Introduce pylint ci task

This also fixes a few complaints from pylint but explicitly ignores many others that did not seem essential for the start. These can be fixed as we go along.

.github/workflows/pylint.yml

@@ -0,0 +1,26 @@
+name: Pylint Check
+
+on: [push, pull_request]
+
+jobs:
+  lint:
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Check out the code
+        uses: actions/checkout@v3
+
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: '3.11'
+
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install pylint
+          pip install -r requirements.txt
+
+      - name: Run Pylint
+        run: |
+          pylint --disable=C0301,C0103,C0114,C0116,R0913,R0914,W1514,R0911,R0912,R1702,R0902,R0915,R0903,W0511,R0917,W0719,W0707 $(find . -name "*.py")

kartograf/collectors/routeviews.py

@@ -21,7 +21,7 @@ def latest_link(base):
     url = base + ym
 
     try:
-        response = requests.get(url)
+        response = requests.get(url, timeout=600)
         response.raise_for_status()
     except requests.exceptions.HTTPError:
         print(f"The page at {url} couldn't be fetched. "
@@ -32,7 +32,7 @@ def latest_link(base):
         url = base + ym
 
         try:
-            response = requests.get(url)
+            response = requests.get(url, timeout=600)
             response.raise_for_status()
         except requests.exceptions.HTTPError:
             print(f"The page at {url} couldn't be fetched. "
@@ -42,6 +42,7 @@ def latest_link(base):
     soup = BeautifulSoup(response.text, 'html.parser')
 
     links = [a["href"] for a in soup.find_all("a", href=True)]
+    latest = ""
 
     for link in links:
         if link.endswith(".pfx2as.gz"):

kartograf/irr/parse.py

@@ -33,13 +33,13 @@ def parse_irr(context):
             lines = f.readlines()
 
         entry_list = []
-        current_entry = dict()
+        current_entry = {}
 
         # Parse the RPSL objects in the IRR DB into Python Dicts
         for line in lines:
             if line == '\n':
                 entry_list.append(current_entry)
-                current_entry = dict()
+                current_entry = {}
             else:
                 if ":" in line:
                     k, v = line.strip().split(':', 1)

kartograf/kartograf.py

@@ -3,7 +3,6 @@
 import shutil
 import time
 
-from . import __version__
 from kartograf.context import Context
 from kartograf.coverage import coverage
 from kartograf.collectors.routeviews import extract_routeviews_pfx2as, fetch_routeviews_pfx2as
@@ -21,8 +20,11 @@
     wait_for_launch
 )
 
+from . import __version__
 
 class Kartograf:
+    ''' Top level project class. '''
+
     @staticmethod
     def map(args):
         print_section_header("Start Kartograf")

kartograf/rpki/fetch.py

@@ -1,9 +1,11 @@
+import subprocess
+import sys
+
 from concurrent.futures import ThreadPoolExecutor
 from threading import Lock
 import os
 import pathlib
 import requests
-import subprocess
 from tqdm import tqdm
 
 from kartograf.timed import timed
@@ -26,7 +28,7 @@ def download_rir_tals(context):
 
     for rir, url in TAL_URLS.items():
         try:
-            response = requests.get(url)
+            response = requests.get(url, timeout=600)
             response.raise_for_status()
 
             tal_path = os.path.join(context.data_dir_rpki_tals, f"{rir}.tal")
@@ -38,17 +40,17 @@ def download_rir_tals(context):
 
         except requests.RequestException as e:
             print(f"Error downloading TAL for {rir.upper()}: {e}")
-            exit(1)
+            sys.exit(1)
 
 
 def data_tals(context):
-    tal_paths = [path for path in pathlib.Path(context.data_dir_rpki_tals).rglob('*.tal')]
+    tal_paths = list(pathlib.Path(context.data_dir_rpki_tals).rglob('*.tal'))
     # We need to have 5 TALs, one from each RIR
     if len(tal_paths) == 5:
         return tal_paths
-    else:
-        print("Not all 5 TALs could be downloaded.")
-        exit(1)
+
+    print("Not all 5 TALs could be downloaded.")
+    sys.exit(1)
 
 
 @timed
@@ -65,12 +67,14 @@ def fetch_rpki_db(context):
                             "-d", context.data_dir_rpki_cache
                             ] + tal_options,
                            stdout=logs,
-                           stderr=logs)
+                           stderr=logs,
+                           check=False)
     else:
         subprocess.run(["rpki-client",
                         "-d", context.data_dir_rpki_cache
                         ] + tal_options,
-                       capture_output=True)
+                       capture_output=True,
+                       check=False)
 
     print(f"Downloaded RPKI Data, hash sum: {calculate_sha256_directory(context.data_dir_rpki_cache)}")
 
@@ -104,7 +108,8 @@ def process_file(file):
                                  context.epoch,
                                  ] + tal_options +
                                  ["-f", file],  # -f has to be last
-                                 capture_output=True)
+                                 capture_output=True,
+                                 check=False)
 
         if result.stderr and context.debug_log:
             stderr_output = result.stderr.decode()

kartograf/util.py

@@ -1,3 +1,4 @@
+from functools import partial
 import hashlib
 import ipaddress
 import os
@@ -19,11 +20,12 @@ def calculate_sha256(file_path):
 def calculate_sha256_directory(directory_path):
     sha256_hash = hashlib.sha256()
 
-    for root, dirs, files in os.walk(directory_path):
+    for root, _dirs, files in os.walk(directory_path):
         for file in sorted(files):
             file_path = os.path.join(root, file)
             with open(file_path, "rb") as f:
-                for byte_block in iter(lambda: f.read(4096), b""):
+                read_block = partial(f.read, 4096)
+                for byte_block in iter(read_block, b""):
                     sha256_hash.update(byte_block)
 
     return sha256_hash.hexdigest()
@@ -72,7 +74,8 @@ def check_compatibility():
             if version_number < 8.4:
                 raise Exception("Error: rpki-client version 8.4 or higher is "
                                 "required.")
-            elif version_number == latest_version:
+
+            if version_number == latest_version:
                 print(f"Using rpki-client version {version} (recommended).")
             elif version_number > latest_version:
                 print("Warning: This kartograf version has not been tested with "
@@ -121,7 +124,6 @@ def format_pfx(pfx):
         if '/' in pfx:
             formatted_pfx = str(ipaddress.ip_network(pfx))
             return f"{formatted_pfx}"
-        else:
-            return str(ipaddress.ip_address(pfx))
+        return str(ipaddress.ip_address(pfx))
     except ValueError:
         return pfx