1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
|
#!/usr/bin/python
#
# linearize-data.py: Construct a linear, no-fork version of the chain.
#
# Copyright (c) 2013 The Bitcoin developers
# Distributed under the MIT/X11 software license, see the accompanying
# file COPYING or http://www.opensource.org/licenses/mit-license.php.
#
import json
import struct
import re
import base64
import httplib
import sys
import hashlib
import datetime
settings = {}
def uint32(x):
return x & 0xffffffffL
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 ''.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)
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.encode('hex')
return hash_str
def get_blk_dt(blk_hdr):
members = struct.unpack("<I", blk_hdr[68:68+4])
dt = datetime.datetime.fromtimestamp(members[0])
dt_ym = datetime.datetime(dt.year, dt.month, 1)
return dt_ym
def get_block_hashes(settings):
blkindex = []
f = open(settings['hashlist'], "r")
for line in f:
line = line.rstrip()
blkindex.append(line)
print("Read " + str(len(blkindex)) + " hashes")
return blkindex
def mkblockset(blkindex):
blkmap = {}
for hash in blkindex:
blkmap[hash] = True
return blkmap
def copydata(settings, blkindex, blkset):
inFn = 0
inF = None
outFn = 0
outsz = 0
outF = None
blkCount = 0
lastDate = datetime.datetime(2000, 1, 1)
timestampSplit = False
fileOutput = True
maxOutSz = settings['max_out_sz']
if 'output' in settings:
fileOutput = False
if settings['split_timestamp'] != 0:
timestampSplit = True
while True:
if not inF:
fname = "%s/blk%05d.dat" % (settings['input'], inFn)
print("Input file" + fname)
inF = open(fname, "rb")
inhdr = inF.read(8)
if (not inhdr or (inhdr[0] == "\0")):
inF.close()
inF = None
inFn = inFn + 1
continue
inMagic = inhdr[:4]
if (inMagic != settings['netmagic']):
print("Invalid magic:" + inMagic)
return
inLenLE = inhdr[4:]
su = struct.unpack("<I", inLenLE)
inLen = su[0]
rawblock = inF.read(inLen)
blk_hdr = rawblock[:80]
hash_str = calc_hash_str(blk_hdr)
if not hash_str in blkset:
print("Skipping unknown block " + hash_str)
continue
if blkindex[blkCount] != hash_str:
print("Out of order block.")
print("Expected " + blkindex[blkCount])
print("Got " + hash_str)
sys.exit(1)
if not fileOutput and ((outsz + inLen) > maxOutSz):
outF.close()
outF = None
outFn = outFn + 1
outsz = 0
if timestampSplit:
blkDate = get_blk_dt(blk_hdr)
if blkDate > lastDate:
print("New month " + blkDate.strftime("%Y-%m") + " @ " + hash_str)
lastDate = blkDate
if outF:
outF.close()
outF = None
outFn = outFn + 1
outsz = 0
if not outF:
if fileOutput:
fname = settings['output_file']
else:
fname = "%s/blk%05d.dat" % (settings['output'], outFn)
print("Output file" + fname)
outF = open(fname, "wb")
outF.write(inhdr)
outF.write(rawblock)
outsz = outsz + inLen + 8
blkCount = blkCount + 1
if (blkCount % 1000) == 0:
print("Wrote " + str(blkCount) + " blocks")
if __name__ == '__main__':
if len(sys.argv) != 2:
print "Usage: linearize-data.py CONFIG-FILE"
sys.exit(1)
f = open(sys.argv[1])
for line in f:
# skip comment lines
m = re.search('^\s*#', line)
if m:
continue
# parse key=value lines
m = re.search('^(\w+)\s*=\s*(\S.*)$', line)
if m is None:
continue
settings[m.group(1)] = m.group(2)
f.close()
if 'netmagic' not in settings:
settings['netmagic'] = 'f9beb4d9'
if 'input' not in settings:
settings['input'] = 'input'
if 'hashlist' not in settings:
settings['hashlist'] = 'hashlist.txt'
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'] = long(settings['max_out_sz'])
settings['split_timestamp'] = int(settings['split_timestamp'])
settings['netmagic'] = settings['netmagic'].decode('hex')
if 'output_file' not in settings and 'output' not in settings:
print("Missing output file / directory")
sys.exit(1)
blkindex = get_block_hashes(settings)
blkset = mkblockset(blkindex)
if not "000000000019d6689c085ae165831e934ff763ae46a2a6c172b3f1b60a8ce26f" in blkset:
print("not found")
else:
copydata(settings, blkindex, blkset)
|
