indickit 0.10.0 → 0.11.0

package/dist/types/js/phonetic.d.ts

@@ -16,8 +16,10 @@ export { MAX_NAME_KEYS };
 export declare const RULES_VERSION: string;
 /** The sorted keys of one word; empty when it holds no letter the rules read. */
 export declare function keys(word: string): string[];
-/** A name split the way nameKeys and match split it: on spaces and
- * punctuation, with anything in brackets removed. */
+/** A name split on spaces and punctuation, with anything in brackets removed.
+ * nameKeys, joinedKeys and match split this way, then drop the leading
+ * titles (Shri, Smt., श्रीमती, திரு) of each comma-separated part ("Bajwa,
+ * Sardar Partap Singh"); a name of titles only keeps its last word. */
 export declare function words(name: string): string[];
 /** The keys of a whole name, one per combination of its words' keys, words
  * separated by a space. Two names match when these share an element, so
@@ -30,6 +32,6 @@ export declare const JOINED_MIN_CLASSES: number;
  * least JOINED_MIN_CLASSES classes. A search looks them up only when
  * nameKeys find nobody; match does not use them. */
 export declare function joinedKeys(name: string): string[];
-/** Whether two names have the same number of words and every pair of words,
- * in order, shares a key. */
+/** Whether two names, their leading titles dropped, have the same number of
+ * words and every pair of words, in order, shares a key. */
 export declare function match(a: string, b: string): boolean;

package/dist/types/js/romanize.d.ts

@@ -3,9 +3,10 @@
  * लक्ष्मी → lakshmi, മലൈക → malaika, پرویز → parvez.
  *
  * A ranked list: one word has several accepted spellings (Choudhury,
- * Chowdhury), and the first is the most likely. Two modes: "words" for
- * running text (the default) and "names" for fields known to hold person
- * names, where a lookup of known names comes first.
+ * Chowdhury), and the first is the most likely. Three modes: "words" for
+ * running text (the default); "names" for fields known to hold person
+ * names, where a lookup of known names comes first; and "places" for place
+ * names (its own tables in nine languages, the "words" tables in the others).
  *
  * The tables are learned from data and loaded per language, on demand:
  *
@@ -17,8 +18,11 @@
  *
  * @module
  */
-/** The tables: "words" for running text, "names" for person names. */
-export type Mode = "words" | "names";
+/**
+ * The tables: "words" for running text, "names" for person names, "places" for
+ * place names (own tables for bn hi ml mr or sat ta te ur; the "words" tables elsewhere).
+ */
+export type Mode = "words" | "names" | "places";
 /** Changes whenever any output changes: store it beside romanized text. */
 export declare const RULES_VERSION: string;
 /** The language codes that have tables, for one mode. */

package/dist/types/js/search-key.d.ts

@@ -0,0 +1,14 @@
+/**
+ * The one key to index and to query by:
+ * searchKey("किताबों", "hi") === searchKey("किताब", "hi"), and
+ * searchKey("हिन्दी", "hi") === searchKey("हिंदी", "hi").
+ *
+ * It normalizes, stems, then folds. The order was measured on search: fold
+ * after stem finds 2.4 points more of the right passages in Hindi and
+ * changes nothing in Bengali, Telugu or Assamese; fold before stem costs
+ * Assamese 3.7 points. A key is for matching only: never store it as text.
+ *
+ * @module
+ */
+/** The search key of `word` in language `lang` (a tag such as "hi", "hi-IN" or "hin"). */
+export declare function searchKey(word: string, lang: string): string;

package/dist/types/js/stem-compounds.d.ts

@@ -0,0 +1,16 @@
+/**
+ * Malayalam compounds for search: the first member that starts a word.
+ * Use it in place of the stem for Malayalam:
+ *
+ *   const key = compoundKey(w) ?? stem(w, "ml");
+ *
+ * It finds compounds and some oblique forms (കേരളസർക്കാർ and കേരളത്തിലെ
+ * share കേരള). On held-out news it found 5.5 points more of the right
+ * sentences than `stem` alone, and was 2.9 points less precise. A separate
+ * file, so that `stem` stays small for every other language. Normalize text
+ * first.
+ *
+ * @module
+ */
+/** The longest first member that starts `word` and leaves at least two code points, or null. */
+export declare function compoundKey(word: string): string | null;

package/dist/types/js/stem.d.ts

@@ -19,8 +19,17 @@ export declare const RULES_VERSION: string;
 /** The language codes that have a table. */
 export declare const LANGUAGES: readonly string[];
 /**
- * The search key of `word` in language `lang` (as bn gu hi kn ml mr ne pa
- * sa ta te ur). Only the tag's language counts: "ta-IN", "TA" and "tam" are
+ * The search key of `word` in language `lang` (any of the 22
+ * languages of the Eighth Schedule). Only the tag's language counts: "ta-IN", "TA" and "tam" are
  * "ta". For any other `lang`, `word` unchanged.
  */
-export declare function stem(word: string, lang: string): string;
+export declare function stem(word: string, lang: string, options?: StemOptions): string;
+/** Options for {@link stem}. */
+export type StemOptions = {
+    /**
+     * The fewest code points a stem keeps (default 2, at most 9). A field of
+     * names wants 4: it halves the names that lose their end (करीना → कर) and
+     * costs 0.5–2 points of search recall.
+     */
+    minStem?: number;
+};

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "indickit",
-  "version": "0.10.0",
+  "version": "0.11.0",
   "description": "Small, exact utilities for text in Indian languages: a phonetic key that matches a name across 21 Indian scripts and English, a normalizer that gives text that looks the same one encoding, a segmenter for the letters a reader sees, and a stemmer for search.",
   "license": "MIT",
   "packageManager": "bun@1.3.14",
@@ -26,6 +26,14 @@
       "types": "./dist/types/js/stem.d.ts",
       "default": "./dist/stem.js"
     },
+    "./search-key": {
+      "types": "./dist/types/js/search-key.d.ts",
+      "default": "./dist/search-key.js"
+    },
+    "./stem-compounds": {
+      "types": "./dist/types/js/stem-compounds.d.ts",
+      "default": "./dist/stem-compounds.js"
+    },
     "./romanize": {
       "types": "./dist/types/js/romanize.d.ts",
       "default": "./dist/romanize.js"
@@ -48,7 +56,7 @@
   ],
   "sideEffects": false,
   "scripts": {
-    "build": "bun build js/phonetic.ts --outfile dist/phonetic.js --target browser --format esm --minify && bun build js/normalize.ts --outfile dist/normalize.js --target browser --format esm --minify && bun build js/segment.ts --outfile dist/segment.js --target browser --format esm --minify && bun build js/stem.ts --outfile dist/stem.js --target browser --format esm --minify && bun build js/romanize.ts --outfile dist/romanize.js --target browser --format esm --minify && bun build js/phonetic-search.ts --outfile dist/phonetic-search.js --target browser --format esm --minify && bun build js/deromanize.ts --outfile dist/deromanize.js --target browser --format esm --minify && bun build js/wellformed.ts --outfile dist/wellformed.js --target browser --format esm --minify && tsc -p tsconfig.json",
+    "build": "bun build js/phonetic.ts --outfile dist/phonetic.js --target browser --format esm --minify && bun build js/normalize.ts --outfile dist/normalize.js --target browser --format esm --minify && bun build js/segment.ts --outfile dist/segment.js --target browser --format esm --minify && bun build js/stem.ts --outfile dist/stem.js --target browser --format esm --minify && bun build js/stem-compounds.ts --outfile dist/stem-compounds.js --target browser --format esm --minify && bun build js/search-key.ts --outfile dist/search-key.js --target browser --format esm --minify && bun build js/romanize.ts --outfile dist/romanize.js --target browser --format esm --minify && bun build js/phonetic-search.ts --outfile dist/phonetic-search.js --target browser --format esm --minify && bun build js/deromanize.ts --outfile dist/deromanize.js --target browser --format esm --minify && bun build js/wellformed.ts --outfile dist/wellformed.js --target browser --format esm --minify && tsc -p tsconfig.json",
     "test": "bun test",
     "check-dist": "node js/check-dist.mjs"
   },