Merge remote-tracking branch 'upstream/master' into chore/update-develop-from-master-v3.5

website/docs/usage/projects.md

@@ -243,6 +243,27 @@ pipelines.
 > python -m spacy project run test . --vars.foo bar
 > ```
 
+> #### Tip: Environment Variables
+>
+> Commands in a project file are not executed in a shell, so they don't have
+> direct access to environment variables. But you can insert environment
+> variables using the `env` dictionary to make values available for
+> interpolation, just like values in `vars`. Here's an example `env` dict that
+> makes `$PATH` available as `ENV_PATH`:
+>
+> ```yaml
+> env:
+>   ENV_PATH: PATH
+> ```
+>
+> This can be used in a project command like so:
+>
+> ```yaml
+>   - name: "echo-path"
+>     script:
+>       - "echo ${env.ENV_PATH}"
+> ```
+
 | Section                                             | Description                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  |
 | --------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
 | `title`                                             | An optional project title used in `--help` message and [auto-generated docs](#custom-docs).                                                                                                                                                                                                                                                                                                                                                                                                                  |

website/meta/universe.json

@@ -1,5 +1,46 @@
 {
     "resources": [
+        {
+            "id": "spacy-cleaner",
+            "title": "spacy-cleaner",
+            "slogan": "Easily clean text with spaCy!",
+            "description": "**spacy-cleaner** utilises spaCy `Language` models to replace, remove, and \n  mutate spaCy tokens. Cleaning actions available are:\n\n* Remove/replace stopwords.\n* Remove/replace punctuation.\n* Remove/replace numbers.\n* Remove/replace emails.\n* Remove/replace URLs.\n* Perform lemmatisation.\n\nSee our [docs](https://ce11an.github.io/spacy-cleaner/) for more information.",
+            "github": "Ce11an/spacy-cleaner",
+            "pip": "spacy-cleaner",
+            "code_example": [
+                "import spacy",
+                "import spacy_cleaner",
+                "from spacy_cleaner.processing import removers, replacers, mutators",
+                "",
+                "model = spacy.load(\"en_core_web_sm\")",
+                "pipeline = spacy_cleaner.Pipeline(",
+                "    model,",
+                "    removers.remove_stopword_token,",
+                "    replacers.replace_punctuation_token,",
+                "    mutators.mutate_lemma_token,",
+                ")",
+                "",
+                "texts = [\"Hello, my name is Cellan! I love to swim!\"]",
+                "",
+                "pipeline.clean(texts)",
+                "# ['hello _IS_PUNCT_ Cellan _IS_PUNCT_ love swim _IS_PUNCT_']"
+            ],
+            "code_language": "python",
+            "url": "https://ce11an.github.io/spacy-cleaner/",
+            "image": "https://raw.githubusercontent.com/Ce11an/spacy-cleaner/main/docs/assets/images/spacemen.png",
+            "author": "Cellan Hall",
+            "author_links": {
+                "twitter": "Ce11an",
+                "github": "Ce11an",
+                "website": "https://www.linkedin.com/in/cellan-hall/"
+            },
+            "category": [
+                "extension"
+            ],
+            "tags": [
+                "text-processing"
+            ]
+        },
         {
             "id": "Zshot",
             "title": "Zshot",