First try to index PDF with pdftotext, and fallback to gs if pdftotext cannot extract any usefull information
parent
a54a1a593b
commit
714b11a2cf
1 changed files with 5 additions and 1 deletions
@ -1,2 +1,6 @@ |
|||||||
#!/bin/bash |
#!/bin/bash |
||||||
gs -q -dNODISPLAY -dSAFER -dDELAYBIND -dWRITESYSTEMDICT -dSIMPLE -c save -f ps2ascii.ps $1 -c quit 2>/dev/null |
RES=$(/usr/bin/pdftotext -eol unix -layout -nopgbrk "$1" -) |
||||||
|
if [ -z "$RES" ]; then |
||||||
|
RES=$(/usr/bin/gs -q -P- -dNODISPLAY -dSAFER -dDELAYBIND -dWRITESYSTEMDICT -dSIMPLE -f ps2ascii.ps "$1" -c quit 2>/dev/null | iconv -f ISO8859-1 -t UTF-8) |
||||||
|
fi |
||||||
|
echo "$RES" |
||||||
|
Loading…
Reference in new issue