code_analyzer/submissionFileReader.py

import sys
from math import trunc
import os
import tempfile
import glob
from ccleaner import CodeCleaner
from pycleaner import CodeCleaner as PyCleaner
sys.path.extend(['.', '..'])
import re
import subprocess
import numpy as np

USEFUL_REGEX = r"(//.*)|(/\*[\w\W\n\r]*?\*/)|(^\s*$)|(\{\s*\})|(^\s*\{\s*$)|(^\s*\}\s*$)"
FILE_REGEX = re.compile(r".*\.(py|c)$",re.IGNORECASE)
#VAR_NO_INIT = re.compile(r"(int|float|double|char|long|string)\s*\*?([a-zA-Z0-9_]+)\s*(,\s*[a-zA-Z0-9)]+\s*)*;")
#VAR_INIT = re.compile(r"(int|float|double|char|long|string)\s*\*?([a-zA-Z0-9_]+)[^=]*=\s*[^,](,\s*[a-zA-Z0-9)][^=]*=\s*[^,])*;")

def readSubmissionContent (path, exerciseID, submissionID):
    filePath = "%s%s/%s/submittedfiles/*.*"%(path, trunc(exerciseID), trunc(submissionID))
    files = glob.glob(filePath)
    files = [f for f in files if FILE_REGEX.match(f) != None]
    #assert len(files) > 0, "Evaluated code for exercise {}, submission {} doesn't have a single submitted .c file at {}".format(exerciseID, submissionID, filePath)
    if len(files) == 0:
        print("Evaluated code for exercise {}, submission {} doesn't have a single submitted .c/.py file at {}".format(exerciseID, submissionID, filePath))
        return ""
    # check type
    file = files[0]
    content = open(file, "r").read()
    try:
        if file.endswith("py") :
            #python
            return minifyPython(content)
        else:
            #c code
            return minifyC(content)
    except Exception as e:
        print(e)
        return ""

def minifyC (text):
    usefulText = CodeCleaner().cleanCode(text)
    #print(usefulText)
    out = ""
    with tempfile.NamedTemporaryFile() as fp:
        fp.write(usefulText.encode("utf-8"))
        fp.flush()
        process = subprocess.run("./cminify.sh {}".format(fp.name),shell=True, capture_output=True, text=True)
        out = process.stdout
        fp.close()
    return out

def minifyPython (text):
    usefulText = PyCleaner().cleanCode(text)
    return usefulText

def getSubmissionFile (path, exerciseID, submissionID):
    filePath = "%s%s/%s/submittedfiles/*.*"%(path, trunc(exerciseID), trunc(submissionID))
    files = glob.glob(filePath)
    files = [f for f in files if FILE_REGEX.match(f) != None]
    assert len(files) > 0, "Evaluated code for exercise {}, submission {} doesn't have a single submitted .c file at {}".format(exerciseID, submissionID, filePath)
    return files[0]

def getUsefulLines (path, exerciseID, submissionID):
    subFile = getSubmissionFile(path, exerciseID, submissionID)
    usefulLines = 0
    with open(subFile, "r") as fileHandler:
        content = fileHandler.read()
        fileHandler.close()
        usefulText = re.sub(USEFUL_REGEX, "", content, flags=re.MULTILINE)
        usefulText = os.linesep.join([s for s in usefulText.splitlines() if s])
        usefulLines = usefulText.count("\n")
    return usefulLines

def levenshteinDistance (seq1, seq2):
    size_x = len(seq1) + 1
    size_y = len(seq2) + 1
    matrix = np.zeros ((size_x, size_y))
    for x in range(size_x):
        matrix [x, 0] = x
    for y in range(size_y):
        matrix [0, y] = y

    for x in range(1, size_x):
        for y in range(1, size_y):
            if seq1[x-1] == seq2[y-1]:
                matrix [x,y] = min(
                    matrix[x-1, y] + 1,
                    matrix[x-1, y-1],
                    matrix[x, y-1] + 1
                )
            else:
                matrix [x,y] = min(
                    matrix[x-1,y] + 1,
                    matrix[x-1,y-1] + 1,
                    matrix[x,y-1] + 1
                )
    return (matrix[size_x - 1, size_y - 1])