Extract caption metadata route assembly

2026-06-27 11:31:39 +02:00
parent 0ccb87799b
commit b38b27acfd
5 changed files with 589 additions and 247 deletions
@@ -0,0 +1,391 @@
+from __future__ import annotations
+
+import re
+from dataclasses import dataclass
+from typing import Any, Callable
+
+
+@dataclass(frozen=True)
+class CaptionMetadataRouteRequest:
+    row: dict[str, Any]
+    detail_level: str
+    keep_style: bool
+
+
+@dataclass(frozen=True)
+class CaptionMetadataRoute:
+    prose: str
+    method: str
+
+    def as_tuple(self) -> tuple[str, str]:
+        return self.prose, self.method
+
+
+@dataclass(frozen=True)
+class CaptionMetadataRouteDependencies:
+    item_labels: tuple[str, ...]
+    clean_text: Callable[[Any], str]
+    row_value: Callable[[dict[str, Any], str, tuple[str, ...]], str]
+    field_row_value: Callable[[dict[str, Any], str], str]
+    clean_clothing: Callable[[str], str]
+    normalize_composition: Callable[[str], str]
+    expression_disabled: Callable[[dict[str, Any]], bool]
+    detail_allows: Callable[..., bool]
+    join_sentences: Callable[[list[str]], str]
+    human_join: Callable[[list[str]], str]
+    article: Callable[[str], str]
+    cap_first: Callable[[str], str]
+    body_phrase: Callable[[Any, Any], str]
+    single_caption_front: Callable[[dict[str, Any]], dict[str, str]]
+    pose_clause: Callable[[str], str]
+    age_subject: Callable[[str, str], str]
+    clean_age_phrase: Callable[[str], str]
+    subject_phrase_from_counts: Callable[[dict[str, Any]], str]
+    verb_for_row: Callable[[dict[str, Any]], str]
+    metadata_action_label: Callable[[dict[str, Any]], str]
+    natural_cast_descriptor_text: Callable[[str], str]
+    cast_labels: Callable[[str], list[str]]
+    natural_label_text: Callable[[Any, list[str]], str]
+    metadata_to_prose: Callable[[dict[str, Any], str, bool], tuple[str, str]]
+
+
+def pronoun(subject: str) -> str:
+    return "She" if subject == "woman" else "He"
+
+
+def possessive_pronoun(subject: str) -> str:
+    return "Her" if subject == "woman" else "His"
+
+
+def couple_clothing_sentence(clothing: str, clean_text: Callable[[Any], str]) -> str:
+    clothing = clean_text(clothing)
+    lower = clothing.lower()
+    partner_text = re.sub(r"\bPartner ([AB]) wears\b", r"Partner \1 wearing", clothing)
+    partner_text = re.sub(r"\bPartner ([AB]) has\b", r"Partner \1 with", partner_text)
+    if lower.startswith("partner a "):
+        return f"The outfits show {partner_text}"
+    if lower.startswith(("two ", "paired ", "coordinated ")):
+        return f"The outfits are {partner_text}"
+    return f"They wear {clothing}"
+
+
+def single_from_row_result(
+    request: CaptionMetadataRouteRequest,
+    deps: CaptionMetadataRouteDependencies,
+) -> CaptionMetadataRoute | None:
+    row = request.row
+    detail_level = request.detail_level
+    keep_style = request.keep_style
+    subject = deps.clean_text(row.get("primary_subject") or row.get("subject") or "")
+    if subject not in ("woman", "man"):
+        return None
+
+    caption_front = deps.single_caption_front(row)
+    age = deps.clean_text(row.get("age") or row.get("age_band") or caption_front.get("caption_age") or "")
+    body_phrase = deps.field_row_value(row, "body_phrase") or caption_front.get("caption_body_phrase", "")
+    if not body_phrase:
+        body = deps.clean_text(row.get("body_type") or row.get("body") or "")
+        figure = deps.clean_text(row.get("figure"))
+        body_phrase = deps.body_phrase(body, figure)
+
+    skin = deps.field_row_value(row, "skin") or caption_front.get("caption_skin", "")
+    hair = deps.field_row_value(row, "hair") or caption_front.get("caption_hair", "")
+    eyes = deps.field_row_value(row, "eyes") or caption_front.get("caption_eyes", "")
+    item = deps.row_value(row, "item", deps.item_labels)
+    if item:
+        item = deps.clean_clothing(item)
+    if not item:
+        item = deps.clean_clothing(deps.row_value(row, "clothing", ("Clothing", "Erotic outfit")))
+    scene = deps.row_value(row, "scene_text", ("Scene", "Setting"))
+    pose = deps.row_value(row, "pose", ("Pose",))
+    expression = "" if deps.expression_disabled(row) else deps.row_value(row, "expression", ("Facial expression", "Facial expressions"))
+    composition = deps.normalize_composition(deps.row_value(row, "composition", ("Composition",)))
+    camera_scene = deps.clean_text(row.get("camera_scene_directive"))
+    prop = deps.row_value(row, "prop", ("Prop/detail",))
+    style = deps.field_row_value(row, "style") if keep_style else ""
+
+    parts = []
+    opener = deps.age_subject(age, subject)
+    appearance_details = [piece for piece in (skin, hair, eyes) if piece]
+    if body_phrase:
+        parts.append(f"{opener} has {deps.article(body_phrase)} {body_phrase}")
+    elif appearance_details:
+        parts.append(f"{opener} has {deps.human_join(appearance_details)}")
+    else:
+        parts.append(opener)
+    if body_phrase and appearance_details:
+        parts.append(f"{pronoun(subject)} has {deps.human_join(appearance_details)}")
+    if item:
+        verb = "wears" if subject == "woman" else "is dressed in"
+        parts.append(f"{pronoun(subject)} {verb} {item}")
+    if prop:
+        parts.append(f"{pronoun(subject)} is {prop}")
+    if pose:
+        parts.append(f"{pronoun(subject)} is {deps.pose_clause(pose)}")
+    if expression:
+        parts.append(f"{possessive_pronoun(subject)} expression is {expression}")
+    if scene:
+        parts.append(f"The setting is {scene}")
+    if deps.detail_allows(detail_level) and camera_scene:
+        parts.append(camera_scene)
+    if deps.detail_allows(detail_level) and composition:
+        parts.append(f"The composition is {composition}")
+    if keep_style and style:
+        parts.append(f"The visual style is {style}")
+    return CaptionMetadataRoute(deps.join_sentences(parts), "metadata(single)")
+
+
+def couple_from_row_result(
+    request: CaptionMetadataRouteRequest,
+    deps: CaptionMetadataRouteDependencies,
+) -> CaptionMetadataRoute | None:
+    row = request.row
+    detail_level = request.detail_level
+    keep_style = request.keep_style
+    subject = deps.clean_text(row.get("subject_phrase") or row.get("primary_subject"))
+    primary = deps.clean_text(row.get("primary_subject"))
+    if "couple" not in primary and subject not in ("two women", "two men", "a woman and a man"):
+        if not primary.startswith("two ") and " and " not in subject:
+            return None
+    if subject == "woman and man":
+        subject = "a woman and a man"
+
+    ages = deps.row_value(row, "age", ("Ages",)) or deps.clean_text(row.get("age_band"))
+    body = deps.row_value(row, "body", ("Body types",)) or deps.clean_text(row.get("body_type"))
+    pose = deps.row_value(row, "pose", ("Pose",))
+    pose = pose.replace(", affectionate and flirtatious but non-explicit", "")
+    clothing = deps.clean_clothing(deps.row_value(row, "item", deps.item_labels) or deps.row_value(row, "clothing", ("Clothing",)))
+    scene = deps.row_value(row, "scene_text", ("Scene", "Setting"))
+    expression = ""
+    if not deps.expression_disabled(row):
+        expression = deps.row_value(row, "character_expression_text") or deps.row_value(
+            row,
+            "expression",
+            ("Facial expressions", "Facial expression"),
+        )
+    composition = deps.normalize_composition(deps.row_value(row, "composition", ("Composition",)))
+    camera_scene = deps.clean_text(row.get("camera_scene_directive"))
+    style = deps.field_row_value(row, "style") if keep_style else ""
+
+    parts = [f"{deps.cap_first(subject)} are adults"]
+    if ages:
+        parts.append(f"The age detail is {deps.clean_age_phrase(ages)}")
+    if body:
+        parts.append(f"Their body types are {body}")
+    if clothing:
+        parts.append(couple_clothing_sentence(clothing, deps.clean_text))
+    if pose:
+        parts.append(f"The pose is {pose}")
+    if scene:
+        parts.append(f"The setting is {scene}")
+    if deps.detail_allows(detail_level) and camera_scene:
+        parts.append(camera_scene)
+    if expression:
+        parts.append(f"Their expressions are {expression}")
+    if deps.detail_allows(detail_level) and composition:
+        parts.append(f"The composition is {composition}")
+    if keep_style and style:
+        parts.append(f"The visual style is {style}")
+    return CaptionMetadataRoute(deps.join_sentences(parts), "metadata(couple)")
+
+
+def configured_cast_from_row_result(
+    request: CaptionMetadataRouteRequest,
+    deps: CaptionMetadataRouteDependencies,
+) -> CaptionMetadataRoute | None:
+    row = request.row
+    detail_level = request.detail_level
+    keep_style = request.keep_style
+    if deps.clean_text(row.get("subject_type")) != "configured_cast":
+        if "hardcore sexual poses" not in deps.clean_text(row.get("main_category")).lower():
+            return None
+
+    subject = deps.subject_phrase_from_counts(row)
+    verb = deps.verb_for_row(row)
+    cast = deps.row_value(row, "cast_summary", ("Cast",))
+    role_graph = deps.row_value(row, "role_graph", ("Role graph",))
+    item = deps.row_value(row, "item", deps.item_labels)
+    scene = deps.row_value(row, "scene_text", ("Setting", "Scene"))
+    expression = ""
+    if not deps.expression_disabled(row):
+        expression = deps.row_value(row, "character_expression_text") or deps.row_value(
+            row,
+            "expression",
+            ("Facial expressions", "Facial expression"),
+        )
+    composition = deps.normalize_composition(deps.row_value(row, "composition", ("Composition",)))
+    camera_scene = deps.clean_text(row.get("camera_scene_directive"))
+    cast_descriptor_text = deps.row_value(row, "cast_descriptor_text", ("Characters", "Cast descriptors"))
+    scene_kind = deps.field_row_value(row, "scene_kind") or "explicit adult sex scene"
+    style = deps.field_row_value(row, "style") if keep_style else ""
+
+    parts = [f"{deps.cap_first(subject)} {verb} shown as a consensual {scene_kind}"]
+    if cast_descriptor_text:
+        parts.append(deps.natural_cast_descriptor_text(cast_descriptor_text))
+    if cast and not cast_descriptor_text:
+        parts.append(f"The cast is {cast}")
+    if role_graph:
+        parts.append(role_graph)
+    if item:
+        parts.append(f"The {deps.metadata_action_label(row)} is {item}")
+    scene_bits = []
+    if scene:
+        scene_bits.append(f"set in {scene}")
+    if expression:
+        scene_bits.append(f"with {expression}")
+    if composition:
+        scene_bits.append(f"framed as {composition}")
+    if scene_bits and deps.detail_allows(detail_level):
+        parts.append(", ".join(scene_bits))
+    if deps.detail_allows(detail_level) and camera_scene:
+        parts.append(camera_scene)
+    if keep_style and style:
+        parts.append(f"The visual style is {style}")
+    return CaptionMetadataRoute(deps.join_sentences(parts), "metadata(configured_cast)")
+
+
+def group_or_layout_from_row_result(
+    request: CaptionMetadataRouteRequest,
+    deps: CaptionMetadataRouteDependencies,
+) -> CaptionMetadataRoute | None:
+    row = request.row
+    detail_level = request.detail_level
+    keep_style = request.keep_style
+    primary = deps.clean_text(row.get("primary_subject"))
+    if "group" not in primary and primary != "layout scene":
+        return None
+
+    subject = deps.field_row_value(row, "subject_phrase") or primary
+    age = deps.row_value(row, "age", ("Ages",)) or deps.clean_text(row.get("age_band"))
+    item = deps.clean_clothing(deps.row_value(row, "item", deps.item_labels) or deps.row_value(row, "clothing", ("Clothing",)))
+    scene = deps.row_value(row, "scene_text", ("Scene", "Setting"))
+    expression = ""
+    if not deps.expression_disabled(row):
+        expression = deps.row_value(row, "character_expression_text") or deps.row_value(
+            row,
+            "expression",
+            ("Facial expressions", "Facial expression"),
+        )
+    composition = deps.normalize_composition(deps.row_value(row, "composition", ("Composition",)))
+    camera_scene = deps.clean_text(row.get("camera_scene_directive"))
+    style = deps.field_row_value(row, "style") if keep_style else ""
+
+    if primary == "layout scene":
+        parts = [f"{deps.cap_first(subject)} is arranged as an adults-only designed illustration layout"]
+        if expression:
+            parts.append(f"The featured expression is {expression}")
+    else:
+        parts = [f"{deps.cap_first(subject)} includes adults"]
+        if age:
+            parts[0] += f" ages {age}"
+        if item:
+            parts.append(f"They wear {item}")
+        if expression:
+            parts.append(f"They show {expression}")
+    if scene:
+        parts.append(f"The setting is {scene}")
+    if deps.detail_allows(detail_level) and camera_scene:
+        parts.append(camera_scene)
+    if deps.detail_allows(detail_level) and composition:
+        parts.append(f"The composition is {composition}")
+    if keep_style and style:
+        parts.append(f"The visual style is {style}")
+    return CaptionMetadataRoute(deps.join_sentences(parts), "metadata(group_layout)")
+
+
+def insta_of_pair_from_row_result(
+    request: CaptionMetadataRouteRequest,
+    deps: CaptionMetadataRouteDependencies,
+) -> CaptionMetadataRoute | None:
+    row = request.row
+    detail_level = request.detail_level
+    keep_style = request.keep_style
+    if deps.clean_text(row.get("mode")).lower() != "insta/of":
+        return None
+    soft_row = row.get("softcore_row")
+    hard_row = row.get("hardcore_row")
+    if not isinstance(soft_row, dict) or not isinstance(hard_row, dict):
+        return None
+
+    hard_row_for_text = dict(hard_row)
+    options = row.get("options")
+    if isinstance(options, dict) and options.get("continuity") == "same_creator_same_room":
+        if soft_row.get("scene_text"):
+            hard_row_for_text["scene_text"] = soft_row["scene_text"]
+        if soft_row.get("composition"):
+            hard_row_for_text["composition"] = soft_row["composition"]
+
+    soft_text, _soft_method = deps.metadata_to_prose(soft_row, detail_level, keep_style)
+    hard_text, _hard_method = deps.metadata_to_prose(hard_row_for_text, detail_level, keep_style)
+    descriptor = deps.clean_text(row.get("shared_descriptor"))
+    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 = "; ".join(deps.clean_text(item) for item in cast_descriptors if deps.clean_text(item))
+    else:
+        cast_descriptor_text = deps.clean_text(cast_descriptors)
+    labels = deps.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(deps.natural_cast_descriptor_text(cast_descriptor_text))
+    elif descriptor:
+        parts.append(f"A {descriptor}")
+    if cast_descriptor_text and not same_soft_cast:
+        parts.append(deps.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")
+        if isinstance(partner_styling, dict):
+            outfits = partner_styling.get("outfits")
+            if isinstance(outfits, list):
+                outfit_text = deps.human_join([deps.clean_text(item) for item in outfits if deps.clean_text(item)])
+                outfit_text = deps.natural_label_text(outfit_text, labels)
+                if outfit_text:
+                    parts.append(f"Softcore partner styling: {outfit_text}")
+            pose = deps.clean_text(partner_styling.get("pose"))
+            if pose:
+                parts.append(f"The shared softcore cast pose is {pose}")
+    if soft_text:
+        parts.append(f"Softcore version: {soft_text}")
+    if hard_text:
+        parts.append(f"Hardcore version: {hard_text}")
+    if not parts:
+        return None
+    return CaptionMetadataRoute(deps.join_sentences(parts), "metadata(insta_of_pair)")
+
+
+def single_from_row(request: CaptionMetadataRouteRequest, deps: CaptionMetadataRouteDependencies) -> tuple[str, str] | None:
+    result = single_from_row_result(request, deps)
+    return result.as_tuple() if result else None
+
+
+def couple_from_row(request: CaptionMetadataRouteRequest, deps: CaptionMetadataRouteDependencies) -> tuple[str, str] | None:
+    result = couple_from_row_result(request, deps)
+    return result.as_tuple() if result else None
+
+
+def configured_cast_from_row(
+    request: CaptionMetadataRouteRequest,
+    deps: CaptionMetadataRouteDependencies,
+) -> tuple[str, str] | None:
+    result = configured_cast_from_row_result(request, deps)
+    return result.as_tuple() if result else None
+
+
+def group_or_layout_from_row(
+    request: CaptionMetadataRouteRequest,
+    deps: CaptionMetadataRouteDependencies,
+) -> tuple[str, str] | None:
+    result = group_or_layout_from_row_result(request, deps)
+    return result.as_tuple() if result else None
+
+
+def insta_of_pair_from_row(
+    request: CaptionMetadataRouteRequest,
+    deps: CaptionMetadataRouteDependencies,
+) -> tuple[str, str] | None:
+    result = insta_of_pair_from_row_result(request, deps)
+    return result.as_tuple() if result else None