sh /tmp/text.sh
2 n.txt
C.UTF-8:        2
name                                 type              encoding         emb sub 
uni object ID
------------------------------------ ----------------- ---------------- --- --- 
--- ---------
XEVJPT+WenQuanYiZenHei               CID TrueType      Identity-H       yes yes 
yes      6  0
MYDSFU+LiberationSerif               TrueType          WinAnsi          yes yes 
yes      7  0
zh_CN.UTF-8:    5
name                                 type              encoding         emb sub 
uni object ID
------------------------------------ ----------------- ---------------- --- --- 
--- ---------
HFTSNP+WenQuanYiZenHeiMono           TrueType          WinAnsi          yes yes 
yes      6  0
MYDSFU+LiberationSerif               TrueType          WinAnsi          yes yes 
yes      7  0
zh_TW.UTF-8:    5
name                                 type              encoding         emb sub 
uni object ID
------------------------------------ ----------------- ---------------- --- --- 
--- ---------
HFTSNP+WenQuanYiZenHeiMono           TrueType          WinAnsi          yes yes 
yes      6  0
MYDSFU+LiberationSerif               TrueType          WinAnsi          yes yes 
yes      7  0>>>>> "JS" == Jonas Smedegaard <jo...@jones.dk> writes:

from

set -e
cd /tmp
t=n.txt
LC_ALL=C.UTF-8 echo 郵編123 > $t
echo >> $t
wc -l $t
for l in C.UTF-8 zh_CN.UTF-8 zh_TW.UTF-8
do
    printf $l:\\t
    LC_ALL=$l abiword --to=pdf $t
    LC_ALL=C.UTF-8 pdftotext -nopgbrk n.pdf -|wc -l
    pdffonts n.pdf
done

Attachment: n.pdf
Description: Adobe PDF document

Reply via email to