From bd2c17e2064528804eb33b75a85fd527da3baa03 Mon Sep 17 00:00:00 2001
From: Madeesh Kannan <shadeMe@users.noreply.github.com>
Date: Fri, 10 Nov 2023 08:05:07 +0100
Subject: [PATCH] Warn about reloading dependencies after downloading models
 (#13081)

* Update the "Missing factory" error message

This accounts for model installations that took place during the current Python session.

* Add a note about Jupyter notebooks

* Move error to `spacy.cli.download`
Add extra message for Jupyter sessions

* Add additional note for interactive sessions

* Remove note about `spacy-transformers` from error message

* `isort`

* Improve checks for colab (also helps displacy)

* Update warning messages

* Improve flow for multiple checks

---------

Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com>
---
 spacy/cli/download.py | 30 +++++++++++++++++++++++++++++-
 spacy/errors.py       |  1 -
 spacy/util.py         | 30 ++++++++++++++++++++++++------
 3 files changed, 53 insertions(+), 8 deletions(-)

diff --git a/spacy/cli/download.py b/spacy/cli/download.py
index de731b0fd..21c777f81 100644
--- a/spacy/cli/download.py
+++ b/spacy/cli/download.py
@@ -7,7 +7,14 @@ from wasabi import msg
 
 from .. import about
 from ..errors import OLD_MODEL_SHORTCUTS
-from ..util import get_minor_version, is_package, is_prerelease_version, run_command
+from ..util import (
+    get_minor_version,
+    is_in_interactive,
+    is_in_jupyter,
+    is_package,
+    is_prerelease_version,
+    run_command,
+)
 from ._util import SDIST_SUFFIX, WHEEL_SUFFIX, Arg, Opt, app
 
 
@@ -77,6 +84,27 @@ def download(
         "Download and installation successful",
         f"You can now load the package via spacy.load('{model_name}')",
     )
+    if is_in_jupyter():
+        reload_deps_msg = (
+            "If you are in a Jupyter or Colab notebook, you may need to "
+            "restart Python in order to load all the package's dependencies. "
+            "You can do this by selecting the 'Restart kernel' or 'Restart "
+            "runtime' option."
+        )
+        msg.warn(
+            "Restart to reload dependencies",
+            reload_deps_msg,
+        )
+    elif is_in_interactive():
+        reload_deps_msg = (
+            "If you are in an interactive Python session, you may need to "
+            "exit and restart Python to load all the package's dependencies. "
+            "You can exit with Ctrl-D (or Ctrl-Z and Enter on Windows)."
+        )
+        msg.warn(
+            "Restart to reload dependencies",
+            reload_deps_msg,
+        )
 
 
 def get_model_filename(model_name: str, version: str, sdist: bool = False) -> str:
diff --git a/spacy/errors.py b/spacy/errors.py
index dac07f804..8b290da6d 100644
--- a/spacy/errors.py
+++ b/spacy/errors.py
@@ -227,7 +227,6 @@ class Errors(metaclass=ErrorsWithCodes):
     E002 = ("Can't find factory for '{name}' for language {lang} ({lang_code}). "
             "This usually happens when spaCy calls `nlp.{method}` with a custom "
             "component name that's not registered on the current language class. "
-            "If you're using a Transformer, make sure to install 'spacy-transformers'. "
             "If you're using a custom component, make sure you've added the "
             "decorator `@Language.component` (for function components) or "
             "`@Language.factory` (for class components).\n\nAvailable "
diff --git a/spacy/util.py b/spacy/util.py
index 8464e411f..c127be03c 100644
--- a/spacy/util.py
+++ b/spacy/util.py
@@ -1077,20 +1077,38 @@ def make_tempdir() -> Generator[Path, None, None]:
 
 
 def is_in_jupyter() -> bool:
-    """Check if user is running spaCy from a Jupyter notebook by detecting the
-    IPython kernel. Mainly used for the displaCy visualizer.
-    RETURNS (bool): True if in Jupyter, False if not.
+    """Check if user is running spaCy from a Jupyter or Colab notebook by
+    detecting the IPython kernel. Mainly used for the displaCy visualizer.
+    RETURNS (bool): True if in Jupyter/Colab, False if not.
     """
     # https://stackoverflow.com/a/39662359/6400719
+    # https://stackoverflow.com/questions/15411967
     try:
-        shell = get_ipython().__class__.__name__  # type: ignore[name-defined]
-        if shell == "ZMQInteractiveShell":
+        if get_ipython().__class__.__name__ == "ZMQInteractiveShell":  # type: ignore[name-defined]
             return True  # Jupyter notebook or qtconsole
+        if get_ipython().__class__.__module__ == "google.colab._shell":  # type: ignore[name-defined]
+            return True  # Colab notebook
     except NameError:
-        return False  # Probably standard Python interpreter
+        pass  # Probably standard Python interpreter
+    # additional check for Colab
+    try:
+        import google.colab
+
+        return True  # Colab notebook
+    except ImportError:
+        pass
     return False
 
 
+def is_in_interactive() -> bool:
+    """Check if user is running spaCy from an interactive Python
+    shell. Will return True in Jupyter notebooks too.
+    RETURNS (bool): True if in interactive mode, False if not.
+    """
+    # https://stackoverflow.com/questions/2356399/tell-if-python-is-in-interactive-mode
+    return hasattr(sys, "ps1") or hasattr(sys, "ps2")
+
+
 def get_object_name(obj: Any) -> str:
     """Get a human-readable name of a Python object, e.g. a pipeline component.