From ea350dd1a70db51805b295b6ad100cee1dc9065c Mon Sep 17 00:00:00 2001
From: Thomas Ryckeboer <tryckeboer@norsys.fr>
Date: Fri, 8 Feb 2019 15:36:29 +0100
Subject: [PATCH 1/5] Add txt files and notebooks files to .gitignore + Drain
 compatibility with Python 3.7

---
 .gitignore                  |  5 +++++
 demo/Drain_demo.py          | 42 ++++++++++++++++++-------------------
 logparser/Drain/Drain.py    |  8 +++----
 logparser/Drain/__init__.py |  2 +-
 4 files changed, 31 insertions(+), 26 deletions(-)

diff --git a/.gitignore b/.gitignore
index 39920103..7eb461c0 100644
--- a/.gitignore
+++ b/.gitignore
@@ -57,3 +57,8 @@ target/
 Unused/
 .idea/
 POP/
+*.txt
+demo/.ipynb_checkpoints/
+demo/DrainEvaluation/.ipynb_checkpoints/
+logparser/Drain/.ipynb_checkpoints/
+*.ipynb
diff --git a/demo/Drain_demo.py b/demo/Drain_demo.py
index daf8759c..c6428ba0 100644
--- a/demo/Drain_demo.py
+++ b/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]+$', # Numbers
-]
-st         = 0.5  # Similarity threshold
-depth      = 4  # Depth of all leaf nodes
-
-parser = Drain.LogParser(log_format, indir=input_dir, outdir=output_dir,  depth=depth, st=st, rex=regex)
-parser.parse(log_file)
-
+#!/usr/bin/env python
+import sys
+sys.path.append('../')
+from logparser.Drain import Drain
+
+input_dir  = '../logs/HDFS/'  # The input directory of log file
+output_dir = 'Drain_result/'  # The output directory of parsing results
+log_file   = 'HDFS_2k.log'  # The input log file name
+log_format = '<Date> <Time> <Pid> <Level> <Component>: <Content>'  # HDFS log format
+# Regular expression list for optional preprocessing (default: [])
+regex      = [
+    r'blk_(|-)[0-9]+' , # block id
+    r'(/|)([0-9]+\.){3}[0-9]+(:[0-9]+|)(:|)', # IP
+    r'(?<=[^A-Za-z0-9])(\-?\+?\d+)(?=[^A-Za-z0-9])|[0-9]+$', # 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)
+
diff --git a/logparser/Drain/Drain.py b/logparser/Drain/Drain.py
index ba93a8f0..61bbd271 100644
--- a/logparser/Drain/Drain.py
+++ b/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('>')
diff --git a/logparser/Drain/__init__.py b/logparser/Drain/__init__.py
index 79b9f0a2..7970b790 100644
--- a/logparser/Drain/__init__.py
+++ b/logparser/Drain/__init__.py
@@ -1 +1 @@
-from Drain import *
\ No newline at end of file
+from logparser.Drain import *

From 91dd9f49033d213add1668395abe61b52d186b3f Mon Sep 17 00:00:00 2001
From: Thomas Ryckeboer <tryckeboer@norsys.fr>
Date: Fri, 8 Feb 2019 16:37:42 +0100
Subject: [PATCH 2/5] Why I did that ?

---
 .gitignore | 1 -
 1 file changed, 1 deletion(-)

diff --git a/.gitignore b/.gitignore
index 7eb461c0..23e49e57 100644
--- a/.gitignore
+++ b/.gitignore
@@ -57,7 +57,6 @@ target/
 Unused/
 .idea/
 POP/
-*.txt
 demo/.ipynb_checkpoints/
 demo/DrainEvaluation/.ipynb_checkpoints/
 logparser/Drain/.ipynb_checkpoints/

From a4cf2205bf1f88c8154ec321faec497c93adec72 Mon Sep 17 00:00:00 2001
From: Jamie Zhu <jimzhu@users.noreply.github.com>
Date: Sat, 9 Feb 2019 11:29:12 +0800
Subject: [PATCH 3/5] Update .gitignore

---
 .gitignore | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/.gitignore b/.gitignore
index 23e49e57..8ad09ebf 100644
--- a/.gitignore
+++ b/.gitignore
@@ -57,7 +57,5 @@ target/
 Unused/
 .idea/
 POP/
-demo/.ipynb_checkpoints/
-demo/DrainEvaluation/.ipynb_checkpoints/
-logparser/Drain/.ipynb_checkpoints/
+.ipynb_checkpoints/
 *.ipynb

From 202c048e8f6c734f8a9cd8d9cfaa90943c43a3a6 Mon Sep 17 00:00:00 2001
From: Jamie Zhu <jimzhu@users.noreply.github.com>
Date: Sat, 9 Feb 2019 11:30:30 +0800
Subject: [PATCH 4/5] Update Drain_demo.py

---
 demo/Drain_demo.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/demo/Drain_demo.py b/demo/Drain_demo.py
index c6428ba0..21fe2576 100644
--- a/demo/Drain_demo.py
+++ b/demo/Drain_demo.py
@@ -1,7 +1,7 @@
 #!/usr/bin/env python
 import sys
 sys.path.append('../')
-from logparser.Drain import Drain
+from logparser import Drain
 
 input_dir  = '../logs/HDFS/'  # The input directory of log file
 output_dir = 'Drain_result/'  # The output directory of parsing results

From 00dbdddd3afa21a46403b092fb573ec7fc7f0993 Mon Sep 17 00:00:00 2001
From: Jamie Zhu <jimzhu@users.noreply.github.com>
Date: Sat, 9 Feb 2019 11:31:43 +0800
Subject: [PATCH 5/5] Update __init__.py

---
 logparser/Drain/__init__.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/logparser/Drain/__init__.py b/logparser/Drain/__init__.py
index 7970b790..7894c615 100644
--- a/logparser/Drain/__init__.py
+++ b/logparser/Drain/__init__.py
@@ -1 +1 @@
-from logparser.Drain import *
+from .Drain import *