const (
// XrefTypeTableEntry indicates a normal xref table entry.
XrefTypeTableEntry xrefType = iota
// XrefTypeObjectStream indicates an xref entry in an xref object stream.
XrefTypeObjectStream xrefType = iota
)
Stream encoding filter names.
const (
StreamEncodingFilterNameFlate = "FlateDecode"
StreamEncodingFilterNameLZW = "LZWDecode"
StreamEncodingFilterNameDCT = "DCTDecode"
StreamEncodingFilterNameRunLength = "RunLengthDecode"
StreamEncodingFilterNameASCIIHex = "ASCIIHexDecode"
StreamEncodingFilterNameASCII85 = "ASCII85Decode"
StreamEncodingFilterNameCCITTFax = "CCITTFaxDecode"
StreamEncodingFilterNameJBIG2 = "JBIG2Decode"
StreamEncodingFilterNameJPX = "JPXDecode"
StreamEncodingFilterNameRaw = "Raw"
)
const (
// DefaultJPEGQuality is the default quality produced by JPEG encoders.
DefaultJPEGQuality = 75
)
JB2ImageAutoThreshold is the const value used by the 'GoImageToJBIG2Image function' used to set auto threshold for the histogram.
const JB2ImageAutoThreshold = -1.0
Common errors that may occur on PDF parsing/writing.
var (
// ErrUnsupportedEncodingParameters error indicates that encoding/decoding was attempted with unsupported
// encoding parameters.
// For example when trying to encode with an unsupported Predictor (flate).
ErrUnsupportedEncodingParameters = errors.New("unsupported encoding parameters")
ErrNoCCITTFaxDecode = errors.New("CCITTFaxDecode encoding is not yet implemented")
ErrNoJBIG2Decode = errors.New("JBIG2Decode encoding is not yet implemented")
ErrNoJPXDecode = errors.New("JPXDecode encoding is not yet implemented")
ErrNoPdfVersion = errors.New("version not found")
ErrTypeError = errors.New("type check error")
ErrRangeError = errors.New("range check error")
ErrNotSupported = xerrors.New("feature not currently supported")
ErrNotANumber = errors.New("not a number")
)
func DecodeStream(streamObj *PdfObjectStream) ([]byte, error)
DecodeStream decodes the stream data and returns the decoded data. An error is returned upon failure.
func EncodeStream(streamObj *PdfObjectStream) error
EncodeStream encodes the stream data using the encoded specified by the stream's dictionary.
func EqualObjects(obj1, obj2 PdfObject) bool
EqualObjects returns true if `obj1` and `obj2` have the same contents.
NOTE: It is a good idea to flatten obj1 and obj2 with FlattenObject before calling this function so that contents, rather than references, can be compared.
func GetBoolVal(obj PdfObject) (b bool, found bool)
GetBoolVal returns the bool value within a *PdObjectBool represented by an PdfObject interface directly or indirectly. If the PdfObject does not represent a bool value, a default value of false is returned (found = false also).
func GetFloatVal(obj PdfObject) (val float64, found bool)
GetFloatVal returns the float64 value represented by the PdfObject directly or indirectly if contained within an indirect object. On type mismatch the found bool flag returned is false and a nil pointer is returned.
func GetIntVal(obj PdfObject) (val int, found bool)
GetIntVal returns the int value represented by the PdfObject directly or indirectly if contained within an indirect object. On type mismatch the found bool flag returned is false and a nil pointer is returned.
func GetNameVal(obj PdfObject) (val string, found bool)
GetNameVal returns the string value represented by the PdfObject directly or indirectly if contained within an indirect object. On type mismatch the found bool flag returned is false and an empty string is returned.
func GetNumberAsFloat(obj PdfObject) (float64, error)
GetNumberAsFloat returns the contents of `obj` as a float if it is an integer or float, or an error if it isn't.
func GetNumberAsInt64(obj PdfObject) (int64, error)
GetNumberAsInt64 returns the contents of `obj` as an int64 if it is an integer or float, or an error if it isn't. This is for cases where expecting an integer, but some implementations actually store the number in a floating point format.
func GetNumbersAsFloat(objects []PdfObject) (floats []float64, err error)
GetNumbersAsFloat converts a list of pdf objects representing floats or integers to a slice of float64 values.
func GetStringBytes(obj PdfObject) (val []byte, found bool)
GetStringBytes is like GetStringVal except that it returns the string as a []byte. It is for convenience.
func GetStringVal(obj PdfObject) (val string, found bool)
GetStringVal returns the string value represented by the PdfObject directly or indirectly if contained within an indirect object. On type mismatch the found bool flag returned is false and an empty string is returned.
func IsDecimalDigit(c byte) bool
IsDecimalDigit checks if the character is a part of a decimal number string.
func IsDelimiter(c byte) bool
IsDelimiter checks if a character represents a delimiter.
func IsFloatDigit(c byte) bool
IsFloatDigit checks if a character can be a part of a float number string.
func IsNullObject(obj PdfObject) bool
IsNullObject returns true if `obj` is a PdfObjectNull.
func IsOctalDigit(c byte) bool
IsOctalDigit checks if a character can be part of an octal digit string.
func IsPrintable(c byte) bool
IsPrintable checks if a character is printable. Regular characters that are outside the range EXCLAMATION MARK(21h) (!) to TILDE (7Eh) (~) should be written using the hexadecimal notation.
func IsWhiteSpace(ch byte) bool
IsWhiteSpace checks if byte represents a white space character.
func PdfCryptNewEncrypt(cf crypto.Filter, userPass, ownerPass []byte, perm security.Permissions) (*PdfCrypt, *EncryptInfo, error)
PdfCryptNewEncrypt makes the document crypt handler based on a specified crypt filter.
func RegisterCustomStreamEncoder(filterName string, customStreamEncoder StreamEncoder)
RegisterCustomStreamEncoder register a custom encoder handler for certain filter.
func ResolveReferencesDeep(o PdfObject, traversed map[PdfObject]struct{}) error
ResolveReferencesDeep recursively traverses through object `o`, looking up and replacing references with indirect objects. Optionally a map of already deep-resolved objects can be provided via `traversed`. The `traversed` map is updated while traversing the objects to avoid traversing same objects multiple times.
ASCII85Encoder implements ASCII85 encoder/decoder.
type ASCII85Encoder struct {
}
func NewASCII85Encoder() *ASCII85Encoder
NewASCII85Encoder makes a new ASCII85 encoder.
func (enc *ASCII85Encoder) DecodeBytes(encoded []byte) ([]byte, error)
DecodeBytes decodes byte array with ASCII85. 5 ASCII characters -> 4 raw binary bytes
func (enc *ASCII85Encoder) DecodeStream(streamObj *PdfObjectStream) ([]byte, error)
DecodeStream implements ASCII85 stream decoding.
func (enc *ASCII85Encoder) EncodeBytes(data []byte) ([]byte, error)
EncodeBytes encodes data into ASCII85 encoded format.
func (enc *ASCII85Encoder) GetFilterName() string
GetFilterName returns the name of the encoding filter.
func (enc *ASCII85Encoder) MakeDecodeParams() PdfObject
MakeDecodeParams makes a new instance of an encoding dictionary based on the current encoder settings.
func (enc *ASCII85Encoder) MakeStreamDict() *PdfObjectDictionary
MakeStreamDict make a new instance of an encoding dictionary for a stream object.
func (enc *ASCII85Encoder) UpdateParams(params *PdfObjectDictionary)
UpdateParams updates the parameter values of the encoder.
ASCIIHexEncoder implements ASCII hex encoder/decoder.
type ASCIIHexEncoder struct {
}
func NewASCIIHexEncoder() *ASCIIHexEncoder
NewASCIIHexEncoder makes a new ASCII hex encoder.
func (enc *ASCIIHexEncoder) DecodeBytes(encoded []byte) ([]byte, error)
DecodeBytes decodes a slice of ASCII encoded bytes and returns the result.
func (enc *ASCIIHexEncoder) DecodeStream(streamObj *PdfObjectStream) ([]byte, error)
DecodeStream implements ASCII hex decoding.
func (enc *ASCIIHexEncoder) EncodeBytes(data []byte) ([]byte, error)
EncodeBytes ASCII encodes the passed in slice of bytes.
func (enc *ASCIIHexEncoder) GetFilterName() string
GetFilterName returns the name of the encoding filter.
func (enc *ASCIIHexEncoder) MakeDecodeParams() PdfObject
MakeDecodeParams makes a new instance of an encoding dictionary based on the current encoder settings.
func (enc *ASCIIHexEncoder) MakeStreamDict() *PdfObjectDictionary
MakeStreamDict makes a new instance of an encoding dictionary for a stream object.
func (enc *ASCIIHexEncoder) UpdateParams(params *PdfObjectDictionary)
UpdateParams updates the parameter values of the encoder.
CCITTFaxEncoder implements Group3 and Group4 facsimile (fax) encoder/decoder.
type CCITTFaxEncoder struct {
K int
EndOfLine bool
EncodedByteAlign bool
Columns int
Rows int
EndOfBlock bool
BlackIs1 bool
DamagedRowsBeforeError int
}
func NewCCITTFaxEncoder() *CCITTFaxEncoder
NewCCITTFaxEncoder makes a new CCITTFax encoder.
func (enc *CCITTFaxEncoder) DecodeBytes(encoded []byte) ([]byte, error)
DecodeBytes decodes the CCITTFax encoded image data.
func (enc *CCITTFaxEncoder) DecodeStream(streamObj *PdfObjectStream) ([]byte, error)
DecodeStream decodes the stream containing CCITTFax encoded image data.
func (enc *CCITTFaxEncoder) EncodeBytes(data []byte) ([]byte, error)
EncodeBytes encodes the image data using either Group3 or Group4 CCITT facsimile (fax) encoding. `data` is expected to be 1 color component, 1 bit per component. It is also valid to provide 8 BPC, 1 CC image like a standard go image Gray data.
func (enc *CCITTFaxEncoder) GetFilterName() string
GetFilterName returns the name of the encoding filter.
func (enc *CCITTFaxEncoder) MakeDecodeParams() PdfObject
MakeDecodeParams makes a new instance of an encoding dictionary based on the current encoder settings.
func (enc *CCITTFaxEncoder) MakeStreamDict() *PdfObjectDictionary
MakeStreamDict makes a new instance of an encoding dictionary for a stream object.
func (enc *CCITTFaxEncoder) UpdateParams(params *PdfObjectDictionary)
UpdateParams updates the parameter values of the encoder.
DCTEncoder provides a DCT (JPG) encoding/decoding functionality for images.
type DCTEncoder struct {
ColorComponents int // 1 (gray), 3 (rgb), 4 (cmyk)
BitsPerComponent int // 8 or 16 bit
Width int
Height int
Quality int
Decode []float64
}
func NewDCTEncoder() *DCTEncoder
NewDCTEncoder makes a new DCT encoder with default parameters.
func (enc *DCTEncoder) DecodeBytes(encoded []byte) ([]byte, error)
DecodeBytes decodes a slice of DCT encoded bytes and returns the result.
func (enc *DCTEncoder) DecodeStream(streamObj *PdfObjectStream) ([]byte, error)
DecodeStream decodes a DCT encoded stream and returns the result as a slice of bytes.
func (enc *DCTEncoder) EncodeBytes(data []byte) ([]byte, error)
EncodeBytes DCT encodes the passed in slice of bytes.
func (enc *DCTEncoder) GetFilterName() string
GetFilterName returns the name of the encoding filter.
func (enc *DCTEncoder) MakeDecodeParams() PdfObject
MakeDecodeParams makes a new instance of an encoding dictionary based on the current encoder settings.
func (enc *DCTEncoder) MakeStreamDict() *PdfObjectDictionary
MakeStreamDict makes a new instance of an encoding dictionary for a stream object. Has the Filter set. Some other parameters are generated elsewhere.
func (enc *DCTEncoder) UpdateParams(params *PdfObjectDictionary)
UpdateParams updates the parameter values of the encoder.
DrawableImage is same as golang image/draw's Image interface that allow drawing images.
type DrawableImage interface {
ColorModel() gocolor.Model
Bounds() goimage.Rectangle
At(x, y int) gocolor.Color
Set(x, y int, c gocolor.Color)
}
EncryptInfo contains an information generated by the document encrypter.
type EncryptInfo struct {
// Version is minimal PDF version that supports specified encryption algorithm.
Version
// Encrypt is an encryption dictionary that contains all necessary parameters.
// It should be stored in all copies of the document trailer.
Encrypt *PdfObjectDictionary
// ID0 and ID1 are IDs used in the trailer. Older algorithms such as RC4 uses them for encryption.
ID0, ID1 string
}
FlateEncoder represents Flate encoding.
type FlateEncoder struct {
Predictor int
BitsPerComponent int
// For predictors
Columns int
Rows int
Colors int
// contains filtered or unexported fields
}
func NewFlateEncoder() *FlateEncoder
NewFlateEncoder makes a new flate encoder with default parameters, predictor 1 and bits per component 8.
func (enc *FlateEncoder) DecodeBytes(encoded []byte) ([]byte, error)
DecodeBytes decodes a slice of Flate encoded bytes and returns the result.
func (enc *FlateEncoder) DecodeStream(streamObj *PdfObjectStream) ([]byte, error)
DecodeStream decodes a FlateEncoded stream object and give back decoded bytes.
func (enc *FlateEncoder) EncodeBytes(data []byte) ([]byte, error)
EncodeBytes encodes a bytes array and return the encoded value based on the encoder parameters.
func (enc *FlateEncoder) GetFilterName() string
GetFilterName returns the name of the encoding filter.
func (enc *FlateEncoder) MakeDecodeParams() PdfObject
MakeDecodeParams makes a new instance of an encoding dictionary based on the current encoder settings.
func (enc *FlateEncoder) MakeStreamDict() *PdfObjectDictionary
MakeStreamDict makes a new instance of an encoding dictionary for a stream object. Has the Filter set and the DecodeParms.
func (enc *FlateEncoder) SetImage(img *imageutil.ImageBase)
SetImage sets the image base for given flate encoder.
func (enc *FlateEncoder) SetPredictor(columns int)
SetPredictor sets the predictor function. Specify the number of columns per row. The columns indicates the number of samples per row. Used for grouping data together for compression.
func (enc *FlateEncoder) UpdateParams(params *PdfObjectDictionary)
UpdateParams updates the parameter values of the encoder.
JBIG2CompressionType defines the enum compression type used by the JBIG2Encoder.
type JBIG2CompressionType int
const (
// JB2Generic is the JBIG2 compression type that uses generic region see 6.2.
JB2Generic JBIG2CompressionType = iota
// JB2SymbolCorrelation is the JBIG2 compression type that uses symbol dictionary and text region encoding procedure
// with the correlation classification.
// NOT IMPLEMENTED YET.
JB2SymbolCorrelation
// JB2SymbolRankHaus is the JBIG2 compression type that uses symbol dictionary and text region encoding procedure
// with the rank hausdorff classification. RankHausMode uses the rank Hausdorff method that classifies the input images.
// It is more robust, more susceptible to confusing components that should be in different classes.
// NOT IMPLEMENTED YET.
JB2SymbolRankHaus
)
JBIG2Encoder implements both jbig2 encoder and the decoder. The encoder allows to encode provided images (best used document scans) in multiple way. By default it uses single page generic encoder. It allows to store lossless data as a single segment. In order to store multiple image pages use the 'FileMode' which allows to store more pages within single jbig2 document. WIP: In order to obtain better compression results the encoder would allow to encode the input in a lossy or lossless way with a component (symbol) mode. It divides the image into components. Then checks if any component is 'similar' to the others and maps them together. The symbol classes are stored in the dictionary. Then the encoder creates text regions which uses the related symbol classes to fill it's space. The similarity is defined by the 'Threshold' variable (default: 0.95). The less the value is, the more components matches to single class, thus the compression is better, but the result might become lossy.
type JBIG2Encoder struct {
// These values are required to be set for the 'EncodeBytes' method.
// ColorComponents defines the number of color components for provided image.
ColorComponents int
// BitsPerComponent is the number of bits that stores per color component
BitsPerComponent int
// Width is the width of the image to encode
Width int
// Height is the height of the image to encode.
Height int
// Globals are the JBIG2 global segments.
Globals jbig2.Globals
// IsChocolateData defines if the data is encoded such that
// binary data '1' means black and '0' white.
// otherwise the data is called vanilla.
// Naming convention taken from: 'https://en.wikipedia.org/wiki/Binary_image#Interpretation'
IsChocolateData bool
// DefaultPageSettings are the settings parameters used by the jbig2 encoder.
DefaultPageSettings JBIG2EncoderSettings
// contains filtered or unexported fields
}
func NewJBIG2Encoder() *JBIG2Encoder
NewJBIG2Encoder creates a new JBIG2Encoder.
func (enc *JBIG2Encoder) AddPageImage(img *JBIG2Image, settings *JBIG2EncoderSettings) (err error)
AddPageImage adds the page with the image 'img' to the encoder context in order to encode it jbig2 document. The 'settings' defines what encoding type should be used by the encoder.
func (enc *JBIG2Encoder) DecodeBytes(encoded []byte) ([]byte, error)
DecodeBytes decodes a slice of JBIG2 encoded bytes and returns the results.
func (enc *JBIG2Encoder) DecodeGlobals(encoded []byte) (jbig2.Globals, error)
DecodeGlobals decodes 'encoded' byte stream and returns their Globally defined segments ('Globals').
func (enc *JBIG2Encoder) DecodeImages(encoded []byte) ([]image.Image, error)
DecodeImages decodes the page images from the jbig2 'encoded' data input. The jbig2 document may contain multiple pages, thus the function can return multiple images. The images order corresponds to the page number.
func (enc *JBIG2Encoder) DecodeStream(streamObj *PdfObjectStream) ([]byte, error)
DecodeStream decodes a JBIG2 encoded stream and returns the result as a slice of bytes.
func (enc *JBIG2Encoder) Encode() (data []byte, err error)
Encode encodes previously prepare jbig2 document and stores it as the byte slice.
func (enc *JBIG2Encoder) EncodeBytes(data []byte) ([]byte, error)
EncodeBytes encodes slice of bytes into JBIG2 encoding format. The input 'data' must be an image. In order to Decode it a user is responsible to load the codec ('png', 'jpg'). Returns jbig2 single page encoded document byte slice. The encoder uses DefaultPageSettings to encode given image.
func (enc *JBIG2Encoder) EncodeImage(img image.Image) ([]byte, error)
EncodeImage encodes 'img' golang image.Image into jbig2 encoded bytes document using default encoder settings.
func (enc *JBIG2Encoder) EncodeJBIG2Image(img *JBIG2Image) ([]byte, error)
EncodeJBIG2Image encodes 'img' into jbig2 encoded bytes stream, using default encoder settings.
func (enc *JBIG2Encoder) GetFilterName() string
GetFilterName returns the name of the encoding filter.
func (enc *JBIG2Encoder) MakeDecodeParams() PdfObject
MakeDecodeParams makes a new instance of an encoding dictionary based on the current encoder settings.
func (enc *JBIG2Encoder) MakeStreamDict() *PdfObjectDictionary
MakeStreamDict makes a new instance of an encoding dictionary for a stream object.
func (enc *JBIG2Encoder) UpdateParams(params *PdfObjectDictionary)
UpdateParams updates the parameter values of the encoder. Implements StreamEncoder interface.
JBIG2EncoderSettings contains the parameters and settings used by the JBIG2Encoder. Current version works only on JB2Generic compression.
type JBIG2EncoderSettings struct {
// FileMode defines if the jbig2 encoder should return full jbig2 file instead of
// shortened pdf mode. This adds the file header to the jbig2 definition.
FileMode bool
// Compression is the setting that defines the compression type used for encoding the page.
Compression JBIG2CompressionType
// DuplicatedLinesRemoval code generic region in a way such that if the lines are duplicated the encoder
// doesn't store it twice.
DuplicatedLinesRemoval bool
// DefaultPixelValue is the bit value initial for every pixel in the page.
DefaultPixelValue uint8
// ResolutionX optional setting that defines the 'x' axis input image resolution - used for single page encoding.
ResolutionX int
// ResolutionY optional setting that defines the 'y' axis input image resolution - used for single page encoding.
ResolutionY int
// Threshold defines the threshold of the image correlation for
// non Generic compression.
// User only for JB2SymbolCorrelation and JB2SymbolRankHaus methods.
// Best results in range [0.7 - 0.98] - the less the better the compression would be
// but the more lossy.
// Default value: 0.95
Threshold float64
}
func (s JBIG2EncoderSettings) Validate() error
Validate validates the page settings for the JBIG2 encoder.
JBIG2Image is the image structure used by the jbig2 encoder. Its Data must be in a 1 bit per component and 1 component per pixel (1bpp). In order to create binary image use GoImageToJBIG2 function. If the image data contains the row bytes padding set the HasPadding to true.
type JBIG2Image struct {
// Width and Height defines the image boundaries.
Width, Height int
// Data is the byte slice data for the input image
Data []byte
// HasPadding is the attribute that defines if the last byte of the data in the row contains
// 0 bits padding.
HasPadding bool
}
func GoImageToJBIG2(i image.Image, bwThreshold float64) (*JBIG2Image, error)
GoImageToJBIG2 creates a binary image on the base of 'i' golang image.Image. If the image is not a black/white image then the function converts provided input into JBIG2Image with 1bpp. For non grayscale images the function performs the conversion to the grayscale temp image. Then it checks the value of the gray image value if it's within bounds of the black white threshold. This 'bwThreshold' value should be in range (0.0, 1.0). The threshold checks if the grayscale pixel (uint) value is greater or smaller than 'bwThreshold' * 255. Pixels inside the range will be white, and the others will be black. If the 'bwThreshold' is equal to -1.0 - JB2ImageAutoThreshold then it's value would be set on the base of it's histogram using Triangle method. For more information go to:
https://www.mathworks.com/matlabcentral/fileexchange/28047-gray-image-thresholding-using-the-triangle-method
func (j *JBIG2Image) ToGoImage() (image.Image, error)
ToGoImage converts the JBIG2Image to the golang image.Image.
JPXEncoder implements JPX encoder/decoder (dummy, for now) FIXME: implement
type JPXEncoder struct{}
func NewJPXEncoder() *JPXEncoder
NewJPXEncoder returns a new instance of JPXEncoder.
func (enc *JPXEncoder) DecodeBytes(encoded []byte) ([]byte, error)
DecodeBytes decodes a slice of JPX encoded bytes and returns the result.
func (enc *JPXEncoder) DecodeStream(streamObj *PdfObjectStream) ([]byte, error)
DecodeStream decodes a JPX encoded stream and returns the result as a slice of bytes.
func (enc *JPXEncoder) EncodeBytes(data []byte) ([]byte, error)
EncodeBytes JPX encodes the passed in slice of bytes.
func (enc *JPXEncoder) GetFilterName() string
GetFilterName returns the name of the encoding filter.
func (enc *JPXEncoder) MakeDecodeParams() PdfObject
MakeDecodeParams makes a new instance of an encoding dictionary based on the current encoder settings.
func (enc *JPXEncoder) MakeStreamDict() *PdfObjectDictionary
MakeStreamDict makes a new instance of an encoding dictionary for a stream object.
func (enc *JPXEncoder) UpdateParams(params *PdfObjectDictionary)
UpdateParams updates the parameter values of the encoder.
LZWEncoder provides LZW encoding/decoding functionality.
type LZWEncoder struct {
Predictor int
BitsPerComponent int
// For predictors
Columns int
Colors int
// LZW algorithm setting.
EarlyChange int
}
func NewLZWEncoder() *LZWEncoder
NewLZWEncoder makes a new LZW encoder with default parameters.
func (enc *LZWEncoder) DecodeBytes(encoded []byte) ([]byte, error)
DecodeBytes decodes a slice of LZW encoded bytes and returns the result.
func (enc *LZWEncoder) DecodeStream(streamObj *PdfObjectStream) ([]byte, error)
DecodeStream decodes a LZW encoded stream and returns the result as a slice of bytes.
func (enc *LZWEncoder) EncodeBytes(data []byte) ([]byte, error)
EncodeBytes implements support for LZW encoding. Currently not supporting predictors (raw compressed data only). Only supports the Early change = 1 algorithm (compress/lzw) as the other implementation does not have a write method. TODO: Consider refactoring compress/lzw to allow both.
func (enc *LZWEncoder) GetFilterName() string
GetFilterName returns the name of the encoding filter.
func (enc *LZWEncoder) MakeDecodeParams() PdfObject
MakeDecodeParams makes a new instance of an encoding dictionary based on the current encoder settings.
func (enc *LZWEncoder) MakeStreamDict() *PdfObjectDictionary
MakeStreamDict makes a new instance of an encoding dictionary for a stream object. Has the Filter set and the DecodeParms.
func (enc *LZWEncoder) UpdateParams(params *PdfObjectDictionary)
UpdateParams updates the parameter values of the encoder.
MultiEncoder supports serial encoding.
type MultiEncoder struct {
// contains filtered or unexported fields
}
func NewMultiEncoder() *MultiEncoder
NewMultiEncoder returns a new instance of MultiEncoder.
func (enc *MultiEncoder) AddEncoder(encoder StreamEncoder)
AddEncoder adds the passed in encoder to the underlying encoder slice.
func (enc *MultiEncoder) DecodeBytes(encoded []byte) ([]byte, error)
DecodeBytes decodes a multi-encoded slice of bytes by passing it through the DecodeBytes method of the underlying encoders.
func (enc *MultiEncoder) DecodeStream(streamObj *PdfObjectStream) ([]byte, error)
DecodeStream decodes a multi-encoded stream by passing it through the DecodeStream method of the underlying encoders.
func (enc *MultiEncoder) EncodeBytes(data []byte) ([]byte, error)
EncodeBytes encodes the passed in slice of bytes by passing it through the EncodeBytes method of the underlying encoders.
func (enc *MultiEncoder) GetFilterArray() *PdfObjectArray
GetFilterArray returns the names of the underlying encoding filters in an array that can be used as /Filter entry.
func (enc *MultiEncoder) GetFilterName() string
GetFilterName returns the names of the underlying encoding filters, separated by spaces. Note: This is just a string, should not be used in /Filter dictionary entry. Use GetFilterArray for that. TODO(v4): Refactor to GetFilter() which can be used for /Filter (either Name or Array), this can be
renamed to String() as a pretty string to use in debugging etc.
func (enc *MultiEncoder) MakeDecodeParams() PdfObject
MakeDecodeParams makes a new instance of an encoding dictionary based on the current encoder settings.
func (enc *MultiEncoder) MakeStreamDict() *PdfObjectDictionary
MakeStreamDict makes a new instance of an encoding dictionary for a stream object.
func (enc *MultiEncoder) UpdateParams(params *PdfObjectDictionary)
UpdateParams updates the parameter values of the encoder.
ParserMetadata is the parser based metadata information about document. The data here could be used on document verification.
type ParserMetadata struct {
// contains filtered or unexported fields
}
func (p ParserMetadata) HasDataAfterEOF() bool
HasDataAfterEOF checks if there is some data after EOF marker.
func (p ParserMetadata) HasEOLAfterHeader() bool
HasEOLAfterHeader gets information if there is a EOL after the version header.
func (p ParserMetadata) HasInvalidHexRunes() bool
HasInvalidHexRunes implements core.ParserMetadata interface.
func (p ParserMetadata) HasInvalidSeparationAfterXRef() bool
HasInvalidSeparationAfterXRef implements core.ParserMetadata interface.
func (p ParserMetadata) HasInvalidSubsectionHeader() bool
HasInvalidSubsectionHeader implements core.ParserMetadata interface.
func (p ParserMetadata) HasNonConformantStream() bool
HasNonConformantStream implements core.ParserMetadata.
func (p ParserMetadata) HasOddLengthHexStrings() bool
HasOddLengthHexStrings checks if the document has odd length hexadecimal strings.
func (p ParserMetadata) HeaderCommentBytes() [4]byte
HeaderCommentBytes gets the header comment bytes.
func (p ParserMetadata) HeaderPosition() int
HeaderPosition gets the file header position.
PdfCrypt provides PDF encryption/decryption support. The PDF standard supports encryption of strings and streams (Section 7.6).
type PdfCrypt struct {
// contains filtered or unexported fields
}
func PdfCryptNewDecrypt(parser *PdfParser, ed, trailer *PdfObjectDictionary) (*PdfCrypt, error)
PdfCryptNewDecrypt makes the document crypt handler based on the encryption dictionary and trailer dictionary. Returns an error on failure to process.
func (crypt *PdfCrypt) Decrypt(obj PdfObject, parentObjNum, parentGenNum int64) error
Decrypt an object with specified key. For numbered objects, the key argument is not used and a new one is generated based on the object and generation number. Traverses through all the subobjects (recursive).
Does not look up references.. That should be done prior to calling.
func (crypt *PdfCrypt) Encrypt(obj PdfObject, parentObjNum, parentGenNum int64) error
Encrypt an object with specified key. For numbered objects, the key argument is not used and a new one is generated based on the object and generation number. Traverses through all the subobjects (recursive).
Does not look up references.. That should be done prior to calling.
func (crypt *PdfCrypt) GetAccessPermissions() security.Permissions
GetAccessPermissions returns the PDF access permissions as an AccessPermissions object.
func (crypt *PdfCrypt) String() string
String returns a descriptive information string about the encryption method used.
PdfIndirectObject represents the primitive PDF indirect object.
type PdfIndirectObject struct {
PdfObjectReference
PdfObject
}
func GetIndirect(obj PdfObject) (ind *PdfIndirectObject, found bool)
GetIndirect returns the *PdfIndirectObject represented by the PdfObject. On type mismatch the found bool flag is false and a nil pointer is returned.
func MakeIndirectObject(obj PdfObject) *PdfIndirectObject
MakeIndirectObject creates an PdfIndirectObject with a specified direct object PdfObject.
func (ind *PdfIndirectObject) String() string
String returns a string describing `ind`.
func (ind *PdfIndirectObject) WriteString() string
WriteString outputs the object as it is to be written to file.
PdfObject is an interface which all primitive PDF objects must implement.
type PdfObject interface {
// String outputs a string representation of the primitive (for debugging).
String() string
// WriteString outputs the PDF primitive as written to file as expected by the standard.
// TODO(dennwc): it should return a byte slice, or accept a writer
WriteString() string
}
func FlattenObject(obj PdfObject) PdfObject
FlattenObject returns the contents of `obj`. In other words, `obj` with indirect objects replaced by their values. The replacements are made recursively to a depth of traceMaxDepth. NOTE: Dicts are sorted to make objects with same contents have the same PDF object strings.
func ParseNumber(buf *bufio.Reader) (PdfObject, error)
ParseNumber parses a numeric objects from a buffered stream. Section 7.3.3. Integer or Float.
An integer shall be written as one or more decimal digits optionally preceded by a sign. The value shall be interpreted as a signed decimal integer and shall be converted to an integer object.
A real value shall be written as one or more decimal digits with an optional sign and a leading, trailing, or embedded PERIOD (2Eh) (decimal point). The value shall be interpreted as a real number and shall be converted to a real object.
Regarding exponential numbers: 7.3.3 Numeric Objects: A conforming writer shall not use the PostScript syntax for numbers with non-decimal radices (such as 16#FFFE) or in exponential format (such as 6.02E23). Nonetheless, we sometimes get numbers with exponential format, so we will support it in the reader (no confusion with other types, so no compromise).
func ResolveReference(obj PdfObject) PdfObject
ResolveReference resolves reference if `o` is a *PdfObjectReference and returns the object referenced to. Otherwise returns back `o`.
func TraceToDirectObject(obj PdfObject) PdfObject
TraceToDirectObject traces a PdfObject to a direct object. For example direct objects contained in indirect objects (can be double referenced even).
PdfObjectArray represents the primitive PDF array object.
type PdfObjectArray struct {
// contains filtered or unexported fields
}
func GetArray(obj PdfObject) (arr *PdfObjectArray, found bool)
GetArray returns the *PdfObjectArray represented by the PdfObject directly or indirectly within an indirect object. On type mismatch the found bool flag is false and a nil pointer is returned.
func MakeArray(objects ...PdfObject) *PdfObjectArray
MakeArray creates an PdfObjectArray from a list of PdfObjects.
func MakeArrayFromFloats(vals []float64) *PdfObjectArray
MakeArrayFromFloats creates an PdfObjectArray from a slice of float64s, where each array element is an PdfObjectFloat.
func MakeArrayFromIntegers(vals []int) *PdfObjectArray
MakeArrayFromIntegers creates an PdfObjectArray from a slice of ints, where each array element is an PdfObjectInteger.
func MakeArrayFromIntegers64(vals []int64) *PdfObjectArray
MakeArrayFromIntegers64 creates an PdfObjectArray from a slice of int64s, where each array element is an PdfObjectInteger.
func (array *PdfObjectArray) Append(objects ...PdfObject)
Append appends PdfObject(s) to the array.
func (array *PdfObjectArray) Clear()
Clear resets the array to an empty state.
func (array *PdfObjectArray) Elements() []PdfObject
Elements returns a slice of the PdfObject elements in the array.
func (array *PdfObjectArray) Get(i int) PdfObject
Get returns the i-th element of the array or nil if out of bounds (by index).
func (array *PdfObjectArray) GetAsFloat64Slice() ([]float64, error)
GetAsFloat64Slice returns the array as []float64 slice. Returns an error if not entirely numeric (only PdfObjectIntegers, PdfObjectFloats).
func (array *PdfObjectArray) Len() int
Len returns the number of elements in the array.
func (array *PdfObjectArray) Set(i int, obj PdfObject) error
Set sets the PdfObject at index i of the array. An error is returned if the index is outside bounds.
func (array *PdfObjectArray) String() string
String returns a string describing `array`.
func (array *PdfObjectArray) ToFloat64Array() ([]float64, error)
ToFloat64Array returns a slice of all elements in the array as a float64 slice. An error is returned if the array contains non-numeric objects (each element can be either PdfObjectInteger or PdfObjectFloat).
func (array *PdfObjectArray) ToInt64Slice() ([]int64, error)
ToInt64Slice returns a slice of all array elements as an int64 slice. An error is returned if the array non-integer objects. Each element can only be PdfObjectInteger.
func (array *PdfObjectArray) ToIntegerArray() ([]int, error)
ToIntegerArray returns a slice of all array elements as an int slice. An error is returned if the array non-integer objects. Each element can only be PdfObjectInteger.
func (array *PdfObjectArray) WriteString() string
WriteString outputs the object as it is to be written to file.
PdfObjectBool represents the primitive PDF boolean object.
type PdfObjectBool bool
func GetBool(obj PdfObject) (bo *PdfObjectBool, found bool)
GetBool returns the *PdfObjectBool object that is represented by a PdfObject directly or indirectly within an indirect object. The bool flag indicates whether a match was found.
func MakeBool(val bool) *PdfObjectBool
MakeBool creates a PdfObjectBool from a bool value.
func (bool *PdfObjectBool) String() string
String returns the state of the bool as "true" or "false".
func (bool *PdfObjectBool) WriteString() string
WriteString outputs the object as it is to be written to file.
PdfObjectDictionary represents the primitive PDF dictionary/map object.
type PdfObjectDictionary struct {
// contains filtered or unexported fields
}
func GetDict(obj PdfObject) (dict *PdfObjectDictionary, found bool)
GetDict returns the *PdfObjectDictionary represented by the PdfObject directly or indirectly within an indirect object. On type mismatch the found bool flag is false and a nil pointer is returned.
func MakeDict() *PdfObjectDictionary
MakeDict creates and returns an empty PdfObjectDictionary.
func MakeDictMap(objmap map[string]PdfObject) *PdfObjectDictionary
MakeDictMap creates a PdfObjectDictionary initialized from a map of keys to values.
func (d *PdfObjectDictionary) Clear()
Clear resets the dictionary to an empty state.
func (d *PdfObjectDictionary) Get(key PdfObjectName) PdfObject
Get returns the PdfObject corresponding to the specified key. Returns a nil value if the key is not set.
func (d *PdfObjectDictionary) GetString(key PdfObjectName) (string, bool)
GetString is a helper for Get that returns a string value. Returns false if the key is missing or a value is not a string.
func (d *PdfObjectDictionary) Keys() []PdfObjectName
Keys returns the list of keys in the dictionary. If `d` is nil returns a nil slice.
func (d *PdfObjectDictionary) Merge(another *PdfObjectDictionary) *PdfObjectDictionary
Merge merges in key/values from another dictionary. Overwriting if has same keys. The mutated dictionary (d) is returned in order to allow method chaining.
func (d *PdfObjectDictionary) Remove(key PdfObjectName)
Remove removes an element specified by key.
func (d *PdfObjectDictionary) Set(key PdfObjectName, val PdfObject)
Set sets the dictionary's key -> val mapping entry. Overwrites if key already set.
func (d *PdfObjectDictionary) SetIfNotNil(key PdfObjectName, val PdfObject)
SetIfNotNil sets the dictionary's key -> val mapping entry -IF- val is not nil. Note that we take care to perform a type switch. Otherwise if we would supply a nil value of another type, e.g. (PdfObjectArray*)(nil), then it would not be a PdfObject(nil) and thus would get set.
func (d *PdfObjectDictionary) String() string
String returns a string describing `d`.
func (d *PdfObjectDictionary) Update(objmap map[string]PdfObject) *PdfObjectDictionary
Update updates multiple keys and returns the dictionary back so can be used in a chained fashion.
func (d *PdfObjectDictionary) WriteString() string
WriteString outputs the object as it is to be written to file.
PdfObjectFloat represents the primitive PDF floating point numerical object.
type PdfObjectFloat float64
func GetFloat(obj PdfObject) (fo *PdfObjectFloat, found bool)
GetFloat returns the *PdfObjectFloat represented by the PdfObject directly or indirectly within an indirect object. On type mismatch the found bool flag is false and a nil pointer is returned.
func MakeFloat(val float64) *PdfObjectFloat
MakeFloat creates an PdfObjectFloat from a float64.
func (float *PdfObjectFloat) String() string
func (float *PdfObjectFloat) WriteString() string
WriteString outputs the object as it is to be written to file.
PdfObjectInteger represents the primitive PDF integer numerical object.
type PdfObjectInteger int64
func GetInt(obj PdfObject) (into *PdfObjectInteger, found bool)
GetInt returns the *PdfObjectBool object that is represented by a PdfObject either directly or indirectly within an indirect object. The bool flag indicates whether a match was found.
func MakeInteger(val int64) *PdfObjectInteger
MakeInteger creates a PdfObjectInteger from an int64.
func (int *PdfObjectInteger) String() string
func (int *PdfObjectInteger) WriteString() string
WriteString outputs the object as it is to be written to file.
PdfObjectName represents the primitive PDF name object.
type PdfObjectName string
func GetName(obj PdfObject) (name *PdfObjectName, found bool)
GetName returns the *PdfObjectName represented by the PdfObject directly or indirectly within an indirect object. On type mismatch the found bool flag is false and a nil pointer is returned.
func MakeName(s string) *PdfObjectName
MakeName creates a PdfObjectName from a string.
func (name *PdfObjectName) String() string
String returns a string representation of `name`.
func (name *PdfObjectName) WriteString() string
WriteString outputs the object as it is to be written to file.
PdfObjectNull represents the primitive PDF null object.
type PdfObjectNull struct{}
func MakeNull() *PdfObjectNull
MakeNull creates an PdfObjectNull.
func (null *PdfObjectNull) String() string
String returns a string describing `null`.
func (null *PdfObjectNull) WriteString() string
WriteString outputs the object as it is to be written to file.
PdfObjectReference represents the primitive PDF reference object.
type PdfObjectReference struct {
ObjectNumber int64
GenerationNumber int64
// contains filtered or unexported fields
}
func (ref *PdfObjectReference) GetParser() *PdfParser
GetParser returns the parser for lazy-loading or compare references.
func (ref *PdfObjectReference) Resolve() PdfObject
Resolve resolves the reference and returns the indirect or stream object. If the reference cannot be resolved, a *PdfObjectNull object is returned.
func (ref *PdfObjectReference) String() string
String returns a string describing `ref`.
func (ref *PdfObjectReference) WriteString() string
WriteString outputs the object as it is to be written to file.
PdfObjectStream represents the primitive PDF Object stream.
type PdfObjectStream struct {
PdfObjectReference
*PdfObjectDictionary
Stream []byte
Lazy bool
TempFile string
}
func GetStream(obj PdfObject) (stream *PdfObjectStream, found bool)
GetStream returns the *PdfObjectStream represented by the PdfObject. On type mismatch the found bool flag is false and a nil pointer is returned.
func MakeStream(contents []byte, encoder StreamEncoder) (*PdfObjectStream, error)
MakeStream creates an PdfObjectStream with specified contents and encoding. If encoding is nil, then raw encoding will be used (i.e. no encoding applied).
func (s *PdfObjectStream) MakeLazy() error
MakeLazy create temporary file for stream to reduce memory usage. It can be used for creating PDF with many images. Temporary files are removed automatically when Write/WriteToFile is called for creator object.
func (stream *PdfObjectStream) String() string
String returns a string describing `stream`.
func (stream *PdfObjectStream) WriteString() string
WriteString outputs the object as it is to be written to file.
PdfObjectStreams represents the primitive PDF object streams. 7.5.7 Object Streams (page 45).
type PdfObjectStreams struct {
PdfObjectReference
// contains filtered or unexported fields
}
func GetObjectStreams(obj PdfObject) (objStream *PdfObjectStreams, found bool)
GetObjectStreams returns the *PdfObjectStreams represented by the PdfObject. On type mismatch the found bool flag is false and a nil pointer is returned.
func MakeObjectStreams(objects ...PdfObject) *PdfObjectStreams
MakeObjectStreams creates an PdfObjectStreams from a list of PdfObjects.
func (streams *PdfObjectStreams) Append(objects ...PdfObject)
Append appends PdfObject(s) to the streams.
func (streams *PdfObjectStreams) Elements() []PdfObject
Elements returns a slice of the PdfObject elements in the array. Preferred over accessing the array directly as type may be changed in future major versions (v3).
func (streams *PdfObjectStreams) Len() int
Len returns the number of elements in the streams.
func (streams *PdfObjectStreams) Set(i int, obj PdfObject) error
Set sets the PdfObject at index i of the streams. An error is returned if the index is outside bounds.
func (streams *PdfObjectStreams) String() string
String returns a string describing `streams`.
func (streams *PdfObjectStreams) WriteString() string
WriteString outputs the object as it is to be written to file.
PdfObjectString represents the primitive PDF string object.
type PdfObjectString struct {
// contains filtered or unexported fields
}
func GetString(obj PdfObject) (so *PdfObjectString, found bool)
GetString returns the *PdfObjectString represented by the PdfObject directly or indirectly within an indirect object. On type mismatch the found bool flag is false and a nil pointer is returned.
func MakeEncodedString(s string, utf16BE bool) *PdfObjectString
MakeEncodedString creates a PdfObjectString with encoded content, which can be either UTF-16BE or PDFDocEncoding depending on whether `utf16BE` is true or false respectively.
func MakeHexString(s string) *PdfObjectString
MakeHexString creates an PdfObjectString from a string intended for output as a hexadecimal string.
func MakeString(s string) *PdfObjectString
MakeString creates an PdfObjectString from a string. NOTE: PDF does not use utf-8 string encoding like Go so `s` will often not be a utf-8 encoded string.
func MakeStringFromBytes(data []byte) *PdfObjectString
MakeStringFromBytes creates an PdfObjectString from a byte array. This is more natural than MakeString as `data` is usually not utf-8 encoded.
func (str *PdfObjectString) Bytes() []byte
Bytes returns the PdfObjectString content as a []byte array.
func (str *PdfObjectString) Decoded() string
Decoded returns the PDFDocEncoding or UTF-16BE decoded string contents. UTF-16BE is applied when the first two bytes are 0xFE, 0XFF, otherwise decoding of PDFDocEncoding is performed.
func (str *PdfObjectString) IsHexadecimal() bool
IsHexadecimal checks if the PdfObjectString contains Hexadecimal data.
func (str *PdfObjectString) Str() string
Str returns the string value of the PdfObjectString. Defined in addition to String() function to clarify that this function returns the underlying string directly, whereas the String function technically could include debug info.
func (str *PdfObjectString) String() string
String returns a string representation of the *PdfObjectString.
func (str *PdfObjectString) WriteString() string
WriteString outputs the object as it is to be written to file.
PdfParser parses a PDF file and provides access to the object structure of the PDF.
type PdfParser struct {
ObjCache objectCache
// contains filtered or unexported fields
}
func NewCompliancePdfParser(rs io.ReadSeeker) (parser *PdfParser, err error)
NewCompliancePdfParser creates a new PdfParser that will parse input reader with the focus on extracting more metadata, which might affect performance of the regular PdfParser this function.
func NewParser(rs io.ReadSeeker) (*PdfParser, error)
NewParser creates a new parser for a PDF file via ReadSeeker. Loads the cross reference stream and trailer. An error is returned on failure.
func NewParserFromString(txt string) *PdfParser
NewParserFromString is used for testing purposes.
func (parser *PdfParser) CheckAccessRights(password []byte) (bool, security.Permissions, error)
CheckAccessRights checks access rights and permissions for a specified password. If either user/owner password is specified, full rights are granted, otherwise the access rights are specified by the Permissions flag.
The bool flag indicates that the user can access and view the file. The AccessPermissions shows what access the user has for editing etc. An error is returned if there was a problem performing the authentication.
func (parser *PdfParser) Decrypt(password []byte) (bool, error)
Decrypt attempts to decrypt the PDF file with a specified password. Also tries to decrypt with an empty password. Returns true if successful, false otherwise. An error is returned when there is a problem with decrypting.
func (parser *PdfParser) GetCrypter() *PdfCrypt
GetCrypter returns the PdfCrypt instance which has information about the PDFs encryption.
func (parser *PdfParser) GetEncryptObj() *PdfIndirectObject
GetEncryptObj returns the PdfIndirectObject which has information about the PDFs encryption details.
func (parser *PdfParser) GetFileOffset() int64
GetFileOffset returns the current file offset, accounting for buffered position.
func (parser *PdfParser) GetObjectNums() []int
GetObjectNums returns a sorted list of object numbers of the PDF objects in the file.
func (parser *PdfParser) GetPreviousRevisionParser() (*PdfParser, error)
GetPreviousRevisionParser returns PdfParser for the previous version of the Pdf document.
func (parser *PdfParser) GetPreviousRevisionReadSeeker() (io.ReadSeeker, error)
GetPreviousRevisionReadSeeker returns ReadSeeker for the previous version of the Pdf document.
func (parser *PdfParser) GetRevision(revisionNumber int) (*PdfParser, error)
GetRevision returns PdfParser for the specific version of the Pdf document.
func (parser *PdfParser) GetRevisionNumber() int
GetRevisionNumber returns the current version of the Pdf document.
func (parser *PdfParser) GetTrailer() *PdfObjectDictionary
GetTrailer returns the PDFs trailer dictionary. The trailer dictionary is typically the starting point for a PDF, referencing other key objects that are important in the document structure.
func (parser *PdfParser) GetUpdatedObjects(prevParser *PdfParser) (map[int64]PdfObject, error)
GetUpdatedObjects returns pdf objects which were updated from the specific version (from prevParser).
func (parser *PdfParser) GetXrefOffset() int64
GetXrefOffset returns the offset of the xref table.
func (parser *PdfParser) GetXrefTable() XrefTable
GetXrefTable returns the PDFs xref table.
func (parser *PdfParser) GetXrefType() *xrefType
GetXrefType returns the type of the first xref object (table or stream).
func (parser *PdfParser) Inspect() (map[string]int, error)
Inspect analyzes the document object structure. Returns a map of object types (by name) with the instance count as value.
func (parser *PdfParser) IsAuthenticated() bool
IsAuthenticated returns true if the PDF has already been authenticated for accessing.
func (parser *PdfParser) IsEncrypted() (bool, error)
IsEncrypted checks if the document is encrypted. A bool flag is returned indicating the result. First time when called, will check if the Encrypt dictionary is accessible through the trailer dictionary. If encrypted, prepares a crypt datastructure which can be used to authenticate and decrypt the document. On failure, an error is returned.
func (parser *PdfParser) LookupByNumber(objNumber int) (PdfObject, error)
LookupByNumber looks up a PdfObject by object number. Returns an error on failure.
func (parser *PdfParser) LookupByReference(ref PdfObjectReference) (PdfObject, error)
LookupByReference looks up a PdfObject by a reference.
func (parser *PdfParser) ParseDict() (*PdfObjectDictionary, error)
ParseDict reads and parses a PDF dictionary object enclosed with '<<' and '>>'
func (parser *PdfParser) ParseIndirectObject() (PdfObject, error)
ParseIndirectObject parses an indirect object from the input stream. Can also be an object stream. Returns the indirect object (*PdfIndirectObject) or the stream object (*PdfObjectStream).
func (parser *PdfParser) ParserMetadata() (ParserMetadata, error)
ParserMetadata gets the pdf parser metadata.
func (parser *PdfParser) PdfVersion() Version
PdfVersion returns version of the PDF file.
func (parser *PdfParser) ReadAtLeast(p []byte, n int) (int, error)
ReadAtLeast reads at least n bytes into slice p. Returns the number of bytes read (should always be == n), and an error on failure.
func (parser *PdfParser) ReadBytesAt(offset, len int64) ([]byte, error)
ReadBytesAt reads byte content at specific offset and length within the PDF.
func (parser *PdfParser) Resolve(obj PdfObject) (PdfObject, error)
Resolve resolves a PdfObject to direct object, looking up and resolving references as needed (unlike TraceToDirect).
func (parser *PdfParser) SetFileOffset(offset int64)
SetFileOffset sets the file to an offset position and resets buffer.
RawEncoder implements Raw encoder/decoder (no encoding, pass through)
type RawEncoder struct{}
func NewRawEncoder() *RawEncoder
NewRawEncoder returns a new instace of RawEncoder.
func (enc *RawEncoder) DecodeBytes(encoded []byte) ([]byte, error)
DecodeBytes returns the passed in slice of bytes. The purpose of the method is to satisfy the StreamEncoder interface.
func (enc *RawEncoder) DecodeStream(streamObj *PdfObjectStream) ([]byte, error)
DecodeStream returns the passed in stream as a slice of bytes. The purpose of the method is to satisfy the StreamEncoder interface.
func (enc *RawEncoder) EncodeBytes(data []byte) ([]byte, error)
EncodeBytes returns the passed in slice of bytes. The purpose of the method is to satisfy the StreamEncoder interface.
func (enc *RawEncoder) GetFilterName() string
GetFilterName returns the name of the encoding filter.
func (enc *RawEncoder) MakeDecodeParams() PdfObject
MakeDecodeParams makes a new instance of an encoding dictionary based on the current encoder settings.
func (enc *RawEncoder) MakeStreamDict() *PdfObjectDictionary
MakeStreamDict makes a new instance of an encoding dictionary for a stream object.
func (enc *RawEncoder) UpdateParams(params *PdfObjectDictionary)
UpdateParams updates the parameter values of the encoder.
RunLengthEncoder represents Run length encoding.
type RunLengthEncoder struct {
}
func NewRunLengthEncoder() *RunLengthEncoder
NewRunLengthEncoder makes a new run length encoder
func (enc *RunLengthEncoder) DecodeBytes(encoded []byte) ([]byte, error)
DecodeBytes decodes a byte slice from Run length encoding.
7.4.5 RunLengthDecode Filter The RunLengthDecode filter decodes data that has been encoded in a simple byte-oriented format based on run length. The encoded data shall be a sequence of runs, where each run shall consist of a length byte followed by 1 to 128 bytes of data. If the length byte is in the range 0 to 127, the following length + 1 (1 to 128) bytes shall be copied literally during decompression. If length is in the range 129 to 255, the following single byte shall be copied 257 - length (2 to 128) times during decompression. A length value of 128 shall denote EOD.
func (enc *RunLengthEncoder) DecodeStream(streamObj *PdfObjectStream) ([]byte, error)
DecodeStream decodes RunLengthEncoded stream object and give back decoded bytes.
func (enc *RunLengthEncoder) EncodeBytes(data []byte) ([]byte, error)
EncodeBytes encodes a bytes array and return the encoded value based on the encoder parameters.
func (enc *RunLengthEncoder) GetFilterName() string
GetFilterName returns the name of the encoding filter.
func (enc *RunLengthEncoder) MakeDecodeParams() PdfObject
MakeDecodeParams makes a new instance of an encoding dictionary based on the current encoder settings.
func (enc *RunLengthEncoder) MakeStreamDict() *PdfObjectDictionary
MakeStreamDict makes a new instance of an encoding dictionary for a stream object.
func (enc *RunLengthEncoder) UpdateParams(params *PdfObjectDictionary)
UpdateParams updates the parameter values of the encoder.
StreamEncoder represents the interface for all PDF stream encoders.
type StreamEncoder interface {
GetFilterName() string
MakeDecodeParams() PdfObject
MakeStreamDict() *PdfObjectDictionary
UpdateParams(params *PdfObjectDictionary)
EncodeBytes(data []byte) ([]byte, error)
DecodeBytes(encoded []byte) ([]byte, error)
DecodeStream(streamObj *PdfObjectStream) ([]byte, error)
}
func NewEncoderFromStream(streamObj *PdfObjectStream) (StreamEncoder, error)
NewEncoderFromStream creates a StreamEncoder based on the stream's dictionary.
Version represents a version of a PDF standard.
type Version struct {
Major int
Minor int
}
func (v Version) String() string
String returns the PDF version as a string. Implements interface fmt.Stringer.
XrefObject defines a cross reference entry which is a map between object number (with generation number) and the location of the actual object, either as a file offset (xref table entry), or as a location within an xref stream object (xref object stream).
type XrefObject struct {
XType xrefType
ObjectNumber int
Generation int
// For normal xrefs (defined by OFFSET)
Offset int64
// For xrefs to object streams.
OsObjNumber int
OsObjIndex int
}
XrefTable represents the cross references in a PDF, i.e. the table of objects and information where to access within the PDF file.
type XrefTable struct {
ObjectMap map[int]XrefObject // Maps object number to XrefObject
// contains filtered or unexported fields
}