de.ipcon.tools

Class PDFParser

java.lang.Object

de.ipcon.tools.PDFParser

public class PDFParser
extends java.lang.Object

Method Summary

Modifier and Type	Method and Description
static java.lang.String	extract(byte[] bytes) Parses a PDF file and extracts the text from it
static java.lang.String	extract(byte[] bytes, boolean toHTML)
static java.lang.String	extract(byte[] bytes, boolean toHTML, boolean fast)
static java.lang.String	extract(byte[] bytes, boolean toHTML, boolean fast, java.lang.String password)
static java.lang.String[]	extract(byte[] bytes, java.awt.Rectangle[] areas) Parses a PDF file and extracts the text from it
static java.lang.String[]	extract(byte[] bytes, java.awt.Rectangle[] areas, int page)
static java.lang.String[]	extract(byte[] bytes, java.awt.Rectangle[] areas, int page, java.lang.String password)
static java.lang.String	extract(java.io.File pdfFile) Parses a PDF file and extracts the text from it
static java.lang.String	extract(java.io.File pdfFile, boolean toHTML)
static java.lang.String	extract(java.io.File pdfFile, boolean toHTML, boolean fast)
static java.lang.String	extract(java.io.File pdfFile, boolean toHTML, boolean fast, java.lang.String password)
static java.lang.String[]	extract(java.io.File f, java.awt.Rectangle[] areas) Parses a PDF file and extracts the text from it
static java.lang.String[]	extract(java.io.File f, java.awt.Rectangle[] areas, int page)
static java.lang.String[]	extract(java.io.File f, java.awt.Rectangle[] areas, int page, java.lang.String password)
static java.awt.image.BufferedImage	getBufferedImage(byte[] pdfdoc, java.lang.String password) Creates a BufferedImage from the given page of the pdf document
static java.awt.image.BufferedImage	getBufferedImage(byte[] pdfdoc, java.lang.String password, int pagenum)
static java.awt.image.BufferedImage	getBufferedImage(byte[] pdfdoc, java.lang.String password, int pagenum, int imageType)
static java.awt.image.BufferedImage	getBufferedImage(byte[] pdfdoc, java.lang.String password, int pagenum, int imageType, int resolution)
static java.awt.image.BufferedImage	getBufferedImage(java.io.File pdfdoc, java.lang.String password) Creates a BufferedImage from the given page of the pdf document
static java.awt.image.BufferedImage	getBufferedImage(java.io.File pdfdoc, java.lang.String password, int pagenum)
static java.awt.image.BufferedImage	getBufferedImage(java.io.File pdfdoc, java.lang.String password, int pagenum, int imageType)
static java.awt.image.BufferedImage	getBufferedImage(java.io.File pdfdoc, java.lang.String password, int pagenum, int imageType, int resolution)

Methods inherited from class java.lang.Object

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

Method Detail

extract

public static java.lang.String[] extract(java.io.File f,
                                         java.awt.Rectangle[] areas)
                                  throws java.io.IOException,
                                         java.io.FileNotFoundException

Parses a PDF file and extracts the text from it

Parameters:

f - A PDF File

areas - The areas on the given page to parse

Returns:

A String containing the file text content

Throws:

java.io.IOException

java.io.FileNotFoundException

extract

public static java.lang.String[] extract(java.io.File f,
                                         java.awt.Rectangle[] areas,
                                         int page)
                                  throws java.io.IOException,
                                         java.io.FileNotFoundException

Throws:

java.io.IOException

java.io.FileNotFoundException

extract

public static java.lang.String[] extract(java.io.File f,
                                         java.awt.Rectangle[] areas,
                                         int page,
                                         java.lang.String password)
                                  throws java.io.IOException,
                                         java.io.FileNotFoundException

Throws:

java.io.IOException

java.io.FileNotFoundException

extract

public static java.lang.String[] extract(byte[] bytes,
                                         java.awt.Rectangle[] areas)
                                  throws java.io.IOException

Parses a PDF file and extracts the text from it

Parameters:

bytes - A bytearray containing a PDF File

areas - The areas on the given page to parse

Returns:

A String containing the file text content

Throws:

java.io.IOException

extract

public static java.lang.String[] extract(byte[] bytes,
                                         java.awt.Rectangle[] areas,
                                         int page)
                                  throws java.io.IOException

Throws:

java.io.IOException

extract

public static java.lang.String[] extract(byte[] bytes,
                                         java.awt.Rectangle[] areas,
                                         int page,
                                         java.lang.String password)
                                  throws java.io.IOException

Throws:

java.io.IOException

extract

public static java.lang.String extract(java.io.File pdfFile)
                                throws java.io.IOException,
                                       java.io.FileNotFoundException

Parses a PDF file and extracts the text from it

Parameters:

f - A PDF File

Returns:

A String containing the file text content

Throws:

java.io.IOException

java.io.FileNotFoundException

extract

public static java.lang.String extract(java.io.File pdfFile,
                                       boolean toHTML)
                                throws java.io.IOException,
                                       java.io.FileNotFoundException

Throws:

java.io.IOException

java.io.FileNotFoundException

extract

public static java.lang.String extract(java.io.File pdfFile,
                                       boolean toHTML,
                                       boolean fast)
                                throws java.io.IOException,
                                       java.io.FileNotFoundException

Throws:

java.io.IOException

java.io.FileNotFoundException

extract

public static java.lang.String extract(java.io.File pdfFile,
                                       boolean toHTML,
                                       boolean fast,
                                       java.lang.String password)
                                throws java.io.IOException,
                                       java.io.FileNotFoundException

Throws:

java.io.IOException

java.io.FileNotFoundException

extract

public static java.lang.String extract(byte[] bytes)
                                throws java.io.IOException

Parses a PDF file and extracts the text from it

Parameters:

bytes - A bytearray containing a PDF File

Returns:

A String containing the file text content

Throws:

java.io.IOException

extract

public static java.lang.String extract(byte[] bytes,
                                       boolean toHTML)
                                throws java.io.IOException

Throws:

java.io.IOException

extract

public static java.lang.String extract(byte[] bytes,
                                       boolean toHTML,
                                       boolean fast)
                                throws java.io.IOException

Throws:

java.io.IOException

extract

public static java.lang.String extract(byte[] bytes,
                                       boolean toHTML,
                                       boolean fast,
                                       java.lang.String password)
                                throws java.io.IOException

Throws:

java.io.IOException

getBufferedImage

public static java.awt.image.BufferedImage getBufferedImage(java.io.File pdfdoc,
                                                            java.lang.String password)
                                                     throws java.io.IOException,
                                                            java.io.FileNotFoundException

Creates a BufferedImage from the given page of the pdf document

Parameters:

pdfdoc - A file containing a PDF

password - A password if required

pagenum - which page to load, 0-based, default 0

imageType - the image type (see BufferedImage.TYPE_*)

resolution - default is 96 dots per inch

Throws:

java.io.IOException

java.io.FileNotFoundException

getBufferedImage

public static java.awt.image.BufferedImage getBufferedImage(java.io.File pdfdoc,
                                                            java.lang.String password,
                                                            int pagenum)
                                                     throws java.io.IOException,
                                                            java.io.FileNotFoundException

Throws:

java.io.IOException

java.io.FileNotFoundException

getBufferedImage

public static java.awt.image.BufferedImage getBufferedImage(java.io.File pdfdoc,
                                                            java.lang.String password,
                                                            int pagenum,
                                                            int imageType)
                                                     throws java.io.IOException,
                                                            java.io.FileNotFoundException

Throws:

java.io.IOException

java.io.FileNotFoundException

getBufferedImage

public static java.awt.image.BufferedImage getBufferedImage(java.io.File pdfdoc,
                                                            java.lang.String password,
                                                            int pagenum,
                                                            int imageType,
                                                            int resolution)
                                                     throws java.io.IOException,
                                                            java.io.FileNotFoundException

Throws:

java.io.IOException

java.io.FileNotFoundException

getBufferedImage

public static java.awt.image.BufferedImage getBufferedImage(byte[] pdfdoc,
                                                            java.lang.String password)
                                                     throws java.io.IOException

Creates a BufferedImage from the given page of the pdf document

Parameters:

pdfdoc - A bytearray containing a PDF File

password - A password if required

pagenum - which page to load, 0-based, default 0

imageType - the image type (see BufferedImage.TYPE_*)

resolution - default is 96 dots per inch

Throws:

java.io.IOException

getBufferedImage

public static java.awt.image.BufferedImage getBufferedImage(byte[] pdfdoc,
                                                            java.lang.String password,
                                                            int pagenum)
                                                     throws java.io.IOException

Throws:

java.io.IOException

getBufferedImage

public static java.awt.image.BufferedImage getBufferedImage(byte[] pdfdoc,
                                                            java.lang.String password,
                                                            int pagenum,
                                                            int imageType)
                                                     throws java.io.IOException

Throws:

java.io.IOException

getBufferedImage

public static java.awt.image.BufferedImage getBufferedImage(byte[] pdfdoc,
                                                            java.lang.String password,
                                                            int pagenum,
                                                            int imageType,
                                                            int resolution)
                                                     throws java.io.IOException

Throws:

java.io.IOException