usr/src/cmd/localedef/data/ctype.sh

   1 #! /usr/bin/sh
   2 #
   3 #
   4 # This file and its contents are supplied under the terms of the
   5 # Common Development and Distribution License ("CDDL"), version 1.0.
   6 # You may only use this file in accordance with the terms of version
   7 # 1.0 of the CDDL.
   8 #
   9 # A full copy of the text of the CDDL should have accompanied this
  10 # source.  A copy of the CDDL is also available via the Internet at
  11 # http://www.illumos.org/license/CDDL.
  12 #
  13
  14 #
  15 # Copyright 2017 Nexenta Systems, Inc.
  16 #
  17
  18 # Combine LC_CTYPE classes from all .UTF-8.src files to be compiled by localedef
  19 # into one LC_CTYPE/LCL_DATA used by all locales, so we have the same case
  20 # mapping tables, character classes, etc. for all of them. This is not general
  21 # purpose parser but is good enough for the stock files supplied with CLDR.
  22
  23 printf "\nLC_CTYPE\n"
  24
  25 for i in upper lower alpha space cntrl graph print punct digit xdigit blank \
  26         toupper tolower; do
  27         # sed can't match both range patterns on the same line so we just make
  28         # it look like valid multiline class by duplicating the definition
  29         sed "/^$i.*>$/ {
  30                 s,$,;/,
  31                 h
  32                 s,^$i\(.*>\);/$,\1,
  33                 H
  34                 x
  35         }" $@ |\
  36         sed -n "/^$i/,/\([>)]\)$/ {
  37                 s,^$i,,
  38                 "'s,\([>)]\)$,\1;/,'"
  39                 /^$/d
  40                 p
  41         }" |\
  42         sort -u |\
  43         sed "1 s,^,$i,;$ s,\([>)]\);/,\1,"
  44 done
  45
  46 # Add the manually assembled definitions from FreeBSD
  47 # (originally tools/tools/locale/etc/manual-input.UTF-8).
  48 cat data/manual-input.UTF-8
  49
  50 printf "\nEND LC_CTYPE\n"