Stopwords

// Input text:
// "The quick brown fox jumps over the lazy dog"

// Without stopwords:
// ["the", "quick", "brown", "fox", "jumps", "over", "the", "lazy", "dog"]

// With English stopwords:
// ["quick", "brown", "fox", "jumps", "lazy", "dog"]
// "the" and "over" removed

import { create } from '@orama/orama'

const customStopwords = ['inc', 'ltd', 'corp', 'co', 'llc']

const db = await create({
  schema: {
    companyName: 'string'
  },
  components: {
    tokenizer: {
      stopWords: customStopwords
    }
  }
})

await insert(db, {
  companyName: 'Acme Corp'
})

// "Corp" is filtered out
// Indexed: ["acme"]

import { create } from '@orama/orama'
import { stopwords as englishStopwords } from '@orama/stopwords/english'

const db = await create({
  schema: {
    content: 'string'
  },
  components: {
    tokenizer: {
      stopWords: (defaultStopWords) => [
        ...englishStopwords,
        ...defaultStopWords,
        // Add custom domain-specific stopwords
        'lorem',
        'ipsum',
        'dolor',
        'click',
        'here'
      ]
    }
  }
})

import { create } from '@orama/orama'

const db = await create({
  schema: {
    content: 'string'
  },
  components: {
    tokenizer: {
      stopWords: false  // Disable stopwords completely
    }
  }
})

// All words are indexed, including "the", "is", "at", etc.

// Pronouns
['i', 'me', 'my', 'myself', 'we', 'us', 'our', 'ours', 'ourselves',
 'you', 'your', 'yours', 'yourself', 'yourselves',
 'he', 'him', 'his', 'himself',
 'she', 'her', 'hers', 'herself',
 'it', 'its', 'itself',
 'they', 'them', 'their', 'theirs', 'themselves']

// Question words
['what', 'which', 'who', 'whom', 'this', 'that', 'these', 'those']

// Verbs (to be, to have, to do)
['am', 'is', 'are', 'was', 'were', 'be', 'been', 'being',
 'have', 'has', 'had', 'having',
 'do', 'does', 'did', 'doing']

// Modal verbs
['will', 'would', 'shall', 'should', 'can', 'could',
 'may', 'might', 'must', 'ought']

// Contractions
["i'm", "you're", "he's", "she's", "it's", "we're", "they're",
 "i've", "you've", "we've", "they've",
 "i'd", "you'd", "he'd", "she'd", "we'd", "they'd",
 "i'll", "you'll", "he'll", "she'll", "we'll", "they'll",
 "isn't", "aren't", "wasn't", "weren't",
 "hasn't", "haven't", "hadn't",
 "doesn't", "don't", "didn't",
 "won't", "wouldn't", "shan't", "shouldn't",
 "can't", "cannot", "couldn't", "mustn't"]

// Articles & conjunctions
['an', 'the', 'and', 'but', 'if', 'or', 'because', 'as', 'until', 'while']

// Prepositions
['of', 'at', 'by', 'for', 'with', 'about', 'against', 'between',
 'into', 'through', 'during', 'before', 'after', 'above', 'below',
 'to', 'from', 'up', 'down', 'in', 'out', 'on', 'off', 'over', 'under']

// Adverbs
['again', 'further', 'then', 'once',
 'here', 'there', 'when', 'where', 'why', 'how']

// Quantifiers
['all', 'any', 'both', 'each', 'few', 'more', 'most',
 'other', 'some', 'such']

// Negation & emphasis
['no', 'nor', 'not', 'only', 'own', 'same', 'so', 'than', 'too', 'very']

// Without stopwords: 1,000,000 tokens indexed
// With English stopwords: ~600,000 tokens indexed
// Reduction: 40%

import { create } from '@orama/orama'
import { stopwords } from '@orama/stopwords/english'

const db = await create({
  schema: {
    content: 'string'
  },
  components: {
    tokenizer: {
      language: 'english',
      stemming: true,
      stopWords: stopwords
    }
  }
})

// Input: "The developers are developing applications"
// 1. Tokenize: ["the", "developers", "are", "developing", "applications"]
// 2. Remove stopwords: ["developers", "developing", "applications"]
// 3. Stem: ["develop", "develop", "applic"]
// 4. Result: ["develop", "applic"] (duplicates removed)

// ✅ Valid: Array of strings
stopWords: ['the', 'is', 'at']

// ✅ Valid: Function returning array of strings
stopWords: (defaults) => [...defaults, 'custom']

// ✅ Valid: Disable stopwords
stopWords: false

// ❌ Invalid: Number
stopWords: 123  // Error: CUSTOM_STOP_WORDS_MUST_BE_FUNCTION_OR_ARRAY

// ❌ Invalid: Array with non-strings
stopWords: ['the', 123, 'is']  // Error: CUSTOM_STOP_WORDS_MUST_BE_FUNCTION_OR_ARRAY

// ❌ Invalid: Function not returning array
stopWords: () => 'the'  // Error: CUSTOM_STOP_WORDS_MUST_BE_FUNCTION_OR_ARRAY

import { create } from '@orama/orama'
import { stopwords as englishStopwords } from '@orama/stopwords/english'

const ecommerceStopwords = [
  ...englishStopwords,
  // Product description filler
  'new',
  'now',
  'available',
  'shop',
  'buy',
  'get',
  'free',
  'shipping',
  // Brand-specific
  'official',
  'authentic',
  'genuine'
]

const db = await create({
  schema: {
    productName: 'string',
    description: 'string'
  },
  components: {
    tokenizer: {
      stopWords: ecommerceStopwords,
      // Don't filter stopwords from product names
      stemmerSkipProperties: ['productName']
    }
  }
})