From d7799f1ff7fca7525fd09c2e51f366be1d0886b5 Mon Sep 17 00:00:00 2001
From: pine <dijsds@163.com>
Date: Thu, 13 Mar 2025 22:59:24 +0800
Subject: feat: simple parser rules load and log processing

---
 src/conventionalrp/core/parser.py | 49 +++++++++++++++++++++++++++++++++++----
 1 file changed, 44 insertions(+), 5 deletions(-)

(limited to 'src')

diff --git a/src/conventionalrp/core/parser.py b/src/conventionalrp/core/parser.py
index 32b1b9f..73f349f 100644
--- a/src/conventionalrp/core/parser.py
+++ b/src/conventionalrp/core/parser.py
@@ -1,15 +1,54 @@
+import json
+import re
+from pathlib import Path
+
 class Parser:
     def __init__(self):
         self.rules = []
 
-    def load_rules(self, rules):
+    def load_rules(self, rules_path : str):
         """Load parsing rules."""
+        if not Path(rules_path).exists():
+            raise FileNotFoundError(f"No such file or directory: {rules_path} ")
+
+        with open(rules_path, "r", encoding="utf-8") as f:
+            rules = json.load(f)
+
+        # validation rule format
+        if rules is None:
+            raise ValueError(f"Rule file cannot be empty.")
+        # to be continue...
+
         self.rules = rules
 
-    def parse_log(self, log):
+    def parse_log(self, log_path: str):
         """Parse the TRPG log based on loaded rules."""
         parsed_data = []
-        for rule in self.rules:
-            # Implement rule-based parsing logic here
-            pass
+
+        if not Path(log_path).exists():
+            raise FileNotFoundError(f"No such file or directory: {log_path} ")
+
+        with open(log_path, "r", encoding="utf-8") as f:
+            log_content = f.read().splitlines()
+
+        # Iterate each line of the log
+        for line in log_content:
+            # pass blank line
+            if not line.strip():
+                continue
+
+            # try to match the current line by rules
+            for rule in self.rules:
+                pattern = rule.get("pattern")
+                rule_type = rule.get("type")
+                match = re.search(pattern, line)
+                if match:
+                    # matched
+                    content = match.group(1).strip()
+                    parsed_data.append({"content": content, "type": rule_type})
+                    break
+            # no matched, marked as an unknown type
+            else:
+                parsed_data.append({"content": line.strip(), "type": "unknown"})
+
         return parsed_data
\ No newline at end of file
-- 
cgit v1.2.3-70-g09d2