From 6f22a9530cccae433a399fd7fcbe3f1e7a585987 Mon Sep 17 00:00:00 2001
From: Erick Ahmed <engineering@erickahmed.com>
Date: Mon, 6 Jul 2026 16:01:14 +0200
Subject: [PATCH] Add simple parser for bxcanlogger project

- Takes text input and parses it to a csv
---
 parser.py | 67 +++++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 67 insertions(+)
 create mode 100644 parser.py

diff --git a/parser.py b/parser.py
new file mode 100644
index 0000000..c68310a
--- /dev/null
+++ b/parser.py
@@ -0,0 +1,67 @@
+import re
+import csv
+from pathlib import Path
+
+def parse_can_log(input_path: str | Path, out_bus1: str | Path, out_bus2: str | Path) -> None:
+    """
+    Parses a CAN bus log file and saves valid frames to separate CSV files for Bus 1 and Bus 2.
+    Corrupted, incomplete, or debug frames are silently discarded.
+    """
+    input_file = Path(input_path)
+    out1_file = Path(out_bus1)
+    out2_file = Path(out_bus2)
+
+    # Group 1: Bus (C1 or C2)
+    # Group 2: ID (1 to 8 hex chars)
+    # Group 3: DLC (1 to 2 hex chars)
+    start_pattern = re.compile(r'(C[12]):([0-9A-Fa-f]{1,8})\s+([0-9A-Fa-f]{1,2})\s+')
+
+    byte_pattern = re.compile(r'^[0-9A-Fa-f]{2}$')
+
+    with input_file.open('r', encoding='utf-8') as f_in, \
+         out1_file.open('w', newline='', encoding='utf-8') as f_out1, \
+         out2_file.open('w', newline='', encoding='utf-8') as f_out2:
+
+        writer1 = csv.writer(f_out1)
+        writer2 = csv.writer(f_out2)
+
+        writer1.writerow(['ID', 'DLC', 'Data'])
+        writer2.writerow(['ID', 'DLC', 'Data'])
+
+        for line in f_in:
+            for match in start_pattern.finditer(line):
+                bus = match.group(1)
+                can_id = match.group(2).upper()
+                dlc_str = match.group(3)
+
+                try:
+                    dlc = int(dlc_str, 16)
+                except ValueError:
+                    continue
+
+                if dlc > 8:
+                    continue
+
+                remaining = line[match.end():]
+                tokens = remaining.split()
+
+                data_bytes = []
+                for token in tokens:
+                    if byte_pattern.match(token):
+                        data_bytes.append(token.upper())
+                    else:
+                        break
+
+                if len(data_bytes) == dlc:
+                    data_str = ' '.join(data_bytes)
+                    row = [can_id, dlc, data_str]
+
+                    if bus == 'C1':
+                        writer1.writerow(row)
+                    elif bus == 'C2':
+                        writer2.writerow(row)
+
+if __name__ == '__main__':
+    # Example usage:
+    # parse_can_log('can_traffic.txt', 'bus1_output.csv', 'bus2_output.csv')
+    pass