Extract caption metadata route assembly
This commit is contained in:
+66
-242
@@ -4,12 +4,14 @@ import re
|
||||
from typing import Any
|
||||
|
||||
try:
|
||||
from . import caption_metadata_routes
|
||||
from . import caption_policy
|
||||
from . import formatter_input as input_policy
|
||||
from . import krea_cast as cast_policy
|
||||
from . import route_metadata as route_metadata_policy
|
||||
from .prompt_hygiene import sanitize_prose_text
|
||||
except ImportError: # Allows local smoke tests with `python -c`.
|
||||
import caption_metadata_routes
|
||||
import caption_policy
|
||||
import formatter_input as input_policy
|
||||
import krea_cast as cast_policy
|
||||
@@ -282,270 +284,92 @@ def _detail_allows(level: str, dense_only: bool = False) -> bool:
|
||||
return caption_policy.detail_allows(level, dense_only=dense_only)
|
||||
|
||||
|
||||
def _caption_metadata_route_dependencies() -> caption_metadata_routes.CaptionMetadataRouteDependencies:
|
||||
return caption_metadata_routes.CaptionMetadataRouteDependencies(
|
||||
item_labels=ITEM_LABELS,
|
||||
clean_text=_clean_text,
|
||||
row_value=_row_value,
|
||||
field_row_value=lambda row, key: _row_value(row, key),
|
||||
clean_clothing=_clean_clothing,
|
||||
normalize_composition=_normalize_composition,
|
||||
expression_disabled=_expression_disabled,
|
||||
detail_allows=_detail_allows,
|
||||
join_sentences=_join_sentences,
|
||||
human_join=_human_join,
|
||||
article=_article,
|
||||
cap_first=_cap_first,
|
||||
body_phrase=_body_phrase,
|
||||
single_caption_front=_single_caption_front,
|
||||
pose_clause=_pose_clause,
|
||||
age_subject=_age_subject,
|
||||
clean_age_phrase=_clean_age_phrase,
|
||||
subject_phrase_from_counts=_subject_phrase_from_counts,
|
||||
verb_for_row=_verb_for_row,
|
||||
metadata_action_label=_metadata_action_label,
|
||||
natural_cast_descriptor_text=_natural_cast_descriptor_text,
|
||||
cast_labels=_cast_labels,
|
||||
natural_label_text=_natural_label_text,
|
||||
metadata_to_prose=_metadata_to_prose,
|
||||
)
|
||||
|
||||
|
||||
def _caption_metadata_route_request(
|
||||
row: dict[str, Any],
|
||||
detail_level: str,
|
||||
keep_style: bool,
|
||||
) -> caption_metadata_routes.CaptionMetadataRouteRequest:
|
||||
return caption_metadata_routes.CaptionMetadataRouteRequest(
|
||||
row=row,
|
||||
detail_level=detail_level,
|
||||
keep_style=keep_style,
|
||||
)
|
||||
|
||||
|
||||
def _single_from_row(row: dict[str, Any], detail_level: str, keep_style: bool) -> tuple[str, str] | None:
|
||||
subject = _clean_text(row.get("primary_subject") or row.get("subject") or "")
|
||||
if subject not in ("woman", "man"):
|
||||
return None
|
||||
|
||||
caption_front = _single_caption_front(row)
|
||||
age = _clean_text(row.get("age") or row.get("age_band") or caption_front.get("caption_age") or "")
|
||||
body_phrase = _row_value(row, "body_phrase") or caption_front.get("caption_body_phrase", "")
|
||||
if not body_phrase:
|
||||
body = _clean_text(row.get("body_type") or row.get("body") or "")
|
||||
figure = _clean_text(row.get("figure"))
|
||||
body_phrase = _body_phrase(body, figure)
|
||||
|
||||
skin = _row_value(row, "skin") or caption_front.get("caption_skin", "")
|
||||
hair = _row_value(row, "hair") or caption_front.get("caption_hair", "")
|
||||
eyes = _row_value(row, "eyes") or caption_front.get("caption_eyes", "")
|
||||
item = _row_value(row, "item", ITEM_LABELS)
|
||||
if item:
|
||||
item = _clean_clothing(item)
|
||||
if not item:
|
||||
item = _clean_clothing(_row_value(row, "clothing", ("Clothing", "Erotic outfit")))
|
||||
scene = _row_value(row, "scene_text", ("Scene", "Setting"))
|
||||
pose = _row_value(row, "pose", ("Pose",))
|
||||
expression = "" if _expression_disabled(row) else _row_value(row, "expression", ("Facial expression", "Facial expressions"))
|
||||
composition = _normalize_composition(_row_value(row, "composition", ("Composition",)))
|
||||
camera_scene = _clean_text(row.get("camera_scene_directive"))
|
||||
prop = _row_value(row, "prop", ("Prop/detail",))
|
||||
style = _row_value(row, "style") if keep_style else ""
|
||||
|
||||
parts = []
|
||||
opener = _age_subject(age, subject)
|
||||
appearance_details = [piece for piece in (skin, hair, eyes) if piece]
|
||||
if body_phrase:
|
||||
parts.append(f"{opener} has {_article(body_phrase)} {body_phrase}")
|
||||
elif appearance_details:
|
||||
parts.append(f"{opener} has {_human_join(appearance_details)}")
|
||||
else:
|
||||
parts.append(opener)
|
||||
if body_phrase and appearance_details:
|
||||
parts.append(f"{pronoun(subject)} has {_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 {_pose_clause(pose)}")
|
||||
if expression:
|
||||
parts.append(f"{possessive_pronoun(subject)} expression is {expression}")
|
||||
if scene:
|
||||
parts.append(f"The setting is {scene}")
|
||||
if _detail_allows(detail_level) and camera_scene:
|
||||
parts.append(camera_scene)
|
||||
if _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 _join_sentences(parts), "metadata(single)"
|
||||
return caption_metadata_routes.single_from_row(
|
||||
_caption_metadata_route_request(row, detail_level, keep_style),
|
||||
_caption_metadata_route_dependencies(),
|
||||
)
|
||||
|
||||
|
||||
def pronoun(subject: str) -> str:
|
||||
return "She" if subject == "woman" else "He"
|
||||
return caption_metadata_routes.pronoun(subject)
|
||||
|
||||
|
||||
def possessive_pronoun(subject: str) -> str:
|
||||
return "Her" if subject == "woman" else "His"
|
||||
return caption_metadata_routes.possessive_pronoun(subject)
|
||||
|
||||
|
||||
def _couple_clothing_sentence(clothing: 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}"
|
||||
return caption_metadata_routes.couple_clothing_sentence(clothing, _clean_text)
|
||||
|
||||
|
||||
def _couple_from_row(row: dict[str, Any], detail_level: str, keep_style: bool) -> tuple[str, str] | None:
|
||||
subject = _clean_text(row.get("subject_phrase") or row.get("primary_subject"))
|
||||
primary = _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 = _row_value(row, "age", ("Ages",)) or _clean_text(row.get("age_band"))
|
||||
body = _row_value(row, "body", ("Body types",)) or _clean_text(row.get("body_type"))
|
||||
pose = _row_value(row, "pose", ("Pose",))
|
||||
pose = pose.replace(", affectionate and flirtatious but non-explicit", "")
|
||||
clothing = _clean_clothing(_row_value(row, "item", ITEM_LABELS) or _row_value(row, "clothing", ("Clothing",)))
|
||||
scene = _row_value(row, "scene_text", ("Scene", "Setting"))
|
||||
expression = ""
|
||||
if not _expression_disabled(row):
|
||||
expression = _row_value(row, "character_expression_text") or _row_value(row, "expression", ("Facial expressions", "Facial expression"))
|
||||
composition = _normalize_composition(_row_value(row, "composition", ("Composition",)))
|
||||
camera_scene = _clean_text(row.get("camera_scene_directive"))
|
||||
style = _row_value(row, "style") if keep_style else ""
|
||||
|
||||
parts = [f"{_cap_first(subject)} are adults"]
|
||||
if ages:
|
||||
parts.append(f"The age detail is {_clean_age_phrase(ages)}")
|
||||
if body:
|
||||
parts.append(f"Their body types are {body}")
|
||||
if clothing:
|
||||
parts.append(_couple_clothing_sentence(clothing))
|
||||
if pose:
|
||||
parts.append(f"The pose is {pose}")
|
||||
if scene:
|
||||
parts.append(f"The setting is {scene}")
|
||||
if _detail_allows(detail_level) and camera_scene:
|
||||
parts.append(camera_scene)
|
||||
if expression:
|
||||
parts.append(f"Their expressions are {expression}")
|
||||
if _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 _join_sentences(parts), "metadata(couple)"
|
||||
return caption_metadata_routes.couple_from_row(
|
||||
_caption_metadata_route_request(row, detail_level, keep_style),
|
||||
_caption_metadata_route_dependencies(),
|
||||
)
|
||||
|
||||
|
||||
def _configured_cast_from_row(row: dict[str, Any], detail_level: str, keep_style: bool) -> tuple[str, str] | None:
|
||||
if _clean_text(row.get("subject_type")) != "configured_cast":
|
||||
if "hardcore sexual poses" not in _clean_text(row.get("main_category")).lower():
|
||||
return None
|
||||
|
||||
subject = _subject_phrase_from_counts(row)
|
||||
verb = _verb_for_row(row)
|
||||
cast = _row_value(row, "cast_summary", ("Cast",))
|
||||
role_graph = _row_value(row, "role_graph", ("Role graph",))
|
||||
item = _row_value(row, "item", ITEM_LABELS)
|
||||
scene = _row_value(row, "scene_text", ("Setting", "Scene"))
|
||||
expression = ""
|
||||
if not _expression_disabled(row):
|
||||
expression = _row_value(row, "character_expression_text") or _row_value(row, "expression", ("Facial expressions", "Facial expression"))
|
||||
composition = _normalize_composition(_row_value(row, "composition", ("Composition",)))
|
||||
camera_scene = _clean_text(row.get("camera_scene_directive"))
|
||||
cast_descriptor_text = _row_value(row, "cast_descriptor_text", ("Characters", "Cast descriptors"))
|
||||
scene_kind = _row_value(row, "scene_kind") or "explicit adult sex scene"
|
||||
style = _row_value(row, "style") if keep_style else ""
|
||||
|
||||
parts = [f"{_cap_first(subject)} {verb} shown as a consensual {scene_kind}"]
|
||||
if 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:
|
||||
parts.append(role_graph)
|
||||
if item:
|
||||
parts.append(f"The {_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 _detail_allows(detail_level):
|
||||
parts.append(", ".join(scene_bits))
|
||||
if _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 _join_sentences(parts), "metadata(configured_cast)"
|
||||
return caption_metadata_routes.configured_cast_from_row(
|
||||
_caption_metadata_route_request(row, detail_level, keep_style),
|
||||
_caption_metadata_route_dependencies(),
|
||||
)
|
||||
|
||||
|
||||
def _group_or_layout_from_row(row: dict[str, Any], detail_level: str, keep_style: bool) -> tuple[str, str] | None:
|
||||
primary = _clean_text(row.get("primary_subject"))
|
||||
if "group" not in primary and primary != "layout scene":
|
||||
return None
|
||||
|
||||
subject = _row_value(row, "subject_phrase") or primary
|
||||
age = _row_value(row, "age", ("Ages",)) or _clean_text(row.get("age_band"))
|
||||
item = _clean_clothing(_row_value(row, "item", ITEM_LABELS) or _row_value(row, "clothing", ("Clothing",)))
|
||||
scene = _row_value(row, "scene_text", ("Scene", "Setting"))
|
||||
expression = ""
|
||||
if not _expression_disabled(row):
|
||||
expression = _row_value(row, "character_expression_text") or _row_value(row, "expression", ("Facial expressions", "Facial expression"))
|
||||
composition = _normalize_composition(_row_value(row, "composition", ("Composition",)))
|
||||
camera_scene = _clean_text(row.get("camera_scene_directive"))
|
||||
style = _row_value(row, "style") if keep_style else ""
|
||||
|
||||
if primary == "layout scene":
|
||||
parts = [f"{_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"{_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 _detail_allows(detail_level) and camera_scene:
|
||||
parts.append(camera_scene)
|
||||
if _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 _join_sentences(parts), "metadata(group_layout)"
|
||||
return caption_metadata_routes.group_or_layout_from_row(
|
||||
_caption_metadata_route_request(row, detail_level, keep_style),
|
||||
_caption_metadata_route_dependencies(),
|
||||
)
|
||||
|
||||
|
||||
def _insta_of_pair_from_row(row: dict[str, Any], detail_level: str, keep_style: bool) -> tuple[str, str] | None:
|
||||
if _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 = _metadata_to_prose(soft_row, detail_level, keep_style)
|
||||
hard_text, _hard_method = _metadata_to_prose(hard_row_for_text, detail_level, keep_style)
|
||||
descriptor = _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(_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(_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(_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 = _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"))
|
||||
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 _join_sentences(parts), "metadata(insta_of_pair)"
|
||||
return caption_metadata_routes.insta_of_pair_from_row(
|
||||
_caption_metadata_route_request(row, detail_level, keep_style),
|
||||
_caption_metadata_route_dependencies(),
|
||||
)
|
||||
|
||||
|
||||
def _metadata_to_prose(row: dict[str, Any], detail_level: str, keep_style: bool) -> tuple[str, str]:
|
||||
|
||||
Reference in New Issue
Block a user