@mailwoman/match 9.4.0 → 10.1.0

package/out/tf.js

@@ -5,24 +5,26 @@
  *
  *   Term-frequency adjustment — making a rare-value agreement count more than a common one.
  *
- *   Two people both named "Vijayan" is far stronger evidence of a match than two both named "Smith",
+ *   Two people who share the name "Vijayan" are far stronger evidence of a match than two who share the name "Smith",
  *   because "Smith" agreements happen by chance all the time and "Vijayan" agreements don't. The
- *   Fellegi-Sunter `m` (how often a true match agrees) is roughly the same either way; what differs
+ *   Fellegi-Sunter `m` (how often a true match agrees) is roughly the same either way. what differs
  *   is `u` — the chance a _non_-match agrees — which for an exact agreement on value `v` is just
  *   how common `v` is. So we leave `m`, and replace the level's average `u` with `frequency(v)`,
  *   adding `log2(u_level / frequency(v))` to the weight: a big positive bump for rare values, a
  *   penalty for common ones.
  *
- *   Crucially for a label-free matcher: the frequencies are computed ON-THE-FLY from the input column
+ *   Crucially for a label-free matcher: the frequencies are computed on-the-FLY from the input column
  *   (the Splink approach) — no external Census table required. Build a {@link TermFrequencyTable}
  *   from the values you're matching, then attach it to a comparison with {@link withTermFrequency}.
  */
-// Local by design: `@mailwoman/record`'s per-field normalizers are the shared home; match takes no record dependency.
+// Local by design: `@mailwoman/record`'s per-field normalizers are the shared home.
+// Match takes no record dependency.
 const defaultNormalize = (value) => value.trim().toLowerCase().replaceAll(/\s+/g, " ");
 /**
- * Build a {@link TermFrequencyTable} from an iterable of values (e.g. every `given` name in the dataset). Values are
- * normalized (default: trim + lowercase + collapse whitespace) before counting, and `frequency()` normalizes its
- * argument the same way, so callers pass raw field values.
+ * Build a {@link TermFrequencyTable} from an iterable of values (e.g. Every `given` name in the dataset).
+ *
+ * Values are normalized (default: trim + lowercase + collapse whitespace) before counting.
+ * `frequency()` normalizes its argument the same way, so callers pass raw field values.
  */
 export function buildTermFrequencyTable(values, opts = {}) {
     const normalize = opts.normalize ?? defaultNormalize;
@@ -48,10 +50,14 @@ export function buildTermFrequencyTable(values, opts = {}) {
     };
 }
 /**
- * Attach a term-frequency adjustment to a comparison. By default it applies to the exact level (index 0) and looks up
- * the value via `value(a, b)` — usually the agreeing field extracted from one side. Returns a new comparison; the
- * underlying `assess` and levels are untouched, so this composes with EM (which re-estimates the base `m`/`u` the
- * adjustment sits on top of).
+ * Attach a term-frequency adjustment to a comparison.
+ *
+ * By default it applies to the exact level (index 0) and looks up the value via
+ * `value(a, b)` — usually the agreeing field extracted from one side.
+ * Returns a new comparison.
+ *
+ * The underlying `assess` and levels are untouched, so this composes with EM
+ * (which re-estimates the base `m`/`u` the adjustment sits on top of).
  */
 export function withTermFrequency(comparison, config) {
     const adjustment = {

package/out/tf.js.map

@@ -1 +1 @@
-{"version":3,"file":"tf.js","sourceRoot":"","sources":["../lib/tf.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;GAkBG;AAsBH,sHAAsH;AACtH,MAAM,gBAAgB,GAAG,CAAC,KAAa,EAAU,EAAE,CAAC,KAAK,CAAC,IAAI,EAAE,CAAC,WAAW,EAAE,CAAC,UAAU,CAAC,MAAM,EAAE,GAAG,CAAC,CAAA;AAEtG;;;;GAIG;AACH,MAAM,UAAU,uBAAuB,CACtC,MAA2C,EAC3C,OAAkD,EAAE;IAEpD,MAAM,SAAS,GAAG,IAAI,CAAC,SAAS,IAAI,gBAAgB,CAAA;IACpD,MAAM,MAAM,GAAG,IAAI,GAAG,EAAkB,CAAA;IACxC,IAAI,KAAK,GAAG,CAAC,CAAA;IAEb,KAAK,MAAM,KAAK,IAAI,MAAM,EAAE,CAAC;QAC5B,IAAI,KAAK,IAAI,IAAI;YAAE,SAAQ;QAC3B,MAAM,GAAG,GAAG,SAAS,CAAC,KAAK,CAAC,CAAA;QAE5B,IAAI,CAAC,GAAG;YAAE,SAAQ;QAClB,MAAM,CAAC,GAAG,CAAC,GAAG,EAAE,CAAC,MAAM,CAAC,GAAG,CAAC,GAAG,CAAC,IAAI,CAAC,CAAC,GAAG,CAAC,CAAC,CAAA;QAE3C,KAAK,EAAE,CAAA;IACR,CAAC;IAED,OAAO;QACN,KAAK;QACL,QAAQ,EAAE,MAAM,CAAC,IAAI;QACrB,SAAS,CAAC,KAAK;YACd,IAAI,KAAK,KAAK,CAAC;gBAAE,OAAO,CAAC,CAAA;YAEzB,OAAO,CAAC,MAAM,CAAC,GAAG,CAAC,SAAS,CAAC,KAAK,CAAC,CAAC,IAAI,CAAC,CAAC,GAAG,KAAK,CAAA;QACnD,CAAC;KACD,CAAA;AACF,CAAC;AAED;;;;;GAKG;AACH,MAAM,UAAU,iBAAiB,CAChC,UAAyB,EACzB,MAeC;IAED,MAAM,UAAU,GAA+B;QAC9C,SAAS,EAAE,CAAC,KAAK,EAAE,EAAE,CAAC,MAAM,CAAC,KAAK,CAAC,SAAS,CAAC,KAAK,CAAC;QACnD,MAAM,EAAE,IAAI,GAAG,CAAC,MAAM,CAAC,MAAM,IAAI,CAAC,CAAC,CAAC,CAAC;QACrC,KAAK,EAAE,MAAM,CAAC,KAAK;QACnB,MAAM,EAAE,MAAM,CAAC,MAAM;QACrB,gBAAgB,EAAE,MAAM,CAAC,gBAAgB;KACzC,CAAA;IAED,OAAO,EAAE,GAAG,UAAU,EAAE,aAAa,EAAE,UAAU,EAAE,CAAA;AACpD,CAAC"}
+{"version":3,"file":"tf.js","sourceRoot":"","sources":["../lib/tf.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;GAkBG;AAsBH,oFAAoF;AACpF,oCAAoC;AACpC,MAAM,gBAAgB,GAAG,CAAC,KAAa,EAAU,EAAE,CAAC,KAAK,CAAC,IAAI,EAAE,CAAC,WAAW,EAAE,CAAC,UAAU,CAAC,MAAM,EAAE,GAAG,CAAC,CAAA;AAEtG;;;;;GAKG;AACH,MAAM,UAAU,uBAAuB,CACtC,MAA2C,EAC3C,IAAI,GAA8C,EAAE;IAEpD,MAAM,SAAS,GAAG,IAAI,CAAC,SAAS,IAAI,gBAAgB,CAAA;IACpD,MAAM,MAAM,GAAG,IAAI,GAAG,EAAkB,CAAA;IACxC,IAAI,KAAK,GAAG,CAAC,CAAA;IAEb,KAAK,MAAM,KAAK,IAAI,MAAM,EAAE,CAAC;QAC5B,IAAI,KAAK,IAAI,IAAI;YAAE,SAAQ;QAC3B,MAAM,GAAG,GAAG,SAAS,CAAC,KAAK,CAAC,CAAA;QAE5B,IAAI,CAAC,GAAG;YAAE,SAAQ;QAClB,MAAM,CAAC,GAAG,CAAC,GAAG,EAAE,CAAC,MAAM,CAAC,GAAG,CAAC,GAAG,CAAC,IAAI,CAAC,CAAC,GAAG,CAAC,CAAC,CAAA;QAE3C,KAAK,EAAE,CAAA;IACR,CAAC;IAED,OAAO;QACN,KAAK;QACL,QAAQ,EAAE,MAAM,CAAC,IAAI;QACrB,SAAS,CAAC,KAAK;YACd,IAAI,KAAK,KAAK,CAAC;gBAAE,OAAO,CAAC,CAAA;YAEzB,OAAO,CAAC,MAAM,CAAC,GAAG,CAAC,SAAS,CAAC,KAAK,CAAC,CAAC,IAAI,CAAC,CAAC,GAAG,KAAK,CAAA;QACnD,CAAC;KACD,CAAA;AACF,CAAC;AAED;;;;;;;;;GASG;AACH,MAAM,UAAU,iBAAiB,CAChC,UAAyB,EACzB,MAqBC;IAED,MAAM,UAAU,GAA+B;QAC9C,SAAS,EAAE,CAAC,KAAK,EAAE,EAAE,CAAC,MAAM,CAAC,KAAK,CAAC,SAAS,CAAC,KAAK,CAAC;QACnD,MAAM,EAAE,IAAI,GAAG,CAAC,MAAM,CAAC,MAAM,IAAI,CAAC,CAAC,CAAC,CAAC;QACrC,KAAK,EAAE,MAAM,CAAC,KAAK;QACnB,MAAM,EAAE,MAAM,CAAC,MAAM;QACrB,gBAAgB,EAAE,MAAM,CAAC,gBAAgB;KACzC,CAAA;IAED,OAAO,EAAE,GAAG,UAAU,EAAE,aAAa,EAAE,UAAU,EAAE,CAAA;AACpD,CAAC"}

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@mailwoman/match",
-  "version": "9.4.0",
+  "version": "10.1.0",
   "description": "The geocode-first record matcher: block → score → cluster. This first reduce ships the string comparators (Jaro / Jaro-Winkler + an edit-distance fallback for compound surnames) that the Fellegi-Sunter scorer is built on.",
   "license": "AGPL-3.0-only OR LicenseRef-Commercial",
   "repository": {
@@ -13,15 +13,10 @@
     "out/**/*.js.map",
     "out/**/*.d.ts",
     "out/**/*.d.ts.map",
-    "*.ts",
-    "*.tsx",
-    "**/*.ts",
-    "**/*.tsx",
-    "!*.test.ts",
-    "!*.test.tsx",
+    "lib/**/*.ts",
+    "lib/**/*.tsx",
     "!**/*.test.ts",
-    "!**/*.test.tsx",
-    "!test/**"
+    "!**/*.test.tsx"
   ],
   "type": "module",
   "sideEffects": false,
@@ -39,45 +34,10 @@
       "node": "./out/index.js",
       "default": "./out/index.js"
     },
-    "./blocking": {
-      "types": "./out/blocking.d.ts",
-      "node": "./out/blocking.js",
-      "default": "./out/blocking.js"
-    },
-    "./clustering": {
-      "types": "./out/clustering.d.ts",
-      "node": "./out/clustering.js",
-      "default": "./out/clustering.js"
-    },
-    "./comparators": {
-      "types": "./out/comparators.d.ts",
-      "node": "./out/comparators.js",
-      "default": "./out/comparators.js"
-    },
-    "./distance": {
-      "types": "./out/distance.d.ts",
-      "node": "./out/distance.js",
-      "default": "./out/distance.js"
-    },
-    "./fellegi-sunter": {
-      "types": "./out/fellegi-sunter.d.ts",
-      "node": "./out/fellegi-sunter.js",
-      "default": "./out/fellegi-sunter.js"
-    },
-    "./em": {
-      "types": "./out/em.d.ts",
-      "node": "./out/em.js",
-      "default": "./out/em.js"
-    },
-    "./tf": {
-      "types": "./out/tf.d.ts",
-      "node": "./out/tf.js",
-      "default": "./out/tf.js"
-    },
-    "./gbt": {
-      "types": "./out/gbt.d.ts",
-      "node": "./out/gbt.js",
-      "default": "./out/gbt.js"
+    "./*": {
+      "types": "./out/*.d.ts",
+      "node": "./out/*.js",
+      "default": "./out/*.js"
     }
   },
   "publishConfig": {
@@ -89,45 +49,10 @@
         "node": "./out/index.js",
         "default": "./out/index.js"
       },
-      "./blocking": {
-        "types": "./out/blocking.d.ts",
-        "node": "./out/blocking.js",
-        "default": "./out/blocking.js"
-      },
-      "./clustering": {
-        "types": "./out/clustering.d.ts",
-        "node": "./out/clustering.js",
-        "default": "./out/clustering.js"
-      },
-      "./comparators": {
-        "types": "./out/comparators.d.ts",
-        "node": "./out/comparators.js",
-        "default": "./out/comparators.js"
-      },
-      "./distance": {
-        "types": "./out/distance.d.ts",
-        "node": "./out/distance.js",
-        "default": "./out/distance.js"
-      },
-      "./fellegi-sunter": {
-        "types": "./out/fellegi-sunter.d.ts",
-        "node": "./out/fellegi-sunter.js",
-        "default": "./out/fellegi-sunter.js"
-      },
-      "./em": {
-        "types": "./out/em.d.ts",
-        "node": "./out/em.js",
-        "default": "./out/em.js"
-      },
-      "./tf": {
-        "types": "./out/tf.d.ts",
-        "node": "./out/tf.js",
-        "default": "./out/tf.js"
-      },
-      "./gbt": {
-        "types": "./out/gbt.d.ts",
-        "node": "./out/gbt.js",
-        "default": "./out/gbt.js"
+      "./*": {
+        "types": "./out/*.d.ts",
+        "node": "./out/*.js",
+        "default": "./out/*.js"
       }
     },
     "imports": {
@@ -139,7 +64,7 @@
     }
   },
   "dependencies": {
-    "@mailwoman/spatial": "9.4.0",
+    "@mailwoman/spatial": "10.1.0",
     "fastest-levenshtein": "^1.0.16"
   },
   "devDependencies": {