Normalize built-in row action metadata

row_normalization.py

@@ -1,5 +1,6 @@
 from __future__ import annotations
 
+import re
 from typing import Any
 
 try:
@@ -67,6 +68,51 @@ def _legacy_subject_metadata(row: dict[str, Any]) -> tuple[str, str, int | None,
     return "", subject, None, None
 
 
+_LEGACY_PROMPT_FIELD_LABELS = (
+    "Ages",
+    "Body types",
+    "Scene",
+    "Pose",
+    "Facial expressions",
+    "Facial expression",
+    "Clothing",
+    "Prop/detail",
+    "Composition",
+    "Use",
+    "Avoid",
+)
+
+
+def _clean_text(value: Any) -> str:
+    text = "" if value is None else str(value)
+    text = re.sub(r"\s+", " ", text.replace("\n", " ")).strip()
+    return re.sub(r"\s+([,.;:])", r"\1", text)
+
+
+def _legacy_prompt_field(row: dict[str, Any], label: str) -> str:
+    prompt = _clean_text(row.get("prompt"))
+    if not prompt:
+        return ""
+    labels = "|".join(re.escape(name) for name in _LEGACY_PROMPT_FIELD_LABELS)
+    pattern = rf"{re.escape(label)}:\s*(.*?)(?=\. (?:{labels}):|\. Use\b|\. Avoid\b|$)"
+    match = re.search(pattern, prompt)
+    if not match:
+        return ""
+    return _clean_text(match.group(1)).rstrip(".")
+
+
+def _clean_legacy_pose(value: Any) -> str:
+    text = _clean_text(value)
+    text = text.replace(", affectionate and flirtatious but non-explicit", "")
+    return text
+
+
+def _clean_legacy_clothing(value: Any) -> str:
+    text = _clean_text(value)
+    text = re.sub(r",?\s*(?:fashion editorial|resort) styling$", "", text, flags=re.IGNORECASE)
+    return text.strip(" ,")
+
+
 def enrich_legacy_row_metadata(row: dict[str, Any]) -> dict[str, Any]:
     if row.get("source") != "built_in_generator":
         return row
@@ -87,6 +133,15 @@ def enrich_legacy_row_metadata(row: dict[str, Any]) -> dict[str, Any]:
         if scene_text:
             row["scene_text"] = scene_text
             row.setdefault("scene_entry", {"slug": scene_slug, "prompt": scene_text})
+    pose = _clean_legacy_pose(_legacy_prompt_field(row, "Pose"))
+    _setdefault_nonempty(row, "pose", pose)
+    expression = _legacy_prompt_field(row, "Facial expression") or _legacy_prompt_field(row, "Facial expressions")
+    _setdefault_nonempty(row, "expression", expression)
+    clothing = _clean_legacy_clothing(_legacy_prompt_field(row, "Clothing"))
+    _setdefault_nonempty(row, "clothing", clothing)
+    _setdefault_nonempty(row, "item", clothing)
+    if clothing:
+        _setdefault_nonempty(row, "item_label", "Clothing")
     return row