Skip to content

Instantly share code, notes, and snippets.

@easherma
Created August 3, 2016 19:07
Show Gist options
  • Save easherma/b4f878f9ee67f9036f687890f16444f1 to your computer and use it in GitHub Desktop.
Save easherma/b4f878f9ee67f9036f687890f16444f1 to your computer and use it in GitHub Desktop.
{
"settings": {
"analysis": {
"tokenizer": {
"peliasNameTokenizer": {
"type": "pattern",
"pattern": "[\\s,/\\\\]+"
},
"peliasStreetTokenizer": {
"type": "pattern",
"pattern": "[,/\\\\]+"
}
},
"analyzer": {
"peliasAdmin": {
"type": "custom",
"tokenizer": "peliasNameTokenizer",
"char_filter": [
"punctuation"
],
"filter": [
"lowercase",
"asciifolding",
"trim",
"word_delimiter",
"notnull"
]
},
"peliasIndexOneEdgeGram": {
"type": "custom",
"tokenizer": "peliasNameTokenizer",
"char_filter": [
"punctuation"
],
"filter": [
"lowercase",
"asciifolding",
"trim",
"full_token_address_suffix_expansion",
"ampersand",
"remove_ordinals",
"removeAllZeroNumericPrefix",
"surround_single_characters_with_word_markers",
"house_number_word_delimiter",
"remove_single_characters",
"surround_house_numbers_with_word_markers",
"peliasOneEdgeGramFilter",
"eliminate_tokens_starting_with_word_marker",
"remove_encapsulating_word_markers",
"unique",
"notnull"
]
},
"peliasIndexTwoEdgeGram": {
"type": "custom",
"tokenizer": "peliasNameTokenizer",
"char_filter": [
"punctuation"
],
"filter": [
"lowercase",
"asciifolding",
"trim",
"full_token_address_suffix_expansion",
"ampersand",
"remove_ordinals",
"removeAllZeroNumericPrefix",
"prefixZeroToSingleDigitNumbers",
"peliasTwoEdgeGramFilter",
"removeAllZeroNumericPrefix",
"direction_synonym_contraction_keep_original",
"unique",
"notnull"
]
},
"peliasQueryPartialToken": {
"type": "custom",
"tokenizer": "peliasNameTokenizer",
"char_filter": [
"punctuation"
],
"filter": [
"lowercase",
"asciifolding",
"trim",
"partial_token_address_suffix_expansion",
"ampersand",
"remove_ordinals",
"removeAllZeroNumericPrefix",
"unique",
"notnull"
]
},
"peliasQueryFullToken": {
"type": "custom",
"tokenizer": "peliasNameTokenizer",
"char_filter": [
"punctuation"
],
"filter": [
"lowercase",
"asciifolding",
"trim",
"remove_ordinals",
"full_token_address_suffix_expansion",
"ampersand",
"removeAllZeroNumericPrefix",
"unique",
"notnull"
]
},
"peliasPhrase": {
"type": "custom",
"tokenizer": "peliasNameTokenizer",
"char_filter": [
"punctuation"
],
"filter": [
"lowercase",
"asciifolding",
"trim",
"ampersand",
"street_synonym",
"direction_synonym",
"unique",
"notnull"
]
},
"peliasZip": {
"type": "custom",
"tokenizer": "keyword",
"char_filter": [
"alphanumeric"
],
"filter": [
"lowercase",
"trim"
]
},
"peliasHousenumber": {
"type": "custom",
"tokenizer": "standard",
"char_filter": [
"numeric"
]
},
"peliasStreet": {
"type": "custom",
"tokenizer": "peliasStreetTokenizer",
"char_filter": [
"punctuation"
],
"filter": [
"lowercase",
"asciifolding",
"remove_duplicate_spaces",
"keyword_street_suffix_alley",
"keyword_street_suffix_annex",
"keyword_street_suffix_avenue",
"keyword_street_suffix_bayou",
"keyword_street_suffix_beach",
"keyword_street_suffix_bend",
"keyword_street_suffix_bluff",
"keyword_street_suffix_bluffs",
"keyword_street_suffix_bottom",
"keyword_street_suffix_boulevard",
"keyword_street_suffix_branch",
"keyword_street_suffix_bridge",
"keyword_street_suffix_brook",
"keyword_street_suffix_bypass",
"keyword_street_suffix_canyon",
"keyword_street_suffix_cape",
"keyword_street_suffix_causeway",
"keyword_street_suffix_center",
"keyword_street_suffix_channel",
"keyword_street_suffix_circle",
"keyword_street_suffix_cliff",
"keyword_street_suffix_close",
"keyword_street_suffix_club",
"keyword_street_suffix_common",
"keyword_street_suffix_commons",
"keyword_street_suffix_connector",
"keyword_street_suffix_corridor",
"keyword_street_suffix_course",
"keyword_street_suffix_court",
"keyword_street_suffix_cove",
"keyword_street_suffix_creek",
"keyword_street_suffix_crescent",
"keyword_street_suffix_crest",
"keyword_street_suffix_crossing",
"keyword_street_suffix_crossroad",
"keyword_street_suffix_crossroads",
"keyword_street_suffix_curve",
"keyword_street_suffix_dale",
"keyword_street_suffix_dam",
"keyword_street_suffix_drive",
"keyword_street_suffix_esplanade",
"keyword_street_suffix_expressway",
"keyword_street_suffix_extended",
"keyword_street_suffix_falls",
"keyword_street_suffix_ferry",
"keyword_street_suffix_field",
"keyword_street_suffix_fields",
"keyword_street_suffix_flat",
"keyword_street_suffix_flats",
"keyword_street_suffix_ford",
"keyword_street_suffix_forest",
"keyword_street_suffix_forge",
"keyword_street_suffix_fork",
"keyword_street_suffix_forks",
"keyword_street_suffix_freeway",
"keyword_street_suffix_garden",
"keyword_street_suffix_gardens",
"keyword_street_suffix_gateway",
"keyword_street_suffix_glen",
"keyword_street_suffix_glenn",
"keyword_street_suffix_green",
"keyword_street_suffix_grove",
"keyword_street_suffix_harbor",
"keyword_street_suffix_haven",
"keyword_street_suffix_heights",
"keyword_street_suffix_highway",
"keyword_street_suffix_hill",
"keyword_street_suffix_hills",
"keyword_street_suffix_hollow",
"keyword_street_suffix_isle",
"keyword_street_suffix_junction",
"keyword_street_suffix_key",
"keyword_street_suffix_keys",
"keyword_street_suffix_knoll",
"keyword_street_suffix_knolls",
"keyword_street_suffix_landing",
"keyword_street_suffix_lane",
"keyword_street_suffix_light",
"keyword_street_suffix_lights",
"keyword_street_suffix_lock",
"keyword_street_suffix_locks",
"keyword_street_suffix_manor",
"keyword_street_suffix_meadow",
"keyword_street_suffix_meadows",
"keyword_street_suffix_mill",
"keyword_street_suffix_mills",
"keyword_street_suffix_mountain",
"keyword_street_suffix_motorway",
"keyword_street_suffix_neck",
"keyword_street_suffix_orchard",
"keyword_street_suffix_parkway",
"keyword_street_suffix_pasage",
"keyword_street_suffix_pier",
"keyword_street_suffix_pine",
"keyword_street_suffix_pines",
"keyword_street_suffix_place",
"keyword_street_suffix_plaza",
"keyword_street_suffix_ranch",
"keyword_street_suffix_ridge",
"keyword_street_suffix_ridges",
"keyword_street_suffix_river",
"keyword_street_suffix_road",
"keyword_street_suffix_route",
"keyword_street_suffix_shore",
"keyword_street_suffix_shores",
"keyword_street_suffix_skyway",
"keyword_street_suffix_spring",
"keyword_street_suffix_springs",
"keyword_street_suffix_square",
"keyword_street_suffix_street",
"keyword_street_suffix_suite",
"keyword_street_suffix_terrace",
"keyword_street_suffix_trail",
"keyword_street_suffix_trafficway",
"keyword_street_suffix_tunnel",
"keyword_street_suffix_turnpike",
"keyword_street_suffix_valley",
"keyword_street_suffix_vista",
"keyword_street_suffix_village",
"keyword_street_suffix_way",
"keyword_compass_southwest",
"keyword_compass_southeast",
"keyword_compass_northwest",
"keyword_compass_northeast",
"keyword_compass_north",
"keyword_compass_south",
"keyword_compass_east",
"keyword_compass_west",
"remove_ordinals",
"trim"
]
}
},
"filter": {
"ampersand": {
"type": "synonym",
"synonyms": [
"and => &"
]
},
"notnull": {
"type": "length",
"min": 1
},
"peliasOneEdgeGramFilter": {
"type": "edgeNGram",
"min_gram": 1,
"max_gram": 18
},
"peliasTwoEdgeGramFilter": {
"type": "edgeNGram",
"min_gram": 2,
"max_gram": 18
},
"prefixZeroToSingleDigitNumbers": {
"type": "pattern_replace",
"pattern": "^([0-9])$",
"replacement": "0$1"
},
"removeAllZeroNumericPrefix": {
"type": "pattern_replace",
"pattern": "^(0*)",
"replacement": ""
},
"address_stop": {
"type": "stop",
"stopwords": [
"alley",
"annex",
"avenue",
"bay",
"bayou",
"beach",
"beltway",
"bend",
"bluff",
"bluffs",
"boulevard",
"bottom",
"branch",
"bridge",
"brook",
"bypass",
"canyon",
"cape",
"causeway",
"center",
"channel",
"circle",
"cliff",
"club",
"common",
"commons",
"connector",
"corridor",
"course",
"cove",
"creek",
"crescent",
"crest",
"crossing",
"crossroad",
"crossroads",
"curve",
"dale",
"dam",
"drive",
"esplanade",
"expressway",
"extended",
"falls",
"ferry",
"field",
"fields",
"flat",
"flats",
"ford",
"forest",
"forge",
"fork",
"forks",
"freeway",
"garden",
"gardens",
"gateway",
"glen",
"glenn",
"green",
"grove",
"harbor",
"haven",
"heights",
"highway",
"hill",
"hills",
"hollow",
"isle",
"junction",
"key",
"keys",
"knoll",
"knolls",
"landing",
"lane",
"light",
"lights",
"lock",
"locks",
"manor",
"meadow",
"meadows",
"mews",
"mill",
"mills",
"mountain",
"motorway",
"neck",
"orchard",
"parade",
"parkway",
"passage",
"pier",
"pike",
"pine",
"pines",
"place",
"plaza",
"promenade",
"ranch",
"ridge",
"ridges",
"river",
"road",
"route",
"row",
"shore",
"shores",
"skyway",
"spring",
"springs",
"square",
"street",
"terrace",
"trail",
"trafficway",
"tunnel",
"turnpike",
"valley",
"vista",
"village",
"viaduct",
"way"
]
},
"street_synonym": {
"type": "synonym",
"synonyms": [
"alley => aly",
"annex => anx",
"avenue => ave",
"bayou => byu",
"beach => bch",
"bend => bnd",
"bluff => blf",
"bluffs => blfs",
"bottom => btm",
"boulevard => blvd",
"branch => br",
"bridge => brg",
"brook => brk",
"bypass => byp",
"canyon => cyn",
"cape => cp",
"causeway => cswy",
"center => ctr",
"channel => chnnl",
"circle => cir",
"cliff => clf",
"close => cl",
"club => clb",
"common => cmn",
"commons => cmns",
"connector => con",
"corridor => cor",
"course => crse",
"court => ct",
"cove => cv",
"creek => crk",
"crescent => cres",
"crest => crst",
"crossing => xing",
"crossroad => xrd",
"crossroads => xrds",
"curve => curv",
"dale => dl",
"dam => dm",
"drive => dr",
"esplanade => esp",
"expressway => expy",
"extended => ext",
"falls => fls",
"ferry => fry",
"field => fld",
"fields => flds",
"flat => flt",
"flats => flts",
"ford => frd",
"forest => frst",
"forge => frg",
"fork => frk",
"forks => frks",
"freeway => fwy",
"garden => gdn",
"gardens => gdns",
"gateway => gtwy",
"glen => gln",
"glenn => gln",
"green => grn",
"grove => grv",
"harbor => hbr",
"haven => hvn",
"heights => hts",
"highway => hwy",
"hill => hl",
"hills => hls",
"hollow => holw",
"isle => is",
"junction => jct",
"key => ky",
"keys => kys",
"knoll => knl",
"knolls => knls",
"landing => lndg",
"lane => ln",
"light => lgt",
"lights => lgts",
"lock => lck",
"locks => lcks",
"manor => mnr",
"meadow => mdw",
"meadows => mdws",
"mill => ml",
"mills => mls",
"mountain => mnt",
"motorway => mtwy",
"neck => nck",
"orchard => orch",
"parkway => pkwy",
"pasage => psge",
"pier => pr",
"pine => pne",
"pines => pnes",
"place => pl",
"plaza => plz",
"ranch => rnch",
"ridge => rdg",
"ridges => rdgs",
"river => riv",
"road => rd",
"route => rte",
"shore => shr",
"shores => shrs",
"skyway => skwy",
"spring => spg",
"springs => spgs",
"square => sq",
"street => st",
"suite => ste",
"terrace => terr",
"trail => tr",
"trafficway => trfy",
"tunnel => tunl",
"turnpike => tpke",
"valley => vly",
"vista => vis",
"village => vlg",
"way => wy"
]
},
"partial_token_address_suffix_expansion": {
"type": "synonym",
"synonyms": [
"aly => alley",
"anx => annex",
"byu => bayou",
"bch => beach",
"bnd => bend",
"blf => bluff",
"blfs => bluffs",
"btm => bottom",
"blvd => boulevard",
"brg => bridge",
"brk => brook",
"cyn => canyon",
"cp => cape",
"cswy => causeway",
"ctr => center",
"chnnl => channel",
"clf => cliff",
"clb => club",
"cmn => common",
"cmns => commons",
"crse => course",
"cv => cove",
"crk => creek",
"crst => crest",
"xing => crossing",
"xrd => crossroad",
"xrds => crossroads",
"dl => dale",
"dm => dam",
"expy => expressway",
"fls => falls",
"fry => ferry",
"fld => field",
"flds => fields",
"flt => flat",
"flts => flats",
"frd => ford",
"frst => forest",
"frg => forge",
"frk => fork",
"frks => forks",
"fwy => freeway",
"gdn => garden",
"gdns => gardens",
"gtwy => gateway",
"gln => glenn",
"grn => green",
"grv => grove",
"hbr => harbor",
"hvn => haven",
"hts => heights",
"hwy => highway",
"hl => hill",
"hls => hills",
"holw => hollow",
"jct => junction",
"ky => key",
"kys => keys",
"knl => knoll",
"knls => knolls",
"lndg => landing",
"ln => lane",
"lgt => light",
"lgts => lights",
"lck => lock",
"lcks => locks",
"mnr => manor",
"mdw => meadow",
"mdws => meadows",
"ml => mill",
"mls => mills",
"mnt => mountain",
"mtwy => motorway",
"nck => neck",
"pkwy => parkway",
"psge => pasage",
"pne => pine",
"pnes => pines",
"plz => plaza",
"rnch => ranch",
"rdg => ridge",
"rdgs => ridges",
"rd => road",
"rte => route",
"shr => shore",
"shrs => shores",
"skwy => skyway",
"spg => spring",
"spgs => springs",
"ste => suite",
"trfy => trafficway",
"tunl => tunnel",
"tpke => turnpike",
"vly => valley",
"vlg => village",
"wy => way"
]
},
"full_token_address_suffix_expansion": {
"type": "synonym",
"synonyms": [
"aly => alley",
"anx => annex",
"byu => bayou",
"bch => beach",
"bnd => bend",
"blf => bluff",
"blfs => bluffs",
"btm => bottom",
"blvd => boulevard",
"brg => bridge",
"brk => brook",
"cyn => canyon",
"cp => cape",
"cswy => causeway",
"ctr => center",
"chnnl => channel",
"clf => cliff",
"clb => club",
"cmn => common",
"cmns => commons",
"crse => course",
"cv => cove",
"crk => creek",
"crst => crest",
"xing => crossing",
"xrd => crossroad",
"xrds => crossroads",
"dl => dale",
"dm => dam",
"expy => expressway",
"fls => falls",
"fry => ferry",
"fld => field",
"flds => fields",
"flt => flat",
"flts => flats",
"frd => ford",
"frst => forest",
"frg => forge",
"frk => fork",
"frks => forks",
"fwy => freeway",
"gdn => garden",
"gdns => gardens",
"gtwy => gateway",
"gln => glenn",
"grn => green",
"grv => grove",
"hbr => harbor",
"hvn => haven",
"hts => heights",
"hwy => highway",
"hl => hill",
"hls => hills",
"holw => hollow",
"jct => junction",
"ky => key",
"kys => keys",
"knl => knoll",
"knls => knolls",
"lndg => landing",
"ln => lane",
"lgt => light",
"lgts => lights",
"lck => lock",
"lcks => locks",
"mnr => manor",
"mdw => meadow",
"mdws => meadows",
"ml => mill",
"mls => mills",
"mnt => mountain",
"mtwy => motorway",
"nck => neck",
"pkwy => parkway",
"psge => pasage",
"pne => pine",
"pnes => pines",
"plz => plaza",
"rnch => ranch",
"rdg => ridge",
"rdgs => ridges",
"rd => road",
"rte => route",
"shr => shore",
"shrs => shores",
"skwy => skyway",
"spg => spring",
"spgs => springs",
"ste => suite",
"trfy => trafficway",
"tunl => tunnel",
"tpke => turnpike",
"vly => valley",
"vlg => village",
"wy => way",
"n => north",
"s => south",
"e => east",
"w => west"
]
},
"direction_synonym": {
"type": "synonym",
"synonyms": [
"southwest => sw",
"southeast => se",
"northwest => nw",
"northeast => ne",
"north => n",
"south => s",
"east => e",
"west => w"
]
},
"direction_synonym_contraction_keep_original": {
"type": "synonym",
"synonyms": [
"north => north,n",
"south => south,s",
"east => east,e",
"west => west,w"
]
},
"remove_ordinals": {
"type": "pattern_replace",
"pattern": "(?i)((^| )((1)st?|(2)nd?|(3)rd?|([4-9])th?)|(([0-9]*)(1[0-9])th?)|(([0-9]*[02-9])((1)st?|(2)nd?|(3)rd?|([04-9])th?))($| ))",
"replacement": "$2$4$5$6$7$9$10$12$14$15$16$17$18"
},
"remove_duplicate_spaces": {
"type": "pattern_replace",
"pattern": " +",
"replacement": " "
},
"surround_single_characters_with_word_markers": {
"description": "wraps single characters with markers, needed to protect valid single characters and not those extracted from house numbers (14a creates an 'a' token)",
"type": "pattern_replace",
"pattern": "^(.{1})$",
"replacement": "\u0002$1\u0003"
},
"house_number_word_delimiter": {
"description": "splits on letter-to-number transition and vice versa, splits 14a -> [14, 14a, a]",
"type": "word_delimiter",
"split_on_numerics": "true",
"preserve_original": "true"
},
"remove_single_characters": {
"description": "removes single characters created from house_number_word_delimiter, removes the letter portion of a house number",
"type": "length",
"min": 2
},
"surround_house_numbers_with_word_markers": {
"description": "surrounds house numbers with markers, needed to protect whole house numbers from elimination step after prefix n-gramming",
"type": "pattern_replace",
"pattern": "^([0-9]+[a-z]?)$",
"replacement": "\u0002$1\u0003"
},
"eliminate_tokens_starting_with_word_marker": {
"description": "remove tokens starting but not ending with markers, saves whole house numbers wrapped in markers",
"type": "pattern_replace",
"pattern": "^\u0002(.*[^\u0003])?$",
"replacement": ""
},
"remove_encapsulating_word_markers": {
"description": "extract the stuff between the markers, extract 14 from \u000214\u0003 since we're done the prefix n-gramming step",
"type": "pattern_replace",
"pattern": "^\u0002(.*)\u0003$",
"replacement": "$1"
},
"keyword_street_suffix_alley": {
"type": "pattern_replace",
"pattern": " alley",
"replacement": " aly"
},
"keyword_street_suffix_annex": {
"type": "pattern_replace",
"pattern": " annex",
"replacement": " anx"
},
"keyword_street_suffix_avenue": {
"type": "pattern_replace",
"pattern": " avenue",
"replacement": " ave"
},
"keyword_street_suffix_bayou": {
"type": "pattern_replace",
"pattern": " bayou",
"replacement": " byu"
},
"keyword_street_suffix_beach": {
"type": "pattern_replace",
"pattern": " beach",
"replacement": " bch"
},
"keyword_street_suffix_bend": {
"type": "pattern_replace",
"pattern": " bend",
"replacement": " bnd"
},
"keyword_street_suffix_bluff": {
"type": "pattern_replace",
"pattern": " bluff",
"replacement": " blf"
},
"keyword_street_suffix_bluffs": {
"type": "pattern_replace",
"pattern": " bluffs",
"replacement": " blfs"
},
"keyword_street_suffix_bottom": {
"type": "pattern_replace",
"pattern": " bottom",
"replacement": " btm"
},
"keyword_street_suffix_boulevard": {
"type": "pattern_replace",
"pattern": " boulevard",
"replacement": " blvd"
},
"keyword_street_suffix_branch": {
"type": "pattern_replace",
"pattern": " branch",
"replacement": " br"
},
"keyword_street_suffix_bridge": {
"type": "pattern_replace",
"pattern": " bridge",
"replacement": " brg"
},
"keyword_street_suffix_brook": {
"type": "pattern_replace",
"pattern": " brook",
"replacement": " brk"
},
"keyword_street_suffix_bypass": {
"type": "pattern_replace",
"pattern": " bypass",
"replacement": " byp"
},
"keyword_street_suffix_canyon": {
"type": "pattern_replace",
"pattern": " canyon",
"replacement": " cyn"
},
"keyword_street_suffix_cape": {
"type": "pattern_replace",
"pattern": " cape",
"replacement": " cp"
},
"keyword_street_suffix_causeway": {
"type": "pattern_replace",
"pattern": " causeway",
"replacement": " cswy"
},
"keyword_street_suffix_center": {
"type": "pattern_replace",
"pattern": " center",
"replacement": " ctr"
},
"keyword_street_suffix_channel": {
"type": "pattern_replace",
"pattern": " channel",
"replacement": " chnnl"
},
"keyword_street_suffix_circle": {
"type": "pattern_replace",
"pattern": " circle",
"replacement": " cir"
},
"keyword_street_suffix_cliff": {
"type": "pattern_replace",
"pattern": " cliff",
"replacement": " clf"
},
"keyword_street_suffix_close": {
"type": "pattern_replace",
"pattern": " close",
"replacement": " cl"
},
"keyword_street_suffix_club": {
"type": "pattern_replace",
"pattern": " club",
"replacement": " clb"
},
"keyword_street_suffix_common": {
"type": "pattern_replace",
"pattern": " common",
"replacement": " cmn"
},
"keyword_street_suffix_commons": {
"type": "pattern_replace",
"pattern": " commons",
"replacement": " cmns"
},
"keyword_street_suffix_connector": {
"type": "pattern_replace",
"pattern": " connector",
"replacement": " con"
},
"keyword_street_suffix_corridor": {
"type": "pattern_replace",
"pattern": " corridor",
"replacement": " cor"
},
"keyword_street_suffix_course": {
"type": "pattern_replace",
"pattern": " course",
"replacement": " crse"
},
"keyword_street_suffix_court": {
"type": "pattern_replace",
"pattern": " court",
"replacement": " ct"
},
"keyword_street_suffix_cove": {
"type": "pattern_replace",
"pattern": " cove",
"replacement": " cv"
},
"keyword_street_suffix_creek": {
"type": "pattern_replace",
"pattern": " creek",
"replacement": " crk"
},
"keyword_street_suffix_crescent": {
"type": "pattern_replace",
"pattern": " crescent",
"replacement": " cres"
},
"keyword_street_suffix_crest": {
"type": "pattern_replace",
"pattern": " crest",
"replacement": " crst"
},
"keyword_street_suffix_crossing": {
"type": "pattern_replace",
"pattern": " crossing",
"replacement": " xing"
},
"keyword_street_suffix_crossroad": {
"type": "pattern_replace",
"pattern": " crossroad",
"replacement": " xrd"
},
"keyword_street_suffix_crossroads": {
"type": "pattern_replace",
"pattern": " crossroads",
"replacement": " xrds"
},
"keyword_street_suffix_curve": {
"type": "pattern_replace",
"pattern": " curve",
"replacement": " curv"
},
"keyword_street_suffix_dale": {
"type": "pattern_replace",
"pattern": " dale",
"replacement": " dl"
},
"keyword_street_suffix_dam": {
"type": "pattern_replace",
"pattern": " dam",
"replacement": " dm"
},
"keyword_street_suffix_drive": {
"type": "pattern_replace",
"pattern": " drive",
"replacement": " dr"
},
"keyword_street_suffix_esplanade": {
"type": "pattern_replace",
"pattern": " esplanade",
"replacement": " esp"
},
"keyword_street_suffix_expressway": {
"type": "pattern_replace",
"pattern": " expressway",
"replacement": " expy"
},
"keyword_street_suffix_extended": {
"type": "pattern_replace",
"pattern": " extended",
"replacement": " ext"
},
"keyword_street_suffix_falls": {
"type": "pattern_replace",
"pattern": " falls",
"replacement": " fls"
},
"keyword_street_suffix_ferry": {
"type": "pattern_replace",
"pattern": " ferry",
"replacement": " fry"
},
"keyword_street_suffix_field": {
"type": "pattern_replace",
"pattern": " field",
"replacement": " fld"
},
"keyword_street_suffix_fields": {
"type": "pattern_replace",
"pattern": " fields",
"replacement": " flds"
},
"keyword_street_suffix_flat": {
"type": "pattern_replace",
"pattern": " flat",
"replacement": " flt"
},
"keyword_street_suffix_flats": {
"type": "pattern_replace",
"pattern": " flats",
"replacement": " flts"
},
"keyword_street_suffix_ford": {
"type": "pattern_replace",
"pattern": " ford",
"replacement": " frd"
},
"keyword_street_suffix_forest": {
"type": "pattern_replace",
"pattern": " forest",
"replacement": " frst"
},
"keyword_street_suffix_forge": {
"type": "pattern_replace",
"pattern": " forge",
"replacement": " frg"
},
"keyword_street_suffix_fork": {
"type": "pattern_replace",
"pattern": " fork",
"replacement": " frk"
},
"keyword_street_suffix_forks": {
"type": "pattern_replace",
"pattern": " forks",
"replacement": " frks"
},
"keyword_street_suffix_freeway": {
"type": "pattern_replace",
"pattern": " freeway",
"replacement": " fwy"
},
"keyword_street_suffix_garden": {
"type": "pattern_replace",
"pattern": " garden",
"replacement": " gdn"
},
"keyword_street_suffix_gardens": {
"type": "pattern_replace",
"pattern": " gardens",
"replacement": " gdns"
},
"keyword_street_suffix_gateway": {
"type": "pattern_replace",
"pattern": " gateway",
"replacement": " gtwy"
},
"keyword_street_suffix_glen": {
"type": "pattern_replace",
"pattern": " glen",
"replacement": " gln"
},
"keyword_street_suffix_glenn": {
"type": "pattern_replace",
"pattern": " glenn",
"replacement": " gln"
},
"keyword_street_suffix_green": {
"type": "pattern_replace",
"pattern": " green",
"replacement": " grn"
},
"keyword_street_suffix_grove": {
"type": "pattern_replace",
"pattern": " grove",
"replacement": " grv"
},
"keyword_street_suffix_harbor": {
"type": "pattern_replace",
"pattern": " harbor",
"replacement": " hbr"
},
"keyword_street_suffix_haven": {
"type": "pattern_replace",
"pattern": " haven",
"replacement": " hvn"
},
"keyword_street_suffix_heights": {
"type": "pattern_replace",
"pattern": " heights",
"replacement": " hts"
},
"keyword_street_suffix_highway": {
"type": "pattern_replace",
"pattern": " highway",
"replacement": " hwy"
},
"keyword_street_suffix_hill": {
"type": "pattern_replace",
"pattern": " hill",
"replacement": " hl"
},
"keyword_street_suffix_hills": {
"type": "pattern_replace",
"pattern": " hills",
"replacement": " hls"
},
"keyword_street_suffix_hollow": {
"type": "pattern_replace",
"pattern": " hollow",
"replacement": " holw"
},
"keyword_street_suffix_isle": {
"type": "pattern_replace",
"pattern": " isle",
"replacement": " is"
},
"keyword_street_suffix_junction": {
"type": "pattern_replace",
"pattern": " junction",
"replacement": " jct"
},
"keyword_street_suffix_key": {
"type": "pattern_replace",
"pattern": " key",
"replacement": " ky"
},
"keyword_street_suffix_keys": {
"type": "pattern_replace",
"pattern": " keys",
"replacement": " kys"
},
"keyword_street_suffix_knoll": {
"type": "pattern_replace",
"pattern": " knoll",
"replacement": " knl"
},
"keyword_street_suffix_knolls": {
"type": "pattern_replace",
"pattern": " knolls",
"replacement": " knls"
},
"keyword_street_suffix_landing": {
"type": "pattern_replace",
"pattern": " landing",
"replacement": " lndg"
},
"keyword_street_suffix_lane": {
"type": "pattern_replace",
"pattern": " lane",
"replacement": " ln"
},
"keyword_street_suffix_light": {
"type": "pattern_replace",
"pattern": " light",
"replacement": " lgt"
},
"keyword_street_suffix_lights": {
"type": "pattern_replace",
"pattern": " lights",
"replacement": " lgts"
},
"keyword_street_suffix_lock": {
"type": "pattern_replace",
"pattern": " lock",
"replacement": " lck"
},
"keyword_street_suffix_locks": {
"type": "pattern_replace",
"pattern": " locks",
"replacement": " lcks"
},
"keyword_street_suffix_manor": {
"type": "pattern_replace",
"pattern": " manor",
"replacement": " mnr"
},
"keyword_street_suffix_meadow": {
"type": "pattern_replace",
"pattern": " meadow",
"replacement": " mdw"
},
"keyword_street_suffix_meadows": {
"type": "pattern_replace",
"pattern": " meadows",
"replacement": " mdws"
},
"keyword_street_suffix_mill": {
"type": "pattern_replace",
"pattern": " mill",
"replacement": " ml"
},
"keyword_street_suffix_mills": {
"type": "pattern_replace",
"pattern": " mills",
"replacement": " mls"
},
"keyword_street_suffix_mountain": {
"type": "pattern_replace",
"pattern": " mountain",
"replacement": " mnt"
},
"keyword_street_suffix_motorway": {
"type": "pattern_replace",
"pattern": " motorway",
"replacement": " mtwy"
},
"keyword_street_suffix_neck": {
"type": "pattern_replace",
"pattern": " neck",
"replacement": " nck"
},
"keyword_street_suffix_orchard": {
"type": "pattern_replace",
"pattern": " orchard",
"replacement": " orch"
},
"keyword_street_suffix_parkway": {
"type": "pattern_replace",
"pattern": " parkway",
"replacement": " pkwy"
},
"keyword_street_suffix_pasage": {
"type": "pattern_replace",
"pattern": " pasage",
"replacement": " psge"
},
"keyword_street_suffix_pier": {
"type": "pattern_replace",
"pattern": " pier",
"replacement": " pr"
},
"keyword_street_suffix_pine": {
"type": "pattern_replace",
"pattern": " pine",
"replacement": " pne"
},
"keyword_street_suffix_pines": {
"type": "pattern_replace",
"pattern": " pines",
"replacement": " pnes"
},
"keyword_street_suffix_place": {
"type": "pattern_replace",
"pattern": " place",
"replacement": " pl"
},
"keyword_street_suffix_plaza": {
"type": "pattern_replace",
"pattern": " plaza",
"replacement": " plz"
},
"keyword_street_suffix_ranch": {
"type": "pattern_replace",
"pattern": " ranch",
"replacement": " rnch"
},
"keyword_street_suffix_ridge": {
"type": "pattern_replace",
"pattern": " ridge",
"replacement": " rdg"
},
"keyword_street_suffix_ridges": {
"type": "pattern_replace",
"pattern": " ridges",
"replacement": " rdgs"
},
"keyword_street_suffix_river": {
"type": "pattern_replace",
"pattern": " river",
"replacement": " riv"
},
"keyword_street_suffix_road": {
"type": "pattern_replace",
"pattern": " road",
"replacement": " rd"
},
"keyword_street_suffix_route": {
"type": "pattern_replace",
"pattern": " route",
"replacement": " rte"
},
"keyword_street_suffix_shore": {
"type": "pattern_replace",
"pattern": " shore",
"replacement": " shr"
},
"keyword_street_suffix_shores": {
"type": "pattern_replace",
"pattern": " shores",
"replacement": " shrs"
},
"keyword_street_suffix_skyway": {
"type": "pattern_replace",
"pattern": " skyway",
"replacement": " skwy"
},
"keyword_street_suffix_spring": {
"type": "pattern_replace",
"pattern": " spring",
"replacement": " spg"
},
"keyword_street_suffix_springs": {
"type": "pattern_replace",
"pattern": " springs",
"replacement": " spgs"
},
"keyword_street_suffix_square": {
"type": "pattern_replace",
"pattern": " square",
"replacement": " sq"
},
"keyword_street_suffix_street": {
"type": "pattern_replace",
"pattern": " street",
"replacement": " st"
},
"keyword_street_suffix_suite": {
"type": "pattern_replace",
"pattern": " suite",
"replacement": " ste"
},
"keyword_street_suffix_terrace": {
"type": "pattern_replace",
"pattern": " terrace",
"replacement": " terr"
},
"keyword_street_suffix_trail": {
"type": "pattern_replace",
"pattern": " trail",
"replacement": " tr"
},
"keyword_street_suffix_trafficway": {
"type": "pattern_replace",
"pattern": " trafficway",
"replacement": " trfy"
},
"keyword_street_suffix_tunnel": {
"type": "pattern_replace",
"pattern": " tunnel",
"replacement": " tunl"
},
"keyword_street_suffix_turnpike": {
"type": "pattern_replace",
"pattern": " turnpike",
"replacement": " tpke"
},
"keyword_street_suffix_valley": {
"type": "pattern_replace",
"pattern": " valley",
"replacement": " vly"
},
"keyword_street_suffix_vista": {
"type": "pattern_replace",
"pattern": " vista",
"replacement": " vis"
},
"keyword_street_suffix_village": {
"type": "pattern_replace",
"pattern": " village",
"replacement": " vlg"
},
"keyword_street_suffix_way": {
"type": "pattern_replace",
"pattern": " way",
"replacement": " wy"
},
"keyword_compass_southwest": {
"type": "pattern_replace",
"pattern": "southwest ",
"replacement": "sw "
},
"keyword_compass_southeast": {
"type": "pattern_replace",
"pattern": "southeast ",
"replacement": "se "
},
"keyword_compass_northwest": {
"type": "pattern_replace",
"pattern": "northwest ",
"replacement": "nw "
},
"keyword_compass_northeast": {
"type": "pattern_replace",
"pattern": "northeast ",
"replacement": "ne "
},
"keyword_compass_north": {
"type": "pattern_replace",
"pattern": "north ",
"replacement": "n "
},
"keyword_compass_south": {
"type": "pattern_replace",
"pattern": "south ",
"replacement": "s "
},
"keyword_compass_east": {
"type": "pattern_replace",
"pattern": "east ",
"replacement": "e "
},
"keyword_compass_west": {
"type": "pattern_replace",
"pattern": "west ",
"replacement": "w "
}
},
"char_filter": {
"punctuation": {
"type": "mapping",
"mappings": [
".=>",
"`=>",
"_=>",
"==>",
"?=>",
"'=>",
"|=>",
"\"=>",
"(=>",
")=>",
"{=>",
"}=>",
"[=>",
"]=>",
"<=>",
">=>",
"*=>",
"#=>",
"^=>",
"$=>",
"@=>",
"!=>",
"~=>",
":=>",
";=>",
"+=>",
"《=>",
"》=>",
"—=>",
"-=>",
",=>",
"。=>",
"、=>",
":=>",
";=>",
"!=>",
"·=>",
"?=>",
"“=>",
"”=>",
")=>",
"(=>",
"【=>",
"】=>",
"[=>",
"]=>",
"●=>"
]
},
"alphanumeric": {
"type": "pattern_replace",
"pattern": "[^a-zA-Z0-9]",
"replacement": ""
},
"numeric": {
"type": "pattern_replace",
"pattern": "[^0-9]",
"replacement": " "
}
}
},
"index": {
"number_of_replicas": "0",
"number_of_shards": "1",
"index_concurrency": "10"
}
},
"mappings": {
"_default_": {
"properties": {
"source": {
"type": "string",
"analyzer": "keyword",
"store": "yes"
},
"layer": {
"type": "string",
"analyzer": "keyword",
"store": "yes"
},
"alpha3": {
"type": "string",
"analyzer": "peliasAdmin",
"store": "yes"
},
"name": {
"type": "object",
"dynamic": true
},
"phrase": {
"type": "object",
"dynamic": true
},
"address_parts": {
"type": "object",
"dynamic": true,
"properties": {
"name": {
"type": "string",
"analyzer": "keyword"
},
"number": {
"type": "string",
"analyzer": "peliasHousenumber"
},
"street": {
"type": "string",
"analyzer": "peliasStreet"
},
"zip": {
"type": "string",
"analyzer": "peliasZip"
}
}
},
"parent": {
"type": "object",
"dynamic": true,
"properties": {
"country": {
"type": "string",
"analyzer": "peliasAdmin",
"store": "yes"
},
"country_a": {
"type": "string",
"analyzer": "peliasAdmin",
"store": "yes"
},
"country_id": {
"type": "string",
"analyzer": "keyword",
"store": "yes"
},
"macroregion": {
"type": "string",
"analyzer": "peliasAdmin",
"store": "yes"
},
"macroregion_a": {
"type": "string",
"analyzer": "peliasAdmin",
"store": "yes"
},
"macroregion_id": {
"type": "string",
"analyzer": "keyword",
"store": "yes"
},
"region": {
"type": "string",
"analyzer": "peliasAdmin",
"store": "yes"
},
"region_a": {
"type": "string",
"analyzer": "peliasAdmin",
"store": "yes"
},
"region_id": {
"type": "string",
"analyzer": "keyword",
"store": "yes"
},
"macrocounty": {
"type": "string",
"analyzer": "peliasAdmin",
"store": "yes"
},
"macrocounty_a": {
"type": "string",
"analyzer": "peliasAdmin",
"store": "yes"
},
"macrocounty_id": {
"type": "string",
"analyzer": "keyword",
"store": "yes"
},
"county": {
"type": "string",
"analyzer": "peliasAdmin",
"store": "yes"
},
"county_a": {
"type": "string",
"analyzer": "peliasAdmin",
"store": "yes"
},
"county_id": {
"type": "string",
"analyzer": "keyword",
"store": "yes"
},
"locality": {
"type": "string",
"analyzer": "peliasAdmin",
"store": "yes"
},
"locality_a": {
"type": "string",
"analyzer": "peliasAdmin",
"store": "yes"
},
"locality_id": {
"type": "string",
"analyzer": "keyword",
"store": "yes"
},
"borough": {
"type": "string",
"analyzer": "peliasAdmin",
"store": "yes"
},
"borough_a": {
"type": "string",
"analyzer": "peliasAdmin",
"store": "yes"
},
"borough_id": {
"type": "string",
"analyzer": "keyword",
"store": "yes"
},
"localadmin": {
"type": "string",
"analyzer": "peliasAdmin",
"store": "yes"
},
"localadmin_a": {
"type": "string",
"analyzer": "peliasAdmin",
"store": "yes"
},
"localadmin_id": {
"type": "string",
"analyzer": "keyword",
"store": "yes"
},
"neighbourhood": {
"type": "string",
"analyzer": "peliasAdmin",
"store": "yes"
},
"neighbourhood_a": {
"type": "string",
"analyzer": "peliasAdmin",
"store": "yes"
},
"neighbourhood_id": {
"type": "string",
"analyzer": "keyword",
"store": "yes"
}
}
},
"center_point": {
"type": "geo_point",
"lat_lon": true,
"geohash": true,
"geohash_prefix": true,
"geohash_precision": 18
},
"shape": {
"type": "geo_shape",
"tree": "quadtree",
"tree_levels": "20"
},
"bounding_box": {
"type": "string",
"index": "no",
"store": "yes"
},
"source_id": {
"type": "string",
"analyzer": "keyword",
"store": "yes"
},
"category": {
"type": "string",
"analyzer": "keyword",
"store": "yes"
},
"population": {
"type": "long",
"null_value": 0
},
"popularity": {
"type": "long",
"null_value": 0
}
},
"dynamic_templates": [{
"nameGram": {
"path_match": "name.*",
"match_mapping_type": "string",
"mapping": {
"type": "string",
"analyzer": "peliasIndexOneEdgeGram",
"fielddata": {
"loading": "eager_global_ordinals"
}
}
}
}, {
"phrase": {
"path_match": "phrase.*",
"match_mapping_type": "string",
"mapping": {
"type": "string",
"analyzer": "peliasPhrase",
"fielddata": {
"loading": "eager_global_ordinals"
}
}
}
}],
"_source": {
"excludes": [
"shape",
"phrase"
]
},
"_all": {
"enabled": false
},
"dynamic": "true"
},
"country": {
"properties": {
"source": {
"type": "string",
"analyzer": "keyword",
"store": "yes"
},
"layer": {
"type": "string",
"analyzer": "keyword",
"store": "yes"
},
"alpha3": {
"type": "string",
"analyzer": "peliasAdmin",
"store": "yes"
},
"name": {
"type": "object",
"dynamic": true
},
"phrase": {
"type": "object",
"dynamic": true
},
"address_parts": {
"type": "object",
"dynamic": true,
"properties": {
"name": {
"type": "string",
"analyzer": "keyword"
},
"number": {
"type": "string",
"analyzer": "peliasHousenumber"
},
"street": {
"type": "string",
"analyzer": "peliasStreet"
},
"zip": {
"type": "string",
"analyzer": "peliasZip"
}
}
},
"parent": {
"type": "object",
"dynamic": true,
"properties": {
"country": {
"type": "string",
"analyzer": "peliasAdmin",
"store": "yes"
},
"country_a": {
"type": "string",
"analyzer": "peliasAdmin",
"store": "yes"
},
"country_id": {
"type": "string",
"analyzer": "keyword",
"store": "yes"
},
"macroregion": {
"type": "string",
"analyzer": "peliasAdmin",
"store": "yes"
},
"macroregion_a": {
"type": "string",
"analyzer": "peliasAdmin",
"store": "yes"
},
"macroregion_id": {
"type": "string",
"analyzer": "keyword",
"store": "yes"
},
"region": {
"type": "string",
"analyzer": "peliasAdmin",
"store": "yes"
},
"region_a": {
"type": "string",
"analyzer": "peliasAdmin",
"store": "yes"
},
"region_id": {
"type": "string",
"analyzer": "keyword",
"store": "yes"
},
"macrocounty": {
"type": "string",
"analyzer": "peliasAdmin",
"store": "yes"
},
"macrocounty_a": {
"type": "string",
"analyzer": "peliasAdmin",
"store": "yes"
},
"macrocounty_id": {
"type": "string",
"analyzer": "keyword",
"store": "yes"
},
"county": {
"type": "string",
"analyzer": "peliasAdmin",
"store": "yes"
},
"county_a": {
"type": "string",
"analyzer": "peliasAdmin",
"store": "yes"
},
"county_id": {
"type": "string",
"analyzer": "keyword",
"store": "yes"
},
"locality": {
"type": "string",
"analyzer": "peliasAdmin",
"store": "yes"
},
"locality_a": {
"type": "string",
"analyzer": "peliasAdmin",
"store": "yes"
},
"locality_id": {
"type": "string",
"analyzer": "keyword",
"store": "yes"
},
"borough": {
"type": "string",
"analyzer": "peliasAdmin",
"store": "yes"
},
"borough_a": {
"type": "string",
"analyzer": "peliasAdmin",
"store": "yes"
},
"borough_id": {
"type": "string",
"analyzer": "keyword",
"store": "yes"
},
"localadmin": {
"type": "string",
"analyzer": "peliasAdmin",
"store": "yes"
},
"localadmin_a": {
"type": "string",
"analyzer": "peliasAdmin",
"store": "yes"
},
"localadmin_id": {
"type": "string",
"analyzer": "keyword",
"store": "yes"
},
"neighbourhood": {
"type": "string",
"analyzer": "peliasAdmin",
"store": "yes"
},
"neighbourhood_a": {
"type": "string",
"analyzer": "peliasAdmin",
"store": "yes"
},
"neighbourhood_id": {
"type": "string",
"analyzer": "keyword",
"store": "yes"
}
}
},
"center_point": {
"type": "geo_point",
"lat_lon": true,
"geohash": true,
"geohash_prefix": true,
"geohash_precision": 18
},
"shape": {
"type": "geo_shape",
"tree": "quadtree",
"tree_levels": "20"
},
"bounding_box": {
"type": "string",
"index": "no",
"store": "yes"
},
"source_id": {
"type": "string",
"analyzer": "keyword",
"store": "yes"
},
"category": {
"type": "string",
"analyzer": "keyword",
"store": "yes"
},
"population": {
"type": "long",
"null_value": 0
},
"popularity": {
"type": "long",
"null_value": 0
}
},
"dynamic_templates": [{
"nameGram": {
"path_match": "name.*",
"match_mapping_type": "string",
"mapping": {
"type": "string",
"analyzer": "peliasIndexOneEdgeGram",
"fielddata": {
"loading": "eager_global_ordinals"
}
}
}
}, {
"phrase": {
"path_match": "phrase.*",
"match_mapping_type": "string",
"mapping": {
"type": "string",
"analyzer": "peliasPhrase",
"fielddata": {
"loading": "eager_global_ordinals"
}
}
}
}],
"_source": {
"excludes": [
"shape",
"phrase"
]
},
"_all": {
"enabled": false
},
"dynamic": "true"
},
"macroregion": {
"properties": {
"source": {
"type": "string",
"analyzer": "keyword",
"store": "yes"
},
"layer": {
"type": "string",
"analyzer": "keyword",
"store": "yes"
},
"alpha3": {
"type": "string",
"analyzer": "peliasAdmin",
"store": "yes"
},
"name": {
"type": "object",
"dynamic": true
},
"phrase": {
"type": "object",
"dynamic": true
},
"address_parts": {
"type": "object",
"dynamic": true,
"properties": {
"name": {
"type": "string",
"analyzer": "keyword"
},
"number": {
"type": "string",
"analyzer": "peliasHousenumber"
},
"street": {
"type": "string",
"analyzer": "peliasStreet"
},
"zip": {
"type": "string",
"analyzer": "peliasZip"
}
}
},
"parent": {
"type": "object",
"dynamic": true,
"properties": {
"country": {
"type": "string",
"analyzer": "peliasAdmin",
"store": "yes"
},
"country_a": {
"type": "string",
"analyzer": "peliasAdmin",
"store": "yes"
},
"country_id": {
"type": "string",
"analyzer": "keyword",
"store": "yes"
},
"macroregion": {
"type": "string",
"analyzer": "peliasAdmin",
"store": "yes"
},
"macroregion_a": {
"type": "string",
"analyzer": "peliasAdmin",
"store": "yes"
},
"macroregion_id": {
"type": "string",
"analyzer": "keyword",
"store": "yes"
},
"region": {
"type": "string",
"analyzer": "peliasAdmin",
"store": "yes"
},
"region_a": {
"type": "string",
"analyzer": "peliasAdmin",
"store": "yes"
},
"region_id": {
"type": "string",
"analyzer": "keyword",
"store": "yes"
},
"macrocounty": {
"type": "string",
"analyzer": "peliasAdmin",
"store": "yes"
},
"macrocounty_a": {
"type": "string",
"analyzer": "peliasAdmin",
"store": "yes"
},
"macrocounty_id": {
"type": "string",
"analyzer": "keyword",
"store": "yes"
},
"county": {
"type": "string",
"analyzer": "peliasAdmin",
"store": "yes"
},
"county_a": {
"type": "string",
"analyzer": "peliasAdmin",
"store": "yes"
},
"county_id": {
"type": "string",
"analyzer": "keyword",
"store": "yes"
},
"locality": {
"type": "string",
"analyzer": "peliasAdmin",
"store": "yes"
},
"locality_a": {
"type": "string",
"analyzer": "peliasAdmin",
"store": "yes"
},
"locality_id": {
"type": "string",
"analyzer": "keyword",
"store": "yes"
},
"borough": {
"type": "string",
"analyzer": "peliasAdmin",
"store": "yes"
},
"borough_a": {
"type": "string",
"analyzer": "peliasAdmin",
"store": "yes"
},
"borough_id": {
"type": "string",
"analyzer": "keyword",
"store": "yes"
},
"localadmin": {
"type": "string",
"analyzer": "peliasAdmin",
"store": "yes"
},
"localadmin_a": {
"type": "string",
"analyzer": "peliasAdmin",
"store": "yes"
},
"localadmin_id": {
"type": "string",
"analyzer": "keyword",
"store": "yes"
},
"neighbourhood": {
"type": "string",
"analyzer": "peliasAdmin",
"store": "yes"
},
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment