在这里我需要处理捕获的异常，我需要将这些 PDF 移动到我在代码“失败文件夹”中指定的文件夹中。
package extractInfoFromPDF;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileOutputStream;
import java.io.FileWriter;
import java.io.IOException;
import java.io.InputStream;
import java.io.OutputStream;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
import com.itextpdf.text.exceptions.InvalidPdfException;
import com.itextpdf.text.pdf.PdfReader;
import com.itextpdf.text.pdf.parser.PdfTextExtractor;
public class Test {
static FileWriter output = null;
public static void main(String[] args) throws IOException {
File file = new File("c:/write.txt");
output = new FileWriter(file);
PdfReader pdfArticle = null;
Pattern pattern = Pattern.compile("\\b(10[.][0-9]{4,}(?:[.][0-9]+)*/(?:(?![\"&\\'<>])\\S)+)\\b", Pattern.CASE_INSENSITIVE);
File ArticleFolder = new File("D:\\AI\\failed1");
File[] listOfArticles = ArticleFolder.listFiles();
int count = 0;
StringBuffer s = null;
for (File article : listOfArticles) {
if(!article.getName().contains("article.fulltext.000001")){
continue;
}
pdfArticle = new PdfReader(article.getAbsolutePath());
try{
s = new StringBuffer(PdfTextExtractor.getTextFromPage(pdfArticle, 1));
} catch (InvalidPdfException|StringIndexOutOfBoundsException|ArrayIndexOutOfBoundsException e) {
copyFile(article, new File ("D:\\AI\\fail"));
delete(article);
}
// System.out.println(s);
Matcher m = pattern.matcher(s);
String DOI = null;
if (m.find()) {
DOI = m.group();
}
if (DOI == null) {
Pattern pattern2 = Pattern.compile("(DOI:).*", Pattern.CASE_INSENSITIVE);
Matcher m2 = pattern2.matcher(s);
if (m2.find()) {
DOI = m2.group();
DOI=DOI.replaceAll("\\s+", "");
m = pattern.matcher(DOI);
if (m.find()) {
DOI = m.group();
}else{
DOI = "DOI-NOT-AVALIABLE";
}
}else{
DOI = "DOI-NOT-AVALIABLE";
}
}
count = count + 1;
String d[]=DOI.split(" ");
for(String d2 : d){
if(d2.contains("10.")){
DOI=d2;
}
}
DOI = DOI.replaceAll("(DOI:)(doi:)(\\s+)([\\.,;)]])", "").trim();
System.out.println(count + " TAN: " + article.getName() + " "
+ DOI);
//if(DOI.matches(""[A-Z-a-z-0-7]"))
output.write(count + " TAN: " + article.getName() + " " + DOI+"\n");
// FileUtils.writeStringToFile(new File("write.txt"), count++
// +" TAN: "+article.getName()+" "+DOI, "UTF-8");
}
output.close();
}
public static void copyFile(File source, File dest) throws IOException{
if(!dest.exists()){
dest.createNewFile();
}
InputStream in = null;
OutputStream out = null;
try{
in = new FileInputStream(source);
out = new FileOutputStream(dest);
byte[] buf = new byte[1024];
int len;
while((len = in.read(buf)) > 0){
out.write(buf, 0, len);
}
}
finally{
in.close();
out.close();
}
}
public static boolean delete(File resource) throws IOException{
if(resource.isDirectory()){
File[] childFiles = resource.listFiles();
for(File child : childFiles){
delete(child);
}
}
return resource.delete();
}
}
这是我的完整代码，下面是我得到异常的特定行。
s = new StringBuffer(PdfTextExtractor.getTextFromPage(pdfArticle, 1));
我从 1000 和 1000 的 PDF 中得到String index out of range（-1 或一些 thime 0）几个 100 的 PDF。当我谷歌它时，没有解决方案。下面是我从 iText 获得的例外情况。而不是来自我的代码。对于某些pdf，我还可以ArrayIndexOutOfBoundsException在代码中的同一行中获得（有时是397或有时是286或其他类似的3位数字）(PdfTextExtractor.getTextFromPage)（有时是 397 或有时是 286 或其他一些 3 位数字） 。
java.lang.StringIndexOutOfBoundsException: String index out of range: -1
at java.lang.String.charAt(String.java:695)
at com.itextpdf.text.pdf.parser.LocationTextExtractionStrategy.getResultantText(LocationTextExtractionStrategy.java:121)
at com.itextpdf.text.pdf.parser.PdfTextExtractor.getTextFromPage(PdfTextExtractor.java:73)
at com.itextpdf.text.pdf.parser.PdfTextExtractor.getTextFromPage(PdfTextExtractor.java:88)
at extractInfoFromPDF.Test.main(Test.java:41)
对于 ArrayIndexOutOfBoundsException 我另一个 PDF 我得到了这个异常
Exception in thread "main" java.lang.ArrayIndexOutOfBoundsException: 397
at com.itextpdf.text.pdf.CMapAwareDocumentFont.getWidth(CMapAwareDocumentFont.java:182)
at com.itextpdf.text.pdf.parser.TextRenderInfo.getStringWidth(TextRenderInfo.java:210)
at com.itextpdf.text.pdf.parser.TextRenderInfo.getUnscaledWidth(TextRenderInfo.java:113)
at com.itextpdf.text.pdf.parser.TextRenderInfo.getUnscaledBaselineWithOffset(TextRenderInfo.java:147)
at com.itextpdf.text.pdf.parser.TextRenderInfo.getBaseline(TextRenderInfo.java:122)
at com.itextpdf.text.pdf.parser.LocationTextExtractionStrategy.renderText(LocationTextExtractionStrategy.java:154)
at com.itextpdf.text.pdf.parser.PdfContentStreamProcessor.displayPdfString(PdfContentStreamProcessor.java:303)
at com.itextpdf.text.pdf.parser.PdfContentStreamProcessor.access$2500(PdfContentStreamProcessor.java:74)
at com.itextpdf.text.pdf.parser.PdfContentStreamProcessor$ShowText.invoke(PdfContentStreamProcessor.java:496)
at com.itextpdf.text.pdf.parser.PdfContentStreamProcessor.invokeOperator(PdfContentStreamProcessor.java:246)
at com.itextpdf.text.pdf.parser.PdfContentStreamProcessor.processContent(PdfContentStreamProcessor.java:366)
at com.itextpdf.text.pdf.parser.PdfReaderContentParser.processContent(PdfReaderContentParser.java:79)
at com.itextpdf.text.pdf.parser.PdfTextExtractor.getTextFromPage(PdfTextExtractor.java:73)
at com.itextpdf.text.pdf.parser.PdfTextExtractor.getTextFromPage(PdfTextExtractor.java:88)
at extractInfoFromPDF.Test.main(Test.java:41)