Skip to content

fixes parsing section and region statements #9

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
ivg merged 1 commit into from
Jun 4, 2018
Merged

fixes parsing section and region statements #9

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
29 changes: 19 additions & 10 deletions src/bap/noeval_parser.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,23 +2,32 @@
'''
Parser for ADT string from bap that does not use eval

The nieve eval-based version runs into out-of-memory conditions on large files
The naive eval-based version runs into out-of-memory conditions on large files
'''
import gc
import sys
import time

# NOTE: uses bap.bir, but cannot import at module level (circular references)
from subprocess import check_output

# bap.1.3 breaks the format of the following types. it prints hexes
# without prefixing them with the `0x` escape. To fix it without
# fixing bap, we will treat integers inside this parents as
# hexadecimals if there is no prefix.
BROKEN_TYPES = [
'Section',
'Region'
]

# NOTE: uses bap.bir, but cannot import at module level (circular references)

def toint(string, start, end):
def toint(string, start, end, base=10):
'''
Convert substring string[start:end] to integer/long without eval

Note: may contain leading whitespace
'''
istr = string[start:end].lstrip()

if sys.version_info > (3,): # then longs don't exist
if istr.endswith('L'):
istr = istr.rstrip('L')
Expand All @@ -31,7 +40,7 @@ def toint(string, start, end):
if istr.startswith('0x'):
return of_str(istr, 16)
else:
return of_str(istr)
return of_str(istr, base)

def setup_progress(totalitems):
'''
Expand Down Expand Up @@ -159,17 +168,19 @@ def _parse_end(in_c, in_s, i, objs, stk):
raise ParserInputError('Mismatched input stream')
j = stk[-1]
parent = objs[j]
ptyp = parent['typ']
assert isinstance(parent, dict)
assert parent, 'parent is empty'
assert parent['typ'] != 'int', 'parent wrong type: %r' % (parent['typ'])
assert ptyp != 'int', 'parent wrong type: %r' % (parent['typ'])
assert 'children' in parent
if top: # add to parent if non empty
# make real int before appending
if top['typ'] == 'd': # int
try:
top = toint(in_s, k, i)
base = 16 if ptyp in BROKEN_TYPES else 10
top = toint(in_s, k, i, base)
except ValueError:
raise ParserInputError("Integer expected between [%d..%d)" % (top, i))
raise ParserInputError("Integer expected between [%d..%d)" % (k, i))
parent['children'].append(top)
if in_c == ',': # add blank object and move on
# next obj
Expand All @@ -179,7 +190,6 @@ def _parse_end(in_c, in_s, i, objs, stk):
return i
else: # we are ending a tuple/list/app do it
# maybe handle apply (num and seq are earlier)
ptyp = parent['typ']
if ptyp == '[':
if in_c != ']':
raise ParserInputError('close %r and open %r mismatch' % (in_c, ptyp))
Expand Down Expand Up @@ -325,4 +335,3 @@ def parser(input_str, disable_gc=False, logger=None):
'format': 'adt',
'load': parser
}