Merge remote-tracking branch 'upstream/v4' into store-activations

.github/azure-steps.yml

@@ -27,7 +27,6 @@ steps:
 
   - script: python -m mypy spacy
     displayName: 'Run mypy'
-    condition: ne(variables['python_version'], '3.10')
 
   - task: DeleteFiles@1
     inputs:
@@ -41,7 +40,7 @@ steps:
 
   - bash: |
       ${{ parameters.prefix }} SDIST=$(python -c "import os;print(os.listdir('./dist')[-1])" 2>&1)
-      ${{ parameters.prefix }} python -m pip install dist/$SDIST
+      ${{ parameters.prefix }} SPACY_NUM_BUILD_JOBS=2 python -m pip install dist/$SDIST
     displayName: "Install from sdist"
 
   - script: |
@@ -64,12 +63,12 @@ steps:
     displayName: "Run GPU tests"
     condition: eq(${{ parameters.gpu }}, true)
 
-#  - script: |
-#      python -m spacy download ca_core_news_sm
-#      python -m spacy download ca_core_news_md
-#      python -c "import spacy; nlp=spacy.load('ca_core_news_sm'); doc=nlp('test')"
-#    displayName: 'Test download CLI'
-#    condition: eq(variables['python_version'], '3.8')
+  - script: |
+      python -m spacy download ca_core_news_sm
+      python -m spacy download ca_core_news_md
+      python -c "import spacy; nlp=spacy.load('ca_core_news_sm'); doc=nlp('test')"
+    displayName: 'Test download CLI'
+    condition: eq(variables['python_version'], '3.8')
 
   - script: |
       python -m spacy convert extra/example_data/ner_example_data/ner-token-per-line-conll2003.json .
@@ -93,17 +92,17 @@ steps:
     displayName: 'Test train CLI'
     condition: eq(variables['python_version'], '3.8')
 
-#  - script: |
-#      python -c "import spacy; config = spacy.util.load_config('ner.cfg'); config['components']['ner'] = {'source': 'ca_core_news_sm'}; config.to_disk('ner_source_sm.cfg')"
-#      PYTHONWARNINGS="error,ignore::DeprecationWarning" python -m spacy assemble ner_source_sm.cfg output_dir
-#    displayName: 'Test assemble CLI'
-#    condition: eq(variables['python_version'], '3.8')
-#
-#  - script: |
-#      python -c "import spacy; config = spacy.util.load_config('ner.cfg'); config['components']['ner'] = {'source': 'ca_core_news_md'}; config.to_disk('ner_source_md.cfg')"
-#      python -m spacy assemble ner_source_md.cfg output_dir 2>&1 | grep -q W113
-#    displayName: 'Test assemble CLI vectors warning'
-#    condition: eq(variables['python_version'], '3.8')
+  - script: |
+      python -c "import spacy; config = spacy.util.load_config('ner.cfg'); config['components']['ner'] = {'source': 'ca_core_news_sm'}; config.to_disk('ner_source_sm.cfg')"
+      PYTHONWARNINGS="error,ignore::DeprecationWarning" python -m spacy assemble ner_source_sm.cfg output_dir
+    displayName: 'Test assemble CLI'
+    condition: eq(variables['python_version'], '3.8')
+
+  - script: |
+      python -c "import spacy; config = spacy.util.load_config('ner.cfg'); config['components']['ner'] = {'source': 'ca_core_news_md'}; config.to_disk('ner_source_md.cfg')"
+      python -m spacy assemble ner_source_md.cfg output_dir 2>&1 | grep -q W113
+    displayName: 'Test assemble CLI vectors warning'
+    condition: eq(variables['python_version'], '3.8')
 
   - script: |
       python .github/validate_universe_json.py website/meta/universe.json

.github/spacy_universe_alert.py

@@ -0,0 +1,67 @@
+import os
+import sys
+import json
+from datetime import datetime
+
+from slack_sdk.web.client import WebClient
+
+CHANNEL = "#alerts-universe"
+SLACK_TOKEN = os.environ.get("SLACK_BOT_TOKEN", "ENV VAR not available!")
+DATETIME_FORMAT = "%Y-%m-%dT%H:%M:%SZ"
+
+client = WebClient(SLACK_TOKEN)
+github_context = json.loads(sys.argv[1])
+
+event = github_context['event']
+pr_title = event['pull_request']["title"]
+pr_link = event['pull_request']["patch_url"].replace(".patch", "")
+pr_author_url = event['sender']["html_url"]
+pr_author_name = pr_author_url.rsplit('/')[-1]
+pr_created_at_dt = datetime.strptime(
+    event['pull_request']["created_at"],
+    DATETIME_FORMAT
+)
+pr_created_at = pr_created_at_dt.strftime("%c")
+pr_updated_at_dt = datetime.strptime(
+    event['pull_request']["updated_at"],
+    DATETIME_FORMAT
+)
+pr_updated_at = pr_updated_at_dt.strftime("%c")
+
+blocks = [
+    {
+      "type": "section",
+      "text": {
+        "type": "mrkdwn",
+        "text": "📣 New spaCy Universe Project Alert ✨"
+      }
+    },
+    {
+      "type": "section",
+      "fields": [
+        {
+          "type": "mrkdwn",
+          "text": f"*Pull Request:*\n<{pr_link}|{pr_title}>"
+        },
+        {
+          "type": "mrkdwn",
+          "text": f"*Author:*\n<{pr_author_url}|{pr_author_name}>"
+        },
+        {
+          "type": "mrkdwn",
+          "text": f"*Created at:*\n {pr_created_at}"
+        },
+        {
+          "type": "mrkdwn",
+          "text": f"*Last Updated:*\n {pr_updated_at}"
+        }
+      ]
+    }
+  ]
+
+
+client.chat_postMessage(
+    channel=CHANNEL,
+    text="spaCy universe project PR alert",
+    blocks=blocks
+)

.github/workflows/spacy_universe_alert.yml

@@ -0,0 +1,30 @@
+name: spaCy universe project alert
+
+on:
+  pull_request_target:
+    paths:
+      - "website/meta/universe.json"
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Dump GitHub context
+        env:
+          GITHUB_CONTEXT: ${{ toJson(github) }}
+          PR_NUMBER: ${{github.event.number}}
+        run: |
+          echo "$GITHUB_CONTEXT"
+
+      - uses: actions/checkout@v1
+      - uses: actions/setup-python@v1
+      - name: Install Bernadette app dependency and send an alert
+        env:
+          SLACK_BOT_TOKEN: ${{ secrets.SLACK_BOT_TOKEN }}
+          GITHUB_CONTEXT: ${{ toJson(github) }}
+          CHANNEL: "#alerts-universe"
+        run: |
+          pip install slack-sdk==3.17.2 aiohttp==3.8.1
+          echo "$CHANNEL"
+          python .github/spacy_universe_alert.py "$GITHUB_CONTEXT"

CONTRIBUTING.md

@@ -271,7 +271,8 @@ except:  # noqa: E722
 
 ### Python conventions
 
-All Python code must be written **compatible with Python 3.6+**.
+All Python code must be written **compatible with Python 3.6+**. More detailed
+code conventions can be found in the [developer docs](https://github.com/explosion/spaCy/blob/master/extra/DEVELOPER_DOCS/Code%20Conventions.md).
 
 #### I/O and handling paths
 

README.md

@@ -16,7 +16,7 @@ production-ready [**training system**](https://spacy.io/usage/training) and easy
 model packaging, deployment and workflow management. spaCy is commercial
 open-source software, released under the MIT license.
 
-💫 **Version 3.3.1 out now!**
+💫 **Version 3.4.0 out now!**
 [Check out the release notes here.](https://github.com/explosion/spaCy/releases)
 
 [![Azure Pipelines](https://img.shields.io/azure-devops/build/explosion-ai/public/8/master.svg?logo=azure-pipelines&style=flat-square&label=build)](https://dev.azure.com/explosion-ai/public/_build?definitionId=8)

build-constraints.txt

@@ -1,6 +1,8 @@
 # build version constraints for use with wheelwright + multibuild
-numpy==1.15.0; python_version<='3.7'
-numpy==1.17.3; python_version=='3.8'
+numpy==1.15.0; python_version<='3.7' and platform_machine!='aarch64'
+numpy==1.19.2; python_version<='3.7' and platform_machine=='aarch64'
+numpy==1.17.3; python_version=='3.8' and platform_machine!='aarch64'
+numpy==1.19.2; python_version=='3.8' and platform_machine=='aarch64'
 numpy==1.19.3; python_version=='3.9'
 numpy==1.21.3; python_version=='3.10'
 numpy; python_version>='3.11'

extra/DEVELOPER_DOCS/ExplosionBot.md

@@ -16,21 +16,41 @@ To summon the robot, write a github comment on the issue/PR you wish to test. Th
 
 Some things to note:
 
-* The `@explosion-bot please` must be the beginning of the command - you cannot add anything in front of this or else the robot won't know how to parse it. Adding anything at the end aside from the test name will also confuse the robot, so keep it simple!
-* The command name (such as `test_gpu`) must be one of the tests that the bot knows how to run. The available commands are documented in the bot's [workflow config](https://github.com/explosion/spaCy/blob/master/.github/workflows/explosionbot.yml#L26) and must match exactly one of the commands listed there.
-* The robot can't do multiple things at once, so if you want it to run multiple tests, you'll have to summon it with one comment per test.
-* For the `test_gpu` command, you can specify an optional thinc branch (from the spaCy repo) or a spaCy branch (from the thinc repo) with either the `--thinc-branch` or `--spacy-branch` flags. By default, the bot will pull in the PR branch from the repo where the command was issued, and the main branch of the other repository. However, if you need to run against another branch, you can say (for example):
+- The `@explosion-bot please` must be the beginning of the command - you cannot add anything in front of this or else the robot won't know how to parse it. Adding anything at the end aside from the test name will also confuse the robot, so keep it simple!
+- The command name (such as `test_gpu`) must be one of the tests that the bot knows how to run. The available commands are documented in the bot's [workflow config](https://github.com/explosion/spaCy/blob/master/.github/workflows/explosionbot.yml#L26) and must match exactly one of the commands listed there.
+- The robot can't do multiple things at once, so if you want it to run multiple tests, you'll have to summon it with one comment per test.
 
-```
-@explosion-bot please test_gpu --thinc-branch develop
-```
-You can also specify a branch from an unmerged PR:
-```
-@explosion-bot please test_gpu --thinc-branch refs/pull/633/head
-```
+### Examples
+
+- Execute spaCy slow GPU tests with a custom thinc branch from a spaCy PR:
+
+  ```
+  @explosion-bot please test_slow_gpu --thinc-branch <branch_name>
+  ```
+
+  `branch_name` can either be a named branch, e.g: `develop`, or an unmerged PR, e.g: `refs/pull/<pr_number>/head`.
+
+- Execute spaCy Transformers GPU tests from a spaCy PR:
+
+  ```
+  @explosion-bot please test_gpu --run-on spacy-transformers --run-on-branch master --spacy-branch current_pr
+  ```
+
+  This will launch the GPU pipeline for the `spacy-transformers` repo on its `master` branch, using the current spaCy PR's branch to build spaCy. The name of the repository passed to `--run-on` is case-sensitive, e.g: use `spaCy` instead of `spacy`.
+
+- General info about supported commands.
+
+  ```
+  @explosion-bot please info
+  ```
+
+- Help text for a specific command
+  ```
+  @explosion-bot please <command> --help
+  ```
 
 ## Troubleshooting
 
-If the robot isn't responding to commands as expected, you can check its logs in the [Github Action](https://github.com/explosion/spaCy/actions/workflows/explosionbot.yml). 
+If the robot isn't responding to commands as expected, you can check its logs in the [Github Action](https://github.com/explosion/spaCy/actions/workflows/explosionbot.yml).
 
 For each command sent to the bot, there should be a run of the `explosion-bot` workflow. In the `Install and run explosion-bot` step, towards the ends of the logs you should see info about the configuration that the bot was run with, as well as any errors that the bot encountered.

pyproject.toml

@@ -5,7 +5,7 @@ requires = [
     "cymem>=2.0.2,<2.1.0",
     "preshed>=3.0.2,<3.1.0",
     "murmurhash>=0.28.0,<1.1.0",
-    "thinc>=8.1.0.dev3,<8.2.0",
+    "thinc>=8.1.0,<8.2.0",
     "pathy",
     "numpy>=1.15.0",
 ]

requirements.txt

@@ -3,7 +3,7 @@ spacy-legacy>=3.0.9,<3.1.0
 spacy-loggers>=1.0.0,<2.0.0
 cymem>=2.0.2,<2.1.0
 preshed>=3.0.2,<3.1.0
-thinc>=8.1.0.dev3,<8.2.0
+thinc>=8.1.0,<8.2.0
 ml_datasets>=0.2.0,<0.3.0
 murmurhash>=0.28.0,<1.1.0
 wasabi>=0.9.1,<1.1.0
@@ -30,7 +30,7 @@ pytest-timeout>=1.3.0,<2.0.0
 mock>=2.0.0,<3.0.0
 flake8>=3.8.0,<3.10.0
 hypothesis>=3.27.0,<7.0.0
-mypy>=0.910,<=0.960
+mypy>=0.910,<0.970; platform_machine!='aarch64'
 types-dataclasses>=0.1.3; python_version < "3.7"
 types-mock>=0.1.1
 types-requests

setup.cfg

@@ -38,15 +38,15 @@ setup_requires =
     cymem>=2.0.2,<2.1.0
     preshed>=3.0.2,<3.1.0
     murmurhash>=0.28.0,<1.1.0
-    thinc>=8.1.0.dev3,<8.2.0
+    thinc>=8.1.0,<8.2.0
 install_requires =
     # Our libraries
     spacy-legacy>=3.0.9,<3.1.0
     spacy-loggers>=1.0.0,<2.0.0
     murmurhash>=0.28.0,<1.1.0
     cymem>=2.0.2,<2.1.0
     preshed>=3.0.2,<3.1.0
-    thinc>=8.1.0.dev3,<8.2.0
+    thinc>=8.1.0,<8.2.0
     wasabi>=0.9.1,<1.1.0
     srsly>=2.4.3,<3.0.0
     catalogue>=2.0.6,<2.1.0
@@ -103,14 +103,18 @@ cuda114 =
     cupy-cuda114>=5.0.0b4,<11.0.0
 cuda115 =
     cupy-cuda115>=5.0.0b4,<11.0.0
+cuda116 =
+    cupy-cuda116>=5.0.0b4,<11.0.0
+cuda117 =
+    cupy-cuda117>=5.0.0b4,<11.0.0
 apple =
     thinc-apple-ops>=0.1.0.dev0,<1.0.0
 # Language tokenizers with external dependencies
 ja =
     sudachipy>=0.5.2,!=0.6.1
     sudachidict_core>=20211220
 ko =
-    natto-py==0.9.0
+    natto-py>=0.9.0
 th =
     pythainlp>=2.0
 

setup.py

@@ -126,6 +126,8 @@ def build_options(self):
 
 class build_ext_subclass(build_ext, build_ext_options):
     def build_extensions(self):
+        if self.parallel is None and os.environ.get("SPACY_NUM_BUILD_JOBS") is not None:
+            self.parallel = int(os.environ.get("SPACY_NUM_BUILD_JOBS"))
         build_ext_options.build_options(self)
         build_ext.build_extensions(self)
 
@@ -206,7 +208,11 @@ def setup_package():
     for name in MOD_NAMES:
         mod_path = name.replace(".", "/") + ".pyx"
         ext = Extension(
-            name, [mod_path], language="c++", include_dirs=include_dirs, extra_compile_args=["-std=c++11"]
+            name,
+            [mod_path],
+            language="c++",
+            include_dirs=include_dirs,
+            extra_compile_args=["-std=c++11"],
         )
         ext_modules.append(ext)
     print("Cythonizing sources")

spacy/about.py

@@ -1,6 +1,6 @@
 # fmt: off
 __title__ = "spacy"
-__version__ = "3.4.0"
+__version__ = "3.4.1"
 __download_url__ = "https://github.com/explosion/spacy-models/releases/download"
 __compatibility__ = "https://raw.githubusercontent.com/explosion/spacy-models/master/compatibility.json"
 __projects__ = "https://github.com/explosion/projects"

spacy/cli/_util.py

@@ -462,6 +462,23 @@ def git_sparse_checkout(repo, subpath, dest, branch):
         shutil.move(str(source_path), str(dest))
 
 
+def git_repo_branch_exists(repo: str, branch: str) -> bool:
+    """Uses 'git ls-remote' to check if a repository and branch exists
+
+    repo (str): URL to get repo.
+    branch (str): Branch on repo to check.
+    RETURNS (bool): True if repo:branch exists.
+    """
+    get_git_version()
+    cmd = f"git ls-remote {repo} {branch}"
+    # We might be tempted to use `--exit-code` with `git ls-remote`, but
+    # `run_command` handles the `returncode` for us, so we'll rely on
+    # the fact that stdout returns '' if the requested branch doesn't exist
+    ret = run_command(cmd, capture=True)
+    exists = ret.stdout != ""
+    return exists
+
+
 def get_git_version(
     error: str = "Could not run 'git'. Make sure it's installed and the executable is available.",
 ) -> Tuple[int, int]:

spacy/cli/pretrain.py

@@ -61,7 +61,7 @@ def pretrain_cli(
         # TODO: What's the solution here? How do we handle optional blocks?
         msg.fail("The [pretraining] block in your config is empty", exits=1)
     if not output_dir.exists():
-        output_dir.mkdir()
+        output_dir.mkdir(parents=True)
         msg.good(f"Created output directory: {output_dir}")
     # Save non-interpolated config
     raw_config.to_disk(output_dir / "config.cfg")