puzlink 0.1.0

package/package.json

@@ -0,0 +1,57 @@
+{
+  "name": "puzlink",
+  "version": "0.1.0",
+  "description": "Tool to find patterns among sets of words",
+  "keywords": [
+    "puzzles"
+  ],
+  "homepage": "https://github.com/cjquines/puzlink.js#readme",
+  "bugs": {
+    "url": "https://github.com/cjquines/puzlink.js/issues"
+  },
+  "repository": {
+    "type": "git",
+    "url": "git+https://github.com/cjquines/puzlink.js.git"
+  },
+  "license": "MIT",
+  "author": "CJ Quines <cj@cjquines.com>",
+  "type": "module",
+  "main": "dist/index.js",
+  "files": [
+    "dist/**/*",
+    "!dist/tsconfig.*",
+    "src/**/*",
+    "!src/**/*.test.ts"
+  ],
+  "scripts": {
+    "build:categories": "tsx scripts/buildCategories.ts && prettier --write src/data/categories",
+    "build:knownLogProbs": "tsx scripts/buildKnownLogProbs.ts",
+    "build:tsc": "tsc --build tsconfig.build.json",
+    "format": "prettier --write .",
+    "lint": "eslint",
+    "test": "vitest run",
+    "test:evals": "tsx scripts/runEvals.ts",
+    "test:speed": "SPEED_TEST=true vitest run",
+    "test:watch": "vitest watch",
+    "typecheck": "tsc --noEmit"
+  },
+  "dependencies": {
+    "cromulence": "^0.4.1",
+    "simple-statistics": "^7.8.8"
+  },
+  "devDependencies": {
+    "@eslint/js": "^9.39.2",
+    "@types/node": "^24.0.15",
+    "@vitest/eslint-plugin": "^1.6.4",
+    "chalk": "^5.6.2",
+    "chokidar": "^5.0.0",
+    "eslint": "^9.39.2",
+    "iso-3166": "^4.4.0",
+    "meow": "^14.0.0",
+    "prettier": "^3.7.4",
+    "tsx": "^4.21.0",
+    "typescript": "^5.9.3",
+    "typescript-eslint": "^8.50.0",
+    "vitest": "^4.0.16"
+  }
+}

package/src/data/answerLengths.ts

@@ -0,0 +1,63 @@
+import { LogNum } from "../lib/logNum.js";
+
+/**
+ * The distribution of word lengths in a corpus is quite different than the
+ * distribution of answer lengths in a puzzlehunt.
+ *
+ * These numbers are based on Mystery Hunt answers from 1994 to 2025, weighing
+ * recent years more heavily.
+ */
+export const answerLengthLogProbs = new Map<number, LogNum>([
+  [1, LogNum.fromExp(-7.047625911102525)],
+  [2, LogNum.fromExp(-6.236695694886197)],
+  [3, LogNum.fromExp(-3.838800422087826)],
+  [4, LogNum.fromExp(-2.6750184983451355)],
+  [5, LogNum.fromExp(-2.5947331605600117)],
+  [6, LogNum.fromExp(-2.4056417519917175)],
+  [7, LogNum.fromExp(-2.299438218279509)],
+  [8, LogNum.fromExp(-2.325784418310741)],
+  [9, LogNum.fromExp(-2.273768359596283)],
+  [10, LogNum.fromExp(-2.3562780288733816)],
+  [11, LogNum.fromExp(-2.7401881334197165)],
+  [12, LogNum.fromExp(-2.806299158531779)],
+  [13, LogNum.fromExp(-2.974334758078257)],
+  [14, LogNum.fromExp(-3.3189249628019173)],
+  [15, LogNum.fromExp(-3.775209319306295)],
+  [16, LogNum.fromExp(-3.6217359168499983)],
+  [17, LogNum.fromExp(-4.25187012958121)],
+  [18, LogNum.fromExp(-4.454238618320455)],
+  [19, LogNum.fromExp(-4.473107102624838)],
+  [20, LogNum.fromExp(-4.864387575741046)],
+  [21, LogNum.fromExp(-5.463505806652715)],
+  [22, LogNum.fromExp(-5.831230586778032)],
+  [23, LogNum.fromExp(-5.7597716227958875)],
+  [24, LogNum.fromExp(-5.831230586778032)],
+  [25, LogNum.fromExp(-5.725870071120206)],
+  [26, LogNum.fromExp(-6.642160802994361)],
+  [27, LogNum.fromExp(-6.293854108726145)],
+  [28, LogNum.fromExp(-5.949013622434416)],
+  [29, LogNum.fromExp(-6.35447873054258)],
+  [30, LogNum.fromExp(-5.831230586778032)],
+  [31, LogNum.fromExp(-7.047625911102525)],
+  [32, LogNum.fromExp(-7.517629540348261)],
+  [33, LogNum.fromExp(-7.517629540348261)],
+  [34, LogNum.fromExp(-6.824482359788315)],
+  [35, LogNum.fromExp(-7.181157303727048)],
+  [36, LogNum.fromExp(-6.488010123167102)],
+  [37, LogNum.fromExp(-7.047625911102525)],
+  [38, LogNum.fromExp(-7.335307983554306)],
+  [39, LogNum.fromExp(-7.517629540348261)],
+  [40, LogNum.fromExp(-8.028455164114252)],
+  [41, LogNum.fromExp(-8.028455164114252)],
+  [42, LogNum.fromExp(-7.335307983554306)],
+  [43, LogNum.fromExp(-7.74077309166247)],
+  [45, LogNum.fromExp(-7.181157303727048)],
+  [50, LogNum.fromExp(-8.028455164114252)],
+  [52, LogNum.fromExp(-9.127067452782361)],
+  [54, LogNum.fromExp(-7.517629540348261)],
+  [56, LogNum.fromExp(-8.433920272222416)],
+  [60, LogNum.fromExp(-7.74077309166247)],
+  [67, LogNum.fromExp(-8.433920272222416)],
+  [86, LogNum.fromExp(-8.028455164114252)],
+  [100, LogNum.fromExp(-8.433920272222416)],
+]);

package/src/data/categories/README.md

@@ -0,0 +1,3 @@
+Files here are generated by `npm run build:categories`.
+
+countryAlpha2 and countryAlpha3 are from the `iso-3166` package.

package/src/data/categories/compass.ts

@@ -0,0 +1 @@
+export default ["w", "sw", "se", "s", "nw", "ne", "n", "e"];

package/src/data/categories/countryAlpha2.ts

@@ -0,0 +1,251 @@
+export default [
+  "zw",
+  "zm",
+  "za",
+  "yt",
+  "ye",
+  "ws",
+  "wf",
+  "vu",
+  "vn",
+  "vi",
+  "vg",
+  "ve",
+  "vc",
+  "va",
+  "uz",
+  "uy",
+  "us",
+  "um",
+  "ug",
+  "ua",
+  "tz",
+  "tw",
+  "tv",
+  "tt",
+  "tr",
+  "to",
+  "tn",
+  "tm",
+  "tl",
+  "tk",
+  "tj",
+  "th",
+  "tg",
+  "tf",
+  "td",
+  "tc",
+  "sz",
+  "sy",
+  "sx",
+  "sv",
+  "st",
+  "ss",
+  "sr",
+  "so",
+  "sn",
+  "sm",
+  "sl",
+  "sk",
+  "sj",
+  "si",
+  "sh",
+  "sg",
+  "se",
+  "sd",
+  "sc",
+  "sb",
+  "sa",
+  "rw",
+  "ru",
+  "rs",
+  "ro",
+  "re",
+  "qa",
+  "py",
+  "pw",
+  "pt",
+  "ps",
+  "pr",
+  "pn",
+  "pm",
+  "pl",
+  "pk",
+  "ph",
+  "pg",
+  "pf",
+  "pe",
+  "pa",
+  "om",
+  "nz",
+  "nu",
+  "nr",
+  "np",
+  "no",
+  "nl",
+  "ni",
+  "ng",
+  "nf",
+  "ne",
+  "nc",
+  "na",
+  "mz",
+  "my",
+  "mx",
+  "mw",
+  "mv",
+  "mu",
+  "mt",
+  "ms",
+  "mr",
+  "mq",
+  "mp",
+  "mo",
+  "mn",
+  "mm",
+  "ml",
+  "mk",
+  "mh",
+  "mg",
+  "mf",
+  "me",
+  "md",
+  "mc",
+  "ma",
+  "ly",
+  "lv",
+  "lu",
+  "lt",
+  "ls",
+  "lr",
+  "lk",
+  "li",
+  "lc",
+  "lb",
+  "la",
+  "kz",
+  "ky",
+  "kw",
+  "kr",
+  "kp",
+  "kn",
+  "km",
+  "ki",
+  "kh",
+  "kg",
+  "ke",
+  "jp",
+  "jo",
+  "jm",
+  "je",
+  "it",
+  "is",
+  "ir",
+  "iq",
+  "io",
+  "in",
+  "im",
+  "il",
+  "ie",
+  "id",
+  "hu",
+  "ht",
+  "hr",
+  "hn",
+  "hm",
+  "hk",
+  "gy",
+  "gw",
+  "gu",
+  "gt",
+  "gs",
+  "gr",
+  "gq",
+  "gp",
+  "gn",
+  "gm",
+  "gl",
+  "gi",
+  "gh",
+  "gg",
+  "gf",
+  "ge",
+  "gd",
+  "gb",
+  "ga",
+  "fr",
+  "fo",
+  "fm",
+  "fk",
+  "fj",
+  "fi",
+  "et",
+  "es",
+  "er",
+  "eh",
+  "eg",
+  "ee",
+  "ec",
+  "dz",
+  "do",
+  "dm",
+  "dk",
+  "dj",
+  "de",
+  "cz",
+  "cy",
+  "cx",
+  "cw",
+  "cv",
+  "cu",
+  "cr",
+  "co",
+  "cn",
+  "cm",
+  "cl",
+  "ck",
+  "ci",
+  "ch",
+  "cg",
+  "cf",
+  "cd",
+  "cc",
+  "ca",
+  "bz",
+  "by",
+  "bw",
+  "bv",
+  "bt",
+  "bs",
+  "br",
+  "bq",
+  "bo",
+  "bn",
+  "bm",
+  "bl",
+  "bj",
+  "bi",
+  "bh",
+  "bg",
+  "bf",
+  "be",
+  "bd",
+  "bb",
+  "ba",
+  "az",
+  "ax",
+  "aw",
+  "au",
+  "at",
+  "as",
+  "ar",
+  "aq",
+  "ao",
+  "am",
+  "al",
+  "ai",
+  "ag",
+  "af",
+  "ae",
+  "ad",
+];

package/src/data/categories/countryAlpha3.ts

@@ -0,0 +1,251 @@
+export default [
+  "zwe",
+  "zmb",
+  "zaf",
+  "yem",
+  "wsm",
+  "wlf",
+  "vut",
+  "vnm",
+  "vir",
+  "vgb",
+  "ven",
+  "vct",
+  "vat",
+  "uzb",
+  "usa",
+  "ury",
+  "umi",
+  "ukr",
+  "uga",
+  "tza",
+  "twn",
+  "tuv",
+  "tur",
+  "tun",
+  "tto",
+  "ton",
+  "tls",
+  "tkm",
+  "tkl",
+  "tjk",
+  "tha",
+  "tgo",
+  "tcd",
+  "tca",
+  "syr",
+  "syc",
+  "sxm",
+  "swz",
+  "swe",
+  "svn",
+  "svk",
+  "sur",
+  "stp",
+  "ssd",
+  "srb",
+  "spm",
+  "som",
+  "smr",
+  "slv",
+  "sle",
+  "slb",
+  "sjm",
+  "shn",
+  "sgs",
+  "sgp",
+  "sen",
+  "sdn",
+  "sau",
+  "rwa",
+  "rus",
+  "rou",
+  "reu",
+  "qat",
+  "pyf",
+  "pse",
+  "pry",
+  "prt",
+  "prk",
+  "pri",
+  "pol",
+  "png",
+  "plw",
+  "phl",
+  "per",
+  "pcn",
+  "pan",
+  "pak",
+  "omn",
+  "nzl",
+  "nru",
+  "npl",
+  "nor",
+  "nld",
+  "niu",
+  "nic",
+  "nga",
+  "nfk",
+  "ner",
+  "ncl",
+  "nam",
+  "myt",
+  "mys",
+  "mwi",
+  "mus",
+  "mtq",
+  "msr",
+  "mrt",
+  "moz",
+  "mnp",
+  "mng",
+  "mne",
+  "mmr",
+  "mlt",
+  "mli",
+  "mkd",
+  "mhl",
+  "mex",
+  "mdv",
+  "mdg",
+  "mda",
+  "mco",
+  "mar",
+  "maf",
+  "mac",
+  "lva",
+  "lux",
+  "ltu",
+  "lso",
+  "lka",
+  "lie",
+  "lca",
+  "lby",
+  "lbr",
+  "lbn",
+  "lao",
+  "kwt",
+  "kor",
+  "kna",
+  "kir",
+  "khm",
+  "kgz",
+  "ken",
+  "kaz",
+  "jpn",
+  "jor",
+  "jey",
+  "jam",
+  "ita",
+  "isr",
+  "isl",
+  "irq",
+  "irn",
+  "irl",
+  "iot",
+  "ind",
+  "imn",
+  "idn",
+  "hun",
+  "hti",
+  "hrv",
+  "hnd",
+  "hmd",
+  "hkg",
+  "guy",
+  "gum",
+  "guf",
+  "gtm",
+  "grl",
+  "grd",
+  "grc",
+  "gnq",
+  "gnb",
+  "gmb",
+  "glp",
+  "gin",
+  "gib",
+  "gha",
+  "ggy",
+  "geo",
+  "gbr",
+  "gab",
+  "fsm",
+  "fro",
+  "fra",
+  "flk",
+  "fji",
+  "fin",
+  "eth",
+  "est",
+  "esp",
+  "esh",
+  "eri",
+  "egy",
+  "ecu",
+  "dza",
+  "dom",
+  "dnk",
+  "dma",
+  "dji",
+  "deu",
+  "cze",
+  "cyp",
+  "cym",
+  "cxr",
+  "cuw",
+  "cub",
+  "cri",
+  "cpv",
+  "com",
+  "col",
+  "cok",
+  "cog",
+  "cod",
+  "cmr",
+  "civ",
+  "chn",
+  "chl",
+  "che",
+  "cck",
+  "can",
+  "caf",
+  "bwa",
+  "bvt",
+  "btn",
+  "brn",
+  "brb",
+  "bra",
+  "bol",
+  "bmu",
+  "blz",
+  "blr",
+  "blm",
+  "bih",
+  "bhs",
+  "bhr",
+  "bgr",
+  "bgd",
+  "bfa",
+  "bes",
+  "ben",
+  "bel",
+  "bdi",
+  "aze",
+  "aut",
+  "aus",
+  "atg",
+  "atf",
+  "ata",
+  "asm",
+  "arm",
+  "arg",
+  "are",
+  "and",
+  "alb",
+  "ala",
+  "aia",
+  "ago",
+  "afg",
+  "abw",
+];

package/src/data/categories/daysOfTheWeek.ts

@@ -0,0 +1 @@
+export default ["wed", "tue", "thu", "sun", "sat", "mon", "fri"];