def highlightAssignment(fingerprints, output):
"""Highlights fingerprints and outputs into a table entry"""
index = 0
output.write('<td>')
output.write('<p> Files by ' + fingerprints[0].auth + ':</p>\n')
#Defines html code to start and end highlighting.
startHighlight = '<SPAN style="BACKGROUND-COLOR: #ffff00">'
endHighlight = '</SPAN>'
#wWhile fingerpritns remain.
while index < len(fingerprints):
filename = fingerprints[index].loc
data = normalizeFileLines(filename).decode() #process the file.
output.write('<p>' + fingerprints[index].loc + ':</p>\n')
line = 0
col = 0
output.write('<pre>\n')
#Go through data one letter at a time.
for letter in data:
#If its the start of a fingerprint commence highlighting.
if (index < len(fingerprints) and line == fingerprints[index].sline
and col == fingerprints[index].scol
and filename == fingerprints[index].loc):
output.write(startHighlight)
#If its the end of highlighing for a fingerprint.
if (index < len(fingerprints) and line == fingerprints[index].eline
and col == fingerprints[index].ecol
and filename == fingerprints[index].loc):
index += 1 #Increment the index.
#If the fingerprints overlap, don't end highlighting
if (index < len(fingerprints) and overlap(
fingerprints[index - 1], fingerprints[index])):
pass
else:
output.write(endHighlight)
if (index < len(fingerprints) and
(fingerprints[index].sline - line < 5 or
(index > 0 and line - fingerprints[index - 1].eline < 5))):
if letter == '<':
output.write("<")
elif letter == '<':
output.write(">")
elif letter == '&':
output.write("&")
elif letter == '\"':
output.write(""")
else:
output.write(letter)
col += 1
#If its now a new line, adjust counters accordingly.
if letter == '\n':
line += 1
col = 0
output.write('</pre>')
output.write('</td>')
def scrutinize(filelist, options):
fingerprints = collections.defaultdict(list)
documents = collections.defaultdict(list)
for filename in filelist:
data = normalizeFileLines(filename)
#print(filename, file=sys.stderr)
for fprint in winnowing(kgrams(tokenize(options.language, data,
options.comments,
options.endlines,
options.whitespace,
options.text),
int(options.size)),
int(options.window)):
documents[filename].append(fprint)
fingerprints[fprint.hash].append(filename)
for document, fprints in documents.items():
matches = collections.defaultdict(int)
for fprint in fprints:
for matching in fingerprints[fprint.hash]:
matches[matching] += 1
tmp = []
for key, val in sorted(matches.items()):
if val > len(fprints) * 0.1 and key != document:
tmp.append((key, val))
if tmp:
print(document, ":", len(fprints))
for key, val in tmp:
print(' ', key, val)
def scrutinize(filelist, options):
fingerprints = collections.defaultdict(list)
documents = collections.defaultdict(list)
for filename in filelist:
data = normalizeFileLines(filename)
#print(filename, file=sys.stderr)
for fprint in winnowing(
kgrams(
tokenize(options.language, data, options.comments,
options.endlines, options.whitespace,
options.text), int(options.size)),
int(options.window)):
documents[filename].append(fprint)
fingerprints[fprint.hash].append(filename)
for document, fprints in documents.items():
matches = collections.defaultdict(int)
for fprint in fprints:
for matching in fingerprints[fprint.hash]:
matches[matching] += 1
tmp = []
for key, val in sorted(matches.items()):
if val > len(fprints) * 0.1 and key != document:
tmp.append((key, val))
if tmp:
print(document, ":", len(fprints))
for key, val in tmp:
print(' ', key, val)
def examine(filename, options):
fingerprints = list()
data = normalizeFileLines(filename)
for fprint in winnowing(
kgrams(
tokenize(options.language, data, options.comments,
options.endlines, options.whitespace, options.text),
int(options.size)), int(options.window)):
# Add all the fingerprints to a list and return it.
fingerprints.append(fprint)
return fingerprints
def examine(filename, options):
fingerprints = list()
data = normalizeFileLines(filename)
for fprint in winnowing(kgrams(tokenize(options.language, data,
options.comments,
options.endlines,
options.whitespace,
options.text),
int(options.size)),
int(options.window)):
# Add all the fingerprints to a list and return it.
fingerprints.append( fprint)
return fingerprints
def highlightAssignment(fingerprints, output):
"""Highlights fingerprints and outputs into a table entry"""
index = 0
output.write("<td>")
output.write("<p> Files by " + fingerprints[0].auth + ":</p>\n")
# Defines html code to start and end highlighting.
startHighlight = '<SPAN style="BACKGROUND-COLOR: #ffff00">'
endHighlight = "</SPAN>"
# wWhile fingerpritns remain.
while index < len(fingerprints):
filename = fingerprints[index].loc
data = normalizeFileLines(filename).decode() # process the file.
output.write("<p>" + fingerprints[index].loc + ":</p>\n")
line = 0
col = 0
output.write("<pre>\n")
# Go through data one letter at a time.
for letter in data:
# If its the start of a fingerprint commence highlighting.
if (
index < len(fingerprints)
and line == fingerprints[index].sline
and col == fingerprints[index].scol
and filename == fingerprints[index].loc
):
output.write(startHighlight)
# If its the end of highlighing for a fingerprint.
if (
index < len(fingerprints)
and line == fingerprints[index].eline
and col == fingerprints[index].ecol
and filename == fingerprints[index].loc
):
index += 1 # Increment the index.
# If the fingerprints overlap, don't end highlighting
if index < len(fingerprints) and overlap(fingerprints[index - 1], fingerprints[index]):
pass
else:
output.write(endHighlight)
if index < len(fingerprints) and (
fingerprints[index].sline - line < 5 or (index > 0 and line - fingerprints[index - 1].eline < 5)
):
if letter == "<":
output.write("<")
elif letter == "<":
output.write(">")
elif letter == "&":
output.write("&")
elif letter == '"':
output.write(""")
else:
output.write(letter)
col += 1
# If its now a new line, adjust counters accordingly.
if letter == "\n":
line += 1
col = 0
output.write("</pre>")
output.write("</td>")