8d1098
Add identity_renderHtmlPlaintext.sh.
@@ -0,0 +1,67 @@
|
|
1
|
+
|
2
|
+
#
|
3
|
+
# identity_renderHtmlPlaintext.sh -- This function takes one HTML file
|
4
|
+
# and produces one plain-text file (i.e., without markup inside).
|
5
|
+
#
|
6
|
+
# Copyright (C) 2009-2011 Alain Reguera Delgado
|
7
|
+
#
|
8
|
+
# This program is free software; you can redistribute it and/or
|
9
|
+
# modify it under the terms of the GNU General Public License as
|
10
|
+
# published by the Free Software Foundation; either version 2 of the
|
11
|
+
# License, or (at your option) any later version.
|
12
|
+
#
|
13
|
+
# This program is distributed in the hope that it will be useful, but
|
14
|
+
# WITHOUT ANY WARRANTY; without even the implied warranty of
|
15
|
+
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
16
|
+
# General Public License for more details.
|
17
|
+
#
|
18
|
+
# You should have received a copy of the GNU General Public License
|
19
|
+
# along with this program; if not, write to the Free Software
|
20
|
+
# Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307
|
21
|
+
# USA.
|
22
|
+
#
|
23
|
+
# ----------------------------------------------------------------------
|
24
|
+
# $Id$
|
25
|
+
# ----------------------------------------------------------------------
|
26
|
+
|
27
|
+
function identity_renderHtmlPlaintext {
|
28
|
+
|
29
|
+
# Verify existence of HTML file.
|
30
|
+
cli_checkFiles ${FILE}.xhtml 'f'
|
31
|
+
|
32
|
+
local COMMAND=''
|
33
|
+
local OPTIONS=''
|
34
|
+
|
35
|
+
# Define the command path to text-based web browser and options
|
36
|
+
# used to produce plain-text files. Most of these programs have a
|
37
|
+
# dump option that print formatted plain-text versions of given
|
38
|
+
# HTML file to stdout.
|
39
|
+
if [[ -x '/usr/bin/lynx' ]];then
|
40
|
+
COMMAND='/usr/bin/lynx'
|
41
|
+
OPTIONS='-force_html -nolist -width 70 -dump'
|
42
|
+
elif [[ -x '/usr/bin/elinks' ]];then
|
43
|
+
COMMAND='/usr/bin/elinks'
|
44
|
+
OPTIONS='-force_html -no-numbering -no-references -width 70 -dump'
|
45
|
+
elif [[ -x '/usr/bin/w3m' ]];then
|
46
|
+
COMMAND='/usr/bin/w3m'
|
47
|
+
OPTIONS='-dump'
|
48
|
+
fi
|
49
|
+
|
50
|
+
if [[ $COMMAND != '' ]];then
|
51
|
+
|
52
|
+
# Print action message.
|
53
|
+
if [[ -f ${FILE}.txt ]];then
|
54
|
+
cli_printMessage "${FILE}.txt" 'AsUpdatingLine'
|
55
|
+
else
|
56
|
+
cli_printMessage "${FILE}.txt" 'AsCreatingLine'
|
57
|
+
fi
|
58
|
+
|
59
|
+
# Convert from HTML to plain-text without markup.
|
60
|
+
${COMMAND} ${OPTIONS} ${FILE}.xhtml > ${FILE}.txt
|
61
|
+
|
62
|
+
else
|
63
|
+
cli_printMessage "`gettext "No way to convert from HTML to plain-text found."`" 'AsErrorLine'
|
64
|
+
cli_printMessage "$(caller)" 'AsToKnowMoreLine'
|
65
|
+
fi
|
66
|
+
|
67
|
+
}
|