From 41350a83757731f7cb59abab82bb170da811962e Mon Sep 17 00:00:00 2001
From: Jiri Konecny <jkonecny@redhat.com>
Date: Wed, 24 Apr 2024 12:06:50 +0200
Subject: [PATCH] Add Flake8 code style linter

Let's avoid code style issues in the project.
---
 README.md                    |  8 ++++++++
 logdetective/logdetective.py | 16 +++++++---------
 tox.ini                      | 12 ++++++++++++
 3 files changed, 27 insertions(+), 9 deletions(-)

diff --git a/README.md b/README.md
index 32ac679..c35dab7 100644
--- a/README.md
+++ b/README.md
@@ -47,6 +47,14 @@ The [tox](https://github.com/tox-dev/tox) is used to manage tests. Please instal
 
 This will create a virtual environment with dependencies and run all the tests. For more information follow the tox help.
 
+To run only a specific test execute this:
+
+    tox run -e style # to run flake8
+
+or
+
+    tox run -e lint # to run pylint
+
 License
 -------
 
diff --git a/logdetective/logdetective.py b/logdetective/logdetective.py
index c3a4673..1f8192e 100644
--- a/logdetective/logdetective.py
+++ b/logdetective/logdetective.py
@@ -54,7 +54,7 @@ def __init__(self):
 
     def __call__(self, block_num, block_size, total_size):
         if not self.pbar:
-            self.pbar=progressbar.ProgressBar(maxval=total_size)
+            self.pbar = progressbar.ProgressBar(maxval=total_size)
             self.pbar.start()
 
         downloaded = block_num * block_size
@@ -74,7 +74,7 @@ def get_chunks(text: str):
     while i < text_len:
         chunk += text[i]
         if text[i] == '\n':
-            if i+1 < text_len and (text[i+1].isspace() or text[i-1] == "\\"):
+            if i + 1 < text_len and (text[i + 1].isspace() or text[i - 1] == "\\"):
                 i += 1
                 continue
             yield chunk
@@ -101,7 +101,7 @@ def __call__(self, log: str, n_lines: int = 2, neighbors: bool = False) -> str:
 
     def rate_chunks(self, log: str, n_lines: int = 2) -> list[tuple]:
         """Scan log by the model and store results.
-        
+
         :param log: log file content
         :param n_lines: How many lines should the model take into consideration
         """
@@ -109,7 +109,7 @@ def rate_chunks(self, log: str, n_lines: int = 2) -> list[tuple]:
         log_lines = log.split("\n")
 
         for i in range(0, len(log_lines), n_lines):
-            block = '\n'.join(log_lines[i:i+n_lines])
+            block = '\n'.join(log_lines[i:i + n_lines])
             prompt = SUMMARIZE_PROPT_TEMPLATE.format(log)
             out = self.model(prompt, max_tokens=7, grammar=self.grammar)
             out = f"{out['choices'][0]['text']}\n"
@@ -117,7 +117,6 @@ def rate_chunks(self, log: str, n_lines: int = 2) -> list[tuple]:
 
         return results
 
-
     def create_extract(self, chunks: list[tuple], neighbors: bool = False) -> str:
         """Extract interesting chunks from the model processing.
         """
@@ -128,7 +127,7 @@ def create_extract(self, chunks: list[tuple], neighbors: bool = False) -> str:
             if chunks[i][1].startswith("Yes"):
                 interesting.append(i)
                 if neighbors:
-                    interesting.extend([max(i-1, 0), min(i+1, len(chunks)-1)])
+                    interesting.extend([max(i - 1, 0), min(i + 1, len(chunks) - 1)])
 
         interesting = np.unique(interesting)
 
@@ -205,13 +204,12 @@ def main():
     parser.add_argument("url", type=str, default="")
     parser.add_argument("-M", "--model", type=str, default=DEFAULT_ADVISOR)
     parser.add_argument("-S", "--summarizer", type=str, default="drain")
-    parser.add_argument("-N","--n_lines", type=int, default=5)
+    parser.add_argument("-N", "--n_lines", type=int, default=5)
     parser.add_argument("-v", "--verbose", action='count', default=0)
     parser.add_argument("-q", "--quiet", action='store_true')
 
     args = parser.parse_args()
 
-
     if args.verbose and args.quiet:
         sys.stderr.write("Error: --quiet and --verbose is mutually exclusive.\n")
         sys.exit(2)
@@ -248,7 +246,7 @@ def main():
     log = requests.get(args.url, timeout=60).text
     log_summary = extractor(log)
 
-    ratio = len(log_summary.split('\n'))/len(log.split('\n'))
+    ratio = len(log_summary.split('\n')) / len(log.split('\n'))
     LOG.debug("Log summary: \n %s", log_summary)
     LOG.info("Compression ratio: %s", ratio)
 
diff --git a/tox.ini b/tox.ini
index e03b0d6..e03041e 100644
--- a/tox.ini
+++ b/tox.ini
@@ -2,9 +2,21 @@
 min_version = 4.0
 env_list = 
     lint
+    style
 
 [testenv:lint]
 description = run Pylint
 deps =
     pylint>=3.0.0
 commands = pylint {posargs:./logdetective/logdetective.py}
+
+[testenv:style]
+description = run Flake8
+deps =
+    flake8>=7.0.0
+commands = flake8 {posargs:./logdetective/logdetective.py}
+
+[flake8]
+ignore = 
+    # disable max line leght, that is already checked by pylint
+    E501