public function testGetSynsets()
{
if (getenv('SKIP_TEST') || !is_dir(get_storage_path('corpora/wordnet'))) {
return;
}
$wn = new WordnetCorpus(get_storage_path('corpora/wordnet'));
$synset = $wn->getSynsetByOffsetAndPos(9825519, 'n');
$this->assertEquals(['automaton', 'zombi', 'zombie'], $synset->getWords());
$this->assertCount(4, $synset->getLinkedSynsets());
}
/**
* Uses file_get_contents to pull down the content from the url
* @return SimpleXMLElement
*/
public function getXmlContent()
{
if ($this->getUseCache() && file_exists(get_storage_path('cache') . $this->getCacheFileName())) {
$contents = file_get_contents(get_storage_path('cache') . $this->getCacheFileName());
} else {
$contents = file_get_contents($this->getUrl());
file_put_contents(get_storage_path('cache') . $this->getCacheFileName(), $contents);
}
return simplexml_load_string($contents);
}
public function testGetMorph()
{
if (getenv('SKIP_TEST') || !is_dir(get_storage_path('corpora/wordnet'))) {
return;
}
$this->assertEquals('play', $this->getWordnetIndex()->getMorph('playing'));
$this->assertEquals('dog', $this->getWordnetIndex()->getMorph('dogs'));
$this->assertEquals('church', $this->getWordnetIndex()->getMorph('churches'));
$this->assertEquals('aardwolf', $this->getWordnetIndex()->getMorph('aardwolves'));
$this->assertEquals('abacus', $this->getWordnetIndex()->getMorph('abaci'));
$this->assertEquals('book', $this->getWordnetIndex()->getMorph('books'));
}
public function testStanfordPos()
{
if (getenv('SKIP_TEST') || !getenv('JAVA_HOME')) {
return;
}
$document = new TokensDocument((new WhitespaceTokenizer())->tokenize($this->text));
$jarPath = get_storage_path('corpora/stanford_pos_tagger') . 'stanford-postagger-3.6.0.jar';
$modelPath = get_storage_path('corpora/stanford_pos_tagger' . DIRECTORY_SEPARATOR . "models") . "english-left3words-distsim.tagger";
$tagger = new StanfordPosTagger($jarPath, $modelPath);
$output = $tagger->tag($document->getDocumentData());
$this->assertFileExists($tagger->getTmpFilePath());
$this->assertEquals(138, filesize($tagger->getTmpFilePath()));
$this->assertEquals(['Michigan', 'NNP'], $output[15], "Did you set JAVA_HOME env variable?");
}
public function testStanfordNer()
{
if (getenv('SKIP_TEST') || !getenv('JAVA_HOME')) {
return;
}
$document = new TokensDocument((new WhitespaceTokenizer())->tokenize($this->text));
$jarPath = get_storage_path('ner') . 'stanford-ner.jar';
$classiferPath = get_storage_path('ner' . DIRECTORY_SEPARATOR . "classifiers") . "english.all.3class.distsim.crf.ser.gz";
$tagger = new StanfordNerTagger($jarPath, $classiferPath);
$output = $tagger->tag($document->getDocumentData());
$this->assertFileExists($tagger->getTmpFilePath());
$this->assertEquals(138, filesize($tagger->getTmpFilePath()));
$this->assertEquals(['Michigan', 'LOCATION'], $output[15], "Did you set JAVA_HOME env variable?");
}
/**
* Returns the path the package should be installed into
* @return string
*/
public function getInstallationPath()
{
return get_storage_path($this->getSubdir() . DIRECTORY_SEPARATOR . $this->getId());
}
/**
* Returns the path the package should be installed into
* @return string
*/
public function getInstallationPath()
{
return get_storage_path('corpora' . DIRECTORY_SEPARATOR . $this->getId());
}
