16 |
&load_affix |
&load_affix |
17 |
); |
); |
18 |
|
|
|
#my @affix_regexp; |
|
|
#my @affix_add; |
|
|
#my @affix_sub; |
|
|
|
|
19 |
my $debug=0; |
my $debug=0; |
20 |
|
|
21 |
# stub |
# |
22 |
|
# make new instance of language, get args |
23 |
|
# |
24 |
sub new { |
sub new { |
25 |
my $class = shift; |
my $class = shift; |
26 |
my $self = {}; |
my $self = {}; |
27 |
bless($self, $class); |
bless($self, $class); |
28 |
$self->{ARGS} = {@_}; |
$self->{ARGS} = {@_}; |
29 |
$debug = $self->{ARGS}->{DEBUG}; |
$debug = $self->{ARGS}->{DEBUG}; |
30 |
|
@{$self->{affix_regexp}} = (); |
31 |
|
@{$self->{affix_add}} = (); |
32 |
|
@{$self->{affix_sub}} = (); |
33 |
$self ? return $self : return undef; |
$self ? return $self : return undef; |
34 |
} |
} |
35 |
|
|
79 |
sub nuke_s { |
sub nuke_s { |
80 |
my $tmp = $_[0]; |
my $tmp = $_[0]; |
81 |
return if (!$tmp); |
return if (!$tmp); |
82 |
$tmp=~s/^ *//g; |
# $tmp=~s/^\s+//g; |
83 |
$tmp=~s/ *$//g; |
# $tmp=~s/\s+$//g; |
84 |
$tmp=~s/ *//g; |
$tmp=~s/\s+//g; |
85 |
return $tmp; |
return $tmp; |
86 |
} |
} |
87 |
|
|
93 |
} |
} |
94 |
|
|
95 |
# |
# |
96 |
|
# function for reading raw findaffix output |
97 |
|
# |
98 |
|
|
99 |
|
sub load_findaffix { |
100 |
|
my $self = shift; |
101 |
|
my $filename = shift; |
102 |
|
|
103 |
|
print STDERR "reading findaffix output $filename\n" if ($debug); |
104 |
|
|
105 |
|
open (A,$filename) || die "Can't open findaffix output $filename: $!"; |
106 |
|
while(<A>) { |
107 |
|
chomp; |
108 |
|
my @line=split(m;/;,$_,4); |
109 |
|
if ($#line > 2) { |
110 |
|
push @{$self->{affix_regexp}},'.'; |
111 |
|
push @{$self->{affix_sub}},$line[0]; |
112 |
|
push @{$self->{affix_add}},$line[1]; |
113 |
|
} |
114 |
|
} |
115 |
|
return 1; |
116 |
|
} |
117 |
|
|
118 |
|
# |
119 |
# function which returns original word and all alternatives |
# function which returns original word and all alternatives |
120 |
# |
# |
121 |
|
|
129 |
my $regexp = $self->{affix_regexp}[$i]; |
my $regexp = $self->{affix_regexp}[$i]; |
130 |
my $add = $self->{affix_add}[$i]; |
my $add = $self->{affix_add}[$i]; |
131 |
my $sub = $self->{affix_sub}[$i]; |
my $sub = $self->{affix_sub}[$i]; |
132 |
|
print STDERR "r:'$regexp'\t-'",$sub||'',"'\t+'",$add||'',"'\n" if ($debug); |
133 |
next if length($word) < length($sub); |
next if length($word) < length($sub); |
134 |
my $tmp_word = $word; |
my $tmp_word = $word; |
135 |
if ($sub) { |
if ($sub) { |
142 |
} else { |
} else { |
143 |
$tmp_word = $word.$add; |
$tmp_word = $word.$add; |
144 |
} |
} |
145 |
|
print STDERR "\t ?:$tmp_word\n" if ($debug); |
146 |
if ($tmp_word =~ m/$regexp/ix) { |
if ($tmp_word =~ m/$regexp/ix) { |
147 |
# print "$word -> $tmp_word\t-$sub, +$add, regexp: $regexp\n"; |
# print "$word -> $tmp_word\t-$sub, +$add, regexp: $regexp\n"; |
148 |
push @out,lc($tmp_word); |
push @out,lc($tmp_word); |
158 |
|
|
159 |
=head1 NAME |
=head1 NAME |
160 |
|
|
161 |
Alternative.pm - see all alternatives of a given word in a given language |
Alternative.pm - alternative spelling of a given word in a given language |
162 |
|
|
163 |
=head1 SYNOPSIS |
=head1 SYNOPSIS |
164 |
|
|