Convert-MRC
view release on metacpan or search on metacpan
t/05-script.t view on Meta::CPAN
my $tbx_file_name = catfile($data_dir, $block->tbx_name);
ok(-e $tbx_file_name, $block->tbx_name . ' was created')
or return;
my $tbx = read_file($tbx_file_name);
unlink $tbx_file_name;
is_xml(
$tbx, $block->tbx,
"'" . $block->name . "' correct TBX output");
};
}
# clean up test files afterwards
for my $block ( blocks ){
for($block->create_file){
my $file = catfile($data_dir, $_);
unlink $file if -e $file;
}
}
__DATA__
=== no renaming required
--- input: chicken.txt
--- log_name: chicken.txt.log
--- log
[MSG] MRC2TBX converter version [version]
[MSG] File includes IDs:
C003
C003fr1
C003en1
--- tbx_name: chicken.txt.tbx
--- tbx
<?xml version='1.0' encoding="UTF-8"?>
<!DOCTYPE martif SYSTEM "TBXBasiccoreStructV02.dtd">
<martif type="TBX-Basic-V1" xml:lang="en">
<martifHeader>
<fileDesc>
<titleStmt>
<title>termbase from MRC file</title>
</titleStmt>
<sourceDesc>
<p>generated by Convert::MRC version [version]</p>
</sourceDesc>
<sourceDesc>
<p>a restaurant menu in English and French</p>
</sourceDesc>
</fileDesc>
<encodingDesc>
<p type="DCSName">TBXBasicXCSV02.xcs</p>
</encodingDesc>
</martifHeader>
<text>
<body>
<termEntry id="C003">
<descripGrp>
<descrip type="subjectField">Restaurant Menus</descrip>
</descripGrp>
<langSet xml:lang="fr">
<tig id="C003fr1">
<term>poulet</term>
<termNote type="partOfSpeech">noun</termNote>
<termNote type="grammaticalGender">masculine</termNote>
</tig>
</langSet>
<langSet xml:lang="en">
<tig id="C003en1">
<term>chicken</term>
<termNote type="partOfSpeech">noun</termNote>
</tig>
</langSet>
</termEntry>
</body>
</text>
</martif>
=== some renaming required because of existing log
--- input: garbanzo.txt
--- create_file
garbanzo.txt.log
--- log_name: garbanzo.txt-1.log
--- log
[MSG] MRC2TBX converter version [version]
[MSG] File includes links to:
http://flickr.com/photos/lilgreen/432468210/
[MSG] File includes IDs:
C005
C005en1
C005en2
C005fr1
--- tbx_name: garbanzo.txt-1.tbx
--- tbx
<?xml version='1.0' encoding="UTF-8"?>
<!DOCTYPE martif SYSTEM "TBXBasiccoreStructV02.dtd">
<martif type="TBX-Basic-V1" xml:lang="en">
<martifHeader>
<fileDesc>
<titleStmt>
<title>termbase from MRC file</title>
</titleStmt>
<sourceDesc>
<p>generated by Convert::MRC version [version]</p>
</sourceDesc>
<sourceDesc>
<p>a restaurant menu in English and French</p>
</sourceDesc>
</fileDesc>
<encodingDesc>
<p type="DCSName">TBXBasicXCSV02.xcs</p>
</encodingDesc>
</martifHeader>
<text>
<body>
<termEntry id="C005">
<descripGrp>
<descrip type="subjectField">Restaurant Menus</descrip>
</descripGrp>
<xref type="xGraphic" target="http://flickr.com/photos/lilgreen/432468210/">garbanzo beans</xref>
<langSet xml:lang="en">
<descripGrp>
<descrip type="definition">an edible legume of the family Fabaceae, subfamily Faboideae</descrip>
<admin type="source">http://en.wikipedia.org/wiki/Chickpea</admin>
</descripGrp>
<tig id="C005en1">
<term>chick peas</term>
<termNote type="partOfSpeech">noun</termNote>
</tig>
<tig id="C005en2">
<term>garbanzo beans</term>
<termNote type="partOfSpeech">noun</termNote>
<termNote type="geographicalUsage">southwest United States</termNote>
<admin type="customerSubset">AlmostRipe Foods</admin>
</tig>
</langSet>
<langSet xml:lang="fr">
<tig id="C005fr1">
<term>pois chiches</term>
<termNote type="partOfSpeech">noun</termNote>
</tig>
</langSet>
</termEntry>
</body>
</text>
</martif>
=== some renaming required because of existing TBX
--- input: chair.txt
--- create_file
chair.txt.tbx
chair.txt-1.tbx
--- log_name: chair.txt-2.log
--- log
[MSG] MRC2TBX converter version [version]
[MSG] File includes IDs:
C005
C005en1
C005en2
--- tbx_name: chair.txt-2.tbx
--- tbx
<?xml version='1.0' encoding="UTF-8"?>
<!DOCTYPE martif SYSTEM "TBXBasiccoreStructV02.dtd">
<martif type="TBX-Basic-V1" xml:lang="en">
<martifHeader>
<fileDesc>
<titleStmt>
<title>termbase from MRC file</title>
</titleStmt>
<sourceDesc>
<p>generated by Convert::MRC version [version]</p>
</sourceDesc>
( run in 0.442 second using v1.01-cache-2.11-cpan-cdf2f3d4e48 )