rolfedh-doc-utils 0.1.9__tar.gz → 0.1.11__tar.gz

{rolfedh_doc_utils-0.1.9/rolfedh_doc_utils.egg-info → rolfedh_doc_utils-0.1.11}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: rolfedh-doc-utils
-Version: 0.1.9
+Version: 0.1.11
 Summary: CLI tools for AsciiDoc documentation projects
 Author: Rolfe Dlugy-Hegwer
 License: MIT License
@@ -79,8 +79,10 @@ pip install -e .
 
 | Tool | Description | Usage |
 |------|-------------|-------|
-| **`replace-link-attributes`** | Resolves Vale LinkAttribute violations by replacing attributes in link URLs | `replace-link-attributes --dry-run` |
-| **`format-asciidoc-spacing`** | Standardizes spacing after headings and around includes | `format-asciidoc-spacing --dry-run modules/` |
+| **`validate-links`** [EXPERIMENTAL] | Validates all links in documentation, with URL transposition for preview environments | `validate-links --transpose "https://prod--https://preview"` |
+| **`extract-link-attributes`** | Extracts link/xref macros with attributes into reusable definitions | `extract-link-attributes --dry-run` |
+| **`replace-link-attributes`** | Resolves Vale LinkAttribute issues by replacing attributes in link URLs | `replace-link-attributes --dry-run` |
+| **`format-asciidoc-spacing`** [EXPERIMENTAL] | Standardizes spacing after headings and around includes | `format-asciidoc-spacing --dry-run modules/` |
 | **`check-scannability`** | Analyzes readability (sentence/paragraph length) | `check-scannability --max-words 25` |
 | **`archive-unused-files`** | Finds and archives unreferenced .adoc files | `archive-unused-files` (preview)<br>`archive-unused-files --archive` (execute) |
 | **`archive-unused-images`** | Finds and archives unreferenced images | `archive-unused-images` (preview)<br>`archive-unused-images --archive` (execute) |

{rolfedh_doc_utils-0.1.9 → rolfedh_doc_utils-0.1.11}/README.md

@@ -46,8 +46,10 @@ pip install -e .
 
 | Tool | Description | Usage |
 |------|-------------|-------|
-| **`replace-link-attributes`** | Resolves Vale LinkAttribute violations by replacing attributes in link URLs | `replace-link-attributes --dry-run` |
-| **`format-asciidoc-spacing`** | Standardizes spacing after headings and around includes | `format-asciidoc-spacing --dry-run modules/` |
+| **`validate-links`** [EXPERIMENTAL] | Validates all links in documentation, with URL transposition for preview environments | `validate-links --transpose "https://prod--https://preview"` |
+| **`extract-link-attributes`** | Extracts link/xref macros with attributes into reusable definitions | `extract-link-attributes --dry-run` |
+| **`replace-link-attributes`** | Resolves Vale LinkAttribute issues by replacing attributes in link URLs | `replace-link-attributes --dry-run` |
+| **`format-asciidoc-spacing`** [EXPERIMENTAL] | Standardizes spacing after headings and around includes | `format-asciidoc-spacing --dry-run modules/` |
 | **`check-scannability`** | Analyzes readability (sentence/paragraph length) | `check-scannability --max-words 25` |
 | **`archive-unused-files`** | Finds and archives unreferenced .adoc files | `archive-unused-files` (preview)<br>`archive-unused-files --archive` (execute) |
 | **`archive-unused-images`** | Finds and archives unreferenced images | `archive-unused-images` (preview)<br>`archive-unused-images --archive` (execute) |

rolfedh_doc_utils-0.1.11/doc_utils/extract_link_attributes.py

@@ -0,0 +1,453 @@
+#!/usr/bin/env python3
+"""
+Extract link and xref macros containing attributes into attribute definitions.
+"""
+
+import os
+import re
+from pathlib import Path
+from typing import Dict, List, Set, Tuple, Optional
+from collections import defaultdict
+import unicodedata
+
+
+def find_attribute_files(base_path: str = '.') -> List[str]:
+    """Find potential attribute files in the repository."""
+    common_patterns = [
+        '**/common-attributes.adoc',
+        '**/attributes.adoc',
+        '**/*-attributes.adoc',
+        '**/attributes-*.adoc',
+        '**/common_attributes.adoc',
+        '**/_common-attributes.adoc'
+    ]
+
+    attribute_files = []
+    base = Path(base_path)
+
+    for pattern in common_patterns:
+        for file_path in base.glob(pattern):
+            if file_path.is_file():
+                rel_path = file_path.relative_to(base)
+                attribute_files.append(str(rel_path))
+
+    # Remove duplicates while preserving order
+    seen = set()
+    unique_files = []
+    for f in attribute_files:
+        if f not in seen:
+            seen.add(f)
+            unique_files.append(f)
+
+    return sorted(unique_files)
+
+
+def select_attribute_file(attribute_files: List[str]) -> str:
+    """Let user interactively select an attribute file."""
+    if not attribute_files:
+        return None
+
+    print("\nMultiple attribute files found. Please select one:")
+    for i, file_path in enumerate(attribute_files, 1):
+        print(f"  {i}. {file_path}")
+
+    while True:
+        try:
+            choice = input(f"\nEnter your choice (1-{len(attribute_files)}): ").strip()
+            index = int(choice) - 1
+            if 0 <= index < len(attribute_files):
+                return attribute_files[index]
+            else:
+                print(f"Please enter a number between 1 and {len(attribute_files)}")
+        except (ValueError, EOFError, KeyboardInterrupt):
+            print("\nOperation cancelled.")
+            return None
+
+
+def load_existing_attributes(file_path: str) -> Dict[str, str]:
+    """Load existing attributes from file."""
+    attributes = {}
+    if not os.path.exists(file_path):
+        return attributes
+
+    with open(file_path, 'r', encoding='utf-8') as f:
+        for line in f:
+            # Match attribute definitions
+            match = re.match(r'^:([^:]+):\s*(.+)$', line)
+            if match:
+                attr_name = match.group(1).strip()
+                attr_value = match.group(2).strip()
+                attributes[attr_name] = attr_value
+
+    return attributes
+
+
+def find_link_macros(file_path: str) -> List[Tuple[str, str, str, int]]:
+    """
+    Find all link: and xref: macros containing attributes in their URLs.
+
+    Returns list of tuples: (full_macro, url, link_text, line_number)
+    """
+    macros = []
+
+    with open(file_path, 'r', encoding='utf-8') as f:
+        for line_num, line in enumerate(f, 1):
+            # Pattern to match link: and xref: macros
+            # Matches: (link|xref):url[text] where url contains {attribute}
+            patterns = [
+                r'(link:([^[\]]*\{[^}]+\}[^[\]]*)\[([^\]]*)\])',
+                r'(xref:([^[\]]*\{[^}]+\}[^[\]]*)\[([^\]]*)\])'
+            ]
+
+            for pattern in patterns:
+                for match in re.finditer(pattern, line, re.IGNORECASE):
+                    full_macro = match.group(1)
+                    url = match.group(2)
+                    link_text = match.group(3)
+                    macros.append((full_macro, url, link_text, line_num))
+
+    return macros
+
+
+def generate_attribute_name(url: str, existing_attrs: Set[str], counter: int) -> str:
+    """Generate a unique attribute name from URL."""
+    # Start with a base name from the URL
+    base_name = url
+
+    # Extract domain or path components
+    if '://' in url:
+        # Remove protocol
+        base_name = re.sub(r'^[^:]+://', '', url)
+
+    # Remove attributes from the name generation
+    base_name = re.sub(r'\{[^}]+\}', '', base_name)
+
+    # Extract meaningful parts
+    if '/' in base_name:
+        parts = base_name.split('/')
+        # Use domain and last path component
+        if len(parts) > 1:
+            domain_part = parts[0].replace('.', '-')
+            path_part = parts[-1].split('.')[0] if parts[-1] else ''
+            if path_part:
+                base_name = f"{domain_part}-{path_part}"
+            else:
+                base_name = domain_part
+
+    # Clean up the name
+    base_name = re.sub(r'[^a-zA-Z0-9-]', '-', base_name)
+    base_name = re.sub(r'-+', '-', base_name)
+    base_name = base_name.strip('-').lower()
+
+    # Limit length
+    if len(base_name) > 30:
+        base_name = base_name[:30]
+
+    # Make it unique
+    attr_name = f"link-{base_name}"
+    original_name = attr_name
+    suffix = 1
+
+    while attr_name in existing_attrs:
+        attr_name = f"{original_name}-{suffix}"
+        suffix += 1
+
+    return attr_name
+
+
+def group_macros_by_url(macros: List[Tuple[str, str, str, str, int]]) -> Dict[str, List[Tuple[str, str, str, int]]]:
+    """
+    Group macros by URL, collecting all link text variations.
+
+    Returns: Dict[url, List[(file_path, link_text, full_macro, line_number)]]
+    """
+    url_groups = defaultdict(list)
+
+    for file_path, full_macro, url, link_text, line_num in macros:
+        url_groups[url].append((file_path, link_text, full_macro, line_num))
+
+    return url_groups
+
+
+def select_link_text(url: str, variations: List[Tuple[str, str, str, int]], interactive: bool = True) -> str:
+    """
+    Select link text for a URL with multiple variations.
+
+    variations: List[(file_path, link_text, full_macro, line_number)]
+    """
+    # Extract unique link texts
+    unique_texts = {}
+    for file_path, link_text, _, line_num in variations:
+        if link_text not in unique_texts:
+            unique_texts[link_text] = []
+        unique_texts[link_text].append(f"{file_path}:{line_num}")
+
+    if len(unique_texts) == 1:
+        # Only one variation, use it
+        return list(unique_texts.keys())[0]
+
+    if not interactive:
+        # Use most common (appears in most locations)
+        most_common = max(unique_texts.items(), key=lambda x: len(x[1]))
+        return most_common[0]
+
+    # Interactive selection
+    print(f"\nMultiple link text variations found for URL: {url}")
+    print("Please select the preferred text:")
+
+    text_list = list(unique_texts.items())
+    for i, (text, locations) in enumerate(text_list, 1):
+        print(f"\n  {i}. \"{text}\"")
+        print(f"     Used in: {', '.join(locations[:3])}")
+        if len(locations) > 3:
+            print(f"     ... and {len(locations) - 3} more locations")
+
+    print(f"\n  {len(text_list) + 1}. Enter custom text")
+
+    while True:
+        try:
+            choice = input(f"\nEnter your choice (1-{len(text_list) + 1}): ").strip()
+            index = int(choice) - 1
+
+            if 0 <= index < len(text_list):
+                return text_list[index][0]
+            elif index == len(text_list):
+                custom_text = input("Enter custom link text: ").strip()
+                if custom_text:
+                    return custom_text
+                else:
+                    print("Text cannot be empty. Please try again.")
+            else:
+                print(f"Please enter a number between 1 and {len(text_list) + 1}")
+        except (ValueError, EOFError, KeyboardInterrupt):
+            print("\nUsing most common text variation.")
+            most_common = max(unique_texts.items(), key=lambda x: len(x[1]))
+            return most_common[0]
+
+
+def collect_all_macros(scan_dirs: List[str] = None) -> List[Tuple[str, str, str, str, int]]:
+    """
+    Collect all link/xref macros with attributes from all .adoc files.
+
+    Returns: List[(file_path, full_macro, url, link_text, line_number)]
+    """
+    if scan_dirs is None:
+        scan_dirs = ['.']
+
+    all_macros = []
+
+    for scan_dir in scan_dirs:
+        for root, _, files in os.walk(scan_dir):
+            # Skip hidden directories and .archive
+            if '/.archive' in root or '/.' in root:
+                continue
+
+            for file in files:
+                if file.endswith('.adoc'):
+                    file_path = os.path.join(root, file)
+                    macros = find_link_macros(file_path)
+                    for full_macro, url, link_text, line_num in macros:
+                        all_macros.append((file_path, full_macro, url, link_text, line_num))
+
+    return all_macros
+
+
+def create_attributes(url_groups: Dict[str, List[Tuple[str, str, str, int]]],
+                     existing_attrs: Dict[str, str],
+                     interactive: bool = True) -> Dict[str, str]:
+    """
+    Create new attributes for each unique URL.
+
+    Returns: Dict[attribute_name, attribute_value]
+    """
+    new_attributes = {}
+    existing_attr_names = set(existing_attrs.keys())
+    counter = 1
+
+    for url, variations in url_groups.items():
+        # Check if this URL already has an attribute
+        existing_attr = None
+        for attr_name, attr_value in existing_attrs.items():
+            if url in attr_value:
+                existing_attr = attr_name
+                break
+
+        if existing_attr:
+            print(f"URL already has attribute {{{existing_attr}}}: {url}")
+            continue
+
+        # Select link text
+        link_text = select_link_text(url, variations, interactive)
+
+        # Generate attribute name
+        attr_name = generate_attribute_name(url, existing_attr_names | set(new_attributes.keys()), counter)
+        counter += 1
+
+        # Determine macro type (link or xref)
+        first_macro = variations[0][2]  # full_macro from first variation
+        macro_type = 'xref' if first_macro.startswith('xref:') else 'link'
+
+        # Create attribute value
+        attr_value = f"{macro_type}:{url}[{link_text}]"
+        new_attributes[attr_name] = attr_value
+
+        print(f"Created attribute: :{attr_name}: {attr_value}")
+
+    return new_attributes
+
+
+def update_attribute_file(file_path: str, new_attributes: Dict[str, str], dry_run: bool = False):
+    """Add new attributes to the attribute file."""
+    if not new_attributes:
+        print("No new attributes to add.")
+        return
+
+    if dry_run:
+        print(f"\n[DRY RUN] Would add {len(new_attributes)} attributes to {file_path}:")
+        for attr_name, attr_value in new_attributes.items():
+            print(f"  :{attr_name}: {attr_value}")
+        return
+
+    # Ensure directory exists
+    os.makedirs(os.path.dirname(file_path) if os.path.dirname(file_path) else '.', exist_ok=True)
+
+    # Append new attributes
+    with open(file_path, 'a', encoding='utf-8') as f:
+        if os.path.getsize(file_path) > 0:
+            f.write('\n')  # Add newline if file not empty
+        f.write('// Extracted link attributes\n')
+        for attr_name, attr_value in sorted(new_attributes.items()):
+            f.write(f":{attr_name}: {attr_value}\n")
+
+    print(f"Added {len(new_attributes)} attributes to {file_path}")
+
+
+def replace_macros_with_attributes(file_updates: Dict[str, List[Tuple[str, str]]], dry_run: bool = False):
+    """
+    Replace link/xref macros with their attribute references.
+
+    file_updates: Dict[file_path, List[(old_macro, attribute_ref)]]
+    """
+    for file_path, replacements in file_updates.items():
+        if dry_run:
+            print(f"\n[DRY RUN] Would update {file_path}:")
+            for old_macro, attr_ref in replacements[:3]:
+                print(f"  Replace: {old_macro}")
+                print(f"     With: {attr_ref}")
+            if len(replacements) > 3:
+                print(f"  ... and {len(replacements) - 3} more replacements")
+            continue
+
+        # Read file
+        with open(file_path, 'r', encoding='utf-8') as f:
+            content = f.read()
+
+        # Apply replacements
+        for old_macro, attr_ref in replacements:
+            content = content.replace(old_macro, attr_ref)
+
+        # Write file
+        with open(file_path, 'w', encoding='utf-8') as f:
+            f.write(content)
+
+        print(f"Updated {file_path}: {len(replacements)} replacements")
+
+
+def prepare_file_updates(url_groups: Dict[str, List[Tuple[str, str, str, int]]],
+                        attribute_mapping: Dict[str, str]) -> Dict[str, List[Tuple[str, str]]]:
+    """
+    Prepare file updates mapping macros to attribute references.
+
+    Returns: Dict[file_path, List[(old_macro, attribute_ref)]]
+    """
+    file_updates = defaultdict(list)
+
+    # Create reverse mapping from URL to attribute name
+    url_to_attr = {}
+    for attr_name, attr_value in attribute_mapping.items():
+        # Extract URL from attribute value
+        match = re.match(r'(?:link|xref):([^\[]+)\[', attr_value)
+        if match:
+            url = match.group(1)
+            url_to_attr[url] = attr_name
+
+    # Map each macro occurrence to its attribute
+    for url, variations in url_groups.items():
+        if url in url_to_attr:
+            attr_name = url_to_attr[url]
+            for file_path, _, full_macro, _ in variations:
+                file_updates[file_path].append((full_macro, f"{{{attr_name}}}"))
+
+    return dict(file_updates)
+
+
+def extract_link_attributes(attributes_file: str = None,
+                           scan_dirs: List[str] = None,
+                           interactive: bool = True,
+                           dry_run: bool = False) -> bool:
+    """
+    Main function to extract link attributes.
+
+    Returns: True if successful, False otherwise
+    """
+    # Find or confirm attributes file
+    if not attributes_file:
+        found_files = find_attribute_files()
+
+        if not found_files:
+            print("No attribute files found.")
+            response = input("Create common-attributes.adoc? (y/n): ").strip().lower()
+            if response == 'y':
+                attributes_file = 'common-attributes.adoc'
+            else:
+                print("Please specify an attribute file with --attributes-file")
+                return False
+        elif len(found_files) == 1:
+            attributes_file = found_files[0]
+            print(f"Using attribute file: {attributes_file}")
+        else:
+            attributes_file = select_attribute_file(found_files)
+            if not attributes_file:
+                return False
+
+    # Load existing attributes
+    existing_attrs = load_existing_attributes(attributes_file)
+    print(f"Loaded {len(existing_attrs)} existing attributes")
+
+    # Collect all macros
+    print("\nScanning for link and xref macros with attributes...")
+    all_macros = collect_all_macros(scan_dirs)
+
+    if not all_macros:
+        print("No link or xref macros with attributes found.")
+        return True
+
+    print(f"Found {len(all_macros)} link/xref macros with attributes")
+
+    # Group by URL
+    url_groups = group_macros_by_url(all_macros)
+    print(f"Grouped into {len(url_groups)} unique URLs")
+
+    # Create new attributes
+    new_attributes = create_attributes(url_groups, existing_attrs, interactive)
+
+    if not new_attributes:
+        print("No new attributes to create.")
+        return True
+
+    # Update attribute file
+    update_attribute_file(attributes_file, new_attributes, dry_run)
+
+    # Prepare file updates
+    all_attributes = {**existing_attrs, **new_attributes}
+    file_updates = prepare_file_updates(url_groups, all_attributes)
+
+    # Replace macros
+    replace_macros_with_attributes(file_updates, dry_run)
+
+    if dry_run:
+        print("\n[DRY RUN] No files were modified. Run without --dry-run to apply changes.")
+    else:
+        print(f"\nSuccessfully extracted {len(new_attributes)} link attributes")
+
+    return True

rolfedh_doc_utils-0.1.11/doc_utils/unused_attributes.py

@@ -0,0 +1,138 @@
+"""
+Module for finding unused AsciiDoc attributes.
+
+Functions:
+- parse_attributes_file: Parse attribute names from an attributes.adoc file.
+- find_adoc_files: Recursively find all .adoc files in a directory (ignoring symlinks).
+- scan_for_attribute_usage: Find which attributes are used in a set of .adoc files.
+- find_unused_attributes: Main function to return unused attributes.
+- find_attributes_files: Find all potential attributes files in the repository.
+"""
+
+import os
+import re
+from pathlib import Path
+from typing import Set, List, Optional
+
+def parse_attributes_file(attr_file: str) -> Set[str]:
+    attributes = set()
+
+    # Check if file exists
+    if not os.path.exists(attr_file):
+        raise FileNotFoundError(f"Attributes file not found: {attr_file}")
+
+    # Check if it's a file (not a directory)
+    if not os.path.isfile(attr_file):
+        raise ValueError(f"Path is not a file: {attr_file}")
+
+    try:
+        with open(attr_file, 'r', encoding='utf-8') as f:
+            for line in f:
+                match = re.match(r'^:([\w-]+):', line.strip())
+                if match:
+                    attributes.add(match.group(1))
+    except PermissionError:
+        raise PermissionError(f"Permission denied reading file: {attr_file}")
+    except UnicodeDecodeError as e:
+        raise ValueError(f"Unable to read file (encoding issue): {attr_file}\n{str(e)}")
+
+    return attributes
+
+def find_adoc_files(root_dir: str) -> List[str]:
+    adoc_files = []
+    for dirpath, dirnames, filenames in os.walk(root_dir, followlinks=False):
+        for fname in filenames:
+            if fname.endswith('.adoc'):
+                full_path = os.path.join(dirpath, fname)
+                if not os.path.islink(full_path):
+                    adoc_files.append(full_path)
+    return adoc_files
+
+def scan_for_attribute_usage(adoc_files: List[str], attributes: Set[str]) -> Set[str]:
+    used = set()
+    attr_pattern = re.compile(r'\{([\w-]+)\}')
+    for file in adoc_files:
+        with open(file, 'r', encoding='utf-8') as f:
+            for line in f:
+                for match in attr_pattern.findall(line):
+                    if match in attributes:
+                        used.add(match)
+    return used
+
+def find_attributes_files(root_dir: str = '.') -> List[str]:
+    """Find all attributes.adoc files in the repository."""
+    attributes_files = []
+    root_path = Path(root_dir)
+
+    # Common attribute file patterns
+    patterns = ['**/attributes.adoc', '**/attributes*.adoc', '**/*attributes.adoc', '**/*-attributes.adoc']
+
+    for pattern in patterns:
+        for path in root_path.glob(pattern):
+            # Skip hidden directories and common build directories
+            parts = path.parts
+            if any(part.startswith('.') or part in ['target', 'build', 'node_modules', '.archive'] for part in parts):
+                continue
+            # Convert to string and avoid duplicates
+            str_path = str(path)
+            if str_path not in attributes_files:
+                attributes_files.append(str_path)
+
+    # Sort for consistent ordering
+    attributes_files.sort()
+    return attributes_files
+
+
+def select_attributes_file(attributes_files: List[str]) -> Optional[str]:
+    """Interactive selection of attributes file from a list."""
+    if not attributes_files:
+        return None
+
+    if len(attributes_files) == 1:
+        print(f"Found attributes file: {attributes_files[0]}")
+        response = input("Use this file? (y/n): ").strip().lower()
+        if response == 'y':
+            return attributes_files[0]
+        else:
+            response = input("Enter the path to your attributes file: ").strip()
+            if os.path.exists(response) and os.path.isfile(response):
+                return response
+            else:
+                print(f"Error: File not found: {response}")
+                return None
+
+    # Multiple files found
+    print("\nFound multiple attributes files:")
+    for i, file_path in enumerate(attributes_files, 1):
+        print(f"  {i}. {file_path}")
+    print(f"  {len(attributes_files) + 1}. Enter custom path")
+
+    while True:
+        response = input(f"\nSelect option (1-{len(attributes_files) + 1}) or 'q' to quit: ").strip()
+        if response.lower() == 'q':
+            return None
+
+        try:
+            choice = int(response)
+            if 1 <= choice <= len(attributes_files):
+                return attributes_files[choice - 1]
+            elif choice == len(attributes_files) + 1:
+                response = input("Enter the path to your attributes file: ").strip()
+                if os.path.exists(response) and os.path.isfile(response):
+                    return response
+                else:
+                    print(f"Error: File not found: {response}")
+            else:
+                print(f"Invalid choice. Please enter a number between 1 and {len(attributes_files) + 1}")
+        except ValueError:
+            print("Invalid input. Please enter a number.")
+
+    return None
+
+
+def find_unused_attributes(attr_file: str, adoc_root: str = '.') -> List[str]:
+    attributes = parse_attributes_file(attr_file)
+    adoc_files = find_adoc_files(adoc_root)
+    used = scan_for_attribute_usage(adoc_files, attributes)
+    unused = sorted(attributes - used)
+    return unused