Skip to content

Commit

Permalink
Merge pull request #5 from joedinsmoor/main
Browse files Browse the repository at this point in the history 
Added modularity, explicit requirements, testing framework. Addresses #3
  • Loading branch information
@phoenixrising1800
phoenixrising1800 authored Sep 8, 2023
2 parents 3146f4c + 4790db0 commit c550d8c
Show file tree
Hide file tree
Showing 6 changed files with 248 additions and 163 deletions.
40 changes: 40 additions & 0 deletions .github/workflows/python-package.yml
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,40 @@
# This workflow will install Python dependencies, run tests and lint with a variety of Python versions
# For more information see: https://docs.github.com/en/actions/automating-builds-and-tests/building-and-testing-python

name: Python package

on:
push:
branches: [ "main" ]
pull_request:
branches: [ "main" ]

jobs:
build:

runs-on: ubuntu-latest
strategy:
fail-fast: false
matrix:
python-version: ["3.9", "3.10", "3.11"]

steps:
- uses: actions/checkout@v3
- name: Set up Python ${{ matrix.python-version }}
uses: actions/setup-python@v3
with:
python-version: ${{ matrix.python-version }}
- name: Install dependencies
run: |
python -m pip install --upgrade pip
python -m pip install flake8 pytest
if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
- name: Lint with flake8
run: |
# stop the build if there are Python syntax errors or undefined names
flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
# exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
- name: Test with pytest
run: |
pytest tests/tests.py
170 changes: 7 additions & 163 deletions main.py
View file
Original file line number Diff line number Diff line change
@@ -1,6 +1,8 @@
import os
import csv
from bitstring import ConstBitStream
from src.sms import *
from src.contacts import *

def input_file():
filename = input("Path to binary BREW OS memory image file: ")
Expand All @@ -23,171 +25,13 @@ def main():
print("Enter valid path to file")
file = input_file()

## Initialize filesize (given a starting and ending offset)
file_size_bytes = os.path.getsize(file)
print(f'File size: {file_size_bytes} bytes') # Print file size

#### EXTRACT CONTACT DATA
## Open phone memory dump image file
data = open(file, 'rb')

## Load file into a bit data stream
s = ConstBitStream(filename=file)
occurances = s.findall(contactHeader, bytealigned=True)
occurances = list(occurances)
foundOccurances = len(occurances)
print("Found " + str(foundOccurances) + " memory addresses matching contact header " + str(contactHeader) + "\n")

totalEntries = 0
foundContactEntries = [["Entry #", "Contact Name", "Associated Phone Number", "Memory Address Offset"]]
## Read list of total occurances found
for i in range(0, foundOccurances):
## Find each offset, then read
occuranceOffset = hex(int(occurances[i]/8))

## Set bit stream position to individual offset
s.bitpos = occurances[i]

## Record ~valid~ contact entry data
# READ THE FIRST 8 BYTES (64 bits) -- a.k.a. the contactHeader (01 06 00 05 08 08 00)
headerData = s.read('hex:64')
# SKIP THE NEXT 6 BYTES (48 bits)
skipData = s.read('pad:48')
# READ THE NEXT 3 BYTES (24 bits) -- bytes leading up to important data (00 04 00)
leadingData = s.read('hex:24')
# READ THE NEXT 1 BYTE (8 bits) -- a.k.a. the length of the following name entry
contactNameLength = s.read('intle:8')
# SKIP THE NEXT 1 BYTE (8 bits)
skipData = s.read('pad:8')
# READ THE NEXT n BYTES (8bit*n-bytes)-- a.k.a. the next number of bytes found from contactNameLength*8
try: # skip entry if error is thrown
CONTACT_NAME = s.read(8*contactNameLength).tobytes().decode()
except UnicodeDecodeError:
continue
# READ THE NEXT 2 BYTES (16 bits) -- should be SAME for all entries (0x0601), else skip this occurance
skipData = s.read('hex:16')
if str(skipData) != afterContactNameHeader:
continue
# READ THE NEXT 1 BYTE (8 bits) -- either 0x0F or 0x0C (AREA CODE or NO AREA CODE included, meaning number is either 10d or 7d long)
areaCodeData = s.read('hex:8')
if str(areaCodeData) == areaCodeInd: # number will be 10d long (includes 3d area code)
phoneNumberLength = 10
elif str(areaCodeData) == noAreaCodeInd: # number will be 7d long (does not include area code)
phoneNumberLength = 7
else: # invalid/broken entry, so move on
continue
# READ THE NEXT 6 BYTES (48 bits) -- should be same for all valid entries, else skip bad entry
skipData = s.read('hex:48')
if str(skipData) != phoneNumberHeader:
continue
# READ THE NEXT n BYTES (8bit*n-bytes) -- a.k.a. the contact's phone number found from phoneNumberLength*8
# Then format phone number
tempPhone = s.read(8*phoneNumberLength).tobytes().decode()
CONTACT_PHONE_NUMBER = ''
is_10d_flag = False
if len(tempPhone) == 10:
is_10d_flag = True
if is_10d_flag:
for i in range(0, len(tempPhone)):
if i == 3 or i == 6:
CONTACT_PHONE_NUMBER = CONTACT_PHONE_NUMBER + '-' + tempPhone[i]
else:
CONTACT_PHONE_NUMBER = CONTACT_PHONE_NUMBER + tempPhone[i]
else:
for i in range(0, len(tempPhone)):
if i == 3:
CONTACT_PHONE_NUMBER = CONTACT_PHONE_NUMBER + '-' + tempPhone[i]
else:
CONTACT_PHONE_NUMBER = CONTACT_PHONE_NUMBER + tempPhone[i]


## Increment found entry with each successful contact parsed
totalEntries += 1

## PRINT all important entry information
print("Contact at address: " + str(occuranceOffset) + ", Entry #: " + str(totalEntries))
print("\tName: " + str(CONTACT_NAME))
print("\tNumber: " + str(CONTACT_PHONE_NUMBER))

foundContactEntries.append([str(totalEntries), CONTACT_NAME, CONTACT_PHONE_NUMBER, str(occuranceOffset)])
data.close()

## Write output to csv file
with open('foundContacts.csv', 'w', newline='') as outfile:
writer = csv.writer(outfile, dialect=csv.excel)
for entry in foundContactEntries:
writer.writerow(entry)
print("\nTotal contact entries found: " + str(totalEntries))
contactEntries = getContacts(file)

print("\nTotal contact entries found: " + str(contactEntries))

#*****************************************************************
#### EXTRACT SMS DATA
data2 = open(file, 'rb')
## Load file into a bit data stream
s = ConstBitStream(filename=file)
occurances = s.findall(smsHeader, bytealigned=True)
occurances = list(occurances)
foundOccurances = len(occurances)
print("Found " + str(foundOccurances) + " memory addresses matching SMS header " + str(smsHeader) + "\n")

totalEntries = 0
foundSmsEntries = [["Entry #", "Message Content", "Associated Phone Number", "Memory Address Offset"]]
## Read list of total occurances found
for i in range(0, foundOccurances):
## Find each offset, then read
occuranceOffset = hex(int(occurances[i]/8))

## Set bit stream position to individual offset
s.bitpos = occurances[i]

## Record ~valid~ contact entry data
# READ THE FIRST 9 BYTES (72 bits) -- a.k.a. the smsHeader (02 15 00 00 01 16 01 04 06)
headerData = s.read('hex:72')
# READ the NEXT 1 BYTE (8 bits) -- a.k.a. length of following message
msgDataLength = s.read('intle:8')
# SKIP the NEXT 1 BYTE (8 bits) -- should always be '00' for all valid entries
#skipData = s.read('pad:8')
skipData = s.read('hex:8')
#print("\tSkip data: " + str(skipData))
# READ the NEXT n BYTES (8bits*n-bytes)
try: # skip entry if error is thrown
MSG_DATA = s.read(8*msgDataLength).tobytes().decode()
except UnicodeDecodeError:
#print("\tUnicodeDecodeError with Message data")
continue
# SKIP the NEXT 17 BYTES (136 bits)
skipData = s.read('hex:136')
# READ the NEXT 2 BYTES (16 bits) -- a.k.a. the msgNumberHeader, if not valid, then skip
skipData = s.read('hex:16')
if str(skipData) != msgNumberHeader:
#print("Error data != msgNumberHeader: " + str(skipData))
continue
# READ THE NEXT 10 BYTES (80 bits) -- a.k.a. the mobile phone number assoc. with SMS message
try:
MOBILE_SENDER = s.read(8*10).tobytes().decode()
MOBILE_SENDER = int(MOBILE_SENDER) # test value for invalid data characters
except UnicodeDecodeError:
continue
except ValueError:
continue
finally:
MOBILE_SENDER = str(MOBILE_SENDER)

## Increment found entry with each successful contact parsed
totalEntries += 1
## PRINT all important SMS information
print("SMS Message at address: " + str(occuranceOffset) + ", Entry #: " + str(totalEntries))
print("\t\"" + str(MSG_DATA) + "\"")
print("\tSender #: " + str(MOBILE_SENDER))

foundSmsEntries.append([str(totalEntries), MSG_DATA, MOBILE_SENDER, str(occuranceOffset)])
data2.close()

## Write output to csv file
with open('foundSMSData.csv', 'w', newline='') as outfile:
writer = csv.writer(outfile, dialect=csv.excel)
for entry in foundSmsEntries:
writer.writerow(entry)
print("\nTotal SMS data entries found: " + str(totalEntries))
smsEntries = getSMS(file)
print("\nTotal SMS data entries found: " + str(smsEntries))

if __name__ == '__main__':
main()
Binary file added requirements.txt
View file
Binary file not shown.
108 changes: 108 additions & 0 deletions src/contacts.py
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,108 @@
import os
import csv
from bitstring import ConstBitStream

def getContacts(file):
contactHeader = b'\x01\x06\x00\x05\x08\x08\x00'
smsHeader = b'\x02\x15\x00\x00\x01\x16\x01\x04\x06'
afterContactNameHeader = '0601'
msgNumberHeader = '7f80'
areaCodeInd = '0f'
noAreaCodeInd = '0c'
phoneNumberHeader = '0000ff000000'


file_size_bytes = os.path.getsize(file)
print(f'File size: {file_size_bytes} bytes') # Print file size

#### EXTRACT CONTACT DATA
## Open phone memory dump image file
data = open(file, 'rb')

## Load file into a bit data stream
s = ConstBitStream(filename=file)
occurances = s.findall(contactHeader, bytealigned=True)
occurances = list(occurances)
foundOccurances = len(occurances)
print("Found " + str(foundOccurances) + " memory addresses matching contact header " + str(contactHeader) + "\n")

totalEntries = 0
foundContactEntries = [["Entry #", "Contact Name", "Associated Phone Number", "Memory Address Offset"]]
## Read list of total occurances found
for i in range(0, foundOccurances):
## Find each offset, then read
occuranceOffset = hex(int(occurances[i]/8))

## Set bit stream position to individual offset
s.bitpos = occurances[i]

## Record ~valid~ contact entry data
# READ THE FIRST 8 BYTES (64 bits) -- a.k.a. the contactHeader (01 06 00 05 08 08 00)
headerData = s.read('hex:64')
# SKIP THE NEXT 6 BYTES (48 bits)
skipData = s.read('pad:48')
# READ THE NEXT 3 BYTES (24 bits) -- bytes leading up to important data (00 04 00)
leadingData = s.read('hex:24')
# READ THE NEXT 1 BYTE (8 bits) -- a.k.a. the length of the following name entry
contactNameLength = s.read('intle:8')
# SKIP THE NEXT 1 BYTE (8 bits)
skipData = s.read('pad:8')
# READ THE NEXT n BYTES (8bit*n-bytes)-- a.k.a. the next number of bytes found from contactNameLength*8
try: # skip entry if error is thrown
CONTACT_NAME = s.read(8*contactNameLength).tobytes().decode()
except UnicodeDecodeError:
continue
# READ THE NEXT 2 BYTES (16 bits) -- should be SAME for all entries (0x0601), else skip this occurance
skipData = s.read('hex:16')
if str(skipData) != afterContactNameHeader:
continue
# READ THE NEXT 1 BYTE (8 bits) -- either 0x0F or 0x0C (AREA CODE or NO AREA CODE included, meaning number is either 10d or 7d long)
areaCodeData = s.read('hex:8')
if str(areaCodeData) == areaCodeInd: # number will be 10d long (includes 3d area code)
phoneNumberLength = 10
elif str(areaCodeData) == noAreaCodeInd: # number will be 7d long (does not include area code)
phoneNumberLength = 7
else: # invalid/broken entry, so move on
continue
# READ THE NEXT 6 BYTES (48 bits) -- should be same for all valid entries, else skip bad entry
skipData = s.read('hex:48')
if str(skipData) != phoneNumberHeader:
continue
# READ THE NEXT n BYTES (8bit*n-bytes) -- a.k.a. the contact's phone number found from phoneNumberLength*8
# Then format phone number
tempPhone = s.read(8*phoneNumberLength).tobytes().decode()
CONTACT_PHONE_NUMBER = ''
is_10d_flag = False
if len(tempPhone) == 10:
is_10d_flag = True
if is_10d_flag:
for i in range(0, len(tempPhone)):
if i == 3 or i == 6:
CONTACT_PHONE_NUMBER = CONTACT_PHONE_NUMBER + '-' + tempPhone[i]
else:
CONTACT_PHONE_NUMBER = CONTACT_PHONE_NUMBER + tempPhone[i]
else:
for i in range(0, len(tempPhone)):
if i == 3:
CONTACT_PHONE_NUMBER = CONTACT_PHONE_NUMBER + '-' + tempPhone[i]
else:
CONTACT_PHONE_NUMBER = CONTACT_PHONE_NUMBER + tempPhone[i]


## Increment found entry with each successful contact parsed
totalEntries += 1

## PRINT all important entry information
print("Contact at address: " + str(occuranceOffset) + ", Entry #: " + str(totalEntries))
print("\tName: " + str(CONTACT_NAME))
print("\tNumber: " + str(CONTACT_PHONE_NUMBER))

foundContactEntries.append([str(totalEntries), CONTACT_NAME, CONTACT_PHONE_NUMBER, str(occuranceOffset)])
data.close()

## Write output to csv file
with open('foundContacts.csv', 'w', newline='') as outfile:
writer = csv.writer(outfile, dialect=csv.excel)
for entry in foundContactEntries:
writer.writerow(entry)
return totalEntries
Loading

0 comments on commit c550d8c

Please sign in to comment.