autograder.py

# autograder.py
# -------------
# Licensing Information: Please do not distribute or publish solutions to this
# project. You are free to use and extend these projects for educational
# purposes. The Pacman AI projects were developed at UC Berkeley, primarily by
# John DeNero (denero@cs.berkeley.edu) and Dan Klein (klein@cs.berkeley.edu).
# Student side autograding was added by Brad Miller, Nick Hay, and Pieter 
# Abbeel in Spring 2013.
# For more info, see http://inst.eecs.berkeley.edu/~cs188/pacman/pacman.html

# imports from python standard library
import grading
import imp
import optparse
import os
import re
import sys
import projectParams
import random
from util import FixedRandom
random.setstate(FixedRandom().random.getstate())

# register arguments and set default values
def readCommand(argv):
    parser = optparse.OptionParser(description = 'Run public tests on student code')
    parser.set_defaults(generateSolutions=False, edxOutput=False, muteOutput=False, printTestCase=False)
    parser.add_option('--test-directory',
                      dest = 'testRoot',
                      default = 'test_cases',
                      help = 'Root test directory which contains subdirectories corresponding to each question')
    parser.add_option('--student-code',
                      dest = 'studentCode',
                      default = projectParams.STUDENT_CODE_DEFAULT,
                      help = 'comma separated list of student code files')
    parser.add_option('--code-directory',
                    dest = 'codeRoot',
                    default = "",
                    help = 'Root directory containing the student and testClass code')
    parser.add_option('--test-case-code',
                      dest = 'testCaseCode',
                      default = projectParams.PROJECT_TEST_CLASSES,
                      help = 'class containing testClass classes for this project')
    parser.add_option('--generate-solutions',
                      dest = 'generateSolutions',
                      action = 'store_true',
                      help = 'Write solutions generated to .solution file')
    parser.add_option('--edx-output',
                    dest = 'edxOutput',
                    action = 'store_true',
                    help = 'Generate edX output files')
    parser.add_option('--mute',
                    dest = 'muteOutput',
                    action = 'store_true',
                    help = 'Mute output from executing tests')
    parser.add_option('--print-tests', '-p',
                    dest = 'printTestCase',
                    action = 'store_true',
                    help = 'Print each test case before running them.')
    parser.add_option('--test', '-t',
                      dest = 'runTest',
                      default = None,
                      help = 'Run one particular test.  Relative to test root.')
    parser.add_option('--question', '-q',
                    dest = 'gradeQuestion',
                    default = None,
                    help = 'Grade one particular question.')
    (options, args) = parser.parse_args(argv)
    return options


# confirm we should author solution files
def confirmGenerate():
    print('WARNING: this action will overwrite any solution files.')
    print('Are you sure you want to proceed? (yes/no)')
    while True:
        ans = sys.stdin.readline().strip()
        if ans == 'yes':
            break
        elif ans == 'no':
            sys.exit(0)
        else:
            print('please answer either "yes" or "no"')


# TODO: Fix this so that it tracebacks work correctly
# Looking at source of the traceback module, presuming it works
# the same as the intepreters, it uses co_filename.  This is,
# however, a readonly attribute.
def setModuleName(module, filename):
    functionType = type(confirmGenerate)
    classType = type(optparse.Option)

    for i in dir(module):
        o = getattr(module, i)
        if hasattr(o, '__file__'): continue
        
        if type(o) == functionType:
            setattr(o, '__file__', filename)
        elif type(o) == classType:
            setattr(o, '__file__', filename)
            # TODO: assign member __file__'s?
        #print i, type(o)            
    

#from cStringIO import StringIO

def loadModuleString(moduleSource):
    # Below broken, imp doesn't believe its being passed a file:
    #    ValueError: load_module arg#2 should be a file or None
    #
    #f = StringIO(moduleCodeDict[k])
    #tmp = imp.load_module(k, f, k, (".py", "r", imp.PY_SOURCE))
    tmp = imp.new_module(k)
    exec moduleCodeDict[k] in tmp.__dict__
    setModuleName(tmp, k)
    return tmp

import py_compile

def loadModuleFile(moduleName, filePath):
    with open(filePath, 'r') as f:
        return imp.load_module(moduleName, f, "%s.py" % moduleName, (".py", "r", imp.PY_SOURCE))

 
def readFile(path, root=""):
    "Read file from disk at specified path and return as string"
    with open(os.path.join(root, path), 'r') as handle:
        return handle.read()


#######################################################################
# Error Hint Map
#######################################################################

# TODO: use these
ERROR_HINT_MAP = {
  'q1': {
    "<type 'exceptions.IndexError'>": """
      We noticed that your project threw an IndexError on q1.
      While many things may cause this, it may have been from
      assuming a certain number of successors from a state space
      or assuming a certain number of actions available from a given
      state. Try making your code more general (no hardcoded indices)
      and submit again!
    """
  },
  'q3': {
      "<type 'exceptions.AttributeError'>": """
        We noticed that your project threw an AttributeError on q3.
        While many things may cause this, it may have been from assuming
        a certain size or structure to the state space. For example, if you have
        a line of code assuming that the state is (x, y) and we run your code
        on a state space with (x, y, z), this error could be thrown. Try
        making your code more general and submit again!

    """
  }
}

import pprint

def splitStrings(d):
    d2 = dict(d)
    for k in d:
        if k[0:2] == "__":
            del d2[k]
            continue
        if d2[k].find("\n") >= 0:
            d2[k] = d2[k].split("\n")
    return d2
            

def printTest(testDict, solutionDict):
    pp = pprint.PrettyPrinter(indent=4)
    print "Test case:"
    for line in testDict["__raw_lines__"]:
        print "   |", line 
    print "Solution:"
    for line in solutionDict["__raw_lines__"]:
        print "   |", line 
    

def runTest(testName, moduleDict, printTestCase=False):
    import testParser
    import testClasses
    for module in moduleDict:
        setattr(sys.modules[__name__], module, moduleDict[module])

    testDict = testParser.TestParser(testName + ".test").parse()
    solutionDict = testParser.TestParser(testName + ".solution").parse()
    testClass = getattr(projectTestClasses, testDict['class'])
    testCase = testClass(testDict)

    if printTestCase: 
        printTest(testDict, solutionDict)
    
    # This is a fragile hack to create a stub grades object
    grades = grading.Grades(projectParams.PROJECT_NAME, [(None,0)])
    testCase.execute(grades, moduleDict, solutionDict)
    

# evaluate student code
def evaluate(generateSolutions, testRoot, moduleDict, exceptionMap=ERROR_HINT_MAP, edxOutput=False, muteOutput=False, 
            printTestCase=False, questionToGrade=None):
    # imports of testbench code.  note that the testClasses import must follow
    # the import of student code due to dependencies
    import testParser
    import testClasses
    for module in moduleDict:
        setattr(sys.modules[__name__], module, moduleDict[module])
    
    problemDict = testParser.TestParser(os.path.join(testRoot, 'CONFIG')).parse()
    
    # iterate through and run tests
    if 'order' in problemDict:
      test_subdirs = problemDict['order'].split()
    else:
      test_subdirs = sorted(os.listdir(testRoot))
    questions = []
    questionDicts = {}
    for q in test_subdirs:
        subdir_path = os.path.join(testRoot, q)
        if not os.path.isdir(subdir_path) or q[0] == '.':
            continue
            
        if questionToGrade != None and q != questionToGrade:
            continue

        # create a question object
        questionDict = testParser.TestParser(os.path.join(subdir_path, 'CONFIG')).parse()
        questionClass = getattr(testClasses, questionDict['class'])
        question = questionClass(questionDict)
        questionDicts[q] = questionDict

        # load test cases into question
        tests = filter(lambda t: re.match('[^#~.].*\.test\Z', t), os.listdir(subdir_path))
        tests = map(lambda t: re.match('(.*)\.test\Z', t).group(1), tests)
        for t in sorted(tests):
            test_file = os.path.join(subdir_path, '%s.test' % t)
            solution_file = os.path.join(subdir_path, '%s.solution' % t)
            testDict = testParser.TestParser(test_file).parse()
            if testDict.get("disabled", "false").lower() == "true":
                continue
            testClass = getattr(projectTestClasses, testDict['class'])
            testCase = testClass(question, testDict)
            def makefun(testCase, solution_file):
                if generateSolutions:
                    # write solution file to disk
                    return lambda grades: testCase.writeSolution(moduleDict, solution_file)
                else:
                    # read in solution dictionary and pass as an argument
                    testDict = testParser.TestParser(test_file).parse()
                    solutionDict = testParser.TestParser(solution_file).parse()
                    if printTestCase:
                        return lambda grades: printTest(testDict, solutionDict) or testCase.execute(grades, moduleDict, solutionDict)
                    else:
                        return lambda grades: testCase.execute(grades, moduleDict, solutionDict)
            question.addTestCase(testCase, makefun(testCase, solution_file))

        # Note extra function is necessary for scoping reasons
        def makefun(question):
            return lambda grades: question.execute(grades)
        setattr(sys.modules[__name__], q, makefun(question))
        questions.append((q, question.getMaxPoints()))

    grades = grading.Grades(projectParams.PROJECT_NAME, questions, edxOutput=edxOutput, muteOutput=muteOutput)
    for q in questionDicts:
      for prereq in questionDicts[q].get('depends', '').split():
        grades.addPrereq(q, prereq)

    grades.grade(sys.modules[__name__])      
    return grades.points


if __name__ == '__main__':
    options = readCommand(sys.argv)
    if options.generateSolutions:
        confirmGenerate()
    codePaths = options.studentCode.split(',')
    # moduleCodeDict = {}
    # for cp in codePaths:
    #     moduleName = re.match('.*?([^/]*)\.py', cp).group(1)
    #     moduleCodeDict[moduleName] = readFile(cp, root=options.codeRoot)
    # moduleCodeDict['projectTestClasses'] = readFile(options.testCaseCode, root=options.codeRoot)
    # moduleDict = loadModuleDict(moduleCodeDict)
    
    moduleDict = {}
    for cp in codePaths:
        moduleName = re.match('.*?([^/]*)\.py', cp).group(1)
        moduleDict[moduleName] = loadModuleFile(moduleName, os.path.join(options.codeRoot, cp))
    moduleName = re.match('.*?([^/]*)\.py', options.testCaseCode).group(1)     
    moduleDict['projectTestClasses'] = loadModuleFile(moduleName, os.path.join(options.codeRoot, options.testCaseCode))    
    
    
    if options.runTest != None:
        runTest(options.runTest, moduleDict, printTestCase=options.printTestCase)
    else:
        evaluate(options.generateSolutions, options.testRoot, moduleDict, 
            edxOutput=options.edxOutput, muteOutput=options.muteOutput, printTestCase=options.printTestCase,
            questionToGrade=options.gradeQuestion)