From 9f080d4ed363f6a25874ae991806f30922a14671 Mon Sep 17 00:00:00 2001

From: Lumir Balhar <lbalhar@redhat.com>

Date: Thu, 24 Oct 2019 10:03:02 +0200

Subject: [PATCH 1/7] Fix prints - from statement to function

---

 officeparser.py | 31 ++++++++++++++++---------------

 1 file changed, 16 insertions(+), 15 deletions(-)

diff --git a/officeparser.py b/officeparser.py

index e521d88..5da5bf4 100755

--- a/officeparser.py

+++ b/officeparser.py

@@ -5,6 +5,7 @@

 #             - VBA: fixed infinite loop when output file already exists

 #             - improved logging output, set default level to INFO

+from __future__ import print_function

 import sys

 from struct import unpack

 from optparse import OptionParser

@@ -268,7 +269,7 @@ def read_chain(self, sector_start):

     def print_fat_sectors(self):

         for sector in self.fat_sectors:

-            print '{0:08X}'.format(sector)

+            print('{0:08X}'.format(sector))

     def get_stream(self, index):

         d = self.directory[index]

@@ -315,7 +316,7 @@ def __init__(self, data, parser_options=None):

         self._sectFat = self.header[18:] # sects of first 109 FAT sectors

     def pretty_print(self):

-        print """HEADER DUMP

+        print("""HEADER DUMP

 _abSig              = {0}

 _clid               = {1}

 _uMinorVersion      = {2}

@@ -353,11 +354,11 @@ def pretty_print(self):

         '{0:08X}'.format(self._sectMiniFatStart),

         '{0:08X}'.format(self._csectMiniFat),

         '{0:08X}'.format(self._sectDifStart),

-        '{0:08X}'.format(self._csectDif))

+        '{0:08X}'.format(self._csectDif)))

         for fat in self._sectFat:

             if fat != FREESECT:

-                print '_sectFat            = {0:08X}'.format(fat)

+                print('_sectFat            = {0:08X}'.format(fat))

 STGTY_INVALID = 0

 STGTY_STORAGE = 1

@@ -416,7 +417,7 @@ def __init__(self, data, index):

         # last two bytes are padding

     def pretty_print(self):

-        print """

+        print("""

 _ab                 = {0}

 _cb                 = {1}

 _mse                = {2}

@@ -446,7 +447,7 @@ def pretty_print(self):

         '{0}'.format(self._time[1]),

         '{0:08X}'.format(self._sectStart),

         '{0:08X} ({0} bytes)'.format(self._ulSize),

-        '{0:04X}'.format(self._dptPropType))

+        '{0:04X}'.format(self._dptPropType)))

 def _main():

@@ -561,22 +562,22 @@ def _main():

     if options.print_directory:

         for x in xrange(0, len(ofdoc.directory)):

-            print "Directory Index {0:08X} ({0})".format(x)

+            print("Directory Index {0:08X} ({0})".format(x))

             ofdoc.directory[x].pretty_print()

-            print

+            print()

     if options.print_fat:

         for sector in xrange(0, len(ofdoc.fat)):

-            print '{0:08X}: {1}'.format(sector, fat_value_to_str(ofdoc.fat[sector]))

+            print('{0:08X}: {1}'.format(sector, fat_value_to_str(ofdoc.fat[sector])))

     if options.print_mini_fat:

         for sector in xrange(0, len(ofdoc.minifat)):

-            print '{0:08X}: {1}'.format(sector, fat_value_to_str(ofdoc.minifat[sector]))

+            print('{0:08X}: {1}'.format(sector, fat_value_to_str(ofdoc.minifat[sector])))

     if options.print_streams:

         for d in ofdoc.directory:

             if d._mse == STGTY_STREAM:

-                print '{0}: {1}'.format(d.index, d.name)

+                print('{0}: {1}'.format(d.index, d.name))

     if options.print_expected_file_size:

         expected_file_size = (len([x for x in ofdoc.fat if x != FREESECT]) * ofdoc.sector_size) + 512

@@ -584,8 +585,8 @@ def _main():

         size_diff = abs(expected_file_size - actual_file_size)

         percent_diff = (float(size_diff) / float(expected_file_size)) * 100.0

-        print "expected file size {0} actual {1} difference {2} ({3:0.2f}%)".format(

-            expected_file_size, actual_file_size, size_diff, percent_diff)

+        print("expected file size {0} actual {1} difference {2} ({3:0.2f}%)".format(

+            expected_file_size, actual_file_size, size_diff, percent_diff))

     #

     # analysis options

@@ -620,7 +621,7 @@ def _main():

                     logging.warning('invalid FAT sector reference {0:08X}'.format(value))

     if options.print_invalid_fat_count:

-        print "invalid FAT sector references: {0}".format(invalid_fat_sectors)

+        print("invalid FAT sector references: {0}".format(invalid_fat_sectors))

     invalid_fat_entries = 0

     if options.check_fat or options.print_invalid_fat_count:

@@ -634,7 +635,7 @@ def _main():

                     logging.warning('invalid FAT sector {0:08X} value {1:08X}'.format(value, ptr))

     if options.print_invalid_fat_count:

-        print "invalid FAT entries: {0}".format(invalid_fat_entries)

+        print("invalid FAT entries: {0}".format(invalid_fat_entries))

     if options.check_orphaned_chains:

         buffer = [False for fat in ofdoc.fat]

From b64db92d77d480f93a973b995fd63c964b16b6fb Mon Sep 17 00:00:00 2001

From: Lumir Balhar <lbalhar@redhat.com>

Date: Thu, 24 Oct 2019 10:47:57 +0200

Subject: [PATCH 2/7] Use BytesIO from compatible io module instead of StringIO

---

 officeparser.py | 6 +++---

 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/officeparser.py b/officeparser.py

index 5da5bf4..82dce4a 100755

--- a/officeparser.py

+++ b/officeparser.py

@@ -9,7 +9,7 @@

 import sys

 from struct import unpack

 from optparse import OptionParser

-from cStringIO import StringIO

+from io import BytesIO

 import logging

 import re

 import os

@@ -218,7 +218,7 @@ def __init__(self, file, parser_options=None):

             # chain in the Fat, with the beginning of the chain stored in the

             # header.

-            data = StringIO(self.read_chain(self.header._sectMiniFatStart))

+            data = BytesIO(self.read_chain(self.header._sectMiniFatStart))

             while True:

                 chunk = data.read(self.sector_size)

                 if chunk == '':

@@ -249,7 +249,7 @@ def __impl_read_chain(self, start, read_sector_f, read_fat_f):

         """Returns the entire contents of a chain starting at the given sector."""

         sector = start

         check = [ sector ] # keep a list of sectors we've already read

-        buffer = StringIO()

+        buffer = BytesIO()

         while sector != ENDOFCHAIN:

             buffer.write(read_sector_f(sector))

             next = read_fat_f(sector)

From 032a0d058bc59d1c3bef5f0b68298720947ac2c5 Mon Sep 17 00:00:00 2001

From: Lumir Balhar <lbalhar@redhat.com>

Date: Thu, 24 Oct 2019 10:48:44 +0200

Subject: [PATCH 3/7] Different parsing bytes to name for Python 2/3

---

 officeparser.py | 9 ++++++++-

 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/officeparser.py b/officeparser.py

index 82dce4a..c9f1d10 100755

--- a/officeparser.py

+++ b/officeparser.py

@@ -28,6 +28,8 @@

 BINFILE_NAME = "/vbaProject.bin"

+PY3 = sys.version_info[0] == 3

+

 def fat_value_to_str(value):

     if value == DIFSECT:

         return '0xFFFFFFFC (DIF)'

@@ -402,7 +404,12 @@ def __init__(self, data, index):

         self._ab = self.directory[0]

         self._cb = self.directory[1]

         # convert wide chars into ASCII

-        self.name = ''.join([x for x in self._ab[0:self._cb] if ord(x) != 0])

+        if PY3:

+            # In Python 3 we have numbers we need to convert to chars

+            self.name = ''.join([chr(x) for x in self._ab[0:self._cb] if x != 0])

+        else:

+            # In Python 2 we have chars we need to convert to numbers to check them

+            self.name = ''.join([x for x in self._ab[0:self._cb] if ord(x) != 0])

         self._mse = self.directory[2]

         self._bflags = self.directory[3]

         self._sidLeftSib = self.directory[4]

From 6afb84b3237cf280bafd95b400e454a8484199be Mon Sep 17 00:00:00 2001

From: Lumir Balhar <lbalhar@redhat.com>

Date: Thu, 24 Oct 2019 10:49:57 +0200

Subject: [PATCH 4/7] Use floor division where we need integer as a result

---

 officeparser.py | 6 +++---

 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/officeparser.py b/officeparser.py

index c9f1d10..2d9aa90 100755

--- a/officeparser.py

+++ b/officeparser.py

@@ -196,14 +196,14 @@ def __init__(self, file, parser_options=None):

             if len(data) != self.sector_size:

                 logging.error('broken FAT (invalid sector size {0} != {1})'.format(len(data), self.sector_size))

             else:

-                for value in unpack('<{0}L'.format(self.sector_size / 4), data):

+                for value in unpack('<{0}L'.format(self.sector_size // 4), data):

                     self.fat.append(value)

         # get the list of directory sectors

         self.directory = []

         buffer = self.read_chain(self.header._sectDirStart)

         directory_index = 0

-        for chunk in unpack("128s" * (len(buffer) / 128), buffer):

+        for chunk in unpack("128s" * (len(buffer) // 128), buffer):

             self.directory.append(Directory(chunk, directory_index))

             directory_index += 1

@@ -228,7 +228,7 @@ def __init__(self, file, parser_options=None):

                 if len(chunk) != self.sector_size:

                     logging.warning("encountered EOF while parsing minifat")

                     continue

-                for value in unpack('<{0}L'.format(self.sector_size / 4), chunk):

+                for value in unpack('<{0}L'.format(self.sector_size // 4), chunk):

                     self.minifat.append(value)

     def read_sector(self, sector):

From ace8691eacba4dce0e6bf95292dab9f3a34396eb Mon Sep 17 00:00:00 2001

From: Lumir Balhar <lbalhar@redhat.com>

Date: Thu, 24 Oct 2019 10:50:34 +0200

Subject: [PATCH 5/7] chunk is '' in Python 2 and b'' in Python 3 so better is

 to check its length

---

 officeparser.py | 2 +-

 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/officeparser.py b/officeparser.py

index 2d9aa90..fb1d07c 100755

--- a/officeparser.py

+++ b/officeparser.py

@@ -223,7 +223,7 @@ def __init__(self, file, parser_options=None):

             data = BytesIO(self.read_chain(self.header._sectMiniFatStart))

             while True:

                 chunk = data.read(self.sector_size)

-                if chunk == '':

+                if len(chunk) == 0:

                     break

                 if len(chunk) != self.sector_size:

                     logging.warning("encountered EOF while parsing minifat")

From 0a4c0189d7f6aefb09e4b7299ca0626a39a6d20b Mon Sep 17 00:00:00 2001

From: Lumir Balhar <lbalhar@redhat.com>

Date: Thu, 24 Oct 2019 10:57:35 +0200

Subject: [PATCH 6/7] Use compatible way for writing binary data to stdout

---

 officeparser.py | 8 ++++----

 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/officeparser.py b/officeparser.py

index fb1d07c..43d45ea 100755

--- a/officeparser.py

+++ b/officeparser.py

@@ -685,20 +685,20 @@ def _main():

     # dump options

     #

     if options.dump_sector:

-        sys.stdout.write(ofdoc.read_sector(options.dump_sector))

+        os.write(sys.stdout.fileno(), ofdoc.read_sector(options.dump_sector))

         sys.exit(0)

     if options.dump_ministream:

-        sys.stdout.write(ofdoc.ministream)

+        os.write(sys.stdout.fileno(), (ofdoc.ministream))

         sys.exit(0)

     if options.dump_stream:

-        sys.stdout.write(ofdoc.get_stream(options.dump_stream))

+        os.write(sys.stdout.fileno(), (ofdoc.get_stream(options.dump_stream)))

         sys.exit(0)

     if options.dump_stream_by_name:

         d = ofdoc.find_stream_by_name(options.dump_stream_by_name)

-        sys.stdout.write(ofdoc.get_stream(d.index))

+        os.write(sys.stdout.fileno(), (ofdoc.get_stream(d.index)))

         sys.exit(0)

     #

From fa56b4b1717eb195cd12605a8e3706a33662ffb8 Mon Sep 17 00:00:00 2001

From: Lumir Balhar <lbalhar@redhat.com>

Date: Thu, 24 Oct 2019 12:45:10 +0200

Subject: [PATCH 7/7] Write bytes to file opened as binary

---

 officeparser.py | 4 ++--

 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/officeparser.py b/officeparser.py

index 43d45ea..fdf155a 100755

--- a/officeparser.py

+++ b/officeparser.py

@@ -801,8 +801,8 @@ def _main():

                 f.write(ofdoc.get_stream(d.index))

                 f.close()

                 if options.create_manifest:

-                    manifest.write(os.path.basename(filename))

-                    manifest.write("\n")

+                    manifest.write(os.path.basename(filename).encode())

+                    manifest.write(b"\n")

                 logging.debug("created file {0}".format(filename))

     while options.extract_macros: