Fixed graph error

.classpath

@@ -0,0 +1,11 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<classpath>
+	<classpathentry kind="src" path=""/>
+	<classpathentry kind="con" path="org.scala-ide.sdt.launching.SCALA_CONTAINER"/>
+	<classpathentry kind="con" path="org.eclipse.jdt.launching.JRE_CONTAINER"/>
+	<classpathentry kind="lib" path="C:/lib/breeze/dlwh-breeze-feca1cf/target/scala-2.9.2/breeze_2.9.2-0.1-SNAPSHOT.jar"/>
+	<classpathentry kind="lib" path="C:/lib/breeze/dlwh-breeze-feca1cf/math/target/scala-2.9.2/breeze-math_2.9.2-0.1-SNAPSHOT.jar" sourcepath="C:/lib/breeze/dlwh-breeze-feca1cf/math/src"/>
+	<classpathentry kind="lib" path="C:/lib/breeze/dlwh-breeze-feca1cf/learn/target/scala-2.9.2/breeze-learn_2.9.2-0.1-SNAPSHOT.jar"/>
+	<classpathentry kind="lib" path="C:/lib/breeze/dlwh-breeze-feca1cf/process/target/breeze-process-assembly-0.1-SNAPSHOT.jar" sourcepath="C:/lib/breeze/dlwh-breeze-feca1cf/process/src/main/scala/breeze"/>
+	<classpathentry kind="output" path="bin"/>
+</classpath>

.project

@@ -0,0 +1,18 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<projectDescription>
+	<name>PapersProject</name>
+	<comment></comment>
+	<projects>
+	</projects>
+	<buildSpec>
+		<buildCommand>
+			<name>org.scala-ide.sdt.core.scalabuilder</name>
+			<arguments>
+			</arguments>
+		</buildCommand>
+	</buildSpec>
+	<natures>
+		<nature>org.scala-ide.sdt.core.scalanature</nature>
+		<nature>org.eclipse.jdt.core.javanature</nature>
+	</natures>
+</projectDescription>

README.txt

@@ -0,0 +1,15 @@
+COMPILATION
+
+In order to correctly compile and execute Trail Head, use sbt or anything you want.
+The only important thing is that the repository containing the final executable file must also contain:
+- the "tools" dossier
+- the "cache" dossier
+- the "pdf2xml.dtd" file
+
+
+
+EXECUTION
+
+When you start the program, after providing the input path, if at that location there isn't any "schedule.xml", an exception will be rised. Since this wasn't part of my tasksand I don't exactly know how this works, I didn't touch at that code part. 
+However, the parsing has been completed before the exception.
+If you don't want this annoying exception, just comment the code after the parsing process.

build.sbt

@@ -2,12 +2,24 @@ name := "Parsing papers"
 
 version := "1.0"
 
-scalaVersion := "2.9.1"
+scalaVersion := "2.9.2"
 
 scalaSource in Compile <<= baseDirectory(_ / "src/paper")
 
 scalacOptions ++= Seq("-unchecked", "-Ywarn-dead-code", "-deprecation")
 
+libraryDependencies  ++= Seq(
+            // other dependencies here
+            // pick and choose:
+            "org.scalanlp" %% "breeze-process" % "0.1"
+)
+
+resolvers ++= Seq(
+            // other resolvers here
+            // if you want to use snapshot builds (currently 0.2-SNAPSHOT), use this.
+            "Sonatype Snapshots" at "https://oss.sonatype.org/content/repositories/snapshots/"
+)
+
 initialCommands := """
   import System.{currentTimeMillis => now}
   def time[T](f: => T): T = {

pdf2xml.dtd

@@ -0,0 +1,28 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!ELEMENT pdf2xml (page+)>
+<!ELEMENT page (fontspec*, text*)>
+<!ATTLIST page
+	number CDATA #REQUIRED
+	position CDATA #REQUIRED
+	top CDATA #REQUIRED
+	left CDATA #REQUIRED
+	height CDATA #REQUIRED
+	width CDATA #REQUIRED
+>
+<!ELEMENT fontspec EMPTY>
+<!ATTLIST fontspec
+	id CDATA #REQUIRED
+	size CDATA #REQUIRED
+	family CDATA #REQUIRED
+	color CDATA #REQUIRED
+>
+<!ELEMENT text (#PCDATA | b | i)*>
+<!ATTLIST text
+	top CDATA #REQUIRED
+	left CDATA #REQUIRED
+	width CDATA #REQUIRED
+	height CDATA #REQUIRED
+	font CDATA #REQUIRED
+>
+<!ELEMENT b (#PCDATA)>
+<!ELEMENT i (#PCDATA)>

src/paper/Analyze.scala

@@ -1,56 +1,118 @@
 package paper
 
 object Analyze {
-  def main(args : Array[String]): Unit = {
-
-    // create analyse
+  def main(args : Array[String]): Unit= {
+    // create analyzer
     val A : Analyzer = new Analyzer()
 
     // Check that a directory is supplied (there is an argument)
-    if (args.length == 0) println("You really need to supply a directory as argument");
+    if (args.length == 0 || args.length > 2) {
+      println("You should provide at least a path and at most a path and an option. Type -h for help.");
+    }
+
+    else {
+      val options = readOptions(args.last)
 
-    // Then go ahead
-    else A.analyze(args(0))
+      // Then go ahead
+      A.analyze(args(0), options)
+    }
+  }
+
+  // Reads in the options and converts them to a map of options
+  def readOptions(s : String) : Map[String,Boolean] = {
+
+    var options : Map[String,Boolean] = Map();
+
+    if (s.length > 0 && s(0) == '-') {
+      // Define options as always false, except
+      options = Map().withDefaultValue(false)
+
+      // Check for parsing
+      if (s.contains('p')) options += ("parse" -> true)
+
+      // Check for getting schedule
+      if (s.contains('s')) options += ("xmlschedule" -> true)
+
+      // Check for extending
+      if (s.contains('e')) options += ("extend" -> true)
+
+      // Check for linking
+      if (s.contains('l')) options += ("link" -> true)
+
+      // Check for linking
+      if (s.contains('g')) options += ("graph" -> true)
+
+      if(s.contains('h')) { 
+        println("""How to call: Analyze [path] 
+        [parameter]?\nPARAMETERS:\n\t-p : parsing\n\t-s : looks for xml 
+        scheduler\n\t-c : compare\n\t-l : link\n\t-g : create graph\n\t-h 
+        : shows this help page\n\tnothing : do everything"""); 
+      }
+
+    }
+
+    else {
+      // If no options are supplied we do everything by default
+      options = Map().withDefaultValue(true)
+    }
+
+    return options
   }
 }
 
+
+
 class Analyzer extends Object with LoadPaper
                               with ParsePaper 
                               with ExtendPaper
-                              with ComparePaper
+                              with BagOfWordsLSI
                               with XMLScheduleParser
                               with Graphs {
 
   // Set a limit in percent for when papers get an edge between them
   val limit : Int = 1
 
   // Get cached papers in this order
-  val cache : List[String] = List(Cache.extended, Cache.linked, Cache.scheduled, Cache.parsed)
+  val cache : List[String] = List(Cache.linked, Cache.extended, Cache.scheduled, Cache.parsed)
 
   // Set sources we want to extend with
   //val sources : List[PaperSource] = List(TalkDates, TalkRooms, PdfLink)
   val sources : List[PaperSource] = List(PdfLink)
 
   // Analyze a paper
-  def analyze(paperPos: String): Unit = {
+  def analyze(paperPos: String, options: Map[String, Boolean]): List[Paper] = {
+
+    var papers : List[Paper] = List();
 
     // Get a list of parsed papers
-    val papers : List[Paper] = load(paperPos, cache, Isit)
+    if (options("parse") == true) {
+      papers = loadAndParse(paperPos, cache, XMLParser, XMLConverterLoader)
+    }
 
     // Mix in the schedule XML data
-    val xmlPapers : List[Paper] = getXMLSchedule(paperPos, papers)
+    if (options("xmlschedule") == true) {
+      papers = getXMLSchedule(paperPos, papers)
+    }
+
+    // Extend papers with tertiary data
+    if (options("extend") == true) {
+      papers = extend(paperPos, papers, sources)
+    }
 
     // Compare the papers individually
-    val comparedPapers : List[Paper] = compare(xmlPapers, limit)
+    if (options("link") == true) {
+      papers = compareBoWLSI(paperPos, papers, limit)
+    }
 
-    // Extend papers with tertiary data
-    val extendedPapers : List[Paper] = extend(comparedPapers, sources) 
-
     // Create graph
-    val graph : Graph = getGraph(extendedPapers)
+    if (options("graph") == true) {
+      val graph : Graph = getGraph(paperPos, papers)
 
-    // Print graph to file 'data.json'
-    graph.save
+      // Print graph to file 'data.json'
+      graph.save
+    }
 
+    // Now return the papers as is
+    return papers
   }
 }