fi.iki.hsivonen.util
Class MetadataExtractor

java.lang.Object
  fi.iki.hsivonen.util.MetadataExtractor

public class MetadataExtractor
extends Object

Author:

hsivonen, ykk

Field Summary

private static char	ANY
private static Pattern	charsetPat
private String	contentType
private static boolean	DEBUG Do we print the debug information
private static char	DIGIT
private Document	doc
private String	encoding
private static String[]	extensions
private static String[]	extensionTypes
private File	file
private String	fileName
private boolean	guessedContentType
private boolean	hasCSSCharset
private static char[][]	magicNumbers
private static String[]	magicTypes
private static int	MAX_MAGIC_LENGTH
private static String[]	mimeTypeNames
private static String[]	mimeTypes
private String	title

Constructor Summary

MetadataExtractor(File f)

MetadataExtractor(File f, String fileName)
Creates a new instance of MetadataExtractor

Method Summary

private void	checkEncoding()
private boolean	couldBeUTF8()
private void	determineTypeFromExtension()
private void	determineTypeFromMagic()
private void	determineTypeFromXML()
private void	determineTypeFromZip()
private void	extractMetaFromHTML()
private void	extractMetaFromPDF()
String	getContentType() Getter for property contentType.
String	getContentTypeWithParams()
Document	getDOM()
String	getEncoding() Getter for property encoding
boolean	getGuessedContentType() Getter for property guessedContentType.
static String[]	getMimeTypeNames()
static String[]	getMimeTypes()
String	getTitle()
private void	guessEncoding()
static void	main(String[] args)
private String	normalizeWhiteSpace(String text)
private void	setTitle(String title)

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Field Detail

DEBUG

private static boolean DEBUG

Do we print the debug information

charsetPat

private static Pattern charsetPat

file

private File file

contentType

private String contentType

title

private String title

doc

private Document doc

encoding

private String encoding

fileName

private String fileName

hasCSSCharset

private boolean hasCSSCharset

guessedContentType

private boolean guessedContentType

ANY

private static final char ANY

See Also:

Constant Field Values

DIGIT

private static final char DIGIT

See Also:

Constant Field Values

MAX_MAGIC_LENGTH

private static final int MAX_MAGIC_LENGTH

See Also:

Constant Field Values

magicNumbers

private static char[][] magicNumbers

magicTypes

private static String[] magicTypes

extensions

private static String[] extensions

extensionTypes

private static String[] extensionTypes

mimeTypes

private static String[] mimeTypes

mimeTypeNames

private static String[] mimeTypeNames

Constructor Detail

MetadataExtractor

public MetadataExtractor(File f)
                  throws IOException

Throws:

IOException

MetadataExtractor

public MetadataExtractor(File f,
                         String fileName)
                  throws IOException

Creates a new instance of MetadataExtractor

Throws:

IOException

Method Detail

main

public static void main(String[] args)
                 throws Exception

Throws:

Exception

checkEncoding

private void checkEncoding()
                    throws IOException

Throws:

IOException

determineTypeFromMagic

private void determineTypeFromMagic()
                             throws IOException

Throws:

IOException

guessEncoding

private void guessEncoding()
                    throws IOException

Throws:

IOException

couldBeUTF8

private boolean couldBeUTF8()
                     throws IOException

Throws:

IOException

determineTypeFromXML

private void determineTypeFromXML()
                           throws IOException

Throws:

IOException

determineTypeFromZip

private void determineTypeFromZip()
                           throws IOException

Throws:

IOException

determineTypeFromExtension

private void determineTypeFromExtension()

extractMetaFromHTML

private void extractMetaFromHTML()
                          throws IOException

Throws:

IOException

extractMetaFromPDF

private void extractMetaFromPDF()
                         throws IOException

Throws:

IOException

normalizeWhiteSpace

private String normalizeWhiteSpace(String text)

setTitle

private void setTitle(String title)

getContentType

public String getContentType()

Getter for property contentType.

Returns:

Value of property contentType.

getEncoding

public String getEncoding()

Getter for property encoding

Returns:

Value of property encoding.

getContentTypeWithParams

public String getContentTypeWithParams()

getGuessedContentType

public boolean getGuessedContentType()

Getter for property guessedContentType. If guessedContentType is true, the content type was derived from the file name and it could be wrong. If guessedContentType is false, the content type was derived from the magic bytes of the file and you can trust on that information.

Returns:

the value of guessedContentType field

getTitle

public String getTitle()

getDOM

public Document getDOM()

getMimeTypes

public static String[] getMimeTypes()

getMimeTypeNames

public static String[] getMimeTypeNames()