Created
December 18, 2015 13:46
-
-
Save riordan/81849cd554043a3d5cfe to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
{ | |
"cells": [ | |
{ | |
"cell_type": "code", | |
"execution_count": 30, | |
"metadata": { | |
"collapsed": true | |
}, | |
"outputs": [], | |
"source": [ | |
"from postal.expand import expand_address\n", | |
"from postal.parser import parse_address\n", | |
"import json\n", | |
"import glob" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 29, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [], | |
"source": [ | |
"def expandparse(query):\n", | |
" return map(parse_address,expand_address(query))\n", | |
"\n", | |
"def print_autocomplete(query):\n", | |
" sofar = \"\"\n", | |
" for char in query:\n", | |
" sofar += char\n", | |
" print(sofar)\n", | |
" print(expandparse(sofar))\n", | |
" print('\\n')\n", | |
" " | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 54, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [ | |
{ | |
"name": "stdout", | |
"output_type": "stream", | |
"text": [ | |
"TEST SET: labels\n", | |
"TEST: San Francisco, San Francisco County, CA\n", | |
"S\n", | |
"[[(u'san', u'road')], [(u'south', u'road')], [(u's', u'road')]]\n", | |
"\n", | |
"\n", | |
"Sa\n", | |
"[[(u'southern', u'house'), (u'australia', u'country')]]\n", | |
"\n", | |
"\n", | |
"San\n", | |
"[[(u'san', u'road')]]\n", | |
"\n", | |
"\n", | |
"San \n", | |
"[[(u'san', u'road')]]\n", | |
"\n", | |
"\n", | |
"San F\n", | |
"[[(u'san', u'road'), (u'flat', u'house')]]\n", | |
"\n", | |
"\n", | |
"San Fr\n", | |
"[[(u'san father', u'road')], [(u'san frontage', u'road')]]\n", | |
"\n", | |
"\n", | |
"San Fra\n", | |
"[[(u'san', u'road'), (u'fra', u'house')]]\n", | |
"\n", | |
"\n", | |
"San Fran\n", | |
"[[(u'san fran', u'road')]]\n", | |
"\n", | |
"\n", | |
"San Franc\n", | |
"[[(u'san franc', u'road')]]\n", | |
"\n", | |
"\n", | |
"San Franci\n", | |
"[[(u'san franci', u'road')]]\n", | |
"\n", | |
"\n", | |
"San Francis\n", | |
"[[(u'san francis', u'house')]]\n", | |
"\n", | |
"\n", | |
"San Francisc\n", | |
"[[(u'san francisc', u'house')]]\n", | |
"\n", | |
"\n", | |
"San Francisco\n", | |
"[[(u'san francisco', u'city')]]\n", | |
"\n", | |
"\n", | |
"San Francisco,\n", | |
"[[(u'san francisco', u'city')]]\n", | |
"\n", | |
"\n", | |
"San Francisco, \n", | |
"[[(u'san francisco', u'city')]]\n", | |
"\n", | |
"\n", | |
"San Francisco, S\n", | |
"[[(u'san francisco san', u'road')], [(u'san', u'city'), (u'francisco south', u'road')], [(u'san francisco s', u'road')]]\n", | |
"\n", | |
"\n", | |
"San Francisco, Sa\n", | |
"[[(u'san francisco southern', u'road'), (u'australia', u'country')]]\n", | |
"\n", | |
"\n", | |
"San Francisco, San\n", | |
"[[(u'san francisco san', u'road')]]\n", | |
"\n", | |
"\n", | |
"San Francisco, San \n", | |
"[[(u'san francisco san', u'road')]]\n", | |
"\n", | |
"\n", | |
"San Francisco, San F\n", | |
"[[(u'san francisco san flat', u'road')]]\n", | |
"\n", | |
"\n", | |
"San Francisco, San Fr\n", | |
"[[(u'san francisco san father', u'road')], [(u'san francisco san frontage', u'road')]]\n", | |
"\n", | |
"\n", | |
"San Francisco, San Fra\n", | |
"[[(u'san francisco san', u'road'), (u'fra', u'country')]]\n", | |
"\n", | |
"\n", | |
"San Francisco, San Fran\n", | |
"[[(u'san francisco san fran', u'road')]]\n", | |
"\n", | |
"\n", | |
"San Francisco, San Franc\n", | |
"[[(u'san francisco san franc', u'road')]]\n", | |
"\n", | |
"\n", | |
"San Francisco, San Franci\n", | |
"[[(u'san francisco san franci', u'road')]]\n", | |
"\n", | |
"\n", | |
"San Francisco, San Francis\n", | |
"[[(u'san francisco san francis', u'road')]]\n", | |
"\n", | |
"\n", | |
"San Francisco, San Francisc\n", | |
"[[(u'san francisco san francisc', u'road')]]\n", | |
"\n", | |
"\n", | |
"San Francisco, San Francisco\n", | |
"[[(u'san francisco', u'road'), (u'san', u'city'), (u'francisco', u'road')]]\n", | |
"\n", | |
"\n", | |
"San Francisco, San Francisco \n", | |
"[[(u'san francisco', u'road'), (u'san', u'city'), (u'francisco', u'road')]]\n", | |
"\n", | |
"\n", | |
"San Francisco, San Francisco C\n", | |
"[[(u'san francisco san francisco centre', u'road')], [(u'san francisco san francisco center', u'road')], [(u'san francisco san francisco central', u'road')]]\n", | |
"\n", | |
"\n", | |
"San Francisco, San Francisco Co\n", | |
"[[(u'san francisco', u'road'), (u'san', u'city'), (u'francisco', u'road'), (u'colorado', u'state')], [(u'san francisco san francisco', u'road'), (u'co', u'state')], [(u'san francisco san francisco', u'road'), (u'company', u'house')], [(u'san francisco san francisco', u'road'), (u'county', u'house')]]\n", | |
"\n", | |
"\n", | |
"San Francisco, San Francisco Cou\n", | |
"[[(u'san francisco san francisco cou', u'road')]]\n", | |
"\n", | |
"\n", | |
"San Francisco, San Francisco Coun\n", | |
"[[(u'san francisco', u'road'), (u'san', u'city'), (u'francisco coun', u'road')]]\n", | |
"\n", | |
"\n", | |
"San Francisco, San Francisco Count\n", | |
"[[(u'san francisco', u'road'), (u'san', u'city'), (u'francisco count', u'road')]]\n", | |
"\n", | |
"\n", | |
"San Francisco, San Francisco County\n", | |
"[[(u'san francisco san francisco', u'road'), (u'county', u'house')]]\n", | |
"\n", | |
"\n", | |
"San Francisco, San Francisco County,\n", | |
"[[(u'san francisco san francisco', u'road'), (u'county', u'house')]]\n", | |
"\n", | |
"\n", | |
"San Francisco, San Francisco County, \n", | |
"[[(u'san francisco san francisco', u'road'), (u'county', u'house')]]\n", | |
"\n", | |
"\n", | |
"San Francisco, San Francisco County, C\n", | |
"[[(u'san francisco san francisco', u'road'), (u'county centre', u'house')], [(u'san francisco san francisco county center', u'road')], [(u'san francisco san francisco', u'road'), (u'county central', u'house')]]\n", | |
"\n", | |
"\n", | |
"San Francisco, San Francisco County, CA\n", | |
"[[(u'san francisco san francisco county', u'road'), (u'california', u'state')], [(u'san francisco san francisco', u'road'), (u'county', u'state_district'), (u'ca', u'state')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: 30 West 26th Street, Manhattan, NY\n", | |
"3\n", | |
"[[(u'3', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"30\n", | |
"[[(u'30', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"30 \n", | |
"[[(u'30', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"30 W\n", | |
"[[(u'30', u'house_number'), (u'west', u'road')], [(u'30', u'house_number'), (u'w', u'house')]]\n", | |
"\n", | |
"\n", | |
"30 We\n", | |
"[[(u'30', u'house_number'), (u'warehouse', u'road')]]\n", | |
"\n", | |
"\n", | |
"30 Wes\n", | |
"[[(u'30', u'house_number'), (u'wes', u'road')]]\n", | |
"\n", | |
"\n", | |
"30 West\n", | |
"[[(u'30', u'house_number'), (u'west', u'road')]]\n", | |
"\n", | |
"\n", | |
"30 West \n", | |
"[[(u'30', u'house_number'), (u'west', u'road')]]\n", | |
"\n", | |
"\n", | |
"30 West 2\n", | |
"[[(u'30', u'house_number'), (u'west', u'road'), (u'2', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"30 West 26\n", | |
"[[(u'30', u'house_number'), (u'west 26', u'road')]]\n", | |
"\n", | |
"\n", | |
"30 West 26t\n", | |
"[[(u'30', u'house_number'), (u'west', u'road'), (u'26t', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"30 West 26th\n", | |
"[[(u'30', u'house_number'), (u'west 26th', u'road')]]\n", | |
"\n", | |
"\n", | |
"30 West 26th \n", | |
"[[(u'30', u'house_number'), (u'west 26th', u'road')]]\n", | |
"\n", | |
"\n", | |
"30 West 26th S\n", | |
"[[(u'30', u'house_number'), (u'west 26th san', u'road')], [(u'30', u'house_number'), (u'west 26th south', u'road')], [(u'30', u'house_number'), (u'west 26th s', u'road')]]\n", | |
"\n", | |
"\n", | |
"30 West 26th St\n", | |
"[[(u'30', u'house_number'), (u'west 26th saint', u'road')], [(u'30', u'house_number'), (u'west 26th street', u'road')]]\n", | |
"\n", | |
"\n", | |
"30 West 26th Str\n", | |
"[[(u'30', u'house_number'), (u'west 26th street', u'road')]]\n", | |
"\n", | |
"\n", | |
"30 West 26th Stre\n", | |
"[[(u'30', u'house_number'), (u'west 26th stre', u'road')]]\n", | |
"\n", | |
"\n", | |
"30 West 26th Stree\n", | |
"[[(u'30', u'house_number'), (u'west 26th stree', u'road')]]\n", | |
"\n", | |
"\n", | |
"30 West 26th Street\n", | |
"[[(u'30', u'house_number'), (u'west 26th street', u'road')]]\n", | |
"\n", | |
"\n", | |
"30 West 26th Street,\n", | |
"[[(u'30', u'house_number'), (u'west 26th street', u'road')]]\n", | |
"\n", | |
"\n", | |
"30 West 26th Street, \n", | |
"[[(u'30', u'house_number'), (u'west 26th street', u'road')]]\n", | |
"\n", | |
"\n", | |
"30 West 26th Street, M\n", | |
"[[(u'30', u'house_number'), (u'west 26th street', u'road'), (u'mail', u'suburb')]]\n", | |
"\n", | |
"\n", | |
"30 West 26th Street, Ma\n", | |
"[[(u'30', u'house_number'), (u'west 26th street', u'road'), (u'massachusetts', u'state')], [(u'30', u'house_number'), (u'west 26th street', u'road'), (u'ma', u'state')]]\n", | |
"\n", | |
"\n", | |
"30 West 26th Street, Man\n", | |
"[[(u'30', u'house_number'), (u'west 26th street', u'road'), (u'man', u'city')]]\n", | |
"\n", | |
"\n", | |
"30 West 26th Street, Manh\n", | |
"[[(u'30', u'house_number'), (u'west 26th street', u'road'), (u'manh', u'city')]]\n", | |
"\n", | |
"\n", | |
"30 West 26th Street, Manha\n", | |
"[[(u'30', u'house_number'), (u'west 26th street', u'road'), (u'manha', u'city')]]\n", | |
"\n", | |
"\n", | |
"30 West 26th Street, Manhat\n", | |
"[[(u'30', u'house_number'), (u'west 26th street', u'road'), (u'manhat', u'city')]]\n", | |
"\n", | |
"\n", | |
"30 West 26th Street, Manhatt\n", | |
"[[(u'30', u'house_number'), (u'west 26th street', u'road'), (u'manhatt', u'city')]]\n", | |
"\n", | |
"\n", | |
"30 West 26th Street, Manhatta\n", | |
"[[(u'30', u'house_number'), (u'west 26th street', u'road'), (u'manhatta', u'city')]]\n", | |
"\n", | |
"\n", | |
"30 West 26th Street, Manhattan\n", | |
"[[(u'30', u'house_number'), (u'west 26th street', u'road'), (u'manhattan', u'city')]]\n", | |
"\n", | |
"\n", | |
"30 West 26th Street, Manhattan,\n", | |
"[[(u'30', u'house_number'), (u'west 26th street', u'road'), (u'manhattan', u'city')]]\n", | |
"\n", | |
"\n", | |
"30 West 26th Street, Manhattan, \n", | |
"[[(u'30', u'house_number'), (u'west 26th street', u'road'), (u'manhattan', u'city')]]\n", | |
"\n", | |
"\n", | |
"30 West 26th Street, Manhattan, N\n", | |
"[[(u'30', u'house_number'), (u'west 26th street', u'road'), (u'manhattan north', u'city')], [(u'30', u'house_number'), (u'west 26th street', u'road'), (u'manhattan', u'city'), (u'n', u'road')]]\n", | |
"\n", | |
"\n", | |
"30 West 26th Street, Manhattan, NY\n", | |
"[[(u'30', u'house_number'), (u'west 26th street', u'road'), (u'manhattan', u'city_district'), (u'new york', u'state')], [(u'30', u'house_number'), (u'west 26th street', u'road'), (u'manhattan', u'state_district'), (u'ny', u'state')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: New South Wales, Australia\n", | |
"N\n", | |
"[[(u'north', u'road')], [(u'n', u'road')]]\n", | |
"\n", | |
"\n", | |
"Ne\n", | |
"[[(u'ne', u'road')], [(u'northeast', u'road')], [(u'nebraska', u'state')]]\n", | |
"\n", | |
"\n", | |
"New\n", | |
"[[(u'new', u'house')]]\n", | |
"\n", | |
"\n", | |
"New \n", | |
"[[(u'new', u'house')]]\n", | |
"\n", | |
"\n", | |
"New S\n", | |
"[[(u'new s', u'house')]]\n", | |
"\n", | |
"\n", | |
"New So\n", | |
"[[(u'new so', u'house')]]\n", | |
"\n", | |
"\n", | |
"New Sou\n", | |
"[[(u'new', u'road'), (u'sou', u'house')]]\n", | |
"\n", | |
"\n", | |
"New Sout\n", | |
"[[(u'new sout', u'house')]]\n", | |
"\n", | |
"\n", | |
"New South\n", | |
"[[(u'new', u'house'), (u'south', u'road')]]\n", | |
"\n", | |
"\n", | |
"New South \n", | |
"[[(u'new', u'house'), (u'south', u'road')]]\n", | |
"\n", | |
"\n", | |
"New South W\n", | |
"[[]]\n", | |
"\n", | |
"\n", | |
"New South Wa\n", | |
"[[]]\n", | |
"\n", | |
"\n", | |
"New South Wal\n", | |
"[[]]\n", | |
"\n", | |
"\n", | |
"New South Wale\n", | |
"[[]]\n", | |
"\n", | |
"\n", | |
"New South Wales\n", | |
"[[(u'new south wales', u'state')]]\n", | |
"\n", | |
"\n", | |
"New South Wales,\n", | |
"[[(u'new south wales', u'state')]]\n", | |
"\n", | |
"\n", | |
"New South Wales, \n", | |
"[[(u'new south wales', u'state')]]\n", | |
"\n", | |
"\n", | |
"New South Wales, A\n", | |
"[[(u'new south wales', u'state'), (u'a', u'postcode')]]\n", | |
"\n", | |
"\n", | |
"New South Wales, Au\n", | |
"[[(u'new south wales', u'state'), (u'au', u'house')]]\n", | |
"\n", | |
"\n", | |
"New South Wales, Aus\n", | |
"[[(u'new south wales', u'state'), (u'aus', u'country')]]\n", | |
"\n", | |
"\n", | |
"New South Wales, Aust\n", | |
"[[(u'new south wales', u'state'), (u'aust', u'postcode')]]\n", | |
"\n", | |
"\n", | |
"New South Wales, Austr\n", | |
"[[(u'new south wales', u'state'), (u'austr', u'house')]]\n", | |
"\n", | |
"\n", | |
"New South Wales, Austra\n", | |
"[[(u'new south wales', u'state'), (u'austra', u'postcode')]]\n", | |
"\n", | |
"\n", | |
"New South Wales, Austral\n", | |
"[[(u'new south wales', u'state'), (u'austral', u'postcode')]]\n", | |
"\n", | |
"\n", | |
"New South Wales, Australi\n", | |
"[[(u'new south wales', u'state'), (u'australi', u'country')]]\n", | |
"\n", | |
"\n", | |
"New South Wales, Australia\n", | |
"[[(u'new south wales', u'state'), (u'australia', u'country')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: California, CA\n", | |
"C\n", | |
"[[(u'centre', u'house')], [(u'center', u'house')], [(u'central', u'house')]]\n", | |
"\n", | |
"\n", | |
"Ca\n", | |
"[[(u'california', u'house')], [(u'ca', u'country')]]\n", | |
"\n", | |
"\n", | |
"Cal\n", | |
"[[(u'cal', u'house')]]\n", | |
"\n", | |
"\n", | |
"Cali\n", | |
"[[(u'cali', u'city')]]\n", | |
"\n", | |
"\n", | |
"Calif\n", | |
"[[(u'calif', u'house')]]\n", | |
"\n", | |
"\n", | |
"Califo\n", | |
"[[(u'califo', u'house')]]\n", | |
"\n", | |
"\n", | |
"Califor\n", | |
"[[(u'califor', u'house')]]\n", | |
"\n", | |
"\n", | |
"Californ\n", | |
"[[(u'californ', u'house')]]\n", | |
"\n", | |
"\n", | |
"Californi\n", | |
"[[(u'californi', u'house')]]\n", | |
"\n", | |
"\n", | |
"California\n", | |
"[[(u'california', u'house')]]\n", | |
"\n", | |
"\n", | |
"California,\n", | |
"[[(u'california', u'house')]]\n", | |
"\n", | |
"\n", | |
"California, \n", | |
"[[(u'california', u'house')]]\n", | |
"\n", | |
"\n", | |
"California, C\n", | |
"[[(u'california centre', u'house')], [(u'california center', u'house')], [(u'california central', u'house')]]\n", | |
"\n", | |
"\n", | |
"California, CA\n", | |
"[[(u'california', u'city'), (u'california', u'state')], [(u'california', u'state'), (u'ca', u'country')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: West Bengal, India\n", | |
"W\n", | |
"[[(u'west', u'city_district')], [(u'w', u'house')]]\n", | |
"\n", | |
"\n", | |
"We\n", | |
"[[(u'warehouse', u'house')]]\n", | |
"\n", | |
"\n", | |
"Wes\n", | |
"[[(u'wes', u'road')]]\n", | |
"\n", | |
"\n", | |
"West\n", | |
"[[(u'west', u'city_district')]]\n", | |
"\n", | |
"\n", | |
"West \n", | |
"[[(u'west', u'city_district')]]\n", | |
"\n", | |
"\n", | |
"West B\n", | |
"[[(u'west', u'road'), (u'b', u'house')]]\n", | |
"\n", | |
"\n", | |
"West Be\n", | |
"[[(u'west', u'road'), (u'be', u'country')]]\n", | |
"\n", | |
"\n", | |
"West Ben\n", | |
"[[(u'west ben', u'road')]]\n", | |
"\n", | |
"\n", | |
"West Beng\n", | |
"[[(u'west', u'road'), (u'beng', u'suburb')]]\n", | |
"\n", | |
"\n", | |
"West Benga\n", | |
"[[(u'west benga', u'road')]]\n", | |
"\n", | |
"\n", | |
"West Bengal\n", | |
"[[(u'west bengal', u'state')]]\n", | |
"\n", | |
"\n", | |
"West Bengal,\n", | |
"[[(u'west bengal', u'state')]]\n", | |
"\n", | |
"\n", | |
"West Bengal, \n", | |
"[[(u'west bengal', u'state')]]\n", | |
"\n", | |
"\n", | |
"West Bengal, I\n", | |
"[[(u'west bengal', u'state'), (u'interstate', u'suburb')], [(u'west bengal', u'state'), (u'island', u'country')]]\n", | |
"\n", | |
"\n", | |
"West Bengal, In\n", | |
"[[(u'west bengal', u'state'), (u'in', u'country')], [(u'west bengal indiana', u'state')]]\n", | |
"\n", | |
"\n", | |
"West Bengal, Ind\n", | |
"[[(u'west bengal', u'state'), (u'ind', u'country')]]\n", | |
"\n", | |
"\n", | |
"West Bengal, Indi\n", | |
"[[(u'west bengal indi', u'state')]]\n", | |
"\n", | |
"\n", | |
"West Bengal, India\n", | |
"[[(u'west bengal', u'state'), (u'india', u'country')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: North West, Singapore\n", | |
"N\n", | |
"[[(u'north', u'road')], [(u'n', u'road')]]\n", | |
"\n", | |
"\n", | |
"No\n", | |
"[[(u'number', u'house')]]\n", | |
"\n", | |
"\n", | |
"Nor\n", | |
"[[(u'nor', u'country')]]\n", | |
"\n", | |
"\n", | |
"Nort\n", | |
"[[(u'north', u'road')]]\n", | |
"\n", | |
"\n", | |
"North\n", | |
"[[(u'north', u'road')]]\n", | |
"\n", | |
"\n", | |
"North \n", | |
"[[(u'north', u'road')]]\n", | |
"\n", | |
"\n", | |
"North W\n", | |
"[[(u'northwest', u'state')]]\n", | |
"\n", | |
"\n", | |
"North We\n", | |
"[[(u'north', u'road'), (u'warehouse', u'house')]]\n", | |
"\n", | |
"\n", | |
"North Wes\n", | |
"[[(u'north wes', u'road')]]\n", | |
"\n", | |
"\n", | |
"North West\n", | |
"[[(u'northwest', u'state')]]\n", | |
"\n", | |
"\n", | |
"North West,\n", | |
"[[(u'northwest', u'state')]]\n", | |
"\n", | |
"\n", | |
"North West, \n", | |
"[[(u'northwest', u'state')]]\n", | |
"\n", | |
"\n", | |
"North West, S\n", | |
"[[(u'northwest', u'suburb'), (u'san', u'road')], [(u'northwest south', u'road')], [(u'northwest s', u'road')]]\n", | |
"\n", | |
"\n", | |
"North West, Si\n", | |
"[[(u'northwest', u'road'), (u'si', u'country')]]\n", | |
"\n", | |
"\n", | |
"North West, Sin\n", | |
"[[(u'northwest', u'road'), (u'sin', u'suburb')]]\n", | |
"\n", | |
"\n", | |
"North West, Sing\n", | |
"[[(u'northwest', u'road'), (u'sing', u'house')]]\n", | |
"\n", | |
"\n", | |
"North West, Singa\n", | |
"[[(u'northwest', u'road'), (u'singa', u'suburb')]]\n", | |
"\n", | |
"\n", | |
"North West, Singap\n", | |
"[[(u'northwest singap', u'road')]]\n", | |
"\n", | |
"\n", | |
"North West, Singapo\n", | |
"[[(u'northwest singapo', u'road')]]\n", | |
"\n", | |
"\n", | |
"North West, Singapor\n", | |
"[[(u'northwest singapor', u'road')]]\n", | |
"\n", | |
"\n", | |
"North West, Singapore\n", | |
"[[(u'northwest', u'road'), (u'singapore', u'city')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: Arbil, Iraq\n", | |
"A\n", | |
"[[(u'a', u'road')]]\n", | |
"\n", | |
"\n", | |
"Ar\n", | |
"[[(u'ar', u'state')], [(u'arkansas', u'state')]]\n", | |
"\n", | |
"\n", | |
"Arb\n", | |
"[[(u'arb', u'house')]]\n", | |
"\n", | |
"\n", | |
"Arbi\n", | |
"[[(u'arbi', u'house')]]\n", | |
"\n", | |
"\n", | |
"Arbil\n", | |
"[[(u'arbil', u'road')]]\n", | |
"\n", | |
"\n", | |
"Arbil,\n", | |
"[[(u'arbil', u'road')]]\n", | |
"\n", | |
"\n", | |
"Arbil, \n", | |
"[[(u'arbil', u'road')]]\n", | |
"\n", | |
"\n", | |
"Arbil, I\n", | |
"[[(u'arbil', u'house_number'), (u'interstate', u'road')], [(u'arbil island', u'road')]]\n", | |
"\n", | |
"\n", | |
"Arbil, Ir\n", | |
"[[(u'arbil', u'house'), (u'ir', u'road')]]\n", | |
"\n", | |
"\n", | |
"Arbil, Ira\n", | |
"[[(u'arbil', u'house_number'), (u'ira', u'road')]]\n", | |
"\n", | |
"\n", | |
"Arbil, Iraq\n", | |
"[[(u'arbil', u'road'), (u'iraq', u'house')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: Madrid, Spain\n", | |
"M\n", | |
"[[(u'mail', u'road')]]\n", | |
"\n", | |
"\n", | |
"Ma\n", | |
"[[(u'massachusetts', u'state')], [(u'ma', u'house')]]\n", | |
"\n", | |
"\n", | |
"Mad\n", | |
"[[(u'mad', u'house')]]\n", | |
"\n", | |
"\n", | |
"Madr\n", | |
"[[(u'madr', u'house')]]\n", | |
"\n", | |
"\n", | |
"Madri\n", | |
"[[(u'madri', u'house')]]\n", | |
"\n", | |
"\n", | |
"Madrid\n", | |
"[[(u'madrid', u'city')]]\n", | |
"\n", | |
"\n", | |
"Madrid,\n", | |
"[[(u'madrid', u'city')]]\n", | |
"\n", | |
"\n", | |
"Madrid, \n", | |
"[[(u'madrid', u'city')]]\n", | |
"\n", | |
"\n", | |
"Madrid, S\n", | |
"[[(u'madrid san', u'road')], [(u'madrid', u'city'), (u'south', u'house')], [(u'madrid s', u'road')]]\n", | |
"\n", | |
"\n", | |
"Madrid, Sp\n", | |
"[[(u'madrid', u'city'), (u'sole proprietorship', u'house')]]\n", | |
"\n", | |
"\n", | |
"Madrid, Spa\n", | |
"[[(u'madrid spa', u'house')]]\n", | |
"\n", | |
"\n", | |
"Madrid, Spai\n", | |
"[[(u'madrid spai', u'house')]]\n", | |
"\n", | |
"\n", | |
"Madrid, Spain\n", | |
"[[(u'madrid', u'city'), (u'spain', u'country')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: 1 Main St, Dungannon, United Kingdom\n", | |
"1\n", | |
"[[(u'1', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"1 \n", | |
"[[(u'1', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"1 M\n", | |
"[[(u'1', u'house_number'), (u'mail', u'road')]]\n", | |
"\n", | |
"\n", | |
"1 Ma\n", | |
"[[(u'1', u'house_number'), (u'massachusetts', u'state')], [(u'1', u'house_number'), (u'ma', u'road')]]\n", | |
"\n", | |
"\n", | |
"1 Mai\n", | |
"[[(u'1 mai', u'road')]]\n", | |
"\n", | |
"\n", | |
"1 Main\n", | |
"[[(u'1', u'house_number'), (u'main', u'road')]]\n", | |
"\n", | |
"\n", | |
"1 Main \n", | |
"[[(u'1', u'house_number'), (u'main', u'road')]]\n", | |
"\n", | |
"\n", | |
"1 Main S\n", | |
"[[(u'1', u'house_number'), (u'main san', u'road')], [(u'1', u'house_number'), (u'main south', u'road')], [(u'1', u'house_number'), (u'main s', u'road')]]\n", | |
"\n", | |
"\n", | |
"1 Main St\n", | |
"[[(u'1', u'house_number'), (u'main saint', u'road')], [(u'1', u'house_number'), (u'main street', u'road')]]\n", | |
"\n", | |
"\n", | |
"1 Main St,\n", | |
"[[(u'1', u'house_number'), (u'main saint', u'road')], [(u'1', u'house_number'), (u'main street', u'road')]]\n", | |
"\n", | |
"\n", | |
"1 Main St, \n", | |
"[[(u'1', u'house_number'), (u'main saint', u'road')], [(u'1', u'house_number'), (u'main street', u'road')]]\n", | |
"\n", | |
"\n", | |
"1 Main St, D\n", | |
"[[(u'1', u'house_number'), (u'main saint d', u'road')], [(u'1', u'house_number'), (u'main saint', u'road'), (u'500', u'house_number')], [(u'1', u'house_number'), (u'main street d', u'road')], [(u'1', u'house_number'), (u'main street', u'road'), (u'500', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"1 Main St, Du\n", | |
"[[(u'1', u'house_number'), (u'main saint du', u'road')], [(u'1', u'house_number'), (u'main street du', u'road')]]\n", | |
"\n", | |
"\n", | |
"1 Main St, Dun\n", | |
"[[(u'1', u'house_number'), (u'main saint dun', u'road')], [(u'1', u'house_number'), (u'main street dun', u'road')]]\n", | |
"\n", | |
"\n", | |
"1 Main St, Dung\n", | |
"[[(u'1', u'house_number'), (u'main saint', u'road'), (u'dung', u'city')], [(u'1', u'house_number'), (u'main street', u'road'), (u'dung', u'city')]]\n", | |
"\n", | |
"\n", | |
"1 Main St, Dunga\n", | |
"[[(u'1', u'house_number'), (u'main saint', u'road'), (u'dunga', u'city')], [(u'1', u'house_number'), (u'main street', u'road'), (u'dunga', u'city')]]\n", | |
"\n", | |
"\n", | |
"1 Main St, Dungan\n", | |
"[[(u'1', u'house_number'), (u'main saint dungan', u'road')], [(u'1', u'house_number'), (u'main street', u'road'), (u'dungan', u'city')]]\n", | |
"\n", | |
"\n", | |
"1 Main St, Dungann\n", | |
"[[(u'1', u'house_number'), (u'main saint dungann', u'road')], [(u'1', u'house_number'), (u'main street', u'road'), (u'dungann', u'city')]]\n", | |
"\n", | |
"\n", | |
"1 Main St, Dunganno\n", | |
"[[(u'1', u'house_number'), (u'main saint dunganno', u'road')], [(u'1', u'house_number'), (u'main street', u'road'), (u'dunganno', u'city')]]\n", | |
"\n", | |
"\n", | |
"1 Main St, Dungannon\n", | |
"[[(u'1', u'house_number'), (u'main saint', u'road'), (u'dungannon', u'city')], [(u'1', u'house_number'), (u'main street', u'road'), (u'dungannon', u'city')]]\n", | |
"\n", | |
"\n", | |
"1 Main St, Dungannon,\n", | |
"[[(u'1', u'house_number'), (u'main saint', u'road'), (u'dungannon', u'city')], [(u'1', u'house_number'), (u'main street', u'road'), (u'dungannon', u'city')]]\n", | |
"\n", | |
"\n", | |
"1 Main St, Dungannon, \n", | |
"[[(u'1', u'house_number'), (u'main saint', u'road'), (u'dungannon', u'city')], [(u'1', u'house_number'), (u'main street', u'road'), (u'dungannon', u'city')]]\n", | |
"\n", | |
"\n", | |
"1 Main St, Dungannon, U\n", | |
"[[(u'1', u'house_number'), (u'main saint', u'road'), (u'dungannon u', u'house')], [(u'1', u'house_number'), (u'main street', u'road'), (u'dungannon', u'city'), (u'u', u'house')]]\n", | |
"\n", | |
"\n", | |
"1 Main St, Dungannon, Un\n", | |
"[[(u'1', u'house_number'), (u'main saint', u'road'), (u'dungannon', u'house'), (u'unit', u'house_number')], [(u'1', u'house_number'), (u'main saint', u'road'), (u'dungannon union', u'house')], [(u'1', u'house_number'), (u'main street', u'road'), (u'dungannon', u'city'), (u'unit', u'house')], [(u'1', u'house_number'), (u'main street', u'road'), (u'dungannon union', u'city')]]\n", | |
"\n", | |
"\n", | |
"1 Main St, Dungannon, Uni\n", | |
"[[(u'1', u'house_number'), (u'main saint', u'road'), (u'dungannon university', u'house')], [(u'1', u'house_number'), (u'main street', u'road'), (u'dungannon university', u'house')]]\n", | |
"\n", | |
"\n", | |
"1 Main St, Dungannon, Unit\n", | |
"[[(u'1', u'house_number'), (u'main saint', u'road'), (u'dungannon', u'house'), (u'unit', u'house_number')], [(u'1', u'house_number'), (u'main street', u'road'), (u'dungannon', u'city'), (u'unit', u'house')]]\n", | |
"\n", | |
"\n", | |
"1 Main St, Dungannon, Unite\n", | |
"[[(u'1', u'house_number'), (u'main saint', u'road'), (u'dungannon', u'city'), (u'unite', u'house')], [(u'1', u'house_number'), (u'main street', u'road'), (u'dungannon', u'city'), (u'unite', u'house')]]\n", | |
"\n", | |
"\n", | |
"1 Main St, Dungannon, United\n", | |
"[[(u'1', u'house_number'), (u'main saint', u'road'), (u'dungannon', u'city'), (u'united', u'house')], [(u'1', u'house_number'), (u'main street', u'road'), (u'dungannon', u'city'), (u'united', u'house')]]\n", | |
"\n", | |
"\n", | |
"1 Main St, Dungannon, United \n", | |
"[[(u'1', u'house_number'), (u'main saint', u'road'), (u'dungannon', u'city'), (u'united', u'house')], [(u'1', u'house_number'), (u'main street', u'road'), (u'dungannon', u'city'), (u'united', u'house')]]\n", | |
"\n", | |
"\n", | |
"1 Main St, Dungannon, United K\n", | |
"[[(u'1', u'house_number'), (u'main saint', u'road'), (u'dungannon', u'city'), (u'united', u'house'), (u'k', u'country')], [(u'1', u'house_number'), (u'main street', u'road'), (u'dungannon', u'city'), (u'united', u'house'), (u'k', u'country')]]\n", | |
"\n", | |
"\n", | |
"1 Main St, Dungannon, United Ki\n", | |
"[[(u'1', u'house_number'), (u'main saint', u'road'), (u'dungannon', u'city'), (u'united ki', u'house')], [(u'1', u'house_number'), (u'main street', u'road'), (u'dungannon', u'city'), (u'united ki', u'house')]]\n", | |
"\n", | |
"\n", | |
"1 Main St, Dungannon, United Kin\n", | |
"[[(u'1', u'house_number'), (u'main saint', u'road'), (u'dungannon', u'city'), (u'united kin', u'house')], [(u'1', u'house_number'), (u'main street', u'road'), (u'dungannon', u'city'), (u'united kin', u'house')]]\n", | |
"\n", | |
"\n", | |
"1 Main St, Dungannon, United King\n", | |
"[[(u'1', u'house_number'), (u'main saint', u'road'), (u'dungannon', u'city'), (u'united king', u'house')], [(u'1', u'house_number'), (u'main street', u'road'), (u'dungannon', u'city'), (u'united king', u'house')]]\n", | |
"\n", | |
"\n", | |
"1 Main St, Dungannon, United Kingd\n", | |
"[[(u'1', u'house_number'), (u'main saint', u'road'), (u'dungannon', u'city'), (u'united kingd', u'house')], [(u'1', u'house_number'), (u'main street', u'road'), (u'dungannon', u'city'), (u'united kingd', u'house')]]\n", | |
"\n", | |
"\n", | |
"1 Main St, Dungannon, United Kingdo\n", | |
"[[(u'1', u'house_number'), (u'main saint', u'road'), (u'dungannon', u'city'), (u'united kingdo', u'house')], [(u'1', u'house_number'), (u'main street', u'road'), (u'dungannon', u'city'), (u'united kingdo', u'house')]]\n", | |
"\n", | |
"\n", | |
"1 Main St, Dungannon, United Kingdom\n", | |
"[[(u'1', u'house_number'), (u'main saint', u'road'), (u'dungannon', u'city'), (u'united kingdom', u'country')], [(u'1', u'house_number'), (u'main street', u'road'), (u'dungannon', u'city'), (u'united kingdom', u'country')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: Hackney City Farm, Haggerston, Greater London\n", | |
"H\n", | |
"[[(u'h', u'house')]]\n", | |
"\n", | |
"\n", | |
"Ha\n", | |
"[[(u'ha', u'house')]]\n", | |
"\n", | |
"\n", | |
"Hac\n", | |
"[[(u'hac', u'house')]]\n", | |
"\n", | |
"\n", | |
"Hack\n", | |
"[[(u'hack', u'house')]]\n", | |
"\n", | |
"\n", | |
"Hackn\n", | |
"[[(u'hackn', u'house')]]\n", | |
"\n", | |
"\n", | |
"Hackne\n", | |
"[[(u'hackne', u'house')]]\n", | |
"\n", | |
"\n", | |
"Hackney\n", | |
"[[(u'hackney', u'house')]]\n", | |
"\n", | |
"\n", | |
"Hackney \n", | |
"[[(u'hackney', u'house')]]\n", | |
"\n", | |
"\n", | |
"Hackney C\n", | |
"[[(u'hackney', u'road'), (u'centre', u'house')], [(u'hackney center', u'house')], [(u'hackney central', u'suburb')]]\n", | |
"\n", | |
"\n", | |
"Hackney Ci\n", | |
"[[(u'hackney circuit', u'road')]]\n", | |
"\n", | |
"\n", | |
"Hackney Cit\n", | |
"[[(u'hackney', u'road'), (u'cit', u'house')]]\n", | |
"\n", | |
"\n", | |
"Hackney City\n", | |
"[[(u'hackney', u'city_district'), (u'city', u'house')]]\n", | |
"\n", | |
"\n", | |
"Hackney City \n", | |
"[[(u'hackney', u'city_district'), (u'city', u'house')]]\n", | |
"\n", | |
"\n", | |
"Hackney City F\n", | |
"[[(u'hackney', u'city_district'), (u'city flat', u'house')]]\n", | |
"\n", | |
"\n", | |
"Hackney City Fa\n", | |
"[[(u'hackney', u'city_district'), (u'city fa', u'house')]]\n", | |
"\n", | |
"\n", | |
"Hackney City Far\n", | |
"[[(u'hackney', u'city_district'), (u'city far', u'house')]]\n", | |
"\n", | |
"\n", | |
"Hackney City Farm\n", | |
"[[(u'hackney', u'city_district'), (u'city', u'road'), (u'farm', u'house')]]\n", | |
"\n", | |
"\n", | |
"Hackney City Farm,\n", | |
"[[(u'hackney', u'city_district'), (u'city', u'road'), (u'farm', u'house')]]\n", | |
"\n", | |
"\n", | |
"Hackney City Farm, \n", | |
"[[(u'hackney', u'city_district'), (u'city', u'road'), (u'farm', u'house')]]\n", | |
"\n", | |
"\n", | |
"Hackney City Farm, H\n", | |
"[[(u'hackney', u'city_district'), (u'city', u'road'), (u'farm', u'house'), (u'h', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"Hackney City Farm, Ha\n", | |
"[[(u'hackney', u'city_district'), (u'city', u'road'), (u'farm', u'house'), (u'ha', u'city')]]\n", | |
"\n", | |
"\n", | |
"Hackney City Farm, Hag\n", | |
"[[(u'hackney', u'city_district'), (u'city', u'road'), (u'farm', u'house'), (u'hag', u'road')]]\n", | |
"\n", | |
"\n", | |
"Hackney City Farm, Hagg\n", | |
"[[(u'hackney', u'city_district'), (u'city', u'road'), (u'farm', u'house'), (u'hagg', u'road')]]\n", | |
"\n", | |
"\n", | |
"Hackney City Farm, Hagge\n", | |
"[[(u'hackney', u'city_district'), (u'city', u'road'), (u'farm', u'house'), (u'hagge', u'city')]]\n", | |
"\n", | |
"\n", | |
"Hackney City Farm, Hagger\n", | |
"[[(u'hackney', u'city_district'), (u'city', u'road'), (u'farm', u'house'), (u'hagger', u'road')]]\n", | |
"\n", | |
"\n", | |
"Hackney City Farm, Haggers\n", | |
"[[(u'hackney', u'city_district'), (u'city', u'road'), (u'farm', u'house'), (u'haggers', u'city')]]\n", | |
"\n", | |
"\n", | |
"Hackney City Farm, Haggerst\n", | |
"[[(u'hackney', u'city_district'), (u'city', u'road'), (u'farm', u'house'), (u'haggerst', u'road')]]\n", | |
"\n", | |
"\n", | |
"Hackney City Farm, Haggersto\n", | |
"[[(u'hackney', u'city_district'), (u'city', u'road'), (u'farm', u'house'), (u'haggersto', u'road')]]\n", | |
"\n", | |
"\n", | |
"Hackney City Farm, Haggerston\n", | |
"[[(u'hackney', u'city_district'), (u'city', u'road'), (u'farm', u'house'), (u'haggerston', u'road')]]\n", | |
"\n", | |
"\n", | |
"Hackney City Farm, Haggerston,\n", | |
"[[(u'hackney', u'city_district'), (u'city', u'road'), (u'farm', u'house'), (u'haggerston', u'road')]]\n", | |
"\n", | |
"\n", | |
"Hackney City Farm, Haggerston, \n", | |
"[[(u'hackney', u'city_district'), (u'city', u'road'), (u'farm', u'house'), (u'haggerston', u'road')]]\n", | |
"\n", | |
"\n", | |
"Hackney City Farm, Haggerston, G\n", | |
"[[(u'hackney', u'city_district'), (u'city', u'road'), (u'farm', u'house'), (u'haggerston', u'house_number'), (u'ground', u'house')]]\n", | |
"\n", | |
"\n", | |
"Hackney City Farm, Haggerston, Gr\n", | |
"[[(u'hackney', u'city_district'), (u'city', u'road'), (u'farm', u'house'), (u'haggerston grove', u'road')]]\n", | |
"\n", | |
"\n", | |
"Hackney City Farm, Haggerston, Gre\n", | |
"[[(u'hackney', u'city_district'), (u'city', u'road'), (u'farm', u'house'), (u'haggerston', u'road'), (u'gre', u'city')]]\n", | |
"\n", | |
"\n", | |
"Hackney City Farm, Haggerston, Grea\n", | |
"[[(u'hackney', u'city_district'), (u'city', u'road'), (u'farm haggerston grea', u'house')]]\n", | |
"\n", | |
"\n", | |
"Hackney City Farm, Haggerston, Great\n", | |
"[[(u'hackney', u'city_district'), (u'city', u'road'), (u'farm', u'house'), (u'haggerston great', u'road')]]\n", | |
"\n", | |
"\n", | |
"Hackney City Farm, Haggerston, Greate\n", | |
"[[(u'hackney', u'city_district'), (u'city', u'road'), (u'farm', u'house'), (u'haggerston greate', u'road')]]\n", | |
"\n", | |
"\n", | |
"Hackney City Farm, Haggerston, Greater\n", | |
"[[(u'hackney', u'city_district'), (u'city', u'road'), (u'farm', u'house'), (u'haggerston', u'road'), (u'greater', u'house')]]\n", | |
"\n", | |
"\n", | |
"Hackney City Farm, Haggerston, Greater \n", | |
"[[(u'hackney', u'city_district'), (u'city', u'road'), (u'farm', u'house'), (u'haggerston', u'road'), (u'greater', u'house')]]\n", | |
"\n", | |
"\n", | |
"Hackney City Farm, Haggerston, Greater L\n", | |
"[[(u'hackney', u'city_district'), (u'city', u'road'), (u'farm', u'house'), (u'haggerston', u'road'), (u'greater level', u'house')]]\n", | |
"\n", | |
"\n", | |
"Hackney City Farm, Haggerston, Greater Lo\n", | |
"[[(u'hackney', u'city_district'), (u'city', u'road'), (u'farm', u'house'), (u'haggerston', u'road'), (u'greater lo', u'house')]]\n", | |
"\n", | |
"\n", | |
"Hackney City Farm, Haggerston, Greater Lon\n", | |
"[[(u'hackney', u'city_district'), (u'city', u'road'), (u'farm', u'house'), (u'haggerston', u'road'), (u'greater lon', u'house')]]\n", | |
"\n", | |
"\n", | |
"Hackney City Farm, Haggerston, Greater Lond\n", | |
"[[(u'hackney', u'city_district'), (u'city', u'road'), (u'farm', u'house'), (u'haggerston', u'road'), (u'greater lond', u'house')]]\n", | |
"\n", | |
"\n", | |
"Hackney City Farm, Haggerston, Greater Londo\n", | |
"[[(u'hackney', u'city_district'), (u'city', u'road'), (u'farm', u'house'), (u'haggerston', u'road'), (u'greater londo', u'house')]]\n", | |
"\n", | |
"\n", | |
"Hackney City Farm, Haggerston, Greater London\n", | |
"[[(u'hackney', u'city_district'), (u'city', u'road'), (u'farm', u'house'), (u'haggerston', u'road'), (u'greater london', u'state_district')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: 1 Grolmanstraße, Berlin, Germany\n", | |
"1\n", | |
"[[(u'1', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"1 \n", | |
"[[(u'1', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"1 G\n", | |
"[[(u'1', u'house_number'), (u'ground', u'road')]]\n", | |
"\n", | |
"\n", | |
"1 Gr\n", | |
"[[(u'1', u'house_number'), (u'grove', u'road')]]\n", | |
"\n", | |
"\n", | |
"1 Gro\n", | |
"[[(u'1', u'house_number'), (u'grove', u'road')]]\n", | |
"\n", | |
"\n", | |
"1 Grol\n", | |
"[[(u'1', u'house_number'), (u'grol', u'road')]]\n", | |
"\n", | |
"\n", | |
"1 Grolm\n", | |
"[[(u'1', u'house_number'), (u'grolm', u'road')]]\n", | |
"\n", | |
"\n", | |
"1 Grolma\n", | |
"[[(u'1', u'house_number'), (u'grolma', u'road')]]\n", | |
"\n", | |
"\n", | |
"1 Grolman\n", | |
"[[(u'1', u'house_number'), (u'grolman', u'road')]]\n", | |
"\n", | |
"\n", | |
"1 Grolmans\n", | |
"[[(u'1', u'house_number'), (u'grolmans', u'road')]]\n", | |
"\n", | |
"\n", | |
"1 Grolmanst\n", | |
"[[(u'1', u'house_number'), (u'grolmanst', u'road')]]\n", | |
"\n", | |
"\n", | |
"1 Grolmanstr\n", | |
"[[(u'1', u'house_number'), (u'grolmanstr', u'road')]]\n", | |
"\n", | |
"\n", | |
"1 Grolmanstra\n", | |
"[[(u'1', u'house_number'), (u'grolmanstra', u'road')]]\n", | |
"\n", | |
"\n", | |
"1 Grolmanstraß\n", | |
"[[(u'1', u'house_number'), (u'grolmanstrass', u'road')]]\n", | |
"\n", | |
"\n", | |
"1 Grolmanstraße\n", | |
"[[(u'1', u'house'), (u'grolmanstrasse', u'road')]]\n", | |
"\n", | |
"\n", | |
"1 Grolmanstraße,\n", | |
"[[(u'1', u'house'), (u'grolmanstrasse', u'road')]]\n", | |
"\n", | |
"\n", | |
"1 Grolmanstraße, \n", | |
"[[(u'1', u'house'), (u'grolmanstrasse', u'road')]]\n", | |
"\n", | |
"\n", | |
"1 Grolmanstraße, B\n", | |
"[[(u'1', u'house'), (u'grolmanstrasse', u'road'), (u'b', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"1 Grolmanstraße, Be\n", | |
"[[(u'1', u'house'), (u'grolmanstrasse', u'road'), (u'be', u'country')]]\n", | |
"\n", | |
"\n", | |
"1 Grolmanstraße, Ber\n", | |
"[[(u'1', u'house'), (u'grolmanstrasse ber', u'road')]]\n", | |
"\n", | |
"\n", | |
"1 Grolmanstraße, Berl\n", | |
"[[(u'1', u'house'), (u'grolmanstrasse', u'road'), (u'berl', u'house')]]\n", | |
"\n", | |
"\n", | |
"1 Grolmanstraße, Berli\n", | |
"[[(u'1', u'house'), (u'grolmanstrasse', u'road'), (u'berli', u'city')]]\n", | |
"\n", | |
"\n", | |
"1 Grolmanstraße, Berlin\n", | |
"[[(u'1', u'house'), (u'grolmanstrasse', u'road'), (u'berlin', u'city')]]\n", | |
"\n", | |
"\n", | |
"1 Grolmanstraße, Berlin,\n", | |
"[[(u'1', u'house'), (u'grolmanstrasse', u'road'), (u'berlin', u'city')]]\n", | |
"\n", | |
"\n", | |
"1 Grolmanstraße, Berlin, \n", | |
"[[(u'1', u'house'), (u'grolmanstrasse', u'road'), (u'berlin', u'city')]]\n", | |
"\n", | |
"\n", | |
"1 Grolmanstraße, Berlin, G\n", | |
"[[(u'1', u'house'), (u'grolmanstrasse', u'road'), (u'berlin ground', u'city')]]\n", | |
"\n", | |
"\n", | |
"1 Grolmanstraße, Berlin, Ge\n", | |
"[[(u'1', u'house'), (u'grolmanstrasse', u'road'), (u'berlin', u'city'), (u'ge', u'country')]]\n", | |
"\n", | |
"\n", | |
"1 Grolmanstraße, Berlin, Ger\n", | |
"[[(u'1', u'house'), (u'grolmanstrasse', u'road'), (u'berlin ger', u'city')]]\n", | |
"\n", | |
"\n", | |
"1 Grolmanstraße, Berlin, Germ\n", | |
"[[(u'1', u'house'), (u'grolmanstrasse', u'road'), (u'berlin', u'house'), (u'germ', u'country')]]\n", | |
"\n", | |
"\n", | |
"1 Grolmanstraße, Berlin, Germa\n", | |
"[[(u'1', u'house'), (u'grolmanstrasse', u'road'), (u'berlin', u'city'), (u'germa', u'house')]]\n", | |
"\n", | |
"\n", | |
"1 Grolmanstraße, Berlin, German\n", | |
"[[(u'1', u'house'), (u'grolmanstrasse', u'road'), (u'berlin german', u'city')]]\n", | |
"\n", | |
"\n", | |
"1 Grolmanstraße, Berlin, Germany\n", | |
"[[(u'1', u'house'), (u'grolmanstrasse', u'road'), (u'berlin', u'city'), (u'germany', u'country')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: New Zealand\n", | |
"N\n", | |
"[[(u'north', u'road')], [(u'n', u'road')]]\n", | |
"\n", | |
"\n", | |
"Ne\n", | |
"[[(u'ne', u'road')], [(u'northeast', u'road')], [(u'nebraska', u'state')]]\n", | |
"\n", | |
"\n", | |
"New\n", | |
"[[(u'new', u'house')]]\n", | |
"\n", | |
"\n", | |
"New \n", | |
"[[(u'new', u'house')]]\n", | |
"\n", | |
"\n", | |
"New Z\n", | |
"[[(u'new z', u'house')]]\n", | |
"\n", | |
"\n", | |
"New Ze\n", | |
"[[(u'new ze', u'house')]]\n", | |
"\n", | |
"\n", | |
"New Zea\n", | |
"[[(u'new zea', u'house')]]\n", | |
"\n", | |
"\n", | |
"New Zeal\n", | |
"[[(u'new zeal', u'house')]]\n", | |
"\n", | |
"\n", | |
"New Zeala\n", | |
"[[(u'new zeala', u'house')]]\n", | |
"\n", | |
"\n", | |
"New Zealan\n", | |
"[[(u'new zealan', u'house')]]\n", | |
"\n", | |
"\n", | |
"New Zealand\n", | |
"[[(u'new zealand', u'country')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: McDonald's, Central Singapore, Singapore\n", | |
"M\n", | |
"[[(u'mail', u'road')]]\n", | |
"\n", | |
"\n", | |
"Mc\n", | |
"[[(u'mailcenter', u'road')]]\n", | |
"\n", | |
"\n", | |
"McD\n", | |
"[[(u'mcd', u'house')], [(u'1400', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"McDo\n", | |
"[[(u'mcdo', u'house')]]\n", | |
"\n", | |
"\n", | |
"McDon\n", | |
"[[(u'mcdon', u'house')]]\n", | |
"\n", | |
"\n", | |
"McDona\n", | |
"[[(u'mcdona', u'house')]]\n", | |
"\n", | |
"\n", | |
"McDonal\n", | |
"[[(u'mcdonal', u'house')]]\n", | |
"\n", | |
"\n", | |
"McDonald\n", | |
"[[(u'mcdonald', u'house')]]\n", | |
"\n", | |
"\n", | |
"McDonald'\n", | |
"[[(u\"mcdonald '\", u'house')]]\n", | |
"\n", | |
"\n", | |
"McDonald's\n", | |
"[[(u\"mcdonald's\", u'house')]]\n", | |
"\n", | |
"\n", | |
"McDonald's,\n", | |
"[[(u\"mcdonald's\", u'house')]]\n", | |
"\n", | |
"\n", | |
"McDonald's, \n", | |
"[[(u\"mcdonald's\", u'house')]]\n", | |
"\n", | |
"\n", | |
"McDonald's, C\n", | |
"[[(u\"mcdonald's centre\", u'house')], [(u\"mcdonald's center\", u'house')], [(u\"mcdonald's central\", u'house')]]\n", | |
"\n", | |
"\n", | |
"McDonald's, Ce\n", | |
"[[(u\"mcdonald's\", u'house'), (u'cove', u'road')]]\n", | |
"\n", | |
"\n", | |
"McDonald's, Cen\n", | |
"[[(u\"mcdonald's center\", u'house')]]\n", | |
"\n", | |
"\n", | |
"McDonald's, Cent\n", | |
"[[(u\"mcdonald's cent\", u'house')]]\n", | |
"\n", | |
"\n", | |
"McDonald's, Centr\n", | |
"[[(u\"mcdonald's\", u'house'), (u'centr', u'road')]]\n", | |
"\n", | |
"\n", | |
"McDonald's, Centra\n", | |
"[[(u\"mcdonald's centra\", u'house')]]\n", | |
"\n", | |
"\n", | |
"McDonald's, Central\n", | |
"[[(u\"mcdonald's central\", u'house')]]\n", | |
"\n", | |
"\n", | |
"McDonald's, Central \n", | |
"[[(u\"mcdonald's central\", u'house')]]\n", | |
"\n", | |
"\n", | |
"McDonald's, Central S\n", | |
"[[(u\"mcdonald's central san\", u'house')], [(u\"mcdonald's central\", u'house'), (u'south', u'road')], [(u\"mcdonald's central\", u'house'), (u's', u'road')]]\n", | |
"\n", | |
"\n", | |
"McDonald's, Central Si\n", | |
"[[(u\"mcdonald's central\", u'house'), (u'si', u'country')]]\n", | |
"\n", | |
"\n", | |
"McDonald's, Central Sin\n", | |
"[[(u\"mcdonald's central sin\", u'house')]]\n", | |
"\n", | |
"\n", | |
"McDonald's, Central Sing\n", | |
"[[(u\"mcdonald's central sing\", u'house')]]\n", | |
"\n", | |
"\n", | |
"McDonald's, Central Singa\n", | |
"[[(u\"mcdonald's central singa\", u'house')]]\n", | |
"\n", | |
"\n", | |
"McDonald's, Central Singap\n", | |
"[[(u\"mcdonald's central singap\", u'house')]]\n", | |
"\n", | |
"\n", | |
"McDonald's, Central Singapo\n", | |
"[[(u\"mcdonald's central singapo\", u'house')]]\n", | |
"\n", | |
"\n", | |
"McDonald's, Central Singapor\n", | |
"[[(u\"mcdonald's central singapor\", u'house')]]\n", | |
"\n", | |
"\n", | |
"McDonald's, Central Singapore\n", | |
"[[(u\"mcdonald's\", u'house'), (u'central', u'road'), (u'singapore', u'city')]]\n", | |
"\n", | |
"\n", | |
"McDonald's, Central Singapore,\n", | |
"[[(u\"mcdonald's\", u'house'), (u'central', u'road'), (u'singapore', u'city')]]\n", | |
"\n", | |
"\n", | |
"McDonald's, Central Singapore, \n", | |
"[[(u\"mcdonald's\", u'house'), (u'central', u'road'), (u'singapore', u'city')]]\n", | |
"\n", | |
"\n", | |
"McDonald's, Central Singapore, S\n", | |
"[[(u\"mcdonald's\", u'house'), (u'central', u'road'), (u'singapore', u'house'), (u'san', u'road')], [(u\"mcdonald's\", u'house'), (u'central', u'road'), (u'singapore', u'house'), (u'south', u'road')], [(u\"mcdonald's\", u'house'), (u'central', u'road'), (u'singapore', u'house'), (u's', u'road')]]\n", | |
"\n", | |
"\n", | |
"McDonald's, Central Singapore, Si\n", | |
"[[(u\"mcdonald's\", u'house'), (u'central', u'road'), (u'singapore', u'house'), (u'si', u'country')]]\n", | |
"\n", | |
"\n", | |
"McDonald's, Central Singapore, Sin\n", | |
"[[(u\"mcdonald's\", u'house'), (u'central', u'road'), (u'singapore', u'house'), (u'sin', u'suburb')]]\n", | |
"\n", | |
"\n", | |
"McDonald's, Central Singapore, Sing\n", | |
"[[(u\"mcdonald's\", u'house'), (u'central', u'road'), (u'singapore sing', u'house')]]\n", | |
"\n", | |
"\n", | |
"McDonald's, Central Singapore, Singa\n", | |
"[[(u\"mcdonald's\", u'house'), (u'central', u'road'), (u'singapore', u'city'), (u'singa', u'country')]]\n", | |
"\n", | |
"\n", | |
"McDonald's, Central Singapore, Singap\n", | |
"[[(u\"mcdonald's\", u'house'), (u'central', u'road'), (u'singapore singap', u'house')]]\n", | |
"\n", | |
"\n", | |
"McDonald's, Central Singapore, Singapo\n", | |
"[[(u\"mcdonald's\", u'house'), (u'central', u'road'), (u'singapore singapo', u'house')]]\n", | |
"\n", | |
"\n", | |
"McDonald's, Central Singapore, Singapor\n", | |
"[[(u\"mcdonald's\", u'house'), (u'central', u'road'), (u'singapore', u'house'), (u'singapor', u'country')]]\n", | |
"\n", | |
"\n", | |
"McDonald's, Central Singapore, Singapore\n", | |
"[[(u\"mcdonald's\", u'house'), (u'central', u'road'), (u'singapore', u'city'), (u'singapore', u'country')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"====================================================================\n", | |
"\n", | |
"TEST SET: autocomplete_focus\n", | |
"TEST: DiDi dumpling\n", | |
"D\n", | |
"[[(u'd', u'house')], [(u'500', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"Di\n", | |
"[[(u'di', u'house')], [(u'501', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"DiD\n", | |
"[[(u'did', u'house')], [(u'500', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"DiDi\n", | |
"[[(u'didi', u'house')], [(u'501', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"DiDi \n", | |
"[[(u'didi', u'house')]]\n", | |
"\n", | |
"\n", | |
"DiDi d\n", | |
"[[(u'didi d', u'house')], [(u'501', u'house'), (u'500', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"DiDi du\n", | |
"[[(u'didi du', u'house')], [(u'501', u'house_number'), (u'du', u'road')]]\n", | |
"\n", | |
"\n", | |
"DiDi dum\n", | |
"[[(u'didi dum', u'house')], [(u'501', u'house_number'), (u'dum', u'road')]]\n", | |
"\n", | |
"\n", | |
"DiDi dump\n", | |
"[[(u'didi dump', u'house')], [(u'501', u'house_number'), (u'dump', u'road')]]\n", | |
"\n", | |
"\n", | |
"DiDi dumpl\n", | |
"[[(u'didi dumpl', u'house')], [(u'501', u'house_number'), (u'dumpl', u'road')]]\n", | |
"\n", | |
"\n", | |
"DiDi dumpli\n", | |
"[[(u'didi dumpli', u'house')], [(u'501', u'house_number'), (u'dumpli', u'road')]]\n", | |
"\n", | |
"\n", | |
"DiDi dumplin\n", | |
"[[(u'didi dumplin', u'house')], [(u'501', u'house_number'), (u'dumplin', u'road')]]\n", | |
"\n", | |
"\n", | |
"DiDi dumpling\n", | |
"[[(u'didi dumpling', u'house')], [(u'501', u'house_number'), (u'dumpling', u'road')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: union square\n", | |
"u\n", | |
"[[(u'u', u'house')]]\n", | |
"\n", | |
"\n", | |
"un\n", | |
"[[(u'unit', u'house')], [(u'union', u'house')]]\n", | |
"\n", | |
"\n", | |
"uni\n", | |
"[[(u'university', u'house')]]\n", | |
"\n", | |
"\n", | |
"unio\n", | |
"[[(u'unio', u'road')]]\n", | |
"\n", | |
"\n", | |
"union\n", | |
"[[(u'union', u'house')]]\n", | |
"\n", | |
"\n", | |
"union \n", | |
"[[(u'union', u'house')]]\n", | |
"\n", | |
"\n", | |
"union s\n", | |
"[[(u'union san', u'road')], [(u'union', u'house'), (u'south', u'road')], [(u'union s', u'road')]]\n", | |
"\n", | |
"\n", | |
"union sq\n", | |
"[[(u'union', u'city'), (u'square', u'road')]]\n", | |
"\n", | |
"\n", | |
"union squ\n", | |
"[[(u'union squ', u'house')]]\n", | |
"\n", | |
"\n", | |
"union squa\n", | |
"[[(u'union squa', u'house')]]\n", | |
"\n", | |
"\n", | |
"union squar\n", | |
"[[(u'union squar', u'house')]]\n", | |
"\n", | |
"\n", | |
"union square\n", | |
"[[(u'union', u'city'), (u'square', u'road')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: union square\n", | |
"u\n", | |
"[[(u'u', u'house')]]\n", | |
"\n", | |
"\n", | |
"un\n", | |
"[[(u'unit', u'house')], [(u'union', u'house')]]\n", | |
"\n", | |
"\n", | |
"uni\n", | |
"[[(u'university', u'house')]]\n", | |
"\n", | |
"\n", | |
"unio\n", | |
"[[(u'unio', u'road')]]\n", | |
"\n", | |
"\n", | |
"union\n", | |
"[[(u'union', u'house')]]\n", | |
"\n", | |
"\n", | |
"union \n", | |
"[[(u'union', u'house')]]\n", | |
"\n", | |
"\n", | |
"union s\n", | |
"[[(u'union san', u'road')], [(u'union', u'house'), (u'south', u'road')], [(u'union s', u'road')]]\n", | |
"\n", | |
"\n", | |
"union sq\n", | |
"[[(u'union', u'city'), (u'square', u'road')]]\n", | |
"\n", | |
"\n", | |
"union squ\n", | |
"[[(u'union squ', u'house')]]\n", | |
"\n", | |
"\n", | |
"union squa\n", | |
"[[(u'union squa', u'house')]]\n", | |
"\n", | |
"\n", | |
"union squar\n", | |
"[[(u'union squar', u'house')]]\n", | |
"\n", | |
"\n", | |
"union square\n", | |
"[[(u'union', u'city'), (u'square', u'road')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: hard rock cafe\n", | |
"h\n", | |
"[[(u'h', u'house')]]\n", | |
"\n", | |
"\n", | |
"ha\n", | |
"[[(u'ha', u'house')]]\n", | |
"\n", | |
"\n", | |
"har\n", | |
"[[(u'har', u'house')]]\n", | |
"\n", | |
"\n", | |
"hard\n", | |
"[[(u'hard', u'city')]]\n", | |
"\n", | |
"\n", | |
"hard \n", | |
"[[(u'hard', u'city')]]\n", | |
"\n", | |
"\n", | |
"hard r\n", | |
"[[(u'hard river', u'house')]]\n", | |
"\n", | |
"\n", | |
"hard ro\n", | |
"[[(u'hard', u'city'), (u'ro', u'country')]]\n", | |
"\n", | |
"\n", | |
"hard roc\n", | |
"[[(u'hard roc', u'house')]]\n", | |
"\n", | |
"\n", | |
"hard rock\n", | |
"[[(u'hard rock', u'house')]]\n", | |
"\n", | |
"\n", | |
"hard rock \n", | |
"[[(u'hard rock', u'house')]]\n", | |
"\n", | |
"\n", | |
"hard rock c\n", | |
"[[(u'hard rock centre', u'house')], [(u'hard rock center', u'house')], [(u'hard rock central', u'house')]]\n", | |
"\n", | |
"\n", | |
"hard rock ca\n", | |
"[[(u'hard rock california', u'house')], [(u'hard rock', u'house'), (u'ca', u'country')]]\n", | |
"\n", | |
"\n", | |
"hard rock caf\n", | |
"[[(u'hard rock caf', u'house')]]\n", | |
"\n", | |
"\n", | |
"hard rock cafe\n", | |
"[[(u'hard rock cafe', u'house')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: hard rock cafe\n", | |
"h\n", | |
"[[(u'h', u'house')]]\n", | |
"\n", | |
"\n", | |
"ha\n", | |
"[[(u'ha', u'house')]]\n", | |
"\n", | |
"\n", | |
"har\n", | |
"[[(u'har', u'house')]]\n", | |
"\n", | |
"\n", | |
"hard\n", | |
"[[(u'hard', u'city')]]\n", | |
"\n", | |
"\n", | |
"hard \n", | |
"[[(u'hard', u'city')]]\n", | |
"\n", | |
"\n", | |
"hard r\n", | |
"[[(u'hard river', u'house')]]\n", | |
"\n", | |
"\n", | |
"hard ro\n", | |
"[[(u'hard', u'city'), (u'ro', u'country')]]\n", | |
"\n", | |
"\n", | |
"hard roc\n", | |
"[[(u'hard roc', u'house')]]\n", | |
"\n", | |
"\n", | |
"hard rock\n", | |
"[[(u'hard rock', u'house')]]\n", | |
"\n", | |
"\n", | |
"hard rock \n", | |
"[[(u'hard rock', u'house')]]\n", | |
"\n", | |
"\n", | |
"hard rock c\n", | |
"[[(u'hard rock centre', u'house')], [(u'hard rock center', u'house')], [(u'hard rock central', u'house')]]\n", | |
"\n", | |
"\n", | |
"hard rock ca\n", | |
"[[(u'hard rock california', u'house')], [(u'hard rock', u'house'), (u'ca', u'country')]]\n", | |
"\n", | |
"\n", | |
"hard rock caf\n", | |
"[[(u'hard rock caf', u'house')]]\n", | |
"\n", | |
"\n", | |
"hard rock cafe\n", | |
"[[(u'hard rock cafe', u'house')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"====================================================================\n", | |
"\n", | |
"TEST SET: exact_matches\n", | |
"TEST: 100 20th street\n", | |
"1\n", | |
"[[(u'1', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"10\n", | |
"[[(u'10', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"100\n", | |
"[[(u'100', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"100 \n", | |
"[[(u'100', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"100 2\n", | |
"[[(u'100 2', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"100 20\n", | |
"[[(u'100 20', u'postcode')]]\n", | |
"\n", | |
"\n", | |
"100 20t\n", | |
"[[(u'100 20t', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"100 20th\n", | |
"[[(u'100', u'house_number'), (u'20th', u'road')]]\n", | |
"\n", | |
"\n", | |
"100 20th \n", | |
"[[(u'100', u'house_number'), (u'20th', u'road')]]\n", | |
"\n", | |
"\n", | |
"100 20th s\n", | |
"[[(u'100', u'house_number'), (u'20th san', u'road')], [(u'100', u'house_number'), (u'20th south', u'road')], [(u'100', u'house_number'), (u'20th s', u'road')]]\n", | |
"\n", | |
"\n", | |
"100 20th st\n", | |
"[[(u'100', u'house_number'), (u'20th saint', u'road')], [(u'100', u'house_number'), (u'20th street', u'road')]]\n", | |
"\n", | |
"\n", | |
"100 20th str\n", | |
"[[(u'100', u'house_number'), (u'20th street', u'road')]]\n", | |
"\n", | |
"\n", | |
"100 20th stre\n", | |
"[[(u'100', u'house_number'), (u'20th stre', u'road')]]\n", | |
"\n", | |
"\n", | |
"100 20th stree\n", | |
"[[(u'100', u'house_number'), (u'20th stree', u'road')]]\n", | |
"\n", | |
"\n", | |
"100 20th street\n", | |
"[[(u'100', u'house_number'), (u'20th street', u'road')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: 40 20th street\n", | |
"4\n", | |
"[[(u'4', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"40\n", | |
"[[(u'40', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"40 \n", | |
"[[(u'40', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"40 2\n", | |
"[[(u'40', u'road'), (u'2', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"40 20\n", | |
"[[(u'40', u'house'), (u'20', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"40 20t\n", | |
"[[(u'40', u'road'), (u'20t', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"40 20th\n", | |
"[[(u'40', u'house_number'), (u'20th', u'road')]]\n", | |
"\n", | |
"\n", | |
"40 20th \n", | |
"[[(u'40', u'house_number'), (u'20th', u'road')]]\n", | |
"\n", | |
"\n", | |
"40 20th s\n", | |
"[[(u'40', u'house_number'), (u'20th san', u'road')], [(u'40', u'house_number'), (u'20th south', u'road')], [(u'40', u'house_number'), (u'20th s', u'road')]]\n", | |
"\n", | |
"\n", | |
"40 20th st\n", | |
"[[(u'40', u'house_number'), (u'20th saint', u'road')], [(u'40', u'house_number'), (u'20th street', u'road')]]\n", | |
"\n", | |
"\n", | |
"40 20th str\n", | |
"[[(u'40', u'house_number'), (u'20th street', u'road')]]\n", | |
"\n", | |
"\n", | |
"40 20th stre\n", | |
"[[(u'40', u'house_number'), (u'20th stre', u'road')]]\n", | |
"\n", | |
"\n", | |
"40 20th stree\n", | |
"[[(u'40', u'house_number'), (u'20th stree', u'road')]]\n", | |
"\n", | |
"\n", | |
"40 20th street\n", | |
"[[(u'40', u'house_number'), (u'20th street', u'road')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: 120 42nd Street\n", | |
"1\n", | |
"[[(u'1', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"12\n", | |
"[[(u'12', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"120\n", | |
"[[(u'120', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"120 \n", | |
"[[(u'120', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"120 4\n", | |
"[[(u'120 4', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"120 42\n", | |
"[[(u'120', u'road'), (u'42', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"120 42n\n", | |
"[[(u'120 42n', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"120 42nd\n", | |
"[[(u'120', u'house_number'), (u'42nd', u'road')]]\n", | |
"\n", | |
"\n", | |
"120 42nd \n", | |
"[[(u'120', u'house_number'), (u'42nd', u'road')]]\n", | |
"\n", | |
"\n", | |
"120 42nd S\n", | |
"[[(u'120', u'house_number'), (u'42nd san', u'road')], [(u'120', u'house_number'), (u'42nd south', u'road')], [(u'120', u'house_number'), (u'42nd s', u'road')]]\n", | |
"\n", | |
"\n", | |
"120 42nd St\n", | |
"[[(u'120', u'house_number'), (u'42nd saint', u'road')], [(u'120', u'house_number'), (u'42nd street', u'road')]]\n", | |
"\n", | |
"\n", | |
"120 42nd Str\n", | |
"[[(u'120', u'house_number'), (u'42nd street', u'road')]]\n", | |
"\n", | |
"\n", | |
"120 42nd Stre\n", | |
"[[(u'120', u'house_number'), (u'42nd stre', u'road')]]\n", | |
"\n", | |
"\n", | |
"120 42nd Stree\n", | |
"[[(u'120', u'house_number'), (u'42nd stree', u'road')]]\n", | |
"\n", | |
"\n", | |
"120 42nd Street\n", | |
"[[(u'120', u'house_number'), (u'42nd street', u'road')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: 358 41st street, ny\n", | |
"3\n", | |
"[[(u'3', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"35\n", | |
"[[(u'35', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"358\n", | |
"[[(u'358', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"358 \n", | |
"[[(u'358', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"358 4\n", | |
"[[(u'358 4', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"358 41\n", | |
"[[(u'358 41', u'postcode')]]\n", | |
"\n", | |
"\n", | |
"358 41s\n", | |
"[[(u'358', u'house_number'), (u'41s', u'road')]]\n", | |
"\n", | |
"\n", | |
"358 41st\n", | |
"[[(u'358', u'house_number'), (u'41st', u'road')]]\n", | |
"\n", | |
"\n", | |
"358 41st \n", | |
"[[(u'358', u'house_number'), (u'41st', u'road')]]\n", | |
"\n", | |
"\n", | |
"358 41st s\n", | |
"[[(u'358', u'house_number'), (u'41st san', u'road')], [(u'358', u'house_number'), (u'41st south', u'road')], [(u'358', u'house_number'), (u'41st s', u'road')]]\n", | |
"\n", | |
"\n", | |
"358 41st st\n", | |
"[[(u'358', u'house_number'), (u'41st saint', u'road')], [(u'358', u'house_number'), (u'41st street', u'road')]]\n", | |
"\n", | |
"\n", | |
"358 41st str\n", | |
"[[(u'358', u'house_number'), (u'41st street', u'road')]]\n", | |
"\n", | |
"\n", | |
"358 41st stre\n", | |
"[[(u'358', u'house_number'), (u'41st stre', u'road')]]\n", | |
"\n", | |
"\n", | |
"358 41st stree\n", | |
"[[(u'358', u'house_number'), (u'41st stree', u'road')]]\n", | |
"\n", | |
"\n", | |
"358 41st street\n", | |
"[[(u'358', u'house_number'), (u'41st street', u'road')]]\n", | |
"\n", | |
"\n", | |
"358 41st street,\n", | |
"[[(u'358', u'house_number'), (u'41st street', u'road')]]\n", | |
"\n", | |
"\n", | |
"358 41st street, \n", | |
"[[(u'358', u'house_number'), (u'41st street', u'road')]]\n", | |
"\n", | |
"\n", | |
"358 41st street, n\n", | |
"[[(u'358', u'house_number'), (u'41st street north', u'road')], [(u'358', u'house_number'), (u'41st street n', u'road')]]\n", | |
"\n", | |
"\n", | |
"358 41st street, ny\n", | |
"[[(u'358', u'house_number'), (u'41st street', u'road'), (u'new york', u'state')], [(u'358', u'house_number'), (u'41st street', u'road'), (u'ny', u'state')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: 1359 54 street, ny\n", | |
"1\n", | |
"[[(u'1', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"13\n", | |
"[[(u'13', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"135\n", | |
"[[(u'135', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"1359\n", | |
"[[(u'1359', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"1359 \n", | |
"[[(u'1359', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"1359 5\n", | |
"[[(u'1359 5', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"1359 54\n", | |
"[[(u'1359', u'house_number'), (u'54', u'road')]]\n", | |
"\n", | |
"\n", | |
"1359 54 \n", | |
"[[(u'1359', u'house_number'), (u'54', u'road')]]\n", | |
"\n", | |
"\n", | |
"1359 54 s\n", | |
"[[(u'1359', u'house_number'), (u'54 san', u'road')], [(u'1359', u'house_number'), (u'54 south', u'road')], [(u'1359', u'house_number'), (u'54 s', u'road')]]\n", | |
"\n", | |
"\n", | |
"1359 54 st\n", | |
"[[(u'1359', u'house_number'), (u'54 saint', u'road')], [(u'1359', u'house_number'), (u'54 street', u'road')]]\n", | |
"\n", | |
"\n", | |
"1359 54 str\n", | |
"[[(u'1359', u'house_number'), (u'54 street', u'road')]]\n", | |
"\n", | |
"\n", | |
"1359 54 stre\n", | |
"[[(u'1359', u'house_number'), (u'54 stre', u'road')]]\n", | |
"\n", | |
"\n", | |
"1359 54 stree\n", | |
"[[(u'1359', u'house_number'), (u'54 stree', u'road')]]\n", | |
"\n", | |
"\n", | |
"1359 54 street\n", | |
"[[(u'1359', u'house_number'), (u'54 street', u'road')]]\n", | |
"\n", | |
"\n", | |
"1359 54 street,\n", | |
"[[(u'1359', u'house_number'), (u'54 street', u'road')]]\n", | |
"\n", | |
"\n", | |
"1359 54 street, \n", | |
"[[(u'1359', u'house_number'), (u'54 street', u'road')]]\n", | |
"\n", | |
"\n", | |
"1359 54 street, n\n", | |
"[[(u'1359', u'house_number'), (u'54 street north', u'road')], [(u'1359', u'house_number'), (u'54 street n', u'road')]]\n", | |
"\n", | |
"\n", | |
"1359 54 street, ny\n", | |
"[[(u'1359', u'house_number'), (u'54 street', u'road'), (u'new york', u'state')], [(u'1359', u'house_number'), (u'54 street', u'road'), (u'ny', u'state')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: 310 7 street, ny\n", | |
"3\n", | |
"[[(u'3', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"31\n", | |
"[[(u'31', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"310\n", | |
"[[(u'310', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"310 \n", | |
"[[(u'310', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"310 7\n", | |
"[[(u'310 7', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"310 7 \n", | |
"[[(u'310 7', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"310 7 s\n", | |
"[[(u'310 7', u'house_number'), (u'san', u'road')], [(u'310 7', u'house_number'), (u'south', u'road')], [(u'310 7', u'house_number'), (u's', u'road')]]\n", | |
"\n", | |
"\n", | |
"310 7 st\n", | |
"[[(u'310 7', u'house_number'), (u'saint', u'road')], [(u'310', u'house_number'), (u'7 street', u'road')]]\n", | |
"\n", | |
"\n", | |
"310 7 str\n", | |
"[[(u'310', u'house_number'), (u'7 street', u'road')]]\n", | |
"\n", | |
"\n", | |
"310 7 stre\n", | |
"[[(u'310 7', u'house_number'), (u'stre', u'road')]]\n", | |
"\n", | |
"\n", | |
"310 7 stree\n", | |
"[[(u'310 7', u'house_number'), (u'stree', u'road')]]\n", | |
"\n", | |
"\n", | |
"310 7 street\n", | |
"[[(u'310', u'house_number'), (u'7 street', u'road')]]\n", | |
"\n", | |
"\n", | |
"310 7 street,\n", | |
"[[(u'310', u'house_number'), (u'7 street', u'road')]]\n", | |
"\n", | |
"\n", | |
"310 7 street, \n", | |
"[[(u'310', u'house_number'), (u'7 street', u'road')]]\n", | |
"\n", | |
"\n", | |
"310 7 street, n\n", | |
"[[(u'310', u'house_number'), (u'7 street north', u'road')], [(u'310', u'house_number'), (u'7 street n', u'road')]]\n", | |
"\n", | |
"\n", | |
"310 7 street, ny\n", | |
"[[(u'310', u'house_number'), (u'7 street', u'road'), (u'new york', u'state')], [(u'310', u'house_number'), (u'7 street', u'road'), (u'ny', u'state')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: 921 83 street, ny\n", | |
"9\n", | |
"[[(u'9', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"92\n", | |
"[[(u'92', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"921\n", | |
"[[(u'921', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"921 \n", | |
"[[(u'921', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"921 8\n", | |
"[[(u'921 8', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"921 83\n", | |
"[[(u'921', u'road'), (u'83', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"921 83 \n", | |
"[[(u'921', u'road'), (u'83', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"921 83 s\n", | |
"[[(u'921', u'road'), (u'83', u'house_number'), (u'san', u'road')], [(u'921', u'road'), (u'83', u'house_number'), (u'south', u'road')], [(u'921', u'road'), (u'83', u'house_number'), (u's', u'road')]]\n", | |
"\n", | |
"\n", | |
"921 83 st\n", | |
"[[(u'921', u'road'), (u'83', u'house_number'), (u'saint', u'road')], [(u'921 83 street', u'road')]]\n", | |
"\n", | |
"\n", | |
"921 83 str\n", | |
"[[(u'921 83 street', u'road')]]\n", | |
"\n", | |
"\n", | |
"921 83 stre\n", | |
"[[(u'921', u'road'), (u'83', u'house_number'), (u'stre', u'road')]]\n", | |
"\n", | |
"\n", | |
"921 83 stree\n", | |
"[[(u'921', u'road'), (u'83', u'house_number'), (u'stree', u'road')]]\n", | |
"\n", | |
"\n", | |
"921 83 street\n", | |
"[[(u'921 83 street', u'road')]]\n", | |
"\n", | |
"\n", | |
"921 83 street,\n", | |
"[[(u'921 83 street', u'road')]]\n", | |
"\n", | |
"\n", | |
"921 83 street, \n", | |
"[[(u'921 83 street', u'road')]]\n", | |
"\n", | |
"\n", | |
"921 83 street, n\n", | |
"[[(u'921 83 street north', u'road')], [(u'921 83 street n', u'road')]]\n", | |
"\n", | |
"\n", | |
"921 83 street, ny\n", | |
"[[(u'921 83 street', u'road'), (u'new york', u'state')], [(u'921 83 street', u'road'), (u'ny', u'state')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: 518 3 street, ny\n", | |
"5\n", | |
"[[(u'5', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"51\n", | |
"[[(u'51', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"518\n", | |
"[[(u'518', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"518 \n", | |
"[[(u'518', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"518 3\n", | |
"[[(u'518 3', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"518 3 \n", | |
"[[(u'518 3', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"518 3 s\n", | |
"[[(u'518 3', u'house_number'), (u'san', u'road')], [(u'518 3', u'house_number'), (u'south', u'road')], [(u'518 3', u'house_number'), (u's', u'road')]]\n", | |
"\n", | |
"\n", | |
"518 3 st\n", | |
"[[(u'518 3', u'house_number'), (u'saint', u'road')], [(u'518', u'house_number'), (u'3 street', u'road')]]\n", | |
"\n", | |
"\n", | |
"518 3 str\n", | |
"[[(u'518', u'house_number'), (u'3 street', u'road')]]\n", | |
"\n", | |
"\n", | |
"518 3 stre\n", | |
"[[(u'518 3', u'house_number'), (u'stre', u'road')]]\n", | |
"\n", | |
"\n", | |
"518 3 stree\n", | |
"[[(u'518 3', u'house_number'), (u'stree', u'road')]]\n", | |
"\n", | |
"\n", | |
"518 3 street\n", | |
"[[(u'518', u'house_number'), (u'3 street', u'road')]]\n", | |
"\n", | |
"\n", | |
"518 3 street,\n", | |
"[[(u'518', u'house_number'), (u'3 street', u'road')]]\n", | |
"\n", | |
"\n", | |
"518 3 street, \n", | |
"[[(u'518', u'house_number'), (u'3 street', u'road')]]\n", | |
"\n", | |
"\n", | |
"518 3 street, n\n", | |
"[[(u'518', u'house_number'), (u'3 street north', u'road')], [(u'518', u'house_number'), (u'3 street n', u'road')]]\n", | |
"\n", | |
"\n", | |
"518 3 street, ny\n", | |
"[[(u'518', u'house_number'), (u'3 street', u'road'), (u'new york', u'state')], [(u'518', u'house_number'), (u'3 street', u'road'), (u'ny', u'state')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"====================================================================\n", | |
"\n", | |
"TEST SET: landmarks\n", | |
"TEST: statue of liberty\n", | |
"s\n", | |
"[[(u'san', u'road')], [(u'south', u'road')], [(u's', u'road')]]\n", | |
"\n", | |
"\n", | |
"st\n", | |
"[[(u'saint', u'house')], [(u'street', u'road')]]\n", | |
"\n", | |
"\n", | |
"sta\n", | |
"[[(u'station', u'house')], [(u'santa', u'road')]]\n", | |
"\n", | |
"\n", | |
"stat\n", | |
"[[(u'stat', u'house')]]\n", | |
"\n", | |
"\n", | |
"statu\n", | |
"[[(u'statu', u'house')]]\n", | |
"\n", | |
"\n", | |
"statue\n", | |
"[[(u'statue', u'house')]]\n", | |
"\n", | |
"\n", | |
"statue \n", | |
"[[(u'statue', u'house')]]\n", | |
"\n", | |
"\n", | |
"statue o\n", | |
"[[(u'statue o', u'house')]]\n", | |
"\n", | |
"\n", | |
"statue of\n", | |
"[[(u'statue of', u'house')]]\n", | |
"\n", | |
"\n", | |
"statue of \n", | |
"[[(u'statue of', u'house')]]\n", | |
"\n", | |
"\n", | |
"statue of l\n", | |
"[[(u'statue of level', u'house')]]\n", | |
"\n", | |
"\n", | |
"statue of li\n", | |
"[[(u'statue of li', u'house')], [(u'statue of 51', u'house')]]\n", | |
"\n", | |
"\n", | |
"statue of lib\n", | |
"[[(u'statue of lib', u'house')]]\n", | |
"\n", | |
"\n", | |
"statue of libe\n", | |
"[[(u'statue of libe', u'house')]]\n", | |
"\n", | |
"\n", | |
"statue of liber\n", | |
"[[(u'statue of liber', u'house')]]\n", | |
"\n", | |
"\n", | |
"statue of libert\n", | |
"[[(u'statue of libert', u'house')]]\n", | |
"\n", | |
"\n", | |
"statue of liberty\n", | |
"[[(u'statue of liberty', u'house')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"====================================================================\n", | |
"\n", | |
"TEST SET: search_coarse\n", | |
"TEST: brooklyn\n", | |
"b\n", | |
"[[(u'b', u'house')]]\n", | |
"\n", | |
"\n", | |
"br\n", | |
"[[(u'brae', u'road')], [(u'brother', u'house')], [(u'brace', u'house')], [(u'bridge', u'house')], [(u'branch', u'house')]]\n", | |
"\n", | |
"\n", | |
"bro\n", | |
"[[(u'bro', u'road')]]\n", | |
"\n", | |
"\n", | |
"broo\n", | |
"[[(u'broo', u'house')]]\n", | |
"\n", | |
"\n", | |
"brook\n", | |
"[[(u'brook', u'house')]]\n", | |
"\n", | |
"\n", | |
"brookl\n", | |
"[[(u'brookl', u'house')]]\n", | |
"\n", | |
"\n", | |
"brookly\n", | |
"[[(u'brookly', u'house')]]\n", | |
"\n", | |
"\n", | |
"brooklyn\n", | |
"[[(u'brooklyn', u'house')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: new york\n", | |
"n\n", | |
"[[(u'north', u'road')], [(u'n', u'road')]]\n", | |
"\n", | |
"\n", | |
"ne\n", | |
"[[(u'ne', u'road')], [(u'northeast', u'road')], [(u'nebraska', u'state')]]\n", | |
"\n", | |
"\n", | |
"new\n", | |
"[[(u'new', u'house')]]\n", | |
"\n", | |
"\n", | |
"new \n", | |
"[[(u'new', u'house')]]\n", | |
"\n", | |
"\n", | |
"new y\n", | |
"[[(u'new y', u'house')]]\n", | |
"\n", | |
"\n", | |
"new yo\n", | |
"[[(u'new yo', u'house')]]\n", | |
"\n", | |
"\n", | |
"new yor\n", | |
"[[(u'new yor', u'house')]]\n", | |
"\n", | |
"\n", | |
"new york\n", | |
"[[(u'new york', u'state')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"====================================================================\n", | |
"\n", | |
"TEST SET: address_matching\n", | |
"TEST: 30 w 26 st\n", | |
"3\n", | |
"[[(u'3', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"30\n", | |
"[[(u'30', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"30 \n", | |
"[[(u'30', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"30 w\n", | |
"[[(u'30', u'house_number'), (u'west', u'road')], [(u'30', u'house_number'), (u'w', u'house')]]\n", | |
"\n", | |
"\n", | |
"30 w \n", | |
"[[(u'30', u'house_number'), (u'west', u'road')], [(u'30', u'house_number'), (u'w', u'house')]]\n", | |
"\n", | |
"\n", | |
"30 w 2\n", | |
"[[(u'30', u'house_number'), (u'west', u'road'), (u'2', u'house_number')], [(u'30', u'house_number'), (u'w', u'road'), (u'2', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"30 w 26\n", | |
"[[(u'30', u'house_number'), (u'west 26', u'road')], [(u'30', u'house_number'), (u'w 26', u'road')]]\n", | |
"\n", | |
"\n", | |
"30 w 26 \n", | |
"[[(u'30', u'house_number'), (u'west 26', u'road')], [(u'30', u'house_number'), (u'w 26', u'road')]]\n", | |
"\n", | |
"\n", | |
"30 w 26 s\n", | |
"[[(u'30', u'house_number'), (u'west 26', u'road'), (u'san', u'city')], [(u'30', u'house_number'), (u'west 26 south', u'road')], [(u'30', u'house_number'), (u'west 26 s', u'road')], [(u'30', u'house_number'), (u'w 26', u'road'), (u'san', u'city')], [(u'30', u'house_number'), (u'w 26 south', u'road')], [(u'30', u'house_number'), (u'w 26 s', u'road')]]\n", | |
"\n", | |
"\n", | |
"30 w 26 st\n", | |
"[[(u'30', u'house_number'), (u'west', u'road'), (u'26', u'house_number'), (u'saint', u'road')], [(u'30', u'house_number'), (u'west 26 street', u'road')], [(u'30', u'house_number'), (u'w', u'road'), (u'26', u'house_number'), (u'saint', u'road')], [(u'30', u'house_number'), (u'w 26 street', u'road')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: 507 hackney rd\n", | |
"5\n", | |
"[[(u'5', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"50\n", | |
"[[(u'50', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"507\n", | |
"[[(u'507', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"507 \n", | |
"[[(u'507', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"507 h\n", | |
"[[(u'507 h', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"507 ha\n", | |
"[[(u'507', u'house_number'), (u'ha', u'road')]]\n", | |
"\n", | |
"\n", | |
"507 hac\n", | |
"[[(u'507', u'house_number'), (u'hac', u'road')]]\n", | |
"\n", | |
"\n", | |
"507 hack\n", | |
"[[(u'507', u'house_number'), (u'hack', u'road')]]\n", | |
"\n", | |
"\n", | |
"507 hackn\n", | |
"[[(u'507', u'house_number'), (u'hackn', u'road')]]\n", | |
"\n", | |
"\n", | |
"507 hackne\n", | |
"[[(u'507', u'house_number'), (u'hackne', u'road')]]\n", | |
"\n", | |
"\n", | |
"507 hackney\n", | |
"[[(u'507', u'house_number'), (u'hackney', u'road')]]\n", | |
"\n", | |
"\n", | |
"507 hackney \n", | |
"[[(u'507', u'house_number'), (u'hackney', u'road')]]\n", | |
"\n", | |
"\n", | |
"507 hackney r\n", | |
"[[(u'507', u'house_number'), (u'hackney river', u'road')]]\n", | |
"\n", | |
"\n", | |
"507 hackney rd\n", | |
"[[(u'507', u'house_number'), (u'hackney road', u'road')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: 49 Kay Street\n", | |
"4\n", | |
"[[(u'4', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"49\n", | |
"[[(u'49', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"49 \n", | |
"[[(u'49', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"49 K\n", | |
"[[(u'49', u'house_number'), (u'k', u'road')]]\n", | |
"\n", | |
"\n", | |
"49 Ka\n", | |
"[[(u'49', u'house_number'), (u'ka', u'road')]]\n", | |
"\n", | |
"\n", | |
"49 Kay\n", | |
"[[(u'49', u'house_number'), (u'kay', u'road')]]\n", | |
"\n", | |
"\n", | |
"49 Kay \n", | |
"[[(u'49', u'house_number'), (u'kay', u'road')]]\n", | |
"\n", | |
"\n", | |
"49 Kay S\n", | |
"[[(u'49', u'house_number'), (u'kay san', u'road')], [(u'49', u'house_number'), (u'kay south', u'road')], [(u'49', u'house_number'), (u'kay s', u'road')]]\n", | |
"\n", | |
"\n", | |
"49 Kay St\n", | |
"[[(u'49', u'house_number'), (u'kay saint', u'road')], [(u'49', u'house_number'), (u'kay street', u'road')]]\n", | |
"\n", | |
"\n", | |
"49 Kay Str\n", | |
"[[(u'49', u'house_number'), (u'kay street', u'road')]]\n", | |
"\n", | |
"\n", | |
"49 Kay Stre\n", | |
"[[(u'49', u'house_number'), (u'kay stre', u'road')]]\n", | |
"\n", | |
"\n", | |
"49 Kay Stree\n", | |
"[[(u'49', u'house_number'), (u'kay stree', u'road')]]\n", | |
"\n", | |
"\n", | |
"49 Kay Street\n", | |
"[[(u'49', u'house_number'), (u'kay street', u'road')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: 339 W Main St, Cheshire, 06410\n", | |
"3\n", | |
"[[(u'3', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"33\n", | |
"[[(u'33', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"339\n", | |
"[[(u'339', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"339 \n", | |
"[[(u'339', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"339 W\n", | |
"[[(u'339', u'house_number'), (u'west', u'road')], [(u'339', u'house_number'), (u'w', u'house')]]\n", | |
"\n", | |
"\n", | |
"339 W \n", | |
"[[(u'339', u'house_number'), (u'west', u'road')], [(u'339', u'house_number'), (u'w', u'house')]]\n", | |
"\n", | |
"\n", | |
"339 W M\n", | |
"[[(u'339', u'house_number'), (u'west mail', u'road')], [(u'339', u'house_number'), (u'w mail', u'road')]]\n", | |
"\n", | |
"\n", | |
"339 W Ma\n", | |
"[[(u'339', u'house_number'), (u'west', u'road'), (u'massachusetts', u'state')], [(u'339', u'house_number'), (u'west', u'road'), (u'ma', u'state')], [(u'339', u'house_number'), (u'w', u'road'), (u'massachusetts', u'state')], [(u'339', u'house_number'), (u'w', u'road'), (u'ma', u'state')]]\n", | |
"\n", | |
"\n", | |
"339 W Mai\n", | |
"[[(u'339', u'house_number'), (u'west mai', u'road')], [(u'339', u'house_number'), (u'w mai', u'road')]]\n", | |
"\n", | |
"\n", | |
"339 W Main\n", | |
"[[(u'339', u'house_number'), (u'west main', u'road')], [(u'339', u'house_number'), (u'w main', u'road')]]\n", | |
"\n", | |
"\n", | |
"339 W Main \n", | |
"[[(u'339', u'house_number'), (u'west main', u'road')], [(u'339', u'house_number'), (u'w main', u'road')]]\n", | |
"\n", | |
"\n", | |
"339 W Main S\n", | |
"[[(u'339', u'house_number'), (u'west main', u'road'), (u'san', u'suburb')], [(u'339', u'house_number'), (u'west main south', u'road')], [(u'339', u'house_number'), (u'west main s', u'road')], [(u'339', u'house_number'), (u'w main', u'road'), (u'san', u'suburb')], [(u'339', u'house_number'), (u'w main south', u'road')], [(u'339', u'house_number'), (u'w main s', u'road')]]\n", | |
"\n", | |
"\n", | |
"339 W Main St\n", | |
"[[(u'339', u'house_number'), (u'west main saint', u'road')], [(u'339', u'house_number'), (u'west main street', u'road')], [(u'339', u'house_number'), (u'w main saint', u'road')], [(u'339', u'house_number'), (u'w main street', u'road')]]\n", | |
"\n", | |
"\n", | |
"339 W Main St,\n", | |
"[[(u'339', u'house_number'), (u'west main saint', u'road')], [(u'339', u'house_number'), (u'west main street', u'road')], [(u'339', u'house_number'), (u'w main saint', u'road')], [(u'339', u'house_number'), (u'w main street', u'road')]]\n", | |
"\n", | |
"\n", | |
"339 W Main St, \n", | |
"[[(u'339', u'house_number'), (u'west main saint', u'road')], [(u'339', u'house_number'), (u'west main street', u'road')], [(u'339', u'house_number'), (u'w main saint', u'road')], [(u'339', u'house_number'), (u'w main street', u'road')]]\n", | |
"\n", | |
"\n", | |
"339 W Main St, C\n", | |
"[[(u'339', u'house_number'), (u'west main saint', u'road'), (u'centre', u'house')], [(u'339', u'house_number'), (u'west main saint', u'road'), (u'center', u'house')], [(u'339', u'house_number'), (u'west main saint central', u'road')], [(u'339', u'house_number'), (u'west main street', u'road'), (u'centre', u'suburb')], [(u'339', u'house_number'), (u'west main street', u'road'), (u'center', u'suburb')], [(u'339', u'house_number'), (u'west main street', u'road'), (u'central', u'suburb')], [(u'339', u'house_number'), (u'w main saint', u'road'), (u'centre', u'house')], [(u'339', u'house_number'), (u'w main street', u'road'), (u'centre', u'suburb')], [(u'339', u'house_number'), (u'w main street', u'road'), (u'center', u'suburb')], [(u'339', u'house_number'), (u'w main street', u'road'), (u'central', u'suburb')]]\n", | |
"\n", | |
"\n", | |
"339 W Main St, Ch\n", | |
"[[(u'339', u'house_number'), (u'west main saint county highway', u'road')], [(u'339', u'house_number'), (u'west main saint chase', u'road')], [(u'339', u'house_number'), (u'west main street', u'road'), (u'county highway', u'suburb')], [(u'339', u'house_number'), (u'west main street chase', u'road')], [(u'339', u'house_number'), (u'w main saint county highway', u'road')], [(u'339', u'house_number'), (u'w main street', u'road'), (u'county highway', u'suburb')], [(u'339', u'house_number'), (u'w main street chase', u'road')]]\n", | |
"\n", | |
"\n", | |
"339 W Main St, Che\n", | |
"[[(u'339', u'house_number'), (u'west main', u'road'), (u'saint', u'city'), (u'che', u'country')], [(u'339', u'house_number'), (u'west main street', u'road'), (u'che', u'country')], [(u'339', u'house_number'), (u'w main', u'road'), (u'saint', u'city'), (u'che', u'country')], [(u'339', u'house_number'), (u'w main street', u'road'), (u'che', u'country')]]\n", | |
"\n", | |
"\n", | |
"339 W Main St, Ches\n", | |
"[[(u'339', u'house_number'), (u'west main saint ches', u'road')], [(u'339', u'house_number'), (u'west main street', u'road'), (u'ches', u'city')], [(u'339', u'house_number'), (u'w main saint ches', u'road')], [(u'339', u'house_number'), (u'w main street', u'road'), (u'ches', u'city')]]\n", | |
"\n", | |
"\n", | |
"339 W Main St, Chesh\n", | |
"[[(u'339', u'house_number'), (u'west main saint chesh', u'road')], [(u'339', u'house_number'), (u'west main street', u'road'), (u'chesh', u'city')], [(u'339', u'house_number'), (u'w main saint chesh', u'road')], [(u'339', u'house_number'), (u'w main street', u'road'), (u'chesh', u'city')]]\n", | |
"\n", | |
"\n", | |
"339 W Main St, Cheshi\n", | |
"[[(u'339', u'house_number'), (u'west main saint cheshi', u'road')], [(u'339', u'house_number'), (u'west main street', u'road'), (u'cheshi', u'city')], [(u'339', u'house_number'), (u'w main saint cheshi', u'road')], [(u'339', u'house_number'), (u'w main street', u'road'), (u'cheshi', u'city')]]\n", | |
"\n", | |
"\n", | |
"339 W Main St, Cheshir\n", | |
"[[(u'339', u'house_number'), (u'west main saint cheshir', u'road')], [(u'339', u'house_number'), (u'west main street', u'road'), (u'cheshir', u'city')], [(u'339', u'house_number'), (u'w main saint cheshir', u'road')], [(u'339', u'house_number'), (u'w main street', u'road'), (u'cheshir', u'city')]]\n", | |
"\n", | |
"\n", | |
"339 W Main St, Cheshire\n", | |
"[[(u'339', u'house_number'), (u'west main saint cheshire', u'road')], [(u'339', u'house_number'), (u'west main street', u'road'), (u'cheshire', u'city')], [(u'339', u'house_number'), (u'w main saint cheshire', u'road')], [(u'339', u'house_number'), (u'w main street', u'road'), (u'cheshire', u'city')]]\n", | |
"\n", | |
"\n", | |
"339 W Main St, Cheshire,\n", | |
"[[(u'339', u'house_number'), (u'west main saint cheshire', u'road')], [(u'339', u'house_number'), (u'west main street', u'road'), (u'cheshire', u'city')], [(u'339', u'house_number'), (u'w main saint cheshire', u'road')], [(u'339', u'house_number'), (u'w main street', u'road'), (u'cheshire', u'city')]]\n", | |
"\n", | |
"\n", | |
"339 W Main St, Cheshire, \n", | |
"[[(u'339', u'house_number'), (u'west main saint cheshire', u'road')], [(u'339', u'house_number'), (u'west main street', u'road'), (u'cheshire', u'city')], [(u'339', u'house_number'), (u'w main saint cheshire', u'road')], [(u'339', u'house_number'), (u'w main street', u'road'), (u'cheshire', u'city')]]\n", | |
"\n", | |
"\n", | |
"339 W Main St, Cheshire, 0\n", | |
"[[(u'339', u'house_number'), (u'west main saint cheshire', u'road'), (u'0', u'house_number')], [(u'339', u'house_number'), (u'west main street cheshire', u'road'), (u'0', u'house_number')], [(u'339', u'house_number'), (u'w main saint cheshire', u'road'), (u'0', u'house_number')], [(u'339', u'house_number'), (u'w main street cheshire', u'road'), (u'0', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"339 W Main St, Cheshire, 06\n", | |
"[[(u'339', u'house_number'), (u'west main saint cheshire', u'road'), (u'06', u'house_number')], [(u'339', u'house_number'), (u'west main street cheshire', u'road'), (u'06', u'house_number')], [(u'339', u'house_number'), (u'w main saint cheshire', u'road'), (u'06', u'house_number')], [(u'339', u'house_number'), (u'w main street cheshire', u'road'), (u'06', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"339 W Main St, Cheshire, 064\n", | |
"[[(u'339', u'house_number'), (u'west main saint cheshire', u'road'), (u'064', u'house_number')], [(u'339', u'house_number'), (u'west main street cheshire', u'road'), (u'064', u'house_number')], [(u'339', u'house_number'), (u'w main saint cheshire', u'road'), (u'064', u'house_number')], [(u'339', u'house_number'), (u'w main street cheshire', u'road'), (u'064', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"339 W Main St, Cheshire, 0641\n", | |
"[[(u'339', u'house_number'), (u'west main saint cheshire', u'road'), (u'0641', u'postcode')], [(u'339', u'house_number'), (u'west main street cheshire', u'road'), (u'0641', u'postcode')], [(u'339', u'house_number'), (u'w main saint cheshire', u'road'), (u'0641', u'postcode')], [(u'339', u'house_number'), (u'w main street cheshire', u'road'), (u'0641', u'postcode')]]\n", | |
"\n", | |
"\n", | |
"339 W Main St, Cheshire, 06410\n", | |
"[[(u'339', u'house_number'), (u'west main saint cheshire', u'road'), (u'06410', u'postcode')], [(u'339', u'house_number'), (u'west main street', u'road'), (u'cheshire', u'city'), (u'06410', u'postcode')], [(u'339', u'house_number'), (u'w main saint cheshire', u'road'), (u'06410', u'postcode')], [(u'339', u'house_number'), (u'w main street', u'road'), (u'cheshire', u'city'), (u'06410', u'postcode')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"====================================================================\n", | |
"\n", | |
"TEST SET: confidence_score\n", | |
"TEST: 1 West 72nd St, New York, NY, 10023\n", | |
"1\n", | |
"[[(u'1', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"1 \n", | |
"[[(u'1', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"1 W\n", | |
"[[(u'1', u'house_number'), (u'west', u'road')], [(u'1', u'house_number'), (u'w', u'house')]]\n", | |
"\n", | |
"\n", | |
"1 We\n", | |
"[[(u'1', u'house_number'), (u'warehouse', u'road')]]\n", | |
"\n", | |
"\n", | |
"1 Wes\n", | |
"[[(u'1', u'house_number'), (u'wes', u'road')]]\n", | |
"\n", | |
"\n", | |
"1 West\n", | |
"[[(u'1', u'house_number'), (u'west', u'road')]]\n", | |
"\n", | |
"\n", | |
"1 West \n", | |
"[[(u'1', u'house_number'), (u'west', u'road')]]\n", | |
"\n", | |
"\n", | |
"1 West 7\n", | |
"[[(u'1', u'house_number'), (u'west', u'road'), (u'7', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"1 West 72\n", | |
"[[(u'1', u'house_number'), (u'west 72', u'road')]]\n", | |
"\n", | |
"\n", | |
"1 West 72n\n", | |
"[[(u'1', u'house_number'), (u'west', u'road'), (u'72n', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"1 West 72nd\n", | |
"[[(u'1', u'house_number'), (u'west 72nd', u'road')]]\n", | |
"\n", | |
"\n", | |
"1 West 72nd \n", | |
"[[(u'1', u'house_number'), (u'west 72nd', u'road')]]\n", | |
"\n", | |
"\n", | |
"1 West 72nd S\n", | |
"[[(u'1', u'house_number'), (u'west 72nd san', u'road')], [(u'1', u'house_number'), (u'west 72nd south', u'road')], [(u'1', u'house_number'), (u'west 72nd s', u'road')]]\n", | |
"\n", | |
"\n", | |
"1 West 72nd St\n", | |
"[[(u'1', u'house_number'), (u'west 72nd saint', u'road')], [(u'1', u'house_number'), (u'west 72nd street', u'road')]]\n", | |
"\n", | |
"\n", | |
"1 West 72nd St,\n", | |
"[[(u'1', u'house_number'), (u'west 72nd saint', u'road')], [(u'1', u'house_number'), (u'west 72nd street', u'road')]]\n", | |
"\n", | |
"\n", | |
"1 West 72nd St, \n", | |
"[[(u'1', u'house_number'), (u'west 72nd saint', u'road')], [(u'1', u'house_number'), (u'west 72nd street', u'road')]]\n", | |
"\n", | |
"\n", | |
"1 West 72nd St, N\n", | |
"[[(u'1', u'house_number'), (u'west 72nd saint north', u'road')], [(u'1', u'house_number'), (u'west 72nd saint n', u'road')], [(u'1', u'house_number'), (u'west 72nd street north', u'road')], [(u'1', u'house_number'), (u'west 72nd street n', u'road')]]\n", | |
"\n", | |
"\n", | |
"1 West 72nd St, Ne\n", | |
"[[(u'1', u'house_number'), (u'west 72nd saint ne', u'road')], [(u'1', u'house_number'), (u'west 72nd saint northeast', u'road')], [(u'1', u'house_number'), (u'west 72nd saint', u'road'), (u'nebraska', u'state')], [(u'1', u'house_number'), (u'west 72nd street ne', u'road')], [(u'1', u'house_number'), (u'west 72nd street northeast', u'road')], [(u'1', u'house_number'), (u'west 72nd street', u'road'), (u'nebraska', u'state')]]\n", | |
"\n", | |
"\n", | |
"1 West 72nd St, New\n", | |
"[[(u'1', u'house_number'), (u'west 72nd saint new', u'road')], [(u'1', u'house_number'), (u'west 72nd street', u'road'), (u'new', u'suburb')]]\n", | |
"\n", | |
"\n", | |
"1 West 72nd St, New \n", | |
"[[(u'1', u'house_number'), (u'west 72nd saint new', u'road')], [(u'1', u'house_number'), (u'west 72nd street', u'road'), (u'new', u'suburb')]]\n", | |
"\n", | |
"\n", | |
"1 West 72nd St, New Y\n", | |
"[[(u'1', u'house_number'), (u'west 72nd saint new y', u'road')], [(u'1', u'house_number'), (u'west 72nd street new y', u'road')]]\n", | |
"\n", | |
"\n", | |
"1 West 72nd St, New Yo\n", | |
"[[(u'1', u'house_number'), (u'west 72nd saint', u'road'), (u'new yo', u'house')], [(u'1', u'house_number'), (u'west 72nd street', u'road'), (u'new yo', u'suburb')]]\n", | |
"\n", | |
"\n", | |
"1 West 72nd St, New Yor\n", | |
"[[(u'1', u'house_number'), (u'west 72nd saint new', u'road'), (u'yor', u'suburb')], [(u'1', u'house_number'), (u'west 72nd street', u'road'), (u'new yor', u'suburb')]]\n", | |
"\n", | |
"\n", | |
"1 West 72nd St, New York\n", | |
"[[(u'1', u'house_number'), (u'west 72nd saint', u'road'), (u'new york', u'state')], [(u'1', u'house_number'), (u'west 72nd street', u'road'), (u'new york', u'state')]]\n", | |
"\n", | |
"\n", | |
"1 West 72nd St, New York,\n", | |
"[[(u'1', u'house_number'), (u'west 72nd saint', u'road'), (u'new york', u'state')], [(u'1', u'house_number'), (u'west 72nd street', u'road'), (u'new york', u'state')]]\n", | |
"\n", | |
"\n", | |
"1 West 72nd St, New York, \n", | |
"[[(u'1', u'house_number'), (u'west 72nd saint', u'road'), (u'new york', u'state')], [(u'1', u'house_number'), (u'west 72nd street', u'road'), (u'new york', u'state')]]\n", | |
"\n", | |
"\n", | |
"1 West 72nd St, New York, N\n", | |
"[[(u'1', u'house_number'), (u'west 72nd saint', u'road'), (u'new', u'state'), (u'york', u'house'), (u'north', u'road')], [(u'1', u'house_number'), (u'west 72nd saint', u'road'), (u'new york', u'state'), (u'n', u'postcode')], [(u'1', u'house_number'), (u'west 72nd street', u'road'), (u'new york', u'state'), (u'north', u'road')], [(u'1', u'house_number'), (u'west 72nd street', u'road'), (u'new york', u'state'), (u'n', u'postcode')]]\n", | |
"\n", | |
"\n", | |
"1 West 72nd St, New York, NY\n", | |
"[[(u'1', u'house_number'), (u'west 72nd saint', u'road'), (u'new york', u'city'), (u'new york', u'state')], [(u'1', u'house_number'), (u'west 72nd saint', u'road'), (u'new york', u'city'), (u'ny', u'state')], [(u'1', u'house_number'), (u'west 72nd street', u'road'), (u'new york', u'city'), (u'new york', u'state')], [(u'1', u'house_number'), (u'west 72nd street', u'road'), (u'new york', u'city'), (u'ny', u'state')]]\n", | |
"\n", | |
"\n", | |
"1 West 72nd St, New York, NY,\n", | |
"[[(u'1', u'house_number'), (u'west 72nd saint', u'road'), (u'new york', u'city'), (u'new york', u'state')], [(u'1', u'house_number'), (u'west 72nd saint', u'road'), (u'new york', u'city'), (u'ny', u'state')], [(u'1', u'house_number'), (u'west 72nd street', u'road'), (u'new york', u'city'), (u'new york', u'state')], [(u'1', u'house_number'), (u'west 72nd street', u'road'), (u'new york', u'city'), (u'ny', u'state')]]\n", | |
"\n", | |
"\n", | |
"1 West 72nd St, New York, NY, \n", | |
"[[(u'1', u'house_number'), (u'west 72nd saint', u'road'), (u'new york', u'city'), (u'new york', u'state')], [(u'1', u'house_number'), (u'west 72nd saint', u'road'), (u'new york', u'city'), (u'ny', u'state')], [(u'1', u'house_number'), (u'west 72nd street', u'road'), (u'new york', u'city'), (u'new york', u'state')], [(u'1', u'house_number'), (u'west 72nd street', u'road'), (u'new york', u'city'), (u'ny', u'state')]]\n", | |
"\n", | |
"\n", | |
"1 West 72nd St, New York, NY, 1\n", | |
"[[(u'1', u'house_number'), (u'west 72nd saint', u'road'), (u'new york', u'city'), (u'new york', u'state'), (u'1', u'postcode')], [(u'1', u'house_number'), (u'west 72nd saint', u'road'), (u'new york', u'city'), (u'ny', u'state'), (u'1', u'postcode')], [(u'1', u'house_number'), (u'west 72nd street', u'road'), (u'new york', u'city'), (u'new york', u'state'), (u'1', u'postcode')], [(u'1', u'house_number'), (u'west 72nd street', u'road'), (u'new york', u'city'), (u'ny', u'state'), (u'1', u'postcode')]]\n", | |
"\n", | |
"\n", | |
"1 West 72nd St, New York, NY, 10\n", | |
"[[(u'1', u'house_number'), (u'west 72nd saint', u'road'), (u'new york', u'city'), (u'new york', u'state'), (u'10', u'postcode')], [(u'1', u'house_number'), (u'west 72nd saint', u'road'), (u'new york', u'city'), (u'ny', u'state'), (u'10', u'postcode')], [(u'1', u'house_number'), (u'west 72nd street', u'road'), (u'new york', u'city'), (u'new york', u'state'), (u'10', u'postcode')], [(u'1', u'house_number'), (u'west 72nd street', u'road'), (u'new york', u'city'), (u'ny', u'state'), (u'10', u'postcode')]]\n", | |
"\n", | |
"\n", | |
"1 West 72nd St, New York, NY, 100\n", | |
"[[(u'1', u'house_number'), (u'west 72nd saint', u'road'), (u'new york', u'city'), (u'new york', u'state'), (u'100', u'postcode')], [(u'1', u'house_number'), (u'west 72nd saint', u'road'), (u'new', u'city'), (u'york', u'house'), (u'ny', u'state'), (u'100', u'postcode')], [(u'1', u'house_number'), (u'west 72nd street', u'road'), (u'new york', u'city'), (u'new york', u'state'), (u'100', u'postcode')], [(u'1', u'house_number'), (u'west 72nd street', u'road'), (u'new york', u'city'), (u'ny', u'state'), (u'100', u'postcode')]]\n", | |
"\n", | |
"\n", | |
"1 West 72nd St, New York, NY, 1002\n", | |
"[[(u'1', u'house_number'), (u'west 72nd saint', u'road'), (u'new york', u'city'), (u'new york', u'state'), (u'1002', u'postcode')], [(u'1', u'house_number'), (u'west 72nd saint', u'road'), (u'new york', u'city'), (u'ny', u'state'), (u'1002', u'postcode')], [(u'1', u'house_number'), (u'west 72nd street', u'road'), (u'new york', u'city'), (u'new york', u'state'), (u'1002', u'postcode')], [(u'1', u'house_number'), (u'west 72nd street', u'road'), (u'new york', u'city'), (u'ny', u'state'), (u'1002', u'postcode')]]\n", | |
"\n", | |
"\n", | |
"1 West 72nd St, New York, NY, 10023\n", | |
"[[(u'1', u'house_number'), (u'west 72nd saint', u'road'), (u'new york', u'city'), (u'new york', u'state'), (u'10023', u'postcode')], [(u'1', u'house_number'), (u'west 72nd saint', u'road'), (u'new york', u'city'), (u'ny', u'state'), (u'10023', u'postcode')], [(u'1', u'house_number'), (u'west 72nd street', u'road'), (u'new york', u'city'), (u'new york', u'state'), (u'10023', u'postcode')], [(u'1', u'house_number'), (u'west 72nd street', u'road'), (u'new york', u'city'), (u'ny', u'state'), (u'10023', u'postcode')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"====================================================================\n", | |
"\n", | |
"TEST SET: address_parsing\n", | |
"TEST: 101 saint mark pl 10009\n", | |
"1\n", | |
"[[(u'1', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"10\n", | |
"[[(u'10', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"101\n", | |
"[[(u'101', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"101 \n", | |
"[[(u'101', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"101 s\n", | |
"[[(u'101', u'house_number'), (u'san', u'road')], [(u'101', u'house_number'), (u'south', u'road')], [(u'101', u'house_number'), (u's', u'road')]]\n", | |
"\n", | |
"\n", | |
"101 sa\n", | |
"[[(u'101', u'house_number'), (u'southern', u'road'), (u'australia', u'country')]]\n", | |
"\n", | |
"\n", | |
"101 sai\n", | |
"[[(u'101', u'house_number'), (u'sai', u'road')]]\n", | |
"\n", | |
"\n", | |
"101 sain\n", | |
"[[(u'101', u'house_number'), (u'sain', u'road')]]\n", | |
"\n", | |
"\n", | |
"101 saint\n", | |
"[[(u'101', u'house_number'), (u'saint', u'road')]]\n", | |
"\n", | |
"\n", | |
"101 saint \n", | |
"[[(u'101', u'house_number'), (u'saint', u'road')]]\n", | |
"\n", | |
"\n", | |
"101 saint m\n", | |
"[[(u'101', u'house_number'), (u'saint mail', u'road')]]\n", | |
"\n", | |
"\n", | |
"101 saint ma\n", | |
"[[(u'101', u'house_number'), (u'saint', u'road'), (u'massachusetts', u'state')], [(u'101', u'house_number'), (u'saint ma', u'road')]]\n", | |
"\n", | |
"\n", | |
"101 saint mar\n", | |
"[[(u'101', u'house_number'), (u'saint mar', u'road')]]\n", | |
"\n", | |
"\n", | |
"101 saint mark\n", | |
"[[(u'101', u'house_number'), (u'saint mark', u'road')]]\n", | |
"\n", | |
"\n", | |
"101 saint mark \n", | |
"[[(u'101', u'house_number'), (u'saint mark', u'road')]]\n", | |
"\n", | |
"\n", | |
"101 saint mark p\n", | |
"[[(u'101', u'house_number'), (u'saint mark p', u'road')]]\n", | |
"\n", | |
"\n", | |
"101 saint mark pl\n", | |
"[[(u'101', u'house_number'), (u'saint mark place', u'road')], [(u'101', u'house_number'), (u'saint mark', u'road'), (u'plain', u'city')]]\n", | |
"\n", | |
"\n", | |
"101 saint mark pl \n", | |
"[[(u'101', u'house_number'), (u'saint mark place', u'road')], [(u'101', u'house_number'), (u'saint mark', u'road'), (u'plain', u'city')]]\n", | |
"\n", | |
"\n", | |
"101 saint mark pl 1\n", | |
"[[(u'101', u'house_number'), (u'saint mark place', u'road'), (u'1', u'house_number')], [(u'101', u'house_number'), (u'saint mark plain', u'road'), (u'1', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"101 saint mark pl 10\n", | |
"[[(u'101', u'house_number'), (u'saint mark place', u'road'), (u'10', u'house_number')], [(u'101', u'house_number'), (u'saint mark plain', u'road'), (u'10', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"101 saint mark pl 100\n", | |
"[[(u'101', u'house_number'), (u'saint mark', u'road'), (u'place', u'house'), (u'100', u'house_number')], [(u'101', u'house_number'), (u'saint mark plain', u'road'), (u'100', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"101 saint mark pl 1000\n", | |
"[[(u'101', u'house_number'), (u'saint mark place', u'road'), (u'1000', u'postcode')], [(u'101', u'house_number'), (u'saint mark', u'road'), (u'plain', u'suburb'), (u'1000', u'postcode')]]\n", | |
"\n", | |
"\n", | |
"101 saint mark pl 10009\n", | |
"[[(u'101', u'house_number'), (u'saint mark place', u'road'), (u'10009', u'postcode')], [(u'101', u'house_number'), (u'saint mark plain', u'road'), (u'10009', u'postcode')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: 1 water st manhattan ny\n", | |
"1\n", | |
"[[(u'1', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"1 \n", | |
"[[(u'1', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"1 w\n", | |
"[[(u'1', u'house_number'), (u'west', u'road')], [(u'1', u'house_number'), (u'w', u'house')]]\n", | |
"\n", | |
"\n", | |
"1 wa\n", | |
"[[(u'1', u'house_number'), (u'wa', u'state')], [(u'1', u'house_number'), (u'washington', u'road')], [(u'1', u'house_number'), (u'western australia', u'state')]]\n", | |
"\n", | |
"\n", | |
"1 wat\n", | |
"[[(u'1', u'house_number'), (u'wat', u'road')]]\n", | |
"\n", | |
"\n", | |
"1 wate\n", | |
"[[(u'1', u'house_number'), (u'wate', u'road')]]\n", | |
"\n", | |
"\n", | |
"1 water\n", | |
"[[(u'1', u'house_number'), (u'water', u'road')]]\n", | |
"\n", | |
"\n", | |
"1 water \n", | |
"[[(u'1', u'house_number'), (u'water', u'road')]]\n", | |
"\n", | |
"\n", | |
"1 water s\n", | |
"[[(u'1', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"1 water st\n", | |
"[[(u'1', u'house_number'), (u'water saint', u'road')], [(u'1', u'house_number'), (u'water street', u'road')]]\n", | |
"\n", | |
"\n", | |
"1 water st \n", | |
"[[(u'1', u'house_number'), (u'water saint', u'road')], [(u'1', u'house_number'), (u'water street', u'road')]]\n", | |
"\n", | |
"\n", | |
"1 water st m\n", | |
"[[(u'1', u'house_number'), (u'water saint mail', u'road')], [(u'1', u'house_number'), (u'water street', u'road'), (u'mail', u'suburb')]]\n", | |
"\n", | |
"\n", | |
"1 water st ma\n", | |
"[[(u'1', u'house_number'), (u'water saint', u'road'), (u'massachusetts', u'state')], [(u'1', u'house_number'), (u'water saint', u'road'), (u'ma', u'state')], [(u'1', u'house_number'), (u'water street', u'road'), (u'massachusetts', u'state')], [(u'1', u'house_number'), (u'water street', u'road'), (u'ma', u'state')]]\n", | |
"\n", | |
"\n", | |
"1 water st man\n", | |
"[[(u'1', u'house_number'), (u'water saint', u'road'), (u'man', u'city')], [(u'1', u'house_number'), (u'water street', u'road'), (u'man', u'city')]]\n", | |
"\n", | |
"\n", | |
"1 water st manh\n", | |
"[[(u'1', u'house_number'), (u'water saint manh', u'road')], [(u'1', u'house_number'), (u'water street', u'road'), (u'manh', u'city')]]\n", | |
"\n", | |
"\n", | |
"1 water st manha\n", | |
"[[(u'1', u'house_number'), (u'water saint manha', u'road')], [(u'1', u'house_number'), (u'water street', u'road'), (u'manha', u'city')]]\n", | |
"\n", | |
"\n", | |
"1 water st manhat\n", | |
"[[(u'1', u'house_number'), (u'water saint manhat', u'road')], [(u'1', u'house_number'), (u'water street', u'road'), (u'manhat', u'city')]]\n", | |
"\n", | |
"\n", | |
"1 water st manhatt\n", | |
"[[(u'1', u'house_number'), (u'water saint manhatt', u'road')], [(u'1', u'house_number'), (u'water street', u'road'), (u'manhatt', u'city')]]\n", | |
"\n", | |
"\n", | |
"1 water st manhatta\n", | |
"[[(u'1', u'house_number'), (u'water saint manhatta', u'road')], [(u'1', u'house_number'), (u'water street', u'road'), (u'manhatta', u'city')]]\n", | |
"\n", | |
"\n", | |
"1 water st manhattan\n", | |
"[[(u'1', u'house_number'), (u'water saint', u'road'), (u'manhattan', u'city')], [(u'1', u'house_number'), (u'water street', u'road'), (u'manhattan', u'city')]]\n", | |
"\n", | |
"\n", | |
"1 water st manhattan \n", | |
"[[(u'1', u'house_number'), (u'water saint', u'road'), (u'manhattan', u'city')], [(u'1', u'house_number'), (u'water street', u'road'), (u'manhattan', u'city')]]\n", | |
"\n", | |
"\n", | |
"1 water st manhattan n\n", | |
"[[(u'1', u'house_number'), (u'water saint', u'road'), (u'manhattan north', u'city')], [(u'1', u'house_number'), (u'water saint', u'road'), (u'manhattan', u'city'), (u'n', u'road')], [(u'1', u'house_number'), (u'water street', u'road'), (u'manhattan north', u'city')], [(u'1', u'house_number'), (u'water street', u'road'), (u'manhattan', u'city'), (u'n', u'road')]]\n", | |
"\n", | |
"\n", | |
"1 water st manhattan ny\n", | |
"[[(u'1', u'house_number'), (u'water saint', u'road'), (u'manhattan', u'city_district'), (u'new york', u'state')], [(u'1', u'house_number'), (u'water saint', u'road'), (u'manhattan', u'state_district'), (u'ny', u'state')], [(u'1', u'house_number'), (u'water street', u'road'), (u'manhattan', u'city_district'), (u'new york', u'state')], [(u'1', u'house_number'), (u'water street', u'road'), (u'manhattan', u'state_district'), (u'ny', u'state')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: 1 water st manhattan ny\n", | |
"1\n", | |
"[[(u'1', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"1 \n", | |
"[[(u'1', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"1 w\n", | |
"[[(u'1', u'house_number'), (u'west', u'road')], [(u'1', u'house_number'), (u'w', u'house')]]\n", | |
"\n", | |
"\n", | |
"1 wa\n", | |
"[[(u'1', u'house_number'), (u'wa', u'state')], [(u'1', u'house_number'), (u'washington', u'road')], [(u'1', u'house_number'), (u'western australia', u'state')]]\n", | |
"\n", | |
"\n", | |
"1 wat\n", | |
"[[(u'1', u'house_number'), (u'wat', u'road')]]\n", | |
"\n", | |
"\n", | |
"1 wate\n", | |
"[[(u'1', u'house_number'), (u'wate', u'road')]]\n", | |
"\n", | |
"\n", | |
"1 water\n", | |
"[[(u'1', u'house_number'), (u'water', u'road')]]\n", | |
"\n", | |
"\n", | |
"1 water \n", | |
"[[(u'1', u'house_number'), (u'water', u'road')]]\n", | |
"\n", | |
"\n", | |
"1 water s\n", | |
"[[(u'1', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"1 water st\n", | |
"[[(u'1', u'house_number'), (u'water saint', u'road')], [(u'1', u'house_number'), (u'water street', u'road')]]\n", | |
"\n", | |
"\n", | |
"1 water st \n", | |
"[[(u'1', u'house_number'), (u'water saint', u'road')], [(u'1', u'house_number'), (u'water street', u'road')]]\n", | |
"\n", | |
"\n", | |
"1 water st m\n", | |
"[[(u'1', u'house_number'), (u'water saint mail', u'road')], [(u'1', u'house_number'), (u'water street', u'road'), (u'mail', u'suburb')]]\n", | |
"\n", | |
"\n", | |
"1 water st ma\n", | |
"[[(u'1', u'house_number'), (u'water saint', u'road'), (u'massachusetts', u'state')], [(u'1', u'house_number'), (u'water saint', u'road'), (u'ma', u'state')], [(u'1', u'house_number'), (u'water street', u'road'), (u'massachusetts', u'state')], [(u'1', u'house_number'), (u'water street', u'road'), (u'ma', u'state')]]\n", | |
"\n", | |
"\n", | |
"1 water st man\n", | |
"[[(u'1', u'house_number'), (u'water saint', u'road'), (u'man', u'city')], [(u'1', u'house_number'), (u'water street', u'road'), (u'man', u'city')]]\n", | |
"\n", | |
"\n", | |
"1 water st manh\n", | |
"[[(u'1', u'house_number'), (u'water saint manh', u'road')], [(u'1', u'house_number'), (u'water street', u'road'), (u'manh', u'city')]]\n", | |
"\n", | |
"\n", | |
"1 water st manha\n", | |
"[[(u'1', u'house_number'), (u'water saint manha', u'road')], [(u'1', u'house_number'), (u'water street', u'road'), (u'manha', u'city')]]\n", | |
"\n", | |
"\n", | |
"1 water st manhat\n", | |
"[[(u'1', u'house_number'), (u'water saint manhat', u'road')], [(u'1', u'house_number'), (u'water street', u'road'), (u'manhat', u'city')]]\n", | |
"\n", | |
"\n", | |
"1 water st manhatt\n", | |
"[[(u'1', u'house_number'), (u'water saint manhatt', u'road')], [(u'1', u'house_number'), (u'water street', u'road'), (u'manhatt', u'city')]]\n", | |
"\n", | |
"\n", | |
"1 water st manhatta\n", | |
"[[(u'1', u'house_number'), (u'water saint manhatta', u'road')], [(u'1', u'house_number'), (u'water street', u'road'), (u'manhatta', u'city')]]\n", | |
"\n", | |
"\n", | |
"1 water st manhattan\n", | |
"[[(u'1', u'house_number'), (u'water saint', u'road'), (u'manhattan', u'city')], [(u'1', u'house_number'), (u'water street', u'road'), (u'manhattan', u'city')]]\n", | |
"\n", | |
"\n", | |
"1 water st manhattan \n", | |
"[[(u'1', u'house_number'), (u'water saint', u'road'), (u'manhattan', u'city')], [(u'1', u'house_number'), (u'water street', u'road'), (u'manhattan', u'city')]]\n", | |
"\n", | |
"\n", | |
"1 water st manhattan n\n", | |
"[[(u'1', u'house_number'), (u'water saint', u'road'), (u'manhattan north', u'city')], [(u'1', u'house_number'), (u'water saint', u'road'), (u'manhattan', u'city'), (u'n', u'road')], [(u'1', u'house_number'), (u'water street', u'road'), (u'manhattan north', u'city')], [(u'1', u'house_number'), (u'water street', u'road'), (u'manhattan', u'city'), (u'n', u'road')]]\n", | |
"\n", | |
"\n", | |
"1 water st manhattan ny\n", | |
"[[(u'1', u'house_number'), (u'water saint', u'road'), (u'manhattan', u'city_district'), (u'new york', u'state')], [(u'1', u'house_number'), (u'water saint', u'road'), (u'manhattan', u'state_district'), (u'ny', u'state')], [(u'1', u'house_number'), (u'water street', u'road'), (u'manhattan', u'city_district'), (u'new york', u'state')], [(u'1', u'house_number'), (u'water street', u'road'), (u'manhattan', u'state_district'), (u'ny', u'state')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: 450 w 37th st, new york, ny 11232\n", | |
"4\n", | |
"[[(u'4', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"45\n", | |
"[[(u'45', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"450\n", | |
"[[(u'450', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"450 \n", | |
"[[(u'450', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"450 w\n", | |
"[[(u'450', u'house_number'), (u'west', u'road')], [(u'450', u'house_number'), (u'w', u'house')]]\n", | |
"\n", | |
"\n", | |
"450 w \n", | |
"[[(u'450', u'house_number'), (u'west', u'road')], [(u'450', u'house_number'), (u'w', u'house')]]\n", | |
"\n", | |
"\n", | |
"450 w 3\n", | |
"[[(u'450', u'house_number'), (u'west', u'road'), (u'3', u'house_number')], [(u'450', u'house_number'), (u'w', u'road'), (u'3', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"450 w 37\n", | |
"[[(u'450', u'house_number'), (u'west 37', u'road')], [(u'450', u'house_number'), (u'w 37', u'road')]]\n", | |
"\n", | |
"\n", | |
"450 w 37t\n", | |
"[[(u'450', u'house_number'), (u'west', u'road'), (u'37t', u'house_number')], [(u'450', u'house_number'), (u'w', u'road'), (u'37t', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"450 w 37th\n", | |
"[[(u'450', u'house_number'), (u'west 37th', u'road')], [(u'450', u'house_number'), (u'w 37th', u'road')]]\n", | |
"\n", | |
"\n", | |
"450 w 37th \n", | |
"[[(u'450', u'house_number'), (u'west 37th', u'road')], [(u'450', u'house_number'), (u'w 37th', u'road')]]\n", | |
"\n", | |
"\n", | |
"450 w 37th s\n", | |
"[[(u'450', u'house_number'), (u'west 37th san', u'road')], [(u'450', u'house_number'), (u'west 37th south', u'road')], [(u'450', u'house_number'), (u'west 37th s', u'road')], [(u'450', u'house_number'), (u'w 37th san', u'road')], [(u'450', u'house_number'), (u'w 37th south', u'road')], [(u'450', u'house_number'), (u'w 37th s', u'road')]]\n", | |
"\n", | |
"\n", | |
"450 w 37th st\n", | |
"[[(u'450', u'house_number'), (u'west 37th saint', u'road')], [(u'450', u'house_number'), (u'west 37th street', u'road')], [(u'450', u'house_number'), (u'w 37th saint', u'road')], [(u'450', u'house_number'), (u'w 37th street', u'road')]]\n", | |
"\n", | |
"\n", | |
"450 w 37th st,\n", | |
"[[(u'450', u'house_number'), (u'west 37th saint', u'road')], [(u'450', u'house_number'), (u'west 37th street', u'road')], [(u'450', u'house_number'), (u'w 37th saint', u'road')], [(u'450', u'house_number'), (u'w 37th street', u'road')]]\n", | |
"\n", | |
"\n", | |
"450 w 37th st, \n", | |
"[[(u'450', u'house_number'), (u'west 37th saint', u'road')], [(u'450', u'house_number'), (u'west 37th street', u'road')], [(u'450', u'house_number'), (u'w 37th saint', u'road')], [(u'450', u'house_number'), (u'w 37th street', u'road')]]\n", | |
"\n", | |
"\n", | |
"450 w 37th st, n\n", | |
"[[(u'450', u'house_number'), (u'west 37th saint north', u'road')], [(u'450', u'house_number'), (u'west 37th saint n', u'road')], [(u'450', u'house_number'), (u'west 37th street north', u'road')], [(u'450', u'house_number'), (u'west 37th street n', u'road')], [(u'450', u'house_number'), (u'w 37th saint north', u'road')], [(u'450', u'house_number'), (u'w 37th street north', u'road')], [(u'450', u'house_number'), (u'w 37th street n', u'road')]]\n", | |
"\n", | |
"\n", | |
"450 w 37th st, ne\n", | |
"[[(u'450', u'house_number'), (u'west 37th saint ne', u'road')], [(u'450', u'house_number'), (u'west 37th saint northeast', u'road')], [(u'450', u'house_number'), (u'west 37th saint', u'road'), (u'nebraska', u'state')], [(u'450', u'house_number'), (u'west 37th street ne', u'road')], [(u'450', u'house_number'), (u'west 37th street northeast', u'road')], [(u'450', u'house_number'), (u'west 37th street', u'road'), (u'nebraska', u'state')], [(u'450', u'house_number'), (u'w 37th saint ne', u'road')], [(u'450', u'house_number'), (u'w 37th street ne', u'road')], [(u'450', u'house_number'), (u'w 37th street northeast', u'road')], [(u'450', u'house_number'), (u'w 37th street', u'road'), (u'nebraska', u'state')]]\n", | |
"\n", | |
"\n", | |
"450 w 37th st, new\n", | |
"[[(u'450', u'house_number'), (u'west 37th saint new', u'road')], [(u'450', u'house_number'), (u'west 37th street', u'road'), (u'new', u'suburb')], [(u'450', u'house_number'), (u'w 37th saint new', u'road')], [(u'450', u'house_number'), (u'w 37th street', u'road'), (u'new', u'suburb')]]\n", | |
"\n", | |
"\n", | |
"450 w 37th st, new \n", | |
"[[(u'450', u'house_number'), (u'west 37th saint new', u'road')], [(u'450', u'house_number'), (u'west 37th street', u'road'), (u'new', u'suburb')], [(u'450', u'house_number'), (u'w 37th saint new', u'road')], [(u'450', u'house_number'), (u'w 37th street', u'road'), (u'new', u'suburb')]]\n", | |
"\n", | |
"\n", | |
"450 w 37th st, new y\n", | |
"[[(u'450', u'house_number'), (u'west 37th saint new y', u'road')], [(u'450', u'house_number'), (u'west 37th street new y', u'road')], [(u'450', u'house_number'), (u'w 37th saint new y', u'road')], [(u'450', u'house_number'), (u'w 37th street new y', u'road')]]\n", | |
"\n", | |
"\n", | |
"450 w 37th st, new yo\n", | |
"[[(u'450', u'house_number'), (u'west 37th saint', u'road'), (u'new yo', u'house')], [(u'450', u'house_number'), (u'west 37th street', u'road'), (u'new yo', u'suburb')], [(u'450', u'house_number'), (u'w 37th saint', u'road'), (u'new yo', u'house')], [(u'450', u'house_number'), (u'w 37th street', u'road'), (u'new yo', u'suburb')]]\n", | |
"\n", | |
"\n", | |
"450 w 37th st, new yor\n", | |
"[[(u'450', u'house_number'), (u'west 37th saint new', u'road'), (u'yor', u'suburb')], [(u'450', u'house_number'), (u'west 37th street', u'road'), (u'new yor', u'suburb')], [(u'450', u'house_number'), (u'w 37th saint new', u'road'), (u'yor', u'suburb')], [(u'450', u'house_number'), (u'w 37th street', u'road'), (u'new yor', u'suburb')]]\n", | |
"\n", | |
"\n", | |
"450 w 37th st, new york\n", | |
"[[(u'450', u'house_number'), (u'west 37th saint', u'road'), (u'new york', u'state')], [(u'450', u'house_number'), (u'west 37th street', u'road'), (u'new york', u'state')], [(u'450', u'house_number'), (u'w 37th saint', u'road'), (u'new york', u'state')], [(u'450', u'house_number'), (u'w 37th street', u'road'), (u'new york', u'state')]]\n", | |
"\n", | |
"\n", | |
"450 w 37th st, new york,\n", | |
"[[(u'450', u'house_number'), (u'west 37th saint', u'road'), (u'new york', u'state')], [(u'450', u'house_number'), (u'west 37th street', u'road'), (u'new york', u'state')], [(u'450', u'house_number'), (u'w 37th saint', u'road'), (u'new york', u'state')], [(u'450', u'house_number'), (u'w 37th street', u'road'), (u'new york', u'state')]]\n", | |
"\n", | |
"\n", | |
"450 w 37th st, new york, \n", | |
"[[(u'450', u'house_number'), (u'west 37th saint', u'road'), (u'new york', u'state')], [(u'450', u'house_number'), (u'west 37th street', u'road'), (u'new york', u'state')], [(u'450', u'house_number'), (u'w 37th saint', u'road'), (u'new york', u'state')], [(u'450', u'house_number'), (u'w 37th street', u'road'), (u'new york', u'state')]]\n", | |
"\n", | |
"\n", | |
"450 w 37th st, new york, n\n", | |
"[[(u'450', u'house_number'), (u'west 37th saint', u'road'), (u'new', u'state'), (u'york', u'house'), (u'north', u'road')], [(u'450', u'house_number'), (u'west 37th saint', u'road'), (u'new york', u'state'), (u'n', u'postcode')], [(u'450', u'house_number'), (u'west 37th street', u'road'), (u'new york', u'state'), (u'north', u'road')], [(u'450', u'house_number'), (u'west 37th street', u'road'), (u'new york', u'state'), (u'n', u'postcode')], [(u'450', u'house_number'), (u'w 37th saint', u'road'), (u'new', u'state'), (u'york', u'house'), (u'north', u'road')], [(u'450', u'house_number'), (u'w 37th street', u'road'), (u'new york', u'state'), (u'north', u'road')], [(u'450', u'house_number'), (u'w 37th street', u'road'), (u'new york', u'state'), (u'n', u'postcode')]]\n", | |
"\n", | |
"\n", | |
"450 w 37th st, new york, ny\n", | |
"[[(u'450', u'house_number'), (u'west 37th saint', u'road'), (u'new york', u'city'), (u'new york', u'state')], [(u'450', u'house_number'), (u'west 37th saint', u'road'), (u'new york', u'city'), (u'ny', u'state')], [(u'450', u'house_number'), (u'west 37th street', u'road'), (u'new york', u'city'), (u'new york', u'state')], [(u'450', u'house_number'), (u'west 37th street', u'road'), (u'new york', u'city'), (u'ny', u'state')], [(u'450', u'house_number'), (u'w 37th saint', u'road'), (u'new york', u'city'), (u'new york', u'state')], [(u'450', u'house_number'), (u'w 37th street', u'road'), (u'new york', u'city'), (u'new york', u'state')], [(u'450', u'house_number'), (u'w 37th street', u'road'), (u'new york', u'city'), (u'ny', u'state')]]\n", | |
"\n", | |
"\n", | |
"450 w 37th st, new york, ny \n", | |
"[[(u'450', u'house_number'), (u'west 37th saint', u'road'), (u'new york', u'city'), (u'new york', u'state')], [(u'450', u'house_number'), (u'west 37th saint', u'road'), (u'new york', u'city'), (u'ny', u'state')], [(u'450', u'house_number'), (u'west 37th street', u'road'), (u'new york', u'city'), (u'new york', u'state')], [(u'450', u'house_number'), (u'west 37th street', u'road'), (u'new york', u'city'), (u'ny', u'state')], [(u'450', u'house_number'), (u'w 37th saint', u'road'), (u'new york', u'city'), (u'new york', u'state')], [(u'450', u'house_number'), (u'w 37th street', u'road'), (u'new york', u'city'), (u'new york', u'state')], [(u'450', u'house_number'), (u'w 37th street', u'road'), (u'new york', u'city'), (u'ny', u'state')]]\n", | |
"\n", | |
"\n", | |
"450 w 37th st, new york, ny 1\n", | |
"[[(u'450', u'house_number'), (u'west 37th saint', u'road'), (u'new york', u'city'), (u'new york', u'state'), (u'1', u'postcode')], [(u'450', u'house_number'), (u'west 37th saint', u'road'), (u'new york', u'city'), (u'ny', u'state'), (u'1', u'postcode')], [(u'450', u'house_number'), (u'west 37th street', u'road'), (u'new york', u'city'), (u'new york', u'state'), (u'1', u'postcode')], [(u'450', u'house_number'), (u'west 37th street', u'road'), (u'new york', u'city'), (u'ny', u'state'), (u'1', u'postcode')], [(u'450', u'house_number'), (u'w 37th saint', u'road'), (u'new york', u'city'), (u'new york', u'state'), (u'1', u'postcode')], [(u'450', u'house_number'), (u'w 37th street', u'road'), (u'new york', u'city'), (u'new york', u'state'), (u'1', u'postcode')], [(u'450', u'house_number'), (u'w 37th street', u'road'), (u'new york', u'city'), (u'ny', u'state'), (u'1', u'postcode')]]\n", | |
"\n", | |
"\n", | |
"450 w 37th st, new york, ny 11\n", | |
"[[(u'450', u'house_number'), (u'west 37th saint', u'road'), (u'new york', u'city'), (u'new york', u'state'), (u'11', u'postcode')], [(u'450', u'house_number'), (u'west 37th saint', u'road'), (u'new york', u'city'), (u'ny', u'state'), (u'11', u'postcode')], [(u'450', u'house_number'), (u'west 37th street', u'road'), (u'new york', u'city'), (u'new york', u'state'), (u'11', u'postcode')], [(u'450', u'house_number'), (u'west 37th street', u'road'), (u'new york', u'city'), (u'ny', u'state'), (u'11', u'postcode')], [(u'450', u'house_number'), (u'w 37th saint', u'road'), (u'new york', u'city'), (u'new york', u'state'), (u'11', u'postcode')], [(u'450', u'house_number'), (u'w 37th street', u'road'), (u'new york', u'city'), (u'new york', u'state'), (u'11', u'postcode')], [(u'450', u'house_number'), (u'w 37th street', u'road'), (u'new york', u'city'), (u'ny', u'state'), (u'11', u'postcode')]]\n", | |
"\n", | |
"\n", | |
"450 w 37th st, new york, ny 112\n", | |
"[[(u'450', u'house_number'), (u'west 37th saint', u'road'), (u'new york', u'city'), (u'new york', u'state'), (u'112', u'postcode')], [(u'450', u'house_number'), (u'west 37th saint', u'road'), (u'new', u'city'), (u'york', u'house'), (u'ny', u'state'), (u'112', u'house_number')], [(u'450', u'house_number'), (u'west 37th street', u'road'), (u'new york', u'city'), (u'new york', u'state'), (u'112', u'postcode')], [(u'450', u'house_number'), (u'west 37th street', u'road'), (u'new york', u'city'), (u'ny', u'state'), (u'112', u'postcode')], [(u'450', u'house_number'), (u'w 37th saint', u'road'), (u'new york', u'city'), (u'new york', u'state'), (u'112', u'postcode')], [(u'450', u'house_number'), (u'w 37th street', u'road'), (u'new york', u'city'), (u'new york', u'state'), (u'112', u'postcode')], [(u'450', u'house_number'), (u'w 37th street', u'road'), (u'new york', u'city'), (u'ny', u'state'), (u'112', u'postcode')]]\n", | |
"\n", | |
"\n", | |
"450 w 37th st, new york, ny 1123\n", | |
"[[(u'450', u'house_number'), (u'west 37th saint', u'road'), (u'new york', u'city'), (u'new york', u'state'), (u'1123', u'postcode')], [(u'450', u'house_number'), (u'west 37th saint', u'road'), (u'new york', u'city'), (u'ny', u'state'), (u'1123', u'postcode')], [(u'450', u'house_number'), (u'west 37th street', u'road'), (u'new york', u'city'), (u'new york', u'state'), (u'1123', u'postcode')], [(u'450', u'house_number'), (u'west 37th street', u'road'), (u'new york', u'city'), (u'ny', u'state'), (u'1123', u'postcode')], [(u'450', u'house_number'), (u'w 37th saint', u'road'), (u'new york', u'city'), (u'new york', u'state'), (u'1123', u'postcode')], [(u'450', u'house_number'), (u'w 37th street', u'road'), (u'new york', u'city'), (u'new york', u'state'), (u'1123', u'postcode')], [(u'450', u'house_number'), (u'w 37th street', u'road'), (u'new york', u'city'), (u'ny', u'state'), (u'1123', u'postcode')]]\n", | |
"\n", | |
"\n", | |
"450 w 37th st, new york, ny 11232\n", | |
"[[(u'450', u'house_number'), (u'west 37th saint', u'road'), (u'new york', u'city'), (u'new york', u'state'), (u'11232', u'postcode')], [(u'450', u'house_number'), (u'west 37th saint', u'road'), (u'new york', u'city'), (u'ny', u'state'), (u'11232', u'postcode')], [(u'450', u'house_number'), (u'west 37th street', u'road'), (u'new york', u'city'), (u'new york', u'state'), (u'11232', u'postcode')], [(u'450', u'house_number'), (u'west 37th street', u'road'), (u'new york', u'city'), (u'ny', u'state'), (u'11232', u'postcode')], [(u'450', u'house_number'), (u'w 37th saint', u'road'), (u'new york', u'city'), (u'new york', u'state'), (u'11232', u'postcode')], [(u'450', u'house_number'), (u'w 37th street', u'road'), (u'new york', u'city'), (u'new york', u'state'), (u'11232', u'postcode')], [(u'450', u'house_number'), (u'w 37th street', u'road'), (u'new york', u'city'), (u'ny', u'state'), (u'11232', u'postcode')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: starbucks 10010\n", | |
"s\n", | |
"[[(u'san', u'road')], [(u'south', u'road')], [(u's', u'road')]]\n", | |
"\n", | |
"\n", | |
"st\n", | |
"[[(u'saint', u'house')], [(u'street', u'road')]]\n", | |
"\n", | |
"\n", | |
"sta\n", | |
"[[(u'station', u'house')], [(u'santa', u'road')]]\n", | |
"\n", | |
"\n", | |
"star\n", | |
"[[(u'star', u'house')]]\n", | |
"\n", | |
"\n", | |
"starb\n", | |
"[[(u'starb', u'house')]]\n", | |
"\n", | |
"\n", | |
"starbu\n", | |
"[[(u'starbu', u'house')]]\n", | |
"\n", | |
"\n", | |
"starbuc\n", | |
"[[(u'starbuc', u'house')]]\n", | |
"\n", | |
"\n", | |
"starbuck\n", | |
"[[(u'starbuck', u'city')]]\n", | |
"\n", | |
"\n", | |
"starbucks\n", | |
"[[(u'starbucks', u'house')]]\n", | |
"\n", | |
"\n", | |
"starbucks \n", | |
"[[(u'starbucks', u'house')]]\n", | |
"\n", | |
"\n", | |
"starbucks 1\n", | |
"[[(u'starbucks', u'house'), (u'1', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"starbucks 10\n", | |
"[[(u'starbucks', u'house'), (u'10', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"starbucks 100\n", | |
"[[(u'starbucks', u'house'), (u'100', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"starbucks 1001\n", | |
"[[(u'starbucks', u'house'), (u'1001', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"starbucks 10010\n", | |
"[[(u'starbucks', u'house'), (u'10010', u'postcode')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: 455 43rd st new york ny 11232\n", | |
"4\n", | |
"[[(u'4', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"45\n", | |
"[[(u'45', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"455\n", | |
"[[(u'455', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"455 \n", | |
"[[(u'455', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"455 4\n", | |
"[[(u'455 4', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"455 43\n", | |
"[[(u'455', u'road'), (u'43', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"455 43r\n", | |
"[[(u'455 43r', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"455 43rd\n", | |
"[[(u'455', u'house_number'), (u'43rd', u'road')]]\n", | |
"\n", | |
"\n", | |
"455 43rd \n", | |
"[[(u'455', u'house_number'), (u'43rd', u'road')]]\n", | |
"\n", | |
"\n", | |
"455 43rd s\n", | |
"[[(u'455', u'house_number'), (u'43rd san', u'road')], [(u'455', u'house_number'), (u'43rd south', u'road')], [(u'455', u'house_number'), (u'43rd s', u'road')]]\n", | |
"\n", | |
"\n", | |
"455 43rd st\n", | |
"[[(u'455', u'house_number'), (u'43rd saint', u'road')], [(u'455', u'house_number'), (u'43rd street', u'road')]]\n", | |
"\n", | |
"\n", | |
"455 43rd st \n", | |
"[[(u'455', u'house_number'), (u'43rd saint', u'road')], [(u'455', u'house_number'), (u'43rd street', u'road')]]\n", | |
"\n", | |
"\n", | |
"455 43rd st n\n", | |
"[[(u'455', u'house_number'), (u'43rd saint north', u'road')], [(u'455', u'house_number'), (u'43rd saint n', u'road')], [(u'455', u'house_number'), (u'43rd street north', u'road')], [(u'455', u'house_number'), (u'43rd street n', u'road')]]\n", | |
"\n", | |
"\n", | |
"455 43rd st ne\n", | |
"[[(u'455', u'house_number'), (u'43rd saint ne', u'road')], [(u'455', u'house_number'), (u'43rd saint northeast', u'road')], [(u'455', u'house_number'), (u'43rd saint', u'road'), (u'nebraska', u'state')], [(u'455', u'house_number'), (u'43rd street ne', u'road')], [(u'455', u'house_number'), (u'43rd street northeast', u'road')], [(u'455', u'house_number'), (u'43rd street', u'road'), (u'nebraska', u'state')]]\n", | |
"\n", | |
"\n", | |
"455 43rd st new\n", | |
"[[(u'455', u'house_number'), (u'43rd saint new', u'road')], [(u'455', u'house_number'), (u'43rd street', u'road'), (u'new', u'suburb')]]\n", | |
"\n", | |
"\n", | |
"455 43rd st new \n", | |
"[[(u'455', u'house_number'), (u'43rd saint new', u'road')], [(u'455', u'house_number'), (u'43rd street', u'road'), (u'new', u'suburb')]]\n", | |
"\n", | |
"\n", | |
"455 43rd st new y\n", | |
"[[(u'455', u'house_number'), (u'43rd saint new y', u'road')], [(u'455', u'house_number'), (u'43rd street new y', u'road')]]\n", | |
"\n", | |
"\n", | |
"455 43rd st new yo\n", | |
"[[(u'455', u'house_number'), (u'43rd saint', u'road'), (u'new yo', u'house')], [(u'455', u'house_number'), (u'43rd street', u'road'), (u'new yo', u'suburb')]]\n", | |
"\n", | |
"\n", | |
"455 43rd st new yor\n", | |
"[[(u'455', u'house_number'), (u'43rd saint new', u'road'), (u'yor', u'suburb')], [(u'455', u'house_number'), (u'43rd street', u'road'), (u'new yor', u'suburb')]]\n", | |
"\n", | |
"\n", | |
"455 43rd st new york\n", | |
"[[(u'455', u'house_number'), (u'43rd saint', u'road'), (u'new york', u'state')], [(u'455', u'house_number'), (u'43rd street', u'road'), (u'new york', u'state')]]\n", | |
"\n", | |
"\n", | |
"455 43rd st new york \n", | |
"[[(u'455', u'house_number'), (u'43rd saint', u'road'), (u'new york', u'state')], [(u'455', u'house_number'), (u'43rd street', u'road'), (u'new york', u'state')]]\n", | |
"\n", | |
"\n", | |
"455 43rd st new york n\n", | |
"[[(u'455', u'house_number'), (u'43rd saint', u'road'), (u'new', u'state'), (u'york', u'house'), (u'north', u'road')], [(u'455', u'house_number'), (u'43rd saint', u'road'), (u'new york', u'state'), (u'n', u'postcode')], [(u'455', u'house_number'), (u'43rd street', u'road'), (u'new york', u'state'), (u'north', u'road')], [(u'455', u'house_number'), (u'43rd street', u'road'), (u'new york', u'state'), (u'n', u'postcode')]]\n", | |
"\n", | |
"\n", | |
"455 43rd st new york ny\n", | |
"[[(u'455', u'house_number'), (u'43rd saint', u'road'), (u'new york', u'city'), (u'new york', u'state')], [(u'455', u'house_number'), (u'43rd saint', u'road'), (u'new york', u'city'), (u'ny', u'state')], [(u'455', u'house_number'), (u'43rd street', u'road'), (u'new york', u'city'), (u'new york', u'state')], [(u'455', u'house_number'), (u'43rd street', u'road'), (u'new york', u'city'), (u'ny', u'state')]]\n", | |
"\n", | |
"\n", | |
"455 43rd st new york ny \n", | |
"[[(u'455', u'house_number'), (u'43rd saint', u'road'), (u'new york', u'city'), (u'new york', u'state')], [(u'455', u'house_number'), (u'43rd saint', u'road'), (u'new york', u'city'), (u'ny', u'state')], [(u'455', u'house_number'), (u'43rd street', u'road'), (u'new york', u'city'), (u'new york', u'state')], [(u'455', u'house_number'), (u'43rd street', u'road'), (u'new york', u'city'), (u'ny', u'state')]]\n", | |
"\n", | |
"\n", | |
"455 43rd st new york ny 1\n", | |
"[[(u'455', u'house_number'), (u'43rd saint', u'road'), (u'new york', u'city'), (u'new york', u'state'), (u'1', u'postcode')], [(u'455', u'house_number'), (u'43rd saint', u'road'), (u'new york', u'city'), (u'ny', u'state'), (u'1', u'postcode')], [(u'455', u'house_number'), (u'43rd street', u'road'), (u'new york', u'city'), (u'new york', u'state'), (u'1', u'postcode')], [(u'455', u'house_number'), (u'43rd street', u'road'), (u'new york', u'city'), (u'ny', u'state'), (u'1', u'postcode')]]\n", | |
"\n", | |
"\n", | |
"455 43rd st new york ny 11\n", | |
"[[(u'455', u'house_number'), (u'43rd saint', u'road'), (u'new york', u'city'), (u'new york', u'state'), (u'11', u'postcode')], [(u'455', u'house_number'), (u'43rd saint', u'road'), (u'new york', u'city'), (u'ny', u'state'), (u'11', u'postcode')], [(u'455', u'house_number'), (u'43rd street', u'road'), (u'new york', u'city'), (u'new york', u'state'), (u'11', u'postcode')], [(u'455', u'house_number'), (u'43rd street', u'road'), (u'new york', u'city'), (u'ny', u'state'), (u'11', u'postcode')]]\n", | |
"\n", | |
"\n", | |
"455 43rd st new york ny 112\n", | |
"[[(u'455', u'house_number'), (u'43rd saint', u'road'), (u'new york', u'city'), (u'new york', u'state'), (u'112', u'postcode')], [(u'455', u'house_number'), (u'43rd saint', u'road'), (u'new', u'city'), (u'york', u'house'), (u'ny', u'state'), (u'112', u'house_number')], [(u'455', u'house_number'), (u'43rd street', u'road'), (u'new york', u'city'), (u'new york', u'state'), (u'112', u'postcode')], [(u'455', u'house_number'), (u'43rd street', u'road'), (u'new york', u'city'), (u'ny', u'state'), (u'112', u'postcode')]]\n", | |
"\n", | |
"\n", | |
"455 43rd st new york ny 1123\n", | |
"[[(u'455', u'house_number'), (u'43rd saint', u'road'), (u'new york', u'city'), (u'new york', u'state'), (u'1123', u'postcode')], [(u'455', u'house_number'), (u'43rd saint', u'road'), (u'new york', u'city'), (u'ny', u'state'), (u'1123', u'postcode')], [(u'455', u'house_number'), (u'43rd street', u'road'), (u'new york', u'city'), (u'new york', u'state'), (u'1123', u'postcode')], [(u'455', u'house_number'), (u'43rd street', u'road'), (u'new york', u'city'), (u'ny', u'state'), (u'1123', u'postcode')]]\n", | |
"\n", | |
"\n", | |
"455 43rd st new york ny 11232\n", | |
"[[(u'455', u'house_number'), (u'43rd saint', u'road'), (u'new york', u'city'), (u'new york', u'state'), (u'11232', u'postcode')], [(u'455', u'house_number'), (u'43rd saint', u'road'), (u'new york', u'city'), (u'ny', u'state'), (u'11232', u'postcode')], [(u'455', u'house_number'), (u'43rd street', u'road'), (u'new york', u'city'), (u'new york', u'state'), (u'11232', u'postcode')], [(u'455', u'house_number'), (u'43rd street', u'road'), (u'new york', u'city'), (u'ny', u'state'), (u'11232', u'postcode')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: 1 main st ny 11201\n", | |
"1\n", | |
"[[(u'1', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"1 \n", | |
"[[(u'1', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"1 m\n", | |
"[[(u'1', u'house_number'), (u'mail', u'road')]]\n", | |
"\n", | |
"\n", | |
"1 ma\n", | |
"[[(u'1', u'house_number'), (u'massachusetts', u'state')], [(u'1', u'house_number'), (u'ma', u'road')]]\n", | |
"\n", | |
"\n", | |
"1 mai\n", | |
"[[(u'1 mai', u'road')]]\n", | |
"\n", | |
"\n", | |
"1 main\n", | |
"[[(u'1', u'house_number'), (u'main', u'road')]]\n", | |
"\n", | |
"\n", | |
"1 main \n", | |
"[[(u'1', u'house_number'), (u'main', u'road')]]\n", | |
"\n", | |
"\n", | |
"1 main s\n", | |
"[[(u'1', u'house_number'), (u'main san', u'road')], [(u'1', u'house_number'), (u'main south', u'road')], [(u'1', u'house_number'), (u'main s', u'road')]]\n", | |
"\n", | |
"\n", | |
"1 main st\n", | |
"[[(u'1', u'house_number'), (u'main saint', u'road')], [(u'1', u'house_number'), (u'main street', u'road')]]\n", | |
"\n", | |
"\n", | |
"1 main st \n", | |
"[[(u'1', u'house_number'), (u'main saint', u'road')], [(u'1', u'house_number'), (u'main street', u'road')]]\n", | |
"\n", | |
"\n", | |
"1 main st n\n", | |
"[[(u'1', u'house_number'), (u'main saint north', u'road')], [(u'1', u'house_number'), (u'main saint n', u'road')], [(u'1', u'house_number'), (u'main street north', u'road')], [(u'1', u'house_number'), (u'main street n', u'road')]]\n", | |
"\n", | |
"\n", | |
"1 main st ny\n", | |
"[[(u'1', u'house_number'), (u'main saint', u'road'), (u'new york', u'state')], [(u'1', u'house_number'), (u'main saint', u'road'), (u'ny', u'state')], [(u'1', u'house_number'), (u'main street', u'road'), (u'new york', u'state')], [(u'1', u'house_number'), (u'main street', u'road'), (u'ny', u'state')]]\n", | |
"\n", | |
"\n", | |
"1 main st ny \n", | |
"[[(u'1', u'house_number'), (u'main saint', u'road'), (u'new york', u'state')], [(u'1', u'house_number'), (u'main saint', u'road'), (u'ny', u'state')], [(u'1', u'house_number'), (u'main street', u'road'), (u'new york', u'state')], [(u'1', u'house_number'), (u'main street', u'road'), (u'ny', u'state')]]\n", | |
"\n", | |
"\n", | |
"1 main st ny 1\n", | |
"[[(u'1', u'house_number'), (u'main saint', u'road'), (u'new york', u'house'), (u'1', u'house_number')], [(u'1', u'house_number'), (u'main saint', u'road'), (u'ny', u'state'), (u'1', u'postcode')], [(u'1', u'house_number'), (u'main street', u'road'), (u'new york', u'state'), (u'1', u'postcode')], [(u'1', u'house_number'), (u'main street', u'road'), (u'ny', u'state'), (u'1', u'postcode')]]\n", | |
"\n", | |
"\n", | |
"1 main st ny 11\n", | |
"[[(u'1', u'house_number'), (u'main saint new york', u'road'), (u'11', u'house_number')], [(u'1', u'house_number'), (u'main saint', u'road'), (u'ny', u'state'), (u'11', u'postcode')], [(u'1', u'house_number'), (u'main street', u'road'), (u'new york', u'state'), (u'11', u'postcode')], [(u'1', u'house_number'), (u'main street', u'road'), (u'ny', u'state'), (u'11', u'postcode')]]\n", | |
"\n", | |
"\n", | |
"1 main st ny 112\n", | |
"[[(u'1', u'house_number'), (u'main saint', u'road'), (u'new york', u'house'), (u'112', u'house_number')], [(u'1', u'house_number'), (u'main saint', u'road'), (u'ny', u'state'), (u'112', u'postcode')], [(u'1', u'house_number'), (u'main street', u'road'), (u'new york', u'state'), (u'112', u'postcode')], [(u'1', u'house_number'), (u'main street', u'road'), (u'ny', u'state'), (u'112', u'postcode')]]\n", | |
"\n", | |
"\n", | |
"1 main st ny 1120\n", | |
"[[(u'1', u'house_number'), (u'main saint new york', u'road'), (u'1120', u'house_number')], [(u'1', u'house_number'), (u'main saint', u'road'), (u'ny', u'state'), (u'1120', u'postcode')], [(u'1', u'house_number'), (u'main street', u'road'), (u'new york', u'state'), (u'1120', u'postcode')], [(u'1', u'house_number'), (u'main street', u'road'), (u'ny', u'state'), (u'1120', u'postcode')]]\n", | |
"\n", | |
"\n", | |
"1 main st ny 11201\n", | |
"[[(u'1', u'house_number'), (u'main saint', u'road'), (u'new york', u'state'), (u'11201', u'postcode')], [(u'1', u'house_number'), (u'main saint', u'road'), (u'ny', u'state'), (u'11201', u'postcode')], [(u'1', u'house_number'), (u'main street', u'road'), (u'new york', u'state'), (u'11201', u'postcode')], [(u'1', u'house_number'), (u'main street', u'road'), (u'ny', u'state'), (u'11201', u'postcode')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: 186 Tuskegee St SE Atlanta GA\n", | |
"1\n", | |
"[[(u'1', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"18\n", | |
"[[(u'18', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"186\n", | |
"[[(u'186', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"186 \n", | |
"[[(u'186', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"186 T\n", | |
"[[(u'186', u'house_number'), (u't', u'road')]]\n", | |
"\n", | |
"\n", | |
"186 Tu\n", | |
"[[(u'186', u'house_number'), (u'tu', u'house')]]\n", | |
"\n", | |
"\n", | |
"186 Tus\n", | |
"[[(u'186', u'house_number'), (u'tus', u'house')]]\n", | |
"\n", | |
"\n", | |
"186 Tusk\n", | |
"[[(u'186', u'house_number'), (u'tusk', u'road')]]\n", | |
"\n", | |
"\n", | |
"186 Tuske\n", | |
"[[(u'186', u'house_number'), (u'tuske', u'road')]]\n", | |
"\n", | |
"\n", | |
"186 Tuskeg\n", | |
"[[(u'186', u'house_number'), (u'tuskeg', u'road')]]\n", | |
"\n", | |
"\n", | |
"186 Tuskege\n", | |
"[[(u'186', u'house_number'), (u'tuskege', u'road')]]\n", | |
"\n", | |
"\n", | |
"186 Tuskegee\n", | |
"[[(u'186', u'house_number'), (u'tuskegee', u'road')]]\n", | |
"\n", | |
"\n", | |
"186 Tuskegee \n", | |
"[[(u'186', u'house_number'), (u'tuskegee', u'road')]]\n", | |
"\n", | |
"\n", | |
"186 Tuskegee S\n", | |
"[[(u'186', u'house_number'), (u'tuskegee san', u'road')], [(u'186', u'house_number'), (u'tuskegee south', u'road')], [(u'186', u'house_number'), (u'tuskegee s', u'road')]]\n", | |
"\n", | |
"\n", | |
"186 Tuskegee St\n", | |
"[[(u'186', u'house_number'), (u'tuskegee saint', u'road')], [(u'186', u'house_number'), (u'tuskegee street', u'road')]]\n", | |
"\n", | |
"\n", | |
"186 Tuskegee St \n", | |
"[[(u'186', u'house_number'), (u'tuskegee saint', u'road')], [(u'186', u'house_number'), (u'tuskegee street', u'road')]]\n", | |
"\n", | |
"\n", | |
"186 Tuskegee St S\n", | |
"[[(u'186', u'house_number'), (u'tuskegee saint san', u'road')], [(u'186', u'house_number'), (u'tuskegee saint south', u'road')], [(u'186', u'house_number'), (u'tuskegee saint s', u'road')], [(u'186', u'house_number'), (u'tuskegee street', u'road'), (u'san', u'suburb')], [(u'186', u'house_number'), (u'tuskegee street south', u'road')], [(u'186', u'house_number'), (u'tuskegee street s', u'road')]]\n", | |
"\n", | |
"\n", | |
"186 Tuskegee St SE\n", | |
"[[(u'186', u'house_number'), (u'tuskegee saint southeast', u'road')], [(u'186', u'house_number'), (u'tuskegee saint', u'road'), (u'european company', u'house')], [(u'186', u'house_number'), (u'tuskegee saint se', u'road')], [(u'186', u'house_number'), (u'tuskegee street southeast', u'road')], [(u'186', u'house_number'), (u'tuskegee street', u'road'), (u'european', u'city'), (u'company', u'house')], [(u'186', u'house_number'), (u'tuskegee street se', u'road')]]\n", | |
"\n", | |
"\n", | |
"186 Tuskegee St SE \n", | |
"[[(u'186', u'house_number'), (u'tuskegee saint southeast', u'road')], [(u'186', u'house_number'), (u'tuskegee saint', u'road'), (u'european company', u'house')], [(u'186', u'house_number'), (u'tuskegee saint se', u'road')], [(u'186', u'house_number'), (u'tuskegee street southeast', u'road')], [(u'186', u'house_number'), (u'tuskegee street', u'road'), (u'european', u'city'), (u'company', u'house')], [(u'186', u'house_number'), (u'tuskegee street se', u'road')]]\n", | |
"\n", | |
"\n", | |
"186 Tuskegee St SE A\n", | |
"[[(u'186', u'house_number'), (u'tuskegee saint southeast a', u'road')], [(u'186', u'house_number'), (u'tuskegee saint european', u'road'), (u'company', u'house'), (u'a', u'road')], [(u'186', u'house_number'), (u'tuskegee saint se a', u'road')], [(u'186', u'house_number'), (u'tuskegee street southeast a', u'road')], [(u'186', u'house_number'), (u'tuskegee street', u'road'), (u'european', u'city'), (u'company a', u'house')], [(u'186', u'house_number'), (u'tuskegee street se a', u'road')]]\n", | |
"\n", | |
"\n", | |
"186 Tuskegee St SE At\n", | |
"[[(u'186', u'house_number'), (u'tuskegee saint southeast at', u'road')], [(u'186', u'house_number'), (u'tuskegee saint', u'road'), (u'european company at', u'house')], [(u'186', u'house_number'), (u'tuskegee saint se at', u'road')], [(u'186', u'house_number'), (u'tuskegee street southeast at', u'road')], [(u'186', u'house_number'), (u'tuskegee street', u'road'), (u'european company', u'city'), (u'at', u'country')], [(u'186', u'house_number'), (u'tuskegee street se at', u'road')]]\n", | |
"\n", | |
"\n", | |
"186 Tuskegee St SE Atl\n", | |
"[[(u'186', u'house_number'), (u'tuskegee saint southeast atl', u'road')], [(u'186', u'house_number'), (u'tuskegee saint', u'road'), (u'european company atl', u'house')], [(u'186', u'house_number'), (u'tuskegee saint se', u'road'), (u'atl', u'house')], [(u'186', u'house_number'), (u'tuskegee street southeast atl', u'road')], [(u'186', u'house_number'), (u'tuskegee street', u'road'), (u'european', u'city'), (u'company atl', u'house')], [(u'186', u'house_number'), (u'tuskegee street se', u'road'), (u'atl', u'city')]]\n", | |
"\n", | |
"\n", | |
"186 Tuskegee St SE Atla\n", | |
"[[(u'186', u'house_number'), (u'tuskegee saint southeast', u'road'), (u'atla', u'city')], [(u'186', u'house_number'), (u'tuskegee saint', u'road'), (u'european company atla', u'house')], [(u'186', u'house_number'), (u'tuskegee saint se', u'road'), (u'atla', u'city')], [(u'186', u'house_number'), (u'tuskegee street southeast', u'road'), (u'atla', u'city')], [(u'186', u'house_number'), (u'tuskegee street', u'road'), (u'european company atla', u'house')], [(u'186', u'house_number'), (u'tuskegee street se', u'road'), (u'atla', u'city')]]\n", | |
"\n", | |
"\n", | |
"186 Tuskegee St SE Atlan\n", | |
"[[(u'186', u'house_number'), (u'tuskegee saint southeast atlan', u'road')], [(u'186', u'house_number'), (u'tuskegee saint', u'road'), (u'european company atlan', u'house')], [(u'186', u'house_number'), (u'tuskegee saint se', u'road'), (u'atlan', u'house')], [(u'186', u'house_number'), (u'tuskegee street southeast atlan', u'road')], [(u'186', u'house_number'), (u'tuskegee street', u'road'), (u'european company atlan', u'house')], [(u'186', u'house_number'), (u'tuskegee street se atlan', u'road')]]\n", | |
"\n", | |
"\n", | |
"186 Tuskegee St SE Atlant\n", | |
"[[(u'186', u'house_number'), (u'tuskegee saint southeast atlant', u'road')], [(u'186', u'house_number'), (u'tuskegee saint', u'road'), (u'european company atlant', u'house')], [(u'186', u'house_number'), (u'tuskegee saint se', u'road'), (u'atlant', u'house')], [(u'186', u'house_number'), (u'tuskegee street southeast atlant', u'road')], [(u'186', u'house_number'), (u'tuskegee street', u'road'), (u'european', u'city'), (u'company atlant', u'house')], [(u'186', u'house_number'), (u'tuskegee street se atlant', u'road')]]\n", | |
"\n", | |
"\n", | |
"186 Tuskegee St SE Atlanta\n", | |
"[[(u'186', u'house_number'), (u'tuskegee saint southeast', u'road'), (u'atlanta', u'city')], [(u'186', u'house_number'), (u'tuskegee saint european', u'road'), (u'company', u'house'), (u'atlanta', u'city')], [(u'186', u'house_number'), (u'tuskegee saint se', u'road'), (u'atlanta', u'city')], [(u'186', u'house_number'), (u'tuskegee street southeast', u'road'), (u'atlanta', u'city')], [(u'186', u'house_number'), (u'tuskegee street', u'road'), (u'european', u'suburb'), (u'company', u'house'), (u'atlanta', u'city')], [(u'186', u'house_number'), (u'tuskegee street se', u'road'), (u'atlanta', u'city')]]\n", | |
"\n", | |
"\n", | |
"186 Tuskegee St SE Atlanta \n", | |
"[[(u'186', u'house_number'), (u'tuskegee saint southeast', u'road'), (u'atlanta', u'city')], [(u'186', u'house_number'), (u'tuskegee saint european', u'road'), (u'company', u'house'), (u'atlanta', u'city')], [(u'186', u'house_number'), (u'tuskegee saint se', u'road'), (u'atlanta', u'city')], [(u'186', u'house_number'), (u'tuskegee street southeast', u'road'), (u'atlanta', u'city')], [(u'186', u'house_number'), (u'tuskegee street', u'road'), (u'european', u'suburb'), (u'company', u'house'), (u'atlanta', u'city')], [(u'186', u'house_number'), (u'tuskegee street se', u'road'), (u'atlanta', u'city')]]\n", | |
"\n", | |
"\n", | |
"186 Tuskegee St SE Atlanta G\n", | |
"[[(u'186', u'house_number'), (u'tuskegee saint southeast', u'road'), (u'atlanta ground', u'city')], [(u'186', u'house_number'), (u'tuskegee saint european', u'road'), (u'company', u'house'), (u'atlanta', u'city'), (u'ground', u'house')], [(u'186', u'house_number'), (u'tuskegee saint se', u'road'), (u'atlanta ground', u'city')], [(u'186', u'house_number'), (u'tuskegee street southeast', u'road'), (u'atlanta ground', u'city')], [(u'186', u'house_number'), (u'tuskegee street', u'road'), (u'european', u'suburb'), (u'company', u'house'), (u'atlanta', u'city'), (u'ground', u'house')], [(u'186', u'house_number'), (u'tuskegee street se', u'road'), (u'atlanta ground', u'city')]]\n", | |
"\n", | |
"\n", | |
"186 Tuskegee St SE Atlanta GA\n", | |
"[[(u'186', u'house_number'), (u'tuskegee saint southeast atlanta gate', u'road')], [(u'186', u'house_number'), (u'tuskegee saint southeast', u'road'), (u'atlanta', u'city'), (u'ga', u'state')], [(u'186', u'house_number'), (u'tuskegee saint southeast', u'road'), (u'atlanta', u'city'), (u'georgia', u'state')], [(u'186', u'house_number'), (u'tuskegee saint european', u'road'), (u'company', u'house'), (u'atlanta gate', u'road')], [(u'186', u'house_number'), (u'tuskegee saint european', u'road'), (u'company', u'house'), (u'atlanta', u'city'), (u'ga', u'state')], [(u'186', u'house_number'), (u'tuskegee saint european', u'road'), (u'company', u'house'), (u'atlanta', u'city'), (u'georgia', u'state')], [(u'186', u'house_number'), (u'tuskegee saint se', u'road'), (u'atlanta', u'city'), (u'gate', u'road')], [(u'186', u'house_number'), (u'tuskegee saint se', u'road'), (u'atlanta', u'city'), (u'ga', u'state')], [(u'186', u'house_number'), (u'tuskegee saint se', u'road'), (u'atlanta', u'city'), (u'georgia', u'state')], [(u'186', u'house_number'), (u'tuskegee street southeast', u'road'), (u'atlanta', u'city'), (u'gate', u'road')], [(u'186', u'house_number'), (u'tuskegee street', u'road'), (u'european', u'suburb'), (u'company', u'house'), (u'atlanta gate', u'road')], [(u'186', u'house_number'), (u'tuskegee street se', u'road'), (u'atlanta', u'city'), (u'gate', u'road')], [(u'186', u'house_number'), (u'tuskegee street se', u'road'), (u'atlanta', u'city'), (u'ga', u'state')], [(u'186', u'house_number'), (u'tuskegee street se', u'road'), (u'atlanta', u'city'), (u'georgia', u'state')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: 3122 16th St San Francisco, CA 94103\n", | |
"3\n", | |
"[[(u'3', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"31\n", | |
"[[(u'31', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"312\n", | |
"[[(u'312', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"3122\n", | |
"[[(u'3122', u'postcode')]]\n", | |
"\n", | |
"\n", | |
"3122 \n", | |
"[[(u'3122', u'postcode')]]\n", | |
"\n", | |
"\n", | |
"3122 1\n", | |
"[[(u'3122 1', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"3122 16\n", | |
"[[(u'3122', u'house_number'), (u'16', u'road')]]\n", | |
"\n", | |
"\n", | |
"3122 16t\n", | |
"[[(u'3122', u'postcode'), (u'16t', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"3122 16th\n", | |
"[[(u'3122', u'house_number'), (u'16th', u'road')]]\n", | |
"\n", | |
"\n", | |
"3122 16th \n", | |
"[[(u'3122', u'house_number'), (u'16th', u'road')]]\n", | |
"\n", | |
"\n", | |
"3122 16th S\n", | |
"[[(u'3122', u'house_number'), (u'16th san', u'road')], [(u'3122', u'house_number'), (u'16th south', u'road')], [(u'3122', u'house_number'), (u'16th s', u'road')]]\n", | |
"\n", | |
"\n", | |
"3122 16th St\n", | |
"[[(u'3122', u'house_number'), (u'16th saint', u'road')], [(u'3122', u'house_number'), (u'16th street', u'road')]]\n", | |
"\n", | |
"\n", | |
"3122 16th St \n", | |
"[[(u'3122', u'house_number'), (u'16th saint', u'road')], [(u'3122', u'house_number'), (u'16th street', u'road')]]\n", | |
"\n", | |
"\n", | |
"3122 16th St S\n", | |
"[[(u'3122', u'house_number'), (u'16th saint san', u'road')], [(u'3122', u'house_number'), (u'16th saint south', u'road')], [(u'3122', u'house_number'), (u'16th saint s', u'road')], [(u'3122', u'house_number'), (u'16th street', u'road'), (u'san', u'suburb')], [(u'3122', u'house_number'), (u'16th street south', u'road')], [(u'3122', u'house_number'), (u'16th street s', u'road')]]\n", | |
"\n", | |
"\n", | |
"3122 16th St Sa\n", | |
"[[(u'3122', u'house_number'), (u'16th saint', u'road'), (u'southern', u'house'), (u'australia', u'country')], [(u'3122', u'house_number'), (u'16th street', u'road'), (u'southern', u'state'), (u'australia', u'country')]]\n", | |
"\n", | |
"\n", | |
"3122 16th St San\n", | |
"[[(u'3122', u'house_number'), (u'16th saint san', u'road')], [(u'3122', u'house_number'), (u'16th street', u'road'), (u'san', u'suburb')]]\n", | |
"\n", | |
"\n", | |
"3122 16th St San \n", | |
"[[(u'3122', u'house_number'), (u'16th saint san', u'road')], [(u'3122', u'house_number'), (u'16th street', u'road'), (u'san', u'suburb')]]\n", | |
"\n", | |
"\n", | |
"3122 16th St San F\n", | |
"[[(u'3122', u'house_number'), (u'16th saint san flat', u'road')], [(u'3122', u'house_number'), (u'16th street', u'road'), (u'san', u'suburb'), (u'flat', u'city')]]\n", | |
"\n", | |
"\n", | |
"3122 16th St San Fr\n", | |
"[[(u'3122', u'house_number'), (u'16th saint san father', u'road')], [(u'3122', u'house_number'), (u'16th saint san frontage', u'road')], [(u'3122', u'house_number'), (u'16th street', u'road'), (u'san father', u'city')], [(u'3122', u'house_number'), (u'16th street san frontage', u'road')]]\n", | |
"\n", | |
"\n", | |
"3122 16th St San Fra\n", | |
"[[(u'3122', u'house_number'), (u'16th saint san', u'road'), (u'fra', u'country')], [(u'3122', u'house_number'), (u'16th street', u'road'), (u'san', u'city'), (u'fra', u'country')]]\n", | |
"\n", | |
"\n", | |
"3122 16th St San Fran\n", | |
"[[(u'3122', u'house_number'), (u'16th saint san fran', u'road')], [(u'3122', u'house_number'), (u'16th street', u'road'), (u'san', u'suburb'), (u'fran', u'city')]]\n", | |
"\n", | |
"\n", | |
"3122 16th St San Franc\n", | |
"[[(u'3122', u'house_number'), (u'16th saint san franc', u'road')], [(u'3122', u'house_number'), (u'16th street', u'road'), (u'san franc', u'suburb')]]\n", | |
"\n", | |
"\n", | |
"3122 16th St San Franci\n", | |
"[[(u'3122', u'house_number'), (u'16th saint san franci', u'road')], [(u'3122', u'house_number'), (u'16th street', u'road'), (u'san', u'suburb'), (u'franci', u'city')]]\n", | |
"\n", | |
"\n", | |
"3122 16th St San Francis\n", | |
"[[(u'3122', u'house_number'), (u'16th saint san francis', u'road')], [(u'3122', u'house_number'), (u'16th street', u'road'), (u'san', u'suburb'), (u'francis', u'city')]]\n", | |
"\n", | |
"\n", | |
"3122 16th St San Francisc\n", | |
"[[(u'3122', u'house_number'), (u'16th saint san francisc', u'road')], [(u'3122', u'house_number'), (u'16th street', u'road'), (u'san', u'suburb'), (u'francisc', u'city')]]\n", | |
"\n", | |
"\n", | |
"3122 16th St San Francisco\n", | |
"[[(u'3122', u'house_number'), (u'16th saint', u'road'), (u'san francisco', u'city')], [(u'3122', u'house_number'), (u'16th street', u'road'), (u'san francisco', u'city')]]\n", | |
"\n", | |
"\n", | |
"3122 16th St San Francisco,\n", | |
"[[(u'3122', u'house_number'), (u'16th saint', u'road'), (u'san francisco', u'city')], [(u'3122', u'house_number'), (u'16th street', u'road'), (u'san francisco', u'city')]]\n", | |
"\n", | |
"\n", | |
"3122 16th St San Francisco, \n", | |
"[[(u'3122', u'house_number'), (u'16th saint', u'road'), (u'san francisco', u'city')], [(u'3122', u'house_number'), (u'16th street', u'road'), (u'san francisco', u'city')]]\n", | |
"\n", | |
"\n", | |
"3122 16th St San Francisco, C\n", | |
"[[(u'3122', u'house_number'), (u'16th saint san francisco centre', u'road')], [(u'3122', u'house_number'), (u'16th saint san', u'road'), (u'francisco center', u'house')], [(u'3122', u'house_number'), (u'16th saint', u'road'), (u'san', u'city'), (u'francisco central', u'road')], [(u'3122', u'house_number'), (u'16th street', u'road'), (u'san francisco centre', u'city')], [(u'3122', u'house_number'), (u'16th street', u'road'), (u'san francisco center', u'city')], [(u'3122', u'house_number'), (u'16th street', u'road'), (u'san francisco', u'city'), (u'central', u'state')]]\n", | |
"\n", | |
"\n", | |
"3122 16th St San Francisco, CA\n", | |
"[[(u'3122', u'house_number'), (u'16th saint', u'road'), (u'san francisco', u'city'), (u'california', u'state')], [(u'3122', u'house_number'), (u'16th saint', u'road'), (u'san francisco', u'city'), (u'ca', u'state')], [(u'3122', u'house_number'), (u'16th street', u'road'), (u'san francisco', u'city'), (u'california', u'state')], [(u'3122', u'house_number'), (u'16th street', u'road'), (u'san francisco', u'city'), (u'ca', u'state')]]\n", | |
"\n", | |
"\n", | |
"3122 16th St San Francisco, CA \n", | |
"[[(u'3122', u'house_number'), (u'16th saint', u'road'), (u'san francisco', u'city'), (u'california', u'state')], [(u'3122', u'house_number'), (u'16th saint', u'road'), (u'san francisco', u'city'), (u'ca', u'state')], [(u'3122', u'house_number'), (u'16th street', u'road'), (u'san francisco', u'city'), (u'california', u'state')], [(u'3122', u'house_number'), (u'16th street', u'road'), (u'san francisco', u'city'), (u'ca', u'state')]]\n", | |
"\n", | |
"\n", | |
"3122 16th St San Francisco, CA 9\n", | |
"[[(u'3122', u'house_number'), (u'16th saint', u'road'), (u'san francisco', u'city'), (u'california', u'state'), (u'9', u'postcode')], [(u'3122', u'house_number'), (u'16th saint', u'road'), (u'san francisco', u'city'), (u'ca', u'state'), (u'9', u'house_number')], [(u'3122', u'house_number'), (u'16th street', u'road'), (u'san francisco', u'city'), (u'california', u'state'), (u'9', u'postcode')], [(u'3122', u'house_number'), (u'16th street', u'road'), (u'san francisco', u'city'), (u'ca', u'state'), (u'9', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"3122 16th St San Francisco, CA 94\n", | |
"[[(u'3122', u'house_number'), (u'16th saint', u'road'), (u'san francisco', u'city'), (u'california', u'state'), (u'94', u'postcode')], [(u'3122', u'house_number'), (u'16th saint', u'road'), (u'san francisco', u'city'), (u'ca', u'state'), (u'94', u'road')], [(u'3122', u'house_number'), (u'16th street', u'road'), (u'san francisco', u'city'), (u'california', u'state'), (u'94', u'postcode')], [(u'3122', u'house_number'), (u'16th street', u'road'), (u'san francisco', u'city'), (u'ca', u'state'), (u'94', u'road')]]\n", | |
"\n", | |
"\n", | |
"3122 16th St San Francisco, CA 941\n", | |
"[[(u'3122', u'house_number'), (u'16th saint', u'road'), (u'san francisco', u'city'), (u'california', u'state'), (u'941', u'postcode')], [(u'3122', u'house_number'), (u'16th saint', u'road'), (u'san francisco', u'city'), (u'ca', u'state'), (u'941', u'road')], [(u'3122', u'house_number'), (u'16th street', u'road'), (u'san francisco', u'city'), (u'california', u'state'), (u'941', u'postcode')], [(u'3122', u'house_number'), (u'16th street', u'road'), (u'san francisco', u'city'), (u'ca', u'state'), (u'941', u'road')]]\n", | |
"\n", | |
"\n", | |
"3122 16th St San Francisco, CA 9410\n", | |
"[[(u'3122', u'house_number'), (u'16th saint', u'road'), (u'san francisco', u'city'), (u'california', u'state'), (u'9410', u'postcode')], [(u'3122', u'house_number'), (u'16th saint', u'road'), (u'san francisco', u'city'), (u'ca', u'state'), (u'9410', u'postcode')], [(u'3122', u'house_number'), (u'16th street', u'road'), (u'san francisco', u'city'), (u'california', u'state'), (u'9410', u'postcode')], [(u'3122', u'house_number'), (u'16th street', u'road'), (u'san francisco', u'city'), (u'ca', u'state'), (u'9410', u'postcode')]]\n", | |
"\n", | |
"\n", | |
"3122 16th St San Francisco, CA 94103\n", | |
"[[(u'3122', u'house_number'), (u'16th saint', u'road'), (u'san francisco', u'city'), (u'california', u'state'), (u'94103', u'postcode')], [(u'3122', u'house_number'), (u'16th saint', u'road'), (u'san francisco', u'city'), (u'ca', u'state'), (u'94103', u'postcode')], [(u'3122', u'house_number'), (u'16th street', u'road'), (u'san francisco', u'city'), (u'california', u'state'), (u'94103', u'postcode')], [(u'3122', u'house_number'), (u'16th street', u'road'), (u'san francisco', u'city'), (u'ca', u'state'), (u'94103', u'postcode')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: 3010 20th St San Francisco CA 94110\n", | |
"3\n", | |
"[[(u'3', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"30\n", | |
"[[(u'30', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"301\n", | |
"[[(u'301', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"3010\n", | |
"[[(u'3010', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"3010 \n", | |
"[[(u'3010', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"3010 2\n", | |
"[[(u'3010 2', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"3010 20\n", | |
"[[(u'3010', u'house_number'), (u'20', u'road')]]\n", | |
"\n", | |
"\n", | |
"3010 20t\n", | |
"[[(u'3010', u'postcode'), (u'20t', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"3010 20th\n", | |
"[[(u'3010', u'house_number'), (u'20th', u'road')]]\n", | |
"\n", | |
"\n", | |
"3010 20th \n", | |
"[[(u'3010', u'house_number'), (u'20th', u'road')]]\n", | |
"\n", | |
"\n", | |
"3010 20th S\n", | |
"[[(u'3010', u'house_number'), (u'20th san', u'road')], [(u'3010', u'house_number'), (u'20th south', u'road')], [(u'3010', u'house_number'), (u'20th s', u'road')]]\n", | |
"\n", | |
"\n", | |
"3010 20th St\n", | |
"[[(u'3010', u'house_number'), (u'20th saint', u'road')], [(u'3010', u'house_number'), (u'20th street', u'road')]]\n", | |
"\n", | |
"\n", | |
"3010 20th St \n", | |
"[[(u'3010', u'house_number'), (u'20th saint', u'road')], [(u'3010', u'house_number'), (u'20th street', u'road')]]\n", | |
"\n", | |
"\n", | |
"3010 20th St S\n", | |
"[[(u'3010', u'house_number'), (u'20th saint san', u'road')], [(u'3010', u'house_number'), (u'20th saint south', u'road')], [(u'3010', u'house_number'), (u'20th saint s', u'road')], [(u'3010', u'house_number'), (u'20th street', u'road'), (u'san', u'suburb')], [(u'3010', u'house_number'), (u'20th street south', u'road')], [(u'3010', u'house_number'), (u'20th street s', u'road')]]\n", | |
"\n", | |
"\n", | |
"3010 20th St Sa\n", | |
"[[(u'3010', u'house_number'), (u'20th saint', u'road'), (u'southern', u'house'), (u'australia', u'country')], [(u'3010', u'house_number'), (u'20th street', u'road'), (u'southern', u'state'), (u'australia', u'country')]]\n", | |
"\n", | |
"\n", | |
"3010 20th St San\n", | |
"[[(u'3010', u'house_number'), (u'20th saint san', u'road')], [(u'3010', u'house_number'), (u'20th street', u'road'), (u'san', u'suburb')]]\n", | |
"\n", | |
"\n", | |
"3010 20th St San \n", | |
"[[(u'3010', u'house_number'), (u'20th saint san', u'road')], [(u'3010', u'house_number'), (u'20th street', u'road'), (u'san', u'suburb')]]\n", | |
"\n", | |
"\n", | |
"3010 20th St San F\n", | |
"[[(u'3010', u'house_number'), (u'20th saint san flat', u'road')], [(u'3010', u'house_number'), (u'20th street', u'road'), (u'san', u'suburb'), (u'flat', u'city')]]\n", | |
"\n", | |
"\n", | |
"3010 20th St San Fr\n", | |
"[[(u'3010', u'house_number'), (u'20th saint san father', u'road')], [(u'3010', u'house_number'), (u'20th saint san frontage', u'road')], [(u'3010', u'house_number'), (u'20th street', u'road'), (u'san father', u'city')], [(u'3010', u'house_number'), (u'20th street san frontage', u'road')]]\n", | |
"\n", | |
"\n", | |
"3010 20th St San Fra\n", | |
"[[(u'3010', u'house_number'), (u'20th saint san', u'road'), (u'fra', u'country')], [(u'3010', u'house_number'), (u'20th street', u'road'), (u'san', u'city'), (u'fra', u'country')]]\n", | |
"\n", | |
"\n", | |
"3010 20th St San Fran\n", | |
"[[(u'3010', u'house_number'), (u'20th saint san fran', u'road')], [(u'3010', u'house_number'), (u'20th street', u'road'), (u'san', u'suburb'), (u'fran', u'city')]]\n", | |
"\n", | |
"\n", | |
"3010 20th St San Franc\n", | |
"[[(u'3010', u'house_number'), (u'20th saint san franc', u'road')], [(u'3010', u'house_number'), (u'20th street', u'road'), (u'san franc', u'suburb')]]\n", | |
"\n", | |
"\n", | |
"3010 20th St San Franci\n", | |
"[[(u'3010', u'house_number'), (u'20th saint san franci', u'road')], [(u'3010', u'house_number'), (u'20th street', u'road'), (u'san', u'suburb'), (u'franci', u'city')]]\n", | |
"\n", | |
"\n", | |
"3010 20th St San Francis\n", | |
"[[(u'3010', u'house_number'), (u'20th saint san francis', u'road')], [(u'3010', u'house_number'), (u'20th street', u'road'), (u'san', u'suburb'), (u'francis', u'city')]]\n", | |
"\n", | |
"\n", | |
"3010 20th St San Francisc\n", | |
"[[(u'3010', u'house_number'), (u'20th saint san francisc', u'road')], [(u'3010', u'house_number'), (u'20th street', u'road'), (u'san', u'suburb'), (u'francisc', u'city')]]\n", | |
"\n", | |
"\n", | |
"3010 20th St San Francisco\n", | |
"[[(u'3010', u'house_number'), (u'20th saint', u'road'), (u'san francisco', u'city')], [(u'3010', u'house_number'), (u'20th street', u'road'), (u'san francisco', u'city')]]\n", | |
"\n", | |
"\n", | |
"3010 20th St San Francisco \n", | |
"[[(u'3010', u'house_number'), (u'20th saint', u'road'), (u'san francisco', u'city')], [(u'3010', u'house_number'), (u'20th street', u'road'), (u'san francisco', u'city')]]\n", | |
"\n", | |
"\n", | |
"3010 20th St San Francisco C\n", | |
"[[(u'3010', u'house_number'), (u'20th saint san francisco centre', u'road')], [(u'3010', u'house_number'), (u'20th saint san', u'road'), (u'francisco center', u'house')], [(u'3010', u'house_number'), (u'20th saint', u'road'), (u'san', u'city'), (u'francisco central', u'road')], [(u'3010', u'house_number'), (u'20th street', u'road'), (u'san francisco centre', u'city')], [(u'3010', u'house_number'), (u'20th street', u'road'), (u'san francisco center', u'city')], [(u'3010', u'house_number'), (u'20th street', u'road'), (u'san francisco', u'city'), (u'central', u'state')]]\n", | |
"\n", | |
"\n", | |
"3010 20th St San Francisco CA\n", | |
"[[(u'3010', u'house_number'), (u'20th saint', u'road'), (u'san francisco', u'city'), (u'california', u'state')], [(u'3010', u'house_number'), (u'20th saint', u'road'), (u'san francisco', u'city'), (u'ca', u'state')], [(u'3010', u'house_number'), (u'20th street', u'road'), (u'san francisco', u'city'), (u'california', u'state')], [(u'3010', u'house_number'), (u'20th street', u'road'), (u'san francisco', u'city'), (u'ca', u'state')]]\n", | |
"\n", | |
"\n", | |
"3010 20th St San Francisco CA \n", | |
"[[(u'3010', u'house_number'), (u'20th saint', u'road'), (u'san francisco', u'city'), (u'california', u'state')], [(u'3010', u'house_number'), (u'20th saint', u'road'), (u'san francisco', u'city'), (u'ca', u'state')], [(u'3010', u'house_number'), (u'20th street', u'road'), (u'san francisco', u'city'), (u'california', u'state')], [(u'3010', u'house_number'), (u'20th street', u'road'), (u'san francisco', u'city'), (u'ca', u'state')]]\n", | |
"\n", | |
"\n", | |
"3010 20th St San Francisco CA 9\n", | |
"[[(u'3010', u'house_number'), (u'20th saint', u'road'), (u'san francisco', u'city'), (u'california', u'state'), (u'9', u'postcode')], [(u'3010', u'house_number'), (u'20th saint', u'road'), (u'san francisco', u'city'), (u'ca', u'state'), (u'9', u'house_number')], [(u'3010', u'house_number'), (u'20th street', u'road'), (u'san francisco', u'city'), (u'california', u'state'), (u'9', u'postcode')], [(u'3010', u'house_number'), (u'20th street', u'road'), (u'san francisco', u'city'), (u'ca', u'state'), (u'9', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"3010 20th St San Francisco CA 94\n", | |
"[[(u'3010', u'house_number'), (u'20th saint', u'road'), (u'san francisco', u'city'), (u'california', u'state'), (u'94', u'postcode')], [(u'3010', u'house_number'), (u'20th saint', u'road'), (u'san francisco', u'city'), (u'ca', u'state'), (u'94', u'road')], [(u'3010', u'house_number'), (u'20th street', u'road'), (u'san francisco', u'city'), (u'california', u'state'), (u'94', u'postcode')], [(u'3010', u'house_number'), (u'20th street', u'road'), (u'san francisco', u'city'), (u'ca', u'state'), (u'94', u'road')]]\n", | |
"\n", | |
"\n", | |
"3010 20th St San Francisco CA 941\n", | |
"[[(u'3010', u'house_number'), (u'20th saint', u'road'), (u'san francisco', u'city'), (u'california', u'state'), (u'941', u'postcode')], [(u'3010', u'house_number'), (u'20th saint', u'road'), (u'san francisco', u'city'), (u'ca', u'state'), (u'941', u'road')], [(u'3010', u'house_number'), (u'20th street', u'road'), (u'san francisco', u'city'), (u'california', u'state'), (u'941', u'postcode')], [(u'3010', u'house_number'), (u'20th street', u'road'), (u'san francisco', u'city'), (u'ca', u'state'), (u'941', u'road')]]\n", | |
"\n", | |
"\n", | |
"3010 20th St San Francisco CA 9411\n", | |
"[[(u'3010', u'house_number'), (u'20th saint', u'road'), (u'san francisco', u'city'), (u'california', u'state'), (u'9411', u'postcode')], [(u'3010', u'house_number'), (u'20th saint', u'road'), (u'san francisco', u'city'), (u'ca', u'state'), (u'9411', u'postcode')], [(u'3010', u'house_number'), (u'20th street', u'road'), (u'san francisco', u'city'), (u'california', u'state'), (u'9411', u'postcode')], [(u'3010', u'house_number'), (u'20th street', u'road'), (u'san francisco', u'city'), (u'ca', u'state'), (u'9411', u'postcode')]]\n", | |
"\n", | |
"\n", | |
"3010 20th St San Francisco CA 94110\n", | |
"[[(u'3010', u'house_number'), (u'20th saint', u'road'), (u'san francisco', u'city'), (u'california', u'state'), (u'94110', u'postcode')], [(u'3010', u'house_number'), (u'20th saint', u'road'), (u'san francisco', u'city'), (u'ca', u'state'), (u'94110', u'postcode')], [(u'3010', u'house_number'), (u'20th street', u'road'), (u'san francisco', u'city'), (u'california', u'state'), (u'94110', u'postcode')], [(u'3010', u'house_number'), (u'20th street', u'road'), (u'san francisco', u'city'), (u'ca', u'state'), (u'94110', u'postcode')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: 3577 Jackson St San Francisco, CA 94118\n", | |
"3\n", | |
"[[(u'3', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"35\n", | |
"[[(u'35', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"357\n", | |
"[[(u'357', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"3577\n", | |
"[[(u'3577', u'postcode')]]\n", | |
"\n", | |
"\n", | |
"3577 \n", | |
"[[(u'3577', u'postcode')]]\n", | |
"\n", | |
"\n", | |
"3577 J\n", | |
"[[(u'3577', u'house_number'), (u'junction', u'road')]]\n", | |
"\n", | |
"\n", | |
"3577 Ja\n", | |
"[[(u'3577 ja', u'postcode')]]\n", | |
"\n", | |
"\n", | |
"3577 Jac\n", | |
"[[(u'3577', u'postcode'), (u'jac', u'road')]]\n", | |
"\n", | |
"\n", | |
"3577 Jack\n", | |
"[[(u'3577', u'house_number'), (u'jack', u'road')]]\n", | |
"\n", | |
"\n", | |
"3577 Jacks\n", | |
"[[(u'3577', u'house_number'), (u'jacks', u'road')]]\n", | |
"\n", | |
"\n", | |
"3577 Jackso\n", | |
"[[(u'3577', u'house_number'), (u'jackso', u'road')]]\n", | |
"\n", | |
"\n", | |
"3577 Jackson\n", | |
"[[(u'3577', u'house_number'), (u'jackson', u'road')]]\n", | |
"\n", | |
"\n", | |
"3577 Jackson \n", | |
"[[(u'3577', u'house_number'), (u'jackson', u'road')]]\n", | |
"\n", | |
"\n", | |
"3577 Jackson S\n", | |
"[[(u'3577', u'house_number'), (u'jackson san', u'road')], [(u'3577', u'house_number'), (u'jackson south', u'road')], [(u'3577', u'house_number'), (u'jackson s', u'road')]]\n", | |
"\n", | |
"\n", | |
"3577 Jackson St\n", | |
"[[(u'3577', u'house_number'), (u'jackson saint', u'road')], [(u'3577', u'house_number'), (u'jackson street', u'road')]]\n", | |
"\n", | |
"\n", | |
"3577 Jackson St \n", | |
"[[(u'3577', u'house_number'), (u'jackson saint', u'road')], [(u'3577', u'house_number'), (u'jackson street', u'road')]]\n", | |
"\n", | |
"\n", | |
"3577 Jackson St S\n", | |
"[[(u'3577', u'house_number'), (u'jackson saint san', u'road')], [(u'3577', u'house_number'), (u'jackson saint south', u'road')], [(u'3577', u'house_number'), (u'jackson saint s', u'road')], [(u'3577', u'house_number'), (u'jackson street', u'road'), (u'san', u'suburb')], [(u'3577', u'house_number'), (u'jackson street south', u'road')], [(u'3577', u'house_number'), (u'jackson street s', u'road')]]\n", | |
"\n", | |
"\n", | |
"3577 Jackson St Sa\n", | |
"[[(u'3577', u'house_number'), (u'jackson saint', u'road'), (u'southern', u'house'), (u'australia', u'country')], [(u'3577', u'house_number'), (u'jackson street', u'road'), (u'southern', u'state'), (u'australia', u'country')]]\n", | |
"\n", | |
"\n", | |
"3577 Jackson St San\n", | |
"[[(u'3577', u'house_number'), (u'jackson saint san', u'road')], [(u'3577', u'house_number'), (u'jackson street', u'road'), (u'san', u'suburb')]]\n", | |
"\n", | |
"\n", | |
"3577 Jackson St San \n", | |
"[[(u'3577', u'house_number'), (u'jackson saint san', u'road')], [(u'3577', u'house_number'), (u'jackson street', u'road'), (u'san', u'suburb')]]\n", | |
"\n", | |
"\n", | |
"3577 Jackson St San F\n", | |
"[[(u'3577', u'house_number'), (u'jackson saint san flat', u'road')], [(u'3577', u'house_number'), (u'jackson street', u'road'), (u'san', u'suburb'), (u'flat', u'city')]]\n", | |
"\n", | |
"\n", | |
"3577 Jackson St San Fr\n", | |
"[[(u'3577', u'house_number'), (u'jackson saint san father', u'road')], [(u'3577', u'house_number'), (u'jackson saint san frontage', u'road')], [(u'3577', u'house_number'), (u'jackson street', u'road'), (u'san father', u'city')], [(u'3577', u'house_number'), (u'jackson street san frontage', u'road')]]\n", | |
"\n", | |
"\n", | |
"3577 Jackson St San Fra\n", | |
"[[(u'3577', u'house_number'), (u'jackson saint san', u'road'), (u'fra', u'country')], [(u'3577', u'house_number'), (u'jackson street', u'road'), (u'san', u'city'), (u'fra', u'country')]]\n", | |
"\n", | |
"\n", | |
"3577 Jackson St San Fran\n", | |
"[[(u'3577', u'house_number'), (u'jackson saint san fran', u'road')], [(u'3577', u'house_number'), (u'jackson street', u'road'), (u'san', u'suburb'), (u'fran', u'city')]]\n", | |
"\n", | |
"\n", | |
"3577 Jackson St San Franc\n", | |
"[[(u'3577', u'house_number'), (u'jackson saint san franc', u'road')], [(u'3577', u'house_number'), (u'jackson street', u'road'), (u'san franc', u'suburb')]]\n", | |
"\n", | |
"\n", | |
"3577 Jackson St San Franci\n", | |
"[[(u'3577', u'house_number'), (u'jackson saint san franci', u'road')], [(u'3577', u'house_number'), (u'jackson street', u'road'), (u'san', u'suburb'), (u'franci', u'city')]]\n", | |
"\n", | |
"\n", | |
"3577 Jackson St San Francis\n", | |
"[[(u'3577', u'house_number'), (u'jackson saint san francis', u'road')], [(u'3577', u'house_number'), (u'jackson street', u'road'), (u'san', u'suburb'), (u'francis', u'city')]]\n", | |
"\n", | |
"\n", | |
"3577 Jackson St San Francisc\n", | |
"[[(u'3577', u'house_number'), (u'jackson saint san francisc', u'road')], [(u'3577', u'house_number'), (u'jackson street', u'road'), (u'san', u'suburb'), (u'francisc', u'city')]]\n", | |
"\n", | |
"\n", | |
"3577 Jackson St San Francisco\n", | |
"[[(u'3577', u'house_number'), (u'jackson saint', u'road'), (u'san francisco', u'city')], [(u'3577', u'house_number'), (u'jackson street', u'road'), (u'san francisco', u'city')]]\n", | |
"\n", | |
"\n", | |
"3577 Jackson St San Francisco,\n", | |
"[[(u'3577', u'house_number'), (u'jackson saint', u'road'), (u'san francisco', u'city')], [(u'3577', u'house_number'), (u'jackson street', u'road'), (u'san francisco', u'city')]]\n", | |
"\n", | |
"\n", | |
"3577 Jackson St San Francisco, \n", | |
"[[(u'3577', u'house_number'), (u'jackson saint', u'road'), (u'san francisco', u'city')], [(u'3577', u'house_number'), (u'jackson street', u'road'), (u'san francisco', u'city')]]\n", | |
"\n", | |
"\n", | |
"3577 Jackson St San Francisco, C\n", | |
"[[(u'3577', u'house_number'), (u'jackson saint san francisco centre', u'road')], [(u'3577', u'house_number'), (u'jackson saint san', u'road'), (u'francisco center', u'house')], [(u'3577', u'house_number'), (u'jackson saint', u'road'), (u'san', u'city'), (u'francisco central', u'road')], [(u'3577', u'house_number'), (u'jackson street', u'road'), (u'san francisco centre', u'city')], [(u'3577', u'house_number'), (u'jackson street', u'road'), (u'san francisco center', u'city')], [(u'3577', u'house_number'), (u'jackson street', u'road'), (u'san francisco', u'city'), (u'central', u'state')]]\n", | |
"\n", | |
"\n", | |
"3577 Jackson St San Francisco, CA\n", | |
"[[(u'3577', u'house_number'), (u'jackson saint', u'road'), (u'san francisco', u'city'), (u'california', u'state')], [(u'3577', u'house_number'), (u'jackson saint', u'road'), (u'san francisco', u'city'), (u'ca', u'state')], [(u'3577', u'house_number'), (u'jackson street', u'road'), (u'san francisco', u'city'), (u'california', u'state')], [(u'3577', u'house_number'), (u'jackson street', u'road'), (u'san francisco', u'city'), (u'ca', u'state')]]\n", | |
"\n", | |
"\n", | |
"3577 Jackson St San Francisco, CA \n", | |
"[[(u'3577', u'house_number'), (u'jackson saint', u'road'), (u'san francisco', u'city'), (u'california', u'state')], [(u'3577', u'house_number'), (u'jackson saint', u'road'), (u'san francisco', u'city'), (u'ca', u'state')], [(u'3577', u'house_number'), (u'jackson street', u'road'), (u'san francisco', u'city'), (u'california', u'state')], [(u'3577', u'house_number'), (u'jackson street', u'road'), (u'san francisco', u'city'), (u'ca', u'state')]]\n", | |
"\n", | |
"\n", | |
"3577 Jackson St San Francisco, CA 9\n", | |
"[[(u'3577', u'house_number'), (u'jackson saint', u'road'), (u'san francisco', u'city'), (u'california', u'state'), (u'9', u'postcode')], [(u'3577', u'house_number'), (u'jackson saint', u'road'), (u'san francisco', u'city'), (u'ca', u'state'), (u'9', u'house_number')], [(u'3577', u'house_number'), (u'jackson street', u'road'), (u'san francisco', u'city'), (u'california', u'state'), (u'9', u'postcode')], [(u'3577', u'house_number'), (u'jackson street', u'road'), (u'san francisco', u'city'), (u'ca', u'state'), (u'9', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"3577 Jackson St San Francisco, CA 94\n", | |
"[[(u'3577', u'house_number'), (u'jackson saint', u'road'), (u'san francisco', u'city'), (u'california', u'state'), (u'94', u'postcode')], [(u'3577', u'house_number'), (u'jackson saint', u'road'), (u'san francisco', u'city'), (u'ca', u'state'), (u'94', u'road')], [(u'3577', u'house_number'), (u'jackson street', u'road'), (u'san francisco', u'city'), (u'california', u'state'), (u'94', u'postcode')], [(u'3577', u'house_number'), (u'jackson street', u'road'), (u'san francisco', u'city'), (u'ca', u'state'), (u'94', u'road')]]\n", | |
"\n", | |
"\n", | |
"3577 Jackson St San Francisco, CA 941\n", | |
"[[(u'3577', u'house_number'), (u'jackson saint', u'road'), (u'san francisco', u'city'), (u'california', u'state'), (u'941', u'postcode')], [(u'3577', u'house_number'), (u'jackson saint', u'road'), (u'san francisco', u'city'), (u'ca', u'state'), (u'941', u'road')], [(u'3577', u'house_number'), (u'jackson street', u'road'), (u'san francisco', u'city'), (u'california', u'state'), (u'941', u'postcode')], [(u'3577', u'house_number'), (u'jackson street', u'road'), (u'san francisco', u'city'), (u'ca', u'state'), (u'941', u'road')]]\n", | |
"\n", | |
"\n", | |
"3577 Jackson St San Francisco, CA 9411\n", | |
"[[(u'3577', u'house_number'), (u'jackson saint', u'road'), (u'san francisco', u'city'), (u'california', u'state'), (u'9411', u'postcode')], [(u'3577', u'house_number'), (u'jackson saint', u'road'), (u'san francisco', u'city'), (u'ca', u'state'), (u'9411', u'postcode')], [(u'3577', u'house_number'), (u'jackson street', u'road'), (u'san francisco', u'city'), (u'california', u'state'), (u'9411', u'postcode')], [(u'3577', u'house_number'), (u'jackson street', u'road'), (u'san francisco', u'city'), (u'ca', u'state'), (u'9411', u'postcode')]]\n", | |
"\n", | |
"\n", | |
"3577 Jackson St San Francisco, CA 94118\n", | |
"[[(u'3577', u'house_number'), (u'jackson saint', u'road'), (u'san francisco', u'city'), (u'california', u'state'), (u'94118', u'postcode')], [(u'3577', u'house_number'), (u'jackson saint', u'road'), (u'san francisco', u'city'), (u'ca', u'state'), (u'94118', u'postcode')], [(u'3577', u'house_number'), (u'jackson street', u'road'), (u'san francisco', u'city'), (u'california', u'state'), (u'94118', u'postcode')], [(u'3577', u'house_number'), (u'jackson street', u'road'), (u'san francisco', u'city'), (u'ca', u'state'), (u'94118', u'postcode')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: whole foods NY\n", | |
"w\n", | |
"[[(u'west', u'city_district')], [(u'w', u'house')]]\n", | |
"\n", | |
"\n", | |
"wh\n", | |
"[[(u'wh', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"who\n", | |
"[[(u'who', u'house')]]\n", | |
"\n", | |
"\n", | |
"whol\n", | |
"[[(u'whol', u'house')]]\n", | |
"\n", | |
"\n", | |
"whole\n", | |
"[[(u'whole', u'house')]]\n", | |
"\n", | |
"\n", | |
"whole \n", | |
"[[(u'whole', u'house')]]\n", | |
"\n", | |
"\n", | |
"whole f\n", | |
"[[(u'whole flat', u'house')]]\n", | |
"\n", | |
"\n", | |
"whole fo\n", | |
"[[(u'whole fo', u'house')]]\n", | |
"\n", | |
"\n", | |
"whole foo\n", | |
"[[(u'whole foo', u'house')]]\n", | |
"\n", | |
"\n", | |
"whole food\n", | |
"[[(u'whole food', u'house')]]\n", | |
"\n", | |
"\n", | |
"whole foods\n", | |
"[[(u'whole foods', u'house')]]\n", | |
"\n", | |
"\n", | |
"whole foods \n", | |
"[[(u'whole foods', u'house')]]\n", | |
"\n", | |
"\n", | |
"whole foods N\n", | |
"[[(u'whole foods', u'house'), (u'north', u'road')], [(u'whole foods', u'house'), (u'n', u'road')]]\n", | |
"\n", | |
"\n", | |
"whole foods NY\n", | |
"[[(u'whole foods', u'house'), (u'new york', u'state')], [(u'whole foods', u'house'), (u'ny', u'state')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"====================================================================\n", | |
"\n", | |
"TEST SET: autocomplete_admin_areas\n", | |
"TEST: brooklyn\n", | |
"b\n", | |
"[[(u'b', u'house')]]\n", | |
"\n", | |
"\n", | |
"br\n", | |
"[[(u'brae', u'road')], [(u'brother', u'house')], [(u'brace', u'house')], [(u'bridge', u'house')], [(u'branch', u'house')]]\n", | |
"\n", | |
"\n", | |
"bro\n", | |
"[[(u'bro', u'road')]]\n", | |
"\n", | |
"\n", | |
"broo\n", | |
"[[(u'broo', u'house')]]\n", | |
"\n", | |
"\n", | |
"brook\n", | |
"[[(u'brook', u'house')]]\n", | |
"\n", | |
"\n", | |
"brookl\n", | |
"[[(u'brookl', u'house')]]\n", | |
"\n", | |
"\n", | |
"brookly\n", | |
"[[(u'brookly', u'house')]]\n", | |
"\n", | |
"\n", | |
"brooklyn\n", | |
"[[(u'brooklyn', u'house')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: new york\n", | |
"n\n", | |
"[[(u'north', u'road')], [(u'n', u'road')]]\n", | |
"\n", | |
"\n", | |
"ne\n", | |
"[[(u'ne', u'road')], [(u'northeast', u'road')], [(u'nebraska', u'state')]]\n", | |
"\n", | |
"\n", | |
"new\n", | |
"[[(u'new', u'house')]]\n", | |
"\n", | |
"\n", | |
"new \n", | |
"[[(u'new', u'house')]]\n", | |
"\n", | |
"\n", | |
"new y\n", | |
"[[(u'new y', u'house')]]\n", | |
"\n", | |
"\n", | |
"new yo\n", | |
"[[(u'new yo', u'house')]]\n", | |
"\n", | |
"\n", | |
"new yor\n", | |
"[[(u'new yor', u'house')]]\n", | |
"\n", | |
"\n", | |
"new york\n", | |
"[[(u'new york', u'state')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: london\n", | |
"l\n", | |
"[[(u'level', u'house')]]\n", | |
"\n", | |
"\n", | |
"lo\n", | |
"[[(u'lo', u'house')]]\n", | |
"\n", | |
"\n", | |
"lon\n", | |
"[[(u'lon', u'road')]]\n", | |
"\n", | |
"\n", | |
"lond\n", | |
"[[(u'lond', u'house')]]\n", | |
"\n", | |
"\n", | |
"londo\n", | |
"[[(u'londo', u'house')]]\n", | |
"\n", | |
"\n", | |
"london\n", | |
"[[(u'london', u'city')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: san francisco\n", | |
"s\n", | |
"[[(u'san', u'road')], [(u'south', u'road')], [(u's', u'road')]]\n", | |
"\n", | |
"\n", | |
"sa\n", | |
"[[(u'southern', u'house'), (u'australia', u'country')]]\n", | |
"\n", | |
"\n", | |
"san\n", | |
"[[(u'san', u'road')]]\n", | |
"\n", | |
"\n", | |
"san \n", | |
"[[(u'san', u'road')]]\n", | |
"\n", | |
"\n", | |
"san f\n", | |
"[[(u'san', u'road'), (u'flat', u'house')]]\n", | |
"\n", | |
"\n", | |
"san fr\n", | |
"[[(u'san father', u'road')], [(u'san frontage', u'road')]]\n", | |
"\n", | |
"\n", | |
"san fra\n", | |
"[[(u'san', u'road'), (u'fra', u'house')]]\n", | |
"\n", | |
"\n", | |
"san fran\n", | |
"[[(u'san fran', u'road')]]\n", | |
"\n", | |
"\n", | |
"san franc\n", | |
"[[(u'san franc', u'road')]]\n", | |
"\n", | |
"\n", | |
"san franci\n", | |
"[[(u'san franci', u'road')]]\n", | |
"\n", | |
"\n", | |
"san francis\n", | |
"[[(u'san francis', u'house')]]\n", | |
"\n", | |
"\n", | |
"san francisc\n", | |
"[[(u'san francisc', u'house')]]\n", | |
"\n", | |
"\n", | |
"san francisco\n", | |
"[[(u'san francisco', u'city')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: victoria\n", | |
"v\n", | |
"[[(u'v', u'house')], [(u'5', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"vi\n", | |
"[[(u'vi', u'house')], [(u'6', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"vic\n", | |
"[[(u'victoria', u'city')], [(u'vic', u'state')], [(u'100', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"vict\n", | |
"[[(u'vict', u'house')]]\n", | |
"\n", | |
"\n", | |
"victo\n", | |
"[[(u'victo', u'house')]]\n", | |
"\n", | |
"\n", | |
"victor\n", | |
"[[(u'victor', u'road')]]\n", | |
"\n", | |
"\n", | |
"victori\n", | |
"[[(u'victori', u'house')]]\n", | |
"\n", | |
"\n", | |
"victoria\n", | |
"[[(u'victoria', u'city')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: wales\n", | |
"w\n", | |
"[[(u'west', u'city_district')], [(u'w', u'house')]]\n", | |
"\n", | |
"\n", | |
"wa\n", | |
"[[(u'wa', u'state')], [(u'washington', u'city')], [(u'western australia', u'state')]]\n", | |
"\n", | |
"\n", | |
"wal\n", | |
"[[(u'wal', u'road')]]\n", | |
"\n", | |
"\n", | |
"wale\n", | |
"[[(u'wale', u'house')]]\n", | |
"\n", | |
"\n", | |
"wales\n", | |
"[[(u'wales', u'state')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: new south wales\n", | |
"n\n", | |
"[[(u'north', u'road')], [(u'n', u'road')]]\n", | |
"\n", | |
"\n", | |
"ne\n", | |
"[[(u'ne', u'road')], [(u'northeast', u'road')], [(u'nebraska', u'state')]]\n", | |
"\n", | |
"\n", | |
"new\n", | |
"[[(u'new', u'house')]]\n", | |
"\n", | |
"\n", | |
"new \n", | |
"[[(u'new', u'house')]]\n", | |
"\n", | |
"\n", | |
"new s\n", | |
"[[(u'new s', u'house')]]\n", | |
"\n", | |
"\n", | |
"new so\n", | |
"[[(u'new so', u'house')]]\n", | |
"\n", | |
"\n", | |
"new sou\n", | |
"[[(u'new', u'road'), (u'sou', u'house')]]\n", | |
"\n", | |
"\n", | |
"new sout\n", | |
"[[(u'new sout', u'house')]]\n", | |
"\n", | |
"\n", | |
"new south\n", | |
"[[(u'new', u'house'), (u'south', u'road')]]\n", | |
"\n", | |
"\n", | |
"new south \n", | |
"[[(u'new', u'house'), (u'south', u'road')]]\n", | |
"\n", | |
"\n", | |
"new south w\n", | |
"[[]]\n", | |
"\n", | |
"\n", | |
"new south wa\n", | |
"[[]]\n", | |
"\n", | |
"\n", | |
"new south wal\n", | |
"[[]]\n", | |
"\n", | |
"\n", | |
"new south wale\n", | |
"[[]]\n", | |
"\n", | |
"\n", | |
"new south wales\n", | |
"[[(u'new south wales', u'state')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: california\n", | |
"c\n", | |
"[[(u'centre', u'house')], [(u'center', u'house')], [(u'central', u'house')]]\n", | |
"\n", | |
"\n", | |
"ca\n", | |
"[[(u'california', u'house')], [(u'ca', u'country')]]\n", | |
"\n", | |
"\n", | |
"cal\n", | |
"[[(u'cal', u'house')]]\n", | |
"\n", | |
"\n", | |
"cali\n", | |
"[[(u'cali', u'city')]]\n", | |
"\n", | |
"\n", | |
"calif\n", | |
"[[(u'calif', u'house')]]\n", | |
"\n", | |
"\n", | |
"califo\n", | |
"[[(u'califo', u'house')]]\n", | |
"\n", | |
"\n", | |
"califor\n", | |
"[[(u'califor', u'house')]]\n", | |
"\n", | |
"\n", | |
"californ\n", | |
"[[(u'californ', u'house')]]\n", | |
"\n", | |
"\n", | |
"californi\n", | |
"[[(u'californi', u'house')]]\n", | |
"\n", | |
"\n", | |
"california\n", | |
"[[(u'california', u'house')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: west bengal\n", | |
"w\n", | |
"[[(u'west', u'city_district')], [(u'w', u'house')]]\n", | |
"\n", | |
"\n", | |
"we\n", | |
"[[(u'warehouse', u'house')]]\n", | |
"\n", | |
"\n", | |
"wes\n", | |
"[[(u'wes', u'road')]]\n", | |
"\n", | |
"\n", | |
"west\n", | |
"[[(u'west', u'city_district')]]\n", | |
"\n", | |
"\n", | |
"west \n", | |
"[[(u'west', u'city_district')]]\n", | |
"\n", | |
"\n", | |
"west b\n", | |
"[[(u'west', u'road'), (u'b', u'house')]]\n", | |
"\n", | |
"\n", | |
"west be\n", | |
"[[(u'west', u'road'), (u'be', u'country')]]\n", | |
"\n", | |
"\n", | |
"west ben\n", | |
"[[(u'west ben', u'road')]]\n", | |
"\n", | |
"\n", | |
"west beng\n", | |
"[[(u'west', u'road'), (u'beng', u'suburb')]]\n", | |
"\n", | |
"\n", | |
"west benga\n", | |
"[[(u'west benga', u'road')]]\n", | |
"\n", | |
"\n", | |
"west bengal\n", | |
"[[(u'west bengal', u'state')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: madrid\n", | |
"m\n", | |
"[[(u'mail', u'road')]]\n", | |
"\n", | |
"\n", | |
"ma\n", | |
"[[(u'massachusetts', u'state')], [(u'ma', u'house')]]\n", | |
"\n", | |
"\n", | |
"mad\n", | |
"[[(u'mad', u'house')]]\n", | |
"\n", | |
"\n", | |
"madr\n", | |
"[[(u'madr', u'house')]]\n", | |
"\n", | |
"\n", | |
"madri\n", | |
"[[(u'madri', u'house')]]\n", | |
"\n", | |
"\n", | |
"madrid\n", | |
"[[(u'madrid', u'city')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: malmo\n", | |
"m\n", | |
"[[(u'mail', u'road')]]\n", | |
"\n", | |
"\n", | |
"ma\n", | |
"[[(u'massachusetts', u'state')], [(u'ma', u'house')]]\n", | |
"\n", | |
"\n", | |
"mal\n", | |
"[[(u'mal', u'house')]]\n", | |
"\n", | |
"\n", | |
"malm\n", | |
"[[(u'malm', u'city')]]\n", | |
"\n", | |
"\n", | |
"malmo\n", | |
"[[(u'malmo', u'city')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: Singarpuram\n", | |
"S\n", | |
"[[(u'san', u'road')], [(u'south', u'road')], [(u's', u'road')]]\n", | |
"\n", | |
"\n", | |
"Si\n", | |
"[[(u'si', u'country')]]\n", | |
"\n", | |
"\n", | |
"Sin\n", | |
"[[(u'sin', u'house')]]\n", | |
"\n", | |
"\n", | |
"Sing\n", | |
"[[(u'sing', u'house')]]\n", | |
"\n", | |
"\n", | |
"Singa\n", | |
"[[(u'singa', u'road')]]\n", | |
"\n", | |
"\n", | |
"Singar\n", | |
"[[(u'singar', u'house')]]\n", | |
"\n", | |
"\n", | |
"Singarp\n", | |
"[[(u'singarp', u'house')]]\n", | |
"\n", | |
"\n", | |
"Singarpu\n", | |
"[[(u'singarpu', u'house')]]\n", | |
"\n", | |
"\n", | |
"Singarpur\n", | |
"[[(u'singarpur', u'house')]]\n", | |
"\n", | |
"\n", | |
"Singarpura\n", | |
"[[(u'singarpura', u'house')]]\n", | |
"\n", | |
"\n", | |
"Singarpuram\n", | |
"[[(u'singarpuram', u'suburb')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"====================================================================\n", | |
"\n", | |
"TEST SET: address_type\n", | |
"TEST: 102 Fleet Street\n", | |
"1\n", | |
"[[(u'1', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"10\n", | |
"[[(u'10', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"102\n", | |
"[[(u'102', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"102 \n", | |
"[[(u'102', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"102 F\n", | |
"[[(u'102 flat', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"102 Fl\n", | |
"[[(u'102', u'house_number'), (u'fl', u'road')], [(u'102 flat', u'house_number')], [(u'102', u'house_number'), (u'fall', u'road')], [(u'102', u'house_number'), (u'florida', u'road')], [(u'102', u'house_number'), (u'floor', u'road')]]\n", | |
"\n", | |
"\n", | |
"102 Fle\n", | |
"[[(u'102', u'house_number'), (u'fle', u'road')]]\n", | |
"\n", | |
"\n", | |
"102 Flee\n", | |
"[[(u'102', u'house_number'), (u'flee', u'road')]]\n", | |
"\n", | |
"\n", | |
"102 Fleet\n", | |
"[[(u'102', u'house_number'), (u'fleet', u'road')]]\n", | |
"\n", | |
"\n", | |
"102 Fleet \n", | |
"[[(u'102', u'house_number'), (u'fleet', u'road')]]\n", | |
"\n", | |
"\n", | |
"102 Fleet S\n", | |
"[[(u'102', u'house_number'), (u'fleet san', u'road')], [(u'102', u'house_number'), (u'fleet south', u'road')], [(u'102', u'house_number'), (u'fleet s', u'road')]]\n", | |
"\n", | |
"\n", | |
"102 Fleet St\n", | |
"[[(u'102', u'house_number'), (u'fleet saint', u'road')], [(u'102', u'house_number'), (u'fleet street', u'road')]]\n", | |
"\n", | |
"\n", | |
"102 Fleet Str\n", | |
"[[(u'102', u'house_number'), (u'fleet street', u'road')]]\n", | |
"\n", | |
"\n", | |
"102 Fleet Stre\n", | |
"[[(u'102', u'house_number'), (u'fleet stre', u'road')]]\n", | |
"\n", | |
"\n", | |
"102 Fleet Stree\n", | |
"[[(u'102', u'house_number'), (u'fleet stree', u'road')]]\n", | |
"\n", | |
"\n", | |
"102 Fleet Street\n", | |
"[[(u'102', u'house_number'), (u'fleet street', u'road')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: Shepherd and Flock\n", | |
"S\n", | |
"[[(u'san', u'road')], [(u'south', u'road')], [(u's', u'road')]]\n", | |
"\n", | |
"\n", | |
"Sh\n", | |
"[[(u'state highway', u'road')]]\n", | |
"\n", | |
"\n", | |
"She\n", | |
"[[(u'she', u'house')]]\n", | |
"\n", | |
"\n", | |
"Shep\n", | |
"[[(u'shep', u'house')]]\n", | |
"\n", | |
"\n", | |
"Sheph\n", | |
"[[(u'sheph', u'house')]]\n", | |
"\n", | |
"\n", | |
"Shephe\n", | |
"[[(u'shephe', u'house')]]\n", | |
"\n", | |
"\n", | |
"Shepher\n", | |
"[[(u'shepher', u'house')]]\n", | |
"\n", | |
"\n", | |
"Shepherd\n", | |
"[[(u'shepherd', u'city')]]\n", | |
"\n", | |
"\n", | |
"Shepherd \n", | |
"[[(u'shepherd', u'city')]]\n", | |
"\n", | |
"\n", | |
"Shepherd a\n", | |
"[[(u'shepherd a', u'house')]]\n", | |
"\n", | |
"\n", | |
"Shepherd an\n", | |
"[[(u'shepherd', u'house'), (u'an', u'road')]]\n", | |
"\n", | |
"\n", | |
"Shepherd and\n", | |
"[[(u'shepherd and', u'house')]]\n", | |
"\n", | |
"\n", | |
"Shepherd and \n", | |
"[[(u'shepherd and', u'house')]]\n", | |
"\n", | |
"\n", | |
"Shepherd and F\n", | |
"[[(u'shepherd', u'house'), (u'0 flat', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"Shepherd and Fl\n", | |
"[[(u'shepherd', u'house'), (u'0', u'house_number'), (u'fl', u'state')], [(u'shepherd', u'house'), (u'0 flat', u'house_number')], [(u'shepherd', u'house'), (u'0', u'house_number'), (u'fall', u'city')], [(u'shepherd', u'house'), (u'0', u'house_number'), (u'florida', u'road')], [(u'shepherd', u'house'), (u'0 floor', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"Shepherd and Flo\n", | |
"[[(u'shepherd', u'house'), (u'0', u'house_number'), (u'flo', u'city_district')]]\n", | |
"\n", | |
"\n", | |
"Shepherd and Floc\n", | |
"[[(u'shepherd', u'house'), (u'0', u'house_number'), (u'floc', u'road')]]\n", | |
"\n", | |
"\n", | |
"Shepherd and Flock\n", | |
"[[(u'shepherd', u'house'), (u'0', u'house_number'), (u'flock', u'road')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: 22 Moor Park Lane\n", | |
"2\n", | |
"[[(u'2', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"22\n", | |
"[[(u'22', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"22 \n", | |
"[[(u'22', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"22 M\n", | |
"[[(u'22', u'house_number'), (u'mail', u'road')]]\n", | |
"\n", | |
"\n", | |
"22 Mo\n", | |
"[[(u'22', u'house_number'), (u'mo', u'road')], [(u'22', u'house_number'), (u'missouri', u'road')]]\n", | |
"\n", | |
"\n", | |
"22 Moo\n", | |
"[[(u'22 moo', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"22 Moor\n", | |
"[[(u'22', u'house_number'), (u'moor', u'road')]]\n", | |
"\n", | |
"\n", | |
"22 Moor \n", | |
"[[(u'22', u'house_number'), (u'moor', u'road')]]\n", | |
"\n", | |
"\n", | |
"22 Moor P\n", | |
"[[(u'22', u'house_number'), (u'moor', u'road'), (u'p', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"22 Moor Pa\n", | |
"[[(u'22', u'house_number'), (u'moor pa', u'road')], [(u'22', u'house_number'), (u'moor', u'road'), (u'pennsylvania', u'state')]]\n", | |
"\n", | |
"\n", | |
"22 Moor Par\n", | |
"[[(u'22', u'house_number'), (u'moor par', u'road')]]\n", | |
"\n", | |
"\n", | |
"22 Moor Park\n", | |
"[[(u'22', u'house_number'), (u'moor park', u'road')]]\n", | |
"\n", | |
"\n", | |
"22 Moor Park \n", | |
"[[(u'22', u'house_number'), (u'moor park', u'road')]]\n", | |
"\n", | |
"\n", | |
"22 Moor Park L\n", | |
"[[(u'22', u'house_number'), (u'moor park level', u'road')]]\n", | |
"\n", | |
"\n", | |
"22 Moor Park La\n", | |
"[[(u'22', u'house_number'), (u'moor park la', u'road')], [(u'22', u'house_number'), (u'moor park lane', u'road')], [(u'22', u'house_number'), (u'moor park', u'road'), (u'louisiana', u'state')]]\n", | |
"\n", | |
"\n", | |
"22 Moor Park Lan\n", | |
"[[(u'22', u'house_number'), (u'moor park', u'road'), (u'lan', u'suburb')]]\n", | |
"\n", | |
"\n", | |
"22 Moor Park Lane\n", | |
"[[(u'22', u'house_number'), (u'moor park lane', u'road')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"====================================================================\n", | |
"\n", | |
"TEST SET: search\n", | |
"TEST: brooklyn\n", | |
"b\n", | |
"[[(u'b', u'house')]]\n", | |
"\n", | |
"\n", | |
"br\n", | |
"[[(u'brae', u'road')], [(u'brother', u'house')], [(u'brace', u'house')], [(u'bridge', u'house')], [(u'branch', u'house')]]\n", | |
"\n", | |
"\n", | |
"bro\n", | |
"[[(u'bro', u'road')]]\n", | |
"\n", | |
"\n", | |
"broo\n", | |
"[[(u'broo', u'house')]]\n", | |
"\n", | |
"\n", | |
"brook\n", | |
"[[(u'brook', u'house')]]\n", | |
"\n", | |
"\n", | |
"brookl\n", | |
"[[(u'brookl', u'house')]]\n", | |
"\n", | |
"\n", | |
"brookly\n", | |
"[[(u'brookly', u'house')]]\n", | |
"\n", | |
"\n", | |
"brooklyn\n", | |
"[[(u'brooklyn', u'house')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: brooklyn, ny\n", | |
"b\n", | |
"[[(u'b', u'house')]]\n", | |
"\n", | |
"\n", | |
"br\n", | |
"[[(u'brae', u'road')], [(u'brother', u'house')], [(u'brace', u'house')], [(u'bridge', u'house')], [(u'branch', u'house')]]\n", | |
"\n", | |
"\n", | |
"bro\n", | |
"[[(u'bro', u'road')]]\n", | |
"\n", | |
"\n", | |
"broo\n", | |
"[[(u'broo', u'house')]]\n", | |
"\n", | |
"\n", | |
"brook\n", | |
"[[(u'brook', u'house')]]\n", | |
"\n", | |
"\n", | |
"brookl\n", | |
"[[(u'brookl', u'house')]]\n", | |
"\n", | |
"\n", | |
"brookly\n", | |
"[[(u'brookly', u'house')]]\n", | |
"\n", | |
"\n", | |
"brooklyn\n", | |
"[[(u'brooklyn', u'house')]]\n", | |
"\n", | |
"\n", | |
"brooklyn,\n", | |
"[[(u'brooklyn', u'house')]]\n", | |
"\n", | |
"\n", | |
"brooklyn, \n", | |
"[[(u'brooklyn', u'house')]]\n", | |
"\n", | |
"\n", | |
"brooklyn, n\n", | |
"[[(u'brooklyn', u'house'), (u'north', u'road')], [(u'brooklyn n', u'house')]]\n", | |
"\n", | |
"\n", | |
"brooklyn, ny\n", | |
"[[(u'brooklyn', u'state_district'), (u'new york', u'state')], [(u'brooklyn', u'city'), (u'ny', u'state')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: philadelphia\n", | |
"p\n", | |
"[[(u'p', u'road')]]\n", | |
"\n", | |
"\n", | |
"ph\n", | |
"[[(u'penthouse', u'house')]]\n", | |
"\n", | |
"\n", | |
"phi\n", | |
"[[(u'phi', u'house')]]\n", | |
"\n", | |
"\n", | |
"phil\n", | |
"[[(u'phil', u'house')]]\n", | |
"\n", | |
"\n", | |
"phila\n", | |
"[[(u'phila', u'city')]]\n", | |
"\n", | |
"\n", | |
"philad\n", | |
"[[(u'philad', u'house')]]\n", | |
"\n", | |
"\n", | |
"philade\n", | |
"[[(u'philade', u'house')]]\n", | |
"\n", | |
"\n", | |
"philadel\n", | |
"[[(u'philadel', u'house')]]\n", | |
"\n", | |
"\n", | |
"philadelp\n", | |
"[[(u'philadelp', u'house')]]\n", | |
"\n", | |
"\n", | |
"philadelph\n", | |
"[[(u'philadelph', u'house')]]\n", | |
"\n", | |
"\n", | |
"philadelphi\n", | |
"[[(u'philadelphi', u'house')]]\n", | |
"\n", | |
"\n", | |
"philadelphia\n", | |
"[[(u'philadelphia', u'house')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: philadelphia, pa\n", | |
"p\n", | |
"[[(u'p', u'road')]]\n", | |
"\n", | |
"\n", | |
"ph\n", | |
"[[(u'penthouse', u'house')]]\n", | |
"\n", | |
"\n", | |
"phi\n", | |
"[[(u'phi', u'house')]]\n", | |
"\n", | |
"\n", | |
"phil\n", | |
"[[(u'phil', u'house')]]\n", | |
"\n", | |
"\n", | |
"phila\n", | |
"[[(u'phila', u'city')]]\n", | |
"\n", | |
"\n", | |
"philad\n", | |
"[[(u'philad', u'house')]]\n", | |
"\n", | |
"\n", | |
"philade\n", | |
"[[(u'philade', u'house')]]\n", | |
"\n", | |
"\n", | |
"philadel\n", | |
"[[(u'philadel', u'house')]]\n", | |
"\n", | |
"\n", | |
"philadelp\n", | |
"[[(u'philadelp', u'house')]]\n", | |
"\n", | |
"\n", | |
"philadelph\n", | |
"[[(u'philadelph', u'house')]]\n", | |
"\n", | |
"\n", | |
"philadelphi\n", | |
"[[(u'philadelphi', u'house')]]\n", | |
"\n", | |
"\n", | |
"philadelphia\n", | |
"[[(u'philadelphia', u'house')]]\n", | |
"\n", | |
"\n", | |
"philadelphia,\n", | |
"[[(u'philadelphia', u'house')]]\n", | |
"\n", | |
"\n", | |
"philadelphia, \n", | |
"[[(u'philadelphia', u'house')]]\n", | |
"\n", | |
"\n", | |
"philadelphia, p\n", | |
"[[(u'philadelphia p', u'house')]]\n", | |
"\n", | |
"\n", | |
"philadelphia, pa\n", | |
"[[(u'philadelphia', u'city'), (u'pa', u'state')], [(u'philadelphia', u'city'), (u'pennsylvania', u'state')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: new york, new york\n", | |
"n\n", | |
"[[(u'north', u'road')], [(u'n', u'road')]]\n", | |
"\n", | |
"\n", | |
"ne\n", | |
"[[(u'ne', u'road')], [(u'northeast', u'road')], [(u'nebraska', u'state')]]\n", | |
"\n", | |
"\n", | |
"new\n", | |
"[[(u'new', u'house')]]\n", | |
"\n", | |
"\n", | |
"new \n", | |
"[[(u'new', u'house')]]\n", | |
"\n", | |
"\n", | |
"new y\n", | |
"[[(u'new y', u'house')]]\n", | |
"\n", | |
"\n", | |
"new yo\n", | |
"[[(u'new yo', u'house')]]\n", | |
"\n", | |
"\n", | |
"new yor\n", | |
"[[(u'new yor', u'house')]]\n", | |
"\n", | |
"\n", | |
"new york\n", | |
"[[(u'new york', u'state')]]\n", | |
"\n", | |
"\n", | |
"new york,\n", | |
"[[(u'new york', u'state')]]\n", | |
"\n", | |
"\n", | |
"new york, \n", | |
"[[(u'new york', u'state')]]\n", | |
"\n", | |
"\n", | |
"new york, n\n", | |
"[[(u'new york', u'house'), (u'north', u'road')], [(u'new york', u'state'), (u'n', u'postcode')]]\n", | |
"\n", | |
"\n", | |
"new york, ne\n", | |
"[[(u'new york ne', u'state')], [(u'new york', u'state'), (u'northeast', u'road')], [(u'new york', u'city'), (u'nebraska', u'state')]]\n", | |
"\n", | |
"\n", | |
"new york, new\n", | |
"[[(u'new york', u'city'), (u'new', u'country')]]\n", | |
"\n", | |
"\n", | |
"new york, new \n", | |
"[[(u'new york', u'city'), (u'new', u'country')]]\n", | |
"\n", | |
"\n", | |
"new york, new y\n", | |
"[[(u'new york', u'city'), (u'new y', u'house')]]\n", | |
"\n", | |
"\n", | |
"new york, new yo\n", | |
"[[(u'new york', u'city'), (u'new yo', u'house')]]\n", | |
"\n", | |
"\n", | |
"new york, new yor\n", | |
"[[(u'new york', u'city'), (u'new', u'house'), (u'yor', u'city')]]\n", | |
"\n", | |
"\n", | |
"new york, new york\n", | |
"[[(u'new york', u'city'), (u'new york', u'state')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: new york city\n", | |
"n\n", | |
"[[(u'north', u'road')], [(u'n', u'road')]]\n", | |
"\n", | |
"\n", | |
"ne\n", | |
"[[(u'ne', u'road')], [(u'northeast', u'road')], [(u'nebraska', u'state')]]\n", | |
"\n", | |
"\n", | |
"new\n", | |
"[[(u'new', u'house')]]\n", | |
"\n", | |
"\n", | |
"new \n", | |
"[[(u'new', u'house')]]\n", | |
"\n", | |
"\n", | |
"new y\n", | |
"[[(u'new y', u'house')]]\n", | |
"\n", | |
"\n", | |
"new yo\n", | |
"[[(u'new yo', u'house')]]\n", | |
"\n", | |
"\n", | |
"new yor\n", | |
"[[(u'new yor', u'house')]]\n", | |
"\n", | |
"\n", | |
"new york\n", | |
"[[(u'new york', u'state')]]\n", | |
"\n", | |
"\n", | |
"new york \n", | |
"[[(u'new york', u'state')]]\n", | |
"\n", | |
"\n", | |
"new york c\n", | |
"[[(u'new york centre', u'house')], [(u'new york center', u'house')], [(u'new york central', u'road')]]\n", | |
"\n", | |
"\n", | |
"new york ci\n", | |
"[[(u'new york circuit', u'house')]]\n", | |
"\n", | |
"\n", | |
"new york cit\n", | |
"[[(u'new york cit', u'house')]]\n", | |
"\n", | |
"\n", | |
"new york city\n", | |
"[[(u'new york city', u'city')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: new york city, usa\n", | |
"n\n", | |
"[[(u'north', u'road')], [(u'n', u'road')]]\n", | |
"\n", | |
"\n", | |
"ne\n", | |
"[[(u'ne', u'road')], [(u'northeast', u'road')], [(u'nebraska', u'state')]]\n", | |
"\n", | |
"\n", | |
"new\n", | |
"[[(u'new', u'house')]]\n", | |
"\n", | |
"\n", | |
"new \n", | |
"[[(u'new', u'house')]]\n", | |
"\n", | |
"\n", | |
"new y\n", | |
"[[(u'new y', u'house')]]\n", | |
"\n", | |
"\n", | |
"new yo\n", | |
"[[(u'new yo', u'house')]]\n", | |
"\n", | |
"\n", | |
"new yor\n", | |
"[[(u'new yor', u'house')]]\n", | |
"\n", | |
"\n", | |
"new york\n", | |
"[[(u'new york', u'state')]]\n", | |
"\n", | |
"\n", | |
"new york \n", | |
"[[(u'new york', u'state')]]\n", | |
"\n", | |
"\n", | |
"new york c\n", | |
"[[(u'new york centre', u'house')], [(u'new york center', u'house')], [(u'new york central', u'road')]]\n", | |
"\n", | |
"\n", | |
"new york ci\n", | |
"[[(u'new york circuit', u'house')]]\n", | |
"\n", | |
"\n", | |
"new york cit\n", | |
"[[(u'new york cit', u'house')]]\n", | |
"\n", | |
"\n", | |
"new york city\n", | |
"[[(u'new york city', u'city')]]\n", | |
"\n", | |
"\n", | |
"new york city,\n", | |
"[[(u'new york city', u'city')]]\n", | |
"\n", | |
"\n", | |
"new york city, \n", | |
"[[(u'new york city', u'city')]]\n", | |
"\n", | |
"\n", | |
"new york city, u\n", | |
"[[(u'new york city u', u'house')]]\n", | |
"\n", | |
"\n", | |
"new york city, us\n", | |
"[[(u'new york city', u'city'), (u'us', u'country')]]\n", | |
"\n", | |
"\n", | |
"new york city, usa\n", | |
"[[(u'new york city', u'city'), (u'usa', u'country')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: 130 dean street brooklyn, ny\n", | |
"1\n", | |
"[[(u'1', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"13\n", | |
"[[(u'13', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"130\n", | |
"[[(u'130', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"130 \n", | |
"[[(u'130', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"130 d\n", | |
"[[(u'130', u'house_number'), (u'd', u'road')], [(u'130', u'house'), (u'500', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"130 de\n", | |
"[[(u'130', u'house_number'), (u'delaware', u'road')], [(u'130', u'house_number'), (u'de', u'road')]]\n", | |
"\n", | |
"\n", | |
"130 dea\n", | |
"[[(u'130', u'house_number'), (u'dea', u'road')]]\n", | |
"\n", | |
"\n", | |
"130 dean\n", | |
"[[(u'130', u'house_number'), (u'dean', u'road')]]\n", | |
"\n", | |
"\n", | |
"130 dean \n", | |
"[[(u'130', u'house_number'), (u'dean', u'road')]]\n", | |
"\n", | |
"\n", | |
"130 dean s\n", | |
"[[(u'130', u'house_number'), (u'dean san', u'road')], [(u'130', u'house_number'), (u'dean south', u'road')], [(u'130', u'house_number'), (u'dean s', u'road')]]\n", | |
"\n", | |
"\n", | |
"130 dean st\n", | |
"[[(u'130', u'house_number'), (u'dean saint', u'road')], [(u'130', u'house_number'), (u'dean street', u'road')]]\n", | |
"\n", | |
"\n", | |
"130 dean str\n", | |
"[[(u'130', u'house_number'), (u'dean street', u'road')]]\n", | |
"\n", | |
"\n", | |
"130 dean stre\n", | |
"[[(u'130', u'house_number'), (u'dean stre', u'road')]]\n", | |
"\n", | |
"\n", | |
"130 dean stree\n", | |
"[[(u'130', u'house_number'), (u'dean stree', u'road')]]\n", | |
"\n", | |
"\n", | |
"130 dean street\n", | |
"[[(u'130', u'house_number'), (u'dean street', u'road')]]\n", | |
"\n", | |
"\n", | |
"130 dean street \n", | |
"[[(u'130', u'house_number'), (u'dean street', u'road')]]\n", | |
"\n", | |
"\n", | |
"130 dean street b\n", | |
"[[(u'130', u'house_number'), (u'dean street b', u'road')]]\n", | |
"\n", | |
"\n", | |
"130 dean street br\n", | |
"[[(u'130', u'house_number'), (u'dean street', u'road'), (u'brae', u'city')], [(u'130', u'house_number'), (u'dean street', u'road'), (u'brother', u'suburb')], [(u'130', u'house_number'), (u'dean street', u'road'), (u'brace', u'city')], [(u'130', u'house_number'), (u'dean street bridge', u'road')], [(u'130', u'house_number'), (u'dean street branch', u'road')]]\n", | |
"\n", | |
"\n", | |
"130 dean street bro\n", | |
"[[(u'130', u'house_number'), (u'dean street', u'road'), (u'bro', u'city')]]\n", | |
"\n", | |
"\n", | |
"130 dean street broo\n", | |
"[[(u'130', u'house_number'), (u'dean street', u'road'), (u'broo', u'city')]]\n", | |
"\n", | |
"\n", | |
"130 dean street brook\n", | |
"[[(u'130', u'house_number'), (u'dean street', u'road'), (u'brook', u'city')]]\n", | |
"\n", | |
"\n", | |
"130 dean street brookl\n", | |
"[[(u'130', u'house_number'), (u'dean street', u'road'), (u'brookl', u'city')]]\n", | |
"\n", | |
"\n", | |
"130 dean street brookly\n", | |
"[[(u'130', u'house_number'), (u'dean street', u'road'), (u'brookly', u'city')]]\n", | |
"\n", | |
"\n", | |
"130 dean street brooklyn\n", | |
"[[(u'130', u'house_number'), (u'dean street', u'road'), (u'brooklyn', u'city')]]\n", | |
"\n", | |
"\n", | |
"130 dean street brooklyn,\n", | |
"[[(u'130', u'house_number'), (u'dean street', u'road'), (u'brooklyn', u'city')]]\n", | |
"\n", | |
"\n", | |
"130 dean street brooklyn, \n", | |
"[[(u'130', u'house_number'), (u'dean street', u'road'), (u'brooklyn', u'city')]]\n", | |
"\n", | |
"\n", | |
"130 dean street brooklyn, n\n", | |
"[[(u'130', u'house_number'), (u'dean street', u'road'), (u'brooklyn north', u'suburb')], [(u'130', u'house_number'), (u'dean street', u'road'), (u'brooklyn n', u'city')]]\n", | |
"\n", | |
"\n", | |
"130 dean street brooklyn, ny\n", | |
"[[(u'130', u'house_number'), (u'dean street', u'road'), (u'brooklyn', u'state_district'), (u'new york', u'state')], [(u'130', u'house_number'), (u'dean street', u'road'), (u'brooklyn', u'state_district'), (u'ny', u'state')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: billerica\n", | |
"b\n", | |
"[[(u'b', u'house')]]\n", | |
"\n", | |
"\n", | |
"bi\n", | |
"[[(u'bi', u'house')]]\n", | |
"\n", | |
"\n", | |
"bil\n", | |
"[[(u'bil', u'house')]]\n", | |
"\n", | |
"\n", | |
"bill\n", | |
"[[(u'bill', u'house')]]\n", | |
"\n", | |
"\n", | |
"bille\n", | |
"[[(u'bille', u'house')]]\n", | |
"\n", | |
"\n", | |
"biller\n", | |
"[[(u'biller', u'house')]]\n", | |
"\n", | |
"\n", | |
"billeri\n", | |
"[[(u'billeri', u'house')]]\n", | |
"\n", | |
"\n", | |
"billeric\n", | |
"[[(u'billeric', u'house')]]\n", | |
"\n", | |
"\n", | |
"billerica\n", | |
"[[(u'billerica', u'city')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: billerica, ma\n", | |
"b\n", | |
"[[(u'b', u'house')]]\n", | |
"\n", | |
"\n", | |
"bi\n", | |
"[[(u'bi', u'house')]]\n", | |
"\n", | |
"\n", | |
"bil\n", | |
"[[(u'bil', u'house')]]\n", | |
"\n", | |
"\n", | |
"bill\n", | |
"[[(u'bill', u'house')]]\n", | |
"\n", | |
"\n", | |
"bille\n", | |
"[[(u'bille', u'house')]]\n", | |
"\n", | |
"\n", | |
"biller\n", | |
"[[(u'biller', u'house')]]\n", | |
"\n", | |
"\n", | |
"billeri\n", | |
"[[(u'billeri', u'house')]]\n", | |
"\n", | |
"\n", | |
"billeric\n", | |
"[[(u'billeric', u'house')]]\n", | |
"\n", | |
"\n", | |
"billerica\n", | |
"[[(u'billerica', u'city')]]\n", | |
"\n", | |
"\n", | |
"billerica,\n", | |
"[[(u'billerica', u'city')]]\n", | |
"\n", | |
"\n", | |
"billerica, \n", | |
"[[(u'billerica', u'city')]]\n", | |
"\n", | |
"\n", | |
"billerica, m\n", | |
"[[(u'billerica', u'city'), (u'mail', u'road')]]\n", | |
"\n", | |
"\n", | |
"billerica, ma\n", | |
"[[(u'billerica', u'city'), (u'massachusetts', u'state')], [(u'billerica', u'city'), (u'ma', u'state')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: 15 call street billerica, ma\n", | |
"1\n", | |
"[[(u'1', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"15\n", | |
"[[(u'15', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"15 \n", | |
"[[(u'15', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"15 c\n", | |
"[[(u'15', u'house_number'), (u'centre', u'road')], [(u'15', u'house_number'), (u'center', u'road')], [(u'15', u'house_number'), (u'central', u'road')]]\n", | |
"\n", | |
"\n", | |
"15 ca\n", | |
"[[(u'15', u'house_number'), (u'california', u'road')], [(u'15', u'house_number'), (u'ca', u'country')]]\n", | |
"\n", | |
"\n", | |
"15 cal\n", | |
"[[(u'15', u'house_number'), (u'cal', u'road')]]\n", | |
"\n", | |
"\n", | |
"15 call\n", | |
"[[(u'15', u'house'), (u'call', u'road')]]\n", | |
"\n", | |
"\n", | |
"15 call \n", | |
"[[(u'15', u'house'), (u'call', u'road')]]\n", | |
"\n", | |
"\n", | |
"15 call s\n", | |
"[[(u'15', u'house'), (u'call', u'road'), (u'san', u'city')], [(u'15', u'house'), (u'call south', u'road')], [(u'15', u'house'), (u'call s', u'road')]]\n", | |
"\n", | |
"\n", | |
"15 call st\n", | |
"[[(u'15', u'house'), (u'call saint', u'road')], [(u'15', u'house'), (u'call street', u'road')]]\n", | |
"\n", | |
"\n", | |
"15 call str\n", | |
"[[(u'15', u'house'), (u'call street', u'road')]]\n", | |
"\n", | |
"\n", | |
"15 call stre\n", | |
"[[(u'15', u'house'), (u'call', u'road'), (u'stre', u'house')]]\n", | |
"\n", | |
"\n", | |
"15 call stree\n", | |
"[[(u'15', u'house'), (u'call stree', u'road')]]\n", | |
"\n", | |
"\n", | |
"15 call street\n", | |
"[[(u'15', u'house'), (u'call street', u'road')]]\n", | |
"\n", | |
"\n", | |
"15 call street \n", | |
"[[(u'15', u'house'), (u'call street', u'road')]]\n", | |
"\n", | |
"\n", | |
"15 call street b\n", | |
"[[(u'15', u'house'), (u'call street b', u'road')]]\n", | |
"\n", | |
"\n", | |
"15 call street bi\n", | |
"[[(u'15', u'house'), (u'call street', u'road'), (u'bi', u'city')]]\n", | |
"\n", | |
"\n", | |
"15 call street bil\n", | |
"[[(u'15', u'house'), (u'call street', u'road'), (u'bil', u'city')]]\n", | |
"\n", | |
"\n", | |
"15 call street bill\n", | |
"[[(u'15', u'house'), (u'call street', u'road'), (u'bill', u'city')]]\n", | |
"\n", | |
"\n", | |
"15 call street bille\n", | |
"[[(u'15', u'house'), (u'call street', u'road'), (u'bille', u'city')]]\n", | |
"\n", | |
"\n", | |
"15 call street biller\n", | |
"[[(u'15', u'house'), (u'call street', u'road'), (u'biller', u'city')]]\n", | |
"\n", | |
"\n", | |
"15 call street billeri\n", | |
"[[(u'15', u'house'), (u'call street', u'road'), (u'billeri', u'city')]]\n", | |
"\n", | |
"\n", | |
"15 call street billeric\n", | |
"[[(u'15', u'house'), (u'call street', u'road'), (u'billeric', u'city')]]\n", | |
"\n", | |
"\n", | |
"15 call street billerica\n", | |
"[[(u'15', u'house'), (u'call street', u'road'), (u'billerica', u'city')]]\n", | |
"\n", | |
"\n", | |
"15 call street billerica,\n", | |
"[[(u'15', u'house'), (u'call street', u'road'), (u'billerica', u'city')]]\n", | |
"\n", | |
"\n", | |
"15 call street billerica, \n", | |
"[[(u'15', u'house'), (u'call street', u'road'), (u'billerica', u'city')]]\n", | |
"\n", | |
"\n", | |
"15 call street billerica, m\n", | |
"[[(u'15', u'house'), (u'call street', u'road'), (u'billerica', u'city'), (u'mail', u'road')]]\n", | |
"\n", | |
"\n", | |
"15 call street billerica, ma\n", | |
"[[(u'15', u'house'), (u'call street', u'road'), (u'billerica', u'city'), (u'massachusetts', u'state')], [(u'15', u'house'), (u'call street', u'road'), (u'billerica', u'city'), (u'ma', u'state')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: union sq\n", | |
"u\n", | |
"[[(u'u', u'house')]]\n", | |
"\n", | |
"\n", | |
"un\n", | |
"[[(u'unit', u'house')], [(u'union', u'house')]]\n", | |
"\n", | |
"\n", | |
"uni\n", | |
"[[(u'university', u'house')]]\n", | |
"\n", | |
"\n", | |
"unio\n", | |
"[[(u'unio', u'road')]]\n", | |
"\n", | |
"\n", | |
"union\n", | |
"[[(u'union', u'house')]]\n", | |
"\n", | |
"\n", | |
"union \n", | |
"[[(u'union', u'house')]]\n", | |
"\n", | |
"\n", | |
"union s\n", | |
"[[(u'union san', u'road')], [(u'union', u'house'), (u'south', u'road')], [(u'union s', u'road')]]\n", | |
"\n", | |
"\n", | |
"union sq\n", | |
"[[(u'union', u'city'), (u'square', u'road')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: portland\n", | |
"p\n", | |
"[[(u'p', u'road')]]\n", | |
"\n", | |
"\n", | |
"po\n", | |
"[[(u'post office', u'house')]]\n", | |
"\n", | |
"\n", | |
"por\n", | |
"[[(u'portion', u'house')]]\n", | |
"\n", | |
"\n", | |
"port\n", | |
"[[(u'port', u'road')]]\n", | |
"\n", | |
"\n", | |
"portl\n", | |
"[[(u'portl', u'house')]]\n", | |
"\n", | |
"\n", | |
"portla\n", | |
"[[(u'portla', u'house')]]\n", | |
"\n", | |
"\n", | |
"portlan\n", | |
"[[(u'portlan', u'house')]]\n", | |
"\n", | |
"\n", | |
"portland\n", | |
"[[(u'portland', u'city')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: portland, oregon\n", | |
"p\n", | |
"[[(u'p', u'road')]]\n", | |
"\n", | |
"\n", | |
"po\n", | |
"[[(u'post office', u'house')]]\n", | |
"\n", | |
"\n", | |
"por\n", | |
"[[(u'portion', u'house')]]\n", | |
"\n", | |
"\n", | |
"port\n", | |
"[[(u'port', u'road')]]\n", | |
"\n", | |
"\n", | |
"portl\n", | |
"[[(u'portl', u'house')]]\n", | |
"\n", | |
"\n", | |
"portla\n", | |
"[[(u'portla', u'house')]]\n", | |
"\n", | |
"\n", | |
"portlan\n", | |
"[[(u'portlan', u'house')]]\n", | |
"\n", | |
"\n", | |
"portland\n", | |
"[[(u'portland', u'city')]]\n", | |
"\n", | |
"\n", | |
"portland,\n", | |
"[[(u'portland', u'city')]]\n", | |
"\n", | |
"\n", | |
"portland, \n", | |
"[[(u'portland', u'city')]]\n", | |
"\n", | |
"\n", | |
"portland, o\n", | |
"[[(u'portland', u'city'), (u'o', u'house')]]\n", | |
"\n", | |
"\n", | |
"portland, or\n", | |
"[[(u'portland', u'city'), (u'oregon', u'state')], [(u'portland', u'city'), (u'or', u'state')]]\n", | |
"\n", | |
"\n", | |
"portland, ore\n", | |
"[[(u'portland', u'city'), (u'ore', u'house')]]\n", | |
"\n", | |
"\n", | |
"portland, oreg\n", | |
"[[(u'portland oreg', u'house')]]\n", | |
"\n", | |
"\n", | |
"portland, orego\n", | |
"[[(u'portland orego', u'house')]]\n", | |
"\n", | |
"\n", | |
"portland, oregon\n", | |
"[[(u'portland', u'city'), (u'oregon', u'state')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: paris\n", | |
"p\n", | |
"[[(u'p', u'road')]]\n", | |
"\n", | |
"\n", | |
"pa\n", | |
"[[(u'pa', u'state')], [(u'pennsylvania', u'state')]]\n", | |
"\n", | |
"\n", | |
"par\n", | |
"[[(u'par', u'house')]]\n", | |
"\n", | |
"\n", | |
"pari\n", | |
"[[(u'pari', u'house')]]\n", | |
"\n", | |
"\n", | |
"paris\n", | |
"[[(u'paris', u'city')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: france\n", | |
"f\n", | |
"[[(u'flat', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"fr\n", | |
"[[(u'father', u'house')], [(u'frontage', u'road')]]\n", | |
"\n", | |
"\n", | |
"fra\n", | |
"[[(u'fra', u'country')]]\n", | |
"\n", | |
"\n", | |
"fran\n", | |
"[[(u'fran', u'house')]]\n", | |
"\n", | |
"\n", | |
"franc\n", | |
"[[(u'franc', u'road')]]\n", | |
"\n", | |
"\n", | |
"france\n", | |
"[[(u'france', u'country')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: london\n", | |
"l\n", | |
"[[(u'level', u'house')]]\n", | |
"\n", | |
"\n", | |
"lo\n", | |
"[[(u'lo', u'house')]]\n", | |
"\n", | |
"\n", | |
"lon\n", | |
"[[(u'lon', u'road')]]\n", | |
"\n", | |
"\n", | |
"lond\n", | |
"[[(u'lond', u'house')]]\n", | |
"\n", | |
"\n", | |
"londo\n", | |
"[[(u'londo', u'house')]]\n", | |
"\n", | |
"\n", | |
"london\n", | |
"[[(u'london', u'city')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: chelsea, new york\n", | |
"c\n", | |
"[[(u'centre', u'house')], [(u'center', u'house')], [(u'central', u'house')]]\n", | |
"\n", | |
"\n", | |
"ch\n", | |
"[[(u'county highway', u'road')], [(u'chase', u'house')]]\n", | |
"\n", | |
"\n", | |
"che\n", | |
"[[(u'che', u'country')]]\n", | |
"\n", | |
"\n", | |
"chel\n", | |
"[[(u'chel', u'house')]]\n", | |
"\n", | |
"\n", | |
"chels\n", | |
"[[(u'chels', u'house')]]\n", | |
"\n", | |
"\n", | |
"chelse\n", | |
"[[(u'chelse', u'house')]]\n", | |
"\n", | |
"\n", | |
"chelsea\n", | |
"[[(u'chelsea', u'city')]]\n", | |
"\n", | |
"\n", | |
"chelsea,\n", | |
"[[(u'chelsea', u'city')]]\n", | |
"\n", | |
"\n", | |
"chelsea, \n", | |
"[[(u'chelsea', u'city')]]\n", | |
"\n", | |
"\n", | |
"chelsea, n\n", | |
"[[(u'chelsea', u'suburb'), (u'north', u'road')], [(u'chelsea', u'house'), (u'n', u'road')]]\n", | |
"\n", | |
"\n", | |
"chelsea, ne\n", | |
"[[(u'chelsea', u'city'), (u'ne', u'state')], [(u'chelsea', u'house'), (u'northeast', u'road')], [(u'chelsea', u'city'), (u'nebraska', u'state')]]\n", | |
"\n", | |
"\n", | |
"chelsea, new\n", | |
"[[(u'chelsea', u'suburb'), (u'new', u'house')]]\n", | |
"\n", | |
"\n", | |
"chelsea, new \n", | |
"[[(u'chelsea', u'suburb'), (u'new', u'house')]]\n", | |
"\n", | |
"\n", | |
"chelsea, new y\n", | |
"[[(u'chelsea', u'suburb'), (u'new y', u'house')]]\n", | |
"\n", | |
"\n", | |
"chelsea, new yo\n", | |
"[[(u'chelsea', u'suburb'), (u'new yo', u'house')]]\n", | |
"\n", | |
"\n", | |
"chelsea, new yor\n", | |
"[[(u'chelsea', u'suburb'), (u'new', u'house'), (u'yor', u'suburb')]]\n", | |
"\n", | |
"\n", | |
"chelsea, new york\n", | |
"[[(u'chelsea', u'suburb'), (u'new york', u'state')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: soho, new york\n", | |
"s\n", | |
"[[(u'san', u'road')], [(u'south', u'road')], [(u's', u'road')]]\n", | |
"\n", | |
"\n", | |
"so\n", | |
"[[(u'south', u'road')]]\n", | |
"\n", | |
"\n", | |
"soh\n", | |
"[[(u'soh', u'house')]]\n", | |
"\n", | |
"\n", | |
"soho\n", | |
"[[(u'soho', u'house')]]\n", | |
"\n", | |
"\n", | |
"soho,\n", | |
"[[(u'soho', u'house')]]\n", | |
"\n", | |
"\n", | |
"soho, \n", | |
"[[(u'soho', u'house')]]\n", | |
"\n", | |
"\n", | |
"soho, n\n", | |
"[[(u'soho', u'house'), (u'north', u'road')], [(u'soho n', u'house')]]\n", | |
"\n", | |
"\n", | |
"soho, ne\n", | |
"[[(u'soho', u'house'), (u'ne', u'road')], [(u'soho', u'house'), (u'northeast', u'road')], [(u'soho', u'suburb'), (u'nebraska', u'state')]]\n", | |
"\n", | |
"\n", | |
"soho, new\n", | |
"[[(u'soho', u'suburb'), (u'new', u'house')]]\n", | |
"\n", | |
"\n", | |
"soho, new \n", | |
"[[(u'soho', u'suburb'), (u'new', u'house')]]\n", | |
"\n", | |
"\n", | |
"soho, new y\n", | |
"[[(u'soho', u'suburb'), (u'new y', u'house')]]\n", | |
"\n", | |
"\n", | |
"soho, new yo\n", | |
"[[(u'soho', u'suburb'), (u'new yo', u'house')]]\n", | |
"\n", | |
"\n", | |
"soho, new yor\n", | |
"[[(u'soho', u'suburb'), (u'new', u'house'), (u'yor', u'suburb')]]\n", | |
"\n", | |
"\n", | |
"soho, new york\n", | |
"[[(u'soho', u'suburb'), (u'new york', u'state')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: perugia airport\n", | |
"p\n", | |
"[[(u'p', u'road')]]\n", | |
"\n", | |
"\n", | |
"pe\n", | |
"[[(u'pe', u'state')], [(u'prince edward island', u'state')]]\n", | |
"\n", | |
"\n", | |
"per\n", | |
"[[(u'per', u'country')]]\n", | |
"\n", | |
"\n", | |
"peru\n", | |
"[[(u'peru', u'country')]]\n", | |
"\n", | |
"\n", | |
"perug\n", | |
"[[(u'perug', u'house')]]\n", | |
"\n", | |
"\n", | |
"perugi\n", | |
"[[(u'perugi', u'house')]]\n", | |
"\n", | |
"\n", | |
"perugia\n", | |
"[[(u'perugia', u'city')]]\n", | |
"\n", | |
"\n", | |
"perugia \n", | |
"[[(u'perugia', u'city')]]\n", | |
"\n", | |
"\n", | |
"perugia a\n", | |
"[[(u'perugia', u'city'), (u'a', u'house')]]\n", | |
"\n", | |
"\n", | |
"perugia ai\n", | |
"[[(u'perugia', u'city'), (u'ai', u'house')]]\n", | |
"\n", | |
"\n", | |
"perugia air\n", | |
"[[(u'perugia air', u'house')]]\n", | |
"\n", | |
"\n", | |
"perugia airp\n", | |
"[[(u'perugia airp', u'house')]]\n", | |
"\n", | |
"\n", | |
"perugia airpo\n", | |
"[[(u'perugia airpo', u'house')]]\n", | |
"\n", | |
"\n", | |
"perugia airpor\n", | |
"[[(u'perugia airpor', u'house')]]\n", | |
"\n", | |
"\n", | |
"perugia airport\n", | |
"[[(u'perugia airport', u'house')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: 101 saint marks pl, new york\n", | |
"1\n", | |
"[[(u'1', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"10\n", | |
"[[(u'10', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"101\n", | |
"[[(u'101', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"101 \n", | |
"[[(u'101', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"101 s\n", | |
"[[(u'101', u'house_number'), (u'san', u'road')], [(u'101', u'house_number'), (u'south', u'road')], [(u'101', u'house_number'), (u's', u'road')]]\n", | |
"\n", | |
"\n", | |
"101 sa\n", | |
"[[(u'101', u'house_number'), (u'southern', u'road'), (u'australia', u'country')]]\n", | |
"\n", | |
"\n", | |
"101 sai\n", | |
"[[(u'101', u'house_number'), (u'sai', u'road')]]\n", | |
"\n", | |
"\n", | |
"101 sain\n", | |
"[[(u'101', u'house_number'), (u'sain', u'road')]]\n", | |
"\n", | |
"\n", | |
"101 saint\n", | |
"[[(u'101', u'house_number'), (u'saint', u'road')]]\n", | |
"\n", | |
"\n", | |
"101 saint \n", | |
"[[(u'101', u'house_number'), (u'saint', u'road')]]\n", | |
"\n", | |
"\n", | |
"101 saint m\n", | |
"[[(u'101', u'house_number'), (u'saint mail', u'road')]]\n", | |
"\n", | |
"\n", | |
"101 saint ma\n", | |
"[[(u'101', u'house_number'), (u'saint', u'road'), (u'massachusetts', u'state')], [(u'101', u'house_number'), (u'saint ma', u'road')]]\n", | |
"\n", | |
"\n", | |
"101 saint mar\n", | |
"[[(u'101', u'house_number'), (u'saint mar', u'road')]]\n", | |
"\n", | |
"\n", | |
"101 saint mark\n", | |
"[[(u'101', u'house_number'), (u'saint mark', u'road')]]\n", | |
"\n", | |
"\n", | |
"101 saint marks\n", | |
"[[(u'101', u'house_number'), (u'saint', u'road'), (u'marks', u'city')]]\n", | |
"\n", | |
"\n", | |
"101 saint marks \n", | |
"[[(u'101', u'house_number'), (u'saint', u'road'), (u'marks', u'city')]]\n", | |
"\n", | |
"\n", | |
"101 saint marks p\n", | |
"[[(u'101', u'house_number'), (u'saint marks p', u'road')]]\n", | |
"\n", | |
"\n", | |
"101 saint marks pl\n", | |
"[[(u'101', u'house_number'), (u'saint marks place', u'road')], [(u'101', u'house_number'), (u'saint marks', u'road'), (u'plain', u'city')]]\n", | |
"\n", | |
"\n", | |
"101 saint marks pl,\n", | |
"[[(u'101', u'house_number'), (u'saint marks place', u'road')], [(u'101', u'house_number'), (u'saint marks', u'road'), (u'plain', u'city')]]\n", | |
"\n", | |
"\n", | |
"101 saint marks pl, \n", | |
"[[(u'101', u'house_number'), (u'saint marks place', u'road')], [(u'101', u'house_number'), (u'saint marks', u'road'), (u'plain', u'city')]]\n", | |
"\n", | |
"\n", | |
"101 saint marks pl, n\n", | |
"[[(u'101', u'house_number'), (u'saint marks place north', u'road')], [(u'101', u'house_number'), (u'saint marks place n', u'road')], [(u'101', u'house_number'), (u'saint marks plain north', u'road')], [(u'101', u'house_number'), (u'saint marks plain n', u'road')]]\n", | |
"\n", | |
"\n", | |
"101 saint marks pl, ne\n", | |
"[[(u'101', u'house_number'), (u'saint marks place ne', u'road')], [(u'101', u'house_number'), (u'saint marks place northeast', u'road')], [(u'101', u'house_number'), (u'saint marks place', u'road'), (u'nebraska', u'state')], [(u'101', u'house_number'), (u'saint marks plain ne', u'road')], [(u'101', u'house_number'), (u'saint marks plain northeast', u'road')], [(u'101', u'house_number'), (u'saint marks', u'road'), (u'plain', u'city'), (u'nebraska', u'state')]]\n", | |
"\n", | |
"\n", | |
"101 saint marks pl, new\n", | |
"[[(u'101', u'house_number'), (u'saint marks place', u'road'), (u'new', u'suburb')], [(u'101', u'house_number'), (u'saint marks plain', u'road'), (u'new', u'suburb')]]\n", | |
"\n", | |
"\n", | |
"101 saint marks pl, new \n", | |
"[[(u'101', u'house_number'), (u'saint marks place', u'road'), (u'new', u'suburb')], [(u'101', u'house_number'), (u'saint marks plain', u'road'), (u'new', u'suburb')]]\n", | |
"\n", | |
"\n", | |
"101 saint marks pl, new y\n", | |
"[[(u'101', u'house_number'), (u'saint marks place new y', u'road')], [(u'101', u'house_number'), (u'saint marks plain new y', u'road')]]\n", | |
"\n", | |
"\n", | |
"101 saint marks pl, new yo\n", | |
"[[(u'101', u'house_number'), (u'saint marks place', u'road'), (u'new yo', u'suburb')], [(u'101', u'house_number'), (u'saint marks plain', u'road'), (u'new yo', u'suburb')]]\n", | |
"\n", | |
"\n", | |
"101 saint marks pl, new yor\n", | |
"[[(u'101', u'house_number'), (u'saint marks place', u'road'), (u'new yor', u'suburb')], [(u'101', u'house_number'), (u'saint marks plain new', u'road'), (u'yor', u'suburb')]]\n", | |
"\n", | |
"\n", | |
"101 saint marks pl, new york\n", | |
"[[(u'101', u'house_number'), (u'saint marks place', u'road'), (u'new york', u'state')], [(u'101', u'house_number'), (u'saint marks plain', u'road'), (u'new york', u'state')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: newark airport\n", | |
"n\n", | |
"[[(u'north', u'road')], [(u'n', u'road')]]\n", | |
"\n", | |
"\n", | |
"ne\n", | |
"[[(u'ne', u'road')], [(u'northeast', u'road')], [(u'nebraska', u'state')]]\n", | |
"\n", | |
"\n", | |
"new\n", | |
"[[(u'new', u'house')]]\n", | |
"\n", | |
"\n", | |
"newa\n", | |
"[[(u'newa', u'house')]]\n", | |
"\n", | |
"\n", | |
"newar\n", | |
"[[(u'newar', u'house')]]\n", | |
"\n", | |
"\n", | |
"newark\n", | |
"[[(u'newark', u'city')]]\n", | |
"\n", | |
"\n", | |
"newark \n", | |
"[[(u'newark', u'city')]]\n", | |
"\n", | |
"\n", | |
"newark a\n", | |
"[[(u'newark', u'city'), (u'a', u'house')]]\n", | |
"\n", | |
"\n", | |
"newark ai\n", | |
"[[(u'newark', u'city'), (u'ai', u'house')]]\n", | |
"\n", | |
"\n", | |
"newark air\n", | |
"[[(u'newark air', u'house')]]\n", | |
"\n", | |
"\n", | |
"newark airp\n", | |
"[[(u'newark airp', u'house')]]\n", | |
"\n", | |
"\n", | |
"newark airpo\n", | |
"[[(u'newark airpo', u'house')]]\n", | |
"\n", | |
"\n", | |
"newark airpor\n", | |
"[[(u'newark airpor', u'house')]]\n", | |
"\n", | |
"\n", | |
"newark airport\n", | |
"[[(u'newark airport', u'house')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: 7 Simon-Dach-Straße\n", | |
"7\n", | |
"[[(u'7', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"7 \n", | |
"[[(u'7', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"7 S\n", | |
"[[(u'7', u'house_number'), (u'san', u'road')], [(u'7', u'house_number'), (u'south', u'road')], [(u'7', u'house_number'), (u's', u'road')]]\n", | |
"\n", | |
"\n", | |
"7 Si\n", | |
"[[(u'7', u'house_number'), (u'si', u'country')]]\n", | |
"\n", | |
"\n", | |
"7 Sim\n", | |
"[[(u'7', u'house_number'), (u'sim', u'road')]]\n", | |
"\n", | |
"\n", | |
"7 Simo\n", | |
"[[(u'7', u'house_number'), (u'simo', u'road')]]\n", | |
"\n", | |
"\n", | |
"7 Simon\n", | |
"[[(u'7', u'house_number'), (u'simon', u'road')]]\n", | |
"\n", | |
"\n", | |
"7 Simon-\n", | |
"[[(u'7', u'house_number'), (u'simon', u'road')]]\n", | |
"\n", | |
"\n", | |
"7 Simon-D\n", | |
"[[(u'7', u'house_number'), (u'simon-d', u'road')], [(u'7 simon-500', u'house')], [(u'7', u'house_number'), (u'simon d', u'road')], [(u'7', u'house_number'), (u'simon', u'road'), (u'500', u'house_number')], [(u'7', u'house_number'), (u'simond', u'road')]]\n", | |
"\n", | |
"\n", | |
"7 Simon-Da\n", | |
"[[(u'7', u'house_number'), (u'simon-da', u'road')], [(u'7', u'house_number'), (u'simon da', u'road')], [(u'7', u'house_number'), (u'simonda', u'road')]]\n", | |
"\n", | |
"\n", | |
"7 Simon-Dac\n", | |
"[[(u'7', u'house_number'), (u'simon-dac', u'road')], [(u'7', u'house_number'), (u'simon dac', u'road')], [(u'7', u'house_number'), (u'simondac', u'road')]]\n", | |
"\n", | |
"\n", | |
"7 Simon-Dach\n", | |
"[[(u'7', u'house_number'), (u'simon-dach', u'road')], [(u'7', u'house_number'), (u'simon dach', u'road')], [(u'7', u'house_number'), (u'simondach', u'road')]]\n", | |
"\n", | |
"\n", | |
"7 Simon-Dach-\n", | |
"[[(u'7', u'house_number'), (u'simon-dach', u'road')], [(u'7', u'house_number'), (u'simon dach', u'road')], [(u'7', u'house_number'), (u'simondach', u'road')]]\n", | |
"\n", | |
"\n", | |
"7 Simon-Dach-S\n", | |
"[[(u'7', u'house_number'), (u'simon-dach-s', u'road')], [(u'7', u'house_number'), (u'simon dach san', u'road')], [(u'7', u'house_number'), (u'simon dach south', u'road')], [(u'7', u'house_number'), (u'simon dach s', u'road')], [(u'7', u'house_number'), (u'simondachs', u'road')]]\n", | |
"\n", | |
"\n", | |
"7 Simon-Dach-St\n", | |
"[[(u'7', u'house_number'), (u'simon-dach-st', u'road')], [(u'7', u'house_number'), (u'simon dach saint', u'road')], [(u'7', u'house_number'), (u'simon dach street', u'road')], [(u'7', u'house_number'), (u'simondachst', u'road')]]\n", | |
"\n", | |
"\n", | |
"7 Simon-Dach-Str\n", | |
"[[(u'7', u'house_number'), (u'simon-dach-str', u'road')], [(u'7', u'house_number'), (u'simon dach street', u'road')], [(u'7', u'house_number'), (u'simondachstr', u'road')]]\n", | |
"\n", | |
"\n", | |
"7 Simon-Dach-Stra\n", | |
"[[(u'7', u'house_number'), (u'simon-dach-stra', u'road')], [(u'7', u'house_number'), (u'simon dach stravenue', u'road')], [(u'7', u'house_number'), (u'simon dach strand', u'road')], [(u'7', u'house_number'), (u'simondachstra', u'road')]]\n", | |
"\n", | |
"\n", | |
"7 Simon-Dach-Straß\n", | |
"[[(u'7', u'house_number'), (u'simon-dach-strass', u'road')], [(u'7', u'house_number'), (u'simon dach', u'road'), (u'strass', u'city')], [(u'7', u'house_number'), (u'simondachstrass', u'road')]]\n", | |
"\n", | |
"\n", | |
"7 Simon-Dach-Straße\n", | |
"[[(u'7', u'house'), (u'simon-dach-strasse', u'road')], [(u'7', u'house_number'), (u'simon dach strasse', u'road')], [(u'7', u'house'), (u'simondachstrasse', u'road')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: Simon-Dach-Straße 7\n", | |
"S\n", | |
"[[(u'san', u'road')], [(u'south', u'road')], [(u's', u'road')]]\n", | |
"\n", | |
"\n", | |
"Si\n", | |
"[[(u'si', u'country')]]\n", | |
"\n", | |
"\n", | |
"Sim\n", | |
"[[(u'sim', u'house')]]\n", | |
"\n", | |
"\n", | |
"Simo\n", | |
"[[(u'simo', u'road')]]\n", | |
"\n", | |
"\n", | |
"Simon\n", | |
"[[(u'simon', u'road')]]\n", | |
"\n", | |
"\n", | |
"Simon-\n", | |
"[[(u'simon', u'road')]]\n", | |
"\n", | |
"\n", | |
"Simon-D\n", | |
"[[(u'simon-d', u'house')], [(u'simon-500', u'house')], [(u'simon d', u'road')], [(u'simon', u'road'), (u'500', u'house_number')], [(u'simond', u'house')]]\n", | |
"\n", | |
"\n", | |
"Simon-Da\n", | |
"[[(u'simon-da', u'house')], [(u'simon da', u'house')], [(u'simonda', u'house')]]\n", | |
"\n", | |
"\n", | |
"Simon-Dac\n", | |
"[[(u'simon-dac', u'house')], [(u'simon dac', u'house')], [(u'simondac', u'house')]]\n", | |
"\n", | |
"\n", | |
"Simon-Dach\n", | |
"[[(u'simon-dach', u'house')], [(u'simon dach', u'house')], [(u'simondach', u'house')]]\n", | |
"\n", | |
"\n", | |
"Simon-Dach-\n", | |
"[[(u'simon-dach', u'house')], [(u'simon dach', u'house')], [(u'simondach', u'house')]]\n", | |
"\n", | |
"\n", | |
"Simon-Dach-S\n", | |
"[[(u'simon-dach-s', u'house')], [(u'simon dach san', u'house')], [(u'simon dach', u'house'), (u'south', u'road')], [(u'simon dach', u'house'), (u's', u'road')], [(u'simondachs', u'house')]]\n", | |
"\n", | |
"\n", | |
"Simon-Dach-St\n", | |
"[[(u'simon-dach-st', u'house')], [(u'simon dach', u'house'), (u'saint', u'road')], [(u'simon', u'house'), (u'dach street', u'road')], [(u'simondachst', u'house')]]\n", | |
"\n", | |
"\n", | |
"Simon-Dach-Str\n", | |
"[[(u'simon-dach-str', u'house')], [(u'simon', u'house'), (u'dach street', u'road')], [(u'simondachstr', u'house')]]\n", | |
"\n", | |
"\n", | |
"Simon-Dach-Stra\n", | |
"[[(u'simon-dach-stra', u'house')], [(u'simon dach', u'house'), (u'stravenue', u'road')], [(u'simon dach', u'house'), (u'strand', u'road')], [(u'simondachstra', u'house')]]\n", | |
"\n", | |
"\n", | |
"Simon-Dach-Straß\n", | |
"[[(u'simon-dach-strass', u'house')], [(u'simon dach', u'house'), (u'strass', u'road')], [(u'simondachstrass', u'house')]]\n", | |
"\n", | |
"\n", | |
"Simon-Dach-Straße\n", | |
"[[(u'simon-dach-strasse', u'road')], [(u'simon', u'house'), (u'dach strasse', u'road')], [(u'simondachstrasse', u'road')]]\n", | |
"\n", | |
"\n", | |
"Simon-Dach-Straße \n", | |
"[[(u'simon-dach-strasse', u'road')], [(u'simon', u'house'), (u'dach strasse', u'road')], [(u'simondachstrasse', u'road')]]\n", | |
"\n", | |
"\n", | |
"Simon-Dach-Straße 7\n", | |
"[[(u'simon-dach-strasse', u'road'), (u'7', u'house_number')], [(u'simon', u'house'), (u'dach strasse', u'road'), (u'7', u'house_number')], [(u'simondachstrasse', u'road'), (u'7', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: 30 West 26th Street\n", | |
"3\n", | |
"[[(u'3', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"30\n", | |
"[[(u'30', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"30 \n", | |
"[[(u'30', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"30 W\n", | |
"[[(u'30', u'house_number'), (u'west', u'road')], [(u'30', u'house_number'), (u'w', u'house')]]\n", | |
"\n", | |
"\n", | |
"30 We\n", | |
"[[(u'30', u'house_number'), (u'warehouse', u'road')]]\n", | |
"\n", | |
"\n", | |
"30 Wes\n", | |
"[[(u'30', u'house_number'), (u'wes', u'road')]]\n", | |
"\n", | |
"\n", | |
"30 West\n", | |
"[[(u'30', u'house_number'), (u'west', u'road')]]\n", | |
"\n", | |
"\n", | |
"30 West \n", | |
"[[(u'30', u'house_number'), (u'west', u'road')]]\n", | |
"\n", | |
"\n", | |
"30 West 2\n", | |
"[[(u'30', u'house_number'), (u'west', u'road'), (u'2', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"30 West 26\n", | |
"[[(u'30', u'house_number'), (u'west 26', u'road')]]\n", | |
"\n", | |
"\n", | |
"30 West 26t\n", | |
"[[(u'30', u'house_number'), (u'west', u'road'), (u'26t', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"30 West 26th\n", | |
"[[(u'30', u'house_number'), (u'west 26th', u'road')]]\n", | |
"\n", | |
"\n", | |
"30 West 26th \n", | |
"[[(u'30', u'house_number'), (u'west 26th', u'road')]]\n", | |
"\n", | |
"\n", | |
"30 West 26th S\n", | |
"[[(u'30', u'house_number'), (u'west 26th san', u'road')], [(u'30', u'house_number'), (u'west 26th south', u'road')], [(u'30', u'house_number'), (u'west 26th s', u'road')]]\n", | |
"\n", | |
"\n", | |
"30 West 26th St\n", | |
"[[(u'30', u'house_number'), (u'west 26th saint', u'road')], [(u'30', u'house_number'), (u'west 26th street', u'road')]]\n", | |
"\n", | |
"\n", | |
"30 West 26th Str\n", | |
"[[(u'30', u'house_number'), (u'west 26th street', u'road')]]\n", | |
"\n", | |
"\n", | |
"30 West 26th Stre\n", | |
"[[(u'30', u'house_number'), (u'west 26th stre', u'road')]]\n", | |
"\n", | |
"\n", | |
"30 West 26th Stree\n", | |
"[[(u'30', u'house_number'), (u'west 26th stree', u'road')]]\n", | |
"\n", | |
"\n", | |
"30 West 26th Street\n", | |
"[[(u'30', u'house_number'), (u'west 26th street', u'road')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: statue of liberty\n", | |
"s\n", | |
"[[(u'san', u'road')], [(u'south', u'road')], [(u's', u'road')]]\n", | |
"\n", | |
"\n", | |
"st\n", | |
"[[(u'saint', u'house')], [(u'street', u'road')]]\n", | |
"\n", | |
"\n", | |
"sta\n", | |
"[[(u'station', u'house')], [(u'santa', u'road')]]\n", | |
"\n", | |
"\n", | |
"stat\n", | |
"[[(u'stat', u'house')]]\n", | |
"\n", | |
"\n", | |
"statu\n", | |
"[[(u'statu', u'house')]]\n", | |
"\n", | |
"\n", | |
"statue\n", | |
"[[(u'statue', u'house')]]\n", | |
"\n", | |
"\n", | |
"statue \n", | |
"[[(u'statue', u'house')]]\n", | |
"\n", | |
"\n", | |
"statue o\n", | |
"[[(u'statue o', u'house')]]\n", | |
"\n", | |
"\n", | |
"statue of\n", | |
"[[(u'statue of', u'house')]]\n", | |
"\n", | |
"\n", | |
"statue of \n", | |
"[[(u'statue of', u'house')]]\n", | |
"\n", | |
"\n", | |
"statue of l\n", | |
"[[(u'statue of level', u'house')]]\n", | |
"\n", | |
"\n", | |
"statue of li\n", | |
"[[(u'statue of li', u'house')], [(u'statue of 51', u'house')]]\n", | |
"\n", | |
"\n", | |
"statue of lib\n", | |
"[[(u'statue of lib', u'house')]]\n", | |
"\n", | |
"\n", | |
"statue of libe\n", | |
"[[(u'statue of libe', u'house')]]\n", | |
"\n", | |
"\n", | |
"statue of liber\n", | |
"[[(u'statue of liber', u'house')]]\n", | |
"\n", | |
"\n", | |
"statue of libert\n", | |
"[[(u'statue of libert', u'house')]]\n", | |
"\n", | |
"\n", | |
"statue of liberty\n", | |
"[[(u'statue of liberty', u'house')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: statue of liberty\n", | |
"s\n", | |
"[[(u'san', u'road')], [(u'south', u'road')], [(u's', u'road')]]\n", | |
"\n", | |
"\n", | |
"st\n", | |
"[[(u'saint', u'house')], [(u'street', u'road')]]\n", | |
"\n", | |
"\n", | |
"sta\n", | |
"[[(u'station', u'house')], [(u'santa', u'road')]]\n", | |
"\n", | |
"\n", | |
"stat\n", | |
"[[(u'stat', u'house')]]\n", | |
"\n", | |
"\n", | |
"statu\n", | |
"[[(u'statu', u'house')]]\n", | |
"\n", | |
"\n", | |
"statue\n", | |
"[[(u'statue', u'house')]]\n", | |
"\n", | |
"\n", | |
"statue \n", | |
"[[(u'statue', u'house')]]\n", | |
"\n", | |
"\n", | |
"statue o\n", | |
"[[(u'statue o', u'house')]]\n", | |
"\n", | |
"\n", | |
"statue of\n", | |
"[[(u'statue of', u'house')]]\n", | |
"\n", | |
"\n", | |
"statue of \n", | |
"[[(u'statue of', u'house')]]\n", | |
"\n", | |
"\n", | |
"statue of l\n", | |
"[[(u'statue of level', u'house')]]\n", | |
"\n", | |
"\n", | |
"statue of li\n", | |
"[[(u'statue of li', u'house')], [(u'statue of 51', u'house')]]\n", | |
"\n", | |
"\n", | |
"statue of lib\n", | |
"[[(u'statue of lib', u'house')]]\n", | |
"\n", | |
"\n", | |
"statue of libe\n", | |
"[[(u'statue of libe', u'house')]]\n", | |
"\n", | |
"\n", | |
"statue of liber\n", | |
"[[(u'statue of liber', u'house')]]\n", | |
"\n", | |
"\n", | |
"statue of libert\n", | |
"[[(u'statue of libert', u'house')]]\n", | |
"\n", | |
"\n", | |
"statue of liberty\n", | |
"[[(u'statue of liberty', u'house')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: 4th and King\n", | |
"4\n", | |
"[[(u'4', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"4t\n", | |
"[[(u'4t', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"4th\n", | |
"[[(u'4th', u'house')]]\n", | |
"\n", | |
"\n", | |
"4th \n", | |
"[[(u'4th', u'house')]]\n", | |
"\n", | |
"\n", | |
"4th a\n", | |
"[[(u'4th a', u'road')]]\n", | |
"\n", | |
"\n", | |
"4th an\n", | |
"[[(u'4th an', u'house')]]\n", | |
"\n", | |
"\n", | |
"4th and\n", | |
"[[(u'4th and', u'house')]]\n", | |
"\n", | |
"\n", | |
"4th and \n", | |
"[[(u'4th and', u'house')]]\n", | |
"\n", | |
"\n", | |
"4th and K\n", | |
"[[(u'4th', u'road'), (u'0 k', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"4th and Ki\n", | |
"[[(u'4th', u'road'), (u'0', u'house_number'), (u'ki', u'city_district')]]\n", | |
"\n", | |
"\n", | |
"4th and Kin\n", | |
"[[(u'4th', u'road'), (u'0', u'house_number'), (u'kin', u'city')]]\n", | |
"\n", | |
"\n", | |
"4th and King\n", | |
"[[(u'4th', u'road'), (u'0', u'house_number'), (u'king', u'road')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: Lancaster\n", | |
"L\n", | |
"[[(u'level', u'house')]]\n", | |
"\n", | |
"\n", | |
"La\n", | |
"[[(u'la', u'house')], [(u'lane', u'road')], [(u'louisiana', u'house')]]\n", | |
"\n", | |
"\n", | |
"Lan\n", | |
"[[(u'lan', u'house')]]\n", | |
"\n", | |
"\n", | |
"Lanc\n", | |
"[[(u'lanc', u'house')]]\n", | |
"\n", | |
"\n", | |
"Lanca\n", | |
"[[(u'lanca', u'house')]]\n", | |
"\n", | |
"\n", | |
"Lancas\n", | |
"[[(u'lancas', u'house')]]\n", | |
"\n", | |
"\n", | |
"Lancast\n", | |
"[[(u'lancast', u'house')]]\n", | |
"\n", | |
"\n", | |
"Lancaste\n", | |
"[[(u'lancaste', u'house')]]\n", | |
"\n", | |
"\n", | |
"Lancaster\n", | |
"[[(u'lancaster', u'city')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: Paris\n", | |
"P\n", | |
"[[(u'p', u'road')]]\n", | |
"\n", | |
"\n", | |
"Pa\n", | |
"[[(u'pa', u'state')], [(u'pennsylvania', u'state')]]\n", | |
"\n", | |
"\n", | |
"Par\n", | |
"[[(u'par', u'house')]]\n", | |
"\n", | |
"\n", | |
"Pari\n", | |
"[[(u'pari', u'house')]]\n", | |
"\n", | |
"\n", | |
"Paris\n", | |
"[[(u'paris', u'city')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: Manchester\n", | |
"M\n", | |
"[[(u'mail', u'road')]]\n", | |
"\n", | |
"\n", | |
"Ma\n", | |
"[[(u'massachusetts', u'state')], [(u'ma', u'house')]]\n", | |
"\n", | |
"\n", | |
"Man\n", | |
"[[(u'man', u'house')]]\n", | |
"\n", | |
"\n", | |
"Manc\n", | |
"[[(u'manc', u'house')]]\n", | |
"\n", | |
"\n", | |
"Manch\n", | |
"[[(u'manch', u'house')]]\n", | |
"\n", | |
"\n", | |
"Manche\n", | |
"[[(u'manche', u'house')]]\n", | |
"\n", | |
"\n", | |
"Manches\n", | |
"[[(u'manches', u'house')]]\n", | |
"\n", | |
"\n", | |
"Manchest\n", | |
"[[(u'manchest', u'house')]]\n", | |
"\n", | |
"\n", | |
"Mancheste\n", | |
"[[(u'mancheste', u'house')]]\n", | |
"\n", | |
"\n", | |
"Manchester\n", | |
"[[(u'manchester', u'city')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"====================================================================\n", | |
"\n", | |
"TEST SET: autocomplete_venues\n", | |
"TEST: DiDi Dumpling\n", | |
"D\n", | |
"[[(u'd', u'house')], [(u'500', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"Di\n", | |
"[[(u'di', u'house')], [(u'501', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"DiD\n", | |
"[[(u'did', u'house')], [(u'500', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"DiDi\n", | |
"[[(u'didi', u'house')], [(u'501', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"DiDi \n", | |
"[[(u'didi', u'house')]]\n", | |
"\n", | |
"\n", | |
"DiDi D\n", | |
"[[(u'didi d', u'house')], [(u'501', u'house'), (u'500', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"DiDi Du\n", | |
"[[(u'didi du', u'house')], [(u'501', u'house_number'), (u'du', u'road')]]\n", | |
"\n", | |
"\n", | |
"DiDi Dum\n", | |
"[[(u'didi dum', u'house')], [(u'501', u'house_number'), (u'dum', u'road')]]\n", | |
"\n", | |
"\n", | |
"DiDi Dump\n", | |
"[[(u'didi dump', u'house')], [(u'501', u'house_number'), (u'dump', u'road')]]\n", | |
"\n", | |
"\n", | |
"DiDi Dumpl\n", | |
"[[(u'didi dumpl', u'house')], [(u'501', u'house_number'), (u'dumpl', u'road')]]\n", | |
"\n", | |
"\n", | |
"DiDi Dumpli\n", | |
"[[(u'didi dumpli', u'house')], [(u'501', u'house_number'), (u'dumpli', u'road')]]\n", | |
"\n", | |
"\n", | |
"DiDi Dumplin\n", | |
"[[(u'didi dumplin', u'house')], [(u'501', u'house_number'), (u'dumplin', u'road')]]\n", | |
"\n", | |
"\n", | |
"DiDi Dumpling\n", | |
"[[(u'didi dumpling', u'house')], [(u'501', u'house_number'), (u'dumpling', u'road')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: hackney city farm\n", | |
"h\n", | |
"[[(u'h', u'house')]]\n", | |
"\n", | |
"\n", | |
"ha\n", | |
"[[(u'ha', u'house')]]\n", | |
"\n", | |
"\n", | |
"hac\n", | |
"[[(u'hac', u'house')]]\n", | |
"\n", | |
"\n", | |
"hack\n", | |
"[[(u'hack', u'house')]]\n", | |
"\n", | |
"\n", | |
"hackn\n", | |
"[[(u'hackn', u'house')]]\n", | |
"\n", | |
"\n", | |
"hackne\n", | |
"[[(u'hackne', u'house')]]\n", | |
"\n", | |
"\n", | |
"hackney\n", | |
"[[(u'hackney', u'house')]]\n", | |
"\n", | |
"\n", | |
"hackney \n", | |
"[[(u'hackney', u'house')]]\n", | |
"\n", | |
"\n", | |
"hackney c\n", | |
"[[(u'hackney', u'road'), (u'centre', u'house')], [(u'hackney center', u'house')], [(u'hackney central', u'suburb')]]\n", | |
"\n", | |
"\n", | |
"hackney ci\n", | |
"[[(u'hackney circuit', u'road')]]\n", | |
"\n", | |
"\n", | |
"hackney cit\n", | |
"[[(u'hackney', u'road'), (u'cit', u'house')]]\n", | |
"\n", | |
"\n", | |
"hackney city\n", | |
"[[(u'hackney', u'city_district'), (u'city', u'house')]]\n", | |
"\n", | |
"\n", | |
"hackney city \n", | |
"[[(u'hackney', u'city_district'), (u'city', u'house')]]\n", | |
"\n", | |
"\n", | |
"hackney city f\n", | |
"[[(u'hackney', u'city_district'), (u'city flat', u'house')]]\n", | |
"\n", | |
"\n", | |
"hackney city fa\n", | |
"[[(u'hackney', u'city_district'), (u'city fa', u'house')]]\n", | |
"\n", | |
"\n", | |
"hackney city far\n", | |
"[[(u'hackney', u'city_district'), (u'city far', u'house')]]\n", | |
"\n", | |
"\n", | |
"hackney city farm\n", | |
"[[(u'hackney', u'city_district'), (u'city', u'road'), (u'farm', u'house')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: 1 Grolmanstrasse\n", | |
"1\n", | |
"[[(u'1', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"1 \n", | |
"[[(u'1', u'house_number')]]\n", | |
"\n", | |
"\n", | |
"1 G\n", | |
"[[(u'1', u'house_number'), (u'ground', u'road')]]\n", | |
"\n", | |
"\n", | |
"1 Gr\n", | |
"[[(u'1', u'house_number'), (u'grove', u'road')]]\n", | |
"\n", | |
"\n", | |
"1 Gro\n", | |
"[[(u'1', u'house_number'), (u'grove', u'road')]]\n", | |
"\n", | |
"\n", | |
"1 Grol\n", | |
"[[(u'1', u'house_number'), (u'grol', u'road')]]\n", | |
"\n", | |
"\n", | |
"1 Grolm\n", | |
"[[(u'1', u'house_number'), (u'grolm', u'road')]]\n", | |
"\n", | |
"\n", | |
"1 Grolma\n", | |
"[[(u'1', u'house_number'), (u'grolma', u'road')]]\n", | |
"\n", | |
"\n", | |
"1 Grolman\n", | |
"[[(u'1', u'house_number'), (u'grolman', u'road')]]\n", | |
"\n", | |
"\n", | |
"1 Grolmans\n", | |
"[[(u'1', u'house_number'), (u'grolmans', u'road')]]\n", | |
"\n", | |
"\n", | |
"1 Grolmanst\n", | |
"[[(u'1', u'house_number'), (u'grolmanst', u'road')]]\n", | |
"\n", | |
"\n", | |
"1 Grolmanstr\n", | |
"[[(u'1', u'house_number'), (u'grolmanstr', u'road')]]\n", | |
"\n", | |
"\n", | |
"1 Grolmanstra\n", | |
"[[(u'1', u'house_number'), (u'grolmanstra', u'road')]]\n", | |
"\n", | |
"\n", | |
"1 Grolmanstras\n", | |
"[[(u'1', u'house_number'), (u'grolmanstras', u'road')]]\n", | |
"\n", | |
"\n", | |
"1 Grolmanstrass\n", | |
"[[(u'1', u'house_number'), (u'grolmanstrass', u'road')]]\n", | |
"\n", | |
"\n", | |
"1 Grolmanstrasse\n", | |
"[[(u'1', u'house'), (u'grolmanstrasse', u'road')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: Beach Bablyon\n", | |
"B\n", | |
"[[(u'b', u'house')]]\n", | |
"\n", | |
"\n", | |
"Be\n", | |
"[[(u'be', u'country')]]\n", | |
"\n", | |
"\n", | |
"Bea\n", | |
"[[(u'bea', u'house')]]\n", | |
"\n", | |
"\n", | |
"Beac\n", | |
"[[(u'beac', u'house')]]\n", | |
"\n", | |
"\n", | |
"Beach\n", | |
"[[(u'beach', u'house')]]\n", | |
"\n", | |
"\n", | |
"Beach \n", | |
"[[(u'beach', u'house')]]\n", | |
"\n", | |
"\n", | |
"Beach B\n", | |
"[[(u'beach b', u'house')]]\n", | |
"\n", | |
"\n", | |
"Beach Ba\n", | |
"[[(u'beach ba', u'house')]]\n", | |
"\n", | |
"\n", | |
"Beach Bab\n", | |
"[[(u'beach bab', u'road')]]\n", | |
"\n", | |
"\n", | |
"Beach Babl\n", | |
"[[(u'beach babl', u'house')]]\n", | |
"\n", | |
"\n", | |
"Beach Bably\n", | |
"[[(u'beach bably', u'house')]]\n", | |
"\n", | |
"\n", | |
"Beach Bablyo\n", | |
"[[(u'beach bablyo', u'house')]]\n", | |
"\n", | |
"\n", | |
"Beach Bablyon\n", | |
"[[(u'beach bablyon', u'house')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: Waiotapu\n", | |
"W\n", | |
"[[(u'west', u'city_district')], [(u'w', u'house')]]\n", | |
"\n", | |
"\n", | |
"Wa\n", | |
"[[(u'wa', u'state')], [(u'washington', u'city')], [(u'western australia', u'state')]]\n", | |
"\n", | |
"\n", | |
"Wai\n", | |
"[[(u'wai', u'house')]]\n", | |
"\n", | |
"\n", | |
"Waio\n", | |
"[[(u'waio', u'house')]]\n", | |
"\n", | |
"\n", | |
"Waiot\n", | |
"[[(u'waiot', u'house')]]\n", | |
"\n", | |
"\n", | |
"Waiota\n", | |
"[[(u'waiota', u'house')]]\n", | |
"\n", | |
"\n", | |
"Waiotap\n", | |
"[[(u'waiotap', u'house')]]\n", | |
"\n", | |
"\n", | |
"Waiotapu\n", | |
"[[(u'waiotapu', u'house')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"====================================================================\n", | |
"\n", | |
"TEST SET: quattroshapes_popularity\n", | |
"TEST: chelsea\n", | |
"c\n", | |
"[[(u'centre', u'house')], [(u'center', u'house')], [(u'central', u'house')]]\n", | |
"\n", | |
"\n", | |
"ch\n", | |
"[[(u'county highway', u'road')], [(u'chase', u'house')]]\n", | |
"\n", | |
"\n", | |
"che\n", | |
"[[(u'che', u'country')]]\n", | |
"\n", | |
"\n", | |
"chel\n", | |
"[[(u'chel', u'house')]]\n", | |
"\n", | |
"\n", | |
"chels\n", | |
"[[(u'chels', u'house')]]\n", | |
"\n", | |
"\n", | |
"chelse\n", | |
"[[(u'chelse', u'house')]]\n", | |
"\n", | |
"\n", | |
"chelsea\n", | |
"[[(u'chelsea', u'city')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: chelsea, ny\n", | |
"c\n", | |
"[[(u'centre', u'house')], [(u'center', u'house')], [(u'central', u'house')]]\n", | |
"\n", | |
"\n", | |
"ch\n", | |
"[[(u'county highway', u'road')], [(u'chase', u'house')]]\n", | |
"\n", | |
"\n", | |
"che\n", | |
"[[(u'che', u'country')]]\n", | |
"\n", | |
"\n", | |
"chel\n", | |
"[[(u'chel', u'house')]]\n", | |
"\n", | |
"\n", | |
"chels\n", | |
"[[(u'chels', u'house')]]\n", | |
"\n", | |
"\n", | |
"chelse\n", | |
"[[(u'chelse', u'house')]]\n", | |
"\n", | |
"\n", | |
"chelsea\n", | |
"[[(u'chelsea', u'city')]]\n", | |
"\n", | |
"\n", | |
"chelsea,\n", | |
"[[(u'chelsea', u'city')]]\n", | |
"\n", | |
"\n", | |
"chelsea, \n", | |
"[[(u'chelsea', u'city')]]\n", | |
"\n", | |
"\n", | |
"chelsea, n\n", | |
"[[(u'chelsea', u'suburb'), (u'north', u'road')], [(u'chelsea', u'house'), (u'n', u'road')]]\n", | |
"\n", | |
"\n", | |
"chelsea, ny\n", | |
"[[(u'chelsea', u'suburb'), (u'new york', u'state')], [(u'chelsea', u'suburb'), (u'ny', u'state')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: williamsburg\n", | |
"w\n", | |
"[[(u'west', u'city_district')], [(u'w', u'house')]]\n", | |
"\n", | |
"\n", | |
"wi\n", | |
"[[(u'wisconsin', u'state')], [(u'wi', u'state')]]\n", | |
"\n", | |
"\n", | |
"wil\n", | |
"[[(u'wil', u'city')]]\n", | |
"\n", | |
"\n", | |
"will\n", | |
"[[(u'will', u'house')]]\n", | |
"\n", | |
"\n", | |
"willi\n", | |
"[[(u'willi', u'house')]]\n", | |
"\n", | |
"\n", | |
"willia\n", | |
"[[(u'willia', u'road')]]\n", | |
"\n", | |
"\n", | |
"william\n", | |
"[[(u'william', u'house')]]\n", | |
"\n", | |
"\n", | |
"williams\n", | |
"[[(u'williams', u'house')]]\n", | |
"\n", | |
"\n", | |
"williamsb\n", | |
"[[(u'williamsb', u'house')]]\n", | |
"\n", | |
"\n", | |
"williamsbu\n", | |
"[[(u'williamsbu', u'house')]]\n", | |
"\n", | |
"\n", | |
"williamsbur\n", | |
"[[(u'williamsbur', u'house')]]\n", | |
"\n", | |
"\n", | |
"williamsburg\n", | |
"[[(u'williamsburg', u'house')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: williamsburg, ny\n", | |
"w\n", | |
"[[(u'west', u'city_district')], [(u'w', u'house')]]\n", | |
"\n", | |
"\n", | |
"wi\n", | |
"[[(u'wisconsin', u'state')], [(u'wi', u'state')]]\n", | |
"\n", | |
"\n", | |
"wil\n", | |
"[[(u'wil', u'city')]]\n", | |
"\n", | |
"\n", | |
"will\n", | |
"[[(u'will', u'house')]]\n", | |
"\n", | |
"\n", | |
"willi\n", | |
"[[(u'willi', u'house')]]\n", | |
"\n", | |
"\n", | |
"willia\n", | |
"[[(u'willia', u'road')]]\n", | |
"\n", | |
"\n", | |
"william\n", | |
"[[(u'william', u'house')]]\n", | |
"\n", | |
"\n", | |
"williams\n", | |
"[[(u'williams', u'house')]]\n", | |
"\n", | |
"\n", | |
"williamsb\n", | |
"[[(u'williamsb', u'house')]]\n", | |
"\n", | |
"\n", | |
"williamsbu\n", | |
"[[(u'williamsbu', u'house')]]\n", | |
"\n", | |
"\n", | |
"williamsbur\n", | |
"[[(u'williamsbur', u'house')]]\n", | |
"\n", | |
"\n", | |
"williamsburg\n", | |
"[[(u'williamsburg', u'house')]]\n", | |
"\n", | |
"\n", | |
"williamsburg,\n", | |
"[[(u'williamsburg', u'house')]]\n", | |
"\n", | |
"\n", | |
"williamsburg, \n", | |
"[[(u'williamsburg', u'house')]]\n", | |
"\n", | |
"\n", | |
"williamsburg, n\n", | |
"[[(u'williamsburg', u'suburb'), (u'north', u'road')], [(u'williamsburg n', u'house')]]\n", | |
"\n", | |
"\n", | |
"williamsburg, ny\n", | |
"[[(u'williamsburg', u'suburb'), (u'new york', u'state')], [(u'williamsburg', u'suburb'), (u'ny', u'state')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: ridgewood\n", | |
"r\n", | |
"[[(u'river', u'house')]]\n", | |
"\n", | |
"\n", | |
"ri\n", | |
"[[(u'ri', u'state')], [(u'rhode island', u'state')], [(u'rise', u'road')]]\n", | |
"\n", | |
"\n", | |
"rid\n", | |
"[[(u'rid', u'house')]]\n", | |
"\n", | |
"\n", | |
"ridg\n", | |
"[[(u'ridg', u'house')]]\n", | |
"\n", | |
"\n", | |
"ridge\n", | |
"[[(u'ridge', u'road')]]\n", | |
"\n", | |
"\n", | |
"ridgew\n", | |
"[[(u'ridgew', u'house')]]\n", | |
"\n", | |
"\n", | |
"ridgewo\n", | |
"[[(u'ridgewo', u'house')]]\n", | |
"\n", | |
"\n", | |
"ridgewoo\n", | |
"[[(u'ridgewoo', u'house')]]\n", | |
"\n", | |
"\n", | |
"ridgewood\n", | |
"[[(u'ridgewood', u'house')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"TEST: ridgewood, ny\n", | |
"r\n", | |
"[[(u'river', u'house')]]\n", | |
"\n", | |
"\n", | |
"ri\n", | |
"[[(u'ri', u'state')], [(u'rhode island', u'state')], [(u'rise', u'road')]]\n", | |
"\n", | |
"\n", | |
"rid\n", | |
"[[(u'rid', u'house')]]\n", | |
"\n", | |
"\n", | |
"ridg\n", | |
"[[(u'ridg', u'house')]]\n", | |
"\n", | |
"\n", | |
"ridge\n", | |
"[[(u'ridge', u'road')]]\n", | |
"\n", | |
"\n", | |
"ridgew\n", | |
"[[(u'ridgew', u'house')]]\n", | |
"\n", | |
"\n", | |
"ridgewo\n", | |
"[[(u'ridgewo', u'house')]]\n", | |
"\n", | |
"\n", | |
"ridgewoo\n", | |
"[[(u'ridgewoo', u'house')]]\n", | |
"\n", | |
"\n", | |
"ridgewood\n", | |
"[[(u'ridgewood', u'house')]]\n", | |
"\n", | |
"\n", | |
"ridgewood,\n", | |
"[[(u'ridgewood', u'house')]]\n", | |
"\n", | |
"\n", | |
"ridgewood, \n", | |
"[[(u'ridgewood', u'house')]]\n", | |
"\n", | |
"\n", | |
"ridgewood, n\n", | |
"[[(u'ridgewood', u'suburb'), (u'north', u'road')], [(u'ridgewood', u'house'), (u'n', u'road')]]\n", | |
"\n", | |
"\n", | |
"ridgewood, ny\n", | |
"[[(u'ridgewood', u'suburb'), (u'new york', u'state')], [(u'ridgewood', u'suburb'), (u'ny', u'state')]]\n", | |
"\n", | |
"\n", | |
"--------------------------------------------------------------\n", | |
"\n", | |
"====================================================================\n", | |
"\n" | |
] | |
} | |
], | |
"source": [ | |
"for files in glob.glob(\"acceptance-tests/test_cases/*.json\"):\n", | |
" # SKIP PLACE AND REVERSE GEO\n", | |
" filename = files[28:-5]\n", | |
" if filename != \"place\" and filename != \"admin_lookup\" and filename != \"reverse_coordinate_wrapping\":\n", | |
" t = json.load(open(files))\n", | |
" print(\"TEST SET: %s\"%(files[28:-5]))\n", | |
" for test in t['tests']:\n", | |
" test_text = test['in']['text']\n", | |
" print(\"TEST: %s\"%test_text)\n", | |
" print_autocomplete(test_text)\n", | |
" print('--------------------------------------------------------------\\n')\n", | |
" print('====================================================================\\n')" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [], | |
"source": [] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [], | |
"source": [] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [], | |
"source": [] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": { | |
"collapsed": true | |
}, | |
"outputs": [], | |
"source": [] | |
} | |
], | |
"metadata": { | |
"kernelspec": { | |
"display_name": "Python 2", | |
"language": "python", | |
"name": "python2" | |
}, | |
"language_info": { | |
"codemirror_mode": { | |
"name": "ipython", | |
"version": 2 | |
}, | |
"file_extension": ".py", | |
"mimetype": "text/x-python", | |
"name": "python", | |
"nbconvert_exporter": "python", | |
"pygments_lexer": "ipython2", | |
"version": "2.7.9" | |
} | |
}, | |
"nbformat": 4, | |
"nbformat_minor": 0 | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment