public class PRTokeniser extends Object
Modifier and Type | Class and Description |
---|---|
static class |
PRTokeniser.TokenType
Enum representing the possible token types
|
Modifier and Type | Field and Description |
---|---|
static boolean[] |
delims |
protected int |
generation |
protected boolean |
hexString |
protected int |
reference |
protected String |
stringValue |
protected PRTokeniser.TokenType |
type |
Constructor and Description |
---|
PRTokeniser(RandomAccessFileOrArray file)
Creates a PRTokeniser for the specified RandomAccessFileOrArray .
|
Modifier and Type | Method and Description |
---|---|
void |
backOnePosition(int ch) |
void |
checkFdfHeader() |
static long[] |
checkObjectStart(byte[] line) |
char |
checkPdfHeader() |
void |
close() |
RandomAccessFileOrArray |
getFile() |
long |
getFilePointer() |
int |
getGeneration() |
int |
getHeaderOffset() |
static int |
getHex(int v) |
int |
getReference()
Gets current reference number.
|
RandomAccessFileOrArray |
getSafeFile() |
long |
getStartxref() |
String |
getStringValue() |
PRTokeniser.TokenType |
getTokenType() |
int |
intValue() |
static boolean |
isDelimiter(int ch) |
static boolean |
isDelimiterWhitespace(int ch) |
boolean |
isHexString() |
static boolean |
isWhitespace(int ch)
Is a certain character a whitespace? Currently checks on the following: '0', '9', '10', '12', '13', '32'.
|
static boolean |
isWhitespace(int ch, boolean isWhitespace)
Checks whether a character is a whitespace.
|
long |
length() |
long |
longValue() |
boolean |
nextToken() |
void |
nextValidToken() |
int |
read() |
boolean |
readLineSegment(byte[] input)
Reads data into the provided byte[].
|
boolean |
readLineSegment(byte[] input, boolean isNullWhitespace)
Reads data into the provided byte[].
|
String |
readString(int size) |
void |
seek(long pos) |
void |
throwError(String error) |
public static final boolean[] delims
protected PRTokeniser.TokenType type
protected String stringValue
protected int reference
protected int generation
protected boolean hexString
public PRTokeniser(RandomAccessFileOrArray file)
RandomAccessFileOrArray
. The beginning of the file is read to determine the location of the header, and the data source is adjusted as necessary to account for any junk that occurs in the byte source before the header
file
- the source
public void seek(long pos) throws IOException
IOException
public long getFilePointer() throws IOException
IOException
public void close() throws IOException
IOException
public long length() throws IOException
IOException
public int read() throws IOException
IOException
public RandomAccessFileOrArray getSafeFile()
public RandomAccessFileOrArray getFile()
public String readString(int size) throws IOException
IOException
public static final boolean isWhitespace(int ch)
isWhiteSpace(ch, true)
.
ch
- int
public static final boolean isWhitespace(int ch, boolean isWhitespace)
ch
- int
isWhitespace
- boolean
public static final boolean isDelimiter(int ch)
public static final boolean isDelimiterWhitespace(int ch)
public PRTokeniser.TokenType getTokenType()
public String getStringValue()
public int getReference()
public int getGeneration()
public void backOnePosition(int ch)
public void throwError(String error) throws IOException
IOException
public int getHeaderOffset() throws IOException
IOException
public char checkPdfHeader() throws IOException
IOException
public void checkFdfHeader() throws IOException
IOException
public long getStartxref() throws IOException
IOException
public static int getHex(int v)
public void nextValidToken() throws IOException
IOException
public boolean nextToken() throws IOException
IOException
public long longValue()
public int intValue()
public boolean readLineSegment(byte[] input) throws IOException
isWhiteSpace(int)
or isWhiteSpace(int, boolean)
for a list of whitespace characters.
readLineSegment(input, true)
.
input
- byte[]
IOException
public boolean readLineSegment(byte[] input, boolean isNullWhitespace) throws IOException
isWhiteSpace(int)
or isWhiteSpace(int, boolean)
for a list of whitespace characters.
input
- byte[]
isNullWhitespace
- boolean to indicate whether '0' is whitespace or not. If in doubt, use true or overloaded method readLineSegment(input)
IOException
public static long[] checkObjectStart(byte[] line)
public boolean isHexString()
Copyright © 1998–2024. All rights reserved.