Update spellcheck to run only on changed files (#3233)

.rst, .md, and .py file changes are included for testing purposes only and will not be merged.

Mering despite of the lint errors, could be fixed in followup PRs I guess

Author: svekars

.github/workflows/spelling.yml

@@ -5,16 +5,149 @@ on:
   push:
     branches:
       - main
+
 jobs:
   pyspelling:
     runs-on: ubuntu-20.04
     steps:
-      - uses: actions/checkout@v3
+      - name: Check for skip label and get changed files
+        id: check-files
+        uses: actions/github-script@v6
+        with:
+          script: |
+            let skipCheck = false;
+            let changedFiles = [];
+            
+            if (context.eventName === 'pull_request') {
+              // Check for skip label
+              const { data: labels } = await github.rest.issues.listLabelsOnIssue({
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                issue_number: context.issue.number
+              });
+              skipCheck = labels.some(label => label.name === 'skip-spell-check');
+              
+              if (!skipCheck) {
+                // Get changed files in PR
+                const { data: files } = await github.rest.pulls.listFiles({
+                  owner: context.repo.owner,
+                  repo: context.repo.repo,
+                  pull_number: context.issue.number
+                });
+                
+                changedFiles = files
+                  .filter(file => file.filename.match(/\.(py|rst|md)$/))
+                  .map(file => file.filename);
+              }
+            } else {
+              // For push events, we'll still need to use git diff
+              // We'll handle this after checkout
+            }
+            
+            core.setOutput('skip', skipCheck.toString());
+            core.setOutput('files', changedFiles.join('\n'));
+            core.setOutput('is-pr', (context.eventName === 'pull_request').toString());
+
+      - uses: actions/checkout@v4
+        if: steps.check-files.outputs.skip != 'true'
+        with:
+          fetch-depth: 0
+
+      - name: Get changed files for push event
+        if: |
+          steps.check-files.outputs.skip != 'true' &&
+          steps.check-files.outputs.is-pr != 'true'
+        id: push-files
+        run: |
+          CHANGED_FILES=$(git diff --name-only HEAD^..HEAD -- '*.py' '*.rst' '*.md')
+          echo "files<<EOF" >> $GITHUB_OUTPUT
+          echo "$CHANGED_FILES" >> $GITHUB_OUTPUT
+          echo "EOF" >> $GITHUB_OUTPUT
+
+      - name: Check if relevant files changed
+        if: steps.check-files.outputs.skip != 'true'
+        id: check
+        run: |
+          if [ "${{ steps.check-files.outputs.is-pr }}" == "true" ]; then
+            FILES="${{ steps.check-files.outputs.files }}"
+          else
+            FILES="${{ steps.push-files.outputs.files }}"
+          fi
+          
+          if [ -z "$FILES" ]; then
+            echo "skip=true" >> $GITHUB_OUTPUT
+            echo "No relevant files changed (*.py, *.rst, *.md), skipping spell check"
+          else
+            echo "skip=false" >> $GITHUB_OUTPUT
+            echo "Found changed files to check:"
+            echo "$FILES"
+          fi
+
       - uses: actions/setup-python@v4
+        if: |
+          steps.check-files.outputs.skip != 'true' &&
+          steps.check.outputs.skip != 'true'
         with:
           python-version: '3.9'
           cache: 'pip'
-      - run: pip install pyspelling
-      - run: sudo apt-get install aspell aspell-en
-      - run: pyspelling
 
+      - name: Install dependencies
+        if: |
+          steps.check-files.outputs.skip != 'true' &&
+          steps.check.outputs.skip != 'true'
+        run: |
+          pip install pyspelling
+          sudo apt-get install aspell aspell-en
+
+      - name: Run spell check on each file
+        id: spellcheck
+        if: |
+          steps.check-files.outputs.skip != 'true' &&
+          steps.check.outputs.skip != 'true'
+        run: |
+          if [ "${{ steps.check-files.outputs.is-pr }}" == "true" ]; then
+            mapfile -t FILES <<< "${{ steps.check-files.outputs.files }}"
+          else
+            mapfile -t FILES <<< "${{ steps.push-files.outputs.files }}"
+          fi
+          
+          # Check each file individually
+          FINAL_EXIT_CODE=0
+          SPELLCHECK_LOG=""
+          for file in "${FILES[@]}"; do
+            if [ -n "$file" ]; then
+              echo "Checking spelling in $file"
+              python3 -c "import yaml; config = yaml.safe_load(open('.pyspelling.yml')); new_matrix = [matrix.copy() for matrix in config['matrix'] if (('python' in matrix['name'].lower() and '$file'.endswith('.py')) or ('rest' in matrix['name'].lower() and '$file'.endswith('.rst')) or ('markdown' in matrix['name'].lower() and '$file'.endswith('.md'))) and not matrix.update({'sources': ['$file']})]; config['matrix'] = new_matrix; yaml.dump(config, open('temp_config.yml', 'w'))"
+
+              if OUTPUT=$(pyspelling -c temp_config.yml 2>&1); then
+                echo "No spelling errors found in $file"
+              else
+                FINAL_EXIT_CODE=1
+                echo "Spelling errors found in $file:"
+                echo "$OUTPUT"
+                SPELLCHECK_LOG+="### $file\n$OUTPUT\n\n"
+              fi
+            fi
+          done
+
+          # Save the results to GITHUB_OUTPUT
+          echo "spell_failed=$FINAL_EXIT_CODE" >> $GITHUB_OUTPUT
+          echo "spell_log<<SPELLEOF" >> $GITHUB_OUTPUT
+          echo "$SPELLCHECK_LOG" >> $GITHUB_OUTPUT
+          echo "SPELLEOF" >> $GITHUB_OUTPUT
+
+          if [ $FINAL_EXIT_CODE -ne 0 ]; then
+            echo "Spell check failed! See above for details."
+            echo
+            echo "Here are a few tips:"
+            echo "- All PyTorch API objects must be in double backticks or use an intersphinx directive."
+            echo "  Example: ``torch.nn``, :func:"
+            echo "- Consult en-wordlist.txt for spellings of some of the words."
+            echo "  You can add a word to en-wordlist.txt if:"
+            echo "  1) It's a common abbreviation, like RNN."
+            echo "  2) It's a word widely accepted in the industry."
+            echo "- Please do not add words like 'dtype', 'torch.nn.Transformer' to pass spellcheck."
+            echo "  Instead wrap it in double backticks or use an intersphinx directive."
+            echo
+            exit 1
+          fi

.pyspelling.yml

@@ -2,10 +2,7 @@ spellchecker: aspell
 matrix:
 - name: python
   sources:
-    - beginner_source/*.py
-    - intermediate_source/*.py
-    - advanced_source/*.py
-    - recipes_source/*/*.py
+  - "**/*.py"
   dictionary:
     wordlists:
       - en-wordlist.txt
@@ -56,7 +53,7 @@ matrix:
   - pyspelling.filters.url:
 - name: reST
   sources:
-  - beginner_source/*.rst
+  - "**/*.rst"
   dictionary:
     wordlists:
       - en-wordlist.txt
@@ -119,3 +116,48 @@ matrix:
       - open: '\.\.\s+(image|include|only)::'
         close: '$'
   - pyspelling.filters.url:
+- name: markdown
+  sources:
+  - '**/*.md'
+  dictionary:
+    wordlists:
+      - en-wordlist.txt
+  pipeline:
+  - pyspelling.filters.markdown:
+      markdown_extensions:
+        - markdown.extensions.extra:
+        - markdown.extensions.admonition:
+        - markdown.extensions.codehilite:
+        - markdown.extensions.meta:
+        - markdown.extensions.tables:
+        - markdown.extensions.toc:
+  - pyspelling.filters.html:
+      comments: false
+      ignores:
+        - code
+        - pre
+        - tt
+        - img
+        - a
+        - table
+        - thead
+        - tbody
+        - th
+        - tr
+        - td
+  - pyspelling.filters.context:
+      context_visible_first: true
+      delimiters:
+        # Ignore code blocks
+        - open: '```[a-z]*\n'
+          close: '```\n'
+        # Ignore inline code
+        - open: '`'
+          close: '`'
+        # Ignore links
+        - open: '\[([^]]*)\]'
+          close: '\([^)]*\)'
+        # Ignore HTML comments
+        - open: '<!--'
+          close: '-->'
+  - pyspelling.filters.url:

README.md

@@ -7,7 +7,7 @@ All the tutorials are now presented as sphinx style documentation at:
 
 # Asking a question
 
-If you have a question about a tutorial, post in https://dev-discuss.pytorch.org/ rather than creating an issue in this repo. Your question will be answered much faster on the dev-discuss forum.
+If you hve a qestion about a tutorial, post in https://dev-discuss.pytorch.org/ rather than creating an issue in this repo. Your question will be answered much faster on the dev-discuss forum.
 
 # Submitting an issue
 
@@ -20,7 +20,7 @@ You can submit the following types of issues:
 
 We use sphinx-gallery's [notebook styled examples](https://sphinx-gallery.github.io/stable/tutorials/index.html) to create the tutorials. Syntax is very simple. In essence, you write a slightly well formatted Python file and it shows up as an HTML page. In addition, a Jupyter notebook is autogenerated and available to run in Google Colab.
 
-Here is how you can create a new tutorial (for a detailed description, see [CONTRIBUTING.md](./CONTRIBUTING.md)):
+Here is how you can ceate a new tutorial (for a detailed description, see [CONTRIBUTING.md](./CONTRIBUTING.md)):
 
 NOTE: Before submitting a new tutorial, read [PyTorch Tutorial Submission Policy](./tutorial_submission_policy.md).
 

beginner_source/colab.rst

@@ -10,8 +10,8 @@ run PyTorch tutorials in Google Colab.
 PyTorch Version in Google Colab
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
-When you are running a tutorial that requires a version of PyTorch that has
-just been released, that version might not be yet available in Google Colab.
+Wen you are running a tutorial that requires a version of PyTorch that has
+jst been released, that version might not be yet available in Google Colab.
 To check that you have the required ``torch`` and compatible domain libraries
 installed, run ``!pip list``.
 
@@ -27,7 +27,7 @@ Using Tutorial Data from Google Drive in Colab
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
 We've added a new feature to tutorials that allows users to open the
-notebook associated with a tutorial in Google Colab. You may need to
+ntebook associated with a tutorial in Google Colab. You may need to
 copy data to your Google drive account to get the more complex tutorials
 to work.
 

beginner_source/introyt/tensors_deeper_tutorial.py

@@ -44,7 +44,7 @@
 
 
 ##########################################################################
-# Let’s unpack what we just did:
+# Let’s upack what we just did:
 # 
 # -  We created a tensor using one of the numerous factory methods
 #    attached to the ``torch`` module.
@@ -85,7 +85,7 @@
 
 
 #########################################################################
-# The factory methods all do just what you’d expect - we have a tensor
+# The fctory methods all do just what you’d expect - we have a tensor
 # full of zeros, another full of ones, and another with random values
 # between 0 and 1.
 #