# =============================================================================

# address_corr.lst - Correction list for locality component

#

# Source: - NSW Health Department AutoStan pattern and classification files

#

# Last update: 12/09/2002, Peter Christen

#

# Entries in the file are of the form:

#

# replacement := values

#

# where 'values' can be one word or character or a comma separated list of

# words or characters. Each value will be replaced by the 'replacement'

# string on the left side.

# Both the replacement string and each of the value strings must be enclosed

# in either single or double quotes.

#

# =============================================================================

# Freely extensible biomedical record linkage (Febrl) Version 0.2.2

# See http://datamining.anu.edu.au/projects/linkage.html

#

# AUSTRALIAN NATIONAL UNIVERSITY OPEN SOURCE LICENSE (ANUOS LICENSE)

# VERSION 1.1

#

# The contents of this file are subject to the ANUOS License Version 1.1 (the

# "License"); you may not use this file except in compliance with the License.

# Software distributed under the License is distributed on an "AS IS" basis,

# WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License for

# the specific language governing rights and limitations under the License.

# The Original Software is "address_corr.lst".

# The Initial Developers of the Original Software are Dr Peter Christen

# (Department of Computer Science, Australian National University) and Dr Tim

# Churches (Centre for Epidemiology and Research, New South Wales Department

# of Health). Copyright (C) 2002, 2003 the Australian National University and

# others. All Rights Reserved.

# Contributors:

#

# =============================================================================

# Remove characters and words from input

' ' := '.', '?', '~', '-', '_', ':', ';', '^', '=', ' na ',

' n/a ', ' n.a.', ' c/o ', ' c/- ', 'also ', ' name ',

' only ', ' abbrev ', ' locked ', ' on ', ' of ',

' unk ', ' unkn ', ' missing ', '*',

' unknown ', ' fc ', ' bc ', ' c / ', ' xx '

# Correct words and symbols

' roman catholic ' := ' r/c ', ' r / c ', ' rc '

' church of england ' := ' c/e ', ' c / e ', ' c of e '

' no fixed address ' := ' nfa ', 'n/f/a ', ' n.f.a.', ' n f a '

' nursing home ' := ' n / home '

' other territory ' := ' o/t ', ' o.t.'

' and ' := '+', '&'

' / ' := '\', '/'

' | ' := '<', '>', '(', ')', '[', ']', '{', '}', '"', "'"

# Remove ' from o'brian etc

' a' := " a'"

' o' := " o'"

' d' := " d'"

' l' := " l'"

' i' := " i'"

'-a' := "-a'"

'-d' := "-d'"

'-o' := "-o'"

'-l' := "-l'"

'-i' := "-i'"

's ' := "'s "

# Correct roman numbers

' 1 ' := ' i '

' 2 ' := ' ii '

' 3 ' := ' iii '

' 4 ' := ' iv '

' 5 ' := ' v '

' 6 ' := ' vi '

' 7 ' := ' vii '

' 8 ' := ' viii '

' 9 ' := ' ix '

' 10 ' := ' x '

' 11 ' := ' xi '

' 12 ' := ' xii '

' 13 ' := ' xiii '

' 14 ' := ' xiv '

' 15 ' := ' xv '

' 16 ' := ' xvi '

' 17 ' := ' xvii '

' 18 ' := ' xviii '

' 19 ' := ' xix '

' 20 ' := ' xx '

# Correct ordinal numbers

' first ' := ' 1st '

' second ' := ' 2nd '

' third ' := ' 3rd '

' fourth ' := ' 4th '

' fifth ' := ' 5th '

' sixth ' := ' 6th '

' seventh ' := ' 7th '

' eighth ' := ' 8th '

' ninth ' := ' 9th '

' tenth ' := ' 10th '

' eleventh ' := ' 11th '

' twelfth ' := ' 12th '

' thirteenth ' := ' 13th '

' fourteenth ' := ' 14th '

' fifteenth ' := ' 15th '

' sixteenth ' := ' 16th '

' seventeenth ' := ' 17th '

' eighteenth ' := ' 18th '

' nineteenth ' := ' 19th '

' twentieth ' := ' 20th '

' thirtieth ' := ' 30th '

' fortieth ' := ' 40th '

' fiftieth ' := ' 50th '

' sixtieth ' := ' 60th '

' seventieth ' := ' 70th '

' eightieth ' := ' 80th '

' ninetieth ' := ' 90th '

' hundredth ' := ' 100th '

# Australian state and territory words

' australia ' := ' aus ', ' aust ', ' austr ', ' autr '

' capital ' := ' cap ', ' capit ', ' capitol ', ' capt '

' land ' := ' lnd '

' territory ' := ' teritory '

' wales ' := ' wals ', ' wal '

# Geographical locations

' alpine ' := ' alpint ', ' apline '

' cove ' := ' coe '

' county ' := ' cnty ', ' coun '

' creek ' := ' ck ', ' crk '

' dale ' := ' dell '

' dam ' := ' dame '

' dock ' := ' dck ', ' dk '

' fairway ' := ' fawy '

' falls ' := ' fals ', ' flls ', ' fls '

' field ' := ' fiedls ', ' field ', ' fields ', ' fiels ',

' filds ', ' filed ', ' fileds ', ' flds '

' forest ' := ' fores ', ' forrest ', ' frest '

' glade ' := ' gld '

' grange ' := ' gra '

' green ' := ' grn ', ' greeen '

' gully ' := ' gly ', ' glly '

' head ' := ' hd '

' heads ' := ' hds '

' hill ' := ' gill ', ' hil ', ' hilll ', ' hiull '

' hills ' := ' hillss ', ' hils ', ' hiolls ', ' hlls ', ' holls '

' inlet ' := ' inley ', ' innlet '

' island ' := ' ils ', ' is ', ' isl '

' lake ' := ' lk ', ' lke '

' lakes ' := ' lks ', ' lkes '

' lookout ' := ' lkt '

' meander ' := ' mndr '

' meadow ' := ' mdw ', ' meado ', ' medow '

' meadows ' := ' mdws ', ' medows '

' midway ' := ' midwy '

' mount ' := ' mnt ', ' mout ', ' mt '

' oaks ' := ' oak ', ' oakes '

' outlook ' := ' otlk '

' parklands ' := ' parkland ', ' pkld ', ' pklds '

' pass ' := ' ps '

' plains ' := ' plain ', ' planes ', ' plians ', ' plns '

' plateau ' := ' plat ', ' platau ', ' platea ', ' platteau ',

' platue ', ' plt ', ' pltu '

' pier ' := ' pir '

' polar ' := ' pola '

' port ' := ' prt '

' range ' := ' rnge '

' ridge ' := ' ridg ', ' rdge '

' river ' := ' riv ', ' rivr ', ' rvr '

' riviera ' := ' rvra '

' rocky ' := ' rockey '

' sands ' := ' sandes '

' slope ' := ' slpe '

' sound ' := ' snd '

' stony ' := ' stoney '

' vale ' := ' vle '

' valley ' := ' valey ', ' vlley ', ' vally ', ' vlly ', ' vly ',

' valleys ', ' vlys '

' wells ' := ' wls ', ' well '

# Various words

' access ' := ' acc ', ' accs '

' amble ' := ' ambl '

' anchorage ' := ' ancg '

' approach ' := ' app '

' artery ' := ' art '

' bayou ' := ' bayoo '

' brace ' := ' brce '

' branch ' := ' br ', ' brnch '

' break ' := ' braek ', ' brk '

' deviation ' := ' devn '

' elbow ' := ' elb '

' foreshore ' := ' fhsr '

' formation ' := ' form '

' front ' := ' frnt '

' frontage ' := ' frtg '

' ground ' := ' grnd '

' key ' := ' ky '

' centennial ' := ' centenial '

' double ' := ' doule '

' hall ' := ' ahll ', ' haqll '

' keys ' := ' keyes '

' kings ' := ' king ', ' kingl ', ' kingsl ', ' kinks ', ' kins '

' nest ' := ' neest '

' neutral ' := ' neutrl '

' pleasant ' := ' plaesant ', ' pleasent ', ' pleasnt ', ' plesant '

' quadrangle ' := ' qdgl '

' quadrant ' := ' qdrt '

' ramble ' := ' rmbl '

' reach ' := ' rch '

' ronde ' := ' rnde '

' rosebowl ' := ' rsbl '

' round ' := ' rnd '

' siding ' := ' sdng '

' stairs ' := ' strs '

' steps ' := ' stps '

' triangle ' := ' tri '

' view ' := ' veiw ', ' vw ', ' views ', ' vws '

' vista ' := ' vis ', ' vist ', ' vst ', ' vsta '