/*
* Copyright 2013 Objectos, Fábrica de Software LTDA.
*
* Licensed 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 br.com.objectos.way.reports.htmltopdf;
import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;
import java.util.List;
import org.apache.pdfbox.cos.COSDocument;
import org.apache.pdfbox.pdfparser.PDFParser;
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.util.PDFTextStripper;
import com.google.common.base.Splitter;
import com.google.common.collect.ImmutableList;
/**
* @author marcio.endo@objectos.com.br (Marcio Endo)
*/
class Pdfs {
private Pdfs() {
}
public static List<String> readLines(File file) {
COSDocument cosDoc = null;
PDDocument pdDoc = null;
try {
PDFTextStripper pdfStripper = new PDFTextStripper();
pdfStripper.setStartPage(1);
pdfStripper.setEndPage(1);
FileInputStream input = new FileInputStream(file);
PDFParser parser = new PDFParser(input);
parser.parse();
cosDoc = parser.getDocument();
pdDoc = new PDDocument(cosDoc);
String text = pdfStripper.getText(pdDoc);
text = text.replaceAll("\t", " ");
Iterable<String> lines = Splitter.on("\n").split(text);
return ImmutableList.copyOf(lines);
} catch (IOException e) {
return ImmutableList.of();
} finally {
if (cosDoc != null) {
try {
cosDoc.close();
} catch (IOException e) {
}
}
if (pdDoc != null) {
try {
pdDoc.close();
} catch (IOException e) {
}
}
}
}
}