From 62a2a3c3f766bb4e467fa3522457e9a1f2cb01d2 Mon Sep 17 00:00:00 2001
From: Roman <zajic@zajic.net>
Date: Fri, 27 Jun 2025 16:31:30 +0800
Subject: [PATCH] fix: disable parsed log output to file

---
 src/node/nomos_node.py |  2 +-
 src/tfidf/tfidf.py     | 20 ++++++++++++--------
 2 files changed, 13 insertions(+), 9 deletions(-)

diff --git a/src/node/nomos_node.py b/src/node/nomos_node.py
index 663f09b..e2646a9 100644
--- a/src/node/nomos_node.py
+++ b/src/node/nomos_node.py
@@ -152,7 +152,7 @@ class NomosNode:
 
         logger.debug(f"Parsing log for node {self.name()}")
         log_tfidf = LogTfidf()
-        log_tfidf.parse_log(self._log_path, f"{self._log_path}.parsed", keywords, True)
+        log_tfidf.parse_log(self._log_path, keywords, None)
 
     def extract_config(self, target_file):
         # Copy the config file from first node
diff --git a/src/tfidf/tfidf.py b/src/tfidf/tfidf.py
index 71b4ac2..cf41bbe 100644
--- a/src/tfidf/tfidf.py
+++ b/src/tfidf/tfidf.py
@@ -15,6 +15,16 @@ def normalize_log_message(text):
     return " ".join(text.split())
 
 
+def write_output(df, output_file=None):
+    lines = df["d1"].astype(str) + "\n"
+
+    if output_file:
+        with open(output_file, "w") as out_file:
+            out_file.writelines(lines)
+
+    print("".join(lines), end="")
+
+
 class LogTfidf:
     def __init__(self):
         self.stemmer = PorterStemmer()
@@ -33,7 +43,7 @@ class LogTfidf:
         tokens = word_tokenize(text.lower())
         return self.get_stemmed_tokens(tokens)
 
-    def parse_log(self, input_file, output_file, keywords, print_to_stdout=True):
+    def parse_log(self, input_file, keywords, output_file=None):
         vectorizer = ext.CountVectorizer(tokenizer=self.get_tokens, stop_words=self.stop_words, token_pattern=None)
         with open(input_file, "r") as file:
             lines = [line.rstrip() for line in file]
@@ -63,10 +73,4 @@ class LogTfidf:
         df = df.drop_duplicates(subset="d1_normalized", keep="first")
         df = df.drop(columns="d1_normalized")
 
-        with open(output_file, "w") as out_file:
-            for index, row in df.iterrows():
-                line = "{0}\n"
-                line = line.format(row["d1"])
-                out_file.write(line)
-                if print_to_stdout:
-                    print(line)
+        write_output(df, output_file)