Adding a JSONResultformatter and the possibility to use a python POS-tagger

.classpath

@@ -0,0 +1,18 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<classpath>
+	<classpathentry kind="src" path="src/main/java"/>
+	<classpathentry kind="src" path="src/test/java"/>
+	<classpathentry kind="src" path="src/main/resources"/>
+	<classpathentry kind="src" path="src/test/resources"/>
+	<classpathentry kind="con" path="org.eclipse.jdt.launching.JRE_CONTAINER/org.eclipse.jdt.internal.debug.ui.launcher.StandardVMType/JavaSE-1.7">
+		<attributes>
+			<attribute name="maven.pomderived" value="true"/>
+		</attributes>
+	</classpathentry>
+	<classpathentry kind="con" path="org.eclipse.m2e.MAVEN2_CLASSPATH_CONTAINER">
+		<attributes>
+			<attribute name="maven.pomderived" value="true"/>
+		</attributes>
+	</classpathentry>
+	<classpathentry kind="output" path="class"/>
+</classpath>

README.md

@@ -2,6 +2,32 @@
 
 **HeidelTime contains automatically created resources for 200+ languages in addition to manually created ones for 13 languages. For further details, take a look at our [EMNLP 2015 paper](https://aclweb.org/anthology/D/D15/D15-1063.pdf).**
 
+## About CRIM-Heideltime
+CRIM-Heideltime extends Heideltime by offering two other part-of-speech-tagger wrappers and a JSON result formatter.
+
+### Part-of-speech-tagger wrappers
+* **Python part-of-speech-tagger wrapper** : the wrapper calls a Python script that returns the CAS tagged with the POS and the sentences. The path to the Python script has to be configured in the `config.props` file.
+* **JSON part-of-speech-tagger wrapper** : the wrapper reads 2 JSON files, one containing the sentence annotations, the other the POS annotations. The paths to the JSON files have to be set as environment variables (_SENTENCE_ANNOTATION_FILE_PATH_ and _POS_ANNOTATION_FILE_PATH_). The JSONtaggerWrapper reads a configuration file (configured in `config.props`) containing the way to retrieve following elements within the JSON files :
+    * sentence_begin
+    * sentence_end
+    * token_begin
+    * token_end
+    * token_pos   
+
+The format of the file is on each line :   
+`element_to_retrieve\t[key|index] [key|index] ...`
+
+Example :
+
+```text
+sentence_begin	offsets 0 begin
+sentence_end	offsets 0 end
+token_begin	offsets 0 begin  
+token_end	offsets 0 end   
+token_pos	category
+```  
+
+
 ## About HeidelTime
 **HeidelTime** is a multilingual, domain-sensitive temporal tagger developed at the [Database Systems Research Group](http://dbs.ifi.uni-heidelberg.de/) at [Heidelberg University](http://www.uni-heidelberg.de/index_e.html). It extracts temporal expressions from documents and normalizes them according to the TIMEX3 annotation standard. HeidelTime is available as [UIMA](http://uima.apache.org/) annotator and as standalone version.
 
@@ -13,7 +39,7 @@ Want to see what it can do before you delve in? Take a look at our **[online dem
 
 ![HeidelTime demo picture](https://drive.google.com/uc?export=download&id=0BwqFBQjz9NUicWEzaWlzT1J1SzQ)
 
-## Latest downloads
+## HeidelTime - Latest downloads
 
 * Our latest as well as past releases are always available on the [Releases page](https://github.com/HeidelTime/heideltime/releases).
 * Bleeding edge version is available via our Git repository.

conf/config.props

@@ -21,7 +21,7 @@ considerTemponym = false
 # Path to TreeTagger home directory
 ###################################
 # Ensure there is no white space in path (try to escape white spaces)
-treeTaggerHome = SET ME IN CONFIG.PROPS! (e.g., /home/jannik/treetagger)
+treeTaggerHome = /misc/home/reco/reboutli/Dev/Java/Treetagger 
 # This one is only necessary if you want to process chinese documents.
 chineseTokenizerPath = SET ME IN CONFIG.PROPS! (e.g., /home/jannik/treetagger/chinese-tokenizer)
 
@@ -45,7 +45,15 @@ config_path =
 hunpos_path = SET ME IN CONFIG.PROPS! (e.g., /home/jannik/hunpos)
 hunpos_model_name = SET ME IN CONFIG.PROPS! (e.g., model.hunpos.mte5.defnpout)
 
+########################################
+## paths to PythonTaggerscript:
+########################################
+python_script_path = SET ME IN CONFIG.PROPS! (e.g., /misc/home/reco/reboutli/Dev/Python/PythonPOSTaggerWrapper/JythonPOSTaggerWrapper.py)
 
+########################################
+## paths to JSONTaggerConfig:
+########################################
+json_config_path = SET ME IN CONFIG.PROPS! (e.g., /misc/home/reco/reboutli/Dev/Python/temporal_annotation/config_JSONReader.txt)
 
 # DO NOT CHANGE THE FOLLOWING
 ################################

pom.xml

@@ -2,13 +2,13 @@
 	xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
 	<modelVersion>4.0.0</modelVersion>
 
-	<groupId>com.github.heideltime</groupId>
-	<artifactId>heideltime</artifactId>
-	<version>2.2.1</version>
+	<groupId>ca.crim.nlp</groupId>
+	<artifactId>crim-heideltime</artifactId>
+	<version>3.0.8-SNAPSHOT</version>
 
 	<name>HeidelTime</name>
-	<description>HeidelTime is a multilingual cross-domain temporal tagger that extracts temporal expressions from documents and normalizes them according to the TIMEX3 annotation standard.</description>
-	<url>https://github.com/HeidelTime/heideltime/</url>
+	<description> This version of HeidelTime extends the well-known multilingual cross-domain temporal tagger (com.github.hiedltime) that extracts temporal expressions from documents and normalizes them according to the TIMEX3 annotation standard.</description>
+	<url>https://github.com/reboutli-crim/heideltime</url>
 
 	<licenses>
 		<license>
@@ -18,7 +18,7 @@
 	</licenses>
 
 	<issueManagement>
-		<url>https://github.com/HeidelTime/heideltime/issues</url>
+		<url>https://github.com/reboutli-crim/heideltime/issues</url>
 		<system>GitHub</system>
 	</issueManagement>
 
@@ -39,16 +39,22 @@
 			<email>[email protected]</email>
 			<url>https://github.com/jzell</url>
 		</developer>
+		<developer>
+			<id>reboutli-crim</id>
+			<name>Lise Rebout</name>
+			<email>[email protected]</email>
+			<url>https://github.com/reboutli-criml</url>
+		</developer>
 	</developers>
 
 	<scm>
-		<url>https://github.com/HeidelTime/heideltime</url>
-		<connection>scm:git:[email protected]:HeidelTime/heideltime.git</connection>
-		<developerConnection>scm:git:[email protected]:HeidelTime/heideltime.git</developerConnection>
+		<url>https://github.com/reboutli-crim/heideltime</url>
+		<connection>scm:git:[email protected]:reboutli-crim/heideltime.git</connection>
+		<developerConnection>scm:git:[email protected]:reboutli-crim/heideltime.git</developerConnection>
 	</scm>
 
 	<build>
-		<sourceDirectory>src</sourceDirectory>
+		<sourceDirectory>src/main/java</sourceDirectory>
 		<outputDirectory>${basedir}/class</outputDirectory>
 		<resources>
 			<resource>
@@ -58,13 +64,12 @@
 				</includes>
 			</resource>
 			<resource>
-				<directory>resources/</directory>
+				<directory>src/main/resources/</directory>
 				<includes>
 					<include>**/*.txt</include>
 				</includes>
 			</resource>
 		</resources>
-		<finalName>de.unihd.dbs.heideltime.standalone</finalName>
 		<plugins>
 			<plugin>
 				<artifactId>maven-compiler-plugin</artifactId>
@@ -107,22 +112,6 @@
 					</execution>
 				</executions>
 			</plugin>
-			<plugin>
-				<groupId>org.apache.maven.plugins</groupId>
-				<artifactId>maven-source-plugin</artifactId>
-				<version>2.2.1</version>
-				<configuration>
-					<excludeResources>true</excludeResources>
-				</configuration>
-				<executions>
-					<execution>
-						<id>attach-sources</id>
-						<goals>
-							<goal>jar-no-fork</goal>
-						</goals>
-					</execution>
-				</executions>
-			</plugin>
 			<plugin>
 				<groupId>org.apache.maven.plugins</groupId>
 				<artifactId>maven-javadoc-plugin</artifactId>
@@ -139,52 +128,15 @@
 					</execution>
 				</executions>
 			</plugin>
-			<plugin>
-				<groupId>org.apache.maven.plugins</groupId>
-				<artifactId>maven-gpg-plugin</artifactId>
-				<version>1.5</version>
-				<executions>
-					<execution>
-						<id>sign-artifacts</id>
-						<phase>verify</phase>
-						<goals>
-							<goal>sign</goal>
-						</goals>
-					</execution>
-				</executions>
-			</plugin>
-			<plugin>
-				<groupId>org.sonatype.plugins</groupId>
-				<artifactId>nexus-staging-maven-plugin</artifactId>
-				<version>1.6.3</version>
-				<extensions>true</extensions>
-				<configuration>
-					<serverId>ossrh</serverId>
-					<nexusUrl>https://oss.sonatype.org/</nexusUrl>
-					<autoReleaseAfterClose>false</autoReleaseAfterClose>
-				</configuration>
-			</plugin>
 		</plugins>
 	</build>
 
-	<distributionManagement>
-		<snapshotRepository>
-			<id>ossrh</id>
-			<url>https://oss.sonatype.org/content/repositories/snapshots</url>
-		</snapshotRepository>
-		<repository>
-			<id>ossrh</id>
-			<url>https://oss.sonatype.org/service/local/staging/deploy/maven2</url>
-		</repository>
-	</distributionManagement>
-
 	<dependencies>
 		<!-- for practically every component -->
 		<dependency>
 			<groupId>org.apache.uima</groupId>
 			<artifactId>uimaj-core</artifactId>
 			<version>2.8.1</version>
-			<scope>provided</scope>
 		</dependency>
 		<!-- for the StanfordPOSTaggerWrapper -->
 		<dependency>
@@ -193,6 +145,25 @@
 			<version>3.3.1</version>
 			<scope>provided</scope>
 		</dependency>
+		<!-- for the JsonPOSTagger -->
+		<dependency>
+		    <groupId>com.googlecode.json-simple</groupId>
+		    <artifactId>json-simple</artifactId>
+		    <version>1.1.1</version>
+		</dependency>
+		<!-- for the JsonResultWritter -->
+		<dependency>
+			<groupId>org.apache.uima</groupId>
+			<artifactId>uimaj-json</artifactId>
+			<version>2.8.1</version>
+		</dependency>
+		<!-- For the Python POSTAger -->
+		<dependency>
+    		<groupId>org.python</groupId>
+   			 <artifactId>jython-standalone</artifactId>
+   			 <version>2.7.1b2</version>
+   			 <scope>provided</scope>
+		</dependency>		
 		<!-- these are for JVnTextPro -->
 		<dependency>
 			<groupId>args4j</groupId>
@@ -206,5 +177,18 @@
 			<version>0.1</version>
 			<scope>provided</scope>
 		</dependency>
+		<!-- For testing -->
+		<dependency>
+    		<groupId>junit</groupId>
+    		<artifactId>junit</artifactId>
+   			<version>4.11</version>
+			<scope>test</scope>
+		</dependency>
+		<dependency>
+ 			<groupId>com.github.stefanbirkner</groupId>
+  			<artifactId>system-rules</artifactId>
+  			<version>1.16.0</version>
+  			<scope>test</scope>
+		</dependency>
 	</dependencies>
 </project>

src/de/unihd/dbs/heideltime/standalone/CLISwitch.java → src/main/java/de/unihd/dbs/heideltime/standalone/CLISwitch.java

@@ -24,6 +24,8 @@ public enum CLISwitch {
 	LOCALE		("Locale", "-locale", null),
 	POSTAGGER	("Part of Speech tagger", "-pos", POSTagger.TREETAGGER),
 	INTERVALS	("Interval Tagger", "-it"),
+	POSFILE		("Path to the JSON-file describing the POS", "-pf", null),
+	SENTENCEFILE("Path to the JSON-file describing the sentences", "-sf", null),
 	HELP		("This screen", "-h"),
 	;
 

src/de/unihd/dbs/heideltime/standalone/Config.java → src/main/java/de/unihd/dbs/heideltime/standalone/Config.java

@@ -55,6 +55,10 @@ public abstract class Config {
 	public static final String HUNPOS_PATH = "hunpos_path";
 	public static final String HUNPOS_MODEL_PATH = "hunpos_model_name";
 
+	public static final String PYTHON_SCRIPT_PATH = "python_script_path";
+
+	public static final String JSON_CONFIG_PATH = "json_config_path";
+
 	public static final String TYPESYSTEMHOME = "typeSystemHome";
 	public static final String TYPESYSTEMHOME_DKPRO = "typeSystemHome_DKPro";