pyvegh 0.7.0__tar.gz → 0.9.0__tar.gz

{pyvegh-0.7.0 → pyvegh-0.9.0}/Cargo.lock

@@ -540,7 +540,7 @@ dependencies = [
 
 [[package]]
 name = "pyvegh"
-version = "0.7.0"
+version = "0.9.0"
 dependencies = [
  "anyhow",
  "bincode",

{pyvegh-0.7.0 → pyvegh-0.9.0}/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "pyvegh"
-version = "0.7.0"
+version = "0.9.0"
 edition = "2024"
 authors = ["CodeTease"]
 readme = "README.md"

{pyvegh-0.7.0 → pyvegh-0.9.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pyvegh
-Version: 0.7.0
+Version: 0.9.0
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
@@ -49,13 +49,16 @@ It delivers the raw performance of Rust (Zstd multithreaded compression, Tar arc
 ## Installation
 
 Install directly from PyPI:
-```bash
+```shell
 pip install pyvegh
+
+# Or via uv
+uv pip install pyvegh
 ```
 
 Or build from source (requires Rust):
 
-```bash
+```shell
 maturin develop --release
 ```
 
@@ -67,7 +70,7 @@ PyVegh provides a powerful command-line interface via the `vegh` (or `pyvegh`) c
 
 Set up your default server URL and Auth Token so you don't have to type them every time.
 
-```bash
+```shell
 vegh config
 # Or one-liner:
 vegh config send --url https://api.teaserverse.online/test --auth YOUR_TOKEN
@@ -79,11 +82,21 @@ vegh config list
 vegh config reset
 ```
 
+**Advanced:** You can also configure custom `audit` patterns in `~/.vegh/config.json`:
+```json
+{
+  "audit": {
+    "patterns": ["custom_secret\\.key", ".*\\.private"],
+    "keywords": ["MY_API_KEY", "INTERNAL_TOKEN"]
+  }
+}
+```
+
 ### 2\. Create Snapshot
 
 Pack a directory into a highly compressed snapshot.
 
-```bash
+```shell
 # Basic snapshot
 vegh snap ./my-project --output backup.vegh
 
@@ -95,7 +108,7 @@ vegh snap ./my-project --dry-run
 
 View the Analytics Dashboard to break down your project by language and lines of code.
 
-```bash
+```shell
 vegh loc backup.vegh
 
 # Show Source Lines of Code (SLOC) instead of total LOC
@@ -106,7 +119,7 @@ vegh loc backup.vegh --sloc
 ### 4\. Prompt
 
 Generate a structured XML context of your codebase to feed directly into ChatGPT, Claude, or Gemini.
-```bash
+```shell
 # Generate XML context to stdout
 vegh prompt .
 
@@ -125,10 +138,13 @@ vegh prompt . --clean --output context.xml
 
 Clean up old snapshots to free disk space.
 
-```bash
+```shell
 # Keep only the 5 most recent snapshots in the current directory
 vegh prune --keep 5
 
+# Delete snapshots older than 30 days (but always keep the 5 most recent)
+vegh prune --older-than 30 --keep 5
+
 # Force clean without confirmation (useful for CI/CD)
 vegh prune --keep 1 --force
 ```
@@ -137,7 +153,7 @@ vegh prune --keep 1 --force
 
 Check file integrity (Blake3) and view embedded metadata.
 
-```bash
+```shell
 vegh check backup.vegh
 ```
 
@@ -145,7 +161,7 @@ vegh check backup.vegh
 
 Restore the snapshot to a target directory. Supports **Partial Restore**.
 
-```bash
+```shell
 # Full restore
 vegh restore backup.vegh ./restored-folder
 
@@ -160,7 +176,7 @@ vegh restore backup.vegh ./restored-folder --flatten
 
 Inspect content without extracting.
 
-```bash
+```shell
 # View a file's content inside the snapshot
 vegh cat backup.vegh src/main.rs
 
@@ -168,6 +184,7 @@ vegh cat backup.vegh src/main.rs
 vegh cat backup.vegh image.png --raw > extracted_image.png
 
 # Compare snapshot with a directory
+# (Automatically performs Blake3 Hash comparison if file sizes match)
 vegh diff backup.vegh ./current-project
 ```
 
@@ -175,7 +192,7 @@ vegh diff backup.vegh ./current-project
 
 Send the snapshot to a remote server. Supports **Chunked Uploads** for reliability.
 
-```bash
+```shell
 # Auto-detects if chunking is needed, or force it:
 vegh send backup.vegh --force-chunk
 ```
@@ -184,7 +201,7 @@ vegh send backup.vegh --force-chunk
 
 Check your environment and installation health.
 
-```bash
+```shell
 vegh doctor
 ```
 
@@ -194,21 +211,19 @@ Create a `.veghhooks.json` in your workspace.
 
 ```json
 {
-  "hooks": {
-    "pre": [
-      "echo '🚀 Pre-snap hook started...'",
-      "echo 'Preparing to backup...'",
-      "echo 'Backing up database...'",
-      "echo 'Backup completed.'"
-    ],
-    "post": [
-      "echo '🎉 Snapshot completed!'",
-      "echo 'Cleaning up...'"
-    ]
-  }
+  "pre": ["echo 'Checking...'", "ruff check -e"],
+  "post": ["echo 'Clean up...'"]
 }
 ```
 
+### 12\. Audit
+
+Scan a snapshot for sensitive filenames and secrets.
+
+```shell
+vegh audit backup.vegh
+```
+
 ## Library Usage
 
 You can also use PyVegh as a library in your own Python scripts:

{pyvegh-0.7.0 → pyvegh-0.9.0}/README.md

@@ -21,13 +21,16 @@ It delivers the raw performance of Rust (Zstd multithreaded compression, Tar arc
 ## Installation
 
 Install directly from PyPI:
-```bash
+```shell
 pip install pyvegh
+
+# Or via uv
+uv pip install pyvegh
 ```
 
 Or build from source (requires Rust):
 
-```bash
+```shell
 maturin develop --release
 ```
 
@@ -39,7 +42,7 @@ PyVegh provides a powerful command-line interface via the `vegh` (or `pyvegh`) c
 
 Set up your default server URL and Auth Token so you don't have to type them every time.
 
-```bash
+```shell
 vegh config
 # Or one-liner:
 vegh config send --url https://api.teaserverse.online/test --auth YOUR_TOKEN
@@ -51,11 +54,21 @@ vegh config list
 vegh config reset
 ```
 
+**Advanced:** You can also configure custom `audit` patterns in `~/.vegh/config.json`:
+```json
+{
+  "audit": {
+    "patterns": ["custom_secret\\.key", ".*\\.private"],
+    "keywords": ["MY_API_KEY", "INTERNAL_TOKEN"]
+  }
+}
+```
+
 ### 2\. Create Snapshot
 
 Pack a directory into a highly compressed snapshot.
 
-```bash
+```shell
 # Basic snapshot
 vegh snap ./my-project --output backup.vegh
 
@@ -67,7 +80,7 @@ vegh snap ./my-project --dry-run
 
 View the Analytics Dashboard to break down your project by language and lines of code.
 
-```bash
+```shell
 vegh loc backup.vegh
 
 # Show Source Lines of Code (SLOC) instead of total LOC
@@ -78,7 +91,7 @@ vegh loc backup.vegh --sloc
 ### 4\. Prompt
 
 Generate a structured XML context of your codebase to feed directly into ChatGPT, Claude, or Gemini.
-```bash
+```shell
 # Generate XML context to stdout
 vegh prompt .
 
@@ -97,10 +110,13 @@ vegh prompt . --clean --output context.xml
 
 Clean up old snapshots to free disk space.
 
-```bash
+```shell
 # Keep only the 5 most recent snapshots in the current directory
 vegh prune --keep 5
 
+# Delete snapshots older than 30 days (but always keep the 5 most recent)
+vegh prune --older-than 30 --keep 5
+
 # Force clean without confirmation (useful for CI/CD)
 vegh prune --keep 1 --force
 ```
@@ -109,7 +125,7 @@ vegh prune --keep 1 --force
 
 Check file integrity (Blake3) and view embedded metadata.
 
-```bash
+```shell
 vegh check backup.vegh
 ```
 
@@ -117,7 +133,7 @@ vegh check backup.vegh
 
 Restore the snapshot to a target directory. Supports **Partial Restore**.
 
-```bash
+```shell
 # Full restore
 vegh restore backup.vegh ./restored-folder
 
@@ -132,7 +148,7 @@ vegh restore backup.vegh ./restored-folder --flatten
 
 Inspect content without extracting.
 
-```bash
+```shell
 # View a file's content inside the snapshot
 vegh cat backup.vegh src/main.rs
 
@@ -140,6 +156,7 @@ vegh cat backup.vegh src/main.rs
 vegh cat backup.vegh image.png --raw > extracted_image.png
 
 # Compare snapshot with a directory
+# (Automatically performs Blake3 Hash comparison if file sizes match)
 vegh diff backup.vegh ./current-project
 ```
 
@@ -147,7 +164,7 @@ vegh diff backup.vegh ./current-project
 
 Send the snapshot to a remote server. Supports **Chunked Uploads** for reliability.
 
-```bash
+```shell
 # Auto-detects if chunking is needed, or force it:
 vegh send backup.vegh --force-chunk
 ```
@@ -156,7 +173,7 @@ vegh send backup.vegh --force-chunk
 
 Check your environment and installation health.
 
-```bash
+```shell
 vegh doctor
 ```
 
@@ -166,21 +183,19 @@ Create a `.veghhooks.json` in your workspace.
 
 ```json
 {
-  "hooks": {
-    "pre": [
-      "echo '🚀 Pre-snap hook started...'",
-      "echo 'Preparing to backup...'",
-      "echo 'Backing up database...'",
-      "echo 'Backup completed.'"
-    ],
-    "post": [
-      "echo '🎉 Snapshot completed!'",
-      "echo 'Cleaning up...'"
-    ]
-  }
+  "pre": ["echo 'Checking...'", "ruff check -e"],
+  "post": ["echo 'Clean up...'"]
 }
 ```
 
+### 12\. Audit
+
+Scan a snapshot for sensitive filenames and secrets.
+
+```shell
+vegh audit backup.vegh
+```
+
 ## Library Usage
 
 You can also use PyVegh as a library in your own Python scripts:

{pyvegh-0.7.0 → pyvegh-0.9.0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "maturin"
 
 [project]
 name = "pyvegh"
-version = "0.7.0"
+version = "0.9.0"
 description = "Python bindings for Vegh - The Snapshot Tool."
 authors = [{name = "CodeTease"}]
 readme = "README.md"

{pyvegh-0.7.0 → pyvegh-0.9.0}/python/vegh/__init__.py

@@ -9,9 +9,10 @@ from ._core import (
     get_metadata,
     count_locs,
     scan_locs_dir,
+    read_snapshot_text,
 )
 
-__version__ = "0.7.0"
+__version__ = "0.8.0"
 __all__ = [
     "create_snap",
     "dry_run_snap",
@@ -20,5 +21,6 @@ __all__ = [
     "get_metadata",
     "count_locs",
     "scan_locs_dir",
+    "read_snapshot_text",
     "__version__",
 ]

pyvegh-0.9.0/python/vegh/analytics.py

@@ -0,0 +1,281 @@
+from pathlib import Path
+from typing import List, Tuple, Dict
+from rich.console import Console
+from rich.table import Table
+from rich.panel import Panel
+from rich.text import Text
+from rich import box
+from rich.layout import Layout
+from rich.align import Align
+
+from .jsonc import parse
+
+# Load configuration from JSON
+config_path = Path(__file__).parent / "config.jsonc"
+with open(config_path, "r", encoding="utf-8") as f:
+    config = parse(f.read())
+
+LANG_MAP = {k: tuple(v) for k, v in config["LANG_MAP"].items()}
+SLOC_IGNORE_EXTS = set(config["SLOC_IGNORE_EXTS"])
+COMMENT_MAP = config["COMMENT_MAP"]
+FILENAME_MAP = {k: tuple(v) for k, v in config["FILENAME_MAP"].items()}
+
+
+class ProjectStats:
+    def __init__(self):
+        self.total_files = 0
+        self.total_loc = 0
+        self.lang_stats: Dict[str, Dict] = {}
+
+    def add_file(self, path_str: str, loc: int):
+        self.total_files += 1
+        self.total_loc += loc
+
+        path = Path(path_str)
+        # .lower() handles both .s and .S
+        ext = path.suffix.lower()
+        name = path.name.lower()
+
+        # Identify Language
+        lang, color = "Other", "white"
+
+        if name in FILENAME_MAP:
+            lang, color = FILENAME_MAP[name]
+        elif ext in LANG_MAP:
+            lang, color = LANG_MAP[ext]
+
+        # Update Stats
+        if lang not in self.lang_stats:
+            self.lang_stats[lang] = {"files": 0, "loc": 0, "color": color}
+
+        self.lang_stats[lang]["files"] += 1
+        self.lang_stats[lang]["loc"] += loc
+
+
+def _make_bar(label: str, percent: float, color: str, width: int = 30) -> Text:
+    """Manually renders a progress bar using unicode blocks."""
+    filled_len = int((percent / 100.0) * width)
+    unfilled_len = width - filled_len
+
+    bar_str = ("█" * filled_len) + ("░" * unfilled_len)
+
+    text = Text()
+    text.append(f"{label:<20}", style=f"bold {color}")
+    text.append(f"{bar_str} ", style=color)
+    text.append(f"{percent:>5.1f}%", style="bold white")
+    return text
+
+
+def scan_sloc(path: str) -> List[Tuple[str, int]]:
+    """Scans a directory for SLOC, using core dry_run_snap for traversal."""
+    # We need to import dry_run_snap here or pass it in.
+    # To avoid circular imports, we'll try to import it inside the function
+    from ._core import dry_run_snap
+
+    results = []
+
+    # Use dry_run_snap to get the file list (respecting .gitignore/veghignore)
+    # dry_run_snap returns (path, size). We just want the path.
+    files = dry_run_snap(path)
+
+    base_path = Path(path)
+
+    for relative_path, _ in files:
+        full_path = base_path / relative_path
+        sloc = calculate_sloc(str(full_path))
+        results.append((relative_path, sloc))
+
+    return results
+
+
+def count_sloc_from_text(content: str, ext: str) -> int:
+    """Core logic to count SLOC from a string content."""
+    if ext in SLOC_IGNORE_EXTS:
+        return 0
+
+    comment_prefix = COMMENT_MAP.get(ext)
+    count = 0
+
+    # Process line by line
+    for line in content.splitlines():
+        line = line.strip()
+        if not line:
+            continue
+        if comment_prefix and line.startswith(comment_prefix):
+            continue
+        count += 1
+
+    return count
+
+
+def calculate_sloc(file_path: str) -> int:
+    """Calculates Source Lines of Code (SLOC) from a file on disk."""
+    path = Path(file_path)
+    ext = path.suffix.lower()
+
+    if ext in SLOC_IGNORE_EXTS:
+        return 0
+
+    try:
+        # Check if file is binary
+        with open(file_path, "rb") as f:
+            chunk = f.read(512)
+            if b"\x00" in chunk:
+                return 0
+
+        # Read file with error handling
+        with open(file_path, "r", encoding="utf-8", errors="ignore") as f:
+            content = f.read()
+            return count_sloc_from_text(content, ext)
+    except Exception:
+        return 0
+
+
+def render_dashboard(
+    console: Console,
+    file_name: str,
+    raw_results: List[Tuple[str, int]],
+    metric_name: str = "LOC",
+):
+    """Draws the beautiful CodeTease Analytics Dashboard."""
+
+    # 1. Process Data
+    stats = ProjectStats()
+    for path, loc in raw_results:
+        if loc > 0:
+            stats.add_file(path, loc)
+
+    if stats.total_loc == 0:
+        console.print(
+            "[yellow]No code detected (or binary only). Is this a ghost project?[/yellow]"
+        )
+        return
+
+    sorted_langs = sorted(
+        stats.lang_stats.items(), key=lambda item: item[1]["loc"], reverse=True
+    )
+
+    # 2. Build Layout
+    layout = Layout()
+    layout.split(
+        Layout(name="header", size=3),
+        Layout(name="body", ratio=1),
+        Layout(name="footer", size=3),
+    )
+
+    layout["body"].split_row(
+        Layout(name="left", ratio=1), Layout(name="right", ratio=1)
+    )
+
+    # --- Header ---
+    title_text = Text(
+        f"📊 Vegh Analytics ({metric_name}): {file_name}",
+        style="bold white on blue",
+        justify="center",
+    )
+    layout["header"].update(Panel(title_text, box=box.HEAVY))
+
+    # --- Left: Detailed Table ---
+    table = Table(box=box.SIMPLE_HEAD, expand=True)
+    table.add_column("Lang", style="bold")
+    table.add_column("Files", justify="right")
+    table.add_column(metric_name, justify="right", style="green")
+    table.add_column("%", justify="right")
+
+    for lang, data in sorted_langs:
+        percent = (data["loc"] / stats.total_loc) * 100
+        table.add_row(
+            f"[{data['color']}]{lang}[/{data['color']}]",
+            str(data["files"]),
+            f"{data['loc']:,}",
+            f"{percent:.1f}%",
+        )
+
+    layout["left"].update(
+        Panel(table, title="[bold]Breakdown[/bold]", border_style="cyan")
+    )
+
+    # --- Right: Custom Manual Bar Chart ---
+    chart_content = Text()
+
+    # Take Top 12 languages
+    for i, (lang, data) in enumerate(sorted_langs[:12]):
+        percent = (data["loc"] / stats.total_loc) * 100
+        bar = _make_bar(lang, percent, data["color"])
+        chart_content.append(bar)
+        chart_content.append("\n")
+
+    if len(sorted_langs) > 12:
+        chart_content.append(
+            f"\n... and {len(sorted_langs) - 12} others", style="dim italic"
+        )
+
+    layout["right"].update(
+        Panel(
+            Align.center(chart_content, vertical="middle"),
+            title="[bold]Distribution[/bold]",
+            border_style="green",
+        )
+    )
+
+    # --- Footer: Summary & Fun Comment ---
+    if sorted_langs:
+        top_lang = sorted_langs[0][0]
+    else:
+        top_lang = "Other"
+
+    comment = "Code Hard, Play Hard! 🚀"
+
+    # Logic Fun Comment
+    if top_lang == "Rust":
+        comment = "Blazingly Fast! 🦀"
+    elif top_lang == "Python":
+        comment = "Snake Charmer! 🐍"
+    elif top_lang == "Haskell":
+        comment = "Purely Functional... and confusing! 😵‍💫"
+    elif top_lang == "Mojo":
+        comment = "AI Speedster! 🔥"
+    elif top_lang == "Solidity":
+        comment = "Wen Lambo? 🏎️"
+    elif top_lang == "Elixir":
+        comment = "Scalability God! 💜"
+    elif top_lang == "Astro":
+        comment = "To the stars! 🚀"
+    elif top_lang == "CSS":
+        comment = "Center a div? Good luck! 🎨"
+    elif "React" in top_lang:
+        comment = "Component Heaven! ⚛️"
+    elif top_lang in ["JavaScript", "TypeScript", "Vue", "Svelte"]:
+        comment = "Web Scale! 🌐"
+    elif top_lang in ["Assembly", "C", "C++"]:
+        comment = "Low Level Wizardry! 🧙‍♂️"
+    elif top_lang in ["FDON", "FWON", "BXSON"]:
+        comment = "Teasers! ⚡"
+    elif top_lang == "HTML":
+        comment = "How To Meet Ladies? 😉"
+    elif top_lang == "Go":
+        comment = "Gopher it! 🐹"
+    elif top_lang == "Java":
+        comment = "Enterprise Grade! ☕"
+    elif top_lang == "C#":
+        comment = "Microsoft Magic! 🪟"
+    elif top_lang == "PHP":
+        comment = "Elephant in the room! 🐘"
+    elif top_lang == "Swift":
+        comment = "Feeling Swift? 🍏"
+    elif top_lang == "Dart":
+        comment = "Fluttering away! 🐦"
+    elif top_lang == "SQL":
+        comment = "DROP TABLE production; 💀"
+    elif top_lang == "Terraform":
+        comment = "Infrastructure as Code! 🏗️"
+    elif top_lang == "Dockerfile":
+        comment = "Containerized! 🐳"
+
+    summary = f"[bold]Total {metric_name}:[/bold] [green]{stats.total_loc:,}[/green] | [bold]Analyzed Files:[/bold] {stats.total_files} | [italic]{comment}[/italic]"
+
+    layout["footer"].update(
+        Panel(Text.from_markup(summary, justify="center"), border_style="blue")
+    )
+
+    console.print(layout)

pyvegh-0.9.0/python/vegh/cli.py

@@ -0,0 +1,7 @@
+from .cli_main import app
+
+# noqa: F401 to expose app at package level
+from . import cli_commands  # noqa: F401
+
+if __name__ == "__main__":
+    app()