newlib/libc/string/mkwide

   1 #! /bin/sh
   2
   3 # generate list of wide characters, with convex closure
   4
   5 skipcheck=false
   6
   7 if [ ! -r EastAsianWidth.txt ]
   8 then    ln -s /usr/share/unicode/ucd/EastAsianWidth.txt . || exit 1
   9 fi
  10 if [ ! -r UnicodeData.txt ]
  11 then    ln -s /usr/share/unicode/ucd/UnicodeData.txt . || exit 1
  12 fi
  13 if [ ! -r Blocks.txt ]
  14 then    ln -s /usr/share/unicode/ucd/Blocks.txt . || exit 1
  15 fi
  16
  17 sed -e "s,^\([^;]*\);[NAH],\1," -e t -e d EastAsianWidth.txt > wide.na
  18 sed -e "s,^\([^;]*\);[WF],\1," -e t -e d EastAsianWidth.txt > wide.fw
  19
  20 PATH="$PATH:." # for uniset
  21
  22 nrfw=`uniset +wide.fw nr | sed -e 's,.*:,,'`
  23 echo FW $nrfw
  24 nrna=`uniset +wide.na nr | sed -e 's,.*:,,'`
  25 echo NAH $nrna
  26
  27 extrablocks="2E80-303E"
  28
  29 # check all blocks
  30 includes () {
  31         nr=`uniset +wide.$2 -$1 nr | sed -e 's,.*:,,'`
  32         test $nr != $3
  33 }
  34 echo "adding compact closure of wide ranges, this may take ~10min"
  35 for b in $extrablocks `sed -e 's,^\([0-9A-F]*\)\.\.\([0-9A-F]*\).*,\1-\2,' -e t -e d Blocks.txt`
  36 do      range=$b
  37         echo checking $range $* >&2
  38         if includes $range fw $nrfw && ! includes $range na $nrna
  39         then    echo $range
  40         fi
  41 done > wide.blocks
  42
  43 (
  44 sed -e "s,^,//," -e 1q EastAsianWidth.txt
  45 sed -e "s,^,//," -e 1q Blocks.txt
  46 uniset `sed -e 's,^,+,' wide.blocks` +wide.fw c
  47 ) > wide.t
  48
  49 rm -f wide.na wide.fw wide.blocks