Merge branch 'v2' of github.com:aaronland/dogeared-extruder into main

Dockerfile

@@ -28,4 +28,4 @@ FROM openjdk:17-slim
 
 RUN mkdir /usr/local/jar
 
-COPY --from=builder /usr/src/dogeared-extruder/target/extruder-1.1.jar /usr/local/jar/dogeared-extruder.jar
+COPY --from=builder /usr/src/dogeared-extruder/target/extruder-2.0.jar /usr/local/jar/dogeared-extruder.jar

Makefile

@@ -7,7 +7,7 @@ build: todo
 	mvn install
 
 run:
-	java -jar target/extruder-1.0.jar server
+	java -jar target/extruder-2.0.jar server
 
 todo:
 	echo "# Generated automatically at" `date` > TODO.txt

README.md

@@ -5,16 +5,12 @@ This is a meant to be a simple HTTP Pony to wrap the `boilerpipe` and `Tika` and
 clones of the `readability` text extraction libraries using the `dropwizard`
 framework.
 
-Important
+Version "2"
 --
 
 This package was not updated between May 2014 and February 2022.
 
-There is a [v2 branch](https://github.com/aaronland/dogeared-extruder/tree/v2) for this package with up-to-date dependencies.
-Unfortunately, some of those dependencies contain changes that need to be accounted for in this package's code. That
-work is underway. Any help or suggestions would be appreciated.
-
-In the meantime, known security vulnerabilities for older dependencies have been addressed.
+In February 2022 "version 2" was released which introduces no new user-facing features but updated the internal code, where necessary, to account for updated dependencies and known security vulnerabilities.
 
 Quick start
 --
@@ -24,7 +20,7 @@ To start the server:
 	$> cd dogeared-extruder
 	$> make build
 	... JAVA STUFF ...
-	$> java -jar target/extruder-1.1.jar server
+	$> java -jar target/extruder-2.0.jar server
 	... MOAR JAVA STUFF ...
 	INFO  [2013-08-30 12:49:12,184] org.eclipse.jetty.server.AbstractConnector: Started InstrumentedBlockingChannelConnector@0.0.0.0:8080
 	INFO  [2013-08-30 12:49:12,189] org.eclipse.jetty.server.AbstractConnector: Started SocketConnector@0.0.0.0:8081

TODO.txt

@@ -1,11 +1,10 @@
-# Generated automatically at Tue Feb 15 22:45:38 PST 2022
+# Generated automatically at Fri Feb 18 17:32:35 PST 2022
 
-./src/main/java/info/aaronland/extruder/ExtruderService.java:30:	// TODO: put me in the config file... (20130908/straup)
 ./src/main/java/info/aaronland/extruder/JavaReadabilityResource.java:54:	// TODO: trap MalformedURLExceptions and return NOT_ACCEPTABLE here (20130901/straup)
-./src/main/java/info/aaronland/extruder/ExtruderApplication.java~:30:	// TODO: put me in the config file... (20130908/straup)
 ./src/main/java/info/aaronland/extruder/BoilerpipeResource.java:52:	// TODO: trap MalformedURLExceptions and return NOT_ACCEPTABLE here (20130901/straup)
+./src/main/java/info/aaronland/extruder/ExtruderApplication.java:40:	// TODO: put me in the config file... (20130908/straup)
 ./src/main/java/com/basistech/readability/Readability.java:93:        // TODO: reset the results.
 ./src/main/java/com/basistech/readability/Readability.java:368:         * http://www.peachpit.com/articles/article.aspx?p=31567&seqNum=5 TODO: Shouldn't this be a reverse
 ./src/main/java/com/basistech/readability/Readability.java:686:         * at the same time without effecting the traversal. TODO: Consider taking into account original
-./src/main/java/info/aaronland/extruder/TikaResource.java:140:    // TO DO: figure out how to make this return HTML instead of text
+./src/main/java/info/aaronland/extruder/TikaResource.java:139:    // TO DO: figure out how to make this return HTML instead of text
 ./src/main/java/info/aaronland/extruder/Upload.java:20:	// TO DO: sort out file extensions etc.

configuration.yml

@@ -1,2 +1,8 @@
 logging:
   level: INFO
+    loggers:
+      info.aaronland.extruder: DEBUG
+viewRendererConfiguration:
+  freemarker:
+    strict_syntax: yes
+    whitespace_stripping: yes

pom.xml

@@ -8,38 +8,53 @@
 
     <groupId>info.aaronland.extruder</groupId> 
     <artifactId>extruder</artifactId>
-    <version>1.1</version>
+    <version>2.0</version>
 
     <dependencies>
 
       <!-- dropwizard stuff -->
 
       <dependency>
-        <groupId>com.yammer.dropwizard</groupId>
+        <groupId>io.dropwizard</groupId>
         <artifactId>dropwizard-core</artifactId>
-        <version>0.6.2</version>
+        <version>2.0.28</version>
       </dependency>
 
       <dependency>
-        <groupId>com.yammer.dropwizard</groupId>
+        <groupId>io.dropwizard</groupId>
         <artifactId>dropwizard-views</artifactId>
-        <version>0.6.2</version>
+        <version>2.0.28</version>
       </dependency>
 
       <dependency>
-        <groupId>com.yammer.metrics</groupId>
-        <artifactId>metrics-core</artifactId>
-        <version>2.2.0</version>
+	<groupId>io.dropwizard</groupId>
+	<artifactId>dropwizard-forms</artifactId>
+	<version>2.0.28</version>
       </dependency>
 
       <dependency>
-        <groupId>com.sun.jersey.contribs</groupId>
-        <artifactId>jersey-multipart</artifactId>
-	<!-- this is important and needs to be in sync with the jersey defined in -->
-	<!-- https://github.com/codahale/dropwizard/blob/master/pom.xml -->
-        <version>1.17.1</version>
-      </dependency>   
+        <groupId>io.dropwizard</groupId>
+        <artifactId>dropwizard-views-freemarker</artifactId>
+        <version>2.0.28</version>
+      </dependency>
+
+      <dependency>
+        <groupId>io.dropwizard.metrics</groupId>
+        <artifactId>metrics-core</artifactId>
+        <version>4.2.8</version>
+      </dependency>
 
+      <!--
+	  not 3.x.y, because dropwizard is still using 2.29
+	  - https://www.dropwizard.io/en/latest/manual/upgrade-notes/upgrade-notes-2_0_x.html
+      -->
+
+      <dependency>
+	<groupId>org.glassfish.jersey.media</groupId>
+	<artifactId>jersey-media-multipart</artifactId>
+	<version>2.29.1</version>
+      </dependency>
+
       <!-- boilerpipe stuff -->
 
       <dependency>
@@ -53,28 +68,41 @@
       <dependency>
         <groupId>org.apache.tika</groupId>
         <artifactId>tika-core</artifactId>
-        <version>1.22</version>
+        <version>2.3.0</version>
       </dependency>
 
       <dependency>
 	<groupId>org.apache.tika</groupId>
 	<artifactId>tika-parsers</artifactId>
-	<version>1.22</version>
+	<version>2.3.0</version>
+	<type>pom</type>	
       </dependency>
 
+      <dependency>
+	<groupId>org.apache.tika</groupId>
+	<artifactId>tika-parsers-standard-package</artifactId>
+	<version>2.3.0</version>
+      </dependency>
+
       <!-- Misc dependencies -->
 
-      <!-- https://mvnrepository.com/artifact/javax.xml.bind/jaxb-api -->
+
       <dependency>
 	<groupId>javax.xml.bind</groupId>
 	<artifactId>jaxb-api</artifactId>
 	<version>2.3.1</version>
       </dependency>
 
+      <dependency>
+	<groupId>javax.mail</groupId>
+	<artifactId>javax.mail-api</artifactId>
+	<version>1.6.2</version>
+      </dependency>
+
       <dependency>
 	<groupId>org.apache.commons</groupId>
 	<artifactId>commons-lang3</artifactId>
-	<version>3.1</version>
+	<version>3.12.0</version>
       </dependency>
 
       <dependency>
@@ -86,7 +114,7 @@
       <dependency>
         <groupId>net.sourceforge.nekohtml</groupId>
         <artifactId>nekohtml</artifactId>
-        <version>1.9.18</version>
+        <version>1.9.22</version>
       </dependency>
 
       <!-- JavaReadability depedencies -->
@@ -102,7 +130,7 @@
       <dependency>
 	<groupId>commons-io</groupId>
 	<artifactId>commons-io</artifactId>
-	<version>2.7</version>
+	<version>2.11.0</version>
 	<type>jar</type>
 	<scope>compile</scope>
       </dependency>
@@ -120,7 +148,7 @@
         <plugin>
           <groupId>org.apache.maven.plugins</groupId>
           <artifactId>maven-compiler-plugin</artifactId>
-          <version>3.0</version>
+          <version>3.10.0</version>
           <configuration>
             <source>1.7</source>
             <target>1.7</target>
@@ -132,7 +160,7 @@
 	<plugin>
           <groupId>org.apache.maven.plugins</groupId>
           <artifactId>maven-shade-plugin</artifactId>
-          <version>1.6<!--2.1--></version>
+          <version>3.2.4</version>
           <executions>
             <execution>
               <phase>package</phase>
@@ -144,7 +172,7 @@
 		<transformers>
                   <transformer implementation="org.apache.maven.plugins.shade.resource.ServicesResourceTransformer"/>
                   <transformer implementation="org.apache.maven.plugins.shade.resource.ManifestResourceTransformer">
-		    <mainClass>info.aaronland.extruder.ExtruderService</mainClass>
+		    <mainClass>info.aaronland.extruder.ExtruderApplication</mainClass>
                   </transformer>
 		</transformers>
 		<!-- http://stackoverflow.com/questions/999489/invalid-signature-file-when-attempting-to-run-a-jar -->
@@ -166,7 +194,7 @@
 	<plugin>
 	  <groupId>org.codehaus.mojo</groupId>
 	  <artifactId>exec-maven-plugin</artifactId>
-	  <version>1.2.1</version>
+	  <version>3.0.0</version>
 	  <configuration>
             <mainClass>info.aaronland.extruder.ExtruderService</mainClass>
             <arguments>

src/main/java/com/basistech/readability/FilePageReader.java

@@ -22,7 +22,9 @@
 import java.io.FileInputStream;
 import java.io.IOException;
 
-import org.apache.tika.io.IOUtils;
+import org.apache.commons.io.IOUtils ;
+
+// import org.apache.tika.io.IOUtils;
 import org.slf4j.Logger;
 import org.slf4j.LoggerFactory;
 

src/main/java/info/aaronland/extruder/BoilerpipeResource.java

@@ -7,9 +7,9 @@
 import java.io.InputStream;
 import java.io.File;
 
-import com.sun.jersey.core.header.FormDataContentDisposition;
-import com.sun.jersey.multipart.FormDataMultiPart;
-import com.sun.jersey.multipart.FormDataBodyPart;
+import org.glassfish.jersey.media.multipart.FormDataContentDisposition;
+import org.glassfish.jersey.media.multipart.FormDataMultiPart;
+import org.glassfish.jersey.media.multipart.FormDataBodyPart;
 import javax.ws.rs.core.MediaType;
 
 import javax.ws.rs.GET;

src/main/java/info/aaronland/extruder/DocumentView.java

@@ -1,11 +1,7 @@
 package info.aaronland.extruder;
 
 import info.aaronland.extruder.Document;
-import com.yammer.dropwizard.views.View;
-
-import com.google.common.base.Charsets;
-import com.google.common.base.Optional;
-import java.nio.charset.Charset;
+import io.dropwizard.views.View;
 
 public class DocumentView extends View {
     private final Document document;
@@ -19,13 +15,4 @@ public Document getDocument(){
         return document;
     }
 
-    // Because in com/codahale/dropwizard/views/freemarker/FreemarkerViewRenderer.java this:
-    // final Charset charset = view.getCharset().or(Charset.forName(configuration.getEncoding(locale)));
-    // And since the default encoding for en-us is ISO-8859-1... good times
-    // (20130908/straup)
-
-    public Optional<Charset> getCharset(){
-	return Optional.of(Charsets.UTF_8);
-    }
-
 }

src/main/java/info/aaronland/extruder/ExtruderApplication.java

@@ -0,0 +1,46 @@
+package info.aaronland.extruder;
+
+import io.dropwizard.Application;
+import io.dropwizard.setup.Bootstrap;
+import io.dropwizard.setup.Environment;
+import io.dropwizard.views.ViewBundle;
+import io.dropwizard.forms.MultiPartBundle;
+
+import info.aaronland.extruder.ExtruderConfiguration;
+
+import java.net.URL;
+import java.util.Map;
+
+public class ExtruderApplication extends Application<ExtruderConfiguration> {
+
+    public static void main(String[] args) throws Exception {
+        new ExtruderApplication().run(args);
+    }
+
+    public void initialize(Bootstrap<ExtruderConfiguration> bootstrap) {
+
+	bootstrap.addBundle(new MultiPartBundle());
+
+	bootstrap.addBundle(new ViewBundle<ExtruderConfiguration>(){
+
+		@Override
+		public Map<String, Map<String, String>> getViewConfiguration(ExtruderConfiguration config) {
+		    return config.getViewRendererConfiguration();
+		}
+	    });
+    }
+
+    @Override
+	public void run(ExtruderConfiguration conf, Environment env) throws Exception {
+
+        env.jersey().register(new BoilerpipeResource());
+        env.jersey().register(new TikaResource());
+        env.jersey().register(new JavaReadabilityResource());
+
+	// TODO: put me in the config file... (20130908/straup)
+	URL healthcheck_url = new URL("https://github.com/aaronland/dogeared-extruder/");
+
+	env.healthChecks().register("internets", new InternetsHealthCheck(healthcheck_url));
+    }
+
+}

src/main/java/info/aaronland/extruder/ExtruderConfiguration.java

@@ -1,9 +1,27 @@
 package info.aaronland.extruder;
 
-import com.yammer.dropwizard.config.Configuration;
+import io.dropwizard.Configuration;
 
 import javax.validation.Valid;
+import javax.validation.constraints.NotNull;
+
+import java.util.Collections;
+import java.util.Map;
+
+import com.fasterxml.jackson.annotation.JsonProperty;
 
 public class ExtruderConfiguration extends Configuration {
 
+    @NotNull
+    private Map<String, Map<String, String>> viewRendererConfiguration = Collections.emptyMap();
+
+    @JsonProperty("viewRendererConfiguration")
+    public Map<String, Map<String, String>> getViewRendererConfiguration() {
+        return viewRendererConfiguration;
+    }
+
+    @JsonProperty("viewRendererConfiguration")
+    public void setViewRendererConfiguration(Map<String, Map<String, String>> viewRendererConfiguration) {
+        this.viewRendererConfiguration = viewRendererConfiguration;
+    }
 }