|
|||||||||
PREV CLASS NEXT CLASS | FRAMES NO FRAMES | ||||||||
SUMMARY: NESTED | FIELD | CONSTR | METHOD | DETAIL: FIELD | CONSTR | METHOD |
java.lang.Object com.lowagie.text.pdf.PdfReader
public class PdfReader
Reads a PDF document.
Field Summary | |
---|---|
protected PRAcroForm |
acroForm
|
protected boolean |
acroFormParsed
|
protected PdfDictionary |
catalog
|
protected java.security.cert.Certificate |
certificate
|
protected java.security.Key |
certificateKey
|
protected java.lang.String |
certificateKeyProvider
|
protected boolean |
consolidateNamedDestinations
|
protected PdfEncryption |
decrypt
|
protected boolean |
encrypted
|
protected int |
eofPos
|
protected int |
freeXref
|
protected int |
lastXref
|
protected boolean |
newXrefType
|
protected java.util.HashMap |
objStmMark
|
protected IntHashtable |
objStmToOffset
|
protected com.lowagie.text.pdf.PdfReader.PageRefs |
pageRefs
|
protected byte[] |
password
|
protected char |
pdfVersion
|
protected int |
pValue
|
protected boolean |
rebuilt
|
protected int |
rValue
|
protected boolean |
sharedStreams
|
protected java.util.ArrayList |
strings
|
protected boolean |
tampered
|
protected PRTokeniser |
tokens
|
protected PdfDictionary |
trailer
|
protected int[] |
xref
|
Constructor Summary | |
---|---|
protected |
PdfReader()
|
|
PdfReader(byte[] pdfIn)
Reads and parses a PDF document. |
|
PdfReader(byte[] pdfIn,
byte[] ownerPassword)
Reads and parses a PDF document. |
|
PdfReader(java.io.InputStream is)
Reads and parses a PDF document. |
|
PdfReader(java.io.InputStream is,
byte[] ownerPassword)
Reads and parses a PDF document. |
|
PdfReader(PdfReader reader)
Creates an independent duplicate. |
|
PdfReader(RandomAccessFileOrArray raf,
byte[] ownerPassword)
Reads and parses a pdf document. |
|
PdfReader(java.lang.String filename)
Reads and parses a PDF document. |
|
PdfReader(java.lang.String filename,
byte[] ownerPassword)
Reads and parses a PDF document. |
|
PdfReader(java.lang.String filename,
java.security.cert.Certificate certificate,
java.security.Key certificateKey,
java.lang.String certificateKeyProvider)
Reads and parses a PDF document. |
|
PdfReader(java.net.URL url)
Reads and parses a PDF document. |
|
PdfReader(java.net.URL url,
byte[] ownerPassword)
Reads and parses a PDF document. |
Method Summary | |
---|---|
PRIndirectReference |
addPdfObject(PdfObject obj)
|
void |
addViewerPreference(PdfName key,
PdfObject value)
Adds a viewer preference |
static byte[] |
ASCII85Decode(byte[] in)
Decodes a stream that has the ASCII85Decode filter. |
static byte[] |
ASCIIHexDecode(byte[] in)
Decodes a stream that has the ASCIIHexDecode filter. |
void |
close()
Closes the reader |
byte[] |
computeUserPassword()
|
void |
consolidateNamedDestinations()
Replaces all the local named links with the actual destinations. |
int |
createFakeFontSubsets()
Finds all the fonts not subset but embedded and marks them as subset. |
static byte[] |
decodePredictor(byte[] in,
PdfObject dicPar)
|
double |
dumpPerc()
|
protected static PdfDictionary |
duplicatePdfDictionary(PdfDictionary original,
PdfDictionary copy,
PdfReader newReader)
|
protected static PdfObject |
duplicatePdfObject(PdfObject original,
PdfReader newReader)
|
void |
eliminateSharedStreams()
Eliminates shared streams if they exist. |
static byte[] |
FlateDecode(byte[] in)
Decodes a stream that has the FlateDecode filter. |
static byte[] |
FlateDecode(byte[] in,
boolean strict)
A helper to FlateDecode. |
AcroFields |
getAcroFields()
Gets a read-only version of AcroFields . |
PRAcroForm |
getAcroForm()
Returns the document's acroform, if it has one. |
Rectangle |
getBoxSize(int index,
java.lang.String boxName)
Gets the box size. |
PdfDictionary |
getCatalog()
Returns the document's catalog. |
int |
getCertificationLevel()
Gets the certification level for this document. |
Rectangle |
getCropBox(int index)
Gets the crop box without taking rotation into account. |
int |
getCryptoMode()
|
int |
getEofPos()
Gets the byte address of the %%EOF marker. |
int |
getFileLength()
Getter for property fileLength. |
java.util.HashMap |
getInfo()
Returns the content of the document information dictionary as a HashMap
of String . |
java.lang.String |
getJavaScript()
Gets the global document JavaScript. |
java.lang.String |
getJavaScript(RandomAccessFileOrArray file)
Gets the global document JavaScript. |
int |
getLastXref()
Gets the byte address of the last xref table. |
java.util.ArrayList |
getLinks(int page)
|
byte[] |
getMetadata()
Gets the XML metadata. |
java.util.HashMap |
getNamedDestination()
Gets all the named destinations as an HashMap . |
java.util.HashMap |
getNamedDestination(boolean keepNames)
Gets all the named destinations as an HashMap . |
java.util.HashMap |
getNamedDestinationFromNames()
Gets the named destinations from the /Dests key in the catalog as an HashMap . |
java.util.HashMap |
getNamedDestinationFromNames(boolean keepNames)
Gets the named destinations from the /Dests key in the catalog as an HashMap . |
java.util.HashMap |
getNamedDestinationFromStrings()
Gets the named destinations from the /Names key in the catalog as an HashMap . |
static Rectangle |
getNormalizedRectangle(PdfArray box)
Normalizes a Rectangle so that llx and lly are smaller than urx and ury. |
int |
getNumberOfPages()
Gets the number of pages in the document. |
byte[] |
getPageContent(int pageNum)
Gets the contents of the page. |
byte[] |
getPageContent(int pageNum,
RandomAccessFileOrArray file)
Gets the contents of the page. |
PdfDictionary |
getPageN(int pageNum)
Gets the dictionary that represents a page. |
PdfDictionary |
getPageNRelease(int pageNum)
|
PRIndirectReference |
getPageOrigRef(int pageNum)
Gets the page reference to this page. |
int |
getPageRotation(int index)
Gets the page rotation. |
Rectangle |
getPageSize(int index)
Gets the page size without taking rotation into account. |
Rectangle |
getPageSize(PdfDictionary page)
Gets the page from a page dictionary |
Rectangle |
getPageSizeWithRotation(int index)
Gets the page size, taking rotation into account. |
Rectangle |
getPageSizeWithRotation(PdfDictionary page)
Gets the rotated page from a page dictionary. |
PdfObject |
getPdfObject(int idx)
|
static PdfObject |
getPdfObject(PdfObject obj)
Reads a PdfObject resolving an indirect reference
if needed. |
static PdfObject |
getPdfObject(PdfObject obj,
PdfObject parent)
|
PdfObject |
getPdfObjectRelease(int idx)
|
static PdfObject |
getPdfObjectRelease(PdfObject obj)
|
static PdfObject |
getPdfObjectRelease(PdfObject obj,
PdfObject parent)
Reads a PdfObject resolving an indirect reference
if needed. |
protected com.lowagie.text.pdf.PdfReaderInstance |
getPdfReaderInstance(PdfWriter writer)
|
char |
getPdfVersion()
Gets the PDF version. |
int |
getPermissions()
Gets the encryption permissions. |
RandomAccessFileOrArray |
getSafeFile()
Gets a new file instance of the original PDF document. |
int |
getSimpleViewerPreferences()
Returns a bitset representing the PageMode and PageLayout viewer preferences. |
static byte[] |
getStreamBytes(PRStream stream)
Get the content from a stream applying the required filters. |
static byte[] |
getStreamBytes(PRStream stream,
RandomAccessFileOrArray file)
Get the content from a stream applying the required filters. |
static byte[] |
getStreamBytesRaw(PRStream stream)
Get the content from a stream as it is without applying any filter. |
static byte[] |
getStreamBytesRaw(PRStream stream,
RandomAccessFileOrArray file)
Get the content from a stream as it is without applying any filter. |
PdfDictionary |
getTrailer()
Gets the trailer dictionary |
int |
getXrefSize()
Gets the number of xref objects. |
boolean |
is128Key()
Returns true if the PDF has a 128 bit key encryption. |
boolean |
isAppendable()
Getter for property appendable. |
boolean |
isEncrypted()
Returns true if the PDF is encrypted. |
boolean |
isHybridXref()
Getter for property hybridXref. |
boolean |
isMetadataEncrypted()
|
boolean |
isNewXrefType()
Getter for property newXrefType. |
boolean |
isOpenedWithFullPermissions()
Checks if the document was opened with the owner password so that the end application can decide what level of access restrictions to apply. |
boolean |
isRebuilt()
Checks if the document had errors and was rebuilt. |
boolean |
isTampered()
Checks if the document was changed. |
static PdfObject |
killIndirect(PdfObject obj)
Eliminates the reference to the object freeing the memory used by it and clearing the xref entry. |
protected void |
killXref(PdfObject obj)
|
static byte[] |
LZWDecode(byte[] in)
Decodes a stream that has the LZWDecode filter. |
protected PdfArray |
readArray()
|
protected PdfDictionary |
readDictionary()
|
protected void |
readDocObj()
|
protected void |
readDocObjPartial()
|
protected void |
readObjStm(PRStream stream,
IntHashtable map)
|
protected PdfObject |
readOneObjStm(PRStream stream,
int idx)
|
protected void |
readPages()
|
protected void |
readPdf()
|
protected void |
readPdfPartial()
|
protected PdfObject |
readPRObject()
|
protected PdfObject |
readSingleObject(int k)
|
protected void |
readXref()
|
protected PdfDictionary |
readXrefSection()
|
protected boolean |
readXRefStream(int ptr)
|
protected void |
rebuildXref()
|
void |
releaseLastXrefPartial()
|
static void |
releaseLastXrefPartial(PdfObject obj)
|
void |
releasePage(int pageNum)
|
void |
removeAnnotations()
Removes all the annotations and fields from the document. |
void |
removeFields()
Removes all the fields from the document. |
protected void |
removeUnusedNode(PdfObject obj,
boolean[] hits)
|
int |
removeUnusedObjects()
Removes all the unreachable objects. |
void |
removeUsageRights()
Removes any usage rights that this PDF may have. |
void |
resetLastXrefPartial()
|
void |
resetReleasePage()
|
void |
selectPages(java.util.List pagesToKeep)
Selects the pages to keep in the document. |
void |
selectPages(java.lang.String ranges)
Selects the pages to keep in the document. |
void |
setAppendable(boolean appendable)
Setter for property appendable. |
void |
setPageContent(int pageNum,
byte[] content)
Sets the contents of the page. |
void |
setPageContent(int pageNum,
byte[] content,
int compressionLevel)
Sets the contents of the page. |
void |
setTampered(boolean tampered)
Sets the tampered state. |
void |
setViewerPreferences(int preferences)
Sets the viewer preferences as the sum of several constants. |
int |
shuffleSubsetNames()
Finds all the font subsets and changes the prefixes to some random values. |
Methods inherited from class java.lang.Object |
---|
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait |
Field Detail |
---|
protected PRTokeniser tokens
protected int[] xref
protected java.util.HashMap objStmMark
protected IntHashtable objStmToOffset
protected boolean newXrefType
protected PdfDictionary trailer
protected PdfDictionary catalog
protected com.lowagie.text.pdf.PdfReader.PageRefs pageRefs
protected PRAcroForm acroForm
protected boolean acroFormParsed
protected boolean encrypted
protected boolean rebuilt
protected int freeXref
protected boolean tampered
protected int lastXref
protected int eofPos
protected char pdfVersion
protected PdfEncryption decrypt
protected byte[] password
protected java.security.Key certificateKey
protected java.security.cert.Certificate certificate
protected java.lang.String certificateKeyProvider
protected java.util.ArrayList strings
protected boolean sharedStreams
protected boolean consolidateNamedDestinations
protected int rValue
protected int pValue
Constructor Detail |
---|
protected PdfReader()
public PdfReader(java.lang.String filename) throws java.io.IOException
filename
- the file name of the document
java.io.IOException
- on errorpublic PdfReader(java.lang.String filename, byte[] ownerPassword) throws java.io.IOException
filename
- the file name of the documentownerPassword
- the password to read the document
java.io.IOException
- on errorpublic PdfReader(byte[] pdfIn) throws java.io.IOException
pdfIn
- the byte array with the document
java.io.IOException
- on errorpublic PdfReader(byte[] pdfIn, byte[] ownerPassword) throws java.io.IOException
pdfIn
- the byte array with the documentownerPassword
- the password to read the document
java.io.IOException
- on errorpublic PdfReader(java.lang.String filename, java.security.cert.Certificate certificate, java.security.Key certificateKey, java.lang.String certificateKeyProvider) throws java.io.IOException
filename
- the file name of the documentcertificate
- the certificate to read the documentcertificateKey
- the private key of the certificatecertificateKeyProvider
- the security provider for certificateKey
java.io.IOException
- on errorpublic PdfReader(java.net.URL url) throws java.io.IOException
url
- the URL of the document
java.io.IOException
- on errorpublic PdfReader(java.net.URL url, byte[] ownerPassword) throws java.io.IOException
url
- the URL of the documentownerPassword
- the password to read the document
java.io.IOException
- on errorpublic PdfReader(java.io.InputStream is, byte[] ownerPassword) throws java.io.IOException
is
- the InputStream
containing the document. The stream is read to the
end but is not closedownerPassword
- the password to read the document
java.io.IOException
- on errorpublic PdfReader(java.io.InputStream is) throws java.io.IOException
is
- the InputStream
containing the document. The stream is read to the
end but is not closed
java.io.IOException
- on errorpublic PdfReader(RandomAccessFileOrArray raf, byte[] ownerPassword) throws java.io.IOException
PdfReader.close()
, reopen is automatic.
raf
- the document locationownerPassword
- the password or null
for no password
java.io.IOException
- on errorpublic PdfReader(PdfReader reader)
reader
- the PdfReader
to duplicateMethod Detail |
---|
public RandomAccessFileOrArray getSafeFile()
protected com.lowagie.text.pdf.PdfReaderInstance getPdfReaderInstance(PdfWriter writer)
public int getNumberOfPages()
public PdfDictionary getCatalog()
public PRAcroForm getAcroForm()
public int getPageRotation(int index)
index
- the page number. The first page is 1
public Rectangle getPageSizeWithRotation(int index)
Rectangle
with the value of the /MediaBox and the /Rotate key.
index
- the page number. The first page is 1
Rectangle
public Rectangle getPageSizeWithRotation(PdfDictionary page)
page
- the page dictionary
public Rectangle getPageSize(int index)
index
- the page number. The first page is 1
public Rectangle getPageSize(PdfDictionary page)
page
- the page dictionary
public Rectangle getCropBox(int index)
index
- the page number. The first page is 1
public Rectangle getBoxSize(int index, java.lang.String boxName)
index
- the page number. The first page is 1boxName
- the box name
public java.util.HashMap getInfo()
HashMap
of String
.
public static Rectangle getNormalizedRectangle(PdfArray box)
Rectangle
so that llx and lly are smaller than urx and ury.
box
- the original rectangle
Rectangle
protected void readPdf() throws java.io.IOException
java.io.IOException
protected void readPdfPartial() throws java.io.IOException
java.io.IOException
public static PdfObject getPdfObjectRelease(PdfObject obj)
obj
-
public static PdfObject getPdfObject(PdfObject obj)
PdfObject
resolving an indirect reference
if needed.
obj
- the PdfObject
to read
PdfObject
public static PdfObject getPdfObjectRelease(PdfObject obj, PdfObject parent)
PdfObject
resolving an indirect reference
if needed. If the reader was opened in partial mode the object will be released
to save memory.
obj
- the PdfObject
to readparent
-
public static PdfObject getPdfObject(PdfObject obj, PdfObject parent)
obj
- parent
-
public PdfObject getPdfObjectRelease(int idx)
idx
-
public PdfObject getPdfObject(int idx)
idx
-
public void resetLastXrefPartial()
public void releaseLastXrefPartial()
public static void releaseLastXrefPartial(PdfObject obj)
obj
- public PRIndirectReference addPdfObject(PdfObject obj)
obj
-
protected void readPages() throws java.io.IOException
java.io.IOException
protected void readDocObjPartial() throws java.io.IOException
java.io.IOException
protected PdfObject readSingleObject(int k) throws java.io.IOException
java.io.IOException
protected PdfObject readOneObjStm(PRStream stream, int idx) throws java.io.IOException
java.io.IOException
public double dumpPerc()
protected void readDocObj() throws java.io.IOException
java.io.IOException
protected void readObjStm(PRStream stream, IntHashtable map) throws java.io.IOException
java.io.IOException
public static PdfObject killIndirect(PdfObject obj)
obj
- the object. If it's an indirect reference it will be eliminated
protected void readXref() throws java.io.IOException
java.io.IOException
protected PdfDictionary readXrefSection() throws java.io.IOException
java.io.IOException
protected boolean readXRefStream(int ptr) throws java.io.IOException
java.io.IOException
protected void rebuildXref() throws java.io.IOException
java.io.IOException
protected PdfDictionary readDictionary() throws java.io.IOException
java.io.IOException
protected PdfArray readArray() throws java.io.IOException
java.io.IOException
protected PdfObject readPRObject() throws java.io.IOException
java.io.IOException
public static byte[] FlateDecode(byte[] in)
in
- the input data
public static byte[] decodePredictor(byte[] in, PdfObject dicPar)
in
- dicPar
-
public static byte[] FlateDecode(byte[] in, boolean strict)
in
- the input datastrict
- true
to read a correct stream. false
to try to read a corrupted stream
public static byte[] ASCIIHexDecode(byte[] in)
in
- the input data
public static byte[] ASCII85Decode(byte[] in)
in
- the input data
public static byte[] LZWDecode(byte[] in)
in
- the input data
public boolean isRebuilt()
public PdfDictionary getPageN(int pageNum)
pageNum
- the page number. 1 is the first
public PdfDictionary getPageNRelease(int pageNum)
pageNum
-
public void releasePage(int pageNum)
pageNum
- public void resetReleasePage()
public PRIndirectReference getPageOrigRef(int pageNum)
pageNum
- the page number. 1 is the first
public byte[] getPageContent(int pageNum, RandomAccessFileOrArray file) throws java.io.IOException
pageNum
- the page number. 1 is the firstfile
- the location of the PDF document
java.io.IOException
- on errorpublic byte[] getPageContent(int pageNum) throws java.io.IOException
pageNum
- the page number. 1 is the first
java.io.IOException
- on errorprotected void killXref(PdfObject obj)
public void setPageContent(int pageNum, byte[] content)
content
- the new page contentpageNum
- the page number. 1 is the firstpublic void setPageContent(int pageNum, byte[] content, int compressionLevel)
content
- the new page contentpageNum
- the page number. 1 is the firstpublic static byte[] getStreamBytes(PRStream stream, RandomAccessFileOrArray file) throws java.io.IOException
stream
- the streamfile
- the location where the stream is
java.io.IOException
- on errorpublic static byte[] getStreamBytes(PRStream stream) throws java.io.IOException
stream
- the stream
java.io.IOException
- on errorpublic static byte[] getStreamBytesRaw(PRStream stream, RandomAccessFileOrArray file) throws java.io.IOException
stream
- the streamfile
- the location where the stream is
java.io.IOException
- on errorpublic static byte[] getStreamBytesRaw(PRStream stream) throws java.io.IOException
stream
- the stream
java.io.IOException
- on errorpublic void eliminateSharedStreams()
public boolean isTampered()
true
if the document was changed,
false
otherwisepublic void setTampered(boolean tampered)
tampered
- the tampered statepublic byte[] getMetadata() throws java.io.IOException
java.io.IOException
- on errorpublic int getLastXref()
public int getXrefSize()
public int getEofPos()
public char getPdfVersion()
public boolean isEncrypted()
true
if the PDF is encrypted.
true
if the PDF is encryptedpublic int getPermissions()
PdfWriter.setEncryption()
.
public boolean is128Key()
true
if the PDF has a 128 bit key encryption.
true
if the PDF has a 128 bit key encryptionpublic PdfDictionary getTrailer()
public int shuffleSubsetNames()
public int createFakeFontSubsets()
public java.util.HashMap getNamedDestination()
HashMap
. The key is the name
and the value is the destinations array.
public java.util.HashMap getNamedDestination(boolean keepNames)
HashMap
. The key is the name
and the value is the destinations array.
keepNames
- true if you want the keys to be real PdfNames instead of Strings
public java.util.HashMap getNamedDestinationFromNames()
HashMap
. The key is the name
and the value is the destinations array.
public java.util.HashMap getNamedDestinationFromNames(boolean keepNames)
HashMap
. The key is the name
and the value is the destinations array.
keepNames
- true if you want the keys to be real PdfNames instead of Strings
public java.util.HashMap getNamedDestinationFromStrings()
HashMap
. The key is the name
and the value is the destinations array.
public void removeFields()
public void removeAnnotations()
public java.util.ArrayList getLinks(int page)
public void consolidateNamedDestinations()
protected static PdfDictionary duplicatePdfDictionary(PdfDictionary original, PdfDictionary copy, PdfReader newReader)
protected static PdfObject duplicatePdfObject(PdfObject original, PdfReader newReader)
public void close()
protected void removeUnusedNode(PdfObject obj, boolean[] hits)
public int removeUnusedObjects()
public AcroFields getAcroFields()
AcroFields
.
AcroFields
public java.lang.String getJavaScript(RandomAccessFileOrArray file) throws java.io.IOException
file
- the document file
java.io.IOException
- on errorpublic java.lang.String getJavaScript() throws java.io.IOException
java.io.IOException
- on errorpublic void selectPages(java.lang.String ranges)
ranges
- the comma separated ranges as described in SequenceList
public void selectPages(java.util.List pagesToKeep)
List
of Integer
. The page ordering can be changed but
no page repetitions are allowed. Note that it may be very slow in partial mode.
pagesToKeep
- the pages to keep in the documentpublic void setViewerPreferences(int preferences)
setViewerPreferences
in interface PdfViewerPreferences
preferences
- the viewer preferencesPdfViewerPreferences.setViewerPreferences(int)
public void addViewerPreference(PdfName key, PdfObject value)
addViewerPreference
in interface PdfViewerPreferences
key
- a key for a viewer preferencevalue
- a value for the viewer preferencePdfViewerPreferences.addViewerPreference(com.lowagie.text.pdf.PdfName, com.lowagie.text.pdf.PdfObject)
public int getSimpleViewerPreferences()
public boolean isAppendable()
public void setAppendable(boolean appendable)
appendable
- New value of property appendable.public boolean isNewXrefType()
public int getFileLength()
public boolean isHybridXref()
public void removeUsageRights()
public int getCertificationLevel()
PdfSignatureAppearance.NOT_CERTIFIED
,
PdfSignatureAppearance.CERTIFIED_NO_CHANGES_ALLOWED
,
PdfSignatureAppearance.CERTIFIED_FORM_FILLING
and
PdfSignatureAppearance.CERTIFIED_FORM_FILLING_AND_ANNOTATIONS
.
No signature validation is made, use the methods available for that in AcroFields
.
public final boolean isOpenedWithFullPermissions()
true
.
true
if the document was opened with the owner password or if it's not encrypted,
false
if the document was opened with the user passwordpublic int getCryptoMode()
public boolean isMetadataEncrypted()
public byte[] computeUserPassword()
|
|||||||||
PREV CLASS NEXT CLASS | FRAMES NO FRAMES | ||||||||
SUMMARY: NESTED | FIELD | CONSTR | METHOD | DETAIL: FIELD | CONSTR | METHOD |