Switch zh tokenizer default pkuseg_model to spacy_ontonotes (#12896)

So that users can use `copy_from_base_model` for other segmenters
without having to override an irrelevant `pkuseg_model` setting, switch
the default `pkuseg_model` to `spacy_ontonotes`.

.github/ISSUE_TEMPLATE/01_bugs.md

@@ -4,11 +4,13 @@ about: Use this template if you came across a bug or unexpected behaviour differ
 
 ---
 
+<!-- NOTE: For questions or install related issues, please open a Discussion instead. -->
+
 ## How to reproduce the behaviour
 <!-- Include a code example or the steps that led to the problem. Please try to be as specific as possible. -->
 
 ## Your Environment
-<!-- Include details of your environment. If you're using spaCy 1.7+, you can also type `python -m spacy info --markdown` and copy-paste the result here.-->
+<!-- Include details of your environment. You can also type `python -m spacy info --markdown` and copy-paste the result here.-->
 * Operating System:
 * Python Version Used:
 * spaCy Version Used:

.github/ISSUE_TEMPLATE/config.yml

@@ -1,8 +1,5 @@
 blank_issues_enabled: false
 contact_links:
-  - name: ⚠️ Python 3.10 Support
-    url: https://github.com/explosion/spaCy/discussions/9418
-    about: Python 3.10 wheels haven't been released yet, see the link for details.
   - name: 🗯 Discussions Forum
     url: https://github.com/explosion/spaCy/discussions
     about: Install issues, usage questions, general discussion and anything else that isn't a bug report.

.github/azure-steps.yml

@@ -1,117 +0,0 @@
-parameters:
-  python_version: ''
-  architecture: ''
-  prefix: ''
-  gpu: false
-  num_build_jobs: 1
-
-steps:
-  - task: UsePythonVersion@0
-    inputs:
-      versionSpec: ${{ parameters.python_version }}
-      architecture: ${{ parameters.architecture }}
-
-  - bash: |
-      echo "##vso[task.setvariable variable=python_version]${{ parameters.python_version }}"
-    displayName: 'Set variables'
-
-  - script: |
-      ${{ parameters.prefix }} python -m pip install -U pip setuptools
-      ${{ parameters.prefix }} python -m pip install -U -r requirements.txt
-    displayName: "Install dependencies"
-
-  - script: |
-      ${{ parameters.prefix }} python setup.py build_ext --inplace -j ${{ parameters.num_build_jobs }}
-      ${{ parameters.prefix }} python setup.py sdist --formats=gztar
-    displayName: "Compile and build sdist"
-
-  - script: python -m mypy spacy
-    displayName: 'Run mypy'
-    condition: ne(variables['python_version'], '3.10')
-
-  - task: DeleteFiles@1
-    inputs:
-      contents: "spacy"
-    displayName: "Delete source directory"
-
-  - script: |
-      ${{ parameters.prefix }} python -m pip freeze --exclude torch --exclude cupy-cuda110 > installed.txt
-      ${{ parameters.prefix }} python -m pip uninstall -y -r installed.txt
-    displayName: "Uninstall all packages"
-
-  - bash: |
-      ${{ parameters.prefix }} SDIST=$(python -c "import os;print(os.listdir('./dist')[-1])" 2>&1)
-      ${{ parameters.prefix }} python -m pip install dist/$SDIST
-    displayName: "Install from sdist"
-
-  - script: |
-      ${{ parameters.prefix }} python -m pip install -U -r requirements.txt
-    displayName: "Install test requirements"
-
-  - script: |
-      ${{ parameters.prefix }} python -m pip install -U cupy-cuda110 -f https://github.com/cupy/cupy/releases/v9.0.0
-      ${{ parameters.prefix }} python -m pip install "torch==1.7.1+cu110" -f https://download.pytorch.org/whl/torch_stable.html
-    displayName: "Install GPU requirements"
-    condition: eq(${{ parameters.gpu }}, true)
-
-  - script: |
-      ${{ parameters.prefix }} python -m pytest --pyargs spacy
-    displayName: "Run CPU tests"
-    condition: eq(${{ parameters.gpu }}, false)
-
-  - script: |
-      ${{ parameters.prefix }} python -m pytest --pyargs spacy -p spacy.tests.enable_gpu
-    displayName: "Run GPU tests"
-    condition: eq(${{ 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 convert extra/example_data/ner_example_data/ner-token-per-line-conll2003.json .
-    displayName: 'Test convert CLI'
-    condition: eq(variables['python_version'], '3.8')
-
-  - script: |
-      python -m spacy init config -p ner -l ca ner.cfg
-      python -m spacy debug config ner.cfg --paths.train ner-token-per-line-conll2003.spacy --paths.dev ner-token-per-line-conll2003.spacy
-    displayName: 'Test debug config CLI'
-    condition: eq(variables['python_version'], '3.8')
-
-  - script: |
-      # will have errors due to sparse data, check for summary in output
-      python -m spacy debug data ner.cfg --paths.train ner-token-per-line-conll2003.spacy --paths.dev ner-token-per-line-conll2003.spacy | grep -q Summary
-    displayName: 'Test debug data CLI'
-    condition: eq(variables['python_version'], '3.8')
-
-  - script: |
-      python -m spacy train ner.cfg --paths.train ner-token-per-line-conll2003.spacy --paths.dev ner-token-per-line-conll2003.spacy --training.max_steps 10 --gpu-id -1
-    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 .github/validate_universe_json.py website/meta/universe.json
-    displayName: 'Test website/meta/universe.json'
-    condition: eq(variables['python_version'], '3.8')
-
-  - script: |
-      ${{ parameters.prefix }} python -m pip install thinc-apple-ops
-      ${{ parameters.prefix }} python -m pytest --pyargs spacy
-    displayName: "Run CPU tests with thinc-apple-ops"
-    condition: and(startsWith(variables['imageName'], 'macos'), eq(variables['python.version'], '3.9'))

.github/contributors/Lucaterre.md

@@ -0,0 +1,106 @@
+# spaCy contributor agreement
+
+This spaCy Contributor Agreement (**"SCA"**) is based on the
+[Oracle Contributor Agreement](http://www.oracle.com/technetwork/oca-405177.pdf).
+The SCA applies to any contribution that you make to any product or project
+managed by us (the **"project"**), and sets out the intellectual property rights
+you grant to us in the contributed materials. The term **"us"** shall mean
+[ExplosionAI GmbH](https://explosion.ai/legal). The term
+**"you"** shall mean the person or entity identified below.
+
+If you agree to be bound by these terms, fill in the information requested
+below and include the filled-in version with your first pull request, under the
+folder [`.github/contributors/`](/.github/contributors/). The name of the file
+should be your GitHub username, with the extension `.md`. For example, the user
+example_user would create the file `.github/contributors/example_user.md`.
+
+Read this agreement carefully before signing. These terms and conditions
+constitute a binding legal agreement.
+
+## Contributor Agreement
+
+1. The term "contribution" or "contributed materials" means any source code,
+object code, patch, tool, sample, graphic, specification, manual,
+documentation, or any other material posted or submitted by you to the project.
+
+2. With respect to any worldwide copyrights, or copyright applications and
+registrations, in your contribution:
+
+    * you hereby assign to us joint ownership, and to the extent that such
+    assignment is or becomes invalid, ineffective or unenforceable, you hereby
+    grant to us a perpetual, irrevocable, non-exclusive, worldwide, no-charge,
+    royalty-free, unrestricted license to exercise all rights under those
+    copyrights. This includes, at our option, the right to sublicense these same
+    rights to third parties through multiple levels of sublicensees or other
+    licensing arrangements;
+
+    * you agree that each of us can do all things in relation to your
+    contribution as if each of us were the sole owners, and if one of us makes
+    a derivative work of your contribution, the one who makes the derivative
+    work (or has it made will be the sole owner of that derivative work;
+
+    * you agree that you will not assert any moral rights in your contribution
+    against us, our licensees or transferees;
+
+    * you agree that we may register a copyright in your contribution and
+    exercise all ownership rights associated with it; and
+
+    * you agree that neither of us has any duty to consult with, obtain the
+    consent of, pay or render an accounting to the other for any use or
+    distribution of your contribution.
+
+3. With respect to any patents you own, or that you can license without payment
+to any third party, you hereby grant to us a perpetual, irrevocable,
+non-exclusive, worldwide, no-charge, royalty-free license to:
+
+    * make, have made, use, sell, offer to sell, import, and otherwise transfer
+    your contribution in whole or in part, alone or in combination with or
+    included in any product, work or materials arising out of the project to
+    which your contribution was submitted, and
+
+    * at our option, to sublicense these same rights to third parties through
+    multiple levels of sublicensees or other licensing arrangements.
+
+4. Except as set out above, you keep all right, title, and interest in your
+contribution. The rights that you grant to us under these terms are effective
+on the date you first submitted a contribution to us, even if your submission
+took place before the date you sign these terms.
+
+5. You covenant, represent, warrant and agree that:
+
+    * Each contribution that you submit is and shall be an original work of
+    authorship and you can legally grant the rights set out in this SCA;
+
+    * to the best of your knowledge, each contribution will not violate any
+    third party's copyrights, trademarks, patents, or other intellectual
+    property rights; and
+
+    * each contribution shall be in compliance with U.S. export control laws and
+    other applicable export and import laws. You agree to notify us if you
+    become aware of any circumstance which would make any of the foregoing
+    representations inaccurate in any respect. We may publicly disclose your
+    participation in the project, including the fact that you have signed the SCA.
+
+6. This SCA is governed by the laws of the State of California and applicable
+U.S. Federal law. Any choice of law rules will not apply.
+
+7. Please place an “x” on one of the applicable statement below. Please do NOT
+mark both statements:
+
+    * [x] I am signing on behalf of myself as an individual and no other person
+    or entity, including my employer, has or will have rights with respect to my
+    contributions.
+
+    * [ ] I am signing on behalf of my employer or a legal entity and I have the
+    actual authority to contractually bind that entity.
+
+## Contributor Details
+
+| Field                          | Entry         |
+|------------------------------- |---------------|
+| Name                           | Lucas Terriel |
+| Company name (if applicable)   |               |
+| Title or role (if applicable)  |               |
+| Date                           | 2022-06-20    |
+| GitHub username                | Lucaterre     |
+| Website (optional)             |               |

.github/contributors/fonfonx.md

@@ -0,0 +1,106 @@
+# spaCy contributor agreement
+
+This spaCy Contributor Agreement (**"SCA"**) is based on the
+[Oracle Contributor Agreement](http://www.oracle.com/technetwork/oca-405177.pdf).
+The SCA applies to any contribution that you make to any product or project
+managed by us (the **"project"**), and sets out the intellectual property rights
+you grant to us in the contributed materials. The term **"us"** shall mean
+[ExplosionAI GmbH](https://explosion.ai/legal). The term
+**"you"** shall mean the person or entity identified below.
+
+If you agree to be bound by these terms, fill in the information requested
+below and include the filled-in version with your first pull request, under the
+folder [`.github/contributors/`](/.github/contributors/). The name of the file
+should be your GitHub username, with the extension `.md`. For example, the user
+example_user would create the file `.github/contributors/example_user.md`.
+
+Read this agreement carefully before signing. These terms and conditions
+constitute a binding legal agreement.
+
+## Contributor Agreement
+
+1. The term "contribution" or "contributed materials" means any source code,
+object code, patch, tool, sample, graphic, specification, manual,
+documentation, or any other material posted or submitted by you to the project.
+
+2. With respect to any worldwide copyrights, or copyright applications and
+registrations, in your contribution:
+
+    * you hereby assign to us joint ownership, and to the extent that such
+    assignment is or becomes invalid, ineffective or unenforceable, you hereby
+    grant to us a perpetual, irrevocable, non-exclusive, worldwide, no-charge,
+    royalty-free, unrestricted license to exercise all rights under those
+    copyrights. This includes, at our option, the right to sublicense these same
+    rights to third parties through multiple levels of sublicensees or other
+    licensing arrangements;
+
+    * you agree that each of us can do all things in relation to your
+    contribution as if each of us were the sole owners, and if one of us makes
+    a derivative work of your contribution, the one who makes the derivative
+    work (or has it made will be the sole owner of that derivative work;
+
+    * you agree that you will not assert any moral rights in your contribution
+    against us, our licensees or transferees;
+
+    * you agree that we may register a copyright in your contribution and
+    exercise all ownership rights associated with it; and
+
+    * you agree that neither of us has any duty to consult with, obtain the
+    consent of, pay or render an accounting to the other for any use or
+    distribution of your contribution.
+
+3. With respect to any patents you own, or that you can license without payment
+to any third party, you hereby grant to us a perpetual, irrevocable,
+non-exclusive, worldwide, no-charge, royalty-free license to:
+
+    * make, have made, use, sell, offer to sell, import, and otherwise transfer
+    your contribution in whole or in part, alone or in combination with or
+    included in any product, work or materials arising out of the project to
+    which your contribution was submitted, and
+
+    * at our option, to sublicense these same rights to third parties through
+    multiple levels of sublicensees or other licensing arrangements.
+
+4. Except as set out above, you keep all right, title, and interest in your
+contribution. The rights that you grant to us under these terms are effective
+on the date you first submitted a contribution to us, even if your submission
+took place before the date you sign these terms.
+
+5. You covenant, represent, warrant and agree that:
+
+    * Each contribution that you submit is and shall be an original work of
+    authorship and you can legally grant the rights set out in this SCA;
+
+    * to the best of your knowledge, each contribution will not violate any
+    third party's copyrights, trademarks, patents, or other intellectual
+    property rights; and
+
+    * each contribution shall be in compliance with U.S. export control laws and
+    other applicable export and import laws. You agree to notify us if you
+    become aware of any circumstance which would make any of the foregoing
+    representations inaccurate in any respect. We may publicly disclose your
+    participation in the project, including the fact that you have signed the SCA.
+
+6. This SCA is governed by the laws of the State of California and applicable
+U.S. Federal law. Any choice of law rules will not apply.
+
+7. Please place an “x” on one of the applicable statement below. Please do NOT
+mark both statements:
+
+    * [x] I am signing on behalf of myself as an individual and no other person
+    or entity, including my employer, has or will have rights with respect to my
+    contributions.
+
+    * [ ] I am signing on behalf of my employer or a legal entity and I have the
+    actual authority to contractually bind that entity.
+
+## Contributor Details
+
+| Field                          | Entry                |
+|------------------------------- | -------------------- |
+| Name                           | Xavier Fontaine      |
+| Company name (if applicable)   |                      |
+| Title or role (if applicable)  |                      |
+| Date                           | 2022-04-13           |
+| GitHub username                | fonfonx              |
+| Website (optional)             |                      |

.github/no-response.yml

@@ -1,13 +0,0 @@
-# Configuration for probot-no-response - https://github.com/probot/no-response
-
-# Number of days of inactivity before an Issue is closed for lack of response
-daysUntilClose: 14
-# Label requiring a response
-responseRequiredLabel: more-info-needed
-# Comment to post when closing an Issue for lack of response. Set to `false` to disable
-closeComment: >
-  This issue has been automatically closed because there has been no response
-  to a request for more information from the original author. With only the
-  information that is currently in the issue, there's not enough information
-  to take action. If you're the original author, feel free to reopen the issue
-  if you have or find the answers needed to investigate further.

.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/autoblack.yml

@@ -1,44 +0,0 @@
-# GitHub Action that uses Black to reformat all Python code and submits a PR
-# in regular intervals. Inspired by: https://github.com/cclauss/autoblack
-
-name: autoblack
-on:
-  workflow_dispatch:  # allow manual trigger
-  schedule:
-    - cron: '0 8 * * 5'  # every Friday at 8am UTC
-
-jobs:
-  autoblack:
-    if: github.repository_owner == 'explosion'
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v2
-        with:
-            ref: ${{ github.head_ref }}
-      - uses: actions/setup-python@v2
-      - run: pip install black
-      - name: Auto-format code if needed
-        run: black spacy
-      # We can't run black --check here because that returns a non-zero excit
-      # code and makes GitHub think the action failed
-      - name: Check for modified files
-        id: git-check
-        run: echo ::set-output name=modified::$(if git diff-index --quiet HEAD --; then echo "false"; else echo "true"; fi)
-      - name: Create Pull Request
-        if: steps.git-check.outputs.modified == 'true'
-        uses: peter-evans/create-pull-request@v3
-        with:
-            title: Auto-format code with black
-            labels: meta
-            commit-message: Auto-format code with black
-            committer: GitHub <noreply@github.com>
-            author: explosion-bot <explosion-bot@users.noreply.github.com>
-            body: _This PR is auto-generated._
-            branch: autoblack
-            delete-branch: true
-            draft: false
-      - name: Check outputs
-        if: steps.git-check.outputs.modified == 'true'
-        run: |
-          echo "Pull Request Number - ${{ steps.cpr.outputs.pull-request-number }}"
-          echo "Pull Request URL - ${{ steps.cpr.outputs.pull-request-url }}"

.github/workflows/explosionbot.yml

@@ -8,14 +8,15 @@ on:
 
 jobs:
   explosion-bot:
-    runs-on: ubuntu-18.04
+    if: github.repository_owner == 'explosion'
+    runs-on: ubuntu-latest
     steps:
       - name: Dump GitHub context
         env:
           GITHUB_CONTEXT: ${{ toJson(github) }}
         run: echo "$GITHUB_CONTEXT"
-      - uses: actions/checkout@v1
-      - uses: actions/setup-python@v1
+      - uses: actions/checkout@v3
+      - uses: actions/setup-python@v4
       - name: Install and run explosion-bot
         run: |
           pip install git+https://${{ secrets.EXPLOSIONBOT_TOKEN }}@github.com/explosion/explosion-bot
@@ -23,5 +24,5 @@ jobs:
         env:
           INPUT_TOKEN: ${{ secrets.EXPLOSIONBOT_TOKEN }}
           INPUT_BK_TOKEN: ${{ secrets.BUILDKITE_SECRET }}
-          ENABLED_COMMANDS: "test_gpu,test_slow"
+          ENABLED_COMMANDS: "test_gpu,test_slow,test_slow_gpu"
           ALLOWED_TEAMS: "spaCy"

.github/workflows/gputests.yml

@@ -0,0 +1,22 @@
+name: Weekly GPU tests
+
+on:
+  schedule:
+    - cron: '0 1 * * MON'
+
+jobs:
+  weekly-gputests:
+    strategy:
+      fail-fast: false
+      matrix:
+        branch: [master, v4]
+    if: github.repository_owner == 'explosion'
+    runs-on: ubuntu-latest
+    steps:
+      - name: Trigger buildkite build
+        uses: buildkite/trigger-pipeline-action@v1.2.0
+        env:
+          PIPELINE: explosion-ai/spacy-slow-gpu-tests
+          BRANCH: ${{ matrix.branch }}
+          MESSAGE: ":github: Weekly GPU + slow tests - triggered from a GitHub Action"
+          BUILDKITE_API_ACCESS_TOKEN: ${{ secrets.BUILDKITE_SECRET }}

.github/workflows/issue-manager.yml

@@ -13,9 +13,10 @@ on:
 
 jobs:
   issue-manager:
+    if: github.repository_owner == 'explosion'
     runs-on: ubuntu-latest
     steps:
-      - uses: tiangolo/issue-manager@0.2.1
+      - uses: tiangolo/issue-manager@0.4.0
         with:
           token: ${{ secrets.GITHUB_TOKEN }}
           config: >
@@ -25,5 +26,11 @@ jobs:
                 "message": "This issue has been automatically closed because it was answered and there was no follow-up discussion.",
                 "remove_label_on_comment": true,
                 "remove_label_on_close": true
+              },
+              "more-info-needed": {
+                "delay": "P7D",
+                "message": "This issue has been automatically closed because there has been no response to a request for more information from the original author. With only the information that is currently in the issue, there's not enough information to take action. If you're the original author, feel free to reopen the issue if you have or find the answers needed to investigate further.",
+                "remove_label_on_comment": true,
+                "remove_label_on_close": true
               }
             }

.github/workflows/lock.yml

@@ -13,13 +13,14 @@ concurrency:
 
 jobs:
   action:
+    if: github.repository_owner == 'explosion'
     runs-on: ubuntu-latest
     steps:
-      - uses: dessant/lock-threads@v3
+      - uses: dessant/lock-threads@v4
         with:
           process-only: 'issues'
           issue-inactive-days: '30'
-          issue-comment: > 
-            This thread has been automatically locked since there 
-            has not been any recent activity after it was closed. 
+          issue-comment: >
+            This thread has been automatically locked since there
+            has not been any recent activity after it was closed.
             Please open a new issue for related bugs.

.github/workflows/slowtests.yml

@@ -0,0 +1,38 @@
+name: Daily slow tests
+
+on:
+  schedule:
+    - cron: '0 0 * * *'
+
+jobs:
+  daily-slowtests:
+    strategy:
+      fail-fast: false
+      matrix:
+        branch: [master, v4]
+    if: github.repository_owner == 'explosion'
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+        with:
+          ref: ${{ matrix.branch }}
+      - name: Get commits from past 24 hours
+        id: check_commits
+        run: |
+          today=$(date '+%Y-%m-%d %H:%M:%S')
+          yesterday=$(date -d "yesterday" '+%Y-%m-%d %H:%M:%S')
+          if git log --after="$yesterday" --before="$today" | grep commit ; then
+            echo run_tests=true >> $GITHUB_OUTPUT
+          else
+            echo run_tests=false >> $GITHUB_OUTPUT
+          fi
+
+      - name: Trigger buildkite build
+        if: steps.check_commits.outputs.run_tests == 'true'
+        uses: buildkite/trigger-pipeline-action@v1.2.0
+        env:
+          PIPELINE: explosion-ai/spacy-slow-tests
+          BRANCH: ${{ matrix.branch }}
+          MESSAGE: ":github: Daily slow tests - triggered from a GitHub Action"
+          BUILDKITE_API_ACCESS_TOKEN: ${{ secrets.BUILDKITE_SECRET }}

.github/workflows/spacy_universe_alert.yml

@@ -0,0 +1,33 @@
+name: spaCy universe project alert
+
+on:
+  pull_request_target:
+    paths:
+      - "website/meta/universe.json"
+
+jobs:
+  build:
+    if: github.repository_owner == 'explosion'
+    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@v3
+      - uses: actions/setup-python@v4
+        with:
+          python-version: '3.10'
+      - 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"

.github/workflows/tests.yml

@@ -0,0 +1,179 @@
+name: tests
+
+on:
+  push:
+    branches-ignore:
+      - "spacy.io"
+      - "nightly.spacy.io"
+      - "v2.spacy.io"
+    paths-ignore:
+      - "*.md"
+      - "*.mdx"
+      - "website/**"
+      - ".github/workflows/**"
+  pull_request:
+    types: [opened, synchronize, reopened, edited]
+    paths-ignore:
+      - "*.md"
+      - "*.mdx"
+      - "website/**"
+
+jobs:
+  validate:
+    name: Validate
+    if: github.repository_owner == 'explosion'
+    runs-on: ubuntu-latest
+    steps:
+      - name: Check out repo
+        uses: actions/checkout@v3
+
+      - name: Configure Python version
+        uses: actions/setup-python@v4
+        with:
+          python-version: "3.8"
+          architecture: x64
+
+      - name: black
+        run: |
+          python -m pip install black -c requirements.txt
+          python -m black spacy --check
+      - name: isort
+        run: |
+          python -m pip install isort -c requirements.txt
+          python -m isort spacy --check
+      - name: flake8
+        run: |
+          python -m pip install flake8==5.0.4
+          python -m flake8 spacy --count --select=E901,E999,F821,F822,F823,W605 --show-source --statistics
+      - name: cython-lint
+        run: |
+          python -m pip install cython-lint -c requirements.txt
+          # E501: line too log, W291: trailing whitespace, E266: too many leading '#' for block comment
+          cython-lint spacy --ignore E501,W291,E266
+
+  tests:
+    name: Test
+    needs: Validate
+    strategy:
+      fail-fast: true
+      matrix:
+        os: [ubuntu-latest, windows-latest, macos-latest]
+        python_version: ["3.11"]
+        include:
+          - os: macos-latest
+            python_version: "3.8"
+          - os: ubuntu-20.04
+            python_version: "3.9"
+          - os: windows-latest
+            python_version: "3.10"
+
+    runs-on: ${{ matrix.os }}
+
+    steps:
+      - name: Check out repo
+        uses: actions/checkout@v3
+
+      - name: Configure Python version
+        uses: actions/setup-python@v4
+        with:
+          python-version: ${{ matrix.python_version }}
+          architecture: x64
+
+      - name: Install dependencies
+        run: |
+          python -m pip install -U build pip setuptools
+          python -m pip install -U -r requirements.txt
+
+      - name: Build sdist
+        run: |
+          python -m build --sdist
+
+      - name: Run mypy
+        run: |
+          python -m mypy spacy
+
+      - name: Delete source directory and .egg-info
+        run: |
+          rm -rf spacy *.egg-info
+        shell: bash
+
+      - name: Uninstall all packages
+        run: |
+          python -m pip freeze
+          python -m pip freeze --exclude pywin32 > installed.txt
+          python -m pip uninstall -y -r installed.txt
+
+      - name: Install from sdist
+        run: |
+          SDIST=$(python -c "import os;print(os.listdir('./dist')[-1])" 2>&1)
+          SPACY_NUM_BUILD_JOBS=2 python -m pip install dist/$SDIST
+        shell: bash
+
+      - name: Test import
+        run: python -W error -c "import spacy"
+
+      #      - name: "Test download CLI"
+      #        run: |
+      #          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')"
+      #        if: matrix.python_version == '3.9'
+      #
+      #      - name: "Test download_url in info CLI"
+      #        run: |
+      #          python -W error -m spacy info ca_core_news_sm | grep -q download_url
+      #        if: matrix.python_version == '3.9'
+      #
+      #      - name: "Test no warnings on load (#11713)"
+      #        run: |
+      #          python -W error -c "import ca_core_news_sm; nlp = ca_core_news_sm.load(); doc=nlp('test')"
+      #        if: matrix.python_version == '3.9'
+
+      - name: "Test convert CLI"
+        run: |
+          python -m spacy convert extra/example_data/ner_example_data/ner-token-per-line-conll2003.json .
+        if: matrix.python_version == '3.9'
+
+      - name: "Test debug config CLI"
+        run: |
+          python -m spacy init config -p ner -l ca ner.cfg
+          python -m spacy debug config ner.cfg --paths.train ner-token-per-line-conll2003.spacy --paths.dev ner-token-per-line-conll2003.spacy
+        if: matrix.python_version == '3.9'
+
+      - name: "Test debug data CLI"
+        run: |
+          # will have errors due to sparse data, check for summary in output
+          python -m spacy debug data ner.cfg --paths.train ner-token-per-line-conll2003.spacy --paths.dev ner-token-per-line-conll2003.spacy | grep -q Summary
+        if: matrix.python_version == '3.9'
+
+      - name: "Test train CLI"
+        run: |
+          python -m spacy train ner.cfg --paths.train ner-token-per-line-conll2003.spacy --paths.dev ner-token-per-line-conll2003.spacy --training.max_steps 10 --gpu-id -1
+        if: matrix.python_version == '3.9'
+
+      #      - name: "Test assemble CLI"
+      #        run: |
+      #          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
+      #        if: matrix.python_version == '3.9'
+      #
+      #      - name: "Test assemble CLI vectors warning"
+      #        run: |
+      #          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
+      #        if: matrix.python_version == '3.9'
+
+      - name: "Install test requirements"
+        run: |
+          python -m pip install -U -r requirements.txt
+
+      - name: "Run CPU tests"
+        run: |
+          python -m pytest --pyargs spacy -W error
+        if: "!(startsWith(matrix.os, 'macos') && matrix.python_version == '3.11')"
+
+      - name: "Run CPU tests with thinc-apple-ops"
+        run: |
+          python -m pip install 'spacy[apple]'
+          python -m pytest --pyargs spacy
+        if: startsWith(matrix.os, 'macos') && matrix.python_version == '3.11'

.github/workflows/universe_validation.yml

@@ -0,0 +1,33 @@
+name: universe validation
+
+on:
+  push:
+    branches-ignore:
+      - "spacy.io"
+      - "nightly.spacy.io"
+      - "v2.spacy.io"
+    paths:
+      - "website/meta/universe.json"
+  pull_request:
+    types: [opened, synchronize, reopened, edited]
+    paths:
+      - "website/meta/universe.json"
+
+jobs:
+  validate:
+    name: Validate
+    if: github.repository_owner == 'explosion'
+    runs-on: ubuntu-latest
+    steps:
+      - name: Check out repo
+        uses: actions/checkout@v3
+
+      - name: Configure Python version
+        uses: actions/setup-python@v4
+        with:
+          python-version: "3.8"
+          architecture: x64
+
+      - name: Validate website/meta/universe.json
+        run: |
+          python .github/validate_universe_json.py website/meta/universe.json

.gitignore

@@ -9,22 +9,12 @@ keys/
 spacy/tests/package/setup.cfg
 spacy/tests/package/pyproject.toml
 spacy/tests/package/requirements.txt
-spacy/tests/universe/universe.json
-
-# Website
-website/.cache/
-website/public/
-website/node_modules
-website/.npm
-website/logs
-*.log
-npm-debug.log*
-quickstart-training-generator.js
 
 # Cython / C extensions
 cythonize.json
 spacy/*.html
 *.cpp
+*.c
 *.so
 
 # Vim / VSCode / editors

.pre-commit-config.yaml

@@ -1,11 +1,12 @@
 repos:
 -   repo: https://github.com/ambv/black
-    rev: 21.6b0
+    rev: 22.3.0
     hooks:
     - id: black
-      language_version: python3.7
--   repo: https://gitlab.com/pycqa/flake8
-    rev: 3.9.2
+      language_version: python3.8
+      additional_dependencies: ['click==8.0.4']
+-   repo: https://github.com/pycqa/flake8
+    rev: 5.0.4
     hooks:
     - id: flake8
       args:

CONTRIBUTING.md

@@ -144,7 +144,7 @@ Changes to `.py` files will be effective immediately.
 
 When fixing a bug, first create an
 [issue](https://github.com/explosion/spaCy/issues) if one does not already
-exist.  The description text can be very short – we don't want to make this too
+exist. The description text can be very short – we don't want to make this too
 bureaucratic.
 
 Next, add a test to the relevant file in the
@@ -173,6 +173,11 @@ formatting and [`flake8`](http://flake8.pycqa.org/en/latest/) for linting its
 Python modules. If you've built spaCy from source, you'll already have both
 tools installed.
 
+As a general rule of thumb, we use f-strings for any formatting of strings.
+One exception are calls to Python's `logging` functionality.
+To avoid unnecessary string conversions in these cases, we use string formatting
+templates with `%s` and `%d` etc.
+
 **⚠️ Note that formatting and linting is currently only possible for Python
 modules in `.py` files, not Cython modules in `.pyx` and `.pxd` files.**
 
@@ -233,7 +238,7 @@ also want to keep an eye on unused declared variables or repeated
 (i.e. overwritten) dictionary keys. If your code was formatted with `black`
 (see above), you shouldn't see any formatting-related warnings.
 
-The [`.flake8`](.flake8) config defines the configuration we use for this
+The `flake8` section in [`setup.cfg`](setup.cfg) defines the configuration we use for this
 codebase. For example, we're not super strict about the line length, and we're
 excluding very large files like lemmatization and tokenizer exception tables.
 
@@ -271,7 +276,8 @@ 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 3.8+**. 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
 

LICENSE

@@ -1,6 +1,6 @@
 The MIT License (MIT)
 
-Copyright (C) 2016-2021 ExplosionAI GmbH, 2016 spaCy GmbH, 2015 Matthew Honnibal
+Copyright (C) 2016-2022 ExplosionAI GmbH, 2016 spaCy GmbH, 2015 Matthew Honnibal
 
 Permission is hereby granted, free of charge, to any person obtaining a copy
 of this software and associated documentation files (the "Software"), to deal

MANIFEST.in

@@ -1,11 +1,8 @@
-recursive-include include *.h
-recursive-include spacy *.pyi *.pyx *.pxd *.txt *.cfg *.jinja *.toml
+recursive-include spacy *.pyi *.pyx *.pxd *.txt *.cfg *.jinja *.toml *.hh
 include LICENSE
 include README.md
 include pyproject.toml
 include spacy/py.typed
-recursive-exclude spacy/lang *.json
-recursive-include spacy/lang *.json.gz
-recursive-include spacy/cli *.json *.yml
+recursive-include spacy/cli *.yml
 recursive-include licenses *
 recursive-exclude spacy *.cpp

Makefile

@@ -1,11 +1,11 @@
 SHELL := /bin/bash
 
 ifndef SPACY_EXTRAS
-override SPACY_EXTRAS = spacy-lookups-data==1.0.2 jieba spacy-pkuseg==0.0.28 sudachipy sudachidict_core pymorphy2
+override SPACY_EXTRAS = spacy-lookups-data==1.0.3
 endif
 
 ifndef PYVER
-override PYVER = 3.6
+override PYVER = 3.8
 endif
 
 VENV := ./env$(PYVER)

README.md

@@ -8,15 +8,18 @@ be used in real products.
 
 spaCy comes with
 [pretrained pipelines](https://spacy.io/models) and
-currently supports tokenization and training for **60+ languages**. It features
+currently supports tokenization and training for **70+ languages**. It features
 state-of-the-art speed and **neural network models** for tagging,
 parsing, **named entity recognition**, **text classification** and more,
 multi-task learning with pretrained **transformers** like BERT, as well as a
 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.
+open-source software, released under the [MIT license](https://github.com/explosion/spaCy/blob/master/LICENSE).
 
-💫 **Version 3.2 out now!**
+💥 **We'd love to hear more about your experience with spaCy!**
+[Fill out our survey here.](https://form.typeform.com/to/aMel9q9f)
+
+💫 **Version 3.5 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)
@@ -32,19 +35,22 @@ open-source software, released under the MIT license.
 
 ## 📖 Documentation
 
-| Documentation              |                                                                |
-| -------------------------- | -------------------------------------------------------------- |
-| ⭐️ **[spaCy 101]**        | New to spaCy? Here's everything you need to know!              |
-| 📚 **[Usage Guides]**      | How to use spaCy and its features.                             |
-| 🚀 **[New in v3.0]**       | New features, backwards incompatibilities and migration guide. |
-| 🪐 **[Project Templates]** | End-to-end workflows you can clone, modify and run.            |
-| 🎛 **[API Reference]**      | The detailed reference for spaCy's API.                        |
-| 📦 **[Models]**            | Download trained pipelines for spaCy.                          |
-| 🌌 **[Universe]**          | Plugins, extensions, demos and books from the spaCy ecosystem. |
-| 👩‍🏫 **[Online Course]**     | Learn spaCy in this free and interactive online course.        |
-| 📺 **[Videos]**            | Our YouTube channel with video tutorials, talks and more.      |
-| 🛠 **[Changelog]**          | Changes and version history.                                   |
-| 💝 **[Contribute]**        | How to contribute to the spaCy project and code base.          |
+| Documentation                 |                                                                        |
+| ----------------------------- | ---------------------------------------------------------------------- |
+| ⭐️ **[spaCy 101]**           | New to spaCy? Here's everything you need to know!                      |
+| 📚 **[Usage Guides]**         | How to use spaCy and its features.                                     |
+| 🚀 **[New in v3.0]**          | New features, backwards incompatibilities and migration guide.         |
+| 🪐 **[Project Templates]**    | End-to-end workflows you can clone, modify and run.                    |
+| 🎛 **[API Reference]**         | The detailed reference for spaCy's API.                                |
+| 📦 **[Models]**               | Download trained pipelines for spaCy.                                  |
+| 🌌 **[Universe]**             | Plugins, extensions, demos and books from the spaCy ecosystem.         |
+| ⚙️ **[spaCy VS Code Extension]** | Additional tooling and features for working with spaCy's config files. |
+| 👩‍🏫 **[Online Course]** | Learn spaCy in this free and interactive online course. |
+| 📺 **[Videos]** | Our YouTube channel with video tutorials, talks and more. |
+| 🛠 **[Changelog]** | Changes and version history. |
+| 💝 **[Contribute]** | How to contribute to the spaCy project and code base. |
+| <a href="https://explosion.ai/spacy-tailored-pipelines"><img src="https://user-images.githubusercontent.com/13643239/152853098-1c761611-ccb0-4ec6-9066-b234552831fe.png" width="125" alt="spaCy Tailored Pipelines"/></a> | Get a custom spaCy pipeline, tailor-made for your NLP problem by spaCy's core developers. Streamlined, production-ready, predictable and maintainable. Start by completing our 5-minute questionnaire to tell us what you need and we'll be in touch! **[Learn more &rarr;](https://explosion.ai/spacy-tailored-pipelines)** |
+| <a href="https://explosion.ai/spacy-tailored-analysis"><img src="https://user-images.githubusercontent.com/1019791/206151300-b00cd189-e503-4797-aa1e-1bb6344062c5.png" width="125" alt="spaCy Tailored Pipelines"/></a> | Bespoke advice for problem solving, strategy and analysis for applied NLP projects. Services include data strategy, code reviews, pipeline design and annotation coaching. Curious? Fill in our 5-minute questionnaire to tell us what you need and we'll be in touch! **[Learn more &rarr;](https://explosion.ai/spacy-tailored-analysis)** |
 
 [spacy 101]: https://spacy.io/usage/spacy-101
 [new in v3.0]: https://spacy.io/usage/v3
@@ -52,6 +58,7 @@ open-source software, released under the MIT license.
 [api reference]: https://spacy.io/api/
 [models]: https://spacy.io/models
 [universe]: https://spacy.io/universe
+[spaCy VS Code Extension]: https://github.com/explosion/spacy-vscode
 [videos]: https://www.youtube.com/c/ExplosionAI
 [online course]: https://course.spacy.io
 [project templates]: https://github.com/explosion/projects
@@ -60,9 +67,7 @@ open-source software, released under the MIT license.
 
 ## 💬 Where to ask questions
 
-The spaCy project is maintained by **[@honnibal](https://github.com/honnibal)**,
-**[@ines](https://github.com/ines)**, **[@svlandeg](https://github.com/svlandeg)**,
-**[@adrianeboyd](https://github.com/adrianeboyd)** and **[@polm](https://github.com/polm)**.
+The spaCy project is maintained by the [spaCy team](https://explosion.ai/about).
 Please understand that we won't be able to provide individual support via email.
 We also believe that help is much more valuable if it's shared publicly, so that
 more people can benefit from it.
@@ -80,7 +85,7 @@ more people can benefit from it.
 
 ## Features
 
-- Support for **60+ languages**
+- Support for **70+ languages**
 - **Trained pipelines** for different languages and tasks
 - Multi-task learning with pretrained **transformers** like BERT
 - Support for pretrained **word vectors** and embeddings
@@ -104,7 +109,7 @@ For detailed installation instructions, see the
 
 - **Operating system**: macOS / OS X · Linux · Windows (Cygwin, MinGW, Visual
   Studio)
-- **Python version**: Python 3.6+ (only 64 bit)
+- **Python version**: Python 3.8+ (only 64 bit)
 - **Package managers**: [pip] · [conda] (via `conda-forge`)
 
 [pip]: https://pypi.org/project/spacy/

azure-pipelines.yml

@@ -1,109 +0,0 @@
-trigger:
-  batch: true
-  branches:
-    include:
-      - "*"
-    exclude:
-      - "spacy.io"
-      - "nightly.spacy.io"
-      - "v2.spacy.io"
-  paths:
-    exclude:
-      - "website/*"
-      - "*.md"
-pr:
-   paths:
-    exclude:
-      - "*.md"
-      - "website/docs/*"
-      - "website/src/*"
-
-jobs:
-  # Perform basic checks for most important errors (syntax etc.) Uses the config
-  # defined in .flake8 and overwrites the selected codes.
-  - job: "Validate"
-    pool:
-      vmImage: "ubuntu-latest"
-    steps:
-      - task: UsePythonVersion@0
-        inputs:
-          versionSpec: "3.7"
-      - script: |
-          pip install flake8==3.9.2
-          python -m flake8 spacy --count --select=E901,E999,F821,F822,F823 --show-source --statistics
-        displayName: "flake8"
-
-  - job: "Test"
-    dependsOn: "Validate"
-    strategy:
-      matrix:
-        # We're only running one platform per Python version to speed up builds
-        Python36Linux:
-          imageName: "ubuntu-latest"
-          python.version: "3.6"
-        #        Python36Windows:
-        #          imageName: "windows-latest"
-        #          python.version: "3.6"
-        #        Python36Mac:
-        #          imageName: "macos-latest"
-        #          python.version: "3.6"
-        #        Python37Linux:
-        #          imageName: "ubuntu-latest"
-        #          python.version: "3.7"
-        Python37Windows:
-          imageName: "windows-latest"
-          python.version: "3.7"
-        #        Python37Mac:
-        #          imageName: "macos-latest"
-        #          python.version: "3.7"
-        #        Python38Linux:
-        #          imageName: "ubuntu-latest"
-        #          python.version: "3.8"
-        #        Python38Windows:
-        #          imageName: "windows-latest"
-        #          python.version: "3.8"
-        Python38Mac:
-          imageName: "macos-latest"
-          python.version: "3.8"
-        Python39Linux:
-          imageName: "ubuntu-latest"
-          python.version: "3.9"
-        #        Python39Windows:
-        #          imageName: "windows-latest"
-        #          python.version: "3.9"
-        #        Python39Mac:
-        #          imageName: "macos-latest"
-        #          python.version: "3.9"
-        Python310Linux:
-          imageName: "ubuntu-latest"
-          python.version: "3.10"
-        Python310Windows:
-          imageName: "windows-latest"
-          python.version: "3.10"
-        Python310Mac:
-          imageName: "macos-latest"
-          python.version: "3.10"
-      maxParallel: 4
-    pool:
-      vmImage: $(imageName)
-    steps:
-      - template: .github/azure-steps.yml
-        parameters:
-          python_version: '$(python.version)'
-          architecture: 'x64'
-
-#  - job: "TestGPU"
-#    dependsOn: "Validate"
-#    strategy:
-#      matrix:
-#        Python38LinuxX64_GPU:
-#          python.version: '3.8'
-#    pool:
-#      name: "LinuxX64_GPU"
-#    steps:
-#      - template: .github/azure-steps.yml
-#        parameters:
-#          python_version: '$(python.version)'
-#          architecture: 'x64'
-#          gpu: true
-#          num_build_jobs: 24

build-constraints.txt

@@ -1,6 +1,7 @@
 # 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==1.17.3; 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'
+numpy==1.23.2; python_version=='3.11'
+numpy; python_version>='3.12'

extra/DEVELOPER_DOCS/Code Conventions.md

@@ -137,7 +137,7 @@ If any of the TODOs you've added are important and should be fixed soon, you sho
 
 ## Type hints
 
-We use Python type hints across the `.py` files wherever possible. This makes it easy to understand what a function expects and returns, and modern editors will be able to show this information to you when you call an annotated function. Type hints are not currently used in the `.pyx` (Cython) code, except for definitions of registered functions and component factories, where they're used for config validation.
+We use Python type hints across the `.py` files wherever possible. This makes it easy to understand what a function expects and returns, and modern editors will be able to show this information to you when you call an annotated function. Type hints are not currently used in the `.pyx` (Cython) code, except for definitions of registered functions and component factories, where they're used for config validation. Ideally when developing, run `mypy spacy` on the code base to inspect any issues.
 
 If possible, you should always use the more descriptive type hints like `List[str]` or even `List[Any]` instead of only `list`. We also annotate arguments and return types of `Callable` – although, you can simplify this if the type otherwise gets too verbose (e.g. functions that return factories to create callbacks). Remember that `Callable` takes two values: a **list** of the argument type(s) in order, and the return values.
 
@@ -155,6 +155,13 @@ def create_callback(some_arg: bool) -> Callable[[str, int], List[str]]:
     return callback
 ```
 
+For typing variables, we prefer the explicit format.
+
+```diff
+- var = value    # type: Type
++ var: Type = value
+```
+
 For model architectures, Thinc also provides a collection of [custom types](https://thinc.ai/docs/api-types), including more specific types for arrays and model inputs/outputs. Even outside of static type checking, using these types will make the code a lot easier to read and follow, since it's always clear what array types are expected (and what might go wrong if the output is different from the expected type).
 
 ```python
@@ -184,6 +191,8 @@ def load_model(name: str) -> "Language":
     ...
 ```
 
+Note that we typically put the `from typing` import statements on the first line(s) of the Python module.
+
 ## Structuring logic
 
 ### Positional and keyword arguments
@@ -268,6 +277,27 @@ If you have to use `try`/`except`, make sure to only include what's **absolutely
 +     return [v.strip() for v in value.split(",")]
 ```
 
+### Numeric comparisons
+
+For numeric comparisons, as a general rule we always use `<` and `>=` and avoid the usage of `<=` and `>`. This is to ensure we consistently
+apply inclusive lower bounds and exclusive upper bounds, helping to prevent off-by-one errors.
+
+One exception to this rule is the ternary case. With a chain like
+
+```python
+if value >= 0 and value < max:
+    ...
+```
+
+it's fine to rewrite this to the shorter form
+
+```python
+if 0 <= value < max:
+    ...
+```
+
+even though this requires the usage of the `<=` operator.
+
 ### Iteration and comprehensions
 
 We generally avoid using built-in functions like `filter` or `map` in favor of list or generator comprehensions.
@@ -444,10 +474,14 @@ spaCy uses the [`pytest`](http://doc.pytest.org/) framework for testing. Tests f
 
 When adding tests, make sure to use descriptive names and only test for one behavior at a time. Tests should be grouped into modules dedicated to the same type of functionality and some test modules are organized as directories of test files related to the same larger area of the library, e.g. `matcher` or `tokenizer`.
 
-Regression tests are tests that refer to bugs reported in specific issues. They should live in the relevant module of the test suite, named according to the issue number (e.g., `test_issue1234.py`), and [marked](https://docs.pytest.org/en/6.2.x/example/markers.html#working-with-custom-markers) appropriately (e.g. `@pytest.mark.issue(1234)`). This system allows us to relate tests for specific bugs back to the original reported issue, which is especially useful if we introduce a regression and a previously passing regression tests suddenly fails again. When fixing a bug, it's often useful to create a regression test for it first. 
+Regression tests are tests that refer to bugs reported in specific issues. They should live in the relevant module of the test suite, named according to the issue number (e.g., `test_issue1234.py`), and [marked](https://docs.pytest.org/en/6.2.x/example/markers.html#working-with-custom-markers) appropriately (e.g. `@pytest.mark.issue(1234)`). This system allows us to relate tests for specific bugs back to the original reported issue, which is especially useful if we introduce a regression and a previously passing regression tests suddenly fails again. When fixing a bug, it's often useful to create a regression test for it first.
 
 The test suite also provides [fixtures](https://github.com/explosion/spaCy/blob/master/spacy/tests/conftest.py) for different language tokenizers that can be used as function arguments of the same name and will be passed in automatically. Those should only be used for tests related to those specific languages. We also have [test utility functions](https://github.com/explosion/spaCy/blob/master/spacy/tests/util.py) for common operations, like creating a temporary file.
 
+### Testing Cython Code
+
+If you're developing Cython code (`.pyx` files), those extensions will need to be built before the test runner can test that code - otherwise it's going to run the tests with stale code from the last time the extension was built. You can build the extensions locally with `python setup.py build_ext -i`.
+
 ### Constructing objects and state
 
 Test functions usually follow the same simple structure: they set up some state, perform the operation you want to test and `assert` conditions that you expect to be true, usually before and after the operation.

extra/DEVELOPER_DOCS/ExplosionBot.md

@@ -0,0 +1,56 @@
+# Explosion-bot
+
+Explosion-bot is a robot that can be invoked to help with running particular test commands.
+
+## Permissions
+
+Only maintainers have permissions to summon explosion-bot. Each of the open source repos that use explosion-bot has its own team(s) of maintainers, and only github users who are members of those teams can successfully run bot commands.
+
+## Running robot commands
+
+To summon the robot, write a github comment on the issue/PR you wish to test. The comment must be in the following format:
+
+```
+@explosion-bot please test_gpu
+```
+
+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.
+
+### 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).
+
+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.

extra/DEVELOPER_DOCS/Satellite Packages.md

@@ -0,0 +1,82 @@
+# spaCy Satellite Packages
+
+This is a list of all the active repos relevant to spaCy besides the main one, with short descriptions, history, and current status. Archived repos will not be covered.
+
+## Always Included in spaCy
+
+These packages are always pulled in when you install spaCy. Most of them are direct dependencies, but some are transitive dependencies through other packages.
+
+- [spacy-legacy](https://github.com/explosion/spacy-legacy): When an architecture in spaCy changes enough to get a new version, the old version is frozen and moved to spacy-legacy. This allows us to keep the core library slim while also preserving backwards compatability.
+- [thinc](https://github.com/explosion/thinc): Thinc is the machine learning library that powers trainable components in spaCy. It wraps backends like Numpy, PyTorch, and Tensorflow to provide a functional interface for specifying architectures.
+- [catalogue](https://github.com/explosion/catalogue): Small library for adding function registries, like those used for model architectures in spaCy.
+- [confection](https://github.com/explosion/confection): This library contains the functionality for config parsing that was formerly contained directly in Thinc.
+- [spacy-loggers](https://github.com/explosion/spacy-loggers): Contains loggers beyond the default logger available in spaCy's core code base. This includes loggers integrated with third-party services, which may differ in release cadence from spaCy itself.
+- [wasabi](https://github.com/explosion/wasabi): A command line formatting library, used for terminal output in spaCy.
+- [srsly](https://github.com/explosion/srsly): A wrapper that vendors several serialization libraries for spaCy. Includes parsers for JSON, JSONL, MessagePack, (extended) Pickle, and YAML.
+- [preshed](https://github.com/explosion/preshed): A Cython library for low-level data structures like hash maps, used for memory efficient data storage.
+- [cython-blis](https://github.com/explosion/cython-blis): Fast matrix multiplication using BLIS without depending on system libraries. Required by Thinc, rather than spaCy directly.
+- [murmurhash](https://github.com/explosion/murmurhash): A wrapper library for a C++ murmurhash implementation, used for string IDs in spaCy and preshed.
+- [cymem](https://github.com/explosion/cymem): A small library for RAII-style memory management in Cython. 
+
+## Optional Extensions for spaCy
+
+These are repos that can be used by spaCy but aren't part of a default installation. Many of these are wrappers to integrate various kinds of third-party libraries.
+
+- [spacy-transformers](https://github.com/explosion/spacy-transformers): A wrapper for the [HuggingFace Transformers](https://huggingface.co/docs/transformers/index) library, this handles the extensive conversion necessary to coordinate spaCy's powerful `Doc` representation, training pipeline, and the Transformer embeddings. When released, this was known as `spacy-pytorch-transformers`, but it changed to the current name when HuggingFace update the name of their library as well.
+- [spacy-huggingface-hub](https://github.com/explosion/spacy-huggingface-hub): This package has a CLI script for uploading a packaged spaCy pipeline (created with `spacy package`) to the [Hugging Face Hub](https://huggingface.co/models).
+- [spacy-alignments](https://github.com/explosion/spacy-alignments): A wrapper for the tokenizations library (mentioned below) with a modified build system to simplify cross-platform wheel creation. Used in spacy-transformers for aligning spaCy and HuggingFace tokenizations.
+- [spacy-experimental](https://github.com/explosion/spacy-experimental): Experimental components that are not quite ready for inclusion in the main spaCy library. Usually there are unresolved questions around their APIs, so the experimental library allows us to expose them to the community for feedback before fully integrating them. 
+- [spacy-lookups-data](https://github.com/explosion/spacy-lookups-data): A repository of linguistic data, such as lemmas, that takes up a lot of disk space. Originally created to reduce the size of the spaCy core library. This is mainly useful if you want the data included but aren't using a pretrained pipeline; for the affected languages, the relevant data is included in pretrained pipelines directly.
+- [coreferee](https://github.com/explosion/coreferee): Coreference resolution for English, French, German and Polish, optimised for limited training data and easily extensible for further languages. Used as a spaCy pipeline component.
+- [spacy-stanza](https://github.com/explosion/spacy-stanza): This is a wrapper that allows the use of Stanford's Stanza library in spaCy. 
+- [spacy-streamlit](https://github.com/explosion/spacy-streamlit): A wrapper for the Streamlit dashboard building library to help with integrating [displaCy](https://spacy.io/api/top-level/#displacy).
+- [spacymoji](https://github.com/explosion/spacymoji): A library to add extra support for emoji to spaCy, such as including character names.
+- [thinc-apple-ops](https://github.com/explosion/thinc-apple-ops): A special backend for OSX that uses Apple's native libraries for improved performance.
+- [os-signpost](https://github.com/explosion/os-signpost): A Python package that allows you to use the `OSSignposter` API in OSX for performance analysis.
+- [spacy-ray](https://github.com/explosion/spacy-ray): A wrapper to integrate spaCy with Ray, a distributed training framework. Currently a work in progress.
+
+## Prodigy
+
+[Prodigy](https://prodi.gy) is Explosion's easy to use and highly customizable tool for annotating data. Prodigy itself requires a license, but the repos below contain documentation, examples, and editor or notebook integrations.
+
+- [prodigy-recipes](https://github.com/explosion/prodigy-recipes): Sample recipes for Prodigy, along with notebooks and other examples of usage.
+- [vscode-prodigy](https://github.com/explosion/vscode-prodigy): A VS Code extension that lets you run Prodigy inside VS Code.
+- [jupyterlab-prodigy](https://github.com/explosion/jupyterlab-prodigy): An extension for JupyterLab that lets you run Prodigy inside JupyterLab.
+
+## Independent Tools or Projects
+
+These are tools that may be related to or use spaCy, but are functional independent projects in their own right as well.
+
+- [floret](https://github.com/explosion/floret): A modification of fastText to use Bloom Embeddings. Can be used to add vectors with subword features to spaCy, and also works independently in the same manner as fastText.
+- [sense2vec](https://github.com/explosion/sense2vec): A library to make embeddings of noun phrases or words coupled with their part of speech. This library uses spaCy.
+- [spacy-vectors-builder](https://github.com/explosion/spacy-vectors-builder): This is a spaCy project that builds vectors using floret and a lot of input text. It handles downloading the input data as well as the actual building of vectors.
+- [holmes-extractor](https://github.com/explosion/holmes-extractor): Information extraction from English and German texts based on predicate logic. Uses spaCy.
+- [healthsea](https://github.com/explosion/healthsea): Healthsea is a project to extract information from comments about health supplements. Structurally, it's a self-contained, large spaCy project.
+- [spacy-pkuseg](https://github.com/explosion/spacy-pkuseg): A fork of the pkuseg Chinese tokenizer. Used for Chinese support in spaCy, but also works independently.
+- [ml-datasets](https://github.com/explosion/ml-datasets): This repo includes loaders for several standard machine learning datasets, like MNIST or WikiNER, and has historically been used in spaCy example code and documentation.
+
+## Documentation and Informational Repos
+
+These repos are used to support the spaCy docs or otherwise present information about spaCy or other Explosion projects.
+
+- [projects](https://github.com/explosion/projects): The projects repo is used to show detailed examples of spaCy usage. Individual projects can be checked out using the spaCy command line tool, rather than checking out the projects repo directly.
+- [spacy-course](https://github.com/explosion/spacy-course): Home to the interactive spaCy course for learning about how to use the library and some basic NLP principles.
+- [spacy-io-binder](https://github.com/explosion/spacy-io-binder): Home to the notebooks used for interactive examples in the documentation.
+
+## Organizational / Meta
+
+These repos are used for organizing data around spaCy, but are not something an end user would need to install as part of using the library.
+
+- [spacy-models](https://github.com/explosion/spacy-models): This repo contains metadata (but not training data) for all the spaCy models. This includes information about where their training data came from, version compatability, and performance information. It also includes tests for the model packages, and the built models are hosted as releases of this repo.
+- [wheelwright](https://github.com/explosion/wheelwright): A tool for automating our PyPI builds and releases.
+- [ec2buildwheel](https://github.com/explosion/ec2buildwheel): A small project that allows you to build Python packages in the manner of cibuildwheel, but on any EC2 image. Used by wheelwright.
+
+## Other
+
+Repos that don't fit in any of the above categories.
+
+- [blis](https://github.com/explosion/blis): A fork of the official BLIS library. The main branch is not updated, but work continues in various branches. This is used for cython-blis.
+- [tokenizations](https://github.com/explosion/tokenizations): A library originally by Yohei Tamura to align strings with tolerance to some variations in features like case and diacritics, used for aligning tokens and wordpieces. Adopted and maintained by Explosion, but usually spacy-alignments is used instead.
+- [conll-2012](https://github.com/explosion/conll-2012): A repo to hold some slightly cleaned up versions of the official scripts for the CoNLL 2012 shared task involving coreference resolution. Used in the coref project.
+- [fastapi-explosion-extras](https://github.com/explosion/fastapi-explosion-extras): Some small tweaks to FastAPI used at Explosion.
+

licenses/3rd_party_licenses.txt

@@ -127,3 +127,34 @@ distributed under the License is distributed on an "AS IS" BASIS,
 WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 See the License for the specific language governing permissions and
 limitations under the License.
+
+
+polyleven
+---------
+
+* Files: spacy/matcher/polyleven.c
+
+MIT License
+
+Copyright (c) 2021 Fujimoto Seiji <fujimoto@ceptord.net>
+Copyright (c) 2021 Max Bachmann <kontakt@maxbachmann.de>
+Copyright (c) 2022 Nick Mazuk
+Copyright (c) 2022 Michael Weiss <code@mweiss.ch>
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

pyproject.toml

@@ -5,9 +5,10 @@ requires = [
     "cymem>=2.0.2,<2.1.0",
     "preshed>=3.0.2,<3.1.0",
     "murmurhash>=0.28.0,<1.1.0",
-    "thinc>=8.0.12,<8.1.0",
-    "blis>=0.4.0,<0.8.0",
-    "pathy",
+    "thinc>=9.0.0.dev2,<9.1.0",
     "numpy>=1.15.0",
 ]
 build-backend = "setuptools.build_meta"
+
+[tool.isort]
+profile = "black"

requirements.txt

@@ -1,37 +1,40 @@
 # Our libraries
-spacy-legacy>=3.0.8,<3.1.0
+spacy-legacy>=4.0.0.dev0,<4.1.0
 spacy-loggers>=1.0.0,<2.0.0
 cymem>=2.0.2,<2.1.0
 preshed>=3.0.2,<3.1.0
-thinc>=8.0.12,<8.1.0
-blis>=0.4.0,<0.8.0
+thinc>=9.0.0.dev2,<9.1.0
 ml_datasets>=0.2.0,<0.3.0
 murmurhash>=0.28.0,<1.1.0
-wasabi>=0.8.1,<1.1.0
-srsly>=2.4.1,<3.0.0
+wasabi>=0.9.1,<1.2.0
+srsly>=2.4.3,<3.0.0
 catalogue>=2.0.6,<2.1.0
-typer>=0.3.0,<0.5.0
-pathy>=0.3.5
+typer>=0.3.0,<0.10.0
+pathy>=0.10.0
+smart-open>=5.2.1,<7.0.0
 # Third party dependencies
 numpy>=1.15.0
 requests>=2.13.0,<3.0.0
 tqdm>=4.38.0,<5.0.0
-pydantic>=1.7.4,!=1.8,!=1.8.1,<1.9.0
+pydantic>=1.7.4,!=1.8,!=1.8.1,<1.11.0
 jinja2
 langcodes>=3.2.0,<4.0.0
 # Official Python utilities
 setuptools
 packaging>=20.0
-typing_extensions>=3.7.4.1,<4.0.0.0; python_version < "3.8"
 # Development dependencies
 pre-commit>=2.13.0
 cython>=0.25,<3.0
-pytest>=5.2.0
+pytest>=5.2.0,!=7.1.0
 pytest-timeout>=1.3.0,<2.0.0
 mock>=2.0.0,<3.0.0
-flake8>=3.8.0,<3.10.0
+flake8>=3.8.0,<6.0.0
 hypothesis>=3.27.0,<7.0.0
-mypy>=0.910
-types-dataclasses>=0.1.3; python_version < "3.7"
+mypy>=0.990,<1.1.0; platform_machine != "aarch64"
 types-mock>=0.1.1
+types-setuptools>=57.0.0
 types-requests
+types-setuptools>=57.0.0
+black==22.3.0
+cython-lint>=0.15.0; python_version >= "3.7"
+isort>=5.0,<6.0

setup.cfg

@@ -17,11 +17,10 @@ classifiers =
     Operating System :: Microsoft :: Windows
     Programming Language :: Cython
     Programming Language :: Python :: 3
-    Programming Language :: Python :: 3.6
-    Programming Language :: Python :: 3.7
     Programming Language :: Python :: 3.8
     Programming Language :: Python :: 3.9
     Programming Language :: Python :: 3.10
+    Programming Language :: Python :: 3.11
     Topic :: Scientific/Engineering
 project_urls =
     Release notes = https://github.com/explosion/spaCy/releases
@@ -30,7 +29,7 @@ project_urls =
 [options]
 zip_safe = false
 include_package_data = true
-python_requires = >=3.6
+python_requires = >=3.8
 setup_requires =
     cython>=0.25,<3.0
     numpy>=1.15.0
@@ -38,31 +37,30 @@ setup_requires =
     cymem>=2.0.2,<2.1.0
     preshed>=3.0.2,<3.1.0
     murmurhash>=0.28.0,<1.1.0
-    thinc>=8.0.12,<8.1.0
+    thinc>=9.0.0.dev2,<9.1.0
 install_requires =
     # Our libraries
-    spacy-legacy>=3.0.8,<3.1.0
+    spacy-legacy>=4.0.0.dev0,<4.1.0
     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>=8.0.12,<8.1.0
-    blis>=0.4.0,<0.8.0
-    wasabi>=0.8.1,<1.1.0
-    srsly>=2.4.1,<3.0.0
+    thinc>=9.0.0.dev2,<9.1.0
+    wasabi>=0.9.1,<1.2.0
+    srsly>=2.4.3,<3.0.0
     catalogue>=2.0.6,<2.1.0
-    typer>=0.3.0,<0.5.0
-    pathy>=0.3.5
     # Third-party dependencies
+    typer>=0.3.0,<0.10.0
+    pathy>=0.10.0
+    smart-open>=5.2.1,<7.0.0
     tqdm>=4.38.0,<5.0.0
     numpy>=1.15.0
     requests>=2.13.0,<3.0.0
-    pydantic>=1.7.4,!=1.8,!=1.8.1,<1.9.0
+    pydantic>=1.7.4,!=1.8,!=1.8.1,<1.11.0
     jinja2
     # Official Python utilities
     setuptools
     packaging>=20.0
-    typing_extensions>=3.7.4,<4.0.0.0; python_version < "3.8"
     langcodes>=3.2.0,<4.0.0
 
 [options.entry_points]
@@ -73,43 +71,53 @@ console_scripts =
 lookups =
     spacy_lookups_data>=1.0.3,<1.1.0
 transformers =
-    spacy_transformers>=1.1.2,<1.2.0
+    spacy_transformers>=1.1.2,<1.3.0
 ray =
     spacy_ray>=0.1.0,<1.0.0
 cuda =
-    cupy>=5.0.0b4,<10.0.0
+    cupy>=5.0.0b4,<13.0.0
 cuda80 =
-    cupy-cuda80>=5.0.0b4,<10.0.0
+    cupy-cuda80>=5.0.0b4,<13.0.0
 cuda90 =
-    cupy-cuda90>=5.0.0b4,<10.0.0
+    cupy-cuda90>=5.0.0b4,<13.0.0
 cuda91 =
-    cupy-cuda91>=5.0.0b4,<10.0.0
+    cupy-cuda91>=5.0.0b4,<13.0.0
 cuda92 =
-    cupy-cuda92>=5.0.0b4,<10.0.0
+    cupy-cuda92>=5.0.0b4,<13.0.0
 cuda100 =
-    cupy-cuda100>=5.0.0b4,<10.0.0
+    cupy-cuda100>=5.0.0b4,<13.0.0
 cuda101 =
-    cupy-cuda101>=5.0.0b4,<10.0.0
+    cupy-cuda101>=5.0.0b4,<13.0.0
 cuda102 =
-    cupy-cuda102>=5.0.0b4,<10.0.0
+    cupy-cuda102>=5.0.0b4,<13.0.0
 cuda110 =
-    cupy-cuda110>=5.0.0b4,<10.0.0
+    cupy-cuda110>=5.0.0b4,<13.0.0
 cuda111 =
-    cupy-cuda111>=5.0.0b4,<10.0.0
+    cupy-cuda111>=5.0.0b4,<13.0.0
 cuda112 =
-    cupy-cuda112>=5.0.0b4,<10.0.0
+    cupy-cuda112>=5.0.0b4,<13.0.0
 cuda113 =
-    cupy-cuda113>=5.0.0b4,<10.0.0
+    cupy-cuda113>=5.0.0b4,<13.0.0
 cuda114 =
-    cupy-cuda114>=5.0.0b4,<10.0.0
+    cupy-cuda114>=5.0.0b4,<13.0.0
+cuda115 =
+    cupy-cuda115>=5.0.0b4,<13.0.0
+cuda116 =
+    cupy-cuda116>=5.0.0b4,<13.0.0
+cuda117 =
+    cupy-cuda117>=5.0.0b4,<13.0.0
+cuda11x =
+    cupy-cuda11x>=11.0.0,<13.0.0
+cuda-autodetect =
+    cupy-wheel>=11.0.0,<13.0.0
 apple =
-    thinc-apple-ops>=0.0.4,<1.0.0
+    thinc-apple-ops>=0.1.0.dev0,<1.0.0
 # Language tokenizers with external dependencies
 ja =
-    sudachipy>=0.4.9
-    sudachidict_core>=20200330
+    sudachipy>=0.5.2,!=0.6.1
+    sudachidict_core>=20211220
 ko =
-    natto-py==0.9.0
+    mecab-ko>=1.0.0
 th =
     pythainlp>=2.0
 

setup.py

@@ -23,19 +23,20 @@ Options.docstrings = True
 
 PACKAGES = find_packages()
 MOD_NAMES = [
+    "spacy.training.alignment_array",
     "spacy.training.example",
     "spacy.parts_of_speech",
     "spacy.strings",
     "spacy.lexeme",
     "spacy.vocab",
     "spacy.attrs",
-    "spacy.kb",
-    "spacy.ml.parser_model",
+    "spacy.kb.candidate",
+    "spacy.kb.kb",
+    "spacy.kb.kb_in_memory",
+    "spacy.ml.tb_framework",
     "spacy.morphology",
-    "spacy.pipeline.dep_parser",
+    "spacy.pipeline._edit_tree_internals.edit_trees",
     "spacy.pipeline.morphologizer",
-    "spacy.pipeline.multitask",
-    "spacy.pipeline.ner",
     "spacy.pipeline.pipe",
     "spacy.pipeline.trainable_pipe",
     "spacy.pipeline.sentencizer",
@@ -43,12 +44,15 @@ MOD_NAMES = [
     "spacy.pipeline.tagger",
     "spacy.pipeline.transition_parser",
     "spacy.pipeline._parser_internals.arc_eager",
+    "spacy.pipeline._parser_internals.batch",
     "spacy.pipeline._parser_internals.ner",
     "spacy.pipeline._parser_internals.nonproj",
+    "spacy.pipeline._parser_internals.search",
     "spacy.pipeline._parser_internals._state",
     "spacy.pipeline._parser_internals.stateclass",
     "spacy.pipeline._parser_internals.transition_system",
     "spacy.pipeline._parser_internals._beam_utils",
+    "spacy.pipeline._parser_internals._parser_utils",
     "spacy.tokenizer",
     "spacy.training.align",
     "spacy.training.gold_io",
@@ -58,12 +62,13 @@ MOD_NAMES = [
     "spacy.tokens.span_group",
     "spacy.tokens.graph",
     "spacy.tokens.morphanalysis",
-    "spacy.tokens._retokenize",
+    "spacy.tokens.retokenizer",
     "spacy.matcher.matcher",
     "spacy.matcher.phrasematcher",
     "spacy.matcher.dependencymatcher",
     "spacy.symbols",
     "spacy.vectors",
+    "spacy.tests.parser._search",
 ]
 COMPILE_OPTIONS = {
     "msvc": ["/Ox", "/EHsc"],
@@ -81,7 +86,6 @@ COPY_FILES = {
     ROOT / "setup.cfg": PACKAGE_ROOT / "tests" / "package",
     ROOT / "pyproject.toml": PACKAGE_ROOT / "tests" / "package",
     ROOT / "requirements.txt": PACKAGE_ROOT / "tests" / "package",
-    ROOT / "website" / "meta" / "universe.json": PACKAGE_ROOT / "tests" / "universe",
 }
 
 
@@ -125,6 +129,8 @@ class build_ext_options:
 
 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)
 
@@ -202,10 +208,25 @@ def setup_package():
         get_python_inc(plat_specific=True),
     ]
     ext_modules = []
+    ext_modules.append(
+        Extension(
+            "spacy.matcher.levenshtein",
+            [
+                "spacy/matcher/levenshtein.pyx",
+                "spacy/matcher/polyleven.c",
+            ],
+            language="c",
+            include_dirs=include_dirs,
+        )
+    )
     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/__init__.py

@@ -1,6 +1,6 @@
-from typing import Union, Iterable, Dict, Any
-from pathlib import Path
 import sys
+from pathlib import Path
+from typing import Any, Dict, Iterable, Union
 
 # set library-specific custom warning handling before doing anything else
 from .errors import setup_default_warnings
@@ -8,20 +8,17 @@ from .errors import setup_default_warnings
 setup_default_warnings()  # noqa: E402
 
 # These are imported as part of the API
-from thinc.api import prefer_gpu, require_gpu, require_cpu  # noqa: F401
-from thinc.api import Config
+from thinc.api import Config, prefer_gpu, require_cpu, require_gpu  # noqa: F401
 
 from . import pipeline  # noqa: F401
-from .cli.info import info  # noqa: F401
-from .glossary import explain  # noqa: F401
-from .about import __version__  # noqa: F401
-from .util import registry, logger  # noqa: F401
-
-from .errors import Errors
-from .language import Language
-from .vocab import Vocab
 from . import util
-
+from .about import __version__  # noqa: F401
+from .cli.info import info  # noqa: F401
+from .errors import Errors
+from .glossary import explain  # noqa: F401
+from .language import Language
+from .util import logger, registry  # noqa: F401
+from .vocab import Vocab
 
 if sys.maxunicode == 65535:
     raise SystemError(Errors.E130)
@@ -31,25 +28,33 @@ def load(
     name: Union[str, Path],
     *,
     vocab: Union[Vocab, bool] = True,
-    disable: Iterable[str] = util.SimpleFrozenList(),
-    exclude: Iterable[str] = util.SimpleFrozenList(),
+    disable: Union[str, Iterable[str]] = util._DEFAULT_EMPTY_PIPES,
+    enable: Union[str, Iterable[str]] = util._DEFAULT_EMPTY_PIPES,
+    exclude: Union[str, Iterable[str]] = util._DEFAULT_EMPTY_PIPES,
     config: Union[Dict[str, Any], Config] = util.SimpleFrozenDict(),
 ) -> Language:
     """Load a spaCy model from an installed package or a local path.
 
     name (str): Package name or model path.
     vocab (Vocab): A Vocab object. If True, a vocab is created.
-    disable (Iterable[str]): Names of pipeline components to disable. Disabled
+    disable (Union[str, Iterable[str]]): Name(s) of pipeline component(s) to disable. Disabled
         pipes will be loaded but they won't be run unless you explicitly
         enable them by calling nlp.enable_pipe.
-    exclude (Iterable[str]): Names of pipeline components to exclude. Excluded
+    enable (Union[str, Iterable[str]]): Name(s) of pipeline component(s) to enable. All other
+        pipes will be disabled (but can be enabled later using nlp.enable_pipe).
+    exclude (Union[str, Iterable[str]]): Name(s) of pipeline component(s) to exclude. Excluded
         components won't be loaded.
     config (Dict[str, Any] / Config): Config overrides as nested dict or dict
         keyed by section values in dot notation.
     RETURNS (Language): The loaded nlp object.
     """
     return util.load_model(
-        name, vocab=vocab, disable=disable, exclude=exclude, config=config
+        name,
+        vocab=vocab,
+        disable=disable,
+        enable=enable,
+        exclude=exclude,
+        config=config,
     )
 
 

spacy/about.py

@@ -1,7 +1,9 @@
 # fmt: off
 __title__ = "spacy"
-__version__ = "3.2.1"
+__version__ = "4.0.0.dev1"
 __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"
 __projects_branch__ = "v3"
+__lookups_tag__ = "v1.0.3"
+__lookups_url__ = f"https://raw.githubusercontent.com/explosion/spacy-lookups-data/{__lookups_tag__}/spacy_lookups_data/data/"

spacy/attrs.pxd

@@ -1,98 +1,50 @@
-# Reserve 64 values for flag features
 from . cimport symbols
 
+
 cdef enum attr_id_t:
-    NULL_ATTR
-    IS_ALPHA
-    IS_ASCII
-    IS_DIGIT
-    IS_LOWER
-    IS_PUNCT
-    IS_SPACE
-    IS_TITLE
-    IS_UPPER
-    LIKE_URL
-    LIKE_NUM
-    LIKE_EMAIL
-    IS_STOP
-    IS_OOV_DEPRECATED
-    IS_BRACKET
-    IS_QUOTE
-    IS_LEFT_PUNCT
-    IS_RIGHT_PUNCT
-    IS_CURRENCY
+    NULL_ATTR = 0
+    IS_ALPHA = symbols.IS_ALPHA
+    IS_ASCII = symbols.IS_ASCII
+    IS_DIGIT = symbols.IS_DIGIT
+    IS_LOWER = symbols.IS_LOWER
+    IS_PUNCT = symbols.IS_PUNCT
+    IS_SPACE = symbols.IS_SPACE
+    IS_TITLE = symbols.IS_TITLE
+    IS_UPPER = symbols.IS_UPPER
+    LIKE_URL = symbols.LIKE_URL
+    LIKE_NUM = symbols.LIKE_NUM
+    LIKE_EMAIL = symbols.LIKE_EMAIL
+    IS_STOP = symbols.IS_STOP
+    IS_BRACKET = symbols.IS_BRACKET
+    IS_QUOTE = symbols.IS_QUOTE
+    IS_LEFT_PUNCT = symbols.IS_LEFT_PUNCT
+    IS_RIGHT_PUNCT = symbols.IS_RIGHT_PUNCT
+    IS_CURRENCY = symbols.IS_CURRENCY
 
-    FLAG19 = 19
-    FLAG20
-    FLAG21
-    FLAG22
-    FLAG23
-    FLAG24
-    FLAG25
-    FLAG26
-    FLAG27
-    FLAG28
-    FLAG29
-    FLAG30
-    FLAG31
-    FLAG32
-    FLAG33
-    FLAG34
-    FLAG35
-    FLAG36
-    FLAG37
-    FLAG38
-    FLAG39
-    FLAG40
-    FLAG41
-    FLAG42
-    FLAG43
-    FLAG44
-    FLAG45
-    FLAG46
-    FLAG47
-    FLAG48
-    FLAG49
-    FLAG50
-    FLAG51
-    FLAG52
-    FLAG53
-    FLAG54
-    FLAG55
-    FLAG56
-    FLAG57
-    FLAG58
-    FLAG59
-    FLAG60
-    FLAG61
-    FLAG62
-    FLAG63
+    ID = symbols.ID
+    ORTH = symbols.ORTH
+    LOWER = symbols.LOWER
+    NORM = symbols.NORM
+    SHAPE = symbols.SHAPE
+    PREFIX = symbols.PREFIX
+    SUFFIX = symbols.SUFFIX
 
-    ID
-    ORTH
-    LOWER
-    NORM
-    SHAPE
-    PREFIX
-    SUFFIX
+    LENGTH = symbols.LENGTH
+    CLUSTER = symbols.CLUSTER
+    LEMMA = symbols.LEMMA
+    POS = symbols.POS
+    TAG = symbols.TAG
+    DEP = symbols.DEP
+    ENT_IOB = symbols.ENT_IOB
+    ENT_TYPE = symbols.ENT_TYPE
+    HEAD = symbols.HEAD
+    SENT_START = symbols.SENT_START
+    SPACY = symbols.SPACY
+    PROB = symbols.PROB
 
-    LENGTH
-    CLUSTER
-    LEMMA
-    POS
-    TAG
-    DEP
-    ENT_IOB
-    ENT_TYPE
-    HEAD
-    SENT_START
-    SPACY
-    PROB
-
-    LANG
+    LANG = symbols.LANG
     ENT_KB_ID = symbols.ENT_KB_ID
-    MORPH
+    MORPH = symbols.MORPH
     ENT_ID = symbols.ENT_ID
 
-    IDX
-    SENT_END
+    IDX = symbols.IDX

spacy/attrs.pyx

@@ -1,3 +1,6 @@
+from .errors import Errors
+
+IOB_STRINGS = ("", "I", "O", "B")
 
 IDS = {
     "": NULL_ATTR,
@@ -13,58 +16,11 @@ IDS = {
     "LIKE_NUM": LIKE_NUM,
     "LIKE_EMAIL": LIKE_EMAIL,
     "IS_STOP": IS_STOP,
-    "IS_OOV_DEPRECATED": IS_OOV_DEPRECATED,
     "IS_BRACKET": IS_BRACKET,
     "IS_QUOTE": IS_QUOTE,
     "IS_LEFT_PUNCT": IS_LEFT_PUNCT,
     "IS_RIGHT_PUNCT": IS_RIGHT_PUNCT,
     "IS_CURRENCY": IS_CURRENCY,
-    "FLAG19": FLAG19,
-    "FLAG20": FLAG20,
-    "FLAG21": FLAG21,
-    "FLAG22": FLAG22,
-    "FLAG23": FLAG23,
-    "FLAG24": FLAG24,
-    "FLAG25": FLAG25,
-    "FLAG26": FLAG26,
-    "FLAG27": FLAG27,
-    "FLAG28": FLAG28,
-    "FLAG29": FLAG29,
-    "FLAG30": FLAG30,
-    "FLAG31": FLAG31,
-    "FLAG32": FLAG32,
-    "FLAG33": FLAG33,
-    "FLAG34": FLAG34,
-    "FLAG35": FLAG35,
-    "FLAG36": FLAG36,
-    "FLAG37": FLAG37,
-    "FLAG38": FLAG38,
-    "FLAG39": FLAG39,
-    "FLAG40": FLAG40,
-    "FLAG41": FLAG41,
-    "FLAG42": FLAG42,
-    "FLAG43": FLAG43,
-    "FLAG44": FLAG44,
-    "FLAG45": FLAG45,
-    "FLAG46": FLAG46,
-    "FLAG47": FLAG47,
-    "FLAG48": FLAG48,
-    "FLAG49": FLAG49,
-    "FLAG50": FLAG50,
-    "FLAG51": FLAG51,
-    "FLAG52": FLAG52,
-    "FLAG53": FLAG53,
-    "FLAG54": FLAG54,
-    "FLAG55": FLAG55,
-    "FLAG56": FLAG56,
-    "FLAG57": FLAG57,
-    "FLAG58": FLAG58,
-    "FLAG59": FLAG59,
-    "FLAG60": FLAG60,
-    "FLAG61": FLAG61,
-    "FLAG62": FLAG62,
-    "FLAG63": FLAG63,
-
     "ID": ID,
     "ORTH": ORTH,
     "LOWER": LOWER,
@@ -72,7 +28,6 @@ IDS = {
     "SHAPE": SHAPE,
     "PREFIX": PREFIX,
     "SUFFIX": SUFFIX,
-
     "LENGTH": LENGTH,
     "LEMMA": LEMMA,
     "POS": POS,
@@ -87,16 +42,15 @@ IDS = {
     "SPACY": SPACY,
     "LANG": LANG,
     "MORPH": MORPH,
-    "IDX": IDX
+    "IDX": IDX,
 }
 
 
-# ATTR IDs, in order of the symbol
-NAMES = [key for key, value in sorted(IDS.items(), key=lambda item: item[1])]
+NAMES = {v: k for k, v in IDS.items()}
 locals().update(IDS)
 
 
-def intify_attrs(stringy_attrs, strings_map=None, _do_deprecated=False):
+def intify_attrs(stringy_attrs, strings_map=None):
     """
     Normalize a dictionary of attributes, converting them to ints.
 
@@ -108,42 +62,16 @@ def intify_attrs(stringy_attrs, strings_map=None, _do_deprecated=False):
         converted to ints.
     """
     inty_attrs = {}
-    if _do_deprecated:
-        if 'F' in stringy_attrs:
-            stringy_attrs["ORTH"] = stringy_attrs.pop("F")
-        if 'L' in stringy_attrs:
-            stringy_attrs["LEMMA"] = stringy_attrs.pop("L")
-        if 'pos' in stringy_attrs:
-            stringy_attrs["TAG"] = stringy_attrs.pop("pos")
-        if 'morph' in stringy_attrs:
-            morphs = stringy_attrs.pop('morph')
-        if 'number' in stringy_attrs:
-            stringy_attrs.pop('number')
-        if 'tenspect' in stringy_attrs:
-            stringy_attrs.pop('tenspect')
-        morph_keys = [
-            'PunctType', 'PunctSide', 'Other', 'Degree', 'AdvType', 'Number',
-            'VerbForm', 'PronType', 'Aspect', 'Tense', 'PartType', 'Poss',
-            'Hyph', 'ConjType', 'NumType', 'Foreign', 'VerbType', 'NounType',
-            'Gender', 'Mood', 'Negative', 'Tense', 'Voice', 'Abbr',
-            'Derivation', 'Echo', 'Foreign', 'NameType', 'NounType', 'NumForm',
-            'NumValue', 'PartType', 'Polite', 'StyleVariant',
-            'PronType', 'AdjType', 'Person', 'Variant', 'AdpType',
-            'Reflex', 'Negative', 'Mood', 'Aspect', 'Case',
-            'Polarity', 'PrepCase', 'Animacy' # U20
-        ]
-        for key in morph_keys:
-            if key in stringy_attrs:
-                stringy_attrs.pop(key)
-            elif key.lower() in stringy_attrs:
-                stringy_attrs.pop(key.lower())
-            elif key.upper() in stringy_attrs:
-                stringy_attrs.pop(key.upper())
     for name, value in stringy_attrs.items():
         int_key = intify_attr(name)
         if int_key is not None:
+            if int_key == ENT_IOB:
+                if value in IOB_STRINGS:
+                    value = IOB_STRINGS.index(value)
+                elif isinstance(value, str):
+                    raise ValueError(Errors.E1025.format(value=value))
             if strings_map is not None and isinstance(value, str):
-                if hasattr(strings_map, 'add'):
+                if hasattr(strings_map, "add"):
                     value = strings_map.add(value)
                 else:
                     value = strings_map[value]

spacy/cli/__init__.py

@@ -1,31 +1,35 @@
 from wasabi import msg
 
 from ._util import app, setup_cli  # noqa: F401
+from .apply import apply  # noqa: F401
+from .assemble import assemble_cli  # noqa: F401
 
 # These are the actual functions, NOT the wrapped CLI commands. The CLI commands
 # are registered automatically and won't have to be imported here.
-from .download import download  # noqa: F401
-from .info import info  # noqa: F401
-from .package import package  # noqa: F401
-from .profile import profile  # noqa: F401
-from .train import train_cli  # noqa: F401
-from .assemble import assemble_cli  # noqa: F401
-from .pretrain import pretrain  # noqa: F401
-from .debug_data import debug_data  # noqa: F401
-from .debug_config import debug_config  # noqa: F401
-from .debug_model import debug_model  # noqa: F401
-from .evaluate import evaluate  # noqa: F401
+from .benchmark_speed import benchmark_speed_cli  # noqa: F401
 from .convert import convert  # noqa: F401
+from .debug_config import debug_config  # noqa: F401
+from .debug_data import debug_data  # noqa: F401
+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_threshold import find_threshold  # noqa: F401
+from .info import info  # noqa: F401
+from .init_config import fill_config, init_config  # noqa: F401
 from .init_pipeline import init_pipeline_cli  # noqa: F401
-from .init_config import init_config, fill_config  # noqa: F401
-from .validate import validate  # noqa: F401
-from .project.clone import project_clone  # noqa: F401
+from .package import package  # noqa: F401
+from .pretrain import pretrain  # noqa: F401
+from .profile import profile  # noqa: F401
 from .project.assets import project_assets  # noqa: F401
-from .project.run import project_run  # noqa: F401
-from .project.dvc import project_update_dvc  # noqa: F401
-from .project.push import project_push  # noqa: F401
-from .project.pull import project_pull  # noqa: F401
+from .project.clone import project_clone  # noqa: F401
 from .project.document import project_document  # noqa: F401
+from .project.dvc import project_update_dvc  # noqa: F401
+from .project.pull import project_pull  # noqa: F401
+from .project.push import project_push  # noqa: F401
+from .project.run import project_run  # noqa: F401
+from .train import train_cli  # noqa: F401
+from .validate import validate  # noqa: F401
 
 
 @app.command("link", no_args_is_help=True, deprecated=True, hidden=True)

spacy/cli/_util.py

@@ -1,29 +1,48 @@
-from typing import Dict, Any, Union, List, Optional, Tuple, Iterable
-from typing import TYPE_CHECKING, overload
-import sys
-import shutil
-from pathlib import Path
-from wasabi import msg, Printer
-import srsly
 import hashlib
+import os
+import shutil
+import sys
+from configparser import InterpolationError
+from contextlib import contextmanager
+from pathlib import Path
+from typing import (
+    TYPE_CHECKING,
+    Any,
+    Dict,
+    Iterable,
+    List,
+    Literal,
+    Optional,
+    Tuple,
+    Union,
+    overload,
+)
+
+import srsly
 import typer
 from click import NoSuchOption
 from click.parser import split_arg_string
-from typer.main import get_command
-from contextlib import contextmanager
 from thinc.api import Config, ConfigValidationError, require_gpu
-from thinc.util import has_cupy, gpu_is_available
-from configparser import InterpolationError
-import os
+from thinc.util import gpu_is_available
+from typer.main import get_command
+from wasabi import Printer, msg
 
-from ..compat import Literal
-from ..schemas import ProjectConfigSchema, validate
-from ..util import import_file, run_command, make_tempdir, registry, logger
-from ..util import is_compatible_version, SimpleFrozenDict, ENV_VARS
 from .. import about
+from ..errors import RENAMED_LANGUAGE_CODES
+from ..schemas import ProjectConfigSchema, validate
+from ..util import (
+    ENV_VARS,
+    SimpleFrozenDict,
+    import_file,
+    is_compatible_version,
+    logger,
+    make_tempdir,
+    registry,
+    run_command,
+)
 
 if TYPE_CHECKING:
-    from pathy import Pathy  # noqa: F401
+    from pathy import FluidPath  # noqa: F401
 
 
 SDIST_SUFFIX = ".tar.gz"
@@ -46,6 +65,7 @@ DEBUG_HELP = """Suite of helpful commands for debugging and profiling. Includes
 commands to check and validate your config files, training and evaluation data,
 and custom model implementations.
 """
+BENCHMARK_HELP = """Commands for benchmarking pipelines."""
 INIT_HELP = """Commands for initializing configs and pipeline packages."""
 
 # Wrappers for Typer's annotations. Initially created to set defaults and to
@@ -54,12 +74,14 @@ Arg = typer.Argument
 Opt = typer.Option
 
 app = typer.Typer(name=NAME, help=HELP)
+benchmark_cli = typer.Typer(name="benchmark", help=BENCHMARK_HELP, no_args_is_help=True)
 project_cli = typer.Typer(name="project", help=PROJECT_HELP, no_args_is_help=True)
 debug_cli = typer.Typer(name="debug", help=DEBUG_HELP, no_args_is_help=True)
 init_cli = typer.Typer(name="init", help=INIT_HELP, no_args_is_help=True)
 
 app.add_typer(project_cli)
 app.add_typer(debug_cli)
+app.add_typer(benchmark_cli)
 app.add_typer(init_cli)
 
 
@@ -87,9 +109,9 @@ def parse_config_overrides(
     cli_overrides = _parse_overrides(args, is_cli=True)
     if cli_overrides:
         keys = [k for k in cli_overrides if k not in env_overrides]
-        logger.debug(f"Config overrides from CLI: {keys}")
+        logger.debug("Config overrides from CLI: %s", keys)
     if env_overrides:
-        logger.debug(f"Config overrides from env variables: {list(env_overrides)}")
+        logger.debug("Config overrides from env variables: %s", list(env_overrides))
     return {**cli_overrides, **env_overrides}
 
 
@@ -132,6 +154,16 @@ def _parse_override(value: Any) -> Any:
         return str(value)
 
 
+def _handle_renamed_language_codes(lang: Optional[str]) -> None:
+    # Throw error for renamed language codes in v4
+    if lang in RENAMED_LANGUAGE_CODES:
+        msg.fail(
+            title="Renamed language code",
+            text=f"Language code '{lang}' was replaced with '{RENAMED_LANGUAGE_CODES[lang]}' in spaCy v4. Update the language code from '{lang}' to '{RENAMED_LANGUAGE_CODES[lang]}'.",
+            exits=1,
+        )
+
+
 def load_project_config(
     path: Path, interpolate: bool = True, overrides: Dict[str, Any] = SimpleFrozenDict()
 ) -> Dict[str, Any]:
@@ -158,15 +190,15 @@ def load_project_config(
         sys.exit(1)
     validate_project_version(config)
     validate_project_commands(config)
+    if interpolate:
+        err = f"{PROJECT_FILE} validation error"
+        with show_validation_error(title=err, hint_fill=False):
+            config = substitute_project_variables(config, overrides)
     # Make sure directories defined in config exist
     for subdir in config.get("directories", []):
         dir_path = path / subdir
         if not dir_path.exists():
             dir_path.mkdir(parents=True)
-    if interpolate:
-        err = f"{PROJECT_FILE} validation error"
-        with show_validation_error(title=err, hint_fill=False):
-            config = substitute_project_variables(config, overrides)
     return config
 
 
@@ -318,6 +350,13 @@ def show_validation_error(
         msg.fail("Config validation error", e, exits=1)
 
 
+def import_code_paths(code_paths: str) -> None:
+    """Helper to import comma-separated list of code paths."""
+    code_paths = [Path(p.strip()) for p in string_to_list(code_paths)]
+    for code_path in code_paths:
+        import_code(code_path)
+
+
 def import_code(code_path: Optional[Union[Path, str]]) -> None:
     """Helper to import Python file provided in training commands / commands
     using the config. This makes custom registered functions available.
@@ -331,7 +370,7 @@ def import_code(code_path: Optional[Union[Path, str]]) -> None:
             msg.fail(f"Couldn't load Python code: {code_path}", e, exits=1)
 
 
-def upload_file(src: Path, dest: Union[str, "Pathy"]) -> None:
+def upload_file(src: Path, dest: Union[str, "FluidPath"]) -> None:
     """Upload a file.
 
     src (Path): The source path.
@@ -339,13 +378,20 @@ def upload_file(src: Path, dest: Union[str, "Pathy"]) -> None:
     """
     import smart_open
 
+    # Create parent directories for local paths
+    if isinstance(dest, Path):
+        if not dest.parent.exists():
+            dest.parent.mkdir(parents=True)
+
     dest = str(dest)
     with smart_open.open(dest, mode="wb") as output_file:
         with src.open(mode="rb") as input_file:
             output_file.write(input_file.read())
 
 
-def download_file(src: Union[str, "Pathy"], dest: Path, *, force: bool = False) -> None:
+def download_file(
+    src: Union[str, "FluidPath"], dest: Path, *, force: bool = False
+) -> None:
     """Download a file using smart_open.
 
     url (str): The URL of the file.
@@ -358,9 +404,9 @@ def download_file(src: Union[str, "Pathy"], dest: Path, *, force: bool = False)
     if dest.exists() and not force:
         return None
     src = str(src)
-    with smart_open.open(src, mode="rb", ignore_ext=True) as input_file:
+    with smart_open.open(src, mode="rb", compression="disable") as input_file:
         with dest.open(mode="wb") as output_file:
-            output_file.write(input_file.read())
+            shutil.copyfileobj(input_file, output_file)
 
 
 def ensure_pathy(path):
@@ -368,7 +414,7 @@ def ensure_pathy(path):
     slow and annoying Google Cloud warning)."""
     from pathy import Pathy  # noqa: F811
 
-    return Pathy(path)
+    return Pathy.fluid(path)
 
 
 def git_checkout(
@@ -462,6 +508,23 @@ 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]:
@@ -554,5 +617,41 @@ def setup_gpu(use_gpu: int, silent=None) -> None:
         require_gpu(use_gpu)
     else:
         local_msg.info("Using CPU")
-        if has_cupy and gpu_is_available():
+        if gpu_is_available():
             local_msg.info("To switch to GPU 0, use the option: --gpu-id 0")
+
+
+def walk_directory(path: Path, suffix: Optional[str] = None) -> List[Path]:
+    """Given a directory and a suffix, recursively find all files matching the suffix.
+    Directories or files with names beginning with a . are ignored, but hidden flags on
+    filesystems are not checked.
+    When provided with a suffix `None`, there is no suffix-based filtering."""
+    if not path.is_dir():
+        return [path]
+    paths = [path]
+    locs = []
+    seen = set()
+    for path in paths:
+        if str(path) in seen:
+            continue
+        seen.add(str(path))
+        if path.parts[-1].startswith("."):
+            continue
+        elif path.is_dir():
+            paths.extend(path.iterdir())
+        elif suffix is not None and not path.parts[-1].endswith(suffix):
+            continue
+        else:
+            locs.append(path)
+    # It's good to sort these, in case the ordering messes up cache.
+    locs.sort()
+    return locs
+
+
+def _format_number(number: Union[int, float], ndigits: int = 2) -> str:
+    """Formats a number (float or int) rounding to `ndigits`, without truncating trailing 0s,
+    as happens with `round(number, ndigits)`"""
+    if isinstance(number, float):
+        return f"{number:.{ndigits}f}"
+    else:
+        return str(number)

spacy/cli/apply.py

@@ -0,0 +1,140 @@
+from itertools import chain
+from pathlib import Path
+from typing import Iterable, List, Optional, Union, cast
+
+import srsly
+import tqdm
+from wasabi import msg
+
+from ..tokens import Doc, DocBin
+from ..util import ensure_path, load_model
+from ..vocab import Vocab
+from ._util import Arg, Opt, app, import_code, setup_gpu, walk_directory
+
+path_help = """Location of the documents to predict on.
+Can be a single file in .spacy format or a .jsonl file.
+Files with other extensions are treated as single plain text documents.
+If a directory is provided it is traversed recursively to grab
+all files to be processed.
+The files can be a mixture of .spacy, .jsonl and text files.
+If .jsonl is provided the specified field is going
+to be grabbed ("text" by default)."""
+
+out_help = "Path to save the resulting .spacy file"
+code_help = (
+    "Path to Python file with additional " "code (registered functions) to be imported"
+)
+gold_help = "Use gold preprocessing provided in the .spacy files"
+force_msg = (
+    "The provided output file already exists. "
+    "To force overwriting the output file, set the --force or -F flag."
+)
+
+
+DocOrStrStream = Union[Iterable[str], Iterable[Doc]]
+
+
+def _stream_docbin(path: Path, vocab: Vocab) -> Iterable[Doc]:
+    """
+    Stream Doc objects from DocBin.
+    """
+    docbin = DocBin().from_disk(path)
+    for doc in docbin.get_docs(vocab):
+        yield doc
+
+
+def _stream_jsonl(path: Path, field: str) -> Iterable[str]:
+    """
+    Stream "text" field from JSONL. If the field "text" is
+    not found it raises error.
+    """
+    for entry in srsly.read_jsonl(path):
+        if field not in entry:
+            msg.fail(f"{path} does not contain the required '{field}' field.", exits=1)
+        else:
+            yield entry[field]
+
+
+def _stream_texts(paths: Iterable[Path]) -> Iterable[str]:
+    """
+    Yields strings from text files in paths.
+    """
+    for path in paths:
+        with open(path, "r") as fin:
+            text = fin.read()
+            yield text
+
+
+@app.command("apply")
+def apply_cli(
+    # fmt: off
+    model: str = Arg(..., help="Model name or path"),
+    data_path: Path = Arg(..., help=path_help, exists=True),
+    output_file: Path = Arg(..., help=out_help, dir_okay=False),
+    code_path: Optional[Path] = Opt(None, "--code", "-c", help=code_help),
+    text_key: str = Opt("text", "--text-key", "-tk", help="Key containing text string for JSONL"),
+    force_overwrite: bool = Opt(False, "--force", "-F", help="Force overwriting the output file"),
+    use_gpu: int = Opt(-1, "--gpu-id", "-g", help="GPU ID or -1 for CPU."),
+    batch_size: int = Opt(1, "--batch-size", "-b", help="Batch size."),
+    n_process: int = Opt(1, "--n-process", "-n", help="number of processors to use.")
+):
+    """
+    Apply a trained pipeline to documents to get predictions.
+    Expects a loadable spaCy pipeline and path to the data, which
+    can be a directory or a file.
+    The data files can be provided in multiple formats:
+        1. .spacy files
+        2. .jsonl files with a specified "field" to read the text from.
+        3. Files with any other extension are assumed to be containing
+           a single document.
+    DOCS: https://spacy.io/api/cli#apply
+    """
+    data_path = ensure_path(data_path)
+    output_file = ensure_path(output_file)
+    code_path = ensure_path(code_path)
+    if output_file.exists() and not force_overwrite:
+        msg.fail(force_msg, exits=1)
+    if not data_path.exists():
+        msg.fail(f"Couldn't find data path: {data_path}", exits=1)
+    import_code(code_path)
+    setup_gpu(use_gpu)
+    apply(data_path, output_file, model, text_key, batch_size, n_process)
+
+
+def apply(
+    data_path: Path,
+    output_file: Path,
+    model: str,
+    json_field: str,
+    batch_size: int,
+    n_process: int,
+):
+    docbin = DocBin(store_user_data=True)
+    paths = walk_directory(data_path)
+    if len(paths) == 0:
+        docbin.to_disk(output_file)
+        msg.warn(
+            "Did not find data to process,"
+            f" {data_path} seems to be an empty directory."
+        )
+        return
+    nlp = load_model(model)
+    msg.good(f"Loaded model {model}")
+    vocab = nlp.vocab
+    streams: List[DocOrStrStream] = []
+    text_files = []
+    for path in paths:
+        if path.suffix == ".spacy":
+            streams.append(_stream_docbin(path, vocab))
+        elif path.suffix == ".jsonl":
+            streams.append(_stream_jsonl(path, json_field))
+        else:
+            text_files.append(path)
+    if len(text_files) > 0:
+        streams.append(_stream_texts(text_files))
+    datagen = cast(DocOrStrStream, chain(*streams))
+    for doc in tqdm.tqdm(nlp.pipe(datagen, batch_size=batch_size, n_process=n_process)):
+        docbin.add(doc)
+    if output_file.suffix == "":
+        output_file = output_file.with_suffix(".spacy")
+    docbin.to_disk(output_file)

spacy/cli/assemble.py

@@ -1,13 +1,20 @@
-from typing import Optional
-from pathlib import Path
-from wasabi import msg
-import typer
 import logging
+from pathlib import Path
+from typing import Optional
+
+import typer
+from wasabi import msg
 
-from ._util import app, Arg, Opt, parse_config_overrides, show_validation_error
-from ._util import import_code
 from .. import util
 from ..util import get_sourced_components, load_model_from_config
+from ._util import (
+    Arg,
+    Opt,
+    app,
+    import_code_paths,
+    parse_config_overrides,
+    show_validation_error,
+)
 
 
 @app.command(
@@ -19,7 +26,7 @@ def assemble_cli(
     ctx: typer.Context,  # This is only used to read additional arguments
     config_path: Path = Arg(..., help="Path to config file", exists=True, allow_dash=True),
     output_path: Path = Arg(..., help="Output directory to store assembled pipeline in"),
-    code_path: Optional[Path] = Opt(None, "--code", "-c", help="Path to Python file with additional code (registered functions) to be imported"),
+    code_path: str = Opt("", "--code", "-c", help="Comma-separated paths to Python files with additional code (registered functions) to be imported"),
     verbose: bool = Opt(False, "--verbose", "-V", "-VV", help="Display more information for debugging purposes"),
     # fmt: on
 ):
@@ -38,7 +45,7 @@ def assemble_cli(
     if not config_path or (str(config_path) != "-" and not config_path.exists()):
         msg.fail("Config file not found", config_path, exits=1)
     overrides = parse_config_overrides(ctx.args)
-    import_code(code_path)
+    import_code_paths(code_path)
     with show_validation_error(config_path):
         config = util.load_config(config_path, overrides=overrides, interpolate=False)
     msg.divider("Initializing pipeline")

spacy/cli/benchmark_speed.py

@@ -0,0 +1,175 @@
+import random
+import time
+from itertools import islice
+from pathlib import Path
+from typing import Iterable, List, Optional
+
+import numpy
+import typer
+from tqdm import tqdm
+from wasabi import msg
+
+from .. import util
+from ..language import Language
+from ..tokens import Doc
+from ..training import Corpus
+from ._util import Arg, Opt, benchmark_cli, setup_gpu
+
+
+@benchmark_cli.command(
+    "speed",
+    context_settings={"allow_extra_args": True, "ignore_unknown_options": True},
+)
+def benchmark_speed_cli(
+    # fmt: off
+    ctx: typer.Context,
+    model: str = Arg(..., help="Model name or path"),
+    data_path: Path = Arg(..., help="Location of binary evaluation data in .spacy format", exists=True),
+    batch_size: Optional[int] = Opt(None, "--batch-size", "-b", min=1, help="Override the pipeline batch size"),
+    no_shuffle: bool = Opt(False, "--no-shuffle", help="Do not shuffle benchmark data"),
+    use_gpu: int = Opt(-1, "--gpu-id", "-g", help="GPU ID or -1 for CPU"),
+    n_batches: int = Opt(50, "--batches", help="Minimum number of batches to benchmark", min=30,),
+    warmup_epochs: int = Opt(3, "--warmup", "-w", min=0, help="Number of iterations over the data for warmup"),
+    # fmt: on
+):
+    """
+    Benchmark a pipeline. Expects a loadable spaCy pipeline and benchmark
+    data in the binary .spacy format.
+    """
+    setup_gpu(use_gpu=use_gpu, silent=False)
+
+    nlp = util.load_model(model)
+    batch_size = batch_size if batch_size is not None else nlp.batch_size
+    corpus = Corpus(data_path)
+    docs = [eg.predicted for eg in corpus(nlp)]
+
+    if len(docs) == 0:
+        msg.fail("Cannot benchmark speed using an empty corpus.", exits=1)
+
+    print(f"Warming up for {warmup_epochs} epochs...")
+    warmup(nlp, docs, warmup_epochs, batch_size)
+
+    print()
+    print(f"Benchmarking {n_batches} batches...")
+    wps = benchmark(nlp, docs, n_batches, batch_size, not no_shuffle)
+
+    print()
+    print_outliers(wps)
+    print_mean_with_ci(wps)
+
+
+# Lowercased, behaves as a context manager function.
+class time_context:
+    """Register the running time of a context."""
+
+    def __enter__(self):
+        self.start = time.perf_counter()
+        return self
+
+    def __exit__(self, type, value, traceback):
+        self.elapsed = time.perf_counter() - self.start
+
+
+class Quartiles:
+    """Calculate the q1, q2, q3 quartiles and the inter-quartile range (iqr)
+    of a sample."""
+
+    q1: float
+    q2: float
+    q3: float
+    iqr: float
+
+    def __init__(self, sample: numpy.ndarray) -> None:
+        self.q1 = numpy.quantile(sample, 0.25)
+        self.q2 = numpy.quantile(sample, 0.5)
+        self.q3 = numpy.quantile(sample, 0.75)
+        self.iqr = self.q3 - self.q1
+
+
+def annotate(
+    nlp: Language, docs: List[Doc], batch_size: Optional[int]
+) -> numpy.ndarray:
+    docs = nlp.pipe(tqdm(docs, unit="doc"), batch_size=batch_size)
+    wps = []
+    while True:
+        with time_context() as elapsed:
+            batch_docs = list(
+                islice(docs, batch_size if batch_size else nlp.batch_size)
+            )
+        if len(batch_docs) == 0:
+            break
+        n_tokens = count_tokens(batch_docs)
+        wps.append(n_tokens / elapsed.elapsed)
+
+    return numpy.array(wps)
+
+
+def benchmark(
+    nlp: Language,
+    docs: List[Doc],
+    n_batches: int,
+    batch_size: int,
+    shuffle: bool,
+) -> numpy.ndarray:
+    if shuffle:
+        bench_docs = [
+            nlp.make_doc(random.choice(docs).text)
+            for _ in range(n_batches * batch_size)
+        ]
+    else:
+        bench_docs = [
+            nlp.make_doc(docs[i % len(docs)].text)
+            for i in range(n_batches * batch_size)
+        ]
+
+    return annotate(nlp, bench_docs, batch_size)
+
+
+def bootstrap(x, statistic=numpy.mean, iterations=10000) -> numpy.ndarray:
+    """Apply a statistic to repeated random samples of an array."""
+    return numpy.fromiter(
+        (
+            statistic(numpy.random.choice(x, len(x), replace=True))
+            for _ in range(iterations)
+        ),
+        numpy.float64,
+    )
+
+
+def count_tokens(docs: Iterable[Doc]) -> int:
+    return sum(len(doc) for doc in docs)
+
+
+def print_mean_with_ci(sample: numpy.ndarray):
+    mean = numpy.mean(sample)
+    bootstrap_means = bootstrap(sample)
+    bootstrap_means.sort()
+
+    # 95% confidence interval
+    low = bootstrap_means[int(len(bootstrap_means) * 0.025)]
+    high = bootstrap_means[int(len(bootstrap_means) * 0.975)]
+
+    print(f"Mean: {mean:.1f} words/s (95% CI: {low-mean:.1f} +{high-mean:.1f})")
+
+
+def print_outliers(sample: numpy.ndarray):
+    quartiles = Quartiles(sample)
+
+    n_outliers = numpy.sum(
+        (sample < (quartiles.q1 - 1.5 * quartiles.iqr))
+        | (sample > (quartiles.q3 + 1.5 * quartiles.iqr))
+    )
+    n_extreme_outliers = numpy.sum(
+        (sample < (quartiles.q1 - 3.0 * quartiles.iqr))
+        | (sample > (quartiles.q3 + 3.0 * quartiles.iqr))
+    )
+    print(
+        f"Outliers: {(100 * n_outliers) / len(sample):.1f}%, extreme outliers: {(100 * n_extreme_outliers) / len(sample)}%"
+    )
+
+
+def warmup(
+    nlp: Language, docs: List[Doc], warmup_epochs: int, batch_size: Optional[int]
+) -> numpy.ndarray:
+    docs = warmup_epochs * docs
+    return annotate(nlp, docs, batch_size)

spacy/cli/convert.py

@@ -1,18 +1,22 @@
-from typing import Callable, Iterable, Mapping, Optional, Any, List, Union
-from enum import Enum
-from pathlib import Path
-from wasabi import Printer
-import srsly
+import itertools
 import re
 import sys
-import itertools
+from enum import Enum
+from pathlib import Path
+from typing import Any, Callable, Iterable, Mapping, Optional, Union
+
+import srsly
+from wasabi import Printer
 
-from ._util import app, Arg, Opt
-from ..training import docs_to_json
 from ..tokens import Doc, DocBin
-from ..training.converters import iob_to_docs, conll_ner_to_docs, json_to_docs
-from ..training.converters import conllu_to_docs
-
+from ..training import docs_to_json
+from ..training.converters import (
+    conll_ner_to_docs,
+    conllu_to_docs,
+    iob_to_docs,
+    json_to_docs,
+)
+from ._util import Arg, Opt, _handle_renamed_language_codes, app, walk_directory
 
 # Converters are matched by file extension except for ner/iob, which are
 # matched by file extension and content. To add a converter, add a new
@@ -28,6 +32,8 @@ CONVERTERS: Mapping[str, Callable[..., Iterable[Doc]]] = {
     "json": json_to_docs,
 }
 
+AUTO = "auto"
+
 
 # File types that can be written to stdout
 FILE_TYPES_STDOUT = ("json",)
@@ -49,7 +55,7 @@ def convert_cli(
     model: Optional[str] = Opt(None, "--model", "--base", "-b", help="Trained spaCy pipeline for sentence segmentation to use as base (for --seg-sents)"),
     morphology: bool = Opt(False, "--morphology", "-m", help="Enable appending morphology to tags"),
     merge_subtokens: bool = Opt(False, "--merge-subtokens", "-T", help="Merge CoNLL-U subtokens"),
-    converter: str = Opt("auto", "--converter", "-c", help=f"Converter: {tuple(CONVERTERS.keys())}"),
+    converter: str = Opt(AUTO, "--converter", "-c", help=f"Converter: {tuple(CONVERTERS.keys())}"),
     ner_map: Optional[Path] = Opt(None, "--ner-map", "-nm", help="NER tag mapping (as JSON-encoded dict of entity types)", exists=True),
     lang: Optional[str] = Opt(None, "--lang", "-l", help="Language (if tokenizer required)"),
     concatenate: bool = Opt(None, "--concatenate", "-C", help="Concatenate output to a single file"),
@@ -70,8 +76,8 @@ def convert_cli(
     output_dir: Union[str, Path] = "-" if output_dir == Path("-") else output_dir
     silent = output_dir == "-"
     msg = Printer(no_print=silent)
-    verify_cli_args(msg, input_path, output_dir, file_type.value, converter, ner_map)
     converter = _get_converter(msg, converter, input_path)
+    verify_cli_args(msg, input_path, output_dir, file_type.value, converter, ner_map)
     convert(
         input_path,
         output_dir,
@@ -100,7 +106,7 @@ def convert(
     model: Optional[str] = None,
     morphology: bool = False,
     merge_subtokens: bool = False,
-    converter: str = "auto",
+    converter: str,
     ner_map: Optional[Path] = None,
     lang: Optional[str] = None,
     concatenate: bool = False,
@@ -110,6 +116,10 @@ def convert(
     input_path = Path(input_path)
     if not msg:
         msg = Printer(no_print=silent)
+
+    # Throw error for renamed language codes in v4
+    _handle_renamed_language_codes(lang)
+
     ner_map = srsly.read_json(ner_map) if ner_map is not None else None
     doc_files = []
     for input_loc in walk_directory(input_path, converter):
@@ -189,33 +199,6 @@ def autodetect_ner_format(input_data: str) -> Optional[str]:
     return None
 
 
-def walk_directory(path: Path, converter: str) -> List[Path]:
-    if not path.is_dir():
-        return [path]
-    paths = [path]
-    locs = []
-    seen = set()
-    for path in paths:
-        if str(path) in seen:
-            continue
-        seen.add(str(path))
-        if path.parts[-1].startswith("."):
-            continue
-        elif path.is_dir():
-            paths.extend(path.iterdir())
-        elif converter == "json" and not path.parts[-1].endswith("json"):
-            continue
-        elif converter == "conll" and not path.parts[-1].endswith("conll"):
-            continue
-        elif converter == "iob" and not path.parts[-1].endswith("iob"):
-            continue
-        else:
-            locs.append(path)
-    # It's good to sort these, in case the ordering messes up cache.
-    locs.sort()
-    return locs
-
-
 def verify_cli_args(
     msg: Printer,
     input_path: Path,
@@ -239,18 +222,22 @@ def verify_cli_args(
         input_locs = walk_directory(input_path, converter)
         if len(input_locs) == 0:
             msg.fail("No input files in directory", input_path, exits=1)
-        file_types = list(set([loc.suffix[1:] for loc in input_locs]))
-        if converter == "auto" and len(file_types) >= 2:
-            file_types_str = ",".join(file_types)
-            msg.fail("All input files must be same type", file_types_str, exits=1)
-    if converter != "auto" and converter not in CONVERTERS:
+    if converter not in CONVERTERS:
         msg.fail(f"Can't find converter for {converter}", exits=1)
 
 
 def _get_converter(msg, converter, input_path: Path):
     if input_path.is_dir():
-        input_path = walk_directory(input_path, converter)[0]
-    if converter == "auto":
+        if converter == AUTO:
+            input_locs = walk_directory(input_path, suffix=None)
+            file_types = list(set([loc.suffix[1:] for loc in input_locs]))
+            if len(file_types) >= 2:
+                file_types_str = ",".join(file_types)
+                msg.fail("All input files must be same type", file_types_str, exits=1)
+            input_path = input_locs[0]
+        else:
+            input_path = walk_directory(input_path, suffix=converter)[0]
+    if converter == AUTO:
         converter = input_path.suffix[1:]
     if converter == "ner" or converter == "iob":
         with input_path.open(encoding="utf8") as file_:

spacy/cli/debug_config.py

@@ -1,15 +1,22 @@
-from typing import Optional, Dict, Any, Union, List
 from pathlib import Path
-from wasabi import msg, table
+from typing import Any, Dict, List, Optional, Union
+
+import typer
 from thinc.api import Config
 from thinc.config import VARIABLE_RE
-import typer
+from wasabi import msg, table
 
-from ._util import Arg, Opt, show_validation_error, parse_config_overrides
-from ._util import import_code, debug_cli
+from .. import util
 from ..schemas import ConfigSchemaInit, ConfigSchemaTraining
 from ..util import registry
-from .. import util
+from ._util import (
+    Arg,
+    Opt,
+    debug_cli,
+    import_code_paths,
+    parse_config_overrides,
+    show_validation_error,
+)
 
 
 @debug_cli.command(
@@ -20,7 +27,7 @@ def debug_config_cli(
     # fmt: off
     ctx: typer.Context,  # This is only used to read additional arguments
     config_path: Path = Arg(..., help="Path to config file", exists=True, allow_dash=True),
-    code_path: Optional[Path] = Opt(None, "--code-path", "--code", "-c", help="Path to Python file with additional code (registered functions) to be imported"),
+    code_path: str = Opt("", "--code", "-c", help="Comma-separated paths to Python files with additional code (registered functions) to be imported"),
     show_funcs: bool = Opt(False, "--show-functions", "-F", help="Show an overview of all registered functions used in the config and where they come from (modules, files etc.)"),
     show_vars: bool = Opt(False, "--show-variables", "-V", help="Show an overview of all variables referenced in the config and their values. This will also reflect variables overwritten on the CLI.")
     # fmt: on
@@ -37,7 +44,7 @@ def debug_config_cli(
     DOCS: https://spacy.io/api/cli#debug-config
     """
     overrides = parse_config_overrides(ctx.args)
-    import_code(code_path)
+    import_code_paths(code_path)
     debug_config(
         config_path, overrides=overrides, show_funcs=show_funcs, show_vars=show_vars
     )

spacy/cli/debug_data.py

@@ -1,26 +1,49 @@
-from typing import Any, Dict, Iterable, List, Optional, Sequence, Set, Tuple, Union
-from typing import cast, overload
-from pathlib import Path
-from collections import Counter
+import math
 import sys
-import srsly
-from wasabi import Printer, MESSAGES, msg
-import typer
+from collections import Counter
+from pathlib import Path
+from typing import (
+    Any,
+    Dict,
+    Iterable,
+    List,
+    Literal,
+    Optional,
+    Sequence,
+    Set,
+    Tuple,
+    Union,
+    cast,
+    overload,
+)
 
-from ._util import app, Arg, Opt, show_validation_error, parse_config_overrides
-from ._util import import_code, debug_cli
-from ..training import Example
-from ..training.initialize import get_sourced_components
-from ..schemas import ConfigSchemaTraining
+import numpy
+import srsly
+import typer
+from wasabi import MESSAGES, Printer, msg
+
+from .. import util
+from ..language import Language
+from ..morphology import Morphology
+from ..pipeline import Morphologizer, SpanCategorizer, TrainablePipe
+from ..pipeline._edit_tree_internals.edit_trees import EditTrees
 from ..pipeline._parser_internals import nonproj
 from ..pipeline._parser_internals.nonproj import DELIMITER
-from ..pipeline import Morphologizer
-from ..morphology import Morphology
-from ..language import Language
+from ..schemas import ConfigSchemaTraining
+from ..training import Example, remove_bilu_prefix
+from ..training.initialize import get_sourced_components
 from ..util import registry, resolve_dot_names
-from ..compat import Literal
-from .. import util
-
+from ..vectors import Mode as VectorsMode
+from ._util import (
+    Arg,
+    Opt,
+    _format_number,
+    app,
+    debug_cli,
+    import_code_paths,
+    parse_config_overrides,
+    show_validation_error,
+)
 
 # Minimum number of expected occurrences of NER label in data to train new label
 NEW_LABEL_THRESHOLD = 50
@@ -29,6 +52,12 @@ DEP_LABEL_THRESHOLD = 20
 # Minimum number of expected examples to train a new pipeline
 BLANK_MODEL_MIN_THRESHOLD = 100
 BLANK_MODEL_THRESHOLD = 2000
+# Arbitrary threshold where SpanCat performs well
+SPAN_DISTINCT_THRESHOLD = 1
+# Arbitrary threshold where SpanCat performs well
+BOUNDARY_DISTINCT_THRESHOLD = 1
+# Arbitrary threshold for filtering span lengths during reporting (percentage)
+SPAN_LENGTH_THRESHOLD_PERCENTAGE = 90
 
 
 @debug_cli.command(
@@ -43,7 +72,7 @@ def debug_data_cli(
     # fmt: off
     ctx: typer.Context,  # This is only used to read additional arguments
     config_path: Path = Arg(..., help="Path to config file", exists=True, allow_dash=True),
-    code_path: Optional[Path] = Opt(None, "--code-path", "--code", "-c", help="Path to Python file with additional code (registered functions) to be imported"),
+    code_path: str = Opt("", "--code", "-c", help="Comma-separated paths to Python files with additional code (registered functions) to be imported"),
     ignore_warnings: bool = Opt(False, "--ignore-warnings", "-IW", help="Ignore warnings, only show stats and errors"),
     verbose: bool = Opt(False, "--verbose", "-V", help="Print additional information and explanations"),
     no_format: bool = Opt(False, "--no-format", "-NF", help="Don't pretty-print the results"),
@@ -63,7 +92,7 @@ def debug_data_cli(
             "--help for an overview of the other available debugging commands."
         )
     overrides = parse_config_overrides(ctx.args)
-    import_code(code_path)
+    import_code_paths(code_path)
     debug_data(
         config_path,
         config_overrides=overrides,
@@ -170,29 +199,164 @@ def debug_data(
         show=verbose,
     )
     if len(nlp.vocab.vectors):
-        msg.info(
-            f"{len(nlp.vocab.vectors)} vectors ({nlp.vocab.vectors.n_keys} "
-            f"unique keys, {nlp.vocab.vectors_length} dimensions)"
-        )
-        n_missing_vectors = sum(gold_train_data["words_missing_vectors"].values())
-        msg.warn(
-            "{} words in training data without vectors ({:.0f}%)".format(
-                n_missing_vectors,
-                100 * (n_missing_vectors / gold_train_data["n_words"]),
-            ),
-        )
-        msg.text(
-            "10 most common words without vectors: {}".format(
-                _format_labels(
-                    gold_train_data["words_missing_vectors"].most_common(10),
-                    counts=True,
-                )
-            ),
-            show=verbose,
-        )
+        if nlp.vocab.vectors.mode == VectorsMode.floret:
+            msg.info(
+                f"floret vectors with {len(nlp.vocab.vectors)} vectors, "
+                f"{nlp.vocab.vectors_length} dimensions, "
+                f"{nlp.vocab.vectors.minn}-{nlp.vocab.vectors.maxn} char "
+                f"n-gram subwords"
+            )
+        else:
+            msg.info(
+                f"{len(nlp.vocab.vectors)} vectors ({nlp.vocab.vectors.n_keys} "
+                f"unique keys, {nlp.vocab.vectors_length} dimensions)"
+            )
+            n_missing_vectors = sum(gold_train_data["words_missing_vectors"].values())
+            msg.warn(
+                "{} words in training data without vectors ({:.0f}%)".format(
+                    n_missing_vectors,
+                    100 * (n_missing_vectors / gold_train_data["n_words"]),
+                ),
+            )
+            msg.text(
+                "10 most common words without vectors: {}".format(
+                    _format_labels(
+                        gold_train_data["words_missing_vectors"].most_common(10),
+                        counts=True,
+                    )
+                ),
+                show=verbose,
+            )
     else:
         msg.info("No word vectors present in the package")
 
+    if "spancat" in factory_names or "spancat_singlelabel" in factory_names:
+        model_labels_spancat = _get_labels_from_spancat(nlp)
+        has_low_data_warning = False
+        has_no_neg_warning = False
+
+        msg.divider("Span Categorization")
+        msg.table(model_labels_spancat, header=["Spans Key", "Labels"], divider=True)
+
+        msg.text("Label counts in train data: ", show=verbose)
+        for spans_key, data_labels in gold_train_data["spancat"].items():
+            msg.text(
+                f"Key: {spans_key}, {_format_labels(data_labels.items(), counts=True)}",
+                show=verbose,
+            )
+        # Data checks: only take the spans keys in the actual spancat components
+        data_labels_in_component = {
+            spans_key: gold_train_data["spancat"][spans_key]
+            for spans_key in model_labels_spancat.keys()
+        }
+        for spans_key, data_labels in data_labels_in_component.items():
+            for label, count in data_labels.items():
+                # Check for missing labels
+                spans_key_in_model = spans_key in model_labels_spancat.keys()
+                if (spans_key_in_model) and (
+                    label not in model_labels_spancat[spans_key]
+                ):
+                    msg.warn(
+                        f"Label '{label}' is not present in the model labels of key '{spans_key}'. "
+                        "Performance may degrade after training."
+                    )
+                # Check for low number of examples per label
+                if count <= NEW_LABEL_THRESHOLD:
+                    msg.warn(
+                        f"Low number of examples for label '{label}' in key '{spans_key}' ({count})"
+                    )
+                    has_low_data_warning = True
+                # Check for negative examples
+                with msg.loading("Analyzing label distribution..."):
+                    neg_docs = _get_examples_without_label(
+                        train_dataset, label, "spancat", spans_key
+                    )
+                if neg_docs == 0:
+                    msg.warn(f"No examples for texts WITHOUT new label '{label}'")
+                    has_no_neg_warning = True
+
+            with msg.loading("Obtaining span characteristics..."):
+                span_characteristics = _get_span_characteristics(
+                    train_dataset, gold_train_data, spans_key
+                )
+
+            msg.info(f"Span characteristics for spans_key '{spans_key}'")
+            msg.info("SD = Span Distinctiveness, BD = Boundary Distinctiveness")
+            _print_span_characteristics(span_characteristics)
+
+            _span_freqs = _get_spans_length_freq_dist(
+                gold_train_data["spans_length"][spans_key]
+            )
+            _filtered_span_freqs = _filter_spans_length_freq_dist(
+                _span_freqs, threshold=SPAN_LENGTH_THRESHOLD_PERCENTAGE
+            )
+
+            msg.info(
+                f"Over {SPAN_LENGTH_THRESHOLD_PERCENTAGE}% of spans have lengths of 1 -- "
+                f"{max(_filtered_span_freqs.keys())} "
+                f"(min={span_characteristics['min_length']}, max={span_characteristics['max_length']}). "
+                f"The most common span lengths are: {_format_freqs(_filtered_span_freqs)}. "
+                "If you are using the n-gram suggester, note that omitting "
+                "infrequent n-gram lengths can greatly improve speed and "
+                "memory usage."
+            )
+
+            msg.text(
+                f"Full distribution of span lengths: {_format_freqs(_span_freqs)}",
+                show=verbose,
+            )
+
+            # Add report regarding span characteristics
+            if span_characteristics["avg_sd"] < SPAN_DISTINCT_THRESHOLD:
+                msg.warn("Spans may not be distinct from the rest of the corpus")
+            else:
+                msg.good("Spans are distinct from the rest of the corpus")
+
+            p_spans = span_characteristics["p_spans"].values()
+            all_span_tokens: Counter = sum(p_spans, Counter())
+            most_common_spans = [w for w, _ in all_span_tokens.most_common(10)]
+            msg.text(
+                "10 most common span tokens: {}".format(
+                    _format_labels(most_common_spans)
+                ),
+                show=verbose,
+            )
+
+            # Add report regarding span boundary characteristics
+            if span_characteristics["avg_bd"] < BOUNDARY_DISTINCT_THRESHOLD:
+                msg.warn("Boundary tokens are not distinct from the rest of the corpus")
+            else:
+                msg.good("Boundary tokens are distinct from the rest of the corpus")
+
+            p_bounds = span_characteristics["p_bounds"].values()
+            all_span_bound_tokens: Counter = sum(p_bounds, Counter())
+            most_common_bounds = [w for w, _ in all_span_bound_tokens.most_common(10)]
+            msg.text(
+                "10 most common span boundary tokens: {}".format(
+                    _format_labels(most_common_bounds)
+                ),
+                show=verbose,
+            )
+
+        if has_low_data_warning:
+            msg.text(
+                f"To train a new span type, your data should include at "
+                f"least {NEW_LABEL_THRESHOLD} instances of the new label",
+                show=verbose,
+            )
+        else:
+            msg.good("Good amount of examples for all labels")
+
+        if has_no_neg_warning:
+            msg.text(
+                "Training data should always include examples of spans "
+                "in context, as well as examples without a given span "
+                "type.",
+                show=verbose,
+            )
+        else:
+            msg.good("Examples without occurrences available for all labels")
+
     if "ner" in factory_names:
         # Get all unique NER labels present in the data
         labels = set(
@@ -203,6 +367,7 @@ def debug_data(
         has_low_data_warning = False
         has_no_neg_warning = False
         has_ws_ents_error = False
+        has_boundary_cross_ents_warning = False
 
         msg.divider("Named Entity Recognition")
         msg.info(f"{len(model_labels)} label(s)")
@@ -217,7 +382,7 @@ def debug_data(
             if label != "-"
         ]
         labels_with_counts = _format_labels(labels_with_counts, counts=True)
-        msg.text(f"Labels in train data: {_format_labels(labels)}", show=verbose)
+        msg.text(f"Labels in train data: {labels_with_counts}", show=verbose)
         missing_labels = model_labels - labels
         if missing_labels:
             msg.warn(
@@ -237,17 +402,25 @@ def debug_data(
                 has_low_data_warning = True
 
                 with msg.loading("Analyzing label distribution..."):
-                    neg_docs = _get_examples_without_label(train_dataset, label)
+                    neg_docs = _get_examples_without_label(train_dataset, label, "ner")
                 if neg_docs == 0:
                     msg.warn(f"No examples for texts WITHOUT new label '{label}'")
                     has_no_neg_warning = True
 
+        if gold_train_data["boundary_cross_ents"]:
+            msg.warn(
+                f"{gold_train_data['boundary_cross_ents']} entity span(s) crossing sentence boundaries"
+            )
+            has_boundary_cross_ents_warning = True
+
         if not has_low_data_warning:
             msg.good("Good amount of examples for all labels")
         if not has_no_neg_warning:
             msg.good("Examples without occurrences available for all labels")
         if not has_ws_ents_error:
             msg.good("No entities consisting of or starting/ending with whitespace")
+        if not has_boundary_cross_ents_warning:
+            msg.good("No entities crossing sentence boundaries")
 
         if has_low_data_warning:
             msg.text(
@@ -367,9 +540,13 @@ def debug_data(
 
     if "tagger" in factory_names:
         msg.divider("Part-of-speech Tagging")
-        label_list = [label for label in gold_train_data["tags"]]
-        model_labels = _get_labels_from_model(nlp, "tagger")
+        label_list, counts = zip(*gold_train_data["tags"].items())
         msg.info(f"{len(label_list)} label(s) in train data")
+        p = numpy.array(counts)
+        p = p / p.sum()
+        norm_entropy = (-p * numpy.log2(p)).sum() / numpy.log2(len(label_list))
+        msg.info(f"{norm_entropy} is the normalised label entropy")
+        model_labels = _get_labels_from_model(nlp, "tagger")
         labels = set(label_list)
         missing_labels = model_labels - labels
         if missing_labels:
@@ -518,6 +695,59 @@ def debug_data(
                 f"Found {gold_train_data['n_cycles']} projectivized train sentence(s) with cycles"
             )
 
+    if "trainable_lemmatizer" in factory_names:
+        msg.divider("Trainable Lemmatizer")
+        trees_train: Set[str] = gold_train_data["lemmatizer_trees"]
+        trees_dev: Set[str] = gold_dev_data["lemmatizer_trees"]
+        # This is necessary context when someone is attempting to interpret whether the
+        # number of trees exclusively in the dev set is meaningful.
+        msg.info(f"{len(trees_train)} lemmatizer trees generated from training data")
+        msg.info(f"{len(trees_dev)} lemmatizer trees generated from dev data")
+        dev_not_train = trees_dev - trees_train
+
+        if len(dev_not_train) != 0:
+            pct = len(dev_not_train) / len(trees_dev)
+            msg.info(
+                f"{len(dev_not_train)} lemmatizer trees ({pct*100:.1f}% of dev trees)"
+                " were found exclusively in the dev data."
+            )
+        else:
+            # Would we ever expect this case? It seems like it would be pretty rare,
+            # and we might actually want a warning?
+            msg.info("All trees in dev data present in training data.")
+
+        if gold_train_data["n_low_cardinality_lemmas"] > 0:
+            n = gold_train_data["n_low_cardinality_lemmas"]
+            msg.warn(f"{n} training docs with 0 or 1 unique lemmas.")
+
+        if gold_dev_data["n_low_cardinality_lemmas"] > 0:
+            n = gold_dev_data["n_low_cardinality_lemmas"]
+            msg.warn(f"{n} dev docs with 0 or 1 unique lemmas.")
+
+        if gold_train_data["no_lemma_annotations"] > 0:
+            n = gold_train_data["no_lemma_annotations"]
+            msg.warn(f"{n} training docs with no lemma annotations.")
+        else:
+            msg.good("All training docs have lemma annotations.")
+
+        if gold_dev_data["no_lemma_annotations"] > 0:
+            n = gold_dev_data["no_lemma_annotations"]
+            msg.warn(f"{n} dev docs with no lemma annotations.")
+        else:
+            msg.good("All dev docs have lemma annotations.")
+
+        if gold_train_data["partial_lemma_annotations"] > 0:
+            n = gold_train_data["partial_lemma_annotations"]
+            msg.info(f"{n} training docs with partial lemma annotations.")
+        else:
+            msg.good("All training docs have complete lemma annotations.")
+
+        if gold_dev_data["partial_lemma_annotations"] > 0:
+            n = gold_dev_data["partial_lemma_annotations"]
+            msg.info(f"{n} dev docs with partial lemma annotations.")
+        else:
+            msg.good("All dev docs have complete lemma annotations.")
+
     msg.divider("Summary")
     good_counts = msg.counts[MESSAGES.GOOD]
     warn_counts = msg.counts[MESSAGES.WARN]
@@ -564,7 +794,12 @@ def _compile_gold(
         "deps": Counter(),
         "words": Counter(),
         "roots": Counter(),
+        "spancat": dict(),
+        "spans_length": dict(),
+        "spans_per_type": dict(),
+        "sb_per_type": dict(),
         "ws_ents": 0,
+        "boundary_cross_ents": 0,
         "n_words": 0,
         "n_misaligned_words": 0,
         "words_missing_vectors": Counter(),
@@ -574,7 +809,13 @@ def _compile_gold(
         "n_cats_multilabel": 0,
         "n_cats_bad_values": 0,
         "texts": set(),
+        "lemmatizer_trees": set(),
+        "no_lemma_annotations": 0,
+        "partial_lemma_annotations": 0,
+        "n_low_cardinality_lemmas": 0,
     }
+    if "trainable_lemmatizer" in factory_names:
+        trees = EditTrees(nlp.vocab.strings)
     for eg in examples:
         gold = eg.reference
         doc = eg.predicted
@@ -593,6 +834,7 @@ def _compile_gold(
                 if nlp.vocab.strings[word] not in nlp.vocab.vectors:
                     data["words_missing_vectors"].update([word])
         if "ner" in factory_names:
+            sent_starts = eg.get_aligned_sent_starts()
             for i, label in enumerate(eg.get_aligned_ner()):
                 if label is None:
                     continue
@@ -600,10 +842,66 @@ def _compile_gold(
                     # "Illegal" whitespace entity
                     data["ws_ents"] += 1
                 if label.startswith(("B-", "U-")):
-                    combined_label = label.split("-")[1]
+                    combined_label = remove_bilu_prefix(label)
                     data["ner"][combined_label] += 1
+                if sent_starts[i] and label.startswith(("I-", "L-")):
+                    data["boundary_cross_ents"] += 1
                 elif label == "-":
                     data["ner"]["-"] += 1
+        if "spancat" in factory_names or "spancat_singlelabel" in factory_names:
+            for spans_key in list(eg.reference.spans.keys()):
+                # Obtain the span frequency
+                if spans_key not in data["spancat"]:
+                    data["spancat"][spans_key] = Counter()
+                for i, span in enumerate(eg.reference.spans[spans_key]):
+                    if span.label_ is None:
+                        continue
+                    else:
+                        data["spancat"][spans_key][span.label_] += 1
+
+                # Obtain the span length
+                if spans_key not in data["spans_length"]:
+                    data["spans_length"][spans_key] = dict()
+                for span in gold.spans[spans_key]:
+                    if span.label_ is None:
+                        continue
+                    if span.label_ not in data["spans_length"][spans_key]:
+                        data["spans_length"][spans_key][span.label_] = []
+                    data["spans_length"][spans_key][span.label_].append(len(span))
+
+                # Obtain spans per span type
+                if spans_key not in data["spans_per_type"]:
+                    data["spans_per_type"][spans_key] = dict()
+                for span in gold.spans[spans_key]:
+                    if span.label_ not in data["spans_per_type"][spans_key]:
+                        data["spans_per_type"][spans_key][span.label_] = []
+                    data["spans_per_type"][spans_key][span.label_].append(span)
+
+                # Obtain boundary tokens per span type
+                window_size = 1
+                if spans_key not in data["sb_per_type"]:
+                    data["sb_per_type"][spans_key] = dict()
+                for span in gold.spans[spans_key]:
+                    if span.label_ not in data["sb_per_type"][spans_key]:
+                        # Creating a data structure that holds the start and
+                        # end tokens for each span type
+                        data["sb_per_type"][spans_key][span.label_] = {
+                            "start": [],
+                            "end": [],
+                        }
+                    for offset in range(window_size):
+                        sb_start_idx = span.start - (offset + 1)
+                        if sb_start_idx >= 0:
+                            data["sb_per_type"][spans_key][span.label_]["start"].append(
+                                gold[sb_start_idx : sb_start_idx + 1]
+                            )
+
+                        sb_end_idx = span.end + (offset + 1)
+                        if sb_end_idx <= len(gold):
+                            data["sb_per_type"][spans_key][span.label_]["end"].append(
+                                gold[sb_end_idx - 1 : sb_end_idx]
+                            )
+
         if "textcat" in factory_names or "textcat_multilabel" in factory_names:
             data["cats"].update(gold.cats)
             if any(val not in (0, 1) for val in gold.cats.values()):
@@ -647,6 +945,25 @@ def _compile_gold(
                 data["n_nonproj"] += 1
             if nonproj.contains_cycle(aligned_heads):
                 data["n_cycles"] += 1
+        if "trainable_lemmatizer" in factory_names:
+            # from EditTreeLemmatizer._labels_from_data
+            if all(token.lemma == 0 for token in gold):
+                data["no_lemma_annotations"] += 1
+                continue
+            if any(token.lemma == 0 for token in gold):
+                data["partial_lemma_annotations"] += 1
+            lemma_set = set()
+            for token in gold:
+                if token.lemma != 0:
+                    lemma_set.add(token.lemma)
+                    tree_id = trees.add(token.text, token.lemma_)
+                    tree_str = trees.tree_to_str(tree_id)
+                    data["lemmatizer_trees"].add(tree_str)
+            # We want to identify cases where lemmas aren't assigned
+            # or are all assigned the same value, as this would indicate
+            # an issue since we're expecting a large set of lemmas
+            if len(lemma_set) < 2 and len(gold) > 1:
+                data["n_low_cardinality_lemmas"] += 1
     return data
 
 
@@ -674,21 +991,242 @@ def _format_labels(
     return ", ".join([f"'{l}'" for l in cast(Iterable[str], labels)])
 
 
-def _get_examples_without_label(data: Sequence[Example], label: str) -> int:
+def _format_freqs(freqs: Dict[int, float], sort: bool = True) -> str:
+    if sort:
+        freqs = dict(sorted(freqs.items()))
+
+    _freqs = [(str(k), v) for k, v in freqs.items()]
+    return ", ".join(
+        [f"{l} ({c}%)" for l, c in cast(Iterable[Tuple[str, float]], _freqs)]
+    )
+
+
+def _get_examples_without_label(
+    data: Sequence[Example],
+    label: str,
+    component: Literal["ner", "spancat"] = "ner",
+    spans_key: Optional[str] = "sc",
+) -> int:
     count = 0
     for eg in data:
-        labels = [
-            label.split("-")[1]
-            for label in eg.get_aligned_ner()
-            if label not in ("O", "-", None)
-        ]
+        if component == "ner":
+            labels = [
+                remove_bilu_prefix(label)
+                for label in eg.get_aligned_ner()
+                if label not in ("O", "-", None)
+            ]
+
+        if component == "spancat":
+            labels = (
+                [span.label_ for span in eg.reference.spans[spans_key]]
+                if spans_key in eg.reference.spans
+                else []
+            )
+
         if label not in labels:
             count += 1
     return count
 
 
-def _get_labels_from_model(nlp: Language, pipe_name: str) -> Set[str]:
-    if pipe_name not in nlp.pipe_names:
-        return set()
-    pipe = nlp.get_pipe(pipe_name)
-    return set(pipe.labels)
+def _get_labels_from_model(nlp: Language, factory_name: str) -> Set[str]:
+    pipe_names = [
+        pipe_name
+        for pipe_name in nlp.pipe_names
+        if nlp.get_pipe_meta(pipe_name).factory == factory_name
+    ]
+    labels: Set[str] = set()
+    for pipe_name in pipe_names:
+        pipe = nlp.get_pipe(pipe_name)
+        assert isinstance(pipe, TrainablePipe)
+        labels.update(pipe.labels)
+    return labels
+
+
+def _get_labels_from_spancat(nlp: Language) -> Dict[str, Set[str]]:
+    pipe_names = [
+        pipe_name
+        for pipe_name in nlp.pipe_names
+        if nlp.get_pipe_meta(pipe_name).factory in ("spancat", "spancat_singlelabel")
+    ]
+    labels: Dict[str, Set[str]] = {}
+    for pipe_name in pipe_names:
+        pipe = nlp.get_pipe(pipe_name)
+        assert isinstance(pipe, SpanCategorizer)
+        if pipe.key not in labels:
+            labels[pipe.key] = set()
+        labels[pipe.key].update(pipe.labels)
+    return labels
+
+
+def _gmean(l: List) -> float:
+    """Compute geometric mean of a list"""
+    return math.exp(math.fsum(math.log(i) for i in l) / len(l))
+
+
+def _wgt_average(metric: Dict[str, float], frequencies: Counter) -> float:
+    total = sum(value * frequencies[span_type] for span_type, value in metric.items())
+    return total / sum(frequencies.values())
+
+
+def _get_distribution(docs, normalize: bool = True) -> Counter:
+    """Get the frequency distribution given a set of Docs"""
+    word_counts: Counter = Counter()
+    for doc in docs:
+        for token in doc:
+            # Normalize the text
+            t = token.text.lower().replace("``", '"').replace("''", '"')
+            word_counts[t] += 1
+    if normalize:
+        total = sum(word_counts.values(), 0.0)
+        word_counts = Counter({k: v / total for k, v in word_counts.items()})
+    return word_counts
+
+
+def _get_kl_divergence(p: Counter, q: Counter) -> float:
+    """Compute the Kullback-Leibler divergence from two frequency distributions"""
+    total = 0.0
+    for word, p_word in p.items():
+        total += p_word * math.log(p_word / q[word])
+    return total
+
+
+def _format_span_row(span_data: List[Dict], labels: List[str]) -> List[Any]:
+    """Compile into one list for easier reporting"""
+    d = {
+        label: [label] + list(_format_number(d[label]) for d in span_data)
+        for label in labels
+    }
+    return list(d.values())
+
+
+def _get_span_characteristics(
+    examples: List[Example], compiled_gold: Dict[str, Any], spans_key: str
+) -> Dict[str, Any]:
+    """Obtain all span characteristics"""
+    data_labels = compiled_gold["spancat"][spans_key]
+    # Get lengths
+    span_length = {
+        label: _gmean(l)
+        for label, l in compiled_gold["spans_length"][spans_key].items()
+    }
+    spans_per_type = {
+        label: len(spans)
+        for label, spans in compiled_gold["spans_per_type"][spans_key].items()
+    }
+    min_lengths = [min(l) for l in compiled_gold["spans_length"][spans_key].values()]
+    max_lengths = [max(l) for l in compiled_gold["spans_length"][spans_key].values()]
+
+    # Get relevant distributions: corpus, spans, span boundaries
+    p_corpus = _get_distribution([eg.reference for eg in examples], normalize=True)
+    p_spans = {
+        label: _get_distribution(spans, normalize=True)
+        for label, spans in compiled_gold["spans_per_type"][spans_key].items()
+    }
+    p_bounds = {
+        label: _get_distribution(sb["start"] + sb["end"], normalize=True)
+        for label, sb in compiled_gold["sb_per_type"][spans_key].items()
+    }
+
+    # Compute for actual span characteristics
+    span_distinctiveness = {
+        label: _get_kl_divergence(freq_dist, p_corpus)
+        for label, freq_dist in p_spans.items()
+    }
+    sb_distinctiveness = {
+        label: _get_kl_divergence(freq_dist, p_corpus)
+        for label, freq_dist in p_bounds.items()
+    }
+
+    return {
+        "sd": span_distinctiveness,
+        "bd": sb_distinctiveness,
+        "spans_per_type": spans_per_type,
+        "lengths": span_length,
+        "min_length": min(min_lengths),
+        "max_length": max(max_lengths),
+        "avg_sd": _wgt_average(span_distinctiveness, data_labels),
+        "avg_bd": _wgt_average(sb_distinctiveness, data_labels),
+        "avg_length": _wgt_average(span_length, data_labels),
+        "labels": list(data_labels.keys()),
+        "p_spans": p_spans,
+        "p_bounds": p_bounds,
+    }
+
+
+def _print_span_characteristics(span_characteristics: Dict[str, Any]):
+    """Print all span characteristics into a table"""
+    headers = ("Span Type", "Length", "SD", "BD", "N")
+    # Wasabi has this at 30 by default, but we might have some long labels
+    max_col = max(30, max(len(label) for label in span_characteristics["labels"]))
+    # Prepare table data with all span characteristics
+    table_data = [
+        span_characteristics["lengths"],
+        span_characteristics["sd"],
+        span_characteristics["bd"],
+        span_characteristics["spans_per_type"],
+    ]
+    table = _format_span_row(
+        span_data=table_data, labels=span_characteristics["labels"]
+    )
+    # Prepare table footer with weighted averages
+    footer_data = [
+        span_characteristics["avg_length"],
+        span_characteristics["avg_sd"],
+        span_characteristics["avg_bd"],
+    ]
+
+    footer = (
+        ["Wgt. Average"] + ["{:.2f}".format(round(f, 2)) for f in footer_data] + ["-"]
+    )
+    msg.table(
+        table,
+        footer=footer,
+        header=headers,
+        divider=True,
+        aligns=["l"] + ["r"] * (len(footer_data) + 1),
+        max_col=max_col,
+    )
+
+
+def _get_spans_length_freq_dist(
+    length_dict: Dict, threshold=SPAN_LENGTH_THRESHOLD_PERCENTAGE
+) -> Dict[int, float]:
+    """Get frequency distribution of spans length under a certain threshold"""
+    all_span_lengths = []
+    for _, lengths in length_dict.items():
+        all_span_lengths.extend(lengths)
+
+    freq_dist: Counter = Counter()
+    for i in all_span_lengths:
+        if freq_dist.get(i):
+            freq_dist[i] += 1
+        else:
+            freq_dist[i] = 1
+
+    # We will be working with percentages instead of raw counts
+    freq_dist_percentage = {}
+    for span_length, count in freq_dist.most_common():
+        percentage = (count / len(all_span_lengths)) * 100.0
+        percentage = round(percentage, 2)
+        freq_dist_percentage[span_length] = percentage
+
+    return freq_dist_percentage
+
+
+def _filter_spans_length_freq_dist(
+    freq_dist: Dict[int, float], threshold: int
+) -> Dict[int, float]:
+    """Filter frequency distribution with respect to a threshold
+
+    We're going to filter all the span lengths that fall
+    around a percentage threshold when summed.
+    """
+    total = 0.0
+    filtered_freq_dist = {}
+    for span_length, dist in freq_dist.items():
+        if total >= threshold:
+            break
+        else:
+            filtered_freq_dist[span_length] = dist
+        total += dist
+    return filtered_freq_dist

spacy/cli/debug_diff.py

@@ -0,0 +1,89 @@
+from pathlib import Path
+from typing import Optional
+
+import typer
+from thinc.api import Config
+from wasabi import MarkdownRenderer, Printer, diff_strings
+
+from ..util import load_config
+from ._util import Arg, Opt, debug_cli, parse_config_overrides, show_validation_error
+from .init_config import Optimizations, init_config
+
+
+@debug_cli.command(
+    "diff-config",
+    context_settings={"allow_extra_args": True, "ignore_unknown_options": True},
+)
+def debug_diff_cli(
+    # fmt: off
+    ctx: typer.Context,
+    config_path: Path = Arg(..., help="Path to config file", exists=True, allow_dash=True),
+    compare_to: Optional[Path] = Opt(None, help="Path to a config file to diff against, or `None` to compare against default settings", exists=True, allow_dash=True),
+    optimize: Optimizations = Opt(Optimizations.efficiency.value, "--optimize", "-o", help="Whether the user config was optimized for efficiency or accuracy. Only relevant when comparing against the default config."),
+    gpu: bool = Opt(False, "--gpu", "-G", help="Whether the original config can run on a GPU. Only relevant when comparing against the default config."),
+    pretraining: bool = Opt(False, "--pretraining", "--pt", help="Whether to compare on a config with pretraining involved. Only relevant when comparing against the default config."),
+    markdown: bool = Opt(False, "--markdown", "-md", help="Generate Markdown for GitHub issues")
+    # fmt: on
+):
+    """Show a diff of a config file with respect to spaCy's defaults or another config file. If
+    additional settings were used in the creation of the config file, then you
+    must supply these as extra parameters to the command when comparing to the default settings. The generated diff
+    can also be used when posting to the discussion forum to provide more
+    information for the maintainers.
+
+    The `optimize`, `gpu`, and `pretraining` options are only relevant when
+    comparing against the default configuration (or specifically when `compare_to` is None).
+
+    DOCS: https://spacy.io/api/cli#debug-diff
+    """
+    debug_diff(
+        config_path=config_path,
+        compare_to=compare_to,
+        gpu=gpu,
+        optimize=optimize,
+        pretraining=pretraining,
+        markdown=markdown,
+    )
+
+
+def debug_diff(
+    config_path: Path,
+    compare_to: Optional[Path],
+    gpu: bool,
+    optimize: Optimizations,
+    pretraining: bool,
+    markdown: bool,
+):
+    msg = Printer()
+    with show_validation_error(hint_fill=False):
+        user_config = load_config(config_path)
+        if compare_to:
+            other_config = load_config(compare_to)
+        else:
+            # Recreate a default config based from user's config
+            lang = user_config["nlp"]["lang"]
+            pipeline = list(user_config["nlp"]["pipeline"])
+            msg.info(f"Found user-defined language: '{lang}'")
+            msg.info(f"Found user-defined pipelines: {pipeline}")
+            other_config = init_config(
+                lang=lang,
+                pipeline=pipeline,
+                optimize=optimize.value,
+                gpu=gpu,
+                pretraining=pretraining,
+                silent=True,
+            )
+
+    user = user_config.to_str()
+    other = other_config.to_str()
+
+    if user == other:
+        msg.warn("No diff to show: configs are identical")
+    else:
+        diff_text = diff_strings(other, user, add_symbols=markdown)
+        if markdown:
+            md = MarkdownRenderer()
+            md.add(md.code_block(diff_text, "diff"))
+            print(md.text)
+        else:
+            print(diff_text)

spacy/cli/debug_model.py

@@ -1,19 +1,32 @@
-from typing import Dict, Any, Optional
-from pathlib import Path
 import itertools
+from pathlib import Path
+from typing import Any, Dict, Optional
+
+import typer
+from thinc.api import (
+    Model,
+    data_validation,
+    fix_random_seed,
+    set_dropout_rate,
+    set_gpu_allocator,
+)
+from wasabi import msg
 
 from spacy.training import Example
 from spacy.util import resolve_dot_names
-from wasabi import msg
-from thinc.api import fix_random_seed, set_dropout_rate
-from thinc.api import Model, data_validation, set_gpu_allocator
-import typer
 
-from ._util import Arg, Opt, debug_cli, show_validation_error
-from ._util import parse_config_overrides, string_to_list, setup_gpu
+from .. import util
 from ..schemas import ConfigSchemaTraining
 from ..util import registry
-from .. import util
+from ._util import (
+    Arg,
+    Opt,
+    debug_cli,
+    parse_config_overrides,
+    setup_gpu,
+    show_validation_error,
+    string_to_list,
+)
 
 
 @debug_cli.command(

spacy/cli/download.py

@@ -1,13 +1,20 @@
-from typing import Optional, Sequence
-import requests
 import sys
-from wasabi import msg
-import typer
+from typing import Optional, Sequence
+
+import requests
+import typer
+from wasabi import msg
 
-from ._util import app, Arg, Opt, WHEEL_SUFFIX, SDIST_SUFFIX
 from .. import about
-from ..util import is_package, get_minor_version, run_command
-from ..errors import OLD_MODEL_SHORTCUTS
+from ..util import (
+    get_installed_models,
+    get_minor_version,
+    get_package_version,
+    is_package,
+    is_prerelease_version,
+    run_command,
+)
+from ._util import SDIST_SUFFIX, WHEEL_SUFFIX, Arg, Opt, app
 
 
 @app.command(
@@ -19,7 +26,7 @@ def download_cli(
     ctx: typer.Context,
     model: str = Arg(..., help="Name of pipeline package to download"),
     direct: bool = Opt(False, "--direct", "-d", "-D", help="Force direct download of name + version"),
-    sdist: bool = Opt(False, "--sdist", "-S", help="Download sdist (.tar.gz) archive instead of pre-built binary wheel")
+    sdist: bool = Opt(False, "--sdist", "-S", help="Download sdist (.tar.gz) archive instead of pre-built binary wheel"),
     # fmt: on
 ):
     """
@@ -35,7 +42,12 @@ def download_cli(
     download(model, direct, sdist, *ctx.args)
 
 
-def download(model: str, direct: bool = False, sdist: bool = False, *pip_args) -> None:
+def download(
+    model: str,
+    direct: bool = False,
+    sdist: bool = False,
+    *pip_args,
+) -> None:
     if (
         not (is_package("spacy") or is_package("spacy-nightly"))
         and "--no-deps" not in pip_args
@@ -49,32 +61,44 @@ def download(model: str, direct: bool = False, sdist: bool = False, *pip_args) -
             "dependencies, you'll have to install them manually."
         )
         pip_args = pip_args + ("--no-deps",)
-    suffix = SDIST_SUFFIX if sdist else WHEEL_SUFFIX
-    dl_tpl = "{m}-{v}/{m}-{v}{s}#egg={m}=={v}"
     if direct:
         components = model.split("-")
         model_name = "".join(components[:-1])
         version = components[-1]
-        download_model(dl_tpl.format(m=model_name, v=version, s=suffix), pip_args)
     else:
         model_name = model
-        if model in OLD_MODEL_SHORTCUTS:
-            msg.warn(
-                f"As of spaCy v3.0, shortcuts like '{model}' are deprecated. Please "
-                f"use the full pipeline package name '{OLD_MODEL_SHORTCUTS[model]}' instead."
-            )
-            model_name = OLD_MODEL_SHORTCUTS[model]
         compatibility = get_compatibility()
         version = get_version(model_name, compatibility)
-        download_model(dl_tpl.format(m=model_name, v=version, s=suffix), pip_args)
+
+    # If we already have this version installed, skip downloading
+    installed = get_installed_models()
+    if model_name in installed:
+        installed_version = get_package_version(model_name)
+        if installed_version == version:
+            msg.warn(f"{model_name} v{version} already installed, skipping")
+            return
+
+    filename = get_model_filename(model_name, version, sdist)
+
+    download_model(filename, pip_args)
     msg.good(
         "Download and installation successful",
         f"You can now load the package via spacy.load('{model_name}')",
     )
 
 
+def get_model_filename(model_name: str, version: str, sdist: bool = False) -> str:
+    dl_tpl = "{m}-{v}/{m}-{v}{s}"
+    suffix = SDIST_SUFFIX if sdist else WHEEL_SUFFIX
+    filename = dl_tpl.format(m=model_name, v=version, s=suffix)
+    return filename
+
+
 def get_compatibility() -> dict:
-    version = get_minor_version(about.__version__)
+    if is_prerelease_version(about.__version__):
+        version: Optional[str] = about.__version__
+    else:
+        version = get_minor_version(about.__version__)
     r = requests.get(about.__compatibility__)
     if r.status_code != 200:
         msg.fail(
@@ -101,6 +125,11 @@ def get_version(model: str, comp: dict) -> str:
     return comp[model][0]
 
 
+def get_latest_version(model: str) -> str:
+    comp = get_compatibility()
+    return get_version(model, comp)
+
+
 def download_model(
     filename: str, user_pip_args: Optional[Sequence[str]] = None
 ) -> None:

spacy/cli/evaluate.py

@@ -1,29 +1,33 @@
-from typing import Optional, List, Dict, Any, Union
-from wasabi import Printer
-from pathlib import Path
 import re
+from pathlib import Path
+from typing import Any, Dict, List, Optional, Union
+
 import srsly
 from thinc.api import fix_random_seed
+from wasabi import Printer
 
-from ..training import Corpus
-from ..tokens import Doc
-from ._util import app, Arg, Opt, setup_gpu, import_code
+from .. import displacy, util
 from ..scorer import Scorer
-from .. import util
-from .. import displacy
+from ..tokens import Doc
+from ..training import Corpus
+from ._util import Arg, Opt, app, benchmark_cli, import_code_paths, setup_gpu
 
 
+@benchmark_cli.command(
+    "accuracy",
+)
 @app.command("evaluate")
 def evaluate_cli(
     # fmt: off
     model: str = Arg(..., help="Model name or path"),
     data_path: Path = Arg(..., help="Location of binary evaluation data in .spacy format", exists=True),
     output: Optional[Path] = Opt(None, "--output", "-o", help="Output JSON file for metrics", dir_okay=False),
-    code_path: Optional[Path] = Opt(None, "--code", "-c", help="Path to Python file with additional code (registered functions) to be imported"),
+    code_path: str = Opt("", "--code", "-c", help="Comma-separated paths to Python files with additional code (registered functions) to be imported"),
     use_gpu: int = Opt(-1, "--gpu-id", "-g", help="GPU ID or -1 for CPU"),
     gold_preproc: bool = Opt(False, "--gold-preproc", "-G", help="Use gold preprocessing"),
     displacy_path: Optional[Path] = Opt(None, "--displacy-path", "-dp", help="Directory to output rendered parses as HTML", exists=True, file_okay=False),
     displacy_limit: int = Opt(25, "--displacy-limit", "-dl", help="Limit of parses to render as HTML"),
+    per_component: bool = Opt(False, "--per-component", "-P", help="Return scores per component, only applicable when an output JSON file is specified."),
     # fmt: on
 ):
     """
@@ -36,9 +40,9 @@ def evaluate_cli(
     dependency parses in a HTML file, set as output directory as the
     displacy_path argument.
 
-    DOCS: https://spacy.io/api/cli#evaluate
+    DOCS: https://spacy.io/api/cli#benchmark-accuracy
     """
-    import_code(code_path)
+    import_code_paths(code_path)
     evaluate(
         model,
         data_path,
@@ -47,6 +51,7 @@ def evaluate_cli(
         gold_preproc=gold_preproc,
         displacy_path=displacy_path,
         displacy_limit=displacy_limit,
+        per_component=per_component,
         silent=False,
     )
 
@@ -61,6 +66,7 @@ def evaluate(
     displacy_limit: int = 25,
     silent: bool = True,
     spans_key: str = "sc",
+    per_component: bool = False,
 ) -> Dict[str, Any]:
     msg = Printer(no_print=silent, pretty=not silent)
     fix_random_seed()
@@ -75,50 +81,61 @@ def evaluate(
     corpus = Corpus(data_path, gold_preproc=gold_preproc)
     nlp = util.load_model(model)
     dev_dataset = list(corpus(nlp))
-    scores = nlp.evaluate(dev_dataset)
-    metrics = {
-        "TOK": "token_acc",
-        "TAG": "tag_acc",
-        "POS": "pos_acc",
-        "MORPH": "morph_acc",
-        "LEMMA": "lemma_acc",
-        "UAS": "dep_uas",
-        "LAS": "dep_las",
-        "NER P": "ents_p",
-        "NER R": "ents_r",
-        "NER F": "ents_f",
-        "TEXTCAT": "cats_score",
-        "SENT P": "sents_p",
-        "SENT R": "sents_r",
-        "SENT F": "sents_f",
-        "SPAN P": f"spans_{spans_key}_p",
-        "SPAN R": f"spans_{spans_key}_r",
-        "SPAN F": f"spans_{spans_key}_f",
-        "SPEED": "speed",
-    }
-    results = {}
-    data = {}
-    for metric, key in metrics.items():
-        if key in scores:
-            if key == "cats_score":
-                metric = metric + " (" + scores.get("cats_score_desc", "unk") + ")"
-            if isinstance(scores[key], (int, float)):
-                if key == "speed":
-                    results[metric] = f"{scores[key]:.0f}"
+    scores = nlp.evaluate(dev_dataset, per_component=per_component)
+    if per_component:
+        data = scores
+        if output is None:
+            msg.warn(
+                "The per-component option is enabled but there is no output JSON file provided to save the scores to."
+            )
+        else:
+            msg.info("Per-component scores will be saved to output JSON file.")
+    else:
+        metrics = {
+            "TOK": "token_acc",
+            "TAG": "tag_acc",
+            "POS": "pos_acc",
+            "MORPH": "morph_acc",
+            "LEMMA": "lemma_acc",
+            "UAS": "dep_uas",
+            "LAS": "dep_las",
+            "NER P": "ents_p",
+            "NER R": "ents_r",
+            "NER F": "ents_f",
+            "TEXTCAT": "cats_score",
+            "SENT P": "sents_p",
+            "SENT R": "sents_r",
+            "SENT F": "sents_f",
+            "SPAN P": f"spans_{spans_key}_p",
+            "SPAN R": f"spans_{spans_key}_r",
+            "SPAN F": f"spans_{spans_key}_f",
+            "SPEED": "speed",
+        }
+        results = {}
+        data = {}
+        for metric, key in metrics.items():
+            if key in scores:
+                if key == "cats_score":
+                    metric = metric + " (" + scores.get("cats_score_desc", "unk") + ")"
+                if isinstance(scores[key], (int, float)):
+                    if key == "speed":
+                        results[metric] = f"{scores[key]:.0f}"
+                    else:
+                        results[metric] = f"{scores[key]*100:.2f}"
                 else:
-                    results[metric] = f"{scores[key]*100:.2f}"
-            else:
-                results[metric] = "-"
-            data[re.sub(r"[\s/]", "_", key.lower())] = scores[key]
+                    results[metric] = "-"
+                data[re.sub(r"[\s/]", "_", key.lower())] = scores[key]
 
-    msg.table(results, title="Results")
-    data = handle_scores_per_type(scores, data, spans_key=spans_key, silent=silent)
+        msg.table(results, title="Results")
+        data = handle_scores_per_type(scores, data, spans_key=spans_key, silent=silent)
 
     if displacy_path:
         factory_names = [nlp.get_pipe_meta(pipe).factory for pipe in nlp.pipe_names]
         docs = list(nlp.pipe(ex.reference.text for ex in dev_dataset[:displacy_limit]))
         render_deps = "parser" in factory_names
         render_ents = "ner" in factory_names
+        render_spans = "spancat" in factory_names
+
         render_parses(
             docs,
             displacy_path,
@@ -126,6 +143,7 @@ def evaluate(
             limit=displacy_limit,
             deps=render_deps,
             ents=render_ents,
+            spans=render_spans,
         )
         msg.good(f"Generated {displacy_limit} parses as HTML", displacy_path)
 
@@ -179,6 +197,7 @@ def render_parses(
     limit: int = 250,
     deps: bool = True,
     ents: bool = True,
+    spans: bool = True,
 ):
     docs[0].user_data["title"] = model_name
     if ents:
@@ -192,6 +211,11 @@ def render_parses(
         with (output_path / "parses.html").open("w", encoding="utf8") as file_:
             file_.write(html)
 
+    if spans:
+        html = displacy.render(docs[:limit], style="span", page=True)
+        with (output_path / "spans.html").open("w", encoding="utf8") as file_:
+            file_.write(html)
+
 
 def print_prf_per_type(
     msg: Printer, scores: Dict[str, Dict[str, float]], name: str, type: str

spacy/cli/find_threshold.py

@@ -0,0 +1,233 @@
+import functools
+import logging
+import operator
+from pathlib import Path
+from typing import Any, Dict, List, Optional, Tuple
+
+import numpy
+import wasabi.tables
+
+from .. import util
+from ..errors import Errors
+from ..pipeline import MultiLabel_TextCategorizer, TextCategorizer
+from ..training import Corpus
+from ._util import Arg, Opt, app, import_code, setup_gpu
+
+_DEFAULTS = {
+    "n_trials": 11,
+    "use_gpu": -1,
+    "gold_preproc": False,
+}
+
+
+@app.command(
+    "find-threshold",
+    context_settings={"allow_extra_args": False, "ignore_unknown_options": True},
+)
+def find_threshold_cli(
+    # fmt: off
+    model: str = Arg(..., help="Model name or path"),
+    data_path: Path = Arg(..., help="Location of binary evaluation data in .spacy format", exists=True),
+    pipe_name: str = Arg(..., help="Name of pipe to examine thresholds for"),
+    threshold_key: str = Arg(..., help="Key of threshold attribute in component's configuration"),
+    scores_key: str = Arg(..., help="Metric to optimize"),
+    n_trials: int = Opt(_DEFAULTS["n_trials"], "--n_trials", "-n", help="Number of trials to determine optimal thresholds"),
+    code_path: Optional[Path] = Opt(None, "--code", "-c", help="Path to Python file with additional code (registered functions) to be imported"),
+    use_gpu: int = Opt(_DEFAULTS["use_gpu"], "--gpu-id", "-g", help="GPU ID or -1 for CPU"),
+    gold_preproc: bool = Opt(_DEFAULTS["gold_preproc"], "--gold-preproc", "-G", help="Use gold preprocessing"),
+    verbose: bool = Opt(False, "--verbose", "-V", "-VV", help="Display more information for debugging purposes"),
+    # fmt: on
+):
+    """
+    Runs prediction trials for a trained model with varying tresholds to maximize
+    the specified metric. The search space for the threshold is traversed linearly
+    from 0 to 1 in `n_trials` steps. Results are displayed in a table on `stdout`
+    (the corresponding API call to `spacy.cli.find_threshold.find_threshold()`
+    returns all results).
+
+    This is applicable only for components whose predictions are influenced by
+    thresholds - e.g. `textcat_multilabel` and `spancat`, but not `textcat`. Note
+    that the full path to the corresponding threshold attribute in the config has to
+    be provided.
+
+    DOCS: https://spacy.io/api/cli#find-threshold
+    """
+
+    util.logger.setLevel(logging.DEBUG if verbose else logging.INFO)
+    import_code(code_path)
+    find_threshold(
+        model=model,
+        data_path=data_path,
+        pipe_name=pipe_name,
+        threshold_key=threshold_key,
+        scores_key=scores_key,
+        n_trials=n_trials,
+        use_gpu=use_gpu,
+        gold_preproc=gold_preproc,
+        silent=False,
+    )
+
+
+def find_threshold(
+    model: str,
+    data_path: Path,
+    pipe_name: str,
+    threshold_key: str,
+    scores_key: str,
+    *,
+    n_trials: int = _DEFAULTS["n_trials"],  # type: ignore
+    use_gpu: int = _DEFAULTS["use_gpu"],  # type: ignore
+    gold_preproc: bool = _DEFAULTS["gold_preproc"],  # type: ignore
+    silent: bool = True,
+) -> Tuple[float, float, Dict[float, float]]:
+    """
+    Runs prediction trials for models with varying tresholds to maximize the specified metric.
+    model (Union[str, Path]): Pipeline to evaluate. Can be a package or a path to a data directory.
+    data_path (Path): Path to file with DocBin with docs to use for threshold search.
+    pipe_name (str): Name of pipe to examine thresholds for.
+    threshold_key (str): Key of threshold attribute in component's configuration.
+    scores_key (str): Name of score to metric to optimize.
+    n_trials (int): Number of trials to determine optimal thresholds.
+    use_gpu (int): GPU ID or -1 for CPU.
+    gold_preproc (bool): Whether to use gold preprocessing. Gold preprocessing helps the annotations align to the
+        tokenization, and may result in sequences of more consistent length. However, it may reduce runtime accuracy due
+        to train/test skew.
+    silent (bool): Whether to print non-error-related output to stdout.
+    RETURNS (Tuple[float, float, Dict[float, float]]): Best found threshold, the corresponding score, scores for all
+        evaluated thresholds.
+    """
+
+    setup_gpu(use_gpu, silent=silent)
+    data_path = util.ensure_path(data_path)
+    if not data_path.exists():
+        wasabi.msg.fail("Evaluation data not found", data_path, exits=1)
+    nlp = util.load_model(model)
+
+    if pipe_name not in nlp.component_names:
+        raise AttributeError(
+            Errors.E001.format(name=pipe_name, opts=nlp.component_names)
+        )
+    pipe = nlp.get_pipe(pipe_name)
+    if not hasattr(pipe, "scorer"):
+        raise AttributeError(Errors.E1045)
+
+    if type(pipe) == TextCategorizer:
+        wasabi.msg.warn(
+            "The `textcat` component doesn't use a threshold as it's not applicable to the concept of "
+            "exclusive classes. All thresholds will yield the same results."
+        )
+
+    if not silent:
+        wasabi.msg.info(
+            title=f"Optimizing for {scores_key} for component '{pipe_name}' with {n_trials} "
+            f"trials."
+        )
+
+    # Load evaluation corpus.
+    corpus = Corpus(data_path, gold_preproc=gold_preproc)
+    dev_dataset = list(corpus(nlp))
+    config_keys = threshold_key.split(".")
+
+    def set_nested_item(
+        config: Dict[str, Any], keys: List[str], value: float
+    ) -> Dict[str, Any]:
+        """Set item in nested dictionary. Adapted from https://stackoverflow.com/a/54138200.
+        config (Dict[str, Any]): Configuration dictionary.
+        keys (List[Any]): Path to value to set.
+        value (float): Value to set.
+        RETURNS (Dict[str, Any]): Updated dictionary.
+        """
+        functools.reduce(operator.getitem, keys[:-1], config)[keys[-1]] = value
+        return config
+
+    def filter_config(
+        config: Dict[str, Any], keys: List[str], full_key: str
+    ) -> Dict[str, Any]:
+        """Filters provided config dictionary so that only the specified keys path remains.
+        config (Dict[str, Any]): Configuration dictionary.
+        keys (List[Any]): Path to value to set.
+        full_key (str): Full user-specified key.
+        RETURNS (Dict[str, Any]): Filtered dictionary.
+        """
+        if keys[0] not in config:
+            wasabi.msg.fail(
+                title=f"Failed to look up `{full_key}` in config: sub-key {[keys[0]]} not found.",
+                text=f"Make sure you specified {[keys[0]]} correctly. The following sub-keys are available instead: "
+                f"{list(config.keys())}",
+                exits=1,
+            )
+        return {
+            keys[0]: filter_config(config[keys[0]], keys[1:], full_key)
+            if len(keys) > 1
+            else config[keys[0]]
+        }
+
+    # Evaluate with varying threshold values.
+    scores: Dict[float, float] = {}
+    config_keys_full = ["components", pipe_name, *config_keys]
+    table_col_widths = (10, 10)
+    thresholds = numpy.linspace(0, 1, n_trials)
+    print(wasabi.tables.row(["Threshold", f"{scores_key}"], widths=table_col_widths))
+    for threshold in thresholds:
+        # Reload pipeline with overrides specifying the new threshold.
+        nlp = util.load_model(
+            model,
+            config=set_nested_item(
+                filter_config(
+                    nlp.config, config_keys_full, ".".join(config_keys_full)
+                ).copy(),
+                config_keys_full,
+                threshold,
+            ),
+        )
+        if hasattr(pipe, "cfg"):
+            setattr(
+                nlp.get_pipe(pipe_name),
+                "cfg",
+                set_nested_item(getattr(pipe, "cfg"), config_keys, threshold),
+            )
+
+        eval_scores = nlp.evaluate(dev_dataset)
+        if scores_key not in eval_scores:
+            wasabi.msg.fail(
+                title=f"Failed to look up score `{scores_key}` in evaluation results.",
+                text=f"Make sure you specified the correct value for `scores_key`. The following scores are "
+                f"available: {list(eval_scores.keys())}",
+                exits=1,
+            )
+        scores[threshold] = eval_scores[scores_key]
+
+        if not isinstance(scores[threshold], (float, int)):
+            wasabi.msg.fail(
+                f"Returned score for key '{scores_key}' is not numeric. Threshold optimization only works for numeric "
+                f"scores.",
+                exits=1,
+            )
+        print(
+            wasabi.row(
+                [round(threshold, 3), round(scores[threshold], 3)],
+                widths=table_col_widths,
+            )
+        )
+
+    best_threshold = max(scores.keys(), key=(lambda key: scores[key]))
+
+    # If all scores are identical, emit warning.
+    if len(set(scores.values())) == 1:
+        wasabi.msg.warn(
+            title="All scores are identical. Verify that all settings are correct.",
+            text=""
+            if (
+                not isinstance(pipe, MultiLabel_TextCategorizer)
+                or scores_key in ("cats_macro_f", "cats_micro_f")
+            )
+            else "Use `cats_macro_f` or `cats_micro_f` when optimizing the threshold for `textcat_multilabel`.",
+        )
+
+    else:
+        if not silent:
+            print(
+                f"\nBest threshold: {round(best_threshold, ndigits=4)} with {scores_key} value of {scores[best_threshold]}."
+            )
+
+    return best_threshold, scores[best_threshold], scores

spacy/cli/info.py

@@ -1,12 +1,15 @@
-from typing import Optional, Dict, Any, Union, List
+import importlib.metadata
+import json
 import platform
 from pathlib import Path
-from wasabi import Printer, MarkdownRenderer
-import srsly
+from typing import Any, Dict, List, Optional, Union
 
-from ._util import app, Arg, Opt, string_to_list
-from .. import util
-from .. import about
+import srsly
+from wasabi import MarkdownRenderer, Printer
+
+from .. import about, util
+from ._util import Arg, Opt, app, string_to_list
+from .download import get_latest_version, get_model_filename
 
 
 @app.command("info")
@@ -16,6 +19,7 @@ def info_cli(
     markdown: bool = Opt(False, "--markdown", "-md", help="Generate Markdown for GitHub issues"),
     silent: bool = Opt(False, "--silent", "-s", "-S", help="Don't print anything (just return)"),
     exclude: str = Opt("labels", "--exclude", "-e", help="Comma-separated keys to exclude from the print-out"),
+    url: bool = Opt(False, "--url", "-u", help="Print the URL to download the most recent compatible version of the pipeline"),
     # fmt: on
 ):
     """
@@ -23,10 +27,19 @@ def info_cli(
     print its meta information. Flag --markdown prints details in Markdown for easy
     copy-pasting to GitHub issues.
 
+    Flag --url prints only the download URL of the most recent compatible
+    version of the pipeline.
+
     DOCS: https://spacy.io/api/cli#info
     """
     exclude = string_to_list(exclude)
-    info(model, markdown=markdown, silent=silent, exclude=exclude)
+    info(
+        model,
+        markdown=markdown,
+        silent=silent,
+        exclude=exclude,
+        url=url,
+    )
 
 
 def info(
@@ -35,11 +48,20 @@ def info(
     markdown: bool = False,
     silent: bool = True,
     exclude: Optional[List[str]] = None,
+    url: bool = False,
 ) -> Union[str, dict]:
     msg = Printer(no_print=silent, pretty=not silent)
     if not exclude:
         exclude = []
-    if model:
+    if url:
+        if model is not None:
+            title = f"Download info for pipeline '{model}'"
+            data = info_model_url(model)
+            print(data["download_url"])
+            return data
+        else:
+            msg.fail("--url option requires a pipeline name", exits=1)
+    elif model:
         title = f"Info about pipeline '{model}'"
         data = info_model(model, silent=silent)
     else:
@@ -99,11 +121,43 @@ def info_model(model: str, *, silent: bool = True) -> Dict[str, Any]:
         meta["source"] = str(model_path.resolve())
     else:
         meta["source"] = str(model_path)
+    download_url = info_installed_model_url(model)
+    if download_url:
+        meta["download_url"] = download_url
     return {
         k: v for k, v in meta.items() if k not in ("accuracy", "performance", "speed")
     }
 
 
+def info_installed_model_url(model: str) -> Optional[str]:
+    """Given a pipeline name, get the download URL if available, otherwise
+    return None.
+
+    This is only available for pipelines installed as modules that have
+    dist-info available.
+    """
+    try:
+        dist = importlib.metadata.distribution(model)
+        text = dist.read_text("direct_url.json")
+        if isinstance(text, str):
+            data = json.loads(text)
+            return data["url"]
+    except Exception:
+        pass
+    return None
+
+
+def info_model_url(model: str) -> Dict[str, Any]:
+    """Return the download URL for the latest version of a pipeline."""
+    version = get_latest_version(model)
+
+    filename = get_model_filename(model, version)
+    download_url = about.__download_url__ + "/" + filename
+    release_tpl = "https://github.com/explosion/spacy-models/releases/tag/{m}-{v}"
+    release_url = release_tpl.format(m=model, v=version)
+    return {"download_url": download_url, "release_url": release_url}
+
+
 def get_markdown(
     data: Dict[str, Any],
     title: Optional[str] = None,

spacy/cli/init_config.py

@@ -1,18 +1,27 @@
-from typing import Optional, List, Tuple
+import re
 from enum import Enum
 from pathlib import Path
-from wasabi import Printer, diff_strings
-from thinc.api import Config
+from typing import List, Optional, Tuple
+
 import srsly
-import re
 from jinja2 import Template
+from thinc.api import Config
+from wasabi import Printer, diff_strings
 
 from .. import util
-from ..language import DEFAULT_CONFIG_PRETRAIN_PATH
+from ..language import DEFAULT_CONFIG_DISTILL_PATH, DEFAULT_CONFIG_PRETRAIN_PATH
 from ..schemas import RecommendationSchema
-from ._util import init_cli, Arg, Opt, show_validation_error, COMMAND
-from ._util import string_to_list, import_code
-
+from ..util import SimpleFrozenList
+from ._util import (
+    COMMAND,
+    Arg,
+    Opt,
+    _handle_renamed_language_codes,
+    import_code,
+    init_cli,
+    show_validation_error,
+    string_to_list,
+)
 
 ROOT = Path(__file__).parent / "templates"
 TEMPLATE_PATH = ROOT / "quickstart_training.jinja"
@@ -24,16 +33,30 @@ class Optimizations(str, Enum):
     accuracy = "accuracy"
 
 
+class InitValues:
+    """
+    Default values for initialization. Dedicated class to allow synchronized default values for init_config_cli() and
+    init_config(), i.e. initialization calls via CLI respectively Python.
+    """
+
+    lang = "en"
+    pipeline = SimpleFrozenList(["tagger", "parser", "ner"])
+    optimize = Optimizations.efficiency
+    gpu = False
+    pretraining = False
+    force_overwrite = False
+
+
 @init_cli.command("config")
 def init_config_cli(
     # fmt: off
     output_file: Path = Arg(..., help="File to save the config to or - for stdout (will only output config and no additional logging info)", allow_dash=True),
-    lang: str = Opt("en", "--lang", "-l", help="Two-letter code of the language to use"),
-    pipeline: str = Opt("tagger,parser,ner", "--pipeline", "-p", help="Comma-separated names of trainable pipeline components to include (without 'tok2vec' or 'transformer')"),
-    optimize: Optimizations = Opt(Optimizations.efficiency.value, "--optimize", "-o", help="Whether to optimize for efficiency (faster inference, smaller model, lower memory consumption) or higher accuracy (potentially larger and slower model). This will impact the choice of architecture, pretrained weights and related hyperparameters."),
-    gpu: bool = Opt(False, "--gpu", "-G", help="Whether the model can run on GPU. This will impact the choice of architecture, pretrained weights and related hyperparameters."),
-    pretraining: bool = Opt(False, "--pretraining", "-pt", help="Include config for pretraining (with 'spacy pretrain')"),
-    force_overwrite: bool = Opt(False, "--force", "-F", help="Force overwriting the output file"),
+    lang: str = Opt(InitValues.lang, "--lang", "-l", help="Code of the language to use"),
+    pipeline: str = Opt(",".join(InitValues.pipeline), "--pipeline", "-p", help="Comma-separated names of trainable pipeline components to include (without 'tok2vec' or 'transformer')"),
+    optimize: Optimizations = Opt(InitValues.optimize, "--optimize", "-o", help="Whether to optimize for efficiency (faster inference, smaller model, lower memory consumption) or higher accuracy (potentially larger and slower model). This will impact the choice of architecture, pretrained weights and related hyperparameters."),
+    gpu: bool = Opt(InitValues.gpu, "--gpu", "-G", help="Whether the model can run on GPU. This will impact the choice of architecture, pretrained weights and related hyperparameters."),
+    pretraining: bool = Opt(InitValues.pretraining, "--pretraining", "-pt", help="Include config for pretraining (with 'spacy pretrain')"),
+    force_overwrite: bool = Opt(InitValues.force_overwrite, "--force", "-F", help="Force overwriting the output file"),
     # fmt: on
 ):
     """
@@ -68,6 +91,7 @@ def init_fill_config_cli(
     # fmt: off
     base_path: Path = Arg(..., help="Path to base config to fill", exists=True, dir_okay=False),
     output_file: Path = Arg("-", help="Path to output .cfg file (or - for stdout)", allow_dash=True),
+    distillation: bool = Opt(False, "--distillation", "-dt", help="Include config for distillation (with 'spacy distill')"),
     pretraining: bool = Opt(False, "--pretraining", "-pt", help="Include config for pretraining (with 'spacy pretrain')"),
     diff: bool = Opt(False, "--diff", "-D", help="Print a visual diff highlighting the changes"),
     code_path: Optional[Path] = Opt(None, "--code-path", "--code", "-c", help="Path to Python file with additional code (registered functions) to be imported"),
@@ -83,13 +107,20 @@ def init_fill_config_cli(
     DOCS: https://spacy.io/api/cli#init-fill-config
     """
     import_code(code_path)
-    fill_config(output_file, base_path, pretraining=pretraining, diff=diff)
+    fill_config(
+        output_file,
+        base_path,
+        distillation=distillation,
+        pretraining=pretraining,
+        diff=diff,
+    )
 
 
 def fill_config(
     output_file: Path,
     base_path: Path,
     *,
+    distillation: bool = False,
     pretraining: bool = False,
     diff: bool = False,
     silent: bool = False,
@@ -108,6 +139,9 @@ def fill_config(
     # replaced with their actual config after loading, so we have to re-add them
     sourced = util.get_sourced_components(config)
     filled["components"].update(sourced)
+    if distillation:
+        distillation_config = util.load_config(DEFAULT_CONFIG_DISTILL_PATH)
+        filled = distillation_config.merge(filled)
     if pretraining:
         validate_config_for_pretrain(filled, msg)
         pretrain_config = util.load_config(DEFAULT_CONFIG_PRETRAIN_PATH)
@@ -133,16 +167,20 @@ def fill_config(
 
 def init_config(
     *,
-    lang: str,
-    pipeline: List[str],
-    optimize: str,
-    gpu: bool,
-    pretraining: bool = False,
+    lang: str = InitValues.lang,
+    pipeline: List[str] = InitValues.pipeline,
+    optimize: str = InitValues.optimize,
+    gpu: bool = InitValues.gpu,
+    pretraining: bool = InitValues.pretraining,
     silent: bool = True,
 ) -> Config:
     msg = Printer(no_print=silent)
     with TEMPLATE_PATH.open("r") as f:
         template = Template(f.read())
+
+    # Throw error for renamed language codes in v4
+    _handle_renamed_language_codes(lang)
+
     # Filter out duplicates since tok2vec and transformer are added by template
     pipeline = [pipe for pipe in pipeline if pipe not in ("tok2vec", "transformer")]
     defaults = RECOMMENDATIONS["__default__"]

spacy/cli/init_pipeline.py

@@ -1,15 +1,24 @@
-from typing import Optional
 import logging
 from pathlib import Path
-from wasabi import msg
-import typer
+from typing import Optional
+
 import srsly
+import typer
+from wasabi import msg
 
 from .. import util
-from ..training.initialize import init_nlp, convert_vectors
 from ..language import Language
-from ._util import init_cli, Arg, Opt, parse_config_overrides, show_validation_error
-from ._util import import_code, setup_gpu
+from ..training.initialize import convert_vectors, init_nlp
+from ._util import (
+    Arg,
+    Opt,
+    _handle_renamed_language_codes,
+    import_code,
+    init_cli,
+    parse_config_overrides,
+    setup_gpu,
+    show_validation_error,
+)
 
 
 @init_cli.command("vectors")
@@ -21,9 +30,9 @@ def init_vectors_cli(
     prune: int = Opt(-1, "--prune", "-p", help="Optional number of vectors to prune to"),
     truncate: int = Opt(0, "--truncate", "-t", help="Optional number of vectors to truncate to when reading in vectors file"),
     mode: str = Opt("default", "--mode", "-m", help="Vectors mode: default or floret"),
-    name: Optional[str] = Opt(None, "--name", "-n", help="Optional name for the word vectors, e.g. en_core_web_lg.vectors"),
     verbose: bool = Opt(False, "--verbose", "-V", "-VV", help="Display more information for debugging purposes"),
     jsonl_loc: Optional[Path] = Opt(None, "--lexemes-jsonl", "-j", help="Location of JSONL-formatted attributes file", hidden=True),
+    attr: str = Opt("ORTH", "--attr", "-a", help="Optional token attribute to use for vectors, e.g. LOWER or NORM"),
     # fmt: on
 ):
     """Convert word vectors for use with spaCy. Will export an nlp object that
@@ -31,6 +40,10 @@ def init_vectors_cli(
     a model with vectors.
     """
     util.logger.setLevel(logging.DEBUG if verbose else logging.INFO)
+
+    # Throw error for renamed language codes in v4
+    _handle_renamed_language_codes(lang)
+
     msg.info(f"Creating blank nlp object for language '{lang}'")
     nlp = util.get_lang_class(lang)()
     if jsonl_loc is not None:
@@ -40,8 +53,8 @@ def init_vectors_cli(
         vectors_loc,
         truncate=truncate,
         prune=prune,
-        name=name,
         mode=mode,
+        attr=attr,
     )
     msg.good(f"Successfully converted {len(nlp.vocab.vectors)} vectors")
     nlp.to_disk(output_dir)

spacy/cli/package.py

@@ -1,17 +1,18 @@
-from typing import Optional, Union, Any, Dict, List, Tuple, cast
+import re
 import shutil
-from pathlib import Path
-from wasabi import Printer, MarkdownRenderer, get_raw_input
-from thinc.api import Config
-from collections import defaultdict
-from catalogue import RegistryError
-import srsly
 import sys
+from collections import defaultdict
+from pathlib import Path
+from typing import Any, Dict, List, Optional, Tuple, Union, cast
 
-from ._util import app, Arg, Opt, string_to_list, WHEEL_SUFFIX, SDIST_SUFFIX
-from ..schemas import validate, ModelMetaSchema
-from .. import util
-from .. import about
+import srsly
+from catalogue import RegistryError
+from thinc.api import Config
+from wasabi import MarkdownRenderer, Printer, get_raw_input
+
+from .. import about, util
+from ..schemas import ModelMetaSchema, validate
+from ._util import SDIST_SUFFIX, WHEEL_SUFFIX, Arg, Opt, app, string_to_list
 
 
 @app.command("package")
@@ -19,7 +20,7 @@ def package_cli(
     # fmt: off
     input_dir: Path = Arg(..., help="Directory with pipeline data", exists=True, file_okay=False),
     output_dir: Path = Arg(..., help="Output parent directory", exists=True, file_okay=False),
-    code_paths: str = Opt("", "--code", "-c", help="Comma-separated paths to Python file with additional code (registered functions) to be included in the package"),
+    code_paths: str = Opt("", "--code", "-c", help="Comma-separated paths to Python files with additional code (registered functions) to be included in the package"),
     meta_path: Optional[Path] = Opt(None, "--meta-path", "--meta", "-m", help="Path to meta.json", exists=True, dir_okay=False),
     create_meta: bool = Opt(False, "--create-meta", "-C", help="Create meta.json, even if one exists"),
     name: Optional[str] = Opt(None, "--name", "-n", help="Package name to override meta"),
@@ -109,6 +110,24 @@ def package(
             ", ".join(meta["requirements"]),
         )
     if name is not None:
+        if not name.isidentifier():
+            msg.fail(
+                f"Model name ('{name}') is not a valid module name. "
+                "This is required so it can be imported as a module.",
+                "We recommend names that use ASCII A-Z, a-z, _ (underscore), "
+                "and 0-9. "
+                "For specific details see: https://docs.python.org/3/reference/lexical_analysis.html#identifiers",
+                exits=1,
+            )
+        if not _is_permitted_package_name(name):
+            msg.fail(
+                f"Model name ('{name}') is not a permitted package name. "
+                "This is required to correctly load the model with spacy.load.",
+                "We recommend names that use ASCII A-Z, a-z, _ (underscore), "
+                "and 0-9. "
+                "For specific details see: https://www.python.org/dev/peps/pep-0426/#name",
+                exits=1,
+            )
         meta["name"] = name
     if version is not None:
         meta["version"] = version
@@ -162,7 +181,7 @@ def package(
         imports="\n".join(f"from . import {m}" for m in imports)
     )
     create_file(package_path / "__init__.py", init_py)
-    msg.good(f"Successfully created package '{model_name_v}'", main_path)
+    msg.good(f"Successfully created package directory '{model_name_v}'", main_path)
     if create_sdist:
         with util.working_dir(main_path):
             util.run_command([sys.executable, "setup.py", "sdist"], capture=False)
@@ -171,8 +190,14 @@ def package(
     if create_wheel:
         with util.working_dir(main_path):
             util.run_command([sys.executable, "setup.py", "bdist_wheel"], capture=False)
-        wheel = main_path / "dist" / f"{model_name_v}{WHEEL_SUFFIX}"
+        wheel_name_squashed = re.sub("_+", "_", model_name_v)
+        wheel = main_path / "dist" / f"{wheel_name_squashed}{WHEEL_SUFFIX}"
         msg.good(f"Successfully created binary wheel", wheel)
+    if "__" in model_name:
+        msg.warn(
+            f"Model name ('{model_name}') contains a run of underscores. "
+            "Runs of underscores are not significant in installed package names.",
+        )
 
 
 def has_wheel() -> bool:
@@ -227,7 +252,7 @@ def get_third_party_dependencies(
                     raise regerr from None
             module_name = func_info.get("module")  # type: ignore[attr-defined]
             if module_name:  # the code is part of a module, not a --code file
-                modules.add(func_info["module"].split(".")[0])  # type: ignore[index]
+                modules.add(func_info["module"].split(".")[0])  # type: ignore[union-attr]
     dependencies = []
     for module_name in modules:
         if module_name in distributions:
@@ -274,8 +299,8 @@ def get_meta(
     }
     nlp = util.load_model_from_path(Path(model_path))
     meta.update(nlp.meta)
-    meta.update(existing_meta)
     meta["spacy_version"] = util.get_minor_version_range(about.__version__)
+    meta.update(existing_meta)
     meta["vectors"] = {
         "width": nlp.vocab.vectors_length,
         "vectors": len(nlp.vocab.vectors),
@@ -422,6 +447,14 @@ def _format_label_scheme(data: Dict[str, Any]) -> str:
     return md.text
 
 
+def _is_permitted_package_name(package_name: str) -> bool:
+    # regex from: https://www.python.org/dev/peps/pep-0426/#name
+    permitted_match = re.search(
+        r"^([A-Z0-9]|[A-Z0-9][A-Z0-9._-]*[A-Z0-9])$", package_name, re.IGNORECASE
+    )
+    return permitted_match is not None
+
+
 TEMPLATE_SETUP = """
 #!/usr/bin/env python
 import io

spacy/cli/pretrain.py

@@ -1,13 +1,21 @@
-from typing import Optional
-from pathlib import Path
-from wasabi import msg
-import typer
 import re
+from pathlib import Path
+from typing import Optional
+
+import typer
+from wasabi import msg
 
-from ._util import app, Arg, Opt, parse_config_overrides, show_validation_error
-from ._util import import_code, setup_gpu
 from ..training.pretrain import pretrain
 from ..util import load_config
+from ._util import (
+    Arg,
+    Opt,
+    app,
+    import_code_paths,
+    parse_config_overrides,
+    setup_gpu,
+    show_validation_error,
+)
 
 
 @app.command(
@@ -19,10 +27,11 @@ def pretrain_cli(
     ctx: typer.Context,  # This is only used to read additional arguments
     config_path: Path = Arg(..., help="Path to config file", exists=True, dir_okay=False, allow_dash=True),
     output_dir: Path = Arg(..., help="Directory to write weights to on each epoch"),
-    code_path: Optional[Path] = Opt(None, "--code", "-c", help="Path to Python file with additional code (registered functions) to be imported"),
+    code_path: str = Opt("", "--code", "-c", help="Comma-separated paths to Python files with additional code (registered functions) to be imported"),
     resume_path: Optional[Path] = Opt(None, "--resume-path", "-r", help="Path to pretrained weights from which to resume pretraining"),
     epoch_resume: Optional[int] = Opt(None, "--epoch-resume", "-er", help="The epoch to resume counting from when using --resume-path. Prevents unintended overwriting of existing weight files."),
     use_gpu: int = Opt(-1, "--gpu-id", "-g", help="GPU ID or -1 for CPU"),
+    skip_last: bool = Opt(False, "--skip-last", "-L", help="Skip saving model-last.bin"),
     # fmt: on
 ):
     """
@@ -47,7 +56,7 @@ def pretrain_cli(
     DOCS: https://spacy.io/api/cli#pretrain
     """
     config_overrides = parse_config_overrides(ctx.args)
-    import_code(code_path)
+    import_code_paths(code_path)
     verify_cli_args(config_path, output_dir, resume_path, epoch_resume)
     setup_gpu(use_gpu)
     msg.info(f"Loading config from: {config_path}")
@@ -61,7 +70,7 @@ 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")
@@ -74,6 +83,7 @@ def pretrain_cli(
         epoch_resume=epoch_resume,
         use_gpu=use_gpu,
         silent=False,
+        skip_last=skip_last,
     )
     msg.good("Successfully finished pretrain")
 

spacy/cli/profile.py

@@ -1,17 +1,18 @@
-from typing import Optional, Sequence, Union, Iterator
-import tqdm
-from pathlib import Path
-import srsly
 import cProfile
+import itertools
 import pstats
 import sys
-import itertools
-from wasabi import msg, Printer
-import typer
+from pathlib import Path
+from typing import Iterator, Optional, Sequence, Union
+
+import srsly
+import tqdm
+import typer
+from wasabi import Printer, msg
 
-from ._util import app, debug_cli, Arg, Opt, NAME
 from ..language import Language
 from ..util import load_model
+from ._util import NAME, Arg, Opt, app, debug_cli
 
 
 @debug_cli.command("profile")

spacy/cli/project/assets.py

@@ -1,15 +1,30 @@
-from typing import Any, Dict, Optional
-from pathlib import Path
-from wasabi import msg
+import os
 import re
 import shutil
+from pathlib import Path
+from typing import Any, Dict, Optional
+
 import requests
 import typer
+from wasabi import msg
 
 from ...util import ensure_path, working_dir
-from .._util import project_cli, Arg, Opt, PROJECT_FILE, load_project_config
-from .._util import get_checksum, download_file, git_checkout, get_git_version
-from .._util import SimpleFrozenDict, parse_config_overrides
+from .._util import (
+    PROJECT_FILE,
+    Arg,
+    Opt,
+    SimpleFrozenDict,
+    download_file,
+    get_checksum,
+    get_git_version,
+    git_checkout,
+    load_project_config,
+    parse_config_overrides,
+    project_cli,
+)
+
+# Whether assets are extra if `extra` is not set.
+EXTRA_DEFAULT = False
 
 
 @project_cli.command(
@@ -20,7 +35,8 @@ def project_assets_cli(
     # fmt: off
     ctx: typer.Context,  # This is only used to read additional arguments
     project_dir: Path = Arg(Path.cwd(), help="Path to cloned project. Defaults to current working directory.", exists=True, file_okay=False),
-    sparse_checkout: bool = Opt(False, "--sparse", "-S", help="Use sparse checkout for assets provided via Git, to only check out and clone the files needed. Requires Git v22.2+.")
+    sparse_checkout: bool = Opt(False, "--sparse", "-S", help="Use sparse checkout for assets provided via Git, to only check out and clone the files needed. Requires Git v22.2+."),
+    extra: bool = Opt(False, "--extra", "-e", help="Download all assets, including those marked as 'extra'.")
     # fmt: on
 ):
     """Fetch project assets like datasets and pretrained weights. Assets are
@@ -31,7 +47,12 @@ def project_assets_cli(
     DOCS: https://spacy.io/api/cli#project-assets
     """
     overrides = parse_config_overrides(ctx.args)
-    project_assets(project_dir, overrides=overrides, sparse_checkout=sparse_checkout)
+    project_assets(
+        project_dir,
+        overrides=overrides,
+        sparse_checkout=sparse_checkout,
+        extra=extra,
+    )
 
 
 def project_assets(
@@ -39,17 +60,29 @@ def project_assets(
     *,
     overrides: Dict[str, Any] = SimpleFrozenDict(),
     sparse_checkout: bool = False,
+    extra: bool = False,
 ) -> None:
     """Fetch assets for a project using DVC if possible.
 
     project_dir (Path): Path to project directory.
+    sparse_checkout (bool): Use sparse checkout for assets provided via Git, to only check out and clone the files
+                            needed.
+    extra (bool): Whether to download all assets, including those marked as 'extra'.
     """
     project_path = ensure_path(project_dir)
     config = load_project_config(project_path, overrides=overrides)
-    assets = config.get("assets", {})
+    assets = [
+        asset
+        for asset in config.get("assets", [])
+        if extra or not asset.get("extra", EXTRA_DEFAULT)
+    ]
     if not assets:
-        msg.warn(f"No assets specified in {PROJECT_FILE}", exits=0)
+        msg.warn(
+            f"No assets specified in {PROJECT_FILE} (if assets are marked as extra, download them with --extra)",
+            exits=0,
+        )
     msg.info(f"Fetching {len(assets)} asset(s)")
+
     for asset in assets:
         dest = (project_dir / asset["dest"]).resolve()
         checksum = asset.get("checksum")
@@ -129,10 +162,17 @@ def fetch_asset(
         the asset failed.
     """
     dest_path = (project_path / dest).resolve()
-    if dest_path.exists() and checksum:
+    if dest_path.exists():
         # If there's already a file, check for checksum
-        if checksum == get_checksum(dest_path):
-            msg.good(f"Skipping download with matching checksum: {dest}")
+        if checksum:
+            if checksum == get_checksum(dest_path):
+                msg.good(f"Skipping download with matching checksum: {dest}")
+                return
+        else:
+            # If there's not a checksum, make sure the file is a possibly valid size
+            if os.path.getsize(dest_path) == 0:
+                msg.warn(f"Asset exists but with size of 0 bytes, deleting: {dest}")
+                os.remove(dest_path)
     # We might as well support the user here and create parent directories in
     # case the asset dir isn't listed as a dir to create in the project.yml
     if not dest_path.parent.exists():
@@ -160,7 +200,11 @@ def convert_asset_url(url: str) -> str:
     RETURNS (str): The converted URL.
     """
     # If the asset URL is a regular GitHub URL it's likely a mistake
-    if re.match(r"(http(s?)):\/\/github.com", url) and "releases/download" not in url:
+    if (
+        re.match(r"(http(s?)):\/\/github.com", url)
+        and "releases/download" not in url
+        and "/raw/" not in url
+    ):
         converted = url.replace("github.com", "raw.githubusercontent.com")
         converted = re.sub(r"/(tree|blob)/", "/", converted)
         msg.warn(

spacy/cli/project/clone.py

@@ -1,17 +1,26 @@
-from typing import Optional
-from pathlib import Path
-from wasabi import msg
-import subprocess
 import re
+import subprocess
+from pathlib import Path
+from typing import Optional
+
+from wasabi import msg
 
 from ... import about
 from ...util import ensure_path
-from .._util import project_cli, Arg, Opt, COMMAND, PROJECT_FILE
-from .._util import git_checkout, get_git_version
+from .._util import (
+    COMMAND,
+    PROJECT_FILE,
+    Arg,
+    Opt,
+    get_git_version,
+    git_checkout,
+    git_repo_branch_exists,
+    project_cli,
+)
 
 DEFAULT_REPO = about.__projects__
 DEFAULT_PROJECTS_BRANCH = about.__projects_branch__
-DEFAULT_BRANCH = "master"
+DEFAULT_BRANCHES = ["main", "master"]
 
 
 @project_cli.command("clone")
@@ -20,7 +29,7 @@ def project_clone_cli(
     name: str = Arg(..., help="The name of the template to clone"),
     dest: Optional[Path] = Arg(None, help="Where to clone the project. Defaults to current working directory", exists=False),
     repo: str = Opt(DEFAULT_REPO, "--repo", "-r", help="The repository to clone from"),
-    branch: Optional[str] = Opt(None, "--branch", "-b", help="The branch to clone from"),
+    branch: Optional[str] = Opt(None, "--branch", "-b", help=f"The branch to clone from. If not provided, will attempt {', '.join(DEFAULT_BRANCHES)}"),
     sparse_checkout: bool = Opt(False, "--sparse", "-S", help="Use sparse Git checkout to only check out and clone the files needed. Requires Git v22.2+.")
     # fmt: on
 ):
@@ -33,9 +42,25 @@ def project_clone_cli(
     """
     if dest is None:
         dest = Path.cwd() / Path(name).parts[-1]
+    if repo == DEFAULT_REPO and branch is None:
+        branch = DEFAULT_PROJECTS_BRANCH
+
     if branch is None:
-        # If it's a user repo, we want to default to other branch
-        branch = DEFAULT_PROJECTS_BRANCH if repo == DEFAULT_REPO else DEFAULT_BRANCH
+        for default_branch in DEFAULT_BRANCHES:
+            if git_repo_branch_exists(repo, default_branch):
+                branch = default_branch
+                break
+        if branch is None:
+            default_branches_msg = ", ".join(f"'{b}'" for b in DEFAULT_BRANCHES)
+            msg.fail(
+                "No branch provided and attempted default "
+                f"branches {default_branches_msg} do not exist.",
+                exits=1,
+            )
+    else:
+        if not git_repo_branch_exists(repo, branch):
+            msg.fail(f"repo: {repo} (branch: {branch}) does not exist.", exits=1)
+    assert isinstance(branch, str)
     project_clone(name, dest, repo=repo, branch=branch, sparse_checkout=sparse_checkout)
 
 
@@ -61,9 +86,9 @@ def project_clone(
     try:
         git_checkout(repo, name, dest, branch=branch, sparse=sparse_checkout)
     except subprocess.CalledProcessError:
-        err = f"Could not clone '{name}' from repo '{repo_name}'"
+        err = f"Could not clone '{name}' from repo '{repo_name}' (branch '{branch}')"
         msg.fail(err, exits=1)
-    msg.good(f"Cloned '{name}' from {repo_name}", project_dir)
+    msg.good(f"Cloned '{name}' from '{repo_name}' (branch '{branch}')", project_dir)
     if not (project_dir / PROJECT_FILE).exists():
         msg.warn(f"No {PROJECT_FILE} found in directory")
     else:

spacy/cli/project/document.py

@@ -1,9 +1,9 @@
 from pathlib import Path
-from wasabi import msg, MarkdownRenderer
+
+from wasabi import MarkdownRenderer, msg
 
 from ...util import working_dir
-from .._util import project_cli, Arg, Opt, PROJECT_FILE, load_project_config
-
+from .._util import PROJECT_FILE, Arg, Opt, load_project_config, project_cli
 
 DOCS_URL = "https://spacy.io"
 INTRO_PROJECT = f"""The [`{PROJECT_FILE}`]({PROJECT_FILE}) defines the data assets required by the

spacy/cli/project/dvc.py

@@ -1,15 +1,28 @@
 """This module contains helpers and subcommands for integrating spaCy projects
 with Data Version Controk (DVC). https://dvc.org"""
-from typing import Dict, Any, List, Optional, Iterable
 import subprocess
 from pathlib import Path
+from typing import Any, Dict, Iterable, List, Optional
+
 from wasabi import msg
 
-from .._util import PROJECT_FILE, load_project_config, get_hash, project_cli
-from .._util import Arg, Opt, NAME, COMMAND
-from ...util import working_dir, split_command, join_command, run_command
-from ...util import SimpleFrozenList
-
+from ...util import (
+    SimpleFrozenList,
+    join_command,
+    run_command,
+    split_command,
+    working_dir,
+)
+from .._util import (
+    COMMAND,
+    NAME,
+    PROJECT_FILE,
+    Arg,
+    Opt,
+    get_hash,
+    load_project_config,
+    project_cli,
+)
 
 DVC_CONFIG = "dvc.yaml"
 DVC_DIR = ".dvc"
@@ -25,6 +38,7 @@ def project_update_dvc_cli(
     project_dir: Path = Arg(Path.cwd(), help="Location of project directory. Defaults to current working directory.", exists=True, file_okay=False),
     workflow: Optional[str] = Arg(None, help=f"Name of workflow defined in {PROJECT_FILE}. Defaults to first workflow if not set."),
     verbose: bool = Opt(False, "--verbose", "-V", help="Print more info"),
+    quiet: bool = Opt(False, "--quiet", "-q", help="Print less info"),
     force: bool = Opt(False, "--force", "-F", help="Force update DVC config"),
     # fmt: on
 ):
@@ -36,7 +50,7 @@ def project_update_dvc_cli(
 
     DOCS: https://spacy.io/api/cli#project-dvc
     """
-    project_update_dvc(project_dir, workflow, verbose=verbose, force=force)
+    project_update_dvc(project_dir, workflow, verbose=verbose, quiet=quiet, force=force)
 
 
 def project_update_dvc(
@@ -44,6 +58,7 @@ def project_update_dvc(
     workflow: Optional[str] = None,
     *,
     verbose: bool = False,
+    quiet: bool = False,
     force: bool = False,
 ) -> None:
     """Update the auto-generated Data Version Control (DVC) config file. A DVC
@@ -54,11 +69,12 @@ def project_update_dvc(
     workflow (Optional[str]): Optional name of workflow defined in project.yml.
         If not set, the first workflow will be used.
     verbose (bool): Print more info.
+    quiet (bool): Print less info.
     force (bool): Force update DVC config.
     """
     config = load_project_config(project_dir)
     updated = update_dvc_config(
-        project_dir, config, workflow, verbose=verbose, force=force
+        project_dir, config, workflow, verbose=verbose, quiet=quiet, force=force
     )
     help_msg = "To execute the workflow with DVC, run: dvc repro"
     if updated:
@@ -72,7 +88,7 @@ def update_dvc_config(
     config: Dict[str, Any],
     workflow: Optional[str] = None,
     verbose: bool = False,
-    silent: bool = False,
+    quiet: bool = False,
     force: bool = False,
 ) -> bool:
     """Re-run the DVC commands in dry mode and update dvc.yaml file in the
@@ -83,7 +99,7 @@ def update_dvc_config(
     path (Path): The path to the project directory.
     config (Dict[str, Any]): The loaded project.yml.
     verbose (bool): Whether to print additional info (via DVC).
-    silent (bool): Don't output anything (via DVC).
+    quiet (bool): Don't output anything (via DVC).
     force (bool): Force update, even if hashes match.
     RETURNS (bool): Whether the DVC config file was updated.
     """
@@ -105,6 +121,14 @@ def update_dvc_config(
         dvc_config_path.unlink()
     dvc_commands = []
     config_commands = {cmd["name"]: cmd for cmd in config.get("commands", [])}
+
+    # some flags that apply to every command
+    flags = []
+    if verbose:
+        flags.append("--verbose")
+    if quiet:
+        flags.append("--quiet")
+
     for name in workflows[workflow]:
         command = config_commands[name]
         deps = command.get("deps", [])
@@ -118,14 +142,26 @@ def update_dvc_config(
         deps_cmd = [c for cl in [["-d", p] for p in deps] for c in cl]
         outputs_cmd = [c for cl in [["-o", p] for p in outputs] for c in cl]
         outputs_nc_cmd = [c for cl in [["-O", p] for p in outputs_no_cache] for c in cl]
-        dvc_cmd = ["run", "-n", name, "-w", str(path), "--no-exec"]
+
+        dvc_cmd = ["run", *flags, "-n", name, "-w", str(path), "--no-exec"]
         if command.get("no_skip"):
             dvc_cmd.append("--always-changed")
         full_cmd = [*dvc_cmd, *deps_cmd, *outputs_cmd, *outputs_nc_cmd, *project_cmd]
         dvc_commands.append(join_command(full_cmd))
+
+    if not dvc_commands:
+        # If we don't check for this, then there will be an error when reading the
+        # config, since DVC wouldn't create it.
+        msg.fail(
+            "No usable commands for DVC found. This can happen if none of your "
+            "commands have dependencies or outputs.",
+            exits=1,
+        )
+
     with working_dir(path):
-        dvc_flags = {"--verbose": verbose, "--quiet": silent}
-        run_dvc_commands(dvc_commands, flags=dvc_flags)
+        for c in dvc_commands:
+            dvc_command = "dvc " + c
+            run_command(dvc_command)
     with dvc_config_path.open("r+", encoding="utf8") as f:
         content = f.read()
         f.seek(0, 0)
@@ -133,26 +169,6 @@ def update_dvc_config(
     return True
 
 
-def run_dvc_commands(
-    commands: Iterable[str] = SimpleFrozenList(), flags: Dict[str, bool] = {}
-) -> None:
-    """Run a sequence of DVC commands in a subprocess, in order.
-
-    commands (List[str]): The string commands without the leading "dvc".
-    flags (Dict[str, bool]): Conditional flags to be added to command. Makes it
-        easier to pass flags like --quiet that depend on a variable or
-        command-line setting while avoiding lots of nested conditionals.
-    """
-    for c in commands:
-        command = split_command(c)
-        dvc_command = ["dvc", *command]
-        # Add the flags if they are set to True
-        for flag, is_active in flags.items():
-            if is_active:
-                dvc_command.append(flag)
-        run_command(dvc_command)
-
-
 def check_workflows(workflows: List[str], workflow: Optional[str] = None) -> None:
     """Validate workflows provided in project.yml and check that a given
     workflow can be used to generate a DVC config.

spacy/cli/project/pull.py

@@ -1,9 +1,9 @@
 from pathlib import Path
+
 from wasabi import msg
-from .remote_storage import RemoteStorage
-from .remote_storage import get_command_hash
-from .._util import project_cli, Arg, logger
-from .._util import load_project_config
+
+from .._util import Arg, load_project_config, logger, project_cli
+from .remote_storage import RemoteStorage, get_command_hash
 from .run import update_lockfile
 
 
@@ -39,14 +39,17 @@ def project_pull(project_dir: Path, remote: str, *, verbose: bool = False):
     # in the list.
     while commands:
         for i, cmd in enumerate(list(commands)):
-            logger.debug(f"CMD: {cmd['name']}.")
+            logger.debug("CMD: %s.", cmd["name"])
             deps = [project_dir / dep for dep in cmd.get("deps", [])]
             if all(dep.exists() for dep in deps):
                 cmd_hash = get_command_hash("", "", deps, cmd["script"])
                 for output_path in cmd.get("outputs", []):
                     url = storage.pull(output_path, command_hash=cmd_hash)
                     logger.debug(
-                        f"URL: {url} for {output_path} with command hash {cmd_hash}"
+                        "URL: %s for %s with command hash %s",
+                        url,
+                        output_path,
+                        cmd_hash,
                     )
                     yield url, output_path
 
@@ -58,7 +61,7 @@ def project_pull(project_dir: Path, remote: str, *, verbose: bool = False):
                 commands.pop(i)
                 break
             else:
-                logger.debug(f"Dependency missing. Skipping {cmd['name']} outputs.")
+                logger.debug("Dependency missing. Skipping %s outputs.", cmd["name"])
         else:
             # If we didn't break the for loop, break the while loop.
             break

spacy/cli/project/push.py

@@ -1,9 +1,9 @@
 from pathlib import Path
+
 from wasabi import msg
-from .remote_storage import RemoteStorage
-from .remote_storage import get_content_hash, get_command_hash
-from .._util import load_project_config
-from .._util import project_cli, Arg, logger
+
+from .._util import Arg, load_project_config, logger, project_cli
+from .remote_storage import RemoteStorage, get_command_hash, get_content_hash
 
 
 @project_cli.command("push")
@@ -37,15 +37,15 @@ def project_push(project_dir: Path, remote: str):
         remote = config["remotes"][remote]
     storage = RemoteStorage(project_dir, remote)
     for cmd in config.get("commands", []):
-        logger.debug(f"CMD: cmd['name']")
+        logger.debug("CMD: %s", cmd["name"])
         deps = [project_dir / dep for dep in cmd.get("deps", [])]
         if any(not dep.exists() for dep in deps):
-            logger.debug(f"Dependency missing. Skipping {cmd['name']} outputs")
+            logger.debug("Dependency missing. Skipping %s outputs", cmd["name"])
             continue
         cmd_hash = get_command_hash(
             "", "", [project_dir / dep for dep in cmd.get("deps", [])], cmd["script"]
         )
-        logger.debug(f"CMD_HASH: {cmd_hash}")
+        logger.debug("CMD_HASH: %s", cmd_hash)
         for output_path in cmd.get("outputs", []):
             output_loc = project_dir / output_path
             if output_loc.exists() and _is_not_empty_dir(output_loc):
@@ -55,7 +55,7 @@ def project_push(project_dir: Path, remote: str):
                     content_hash=get_content_hash(output_loc),
                 )
                 logger.debug(
-                    f"URL: {url} for output {output_path} with cmd_hash {cmd_hash}"
+                    "URL: %s for output %s with cmd_hash %s", url, output_path, cmd_hash
                 )
                 yield output_path, url
 

spacy/cli/project/remote_storage.py

@@ -1,18 +1,28 @@
-from typing import Optional, List, Dict, TYPE_CHECKING
+import hashlib
 import os
 import site
-import hashlib
-import urllib.parse
 import tarfile
+import urllib.parse
 from pathlib import Path
+from typing import TYPE_CHECKING, Dict, List, Optional
+
+from wasabi import msg
 
-from .._util import get_hash, get_checksum, download_file, ensure_pathy
-from ...util import make_tempdir, get_minor_version, ENV_VARS, check_bool_env_var
-from ...git_info import GIT_VERSION
 from ... import about
+from ...errors import Errors
+from ...git_info import GIT_VERSION
+from ...util import ENV_VARS, check_bool_env_var, get_minor_version
+from .._util import (
+    download_file,
+    ensure_pathy,
+    get_checksum,
+    get_hash,
+    make_tempdir,
+    upload_file,
+)
 
 if TYPE_CHECKING:
-    from pathy import Pathy  # noqa: F401
+    from pathy import FluidPath  # noqa: F401
 
 
 class RemoteStorage:
@@ -27,7 +37,7 @@ class RemoteStorage:
         self.url = ensure_pathy(url)
         self.compression = compression
 
-    def push(self, path: Path, command_hash: str, content_hash: str) -> "Pathy":
+    def push(self, path: Path, command_hash: str, content_hash: str) -> "FluidPath":
         """Compress a file or directory within a project and upload it to a remote
         storage. If an object exists at the full URL, nothing is done.
 
@@ -48,9 +58,7 @@ class RemoteStorage:
             mode_string = f"w:{self.compression}" if self.compression else "w"
             with tarfile.open(tar_loc, mode=mode_string) as tar_file:
                 tar_file.add(str(loc), arcname=str(path))
-            with tar_loc.open(mode="rb") as input_file:
-                with url.open(mode="wb") as output_file:
-                    output_file.write(input_file.read())
+            upload_file(tar_loc, url)
         return url
 
     def pull(
@@ -59,7 +67,7 @@ class RemoteStorage:
         *,
         command_hash: Optional[str] = None,
         content_hash: Optional[str] = None,
-    ) -> Optional["Pathy"]:
+    ) -> Optional["FluidPath"]:
         """Retrieve a file from the remote cache. If the file already exists,
         nothing is done.
 
@@ -84,7 +92,23 @@ class RemoteStorage:
                 with tarfile.open(tar_loc, mode=mode_string) as tar_file:
                     # This requires that the path is added correctly, relative
                     # to root. This is how we set things up in push()
-                    tar_file.extractall(self.root)
+
+                    # Disallow paths outside the current directory for the tar
+                    # file (CVE-2007-4559, directory traversal vulnerability)
+                    def is_within_directory(directory, target):
+                        abs_directory = os.path.abspath(directory)
+                        abs_target = os.path.abspath(target)
+                        prefix = os.path.commonprefix([abs_directory, abs_target])
+                        return prefix == abs_directory
+
+                    def safe_extract(tar, path):
+                        for member in tar.getmembers():
+                            member_path = os.path.join(path, member.name)
+                            if not is_within_directory(path, member_path):
+                                raise ValueError(Errors.E852)
+                        tar.extractall(path)
+
+                    safe_extract(tar_file, self.root)
         return url
 
     def find(
@@ -93,25 +117,37 @@ class RemoteStorage:
         *,
         command_hash: Optional[str] = None,
         content_hash: Optional[str] = None,
-    ) -> Optional["Pathy"]:
+    ) -> Optional["FluidPath"]:
         """Find the best matching version of a file within the storage,
         or `None` if no match can be found. If both the creation and content hash
         are specified, only exact matches will be returned. Otherwise, the most
         recent matching file is preferred.
         """
         name = self.encode_name(str(path))
+        urls = []
         if command_hash is not None and content_hash is not None:
-            url = self.make_url(path, command_hash, content_hash)
+            url = self.url / name / command_hash / content_hash
             urls = [url] if url.exists() else []
         elif command_hash is not None:
-            urls = list((self.url / name / command_hash).iterdir())
+            if (self.url / name / command_hash).exists():
+                urls = list((self.url / name / command_hash).iterdir())
         else:
-            urls = list((self.url / name).iterdir())
-            if content_hash is not None:
-                urls = [url for url in urls if url.parts[-1] == content_hash]
+            if (self.url / name).exists():
+                for sub_dir in (self.url / name).iterdir():
+                    urls.extend(sub_dir.iterdir())
+                if content_hash is not None:
+                    urls = [url for url in urls if url.parts[-1] == content_hash]
+        if len(urls) >= 2:
+            try:
+                urls.sort(key=lambda x: x.stat().last_modified)  # type: ignore
+            except Exception:
+                msg.warn(
+                    "Unable to sort remote files by last modified. The file(s) "
+                    "pulled from the cache may not be the most recent."
+                )
         return urls[-1] if urls else None
 
-    def make_url(self, path: Path, command_hash: str, content_hash: str) -> "Pathy":
+    def make_url(self, path: Path, command_hash: str, content_hash: str) -> "FluidPath":
         """Construct a URL from a subpath, a creation hash and a content hash."""
         return self.url / self.encode_name(str(path)) / command_hash / content_hash
 

spacy/cli/project/run.py

@@ -1,18 +1,39 @@
-from typing import Optional, List, Dict, Sequence, Any, Iterable
-from pathlib import Path
-from wasabi import msg
-from wasabi.util import locale_escape
+import os.path
 import sys
+from pathlib import Path
+from typing import Any, Dict, Iterable, List, Optional, Sequence, Tuple
+
 import srsly
 import typer
+from wasabi import msg
+from wasabi.util import locale_escape
 
 from ... import about
 from ...git_info import GIT_VERSION
-from ...util import working_dir, run_command, split_command, is_cwd, join_command
-from ...util import SimpleFrozenList, is_minor_version_match, ENV_VARS
-from ...util import check_bool_env_var, SimpleFrozenDict
-from .._util import PROJECT_FILE, PROJECT_LOCK, load_project_config, get_hash
-from .._util import get_checksum, project_cli, Arg, Opt, COMMAND, parse_config_overrides
+from ...util import (
+    ENV_VARS,
+    SimpleFrozenDict,
+    SimpleFrozenList,
+    check_bool_env_var,
+    is_cwd,
+    is_minor_version_match,
+    join_command,
+    run_command,
+    split_command,
+    working_dir,
+)
+from .._util import (
+    COMMAND,
+    PROJECT_FILE,
+    PROJECT_LOCK,
+    Arg,
+    Opt,
+    get_checksum,
+    get_hash,
+    load_project_config,
+    parse_config_overrides,
+    project_cli,
+)
 
 
 @project_cli.command(
@@ -50,6 +71,7 @@ def project_run(
     force: bool = False,
     dry: bool = False,
     capture: bool = False,
+    skip_requirements_check: bool = False,
 ) -> None:
     """Run a named script defined in the project.yml. If the script is part
     of the default pipeline (defined in the "run" section), DVC is used to
@@ -66,11 +88,19 @@ def project_run(
         sys.exit will be called with the return code. You should use capture=False
         when you want to turn over execution to the command, and capture=True
         when you want to run the command more like a function.
+    skip_requirements_check (bool): Whether to skip the requirements check.
     """
     config = load_project_config(project_dir, overrides=overrides)
     commands = {cmd["name"]: cmd for cmd in config.get("commands", [])}
     workflows = config.get("workflows", {})
     validate_subcommand(list(commands.keys()), list(workflows.keys()), subcommand)
+
+    req_path = project_dir / "requirements.txt"
+    if not skip_requirements_check:
+        if config.get("check_requirements", True) and os.path.exists(req_path):
+            with req_path.open() as requirements_file:
+                _check_requirements([req.strip() for req in requirements_file])
+
     if subcommand in workflows:
         msg.info(f"Running workflow '{subcommand}'")
         for cmd in workflows[subcommand]:
@@ -81,6 +111,7 @@ def project_run(
                 force=force,
                 dry=dry,
                 capture=capture,
+                skip_requirements_check=True,
             )
     else:
         cmd = commands[subcommand]
@@ -88,8 +119,8 @@ def project_run(
             if not (project_dir / dep).exists():
                 err = f"Missing dependency specified by command '{subcommand}': {dep}"
                 err_help = "Maybe you forgot to run the 'project assets' command or a previous step?"
-                err_kwargs = {"exits": 1} if not dry else {}
-                msg.fail(err, err_help, **err_kwargs)
+                err_exits = 1 if not dry else None
+                msg.fail(err, err_help, exits=err_exits)
         check_spacy_commit = check_bool_env_var(ENV_VARS.PROJECT_USE_GIT_VERSION)
         with working_dir(project_dir) as current_dir:
             msg.divider(subcommand)
@@ -195,6 +226,8 @@ def validate_subcommand(
         msg.fail(f"No commands or workflows defined in {PROJECT_FILE}", exits=1)
     if subcommand not in commands and subcommand not in workflows:
         help_msg = []
+        if subcommand in ["assets", "asset"]:
+            help_msg.append("Did you mean to run: python -m spacy project assets?")
         if commands:
             help_msg.append(f"Available commands: {', '.join(commands)}")
         if workflows:
@@ -308,3 +341,39 @@ def get_fileinfo(project_dir: Path, paths: List[str]) -> List[Dict[str, Optional
         md5 = get_checksum(file_path) if file_path.exists() else None
         data.append({"path": path, "md5": md5})
     return data
+
+
+def _check_requirements(requirements: List[str]) -> Tuple[bool, bool]:
+    """Checks whether requirements are installed and free of version conflicts.
+    requirements (List[str]): List of requirements.
+    RETURNS (Tuple[bool, bool]): Whether (1) any packages couldn't be imported, (2) any packages with version conflicts
+        exist.
+    """
+    import pkg_resources
+
+    failed_pkgs_msgs: List[str] = []
+    conflicting_pkgs_msgs: List[str] = []
+
+    for req in requirements:
+        try:
+            pkg_resources.require(req)
+        except pkg_resources.DistributionNotFound as dnf:
+            failed_pkgs_msgs.append(dnf.report())
+        except pkg_resources.VersionConflict as vc:
+            conflicting_pkgs_msgs.append(vc.report())
+        except Exception:
+            msg.warn(
+                f"Unable to check requirement: {req} "
+                "Checks are currently limited to requirement specifiers "
+                "(PEP 508)"
+            )
+
+    if len(failed_pkgs_msgs) or len(conflicting_pkgs_msgs):
+        msg.warn(
+            title="Missing requirements or requirement conflicts detected. Make sure your Python environment is set up "
+            "correctly and you installed all requirements specified in your project's requirements.txt: "
+        )
+        for pgk_msg in failed_pkgs_msgs + conflicting_pkgs_msgs:
+            msg.text(pgk_msg)
+
+    return len(failed_pkgs_msgs) > 0, len(conflicting_pkgs_msgs) > 0

spacy/cli/templates/quickstart_training.jinja

@@ -1,11 +1,17 @@
 {# This is a template for training configs used for the quickstart widget in
 the docs and the init config command. It encodes various best practices and
 can help generate the best possible configuration, given a user's requirements. #}
-{%- set use_transformer = hardware != "cpu" -%}
+{%- set use_transformer = hardware != "cpu" and transformer_data -%}
 {%- set transformer = transformer_data[optimize] if use_transformer else {} -%}
+{%- set listener_components = ["tagger", "morphologizer", "parser", "ner", "textcat", "textcat_multilabel", "entity_linker", "span_finder", "spancat", "spancat_singlelabel", "trainable_lemmatizer"] -%}
 [paths]
 train = null
 dev = null
+{% if use_transformer or optimize == "efficiency" or not word_vectors -%}
+vectors = null
+{% else -%}
+vectors = "{{ word_vectors }}"
+{% endif -%}
 
 [system]
 {% if use_transformer -%}
@@ -18,11 +24,14 @@ gpu_allocator = null
 lang = "{{ lang }}"
 {%- set has_textcat = ("textcat" in components or "textcat_multilabel" in components) -%}
 {%- set with_accuracy = optimize == "accuracy" -%}
-{%- set has_accurate_textcat = has_textcat and with_accuracy -%}
-{%- if ("tagger" in components or "morphologizer" in components or "parser" in components or "ner" in components or "entity_linker" in components or has_accurate_textcat) -%}
-{%- set full_pipeline = ["transformer" if use_transformer else "tok2vec"] + components %}
+{# The BOW textcat doesn't need a source of features, so it can omit the
+tok2vec/transformer. #}
+{%- set with_accuracy_or_transformer = (use_transformer or with_accuracy) -%}
+{%- set textcat_needs_features = has_textcat and with_accuracy_or_transformer -%}
+{%- if ("tagger" in components or "morphologizer" in components or "parser" in components or "ner" in components or "span_finder" in components or "spancat" in components or "spancat_singlelabel" in components or "trainable_lemmatizer" in components or "entity_linker" in components or textcat_needs_features) -%}
+{%- set full_pipeline = ["transformer" if use_transformer else "tok2vec"] + components -%}
 {%- else -%}
-{%- set full_pipeline = components %}
+{%- set full_pipeline = components -%}
 {%- endif %}
 pipeline = {{ full_pipeline|pprint()|replace("'", '"')|safe }}
 batch_size = {{ 128 if hardware == "gpu" else 1000 }}
@@ -49,7 +58,7 @@ stride = 96
 factory = "morphologizer"
 
 [components.morphologizer.model]
-@architectures = "spacy.Tagger.v1"
+@architectures = "spacy.Tagger.v2"
 nO = null
 
 [components.morphologizer.model.tok2vec]
@@ -65,7 +74,7 @@ grad_factor = 1.0
 factory = "tagger"
 
 [components.tagger.model]
-@architectures = "spacy.Tagger.v1"
+@architectures = "spacy.Tagger.v2"
 nO = null
 
 [components.tagger.model.tok2vec]
@@ -81,12 +90,11 @@ grad_factor = 1.0
 factory = "parser"
 
 [components.parser.model]
-@architectures = "spacy.TransitionBasedParser.v2"
+@architectures = "spacy.TransitionBasedParser.v3"
 state_type = "parser"
 extra_state_tokens = false
 hidden_width = 128
 maxout_pieces = 3
-use_upper = false
 nO = null
 
 [components.parser.model.tok2vec]
@@ -102,12 +110,11 @@ grad_factor = 1.0
 factory = "ner"
 
 [components.ner.model]
-@architectures = "spacy.TransitionBasedParser.v2"
+@architectures = "spacy.TransitionBasedParser.v3"
 state_type = "ner"
 extra_state_tokens = false
 hidden_width = 64
 maxout_pieces = 2
-use_upper = false
 nO = null
 
 [components.ner.model.tok2vec]
@@ -118,6 +125,114 @@ grad_factor = 1.0
 @layers = "reduce_mean.v1"
 {% endif -%}
 
+{% if "span_finder" in components -%}
+[components.span_finder]
+factory = "span_finder"
+max_length = 25
+min_length = null
+scorer = {"@scorers":"spacy.span_finder_scorer.v1"}
+spans_key = "sc"
+threshold = 0.5
+
+[components.span_finder.model]
+@architectures = "spacy.SpanFinder.v1"
+
+[components.span_finder.model.scorer]
+@layers = "spacy.LinearLogistic.v1"
+nO = 2
+
+[components.span_finder.model.tok2vec]
+@architectures = "spacy-transformers.TransformerListener.v1"
+grad_factor = 1.0
+
+[components.span_finder.model.tok2vec.pooling]
+@layers = "reduce_mean.v1"
+{% endif -%}
+
+{% if "spancat" in components -%}
+[components.spancat]
+factory = "spancat"
+max_positive = null
+scorer = {"@scorers":"spacy.spancat_scorer.v1"}
+spans_key = "sc"
+threshold = 0.5
+
+[components.spancat.model]
+@architectures = "spacy.SpanCategorizer.v1"
+
+[components.spancat.model.reducer]
+@layers = "spacy.mean_max_reducer.v1"
+hidden_size = 128
+
+[components.spancat.model.scorer]
+@layers = "spacy.LinearLogistic.v1"
+nO = null
+nI = null
+
+[components.spancat.model.tok2vec]
+@architectures = "spacy-transformers.TransformerListener.v1"
+grad_factor = 1.0
+
+[components.spancat.model.tok2vec.pooling]
+@layers = "reduce_mean.v1"
+
+[components.spancat.suggester]
+@misc = "spacy.ngram_suggester.v1"
+sizes = [1,2,3]
+{% endif -%}
+
+{% if "spancat_singlelabel" in components %}
+[components.spancat_singlelabel]
+factory = "spancat_singlelabel"
+negative_weight = 1.0
+allow_overlap = true
+scorer = {"@scorers":"spacy.spancat_scorer.v1"}
+spans_key = "sc"
+
+[components.spancat_singlelabel.model]
+@architectures = "spacy.SpanCategorizer.v1"
+
+[components.spancat_singlelabel.model.reducer]
+@layers = "spacy.mean_max_reducer.v1"
+hidden_size = 128
+
+[components.spancat_singlelabel.model.scorer]
+@layers = "Softmax.v2"
+
+[components.spancat_singlelabel.model.tok2vec]
+@architectures = "spacy-transformers.TransformerListener.v1"
+grad_factor = 1.0
+
+[components.spancat_singlelabel.model.tok2vec.pooling]
+@layers = "reduce_mean.v1"
+
+[components.spancat_singlelabel.suggester]
+@misc = "spacy.ngram_suggester.v1"
+sizes = [1,2,3]
+{% endif %}
+
+{% if "trainable_lemmatizer" in components -%}
+[components.trainable_lemmatizer]
+factory = "trainable_lemmatizer"
+backoff = "orth"
+min_tree_freq = 3
+overwrite = false
+scorer = {"@scorers":"spacy.lemmatizer_scorer.v1"}
+top_k = 1
+
+[components.trainable_lemmatizer.model]
+@architectures = "spacy.Tagger.v2"
+nO = null
+normalize = false
+
+[components.trainable_lemmatizer.model.tok2vec]
+@architectures = "spacy-transformers.TransformerListener.v1"
+grad_factor = 1.0
+
+[components.trainable_lemmatizer.model.tok2vec.pooling]
+@layers = "reduce_mean.v1"
+{% endif -%}
+
 {% if "entity_linker" in components -%}
 [components.entity_linker]
 factory = "entity_linker"
@@ -126,7 +241,7 @@ incl_context = true
 incl_prior = true
 
 [components.entity_linker.model]
-@architectures = "spacy.EntityLinker.v1"
+@architectures = "spacy.EntityLinker.v2"
 nO = null
 
 [components.entity_linker.model.tok2vec]
@@ -161,10 +276,16 @@ no_output_layer = false
 
 {% else -%}
 [components.textcat.model]
-@architectures = "spacy.TextCatBOW.v2"
+@architectures = "spacy.TextCatCNN.v2"
 exclusive_classes = true
-ngram_size = 1
-no_output_layer = false
+nO = null
+
+[components.textcat.model.tok2vec]
+@architectures = "spacy-transformers.TransformerListener.v1"
+grad_factor = 1.0
+
+[components.textcat.model.tok2vec.pooling]
+@layers = "reduce_mean.v1"
 {%- endif %}
 {%- endif %}
 
@@ -192,10 +313,16 @@ no_output_layer = false
 
 {% else -%}
 [components.textcat_multilabel.model]
-@architectures = "spacy.TextCatBOW.v2"
+@architectures = "spacy.TextCatCNN.v2"
 exclusive_classes = false
-ngram_size = 1
-no_output_layer = false
+nO = null
+
+[components.textcat_multilabel.model.tok2vec]
+@architectures = "spacy-transformers.TransformerListener.v1"
+grad_factor = 1.0
+
+[components.textcat_multilabel.model.tok2vec.pooling]
+@layers = "reduce_mean.v1"
 {%- endif %}
 {%- endif %}
 
@@ -211,13 +338,8 @@ factory = "tok2vec"
 [components.tok2vec.model.embed]
 @architectures = "spacy.MultiHashEmbed.v2"
 width = ${components.tok2vec.model.encode.width}
-{% if has_letters -%}
 attrs = ["NORM", "PREFIX", "SUFFIX", "SHAPE"]
-rows = [5000, 2500, 2500, 2500]
-{% else -%}
-attrs = ["ORTH", "SHAPE"]
-rows = [5000, 2500]
-{% endif -%}
+rows = [5000, 1000, 2500, 2500]
 include_static_vectors = {{ "true" if optimize == "accuracy" else "false" }}
 
 [components.tok2vec.model.encode]
@@ -231,9 +353,10 @@ maxout_pieces = 3
 {% if "morphologizer" in components %}
 [components.morphologizer]
 factory = "morphologizer"
+label_smoothing = 0.05
 
 [components.morphologizer.model]
-@architectures = "spacy.Tagger.v1"
+@architectures = "spacy.Tagger.v2"
 nO = null
 
 [components.morphologizer.model.tok2vec]
@@ -244,9 +367,10 @@ width = ${components.tok2vec.model.encode.width}
 {% if "tagger" in components %}
 [components.tagger]
 factory = "tagger"
+label_smoothing = 0.05
 
 [components.tagger.model]
-@architectures = "spacy.Tagger.v1"
+@architectures = "spacy.Tagger.v2"
 nO = null
 
 [components.tagger.model.tok2vec]
@@ -259,12 +383,11 @@ width = ${components.tok2vec.model.encode.width}
 factory = "parser"
 
 [components.parser.model]
-@architectures = "spacy.TransitionBasedParser.v2"
+@architectures = "spacy.TransitionBasedParser.v3"
 state_type = "parser"
 extra_state_tokens = false
 hidden_width = 128
 maxout_pieces = 3
-use_upper = true
 nO = null
 
 [components.parser.model.tok2vec]
@@ -277,12 +400,11 @@ width = ${components.tok2vec.model.encode.width}
 factory = "ner"
 
 [components.ner.model]
-@architectures = "spacy.TransitionBasedParser.v2"
+@architectures = "spacy.TransitionBasedParser.v3"
 state_type = "ner"
 extra_state_tokens = false
 hidden_width = 64
 maxout_pieces = 2
-use_upper = true
 nO = null
 
 [components.ner.model.tok2vec]
@@ -290,6 +412,102 @@ nO = null
 width = ${components.tok2vec.model.encode.width}
 {% endif %}
 
+{% if "span_finder" in components %}
+[components.span_finder]
+factory = "span_finder"
+max_length = 25
+min_length = null
+scorer = {"@scorers":"spacy.span_finder_scorer.v1"}
+spans_key = "sc"
+threshold = 0.5
+
+[components.span_finder.model]
+@architectures = "spacy.SpanFinder.v1"
+
+[components.span_finder.model.scorer]
+@layers = "spacy.LinearLogistic.v1"
+nO = 2
+
+[components.span_finder.model.tok2vec]
+@architectures = "spacy.Tok2VecListener.v1"
+width = ${components.tok2vec.model.encode.width}
+{% endif %}
+
+{% if "spancat" in components %}
+[components.spancat]
+factory = "spancat"
+max_positive = null
+scorer = {"@scorers":"spacy.spancat_scorer.v1"}
+spans_key = "sc"
+threshold = 0.5
+
+[components.spancat.model]
+@architectures = "spacy.SpanCategorizer.v1"
+
+[components.spancat.model.reducer]
+@layers = "spacy.mean_max_reducer.v1"
+hidden_size = 128
+
+[components.spancat.model.scorer]
+@layers = "spacy.LinearLogistic.v1"
+nO = null
+nI = null
+
+[components.spancat.model.tok2vec]
+@architectures = "spacy.Tok2VecListener.v1"
+width = ${components.tok2vec.model.encode.width}
+
+[components.spancat.suggester]
+@misc = "spacy.ngram_suggester.v1"
+sizes = [1,2,3]
+{% endif %}
+
+{% if "spancat_singlelabel" in components %}
+[components.spancat_singlelabel]
+factory = "spancat_singlelabel"
+negative_weight = 1.0
+allow_overlap = true
+scorer = {"@scorers":"spacy.spancat_scorer.v1"}
+spans_key = "sc"
+
+[components.spancat_singlelabel.model]
+@architectures = "spacy.SpanCategorizer.v1"
+
+[components.spancat_singlelabel.model.reducer]
+@layers = "spacy.mean_max_reducer.v1"
+hidden_size = 128
+
+[components.spancat_singlelabel.model.scorer]
+@layers = "Softmax.v2"
+
+[components.spancat_singlelabel.model.tok2vec]
+@architectures = "spacy.Tok2VecListener.v1"
+width = ${components.tok2vec.model.encode.width}
+
+[components.spancat_singlelabel.suggester]
+@misc = "spacy.ngram_suggester.v1"
+sizes = [1,2,3]
+{% endif %}
+
+{% if "trainable_lemmatizer" in components -%}
+[components.trainable_lemmatizer]
+factory = "trainable_lemmatizer"
+backoff = "orth"
+min_tree_freq = 3
+overwrite = false
+scorer = {"@scorers":"spacy.lemmatizer_scorer.v1"}
+top_k = 1
+
+[components.trainable_lemmatizer.model]
+@architectures = "spacy.Tagger.v2"
+nO = null
+normalize = false
+
+[components.trainable_lemmatizer.model.tok2vec]
+@architectures = "spacy.Tok2VecListener.v1"
+width = ${components.tok2vec.model.encode.width}
+{% endif -%}
+
 {% if "entity_linker" in components -%}
 [components.entity_linker]
 factory = "entity_linker"
@@ -298,7 +516,7 @@ incl_context = true
 incl_prior = true
 
 [components.entity_linker.model]
-@architectures = "spacy.EntityLinker.v1"
+@architectures = "spacy.EntityLinker.v2"
 nO = null
 
 [components.entity_linker.model.tok2vec]
@@ -364,7 +582,7 @@ no_output_layer = false
 {% endif %}
 
 {% for pipe in components %}
-{% if pipe not in ["tagger", "morphologizer", "parser", "ner", "textcat", "textcat_multilabel", "entity_linker"] %}
+{% if pipe not in listener_components %}
 {# Other components defined by the user: we just assume they're factories #}
 [components.{{ pipe }}]
 factory = "{{ pipe }}"
@@ -421,8 +639,4 @@ compound = 1.001
 {% endif %}
 
 [initialize]
-{% if use_transformer or optimize == "efficiency" or not word_vectors -%}
 vectors = ${paths.vectors}
-{% else -%}
-vectors = "{{ word_vectors }}"
-{% endif -%}

spacy/cli/templates/quickstart_training_recommendations.yml

@@ -37,6 +37,15 @@ bn:
     accuracy:
       name: sagorsarker/bangla-bert-base
       size_factor: 3
+ca:
+  word_vectors: null
+  transformer:
+    efficiency:
+      name: projecte-aina/roberta-base-ca-v2
+      size_factor: 3
+    accuracy:
+      name: projecte-aina/roberta-base-ca-v2
+      size_factor: 3
 da:
   word_vectors: da_core_news_lg
   transformer:
@@ -271,4 +280,3 @@ zh:
     accuracy:
       name: bert-base-chinese
       size_factor: 3
-  has_letters: false

spacy/cli/train.py

@@ -1,15 +1,23 @@
-from typing import Optional, Dict, Any, Union
-from pathlib import Path
-from wasabi import msg
-import typer
 import logging
 import sys
+from pathlib import Path
+from typing import Any, Dict, Optional, Union
+
+import typer
+from wasabi import msg
 
-from ._util import app, Arg, Opt, parse_config_overrides, show_validation_error
-from ._util import import_code, setup_gpu
-from ..training.loop import train as train_nlp
-from ..training.initialize import init_nlp
 from .. import util
+from ..training.initialize import init_nlp
+from ..training.loop import train as train_nlp
+from ._util import (
+    Arg,
+    Opt,
+    app,
+    import_code_paths,
+    parse_config_overrides,
+    setup_gpu,
+    show_validation_error,
+)
 
 
 @app.command(
@@ -20,7 +28,7 @@ def train_cli(
     ctx: typer.Context,  # This is only used to read additional arguments
     config_path: Path = Arg(..., help="Path to config file", exists=True, allow_dash=True),
     output_path: Optional[Path] = Opt(None, "--output", "--output-path", "-o", help="Output directory to store trained pipeline in"),
-    code_path: Optional[Path] = Opt(None, "--code", "-c", help="Path to Python file with additional code (registered functions) to be imported"),
+    code_path: str = Opt("", "--code", "-c", help="Comma-separated paths to Python files with additional code (registered functions) to be imported"),
     verbose: bool = Opt(False, "--verbose", "-V", "-VV", help="Display more information for debugging purposes"),
     use_gpu: int = Opt(-1, "--gpu-id", "-g", help="GPU ID or -1 for CPU")
     # fmt: on
@@ -41,7 +49,7 @@ def train_cli(
     """
     util.logger.setLevel(logging.DEBUG if verbose else logging.INFO)
     overrides = parse_config_overrides(ctx.args)
-    import_code(code_path)
+    import_code_paths(code_path)
     train(config_path, output_path, use_gpu=use_gpu, overrides=overrides)
 
 

spacy/cli/validate.py

@@ -1,14 +1,21 @@
-from typing import Tuple
-from pathlib import Path
 import sys
-import requests
-from wasabi import msg, Printer
 import warnings
+from pathlib import Path
+from typing import Tuple
+
+import requests
+from wasabi import Printer, msg
 
-from ._util import app
 from .. import about
-from ..util import get_package_version, get_installed_models, get_minor_version
-from ..util import get_package_path, get_model_meta, is_compatible_version
+from ..util import (
+    get_installed_models,
+    get_minor_version,
+    get_model_meta,
+    get_package_path,
+    get_package_version,
+    is_compatible_version,
+)
+from ._util import app
 
 
 @app.command("validate")

spacy/compat.py

@@ -1,5 +1,6 @@
 """Helpers for Python and platform compatibility."""
 import sys
+
 from thinc.util import copy_array
 
 try:
@@ -22,19 +23,6 @@ try:
 except ImportError:
     cupy = None
 
-if sys.version_info[:2] >= (3, 8):  # Python 3.8+
-    from typing import Literal, Protocol, runtime_checkable
-else:
-    from typing_extensions import Literal, Protocol, runtime_checkable  # noqa: F401
-
-# Important note: The importlib_metadata "backport" includes functionality
-# that's not part of the built-in importlib.metadata. We should treat this
-# import like the built-in and only use what's available there.
-try:  # Python 3.8+
-    import importlib.metadata as importlib_metadata
-except ImportError:
-    from catalogue import _importlib_metadata as importlib_metadata  # type: ignore[no-redef]    # noqa: F401
-
 from thinc.api import Optimizer  # noqa: F401
 
 pickle = pickle

spacy/default_config.cfg

@@ -68,12 +68,14 @@ seed = ${system.seed}
 gpu_allocator = ${system.gpu_allocator}
 dropout = 0.1
 accumulate_gradient = 1
-# Controls early-stopping. 0 disables early stopping.
+# Controls early-stopping, i.e., the number of steps to continue without
+# improvement before stopping. 0 disables early stopping.
 patience = 1600
 # Number of epochs. 0 means unlimited. If >= 0, train corpus is loaded once in
 # memory and shuffled within the training loop. -1 means stream train corpus
 # rather than loading in memory with no shuffling within the training loop.
 max_epochs = 0
+# Maximum number of update steps to train for. 0 means an unlimited number of steps.
 max_steps = 20000
 eval_frequency = 200
 # Control how scores are printed and checkpoints are evaluated.
@@ -88,6 +90,8 @@ dev_corpus = "corpora.dev"
 train_corpus = "corpora.train"
 # Optional callback before nlp object is saved to disk after training
 before_to_disk = null
+# Optional callback that is invoked at the start of each training step
+before_update = null
 
 [training.logger]
 @loggers = "spacy.ConsoleLogger.v1"

spacy/default_config_distillation.cfg

@@ -0,0 +1,34 @@
+[paths]
+raw_text = null
+
+[distillation]
+corpus = "corpora.distillation"
+dropout = 0.1
+max_epochs = 1
+max_steps = 0
+student_to_teacher = {}
+
+[distillation.batcher]
+@batchers = "spacy.batch_by_words.v1"
+size = 3000
+discard_oversize = false
+tolerance = 0.2
+
+[distillation.optimizer]
+@optimizers = "Adam.v1"
+beta1 = 0.9
+beta2 = 0.999
+L2_is_weight_decay = true
+L2 = 0.01
+grad_clip = 1.0
+use_averages = true
+eps = 1e-8
+learn_rate = 1e-4
+
+[corpora]
+
+[corpora.distillation]
+@readers = "spacy.PlainTextCorpus.v1"
+path = ${paths.raw_text}
+min_length = 0
+max_length = 0

spacy/displacy/__init__.py

@@ -4,14 +4,13 @@ spaCy's built in visualization suite for dependencies and named entities.
 DOCS: https://spacy.io/api/top-level#displacy
 USAGE: https://spacy.io/usage/visualizers
 """
-from typing import Union, Iterable, Optional, Dict, Any, Callable
 import warnings
+from typing import Any, Callable, Dict, Iterable, Optional, Union
 
-from .render import DependencyRenderer, EntityRenderer
-from ..tokens import Doc, Span
 from ..errors import Errors, Warnings
-from ..util import is_in_jupyter
-
+from ..tokens import Doc, Span
+from ..util import find_available_port, is_in_jupyter
+from .render import DependencyRenderer, EntityRenderer, SpanRenderer
 
 _html = {}
 RENDER_WRAPPER = None
@@ -36,7 +35,7 @@ def render(
     jupyter (bool): Override Jupyter auto-detection.
     options (dict): Visualiser-specific options, e.g. colors.
     manual (bool): Don't parse `Doc` and instead expect a dict/list of dicts.
-    RETURNS (str): Rendered HTML markup.
+    RETURNS (str): Rendered SVG or HTML markup.
 
     DOCS: https://spacy.io/api/top-level#displacy.render
     USAGE: https://spacy.io/usage/visualizers
@@ -44,6 +43,7 @@ def render(
     factories = {
         "dep": (DependencyRenderer, parse_deps),
         "ent": (EntityRenderer, parse_ents),
+        "span": (SpanRenderer, parse_spans),
     }
     if style not in factories:
         raise ValueError(Errors.E087.format(style=style))
@@ -55,6 +55,10 @@ def render(
     renderer_func, converter = factories[style]
     renderer = renderer_func(options=options)
     parsed = [converter(doc, options) for doc in docs] if not manual else docs  # type: ignore
+    if manual:
+        for doc in docs:
+            if isinstance(doc, dict) and "ents" in doc:
+                doc["ents"] = sorted(doc["ents"], key=lambda x: (x["start"], x["end"]))
     _html["parsed"] = renderer.render(parsed, page=page, minify=minify).strip()  # type: ignore
     html = _html["parsed"]
     if RENDER_WRAPPER is not None:
@@ -62,7 +66,7 @@ def render(
     if jupyter or (jupyter is None and is_in_jupyter()):
         # return HTML rendered by IPython display()
         # See #4840 for details on span wrapper to disable mathjax
-        from IPython.core.display import display, HTML
+        from IPython.core.display import HTML, display
 
         return display(HTML('<span class="tex2jax_ignore">{}</span>'.format(html)))
     return html
@@ -77,6 +81,7 @@ def serve(
     manual: bool = False,
     port: int = 5000,
     host: str = "0.0.0.0",
+    auto_select_port: bool = False,
 ) -> None:
     """Serve displaCy visualisation.
 
@@ -88,12 +93,15 @@ def serve(
     manual (bool): Don't parse `Doc` and instead expect a dict/list of dicts.
     port (int): Port to serve visualisation.
     host (str): Host to serve visualisation.
+    auto_select_port (bool): Automatically select a port if the specified port is in use.
 
     DOCS: https://spacy.io/api/top-level#displacy.serve
     USAGE: https://spacy.io/usage/visualizers
     """
     from wsgiref import simple_server
 
+    port = find_available_port(port, host, auto_select_port)
+
     if is_in_jupyter():
         warnings.warn(Warnings.W011)
     render(docs, style=style, page=page, minify=minify, options=options, manual=manual)
@@ -115,12 +123,17 @@ def app(environ, start_response):
     return [res]
 
 
-def parse_deps(orig_doc: Doc, options: Dict[str, Any] = {}) -> Dict[str, Any]:
+def parse_deps(
+    orig_doc: Union[Doc, Span], options: Dict[str, Any] = {}
+) -> Dict[str, Any]:
     """Generate dependency parse in {'words': [], 'arcs': []} format.
 
-    doc (Doc): Document do parse.
+    orig_doc (Union[Doc, Span]): Document to parse.
+    options (Dict[str, Any]): Dependency parse specific visualisation options.
     RETURNS (dict): Generated dependency parse keyed by words and arcs.
     """
+    if isinstance(orig_doc, Span):
+        orig_doc = orig_doc.as_doc()
     doc = Doc(orig_doc.vocab).from_bytes(
         orig_doc.to_bytes(exclude=["user_data", "user_hooks"])
     )
@@ -203,6 +216,43 @@ def parse_ents(doc: Doc, options: Dict[str, Any] = {}) -> Dict[str, Any]:
     return {"text": doc.text, "ents": ents, "title": title, "settings": settings}
 
 
+def parse_spans(doc: Doc, options: Dict[str, Any] = {}) -> Dict[str, Any]:
+    """Generate spans in [{start_token: i, end_token: i, label: 'label'}] format.
+
+    doc (Doc): Document to parse.
+    options (Dict[str, any]): Span-specific visualisation options.
+    RETURNS (dict): Generated span types keyed by text (original text) and spans.
+    """
+    kb_url_template = options.get("kb_url_template", None)
+    spans_key = options.get("spans_key", "sc")
+    spans = [
+        {
+            "start": span.start_char,
+            "end": span.end_char,
+            "start_token": span.start,
+            "end_token": span.end,
+            "label": span.label_,
+            "kb_id": span.kb_id_ if span.kb_id_ else "",
+            "kb_url": kb_url_template.format(span.kb_id_) if kb_url_template else "#",
+        }
+        for span in doc.spans.get(spans_key, [])
+    ]
+    tokens = [token.text for token in doc]
+
+    if not spans:
+        keys = list(doc.spans.keys())
+        warnings.warn(Warnings.W117.format(spans_key=spans_key, keys=keys))
+    title = doc.user_data.get("title", None) if hasattr(doc, "user_data") else None
+    settings = get_doc_settings(doc)
+    return {
+        "text": doc.text,
+        "spans": spans,
+        "title": title,
+        "settings": settings,
+        "tokens": tokens,
+    }
+
+
 def set_render_wrapper(func: Callable[[str], str]) -> None:
     """Set an optional wrapper function that is called around the generated
     HTML markup on displacy.render. This can be used to allow integration into

spacy/displacy/render.py

@@ -1,12 +1,28 @@
-from typing import Dict, Any, List, Optional, Union
 import uuid
+from typing import Any, Dict, List, Optional, Tuple, Union
 
-from .templates import TPL_DEP_SVG, TPL_DEP_WORDS, TPL_DEP_WORDS_LEMMA, TPL_DEP_ARCS
-from .templates import TPL_ENT, TPL_ENT_RTL, TPL_FIGURE, TPL_TITLE, TPL_PAGE
-from .templates import TPL_ENTS, TPL_KB_LINK
-from ..util import minify_html, escape_html, registry
 from ..errors import Errors
-
+from ..util import escape_html, minify_html, registry
+from .templates import (
+    TPL_DEP_ARCS,
+    TPL_DEP_SVG,
+    TPL_DEP_WORDS,
+    TPL_DEP_WORDS_LEMMA,
+    TPL_ENT,
+    TPL_ENT_RTL,
+    TPL_ENTS,
+    TPL_FIGURE,
+    TPL_KB_LINK,
+    TPL_PAGE,
+    TPL_SPAN,
+    TPL_SPAN_RTL,
+    TPL_SPAN_SLICE,
+    TPL_SPAN_SLICE_RTL,
+    TPL_SPAN_START,
+    TPL_SPAN_START_RTL,
+    TPL_SPANS,
+    TPL_TITLE,
+)
 
 DEFAULT_LANG = "en"
 DEFAULT_DIR = "ltr"
@@ -18,7 +34,7 @@ DEFAULT_LABEL_COLORS = {
     "LOC": "#ff9561",
     "PERSON": "#aa9cfc",
     "NORP": "#c887fb",
-    "FACILITY": "#9cc9cc",
+    "FAC": "#9cc9cc",
     "EVENT": "#ffeb80",
     "LAW": "#ff8197",
     "LANGUAGE": "#ff8197",
@@ -33,6 +49,224 @@ DEFAULT_LABEL_COLORS = {
 }
 
 
+class SpanRenderer:
+    """Render Spans as SVGs."""
+
+    style = "span"
+
+    def __init__(self, options: Dict[str, Any] = {}) -> None:
+        """Initialise span renderer
+
+        options (dict): Visualiser-specific options (colors, spans)
+        """
+        # Set up the colors and overall look
+        colors = dict(DEFAULT_LABEL_COLORS)
+        user_colors = registry.displacy_colors.get_all()
+        for user_color in user_colors.values():
+            if callable(user_color):
+                # Since this comes from the function registry, we want to make
+                # sure we support functions that *return* a dict of colors
+                user_color = user_color()
+            if not isinstance(user_color, dict):
+                raise ValueError(Errors.E925.format(obj=type(user_color)))
+            colors.update(user_color)
+        colors.update(options.get("colors", {}))
+        self.default_color = DEFAULT_ENTITY_COLOR
+        self.colors = {label.upper(): color for label, color in colors.items()}
+
+        # Set up how the text and labels will be rendered
+        self.direction = DEFAULT_DIR
+        self.lang = DEFAULT_LANG
+        # These values are in px
+        self.top_offset = options.get("top_offset", 40)
+        # This is how far under the top offset the span labels appear
+        self.span_label_offset = options.get("span_label_offset", 20)
+        self.offset_step = options.get("top_offset_step", 17)
+
+        # Set up which templates will be used
+        template = options.get("template")
+        if template:
+            self.span_template = template["span"]
+            self.span_slice_template = template["slice"]
+            self.span_start_template = template["start"]
+        else:
+            if self.direction == "rtl":
+                self.span_template = TPL_SPAN_RTL
+                self.span_slice_template = TPL_SPAN_SLICE_RTL
+                self.span_start_template = TPL_SPAN_START_RTL
+            else:
+                self.span_template = TPL_SPAN
+                self.span_slice_template = TPL_SPAN_SLICE
+                self.span_start_template = TPL_SPAN_START
+
+    def render(
+        self, parsed: List[Dict[str, Any]], page: bool = False, minify: bool = False
+    ) -> str:
+        """Render complete markup.
+
+        parsed (list): Dependency parses to render.
+        page (bool): Render parses wrapped as full HTML page.
+        minify (bool): Minify HTML markup.
+        RETURNS (str): Rendered SVG or HTML markup.
+        """
+        rendered = []
+        for i, p in enumerate(parsed):
+            if i == 0:
+                settings = p.get("settings", {})
+                self.direction = settings.get("direction", DEFAULT_DIR)
+                self.lang = settings.get("lang", DEFAULT_LANG)
+            rendered.append(self.render_spans(p["tokens"], p["spans"], p.get("title")))
+
+        if page:
+            docs = "".join([TPL_FIGURE.format(content=doc) for doc in rendered])
+            markup = TPL_PAGE.format(content=docs, lang=self.lang, dir=self.direction)
+        else:
+            markup = "".join(rendered)
+        if minify:
+            return minify_html(markup)
+        return markup
+
+    def render_spans(
+        self,
+        tokens: List[str],
+        spans: List[Dict[str, Any]],
+        title: Optional[str],
+    ) -> str:
+        """Render span types in text.
+
+        Spans are rendered per-token, this means that for each token, we check if it's part
+        of a span slice (a member of a span type) or a span start (the starting token of a
+        given span type).
+
+        tokens (list): Individual tokens in the text
+        spans (list): Individual entity spans and their start, end, label, kb_id and kb_url.
+        title (str / None): Document title set in Doc.user_data['title'].
+        """
+        per_token_info = []
+        # we must sort so that we can correctly describe when spans need to "stack"
+        # which is determined by their start token, then span length (longer spans on top),
+        # then break any remaining ties with the span label
+        spans = sorted(
+            spans,
+            key=lambda s: (
+                s["start_token"],
+                -(s["end_token"] - s["start_token"]),
+                s["label"],
+            ),
+        )
+        for s in spans:
+            # this is the vertical 'slot' that the span will be rendered in
+            # vertical_position = span_label_offset + (offset_step * (slot - 1))
+            s["render_slot"] = 0
+        for idx, token in enumerate(tokens):
+            # Identify if a token belongs to a Span (and which) and if it's a
+            # start token of said Span. We'll use this for the final HTML render
+            token_markup: Dict[str, Any] = {}
+            token_markup["text"] = token
+            concurrent_spans = 0
+            entities = []
+            for span in spans:
+                ent = {}
+                if span["start_token"] <= idx < span["end_token"]:
+                    concurrent_spans += 1
+                    span_start = idx == span["start_token"]
+                    ent["label"] = span["label"]
+                    ent["is_start"] = span_start
+                    if span_start:
+                        # When the span starts, we need to know how many other
+                        # spans are on the 'span stack' and will be rendered.
+                        # This value becomes the vertical render slot for this entire span
+                        span["render_slot"] = concurrent_spans
+                    ent["render_slot"] = span["render_slot"]
+                    kb_id = span.get("kb_id", "")
+                    kb_url = span.get("kb_url", "#")
+                    ent["kb_link"] = (
+                        TPL_KB_LINK.format(kb_id=kb_id, kb_url=kb_url) if kb_id else ""
+                    )
+                    entities.append(ent)
+                else:
+                    # We don't specifically need to do this since we loop
+                    # over tokens and spans sorted by their start_token,
+                    # so we'll never use a span again after the last token it appears in,
+                    # but if we were to use these spans again we'd want to make sure
+                    # this value was reset correctly.
+                    span["render_slot"] = 0
+            token_markup["entities"] = entities
+            per_token_info.append(token_markup)
+        markup = self._render_markup(per_token_info)
+        markup = TPL_SPANS.format(content=markup, dir=self.direction)
+        if title:
+            markup = TPL_TITLE.format(title=title) + markup
+        return markup
+
+    def _render_markup(self, per_token_info: List[Dict[str, Any]]) -> str:
+        """Render the markup from per-token information"""
+        markup = ""
+        for token in per_token_info:
+            entities = sorted(token["entities"], key=lambda d: d["render_slot"])
+            # Whitespace tokens disrupt the vertical space (no line height) so that the
+            # span indicators get misaligned. We don't render them as individual
+            # tokens anyway, so we'll just not display a span indicator either.
+            is_whitespace = token["text"].strip() == ""
+            if entities and not is_whitespace:
+                slices = self._get_span_slices(token["entities"])
+                starts = self._get_span_starts(token["entities"])
+                total_height = (
+                    self.top_offset
+                    + self.span_label_offset
+                    + (self.offset_step * (len(entities) - 1))
+                )
+                markup += self.span_template.format(
+                    text=escape_html(token["text"]),
+                    span_slices=slices,
+                    span_starts=starts,
+                    total_height=total_height,
+                )
+            else:
+                markup += escape_html(token["text"] + " ")
+        return markup
+
+    def _get_span_slices(self, entities: List[Dict]) -> str:
+        """Get the rendered markup of all Span slices"""
+        span_slices = []
+        for entity in entities:
+            # rather than iterate over multiples of offset_step, we use entity['render_slot']
+            # to determine the vertical position, since that tells where
+            # the span starts vertically so we can extend it horizontally,
+            # past other spans that might have already ended
+            color = self.colors.get(entity["label"].upper(), self.default_color)
+            top_offset = self.top_offset + (
+                self.offset_step * (entity["render_slot"] - 1)
+            )
+            span_slice = self.span_slice_template.format(
+                bg=color,
+                top_offset=top_offset,
+            )
+            span_slices.append(span_slice)
+        return "".join(span_slices)
+
+    def _get_span_starts(self, entities: List[Dict]) -> str:
+        """Get the rendered markup of all Span start tokens"""
+        span_starts = []
+        for entity in entities:
+            color = self.colors.get(entity["label"].upper(), self.default_color)
+            top_offset = self.top_offset + (
+                self.offset_step * (entity["render_slot"] - 1)
+            )
+            span_start = (
+                self.span_start_template.format(
+                    bg=color,
+                    top_offset=top_offset,
+                    label=entity["label"],
+                    kb_link=entity["kb_link"],
+                )
+                if entity["is_start"]
+                else ""
+            )
+            span_starts.append(span_start)
+        return "".join(span_starts)
+
+
 class DependencyRenderer:
     """Render dependency parses as SVGs."""
 
@@ -105,7 +339,7 @@ class DependencyRenderer:
         RETURNS (str): Rendered SVG markup.
         """
         self.levels = self.get_levels(arcs)
-        self.highest_level = len(self.levels)
+        self.highest_level = max(self.levels.values(), default=0)
         self.offset_y = self.distance / 2 * self.highest_level + self.arrow_stroke
         self.width = self.offset_x + len(words) * self.distance
         self.height = self.offset_y + 3 * self.word_spacing
@@ -165,7 +399,7 @@ class DependencyRenderer:
         if start < 0 or end < 0:
             error_args = dict(start=start, end=end, label=label, dir=direction)
             raise ValueError(Errors.E157.format(**error_args))
-        level = self.levels.index(end - start) + 1
+        level = self.levels[(start, end, label)]
         x_start = self.offset_x + start * self.distance + self.arrow_spacing
         if self.direction == "rtl":
             x_start = self.width - x_start
@@ -181,7 +415,7 @@ class DependencyRenderer:
         y_curve = self.offset_y - level * self.distance / 2
         if self.compact:
             y_curve = self.offset_y - level * self.distance / 6
-        if y_curve == 0 and len(self.levels) > 5:
+        if y_curve == 0 and max(self.levels.values(), default=0) > 5:
             y_curve = -self.distance
         arrowhead = self.get_arrowhead(direction, x_start, y, x_end)
         arc = self.get_arc(x_start, y, y_curve, x_end)
@@ -225,15 +459,23 @@ class DependencyRenderer:
             p1, p2, p3 = (end, end + self.arrow_width - 2, end - self.arrow_width + 2)
         return f"M{p1},{y + 2} L{p2},{y - self.arrow_width} {p3},{y - self.arrow_width}"
 
-    def get_levels(self, arcs: List[Dict[str, Any]]) -> List[int]:
+    def get_levels(self, arcs: List[Dict[str, Any]]) -> Dict[Tuple[int, int, str], int]:
         """Calculate available arc height "levels".
         Used to calculate arrow heights dynamically and without wasting space.
 
         args (list): Individual arcs and their start, end, direction and label.
-        RETURNS (list): Arc levels sorted from lowest to highest.
+        RETURNS (dict): Arc levels keyed by (start, end, label).
         """
-        levels = set(map(lambda arc: arc["end"] - arc["start"], arcs))
-        return sorted(list(levels))
+        arcs = [dict(t) for t in {tuple(sorted(arc.items())) for arc in arcs}]
+        length = max([arc["end"] for arc in arcs], default=0)
+        max_level = [0] * length
+        levels = {}
+        for arc in sorted(arcs, key=lambda arc: arc["end"] - arc["start"]):
+            level = max(max_level[arc["start"] : arc["end"]]) + 1
+            for i in range(arc["start"], arc["end"]):
+                max_level[i] = level
+            levels[(arc["start"], arc["end"], arc["label"])] = level
+        return levels
 
 
 class EntityRenderer:
@@ -242,7 +484,7 @@ class EntityRenderer:
     style = "ent"
 
     def __init__(self, options: Dict[str, Any] = {}) -> None:
-        """Initialise dependency renderer.
+        """Initialise entity renderer.
 
         options (dict): Visualiser-specific options (colors, ents)
         """
@@ -281,7 +523,7 @@ class EntityRenderer:
         parsed (list): Dependency parses to render.
         page (bool): Render parses wrapped as full HTML page.
         minify (bool): Minify HTML markup.
-        RETURNS (str): Rendered HTML markup.
+        RETURNS (str): Rendered SVG or HTML markup.
         """
         rendered = []
         for i, p in enumerate(parsed):

spacy/displacy/templates.py

@@ -62,6 +62,55 @@ TPL_ENT_RTL = """
 </mark>
 """
 
+TPL_SPANS = """
+<div class="spans" style="line-height: 2.5; direction: {dir}">{content}</div>
+"""
+
+TPL_SPAN = """
+<span style="font-weight: bold; display: inline-block; position: relative; height: {total_height}px;">
+    {text}
+    {span_slices}
+    {span_starts}
+</span>
+"""
+
+TPL_SPAN_SLICE = """
+<span style="background: {bg}; top: {top_offset}px; height: 4px; left: -1px; width: calc(100% + 2px); position: absolute;">
+</span>
+"""
+
+
+TPL_SPAN_START = """
+<span style="background: {bg}; top: {top_offset}px; height: 4px; border-top-left-radius: 3px; border-bottom-left-radius: 3px; left: -1px; width: calc(100% + 2px); position: absolute;">
+    <span style="background: {bg}; z-index: 10; color: #000; top: -0.5em; padding: 2px 3px; position: absolute; font-size: 0.6em; font-weight: bold; line-height: 1; border-radius: 3px">
+        {label}{kb_link}
+    </span>
+</span>
+
+"""
+
+TPL_SPAN_RTL = """
+<span style="font-weight: bold; display: inline-block; position: relative;">
+    {text}
+    {span_slices}
+    {span_starts}
+</span>
+"""
+
+TPL_SPAN_SLICE_RTL = """
+<span style="background: {bg}; top: {top_offset}px; height: 4px; left: -1px; width: calc(100% + 2px); position: absolute;">
+</span>
+"""
+
+TPL_SPAN_START_RTL = """
+<span style="background: {bg}; top: {top_offset}px; height: 4px; border-top-left-radius: 3px; border-bottom-left-radius: 3px; left: -1px; width: calc(100% + 2px); position: absolute;">
+    <span style="background: {bg}; z-index: 10; color: #000; top: -0.5em; padding: 2px 3px; position: absolute; font-size: 0.6em; font-weight: bold; line-height: 1; border-radius: 3px">
+        {label}{kb_link}
+    </span>
+</span>
+"""
+
+
 # Important: this needs to start with a space!
 TPL_KB_LINK = """
  <a style="text-decoration: none; color: inherit; font-weight: normal" href="{kb_url}">{kb_id}</a>

spacy/errors.py

@@ -1,4 +1,7 @@
 import warnings
+from typing import Literal
+
+from . import about
 
 
 class ErrorsWithCodes(type):
@@ -15,8 +18,8 @@ def setup_default_warnings():
     filter_warning("ignore", error_msg="numpy.dtype size changed")  # noqa
     filter_warning("ignore", error_msg="numpy.ufunc size changed")  # noqa
 
-    # warn about entity_ruler & matcher having no patterns only once
-    for pipe in ["matcher", "entity_ruler"]:
+    # warn about entity_ruler, span_ruler & matcher having no patterns only once
+    for pipe in ["matcher", "entity_ruler", "span_ruler"]:
         filter_warning("once", error_msg=Warnings.W036.format(name=pipe))
 
     # warn once about lemmatizer without required POS
@@ -26,7 +29,10 @@ def setup_default_warnings():
     filter_warning("once", error_msg="[W114]")
 
 
-def filter_warning(action: str, error_msg: str):
+def filter_warning(
+    action: Literal["default", "error", "ignore", "always", "module", "once"],
+    error_msg: str,
+):
     """Customize how spaCy should handle a certain warning.
 
     error_msg (str): e.g. "W006", or a full error message
@@ -78,7 +84,7 @@ class Warnings(metaclass=ErrorsWithCodes):
             "ignoring the duplicate entry.")
     W021 = ("Unexpected hash collision in PhraseMatcher. Matches may be "
             "incorrect. Modify PhraseMatcher._terminal_hash to fix.")
-    W024 = ("Entity '{entity}' - Alias '{alias}' combination already exists in "
+    W024 = ("Entity '{entity}' - alias '{alias}' combination already exists in "
             "the Knowledge Base.")
     W026 = ("Unable to set all sentence boundaries from dependency parses. If "
             "you are constructing a parse tree incrementally by setting "
@@ -99,13 +105,14 @@ class Warnings(metaclass=ErrorsWithCodes):
             "table. This may degrade the performance of the model to some "
             "degree. If this is intentional or the language you're using "
             "doesn't have a normalization table, please ignore this warning. "
-            "If this is surprising, make sure you have the spacy-lookups-data "
-            "package installed and load the table in your config. The "
-            "languages with lexeme normalization tables are currently: "
-            "{langs}\n\nLoad the table in your config with:\n\n"
+            "If this is surprising, make sure you are loading the table in "
+            "your config. The languages with lexeme normalization tables are "
+            "currently: {langs}\n\nAn example of how to load a table in "
+            "your config :\n\n"
             "[initialize.lookups]\n"
-            "@misc = \"spacy.LookupsDataLoader.v1\"\n"
+            "@misc = \"spacy.LookupsDataLoaderFromURL.v1\"\n"
             "lang = ${{nlp.lang}}\n"
+             f'url = "{about.__lookups_url__}"\n'
             "tables = [\"lexeme_norm\"]\n")
     W035 = ("Discarding subpattern '{pattern}' due to an unrecognized "
             "attribute or operator.")
@@ -127,13 +134,6 @@ class Warnings(metaclass=ErrorsWithCodes):
             "and make it independent. For example, `replace_listeners = "
             "[\"model.tok2vec\"]` See the documentation for details: "
             "https://spacy.io/usage/training#config-components-listeners")
-    W088 = ("The pipeline component {name} implements a `begin_training` "
-            "method, which won't be called by spaCy. As of v3.0, `begin_training` "
-            "has been renamed to `initialize`, so you likely want to rename the "
-            "component method. See the documentation for details: "
-            "https://spacy.io/api/language#initialize")
-    W089 = ("As of spaCy v3.0, the `nlp.begin_training` method has been renamed "
-            "to `nlp.initialize`.")
     W090 = ("Could not locate any {format} files in path '{path}'.")
     W091 = ("Could not clean/remove the temp directory at {dir}: {msg}.")
     W092 = ("Ignoring annotations for sentence starts, as dependency heads are set.")
@@ -192,6 +192,34 @@ class Warnings(metaclass=ErrorsWithCodes):
     W115 = ("Skipping {method}: the floret vector table cannot be modified. "
             "Vectors are calculated from character ngrams.")
     W116 = ("Unable to clean attribute '{attr}'.")
+    W117 = ("No spans to visualize found in Doc object with spans_key: '{spans_key}'. If this is "
+            "surprising to you, make sure the Doc was processed using a model "
+            "that supports span categorization, and check the `doc.spans[spans_key]` "
+            "property manually if necessary.\n\nAvailable keys: {keys}")
+    W118 = ("Term '{term}' not found in glossary. It may however be explained in documentation "
+            "for the corpora used to train the language. Please check "
+            "`nlp.meta[\"sources\"]` for any relevant links.")
+    W119 = ("Overriding pipe name in `config` is not supported. Ignoring override '{name_in_config}'.")
+    W120 = ("Unable to load all spans in Doc.spans: more than one span group "
+            "with the name '{group_name}' was found in the saved spans data. "
+            "Only the last span group will be loaded under "
+            "Doc.spans['{group_name}']. Skipping span group with values: "
+            "{group_values}")
+    W121 = ("Attempting to trace non-existent method '{method}' in pipe '{pipe}'")
+    W122 = ("Couldn't trace method '{method}' in pipe '{pipe}'. This can happen if the pipe class "
+            "is a Cython extension type.")
+    W123 = ("Argument `enable` with value {enable} does not contain all values specified in the config option "
+            "`enabled` ({enabled}). Be aware that this might affect other components in your pipeline.")
+    W124 = ("{host}:{port} is already in use, using the nearest available port {serve_port} as an alternative.")
+    W125 = ("The StaticVectors key_attr is no longer used. To set a custom "
+            "key attribute for vectors, configure it through Vectors(attr=) or "
+            "'spacy init vectors --attr'")
+
+    # v4 warning strings
+    W400 = ("`use_upper=False` is ignored, the upper layer is always enabled")
+    W401 = ("`incl_prior is True`, but the selected knowledge base type {kb_type} doesn't support prior probability "
+            "lookups so this setting will be ignored. If your KB does support prior probability lookups, make sure "
+            "to return `True` in `.supports_prior_probs`.")
 
 
 class Errors(metaclass=ErrorsWithCodes):
@@ -210,8 +238,9 @@ class Errors(metaclass=ErrorsWithCodes):
             "initialized component.")
     E004 = ("Can't set up pipeline component: a factory for '{name}' already "
             "exists. Existing factory: {func}. New factory: {new_func}")
-    E005 = ("Pipeline component '{name}' returned None. If you're using a "
-            "custom component, maybe you forgot to return the processed Doc?")
+    E005 = ("Pipeline component '{name}' returned {returned_type} instead of a "
+            "Doc. If you're using a custom component, maybe you forgot to "
+            "return the processed Doc?")
     E006 = ("Invalid constraints for adding pipeline component. You can only "
             "set one of the following: before (component name or index), "
             "after (component name or index), first (True) or last (True). "
@@ -227,9 +256,7 @@ class Errors(metaclass=ErrorsWithCodes):
             "https://spacy.io/usage/models")
     E011 = ("Unknown operator: '{op}'. Options: {opts}")
     E012 = ("Cannot add pattern for zero tokens to matcher.\nKey: {key}")
-    E016 = ("MultitaskObjective target should be function or one of: dep, "
-            "tag, ent, dep_tag_offset, ent_tag.")
-    E017 = ("Can only add unicode or bytes. Got type: {value_type}")
+    E017 = ("Can only add 'str' inputs to StringStore. Got type: {value_type}")
     E018 = ("Can't retrieve string for hash '{hash_value}'. This usually "
             "refers to an issue with the `Vocab` or `StringStore`.")
     E019 = ("Can't create transition with unknown action ID: {action}. Action "
@@ -322,6 +349,11 @@ class Errors(metaclass=ErrorsWithCodes):
             "clear the existing vectors and resize the table.")
     E074 = ("Error interpreting compiled match pattern: patterns are expected "
             "to end with the attribute {attr}. Got: {bad_attr}.")
+    E079 = ("Error computing states in beam: number of predicted beams "
+            "({pbeams}) does not equal number of gold beams ({gbeams}).")
+    E080 = ("Duplicate state found in beam: {key}.")
+    E081 = ("Error getting gradient in beam: number of histories ({n_hist}) "
+            "does not equal number of losses ({losses}).")
     E082 = ("Error deprojectivizing parse: number of heads ({n_heads}), "
             "projective heads ({n_proj_heads}) and labels ({n_labels}) do not "
             "match.")
@@ -369,7 +401,7 @@ class Errors(metaclass=ErrorsWithCodes):
             "consider using doc.spans instead.")
     E106 = ("Can't find `doc._.{attr}` attribute specified in the underscore "
             "settings: {opts}")
-    E107 = ("Value of `doc._.{attr}` is not JSON-serializable: {value}")
+    E107 = ("Value of custom attribute `{attr}` is not JSON-serializable: {value}")
     E109 = ("Component '{name}' could not be run. Did you forget to "
             "call `initialize()`?")
     E110 = ("Invalid displaCy render wrapper. Expected callable, got: {obj}")
@@ -415,8 +447,7 @@ class Errors(metaclass=ErrorsWithCodes):
     E133 = ("The sum of prior probabilities for alias '{alias}' should not "
             "exceed 1, but found {sum}.")
     E134 = ("Entity '{entity}' is not defined in the Knowledge Base.")
-    E139 = ("Knowledge base for component '{name}' is empty. Use the methods "
-            "`kb.add_entity` and `kb.add_alias` to add entries.")
+    E139 = ("Knowledge base for component '{name}' is empty.")
     E140 = ("The list of entities, prior probabilities and entity vectors "
             "should be of equal length.")
     E141 = ("Entity vectors should be of length {required} instead of the "
@@ -437,13 +468,13 @@ class Errors(metaclass=ErrorsWithCodes):
             "same, but found '{nlp}' and '{vocab}' respectively.")
     E152 = ("The attribute {attr} is not supported for token patterns. "
             "Please use the option `validate=True` with the Matcher, PhraseMatcher, "
-            "or EntityRuler for more details.")
+            "SpanRuler or AttributeRuler for more details.")
     E153 = ("The value type {vtype} is not supported for token patterns. "
             "Please use the option validate=True with Matcher, PhraseMatcher, "
-            "or EntityRuler for more details.")
+            "SpanRuler or AttributeRuler for more details.")
     E154 = ("One of the attributes or values is not supported for token "
             "patterns. Please use the option `validate=True` with the Matcher, "
-            "PhraseMatcher, or EntityRuler for more details.")
+            "PhraseMatcher, or SpanRuler for more details.")
     E155 = ("The pipeline needs to include a {pipe} in order to use "
             "Matcher or PhraseMatcher with the attribute {attr}. "
             "Try using `nlp()` instead of `nlp.make_doc()` or `list(nlp.pipe())` "
@@ -467,7 +498,7 @@ class Errors(metaclass=ErrorsWithCodes):
             "Current DocBin: {current}\nOther DocBin: {other}")
     E169 = ("Can't find module: {module}")
     E170 = ("Cannot apply transition {name}: invalid for the current state.")
-    E171 = ("Matcher.add received invalid 'on_match' callback argument: expected "
+    E171 = ("{name}.add received invalid 'on_match' callback argument: expected "
             "callable or None, but got: {arg_type}")
     E175 = ("Can't remove rule for unknown match pattern ID: {key}")
     E176 = ("Alias '{alias}' is not defined in the Knowledge Base.")
@@ -483,7 +514,7 @@ class Errors(metaclass=ErrorsWithCodes):
             "components, since spans are only views of the Doc. Use Doc and "
             "Token attributes (or custom extension attributes) only and remove "
             "the following: {attrs}")
-    E181 = ("Received invalid attributes for unkown object {obj}: {attrs}. "
+    E181 = ("Received invalid attributes for unknown object {obj}: {attrs}. "
             "Only Doc and Token attributes are supported.")
     E182 = ("Received invalid attribute declaration: {attr}\nDid you forget "
             "to define the attribute? For example: `{attr}.???`")
@@ -515,15 +546,30 @@ class Errors(metaclass=ErrorsWithCodes):
     E198 = ("Unable to return {n} most similar vectors for the current vectors "
             "table, which contains {n_rows} vectors.")
     E199 = ("Unable to merge 0-length span at `doc[{start}:{end}]`.")
-    E200 = ("Can't yet set {attr} from Span. Vote for this feature on the "
-            "issue tracker: http://github.com/explosion/spaCy/issues")
+    E200 = ("Can't set {attr} from Span.")
     E202 = ("Unsupported {name} mode '{mode}'. Supported modes: {modes}.")
+    E203 = ("If the {name} embedding layer is not updated "
+            "during training, make sure to include it in 'annotating components'")
 
     # New errors added in v3.x
+    E850 = ("The PretrainVectors objective currently only supports default or "
+            "floret vectors, not {mode} vectors.")
+    E851 = ("The 'textcat' component labels should only have values of 0 or 1, "
+            "but found value of '{val}'.")
+    E852 = ("The tar file pulled from the remote attempted an unsafe path "
+            "traversal.")
+    E853 = ("Unsupported component factory name '{name}'. The character '.' is "
+            "not permitted in factory names.")
+    E854 = ("Unable to set doc.ents. Check that the 'ents_filter' does not "
+            "permit overlapping spans.")
+    E855 = ("Invalid {obj}: {obj} is not from the same doc.")
+    E856 = ("Error accessing span at position {i}: out of bounds in span group "
+            "of length {length}.")
+    E857 = ("Entry '{name}' not found in edit tree lemmatizer labels.")
     E858 = ("The {mode} vector table does not support this operation. "
             "{alternative}")
     E859 = ("The floret vector table cannot be modified.")
-    E860 = ("Can't truncate fasttext-bloom vectors.")
+    E860 = ("Can't truncate floret vectors.")
     E861 = ("No 'keys' should be provided when initializing floret vectors "
             "with 'minn' and 'maxn'.")
     E862 = ("'hash_count' must be between 1-4 for floret vectors.")
@@ -566,9 +612,6 @@ class Errors(metaclass=ErrorsWithCodes):
     E879 = ("Unexpected type for 'spans' data. Provide a dictionary mapping keys to "
             "a list of spans, with each span represented by a tuple (start_char, end_char). "
             "The tuple can be optionally extended with a label and a KB ID.")
-    E880 = ("The 'wandb' library could not be found - did you install it? "
-            "Alternatively, specify the 'ConsoleLogger' in the 'training.logger' "
-            "config section, instead of the 'WandbLogger'.")
     E884 = ("The pipeline could not be initialized because the vectors "
             "could not be found at '{vectors}'. If your pipeline was already "
             "initialized/trained before, call 'resume_training' instead of 'initialize', "
@@ -682,11 +725,11 @@ class Errors(metaclass=ErrorsWithCodes):
             "need to modify the pipeline, use the built-in methods like "
             "`nlp.add_pipe`, `nlp.remove_pipe`, `nlp.disable_pipe` or "
             "`nlp.enable_pipe` instead.")
-    E927 = ("Can't write to frozen list Maybe you're trying to modify a computed "
+    E927 = ("Can't write to frozen list. Maybe you're trying to modify a computed "
             "property or default function argument?")
-    E928 = ("A KnowledgeBase can only be serialized to/from from a directory, "
+    E928 = ("An InMemoryLookupKB can only be serialized to/from from a directory, "
             "but the provided argument {loc} points to a file.")
-    E929 = ("Couldn't read KnowledgeBase from {loc}. The path does not seem to exist.")
+    E929 = ("Couldn't read InMemoryLookupKB from {loc}. The path does not seem to exist.")
     E930 = ("Received invalid get_examples callback in `{method}`. "
             "Expected function that returns an iterable of Example objects but "
             "got: {obj}")
@@ -694,13 +737,6 @@ class Errors(metaclass=ErrorsWithCodes):
             "method in component '{name}'. If you want to use this "
             "method, make sure it's overwritten on the subclass.")
     E940 = ("Found NaN values in scores.")
-    E941 = ("Can't find model '{name}'. It looks like you're trying to load a "
-            "model from a shortcut, which is obsolete as of spaCy v3.0. To "
-            "load the model, use its full name instead:\n\n"
-            "nlp = spacy.load(\"{full}\")\n\nFor more details on the available "
-            "models, see the models directory: https://spacy.io/models. If you "
-            "want to create a blank model, use spacy.blank: "
-            "nlp = spacy.blank(\"{name}\")")
     E942 = ("Executing `after_{name}` callback failed. Expected the function to "
             "return an initialized nlp object but got: {value}. Maybe "
             "you forgot to return the modified object in your function?")
@@ -714,7 +750,7 @@ class Errors(metaclass=ErrorsWithCodes):
             "loaded nlp object, but got: {source}")
     E947 = ("`Matcher.add` received invalid `greedy` argument: expected "
             "a string value from {expected} but got: '{arg}'")
-    E948 = ("`Matcher.add` received invalid 'patterns' argument: expected "
+    E948 = ("`{name}.add` received invalid 'patterns' argument: expected "
             "a list, but got: {arg_type}")
     E949 = ("Unable to align tokens for the predicted and reference docs. It "
             "is only possible to align the docs when both texts are the same "
@@ -888,19 +924,83 @@ class Errors(metaclass=ErrorsWithCodes):
     E1021 = ("`pos` value \"{pp}\" is not a valid Universal Dependencies tag. "
              "Non-UD tags should use the `tag` property.")
     E1022 = ("Words must be of type str or int, but input is of type '{wtype}'")
-    E1023 = ("Couldn't read EntityRuler from the {path}. This file doesn't exist.")
-    E1024 = ("A pattern with ID \"{ent_id}\" is not present in EntityRuler patterns.")
-    
+    E1024 = ("A pattern with {attr_type} '{label}' is not present in "
+             "'{component}' patterns.")
+    E1025 = ("Cannot intify the value '{value}' as an IOB string. The only "
+             "supported values are: 'I', 'O', 'B' and ''")
+    E1026 = ("Edit tree has an invalid format:\n{errors}")
+    E1027 = ("AlignmentArray only supports slicing with a step of 1.")
+    E1028 = ("AlignmentArray only supports indexing using an int or a slice.")
+    E1029 = ("Edit tree cannot be applied to form.")
+    E1030 = ("Edit tree identifier out of range.")
+    E1031 = ("Could not find gold transition - see logs above.")
+    E1032 = ("Span {var} {value} is out of bounds for {obj} with length {length}.")
+    E1033 = ("Dimension {name} invalid -- only nO, nF, nP")
+    E1034 = ("Node index {i} out of bounds ({length})")
+    E1035 = ("Token index {i} out of bounds ({length})")
+    E1036 = ("Cannot index into NoneNode")
+    E1037 = ("Invalid attribute value '{attr}'.")
+    E1038 = ("Invalid JSON input: {message}")
+    E1039 = ("The {obj} start or end annotations (start: {start}, end: {end}) "
+             "could not be aligned to token boundaries.")
+    E1040 = ("Doc.from_json requires all tokens to have the same attributes. "
+             "Some tokens do not contain annotation for: {partial_attrs}")
+    E1041 = ("Expected a string, Doc, or bytes as input, but got: {type}")
+    E1042 = ("`enable={enable}` and `disable={disable}` are inconsistent with each other.\nIf you only passed "
+             "one of `enable` or `disable`, the other argument is specified in your pipeline's configuration.\nIn that "
+             "case pass an empty list for the previously not specified argument to avoid this error.")
+    E1043 = ("Expected None or a value in range [{range_start}, {range_end}] for entity linker threshold, but got "
+             "{value}.")
+    E1044 = ("Expected `candidates_batch_size` to be >= 1, but got: {value}")
+    E1045 = ("Encountered {parent} subclass without `{parent}.{method}` "
+             "method in '{name}'. If you want to use this method, make "
+             "sure it's overwritten on the subclass.")
+    E1046 = ("{cls_name} is an abstract class and cannot be instantiated. If you are looking for spaCy's default "
+             "knowledge base, use `InMemoryLookupKB`.")
+    E1047 = ("`find_threshold()` only supports components with a `scorer` attribute.")
+    E1048 = ("Got '{unexpected}' as console progress bar type, but expected one of the following: {expected}")
+    E1049 = ("No available port found for displaCy on host {host}. Please specify an available port "
+             "with `displacy.serve(doc, port=port)`")
+    E1050 = ("Port {port} is already in use. Please specify an available port with `displacy.serve(doc, port=port)` "
+             "or use `auto_select_port=True` to pick an available port automatically.")
+    E1051 = ("'allow_overlap' can only be False when max_positive is 1, but found 'max_positive': {max_positive}.")
+    E1052 = ("Unable to copy spans: the character offsets for the span at "
+             "index {i} in the span group do not align with the tokenization "
+             "in the target doc.")
+    E1053 = ("Both 'min_length' and 'max_length' should be larger than 0, but found"
+             " 'min_length': {min_length}, 'max_length': {max_length}")
+    E1054 = ("The text, including whitespace, must match between reference and "
+             "predicted docs when training {component}.")
+
+    # v4 error strings
+    E4000 = ("Expected a Doc as input, but got: '{type}'")
+    E4001 = ("Expected input to be one of the following types: ({expected_types}), "
+             "but got '{received_type}'")
+    E4002 = ("Pipe '{name}' requires a teacher pipe for distillation.")
+    E4003 = ("Training examples for distillation must have the exact same tokens in the "
+             "reference and predicted docs.")
+    E4004 = ("Backprop is not supported when is_train is not set.")
+    E4005 = ("EntityLinker_v1 is not supported in spaCy v4. Update your configuration.")
+    E4006 = ("Expected `entity_id` to be of type {exp_type}, but is of type {found_type}.")
+    E4007 = ("Span {var} {value} must be {op} Span {existing_var} "
+             "{existing_value}.")
+    E4008 = ("Span {pos}_char {value} does not correspond to a token {pos}.")
+    E4009 = ("The '{attr}' parameter should be 'None' or 'True', but found '{value}'.")
+    E4010 = ("Required lemmatizer table(s) {missing_tables} not found in "
+             "[initialize] or in registered lookups (spacy-lookups-data). An "
+             "example for how to load lemmatizer tables in [initialize]:\n\n"
+             "[initialize.components]\n\n"
+             "[initialize.components.{pipe_name}]\n\n"
+             "[initialize.components.{pipe_name}.lookups]\n"
+             '@misc = "spacy.LookupsDataLoaderFromURL.v1"\n'
+             "lang = ${{nlp.lang}}\n"
+             f'url = "{about.__lookups_url__}"\n'
+             "tables = {tables}\n"
+             "# or required tables only: tables = {required_tables}\n")
+    E4011 = ("Server error ({status_code}), couldn't fetch {url}")
 
 
-# Deprecated model shortcuts, only used in errors and warnings
-OLD_MODEL_SHORTCUTS = {
-    "en": "en_core_web_sm", "de": "de_core_news_sm", "es": "es_core_news_sm",
-    "pt": "pt_core_news_sm", "fr": "fr_core_news_sm", "it": "it_core_news_sm",
-    "nl": "nl_core_news_sm", "el": "el_core_news_sm", "nb": "nb_core_news_sm",
-    "lt": "lt_core_news_sm", "xx": "xx_ent_wiki_sm"
-}
-
+RENAMED_LANGUAGE_CODES = {"xx": "mul", "is": "isl"}
 
 # fmt: on
 

spacy/glossary.py

@@ -1,3 +1,8 @@
+import warnings
+
+from .errors import Warnings
+
+
 def explain(term):
     """Get a description for a given POS tag, dependency label or entity type.
 
@@ -11,6 +16,8 @@ def explain(term):
     """
     if term in GLOSSARY:
         return GLOSSARY[term]
+    else:
+        warnings.warn(Warnings.W118.format(term=term))
 
 
 GLOSSARY = {
@@ -267,6 +274,7 @@ GLOSSARY = {
     "relcl": "relative clause modifier",
     "reparandum": "overridden disfluency",
     "root": "root",
+    "ROOT": "root",
     "vocative": "vocative",
     "xcomp": "open clausal complement",
     # Dependency labels (German)
@@ -310,7 +318,6 @@ GLOSSARY = {
     "re": "repeated element",
     "rs": "reported speech",
     "sb": "subject",
-    "sb": "subject",
     "sbp": "passivized subject (PP)",
     "sp": "subject or predicate",
     "svp": "separable verb prefix",

spacy/kb/__init__.py

@@ -0,0 +1,5 @@
+from .candidate import Candidate, InMemoryCandidate
+from .kb import KnowledgeBase
+from .kb_in_memory import InMemoryLookupKB
+
+__all__ = ["KnowledgeBase", "InMemoryLookupKB", "Candidate", "InMemoryCandidate"]

spacy/kb/candidate.pxd

@@ -0,0 +1,17 @@
+from libcpp.vector cimport vector
+
+from ..typedefs cimport hash_t
+from .kb_in_memory cimport InMemoryLookupKB
+
+
+cdef class Candidate:
+    pass
+
+
+cdef class InMemoryCandidate(Candidate):
+    cdef readonly hash_t _entity_hash
+    cdef readonly hash_t _alias_hash
+    cdef vector[float] _entity_vector
+    cdef float _prior_prob
+    cdef readonly InMemoryLookupKB _kb
+    cdef float _entity_freq

spacy/kb/candidate.pyx

@@ -0,0 +1,98 @@
+# cython: infer_types=True, profile=True
+
+from .kb_in_memory cimport InMemoryLookupKB
+
+from ..errors import Errors
+
+
+cdef class Candidate:
+    """A `Candidate` object refers to a textual mention that may or may not be resolved
+    to a specific entity from a Knowledge Base. This will be used as input for the entity linking
+    algorithm which will disambiguate the various candidates to the correct one.
+    Each candidate, which represents a possible link between one textual mention and one entity in the knowledge base,
+    is assigned a certain prior probability.
+
+    DOCS: https://spacy.io/api/kb/#candidate-init
+    """
+
+    def __init__(self):
+        # Make sure abstract Candidate is not instantiated.
+        if self.__class__ == Candidate:
+            raise TypeError(
+                Errors.E1046.format(cls_name=self.__class__.__name__)
+            )
+
+    @property
+    def entity_id(self) -> int:
+        """RETURNS (int): Numerical representation of entity ID (if entity ID is numerical, this is just the entity ID,
+        otherwise the hash of the entity ID string)."""
+        raise NotImplementedError
+
+    @property
+    def entity_id_(self) -> str:
+        """RETURNS (str): String representation of entity ID."""
+        raise NotImplementedError
+
+    @property
+    def entity_vector(self) -> vector[float]:
+        """RETURNS (vector[float]): Entity vector."""
+        raise NotImplementedError
+
+
+cdef class InMemoryCandidate(Candidate):
+    """Candidate for InMemoryLookupKB."""
+
+    def __init__(
+        self,
+        kb: InMemoryLookupKB,
+        entity_hash: int,
+        alias_hash: int,
+        entity_vector: vector[float],
+        prior_prob: float,
+        entity_freq: float
+    ):
+        """
+        kb (InMemoryLookupKB]): InMemoryLookupKB instance.
+        entity_id (int): Entity ID as hash that can be looked up with InMemoryKB.vocab.strings.__getitem__().
+        entity_freq (int): Entity frequency in KB corpus.
+        entity_vector (List[float]): Entity embedding.
+        alias_hash (int): Alias hash.
+        prior_prob (float): Prior probability of entity for this alias. I. e. the probability that, independent of
+            the context, this alias - which matches one of this entity's aliases - resolves to one this entity.
+        """
+        super().__init__()
+
+        self._entity_hash = entity_hash
+        self._entity_vector = entity_vector
+        self._prior_prob = prior_prob
+        self._kb = kb
+        self._alias_hash = alias_hash
+        self._entity_freq = entity_freq
+
+    @property
+    def entity_id(self) -> int:
+        return self._entity_hash
+
+    @property
+    def entity_vector(self) -> vector[float]:
+        return self._entity_vector
+
+    @property
+    def prior_prob(self) -> float:
+        """RETURNS (float): Prior probability that this alias, which matches one of this entity's synonyms, resolves to
+        this entity."""
+        return self._prior_prob
+
+    @property
+    def alias(self) -> str:
+        """RETURNS (str): Alias."""
+        return self._kb.vocab.strings[self._alias_hash]
+
+    @property
+    def entity_id_(self) -> str:
+        return self._kb.vocab.strings[self._entity_hash]
+
+    @property
+    def entity_freq(self) -> float:
+        """RETURNS (float): Entity frequency in KB corpus."""
+        return self._entity_freq

spacy/kb/kb.pxd

@@ -0,0 +1,12 @@
+"""Knowledge-base for entity or concept linking."""
+
+from cymem.cymem cimport Pool
+from libc.stdint cimport int64_t
+
+from ..vocab cimport Vocab
+
+
+cdef class KnowledgeBase:
+    cdef Pool mem
+    cdef readonly Vocab vocab
+    cdef readonly int64_t entity_vector_length

spacy/kb/kb.pyx

@@ -0,0 +1,137 @@
+# cython: infer_types=True, profile=True
+
+from pathlib import Path
+from typing import Iterable, Tuple, Union
+
+from cymem.cymem cimport Pool
+
+from ..errors import Errors
+from ..tokens import Span, SpanGroup
+from ..util import SimpleFrozenList
+from .candidate import Candidate
+
+
+cdef class KnowledgeBase:
+    """A `KnowledgeBase` instance stores unique identifiers for entities and
+    their textual aliases, to support entity linking of named entities to
+    real-world concepts.
+    This is an abstract class and requires its operations to be implemented.
+
+    DOCS: https://spacy.io/api/kb
+    """
+
+    def __init__(self, vocab: Vocab, entity_vector_length: int):
+        """Create a KnowledgeBase."""
+        # Make sure abstract KB is not instantiated.
+        if self.__class__ == KnowledgeBase:
+            raise TypeError(
+                Errors.E1046.format(cls_name=self.__class__.__name__)
+            )
+
+        self.vocab = vocab
+        self.entity_vector_length = entity_vector_length
+        self.mem = Pool()
+
+    def get_candidates_batch(
+            self, mentions: SpanGroup
+    ) -> Iterable[Iterable[Candidate]]:
+        """
+        Return candidate entities for a specified Span mention. Each candidate defines at least the entity and the
+        entity's embedding vector. Depending on the KB implementation, further properties - such as the prior
+        probability of the specified mention text resolving to that entity - might be included.
+        If no candidates are found for a given mention, an empty list is returned.
+        mentions (SpanGroup): Mentions for which to get candidates.
+        RETURNS (Iterable[Iterable[Candidate]]): Identified candidates.
+        """
+        return [self.get_candidates(span) for span in mentions]
+
+    def get_candidates(self, mention: Span) -> Iterable[Candidate]:
+        """
+        Return candidate entities for a specific mention. Each candidate defines at least the entity and the
+        entity's embedding vector. Depending on the KB implementation, further properties - such as the prior
+        probability of the specified mention text resolving to that entity - might be included.
+        If no candidate is found for the given mention, an empty list is returned.
+        mention (Span): Mention for which to get candidates.
+        RETURNS (Iterable[Candidate]): Identified candidates.
+        """
+        raise NotImplementedError(
+            Errors.E1045.format(
+                parent="KnowledgeBase", method="get_candidates", name=self.__name__
+            )
+        )
+
+    def get_vectors(self, entities: Iterable[str]) -> Iterable[Iterable[float]]:
+        """
+        Return vectors for entities.
+        entity (str): Entity name/ID.
+        RETURNS (Iterable[Iterable[float]]): Vectors for specified entities.
+        """
+        return [self.get_vector(entity) for entity in entities]
+
+    def get_vector(self, str entity) -> Iterable[float]:
+        """
+        Return vector for entity.
+        entity (str): Entity name/ID.
+        RETURNS (Iterable[float]): Vector for specified entity.
+        """
+        raise NotImplementedError(
+            Errors.E1045.format(
+                parent="KnowledgeBase", method="get_vector", name=self.__name__
+            )
+        )
+
+    def to_bytes(self, **kwargs) -> bytes:
+        """Serialize the current state to a binary string.
+        RETURNS (bytes): Current state as binary string.
+        """
+        raise NotImplementedError(
+            Errors.E1045.format(
+                parent="KnowledgeBase", method="to_bytes", name=self.__name__
+            )
+        )
+
+    def from_bytes(self, bytes_data: bytes, *, exclude: Tuple[str] = tuple()):
+        """Load state from a binary string.
+        bytes_data (bytes): KB state.
+        exclude (Tuple[str]): Properties to exclude when restoring KB.
+        """
+        raise NotImplementedError(
+            Errors.E1045.format(
+                parent="KnowledgeBase", method="from_bytes", name=self.__name__
+            )
+        )
+
+    def to_disk(
+            self, path: Union[str, Path], exclude: Iterable[str] = SimpleFrozenList()
+    ) -> None:
+        """
+        Write KnowledgeBase content to disk.
+        path (Union[str, Path]): Target file path.
+        exclude (Iterable[str]): List of components to exclude.
+        """
+        raise NotImplementedError(
+            Errors.E1045.format(
+                parent="KnowledgeBase", method="to_disk", name=self.__name__
+            )
+        )
+
+    def from_disk(
+            self, path: Union[str, Path], exclude: Iterable[str] = SimpleFrozenList()
+    ) -> None:
+        """
+        Load KnowledgeBase content from disk.
+        path (Union[str, Path]): Target file path.
+        exclude (Iterable[str]): List of components to exclude.
+        """
+        raise NotImplementedError(
+            Errors.E1045.format(
+                parent="KnowledgeBase", method="from_disk", name=self.__name__
+            )
+        )
+
+    @property
+    def supports_prior_probs(self) -> bool:
+        """RETURNS (bool): Whether this KB type supports looking up prior probabilities for entity mentions."""
+        raise NotImplementedError(
+            Errors.E1045.format(parent="KnowledgeBase", method="supports_prior_probs", name=self.__name__)
+        )

spacy/kb/kb_in_memory.pxd

@@ -1,14 +1,12 @@
 """Knowledge-base for entity or concept linking."""
-from cymem.cymem cimport Pool
-from preshed.maps cimport PreshMap
-from libcpp.vector cimport vector
 from libc.stdint cimport int32_t, int64_t
 from libc.stdio cimport FILE
+from libcpp.vector cimport vector
+from preshed.maps cimport PreshMap
 
-from .vocab cimport Vocab
-from .typedefs cimport hash_t
-from .structs cimport KBEntryC, AliasC
-
+from ..structs cimport AliasC, KBEntryC
+from ..typedefs cimport hash_t
+from .kb cimport KnowledgeBase
 
 ctypedef vector[KBEntryC] entry_vec
 ctypedef vector[AliasC] alias_vec
@@ -16,21 +14,7 @@ ctypedef vector[float] float_vec
 ctypedef vector[float_vec] float_matrix
 
 
-# Object used by the Entity Linker that summarizes one entity-alias candidate combination.
-cdef class Candidate:
-    cdef readonly KnowledgeBase kb
-    cdef hash_t entity_hash
-    cdef float entity_freq
-    cdef vector[float] entity_vector
-    cdef hash_t alias_hash
-    cdef float prior_prob
-
-
-cdef class KnowledgeBase:
-    cdef Pool mem
-    cdef readonly Vocab vocab
-    cdef int64_t entity_vector_length
-
+cdef class InMemoryLookupKB(KnowledgeBase):
     # This maps 64bit keys (hash of unique entity string)
     # to 64bit values (position of the _KBEntryC struct in the _entries vector).
     # The PreshMap is pretty space efficient, as it uses open addressing. So
@@ -71,23 +55,28 @@ cdef class KnowledgeBase:
     # optional data, we can let users configure a DB as the backend for this.
     cdef object _features_table
 
-
     cdef inline int64_t c_add_vector(self, vector[float] entity_vector) nogil:
         """Add an entity vector to the vectors table."""
         cdef int64_t new_index = self._vectors_table.size()
         self._vectors_table.push_back(entity_vector)
         return new_index
 
-
-    cdef inline int64_t c_add_entity(self, hash_t entity_hash, float freq,
-                                     int32_t vector_index, int feats_row) nogil:
+    cdef inline int64_t c_add_entity(
+        self,
+        hash_t entity_hash,
+        float freq,
+        int32_t vector_index,
+        int feats_row
+    ) nogil:
         """Add an entry to the vector of entries.
-        After calling this method, make sure to update also the _entry_index using the return value"""
+        After calling this method, make sure to update also the _entry_index
+        using the return value"""
         # This is what we'll map the entity hash key to. It's where the entry will sit
         # in the vector of entries, so we can get it later.
         cdef int64_t new_index = self._entries.size()
 
-        # Avoid struct initializer to enable nogil, cf https://github.com/cython/cython/issues/1642
+        # Avoid struct initializer to enable nogil, cf.
+        # https://github.com/cython/cython/issues/1642
         cdef KBEntryC entry
         entry.entity_hash = entity_hash
         entry.vector_index = vector_index
@@ -97,11 +86,17 @@ cdef class KnowledgeBase:
         self._entries.push_back(entry)
         return new_index
 
-    cdef inline int64_t c_add_aliases(self, hash_t alias_hash, vector[int64_t] entry_indices, vector[float] probs) nogil:
-        """Connect a mention to a list of potential entities with their prior probabilities .
-        After calling this method, make sure to update also the _alias_index using the return value"""
-        # This is what we'll map the alias hash key to. It's where the alias will be defined
-        # in the vector of aliases.
+    cdef inline int64_t c_add_aliases(
+        self,
+        hash_t alias_hash,
+        vector[int64_t] entry_indices,
+        vector[float] probs
+    ) nogil:
+        """Connect a mention to a list of potential entities with their prior
+        probabilities. After calling this method, make sure to update also the
+        _alias_index using the return value"""
+        # This is what we'll map the alias hash key to. It's where the alias will be
+        # defined in the vector of aliases.
         cdef int64_t new_index = self._aliases_table.size()
 
         # Avoid struct initializer to enable nogil
@@ -114,8 +109,9 @@ cdef class KnowledgeBase:
 
     cdef inline void _create_empty_vectors(self, hash_t dummy_hash) nogil:
         """
-        Initializing the vectors and making sure the first element of each vector is a dummy,
-        because the PreshMap maps pointing to indices in these vectors can not contain 0 as value
+        Initializing the vectors and making sure the first element of each vector is a
+        dummy, because the PreshMap maps pointing to indices in these vectors can not
+        contain 0 as value.
         cf. https://github.com/explosion/preshed/issues/17
         """
         cdef int32_t dummy_value = 0
@@ -146,12 +142,18 @@ cdef class KnowledgeBase:
 cdef class Writer:
     cdef FILE* _fp
 
-    cdef int write_header(self, int64_t nr_entries, int64_t entity_vector_length) except -1
+    cdef int write_header(
+        self, int64_t nr_entries, int64_t entity_vector_length
+    ) except -1
     cdef int write_vector_element(self, float element) except -1
-    cdef int write_entry(self, hash_t entry_hash, float entry_freq, int32_t vector_index) except -1
+    cdef int write_entry(
+        self, hash_t entry_hash, float entry_freq, int32_t vector_index
+    ) except -1
 
     cdef int write_alias_length(self, int64_t alias_length) except -1
-    cdef int write_alias_header(self, hash_t alias_hash, int64_t candidate_length) except -1
+    cdef int write_alias_header(
+        self, hash_t alias_hash, int64_t candidate_length
+    ) except -1
     cdef int write_alias(self, int64_t entry_index, float prob) except -1
 
     cdef int _write(self, void* value, size_t size) except -1
@@ -159,12 +161,18 @@ cdef class Writer:
 cdef class Reader:
     cdef FILE* _fp
 
-    cdef int read_header(self, int64_t* nr_entries, int64_t* entity_vector_length) except -1
+    cdef int read_header(
+        self, int64_t* nr_entries, int64_t* entity_vector_length
+    ) except -1
     cdef int read_vector_element(self, float* element) except -1
-    cdef int read_entry(self, hash_t* entity_hash, float* freq, int32_t* vector_index) except -1
+    cdef int read_entry(
+        self, hash_t* entity_hash, float* freq, int32_t* vector_index
+    ) except -1
 
     cdef int read_alias_length(self, int64_t* alias_length) except -1
-    cdef int read_alias_header(self, hash_t* alias_hash, int64_t* candidate_length) except -1
+    cdef int read_alias_header(
+        self, hash_t* alias_hash, int64_t* candidate_length
+    ) except -1
     cdef int read_alias(self, int64_t* entry_index, float* prob) except -1
 
     cdef int _read(self, void* value, size_t size) except -1

spacy/kb/kb_in_memory.pyx

@@ -1,113 +1,59 @@
 # cython: infer_types=True, profile=True
-from typing import Iterator, Iterable, Callable, Dict, Any
+from typing import Any, Callable, Dict, Iterable
 
 import srsly
-from cymem.cymem cimport Pool
-from preshed.maps cimport PreshMap
+
 from cpython.exc cimport PyErr_SetFromErrno
-from libc.stdio cimport fopen, fclose, fread, fwrite, feof, fseek
 from libc.stdint cimport int32_t, int64_t
+from libc.stdio cimport fclose, feof, fopen, fread, fseek, fwrite
 from libcpp.vector cimport vector
+from preshed.maps cimport PreshMap
 
-from pathlib import Path
 import warnings
+from pathlib import Path
 
-from .typedefs cimport hash_t
-from .errors import Errors, Warnings
-from . import util
-from .util import SimpleFrozenList, ensure_path
+from ..tokens import Span
 
-cdef class Candidate:
-    """A `Candidate` object refers to a textual mention (`alias`) that may or may not be resolved
-    to a specific `entity` from a Knowledge Base. This will be used as input for the entity linking
-    algorithm which will disambiguate the various candidates to the correct one.
-    Each candidate (alias, entity) pair is assigned to a certain prior probability.
+from ..typedefs cimport hash_t
 
-    DOCS: https://spacy.io/api/kb/#candidate_init
-    """
+from .. import util
+from ..errors import Errors, Warnings
+from ..util import SimpleFrozenList, ensure_path
 
-    def __init__(self, KnowledgeBase kb, entity_hash, entity_freq, entity_vector, alias_hash, prior_prob):
-        self.kb = kb
-        self.entity_hash = entity_hash
-        self.entity_freq = entity_freq
-        self.entity_vector = entity_vector
-        self.alias_hash = alias_hash
-        self.prior_prob = prior_prob
+from ..vocab cimport Vocab
+from .kb cimport KnowledgeBase
 
-    @property
-    def entity(self):
-        """RETURNS (uint64): hash of the entity's KB ID/name"""
-        return self.entity_hash
-
-    @property
-    def entity_(self):
-        """RETURNS (str): ID/name of this entity in the KB"""
-        return self.kb.vocab.strings[self.entity_hash]
-
-    @property
-    def alias(self):
-        """RETURNS (uint64): hash of the alias"""
-        return self.alias_hash
-
-    @property
-    def alias_(self):
-        """RETURNS (str): ID of the original alias"""
-        return self.kb.vocab.strings[self.alias_hash]
-
-    @property
-    def entity_freq(self):
-        return self.entity_freq
-
-    @property
-    def entity_vector(self):
-        return self.entity_vector
-
-    @property
-    def prior_prob(self):
-        return self.prior_prob
+from .candidate import InMemoryCandidate
 
 
-def get_candidates(KnowledgeBase kb, span) -> Iterator[Candidate]:
-    """
-    Return candidate entities for a given span by using the text of the span as the alias
-    and fetching appropriate entries from the index.
-    This particular function is optimized to work with the built-in KB functionality,
-    but any other custom candidate generation method can be used in combination with the KB as well.
-    """
-    return kb.get_alias_candidates(span.text)
+cdef class InMemoryLookupKB(KnowledgeBase):
+    """An `InMemoryLookupKB` instance stores unique identifiers for entities
+    and their textual aliases, to support entity linking of named entities to
+    real-world concepts.
 
-
-cdef class KnowledgeBase:
-    """A `KnowledgeBase` instance stores unique identifiers for entities and their textual aliases,
-    to support entity linking of named entities to real-world concepts.
-
-    DOCS: https://spacy.io/api/kb
+    DOCS: https://spacy.io/api/inmemorylookupkb
     """
 
     def __init__(self, Vocab vocab, entity_vector_length):
-        """Create a KnowledgeBase."""
-        self.mem = Pool()
-        self.entity_vector_length = entity_vector_length
+        """Create an InMemoryLookupKB."""
+        super().__init__(vocab, entity_vector_length)
         self._entry_index = PreshMap()
         self._alias_index = PreshMap()
-        self.vocab = vocab
         self._create_empty_vectors(dummy_hash=self.vocab.strings[""])
 
-    def initialize_entities(self, int64_t nr_entities):
+    def _initialize_entities(self, int64_t nr_entities):
         self._entry_index = PreshMap(nr_entities + 1)
         self._entries = entry_vec(nr_entities + 1)
 
-    def initialize_vectors(self, int64_t nr_entities):
+    def _initialize_vectors(self, int64_t nr_entities):
         self._vectors_table = float_matrix(nr_entities + 1)
 
-    def initialize_aliases(self, int64_t nr_aliases):
+    def _initialize_aliases(self, int64_t nr_aliases):
         self._alias_index = PreshMap(nr_aliases + 1)
         self._aliases_table = alias_vec(nr_aliases + 1)
 
-    @property
-    def entity_vector_length(self):
-        """RETURNS (uint64): length of the entity vectors"""
-        return self.entity_vector_length
+    def is_empty(self):
+        return len(self) == 0
 
     def __len__(self):
         return self.get_size_entities()
@@ -126,7 +72,8 @@ cdef class KnowledgeBase:
 
     def add_entity(self, str entity, float freq, vector[float] entity_vector):
         """
-        Add an entity to the KB, optionally specifying its log probability based on corpus frequency
+        Add an entity to the KB, optionally specifying its log probability
+        based on corpus frequency.
         Return the hash of the entity ID/name at the end.
         """
         cdef hash_t entity_hash = self.vocab.strings.add(entity)
@@ -138,14 +85,20 @@ cdef class KnowledgeBase:
 
         # Raise an error if the provided entity vector is not of the correct length
         if len(entity_vector) != self.entity_vector_length:
-            raise ValueError(Errors.E141.format(found=len(entity_vector), required=self.entity_vector_length))
+            raise ValueError(
+                Errors.E141.format(
+                    found=len(entity_vector), required=self.entity_vector_length
+                )
+            )
 
         vector_index = self.c_add_vector(entity_vector=entity_vector)
 
-        new_index = self.c_add_entity(entity_hash=entity_hash,
-                                      freq=freq,
-                                      vector_index=vector_index,
-                                      feats_row=-1)  # Features table currently not implemented
+        new_index = self.c_add_entity(
+            entity_hash=entity_hash,
+            freq=freq,
+            vector_index=vector_index,
+            feats_row=-1
+        )  # Features table currently not implemented
         self._entry_index[entity_hash] = new_index
 
         return entity_hash
@@ -155,8 +108,8 @@ cdef class KnowledgeBase:
             raise ValueError(Errors.E140)
 
         nr_entities = len(set(entity_list))
-        self.initialize_entities(nr_entities)
-        self.initialize_vectors(nr_entities)
+        self._initialize_entities(nr_entities)
+        self._initialize_vectors(nr_entities)
 
         i = 0
         cdef KBEntryC entry
@@ -170,7 +123,12 @@ cdef class KnowledgeBase:
             else:
                 entity_vector = vector_list[i]
                 if len(entity_vector) != self.entity_vector_length:
-                    raise ValueError(Errors.E141.format(found=len(entity_vector), required=self.entity_vector_length))
+                    raise ValueError(
+                        Errors.E141.format(
+                            found=len(entity_vector),
+                            required=self.entity_vector_length
+                        )
+                    )
 
                 entry.entity_hash = entity_hash
                 entry.freq = freq_list[i]
@@ -204,11 +162,15 @@ cdef class KnowledgeBase:
         previous_alias_nr = self.get_size_aliases()
         # Throw an error if the length of entities and probabilities are not the same
         if not len(entities) == len(probabilities):
-            raise ValueError(Errors.E132.format(alias=alias,
-                                                entities_length=len(entities),
-                                                probabilities_length=len(probabilities)))
+            raise ValueError(
+                Errors.E132.format(
+                    alias=alias,
+                    entities_length=len(entities),
+                    probabilities_length=len(probabilities))
+            )
 
-        # Throw an error if the probabilities sum up to more than 1 (allow for some rounding errors)
+        # Throw an error if the probabilities sum up to more than 1 (allow for
+        # some rounding errors)
         prob_sum = sum(probabilities)
         if prob_sum > 1.00001:
             raise ValueError(Errors.E133.format(alias=alias, sum=prob_sum))
@@ -225,40 +187,47 @@ cdef class KnowledgeBase:
 
         for entity, prob in zip(entities, probabilities):
             entity_hash = self.vocab.strings[entity]
-            if not entity_hash in self._entry_index:
+            if entity_hash not in self._entry_index:
                 raise ValueError(Errors.E134.format(entity=entity))
 
             entry_index = <int64_t>self._entry_index.get(entity_hash)
             entry_indices.push_back(int(entry_index))
             probs.push_back(float(prob))
 
-        new_index = self.c_add_aliases(alias_hash=alias_hash, entry_indices=entry_indices, probs=probs)
+        new_index = self.c_add_aliases(
+            alias_hash=alias_hash, entry_indices=entry_indices, probs=probs
+        )
         self._alias_index[alias_hash] = new_index
 
         if previous_alias_nr + 1 != self.get_size_aliases():
             raise RuntimeError(Errors.E891.format(alias=alias))
         return alias_hash
 
-    def append_alias(self, str alias, str entity, float prior_prob, ignore_warnings=False):
+    def append_alias(
+        self, str alias, str entity, float prior_prob, ignore_warnings=False
+    ):
         """
-        For an alias already existing in the KB, extend its potential entities with one more.
+        For an alias already existing in the KB, extend its potential entities
+        with one more.
         Throw a warning if either the alias or the entity is unknown,
         or when the combination is already previously recorded.
         Throw an error if this entity+prior prob would exceed the sum of 1.
-        For efficiency, it's best to use the method `add_alias` as much as possible instead of this one.
+        For efficiency, it's best to use the method `add_alias` as much as
+        possible instead of this one.
         """
         # Check if the alias exists in the KB
         cdef hash_t alias_hash = self.vocab.strings[alias]
-        if not alias_hash in self._alias_index:
+        if alias_hash not in self._alias_index:
             raise ValueError(Errors.E176.format(alias=alias))
 
         # Check if the entity exists in the KB
         cdef hash_t entity_hash = self.vocab.strings[entity]
-        if not entity_hash in self._entry_index:
+        if entity_hash not in self._entry_index:
             raise ValueError(Errors.E134.format(entity=entity))
         entry_index = <int64_t>self._entry_index.get(entity_hash)
 
-        # Throw an error if the prior probabilities (including the new one) sum up to more than 1
+        # Throw an error if the prior probabilities (including the new one)
+        # sum up to more than 1
         alias_index = <int64_t>self._alias_index.get(alias_hash)
         alias_entry = self._aliases_table[alias_index]
         current_sum = sum([p for p in alias_entry.probs])
@@ -286,26 +255,34 @@ cdef class KnowledgeBase:
             alias_entry.probs = probs
             self._aliases_table[alias_index] = alias_entry
 
-    def get_alias_candidates(self, str alias) -> Iterator[Candidate]:
+    def get_candidates(self, mention: Span) -> Iterable[InMemoryCandidate]:
+        return self._get_alias_candidates(mention.text)  # type: ignore
+
+    def _get_alias_candidates(self, str alias) -> Iterable[InMemoryCandidate]:
         """
-        Return candidate entities for an alias. Each candidate defines the entity, the original alias,
-        and the prior probability of that alias resolving to that entity.
+        Return candidate entities for an alias. Each candidate defines the
+        entity, the original alias, and the prior probability of that alias
+        resolving to that entity.
         If the alias is not known in the KB, and empty list is returned.
         """
         cdef hash_t alias_hash = self.vocab.strings[alias]
-        if not alias_hash in self._alias_index:
+        if alias_hash not in self._alias_index:
             return []
         alias_index = <int64_t>self._alias_index.get(alias_hash)
         alias_entry = self._aliases_table[alias_index]
 
-        return [Candidate(kb=self,
-                          entity_hash=self._entries[entry_index].entity_hash,
-                          entity_freq=self._entries[entry_index].freq,
-                          entity_vector=self._vectors_table[self._entries[entry_index].vector_index],
-                          alias_hash=alias_hash,
-                          prior_prob=prior_prob)
-                for (entry_index, prior_prob) in zip(alias_entry.entry_indices, alias_entry.probs)
-                if entry_index != 0]
+        return [
+            InMemoryCandidate(
+                kb=self,
+                entity_hash=self._entries[entry_index].entity_hash,
+                alias_hash=alias_hash,
+                entity_vector=self._vectors_table[self._entries[entry_index].vector_index],
+                prior_prob=prior_prob,
+                entity_freq=self._entries[entry_index].freq
+            )
+            for (entry_index, prior_prob) in zip(alias_entry.entry_indices, alias_entry.probs)
+            if entry_index != 0
+        ]
 
     def get_vector(self, str entity):
         cdef hash_t entity_hash = self.vocab.strings[entity]
@@ -318,8 +295,9 @@ cdef class KnowledgeBase:
         return self._vectors_table[self._entries[entry_index].vector_index]
 
     def get_prior_prob(self, str entity, str alias):
-        """ Return the prior probability of a given alias being linked to a given entity,
-        or return 0.0 when this combination is not known in the knowledge base"""
+        """ Return the prior probability of a given alias being linked to a
+        given entity, or return 0.0 when this combination is not known in the
+        knowledge base."""
         cdef hash_t alias_hash = self.vocab.strings[alias]
         cdef hash_t entity_hash = self.vocab.strings[entity]
 
@@ -330,23 +308,34 @@ cdef class KnowledgeBase:
         entry_index = self._entry_index[entity_hash]
 
         alias_entry = self._aliases_table[alias_index]
-        for (entry_index, prior_prob) in zip(alias_entry.entry_indices, alias_entry.probs):
+        for (entry_index, prior_prob) in zip(
+            alias_entry.entry_indices, alias_entry.probs
+        ):
             if self._entries[entry_index].entity_hash == entity_hash:
                 return prior_prob
 
         return 0.0
 
+    def supports_prior_probs(self) -> bool:
+        return True
+
     def to_bytes(self, **kwargs):
         """Serialize the current state to a binary string.
         """
         def serialize_header():
-            header = (self.get_size_entities(), self.get_size_aliases(), self.entity_vector_length)
+            header = (
+                self.get_size_entities(),
+                self.get_size_aliases(),
+                self.entity_vector_length
+            )
             return srsly.json_dumps(header)
 
         def serialize_entries():
             i = 1
             tuples = []
-            for entry_hash, entry_index in sorted(self._entry_index.items(), key=lambda x: x[1]):
+            for entry_hash, entry_index in sorted(
+                self._entry_index.items(), key=lambda x: x[1]
+            ):
                 entry = self._entries[entry_index]
                 assert entry.entity_hash == entry_hash
                 assert entry_index == i
@@ -359,7 +348,9 @@ cdef class KnowledgeBase:
             headers = []
             indices_lists = []
             probs_lists = []
-            for alias_hash, alias_index in sorted(self._alias_index.items(), key=lambda x: x[1]):
+            for alias_hash, alias_index in sorted(
+                self._alias_index.items(), key=lambda x: x[1]
+            ):
                 alias = self._aliases_table[alias_index]
                 assert alias_index == i
                 candidate_length = len(alias.entry_indices)
@@ -388,9 +379,9 @@ cdef class KnowledgeBase:
             nr_entities = header[0]
             nr_aliases = header[1]
             entity_vector_length = header[2]
-            self.initialize_entities(nr_entities)
-            self.initialize_vectors(nr_entities)
-            self.initialize_aliases(nr_aliases)
+            self._initialize_entities(nr_entities)
+            self._initialize_vectors(nr_entities)
+            self._initialize_aliases(nr_aliases)
             self.entity_vector_length = entity_vector_length
 
         def deserialize_vectors(b):
@@ -417,7 +408,7 @@ cdef class KnowledgeBase:
             indices = srsly.json_loads(all_data[1])
             probs = srsly.json_loads(all_data[2])
             for header, indices, probs in zip(headers, indices, probs):
-                alias_hash, candidate_length = header
+                alias_hash, _candidate_length = header
                 alias.entry_indices = indices
                 alias.probs = probs
                 self._aliases_table[i] = alias
@@ -466,10 +457,14 @@ cdef class KnowledgeBase:
                 writer.write_vector_element(element)
             i = i+1
 
-        # dumping the entry records in the order in which they are in the _entries vector.
-        # index 0 is a dummy object not stored in the _entry_index and can be ignored.
+        # dumping the entry records in the order in which they are in the
+        # _entries vector.
+        # index 0 is a dummy object not stored in the _entry_index and can
+        # be ignored.
         i = 1
-        for entry_hash, entry_index in sorted(self._entry_index.items(), key=lambda x: x[1]):
+        for entry_hash, entry_index in sorted(
+            self._entry_index.items(), key=lambda x: x[1]
+        ):
             entry = self._entries[entry_index]
             assert entry.entity_hash == entry_hash
             assert entry_index == i
@@ -481,7 +476,9 @@ cdef class KnowledgeBase:
         # dumping the aliases in the order in which they are in the _alias_index vector.
         # index 0 is a dummy object not stored in the _aliases_table and can be ignored.
         i = 1
-        for alias_hash, alias_index in sorted(self._alias_index.items(), key=lambda x: x[1]):
+        for alias_hash, alias_index in sorted(
+                self._alias_index.items(), key=lambda x: x[1]
+        ):
             alias = self._aliases_table[alias_index]
             assert alias_index == i
 
@@ -512,8 +509,8 @@ cdef class KnowledgeBase:
         cdef int64_t entity_vector_length
         reader.read_header(&nr_entities, &entity_vector_length)
 
-        self.initialize_entities(nr_entities)
-        self.initialize_vectors(nr_entities)
+        self._initialize_entities(nr_entities)
+        self._initialize_vectors(nr_entities)
         self.entity_vector_length = entity_vector_length
 
         # STEP 1: load entity vectors
@@ -552,7 +549,7 @@ cdef class KnowledgeBase:
         # STEP 3: load aliases
         cdef int64_t nr_aliases
         reader.read_alias_length(&nr_aliases)
-        self.initialize_aliases(nr_aliases)
+        self._initialize_aliases(nr_aliases)
 
         cdef int64_t nr_candidates
         cdef vector[int64_t] entry_indices
@@ -587,7 +584,8 @@ cdef class Writer:
     def __init__(self, path):
         assert isinstance(path, Path)
         content = bytes(path)
-        cdef bytes bytes_loc = content.encode('utf8') if type(content) == str else content
+        cdef bytes bytes_loc = content.encode('utf8') \
+            if type(content) == str else content
         self._fp = fopen(<char*>bytes_loc, 'wb')
         if not self._fp:
             raise IOError(Errors.E146.format(path=path))
@@ -597,14 +595,18 @@ cdef class Writer:
         cdef size_t status = fclose(self._fp)
         assert status == 0
 
-    cdef int write_header(self, int64_t nr_entries, int64_t entity_vector_length) except -1:
+    cdef int write_header(
+        self, int64_t nr_entries, int64_t entity_vector_length
+    ) except -1:
         self._write(&nr_entries, sizeof(nr_entries))
         self._write(&entity_vector_length, sizeof(entity_vector_length))
 
     cdef int write_vector_element(self, float element) except -1:
         self._write(&element, sizeof(element))
 
-    cdef int write_entry(self, hash_t entry_hash, float entry_freq, int32_t vector_index) except -1:
+    cdef int write_entry(
+        self, hash_t entry_hash, float entry_freq, int32_t vector_index
+    ) except -1:
         self._write(&entry_hash, sizeof(entry_hash))
         self._write(&entry_freq, sizeof(entry_freq))
         self._write(&vector_index, sizeof(vector_index))
@@ -613,7 +615,9 @@ cdef class Writer:
     cdef int write_alias_length(self, int64_t alias_length) except -1:
         self._write(&alias_length, sizeof(alias_length))
 
-    cdef int write_alias_header(self, hash_t alias_hash, int64_t candidate_length) except -1:
+    cdef int write_alias_header(
+        self, hash_t alias_hash, int64_t candidate_length
+    ) except -1:
         self._write(&alias_hash, sizeof(alias_hash))
         self._write(&candidate_length, sizeof(candidate_length))
 
@@ -629,16 +633,19 @@ cdef class Writer:
 cdef class Reader:
     def __init__(self, path):
         content = bytes(path)
-        cdef bytes bytes_loc = content.encode('utf8') if type(content) == str else content
+        cdef bytes bytes_loc = content.encode('utf8') \
+            if type(content) == str else content
         self._fp = fopen(<char*>bytes_loc, 'rb')
         if not self._fp:
             PyErr_SetFromErrno(IOError)
-        status = fseek(self._fp, 0, 0)  # this can be 0 if there is no header
+        fseek(self._fp, 0, 0)  # this can be 0 if there is no header
 
     def __dealloc__(self):
         fclose(self._fp)
 
-    cdef int read_header(self, int64_t* nr_entries, int64_t* entity_vector_length) except -1:
+    cdef int read_header(
+        self, int64_t* nr_entries, int64_t* entity_vector_length
+    ) except -1:
         status = self._read(nr_entries, sizeof(int64_t))
         if status < 1:
             if feof(self._fp):
@@ -658,7 +665,9 @@ cdef class Reader:
                 return 0  # end of file
             raise IOError(Errors.E145.format(param="vector element"))
 
-    cdef int read_entry(self, hash_t* entity_hash, float* freq, int32_t* vector_index) except -1:
+    cdef int read_entry(
+        self, hash_t* entity_hash, float* freq, int32_t* vector_index
+    ) except -1:
         status = self._read(entity_hash, sizeof(hash_t))
         if status < 1:
             if feof(self._fp):
@@ -689,7 +698,9 @@ cdef class Reader:
                 return 0  # end of file
             raise IOError(Errors.E145.format(param="alias length"))
 
-    cdef int read_alias_header(self, hash_t* alias_hash, int64_t* candidate_length) except -1:
+    cdef int read_alias_header(
+        self, hash_t* alias_hash, int64_t* candidate_length
+    ) except -1:
         status = self._read(alias_hash, sizeof(hash_t))
         if status < 1:
             if feof(self._fp):

spacy/lang/af/__init__.py

@@ -1,5 +1,5 @@
+from ...language import BaseDefaults, Language
 from .stop_words import STOP_WORDS
-from ...language import Language, BaseDefaults
 
 
 class AfrikaansDefaults(BaseDefaults):

spacy/lang/am/__init__.py

@@ -1,12 +1,11 @@
-from .stop_words import STOP_WORDS
+from ...attrs import LANG
+from ...language import BaseDefaults, Language
+from ...util import update_exc
+from ..tokenizer_exceptions import BASE_EXCEPTIONS
 from .lex_attrs import LEX_ATTRS
 from .punctuation import TOKENIZER_SUFFIXES
-
+from .stop_words import STOP_WORDS
 from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
-from ..tokenizer_exceptions import BASE_EXCEPTIONS
-from ...language import Language, BaseDefaults
-from ...attrs import LANG
-from ...util import update_exc
 
 
 class AmharicDefaults(BaseDefaults):

spacy/lang/am/punctuation.py

@@ -1,5 +1,11 @@
-from ..char_classes import LIST_PUNCT, LIST_ELLIPSES, LIST_QUOTES, CURRENCY
-from ..char_classes import UNITS, ALPHA_UPPER
+from ..char_classes import (
+    ALPHA_UPPER,
+    CURRENCY,
+    LIST_ELLIPSES,
+    LIST_PUNCT,
+    LIST_QUOTES,
+    UNITS,
+)
 
 _list_punct = LIST_PUNCT + "፡ ። ፣ ፤ ፥ ፦ ፧ ፠ ፨".strip().split()
 

spacy/lang/am/tokenizer_exceptions.py

@@ -1,5 +1,4 @@
-from ...symbols import ORTH, NORM
-
+from ...symbols import NORM, ORTH
 
 _exc = {}
 

spacy/lang/ar/__init__.py

@@ -1,8 +1,8 @@
-from .stop_words import STOP_WORDS
+from ...language import BaseDefaults, Language
 from .lex_attrs import LEX_ATTRS
 from .punctuation import TOKENIZER_SUFFIXES
+from .stop_words import STOP_WORDS
 from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
-from ...language import Language, BaseDefaults
 
 
 class ArabicDefaults(BaseDefaults):

spacy/lang/ar/punctuation.py

@@ -1,5 +1,11 @@
-from ..char_classes import LIST_PUNCT, LIST_ELLIPSES, LIST_QUOTES, CURRENCY
-from ..char_classes import UNITS, ALPHA_UPPER
+from ..char_classes import (
+    ALPHA_UPPER,
+    CURRENCY,
+    LIST_ELLIPSES,
+    LIST_PUNCT,
+    LIST_QUOTES,
+    UNITS,
+)
 
 _suffixes = (
     LIST_PUNCT

spacy/lang/ar/tokenizer_exceptions.py

@@ -1,7 +1,6 @@
-from ..tokenizer_exceptions import BASE_EXCEPTIONS
-from ...symbols import ORTH, NORM
+from ...symbols import NORM, ORTH
 from ...util import update_exc
-
+from ..tokenizer_exceptions import BASE_EXCEPTIONS
 
 _exc = {}
 

spacy/lang/az/__init__.py

@@ -1,6 +1,6 @@
-from .stop_words import STOP_WORDS
+from ...language import BaseDefaults, Language
 from .lex_attrs import LEX_ATTRS
-from ...language import Language, BaseDefaults
+from .stop_words import STOP_WORDS
 
 
 class AzerbaijaniDefaults(BaseDefaults):

spacy/lang/az/lex_attrs.py

@@ -1,6 +1,5 @@
 from ...attrs import LIKE_NUM
 
-
 # Eleven, twelve etc. are written separate: on bir, on iki
 
 _num_words = [

spacy/lang/bg/__init__.py

@@ -1,11 +1,14 @@
+from ...attrs import LANG
+from ...language import BaseDefaults, Language
+from ...util import update_exc
+from ..punctuation import (
+    COMBINING_DIACRITICS_TOKENIZER_INFIXES,
+    COMBINING_DIACRITICS_TOKENIZER_SUFFIXES,
+)
+from ..tokenizer_exceptions import BASE_EXCEPTIONS
+from .lex_attrs import LEX_ATTRS
 from .stop_words import STOP_WORDS
 from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
-from .lex_attrs import LEX_ATTRS
-from ..tokenizer_exceptions import BASE_EXCEPTIONS
-
-from ...language import Language, BaseDefaults
-from ...attrs import LANG
-from ...util import update_exc
 
 
 class BulgarianDefaults(BaseDefaults):
@@ -16,6 +19,8 @@ class BulgarianDefaults(BaseDefaults):
 
     stop_words = STOP_WORDS
     tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
+    suffixes = COMBINING_DIACRITICS_TOKENIZER_SUFFIXES
+    infixes = COMBINING_DIACRITICS_TOKENIZER_INFIXES
 
 
 class Bulgarian(Language):

spacy/lang/bg/lex_attrs.py

@@ -1,6 +1,5 @@
 from ...attrs import LIKE_NUM
 
-
 _num_words = [
     "нула",
     "едно",

spacy/lang/bg/tokenizer_exceptions.py

@@ -4,8 +4,7 @@ References:
     (countries, occupations, fields of studies and more).
 """
 
-from ...symbols import ORTH, NORM
-
+from ...symbols import NORM, ORTH
 
 _exc = {}
 

spacy/lang/bn/__init__.py

@@ -1,10 +1,12 @@
-from typing import Optional, Callable
+from typing import Callable, Optional
+
 from thinc.api import Model
-from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
-from .punctuation import TOKENIZER_PREFIXES, TOKENIZER_SUFFIXES, TOKENIZER_INFIXES
-from .stop_words import STOP_WORDS
-from ...language import Language, BaseDefaults
+
+from ...language import BaseDefaults, Language
 from ...pipeline import Lemmatizer
+from .punctuation import TOKENIZER_INFIXES, TOKENIZER_PREFIXES, TOKENIZER_SUFFIXES
+from .stop_words import STOP_WORDS
+from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
 
 
 class BengaliDefaults(BaseDefaults):

spacy/lang/bn/punctuation.py

@@ -1,6 +1,14 @@
-from ..char_classes import LIST_PUNCT, LIST_ELLIPSES, LIST_QUOTES, LIST_ICONS
-from ..char_classes import ALPHA_LOWER, ALPHA, HYPHENS, CONCAT_QUOTES, UNITS
-
+from ..char_classes import (
+    ALPHA,
+    ALPHA_LOWER,
+    CONCAT_QUOTES,
+    HYPHENS,
+    LIST_ELLIPSES,
+    LIST_ICONS,
+    LIST_PUNCT,
+    LIST_QUOTES,
+    UNITS,
+)
 
 _currency = r"\$¢£€¥฿৳"
 _quotes = CONCAT_QUOTES.replace("'", "")

spacy/lang/bn/tokenizer_exceptions.py

@@ -1,7 +1,6 @@
-from ..tokenizer_exceptions import BASE_EXCEPTIONS
-from ...symbols import ORTH, NORM
+from ...symbols import NORM, ORTH
 from ...util import update_exc
-
+from ..tokenizer_exceptions import BASE_EXCEPTIONS
 
 _exc = {}
 

spacy/lang/ca/__init__.py

@@ -1,14 +1,14 @@
-from typing import Optional, Callable
+from typing import Callable, Optional
 
 from thinc.api import Model
 
-from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
-from .punctuation import TOKENIZER_INFIXES, TOKENIZER_SUFFIXES, TOKENIZER_PREFIXES
-from .stop_words import STOP_WORDS
-from .lex_attrs import LEX_ATTRS
-from .syntax_iterators import SYNTAX_ITERATORS
-from ...language import Language, BaseDefaults
+from ...language import BaseDefaults, Language
 from .lemmatizer import CatalanLemmatizer
+from .lex_attrs import LEX_ATTRS
+from .punctuation import TOKENIZER_INFIXES, TOKENIZER_PREFIXES, TOKENIZER_SUFFIXES
+from .stop_words import STOP_WORDS
+from .syntax_iterators import SYNTAX_ITERATORS
+from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
 
 
 class CatalanDefaults(BaseDefaults):

spacy/lang/ca/lemmatizer.py

@@ -72,10 +72,10 @@ class CatalanLemmatizer(Lemmatizer):
                         oov_forms.append(form)
         if not forms:
             forms.extend(oov_forms)
-        if not forms and string in lookup_table.keys():
-            forms.append(self.lookup_lemmatize(token)[0])
+
+        # use lookups, and fall back to the token itself
         if not forms:
-            forms.append(string)
+            forms.append(lookup_table.get(string, [string])[0])
         forms = list(dict.fromkeys(forms))
         self.cache[cache_key] = forms
         return forms