WiktionaryDumps to words: Difference between revisions

Line 497:

my %needles; my $plain = my $tail = '';

my $ua = LWP::UserAgent->new;

my $bz = new Compress::Raw::Bunzip2({ -Bufsize => 1, -AppendOutput => 0 });

my $res = $ua->request( HTTP::Request->new(GET => $URL),

sub { # @_ = Data Chunk, HTTP::Response

sub {

my ~~@Char_Array~~ ~~= split(~~'', $_[0]) ;

foreach (split '', $_[0]) {

foreach (@Char_Array) {

my $status = $bz->bzinflate($_, substr($plain, 0)) ;

last if $status == BZ_STREAM_END or $status != BZ_OK ;

}

my @haystacks = split("\n", $plain);

if ( scalar ( my @haystacks = split "\n", $plain)) {

if ( scalar @haystacks ) {

$haystacks[0] = $tail . $haystacks[0];

$tail = $haystacks[$#haystacks];

Line 516:

Line 513:

my ($title,$got_text_last) = '', 0 ;

foreach (@haystacks[0..$#haystacks-1]) {

foreach ( @haystacks[0..$#haystacks-1] ) {

if ( /<title>(\w+?)<\/title>/ ) {

($title,$got_text_last) = $1, 0;

Line 524:

Line 521:

$needles{$title}++ if ( $got_text_last and $title.defined );

if ( %needles >= $Target ) {

print "$_\n" for keys %needles;

print "$_\n" for sort keys %needles;

exit;

}

Line 535:

Line 532:

<pre>

chien

gratis

pond

chien

gratuit

livre

pond

</pre>