FazBrowse GitHub Viewer
|
Trending
|
URL:
|
Home
Tools:
[Download Repo ZIP]
[View Raw Code]
[Original HTTPS Page]
redebug/patchloader.py at master · OS3Lab/redebug · GitHub
OS3Lab
/
redebug
Public
Notifications
You must be signed in to change notification settings
Fork
0
Star
0
Code
Issues
0
Pull requests
0
Projects
Security and quality
0
Insights
Additional navigation options
Code
Issues
Pull requests
Projects
Security and quality
Insights
Expand file tree
Breadcrumbs
redebug
/
patchloader.py
Copy path
More file actions
More file actions
Latest commit
History
History
History
206 lines (184 loc) · 9.16 KB
Breadcrumbs
redebug
/
patchloader.py
Copy path
File metadata and controls
206 lines (184 loc) · 9.16 KB
Raw
Copy raw file
Download raw file
Open symbols panel
Edit and raw actions
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
# patchloader.py
# PatchLoader class
#
# Jiyong Jang, 2012
#
import
os
import
re
import
time
import
mimetypes
import
common
class
PatchLoader
(
object
):
def
__init__
(
self
):
self
.
_patch_list
=
[]
self
.
_npatch
=
0
def
traverse
(
self
,
patch_path
):
'''
Traverse patch files
'''
print
(
'[+] traversing patch files'
)
start_time
=
time
.
time
()
if
os
.
path
.
isfile
(
patch_path
):
magic_type
=
common
.
file_type
(
patch_path
)
common
.
verbose_print
(
' [-] %s: %s'
%
(
patch_path
,
magic_type
))
if
magic_type
.
startswith
(
'text'
):
main_type
,
sub_type
=
magic_type
.
split
(
'/'
)
self
.
_process
(
patch_path
)
elif
os
.
path
.
isdir
(
patch_path
):
for
root
,
dirs
,
files
in
os
.
walk
(
patch_path
):
for
file
in
files
:
file_path
=
os
.
path
.
join
(
root
,
file
)
magic_type
=
common
.
file_type
(
file_path
)
common
.
verbose_print
(
' [-] %s: %s'
%
(
file_path
,
magic_type
))
if
magic_type
.
startswith
(
'text'
):
main_type
,
sub_type
=
magic_type
.
split
(
'/'
)
self
.
_process
(
file_path
)
self
.
_npatch
=
len
(
self
.
_patch_list
)
elapsed_time
=
time
.
time
()
-
start_time
print
(
'[+] %d patches ... %.1fs
\n
'
%
(
self
.
_npatch
,
elapsed_time
))
return
self
.
_npatch
def
_process
(
self
,
patch_path
):
'''
Normalize a patch file and build a hash list
'''
patch_filename
=
patch_path
.
split
(
'/'
)[
-
1
]
patch_file
=
open
(
patch_path
,
'r'
)
patch_lines
=
patch_file
.
readlines
()
patch_file
.
close
()
magic_ext
=
None
process_flag
=
False
diff_file
=
''
diff_cnt
=
0
diff_vuln_lines
=
[]
diff_orig_lines
=
[]
for
line
in
patch_lines
:
if
line
.
startswith
(
'--- '
):
if
diff_vuln_lines
:
diff_norm_lines
=
self
.
_normalize
(
''
.
join
(
diff_vuln_lines
),
magic_ext
).
split
()
if
len
(
diff_norm_lines
)
>=
common
.
ngram_size
:
common
.
verbose_print
(
' [-] %s %d (ext: %d)'
%
(
diff_file
,
diff_cnt
,
magic_ext
))
path
=
'[%s] %s #%d'
%
(
patch_filename
,
diff_file
,
diff_cnt
)
hash_list
=
self
.
_build_hash_list
(
diff_norm_lines
)
self
.
_patch_list
.
append
(
common
.
PatchInfo
(
path
,
magic_ext
,
''
.
join
(
diff_orig_lines
),
diff_norm_lines
,
hash_list
))
else
:
common
.
verbose_print
(
' [-] %s %d (ext: %d) - skipped (%d lines)'
%
(
diff_file
,
diff_cnt
,
magic_ext
,
len
(
diff_norm_lines
)))
del
diff_vuln_lines
[:]
del
diff_orig_lines
[:]
diff_path
=
line
.
split
()[
1
]
if
diff_path
==
'/dev/null'
:
process_flag
=
False
else
:
process_flag
=
True
diff_cnt
=
0
diff_file
=
diff_path
.
split
(
'/'
)[
-
1
]
magic_ext
=
self
.
_get_file_type
(
diff_file
)
elif
process_flag
:
# exclude the line '--' at the end of `git format-patch -1`
if
line
.
startswith
(
'--'
):
continue
if
line
.
startswith
(
'+++ '
):
diff_path
=
line
.
split
()[
1
]
if
diff_path
==
'/dev/null'
:
process_flag
=
False
elif
line
.
startswith
(
'@@'
):
if
diff_vuln_lines
:
diff_norm_lines
=
self
.
_normalize
(
''
.
join
(
diff_vuln_lines
),
magic_ext
).
split
()
if
len
(
diff_norm_lines
)
>=
common
.
ngram_size
:
common
.
verbose_print
(
' [-] %s %d (ext: %d)'
%
(
diff_file
,
diff_cnt
,
magic_ext
))
path
=
'[%s] %s #%d'
%
(
patch_filename
,
diff_file
,
diff_cnt
)
hash_list
=
self
.
_build_hash_list
(
diff_norm_lines
)
self
.
_patch_list
.
append
(
common
.
PatchInfo
(
path
,
magic_ext
,
''
.
join
(
diff_orig_lines
),
diff_norm_lines
,
hash_list
))
else
:
common
.
verbose_print
(
' [-] %s %d (ext: %d) - skipped (%d lines)'
%
(
diff_file
,
diff_cnt
,
magic_ext
,
len
(
diff_norm_lines
)))
del
diff_vuln_lines
[:]
del
diff_orig_lines
[:]
diff_cnt
+=
1
elif
line
.
startswith
(
'-'
):
diff_vuln_lines
.
append
(
line
[
1
:])
diff_orig_lines
.
append
(
'<font color=
\"
#AA0000
\"
>'
)
diff_orig_lines
.
append
(
line
.
replace
(
'<'
,
'<'
).
replace
(
'>'
,
'>'
))
diff_orig_lines
.
append
(
'</font>'
)
elif
line
.
startswith
(
'+'
):
diff_orig_lines
.
append
(
'<font color=
\"
#00AA00
\"
>'
)
diff_orig_lines
.
append
(
line
.
replace
(
'<'
,
'<'
).
replace
(
'>'
,
'>'
))
diff_orig_lines
.
append
(
'</font>'
)
elif
line
.
startswith
(
' '
):
diff_vuln_lines
.
append
(
line
[
1
:])
diff_orig_lines
.
append
(
line
.
replace
(
'<'
,
'<'
).
replace
(
'>'
,
'>'
))
if
diff_vuln_lines
:
diff_norm_lines
=
self
.
_normalize
(
''
.
join
(
diff_vuln_lines
),
magic_ext
).
split
()
if
len
(
diff_norm_lines
)
>=
common
.
ngram_size
:
common
.
verbose_print
(
' [-] %s %d (ext: %d)'
%
(
diff_file
,
diff_cnt
,
magic_ext
))
path
=
'[%s] %s #%d'
%
(
patch_filename
,
diff_file
,
diff_cnt
)
hash_list
=
self
.
_build_hash_list
(
diff_norm_lines
)
self
.
_patch_list
.
append
(
common
.
PatchInfo
(
path
,
magic_ext
,
''
.
join
(
diff_orig_lines
),
diff_norm_lines
,
hash_list
))
else
:
common
.
verbose_print
(
' [-] %s %d (ext: %d) - skipped (%d lines)'
%
(
diff_file
,
diff_cnt
,
magic_ext
,
len
(
diff_norm_lines
)))
def
_normalize
(
self
,
patch
,
ext
):
'''
Normalize a patch file
'''
# Language-specific optimization
if
ext
==
common
.
FileExt
.
C
or
ext
==
common
.
FileExt
.
Java
:
patch
=
''
.
join
([
c
.
group
(
'noncomment'
)
for
c
in
common
.
c_regex
.
finditer
(
patch
)
if
c
.
group
(
'noncomment'
)])
patch
=
''
.
join
([
c
.
group
(
'noncomment'
)
for
c
in
common
.
c_partial_comment_regex
.
finditer
(
patch
)
if
c
.
group
(
'noncomment'
)])
elif
ext
==
common
.
FileExt
.
ShellScript
or
ext
==
common
.
FileExt
.
Python
:
patch
=
''
.
join
([
c
.
group
(
'noncomment'
)
for
c
in
common
.
shellscript_regex
.
finditer
(
patch
)
if
c
.
group
(
'noncomment'
)])
elif
ext
==
common
.
FileExt
.
Perl
:
patch
=
''
.
join
([
c
.
group
(
'noncomment'
)
for
c
in
common
.
perl_regex
.
finditer
(
patch
)
if
c
.
group
(
'noncomment'
)])
elif
ext
==
common
.
FileExt
.
PHP
:
patch
=
''
.
join
([
c
.
group
(
'noncomment'
)
for
c
in
common
.
php_regex
.
finditer
(
patch
)
if
c
.
group
(
'noncomment'
)])
patch
=
''
.
join
([
c
.
group
(
'noncomment'
)
for
c
in
common
.
c_partial_comment_regex
.
finditer
(
patch
)
if
c
.
group
(
'noncomment'
)])
elif
ext
==
common
.
FileExt
.
Ruby
:
patch
=
''
.
join
([
c
.
group
(
'noncomment'
)
for
c
in
common
.
ruby_regex
.
finditer
(
patch
)
if
c
.
group
(
'noncomment'
)])
patch
=
''
.
join
([
c
.
group
(
'noncomment'
)
for
c
in
common
.
ruby_partial_comment_regex
.
finditer
(
patch
)
if
c
.
group
(
'noncomment'
)])
# Remove whitespaces except newlines
patch
=
common
.
whitespaces_regex
.
sub
(
""
,
patch
)
# Convert into lowercases
return
patch
.
lower
()
def
_build_hash_list
(
self
,
diff_norm_lines
):
'''
Build a hash list
'''
hash_list
=
[]
num_ngram
=
len
(
diff_norm_lines
)
-
common
.
ngram_size
+
1
for
i
in
range
(
0
,
num_ngram
):
ngram
=
''
.
join
(
diff_norm_lines
[
i
:
i
+
common
.
ngram_size
])
hash1
=
common
.
fnv1a_hash
(
ngram
)
&
(
common
.
bloomfilter_size
-
1
)
hash2
=
common
.
djb2_hash
(
ngram
)
&
(
common
.
bloomfilter_size
-
1
)
hash3
=
common
.
sdbm_hash
(
ngram
)
&
(
common
.
bloomfilter_size
-
1
)
hash_list
.
append
(
hash1
)
hash_list
.
append
(
hash2
)
hash_list
.
append
(
hash3
)
return
hash_list
def
_get_file_type
(
self
,
file_path
):
'''
Guess a file type based upon a file extension (mimetypes module)
'''
file_type
,
encoding
=
mimetypes
.
guess_type
(
file_path
)
magic_ext
=
None
if
file_type
is
None
:
magic_ext
=
common
.
FileExt
.
Text
else
:
main_type
,
sub_type
=
file_type
.
split
(
'/'
)
if
sub_type
.
startswith
(
'x-c'
):
magic_ext
=
common
.
FileExt
.
C
elif
sub_type
==
'x-java'
:
magic_ext
=
common
.
FileExt
.
Java
elif
sub_type
==
'x-sh'
:
magic_ext
=
common
.
FileExt
.
ShellScript
elif
sub_type
==
'x-perl'
:
magic_ext
=
common
.
FileExt
.
Perl
elif
sub_type
==
'x-python'
:
magic_ext
=
common
.
FileExt
.
Python
elif
sub_type
==
'x-httpd-php'
:
magic_ext
=
common
.
FileExt
.
PHP
elif
sub_type
==
'x-ruby'
:
magic_ext
=
common
.
FileExt
.
Ruby
else
:
magic_ext
=
common
.
FileExt
.
Text
return
magic_ext
def
items
(
self
):
return
self
.
_patch_list
def
length
(
self
):
return
self
.
_npatch
Back
|
FazBrowse Home
|
New Git URL