moparisthebest/poi
1
0
Fork 0
Code Issues Pull Requests Releases 1 Wiki Activity

Support fo text extraction of footnotes, endnotes and comments in HWPF, see Bugzilla 47400

Browse Source 
git-svn-id: https://svn.apache.org/repos/asf/poi/trunk@788949 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
Yegor Kozlov 2009-06-27 10:39:51 +00:00
parent 0a044cce25
commit 12806cceaa
5 changed files with 119 additions and 23 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
src/documentation/content/xdocs/status.xml
View File

@ -33,6 +33,7 @@
<changes>
<release version="3.5-beta7" date="2009-??-??">
<action dev="POI-DEVELOPERS" type="add">47400 - Support fo text extraction of footnotes, endnotes and comments in HWPF</action>
<action dev="POI-DEVELOPERS" type="fix">47415 - Fixed PageSettingsBlock to allow multiple PLS records</action>
<action dev="POI-DEVELOPERS" type="fix">47412 - Fixed concurrency issue with EscherProperties.initProps()</action>
<action dev="POI-DEVELOPERS" type="fix">47143 - Fixed OOM in HSSFWorkbook#getAllPictures when reading .xls files containing metafiles</action>

22
src/scratchpad/src/org/apache/poi/hwpf/HWPFDocument.java
View File

@ -344,6 +344,28 @@ public final class HWPFDocument extends POIDocument
);
}
/**
* Returns the range which covers all the Endnotes.
*/
public Range getEndnoteRange() {
return new Range(
_cpSplit.getEndNoteStart(),
_cpSplit.getEndNoteEnd(),
this
);
}
/**
* Returns the range which covers all the Endnotes.
*/
public Range getCommentsRange() {
return new Range(
_cpSplit.getCommentsStart(),
_cpSplit.getCommentsEnd(),
this
);
}
/**
* Returns the range which covers all "Header Stories".
* A header story contains a header, footer, end note

71
src/scratchpad/src/org/apache/poi/hwpf/extractor/WordExtractor.java
View File

@ -22,6 +22,7 @@ import java.io.InputStream;
import java.io.FileInputStream;
import java.io.UnsupportedEncodingException;
import java.util.Iterator;
import java.util.Arrays;
import org.apache.poi.POIOLE2TextExtractor;
import org.apache.poi.hwpf.HWPFDocument;
@ -95,34 +96,58 @@ public final class WordExtractor extends POIOLE2TextExtractor {
* Get the text from the word file, as an array with one String
* per paragraph
*/
public String[] getParagraphText() {
String[] ret;
public String[] getParagraphText() {
String[] ret;
// Extract using the model code
try {
Range r = doc.getRange();
// Extract using the model code
try {
Range r = doc.getRange();
ret = new String[r.numParagraphs()];
for(int i=0; i<ret.length; i++) {
Paragraph p = r.getParagraph(i);
ret[i] = p.text();
ret = getParagraphText(r);
} catch (Exception e) {
// Something's up with turning the text pieces into paragraphs
// Fall back to ripping out the text pieces
ret = new String[1];
ret[0] = getTextFromPieces();
}
// Fix the line ending
if(ret[i].endsWith("\r")) {
ret[i] = ret[i] + "\n";
}
}
} catch(Exception e) {
// Something's up with turning the text pieces into paragraphs
// Fall back to ripping out the text pieces
ret = new String[1];
ret[0] = getTextFromPieces();
}
return ret;
}
return ret;
}
public String[] getFootnoteText() {
Range r = doc.getFootnoteRange();
/**
return getParagraphText(r);
}
public String[] getEndnoteText() {
Range r = doc.getEndnoteRange();
return getParagraphText(r);
}
public String[] getCommentsText() {
Range r = doc.getCommentsRange();
return getParagraphText(r);
}
private String[] getParagraphText(Range r) {
String[] ret;
ret = new String[r.numParagraphs()];
for (int i = 0; i < ret.length; i++) {
Paragraph p = r.getParagraph(i);
ret[i] = p.text();
// Fix the line ending
if (ret[i].endsWith("\r")) {
ret[i] = ret[i] + "\n";
}
}
return ret;
}
/**
* Add the header/footer text, if it's not empty
*/
private void appendHeaderFooter(String text, StringBuffer out) {

BIN
src/scratchpad/testcases/org/apache/poi/hwpf/data/footnote.doc Executable file
View File

Binary file not shown.

48
src/scratchpad/testcases/org/apache/poi/hwpf/extractor/TestWordExtractor.java
View File

@ -60,6 +60,8 @@ public final class TestWordExtractor extends TestCase {
private String filename4;
// With unicode header and footer
private String filename5;
// With footnote
private String filename6;
protected void setUp() throws Exception {
String dirname = System.getProperty("HWPF.testdata.path");
@ -70,6 +72,7 @@ public final class TestWordExtractor extends TestCase {
filename3 = pdirname + "/excel_with_embeded.xls";
filename4 = dirname + "/ThreeColHeadFoot.doc";
filename5 = dirname + "/HeaderFooterUnicode.doc";
filename6 = dirname + "/footnote.doc";
extractor = new WordExtractor(new FileInputStream(filename));
extractor2 = new WordExtractor(new FileInputStream(filename2));
@ -226,4 +229,49 @@ public final class TestWordExtractor extends TestCase {
text.indexOf("The footer, with") > -1
);
}
public void testFootnote() throws Exception {
HWPFDocument doc = new HWPFDocument(
new FileInputStream(filename6)
);
extractor = new WordExtractor(doc);
String[] text = extractor.getFootnoteText();
StringBuffer b = new StringBuffer();
for (int i=0; i<text.length; i++) {
b.append(text[i]);
}
assertTrue(b.toString().contains("TestFootnote"));
}
public void testEndnote() throws Exception {
HWPFDocument doc = new HWPFDocument(
new FileInputStream(filename6)
);
extractor = new WordExtractor(doc);
String[] text = extractor.getEndnoteText();
StringBuffer b = new StringBuffer();
for (int i=0; i<text.length; i++) {
b.append(text[i]);
}
assertTrue(b.toString().contains("TestEndnote"));
}
public void testComments() throws Exception {
HWPFDocument doc = new HWPFDocument(
new FileInputStream(filename6)
);
extractor = new WordExtractor(doc);
String[] text = extractor.getCommentsText();
StringBuffer b = new StringBuffer();
for (int i=0; i<text.length; i++) {
b.append(text[i]);
}
assertTrue(b.toString().contains("TestComment"));
}
}