Java Examples

https://trac.xapian.org/ticket/716

Converting Python examples to Java

Examples converted:
* index1.py
* search1.py
* delete1.py

ToDo:
* index_ranges.py
* index_filters.py
* index_sorting.py
* search_filters.py
* search_ranges.py
* search_sorting.py

code/java/delete1.java

@@ -0,0 +1,34 @@
+package code.java;
+
+import org.xapian.WritableDatabase;
+import org.xapian.XapianConstants;
+
+public class delete1 {
+
+    // Command line args - dbpath identifiers...
+    public static void main(String[] args)
+    {
+        if(args.length < 2)
+        {
+            System.out.println("Insufficient number of arguments (should be dbpath identifiers...)");
+            return;
+        }
+        deleteDocs(args[0], args);
+    }
+
+    public static void deleteDocs(String dbpath, String[] identifierArgs)
+    {
+        // Open the database we're going to be deleting from.
+        WritableDatabase db = new WritableDatabase(dbpath, XapianConstants.DB_OPEN);
+
+        // Identifiers start from index 1
+        for(int i=1; i < identifierArgs.length; i++)
+        {
+            String idterm = "Q" + identifierArgs[i];
+            db.deleteDocument(idterm);
+        }
+
+        // Commit to delete documents from disk
+        db.commit();
+    }
+}

code/java/index1.java

@@ -0,0 +1,103 @@
+package code.java;
+
+import java.io.File;
+import java.io.FileNotFoundException;
+import java.util.Scanner;
+import java.util.logging.Level;
+import java.util.logging.Logger;
+import org.xapian.Document;
+import org.xapian.Stem;
+import org.xapian.TermGenerator;
+import org.xapian.WritableDatabase;
+import org.xapian.XapianConstants;
+import org.xapian.XapianJNI;
+
+public class index1 {
+
+    // Command line args - dbpath datapath
+    public static void main(String[] args)
+    {
+        if(args.length < 2)
+        {
+            System.out.println("Insufficient number of arguments (should be dbpath datapath)");
+            return;
+        }
+        index(args[0], args[1]);
+    }
+
+    public static void index(String dbpath, String datapath)
+    {
+        // Create or open the database we're goign to be writing to.
+        WritableDatabase db = new WritableDatabase(dbpath, XapianConstants.DB_CREATE_OR_OPEN);
+        // Set up a TermGenerator that we'll use in indexing.
+        TermGenerator termGenerator = new TermGenerator();
+        termGenerator.setStemmer(new Stem("en"));
+
+        //Parsing the CSV input file
+        Scanner csvScanner,lineScanner;        
+        csvScanner = lineScanner = null;
+
+        try {
+            File csv = new File(datapath);
+            csvScanner = new Scanner(csv);
+        } catch (FileNotFoundException ex) {
+        	Logger.getLogger(index1.class.getName()).log(Level.SEVERE, null, ex);
+        }
+
+        // Ignoring first line (contains descriptors)
+        csvScanner.nextLine();
+
+        while(csvScanner.hasNextLine())
+        {
+            String currentLine = csvScanner.nextLine();
+            lineScanner = new Scanner(currentLine);
+            lineScanner.useDelimiter(",");
+
+            /* Parsing each line for identifier, title, and description */
+
+            // Identifier is the first comma seperated value (according to CSV file)
+            String identifier = lineScanner.next();
+
+            // Title is third comma seperated value
+            lineScanner.next();
+            String title = lineScanner.next();
+
+            // Description is ninth comma sperated value
+            for(int i=0;i<5;i++)
+                   lineScanner.next();
+            String description = lineScanner.next();
+
+            /* Finished Parsing line */
+
+            // We make a document and tell the term generator to use this.
+            Document doc = new Document();
+            termGenerator.setDocument(doc);
+
+            // Index each field with a suitable prefix.
+            termGenerator.indexText(title, 1, "S");
+            termGenerator.indexText(description, 1, "XD");
+
+            // Index fields without prefixes for general search.
+            termGenerator.indexText(title);
+            termGenerator.increaseTermpos();
+            termGenerator.indexText(description);
+
+            // Store all fields for display purposes
+            doc.setData(currentLine);
+            doc.addValue(0, title);
+
+            // We use the identifier to ensure each object ends up in the
+            // database only once no matter how many times we run the
+            // indexer.
+            String idterm = "Q"+identifier;
+            doc.addBooleanTerm(idterm);
+            db.replaceDocument(idterm, doc);
+        }
+
+        // Commit to write documents to disk
+        db.commit();
+
+        lineScanner.close();
+        csvScanner.close();        
+    }
+}

code/java/search1.java

@@ -0,0 +1,70 @@
+package code.java;
+
+import org.xapian.Database;
+import org.xapian.Document;
+import org.xapian.Enquire;
+import org.xapian.MSet;
+import org.xapian.MSetIterator;
+import org.xapian.Query;
+import org.xapian.QueryParser;
+import org.xapian.Stem;
+
+public class search1 {
+
+    // Command line args - dbpath querystring
+    public static void main(String[] args)
+    {
+        if(args.length < 2)
+        {
+            System.out.println("Insufficient number of arguments (should be dbpath querystring)");
+            return;
+        }
+        search(args[0], args[1]);
+    }
+
+    public static void search(String dbpath, String queryString)
+    {
+        search(dbpath, queryString, 0, 10);
+    }
+
+    public static void search(String dbpath, String queryString, int offset, int pagesize)
+    {
+        // offset - defines starting point within result set
+        // pagesize - defines number of records to retrieve
+
+        // Open the databse we're going to search.
+        Database db = new Database(dbpath);
+
+        // Set up a QueryParser with a stemmer and suitable prefixes
+        QueryParser queryParser = new QueryParser();
+        queryParser.setStemmer(new Stem("en"));
+        queryParser.setStemmingStrategy(QueryParser.stem_strategy.STEM_SOME);
+        // Start of prefix configuration.
+        queryParser.addPrefix("title", "S");
+        queryParser.addPrefix("description", "XD");
+        // End of prefix configuration.
+
+        // And parse the query
+        Query query = queryParser.parseQuery(queryString);
+
+        // Use an Enquire object on the database to run the query
+        Enquire enquire = new Enquire(db);
+        enquire.setQuery(query);
+
+        // And print out something about each match
+        MSet mset= enquire.getMSet(offset, pagesize);
+        MSetIterator msetIterator = mset.begin();
+
+        while(msetIterator.hasNext())
+        {
+            long rank = msetIterator.getRank();
+            long docID = msetIterator.getDocId();
+            Document doc = db.getDocument(docID);
+            String title = doc.getValue(0);
+
+            System.out.println((rank+1)+": #"+docID+" "+title);
+            msetIterator.next();
+        }
+
+    }
+}

code/java/search1.java.out

@@ -0,0 +1,2 @@
+1: #001 Ansonia Sunwatch (pocket compas dial)
+INFO:xapian.search:'title:sunwatch'[0:10] = 1