aboutsummaryrefslogtreecommitdiff
path: root/pdf-as-lib/src/main/java/at/gv/egiz/pdfas/framework/input/ExtractionStage.java
diff options
context:
space:
mode:
Diffstat (limited to 'pdf-as-lib/src/main/java/at/gv/egiz/pdfas/framework/input/ExtractionStage.java')
-rw-r--r--pdf-as-lib/src/main/java/at/gv/egiz/pdfas/framework/input/ExtractionStage.java90
1 files changed, 90 insertions, 0 deletions
diff --git a/pdf-as-lib/src/main/java/at/gv/egiz/pdfas/framework/input/ExtractionStage.java b/pdf-as-lib/src/main/java/at/gv/egiz/pdfas/framework/input/ExtractionStage.java
new file mode 100644
index 0000000..19065b0
--- /dev/null
+++ b/pdf-as-lib/src/main/java/at/gv/egiz/pdfas/framework/input/ExtractionStage.java
@@ -0,0 +1,90 @@
+/**
+ * <copyright> Copyright 2006 by Know-Center, Graz, Austria </copyright>
+ * PDF-AS has been contracted by the E-Government Innovation Center EGIZ, a
+ * joint initiative of the Federal Chancellery Austria and Graz University of
+ * Technology.
+ *
+ * Licensed under the EUPL, Version 1.1 or - as soon they will be approved by
+ * the European Commission - subsequent versions of the EUPL (the "Licence");
+ * You may not use this work except in compliance with the Licence.
+ * You may obtain a copy of the Licence at:
+ * http://www.osor.eu/eupl/
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the Licence is distributed on an "AS IS" basis,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the Licence for the specific language governing permissions and
+ * limitations under the Licence.
+ *
+ * This product combines work with different licenses. See the "NOTICE" text
+ * file for details on the various modules and licenses.
+ * The "NOTICE" text file is part of the distribution. Any derivative works
+ * that you distribute must include a readable copy of the "NOTICE" text file.
+ */
+package at.gv.egiz.pdfas.framework.input;
+
+import java.util.List;
+
+import org.apache.commons.logging.Log;
+import org.apache.commons.logging.LogFactory;
+
+import at.gv.egiz.pdfas.exceptions.ErrorCode;
+import at.gv.egiz.pdfas.exceptions.framework.VerificationFilterException;
+import at.gv.egiz.pdfas.framework.DataSourceHolder;
+import at.gv.egiz.pdfas.framework.vfilter.VerificationFilter;
+import at.gv.egiz.pdfas.framework.vfilter.VerificationFilterParameters;
+import at.gv.egiz.pdfas.impl.input.IncrementalUpdateParser;
+import at.gv.egiz.pdfas.impl.vfilter.VerificationFilterImpl;
+import at.knowcenter.wag.egov.egiz.exceptions.PDFDocumentException;
+import at.knowcenter.wag.egov.egiz.exceptions.PresentableException;
+
+/**
+ * Extracts all signatures from a given input DataSource.
+ *
+ * @author wprinz
+ */
+public class ExtractionStage
+{
+ /**
+ * The log.
+ */
+ private static final Log log = LogFactory.getLog(ExtractionStage.class);
+
+ public List extractSignatureHolders(final DataSourceHolder dataSource, VerificationFilterParameters parameters) throws PresentableException
+ {
+ if (dataSource.getDataSource() instanceof PdfDataSource)
+ {
+ PdfDataSource pdfDataSource = (PdfDataSource) dataSource.getDataSource();
+
+ PdfDataSourceHolder pdsh = new PdfDataSourceHolder(pdfDataSource);
+ List blocks = parsePdfIntoBlocks(pdsh);
+ dataSource.setDataSource(pdsh.getDataSource());
+ parameters.setBeenCorrected(pdsh.hasChanged());
+
+ VerificationFilter vf = new VerificationFilterImpl();
+ List signatures = vf.extractSignatureHolders(pdsh.getDataSource(), blocks, parameters);
+
+ return signatures;
+ }
+
+ if (dataSource.getDataSource() instanceof TextDataSource)
+ {
+ TextDataSource textDataSource = (TextDataSource) dataSource.getDataSource();
+
+ VerificationFilter vf = new VerificationFilterImpl();
+ List signatures = vf.extractSignaturHolders(textDataSource, parameters);
+
+ return signatures;
+ }
+
+ String msg = "The input DataSource is neither pdf nor text. class.name = " + dataSource.getClass().getName();
+ log.error(msg);
+ throw new VerificationFilterException(ErrorCode.DOCUMENT_CANNOT_BE_READ, msg);
+ }
+
+ protected List parsePdfIntoBlocks(PdfDataSourceHolder pdfDataSource) throws PDFDocumentException
+ {
+ List blocks = IncrementalUpdateParser.parsePdfIntoIUBlocks(pdfDataSource);
+ return blocks;
+ }
+}