rolfedh-doc-utils 0.1.13__py3-none-any.whl → 0.1.15__py3-none-any.whl

doc_utils/extract_link_attributes.py

@@ -85,10 +85,14 @@ def load_existing_attributes(file_path: str) -> Dict[str, str]:
     return attributes
 
 
-def find_link_macros(file_path: str) -> List[Tuple[str, str, str, int]]:
+def find_link_macros(file_path: str, macro_type: str = 'both') -> List[Tuple[str, str, str, int]]:
     """
     Find all link: and xref: macros containing attributes in their URLs.
 
+    Args:
+        file_path: Path to the file to scan
+        macro_type: Type of macros to find - 'link', 'xref', or 'both' (default: 'both')
+
     Returns list of tuples: (full_macro, url, link_text, line_number)
     """
     macros = []
@@ -97,10 +101,13 @@ def find_link_macros(file_path: str) -> List[Tuple[str, str, str, int]]:
         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:([^[\]]*\{[^}]+\}[^[\]]*)\[([^\]]*)\])'
-            ]
+            patterns = []
+
+            if macro_type in ('link', 'both'):
+                patterns.append(r'(link:([^[\]]*\{[^}]+\}[^[\]]*)\[([^\]]*)\])')
+
+            if macro_type in ('xref', 'both'):
+                patterns.append(r'(xref:([^[\]]*\{[^}]+\}[^[\]]*)\[([^\]]*)\])')
 
             for pattern in patterns:
                 for match in re.finditer(pattern, line, re.IGNORECASE):
@@ -228,10 +235,15 @@ def select_link_text(url: str, variations: List[Tuple[str, str, str, int]], inte
             return most_common[0]
 
 
-def collect_all_macros(scan_dirs: List[str] = None) -> List[Tuple[str, str, str, str, int]]:
+def collect_all_macros(scan_dirs: List[str] = None, macro_type: str = 'both', exclude_files: List[str] = None) -> List[Tuple[str, str, str, str, int]]:
     """
     Collect all link/xref macros with attributes from all .adoc files.
 
+    Args:
+        scan_dirs: Directories to scan (default: current directory)
+        macro_type: Type of macros to find - 'link', 'xref', or 'both' (default: 'both')
+        exclude_files: List of file paths to exclude from scanning (typically all attributes files)
+
     Returns: List[(file_path, full_macro, url, link_text, line_number)]
     """
     if scan_dirs is None:
@@ -239,6 +251,13 @@ def collect_all_macros(scan_dirs: List[str] = None) -> List[Tuple[str, str, str,
 
     all_macros = []
 
+    # Normalize all exclude file paths
+    exclude_paths = set()
+    if exclude_files:
+        for file in exclude_files:
+            if file:  # Check for None or empty string
+                exclude_paths.add(os.path.abspath(file))
+
     for scan_dir in scan_dirs:
         for root, _, files in os.walk(scan_dir):
             # Skip hidden directories and .archive
@@ -248,7 +267,10 @@ def collect_all_macros(scan_dirs: List[str] = None) -> List[Tuple[str, str, str,
             for file in files:
                 if file.endswith('.adoc'):
                     file_path = os.path.join(root, file)
-                    macros = find_link_macros(file_path)
+                    # Skip any attributes files to prevent self-referencing
+                    if exclude_paths and os.path.abspath(file_path) in exclude_paths:
+                        continue
+                    macros = find_link_macros(file_path, macro_type)
                     for full_macro, url, link_text, line_num in macros:
                         all_macros.append((file_path, full_macro, url, link_text, line_num))
 
@@ -452,10 +474,20 @@ def extract_link_attributes(attributes_file: str = None,
                            interactive: bool = True,
                            dry_run: bool = False,
                            validate_links: bool = False,
-                           fail_on_broken: bool = False) -> bool:
+                           fail_on_broken: bool = False,
+                           macro_type: str = 'both') -> bool:
     """
     Main function to extract link attributes.
 
+    Args:
+        attributes_file: Path to attributes file
+        scan_dirs: Directories to scan
+        interactive: Enable interactive mode
+        dry_run: Preview changes without modifying files
+        validate_links: Validate URLs before extraction
+        fail_on_broken: Exit if broken links found
+        macro_type: Type of macros to process - 'link', 'xref', or 'both' (default: 'both')
+
     Returns: True if successful, False otherwise
     """
     # Find or confirm attributes file
@@ -489,17 +521,27 @@ def extract_link_attributes(attributes_file: str = None,
     existing_attrs = load_existing_attributes(attributes_file)
     spinner.stop(f"Loaded {len(existing_attrs)} existing attributes")
 
-    # Collect all macros
-    spinner = Spinner("Scanning for link and xref macros with attributes")
+    # Find all attributes files to exclude from processing
+    all_attribute_files = find_attribute_files()
+
+    # Notify user about excluded files if there are multiple
+    if len(all_attribute_files) > 1:
+        print(f"Excluding {len(all_attribute_files)} attributes files from processing:")
+        for f in all_attribute_files:
+            print(f"  - {f}")
+
+    # Collect all macros, excluding ALL attributes files
+    macro_desc = {'link': 'link', 'xref': 'xref', 'both': 'link and xref'}[macro_type]
+    spinner = Spinner(f"Scanning for {macro_desc} macros with attributes")
     spinner.start()
-    all_macros = collect_all_macros(scan_dirs)
+    all_macros = collect_all_macros(scan_dirs, macro_type, exclude_files=all_attribute_files)
     spinner.stop()
 
     if not all_macros:
-        print("No link or xref macros with attributes found.")
+        print(f"No {macro_desc} macros with attributes found.")
         return True
 
-    print(f"Found {len(all_macros)} link/xref macros with attributes")
+    print(f"Found {len(all_macros)} {macro_desc} macros with attributes")
 
     # Group by URL
     spinner = Spinner("Grouping macros by URL")

doc_utils/replace_link_attributes.py

@@ -65,8 +65,18 @@ def resolve_nested_attributes(attributes: Dict[str, str], max_iterations: int =
     return attributes
 
 
-def replace_link_attributes_in_file(file_path: Path, attributes: Dict[str, str], dry_run: bool = False) -> int:
-    """Replace attribute references within link macros in a single file."""
+def replace_link_attributes_in_file(file_path: Path, attributes: Dict[str, str], dry_run: bool = False, macro_type: str = 'both') -> int:
+    """
+    Replace attribute references within link macros in a single file.
+
+    Args:
+        file_path: Path to the file to process
+        attributes: Dictionary of attribute definitions
+        dry_run: Preview changes without modifying files
+        macro_type: Type of macros to process - 'link', 'xref', or 'both' (default: 'both')
+
+    Returns: Number of replacements made
+    """
     with open(file_path, 'r', encoding='utf-8') as f:
         content = f.read()
 
@@ -75,14 +85,23 @@ def replace_link_attributes_in_file(file_path: Path, attributes: Dict[str, str],
 
     # Find all link macros containing attributes in the URL portion only
     # Match link: and xref: macros, capturing URL and text separately
-    link_patterns = [
+    link_patterns = []
+
+    if macro_type in ('link', 'both'):
         # link:url[text] - replace only in URL portion
-        (r'link:([^[\]]*)\[([^\]]*)\]', 'link'),
+        link_patterns.append((r'link:([^[\]]*)\[([^\]]*)\]', 'link'))
+
+    if macro_type in ('xref', 'both'):
         # xref:target[text] - replace only in target portion
-        (r'xref:([^[\]]*)\[([^\]]*)\]', 'xref'),
-        # link:url[] or xref:target[] - replace in URL/target portion
-        (r'(link|xref):([^[\]]*)\[\]', 'empty_text')
-    ]
+        link_patterns.append((r'xref:([^[\]]*)\[([^\]]*)\]', 'xref'))
+
+    # Handle empty text cases based on macro type
+    if macro_type == 'both':
+        link_patterns.append((r'(link|xref):([^[\]]*)\[\]', 'empty_text'))
+    elif macro_type == 'link':
+        link_patterns.append((r'(link):([^[\]]*)\[\]', 'empty_text'))
+    elif macro_type == 'xref':
+        link_patterns.append((r'(xref):([^[\]]*)\[\]', 'empty_text'))
 
     for pattern, link_type in link_patterns:
         matches = list(re.finditer(pattern, content))

extract_link_attributes.py

@@ -77,6 +77,13 @@ Examples:
         help='Exit extraction if broken links are found in attributes (requires --validate-links)'
     )
 
+    parser.add_argument(
+        '--macro-type',
+        choices=['link', 'xref', 'both'],
+        default='both',
+        help='Type of macros to process: link, xref, or both (default: both)'
+    )
+
     args = parser.parse_args()
 
     try:
@@ -86,7 +93,8 @@ Examples:
             interactive=not args.non_interactive,
             dry_run=args.dry_run,
             validate_links=args.validate_links,
-            fail_on_broken=args.fail_on_broken
+            fail_on_broken=args.fail_on_broken,
+            macro_type=args.macro_type
         )
 
         if not success:

replace_link_attributes.py

@@ -102,6 +102,12 @@ def main():
         type=str,
         help='Path to attributes.adoc file (skips interactive selection)'
     )
+    parser.add_argument(
+        '--macro-type',
+        choices=['link', 'xref', 'both'],
+        default='both',
+        help='Type of macros to process: link, xref, or both (default: both)'
+    )
 
     args = parser.parse_args()
 
@@ -149,8 +155,18 @@ def main():
     adoc_files = find_adoc_files(repo_root)
     spinner.stop()
 
-    # Exclude the attributes file itself
-    adoc_files = [f for f in adoc_files if f != attributes_file]
+    # Find ALL attributes files to exclude from processing
+    all_attribute_files = find_attributes_files(repo_root)
+    exclude_paths = {f.resolve() for f in all_attribute_files}
+
+    # Notify user about excluded files if there are multiple
+    if len(all_attribute_files) > 1:
+        print(f"Excluding {len(all_attribute_files)} attributes files from processing:")
+        for f in all_attribute_files:
+            print(f"  - {f.relative_to(repo_root)}")
+
+    # Exclude ALL attributes files, not just the selected one
+    adoc_files = [f for f in adoc_files if f.resolve() not in exclude_paths]
 
     print(f"Found {len(adoc_files)} AsciiDoc files to process")
 
@@ -165,7 +181,7 @@ def main():
     spinner.start()
 
     for file_path in adoc_files:
-        replacements = replace_link_attributes_in_file(file_path, attributes, args.dry_run)
+        replacements = replace_link_attributes_in_file(file_path, attributes, args.dry_run, args.macro_type)
         if replacements > 0:
             rel_path = file_path.relative_to(repo_root)
             total_replacements += replacements

{rolfedh_doc_utils-0.1.13.dist-info → rolfedh_doc_utils-0.1.15.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: rolfedh-doc-utils
-Version: 0.1.13
+Version: 0.1.15
 Summary: CLI tools for AsciiDoc documentation projects
 Author: Rolfe Dlugy-Hegwer
 License: MIT License

{rolfedh_doc_utils-0.1.13.dist-info → rolfedh_doc_utils-0.1.15.dist-info}/RECORD

@@ -1,16 +1,16 @@
 archive_unused_files.py,sha256=h7CRwSPBVCOQs0hn_ASD4EXz8QJFcAO2x3KX9FVhXNM,1974
 archive_unused_images.py,sha256=4GSVPYkxqFoY-isy47P_1AhD1ziXgmajFiBGCtZ3olg,1564
 check_scannability.py,sha256=MvGLW4UGGcx-jZLsVRYXpXNAIEQyJZZnsN99zJzbtyc,5178
-extract_link_attributes.py,sha256=rp1yRYIWOEvU3l6lpN4b5rCBae5Q7bdBxEDQ9BNuFH8,2976
+extract_link_attributes.py,sha256=grPvVwOF9kqIOZ_uxYtJTkO3C2DNtIpKNPp6LlGK3Xs,3216
 find_unused_attributes.py,sha256=IUJKJr_MzxBXqg9rafUs9Kwi8AbU0x-H0AVflc1dhCU,3288
 format_asciidoc_spacing.py,sha256=_XpHqxYWm1AnZLUK_cDpfAJtsDCDF0b66m3opfYnIuU,3912
-replace_link_attributes.py,sha256=ZkBqrrpIiYGccGMgRjDBrWQKgpfOzHIegURmcgTwaHg,6614
+replace_link_attributes.py,sha256=lJHrzIRJOmdt5WzCD0Lf-v9lOJDXBV7b75bOFZLNDPQ,7324
 validate_links.py,sha256=409fTAyBGTUrp6iSWuJ9AXExcdz8dC_4QeA_RvCIhus,5845
 doc_utils/__init__.py,sha256=qqZR3lohzkP63soymrEZPBGzzk6-nFzi4_tSffjmu_0,74
-doc_utils/extract_link_attributes.py,sha256=IIEq2bQmACwDszmaCMeMnYnPKwxSOHWbu_spYOJezlE,20700
+doc_utils/extract_link_attributes.py,sha256=U0EvPZReJQigNfbT-icBsVT6Li64hYki5W7MQz6qqbc,22743
 doc_utils/file_utils.py,sha256=fpTh3xx759sF8sNocdn_arsP3KAv8XA6cTQTAVIZiZg,4247
 doc_utils/format_asciidoc_spacing.py,sha256=XnVJekaj39aDzjV3xFKl58flM41AaJzejxNYJIIAMz0,10139
-doc_utils/replace_link_attributes.py,sha256=kBiePbxjQn3O2rzqmYY8Mqy_mJgZ6yw048vSZ5SSB5E,6587
+doc_utils/replace_link_attributes.py,sha256=gmAs68_njBqEz-Qni-UGgeYEDTMxlTWk_IOm76FONNE,7279
 doc_utils/scannability.py,sha256=XwlmHqDs69p_V36X7DLjPTy0DUoLszSGqYjJ9wE-3hg,982
 doc_utils/spinner.py,sha256=lJg15qzODiKoR0G6uFIk2BdVNgn9jFexoTRUMrjiWvk,3554
 doc_utils/topic_map_parser.py,sha256=tKcIO1m9r2K6dvPRGue58zqMr0O2zKU1gnZMzEE3U6o,4571
@@ -18,9 +18,9 @@ doc_utils/unused_adoc.py,sha256=2cbqcYr1os2EhETUU928BlPRlsZVSdI00qaMhqjSIqQ,5263
 doc_utils/unused_attributes.py,sha256=EjTtWIKW_aXsR1JOgw5RSDVAqitJ_NfRMVOXVGaiWTY,5282
 doc_utils/unused_images.py,sha256=nqn36Bbrmon2KlGlcaruNjJJvTQ8_9H0WU9GvCW7rW8,1456
 doc_utils/validate_links.py,sha256=iBGXnwdeLlgIT3fo3v01ApT5k0X2FtctsvkrE6E3VMk,19610
-rolfedh_doc_utils-0.1.13.dist-info/licenses/LICENSE,sha256=vLxtwMVOJA_hEy8b77niTkdmQI9kNJskXHq0dBS36e0,1075
-rolfedh_doc_utils-0.1.13.dist-info/METADATA,sha256=BijPKBcklacOn-2U2VTfcMEJBkyOMoI84Ce5ItNK-vc,7386
-rolfedh_doc_utils-0.1.13.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-rolfedh_doc_utils-0.1.13.dist-info/entry_points.txt,sha256=2J4Ojc3kkuArpe2xcUOPc0LxSWCmnctvw8hy8zpnbO4,418
-rolfedh_doc_utils-0.1.13.dist-info/top_level.txt,sha256=1w0JWD7w7gnM5Sga2K4fJieNZ7CHPTAf0ozYk5iIlmo,182
-rolfedh_doc_utils-0.1.13.dist-info/RECORD,,
+rolfedh_doc_utils-0.1.15.dist-info/licenses/LICENSE,sha256=vLxtwMVOJA_hEy8b77niTkdmQI9kNJskXHq0dBS36e0,1075
+rolfedh_doc_utils-0.1.15.dist-info/METADATA,sha256=wUhG5aOP3eUggSenYO_D3bS8R4wCI7abvg1F7gWgR3E,7386
+rolfedh_doc_utils-0.1.15.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+rolfedh_doc_utils-0.1.15.dist-info/entry_points.txt,sha256=2J4Ojc3kkuArpe2xcUOPc0LxSWCmnctvw8hy8zpnbO4,418
+rolfedh_doc_utils-0.1.15.dist-info/top_level.txt,sha256=1w0JWD7w7gnM5Sga2K4fJieNZ7CHPTAf0ozYk5iIlmo,182
+rolfedh_doc_utils-0.1.15.dist-info/RECORD,,