public function start_process()
{
if (!$this->path_to_xml_file) {
return false;
}
if (!$this->valid_xml) {
return false;
}
$this->archive_builder = new \eol_schema\ContentArchiveBuilder(array('directory_path' => DOC_ROOT . 'temp/xml_to_archive/'));
$this->taxon_ids = array();
$this->media_ids = array();
$this->vernacular_name_ids = array();
$this->reference_ids = array();
$this->agent_ids = array();
$reader = new \XMLReader();
$file = file_get_contents($this->path_to_xml_file);
$file = iconv("UTF-8", "UTF-8//IGNORE", $file);
$reader->XML($file);
$i = 0;
while (@$reader->read()) {
if ($reader->nodeType == \XMLReader::ELEMENT && $reader->name == "taxon") {
$taxon_xml = $reader->readOuterXML();
$t = simplexml_load_string($taxon_xml, null, LIBXML_NOCDATA);
if ($t) {
$this->add_taxon_to_archive($t);
}
$i++;
if ($i % 100 == 0) {
echo "Parsed taxon {$i} : " . time_elapsed() . "\n";
}
// if($i >= 5000) break;
}
}
$this->archive_builder->finalize();
}
private function writeReaderImpl(XMLWriter $writer, XMLReader $reader)
{
switch ($reader->nodeType) {
case XMLReader::ELEMENT:
$writer->startElement($reader->name);
if ($reader->moveToFirstAttribute()) {
do {
$writer->writeAttribute($reader->name, $reader->value);
} while ($reader->moveToNextAttribute());
$reader->moveToElement();
}
if ($reader->isEmptyElement) {
$writer->endElement();
}
break;
case XMLReader::END_ELEMENT:
$writer->endElement();
break;
case XMLReader::COMMENT:
$writer->writeComment($reader->value);
break;
case XMLReader::SIGNIFICANT_WHITESPACE:
case XMLReader::TEXT:
$writer->text($reader->value);
break;
case XMLReader::PI:
$writer->writePi($reader->name, $reader->value);
break;
default:
XMLReaderNode::dump($reader);
}
}
public static function generateAcronymInfo($filename)
{
static $info;
if ($info) {
return $info;
}
$r = new \XMLReader();
if (!$r->open($filename)) {
throw new \Exception("Could not open file for accessing acronym information: {$filename}");
}
$acronyms = array();
while ($r->read()) {
if ($r->nodeType != \XMLReader::ELEMENT) {
continue;
}
if ($r->name == "term") {
$r->read();
$k = $r->value;
$acronyms[$k] = "";
} else {
if ($r->name == "simpara") {
$r->read();
$acronyms[$k] = $r->value;
}
}
}
$info = $acronyms;
return $acronyms;
}
/**
* @param FeedTypeInterface $type
* @param OutputInterface $output
*
* @return int
*/
protected function validate(FeedTypeInterface $type, OutputInterface $output)
{
$file = $this->exporter->getFeedFilename($type);
if (!file_exists($file)) {
throw new FileNotFoundException(sprintf('<error>Feed "%s" has not yet been exported</error>', $type->getName()));
}
$options = LIBXML_NOENT | LIBXML_COMPACT | LIBXML_PARSEHUGE | LIBXML_NOERROR | LIBXML_NOWARNING;
$this->reader = new \XMLReader($options);
$this->reader->open($file);
$this->reader->setParserProperty(\XMLReader::SUBST_ENTITIES, true);
// foreach ($type->getNamespaces() as $name => $location) {
// $this->reader->setSchema($location);
// }
libxml_clear_errors();
libxml_use_internal_errors(true);
libxml_disable_entity_loader(true);
$progress = new ProgressBar($output);
$progress->start();
// go through the whole thing
while ($this->reader->read()) {
if ($this->reader->nodeType === \XMLReader::ELEMENT && $this->reader->name === $type->getItemNode()) {
$progress->advance();
$this->currentItem = $this->reader->readOuterXml();
}
if ($error = libxml_get_last_error()) {
throw new \RuntimeException(sprintf('[%s %s] %s (in %s - line %d, column %d)', LIBXML_ERR_WARNING === $error->level ? 'WARNING' : 'ERROR', $error->code, trim($error->message), $error->file ? $error->file : 'n/a', $error->line, $error->column));
}
}
$progress->finish();
}
function getClioNum($appurl, $link)
{
$clio = $current = $currentA = "";
$reader = new XMLReader();
$clioQ = $appurl . '/getSingleStuff.xq?doc=' . $link . '_ead.xml§ion=summary';
$reader->open($clioQ);
while ($reader->read()) {
if ($reader->name == "unitid" && $reader->getAttribute("type") == "clio") {
if ($reader->nodeType == XMLReader::ELEMENT) {
$currentA = "clio";
} else {
if ($reader->nodeType == XMLReader::END_ELEMENT) {
$currentA = "";
}
}
}
//echo "{$reader->name} and $currentA<br />";
if ($reader->name == "#text" && $currentA == "clio") {
$clio = $reader->value;
// there can be only one
}
}
// end WHILE
$reader->close();
return $clio;
}
/**
* Parses a specific XML file
*
* @param string $inputFile File to parse
* @return \Generator
*/
public function parse($inputFile)
{
$DCNamespace = 'http://purl.org/rss/1.0/modules/content/';
$WPNamespace = 'http://wordpress.org/export/1.2/';
$reader = new \XMLReader();
$dom = new \DOMDocument('1.0', 'UTF-8');
$reader->open($inputFile);
while ($reader->read() && $reader->name !== 'item') {
}
while ($reader->name == 'item') {
$xml = simplexml_import_dom($dom->importNode($reader->expand(), true));
$wpItems = $xml->children($WPNamespace);
$content = $xml->children($DCNamespace)->encoded;
$categories = [];
$tags = [];
foreach ($xml->category as $category) {
if ('category' == $category->attributes()->domain) {
$categories[] = (string) $category;
}
if ('post_tag' == $category->attributes()->domain) {
$tags[] = (string) $category;
}
}
if ($wpItems) {
$post_type = (string) $wpItems->post_type;
$data = ['type' => $post_type, 'post_date' => new \DateTime((string) $wpItems->post_date), 'title' => (string) $xml->title, 'content' => (string) $content, 'tags' => $tags, 'categories' => $categories];
(yield $data);
}
$reader->next('item');
}
}
/**
* @throws RuntimeException
* @return array of arrays.
* array( 'dumpKey' => array( 'match1', 'match2' ) )
*/
public function scan()
{
$openSuccess = $this->reader->open($this->dumpLocation);
if (!$openSuccess) {
throw new RuntimeException('Failed to open XML: ' . $this->dumpLocation);
}
$result = array();
foreach ($this->query as $queryKey => $query) {
$result[$queryKey] = array();
// Make sure keys are returned even if empty
}
while ($this->reader->read() && $this->reader->name !== 'page') {
}
while ($this->reader->name === 'page') {
$element = new SimpleXMLElement($this->reader->readOuterXML());
$page = $this->getPageFromElement($element);
foreach ($this->query as $queryKey => $query) {
$match = $this->matchPage($page, $query);
if ($match) {
//TODO allow the user to choose what to return
$result[$queryKey][] = $page->getTitle()->getTitle();
}
}
$this->reader->next('page');
}
$this->reader->close();
return $result;
}
public function parseErrorResponse($statusCode, $content, MnsException $exception = NULL)
{
$this->succeed = FALSE;
$xmlReader = new \XMLReader();
try {
$xmlReader->XML($content);
$result = XMLParser::parseNormalError($xmlReader);
if ($result['Code'] == Constants::TOPIC_NOT_EXIST) {
throw new TopicNotExistException($statusCode, $result['Message'], $exception, $result['Code'], $result['RequestId'], $result['HostId']);
}
if ($result['Code'] == Constants::INVALID_ARGUMENT) {
throw new InvalidArgumentException($statusCode, $result['Message'], $exception, $result['Code'], $result['RequestId'], $result['HostId']);
}
if ($result['Code'] == Constants::MALFORMED_XML) {
throw new MalformedXMLException($statusCode, $result['Message'], $exception, $result['Code'], $result['RequestId'], $result['HostId']);
}
throw new MnsException($statusCode, $result['Message'], $exception, $result['Code'], $result['RequestId'], $result['HostId']);
} catch (\Exception $e) {
if ($exception != NULL) {
throw $exception;
} elseif ($e instanceof MnsException) {
throw $e;
} else {
throw new MnsException($statusCode, $e->getMessage());
}
} catch (\Throwable $t) {
throw new MnsException($statusCode, $t->getMessage());
}
}
protected function readNext(XMLReader $reader)
{
do {
if ($this->isStartElement('ancode')) {
$pos_id = (int) $reader->getAttribute('pos_id');
if (!isset($this->poses[$pos_id])) {
throw new Exception("Invalid pos id '{$pos_id}' found in ancode '" . $reader->getAttribute('id') . "'");
}
$pos = $this->poses[$pos_id];
$ancode = new phpMorphy_Dict_Ancode($reader->getAttribute('id'), $pos['name'], $pos['is_predict']);
while ($this->read()) {
if ($this->isStartElement('grammem')) {
$grammem_id = (int) $reader->getAttribute('id');
if (!isset($this->grammems[$grammem_id])) {
throw new Exception("Invalid grammem id '{$grammem_id}' found in ancode '" . $ancode->getId() . "'");
}
$ancode->addGrammem($this->grammems[$grammem_id]['name']);
} elseif ($this->isEndElement('ancode')) {
break;
}
}
unset($this->current);
$this->current = $ancode;
break;
}
} while ($this->read());
}
public function parseErrorResponse($statusCode, $content, MnsException $exception = NULL)
{
$this->succeed = FALSE;
$xmlReader = new \XMLReader();
try {
$xmlReader->XML($content);
while ($xmlReader->read()) {
if ($xmlReader->nodeType == \XMLReader::ELEMENT) {
switch ($xmlReader->name) {
case Constants::ERROR:
$this->parseNormalErrorResponse($xmlReader);
break;
default:
// case Constants::Messages
$this->parseBatchSendErrorResponse($xmlReader);
break;
}
}
}
} catch (\Exception $e) {
if ($exception != NULL) {
throw $exception;
} elseif ($e instanceof MnsException) {
throw $e;
} else {
throw new MnsException($statusCode, $e->getMessage());
}
} catch (\Throwable $t) {
throw new MnsException($statusCode, $t->getMessage());
}
}
public function parseErrorResponse($statusCode, $content, MnsException $exception = NULL)
{
$this->succeed = FALSE;
$xmlReader = new \XMLReader();
try {
$xmlReader->XML($content);
$result = XMLParser::parseNormalError($xmlReader);
if ($result['Code'] == Constants::QUEUE_NOT_EXIST) {
throw new QueueNotExistException($statusCode, $result['Message'], $exception, $result['Code'], $result['RequestId'], $result['HostId']);
}
if ($result['Code'] == Constants::MESSAGE_NOT_EXIST) {
throw new MessageNotExistException($statusCode, $result['Message'], $exception, $result['Code'], $result['RequestId'], $result['HostId']);
}
throw new MnsException($statusCode, $result['Message'], $exception, $result['Code'], $result['RequestId'], $result['HostId']);
} catch (\Exception $e) {
if ($exception != NULL) {
throw $exception;
} elseif ($e instanceof MnsException) {
throw $e;
} else {
throw new MnsException($statusCode, $e->getMessage());
}
} catch (\Throwable $t) {
throw new MnsException($statusCode, $t->getMessage());
}
}
public static function &buildTree($source, $mode = XMLDocument::BUILD_MODE_FROM_FILE, $ns = NULL)
{
if ($mode == XMLDocument::BUILD_MODE_FROM_FILE) {
if (($content = Filesystem::getFileContent($source)) === NULL) {
return NULL;
}
} else {
if ($source == "" || $source == NULL) {
return new xmlTree();
}
$content = $ns == NULL ? "<ROOT>" . $source . "</ROOT>" : "<ROOT xmlns:{$ns}=\".\">" . $source . "</ROOT>";
}
/*$content = ereg_replace( "&", "&", $content );
$content = ereg_replace( "&", "&", $content );*/
//echo $content;
$content = preg_replace("/&/", "&", $content);
$content = preg_replace("/&/", "&", $content);
$content = iconv("windows-1251", "UTF-8", $content);
$reader = new XMLReader();
if ($reader->XML($content)) {
$_docTree = NULL;
$_docTree = new xmlTree();
self::_appendChilds($_docTree->getCurrent(), $reader, 0);
$reader = NULL;
return $_docTree;
} else {
self::raiseException(ERR_XML_INVALID_XML, $content);
return NULL;
}
}
/**
* Method to load a URI into the feed reader for parsing.
*
* @param string $uri The URI of the feed to load. Idn uris must be passed already converted to punycode.
*
* @return JFeedReader
*
* @since 12.3
* @throws InvalidArgumentException
* @throws RuntimeException
*/
public function getFeed($uri)
{
// Create the XMLReader object.
$reader = new XMLReader();
// Open the URI within the stream reader.
if (!@$reader->open($uri, null, LIBXML_NOERROR | LIBXML_ERR_NONE | LIBXML_NOWARNING)) {
// Retry with JHttpFactory that allow using CURL and Sockets as alternative method when available
// Adding a valid user agent string, otherwise some feed-servers returning an error
$options = new \joomla\Registry\Registry();
$options->set('userAgent', 'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:41.0) Gecko/20100101 Firefox/41.0');
$connector = JHttpFactory::getHttp($options);
$feed = $connector->get($uri);
if ($feed->code != 200) {
throw new RuntimeException('Unable to open the feed.');
}
// Set the value to the XMLReader parser
if (!$reader->xml($feed->body, null, LIBXML_NOERROR | LIBXML_ERR_NONE | LIBXML_NOWARNING)) {
throw new RuntimeException('Unable to parse the feed.');
}
}
try {
// Skip ahead to the root node.
while ($reader->read()) {
if ($reader->nodeType == XMLReader::ELEMENT) {
break;
}
}
} catch (Exception $e) {
throw new RuntimeException('Error reading feed.', $e->getCode(), $e);
}
// Setup the appopriate feed parser for the feed.
$parser = $this->_fetchFeedParser($reader->name, $reader);
return $parser->parse();
}
private static function testXml()
{
$xml = new \XMLReader();
$xml->XML(self::$TestXml);
$xmlarray = xmlWithArray::xmlToarray($xml);
return $xmlarray;
}
protected function parseEntrypoints(\XMLReader $xml, InfosAbstract $object)
{
$property = $xml->name;
while ($xml->read()) {
if ($xml->nodeType == \XMLReader::END_ELEMENT && 'entrypoints' == $xml->name) {
break;
}
if ($xml->nodeType == \XMLReader::ELEMENT) {
$id = $config = '';
$type = 'classic';
while ($xml->moveToNextAttribute()) {
if ($xml->name == 'file') {
$id = $xml->value;
} else {
if ($xml->name == 'config') {
$config = $xml->value;
} else {
if ($xml->name == 'type') {
$type = $xml->value;
}
}
}
}
if ($id) {
if (strpos($id, '.php') === false) {
$id .= '.php';
}
$object->entrypoints[$id] = array('config' => $config, 'file' => $id, 'type' => $type);
}
}
}
}
/**
* Method to load a URI into the feed reader for parsing.
*
* @param string $uri The URI of the feed to load. Idn uris must be passed already converted to punycode.
*
* @return JFeedReader
*
* @since 12.3
* @throws InvalidArgumentException
* @throws RuntimeException
*/
public function getFeed($uri)
{
// Create the XMLReader object.
$reader = new XMLReader();
// Open the URI within the stream reader.
if (!@$reader->open($uri, null, LIBXML_NOERROR | LIBXML_ERR_NONE | LIBXML_NOWARNING)) {
// If allow_url_fopen is enabled
if (ini_get('allow_url_fopen')) {
// This is an error
throw new RuntimeException('Unable to open the feed.');
} else {
// Retry with JHttpFactory that allow using CURL and Sockets as alternative method when available
$connector = JHttpFactory::getHttp();
$feed = $connector->get($uri);
// Set the value to the XMLReader parser
if (!$reader->xml($feed->body, null, LIBXML_NOERROR | LIBXML_ERR_NONE | LIBXML_NOWARNING)) {
throw new RuntimeException('Unable to parse the feed.');
}
}
}
try {
// Skip ahead to the root node.
while ($reader->read()) {
if ($reader->nodeType == XMLReader::ELEMENT) {
break;
}
}
} catch (Exception $e) {
throw new RuntimeException('Error reading feed.');
}
// Setup the appopriate feed parser for the feed.
$parser = $this->_fetchFeedParser($reader->name, $reader);
return $parser->parse();
}
public function actionFias()
{
$file = 'AS_ADDROBJ_20160609_c5080ba4-9f46-4b6e-aecc-72a630730b3a.XML';
$interestingNodes = array('AOGUID');
$xmlObject = new \XMLReader();
$xmlObject->open($file);
header('Content-Type: text/html; charset=utf-8');
$i = 0;
while ($xmlObject->read()) {
if ($xmlObject->name == 'Object') {
if ($xmlObject->getAttribute('IFNSFL') == '8603') {
// if (($xmlObject->getAttribute('PARENTGUID') == '0bf0f4ed-13f8-446e-82f6-325498808076' && $xmlObject->getAttribute('AOLEVEL') == '7') || $xmlObject->getAttribute('AOGUID') == '0bf0f4ed-13f8-446e-82f6-325498808076') {
$fias = new Fias();
$fias->AOGUID = $xmlObject->getAttribute('AOGUID');
$fias->OFFNAME = $xmlObject->getAttribute('OFFNAME');
$fias->SHORTNAME = $xmlObject->getAttribute('SHORTNAME');
$fias->IFNSFL = $xmlObject->getAttribute('IFNSFL');
$fias->AOLEVEL = $xmlObject->getAttribute('AOLEVEL');
$fias->PARENTGUID = $xmlObject->getAttribute('PARENTGUID');
if ($fias->validate()) {
$fias->save();
} else {
var_dump($fias->attributes);
var_dump($fias->getErrors());
}
// $i++;
}
}
}
echo 'ok';
$xmlObject->close();
}
function eol_xml_stats()
{
$path = "http://localhost/eol_php_code/applications/content_server/resources/218.xml";
$reader = new \XMLReader();
$reader->open($path);
$i = 0;
$dist_count = 0;
$taxa_count = 0;
while (@$reader->read()) {
if ($reader->nodeType == \XMLReader::ELEMENT && $reader->name == "taxon") {
$string = $reader->readOuterXML();
$string = str_ireplace("dc:", "dc_", $string);
$string = str_ireplace("dwc:", "dwc_", $string);
if ($xml = simplexml_load_string($string)) {
$taxa_with_dist = false;
$taxon_id = (string) $xml->dc_identifier;
print "[{$taxon_id}]";
foreach ($xml->dataObject as $o) {
if (@$o->subject == "http://rs.tdwg.org/ontology/voc/SPMInfoItems#Distribution") {
$dist_count++;
$taxa_with_dist = true;
}
}
if ($taxa_with_dist) {
$taxa_count++;
}
}
}
}
print "\n\n";
print "\n distribution: [{$dist_count}]";
print "\n taxa with dist: [" . $taxa_count . "]";
print "\n\n";
}
/**
* Method to load a URI into the feed reader for parsing.
*
* @param string $uri The URI of the feed to load.
*
* @return JFeedReader
*
* @since 3.0
* @throws InvalidArgumentException
* @throws RuntimeException
*/
public function getFeed($uri)
{
// Make sure the file exists.
try {
$this->http->get($uri);
} catch (RunTimeException $e) {
throw new InvalidArgumentException('The file ' . $uri . ' does not exist.');
}
// Create the XMLReader object.
$reader = new XMLReader();
// Open the URI within the stream reader.
if (!@$reader->open($uri, null, LIBXML_NOERROR | LIBXML_ERR_NONE | LIBXML_NOWARNING)) {
throw new RuntimeException('Unable to open the feed.');
}
try {
// Skip ahead to the root node.
while ($reader->read() && $reader->nodeType !== XMLReader::ELEMENT) {
}
} catch (Exception $e) {
throw new RuntimeException('Error reading feed.');
}
// Setup the appopriate feed parser for the feed.
$parser = $this->_fetchFeedParser($reader->name, $reader);
return $parser->parse();
}
public static function generateAcronymInfo($filename)
{
static $info;
if ($info) {
return $info;
}
if (!is_file($filename)) {
v("Can't find acronym file (%s), skipping", $filename, E_USER_WARNING);
return array();
}
$r = new \XMLReader();
if (!$r->open($filename)) {
v("Could not open file for accessing acronym information (%s)", $filename, E_USER_ERROR);
}
$acronyms = array();
while ($r->read()) {
if ($r->nodeType != \XMLReader::ELEMENT) {
continue;
}
if ($r->name == "term") {
$r->read();
$k = $r->value;
$acronyms[$k] = "";
} else {
if ($r->name == "simpara") {
$r->read();
$acronyms[$k] = $r->value;
}
}
}
$info = $acronyms;
return $acronyms;
}
function isXml($filename)
{
$xml = new XMLReader();
$xml->open($filename);
$xml->setParserProperty(XMLReader::VALIDATE, true);
return $xml->isValid();
}
public function transferXmlToDb()
{
$reader = new \XMLReader();
if (!$reader->open(Yii::getAlias('@webroot') . '/import/' . $this->filename, 'utf-8')) {
throw new Exception('XML-файл не удалось найти.');
}
return $this->parseAndSaveData($reader);
}
private function createReader()
{
$reader = new XMLReader();
if (false === $reader->open($this->xml_file)) {
throw new Exception("Can`t open '{$this->xml_file}' xml file");
}
return $reader;
}
/**
* Проверка по схеме
*/
public function validate($schemaPath)
{
$xr = new XMLReader();
$xr->XML($this->toXmlStr());
$xr->setSchema($schemaPath);
while ($xr->read()) {
}
}
/**
* Test get element returns null
*/
public function testGetElementReturnsNull()
{
$filename = __DIR__ . '/../_files/documents/reader.docx.zip';
$object = new XMLReader();
$object->getDomFromZip($filename, '[Content_Types].xml');
$element = $object->getElements('*')->item(0);
$this->assertNull($object->getElement('yadayadaya', $element));
}
public function filter($value)
{
$this->_initReaderWriter();
$this->_reader->XML($value);
$this->_doXmlTrim();
$this->_writer->endDocument();
return $this->_writer->outputMemory();
}
public function rewind()
{
if ($this->reader->nodeType !== XMLReader::NONE) {
throw new BadMethodCallException('Reader can not be rewound');
}
$this->index = 0;
$this->valid = $this->reader->read();
}
protected function parse()
{
$depth = 0;
$elements = array();
$elements_[$depth] =& $elements;
while ($this->xml->read()) {
switch ($this->xml->nodeType) {
case XMLReader::END_ELEMENT:
if ($this->xml->depth - 1 < $depth) {
$elements =& $elements_[$depth];
$element =& $elements[sizeof($elements) - 1];
$depth = $this->xml->depth - 1;
}
break;
case XMLReader::ATTRIBUTE:
# Read does not go through attributes :(
break;
case XMLReader::ELEMENT:
if (strlen($this->xml->name) == 0) {
continue;
}
if ($this->xml->depth > $depth) {
$depth = $this->xml->depth;
$elements_[$depth] =& $elements;
$elements =& $element['elements'];
}
$elements[] = array('tag' => $this->xml->name);
# Working Element
$element =& $elements[sizeof($elements) - 1];
# Attributes
if ($this->xml->hasAttributes) {
$this->xml->moveToFirstAttribute();
$element['attributes'] = array();
$element['attributes'][$this->xml->name] = $this->xml->value;
while ($this->xml->moveToNextAttribute()) {
$element['attributes'][$this->xml->name] = $this->xml->value;
}
}
if ($this->xml->isEmptyElement) {
if ($this->xml->depth - 1 < $depth) {
$elements =& $elements_[$depth];
$element =& $elements[sizeof($elements) - 1];
$depth = $this->xml->depth - 1;
}
}
break;
case XMLReader::TEXT:
case XMLReader::CDATA:
if (!isset($element['value'])) {
$element['value'] = $this->xml->value;
} else {
$element['value'] .= $this->xml->value;
}
break;
}
}
$this->elements = $elements;
}
public function create()
{
$database_logs = Database_Logs::getInstance();
Database_SQLite::exec($this->db, "PRAGMA temp_store = MEMORY;");
Database_SQLite::exec($this->db, "PRAGMA synchronous = OFF;");
Database_SQLite::exec($this->db, "PRAGMA journal_mode = OFF;");
$sql = <<<'EOD'
CREATE TABLE IF NOT EXISTS morphhb (
book integer,
chapter integer,
verse integer,
hebrew text
);
EOD;
Database_SQLite::exec($this->db, $sql);
$books = array("Gen", "Exod", "Lev", "Num", "Deut", "Josh", "Judg", "Ruth", "1Sam", "2Sam", "1Kgs", "2Kgs", "1Chr", "2Chr", "Ezra", "Neh", "Esth", "Job", "Ps", "Prov", "Eccl", "Song", "Isa", "Jer", "Lam", "Ezek", "Dan", "Hos", "Joel", "Amos", "Obad", "Jonah", "Mic", "Nah", "Hab", "Zeph", "Hag", "Zech", "Mal");
foreach ($books as $book => $osis) {
$book++;
$database_logs->log("Importing Hebrew data for {$book} {$osis}");
$xml = new XMLReader();
$xml->open("../morphhb/{$osis}.xml");
$chapter = 0;
$verse = 0;
$word = false;
$hebrew = "";
while ($xml->read()) {
$nodeType = $xml->nodeType;
$name = $xml->name;
if ($nodeType == XMLReader::ELEMENT) {
if ($name == "verse") {
$osisID = $xml->getAttribute("osisID");
$osisID = explode(".", $osisID);
$chapter = intval($osisID[1]);
$verse = intval($osisID[2]);
}
if ($name == "w") {
$word = true;
}
}
if ($nodeType == XMLReader::TEXT) {
if ($word) {
$hebrew = $xml->value;
$hebrew = trim($hebrew);
$hebrew = str_replace("/", "", $hebrew);
$hebrew = str_replace("'", "''", $hebrew);
$sql = "INSERT INTO morphhb (book, chapter, verse, hebrew) VALUES ({$book}, {$chapter}, {$verse}, '{$hebrew}');";
Database_SQLite::exec($this->db, $sql);
}
}
if ($nodeType == XMLReader::END_ELEMENT) {
if ($name == "w") {
$word = false;
}
}
}
$xml->close();
}
}
public function testParseXmlFromHttpStream()
{
$stream = fopen('http://www.splunk.com/', 'rb');
$streamUri = Splunk_StreamStream::createUriForStream($stream);
$xmlReader = new XMLReader();
$xmlReader->open($streamUri);
}
