end_seq
}
\cs_new_protected_nopar:Npn \regex_build_begin_alternation:
{
\regex_build_new_state:
- \seq_get:NN \l_regex_left_state_seq \l_regex_tmpa_tl
- \int_set:Nn \l_regex_left_state_int \l_regex_tmpa_tl
+ \regex_seq_get:N \l_regex_group_begin_seq
\regex_toks_put_right:Nx \l_regex_left_state_int
- { \regex_action_free:n { \int_use:N \l_regex_right_state_int } }
+ {
+ \regex_action_free:n
+ {
+ \int_eval:n
+ { \l_regex_right_state_int - \l_regex_left_state_int }
+ }
+ }
}
\cs_new_protected_nopar:Npn \regex_build_end_alternation:
{
- \seq_get:NN \l_regex_right_state_seq \l_regex_tmpa_tl
- \regex_toks_put_right:Nx \l_regex_right_state_int
- { \regex_action_free:n { \l_regex_tmpa_tl } }
+ \int_set_eq:NN \l_regex_left_state_int \l_regex_right_state_int
+ \regex_seq_get:N \l_regex_group_end_seq
+ \regex_toks_put_right:Nx \l_regex_left_state_int
+ {
+ \regex_action_free:n
+ {
+ \int_eval:n
+ { \l_regex_right_state_int - \l_regex_left_state_int }
+ }
+ }
}
\cs_new_protected_nopar:Npn \regex_build_special_group:NN #1#2
{
\cs_if_exist_use:cF { regex_build_special_group_\token_to_str:N #2 : }
{
- \regex_build_error:n { -998 }
+ \msg_error:nn { regex } { -998 }
\regex_build_control:N ( % )
\regex_build_raw:N ?
#1 #2
@@ -863,6 +886,40 @@
\seq_push:Nx \l_regex_capturing_group_seq { * }
\regex_build_open_aux:
}
+\cs_new_protected_nopar:Npn \regex_build_special_group_i:
+ {
+ \regex_build_options:NNN +
+ \regex_build_raw:N i
+ }
+\cs_new_protected_nopar:cpn { regex_build_special_group_-: }
+ {
+ \regex_build_options:NNN -
+ }
+\cs_new_protected_nopar:Npn \regex_build_options:NNN #1#2#3
+ {
+ \token_if_eq_meaning:NNTF \regex_build_raw:N #2
+ {
+ \cs_if_exist_use:cF { regex_build_option_#1#3: }
+ { \msg_error:nnx { regex } { unknown-option } { #3 } }
+ \regex_build_options:NNN #1
+ }
+ {
+ \prg_case_str:nnn { #3 }
+ { % (
+ { ) } { }
+ { - } { \regex_build_options:NNN - }
+ }
+ { \msg_error:nnx { regex } { invalid-in-option } { #3 } }
+ }
+ }
+\cs_new_protected_nopar:cpn { regex_build_option_+i: }
+ {
+ \regex_build_caseless:
+ \cs_set_eq:NN \regex_match_loop_case_hook:
+ \regex_match_loop_caseless_hook:
+ }
+\cs_new_protected_nopar:cpn { regex_build_option_-i: }
+ { \regex_build_caseful: }
\cs_new_protected_nopar:Npn \regex_build_group_quantifier:
{
\tl_set:Nn \l_regex_one_or_group_tl { group }
@@ -891,21 +948,33 @@
\int_set_eq:NN \l_regex_tmpa_int \l_regex_left_state_int
\regex_build_new_state:
\tex_toks:D \l_regex_right_state_int = \tex_toks:D \l_regex_tmpa_int
- \use:x
+ \regex_toks_put_left:Nx \l_regex_right_state_int
+ {
+ \int_set:Nn \l_regex_current_state_int
+ { \int_use:N \l_regex_tmpa_int } % ^^A here we lie!
+ }
+ \cs_set:Npx \regex_tmp:w
{
\tex_toks:D \l_regex_tmpa_int
- { \s_regex_toks #1 { \int_use:N \l_regex_right_state_int } }
+ {
+ \s_regex_toks
+ #1 { \int_eval:n { \l_regex_right_state_int - \l_regex_tmpa_int } }
+ }
}
+ \regex_tmp:w
\regex_build_group_submatches:NN
\l_regex_right_state_int \l_regex_left_state_int
- \int_set_eq:NN \l_regex_right_state_int \l_regex_left_state_int
}
\cs_new_protected_nopar:Npn \regex_build_group_qs_aux:NN #1#2
{
\regex_build_group_shift:N \regex_action_free:n
+ \int_set_eq:NN \l_regex_right_state_int \l_regex_left_state_int
\regex_build_transition_aux:NN \regex_action_free:n #1
#2 \l_regex_tmpa_int
- { \regex_action_free:n { \int_use:N \l_regex_right_state_int } }
+ {
+ \regex_action_free:n
+ { \int_eval:n { \l_regex_right_state_int - \l_regex_tmpa_int } }
+ }
}
\cs_new_protected_nopar:cpn { regex_build_group_?: }
{
@@ -945,77 +1014,63 @@
\regex_action_free:n \l_regex_right_state_int
\regex_action_free:n \l_regex_tmpa_int
}
-\cs_new_protected_nopar:Npn \regex_build_group_n: #1
+\cs_new_protected_nopar:Npn \regex_build_group_n_aux:n #1
{
- \regex_build_group_shift:N \regex_action_repeat_move:n
- \regex_build_transition_aux:NN
- \regex_action_free:n \l_regex_tmpa_int
- \use:x
+ \regex_toks_put_right:Nx \l_regex_right_state_int
{
- \tex_toks:D \l_regex_tmpa_int
- {
- \s_regex_toks
- \exp_not:N \if_num:w #1 > \l_regex_repetition_int
- \tex_the:D \tex_toks:D \l_regex_tmpa_int
- \exp_not:N \else:
- \regex_action_no_repeat_move:n
- { \int_use:N \l_regex_right_state_int }
- \exp_not:N \fi:
- }
+ \regex_action_free:n
+ { \int_eval:n { \l_regex_max_state_int - \l_regex_left_state_int } }
}
- }
-\cs_new_eq:cN { regex_build_group_n?: } \regex_build_group_n:
-\cs_new_protected_nopar:Npn \regex_build_group_nn: #1#2
- {
- \regex_build_group_shift:N \regex_action_repeat_move:n
- \regex_build_transition_aux:NN
- \regex_action_free:n \l_regex_tmpa_int
- \use:x
+ \int_set_eq:NN \l_regex_tmpa_int \l_regex_left_state_int
+ \int_set:Nn \l_regex_tmpb_int { \l_regex_max_state_int + \c_one }
+ \int_set:Nn \l_regex_max_state_int
{
- \tex_toks:D \l_regex_tmpa_int
- {
- \s_regex_toks
- \exp_not:N \if_num:w #1 > \l_regex_repetition_int
- \tex_the:D \tex_toks:D \l_regex_tmpa_int
- \exp_not:N \else:
- \exp_not:N \if_num:w #2 > \l_regex_repetition_int
- \tex_the:D \tex_toks:D \l_regex_tmpa_int
- \exp_not:N \fi:
- \regex_action_no_repeat_copy:n
- { \int_use:N \l_regex_right_state_int }
- \exp_not:N \fi:
- }
+ \l_regex_left_state_int - \c_one
+ + #1 * ( \l_regex_max_state_int - \l_regex_left_state_int + \c_one )
+ }
+ \int_until_do:nNnn \l_regex_tmpb_int > \l_regex_max_state_int
+ {
+ \tex_toks:D \l_regex_tmpb_int = \tex_toks:D \l_regex_tmpa_int
+ \int_incr:N \l_regex_tmpa_int
+ \int_incr:N \l_regex_tmpb_int
}
}
-\cs_new_protected_nopar:cpn { regex_build_group_nn?: } #1#2
- {
- \regex_build_group_shift:N \regex_action_repeat_move:n
+\cs_new_protected_nopar:Npn \regex_build_group_n: #1
+ { % ^^A todo: catch case #1 <= 0.
+ \regex_build_group_n_aux:n {#1}
\regex_build_transition_aux:NN
+ \regex_action_free:n \l_regex_right_state_int
+ \regex_build_group_submatches:NN
+ \l_regex_tmpa_int \l_regex_left_state_int
+ }
+\cs_new_eq:cN { regex_build_group_n?: } \regex_build_group_n:
+\cs_new_protected_nopar:cpn { regex_build_group_n*: } #1
+ { % ^^A todo: catch case #1 <= 0.
+ \regex_build_group_n_aux:n {#1}
+ \regex_build_transitions_aux:NNNN
\regex_action_free:n \l_regex_tmpa_int
- \use:x
- {
- \tex_toks:D \l_regex_tmpa_int
- {
- \s_regex_toks
- \exp_not:N \if_num:w #1 > \l_regex_repetition_int
- \tex_the:D \tex_toks:D \l_regex_tmpa_int
- \exp_not:N \else:
- \regex_action_no_repeat_copy:n
- { \int_use:N \l_regex_right_state_int }
- \exp_not:N \if_num:w #2 > \l_regex_repetition_int
- \tex_the:D \tex_toks:D \l_regex_tmpa_int
- \exp_not:N \fi:
- \exp_not:N \fi:
- }
- }
+ \regex_action_free:n \l_regex_right_state_int
+ \regex_build_group_submatches:NN
+ \l_regex_tmpa_int \l_regex_left_state_int
}
-\cs_new_protected:Npn \regex_if_state_free:nT #1
- {
- \if_num:w \tex_dimen:D #1 = \l_regex_unique_step_int
- \exp_after:wN \use_none:n
- \else:
- \exp_after:wN \use:n
- \fi:
+\cs_new_protected_nopar:cpn { regex_build_group_n*?: } #1
+ { % ^^A todo: catch case #1 <= 0.
+ \regex_build_group_n_aux:n {#1}
+ \regex_build_transitions_aux:NNNN
+ \regex_action_free:n \l_regex_right_state_int
+ \regex_action_free:n \l_regex_tmpa_int
+ \regex_build_group_submatches:NN
+ \l_regex_tmpa_int \l_regex_left_state_int
+ }
+\cs_new_protected_nopar:Npn \regex_build_group_nn: #1#2
+ { % ^^A Not Implemented Yet!
+ \msg_expandable_error:n { Quantifier~{m,n}~not~implemented~yet }
+ \use:c { regex_build_group_n*: } {#1}
+ }
+\cs_new_protected_nopar:cpn { regex_build_group_nn?: } #1#2
+ { % ^^A Not Implemented Yet!
+ \msg_expandable_error:n { Quantifier~{m,n}~not~implemented~yet }
+ \use:c { regex_build_group_n*?: } {#1}
}
\cs_new_protected:Npn \regex_store_state:n #1
{
@@ -1023,23 +1078,24 @@
\tex_skip:D \l_regex_max_index_int #1 sp \scan_stop:
\regex_store_submatches:n {#1}
}
-\cs_new_protected_nopar:Npn \regex_state_use_submatches:
+\cs_new_protected_nopar:Npn \regex_state_use_with_submatches:
{ \regex_state_use_aux:n { } }
\cs_new_protected_nopar:Npn \regex_state_use:
{ \regex_state_use_aux:n { \exp_after:wN \regex_state_use_aux_ii:w } }
-\cs_new:Npn \regex_state_use_aux_ii:w #1 \s_regex_toks { }
-\cs_new_protected:Npn \regex_state_use_aux:n #1
- {
- \regex_if_state_free:nT { \l_regex_current_state_int }
- {
- \tex_dimen:D \l_regex_current_state_int
- = \l_regex_unique_step_int sp \scan_stop:
- #1 \tex_the:D \tex_toks:D \l_regex_current_state_int \scan_stop:
- }
+\cs_new_nopar:Npn \regex_state_use_aux_ii:w #1 \s_regex_toks { }
+\cs_new_protected_nopar:Npn \regex_state_use_aux:n #1
+ {
+ \if_num:w \tex_dimen:D \l_regex_current_state_int
+ < \l_regex_unique_step_int
+ \tex_dimen:D \l_regex_current_state_int
+ = \l_regex_unique_step_int sp \scan_stop:
+ #1 \tex_the:D \tex_toks:D \exp_after:wN \l_regex_current_state_int
+ \fi:
+ \scan_stop:
}
\cs_new_protected_nopar:Npn \regex_disable_submatches:
{
- \cs_set_eq:NN \regex_state_use_submatches: \regex_state_use:
+ \cs_set_eq:NN \regex_state_use_with_submatches: \regex_state_use:
\cs_set_eq:NN \regex_store_submatches:n
\regex_protected_use_none:n
\cs_set_eq:NN \regex_action_submatches:n
@@ -1048,55 +1104,73 @@
\cs_new_protected:Npn \regex_protected_use_none:n #1 { }
\cs_new_protected:Npn \regex_store_submatches:n #1
{
- \exp_after:wN \regex_store_submatches_aux:Nw
- \exp_after:wN \l_regex_current_submatches_prop
- \tex_the:D \tex_toks:D #1 \scan_stop: \q_stop
- { #1 }
+ \tex_toks:D #1 \exp_after:wN
+ {
+ \tex_romannumeral:D
+ \exp_after:wN \regex_store_submatches_aux:w
+ \tex_the:D \tex_toks:D #1
+ }
}
-\cs_new_protected:Npn \regex_store_submatches_aux:Nw #1 #2 \s_regex_toks
+\cs_new_protected:Npn \regex_store_submatches_aux:w #1 \s_regex_toks
{
- \exp_args:No \regex_store_submatches_aux_ii:wnnwwn { #1 }
- #2
- \regex_state_submatches:nn { \c_minus_one } { \q_prop }
+ \regex_store_submatches_aux_ii:Nnnw
+ #1
+ \regex_state_submatches:nn \c_minus_one \q_prop
\s_regex_toks
}
-\cs_new_protected:Npn \regex_store_submatches_aux_ii:wnnwwn
- #1 \regex_state_submatches:nn #2#3 #4 \s_regex_toks #5 \q_stop #6
+\cs_new_protected:Npn \regex_store_submatches_aux_ii:Nnnw
+ \regex_state_submatches:nn #1 #2 #3 \s_regex_toks
{
- \tex_toks:D #6 \exp_after:wN
+ \exp_after:wN \c_zero
+ \exp_after:wN \regex_state_submatches:nn \exp_after:wN
{
- \exp_after:wN \regex_state_submatches:nn \exp_after:wN
- { \int_value:w \int_eval:w \l_regex_unique_step_int + \c_one }
- { #1 }
- \regex_state_submatches:nn {#2} {#3}
- \s_regex_toks
- #5
+ \int_value:w \int_eval:w
+ \l_regex_unique_step_int + \c_one
+ \exp_after:wN
}
+ \exp_after:wN { \l_regex_current_submatches_prop }
+ \regex_state_submatches:nn {#1} {#2}
+ \s_regex_toks
}
\cs_new_protected:Npn \regex_state_submatches:nn #1#2
{
\if_num:w #1 = \l_regex_unique_step_int
- \tl_set:Nn \l_regex_current_submatches_prop {#2}
+ \tl_set:Nn \l_regex_current_submatches_prop { #2 }
\fi:
}
\cs_new_protected:Npn \regex_match:n #1
{
- \tl_set:Nx \l_regex_query_str { \tl_to_other_str:n {#1} }
+ \tl_set:Nx \l_regex_query_other_str { \tl_to_other_str:n {#1} }
\regex_match_initial_setup:
\regex_match_once:
}
\cs_new_protected_nopar:Npn \regex_match_once:
{
\regex_match_setup:
- \exp_after:wN \regex_match_once_aux: \l_regex_query_str
+ \exp_after:wN \regex_match_once_aux: \l_regex_query_other_str
\q_recursion_tail \q_recursion_stop
\bool_if:NT \l_regex_success_bool { \l_regex_every_match_tl }
}
\cs_new_protected_nopar:Npn \regex_match_once_aux:
- { \str_skip_do:nn { \l_regex_start_step_int } { \regex_match_loop:N } }
+ {
+ \int_compare:nNnTF \l_regex_start_step_int = \c_zero
+ {
+ \int_set_eq:NN \l_regex_current_char_int \c_minus_one
+ \regex_match_loop:N
+ }
+ {
+ \str_skip_do:nn
+ { \l_regex_start_step_int - \c_one }
+ { \regex_match_once_aux_ii:N }
+ }
+ }
+\cs_new_protected_nopar:Npn \regex_match_once_aux_ii:N #1
+ {
+ \int_set:Nn \l_regex_current_char_int { `#1 }
+ \regex_match_loop:N
+ }
\cs_new_protected_nopar:Npn \regex_match_initial_setup:
{
- \tl_clear:N \l_regex_look_behind_str
\prg_stepwise_inline:nnnn {1} {1} { \l_regex_max_state_int }
{ \tex_dimen:D ##1 \c_minus_one sp \scan_stop: }
\int_set_eq:NN \l_regex_unique_step_int \c_minus_one
@@ -1118,20 +1192,11 @@
\int_zero:N \l_regex_max_index_int
\regex_store_state:n {1}
}
-\cs_new_protected_nopar:Npn \regex_match_loop_setup:
- {
- \int_incr:N \l_regex_current_step_int
- \int_incr:N \l_regex_unique_step_int
- \bool_set_false:N \l_regex_fresh_thread_bool
- }
\cs_new_eq:NN \s_regex_step \scan_stop:
\cs_new:Npn \regex_break_step:w #1 \s_regex_step { }
\cs_new_protected_nopar:Npn \regex_match_loop:N #1
{
- \regex_match_loop_setup:
- \token_if_eq_meaning:NNTF #1 \q_recursion_tail
- { \int_set_eq:NN \l_regex_current_char_int \c_minus_one }
- { \int_set:Nn \l_regex_current_char_int {`#1} }
+ \regex_match_loop_setup:N #1
\cs_set_nopar:Npx \regex_tmp:w
{
\int_zero:N \l_regex_max_index_int
@@ -1145,19 +1210,49 @@
\exp_after:wN \use_none_delimit_by_q_recursion_stop:w
\fi:
\quark_if_recursion_tail_stop:N #1
- \bool_if:NT \l_regex_look_behind_bool
- { \tl_put_left:Nx \l_regex_look_behind_str {#1} }
\regex_match_loop:N
}
\cs_new_nopar:Npn \regex_match_one_index:n #1
{
- \regex_match_one_index_aux:n { \int_value:w \tex_skip:D #1 }
+ \regex_match_one_index_aux:n
+ { \int_value:w \tex_skip:D #1 }
}
\cs_new_protected_nopar:Npn \regex_match_one_index_aux:n #1
{
\int_set:Nn \l_regex_current_state_int {#1}
\prop_clear:N \l_regex_current_submatches_prop
- \regex_state_use_submatches:
+ \regex_state_use_with_submatches:
+ }
+\cs_new_protected_nopar:Npn \regex_match_loop_setup:N #1
+ {
+ \int_incr:N \l_regex_current_step_int
+ \int_incr:N \l_regex_unique_step_int
+ \bool_set_false:N \l_regex_fresh_thread_bool
+ \int_set_eq:NN \l_regex_last_char_int \l_regex_current_char_int
+ \if_meaning:w #1 \q_recursion_tail
+ \int_set_eq:NN \l_regex_current_char_int \c_minus_one
+ \else:
+ \int_set:Nn \l_regex_current_char_int {`#1}
+ \fi:
+ \regex_match_loop_case_hook:
+ }
+\cs_new_protected_nopar:Npn \regex_match_loop_case_hook: { }
+\cs_new_protected_nopar:Npn \regex_match_loop_caseless_hook:
+ {
+ \int_set_eq:NN \l_regex_case_changed_char_int \l_regex_current_char_int
+ \if_num:w \l_regex_current_char_int < \c_ninety_one
+ \if_num: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_num:w \l_regex_current_char_int < \c_one_hundred_twenty_three
+ \if_num: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_protected_nopar:Npn \regex_action_start_wildcard:nn #1#2
{
@@ -1167,7 +1262,10 @@
\regex_action_cost:n {#1}
}
\cs_new_protected_nopar:Npn \regex_action_cost:n #1
- { \regex_store_state:n {#1} }
+ {
+ \exp_args:Nf \regex_store_state:n %^^A optimize!
+ { \int_eval:n { \l_regex_current_state_int + #1 } }
+ }
\cs_new_protected_nopar:Npn \regex_action_success:
{
\regex_last_match_empty:F
@@ -1184,30 +1282,22 @@
}
\cs_new_protected_nopar:Npn \regex_action_free:n #1
{
- \regex_if_state_free:nT {#1}
+ \cs_set_nopar:Npx \regex_tmp:w
{
- \use:x
- {
- \int_set:Nn \l_regex_current_state_int {#1}
- \regex_store_submatches:n { \l_regex_current_state_int }
- \regex_state_use:
- \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 }
- }
+ \int_add:Nn \l_regex_current_state_int {#1}
+ \regex_state_use:
+ \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 }
}
+ \regex_tmp:w
}
\cs_new_protected_nopar:Npn \regex_action_submatch:n #1
{
\prop_put:Nno \l_regex_current_submatches_prop {#1}
{ \int_use:N \l_regex_current_step_int }
- \regex_store_submatches:n { \l_regex_current_state_int }
}
-\cs_new_protected_nopar:Npn \regex_action_repeat_copy:n { \ERROR }
-\cs_new_protected_nopar:Npn \regex_action_repeat_move:n { \ERROR }
-\cs_new_protected_nopar:Npn \regex_action_no_repeat_copy:n { \ERROR }
-\cs_new_protected_nopar:Npn \regex_action_no_repeat_move:n { \ERROR }
\cs_new_protected_nopar:Npn \regex_extract:
{
\seq_gclear:N \g_regex_submatches_seq
@@ -1217,11 +1307,7 @@
\regex_extract_aux:nTF { ##1 }
{
\seq_gput_right:Nx \g_regex_submatches_seq
- {
- \str_from_to:Nnn \l_regex_query_str
- { \l_regex_tmpa_tl }
- { \l_regex_tmpb_tl }
- }
+ { \regex_query_substr:NN \l_regex_tmpa_tl \l_regex_tmpb_tl }
}
{ \seq_gput_right:Nn \g_regex_submatches_seq { } }
}
@@ -1253,9 +1339,13 @@
= \int_use:N \l_regex_max_state_int
\l_regex_capturing_group_int
= \int_use:N \l_regex_capturing_group_int
- \bool_if:NTF \l_regex_look_behind_bool
- { \bool_set_true:N \l_regex_look_behind_bool }
- { \bool_set_false:N \l_regex_look_behind_bool }
+ \token_if_eq_meaning:NNT
+ \regex_match_loop_case_hook:
+ \regex_match_loop_caseless_hook:
+ {
+ \cs_set_eq:NN \regex_match_loop_case_hook:
+ \regex_match_loop_caseless_hook:
+ }
\prg_stepwise_function:nnnN
{1} {1} {\l_regex_max_state_int}
\regex_set_aux:n
@@ -1269,7 +1359,7 @@
\cs_new:Npn \regex_nfa:Nw #1 #2 \regex_nfa_end:
{ \msg_expandable_error:n { Automaton~#1 used~incorrectly. } }
\cs_new_eq:NN \regex_nfa_end: \scan_stop:
-\prg_new_protected_conditional:Npnn \regex_check_nfa:N #1 { TF }
+\prg_new_protected_conditional:Npnn \regex_check_nfa:N #1 { T , TF }
{ \exp_after:wN \regex_check_nfa_aux:Nw #1 \q_stop }
\cs_new:Npn \regex_check_nfa_aux:Nw #1 #2 \q_stop
{
@@ -1280,11 +1370,6 @@
\prg_return_false:
\fi:
}
-\msg_new:nnn { regex } { not-nfa }
- {
- I~was~expecting~a~regular~expression~variable.\\
- Instead,~I~got~#1.
- }
\cs_new_protected_nopar:Npn \regex_use:N #1
{ \exp_after:wN \use_none:nn #1 }
\cs_new_protected:Npn \regex_user_aux:n #1
@@ -1296,7 +1381,7 @@
}
\cs_new_protected_nopar:Npn \regex_return_after_group:
{
- \if_bool:N \l_regex_success_bool
+ \if_meaning:w \c_true_bool \l_regex_success_bool
\group_insert_after:N \prg_return_true:
\else:
\group_insert_after:N \prg_return_false:
@@ -1304,7 +1389,7 @@
}
\cs_new_protected_nopar:Npn \regex_extract_after_group:N #1
{
- \if_bool:N \l_regex_success_bool
+ \if_meaning:w \c_true_bool \l_regex_success_bool
\regex_extract:
\group_insert_after:N \seq_set_eq:NN
\group_insert_after:N #1
@@ -1359,7 +1444,7 @@
}
\cs_new_protected:Npn \regex_count:NnN #1#2#3
{
- \regex_check_nfa:NTF #1
+ \regex_check_nfa:NT #1
{
\regex_user_aux:n
{
@@ -1375,9 +1460,8 @@
\regex_count_after_group:N #3
}
}
- { }
}
-\cs_new_protected:Npn \regex_extract:nnN #1#2#3
+\cs_new_protected:Npn \regex_extract_once:nnN #1#2#3
{
\regex_user_aux:n
{
@@ -1386,7 +1470,8 @@
\regex_extract_after_group:N #3
}
}
-\prg_new_protected_conditional:Npnn \regex_extract:nnN #1#2#3 { T , F , TF }
+\prg_new_protected_conditional:Npnn \regex_extract_once:nnN #1#2#3
+ { T , F , TF }
{
\regex_user_aux:n
{
@@ -1396,9 +1481,9 @@
\regex_return_after_group:
}
}
-\cs_new_protected:Npn \regex_extract:NnN #1#2#3
+\cs_new_protected:Npn \regex_extract_once:NnN #1#2#3
{
- \regex_check_nfa:NTF #1
+ \regex_check_nfa:NT #1
{
\regex_user_aux:n
{
@@ -1407,9 +1492,9 @@
\regex_extract_after_group:N #3
}
}
- { }
}
-\prg_new_protected_conditional:Npnn \regex_extract:NnN #1#2#3 { T , F , TF }
+\prg_new_protected_conditional:Npnn \regex_extract_once:NnN #1#2#3
+ { T , F , TF }
{
\regex_check_nfa:NTF #1
{
@@ -1423,6 +1508,48 @@
}
{ \prg_return_false: }
}
+\cs_new_protected:Npn \regex_extract_all:nnN #1#2#3
+ {
+ \regex_user_aux:n
+ {
+ \seq_gclear:N \g_regex_extract_all_seq
+ \tl_set:Nn \l_regex_every_match_tl { \regex_extract_all_aux: }
+ \regex_build:n {#1}
+ \regex_match:n {#2}
+ \regex_extract_all_after_group:N #3
+ }
+ }
+\cs_new_protected:Npn \regex_extract_all:NnN #1#2#3
+ {
+ \regex_check_nfa:NT #1
+ {
+ \regex_user_aux:n
+ {
+ \seq_gclear:N \g_regex_extract_all_seq
+ \tl_set:Nn \l_regex_every_match_tl { \regex_extract_all_aux: }
+ \regex_use:N #1
+ \regex_match:n {#2}
+ \regex_extract_all_after_group:N #3
+ }
+ }
+ }
+\cs_new_protected_nopar:Npn \regex_extract_all_aux:
+ {
+ \regex_extract:
+ \seq_gconcat:NNN \g_regex_extract_all_seq
+ \g_regex_extract_all_seq \g_regex_submatches_seq
+ \regex_match_once:
+ }
+\cs_new_protected_nopar:Npn \regex_extract_all_after_group:N #1
+ {
+ \seq_if_empty:NF \g_regex_extract_all_seq
+ {
+ \regex_extract:
+ \group_insert_after:N \seq_set_eq:NN
+ \group_insert_after:N #1
+ \group_insert_after:N \g_regex_extract_all_seq
+ }
+ }
\cs_new_protected:Npn \regex_split:nnN #1#2#3
{
\regex_user_aux:n
@@ -1436,7 +1563,7 @@
}
\cs_new_protected:Npn \regex_split:NnN #1#2#3
{
- \regex_check_nfa:NTF #1
+ \regex_check_nfa:NT #1
{
\regex_user_aux:n
{
@@ -1447,7 +1574,6 @@
\regex_split_after_group:N #3
}
}
- { }
}
\cs_new_protected_nopar:Npn \regex_split_aux:
{
@@ -1459,9 +1585,8 @@
{
\seq_gput_left:Nx \g_regex_submatches_seq
{
- \str_from_to:Nnn \l_regex_query_str
- { \int_use:N \l_regex_start_step_int }
- { \l_regex_tmpa_tl }
+ \regex_query_substr:NN
+ \l_regex_start_step_int \l_regex_tmpa_tl
}
}
{ \msg_error:nn { regex } { internal } }
@@ -1480,9 +1605,8 @@
{
\seq_gput_right:Nx \g_regex_split_seq
{
- \str_from_to:Nnn \l_regex_query_str
- { \int_use:N \l_regex_start_step_int }
- { \int_use:N \l_regex_current_step_int }
+ \regex_query_substr:NN
+ \l_regex_start_step_int \l_regex_current_step_int
}
}
\group_insert_after:N \seq_set_eq:NN
@@ -1494,40 +1618,57 @@
\str_aux_escape:NNNn
\prg_do_nothing:
\regex_replacement_escaped:N
- \regex_replacement_raw:N
+ \prg_do_nothing:
{#1}
\tl_set_eq:NN \l_regex_replacement_tl \g_str_result_tl
\tl_set:Nx \l_regex_replacement_tl
{ \l_regex_replacement_tl \prg_do_nothing: }
}
-\cs_new_nopar:Npn \regex_replacement_raw:N { \exp_not:N \prg_do_nothing: }
\cs_new_nopar:Npn \regex_replacement_escaped:N #1
{
- \if_num:w 9 < 1 #1 \exp_stop_f:
- \exp_not:N \regex_replacement_escaped_ii:nN {#1}
- \else:
- #1
- \fi:
+ \regex_token_if_other_digit:NTF #1
+ {
+ \exp_not:n
+ { \exp_not:n { \seq_item:Nn \g_regex_submatches_seq } } {#1}
+ }
+ {
+ \token_if_eq_charcode:NNTF g #1
+ { \exp_not:N \regex_replacement_submatch:w }
+ { #1 }
+ }
}
-\cs_new_nopar:Npn \regex_replacement_escaped_ii:nN #1#2
+\cs_new_nopar:Npn \regex_replacement_submatch:w #1
{
- \regex_token_if_other_digit:NTF #2
- { \regex_replacement_escaped_ii:nN {#1#2} }
- { \exp_not:N \seq_item:Nn \exp_not:N \g_regex_submatches_seq {#1} #2 }
+ \exp_after:wN \token_if_eq_meaning:NNTF \c_lbrace_str #1
+ { \regex_replacement_submatch_aux:nN { } }
+ {
+ \regex_token_if_other_digit:NTF #1
+ { \exp_not:n { \seq_item:Nn \g_regex_submatches_seq } }
+ { \msg_expandable_error:n { \g misused~in~replacement~text. } }
+ #1
+ }
}
-\prg_new_conditional:Npnn \regex_token_if_other_digit:N #1 { TF }
+\cs_new_nopar:Npn \regex_replacement_submatch_aux:nN #1 #2
{
- \if_num:w 9 < 1 \exp_not:N #1 \exp_stop_f:
- \prg_return_true:
- \else:
- \prg_return_false:
- \fi:
+ \regex_token_if_other_digit:NTF #2
+ { \regex_replacement_submatch_aux:nN {#1#2} }
+ {
+ \exp_not:n { \seq_item:Nn \g_regex_submatches_seq } {#1}
+ \exp_after:wN \token_if_eq_meaning:NNF \c_rbrace_str #2
+ {
+ \msg_expandable_error:n { \g misused~in~replacement~text. }
+ #2
+ }
+ }
}
\cs_new_protected_nopar:Npn \regex_replace_after_group:N #1
{
- \group_insert_after:N \tl_set_eq:NN
+ \group_insert_after:N \tl_set:Nx
\group_insert_after:N #1
- \group_insert_after:N \g_regex_replaced_str
+ \group_insert_after:N {
+ \group_insert_after:N \tl_to_str:N
+ \group_insert_after:N \g_regex_replaced_str
+ \group_insert_after:N }
}
\cs_new_protected:Npn \regex_replace_once_aux:Nn #1#2
{
@@ -1539,15 +1680,16 @@
\regex_extract:
\regex_extract_aux:nTF {0}
{
+ \cs_set_nopar:Npn \regex_tmp:w
+ { \str_skip_do:nn { \l_regex_tmpb_tl } { } }
\tl_gset:Nx \g_regex_replaced_str
{
- \str_from_to:Nnn \l_regex_query_str {0} { \l_regex_tmpa_tl }
+ \regex_query_substr:NN \c_zero \l_regex_tmpa_tl
\l_regex_replacement_tl
- \str_from_to:Nnn \l_regex_query_str
- { \l_regex_tmpb_tl } { \c_max_int }
+ \exp_after:wN \regex_tmp:w \l_regex_query_other_str
}
}
- { \tl_gset_eq:NN \g_regex_replaced_str \l_regex_query_str }
+ { \tl_gset_eq:NN \g_regex_replaced_str \l_regex_query_other_str }
\group_end:
}
\cs_new_protected:Npn \regex_replace_once:nnN #1#2#3
@@ -1592,12 +1734,10 @@
\tl_gclear:N \g_regex_replaced_str
#2
\exp_args:No \regex_match:n {#1}
+ \cs_set_nopar:Npn \regex_tmp:w
+ { \str_skip_do:nn { \l_regex_start_step_int } { } }
\tl_gput_right:Nx \g_regex_replaced_str
- {
- \str_from_to:Nnn \l_regex_query_str
- { \int_use:N \l_regex_start_step_int }
- { \c_max_int }
- }
+ { \exp_after:wN \regex_tmp:w \l_regex_query_other_str }
\group_end:
}
\cs_new_protected_nopar:Npn \regex_replace_all_aux:
@@ -1607,9 +1747,8 @@
{
\tl_gput_right:Nx \g_regex_replaced_str
{
- \str_from_to:Nnn \l_regex_query_str
- { \int_use:N \l_regex_start_step_int }
- { \l_regex_tmpa_tl }
+ \regex_query_substr:NN
+ \l_regex_start_step_int \l_regex_tmpa_tl
\l_regex_replacement_tl
}
}
@@ -1632,6 +1771,26 @@
\regex_replacement:n {#2}
}
}
+\msg_new:nnn { regex } { -998 } { Unsupported~construct }
+\msg_new:nnn { regex } { -997 }
+ { The~regular~expression~is~too~large~(32768~states). }
+\msg_new:nnn { regex } { 1 } { \iow_char:N\\~at~end~of~pattern }
+\msg_new:nnn { regex } { 4 }
+ { Numbers~out~of~order~in~\iow_char:N\{\iow_char\}~quantifier. }
+\msg_new:nnn { regex } { 6 }
+ { Missing~terminating~\iow_char:N\]~for~character~class }
+\msg_new:nnn { regex } { 7 }
+ { Invalid~escape~sequence~in~character~class }
+\msg_new:nnn { regex } { 8 }
+ { Range~out~of~order~in~character~class }
+\msg_new:nnn { regex } { 22 } { Mismatched~parentheses }
+\msg_new:nnn { regex } { 34 }
+ { Character~value~in~\iow_char:N\\x{...}~sequence~is~too~large }
+\msg_new:nnn { regex } { not-nfa }
+ {
+ LaTeX~was~expecting~a~regular~expression~variable.\\
+ Instead,~LaTeX~found~'#1'.
+ }
%%
%%
%% End of file `l3regex.sty'.
diff --git a/Master/texmf-dist/tex/latex/l3experimental/l3str/l3str.sty b/Master/texmf-dist/tex/latex/l3experimental/l3str/l3str.sty
index 9a69d0da0a6..c705f6366b3 100644
--- a/Master/texmf-dist/tex/latex/l3experimental/l3str/l3str.sty
+++ b/Master/texmf-dist/tex/latex/l3experimental/l3str/l3str.sty
@@ -46,30 +46,27 @@
%%
%% -----------------------------------------------------------------------
\RequirePackage{expl3}
-\GetIdInfo$Id: l3str.dtx 2895 2011-10-09 15:58:19Z joseph $
+\GetIdInfo$Id: l3str.dtx 2921 2011-10-17 13:23:36Z bruno $
{L3 Experimental Strings}
\ProvidesExplPackage
{\ExplFileName}{\ExplFileDate}{\ExplFileVersion}{\ExplFileDescription}
-\cs_if_exist:NF \cs_if_exist_use:cF
- {
- \cs_new:Npn \cs_if_exist_use:cF #1
- { \cs_if_exist:cTF {#1} { \use:c {#1} } }
- }
\cs_if_exist:NF \use_i:nnnnnnnn
{ \cs_new:Npn \use_i:nnnnnnnn #1#2#3#4#5#6#7#8 {#1} }
-\cs_set:Npn \str_tmp:w #1
- {
- \cs_new_protected:cpx { str_#1:Nn } ##1##2
- { \exp_not:c { tl_#1:Nx } ##1 { \exp_not:N \tl_to_str:n {##2} } }
- \exp_args:Nc \cs_generate_variant:Nn { str_#1:Nn } { Nx , cn , cx }
- }
-\str_tmp:w {set}
-\str_tmp:w {gset}
-\str_tmp:w {put_left}
-\str_tmp:w {gput_left}
-\str_tmp:w {put_right}
-\str_tmp:w {gput_right}
-\cs_set_protected_nopar:Npn \str_tmp:w { }
+\group_begin:
+ \cs_set_protected_nopar:Npn \str_tmp:w #1
+ {
+ \cs_new_protected:cpx { str_ #1 :Nn } ##1##2
+ { \exp_not:c { tl_ #1 :Nx } ##1 { \exp_not:N \tl_to_str:n {##2} } }
+ \exp_args:Nc \cs_generate_variant:Nn { str_ #1 :Nn } { Nx , cn , cx }
+ }
+ \str_tmp:w { set }
+ \str_tmp:w { gset }
+ \str_tmp:w { put_left }
+ \str_tmp:w { gput_left }
+ \str_tmp:w { put_right }
+ \str_tmp:w { gput_right }
+\group_end:
+\cs_new_protected_nopar:Npn \str_tmp:w { }
\tl_new:N \g_str_tmpa_tl
\tl_new:N \g_str_result_tl
\int_new:N \l_str_char_int
@@ -80,34 +77,31 @@
\tl_const:Nx \c_hash_str { \cs_to_str:N \# }
\tl_const:Nx \c_percent_str { \cs_to_str:N \% }
\group_begin:
-\char_set_lccode:nn {`\*}{`\ }
-\char_set_lccode:nn {`\A}{`\A}
-\tl_to_lowercase:n {
- \group_end:
- \cs_new:Npn \tl_to_other_str:n #1
- {
- \exp_after:wN \tl_to_other_str_loop:w \tl_to_str:n {#1} ~ %
- A ~ A ~ A ~ A ~ A ~ A ~ A ~ A ~ \q_mark \q_stop
- }
- \cs_new_nopar:Npn \tl_to_other_str_loop:w
+\char_set_lccode:nn { `\* } { `\ }
+\char_set_lccode:nn { `\A } { `\A }
+\tl_to_lowercase:n
+ {
+ \group_end:
+ \cs_new:Npn \tl_to_other_str:n #1
+ {
+ \exp_after:wN \tl_to_other_str_loop:w \tl_to_str:n {#1} ~ %
+ A ~ A ~ A ~ A ~ A ~ A ~ A ~ A ~ \q_mark \q_stop
+ }
+ \cs_new_nopar:Npn \tl_to_other_str_loop:w
#1 ~ #2 ~ #3 ~ #4 ~ #5 ~ #6 ~ #7 ~ #8 ~ #9 \q_stop
- {
- \if_meaning:w A #8
- \tl_to_other_str_end:w
- \fi:
- \tl_to_other_str_loop:w
- #9 #1 * #2 * #3 * #4 * #5 * #6 * #7 * #8 * \q_stop
- }
- \cs_new_nopar:Npn \tl_to_other_str_end:w \fi: #1 \q_mark #2 * A #3 \q_stop
- { \fi: #2 }
-}
-\cs_new_nopar:Npn \tl_to_other_str:N
- { \exp_args:No \tl_to_other_str:n }
-\cs_new:Npn \str_sanitize_args:Nn #1 #2
- {
- \exp_args:Nf #1
- { \tl_to_other_str:n {#2} }
+ {
+ \if_meaning:w A #8
+ \tl_to_other_str_end:w
+ \fi:
+ \tl_to_other_str_loop:w
+ #9 #1 * #2 * #3 * #4 * #5 * #6 * #7 * #8 * \q_stop
+ }
+ \cs_new_nopar:Npn \tl_to_other_str_end:w \fi: #1 \q_mark #2 * A #3 \q_stop
+ { \fi: #2 }
}
+\cs_new_nopar:Npn \tl_to_other_str:N { \exp_args:No \tl_to_other_str:n }
+\cs_new:Npn \str_sanitize_args:Nn #1#2
+ { \exp_args:Nf #1 { \tl_to_other_str:n {#2} } }
\cs_new:Npn \str_sanitize_args:Nnn #1#2#3
{
\exp_args:Nff #1
@@ -141,15 +135,15 @@
\fi:
\c_nine + \str_length_loop:NNNNNNNNN
}
-\cs_set_nopar:Npn \str_head:N { \exp_args:No \str_head:n }
+\cs_new_nopar:Npn \str_head:N { \exp_args:No \str_head:n }
\cs_set:Npn \str_head:n #1
{
\exp_after:wN \str_head_aux:w
\tl_to_str:n {#1}
{ { } } ~ \q_stop
}
-\cs_set_nopar:Npx \str_head_aux:w #1 ~ %
- { \exp_not:N \use_i_delimit_by_q_stop:nw #1 { ~ } }
+\cs_set_nopar:Npn \str_head_aux:w #1 ~ %
+ { \use_i_delimit_by_q_stop:nw #1 { ~ } }
\cs_new:Npn \str_head_ignore_spaces:n #1
{ \exp_after:wN \use_i_delimit_by_q_stop:nw \tl_to_str:n {#1} { } \q_stop }
\cs_new_nopar:Npn \str_head_unsafe:n #1
@@ -169,15 +163,17 @@
}
\cs_new_nopar:Npn \str_tail_unsafe:n #1
{ \str_tail_aux_ii:w #1 X { } X \q_stop }
-\cs_set_nopar:Npn \str_tail_aux_ii:w #1 #2 X #3 \q_stop { #2 }
+\cs_new_nopar:Npn \str_tail_aux_ii:w #1 #2 X #3 \q_stop { #2 }
\cs_new:Npn \str_skip_do:nn #1
{
- \int_compare:nNnTF {#1} > \c_seven
- { \str_skip_aux:nnnnnnnnn }
- { \str_skip_end:n }
+ \if_num:w \int_eval:w #1 > \c_seven
+ \exp_after:wN \str_skip_aux:nnnnnnnnn
+ \else:
+ \exp_after:wN \str_skip_end:n
+ \fi:
{#1}
}
-\cs_new:Npn \str_skip_aux:nnnnnnnnn #1#2 #3#4#5#6#7#8#9
+\cs_new:Npn \str_skip_aux:nnnnnnnnn #1#2#3#4#5#6#7#8#9
{ \exp_args:Nf \str_skip_do:nn { \int_eval:n { #1 - \c_seven } } {#2} }
\cs_new:Npn \str_skip_end:n #1
{
@@ -193,7 +189,7 @@
\else: \str_skip_end_ii:nwn { XXXXXXX }
\fi:
}
-\cs_new:Npn \str_skip_end_ii:nwn #1 #2 \fi: #3
+\cs_new:Npn \str_skip_end_ii:nwn #1#2 \fi: #3
{ \fi: \use_i:nnnnnnnn {#3} #1 }
\cs_new:Npn \str_collect_do:nn #1#2
{ \str_collect_aux:n {#1} { \str_collect_end_iii:nwNNNNNNN {#2} } }
@@ -213,18 +209,18 @@
\cs_new:Npn \str_collect_end:n #1
{
\if_case:w \int_eval:w #1 \int_eval_end:
- \str_collect_end_ii:nwn { {}{}{}{}{}{}{} }
- \or: \str_collect_end_ii:nwn { {}{}{}{}{}{} }
- \or: \str_collect_end_ii:nwn { {}{}{}{}{} }
- \or: \str_collect_end_ii:nwn { {}{}{}{} }
- \or: \str_collect_end_ii:nwn { {}{}{} }
- \or: \str_collect_end_ii:nwn { {}{} }
- \or: \str_collect_end_ii:nwn { {} }
+ \str_collect_end_ii:nwn { { } { } { } { } { } { } { } }
+ \or: \str_collect_end_ii:nwn { { } { } { } { } { } { } }
+ \or: \str_collect_end_ii:nwn { { } { } { } { } { } }
+ \or: \str_collect_end_ii:nwn { { } { } { } { } }
+ \or: \str_collect_end_ii:nwn { { } { } { } }
+ \or: \str_collect_end_ii:nwn { { } { } }
+ \or: \str_collect_end_ii:nwn { { } }
\or: \str_collect_end_ii:nwn { }
- \else: \str_collect_end_ii:nwn { {}{}{}{}{}{}{} }
+ \else: \str_collect_end_ii:nwn { { } { } { } { } { } { } { } }
\fi:
}
-\cs_new:Npn \str_collect_end_ii:nwn #1 #2 \fi: #3
+\cs_new:Npn \str_collect_end_ii:nwn #1#2 \fi: #3
{ \fi: #3 \q_stop #1 }
\cs_new:Npn \str_collect_end_iii:nwNNNNNNN #1 #2 \q_stop #3#4#5#6#7#8#9
{ #1 {#2#3#4#5#6#7#8#9} }
@@ -264,30 +260,30 @@
{ \use_none_delimit_by_q_stop:w }
}
}
-\cs_new_nopar:Npn \str_from_to:Nnn { \exp_args:No \str_from_to:nnn }
-\cs_new:Npn \str_from_to:nnn #1#2#3
+\cs_new_nopar:Npn \str_substr:Nnn { \exp_args:No \str_substr:nnn }
+\cs_new:Npn \str_substr:nnn #1#2#3
{
\exp_args:Nf \tl_to_str:n
- { \str_sanitize_args:Nn \str_from_to_unsafe:nnn {#1}{#2}{#3} }
+ { \str_sanitize_args:Nn \str_substr_unsafe:nnn {#1} {#2} {#3} }
}
-\cs_new:Npn \str_from_to_ignore_spaces:nnn #1
- { \exp_args:No \str_from_to_unsafe:nnn { \tl_to_str:n {#1} } }
-\cs_new:Npn \str_from_to_unsafe:nnn #1#2#3 % <string> <from> <to>
+\cs_new:Npn \str_substr_ignore_spaces:nnn #1
+ { \exp_args:No \str_substr_unsafe:nnn { \tl_to_str:n {#1} } }
+\cs_new:Npn \str_substr_unsafe:nnn #1#2#3
{
- \str_aux_eval_args:Nnnn \str_from_to_aux:nnnw
+ \str_aux_eval_args:Nnnn \str_substr_aux:nnnw
{ \str_length_unsafe:n {#1} }
{#2}
{#3}
#1
\q_stop
}
-\cs_new:Npn \str_from_to_aux:nnnw #1#2#3 % <len> <from> <to>
+\cs_new:Npn \str_substr_aux:nnnw #1#2#3
{
- \exp_args:Nf \str_from_to_aux_ii:nnw
+ \exp_args:Nf \str_substr_aux_ii:nnw
{ \str_aux_normalize_range:nn {#2} {#1} }
{ \str_aux_normalize_range:nn {#3} {#1} }
}
-\cs_new:Npn \str_from_to_aux_ii:nnw #1#2
+\cs_new:Npn \str_substr_aux_ii:nnw #1#2
{
\str_skip_do:nn {#1}
{
@@ -376,7 +372,7 @@
}
\prg_new_protected_conditional:Npnn \str_aux_hexadecimal_test:N #1 { TF }
{
- \tl_if_in:onTF { \tl_to_str:n {abcdef} } {#1}
+ \tl_if_in:onTF { \tl_to_str:n { abcdef } } {#1}
{
\int_set:Nn \l_str_char_int
{ \c_sixteen * \l_str_char_int + `#1 - 87 }
@@ -423,7 +419,7 @@
\cs_set_nopar:Npn \str_aux_escape_unescaped:N { #1 }
\cs_set_nopar:Npn \str_aux_escape_escaped:N { #2 }
\cs_set_nopar:Npn \str_aux_escape_raw:N { #3 }
- \int_set:Nn \tex_escapechar:D {92}
+ \int_set:Nn \tex_escapechar:D { 92 }
\tl_gset:Nx \g_str_result_tl { \tl_to_other_str:n {#4} }
\tl_gset:Nx \g_str_result_tl
{
@@ -531,28 +527,22 @@
}
}
\group_end:
-\msg_new:nnn { str } { x-missing-brace }
- {
- You~wrote~something~like~
- `\iow_char:N\\x\{ \int_to_hexadecimal:n { \l_str_char_int }'.~
- The~closing~brace~is~missing.
- }
\group_begin:
- \char_set_catcode_other:n {`\^^@}
+ \char_set_catcode_other:n { `\^^@ }
\cs_new_protected_nopar:Npn \str_aux_convert_store:
{
- \char_set_lccode:nn {\c_zero} {\l_str_char_int}
+ \char_set_lccode:nn { \c_zero } { \l_str_char_int }
\tl_to_lowercase:n { \tl_gput_right:Nx \g_str_result_tl {^^@} }
}
\cs_new_protected_nopar:Npn \str_aux_convert_store:NNn #1#2#3
{
- \char_set_lccode:nn {\c_zero} {#3}
+ \char_set_lccode:nn { \c_zero } {#3}
\tl_to_lowercase:n { #1 #2 {^^@} }
}
\group_end:
\cs_new_nopar:Npn \str_aux_byte_to_hexadecimal:N #1
{
- \int_compare:nNnTF {`#1} < {256}
+ \int_compare:nNnTF {`#1} < { 256 }
{
\int_to_letter:n { \int_div_truncate:nn {`#1} \c_sixteen }
\int_to_letter:n { \int_mod:nn {`#1} \c_sixteen }
@@ -561,14 +551,14 @@
}
\cs_new_nopar:Npn \str_aux_byte_to_octal:N #1
{
- \int_compare:nNnTF {`#1} < {64}
+ \int_compare:nNnTF {`#1} < { 64 }
{
0
\int_to_letter:n { \int_div_truncate:nn {`#1} \c_eight }
\int_to_letter:n { \int_mod:nn {`#1} \c_eight }
}
{
- \int_compare:nNnTF {`#1} < {256}
+ \int_compare:nNnTF {`#1} < { 256 }
{ \int_to_octal:n {`#1} }
{ \msg_expandable_error:n { Invalid~byte~`#1'. } }
}
@@ -579,7 +569,7 @@
{ \str_map_tokens:Nn #2 \str_aux_byte_to_hexadecimal:N }
}
\tl_const:Nx \c_str_bytes_escape_name_str
- { \c_hash_str \c_percent_str \c_lbrace_str \c_rbrace_str () /<>[] }
+ { \c_hash_str \c_percent_str \c_lbrace_str \c_rbrace_str ()/<>[] }
\cs_new_protected_nopar:Npn \str_bytes_escape_name:NN #1#2
{
\str_set:Nx #1
@@ -587,10 +577,10 @@
}
\cs_new_nopar:Npn \str_bytes_escape_name_aux:N #1
{
- \int_compare:nNnTF {`#1} < {"21}
+ \int_compare:nNnTF {`#1} < { "21 }
{ \c_hash_str \str_aux_byte_to_hexadecimal:N #1 }
{
- \int_compare:nNnTF {`#1} > {"7E}
+ \int_compare:nNnTF {`#1} > { "7E }
{ \c_hash_str \str_aux_byte_to_hexadecimal:N #1 }
{
\str_if_contains_char:NNTF \c_str_bytes_escape_name_str #1
@@ -607,10 +597,10 @@
}
\cs_new_nopar:Npn \str_bytes_escape_string_aux:N #1
{
- \int_compare:nNnTF {`#1} < {"21}
+ \int_compare:nNnTF {`#1} < { "21 }
{ \c_backslash_str \str_aux_byte_to_octal:N #1 }
{
- \int_compare:nNnTF {`#1} > {"7E}
+ \int_compare:nNnTF {`#1} > { "7E }
{ \c_backslash_str \str_aux_byte_to_octal:N #1 }
{
\str_if_contains_char:NNT \c_str_bytes_escape_string_str #1
@@ -719,16 +709,16 @@
{
\prg_case_str:xxn {#2}
{
- {n} {10}
- {r} {13}
- {t} {9}
- {b} {8}
- {f} {12}
- {(} {40}
- {)} {41}
- {\c_backslash_str} {92}
- {^^J} {-1}
- {^^M} {-1}
+ { n } { 10 }
+ { r } { 13 }
+ { t } { 9 }
+ { b } { 8 }
+ { f } { 12 }
+ { ( } { 40 }
+ { ) } { 41 }
+ { \c_backslash_str } { 92 }
+ { ^^J } { -1 }
+ { ^^M } { -1 }
}
{`#2}
}
@@ -768,14 +758,14 @@
}
\cs_new_nopar:Npn \str_bytes_percent_encode_aux:N #1
{
- \int_compare:nNnTF {`#1} < {"41}
+ \int_compare:nNnTF {`#1} < { "41 }
{
\str_if_contains_char:NNTF \c_str_bytes_percent_encode_not_str #1
{ #1 }
{ \c_percent_str \str_aux_byte_to_hexadecimal:N #1 }
}
{
- \int_compare:nNnTF {`#1} > {"7E}
+ \int_compare:nNnTF {`#1} > { "7E }
{ \c_percent_str \str_aux_byte_to_hexadecimal:N #1 }
{
\str_if_contains_char:NNTF \c_str_bytes_percent_encode_str #1
@@ -837,19 +827,18 @@
\cs_new_protected_nopar:Npn \str_native_from_UTF_viii_aux_i:N #1
{
\quark_if_recursion_tail_stop:N #1
- \int_set:Nn \l_str_char_int { `#1 }
- \str_native_from_UTF_viii_aux_ii:nN {128} \c_one
- \str_native_from_UTF_viii_aux_ii:nN {64} \c_zero
- \str_native_from_UTF_viii_aux_ii:nN {32} \c_two
- \str_native_from_UTF_viii_aux_ii:nN {16} \c_three
- \str_native_from_UTF_viii_aux_ii:nN {8} \c_four
+ \int_set:Nn \l_str_char_int {`#1}
+ \str_native_from_UTF_viii_aux_ii:nN { 128 } \c_one
+ \str_native_from_UTF_viii_aux_ii:nN { 64 } \c_zero
+ \str_native_from_UTF_viii_aux_ii:nN { 32 } \c_two
+ \str_native_from_UTF_viii_aux_ii:nN { 16 } \c_three
+ \str_native_from_UTF_viii_aux_ii:nN { 8 } \c_four
\msg_error:nnx { str } { utf8-invalid-byte } {#1}
\use_i:nnn \str_native_from_UTF_viii_aux_i:N
\q_stop
\str_native_from_UTF_viii_aux_iii:N
}
-\cs_new_protected_nopar:Npn
- \str_native_from_UTF_viii_aux_ii:nN #1#2
+\cs_new_protected_nopar:Npn \str_native_from_UTF_viii_aux_ii:nN #1#2
{
\int_compare:nNnTF \l_str_char_int < {#1}
{
@@ -858,8 +847,7 @@
}
{ \int_sub:Nn \l_str_char_int {#1} }
}
-\cs_new_protected_nopar:Npn
- \str_native_from_UTF_viii_aux_iii:N #1
+\cs_new_protected_nopar:Npn \str_native_from_UTF_viii_aux_iii:N #1
{
\int_compare:nNnTF \l_str_bytes_int < \c_two
{ \str_native_from_UTF_viii_aux_iv: #1 }
@@ -869,11 +857,11 @@
\exp_after:wN \use_none_delimit_by_q_recursion_stop:w
\fi:
\quark_if_recursion_tail_stop:N #1
- \tex_multiply:D \l_str_char_int by 64 \scan_stop: % no interface??
+ \tex_multiply:D \l_str_char_int by 64 \scan_stop:
\int_decr:N \l_str_bytes_int
- \int_compare:nNnTF {`#1} < {128}
+ \int_compare:nNnTF {`#1} < { 128 }
{ \use_ii:nn }
- { \int_compare:nNnTF {`#1} < {192} }
+ { \int_compare:nNnTF {`#1} < { 192 } }
{
\int_add:Nn \l_str_char_int { `#1 - 128 }
\str_native_from_UTF_viii_aux_iii:N
@@ -884,47 +872,32 @@
}
}
}
-\cs_new_protected_nopar:Npn
- \str_native_from_UTF_viii_aux_iv:
+\cs_new_protected_nopar:Npn \str_native_from_UTF_viii_aux_iv:
{
\int_compare:nNnTF \l_str_bytes_int = \c_zero
{
\msg_error:nnx { str } { utf8-extra-byte }
{ \int_eval:n { \l_str_char_int + 128 } }
}
+ { \str_native_from_UTF_viii_aux_v: }
+ \str_native_from_UTF_viii_aux_i:N
+ }
+\pdftex_if_engine:TF
+ {
+ \cs_new_protected_nopar:Npn \str_native_from_UTF_viii_aux_v:
{
- \pdftex_if_engine:TF
+ \int_compare:nNnTF { \l_str_char_int } < { 256 }
+ { \str_aux_convert_store: }
{
- \int_compare:nNnTF { \l_str_char_int } < { 256 }
- { \str_aux_convert_store: }
- {
- \msg_error:nnx { str } { utf8-pdftex-overflow }
- { \int_use:N \l_str_char_int }
- }
+ \msg_error:nnx { str } { utf8-pdftex-overflow }
+ { \int_use:N \l_str_char_int }
}
- { \str_aux_convert_store: }
}
- \str_native_from_UTF_viii_aux_i:N
}
-\msg_new:nnn { str } { utf8-invalid-byte }
{
- \int_compare:nNnTF {`#1} < {256}
- { Byte~number~\int_eval:n {`#1}~invalid~in~utf-8~encoding. }
- { The~character~number~\int_eval:n {`#1}~is~not~a~byte. }
+ \cs_new_protected_nopar:Npn \str_native_from_UTF_viii_aux_v:
+ { \str_aux_convert_store: }
}
-\msg_new:nnn { str } { utf8-missing-byte }
- { The~byte~number~\int_eval:n {`#1}~is~not~a~valid~continuation~byte. }
-\msg_new:nnn { str } { utf8-extra-byte }
- { The~byte~number~\int_eval:n {`#1}~is~only~valid~as~a~continuation~byte. }
-\msg_new:nnnn { str } { utf8-premature-end }
- { Incomplete~last~utf8~character. }
- {
- The~sequence~of~byte~that~I~need~to~convert~to~utf8 \
- ended~before~the~last~character~was~complete.~Perhaps \
- it~was~mistakenly~truncated?
- }
-\msg_new:nnn { str } { utf8-pdftex-overflow }
- { The~character~number~#1~is~too~big~for~pdfTeX. }
\cs_new_protected_nopar:Npn \str_UTF_viii_from_native:NN #1#2
{
\group_begin:
@@ -936,14 +909,14 @@
\cs_new_protected_nopar:Npn \str_UTF_viii_from_native_aux_i:N #1
{
\int_set:Nn \l_str_char_int {`#1}
- \int_compare:nNnTF \l_str_char_int < {128}
+ \int_compare:nNnTF \l_str_char_int < { 128 }
{ \tl_gput_right:Nx \g_str_result_tl {#1} }
{
\tl_gclear:N \g_str_tmpa_tl
\int_set:Nn \l_str_bytes_int { 64 }
- \str_UTF_viii_from_native_aux_ii:n {32}
- \str_UTF_viii_from_native_aux_ii:n {16}
- \str_UTF_viii_from_native_aux_ii:n {8}
+ \str_UTF_viii_from_native_aux_ii:n { 32 }
+ \str_UTF_viii_from_native_aux_ii:n { 16 }
+ \str_UTF_viii_from_native_aux_ii:n { 8 }
\ERROR % somehow the unicode char was > "1FFFFF > "10FFFF
\tl_gclear:N \g_str_tmpa_tl
\use_none:n \q_stop
@@ -956,15 +929,41 @@
{
\str_aux_convert_store:NNn
\tl_gput_left:Nx \g_str_tmpa_tl
- { 128 + \int_mod:nn { \l_str_char_int } {64} }
- \tex_divide:D \l_str_char_int by 64 \scan_stop: % no interface??
+ { 128 + \int_mod:nn { \l_str_char_int } { 64 } }
+ \tex_divide:D \l_str_char_int by 64 \scan_stop:
\int_add:Nn \l_str_bytes_int {#1}
\int_compare:nNnT \l_str_char_int < {#1}
{ \use_none_delimit_by_q_stop:w }
}
-\cs_gset:Npn \str_length_skip_spaces:N
+\msg_new:nnnn { str } { x-missing-brace }
+ { Missing~closing~brace~in~ \token_to_str:N \x ~byte~sequence. }
+ {
+ You~wrote~something~like~
+ `\iow_char:N\\x\{ \int_to_hexadecimal:n { \l_str_char_int }'.~
+ The~closing~brace~is~missing.
+ }
+\msg_new:nnn { str } { utf8-invalid-byte }
+ {
+ \int_compare:nNnTF {`#1} < { 256 }
+ { Byte~number~ \int_eval:n {`#1} ~invalid~in~utf-8~encoding. }
+ { The~character~number~ \int_eval:n {`#1} ~is~not~a~byte. }
+ }
+\msg_new:nnn { str } { utf8-missing-byte }
+ { The~byte~number~ \int_eval:n {`#1} ~is~not~a~valid~continuation~byte. }
+\msg_new:nnn { str } { utf8-extra-byte }
+ { The~byte~number~ \int_eval:n {`#1} ~is~only~valid~as~a~continuation~byte. }
+\msg_new:nnnn { str } { utf8-premature-end }
+ { Incomplete~last~UTF8~character. }
+ {
+ The~sequence~of~byte~that~to~be~converted~to~UTF8~
+ ended~before~the~last~character~was~complete.~Perhaps~
+ it~was~mistakenly~truncated?
+ }
+\msg_new:nnn { str } { utf8-pdftex-overflow }
+ { The~character~number~#1~is~too~big~for~pdfTeX. }
+\cs_set:Npn \str_length_skip_spaces:N
{ \exp_args:No \str_length_skip_spaces:n }
-\cs_gset_eq:NN \str_length_skip_spaces:n \str_length_ignore_spaces:n
+\cs_set_eq:NN \str_length_skip_spaces:n \str_length_ignore_spaces:n
%%
%%
%% End of file `l3str.sty'.
diff --git a/Master/texmf-dist/tex/latex/l3experimental/xcoffins/xcoffins.sty b/Master/texmf-dist/tex/latex/l3experimental/xcoffins/xcoffins.sty
index 79490432742..9d4a42407e3 100644
--- a/Master/texmf-dist/tex/latex/l3experimental/xcoffins/xcoffins.sty
+++ b/Master/texmf-dist/tex/latex/l3experimental/xcoffins/xcoffins.sty
@@ -47,7 +47,7 @@
%% -----------------------------------------------------------------------
%%
\RequirePackage{xparse}
-\GetIdInfo$Id: xcoffins.dtx 2895 2011-10-09 15:58:19Z joseph $
+\GetIdInfo$Id: xcoffins.dtx 2963 2011-11-15 22:06:41Z joseph $
{L3 Experimental design-level coffins}
\ProvidesExplPackage
{\ExplFileName}{\ExplFileDate}{\ExplFileVersion}{\ExplFileDescription}
@@ -146,6 +146,14 @@
{ \coffin_resize:Nnn #1 {#2} {#3} }
\NewDocumentCommand \ScaleCoffin { m m m }
{ \coffin_scale:Nnn #1 {#2} {#3} }
+\NewDocumentCommand \CoffinDepth { m }
+ { \coffin_dp:N #1 }
+\NewDocumentCommand \CoffinHeight { m }
+ { \coffin_ht:N #1 }
+\NewDocumentCommand \CoffinTotalHeight { m }
+ { \dim_eval:w \coffin_ht:N #1 + \coffin_dp:N #1 \dim_eval_end: }
+\NewDocumentCommand \CoffinWidth { m }
+ { \coffin_wd:N #1 }
\NewDocumentCommand \DisplayCoffinHandles { m m }
{
\cs_if_exist:cTF { l_coffin_poles_ \int_value:w #1 _prop }
diff --git a/Master/texmf-dist/tex/latex/l3experimental/xgalley/l3galley.sty b/Master/texmf-dist/tex/latex/l3experimental/xgalley/l3galley.sty
index b626f072d30..e8a3345204f 100644
--- a/Master/texmf-dist/tex/latex/l3experimental/xgalley/l3galley.sty
+++ b/Master/texmf-dist/tex/latex/l3experimental/xgalley/l3galley.sty
@@ -48,11 +48,14 @@
%% -----------------------------------------------------------------------
%%
\RequirePackage{l3names}
-\GetIdInfo$Id: l3galley.dtx 2899 2011-10-09 21:22:06Z joseph $
+\GetIdInfo$Id: l3galley.dtx 2938 2011-10-25 18:41:20Z joseph $
{L3 Experimental galley code}
\ProvidesExplPackage
{\ExplFileName}{\ExplFileDate}{\ExplFileVersion}{\ExplFileDescription}
\package_check_loaded_expl:
+\cs_new_protected:Npn \scan_marker_new:N #1
+ { \cs_new_eq:NN #1 \scan_stop: }
+\cs_generate_variant:Nn \scan_marker_new:N { c }
\cs_new_protected_nopar:Npn \galley_leave_vmode:
{ \tex_unhbox:D \c_empty_box }
\clist_new:N \l_galley_parshape_left_indent_clist
@@ -69,7 +72,6 @@
\cs_new_eq:NN \l_galley_width_dim \tex_hsize:D
\bool_new:N \g_galley_begin_level_bool
\bool_new:N \l_galley_begin_level_bool
-\bool_gset_true:N \g_galley_begin_level_bool
\bool_new:N \g_galley_omit_next_indent_bool
\bool_new:N \l_galley_omit_next_indent_bool
\bool_new:N \g_galley_parshape_set_bool
@@ -107,9 +109,10 @@
\bool_gset_false:N \g_galley_parshape_set_bool
\int_gzero:N \g_galley_previous_par_lines_int
\tl_gclear:N \g_galley_restore_running_tl
- \tl_gclear:N \g_galley_whatsits_previous_tl
- \tl_gclear:N \g_galley_whatsits_next_tl
+ \tl_gclear:N \g_galley_whatsit_previous_tl
+ \tl_gclear:N \g_galley_whatsit_next_tl
}
+\galley_initialise_variables:
\cs_new_protected_nopar:Npn \galley_initialise_settings:
{
\dim_set_eq:NN \l_galley_text_width_dim \l_galley_width_dim
@@ -142,10 +145,10 @@
\g_galley_previous_par_lines_int
\tl_set_eq:NN \l_galley_restore_running_tl
\g_galley_restore_running_tl
- \tl_set_eq:NN \l_galley_whatsits_previous_tl
- \g_galley_whatsits_previous_tl
- \tl_set_eq:NN \l_galley_whatsits_next_tl
- \g_galley_whatsits_next_tl
+ \tl_set_eq:NN \l_galley_whatsit_previous_tl
+ \g_galley_whatsit_previous_tl
+ \tl_set_eq:NN \l_galley_whatsit_next_tl
+ \g_galley_whatsit_next_tl
}
\cs_new_protected_nopar:Npn \galley_restore_parameters:
{
@@ -171,10 +174,10 @@
\l_galley_previous_par_lines_int
\tl_gset_eq:NN \g_galley_restore_running_tl
\l_galley_restore_running_tl
- \tl_gset_eq:NN \g_galley_whatsits_previous_tl
- \l_galley_whatsits_previous_tl
- \tl_gset_eq:NN \g_galley_whatsits_next_tl
- \l_galley_whatsits_next_tl
+ \tl_gset_eq:NN \g_galley_whatsit_previous_tl
+ \l_galley_whatsit_previous_tl
+ \tl_gset_eq:NN \g_galley_whatsit_next_tl
+ \l_galley_whatsit_next_tl
}
\cs_new_protected_nopar:Npn \galley_level:
{
@@ -190,8 +193,28 @@
\galley_restore_parameters:
\group_end:
}
+\scan_marker_new:N \s_par_omit
\cs_new_protected_nopar:Npn \galley_std_par:
{
+ \s_par_omit
+ \exp_after:wN \galley_std_par_aux_i: \tex_romannumeral:D - `0
+ }
+\cs_new_protected:Npn \galley_std_par_aux_i:
+ {
+ \peek_meaning:NTF \s_par_omit
+ { \galley_std_par_aux:N }
+ { \galley_std_par_aux_ii: }
+ }
+\cs_new_protected:Npn \galley_std_par_aux:N #1
+ {
+ \str_if_eq:xxF {#1} { \s_par_omit }
+ {
+ \galley_std_par_aux_ii:
+ #1
+ }
+ }
+\cs_new_protected_nopar:Npn \galley_std_par_aux_ii:
+ {
\mode_if_vertical:TF
{ \tex_par:D }
{
@@ -206,6 +229,15 @@
\tl_gclear:N \g_galley_par_after_hook_tl
\tex_penalty:D \c_ten_thousand
}
+\cs_new_protected:Npn \galley_end_par:n #1
+ {
+ \s_par_omit
+ \bool_if:nF \g_galley_begin_level_bool
+ {
+ #1
+ \galley_std_par:
+ }
+ }
\cs_set_protected_nopar:Npn \par { \galley_std_par: }
\tl_set:Nn \@par { \galley_std_par: }
\cs_new_protected_nopar:Npn \galley_display_begin:
@@ -354,14 +386,14 @@
{
\g_galley_whatsit_next_tl
\tl_gclear:N \g_galley_whatsit_next_tl
- \bool_if:NT \g_galley_omit_next_indent_bool
+ \bool_if:NF \g_galley_omit_next_indent_bool
{
- \box_if_empty:NF \g_galley_last_box
+ \box_if_empty:NF \g_galley_last_box
{ \hbox_to_wd:nn \l_galley_par_indent_dim { } }
}
\skip_horizontal:N \l_galley_par_begin_skip
\g_galley_par_begin_hook_tl
- \bool_gset_true:N \g_galley_omit_next_indent_bool
+ \bool_gset_false:N \g_galley_omit_next_indent_bool
}
\cs_new_protected_nopar:Npn \galley_restore_running_parameters:
{
@@ -732,6 +764,20 @@
{ \int_use:N \etex_widowpenalties:D \int_eval:w #1 \int_eval_end: , }
\cs_new_protected_nopar:Npn \galley_interline_penalty:
{ \int_use:N \etex_interlinepenalties:D \etex_interlinepenalties:D \c_zero }
+\cs_set_protected_nopar:Npn \nobreak
+ { \bool_gset_true:N \g_galley_no_break_next_bool }
+\cs_set_protected_nopar:Npn \noindent
+ {
+ \tex_noindent:D
+ \bool_gset_false:N \g_galley_omit_next_indent_bool
+ }
+\cs_set_protected_nopar:Npn \vspace #1
+ {
+ \@ifstar
+ { \galley_set_user_vspace:n {#1} }
+ { \galley_set_user_vspace:n {#1} }
+ }
+\cs_set_eq:NN \@@par \galley_std_par:
\cs_set_protected_nopar:Npn \@afterheading
{
\bool_gset_true:N \g_galley_no_break_next_bool
@@ -742,6 +788,8 @@
}
\cs_set_protected:Npn \@hangfrom #1
{
+ \bool_gset_true:N \g_galley_omit_next_indent_bool
+ \leavevmode
\setbox \@tempboxa = \hbox { {#1} }
\galley_parshape_single_par:nnnN
\c_one
@@ -749,16 +797,9 @@
\c_zero_dim
\c_false_bool
\bool_gset_true:N \g_galley_no_break_next_bool
- \bool_gset_true:N \galley_omit_next_indent_bool
+ \bool_gset_true:N \g_galley_omit_next_indent_bool
\box \@tempboxa
}
-\cs_set_protected:Npn \@makefntext #1
- {
- \UseTemplate { justification } { std } { indent-width = 1 em }
- \bool_gset_true:N \galley_omit_next_indent_bool
- \galley_leave_vmode:
- \hb@xt@ 1.8em { \hss \@makefnmark } #1
- }
%%
%%
%% End of file `l3galley.sty'.
diff --git a/Master/texmf-dist/tex/latex/l3experimental/xgalley/xgalley.sty b/Master/texmf-dist/tex/latex/l3experimental/xgalley/xgalley.sty
index 160fca57631..5ebe766a12b 100644
--- a/Master/texmf-dist/tex/latex/l3experimental/xgalley/xgalley.sty
+++ b/Master/texmf-dist/tex/latex/l3experimental/xgalley/xgalley.sty
@@ -48,7 +48,7 @@
%% -----------------------------------------------------------------------
%%
\RequirePackage{l3names}
-\GetIdInfo$Id: xgalley.dtx 2895 2011-10-09 15:58:19Z joseph $
+\GetIdInfo$Id: xgalley.dtx 2922 2011-10-17 19:01:04Z joseph $
{L3 Experimental galley}
\ProvidesExplPackage
{\ExplFileName}{\ExplFileDate}{\ExplFileVersion}{\ExplFileDescription}
@@ -606,11 +606,6 @@
{ \skip_eval:n { \l_galley_display_end_vspace_tl } }
}
}
-\RenewDocumentCommand \nobreak { }
- { \bool_gset_true:N \g_galley_no_break_next_bool }
-\RenewDocumentCommand \noindent { }
- { \bool_gset_false:N \g_galley_omit_next_indent_bool }
-\RenewDocumentCommand \vspace { s m } { \galley_set_vspace_user:n {#2} }
%%
%%
%% End of file `xgalley.sty'.