Tighten hardcore Krea action wording

caption_naturalizer.py

@@ -83,6 +83,52 @@ def _human_join(parts: list[str]) -> str:
     return f"{', '.join(parts[:-1])}, and {parts[-1]}"
 
 
+def _prompt_cast_descriptors(text: str) -> str:
+    return _clean_text(text).replace("Woman A / primary creator:", "Woman A:")
+
+
+def _cast_entries(text: str) -> list[tuple[str, str]]:
+    text = _prompt_cast_descriptors(text)
+    entries: list[tuple[str, str]] = []
+    for part in text.split(";"):
+        part = _clean_text(part)
+        match = re.match(r"^((?:Woman|Man) [A-Z]):\s*(.+)$", part)
+        if match:
+            entries.append((match.group(1), _clean_text(match.group(2))))
+    return entries
+
+
+def _natural_cast_descriptor_text(text: str) -> str:
+    entries = _cast_entries(text)
+    if not entries:
+        return _clean_text(text)
+    labels = [label for label, _descriptor in entries]
+    if labels == ["Woman A"] or labels == ["Man A"]:
+        return f"A {entries[0][1]}"
+    if set(labels) == {"Woman A", "Man A"} and len(labels) == 2:
+        by_label = {label: descriptor for label, descriptor in entries}
+        return f"A {by_label['Woman A']} alongside a {by_label['Man A']}"
+    return " ".join(f"{label} is {descriptor}." for label, descriptor in entries)
+
+
+def _cast_labels(text: str) -> list[str]:
+    return [label for label, _descriptor in _cast_entries(text)]
+
+
+def _natural_label_text(text: Any, labels: list[str]) -> str:
+    text = _clean_text(text)
+    if not text:
+        return ""
+    if set(labels) == {"Woman A", "Man A"}:
+        text = re.sub(r"\bWoman A\b", "the woman", text)
+        text = re.sub(r"\bMan A\b", "the man", text)
+    elif labels == ["Woman A"]:
+        text = re.sub(r"\bWoman A\b", "the woman", text)
+    elif labels == ["Man A"]:
+        text = re.sub(r"\bMan A\b", "the man", text)
+    return text
+
+
 def _strip_style_tail(text: str) -> str:
     text = _clean_text(text)
     for tail in STYLE_TAILS:
@@ -428,7 +474,7 @@ def _configured_cast_from_row(row: dict[str, Any], detail_level: str, keep_style
 
     parts = [f"{_cap_first(subject)} {verb} shown as a consensual {scene_kind}"]
     if cast_descriptor_text:
-        parts.append(f"The named characters are {cast_descriptor_text}")
+        parts.append(_natural_cast_descriptor_text(cast_descriptor_text))
     if cast and not cast_descriptor_text:
         parts.append(f"The cast is {cast}")
     if role_graph:
@@ -505,19 +551,20 @@ def _insta_of_pair_from_row(row: dict[str, Any], detail_level: str, keep_style:
     options = row.get("options") if isinstance(row.get("options"), dict) else {}
     cast_descriptors = row.get("shared_cast_descriptors")
     if isinstance(cast_descriptors, list):
-        cast_descriptor_text = _human_join([_clean_text(item) for item in cast_descriptors if _clean_text(item)])
+        cast_descriptor_text = "; ".join(_clean_text(item) for item in cast_descriptors if _clean_text(item))
     else:
         cast_descriptor_text = _clean_text(cast_descriptors)
+    labels = _cast_labels(cast_descriptor_text)
 
     same_soft_cast = options.get("softcore_cast") == "same_as_hardcore"
 
     parts = []
     if cast_descriptor_text and same_soft_cast:
-        parts.append(f"The shared cast descriptors are {cast_descriptor_text}")
+        parts.append(_natural_cast_descriptor_text(cast_descriptor_text))
     elif descriptor:
-        parts.append(f"The softcore primary creator descriptor is {descriptor}")
+        parts.append(f"A {descriptor}")
     if cast_descriptor_text and not same_soft_cast:
-        parts.append(f"The hardcore cast descriptors are {cast_descriptor_text}")
+        parts.append(_natural_cast_descriptor_text(cast_descriptor_text))
     if same_soft_cast:
         parts.append("The softcore version keeps the same adult cast present together in a non-explicit teaser setup")
         partner_styling = row.get("softcore_partner_styling")
@@ -525,6 +572,7 @@ def _insta_of_pair_from_row(row: dict[str, Any], detail_level: str, keep_style:
             outfits = partner_styling.get("outfits")
             if isinstance(outfits, list):
                 outfit_text = _human_join([_clean_text(item) for item in outfits if _clean_text(item)])
+                outfit_text = _natural_label_text(outfit_text, labels)
                 if outfit_text:
                     parts.append(f"Softcore partner styling: {outfit_text}")
             pose = _clean_text(partner_styling.get("pose"))