diff options
Diffstat (limited to 'contrib')
| -rwxr-xr-x | contrib/devtools/check-doc.py | 2 | ||||
| -rwxr-xr-x | contrib/devtools/copyright_header.py | 4 | ||||
| -rwxr-xr-x | contrib/devtools/lint-python.sh | 6 | ||||
| -rwxr-xr-x | contrib/devtools/security-check.py | 2 | ||||
| -rwxr-xr-x | contrib/devtools/test-security-check.py | 32 | ||||
| -rwxr-xr-x | contrib/linearize/linearize-data.py | 532 | ||||
| -rwxr-xr-x | contrib/linearize/linearize-hashes.py | 248 | ||||
| -rwxr-xr-x | contrib/seeds/generate-seeds.py | 2 |
8 files changed, 421 insertions, 407 deletions
diff --git a/contrib/devtools/check-doc.py b/contrib/devtools/check-doc.py index 0c2e1a24be..de5719eb29 100755 --- a/contrib/devtools/check-doc.py +++ b/contrib/devtools/check-doc.py @@ -17,7 +17,7 @@ import sys FOLDER_GREP = 'src' FOLDER_TEST = 'src/test/' REGEX_ARG = '(?:ForceSet|SoftSet|Get|Is)(?:Bool)?Args?(?:Set)?\("(-[^"]+)"' -REGEX_DOC = 'HelpMessageOpt\("(-[^"=]+?)(?:=|")' +REGEX_DOC = 'AddArg\("(-[^"=]+?)(?:=|")' CMD_ROOT_DIR = '`git rev-parse --show-toplevel`/{}'.format(FOLDER_GREP) CMD_GREP_ARGS = r"git grep --perl-regexp '{}' -- {} ':(exclude){}'".format(REGEX_ARG, CMD_ROOT_DIR, FOLDER_TEST) CMD_GREP_DOCS = r"git grep --perl-regexp '{}' {}".format(REGEX_DOC, CMD_ROOT_DIR) diff --git a/contrib/devtools/copyright_header.py b/contrib/devtools/copyright_header.py index e7cccaab03..82d3c19683 100755 --- a/contrib/devtools/copyright_header.py +++ b/contrib/devtools/copyright_header.py @@ -506,7 +506,7 @@ def file_has_hashbang(file_lines): def insert_python_header(filename, file_lines, start_year, end_year): if file_has_hashbang(file_lines): - insert_idx = 1 + insert_idx = 1 else: insert_idx = 0 header_lines = get_python_header_lines_to_insert(start_year, end_year) @@ -571,7 +571,7 @@ def insert_cmd(argv): if extension not in ['.h', '.cpp', '.cc', '.c', '.py']: sys.exit("*** cannot insert for file extension %s" % extension) - if extension == '.py': + if extension == '.py': style = 'python' else: style = 'cpp' diff --git a/contrib/devtools/lint-python.sh b/contrib/devtools/lint-python.sh index 239337000d..7d3555b6d4 100755 --- a/contrib/devtools/lint-python.sh +++ b/contrib/devtools/lint-python.sh @@ -6,11 +6,13 @@ # # Check for specified flake8 warnings in python files. +# E101 indentation contains mixed spaces and tabs # E112 expected an indented block # E113 unexpected indentation # E115 expected an indented block (comment) # E116 unexpected indentation (comment) # E125 continuation line with same indent as next logical line +# E129 visually indented line with same indent as next logical line # E131 continuation line unaligned for hanging indent # E133 closing bracket is missing indentation # E223 tab before operator @@ -61,6 +63,8 @@ # F823 local variable name … referenced before assignment # F831 duplicate argument name in function definition # F841 local variable 'foo' is assigned to but never used +# W191 indentation contains tabs +# W291 trailing whitespace # W292 no newline at end of file # W293 blank line contains whitespace # W504 line break after binary operator @@ -71,4 +75,4 @@ # W605 invalid escape sequence "x" # W606 'async' and 'await' are reserved keywords starting with Python 3.7 -flake8 --ignore=B,C,E,F,I,N,W --select=E112,E113,E115,E116,E125,E131,E133,E223,E224,E242,E266,E271,E272,E273,E274,E275,E304,E306,E401,E402,E502,E701,E702,E703,E714,E721,E741,E742,E743,F401,E901,E902,F402,F404,F406,F407,F601,F602,F621,F622,F631,F701,F702,F703,F704,F705,F706,F707,F811,F812,F821,F822,F823,F831,F841,W292,W293,W504,W601,W602,W603,W604,W605,W606 . +flake8 --ignore=B,C,E,F,I,N,W --select=E101,E112,E113,E115,E116,E125,E129,E131,E133,E223,E224,E242,E266,E271,E272,E273,E274,E275,E304,E306,E401,E402,E502,E701,E702,E703,E714,E721,E741,E742,E743,F401,E901,E902,F402,F404,F406,F407,F601,F602,F621,F622,F631,F701,F702,F703,F704,F705,F706,F707,F811,F812,F821,F822,F823,F831,F841,W191,W291,W292,W293,W504,W601,W602,W603,W604,W605,W606 . diff --git a/contrib/devtools/security-check.py b/contrib/devtools/security-check.py index 0f2099953f..c9516ef83f 100755 --- a/contrib/devtools/security-check.py +++ b/contrib/devtools/security-check.py @@ -150,7 +150,7 @@ def check_PE_DYNAMIC_BASE(executable): def check_PE_HIGH_ENTROPY_VA(executable): '''PIE: DllCharacteristics bit 0x20 signifies high-entropy ASLR''' (arch,bits) = get_PE_dll_characteristics(executable) - if arch == 'i386:x86-64': + if arch == 'i386:x86-64': reqbits = IMAGE_DLL_CHARACTERISTICS_HIGH_ENTROPY_VA else: # Unnecessary on 32-bit assert(arch == 'i386') diff --git a/contrib/devtools/test-security-check.py b/contrib/devtools/test-security-check.py index ee87c8bab4..307e057736 100755 --- a/contrib/devtools/test-security-check.py +++ b/contrib/devtools/test-security-check.py @@ -32,29 +32,39 @@ class TestSecurityChecks(unittest.TestCase): cc = 'gcc' write_testcode(source) - self.assertEqual(call_security_check(cc, source, executable, ['-Wl,-zexecstack','-fno-stack-protector','-Wl,-znorelro']), + self.assertEqual(call_security_check(cc, source, executable, ['-Wl,-zexecstack','-fno-stack-protector','-Wl,-znorelro']), (1, executable+': failed PIE NX RELRO Canary')) - self.assertEqual(call_security_check(cc, source, executable, ['-Wl,-znoexecstack','-fno-stack-protector','-Wl,-znorelro']), + self.assertEqual(call_security_check(cc, source, executable, ['-Wl,-znoexecstack','-fno-stack-protector','-Wl,-znorelro']), (1, executable+': failed PIE RELRO Canary')) - self.assertEqual(call_security_check(cc, source, executable, ['-Wl,-znoexecstack','-fstack-protector-all','-Wl,-znorelro']), + self.assertEqual(call_security_check(cc, source, executable, ['-Wl,-znoexecstack','-fstack-protector-all','-Wl,-znorelro']), (1, executable+': failed PIE RELRO')) - self.assertEqual(call_security_check(cc, source, executable, ['-Wl,-znoexecstack','-fstack-protector-all','-Wl,-znorelro','-pie','-fPIE']), + self.assertEqual(call_security_check(cc, source, executable, ['-Wl,-znoexecstack','-fstack-protector-all','-Wl,-znorelro','-pie','-fPIE']), (1, executable+': failed RELRO')) - self.assertEqual(call_security_check(cc, source, executable, ['-Wl,-znoexecstack','-fstack-protector-all','-Wl,-zrelro','-Wl,-z,now','-pie','-fPIE']), + self.assertEqual(call_security_check(cc, source, executable, ['-Wl,-znoexecstack','-fstack-protector-all','-Wl,-zrelro','-Wl,-z,now','-pie','-fPIE']), (0, '')) - def test_PE(self): + def test_32bit_PE(self): source = 'test1.c' executable = 'test1.exe' cc = 'i686-w64-mingw32-gcc' write_testcode(source) - self.assertEqual(call_security_check(cc, source, executable, []), - (1, executable+': failed PIE NX')) - self.assertEqual(call_security_check(cc, source, executable, ['-Wl,--nxcompat']), - (1, executable+': failed PIE')) - self.assertEqual(call_security_check(cc, source, executable, ['-Wl,--nxcompat','-Wl,--dynamicbase']), + self.assertEqual(call_security_check(cc, source, executable, []), + (1, executable+': failed DYNAMIC_BASE NX')) + self.assertEqual(call_security_check(cc, source, executable, ['-Wl,--nxcompat']), + (1, executable+': failed DYNAMIC_BASE')) + self.assertEqual(call_security_check(cc, source, executable, ['-Wl,--nxcompat','-Wl,--dynamicbase']), (0, '')) + def test_64bit_PE(self): + source = 'test1.c' + executable = 'test1.exe' + cc = 'x86_64-w64-mingw32-gcc' + write_testcode(source) + + self.assertEqual(call_security_check(cc, source, executable, []), (1, executable+': failed DYNAMIC_BASE NX\n'+executable+': warning HIGH_ENTROPY_VA')) + self.assertEqual(call_security_check(cc, source, executable, ['-Wl,--nxcompat']), (1, executable+': failed DYNAMIC_BASE\n'+executable+': warning HIGH_ENTROPY_VA')) + self.assertEqual(call_security_check(cc, source, executable, ['-Wl,--nxcompat','-Wl,--dynamicbase']), (0, executable+': warning HIGH_ENTROPY_VA')) + self.assertEqual(call_security_check(cc, source, executable, ['-Wl,--nxcompat','-Wl,--dynamicbase','-Wl,--high-entropy-va']), (0, '')) if __name__ == '__main__': unittest.main() diff --git a/contrib/linearize/linearize-data.py b/contrib/linearize/linearize-data.py index c609e9b336..f8aea27342 100755 --- a/contrib/linearize/linearize-data.py +++ b/contrib/linearize/linearize-data.py @@ -22,300 +22,300 @@ from binascii import hexlify, unhexlify settings = {} 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() + """ 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 + return x & 0xffffffff def bytereverse(x): - return uint32(( ((x) << 24) | (((x) << 8) & 0x00ff0000) | - (((x) >> 8) & 0x0000ff00) | ((x) >> 24) )) + 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) + 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) + 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() + hash1 = hashlib.sha256() + hash1.update(blk_hdr) + hash1_o = hash1.digest() - hash2 = hashlib.sha256() - hash2.update(hash1_o) - hash2_o = hash2.digest() + hash2 = hashlib.sha256() + hash2.update(hash1_o) + hash2_o = hash2.digest() - return hash2_o + return hash2_o def calc_hash_str(blk_hdr): - hash = calc_hdr_hash(blk_hdr) - hash = bufreverse(hash) - hash = wordreverse(hash) - hash_str = hexlify(hash).decode('utf-8') - return hash_str + hash = calc_hdr_hash(blk_hdr) + hash = bufreverse(hash) + hash = wordreverse(hash) + hash_str = hexlify(hash).decode('utf-8') + return hash_str def get_blk_dt(blk_hdr): - members = struct.unpack("<I", blk_hdr[68:68+4]) - nTime = members[0] - dt = datetime.datetime.fromtimestamp(nTime) - dt_ym = datetime.datetime(dt.year, dt.month, 1) - return (dt_ym, nTime) + members = struct.unpack("<I", blk_hdr[68:68+4]) + nTime = members[0] + dt = datetime.datetime.fromtimestamp(nTime) + 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) + 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") + print("Read " + str(len(blkindex)) + " hashes") - return blkindex + return blkindex # The block map shouldn't give or receive byte-reversed hashes. def mkblockmap(blkindex): - blkmap = {} - for height,hash in enumerate(blkindex): - blkmap[hash] = height - return blkmap + blkmap = {} + for height,hash in enumerate(blkindex): + blkmap[hash] = height + return blkmap # Block header and extent on disk BlockExtent = namedtuple('BlockExtent', ['fn', 'offset', 'inhdr', 'blkhdr', 'size']) class BlockDataCopier: - def __init__(self, settings, blkindex, blkmap): - self.settings = settings - self.blkindex = blkindex - self.blkmap = blkmap - - self.inFn = 0 - self.inF = None - self.outFn = 0 - self.outsz = 0 - self.outF = None - self.outFname = None - self.blkCountIn = 0 - self.blkCountOut = 0 - - self.lastDate = datetime.datetime(2000, 1, 1) - self.highTS = 1408893517 - 315360000 - self.timestampSplit = False - self.fileOutput = True - self.setFileTime = False - self.maxOutSz = settings['max_out_sz'] - if 'output' in settings: - self.fileOutput = False - if settings['file_timestamp'] != 0: - self.setFileTime = True - if settings['split_timestamp'] != 0: - self.timestampSplit = True - # Extents and cache for out-of-order blocks - self.blockExtents = {} - self.outOfOrderData = {} - self.outOfOrderSize = 0 # running total size for items in outOfOrderData - - def writeBlock(self, inhdr, blk_hdr, rawblock): - blockSizeOnDisk = len(inhdr) + len(blk_hdr) + len(rawblock) - if not self.fileOutput and ((self.outsz + blockSizeOnDisk) > 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'], "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) - 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('%i blocks scanned, %i blocks written (of %i, %.1f%% complete)' % - (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'], "blk%05d.dat" % fn) - - 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: " + hexlify(inMagic).decode('utf-8')) - return - inLenLE = inhdr[4:] - su = struct.unpack("<I", inLenLE) - inLen = su[0] - 80 # length without header - blk_hdr = self.inF.read(80) - inExtent = BlockExtent(self.inFn, self.inF.tell(), inhdr, blk_hdr, inLen) - - 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[self.hash_str] - self.blkCountIn += 1 - - if self.blkCountOut == blkHeight: - # If in-order block, just copy - rawblock = self.inF.read(inLen) - self.writeBlock(inhdr, blk_hdr, rawblock) - - # See if we can catch up to prior out-of-order blocks - while self.blkCountOut in self.blockExtents: - self.copyOneBlock() - - else: # If out-of-order, skip over block data for now - self.blockExtents[blkHeight] = inExtent - if self.outOfOrderSize < self.settings['out_of_order_cache_sz']: - # If there is space in the cache, read the data - # Reading the data in file sequence instead of seeking and fetching it later is preferred, - # but we don't want to fill up memory - self.outOfOrderData[blkHeight] = self.inF.read(inLen) - self.outOfOrderSize += inLen - else: # If no space in cache, seek forward - self.inF.seek(inLen, os.SEEK_CUR) - - print("Done (%i blocks written)" % (self.blkCountOut)) + def __init__(self, settings, blkindex, blkmap): + self.settings = settings + self.blkindex = blkindex + self.blkmap = blkmap + + self.inFn = 0 + self.inF = None + self.outFn = 0 + self.outsz = 0 + self.outF = None + self.outFname = None + self.blkCountIn = 0 + self.blkCountOut = 0 + + self.lastDate = datetime.datetime(2000, 1, 1) + self.highTS = 1408893517 - 315360000 + self.timestampSplit = False + self.fileOutput = True + self.setFileTime = False + self.maxOutSz = settings['max_out_sz'] + if 'output' in settings: + self.fileOutput = False + if settings['file_timestamp'] != 0: + self.setFileTime = True + if settings['split_timestamp'] != 0: + self.timestampSplit = True + # Extents and cache for out-of-order blocks + self.blockExtents = {} + self.outOfOrderData = {} + self.outOfOrderSize = 0 # running total size for items in outOfOrderData + + def writeBlock(self, inhdr, blk_hdr, rawblock): + blockSizeOnDisk = len(inhdr) + len(blk_hdr) + len(rawblock) + if not self.fileOutput and ((self.outsz + blockSizeOnDisk) > 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'], "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) + 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('%i blocks scanned, %i blocks written (of %i, %.1f%% complete)' % + (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'], "blk%05d.dat" % fn) + + 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: " + hexlify(inMagic).decode('utf-8')) + return + inLenLE = inhdr[4:] + su = struct.unpack("<I", inLenLE) + inLen = su[0] - 80 # length without header + blk_hdr = self.inF.read(80) + inExtent = BlockExtent(self.inFn, self.inF.tell(), inhdr, blk_hdr, inLen) + + 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[self.hash_str] + self.blkCountIn += 1 + + if self.blkCountOut == blkHeight: + # If in-order block, just copy + rawblock = self.inF.read(inLen) + self.writeBlock(inhdr, blk_hdr, rawblock) + + # See if we can catch up to prior out-of-order blocks + while self.blkCountOut in self.blockExtents: + self.copyOneBlock() + + else: # If out-of-order, skip over block data for now + self.blockExtents[blkHeight] = inExtent + if self.outOfOrderSize < self.settings['out_of_order_cache_sz']: + # If there is space in the cache, read the data + # Reading the data in file sequence instead of seeking and fetching it later is preferred, + # but we don't want to fill up memory + self.outOfOrderData[blkHeight] = self.inF.read(inLen) + self.outOfOrderSize += inLen + else: # If no space in cache, seek forward + self.inF.seek(inLen, os.SEEK_CUR) + + print("Done (%i blocks written)" % (self.blkCountOut)) 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() - - # 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: - settings['genesis'] = '000000000019d6689c085ae165831e934ff763ae46a2a6c172b3f1b60a8ce26f' - if 'input' not in settings: - settings['input'] = 'input' - if 'hashlist' not in settings: - settings['hashlist'] = 'hashlist.txt' - if 'file_timestamp' not in settings: - settings['file_timestamp'] = 0 - if 'split_timestamp' not in settings: - settings['split_timestamp'] = 0 - if 'max_out_sz' not in settings: - 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'] = int(settings['max_out_sz']) - settings['split_timestamp'] = int(settings['split_timestamp']) - settings['file_timestamp'] = int(settings['file_timestamp']) - 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") - sys.exit(1) - - 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() + 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() + + # 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: + settings['genesis'] = '000000000019d6689c085ae165831e934ff763ae46a2a6c172b3f1b60a8ce26f' + if 'input' not in settings: + settings['input'] = 'input' + if 'hashlist' not in settings: + settings['hashlist'] = 'hashlist.txt' + if 'file_timestamp' not in settings: + settings['file_timestamp'] = 0 + if 'split_timestamp' not in settings: + settings['split_timestamp'] = 0 + if 'max_out_sz' not in settings: + 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'] = int(settings['max_out_sz']) + settings['split_timestamp'] = int(settings['split_timestamp']) + settings['file_timestamp'] = int(settings['file_timestamp']) + 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") + sys.exit(1) + + 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 e1304e26d0..8e1266ae0b 100755 --- a/contrib/linearize/linearize-hashes.py +++ b/contrib/linearize/linearize-hashes.py @@ -22,135 +22,135 @@ import os.path settings = {} 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() + """ 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) - 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): - 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().decode('utf-8') - resp_obj = json.loads(body) - return resp_obj - - @staticmethod - def build_request(idx, method, params): - obj = { 'version' : '1.1', - 'method' : method, - 'id' : idx } - if params is None: - obj['params'] = [] - else: - obj['params'] = params - return obj - - @staticmethod - def response_is_error(resp_obj): - return 'error' in resp_obj and resp_obj['error'] is not None + def __init__(self, host, port, username, password): + authpair = "%s:%s" % (username, password) + 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): + 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().decode('utf-8') + resp_obj = json.loads(body) + return resp_obj + + @staticmethod + def build_request(idx, method, params): + obj = { 'version' : '1.1', + 'method' : method, + 'id' : idx } + if params is None: + obj['params'] = [] + else: + obj['params'] = params + return obj + + @staticmethod + def response_is_error(resp_obj): + return 'error' in resp_obj and resp_obj['error'] is not None def get_block_hashes(settings, max_blocks_per_call=10000): - rpc = BitcoinRPC(settings['host'], settings['port'], - settings['rpcuser'], settings['rpcpassword']) - - height = settings['min_height'] - while height < settings['max_height']+1: - num_blocks = min(settings['max_height']+1-height, max_blocks_per_call) - batch = [] - for x in range(num_blocks): - 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) - sys.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 + rpc = BitcoinRPC(settings['host'], settings['port'], + settings['rpcuser'], settings['rpcpassword']) + + height = settings['min_height'] + while height < settings['max_height']+1: + num_blocks = min(settings['max_height']+1-height, max_blocks_per_call) + batch = [] + for x in range(num_blocks): + 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) + sys.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 def get_rpc_cookie(): - # Open the cookie file - with open(os.path.join(os.path.expanduser(settings['datadir']), '.cookie'), 'r') as f: - combined = f.readline() - combined_split = combined.split(":") - settings['rpcuser'] = combined_split[0] - settings['rpcpassword'] = combined_split[1] + # Open the cookie file + with open(os.path.join(os.path.expanduser(settings['datadir']), '.cookie'), 'r') as f: + combined = f.readline() + combined_split = combined.split(":") + settings['rpcuser'] = combined_split[0] + settings['rpcpassword'] = combined_split[1] if __name__ == '__main__': - if len(sys.argv) != 2: - print("Usage: linearize-hashes.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.*)$', line) - if m is None: - continue - settings[m.group(1)] = m.group(2) - f.close() - - if 'host' not in settings: - settings['host'] = '127.0.0.1' - if 'port' not in settings: - settings['port'] = 8332 - if 'min_height' not in settings: - settings['min_height'] = 0 - if 'max_height' not in settings: - settings['max_height'] = 313000 - if 'rev_hash_bytes' not in settings: - settings['rev_hash_bytes'] = 'false' - - use_userpass = True - use_datadir = False - if 'rpcuser' not in settings or 'rpcpassword' not in settings: - use_userpass = False - if 'datadir' in settings and not use_userpass: - use_datadir = True - if not use_userpass and not use_datadir: - print("Missing datadir or username and/or password in cfg file", file=sys.stderr) - sys.exit(1) - - settings['port'] = int(settings['port']) - settings['min_height'] = int(settings['min_height']) - settings['max_height'] = int(settings['max_height']) - - # Force hash byte format setting to be lowercase to make comparisons easier. - settings['rev_hash_bytes'] = settings['rev_hash_bytes'].lower() - - # Get the rpc user and pass from the cookie if the datadir is set - if use_datadir: - get_rpc_cookie() - - get_block_hashes(settings) + if len(sys.argv) != 2: + print("Usage: linearize-hashes.py CONFIG-FILE") + sys.exit(1) + + f = open(sys.argv[1]) + for line in f: + # skip comment lines + m = re.search('^\s*#', line) + if m: + continue + + # parse key=value lines + m = re.search('^(\w+)\s*=\s*(\S.*)$', line) + if m is None: + continue + settings[m.group(1)] = m.group(2) + f.close() + + if 'host' not in settings: + settings['host'] = '127.0.0.1' + if 'port' not in settings: + settings['port'] = 8332 + if 'min_height' not in settings: + 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' + + use_userpass = True + use_datadir = False + if 'rpcuser' not in settings or 'rpcpassword' not in settings: + use_userpass = False + if 'datadir' in settings and not use_userpass: + use_datadir = True + if not use_userpass and not use_datadir: + print("Missing datadir or username and/or password in cfg file", file=sys.stderr) + sys.exit(1) + + settings['port'] = int(settings['port']) + settings['min_height'] = int(settings['min_height']) + settings['max_height'] = int(settings['max_height']) + + # Force hash byte format setting to be lowercase to make comparisons easier. + settings['rev_hash_bytes'] = settings['rev_hash_bytes'].lower() + + # Get the rpc user and pass from the cookie if the datadir is set + if use_datadir: + get_rpc_cookie() + + get_block_hashes(settings) diff --git a/contrib/seeds/generate-seeds.py b/contrib/seeds/generate-seeds.py index 72eb7255f3..ace7d3534f 100755 --- a/contrib/seeds/generate-seeds.py +++ b/contrib/seeds/generate-seeds.py @@ -11,7 +11,7 @@ argument: nodes_main.txt nodes_test.txt -These files must consist of lines in the format +These files must consist of lines in the format <ip> <ip>:<port> |