diff options
Diffstat (limited to 'src/image/jpeg/reader.go')
-rw-r--r-- | src/image/jpeg/reader.go | 524 |
1 files changed, 524 insertions, 0 deletions
diff --git a/src/image/jpeg/reader.go b/src/image/jpeg/reader.go new file mode 100644 index 000000000..c8fae3cea --- /dev/null +++ b/src/image/jpeg/reader.go @@ -0,0 +1,524 @@ +// Copyright 2009 The Go Authors. All rights reserved. +// Use of this source code is governed by a BSD-style +// license that can be found in the LICENSE file. + +// Package jpeg implements a JPEG image decoder and encoder. +// +// JPEG is defined in ITU-T T.81: http://www.w3.org/Graphics/JPEG/itu-t81.pdf. +package jpeg + +import ( + "image" + "image/color" + "io" +) + +// TODO(nigeltao): fix up the doc comment style so that sentences start with +// the name of the type or function that they annotate. + +// A FormatError reports that the input is not a valid JPEG. +type FormatError string + +func (e FormatError) Error() string { return "invalid JPEG format: " + string(e) } + +// An UnsupportedError reports that the input uses a valid but unimplemented JPEG feature. +type UnsupportedError string + +func (e UnsupportedError) Error() string { return "unsupported JPEG feature: " + string(e) } + +// Component specification, specified in section B.2.2. +type component struct { + h int // Horizontal sampling factor. + v int // Vertical sampling factor. + c uint8 // Component identifier. + tq uint8 // Quantization table destination selector. +} + +const ( + dcTable = 0 + acTable = 1 + maxTc = 1 + maxTh = 3 + maxTq = 3 + + // A grayscale JPEG image has only a Y component. + nGrayComponent = 1 + // A color JPEG image has Y, Cb and Cr components. + nColorComponent = 3 + + // We only support 4:4:4, 4:4:0, 4:2:2 and 4:2:0 downsampling, and therefore the + // number of luma samples per chroma sample is at most 2 in the horizontal + // and 2 in the vertical direction. + maxH = 2 + maxV = 2 +) + +const ( + soiMarker = 0xd8 // Start Of Image. + eoiMarker = 0xd9 // End Of Image. + sof0Marker = 0xc0 // Start Of Frame (Baseline). + sof2Marker = 0xc2 // Start Of Frame (Progressive). + dhtMarker = 0xc4 // Define Huffman Table. + dqtMarker = 0xdb // Define Quantization Table. + sosMarker = 0xda // Start Of Scan. + driMarker = 0xdd // Define Restart Interval. + rst0Marker = 0xd0 // ReSTart (0). + rst7Marker = 0xd7 // ReSTart (7). + app0Marker = 0xe0 // APPlication specific (0). + app15Marker = 0xef // APPlication specific (15). + comMarker = 0xfe // COMment. +) + +// unzig maps from the zig-zag ordering to the natural ordering. For example, +// unzig[3] is the column and row of the fourth element in zig-zag order. The +// value is 16, which means first column (16%8 == 0) and third row (16/8 == 2). +var unzig = [blockSize]int{ + 0, 1, 8, 16, 9, 2, 3, 10, + 17, 24, 32, 25, 18, 11, 4, 5, + 12, 19, 26, 33, 40, 48, 41, 34, + 27, 20, 13, 6, 7, 14, 21, 28, + 35, 42, 49, 56, 57, 50, 43, 36, + 29, 22, 15, 23, 30, 37, 44, 51, + 58, 59, 52, 45, 38, 31, 39, 46, + 53, 60, 61, 54, 47, 55, 62, 63, +} + +// Reader is deprecated. +type Reader interface { + io.ByteReader + io.Reader +} + +// bits holds the unprocessed bits that have been taken from the byte-stream. +// The n least significant bits of a form the unread bits, to be read in MSB to +// LSB order. +type bits struct { + a uint32 // accumulator. + m uint32 // mask. m==1<<(n-1) when n>0, with m==0 when n==0. + n int32 // the number of unread bits in a. +} + +type decoder struct { + r io.Reader + bits bits + // bytes is a byte buffer, similar to a bufio.Reader, except that it + // has to be able to unread more than 1 byte, due to byte stuffing. + // Byte stuffing is specified in section F.1.2.3. + bytes struct { + // buf[i:j] are the buffered bytes read from the underlying + // io.Reader that haven't yet been passed further on. + buf [4096]byte + i, j int + // nUnreadable is the number of bytes to back up i after + // overshooting. It can be 0, 1 or 2. + nUnreadable int + } + width, height int + img1 *image.Gray + img3 *image.YCbCr + ri int // Restart Interval. + nComp int + progressive bool + eobRun uint16 // End-of-Band run, specified in section G.1.2.2. + comp [nColorComponent]component + progCoeffs [nColorComponent][]block // Saved state between progressive-mode scans. + huff [maxTc + 1][maxTh + 1]huffman + quant [maxTq + 1]block // Quantization tables, in zig-zag order. + tmp [blockSize + 1]byte +} + +// fill fills up the d.bytes.buf buffer from the underlying io.Reader. It +// should only be called when there are no unread bytes in d.bytes. +func (d *decoder) fill() error { + if d.bytes.i != d.bytes.j { + panic("jpeg: fill called when unread bytes exist") + } + // Move the last 2 bytes to the start of the buffer, in case we need + // to call unreadByteStuffedByte. + if d.bytes.j > 2 { + d.bytes.buf[0] = d.bytes.buf[d.bytes.j-2] + d.bytes.buf[1] = d.bytes.buf[d.bytes.j-1] + d.bytes.i, d.bytes.j = 2, 2 + } + // Fill in the rest of the buffer. + n, err := d.r.Read(d.bytes.buf[d.bytes.j:]) + d.bytes.j += n + return err +} + +// unreadByteStuffedByte undoes the most recent readByteStuffedByte call, +// giving a byte of data back from d.bits to d.bytes. The Huffman look-up table +// requires at least 8 bits for look-up, which means that Huffman decoding can +// sometimes overshoot and read one or two too many bytes. Two-byte overshoot +// can happen when expecting to read a 0xff 0x00 byte-stuffed byte. +func (d *decoder) unreadByteStuffedByte() { + if d.bytes.nUnreadable == 0 { + panic("jpeg: unreadByteStuffedByte call cannot be fulfilled") + } + d.bytes.i -= d.bytes.nUnreadable + d.bytes.nUnreadable = 0 + if d.bits.n >= 8 { + d.bits.a >>= 8 + d.bits.n -= 8 + d.bits.m >>= 8 + } +} + +// readByte returns the next byte, whether buffered or not buffered. It does +// not care about byte stuffing. +func (d *decoder) readByte() (x byte, err error) { + for d.bytes.i == d.bytes.j { + if err = d.fill(); err != nil { + return 0, err + } + } + x = d.bytes.buf[d.bytes.i] + d.bytes.i++ + d.bytes.nUnreadable = 0 + return x, nil +} + +// errMissingFF00 means that readByteStuffedByte encountered an 0xff byte (a +// marker byte) that wasn't the expected byte-stuffed sequence 0xff, 0x00. +var errMissingFF00 = FormatError("missing 0xff00 sequence") + +// readByteStuffedByte is like readByte but is for byte-stuffed Huffman data. +func (d *decoder) readByteStuffedByte() (x byte, err error) { + // Take the fast path if d.bytes.buf contains at least two bytes. + if d.bytes.i+2 <= d.bytes.j { + x = d.bytes.buf[d.bytes.i] + d.bytes.i++ + d.bytes.nUnreadable = 1 + if x != 0xff { + return x, err + } + if d.bytes.buf[d.bytes.i] != 0x00 { + return 0, errMissingFF00 + } + d.bytes.i++ + d.bytes.nUnreadable = 2 + return 0xff, nil + } + + x, err = d.readByte() + if err != nil { + return 0, err + } + if x != 0xff { + d.bytes.nUnreadable = 1 + return x, nil + } + + x, err = d.readByte() + if err != nil { + d.bytes.nUnreadable = 1 + return 0, err + } + d.bytes.nUnreadable = 2 + if x != 0x00 { + return 0, errMissingFF00 + } + return 0xff, nil +} + +// readFull reads exactly len(p) bytes into p. It does not care about byte +// stuffing. +func (d *decoder) readFull(p []byte) error { + // Unread the overshot bytes, if any. + if d.bytes.nUnreadable != 0 { + if d.bits.n >= 8 { + d.unreadByteStuffedByte() + } + d.bytes.nUnreadable = 0 + } + + for { + n := copy(p, d.bytes.buf[d.bytes.i:d.bytes.j]) + p = p[n:] + d.bytes.i += n + if len(p) == 0 { + break + } + if err := d.fill(); err != nil { + if err == io.EOF { + err = io.ErrUnexpectedEOF + } + return err + } + } + return nil +} + +// ignore ignores the next n bytes. +func (d *decoder) ignore(n int) error { + // Unread the overshot bytes, if any. + if d.bytes.nUnreadable != 0 { + if d.bits.n >= 8 { + d.unreadByteStuffedByte() + } + d.bytes.nUnreadable = 0 + } + + for { + m := d.bytes.j - d.bytes.i + if m > n { + m = n + } + d.bytes.i += m + n -= m + if n == 0 { + break + } + if err := d.fill(); err != nil { + if err == io.EOF { + err = io.ErrUnexpectedEOF + } + return err + } + } + return nil +} + +// Specified in section B.2.2. +func (d *decoder) processSOF(n int) error { + switch n { + case 6 + 3*nGrayComponent: + d.nComp = nGrayComponent + case 6 + 3*nColorComponent: + d.nComp = nColorComponent + default: + return UnsupportedError("SOF has wrong length") + } + if err := d.readFull(d.tmp[:n]); err != nil { + return err + } + // We only support 8-bit precision. + if d.tmp[0] != 8 { + return UnsupportedError("precision") + } + d.height = int(d.tmp[1])<<8 + int(d.tmp[2]) + d.width = int(d.tmp[3])<<8 + int(d.tmp[4]) + if int(d.tmp[5]) != d.nComp { + return UnsupportedError("SOF has wrong number of image components") + } + for i := 0; i < d.nComp; i++ { + d.comp[i].c = d.tmp[6+3*i] + d.comp[i].tq = d.tmp[8+3*i] + if d.nComp == nGrayComponent { + // If a JPEG image has only one component, section A.2 says "this data + // is non-interleaved by definition" and section A.2.2 says "[in this + // case...] the order of data units within a scan shall be left-to-right + // and top-to-bottom... regardless of the values of H_1 and V_1". Section + // 4.8.2 also says "[for non-interleaved data], the MCU is defined to be + // one data unit". Similarly, section A.1.1 explains that it is the ratio + // of H_i to max_j(H_j) that matters, and similarly for V. For grayscale + // images, H_1 is the maximum H_j for all components j, so that ratio is + // always 1. The component's (h, v) is effectively always (1, 1): even if + // the nominal (h, v) is (2, 1), a 20x5 image is encoded in three 8x8 + // MCUs, not two 16x8 MCUs. + d.comp[i].h = 1 + d.comp[i].v = 1 + continue + } + hv := d.tmp[7+3*i] + d.comp[i].h = int(hv >> 4) + d.comp[i].v = int(hv & 0x0f) + // For color images, we only support 4:4:4, 4:4:0, 4:2:2 or 4:2:0 chroma + // downsampling ratios. This implies that the (h, v) values for the Y + // component are either (1, 1), (1, 2), (2, 1) or (2, 2), and the (h, v) + // values for the Cr and Cb components must be (1, 1). + if i == 0 { + if hv != 0x11 && hv != 0x21 && hv != 0x22 && hv != 0x12 { + return UnsupportedError("luma/chroma downsample ratio") + } + } else if hv != 0x11 { + return UnsupportedError("luma/chroma downsample ratio") + } + } + return nil +} + +// Specified in section B.2.4.1. +func (d *decoder) processDQT(n int) error { + const qtLength = 1 + blockSize + for ; n >= qtLength; n -= qtLength { + if err := d.readFull(d.tmp[:qtLength]); err != nil { + return err + } + pq := d.tmp[0] >> 4 + if pq != 0 { + return UnsupportedError("bad Pq value") + } + tq := d.tmp[0] & 0x0f + if tq > maxTq { + return FormatError("bad Tq value") + } + for i := range d.quant[tq] { + d.quant[tq][i] = int32(d.tmp[i+1]) + } + } + if n != 0 { + return FormatError("DQT has wrong length") + } + return nil +} + +// Specified in section B.2.4.4. +func (d *decoder) processDRI(n int) error { + if n != 2 { + return FormatError("DRI has wrong length") + } + if err := d.readFull(d.tmp[:2]); err != nil { + return err + } + d.ri = int(d.tmp[0])<<8 + int(d.tmp[1]) + return nil +} + +// decode reads a JPEG image from r and returns it as an image.Image. +func (d *decoder) decode(r io.Reader, configOnly bool) (image.Image, error) { + d.r = r + + // Check for the Start Of Image marker. + if err := d.readFull(d.tmp[:2]); err != nil { + return nil, err + } + if d.tmp[0] != 0xff || d.tmp[1] != soiMarker { + return nil, FormatError("missing SOI marker") + } + + // Process the remaining segments until the End Of Image marker. + for { + err := d.readFull(d.tmp[:2]) + if err != nil { + return nil, err + } + for d.tmp[0] != 0xff { + // Strictly speaking, this is a format error. However, libjpeg is + // liberal in what it accepts. As of version 9, next_marker in + // jdmarker.c treats this as a warning (JWRN_EXTRANEOUS_DATA) and + // continues to decode the stream. Even before next_marker sees + // extraneous data, jpeg_fill_bit_buffer in jdhuff.c reads as many + // bytes as it can, possibly past the end of a scan's data. It + // effectively puts back any markers that it overscanned (e.g. an + // "\xff\xd9" EOI marker), but it does not put back non-marker data, + // and thus it can silently ignore a small number of extraneous + // non-marker bytes before next_marker has a chance to see them (and + // print a warning). + // + // We are therefore also liberal in what we accept. Extraneous data + // is silently ignored. + // + // This is similar to, but not exactly the same as, the restart + // mechanism within a scan (the RST[0-7] markers). + // + // Note that extraneous 0xff bytes in e.g. SOS data are escaped as + // "\xff\x00", and so are detected a little further down below. + d.tmp[0] = d.tmp[1] + d.tmp[1], err = d.readByte() + if err != nil { + return nil, err + } + } + marker := d.tmp[1] + if marker == 0 { + // Treat "\xff\x00" as extraneous data. + continue + } + for marker == 0xff { + // Section B.1.1.2 says, "Any marker may optionally be preceded by any + // number of fill bytes, which are bytes assigned code X'FF'". + marker, err = d.readByte() + if err != nil { + return nil, err + } + } + if marker == eoiMarker { // End Of Image. + break + } + if rst0Marker <= marker && marker <= rst7Marker { + // Figures B.2 and B.16 of the specification suggest that restart markers should + // only occur between Entropy Coded Segments and not after the final ECS. + // However, some encoders may generate incorrect JPEGs with a final restart + // marker. That restart marker will be seen here instead of inside the processSOS + // method, and is ignored as a harmless error. Restart markers have no extra data, + // so we check for this before we read the 16-bit length of the segment. + continue + } + + // Read the 16-bit length of the segment. The value includes the 2 bytes for the + // length itself, so we subtract 2 to get the number of remaining bytes. + if err = d.readFull(d.tmp[:2]); err != nil { + return nil, err + } + n := int(d.tmp[0])<<8 + int(d.tmp[1]) - 2 + if n < 0 { + return nil, FormatError("short segment length") + } + + switch { + case marker == sof0Marker || marker == sof2Marker: // Start Of Frame. + d.progressive = marker == sof2Marker + err = d.processSOF(n) + if configOnly { + return nil, err + } + case marker == dhtMarker: // Define Huffman Table. + err = d.processDHT(n) + case marker == dqtMarker: // Define Quantization Table. + err = d.processDQT(n) + case marker == sosMarker: // Start Of Scan. + err = d.processSOS(n) + case marker == driMarker: // Define Restart Interval. + err = d.processDRI(n) + case app0Marker <= marker && marker <= app15Marker || marker == comMarker: // APPlication specific, or COMment. + err = d.ignore(n) + default: + err = UnsupportedError("unknown marker") + } + if err != nil { + return nil, err + } + } + if d.img1 != nil { + return d.img1, nil + } + if d.img3 != nil { + return d.img3, nil + } + return nil, FormatError("missing SOS marker") +} + +// Decode reads a JPEG image from r and returns it as an image.Image. +func Decode(r io.Reader) (image.Image, error) { + var d decoder + return d.decode(r, false) +} + +// DecodeConfig returns the color model and dimensions of a JPEG image without +// decoding the entire image. +func DecodeConfig(r io.Reader) (image.Config, error) { + var d decoder + if _, err := d.decode(r, true); err != nil { + return image.Config{}, err + } + switch d.nComp { + case nGrayComponent: + return image.Config{ + ColorModel: color.GrayModel, + Width: d.width, + Height: d.height, + }, nil + case nColorComponent: + return image.Config{ + ColorModel: color.YCbCrModel, + Width: d.width, + Height: d.height, + }, nil + } + return image.Config{}, FormatError("missing SOF marker") +} + +func init() { + image.RegisterFormat("jpeg", "\xff\xd8", Decode, DecodeConfig) +} |