Skip to content

Add a transformer for changing absolute IDs into relative ones #2

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 5 commits into
base: master
Choose a base branch
from
Open

Add a transformer for changing absolute IDs into relative ones #2

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
4fa033c
Initial commit of id-relativizing transformer
mikesname Aug 29, 2014
896542e
Handle slashes, and add a real-life JMP test case
mikesname Aug 29, 2014
9a8a581
Cleanup
mikesname Aug 29, 2014
2cbec87
Test we don't mangle already relative IDs
mikesname Aug 29, 2014
5d39739
Merge branch 'master' into relativize-identifiers
mikesname Jan 22, 2015
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions pom.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,6 +14,7 @@
<module>add-language-of-descriptions</module>
<module>identify-main-identifier</module>
<module>leave-only-one-identifier</module>
<module>relativize-identifiers</module>
</modules>
<dependencyManagement>
<dependencies>
Expand Down
10 changes: 10 additions & 0 deletions relativize-identifiers/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,10 @@
relativize-identifiers
=========================

Part of the ehri-ead-preprocessing tools to normalise EAD files before importing into the EHRI database.

precondition: The EAD file has absolute identifiers, where unitids in each c-level include the full ID of their parent unitid
postcondition: The EAD file has relative identifiers.

usage:
java -jar relativize-identifiers/target/relativize-identifier-1.0-SNAPSHOT-jar-with-dependencies.jar <ead.xml>
72 changes: 72 additions & 0 deletions relativize-identifiers/pom.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,72 @@
<?xml version="1.0"?>
<project xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd" xmlns="http://maven.apache.org/POM/4.0.0"
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">
<modelVersion>4.0.0</modelVersion>
<parent>
<groupId>ehri-project-preprocess</groupId>
<artifactId>ead-preprocessing</artifactId>
<version>1.0</version>
</parent>
<groupId>ehri-project</groupId>
<artifactId>relativize-identifiers</artifactId>
<version>1.0-SNAPSHOT</version>
<name>relativize-identifiers</name>
<url>http://maven.apache.org</url>
<properties>
<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
</properties>
<dependencies>
<dependency>
<groupId>junit</groupId>
<artifactId>junit</artifactId>
<version>4.10</version>
<scope>test</scope>
</dependency>

<!-- STAX parser -->
<dependency>
<groupId>stax</groupId>
<artifactId>stax</artifactId>
<version>1.2.0</version>
</dependency>
<dependency>
<groupId>stax</groupId>
<artifactId>stax-api</artifactId>
<version>1.0.1</version>
</dependency>
<dependency>
<groupId>org.apache.commons</groupId>
<artifactId>commons-io</artifactId>
<version>1.3.2</version>
</dependency>

</dependencies>

<build>
<plugins>
<plugin>
<artifactId>maven-assembly-plugin</artifactId>
<configuration>
<archive>
<manifest>
<mainClass>eu.ehri.relativize_identifiers.RelativizeIdentifiers</mainClass>
</manifest>
</archive>
<descriptorRefs>
<descriptorRef>jar-with-dependencies</descriptorRef>
</descriptorRefs>
</configuration>
<executions>
<execution>
<id>make-assembly</id> <!-- this is used for inheritance merges -->
<phase>package</phase> <!-- bind to the packaging phase -->
<goals>
<goal>single</goal>
</goals>
</execution>
</executions>
</plugin>
</plugins>
</build>

</project>
90 changes: 90 additions & 0 deletions ...ivize-identifiers/src/main/java/eu/ehri/relativize_identifiers/RelativizeIdentifiers.java
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,90 @@
package eu.ehri.relativize_identifiers;

import java.io.FileInputStream;
import java.io.FileWriter;
import java.io.IOException;
import java.io.Writer;

import java.util.Stack;
import java.util.regex.Pattern;
import javax.xml.parsers.FactoryConfigurationError;
import javax.xml.stream.XMLEventFactory;
import javax.xml.stream.XMLEventReader;
import javax.xml.stream.XMLEventWriter;
import javax.xml.stream.XMLInputFactory;
import javax.xml.stream.XMLOutputFactory;
import javax.xml.stream.XMLStreamException;
import javax.xml.stream.events.Characters;
import javax.xml.stream.events.XMLEvent;


public class RelativizeIdentifiers {

public final static String SUFFIX = "_relid.xml";

static XMLEventFactory eventFactory = XMLEventFactory.newInstance();
static XMLOutputFactory factory = XMLOutputFactory.newInstance();


public static void main(String[] args) throws XMLStreamException, javax.xml.stream.FactoryConfigurationError, IOException {
String eadfile = args[0];
String outputfile = eadfile.replace(".xml", SUFFIX);
RelativizeIdentifiers.relativizeIdentifiers(eadfile, new FileWriter(outputfile));
}

/**
* precondition: The EAD file has absolute identifiers, where unitids in each c-level
* include the full ID of their parent unitid
* postcondition: The EAD file has relative identifiers.
*
* @param eadfile the name of the ead file
* @throws javax.xml.stream.XMLStreamException
* @throws javax.xml.parsers.FactoryConfigurationError
* @throws java.io.IOException
*/
public static String relativizeIdentifiers(String eadfile, Writer outputWriter)
throws XMLStreamException, FactoryConfigurationError, IOException {

FileInputStream fileInputStreamEAD = new FileInputStream(eadfile);
XMLEventWriter writer = factory.createXMLEventWriter(outputWriter);

Stack<String> idStack = new Stack<String>();
Pattern childPattern = Pattern.compile("c\\d\\d");

String thisId;

XMLEventReader xmlEventReaderEAD = XMLInputFactory.newInstance().createXMLEventReader(fileInputStreamEAD);
while (xmlEventReaderEAD.hasNext()) {
XMLEvent event = xmlEventReaderEAD.nextEvent();
writer.add(event);
if (event.isStartElement()) {
if (event.asStartElement().getName().getLocalPart().equals("unitid")) {
XMLEvent nextEvent = xmlEventReaderEAD.nextEvent();
if (nextEvent.isCharacters()) {
thisId = nextEvent.asCharacters().getData();
if (!idStack.empty() && thisId.contains(idStack.peek())) {
// Replace the ID and any non-ID trailing chars, such as spaces,
// colons, or dashes.
String regex = "^" + Pattern.quote(idStack.peek()) + "[\\s\\-:_\\/]*";
String newId = thisId.replaceFirst(regex, "");
Characters chars = eventFactory.createCharacters(newId);
writer.add(chars);
} else {
writer.add(nextEvent);
}
idStack.push(thisId);
}
}
} else if (event.isEndElement()) {
if (event.asEndElement().getName().getLocalPart()
.matches(childPattern.pattern())) {
idStack.pop();
}
}
}

writer.close();
xmlEventReaderEAD.close();
return null;
}
}
88 changes: 88 additions & 0 deletions ...e-identifiers/src/test/java/eu/ehri/relativize_identifiers/RelativizeIdentifiersTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,88 @@
package eu.ehri.relativize_identifiers;

import org.junit.Before;
import org.junit.Test;
import org.w3c.dom.Document;
import org.xml.sax.SAXException;

import javax.xml.parsers.DocumentBuilder;
import javax.xml.parsers.DocumentBuilderFactory;
import javax.xml.stream.XMLStreamException;
import javax.xml.transform.dom.DOMSource;
import javax.xml.xpath.XPath;
import javax.xml.xpath.XPathExpression;
import javax.xml.xpath.XPathFactory;
import java.io.*;
import java.net.URISyntaxException;
import java.net.URL;

import static org.junit.Assert.assertEquals;

/**
* @author Mike Bryant (http://github.com/mikesname)
*/
public class RelativizeIdentifiersTest {

DocumentBuilder builder;
XPath xpath;

@Before
public void setUp() throws Exception {
builder = DocumentBuilderFactory.newInstance().newDocumentBuilder();
xpath = XPathFactory.newInstance().newXPath();
}

@Test
public void testRelativizeIdentifiersWithSpaces() throws Exception {
Document outDoc = getOutputDocument("/absoluteids-spaces.xml");
assertEquals("1", xpath.compile("/ead/archdesc/dsc/c01/did/unitid").evaluate(outDoc));
assertEquals("1", xpath.compile("/ead/archdesc/dsc/c01/c02[1]/did/unitid").evaluate(outDoc));
assertEquals("1", xpath.compile("/ead/archdesc/dsc/c01/c02[1]/c03/did/unitid").evaluate(outDoc));
assertEquals("2", xpath.compile("/ead/archdesc/dsc/c01/c02[2]/did/unitid").evaluate(outDoc));
assertEquals("1", xpath.compile("/ead/archdesc/dsc/c01/c02[2]/c03/did/unitid").evaluate(outDoc));
assertEquals("2 root 1 2", xpath.compile("/ead/archdesc/dsc/c01/c02[2]/c03[2]/did/unitid").evaluate(outDoc));
}

@Test
public void testRelativizeIdentifiersWithHyphens() throws Exception {
Document outDoc = getOutputDocument("/absoluteids-hyphens.xml");
assertEquals("1", xpath.compile("/ead/archdesc/dsc/c01/did/unitid").evaluate(outDoc));
assertEquals("1", xpath.compile("/ead/archdesc/dsc/c01/c02[1]/did/unitid").evaluate(outDoc));
assertEquals("1", xpath.compile("/ead/archdesc/dsc/c01/c02[1]/c03/did/unitid").evaluate(outDoc));
assertEquals("2", xpath.compile("/ead/archdesc/dsc/c01/c02[2]/did/unitid").evaluate(outDoc));
assertEquals("1", xpath.compile("/ead/archdesc/dsc/c01/c02[2]/c03/did/unitid").evaluate(outDoc));
}

@Test
public void testRelativizeIdentifiersWithSlashes() throws Exception {
Document outDoc = getOutputDocument("/wp2_jmp_ead.xml");
assertEquals("COLLECTION.JMP.SHOAH/T", xpath.compile("/ead/archdesc/did/unitid").evaluate(outDoc));
assertEquals("2", xpath.compile("/ead/archdesc/dsc/c01[1]/did/unitid").evaluate(outDoc));
assertEquals("A", xpath.compile("/ead/archdesc/dsc/c01[1]/c02[1]/did/unitid").evaluate(outDoc));
assertEquals("1", xpath.compile("/ead/archdesc/dsc/c01[1]/c02[1]/c03[1]/did/unitid").evaluate(outDoc));
assertEquals("a", xpath.compile("/ead/archdesc/dsc/c01[1]/c02[1]/c03[1]/c04[1]/did/unitid").evaluate(outDoc));
assertEquals("028", xpath.compile("/ead/archdesc/dsc/c01[1]/c02[1]/c03[1]/c04[1]/c05[1]/did/unitid").evaluate
(outDoc));
}

@Test
public void testRelativizeIdentifiersAlreadyRelative() throws Exception {
Document outDoc = getOutputDocument("/relativeids.xml");
assertEquals("c1", xpath.compile("/ead/archdesc/dsc/c01/did/unitid").evaluate(outDoc));
assertEquals("c2-1", xpath.compile("/ead/archdesc/dsc/c01/c02[1]/did/unitid").evaluate(outDoc));
assertEquals("c3-1", xpath.compile("/ead/archdesc/dsc/c01/c02[1]/c03/did/unitid").evaluate(outDoc));
assertEquals("c2-2", xpath.compile("/ead/archdesc/dsc/c01/c02[2]/did/unitid").evaluate(outDoc));
assertEquals("c3-1", xpath.compile("/ead/archdesc/dsc/c01/c02[2]/c03/did/unitid").evaluate(outDoc));
}

private Document getOutputDocument(String resourceName) throws URISyntaxException, XMLStreamException,
IOException, SAXException {
URL resource = RelativizeIdentifiersTest.class.getResource(resourceName);
String path = new File(resource.toURI()).getAbsolutePath();
StringWriter stringWriter = new StringWriter();
RelativizeIdentifiers.relativizeIdentifiers(path, stringWriter);
stringWriter.close();
ByteArrayInputStream byteArrayInputStream = new ByteArrayInputStream(stringWriter.getBuffer().toString().getBytes());
return builder.parse(byteArrayInputStream);
}
}
37 changes: 37 additions & 0 deletions relativize-identifiers/src/test/resources/absoluteids-hyphens.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,37 @@
<ead>
<eadheader>

</eadheader>
<archdesc>
<did>
<unitid>root</unitid>
</did>
<dsc type="combined">
<c01>
<did>
<unitid>root-1</unitid>
</did>
<c02>
<did>
<unitid>root-1-1</unitid>
</did>
<c03>
<did>
<unitid>root-1-1-1</unitid>
</did>
</c03>
</c02>
<c02>
<did>
<unitid>root-1-2</unitid>
</did>
<c03>
<did>
<unitid>root-1-2-1</unitid>
</did>
</c03>
</c02>
</c01>
</dsc>
</archdesc>
</ead>
44 changes: 44 additions & 0 deletions relativize-identifiers/src/test/resources/absoluteids-spaces.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,44 @@
<ead>
<eadheader>

</eadheader>
<archdesc>
<did>
<unitid>root</unitid>
</did>
<dsc type="combined">
<c01>
<did>
<unitid>root 1</unitid>
</did>
<c02>
<did>
<unitid>root 1 1</unitid>
</did>
<c03>
<did>
<unitid>root 1 1 1</unitid>
</did>
</c03>
</c02>
<c02>
<did>
<unitid>root 1 2</unitid>
</did>
<c03>
<did>
<unitid>root 1 2 1</unitid>
</did>
</c03>
<c03>
<did>
<!-- Ensure an ID with it's parent ID repeated somewhere
other than the start doesn't get munged. -->
<unitid>root 1 2 2 root 1 2</unitid>
</did>
</c03>
</c02>
</c01>
</dsc>
</archdesc>
</ead>
37 changes: 37 additions & 0 deletions relativize-identifiers/src/test/resources/relativeids.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,37 @@
<ead>
<eadheader>

</eadheader>
<archdesc>
<did>
<unitid>root</unitid>
</did>
<dsc type="combined">
<c01>
<did>
<unitid>c1</unitid>
</did>
<c02>
<did>
<unitid>c2-1</unitid>
</did>
<c03>
<did>
<unitid>c3-1</unitid>
</did>
</c03>
</c02>
<c02>
<did>
<unitid>c2-2</unitid>
</did>
<c03>
<did>
<unitid>c3-1</unitid>
</did>
</c03>
</c02>
</c01>
</dsc>
</archdesc>
</ead>
Loading