fix cloc output scrapping. add clone progress and python output to docker logs.

.env.example

@@ -0,0 +1,5 @@
+# Copy this file to .env and fill in your actual tokens
+# The .env file is gitignored and will be used for local development
+
+PICABLE_DISCORD_TOKEN=your_discord_token_here
+PICABLE_GITHUB_TOKEN=your_github_token_here

.gitignore

@@ -1,2 +1,7 @@
 **/__pycache__/
 **/*_tok
+**/.idea/
+
+# Environment variables and local development overrides
+.env
+docker-compose.override.yml

Dockerfile

@@ -0,0 +1,21 @@
+FROM python:3.14-slim
+
+RUN set -eux; \
+	apt-get update; \
+	apt-get install -y --no-install-recommends cloc git; \
+	apt-get clean; \
+	rm -rf /var/lib/apt/lists/*
+
+WORKDIR /app
+RUN pip install --no-cache-dir discord.py requests
+
+COPY main.py .
+COPY PICable.py .
+
+RUN useradd -m appuser && \
+	mkdir -p /temp && \
+	chown appuser:appuser /temp
+
+USER appuser
+
+CMD ["python", "-u", "main.py"]

PICable.py

@@ -1,15 +1,16 @@
 import os
 import subprocess
-import sys
 from datetime import datetime, timedelta
 
 import requests
 
-LIMIT_COMMITS_30_DAYS = 50
+LIMIT_COMMITS_30_DAYS = int(os.getenv("LIMIT_COMMITS_30_DAYS", "50"))
-LIMIT_STARS = 200
+LIMIT_STARS = int(os.getenv("LIMIT_STARS", "200"))
-LIMIT_NLOC = 100000
+LIMIT_NLOC = int(os.getenv("LIMIT_NLOC", "100000"))
+
 MARGIN = 0.1
-CLONE_DIR = "~/temp/PICable"
+CLONE_DIR = "/temp"
+EXCLUDED_LANGUAGES = ["CSV", "diff", "INI", "JSON", "Markdown", "reStructuredText", "SVG", "Text", "YAML"]
 
 
 def get_stars_info(owner, repository, request_headers):
@@ -47,45 +48,45 @@ def get_commits_last_30_days(owner, repository, request_headers):
 
 
 def get_lines_of_code(owner, repository):
-    repo_url = f"https://github.com/{owner}/{repository}.git"
+    repository_url = f"https://github.com/{owner}/{repository}.git"
-    repository_clone_dir = os.path.expanduser(f"{CLONE_DIR}/{repository}")
+    parent_dir = os.path.expanduser(f"{CLONE_DIR}/{owner}")
+    repository_clone_dir = os.path.expanduser(f"{parent_dir}/{repository}")
 
     try:
+        print(f"Cloning {repository_url}...")
         subprocess.run(
-            ["git", "clone", repo_url, repository_clone_dir],
+            ["git", "clone", "--depth", "1", "--progress", repository_url, repository_clone_dir],
             check=True,
-            stdout=sys.stdout,
-            stderr=sys.stderr,
         )
-    except Exception:
+        print("Clone complete. Running cloc...")
+        result = subprocess.run(
+            ["cloc", f"--exclude-lang={','.join(EXCLUDED_LANGUAGES)}", repository_clone_dir],
+            capture_output=True,
+            text=True,
+            check=True,
+        )
+        
+        # Find the SUM line and extract the last column (code lines)
+        for line in result.stdout.split("\n"):
+            if line.strip().startswith("SUM:"):
+                number_of_lines_of_code = int(line.split()[-1])
+                break
+        else:
+            raise ValueError("Could not find SUM line in cloc output")
+    except Exception as e:
+        print(f"Error occurred: {e}")
         return -1
-
+    finally:
-    result = subprocess.run(["sloccount", repository_clone_dir], capture_output=True, text=True, check=True)
+        subprocess.run(["rm", "-rf", parent_dir], check=True)
-    for line in result.stdout.splitlines():
+    return number_of_lines_of_code
-        if "Total Physical Source Lines of Code (SLOC)" in line:
-            loc = int(line.split()[8].replace(",", ""))
-            break
-    else:
-        loc = 0
-    subprocess.run(["rm", "-rf", repository_clone_dir], check=True)
-    return loc
-
-
-def is_valid_repository(owner, repository, request_headers):
-    repository_url = f"https://api.github.com/repos/{owner}/{repository}"
-    repository_response = requests.get(repository_url, headers=request_headers)
-    return repository_response.status_code == 200
 
 
 def PICable(owner, repository, token):
     margin_percentage = round(MARGIN * 100)
     request_headers = {"Authorization": f"token {token}"}
-    picable_report = ""
+    picable_report = f"Analysis complete for the repository {owner}/{repository}.\n\n"
     repository_url = f"https://www.github.com/{owner}/{repository}"
 
-    if not is_valid_repository(owner, repository, request_headers):
-        return f"Invalid repository: {owner}/{repository} :x:"
-
     stars = get_stars_info(owner, repository, request_headers)
     if stars == -1:
         return "Error fetching stars info. :x:"
@@ -132,6 +133,7 @@ def PICable(owner, repository, token):
     elif stars >= LIMIT_STARS and commits_30_days >= LIMIT_COMMITS_30_DAYS and lines_of_code >= LIMIT_NLOC:
         picable_report += f"The repository {repository_url} is PICable. :white_check_mark:\n"
     else:
-        picable_report += f"The repository {repository_url} is almost PICable. :warning:\nThere is at least one requirement which is below the requirement, but by less than {margin_percentage}%. Consult with a professor before proceeding.\n"
+        picable_report += f"The repository {repository_url} is almost PICable. :warning:\nThere is at least one parameter which is below the requirement, but by less than {margin_percentage}%.\nConsult with a professor before proceeding.\n"
 
+    print("Analysis complete.")
     return picable_report

README.md

@@ -1,2 +1,3 @@
 # PICable
+
 Simple script to determine if a project is eligible as the final PIC of LEIC-T.

docker-compose.yml

@@ -0,0 +1,8 @@
+services:
+  picable:
+    image: didas72/picable:latest
+    container_name: picable
+    environment:
+      - PICABLE_DISCORD_TOKEN=${PICABLE_DISCORD_TOKEN}
+      - PICABLE_GITHUB_TOKEN=${PICABLE_GITHUB_TOKEN}
+    restart: unless-stopped

main.py

@@ -1,36 +1,34 @@
-import asyncio
+import os
-from sys import argv
+from asyncio import Condition, Lock, create_task, shield, to_thread, wait_for
 
-import discord
+import requests
+from discord import Game, Intents, Interaction, app_commands
 from discord.ext import commands
 
-import PICable
+from PICable import PICable
 
-if len(argv) != 3:
+MAX_STORAGE_KB = 50 * 1024 * 1024  # 50GB
-    print("Usage:\n\t" + argv[0] + " <discord_token> <github_token>")
+DISCORD_TOKEN = os.getenv("PICABLE_DISCORD_TOKEN")
+GITHUB_TOKEN = os.getenv("PICABLE_GITHUB_TOKEN")
+
+current_storage_kb = 0
+storage_condition = Condition()
+current_repositories = set()
+current_repositories_lock = Lock()
+
+if not DISCORD_TOKEN or not GITHUB_TOKEN:
+    print("Discord or Github tokens not set in env. Use variables PICABLE_DISCORD_TOKEN and PICABLE_GITHUB_TOKEN")
     exit(1)
-discord_token = argv[1]
-github_token = argv[2]
 
-intents = discord.Intents.default()
+intents = Intents.default()
 intents.message_content = True
 client = commands.Bot(command_prefix="/", intents=intents)
 
 
-async def reply_message_async(interaction: discord.Interaction, owner: str, repo: str):
-    try:
-        result = await asyncio.to_thread(PICable.PICable, owner, repo, github_token)
-        await interaction.followup.send(result)
-    except Exception as e:
-        print(f"Error processing PICable check: {e}")
-        await interaction.followup.send("An error occurred while processing your request. Please try again later.")
-    return
-
-
 @client.event
 async def on_ready():
     print(f"We have logged in as {client.user}")
-    await client.change_presence(activity=discord.Game("with PIC ideas"))
+    await client.change_presence(activity=Game("with PIC ideas"))
     try:
         synced = await client.tree.sync()
         print(f"Synced {len(synced)} command(s)")
@@ -38,10 +36,81 @@ async def on_ready():
         print(f"Failed to sync commands: {e}")
 
 
-@client.tree.command(name="picable", description="Check if a Github repository is eligible for PIC.")
+@client.tree.command(name="ping", description="Check the bot's latency.")
-@discord.app_commands.describe(owner="The owner of the repository", repository="The name of the repository")
+async def ping(interaction: Interaction):
-async def picable(interaction: discord.Interaction, owner: str, repository: str):
+    latency = client.latency * 1000
-    await interaction.response.defer(ephemeral=False, thinking=True)
+    await interaction.response.send_message(f"Pong! Latency: {latency:.2f}ms")
-    asyncio.create_task(reply_message_async(interaction, owner, repository))
 
-client.run(discord_token)
+
+async def handle_picable(owner: str, repository: str, repository_size_kb: int, github_token: str):
+    global current_storage_kb
+    async with storage_condition:
+        await storage_condition.wait_for(lambda: current_storage_kb + repository_size_kb <= MAX_STORAGE_KB)
+        current_storage_kb += repository_size_kb
+
+    print(f"Storage is {current_storage_kb / MAX_STORAGE_KB * 100:.2f}% full.")
+    return await to_thread(PICable, owner, repository, github_token)
+
+
+@client.tree.command(name="picable", description="Check if a Github repository is eligible for PIC.")
+@app_commands.describe(owner="The owner of the repository", repository="The name of the repository")
+async def picable(interaction: Interaction, owner: str, repository: str):
+    await interaction.response.defer(thinking=True)
+
+    repository_full_name = f"{owner}/{repository}"
+    async with current_repositories_lock:
+        if repository_full_name in current_repositories:
+            await interaction.followup.send(
+                f"The repository {repository_full_name} is already being analyzed. Please wait for the current analysis to complete. :warning:"
+            )
+            return
+
+        current_repositories.add(repository_full_name)
+
+    url = f"https://api.github.com/repos/{owner}/{repository}"
+    headers = {"Authorization": f"token {GITHUB_TOKEN}"}
+    response = requests.get(url, headers=headers)
+
+    if not response.status_code == 200:
+        await interaction.followup.send(
+            "Invalid Repository. Please check the repository name and owner and try again. :x:"
+        )
+        return
+
+    response.raise_for_status()
+    repo_info = response.json()
+    repository_size_kb = repo_info["size"]
+    print(f"Repository size: {repository_size_kb / 1024} MB")
+
+    if repository_size_kb > MAX_STORAGE_KB:
+        await interaction.followup.send(
+            f"The repository {repository_full_name} is too large to analyze. Please try a smaller repository. :warning:"
+        )
+        current_repositories.remove(repository_full_name)
+        return
+
+    global current_storage_kb
+    try:
+        result_future = create_task(handle_picable(owner, repository, repository_size_kb, GITHUB_TOKEN))
+        try:
+            result = await wait_for(shield(result_future), timeout=600)
+            await interaction.followup.send(result)
+        except TimeoutError:
+            await interaction.followup.send(
+                f"The analysis for {repository_full_name} is still taking place. The results will be posted here once the analysis is complete. :clock4:"
+            )
+            result = await result_future
+            await interaction.channel.send(f"{interaction.user.mention}\n{result}")
+    except Exception as e:
+        print(f"Error processing PICable check: {e}")
+        await interaction.channel.send("An error occurred while processing your request. Please try again later.")
+    finally:
+        async with current_repositories_lock:
+            current_repositories.remove(repository_full_name)
+        async with storage_condition:
+            current_storage_kb -= repository_size_kb
+            storage_condition.notify_all()
+
+
+if __name__ == "__main__":
+    client.run(DISCORD_TOKEN)

run.sh

@@ -1 +0,0 @@
-python3 main.py MTM0MzMzNzAzMzkyOTU4ODg5MA.Gx2pEq.uLdXFORUFlYurLUF6Lnsuh_EWFQRI8SAKFebDM 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