Get most of the hwpf tests passing again

git-svn-id: https://svn.apache.org/repos/asf/poi/trunk@684322 13f79535-47bb-0310-9956-ffa450edef68

src/scratchpad/src/org/apache/poi/hwpf/extractor/WordExtractor.java

@@ -128,7 +128,7 @@ public class WordExtractor extends POIOLE2TextExtractor {
     		TextPiece piece = (TextPiece) textPieces.next();
 
     		String encoding = "Cp1252";
-    		if (piece.usesUnicode()) {
+    		if (piece.isUnicode()) {
     			encoding = "UTF-16LE";
     		}
     		try {

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

@@ -104,7 +104,6 @@ public class SectionTable
       }
       int FC = TP.getPieceDescriptor().getFilePosition();
       int offset = CP - TP.getCP();
-      if(TP.usesUnicode()) offset*=2;
       FC = FC+offset-((TextPiece)_text.get(0)).getPieceDescriptor().getFilePosition();
       return FC;
     }
@@ -120,12 +119,12 @@ public class SectionTable
 
        if (fc <= piece.getEnd())
        {
-         cp += ((fc - piece.getStart())/ (piece.usesUnicode() ? 2 : 1));
+         cp += (fc - piece.getStart());
          break;
        }
        else
        {
-         cp += ((piece.getEnd() - piece.getStart())/ (piece.usesUnicode() ? 2 : 1));
+         cp += (piece.getEnd() - piece.getStart());
        }
      }
      return cp;

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

@@ -73,9 +73,9 @@ public class TextPiece extends PropertyNode implements Comparable
   }
   
   /**
-   * @return If this text piece uses unicode
+   * @return If this text piece is unicode
    */
-   public boolean usesUnicode()
+   public boolean isUnicode()
    {
       return _usesUnicode;
    }

src/scratchpad/src/org/apache/poi/hwpf/usermodel/Range.java

@@ -239,7 +239,7 @@ public class Range
 	for (int i = _textStart; i < _textEnd; i++)
 	{
 	  TextPiece piece = (TextPiece)_text.get(i);
-	  if (piece.usesUnicode())
+	  if (piece.isUnicode())
 		  return true;
 	}
 
@@ -332,8 +332,6 @@ public class Range
     // Since this is the first item in our list, it is safe to assume that
     // _start >= tp.getStart()
     int insertIndex = _start - tp.getStart();
-	if (tp.usesUnicode())
-		insertIndex /= 2;
     sb.insert(insertIndex, text);
 
     int adjustedLength = _doc.getTextTable().adjustForInsert(_textStart, text.length());

src/scratchpad/testcases/org/apache/poi/hwpf/extractor/TestDifferentRoutes.java

@@ -87,7 +87,7 @@ public class TestDifferentRoutes extends TestCase {
     		TextPiece piece = (TextPiece) textPieces.next();
 
     		String encoding = "Cp1252";
-    		if (piece.usesUnicode()) {
+    		if (piece.isUnicode()) {
     			encoding = "UTF-16LE";
     		}
     		String text = new String(piece.getRawBytes(), encoding);

src/scratchpad/testcases/org/apache/poi/hwpf/model/TestTextPieceTable.java

@@ -118,9 +118,9 @@ public class TestTextPieceTable extends TestCase {
 		TextPiece tpB = (TextPiece)tbl.getTextPieces().get(1);
 		TextPiece tpC = (TextPiece)tbl.getTextPieces().get(2);
 		
-		assertTrue(tpA.usesUnicode());
+		assertTrue(tpA.isUnicode());
-		assertTrue(tpB.usesUnicode());
+		assertTrue(tpB.isUnicode());
-		assertTrue(tpC.usesUnicode());
+		assertTrue(tpC.isUnicode());
 		
 		assertEquals(256, tpA.characterLength());
 		assertEquals(256, tpB.characterLength());
@@ -147,9 +147,9 @@ public class TestTextPieceTable extends TestCase {
 		tpB = (TextPiece)tbl.getTextPieces().get(1);
 		tpC = (TextPiece)tbl.getTextPieces().get(2);
 		
-		assertTrue(tpA.usesUnicode());
+		assertTrue(tpA.isUnicode());
-		assertTrue(tpB.usesUnicode());
+		assertTrue(tpB.isUnicode());
-		assertTrue(tpC.usesUnicode());
+		assertTrue(tpC.isUnicode());
 		
 		assertEquals(256, tpA.characterLength());
 		assertEquals(256, tpB.characterLength());

src/scratchpad/testcases/org/apache/poi/hwpf/usermodel/TestRangeProperties.java

@@ -0,0 +1,82 @@
+/* ====================================================================
+   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.usermodel;
+
+import java.io.File;
+import java.io.FileInputStream;
+
+import org.apache.poi.hwpf.HWPFDocFixture;
+import org.apache.poi.hwpf.HWPFDocument;
+
+import junit.framework.TestCase;
+
+/**
+ * Tests to ensure that our ranges end up with
+ *  the right text in them, and the right font/styling
+ *  properties applied to them.
+ */
+public class TestRangeProperties extends TestCase {
+	private static final char page_break = (char)12;
+	
+	private static final String u_page_1 =
+		"This is a fairly simple word document, over two pages, with headers and footers.\r" +
+		"The trick with this one is that it contains some Unicode based strings in it.\r" +
+		"Firstly, some currency symbols:\r" +
+		"\tGBP - \u00a3\r" +
+        "\tEUR - \u20ac\r" +
+        "Now, we\u2019ll have some French text, in bold and big:\r" +
+        "\tMoli\u00e8re\r" +
+        "And some normal French text:\r" +
+        "\tL'Avare ou l'\u00c9cole du mensonge\r" +
+        "That\u2019s it for page one\r"
+	;
+	private static final String u_page_2 =
+		"This is page two. Les Pr\u00e9cieuses ridicules. The end.\r"
+	;
+	
+	private HWPFDocument u;
+	// TODO - a non unicode document too
+	
+	private String dirname;
+	
+	protected void setUp() throws Exception {
+		dirname = System.getProperty("HWPF.testdata.path");
+		u = new HWPFDocument(
+				new FileInputStream(new File(dirname, "HeaderFooterUnicode.doc"))
+		);
+	}
+
+	public void testUnicodeTextParagraphs() throws Exception {
+		Range r = u.getRange();
+		assertEquals(
+				u_page_1 +
+				page_break + "\r" + 
+				u_page_2,
+				r.text()
+		);
+		
+		assertEquals(
+				5,
+				r.numParagraphs()
+		);
+		
+		System.out.println(r.getParagraph(2).text());
+	}
+	public void testUnicodeStyling() throws Exception {
+		
+	}
+}