Path: utzoo!utgpu!news-server.csri.toronto.edu!cs.utexas.edu!swrinde!zaphod.mps.ohio-state.edu!sdd.hp.com!elroy.jpl.nasa.gov!jpl-devvax!lwall
From: lwall@jpl-devvax.JPL.NASA.GOV (Larry Wall)
Newsgroups: comp.emacs
Subject: Re: ALL CAPS-->Mixed case converter?
Message-ID: <9467@jpl-devvax.JPL.NASA.GOV>
Date: 11 Sep 90 19:48:14 GMT
References: <3245@nems.dt.navy.mil> <MDB.90Sep1111521@kosciusko.ESD.3Com.COM> <1990Sep11.185353.26919@tc.fluke.COM>
Reply-To: lwall@jpl-devvax.JPL.NASA.GOV (Larry Wall)
Organization: Jet Propulsion Laboratory, Pasadena, CA
Lines: 207

Here's what Peter Yee uses to translate the NASA articles he posts.
No doubt he has a more up-to-date exception list by now.

Larry Wall
lwall@jpl-devvax.jpl.nasa.gov

#!/bin/sh
: make a subdirectory, cd to it, and run this through sh.
echo 'If this kit is complete, "End of kit" will echo at the end'
echo Extracting unuc
sed >unuc <<'!STUFFY!FUNK!' -e 's/X//'
X#!/usr/bin/perl
X
Xprint STDERR "Loading proper nouns...\n";
Xopen(DICT,"/usr/dict/words") || die "Can't find /usr/dict/words: $!\n";
Xwhile (<DICT>) {
X    if (/^[A-Z]/) {
X	chop;
X	($lower = $_) =~ y/A-Z/a-z/;
X	$proper{$lower} = $_;
X    }
X}
Xclose DICT;
Xprint STDERR "Loading exceptions...\n";
X
Xopen(PATS,"unuc.pats") || die "Can't find unuc.pats: $!\n";
X
X$prog = <<'EOT';
Xwhile (<>) {
X    next if /[a-z]/;
X    y/A-Z/a-z/;
X    s/(\w+)/$proper{$1} ? $proper{$1} : $1/eg;
X    s/^(\s*)([a-z])/$1 . (($tmp = $2) =~ y:a-z:A-Z:,$tmp)/e;
X    s/([-.?!]["']?(\n\s*|  \s*)["']?)([a-z])/$1 . (($tmp = $3) =~ y:a-z:A-Z:,$tmp)/eg;
X    s/\b([b-df-hj-np-tv-xz]+)\b/(($tmp = $1) =~ y:a-z:A-Z:,$tmp)/eg;
X    s/([a-z])'([SDT])\b/$1 . "'" . (($tmp = $2) =~ y:A-Z:a-z:,$tmp)/eg;
XEOT
Xwhile (<PATS>) {
X    chop;
X    next if /^$/;
X    next if /^#/;
X    if (! /;$/) {
X	$foo = $_;
X	$foo =~ y/A-Z/a-z/;
X	print STDERR "Dup $_\n" if $proper{$foo};
X	$foo =~ s/([^\w ])/\\$1/g;
X	$foo =~ s/ /(\\s+)/g;
X	$foo = "\\b" . $foo if $foo =~ /^\w/;
X	$foo .= "\\b" if $foo =~ /\w$/;
X	$i = 0;
X	($bar = $_) =~ s/ /'$' . ++$i/eg;
X	$_ = "s/$foo/$bar/gi;";
X    }
X    $prog .= '    ' . $_ . "\n";
X}
Xclose PATS;
X$prog .= "}\ncontinue {\n    print;\n}\n";
X
X$/ = '';
X#print $prog;
Xeval $prog; die $@ if $@;
!STUFFY!FUNK!
echo Extracting unuc.pats
sed >unuc.pats <<'!STUFFY!FUNK!' -e 's/X//'
XA.M.
XAir Force
XAir Force Base
XAir Force Station
XAmerican
XApr.
XAriane
XAug.
XAugust
XBureau of Labor Statistics
XCIT
XCaltech
XCape Canaveral
XChallenger
XChina
XCorporation
XCrippen
XDaily News in Brief
XDaniel Quayle
XDec.
XDiscovery
XEdwards
XEndeavour
XFeb.
XFord Aerospace
XFri.
XGeneral Dynamics
XGeorge Bush
XHeadline News
XHOTOL
XI
XII
XIII
XIV
XIX
XInstitute of Technology
XJPL
XJan.
XJul.
XJun.
XKennedy Space Center
XLDEF
XLong Duration Exposure Facility
XLong March
XMar.
XMarch
XMartin
XMartin Marietta
XMercury
XMon.
Xin May
Xs/\bmay (\d)/May $1/g;
Xs/\boffice of (\w)/'Office of ' . (($tmp = $1) =~ y:a-z:A-Z:,$tmp)/eg;
XNational Science Foundation
XNASA Select
XNew Mexico
XNov.
XOMB
XOct.
XOffice of Management and Budget
XPresident
XPresident Bush
XRichard Truly
XRocketdyne
XRussian
XRussians
XSat.
XSep.
XSoviet
XSoviet Union
XSoviets
XSpace Shuttle
XSun.
XThu.
XTue.
XU.S.
XUnion of Soviet Socialist Republics
XUnited States
XVI
XVII
XVIII
XVice President
XVice President Quayle
XWed.
XWhite Sands
XKaman Aerospace
XAerospace Daily
XAviation Week
XSpace Technology
XWashington Post
XLos Angeles Times
XNew York Times
XAerospace Industries Association
Xpresident of
XJohnson Space Center
XSpace Services
XInc.
XCo.
XHughes Aircraft
XCompany
XOrbital Sciences
XSwedish Space
XArnauld
XNicogosian
XMagellan
XGalileo
XMir
XJet Propulsion Laboratory
XUniversity
XDepartment of Defense
XOrbital Science
XOMS
XUnited Press International
XUnited Press
XUPI
XAssociated Press
XAP
XCable News Network
XCape York
XZenit
XSYNCOM
XEastern
XWestern
XTest Range
XJcsat
XJapanese Satellite Communications
XDefence Ministry
XDefense Ministry
XSkynet
XFixed Service Structure
XLaunch Processing System
XAsiasat
XLaunch Control Center
XEarth
XCNES
XGlavkosmos
XPacific
XAtlantic
!STUFFY!FUNK!
echo ""
echo "End of kit"
: I do not append .signature, but someone might mail this.
exit