add pre-commit

.gitignore

@@ -172,4 +172,3 @@ cython_debug/
 
 .vscode/
 polyglot_data/
-

.pre-commit-config.yaml

@@ -0,0 +1,19 @@
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.1.0 # Use the ref you want to point at
+    hooks:
+      - id: check-added-large-files
+        args: ["--maxkb=1024"] # throw an error if we try to commit a 1MB or greater file
+      - id: check-case-conflict # so we don't rename files that will break case insensitive filesystems
+      - id: check-merge-conflict # don't accidentally commit files with incomplete merges
+      - id: end-of-file-fixer # makes all files end in a newline
+      - id: mixed-line-ending # fixes mixed line endings automatically
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    # Ruff version.
+    rev: v0.6.2
+    hooks:
+      # Run the linter.
+      - id: ruff
+        args: [--fix]
+      # Run the formatter.
+      - id: ruff-format

Makefile

@@ -60,4 +60,4 @@ help:
 	@python -c "${PRINT_HELP_PYSCRIPT}" < $(MAKEFILE_LIST)
 
 api:
-	fastapi dev labs/api/main.py  
+	fastapi dev labs/api/main.py  

docker-compose.yml

@@ -31,4 +31,4 @@ services:
 
 
 volumes:
-  db-data: { }
+  db-data: { }

environment.yml

@@ -13,4 +13,4 @@ dependencies:
   - pip:
     - python-dotenv
     - awscli
-    - -e .
+    - -e .

labs/fnmatch.py

@@ -9,14 +9,16 @@
 The function translate(PATTERN) returns a regular expression
 corresponding to PATTERN.  (It does not compile it.)
 """
+
 import os
 import os.path
 import posixpath
 import re
-#import functools
+# import functools
 
 __all__ = ["filter", "fnmatch", "fnmatchcase", "translate"]
 
+
 def fnmatch(name, pat):
     """Test whether FILENAME matches PATTERN.
 
@@ -36,16 +38,18 @@ def fnmatch(name, pat):
     pat = os.path.normcase(pat)
     return fnmatchcase(name, pat)
 
-#@functools.lru_cache(maxsize=256, typed=True)
+
+# @functools.lru_cache(maxsize=256, typed=True)
 def _compile_pattern(pat):
     if isinstance(pat, bytes):
-        pat_str = str(pat, 'ISO-8859-1')
+        pat_str = str(pat, "ISO-8859-1")
         res_str = translate(pat_str)
-        res = bytes(res_str, 'ISO-8859-1')
+        res = bytes(res_str, "ISO-8859-1")
     else:
         res = translate(pat)
     return re.compile(res).match
 
+
 def filter(names, pat):
     """Return the subset of the list NAMES that match PAT."""
     result = []
@@ -62,6 +66,7 @@ def filter(names, pat):
                 result.append(name)
     return result
 
+
 def fnmatchcase(name, pat):
     """Test whether FILENAME matches PATTERN, including case.
 
@@ -79,33 +84,33 @@ def translate(pat):
     """
 
     i, n = 0, len(pat)
-    res = ''
+    res = ""
     while i < n:
         c = pat[i]
-        i = i+1
-        if c == '*':
-            res = res + '.*'
-        elif c == '?':
-            res = res + '.'
-        elif c == '[':
+        i = i + 1
+        if c == "*":
+            res = res + ".*"
+        elif c == "?":
+            res = res + "."
+        elif c == "[":
             j = i
-            if j < n and pat[j] == '!':
-                j = j+1
-            if j < n and pat[j] == ']':
-                j = j+1
-            while j < n and pat[j] != ']':
-                j = j+1
+            if j < n and pat[j] == "!":
+                j = j + 1
+            if j < n and pat[j] == "]":
+                j = j + 1
+            while j < n and pat[j] != "]":
+                j = j + 1
             if j >= n:
-                res = res + '\\['
+                res = res + "\\["
             else:
-                stuff = pat[i:j].replace('\\','\\\\')
-                i = j+1
-                if stuff[0] == '!':
-                    stuff = '^' + stuff[1:]
-                elif stuff[0] == '^':
-                    stuff = '\\' + stuff
-                res = '%s[%s]' % (res, stuff)
+                stuff = pat[i:j].replace("\\", "\\\\")
+                i = j + 1
+                if stuff[0] == "!":
+                    stuff = "^" + stuff[1:]
+                elif stuff[0] == "^":
+                    stuff = "\\" + stuff
+                res = "%s[%s]" % (res, stuff)
         else:
             res = res + re.escape(c)
     # Original patterns is undefined, see http://bugs.python.org/issue21464
-    return '(?ms)' + res + '\Z'
+    return "(?ms)" + res + "\Z"

labs/github/github.py

@@ -13,7 +13,6 @@ class GithubRequests:
     """Class to handle Github API requests"""
 
     def __init__(self, github_token, repo_owner, repo_name, user_name=None):
-
         self.github_token = github_token
         self.repo_owner = repo_owner
         self.repo_name = repo_name
@@ -142,7 +141,6 @@ def commit_changes(self, message, branch_name, files):
 
         tree_items = []
         for file_path in files:
-
             file_name = file_path.replace(f"{self.directory_dir}/", "")
             # Step 3: Read the file content and encode it in Base64
             with open(file_path, "rb") as file:

labs/nlp.py

@@ -3,7 +3,7 @@
 import spacy
 
 # Do not remove this import as it is used for self.nlp.add_pipe("spacytextblob")
-from spacytextblob.spacytextblob import SpacyTextBlob
+from spacytextblob.spacytextblob import SpacyTextBlob  # noqa: F401
 from spacy.lang.en.stop_words import STOP_WORDS as stop_words_en
 from spacy.lang.pt.stop_words import STOP_WORDS as stop_words_pt
 from string import punctuation

labs/test/test_GithubRequests.py

@@ -4,10 +4,8 @@
 
 
 class TestGithubRequests:
-
     # Listing issues with default parameters returns open issues assigned to the user
     def test_list_issues_default_parameters(self, mocker):
-
         mock_get = mocker.patch("requests.get")
 
         sample_response = [
@@ -40,7 +38,6 @@ def test_list_issues_default_parameters(self, mocker):
         )
 
     def test_list_issues_http_failure(self, mocker):
-
         mock_response = mocker.Mock()
         mock_response.raise_for_status.side_effect = (
             requests.exceptions.RequestException("HTTP Error")
@@ -56,7 +53,6 @@ def test_list_issues_http_failure(self, mocker):
         assert issues == []
 
     def test_get_issue_returns_correct_details(self, mocker):
-
         mock_get = mocker.patch("requests.get")
 
         sample_response = {"id": 1, "title": "Sample Issue", "state": "open"}
@@ -81,7 +77,6 @@ def test_get_issue_returns_correct_details(self, mocker):
         )
 
     def test_handle_http_request_failure_get_issue(self, mocker):
-
         mock_response = mocker.Mock()
         mock_response.raise_for_status.side_effect = (
             requests.exceptions.RequestException("Mocked Request Exception")
@@ -97,7 +92,6 @@ def test_handle_http_request_failure_get_issue(self, mocker):
         assert issue is None
 
     def test_change_issue_status(self, mocker):
-
         mock_response = mocker.Mock()
         mock_response.json.return_value = {"status": "closed"}
         mocker.patch("requests.patch", return_value=mock_response)
@@ -111,7 +105,6 @@ def test_change_issue_status(self, mocker):
         assert response == {"status": "closed"}
 
     def test_commit_changes_successfully(self, mocker):
-
         mock_response_get = mocker.Mock()
         mock_response_get.status_code = 200
         mock_response_get.json.return_value = {
@@ -158,7 +151,6 @@ def test_commit_changes_successfully(self, mocker):
         assert result == {"sha": "fake_update_sha"}
 
     def test_create_pull_request_default_parameters(self, mocker):
-
         mock_response = mocker.Mock()
         expected_json = {"id": 123, "title": "New Pull Request"}
         mock_response.json.return_value = expected_json

labs/test/test_middleman.py

@@ -6,7 +6,6 @@
 
 
 class TestCallLlmWithContext:
-
     # Successfully calls the LLM with the provided context and returns the expected output
     @patch("middleman_functions.find_similar_embeddings")
     @patch.object(RequestLiteLLM, "completion_without_proxy")
@@ -15,7 +14,6 @@ class TestCallLlmWithContext:
     def test_successful_llm_call_with_context(
         self, mocked_agent, mocked_vectorized, mocked_completion, mocked_embeddings
     ):
-
         # Mocking dependencies
         mocked_embeddings.return_value = [["file1", "/path/to/file1", "content1"]]
         mocked_completion.return_value = (
@@ -35,7 +33,6 @@ def test_successful_llm_call_with_context(
     # Ensure the GithubModel is instantiated correctly with the correct parameters
 
     def test_empty_summary(self):
-
         github = GithubModel(github_token="token", repo_owner="owner", repo_name="repo")
         issue_summary = ""
         litellm_api_key = "fake_api_key"

middleman_functions.py

@@ -10,7 +10,9 @@ def call_llm_with_context(github: GithubModel, issue_summary, litellm_api_key):
         raise ValueError("issue_summary cannot be empty")
     litellm_requests = RequestLiteLLM(litellm_api_key)
     destination = f"/tmp/{github.repo_owner}/{github.repo_name}"
-    vectorize_to_db(f"https://github.com/{github.repo_owner}/{github.repo_name}", None, destination)
+    vectorize_to_db(
+        f"https://github.com/{github.repo_owner}/{github.repo_name}", None, destination
+    )
     # find_similar_embeddings narrows down codebase to files that matter for the issue at hand.
     context = find_similar_embeddings(issue_summary)
     prompt = f"""