Add and update commit frequency metrics (#173)

* add and update commit frequency metrics * docs formatting * correct the counting of files * fix cli test * update count_files Co-Authored-By: Faisal Alquaddoomi <[email protected]> * include commit date unified w/ files in test repos Co-Authored-By: Faisal Alquaddoomi <[email protected]> * fix docs test * linting --------- Co-authored-by: Faisal Alquaddoomi <[email protected]>
software-gardening · Nov 21, 2024 · c06376b · c06376b
1 parent c6cc135
commit c06376b
Show file tree

Hide file tree

Showing 10 changed files with 473 additions and 166 deletions.
diff --git a/pyproject.toml b/pyproject.toml
@@ -75,7 +75,6 @@ root = "."
 [tool.ruff]
 target-version = "py311"
 fix = true
-
 lint.select = [
   # mccabe
   "C90",

diff --git a/src/almanack/git.py b/src/almanack/git.py
@@ -4,7 +4,7 @@
 
 import pathlib
 import tempfile
-from typing import Dict, List, Optional
+from typing import Dict, List, Optional, Union
 
 import pygit2
 from charset_normalizer import from_bytes
@@ -42,9 +42,8 @@ def get_commits(repo: pygit2.Repository) -> List[pygit2.Commit]:
     # Get the latest commit (HEAD) from the repository
     head = repo.revparse_single("HEAD")
     # Create a walker to iterate over commits starting from the HEAD
-    walker = repo.walk(
-        head.id, pygit2.enums.SortMode.NONE
-    )  #  SortMode.NONE traverses commits in natural order; no sorting applied.
+    # sorting by time.
+    walker = repo.walk(head.id, pygit2.GIT_SORT_TIME)
     # Collect all commits from the walker into a list
     commits = list(walker)
     return commits
@@ -147,14 +146,6 @@ def get_most_recent_commits(repo_path: pathlib.Path) -> tuple[str, str]:
     return str(source_commit.id), str(target_commit.id)
 
 
-"""
-Module for handling various tasks with git repo blobs.
-"""
-
-
-import pygit2
-
-
 def detect_encoding(blob_data: bytes) -> str:
     """
     Detect the encoding of the given blob data using charset-normalizer.
@@ -227,6 +218,34 @@ def find_file(
     return found_entry
 
 
+def count_files(tree: Union[pygit2.Tree, pygit2.Blob]) -> int:
+    """
+    Counts all files (Blobs) within a Git tree, including files
+    in subdirectories.
+
+    This function recursively traverses the provided `tree`
+    object to count each file, represented as a `pygit2.Blob`,
+    within the tree and any nested subdirectories.
+
+    Args:
+        tree (Union[pygit2.Tree, pygit2.Blob]):
+            The Git tree object (of type `pygit2.Tree`)
+            to traverse and count files. The initial call
+            should be made with the root tree of a commit.
+
+    Returns:
+        int:
+            The total count of files (Blobs) within the tree,
+            including nested files in subdirectories.
+    """
+    if isinstance(tree, pygit2.Blob):
+        # Directly return 1 if the input is a Blob
+        return 1
+    elif isinstance(tree, pygit2.Tree):
+        # Recursively count files for Tree
+        return sum(count_files(entry) for entry in tree)
+
+
 def read_file(
     repo: pygit2.Repository,
     entry: Optional[pygit2.Object] = None,

diff --git a/src/almanack/metrics/data.py b/src/almanack/metrics/data.py
@@ -11,7 +11,14 @@
 import pygit2
 import yaml
 
-from ..git import clone_repository, find_file, get_commits, get_edited_files, read_file
+from ..git import (
+    clone_repository,
+    count_files,
+    find_file,
+    get_commits,
+    get_edited_files,
+    read_file,
+)
 from .entropy.calculate_entropy import (
     calculate_aggregate_entropy,
     calculate_normalized_entropy,
@@ -195,6 +202,41 @@ def default_branch_is_not_master(repo: pygit2.Repository) -> bool:
         return repo.head.shorthand != "master"
 
 
+def days_of_development(repo: pygit2.Repository) -> float:
+    """
+
+
+    Args:
+        repo (pygit2.Repository): Path to the git repository.
+
+    Returns:
+        float: The average number of commits per day over the period of time.
+    """
+    try:
+        # Try to get the HEAD commit. If it raises an error, there are no commits.
+        repo.revparse_single("HEAD")
+    except KeyError:
+        # If HEAD doesn't exist (repo is empty), return 0 commits.
+        return 0
+
+    # Traverse the commit history and collect commit dates
+    commit_dates = [
+        datetime.fromtimestamp(commit.commit_time).date()
+        for commit in repo.walk(repo.head.target, pygit2.GIT_SORT_TIME)
+    ]
+
+    # If no commits, return 0
+    if not commit_dates:
+        return 0
+
+    # Calculate the number of days between the first and last commit
+    # +1 to include the first day
+    total_days = (max(commit_dates) - min(commit_dates)).days + 1
+
+    # Return the average commits per day
+    return total_days
+
+
 def includes_common_docs(repo: pygit2.Repository) -> bool:
     """
     Check whether the repo includes common documentation files and directories
@@ -244,74 +286,75 @@ def compute_repo_data(repo_path: str) -> None:
     Returns:
         dict: A dictionary containing data key-pairs.
     """
-    try:
-        # Convert repo_path to an absolute path and initialize the repository
-        repo_path = pathlib.Path(repo_path).resolve()
-        repo = pygit2.Repository(str(repo_path))
-
-        # Retrieve the list of commits from the repository
-        commits = get_commits(repo)
-        most_recent_commit = commits[0]
-        first_commit = commits[-1]
-
-        # Get a list of files that have been edited between the first and most recent commit
-        file_names = get_edited_files(repo, first_commit, most_recent_commit)
-
-        # Calculate the normalized total entropy for the repository
-        normalized_total_entropy = calculate_aggregate_entropy(
-            repo_path,
-            str(first_commit.id),
-            str(most_recent_commit.id),
-            file_names,
-        )
-
-        # Calculate the normalized entropy for the changes between the first and most recent commits
-        file_entropy = calculate_normalized_entropy(
-            repo_path,
-            str(first_commit.id),
-            str(most_recent_commit.id),
-            file_names,
-        )
-        # Convert commit times to UTC datetime objects, then format as date strings.
-        first_commit_date, most_recent_commit_date = (
-            datetime.fromtimestamp(commit.commit_time, tz=timezone.utc)
-            .date()
-            .isoformat()
-            for commit in (first_commit, most_recent_commit)
-        )
-
-        # Return the data structure
-        return {
-            "repo-path": str(repo_path),
-            "repo-commits": len(commits),
-            "repo-file-count": len(file_names),
-            "repo-commit-time-range": (first_commit_date, most_recent_commit_date),
-            "repo-includes-readme": file_exists_in_repo(
-                repo=repo,
-                expected_file_name="readme",
-            ),
-            "repo-includes-contributing": file_exists_in_repo(
-                repo=repo,
-                expected_file_name="contributing",
-            ),
-            "repo-includes-code-of-conduct": file_exists_in_repo(
-                repo=repo,
-                expected_file_name="code_of_conduct",
-            ),
-            "repo-includes-license": file_exists_in_repo(
-                repo=repo,
-                expected_file_name="license",
-            ),
-            "repo-is-citable": is_citable(repo=repo),
-            "repo-default-branch-not-master": default_branch_is_not_master(repo=repo),
-            "repo-includes-common-docs": includes_common_docs(repo=repo),
-            "repo-agg-info-entropy": normalized_total_entropy,
-            "repo-file-info-entropy": file_entropy,
-        }
-
-    except Exception as e:
-        # If processing fails, return an error dictionary
-        return {"repo_path": str(repo_path), "error": str(e)}
+    # Convert repo_path to an absolute path and initialize the repository
+    repo_path = pathlib.Path(repo_path).resolve()
+    repo = pygit2.Repository(str(repo_path))
+
+    # Retrieve the list of commits from the repository
+    commits = get_commits(repo)
+    most_recent_commit = commits[0]
+    first_commit = commits[-1]
+
+    # Get a list of files that have been edited between the first and most recent commit
+    edited_file_names = get_edited_files(repo, first_commit, most_recent_commit)
+
+    # Calculate the normalized total entropy for the repository
+    normalized_total_entropy = calculate_aggregate_entropy(
+        repo_path,
+        str(first_commit.id),
+        str(most_recent_commit.id),
+        edited_file_names,
+    )
+
+    # Calculate the normalized entropy for the changes between the first and most recent commits
+    file_entropy = calculate_normalized_entropy(
+        repo_path,
+        str(first_commit.id),
+        str(most_recent_commit.id),
+        edited_file_names,
+    )
+    # Convert commit times to UTC datetime objects, then format as date strings.
+    first_commit_date, most_recent_commit_date = (
+        datetime.fromtimestamp(commit.commit_time).date()
+        for commit in (first_commit, most_recent_commit)
+    )
+
+    # Return the data structure
+    return {
+        "repo-path": str(repo_path),
+        "repo-commits": (commits_count := len(commits)),
+        "repo-file-count": count_files(tree=most_recent_commit.tree),
+        "repo-commit-time-range": (
+            first_commit_date.isoformat(),
+            most_recent_commit_date.isoformat(),
+        ),
+        "repo-days-of-development": (
+            days_of_development := (most_recent_commit_date - first_commit_date).days
+            + 1
+        ),
+        "repo-commits-per-day": commits_count / days_of_development,
+        "repo-includes-readme": file_exists_in_repo(
+            repo=repo,
+            expected_file_name="readme",
+        ),
+        "repo-includes-contributing": file_exists_in_repo(
+            repo=repo,
+            expected_file_name="contributing",
+        ),
+        "repo-includes-code-of-conduct": file_exists_in_repo(
+            repo=repo,
+            expected_file_name="code_of_conduct",
+        ),
+        "repo-includes-license": file_exists_in_repo(
+            repo=repo,
+            expected_file_name="license",
+        ),
+        "repo-is-citable": is_citable(repo=repo),
+        "repo-default-branch-not-master": default_branch_is_not_master(repo=repo),
+        "repo-includes-common-docs": includes_common_docs(repo=repo),
+        "repo-agg-info-entropy": normalized_total_entropy,
+        "repo-file-info-entropy": file_entropy,
+    }
 
 
 def compute_pr_data(repo_path: str, pr_branch: str, main_branch: str) -> Dict[str, Any]:

diff --git a/src/almanack/metrics/metrics.yml b/src/almanack/metrics/metrics.yml
@@ -20,6 +20,18 @@ metrics:
     result-type: "tuple"
     description: >-
       Starting commit and most recent commit for the repository.
+  - name: "repo-days-of-development"
+    id: "SGA-META-0005"
+    result-type: "int"
+    description: >-
+      Integer representing the number of days of development
+      between most recent commit and first commit.
+  - name: "repo-commits-per-day"
+    id: "SGA-META-0006"
+    result-type: "float"
+    description: >-
+      Floating point number which represents the number of commits
+      per day (using days of development).
   - name: "repo-includes-readme"
     id: "SGA-GL-0001"
     result-type: "bool"

diff --git a/tests/conftest.py b/tests/conftest.py
@@ -118,12 +118,16 @@ def community_health_repository_path(tmp_path_factory):
 
     yield repo_setup(
         repo_path=pathlib.Path(temp_dir),
-        files={
-            "README.md": "# This is an example readme\n\nWelcome to our repo!",
-            "CONTRIBUTING.md": "# This is a stub for a CONTRIBUTING.md",
-            "CODE_OF_CONDUCT.md": "# This is a stub for a CODE_OF_CONDUCT.md",
-            "LICENSE.txt": "This is an example LICENSE file.",
-        },
+        files=[
+            {
+                "files": {
+                    "README.md": "# This is an example readme\n\nWelcome to our repo!",
+                    "CONTRIBUTING.md": "# This is a stub for a CONTRIBUTING.md",
+                    "CODE_OF_CONDUCT.md": "# This is a stub for a CODE_OF_CONDUCT.md",
+                    "LICENSE.txt": "This is an example LICENSE file.",
+                }
+            }
+        ],
     )