diff options
Diffstat (limited to 'contrib/linearize')
| -rw-r--r-- | contrib/linearize/README.md | 51 | ||||
| -rw-r--r-- | contrib/linearize/example-linearize.cfg | 19 | ||||
| -rwxr-xr-x | contrib/linearize/linearize-data.py | 79 | ||||
| -rwxr-xr-x | contrib/linearize/linearize-hashes.py | 45 |
4 files changed, 135 insertions, 59 deletions
diff --git a/contrib/linearize/README.md b/contrib/linearize/README.md index 06f278f3b3..0971e7816b 100644 --- a/contrib/linearize/README.md +++ b/contrib/linearize/README.md @@ -1,33 +1,54 @@ # Linearize -Construct a linear, no-fork, best version of the blockchain. +Construct a linear, no-fork, best version of the Bitcoin blockchain. The scripts +run using Python 3 but are compatible with Python 2. ## Step 1: Download hash list $ ./linearize-hashes.py linearize.cfg > hashlist.txt Required configuration file settings for linearize-hashes: -* RPC: rpcuser, rpcpassword +* RPC: `rpcuser`, `rpcpassword` Optional config file setting for linearize-hashes: -* RPC: host, port -* Block chain: min_height, max_height +* RPC: `host` (Default: `127.0.0.1`) +* RPC: `port` (Default: `8332`) +* Blockchain: `min_height`, `max_height` +* `rev_hash_bytes`: If true, the written block hash list will be +byte-reversed. (In other words, the hash returned by getblockhash will have its +bytes reversed.) False by default. Intended for generation of +standalone hash lists but safe to use with linearize-data.py, which will output +the same data no matter which byte format is chosen. + +The `linearize-hashes` script requires a connection, local or remote, to a +JSON-RPC server. Running `bitcoind` or `bitcoin-qt -server` will be sufficient. ## Step 2: Copy local block data $ ./linearize-data.py linearize.cfg Required configuration file settings: -* "input": bitcoind blocks/ directory containing blkNNNNN.dat -* "hashlist": text file containing list of block hashes, linearized-hashes.py -output. -* "output_file": bootstrap.dat +* `output_file`: The file that will contain the final blockchain. or -* "output": output directory for linearized blocks/blkNNNNN.dat output +* `output`: Output directory for linearized `blocks/blkNNNNN.dat` output. Optional config file setting for linearize-data: -* "netmagic": network magic number -* "max_out_sz": maximum output file size (default `1000*1000*1000`) -* "split_timestamp": Split files when a new month is first seen, in addition to -reaching a maximum file size. -* "file_timestamp": Set each file's last-modified time to that of the -most recent block in that file. +* `debug_output`: Some printouts may not always be desired. If true, such output +will be printed. +* `file_timestamp`: Set each file's last-accessed and last-modified times, +respectively, to the current time and to the timestamp of the most recent block +written to the script's blockchain. +* `genesis`: The hash of the genesis block in the blockchain. +* `input`: bitcoind blocks/ directory containing blkNNNNN.dat +* `hashlist`: text file containing list of block hashes created by +linearize-hashes.py. +* `max_out_sz`: Maximum size for files created by the `output_file` option. +(Default: `1000*1000*1000 bytes`) +* `netmagic`: Network magic number. +* `out_of_order_cache_sz`: If out-of-order blocks are being read, the block can +be written to a cache so that the blockchain doesn't have to be seeked again. +This option specifies the cache size. (Default: `100*1000*1000 bytes`) +* `rev_hash_bytes`: If true, the block hash list written by linearize-hashes.py +will be byte-reversed when read by linearize-data.py. See the linearize-hashes +entry for more information. +* `split_timestamp`: Split blockchain files when a new month is first seen, in +addition to reaching a maximum file size (`max_out_sz`). diff --git a/contrib/linearize/example-linearize.cfg b/contrib/linearize/example-linearize.cfg index 38da02e66c..2cc910edfe 100644 --- a/contrib/linearize/example-linearize.cfg +++ b/contrib/linearize/example-linearize.cfg @@ -1,4 +1,3 @@ - # bitcoind RPC settings (linearize-hashes) rpcuser=someuser rpcpassword=somepassword @@ -21,9 +20,23 @@ input=/home/example/.bitcoin/blocks #genesis=000000000933ea01ad0ee984209779baaec3ced90fa3f408719526f8d77f4943 #input=/home/example/.bitcoin/testnet3/blocks +# "output" option causes blockchain files to be written to the given location, +# with "output_file" ignored. If not used, "output_file" is used instead. +# output=/home/example/blockchain_directory output_file=/home/example/Downloads/bootstrap.dat hashlist=hashlist.txt -split_year=1 -# Maxmimum size in bytes of out-of-order blocks cache in memory +# Maximum size in bytes of out-of-order blocks cache in memory out_of_order_cache_sz = 100000000 + +# Do we want the reverse the hash bytes coming from getblockhash? +rev_hash_bytes = False + +# On a new month, do we want to set the access and modify times of the new +# blockchain file? +file_timestamp = 0 +# Do we want to split the blockchain files given a new month or specific height? +split_timestamp = 0 + +# Do we want debug printouts? +debug_output = False diff --git a/contrib/linearize/linearize-data.py b/contrib/linearize/linearize-data.py index 8badb4b318..afcec2b60a 100755 --- a/contrib/linearize/linearize-data.py +++ b/contrib/linearize/linearize-data.py @@ -1,30 +1,34 @@ -#!/usr/bin/env python +#!/usr/bin/env python3 # # linearize-data.py: Construct a linear, no-fork version of the chain. # -# Copyright (c) 2013-2014 The Bitcoin Core developers +# Copyright (c) 2013-2016 The Bitcoin Core developers # Distributed under the MIT software license, see the accompanying # file COPYING or http://www.opensource.org/licenses/mit-license.php. # from __future__ import print_function, division -import json import struct import re import os import os.path -import base64 -import httplib import sys import hashlib import datetime import time from collections import namedtuple +from binascii import hexlify, unhexlify settings = {} +##### Switch endian-ness ##### +def hex_switchEndian(s): + """ Switches the endianness of a hex string (in pairs of hex chars) """ + pairList = [s[i:i+2].encode() for i in range(0, len(s), 2)] + return b''.join(pairList[::-1]).decode() + def uint32(x): - return x & 0xffffffffL + return x & 0xffffffff def bytereverse(x): return uint32(( ((x) << 24) | (((x) << 8) & 0x00ff0000) | @@ -35,14 +39,14 @@ def bufreverse(in_buf): for i in range(0, len(in_buf), 4): word = struct.unpack('@I', in_buf[i:i+4])[0] out_words.append(struct.pack('@I', bytereverse(word))) - return ''.join(out_words) + return b''.join(out_words) def wordreverse(in_buf): out_words = [] for i in range(0, len(in_buf), 4): out_words.append(in_buf[i:i+4]) out_words.reverse() - return ''.join(out_words) + return b''.join(out_words) def calc_hdr_hash(blk_hdr): hash1 = hashlib.sha256() @@ -59,7 +63,7 @@ def calc_hash_str(blk_hdr): hash = calc_hdr_hash(blk_hdr) hash = bufreverse(hash) hash = wordreverse(hash) - hash_str = hash.encode('hex') + hash_str = hexlify(hash).decode('utf-8') return hash_str def get_blk_dt(blk_hdr): @@ -69,17 +73,21 @@ def get_blk_dt(blk_hdr): dt_ym = datetime.datetime(dt.year, dt.month, 1) return (dt_ym, nTime) +# When getting the list of block hashes, undo any byte reversals. def get_block_hashes(settings): blkindex = [] f = open(settings['hashlist'], "r") for line in f: line = line.rstrip() + if settings['rev_hash_bytes'] == 'true': + line = hex_switchEndian(line) blkindex.append(line) print("Read " + str(len(blkindex)) + " hashes") return blkindex +# The block map shouldn't give or receive byte-reversed hashes. def mkblockmap(blkindex): blkmap = {} for height,hash in enumerate(blkindex): @@ -126,7 +134,7 @@ class BlockDataCopier: if not self.fileOutput and ((self.outsz + blockSizeOnDisk) > self.maxOutSz): self.outF.close() if self.setFileTime: - os.utime(outFname, (int(time.time()), highTS)) + os.utime(self.outFname, (int(time.time()), self.highTS)) self.outF = None self.outFname = None self.outFn = self.outFn + 1 @@ -134,12 +142,12 @@ class BlockDataCopier: (blkDate, blkTS) = get_blk_dt(blk_hdr) if self.timestampSplit and (blkDate > self.lastDate): - print("New month " + blkDate.strftime("%Y-%m") + " @ " + hash_str) - lastDate = blkDate - if outF: - outF.close() - if setFileTime: - os.utime(outFname, (int(time.time()), highTS)) + print("New month " + blkDate.strftime("%Y-%m") + " @ " + self.hash_str) + self.lastDate = blkDate + if self.outF: + self.outF.close() + if self.setFileTime: + os.utime(self.outFname, (int(time.time()), self.highTS)) self.outF = None self.outFname = None self.outFn = self.outFn + 1 @@ -147,11 +155,11 @@ class BlockDataCopier: if not self.outF: if self.fileOutput: - outFname = self.settings['output_file'] + self.outFname = self.settings['output_file'] else: - outFname = os.path.join(self.settings['output'], "blk%05d.dat" % self.outFn) - print("Output file " + outFname) - self.outF = open(outFname, "wb") + self.outFname = os.path.join(self.settings['output'], "blk%05d.dat" % self.outFn) + print("Output file " + self.outFname) + self.outF = open(self.outFname, "wb") self.outF.write(inhdr) self.outF.write(blk_hdr) @@ -207,7 +215,7 @@ class BlockDataCopier: inMagic = inhdr[:4] if (inMagic != self.settings['netmagic']): - print("Invalid magic: " + inMagic.encode('hex')) + print("Invalid magic: " + hexlify(inMagic).decode('utf-8')) return inLenLE = inhdr[4:] su = struct.unpack("<I", inLenLE) @@ -215,13 +223,16 @@ class BlockDataCopier: blk_hdr = self.inF.read(80) inExtent = BlockExtent(self.inFn, self.inF.tell(), inhdr, blk_hdr, inLen) - hash_str = calc_hash_str(blk_hdr) - if not hash_str in blkmap: - print("Skipping unknown block " + hash_str) + self.hash_str = calc_hash_str(blk_hdr) + if not self.hash_str in blkmap: + # Because blocks can be written to files out-of-order as of 0.10, the script + # may encounter blocks it doesn't know about. Treat as debug output. + if settings['debug_output'] == 'true': + print("Skipping unknown block " + self.hash_str) self.inF.seek(inLen, os.SEEK_CUR) continue - blkHeight = self.blkmap[hash_str] + blkHeight = self.blkmap[self.hash_str] self.blkCountIn += 1 if self.blkCountOut == blkHeight: @@ -265,6 +276,12 @@ if __name__ == '__main__': settings[m.group(1)] = m.group(2) f.close() + # Force hash byte format setting to be lowercase to make comparisons easier. + # Also place upfront in case any settings need to know about it. + if 'rev_hash_bytes' not in settings: + settings['rev_hash_bytes'] = 'false' + settings['rev_hash_bytes'] = settings['rev_hash_bytes'].lower() + if 'netmagic' not in settings: settings['netmagic'] = 'f9beb4d9' if 'genesis' not in settings: @@ -278,15 +295,18 @@ if __name__ == '__main__': if 'split_timestamp' not in settings: settings['split_timestamp'] = 0 if 'max_out_sz' not in settings: - settings['max_out_sz'] = 1000L * 1000 * 1000 + settings['max_out_sz'] = 1000 * 1000 * 1000 if 'out_of_order_cache_sz' not in settings: settings['out_of_order_cache_sz'] = 100 * 1000 * 1000 + if 'debug_output' not in settings: + settings['debug_output'] = 'false' - settings['max_out_sz'] = long(settings['max_out_sz']) + settings['max_out_sz'] = int(settings['max_out_sz']) settings['split_timestamp'] = int(settings['split_timestamp']) settings['file_timestamp'] = int(settings['file_timestamp']) - settings['netmagic'] = settings['netmagic'].decode('hex') + settings['netmagic'] = unhexlify(settings['netmagic'].encode('utf-8')) settings['out_of_order_cache_sz'] = int(settings['out_of_order_cache_sz']) + settings['debug_output'] = settings['debug_output'].lower() if 'output_file' not in settings and 'output' not in settings: print("Missing output file / directory") @@ -295,9 +315,8 @@ if __name__ == '__main__': blkindex = get_block_hashes(settings) blkmap = mkblockmap(blkindex) + # Block hash map won't be byte-reversed. Neither should the genesis hash. if not settings['genesis'] in blkmap: print("Genesis block not found in hashlist") else: BlockDataCopier(settings, blkindex, blkmap).run() - - diff --git a/contrib/linearize/linearize-hashes.py b/contrib/linearize/linearize-hashes.py index cb40c664fa..00a54d0820 100755 --- a/contrib/linearize/linearize-hashes.py +++ b/contrib/linearize/linearize-hashes.py @@ -1,39 +1,53 @@ -#!/usr/bin/env python +#!/usr/bin/env python3 # # linearize-hashes.py: List blocks in a linear, no-fork version of the chain. # -# Copyright (c) 2013-2014 The Bitcoin Core developers +# Copyright (c) 2013-2016 The Bitcoin Core developers # Distributed under the MIT software license, see the accompanying # file COPYING or http://www.opensource.org/licenses/mit-license.php. # from __future__ import print_function +try: # Python 3 + import http.client as httplib +except ImportError: # Python 2 + import httplib import json -import struct import re import base64 -import httplib import sys settings = {} +##### Switch endian-ness ##### +def hex_switchEndian(s): + """ Switches the endianness of a hex string (in pairs of hex chars) """ + pairList = [s[i:i+2].encode() for i in range(0, len(s), 2)] + return b''.join(pairList[::-1]).decode() + class BitcoinRPC: def __init__(self, host, port, username, password): authpair = "%s:%s" % (username, password) - self.authhdr = "Basic %s" % (base64.b64encode(authpair)) - self.conn = httplib.HTTPConnection(host, port, False, 30) + authpair = authpair.encode('utf-8') + self.authhdr = b"Basic " + base64.b64encode(authpair) + self.conn = httplib.HTTPConnection(host, port=port, timeout=30) def execute(self, obj): - self.conn.request('POST', '/', json.dumps(obj), - { 'Authorization' : self.authhdr, - 'Content-type' : 'application/json' }) + try: + self.conn.request('POST', '/', json.dumps(obj), + { 'Authorization' : self.authhdr, + 'Content-type' : 'application/json' }) + except ConnectionRefusedError: + print('RPC connection refused. Check RPC settings and the server status.', + file=sys.stderr) + return None resp = self.conn.getresponse() if resp is None: print("JSON-RPC: no response", file=sys.stderr) return None - body = resp.read() + body = resp.read().decode('utf-8') resp_obj = json.loads(body) return resp_obj @@ -64,12 +78,17 @@ def get_block_hashes(settings, max_blocks_per_call=10000): batch.append(rpc.build_request(x, 'getblockhash', [height + x])) reply = rpc.execute(batch) + if reply is None: + print('Cannot continue. Program will halt.') + return None for x,resp_obj in enumerate(reply): if rpc.response_is_error(resp_obj): print('JSON-RPC: error at height', height+x, ': ', resp_obj['error'], file=sys.stderr) exit(1) assert(resp_obj['id'] == x) # assume replies are in-sequence + if settings['rev_hash_bytes'] == 'true': + resp_obj['result'] = hex_switchEndian(resp_obj['result']) print(resp_obj['result']) height += num_blocks @@ -101,6 +120,8 @@ if __name__ == '__main__': settings['min_height'] = 0 if 'max_height' not in settings: settings['max_height'] = 313000 + if 'rev_hash_bytes' not in settings: + settings['rev_hash_bytes'] = 'false' if 'rpcuser' not in settings or 'rpcpassword' not in settings: print("Missing username and/or password in cfg file", file=stderr) sys.exit(1) @@ -109,5 +130,7 @@ if __name__ == '__main__': settings['min_height'] = int(settings['min_height']) settings['max_height'] = int(settings['max_height']) - get_block_hashes(settings) + # Force hash byte format setting to be lowercase to make comparisons easier. + settings['rev_hash_bytes'] = settings['rev_hash_bytes'].lower() + get_block_hashes(settings) |