FAQ

git clone https://github.com/naineel1209/swissknife.git
cd swissknife
pip install uv --upgrade
uv sync
source .venv/bin/activate  # Windows: .venv\Scripts\activate

pip install pypandoc pillow imageio-ffmpeg patoolib google-genai pypdf

uv add pypandoc          # Document conversions
uv add pillow            # Image processing
uv add imageio-ffmpeg    # Audio/video conversions
uv add patoolib          # Archive handling
uv add google-genai      # AI summarization
uv add pypdf             # PDF operations

# Download MiKTeX from miktex.org
# Or using Chocolatey:
choco install texlive

sudo apt update
sudo apt install -y texlive-latex-base texlive-latex-recommended texlive-fonts-recommended

brew install --cask basictex
export PATH=/Library/TeX/texbin:$PATH

sudo apt install p7zip-full unrar rar

brew install p7zip unrar rar

# Get API key from aistudio.google.com
export GOOGLE_API_KEY="your_api_key_here"

# Test Python packages
python -c "import pypandoc, PIL, imageio_ffmpeg, patoolib, google.genai, pypdf"

# Test system tools
pandoc --version
xelatex --version
7z --version

Error: Module <name> not found. Please install it using pip.
Error: Try: pip install <package_name>
Error: This module is required for the requested operation.

python solution.py convert protected.zip extracted.tar.gz --password mypassword
python solution.py convert secure.rar backup.7z --password secretpass

# Extract password-protected ZIP and create password-protected 7Z
python solution.py convert secure.zip backup.7z --password mypass

# Extract password-protected RAR and create unprotected ZIP
# (Password used only for extraction, not reapplied)
python solution.py convert protected.rar output.zip --password oldpass

patoolib.extract_archive(work_path, outdir=temp_extract_dir, 
                       password=password if password else None, 
                       interactive=False)

file_size_mb = input_abs.stat().st_size / (1024 * 1024)
if file_size_mb > 100:
    raise ValueError(f"File size ({file_size_mb:.1f}MB) exceeds maximum limit of 100MB")

# Text files are typically much smaller than formatted documents
python solution.py convert large_document.pdf extracted.txt
python solution.py summarize extracted.txt --length medium

# For PDFs, extract specific page ranges
python solution.py split large_book.pdf "1-50"
python solution.py split large_book.pdf "51-100"

# Summarize each section
python solution.py summarize large_book_part1.pdf --length medium
python solution.py summarize large_book_part2.pdf --length medium

Info: File validated (45.3MB) - uploading to AI service...

with open("./summarize_prompt.txt", "r", encoding="utf-8") as f:
    prompt = f.read()

configs = {
    "short": {
        "description": "a brief summary about the essence of the document in 1 paragraph",
        "max_tokens": 1500,
        "temperature": 0.5
    },
    "medium": {
        "description": "a concise summary about the essence of the document in 2-3 paragraphs",
        "max_tokens": 2500,
        "temperature": 0.7
    },
    "long": {
        "description": "a detailed summary about the essence of the document in 3-4 paragraphs",
        "max_tokens": 4000,
        "temperature": 0.8
    }
}

You are an AI assistant specialized in technical documentation.

Analyze this document and focus on:
- Technical concepts and methodologies
- Key findings and conclusions
- Practical applications

File Details:
{{FILE_DETAILS}}

Requirements:
{{SUMMARY_REQUIREMENTS}}

Provide your summary in a professional, technical tone.

Create a structured summary with the following sections:

1. Overview: {{SUMMARY_REQUIREMENTS}}
2. Main Points: List 3-5 key takeaways
3. Conclusion: Final thoughts

Document Information:
{{FILE_DETAILS}}

# Edit the prompt file
nano summarize_prompt.txt

# Run summarization with your custom prompt
python solution.py summarize document.pdf --length medium

response = client.models.generate_content(
    model="gemini-2.5-flash",
    contents=[prompt, doc],
    config=genai.types.GenerateContentConfig(
        temperature=config["temperature"],  # 0.5, 0.7, or 0.8
        top_p=0.9,
        max_output_tokens=config["max_tokens"]  # 1500, 2500, or 4000
    )
)

# Preserve original file
python solution.py convert important.docx output.pdf --preserve-original

# Original file is modified (default)
python solution.py convert temp.docx output.pdf

# Combine with password protection
python solution.py convert secure.zip backup.7z --password mypass --preserve-original

def create_temp_copy(file_path):
    temp_dir = tempfile.mkdtemp()
    temp_file = Path(temp_dir) / Path(file_path).name
    shutil.copy2(file_path, temp_file)
    return str(temp_file)

work_path = input_abs
if preserve_original:
    temp_file_path = create_temp_copy(input_abs)
    work_path = temp_file_path

if temp_file_path and Path(temp_file_path).exists():
    shutil.rmtree(Path(temp_file_path).parent, ignore_errors=True)

convert_file(str(input_file), str(output_file), preserve_original=True)

finally:
    end_time = time.time()
    duration = end_time - start_time
    print(f"Info: Conversion completed in {duration:.2f} seconds.")
    if temp_file_path and Path(temp_file_path).exists():
        shutil.rmtree(Path(temp_file_path).parent, ignore_errors=True)

Output file /path/to/output.pdf exists. Overwrite? (y/N):

if output_abs.exists():
    response = input(f"Output file {output_abs} exists. Overwrite? (y/N): ")
    if response.lower() != "y":
        sys.exit("Operation cancelled.")

python solution.py convert input.pdf output_v2.pdf
python solution.py convert input.pdf output_$(date +%Y%m%d).pdf

rm output.pdf
python solution.py convert input.pdf output.pdf

python solution.py batch-convert ./input ./output_new .docx .pdf

for input_file in input_files:
    try:
        output_filename = input_file.stem + output_ext
        output_file = output_path / output_filename
        print(f"Converting: {input_file.name} → {output_filename}")
        convert_file(str(input_file), str(output_file), preserve_original=True)

summary_file = input_abs.with_name(input_abs.stem + "_summary.txt")

python solution.py batch-convert <input_dir> <output_dir> <input_ext> <output_ext>

input_path = Path(input_dir).resolve()
if not input_path.exists():
    raise FileNotFoundError(f"Input directory {input_path} does not exist.")
if not input_path.is_dir():
    raise ValueError(f"Input path {input_path} is not a directory.")

# Both .txt and txt are accepted
if not input_ext.startswith('.'):
    input_ext = '.' + input_ext
if not output_ext.startswith('.'):
    output_ext = '.' + output_ext

output_path.mkdir(parents=True, exist_ok=True)

input_files = list(input_path.glob(f"*{input_ext}"))
if not input_files:
    print(f"Info: No files with extension {input_ext} found in {input_path}")
    return

successful_conversions = 0
failed_conversions = 0
for input_file in input_files:
    try:
        output_filename = input_file.stem + output_ext
        output_file = output_path / output_filename
        convert_file(str(input_file), str(output_file), preserve_original=True)
        successful_conversions += 1
    except Exception as e:
        print(f"Error: Failed to convert {input_file.name}: {e}")
        failed_conversions += 1
        continue

python solution.py batch-convert ./documents ./pdf_output .docx .pdf

python solution.py batch-convert ./photos ./jpeg_output .png .jpg

python solution.py batch-convert ./audio ./mp3_output .flac .mp3

# Both commands are equivalent
python solution.py batch-convert ./docs ./output .txt .pdf
python solution.py batch-convert ./docs ./output txt pdf

Info: Found 25 files with extension .docx
Info: Converting from /path/input to /path/output, .docx → .pdf
Converting: document1.docx → document1.pdf
Converting: document2.docx → document2.pdf
...
--------------------------------------------------
Info: Batch conversion completed - Successful: 23
Info: Failed: 2
Info: Output directory: /path/output

python solution.py batch-convert ./input ./output_$(date +%Y%m%d) .docx .pdf

# Copy a few files to test directory
mkdir test_input
cp ./documents/*.docx test_input/ | head -5
python solution.py batch-convert ./test_input ./test_output .docx .pdf

# Convert different types to different directories
python solution.py batch-convert ./docs ./output/pdfs .docx .pdf
python solution.py batch-convert ./docs ./output/markdown .docx .md

response = client.models.generate_content(
    model="gemini-2.5-flash",
    contents=[prompt, doc],
    config=genai.types.GenerateContentConfig(
        temperature=config["temperature"],
        top_p=0.9,
        max_output_tokens=config["max_tokens"]
    )
)

if "GOOGLE_API_KEY" not in os.environ:
    raise EnvironmentError("GOOGLE_API_KEY environment variable is not set.")

pip install google-genai

Info: Conversion completed in 3.47 seconds.

start_time = time.time()
# ... conversion process ...
end_time = time.time()
duration = end_time - start_time
print(f"Info: Conversion completed in {duration:.2f} seconds.")

# Conversion succeeds, program exits normally
convert_file(args.input, args.output)
# Exits with code 0

except KeyboardInterrupt:
    print("\nError: Operation cancelled by user")
    sys.exit(1)
except Exception as e:
    print(f"Error: {e}")
    sys.exit(1)

#!/bin/bash

# Convert all documents in multiple directories
for dir in docs1 docs2 docs3; do
    python solution.py batch-convert "./$dir" "./output/$dir" .docx .pdf
    if [ $? -ne 0 ]; then
        echo "Failed to process $dir"
        exit 1
    fi
done

echo "All conversions completed successfully"

import subprocess
import sys

files_to_convert = [
    ("report.docx", "report.pdf"),
    ("data.xlsx", "data.pdf"),
    ("notes.md", "notes.html")
]

for input_file, output_file in files_to_convert:
    result = subprocess.run(
        ["python", "solution.py", "convert", input_file, output_file],
        capture_output=True,
        text=True
    )
    
    if result.returncode != 0:
        print(f"Failed to convert {input_file}: {result.stderr}")
        sys.exit(1)
    
    print(result.stdout)

Output file exists. Overwrite? (y/N):

rm -f output.pdf
python solution.py convert input.docx output.pdf

timestamp=$(date +%Y%m%d_%H%M%S)
python solution.py convert input.docx "output_${timestamp}.pdf"

echo y | python solution.py convert input.docx output.pdf

# Capture stdout and stderr
result = subprocess.run(
    ["python", "solution.py", "convert", "input.pdf", "output.docx"],
    capture_output=True,
    text=True
)

print("STDOUT:", result.stdout)
print("STDERR:", result.stderr)
print("Exit code:", result.returncode)

export GOOGLE_API_KEY="your_key_here"
python solution.py summarize document.pdf --length medium

import os
os.environ["GOOGLE_API_KEY"] = "your_key_here"
subprocess.run(["python", "solution.py", "summarize", "doc.pdf"])

try:
    convert_file(...)
    successful_conversions += 1
except Exception as e:
    print(f"Error: Failed to convert {input_file.name}: {e}")
    failed_conversions += 1
    continue  # Process next file

Info: Batch conversion completed - Successful: 23
Info: Failed: 2

# Convert documents daily at 2 AM
0 2 * * * cd /path/to/swissknife && source .venv/bin/activate && python solution.py batch-convert ./daily_docs ./output .docx .pdf >> /var/log/swissknife.log 2>&1