# Description:
# A script to reformat a plain text file document which contains
# a dairy of some sort into some kind of html. By a 'diary' I mean
# a series of entries for particular dates. Specifically, the text file
# should contain dates in a format like '* 3 march 2003, Saturday' or
# something similar, and should be followed by some sort of descriptive
# text relating to that date. The script recognises some special structures
# within the plain text document. For example:
#
# The diary entry dates should be on a line by themselves and should
# begin with a * character like this:
# * 3 January 1992, Friday
#
# The '=' character, when the first non-whitespace character on a line indicates
# that all the following text on the line should be formatted as a
# 'heading'. Also, url style strings should be recognised and given
# a hyperlink token in from of them, such as '[*]'. I prefer this to underlining
# the entire url, because I find that the underlining tends to interfer with
# the readability of the text. Some people would say, "use style-sheets" but to
# them I would reply that the 'heraldic' visual pattern of the underlined hyperlink
# is imprinted in many internet users brains, and to change that 'iconography' can
# lead to unnecessary confusion.
#
# Examples:
# ./diary2html.sh mjb-work.txt notran > mjb-work.html
# This command line, executed in some kind of a bash shell, will transform a
# plain text file which has 'diary' style entries, into an HTML file (that is
# it will create a new HTML file and leave the original text file unchanged) and
# will not display the automatic translation links to Google.
# Also an HTML table of contents (with one entry for each date) will be
# inserted in the HTML document.
#
# ./diary2html.sh mjb-work.txt notran notoc > mjb-work.html
# The text file will be transformed into HTML but no table of contents
# will be inserted nor any translation links.
#
# ./diary2html.sh mjb-work.txt blah notoc > mjb-work.html
# If translation links are desired but no table of contents use a
# command line similar to above. The string 'blah' could be anything
# as long as its not 'notran'. This slighty dodgy 'feature' is owing to the
# fact that I am not using any 'getopt' style option parsing.
#
# Parameters:
# textFileName [required]
# The name of the text file which is to be transformed from text into html
# notran [optional]
# If the second parameter is the string 'notran' then the javascript links
# to the google automatic language translation engine will NOT be inserted
# into the HTML page. This is useful, for example, when the HTML page is
# going to be located within a 'password-protected' directory, because
# the Google translation engine will not be able to access the page, and
# therefor the translation links will not work.
# notoc [optional]
# If the third parameter is the string "notoc", then no HTML table of
# contents will be generated.
# Notes:
# This script contains an improved url detection regular expresion, better than that
# in say txtdoc2html.sh. But the url pattern matcher still has a problem when
# somebody puts a full stop after a url. It thinks that that dot is part of the
# url.
# See Also:
# txtdoc2html.sh, linkdoc2html.sh, plaintext2html.sh
# Author:
# m.j.bishop
if [ "$1" = "" ]
then
echo "usage: $0 textFileName [notran] [notoc]"
cat $0 | sed -n "/^[ ]*#/p"
exit 1;
fi
#-- The section below creates the table of contents for the diary.
#-- This line is designed to only number lines which match a pattern
#-- In theory 'nl -bpPATTERN' should also do this, but it insisted on
#-- 'double-spacing' the output
cat $1 | expand | mawk '/^[ ]*\*[ ]*[^ ]+/{ii++; print ii $0}!/^[ ]*\*[ ]*([^ ]+)/' > $1.temp
(echo "<center><a name = \"toc\"></a>"; \
cat $1.temp | \
sed "/^[ ]*\([0-9]\{1,\}\)[ ]*\*\(.*\)/!d" | \
sed "s/\(monday\|tuesday\|wednesday\|thursday\|friday\|saturday\|sunday\)//gi" | \
sed "s/^[ ]*\([0-9]\{1,\}\)[ ]*\*\(.*\)/<a href=\"#item\1\" class = \"t\">\2<\/a> | /g"; \
echo "</center>";) > diary-toc.temp
echo "<!DOCTYPE HTML PUBLIC \"-//W3C//DTD HTML 3.2//EN\">"
echo "<html>"
echo " <META HTTP-EQUIV=\"Content-Type\" CONTENT=\"text/html; CHARSET=iso-8859-1\">"
echo " <META HTTP-EQUIV=\"Keywords\""
echo " CONTENT=\"\">"
echo " <META HTTP-EQUIV=\"Description\""
echo " CONTENT=\"\">"
echo " <LINK REV=\"made\" HREF=\"mailto:webmaster@ella-associates.org\">"
echo ""
echo "<!-- HTML generated by the \"$(basename $0)\" script -->"
echo "<!-- From the File: \"$1\" -->"
echo "<!-- On the Date: $(date) -->"
echo "<!-- see http://www.ella-associates.org/utils/$(basename $0) -->"
echo "<link rel = \"stylesheet\" type = \"text/css\""
echo " href = \"/stylesheets/swish-style.css\">"
echo "<head>"
echo "<script language = \"javascript\">"
echo "
<!--
function redirectToGoogleTranslation(sSourceLanguage, sTargetLanguage)
{
var sTranslationUrl = 'http://translate.google.com/translate?u=';
sTranslationUrl += escape(document.location.href);
sTranslationUrl += '&langpair=' + sSourceLanguage + '|' + sTargetLanguage;
sTranslationUrl += '&hl=' + sSourceLanguage;
// document.testForm.test.value=sTranslationUrl;
window.location = sTranslationUrl;
} //-- redirectToGoogleTranslation()
--> "
echo "</script>"
echo "</head>"
echo "<body>"
#-- The Google automatic translation links below, are sometimes disabled because they will
#-- not work from within a password protected directory, since Google does not
#-- have permission to view that directory.
if [ "$2" != "notran" ]
then
echo "<center>"
echo "See this page in (approximate):"
echo "<a href=\"javascript:redirectToGoogleTranslation('en', 'es');\">Español</a>|"
echo "<a href=\"javascript:redirectToGoogleTranslation('en', 'fr');\">Français</a>|"
echo "<a href=\"javascript:redirectToGoogleTranslation('en', 'it');\">Italiano</a>|"
echo "<a href=\"javascript:redirectToGoogleTranslation('en', 'de');\">Deutsch</a>|"
echo "<a href=\"javascript:redirectToGoogleTranslation('en', 'pt');\">Português</a>"
echo "</center>"
fi
#-- This was the old regular expression used to find dates, but now I am using * format
#--
#- sed "s/^[ 0-9,]*\(jan\|feb\|mar\|apr\|may\|jun\|jul\
# |aug\|sep\|oct\|nov\|dec\)[a-z]*[ 0-9,]*.*/<strong>&<\/strong>/gi" | \
#-- Put the page heading before the table of contents
#--
cat $1.temp | \
sed "/^[ ]*=[ ]*.*/!d" | \
sed -e "s/</\</g" -e "s/>/\>/g" | \
sed "s/^[ ]*=[ ]*\(.*\)/<center><h2>\1<\/h2><\/center>/gi"
echo "<table align=\"center\" width = \"90%\"><tr><td>"
#-- Inset the table of contents
if [ "$3" != "notoc" ]
then
cat diary-toc.temp
fi
#-- Transform the text to HTML, insert anchors
#-- Also delete the heading line which has already been inserted in the HTML
#-- But, the line will also delete lines beginning in == or === etc, which
#-- may not be desirable.
cat $1.temp | \
expand | \
sed "/^[ ]*=[ ]*\(.*\)/d" | \
sed -e "s/</\</g" -e "s/>/\>/g" | \
sed -e "s/^[ ]*\-\-\>\>/<pre class = \"sed\">/g" -e "s/^[ ]*\-\-\<\</<\/pre>/g" | \
sed "s/^[ ]*\([0-9]\{1,\}\)[ ]*\*\(.*\)/<br><u><strong><a name=\"item\1\">\2<\/a><\/strong><\/u> <a href=\"#toc\">[TOC]<\/a>/g" | \
sed "s/\(http:\/\/[-a-z\%0-9\~\\\/\"\'\.\@]\{3,\}\)/<a href='\1' class = \"t\">[*]<\/a><tt> \1<\/tt>/gi" | \
sed "s/[^a-zA-Z\/]\(www\.[-a-z\%0-9\~\\\/\"\'\.\@]\{2,\}\)/<a href='http:\/\/\1'>[*]<\/a><tt> \1<\/tt>/gi" | \
sed "/<pre class = \"sed\">/,/<\/pre>/!s/[ ]\{2\}/\ \ /g" | \
sed "/<pre class = \"sed\">/,/<\/pre>/!s/^/<br>/g"
echo "<br>"
echo "</td></tr></table>"
if [ "$2" != "notran" ]
then
echo "<center>"
echo "See this page in (approximate):"
echo "<a href=\"javascript:redirectToGoogleTranslation('en', 'es');\">Español</a>|"
echo "<a href=\"javascript:redirectToGoogleTranslation('en', 'fr');\">Français</a>|"
echo "<a href=\"javascript:redirectToGoogleTranslation('en', 'it');\">Italiano</a>|"
echo "<a href=\"javascript:redirectToGoogleTranslation('en', 'de');\">Deutsch</a>|"
echo "<a href=\"javascript:redirectToGoogleTranslation('en', 'pt');\">Português</a>"
echo "</center>"
fi
echo "</body>"
echo "</html>"
rm -f diary-toc.temp
rm -f $1.temp