Add GitHub repository seed reader plugin

.github/CODEOWNERS

@@ -7,4 +7,5 @@
 /.github/ @NVIDIA-NeMo/data_designer_reviewers
 
 # Plugins
+/plugins/data-designer-github/ @eric-tramel
 /plugins/data-designer-template/ @NVIDIA-NeMo/data_designer_reviewers

docs/catalog.md

@@ -4,4 +4,5 @@ Auto-generated from plugin metadata. Do not edit manually.
 
 | Plugin | Version | Column Type | Description |
 |--------|---------|-------------|-------------|
+| data-designer-github | 0.1.0 | `github` | GitHub and local git repository seed reader for Data Designer |
 | data-designer-template | 0.1.0 | `text-transform` | Template Data Designer plugin — text transform column generator |

plugins/data-designer-github/CODEOWNERS

@@ -0,0 +1,3 @@
+# Owner(s) of this plugin — used to generate the root CODEOWNERS file.
+# GitHub accepts @username, @org/team, or email format.
+* @eric-tramel

plugins/data-designer-github/README.md

@@ -0,0 +1,51 @@
+# data-designer-github
+
+GitHub and local git repository seed reader for
+[NeMo Data Designer](https://github.com/NVIDIA-NeMo/DataDesigner).
+
+## Installation
+
+```bash
+pip install data-designer-github
+```
+
+## Usage
+
+This plugin provides a `github` seed source. Once installed, the seed reader is
+automatically discovered by Data Designer.
+
+```python
+from data_designer.config.config_builder import DataDesignerConfigBuilder
+from data_designer.interface.data_designer import DataDesigner
+from data_designer_github.config import GitHubSeedSource
+
+builder = DataDesignerConfigBuilder()
+builder.with_seed_dataset(
+    GitHubSeedSource(
+        repositories=["NVIDIA-NeMo/DataDesigner"],
+        file_pattern="*.py",
+        recursive=True,
+    )
+)
+
+preview = DataDesigner().preview(builder, num_records=5)
+print(preview.dataset[["repo_id", "relative_path", "code_lang", "content"]])
+```
+
+The reader can also scan local git repositories:
+
+```python
+builder.with_seed_dataset(
+    GitHubSeedSource(
+        path="/path/to/repos",
+        repository_paths=["/path/to/one/repo"],
+        file_pattern="*.py",
+    )
+)
+```
+
+Seed columns include repository metadata, file paths, language hints, file
+content, and content SHA-256 hashes.
+
+For the full plugin authoring guide, see the
+[main repository docs](https://github.com/NVIDIA-NeMo/DataDesignerPlugins/blob/main/docs/adding-a-plugin.md).

plugins/data-designer-github/pyproject.toml

@@ -0,0 +1,36 @@
+# SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+# SPDX-License-Identifier: Apache-2.0
+
+[project]
+name = "data-designer-github"
+version = "0.1.0"
+description = "GitHub and local git repository seed reader for Data Designer"
+requires-python = ">=3.10"
+dependencies = [
+    "data-designer>=0.5.7",
+]
+license = "Apache-2.0"
+readme = "README.md"
+authors = [
+    {name = "NVIDIA Corporation"},
+]
+classifiers = [
+    "Development Status :: 3 - Alpha",
+    "Programming Language :: Python :: 3",
+]
+
+[project.entry-points."data_designer.plugins"]
+github = "data_designer_github.plugin:plugin"
+
+[project.urls]
+Repository = "https://github.com/NVIDIA-NeMo/DataDesignerPlugins"
+
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/data_designer_github"]
+
+[tool.ruff]
+extend = "../../pyproject.toml"

plugins/data-designer-github/src/data_designer_github/__init__.py

@@ -0,0 +1,2 @@
+# SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+# SPDX-License-Identifier: Apache-2.0

plugins/data-designer-github/src/data_designer_github/config.py

@@ -0,0 +1,217 @@
+# SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+# SPDX-License-Identifier: Apache-2.0
+
+from __future__ import annotations
+
+import codecs
+from pathlib import Path
+from typing import ClassVar, Literal
+
+from data_designer.config.base import ConfigBase
+from data_designer.config.seed_source import FileSystemSeedSource
+from pydantic import Field, field_validator, model_validator
+from typing_extensions import Self
+
+DEFAULT_CODE_EXTENSIONS = [
+    ".bash",
+    ".c",
+    ".cc",
+    ".cfg",
+    ".cpp",
+    ".cs",
+    ".css",
+    ".go",
+    ".h",
+    ".hpp",
+    ".html",
+    ".java",
+    ".js",
+    ".json",
+    ".jsx",
+    ".kt",
+    ".kts",
+    ".lua",
+    ".md",
+    ".php",
+    ".py",
+    ".rb",
+    ".rs",
+    ".scala",
+    ".sh",
+    ".sql",
+    ".swift",
+    ".toml",
+    ".ts",
+    ".tsx",
+    ".yaml",
+    ".yml",
+    ".zsh",
+]
+
+DEFAULT_CODE_FILENAMES = [
+    "Dockerfile",
+    "Makefile",
+]
+
+DEFAULT_EXCLUDE_PATTERNS = [
+    ".git/*",
+    ".git/**",
+    ".mypy_cache/*",
+    ".pytest_cache/*",
+    ".ruff_cache/*",
+    ".tox/*",
+    ".venv/*",
+    "__pycache__/*",
+    "build/*",
+    "dist/*",
+    "node_modules/*",
+    "venv/*",
+    "**/.git/*",
+    "**/.git/**",
+    "**/.mypy_cache/*",
+    "**/.pytest_cache/*",
+    "**/.ruff_cache/*",
+    "**/.tox/*",
+    "**/.venv/*",
+    "**/__pycache__/*",
+    "**/build/*",
+    "**/dist/*",
+    "**/node_modules/*",
+    "**/venv/*",
+]
+
+
+class GitHubSeedSource(FileSystemSeedSource, ConfigBase):
+    """Seed source for reading code files from GitHub and local git repositories."""
+
+    seed_type: Literal["github"] = "github"
+
+    path: str | None = Field(
+        None,
+        description=(
+            "Optional local git repository path, or a directory whose immediate children are git repositories. "
+            "Relative paths are resolved from the current working directory when the config is loaded."
+        ),
+    )
+    repositories: list[str] = Field(
+        default_factory=list,
+        description=(
+            "GitHub repositories to clone before reading. Each entry may be 'owner/name', "
+            "'https://github.com/owner/name', or 'https://github.com/owner/name.git'."
+        ),
+    )
+    repository_paths: list[str] = Field(
+        default_factory=list,
+        description="Additional local git repository paths to read.",
+    )
+    ref: str | None = Field(
+        None,
+        description="Optional branch, tag, or commit to check out after cloning GitHub repositories.",
+    )
+    clone_depth: int | None = Field(
+        1,
+        ge=1,
+        description="Depth for GitHub clones. Set to null for a full clone.",
+    )
+    clone_timeout_seconds: int = Field(
+        300,
+        ge=1,
+        description="Timeout for each git clone or checkout operation.",
+    )
+    include_extensions: list[str] | None = Field(
+        default_factory=lambda: list(DEFAULT_CODE_EXTENSIONS),
+        description=(
+            "Lowercase file extensions to include. Values may include or omit the leading dot. "
+            "Set to null to include every extension."
+        ),
+    )
+    include_file_names: list[str] = Field(
+        default_factory=lambda: list(DEFAULT_CODE_FILENAMES),
+        description="Extensionless file names to include, such as Dockerfile or Makefile.",
+    )
+    exclude_patterns: list[str] = Field(
+        default_factory=lambda: list(DEFAULT_EXCLUDE_PATTERNS),
+        description="Relative path glob patterns to exclude from repository scans.",
+    )
+    max_file_size_bytes: int = Field(
+        1_000_000,
+        ge=1,
+        description="Maximum file size to hydrate into the content column.",
+    )
+    encoding: str = Field(
+        "utf-8",
+        description="Text encoding used when hydrating repository file contents.",
+    )
+
+    _source_fields: ClassVar[tuple[str, ...]] = ("path", "repositories", "repository_paths")
+
+    @model_validator(mode="after")
+    def validate_has_repository_source(self) -> Self:
+        """Ensure the seed source has at least one repository source."""
+        if self.path is None and not self.repositories and not self.repository_paths:
+            fields = ", ".join(self._source_fields)
+            raise ValueError(f"At least one of {fields} must be provided.")
+        return self
+
+    @field_validator("encoding", mode="after")
+    @classmethod
+    def validate_encoding(cls, value: str) -> str:
+        """Validate that the configured text encoding exists."""
+        try:
+            codecs.lookup(value)
+        except LookupError as error:
+            raise ValueError(f"Unknown encoding: {value!r}. Use a valid Python codec name.") from error
+        return value
+
+    @field_validator("include_extensions", mode="after")
+    @classmethod
+    def normalize_include_extensions(cls, value: list[str] | None) -> list[str] | None:
+        """Normalize configured extensions to lowercase dotted values."""
+        if value is None:
+            return None
+
+        normalized: list[str] = []
+        for extension in value:
+            stripped = extension.strip().lower()
+            if not stripped:
+                raise ValueError("include_extensions cannot contain empty values.")
+            normalized.append(stripped if stripped.startswith(".") else f".{stripped}")
+        return sorted(set(normalized))
+
+    @field_validator("include_file_names", "exclude_patterns", mode="after")
+    @classmethod
+    def validate_non_empty_strings(cls, value: list[str]) -> list[str]:
+        """Validate string list fields do not contain blank entries."""
+        for item in value:
+            if not item.strip():
+                raise ValueError("String lists cannot contain empty values.")
+        return value
+
+    @field_validator("repositories", mode="after")
+    @classmethod
+    def validate_repositories(cls, value: list[str]) -> list[str]:
+        """Validate repository specs do not contain blank entries."""
+        for repository in value:
+            if not repository.strip():
+                raise ValueError("repositories cannot contain empty values.")
+        return value
+
+    @field_validator("repository_paths", mode="after")
+    @classmethod
+    def validate_repository_paths(cls, value: list[str]) -> list[str]:
+        """Validate explicit local repository paths exist."""
+        for repository_path in value:
+            path = Path(repository_path).expanduser().resolve()
+            if not path.is_dir():
+                raise ValueError(f"Repository path {path} is not a directory.")
+        return value
+
+    @property
+    def runtime_path(self) -> str:
+        """Return the resolved local scan root after a reader has prepared it."""
+        if self._runtime_path is not None:
+            return self._runtime_path
+        if self.path is None:
+            raise ValueError("GitHubSeedSource.runtime_path is available after the seed reader is attached.")
+        self._runtime_path = str(Path(self.path).expanduser().resolve())
+        return self._runtime_path