from collections import defaultdict def classify_tags (tags: list[str], local_test: bool = False): # Dictionary for automatic classification classified_tags: defaultdict[str, str] = defaultdict(list) fuzzy_match_tags: defaultdict[str, str] = defaultdict(list) fuzzy_match_keylen = 0 fuzzy_match_category = "" unclassified_tags: list[str] = [] # Logic for automatic grouping for tag in tags: classified = False tag_new = tag.replace(" ", "_").replace("-", "_").replace("\\(", "(").replace("\\)", ")") # Replace spaces in source tags with underscores \" keyword = "" category = "" if tag_new in reversed_categories: category = reversed_categories[tag_new] classified = True else: tag_parts = tag_new.split("_") # Split tags by "_" to ensure keyword matching is based on whole words for keyword, category in reversed_categories.items(): keyword = keyword.replace("-", "_").strip("_") verify = tag_new.replace(keyword, "") # Check if the tag contains the keyword if (tag_new == keyword or tag_new.lstrip("0123456789") == keyword or (keyword in tag_new and (verify.startswith("_") or verify.endswith("_")))): classified = True elif any(tag_part == keyword for tag_part in tag_parts): classified = True elif local_test and keyword in tag_new and len(keyword) > fuzzy_match_keylen: fuzzy_match_keylen = len(keyword) fuzzy_match_category = category if classified: break if classified and tag not in classified_tags[category]: # Avoid duplicates classified_tags[category].append(tag) if not classified and fuzzy_match_keylen > 0 and tag not in fuzzy_match_tags[fuzzy_match_category]: classified = True fuzzy_match_tags[fuzzy_match_category].append(tag) fuzzy_match_keylen = 0 fuzzy_match_category = "" if not classified and tag not in unclassified_tags: unclassified_tags.append(tag) # Unclassified tags if local_test: # Output the grouping result for category, tags in classified_tags.items(): print(f"{category}:") print(", ".join(tags)) print() print() print("Fuzzy match:") for category, tags in fuzzy_match_tags.items(): print(f"{category}:") print(", ".join(tags)) print() print() if len(unclassified_tags) > 0: print(f"\nUnclassified tags: {len(unclassified_tags)}") print(f"{unclassified_tags[:200]}") # Display some unclassified tags return classified_tags, unclassified_tags # Define grouping rules (categories and keywords) categories = { "explicit" : ["sex", "69", "paizuri", "cum", "precum", "areola_slip", "hetero", "erection", "oral", "fellatio", "yaoi", "ejaculation", "ejaculating", "masturbation", "handjob", "bulge", "rape", "doggystyle", "threesome", "missionary", "object_insertion", "nipple", "nipples", "pussy", "anus", "penis", "groin", "testicles", "testicle", "anal", "cameltoe", "areolae", "dildo", "clitoris", "top-down_bottom-up", "gag", "groping", "gagged", "gangbang", "orgasm", "femdom", "incest", "bukkake", "breast_out", "vaginal", "vagina", "public_indecency", "breast_sucking", "folded", "cunnilingus", "foreskin", "bestiality", "footjob", "uterus", "flaccid", "defloration", "butt_plug", "cowgirl_position", "reverse_cowgirl_position", "squatting_cowgirl_position", "reverse_upright_straddle", "irrumatio", "deepthroat", "pokephilia", "gaping", "orgy", "cleft_of_venus", "futanari", "futasub", "futa", "cumdrip", "fingering", "vibrator", "partially_visible_vulva", "penetration", "penetrated", "cumshot", "exhibitionism", "breast_milk", "grinding", "clitoral", "urethra", "phimosis", "cervix", "impregnation", "tribadism", "molestation", "pubic_hair", "clothed_female_nude_male", "clothed_male_nude_female", "clothed_female_nude_female", "clothed_male_nude_male", "sex_machine", "milking_machine", "ovum", "chikan", "pussy_juice_drip_through_clothes", "ejaculating_while_penetrated", "suspended_congress", "reverse_suspended_congress", "spread_pussy_under_clothes", "anilingus", "reach-around", "humping", "consensual_tentacles", "tentacle_pit", ], #外観状態／外觀狀態 "Appearance Status" : ["backless", "bandaged_neck", "bleeding", "blood", "blush", "body_writing", "bodypaint", "bottomless", "breath", "bruise", "butt_crack", "cold", "covered_mouth", "crack", "cross-section", "crotchless", "crying", "curvy", "cuts", "dirty", "dripping", "drunk", "from_mouth", "glowing", "hairy", "halterneck", "hot", "injury", "latex", "leather", "levitation", "lipstick_mark", "_markings", "makeup", "mole", "moles", "no_bra", "nosebleed", "nude", "outfit", "pantylines", "peeing", "piercing", "piercings", "pregnant", "public_nudity", "reverse", "_skin", "_submerged", "saliva", "scar", "scratches", "see-through", "shadow", "shibari", "sideless", "skindentation", "sleeping","tan", "soap_bubbles", "steam", "steaming_body", "stitches", "sweat", "sweatdrop", "sweaty", "tanlines", "tattoo", "tattoo", "tears", "topless", "transparent", "trefoil", "trembling", "veins", "visible_air", "wardrobe_malfunction", "wet", "x-ray", "unconscious", "handprint", ], #動作姿勢／動作姿勢 "Action Pose" : ["afloat", "afterimage", "against_fourth_wall", "against_wall", "aiming", "all_fours", "another's_mouth", "arm_", "arm_support", "arms_", "arms_behind_back", "asphyxiation", "attack", "back", "ballet", "bara", "bathing", "battle", "bdsm", "beckoning", "bent_over", "bite_mark", "biting", "bondage", "breast_suppress", "breathing", "burning", "bust_cup", "carry", "carrying", "caught", "chained", "cheek_squash", "chewing", "cigarette", "clapping", "closed_eye", "come_hither", "cooking", "covering", "cuddling", "dancing", "_docking", "destruction", "dorsiflexion", "dreaming", "dressing", "drinking", "driving", "dropping", "eating", "exercise", "expansion", "exposure", "facing", "failure", "fallen_down", "falling", "feeding", "fetal_position", "fighting", "finger_on_trigger", "finger_to_cheek", "finger_to_mouth", "firing", "fishing", "flashing", "fleeing", "flexible", "flexing", "floating", "flying", "fourth_wall", "freediving", "frogtie", "_grab", "girl_on_top", "giving", "grabbing", "grabbing_", "gymnastics", "_hold", "hadanugi_dousa", "hairdressing", "hand_", "hand_on", "hand_on_wall", "hands_", "headpat", "hiding", "holding", "hug", "hugging", "imagining", "in_container", "in_mouth", "in_palm", "jealous", "jumping", "kabedon", "kicking", "kiss", "kissing", "kneeling", "_lift", "lactation", "laundry", "licking", "lifted_by_self", "looking", "lowleg", "lying", "melting", "midair", "moaning", "_open", "on_back", "on_bed", "on_ground", "on_lap", "on_one_knee", "one_eye_closed", "open_", "over_mouth", "own_mouth", "_peek", "_pose", "_press", "_pull", "padding", "paint", "painting_(action)", "palms_together", "pee", "peeking", "pervert", "petting", "pigeon-toed", "piggyback", "pinching", "pinky_out", "pinned", "plantar_flexion", "planted", "playing", "pocky", "pointing", "poke", "poking", "pouring", "pov", "praying", "presenting", "profanity", "pulled_by_self", "pulling", "pump_action", "punching", "_rest", "raised", "reaching", "reading", "reclining", "reverse_grip", "riding", "running", "_slip", "salute", "screaming", "seiza", "selfie", "sewing", "shaking", "shoe_dangle", "shopping", "shouting", "showering", "shushing", "singing", "sitting", "slapping", "smell", "smelling", "smoking", "smother", "solo", "spanked", "spill", "spilling", "spinning", "splashing", "split", "squatting", "squeezed", "standing", "staring", "straddling", "strangling", "stretching", "surfing", "suspension", "swimming", "talking", "teardrop", "tearing_clothes", "throwing", "tied_up", "tiptoes", "toe_scrunch", "toothbrush", "trigger_discipline", "tripping", "tsundere", "turning_head", "twitching", "two-handed", "tying", "_up", "unbuttoned", "undressed", "undressing", "unsheathed", "unsheathing", "unzipped", "unzipping", "upright_straddle", "v", "V", "vore", "_wielding","wading", "walk-in", "walking", "wariza", "waving", "wedgie", "wrestling", "writing", "yawning", "yokozuwari", "_conscious", "massage", "struggling", "shrugging", "drugged", "tentacles_under_clothes", "archery", "cleaning", "tempura", "facepalm", "sadism", ], #頭部装飾／頭部服飾 "Headwear" : ["antennae", "antlers", "aura", "bandaged_head", "bandana", "bandeau", "beanie", "beanie", "beret", "bespectacled", "blindfold", "bonnet", "_cap", "circlet", "crown", "_drill", "_drills", "diadem", "_eyewear", "ear_covers", "ear_ornament", "ear_tag", "earbuds", "earclip", "earmuffs", "earphones", "earpiece", "earring", "earrings", "eyeliner", "eyepatch", "eyewear_on_head", "facial", "fedora", "glasses", "goggles", "_headwear", "hachimaki", "hair_bobbles", "hair_ornament", "hair_rings", "hair_tie", "hairband", "hairclip", "hairpin", "hairpods", "halo", "hat", "head-mounted_display", "head_wreath", "headband", "headdress", "headgear", "headphones", "headpiece", "headset", "helm", "helmet", "hood", "kabuto_(helmet)", "kanzashi", "_mask", "maid_headdress", "mask", "mask", "mechanical_ears", "mechanical_eye", "mechanical_horns", "mob_cap", "monocle", "neck_ruff", "nightcap", "on_head", "pince-nez", "qingdai_guanmao", "scarf_over_mouth", "scrunchie", "sunglasses", "tam_o'_shanter", "tate_eboshi", "tiara", "topknot", "turban", "veil", "visor", "wig", "mitre", "tricorne", "bicorne", ], #手部装飾／手部服飾 "Handwear" : ["arm_warmers", "armband", "armlet", "bandaged_arm", "bandaged_fingers", "bandaged_hand", "bandaged_wrist", "bangle", "bracelet", "bracelets", "bracer", "cuffs", "elbow_pads", "_gauntlets", "_glove", "_gloves", "gauntlets", "gloves", "kote", "kurokote", "mechanical_arm", "mechanical_arms", "mechanical_hands", "mittens", "mitts", "nail_polish", "prosthetic_arm", "wrist_cuffs", "wrist_guards", "wristband", "yugake", ], #ワンピース衣装／一件式服裝 "One-Piece Outfit" : ["bodystocking", "bodysuit", "dress", "furisode", "gown", "hanfu", "jumpsuit", "kimono", "leotard", "microdress", "one-piece", "overalls", "robe", "spacesuit", "sundress", "yukata", ], #上半身衣装／上半身服裝 "Upper Body Clothing" : ["aiguillette", "apron", "armor", "ascot", "babydoll", "bikini", "blazer", "blouse", "bowtie", "bra", "breast_curtain", "breast_curtains", "breast_pocket", "breastplate", "bustier", "_collar", "camisole", "cape", "capelet", "cardigan", "center_opening", "chemise", "chest_jewel", "choker", "cloak", "coat", "coattails", "collar", "corset", "criss-cross_halter", "crop_top", "dougi", "feather_boa", "gakuran", "hagoromo", "hanten_(clothes)", "haori", "harem_pants", "harness", "hoodie", "jacket", "japanese_clothes", "kappougi", "kariginu", "lapels", "lingerie", "maid", "mechanical_wings", "mizu_happi", "muneate", "neckerchief", "necktie", "negligee", "nightgown", "pajamas", "pauldron", "pauldrons", "plunging_neckline", "raincoat", "rei_no_himo", "sailor_collar", "sarashi", "scarf", "serafuku", "shawl", "shirt", "shoulder_", "sleepwear", "sleeve", "sleeveless", "sleeves", "sode", "spaghetti_strap", "sportswear", "strapless", "suit", "sundress", "suspenders", "sweater", "swimsuit", "_top", "_torso", "t-shirt", "tabard", "tailcoat", "tank_top", "tasuki", "tie_clip", "tunic", "turtleneck", "tuxedo", "_uniform", "undershirt", "uniform", "v-neck", "vambraces", "vest", "waistcoat", ], #下半身衣装／下半身服裝 "Lower Body Clothing" : ["bare_hips", "bloomers", "briefs", "buruma", "crotch_seam", "cutoffs", "denim", "faulds", "fundoshi", "g-string", "garter_straps", "hakama", "hip_vent", "jeans", "knee_pads", "loincloth", "mechanical_tail", "microskirt", "miniskirt", "overskirt", "panties", "pants", "pantsu", "panty_straps", "pelvic_curtain", "petticoat", "sarong", "shorts", "side_slit", "skirt", "sweatpants", "swim_trunks", "thong", "underwear", "waist_cape", ], #足元・レッグウェア／腳與腿部服飾 "Foot & Legwear" : ["anklet", "bandaged_leg", "boot", "boots", "_footwear", "flats", "flip-flops", "geta", "greaves", "_heels", "kneehigh", "kneehighs", "_legwear", "leg_warmers", "leggings", "loafers", "mary_janes", "mechanical_legs", "okobo", "over-kneehighs", "pantyhose", "prosthetic_leg", "pumps", "_shoe", "_sock", "sandals", "shoes", "skates", "slippers", "sneakers", "socks", "spikes", "tabi", "tengu-geta", "thigh_strap", "thighhighs", "uwabaki", "zouri", "legband", "ankleband", ], #その他の装飾／其他服飾 "Other Accessories" : ["alternate_", "anklet", "badge", "beads", "belt", "belts", "bow", "brooch", "buckle", "button", "buttons", "_clothes", "_costume", "_cutout", "casual", "charm", "clothes_writing", "clothing_aside", "costume", "cow_print", "cross", "d-pad", "double-breasted", "drawstring", "epaulettes", "fabric", "fishnets", "floral_print", "formal", "frills", "_garter", "gem", "holster", "jewelry", "_knot", "lace", "lanyard", "leash", "magatama", "mechanical_parts", "medal", "medallion", "naked_bandage", "necklace", "_ornament", "(ornament)", "o-ring", "obi", "obiage", "obijime", "_pin", "_print", "padlock", "patterned_clothing", "pendant", "piercing", "plaid", "pocket", "polka_dot", "pom_pom_(clothes)", "pom_pom_(clothes)", "pouch", "ribbon", "_stripe", "_stripes", "sash", "shackles", "shimenawa", "shrug_(clothing)", "skin_tight", "spandex", "strap", "sweatband", "_trim", "tassel", "zettai_ryouiki", "zipper", ], #表情／表情 "Facial Expression" : ["ahegao", "anger_vein", "angry", "annoyed", "confused", "drooling", "embarrassed", "expressionless", "eye_contact", "_face", "frown", "fucked_silly", "furrowed_brow", "glaring", "gloom_(expression)", "grimace", "grin", "happy", "jitome", "laughing", "_mouth", "nervous", "notice_lines", "o_o", "parted_lips", "pout", "puff_of_air", "restrained", "sad", "sanpaku", "scared", "scowl", "serious", "shaded_face", "shy", "sigh", "sleepy", "smile", "smirk", "smug", "snot", "spoken_ellipsis", "spoken_exclamation_mark", "spoken_interrobang", "spoken_question_mark", "squiggle", "surprised", "tareme", "tearing_up", "thinking", "tongue", "tongue_out", "torogao", "tsurime", "turn_pale", "wide-eyed", "wince", "worried", "heartbeat", ], #絵文字／表情符號 "Facial Emoji" : ["!!", "!", "!?", "+++", "+_+", "...", "...?", "._.", "03:00", "0_0", ":/", ":3", ":<", ":>", ":>=", ":d", ":i", ":o", ":p", ":q", ":t", ":x", ":|", ";(", ";)", ";3", ";d", ";o", ";p", ";q", "=_=", ">:(", ">:)", ">_<", ">_o", ">o<", "?", "??", "@_@", "\m/", "\n/", "\o/", "\||/", "^^^", "^_^", "c:", "d:", "o_o", "o3o", "u_u", "w", "x", "x_x", "xd", "zzz", "|_|", ], #頭部／頭部 "Head" : ["afro", "ahoge", "animal_ear_fluff", "_bangs", "_bun", "bald", "beard", "blunt_bangs", "blunt_ends", "bob_cut", "bowl_cut", "braid", "braids", "buzz_cut", "circle_cut", "colored_tips", "cowlick", "dot_nose", "dreadlocks", "_ear", "_ears", "_eye", "_eyes", "enpera", "eyeball", "eyebrow", "eyebrow_cut", "eyebrows", "eyelashes", "eyeshadow", "faceless", "facepaint", "facial_mark", "fang", "forehead", "freckles", "goatee", "_hair", "_horn", "_horns", "hair_", "hair_bun", "hair_flaps", "hair_intakes", "hair_tubes", "half_updo", "head_tilt", "heterochromia", "hime_cut", "hime_cut", "horns", "in_eye", "inverted_bob", "kemonomimi_mode", "lips", "mascara", "mohawk", "mouth_", "mustache", "nose", "one-eyed", "one_eye", "one_side_up", "_pupils", "parted_bangs", "pompadour", "ponytail", "ringlets", "_sclera", "sideburns", "sidecut", "sidelock", "sidelocks", "skull", "snout", "stubble", "swept_bangs", "tails", "teeth", "third_eye", "twintails", "two_side_up", "undercut", "updo", "v-shaped_eyebrows", "whiskers", "tentacle_hair", ], #手部／手部 "Hands" : ["_arm", "_arms", "claws", "_finger", "_fingers", "fingernails", "_hand", "_nail", "_nails", "palms", "rings", "thumbs_up", ], #上半身／上半身 "Upper Body" : ["abs", "armpit", "armpits", "backboob", "belly", "biceps", "breast_rest", "breasts", "button_gap", "cleavage", "collarbone", "dimples_of_venus", "downblouse", "flat_chest", "linea_alba", "median_furrow", "midriff", "nape", "navel", "pectorals", "ribs", "_shoulder", "_shoulders", "shoulder_blades", "sideboob", "sidetail", "spine", "stomach", "strap_gap", "toned", "underboob", "underbust", ], #下半身／下半身 "Lower Body" : ["ankles", "ass", "barefoot", "crotch", "feet", "highleg", "hip_bones", "hooves", "kneepits", "knees", "legs", "soles", "tail", "thigh_gap", "thighlet", "thighs", "toenail", "toenails", "toes", "wide_hips", ], #生物／生物 "Creature" : ["(animal)", "anglerfish", "animal", "bear", "bee", "bird", "bug", "butterfly", "cat", "chick", "chicken", "chinese_zodiac", "clownfish", "coral", "crab", "creature", "crow", "dog", "dove", "dragon", "duck", "eagle", "fish", "fish", "fox", "fox", "frog", "frog", "goldfish", "hamster", "horse", "jellyfish", "ladybug", "lion", "mouse", "octopus", "owl", "panda", "penguin", "pig", "pigeon", "rabbit", "rooster", "seagull", "shark", "sheep", "shrimp", "snail", "snake", "squid", "starfish", "tanuki", "tentacles", "tiger", "turtle", "weasel", "whale", "wolf", "parrot", "sparrow", "unicorn", ], #植物／植物 "Plant" : ["bamboo", "bouquet", "branch", "bush", "cherry_blossoms", "clover", "daisy", "(flower)", "flower", "flower", "gourd", "hibiscus", "holly", "hydrangea", "leaf", "lily_pad", "lotus", "moss", "palm_leaf", "palm_tree", "petals", "plant", "plum_blossoms", "rose", "spider_lily", "sunflower", "thorns", "tree", "tulip", "vines", "wisteria", "acorn", ], #食べ物／食物 "Food" : ["apple", "baguette", "banana", "baozi", "beans", "bento", "berry", "blueberry", "bread", "broccoli", "burger", "cabbage", "cake", "candy", "carrot", "cheese", "cherry", "chili_pepper", "chocolate", "coconut", "cookie", "corn", "cream", "crepe", "cucumber", "cucumber", "cupcake", "curry", "dango", "dessert", "doughnut", "egg", "eggplant", "_(food)", "_(fruit)", "food", "french_fries", "fruit", "grapes", "ice_cream", "icing", "lemon", "lettuce", "lollipop", "macaron", "mandarin_orange", "meat", "melon", "mochi", "mushroom", "noodles", "omelet", "omurice", "onigiri", "onion", "pancake", "parfait", "pasties", "pastry", "peach", "pineapple", "pizza", "popsicle", "potato", "pudding", "pumpkin", "radish", "ramen", "raspberry", "rice", "roasted_sweet_potato", "sandwich", "sausage", "seaweed", "skewer", "spitroast", "spring_onion", "strawberry", "sushi", "sweet_potato", "sweets", "taiyaki", "takoyaki", "tamagoyaki", "tempurakanbea", "toast", "tomato", "vegetable", "wagashi", "wagashi", "watermelon", "jam", "popcorn", ], #飲み物／飲品 "Beverage" : ["alcohol", "beer", "coffee", "cola", "drink", "juice", "juice_box", "milk", "sake", "soda", "tea", "whiskey", "wine", "cocktail", ], #音楽／音樂 "Music" : ["band", "baton_(conducting)", "beamed", "cello", "concert", "drum", "drumsticks", "eighth_note", "flute", "guitar", "harp", "horn", "(instrument)", "idol", "instrument", "k-pop", "lyre", "(music)", "megaphone", "microphone", "music", "musical_note", "phonograph", "piano", "plectrum", "quarter_note", "recorder", "sixteenth_note", "sound_effects", "trumpet", "utaite", "violin", "whistle", ], #武器・装備／武器・裝備 "Weapons & Equipment" : ["ammunition", "arrow_(projectile)", "axe", "bandolier", "baseball_bat", "beretta_92", "bolt_action", "bomb", "bullet", "bullpup", "cannon", "chainsaw", "crossbow", "dagger", "energy_sword", "explosive", "fighter_jet", "gohei", "grenade", "gun", "hammer", "handgun", "holstered", "jet", "katana", "knife", "kunai", "lance", "mallet", "nata_(tool)", "polearm", "quiver", "rapier", "revolver", "rifle", "rocket_launcher", "scabbard", "scope", "scythe", "sheath", "sheathed", "shield", "shotgun", "shuriken", "spear", "staff", "suppressor", "sword", "tank", "tantou", "torpedo", "trident", "(weapon)", "wand", "weapon", "whip", "yumi_(bow)", "h&k_hk416", "rocket_launcher", "heckler_&_koch", ], #乗り物／交通器具 "Vehicles" : ["aircraft", "airplane", "bicycle", "boat", "car", "caterpillar_tracks", "flight_deck", "helicopter", "motor_vehicle", "motorcycle", "ship", "spacecraft", "spoiler_(automobile)", "train", "truck", "watercraft", "wheel", "wheelbarrow", "wheelchair", "inflatable_raft", ], #建物／建物 "Buildings" : ["apartment", "aquarium", "architecture", "balcony", "building", "cafe", "castle", "church", "gym", "hallway", "hospital", "house", "library", "(place)", "porch", "restaurant", "restroom", "rooftop", "shop", "skyscraper", "stadium", "stage", "temple", "toilet", "tower", "train_station", "veranda", ], #室内／室內 "Indoor" : ["bath", "bathroom", "bathtub", "bed", "bed_sheet", "bedroom", "blanket", "bookshelf", "carpet", "ceiling", "chair", "chalkboard", "classroom", "counter", "cupboard", "curtains", "cushion", "dakimakura", "desk", "door", "doorway", "drawer", "_floor", "floor", "futon", "indoors", "interior", "kitchen", "kotatsu", "locker", "mirror", "pillow", "room", "rug", "school_desk", "shelf", "shouji", "sink", "sliding_doors", "stairs", "stool", "storeroom", "table", "tatami", "throne", "window", "windowsill", "bathhouse", "chest_of_drawers", ], #屋外／室外 "Outdoor" : ["alley", "arch", "beach", "bridge", "bus_stop", "bush", "cave", "(city)", "city", "cliff", "crescent", "crosswalk", "day", "desert", "fence", "ferris_wheel", "field", "forest", "grass", "graveyard", "hill", "lake", "lamppost", "moon", "mountain", "night", "ocean", "onsen", "outdoors", "path", "pool", "poolside", "railing", "railroad", "river", "road", "rock", "sand", "shore", "sky", "smokestack", "snow", "snowball", "snowman", "street", "sun", "sunlight", "sunset", "tent", "torii", "town", "tree", "turret", "utility_pole", "valley", "village", "waterfall", ], #物品／物品 "Objects" : ["anchor", "android", "armchair", "(bottle)", "backpack", "bag", "ball", "balloon", "bandages", "bandaid", "bandaids", "banknote", "banner", "barcode", "barrel", "baseball", "basket", "basketball", "beachball", "bell", "bench", "binoculars", "board_game", "bone", "book", "bottle", "bowl", "box", "box_art", "briefcase", "broom", "bucket", "(chess)", "(computer)", "(computing)", "(container)", "cage", "calligraphy_brush", "camera", "can", "candle", "candlestand", "cane", "card", "cartridge", "cellphone", "chain", "chandelier", "chess", "chess_piece", "choko_(cup)", "chopsticks", "cigar", "clipboard", "clock", "clothesline", "coin", "comb", "computer", "condom", "controller", "cosmetics", "couch", "cowbell", "crazy_straw", "cup", "cutting_board", "dice", "digital_media_player", "doll", "drawing_tablet", "drinking_straw", "easel", "electric_fan", "emblem", "envelope", "eraser", "feathers", "figure", "fire", "fishing_rod", "flag", "flask", "folding_fan", "fork", "frying_pan", "(gemstone)", "game_console", "gears", "gemstone", "gift", "glass", "glowstick", "gold", "handbag", "handcuffs", "handheld_game_console", "hose", "id_card", "innertube", "iphone", "jack-o'-lantern", "jar", "joystick", "key", "keychain", "kiseru", "ladder", "ladle", "lamp", "lantern", "laptop", "letter", "letterboxed", "lifebuoy", "lipstick", "liquid", "lock", "lotion", "_machine", "map", "marker", "model_kit", "money", "monitor", "mop", "mug", "needle", "newspaper", "nintendo", "nintendo_switch", "notebook", "(object)", "ofuda", "orb", "origami", "(playing_card)", "pack", "paddle", "paintbrush", "pan", "paper", "parasol", "patch", "pc", "pen", "pencil", "pencil", "pendant_watch", "phone", "pill", "pinwheel", "plate", "playstation", "pocket_watch", "pointer", "poke_ball", "pole", "quill", "racket", "randoseru", "remote_control", "ring", "rope", "sack", "saddle", "sakazuki", "satchel", "saucer", "scissors", "scroll", "seashell", "seatbelt", "shell", "shide", "shopping_cart", "shovel", "shower_head", "silk", "sketchbook", "smartphone", "soap", "sparkler", "spatula", "speaker", "spoon", "statue", "stethoscope", "stick", "sticker", "stopwatch", "string", "stuffed_", "stylus", "suction_cups", "suitcase", "surfboard", "syringe", "talisman", "tanzaku", "tape", "teacup", "teapot", "teddy_bear", "television", "test_tube", "tiles", "tokkuri", "tombstone", "torch", "towel", "toy", "traffic_cone", "tray", "treasure_chest", "uchiwa", "umbrella", "vase", "vial", "video_game", "viewfinder", "volleyball", "wallet", "watch", "watch", "whisk", "whiteboard", "wreath", "wrench", "wristwatch", "yunomi", "ace_of_hearts", "inkwell", "compass", "ipod", "sunscreen", "rocket", "cobblestone", ], #キャラクター設定／角色設定 "Character Design" : ["+boys", "+girls", "1other", "39", "_boys", "_challenge", "_connection", "_female", "_fur", "_girls", "_interface", "_male", "_man", "_person", "abyssal_ship", "age_difference", "aged_down", "aged_up", "albino", "alien", "alternate_muscle_size", "ambiguous_gender", "amputee", "androgynous", "angel", "animalization", "ass-to-ass", "assault_visor", "au_ra", "baby", "bartender", "beak", "bishounen", "borrowed_character", "boxers", "boy", "breast_envy", "breathing_fire", "bride", "broken", "brother_and_sister", "brothers", "camouflage", "cheating_(relationship)", "cheerleader", "chibi", "child", "clone", "command_spell", "comparison", "contemporary", "corpse", "corruption", "cosplay", "couple", "creature_and_personification", "crossdressing", "crossover", "cyberpunk", "cyborg", "cyclops", "damaged", "dancer", "danmaku", "darkness", "death", "defeat", "demon", "disembodied_", "draph", "drone", "duel", "dwarf", "egyptian", "electricity", "elezen", "elf", "enmaided", "erune", "everyone", "evolutionary_line", "expressions", "fairy", "family", "fangs", "fantasy", "fashion", "fat", "father_and_daughter", "father_and_son", "fewer_digits", "fins", "flashback", "fluffy", "fumo_(doll)", "furry", "fusion", "fuuin_no_tsue", "gameplay_mechanics", "genderswap", "ghost", "giant", "giantess", "gibson_les_paul", "girl", "goblin", "groom", "guro", "gyaru", "habit", "harem", "harpy", "harvin", "heads_together", "health_bar", "height_difference", "hitodama", "horror_(theme)", "humanization", "husband_and_wife", "hydrokinesis", "hypnosis", "hyur", "idol", "insignia", "instant_loss", "interracial", "interspecies", "japari_bun", "jeweled_branch_of_hourai", "jiangshi", "jirai_kei", "joints", "karakasa_obake", "keyhole", "kitsune", "knight", "kodona", "kogal", "kyuubi", "lamia", "left-handed", "loli", "lolita", "look-alike", "machinery", "magic", "male_focus", "manly", "matching_outfits", "mature_female", "mecha", "mermaid", "meta", "miko", "milestone_celebration", "military", "mind_control", "miniboy", "minigirl", "miqo'te", "monster", "monsterification", "mother_and_daughter", "mother_and_son", "multiple_others", "muscular", "nanodesu_(phrase)", "narrow_waist", "nekomata", "netorare", "ninja", "no_humans", "nontraditional", "nun", "nurse", "object_namesake", "obliques", "office_lady", "old", "on_body", "onee-shota", "oni", "orc", "others", "otoko_no_ko", "oversized_object", "paint_splatter", "pantyshot", "pawpads", "persona", "personality", "personification", "pet_play", "petite", "pirate", "playboy_bunny", "player_2", "plugsuit", "plump", "poi", "pokemon", "police", "policewoman", "pom_pom_(cheerleading)", "princess", "prosthesis", "pun", "puppet", "race_queen", "radio_antenna", "real_life_insert", "redesign", "reverse_trap", "rigging", "robot", "rod_of_remorse", "sailor", "salaryman", "samurai", "sangvis_ferri", "scales", "scene_reference", "school", "sheikah", "shota", "shrine", "siblings", "side-by-side", "sidesaddle", "sisters", "size_difference", "skeleton", "skinny", "slave", "slime_(substance)", "soldier", "spiked_shell", "spokencharacter", "steampunk", "streetwear", "striker_unit", "strongman", "submerged", "suggestive", "super_saiyan", "superhero", "surreal", "take_your_pick", "tall", "talons", "taur", "teacher", "team_rocket", "three-dimensional_maneuver_gear", "time_paradox", "tomboy", "traditional_youkai", "transformation", "trick_or_treat", "tusks", "twins", "ufo", "under_covers", "v-fin", "v-fin", "vampire", "virtual_youtuber", "waitress", "watching_television", "wedding", "what", "when_you_see_it", "wife_and_wife", "wing", "wings", "witch", "world_war_ii", "yandere", "year_of", "yes", "yin_yang", "yordle", "you're_doing_it_wrong", "you_gonna_get_raped", "yukkuri_shiteitte_ne", "yuri", "zombie", "(alice_in_wonderland)", "(arknights)", "(blue_archive)", "(cosplay)", "(creature)", "(emblem)", "(evangelion)", "(fate)", "(fate/stay_night)", "(ff11)", "(fire_emblem)", "(genshin_impact)", "(grimm)", "(houseki_no_kuni)", "(hyouka)", "(idolmaster)", "(jojo)", "(kancolle)", "(kantai_collection)", "(kill_la_kill)", "(league_of_legends)", "(legends)", "(lyomsnpmp)", "(machimazo)", "(madoka_magica)", "(mecha)", "(meme)", "(nier:automata)", "(organ)", "(overwatch)", "(pokemon)", "(project_moon)", "(project_sekai)", "(sao)", "(senran_kagura)", "(splatoon)", "(touhou)", "(tsukumo_sana)", "(youkai_watch)", "(yu-gi-oh!_gx)", "(zelda)", "sextuplets", "imperial_japanese_army", "extra_faces", ], #構図／構圖 "Composition" : ["abstract", "anime_coloring", "animification", "back-to-back", "bad_anatomy", "blurry", "border", "bound", "cameo", "cheek-to-cheek", "chromatic_aberration", "close-up", "collage", "color_guide", "colorful", "comic", "contrapposto", "cover", "cowboy_shot", "crosshatching", "depth_of_field", "dominatrix", "dutch_angle", "_focus", "face-to-face", "fake_screenshot", "film_grain", "fisheye", "flat_color", "foreshortening", "from_above", "from_behind", "from_below", "from_side", "full_body", "glitch", "greyscale", "halftone", "head_only", "heads-up_display", "high_contrast", "horizon", "_inset", "inset", "jaggy_lines", "1koma", "2koma", "3koma", "4koma", "5koma", "leaning", "leaning_forward", "leaning_to_the_side", "left-to-right_manga", "lens_flare", "limited_palette", "lineart", "lineup", "lower_body", "(medium)", "marker_(medium)", "meme", "mixed_media", "monochrome", "multiple_views", "muted_color", "oekaki", "on_side", "out_of_frame", "outline", "painting", "parody", "partially_colored", "partially_underwater_shot", "perspective", "photorealistic", "picture_frame", "pillarboxed", "portrait", "poster_(object)", "product_placement", "profile", "realistic", "recording", "retro_artstyle", "(style)", "_style", "sandwiched", "science_fiction", "sepia", "shikishi", "side-by-side", "sideways", "sideways_glance", "silhouette", "sketch", "spot_color", "still_life", "straight-on", "symmetry", "(texture)", "tachi-e", "taking_picture", "tegaki", "too_many", "traditional_media", "turnaround", "underwater", "upper_body", "upside-down", "upskirt", "variations", "wide_shot", "_design", "symbolism", "rounded_corners", "surrounded", ], #季節／季節 "Season" : ["akeome", "anniversary", "autumn", "birthday", "christmas", "_day", "festival", "halloween", "kotoyoro", "nengajou", "new_year", "spring_(season)", "summer", "tanabata", "valentine", "winter", ], #背景／背景 "Background" : ["_background", "backlighting", "bloom", "bokeh", "brick_wall", "bubble", "cable", "caustics", "cityscape", "cloud", "confetti", "constellation", "contrail", "crowd", "crystal", "dark", "debris", "dusk", "dust", "egasumi", "embers", "emphasis_lines", "energy", "evening", "explosion", "fireworks", "fog", "footprints", "glint", "graffiti", "ice", "industrial_pipe", "landscape", "light", "light_particles", "light_rays", "lightning", "lights", "moonlight", "motion_blur", "motion_lines", "mountainous_horizon", "nature", "(planet)", "pagoda", "people", "pillar", "planet", "power_lines", "puddle", "rain", "rainbow", "reflection", "ripples", "rubble", "ruins", "scenery", "shade", "shooting_star", "sidelighting", "smoke", "snowflakes", "snowing", "space", "sparkle", "sparks", "speed_lines", "spider_web", "spotlight", "star_(sky)", "stone_wall", "sunbeam", "sunburst", "sunrise", "_theme", "tile_wall", "twilight", "wall_clock", "wall_of_text", "water", "waves", "wind", "wire", "wooden_wall", "lighthouse", ], # パターン／圖案 "Patterns" : ["arrow", "bass_clef", "blank_censor", "circle", "cube", "heart", "hexagon", "hexagram", "light_censor", "(pattern)", "pattern", "pentagram", "roman_numeral", "(shape)", "(symbol)", "shape", "sign", "symbol", "tally", "treble_clef", "triangle", "tube", "yagasuri", ], #検閲／審查 "Censorship" : ["blur_censor", "_censor", "_censoring", "censored", "character_censor", "convenient", "hair_censor", "heart_censor", "identity_censor", "maebari", "novelty_censor", "soap_censor", "steam_censor", "tail_censor", "uncensored", ], #その他／其他 "Others" : ["2007", "2008", "2009", "2010", "2011", "2012", "2013", "2014", "2015", "2016", "2017", "2018", "2019", "2020", "2021", "2022", "2023", "2024", "artist", "artist_name", "artistic_error", "asian", "(company)", "character_name", "content_rating", "copyright", "cover_page", "dated", "english_text", "japan", "layer", "logo", "name", "numbered", "page_number", "pixiv_id", "ranguage", "reference_sheet", "signature", "speech_bubble", "subtitled", "text", "thank_you", "typo", "username", "wallpaper", "watermark", "web_address", "screwdriver", ], } # Use dictionary comprehension to reverse key-value pairs reversed_categories = {value: key for key, values in categories.items() for value in values} tags = [] if __name__ == "__main__": classify_tags (tags, True)