I am trying to extract the data from input file and store it for plotting. I have tested this code for a few files of same format. I am not sure if the code works correctly with the little change in input file (like more blank spaces in between). I might have also done some terrible mistakes which i cannot findout while testing. Basically i need this code to be bug free.

Is there any better way of doing this task, improvements and better ways of parsing the file.

Thanks in advance.

code:

I am trying to extract the data from input file and store it for plotting. I have tested this code for a few files of same format. I am not sure if the code works correctly with the little change in input file (like more blank spaces in between). I might have also done some terrible mistakes which I cannot find out while testing. Basically I need this code to be bug free.

Is there any better way of doing this task, improvements and better ways of parsing the file?

Code:

    def parseFile(input, output, mode):
        infile  = open(input)
        outfile = open(output, mode)
    
        for line in infile:
            if re.match("random seed", line):
                tokens      = re.search(r'random seed = (.*)', line, re.M|re.I)
                seed        = tokens.group(1)
                #print seed
    
            if re.match("input", line):
                tokens      = re.search(r'(.*)n = (.*), m = (.*), k = (.*) \[(.*) ms\] {peak:(.*)GiB} {curr:(.*)GiB}', line, re.M|re.L)
                n           = tokens.group(2).strip()
                m           = tokens.group(3).strip()
                k           = tokens.group(4).strip()
                t           = tokens.group(5).strip()
                inPeak      = tokens.group(6).strip()
                inCurr      = tokens.group(7).strip()
                #print n, m, k, t, peak, curr
    
            if re.match("root build", line):
                tokens      = re.search(r'root build (.*)\[zero: (.*)ms\] \[pos: (.*)ms\] \[adj: (.*)ms\] \[adjsort: (.*)ms\] \[shade: (.*)ms\] done. \[(.*)ms\] {peak:(.*)GiB} {curr:(.*)GiB}', line, re.M|re.L)
                zero        = tokens.group(2).strip()
                pos         = tokens.group(3).strip()
                adj         = tokens.group(4).strip()
                adjSort     = tokens.group(5).strip()
                shade       = tokens.group(6).strip()
                rTotalTime  = tokens.group(7).strip()
                rPeak       = tokens.group(8).strip()
                rCurr       = tokens.group(9).strip()
                #print zero, pos, adj, adjSort, shade, rTotalTime, rPeak, rCurr
    
            if re.match("oracle:", line):
                tokens  = re.search(r'oracle: (.*) (.*)ms \[ (.*)GiB (.*)GiB/s (.*)GHz (.*)GHz\] (.) -- (.*)', line, re.M|re.L);
                sum         = tokens.group(1).strip()
                oracleTime  = tokens.group(2).strip()
                inSize      = tokens.group(3).strip()
                transRate   = tokens.group(4).strip()
                mulRate     = tokens.group(5).strip()
                instrRate   = tokens.group(6).strip()
                yes         = tokens.group(7).strip()
                kpath       = tokens.group(8).strip()
                #print sum, time, inSize, transRate, mulRate, instrRate, yes, kpath

        if re.match("command done", line):
            tokens      = re.search(r'command done \[(.*)ms\]', line, re.M|re.L)
            cmdTime     = tokens.group(1).strip()
            #print cmdTime

        if re.match("grand total", line, re.M|re.L):
            tokens      = re.search(r'grand total \[(.*)ms\] {peak: (.*)GiB}(.*)', line, re.M|re.L)
            totalTime   = tokens.group(1).strip()
            gPeak       = tokens.group(2).strip()
            #print totalTime

        if re.match("host", line):
            tokens      = re.search(r'host: (.*)', line, re.M|re.L)
            host        = tokens.group(1).strip()
            #print host
        if re.match("build:", line):
            tokens      = re.search(r'build: (.*) with(.*)', line, re.M|re.L)
            build       = tokens.group(1).strip()
            #print build

    outfile.write("%s %s %s "% (host, yes, kpath))
    outfile.write(" %6d %8d %2d %10d %8.2lf %8.2lf %8.2lf"%
                    (int(n), int(m), int(k), int(seed), float(t), float(inPeak),
                    float(inCurr)))
    outfile.write(" %8.2lf %8.2lf %8.2lf %8.2lf %8.2lf %8.2lf %8.2lf %8.2lf"%
                    (float(zero), float(pos), float(adj), float(adjSort),
                    float(shade), float(rTotalTime), float(rPeak), float(rCurr)))
    outfile.write(" %s %10.2f %6.3lf %7.2lf %7.2lf %7.2lf"%
                    (sum, float(oracleTime), float(inSize), float(transRate),
                    float(mulRate), float(instrRate)))
    outfile.write(" %8.2lf %8.2lf %8.2lf"%
                    (float(cmdTime), float(totalTime), float(gPeak)))
    outfile.write(" %s\n"% (build))

    #close files
    outfile.close()
    infile.close()
#end of parseFile

def parseFile(input, output, mode):
    infile  = open(input)
    outfile = open(output, mode)

    for line in infile:
        if re.match("random seed", line):
            tokens      = re.search(r'random seed = (.*)', line, re.M|re.I)
            seed        = tokens.group(1)
            #print seed

        if re.match("input", line):
            tokens      = re.search(r'(.*)n = (.*), m = (.*), k = (.*) \[(.*) ms\] {peak:(.*)GiB} {curr:(.*)GiB}', line, re.M|re.L)
            n           = tokens.group(2).strip()
            m           = tokens.group(3).strip()
            k           = tokens.group(4).strip()
            t           = tokens.group(5).strip()
            inPeak      = tokens.group(6).strip()
            inCurr      = tokens.group(7).strip()
            #print n, m, k, t, peak, curr

        if re.match("root build", line):
            tokens      = re.search(r'root build (.*)\[zero:(.*)ms\] \[pos:(.*)ms\] \[adj:(.*)ms\] \[adjsort:(.*)ms\] \[shade:(.*)ms\] done. \[(.*)ms\] {peak:(.*)GiB} {curr:(.*)GiB}', line, re.M|re.L)
            zero        = tokens.group(2).strip()
            pos         = tokens.group(3).strip()
            adj         = tokens.group(4).strip()
            adjSort     = tokens.group(5).strip()
            shade       = tokens.group(6).strip()
            rTotalTime  = tokens.group(7).strip()
            rPeak       = tokens.group(8).strip()
            rCurr       = tokens.group(9).strip()
            #print zero, pos, adj, adjSort, shade, rTotalTime, rPeak, rCurr

        if re.match("oracle:", line):
            tokens  = re.search(r'oracle: (.*) (.*)ms \[ (.*)GiB (.*)GiB/s (.*)GHz (.*)GHz\] (.) -- (.*)', line, re.M|re.L);
            sum         = tokens.group(1).strip()
            oracleTime  = tokens.group(2).strip()
            inSize      = tokens.group(3).strip()
            transRate   = tokens.group(4).strip()
            mulRate     = tokens.group(5).strip()
            instrRate   = tokens.group(6).strip()
            yes         = tokens.group(7).strip()
            kpath       = tokens.group(8).strip()
            #print sum, time, inSize, transRate, mulRate, instrRate, yes, kpath

        if re.match("command done", line):
            tokens      = re.search(r'command done \[(.*)ms\]', line, re.M|re.L)
            cmdTime     = tokens.group(1).strip()
            #print cmdTime

        if re.match("grand total", line, re.M|re.L):
            tokens      = re.search(r'grand total \[(.*)ms\] {peak:(.*)GiB}(.*)', line, re.M|re.L)
            totalTime   = tokens.group(1).strip()
            gPeak       = tokens.group(2).strip()
            #print totalTime

        if re.match("host", line):
            tokens      = re.search(r'host:(.*)', line, re.M|re.L)
            host        = tokens.group(1).strip()
            #print host
        if re.match("build:", line):
            tokens      = re.search(r'build:(.*) with(.*)', line, re.M|re.L)
            build       = tokens.group(1).strip()
            #print build

    outfile.write("%s %s %s "% (host, yes, kpath))
    outfile.write(" %6d %8d %2d %10d %8.2lf %8.2lf %8.2lf"%
                    (int(n), int(m), int(k), int(seed), float(t), float(inPeak),
                    float(inCurr)))
    outfile.write(" %8.2lf %8.2lf %8.2lf %8.2lf %8.2lf %8.2lf %8.2lf %8.2lf"%
                    (float(zero), float(pos), float(adj), float(adjSort),
                    float(shade), float(rTotalTime), float(rPeak), float(rCurr)))
    outfile.write(" %s %10.2f %6.3lf %7.2lf %7.2lf %7.2lf"%
                    (sum, float(oracleTime), float(inSize), float(transRate),
                    float(mulRate), float(instrRate)))
    outfile.write(" %8.2lf %8.2lf %8.2lf"%
                    (float(cmdTime), float(totalTime), float(gPeak)))
    outfile.write(" %s\n"% (build))

    #close files
    outfile.close()
    infile.close()
#end of parseFile