Renaming to git-analytics-sqlite + adding overall feature

README.md

@@ -1,26 +1,44 @@
-# Git-Analytics
 
-[![PyPI](https://img.shields.io/pypi/v/git-analytics.svg?color=green)](https://pypi.org/project/git-analytics/)
-[![Python Versions](https://img.shields.io/pypi/pyversions/git-analytics.svg)](https://pypi.org/project/git-analytics/)
-[![code quality check](https://github.com/n0rfas/git-analytics/actions/workflows/code-check-dev.yml/badge.svg?branch=dev)](https://github.com/n0rfas/git-analytics/tree/dev)
-[![python versions check](https://github.com/n0rfas/git-analytics/actions/workflows/python-matrix-main.yml/badge.svg?branch=main)](https://github.com/n0rfas/git-analytics/tree/main)
-
-The detailed analysis tool for git repositories.
+The detailed analysis tool for git repositories - forked version from [here](https://github.com/n0rfas/git-analytics) with SQLite acting as the data store to provide better experience.
 
 ## Installation
 
 The latest stable version can be installed directly from PyPI:
 
 ```sh
-pip install git-analytics
+pip install git-analytics-sqlite
 ```
 
 ## Usage
 
-To run, enter the command and open the browser at [http://localhost:8000/](http://localhost:8000/).
+Run from inside any git repository, then open [http://localhost:8000/](http://localhost:8000/) in your browser:
+
+```sh
+git-analytics-sqlite
+```
+
+On first launch the dashboard will show a **Scan repository** button. Click it to parse the git history and populate the local database. Subsequent launches load instantly from the cached data. Use the **Scan** button in the header at any time to pick up new commits.
+
+### SQLite database
+
+Commit data is stored in a per-repository SQLite database under your platform's user data directory:
+
+| Platform | Location |
+|----------|----------|
+| Linux    | `~/.local/share/git-analytics/<repo>/<repo>_<hash>.db` |
+| macOS    | `~/Library/Application Support/git-analytics/<repo>/<repo>_<hash>.db` |
+| Windows  | `%APPDATA%\git-analytics\<repo>\<repo>_<hash>.db` |
+
+The `<hash>` is a short fingerprint of the repository's full path, so two repositories with the same folder name never share a database.
+
+Use the folder icon button in the header to open the database directory in your file manager.
+
+### Custom database path
+
+Pass `--db` to override the default location:
 
 ```sh
-git-analytics
+git-analytics-sqlite --db /path/to/my.db
 ```
 
 ## Screenshots
@@ -38,7 +56,20 @@ poetry install --with dev
 ### Running
 
 ```bash
-poetry run git-analytics
+poetry run git-analytics-sqlite
+```
+
+### Building
+
+```bash
+poetry build
+# produces dist/git_analytics-<version>-py3-none-any.whl
+```
+
+Install the built wheel directly with pip:
+
+```bash
+pip install dist/git_analytics-*.whl
 ```
 
 ### Tests

git_analytics/main.py

@@ -1,8 +1,8 @@
+import argparse
 import os
+from pathlib import Path
 from wsgiref.simple_server import make_server
 
-from git import InvalidGitRepositoryError, Repo
-
 from git_analytics.analyzers import (
     AuthorsStatisticsAnalyzer,
     CommitsSummaryAnalyzer,
@@ -12,7 +12,7 @@
     LinesAnalyzer,
 )
 from git_analytics.engine import CommitAnalyticsEngine, FileAnalyticsEngine
-from git_analytics.sources import GitCommitSource
+from git_analytics.sources import SqliteCommitSource, repo_db_path
 from git_analytics.web_app import create_web_app
 
 
@@ -28,23 +28,27 @@ def make_analyzers():
 
 
 def run():
-    try:
-        path_repo = os.getenv("PATH_REPO", ".")
-        repo = Repo(path_repo)
-        name_branch = repo.active_branch.name
-    except InvalidGitRepositoryError:
-        print("Error: Current directory is not a git repository.")
-        return
+    parser = argparse.ArgumentParser(prog="git-analytics")
+    parser.add_argument(
+        "--db",
+        metavar="PATH",
+        help="path to SQLite database (default: user data directory)",
+    )
+    args = parser.parse_args()
 
-    extension_stats = FileAnalyticsEngine().run()
+    path_repo = os.getenv("PATH_REPO", ".")
+    db_path = Path(args.db) if args.db else repo_db_path(path_repo)
+
+    repo = _try_get_repo(path_repo)
+    additional_data = _build_additional_data(repo)
 
     engine = CommitAnalyticsEngine(
-        source=GitCommitSource(repo),
+        source=SqliteCommitSource(db_path),
         analyzers_factory=make_analyzers,
-        additional_data={"name_branch": name_branch, "extension_stats": extension_stats},
+        additional_data=additional_data,
     )
 
-    web_app = create_web_app(engine=engine)
+    web_app = create_web_app(engine=engine, db_path=db_path, repo=repo)
 
     with make_server("", 8000, web_app) as httpd:
         print("Web service started at http://localhost:8000/")
@@ -58,5 +62,27 @@ def run():
             print("Web service stopped")
 
 
+def _try_get_repo(path: str):
+    try:
+        from git import InvalidGitRepositoryError, Repo
+        return Repo(path)
+    except Exception:
+        return None
+
+
+def _build_additional_data(repo):
+    data = {}
+    if repo is not None:
+        try:
+            data["name_branch"] = repo.active_branch.name
+        except Exception:
+            pass
+    try:
+        data["extension_stats"] = FileAnalyticsEngine().run()
+    except Exception:
+        pass
+    return data
+
+
 if __name__ == "__main__":
     run()

git_analytics/sources/__init__.py

@@ -1,7 +1,11 @@
 from .git_commit_adapter import GitCommitSource
 from .git_log_adapter import GitLogSource
+from .sqlite_commit_source import SqliteCommitSource, populate_sqlite, repo_db_path
 
 __all__ = [
     "GitCommitSource",
     "GitLogSource",
+    "SqliteCommitSource",
+    "populate_sqlite",
+    "repo_db_path",
 ]

git_analytics/sources/sqlite_commit_source.py

@@ -0,0 +1,115 @@
+import hashlib
+import os
+import sqlite3
+import sys
+from datetime import datetime
+from pathlib import Path
+from typing import Iterator
+
+from git_analytics.entities import AnalyticsCommit, FileChangeStats
+from git_analytics.interfaces import CommitSource
+
+
+def user_data_dir() -> Path:
+    if sys.platform == "win32":
+        base = Path(os.environ.get("APPDATA", Path.home()))
+    elif sys.platform == "darwin":
+        base = Path.home() / "Library" / "Application Support"
+    else:
+        base = Path(os.environ.get("XDG_DATA_HOME", Path.home() / ".local" / "share"))
+    return base / "git-analytics"
+
+
+def repo_db_path(repo_path: str = ".") -> Path:
+    full_path = str(Path(repo_path).resolve())
+    name = Path(full_path).name
+    path_hash = hashlib.sha1(full_path.encode()).hexdigest()[:8]
+    return user_data_dir() / name / f"{name}_{path_hash}.db"
+
+
+_CREATE_COMMITS = """
+CREATE TABLE IF NOT EXISTS commits (
+    sha                TEXT PRIMARY KEY,
+    commit_author       TEXT NOT NULL,
+    committed_datetime  TEXT NOT NULL,
+    lines_insertions    INTEGER NOT NULL,
+    lines_deletions     INTEGER NOT NULL,
+    files_changed       INTEGER NOT NULL,
+    message             TEXT NOT NULL
+)
+"""
+
+_CREATE_COMMIT_FILES = """
+CREATE TABLE IF NOT EXISTS commit_files (
+    sha         TEXT NOT NULL REFERENCES commits(sha),
+    filepath    TEXT NOT NULL,
+    insertions  INTEGER NOT NULL,
+    deletions   INTEGER NOT NULL
+)
+"""
+
+
+def populate_sqlite(source: CommitSource, db_path: Path) -> None:
+    db_path.parent.mkdir(parents=True, exist_ok=True)
+    conn = sqlite3.connect(db_path)
+    try:
+        conn.execute(_CREATE_COMMITS)
+        conn.execute(_CREATE_COMMIT_FILES)
+        with conn:
+            for commit in source.iter_commits():
+                conn.execute(
+                    "INSERT OR REPLACE INTO commits VALUES (?,?,?,?,?,?,?)",
+                    (
+                        commit.sha,
+                        commit.commit_author,
+                        commit.committed_datetime.isoformat(),
+                        commit.lines_insertions,
+                        commit.lines_deletions,
+                        commit.files_changed,
+                        commit.message,
+                    ),
+                )
+                for filepath, stats in commit.files.items():
+                    conn.execute(
+                        "INSERT INTO commit_files VALUES (?,?,?,?)",
+                        (commit.sha, filepath, stats.insertions, stats.deletions),
+                    )
+    finally:
+        conn.close()
+
+
+class SqliteCommitSource(CommitSource):
+    def __init__(self, db_path: Path) -> None:
+        self._db_path = db_path
+
+    def iter_commits(self) -> Iterator[AnalyticsCommit]:
+        conn = sqlite3.connect(self._db_path)
+        try:
+            rows = conn.execute(
+                "SELECT sha, commit_author, committed_datetime, lines_insertions, "
+                "lines_deletions, files_changed, message "
+                "FROM commits ORDER BY committed_datetime DESC"
+            ).fetchall()
+
+            for row in rows:
+                sha, author, dt_str, insertions, deletions, files_changed, message = row
+                files_rows = conn.execute(
+                    "SELECT filepath, insertions, deletions FROM commit_files WHERE sha=?",
+                    (sha,),
+                ).fetchall()
+                files = {
+                    filepath: FileChangeStats(insertions=ins, deletions=dels)
+                    for filepath, ins, dels in files_rows
+                }
+                yield AnalyticsCommit(
+                    sha=sha,
+                    commit_author=author,
+                    committed_datetime=datetime.fromisoformat(dt_str),
+                    lines_insertions=insertions,
+                    lines_deletions=deletions,
+                    files_changed=files_changed,
+                    message=message,
+                    files=files,
+                )
+        finally:
+            conn.close()

git_analytics/static/index.html

@@ -27,13 +27,21 @@
                 <img src="favicon.svg" alt="Logo" width="32" height="32" class="me-2">
                 <h1 class="h4 mb-0">Git-Analytics</h1>
             </div>
-            <div>
+            <div class="d-flex align-items-center gap-2">
                 <a href="https://git-analytics.com" target="_blank" class="btn btn-outline-light">
                     <i class="bi bi-link-45deg"></i> Site
                 </a>
                 <a href="https://github.com/n0rfas/git-analytics"  target="_blank"  class="btn btn-outline-light">
                     <i class="bi bi-github"></i> GitHub
                 </a>
+                <button id="scanBtn" class="btn btn-success d-none" onclick="scanRepository()">
+                    <i class="bi bi-arrow-repeat" id="scanIcon"></i> Scan
+                </button>
+                <button id="openFolderBtn" class="btn btn-outline-light d-none"
+                        title="" onclick="openDbFolder()" style="font-size:0.8rem;">
+                    <i class="bi bi-folder2-open"></i>
+                    <span id="dbFolderLabel" class="ms-1"></span>
+                </button>
             </div>
             <div class="d-flex align-items-center gap-2">
                 <div class="dropdown">
@@ -68,6 +76,19 @@ <h1 class="h4 mb-0">Git-Analytics</h1>
         <!-- content -->
         <main class="flex-grow-1 p-3">
             <div class="container">
+                <!-- first-run banner, shown when DB has no data -->
+                <div id="noDataBanner" class="d-none mb-4">
+                    <div class="card border-warning">
+                        <div class="card-body text-center py-5">
+                            <i class="bi bi-database-x display-4 text-warning mb-3 d-block"></i>
+                            <h4>No data yet</h4>
+                            <p class="text-muted mb-4">Scan your repository to populate the database and view analytics.</p>
+                            <button class="btn btn-success btn-lg" onclick="scanRepository()">
+                                <i class="bi bi-arrow-repeat"></i> Scan repository
+                            </button>
+                        </div>
+                    </div>
+                </div>
                 <section class="view" data-view="overview">
                     <div class="row">
                         <div class="col-md-12 mb-3">
@@ -382,5 +403,17 @@ <h2>Commits</h2>
         </div>
     </div>
 
+    <!-- Scanning Modal -->
+    <div class="modal" id="scanningModal" tabindex="-1" aria-hidden="true" data-bs-backdrop="static" data-bs-keyboard="false">
+        <div class="modal-dialog modal-dialog-centered">
+            <div class="modal-content text-center">
+                <div class="modal-body">
+                    <div class="spinner-border text-success mb-3" role="status"></div>
+                    <p class="mb-0"><strong>Scanning repository. This may take a moment...</strong></p>
+                </div>
+            </div>
+        </div>
+    </div>
+
 </body>
 </html>