From 8baf53b9525b3957c33fb5105a751ee742d33e5d Mon Sep 17 00:00:00 2001
From: Schuyler Martin <schuylermartin45@gmail.com>
Date: Tue, 13 Feb 2024 14:32:30 -0700
Subject: [PATCH] Handles `/about` section transformations for new format

- Handles transformations found in the new `/about` section. See
  [here](https://github.com/conda-incubator/ceps/blob/main/cep-14.md#about-section)
  for more details
---
 percy/parser/recipe_parser.py                 | 43 ++++++++++-
 percy/tests/parser/test_recipe_parser.py      |  2 +-
 .../new_format_huggingface_hub.yaml           | 75 +++++++++++++++++++
 3 files changed, 118 insertions(+), 2 deletions(-)
 create mode 100644 percy/tests/test_aux_files/new_format_huggingface_hub.yaml

diff --git a/percy/parser/recipe_parser.py b/percy/parser/recipe_parser.py
index df15371..c18fe0b 100644
--- a/percy/parser/recipe_parser.py
+++ b/percy/parser/recipe_parser.py
@@ -769,7 +769,48 @@ def _patch_and_log(patch: JsonPatchType) -> None:
                     _patch_and_log({"op": "add", "path": requirements_path, "value": None})
                 _patch_and_log({"op": "move", "from": old_ire_path, "path": new_ire_path})
 
-        # TODO Complete: handle changes to the recipe structure and fields
+        ## `about` section changes and validation ##
+        # Warn if "required" fields are missing
+        about_required: Final[list[str]] = [
+            "summary",
+            "description",
+            "license",
+            "license_file",
+            "license_url",
+        ]
+        for field in about_required:
+            path = f"/about/{field}"
+            if not new_recipe.contains_value(path):
+                msg_tbl.add_message(MessageCategory.WARNING, f"Required field missing: {path}")
+
+        # Transform renamed fields
+        about_rename: Final[list[tuple[str, str]]] = [
+            ("home", "homepage"),
+            ("dev_url", "repository"),
+            ("doc_url", "documentation"),
+        ]
+        for old, new in about_rename:
+            old_path = f"/about/{old}"
+            new_path = f"/about/{new}"
+            if new_recipe.contains_value(old_path):
+                _patch_and_log({"op": "move", "from": old_path, "path": new_path})
+
+        # TODO validate: /about/license must be SPDX recognized.
+
+        # Remove deprecated `about` fields
+        about_deprecated: Final[list[str]] = [
+            "prelink_message",
+            "license_family",
+            "identifiers",
+            "tags",
+            "keywords",
+            "doc_source_url",
+        ]
+        for field in about_deprecated:
+            path = f"/about/{field}"
+            if new_recipe.contains_value(path):
+                _patch_and_log({"op": "remove", "path": path})
+
         # TODO Complete: move operations may result in empty fields we can eliminate. This may require changes
         #                to `contains_value()`
 
diff --git a/percy/tests/parser/test_recipe_parser.py b/percy/tests/parser/test_recipe_parser.py
index 835b2c0..79f9cef 100644
--- a/percy/tests/parser/test_recipe_parser.py
+++ b/percy/tests/parser/test_recipe_parser.py
@@ -317,7 +317,7 @@ def test_render_to_object_multi_output() -> None:
     }
 
 
-@pytest.mark.parametrize("file_base", ["simple-recipe.yaml", "multi-output.yaml"])
+@pytest.mark.parametrize("file_base", ["simple-recipe.yaml", "multi-output.yaml", "huggingface_hub.yaml"])
 def test_render_to_new_recipe_format(file_base: str) -> None:
     """
     Validates rendering a recipe in the new format.
diff --git a/percy/tests/test_aux_files/new_format_huggingface_hub.yaml b/percy/tests/test_aux_files/new_format_huggingface_hub.yaml
new file mode 100644
index 0000000..4988ead
--- /dev/null
+++ b/percy/tests/test_aux_files/new_format_huggingface_hub.yaml
@@ -0,0 +1,75 @@
+schema_version: 1
+
+context:
+  name: huggingface_hub
+  version: 0.15.1
+
+package:
+  name: ${{ name|lower }}
+  version: ${{ version }}
+
+source:
+  url: https://pypi.io/packages/source/${{ name[0] }}/${{ name }}/${{ name }}-${{ version }}.tar.gz
+  sha256: a61b7d1a7769fe10119e730277c72ab99d95c48d86a3d6da3e9f3d0f632a4081
+
+build:
+  number: 0
+  skip: ${{ true if py<37 }}
+  entry_points:
+    - huggingface-cli=huggingface_hub.commands.huggingface_cli:main
+  script: ${{ PYTHON }} -m pip install . --no-deps --no-build-isolation -vv
+
+requirements:
+  host:
+    - python
+    - pip
+    - setuptools
+    - wheel
+  run:
+    - python
+    - filelock
+    - fsspec
+    - if: py<38
+      then: importlib-metadata
+    - packaging >=20.9
+    - pyyaml >=5.1
+    - requests
+    - tqdm >=4.42.1
+    - typing-extensions >=3.7.4.3
+  run_constrained:
+    - fastai >=2.4
+    - fastcore >=1.3.27
+    - InquirerPy ==0.3.4
+
+test:
+  imports:
+    - huggingface_hub
+    - huggingface_hub.commands
+  requires:
+    - pip
+  commands:
+    - pip check
+    - huggingface-cli --help
+
+about:
+  summary: Client library to download and publish models, datasets and other repos on the huggingface.co hub
+  description: |
+    The huggingface_hub is a client library to interact with the Hugging Face Hub. The Hugging Face Hub is a platform with over 35K models, 4K datasets, and 2K demos in which people can easily collaborate in their ML workflows. The Hub works as a central place where anyone can share, explore, discover, and experiment with open-source Machine Learning.
+
+    With huggingface_hub, you can easily download and upload models, datasets, and Spaces. You can extract useful information from the Hub, and do much more. Some example use cases:
+
+    - Downloading and caching files from a Hub repository.
+    - Creating repositories and uploading an updated model every few epochs.
+    - Extract metadata from all models that match certain criteria (e.g. models for text-classification).
+    - List all files from a specific repository.
+  license: Apache-2.0
+  license_file: LICENSE
+  homepage: https://github.com/huggingface/huggingface_hub
+  repository: https://github.com/huggingface/huggingface_hub
+  documentation: https://huggingface.co/docs/hub/index
+
+extra:
+  recipe-maintainers:
+    - BastianZim
+  skip-lints:
+    - python_build_tool_in_run