def testCodeExtractFileNotExistFailure(self):
bugData = self.getIncorrectBugDataFileNotExist()
with self.assertRaises(FileNotFoundError):
extractor = CodeExtractor(bugData)
extractor.loadCodeFromFile()
extractor.extractBugCode()
extractedCode = extractor.getBugCodeFragment()
def testCodeFixExtractSuccessAllChanges(self):
bugData = self.getCorrectBugDataFileMiddle()
expectedFixedCode = """int main(void)
{
int a, b;
b = 2;
a = 3;
a = 0;
if (a != 0)
{
"""
fileDiff = self.getFileDiff(bugData.getStartLine() - 1, [],
[' int a;'])
fileDiff += "\n" + self.getFileDiff(
bugData.getStartLine(), [' int a, b;', ' b = 2;'], [])
fileDiff += "\n" + self.getFileDiff(bugData.getStartLine() + 2,
[' if (a != 0)'],
[' if (a == 0)'])
extractor = CodeExtractor(bugData)
extractor.loadCodeFromFile()
extractor.extractBugCode()
extractor.loadDiff(fileDiff)
extractor.extractFixCode()
fixedCode = extractor.getFixCodeFragment()
usedDiffs = extractor.getUsedDiffs()
self.assertEqual(expectedFixedCode, fixedCode)
self.assertEqual(3, len(usedDiffs))
self.assertEqual('7d7', usedDiffs[0])
self.assertEqual('7a7', usedDiffs[1])
self.assertEqual('10c10', usedDiffs[2])
def testCodeExtractLineBoundariesSwapFailure(self):
bugData = self.getIncorrectBugDataLineBoundariesSwap()
with self.assertRaises(ValueError):
extractor = CodeExtractor(bugData)
extractor.loadCodeFromFile()
extractor.extractBugCode()
extractedCode = extractor.getBugCodeFragment()
def testExtractCodeWithEmptyDiffBetweenTwoCommits(self):
gp = gitprovider.GitProvider(config.getRepoDir())
commits = gp.getAllVersions('trainDbScriptTest')
commit1 = commits[-2]
commit2 = commits[-2]
file1 = gp.getFileContents('bugcode2.cpp', commit1)
file2 = gp.getFileContents('bugcode2.cpp', commit2)
diff = LinuxDiffer().diff(file1, file2)
usedDiffs = []
bugData = self.getBugData()
extractor = CodeExtractor(bugData)
extractor.loadCodeFromText(file1, '\r\n', '\n')
extractor.extractBugCode()
extractor.loadDiff(diff)
with self.assertRaises(ValueError):
extractor.extractFixCode()
bugCode = extractor.getBugCodeFragment()
fixCode = extractor.getFixCodeFragment()
usedDiffs = extractor.getUsedDiffs()
expectedOutputFix = ''
expectedOutputBug = """int main(void)
{
int a;
a = 3;
a = 0;
if (a == 0)
{
"""
self.assertEqual(expectedOutputBug, bugCode)
self.assertEqual(expectedOutputFix, fixCode)
self.assertEqual(0, len(usedDiffs))
def testCodeExtractSuccess(self):
bugData = self.getCorrectBugDataFileMiddle()
extractor = CodeExtractor(bugData)
extractor.loadCodeFromFile()
extractor.extractBugCode()
extractedCode = extractor.getBugCodeFragment()
correctCode = self.getBugCodeFileMiddle()
self.assertEqual(extractedCode, correctCode)
def testCodeExtractFileEndSuccess(self):
bugData = self.getCorrectBugDataFileEnd()
extractor = CodeExtractor(bugData)
extractor.loadCodeFromFile()
extractor.extractBugCode()
extractedCode = extractor.getBugCodeFragment()
correctCode = """ cout << b << endl;
}
return 0;
}"""
self.assertEqual(extractedCode, correctCode)
def testCodeExtractFileBeginSuccess(self):
bugData = self.getCorrectBugDataFileBegin()
extractor = CodeExtractor(bugData)
extractor.loadCodeFromFile()
extractor.extractBugCode()
extractedCode = extractor.getBugCodeFragment()
correctCode = """#include <iostream>
using namespace std;
"""
self.assertEqual(extractedCode, correctCode)
def testCodeExtractMultiLineSuccess(self):
bugData = self.getCorrectBugDataFileMultiLine()
extractor = CodeExtractor(bugData)
extractor.loadCodeFromFile()
extractor.extractBugCode()
extractedCode = extractor.getBugCodeFragment()
correctCode = """
int main(void)
{
int a;
a = 3;
a = 0;
if (a == 0)
{
int b = 1 / a;
"""
self.assertEqual(extractedCode, correctCode)
def testCodeFixExtractFailureNoDiff(self):
bugData = self.getCorrectBugDataFileMiddle()
bugCode = self.getBugCodeFileMiddle()
expectedFixedCode = ''
fileDiff = self.getFileDiff(bugData.getEndLine() + 20, [],
[' a = 3;'])
extractor = CodeExtractor(bugData)
extractor.loadCodeFromFile()
extractor.extractBugCode()
extractor.loadDiff(fileDiff)
with self.assertRaises(ValueError):
extractor.extractFixCode()
fixedCode = extractor.getFixCodeFragment()
usedDiffs = extractor.getUsedDiffs()
self.assertEqual(expectedFixedCode, fixedCode)
self.assertEqual(0, len(usedDiffs))
def testCodeFixExtractSuccessRemove(self):
bugData = self.getCorrectBugDataFileMiddle()
expectedFixedCode = """int main(void)
{
int a;
a = 0;
if (a == 0)
{
"""
fileDiff = self.getFileDiff(bugData.getStartLine(), [], [' a = 3;'])
extractor = CodeExtractor(bugData)
extractor.loadCodeFromFile()
extractor.extractBugCode()
extractor.loadDiff(fileDiff)
extractor.extractFixCode()
fixedCode = extractor.getFixCodeFragment()
usedDiffs = extractor.getUsedDiffs()
self.assertEqual(expectedFixedCode, fixedCode)
self.assertEqual(1, len(usedDiffs))
self.assertEqual('8d8', usedDiffs[0])
def testExtractCodeWithDiffBetweenTwoCommitsMultiDiffInFragment(self):
gp = gitprovider.GitProvider(config.getRepoDir())
commits = gp.getAllVersions('trainDbScriptTest')
commit1 = commits[-6]
commit2 = commits[-7]
file1 = gp.getFileContents('bugcode3.cpp', commit1)
file2 = gp.getFileContents('bugcode3.cpp', commit2)
diff = LinuxDiffer().diff(file1, file2)
usedDiffs = []
bugData = self.getBugData3()
extractor = CodeExtractor(bugData)
extractor.loadCodeFromText(file1, '\r\n', '\n')
extractor.extractBugCode()
extractor.loadDiff(diff)
extractor.extractFixCode()
bugCode = extractor.getBugCodeFragment()
fixCode = extractor.getFixCodeFragment()
usedDiffs = extractor.getUsedDiffs()
expectedOutputFix = """{;
int a;
a = 0;
a = 2;
if (a != 0)
{;
int b = 1 / a;
"""
expectedOutputBug = """{
int a;
a = 0;
a = 2;
if (a != 0)
{
int b = 1 / a;
"""
self.assertEqual(expectedOutputBug, bugCode)
self.assertEqual(expectedOutputFix, fixCode)
self.assertEqual(2, len(usedDiffs))
def predict(self, id, checker):
# Load all bugs
print("Loading bug data...")
ids = []
if id == -1:
bugs = self.ccdb.getAllBugsForChecker(checker)
ids = [x[0] for x in bugs]
else:
ids.append(id)
# Loading model
print("Loading model...")
model = load_model(config.cfModelFilenameFormat.format(checker))
model.summary()
vLabels = ['NOT OK', 'OK', 'Skipped']
# Initialize coder
print("Initializing coder...")
self.dictionary = Dictionary(checker)
self.coder = Coder(self.dictionary)
self.totalDictionaryLength = self.dictionary.length()
# Predicting
print("Starting predictions...")
for i in ids:
allData = self.ccdb.getBugData(i)
if allData.getChecker(
) not in globals.availableCheckers or allData.getChecker(
) != checker:
print("Bug #{0} - checker not supported".format(i))
else:
# Load extra tokens from checker message
checkerInfo = self.checkers.extractTokensForChecker(
allData.getChecker(), allData.getMessage())
# Retrieve code fragment with bug
fileRelativePath = self.convertFilePathToRepoRelativePath(
allData.getFile())
fullCodeWithBug = self.vcs.getFileContents(
fileRelativePath, self.commits[self.currentCommitIndex])
extractor = CodeExtractor(allData)
extractor.loadCodeFromText(fullCodeWithBug)
extractor.extractBugCode()
bugCodeFragment = extractor.getBugCodeFragment()
fixCodeFragment = ''
# Encode it
encodedBugData, initialUnkList = self.coder.encode(
bugCodeFragment, checkerData=checkerInfo)
# Convert to one-hot
MODEL_X_MAX_LEN = model.get_layer(index=0).input_shape[1]
if len(encodedBugData) > MODEL_X_MAX_LEN:
print(
"Bug #{0} - Code too big for model, ignored".format(i))
continue
elif id == -1:
print("Bug #{0} - Good to go".format(i))
continue
noZerosToPad = MODEL_X_MAX_LEN - len(encodedBugData)
if noZerosToPad > 0:
encodedBugData = self.coder.applyPadding(
encodedBugData, noZerosToPad)
X = np.zeros((1, MODEL_X_MAX_LEN, self.totalDictionaryLength))
X[0] = self.coder.convertToOneHot(
encodedBugData,
np.zeros((MODEL_X_MAX_LEN, self.totalDictionaryLength)))
# Predict and convert from one-hot
Y = self.coder.convertFromOneHot(model.predict(X)[0])
print(Y)
# Decode
Y = self.coder.removePadding(Y)
fixCodeFragment = self.coder.decode(Y, initialUnkList)
#Verify?
vStatus = 2
if config.cfVerifyPrediction:
# Apply fix in source code file
extractor.applyFix(fixCodeFragment)
extractor.saveToFile(allData.getFile())
# Run CodeChecker and analyze code
self.codeChecker.check(True)
resolvedIds = self.getDiffResolvedIds()
# Check if ID is resolved in tmp folder
isFixed = i in resolvedIds
# Set vStatus accordingly
if isFixed:
vStatus = 1
else:
vStatus = 0
#Print
print("Bug #{0} - summary".format(i))
print("== Code fragment with bug ==")
print(bugCodeFragment)
print("== Suggested fix ==")
print(fixCodeFragment)
print("Verification: {0}".format(vLabels[vStatus]))
a = ' '
while a != 'y' and a != 'n':
a = input("Apply fix? (y/n): ")
if a == 'y':
if not config.cfVerifyPrediction:
# Apply fix in source code file
extractor.applyFix(fixCodeFragment)
extractor.saveToFile(allData.getFile())
elif config.cfVerifyPrediction:
# Revert file contents
self.vcs.checkout(self.commits[self.currentCommitIndex])
print('Done')
print("All done, exiting...")
def main(self):
# Do analysis
shutil.rmtree(config.getTmpDir())
self.codeChecker.check(True)
# Diff new
newBugs = self.getDiffNew()
if len(newBugs) < 1:
print('No new bugs introduced, commit is accepted!')
return
print("New bugs found! Count: {0}. Attempting repairs...".format(len(newBugs)))
# Load models
models = {}
for checker in globals.availableCheckers:
models[checker] = load_model(config.cfModelFilenameFormat.format(checker))
# Load all content from files having new
files = set([self.convertFilePathToRepoRelativePath(x.getFile()) for x in newBugs])
fileContents = {}
for f in files:
fn = config.getRepoDir() + f
with open(fn, 'r') as fh:
fileContents[f] = ''.join(fh.readlines())
# For each file sort by bug line desc
suggestions = []
validSuggestions = 0
for f in files:
bugs = [x for x in newBugs if self.convertFilePathToRepoRelativePath(x.getFile()) == f]
bugs.sort(key=lambda x: x.getLine(), reverse=True)
print("=== File: {0} ===".format(f))
# For each bug get a suggestion and test it
for b in bugs:
print("L{0}, Type: {1}".format(b.getLine(), b.getChecker()))
# Prepare useful data
dictionary = Dictionary(b.getChecker())
coder = Coder(dictionary)
totalDictionaryLength = dictionary.length()
# Prepare and extract bug fragment
checkerInfo = self.checkers.extractTokensForChecker(b.getChecker(), b.getMessage())
extractor = CodeExtractor(b)
extractor.loadCodeFromText(fileContents[f])
extractor.extractBugCode()
bugCodeFragment = extractor.getBugCodeFragment()
fixCodeFragment = ''
# Encode it
encodedBugData, initialUnkList = coder.encode(bugCodeFragment, checkerData = checkerInfo)
# Convert to one-hot
MODEL_X_MAX_LEN = models[b.getChecker()].get_layer(index = 0).input_shape[1]
if len(encodedBugData) > MODEL_X_MAX_LEN:
print("Ignored: Code too big for model")
continue
noZerosToPad = MODEL_X_MAX_LEN - len(encodedBugData)
if noZerosToPad > 0:
encodedBugData = coder.applyPadding(encodedBugData, noZerosToPad)
X = np.zeros((1, MODEL_X_MAX_LEN, totalDictionaryLength))
X[0] = coder.convertToOneHot(encodedBugData, np.zeros((MODEL_X_MAX_LEN, totalDictionaryLength)))
# Predict and convert from one-hot
Y = coder.convertFromOneHot(models[b.getChecker()].predict(X)[0])
Y = coder.removePadding(Y)
# Decode
fixCodeFragment = coder.decode(Y, initialUnkList)[:-1]
#Verify?
vStatus = 2
if config.cfVerifyPrediction:
# Apply fix in source code file
extractor.applyFix(fixCodeFragment)
extractor.saveToFile(b.getFile())
# Run CodeChecker and analyze code
shutil.rmtree(config.getTmpDir())
compilationLog = self.codeChecker.check(True)
newBugsAfterFix = self.getDiffNew()
# Check if ID is resolved in tmp folder
isFixed = 'Build failed' not in compilationLog
for nb in newBugsAfterFix:
if self.isBugDataEqual(b, nb):
isFixed = False
# Set vStatus accordingly
if isFixed:
vStatus = 1
else:
vStatus = 0
# Revert file
extractor.loadCodeFromText(fileContents[f])
extractor.saveToFile(b.getFile())
if vStatus == 0:
print("Verification: Negative, cannot be applied")
elif vStatus == 1:
print("Verification: Positive, can be applied")
validSuggestions += 1
elif vStatus == 2:
print("Verification: Skipped")
validSuggestions += 1
sugg = SuggestionData(f, b, bugCodeFragment, fixCodeFragment, vStatus)
suggestions.append(sugg)
print("Valid suggestions prepared for {0} / {1} bugs.".format(validSuggestions, len(newBugs)))
if validSuggestions > 0:
print("Apply valid suggestions (a), display them (d), ignore them (i) or abort commit (q)?")
apply = False
choice = True
while choice:
c = sys.stdin.read(1)
if c == 'a':
apply = True
choice = False
print("Applying fixes...")
elif c == 'i':
choice = False
print("Fixes ignored...")
elif c == 'd':
self.displaySuggestions(suggestions)
print("Apply valid suggestions (a), ignore them (i) or abort commit (q)?")
elif c == 'q':
print("Aborting commit...")
sys.exit(1)
if apply:
self.applyValidFixes(suggestions, files)
print("Fixes applied!")
if validSuggestions != len(newBugs):
print("Unable to fix all bugs, continue with commit (c) or abort (q)?")
choice = True
while choice:
c = sys.stdin.read(1)
if c == 'c':
choice = False
print("Continuing...")
elif c == 'q':
print("Aborting commit...")
sys.exit(1)
else:
print("Bugs corrected, commit is good to go!")
def applyFix(self, s):
extractor = CodeExtractor(s.bug)
extractor.loadCodeFromFile()
extractor.extractBugCode()
extractor.applyFix(s.fixCode)
extractor.saveToFile(s.bug.getFile())
def ProcessBugsInFile(fileName):
# 5.1.
# 5.2.
for bug in bugsPerFile[fileName]:
bugData = bugDataList[bug]
cleanFn = fileName[:-4]
fn = '../Results/Analysis/{0}_{1}_{2}.txt'.format(
cleanFn, bug, bugData.getChecker())
repoFn = os.fsdecode(
os.path.join(os.fsencode(config.getRepoDir()),
os.fsencode(fileName)))
if os.path.isfile(fn):
continue
model = None
if bugData.getChecker() == 'deadcode.DeadStores':
model = model1
coder = coder1
totalDictionaryLength = totalDictionaryLength1
if bugData.getChecker(
) == 'clang-diagnostic-tautological-constant-out-of-range-compare':
model = model2
coder = coder2
totalDictionaryLength = totalDictionaryLength2
if bugData.getChecker() == 'clang-diagnostic-unused-parameter':
model = model3
coder = coder3
totalDictionaryLength = totalDictionaryLength3
if bugData.getChecker() == 'clang-diagnostic-constant-conversion':
model = model4
coder = coder4
totalDictionaryLength = totalDictionaryLength4
MODEL_X_MAX_LEN = model.get_layer(index=0).input_shape[1]
# 5.2.1.
fullCodeWithBug = fileContents[fileName]
extractor = CodeExtractor(bugData)
extractor.loadCodeFromText(fullCodeWithBug)
extractor.extractBugCode()
bugCodeFragment = extractor.getBugCodeFragment()
# 5.2.2.
fullCodeWithoutBug = ''.join(fix(extractor.code, bugData))
diff = POSIXDiffer().diff(fullCodeWithBug, fullCodeWithoutBug)
extractor.loadDiff(diff)
try:
extractor.extractFixCode()
except ValueError as ve:
print(
"Unable to generate expected fix for bug #{0} ({1}), checker = {2}"
.format(bug, fileName, bugData.getChecker()))
continue
expectedFixCodeFragment = extractor.getFixCodeFragment()
# 5.2.3.
checkerInfo = checkers.extractTokensForChecker(bugData.getChecker(),
bugData.getMessage())
encodedBugData, initialUnkList = coder.encode(bugCodeFragment,
checkerData=checkerInfo)
noZerosToPad = MODEL_X_MAX_LEN - len(encodedBugData)
if noZerosToPad > 0:
encodedBugData = coder.applyPadding(encodedBugData, noZerosToPad)
X = np.zeros((1, MODEL_X_MAX_LEN, totalDictionaryLength))
X[0] = coder.convertToOneHot(
encodedBugData, np.zeros((MODEL_X_MAX_LEN, totalDictionaryLength)))
Y = coder.convertFromOneHot(model.predict(X)[0])
while (Y[-1] == 0):
Y.pop()
fixCodeFragment = coder.decode(Y, initialUnkList)
# 5.2.4.
isCompiling = False
f1 = os.fsdecode(
os.path.join(os.fsencode(config.getRepoDir()),
os.fsencode(cleanFn)))
f2 = os.fsdecode(
os.path.join(os.fsencode(config.getRepoDir()),
os.fsencode('{0}.o'.format(cleanFn))))
if os.path.isfile(f1):
os.remove(f1)
if os.path.isfile(f2):
os.remove(f2)
extractor.loadCodeFromText(fullCodeWithBug)
extractor.applyFix(fixCodeFragment)
with open(repoFn, 'wt') as f:
f.writelines(extractor.code)
log = codechecker.runCmd(
'CodeChecker check -e all -b "cd {0} && make {1}" -o /tmp/codefixer_{1}'
.format(config.getRepoDir(), cleanFn))
if os.path.isfile(f1):
isCompiling = True
# 5.2.5.
isFixed = False
ids = []
if isCompiling:
resolved = codechecker.diffResolved(
config.getCcRunName(), '/tmp/codefixer_{0}'.format(cleanFn),
ccdb)
for bugInfo in resolved:
ids.append(bugInfo['reportId'])
if bug in ids:
isFixed = True
# 5.2.6.
isExpected = False
if fixCodeFragment == expectedFixCodeFragment:
isExpected = True
# 5.2.7.
encodedExpFix, finalUnkList = coder.encode(expectedFixCodeFragment,
unkList=initialUnkList,
reverse=False)
noXTokens = len(encodedExpFix)
noYTokens = len(Y)
noAllTokens = max(noXTokens, noYTokens)
noCorrectTokens = 0
#print(encodedExpFix)
#print(Y)
for i in range(min(noXTokens, noYTokens)):
if encodedExpFix[i] == Y[i]:
noCorrectTokens += 1
# 5.2.8.
with open(fn, 'wt') as f:
f.write(
'#BUG#\n{0}\n#EXP#\n{1}\n#FIX#\n{2}\n#STATS#\n{3},{4},{5},{6},{7},{8},{9}\n{10}\n{11}'
.format(bugCodeFragment, expectedFixCodeFragment,
fixCodeFragment, isCompiling, isFixed, isExpected,
noXTokens, noYTokens, noAllTokens, noCorrectTokens,
log, ids))
# 5.2.9.
with open(repoFn, 'wt') as f:
f.write(fileContents[fileName])
# 5.2.10.
# Not used due to multithreading issues, will be done on file-by-file basis after closing pool
# 5.3.
return fileName