Refine Krea hardcore pose phrasing

krea_formatter.py

@@ -218,12 +218,12 @@ def _cast_prose(text: str, central_label: str = "Woman A") -> tuple[str, list[st
         return (f"{central_label} is {_clean(text)}" if _clean(text) else "", [])
     labels = [label for label, _descriptor in entries]
     if labels == ["Woman A"]:
-        return f"A {entries[0][1]}", labels
+        return _with_indefinite_article(entries[0][1]), labels
     if labels == ["Man A"]:
-        return f"A {entries[0][1]}", labels
+        return _with_indefinite_article(entries[0][1]), labels
     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']}", labels
+        return f"{_with_indefinite_article(by_label['Woman A'])} alongside {_with_indefinite_article(by_label['Man A'])}", labels
     sentences = []
     for label, descriptor in entries:
         sentences.append(f"{label} is {descriptor}.")
@@ -239,9 +239,14 @@ def _sanitize_scene_text_for_cast(text: Any, labels: list[str]) -> str:
     if len(labels) < 3:
         text = re.sub(r"\s*(?:while|as)\s+another partner watches\b", "", text, flags=re.IGNORECASE)
         text = re.sub(r"\banother partner watches\b", "", text, flags=re.IGNORECASE)
+        text = re.sub(r",?\s*\bone partner held between two bodies\b", "", text, flags=re.IGNORECASE)
+        text = re.sub(r",?\s*\bthree bodies locked together\b", "", text, flags=re.IGNORECASE)
+        text = re.sub(r",?\s*\bthree bodies\b", "", text, flags=re.IGNORECASE)
+        text = re.sub(r"\bwith\s*,\s*", "with ", text, flags=re.IGNORECASE)
     text = re.sub(r"\bwhile blowjob\b", "during a blowjob", text, flags=re.IGNORECASE)
     text = re.sub(r"\bfeaturing blowjob\b", "featuring a blowjob", text, flags=re.IGNORECASE)
     text = re.sub(r"\s+,", ",", text)
+    text = re.sub(r",\s*,", ",", text)
     text = re.sub(r"\s{2,}", " ", text).strip(" ,")
     return text
 
@@ -275,7 +280,227 @@ def _natural_clothing_state(text: Any) -> str:
     return text
 
 
-def _hardcore_action_sentence(role_graph: str, hard_item: str) -> str:
+def _hardcore_pose_anchor(role_graph: str, hard_item: str, composition: str = "") -> str:
+    text = " ".join(_clean(part).lower() for part in (role_graph, hard_item, composition) if _clean(part))
+    item_text = _clean(hard_item).lower()
+    if not text:
+        return ""
+    if "double penetration" in text or "vaginal and anal penetration" in text or "front-and-back" in text:
+        if "bed-edge" in text or "edge-of-bed" in text:
+            return "bed-edge front-and-back double-penetration pose"
+        if "standing supported" in text:
+            return "standing supported front-and-back double-penetration pose"
+        if "kneeling" in text:
+            return "kneeling front-and-back double-penetration pose"
+        return "front-and-back double-penetration pose"
+    if "face-sitting" in text:
+        return "face-sitting oral pose"
+    if "sixty-nine" in text:
+        return "sixty-nine oral pose"
+    if "cunnilingus" in text or "pussy licking" in text or "mouth on her pussy" in text:
+        if "reclining" in text:
+            return "reclining cunnilingus pose"
+        if "straddled" in text:
+            return "straddled cunnilingus pose"
+        return "open-thigh cunnilingus pose"
+    if "oral" in text or "blowjob" in text or "penis in her mouth" in text or "penis in mouth" in text:
+        if "side-lying oral position" in item_text:
+            return "side-lying oral pose"
+        if "spread-leg oral position" in item_text:
+            return "spread-leg oral pose"
+        if "edge-of-bed oral position" in item_text:
+            return "edge-of-bed oral pose"
+        if "standing oral position" in item_text:
+            return "standing oral pose"
+        if "chair oral position" in item_text:
+            return "chair oral pose"
+        if "kneeling oral position" in item_text or "kneeling" in text:
+            return "kneeling oral pose"
+        if "standing" in text:
+            return "standing oral pose"
+        if "side-lying" in text:
+            return "side-lying oral pose"
+        if "edge-of-bed" in text or "bed-edge" in text:
+            return "edge-of-bed oral pose"
+        if "spread-leg" in text:
+            return "spread-leg oral pose"
+        if "chair oral" in text:
+            return "chair oral pose"
+        return "mouth-to-genitals oral pose"
+    if "anal" in text or "ass" in text or "rear-entry" in text:
+        if "bed-edge" in text or "edge-of-bed" in text:
+            return "bed-edge rear-entry anal pose"
+        if "bent-over" in text:
+            return "bent-over rear-entry anal pose"
+        if "doggy" in text:
+            return "doggy-style anal pose"
+        return "rear-entry anal pose"
+    positions = (
+        "missionary",
+        "cowgirl",
+        "reverse cowgirl",
+        "doggy style",
+        "standing sex",
+        "spooning sex",
+        "edge-of-bed",
+        "kneeling straddle",
+        "lotus",
+        "bent-over",
+    )
+    for position in positions:
+        if position in text:
+            return f"{position.replace('doggy style', 'doggy-style')} pose"
+    if "threesome" in text or "three-body" in text:
+        return "three-body explicit sex pose"
+    if "group" in text or "orgy" in text:
+        return "multi-body explicit sex pose"
+    if "penetrat" in text or "thrust" in text:
+        return "hip-aligned penetrative sex pose"
+    return ""
+
+
+def _hardcore_pose_arrangement(anchor: str, role_graph: str, hard_item: str, composition: str = "") -> str:
+    text = " ".join(_clean(part).lower() for part in (anchor, role_graph, hard_item, composition) if _clean(part))
+    if not text:
+        return ""
+    if "double-penetration" in text or "double penetration" in text:
+        if "toy" in text:
+            return "with the woman's hips spread and front-and-back alignment visible"
+        return "with the central body held between front-and-back contact"
+    if "anal" in text or "rear-entry" in text:
+        return "with the woman's hips raised, ass exposed, and penetration alignment visible"
+    if "cunnilingus" in text or "mouth on her pussy" in text or "pussy licking" in text:
+        return "with the woman's thighs open and the giver's mouth pressed to her pussy"
+    if "oral" in text or "blowjob" in text or "penis in her mouth" in text or "penis in mouth" in text:
+        if "sixty-nine" in text:
+            return "with both bodies arranged mouth-to-genitals"
+        if "takes the man's penis in her mouth" in text or "penis in her mouth" in text:
+            return "with the woman's mouth close to the man's hips"
+        return "with mouth and genitals aligned clearly"
+    if "threesome" in text or "three-body" in text:
+        return "with all three adult bodies clearly placed around the central subject"
+    if "group" in text or "orgy" in text:
+        return "with each adult body readable in the shared sex act"
+    if "penetrat" in text or "thrust" in text:
+        return "with hips aligned and legs open around the contact point"
+    return ""
+
+
+def _hardcore_item_detail(hard_item: str) -> str:
+    text = _clean(hard_item).rstrip(".")
+    if not text:
+        return ""
+    text = re.sub(r"^hardcore\s+", "", text, flags=re.IGNORECASE)
+    text = re.sub(r"^explicit\s+", "", text, flags=re.IGNORECASE)
+    text = re.sub(r"^(?:mouth-to-genitals|double-contact sex|adult group pile|sex pile)\s+pose:\s*", "", text, flags=re.IGNORECASE)
+    text = re.sub(r"^(?:oral|threesome|orgy)\s+scene\s+with\s+", "", text, flags=re.IGNORECASE)
+    text = re.sub(r"^(?:threesome|orgy)\s+pose:\s*", "", text, flags=re.IGNORECASE)
+    act_patterns = (
+        r"(?:penis and toy|toy and strap-on|toy-assisted|front-and-back|hardcore|deep|kneeling|standing supported)?\s*double penetration",
+        r"toy-assisted vaginal and anal penetration at the same time",
+        r"vaginal and anal penetration at the same time",
+        r"one penis in pussy and one penis in ass",
+        r"anal penetration with visible genital contact",
+        r"rear-entry anal penetration",
+        r"anal sex with spread cheeks",
+        r"ass stretched around a penis",
+        r"penis entering ass",
+        r"deep anal sex",
+        r"bent-over anal sex",
+        r"hardcore anal thrusting",
+        r"vaginal penetration with visible genital contact",
+        r"penis entering pussy",
+        r"pussy stretched around a penis",
+        r"deep vaginal sex",
+        r"explicit penetrative sex",
+        r"hardcore vaginal thrusting",
+        r"full-body penetrative sex",
+        r"close-contact vaginal sex",
+        r"fellatio with penis in mouth",
+        r"deepthroat blowjob",
+        r"blowjob",
+        r"penis sucking with visible saliva",
+        r"cunnilingus with tongue on pussy",
+        r"face-sitting cunnilingus",
+        r"pussy licking with thighs spread",
+        r"oral sex with tongue and fingers",
+        r"mouth on genitals with explicit contact",
+        r"sixty-nine oral sex",
+    )
+    act_pattern = "|".join(act_patterns)
+    position_pattern = (
+        r"missionary position|cowgirl position|reverse cowgirl position|doggy style position|"
+        r"standing sex position|spooning sex position|edge-of-bed position|kneeling straddle position|"
+        r"lotus sex position|bent-over position|kneeling oral position|face-sitting position|"
+        r"sixty-nine position|edge-of-bed oral position|standing oral position|reclining cunnilingus position|"
+        r"straddled oral position|side-lying oral position|spread-leg oral position|chair oral position"
+    )
+    text = re.sub(
+        rf"^({position_pattern})\s+(?:while|with|featuring)\s+(?:{act_pattern})\s*,?\s*",
+        r"\1, ",
+        text,
+        flags=re.IGNORECASE,
+    )
+    text = re.sub(
+        rf"^(?:{act_pattern})\s*(?:in|from|on|with|while|featuring)?\s*",
+        "",
+        text,
+        flags=re.IGNORECASE,
+    )
+    text = re.sub(r"^(?:position|pose)\s+", "", text, flags=re.IGNORECASE)
+    text = re.sub(r"^with\s+", "", text, flags=re.IGNORECASE)
+    text = re.sub(r"\bwith with\b", "with", text, flags=re.IGNORECASE)
+    text = re.sub(r",\s*with\s+", ", ", text, flags=re.IGNORECASE)
+    text = re.sub(r",\s+and\s+", ", ", text)
+    text = re.sub(r"\s*,\s*", ", ", text).strip(" ,;")
+    return _clean(text)
+
+
+def _dedupe_hardcore_detail(detail: str, anchor: str) -> str:
+    detail = _clean(detail)
+    anchor_lower = anchor.lower()
+    duplicate_phrases = {
+        "front-and-back": (r"front-and-back contact",),
+        "side-lying oral": (r"side-lying oral position",),
+        "kneeling oral": (r"kneeling oral position",),
+        "face-sitting": (r"face-sitting position",),
+        "sixty-nine": (
+            r"sixty-nine position",
+            r"sixty-nine oral sex",
+            r"kneeling oral position",
+            r"face-sitting position",
+            r"edge-of-bed oral position",
+            r"standing oral position",
+            r"reclining cunnilingus position",
+            r"straddled oral position",
+            r"side-lying oral position",
+            r"spread-leg oral position",
+            r"chair oral position",
+        ),
+        "edge-of-bed oral": (r"edge-of-bed oral position",),
+        "standing oral": (r"standing oral position",),
+        "spread-leg oral": (r"spread-leg oral position",),
+        "chair oral": (r"chair oral position",),
+        "reclining cunnilingus": (r"reclining cunnilingus position",),
+        "straddled cunnilingus": (r"straddled oral position", r"straddled cunnilingus position"),
+        "open-thigh cunnilingus": (r"reclining cunnilingus position", r"straddled cunnilingus position"),
+        "bent-over": (r"bent-over position",),
+        "missionary": (r"missionary position",),
+        "cowgirl": (r"cowgirl position",),
+        "reverse cowgirl": (r"reverse cowgirl position",),
+        "doggy-style": (r"doggy style position",),
+        "edge-of-bed": (r"edge-of-bed position",),
+    }
+    for anchor_token, phrases in duplicate_phrases.items():
+        if anchor_token in anchor_lower:
+            for phrase in phrases:
+                detail = re.sub(rf"\b{phrase}\b,?\s*", "", detail, flags=re.IGNORECASE)
+    detail = re.sub(r"^\s*,\s*", "", detail)
+    detail = re.sub(r",\s*,", ",", detail)
+    return _clean(detail).strip(" ,;")
+
+
+def _hardcore_action_sentence(role_graph: str, hard_item: str, composition: str = "") -> str:
     role_graph = _clean(role_graph).rstrip(".")
     hard_item = _clean(hard_item).rstrip(".")
     role_graph = re.sub(
@@ -284,12 +509,30 @@ def _hardcore_action_sentence(role_graph: str, hard_item: str) -> str:
         role_graph,
         flags=re.IGNORECASE,
     )
+    role_graph = re.sub(
+        r"\bthe man thrusts his penis into the woman while a toy adds a second penetration point\b",
+        "the man's penis thrusts into the woman while a toy adds the second penetration point",
+        role_graph,
+        flags=re.IGNORECASE,
+    )
+    role_graph = re.sub(
+        r"\bthe man thrusts his penis into the woman\b",
+        "the man's penis thrusts into the woman",
+        role_graph,
+        flags=re.IGNORECASE,
+    )
     role_graph = re.sub(
         r"\bthe man penetrates the woman anally\b",
         "the man's penis thrusts into the woman's ass",
         role_graph,
         flags=re.IGNORECASE,
     )
+    role_graph = re.sub(
+        r"\bthe man thrusts his penis into the woman's ass\b",
+        "the man's penis thrusts into the woman's ass",
+        role_graph,
+        flags=re.IGNORECASE,
+    )
     role_graph = re.sub(
         r"\bthe man penetrates the woman\b",
         "the man's penis thrusts into the woman",
@@ -308,13 +551,52 @@ def _hardcore_action_sentence(role_graph: str, hard_item: str) -> str:
         role_graph,
         flags=re.IGNORECASE,
     )
-    if hard_item and role_graph:
+    detail = _hardcore_item_detail(hard_item)
-        return f"Explicit hardcore action: {role_graph}; {hard_item}"
+    anchor = _hardcore_pose_anchor(role_graph, hard_item, composition)
-    if role_graph:
+    detail = _dedupe_hardcore_detail(detail, anchor) if anchor else detail
-        return f"Explicit hardcore action: {role_graph}"
+    arrangement = _hardcore_pose_arrangement(anchor, role_graph, hard_item, composition)
-    if hard_item:
+    anchor_phrase = _with_indefinite_article(anchor) if anchor else ""
-        return f"Explicit hardcore action: {hard_item}"
+    if arrangement and anchor_phrase:
-    return ""
+        anchor_phrase = f"{anchor_phrase} {arrangement}"
+    if role_graph and anchor_phrase:
+        sentence = f"In {anchor_phrase}, {role_graph}"
+    elif role_graph:
+        sentence = role_graph
+    elif detail and anchor_phrase:
+        sentence = f"In {anchor_phrase}, {detail}"
+        detail = ""
+    else:
+        sentence = detail or hard_item
+        detail = ""
+    if detail:
+        sentence = f"{sentence}; {detail}"
+    return sentence
+
+
+def _composition_phrase(composition: Any, action: str = "", prefix: str = "framed as") -> str:
+    composition = _clean(composition)
+    if not composition:
+        return ""
+    action_lower = _clean(action).lower()
+    composition_lower = composition.lower()
+    oral_pose_tokens = (
+        "kneeling oral",
+        "side-lying oral",
+        "spread-leg oral",
+        "standing oral",
+        "edge-of-bed oral",
+        "face-sitting",
+        "sixty-nine",
+        "reclining cunnilingus",
+        "straddled oral",
+        "chair oral",
+    )
+    if "oral" in action_lower:
+        composition_oral_tokens = [token for token in oral_pose_tokens if token in composition_lower]
+        if composition_oral_tokens and not any(token in action_lower for token in composition_oral_tokens):
+            match = re.search(r"\bwith\s+(.+)$", composition, flags=re.IGNORECASE)
+            return f"framed with {match.group(1)}" if match else ""
+    return f"{prefix} {composition}"
 
 
 def _clean_age(age: Any) -> str:
@@ -454,9 +736,11 @@ def _normal_row_to_krea(row: dict[str, Any], detail_level: str, style_mode: str)
         cast_prose, cast_labels = _cast_prose(cast_descriptor_text)
         if not cast_labels and women_count == 1 and men_count == 1:
             cast_labels = ["Woman A", "Man A"]
-        role_graph = _natural_label_text(_clean(row.get("role_graph")), cast_labels)
+        role_graph = _sanitize_scene_text_for_cast(row.get("role_graph"), cast_labels)
+        item = _sanitize_scene_text_for_cast(item, cast_labels)
+        role_graph = _natural_label_text(role_graph, cast_labels)
         item = _natural_label_text(item, cast_labels)
-        action = _hardcore_action_sentence(role_graph, item)
+        action = _hardcore_action_sentence(role_graph, item, composition)
         parts = [
             action,
             cast_prose,
@@ -464,7 +748,7 @@ def _normal_row_to_krea(row: dict[str, Any], detail_level: str, style_mode: str)
             f"The cast includes {cast}" if cast and not cast_prose and not (women_count == 1 and men_count == 1) else "",
             f"The setting is {scene}" if scene else "",
             f"Facial expressions are {expression}" if expression else "",
-            f"The image is framed as {composition}" if composition else "",
+            _composition_phrase(composition, action, "The image is framed as"),
             camera,
             style if detail_level != "concise" else "",
         ]
@@ -550,7 +834,7 @@ def _insta_pair_to_krea(row: dict[str, Any], detail_level: str, style_mode: str)
     hard_role_graph = _sanitize_scene_text_for_cast(hard.get("role_graph"), hard_labels)
     hard_item = _natural_label_text(hard_item, hard_labels)
     hard_role_graph = _natural_label_text(hard_role_graph, hard_labels)
-    hard_action = _hardcore_action_sentence(hard_role_graph, hard_item)
+    hard_action = _hardcore_action_sentence(hard_role_graph, hard_item, hard_composition)
     same_soft_cast = options.get("softcore_cast") == "same_as_hardcore"
     soft_cast_presence = (
         f"{_label_join(soft_labels)} are together in a non-explicit teaser pose, with no sex act or genital contact"
@@ -586,7 +870,7 @@ def _insta_pair_to_krea(row: dict[str, Any], detail_level: str, style_mode: str)
         hard_cast_prose,
         f"set in {hard_scene}" if hard_scene else "",
         f"with {hard.get('expression')}" if hard.get("expression") else "",
-        f"framed as {hard_composition}" if hard_composition else "",
+        _composition_phrase(hard_composition, hard_action),
         hard_camera,
         hard_style if detail_level != "concise" else "",
     ]