pystylometry 0.1.0__py3-none-any.whl → 1.1.0__py3-none-any.whl

pystylometry/dialect/_data/dialect_markers.json

@@ -0,0 +1,1134 @@
+{
+  "metadata": {
+    "version": "1.1.0",
+    "last_updated": "2026-01-25",
+    "sources": [
+      "Oxford English Dictionary",
+      "Cambridge Dictionary",
+      "Merriam-Webster Dictionary",
+      "British National Corpus",
+      "Corpus of Contemporary American English",
+      "Lingua 2022 - Dialectometrical evaluation",
+      "Encyclopedia.com - Slang, Dialect, and Marked Language"
+    ],
+    "notes": "Extensible dialect marker database for stylometric analysis with feature weighting based on linguistic research"
+  },
+  "feature_levels": {
+    "description": "Categorize markers by linguistic level for fine-grained analysis",
+    "phonological": {
+      "description": "Spelling differences reflecting pronunciation",
+      "examples": ["grey/gray", "programme/program", "colour/color"]
+    },
+    "morphological": {
+      "description": "Word formation differences",
+      "examples": ["travelled/traveled", "-ise/-ize", "-our/-or"]
+    },
+    "lexical": {
+      "description": "Different words for same concept",
+      "examples": ["flat/apartment", "lorry/truck", "lift/elevator"]
+    },
+    "syntactic": {
+      "description": "Grammar and sentence structure differences",
+      "examples": ["have got/have", "collective noun agreement", "shall/will"]
+    }
+  },
+  "eye_dialect": {
+    "description": "Spellings that look nonstandard but reflect standard pronunciation - indicate informal register, not regional dialect",
+    "informal_contractions": [
+      "gonna", "wanna", "gotta", "kinda", "sorta", "outta", "shoulda", "coulda", "woulda",
+      "lemme", "gimme", "dunno", "innit", "ain't", "y'all", "dontcha", "gotcha", "betcha",
+      "whatcha", "cuz", "cos", "cause", "coz", "tryna", "finna"
+    ],
+    "phonetic_spellings": [
+      "wuz", "sez", "cuz", "ur", "u", "r", "b4", "2", "4", "thru", "tho", "bro",
+      "nite", "lite", "rite", "luv", "ya", "yea", "yeah", "nah", "huh", "mhm", "uh-huh"
+    ],
+    "note": "High eye_dialect count suggests informal register or speech transcription, not true dialect"
+  },
+  "pragmatic_markers": {
+    "description": "Discourse and politeness markers that vary by dialect",
+    "british_hedging": {
+      "words": ["quite", "rather", "terribly", "awfully", "frightfully", "jolly", "fairly", "somewhat"],
+      "note": "British English uses more hedging and softening"
+    },
+    "british_discourse": {
+      "words": ["right then", "brilliant", "lovely", "cheers", "mind you", "I reckon", "as it were", "at any rate", "in a sense"],
+      "note": "Common British discourse markers"
+    },
+    "american_discourse": {
+      "words": ["awesome", "cool", "you guys", "totally", "like", "basically", "literally", "actually", "I guess", "for sure", "no way"],
+      "note": "Common American discourse markers"
+    },
+    "british_politeness": {
+      "patterns": ["would you mind", "I was wondering if", "might I", "could I possibly", "I don't suppose"],
+      "note": "More indirect request forms"
+    },
+    "american_politeness": {
+      "patterns": ["can you", "could you", "would you", "I want", "I need"],
+      "note": "More direct request forms"
+    }
+  },
+  "vocabulary": {
+    "pairs": [
+      {"american": "airplane", "british": "aeroplane", "category": "transportation"},
+      {"american": "aluminum", "british": "aluminium", "category": "materials"},
+      {"american": "antenna", "british": "aerial", "category": "technology"},
+      {"american": "apartment", "british": "flat", "category": "housing"},
+      {"american": "appetizer", "british": "starter", "category": "food"},
+      {"american": "ATM", "british": "cash point", "category": "finance"},
+      {"american": "attorney", "british": "solicitor", "category": "legal"},
+      {"american": "baby carriage", "british": "pram", "category": "household"},
+      {"american": "backyard", "british": "garden", "category": "housing"},
+      {"american": "band-aid", "british": "plaster", "category": "medical"},
+      {"american": "bangs", "british": "fringe", "category": "appearance"},
+      {"american": "bathroom", "british": "loo", "category": "housing"},
+      {"american": "bathrobe", "british": "dressing gown", "category": "clothing"},
+      {"american": "beet", "british": "beetroot", "category": "food"},
+      {"american": "bill", "british": "note", "category": "finance"},
+      {"american": "billion", "british": "milliard", "category": "numbers", "notes": "historical British usage"},
+      {"american": "biscuit", "british": "scone", "category": "food"},
+      {"american": "bleachers", "british": "terraces", "category": "sports"},
+      {"american": "blinders", "british": "blinkers", "category": "animals"},
+      {"american": "broil", "british": "grill", "category": "cooking"},
+      {"american": "busy signal", "british": "engaged tone", "category": "technology"},
+      {"american": "cab", "british": "taxi", "category": "transportation"},
+      {"american": "call collect", "british": "reverse charges", "category": "technology"},
+      {"american": "can", "british": "tin", "category": "food"},
+      {"american": "candy", "british": "sweets", "category": "food"},
+      {"american": "cart", "british": "trolley", "category": "shopping"},
+      {"american": "catalog", "british": "catalogue", "category": "general"},
+      {"american": "cell phone", "british": "mobile phone", "category": "technology"},
+      {"american": "check", "british": "cheque", "category": "finance"},
+      {"american": "checkers", "british": "draughts", "category": "games"},
+      {"american": "chips", "british": "crisps", "category": "food"},
+      {"american": "cilantro", "british": "coriander", "category": "food"},
+      {"american": "closet", "british": "wardrobe", "category": "housing"},
+      {"american": "comforter", "british": "duvet", "category": "household"},
+      {"american": "cookie", "british": "biscuit", "category": "food"},
+      {"american": "corn", "british": "maize", "category": "food"},
+      {"american": "cotton candy", "british": "candyfloss", "category": "food"},
+      {"american": "counterclockwise", "british": "anticlockwise", "category": "direction"},
+      {"american": "crib", "british": "cot", "category": "household"},
+      {"american": "crosswalk", "british": "zebra crossing", "category": "transportation"},
+      {"american": "curb", "british": "kerb", "category": "infrastructure"},
+      {"american": "diaper", "british": "nappy", "category": "household"},
+      {"american": "dish towel", "british": "tea towel", "category": "household"},
+      {"american": "divided highway", "british": "dual carriageway", "category": "transportation"},
+      {"american": "downtown", "british": "city centre", "category": "location"},
+      {"american": "drapes", "british": "curtains", "category": "household"},
+      {"american": "driver's license", "british": "driving licence", "category": "legal"},
+      {"american": "drugstore", "british": "chemist", "category": "shopping"},
+      {"american": "dumpster", "british": "skip", "category": "infrastructure"},
+      {"american": "eggplant", "british": "aubergine", "category": "food"},
+      {"american": "elementary school", "british": "primary school", "category": "education"},
+      {"american": "elevator", "british": "lift", "category": "building"},
+      {"american": "eraser", "british": "rubber", "category": "stationery"},
+      {"american": "expressway", "british": "motorway", "category": "transportation"},
+      {"american": "fall", "british": "autumn", "category": "time"},
+      {"american": "faucet", "british": "tap", "category": "household"},
+      {"american": "fender", "british": "wing", "category": "automotive"},
+      {"american": "first floor", "british": "ground floor", "category": "building"},
+      {"american": "flashlight", "british": "torch", "category": "household"},
+      {"american": "french fries", "british": "chips", "category": "food"},
+      {"american": "freeway", "british": "motorway", "category": "transportation"},
+      {"american": "garbage", "british": "rubbish", "category": "general"},
+      {"american": "garbage can", "british": "dustbin", "category": "household"},
+      {"american": "gas", "british": "petrol", "category": "automotive"},
+      {"american": "gas pedal", "british": "accelerator", "category": "automotive"},
+      {"american": "gear shift", "british": "gear lever", "category": "automotive"},
+      {"american": "generator", "british": "dynamo", "category": "technology"},
+      {"american": "gotten", "british": "got", "category": "grammar"},
+      {"american": "grade", "british": "year", "category": "education"},
+      {"american": "gram", "british": "gramme", "category": "measurement"},
+      {"american": "ground beef", "british": "mince", "category": "food"},
+      {"american": "highway", "british": "main road", "category": "transportation"},
+      {"american": "hood", "british": "bonnet", "category": "automotive"},
+      {"american": "intersection", "british": "junction", "category": "transportation"},
+      {"american": "jello", "british": "jelly", "category": "food"},
+      {"american": "jelly", "british": "jam", "category": "food"},
+      {"american": "kerosene", "british": "paraffin", "category": "materials"},
+      {"american": "ladybug", "british": "ladybird", "category": "animals"},
+      {"american": "lawyer", "british": "barrister", "category": "legal"},
+      {"american": "license plate", "british": "number plate", "category": "automotive"},
+      {"american": "line", "british": "queue", "category": "general"},
+      {"american": "liquor store", "british": "off-licence", "category": "shopping"},
+      {"american": "living room", "british": "lounge", "category": "housing"},
+      {"american": "mail", "british": "post", "category": "communication"},
+      {"american": "mailbox", "british": "postbox", "category": "communication"},
+      {"american": "mailman", "british": "postman", "category": "occupation"},
+      {"american": "math", "british": "maths", "category": "education"},
+      {"american": "median strip", "british": "central reservation", "category": "transportation"},
+      {"american": "mom", "british": "mum", "category": "family"},
+      {"american": "movie", "british": "film", "category": "entertainment"},
+      {"american": "movie theater", "british": "cinema", "category": "entertainment"},
+      {"american": "muffler", "british": "silencer", "category": "automotive"},
+      {"american": "napkin", "british": "serviette", "category": "household"},
+      {"american": "nightstand", "british": "bedside table", "category": "household"},
+      {"american": "oatmeal", "british": "porridge", "category": "food"},
+      {"american": "overpass", "british": "flyover", "category": "transportation"},
+      {"american": "pacifier", "british": "dummy", "category": "household"},
+      {"american": "pajamas", "british": "pyjamas", "category": "clothing"},
+      {"american": "pants", "british": "trousers", "category": "clothing"},
+      {"american": "pantyhose", "british": "tights", "category": "clothing"},
+      {"american": "parking garage", "british": "car park", "category": "transportation"},
+      {"american": "parking lot", "british": "car park", "category": "transportation"},
+      {"american": "pavement", "british": "road surface", "category": "infrastructure"},
+      {"american": "period", "british": "full stop", "category": "punctuation"},
+      {"american": "pharmacist", "british": "chemist", "category": "occupation"},
+      {"american": "pitcher", "british": "jug", "category": "household"},
+      {"american": "potato chips", "british": "crisps", "category": "food"},
+      {"american": "private school", "british": "public school", "category": "education"},
+      {"american": "purse", "british": "handbag", "category": "accessories"},
+      {"american": "race car", "british": "racing car", "category": "automotive"},
+      {"american": "railroad", "british": "railway", "category": "transportation"},
+      {"american": "raise", "british": "rise", "category": "finance"},
+      {"american": "realtor", "british": "estate agent", "category": "occupation"},
+      {"american": "recess", "british": "break", "category": "education"},
+      {"american": "rent", "british": "hire", "category": "finance"},
+      {"american": "restroom", "british": "toilet", "category": "building"},
+      {"american": "resume", "british": "CV", "category": "employment"},
+      {"american": "rooster", "british": "cockerel", "category": "animals"},
+      {"american": "rotary", "british": "roundabout", "category": "transportation"},
+      {"american": "row house", "british": "terraced house", "category": "housing"},
+      {"american": "run", "british": "ladder", "category": "clothing", "notes": "in stockings"},
+      {"american": "rutabaga", "british": "swede", "category": "food"},
+      {"american": "sailboat", "british": "sailing boat", "category": "transportation"},
+      {"american": "sanitarium", "british": "sanatorium", "category": "medical"},
+      {"american": "schedule", "british": "timetable", "category": "general"},
+      {"american": "sedan", "british": "saloon", "category": "automotive"},
+      {"american": "semester", "british": "term", "category": "education"},
+      {"american": "shrimp", "british": "prawn", "category": "food"},
+      {"american": "sidewalk", "british": "pavement", "category": "infrastructure"},
+      {"american": "silverware", "british": "cutlery", "category": "household"},
+      {"american": "sneakers", "british": "trainers", "category": "clothing"},
+      {"american": "soccer", "british": "football", "category": "sports"},
+      {"american": "soda", "british": "fizzy drink", "category": "food"},
+      {"american": "softball", "british": "rounders", "category": "sports"},
+      {"american": "spelling bee", "british": "spelling competition", "category": "education"},
+      {"american": "squash", "british": "marrow", "category": "food"},
+      {"american": "station wagon", "british": "estate car", "category": "automotive"},
+      {"american": "stove", "british": "cooker", "category": "household"},
+      {"american": "streetcar", "british": "tram", "category": "transportation"},
+      {"american": "stroller", "british": "pushchair", "category": "household"},
+      {"american": "subway", "british": "underground", "category": "transportation"},
+      {"american": "suspenders", "british": "braces", "category": "clothing"},
+      {"american": "sweater", "british": "jumper", "category": "clothing"},
+      {"american": "takeout", "british": "takeaway", "category": "food"},
+      {"american": "thumbtack", "british": "drawing pin", "category": "stationery"},
+      {"american": "tic-tac-toe", "british": "noughts and crosses", "category": "games"},
+      {"american": "tire", "british": "tyre", "category": "automotive"},
+      {"american": "trailer", "british": "caravan", "category": "transportation"},
+      {"american": "trash", "british": "rubbish", "category": "general"},
+      {"american": "trash can", "british": "bin", "category": "household"},
+      {"american": "truck", "british": "lorry", "category": "transportation"},
+      {"american": "trunk", "british": "boot", "category": "automotive"},
+      {"american": "underpants", "british": "pants", "category": "clothing"},
+      {"american": "undershirt", "british": "vest", "category": "clothing"},
+      {"american": "vacation", "british": "holiday", "category": "time"},
+      {"american": "van", "british": "people carrier", "category": "transportation"},
+      {"american": "vest", "british": "waistcoat", "category": "clothing"},
+      {"american": "windshield", "british": "windscreen", "category": "automotive"},
+      {"american": "wrench", "british": "spanner", "category": "tools"},
+      {"american": "yard", "british": "garden", "category": "housing"},
+      {"american": "zee", "british": "zed", "category": "alphabet"},
+      {"american": "zero", "british": "nought", "category": "numbers"},
+      {"american": "zipper", "british": "zip", "category": "clothing"},
+      {"american": "zucchini", "british": "courgette", "category": "food"}
+    ],
+    "exclusive": {
+      "australian": [
+        "arvo",
+        "barbie",
+        "bathers",
+        "bikkie",
+        "bloke",
+        "bogan",
+        "brekkie",
+        "chook",
+        "dunny",
+        "esky",
+        "footy",
+        "g'day",
+        "heaps",
+        "lollies",
+        "macca's",
+        "mate",
+        "mozzie",
+        "outback",
+        "reckon",
+        "ripper",
+        "servo",
+        "sheila",
+        "sickie",
+        "snag",
+        "strewth",
+        "sunnies",
+        "ta",
+        "thongs",
+        "ute",
+        "yakka"
+      ],
+      "british": [
+        "blimey",
+        "bloody",
+        "bollocks",
+        "brilliant",
+        "cheers",
+        "chuffed",
+        "codswallop",
+        "crikey",
+        "dodgy",
+        "fortnight",
+        "gobsmacked",
+        "gutted",
+        "knackered",
+        "lovely",
+        "mental",
+        "naff",
+        "posh",
+        "proper",
+        "quid",
+        "rubbish",
+        "sacked",
+        "shattered",
+        "snog",
+        "sorted",
+        "spot-on",
+        "stonking",
+        "whilst",
+        "wicked"
+      ],
+      "american": [
+        "awesome",
+        "buck",
+        "bummer",
+        "cop",
+        "dude",
+        "fanny pack",
+        "gotten",
+        "guy",
+        "jock",
+        "kinda",
+        "lame",
+        "nerd",
+        "nuts",
+        "oftentimes",
+        "rookie",
+        "schlep",
+        "schmuck",
+        "swell",
+        "trash",
+        "wanna",
+        "yep"
+      ],
+      "canadian": [
+        "chesterfield",
+        "chinook",
+        "donair",
+        "eh",
+        "garburator",
+        "homo milk",
+        "keener",
+        "loonie",
+        "mickey",
+        "parkade",
+        "poutine",
+        "serviette",
+        "toque",
+        "toonie",
+        "two-four",
+        "washroom"
+      ],
+      "south_african": [
+        "braai",
+        "bru",
+        "eish",
+        "howzit",
+        "ja",
+        "jol",
+        "lekker",
+        "now-now",
+        "robot",
+        "shame",
+        "yebo"
+      ],
+      "irish": [
+        "craic",
+        "eejit",
+        "feck",
+        "fierce",
+        "grand",
+        "gurrier",
+        "knacker",
+        "langers",
+        "manky",
+        "mot",
+        "savage",
+        "shift",
+        "slagging",
+        "sound",
+        "yoke"
+      ],
+      "scottish": [
+        "bairn",
+        "bonnie",
+        "braw",
+        "dinnae",
+        "dreich",
+        "frae",
+        "ken",
+        "lad",
+        "lass",
+        "wee"
+      ]
+    }
+  },
+  "spelling_patterns": {
+    "british_american": [
+      {
+        "name": "ise_ize",
+        "description": "British '-ise' vs American '-ize' suffix",
+        "british_suffix": "ise",
+        "american_suffix": "ize",
+        "pattern_british": "\\b\\w+ise\\b",
+        "pattern_american": "\\b\\w+ize\\b",
+        "weight": 0.7,
+        "feature_level": "morphological",
+        "note": "Lower weight - both forms accepted in British English",
+        "examples": [
+          "organise/organize",
+          "realise/realize",
+          "recognise/recognize",
+          "apologise/apologize",
+          "authorise/authorize",
+          "categorise/categorize",
+          "centralise/centralize",
+          "characterise/characterize",
+          "civilise/civilize",
+          "colonise/colonize",
+          "criticise/criticize",
+          "customise/customize",
+          "emphasise/emphasize",
+          "finalise/finalize",
+          "generalise/generalize",
+          "hospitalise/hospitalize",
+          "hypnotise/hypnotize",
+          "legalise/legalize",
+          "localise/localize",
+          "memorise/memorize",
+          "minimise/minimize",
+          "modernise/modernize",
+          "nationalise/nationalize",
+          "normalise/normalize",
+          "optimise/optimize",
+          "paralyse/paralyze",
+          "patronise/patronize",
+          "penalise/penalize",
+          "personalise/personalize",
+          "plagiarise/plagiarize",
+          "polarise/polarize",
+          "prioritise/prioritize",
+          "privatise/privatize",
+          "publicise/publicize",
+          "rationalise/rationalize",
+          "revolutionise/revolutionize",
+          "scrutinise/scrutinize",
+          "specialise/specialize",
+          "stabilise/stabilize",
+          "standardise/standardize",
+          "summarise/summarize",
+          "symbolise/symbolize",
+          "sympathise/sympathize",
+          "synchronise/synchronize",
+          "terrorise/terrorize",
+          "tranquillise/tranquilize",
+          "trivialise/trivialize",
+          "urbanise/urbanize",
+          "utilise/utilize",
+          "visualise/visualize"
+        ],
+        "exceptions": ["advertise", "advise", "arise", "comprise", "compromise", "despise", "devise", "disguise", "enterprise", "excise", "exercise", "franchise", "improvise", "incise", "merchandise", "premise", "revise", "rise", "supervise", "surmise", "surprise", "televise"]
+      },
+      {
+        "name": "isation_ization",
+        "description": "British '-isation' vs American '-ization' suffix",
+        "british_suffix": "isation",
+        "american_suffix": "ization",
+        "pattern_british": "\\b\\w+isation\\b",
+        "pattern_american": "\\b\\w+ization\\b",
+        "weight": 0.7,
+        "feature_level": "morphological",
+        "examples": [
+          "organisation/organization",
+          "realisation/realization",
+          "civilisation/civilization",
+          "colonisation/colonization",
+          "globalisation/globalization",
+          "hospitalisation/hospitalization",
+          "nationalisation/nationalization",
+          "normalisation/normalization",
+          "optimisation/optimization",
+          "privatisation/privatization",
+          "specialisation/specialization",
+          "standardisation/standardization",
+          "synchronisation/synchronization",
+          "urbanisation/urbanization"
+        ]
+      },
+      {
+        "name": "our_or",
+        "description": "British '-our' vs American '-or' suffix",
+        "british_suffix": "our",
+        "american_suffix": "or",
+        "pattern_british": "\\b(colour|favour|honour|labour|neighbour|behaviour|endeavour|flavour|harbour|humour|odour|parlour|rumour|savour|splendour|tumour|vapour|vigour|clamour|candour|fervour|rancour|succour|armour|demeanour|valour|saviour|glamour)s?\\b",
+        "pattern_american": "\\b(color|favor|honor|labor|neighbor|behavior|endeavor|flavor|harbor|humor|odor|parlor|rumor|savor|splendor|tumor|vapor|vigor|clamor|candor|fervor|rancor|succor|armor|demeanor|valor|savior)s?\\b",
+        "weight": 0.95,
+        "feature_level": "phonological",
+        "note": "High diagnostic value - rarely confused",
+        "examples": [
+          "colour/color",
+          "favour/favor",
+          "honour/honor",
+          "labour/labor",
+          "neighbour/neighbor",
+          "behaviour/behavior",
+          "endeavour/endeavor",
+          "flavour/flavor",
+          "harbour/harbor",
+          "humour/humor",
+          "odour/odor",
+          "parlour/parlor",
+          "rumour/rumor",
+          "savour/savor",
+          "splendour/splendor",
+          "tumour/tumor",
+          "vapour/vapor",
+          "vigour/vigor"
+        ],
+        "exceptions": ["contour", "velour", "paramour", "troubadour"]
+      },
+      {
+        "name": "re_er",
+        "description": "British '-re' vs American '-er' suffix",
+        "british_suffix": "re",
+        "american_suffix": "er",
+        "pattern_british": "\\b(centre|theatre|metre|litre|fibre|calibre|goitre|kilometre|louvre|lustre|meagre|mitre|nitre|ochre|reconnoitre|sabre|saltpetre|sepulchre|sombre|spectre|titre|centimetre|millimetre)s?\\b",
+        "pattern_american": "\\b(center|theater|meter|liter|fiber|caliber|goiter|kilometer|louver|luster|meager|miter|niter|ocher|reconnoiter|saber|saltpeter|sepulcher|somber|specter|titer|centimeter|millimeter)s?\\b",
+        "weight": 0.9,
+        "feature_level": "phonological",
+        "examples": [
+          "centre/center",
+          "theatre/theater",
+          "metre/meter",
+          "litre/liter",
+          "fibre/fiber",
+          "calibre/caliber",
+          "goitre/goiter",
+          "kilometre/kilometer",
+          "louvre/louver",
+          "lustre/luster",
+          "manoeuvre/maneuver",
+          "meagre/meager",
+          "mitre/miter",
+          "nitre/niter",
+          "ochre/ocher",
+          "reconnoitre/reconnoiter",
+          "sabre/saber",
+          "saltpetre/saltpeter",
+          "sepulchre/sepulcher",
+          "sombre/somber",
+          "spectre/specter",
+          "titre/titer"
+        ],
+        "exceptions": ["acre", "lucre", "massacre", "mediocre", "ogre"]
+      },
+      {
+        "name": "ce_se",
+        "description": "British '-ce' vs American '-se' in nouns (licence/license, defence/defense)",
+        "british_suffix": "ce",
+        "american_suffix": "se",
+        "pattern_british": "\\b(defence|offence|licence|pretence)\\b",
+        "pattern_american": "\\b(defense|offense|license|pretense)\\b",
+        "weight": 0.95,
+        "feature_level": "phonological",
+        "examples": [
+          "defence/defense",
+          "offence/offense",
+          "licence/license",
+          "pretence/pretense"
+        ],
+        "notes": "In British English, nouns end in '-ce' while verbs end in '-se'. American English uses '-se' for both."
+      },
+      {
+        "name": "ogue_og",
+        "description": "British '-ogue' vs American '-og' suffix",
+        "british_suffix": "ogue",
+        "american_suffix": "og",
+        "pattern_british": "\\b(catalogue|dialogue|analogue|epilogue|monologue|prologue|homologue|travelogue|demagogue|pedagogue|synagogue)s?\\b",
+        "pattern_american": "\\b(catalog|dialog|analog|epilog|monolog|prolog|homolog|travelog|demagog|pedagog|synagog)s?\\b",
+        "weight": 0.8,
+        "feature_level": "morphological",
+        "examples": [
+          "catalogue/catalog",
+          "dialogue/dialog",
+          "analogue/analog",
+          "epilogue/epilog",
+          "monologue/monolog",
+          "prologue/prolog",
+          "homologue/homolog",
+          "travelogue/travelog"
+        ],
+        "notes": "Both spellings are used in American English, but the shorter form is more common in computing contexts"
+      },
+      {
+        "name": "ae_e",
+        "description": "British '-ae-' vs American '-e-' (Latin/Greek origins)",
+        "british_infix": "ae",
+        "american_infix": "e",
+        "pattern_british": "\\b(anaemia|anaesthesia|anaesthetic|anaesthetist|archaeology|encyclopaedia|faeces|gynaecology|haematology|haemoglobin|haemophilia|haemorrhage|leukaemia|orthopaedic|paediatric|paediatrician|aeon|mediaeval|caesarean)s?\\b",
+        "pattern_american": "\\b(anemia|anesthesia|anesthetic|anesthetist|archeology|encyclopedia|feces|gynecology|hematology|hemoglobin|hemophilia|hemorrhage|leukemia|orthopedic|pediatric|pediatrician|eon|medieval|cesarean)s?\\b",
+        "weight": 0.9,
+        "feature_level": "phonological",
+        "examples": [
+          "anaemia/anemia",
+          "anaesthesia/anesthesia",
+          "anaesthetic/anesthetic",
+          "archaeology/archeology",
+          "encyclopaedia/encyclopedia",
+          "faeces/feces",
+          "gynaecology/gynecology",
+          "haematology/hematology",
+          "haemoglobin/hemoglobin",
+          "haemophilia/hemophilia",
+          "haemorrhage/hemorrhage",
+          "leukaemia/leukemia",
+          "orthopaedic/orthopedic",
+          "paediatric/pediatric"
+        ]
+      },
+      {
+        "name": "oe_e",
+        "description": "British '-oe-' vs American '-e-' (Latin/Greek origins)",
+        "british_infix": "oe",
+        "american_infix": "e",
+        "pattern_british": "\\b(foetus|oestrogen|oesophagus|diarrhoea|gonorrhoea|amoeba|manoeuvre|coeliac|homoeopathy|phoenician)s?\\b",
+        "pattern_american": "\\b(fetus|estrogen|esophagus|diarrhea|gonorrhea|ameba|maneuver|celiac|homeopathy|phoenician)s?\\b",
+        "weight": 0.9,
+        "feature_level": "phonological",
+        "examples": [
+          "foetus/fetus",
+          "oestrogen/estrogen",
+          "oesophagus/esophagus",
+          "diarrhoea/diarrhea",
+          "gonorrhoea/gonorrhea",
+          "amoeba/ameba",
+          "manoeuvre/maneuver"
+        ]
+      },
+      {
+        "name": "doubled_l",
+        "description": "British doubles 'l' before suffixes, American does not",
+        "pattern_british": "\\b(cancelled|cancelling|counselled|counselling|counsellor|dialled|dialling|equalled|equalling|fuelled|fuelling|gruelling|jewelled|jeweller|labelled|labelling|levelled|levelling|libelled|libelling|marvelled|marvelling|marvellous|modelled|modelling|panelled|panelling|pedalled|pedalling|pencilled|pencilling|quarrelled|quarrelling|ravelled|ravelling|revelled|revelling|rivalled|rivalling|signalled|signalling|snorkelled|snorkelling|spiralled|spiralling|stencilled|stencilling|swivelled|swivelling|totalled|totalling|towelled|towelling|travelled|travelling|traveller|trialled|trialling|tunnelled|tunnelling|yodelled|yodelling)\\b",
+        "pattern_american": "\\b(canceled|canceling|counseled|counseling|counselor|dialed|dialing|equaled|equaling|fueled|fueling|grueling|jeweled|jeweler|labeled|labeling|leveled|leveling|libeled|libeling|marveled|marveling|marvelous|modeled|modeling|paneled|paneling|pedaled|pedaling|penciled|penciling|quarreled|quarreling|raveled|raveling|reveled|reveling|rivaled|rivaling|signaled|signaling|snorkeled|snorkeling|spiraled|spiraling|stenciled|stenciling|swiveled|swiveling|totaled|totaling|toweled|toweling|traveled|traveling|traveler|trialed|trialing|tunneled|tunneling|yodeled|yodeling)\\b",
+        "weight": 0.85,
+        "feature_level": "morphological",
+        "examples": [
+          "cancelled/canceled",
+          "cancelling/canceling",
+          "counselled/counseled",
+          "counselling/counseling",
+          "counsellor/counselor",
+          "dialled/dialed",
+          "dialling/dialing",
+          "equalled/equaled",
+          "equalling/equaling",
+          "fuelled/fueled",
+          "fuelling/fueling",
+          "gruelling/grueling",
+          "jewelled/jeweled",
+          "jeweller/jeweler",
+          "labelled/labeled",
+          "labelling/labeling",
+          "levelled/leveled",
+          "levelling/leveling",
+          "libelled/libeled",
+          "libelling/libeling",
+          "marvelled/marveled",
+          "marvelling/marveling",
+          "marvellous/marvelous",
+          "modelled/modeled",
+          "modelling/modeling",
+          "panelled/paneled",
+          "panelling/paneling",
+          "pedalled/pedaled",
+          "pedalling/pedaling",
+          "pencilled/penciled",
+          "pencilling/penciling",
+          "quarrelled/quarreled",
+          "quarrelling/quarreling",
+          "ravelled/raveled",
+          "ravelling/raveling",
+          "revelled/reveled",
+          "revelling/reveling",
+          "rivalled/rivaled",
+          "rivalling/rivaling",
+          "signalled/signaled",
+          "signalling/signaling",
+          "snorkelled/snorkeled",
+          "snorkelling/snorkeling",
+          "spiralled/spiraled",
+          "spiralling/spiraling",
+          "stencilled/stenciled",
+          "stencilling/stenciling",
+          "swivelled/swiveled",
+          "swivelling/swiveling",
+          "totalled/totaled",
+          "totalling/totaling",
+          "towelled/toweled",
+          "towelling/toweling",
+          "travelled/traveled",
+          "travelling/traveling",
+          "traveller/traveler",
+          "trialled/trialed",
+          "trialling/trialing",
+          "tunnelled/tunneled",
+          "tunnelling/tunneling",
+          "yodelled/yodeled",
+          "yodelling/yodeling"
+        ]
+      },
+      {
+        "name": "ence_ense",
+        "description": "British '-ence' vs American '-ense' in some words",
+        "pattern_british": "\\b(defence|offence|pretence)\\b",
+        "pattern_american": "\\b(defense|offense|pretense)\\b",
+        "examples": [
+          "defence/defense",
+          "offence/offense",
+          "pretence/pretense"
+        ]
+      },
+      {
+        "name": "eable_able",
+        "description": "British keeps 'e' before '-able', American drops it",
+        "pattern_british": "\\b(sizeable|likeable|moveable|rateable|saleable|shakeable|unshakeable|nameable|loveable|liveable|blameable|tameable)\\b",
+        "pattern_american": "\\b(sizable|likable|movable|ratable|salable|shakable|unshakable|namable|lovable|livable|blamable|tamable)\\b",
+        "weight": 0.8,
+        "feature_level": "morphological",
+        "examples": [
+          "sizeable/sizable",
+          "likeable/likable",
+          "moveable/movable",
+          "rateable/ratable",
+          "saleable/salable",
+          "shakeable/shakable",
+          "unshakeable/unshakable"
+        ]
+      },
+      {
+        "name": "xion_ction",
+        "description": "British '-xion' vs American '-ction' (archaic in British)",
+        "pattern_british": "\\b(connexion|inflexion|reflexion)s?\\b",
+        "pattern_american": null,
+        "weight": 0.7,
+        "feature_level": "morphological",
+        "examples": [
+          "connexion/connection",
+          "inflexion/inflection",
+          "reflexion/reflection"
+        ],
+        "notes": "The '-xion' forms are largely archaic in modern British English. American pattern disabled as -ction is too common."
+      },
+      {
+        "name": "yse_yze",
+        "description": "British '-yse' vs American '-yze'",
+        "british_suffix": "yse",
+        "american_suffix": "yze",
+        "pattern_british": "\\b\\w+yse\\b",
+        "pattern_american": "\\b\\w+yze\\b",
+        "weight": 0.95,
+        "feature_level": "morphological",
+        "examples": [
+          "analyse/analyze",
+          "breathalyse/breathalyze",
+          "catalyse/catalyze",
+          "dialyse/dialyze",
+          "electrolyse/electrolyze",
+          "hydrolyse/hydrolyze",
+          "paralyse/paralyze",
+          "psychoanalyse/psychoanalyze"
+        ]
+      },
+      {
+        "name": "gramme_gram",
+        "description": "British '-gramme' vs American '-gram' for units",
+        "pattern_british": "\\b(gramme|kilogramme|programme|centigramme|decigramme|milligramme|programmes)\\b",
+        "pattern_american": "\\b(gram|kilogram|program|centigram|decigram|milligram|programs)\\b",
+        "weight": 0.85,
+        "feature_level": "morphological",
+        "examples": [
+          "gramme/gram",
+          "kilogramme/kilogram",
+          "programme/program"
+        ],
+        "notes": "British English uses 'program' for computer software but 'programme' for TV/radio/events"
+      },
+      {
+        "name": "wards_ward",
+        "description": "British '-wards' vs American '-ward'",
+        "british_suffix": "wards",
+        "american_suffix": "ward",
+        "pattern_british": "\\b(afterwards|backwards|downwards|forwards|inwards|onwards|outwards|towards|upwards|homewards|northwards|southwards|eastwards|westwards)\\b",
+        "pattern_american": "\\b(afterward|backward|downward|forward|inward|onward|outward|toward|upward|homeward|northward|southward|eastward|westward)\\b",
+        "weight": 0.6,
+        "feature_level": "morphological",
+        "examples": [
+          "afterwards/afterward",
+          "backwards/backward",
+          "downwards/downward",
+          "forwards/forward",
+          "inwards/inward",
+          "onwards/onward",
+          "outwards/outward",
+          "towards/toward",
+          "upwards/upward"
+        ],
+        "notes": "Both forms are used in both dialects, but the preferences differ"
+      },
+      {
+        "name": "ement_ment",
+        "description": "British keeps 'e' in judgement/acknowledgement",
+        "pattern_british": "\\b(judgement|acknowledgement|abridgement)\\b",
+        "pattern_american": "\\b(judgment|acknowledgment|abridgment)\\b",
+        "examples": [
+          "judgement/judgment",
+          "acknowledgement/acknowledgment",
+          "abridgement/abridgment"
+        ],
+        "notes": "British legal writing often uses 'judgment'"
+      }
+    ],
+    "standalone": [
+      {"british": "aeroplane", "american": "airplane"},
+      {"british": "ageing", "american": "aging"},
+      {"british": "aluminium", "american": "aluminum"},
+      {"british": "annexe", "american": "annex"},
+      {"british": "artefact", "american": "artifact"},
+      {"british": "axe", "american": "ax"},
+      {"british": "behove", "american": "behoove"},
+      {"british": "burnt", "american": "burned"},
+      {"british": "busses", "american": "buses"},
+      {"british": "cancelled", "american": "canceled"},
+      {"british": "catalogue", "american": "catalog"},
+      {"british": "cheque", "american": "check"},
+      {"british": "chilli", "american": "chili"},
+      {"british": "cosy", "american": "cozy"},
+      {"british": "defence", "american": "defense"},
+      {"british": "dialogue", "american": "dialog"},
+      {"british": "disc", "american": "disk"},
+      {"british": "doughnut", "american": "donut"},
+      {"british": "draught", "american": "draft"},
+      {"british": "dreamt", "american": "dreamed"},
+      {"british": "encyclopaedia", "american": "encyclopedia"},
+      {"british": "enquiry", "american": "inquiry"},
+      {"british": "enrol", "american": "enroll"},
+      {"british": "enrolment", "american": "enrollment"},
+      {"british": "favourite", "american": "favorite"},
+      {"british": "fibre", "american": "fiber"},
+      {"british": "flavour", "american": "flavor"},
+      {"british": "focussed", "american": "focused"},
+      {"british": "fulfil", "american": "fulfill"},
+      {"british": "gaol", "american": "jail"},
+      {"british": "grey", "american": "gray"},
+      {"british": "harbour", "american": "harbor"},
+      {"british": "honour", "american": "honor"},
+      {"british": "humour", "american": "humor"},
+      {"british": "jewellery", "american": "jewelry"},
+      {"british": "kerb", "american": "curb"},
+      {"british": "labour", "american": "labor"},
+      {"british": "learnt", "american": "learned"},
+      {"british": "licence", "american": "license"},
+      {"british": "litre", "american": "liter"},
+      {"british": "manoeuvre", "american": "maneuver"},
+      {"british": "maths", "american": "math"},
+      {"british": "metre", "american": "meter"},
+      {"british": "mould", "american": "mold"},
+      {"british": "moustache", "american": "mustache"},
+      {"british": "neighbour", "american": "neighbor"},
+      {"british": "offence", "american": "offense"},
+      {"british": "omelette", "american": "omelet"},
+      {"british": "organisation", "american": "organization"},
+      {"british": "paediatric", "american": "pediatric"},
+      {"british": "plough", "american": "plow"},
+      {"british": "practise", "american": "practice"},
+      {"british": "programme", "american": "program"},
+      {"british": "pyjamas", "american": "pajamas"},
+      {"british": "realise", "american": "realize"},
+      {"british": "recognise", "american": "recognize"},
+      {"british": "rumour", "american": "rumor"},
+      {"british": "sceptic", "american": "skeptic"},
+      {"british": "skilful", "american": "skillful"},
+      {"british": "smelt", "american": "smelled"},
+      {"british": "speciality", "american": "specialty"},
+      {"british": "spelt", "american": "spelled"},
+      {"british": "spoilt", "american": "spoiled"},
+      {"british": "storey", "american": "story"},
+      {"british": "sulphur", "american": "sulfur"},
+      {"british": "theatre", "american": "theater"},
+      {"british": "tonne", "american": "ton"},
+      {"british": "travelled", "american": "traveled"},
+      {"british": "travelling", "american": "traveling"},
+      {"british": "traveller", "american": "traveler"},
+      {"british": "tyre", "american": "tire"},
+      {"british": "valour", "american": "valor"},
+      {"british": "vigour", "american": "vigor"},
+      {"british": "waggon", "american": "wagon"},
+      {"british": "whilst", "american": "while"},
+      {"british": "whisky", "american": "whiskey"},
+      {"british": "wilful", "american": "willful"},
+      {"british": "woollen", "american": "woolen"},
+      {"british": "yoghurt", "american": "yogurt"}
+    ]
+  },
+  "grammar_patterns": {
+    "have_got": {
+      "description": "British prefers 'have got', American prefers 'have'",
+      "british_pattern": "\\bhave got\\b|\\bhas got\\b|\\b've got\\b|\\b's got\\b",
+      "american_pattern": "\\bhave a\\b|\\bhas a\\b",
+      "examples": {
+        "british": ["I've got a car", "She's got three children", "Have you got any milk?"],
+        "american": ["I have a car", "She has three children", "Do you have any milk?"]
+      }
+    },
+    "gotten": {
+      "description": "American uses 'gotten' as past participle of 'get'",
+      "american_pattern": "\\bgotten\\b",
+      "british_equivalent": "got",
+      "examples": {
+        "american": ["I've gotten better", "Things have gotten worse", "She's gotten a promotion"],
+        "british": ["I've got better", "Things have got worse", "She's got a promotion"]
+      }
+    },
+    "collective_nouns": {
+      "description": "British treats collective nouns as plural, American as singular",
+      "examples": {
+        "british": ["The team are playing well", "The government have decided", "The staff are on strike", "The committee have voted"],
+        "american": ["The team is playing well", "The government has decided", "The staff is on strike", "The committee has voted"]
+      }
+    },
+    "present_perfect_vs_past": {
+      "description": "British uses present perfect more often for recent events",
+      "examples": {
+        "british": ["I've just eaten", "Have you seen the news?", "She's already left", "I've lost my keys"],
+        "american": ["I just ate", "Did you see the news?", "She already left", "I lost my keys"]
+      }
+    },
+    "preposition_usage": {
+      "description": "Different preposition preferences",
+      "patterns": [
+        {
+          "context": "days of week",
+          "british": "at the weekend",
+          "american": "on the weekend"
+        },
+        {
+          "context": "time",
+          "british": "quarter past/to",
+          "american": "quarter after/of"
+        },
+        {
+          "context": "location",
+          "british": "in hospital",
+          "american": "in the hospital"
+        },
+        {
+          "context": "correspondence",
+          "british": "write to",
+          "american": "write"
+        },
+        {
+          "context": "streets",
+          "british": "in the street",
+          "american": "on the street"
+        },
+        {
+          "context": "teams",
+          "british": "in the team",
+          "american": "on the team"
+        },
+        {
+          "context": "protest",
+          "british": "protest against",
+          "american": "protest"
+        },
+        {
+          "context": "different",
+          "british": "different to/from",
+          "american": "different from/than"
+        },
+        {
+          "context": "fill",
+          "british": "fill in a form",
+          "american": "fill out a form"
+        },
+        {
+          "context": "home",
+          "british": "at home",
+          "american": "home"
+        }
+      ]
+    },
+    "verb_forms": {
+      "description": "Different past tense and participle forms",
+      "patterns": [
+        {"verb": "dive", "british_past": "dived", "american_past": "dove"},
+        {"verb": "fit", "british_past": "fitted", "american_past": "fit"},
+        {"verb": "get", "british_participle": "got", "american_participle": "gotten"},
+        {"verb": "plead", "british_past": "pleaded", "american_past": "pled"},
+        {"verb": "prove", "british_participle": "proved", "american_participle": "proven"},
+        {"verb": "quit", "british_past": "quitted", "american_past": "quit"},
+        {"verb": "saw", "british_past": "sawed", "american_past": "sawed", "british_participle": "sawn", "american_participle": "sawed"},
+        {"verb": "sew", "british_participle": "sewn", "american_participle": "sewed"},
+        {"verb": "shine", "british_past": "shone", "american_past": "shined"},
+        {"verb": "show", "british_participle": "shown", "american_participle": "showed"},
+        {"verb": "shrink", "british_past": "shrank", "american_past": "shrunk"},
+        {"verb": "sink", "british_past": "sank", "american_past": "sunk"},
+        {"verb": "smell", "british_past": "smelt", "american_past": "smelled"},
+        {"verb": "sneak", "british_past": "sneaked", "american_past": "snuck"},
+        {"verb": "spell", "british_past": "spelt", "american_past": "spelled"},
+        {"verb": "spill", "british_past": "spilt", "american_past": "spilled"},
+        {"verb": "spit", "british_past": "spat", "american_past": "spit"},
+        {"verb": "spring", "british_past": "sprang", "american_past": "sprung"},
+        {"verb": "stink", "british_past": "stank", "american_past": "stunk"},
+        {"verb": "strive", "british_past": "strove", "american_past": "strived"},
+        {"verb": "swear", "british_participle": "sworn", "american_participle": "swore"},
+        {"verb": "wake", "british_past": "woke", "american_past": "waked"},
+        {"verb": "wet", "british_past": "wet", "american_past": "wetted"}
+      ]
+    },
+    "shall_will": {
+      "description": "British uses 'shall' for first person future, American prefers 'will'",
+      "british_pattern": "\\b(I|we) shall\\b",
+      "american_pattern": "\\b(I|we) will\\b",
+      "examples": {
+        "british": ["I shall go tomorrow", "Shall we dance?", "We shall see"],
+        "american": ["I will go tomorrow", "Will we dance?", "We will see"]
+      }
+    },
+    "do_auxiliary": {
+      "description": "British uses 'do' forms more in certain constructions",
+      "examples": {
+        "british": ["I haven't a clue", "Have you any idea?", "I hadn't time"],
+        "american": ["I don't have a clue", "Do you have any idea?", "I didn't have time"]
+      }
+    },
+    "neednt_dont_need": {
+      "description": "British uses 'needn't', American uses 'don't need to'",
+      "british_pattern": "\\bneedn't\\b",
+      "american_pattern": "\\bdon't need to\\b|\\bdoesn't need to\\b",
+      "examples": {
+        "british": ["You needn't worry", "She needn't come"],
+        "american": ["You don't need to worry", "She doesn't need to come"]
+      }
+    }
+  },
+  "punctuation_patterns": {
+    "quotation_marks": {
+      "description": "British prefers single quotes, American prefers double",
+      "british_primary": "'",
+      "american_primary": "\"",
+      "examples": {
+        "british": ["He said, 'Hello.'", "'That's odd,' she replied."],
+        "american": ["He said, \"Hello.\"", "\"That's odd,\" she replied."]
+      }
+    },
+    "period_placement": {
+      "description": "American puts periods inside quotes, British outside (for non-sentence quotes)",
+      "examples": {
+        "british": ["The sign said 'No Entry'.", "She called it 'rubbish'."],
+        "american": ["The sign said \"No Entry.\"", "She called it \"rubbish.\""]
+      }
+    },
+    "titles_abbreviations": {
+      "description": "British omits periods after titles, American includes them",
+      "british_pattern": "\\b(Mr|Mrs|Ms|Dr|Prof|Jr|Sr)\\b(?!\\.)",
+      "american_pattern": "\\b(Mr|Mrs|Ms|Dr|Prof|Jr|Sr)\\.",
+      "examples": {
+        "british": ["Mr Smith", "Dr Jones", "Mrs Brown"],
+        "american": ["Mr. Smith", "Dr. Jones", "Mrs. Brown"]
+      }
+    },
+    "date_formats": {
+      "description": "British uses DD/MM/YYYY, American uses MM/DD/YYYY",
+      "british_pattern": "\\b(0?[1-9]|[12][0-9]|3[01])/(0?[1-9]|1[0-2])/\\d{2,4}\\b",
+      "american_pattern": "\\b(0?[1-9]|1[0-2])/(0?[1-9]|[12][0-9]|3[01])/\\d{2,4}\\b",
+      "examples": {
+        "british": ["25/01/2026", "1st January 2026", "1 January 2026"],
+        "american": ["01/25/2026", "January 1st, 2026", "January 1, 2026"]
+      }
+    },
+    "time_formats": {
+      "description": "British prefers 24-hour clock, American prefers 12-hour with AM/PM",
+      "examples": {
+        "british": ["14:30", "09:00", "half past two"],
+        "american": ["2:30 PM", "9:00 AM", "two thirty"]
+      }
+    },
+    "oxford_comma": {
+      "description": "American typically uses Oxford comma, British often omits",
+      "examples": {
+        "british": ["red, white and blue", "apples, oranges and bananas"],
+        "american": ["red, white, and blue", "apples, oranges, and bananas"]
+      },
+      "notes": "This is a tendency rather than a strict rule; both forms are used in both dialects"
+    }
+  },
+  "idiomatic_expressions": {
+    "british": [
+      {"expression": "at the end of the day", "meaning": "ultimately"},
+      {"expression": "bob's your uncle", "meaning": "there you have it"},
+      {"expression": "brilliant", "meaning": "excellent (as exclamation)"},
+      {"expression": "can't be arsed", "meaning": "can't be bothered"},
+      {"expression": "couldn't care less", "meaning": "don't care at all"},
+      {"expression": "fancy", "meaning": "want/like (as verb)"},
+      {"expression": "give someone a bell", "meaning": "call someone"},
+      {"expression": "go pear-shaped", "meaning": "go wrong"},
+      {"expression": "have a go", "meaning": "try"},
+      {"expression": "it's not my cup of tea", "meaning": "not my preference"},
+      {"expression": "knackered", "meaning": "exhausted"},
+      {"expression": "mind the gap", "meaning": "watch out for the space"},
+      {"expression": "not my cup of tea", "meaning": "not to my liking"},
+      {"expression": "pissed", "meaning": "drunk (not angry)"},
+      {"expression": "quite", "meaning": "somewhat (understating)"},
+      {"expression": "rather", "meaning": "somewhat/quite"},
+      {"expression": "spot on", "meaning": "exactly right"},
+      {"expression": "straightaway", "meaning": "immediately"},
+      {"expression": "take the piss", "meaning": "mock/tease"},
+      {"expression": "the bee's knees", "meaning": "excellent"},
+      {"expression": "throw a spanner in the works", "meaning": "cause problems"}
+    ],
+    "american": [
+      {"expression": "a dime a dozen", "meaning": "very common"},
+      {"expression": "ballpark figure", "meaning": "rough estimate"},
+      {"expression": "beat around the bush", "meaning": "avoid the main topic"},
+      {"expression": "blow off steam", "meaning": "release stress"},
+      {"expression": "could care less", "meaning": "don't care (informal)"},
+      {"expression": "figure out", "meaning": "understand/solve"},
+      {"expression": "get the hang of", "meaning": "learn how to do"},
+      {"expression": "go figure", "meaning": "who would have thought"},
+      {"expression": "go with the flow", "meaning": "be flexible"},
+      {"expression": "hang out", "meaning": "spend time casually"},
+      {"expression": "heads up", "meaning": "warning/advance notice"},
+      {"expression": "hit the sack", "meaning": "go to bed"},
+      {"expression": "how come", "meaning": "why"},
+      {"expression": "monday morning quarterback", "meaning": "critic after the fact"},
+      {"expression": "on the same page", "meaning": "in agreement"},
+      {"expression": "piece of cake", "meaning": "easy"},
+      {"expression": "pissed", "meaning": "angry (not drunk)"},
+      {"expression": "take a rain check", "meaning": "postpone"},
+      {"expression": "throw a wrench in", "meaning": "cause problems"},
+      {"expression": "touch base", "meaning": "make contact"},
+      {"expression": "you bet", "meaning": "certainly"}
+    ]
+  }
+}