Add a script to harvest tags and categories. Initially by Grok, then fine-tuned.

Author: normanlorrain

create_post.sh

@@ -1,8 +1,8 @@
 #!/bin/bash
 
 # Calculate the next Tuesday (or today if it's Tuesday)
-current_weekday=$(date +%w)              # 0=Sun ... 6=Sat
-days_to_tuesday=$(( (2 - current_weekday + 7) % 7 ))
+current_weekday=$(date +%w) # 0=Sun ... 6=Sat
+days_to_tuesday=$(((2 - current_weekday + 7) % 7))
 
 # Add the calculated days (compatible with both macOS and Linux)
 if date -v +0d &>/dev/null; then
@@ -13,9 +13,10 @@ else
   tuesday=$(date -d "+${days_to_tuesday} days" +%Y-%m-%d)
 fi
 
-year=${tuesday%%-*}                       # 2026
-month=${tuesday#*-}; month=${month%-*}    # 02
-day=${tuesday##*-}                        # 24
+year=${tuesday%%-*} # 2026
+month=${tuesday#*-}
+month=${month%-*}  # 02
+day=${tuesday##*-} # 24
 
 # Define paths
 folder_path="docs/posts/$year/$month/$day"
@@ -25,7 +26,7 @@ file_path="$folder_path/index.md"
 mkdir -p "$folder_path"
 
 # YAML frontmatter
-cat << EOF > "$file_path"
+cat <<EOF >"$file_path"
 ---
 title: "Your Blog Post Title"
 date: $tuesday
@@ -50,4 +51,7 @@ EOF
 
 echo "Blog post template created at $file_path"
 echo ""
-echo "Reminder: Use existing categories and tags when possible."
+echo "Reminder: Use existing categories and tags when possible."
+
+python "./docs/find_tags_categories.py"
+

docs/find_tags_categories.py

@@ -0,0 +1,77 @@
+#!/usr/bin/env python3
+"""
+Lists all unique tags and categories found in YAML front matter of .md files.
+Looks for both 'tags' and 'categories' keys (common variations).
+"""
+
+import os
+import yaml
+from pathlib import Path
+from typing import Set
+
+DOCS_DIR = Path(__file__).parent
+EXTENSIONS = (".md", ".markdown", ".mkd")
+
+def extract_frontmatter(file_path: Path) -> dict:
+    """Extract YAML front matter if present."""
+    content = file_path.read_text(encoding="utf-8")
+    if not content.startswith("---"):
+        return {}
+    try:
+        parts = content.split("---", 2)
+        if len(parts) < 3:
+            return {}
+        fm = yaml.safe_load(parts[1]) or {}
+        return fm if isinstance(fm, dict) else {}
+    except yaml.YAMLError:
+        print(f"Warning: Invalid YAML in {file_path}")
+        return {}
+
+def collect_tags() -> tuple[Set[str], Set[str]]:
+    all_tags: Set[str] = set()
+    all_categories: Set[str] = set()
+
+    docs_path = Path(DOCS_DIR)
+    if not docs_path.is_dir():
+        print(f"Error: Directory not found: {docs_path}")
+        return all_tags, all_categories
+
+    for file_path in docs_path.rglob("*"):
+        if not file_path.is_file() or not file_path.suffix.lower() in EXTENSIONS:
+            continue
+
+        fm = extract_frontmatter(file_path)
+
+        # Handle 'tags'
+        tags = fm.get("tags", [])
+        if isinstance(tags, str):
+            tags = [t.strip() for t in tags.split(",") if t.strip()]
+        if isinstance(tags, list):
+            all_tags.update(str(t).strip() for t in tags if t)
+
+        # Handle 'categories' (sometimes used instead / in addition)
+        cats = fm.get("categories", [])
+        if isinstance(cats, str):
+            cats = [c.strip() for c in cats.split(",") if c.strip()]
+        if isinstance(cats, list):
+            all_categories.update(str(c).strip() for c in cats if c)
+        
+        all_tags.discard('TAG_ONE')
+        all_tags.discard('TAG_TWO')
+        all_categories.discard('CATEGORY_ONE')
+        all_categories.discard('CATEGORY_TWO')
+
+    return all_tags, all_categories
+
+
+def main():
+    tags, categories = collect_tags()
+
+    print(f"\nExisting categories: {', '.join(sorted(categories))}", )
+    print(f"\nExisting tags: {', '.join(sorted(tags))}", )
+
+
+if __name__ == "__main__":
+    main()
+
+