class rule_seq_match(redact_rule):
"""Redacts any sequence that matches the given pattern"""
def __init__(self, line, lgpattern):
redact_rule.__init__(self, line)
logging.debug("Creating lightgrep-based rule for pattern: "+lgpattern)
self.lg = Lightgrep()
self.accum = HitAccumulator()
self.lgpattern = lgpattern
self.complete = False
pats = [(lgpattern, ['US-ASCII', 'UTF-8', 'UTF-16LE', 'ISO-8859-1'],
KeyOpts(fixedString=False, caseInsensitive=True))]
prog, pmap = Lightgrep.createProgram(pats)
self.lg.createContext(prog, pmap, self.accum.lgCallback)
def should_redact(self, fileobject):
hitcount = self.lg.searchBuffer(fileobject.contents(), self.accum)
return hitcount > 0
def runs_to_redact(self, fi):
"""Overridden to return the byte runs of just the given text"""
red_seqs = []
for h in self.accum.Hits:
new = True
for seq in red_seqs:
if seq[0] == h['start'] and seq[1] == h['end']:
new = False
break
if new:
red_seqs.append((h['start'], h['end']))
self.lg.reset()
self.accum.reset()
return get_runs_for_file_sequences(fi, red_seqs)
def __init__(self, line, lgpattern):
redact_rule.__init__(self, line)
logging.debug("Creating lightgrep-based rule for pattern: "+lgpattern)
self.lg = Lightgrep()
self.accum = HitAccumulator()
self.lgpattern = lgpattern
self.complete = False
pats = [(lgpattern, ['US-ASCII', 'UTF-8', 'UTF-16LE', 'ISO-8859-1'],
KeyOpts(fixedString=False, caseInsensitive=True))]
prog, pmap = Lightgrep.createProgram(pats)
self.lg.createContext(prog, pmap, self.accum.lgCallback)
def __init__(self, line, text):
redact_rule.__init__(self, line)
logging.debug("Creating lightgrep-based rule for fixed string: "+text)
self.lg = Lightgrep()
self.accum = HitAccumulator()
self.complete = False
# Note reliance on fixedString keyopt below
pats = [(text, ['US-ASCII', 'UTF-8', 'UTF-16LE', 'ISO-8859-1'],
KeyOpts(fixedString=True, caseInsensitive=False))]
prog, pmap = Lightgrep.createProgram(pats)
self.lg.createContext(prog, pmap, self.accum.lgCallback)
