Add pre-commit hooks

Author: mmalenic

.pre-commit-config.yaml

@@ -0,0 +1,20 @@
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.4.0
+    hooks:
+      - id: check-added-large-files
+        args: ["--maxkb=16384"]
+      - id: check-yaml
+
+  - repo: https://github.com/yelp/detect-secrets
+    rev: v1.4.0
+    hooks:
+      - id: detect-secrets
+        args:
+          ["--baseline", ".secrets.baseline"]
+        exclude: package.lock.json
+
+  - repo: https://github.com/psf/black-pre-commit-mirror
+    rev: 23.9.0
+    hooks:
+      - id: black-jupyter

.secrets.baseline

@@ -0,0 +1,112 @@
+{
+  "version": "1.4.0",
+  "plugins_used": [
+    {
+      "name": "ArtifactoryDetector"
+    },
+    {
+      "name": "AWSKeyDetector"
+    },
+    {
+      "name": "AzureStorageKeyDetector"
+    },
+    {
+      "name": "Base64HighEntropyString",
+      "limit": 4.5
+    },
+    {
+      "name": "BasicAuthDetector"
+    },
+    {
+      "name": "CloudantDetector"
+    },
+    {
+      "name": "DiscordBotTokenDetector"
+    },
+    {
+      "name": "GitHubTokenDetector"
+    },
+    {
+      "name": "HexHighEntropyString",
+      "limit": 3.0
+    },
+    {
+      "name": "IbmCloudIamDetector"
+    },
+    {
+      "name": "IbmCosHmacDetector"
+    },
+    {
+      "name": "JwtTokenDetector"
+    },
+    {
+      "name": "KeywordDetector",
+      "keyword_exclude": ""
+    },
+    {
+      "name": "MailchimpDetector"
+    },
+    {
+      "name": "NpmDetector"
+    },
+    {
+      "name": "PrivateKeyDetector"
+    },
+    {
+      "name": "SendGridDetector"
+    },
+    {
+      "name": "SlackDetector"
+    },
+    {
+      "name": "SoftlayerDetector"
+    },
+    {
+      "name": "SquareOAuthDetector"
+    },
+    {
+      "name": "StripeDetector"
+    },
+    {
+      "name": "TwilioKeyDetector"
+    }
+  ],
+  "filters_used": [
+    {
+      "path": "detect_secrets.filters.allowlist.is_line_allowlisted"
+    },
+    {
+      "path": "detect_secrets.filters.common.is_ignored_due_to_verification_policies",
+      "min_level": 2
+    },
+    {
+      "path": "detect_secrets.filters.heuristic.is_indirect_reference"
+    },
+    {
+      "path": "detect_secrets.filters.heuristic.is_likely_id_string"
+    },
+    {
+      "path": "detect_secrets.filters.heuristic.is_lock_file"
+    },
+    {
+      "path": "detect_secrets.filters.heuristic.is_not_alphanumeric_string"
+    },
+    {
+      "path": "detect_secrets.filters.heuristic.is_potential_uuid"
+    },
+    {
+      "path": "detect_secrets.filters.heuristic.is_prefixed_with_dollar_sign"
+    },
+    {
+      "path": "detect_secrets.filters.heuristic.is_sequential_string"
+    },
+    {
+      "path": "detect_secrets.filters.heuristic.is_swagger_file"
+    },
+    {
+      "path": "detect_secrets.filters.heuristic.is_templated_secret"
+    }
+  ],
+  "results": {},
+  "generated_at": "2023-09-10T23:08:58Z"
+}

prepare/downloader.py

@@ -8,7 +8,9 @@ class Downloader:
     Downloads data from a url or bucket.
     """
 
-    def __init__(self, url: str, prefix: str = "", mode: Literal["url", "s3"] = "url") -> None:
+    def __init__(
+        self, url: str, prefix: str = "", mode: Literal["url", "s3"] = "url"
+    ) -> None:
         """
         Initialize this class.
 
@@ -29,7 +31,6 @@ def download(self, name: str, save_to: Optional[str | Path] = None) -> str | Non
 
         :return: return the downloaded data or None if saving.
         """
-
         if self.mode == "url":
             if save_to is None:
                 with urllib.request.urlopen(self.url + self.prefix + name) as f:
@@ -39,7 +40,9 @@ def download(self, name: str, save_to: Optional[str | Path] = None) -> str | Non
         else:
             raise NotImplementedError
 
-    def get_or_download(self, output_dir: str, name: str, read_data: bool = True) -> str | None:
+    def get_or_download(
+        self, output_dir: str, name: str, read_data: bool = True
+    ) -> str | None:
         """
         Get the data from the output_dir or download and save it to the output directory.
 

prepare/prepare_serve.py

@@ -15,7 +15,11 @@ class PrepareServe:
 
     _data: dict[str, str] = {}
 
-    def __init__(self, url: str = "https://storage.googleapis.com/hmf-public/HMFtools-Resources/serve/38/", output_dir: str = "data/serve/") -> None:
+    def __init__(
+        self,
+        url: str = "https://storage.googleapis.com/hmf-public/HMFtools-Resources/serve/38/",
+        output_dir: str = "data/serve/",
+    ) -> None:
         """
         Initialize this class.
 

prepare/prepare_software.py

@@ -9,8 +9,11 @@ class PrepareSoftware:
     _protect_jar = "protect-v2.3/protect.jar"
     _linx_jar = "linx-v1.21/linx_v1.21.jar"
 
-    def __init__(self, url: str = "https://github.com/hartwigmedical/hmftools/releases/download/",
-                 output_dir: str = "data/software/") -> None:
+    def __init__(
+        self,
+        url: str = "https://github.com/hartwigmedical/hmftools/releases/download/",
+        output_dir: str = "data/software/",
+    ) -> None:
         """
         Initialize this class.