Mercurial > repo
annotate perl-5.22.2/regen/regcharclass_multi_char_folds.pl @ 8045:a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
author | HackBot |
---|---|
date | Sat, 14 May 2016 14:54:38 +0000 |
parents | |
children |
rev | line source |
---|---|
8045
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
1 package regcharclass_multi_char_folds; |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
2 use 5.015; |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
3 use strict; |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
4 use warnings; |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
5 use Unicode::UCD "prop_invmap"; |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
6 |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
7 # This returns an array of strings of the form |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
8 # "\x{foo}\x{bar}\x{baz}" |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
9 # of the sequences of code points that are multi-character folds in the |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
10 # current Unicode version. If the parameter is 1, all such folds are |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
11 # returned. If the parameters is 0, only the ones containing exclusively |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
12 # Latin1 characters are returned. In the latter case all combinations of |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
13 # Latin1 characters that can fold to the base one are returned. Thus for |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
14 # 'ss', it would return in addition, 'Ss', 'sS', and 'SS'. This is because |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
15 # this code is designed to help regcomp.c, and EXACTFish regnodes. For |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
16 # non-UTF-8 patterns, the strings are not folded, so we need to check for the |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
17 # upper and lower case versions. For UTF-8 patterns, the strings are folded, |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
18 # except in EXACTFL nodes) so we only need to worry about the fold version. |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
19 # All folded-to characters in non-UTF-8 (Latin1) are members of fold-pairs, |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
20 # at least within Latin1, 'k', and 'K', for example. So there aren't |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
21 # complications with dealing with unfolded input. That's not true of UTF-8 |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
22 # patterns, where things can get tricky. Thus for EXACTFL nodes where things |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
23 # aren't all folded, code has to be written specially to handle this, instead |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
24 # of the macros here being extended to try to handle it. |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
25 # |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
26 # There are no non-ASCII Latin1 multi-char folds currently, and none likely to |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
27 # be ever added. Thus the output is the same as if it were just asking for |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
28 # ASCII characters, not full Latin1. Hence, it is suitable for generating |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
29 # things that match EXACTFA. It does check for and croak if there ever were |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
30 # to be an upper Latin1 range multi-character fold. |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
31 # |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
32 # This is designed for input to regen/regcharlass.pl. |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
33 |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
34 sub gen_combinations ($;) { |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
35 # Generate all combinations for the first parameter which is an array of |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
36 # arrays. |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
37 |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
38 my ($fold_ref, $string, $i) = @_; |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
39 $string = "" unless $string; |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
40 $i = 0 unless $i; |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
41 |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
42 my @ret; |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
43 |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
44 # Look at each element in this level's array. |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
45 foreach my $j (0 .. @{$fold_ref->[$i]} - 1) { |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
46 |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
47 # Append its representation to what we have currently |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
48 my $new_string = sprintf "$string\\x{%X}", $fold_ref->[$i][$j]; |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
49 |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
50 if ($i >= @$fold_ref - 1) { # Final level: just return it |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
51 push @ret, "\"$new_string\""; |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
52 } |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
53 else { # Generate the combinations for the next level with this one's |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
54 push @ret, &gen_combinations($fold_ref, $new_string, $i + 1); |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
55 } |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
56 } |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
57 |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
58 return @ret; |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
59 } |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
60 |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
61 sub multi_char_folds ($) { |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
62 my $all_folds = shift; # The single parameter is true if wants all |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
63 # multi-char folds; false if just the ones that |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
64 # are all ascii |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
65 |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
66 my ($cp_ref, $folds_ref, $format) = prop_invmap("Case_Folding"); |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
67 die "Could not find inversion map for Case_Folding" unless defined $format; |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
68 die "Incorrect format '$format' for Case_Folding inversion map" |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
69 unless $format eq 'al'; |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
70 my @folds; |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
71 |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
72 for my $i (0 .. @$folds_ref - 1) { |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
73 next unless ref $folds_ref->[$i]; # Skip single-char folds |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
74 |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
75 # The code in regcomp.c currently assumes that no multi-char fold |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
76 # folds to the upper Latin1 range. It's not a big deal to add; we |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
77 # just have to forbid such a fold in EXACTFL nodes, like we do already |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
78 # for ascii chars in EXACTFA (and EXACTFL) nodes. But I (khw) doubt |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
79 # that there will ever be such a fold created by Unicode, so the code |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
80 # isn't there to occupy space and time; instead there is this check. |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
81 die sprintf("regcomp.c can't cope with a latin1 multi-char fold (found in the fold of 0x%X", $cp_ref->[$i]) if grep { $_ < 256 && chr($_) !~ /[[:ascii:]]/ } @{$folds_ref->[$i]}; |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
82 |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
83 # Create a line that looks like "\x{foo}\x{bar}\x{baz}" of the code |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
84 # points that make up the fold. |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
85 my $fold = join "", map { sprintf "\\x{%X}", $_ } @{$folds_ref->[$i]}; |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
86 $fold = "\"$fold\""; |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
87 |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
88 # Skip if something else already has this fold |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
89 next if grep { $_ eq $fold } @folds; |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
90 |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
91 if ($all_folds) { |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
92 push @folds, $fold |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
93 } # Skip if wants only all-ascii folds, and there is a non-ascii |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
94 elsif (! grep { chr($_) =~ /[^[:ascii:]]/ } @{$folds_ref->[$i]}) { |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
95 |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
96 # If the fold is to a cased letter, replace the entry with an |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
97 # array which also includes its upper case. |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
98 my $this_fold_ref = $folds_ref->[$i]; |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
99 for my $j (0 .. @$this_fold_ref - 1) { |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
100 my $this_ord = $this_fold_ref->[$j]; |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
101 if (chr($this_ord) =~ /\p{Cased}/) { |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
102 my $uc = ord(uc(chr($this_ord))); |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
103 undef $this_fold_ref->[$j]; |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
104 @{$this_fold_ref->[$j]} = ( $this_ord, $uc); |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
105 } |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
106 } |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
107 |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
108 # Then generate all combinations of upper/lower case of the fold. |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
109 push @folds, gen_combinations($this_fold_ref); |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
110 |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
111 } |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
112 } |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
113 |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
114 # \x17F is the small LONG S, which folds to 's'. Both Capital and small |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
115 # LATIN SHARP S fold to 'ss'. Therefore, they should also match two 17F's |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
116 # in a row under regex /i matching. But under /iaa regex matching, all |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
117 # three folds to 's' are prohibited, but the sharp S's should still match |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
118 # two 17F's. This prohibition causes our regular regex algorithm that |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
119 # would ordinarily allow this match to fail. This is the only instance in |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
120 # all Unicode of this kind of issue. By adding a special case here, we |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
121 # can use the regular algorithm (with some other changes elsewhere as |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
122 # well). |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
123 # |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
124 # It would be possible to re-write the above code to automatically detect |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
125 # and handle this case, and any others that might eventually get added to |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
126 # the Unicode standard, but I (khw) don't think it's worth it. I believe |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
127 # that it's extremely unlikely that more folds to ASCII characters are |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
128 # going to be added, and if I'm wrong, fold_grind.t has the intelligence |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
129 # to detect them, and test that they work, at which point another special |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
130 # case could be added here if necessary. |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
131 # |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
132 # No combinations of this with 's' need be added, as any of these |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
133 # containing 's' are prohibted under /iaa. |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
134 push @folds, '"\x{17F}\x{17F}"' if $all_folds; |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
135 |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
136 |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
137 return @folds; |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
138 } |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
139 |
a16537d2fe07
<xfix> tar xf perl-5.22.2.tar.gz # Ah, whatever, I\'m doing it anyway
HackBot
parents:
diff
changeset
|
140 1 |