| 1 |
#!/usr/bin/perl |
#!/usr/bin/perl |
| 2 |
use strict; |
use strict; |
| 3 |
|
|
| 4 |
my $source_file_name = q[.spec.en.html]; |
BEGIN { require 'common.pl' } |
| 5 |
my $data_dir_name = q[data/]; |
|
| 6 |
my $data_suffix = q[.dat]; |
my $source_file_name = shift; |
| 7 |
my $result_file_name = q[non-normative.ja.html.u8]; |
my $result_file_name = shift; |
| 8 |
|
my $status_file_name = shift; |
| 9 |
sub normalize ($) { |
my $tbt_file_name_stem = shift; |
|
my $s = shift; |
|
|
$s =~ s/\s+/ /g; |
|
|
$s =~ s/^ //; |
|
|
$s =~ s/ $//g; |
|
|
return $s; |
|
|
} # normalize |
|
|
|
|
|
sub create_pattern1 ($) { |
|
|
my $s = quotemeta shift; |
|
|
$s =~ s/\\\*/(.+)/g; |
|
|
return $s; |
|
|
} # create_pattern1 |
|
|
|
|
|
sub replace_pattern2 ($@) { |
|
|
my $s = shift; |
|
|
my @arg = @_; |
|
|
$s =~ s/\$(\d+)/$arg[$1 - 1]/g; |
|
|
return $s; |
|
|
} # replace_pattern2 |
|
| 10 |
|
|
| 11 |
my %data; |
my %data; |
| 12 |
my %pattern; |
my %pattern; |
| 13 |
{ |
for_each_data_file (sub ($) { |
| 14 |
opendir my $data_dir, $data_dir_name or die "$0: $data_dir_name: $!"; |
my $data_file_name = shift; |
| 15 |
local $/ = undef; |
warn "$data_file_name...\n"; |
| 16 |
for (readdir $data_dir) { |
load_data_file ($data_file_name, \%data, \%pattern); |
| 17 |
next if /^\./; # hidden files |
}); |
|
my $data_file_name = qq[$data_dir_name$_]; |
|
|
next unless $data_file_name =~ /\Q$data_suffix\E$/; |
|
|
warn "$data_file_name...\n"; |
|
|
open my $data_file, '<:utf8', $data_file_name |
|
|
or die "$0: $data_file_name: $!"; |
|
|
for (split /\n\n+(?=#)/, scalar <$data_file>) { |
|
|
my ($en, $ja) = split /\n#ja\n/, $_; |
|
|
if ($en =~ s/^#en\n//) { |
|
|
$data{normalize ($en)} = $ja; |
|
|
} elsif ($en =~ s/^#regexp\n//) { |
|
|
$pattern{create_pattern1 (normalize ($en))} = $ja; |
|
|
} |
|
|
} |
|
|
} |
|
|
} |
|
| 18 |
my @pattern = sort {length $b <=> length $a} keys %pattern; |
my @pattern = sort {length $b <=> length $a} keys %pattern; |
| 19 |
|
|
| 20 |
my $source_text; |
my $source_text; |
| 26 |
$source_text = <$source_file>; |
$source_text = <$source_file>; |
| 27 |
} |
} |
| 28 |
|
|
| 29 |
|
my $part = 'cover'; |
| 30 |
|
my $status = {}; |
| 31 |
|
my $all_status = {}; |
| 32 |
|
my $tbt_added = {}; |
| 33 |
|
|
| 34 |
|
open my $tbt_file, '>:utf8', $tbt_file_name_stem . '.dat' or |
| 35 |
|
die "$0: $tbt_file_name_stem.dat: $!"; |
| 36 |
|
open my $part_tbt_file, '>:utf8', $tbt_file_name_stem . '-' . $part . '.dat' or |
| 37 |
|
die "$0: $tbt_file_name_stem-$part.dat: $!"; |
| 38 |
|
|
| 39 |
warn "Generating...\n"; |
warn "Generating...\n"; |
| 40 |
$source_text =~ s{(<(?>p(?>re)?|li|d[td]|t[dh]|h[1-6])(?>\s[^>]*)?>)((?>(?!</?(?>p(?>re)?|li|d(?>[tdl]|iv)|t[dh]|h[1-6]|ul|ol)(?>\s[^>]*)?>).)+)} |
$source_text =~ s{(<(?>p(?>re)?|li|d[td]|t[dh]|h[1-6])(?>\s[^>]*)?>)((?>(?!</?(?>p(?>re)?|li|d(?>[tdl]|iv)|t(?>[dr]|h(?>ead)?|able|body|foot)|h[1-6r]|ul|ol)(?>\s[^>]*)?>).)+)} |
| 41 |
{ |
{ |
| 42 |
my ($tag, $text) = ($1, $2); |
my ($tag, $text) = ($1, $2); |
| 43 |
my $n_text = normalize ($text); |
my $n_text = normalize ($text); |
| 44 |
my $ja_text = $data{$n_text}; |
|
| 45 |
if (defined $ja_text) { |
if ($tag =~ /^<h2 id=(\w+)/) { |
| 46 |
$tag . q[<span class=ja-translation lang=ja>] . $ja_text . q[</span>]; |
$part = $1; |
| 47 |
} else { |
open $part_tbt_file, '>:utf8', $tbt_file_name_stem . '-' . $part . '.dat' or |
| 48 |
my $v = $tag . $text; |
die "$0: $tbt_file_name_stem-$part.dat: $!"; |
| 49 |
for my $pattern (@pattern) { |
} |
| 50 |
if ($n_text =~ /^$pattern$/) { |
|
| 51 |
$v = $tag . q[<span class=ja-translation lang=ja>] . |
if (length $n_text) { |
| 52 |
replace_pattern2 ($pattern{$pattern}, $1, $2, $3, $4, $5) . |
my $ja_text = $data{$n_text}; |
| 53 |
q[</span>]; |
|
| 54 |
last; |
$status->{all}++; |
| 55 |
|
$all_status->{$part}->{all}++; |
| 56 |
|
|
| 57 |
|
if (defined $ja_text) { |
| 58 |
|
$status->{ja}++; |
| 59 |
|
$all_status->{$part}->{ja}++; |
| 60 |
|
$tag . q[<span class=ja-translation lang=ja>] . $ja_text . q[</span>]; |
| 61 |
|
} else { |
| 62 |
|
my $v = $tag . $text; |
| 63 |
|
my $has_ja; |
| 64 |
|
for my $pattern (@pattern) { |
| 65 |
|
if ($n_text =~ /^$pattern$/) { |
| 66 |
|
$status->{ja}++; |
| 67 |
|
$v = $tag . q[<span class=ja-translation lang=ja>] . |
| 68 |
|
replace_pattern2 ($pattern{$pattern}, $1, $2, $3, $4, $5) . |
| 69 |
|
q[</span>]; |
| 70 |
|
$has_ja = 1; |
| 71 |
|
last; |
| 72 |
|
} |
| 73 |
|
} |
| 74 |
|
|
| 75 |
|
unless ($has_ja) { |
| 76 |
|
$text =~ s/^\s+//; |
| 77 |
|
$text =~ s/\s+\z//; |
| 78 |
|
$text =~ s/\x0D?\x0A(?:\x0D?\x0A)+/\n/g; |
| 79 |
|
unless ($tbt_added->{$text}) { |
| 80 |
|
print $tbt_file ($text); |
| 81 |
|
print $tbt_file ("\n\n"); |
| 82 |
|
print $part_tbt_file ($text); |
| 83 |
|
print $part_tbt_file ("\n\n"); |
| 84 |
|
$tbt_added->{$text} = 1; |
| 85 |
|
} |
| 86 |
} |
} |
| 87 |
|
|
| 88 |
|
$v; |
| 89 |
} |
} |
| 90 |
$v; |
} else { |
| 91 |
|
$1 . $2; |
| 92 |
} |
} |
| 93 |
}ges; |
}ges; |
| 94 |
$source_text =~ s{(<(?>link|img|script)\s[^>]+>)}{ |
$source_text =~ s{(<(?>link|img|script)\s[^>]+>)}{ |
| 113 |
or die "$0: $result_file_name: $!"; |
or die "$0: $result_file_name: $!"; |
| 114 |
print $result_file $source_text; |
print $result_file $source_text; |
| 115 |
} |
} |
| 116 |
|
|
| 117 |
|
{ |
| 118 |
|
my $time = time; |
| 119 |
|
my @item = ($time, $status->{ja}, $status->{all}); |
| 120 |
|
for my $part (qw(cover introduction infrastructure dom semantics browsers |
| 121 |
|
editing comms syntax rendering no)) { |
| 122 |
|
push @item, $all_status->{$part}->{ja}; |
| 123 |
|
push @item, $all_status->{$part}->{all}; |
| 124 |
|
} |
| 125 |
|
|
| 126 |
|
open my $status_file, '>>', $status_file_name |
| 127 |
|
or die "$0: $status_file_name: $!"; |
| 128 |
|
print $status_file join "\t", @item; |
| 129 |
|
print $status_file "\n"; |
| 130 |
|
close $status_file; |
| 131 |
|
} |
Parent Directory
| 
Revision Log
| 
Patch