anhhh.11 anhhh11

## index.html
<!DOCTYPE html>
<html>
<head>
<script src="http://code.jquery.com/jquery-git2.js"></script>
  <meta charset="utf-8">
  <title>JS Bin</title>
</head>
<body>
  <div id="box">Hello</div>
<script id="jsbin-javascript">

## Tesseract - OCR
gs -sDEVICE=tiffgray -dNOPAUSE -r300 -sOutputFile="o-%04d.tiff" ./ttnt.pdf -c quit
for i in *.tif ; do tesseract $i $i -l vie -psm 1 ; done
mkdir done
for i in *.tiff;do if [ -f $i.txt ];then mv $i.txt done/;mv $i done/;fi;done
gs -sDEVICE=jpeg -dJPEGQ=100 -dNOPAUSE -r300 -sOutputFile="o-%04d.jpeg" ./ttnt.pdf -q -c quit
for i in done/*.txt; do j="`basename -s .tiff.txt $i`.jpeg";if [ -f $j ];then rm -f $j;fi; done
for i in *.jpeg ; do tesseract $i $i -l vie; done


## convert office file to PDF
#go to bash
soffice.exe --headless --convert-to pdf *.ppt

## remove all .gz file
sudo find . -type f -name '*.gz' | xargs rm

## gist:6933688
tar cvf - website/ | gzip -9 - >~/website.tar.gz
	<!DOCTYPE html>
	<html>
	<head>
	<script src="http://code.jquery.com/jquery-git2.js"></script>
	<meta charset="utf-8">
	<title>JS Bin</title>
	</head>
	<body>
	<div id="box">Hello</div>
	<script id="jsbin-javascript">
	gs -sDEVICE=tiffgray -dNOPAUSE -r300 -sOutputFile="o-%04d.tiff" ./ttnt.pdf -c quit
	for i in *.tif ; do tesseract $i $i -l vie -psm 1 ; done
	mkdir done
	for i in *.tiff;do if [ -f $i.txt ];then mv $i.txt done/;mv $i done/;fi;done
	gs -sDEVICE=jpeg -dJPEGQ=100 -dNOPAUSE -r300 -sOutputFile="o-%04d.jpeg" ./ttnt.pdf -q -c quit
	for i in done/*.txt; do j="`basename -s .tiff.txt $i`.jpeg";if [ -f $j ];then rm -f $j;fi; done
	for i in *.jpeg ; do tesseract $i $i -l vie; done