Skip to content

Instantly share code, notes, and snippets.

@juanpujol
Created November 6, 2017 16:21
Show Gist options
  • Save juanpujol/58f84ff35c66acd65b7c547cd9f4537c to your computer and use it in GitHub Desktop.
Save juanpujol/58f84ff35c66acd65b7c547cd9f4537c to your computer and use it in GitHub Desktop.
Elasticsearch english analyzer
"settings": {
"analysis": {
"filter": {
"english_stop": {
"type": "stop",
"stopwords": [
"a",
"about",
"above",
"after",
"ag'ain",
"ag'ainst",
"around",
"all",
"am",
"an",
"and",
"any",
"are",
"aren't",
"as",
"at",
"be",
"because",
"been",
"before",
"being",
"below",
"between",
"both",
"but",
"by",
"can't",
"cannot",
"could",
"couldn't",
"did",
"didn't",
"do",
"does",
"doesn't",
"doing",
"don't",
"down",
"during",
"each",
"few",
"for",
"from",
"further",
"had",
"hadn't",
"has",
"hasn't",
"have",
"haven't",
"having",
"he",
"he'd",
"he'll",
"he's",
"her",
"here",
"here's",
"hers",
"herself",
"him",
"himself",
"his",
"how",
"how's",
"i",
"i'd",
"i'll",
"i'm",
"i've",
"if",
"in",
"into",
"is",
"isn't",
"it",
"it's",
"its",
"itself",
"let's",
"me",
"more",
"most",
"mustn't",
"my",
"myself",
"near",
"no",
"nor",
"not",
"of",
"off",
"on",
"once",
"only",
"or",
"other",
"ought",
"our",
"ours",
"ourselves",
"out",
"over",
"own",
"same",
"shan't",
"she",
"she'd",
"she'll",
"she's",
"should",
"shouldn't",
"so",
"some",
"such",
"than",
"that",
"that's",
"the",
"their",
"theirs",
"them",
"themselves",
"then",
"there",
"there's",
"these",
"they",
"they'd",
"they'll",
"they're",
"they've",
"this",
"those",
"through",
"to",
"too",
"under",
"until",
"up",
"very",
"was",
"wasn't",
"we",
"we'd",
"we'll",
"we're",
"we've",
"were",
"weren't",
"what",
"what's",
"when",
"when's",
"where",
"where's",
"which",
"while",
"who",
"who's",
"whom",
"why",
"why's",
"with",
"won't",
"would",
"wouldn't",
"you",
"you'd",
"you'll",
"you're",
"you've",
"your",
"yours",
"yourself",
"yourselves",
"?"
]
},
"english_stemmer": {
"type": "stemmer",
"language": "english"
},
"english_possessive_stemmer": {
"type": "stemmer",
"language": "possessive_english"
}
},
"analyzer": {
"english": {
"tokenizer": "standard",
"filter": [
"english_possessive_stemmer",
"lowercase",
"english_stop"
]
}
}
}
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment