Drain compatibility with Python 3.7

.gitignore

@@ -57,3 +57,5 @@ target/
 Unused/
 .idea/
 POP/
+.ipynb_checkpoints/
+*.ipynb

demo/Drain_demo.py

@@ -1,21 +1,21 @@
-#!/usr/bin/env python
-import sys
-sys.path.append('../')
-from logparser import Drain
-
-input_dir  = '../logs/HDFS/'  # The input directory of log file
-output_dir = 'Drain_result/'  # The output directory of parsing results
-log_file   = 'HDFS_2k.log'  # The input log file name
-log_format = '<Date> <Time> <Pid> <Level> <Component>: <Content>'  # HDFS log format
-# Regular expression list for optional preprocessing (default: [])
-regex      = [
-    r'blk_(|-)[0-9]+' , # block id
-    r'(/|)([0-9]+\.){3}[0-9]+(:[0-9]+|)(:|)', # IP
-    r'(?<=[^A-Za-z0-9])(\-?\+?\d+)(?=[^A-Za-z0-9])|[0-9]+$', # Numbers
-]
-st         = 0.5  # Similarity threshold
-depth      = 4  # Depth of all leaf nodes
-
-parser = Drain.LogParser(log_format, indir=input_dir, outdir=output_dir,  depth=depth, st=st, rex=regex)
-parser.parse(log_file)
-
+#!/usr/bin/env python
+import sys
+sys.path.append('../')
+from logparser import Drain
+
+input_dir  = '../logs/HDFS/'  # The input directory of log file
+output_dir = 'Drain_result/'  # The output directory of parsing results
+log_file   = 'HDFS_2k.log'  # The input log file name
+log_format = '<Date> <Time> <Pid> <Level> <Component>: <Content>'  # HDFS log format
+# Regular expression list for optional preprocessing (default: [])
+regex      = [
+    r'blk_(|-)[0-9]+' , # block id
+    r'(/|)([0-9]+\.){3}[0-9]+(:[0-9]+|)(:|)', # IP
+    r'(?<=[^A-Za-z0-9])(\-?\+?\d+)(?=[^A-Za-z0-9])|[0-9]+$', # Numbers
+]
+st         = 0.5  # Similarity threshold
+depth      = 4  # Depth of all leaf nodes
+
+parser = Drain.LogParser(log_format, indir=input_dir, outdir=output_dir,  depth=depth, st=st, rex=regex)
+parser.parse(log_file)
+

logparser/Drain/Drain.py

@@ -224,7 +224,7 @@ def outputResult(self, logClustL):
 
     def printTree(self, node, dep):
         pStr = ''   
-        for i in xrange(dep):
+        for i in range(dep):
             pStr += '\t'
 
         if node.depth == 0:
@@ -234,7 +234,7 @@ def printTree(self, node, dep):
         else:
             pStr += node.digitOrtoken
 
-        print pStr
+        print(pStr)
 
         if node.depth == self.depth:
             return 1
@@ -273,7 +273,7 @@ def parse(self, logName):
 
             count += 1
             if count % 1000 == 0 or count == len(self.df_log):
-                print 'Processed {0:.1f}% of log lines.'.format(count * 100.0 / len(self.df_log))
+                print('Processed {0:.1f}% of log lines.'.format(count * 100.0 / len(self.df_log)))
 
 
         if not os.path.exists(self.savePath):
@@ -320,7 +320,7 @@ def generate_logformat_regex(self, logformat):
         regex = ''
         for k in range(len(splitters)):
             if k % 2 == 0:
-                splitter = re.sub(' +', '\s+', splitters[k])
+                splitter = re.sub(' +', '\\\s+', splitters[k])
                 regex += splitter
             else:
                 header = splitters[k].strip('<').strip('>')

logparser/Drain/__init__.py

@@ -1 +1 @@
-from Drain import *
+from .Drain import *