diff --git a/contrib/linearize/linearize-data.py b/contrib/linearize/linearize-data.py index 002513721..732f78a33 100755 --- a/contrib/linearize/linearize-data.py +++ b/contrib/linearize/linearize-data.py @@ -1,345 +1,345 @@ #!/usr/bin/env python3 # # linearize-data.py: Construct a linear, no-fork version of the chain. # # 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 division, print_function import datetime import hashlib import os import os.path import re import struct import sys import time from binascii import unhexlify from collections import namedtuple from typing import Any, Dict settings: Dict[str, Any] = {} 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 & 0xffffffff def bytereverse(x): return uint32((((x) << 24) | (((x) << 8) & 0x00ff0000) | (((x) >> 8) & 0x0000ff00) | ((x) >> 24))) def bufreverse(in_buf): out_words = [] 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 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 b''.join(out_words) def calc_hdr_hash(blk_hdr): hash1 = hashlib.sha256() hash1.update(blk_hdr) hash1_o = hash1.digest() hash2 = hashlib.sha256() hash2.update(hash1_o) hash2_o = hash2.digest() return hash2_o def calc_hash_str(blk_hdr): - hash = calc_hdr_hash(blk_hdr) - hash = bufreverse(hash) - hash = wordreverse(hash) - hash_str = hash.hex() + blockhash = calc_hdr_hash(blk_hdr) + blockhash = bufreverse(blockhash) + blockhash = wordreverse(blockhash) + hash_str = blockhash.hex() return hash_str def get_blk_dt(blk_hdr): members = struct.unpack(" self.maxOutSz): 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 self.outsz = 0 (blkDate, blkTS) = get_blk_dt(blk_hdr) if self.timestampSplit and (blkDate > self.lastDate): 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 self.outsz = 0 if not self.outF: if self.fileOutput: self.outFname = self.settings['output_file'] else: self.outFname = os.path.join( self.settings['output'], f"blk{self.outFn:05d}.dat") print("Output file " + self.outFname) self.outF = open(self.outFname, "wb") self.outF.write(inhdr) self.outF.write(blk_hdr) self.outF.write(rawblock) self.outsz = self.outsz + len(inhdr) + len(blk_hdr) + len(rawblock) self.blkCountOut = self.blkCountOut + 1 if blkTS > self.highTS: self.highTS = blkTS if (self.blkCountOut % 1000) == 0: print('{} blocks scanned, {} blocks written (of {}, {:.1f}% complete)'.format( self.blkCountIn, self.blkCountOut, len(self.blkindex), 100.0 * self.blkCountOut / len(self.blkindex))) def inFileName(self, fn): return os.path.join(self.settings['input'], f"blk{fn:05d}.dat") def fetchBlock(self, extent): '''Fetch block contents from disk given extents''' with open(self.inFileName(extent.fn), "rb") as f: f.seek(extent.offset) return f.read(extent.size) def copyOneBlock(self): '''Find the next block to be written in the input, and copy it to the output.''' extent = self.blockExtents.pop(self.blkCountOut) if self.blkCountOut in self.outOfOrderData: # If the data is cached, use it from memory and remove from the # cache rawblock = self.outOfOrderData.pop(self.blkCountOut) self.outOfOrderSize -= len(rawblock) else: # Otherwise look up data on disk rawblock = self.fetchBlock(extent) self.writeBlock(extent.inhdr, extent.blkhdr, rawblock) def run(self): while self.blkCountOut < len(self.blkindex): if not self.inF: fname = self.inFileName(self.inFn) print("Input file " + fname) try: self.inF = open(fname, "rb") except IOError: print("Premature end of block data") return inhdr = self.inF.read(8) if (not inhdr or (inhdr[0] == "\0")): self.inF.close() self.inF = None self.inFn = self.inFn + 1 continue inMagic = inhdr[:4] if (inMagic != self.settings['netmagic']): print("Invalid magic: " + inMagic.hex()) return inLenLE = inhdr[4:] su = struct.unpack("