def print_status(self, verbose):
"""Print file reader status text."""
if verbose >= 1:
# print buffer offset
print("# File: '%s', stream_offset: %s, count: %s, more: %r" %
(self.filename, self.stream_offset,
len(self.current), self.more()))
if verbose >= 2:
# print buffer contents
print("# previous: '%s'\nCurrent: '%s'" %
(be_scan.escape(self.previous),
be_scan.escape(self.current)))
def recurse(uncompressed_buffer, recursion_prefix, depth):
"""Recursively scan and uncompress until max depth."""
# runtime status
if args.verbose >= 1:
print("# Processing %s count %d depth %d..." %
(recursion_prefix, len(uncompressed_buffer), depth))
if args.verbose >= 2:
print("# %s\n" % be_scan.escape(uncompressed_buffer))
# open a scanner
artifacts = be_scan.artifacts_t()
scanner = be_scan.scanner_t(scan_engine, artifacts)
scanner.scan_setup(args.filename, recursion_prefix)
# scan
status = scanner.scan_final(0, "", uncompressed_buffer)
if status:
raise ValueError(status)
# consume recursed artifacts
while True:
artifact = artifacts.get()
if artifact.blank():
break
# prepare for zip or gzip
if artifact.artifact_class == "zip" or \
artifact.artifact_class == "gzip":
# uncompress
uncompressed = uncompressor.uncompress(uncompressed_buffer,
artifact.offset)
if not uncompressed.status and not uncompressed.buffer:
# no error and nothing uncompressed so disregard artifact
continue
set_compression_text(artifact, uncompressed)
# skip popular useless uncompressed data
if artifact.artifact == "8da7a0b0144fc58332b03e90aaf7ba25":
continue
# prepare for other artifact types as needed
# none.
# print the artifact
print(artifact.to_string())
# manage recursion
if (artifact.artifact_class == "zip" or \
artifact.artifact_class == "gzip") and \
depth <= MAX_RECURSION_DEPTH:
# calculate next recursion prefix
next_recursion_prefix = "%s-%d-%s" % (
artifact.recursion_prefix, artifact.offset,
artifact.artifact_class.upper())
# recurse
recurse(uncompressed.buffer, next_recursion_prefix, depth + 1)
def test_escape():
str_equals(be_scan.escape("a\0b"), "a\\x00b")
def scan_range(filename, offset, page_size, margin_size, max_depth, verbose):
with open(filename, 'rb') as f:
f.seek(offset)
buffer1 = f.read(page_size)
buffer2 = f.read(margin_size)
# print runtime status
if verbose >= 1:
# print buffer offset
print("# File: '%s', offset: %d, size: %d, overflow size: %d" %
(filename, offset, len(buffer1), len(buffer2)))
if verbose >= 2:
# print buffer contents
print("# previous: '%s'\nCurrent: '%s'" %
(be_scan.escape(buffer1), be_scan.escape(buffer2)))
# the uncompressor this process will use, if needed
uncompressor = None
# the formatted artifacts
formatted_artifacts = list()
# create scanner
artifacts = be_scan.artifacts_t()
scanner = be_scan.scanner_t(scan_engine, artifacts)
scanner.scan_setup(args.filename, "")
# scan buffer
status = scanner.scan_stream(offset, "", buffer1)
if status:
raise ValueError(status)
# scan fence
status = scanner.scan_fence_final(offset, buffer1, buffer2)
if status:
raise ValueError(status)
# consume
while not artifacts.empty():
artifact = artifacts.get()
# check for compression
if artifact.artifact_class == "zip" or \
artifact.artifact_class == "gzip":
# get uncompressor ready
if uncompressor == None:
uncompressor = be_scan.uncompressor_t()
# get buffer to uncompress
buffer1_offset = artifact.offset - offset
if buffer1_offset + margin_size > len(buffer1):
print("scan_range.a buffer1 offset: %d" % buffer1_offset)
# use margin size
buffer3 = buffer1[buffer1_offset:] + buffer2
# uncompress
uncompressed = uncompressor.uncompress(buffer3, 0)
else:
# use buffer1
print("scan_range.b buffer1 offset: %d" % buffer1_offset)
uncompressed = uncompressor.uncompress(
buffer1, buffer1_offset)
# no error and nothing uncompressed so disregard this artifact
if not uncompressed.status and not uncompressed.buffer:
continue
# set artifact text for this uncompression
set_compression_text(artifact, uncompressed)
# skip popular useless uncompressed data
if artifact.artifact == "8da7a0b0144fc58332b03e90aaf7ba25":
continue
# prepare for other artifact types as needed
# none.
# consume this artifact
formatted_artifacts.append(artifact.to_string())
# manage recursion
if (artifact.artifact_class == "zip" or \
artifact.artifact_class == "gzip") and \
max_depth >= 1:
# calculate recursion prefix for first recursion depth
next_recursion_prefix = "%d-%s" % (
artifact.offset, artifact.artifact_class.upper())
# recurse
recurse(uncompressed.buffer, next_recursion_prefix, 1,
uncompressor, formatted_artifacts, max_depth, verbose)
# return the accumulated list of formatted artifacts
return formatted_artifacts