Develop Reference

pdf clown- not highlighting specific search keyword

I am using pdf-clown with pdfclown-0.2.0-HEAD.jar.I have written below code for highlighting search the keyword in Chinese language pdf file and same code is working fine with english pdf file.
import java.awt.Color;
import java.awt.Desktop;
import java.awt.geom.Rectangle2D;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.UnsupportedEncodingException;
import java.net.URL;
import java.nio.charset.Charset;
import java.util.ArrayList;
import java.util.Collection;
import java.util.Date;
import java.util.HashMap;
import java.util.List;
import java.util.Map;
import java.util.concurrent.TimeUnit;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
import java.io.BufferedInputStream;
import java.io.File;
import org.pdfclown.documents.Page;
import org.pdfclown.documents.contents.ITextString;
import org.pdfclown.documents.contents.TextChar;
import org.pdfclown.documents.contents.colorSpaces.DeviceRGBColor;
import org.pdfclown.documents.interaction.annotations.TextMarkup;
import org.pdfclown.documents.interaction.annotations.TextMarkup.MarkupTypeEnum;
import org.pdfclown.files.SerializationModeEnum;
import org.pdfclown.util.math.Interval;
import org.pdfclown.util.math.geom.Quad;
import org.pdfclown.tools.TextExtractor;
public class pdfclown2 {
private static int count;
public static void main(String[] args) throws IOException {
highlight("ebook.pdf","C:\\Users\\Downloads\\6.pdf");
System.out.println("OK");
}
private static void highlight(String inputPath, String outputPath) throws IOException {
URL url = new URL(inputPath);
InputStream in = new BufferedInputStream(url.openStream());
org.pdfclown.files.File file = null;
try {
file = new org.pdfclown.files.File("C:\\Users\\Desktop\\pdf\\test123.pdf");
Map<String, String> m = new HashMap<String, String>();
m.put("亿元或","hi");
m.put("收入亿来","hi");
System.out.println("map size"+m.size());
long startTime = System.currentTimeMillis();
// 2. Iterating through the document pages...
TextExtractor textExtractor = new TextExtractor(true, true);
for (final Page page : file.getDocument().getPages()) {
Map<Rectangle2D, List<ITextString>> textStrings = textExtractor.extract(page);
for (Map.Entry<String, String> entry : m.entrySet()) {
Pattern pattern;
String serachKey = entry.getKey();
final String translationKeyword = entry.getValue();
/*
if ((serachKey.contains(")") && serachKey.contains("("))
|| (serachKey.contains("(") && !serachKey.contains(")"))
|| (serachKey.contains(")") && !serachKey.contains("(")) || serachKey.contains("?")
|| serachKey.contains("*") || serachKey.contains("+")) {s
pattern = Pattern.compile(Pattern.quote(serachKey), Pattern.CASE_INSENSITIVE);
}
else*/
pattern = Pattern.compile(serachKey, Pattern.CASE_INSENSITIVE);
// 2.1. Extract the page text!
//System.out.println(textStrings.toString().indexOf(entry.getKey()));
// 2.2. Find the text pattern matches!
final Matcher matcher = pattern.matcher(TextExtractor.toString(textStrings));
// 2.3. Highlight the text pattern matches!
textExtractor.filter(textStrings, new TextExtractor.IIntervalFilter() {
public boolean hasNext() {
// System.out.println(matcher.find());
// if(key.getMatchCriteria() == 1){
if (matcher.find()) {
return true;
}
/*
* } else if(key.getMatchCriteria() == 2) { if
* (matcher.hitEnd()) { count++; return true; } }
*/
return false;
}
public Interval<Integer> next() {
return new Interval<Integer>(matcher.start(), matcher.end());
}
public void process(Interval<Integer> interval, ITextString match) {
// Defining the highlight box of the text pattern
// match...
System.out.println(match);
/* List<Quad> highlightQuads = new ArrayList<Quad>();
{
Rectangle2D textBox = null;
for (TextChar textChar : match.getTextChars()) {
Rectangle2D textCharBox = textChar.getBox();
if (textBox == null) {
textBox = (Rectangle2D) textCharBox.clone();
} else {
if (textCharBox.getY() > textBox.getMaxY()) {
highlightQuads.add(Quad.get(textBox));
textBox = (Rectangle2D) textCharBox.clone();
} else {
textBox.add(textCharBox);
}
}
}
textBox.setRect(textBox.getX(), textBox.getY(), textBox.getWidth(), textBox.getHeight());
highlightQuads.add(Quad.get(textBox));
}*/
List<Quad> highlightQuads = new ArrayList<Quad>();
List<TextChar> textChars = match.getTextChars();
Rectangle2D firstRect = textChars.get(0).getBox();
Rectangle2D lastRect = textChars.get(textChars.size()-1).getBox();
Rectangle2D rect = firstRect.createUnion(lastRect);
highlightQuads.add(Quad.get(rect).get(rect));
// subtype can be Highlight, Underline, StrikeOut, Squiggly
new TextMarkup(page, highlightQuads, translationKeyword, MarkupTypeEnum.Highlight);
}
public void remove() {
throw new UnsupportedOperationException();
}
});
}
}
SerializationModeEnum serializationMode = SerializationModeEnum.Standard;
file.save(new java.io.File(outputPath), serializationMode);
System.out.println("file created");
long endTime = System.currentTimeMillis();
System.out.println("seconds take for execution is:"+(endTime-startTime)/1000);
} catch (Exception e) {
e.printStackTrace();
}
finally{
in.close();
}
}
}
Kindly provide your inputs to highlight specific search keyword for non english pdf files.
I am serching the keyword in below text which is in chinese langauage.
普双套习近平修宪普京利用双套车绕开宪法装班要走普京
enter image description here

Your PDF Clown version
The PDF Clown version you retrieved here from Tymate's maven repository on github has been pushed there April 23rd, 2015. The final (as of now) check-in to the PDF Clown subversion source code repository TRUNK on sourceforge, on the other hand, is from May 27th, 2015. There actually are some 30 checkins after April 23rd, 2015. Thus, you definitely do not use the most current version of this apparently dead PDF library project.
Using the current 0.2.0 snapshot
I tested your code with the 0.2.0 development version compiled from that trunk and the result indeed is different:
It is better insofar as the highlights have the width of the sought character and are located nearer to the actual character position. There still is a bug, though, as the second and third match highlights are somewhat off.
Fixing the bug
The remaining problem actually is not related to the language of the text. It simply is a bug in the processing of one type of the PDF text drawing commands, so it can be observed in documents with text in arbitrary languages. Due to the fact that these commands nowadays are used very seldom only, though, the bug is hardly ever observed, let alone reported. Your PDF, on the other hand, makes use of that kind of text drawing commands.
The bug is in the ShowText class (package org.pdfclown.documents.contents.objects). At the end of the scan method the text line matrix in the graphics state is updated like this if the ShowText instance actually is a ShowTextToNextLine instance derived from it:
if(textScanner == null)
{
state.setTm(tm);
if(this instanceof ShowTextToNextLine)
{state.setTlm((AffineTransform)tm.clone());}
}
The text line matrix here is set to the text matrix after the move to the next line and the drawing of the text. This is wrong, it must instead be set to text matrix right after the move to the next line before the drawing of the text.
This can be fixed e.g. like this:
if(textScanner == null)
{
state.setTm(tm);
if(this instanceof ShowTextToNextLine)
state.getTlm().concatenate(new AffineTransform(1, 0, 0, 1, 0, -state.getLead()));
}
With this change in place the result looks like this:

Getting sub links of a URL using jsoup

Consider a URl www.example.com it may have plenty numbers of links ,some may be internal and other may be external.I want to get a list of all the sub links ,not even the sub-sub links but only sub link.
E.G if there are four links as follows
1)www.example.com/images/main
2)www.example.com/data
3)www.example.com/users
4)www.example.com/admin/data
Then out of the four only 2 and 3 are of use as they are sub links not the sub-sub and so on links .Is there a way to achieve it through j-soup..If this could not be achieved through j-soup then one can introduce me with some other java API.
Also note that it should be a link of the parent Url which is initially sent(i.e. www.example.com)

If i can understand a sub-link can contain one slash you can attempt with this with counting the number of slashes for example :
List<String> list = new ArrayList<>();
list.add("www.example.com/images/main");
list.add("www.example.com/data");
list.add("www.example.com/users");
list.add("www.example.com/admin/data");
for(String link : list){
if((link.length() - link.replaceAll("[/]", "").length()) == 1){
System.out.println(link);
}
}
link.length(): count the number of characters
link.replaceAll("[/]", "").length() : count the number of slashes
If the difference equal to one then right link else no.
EDIT
How will i scan the whole website for sub links?
The answer for this with the robots.txt file or Robots exclusion standard, so in this it define all the sub-links of the web site for example https://stackoverflow.com/robots.txt, so the idea is, to read this file and you can extract the sub-links from this web-site here is a piece of code that can help you :
public static void main(String[] args) throws Exception {
//Your web site
String website = "http://stackoverflow.com";
//We will read the URL https://stackoverflow.com/robots.txt
URL url = new URL(website + "/robots.txt");
//List of your sub-links
List<String> list;
//Read the file with BufferedReader
try (BufferedReader in = new BufferedReader(new InputStreamReader(url.openStream()))) {
String subLink;
list = new ArrayList<>();
//Loop throw your file
while ((subLink = in.readLine()) != null) {
//Check if the sub-link is match with this regex, if yes then add it to your list
if (subLink.matches("Disallow: \\/\\w+\\/")) {
list.add(website + "/" + subLink.replace("Disallow: /", ""));
}else{
System.out.println("not match");
}
}
}
//Print your result
System.out.println(list);
}
This will show you :
[https://stackoverflow.com/posts/, https://stackoverflow.com/posts?,
https://stackoverflow.com/search/, https://stackoverflow.com/search?,
https://stackoverflow.com/feeds/, https://stackoverflow.com/feeds?,
https://stackoverflow.com/unanswered/,
https://stackoverflow.com/unanswered?, https://stackoverflow.com/u/,
https://stackoverflow.com/messages/, https://stackoverflow.com/ajax/,
https://stackoverflow.com/plugins/]
Here is a Demo about the regex that i use.
Hope this can help you.

To scan the links on the web page you can use JSoup library.
import java.io.IOException;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;
class read_data {
public static void main(String[] args) {
try {
Document doc = Jsoup.connect("**your_url**").get();
Elements links = doc.select("a");
List<String> list = new ArrayList<>();
for (Element link : links) {
list.add(link.attr("abs:href"));
}
} catch (IOException ex) {
}
}
}
list can be used as suggested in the previous answer.
The code for reading all the links on a website is given below. I have used http://stackoverflow.com/ for illustration. I would recommend you to go through company's terms of use before scraping it's website.
import java.io.IOException;
import java.util.HashSet;
import java.util.Set;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.select.Elements;
public class readAllLinks {
public static Set<String> uniqueURL = new HashSet<String>();
public static String my_site;
public static void main(String[] args) {
readAllLinks obj = new readAllLinks();
my_site = "stackoverflow.com";
obj.get_links("http://stackoverflow.com/");
}
private void get_links(String url) {
try {
Document doc = Jsoup.connect(url).get();
Elements links = doc.select("a");
links.stream().map((link) -> link.attr("abs:href")).forEachOrdered((this_url) -> {
boolean add = uniqueURL.add(this_url);
if (add && this_url.contains(my_site)) {
System.out.println(this_url);
get_links(this_url);
}
});
} catch (IOException ex) {
}
}
}
You will get list of all the links in uniqueURL field.

Jena Fuseki API add new data to an exsisting dataset [java]

i was trying to upload an RDF/OWL file to my Sparql endpoint (given by Fuseki). Right now i'm able to upload a single file, but if i try to repeat the action, the new dataset will override the old one. I'm searching a way to "merge" the content of the data in the dataset with the new ones of the rdf file just uploaded. Anyone can help me? thanks.
Following the code to upload/query the endpoint (i'm not the author)
// Written in 2015 by Thilo Planz
// To the extent possible under law, I have dedicated all copyright and related and neighboring rights
// to this software to the public domain worldwide. This software is distributed without any warranty.
// http://creativecommons.org/publicdomain/zero/1.0/
import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;
import java.io.ByteArrayOutputStream;
import org.apache.jena.query.DatasetAccessor;
import org.apache.jena.query.DatasetAccessorFactory;
import org.apache.jena.query.QueryExecution;
import org.apache.jena.query.QueryExecutionFactory;
import org.apache.jena.query.QuerySolution;
import org.apache.jena.query.ResultSet;
import org.apache.jena.query.ResultSetFormatter;
import org.apache.jena.rdf.model.Model;
import org.apache.jena.rdf.model.ModelFactory;
import org.apache.jena.rdf.model.RDFNode;
class FusekiExample {
public static void uploadRDF(File rdf, String serviceURI)
throws IOException {
// parse the file
Model m = ModelFactory.createDefaultModel();
try (FileInputStream in = new FileInputStream(rdf)) {
m.read(in, null, "RDF/XML");
}
// upload the resulting model
DatasetAccessor accessor = DatasetAccessorFactory.createHTTP(serviceURI);
accessor.putModel(m);
}
public static void execSelectAndPrint(String serviceURI, String query) {
QueryExecution q = QueryExecutionFactory.sparqlService(serviceURI,
query);
ResultSet results = q.execSelect();
// write to a ByteArrayOutputStream
ByteArrayOutputStream outputStream = new ByteArrayOutputStream();
//convert to JSON format
ResultSetFormatter.outputAsJSON(outputStream, results);
//turn json to string
String json = new String(outputStream.toByteArray());
//print json string
System.out.println(json);
}
public static void execSelectAndProcess(String serviceURI, String query) {
QueryExecution q = QueryExecutionFactory.sparqlService(serviceURI,
query);
ResultSet results = q.execSelect();
while (results.hasNext()) {
QuerySolution soln = results.nextSolution();
// assumes that you have an "?x" in your query
RDFNode x = soln.get("x");
System.out.println(x);
}
}
public static void main(String argv[]) throws IOException {
// uploadRDF(new File("test.rdf"), );
uploadRDF(new File("test.rdf"), "http://localhost:3030/MyEndpoint/data");
}
}

Use accessor.add(m) instead of putModel(m). As you can see in the Javadoc, putModel replaces the existing data.

Amazon Product Advertising API through Java/SOAP

I have been playing with Amazon's Product Advertising API, and I cannot get a request to go through and give me data. I have been working off of this: http://docs.amazonwebservices.com/AWSECommerceService/2011-08-01/GSG/ and this: Amazon Product Advertising API signed request with Java
Here is my code. I generated the SOAP bindings using this: http://docs.amazonwebservices.com/AWSECommerceService/2011-08-01/GSG/YourDevelopmentEnvironment.html#Java
On the Classpath, I only have: commons-codec.1.5.jar
import com.ECS.client.jax.AWSECommerceService;
import com.ECS.client.jax.AWSECommerceServicePortType;
import com.ECS.client.jax.Item;
import com.ECS.client.jax.ItemLookup;
import com.ECS.client.jax.ItemLookupRequest;
import com.ECS.client.jax.ItemLookupResponse;
import com.ECS.client.jax.ItemSearchResponse;
import com.ECS.client.jax.Items;
public class Client {
public static void main(String[] args) {
String secretKey = <my-secret-key>;
String awsKey = <my-aws-key>;
System.out.println("API Test started");
AWSECommerceService service = new AWSECommerceService();
service.setHandlerResolver(new AwsHandlerResolver(
secretKey)); // important
AWSECommerceServicePortType port = service.getAWSECommerceServicePort();
// Get the operation object:
com.ECS.client.jax.ItemSearchRequest itemRequest = new com.ECS.client.jax.ItemSearchRequest();
// Fill in the request object:
itemRequest.setSearchIndex("Books");
itemRequest.setKeywords("Star Wars");
// itemRequest.setVersion("2011-08-01");
com.ECS.client.jax.ItemSearch ItemElement = new com.ECS.client.jax.ItemSearch();
ItemElement.setAWSAccessKeyId(awsKey);
ItemElement.getRequest().add(itemRequest);
// Call the Web service operation and store the response
// in the response object:
com.ECS.client.jax.ItemSearchResponse response = port
.itemSearch(ItemElement);
String r = response.toString();
System.out.println("response: " + r);
for (Items itemList : response.getItems()) {
System.out.println(itemList);
for (Item item : itemList.getItem()) {
System.out.println(item);
}
}
System.out.println("API Test stopped");
}
}
Here is what I get back.. I was hoping to see some Star Wars books available on Amazon dumped out to my console :-/:
API Test started
response: com.ECS.client.jax.ItemSearchResponse#7a6769ea
com.ECS.client.jax.Items#1b5ac06e
API Test stopped
What am I doing wrong (Note that no "item" in the second for loop is being printed out, because its empty)? How can I troubleshoot this or get relevant error information?

I don't use the SOAP API but your Bounty requirements didn't state that it had to use SOAP only that you wanted to call Amazon and get results. So, I'll post this working example using the REST API which will at least fulfill your stated requirements:
I would like some working example code that hits the amazon server and returns results
You'll need to download the following to fulfill the signature requirements:
http://associates-amazon.s3.amazonaws.com/signed-requests/samples/amazon-product-advt-api-sample-java-query.zip
Unzip it and grab the com.amazon.advertising.api.sample.SignedRequestsHelper.java file and put it directly into your project. This code is used to sign the request.
You'll also need to download Apache Commons Codec 1.3 from the following and add it to your classpath i.e. add it to your project's library. Note that this is the only version of Codec that will work with the above class (SignedRequestsHelper)
http://archive.apache.org/dist/commons/codec/binaries/commons-codec-1.3.zip
Now you can copy and paste the following making sure to replace your.pkg.here with the proper package name and replace the SECRET and the KEY properties:
package your.pkg.here;
import java.io.FileNotFoundException;
import java.io.IOException;
import java.io.StringWriter;
import java.util.HashMap;
import java.util.Map;
import java.util.Properties;
import java.util.logging.Level;
import java.util.logging.Logger;
import javax.xml.parsers.DocumentBuilder;
import javax.xml.parsers.DocumentBuilderFactory;
import javax.xml.parsers.ParserConfigurationException;
import javax.xml.transform.OutputKeys;
import javax.xml.transform.Transformer;
import javax.xml.transform.TransformerException;
import javax.xml.transform.TransformerFactory;
import javax.xml.transform.dom.DOMSource;
import javax.xml.transform.stream.StreamResult;
import org.w3c.dom.Document;
import org.xml.sax.SAXException;
public class Main {
private static final String SECRET_KEY = "<YOUR_SECRET_KEY>";
private static final String AWS_KEY = "<YOUR_KEY>";
public static void main(String[] args) {
SignedRequestsHelper helper = SignedRequestsHelper.getInstance("ecs.amazonaws.com", AWS_KEY, SECRET_KEY);
Map<String, String> params = new HashMap<String, String>();
params.put("Service", "AWSECommerceService");
params.put("Version", "2009-03-31");
params.put("Operation", "ItemLookup");
params.put("ItemId", "1451648537");
params.put("ResponseGroup", "Large");
String url = helper.sign(params);
try {
Document response = getResponse(url);
printResponse(response);
} catch (Exception ex) {
Logger.getLogger(Main.class.getName()).log(Level.SEVERE, null, ex);
}
}
private static Document getResponse(String url) throws ParserConfigurationException, IOException, SAXException {
DocumentBuilder builder = DocumentBuilderFactory.newInstance().newDocumentBuilder();
Document doc = builder.parse(url);
return doc;
}
private static void printResponse(Document doc) throws TransformerException, FileNotFoundException {
Transformer trans = TransformerFactory.newInstance().newTransformer();
Properties props = new Properties();
props.put(OutputKeys.INDENT, "yes");
trans.setOutputProperties(props);
StreamResult res = new StreamResult(new StringWriter());
DOMSource src = new DOMSource(doc);
trans.transform(src, res);
String toString = res.getWriter().toString();
System.out.println(toString);
}
}
As you can see this is much simpler to setup and use than the SOAP API. If you don't have a specific requirement for using the SOAP API then I would highly recommend that you use the REST API instead.
One of the drawbacks of using the REST API is that the results aren't unmarshaled into objects for you. This could be remedied by creating the required classes based on the wsdl.

This ended up working (I had to add my associateTag to the request):
public class Client {
public static void main(String[] args) {
String secretKey = "<MY_SECRET_KEY>";
String awsKey = "<MY AWS KEY>";
System.out.println("API Test started");
AWSECommerceService service = new AWSECommerceService();
service.setHandlerResolver(new AwsHandlerResolver(secretKey)); // important
AWSECommerceServicePortType port = service.getAWSECommerceServicePort();
// Get the operation object:
com.ECS.client.jax.ItemSearchRequest itemRequest = new com.ECS.client.jax.ItemSearchRequest();
// Fill in the request object:
itemRequest.setSearchIndex("Books");
itemRequest.setKeywords("Star Wars");
itemRequest.getResponseGroup().add("Large");
// itemRequest.getResponseGroup().add("Images");
// itemRequest.setVersion("2011-08-01");
com.ECS.client.jax.ItemSearch ItemElement = new com.ECS.client.jax.ItemSearch();
ItemElement.setAWSAccessKeyId(awsKey);
ItemElement.setAssociateTag("th0426-20");
ItemElement.getRequest().add(itemRequest);
// Call the Web service operation and store the response
// in the response object:
com.ECS.client.jax.ItemSearchResponse response = port
.itemSearch(ItemElement);
String r = response.toString();
System.out.println("response: " + r);
for (Items itemList : response.getItems()) {
System.out.println(itemList);
for (Item itemObj : itemList.getItem()) {
System.out.println(itemObj.getItemAttributes().getTitle()); // Title
System.out.println(itemObj.getDetailPageURL()); // Amazon URL
}
}
System.out.println("API Test stopped");
}
}

It looks like the response object does not override toString(), so if it contains some sort of error response, simply printing it will not tell you what the error response is. You'll need to look at the api for what fields are returned in the response object and individually print those. Either you'll get an obvious error message or you'll have to go back to their documentation to try to figure out what is wrong.

You need to call the get methods on the Item object to retrieve its details, e.g.:
for (Item item : itemList.getItem()) {
System.out.println(item.getItemAttributes().getTitle()); //Title of item
System.out.println(item.getDetailPageURL()); // Amazon URL
//etc
}
If there are any errors you can get them by calling getErrors()
if (response.getOperationRequest().getErrors() != null) {
System.out.println(response.getOperationRequest().getErrors().getError().get(0).getMessage());
}

Identifying file type in Java

Please help me to find out the type of the file which is being uploaded.
I wanted to distinguish between excel type and csv.
MIMEType returns same for both of these file. Please help.

I use Apache Tika which identifies the filetype using magic byte patterns and globbing hints (the file extension) to detect the MIME type. It also supports additional parsing of file contents (which I don't really use).
Here is a quick and dirty example on how Tika can be used to detect the file type without performing any additional parsing on the file:
import java.io.File;
import java.io.FileInputStream;
import java.io.InputStream;
import java.util.HashMap;
import org.apache.tika.metadata.HttpHeaders;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.metadata.TikaMetadataKeys;
import org.apache.tika.mime.MediaType;
import org.apache.tika.parser.AutoDetectParser;
import org.apache.tika.parser.ParseContext;
import org.apache.tika.parser.Parser;
import org.xml.sax.helpers.DefaultHandler;
public class Detector {
public static void main(String[] args) throws Exception {
File file = new File("/pats/to/file.xls");
AutoDetectParser parser = new AutoDetectParser();
parser.setParsers(new HashMap<MediaType, Parser>());
Metadata metadata = new Metadata();
metadata.add(TikaMetadataKeys.RESOURCE_NAME_KEY, file.getName());
InputStream stream = new FileInputStream(file);
parser.parse(stream, new DefaultHandler(), metadata, new ParseContext());
stream.close();
String mimeType = metadata.get(HttpHeaders.CONTENT_TYPE);
System.out.println(mimeType);
}
}

I hope this will help. Taken from an example not from mine:
import javax.activation.MimetypesFileTypeMap;
import java.io.File;
class GetMimeType {
public static void main(String args[]) {
File f = new File("test.gif");
System.out.println("Mime Type of " + f.getName() + " is " +
new MimetypesFileTypeMap().getContentType(f));
// expected output :
// "Mime Type of test.gif is image/gif"
}
}
Same may be true for excel and csv types. Not tested.

I figured out a cheaper way of doing this with java.nio.file.Files
public String getContentType(File file) throws IOException {
return Files.probeContentType(file.toPath());
}
- or -
public String getContentType(Path filePath) throws IOException {
return Files.probeContentType(filePath);
}
Hope that helps.
Cheers.

A better way without using javax.activation.*:
URLConnection.guessContentTypeFromName(f.getAbsolutePath()));

If you are already using Spring this works for csv and excel:
import org.springframework.mail.javamail.ConfigurableMimeFileTypeMap;
import javax.activation.FileTypeMap;
import java.io.IOException;
public class ContentTypeResolver {
private FileTypeMap fileTypeMap;
public ContentTypeResolver() {
fileTypeMap = new ConfigurableMimeFileTypeMap();
}
public String getContentType(String fileName) throws IOException {
if (fileName == null) {
return null;
}
return fileTypeMap.getContentType(fileName.toLowerCase());
}
}
or with javax.activation you can update the mime.types file.

The CSV will start with text and the excel type is most likely binary.
However the simplest approach is to try to load the excel document using POI. If this fails try to load the file as a CSV, if that fails its possibly neither type.