add error id, ignore unrecognized chunks

1 files changed, 10 insertions, 9 deletions

diff --git a/errors2csv.py b/errors2csv.py
index b432e72..6cabad3 100755
--- a/errors2csv.py
+++ b/errors2csv.py
@@ -1,12 +1,13 @@
 #!/usr/bin/env python3
 import csv
+import hashlib
 import shlex
 
-unique_errors = set()
+fieldnames = ['ID', 'ERROR', 'MSG', 'STACK', 'STEP', 'ACTIVE', 'STATE', 'ACTION', 'ARGS', 'SETUP', 'DATA', 'DUMP']
+key_fieldsnames = ['ERROR', 'STATE', 'MSG']
 
+unique_errors = set()
 with open('errors.txt', 'r') as f, open('errors.csv', 'w', newline='') as csvfile:
-    fieldnames = ['ERROR', 'MSG', 'STACK', 'STEP', 'ACTIVE', 'STATE', 'ACTION', 'ARGS', 'SETUP', 'DATA', 'DUMP']
-    key_fieldsnames = ['ERROR', 'STATE', 'MSG']
     writer = csv.DictWriter(csvfile, fieldnames=fieldnames)
     writer.writeheader()
 
@@ -14,15 +15,15 @@ with open('errors.txt', 'r') as f, open('errors.csv', 'w', newline='') as csvfil
         line = line.strip()
         if line.startswith("Loading") or line.startswith("INFO:"):
             continue
-        # print(line)
         data = {}
         for keyval in shlex.split(line):
-            # print(keyval)
-            key, val = keyval.split("=", 2)
-            # print("key", key)
-            # print("val", val)
-            data[key] = val
+            try:
+                key, val = keyval.split("=", 2)
+                data[key] = val
+            except ValueError:
+                pass
         error_key = "_".join([data.get(key, '') for key in key_fieldsnames])
         if error_key not in unique_errors:
             unique_errors.add(error_key)
+            data['ID'] = hashlib.sha256(error_key.encode()).hexdigest()[:8]
             writer.writerow(data)