@indodev/toolkit 0.1.5 → 0.3.0

package/dist/text/index.js

@@ -0,0 +1,1705 @@
+// src/text/constants.ts
+var LOWERCASE_WORDS = [
+  // Indonesian prepositions (kata depan)
+  "di",
+  "ke",
+  "dari",
+  "pada",
+  "dalam",
+  "untuk",
+  "dengan",
+  "oleh",
+  "kepada",
+  "terhadap",
+  "tentang",
+  "tanpa",
+  "hingga",
+  "sampai",
+  "sejak",
+  "menuju",
+  "melalui",
+  // Indonesian conjunctions (kata hubung)
+  "dan",
+  "atau",
+  "tetapi",
+  "namun",
+  "serta",
+  "maupun",
+  "melainkan",
+  "sedangkan",
+  // Indonesian articles/particles
+  "yang",
+  "sebagai",
+  "adalah",
+  "ialah",
+  "yaitu",
+  "bahwa",
+  "akan",
+  "telah",
+  "sudah",
+  "belum",
+  // English articles
+  "a",
+  "an",
+  "the",
+  // English conjunctions
+  "and",
+  "or",
+  "but",
+  "nor",
+  "for",
+  "yet",
+  "so",
+  "as",
+  // English prepositions (short ones, < 5 letters)
+  "at",
+  "by",
+  "in",
+  "of",
+  "on",
+  "to",
+  "up",
+  "via",
+  "per",
+  "off",
+  "out"
+  // English prepositions (5+ letters - optional, some style guides capitalize these)
+  // 'about',
+  // 'above',
+  // 'across',
+  // 'after',
+  // 'among',
+  // 'below',
+  // 'under',
+  // 'until',
+  // 'with',
+];
+var ACRONYMS = [
+  // Indonesian government & military
+  "DKI",
+  // Daerah Khusus Ibukota
+  "DIY",
+  // Daerah Istimewa Yogyakarta
+  "TNI",
+  // Tentara Nasional Indonesia
+  "POLRI",
+  // Kepolisian Republik Indonesia
+  "ABRI",
+  // Angkatan Bersenjata Republik Indonesia
+  "MPR",
+  // Majelis Permusyawaratan Rakyat
+  "DPR",
+  // Dewan Perwakilan Rakyat
+  "KPK",
+  // Komisi Pemberantasan Korupsi
+  "BIN",
+  // Badan Intelijen Negara
+  // Indonesian business entities
+  "PT",
+  // Perseroan Terbatas
+  "CV",
+  // Commanditaire Vennootschap
+  "UD",
+  // Usaha Dagang
+  "PD",
+  // Perusahaan Daerah
+  "Tbk",
+  // Terbuka (publicly traded)
+  "BUMN",
+  // Badan Usaha Milik Negara
+  "BUMD",
+  // Badan Usaha Milik Daerah
+  // Indonesian banks
+  "BCA",
+  // Bank Central Asia
+  "BRI",
+  // Bank Rakyat Indonesia
+  "BNI",
+  // Bank Negara Indonesia
+  "BTN",
+  // Bank Tabungan Negara
+  "BSI",
+  // Bank Syariah Indonesia
+  "BPD",
+  // Bank Pembangunan Daerah
+  // Indonesian government services
+  "KTP",
+  // Kartu Tanda Penduduk
+  "NIK",
+  // Nomor Induk Kependudukan
+  "NPWP",
+  // Nomor Pokok Wajib Pajak
+  "SIM",
+  // Surat Izin Mengemudi
+  "STNK",
+  // Surat Tanda Nomor Kendaraan
+  "BPJS",
+  // Badan Penyelenggara Jaminan Sosial
+  "KIS",
+  // Kartu Indonesia Sehat
+  "KIP",
+  // Kartu Indonesia Pintar
+  "PKH",
+  // Program Keluarga Harapan
+  // Indonesian utilities & infrastructure
+  "PLN",
+  // Perusahaan Listrik Negara
+  "PDAM",
+  // Perusahaan Daerah Air Minum
+  "PGN",
+  // Perusahaan Gas Negara
+  "KAI",
+  // Kereta Api Indonesia
+  "MRT",
+  // Mass Rapid Transit
+  "LRT",
+  // Light Rail Transit
+  // Indonesian taxes & fees
+  "PBB",
+  // Pajak Bumi dan Bangunan
+  "PPh",
+  // Pajak Penghasilan
+  "PPN",
+  // Pajak Pertambahan Nilai
+  "BPHTB",
+  // Bea Perolehan Hak atas Tanah dan Bangunan
+  // Indonesian education
+  "UI",
+  // Universitas Indonesia
+  "ITB",
+  // Institut Teknologi Bandung
+  "UGM",
+  // Universitas Gadjah Mada
+  "IPB",
+  // Institut Pertanian Bogor
+  "ITS",
+  // Institut Teknologi Sepuluh Nopember
+  "UNPAD",
+  // Universitas Padjadjaran
+  "UNDIP",
+  // Universitas Diponegoro
+  "UNAIR",
+  // Universitas Airlangga
+  "UNS",
+  // Universitas Sebelas Maret
+  // Indonesian degrees (gelar)
+  "S.Pd",
+  // Sarjana Pendidikan
+  "S.H",
+  // Sarjana Hukum
+  "S.E",
+  // Sarjana Ekonomi
+  "S.T",
+  // Sarjana Teknik
+  "S.Kom",
+  // Sarjana Komputer
+  "S.Si",
+  // Sarjana Sains
+  "S.Sos",
+  // Sarjana Sosial
+  "M.Pd",
+  // Magister Pendidikan
+  "M.M",
+  // Magister Manajemen
+  "M.T",
+  // Magister Teknik
+  "M.Kom",
+  // Magister Komputer
+  // Common services
+  "ATM",
+  // Automated Teller Machine
+  "POS",
+  // Point of Sale
+  "SMS",
+  // Short Message Service
+  "GPS",
+  // Global Positioning System
+  "WiFi",
+  // Wireless Fidelity (technically Wi-Fi)
+  "USB",
+  // Universal Serial Bus
+  "PIN",
+  // Personal Identification Number
+  "OTP",
+  // One Time Password
+  "QR",
+  // Quick Response
+  // Technology & IT
+  "IT",
+  // Information Technology
+  "AI",
+  // Artificial Intelligence
+  "ML",
+  // Machine Learning
+  "API",
+  // Application Programming Interface
+  "UI",
+  // User Interface (duplicate with Universitas Indonesia, context matters)
+  "UX",
+  // User Experience
+  "SEO",
+  // Search Engine Optimization
+  "SaaS",
+  // Software as a Service
+  "CRM",
+  // Customer Relationship Management
+  "ERP",
+  // Enterprise Resource Planning
+  // Business titles
+  "CEO",
+  // Chief Executive Officer
+  "CFO",
+  // Chief Financial Officer
+  "CTO",
+  // Chief Technology Officer
+  "COO",
+  // Chief Operating Officer
+  "CMO",
+  // Chief Marketing Officer
+  "HR",
+  // Human Resources
+  "PR",
+  // Public Relations
+  "VP",
+  // Vice President
+  "GM",
+  // General Manager
+  // International organizations
+  "UN",
+  // United Nations
+  "WHO",
+  // World Health Organization
+  "UNESCO",
+  // United Nations Educational, Scientific and Cultural Organization
+  "NATO",
+  // North Atlantic Treaty Organization
+  "ASEAN",
+  // Association of Southeast Asian Nations
+  "APEC",
+  // Asia-Pacific Economic Cooperation
+  "WTO",
+  // World Trade Organization
+  "IMF",
+  // International Monetary Fund
+  // Medical
+  "ICU",
+  // Intensive Care Unit
+  "ER",
+  // Emergency Room
+  "MRI",
+  // Magnetic Resonance Imaging
+  "CT",
+  // Computed Tomography
+  "DNA",
+  // Deoxyribonucleic Acid
+  "RNA",
+  // Ribonucleic Acid
+  "HIV",
+  // Human Immunodeficiency Virus
+  "AIDS",
+  // Acquired Immunodeficiency Syndrome
+  "COVID",
+  // Coronavirus Disease
+  // Measurements & units
+  "KM",
+  // Kilometer
+  "CM",
+  // Centimeter
+  "MM",
+  // Millimeter
+  "KG",
+  // Kilogram
+  "RPM",
+  // Revolutions Per Minute
+  "MPH",
+  // Miles Per Hour
+  "KPH",
+  // Kilometers Per Hour
+  // Finance
+  "IPO",
+  // Initial Public Offering
+  "ATM",
+  // Automated Teller Machine (duplicate)
+  "ROI",
+  // Return on Investment
+  "GDP",
+  // Gross Domestic Product
+  "VAT"
+  // Value Added Tax
+];
+var ABBREVIATIONS = {
+  // ========== Address Abbreviations ==========
+  "Jl.": "Jalan",
+  "Gg.": "Gang",
+  "No.": "Nomor",
+  "Kp.": "Kampung",
+  "Ds.": "Desa",
+  "Kel.": "Kelurahan",
+  "Kec.": "Kecamatan",
+  "Kab.": "Kabupaten",
+  Kota: "Kota",
+  "Prov.": "Provinsi",
+  "Prop.": "Provinsi",
+  "Rt.": "Rukun Tetangga",
+  "Rw.": "Rukun Warga",
+  Blok: "Blok",
+  "Komp.": "Kompleks",
+  Perumahan: "Perumahan",
+  "Perum.": "Perumahan",
+  // ========== Academic Titles ==========
+  "Dr.": "Doktor",
+  "Ir.": "Insinyur",
+  "Prof.": "Profesor",
+  "Drs.": "Doktorandus",
+  "Dra.": "Doktoranda",
+  // Bachelor degrees
+  "S.Pd.": "Sarjana Pendidikan",
+  "S.H.": "Sarjana Hukum",
+  "S.E.": "Sarjana Ekonomi",
+  "S.T.": "Sarjana Teknik",
+  "S.Kom.": "Sarjana Komputer",
+  "S.Si.": "Sarjana Sains",
+  "S.Sos.": "Sarjana Sosial",
+  "S.I.Kom.": "Sarjana Ilmu Komunikasi",
+  "S.S.": "Sarjana Sastra",
+  "S.Psi.": "Sarjana Psikologi",
+  "S.Farm.": "Sarjana Farmasi",
+  "S.Ked.": "Sarjana Kedokteran",
+  // Master degrees
+  "M.Sc.": "Master of Science",
+  "M.M.": "Magister Manajemen",
+  "M.Pd.": "Magister Pendidikan",
+  "M.T.": "Magister Teknik",
+  "M.Kom.": "Magister Komputer",
+  "M.Si.": "Magister Sains",
+  "M.H.": "Magister Hukum",
+  "M.A.": "Master of Arts",
+  MBA: "Master of Business Administration",
+  // ========== Honorifics ==========
+  "Bpk.": "Bapak",
+  Ibu: "Ibu",
+  "Sdr.": "Saudara",
+  "Sdri.": "Saudari",
+  "Yth.": "Yang Terhormat",
+  "H.": "Haji",
+  "Hj.": "Hajjah",
+  "Tn.": "Tuan",
+  "Ny.": "Nyonya",
+  "Nn.": "Nona",
+  // ========== Organizations ==========
+  "PT.": "Perseroan Terbatas",
+  "CV.": "Commanditaire Vennootschap",
+  "UD.": "Usaha Dagang",
+  "PD.": "Perusahaan Daerah",
+  "Tbk.": "Terbuka",
+  Koperasi: "Koperasi",
+  Yayasan: "Yayasan",
+  // ========== Common Abbreviations ==========
+  "dst.": "dan seterusnya",
+  "dsb.": "dan sebagainya",
+  "dll.": "dan lain-lain",
+  "dkk.": "dan kawan-kawan",
+  "a.n.": "atas nama",
+  "u.p.": "untuk perhatian",
+  "u.b.": "untuk beliau",
+  "c.q.": "casu quo",
+  "hlm.": "halaman",
+  "tgl.": "tanggal",
+  "bln.": "bulan",
+  "thn.": "tahun",
+  "ttd.": "tertanda",
+  // ========== Contact Information ==========
+  "Tlp.": "Telepon",
+  "Telp.": "Telepon",
+  "HP.": "Handphone",
+  Fax: "Faksimile",
+  Email: "Email",
+  Website: "Website",
+  // ========== Days (Indonesian) ==========
+  "Sen.": "Senin",
+  "Sel.": "Selasa",
+  "Rab.": "Rabu",
+  "Kam.": "Kamis",
+  "Jum.": "Jumat",
+  "Sab.": "Sabtu",
+  "Min.": "Minggu",
+  // ========== Months (Indonesian) ==========
+  "Jan.": "Januari",
+  "Feb.": "Februari",
+  "Mar.": "Maret",
+  "Apr.": "April",
+  Mei: "Mei",
+  "Jun.": "Juni",
+  "Jul.": "Juli",
+  "Agt.": "Agustus",
+  "Sep.": "September",
+  "Okt.": "Oktober",
+  "Nov.": "November",
+  "Des.": "Desember",
+  // ========== Units & Measurements ==========
+  "kg.": "kilogram",
+  "gr.": "gram",
+  "lt.": "liter",
+  "ml.": "mililiter",
+  "km.": "kilometer",
+  "cm.": "sentimeter",
+  "mm.": "milimeter",
+  "m2.": "meter persegi",
+  "m3.": "meter kubik",
+  "ha.": "hektar"
+};
+var PROFANITY = [
+  "anjing",
+  "babi",
+  "bangsat",
+  "bajingan",
+  "brengsek",
+  "goblok",
+  "tolol",
+  "idiot",
+  "perek",
+  "jablay",
+  "kontol",
+  "memek",
+  "ngewe",
+  "puki",
+  "jembut",
+  "asu",
+  "itil",
+  "lanjiao",
+  "pantek",
+  "anying",
+  "anjrit"
+];
+var STOPWORDS = [
+  "ada",
+  "adalah",
+  "adanya",
+  "adapun",
+  "agak",
+  "agaknya",
+  "agar",
+  "akan",
+  "akankah",
+  "akhir",
+  "akhiri",
+  "akhirnya",
+  "aku",
+  "akulah",
+  "amat",
+  "amatlah",
+  "anda",
+  "andalah",
+  "antar",
+  "antara",
+  "antaranya",
+  "apa",
+  "apaan",
+  "apabila",
+  "apakah",
+  "apalagi",
+  "apatah",
+  "artinya",
+  "asal",
+  "asalkan",
+  "atas",
+  "atau",
+  "ataukah",
+  "ataupun",
+  "awal",
+  "awalnya",
+  "bagai",
+  "bagaikan",
+  "bagaimana",
+  "bagaimanakah",
+  "bagaimanapun",
+  "bagi",
+  "bagian",
+  "bahkan",
+  "bahwa",
+  "bahwasanya",
+  "baik",
+  "bakal",
+  "bakalan",
+  "balik",
+  "banyak",
+  "bapak",
+  "baru",
+  "bawah",
+  "beberapa",
+  "begini",
+  "beginian",
+  "beginikah",
+  "beginilah",
+  "begitu",
+  "begitukah",
+  "begitulah",
+  "begitupun",
+  "bekerja",
+  "belakang",
+  "belakangan",
+  "belum",
+  "belumlah",
+  "benar",
+  "benarkah",
+  "benarlah",
+  "berada",
+  "berakhir",
+  "berakhirlah",
+  "berakhirnya",
+  "berapa",
+  "berapakah",
+  "berapalah",
+  "berapapun",
+  "berarti",
+  "berawal",
+  "berbagai",
+  "berikut",
+  "berikutnya",
+  "berjumlah",
+  "berkali-kali",
+  "berkata",
+  "berkeinginan",
+  "berkenaan",
+  "berlainan",
+  "berlalu",
+  "berlangsung",
+  "berlebihan",
+  "bermacam",
+  "bermacam-macam",
+  "bermaksud",
+  "bermula",
+  "bersama",
+  "bersama-sama",
+  "bersiap",
+  "bersiap-siap",
+  "bertanya",
+  "bertanya-tanya",
+  "berturut",
+  "berturut-turut",
+  "bertutur",
+  "berujar",
+  "berupa",
+  "besar",
+  "betul",
+  "betulkah",
+  "biasa",
+  "biasanya",
+  "bila",
+  "bilakah",
+  "bisa",
+  "bisakah",
+  "boleh",
+  "bolehkah",
+  "bolehlah",
+  "buat",
+  "bukan",
+  "bukankah",
+  "bukanlah",
+  "bukannya",
+  "bulan",
+  "bung",
+  "cara",
+  "caranya",
+  "cukup",
+  "cukupkah",
+  "cukuplah",
+  "cuma",
+  "dahulu",
+  "dalam",
+  "dan",
+  "dapat",
+  "dari",
+  "daripada",
+  "datang",
+  "dekat",
+  "demi",
+  "demikian",
+  "demikianlah",
+  "dengan",
+  "depan",
+  "di",
+  "dia",
+  "diakhiri",
+  "diakhirinya",
+  "dialah",
+  "diantara",
+  "diantaranya",
+  "diberi",
+  "diberikan",
+  "diberikannya",
+  "dibuat",
+  "dibuatnya",
+  "didapat",
+  "didatangkan",
+  "digunakan",
+  "diibaratkan",
+  "diingat",
+  "diingatkan",
+  "diinginkan",
+  "dijawab",
+  "dijelaskan",
+  "dijelaskannya",
+  "dikarenakan",
+  "dikatakan",
+  "dikatakannya",
+  "dikerjakan",
+  "diketahui",
+  "diketahuinya",
+  "dikira",
+  "dilakukan",
+  "dilalui",
+  "dilihat",
+  "dimaksud",
+  "dimaksudkan",
+  "dimaksudkannya",
+  "dimana",
+  "dimanalah",
+  "dimulai",
+  "dimulailah",
+  "dimulainya",
+  "diminta",
+  "dimintai",
+  "dimisalkan",
+  "dimungkinkan",
+  "dini",
+  "dipastikan",
+  "diperbuat",
+  "diperbuatnya",
+  "dipergunakan",
+  "diperkirakan",
+  "diperlihatkan",
+  "diperlukan",
+  "diperlukannya",
+  "dipersoalkan",
+  "dipertanyakan",
+  "dipunyai",
+  "diri",
+  "dirinya",
+  "disampaikan",
+  "disebut",
+  "disebutkan",
+  "disebutkannya",
+  "disini",
+  "disinilah",
+  "disitulah",
+  "diterangkan",
+  "diterangkannya",
+  "diteruskan",
+  "ditujukan",
+  "ditunjuk",
+  "ditunjuki",
+  "ditunjukkan",
+  "ditunjukkannya",
+  "ditunjuknya",
+  "dituturkan",
+  "dituturkannya",
+  "diucapkan",
+  "diucapkannya",
+  "diungkapkan",
+  "dua",
+  "dulu",
+  "empat",
+  "enggak",
+  "enggaknya",
+  "entah",
+  "entahlah",
+  "guna",
+  "gunakan",
+  "hal",
+  "hampir",
+  "hanya",
+  "hanyalah",
+  "hari",
+  "harus",
+  "haruslah",
+  "harusnya",
+  "hendak",
+  "hendaklah",
+  "hendaknya",
+  "hingga",
+  "ia",
+  "ialah",
+  "ibarat",
+  "ibaratkan",
+  "ibaratnya",
+  "ibu",
+  "ikut",
+  "ingat",
+  "ingat-ingat",
+  "ingin",
+  "inginkah",
+  "inginkan",
+  "ini",
+  "inikah",
+  "inilah",
+  "itu",
+  "itukah",
+  "itulah",
+  "jadi",
+  "jadilah",
+  "jadinya",
+  "jangan",
+  "jangankan",
+  "janganlah",
+  "jauh",
+  "jawab",
+  "jawaban",
+  "jawabnya",
+  "jelas",
+  "jelaskan",
+  "jelaslah",
+  "jelasnya",
+  "jika",
+  "jikalau",
+  "juga",
+  "jumlah",
+  "jumlahnya",
+  "justru",
+  "kala",
+  "kalau",
+  "kalaulah",
+  "kalaupun",
+  "kali",
+  "kalian",
+  "kami",
+  "kamilah",
+  "kamu",
+  "kamulah",
+  "kan",
+  "kapan",
+  "kapankah",
+  "kapanpun",
+  "karena",
+  "karenanya",
+  "ke",
+  "keadaan",
+  "kebetulan",
+  "kecil",
+  "kedua",
+  "keduanya",
+  "keinginan",
+  "kelak",
+  "kelihatan",
+  "kelihatannya",
+  "kelima",
+  "keluar",
+  "kembali",
+  "kemudian",
+  "kemungkinan",
+  "kemungkinannya",
+  "kenapa",
+  "kepada",
+  "kepadanya",
+  "kesampaian",
+  "keseluruhan",
+  "keseluruhannya",
+  "keterlaluan",
+  "ketika",
+  "khususnya",
+  "kini",
+  "kinilah",
+  "kira",
+  "kira-kira",
+  "kiranya",
+  "kita",
+  "kitalah",
+  "kok",
+  "kurang",
+  "lagi",
+  "lagian",
+  "lah",
+  "lain",
+  "lainnya",
+  "lalu",
+  "lama",
+  "lamanya",
+  "lanjut",
+  "lanjutnya",
+  "lebih",
+  "lewat",
+  "luar",
+  "macam",
+  "maka",
+  "makanya",
+  "makin",
+  "malah",
+  "malahan",
+  "mampu",
+  "mampukah",
+  "mana",
+  "manakala",
+  "manalagi",
+  "masih",
+  "masihkah",
+  "masing",
+  "masing-masing",
+  "mau",
+  "maupun",
+  "melainkan",
+  "melakukan",
+  "melalui",
+  "melihat",
+  "melihatnya",
+  "memang",
+  "memastikan",
+  "memberi",
+  "memberikan",
+  "membuat",
+  "memerlukan",
+  "memihak",
+  "meminta",
+  "memisalkan",
+  "memperbuat",
+  "mempergunakan",
+  "memperkirakan",
+  "memperlihatkan",
+  "mempersiapkan",
+  "mempersoalkan",
+  "mempertanyakan",
+  "mempunyai",
+  "memulai",
+  "memungkinkan",
+  "memutuskan",
+  "menanti",
+  "menanti-nanti",
+  "menantikan",
+  "menunjuk",
+  "menunjuknya",
+  "menuju",
+  "menurut",
+  "menurutnya",
+  "menurutmu",
+  "menurutku",
+  "menurutnya",
+  "menurut mereka",
+  "menyampaikan",
+  "menyebut",
+  "menyebutkan",
+  "menjelaskan",
+  "menjadi",
+  "menjadikan",
+  "menjalani",
+  "menjelang",
+  "menjawab",
+  "menunjukkan",
+  "menuangkan",
+  "menulis",
+  "menyatakan",
+  "merupakan",
+  "mereka",
+  "merekalah",
+  "meski",
+  "meskipun",
+  "mula",
+  "mulai",
+  "mulailah",
+  "mulanya",
+  "mungkin",
+  "mungkinkah",
+  "nah",
+  "naik",
+  "namun",
+  "nanti",
+  "nantinya",
+  "nyaris",
+  "oleh",
+  "olehnya",
+  "orang",
+  "pada",
+  "padahal",
+  "padanya",
+  "pakai",
+  "paling",
+  "panjang",
+  "pantas",
+  "para",
+  "pasti",
+  "pastilah",
+  "pagi",
+  "per",
+  "pernah",
+  "persoalan",
+  "pertama",
+  "pertama-tama",
+  "perlu",
+  "perlukah",
+  "perlulah",
+  "pernah",
+  "pihak",
+  "pihaknya",
+  "pukul",
+  "pula",
+  "pun",
+  "punya",
+  "rasa",
+  "rasanya",
+  "rata",
+  "rupanya",
+  "saat",
+  "saatnya",
+  "saja",
+  "sajalah",
+  "salam",
+  "saling",
+  "sama",
+  "sama-sama",
+  "sambil",
+  "sampai",
+  "sampai-sampai",
+  "sampaikan",
+  "sana",
+  "sangat",
+  "sangatlah",
+  "satu",
+  "saya",
+  "sayalah",
+  "sayang",
+  "seperti",
+  "seperti-itu",
+  "sepura",
+  "sebab",
+  "sebabnya",
+  "sebagai",
+  "sebagaimana",
+  "sebagainya",
+  "sebagian",
+  "sebaik",
+  "sebaik-baiknya",
+  "sebaiknya",
+  "sebaliknya",
+  "sebanyak",
+  "sebegini",
+  "sebegitu",
+  "sebelum",
+  "sebelumnya",
+  "sebenarnya",
+  "seberapa",
+  "sebesar",
+  "sebetulnya",
+  "sebisanya",
+  "sebuah",
+  "sebut",
+  "sebutkan",
+  "sebutnya",
+  "secara",
+  "secukupnya",
+  "sedang",
+  "sedangkan",
+  "sedikit",
+  "sedikitnya",
+  "sedemikian",
+  "sediakala",
+  "sedikit",
+  "sedikitnya",
+  "segala",
+  "segalanya",
+  "segera",
+  "seharusnya",
+  "sehingga",
+  "seingat",
+  "sejak",
+  "sejauh",
+  "sejenak",
+  "sejumlah",
+  "sekali",
+  "sekali-kali",
+  "sekalian",
+  "sekaligus",
+  "sekalipun",
+  "sekarang",
+  "sekaranglah",
+  "sekecil",
+  "seketika",
+  "sekiranya",
+  "sekitar",
+  "sekitarnya",
+  "sekurang",
+  "sekurangnya",
+  "sela",
+  "selalu",
+  "selama",
+  "selama-lamanya",
+  "selamanya",
+  "selanjutnya",
+  "seluruh",
+  "seluruhnya",
+  "semacam",
+  "semakin",
+  "semampu",
+  "semampunya",
+  "semasa",
+  "semata",
+  "semata-mata",
+  "semaunya",
+  "sementara",
+  "semisal",
+  "semisalnya",
+  "sempat",
+  "semua",
+  "semuanya",
+  "semula",
+  "sendiri",
+  "sendirinya",
+  "seolah",
+  "seolah-olah",
+  "seorang",
+  "sepanjang",
+  "sepantasnya",
+  "sepantasnyalah",
+  "seperempat",
+  "seperti",
+  "sepertinya",
+  "sepihak",
+  "sepuluh",
+  "seratus",
+  "seribu",
+  "sering",
+  "seringnya",
+  "serta",
+  "serupa",
+  "sesaat",
+  "sesama",
+  "sesampai",
+  "sesampainya",
+  "sesegera",
+  "sesekali",
+  "seseorang",
+  "sesuatu",
+  "sesuatunya",
+  "sesudah",
+  "sesudahnya",
+  "setelah",
+  "setempat",
+  "setengah",
+  "seterusnya",
+  "setiap",
+  "setidaknya",
+  "setinggi",
+  "seusai",
+  "sewaktu",
+  "siap",
+  "siapa",
+  "siapakah",
+  "siapapun",
+  "sini",
+  "sinilah",
+  "situ",
+  "situlah",
+  "suatu",
+  "sudah",
+  "sudahkah",
+  "sudahlah",
+  "supaya",
+  "tadi",
+  "tadinya",
+  "tahu",
+  "tak",
+  "tambah",
+  "tambahnya",
+  "tampak",
+  "tampaknya",
+  "tandas",
+  "tandasnya",
+  "tanpa",
+  "tanya",
+  "tanyakan",
+  "tanyanya",
+  "tapi",
+  "tegas",
+  "tegasnya",
+  "telah",
+  "tempat",
+  "tengah",
+  "tentang",
+  "tentu",
+  "tentulah",
+  "tentunya",
+  "tepat",
+  "terakhir",
+  "terasa",
+  "terbanyak",
+  "terdahulu",
+  "terdapat",
+  "terdiri",
+  "terdiri-dari",
+  "terhadap",
+  "terhadapnya",
+  "teringat",
+  "teringat-ingat",
+  "terjadi",
+  "terjadilah",
+  "terjadinya",
+  "terkira",
+  "terlalu",
+  "terlebih",
+  "terlihat",
+  "termasuk",
+  "ternyata",
+  "tersampaikan",
+  "tersebut",
+  "tersebutlah",
+  "tertentu",
+  "tertuju",
+  "terus",
+  "terutama",
+  "tetap",
+  "tetapi",
+  "tiap",
+  "tiba",
+  "tiba-tiba",
+  "tidak",
+  "tidakkah",
+  "tidaklah",
+  "tiga",
+  "tadi",
+  "tadinya",
+  "tinggi",
+  "toh",
+  "tuju",
+  "tunjuk",
+  "turut",
+  "tutur",
+  "tuturnya",
+  "ucap",
+  "ucapnya",
+  "ujar",
+  "ujarnya",
+  "umumnya",
+  "ungkap",
+  "ungkapnya",
+  "untuk",
+  "untaian",
+  "usai",
+  "usah",
+  "waduh",
+  "wah",
+  "wahai",
+  "walau",
+  "walaupun",
+  "wong",
+  "yaitu",
+  "yakin",
+  "yakni",
+  "yang"
+];
+
+// src/text/capitalization.ts
+function capitalize(text) {
+  if (!text) return text;
+  return text.charAt(0).toUpperCase() + text.slice(1).toLowerCase();
+}
+function toTitleCase(text, options) {
+  if (!text) return text;
+  const {
+    preserveAcronyms = true,
+    strict = false,
+    exceptions = []
+  } = options || {};
+  const lowercaseSet = /* @__PURE__ */ new Set([...LOWERCASE_WORDS, ...exceptions]);
+  const acronymSet = new Set(ACRONYMS);
+  const normalized = normalizeSpaces(text);
+  const words = normalized.split(" ");
+  return words.map((word, index) => {
+    if (!word) return word;
+    if (word.includes("-")) {
+      return processHyphenatedWord(word, index === 0, {
+        lowercaseSet,
+        acronymSet,
+        preserveAcronyms,
+        strict
+      });
+    }
+    return processWord(word, index === 0, {
+      lowercaseSet,
+      acronymSet,
+      preserveAcronyms,
+      strict
+    });
+  }).join(" ");
+}
+function normalizeSpaces(text) {
+  return text.trim().replace(/\s+/g, " ");
+}
+function processWord(word, isFirstWord, context) {
+  const { lowercaseSet, acronymSet, preserveAcronyms, strict } = context;
+  const lowerWord = word.toLowerCase();
+  const upperWord = word.toUpperCase();
+  if (preserveAcronyms && acronymSet.has(upperWord)) {
+    return upperWord;
+  }
+  if (!isFirstWord && lowercaseSet.has(lowerWord)) {
+    return lowerWord;
+  }
+  if (strict) {
+    return capitalizeFirstLetter(lowerWord);
+  }
+  return capitalizeFirstLetter(word.toLowerCase());
+}
+function processHyphenatedWord(word, isFirstWord, context) {
+  return word.split("-").map(
+    (part, index) => processWord(part, isFirstWord && index === 0, context)
+  ).join("-");
+}
+function capitalizeFirstLetter(word) {
+  if (!word) return word;
+  return word.charAt(0).toUpperCase() + word.slice(1);
+}
+function toSentenceCase(text) {
+  if (!text) return text;
+  const normalized = text.trim().replace(/\s+/g, " ");
+  let result = "";
+  let shouldCapitalize = true;
+  for (let i = 0; i < normalized.length; i++) {
+    const char = normalized[i];
+    if (shouldCapitalize && /[a-zA-ZÀ-ÿ]/.test(char)) {
+      result += char.toUpperCase();
+      shouldCapitalize = false;
+    } else {
+      result += char.toLowerCase();
+    }
+    if (isSentenceEnd(char)) {
+      shouldCapitalize = true;
+    }
+    if (char === "." && i + 1 < normalized.length) {
+      const nextChar = normalized[i + 1];
+      if (nextChar !== " " && !/[.!?]/.test(nextChar)) {
+        shouldCapitalize = false;
+      }
+    }
+  }
+  return result;
+}
+function isSentenceEnd(char) {
+  return char === "." || char === "!" || char === "?";
+}
+
+// src/text/slug.ts
+function slugify(text, options) {
+  if (!text) return "";
+  const {
+    separator = "-",
+    lowercase = true,
+    replacements = {},
+    trim = true
+  } = options || {};
+  let result = text;
+  for (const [search, replace] of Object.entries(replacements)) {
+    result = result.replace(new RegExp(escapeRegex(search), "g"), replace);
+  }
+  result = result.replace(/&/g, " dan ");
+  result = result.replace(/\//g, " atau ");
+  if (lowercase) {
+    result = result.toLowerCase();
+  }
+  result = result.replace(/[.'@éèêëàâäôöûüùïîçñ™®©]/g, "");
+  result = result.replace(/[^\w\s-]+/g, separator);
+  result = result.replace(/\s+/g, separator);
+  if (separator !== "-") {
+    result = result.replace(/-/g, separator);
+  }
+  if (trim) {
+    const separatorRegex = new RegExp(`\\${separator}+`, "g");
+    result = result.replace(separatorRegex, separator);
+    const trimRegex = new RegExp(`^\\${separator}+|\\${separator}+$`, "g");
+    result = result.replace(trimRegex, "");
+  }
+  return result;
+}
+function escapeRegex(str) {
+  return str.replace(/[.*+?^${}()|[\]\\]/g, "\\$&");
+}
+
+// src/text/sanitize.ts
+function normalizeWhitespace(text) {
+  if (!text) return text;
+  return text.trim().replace(/\s+/g, " ");
+}
+function sanitize(text, options) {
+  if (!text) return text;
+  const {
+    removeNewlines = false,
+    removeExtraSpaces = true,
+    removePunctuation = false,
+    allowedChars,
+    trim = true
+  } = options || {};
+  let result = text;
+  if (removeNewlines) {
+    result = result.replace(/[\n\r]/g, " ");
+  }
+  if (removePunctuation) {
+    result = result.replace(/[!"#$%&'()*+,\-./:;<=>?@[\\\]^_`{|}~]/g, "");
+  }
+  if (allowedChars) {
+    const allowedRegex = new RegExp(`[^${allowedChars}]`, "g");
+    result = result.replace(allowedRegex, "");
+  }
+  if (removeExtraSpaces) {
+    if (trim) {
+      if (removeNewlines) {
+        result = result.replace(/\s+/g, " ");
+      } else {
+        result = result.replace(/[ \t]+/g, " ");
+      }
+    } else {
+      const leadingMatch = result.match(/^([ \t]*)/);
+      const trailingMatch = result.match(/([ \t]*)$/);
+      const leading = leadingMatch ? leadingMatch[1] : "";
+      const trailing = trailingMatch ? trailingMatch[1] : "";
+      const middle = result.slice(
+        leading.length,
+        result.length - trailing.length
+      );
+      const normalizedMiddle = removeNewlines ? middle.replace(/\s+/g, " ") : middle.replace(/[ \t]+/g, " ");
+      result = leading + normalizedMiddle + trailing;
+    }
+  }
+  if (trim) {
+    result = result.trim();
+  }
+  return result;
+}
+function removeAccents(text) {
+  if (!text) return text;
+  const specialChars = {
+    \u00D8: "O",
+    \u00F8: "o",
+    \u00C6: "AE",
+    \u00E6: "ae",
+    \u00C5: "A",
+    \u00E5: "a",
+    \u0110: "D",
+    \u0111: "d",
+    \u0141: "L",
+    \u0142: "l",
+    \u00DE: "TH",
+    \u00FE: "th",
+    \u00DF: "ss"
+  };
+  let result = text;
+  for (const [accented, plain] of Object.entries(specialChars)) {
+    result = result.replace(new RegExp(accented, "g"), plain);
+  }
+  return result.normalize("NFD").replace(/[\u0300-\u036f]/g, "");
+}
+
+// src/text/abbreviation.ts
+function expandAbbreviation(text, options) {
+  if (!text) return text;
+  const { mode = "all", customMap = {}, preserveCase = false } = options || {};
+  const abbreviationsMap = {
+    ...getAbbreviationsByMode(mode),
+    ...customMap
+  };
+  let result = text;
+  const sortedAbbrevs = Object.keys(abbreviationsMap).sort(
+    (a, b) => b.length - a.length
+  );
+  for (const abbrev of sortedAbbrevs) {
+    const expansion = abbreviationsMap[abbrev];
+    const startBoundary = /^\w/.test(abbrev) ? "\\b" : "";
+    const endBoundary = /\w$/.test(abbrev) ? "\\b" : "";
+    const regex = new RegExp(
+      `${startBoundary}${escapeRegex2(abbrev)}${endBoundary}`,
+      "gi"
+    );
+    result = result.replace(regex, (match) => {
+      if (!preserveCase) {
+        return expansion;
+      }
+      return matchCase(match, expansion);
+    });
+  }
+  return result;
+}
+function getAbbreviationsByMode(mode) {
+  if (mode === "all") {
+    return ABBREVIATIONS;
+  }
+  const filtered = {};
+  const addressAbbrevs = [
+    "Jl.",
+    "Gg.",
+    "No.",
+    "Kp.",
+    "Ds.",
+    "Kel.",
+    "Kec.",
+    "Kab.",
+    "Kota",
+    "Prov.",
+    "Prop.",
+    "Rt.",
+    "Rw.",
+    "Blok",
+    "Komp.",
+    "Perumahan",
+    "Perum."
+  ];
+  const titleAbbrevs = [
+    "Dr.",
+    "Ir.",
+    "Prof.",
+    "Drs.",
+    "Dra.",
+    "S.Pd.",
+    "S.H.",
+    "S.E.",
+    "S.T.",
+    "S.Kom.",
+    "S.Si.",
+    "S.Sos.",
+    "S.I.Kom.",
+    "S.S.",
+    "S.Psi.",
+    "S.Farm.",
+    "S.Ked.",
+    "M.Sc.",
+    "M.M.",
+    "M.Pd.",
+    "M.T.",
+    "M.Kom.",
+    "M.Si.",
+    "M.H.",
+    "M.A.",
+    "MBA"
+  ];
+  const orgAbbrevs = [
+    "PT.",
+    "CV.",
+    "UD.",
+    "PD.",
+    "Tbk.",
+    "Koperasi",
+    "Yayasan"
+  ];
+  for (const [abbrev, expansion] of Object.entries(ABBREVIATIONS)) {
+    if (mode === "address" && addressAbbrevs.includes(abbrev)) {
+      filtered[abbrev] = expansion;
+    } else if (mode === "title" && titleAbbrevs.includes(abbrev)) {
+      filtered[abbrev] = expansion;
+    } else if (mode === "org" && orgAbbrevs.includes(abbrev)) {
+      filtered[abbrev] = expansion;
+    }
+  }
+  return filtered;
+}
+function escapeRegex2(str) {
+  return str.replace(/[.*+?^${}()|[\]\\]/g, "\\$&");
+}
+function matchCase(original, replacement) {
+  if (original === original.toUpperCase()) {
+    return replacement.toUpperCase();
+  }
+  if (original === original.toLowerCase()) {
+    return replacement.toLowerCase();
+  }
+  if (original.charAt(0) === original.charAt(0).toUpperCase()) {
+    return replacement.charAt(0).toUpperCase() + replacement.slice(1).toLowerCase();
+  }
+  return replacement;
+}
+function contractAbbreviation(text, options) {
+  if (!text) return text;
+  const { mode = "all" } = options || {};
+  const abbreviationsMap = getAbbreviationsByMode(mode);
+  const reverseMap = {};
+  for (const [abbrev, expansion] of Object.entries(abbreviationsMap)) {
+    reverseMap[expansion] = abbrev;
+  }
+  let result = text;
+  const sortedExpansions = Object.keys(reverseMap).sort(
+    (a, b) => b.length - a.length
+  );
+  for (const expansion of sortedExpansions) {
+    const abbrev = reverseMap[expansion];
+    const regex = new RegExp(`\\b${escapeRegex2(expansion)}\\b`, "gi");
+    result = result.replace(regex, abbrev);
+  }
+  return result;
+}
+
+// src/text/filter.ts
+function profanityFilter(text, mask = "*") {
+  let filtered = text;
+  PROFANITY.forEach((word) => {
+    const regex = new RegExp(`\\b${word}\\b`, "gi");
+    filtered = filtered.replace(regex, mask.repeat(word.length));
+  });
+  return filtered;
+}
+function removeStopwords(text) {
+  const words = text.split(/\s+/);
+  const filtered = words.filter(
+    (word) => !STOPWORDS.includes(word.toLowerCase())
+  );
+  return filtered.join(" ");
+}
+
+// src/text/normalization.ts
+var INFORMAL_MAP = {
+  gw: "saya",
+  gua: "saya",
+  lu: "kamu",
+  lo: "kamu",
+  elo: "kamu",
+  lagi: "sedang",
+  gue: "saya",
+  gwe: "saya",
+  gak: "tidak",
+  ga: "tidak",
+  nggak: "tidak",
+  kalo: "kalau",
+  karna: "karena",
+  tapi: "tetapi",
+  udah: "sudah",
+  dah: "sudah",
+  aja: "saja",
+  banget: "sekali",
+  emang: "memang",
+  pake: "pakai",
+  bikin: "membuat",
+  kasih: "memberi",
+  dapet: "dapat",
+  liat: "lihat",
+  ngasih: "memberi",
+  nyari: "mencari",
+  nanya: "bertanya",
+  bilang: "berkata"
+};
+function toFormal(text) {
+  const words = text.split(/\s+/);
+  const formalized = words.map((word) => {
+    const lower = word.toLowerCase().replace(/[^\w]/g, "");
+    const formal = INFORMAL_MAP[lower];
+    if (formal) {
+      if (word[0] === word[0].toUpperCase()) {
+        return formal.charAt(0).toUpperCase() + formal.slice(1);
+      }
+      return formal;
+    }
+    return word;
+  });
+  return formalized.join(" ");
+}
+function isAlay(text) {
+  if (!text) return false;
+  const alternatingCaps = /([a-z][A-Z][a-z]|[A-Z][a-z][A-Z])/.test(text);
+  const numberSub = /\b\w*[0431572]\w*\b/.test(text);
+  const qSub = /q/i.test(text) && !/u/i.test(text);
+  const excessiveChars = /(.)\1{2,}/.test(text);
+  return alternatingCaps || numberSub || qSub || excessiveChars;
+}
+
+// src/text/extract.ts
+function truncate(text, maxLength, options) {
+  if (!text || maxLength <= 0) {
+    return "";
+  }
+  const { ellipsis = "...", wordBoundary = true } = options || {};
+  if (text.length <= maxLength) {
+    return text;
+  }
+  const availableLength = maxLength - ellipsis.length;
+  if (availableLength <= 0) {
+    return ellipsis.slice(0, maxLength);
+  }
+  let truncated = text.slice(0, availableLength);
+  if (wordBoundary) {
+    const lastSpaceIndex = truncated.lastIndexOf(" ");
+    if (lastSpaceIndex > 0) {
+      truncated = truncated.slice(0, lastSpaceIndex);
+    }
+  }
+  truncated = truncated.trimEnd();
+  return truncated + ellipsis;
+}
+function extractWords(text, options) {
+  if (!text || !text.trim()) {
+    return [];
+  }
+  const {
+    minLength = 0,
+    includeHyphenated = true,
+    lowercase = false
+  } = options || {};
+  let cleaned = text;
+  if (includeHyphenated) {
+    cleaned = text.replace(/[^\w\s-]/g, " ");
+  } else {
+    cleaned = text.replace(/[^\w\s]/g, " ");
+  }
+  const words = cleaned.split(/\s+/).map((word) => word.trim()).filter((word) => word.length > 0).filter((word) => !/^-+$/.test(word));
+  let result = words;
+  if (minLength > 0) {
+    result = result.filter((word) => word.length >= minLength);
+  }
+  if (lowercase) {
+    result = result.map((word) => word.toLowerCase());
+  }
+  return result;
+}
+
+// src/text/compare.ts
+function compareStrings(str1, str2, options) {
+  if (str1 === str2) {
+    return true;
+  }
+  const s1 = str1 || "";
+  const s2 = str2 || "";
+  const {
+    caseSensitive = false,
+    ignoreWhitespace = false,
+    ignoreAccents = false
+  } = options || {};
+  let normalized1 = s1;
+  let normalized2 = s2;
+  if (ignoreWhitespace) {
+    normalized1 = normalizeWhitespace(normalized1);
+    normalized2 = normalizeWhitespace(normalized2);
+  }
+  if (ignoreAccents) {
+    normalized1 = removeAccents(normalized1);
+    normalized2 = removeAccents(normalized2);
+  }
+  if (!caseSensitive) {
+    normalized1 = normalized1.toLowerCase();
+    normalized2 = normalized2.toLowerCase();
+  }
+  return normalized1 === normalized2;
+}
+function similarity(str1, str2) {
+  if (str1 === str2) return 1;
+  if (str1.length === 0) return str2.length === 0 ? 1 : 0;
+  if (str2.length === 0) return 0;
+  const len1 = str1.length;
+  const len2 = str2.length;
+  let prevRow = Array(len2 + 1).fill(0);
+  let currentRow = Array(len2 + 1).fill(0);
+  for (let j = 0; j <= len2; j++) {
+    prevRow[j] = j;
+  }
+  for (let i = 1; i <= len1; i++) {
+    currentRow[0] = i;
+    for (let j = 1; j <= len2; j++) {
+      const cost = str1[i - 1] === str2[j - 1] ? 0 : 1;
+      currentRow[j] = Math.min(
+        currentRow[j - 1] + 1,
+        // Insertion
+        prevRow[j] + 1,
+        // Deletion
+        prevRow[j - 1] + cost
+        // Substitution
+      );
+    }
+    [prevRow, currentRow] = [currentRow, prevRow];
+  }
+  const distance = prevRow[len2];
+  const maxLength = Math.max(len1, len2);
+  return 1 - distance / maxLength;
+}
+
+export { ABBREVIATIONS, ACRONYMS, LOWERCASE_WORDS, capitalize, compareStrings, contractAbbreviation, expandAbbreviation, extractWords, isAlay, normalizeWhitespace, profanityFilter, removeAccents, removeStopwords, sanitize, similarity, slugify, toFormal, toSentenceCase, toTitleCase, truncate };
+//# sourceMappingURL=index.js.map
+//# sourceMappingURL=index.js.map