Expand Doris Kitchen import, failures, and tag curation

automation/bin/kitchenowl_recipe_import.py

@@ -236,12 +236,118 @@ def coerce_text(value: Any) -> str:
     return unescape(str(value)).strip()
 
 
+def normalize_whitespace(value: str) -> str:
+    cleaned = re.sub(r'\s+', ' ', value or '').strip()
+    return re.sub(r'(?<=[.!?])(?=[A-Z])', ' ', cleaned)
+
+
+def split_paragraphs(value: str) -> list[str]:
+    parts: list[str] = []
+    for chunk in re.split(r'\n\s*\n|\r\n\r\n', value or ''):
+        cleaned = normalize_whitespace(chunk)
+        if cleaned:
+            parts.append(cleaned)
+    return parts
+
+
+def extract_instruction_steps(value: Any) -> list[str]:
+    steps: list[str] = []
+
+    def visit(node: Any) -> None:
+        if node is None:
+            return
+        if isinstance(node, str):
+            for chunk in re.split(r'\n+', node):
+                cleaned = normalize_whitespace(chunk)
+                if cleaned:
+                    steps.append(cleaned)
+            return
+        if isinstance(node, list):
+            for item in node:
+                visit(item)
+            return
+        if isinstance(node, dict):
+            if node.get('@type') == 'HowToSection':
+                name = normalize_whitespace(coerce_text(node.get('name')))
+                if name:
+                    steps.append(f'{name}:')
+                visit(node.get('itemListElement'))
+                return
+            if node.get('@type') in {'HowToStep', 'ListItem'}:
+                text = normalize_whitespace(coerce_text(node.get('text') or node.get('name') or node.get('item')))
+                if text:
+                    steps.append(text)
+                elif node.get('itemListElement') is not None:
+                    visit(node.get('itemListElement'))
+                return
+            if node.get('itemListElement') is not None:
+                visit(node.get('itemListElement'))
+                return
+            text = normalize_whitespace(coerce_text(node.get('text') or node.get('name')))
+            if text:
+                steps.append(text)
+
+    visit(value)
+    deduped: list[str] = []
+    seen: set[str] = set()
+    for step in steps:
+        key = step.lower()
+        if key in seen:
+            continue
+        seen.add(key)
+        deduped.append(step)
+    return deduped
+
+
+def build_description(recipe_node: dict[str, Any]) -> str:
+    intro_parts = split_paragraphs(coerce_text(recipe_node.get('description')))
+    intro = intro_parts[0] if intro_parts else ''
+    notes = intro_parts[1:] if len(intro_parts) > 1 else []
+    steps = extract_instruction_steps(recipe_node.get('recipeInstructions'))
+    parts: list[str] = []
+    if intro:
+        parts.append(intro)
+    if steps:
+        rendered_steps = []
+        step_number = 1
+        for step in steps:
+            if step.endswith(':'):
+                rendered_steps.append(step)
+            else:
+                rendered_steps.append(f'{step_number}. {step}')
+                step_number += 1
+        parts.append('\n'.join(rendered_steps))
+    elif intro_parts[1:]:
+        parts.append('\n'.join(intro_parts[1:]))
+    if notes:
+        parts.append('Notes:\n- ' + '\n- '.join(notes))
+    return '\n\n'.join(part for part in parts if part).strip()
+
+
 def slugify_tag(value: str) -> str:
     value = value.strip().lower()
     value = re.sub(r'[^a-z0-9]+', '-', value)
     return value.strip('-')[:48]
 
 
+def extract_image_url(value: Any) -> str | None:
+    if isinstance(value, str):
+        cleaned = value.strip()
+        return cleaned or None
+    if isinstance(value, list):
+        for item in value:
+            found = extract_image_url(item)
+            if found:
+                return found
+        return None
+    if isinstance(value, dict):
+        for key in ('url', 'contentUrl'):
+            found = extract_image_url(value.get(key))
+            if found:
+                return found
+    return None
+
+
 def normalize_keywords(value: Any) -> list[str]:
     out: list[str] = []
     if isinstance(value, str):
@@ -294,15 +400,7 @@ def split_ingredient(line: str) -> tuple[str, str]:
 
 def normalize_recipe(url: str, recipe_node: dict[str, Any], title_fallback: str | None = None) -> dict[str, Any]:
     name = coerce_text(recipe_node.get('name')) or (title_fallback or url)
-    description_parts: list[str] = []
-    desc = coerce_text(recipe_node.get('description'))
-    instructions = recipe_node.get('recipeInstructions')
-    instructions_text = coerce_text(instructions)
-    if desc:
-        description_parts.append(desc)
-    if instructions_text:
-        description_parts.append(instructions_text)
-    description = '\n\n'.join(part for part in description_parts if part).strip()
+    description = build_description(recipe_node)
 
     ingredients = recipe_node.get('recipeIngredient') or []
     items = []
@@ -348,6 +446,9 @@ def normalize_recipe(url: str, recipe_node: dict[str, Any], title_fallback: str
         'items': items,
         'tags': deduped_tags[:20],
     }
+    image_url = extract_image_url(recipe_node.get('image'))
+    if image_url:
+        payload['photo'] = image_url
     cook_time = parse_duration_minutes(recipe_node.get('cookTime'))
     prep_time = parse_duration_minutes(recipe_node.get('prepTime'))
     total_time = parse_duration_minutes(recipe_node.get('totalTime'))