cut-bytes.py

#!/usr/bin/env python

__description__ = 'Cut a section of bytes out of a file'
__author__ = 'Didier Stevens'
__version__ = '0.0.17'
__date__ = '2024/06/26'

"""

Source code put in public domain by Didier Stevens, no Copyright
https://DidierStevens.com
Use at your own risk

History:
  2015/09/13: start
  2015/11/10: 0.0.2 added support for :-number
  2015/12/16: 0.0.3 added support [...]number+number
  2015/12/17: continue
  2016/08/02: 0.0.4 added dumps
  2017/03/04: 0.0.5 updated man
  2017/11/01: 0.0.6 updated cDump, added cBinaryFile
  2017/12/01: 0.0.7 updated FilenameCheckHash to handle empty file: #
  2018/03/05: updated #e# expressions
  2018/11/07: 0.0.8 added options -A, -g, -G and --jsonoutput; added hexadecimal support for offset in cut-expression
  2019/02/16: 0.0.9 updated cut expression format
  2019/07/22: 0.0.10 bugfix #e#chr
  2019/10/10: added options prefix and suffix
  2019/10/28: Python 3 fixes
  2020/01/20: 0.0.11 added ParsePackExpression #p#
  2020/01/24: added #h# support for spaces
  2020/01/25: fix ascii dump 127
  2020/02/01: 0.0.12 added #u#
  2020/02/18: 0.0.13 added #E#
  2020/10/21: Python 3 fix in cBinaryFile
  2020/12/08: base64dump fix
  2022/04/11: 0.0.14 added data for prefix and suffix
  2022/06/27: 0.0.15 Python 3 fix
  2023/02/13: 0.0.16 added options -P and -S; added pyzipper
  2024/06/26: 0.0.17 added support for files to prefix and suffix options

Todo:
"""

import optparse
import textwrap
import re
import sys
import os
import binascii
import random
import gzip
import json
import struct
import codecs
if sys.version_info[0] >= 3:
    from io import BytesIO as DataIO
else:
    from cStringIO import StringIO as DataIO
if sys.version_info[0] >= 3:
    from io import StringIO
else:
    from cStringIO import StringIO
if sys.version_info[0] >= 3:
    import urllib.request as urllib23
else:
    import urllib2 as urllib23
try:
    import pyzipper as zipfile
except ImportError:
    import zipfile

MALWARE_PASSWORD = 'infected'
dumplinelength = 16

def PrintManual():
    manual = '''
Manual:

cut-bytes.py reads a file (from disk, from stdin or from inside a (password protected) ZIP file) or a here document (#), and outputs it (partially) to stdout.
cut-bytes.py can be instructed via a cut-expression to only send partial input to stdout.
The cut-expression selects a part of the data to output. By default, only one match of the cut-expression is performed. With option -g (grep), all matches are selected. Option -G (grepno, e.g. grep non-overlapping) is the same as -g, but without overlap of the selected parts.

The cut-expression allows for the partial selection of a stream. Use this expression to "cut out" part of the stream.
This cut-expression is composed of 2 terms separated by a colon (:), like this:
termA:termB
termA and termB can be:
- nothing (an empty string)
- a positive decimal number; example: 10
- an hexadecimal number (to be preceded by 0x); example: 0x10
- a case sensitive ASCII string to search for (surrounded by square brackets and single quotes); example: ['MZ']
- a case sensitive UNICODE string to search for (surrounded by square brackets and single quotes prefixed with u); example: [u'User']
- an hexadecimal string to search for (surrounded by square brackets); example: [d0cf11e0]
If termA is nothing, then the cut section of bytes starts with the byte at position 0.
If termA is a number, then the cut section of bytes starts with the byte at the position given by the number (first byte has index 0).
If termA is a string to search for, then the cut section of bytes starts with the byte at the position where the string is first found. If the string is not found, the cut is empty (0 bytes).
If termB is nothing, then the cut section of bytes ends with the last byte.
If termB is a number, then the cut section of bytes ends with the byte at the position given by the number (first byte has index 0).
When termB is a number, it can have suffix letter l. This indicates that the number is a length (number of bytes), and not a position.
termB can also be a negative number (decimal or hexademical): in that case the position is counted from the end of the file. For example, :-5 selects the complete file except the last 5 bytes.
If termB is a string to search for, then the cut section of bytes ends with the last byte at the position where the string is first found. If the string is not found, the cut is empty (0 bytes).
No checks are made to assure that the position specified by termA is lower than the position specified by termB. This is left up to the user.
Search string expressions (ASCII, UNICODE and hexadecimal) can be followed by an instance (a number equal to 1 or greater) to indicate which instance needs to be taken. For example, ['ABC']2 will search for the second instance of string 'ABC'. If this instance is not found, then nothing is selected.
Search string expressions (ASCII, UNICODE and hexadecimal) can be followed by an offset (+ or - a number) to add (or substract) an offset to the found instance. This number can be a decimal or hexadecimal (prefix 0x) value. For example, ['ABC']+3 will search for the first instance of string 'ABC' and then select the bytes after ABC (+ 3).
Finally, search string expressions (ASCII, UNICODE and hexadecimal) can be followed by an instance and an offset.
Examples:
This cut-expression can be used to dump the first 256 bytes of a PE file located inside the stream: ['MZ']:0x100l
This cut-expression can be used to dump the OLE file located inside the stream: [d0cf11e0]:

Data can be added to the selected data using option -p --prefix or/and -s --suffix. The value for option -p and -s is a here document (#..., see later).

Data can be processed with a Python function using option -P (don't use untrusted input for this option, as it is processed by Python's eval function).

Example:
 cut-bytes.py -P "lambda a: a.upper()" : #Hello
Output:
 HELLO

An extra Python script (for example with custom definitions) can be loaded using option -s.

By default the output uses the same representation as the input, but this can be changed to hex, ascii dump or base64 with options -x, -X, -a, -A, -b and -B.

With option --jsonoutput (to be used with -g or -G), cut-bytes will output selected content as a JSON object that can be piped into other tools that support this JSON format.

In stead of cutting from a file, the file argument can be a here document. To achieve this, precede the text with character #.
If the text to pass via the argument contains control characters or non-printable characters, hexadecimal (#h#) or base64 (#b#) can be used.

Example:
 cut-bytes.py : #Hello
Output:
 Hello

Example:
 cut-bytes.py : #h#48656C6C6F
Output:
 Hello

Example:
 cut-bytes.py : #b#SGVsbG8=
Output:
 Hello

File arguments that start with #e# are a notational convention to use expressions to generate data. An expression is a single function/string or the concatenation of several functions/strings (using character + as concatenation operator).
Strings can be characters enclosed by single quotes ('example') or hexadecimal strings prefixed by 0x (0xBEEF).
4 functions are available: random, loremipsum, repeat and chr.

Function random takes exactly one argument: an integer (with value 1 or more). Integers can be specified using decimal notation or hexadecimal notation (prefix 0x).
The random function generates a sequence of bytes with a random value (between 0 and 255), the argument specifies how many bytes need to be generated. Remark that the random number generator that is used is just the Python random number generator, not a cryptographic random number generator.

Example:

tool.py #e#random(100)

will make the tool process data consisting of a sequence of 100 random bytes.

Function loremipsum takes exactly one argument: an integer (with value 1 or more).
The loremipsum function generates "lorem ipsum" text (fake latin), the argument specifies the number of sentences to generate.

Example: #e#loremipsum(2) generates this text:
Ipsum commodo proin pulvinar hac vel nunc dignissim neque eget odio erat magna lorem urna cursus fusce facilisis porttitor congue eleifend taciti. Turpis duis suscipit facilisi tristique dictum praesent natoque sem mi egestas venenatis per dui sit sodales est condimentum habitasse ipsum phasellus non bibendum hendrerit.

Function chr takes one argument or two arguments.
chr with one argument takes an integer between 0 and 255, and generates a single byte with the value specified by the integer.
chr with two arguments takes two integers between 0 and 255, and generates a byte sequence with the values specified by the integers.
For example #e#chr(0x41,0x45) generates data ABCDE.

Function repeat takes two arguments: an integer (with value 1 or more) and a byte sequence. This byte sequence can be a quoted string of characters (single quotes), like 'ABCDE' or an hexadecimal string prefixed with 0x, like 0x4142434445.
The repeat function will create a sequence of bytes consisting of the provided byte sequence (the second argument) repeated as many times as specified by the first argument.
For example, #e#repeat(3, 'AB') generates byte sequence ABABAB.

When more than one function needs to be used, the byte sequences generated by the functions can be concatenated with the + operator.
For example, #e#repeat(10,0xFF)+random(100) will generate a byte sequence of 10 FF bytes followed by 100 random bytes.

File arguments that start with #p# are a notational convention to pack a Python expression to generate data (using Python module struct).
The string after #p# must contain 2 expressions separated by a # character, like #p#I#123456.
The first expression (I in this example) is the format string for the Python struct.pack function, and the second expression (123456 in this example) is a Python expression that needs to be packed by struct.pack.
In this example, format string I represents an unsigned, 32-bit, little-endian integer, and thus #p#I#123456 generates byte sequence 40E20100 (hexadecimal).
Remark that the Python expression is evaluated with Python's eval function: this can be abused to achieve arbitrary code execution.

File arguments that start with #u# are a notational convention to download a file using an url.
For example: #u#http://didierstevens.com

File arguments that start with #E# are a notational convention for strings with escape characters.
For example: #E#line1\nline2

To process a file that starts with #, prefix it with a relative path to the current directory:
 cut-bytes.py : .\#data
Output:
 Test!

Or use option --literalfilenames.

cut-bytes can process a file stored inside a (password protected) ZIP file too. To process the ZIP file itself, use option --noextraction. The default password is infected, and can be changed with option --password.

This Python script was developed with Python 2.7 and tested with Python 2.7 and 3.6.

'''
    for line in manual.split('\n'):
        print(textwrap.fill(line))

#Convert 2 Bytes If Python 3
def C2BIP3(string):
    if sys.version_info[0] > 2:
        return bytes([ord(x) for x in string])
    else:
        return string

def IfWIN32SetBinary(io):
    if sys.platform == 'win32':
        import msvcrt
        msvcrt.setmode(io.fileno(), os.O_BINARY)

# CIC: Call If Callable
def CIC(expression):
    if callable(expression):
        return expression()
    else:
        return expression

# IFF: IF Function
def IFF(expression, valueTrue, valueFalse):
    if expression:
        return CIC(valueTrue)
    else:
        return CIC(valueFalse)

class cDump():
    def __init__(self, data, prefix='', offset=0, dumplinelength=16):
        self.data = data
        self.prefix = prefix
        self.offset = offset
        self.dumplinelength = dumplinelength

    def HexDump(self):
        oDumpStream = self.cDumpStream(self.prefix)
        hexDump = ''
        for i, b in enumerate(self.data):
            if i % self.dumplinelength == 0 and hexDump != '':
                oDumpStream.Addline(hexDump)
                hexDump = ''
            hexDump += IFF(hexDump == '', '', ' ') + '%02X' % self.C2IIP2(b)
        oDumpStream.Addline(hexDump)
        return oDumpStream.Content()

    def CombineHexAscii(self, hexDump, asciiDump):
        if hexDump == '':
            return ''
        countSpaces = 3 * (self.dumplinelength - len(asciiDump))
        if len(asciiDump) <= self.dumplinelength / 2:
            countSpaces += 1
        return hexDump + '  ' + (' ' * countSpaces) + asciiDump

    def HexAsciiDump(self, rle=False):
        oDumpStream = self.cDumpStream(self.prefix)
        position = ''
        hexDump = ''
        asciiDump = ''
        previousLine = None
        countRLE = 0
        for i, b in enumerate(self.data):
            b = self.C2IIP2(b)
            if i % self.dumplinelength == 0:
                if hexDump != '':
                    line = self.CombineHexAscii(hexDump, asciiDump)
                    if not rle or line != previousLine:
                        if countRLE > 0:
                            oDumpStream.Addline('* %d 0x%02x' % (countRLE, countRLE * self.dumplinelength))
                        oDumpStream.Addline(position + line)
                        countRLE = 0
                    else:
                        countRLE += 1
                    previousLine = line
                position = '%08X:' % (i + self.offset)
                hexDump = ''
                asciiDump = ''
            if i % self.dumplinelength == self.dumplinelength / 2:
                hexDump += ' '
            hexDump += ' %02X' % b
            asciiDump += IFF(b >= 32 and b < 127, chr(b), '.')
        if countRLE > 0:
            oDumpStream.Addline('* %d 0x%02x' % (countRLE, countRLE * self.dumplinelength))
        oDumpStream.Addline(self.CombineHexAscii(position + hexDump, asciiDump))
        return oDumpStream.Content()

    def Base64Dump(self, nowhitespace=False):
        encoded = binascii.b2a_base64(self.data).decode().strip()
        if nowhitespace:
            return encoded
        oDumpStream = self.cDumpStream(self.prefix)
        length = 64
        for i in range(0, len(encoded), length):
            oDumpStream.Addline(encoded[0+i:length+i])
        return oDumpStream.Content()

    class cDumpStream():
        def __init__(self, prefix=''):
            self.oStringIO = StringIO()
            self.prefix = prefix

        def Addline(self, line):
            if line != '':
                self.oStringIO.write(self.prefix + line + '\n')

        def Content(self):
            return self.oStringIO.getvalue()

    @staticmethod
    def C2IIP2(data):
        if sys.version_info[0] > 2:
            return data
        else:
            return ord(data)

def HexDump(data):
    return cDump(data, dumplinelength=dumplinelength).HexDump()

def HexAsciiDump(data, rle=False):
    return cDump(data, dumplinelength=dumplinelength).HexAsciiDump(rle=rle)

def Base64Dump(data, nowhitespace=False):
    return cDump(data, dumplinelength=dumplinelength).Base64Dump(nowhitespace=nowhitespace)

CUTTERM_NOTHING = 0
CUTTERM_POSITION = 1
CUTTERM_FIND = 2
CUTTERM_LENGTH = 3

def Replace(string, dReplacements):
    if string in dReplacements:
        return dReplacements[string]
    else:
        return string

def ParseInteger(argument):
    sign = 1
    if argument.startswith('+'):
        argument = argument[1:]
    elif argument.startswith('-'):
        argument = argument[1:]
        sign = -1
    if argument.startswith('0x'):
        return sign * int(argument[2:], 16)
    else:
        return sign * int(argument)

def ParseCutTerm(argument):
    if argument == '':
        return CUTTERM_NOTHING, None, ''
    oMatch = re.match(r'\-?0x([0-9a-f]+)', argument, re.I)
    if oMatch == None:
        oMatch = re.match(r'\-?(\d+)', argument)
    else:
        value = int(oMatch.group(1), 16)
        if argument.startswith('-'):
            value = -value
        return CUTTERM_POSITION, value, argument[len(oMatch.group(0)):]
    if oMatch == None:
        oMatch = re.match(r'\[([0-9a-f]+)\](\d+)?([+-](?:0x[0-9a-f]+|\d+))?', argument, re.I)
    else:
        value = int(oMatch.group(1))
        if argument.startswith('-'):
            value = -value
        return CUTTERM_POSITION, value, argument[len(oMatch.group(0)):]
    if oMatch == None:
        oMatch = re.match(r"\[u?\'(.+?)\'\](\d+)?([+-](?:0x[0-9a-f]+|\d+))?", argument)
    else:
        if len(oMatch.group(1)) % 2 == 1:
            raise Exception("Uneven length hexadecimal string")
        else:
            return CUTTERM_FIND, (binascii.a2b_hex(oMatch.group(1)), int(Replace(oMatch.group(2), {None: '1'})), ParseInteger(Replace(oMatch.group(3), {None: '0'}))), argument[len(oMatch.group(0)):]
    if oMatch == None:
        return None, None, argument
    else:
        if argument.startswith("[u'"):
            # convert ascii to unicode 16 byte sequence
            searchtext = oMatch.group(1).encode('utf16')[2:]
        else:
            searchtext = oMatch.group(1).encode('latin')
        return CUTTERM_FIND, (searchtext, int(Replace(oMatch.group(2), {None: '1'})), ParseInteger(Replace(oMatch.group(3), {None: '0'}))), argument[len(oMatch.group(0)):]

def ParseCutArgument(argument):
    type, value, remainder = ParseCutTerm(argument.strip())
    if type == CUTTERM_NOTHING:
        return CUTTERM_NOTHING, None, CUTTERM_NOTHING, None
    elif type == None:
        if remainder.startswith(':'):
            typeLeft = CUTTERM_NOTHING
            valueLeft = None
            remainder = remainder[1:]
        else:
            return None, None, None, None
    else:
        typeLeft = type
        valueLeft = value
        if typeLeft == CUTTERM_POSITION and valueLeft < 0:
            return None, None, None, None
        if typeLeft == CUTTERM_FIND and valueLeft[1] == 0:
            return None, None, None, None
        if remainder.startswith(':'):
            remainder = remainder[1:]
        else:
            return None, None, None, None
    type, value, remainder = ParseCutTerm(remainder)
    if type == CUTTERM_POSITION and remainder == 'l':
        return typeLeft, valueLeft, CUTTERM_LENGTH, value
    elif type == None or remainder != '':
        return None, None, None, None
    elif type == CUTTERM_FIND and value[1] == 0:
        return None, None, None, None
    else:
        return typeLeft, valueLeft, type, value

def Find(data, value, nth, startposition=-1):
    position = startposition
    while nth > 0:
        position = data.find(value, position + 1)
        if position == -1:
            return -1
        nth -= 1
    return position

def CutData(stream, cutArgument):
    if cutArgument == '':
        return [stream, None, None]

    typeLeft, valueLeft, typeRight, valueRight = ParseCutArgument(cutArgument)

    if typeLeft == None:
        return [stream, None, None]

    if typeLeft == CUTTERM_NOTHING:
        positionBegin = 0
    elif typeLeft == CUTTERM_POSITION:
        positionBegin = valueLeft
    elif typeLeft == CUTTERM_FIND:
        positionBegin = Find(stream, valueLeft[0], valueLeft[1])
        if positionBegin == -1:
            return ['', None, None]
        positionBegin += valueLeft[2]
    else:
        raise Exception("Unknown value typeLeft")

    if typeRight == CUTTERM_NOTHING:
        positionEnd = len(stream)
    elif typeRight == CUTTERM_POSITION and valueRight < 0:
        positionEnd = len(stream) + valueRight
    elif typeRight == CUTTERM_POSITION:
        positionEnd = valueRight + 1
    elif typeRight == CUTTERM_LENGTH:
        positionEnd = positionBegin + valueRight
    elif typeRight == CUTTERM_FIND:
        positionEnd = Find(stream, valueRight[0], valueRight[1], positionBegin)
        if positionEnd == -1:
            return ['', None, None]
        else:
            positionEnd += len(valueRight[0])
        positionEnd += valueRight[2]
    else:
        raise Exception("Unknown value typeRight")

    return [stream[positionBegin:positionEnd], positionBegin, positionEnd]

#Fix for http://bugs.python.org/issue11395
def StdoutWriteChunked(data):
    if sys.version_info[0] > 2:
        if isinstance(data, str):
            sys.stdout.write(data)
        else:
            sys.stdout.buffer.write(data)
    else:
        while data != '':
            sys.stdout.write(data[0:10000])
            try:
                sys.stdout.flush()
            except IOError:
                return
            data = data[10000:]

def LoremIpsumSentence(minimum, maximum):
    words = ['lorem', 'ipsum', 'dolor', 'sit', 'amet', 'consectetur', 'adipiscing', 'elit', 'etiam', 'tortor', 'metus', 'cursus', 'sed', 'sollicitudin', 'ac', 'sagittis', 'eget', 'massa', 'praesent', 'sem', 'fermentum', 'dignissim', 'in', 'vel', 'augue', 'scelerisque', 'auctor', 'libero', 'nam', 'a', 'gravida', 'odio', 'duis', 'vestibulum', 'vulputate', 'quam', 'nec', 'cras', 'nibh', 'feugiat', 'ut', 'vitae', 'ornare', 'justo', 'orci', 'varius', 'natoque', 'penatibus', 'et', 'magnis', 'dis', 'parturient', 'montes', 'nascetur', 'ridiculus', 'mus', 'curabitur', 'nisl', 'egestas', 'urna', 'iaculis', 'lectus', 'maecenas', 'ultrices', 'velit', 'eu', 'porta', 'hac', 'habitasse', 'platea', 'dictumst', 'integer', 'id', 'commodo', 'mauris', 'interdum', 'malesuada', 'fames', 'ante', 'primis', 'faucibus', 'accumsan', 'pharetra', 'aliquam', 'nunc', 'at', 'est', 'non', 'leo', 'nulla', 'sodales', 'porttitor', 'facilisis', 'aenean', 'condimentum', 'rutrum', 'facilisi', 'tincidunt', 'laoreet', 'ultricies', 'neque', 'diam', 'euismod', 'consequat', 'tempor', 'elementum', 'lobortis', 'erat', 'ligula', 'risus', 'donec', 'phasellus', 'quisque', 'vivamus', 'pellentesque', 'tristique', 'venenatis', 'purus', 'mi', 'dictum', 'posuere', 'fringilla', 'quis', 'magna', 'pretium', 'felis', 'pulvinar', 'lacinia', 'proin', 'viverra', 'lacus', 'suscipit', 'aliquet', 'dui', 'molestie', 'dapibus', 'mollis', 'suspendisse', 'sapien', 'blandit', 'morbi', 'tellus', 'enim', 'maximus', 'semper', 'arcu', 'bibendum', 'convallis', 'hendrerit', 'imperdiet', 'finibus', 'fusce', 'congue', 'ullamcorper', 'placerat', 'nullam', 'eros', 'habitant', 'senectus', 'netus', 'turpis', 'luctus', 'volutpat', 'rhoncus', 'mattis', 'nisi', 'ex', 'tempus', 'eleifend', 'vehicula', 'class', 'aptent', 'taciti', 'sociosqu', 'ad', 'litora', 'torquent', 'per', 'conubia', 'nostra', 'inceptos', 'himenaeos']
    sample = random.sample(words, random.randint(minimum, maximum))
    sample[0] = sample[0].capitalize()
    return ' '.join(sample) + '.'

def LoremIpsum(sentences):
    return ' '.join([LoremIpsumSentence(15, 30) for i in range(sentences)])

STATE_START = 0
STATE_IDENTIFIER = 1
STATE_STRING = 2
STATE_SPECIAL_CHAR = 3
STATE_ERROR = 4

FUNCTIONNAME_REPEAT = 'repeat'
FUNCTIONNAME_RANDOM = 'random'
FUNCTIONNAME_CHR = 'chr'
FUNCTIONNAME_LOREMIPSUM = 'loremipsum'

def Tokenize(expression):
    result = []
    token = ''
    state = STATE_START
    while expression != '':
        char = expression[0]
        expression = expression[1:]
        if char == "'":
            if state == STATE_START:
                state = STATE_STRING
            elif state == STATE_IDENTIFIER:
                result.append([STATE_IDENTIFIER, token])
                state = STATE_STRING
                token = ''
            elif state == STATE_STRING:
                result.append([STATE_STRING, token])
                state = STATE_START
                token = ''
        elif char >= '0' and char <= '9' or char.lower() >= 'a' and char.lower() <= 'z':
            if state == STATE_START:
                token = char
                state = STATE_IDENTIFIER
            else:
                token += char
        elif char == ' ':
            if state == STATE_IDENTIFIER:
                result.append([STATE_IDENTIFIER, token])
                token = ''
                state = STATE_START
            elif state == STATE_STRING:
                token += char
        else:
            if state == STATE_IDENTIFIER:
                result.append([STATE_IDENTIFIER, token])
                token = ''
                state = STATE_START
                result.append([STATE_SPECIAL_CHAR, char])
            elif state == STATE_STRING:
                token += char
            else:
                result.append([STATE_SPECIAL_CHAR, char])
                token = ''
    if state == STATE_IDENTIFIER:
        result.append([state, token])
    elif state == STATE_STRING:
        result = [[STATE_ERROR, 'Error: string not closed', token]]
    return result

def ParseFunction(tokens):
    if len(tokens) == 0:
        print('Parsing error')
        return None, tokens
    if tokens[0][0] == STATE_STRING or tokens[0][0] == STATE_IDENTIFIER and tokens[0][1].startswith('0x'):
        return [[FUNCTIONNAME_REPEAT, [[STATE_IDENTIFIER, '1'], tokens[0]]], tokens[1:]]
    if tokens[0][0] != STATE_IDENTIFIER:
        print('Parsing error')
        return None, tokens
    function = tokens[0][1]
    tokens = tokens[1:]
    if len(tokens) == 0:
        print('Parsing error')
        return None, tokens
    if tokens[0][0] != STATE_SPECIAL_CHAR or tokens[0][1] != '(':
        print('Parsing error')
        return None, tokens
    tokens = tokens[1:]
    if len(tokens) == 0:
        print('Parsing error')
        return None, tokens
    arguments = []
    while True:
        if tokens[0][0] != STATE_IDENTIFIER and tokens[0][0] != STATE_STRING:
            print('Parsing error')
            return None, tokens
        arguments.append(tokens[0])
        tokens = tokens[1:]
        if len(tokens) == 0:
            print('Parsing error')
            return None, tokens
        if tokens[0][0] != STATE_SPECIAL_CHAR or (tokens[0][1] != ',' and tokens[0][1] != ')'):
            print('Parsing error')
            return None, tokens
        if tokens[0][0] == STATE_SPECIAL_CHAR and tokens[0][1] == ')':
            tokens = tokens[1:]
            break
        tokens = tokens[1:]
        if len(tokens) == 0:
            print('Parsing error')
            return None, tokens
    return [[function, arguments], tokens]

def Parse(expression):
    tokens = Tokenize(expression)
    if len(tokens) == 0:
        print('Parsing error')
        return None
    if tokens[0][0] == STATE_ERROR:
        print(tokens[0][1])
        print(tokens[0][2])
        print(expression)
        return None
    functioncalls = []
    while True:
        functioncall, tokens = ParseFunction(tokens)
        if functioncall == None:
            return None
        functioncalls.append(functioncall)
        if len(tokens) == 0:
            return functioncalls
        if tokens[0][0] != STATE_SPECIAL_CHAR or tokens[0][1] != '+':
            print('Parsing error')
            return None
        tokens = tokens[1:]

def InterpretInteger(token):
    if token[0] != STATE_IDENTIFIER:
        return None
    try:
        return int(token[1])
    except:
        return None

def Hex2Bytes(hexadecimal):
    if len(hexadecimal) % 2 == 1:
        hexadecimal = '0' + hexadecimal
    try:
        return binascii.a2b_hex(hexadecimal)
    except:
        return None

def C2IIP2(data):
    if sys.version_info[0] > 2:
        return data
    else:
        return ord(data)

def InterpretHexInteger(token):
    if token[0] != STATE_IDENTIFIER:
        return None
    if not token[1].startswith('0x'):
        return None
    bytes = Hex2Bytes(token[1][2:])
    if bytes == None:
        return None
    integer = 0
    for byte in bytes:
        integer = integer * 0x100 + C2IIP2(byte)
    return integer

def InterpretNumber(token):
    number = InterpretInteger(token)
    if number == None:
        return InterpretHexInteger(token)
    else:
        return number

def InterpretBytes(token):
    if token[0] == STATE_STRING:
        return token[1]
    if token[0] != STATE_IDENTIFIER:
        return None
    if not token[1].startswith('0x'):
        return None
    return Hex2Bytes(token[1][2:])

def CheckFunction(functionname, arguments, countarguments, maxcountarguments=None):
    if maxcountarguments == None:
        if countarguments == 0 and len(arguments) != 0:
            print('Error: function %s takes no arguments, %d are given' % (functionname, len(arguments)))
            return True
        if countarguments == 1 and len(arguments) != 1:
            print('Error: function %s takes 1 argument, %d are given' % (functionname, len(arguments)))
            return True
        if countarguments != len(arguments):
            print('Error: function %s takes %d arguments, %d are given' % (functionname, countarguments, len(arguments)))
            return True
    else:
        if len(arguments) < countarguments or len(arguments) > maxcountarguments:
            print('Error: function %s takes between %d and %d arguments, %d are given' % (functionname, countarguments, maxcountarguments, len(arguments)))
            return True
    return False

def CheckNumber(argument, minimum=None, maximum=None):
    number = InterpretNumber(argument)
    if number == None:
        print('Error: argument should be a number: %s' % argument[1])
        return None
    if minimum != None and number < minimum:
        print('Error: argument should be minimum %d: %d' % (minimum, number))
        return None
    if maximum != None and number > maximum:
        print('Error: argument should be maximum %d: %d' % (maximum, number))
        return None
    return number

def Interpret(expression):
    functioncalls = Parse(expression)
    if functioncalls == None:
        return None
    decoded = ''
    for functioncall in functioncalls:
        functionname, arguments = functioncall
        if functionname == FUNCTIONNAME_REPEAT:
            if CheckFunction(functionname, arguments, 2):
                return None
            number = CheckNumber(arguments[0], minimum=1)
            if number == None:
                return None
            bytes = InterpretBytes(arguments[1])
            if bytes == None:
                print('Error: argument should be a byte sequence: %s' % arguments[1][1])
                return None
            decoded += number * bytes.decode('latin')
        elif functionname == FUNCTIONNAME_RANDOM:
            if CheckFunction(functionname, arguments, 1):
                return None
            number = CheckNumber(arguments[0], minimum=1)
            if number == None:
                return None
            decoded += ''.join([chr(random.randint(0, 255)) for x in range(number)])
        elif functionname == FUNCTIONNAME_LOREMIPSUM:
            if CheckFunction(functionname, arguments, 1):
                return None
            number = CheckNumber(arguments[0], minimum=1)
            if number == None:
                return None
            decoded += LoremIpsum(number)
        elif functionname == FUNCTIONNAME_CHR:
            if CheckFunction(functionname, arguments, 1, 2):
                return None
            number = CheckNumber(arguments[0], minimum=0, maximum=255)
            if number == None:
                return None
            if len(arguments) == 1:
                decoded += chr(number)
            else:
                number2 = CheckNumber(arguments[1], minimum=0, maximum=255)
                if number2 == None:
                    return None
                decoded += ''.join([chr(n) for n in range(number, number2 + 1)])
        else:
            print('Error: unknown function: %s' % functionname)
            return None
    return decoded

def ParsePackExpression(expression, data):
    try:
        packFormat, pythonExpression = expression.split('#', 1)
        result = struct.pack(packFormat, eval(pythonExpression))
        return result
    except:
        return None

FCH_FILENAME = 0
FCH_DATA = 1
FCH_ERROR = 2

ESCAPE_SEQUENCE_RE = re.compile(r'''
    ( \\U........      # 8-digit hex escapes
    | \\u....          # 4-digit hex escapes
    | \\x..            # 2-digit hex escapes
    | \\[0-7]{1,3}     # Octal escapes
    | \\N\{[^}]+\}     # Unicode characters by name
    | \\[\\'"abfnrtv]  # Single-character escapes
    )''', re.UNICODE | re.VERBOSE)

def DecodeEscapes(str):
    def DecodeMatch(match):
        return codecs.decode(match.group(0), 'unicode-escape')

    return ESCAPE_SEQUENCE_RE.sub(DecodeMatch, str)

def DownloadFile(url):
    try:
        if sys.hexversion >= 0x020601F0:
            infile = urllib23.urlopen(url, timeout=5)
        else:
            infile = urllib23.urlopen(url)
    except urllib23.HTTPError:
        return None, 'urlopen'
    try:
        data = infile.read()
    except:
        return None, 'read'
    infile.close()
    return data, None

def FilenameCheckHash(filename, literalfilename, data=b''):
    if literalfilename:
        return FCH_FILENAME, filename
    elif filename.startswith('#h#'):
        result = Hex2Bytes(filename[3:].replace(' ', ''))
        if result == None:
            return FCH_ERROR, 'hexadecimal'
        else:
            return FCH_DATA, result
    elif filename.startswith('#b#'):
        try:
            return FCH_DATA, binascii.a2b_base64(filename[3:])
        except:
            return FCH_ERROR, 'base64'
    elif filename.startswith('#e#'):
        result = Interpret(filename[3:])
        if result == None:
            return FCH_ERROR, 'expression'
        else:
            return FCH_DATA, C2BIP3(result)
    elif filename.startswith('#p#'):
        result = ParsePackExpression(filename[3:], data)
        if result == None:
            return FCH_ERROR, 'pack'
        else:
            return FCH_DATA, result
    elif filename.startswith('#u#'):
        result, error = DownloadFile(filename[3:])
        if result == None:
            return FCH_ERROR, 'url:' + error
        else:
            return FCH_DATA, result
    elif filename.startswith('#E#'):
        result = DecodeEscapes(filename[3:])
        if result == None:
            return FCH_ERROR, 'escapes'
        else:
            return FCH_DATA, C2BIP3(result)
    elif filename.startswith('#'):
        return FCH_DATA, C2BIP3(filename[1:])
    else:
        return FCH_FILENAME, filename

def CreateZipFileObject(arg1, arg2):
    if 'AESZipFile' in dir(zipfile):
        return zipfile.AESZipFile(arg1, arg2)
    else:
        return zipfile.ZipFile(arg1, arg2)

class cBinaryFile:
    def __init__(self, filename, zippassword='infected', noextraction=False, literalfilename=False):
        self.filename = filename
        self.zippassword = zippassword
        self.noextraction = noextraction
        self.literalfilename = literalfilename
        self.oZipfile = None

        fch, data = FilenameCheckHash(self.filename, self.literalfilename)
        if fch == FCH_ERROR:
            if data.startswith('url:'):
                raise Exception('Error %s downloading: %s' % (data.split(':')[1], self.filename[3:]))
            else:
                raise Exception('Error %s parsing filename: %s' % (data, self.filename))

        if self.filename == '':
            if sys.platform == 'win32':
                import msvcrt
                msvcrt.setmode(sys.stdin.fileno(), os.O_BINARY)
            self.fIn = sys.stdin
        elif fch == FCH_DATA:
            self.fIn = DataIO(data)
        elif not self.noextraction and self.filename.lower().endswith('.zip'):
            self.oZipfile = CreateZipFileObject(self.filename, 'r')
            if len(self.oZipfile.infolist()) == 1:
                self.fIn = self.oZipfile.open(self.oZipfile.infolist()[0], 'r', self.zippassword)
            else:
                self.oZipfile.close()
                self.oZipfile = None
                self.fIn = open(self.filename, 'rb')
        elif not self.noextraction and self.filename.lower().endswith('.gz'):
            self.fIn = gzip.GzipFile(self.filename, 'rb')
        else:
            self.fIn = open(self.filename, 'rb')

    def close(self):
        if self.fIn != sys.stdin:
            self.fIn.close()
        if self.oZipfile != None:
            self.oZipfile.close()

    def read(self, size=None):
        try:
            fRead = self.fIn.buffer
        except:
            fRead = self.fIn
        if size == None:
            return fRead.read()
        else:
            return fRead.read(size)

    def Data(self):
        data = self.read()
        self.close()
        return data

def LoadScriptIfExists(filename):
    if os.path.exists(filename):
        exec(open(filename, 'r').read(), globals(), globals())

def CutBytes(expression, filename, options):
    data = cBinaryFile(filename, C2BIP3(options.password), options.noextraction, options.literalfilenames).Data()
    if options.grep or options.grepno:
        start = 0
        if options.jsonoutput:
            object = []
            counter = 1
        while True:
            result = CutData(data[start:], expression)
            if result[0] == '':
                break
            else:
                oDump = cDump(result[0], offset=start + result[1], dumplinelength=dumplinelength)
                if options.hexdump:
                    StdoutWriteChunked(oDump.HexDump() + '\n')
                elif options.hexdumpnows:
                    StdoutWriteChunked(binascii.b2a_hex(result[0]) + '\n')
                elif options.base64:
                    StdoutWriteChunked(oDump.Base64Dump())
                elif options.base64nows:
                    StdoutWriteChunked(oDump.Base64Dump(True) + '\n')
                elif options.asciidump:
                    StdoutWriteChunked(oDump.HexAsciiDump() + '\n')
                elif options.asciidumprle:
                    StdoutWriteChunked(oDump.HexAsciiDump(True) + '\n')
                elif options.jsonoutput:
                    object.append({'id': counter, 'name': '0x%08x' % (start + result[1]), 'content': binascii.b2a_base64(result[0]).strip('\n')})
                    counter += 1
                else:
                    if start == 0:
                        IfWIN32SetBinary(sys.stdout)
                    StdoutWriteChunked(result[0])
                if options.grep:
                    start += result[1] + 1
                else:
                    start += result[2]
        if options.jsonoutput:
            print(json.dumps({'version': 2, 'id': 'didierstevens.com', 'type': 'content', 'fields': ['id', 'name', 'content'], 'items': object}))

    else:
        if options.hexdump:
            DumpFunction = lambda x: C2BIP3(HexDump(x))
        elif options.hexdumpnows:
            DumpFunction = lambda x: binascii.b2a_hex(x)
        elif options.base64:
            DumpFunction = Base64Dump
        elif options.base64nows:
            DumpFunction = lambda x: Base64Dump(x, True)
        elif options.asciidump:
            DumpFunction = lambda x: C2BIP3(HexAsciiDump(x, False))
        elif options.asciidumprle:
            DumpFunction = lambda x: C2BIP3(HexAsciiDump(x, True))
        else:
            DumpFunction = lambda x: x
            IfWIN32SetBinary(sys.stdout)

        data = CutData(data, expression)[0]

        if options.prefix != '':
            fch, prefix = FilenameCheckHash(options.prefix, False, data)
            if fch == FCH_DATA:
                data = prefix + data
            elif fch == FCH_FILENAME:
                data = cBinaryFile(prefix, C2BIP3(options.password), options.noextraction, options.literalfilenames).Data() + data
            else:
                raise Exception('Error %s parsing prefix: %s' % (prefix, options.prefix))

        if options.suffix != '':
            fch, suffix = FilenameCheckHash(options.suffix, False, data)
            if fch == FCH_DATA:
                data = data + suffix
            elif fch == FCH_FILENAME:
                data = data + cBinaryFile(suffix, C2BIP3(options.password), options.noextraction, options.literalfilenames).Data()
            else:
                raise Exception('Error %s parsing suffix: %s' % (suffix, options.suffix))

        if options.script != '':
            LoadScriptIfExists(options.script)
        if options.python != '':
            data = eval(options.python)(data)

        StdoutWriteChunked(DumpFunction(data))

def Main():
    oParser = optparse.OptionParser(usage='usage: %prog [options] cut-expression [[#]file]\n' + __description__, version='%prog ' + __version__)
    oParser.add_option('-m', '--man', action='store_true', default=False, help='Print manual')
    oParser.add_option('-g', '--grep', action='store_true', default=False, help='binary grep')
    oParser.add_option('-G', '--grepno', action='store_true', default=False, help='binary grep non-overlapping')
    oParser.add_option('--jsonoutput', action='store_true', default=False, help='produce json output')
    oParser.add_option('-p', '--prefix', default='', help='Prefix expression')
    oParser.add_option('-s', '--suffix', default='', help='Suffix expression')
    oParser.add_option('-P', '--python', default='', help='Python expression')
    oParser.add_option('-S', '--script', type=str, default='', help='Script with definitions to include')
    oParser.add_option('-d', '--dump', action='store_true', default=False, help='perform dump')
    oParser.add_option('-x', '--hexdump', action='store_true', default=False, help='perform hex dump')
    oParser.add_option('-X', '--hexdumpnows', action='store_true', default=False, help='perform hex dump without whitespace')
    oParser.add_option('-a', '--asciidump', action='store_true', default=False, help='perform ascii dump')
    oParser.add_option('-A', '--asciidumprle', action='store_true', default=False, help='perform ascii dump with RLE')
    oParser.add_option('-b', '--base64', action='store_true', default=False, help='perform BASE64 dump')
    oParser.add_option('-B', '--base64nows', action='store_true', default=False, help='perform BASE64 dump without whitespace')
    oParser.add_option('--password', default='infected', help='The ZIP password to be used (default infected)')
    oParser.add_option('--noextraction', action='store_true', default=False, help='Do not extract from archive file')
    oParser.add_option('--literalfilenames', action='store_true', default=False, help='Do not interpret filenames')
    (options, args) = oParser.parse_args()

    if options.man:
        oParser.print_help()
        PrintManual()
        return

    if len(args) == 0 or len(args) > 2:
        oParser.print_help()
        print('')
        print('  Source code put in the public domain by Didier Stevens, no Copyright')
        print('  Use at your own risk')
        print('  https://DidierStevens.com')
        return

    if ParseCutArgument(args[0])[0] == None:
        print('Error: the cut-expression is invalid: %s' % args[0])
        return

    if len(args) == 1:
        CutBytes(args[0], '', options)
    else:
        CutBytes(args[0], args[1], options)

if __name__ == '__main__':
    Main()