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

# name_corr.lst - Correction list for name component

#

# Source: - NSW Health Department 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 "name_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

' ' := '.', '?', '~', '_', ':', ';', '^', '=', ' n a ', '*',

' n/a ', ' n.a.', '\', ' also ', ' name ', ' only ',

' abbrev ', ' initials ', ' unk ', ' unkn ',

' missing ', ' unknown '

# Correct words and symbols

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

' baby ' := ' babe '

' baby of ' := ' babyof ', ' babeof ', ' b/o ', ' b.o.'

' daughter of ' := ' daughterof ', ' d/o ', ' d.o.'

' son of ' := ' sonof ', ' s/o ', ' s.o.'

' known as ' := ' knownas ', ' a.k.a. ', ' aka '

' - ' := '-', '/'

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

# Remove ' from o'brian etc

' o' := " o'"

' a' := " a'"

' l' := " l'"

' i' := " i'"

'-o' := "-o'"

'-a' := "-a'"

'-l' := "-l'"

'-i' := "-i'"

# Correct roman numbers

# ' i ' := ' first '

' ii ' := ' second '

' iii ' := ' third '