-
Notifications
You must be signed in to change notification settings - Fork 1
/
soundslike.pl
executable file
·163 lines (149 loc) · 4.36 KB
/
soundslike.pl
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
#!/usr/bin/perl
# This program is free software: you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program. If not, see <http://www.gnu.org/licenses/>.
#
# https://github.com/flimzy/minimal-pairs/
use strict;
use warnings;
use utf8;
use open qw(:std :utf8);
use Unicode::GCString;
use List::Util qw( max );
use List::MoreUtils qw( any );
my $ignore = "-ːˈ ˌ";
my %chars;
my %ipa;
while (my $line = <>) {
$line =~ m#^\s*(.*?)\s:\s(.*)$# or die "Unable to read input: $line\n";
my ( $ipa, $words ) = ($1,$2);
$ipa =~ s/[$ignore]//g;
my $gc = Unicode::GCString->new($ipa);
$ipa{$ipa} = [ $gc, [split /, /,$words] ];
$chars{ "$_" }++ for $gc->as_array;
}
my $longest_word = max ( map { $_->[0]->columns } values %ipa );
my %pairs;
for my $word (keys %ipa) {
# print "$word";
my @matches = find_matches($word);
# printf " (%i)\n", scalar @matches;
next if ! @matches;
$pairs{$word} ||= [];
push @{$pairs{$word}}, @matches;
# last if scalar keys %pairs > 100;
}
sub find_matches {
my ( $word ) = @_;
my $len = $ipa{$word}[0]->columns;
my @candidates =
grep { $ipa{$_}[0]->columns eq $len } keys %ipa;
# printf("Found %i candiates\n", scalar @candidates);
# Eliminate words with more than one difference
# for (my $i=0; $i < $len-1; $i++) {
#
# }
my @final;
for my $c ( @candidates ) {
my @diff = array_diff($ipa{$word}->[0], $ipa{$c}->[0]);
# printf("Candidate: %s (%i difference)\n", $c, scalar @diff);
if (scalar @diff == 1) {
push @final, $c;
}
}
return @final;
for my $c ( @final ) {
printf("Final candidate: %s\n", $c);
}
}
sub array_diff {
my ( $a, $b ) = @_;
my @diffidx;
for (my $i=0; $i< scalar @$a; $i++) {
if ( $a->[$i] ne $b->[$i] ) {
return if @diffidx == 1; # Early exit
push @diffidx, $i;
}
}
return @diffidx;
}
# for (my $i=0; $i < $longest_word; $i++) {
# for my $word (keys %ipa) {
# next if length($word) <= $i;
# my @word = $ipa{$word}[0]->as_array;
# delete $word[$i];
# my $key = join('', grep { defined } @word);
# $pairs{$key} ||= [];
# push @{$pairs{$key}}, $word;
# }
# }
sub heading {
print<<EOF;
<tr>
<th>Main Pronunciation</th>
<th>Main Word(s)</th>
<th>Pronunciation</th>
<th>Sounds like</th>
</tr>
EOF
}
my $count;
for (keys %pairs) {
next if scalar @{$pairs{$_}}==1;
$count++;
}
print<<EOF;
<html>
<head>
<meta charset="UTF-8">
</head>
<style>
table {
border: 1px solid black;
text-align: left;
}
td {
border: 1px solid black;
}
.ipa {
font-family: 'Charis SIL', 'DejaVu Sans', 'Segoe UI', 'Lucida Grande', 'Doulos SIL', 'TITUS Cyberbit Basic', Code2000, 'Lucida Sans Unicode', sans-serif
}
</style>
<h1>$count French Minimal Pairs</h1>
<p>This file was generated automatically by a script which is <a href='https://github.com/flimzy/minimal-pairs/'>hosted on GitHub</a>.
<table>
EOF
my $j=0;
heading();
for my $pair ( sort { scalar @{$pairs{$b}} <=> scalar @{$pairs{$a}} || $a cmp $b } keys %pairs ) {
last if scalar @{$pairs{$pair}} == 1;
if ( $j >= 30 ) {
heading();
$j=0;
}
my @matches;
for my $ipa ( sort @{$pairs{$pair}} ) {
$j++;
my $gc = $ipa{$ipa}->[0];
push @matches, sprintf "<td class='ipa'>/%s/</td><td>%s</td>\n",
$gc, join(', ',@{$ipa{$ipa}[1]});
}
my $matches = scalar(@{ $pairs{$pair} });
printf "<tr><td rowspan='%i'><span class='ipa'>/%s/</span><br />%i phonetically similar words</td>\n",
$matches, $pair, $matches;
printf "<td rowspan='%i'>" . join(', ', @{$ipa{$pair}[1]}) . "</td>\n",
$matches;
print join("</tr>\n<tr>",@matches)."</tr>\n";
}
print "</table>\n";
printf "<p>Encountered %i distinct graphemes: %s</p>\n",
scalar(keys %chars), join(' ', sort keys %chars);