/,/<\/pre>/!{/\[IMAGE-INDEX-BEGIN\]/,/\[IMAGE-INDEX-END\]/! s/[ ]\{2\}/\ \ /g;}" | \
// #-- Make paragraphs where there are blank lines
// #sed "//,/<\/pre>/!s/^[ ]*$//g" | \
// #-- Make 'fake' headings
// sed "/
/,/<\/pre>/!s/{{ //g" | \
// sed "//,/<\/pre>/!s/ }}/<\/em><\/strong>/g" | \
// sed "//,/<\/pre>/!s/[ ]*==[ ]*\(.*\)/\1<\/em><\/strong><\/font>/g" | \
// #-- Turn line breaks into
tags unles they are between 'pre' tags. This isn't really
// #-- a good idea since you dont know the width of the target screen
// #sed "//,/<\/pre>/!{/\[IMAGE-INDEX-BEGIN\]/,/\[IMAGE-INDEX-END\]/! s/^/
/g;}"
// #sed "//,/<\/pre>/!{//!s/^/
/g;}" | \
// sed "//,/<\/pre>/!{/\[BAND-DETAIL-LIST-BEGIN\]/,/\[BAND-DETAIL-LIST-END\]/!s/^/
/g;}" | \
// sed -e "s/\[BAND-DETAIL-LIST-BEGIN\]/
/g" -e "s/\[BAND-DETAIL-LIST-END\]/<\/table>/g" | \
// #-- Get rid of Image Index tags
// sed -e "s/\[IMAGE-INDEX-BEGIN\]//g" -e "s/\[IMAGE-INDEX-END\]//g"
//#sbResult.append("
\n");
//
// sbResult.append("
\n");
//
// #-- Define the cgi program which will handle the updating of the document
// #-- according to the contents of the HTML textarea component
// if [ "$4" != "" ]
// {
// sProcessorUrl="$4"
// } else {
// #-- It would be possible to replace the Domain Name below with
// #-- an IP address, which would mean that the script would still
// #-- work even if the DNS configuration failed. I am not sure if this
// #-- is really a good idea or not.
// #sProcessorUrl="http://www.ella-associates.org/cgi-bin/edit-wiki.cgi"
// sProcessorUrl="http://63.105.73.195/cgi-bin/edit-wiki.cgi"
// } //-- if
// #-- There is a problem in that I need to find the full path
// #-- name of the $1 variable, but I dont know how to do this. This
// #-- is necessary because the target processor is not in the same
// #-- directory as the source document (the text file)
// #-- For the time being I have used the remedy of seeing if the path
// #-- is relative or absolute. The slightly dodgy path generating code below
// #-- appears to be working. There is almost certainly a much easier way
// #-- of doing it
//
// sRelativePath=$(dirname $1)
// sFirstCharacter=$(echo $sRelativePath | sed "s/^\(.\).*$/\1/g")
// if (sRelativePath.equalsIgnoreCase("."))
// {
// sFullPathName="$(pwd)/$1"
// } else if (sFirstCharacter.equalsIgnoreCase("."))
// {
// sFullPathName="$(pwd)/$1"
// } else if (sFirstCharacter.equalsIgnoreCase("/"))
// {
// sFullPathName="$1"
// } else {
// sFullPathName="$(pwd)/$1"
// } //-- if
// # echo $sFullPathName
//
// echo "
// \n");
//
// if (bTranslationLinks)
// {
// sbResult.append(" \n");
// if (sOutputLanguage.equalsIgnoreCase("spanish"))
// {
// sbResult.append("Vea este pagina en (aproximado): \n");
// sbResult.append("English \n");
// } else if (sOutputLanguage.equalsIgnoreCase("french"))
// {
// sbResult.append("Voir la cette page dedans (approximatif): \n");
// sbResult.append("English \n");
// } else if (sOutputLanguage.equalsIgnoreCase("italian"))
// {
// sbResult.append("Osservi questa pagina come (approssimativo): \n");
// sbResult.append("English \n");
// } else {
// sbResult.append("See this page in (approximate): \n");
// sbResult.append("Español| \n");
// sbResult.append("Français| \n");
// sbResult.append("Italiano| \n");
// sbResult.append("Deutsch| \n");
// sbResult.append("Português \n");
// } //-- if
// sbResult.append(" \n");
// } //-- if
//
// sbResult.append(" \n");
// sbResult.append(" \n");
//
// #rm -f $1.temp
// #rm -f plain-text-toc.temp
import java.io.*;
import java.net.*;
import java.util.*;
import java.text.*;
//import javax.mail.*;
//import javax.activation.*;
//import javax.mail.internet.*;
/**
* This class is designed to put a file from the local filesystem to a WebDav Server
*
*
* Description:
*
* This program is in the process of being adapted from a bash shell script
*
* A script/ program to reformat a plain text file document which contains no
* particular format into HTML. The text file stores some kind of structured content. The idea
* of the script is to reformat plain text files which contain 'information' rather
* than 'display instructions', although this script also accepts some display instruction
* indicators.
*
* The script will work in conjuction with the cgi script 'edit-wiki.cgi' to allow the
* visitor to the web page to edit the page. It does this by generating an HTML form
* which points to the cgi script
*
* Automatically Formatted Text Structures:
*
* The script recognises some 'cues' within the plain text document.
* I refer to these cues or 'structures' as 'Invisible Markup Language' (IML) or Mas
* o Menos Markup Language (MMML). The basic ideas is to have as little actual
* 'markup' in the text document as possible, and the markup which is present should
* 'look good' in the plain text file. So,
* instead of using, say,
* %^* Section Heading
* which is valid markup but looks ugly in the text file, we use all capitals
* which, in my opinion, looks better in the text file
*
* The document title:
* ---------------------------
* A line beginning with a '=' character is the 'document title'. In the resulting HTML it
* will be made big and put at the top of the web-page. It will also be used as the HTML title
* Links to document formats:
* ---------------------------
* A line beginning with '*' will be hyperlinked, and formatted in a special kind of way.
* These 'star' lines can be used to provide links to various formats of one particular document
* such as pdf, text, html ...
* Hyper-linking URLs:
* ---------------------------
* URLs get automatically hyperlinked if they begin with http:// or www. The display text of the
* hyper-link will be the actual url itself. To change this display text use the format
* "Hyperlink display text" http://some.url.dom/ This format does not have to begin the line.
* To create a link to a relative url use the format link://some/relative/url/path
* Document Section Headings:
* ---------------------------
* Lines which contain only capital (upper-case) letters are interpreted as 'section headings'
* These section headings will be used to form a HTML hyper-linked table of contents if that is
* required (see the '[]' code below).
*
* Unformatted blocks of text:
* ---------------------------
* If you want blocks of the text file to be 'untouched' by the transformation script then
* you can surround those blocks with -->> and --<< This is useful for displaying listings
* of computer code and for displaying tables of data.
* Document Title Codes:
* ---------------------------
* Certain codes can be placed after the document title (as defined above: a line beginning with '=')
* This codes can have a large influence on the appearance of the resulting HTML. All codes can
* be combined in what ever combination
* {x} means number all section headings (including in the Table of Contents)
* {~} means make the section headings into 'capital case'
* These can be combined, for example: {~x} //-- if
* [] means display the table of contents
* [~] means display the TOC with items in 'capital case'
* (+) means display automatic google translation links in the HTML
* (XX) display 'user messages' in the language specified by the two letter language code
* A list of these codes can be found at http://www.w3.org/WAI/ER/IG/ert/iso639.htm
* At the moment only common european languages are supported, and even those, incompletely
*
* In some cases the function of these codes is duplicated by parameters which may be passed to the
* shell script.
*
* Specific Display Indicators:
* ---------------------------
* The following are designed to allow greater control over the appearance of the resulting HTML.
* This contradicts the general principle of this script which is to encourage the creation of
* 'information' rather than display instructions, but these indicators do not have to be used,
* and they may be grouped together at the end of the text file to minimize their corrupting influence
*
* background-color: some-color
* This changes the background color of the resulting HTML
* background-image: some-image-url
* This changes the background image of the resulting HTML
* section-heading-css-class:
* Determines the css class which will govern the appearance of the section headings
* css-style-sheet:
* Determines the css style sheet which will be applied to the document
* Title Image Html: some-title-image-html
* This is designed to allow the placement of an image such as a logo at the top
* of a web-page which will also act as a link to some home page. This is not
* a particular useful concept
* Title Decoration:
* This is a strange concept which I had of allowing Ascii style decorations at
* the top of the HTML page underneath the heading for the page. This was after
* noticing that some ascii characters, when enlarged with a big font can be quite
* aesthetically pleasing
*
* [IMAGE-INDEX-BEGIN] / [IMAGE-INDEX-END]
* These block tags are use to create and 'image index' which is a list
* of Hyperlinked images with descriptive text next to each of the images
* These tags are soly for presentation purposes
* [BAND-INDEX-BEGIN] / [BAND-INDEX-END]
* These tags are used to delineate a list of musical bands. These two sets of block
* tags were really invented in order to fulfill the requirement of the website which
* is at http://poseidonia.ella-associates.org (august 2003). Since this site is for
* a music festival which will soon be over, and since it is hosted on a rented server
* in the United States, it is quite likely that this site will not exist for very long.
*
* Examples:
* If the scripts are on the system 'path' the the leading './' characters
* below are not necessary
*
* ./plaintext2html-wiki.sh concert-details.txt notran > concert-details.html
* This command line, executed in some kind of a bash shell, will transform
* a plain text file which isn't is any particular format, 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 heading,
* if there are headings) will be inserted in the HTML document.
*
* ./plaintext2html-wiki.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.
*
* ./plaintext2html-wiki.sh mjb-work.txt tran 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.
*
* ./plaintext2html-wiki.sh stuff.txt notran toc "http://63.105.73.195/cgi-bin/some-weird-script"
* This transforms the file stuff.txt omitting translation links, inserting
* a hyperlinked table of contents, and setting the target for the 'edit
* document' form to the URL specified in the last parameter.
*
* For examples of using 'invisible markup language' you can try looking at the URLs
* http://poseidonia.ella-associates.org/ and
* http://poseidonia.ella-associates.org/band-details.html
* however, the whole point about the invisible markup language is that you dont really need to
* know how to use it, since it guesses how it should behave.
*
* 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.
* forumProcessorUrl [optional]
* This parameter indicates where the processing script is located. If it
* is omitted, currently the url will default to
* http://www.ella-associates.org/cgi-bin/add-comment
* output-language [optional] {Not implemented}
* This is the language in which the message on the generated HTML page
* will appear. For example messages next to the comment boxes and the
* translation links.
* noforum {Not implemented}
* If this parameter is present no HTML form will be produced in the ouput
* and therefor the web-visitor will not be able to add comments to the
* pages.
* path-to-style-sheet [optional] {Not implemented}
* Still to implement
* This is the full path (relative to the Web Server Document Root)
* to the style sheet which is to be used by the generated HTML page
*
*
* Notes:
* This script was derived directly from text2html-collab.sh which in turn
* was derived from poseidontext2html-collab.sh which was derived from
* plaintext2html-forum.sh and so on
*
* When I say derived I mean that the script was created by modifying that script
* This script should also transform quotes into " & into & etc The
* script appears to be working reasonably well in conjunction with the
* 'edit-wiki' cgi script.
*
* The 'nl' number-line program, when used with the -bp option
* double spaces the text file with lines containing only spaces. Therefore
* some extra 'sed' lines are necessary to remove these blank lines
*
* See Also:
* There is a whole set of 'plaintext' transformation scripts which can be found
* (august 2003) at http://www.ella-associates.org/utils/ This is probably not a very
* long-term URL
*
* edit-wiki.cgi
* This is the cgi script which can work in conjunction with the current script
* diary2html.sh,
* Turns a 'diary' style text file into HTML
* linkdoc2html.sh,
* Turns a text file which has a list of URL links and descriptions into HTML
* linkdoc2html-index.sh
* As above but also adds an HTML 'table of contents' for possible 'section headings'
* linkdoc2html-forum.sh
* Turns a text file with a URL list into an HTML file which has the capability
* to be contributed to by a web-visitor (using cgi-scripts)
* plaintext2pdf.sh,
* Turns a text file into a pdf file with an optional table of contents. Relies on
* the 'htmldoc' program
* plaintext2html-forum.sh
* Renders a text file as HTML and displays a form which allows the web-visitor
* to add 'comments' to the page (text file)
* plaintext2html.sh
* Turns a text file with possible section headings and urls into an HTML file
* glossary2xml.sh
* Turn a text file which is a sort of 'glossary' into a dodgy xml file. This
* needs to be improved to produce DocBook XML, which has the tag
* alphabetize-glossary.sh
* Re-arranges a text file which contains a series of definitions of 'items' or 'terms'
* so that the items are ordered alphabetically.
* add-comment
* a cgi-script which can be used in conjuction with some of the
* scripts above to add content specified by web-visitors to a web page
* script-summary.txt
* contains more short descriptions of scripts and what they do.
* plaintext2docbook.sh
* Turns text files into DocBook Xml, fairly well but not fail-proof
* text2html-collab.sh
* This is very similar to the current script but the HTML editing box is on
* the same page as the text
* Author:
* m.j.bishop
*
* Bugs and Ideas
* In Internet explorer the 'capital case' function does not work properly. The
* entire text is lower-cased and the first letter is NOT upper-cased. This is
* probably another 'text-area' line ending problem
*
* When you hit 'refresh' in Netscape and IE the contents of the HTML textarea
* are not 'refreshed'. That is, the contents do not reflect the true contents
* as dictated by the HTML source code. Rather the editings of the user are
* preserved. I presume this is customizable.
*
* In IE when you hit refresh the page does not refresh at all, which means that
* the user is unable to see the changes which she has made.
*
* This script needs more internationalization
*
* The script could also check if there are translations of the current
* HTML or text file, using the standard naming convention of name.file-type.language-code
* An example of this naming convention is stuff.html.es which should
* be an HTML file which contains Spanish language content. This present
* script could check for files which have the same name as the source
* file but which have a different language code extension, and could
* therefore automatically add a link to the translated file (in addition,
* perhaps to the Google translation links). The script would only
* check in the current directory for these 'translated' files.
*
* When there are no numbers for section headings capital case in not working 6june
*
* This is becoming a script which attempts to do absolutely everything. This may
* well not be a good idea
*
* Dependencies:
* iso2html.sed
* A script which turns accented characters into HTML entities. This is
* a bit tricky since the American Server uses UTF-8 rather than ISO-8859
* I could get around this by using a directive in the head, but I am not sure
* if all browsers can handle the utf-8 character set.
* capital-case.sed
* A script which 'capital cases' words. That is the first letter is upper
* case and all the rest lower case
* capital-case-headings.sed
* This does the same as above but on for lines which are 'section headings'
* which means all capital letters
* edit-wiki
* This is not a total dependency, but the HTML form generated by the
* current script will not do anything useful without this script
* procgi
* A bash shell cgi HTML form value extractor used by 'edit-collab'
* The 'uncle-sam.gif' image
* which is used next to the text box message
* The images used on the 'poseidon site'
* various Unix tools, a Bash shell
* iconv
* A unix program to convert from different text encodings, such as
* iso-8859-1 to utf-8
*
* History:
*
* june 3, 2003
* Adapted this script from 'poseidon-text2html-forum.sh'
* june 6, 2003
* Improved the handling of accented characters. All section headings are
* now governed by the variable 'sHeadingPattern'
* june 30
* adapted from text2html-collab.sh
* august 6, 2003
* beginning the process of porting this script to java
*
*
*
* @author mjb
* @see "http://www.ella-associates.org/utils/plaintext2html-wiki.sh"
*/
public class Invisible2HtmlWiki
{
public static void main (String[]args) throws Exception
{
String sFileName = "";
if (args.length == 1)
{
sFileName = args[0];
} //-- if
} else if (args.length == 2)
{
sFileName = args[0];
sFileName = args[1];
} //-- if
} else {
{
//-- The following attempts to display the javadoc from this file
//--
FileReader firTheFile = new FileReader ("/var/www/utils/Invisible2HtmlWiki.java");
BufferedReader buffrTextFile = new BufferedReader (firTheFile);
String sTextLine;
sTextLine = buffrTextFile.readLine();
while (sTextLine != null)
{
if (sTextLine.matches("\\s*\\*.*"))
{ System.out.println(sTextLine); }
sTextLine = buffrTextFile.readLine();
}
System.exit (-1);
} //-- if, else [Command Line Arguments]
System.out.println(makeAutoTranslationLinks("spanish"));
BufferedReader brdTheTextFile = new BufferedReader(new FileReader(sFileName));
String sCurrentTextLine;
sCurrentTextLine = brdTheTextFile.readLine();
while (sCurrentTextLine != null)
{
if (sCurrentTextLine.matches(".*"))
{
System.out.println(sCurrentTextLine.replaceAll(
"[^a-zA-Z\\/\"](http://[^ ]+)",
""));
} //-- if
sCurrentTextLine = brdTheTextFile.readLine();
//-- place the flag variable assignments here. For example if the line matchs then
//-- turn the bBetweenPreFlag on
}
//sed "//,/<\/pre>/!s/[^a-zA-Z\/\">]\(www\.[-a-z:_\%0-9\~\\\/\"\'\.\@]\{2,\}\)/[*]<\/a>\1<\/tt>/gi" | \
//
} // main
public static StringBuffer makeAutoTranslationLinks(String sSourceLanguage)
{
StringBuffer sbResult = new StringBuffer("");
if (sSourceLanguage.equalsIgnoreCase("spanish"))
{
sbResult.append("Vea este página en (aproximado): \n");
sbResult.append("English \n");
} //-- if
} else if (sSourceLanguage.equalsIgnoreCase("french"))
{
} //-- if
return sbResult;
// if (bTranslationLinks)
// {
// sbResult.append(" \n");
// if (sOutputLanguage.equalsIgnoreCase("spanish"))
// {
// sbResult.append("Vea este pagina en (aproximado): \n");
// sbResult.append("English \n");
// } else if (sOutputLanguage.equalsIgnoreCase("french"))
// {
// sbResult.append("Voir la cette page dedans (approximatif): \n");
// sbResult.append("English \n");
// } else if (sOutputLanguage.equalsIgnoreCase("italian"))
// {
// sbResult.append("Osservi questa pagina come (approssimativo): \n");
// sbResult.append("English \n");
// } else {
// sbResult.append("See this page in (approximate): \n");
// sbResult.append("Español| \n");
// sbResult.append("Français| \n");
// sbResult.append("Italiano| \n");
// sbResult.append("Deutsch| \n");
// sbResult.append("Português \n");
// } //-- if
// sbResult.append(" \n");
// } //-- if
//
//
} // method: makeAutoTranslationLinks
} // class: Invisible2html-wiki