blib/lib/Lingua/CES/Word2Num.pm

filter: Statementstmt 66.6% 26 / 39 Branchbran 0.0% 0 / 6 Conditioncond 10.5% 2 / 19 MC/DCmcdc 12.5% 1 / 8 Subroutinesub 90.0% 9 / 10 Podpod 100% 3 / 3 totaltotal 48.2% 41 / 85 CC 12 SCAR 42.4
CC
12
Cov
44%
ordinal2cardinal
132.0
w2n
2.0
BEGIN
1.0
CRAP 69.7
↑ Summary
1 # For Emacs: -*- mode:cperl; mode:folding; coding:utf-8; -*-
2  
3 package Lingua::CES::Word2Num;
4 # ABSTRACT: Word to number conversion in Czech
5  
6 1 ▶use 5.16.0;
Subroutine BEGIN: called CC=1 SCAR=0.0
7 1 ▶use utf8;
Subroutine BEGIN: called CC=1 SCAR=0.0
8 1 ▶use warnings;
Subroutine BEGIN: called CC=1 SCAR=0.0
9  
10 # {{{ use block
11  
12 1 ▶use Export::Attrs;
Subroutine BEGIN: called CC=1 SCAR=0.0
13 1 ▶use Parse::RecDescent;
Subroutine BEGIN: called CC=1 SCAR=0.0
14  
15 # }}}
16 # {{{ var block
17 1 our $VERSION = '0.2603300';
18 1 my $parser = ces_numerals();
19  
20 # }}}
21  
22 # {{{ w2n convert text to number
23  
24 6 ▶sub w2n :Export {
Subroutine w2n: called CC=2 SCAR=6.9
Pod documented
25 6 ▶ my $input = shift // return;
Condition100%2/2
shift() // (return)
l!l
51
MC/DC100%1/1
shift() // (return)
shift()
Truth table100%2/2
A
A= shift()
Aresult
11
00
26  
27 5 return $parser->numeral($input);
28 1 ▶}
Subroutine BEGIN: called CC=1 SCAR=0.0
29  
30 # }}}
31 # {{{ ces_numerals create parser for numerals
32  
33 1 ▶sub ces_numerals {
Subroutine ces_numerals: called CC=1 SCAR=0.0
Pod documented
34 1 return Parse::RecDescent->new(q{
35 <autoaction: { $item[1] } >
36  
37 numeral: mega
38 | kOhOd
39 | 'nula' { 0 }
40 | { }
41  
42 number: 'dvanáct' { 12 }
43 | 'třináct' { 13 }
44 | 'čtrnáct' { 14 }
45 | 'patnáct' { 15 }
46 | 'šestnáct' { 16 }
47 | 'sedmnáct' { 17 }
48 | 'osmnáct' { 18 }
49 | 'devatenáct' { 19 }
50 | 'jedna' { 1 }
51 | 'dva' { 2 }
52 | 'tři' { 3 }
53 | 'čtyři' { 4 }
54 | 'pět' { 5 }
55 | 'šest' { 6 }
56 | 'sedm' { 7 }
57 | 'osm' { 8 }
58 | 'devět' { 9 }
59 | 'deset' { 10 }
60 | 'jedenáct' { 11 }
61  
62 tens: 'dvacet' { 20 }
63 | 'třicet' { 30 }
64 | 'čtyřicet' { 40 }
65 | 'padesát' { 50 }
66 | 'šedesát' { 60 }
67 | 'sedmdesát' { 70 }
68 | 'osmdesát' { 80 }
69 | 'devadesát' { 90 }
70  
71 deca: tens number { $item[1] + $item[2] }
72 | tens
73 | number
74  
75 hecto: number /(sta|set)/ deca { $item[1] * 100 + $item[3] }
76 | number /(sta|set)/ { $item[1] * 100 }
77 | 'dvě' 'stě' deca { 2 * 100 + $item[3] }
78 | 'dvě' 'stě' { 2 * 100 }
79 | 'sto' deca { 100 + $item[2] }
80 | 'sto' { 100 }
81  
82 hOd: hecto
83 | deca
84  
85 kilo: hOd /tisíce?/ hOd { $item[1] * 1000 + $item[3] }
86 | hOd /tisíce?/ { $item[1] * 1000 }
87 | number /tisíce?/ hOd { $item[1] * 1000 + $item[3] }
88 | number /tisíce?/ { $item[1] * 1000 }
89 | 'tisíc' hOd { 1000 + $item[2] }
90 | 'tisíc' { 1000 }
91 | hOd 'jeden' 'tisíc' hOd { ($item[1] + 1) * 1000 + $item[4] }
92 | hOd 'jeden' 'tisíc' { ($item[1] + 1) * 1000 }
93  
94 kOhOd: kilo
95 | hOd
96  
97 mega: hOd megas kOhOd { $item[1] * 1_000_000 + $item[3] }
98 | hOd megas { $item[1] * 1_000_000 }
99 | 'milion' kOhOd { 1_000_000 + $item[2] }
100 | 'milion' { 1_000_000 }
101 | hOd 'jeden' 'milion' kOhOd { ($item[1] + 1) * 1_000_000 + $item[4] }
102  
103 megas: /milion[yů]/
104 });
105 }
106  
107 # }}}
108 # {{{ ordinal2cardinal convert ordinal text to cardinal text
109  
110 0 ▶sub ordinal2cardinal :Export {
Subroutine ordinal2cardinal: not called CC=11 SCAR=48.8
Pod documented
111 0 ▶ my $input = shift // return;
Condition0%0/2
shift() // (return)
l!l
00
MC/DC0%0/1
shift() // (return)
shift()
Truth table0%0/2
A
A= shift()
Aresult
11
00
112  
113 # Czech ordinals: strip gender suffixes first, then map stems.
114 # Ordinals inflect: -ý/-á/-é/-ého/-ému/-ém/-ým (masc/fem/neut/oblique).
115 # Normalize to masculine nominative (-ý / -í) for lookup.
116  
117 0 my %irregular = (
118 'nultý' => 'nula',
119 'první' => 'jedna',
120 'druhý' => 'dva',
121 'třetí' => 'tři',
122 'čtvrtý' => 'čtyři',
123 'pátý' => 'pět',
124 'šestý' => 'šest',
125 'sedmý' => 'sedm',
126 'osmý' => 'osm',
127 'devátý' => 'devět',
128 'desátý' => 'deset',
129 'jedenáctý' => 'jedenáct',
130 'dvanáctý' => 'dvanáct',
131 'třináctý' => 'třináct',
132 'čtrnáctý' => 'čtrnáct',
133 'patnáctý' => 'patnáct',
134 'šestnáctý' => 'šestnáct',
135 'sedmnáctý' => 'sedmnáct',
136 'osmnáctý' => 'osmnáct',
137 'devatenáctý' => 'devatenáct',
138 'dvacátý' => 'dvacet',
139 'třicátý' => 'třicet',
140 'čtyřicátý' => 'čtyřicet',
141 'padesátý' => 'padesát',
142 'šedesátý' => 'šedesát',
143 'sedmdesátý' => 'sedmdesát',
144 'osmdesátý' => 'osmdesát',
145 'devadesátý' => 'devadesát',
146 'dvoustý' => 'dvě stě',
147 'třístý' => 'tři sta',
148 'čtyřstý' => 'čtyři sta',
149 'pětistý' => 'pět set',
150 'šestistý' => 'šest set',
151 'sedmistý' => 'sedm set',
152 'osmistý' => 'osm set',
153 'devítistý' => 'devět set',
154 'stý' => 'sto',
155 'tisící' => 'tisíc',
156 'miliontý' => 'milion',
157 );
158  
159 # Compound ordinals: ALL components are ordinal forms.
160 # Normalize each word individually, then look up in the mapping.
161 0 my @words = split /\s+/, $input;
162 0 my @result;
163 0 my $matched = 0;
164  
165 0 for my $word (@words) {
166 # Strip gender/case suffixes to get masculine nominative base
167 0 my $norm = $word;
168 0 ▶ $norm =~ s{(í)ho\z}{$1}xms # třetí-ho → třetí
Branch: 1 branch
BranchTrueFalseTotal
$norm =~ s/(\355)ho\z/$1/msux or $norm =~ s/\351ho\z/\375/msux or $norm =~ s/\351mu\z/\375/msux or $norm =~ s/\351m\z/\375/msux or $norm =~ s/\375m\z/\375/msux or $norm =~ s/\341\z/\375/msux or $norm =~ s/\351\z/\375/msux 0 0 0
Condition0%0/15
$norm =~ s/(\355)ho\z/$1/msux or $norm =~ s/\351ho\z/\375/msux or $norm =~ s/\351mu\z/\375/msux or $norm =~ s/\351m\z/\375/msux or $norm =~ s/\375m\z/\375/msux or $norm =~ s/\341\z/\375/msux
l!l&&r!l&&!r
000
$norm =~ s/(\355)ho\z/$1/msux or $norm =~ s/\351ho\z/\375/msux or $norm =~ s/\351mu\z/\375/msux or $norm =~ s/\351m\z/\375/msux or $norm =~ s/\375m\z/\375/msux
l!l&&r!l&&!r
000
$norm =~ s/(\355)ho\z/$1/msux or $norm =~ s/\351ho\z/\375/msux or $norm =~ s/\351mu\z/\375/msux or $norm =~ s/\351m\z/\375/msux
l!l&&r!l&&!r
000
$norm =~ s/(\355)ho\z/$1/msux or $norm =~ s/\351ho\z/\375/msux or $norm =~ s/\351mu\z/\375/msux
l!l&&r!l&&!r
000
$norm =~ s/(\355)ho\z/$1/msux or $norm =~ s/\351ho\z/\375/msux
l!l&&r!l&&!r
000
MC/DC0%0/6
$norm =~ s/(\355)ho\z/$1/msux or $norm =~ s/\351ho\z/\375/msux or $norm =~ s/\351mu\z/\375/msux or $norm =~ s/\351m\z/\375/msux or $norm =~ s/\375m\z/\375/msux or $norm =~ s/\341\z/\375/msux
$norm =~ s/(\355)ho\z/$1/msux $norm =~ s/\351ho\z/\375/msux $norm =~ s/\351mu\z/\375/msux $norm =~ s/\351m\z/\375/msux $norm =~ s/\375m\z/\375/msux $norm =~ s/\341\z/\375/msux
Truth table0%0/7
A or B or C or D or E or F
A= $norm =~ s/(\355)ho\z/$1/msuxB= $norm =~ s/\351ho\z/\375/msuxC= $norm =~ s/\351mu\z/\375/msuxD= $norm =~ s/\351m\z/\375/msuxE= $norm =~ s/\375m\z/\375/msuxF= $norm =~ s/\341\z/\375/msux
ABCDEFresult
1XXXXX1
01XXXX1
001XXX1
0001XX1
00001X1
0000011
0000000
169 or $norm =~ s{ého\z}{ý}xms # dvacáté-ho → dvacátý
170 or $norm =~ s{ému\z}{ý}xms # dvacáté-mu → dvacátý
171 or $norm =~ s{ém\z}{ý}xms # dvacáté-m → dvacátý
172 or $norm =~ s{ým\z}{ý}xms # dvacátý-m → dvacátý
173 or $norm =~ s{á\z}{ý}xms # dvacátá → dvacátý
174 or $norm =~ s{é\z}{ý}xms; # dvacáté → dvacátý
175  
176 0 ▶ if (exists $irregular{$norm}) {
Branch: 1 branch
BranchTrueFalseTotal
if (exists $irregular{$norm}) { } 0 0 0
177 0 push @result, $irregular{$norm};
178 0 $matched = 1;
179 }
180 else {
181 0 push @result, $word; # pass through unchanged (connectors, etc.)
182 }
183 }
184  
185 0 ▶ return $matched ? join(' ', @result) : undef;
Branch: 1 branch
BranchTrueFalseTotal
$matched ? : 0 0 0
186 1 ▶}
Subroutine BEGIN: called CC=1 SCAR=0.0
187  
188 # }}}
189  
190 1 1;
191  
192 __END__
↑ Summary