Prepare to change how we do ranges, to handle different kinds of text in the cp area

git-svn-id: https://svn.apache.org/repos/asf/poi/trunk@684282 13f79535-47bb-0310-9956-ffa450edef68

src/scratchpad/src/org/apache/poi/hwpf/HWPFDocument.java

@@ -50,8 +50,10 @@ import org.apache.poi.hwpf.usermodel.*;
 public class HWPFDocument extends POIDocument
 //  implements Cloneable
 {
-  /** The FIB*/
+  /** The FIB */
   protected FileInformationBlock _fib;
+  /** And for making sense of CP lengths in the FIB */
+  protected CPSplitCalculator _cpSplit;
 
   /** main document stream buffer*/
   protected byte[] _mainStream;
@@ -177,6 +179,7 @@ public class HWPFDocument extends POIDocument
 
     // Create our FIB, and check for the doc being encrypted
     _fib = new FileInformationBlock(_mainStream);
+    _cpSplit = new CPSplitCalculator(_fib);
     if(_fib.isFEncrypted()) {
     	throw new EncryptedDocumentException("Cannot process encrypted word files!");
     }
@@ -291,8 +294,12 @@ public class HWPFDocument extends POIDocument
     return _dop;
   }
   
-  public Range getRange()
-  {
+  /**
+   * Returns the range that covers all text in the
+   *  file, including main text, footnotes, headers
+   *  and comments
+   */
+  public Range getOverallRange() {
 	  // hack to get the ending cp of the document, Have to revisit this.
 	  java.util.List text = _tpt.getTextPieces();
 	  PropertyNode p = (PropertyNode)text.get(text.size() - 1);
@@ -300,6 +307,42 @@ public class HWPFDocument extends POIDocument
       return new Range(0, p.getEnd(), this);
   }
 
+  /**
+   * Returns the range which covers the whole of the
+   *  document, but excludes any headers and footers.
+   */
+  public Range getRange() {
+	  return new Range(
+			  _cpSplit.getMainDocumentStart(), 
+			  _cpSplit.getMainDocumentEnd(), 
+			  this
+      );
+  }
+  
+  /**
+   * Returns the range which covers all the Footnotes.
+   */
+  public Range getFootnoteRange() {
+	  return new Range(
+			  _cpSplit.getFootnoteStart(), 
+			  _cpSplit.getFootnoteEnd(), 
+			  this
+      );
+  }
+  
+  /**
+   * Returns the range which covers all "Header Stories".
+   * A header story contains a header, footer, end note
+   *  separators and footnote separators. 
+   */
+  public Range getHeaderStoryRange() {
+	  return new Range(
+			  _cpSplit.getHeaderStoryStart(), 
+			  _cpSplit.getHeaderStoryEnd(), 
+			  this
+      );
+  }
+
   /**
    * Returns the character length of a document.
    * @return the character length of a document

src/scratchpad/src/org/apache/poi/hwpf/dev/HWPFLister.java

@@ -0,0 +1,52 @@
+/* ====================================================================
+   Licensed to the Apache Software Foundation (ASF) under one or more
+   contributor license agreements.  See the NOTICE file distributed with
+   this work for additional information regarding copyright ownership.
+   The ASF licenses this file to You under the Apache License, Version 2.0
+   (the "License"); you may not use this file except in compliance with
+   the License.  You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.
+==================================================================== */
+package org.apache.poi.hwpf.dev;
+
+import java.io.FileInputStream;
+
+import org.apache.poi.hwpf.HWPFDocument;
+import org.apache.poi.hwpf.model.FileInformationBlock;
+
+/**
+ * Used by developers to list out key information on a
+ *  HWPF file. End users will probably never need to
+ *  use this program.
+ */
+public class HWPFLister {
+	private HWPFDocument doc;
+	public HWPFLister(HWPFDocument doc) {
+		this.doc = doc;
+	}
+	
+	public static void main(String[] args) throws Exception {
+		if(args.length == 0) {
+			System.err.println("Use:");
+			System.err.println("   HWPFLister <filename>");
+			System.exit(1);
+		}
+		
+		HWPFLister l = new HWPFLister(
+				new HWPFDocument(new FileInputStream(args[0]))
+		);
+		l.dumpFIB();
+	}
+	
+	public void dumpFIB() throws Exception {
+		FileInformationBlock fib = doc.getFileInformationBlock();
+		System.out.println(fib.toString());
+	}
+}

src/scratchpad/src/org/apache/poi/hwpf/model/CPSplitCalculator.java

@@ -0,0 +1,79 @@
+/* ====================================================================
+   Licensed to the Apache Software Foundation (ASF) under one or more
+   contributor license agreements.  See the NOTICE file distributed with
+   this work for additional information regarding copyright ownership.
+   The ASF licenses this file to You under the Apache License, Version 2.0
+   (the "License"); you may not use this file except in compliance with
+   the License.  You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.
+==================================================================== */
+package org.apache.poi.hwpf.model;
+
+import org.apache.poi.hwpf.HWPFDocument;
+
+/**
+ * Helper class for {@link HWPFDocument}, which figures out
+ *  where different kinds of text can be found within the
+ *  overall CP splurge.
+ */
+public class CPSplitCalculator {
+	private FileInformationBlock fib;
+	public CPSplitCalculator(FileInformationBlock fib) {
+		this.fib = fib;
+	}
+	
+	/**
+	 * Where the main document text starts. Always 0.
+	 */
+	public int getMainDocumentStart() {
+		return 0;
+	}
+	/**
+	 * Where the main document text ends. 
+	 * Given by FibRgLw97.ccpText
+	 */
+	public int getMainDocumentEnd() {
+		return fib.getCcpText();
+	}
+	
+	/**
+	 * Where the Footnotes text starts.
+	 * Follows straight on from the main text.
+	 */
+	public int getFootnoteStart() {
+		return getMainDocumentEnd();
+	}
+	/**
+	 * Where the Footnotes text ends.
+	 * Length comes from FibRgLw97.ccpFtn
+	 */
+	public int getFootnoteEnd() {
+		throw new IllegalStateException("Not yet finished!");
+//		return getFootnoteStart() +
+//			???;
+	}
+	
+	/**
+	 * Where the "Header Story" text starts.
+	 * Follows straight on from the footnotes.
+	 */
+	public int getHeaderStoryStart() {
+		return getFootnoteEnd();
+	}
+	/**
+	 * Where the "Header Story" text ends.
+	 * Length comes from FibRgLw97.ccpHdd
+	 */
+	public int getHeaderStoryEnd() {
+		throw new IllegalStateException("Not yet finished!");
+//		return getHeaderStoryStart() +
+//			???;
+	}
+}