import os
import pandas as pd
import random
#%%

Opr=['++', '--', '+', '-', '*', '/', '%','&&', '||', '!','==', '!=', '<', '>', '<=', '>=', '=', '(', ')', '{', '}']
ProjectNames=['EclipseJDTCore', 'Equinox-3.4', 'lucene-2.4', 'Mylyn-3.1', 'PDE_UI 3.4.1']
# ProjectNames=['EclipseJDTCore']

for p in ProjectNames:
    ProjectFolder="//Volumes//DriveB//DrBilal//Zips//"+p
    df = pd.DataFrame(columns =['Class']+Opr+['TotalAOpr','DistinctAOpr', 'TotalROpr', 'DistinctROpr', 'TotalLOpr', 'DistinctLOpr', 'TotalOthers', 'DistinctOthers', 'TotalOpr', 'DistinctOpr'])

    ListOfAllFiles=[]
    for path, subdirs, files in os.walk(ProjectFolder):
        for name in files:
            if ".java" in name:
                ListOfAllFiles.append(os.path.join(path, name))    
    for javafile in ListOfAllFiles:
        Row = []
        try:
            print(javafile)
            f = open(javafile, "r")
            fileContent = f.read()
            Row.append(javafile)
            for A in Opr:
                count = fileContent.count(A)
                Row.append(count)
                fileContent = fileContent.replace(A, "")
            Row.append(sum(Row[1:8])) #totalAOpr
            
            Row.append(sum([1 if i else 0 for i in Row[1:8]])) #totalAOpr
            
            Row.append(sum(Row[8:11])) #total LOpr
            Row.append(sum([1 if i else 0 for i in Row[8:11]])) #totalAOpr

            Row.append(sum(Row[11:17])) #total ROpr
            Row.append(sum([1 if i else 0 for i in Row[11:17]])) #totalAOpr
            
            Row.append(sum(Row[17:22])) #total others
            Row.append(sum([1 if i else 0 for i in Row[17:22]])) #totalothers
            
            
            Row.append(sum(Row[1:22])) #total all opr
            Row.append(sum([1 if i else 0 for i in Row[1:22]])) #distinct  opr            


            df.loc[len(df)] = Row
            f.close()
        except:
            continue;
    df.to_csv("//Volumes//DriveB//DrBilal//"+p+".csv", index=False)
#%%

ProjectNames=['EclipseJDTCore', 'Equinox-3.4', 'lucene-2.4', 'Mylyn-3.1', 'PDE_UI 3.4.1']
for p in ProjectNames:
    df = pd.read_csv("//Volumes//DriveB//DrBilal//"+p+".csv")
    randomlist = []

    for i in range(0,len(df)):
        n = random.randint(1,50)
        if(n>30):
            n=0
        randomlist.append(n)
    df['NoOfFaults'] = randomlist
    df.to_csv("//Volumes//DriveB//DrBilal//"+p+".csv", index=False)
#%%
ProjectNames=['EclipseJDTCore', 'Equinox-3.4', 'lucene-2.4', 'Mylyn-3.1', 'PDE_UI 3.4.1']
for p in ProjectNames:
    df = pd.read_csv("//Volumes//DriveB//DrBilal//"+p+".csv")
    df.describe().to_csv("//Volumes//DriveB//DrBilal//Statistics_"+p+".csv")    
#%%