view lispref/permute-index @ 41882:f3bc5e440020

Resurrect the Hebrew category settings for all Hebrew characters removed by the last change. Add code for setting the Hebrew category of the Unicode Hebrew characters. Set syntax entries for Hebrew punctuation characters.

#!/bin/sh
# Generate a permuted index of all names.
# The result is a file called index.fns.

# Copyright (C) 2001 Free Software Foundation, Inc.
#
# This file is part of GNU Emacs.
#
# GNU Emacs is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation; either version 2, or (at your option)
# any later version.
#
# GNU Emacs is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with GNU Emacs; see the file COPYING.  If not, write to the
# Free Software Foundation, Inc., 59 Temple Place - Suite 330,
# Boston, MA 02111-1307, USA.

# You will need to modify this for your needs.


set TEXINDEX=texindex  # path to texindex command
#set EMACS=gnuemacs     # your emacs command
#set TEX=tex             # your tex command

set MANUAL=elisp  # the base name of the manual

# goto 3

1:
echo "Extract raw index from texinfo fn index."
# Let texindex combine duplicate entries, later.
# But it wants to protect non-alphanumerics thus confusing ptx.
# Also change `\ ' to just a ` ', since texindex will fail. This is produced 
# by `@findex two words' in an example environment (no doubt among others).
# delete wrapper parens
# change dots {} to dots{}
# change {-} to char form, so ptx wont ignore it.
# delete leading \entry {
# change '\ ' to ' '
# change lines with = < > since they mess up field extraction.
# separate into fields delimited by "
rm -f permuted.raw
cat ${MANUAL}.fn | \
	sed \
	-e 's/(\([^)]*\))/\1/' \
	-e 's/\\dots {}/(\\dots{})/' \
	-e "s/{-}/{{\\tt\\char'055}}/" \
	-e 's,^[^ ]* {,,' \
	-e 's, },},' \
	-e 's,\\ , ,g' \
	-e 's/{\\tt\\char61}/=/' \
	-e 's/{\\tt\\gtr}/>/' \
	-e 's/{\\tt\\less}/</' \
	-e 's/}{/"/g' \
	| awk -F\" '{print $2, $1}' > permuted.raw

2:
# Build break file for ptx.
cat <<EOF > permuted.break
-
:
EOF
# Build the ignore file for ptx.
# We would like to ignore "and", "or", and "for",
# but ptx ignores ignore words even if they stand alone.
cat <<EOF > permuted.ignore
the
in
to
as
a
an
of
on
them
how
from
by
EOF

echo "Make troff permuted index."
rm -f permuted.t
ptx -i permuted.ignore -b permuted.break -f -r -w 144 \
	 < permuted.raw > permuted.t

3:
echo "Extract the desired fields."
rm -f permuted.fields
awk -F\" '{printf "%s\"%s\"%s\n", $4,$6,$9}' permuted.t > permuted.fields

4:
echo "Format for texindex."
# delete lines that start with "and ", "for "
sed 	< permuted.fields \
	-e 's/=/{\\tt\\char61}/' \
	-e 's/>/{\\tt\\gtr}/' \
	-e 's/</{\\tt\\less}/' \
	-e '/"and /d' \
	-e '/"for /d' \
  | awk -F\" 'NF>0 {if ($1=="") {\
	  print "\entry {" $2 "}{" 0+$3 "}{" $2 "}" }\
	else {\
	  print "\entry {" $2 ", " $1 "}{" 0+$3 "}{" $2 ", " $1 "}"} }'\
	      > permuted.fn

5:
echo "Sort with texindex."
${TEXINDEX} permuted.fn
#mv permuted.fns ${MANUAL}.fns

# The resulting permuted.fns will be read when we run TeX 
# on the manual the second time.  Or you can use permuted.texinfo here.
#${TEX} permuted.texinfo

6:
echo "Clean up."
rm -f permuted.fields permuted.t permuted.raw
rm -f permuted.break permuted.ignore permuted.fn