Update README.md: Change emoji and color scheme, update app file path, and add server run instructions

.gitignore

@@ -0,0 +1,197 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+# Abstra
+# Abstra is an AI-powered process automation framework.
+# Ignore directories containing user credentials, local state, and settings.
+# Learn more at https://abstra.io/docs
+.abstra/
+
+# Visual Studio Code
+#  Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore 
+#  that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
+#  and can be added to the global gitignore or merged into this file. However, if you prefer, 
+#  you could uncomment the following to ignore the enitre vscode folder
+# .vscode/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Cursor
+#  Cursor is an AI-powered code editor. `.cursorignore` specifies files/directories to
+#  exclude from AI features like autocomplete and code analysis. Recommended for sensitive data
+#  refer to https://docs.cursor.com/context/ignore-files
+.cursorignore
+.cursorindexingignore
+
+./temp
+.gradio

README.md

@@ -1,14 +1,25 @@
 ---
 title: Universal File Converter
-emoji: 😻
-colorFrom: red
-colorTo: yellow
+emoji: 🗃️
+colorFrom: yellow
+colorTo: green
 sdk: gradio
 sdk_version: 5.32.0
-app_file: app.py
+app_file: src/app.py
 pinned: false
 license: apache-2.0
 short_description: Convert any file to any file format.
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+
+To run the server use:
+
+```bash
+uv run python src/app.py
+```
+
+To test the server use:
+
+```bash
+uv run python .\test\test_app.py
+```

requirements.txt

@@ -0,0 +1 @@
+convertapi>=2.0.0

src/app.py

@@ -0,0 +1,160 @@
+import os
+from pathlib import Path
+from urllib.parse import urlparse
+
+import convertapi
+import gradio as gr
+from dotenv import load_dotenv
+
+load_dotenv()
+convertapi.api_credentials = os.getenv("CONVERTAPI_TOKEN")
+
+
+# Function to convert a local file
+def convert_local_file(local_file_path, output_format):
+    """
+    Convert a local document to a different format.
+
+    Args:
+        local_file_path (str): The path to the input file.
+        output_format (str): The format to convert the file to.
+
+    Returns:
+        str: The path to the converted file or an error message.
+    """
+    try:
+        if not local_file_path or not os.path.exists(local_file_path):
+            return "Invalid or non-existent local file path."
+
+        # Convert the local file
+        result = convertapi.convert(output_format, {"File": local_file_path})
+
+        # Derive filename from local path
+        input_filename = Path(local_file_path).stem
+
+        # Save the converted file to a temporary location
+        output_filename = f"{input_filename}.{output_format}"
+        output_path = Path("temp") / output_filename
+        output_path.parent.mkdir(exist_ok=True)
+
+        result.file.save(str(output_path))
+
+        # Return the file path string on success
+        return str(output_path)
+
+    except Exception as e:
+        return f"Error converting file: {str(e)}"
+
+
+# Function to convert a file from a URL
+def convert_from_url(document_url, output_format):
+    """
+    Convert a document from a URL to a different format.
+
+    Args:
+        document_url (str): The URL of the input file.
+        output_format (str): The format to convert the file to.
+
+    Returns:
+        str: The path to the converted file or an error message.
+    """
+    try:
+        if not document_url or not (
+            document_url.lower().startswith("http://")
+            or document_url.lower().startswith("https://")
+        ):
+            return "Invalid or unsupported URL format."
+
+        # Convert the file from a URL
+        result = convertapi.convert(output_format, {"File": document_url})
+
+        # Attempt to derive a filename from the URL for saving
+        try:
+            url_path = urlparse(document_url).path
+            input_filename = (
+                Path(url_path).stem or "converted_file"
+            )  # Fallback for complex URLs or no path
+        except Exception:
+            input_filename = "converted_file"
+
+        # Save the converted file to a temporary location
+        output_filename = f"{input_filename}.{output_format}"
+        output_path = Path("temp") / output_filename
+        output_path.parent.mkdir(exist_ok=True)
+
+        result.file.save(str(output_path))
+
+        # Return the file path string on success
+        return str(output_path)
+
+    except Exception as e:
+        return f"Error converting file from URL: {str(e)}"
+
+
+# Create Gradio interfaces
+local_file_demo = gr.Interface(
+    fn=convert_local_file,
+    inputs=[
+        gr.File(label="Upload File"),
+        gr.Dropdown(
+            choices=[
+                "docx",
+                "pdf",
+                "txt",
+                "png",
+                "jpg",
+                "jpeg",
+                "xlsx",
+                "pptx",
+                "html",
+                "rtf",
+            ],
+            label="Output Format",
+            value="pdf",
+        ),
+    ],
+    outputs=gr.File(label="Download Converted File"),
+    title="Local File Converter",
+    description="Convert documents from your local file system to different formats.",
+)
+
+url_demo = gr.Interface(
+    fn=convert_from_url,
+    inputs=[
+        gr.Textbox(
+            label="Document URL",
+            placeholder="Enter the URL of the document to convert (e.g., https://example.com/document.pdf)",
+            value="",
+        ),
+        gr.Dropdown(
+            choices=[
+                "docx",
+                "pdf",
+                "txt",
+                "png",
+                "jpg",
+                "jpeg",
+                "xlsx",
+                "pptx",
+                "html",
+                "rtf",
+            ],
+            label="Output Format",
+            value="pdf",
+        ),
+    ],
+    outputs=gr.File(label="Download Converted File"),
+    title="URL Document Converter",
+    description="Download and convert documents directly from URLs to different formats.",
+)
+
+# Create tabbed interface
+demo = gr.TabbedInterface(
+    [local_file_demo, url_demo],
+    ["Local Files", "Online Files"],
+    title="Universal Document Converter",
+)
+
+if __name__ == "__main__":
+    # Launch without MCP server to avoid initialization issues
+    demo.launch(share=False, mcp_server=True, debug=True)

tests/test_app.py

@@ -0,0 +1,25 @@
+from gradio_client import Client
+
+client = Client("http://127.0.0.1:7860/")
+result_1 = client.predict(
+    local_file_path="data/test-document.pdf", output_format="docx", api_name="/predict"
+)
+print("Link to the document:", result_1)
+assert (
+    isinstance(result_1, dict)
+    and result_1.get("output_file") is not None
+    and result_1.get("output_file").endswith(".docx")
+)
+
+result_2 = client.predict(
+    document_url="https://raw.githubusercontent.com/kingabzpro/bbc-news-class-mlops/refs/heads/master/README.md",
+    output_format="pdf",
+    api_name="/predict_1",
+)
+
+print("Link to the document:", result_2)
+assert (
+    isinstance(result_2, dict)
+    and result_2.get("output_file") is not None
+    and result_2.get("output_file").endswith(".pdf")
+)