diff options
Diffstat (limited to 'node_modules/seek-bzip')
| -rw-r--r-- | node_modules/seek-bzip/LICENSE | 26 | ||||
| -rw-r--r-- | node_modules/seek-bzip/README.md | 185 | ||||
| -rw-r--r-- | node_modules/seek-bzip/bin/seek-bunzip | 129 | ||||
| -rw-r--r-- | node_modules/seek-bzip/bin/seek-bzip-table | 71 | ||||
| -rw-r--r-- | node_modules/seek-bzip/lib/bitreader.js | 94 | ||||
| -rw-r--r-- | node_modules/seek-bzip/lib/crc32.js | 104 | ||||
| -rw-r--r-- | node_modules/seek-bzip/lib/index.js | 605 | ||||
| -rw-r--r-- | node_modules/seek-bzip/lib/stream.js | 42 | ||||
| -rw-r--r-- | node_modules/seek-bzip/package.json | 34 |
9 files changed, 1290 insertions, 0 deletions
diff --git a/node_modules/seek-bzip/LICENSE b/node_modules/seek-bzip/LICENSE new file mode 100644 index 0000000..8bfd775 --- /dev/null +++ b/node_modules/seek-bzip/LICENSE @@ -0,0 +1,26 @@ +The MIT License (MIT) + +Copyright © 2013-2015 C. Scott Ananian + +Copyright © 2012-2015 Eli Skeggs + +Copyright © 2011 Kevin Kwok + +Permission is hereby granted, free of charge, to any person obtaining +a copy of this software and associated documentation files (the +"Software"), to deal in the Software without restriction, including +without limitation the rights to use, copy, modify, merge, publish, +distribute, sublicense, and/or sell copies of the Software, and to +permit persons to whom the Software is furnished to do so, subject to +the following conditions: + +The above copyright notice and this permission notice shall be +included in all copies or substantial portions of the Software. + +THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, +EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF +MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND +NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE +LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION +OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION +WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. diff --git a/node_modules/seek-bzip/README.md b/node_modules/seek-bzip/README.md new file mode 100644 index 0000000..9a6f368 --- /dev/null +++ b/node_modules/seek-bzip/README.md @@ -0,0 +1,185 @@ +# seek-bzip + +[![Build Status][1]][2] [![dependency status][3]][4] [![dev dependency status][5]][6] + +`seek-bzip` is a pure-javascript Node.JS module adapted from [node-bzip](https://github.com/skeggse/node-bzip) and before that [antimatter15's pure-javascript bzip2 decoder](https://github.com/antimatter15/bzip2.js). Like these projects, `seek-bzip` only does decompression (see [compressjs](https://github.com/cscott/compressjs) if you need compression code). Unlike those other projects, `seek-bzip` can seek to and decode single blocks from the bzip2 file. + +`seek-bzip` primarily decodes buffers into other buffers, synchronously. +With the help of the [fibers](https://github.com/laverdet/node-fibers) +package, it can operate on node streams; see `test/stream.js` for an +example. + +## How to Install + +``` +npm install seek-bzip +``` + +This package uses +[Typed Arrays](https://developer.mozilla.org/en-US/docs/JavaScript/Typed_arrays), which are present in node.js >= 0.5.5. + +## Usage + +After compressing some example data into `example.bz2`, the following will recreate that original data and save it to `example`: + +``` +var Bunzip = require('seek-bzip'); +var fs = require('fs'); + +var compressedData = fs.readFileSync('example.bz2'); +var data = Bunzip.decode(compressedData); + +fs.writeFileSync('example', data); +``` + +See the tests in the `tests/` directory for further usage examples. + +For uncompressing single blocks of bzip2-compressed data, you will need +an out-of-band index listing the start of each bzip2 block. (Presumably +you generate this at the same time as you index the start of the information +you wish to seek to inside the compressed file.) The `seek-bzip` module +has been designed to be compatible with the C implementation `seek-bzip2` +available from https://bitbucket.org/james_taylor/seek-bzip2. That codebase +contains a `bzip-table` tool which will generate bzip2 block start indices. +There is also a pure-JavaScript `seek-bzip-table` tool in this package's +`bin` directory. + +## Documentation + +`require('seek-bzip')` returns a `Bunzip` object. It contains three static +methods. The first is a function accepting one or two parameters: + +`Bunzip.decode = function(input, [Number expectedSize] or [output], [boolean multistream])` + +The `input` argument can be a "stream" object (which must implement the +`readByte` method), or a `Buffer`. + +If `expectedSize` is not present, `decodeBzip` simply decodes `input` and +returns the resulting `Buffer`. + +If `expectedSize` is present (and numeric), `decodeBzip` will store +the results in a `Buffer` of length `expectedSize`, and throw an error +in the case that the size of the decoded data does not match +`expectedSize`. + +If you pass a non-numeric second parameter, it can either be a `Buffer` +object (which must be of the correct length; an error will be thrown if +the size of the decoded data does not match the buffer length) or +a "stream" object (which must implement a `writeByte` method). + +The optional third `multistream` parameter, if true, attempts to continue +reading past the end of the bzip2 file. This supports "multistream" +bzip2 files, which are simply multiple bzip2 files concatenated together. +If this argument is true, the input stream must have an `eof` method +which returns true when the end of the input has been reached. + +The second exported method is a function accepting two or three parameters: + +`Bunzip.decodeBlock = function(input, Number blockStartBits, [Number expectedSize] or [output])` + +The `input` and `expectedSize`/`output` parameters are as above. +The `blockStartBits` parameter gives the start of the desired block, in bits. + +If passing a stream as the `input` parameter, it must implement the +`seek` method. + +The final exported method is a function accepting two or three parameters: + +`Bunzip.table = function(input, Function callback, [boolean multistream])` + +The `input` and `multistream` parameters are identical to those for the +`decode` method. + +This function will invoke `callback(position, size)` once per bzip2 block, +where `position` gives the starting position of the block (in *bits*), and +`size` gives the uncompressed size of the block (in bytes). + +This can be used to construct an index allowing direct access to a particular +block inside a bzip2 file, using the `decodeBlock` method. + +## Command-line +There are binaries available in bin. The first generates an index of all +the blocks in a bzip2-compressed file: +``` +$ bin/seek-bzip-table test/sample4.bz2 +32 99981 +320555 99981 +606348 99981 +847568 99981 +1089094 99981 +1343625 99981 +1596228 99981 +1843336 99981 +2090919 99981 +2342106 39019 +$ +``` +The first field is the starting position of the block, in bits, and the +second field is the length of the block, in bytes. + +The second binary decodes an arbitrary block of a bzip2 file: +``` +$ bin/seek-bunzip -d -b 2342106 test/sample4.bz2 | tail +élan's +émigré +émigré's +émigrés +épée +épée's +épées +étude +étude's +études +$ +``` + +Use `--help` to see other options. + +## Help wanted + +Improvements to this module would be generally useful. +Feel free to fork on github and submit pull requests! + +## Related projects + +* https://github.com/skeggse/node-bzip node-bzip (original upstream source) +* https://github.com/cscott/compressjs + Lots of compression/decompression algorithms from the same author as this + module, including bzip2 compression code. +* https://github.com/cscott/lzjb fast LZJB compression/decompression + +## License + +#### MIT License + +> Copyright © 2013-2015 C. Scott Ananian +> +> Copyright © 2012-2015 Eli Skeggs +> +> Copyright © 2011 Kevin Kwok +> +> Permission is hereby granted, free of charge, to any person obtaining +> a copy of this software and associated documentation files (the +> "Software"), to deal in the Software without restriction, including +> without limitation the rights to use, copy, modify, merge, publish, +> distribute, sublicense, and/or sell copies of the Software, and to +> permit persons to whom the Software is furnished to do so, subject to +> the following conditions: +> +> The above copyright notice and this permission notice shall be +> included in all copies or substantial portions of the Software. +> +> THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, +> EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF +> MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND +> NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE +> LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION +> OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION +> WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. + +[1]: https://travis-ci.org/cscott/seek-bzip.png +[2]: https://travis-ci.org/cscott/seek-bzip +[3]: https://david-dm.org/cscott/seek-bzip.png +[4]: https://david-dm.org/cscott/seek-bzip +[5]: https://david-dm.org/cscott/seek-bzip/dev-status.png +[6]: https://david-dm.org/cscott/seek-bzip#info=devDependencies diff --git a/node_modules/seek-bzip/bin/seek-bunzip b/node_modules/seek-bzip/bin/seek-bunzip new file mode 100644 index 0000000..da117fc --- /dev/null +++ b/node_modules/seek-bzip/bin/seek-bunzip @@ -0,0 +1,129 @@ +#!/usr/bin/env node + +var program = require('commander'); +var Bunzip = require('../'); +var fs = require('fs'); + +program + .version(Bunzip.version) + .usage('-d|-z [infile] [outfile]') + .option('-d, --decompress', + 'Decompress stdin to stdout') + //.option('-z, --compress', + // 'Compress stdin to stdout') + .option('-b, --block <n>', + 'Extract a single block, starting at <n> bits.', undefined) + .option('-m, --multistream', + 'Read a multistream bzip2 file'); +program.on('--help', function() { + console.log(' If <infile> is omitted, reads from stdin.'); + console.log(' If <outfile> is omitted, writes to stdout.'); +}); +program.parse(process.argv); + +if (!program.compress) { program.decompress = true; } + +if (program.compress && program.block !== undefined) { + console.error('--block can only be used with decompression'); + return 1; +} + +if (program.decompress && program.compress) { + console.error('Must specify either -d or -z.'); + return 1; +} + +var makeInStream = function(in_fd) { + var stat = fs.fstatSync(in_fd); + var stream = { + buffer: new Buffer(4096), + filePos: null, + pos: 0, + end: 0, + _fillBuffer: function() { + this.end = fs.readSync(in_fd, this.buffer, 0, this.buffer.length, + this.filePos); + this.pos = 0; + if (this.filePos !== null && this.end > 0) { + this.filePos += this.end; + } + }, + readByte: function() { + if (this.pos >= this.end) { this._fillBuffer(); } + if (this.pos < this.end) { + return this.buffer[this.pos++]; + } + return -1; + }, + read: function(buffer, bufOffset, length) { + if (this.pos >= this.end) { this._fillBuffer(); } + var bytesRead = 0; + while (bytesRead < length && this.pos < this.end) { + buffer[bufOffset++] = this.buffer[this.pos++]; + bytesRead++; + } + return bytesRead; + }, + seek: function(seek_pos) { + this.filePos = seek_pos; + this.pos = this.end = 0; + }, + eof: function() { + if (this.pos >= this.end) { this._fillBuffer(); } + return !(this.pos < this.end); + } + }; + if (stat.size) { + stream.size = stat.size; + } + return stream; +}; +var makeOutStream = function(out_fd) { + return { + buffer: new Buffer(4096), + pos: 0, + flush: function() { + fs.writeSync(out_fd, this.buffer, 0, this.pos); + this.pos = 0; + }, + writeByte: function(byte) { + if (this.pos >= this.buffer.length) { this.flush(); } + this.buffer[this.pos++] = byte; + } + }; +}; + +var in_fd = 0, close_in = function(){}; +var out_fd = 1, close_out = function(){}; +if (program.args.length > 0) { + in_fd = fs.openSync(program.args.shift(), 'r'); + close_in = function() { fs.closeSync(in_fd); }; +} +if (program.args.length > 0) { + out_fd = fs.openSync(program.args.shift(), 'w'); + close_out = function() { fs.closeSync(out_fd); }; +} + +var inStream = makeInStream(in_fd); +var outStream= makeOutStream(out_fd); + +if (program.decompress) { + try { + if (program.block !== undefined) { + Bunzip.decodeBlock(inStream, +program.block, outStream); + } else { + Bunzip.decode(inStream, outStream, program.multistream); + } + outStream.flush(); + } catch (e) { + if (e.code !== 'EPIPE') throw e; + } + close_in(); + close_out(); + return 0; +} +if (program.compress) { + console.error('Compression not yet implemented.'); + return 1; +} +return 1; diff --git a/node_modules/seek-bzip/bin/seek-bzip-table b/node_modules/seek-bzip/bin/seek-bzip-table new file mode 100644 index 0000000..9d852b3 --- /dev/null +++ b/node_modules/seek-bzip/bin/seek-bzip-table @@ -0,0 +1,71 @@ +#!/usr/bin/env node + +var program = require('commander'); +var Bunzip = require('../'); +var fs = require('fs'); + +program + .version(Bunzip.version) + .usage('[infile]') + .option('-m, --multistream', + 'Read a multistream bzip2 file'); +program.on('--help', function() { + console.log(' If <infile> is omitted, reads from stdin.'); +}); +program.parse(process.argv); + +var makeInStream = function(in_fd) { + var stat = fs.fstatSync(in_fd); + var stream = { + buffer: new Buffer(4096), + totalPos: 0, + pos: 0, + end: 0, + _fillBuffer: function() { + this.end = fs.readSync(in_fd, this.buffer, 0, this.buffer.length); + this.pos = 0; + }, + readByte: function() { + if (this.pos >= this.end) { this._fillBuffer(); } + if (this.pos < this.end) { + this.totalPos++; + return this.buffer[this.pos++]; + } + return -1; + }, + read: function(buffer, bufOffset, length) { + if (this.pos >= this.end) { this._fillBuffer(); } + var bytesRead = 0; + while (bytesRead < length && this.pos < this.end) { + buffer[bufOffset++] = this.buffer[this.pos++]; + bytesRead++; + } + this.totalPos += bytesRead; + return bytesRead; + }, + eof: function() { + if (this.pos >= this.end) { this._fillBuffer(); } + return !(this.pos < this.end); + } + }; + if (stat.size) { + stream.size = stat.size; + } + return stream; +}; + +var in_fd = 0, close_in = function(){}; +if (program.args.length > 0) { + in_fd = fs.openSync(program.args.shift(), 'r'); + close_in = function() { fs.closeSync(in_fd); }; +} + +var inStream = makeInStream(in_fd); + +var report = function(position, blocksize) { + console.log(position+'\t'+blocksize); +}; + +Bunzip.table(inStream, report, program.multistream); +close_in(); +return 0; diff --git a/node_modules/seek-bzip/lib/bitreader.js b/node_modules/seek-bzip/lib/bitreader.js new file mode 100644 index 0000000..7bcb396 --- /dev/null +++ b/node_modules/seek-bzip/lib/bitreader.js @@ -0,0 +1,94 @@ +/* +node-bzip - a pure-javascript Node.JS module for decoding bzip2 data + +Copyright (C) 2012 Eli Skeggs + +Permission is hereby granted, free of charge, to any person obtaining +a copy of this software and associated documentation files (the +"Software"), to deal in the Software without restriction, including +without limitation the rights to use, copy, modify, merge, publish, +distribute, sublicense, and/or sell copies of the Software, and to +permit persons to whom the Software is furnished to do so, subject to +the following conditions: + +The above copyright notice and this permission notice shall be +included in all copies or substantial portions of the Software. + +THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, +EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF +MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND +NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE +LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION +OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION +WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. + +Adapted from bzip2.js, copyright 2011 antimatter15 (antimatter15@gmail.com). + +Based on micro-bunzip by Rob Landley (rob@landley.net). + +Based on bzip2 decompression code by Julian R Seward (jseward@acm.org), +which also acknowledges contributions by Mike Burrows, David Wheeler, +Peter Fenwick, Alistair Moffat, Radford Neal, Ian H. Witten, +Robert Sedgewick, and Jon L. Bentley. +*/ + +var BITMASK = [0x00, 0x01, 0x03, 0x07, 0x0F, 0x1F, 0x3F, 0x7F, 0xFF]; + +// offset in bytes +var BitReader = function(stream) { + this.stream = stream; + this.bitOffset = 0; + this.curByte = 0; + this.hasByte = false; +}; + +BitReader.prototype._ensureByte = function() { + if (!this.hasByte) { + this.curByte = this.stream.readByte(); + this.hasByte = true; + } +}; + +// reads bits from the buffer +BitReader.prototype.read = function(bits) { + var result = 0; + while (bits > 0) { + this._ensureByte(); + var remaining = 8 - this.bitOffset; + // if we're in a byte + if (bits >= remaining) { + result <<= remaining; + result |= BITMASK[remaining] & this.curByte; + this.hasByte = false; + this.bitOffset = 0; + bits -= remaining; + } else { + result <<= bits; + var shift = remaining - bits; + result |= (this.curByte & (BITMASK[bits] << shift)) >> shift; + this.bitOffset += bits; + bits = 0; + } + } + return result; +}; + +// seek to an arbitrary point in the buffer (expressed in bits) +BitReader.prototype.seek = function(pos) { + var n_bit = pos % 8; + var n_byte = (pos - n_bit) / 8; + this.bitOffset = n_bit; + this.stream.seek(n_byte); + this.hasByte = false; +}; + +// reads 6 bytes worth of data using the read method +BitReader.prototype.pi = function() { + var buf = new Buffer(6), i; + for (i = 0; i < buf.length; i++) { + buf[i] = this.read(8); + } + return buf.toString('hex'); +}; + +module.exports = BitReader; diff --git a/node_modules/seek-bzip/lib/crc32.js b/node_modules/seek-bzip/lib/crc32.js new file mode 100644 index 0000000..8c9a169 --- /dev/null +++ b/node_modules/seek-bzip/lib/crc32.js @@ -0,0 +1,104 @@ +/* CRC32, used in Bzip2 implementation. + * This is a port of CRC32.java from the jbzip2 implementation at + * https://code.google.com/p/jbzip2 + * which is: + * Copyright (c) 2011 Matthew Francis + * + * Permission is hereby granted, free of charge, to any person + * obtaining a copy of this software and associated documentation + * files (the "Software"), to deal in the Software without + * restriction, including without limitation the rights to use, + * copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following + * conditions: + * + * The above copyright notice and this permission notice shall be + * included in all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES + * OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT + * HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, + * WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + * This JavaScript implementation is: + * Copyright (c) 2013 C. Scott Ananian + * with the same licensing terms as Matthew Francis' original implementation. + */ +module.exports = (function() { + + /** + * A static CRC lookup table + */ + var crc32Lookup = new Uint32Array([ + 0x00000000, 0x04c11db7, 0x09823b6e, 0x0d4326d9, 0x130476dc, 0x17c56b6b, 0x1a864db2, 0x1e475005, + 0x2608edb8, 0x22c9f00f, 0x2f8ad6d6, 0x2b4bcb61, 0x350c9b64, 0x31cd86d3, 0x3c8ea00a, 0x384fbdbd, + 0x4c11db70, 0x48d0c6c7, 0x4593e01e, 0x4152fda9, 0x5f15adac, 0x5bd4b01b, 0x569796c2, 0x52568b75, + 0x6a1936c8, 0x6ed82b7f, 0x639b0da6, 0x675a1011, 0x791d4014, 0x7ddc5da3, 0x709f7b7a, 0x745e66cd, + 0x9823b6e0, 0x9ce2ab57, 0x91a18d8e, 0x95609039, 0x8b27c03c, 0x8fe6dd8b, 0x82a5fb52, 0x8664e6e5, + 0xbe2b5b58, 0xbaea46ef, 0xb7a96036, 0xb3687d81, 0xad2f2d84, 0xa9ee3033, 0xa4ad16ea, 0xa06c0b5d, + 0xd4326d90, 0xd0f37027, 0xddb056fe, 0xd9714b49, 0xc7361b4c, 0xc3f706fb, 0xceb42022, 0xca753d95, + 0xf23a8028, 0xf6fb9d9f, 0xfbb8bb46, 0xff79a6f1, 0xe13ef6f4, 0xe5ffeb43, 0xe8bccd9a, 0xec7dd02d, + 0x34867077, 0x30476dc0, 0x3d044b19, 0x39c556ae, 0x278206ab, 0x23431b1c, 0x2e003dc5, 0x2ac12072, + 0x128e9dcf, 0x164f8078, 0x1b0ca6a1, 0x1fcdbb16, 0x018aeb13, 0x054bf6a4, 0x0808d07d, 0x0cc9cdca, + 0x7897ab07, 0x7c56b6b0, 0x71159069, 0x75d48dde, 0x6b93dddb, 0x6f52c06c, 0x6211e6b5, 0x66d0fb02, + 0x5e9f46bf, 0x5a5e5b08, 0x571d7dd1, 0x53dc6066, 0x4d9b3063, 0x495a2dd4, 0x44190b0d, 0x40d816ba, + 0xaca5c697, 0xa864db20, 0xa527fdf9, 0xa1e6e04e, 0xbfa1b04b, 0xbb60adfc, 0xb6238b25, 0xb2e29692, + 0x8aad2b2f, 0x8e6c3698, 0x832f1041, 0x87ee0df6, 0x99a95df3, 0x9d684044, 0x902b669d, 0x94ea7b2a, + 0xe0b41de7, 0xe4750050, 0xe9362689, 0xedf73b3e, 0xf3b06b3b, 0xf771768c, 0xfa325055, 0xfef34de2, + 0xc6bcf05f, 0xc27dede8, 0xcf3ecb31, 0xcbffd686, 0xd5b88683, 0xd1799b34, 0xdc3abded, 0xd8fba05a, + 0x690ce0ee, 0x6dcdfd59, 0x608edb80, 0x644fc637, 0x7a089632, 0x7ec98b85, 0x738aad5c, 0x774bb0eb, + 0x4f040d56, 0x4bc510e1, 0x46863638, 0x42472b8f, 0x5c007b8a, 0x58c1663d, 0x558240e4, 0x51435d53, + 0x251d3b9e, 0x21dc2629, 0x2c9f00f0, 0x285e1d47, 0x36194d42, 0x32d850f5, 0x3f9b762c, 0x3b5a6b9b, + 0x0315d626, 0x07d4cb91, 0x0a97ed48, 0x0e56f0ff, 0x1011a0fa, 0x14d0bd4d, 0x19939b94, 0x1d528623, + 0xf12f560e, 0xf5ee4bb9, 0xf8ad6d60, 0xfc6c70d7, 0xe22b20d2, 0xe6ea3d65, 0xeba91bbc, 0xef68060b, + 0xd727bbb6, 0xd3e6a601, 0xdea580d8, 0xda649d6f, 0xc423cd6a, 0xc0e2d0dd, 0xcda1f604, 0xc960ebb3, + 0xbd3e8d7e, 0xb9ff90c9, 0xb4bcb610, 0xb07daba7, 0xae3afba2, 0xaafbe615, 0xa7b8c0cc, 0xa379dd7b, + 0x9b3660c6, 0x9ff77d71, 0x92b45ba8, 0x9675461f, 0x8832161a, 0x8cf30bad, 0x81b02d74, 0x857130c3, + 0x5d8a9099, 0x594b8d2e, 0x5408abf7, 0x50c9b640, 0x4e8ee645, 0x4a4ffbf2, 0x470cdd2b, 0x43cdc09c, + 0x7b827d21, 0x7f436096, 0x7200464f, 0x76c15bf8, 0x68860bfd, 0x6c47164a, 0x61043093, 0x65c52d24, + 0x119b4be9, 0x155a565e, 0x18197087, 0x1cd86d30, 0x029f3d35, 0x065e2082, 0x0b1d065b, 0x0fdc1bec, + 0x3793a651, 0x3352bbe6, 0x3e119d3f, 0x3ad08088, 0x2497d08d, 0x2056cd3a, 0x2d15ebe3, 0x29d4f654, + 0xc5a92679, 0xc1683bce, 0xcc2b1d17, 0xc8ea00a0, 0xd6ad50a5, 0xd26c4d12, 0xdf2f6bcb, 0xdbee767c, + 0xe3a1cbc1, 0xe760d676, 0xea23f0af, 0xeee2ed18, 0xf0a5bd1d, 0xf464a0aa, 0xf9278673, 0xfde69bc4, + 0x89b8fd09, 0x8d79e0be, 0x803ac667, 0x84fbdbd0, 0x9abc8bd5, 0x9e7d9662, 0x933eb0bb, 0x97ffad0c, + 0xafb010b1, 0xab710d06, 0xa6322bdf, 0xa2f33668, 0xbcb4666d, 0xb8757bda, 0xb5365d03, 0xb1f740b4 + ]); + + var CRC32 = function() { + /** + * The current CRC + */ + var crc = 0xffffffff; + + /** + * @return The current CRC + */ + this.getCRC = function() { + return (~crc) >>> 0; // return an unsigned value + }; + + /** + * Update the CRC with a single byte + * @param value The value to update the CRC with + */ + this.updateCRC = function(value) { + crc = (crc << 8) ^ crc32Lookup[((crc >>> 24) ^ value) & 0xff]; + }; + + /** + * Update the CRC with a sequence of identical bytes + * @param value The value to update the CRC with + * @param count The number of bytes + */ + this.updateCRCRun = function(value, count) { + while (count-- > 0) { + crc = (crc << 8) ^ crc32Lookup[((crc >>> 24) ^ value) & 0xff]; + } + }; + }; + return CRC32; +})(); diff --git a/node_modules/seek-bzip/lib/index.js b/node_modules/seek-bzip/lib/index.js new file mode 100644 index 0000000..f3bab49 --- /dev/null +++ b/node_modules/seek-bzip/lib/index.js @@ -0,0 +1,605 @@ +/* +seek-bzip - a pure-javascript module for seeking within bzip2 data + +Copyright (C) 2013 C. Scott Ananian +Copyright (C) 2012 Eli Skeggs +Copyright (C) 2011 Kevin Kwok + +Permission is hereby granted, free of charge, to any person obtaining +a copy of this software and associated documentation files (the +"Software"), to deal in the Software without restriction, including +without limitation the rights to use, copy, modify, merge, publish, +distribute, sublicense, and/or sell copies of the Software, and to +permit persons to whom the Software is furnished to do so, subject to +the following conditions: + +The above copyright notice and this permission notice shall be +included in all copies or substantial portions of the Software. + +THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, +EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF +MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND +NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE +LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION +OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION +WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. + +Adapted from node-bzip, copyright 2012 Eli Skeggs. +Adapted from bzip2.js, copyright 2011 Kevin Kwok (antimatter15@gmail.com). + +Based on micro-bunzip by Rob Landley (rob@landley.net). + +Based on bzip2 decompression code by Julian R Seward (jseward@acm.org), +which also acknowledges contributions by Mike Burrows, David Wheeler, +Peter Fenwick, Alistair Moffat, Radford Neal, Ian H. Witten, +Robert Sedgewick, and Jon L. Bentley. +*/ + +var BitReader = require('./bitreader'); +var Stream = require('./stream'); +var CRC32 = require('./crc32'); +var pjson = require('../package.json'); + +var MAX_HUFCODE_BITS = 20; +var MAX_SYMBOLS = 258; +var SYMBOL_RUNA = 0; +var SYMBOL_RUNB = 1; +var MIN_GROUPS = 2; +var MAX_GROUPS = 6; +var GROUP_SIZE = 50; + +var WHOLEPI = "314159265359"; +var SQRTPI = "177245385090"; + +var mtf = function(array, index) { + var src = array[index], i; + for (i = index; i > 0; i--) { + array[i] = array[i-1]; + } + array[0] = src; + return src; +}; + +var Err = { + OK: 0, + LAST_BLOCK: -1, + NOT_BZIP_DATA: -2, + UNEXPECTED_INPUT_EOF: -3, + UNEXPECTED_OUTPUT_EOF: -4, + DATA_ERROR: -5, + OUT_OF_MEMORY: -6, + OBSOLETE_INPUT: -7, + END_OF_BLOCK: -8 +}; +var ErrorMessages = {}; +ErrorMessages[Err.LAST_BLOCK] = "Bad file checksum"; +ErrorMessages[Err.NOT_BZIP_DATA] = "Not bzip data"; +ErrorMessages[Err.UNEXPECTED_INPUT_EOF] = "Unexpected input EOF"; +ErrorMessages[Err.UNEXPECTED_OUTPUT_EOF] = "Unexpected output EOF"; +ErrorMessages[Err.DATA_ERROR] = "Data error"; +ErrorMessages[Err.OUT_OF_MEMORY] = "Out of memory"; +ErrorMessages[Err.OBSOLETE_INPUT] = "Obsolete (pre 0.9.5) bzip format not supported."; + +var _throw = function(status, optDetail) { + var msg = ErrorMessages[status] || 'unknown error'; + if (optDetail) { msg += ': '+optDetail; } + var e = new TypeError(msg); + e.errorCode = status; + throw e; +}; + +var Bunzip = function(inputStream, outputStream) { + this.writePos = this.writeCurrent = this.writeCount = 0; + + this._start_bunzip(inputStream, outputStream); +}; +Bunzip.prototype._init_block = function() { + var moreBlocks = this._get_next_block(); + if ( !moreBlocks ) { + this.writeCount = -1; + return false; /* no more blocks */ + } + this.blockCRC = new CRC32(); + return true; +}; +/* XXX micro-bunzip uses (inputStream, inputBuffer, len) as arguments */ +Bunzip.prototype._start_bunzip = function(inputStream, outputStream) { + /* Ensure that file starts with "BZh['1'-'9']." */ + var buf = new Buffer(4); + if (inputStream.read(buf, 0, 4) !== 4 || + String.fromCharCode(buf[0], buf[1], buf[2]) !== 'BZh') + _throw(Err.NOT_BZIP_DATA, 'bad magic'); + + var level = buf[3] - 0x30; + if (level < 1 || level > 9) + _throw(Err.NOT_BZIP_DATA, 'level out of range'); + + this.reader = new BitReader(inputStream); + + /* Fourth byte (ascii '1'-'9'), indicates block size in units of 100k of + uncompressed data. Allocate intermediate buffer for block. */ + this.dbufSize = 100000 * level; + this.nextoutput = 0; + this.outputStream = outputStream; + this.streamCRC = 0; +}; +Bunzip.prototype._get_next_block = function() { + var i, j, k; + var reader = this.reader; + // this is get_next_block() function from micro-bunzip: + /* Read in header signature and CRC, then validate signature. + (last block signature means CRC is for whole file, return now) */ + var h = reader.pi(); + if (h === SQRTPI) { // last block + return false; /* no more blocks */ + } + if (h !== WHOLEPI) + _throw(Err.NOT_BZIP_DATA); + this.targetBlockCRC = reader.read(32) >>> 0; // (convert to unsigned) + this.streamCRC = (this.targetBlockCRC ^ + ((this.streamCRC << 1) | (this.streamCRC>>>31))) >>> 0; + /* We can add support for blockRandomised if anybody complains. There was + some code for this in busybox 1.0.0-pre3, but nobody ever noticed that + it didn't actually work. */ + if (reader.read(1)) + _throw(Err.OBSOLETE_INPUT); + var origPointer = reader.read(24); + if (origPointer > this.dbufSize) + _throw(Err.DATA_ERROR, 'initial position out of bounds'); + /* mapping table: if some byte values are never used (encoding things + like ascii text), the compression code removes the gaps to have fewer + symbols to deal with, and writes a sparse bitfield indicating which + values were present. We make a translation table to convert the symbols + back to the corresponding bytes. */ + var t = reader.read(16); + var symToByte = new Buffer(256), symTotal = 0; + for (i = 0; i < 16; i++) { + if (t & (1 << (0xF - i))) { + var o = i * 16; + k = reader.read(16); + for (j = 0; j < 16; j++) + if (k & (1 << (0xF - j))) + symToByte[symTotal++] = o + j; + } + } + + /* How many different huffman coding groups does this block use? */ + var groupCount = reader.read(3); + if (groupCount < MIN_GROUPS || groupCount > MAX_GROUPS) + _throw(Err.DATA_ERROR); + /* nSelectors: Every GROUP_SIZE many symbols we select a new huffman coding + group. Read in the group selector list, which is stored as MTF encoded + bit runs. (MTF=Move To Front, as each value is used it's moved to the + start of the list.) */ + var nSelectors = reader.read(15); + if (nSelectors === 0) + _throw(Err.DATA_ERROR); + + var mtfSymbol = new Buffer(256); + for (i = 0; i < groupCount; i++) + mtfSymbol[i] = i; + + var selectors = new Buffer(nSelectors); // was 32768... + + for (i = 0; i < nSelectors; i++) { + /* Get next value */ + for (j = 0; reader.read(1); j++) + if (j >= groupCount) _throw(Err.DATA_ERROR); + /* Decode MTF to get the next selector */ + selectors[i] = mtf(mtfSymbol, j); + } + + /* Read the huffman coding tables for each group, which code for symTotal + literal symbols, plus two run symbols (RUNA, RUNB) */ + var symCount = symTotal + 2; + var groups = [], hufGroup; + for (j = 0; j < groupCount; j++) { + var length = new Buffer(symCount), temp = new Uint16Array(MAX_HUFCODE_BITS + 1); + /* Read huffman code lengths for each symbol. They're stored in + a way similar to mtf; record a starting value for the first symbol, + and an offset from the previous value for everys symbol after that. */ + t = reader.read(5); // lengths + for (i = 0; i < symCount; i++) { + for (;;) { + if (t < 1 || t > MAX_HUFCODE_BITS) _throw(Err.DATA_ERROR); + /* If first bit is 0, stop. Else second bit indicates whether + to increment or decrement the value. */ + if(!reader.read(1)) + break; + if(!reader.read(1)) + t++; + else + t--; + } + length[i] = t; + } + + /* Find largest and smallest lengths in this group */ + var minLen, maxLen; + minLen = maxLen = length[0]; + for (i = 1; i < symCount; i++) { + if (length[i] > maxLen) + maxLen = length[i]; + else if (length[i] < minLen) + minLen = length[i]; + } + + /* Calculate permute[], base[], and limit[] tables from length[]. + * + * permute[] is the lookup table for converting huffman coded symbols + * into decoded symbols. base[] is the amount to subtract from the + * value of a huffman symbol of a given length when using permute[]. + * + * limit[] indicates the largest numerical value a symbol with a given + * number of bits can have. This is how the huffman codes can vary in + * length: each code with a value>limit[length] needs another bit. + */ + hufGroup = {}; + groups.push(hufGroup); + hufGroup.permute = new Uint16Array(MAX_SYMBOLS); + hufGroup.limit = new Uint32Array(MAX_HUFCODE_BITS + 2); + hufGroup.base = new Uint32Array(MAX_HUFCODE_BITS + 1); + hufGroup.minLen = minLen; + hufGroup.maxLen = maxLen; + /* Calculate permute[]. Concurently, initialize temp[] and limit[]. */ + var pp = 0; + for (i = minLen; i <= maxLen; i++) { + temp[i] = hufGroup.limit[i] = 0; + for (t = 0; t < symCount; t++) + if (length[t] === i) + hufGroup.permute[pp++] = t; + } + /* Count symbols coded for at each bit length */ + for (i = 0; i < symCount; i++) + temp[length[i]]++; + /* Calculate limit[] (the largest symbol-coding value at each bit + * length, which is (previous limit<<1)+symbols at this level), and + * base[] (number of symbols to ignore at each bit length, which is + * limit minus the cumulative count of symbols coded for already). */ + pp = t = 0; + for (i = minLen; i < maxLen; i++) { + pp += temp[i]; + /* We read the largest possible symbol size and then unget bits + after determining how many we need, and those extra bits could + be set to anything. (They're noise from future symbols.) At + each level we're really only interested in the first few bits, + so here we set all the trailing to-be-ignored bits to 1 so they + don't affect the value>limit[length] comparison. */ + hufGroup.limit[i] = pp - 1; + pp <<= 1; + t += temp[i]; + hufGroup.base[i + 1] = pp - t; + } + hufGroup.limit[maxLen + 1] = Number.MAX_VALUE; /* Sentinal value for reading next sym. */ + hufGroup.limit[maxLen] = pp + temp[maxLen] - 1; + hufGroup.base[minLen] = 0; + } + /* We've finished reading and digesting the block header. Now read this + block's huffman coded symbols from the file and undo the huffman coding + and run length encoding, saving the result into dbuf[dbufCount++]=uc */ + + /* Initialize symbol occurrence counters and symbol Move To Front table */ + var byteCount = new Uint32Array(256); + for (i = 0; i < 256; i++) + mtfSymbol[i] = i; + /* Loop through compressed symbols. */ + var runPos = 0, dbufCount = 0, selector = 0, uc; + var dbuf = this.dbuf = new Uint32Array(this.dbufSize); + symCount = 0; + for (;;) { + /* Determine which huffman coding group to use. */ + if (!(symCount--)) { + symCount = GROUP_SIZE - 1; + if (selector >= nSelectors) { _throw(Err.DATA_ERROR); } + hufGroup = groups[selectors[selector++]]; + } + /* Read next huffman-coded symbol. */ + i = hufGroup.minLen; + j = reader.read(i); + for (;;i++) { + if (i > hufGroup.maxLen) { _throw(Err.DATA_ERROR); } + if (j <= hufGroup.limit[i]) + break; + j = (j << 1) | reader.read(1); + } + /* Huffman decode value to get nextSym (with bounds checking) */ + j -= hufGroup.base[i]; + if (j < 0 || j >= MAX_SYMBOLS) { _throw(Err.DATA_ERROR); } + var nextSym = hufGroup.permute[j]; + /* We have now decoded the symbol, which indicates either a new literal + byte, or a repeated run of the most recent literal byte. First, + check if nextSym indicates a repeated run, and if so loop collecting + how many times to repeat the last literal. */ + if (nextSym === SYMBOL_RUNA || nextSym === SYMBOL_RUNB) { + /* If this is the start of a new run, zero out counter */ + if (!runPos){ + runPos = 1; + t = 0; + } + /* Neat trick that saves 1 symbol: instead of or-ing 0 or 1 at + each bit position, add 1 or 2 instead. For example, + 1011 is 1<<0 + 1<<1 + 2<<2. 1010 is 2<<0 + 2<<1 + 1<<2. + You can make any bit pattern that way using 1 less symbol than + the basic or 0/1 method (except all bits 0, which would use no + symbols, but a run of length 0 doesn't mean anything in this + context). Thus space is saved. */ + if (nextSym === SYMBOL_RUNA) + t += runPos; + else + t += 2 * runPos; + runPos <<= 1; + continue; + } + /* When we hit the first non-run symbol after a run, we now know + how many times to repeat the last literal, so append that many + copies to our buffer of decoded symbols (dbuf) now. (The last + literal used is the one at the head of the mtfSymbol array.) */ + if (runPos){ + runPos = 0; + if (dbufCount + t > this.dbufSize) { _throw(Err.DATA_ERROR); } + uc = symToByte[mtfSymbol[0]]; + byteCount[uc] += t; + while (t--) + dbuf[dbufCount++] = uc; + } + /* Is this the terminating symbol? */ + if (nextSym > symTotal) + break; + /* At this point, nextSym indicates a new literal character. Subtract + one to get the position in the MTF array at which this literal is + currently to be found. (Note that the result can't be -1 or 0, + because 0 and 1 are RUNA and RUNB. But another instance of the + first symbol in the mtf array, position 0, would have been handled + as part of a run above. Therefore 1 unused mtf position minus + 2 non-literal nextSym values equals -1.) */ + if (dbufCount >= this.dbufSize) { _throw(Err.DATA_ERROR); } + i = nextSym - 1; + uc = mtf(mtfSymbol, i); + uc = symToByte[uc]; + /* We have our literal byte. Save it into dbuf. */ + byteCount[uc]++; + dbuf[dbufCount++] = uc; + } + /* At this point, we've read all the huffman-coded symbols (and repeated + runs) for this block from the input stream, and decoded them into the + intermediate buffer. There are dbufCount many decoded bytes in dbuf[]. + Now undo the Burrows-Wheeler transform on dbuf. + See http://dogma.net/markn/articles/bwt/bwt.htm + */ + if (origPointer < 0 || origPointer >= dbufCount) { _throw(Err.DATA_ERROR); } + /* Turn byteCount into cumulative occurrence counts of 0 to n-1. */ + j = 0; + for (i = 0; i < 256; i++) { + k = j + byteCount[i]; + byteCount[i] = j; + j = k; + } + /* Figure out what order dbuf would be in if we sorted it. */ + for (i = 0; i < dbufCount; i++) { + uc = dbuf[i] & 0xff; + dbuf[byteCount[uc]] |= (i << 8); + byteCount[uc]++; + } + /* Decode first byte by hand to initialize "previous" byte. Note that it + doesn't get output, and if the first three characters are identical + it doesn't qualify as a run (hence writeRunCountdown=5). */ + var pos = 0, current = 0, run = 0; + if (dbufCount) { + pos = dbuf[origPointer]; + current = (pos & 0xff); + pos >>= 8; + run = -1; + } + this.writePos = pos; + this.writeCurrent = current; + this.writeCount = dbufCount; + this.writeRun = run; + + return true; /* more blocks to come */ +}; +/* Undo burrows-wheeler transform on intermediate buffer to produce output. + If start_bunzip was initialized with out_fd=-1, then up to len bytes of + data are written to outbuf. Return value is number of bytes written or + error (all errors are negative numbers). If out_fd!=-1, outbuf and len + are ignored, data is written to out_fd and return is RETVAL_OK or error. +*/ +Bunzip.prototype._read_bunzip = function(outputBuffer, len) { + var copies, previous, outbyte; + /* james@jamestaylor.org: writeCount goes to -1 when the buffer is fully + decoded, which results in this returning RETVAL_LAST_BLOCK, also + equal to -1... Confusing, I'm returning 0 here to indicate no + bytes written into the buffer */ + if (this.writeCount < 0) { return 0; } + + var gotcount = 0; + var dbuf = this.dbuf, pos = this.writePos, current = this.writeCurrent; + var dbufCount = this.writeCount, outputsize = this.outputsize; + var run = this.writeRun; + + while (dbufCount) { + dbufCount--; + previous = current; + pos = dbuf[pos]; + current = pos & 0xff; + pos >>= 8; + if (run++ === 3){ + copies = current; + outbyte = previous; + current = -1; + } else { + copies = 1; + outbyte = current; + } + this.blockCRC.updateCRCRun(outbyte, copies); + while (copies--) { + this.outputStream.writeByte(outbyte); + this.nextoutput++; + } + if (current != previous) + run = 0; + } + this.writeCount = dbufCount; + // check CRC + if (this.blockCRC.getCRC() !== this.targetBlockCRC) { + _throw(Err.DATA_ERROR, "Bad block CRC "+ + "(got "+this.blockCRC.getCRC().toString(16)+ + " expected "+this.targetBlockCRC.toString(16)+")"); + } + return this.nextoutput; +}; + +var coerceInputStream = function(input) { + if ('readByte' in input) { return input; } + var inputStream = new Stream(); + inputStream.pos = 0; + inputStream.readByte = function() { return input[this.pos++]; }; + inputStream.seek = function(pos) { this.pos = pos; }; + inputStream.eof = function() { return this.pos >= input.length; }; + return inputStream; +}; +var coerceOutputStream = function(output) { + var outputStream = new Stream(); + var resizeOk = true; + if (output) { + if (typeof(output)==='number') { + outputStream.buffer = new Buffer(output); + resizeOk = false; + } else if ('writeByte' in output) { + return output; + } else { + outputStream.buffer = output; + resizeOk = false; + } + } else { + outputStream.buffer = new Buffer(16384); + } + outputStream.pos = 0; + outputStream.writeByte = function(_byte) { + if (resizeOk && this.pos >= this.buffer.length) { + var newBuffer = new Buffer(this.buffer.length*2); + this.buffer.copy(newBuffer); + this.buffer = newBuffer; + } + this.buffer[this.pos++] = _byte; + }; + outputStream.getBuffer = function() { + // trim buffer + if (this.pos !== this.buffer.length) { + if (!resizeOk) + throw new TypeError('outputsize does not match decoded input'); + var newBuffer = new Buffer(this.pos); + this.buffer.copy(newBuffer, 0, 0, this.pos); + this.buffer = newBuffer; + } + return this.buffer; + }; + outputStream._coerced = true; + return outputStream; +}; + +/* Static helper functions */ +Bunzip.Err = Err; +// 'input' can be a stream or a buffer +// 'output' can be a stream or a buffer or a number (buffer size) +Bunzip.decode = function(input, output, multistream) { + // make a stream from a buffer, if necessary + var inputStream = coerceInputStream(input); + var outputStream = coerceOutputStream(output); + + var bz = new Bunzip(inputStream, outputStream); + while (true) { + if ('eof' in inputStream && inputStream.eof()) break; + if (bz._init_block()) { + bz._read_bunzip(); + } else { + var targetStreamCRC = bz.reader.read(32) >>> 0; // (convert to unsigned) + if (targetStreamCRC !== bz.streamCRC) { + _throw(Err.DATA_ERROR, "Bad stream CRC "+ + "(got "+bz.streamCRC.toString(16)+ + " expected "+targetStreamCRC.toString(16)+")"); + } + if (multistream && + 'eof' in inputStream && + !inputStream.eof()) { + // note that start_bunzip will also resync the bit reader to next byte + bz._start_bunzip(inputStream, outputStream); + } else break; + } + } + if ('getBuffer' in outputStream) + return outputStream.getBuffer(); +}; +Bunzip.decodeBlock = function(input, pos, output) { + // make a stream from a buffer, if necessary + var inputStream = coerceInputStream(input); + var outputStream = coerceOutputStream(output); + var bz = new Bunzip(inputStream, outputStream); + bz.reader.seek(pos); + /* Fill the decode buffer for the block */ + var moreBlocks = bz._get_next_block(); + if (moreBlocks) { + /* Init the CRC for writing */ + bz.blockCRC = new CRC32(); + + /* Zero this so the current byte from before the seek is not written */ + bz.writeCopies = 0; + + /* Decompress the block and write to stdout */ + bz._read_bunzip(); + // XXX keep writing? + } + if ('getBuffer' in outputStream) + return outputStream.getBuffer(); +}; +/* Reads bzip2 file from stream or buffer `input`, and invoke + * `callback(position, size)` once for each bzip2 block, + * where position gives the starting position (in *bits*) + * and size gives uncompressed size of the block (in *bytes*). */ +Bunzip.table = function(input, callback, multistream) { + // make a stream from a buffer, if necessary + var inputStream = new Stream(); + inputStream.delegate = coerceInputStream(input); + inputStream.pos = 0; + inputStream.readByte = function() { + this.pos++; + return this.delegate.readByte(); + }; + if (inputStream.delegate.eof) { + inputStream.eof = inputStream.delegate.eof.bind(inputStream.delegate); + } + var outputStream = new Stream(); + outputStream.pos = 0; + outputStream.writeByte = function() { this.pos++; }; + + var bz = new Bunzip(inputStream, outputStream); + var blockSize = bz.dbufSize; + while (true) { + if ('eof' in inputStream && inputStream.eof()) break; + + var position = inputStream.pos*8 + bz.reader.bitOffset; + if (bz.reader.hasByte) { position -= 8; } + + if (bz._init_block()) { + var start = outputStream.pos; + bz._read_bunzip(); + callback(position, outputStream.pos - start); + } else { + var crc = bz.reader.read(32); // (but we ignore the crc) + if (multistream && + 'eof' in inputStream && + !inputStream.eof()) { + // note that start_bunzip will also resync the bit reader to next byte + bz._start_bunzip(inputStream, outputStream); + console.assert(bz.dbufSize === blockSize, + "shouldn't change block size within multistream file"); + } else break; + } + } +}; + +Bunzip.Stream = Stream; + +Bunzip.version = pjson.version; +Bunzip.license = pjson.license; + +module.exports = Bunzip; diff --git a/node_modules/seek-bzip/lib/stream.js b/node_modules/seek-bzip/lib/stream.js new file mode 100644 index 0000000..90f6155 --- /dev/null +++ b/node_modules/seek-bzip/lib/stream.js @@ -0,0 +1,42 @@ +/* very simple input/output stream interface */ +var Stream = function() { +}; + +// input streams ////////////// +/** Returns the next byte, or -1 for EOF. */ +Stream.prototype.readByte = function() { + throw new Error("abstract method readByte() not implemented"); +}; +/** Attempts to fill the buffer; returns number of bytes read, or + * -1 for EOF. */ +Stream.prototype.read = function(buffer, bufOffset, length) { + var bytesRead = 0; + while (bytesRead < length) { + var c = this.readByte(); + if (c < 0) { // EOF + return (bytesRead===0) ? -1 : bytesRead; + } + buffer[bufOffset++] = c; + bytesRead++; + } + return bytesRead; +}; +Stream.prototype.seek = function(new_pos) { + throw new Error("abstract method seek() not implemented"); +}; + +// output streams /////////// +Stream.prototype.writeByte = function(_byte) { + throw new Error("abstract method readByte() not implemented"); +}; +Stream.prototype.write = function(buffer, bufOffset, length) { + var i; + for (i=0; i<length; i++) { + this.writeByte(buffer[bufOffset++]); + } + return length; +}; +Stream.prototype.flush = function() { +}; + +module.exports = Stream; diff --git a/node_modules/seek-bzip/package.json b/node_modules/seek-bzip/package.json new file mode 100644 index 0000000..b8f8c3e --- /dev/null +++ b/node_modules/seek-bzip/package.json @@ -0,0 +1,34 @@ +{ + "name": "seek-bzip", + "version": "1.0.6", + "contributors": [ + "C. Scott Ananian (http://cscott.net)", + "Eli Skeggs", + "Kevin Kwok", + "Rob Landley (http://landley.net)" + ], + "description": "a pure-JavaScript Node.JS module for random-access decoding bzip2 data", + "main": "./lib/index.js", + "repository": { + "type": "git", + "url": "https://github.com/cscott/seek-bzip.git" + }, + "license": "MIT", + "bin": { + "seek-bunzip": "./bin/seek-bunzip", + "seek-table": "./bin/seek-bzip-table" + }, + "directories": { + "test": "test" + }, + "dependencies": { + "commander": "^2.8.1" + }, + "devDependencies": { + "fibers": "~1.0.6", + "mocha": "~2.2.5" + }, + "scripts": { + "test": "mocha" + } +} |