Merge branch 'test/95--Explore-XML-Schema-validator-warnings'

Calpano · Apr 25, 2023 · 92288e1 · 92288e1
2 parents b8fe05e + 95bac0f
commit 92288e1
Show file tree

Hide file tree

Showing 8 changed files with 316 additions and 11 deletions.
diff --git a/.github/workflows/build-and-test.yml b/.github/workflows/build-and-test.yml
@@ -0,0 +1,43 @@
+name: Build and Test
+
+on:
+  push:
+
+jobs:
+  build-and-test:
+    # list of OSes and what they contain https://github.com/actions/virtual-environments
+    runs-on: ubuntu-latest
+    steps:
+      - name: ↙️ Check out repository code from git
+        uses: actions/checkout@v3
+        with:
+          repository: Calpano/graphinout
+          path: graphinout
+
+      - name: ☕ Setup Java JDK
+        uses: actions/setup-java@v3
+        with:
+          distribution: 'temurin'
+          java-version: '17'
+          cache: 'maven'
+
+      - name: ⬇️ Install root project
+        working-directory: graphinout
+        run: mvn clean -U -N install
+
+      - name: 🔨️ Build & ⬇ install base
+        working-directory: graphinout/base
+        run: mvn clean -U install
+
+      - name: 🔨️ Build & ⬇ install readers
+        working-directory: graphinout
+        run: mvn clean -U -pl !base,!engine,!app-cmdline install
+        env:
+          MAVEN_OPTS: "-Xmx6144m"
+
+      - name: 🔨️ Build & ⬇ install engine & app-cmdline
+        working-directory: graphinout
+        run: mvn clean -U -pl engine,app-cmdline install
+        env:
+          MAVEN_OPTS: "-Xmx6144m"
+
diff --git a/base/src/main/java/com/calpano/graphinout/base/reader/GioReader.java b/base/src/main/java/com/calpano/graphinout/base/reader/GioReader.java
@@ -1,18 +1,28 @@
 package com.calpano.graphinout.base.reader;
 
+import com.calpano.graphinout.base.gio.DelegatingGioWriter;
 import com.calpano.graphinout.base.gio.GioWriter;
+import com.calpano.graphinout.base.gio.GioWriterImpl;
+import com.calpano.graphinout.base.gio.ValidatingGioWriter;
 import com.calpano.graphinout.base.input.InputSource;
 import com.calpano.graphinout.base.input.SingleInputSource;
+import com.calpano.graphinout.base.output.ValidatingGraphMlWriter;
+import org.slf4j.Logger;
 
 import java.io.IOException;
 import java.util.concurrent.atomic.AtomicBoolean;
 import java.util.function.Consumer;
 
+import static org.slf4j.LoggerFactory.getLogger;
+
 public interface GioReader {
 
+    Logger log = getLogger(GioReader.class);
+
     /**
-     * Set error handler to the reader. Reader will use it to report errors while parsing.
-     * IOExceptions remain normal IOExceptions.
+     * Set error handler to the reader. Reader will use it to report errors while parsing. IOExceptions remain normal
+     * IOExceptions.
+     *
      * @param errorHandler
      */
     void errorHandler(Consumer<ContentError> errorHandler);
@@ -26,19 +36,26 @@ public interface GioReader {
 
     /**
      * Inspect input
+     *
      * @param singleInputSource
      * @return
      * @throws IOException
      */
     default boolean isValid(SingleInputSource singleInputSource) throws IOException {
         AtomicBoolean valid = new AtomicBoolean(true);
-        errorHandler((error) -> {
+        Consumer<ContentError> eh = error -> {
             if (error.level == ContentError.ErrorLevel.Error || error.level == ContentError.ErrorLevel.Warn) {
                 valid.set(false);
             }
-        });
-        // FIXME dont use null, use a dummy do-nothing-writer
-        read(singleInputSource, null);
+        };
+        errorHandler(eh);
+        try {
+            GioWriter writer = new DelegatingGioWriter(new ValidatingGioWriter(), new GioWriterImpl(new ValidatingGraphMlWriter()));
+            read(singleInputSource, writer);
+        } catch (Exception t) {
+            log.warn("Invalid input in "+singleInputSource.name(), t);
+            eh.accept(new ContentError(ContentError.ErrorLevel.Error,t.getMessage(), null));
+        }
         return valid.get();
     }
 

diff --git a/base/src/test/java/com/calpano/graphinout/base/xml/GraphmlValidatorTest.java b/base/src/test/java/com/calpano/graphinout/base/xml/GraphmlValidatorTest.java
@@ -1,6 +1,8 @@
 package com.calpano.graphinout.base.xml;
 
 import com.calpano.graphinout.base.input.SingleInputSource;
+import org.junit.jupiter.api.AfterEach;
+import org.junit.jupiter.api.BeforeEach;
 import org.junit.jupiter.api.Test;
 
 import java.io.IOException;
@@ -51,4 +53,15 @@ void testWrongElement() throws IOException {
         assertFalse(GraphmlValidator.isValidGraphml(SingleInputSource.of("funnybunny", badGraphml)));
     }
 
+    @BeforeEach
+    void setUp() {
+    }
+
+    @AfterEach
+    void tearDown() {
+    }
+
+    @Test
+    void isValidGraphml() {
+    }
 }
diff --git a/pom.xml b/pom.xml
@@ -33,6 +33,7 @@
         <mockito-core-version>5.1.1</mockito-core-version>
         <mockito-junit-jupiter-version>5.1.1</mockito-junit-jupiter-version>
         <lombok-version>1.18.24</lombok-version>
+        <maven-surefire-plugin.version>3.0.0-M7</maven-surefire-plugin.version>
     </properties>
 
     <dependencyManagement>
@@ -111,10 +112,49 @@
             </plugin>
             <plugin>
                 <artifactId>maven-surefire-plugin</artifactId>
-                <version>3.0.0-M7</version>
+                <version>${maven-surefire-plugin.version}</version>
+                <executions>
+                    <execution>
+                        <id>default-test</id>
+                        <phase>test</phase>
+                        <goals>
+                            <goal>test</goal>
+                        </goals>
+                    </execution>
+                </executions>
             </plugin>
+            <plugin>
+                <groupId>org.apache.maven.plugins</groupId>
+                <artifactId>maven-jar-plugin</artifactId>
+                <version>3.0.2</version>
+                <executions>
+                    <execution>
+                        <goals>
+                            <goal>test-jar</goal>
+                        </goals>
+                    </execution>
+                </executions>
+            </plugin>
+            <plugin>
+                <!-- create "-sources.jar" at verify-phase just before install-phase -->
+                <groupId>org.apache.maven.plugins</groupId>
+                <artifactId>maven-source-plugin</artifactId>
+                <version>3.2.1</version>
+                <executions>
+                    <execution>
+                        <id>attach-sources</id>
+                        <phase>verify</phase>
+                        <goals>
+                            <goal>jar-no-fork</goal>
+                        </goals>
+                    </execution>
+                </executions>
+            </plugin>
+
         </plugins>
     </build>
+
+
     <dependencies>
         <!-- https://mvnrepository.com/artifact/com.google.code.findbugs/jsr305 -->
         <dependency>
@@ -134,4 +174,4 @@
             <scope>test</scope>
         </dependency>
     </dependencies>
-</project>
+</project>
diff --git a/reader-graphml/src/main/java/com/calpano/graphinout/reader/graphml/GraphmlReader.java b/reader-graphml/src/main/java/com/calpano/graphinout/reader/graphml/GraphmlReader.java
@@ -6,15 +6,25 @@
 import com.calpano.graphinout.base.reader.ContentError;
 import com.calpano.graphinout.base.reader.GioFileFormat;
 import com.calpano.graphinout.base.reader.GioReader;
+import org.xml.sax.ErrorHandler;
 import org.xml.sax.SAXException;
+import org.xml.sax.SAXParseException;
+import org.xml.sax.XMLReader;
 
 import javax.xml.parsers.ParserConfigurationException;
 import javax.xml.parsers.SAXParser;
 import javax.xml.parsers.SAXParserFactory;
+import javax.xml.transform.Source;
+import javax.xml.transform.stream.StreamSource;
+import javax.xml.validation.SchemaFactory;
 import java.io.IOException;
+import java.util.ArrayList;
+import java.util.List;
 import java.util.function.Consumer;
 
 public class GraphmlReader implements GioReader {
+    //TODO This can load from config file
+    private List<String> externalSchemaList = new ArrayList<>();
     private Consumer<ContentError> errorHandler;
 
     @Override
@@ -47,8 +57,123 @@ public void read(InputSource inputSource, GioWriter writer) throws IOException {
                 throw new IOException(e);
             }
         } catch (Throwable t) {
-            errorHandler.accept(new ContentError(ContentError.ErrorLevel.Error, "Failed reading '" + inputSource.name() + "'. Details: "+t.getMessage(), null));
+            errorHandler.accept(new ContentError(ContentError.ErrorLevel.Error, "Failed reading '" + inputSource.name() + "'. Details: " + t.getMessage(), null));
             throw new RuntimeException("Failed reading '" + inputSource.name() + "'", t);
         }
     }
+
+    @Override
+    public boolean isValid(SingleInputSource singleInputSource) throws IOException {
+
+        try {
+            validateWellFormed(singleInputSource);
+           //TODO There is no internal DTD in any of the files that have been processed so far.
+           //If it exists, it can be verified with this method
+           //validateInternalDTD(singleInputSource);
+           //ValidateInternalXSD(singleInputSource);
+           //ValidateExternalSchema(singleInputSource);
+        } catch (ParserConfigurationException e) {
+            throw new RuntimeException(e);
+        } catch (SAXException e) {
+            throw new RuntimeException(e);
+        }
+        return GioReader.super.isValid(singleInputSource);
+    }
+
+    void validateWellFormed(SingleInputSource inputSource) throws ParserConfigurationException, SAXException, IOException {
+        SAXParserFactory factory = SAXParserFactory.newInstance();
+        factory.setValidating(false);
+        factory.setNamespaceAware(true);
+
+        SAXParser parser = factory.newSAXParser();
+
+        XMLReader reader = parser.getXMLReader();
+        reader.setErrorHandler(new SimpleErrorHandler(this.errorHandler));
+        reader.parse(new org.xml.sax.InputSource(inputSource.inputStream()));
+    }
+
+    void validateInternalDTD(SingleInputSource inputSource) throws ParserConfigurationException, SAXException, IOException {
+        SAXParserFactory factory = SAXParserFactory.newInstance();
+        factory.setValidating(true);
+        factory.setNamespaceAware(true);
+
+        SAXParser parser = factory.newSAXParser();
+
+        XMLReader reader = parser.getXMLReader();
+        reader.setErrorHandler(new SimpleErrorHandler(this.errorHandler));
+        reader.parse(new org.xml.sax.InputSource(inputSource.inputStream()));
+    }
+
+    void validateInternalXSD(SingleInputSource inputSource) throws ParserConfigurationException, SAXException, IOException {
+        SAXParserFactory factory = SAXParserFactory.newInstance();
+        factory.setValidating(true);
+        factory.setNamespaceAware(true);
+
+        SAXParser parser = factory.newSAXParser();
+        parser.setProperty("http://java.sun.com/xml/jaxp/properties/schemaLanguage",
+                "http://www.w3.org/2001/XMLSchema");
+
+        XMLReader reader = parser.getXMLReader();
+        reader.setErrorHandler(new SimpleErrorHandler(this.errorHandler));
+        reader.parse(new org.xml.sax.InputSource(inputSource.inputStream()));
+    }
+
+    /**
+     * Two sub-options: (1) XML file contains "xsi:schemaLocation" -> take XML Schema from there;
+     * (2) we pre-downloaded Graphml.XSD, use it, and ignore "xsi:schemaLocation" -- http://graphml.graphdrawing.org/xmlns/1.1/graphml.xsd
+     * @param inputSource
+     * @throws SAXException
+     * @throws IOException
+     * @throws ParserConfigurationException
+     */
+    void validateExternalSchema(SingleInputSource inputSource) throws SAXException, IOException, ParserConfigurationException {
+        if (externalSchemaList.isEmpty()) return;
+
+        Source[] listOfAvailableSchema = externalSchemaList.stream().toArray(StreamSource[]::new);
+        SAXParserFactory factory = SAXParserFactory.newInstance();
+        factory.setValidating(false);
+        factory.setNamespaceAware(true);
+
+        SchemaFactory schemaFactory =
+                SchemaFactory.newInstance("http://www.w3.org/2001/XMLSchema");
+        factory.setSchema(schemaFactory.newSchema(listOfAvailableSchema));
+
+        SAXParser parser = factory.newSAXParser();
+        XMLReader reader = parser.getXMLReader();
+        reader.setErrorHandler(new SimpleErrorHandler(this.errorHandler));
+        reader.parse(new org.xml.sax.InputSource(inputSource.inputStream()));
+
+    }
+
+    class SimpleErrorHandler implements ErrorHandler {
+
+
+        private final Consumer<ContentError> errorConsumer;
+
+        public SimpleErrorHandler(Consumer<ContentError> errorConsumer) {
+            this.errorConsumer = errorConsumer;
+        }
+
+        @Override
+        public void warning(SAXParseException e) throws SAXException {
+            ContentError contentError = new ContentError(ContentError.ErrorLevel.Warn, e.getMessage(),
+                    null);
+            if (errorConsumer != null) {
+                errorConsumer.accept(contentError);
+            }
+        }
+
+        @Override
+        public void error(SAXParseException e) throws SAXException {
+            //TODO Throw exception Or log to errorConsumer?
+            throw e;
+
+        }
+
+        @Override
+        public void fatalError(SAXParseException e) throws SAXException {
+            //TODO Throw exception Or log to errorConsumer?
+            throw e;
+        }
+    }
 }