refactor: use Path objects instead of strings

Don't convert Paths to Paths.
Simplify code and take advantage of Path object methods.

Signed-off-by: Rafal Ilnicki <[email protected]>

Author: rilnicki

cve_bin_tool/cli.py

@@ -830,8 +830,7 @@ def main(argv=None):
         error_mode=error_mode,
     )
 
-    # if OLD_CACHE_DIR (from cvedb.py) exists, print warning
-    if Path(OLD_CACHE_DIR).exists():
+    if OLD_CACHE_DIR.exists():
         LOGGER.warning(
             f"Obsolete cache dir {OLD_CACHE_DIR} is no longer needed and can be removed."
         )

cve_bin_tool/cve_scanner.py

@@ -5,7 +5,6 @@
 import sys
 from collections import defaultdict
 from logging import Logger
-from pathlib import Path
 from string import ascii_lowercase
 from typing import DefaultDict, Dict, List
 
@@ -31,7 +30,7 @@ class CVEScanner:
     all_cve_version_info: Dict[str, VersionInfo]
 
     RANGE_UNSET: str = ""
-    dbname: str = str(Path(DISK_LOCATION_DEFAULT) / DBNAME)
+    dbname: str = str(DISK_LOCATION_DEFAULT / DBNAME)
     CONSOLE: Console = Console(file=sys.stderr, theme=cve_theme)
     ALPHA_TO_NUM: Dict[str, int] = dict(zip(ascii_lowercase, range(26)))
 

cve_bin_tool/data_sources/curl_source.py

@@ -5,7 +5,6 @@
 
 import json
 import logging
-from pathlib import Path
 
 import aiohttp
 
@@ -66,7 +65,7 @@ async def download_curl_vulnerabilities(self, session: RateLimiter) -> None:
         async with await session.get(self.DATA_SOURCE_LINK) as response:
             response.raise_for_status()
             self.vulnerability_data = await response.json()
-        path = Path(str(Path(self.cachedir) / "vuln.json"))
+        path = self.cachedir / "vuln.json"
         filepath = path.resolve()
         async with FileIO(filepath, "w") as f:
             await f.write(json.dumps(self.vulnerability_data, indent=4))

cve_bin_tool/data_sources/epss_source.py

@@ -6,7 +6,6 @@
 import csv
 import gzip
 import logging
-import os
 from datetime import datetime, timedelta
 from io import StringIO
 from pathlib import Path
@@ -34,8 +33,8 @@ def __init__(self, error_mode=ErrorMode.TruncTrace):
         self.error_mode = error_mode
         self.cachedir = self.CACHEDIR
         self.backup_cachedir = self.BACKUPCACHEDIR
-        self.epss_path = str(Path(self.cachedir) / "epss")
-        self.file_name = os.path.join(self.epss_path, "epss_scores-current.csv")
+        self.epss_path = self.cachedir / "epss"
+        self.file_name = self.epss_path / "epss_scores-current.csv"
         self.source_name = self.SOURCE
 
     async def update_epss(self):
@@ -58,11 +57,11 @@ async def download_epss_data(self):
         """Downloads the EPSS CSV file and saves it to the local filesystem.
         The download is only performed if the file is older than 24 hours.
         """
-        os.makedirs(self.epss_path, exist_ok=True)
+        self.epss_path.mkdir(parents=True, exist_ok=True)
         # Check if the file exists
-        if os.path.exists(self.file_name):
+        if self.file_name.exists():
             # Get the modification time of the file
-            modified_time = os.path.getmtime(self.file_name)
+            modified_time = self.file_name.stat().st_mtime
             last_modified = datetime.fromtimestamp(modified_time)
 
             # Calculate the time difference between now and the last modified time
@@ -80,8 +79,7 @@ async def download_epss_data(self):
                             decompressed_data = gzip.decompress(await response.read())
 
                     # Save the downloaded data to the file
-                    with open(self.file_name, "wb") as file:
-                        file.write(decompressed_data)
+                    self.file_name.write_bytes(decompressed_data)
 
                 except aiohttp.ClientError as e:
                     self.LOGGER.error(f"An error occurred during updating epss {e}")
@@ -102,8 +100,7 @@ async def download_epss_data(self):
                         decompressed_data = gzip.decompress(await response.read())
 
                 # Save the downloaded data to the file
-                with open(self.file_name, "wb") as file:
-                    file.write(decompressed_data)
+                self.file_name.write_bytes(decompressed_data)
 
             except aiohttp.ClientError as e:
                 self.LOGGER.error(f"An error occurred during downloading epss {e}")
@@ -114,9 +111,8 @@ def parse_epss_data(self, file_path=None):
         if file_path is None:
             file_path = self.file_name
 
-        with open(file_path) as file:
-            # Read the content of the CSV file
-            decoded_data = file.read()
+        # Read the content of the CSV file
+        decoded_data = Path(file_path).read_text()
 
         # Create a CSV reader to read the data from the decoded CSV content
         reader = csv.reader(StringIO(decoded_data), delimiter=",")

cve_bin_tool/data_sources/gad_source.py

@@ -8,7 +8,6 @@
 import io
 import re
 import zipfile
-from pathlib import Path
 
 import aiohttp
 import yaml
@@ -39,7 +38,7 @@ def __init__(
     ):
         self.cachedir = self.CACHEDIR
         self.slugs = None
-        self.gad_path = str(Path(self.cachedir) / "gad")
+        self.gad_path = self.cachedir / "gad"
         self.source_name = self.SOURCE
 
         self.error_mode = error_mode
@@ -90,8 +89,8 @@ async def fetch_cves(self):
 
         self.db = cvedb.CVEDB()
 
-        if not Path(self.gad_path).exists():
-            Path(self.gad_path).mkdir()
+        if not self.gad_path.exists():
+            self.gad_path.mkdir()
             # As no data, force full update
             self.incremental_update = False
 
@@ -155,7 +154,7 @@ async def fetch_cves(self):
     async def update_cve_entries(self):
         """Updates CVE entries from CVEs in cache."""
 
-        p = Path(self.gad_path).glob("**/*")
+        p = self.gad_path.glob("**/*")
         # Need to find files which are new to the cache
         last_update_timestamp = (
             self.time_of_last_update.timestamp()

cve_bin_tool/data_sources/nvd_source.py

@@ -77,7 +77,7 @@ def __init__(
         self.source_name = self.SOURCE
 
         # set up the db if needed
-        self.dbpath = str(Path(self.cachedir) / DBNAME)
+        self.dbpath = self.cachedir / DBNAME
         self.connection: sqlite3.Connection | None = None
         self.session = session
         self.cve_count = -1
@@ -543,12 +543,9 @@ async def cache_update(
         Update the cache for a single year of NVD data.
         """
         filename = url.split("/")[-1]
-        # Ensure we only write to files within the cachedir
-        cache_path = Path(self.cachedir)
-        filepath = Path(str(cache_path / filename)).resolve()
-        if not str(filepath).startswith(str(cache_path.resolve())):
-            with ErrorHandler(mode=self.error_mode, logger=self.LOGGER):
-                raise AttemptedToWriteOutsideCachedir(filepath)
+        cache_path = self.cachedir
+        filepath = cache_path / filename
+
         # Validate the contents of the cached file
         if filepath.is_file():
             # Validate the sha and write out
@@ -600,7 +597,7 @@ def load_nvd_year(self, year: int) -> dict[str, str | object]:
         Return the dict of CVE data for the given year.
         """
 
-        filename = Path(self.cachedir) / self.NVDCVE_FILENAME_TEMPLATE.format(year)
+        filename = self.cachedir / self.NVDCVE_FILENAME_TEMPLATE.format(year)
         # Check if file exists
         if not filename.is_file():
             with ErrorHandler(mode=self.error_mode, logger=self.LOGGER):
@@ -619,5 +616,5 @@ def nvd_years(self) -> list[int]:
         """
         return sorted(
             int(filename.split(".")[-3].split("-")[-1])
-            for filename in glob.glob(str(Path(self.cachedir) / "nvdcve-1.1-*.json.gz"))
+            for filename in glob.glob(str(self.cachedir / "nvdcve-1.1-*.json.gz"))
         )

cve_bin_tool/data_sources/osv_source.py

@@ -7,7 +7,6 @@
 import datetime
 import io
 import json
-import os
 import shutil
 import zipfile
 from pathlib import Path
@@ -25,7 +24,7 @@
 
 def find_gsutil():
     gsutil_path = shutil.which("gsutil")
-    if not os.path.exists(gsutil_path):
+    if not Path(gsutil_path).exists():
         raise FileNotFoundError(
             "gsutil not found. Did you need to install requirements or activate a venv where gsutil is installed?"
         )
@@ -46,7 +45,7 @@ def __init__(
     ):
         self.cachedir = self.CACHEDIR
         self.ecosystems = None
-        self.osv_path = str(Path(self.cachedir) / "osv")
+        self.osv_path = self.cachedir / "osv"
         self.source_name = self.SOURCE
 
         self.error_mode = error_mode
@@ -113,7 +112,7 @@ async def get_ecosystem_incremental(self, ecosystem, time_of_last_update, sessio
             tasks.append(task)
 
         for r in await asyncio.gather(*tasks):
-            filepath = Path(self.osv_path) / (r.get("id") + ".json")
+            filepath = self.osv_path / (r.get("id") + ".json")
             r = json.dumps(r)
 
             async with FileIO(filepath, "w") as f:
@@ -158,9 +157,9 @@ async def get_totalfiles(self, ecosystem):
 
         gsutil_path = find_gsutil()  # use helper function
         gs_file = self.gs_url + ecosystem + "/all.zip"
-        await aio_run_command([gsutil_path, "cp", gs_file, self.osv_path])
+        await aio_run_command([gsutil_path, "cp", gs_file, str(self.osv_path)])
 
-        zip_path = Path(self.osv_path) / "all.zip"
+        zip_path = self.osv_path / "all.zip"
         totalfiles = 0
 
         with zipfile.ZipFile(zip_path, "r") as z:
@@ -179,8 +178,8 @@ async def fetch_cves(self):
 
         self.db = cvedb.CVEDB()
 
-        if not Path(self.osv_path).exists():
-            Path(self.osv_path).mkdir()
+        if not self.osv_path.exists():
+            self.osv_path.mkdir()
             # As no data, force full update
             self.incremental_update = False
 
@@ -239,7 +238,7 @@ async def fetch_cves(self):
     async def update_cve_entries(self):
         """Updates CVE entries from CVEs in cache"""
 
-        p = Path(self.osv_path).glob("**/*")
+        p = self.osv_path.glob("**/*")
         # Need to find files which are new to the cache
         last_update_timestamp = (
             self.time_of_last_update.timestamp()

cve_bin_tool/data_sources/purl2cpe_source.py

@@ -2,7 +2,6 @@
 
 import zipfile
 from io import BytesIO
-from pathlib import Path
 
 import aiohttp
 
@@ -25,7 +24,7 @@ def __init__(
         self, error_mode: ErrorMode = ErrorMode.TruncTrace, incremental_update=False
     ):
         self.cachedir = self.CACHEDIR
-        self.purl2cpe_path = str(Path(self.cachedir) / "purl2cpe")
+        self.purl2cpe_path = self.cachedir / "purl2cpe"
         self.source_name = self.SOURCE
         self.error_mode = error_mode
         self.incremental_update = incremental_update
@@ -36,8 +35,8 @@ async def fetch_cves(self):
         """Fetches PURL2CPE database and places it in purl2cpe_path."""
         LOGGER.info("Getting PURL2CPE data...")
 
-        if not Path(self.purl2cpe_path).exists():
-            Path(self.purl2cpe_path).mkdir()
+        if not self.purl2cpe_path.exists():
+            self.purl2cpe_path.mkdir()
 
         if not self.session:
             connector = aiohttp.TCPConnector(limit_per_host=10)

cve_bin_tool/data_sources/redhat_source.py

@@ -3,7 +3,6 @@
 
 import datetime
 import json
-from pathlib import Path
 
 import aiohttp
 
@@ -28,7 +27,7 @@ def __init__(
         self, error_mode: ErrorMode = ErrorMode.TruncTrace, incremental_update=False
     ):
         self.cachedir = self.CACHEDIR
-        self.redhat_path = str(Path(self.cachedir) / "redhat")
+        self.redhat_path = self.cachedir / "redhat"
         self.source_name = self.SOURCE
 
         self.error_mode = error_mode
@@ -57,7 +56,7 @@ async def store_data(self, content):
         """Asynchronously stores CVE data in separate JSON files, excluding entries without a CVE ID."""
         for c in content:
             if c["CVE"] != "":
-                filepath = Path(self.redhat_path) / (str(c["CVE"]) + ".json")
+                filepath = self.redhat_path / (str(c["CVE"]) + ".json")
                 r = json.dumps(c)
                 async with FileIO(filepath, "w") as f:
                     await f.write(r)
@@ -73,8 +72,8 @@ async def fetch_cves(self):
 
         self.db = cvedb.CVEDB()
 
-        if not Path(self.redhat_path).exists():
-            Path(self.redhat_path).mkdir()
+        if not self.redhat_path.exists():
+            self.redhat_path.mkdir()
             # As no data, force full update
             self.incremental_update = False
 
@@ -121,7 +120,7 @@ async def fetch_cves(self):
     async def update_cve_entries(self):
         """Updates CVE entries from CVEs in cache."""
 
-        p = Path(self.redhat_path).glob("**/*")
+        p = self.redhat_path.glob("**/*")
         # Need to find files which are new to the cache
         last_update_timestamp = (
             self.time_of_last_update.timestamp()

cve_bin_tool/data_sources/rsd_source.py

@@ -8,7 +8,6 @@
 import io
 import json
 import zipfile
-from pathlib import Path
 
 import aiohttp
 from cvss import CVSS2, CVSS3
@@ -36,7 +35,7 @@ def __init__(
         self, error_mode: ErrorMode = ErrorMode.TruncTrace, incremental_update=False
     ):
         self.cachedir = self.CACHEDIR
-        self.rsd_path = str(Path(self.cachedir) / "rsd")
+        self.rsd_path = self.cachedir / "rsd"
         self.source_name = self.SOURCE
 
         self.error_mode = error_mode
@@ -71,8 +70,8 @@ async def fetch_cves(self):
 
         self.db = cvedb.CVEDB()
 
-        if not Path(self.rsd_path).exists():
-            Path(self.rsd_path).mkdir()
+        if not self.rsd_path.exists():
+            self.rsd_path.mkdir()
 
         if not self.session:
             connector = aiohttp.TCPConnector(limit_per_host=19)
@@ -133,7 +132,7 @@ async def fetch_cves(self):
     async def update_cve_entries(self):
         """Updates CVE entries from CVEs in cache."""
 
-        p = Path(self.rsd_path).glob("**/*")
+        p = self.rsd_path.glob("**/*")
         # Need to find files which are new to the cache
         last_update_timestamp = (
             self.time_of_last_update.timestamp()