Kokborok (Kókborok) Language Library for Python

Kokborok (Kókborok) is the first-ever comprehensive, standard-library-style Python NLP and linguistic preservation toolkit for Kokborok (Tripuri)—the official Sino-Tibetan / Bodo-Garo language of the state of Tripura in Northeast India.

Built with 500,000 quadri-lingual headwords (Kokborok-English-Hindi-Bengali), 180 classical and descriptive grammar rules and validation engine, dynamic generation of 1,600,000+ morphological inflections, complete cultural compendiums (attire, clans, cuisine, deities, folklore, geography, idioms, music, botany, wildlife, rituals, sacred sites, songs), Roman <-> Bengali script transliteration, semantic numeral classifiers, and audio synthesis.

🌟 Key Features

1. 500,000+ Quadri-lingual Dictionary: Curated and book-extracted vocabulary with definitions in Kokborok, English, Hindi, and Bengali, supporting unhyphenated fast lookup and morphological root fallbacks.
2. Classical Grammar Rules Engine (kokborok.grammar.rules): 180 classical grammar rules spanning phonology, nominal agreement, case postpositions, verbal TAM morphology, negation, valency/voice, syntax, and reduplication/expressives with automated clause diagnostics.
3. 1,600,000+ Morphological Inflections: Decomposes and generates verbal aspects (-kha, -nai, -tong, -ya, -liya, -yakhw, -glak), nominal case postpositions (-no, -ni, -o, -bai, -ni-simi, -ha, -sog, -hai), and adjectival prefixation (kw- / k-).
4. Comprehensive Cultural Heritage Subsystems:
   • Attire & Handloom: Rignai, Risa, Rikutu, Kamchwlwi, Takborok, Chamathwi Bar weaving motifs.
   • Clans & Tribes: 19 indigenous tribes and clans of Tripura (Debbarma, Reang/Bru, Jamatia, Noatia, Kalai, Murasing, Halam, Uchoi, Chakma, Mog, Garo, Lushai).
   • Cuisine: Berma, Chakhwi (zero-oil alkaline stew), Gudok, Mosdeng, Bangui, Mwkhwi, Wahan Mosdeng.
   • Deities: Subrai, Baba Garia, Mailuma, Khuluma, Tuibuma, Lampra, Ker, Chaturdasha Devata.
   • Folklore: Chethwang, Subrai creation of the hills, Haithathorani, Dumbur waterfall legend, Champaknagar lore.
   • Sacred Geography: Longtharai Hills, Jampui Hills, Baramura, Gomati River, Saidra (Howrah), Dumbur Lake, Unakoti, Neermahal, Ujjayanta Palace, Matabari.
   • Idioms & Sayings: Authentic Kokborok idioms and metaphors (Kok-Hajakma).
   • Music & Dance: Kham, Sumui, Sarinda, Chongpreng, Dangdu; Hojagiri dance, Garia dance, Lebang Boomani.
   • Botany & Wildlife: Muli bamboo (Melocanna baccifera), Muya shoots, Chundri herb; Phayre's leaf monkey, Green Imperial Pigeon, Hoolock gibbon, Clouded leopard.
   • Rituals & Sacred Sites: Ochai shamanic priesthood, Chukbar wedding, Risa Sormani rite of passage; Unakoti rock carvings, Tripura Sundari Matabari.
   • Folk Songs: Jaduni romantic hill ballads, Baba Garia processional chants, Hojagiri dance songs, lullabies.
5. Digitized Books & Whole-Book Literature Library (kokborok.books): 225 authentic, public-domain Kokborok books (32,995 pages, 9,229,226 words) digitized page-by-page from the Ministry of Tribal Affairs and DLI, with in-book and cross-book search.
6. Roman & Bengali Script Support: High-accuracy bidirectional transliteration between official Roman Kokborok orthography and Bengali-Assamese script.
7. Tone & Syllable Engine: High-tone pitch accent marking (á, é, í, ó, ú, ẃ), tone stripping, and syllable segmentation.
8. Numeral & Classifier System: 1 to 1,000,000 numerals with human (khorok-), animal (kwtwi-), long (gong-), flat (tai-), and plant (phang-) classifiers.
9. Universal Multi-Lingual Translation: Bidirectional translation across Kokborok, English, Hindi, and Bengali with dialect adaptation (Debbarma, Reang/Bru, Jamatia, Noatia).
10. Command-Line Interface (CLI): Full CLI (kokborok translate, lookup, num, culture, books, read, search-books, stats).

📦 Installation

pip install kokborok

Or install from source:

git clone https://github.com/infoakshatsinghbisht-eng/kokborok-language-Library.git
cd kokborok-language-Library
pip install -e .

🚀 Quick Start Guide

1. Classical Grammar Rules Engine

import kokborok

# Query all 180 classical grammar rules
rules = kokborok.grammar_rules()
print(f"Catalogued rules: {len(rules)}")

# Lookup a specific rule
r = kokborok.get_grammar_rules_engine().get("PHON-01")
print(r.name)         # "Close Back Unrounded Vowel Representation ('w')"
print(r.formula)      # "'w' -> /ɯ/ (unrounded close back vowel)"

# Perform automated grammatical clause validation
engine = kokborok.get_grammar_rules_engine()
diag = engine.validate_clause("Ang bo-no mai rwi-kha de?")
for item in diag["applicable_rules"]:
    print(f"- {item['rule']}: {item['note']}")

2. Comprehensive 500,000+ Dictionary & Search

# Exact or unhyphenated lookup
entry = kokborok.lookup("risa")
print(entry)
# {'kokborok': 'risa', 'english': 'handwoven upper bust wrap / stole', 'hindi': 'रीसा', 'bengali': 'রিসা'}

entry_derived = kokborok.lookup("swinai")
print(entry_derived["english"])  # "writer / author / one who writes"

# Search across English, Hindi, Bengali, or Kokborok
results = kokborok.search("bamboo")
print(f"Found {len(results)} matching vocabulary terms")

3. Cultural Heritage, Attire, Cuisine & Folklore

# Traditional Attire & Weaving Motifs
for g in kokborok.list_attire():
    print(f"{g['name']} ({g['gender']}): {g['english_name']}")

# Traditional Cuisine
chakhwi = kokborok.get_dish("chakhwi")
print(chakhwi["description"])

# Tripuri Clans
clans = kokborok.list_clans()
print(f"Total tribes and clans: {len(clans)}")

# Sacred Geography & Ancient Shrines
unakoti = kokborok.get_place("unakoti")
print(unakoti["description"])

# Idioms & Metaphors (Kok-Hajakma)
for idiom in kokborok.list_idioms()[:3]:
    print(f"'{idiom['idiom']}': {idiom['meaning']}")

4. Translation Across Dialects & Languages

# English -> Kokborok
res = kokborok.translate("How are you?")
print(res.text)  # "Nwng bahai tong?"

# Hindi -> Kokborok
res_hi = kokborok.translate("नमस्ते")
print(res_hi.text)  # "Khulumkha!"

# Bengali -> Kokborok
res_ben = kokborok.translate("ধন্যবাদ")
print(res_ben.text)  # "Hambai!"

5. Grammar & Verbal Conjugation

# Verb conjugation across tenses and aspects
print(kokborok.conjugate("thang", tense="past", subject="ang"))
# "ang thang-kha" (I went)

print(kokborok.conjugate("thang", tense="future", subject="bo"))
# "bo thang-nai" (He/She will go)

print(kokborok.conjugate("thang", tense="present", subject="bo", negative=True))
# "bo thang-ya" (He/She does not go)

# Causative and Reciprocal forms
print(kokborok.causative("thang"))    # "thang-ri" (cause to go)
print(kokborok.reciprocal("hamjak"))  # "hamjak-lai" (love each other)

# Noun case declensions with postpositions
print(kokborok.decline_noun("borok", "accusative"))  # "borok-no"
print(kokborok.decline_noun("nok", "genitive"))       # "nok-ni"
print(kokborok.pluralize("borok"))                   # "borok-rok"

6. Numerals & Semantic Classifiers

# Numbers to words
print(kokborok.num_to_words(1))    # "sa"
print(kokborok.num_to_words(25))   # "rwichi-ba"
print(kokborok.num_to_words(100))  # "ra-sa"

# Applying numeral classifiers
print(kokborok.apply_classifier(2, "khorok"))  # "khorok-nwi" (2 persons)
print(kokborok.apply_classifier(3, "gong"))    # "gong-tham" (3 long items/pens)
print(kokborok.apply_classifier(4, "tai"))     # "tai-brwi" (4 flat items/clothes)

7. Digitized Books & Literature Library

# Check digitized literature counts
print(kokborok.total_books())  # 225 books
print(f"{kokborok.total_pages():,} pages")  # 32,995 pages
print(f"{kokborok.total_words():,} words")  # 9,229,226 words

# Load and read a book page-by-page
book = kokborok.get_book("kokborok_swrongma")
print(f"{book.title} by {book.author}")
print("Page 1 snippet:", book.get_page(1)[:200])

# Search within book
matches = book.search("kokborok")
for m in matches[:2]:
    print(f"Page {m['page_number']}: {m['snippet']}")

# Cross-book search
results = kokborok.search_books("Tripura", max_results=3)
for r in results:
    print(f"[{r['book_title']} P.{r['page_number']}]: {r['snippet']}")

🖥️ Command-Line Interface (CLI)

# Check library stats
kokborok stats

# Translate
kokborok translate "Hello how are you?" --to kokborok

# Dictionary lookup
kokborok lookup "khulumkha"

# Convert numbers with classifiers
kokborok num 42 --classifier khorok

# Explore cultural topics
kokborok culture festivals
kokborok culture authors
kokborok culture kinship

# Read and search digitized literature
kokborok books
kokborok read kokborok_swrongma --page 1
kokborok search-books "Tripura"

👨‍💻 Author & Maintainer Profile

• Author: Akshat Singh Bisht
• Email: infoakshatsinghbisht@gmail.com
• Official Website: akshatsinghbisht.com
• GitHub: @infoakshatsinghbisht-eng
• LinkedIn: Akshat Singh Bisht on LinkedIn
• Amazon Author Profile: Akshat Singh Bisht on Amazon
• ResearchGate Profile: Akshat Bisht on ResearchGate

📜 License

This project is licensed under the MIT License — see the LICENSE file for full details.