Merge pull request #9 from aojea/CLF

Added Common Log Format output

Author: Kirit Basu

apache-fake-log-gen.py

@@ -40,6 +40,7 @@ def match(self, *args):
 
 parser = argparse.ArgumentParser(__file__, description="Fake Apache Log Generator")
 parser.add_argument("--output", "-o", dest='output_type', help="Write to a Log file, a gzip file or to STDOUT", choices=['LOG','GZ','CONSOLE'] )
+parser.add_argument("--log-format", "-l", dest='log_format', help="Log format, Common or Extended Log Format ", choices=['CLF','ELF'], default="ELF" )
 parser.add_argument("--num", "-n", dest='num_lines', help="Number of lines to generate (0 for infinite)", type=int, default=1)
 parser.add_argument("--prefix", "-p", dest='file_prefix', help="Prefix the output file name", type=str)
 parser.add_argument("--sleep", "-s", help="Sleep this long between lines (in seconds)", default=0.0, type=float)
@@ -49,6 +50,7 @@ def match(self, *args):
 log_lines = args.num_lines
 file_prefix = args.file_prefix
 output_type = args.output_type
+log_format = args.log_format
 
 faker = Faker()
 
@@ -58,15 +60,15 @@ def match(self, *args):
 outFileName = 'access_log_'+timestr+'.log' if not file_prefix else file_prefix+'_access_log_'+timestr+'.log'
 
 for case in switch(output_type):
-	if case('LOG'):
-		f = open(outFileName,'w')
-		break
-	if case('GZ'):
-		f = gzip.open(outFileName+'.gz','w')
-		break
-	if case('CONSOLE'): pass
-	if case():
-		f = sys.stdout
+    if case('LOG'):
+        f = open(outFileName,'w')
+        break
+    if case('GZ'):
+        f = gzip.open(outFileName+'.gz','w')
+        break
+    if case('CONSOLE'): pass
+    if case():
+        f = sys.stdout
 
 response=["200","404","500","301"]
 
@@ -78,29 +80,32 @@ def match(self, *args):
 
 flag = True
 while (flag):
-	if args.sleep:
-		increment = datetime.timedelta(seconds=args.sleep)
-	else:
-		increment = datetime.timedelta(seconds=random.randint(30, 300))
-	otime += increment
-
-	ip = faker.ipv4()
-	dt = otime.strftime('%d/%b/%Y:%H:%M:%S')
-	tz = datetime.datetime.now(local).strftime('%z')
-	vrb = numpy.random.choice(verb,p=[0.6,0.1,0.1,0.2])
-
-	uri = random.choice(resources)
-	if uri.find("apps")>0:
-		uri += str(random.randint(1000,10000))
-
-	resp = numpy.random.choice(response,p=[0.9,0.04,0.02,0.04])
-	byt = int(random.gauss(5000,50))
-	referer = faker.uri()
-	useragent = numpy.random.choice(ualist,p=[0.5,0.3,0.1,0.05,0.05] )()
-	f.write('%s - - [%s %s] "%s %s HTTP/1.0" %s %s "%s" "%s"\n' % (ip,dt,tz,vrb,uri,resp,byt,referer,useragent))
-	f.flush()
-
-	log_lines = log_lines - 1
-	flag = False if log_lines == 0 else True
-	if args.sleep:
-		time.sleep(args.sleep)
+    if args.sleep:
+        increment = datetime.timedelta(seconds=args.sleep)
+    else:
+        increment = datetime.timedelta(seconds=random.randint(30, 300))
+    otime += increment
+
+    ip = faker.ipv4()
+    dt = otime.strftime('%d/%b/%Y:%H:%M:%S')
+    tz = datetime.datetime.now(local).strftime('%z')
+    vrb = numpy.random.choice(verb,p=[0.6,0.1,0.1,0.2])
+
+    uri = random.choice(resources)
+    if uri.find("apps")>0:
+        uri += str(random.randint(1000,10000))
+
+    resp = numpy.random.choice(response,p=[0.9,0.04,0.02,0.04])
+    byt = int(random.gauss(5000,50))
+    referer = faker.uri()
+    useragent = numpy.random.choice(ualist,p=[0.5,0.3,0.1,0.05,0.05] )()
+    if log_format == "CLF":
+        f.write('%s - - [%s %s] "%s %s HTTP/1.0" %s %s\n' % (ip,dt,tz,vrb,uri,resp,byt))
+    elif log_format == "ELF": 
+        f.write('%s - - [%s %s] "%s %s HTTP/1.0" %s %s "%s" "%s"\n' % (ip,dt,tz,vrb,uri,resp,byt,referer,useragent))
+    f.flush()
+
+    log_lines = log_lines - 1
+    flag = False if log_lines == 0 else True
+    if args.sleep:
+        time.sleep(args.sleep)