[10333] | 1 | : Use /bin/sh |
---|
| 2 | # |
---|
| 3 | # $Id: tryaffix.X,v 1.1.1.1 1997-09-03 21:08:09 ghudson Exp $ |
---|
| 4 | # |
---|
| 5 | # Copyright 1987, 1988, 1989, 1992, 1993, Geoff Kuenning, Granada Hills, CA |
---|
| 6 | # All rights reserved. |
---|
| 7 | # |
---|
| 8 | # Redistribution and use in source and binary forms, with or without |
---|
| 9 | # modification, are permitted provided that the following conditions |
---|
| 10 | # are met: |
---|
| 11 | # |
---|
| 12 | # 1. Redistributions of source code must retain the above copyright |
---|
| 13 | # notice, this list of conditions and the following disclaimer. |
---|
| 14 | # 2. Redistributions in binary form must reproduce the above copyright |
---|
| 15 | # notice, this list of conditions and the following disclaimer in the |
---|
| 16 | # documentation and/or other materials provided with the distribution. |
---|
| 17 | # 3. All modifications to the source code must be clearly marked as |
---|
| 18 | # such. Binary redistributions based on modified source code |
---|
| 19 | # must be clearly marked as modified versions in the documentation |
---|
| 20 | # and/or other materials provided with the distribution. |
---|
| 21 | # 4. All advertising materials mentioning features or use of this software |
---|
| 22 | # must display the following acknowledgment: |
---|
| 23 | # This product includes software developed by Geoff Kuenning and |
---|
| 24 | # other unpaid contributors. |
---|
| 25 | # 5. The name of Geoff Kuenning may not be used to endorse or promote |
---|
| 26 | # products derived from this software without specific prior |
---|
| 27 | # written permission. |
---|
| 28 | # |
---|
| 29 | # THIS SOFTWARE IS PROVIDED BY GEOFF KUENNING AND CONTRIBUTORS ``AS IS'' AND |
---|
| 30 | # ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE |
---|
| 31 | # IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE |
---|
| 32 | # ARE DISCLAIMED. IN NO EVENT SHALL GEOFF KUENNING OR CONTRIBUTORS BE LIABLE |
---|
| 33 | # FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL |
---|
| 34 | # DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS |
---|
| 35 | # OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) |
---|
| 36 | # HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT |
---|
| 37 | # LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY |
---|
| 38 | # OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF |
---|
| 39 | # SUCH DAMAGE. |
---|
| 40 | # |
---|
| 41 | # Try out affixes to see if they produce valid roots |
---|
| 42 | # |
---|
| 43 | # Usage: |
---|
| 44 | # |
---|
| 45 | # tryaffix [-p | -s] [-c] dict-file affix[+addition] ... |
---|
| 46 | # |
---|
| 47 | # The -p and -s flags specify whether prefixes or suffixes |
---|
| 48 | # are being tried; if neither is specified, suffixes are assumed. |
---|
| 49 | # |
---|
| 50 | # If the -c flag is given, statistics on the various affixes are given: |
---|
| 51 | # a count of words it potentially applies to, and an estimate of the |
---|
| 52 | # number of dictionary bytes the flag would save. The estimate will |
---|
| 53 | # be high if the flag generates words that are currently generated |
---|
| 54 | # by other flags. |
---|
| 55 | # |
---|
| 56 | # The dictionary file, dict-file, must already be expanded and sorted, |
---|
| 57 | # and things will work best if uppercase has been folded to lower with |
---|
| 58 | # 'tr'. |
---|
| 59 | # |
---|
| 60 | # The "affixes" are things to be stripped from the dictionary |
---|
| 61 | # file to produce trial roots: for English, "con" and "ing" |
---|
| 62 | # are examples. The "additions" are letters that would have |
---|
| 63 | # been stripped off the root before adding the affix. For |
---|
| 64 | # example, the affix "ing" strips "e" for words ending in "e" |
---|
| 65 | # (as in "like --> liking") so we might run: |
---|
| 66 | # |
---|
| 67 | # tryaffix ing ing+e |
---|
| 68 | # |
---|
| 69 | # to cover both cases. |
---|
| 70 | # |
---|
| 71 | # $Log: not supported by cvs2svn $ |
---|
| 72 | # Revision 1.6 1994/01/25 07:12:18 geoff |
---|
| 73 | # Get rid of all old RCS log lines in preparation for the 3.1 release. |
---|
| 74 | # |
---|
| 75 | # |
---|
| 76 | SORTTMP="-T ${TMPDIR-/usr/tmp}" # !!SORTTMP!! |
---|
| 77 | USAGE='tryaffix [-p | -s] [-c] dict-file affix[+addition] ...' |
---|
| 78 | counts=no |
---|
| 79 | pre= |
---|
| 80 | suf='$' |
---|
| 81 | while : |
---|
| 82 | do |
---|
| 83 | case "$1" in |
---|
| 84 | -p) |
---|
| 85 | pre='^' |
---|
| 86 | suf= |
---|
| 87 | ;; |
---|
| 88 | -s) |
---|
| 89 | pre= |
---|
| 90 | suf='$' |
---|
| 91 | ;; |
---|
| 92 | -c) |
---|
| 93 | counts=yes |
---|
| 94 | ;; |
---|
| 95 | -*) |
---|
| 96 | echo "$USAGE" 1>&2 |
---|
| 97 | exit 1 |
---|
| 98 | ;; |
---|
| 99 | *) |
---|
| 100 | break |
---|
| 101 | ;; |
---|
| 102 | esac |
---|
| 103 | shift |
---|
| 104 | done |
---|
| 105 | dict="$1" |
---|
| 106 | shift |
---|
| 107 | if [ ! -r "$dict" ] |
---|
| 108 | then |
---|
| 109 | echo "Can't read $dict" 1>&2 |
---|
| 110 | echo "$USAGE" 1>&2 |
---|
| 111 | exit 1 |
---|
| 112 | elif [ $# -eq 0 ] |
---|
| 113 | then |
---|
| 114 | echo "$USAGE" 1>&2 |
---|
| 115 | exit 1 |
---|
| 116 | fi |
---|
| 117 | while [ $# -ne 0 ] |
---|
| 118 | do |
---|
| 119 | case "$1" in |
---|
| 120 | *+*) |
---|
| 121 | affix=`expr "$1" : '\(.*\)+'` |
---|
| 122 | addition=`expr "$1" : '.*+\(.*\)'` |
---|
| 123 | sedscript="s/$pre$affix$suf/$addition/p" |
---|
| 124 | ;; |
---|
| 125 | *) |
---|
| 126 | sedscript="s/$pre$1$suf//p" |
---|
| 127 | ;; |
---|
| 128 | esac |
---|
| 129 | if [ "$counts" = no ] |
---|
| 130 | then |
---|
| 131 | echo ===== "$1" ===== |
---|
| 132 | sed -n "$sedscript" "$dict" | comm -12 - "$dict" |
---|
| 133 | else |
---|
| 134 | echo "$1" `sed -n "$sedscript" "$dict" | comm -12 - "$dict" | wc -lc` |
---|
| 135 | fi |
---|
| 136 | shift |
---|
| 137 | done |
---|