rolfedh-doc-utils 0.1.2__py3-none-any.whl → 0.1.4__py3-none-any.whl

doc_utils/topic_map_parser.py

@@ -0,0 +1,130 @@
+# doc_utils/topic_map_parser.py
+
+import os
+import yaml
+import glob
+
+def detect_repo_type(base_path='.'):
+    """
+    Detect whether the repository uses topic maps (OpenShift-docs style) 
+    or master.adoc files (traditional style).
+    
+    Returns:
+        'topic_map' - if _topic_maps directory with .yml files exists
+        'master_adoc' - if master.adoc files are found
+        'unknown' - if neither pattern is detected
+    """
+    topic_maps_dir = os.path.join(base_path, '_topic_maps')
+    
+    # Check for topic maps
+    if os.path.isdir(topic_maps_dir):
+        yml_files = glob.glob(os.path.join(topic_maps_dir, '*.yml'))
+        if yml_files:
+            return 'topic_map'
+    
+    # Check for master.adoc files using os.walk to avoid symlink issues
+    master_files = []
+    for root, dirs, files in os.walk(base_path):
+        # Skip symbolic link directories to prevent infinite recursion
+        dirs[:] = [d for d in dirs if not os.path.islink(os.path.join(root, d))]
+        
+        # Check for master.adoc in this directory
+        if 'master.adoc' in files:
+            master_files.append(os.path.join(root, 'master.adoc'))
+            
+    if master_files:
+        return 'master_adoc'
+    
+    return 'unknown'
+
+
+def extract_files_from_topic_map(topic_map_path):
+    """
+    Extract all referenced .adoc files from a topic map YAML file.
+    
+    Returns a set of file paths referenced in the topic map.
+    """
+    referenced_files = set()
+    
+    try:
+        with open(topic_map_path, 'r', encoding='utf-8') as f:
+            # Use safe_load_all to handle multiple YAML documents
+            documents = yaml.safe_load_all(f)
+            
+            for doc in documents:
+                if doc is None:
+                    continue
+                    
+                # Process each topic group
+                process_topic_group(doc, referenced_files)
+                
+    except Exception as e:
+        print(f"Warning: Could not parse topic map {topic_map_path}: {e}")
+    
+    return referenced_files
+
+
+def process_topic_group(group, referenced_files, parent_dir=''):
+    """
+    Recursively process a topic group to extract all file references.
+    """
+    if not isinstance(group, dict):
+        return
+        
+    # Get the directory for this group
+    current_dir = group.get('Dir', '')
+    if parent_dir and current_dir:
+        current_dir = os.path.join(parent_dir, current_dir)
+    elif parent_dir:
+        current_dir = parent_dir
+        
+    # Process topics in this group
+    topics = group.get('Topics', [])
+    if isinstance(topics, list):
+        for topic in topics:
+            if isinstance(topic, dict):
+                # If topic has a File, add it
+                if 'File' in topic:
+                    file_path = topic['File']
+                    if current_dir:
+                        file_path = os.path.join(current_dir, file_path)
+                    # Add .adoc extension if not present
+                    if not file_path.endswith('.adoc'):
+                        file_path += '.adoc'
+                    referenced_files.add(file_path)
+                
+                # If topic has nested topics (sub-group), process recursively
+                if 'Topics' in topic:
+                    # For nested topics, use the Dir from the topic if present
+                    sub_dir = topic.get('Dir', '')
+                    if sub_dir:
+                        # If topic has its own Dir, append it to current_dir
+                        if current_dir:
+                            next_dir = os.path.join(current_dir, sub_dir)
+                        else:
+                            next_dir = sub_dir
+                    else:
+                        # If no Dir specified, keep current_dir
+                        next_dir = current_dir
+                    # Process only the Topics, not the whole topic dict
+                    process_topic_group({'Topics': topic['Topics']}, referenced_files, next_dir)
+
+
+def get_all_topic_map_references(base_path='.'):
+    """
+    Get all .adoc files referenced in all topic maps.
+    
+    Returns a set of all referenced file paths.
+    """
+    topic_maps_dir = os.path.join(base_path, '_topic_maps')
+    all_references = set()
+    
+    if not os.path.isdir(topic_maps_dir):
+        return all_references
+        
+    # Process all .yml files in _topic_maps
+    for yml_file in glob.glob(os.path.join(topic_maps_dir, '*.yml')):
+        references = extract_files_from_topic_map(yml_file)
+        all_references.update(references)
+    
+    return all_references

doc_utils/unused_adoc.py

@@ -3,22 +3,51 @@
 import os
 import re
 from .file_utils import collect_files, write_manifest_and_archive
+from .topic_map_parser import detect_repo_type, get_all_topic_map_references
 
 def find_unused_adoc(scan_dirs, archive_dir, archive=False, exclude_dirs=None, exclude_files=None):
+    # Print safety warning
+    print("\n⚠️  SAFETY: Work in a git branch! Run without --archive first to preview.\n")
+    
+    # Detect repository type
+    repo_type = detect_repo_type()
+    print(f"Detected repository type: {repo_type}")
+    
+    # Collect all .adoc files in scan directories
     asciidoc_files = collect_files(scan_dirs, {'.adoc'}, exclude_dirs, exclude_files)
+    
+    # Track which files are referenced
+    referenced_files = set()
+    
+    if repo_type == 'topic_map':
+        # For OpenShift-docs style repos, get references from topic maps
+        topic_references = get_all_topic_map_references()
+        # Convert to basenames for comparison
+        referenced_files.update(os.path.basename(ref) for ref in topic_references)
+    
+    # Always scan for include:: directives in all .adoc files
     include_pattern = re.compile(r'include::(.+?)\[')
-    included_files = set()
     adoc_files = collect_files(['.'], {'.adoc'}, exclude_dirs, exclude_files)
+    
     for file_path in adoc_files:
         try:
             with open(file_path, 'r', encoding='utf-8') as f:
                 content = f.read()
                 includes = include_pattern.findall(content)
-                included_files.update(os.path.basename(include) for include in includes)
+                # Extract just the filename from the include path
+                for include in includes:
+                    # Handle both relative and absolute includes
+                    include_basename = os.path.basename(include)
+                    referenced_files.add(include_basename)
         except Exception as e:
             print(f"Warning: could not read {file_path}: {e}")
-    unused_files = [f for f in asciidoc_files if os.path.basename(f) not in included_files]
-    unused_files = list(dict.fromkeys(unused_files))
+    
+    # Find unused files by comparing basenames
+    unused_files = [f for f in asciidoc_files if os.path.basename(f) not in referenced_files]
+    unused_files = list(dict.fromkeys(unused_files))  # Remove duplicates
+    
+    print(f"Found {len(unused_files)} unused files out of {len(asciidoc_files)} total files in scan directories")
+    
     return write_manifest_and_archive(
         unused_files, archive_dir, 'to-archive', 'to-archive', archive=archive
     )

doc_utils/unused_images.py

@@ -7,6 +7,9 @@ from .file_utils import collect_files, write_manifest_and_archive
 IMAGE_EXTENSIONS = {'.png', '.jpg', '.jpeg', '.gif', '.svg'}
 
 def find_unused_images(scan_dirs, archive_dir, archive=False, exclude_dirs=None, exclude_files=None):
+    # Print safety warning
+    print("\n⚠️  SAFETY: Work in a git branch! Run without --archive first to preview.\n")
+    
     image_files = collect_files(scan_dirs, IMAGE_EXTENSIONS, exclude_dirs, exclude_files)
     adoc_files = collect_files(['.'], {'.adoc'}, exclude_dirs, exclude_files)
     referenced_images = set()

{rolfedh_doc_utils-0.1.2.dist-info → rolfedh_doc_utils-0.1.4.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: rolfedh-doc-utils
-Version: 0.1.2
+Version: 0.1.4
 Summary: CLI tools for AsciiDoc documentation projects
 Author: Rolfe Dlugy-Hegwer
 License: MIT License
@@ -28,6 +28,7 @@ License: MIT License
 Requires-Python: >=3.8
 Description-Content-Type: text/markdown
 License-File: LICENSE
+Requires-Dist: PyYAML>=6.0
 Dynamic: license-file
 
 # doc-utils
@@ -50,11 +51,34 @@ A set of Python utilities and CLI tools to help technical writers maintain Ascii
 
 ### From PyPI
 
-Install the package from PyPI:
+On modern Linux distributions, you may encounter an "externally-managed-environment" error. Use one of these methods:
 
+**Option 1: pipx (Recommended for CLI tools)**
+```sh
+pipx install rolfedh-doc-utils
+```
+
+**Option 2: pip with --user flag**
+```sh
+pip install --user rolfedh-doc-utils
+```
+
+**Option 3: Traditional pip (may require virtual environment)**
 ```sh
 pip install rolfedh-doc-utils
-````
+```
+
+### Upgrading
+
+To upgrade to the latest version:
+
+```sh
+# If installed with pipx:
+pipx upgrade rolfedh-doc-utils
+
+# If installed with pip:
+pip install --upgrade rolfedh-doc-utils  # or --user flag if needed
+```
 
 ### For Development
 
@@ -116,6 +140,10 @@ Scans `.adoc` files in the current directory to report:
 
 Scans the `./modules` and `./assemblies` directories for `.adoc` files that are not referenced. Optionally archives and deletes them.
 
+Works with both:
+- **OpenShift-docs style** repositories (uses `_topic_maps/*.yml` files)
+- **Traditional AsciiDoc** repositories (uses `master.adoc` files)
+
 ➡️ See [`archive_unused_files.md`](https://github.com/rolfedh/doc-utils/blob/main/archive_unused_files.md).
 
 ---
@@ -211,7 +239,7 @@ If you see an error like `ModuleNotFoundError: No module named 'find_unused_attr
 
 1. The package isn't installed. Run:
    ```sh
-   pip install rolfedh-doc-utils
+   pipx install rolfedh-doc-utils  # or pip install --user rolfedh-doc-utils
    ```
 
 2. You're trying to run the script directly without installation. Either:

{rolfedh_doc_utils-0.1.2.dist-info → rolfedh_doc_utils-0.1.4.dist-info}/RECORD

@@ -5,12 +5,13 @@ find_unused_attributes.py,sha256=fk-K32eoCVHxoj7RiBNgSmX1arBLuwYfdSAOMc-wIx0,167
 doc_utils/__init__.py,sha256=qqZR3lohzkP63soymrEZPBGzzk6-nFzi4_tSffjmu_0,74
 doc_utils/file_utils.py,sha256=fpTh3xx759sF8sNocdn_arsP3KAv8XA6cTQTAVIZiZg,4247
 doc_utils/scannability.py,sha256=XwlmHqDs69p_V36X7DLjPTy0DUoLszSGqYjJ9wE-3hg,982
-doc_utils/unused_adoc.py,sha256=gvP1eClEbVebN2jXA41-bPnbVhYz6JHEIbGZCg8JD0s,1115
+doc_utils/topic_map_parser.py,sha256=tKcIO1m9r2K6dvPRGue58zqMr0O2zKU1gnZMzEE3U6o,4571
+doc_utils/unused_adoc.py,sha256=Bx8TH7twhtuDfxzrPLOWOzTLc5YBhIqrCNaKJJR_V38,2312
 doc_utils/unused_attributes.py,sha256=HBgmHelqearfWl3TTC2bZGiJytjLADIgiGQUNKqXXPg,1847
-doc_utils/unused_images.py,sha256=P9vcm00BidrLmxhjeczBtiFU-1wgfN5nCYdZjeCH1kM,1329
-rolfedh_doc_utils-0.1.2.dist-info/licenses/LICENSE,sha256=vLxtwMVOJA_hEy8b77niTkdmQI9kNJskXHq0dBS36e0,1075
-rolfedh_doc_utils-0.1.2.dist-info/METADATA,sha256=cAvrckQs2hogV3m8mpBzlkVSWBi3a5sUHxaQOi2ipKU,7389
-rolfedh_doc_utils-0.1.2.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-rolfedh_doc_utils-0.1.2.dist-info/entry_points.txt,sha256=i8LqEsp0KD4YyVI_7wQ1TMgCuag32D7gQes6bLufmtM,216
-rolfedh_doc_utils-0.1.2.dist-info/top_level.txt,sha256=BkaYN3KbtNvLQjs-QGBKCJb5UAtjEbC_IqxSSIN9P-w,95
-rolfedh_doc_utils-0.1.2.dist-info/RECORD,,
+doc_utils/unused_images.py,sha256=nqn36Bbrmon2KlGlcaruNjJJvTQ8_9H0WU9GvCW7rW8,1456
+rolfedh_doc_utils-0.1.4.dist-info/licenses/LICENSE,sha256=vLxtwMVOJA_hEy8b77niTkdmQI9kNJskXHq0dBS36e0,1075
+rolfedh_doc_utils-0.1.4.dist-info/METADATA,sha256=lPNDY0Lu9pBKxxzCXZp5TqSe3DuBqvBHYPVFyLWpP14,8152
+rolfedh_doc_utils-0.1.4.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+rolfedh_doc_utils-0.1.4.dist-info/entry_points.txt,sha256=i8LqEsp0KD4YyVI_7wQ1TMgCuag32D7gQes6bLufmtM,216
+rolfedh_doc_utils-0.1.4.dist-info/top_level.txt,sha256=BkaYN3KbtNvLQjs-QGBKCJb5UAtjEbC_IqxSSIN9P-w,95
+rolfedh_doc_utils-0.1.4.dist-info/RECORD,,