This repository has been archived on 2023-01-23. You can view files and clone it, but cannot push or open issues or pull requests.
importer-parsers-archive-2022/parsers/FDH-Import-By-Dir-Structure.php

254 lines
9.3 KiB
PHP
Raw Normal View History

2023-01-23 15:21:35 +01:00
<?PHP
/**
* Parser for XML generated through CSVXML.
*
* @author Joshua Ramon Enslin <joshua@museum-digital.de>
* @author Stefan Rohde-Enslin <s.rohde-enslin@museum-digital.de>
* @link https://imports.museum-digital.org/importer/parsers/csvxml.php
*/
declare(strict_types = 1);
/**
* Parses a folder name to object group and inventory number.
*
* @param string $folder_path Folder path.
*
* @return array{0: array<string>, 1: string}
*/
function parseFolderToObjGroupInvNo(string $folder_path):array {
$parts = explode('/', $folder_path);
$invNo = str_replace('jpg ', '', end($parts));
$parts = array_diff($parts, [$invNo]);
$objGroups = [];
foreach ($parts as $part) {
$objGroups[] = str_replace('jpg ', '', $part);
}
return [$objGroups, $invNo];
}
/**
* Recurses down a folder directory to list all folders with JPG files in them.
*
* @param string $folder_path Folder path.
*
* @return array<string>
*/
function getFoldersWithJpgs(string $folder_path):array {
$filesFolders = MD_STD::scandir($folder_path);
$addToList = false;
$output = [];
foreach ($filesFolders as $fileOrFolderName) {
$fileOrFolder = $folder_path . '/' . $fileOrFolderName;
if (is_dir($fileOrFolder)) {
$output = array_merge($output, getFoldersWithJpgs($fileOrFolder));
continue;
}
// If is_file
if (in_array(mime_content_type($fileOrFolder), ['image/jpeg'], true)) {
$addToList = true;
}
}
if ($addToList === true) {
$output[] = $folder_path;
}
return $output;
}
/**
* Parse function.
*
* @param array<mixed> $version Instance to import into.
* @param integer $institution_id Institution to import to.
* @param non-empty-string $XMLFolder Folder of the XML files to import.
* @param string $dataFolder Data folder.
* @param integer $sammlung_id Collection ID. Optional.
* @param boolean $visibility Import objects to be directly visible?.
* @param boolean $insertOnly If set to true, only new objects are added,
* old are not updated.
*
* @return void
*/
function parseImportXML(array $version, int $institution_id, string $XMLFolder, string $dataFolder = "", int $sammlung_id = 0, bool $visibility = false, bool $insertOnly = false) {
if (!is_dir(MD_IMPORTER_CONF::$import_dir_xml . "{$XMLFolder}")) throw new MDFileDoesNotExist("The folder to import from ($XMLFolder) does not exist.");
if (empty($dataFolder)) {
throw new Exception("You need to select a data folder to run image-only imports");
}
else $importImages = true;
// Set up writers
$outputHandler = new MDOutputHandler;
$outputHandler->setVerbosity(2);
$objectWriter = new MDObjectWriter($version['mainDB'], $version['nodaDB'], $version['link'], $version['filepath'], $version['dataFolderLink']);
/*
$objectWriter->disableUpdateBaseData = true;
$objectWriter->disableImportAdditionalData = true;
$objectWriter->disableImportImagesResources = true;
$objectWriter->disableImportTags = true;
$objectWriter->disableImportLiterature = true;
$objectWriter->disableImportHyperlinks = true;
$objectWriter->disableImportSeries = true;
$objectWriter->disableImportCollections = true;
$objectWriter->disableImportObjectRecords = true;
$objectWriter->disableImportTranscriptions = true;
$objectWriter->disableImportMarkings = true;
$objectWriter->disableImportExhibitions = true;
$objectWriter->disableImportReception = true;
*/
$i = 0;
$startAtCounter = 0;
// Get folders with JPGS
$filesByInvNo = [];
$foldersToSkip = 0;
$foldersSkipped = 0;
foreach (MD_STD::scandir(MD_IMPORTER_CONF::$import_dir_files . $dataFolder) as $tFolder) {
if ($foldersSkipped < $foldersToSkip) {
echo 'Skipped folder ' . $tFolder . PHP_EOL;
++$foldersSkipped;
continue;
}
$foldersToImport = getFoldersWithJpgs(MD_IMPORTER_CONF::$import_dir_files . $dataFolder . '/' . $tFolder);
foreach ($foldersToImport as $folderToImport) {
/*
$folderName = str_replace(MD_IMPORTER_CONF::$import_dir_files . $dataFolder . '/', "", $folderToImport);
echo $folderName . PHP_EOL;
list($objectGroups, $invNo) = parseFolderToObjGroupInvNo($folderName);
print_r($objectGroups);
print_r($invNo);
*/
foreach (MD_STD::scandir($folderToImport) as $tFile) {
if (!in_array(mime_content_type($folderToImport . '/' . $tFile), ['image/jpeg'], true)) {
continue;
}
$invNo = explode('_', $tFile)[0];
if (empty($filesByInvNo[$invNo])) $filesByInvNo[$invNo] = [];
$filesByInvNo[$invNo][] = $folderToImport . '/' . $tFile;
}
}
}
$tagWriter = new MDTagWriter($version['nodaDB']);
$seriesWriter = new MDSeriesWriter($version['mainDB']);
$literatureWriter = new MDLiteratureWriter($version['mainDB']);
foreach ($filesByInvNo as $invNo => $imageFiles) {
if (empty($invNo)) continue;
++$i;
if ($i > $startAtCounter || $i < 20) {
continue;
}
$outputHandler->toLog("Starting to process file #{$i}", 2);
$object = new MDObject($version['mainDB'], $version['nodaDB'], $version['language'], $institution_id, $invNo, "Handschrift", $invNo, "Handschrift Friedrich von Hardenbergs.", $outputHandler);
$images = [];
foreach ($imageFiles as $cur_img) {
// Image title is the first line after the file name. Everything after is the description.
$image_title = pathinfo($cur_img, PATHINFO_FILENAME);
$image = new MDImage($version['mainDB'], $image_title, $cur_img);
# $image->set_image_beschreibung($img_description);
/*
if (isset($objectData["image_rights" . $suffix])) $image->set_image_rights($objectData["image_rights" . $suffix]);
if (isset($objectData["image_owner" . $suffix])) $image->set_image_owner($objectData["image_owner" . $suffix]);
if (isset($objectData["image_creator" . $suffix])) $image->set_image_creator($objectData["image_creator" . $suffix]);
*/
$image->set_visible(true);
$images[] = $image;
$outputHandler->toLog("Added image $image_title", 2);
usleep(1800);
}
if (!empty($images)) $images[0]->set_main_image(true);
foreach ($images as $image) $object->appendImage($image);
while ($version['mainDB']->more_results()) $version['mainDB']->next_result();
while ($version['nodaDB']->more_results()) $version['nodaDB']->next_result();
$object->appendTagByID(576);
// Get object groups to link
$folderName = str_replace(MD_IMPORTER_CONF::$import_dir_files . $dataFolder . '/', "", pathinfo($imageFiles[0], PATHINFO_DIRNAME));
list($objectGroups, $inventNo) = parseFolderToObjGroupInvNo($folderName);
foreach ($objectGroups as $objectGroup) {
$object->appendSeriesByName($objectGroup, $objectGroup, $seriesWriter, ["serie_weitergabe" => "100"]);
if (strpos($objectGroup, 'Kiste') !== false) {
$object->set_string("standort_eigentlich", $objectGroup);
}
}
if ($sammlung_id !== 0) {
$object->appendCollectionByID($sammlung_id);
}
$event = new MDEvent($version['mainDB'], $version['nodaDB'], $version['language'], 7, $outputHandler);
$event->set_persinst_id("Georg Philipp Friedrich von Hardenberg", "1772", "1801");
$event->set_ereignis_persinst_sicher(true);
$object->appendEvent($event);
// Get literature link
$litAlreadyLinked = [];
foreach ($imageFiles as $imageFile) {
$imageFile = trim($imageFile, "_ &%");
$imgFileEnd = explode('_', str_replace("_000", '', pathinfo($imageFile, PATHINFO_FILENAME)));
if (($litLink = end($imgFileEnd)) && !in_array($litLink, $litAlreadyLinked, true)) {
$litAlreadyLinked[] = $litLink;
if (substr($litLink, 0, 3) === 'HKA') {
if (($litNameEnd = strpos($litLink, ',')) !== false) {
$litName = substr($litLink, 0, $litNameEnd);
$litInLit = substr($litLink, $litNameEnd + 1);
$object->appendLiteratureByName($litName, "", "", "", $litInLit, $literatureWriter);
$object->appendSeriesByName($litName, $litName, $seriesWriter, ["serie_weitergabe" => "100"]);
$object->appendSeriesByName($litName . ' ' . $litInLit, $litName . ' ' . $litInLit, $seriesWriter, ["serie_weitergabe" => "100"]);
}
else {
$object->appendLiteratureByName($litLink, "", "", "", "", $literatureWriter);
}
}
}
}
$object->set_objekt_publik($visibility);
$outputHandler->toLog("Importing file #{$i}, inv. no: $invNo", 2);
$newObjectID = $objectWriter->writeObject($object, true, $insertOnly, $outputHandler);
usleep(2000);
}
}