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

Fix a typo in the file name, and add a generic method to POITextExtractor to get the appropriate metadata text extractor

Browse Source 
git-svn-id: https://svn.apache.org/repos/asf/poi/trunk@685267 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
Nick Burch 2008-08-12 19:02:41 +00:00
parent f2d371df00
commit d60c98c37b
7 changed files with 37 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
src/documentation/content/xdocs/changes.xml
View File

@ -37,7 +37,7 @@
<!-- Don't forget to update status.xml too! -->
<release version="3.1.1-alpha1" date="2008-??-??">
<action dev="POI-DEVELOPERS" type="add">New HPSF based TextExtractor for document metadata, org.apache.poi.hpsf.extractor.HPFSPropertiesExtractor</action>
<action dev="POI-DEVELOPERS" type="add">New HPSF based TextExtractor for document metadata, org.apache.poi.hpsf.extractor.HPSFPropertiesExtractor</action>
<action dev="POI-DEVELOPERS" type="fix">Properly update the array of Slide's text runs in HSLF when new text shapes are added</action>
<action dev="POI-DEVELOPERS" type="fix">45590 - Fix for Header/footer extraction for .ppt files saved in Office 2007</action>
<action dev="POI-DEVELOPERS" type="fix">Big improvement in how HWPF handles unicode text, and more sanity checking of text ranges within HWPF</action>

2
src/documentation/content/xdocs/hpsf/how-to.xml
View File

@ -95,7 +95,7 @@
<p>If all you are interested in is getting the textual content of
all the document properties, such as for full text indexing, then
take a look at
<code>org.apache.poi.hpsf.extractor.HPFSPropertiesExtractor</code>. However,
<code>org.apache.poi.hpsf.extractor.HPSFPropertiesExtractor</code>. However,
if you want full access to the properties, please read on!</p>
<p>The first thing you should understand is that a Microsoft Office file is

2
src/documentation/content/xdocs/status.xml
View File

@ -34,7 +34,7 @@
<!-- Don't forget to update changes.xml too! -->
<changes>
<release version="3.1.1-alpha1" date="2008-??-??">
<action dev="POI-DEVELOPERS" type="add">New HPSF based TextExtractor for document metadata, org.apache.poi.hpsf.extractor.HPFSPropertiesExtractor</action>
<action dev="POI-DEVELOPERS" type="add">New HPSF based TextExtractor for document metadata, org.apache.poi.hpsf.extractor.HPSFPropertiesExtractor</action>
<action dev="POI-DEVELOPERS" type="fix">Properly update the array of Slide's text runs in HSLF when new text shapes are added</action>
<action dev="POI-DEVELOPERS" type="fix">45590 - Fix for Header/footer extraction for .ppt files saved in Office 2007</action>
<action dev="POI-DEVELOPERS" type="fix">Big improvement in how HWPF handles unicode text, and more sanity checking of text ranges within HWPF</action>

9
src/java/org/apache/poi/POIOLE2TextExtractor.java
View File

@ -18,6 +18,7 @@ package org.apache.poi;
import org.apache.poi.hpsf.DocumentSummaryInformation;
import org.apache.poi.hpsf.SummaryInformation;
import org.apache.poi.hpsf.extractor.HPSFPropertiesExtractor;
/**
* Common Parent for OLE2 based Text Extractors
@ -50,4 +51,12 @@ public abstract class POIOLE2TextExtractor extends POITextExtractor {
public SummaryInformation getSummaryInformation() {
return document.getSummaryInformation();
}
/**
* Returns an HPSF powered text extractor for the
* document properties metadata, such as title and author.
*/
public POITextExtractor getMetadataTextExtractor() {
return new HPSFPropertiesExtractor(this);
}
}

7
src/java/org/apache/poi/POITextExtractor.java
View File

@ -54,4 +54,11 @@ public abstract class POITextExtractor {
* @return All the text from the document
*/
public abstract String getText();
/**
* Returns another text extractor, which is able to
* output the textual content of the document
* metadata / properties, such as author and title.
*/
public abstract POITextExtractor getMetadataTextExtractor();
}

15
src/java/org/apache/poi/hpsf/extractor/HPFSPropertiesExtractor.java → src/java/org/apache/poi/hpsf/extractor/HPSFPropertiesExtractor.java
View File

@ -36,14 +36,14 @@ import org.apache.poi.util.LittleEndian;
* build in and custom, returning them in
* textual form.
*/
public class HPFSPropertiesExtractor extends POITextExtractor {
public HPFSPropertiesExtractor(POITextExtractor mainExtractor) {
public class HPSFPropertiesExtractor extends POITextExtractor {
public HPSFPropertiesExtractor(POITextExtractor mainExtractor) {
super(mainExtractor);
}
public HPFSPropertiesExtractor(POIDocument doc) {
public HPSFPropertiesExtractor(POIDocument doc) {
super(doc);
}
public HPFSPropertiesExtractor(POIFSFileSystem fs) {
public HPSFPropertiesExtractor(POIFSFileSystem fs) {
super(new PropertiesOnlyDocument(fs));
}
@ -127,6 +127,13 @@ public class HPFSPropertiesExtractor extends POITextExtractor {
public String getText() {
return getSummaryInformationText() + getDocumentSummaryInformationText();
}
/**
* Prevent recursion!
*/
public POITextExtractor getMetadataTextExtractor() {
throw new IllegalStateException("You already have the Metadata Text Extractor, not recursing!");
}
/**
* So we can get at the properties of any

14
src/testcases/org/apache/poi/hpsf/extractor/TestHPFSPropertiesExtractor.java → src/testcases/org/apache/poi/hpsf/extractor/TestHPSFPropertiesExtractor.java
View File

@ -25,7 +25,7 @@ import org.apache.poi.poifs.filesystem.POIFSFileSystem;
import junit.framework.TestCase;
public class TestHPFSPropertiesExtractor extends TestCase {
public class TestHPSFPropertiesExtractor extends TestCase {
private String dir;
protected void setUp() throws Exception {
@ -37,7 +37,7 @@ public class TestHPFSPropertiesExtractor extends TestCase {
POIFSFileSystem fs = new POIFSFileSystem(
new FileInputStream(new File(dir, "TestMickey.doc"))
);
HPFSPropertiesExtractor ext = new HPFSPropertiesExtractor(fs);
HPSFPropertiesExtractor ext = new HPSFPropertiesExtractor(fs);
ext.getText();
// Check each bit in turn
@ -60,7 +60,7 @@ public class TestHPFSPropertiesExtractor extends TestCase {
POIFSFileSystem fs = new POIFSFileSystem(
new FileInputStream(new File(dir, "TestUnicode.xls"))
);
HPFSPropertiesExtractor ext = new HPFSPropertiesExtractor(fs);
HPSFPropertiesExtractor ext = new HPSFPropertiesExtractor(fs);
ext.getText();
// Check each bit in turn
@ -83,7 +83,7 @@ public class TestHPFSPropertiesExtractor extends TestCase {
POIFSFileSystem fs = new POIFSFileSystem(
new FileInputStream(new File(dir, "TestMickey.doc"))
);
HPFSPropertiesExtractor ext = new HPFSPropertiesExtractor(fs);
HPSFPropertiesExtractor ext = new HPSFPropertiesExtractor(fs);
// Custom properties are part of the document info stream
String dinfText = ext.getDocumentSummaryInformationText();
@ -102,9 +102,9 @@ public class TestHPFSPropertiesExtractor extends TestCase {
HSSFWorkbook wb = new HSSFWorkbook(fs);
ExcelExtractor excelExt = new ExcelExtractor(wb);
String fsText = (new HPFSPropertiesExtractor(fs)).getText();
String hwText = (new HPFSPropertiesExtractor(wb)).getText();
String eeText = (new HPFSPropertiesExtractor(excelExt)).getText();
String fsText = (new HPSFPropertiesExtractor(fs)).getText();
String hwText = (new HPSFPropertiesExtractor(wb)).getText();
String eeText = (new HPSFPropertiesExtractor(excelExt)).getText();
assertEquals(fsText, hwText);
assertEquals(fsText, eeText);