initial commit

.gitignore

@@ -0,0 +1 @@
+__pycache__/

README.md

@@ -0,0 +1,11 @@
+---
+title: Repo Info
+emoji: 👁
+colorFrom: red
+colorTo: indigo
+sdk: gradio
+sdk_version: 5.5.0
+app_file: app.py
+pinned: false
+short_description: Get file and branch stats about any public repo
+---

app.py

@@ -0,0 +1,115 @@
+# pylint: disable=no-member
+import gradio as gr
+import requests
+from huggingface_hub import HfApi
+import pandas as pd
+import plotly.express as px
+
+HF_API = HfApi()
+
+
+def format_repo_size(r_size: int) -> str:
+    units = {0: "B", 1: "KB", 2: "MB", 3: "GB", 4: "TB", 5: "PB"}
+    order = 0
+    while r_size >= 1024 and order < len(units) - 1:
+        r_size /= 1024
+        order += 1
+    return f"{r_size:.2f} {units[order]}"
+
+
+def repo_files(r_type: str, r_id: str) -> dict:
+    r_info = HF_API.repo_info(repo_id=r_id, repo_type=r_type, files_metadata=True)
+    files = {}
+    for sibling in r_info.siblings:
+        ext = sibling.rfilename.split(".")[-1]
+        if ext in files:
+            files[ext]["size"] += sibling.size
+            files[ext]["count"] += 1
+        else:
+            files[ext] = {}
+            files[ext]["size"] = sibling.size
+            files[ext]["count"] = 1
+    return files
+
+
+def repo_size(r_type, r_id):
+    r_refs = HF_API.list_repo_refs(repo_id=r_id, repo_type=r_type)
+    repo_sizes = {}
+    for branch in r_refs.branches:
+        try:
+            response = requests.get(
+                f"https://huggingface.co/api/{r_type}s/{r_id}/treesize/{branch.name}",
+                timeout=1000,
+            )
+            response = response.json()
+        except Exception:
+            response = {}
+
+        size = response.get("size")
+        if size is not None:
+            repo_sizes[branch.name] = size
+    return repo_sizes
+
+
+def get_repo_info(r_type, r_id):
+    repo_sizes = repo_size(r_type, r_id)
+    repo_files_info = repo_files(r_type, r_id)
+    rf_sizes_df = (
+        pd.DataFrame(repo_files_info)
+        .T.reset_index(names="ext")
+        .sort_values(by="size", ascending=False)
+    )
+    r_sizes_df = pd.DataFrame(repo_sizes, index=["size"]).T.reset_index(names="branch")
+    r_sizes_df["formatted_size"] = r_sizes_df["size"].apply(format_repo_size)
+    rf_sizes_df["formatted_size"] = rf_sizes_df["size"].apply(format_repo_size)
+    r_sizes_df.columns = ["Branch", "bytes", "Size"]
+    rf_sizes_df.columns = ["Extension", "bytes", "Count", "Size"]
+    rf_sizes_plot = px.pie(
+        rf_sizes_df,
+        values="bytes",
+        names="Extension",
+        hover_data=["Size"],
+        title=f"File Distribution in {r_id}",
+        hole=0.3,
+    )
+    return (
+        gr.Row(visible=True),
+        gr.Dataframe(
+            value=rf_sizes_df[["Extension", "Count", "Size"]],
+            visible=True,
+        ),
+        gr.Plot(rf_sizes_plot, visible=True),
+        gr.Dataframe(value=r_sizes_df[["Branch", "Size"]], visible=True),
+    )
+
+
+with gr.Blocks(theme="citrus") as demo:
+    gr.Markdown("# Repository Information")
+    gr.Markdown(
+        "Enter a repository ID and repository type and get back information about the repository's files and branches."
+    )
+    with gr.Blocks():
+        repo_id = gr.Textbox(label="Repository ID", placeholder="123456")
+        repo_type = gr.Radio(
+            choices=["model", "dataset", "space"],
+            label="Repository Type",
+            value="model",
+        )
+        search_button = gr.Button(value="Search")
+    with gr.Blocks():
+        with gr.Row(visible=False) as results:
+            with gr.Column():
+                gr.Markdown("## File Information")
+                with gr.Row():
+                    file_info = gr.Dataframe(visible=False)
+                    file_info_plot = gr.Plot(visible=False)
+                gr.Markdown("## Branch Sizes")
+                branch_sizes = gr.Dataframe(visible=False)
+
+    search_button.click(
+        get_repo_info,
+        inputs=[repo_type, repo_id],
+        outputs=[results, file_info, file_info_plot, branch_sizes],
+    )
+
+demo.launch()

pyproject.toml

@@ -0,0 +1,17 @@
+[tool.poetry]
+name = "repo-info"
+version = "0.1.0"
+description = ""
+authors = ["jsulz <[email protected]>"]
+readme = "README.md"
+
+[tool.poetry.dependencies]
+python = "^3.12"
+gradio = "^5.5.0"
+huggingface-hub = "^0.26.2"
+plotly = "^5.24.1"
+
+
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"

requirements.txt

@@ -0,0 +1,54 @@
+aiofiles==23.2.1 
+annotated-types==0.7.0 
+anyio==4.6.2.post1 
+certifi==2024.8.30 
+charset-normalizer==3.4.0 
+click==8.1.7  
+colorama==0.4.6
+fastapi==0.115.5 
+ffmpy==0.4.0 
+filelock==3.16.1 
+fsspec==2024.10.0 
+gradio-client==1.4.2 
+gradio==5.5.0 
+h11==0.14.0 
+httpcore==1.0.6 
+httpx==0.27.2 
+huggingface-hub==0.26.2 
+idna==3.10 
+jinja2==3.1.4 
+markdown-it-py==3.0.0  
+markupsafe==2.1.5 
+mdurl==0.1.2  
+numpy==2.1.3 
+orjson==3.10.11 
+packaging==24.2 
+pandas==2.2.3 
+pillow==11.0.0 
+plotly==5.24.1 
+pydantic-core==2.23.4 
+pydantic==2.9.2 
+pydub==0.25.1 
+pygments==2.18.0  
+python-dateutil==2.9.0.post0 
+python-multipart==0.0.12 
+pytz==2024.2 
+pyyaml==6.0.2 
+requests==2.32.3 
+rich==13.9.4  
+ruff==0.7.3  
+safehttpx==0.1.1 
+semantic-version==2.10.0 
+shellingham==1.5.4  
+six==1.16.0 
+sniffio==1.3.1 
+starlette==0.41.2 
+tenacity==9.0.0 
+tomlkit==0.12.0 
+tqdm==4.67.0 
+typer==0.13.0  
+typing-extensions==4.12.2 
+tzdata==2024.2 
+urllib3==2.2.3 
+uvicorn==0.32.0  
+websockets==12.0