smu-noxz

commit 0d5c6e340c134c2ee58e0e8715a7cbaae7895ad0
Author: Chris Noxz <chris@noxz.tech>
Date:   Thu, 19 Sep 2019 14:08:43 +0200

Initial commit of fork of smu

Diffstat:
A
LICENSE
 | 
21
+++++++++++++++++++++
A
Makefile
 | 
55
+++++++++++++++++++++++++++++++++++++++++++++++++++++++
A
config.mk
 | 
20
++++++++++++++++++++
A
documentation
 | 
201
+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
A
smu.1
 | 
23
+++++++++++++++++++++++
A
smu.c
 | 
624
+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
A
smu.h
 | 
19
+++++++++++++++++++
A
testdoc
 | 
80
+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++

8 files changed, 1043 insertions(+), 0 deletions(-)
diff --git a/LICENSE b/LICENSE
@@ -0,0 +1,21 @@
+MIT/X Consortium License
+
+(c) 2007-2014 Enno Boland <g s01 de>
+
+Permission is hereby granted, free of charge, to any person obtaining a
+copy of this software and associated documentation files (the "Software"),
+to deal in the Software without restriction, including without limitation
+the rights to use, copy, modify, merge, publish, distribute, sublicense,
+and/or sell copies of the Software, and to permit persons to whom the 
+Software is furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in 
+all copies or substantial portions of the Software. 
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL 
+THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+DEALINGS IN THE SOFTWARE.
diff --git a/Makefile b/Makefile
@@ -0,0 +1,55 @@
+# libsmu - simple markup
+# (c) 2007, 2008 Enno Boland
+
+include config.mk
+
+SRC    = smu.c
+OBJ    = ${SRC:.c=.o}
+
+all: options smu
+
+options:
+	@echo smu build options:
+	@echo "CFLAGS   = ${CFLAGS}"
+	@echo "LDFLAGS  = ${LDFLAGS}"
+	@echo "CC       = ${CC}"
+
+.c.o:
+	@echo CC $<
+	@${CC} -c ${CFLAGS} $<
+
+${OBJ}: config.mk
+
+smu: ${OBJ}
+	@echo LD $@
+	@${CC} -o $@ ${OBJ} ${LDFLAGS}
+
+clean:
+	@echo cleaning
+	@rm -f smu ${OBJ} ${LIBOBJ} smu-${VERSION}.tar.gz
+
+dist: clean
+	@echo creating dist tarball
+	@mkdir -p smu-${VERSION}
+	@cp -R LICENSE Makefile config.mk smu.1 ${SRC} smu-${VERSION}
+	@tar -cf smu-${VERSION}.tar smu-${VERSION}
+	@gzip smu-${VERSION}.tar
+	@rm -rf smu-${VERSION}
+
+install: all
+	@echo installing executable file to ${DESTDIR}${PREFIX}/bin
+	@mkdir -p ${DESTDIR}${PREFIX}/bin
+	@cp -f smu ${DESTDIR}${PREFIX}/bin
+	@chmod 755 ${DESTDIR}${PREFIX}/bin/smu
+	@echo installing manual page to ${DESTDIR}${MANPREFIX}/man1
+	@mkdir -p ${DESTDIR}${MANPREFIX}/man1
+	@sed "s/VERSION/${VERSION}/g" < smu.1 > ${DESTDIR}${MANPREFIX}/man1/smu.1
+	@chmod 644 ${DESTDIR}${MANPREFIX}/man1/smu.1
+
+uninstall:
+	@echo removing executable file from ${DESTDIR}${PREFIX}/bin
+	@rm -f ${DESTDIR}${PREFIX}/bin/smu
+	@echo removing manual page from ${DESTDIR}${MANPREFIX}/man1
+	@rm -f ${DESTDIR}${MANPREFIX}/man1/smu.1
+
+.PHONY: all options clean dist install uninstall
diff --git a/config.mk b/config.mk
@@ -0,0 +1,20 @@
+# smu version
+VERSION = 1.4
+
+# paths
+PREFIX = /usr/local
+MANPREFIX = ${PREFIX}/share/man
+
+# includes and libs
+INCS = -I. -I/usr/include
+LIBS = -L/usr/lib
+
+# flags
+CFLAGS = -g -O0 -Wall -Werror -ansi ${INCS} -DVERSION=\"${VERSION}\"
+#CFLAGS = -fprofile-arcs -ftest-coverage -pg -g -O0 -Wall -Werror -ansi ${INCS} -DVERSION=\"${VERSION}\"
+#CFLAGS = -Os -Wall -Werror -ansi ${INCS} -DVERSION=\"${VERSION}\"
+#LDFLAGS = -fprofile-arcs -ftest-coverage -pg ${LIBS}
+LDFLAGS = ${LIBS}
+
+# compiler
+CC = cc
diff --git a/documentation b/documentation
@@ -0,0 +1,201 @@
+smu - a Simple Markup Language
+==============================
+
+_smu_ is a very simple and minimal markup language. It is designed for use in
+wiki-like environments. smu makes it very easy to write your documents on the
+fly and convert them into HTML.
+
+smu is capable of parsing very large documents. It scales just great as long
+as you avoid a huge amount of indents (this will be fixed in future releases
+of smu).
+
+Syntax
+======
+
+smu was started as a rewrite of
+[markdown](http://daringfireball.net/projects/markdown/) but became something
+more lightweight and consistent. The biggest difference between markdown and smu
+is that smu doesn't support _reference style links_
+
+Inline pattern
+--------------
+
+There are several pattern you can use to highlight your text:
+
+* Emphasis
+  * Surround your text with `*` or `_` to get *emphasised* text:
+    	This *is* cool.
+    	This _is_ cool, too.
+  * Surround your text with `**` or `__` to get **strong** text:
+    	This **is** cool.
+    	This __is__ cool, too.
+  * Surround your text with `***` or `___` to get ***strong and emphasised*** text:
+    	This ***is*** cool.
+    	This ___is___ cool, too.
+  * But this example won't work as expected:
+    	***Hello** you*
+    This is a wontfix bug because it would make the source too complex.
+    Use this instead:
+    	***Hello*** *you*
+
+* inline Code
+
+  You can produce inline code with surrounding `\`` or `\`\``
+
+  	Use `rm -rf /` if you're a N00b.
+
+  	Use ``rm -rf /`` if you're a N00b.
+
+  `\`\`ABC\`\`` makes it possible to use Backticks without backslashing them.
+
+
+Titles
+------
+
+Creating titles in smu is very easy. There are two different syntax styles. The
+first is underlining:
+
+	Heading
+	=======
+	
+	Topic
+	-----
+
+This is very intuitive and self explaining. The resulting sourcecode looks like
+this:
+
+	<h1>Heading</h1>
+	<h2>Topic</h2>
+
+Use the following prefixes if you don't like underlining:
+
+	# h1
+	## h2
+	### h3
+	#### h4
+	##### h5
+	###### h6
+
+Links
+-----
+
+The simplest way to define a link is with simple `<>`.
+
+	<http://s01.de>
+
+You can do the same for E-Mail addresses:
+
+	<yourname@s01.de>
+
+If you want to define a label for the url, you have to use a different syntax
+
+	[smu - simple mark up](http://s01.de/~gottox/index.cgi/proj_smu)
+
+The resulting HTML-Code
+
+	<a href="http://s01.de/~gottox/index.cgi/proj_smu">smu - simple mark up</a></p>
+
+Lists
+-----
+
+Defining lists is very straightforward:
+
+	* Item 1
+	* Item 2
+	* Item 3
+
+Result:
+
+	<ul>
+	<li>Item 1</li>
+	<li>Item 2</li>
+	<li>Item 3</li>
+	</ul>
+
+Defining ordered lists is also very easy:
+
+	1. Item 1
+	2. Item 2
+	3. Item 3
+
+It is possible to use any leading number you want. So if you don't want to keep
+your list synchronised, you simple can use any number. In this case it's
+recommended to use `0.`, but it isn't mandatory.
+
+	0. Item 1
+	0. Item 2
+	0. Item 3
+
+Both examples will cause the same result. Even this is possible:
+
+	1000. Item 1
+	432.  Item 2
+	0.    Item 3
+
+This will be the result in these example:
+
+	<ol>
+	<li>Item 1</li>
+	<li>Item 2</li>
+	<li>Item 3</li>
+	</ol>
+
+Code & Blockquote
+-----------------
+
+Use the `> ` as a line prefix for defining blockquotes. Blockquotes are
+interpreted as well. This makes it possible to embed links, headings and even
+other quotes into a quote:
+
+	> Hello
+	> This is a quote with a [link](http://s01.de/~gottox)
+
+Result:
+	<blockquote><p>
+	Hello
+	This is a quote with a <a href="http://s01.de/~gottox">link</a></p>
+	</blockquote>
+
+
+You can define block code with a leading Tab or with __3__ leading spaces
+
+		this.is(code)
+	
+	   this.is(code, too)
+
+Result:
+	<pre><code>this.is(code)</code></pre>
+	<pre><code>this.is(code, too)
+	</code></pre>
+
+Please note that you can't use HTML or smu syntax in a code block.
+
+Other interesting stuff
+-----------------------
+
+* to insert a horizontal rule simple add `- - -` into an empty line:
+
+  	Hello
+  	- - -
+  	Hello2
+
+  Result:
+  	<p>
+  	Hello
+  	<hr />
+  	
+  	Hello2</p>
+
+* You can escape the following pattern to avoid them from being interpreted:
+
+  	\ ` * _ { } [ ] ( ) # + - . !
+
+* To force a linebreak simple add two spaces to the end of the line:
+
+  	No linebreak
+  	here.
+  	But here is  
+  	one.
+
+embed HTML
+----------
diff --git a/smu.1 b/smu.1
@@ -0,0 +1,23 @@
+.TH smu 1 smu\-VERSION
+.SH NAME
+smu \- simple markup
+.SH SYNOPSIS
+.B smu
+.RB [ \-h ]
+.RB [ \-v ]
+.RB [ \-n ]
+.RB [ file ]
+.SH DESCRIPTION
+smu is a simple interpreter for a simplified markdown dialect.
+.SH OPTIONS
+.TP
+.B \-v
+prints version information to standard error, then exits.
+.TP
+.B \-h
+prints usage information to standard error, then exits.
+.TP
+.B \-n
+escapes all HTML Tags.
+.SH BUGS
+Please report any Bugs to https://github.com/Gottox/smu/issues or via mail.
diff --git a/smu.c b/smu.c
@@ -0,0 +1,624 @@
+/* smu - simple markup
+ * Copyright (C) <2007, 2008> Enno Boland <g s01 de>
+ *
+ * See LICENSE for further informations
+ */
+#include <stdarg.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <ctype.h>
+
+#define LENGTH(x)  sizeof(x)/sizeof(x[0])
+#define ADDC(b,i)  if(i % BUFSIZ == 0) { b = realloc(b, (i + BUFSIZ) * sizeof(char)); if(!b) eprint("Malloc failed."); } b[i]
+
+typedef int (*Parser)(const char *, const char *, int);
+typedef struct {
+	char *search;
+	int process;
+	char *before, *after;
+} Tag;
+
+static int doamp(const char *begin, const char *end, int newblock);       /* Parser for & */
+static int docomment(const char *begin, const char *end, int newblock);   /* Parser for html-comments */
+static int dogtlt(const char *begin, const char *end, int newblock);      /* Parser for < and > */
+static int dohtml(const char *begin, const char *end, int newblock);      /* Parser for html */
+static int dolineprefix(const char *begin, const char *end, int newblock);/* Parser for line prefix tags */
+static int dolink(const char *begin, const char *end, int newblock);      /* Parser for links and images */
+static int dolist(const char *begin, const char *end, int newblock);      /* Parser for lists */
+static int doparagraph(const char *begin, const char *end, int newblock); /* Parser for paragraphs */
+static int doreplace(const char *begin, const char *end, int newblock);   /* Parser for simple replaces */
+static int doshortlink(const char *begin, const char *end, int newblock); /* Parser for links and images */
+static int dosurround(const char *begin, const char *end, int newblock);  /* Parser for surrounding tags */
+static int dounderline(const char *begin, const char *end, int newblock); /* Parser for underline tags */
+static void *ereallocz(void *p, size_t size);
+static void hprint(const char *begin, const char *end);                   /* escapes HTML and prints it to output */
+static void process(const char *begin, const char *end, int isblock);     /* Processes range between begin and end. */
+
+/* list of parsers */
+static Parser parsers[] = { dounderline, docomment, dolineprefix,
+                            dolist, doparagraph, dogtlt, dosurround, dolink,
+                            doshortlink, dohtml, doamp, doreplace };
+static int nohtml = 0;
+
+static Tag lineprefix[] = {
+	{ "   ",	0,	"<pre><code>", "</code></pre>" },
+	{ "\t",		0,	"<pre><code>", "</code></pre>" },
+	{ "> ",		2,	"<blockquote>",	"</blockquote>" },
+	{ "###### ",	1,	"<h6>",		"</h6>" },
+	{ "##### ",	1,	"<h5>",		"</h5>" },
+	{ "#### ",	1,	"<h4>",		"</h4>" },
+	{ "### ",	1,	"<h3>",		"</h3>" },
+	{ "## ",	1,	"<h2>",		"</h2>" },
+	{ "# ",		1,	"<h1>",		"</h1>" },
+	{ "- - -\n",	1,	"<hr />",	""},
+};
+
+static Tag underline[] = {
+	{ "=",		1,	"<h1>",		"</h1>\n" },
+	{ "-",		1,	"<h2>",		"</h2>\n" },
+};
+
+static Tag surround[] = {
+	{ "``",		0,	"<code>",	"</code>" },
+	{ "`",		0,	"<code>",	"</code>" },
+	{ "___",	1,	"<strong><em>",	"</em></strong>" },
+	{ "***",	1,	"<strong><em>",	"</em></strong>" },
+	{ "__",		1,	"<strong>",	"</strong>" },
+	{ "**",		1,	"<strong>",	"</strong>" },
+	{ "_",		1,	"<em>",		"</em>" },
+	{ "*",		1,	"<em>",		"</em>" },
+};
+
+static const char *replace[][2] = {
+	{ "\\\\",	"\\" },
+	{ "\\`",	"`" },
+	{ "\\*",	"*" },
+	{ "\\_",	"_" },
+	{ "\\{",	"{" },
+	{ "\\}",	"}" },
+	{ "\\[",	"[" },
+	{ "\\]",	"]" },
+	{ "\\(",	"(" },
+	{ "\\)",	")" },
+	{ "\\#",	"#" },
+	{ "\\+",	"+" },
+	{ "\\-",	"-" },
+	{ "\\.",	"." },
+	{ "\\!",	"!" },
+};
+
+static const char *insert[][2] = {
+	{ "  \n",	"<br />" },
+};
+
+void
+eprint(const char *format, ...) {
+	va_list ap;
+
+	va_start(ap, format);
+	vfprintf(stderr, format, ap);
+	va_end(ap);
+	exit(EXIT_FAILURE);
+}
+
+int
+doamp(const char *begin, const char *end, int newblock) {
+	const char *p;
+
+	if(*begin != '&')
+		return 0;
+	if(!nohtml) {
+		for(p = begin + 1; p != end && !strchr("; \\\n\t", *p); p++);
+		if(p == end || *p == ';')
+			return 0;
+	}
+	fputs("&amp;", stdout);
+	return 1;
+}
+
+int
+dogtlt(const char *begin, const char *end, int newblock) {
+	int brpos;
+	char c;
+
+	if(nohtml || begin + 1 >= end)
+		return 0;
+	brpos = begin[1] == '>';
+	if(!brpos && *begin != '<')
+		return 0;
+	c = begin[brpos ? 0 : 1];
+	if(!brpos && (c < 'a' || c > 'z') && (c < 'A' || c > 'Z')) {
+		fputs("&lt;", stdout);
+		return 1;
+	}
+	else if(brpos && (c < 'a' || c > 'z') && (c < 'A' || c > 'Z') && !strchr("/\"'",c)) {
+		fprintf(stdout, "%c&gt;",c);
+		return 2;
+	}
+	return 0;
+}
+
+int
+docomment(const char *begin, const char *end, int newblock) {
+	char *p;
+
+	if(nohtml || strncmp("<!--", begin, 4))
+		return 0;
+	p = strstr(begin, "-->");
+	if(!p || p + 3 >= end)
+		return 0;
+	return (p + 3 - begin) * (newblock ? -1 : 1);
+}
+
+int
+dohtml(const char *begin, const char *end, int newblock) {
+	const char *p, *tag, *tagend;
+
+	if(nohtml || begin + 2 >= end)
+		return 0;
+	p = begin;
+	if(p[0] != '<' || !isalpha(p[1]))
+		return 0;
+	p++;
+	tag = p;
+	for(; isalnum(*p) && p < end; p++);
+	tagend = p;
+	if(p > end || tag == tagend)
+		return 0;
+	while((p = strstr(p, "</")) && p < end) {
+		p += 2;
+		if(strncmp(p, tag, tagend - tag) == 0 && p[tagend - tag] == '>') {
+			p++;
+			fwrite(begin, sizeof(char), p - begin + tagend - tag + 1, stdout);
+			return p - begin + tagend - tag + 1;
+		}
+	}
+	p = strchr(tagend, '>');
+	if(p) {
+		fwrite(begin, sizeof(char), p - begin + 2, stdout);
+		return p - begin + 2;
+	}
+	else
+		return 0;
+}
+
+int
+dolineprefix(const char *begin, const char *end, int newblock) {
+	unsigned int i, j, l;
+	char *buffer;
+	const char *p;
+
+	if(newblock)
+		p = begin;
+	else if(*begin == '\n')
+		p = begin + 1;
+	else
+		return 0;
+	for(i = 0; i < LENGTH(lineprefix); i++) {
+		l = strlen(lineprefix[i].search);
+		if(end - p < l)
+			continue;
+		if(strncmp(lineprefix[i].search, p, l))
+			continue;
+		if(*begin == '\n')
+			fputc('\n', stdout);
+		fputs(lineprefix[i].before, stdout);
+		if(lineprefix[i].search[l-1] == '\n') {
+			fputc('\n', stdout);
+			return l;
+		}
+		if(!(buffer = malloc(BUFSIZ)))
+			eprint("Malloc failed.");
+		buffer[0] = '\0';
+		for(j = 0, p += l; p < end; p++, j++) {
+			ADDC(buffer, j) = *p;
+			if(*p == '\n' && p + l < end) {
+				if(strncmp(lineprefix[i].search, p + 1, l) != 0)
+					break;
+				p += l;
+			}
+		}
+		ADDC(buffer, j) = '\0';
+		if(lineprefix[i].process)
+			process(buffer, buffer + strlen(buffer), lineprefix[i].process >= 2);
+		else
+			hprint(buffer, buffer + strlen(buffer));
+		puts(lineprefix[i].after);
+		free(buffer);
+		return -(p - begin);
+	}
+	return 0;
+}
+
+int
+dolink(const char *begin, const char *end, int newblock) {
+	int img, len, sep;
+	const char *desc, *link, *p, *q, *descend, *linkend;
+	const char *title = NULL, *titleend = NULL;
+
+	if(*begin == '[')
+		img = 0;
+	else if(strncmp(begin, "![", 2) == 0)
+		img = 1;
+	else
+		return 0;
+	p = desc = begin + 1 + img;
+	if(!(p = strstr(desc, "](")) || p > end)
+		return 0;
+	for(q = strstr(desc, "!["); q && q < end && q < p; q = strstr(q + 1, "!["))
+		if(!(p = strstr(p + 1, "](")) || p > end)
+			return 0;
+	descend = p;
+	link = p + 2;
+	if(!(q = strchr(link, ')')) || q > end)
+		return 0;
+	if((p = strpbrk(link, "\"'")) && p < end && q > p) {
+		sep = p[0]; /* separator: can be " or ' */
+		title = p + 1;
+		/* strip trailing whitespace */
+		for(linkend = p; linkend > link && isspace(*(linkend - 1)); linkend--);
+		if(!(p = strchr(title, sep)) || q > end || p > q)
+			return 0;
+		titleend = p;
+		len = p + 2 - begin;
+	}
+	else {
+		linkend = q;
+		len = q + 1 - begin;
+	}
+	if(img) {
+		fputs("<img src=\"", stdout);
+		hprint(link, linkend);
+		fputs("\" alt=\"", stdout);
+		hprint(desc, descend);
+		fputs("\" ", stdout);
+		if(title && titleend) {
+			fputs("title=\"", stdout);
+			hprint(title, titleend);
+			fputs("\" ", stdout);
+		}
+		fputs("/>", stdout);
+	}
+	else {
+		fputs("<a href=\"", stdout);
+		hprint(link, linkend);
+		fputs("\"", stdout);
+		if(title && titleend) {
+			fputs(" title=\"", stdout);
+			hprint(title, titleend);
+			fputs("\"", stdout);
+		}
+		fputs(">", stdout);
+		process(desc, descend, 0);
+		fputs("</a>", stdout);
+	}
+	return len;
+}
+
+int
+dolist(const char *begin, const char *end, int newblock) {
+	unsigned int i, j, indent, run, ul, isblock;
+	const char *p, *q;
+	char *buffer = NULL;
+
+	isblock = 0;
+	if(newblock)
+		p = begin;
+	else if(*begin == '\n')
+		p = begin + 1;
+	else
+		return 0;
+	q = p;
+	if(*p == '-' || *p == '*' || *p == '+')
+		ul = 1;
+	else {
+		ul = 0;
+		for(; p < end && *p >= '0' && *p <= '9'; p++);
+		if(p >= end || *p != '.')
+			return 0;
+	}
+	p++;
+	if(p >= end || !(*p == ' ' || *p == '\t'))
+		return 0;
+	for(p++; p != end && (*p == ' ' || *p == '\t'); p++);
+	indent = p - q;
+	buffer = ereallocz(buffer, BUFSIZ);
+	if(!newblock)
+		fputc('\n', stdout);
+	fputs(ul ? "<ul>\n" : "<ol>\n", stdout);
+	run = 1;
+	for(; p < end && run; p++) {
+		for(i = 0; p < end && run; p++, i++) {
+			if(*p == '\n') {
+				if(p + 1 == end)
+					break;
+				else if(p[1] == '\n') {
+					p++;
+					ADDC(buffer, i) = '\n';
+					i++;
+					run = 0;
+					isblock++;
+				}
+				q = p + 1;
+				j = 0;
+				if(ul && (*q == '-' || *q == '*' || *q == '+'))
+					j = 1;
+				else if(!ul) {
+					for(; q + j != end && q[j] >= '0' && q[j] <= '9' && j < indent; j++);
+					if(q + j == end)
+						break;
+					if(j > 0 && q[j] == '.')
+						j++;
+					else
+						j = 0;
+				}
+				if(q + indent < end)
+					for(; (q[j] == ' ' || q[j] == '\t') && j < indent; j++);
+				if(j == indent) {
+					ADDC(buffer, i) = '\n';
+					i++;
+					p += indent;
+					run = 1;
+					if(*q == ' ' || *q == '\t')
+						p++;
+					else
+						break;
+				}
+			}
+			ADDC(buffer, i) = *p;
+		}
+		ADDC(buffer, i) = '\0';
+		fputs("<li>", stdout);
+		process(buffer, buffer + i, isblock > 1 || (isblock == 1 && run));
+		fputs("</li>\n", stdout);
+	}
+	fputs(ul ? "</ul>\n" : "</ol>\n", stdout);
+	free(buffer);
+	p--;
+	while(*(--p) == '\n');
+	return -(p - begin + 1);
+}
+
+int
+doparagraph(const char *begin, const char *end, int newblock) {
+	const char *p;
+
+	if(!newblock)
+		return 0;
+	p = strstr(begin, "\n\n");
+	if(!p || p > end)
+		p = end;
+	if(p - begin <= 1)
+		return 0;
+	fputs("<p>", stdout);
+	process(begin, p, 0);
+	fputs("</p>\n", stdout);
+	return -(p - begin);
+}
+
+int
+doreplace(const char *begin, const char *end, int newblock) {
+	unsigned int i, l;
+
+	for(i = 0; i < LENGTH(insert); i++)
+		if(strncmp(insert[i][0], begin, strlen(insert[i][0])) == 0)
+			fputs(insert[i][1], stdout);
+	for(i = 0; i < LENGTH(replace); i++) {
+		l = strlen(replace[i][0]);
+		if(end - begin < l)
+			continue;
+		if(strncmp(replace[i][0], begin, l) == 0) {
+			fputs(replace[i][1], stdout);
+			return l;
+		}
+	}
+	return 0;
+}
+
+int
+doshortlink(const char *begin, const char *end, int newblock) {
+	const char *p, *c;
+	int ismail = 0;
+
+	if(*begin != '<')
+		return 0;
+	for(p = begin + 1; p != end; p++) {
+		switch(*p) {
+		case ' ':
+		case '\t':
+		case '\n':
+			return 0;
+		case '#':
+		case ':':
+			ismail = -1;
+			break;
+		case '@':
+			if(ismail == 0)
+				ismail = 1;
+			break;
+		case '>':
+			if(ismail == 0)
+				return 0;
+			fputs("<a href=\"", stdout);
+			if(ismail == 1) {
+				/* mailto: */
+				fputs("&#x6D;&#x61;i&#x6C;&#x74;&#x6F;:", stdout);
+				for(c = begin + 1; *c != '>'; c++)
+					fprintf(stdout, "&#%u;", *c);
+				fputs("\">", stdout);
+				for(c = begin + 1; *c != '>'; c++)
+					fprintf(stdout, "&#%u;", *c);
+			}
+			else {
+				hprint(begin + 1, p);
+				fputs("\">", stdout);
+				hprint(begin + 1, p);
+			}
+			fputs("</a>", stdout);
+			return p - begin + 1;
+		}
+	}
+	return 0;
+}
+
+int
+dosurround(const char *begin, const char *end, int newblock) {
+	unsigned int i, l;
+	const char *p, *start, *stop;
+
+	for(i = 0; i < LENGTH(surround); i++) {
+		l = strlen(surround[i].search);
+		if(end - begin < 2*l || strncmp(begin, surround[i].search, l) != 0)
+			continue;
+		start = begin + l;
+		p = start - 1;
+		do {
+			stop = p;
+			p = strstr(p + 1, surround[i].search);
+		} while(p && p[-1] == '\\');
+		if (p && p[-1] != '\\')
+			stop = p;
+		if(!stop || stop < start || stop >= end)
+			continue;
+		fputs(surround[i].before, stdout);
+		if(surround[i].process)
+			process(start, stop, 0);
+		else
+			hprint(start, stop);
+		fputs(surround[i].after, stdout);
+		return stop - begin + l;
+	}
+	return 0;
+}
+
+int
+dounderline(const char *begin, const char *end, int newblock) {
+	unsigned int i, j, l;
+	const char *p;
+
+	if(!newblock)
+		return 0;
+	p = begin;
+	for(l = 0; p + l != end && p[l] != '\n'; l++);
+	p += l + 1;
+	if(l == 0)
+		return 0;
+	for(i = 0; i < LENGTH(underline); i++) {
+		for(j = 0; p + j != end && p[j] != '\n' && p[j] == underline[i].search[0]; j++);
+		if(j >= l) {
+			fputs(underline[i].before, stdout);
+			if(underline[i].process)
+				process(begin, begin + l, 0);
+			else
+				hprint(begin, begin + l);
+			fputs(underline[i].after, stdout);
+			return -(j + p - begin);
+		}
+	}
+	return 0;
+}
+
+void *
+ereallocz(void *p, size_t size) {
+	void *res;
+	if(p)
+		res = realloc(p , size);
+	else
+		res = calloc(1, size);
+
+	if(!res)
+		eprint("fatal: could not malloc() %u bytes\n", size);
+	return res;
+}
+
+void
+hprint(const char *begin, const char *end) {
+	const char *p;
+
+	for(p = begin; p != end; p++) {
+		if(*p == '&')
+			fputs("&amp;", stdout);
+		else if(*p == '"')
+			fputs("&quot;", stdout);
+		else if(*p == '>')
+			fputs("&gt;", stdout);
+		else if(*p == '<')
+			fputs("&lt;", stdout);
+		else
+			fputc(*p, stdout);
+	}
+}
+
+void
+process(const char *begin, const char *end, int newblock) {
+	const char *p, *q;
+	int affected;
+	unsigned int i;
+
+	for(p = begin; p < end;) {
+		if(newblock)
+			while(*p == '\n')
+				if(++p == end)
+					return;
+		affected = 0;
+		for(i = 0; i < LENGTH(parsers) && !affected; i++)
+			affected = parsers[i](p, end, newblock);
+		p += abs(affected);
+		if(!affected) {
+			if(nohtml)
+				hprint(p, p + 1);
+			else
+				fputc(*p, stdout);
+			p++;
+		}
+		for(q = p; q != end && *q == '\n'; q++);
+		if(q == end)
+			return;
+		else if(p[0] == '\n' && p + 1 != end && p[1] == '\n')
+			newblock = 1;
+		else
+			newblock = affected < 0;
+	}
+}
+
+int
+main(int argc, char *argv[]) {
+	char *buffer = NULL;
+	int s, i;
+	unsigned long len, bsize;
+	FILE *source = stdin;
+
+	for(i = 1; i < argc; i++) {
+		if(!strcmp("-v", argv[i]))
+			eprint("simple markup %s (C) Enno Boland\n",VERSION);
+		else if(!strcmp("-n", argv[i]))
+			nohtml = 1;
+		else if(argv[i][0] != '-')
+			break;
+		else if(!strcmp("--", argv[i])) {
+			i++;
+			break;
+		}
+		else
+			eprint("Usage %s [-n] [file]\n -n escape html strictly\n", argv[0]);
+	}
+	if(i < argc && !(source = fopen(argv[i], "r")))
+		eprint("Cannot open file `%s`\n",argv[i]);
+	bsize = 2 * BUFSIZ;
+	buffer = ereallocz(buffer, bsize);
+	len = 0;
+	while((s = fread(buffer + len, 1, BUFSIZ, source))) {
+		len += s;
+		if(BUFSIZ + len + 1 > bsize) {
+			bsize += BUFSIZ;
+			if(!(buffer = realloc(buffer, bsize)))
+				eprint("realloc failed.");
+		}
+	}
+	buffer[len] = '\0';
+	process(buffer, buffer + len, 1);
+	fclose(source);
+	free(buffer);
+	return EXIT_SUCCESS;
+}
diff --git a/smu.h b/smu.h
@@ -0,0 +1,19 @@
+/* libsmu - simple markup library
+ * Copyright (C) <2007, 2008> Enno Boland <g s01 de>
+ *
+ * See LICENSE for further informations
+ */
+#include <stdio.h>
+
+/**
+ * Converts contents of a simple markup stream (in) and prints them to out.
+ * If suppresshtml == 1, it will create plain text of the simple markup instead
+ * of HTML.
+ *
+ * Returns 0 on success.
+ */
+int smu_convert(FILE *out, FILE *in, int suppresshtml);
+
+/** utility */
+void eprint(const char *format, ...);
+
diff --git a/testdoc b/testdoc
@@ -0,0 +1,80 @@
+smu test
+========
+
+simple tests
+------------
+
+first paragraph.
+testing surround: _emph_ then **strong** and `code`.
+
+`\`escaped backticks\``.
+
+`x = *y * 6;`
+
+horizontal rule:
+
+- - -
+
+
+blocks and entities
+-------------------
+
+preformatted block:
+	.'''' .'.'. |  |
+	 '''. | ' | |  |
+	''''  '   '  ""
+
+quoted text:
+> When in doubt,
+> use brute force.
+
+list:
+* Make each program do one thing well.
+* Expect the output of every program to become the input to another,
+as yet unknown, program.
+* Design and build software, even operating systems, to be tried early,
+ideally within weeks.
+* Use tools in preference to unskilled help to lighten a programming task.
+
+list in list:
+* a
+  * b
+    1. c
+    2. d
+  * e
+* f
+
+entity: &, <, >
+
+code:
+	int powerof2(unsigned int n) {
+		return !((n - 1) & n) && n > 0;
+	}
+
+links
+-----
+
+link: [suckless](http://suckless.org/)
+
+link with title: [suckless](http://suckless.org/ "software that sucks less")
+
+link with title (single quote): [suckless](http://suckless.org/ 'software that sucks less')
+
+
+images
+------
+
+image: ![](http://st.suckless.org/screenshots/20h-2012-s.png)
+
+image with alt text: ![alt text](http://st.suckless.org/screenshots/20h-2012-s.png)
+
+image with title: ![alt text](http://st.suckless.org/screenshots/20h-2012-s.png "screenshot of st")
+
+image with title (single quote): ![alt text](http://st.suckless.org/screenshots/20h-2012-s.png 'screenshot of st')
+
+inline html
+-----------
+
+<center>
+	ABC
+</center>