@lacspace/nepali-match 1.0.0

package/LICENSE

@@ -0,0 +1,51 @@
+Lacspace Free Licence
+Version 1.0, August 2026
+
+Copyright (c) 2026 Lacspace
+
+PREAMBLE
+
+This software is published by Lacspace under the Lacspace Free Licence — a free,
+permissive licence that lets you use this software for any purpose, including in
+commercial products and services, at no cost. It grants the same freedoms as
+common permissive open-source licences; the only condition is that this notice
+travels with the software. The canonical, always-current text of this licence is
+maintained at https://lacspace.com/licenses/lacspace-free-1.0
+
+GRANT OF RIGHTS
+
+Permission is hereby granted, free of charge, to any person or organisation
+obtaining a copy of this software and its associated documentation and data files
+(the "Software"), to deal in the Software without restriction, including without
+limitation the rights to use, copy, modify, merge, publish, distribute,
+sublicense, and/or sell copies of the Software, and to permit persons to whom the
+Software is furnished to do so, subject to the conditions below. These rights are
+granted for any purpose, personal or commercial, and are perpetual, worldwide,
+non-exclusive, and royalty-free.
+
+CONDITIONS
+
+The above copyright notice, this permission notice, and the name of this licence
+("Lacspace Free Licence") shall be included in all copies or substantial portions
+of the Software.
+
+TRADEMARKS
+
+This licence does not grant permission to use the trade names, trademarks, service
+marks, logos, or product names of Lacspace, except as required to reproduce the
+notice above or to describe the origin of the Software in a truthful manner.
+
+DISCLAIMER OF WARRANTY AND LIMITATION OF LIABILITY
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS
+FOR A PARTICULAR PURPOSE, AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR
+COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES, OR OTHER LIABILITY, WHETHER IN
+AN ACTION OF CONTRACT, TORT, OR OTHERWISE, ARISING FROM, OUT OF, OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+
+---
+
+The Lacspace Free Licence is a source-available, permissive licence and is not (as
+of this version) an OSI-approved licence. In substance it grants the same freedoms
+as the MIT Licence. Learn more at https://lacspace.com/licenses

package/README.md

@@ -0,0 +1,78 @@
+# @lacspace/nepali-match
+
+Find names and keywords in Nepali and English text the way a Nepali reader would:
+- **Spelling variants match:** काठमाडौँ, काठमाडौं and काठमाण्डौ, or चन्द्र and चंद्र.
+- **Words with a postposition match:** झापाको is Jhapa and चितवनमा is Chitwan.
+- **Different words don't match:** पर्वतारोही (climber) is not Parbat.
+- **Short English acronyms are exact-case:** "SEE results" counts, "Come and see" doesn't.
+
+It is pure JS with no dependencies, and it is safe for React Native.
+
+```ts
+import { createMatcher, districtTerms, near, normaliseNe } from "@lacspace/nepali-match";
+
+const areas = createMatcher(districtTerms());
+areas.ids("चितवनमा बाढी, झापाको मेचीनगरमा पहिरो");   // ["chitwan", "jhapa"]
+areas.test("दुई पर्वतारोही बेपत्ता");                  // false
+areas.find("काठमाण्डौबाटै आएका")[0];
+// { id: "kathmandu", term: "काठमाण्डौ", lang: "ne", index: 0, end: 13, text: "काठमाण्डौबाटै", suffix: "बाटै" }
+
+const exam = ["परीक्षा", "नतिजा", "विज्ञापन", "exam", "result"];
+near("लोकसेवा आयोगले निजामती विधेयकमा राय दियो", "लोकसेवा", exam, 60);   // null: not exam news
+near("लोकसेवा आयोगको खरिदार परीक्षाको नतिजा", "लोकसेवा", exam, 60);    // { a, b, gap }
+
+createMatcher([{ id: "see", en: "SEE", ne: "एसईई" }]).test("Come and see");   // false
+normaliseNe("काठमाडौँ") === normaliseNe("काठमाडौं");                          // true
+```
+
+## How matching works
+
+**`normaliseNe(text, { loose?, digits? })`** applies these steps in order:
+1. NFC.
+2. Chandrabindu → anusvara.
+3. A half nasal before a consonant (ङ्, ञ्, ण्, न्, म्) → anusvara.
+4. ई/ी → इ/ि and ऊ/ू → उ/ु.
+5. Nukta, ZWJ, ZWNJ and soft hyphens are removed.
+6. Devanagari digits → ASCII.
+7. Whitespace collapses.
+
+`loose: true` also folds श/ष → स, व → ब and ण → न. Latin text is left as it is.
+
+**Nepali terms** match as whole words:
+- Nothing may stand before the word except a space or punctuation.
+- After the word, a chain of up to three `POSTPOSITIONS` may follow: मा, को, का, की, ले, लाई, बाट, सँग, देखि, सम्म, तिर, भित्र, हरू, मै, बाटै, नै … Anything else after it means it's a different word.
+- Turn this off with `postpositions: false`. Add your own with `extraSuffixes`.
+
+**English terms** match as whole words, ignoring case. Exceptions:
+- Under the default `caseSensitive: "auto"` rule, an all-caps term of 2–5 letters (SEE, NEB, PSC) must match its case exactly.
+- Set `caseSensitive` per term or per matcher to change this.
+- An all-caps headline ("COME AND SEE") still matches SEE. Check the case of the surrounding text if your input has shouty headlines.
+
+**Overlaps:** the longest match wins, so "Nawalparasi West" beats "Nawalparasi". Pass `overlaps: true` to keep both.
+
+Every match carries `index`/`end` offsets into the original text (after NFC), so you can highlight or cut it.
+
+## API
+
+- **`createMatcher(terms, options?)`** returns `{ find(text), test(text, id?), ids(text), size }`. Compile it once and reuse it.
+  - A term is either a string, or `{ id?, en?, ne?, aliases?, caseSensitive? }`. `en` and `ne` each take one spelling or an array.
+- **`findTerms(text, terms, options?)`** and **`contains(text, terms, options?)`** are one-off shortcuts.
+- **`near(text, a, b, maxChars | options, sameSentence?)`** returns the closest `{ a, b, gap }` pair of matches within `maxChars` (default 60), in either order, or null.
+  - By default both must sit in the same sentence. A sentence ends at । ॥ ? ! or a newline, or at "." before a space.
+  - Dotted abbreviations such as ने.क.पा. and U.S. never end a sentence.
+- **`sentenceSpans(text)`** returns the sentence boundaries `near` uses.
+- **`splitSuffix(word)`**: for example, `"जिल्लाहरूमा"` → `{ stem: "जिल्ला", suffixes: ["हरु", "मा"] }`.
+- **`districtTerms()`** returns all 77 districts.
+  - **Names and ids:** names come from `@lacspace/nepali-utils`. Ids are slugs such as `"nawalparasi-east"`, and `province` is a number.
+  - **Spellings:** each district carries the spellings seen in real copy: Kavre/काभ्रे, Rukum East/रुकुम पूर्व, Kapilbastu, मोरंग/मोरङ…
+  - **Case:** English district names are exact-case, so "dang it" is not Dang.
+  - **`ambiguous: true`:** marks Parbat, because पर्वत also means "mountain". Confirm it with `near()` or with district/area context before you tag a story.
+
+## Limits
+
+- The matcher is rule-based and does no stemming beyond postpositions. Verb forms and compounds won't match, which is the point.
+- Spellings that differ in more than the folded letters (for example गोर्खा and गोरखा) need an alias.
+
+---
+
+Built by [Lacspace](https://lacspace.com). Licensed under the Lacspace Free Licence v1.0 (see LICENSE).

package/dist/index.cjs

@@ -0,0 +1,428 @@
+'use strict';
+
+// ../nepali-utils/dist/index.js
+var DISTRICTS = [
+  // Koshi (1)
+  { name: "Bhojpur", nameNp: "\u092D\u094B\u091C\u092A\u0941\u0930", province: 1 },
+  { name: "Dhankuta", nameNp: "\u0927\u0928\u0915\u0941\u091F\u093E", province: 1 },
+  { name: "Ilam", nameNp: "\u0907\u0932\u093E\u092E", province: 1 },
+  { name: "Jhapa", nameNp: "\u091D\u093E\u092A\u093E", province: 1 },
+  { name: "Khotang", nameNp: "\u0916\u094B\u091F\u093E\u0919", province: 1 },
+  { name: "Morang", nameNp: "\u092E\u094B\u0930\u0919", province: 1 },
+  { name: "Okhaldhunga", nameNp: "\u0913\u0916\u0932\u0922\u0941\u0902\u0917\u093E", province: 1 },
+  { name: "Panchthar", nameNp: "\u092A\u093E\u0901\u091A\u0925\u0930", province: 1 },
+  { name: "Sankhuwasabha", nameNp: "\u0938\u0902\u0916\u0941\u0935\u093E\u0938\u092D\u093E", province: 1 },
+  { name: "Solukhumbu", nameNp: "\u0938\u094B\u0932\u0941\u0916\u0941\u092E\u094D\u092C\u0941", province: 1 },
+  { name: "Sunsari", nameNp: "\u0938\u0941\u0928\u0938\u0930\u0940", province: 1 },
+  { name: "Taplejung", nameNp: "\u0924\u093E\u092A\u094D\u0932\u0947\u091C\u0941\u0919", province: 1 },
+  { name: "Terhathum", nameNp: "\u0924\u0947\u0939\u094D\u0930\u0925\u0941\u092E", province: 1 },
+  { name: "Udayapur", nameNp: "\u0909\u0926\u092F\u092A\u0941\u0930", province: 1 },
+  // Madhesh (2)
+  { name: "Bara", nameNp: "\u092C\u093E\u0930\u093E", province: 2 },
+  { name: "Dhanusha", nameNp: "\u0927\u0928\u0941\u0937\u093E", province: 2 },
+  { name: "Mahottari", nameNp: "\u092E\u0939\u094B\u0924\u094D\u0924\u0930\u0940", province: 2 },
+  { name: "Parsa", nameNp: "\u092A\u0930\u094D\u0938\u093E", province: 2 },
+  { name: "Rautahat", nameNp: "\u0930\u094C\u0924\u0939\u091F", province: 2 },
+  { name: "Saptari", nameNp: "\u0938\u092A\u094D\u0924\u0930\u0940", province: 2 },
+  { name: "Sarlahi", nameNp: "\u0938\u0930\u094D\u0932\u093E\u0939\u0940", province: 2 },
+  { name: "Siraha", nameNp: "\u0938\u093F\u0930\u0939\u093E", province: 2 },
+  // Bagmati (3)
+  { name: "Bhaktapur", nameNp: "\u092D\u0915\u094D\u0924\u092A\u0941\u0930", province: 3 },
+  { name: "Chitwan", nameNp: "\u091A\u093F\u0924\u0935\u0928", province: 3 },
+  { name: "Dhading", nameNp: "\u0927\u093E\u0926\u093F\u0919", province: 3 },
+  { name: "Dolakha", nameNp: "\u0926\u094B\u0932\u0916\u093E", province: 3 },
+  { name: "Kathmandu", nameNp: "\u0915\u093E\u0920\u092E\u093E\u0921\u094C\u0902", province: 3 },
+  { name: "Kavrepalanchok", nameNp: "\u0915\u093E\u092D\u094D\u0930\u0947\u092A\u0932\u093E\u091E\u094D\u091A\u094B\u0915", province: 3 },
+  { name: "Lalitpur", nameNp: "\u0932\u0932\u093F\u0924\u092A\u0941\u0930", province: 3 },
+  { name: "Makwanpur", nameNp: "\u092E\u0915\u0935\u093E\u0928\u092A\u0941\u0930", province: 3 },
+  { name: "Nuwakot", nameNp: "\u0928\u0941\u0935\u093E\u0915\u094B\u091F", province: 3 },
+  { name: "Ramechhap", nameNp: "\u0930\u093E\u092E\u0947\u091B\u093E\u092A", province: 3 },
+  { name: "Rasuwa", nameNp: "\u0930\u0938\u0941\u0935\u093E", province: 3 },
+  { name: "Sindhuli", nameNp: "\u0938\u093F\u0928\u094D\u0927\u0941\u0932\u0940", province: 3 },
+  { name: "Sindhupalchok", nameNp: "\u0938\u093F\u0928\u094D\u0927\u0941\u092A\u093E\u0932\u094D\u091A\u094B\u0915", province: 3 },
+  // Gandaki (4)
+  { name: "Baglung", nameNp: "\u092C\u093E\u0917\u0932\u0941\u0919", province: 4 },
+  { name: "Gorkha", nameNp: "\u0917\u094B\u0930\u0916\u093E", province: 4 },
+  { name: "Kaski", nameNp: "\u0915\u093E\u0938\u094D\u0915\u0940", province: 4 },
+  { name: "Lamjung", nameNp: "\u0932\u092E\u091C\u0941\u0919", province: 4 },
+  { name: "Manang", nameNp: "\u092E\u0928\u093E\u0919", province: 4 },
+  { name: "Mustang", nameNp: "\u092E\u0941\u0938\u094D\u0924\u093E\u0919", province: 4 },
+  { name: "Myagdi", nameNp: "\u092E\u094D\u092F\u093E\u0917\u094D\u0926\u0940", province: 4 },
+  { name: "Nawalparasi East", nameNp: "\u0928\u0935\u0932\u092A\u0930\u093E\u0938\u0940 (\u092C\u0930\u094D\u0926\u0918\u093E\u091F \u0938\u0941\u0938\u094D\u0924\u093E \u092A\u0942\u0930\u094D\u0935)", province: 4, aliases: ["Nawalpur", "\u0928\u0935\u0932\u092A\u0941\u0930", "Nawalparasi (East of Bardaghat Susta)", "Nawalparasi (Bardaghat Susta East)", "Nawalparasi Purba", "\u0928\u0935\u0932\u092A\u0930\u093E\u0938\u0940 \u092A\u0942\u0930\u094D\u0935"] },
+  { name: "Parbat", nameNp: "\u092A\u0930\u094D\u0935\u0924", province: 4 },
+  { name: "Syangja", nameNp: "\u0938\u094D\u092F\u093E\u0919\u094D\u091C\u093E", province: 4 },
+  { name: "Tanahun", nameNp: "\u0924\u0928\u0939\u0941\u0901", province: 4 },
+  // Lumbini (5)
+  { name: "Arghakhanchi", nameNp: "\u0905\u0930\u094D\u0918\u093E\u0916\u093E\u0901\u091A\u0940", province: 5 },
+  { name: "Banke", nameNp: "\u092C\u093E\u0901\u0915\u0947", province: 5 },
+  { name: "Bardiya", nameNp: "\u092C\u0930\u094D\u0926\u093F\u092F\u093E", province: 5 },
+  { name: "Dang", nameNp: "\u0926\u093E\u0919", province: 5 },
+  { name: "Eastern Rukum", nameNp: "\u092A\u0942\u0930\u094D\u0935\u0940 \u0930\u0941\u0915\u0941\u092E", province: 5, aliases: ["Rukum East", "Rukum Purba", "\u0930\u0941\u0915\u0941\u092E \u092A\u0942\u0930\u094D\u0935"] },
+  { name: "Gulmi", nameNp: "\u0917\u0941\u0932\u094D\u092E\u0940", province: 5 },
+  { name: "Kapilvastu", nameNp: "\u0915\u092A\u093F\u0932\u0935\u0938\u094D\u0924\u0941", province: 5 },
+  { name: "Nawalparasi West", nameNp: "\u0928\u0935\u0932\u092A\u0930\u093E\u0938\u0940 (\u092C\u0930\u094D\u0926\u0918\u093E\u091F \u0938\u0941\u0938\u094D\u0924\u093E \u092A\u0936\u094D\u091A\u093F\u092E)", province: 5, aliases: ["Parasi", "\u092A\u0930\u093E\u0938\u0940", "Nawalparasi (West of Bardaghat Susta)", "Nawalparasi (Bardaghat Susta West)", "Nawalparasi Paschim", "\u0928\u0935\u0932\u092A\u0930\u093E\u0938\u0940 \u092A\u0936\u094D\u091A\u093F\u092E"] },
+  { name: "Palpa", nameNp: "\u092A\u093E\u0932\u094D\u092A\u093E", province: 5 },
+  { name: "Pyuthan", nameNp: "\u092A\u094D\u092F\u0941\u0920\u093E\u0928", province: 5 },
+  { name: "Rolpa", nameNp: "\u0930\u094B\u0932\u094D\u092A\u093E", province: 5 },
+  { name: "Rupandehi", nameNp: "\u0930\u0942\u092A\u0928\u094D\u0926\u0947\u0939\u0940", province: 5 },
+  // Karnali (6)
+  { name: "Dailekh", nameNp: "\u0926\u0948\u0932\u0947\u0916", province: 6 },
+  { name: "Dolpa", nameNp: "\u0921\u094B\u0932\u094D\u092A\u093E", province: 6 },
+  { name: "Humla", nameNp: "\u0939\u0941\u092E\u094D\u0932\u093E", province: 6 },
+  { name: "Jajarkot", nameNp: "\u091C\u093E\u091C\u0930\u0915\u094B\u091F", province: 6 },
+  { name: "Jumla", nameNp: "\u091C\u0941\u092E\u094D\u0932\u093E", province: 6 },
+  { name: "Kalikot", nameNp: "\u0915\u093E\u0932\u093F\u0915\u094B\u091F", province: 6 },
+  { name: "Mugu", nameNp: "\u092E\u0941\u0917\u0941", province: 6 },
+  { name: "Salyan", nameNp: "\u0938\u0932\u094D\u092F\u093E\u0928", province: 6 },
+  { name: "Surkhet", nameNp: "\u0938\u0941\u0930\u094D\u0916\u0947\u0924", province: 6 },
+  { name: "Western Rukum", nameNp: "\u092A\u0936\u094D\u091A\u093F\u092E\u0940 \u0930\u0941\u0915\u0941\u092E", province: 6, aliases: ["Rukum West", "Rukum Paschim", "\u0930\u0941\u0915\u0941\u092E \u092A\u0936\u094D\u091A\u093F\u092E"] },
+  // Sudurpashchim (7)
+  { name: "Achham", nameNp: "\u0905\u091B\u093E\u092E", province: 7 },
+  { name: "Baitadi", nameNp: "\u092C\u0948\u0924\u0921\u0940", province: 7 },
+  { name: "Bajhang", nameNp: "\u092C\u091D\u093E\u0919", province: 7 },
+  { name: "Bajura", nameNp: "\u092C\u093E\u091C\u0941\u0930\u093E", province: 7 },
+  { name: "Dadeldhura", nameNp: "\u0921\u0921\u0947\u0932\u094D\u0927\u0941\u0930\u093E", province: 7 },
+  { name: "Darchula", nameNp: "\u0926\u093E\u0930\u094D\u091A\u0941\u0932\u093E", province: 7 },
+  { name: "Doti", nameNp: "\u0921\u094B\u091F\u0940", province: 7 },
+  { name: "Kailali", nameNp: "\u0915\u0948\u0932\u093E\u0932\u0940", province: 7 },
+  { name: "Kanchanpur", nameNp: "\u0915\u091E\u094D\u091A\u0928\u092A\u0941\u0930", province: 7 }
+];
+
+// src/districts.ts
+var ALIASES = {
+  Kathmandu: { en: ["Katmandu"], ne: ["\u0915\u093E\u0920\u092E\u093E\u0923\u094D\u0921\u094C", "\u0915\u093E\u0920\u092E\u093E\u0928\u094D\u0921\u0941"] },
+  Kavrepalanchok: { en: ["Kavre", "Kabhre", "Kabhrepalanchok", "Kavrepalanchowk"], ne: ["\u0915\u093E\u092D\u094D\u0930\u0947", "\u0915\u093E\u092D\u094D\u0930\u0947\u092A\u0932\u093E\u0928\u094D\u091A\u094B\u0915"] },
+  Sindhupalchok: { en: ["Sindhupalchowk"] },
+  "Nawalparasi East": { en: ["Nawalparasi (East)", "East Nawalparasi", "Nawalpur"], ne: ["\u0928\u0935\u0932\u092A\u0930\u093E\u0938\u0940 \u092A\u0942\u0930\u094D\u0935", "\u092A\u0942\u0930\u094D\u0935\u0940 \u0928\u0935\u0932\u092A\u0930\u093E\u0938\u0940", "\u0928\u0935\u0932\u092A\u0941\u0930"] },
+  "Nawalparasi West": { en: ["Nawalparasi (West)", "West Nawalparasi"], ne: ["\u0928\u0935\u0932\u092A\u0930\u093E\u0938\u0940 \u092A\u0936\u094D\u091A\u093F\u092E", "\u092A\u0936\u094D\u091A\u093F\u092E\u0940 \u0928\u0935\u0932\u092A\u0930\u093E\u0938\u0940"] },
+  "Eastern Rukum": { en: ["Rukum East", "East Rukum", "Rukum (East)"], ne: ["\u0930\u0941\u0915\u0941\u092E \u092A\u0942\u0930\u094D\u0935"] },
+  "Western Rukum": { en: ["Rukum West", "West Rukum", "Rukum (West)"], ne: ["\u0930\u0941\u0915\u0941\u092E \u092A\u0936\u094D\u091A\u093F\u092E"] },
+  Tanahun: { en: ["Tanahu"], ne: ["\u0924\u0928\u0939\u0941"] },
+  Dhanusha: { en: ["Dhanusa"] },
+  Kapilvastu: { en: ["Kapilbastu"], ne: ["\u0915\u092A\u093F\u0932\u092C\u0938\u094D\u0924\u0941"] },
+  Makwanpur: { en: ["Makawanpur"] },
+  Sankhuwasabha: { en: ["Sankhuwasava"] },
+  Terhathum: { en: ["Tehrathum"], ne: ["\u0924\u0947\u0939\u0925\u0941\u092E"] },
+  Okhaldhunga: { ne: ["\u0913\u0916\u0932\u0922\u0941\u0919\u094D\u0917\u093E"] },
+  Syangja: { en: ["Syanja"], ne: ["\u0938\u094D\u092F\u093E\u0919\u091C\u093E"] },
+  Achham: { en: ["Accham"] },
+  Udayapur: { en: ["Udaypur"] },
+  Bardiya: { en: ["Bardia"] },
+  Ilam: { en: ["Illam"] },
+  Baglung: { ne: ["\u092C\u093E\u0917\u094D\u0932\u0941\u0919"] },
+  Rupandehi: { ne: ["\u0930\u0941\u092A\u0928\u094D\u0926\u0947\u0939\u0940"] },
+  Dadeldhura: { ne: ["\u0921\u0901\u0921\u0947\u0932\u0927\u0941\u0930\u093E"] },
+  Mahottari: { ne: ["\u092E\u0939\u094B\u0924\u0930\u0940"] }
+};
+var AMBIGUOUS = /* @__PURE__ */ new Set(["Parbat"]);
+var slug = (s) => s.toLowerCase().replace(/[^a-z0-9]+/g, "-").replace(/^-|-$/g, "");
+function districtTerms() {
+  return DISTRICTS.map((d) => {
+    const extra = ALIASES[d.name] ?? {};
+    const ne = /* @__PURE__ */ new Set([d.nameNp, ...extra.ne ?? []]);
+    for (const n of [...ne]) if (n.endsWith("\u0919")) ne.add(n.slice(0, -1) + "\u0902\u0917");
+    return {
+      id: slug(d.name),
+      en: [d.name, ...extra.en ?? []],
+      ne: [...ne],
+      province: d.province,
+      ...AMBIGUOUS.has(d.name) ? { ambiguous: true } : {},
+      caseSensitive: true
+    };
+  });
+}
+
+// src/index.ts
+var VERSION = "1.0.0";
+var NUKTA = 2364;
+var HALANT = 2381;
+var NASALS = /* @__PURE__ */ new Set([2329, 2334, 2339, 2344, 2350]);
+var DROP = /* @__PURE__ */ new Set([NUKTA, 8204, 8205, 173, 65279]);
+var FOLD = {
+  2305: 2306,
+  // ँ → ं
+  2312: 2311,
+  // ई → इ
+  2314: 2313,
+  // ऊ → उ
+  2368: 2367,
+  // ी → ि
+  2370: 2369
+  // ू → ु
+};
+var LOOSE = {
+  2358: 2360,
+  // श → स
+  2359: 2360,
+  // ष → स
+  2357: 2348,
+  // व → ब
+  2339: 2344
+  // ण → न
+};
+var isConsonant = (c) => c >= 2325 && c <= 2361 || c >= 2392 && c <= 2399;
+function mapNormalise(input, opts = {}) {
+  const digits = opts.digits !== false;
+  const s = input.normalize("NFC");
+  const out = [];
+  const map = [];
+  const push = (ch, i) => {
+    out.push(ch);
+    map.push(i);
+  };
+  const next = (i) => {
+    let j = i + 1;
+    while (j < s.length && DROP.has(s.charCodeAt(j))) j++;
+    return j;
+  };
+  let lastSpace = false;
+  for (let i = 0; i < s.length; i++) {
+    let c = s.charCodeAt(i);
+    if (DROP.has(c)) continue;
+    if (/\s/.test(s[i])) {
+      if (!lastSpace) push(" ", i);
+      lastSpace = true;
+      continue;
+    }
+    lastSpace = false;
+    if (NASALS.has(c)) {
+      const h = next(i);
+      if (s.charCodeAt(h) === HALANT) {
+        const k = next(h);
+        if (k < s.length && isConsonant(s.charCodeAt(k))) {
+          push("\u0902", i);
+          i = h;
+          continue;
+        }
+      }
+    }
+    if (FOLD[c] !== void 0) c = FOLD[c];
+    if (opts.loose && LOOSE[c] !== void 0) c = LOOSE[c];
+    if (digits && c >= 2406 && c <= 2415) c = 48 + (c - 2406);
+    if (c >= 55296 && c <= 56319 && i + 1 < s.length) {
+      push(s[i], i);
+      push(s[i + 1], i + 1);
+      i++;
+      continue;
+    }
+    push(String.fromCharCode(c), i);
+  }
+  return { text: out.join(""), map };
+}
+function normaliseNe(text, opts = {}) {
+  return mapNormalise(text, opts).text;
+}
+var normalizeNe = normaliseNe;
+var POSTPOSITIONS = [
+  "\u092E\u093E",
+  "\u092E\u0948",
+  "\u0915\u094B",
+  "\u0915\u093E",
+  "\u0915\u0940",
+  "\u0915\u0947",
+  "\u0915\u0948",
+  "\u0932\u0947",
+  "\u0932\u093E\u0908",
+  "\u092C\u093E\u091F",
+  "\u092C\u093E\u091F\u0948",
+  "\u0938\u0901\u0917",
+  "\u0938\u0902\u0917",
+  "\u0938\u093F\u0924",
+  "\u0926\u0947\u0916\u093F",
+  "\u0926\u0947\u0916\u093F\u0928\u0948",
+  "\u0938\u092E\u094D\u092E",
+  "\u0938\u092E\u094D\u092E\u0948",
+  "\u0924\u093F\u0930",
+  "\u0924\u0930\u094D\u092B",
+  "\u092D\u093F\u0924\u094D\u0930",
+  "\u092C\u093E\u0939\u093F\u0930",
+  "\u092E\u093E\u0925\u093F",
+  "\u092E\u0941\u0928\u093F",
+  "\u0928\u091C\u093F\u0915",
+  "\u092A\u091B\u093F",
+  "\u0905\u0918\u093F",
+  "\u0905\u0917\u093E\u0921\u093F",
+  "\u092A\u093E\u0930\u093F",
+  "\u0935\u093E\u0930\u093F",
+  "\u0926\u094D\u0935\u093E\u0930\u093E",
+  "\u0939\u0930\u0942",
+  "\u0939\u0930\u0941",
+  "\u0928\u0948",
+  "\u092D\u0930",
+  "\u092D\u0930\u093F",
+  "\u0935\u093E\u0938\u0940",
+  "\u092C\u093E\u0938\u0940",
+  "\u0938\u094D\u0925\u093F\u0924",
+  "\u0928\u093F\u0935\u093E\u0938\u0940"
+];
+var isNeLetter = (c) => c >= 2304 && c <= 2403 || c >= 2417 && c <= 2431;
+var isWordChar = (ch) => !!ch && /[\p{L}\p{M}\p{N}]/u.test(ch);
+var hasDevanagari = (s) => /[ऀ-ॿ]/.test(s);
+var escapeRe = (s) => s.replace(/[.*+?^${}()|[\]\\]/g, "\\$&");
+function autoCase(term) {
+  const letters = term.replace(/[^\p{L}]/gu, "");
+  return letters.length >= 2 && letters.length <= 5 && letters === letters.toUpperCase() && letters !== letters.toLowerCase();
+}
+function createMatcher(terms, opts = {}) {
+  const nopts = { loose: opts.loose, digits: opts.digits };
+  const suffixes = opts.postpositions === false ? [] : [...new Set([...POSTPOSITIONS, ...opts.extraSuffixes ?? []].map((s) => normaliseNe(s, nopts)))].sort((a, b) => b.length - a.length);
+  const variants = [];
+  for (const t of terms) {
+    const obj = typeof t === "string" ? { id: t, aliases: [t] } : t;
+    const list = (v) => v === void 0 ? [] : typeof v === "string" ? [v] : [...v];
+    const spellings = [...list(obj.en), ...list(obj.ne), ...obj.aliases ?? []].map((s) => s.trim()).filter(Boolean);
+    const id = obj.id ?? spellings[0] ?? "";
+    for (const sp of new Set(spellings)) {
+      if (hasDevanagari(sp)) {
+        variants.push({ id, term: sp, lang: "ne", key: normaliseNe(sp, nopts) });
+      } else {
+        const rule = obj.caseSensitive ?? opts.caseSensitive ?? "auto";
+        const exact = rule === "auto" ? autoCase(sp) : rule;
+        const body = sp.split(/\s+/).map(escapeRe).join("\\s+");
+        variants.push({ id, term: sp, lang: "en", key: sp, re: new RegExp(body, exact ? "gu" : "giu") });
+      }
+    }
+  }
+  const suffixEnd = (s, pos, depth) => {
+    if (pos >= s.length || !isNeLetter(s.charCodeAt(pos))) return pos;
+    if (depth >= 3) return -1;
+    for (const suf of suffixes) {
+      if (s.startsWith(suf, pos)) {
+        const e = suffixEnd(s, pos + suf.length, depth + 1);
+        if (e >= 0) return e;
+      }
+    }
+    return -1;
+  };
+  const find = (text) => {
+    const { text: n, map } = mapNormalise(text, nopts);
+    const toOrig = (i) => i >= map.length ? text.normalize("NFC").length : map[i];
+    const nfc = text.normalize("NFC");
+    const found = [];
+    for (const v of variants) {
+      if (v.lang === "ne") {
+        if (!v.key) continue;
+        let at = n.indexOf(v.key);
+        while (at >= 0) {
+          const before = n[at - 1];
+          if (!isWordChar(before)) {
+            const wordEnd = at + v.key.length;
+            const end = suffixEnd(n, wordEnd, 0);
+            const after = n[end];
+            if (end >= 0 && !isWordChar(after)) {
+              const s = toOrig(at);
+              const e = end >= n.length ? nfc.length : toOrig(end);
+              found.push({ id: v.id, term: v.term, lang: "ne", index: s, end: e, text: nfc.slice(s, e), ...end > wordEnd ? { suffix: n.slice(wordEnd, end) } : {} });
+            }
+          }
+          at = n.indexOf(v.key, at + 1);
+        }
+      } else {
+        v.re.lastIndex = 0;
+        for (const m of n.matchAll(v.re)) {
+          const at = m.index;
+          const end = at + m[0].length;
+          if (isWordChar(n[at - 1]) || isWordChar(n[end])) continue;
+          const s = toOrig(at);
+          const e = end >= n.length ? nfc.length : toOrig(end);
+          found.push({ id: v.id, term: v.term, lang: "en", index: s, end: e, text: nfc.slice(s, e) });
+        }
+      }
+    }
+    found.sort((a, b) => a.index - b.index || b.end - a.end);
+    if (opts.overlaps) return found;
+    const kept = [];
+    let reach = -1;
+    for (const m of found) {
+      if (m.index >= reach) {
+        kept.push(m);
+        reach = m.end;
+      }
+    }
+    return kept;
+  };
+  return {
+    find,
+    test: (text, id) => find(text).some((m) => id === void 0 || m.id === id),
+    ids: (text) => [...new Set(find(text).map((m) => m.id))],
+    get size() {
+      return variants.length;
+    }
+  };
+}
+function findTerms(text, terms, opts) {
+  return createMatcher(Array.isArray(terms) ? terms : [terms], opts).find(text);
+}
+function contains(text, term, opts) {
+  return findTerms(text, term, opts).length > 0;
+}
+function splitSuffix(word) {
+  const { text: n, map } = mapNormalise(word.trim());
+  const sufs = [...new Set(POSTPOSITIONS.map((s) => normaliseNe(s)))].sort((a, b) => b.length - a.length);
+  const nfc = word.trim().normalize("NFC");
+  let end = n.length;
+  const out = [];
+  while (out.length < 3) {
+    const hit = sufs.find((s) => end - s.length >= 2 && n.slice(end - s.length, end) === s);
+    if (!hit) break;
+    out.unshift(hit);
+    end -= hit.length;
+  }
+  return { stem: nfc.slice(0, end >= n.length ? nfc.length : map[end]), suffixes: out };
+}
+var dottedAbbr = (s, i) => {
+  let j = i - 1;
+  while (j >= 0 && !/\s/.test(s[j])) j--;
+  return s.slice(j + 1, i).includes(".");
+};
+function sentenceSpans(text) {
+  const s = text.normalize("NFC");
+  const spans = [];
+  let start = 0;
+  for (let i = 0; i < s.length; i++) {
+    const ch = s[i];
+    const end = ch === "\u0964" || ch === "\u0965" || ch === "?" || ch === "!" || ch === "\n" || ch === "." && (i + 1 >= s.length || /\s/.test(s[i + 1])) && !dottedAbbr(s, i);
+    if (end) {
+      spans.push([start, i + 1]);
+      start = i + 1;
+    }
+  }
+  if (start < s.length) spans.push([start, s.length]);
+  return spans;
+}
+function near(text, a, b, maxCharsOrOpts = {}, sameSentence) {
+  const opts = typeof maxCharsOrOpts === "number" ? { maxChars: maxCharsOrOpts } : { ...maxCharsOrOpts };
+  if (sameSentence !== void 0) opts.sameSentence = sameSentence;
+  const max = opts.maxChars ?? 60;
+  const same = opts.sameSentence !== false;
+  const am = findTerms(text, a, opts);
+  const bm = findTerms(text, b, opts);
+  if (!am.length || !bm.length) return null;
+  const spans = same ? sentenceSpans(text) : [];
+  const sentenceOf = (i) => spans.findIndex(([s, e]) => i >= s && i < e);
+  let best = null;
+  for (const x of am) {
+    for (const y of bm) {
+      if (x.index < y.end && y.index < x.end) continue;
+      const gap = x.end <= y.index ? y.index - x.end : x.index - y.end;
+      if (gap > max) continue;
+      if (same && sentenceOf(x.index) !== sentenceOf(y.index)) continue;
+      if (!best || gap < best.gap) best = { a: x, b: y, gap };
+    }
+  }
+  return best;
+}
+
+exports.POSTPOSITIONS = POSTPOSITIONS;
+exports.VERSION = VERSION;
+exports.contains = contains;
+exports.createMatcher = createMatcher;
+exports.districtTerms = districtTerms;
+exports.findTerms = findTerms;
+exports.near = near;
+exports.normaliseNe = normaliseNe;
+exports.normalizeNe = normalizeNe;
+exports.sentenceSpans = sentenceSpans;
+exports.splitSuffix = splitSuffix;
+//# sourceMappingURL=index.cjs.map
+//# sourceMappingURL=index.cjs.map