logos-blockchain/logos-blockchain-e2e-tests
1
0
Fork 0
mirror of https://github.com/logos-blockchain/logos-blockchain-e2e-tests.git synced 2026-01-10 09:03:08 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: disable parsed log output to file

Browse Source
This commit is contained in:
Roman 2025-06-27 16:31:30 +08:00
parent c55e4ff838
commit 62a2a3c3f7
No known key found for this signature in database
GPG Key ID: 583BDF43C238B83E
2 changed files with 13 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
src/node/nomos_node.py
View File

@ -152,7 +152,7 @@ class NomosNode:
logger.debug(f"Parsing log for node {self.name()}") logger.debug(f"Parsing log for node {self.name()}")
log_tfidf = LogTfidf() 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): def extract_config(self, target_file):
# Copy the config file from first node # Copy the config file from first node

20
src/tfidf/tfidf.py
View File

@ -15,6 +15,16 @@ def normalize_log_message(text):
return " ".join(text.split()) 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: class LogTfidf:
def __init__(self): def __init__(self):
self.stemmer = PorterStemmer() self.stemmer = PorterStemmer()
@ -33,7 +43,7 @@ class LogTfidf:
tokens = word_tokenize(text.lower()) tokens = word_tokenize(text.lower())
return self.get_stemmed_tokens(tokens) 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) vectorizer = ext.CountVectorizer(tokenizer=self.get_tokens, stop_words=self.stop_words, token_pattern=None)
with open(input_file, "r") as file: with open(input_file, "r") as file:
lines = [line.rstrip() for line in 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_duplicates(subset="d1_normalized", keep="first")
df = df.drop(columns="d1_normalized") df = df.drop(columns="d1_normalized")
with open(output_file, "w") as out_file: write_output(df, output_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)