#427

Committed 12 May 2025 02:44PM UTC coverage: 89.284% (-0.9%) from 90.169%

Build # #427

Build Type

Pull #258

github

Committed by

web-flow

Commit Message

Merge e2a4bf3f1 into 810d1995c

Pull Request Pull Request #258: Support .ELN-style crates in all zip readers and writers

Run Details

223 of 244 new or added lines in 14 files covered. (91.39%)

26 existing lines in 5 files now uncovered.

1983 of 2221 relevant lines covered (89.28%)

0.89 hits per line

Source File
Press 'n' to go to next uncovered line, 'b' for previous

95.0

/src/main/java/edu/kit/datamanager/ro_crate/reader/ZipStrategy.java

package edu.kit.datamanager.ro_crate.reader;

import com.fasterxml.jackson.databind.ObjectMapper;
import com.fasterxml.jackson.databind.node.ObjectNode;
import edu.kit.datamanager.ro_crate.entities.contextual.JsonDescriptor;
import edu.kit.datamanager.ro_crate.objectmapper.MyObjectMapper;
import net.lingala.zip4j.ZipFile;
import org.apache.commons.io.FileUtils;
import org.apache.commons.io.filefilter.FileFilterUtils;

import java.io.File;
import java.io.IOException;
import java.nio.file.Path;
import java.util.UUID;

/**
 * A ReaderStrategy implementation which reads from ZipFiles.
 * <p>
 * May be used as a dependency for CrateReader. It will unzip
 * the ZipFile in a path relative to the directory this application runs in.
 * By default, it will be `./.tmp/ro-crate-java/zipReader/$UUID/`.
 * <p>
 * NOTE: The resulting crate may refer to these temporary files. Therefore,
 * these files are only being deleted before the JVM exits. If you need to free
 * space because your application is long-running or creates a lot of
 * crates, you may use the getters to retrieve information which will help
 * you to clean up manually. Keep in mind that crates may refer to this
 * folder after extraction. Use RoCrateWriter to export it so some
 * persistent location and possibly read it from there, if required. Or use
 * the ZipWriter to write it back to its source.
 */
public class ZipStrategy implements GenericReaderStrategy<String> {

  protected final String ID = UUID.randomUUID().toString();
  protected Path temporaryFolder = Path.of(String.format("./.tmp/ro-crate-java/zipReader/%s/", ID));
  protected boolean isExtracted = false;

  /**
   * Crates a ZipReader with the default configuration as described in the class documentation.
   */
  public ZipStrategy() {}

  /**
   * Creates a ZipReader which will extract the contents temporary
   * to the given location instead of the default location.
   *
   * @param folderPath            the custom directory to extract
   *                              content to for temporary access.
   * @param shallAddUuidSubfolder if true, the reader will extract
   *                              into subdirectories of the given
   *                              directory. These subdirectories
   *                              will have UUIDs as their names.
   */
  public ZipStrategy(Path folderPath, boolean shallAddUuidSubfolder) {
    if (shallAddUuidSubfolder) {
      this.temporaryFolder = folderPath.resolve(ID);
    } else {
      this.temporaryFolder = folderPath;
    }
  }

  /**
   * @return the identifier which may be used as the name for a subfolder in the temporary directory.
   */
  public String getID() {
    return ID;
  }

  /**
   * @return the folder (considered temporary) where the zipped crate will be or has been extracted to.
   */
  public Path getTemporaryFolder() {
    return temporaryFolder;
  }

  /**
   * @return whether the crate has already been extracted into the temporary folder.
   */
  public boolean isExtracted() {
    return isExtracted;
  }

  private void readCrate(String location) throws IOException {
    File folder = temporaryFolder.toFile();
    // ensure the directory is clean
    if (folder.isDirectory()) {
      FileUtils.cleanDirectory(folder);
    } else if (folder.isFile()) {
      FileUtils.delete(folder);
    }
    // extract
    try (ZipFile zf = new ZipFile(location)) {
      zf.extractAll(temporaryFolder.toAbsolutePath().toString());
      this.isExtracted = true;
    }
    // register deletion on exit
    FileUtils.forceDeleteOnExit(folder);
  }

  @Override
  public ObjectNode readMetadataJson(String location) throws IOException {
    if (!isExtracted) {
      this.readCrate(location);
    }

    ObjectMapper objectMapper = MyObjectMapper.getMapper();
    File jsonMetadata = this.temporaryFolder.resolve(JsonDescriptor.ID).toFile();
    if (!jsonMetadata.isFile()) {
      // Try to find the metadata file in subdirectories
      File firstSubdir = FileUtils.listFilesAndDirs(
            temporaryFolder.toFile(),
            FileFilterUtils.directoryFileFilter(),
            null // not recursive
        )
        .stream()
        .limit(50)
        .filter(file -> file.toPath().toAbsolutePath().resolve(JsonDescriptor.ID).toFile().isFile())
        .findFirst()
        .orElseThrow(() -> new IllegalStateException("No %s found in zip file".formatted(JsonDescriptor.ID)));
      jsonMetadata = firstSubdir.toPath().resolve(JsonDescriptor.ID).toFile();
    }

    return objectMapper.readTree(jsonMetadata).deepCopy();
  }

  @Override
  public File readContent(String location) throws IOException {
    if (!isExtracted) {
      this.readCrate(location);
    }
    return temporaryFolder.toFile();
  }
}

1	package edu.kit.datamanager.ro_crate.reader;
2
3	import com.fasterxml.jackson.databind.ObjectMapper;
4	import com.fasterxml.jackson.databind.node.ObjectNode;
5	import edu.kit.datamanager.ro_crate.entities.contextual.JsonDescriptor;
6	import edu.kit.datamanager.ro_crate.objectmapper.MyObjectMapper;
7	import net.lingala.zip4j.ZipFile;
8	import org.apache.commons.io.FileUtils;
9	import org.apache.commons.io.filefilter.FileFilterUtils;
10
11	import java.io.File;
12	import java.io.IOException;
13	import java.nio.file.Path;
14	import java.util.UUID;
15
16	/**
17	* A ReaderStrategy implementation which reads from ZipFiles.
18	* <p>
19	* May be used as a dependency for CrateReader. It will unzip
20	* the ZipFile in a path relative to the directory this application runs in.
21	* By default, it will be `./.tmp/ro-crate-java/zipReader/$UUID/`.
22	* <p>
23	* NOTE: The resulting crate may refer to these temporary files. Therefore,
24	* these files are only being deleted before the JVM exits. If you need to free
25	* space because your application is long-running or creates a lot of
26	* crates, you may use the getters to retrieve information which will help
27	* you to clean up manually. Keep in mind that crates may refer to this
28	* folder after extraction. Use RoCrateWriter to export it so some
29	* persistent location and possibly read it from there, if required. Or use
30	* the ZipWriter to write it back to its source.
31	*/
32	public class ZipStrategy implements GenericReaderStrategy<String> {
33
34	protected final String ID = UUID.randomUUID().toString();	1✔
35	protected Path temporaryFolder = Path.of(String.format("./.tmp/ro-crate-java/zipReader/%s/", ID));	1✔
36	protected boolean isExtracted = false;	1✔
37
38	/**
39	* Crates a ZipReader with the default configuration as described in the class documentation.
40	*/
41	public ZipStrategy() {}	1✔
42
43	/**
44	* Creates a ZipReader which will extract the contents temporary
45	* to the given location instead of the default location.
46	*
47	* @param folderPath the custom directory to extract
48	* content to for temporary access.
49	* @param shallAddUuidSubfolder if true, the reader will extract
50	* into subdirectories of the given
51	* directory. These subdirectories
52	* will have UUIDs as their names.
53	*/
54	public ZipStrategy(Path folderPath, boolean shallAddUuidSubfolder) {	1✔
55	if (shallAddUuidSubfolder) {	1✔
56	this.temporaryFolder = folderPath.resolve(ID);	1✔
57	} else {
58	this.temporaryFolder = folderPath;	1✔
59	}
60	}	1✔
61
62	/**
63	* @return the identifier which may be used as the name for a subfolder in the temporary directory.
64	*/
65	public String getID() {
66	return ID;	1✔
67	}
68
69	/**
70	* @return the folder (considered temporary) where the zipped crate will be or has been extracted to.
71	*/
72	public Path getTemporaryFolder() {
73	return temporaryFolder;	1✔
74	}
75
76	/**
77	* @return whether the crate has already been extracted into the temporary folder.
78	*/
79	public boolean isExtracted() {
80	return isExtracted;	1✔
81	}
82
83	private void readCrate(String location) throws IOException {
84	File folder = temporaryFolder.toFile();	1✔
85	// ensure the directory is clean
86	if (folder.isDirectory()) {	1✔
87	FileUtils.cleanDirectory(folder);	1✔
88	} else if (folder.isFile()) {	1✔
NEW 89	FileUtils.delete(folder);	×
90	}
91	// extract
92	try (ZipFile zf = new ZipFile(location)) {	1✔
93	zf.extractAll(temporaryFolder.toAbsolutePath().toString());	1✔
94	this.isExtracted = true;	1✔
95	}
96	// register deletion on exit
97	FileUtils.forceDeleteOnExit(folder);	1✔
98	}	1✔
99
100	@Override
101	public ObjectNode readMetadataJson(String location) throws IOException {
102	if (!isExtracted) {	1✔
103	this.readCrate(location);	1✔
104	}
105
106	ObjectMapper objectMapper = MyObjectMapper.getMapper();	1✔
107	File jsonMetadata = this.temporaryFolder.resolve(JsonDescriptor.ID).toFile();	1✔
108	if (!jsonMetadata.isFile()) {	1✔
109	// Try to find the metadata file in subdirectories
110	File firstSubdir = FileUtils.listFilesAndDirs(	1✔
111	temporaryFolder.toFile(),	1✔
112	FileFilterUtils.directoryFileFilter(),	1✔
113	null // not recursive
114	)
115	.stream()	1✔
116	.limit(50)	1✔
117	.filter(file -> file.toPath().toAbsolutePath().resolve(JsonDescriptor.ID).toFile().isFile())	1✔
118	.findFirst()	1✔
119	.orElseThrow(() -> new IllegalStateException("No %s found in zip file".formatted(JsonDescriptor.ID)));	1✔
120	jsonMetadata = firstSubdir.toPath().resolve(JsonDescriptor.ID).toFile();	1✔
121	}
122
123	return objectMapper.readTree(jsonMetadata).deepCopy();	1✔
124	}
125
126	@Override
127	public File readContent(String location) throws IOException {
128	if (!isExtracted) {	1✔
129	this.readCrate(location);	×
130	}
131	return temporaryFolder.toFile();	1✔
132	}
133	}

kit-data-manager / ro-crate-java / #427

Source File Press 'n' to go to next uncovered line, 'b' for previous

Source File
Press 'n' to go to next uncovered line, 'b' for previous