msword.sum

来自「harvest是一个下载html网页得机器人」· SUM 代码 · 共 27 行

#!/bin/sh
#
#  MSWord.sum - Summarizes Microsoft Word files.
#
#  Convert Microsoft Word files to HTML with wvHtml and use HTML summarizer
#  to summarize the resulting HTML file.
#
#  wvHtml is part of wvWare and is available at:
#  http://wvware.sourceforge.net/
#
#if test -z "$TMPDIR"; then
#	TMPDIR="/tmp"
#fi
#if test ! -r "$1"; then
#	echo "MSWord.sum: Cannot read file: $1" 1>&2
#	exit 1
#fi
#tfile="$TMPDIR/mswsum.$$"
#wvHtml $1 $tfile
#HTML.sum $tfile
#rm -f $tfile
#exit 0
#
#  Use catdoc and take first 6000 lines of text.
#
catdoc -s koi8-r -d koi8-r $1 | fmt -s -w 160 | head -n 6000 | wrapit "Partial-Text"