Add cli for finding locations of registered func (#12757)

* Add cli for finding locations of registered func

* fixes: naming and typing

* isort

* update naming

* remove to find-function

* remove file:// bit

* use registry name if given and exit gracefully if a registry was not found

* clean up failure msg

* specify registry_name options

* mypy fixes

* return location for internal usage

* add documentation

* more mypy fixes

* clean up example

* add section to menu

* add tests

---------

Co-authored-by: svlandeg <svlandeg@github.com>

spacy/cli/__init__.py

@@ -14,6 +14,7 @@ from .debug_diff import debug_diff  # noqa: F401
 from .debug_model import debug_model  # noqa: F401
 from .download import download  # noqa: F401
 from .evaluate import evaluate  # noqa: F401
+from .find_function import find_function  # noqa: F401
 from .find_threshold import find_threshold  # noqa: F401
 from .info import info  # noqa: F401
 from .init_config import fill_config, init_config  # noqa: F401

spacy/cli/find_function.py

@@ -0,0 +1,69 @@
+from typing import Optional, Tuple
+
+from catalogue import RegistryError
+from wasabi import msg
+
+from ..util import registry
+from ._util import Arg, Opt, app
+
+
+@app.command("find-function")
+def find_function_cli(
+    # fmt: off
+    func_name: str = Arg(..., help="Name of the registered function."),
+    registry_name: Optional[str] = Opt(None, "--registry", "-r", help="Name of the catalogue registry."),
+    # fmt: on
+):
+    """
+    Find the module, path and line number to the file the registered
+    function is defined in, if available.
+
+    func_name (str): Name of the registered function.
+    registry_name (Optional[str]): Name of the catalogue registry.
+
+    DOCS: https://spacy.io/api/cli#find-function
+    """
+    if not registry_name:
+        registry_names = registry.get_registry_names()
+        for name in registry_names:
+            if registry.has(name, func_name):
+                registry_name = name
+                break
+
+    if not registry_name:
+        msg.fail(
+            f"Couldn't find registered function: '{func_name}'",
+            exits=1,
+        )
+
+    assert registry_name is not None
+    find_function(func_name, registry_name)
+
+
+def find_function(func_name: str, registry_name: str) -> Tuple[str, int]:
+    registry_desc = None
+    try:
+        registry_desc = registry.find(registry_name, func_name)
+    except RegistryError as e:
+        msg.fail(
+            f"Couldn't find registered function: '{func_name}' in registry '{registry_name}'",
+        )
+        msg.fail(f"{e}", exits=1)
+    assert registry_desc is not None
+
+    registry_path = None
+    line_no = None
+    if registry_desc["file"]:
+        registry_path = registry_desc["file"]
+        line_no = registry_desc["line_no"]
+
+    if not registry_path or not line_no:
+        msg.fail(
+            f"Couldn't find path to registered function: '{func_name}' in registry '{registry_name}'",
+            exits=1,
+        )
+    assert registry_path is not None
+    assert line_no is not None
+
+    msg.good(f"Found registered function '{func_name}' at {registry_path}:{line_no}")
+    return str(registry_path), int(line_no)

spacy/tests/test_cli_app.py

@@ -233,3 +233,37 @@ def test_project_push_pull(project_dir):
         result = CliRunner().invoke(app, ["project", "pull", remote, str(project_dir)])
         assert result.exit_code == 0
         assert test_file.is_file()
+
+
+def test_find_function_valid():
+    # example of architecture in main code base
+    function = "spacy.TextCatBOW.v2"
+    result = CliRunner().invoke(app, ["find-function", function, "-r", "architectures"])
+    assert f"Found registered function '{function}'" in result.stdout
+    assert "textcat.py" in result.stdout
+
+    result = CliRunner().invoke(app, ["find-function", function])
+    assert f"Found registered function '{function}'" in result.stdout
+    assert "textcat.py" in result.stdout
+
+    # example of architecture in spacy-legacy
+    function = "spacy.TextCatBOW.v1"
+    result = CliRunner().invoke(app, ["find-function", function])
+    assert f"Found registered function '{function}'" in result.stdout
+    assert "spacy_legacy" in result.stdout
+    assert "textcat.py" in result.stdout
+
+
+def test_find_function_invalid():
+    # invalid registry
+    function = "spacy.TextCatBOW.v2"
+    registry = "foobar"
+    result = CliRunner().invoke(
+        app, ["find-function", function, "--registry", registry]
+    )
+    assert f"Unknown function registry: '{registry}'" in result.stdout
+
+    # invalid function
+    function = "spacy.TextCatBOW.v666"
+    result = CliRunner().invoke(app, ["find-function", function])
+    assert f"Couldn't find registered function: '{function}'" in result.stdout

website/docs/api/cli.mdx

@@ -7,6 +7,7 @@ menu:
   - ['info', 'info']
   - ['validate', 'validate']
   - ['init', 'init']
+  - ['find-function', 'find-function']
   - ['convert', 'convert']
   - ['debug', 'debug']
   - ['train', 'train']
@@ -251,6 +252,27 @@ $ python -m spacy init labels [config_path] [output_path] [--code] [--verbose] [
 | overrides         | Config parameters to override. Should be options starting with `--` that correspond to the config section and value to override, e.g. `--paths.train ./train.spacy`. ~~Any (option/flag)~~                         |
 | **CREATES**       | The label files.                                                                                                                                                                                                   |
 
+## find-function {id="find-function",version="3.7",tag="command"}
+
+Find the module, path and line number to the file for a given registered
+function. This functionality is helpful to understand where registered
+functions, as used in the config file, are defined.
+
+```bash
+$ python -m spacy find-function [func_name] [--registry]
+```
+
+> #### Example
+>
+> ```bash
+> $ python -m spacy find-function spacy.TextCatBOW.v1
+> ```
+
+| Name               | Description                                           |
+| ------------------ | ----------------------------------------------------- |
+| `func_name`        | Name of the registered function. ~~str (positional)~~ |
+| `--registry`, `-r` | Name of the catalogue registry. ~~str (option)~~      |
+
 ## convert {id="convert",tag="command"}
 
 Convert files into spaCy's
@@ -1651,10 +1673,10 @@ $ python -m spacy huggingface-hub push [whl_path] [--org] [--msg] [--verbose]
 > $ python -m spacy huggingface-hub push en_ner_fashion-0.0.0-py3-none-any.whl
 > ```
 
-| Name                 | Description                                                                                                                                     |
+| Name              | Description                                                                                                         |
-| -------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------- |
+| ----------------- | ------------------------------------------------------------------------------------------------------------------- |
-| `whl_path`           | The path to the `.whl` file packaged with [`spacy package`](https://spacy.io/api/cli#package). ~~Path(positional)~~                             |
+| `whl_path`        | The path to the `.whl` file packaged with [`spacy package`](https://spacy.io/api/cli#package). ~~Path(positional)~~ |
-| `--org`, `-o`        | Optional name of organization to which the pipeline should be uploaded. ~~str (option)~~                                                        |
+| `--org`, `-o`     | Optional name of organization to which the pipeline should be uploaded. ~~str (option)~~                            |
-| `--msg`, `-m`        | Commit message to use for update. Defaults to `"Update spaCy pipeline"`. ~~str (option)~~                                                       |
+| `--msg`, `-m`     | Commit message to use for update. Defaults to `"Update spaCy pipeline"`. ~~str (option)~~                           |
-| `--verbose`, `-V`    | Output additional info for debugging, e.g. the full generated hub metadata. ~~bool (flag)~~                                                     |
+| `--verbose`, `-V` | Output additional info for debugging, e.g. the full generated hub metadata. ~~bool (flag)~~                         |
-| **UPLOADS**          | The pipeline to the hub.                                                                                                                        |
+| **UPLOADS**       | The pipeline to the hub.                                                                                            |