merge

Author: Joshua Croft

.github/ISSUE_TEMPLATE/bug-report.yml

@@ -40,7 +40,7 @@ body:
       label: Observed Behavior / Content
       description: Describe the behavior / content you are observing.
     validations:
-      required: true
+      required: false
   - type: textarea
     id: steps
     attributes:

.github/spelling/check_spelling.py

@@ -19,47 +19,45 @@
 jsx_like_tags_pattern = re.compile(r'<[^>]*>[\s\S]*?<\/[^>]*>|<[^>]*?/>', re.DOTALL)
 path_pattern = re.compile(r'path:\s*"/[^"]*"')
 guidebox_pattern = re.compile(r'<GuideBox[\s\S]*?/>', re.IGNORECASE)
-hex_colours = re.compile(r'([A-Fa-f0-9]{6}|[A-Fa-f0-9]{3})')
+api_endpoint_pattern = re.compile(r'<ApiEndpointRequestResponse[\s\S]*?/>', re.IGNORECASE)
+
+# New patterns to remove content inside <GithubCodeSegment> and <CodeGroup> tags
+github_code_segment_pattern = re.compile(r'<GithubCodeSegment[\s\S]*?</GithubCodeSegment>', re.IGNORECASE)
+code_group_pattern = re.compile(r'<CodeGroup[\s\S]*?</CodeGroup>', re.IGNORECASE)
 
 # Corrected word pattern to allow apostrophes in valid words
 word_pattern = re.compile(r"\b\w+(?:'\w+)?\b")
 
 # Pattern to exclude words containing escape sequences (\n, \u, etc.)
 escape_sequence_pattern = re.compile(r'\\[nu][0-9a-fA-F]+|u[0-9a-fA-F]{4}')
 
-# Function to extract text while ignoring specified components and handling code blocks differently
+# Function to extract text while ignoring specified components and skipping code blocks
 def extract_text_from_mdx(file_path):
     with open(file_path, 'r') as file:
         content = file.read()
 
-    # Remove import statements
+    # Remove ignored components
+    content = github_code_segment_pattern.sub('', content)
+    content = code_group_pattern.sub('', content)
+    content = api_endpoint_pattern.sub('', content)  # Ignore ApiEndpointRequestResponse blocks
     content = import_pattern.sub('', content)
-
-    # Remove paths and GuideBox components
     content = path_pattern.sub('', content)
     content = guidebox_pattern.sub('', content)
-
-    # Remove JSX components and JSX-like tags
     content = jsx_like_tags_pattern.sub('', content)
 
     # Initialize the Markdown parser
     md = MarkdownIt()
     parsed = md.parse(content)
 
-    # Extract text while separating code blocks for warnings
+    # Extract text while skipping code blocks
     text = []
-    code_blocks = []
-    in_code_block = False
 
     def traverse(node):
-        nonlocal in_code_block
-        if node.type == 'fence':
-            if not in_code_block:
-                code_blocks.append(node.content)  # Capture code block content
-            in_code_block = not in_code_block
-        elif node.type == 'code_inline' and not in_code_block:
+        if node.type == 'fence':  # Skip fenced code blocks
             return
-        elif node.type == 'text' and not in_code_block:
+        elif node.type == 'code_inline':  # Skip inline code
+            return
+        elif node.type == 'text':
             text.append(node.content)
 
         for child in node.children or []:
@@ -68,10 +66,10 @@ def traverse(node):
     for node in parsed:
         traverse(node)
 
-    return '\n'.join(text), code_blocks
+    return '\n'.join(text)
 
 # Function to check for spelling errors
-def check_spelling(text, is_code_block=False):
+def check_spelling(text):
     def split_underscore_words(word):
         return re.split(r'[_\s]+', word)
 
@@ -89,7 +87,7 @@ def split_underscore_words(word):
     css_value_pattern = re.compile(r'^\d+(px|%|em|rem|vh|vw|pt|cm|mm|in|s|ms|deg)?$')  # CSS values
     hex_color_pattern = re.compile(r'^(#?[A-Fa-f0-9]{3}|#?[A-Fa-f0-9]{6})$')  # Hex colors
     eth_address_pattern = re.compile(r'^0x[a-fA-F0-9]{40}$')  # Ethereum addresses
-    hash_pattern = re.compile(r'^[a-f0-9]{40}$')  # Hash-like strings (40 hex characters)
+    hash_pattern = re.compile(r'^[a-f0-9]{40}$')  # Hash-like strings
 
     # Filter out custom words, valid words with apostrophes,
     # words matching escape sequences, "n-prefixed" words, CSS values, hex colors, ETH addresses, and hash strings
@@ -109,8 +107,8 @@ def split_underscore_words(word):
     ]
     misspelled = spell.unknown(reduced_words)
 
-    # Return misspelled words with a flag indicating if they came from code
-    return misspelled if not is_code_block else {'warnings': misspelled}
+    # Return misspelled words
+    return misspelled
 
 # Function to check all .mdx files in a directory
 def check_directory(directory):
@@ -122,8 +120,8 @@ def check_directory(directory):
                 file_path = os.path.join(root, file)
                 print(f'========== Checking file: {file_path} ==========')
 
-                # Extract text and code blocks from the MDX file
-                text, code_blocks = extract_text_from_mdx(file_path)
+                # Extract text from the MDX file
+                text = extract_text_from_mdx(file_path)
 
                 # Check for spelling errors in text
                 errors = check_spelling(text)
@@ -133,16 +131,6 @@ def check_directory(directory):
                         print(f'  - {error}')
                     has_errors = True
 
-                # Check for spelling errors in code blocks (warnings)
-                warnings = []
-                for code_block in code_blocks:
-                    warnings = check_spelling(code_block, is_code_block=True).get('warnings', [])
-
-                if warnings:
-                    print(f'Warnings (spelling errors in code block) in {file_path}:')
-                    for warning in warnings:
-                        print(f'  - {warning}')
-
     return has_errors
 
 # Directory to check