X-Git-Url: http://git.rot13.org/?p=webpac2;a=blobdiff_plain;f=t%2F3-normalize.t;h=76acb045b04b1a6f34e6fbd1bda8bb9629d9e94d;hp=6dcc3b33dd90a74dbfd3721b7f6c019b0b30110d;hb=e60b14a6092e1341c96d6d586b0d6968502b1dae;hpb=d8abf58ba24b367d2a8cbd5c87c890a8498ec561 diff --git a/t/3-normalize.t b/t/3-normalize.t index 6dcc3b3..76acb04 100755 --- a/t/3-normalize.t +++ b/t/3-normalize.t @@ -1,25 +1,17 @@ #!/usr/bin/perl -w use strict; +use lib 'lib'; -use Test::More tests => 322; -use Test::Exception; -use Cwd qw/abs_path/; -use blib; -use File::Slurp; -use Getopt::Long; +use Test::More tests => 364; + +use utf8; BEGIN { + use_ok( 'WebPAC::Test' ); use_ok( 'WebPAC::Normalize' ); } -use Data::Dump qw/dump/; - -my $debug = 0; -GetOptions( - "debug+", \$debug -); - cmp_ok(_debug(1), '==', 1, '_debug level'); cmp_ok(_debug(0), '==', 0, '_debug level'); @@ -28,10 +20,6 @@ if ($debug > 2) { diag "debug level for WebPAC::Normalize is ", _debug( $debug - 2 ); } -ok(my $abs_path = abs_path($0), "abs_path"); -$abs_path =~ s#/[^/]*$#/#; -diag "abs_path: $abs_path" if ($debug); - my $rec1 = { '200' => [{ 'a' => '200a', @@ -69,7 +57,7 @@ my $rec2 = { } ], '700' => [ { 'a' => 'Haynal', - 'b' => 'André' + 'b' => 'André' } ], '801' => [ 'FFZG' ], '991' => [ '8302' ], @@ -92,7 +80,7 @@ my $rec2 = { 'e' => 'from Freud and Ferenczi to Michael balint', 'a' => 'Controversies in psychoanalytic method', 'g' => 'translated by Elizabeth Holder on the basisi of a first draft by Archie Hooton ; with a preface by Daniel N. Stern', - 'f' => 'by André E. Haynal' + 'f' => 'by André E. Haynal' } ], '610' => [ 'povijest psihoanalize' ], '994' => [ { @@ -176,7 +164,7 @@ sub test_s { ok(! _set_lookup( undef ), "set_lookup(undef)"); - _set_rec( $rec1 ); + _set_ds( $rec1 ); cmp_ok( join(",", rec2('200','a') ), 'eq', '200a,200a*2', 'join rec2' ); cmp_ok( join(",", rec2('200','a'), rec2('200','b') ), 'eq', '200a,200a*2,200b', 'join rec2 rec2' ); @@ -191,8 +179,16 @@ sub test_s { # simple list manipulatons cmp_ok( join('', prefix('ab', 'cd') ), 'eq', 'abcd', 'prefix'); + cmp_ok( join('-', prefix('', 'x', 'y') ), 'eq', 'x-y', 'prefix empty'); + cmp_ok( join('-', prefix(0, 'x', 'y') ), 'eq', '0x-0y', 'prefix 0'); + cmp_ok( join('', suffix('xy', 'cd') ), 'eq', 'cdxy', 'suffix'); + cmp_ok( join('-', suffix('', 'x', 'y' ) ), 'eq', 'x-y', 'suffix empty'); + cmp_ok( join('-', suffix(0, 'x', 'y' ) ), 'eq', 'x0-y0', 'suffix 0'); + cmp_ok( join('', surround('->', '<-', 'a','b','c') ), 'eq', '->a<-->b<-->c<-', 'surround'); + cmp_ok( join('-', surround('', '', 'x','y','z') ), 'eq', 'x-y-z', 'surround empty'); + cmp_ok( join('-', surround(0, 0, 'x','y','z') ), 'eq', '0x0-0y0-0z0', 'surround 0 0'); # count my @el; @@ -207,7 +203,7 @@ sub test_s { ok(_set_load_row(sub { my ($database,$input,$mfn) = @_; - diag "load_row( $database, $input, $mfn )"; + diag "load_row( $database, $input, $mfn )" if ($debug); cmp_ok( $#_, '==', 2, 'have 3 arguments'); ok($database, '_load_row database'); ok($input, '_load_row input'); @@ -236,13 +232,13 @@ sub test_s { ); ok(my $l = WebPAC::Normalize::_get_lookup(), '_get_lookup'); - diag "_get_lookup = ", dump($l); + diag "_get_lookup = ", dump($l) if ($debug); my @lookup; ok(@lookup = lookup( sub { - diag "in show"; + diag "in show" if ($debug); rec('900','x'); }, 'db','input','key', @@ -261,7 +257,7 @@ sub test_s { } ok(my $l = WebPAC::Normalize::_get_lookup(), '_get_lookup'); - diag "_get_lookup = ", dump($l); + diag "_get_lookup = ", dump($l) if ($debug); is_deeply( $l, { db => { @@ -281,7 +277,7 @@ sub test_s { ####### - diag "lookup_hash1 = ", dump($lookup_hash1); + diag "lookup_hash1 = ", dump($lookup_hash1) if ($debug); ok(_set_lookup( $lookup_hash1 ), '_set_lookup $lookup_hash1'); throws_ok { _set_load_row() } qr/CODE/, 'empty _set_load_row()'; @@ -364,15 +360,15 @@ sub test_s { #ok(! lookup('non-existent'), 'lookup non-existant' ); - _set_rec( $rec2 ); + _set_ds( $rec2 ); test_s(qq{ - tag('Title', + search_display('Title', rec('200','a') ); }); test_s(qq{ - tag('Who', + search_display('Who', join_with(" ", rec('702','a'), rec('702','b') @@ -423,11 +419,16 @@ sub test_s { test_check_ds('display'); _clean_ds(); - test_s(qq{ tag('something', '42'); }); - test_s(qq{ tag('empty', ''); }); + test_s(qq{ search_display('something', '42'); }); + test_s(qq{ search_display('empty', ''); }); test_check_ds('search'); test_check_ds('display'); + _clean_ds(); + test_s(qq{ sorted('something', '42'); }); + test_s(qq{ sorted('empty', ''); }); + test_check_ds('sorted'); + _clean_ds(); my $n = read_file( "$abs_path/data/normalize.pl" ); $n .= "\n1;\n"; @@ -446,13 +447,12 @@ sub test_s { my $rules = qq{ search('mixed', rec('200') ) }; _clean_ds(); - _set_rec( $rec ); + _set_ds( $rec ); test_s( $rules ); ok($ds = _get_ds(), "get_ds"); is_deeply( $ds, { 'mixed' => { 'search' => [ '200a', '200b' ], - 'tag' => 'mixed' } }, 'correct get_ds'); @@ -464,7 +464,7 @@ sub test_s { # wird and non-valid structure which is supported anyway _clean_ds(); - _set_rec({ + _set_ds({ '200' => [{ 'a' => '200a', }, @@ -476,7 +476,6 @@ sub test_s { is_deeply( $ds, { 'mixed' => { 'search' => [ '200a', '200-solo' ], - 'tag' => 'mixed' } }, 'correct get_ds'); @@ -488,7 +487,7 @@ sub test_s { test_s(qq{ marc_indicators('900',1,2) }); test_s(qq{ marc('900','a', rec('200') ) }); my $marc; - ok($marc = WebPAC::Normalize::_get_marc_fields(), "_get_marc_fields"); + ok($marc = WebPAC::Normalize::MARC::_get_marc_fields(), "_get_marc_fields"); diag dump( $marc ) if ($debug); is_deeply( $marc, [ @@ -499,7 +498,7 @@ sub test_s { test_s(qq{ marc_indicators('900',' ',9) }); test_s(qq{ marc_repeatable_subfield('900','a', rec('200') ) }); - ok($marc = WebPAC::Normalize::_get_marc_fields(), "_get_marc_fields"); + ok($marc = WebPAC::Normalize::MARC::_get_marc_fields(), "_get_marc_fields"); diag dump( $marc ) if ($debug); is_deeply( $marc, [ @@ -515,17 +514,18 @@ sub test_s { my ($msg, $rec, $rules, $struct) = @_; _clean_ds(); - _set_rec($rec); + _set_ds($rec); - foreach my $r (split(/;/, $rules)) { + foreach my $r (split(/;\s*$/, $rules)) { $r =~ s/[\s\n\r]+/ /gs; $r =~ s/^\s+//gs; $r =~ s/\s+$//gs; + diag "rule: $r" if $debug; test_s($r) if ($r); } - ok(my $marc = WebPAC::Normalize::_get_marc_fields(), "_get_marc_fields"); - diag dump( $marc ) if ($debug); + ok(my $marc = WebPAC::Normalize::MARC::_get_marc_fields(), "_get_marc_fields"); + diag dump( $marc ) if $debug; diag "expects:\n", dump($struct) if ($debug > 1); is_deeply( $marc, $struct, $msg ); } @@ -624,7 +624,7 @@ sub test_s { sub test_rule { my ($msg, $rec, $rule, $struct) = @_; _clean_ds(); - _set_rec( $rec ); + _set_ds( $rec ); $rule =~ s/\\/\\/gs; my $r = test_s( $rule ); diag "for ", dump($rec), " got:\n", dump($r), "\nexpect:\n" if ($debug > 1); @@ -734,21 +734,26 @@ sub test_s { ); test_s(qq{ marc_remove('*'); }); - ok(! WebPAC::Normalize::_get_marc_fields(), 'marc_remove(*)'); + ok(! WebPAC::Normalize::MARC::_get_marc_fields(), 'marc_remove(*)'); test_rec_rules( 'marc_duplicate', { '200' => [{ a => 42, b => 'bar', c => 'baz', d => 'bing', e => 'bong' }] }, qq{ + marc_leader('06',42); + marc_leader('11',0); marc('900', 'a', rec('200','a') ); marc('900', 'b', rec('200','b') ); marc_duplicate; + marc_leader('11',1); marc_remove('900','b'); marc('900', 'b', rec('200','c') ); marc_duplicate; + marc_leader('11',2); marc_remove('900','b'); marc('900', 'b', rec('200','d') ); marc_duplicate; + marc_leader('11',3); marc_remove('900','b'); marc('900', 'b', rec('200','e') ); }, @@ -758,10 +763,12 @@ sub test_s { ], ); + cmp_ok( marc_count(), '==', 3, 'marc_count' ); + my $i = 0; foreach my $v ( qw/bar baz bing bong/ ) { - ok($marc = WebPAC::Normalize::_get_marc_fields( offset => $i ), + ok($marc = WebPAC::Normalize::MARC::_get_marc_fields( offset => $i ), "_get_marc_fields( offset => $i )" ); diag "marc $i = ", dump( $marc ) if ($debug); @@ -769,6 +776,7 @@ sub test_s { [ [ '900', ' ', ' ', 'a', 42, 'b', $v ] ], "MARC copy $i has $v", ); + is_deeply(WebPAC::Normalize::MARC::_get_marc_leader(), { '06' => 42, 11 => $i }, "_get_marc_leader copy $i"); $i++; } @@ -792,6 +800,27 @@ sub test_s { ], ); + test_rec_rules( + 'marc_original_order and marc_indicators', + { + '200' => [ { + a => [ 'a1', 'a2' ], b => [ 'b1', 'b2' ], c => [ 'c1', 'c2' ], + subfields => [ qw/a 0 b 0 a 1 b 1 c 0 c 1/ ], + }, { + a => [ 'a3', 'a4', 'a5' ], b => 'b3', c => 'c3', + subfields => [ qw/a 0 a 1 b 0 c 0 a 2/ ], + } ], + }, + qq{ + marc_original_order(900,200); + marc_indicators(900,1,2); + }, + [ + [ '900', '1', '2', 'a', 'a1', 'b', 'b1', 'a', 'a2', 'b', 'b2', 'c', 'c1', 'c', 'c2', ], + [ '900', '1', '2', 'a', 'a3', 'a', 'a4', 'b', 'b3', 'c', 'c3', 'a', 'a5', ], + ], + ); + test_rule( 'rec1 skips subfields', { @@ -827,5 +856,96 @@ sub test_s { '^aa1^bb1^aa2^bb2^cc1^cc2', '_pack_subfields_hash( $h, 1 )' ); + + _clean_ds(); + test_s(qq{ + marc_fixed('008', 0, 'abcdef'); + marc_fixed('000', 5, '5'); + marc_fixed('000', 10, 'A'); + marc_fixed('000', 0, '0'); + }); + ok( my $m = WebPAC::Normalize::MARC::_get_marc_fields(), '_get_marc_fields'); + diag dump( $m ); + is_deeply( WebPAC::Normalize::MARC::_get_marc_fields(), + [ + ["008", "abcdef"], + # 0....5....10 + ["000", "0 5 A"] + ] + ); + + test_s(qq{ isbn_13( '1558607013', '978-1558607019' ) }); + test_s(qq{ isbn_10( '1558607013', '978-1558607019' ) }); + + is_deeply( + [ isbn_13( '1558607013', '978-1558607019' ) ], + [ '978-1-55860-701-9', '978-1-55860-701-9', ], + 'isbn_13' ); + + is_deeply( + [ isbn_10( '1558607013', '978-1558607019' ) ], + [ '1-55860-701-3', '1-55860-701-3' ], + 'isbn_10' ); + + # frec + + $rec = { + '200' => [ { + a => [ 'a1', 'a2' ], b => [ 'b1', 'b2' ], c => [ 'c1', 'c2' ], + subfields => [ qw/a 0 b 0 a 1 b 1 c 0 c 1/ ], + i1 => '0', i2 => '1', + }, { + a => [ 'a3', 'a4', 'a5' ], b => 'b3', c => 'c3', + subfields => [ qw/a 0 a 1 b 0 c 0 a 2/ ], + } ], + }; + + test_rule( 'frec', $rec, qq{ frec(200) }, [ 'a1' ] ); + test_rule( 'frec', $rec, qq{ frec(200,'a') }, [ 'a1' ] ); + test_rule( 'frec', $rec, qq{ frec(200,'b') }, [ 'b1' ] ); + test_rule( 'frec', $rec, qq{ frec(200,'c') }, [ 'c1' ] ); + test_rule( 'frec', $rec, qq{ frec(200,'i1') }, [ '0' ] ); + test_rule( 'frec', $rec, qq{ frec(200,'i2') }, [ '1' ] ); + + $rec->{'900'} = $rec->{'200'}; + foreach my $sf ( qw/a b c/ ) { + ok( frec_eq( '200' => $sf, '900' => $sf ), "frec_eq 200 == 900 $sf"); + ok( ! frec_ne( '200' => $sf, '900' => $sf ), "! frec_ne 200 == 900 $sf"); + } + + foreach my $sf ( qw/a b/ ) { + ok( ! frec_eq( '200' => $sf, '200' => 'c' ), "! frec_eq 200 $sf == 200 c"); + ok( frec_ne( '200' => $sf, '200' => 'c' ), "frec_ne 200 $sf == 200 c"); + } + + test_rule( 'rec(200,i1)', $rec, qq{ rec(200,'i1') }, [ '0' ] ); + test_rule( 'rec(200,i2)', $rec, qq{ rec(200,'i2') }, [ '1' ] ); + + my $hash = { a => '[a]', 'b' => '[b]', subfields => [ 'a', 0, 'b', 0 ] }; + is_deeply([ _pack_subfields_hash( $hash ) ], [ '[a]', '[b]' ], '_pack_subfields_hash' ); + ok( $hash->{subfields}, 'subfields exist' ); + cmp_ok( _pack_subfields_hash( $hash, 1 ), 'eq', '^a[a]^b[b]', '_pack_subfields_hash' ); + ok( $hash->{subfields}, 'subfields exist' ); + + $rec = { 'arr' => [ 1, 2, 3 ] }; + test_rule( 'rec_array', $rec, qq{ rec_array('arr') }, $rec->{arr} ); + + _clean_ds(); + _set_ds( $rec ); + test_s(q{ + row( 'table', e => $_ ) foreach ( rec_array('arr') ); + }); + ok( my $rows = _get_ds->{_rows}->{table}, 'ds have _rows' ); + + foreach my $i ( 1 .. 3 ) { + cmp_ok( $rows->[ $i - 1 ]->{e}, '==', $i, "e $i" ); + } + + test_rule( 'utf-8' + , { '900' => [{ a => 'Čev', b => 'ić' }] } + , qq{ join_with('', rec(900,'a'), 'apč', rec(900,'b') ) } + , [ "\x{10C}evap\x{10D}i\x{107}" ] + ); + }