Extract caption naturalizer policy

caption_policy.py

@@ -0,0 +1,99 @@
+from __future__ import annotations
+
+import re
+from typing import Any
+
+try:
+    from . import formatter_input as input_policy
+    from .hardcore_action_metadata import normalize_hardcore_action_family
+except ImportError:  # Allows local smoke tests with `python tools/prompt_smoke.py`.
+    import formatter_input as input_policy
+    from hardcore_action_metadata import normalize_hardcore_action_family
+
+
+OLD_TRIGGER = "sxcpinup_coloredpencil"
+DEFAULT_TRIGGER = "sxcppnl7"
+
+DETAIL_LEVELS = ("balanced", "concise", "dense")
+STYLE_POLICIES = ("drop_style_tail", "keep_style_terms")
+
+STYLE_TAILS = [
+    ", coloured pencil comic illustration, crisp linework, hatching, soft pastel palette, warm sensual lighting, textured parchment paper",
+    ", coloured pencil comic illustration, crisp linework, hatching, soft pastel palette, warm sensual lighting, textured paper",
+]
+
+ITEM_LABELS = (
+    "Sexual pose",
+    "Erotic outfit",
+    "Clothing",
+)
+
+ACTION_FAMILY_CAPTION_LABELS = {
+    "foreplay": "foreplay action",
+    "outercourse": "non-penetrative action",
+    "oral": "oral action",
+    "penetration": "penetrative action",
+    "toy_double": "toy-assisted double-contact action",
+    "climax": "climax action",
+}
+
+POSITION_FAMILY_CAPTION_LABELS = {
+    "penetrative": "penetrative action",
+    "foreplay": "foreplay action",
+    "interaction": "interaction beat",
+    "manual": "manual action",
+    "oral": "oral action",
+    "outercourse": "non-penetrative action",
+    "anal": "anal action",
+    "climax": "climax action",
+    "threesome": "three-person action",
+    "group": "group action",
+}
+
+
+def normalize_detail_level(value: str) -> str:
+    return value if value in DETAIL_LEVELS else "balanced"
+
+
+def normalize_style_policy(value: str) -> str:
+    return value if value in STYLE_POLICIES else "drop_style_tail"
+
+
+def keep_style_terms(style_policy: str) -> bool:
+    return normalize_style_policy(style_policy) == "keep_style_terms"
+
+
+def detail_allows(level: str, dense_only: bool = False) -> bool:
+    level = normalize_detail_level((level or "balanced").strip().lower())
+    if dense_only:
+        return level == "dense"
+    return level != "concise"
+
+
+def strip_style_tail(text: str) -> str:
+    text = input_policy.clean_text(text)
+    for tail in STYLE_TAILS:
+        if text.endswith(tail):
+            return text[: -len(tail)].strip(" ,")
+    return text
+
+
+def metadata_action_label(row: dict[str, Any], default: str = "sexual pose") -> str:
+    position_family = input_policy.clean_text(row.get("position_family")).lower()
+    if position_family in POSITION_FAMILY_CAPTION_LABELS:
+        return POSITION_FAMILY_CAPTION_LABELS[position_family]
+    action_family = normalize_hardcore_action_family(row.get("action_family"))
+    if action_family in ACTION_FAMILY_CAPTION_LABELS:
+        return ACTION_FAMILY_CAPTION_LABELS[action_family]
+    return default
+
+
+def normalize_composition(text: str) -> str:
+    return re.sub(r"^vertical\s+", "", input_policy.clean_text(text), flags=re.IGNORECASE)
+
+
+def clean_clothing(text: str) -> str:
+    text = input_policy.clean_text(text)
+    text = re.sub(r",?\s*fashion editorial styling$", "", text, flags=re.IGNORECASE)
+    text = re.sub(r",?\s*resort styling$", "", text, flags=re.IGNORECASE)
+    return text.strip(" ,")