use of com.google.refine.importers.ImportingParserBase in project OpenRefine by OpenRefine.
the class ImportingUtilitiesTests method importArchive.
/**
* This tests both exploding a zip archive into it's constituent files as well as importing them all (both) and
* making sure that the recording of archive names and file names works correctly.
*
* It's kind of a lot to have in one test, but it's a sequence of steps that need to be done in order.
*
* @throws IOException
*/
@SuppressWarnings("unchecked")
@Test
public void importArchive() throws IOException {
String filename = "movies.zip";
String filepath = ClassLoader.getSystemResource(filename).getPath();
// Make a copy in our data directory where it's expected
File tmp = File.createTempFile("openrefine-test-movies", ".zip", job.getRawDataDir());
tmp.deleteOnExit();
FileUtils.copyFile(new File(filepath), tmp);
Progress dummyProgress = new Progress() {
@Override
public void setProgress(String message, int percent) {
}
@Override
public boolean isCanceled() {
return false;
}
};
ArrayNode fileRecords = ParsingUtilities.mapper.createArrayNode();
ObjectNode fileRecord = ParsingUtilities.mapper.createObjectNode();
JSONUtilities.safePut(fileRecord, "origin", "upload");
JSONUtilities.safePut(fileRecord, "declaredEncoding", "UTF-8");
JSONUtilities.safePut(fileRecord, "declaredMimeType", "application/x-zip-compressed");
JSONUtilities.safePut(fileRecord, "fileName", filename);
JSONUtilities.safePut(fileRecord, "location", tmp.getName());
assertTrue(ImportingUtilities.postProcessRetrievedFile(job.getRawDataDir(), tmp, fileRecord, fileRecords, dummyProgress));
assertEquals(fileRecords.size(), 2);
assertEquals(fileRecords.get(0).get("fileName").asText(), "movies-condensed.tsv");
assertEquals(fileRecords.get(0).get("archiveFileName").asText(), "movies.zip");
assertEquals(fileRecords.get(1).get("fileName").asText(), "movies.tsv");
ObjectNode options = ParsingUtilities.mapper.createObjectNode();
JSONUtilities.safePut(options, "includeArchiveFileName", true);
JSONUtilities.safePut(options, "includeFileSources", true);
ImportingParserBase parser = new SeparatorBasedImporter();
List<Exception> exceptions = new ArrayList<Exception>();
parser.parse(project, metadata, job, IteratorUtils.toList(fileRecords.iterator()), "tsv", -1, options, exceptions);
assertEquals(exceptions.size(), 0);
project.update();
assertEquals(project.columnModel.columns.get(0).getName(), "Archive");
assertEquals(project.rows.get(0).getCell(0).getValue(), "movies.zip");
assertEquals(project.columnModel.columns.get(1).getName(), "File");
assertEquals(project.rows.get(0).getCell(1).getValue(), "movies-condensed.tsv");
assertEquals(project.columnModel.columns.get(2).getName(), "name");
assertEquals(project.rows.get(0).getCell(2).getValue(), "Wayne's World");
// Make sure we imported both files contained in the zip file
assertEquals(project.rows.size(), 252);
ArrayNode importOptionsArray = metadata.getImportOptionMetadata();
assertEquals(importOptionsArray.size(), 2);
ObjectNode importOptions = (ObjectNode) importOptionsArray.get(0);
assertEquals(importOptions.get("archiveFileName").asText(), "movies.zip");
assertEquals(importOptions.get("fileSource").asText(), "movies-condensed.tsv");
assertTrue(importOptions.get("includeFileSources").asBoolean());
assertTrue(importOptions.get("includeArchiveFileName").asBoolean());
importOptions = (ObjectNode) importOptionsArray.get(1);
assertEquals(importOptions.get("fileSource").asText(), "movies.tsv");
assertEquals(importOptions.get("archiveFileName").asText(), "movies.zip");
}
Aggregations