jtextile.JTextile Maven / Gradle / Ivy
/*
This is Textile
A Humane Web Text Generator
Original PHP Version
Version 1.0
21 Feb, 2003
Copyright (c) 2003, Dean Allen, www.textism.com
All rights reserved.
This java version by Gareth Simpson
1.0 April 2003
1.1 mid 2004
1.2 March 2006
_______
LICENSE
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
* Redistributions of source code must retain the above copyright notice,
this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above copyright notice,
this list of conditions and the following disclaimer in the documentation
and/or other materials provided with the distribution.
* Neither the name Textile nor the names of its contributors may be used to
endorse or promote products derived from this software without specific
prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
POSSIBILITY OF SUCH DAMAGE.
_____________
USING TEXTILE
Block modifier syntax:
Header: hn.
Paragraphs beginning with 'hn. ' (where n is 1-6) are wrapped in header tags.
Example: Text
Header with CSS class: hn(class).
Paragraphs beginning with 'hn(class). ' receive a CSS class attribute.
Example: Text
Paragraph: p. (applied by default)
Paragraphs beginning with 'p. ' are wrapped in paragraph tags.
Example: Text
Paragraph with CSS class: p(class).
Paragraphs beginning with 'p(class). ' receive a CSS class attribute.
Example: Text
Blockquote: bq.
Paragraphs beginning with 'bq. ' are wrapped in block quote tags.
Example: Text
Blockquote with citation: bq(citeurl).
Paragraphs beginning with 'bq(citeurl). ' recieve a citation attribute.
Example: Text
Numeric list: #
Consecutive paragraphs beginning with # are wrapped in ordered list tags.
Example: - ordered list
Bulleted list: *
Consecutive paragraphs beginning with * are wrapped in unordered list tags.
Example: - unordered list
Phrase modifier syntax:
_emphasis_ emphasis
__italic__ italic
*strong* strong
**bold** bold
??citation?? citation
-deleted text- deleted
+inserted text+ inserted
^superscript^ superscript
~subscript~ subscript
@code@ computer code
==notextile== leave text alone (do not format)
"linktext":url linktext
"linktext(title)":url linktext
!imageurl! 
!imageurl(alt text)!
!imageurl!:linkurl
ABC(Always Be Closing) ABC
*/
package jtextile;
import java.util.ArrayList;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
public class JTextile
{
@SuppressWarnings("unused")
private static final int ENT_COMPAT = 0;
private static final int ENT_NOQUOTES = 2;
private static final int ENT_QUOTES = 3;
public JTextile()
{
}
public static String textile(String text) throws Exception
{
//$text = stripslashes($text);
//# turn any incoming ampersands into a dummy character for now.
//# This uses a negative lookahead for alphanumerics followed by a semicolon,
//# implying an incoming html entity, to be skipped
text = preg_replace("&(?![#a-zA-Z0-9]+;)","x%x%",text);
//# unentify angle brackets and ampersands
text = replace(text,">", ">");
text = replace(text,"<", "<");
text = replace(text,"&", "&");
//# zap carriage returns
text = replace(text,"\r\n", "\n");
//# zap tabs
text = replace(text,"\t", "" );
// trim each line
StringBuffer splitBuffer = new StringBuffer();
String[] sList = text.split("/\n/");
for(int i = 0; i < sList.length; i++)
{
splitBuffer.append(sList[i].trim());
splitBuffer.append("\n");
}
text = splitBuffer.toString();
//### Find and replace quick tags
//# double equal signs mean
text = preg_replace("(^|\\s)==(.*?)==([^\\w]{0,2})","$1$2 $3$4",text);
//# image qtag
text = preg_replace("!([^!\\s\\(=]+?)\\s?(\\(([^\\)]+?)\\))?!","![\"$3\"](\"$1\")
",text);
//# image with hyperlink
text = preg_replace("($1", //# 3+ uppercase acronym
//"$1$2$3", //# 3+ uppercase caps
"$1$2$3", //# 3+ uppercase caps
"—", //# em dash
" – ", //# en dash
"$1–$2", //# en dash
"$1×$2", //# dimension sign
"™", //# trademark
"®", //# registered
"©" //# copyright
};
// # set toggle for turning off replacements between or
boolean codepre = false;
boolean notextile = false;
//# if there is no html, do a simple search and replace
if(!preg_match("<.[^<]*>",text))
{
text = preg_replace(glyph_search,glyph_replace,text);
}
else
{
StringBuffer out = new StringBuffer();
//# else split the text into an array at <.*>
//$text = preg_split("/(<.*>)/U",$text,-1,PREG_SPLIT_DELIM_CAPTURE);
String[] textSplit = preg_split("<.[^<]*>",text);
for(int i = 0; i < textSplit.length; i++)
{
// # matches are off if we're between , etc.
if(preg_match("<(code|pre|kbd)>",textSplit[i].toLowerCase()))
{
codepre = true;
}
if(preg_match("",textSplit[i].toLowerCase()))
{
codepre = true;
notextile = true;
}
else if(preg_match("",textSplit[i].toLowerCase()))
{
codepre = false;
}
else if(preg_match(" ",textSplit[i].toLowerCase()))
{
codepre = false;
notextile = false;
}
if(!preg_match("<.[^<]*?>",textSplit[i]) && codepre == false)
{
textSplit[i] = preg_replace(glyph_search,glyph_replace,textSplit[i]);
}
//# convert htmlspecial if between
if (codepre == true && notextile == false){
textSplit[i] = htmlspecialchars(textSplit[i],ENT_NOQUOTES);
textSplit[i] = replace(textSplit[i],"<pre>","");
textSplit[i] = replace(textSplit[i],"<code>","");
textSplit[i] = replace(textSplit[i],"<notextile>","");
}
if(notextile == true)
{
textSplit[i] = replace(textSplit[i],"\n","({)(})");
}
//# each line gets pushed to a new array
out.append( textSplit[i]);
}
text = out.toString();
}
//### Block level formatting
//# deal with forced breaks; this is going to be a problem between
//# tags, but we'll clean them later
//////!!! not working
//text = preg_replace("(\\S)(_*)([[:punct:]]*) *\n([^#*\\s])", "$1$2$3
$4", text);
//text = preg_replace("(\\S)(_*)([:punct:]*) *\\n([^#*\\s])", "$1$2$3
$4", text);
text = preg_replace("(\\S)(_*)([:punct:]*) *\\n([^#*\\s])", "$1$2$3
$4", text);
//# might be a problem with lists
text = replace(text,"l>
", "l>\n");
boolean pre = false;
String[] block_find = {
"^\\s?\\*\\s(.*)", //# bulleted list *
"^\\s?#\\s(.*)", //# numeric list #
"^bq\\. (.*)", //# blockquote bq.
"^bq\\((\\S+?)\\). (.*)", //# blockquote bq(cite-url).
"^h(\\d)\\(([\\w]+)\\)\\.\\s(.*)", //# header hn(class). w/ css class
"^h(\\d)\\. (.*)", //# plain header hn.
"^p\\(([[:alnum:]]+)\\)\\.\\s(.*)", //# para p(class). w/ css class
"^p\\. (.*)", //# plain paragraph
"^([^\\t ]+.*)" //# remaining plain paragraph
};
/*
String[] block_find = {
"/^\\s?\\*\\s(.*)/", // # bulleted list *
"/^\\s?#\\s(.*)/", // # numeric list #
"/^bq\\. (.*)/", // # blockquote bq.
"/^h(\\d)\\(([[:alnum:]]+)\\)\\.\\s(.*)/", // # header hn(class). w/ css class
"/^h(\\d)\\. (.*)/", // # plain header hn.
"/^p\\(([[:alnum:]]+)\\)\\.\\s(.*)/", // # para p(class). w/ css class
"/^p\\. (.*)/i", // # plain paragraph
"/^([^\\t ]+.*)/i" // # remaining plain paragraph
};
*/
String[] block_replace = {
// "\t$1 $2",
// "\t$1 $2",
"\t$1 ",
"\t$1 ",
"\t$1
",
"\t$2
",
"\t$3 $4",
// "\t$2 $3",
"\t$2 ",
"\t$2
$3",
"\t$1
",
// "\t$1
$2"
"\t$1
"
};
StringBuffer blockBuffer = new StringBuffer();
String list = "";
// This done to ensure that lists close after themselves
text += " \n";
//# split the text into an array by newlines
String[] bList = text.split("\n");
for(int i = 0; i <= bList.length; i++)
{
String line = " ";
if(i < bList.length)
line = bList[i];
//#make sure the line isn't blank
if (true || line.length() > 0 ) // actually i think we want blank lines
{
//# matches are off if we're between or tags
if(line.toLowerCase().indexOf("") > -1)
{
pre = true;
}
//# deal with block replacements first, then see if we're in a list
if (!pre)
{
line = preg_replace(block_find,block_replace,line);
}
//# kill any br tags that slipped in earlier
if (pre == true)
{
line = replace(line,"
","\n");
}
//# matches back on after
if(line.toLowerCase().indexOf("
") > -1)
{
pre = false;
}
//# at the beginning of a list, $line switches to a value
if (list.length() == 0 && preg_match("\\t\n$1$2",line);
list = line.substring(2,3);
}
//# at the end of a list, $line switches to empty
else if (list.length() > 0 && !preg_match("\\t\n$1",line);
list = "";
}
}
// push each line to a new array once it's processed
blockBuffer.append(line);
blockBuffer.append("\n");
}
text = blockBuffer.toString();
//#clean up
text = preg_replace("<\\/?notextile>", "",text);
//#clean up
text = replace(text,"({)(})", "\n");
//# clean up liu and lio
text = preg_replace("<(\\/?)li(u|o)>", "<$1li>",text);
//# turn the temp char back to an ampersand entity
text = replace(text,"x%x%","&");
//# Newline linebreaks, just for markup tidiness
text = replace(text,"
","
\n");
return text;
}
/**
* Does just that.
*
* @param source The string to start with
* @param searchFor The string we are looking for
* @param replaceWith The replacement
*
* @return The reformatted string
*
*/
private static String replace ( String source , String searchFor , String replaceWith )
{
if (source == null || "".equals(source)) {
return source;
}
if (replaceWith == null) {
return source;
}
if ("".equals(searchFor)) {
return source;
}
int s = 0;
int e = 0;
StringBuffer result = new StringBuffer();
while ((e = source.indexOf(searchFor, s)) >= 0)
{
result.append(source.substring(s, e));
result.append(replaceWith);
s = e + searchFor.length();
}
result.append(source.substring(s));
return result.toString();
}
private static String htmlspecialchars(String text, int mode)
{
text = replace(text,"&", "&");
if (mode != ENT_NOQUOTES)
text = replace(text,"\"", """);
if (mode == ENT_QUOTES)
text = replace(text,"'", "'");
text = replace(text,"<", "<");
text = replace(text,">", ">");
return text ;
}
private static String preg_replace(String pattern,String replace,String text) throws Exception
{
// gnu.regexp.RE r = new gnu.regexp.RE(pattern);
// return r.substituteAll(text,replace);
return Pattern.compile(pattern).matcher(text).replaceAll(replace);
}
private static String preg_replace(String[] pattern,String[] replace,String text) throws Exception
{
for(int i = 0; i < pattern.length; i++)
{
text = preg_replace(pattern[i],replace[i],text);
}
return text;
}
private static boolean preg_match(String pattern,String text) throws Exception
{
// gnu.regexp.RE r = new gnu.regexp.RE(pattern);
// return r.getMatch(text) != null;
return Pattern.compile(pattern).matcher(text).find();
}
private static String[] preg_split(String pattern,String text) throws Exception
{
int startAt = 0;
ArrayList tempList = new ArrayList();
// gnu.regexp.RE r = new gnu.regexp.RE(pattern);
Matcher m = Pattern.compile(pattern).matcher(text);
m.find();
// gnu.regexp.REMatch match = r.getMatch(text);
while(m.find())
{
String beforeMatch = text.substring(startAt, m.start());
tempList.add(beforeMatch);
tempList.add(text.substring(m.start(), m.end()));
startAt = m.end();
}
tempList.add(text.substring(startAt));
// copy out our templist to an array of strings which is what we return
String[] ret = new String[tempList.size()];
for(int i = 0; i < ret.length; i++)
{
ret[i] = tempList.get(i);
}
return ret;
}
}