Changeset 5193

Timestamp:

Nov 27, 2009, 2:06:17 PM (14 years ago)

Author:

Nicklas Nordborg

Message:

References #1444: Implement generic BFS writers and readers/parsers

Implemented writers and parsers for metadata and annotation files. I am not 100% sure the event system for getting the data out is flexible enough.

Location:

trunk/src

Files:

• core/net/sf/basedb/util/bfs (added)
• core/net/sf/basedb/util/bfs/AnnotationParser.java (added)
• core/net/sf/basedb/util/bfs/AnnotationWriter.java (added)
• core/net/sf/basedb/util/bfs/EventHandler.java (added)
• core/net/sf/basedb/util/bfs/EventType.java (added)
• core/net/sf/basedb/util/bfs/MetadataModel.java (added)
• core/net/sf/basedb/util/bfs/MetadataParser.java (added)
• core/net/sf/basedb/util/bfs/MetadataWriter.java (added)
• core/net/sf/basedb/util/encode/TabCrLfEncoderDecoder.java (modified) (5 diffs)
• core/net/sf/basedb/util/export/TableWriter.java (modified) (1 diff)
• core/net/sf/basedb/util/parser/FlatFileParser.java (modified) (8 diffs)
• test/TestAll.java (modified) (1 diff)
• test/TestBfs.java (added)
• test/TestEncoderDecoder.java (modified) (1 diff)

trunk/src/core/net/sf/basedb/util/encode/TabCrLfEncoderDecoder.java

@@ -26 +26 @@
   tab and backslash with \n, \r, \t and \\. This encoder is suitable for use with
   tab-separated text files.
+  
   @author Nicklas
   @since 2.15
@@ -33 +34 @@
 {
 
-  public TabCrLfEncoderDecoder()
-  {}
+  private final boolean nullIsEmptyString;
+  
+  /**
+    Creates a new encoder/decoder.
+    @param nullIsEmptyString TRUE to encode null as empty string,
+      FALSE to not encode null. NOTE! If TRUE, this encoder is no
+      longer symmetrical
+  */
+  public TabCrLfEncoderDecoder(boolean nullIsEmptyString)
+  {
+    this.nullIsEmptyString = nullIsEmptyString;
+  }
   
   /*
@@ -43 +54 @@
   public boolean isSymmetrical() 
   {
-    return true;
+    return !nullIsEmptyString;
   }
 
@@ -50 +61 @@
   {
     if (s == null) return null;
+    if (s.length() == 0) return nullIsEmptyString ? null : s;
     boolean neededDecode = false;
     StringBuilder sb = new StringBuilder(s.length());
@@ -97 +109 @@
   public String encode(String s) 
   {
-    if (s == null) return null;
+    if (s == null) return nullIsEmptyString ? "" : null;
     boolean neededEncode = false;
     StringBuilder sb = new StringBuilder(s.length());

trunk/src/core/net/sf/basedb/util/export/TableWriter.java

@@ -169 +169 @@
       first = false;
     }
-    println();
+    print("\n");
   }
   

trunk/src/core/net/sf/basedb/util/parser/FlatFileParser.java

@@ -181 +181 @@
   
   /**
+    The regular expression for matching the beginning-of-file marker
+  */
+  private Pattern bofMarker;
+  
+  /**
     The regular expression for matching a header line.
   */
@@ -263 +268 @@
   
   /**
+    The value that was captured by the bofMarker pattern.
+  */
+  private String bofType;
+  
+  /**
     List of lines parsed by the {@link #parseHeaders()} method.
   */
@@ -335 +345 @@
   }
 
+  /**
+    Set a regular expression that maches a beginning-of-file
+    marker. This property should be set before starting to parse
+    the file (otherwise it is ignored). The first method call that
+    causes the parsing to be started will invoke {@link #parseToBof()} 
+    (can also be invoked manually).
+    <p>
+    The regular expression may contain a single capturing group. The
+    matched value is returned by {@link #getBofType()}.
+    
+    @param regexp A regular expression
+    @since 2.15
+  */
+  public void setBofMarkerRegexp(Pattern regexp)
+  {
+    this.bofMarker = regexp;
+  }
+  
   /**
     Set a regular expression that can be matched against a header.
@@ -537 +565 @@
   }
 
+  /**
+    Parse the file until the beginning-of-file marker is found. If no 
+    regular expression has been set with {@link #setBofMarkerRegexp(Pattern)}
+    or if the parsing of the file has already started, this method call is 
+    ignored. 
+    
+    @return TRUE if this call resulted in parsing and the BOF marker was found,
+      FALSE otherwise
+    @since 2.15
+  */
+  public boolean parseToBof()
+    throws IOException
+  {
+    if (bofMarker == null || parsedLines > 0) return false;
+    
+    boolean done = false;
+    boolean matched = false;
+    while (!done)
+    {
+      ThreadSignalHandler.checkInterrupted();
+      String line = reader.readLine();
+      parsedLines++;
+      if (line == null)
+      {
+        done = true;
+      }
+      else
+      {
+        parsedCharacters += line.length(); 
+        Matcher m = bofMarker.matcher(line);
+        if (m.matches())
+        {
+          bofType = m.groupCount() > 0 ? m.group(1) : m.group();
+          matched = true;
+          done = true;
+        }
+      }
+    }
+    return matched;
+  }
+  
+  /**
+    Get the value captured by the BOF marker regular expression. If
+    no capturing groups was specified in the pattern this value is the
+    string that matched the entire pattern.
+    
+    @return The matched value, or null if BOF matching has not been done
+    @since 2.15
+  */
+  public String getBofType()
+  {
+    return bofType;
+  }
+  
   /**
     Start parsing the input stream. The parser will read a single
@@ -583 +665 @@
     throws IOException
   {
+    if (parsedLines == 0) parseToBof();
     lines = new ArrayList<Line>(maxUnknownLines);
     headers = new HashMap<String,String>();
-    if (dataSplitter == null) return LineType.UNKNOWN;
 
     nextData = null;
@@ -1031 +1113 @@
     if (nextData == null && nextSection == null)
     {
+      if (parsedLines == 0) parseToBof();
       ignoredLines = 0;
       unknownLines = 0;
@@ -1267 +1350 @@
     if (nextSection == null)
     {
+      if (parsedLines == 0) parseToBof();
       boolean done = false;
       while (!done)
@@ -1561 +1645 @@
         nullIsNull && "NULL".equalsIgnoreCase(value) ? null : value;
     }
+    
+    /**
+      The data line as an array of strings.
+      @since 2.15
+    */
+    public String[] data()
+    {
+      return result;
+    }
   }
   

trunk/src/test/TestAll.java

@@ -132 +132 @@
     results.put("TestJep", TestJep.test_all());
     results.put("TestEncoderDecoder", TestEncoderDecoder.test_all());
+    results.put("TestBfs", TestBfs.test_all());
     results.put("TestDbInfo", TestDbInfo.test_all());
     results.put("TestPresets", TestPresets.test_all());

trunk/src/test/TestEncoderDecoder.java

@@ -40 +40 @@
   {
     write("++Testing string encode/decode");
-    EncoderDecoder tabCrLf = new TabCrLfEncoderDecoder();
+    EncoderDecoder tabCrLf = new TabCrLfEncoderDecoder(false);
     test_code(tabCrLf, "nothingtocode", "nothingtocode");
     test_code(tabCrLf, "a\tb\nc\rd\\e", "a\\tb\\nc\\rd\\\\e");