From 18afdf13c0278e5c283640cc0e923481f3370972 Mon Sep 17 00:00:00 2001 From: Bradley Taunt Date: Fri, 2 Feb 2024 12:48:04 -0500 Subject: [PATCH] Initial commit for cgit platform --- .gitignore | 2 + LICENSE | 21 + Makefile | 71 ++ README | 258 ++++++ config.mk | 20 + docs/index.html | 236 ++++++ smu.1 | 23 + smu.c | 791 ++++++++++++++++++ smu.h | 19 + tests/code_fence.html | 25 + tests/code_fence.text | 37 + tests/commonmark/backslash_escapes.html | 3 + tests/commonmark/backslash_escapes.text | 5 + tests/html.html | 7 + tests/html.text | 10 + tests/linebreak.html | 2 + tests/linebreak.text | 2 + tests/lists.html | 14 + tests/lists.text | 10 + tests/mdtest/Amps_and_angle_encoding.html | 6 + tests/mdtest/Amps_and_angle_encoding.text | 12 + tests/mdtest/Auto_links.html | 12 + tests/mdtest/Auto_links.text | 13 + .../mdtest/Blockquotes_with_code_blocks.html | 11 + .../mdtest/Blockquotes_with_code_blocks.text | 11 + tests/mdtest/Code_Blocks.html | 12 + tests/mdtest/Code_Blocks.text | 14 + tests/mdtest/Code_Spans.html | 3 + tests/mdtest/Code_Spans.text | 5 + tests/mdtest/Inline_HTML_comments.html | 8 + tests/mdtest/Inline_HTML_comments.text | 13 + tests/mdtest/LICENSE | 339 ++++++++ tests/mdtest/Links,_inline_style.html | 12 + tests/mdtest/Links,_inline_style.text | 24 + tests/mdtest/Literal_quotes_in_titles.html | 1 + tests/mdtest/Literal_quotes_in_titles.text | 1 + tests/mdtest/Nested_blockquotes.html | 5 + tests/mdtest/Nested_blockquotes.text | 5 + tests/mdtest/Ordered_and_unordered_lists.html | 129 +++ tests/mdtest/Ordered_and_unordered_lists.text | 122 +++ tests/mdtest/README.md | 1 + tests/mdtest/Strong_and_em_together.html | 4 + tests/mdtest/Strong_and_em_together.text | 7 + tests/mdtest/Tabs.html | 21 + tests/mdtest/Tabs.text | 21 + tests/mdtest/Tidyness.html | 7 + tests/mdtest/Tidyness.text | 5 + tests/nohtml/basic.html | 7 + tests/nohtml/basic.text | 7 + tests/old_readme.html | 220 +++++ tests/old_readme.text | 238 ++++++ tests/ruler.html | 9 + tests/ruler.text | 11 + tests/table.html | 9 + tests/table.text | 10 + tests/testdoc.html | 72 ++ tests/testdoc.text | 80 ++ tests/unicode.html | 2 + tests/unicode.text | 5 + 59 files changed, 3050 insertions(+) create mode 100644 .gitignore create mode 100644 LICENSE create mode 100644 Makefile create mode 100644 README create mode 100644 config.mk create mode 100644 docs/index.html create mode 100644 smu.1 create mode 100644 smu.c create mode 100644 smu.h create mode 100644 tests/code_fence.html create mode 100644 tests/code_fence.text create mode 100644 tests/commonmark/backslash_escapes.html create mode 100644 tests/commonmark/backslash_escapes.text create mode 100644 tests/html.html create mode 100644 tests/html.text create mode 100644 tests/linebreak.html create mode 100644 tests/linebreak.text create mode 100644 tests/lists.html create mode 100644 tests/lists.text create mode 100644 tests/mdtest/Amps_and_angle_encoding.html create mode 100644 tests/mdtest/Amps_and_angle_encoding.text create mode 100644 tests/mdtest/Auto_links.html create mode 100644 tests/mdtest/Auto_links.text create mode 100644 tests/mdtest/Blockquotes_with_code_blocks.html create mode 100644 tests/mdtest/Blockquotes_with_code_blocks.text create mode 100644 tests/mdtest/Code_Blocks.html create mode 100644 tests/mdtest/Code_Blocks.text create mode 100644 tests/mdtest/Code_Spans.html create mode 100644 tests/mdtest/Code_Spans.text create mode 100644 tests/mdtest/Inline_HTML_comments.html create mode 100644 tests/mdtest/Inline_HTML_comments.text create mode 100644 tests/mdtest/LICENSE create mode 100644 tests/mdtest/Links,_inline_style.html create mode 100644 tests/mdtest/Links,_inline_style.text create mode 100644 tests/mdtest/Literal_quotes_in_titles.html create mode 100644 tests/mdtest/Literal_quotes_in_titles.text create mode 100644 tests/mdtest/Nested_blockquotes.html create mode 100644 tests/mdtest/Nested_blockquotes.text create mode 100644 tests/mdtest/Ordered_and_unordered_lists.html create mode 100644 tests/mdtest/Ordered_and_unordered_lists.text create mode 100644 tests/mdtest/README.md create mode 100644 tests/mdtest/Strong_and_em_together.html create mode 100644 tests/mdtest/Strong_and_em_together.text create mode 100644 tests/mdtest/Tabs.html create mode 100644 tests/mdtest/Tabs.text create mode 100644 tests/mdtest/Tidyness.html create mode 100644 tests/mdtest/Tidyness.text create mode 100644 tests/nohtml/basic.html create mode 100644 tests/nohtml/basic.text create mode 100644 tests/old_readme.html create mode 100644 tests/old_readme.text create mode 100644 tests/ruler.html create mode 100644 tests/ruler.text create mode 100644 tests/table.html create mode 100644 tests/table.text create mode 100644 tests/testdoc.html create mode 100644 tests/testdoc.text create mode 100644 tests/unicode.html create mode 100644 tests/unicode.text diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000..dc6a1ca --- /dev/null +++ b/.gitignore @@ -0,0 +1,2 @@ +smu.o +smu diff --git a/LICENSE b/LICENSE new file mode 100644 index 0000000..5956c4f --- /dev/null +++ b/LICENSE @@ -0,0 +1,21 @@ +MIT/X Consortium License + +(c) 2007-2014 Enno Boland + +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 new file mode 100644 index 0000000..38039e8 --- /dev/null +++ b/Makefile @@ -0,0 +1,71 @@ +# libsmu - simple markup +# (c) 2007, 2008 Enno Boland + +include config.mk + +SRC = smu.c +OBJ = ${SRC:.c=.o} +# VALGRIND = valgrind -q --error-exitcode=1 + +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 + +test: $(patsubst %.text,%.html,$(wildcard tests/*.text tests/*/*.text)) + git diff --exit-code -- tests + +docs: docs/index.html + +docs/index.html: README smu + ./smu $< > $@ + +tests/nohtml/%.html: tests/nohtml/%.text smu + ${VALGRIND} ./smu -n $< > $@ + +%.html: %.text smu + ${VALGRIND} ./smu $< > $@ + +.PHONY: all options clean dist install uninstall +.DELETE_ON_ERROR: diff --git a/README b/README new file mode 100644 index 0000000..cfe91c7 --- /dev/null +++ b/README @@ -0,0 +1,258 @@ +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. + +Syntax +====== + +smu was started as a rewrite of +[markdown](http://daringfireball.net/projects/markdown/) but became something +more lightweight and consistent. It differs from [CommonMark](https://commonmark.org/) in the following ways: + +* No support for _reference style links_ +* Stricter indentation rules for lists +* Lists don't end paragraphs by themselves (blank line needed) +* Horizontal rules (`
`) must use `- - -` as syntax +* Code fences have stricter syntax + +Patches that increase the CommonMark compatibility are welcome as long as they don't increase the code complexity significantly. + +This project is a fork of the [original smu](https://github.com/gottox/smu) by +[Enno Boland (gottox)](https://eboland.de). The main differences to the +original smu are: + +* Support for code fences +* Improved [CommonMark](https://commonmark.org/) compatibility. E.g. + * Code blocks need four spaces indentation instead of three + * Skip empty lines at end of code blocks + * Ignore single spaces around code spans + * Keep HTML comments in output + * Improved spec compliance for lists + * Nesting code block in blockquotes works + * "Empty" lines in lists behave identically, no matter how much whitespace they contain + * No backslash escapes in code blocks + * Use first number as start number for ordered lists +* Added a simple test suite to check for compliance and avoid regressions + +Inline patterns +--------------- + +There are several patterns 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 by surrounding it with backticks. + + Use `rm -rf /` if you're a N00b. + Use ``rm -rf /`` if you're a N00b. + Use ```rm -rf /``` if you're a N00b. + + Double and triple backticks can be used if the code itself contains backticks. + + +Titles +------ + +Creating titles in smu is very easy. There are two different syntax styles. The +first is underlining with at least three characters: + + Heading + ======= + + Topic + ----- + +This is very intuitive and self explaining. The resulting sourcecode looks like +this: + +

Heading

+

Topic

+ +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 `<>`. + + + +You can do the same for E-Mail addresses: + + + +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 + + smu - simple mark up

+ +Lists +----- + +Defining lists is very straightforward: + + * Item 1 + * Item 2 + * Item 3 + +Result: + +
    +
  • Item 1
    • +
  • Item 2
    • +
  • Item 3
    • +
+ +Defining ordered lists is also very easy: + + 1. Item 1 + 2. Item 2 + 3. Item 3 + +Only the first number in a list is meaningful. All following list items are +continously counted. If you want a list starting at 2, you could write: + + 2. Item 1 + 2. Item 2 + 2. Item 3 + +and get the following HTML which will render with the numbers 2, 3, 4: + +
    +
  1. Item 1
    2. +
  2. Item 2
    3. +
  3. Item 3
    4. +
+ +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: +

+ Hello + This is a quote with a link

+
+ + +You can define a code block with a leading Tab or with __4__ leading spaces + + this.is(code) + + this.is(code, too) + +Result: + 
this.is(code)
+ 
this.is(code, too)
+
+ +Please note that you can't use HTML or smu syntax in a code block. + +Another way to write code blocks is to use code fences: + + ```json + {"some": "code"} + ``` + +This has two advantages: +* The optional language identifier will be turned into a `language-` class name +* You can keep the original indentation which helps when doing copy & paste + +Tables +------ + +Tables can be generated with the following syntax: + + | Heading1 | Heading2 | + | -------- | -------- | + | Cell 1 | Cell2 | + +Aligning the columns make the input nicer to read, but is not necessary to get +correct table output. You could just write + + | Heading1 | Heading2 | + | --- | --- | + | Cell 1 | Cell2 | + +To align the content of table cells, use `|:--|` for left, `|--:|` for right +and `|:--:|` for centered alignment in the row which separates the header from +the table body. + + | Heading1 | Heading2 | Heading3 | + | :------- | :------: | -------: | + | Left | Center | Right | + +Other interesting stuff +----------------------- + +* to insert a horizontal rule simple add `- - -` into an empty line: + + Hello + - - - + Hello2 + + Result: +

+ Hello +

+ + Hello2

+ +* Any ASCII punctuation character may escaped by precedeing them with a + backslash to avoid them 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 +---------- + +You can include arbitrary HTML code in your documents. The HTML will be +passed through to the resulting document without modification. This is a good +way to work around features that are missing in smu. If you don't want this +behaviour, use the `-n` flag when executing smu to stricly escape the HTML +tags. diff --git a/config.mk b/config.mk new file mode 100644 index 0000000..a41c92f --- /dev/null +++ b/config.mk @@ -0,0 +1,20 @@ +# smu version +VERSION = 1.5 + +# 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}\" -Wstrict-prototypes +#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/docs/index.html b/docs/index.html new file mode 100644 index 0000000..51bfc42 --- /dev/null +++ b/docs/index.html @@ -0,0 +1,236 @@ +

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.

+

Syntax

+

smu was started as a rewrite of +markdown but became something +more lightweight and consistent. It differs from CommonMark in the following ways:

+
    +
  • No support for reference style links
    • +
  • Stricter indentation rules for lists
    • +
  • Lists don't end paragraphs by themselves (blank line needed)
    • +
  • Horizontal rules (<hr>) must use - - - as syntax
    • +
  • Code fences have stricter syntax
    • +
+

Patches that increase the CommonMark compatibility are welcome as long as they don't increase the code complexity significantly.

+

This project is a fork of the original smu by +Enno Boland (gottox). The main differences to the +original smu are:

+
    +
  • Support for code fences
    • +
  • Improved CommonMark compatibility. E.g. +
      +
    • Code blocks need four spaces indentation instead of three
      • +
    • Skip empty lines at end of code blocks
      • +
    • Ignore single spaces around code spans
      • +
    • Keep HTML comments in output
      • +
    • Improved spec compliance for lists
      • +
    • Nesting code block in blockquotes works
      • +
    • "Empty" lines in lists behave identically, no matter how much whitespace they contain
      • +
    • No backslash escapes in code blocks
      • +
    • Use first number as start number for ordered lists
      • +
    +
    • +
  • Added a simple test suite to check for compliance and avoid regressions
    • +
+

Inline patterns

+

There are several patterns 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 by surrounding it with backticks.

    +
    Use `rm -rf /` if you're a N00b.
+Use ``rm -rf /`` if you're a N00b.
+Use ```rm -rf /``` if you're a N00b.
+
    +

    Double and triple backticks can be used if the code itself contains backticks.

    +
    • +
+

Titles

+

Creating titles in smu is very easy. There are two different syntax styles. The +first is underlining with at least three characters:

+
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
+
+

Only the first number in a list is meaningful. All following list items are +continously counted. If you want a list starting at 2, you could write:

+
2. Item 1
+2. Item 2
+2. Item 3
+
+

and get the following HTML which will render with the numbers 2, 3, 4:

+
<ol start="2">
+<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 a code block with a leading Tab or with 4 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.

+

Another way to write code blocks is to use code fences:

+
```json
+{"some": "code"}
+```
+
+

This has two advantages:

+ +
    +
  • The optional language identifier will be turned into a language- class name
    • +
  • You can keep the original indentation which helps when doing copy & paste
    • +
+

Tables

+

Tables can be generated with the following syntax:

+ + + +
Heading1 Heading2
Cell 1 Cell2
+

Aligning the columns make the input nicer to read, but is not necessary to get +correct table output. You could just write

+ + + +
Heading1 Heading2
Cell 1 Cell2
+

To align the content of table cells, use |:--| for left, |--:| for right +and |:--:| for centered alignment in the row which separates the header from +the table body.

+ + + +
Heading1 Heading2 Heading3
Left Center Right
+

Other interesting stuff

+
    +

  • to insert a horizontal rule simple add - - - into an empty line:

    +
    Hello
+- - -
+Hello2
+
    +

    Result: +

    +
    <p>
+Hello
+<hr />
+
    +
    Hello2</p>
+
    +
    • +

  • Any ASCII punctuation character may escaped by precedeing them with a +backslash to avoid them 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

+

You can include arbitrary HTML code in your documents. The HTML will be +passed through to the resulting document without modification. This is a good +way to work around features that are missing in smu. If you don't want this +behaviour, use the -n flag when executing smu to stricly escape the HTML +tags.

diff --git a/smu.1 b/smu.1 new file mode 100644 index 0000000..3ddd112 --- /dev/null +++ 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 new file mode 100644 index 0000000..63e1977 --- /dev/null +++ b/smu.c @@ -0,0 +1,791 @@ +/* smu - simple markup + * Copyright (C) <2007, 2008> Enno Boland + * 2019-2022 Karl Bartel + * 2022 bzt + * + * See LICENSE for further informations + */ +#include +#include +#include +#include +#include +#include + +#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 docomment(const char *begin, const char *end, int newblock); /* Parser for html-comments */ +static int docodefence(const char *begin, const char *end, int newblock); /* Parser for code fences */ +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 dotable(const char *begin, const char *end, int newblock); /* Parser for tables */ +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, docodefence, dolineprefix, + dolist, dotable, doparagraph, dosurround, dolink, + doshortlink, dohtml, doreplace }; +static int nohtml = 0; +static int in_paragraph = 0; + +regex_t p_end_regex; /* End of paragraph */ + +static Tag lineprefix[] = { + { " ", 0, "
", "\n
" }, + { "\t", 0, "
", "\n
" }, + { ">", 2, "
", "
" }, + { "###### ", 1, "
", "
" }, + { "##### ", 1, "
", "
" }, + { "#### ", 1, "

", "

" }, + { "### ", 1, "

", "

" }, + { "## ", 1, "

", "

" }, + { "# ", 1, "

", "

" }, + { "- - -\n", 1, "
", ""}, + { "---\n", 1, "
", ""}, +}; + +static Tag underline[] = { + { "=", 1, "

", "

\n" }, + { "-", 1, "

", "

\n" }, +}; + +static Tag surround[] = { + { "```", 0, "", "" }, + { "``", 0, "", "" }, + { "`", 0, "", "" }, + { "___", 1, "", "" }, + { "***", 1, "", "" }, + { "__", 1, "", "" }, + { "**", 1, "", "" }, + { "_", 1, "", "" }, + { "*", 1, "", "" }, +}; + +static const char *replace[][2] = { + /* Backslash escapes */ + { "\\\\", "\\" }, + { "\\`", "`" }, + { "\\*", "*" }, + { "\\_", "_" }, + { "\\{", "{" }, + { "\\}", "}" }, + { "\\[", "[" }, + { "\\]", "]" }, + { "\\(", "(" }, + { "\\)", ")" }, + { "\\#", "#" }, + { "\\+", "+" }, + { "\\-", "-" }, + { "\\.", "." }, + { "\\!", "!" }, + { "\\\"", """ }, + { "\\$", "$" }, + { "\\%", "%" }, + { "\\&", "&" }, + { "\\'", "'" }, + { "\\,", "," }, + { "\\-", "-" }, + { "\\.", "." }, + { "\\/", "/" }, + { "\\:", ":" }, + { "\\;", ";" }, + { "\\<", "<" }, + { "\\>", ">" }, + { "\\=", "=" }, + { "\\?", "?" }, + { "\\@", "@" }, + { "\\^", "^" }, + { "\\|", "|" }, + { "\\~", "~" }, + /* HTML syntax symbols that need to be turned into entities */ + { "<", "<" }, + { ">", ">" }, + { "&", "&" }, /* Avoid replacing the & in & */ + { "&", "&" }, + /* Preserve newlines with two spaces before linebreak */ + { " \n", "
\n" }, +}; + +static const char *code_fence = "```"; + +void +eprint(const char *format, ...) { + va_list ap; + + va_start(ap, format); + vfprintf(stderr, format, ap); + va_end(ap); + exit(EXIT_FAILURE); +} + +void end_paragraph(void) { + if (in_paragraph) { + fputs("

\n", stdout); + in_paragraph = 0; + } +} + +int +docomment(const char *begin, const char *end, int newblock) { + char *p; + + if (nohtml || strncmp(""); + if (!p || p + 3 >= end) + return 0; + fprintf(stdout, "%.*s\n", (int)(p + 3 - begin), begin); + return (p + 3 - begin) * (newblock ? -1 : 1); +} + +int +docodefence(const char *begin, const char *end, int newblock) { + const char *p, *start, *stop, *lang_start, *lang_stop; + unsigned int l = strlen(code_fence); + + if (!newblock) + return 0; + + if (strncmp(begin, code_fence, l) != 0) + return 0; + + /* Find start of content and read language string */ + start = begin + l; + lang_start = start; + while (start[0] != '\n') + start++; + lang_stop = start; + start++; + + /* Find end of fence */ + p = start - 1; + do { + stop = p; + p = strstr(p + 1, code_fence); + } while (p && p[-1] == '\\'); + if (p && p[-1] != '\\') + stop = p; + + /* No closing code fence means the rest of file is code (CommonMark) */ + if (!p) + stop = end; + + /* Print output */ + if (lang_start == lang_stop) { + fputs("
", stdout);
+	} else {
+		fputs("
", stdout);
+	}
+	hprint(start, stop);
+	fputs("
\n", stdout);
+	return -(stop - begin + l);
+}
+
+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++;
+			fwrite(begin, sizeof(char), p - begin + tagend - tag, stdout);
+			return p - begin + tagend - tag;
+		}
+	}
+	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;
+	int consumed_input = 0;
+
+	if (newblock)
+		p = begin;
+	else if (*begin == '\n') {
+		p = begin + 1;
+		consumed_input += 1;
+	} else
+		return 0;
+	for (i = 0; i < LENGTH(lineprefix); i++) {
+		l = strlen(lineprefix[i].search);
+		if (end - p + 1 < l)
+			continue;
+		if (strncmp(lineprefix[i].search, p, l))
+			continue;
+		if (*begin == '\n')
+			fputc('\n', stdout);
+
+		/* All line prefixes add a block element. These are not allowed
+		 * inside paragraphs, so we must end the paragraph first. */
+		end_paragraph();
+
+		fputs(lineprefix[i].before, stdout);
+		if (lineprefix[i].search[l-1] == '\n') {
+			fputc('\n', stdout);
+			return l - 1 + consumed_input;
+		}
+		if (!(buffer = malloc(BUFSIZ)))
+			eprint("Malloc failed.");
+		buffer[0] = '\0';
+
+		/* Collect lines into buffer while they start with the prefix */
+		j = 0;
+		while ((strncmp(lineprefix[i].search, p, l) == 0) && p + l < end) {
+			p += l;
+
+			/* Special case for blockquotes: optional space after > */
+			if (lineprefix[i].search[0] == '>' && *p == ' ') {
+				p++;
+			}
+
+			while (p < end) {
+				ADDC(buffer, j) = *p;
+				j++;
+				if (*(p++) == '\n')
+					break;
+			}
+		}
+
+		/* Skip empty lines in block */
+		while (*(buffer + j - 1) == '\n') {
+			j--;
+		}
+
+		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, parens_depth = 1;
+	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;
+
+	/* find end of link while handling nested parens */
+	q = link;
+	while (parens_depth) {
+		if (!(q = strpbrk(q, "()")) || q > end)
+			return 0;
+		if (*q == '(')
+			parens_depth++;
+		else
+			parens_depth--;
+		if (parens_depth && q < end)
+			q++;
+	}
+
+	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--);
+		for (titleend = q - 1; titleend > link && isspace(*(titleend)); titleend--);
+		if (titleend < title || *titleend != sep) {
+			return 0;
+		}
+	}
+	else {
+		linkend = q;
+	}
+
+	/* Links can be given in angular brackets */
+	if (*link == '<' && *(linkend - 1) == '>') {
+		link++;
+		linkend--;
+	}
+
+	len = q + 1 - begin;
+	if (img) {
+		fputs("\"",", stdout);
+	}
+	else {
+		fputs("", stdout);
+		process(desc, descend, 0);
+		fputs("", stdout);
+	}
+	return len;
+}
+
+int
+dolist(const char *begin, const char *end, int newblock) {
+	unsigned int i, j, indent, run, isblock, start_number;
+	const char *p, *q, *num_start;
+	char *buffer = NULL;
+	char marker = '\0';  /* Bullet symbol or \0 for unordered lists */
+
+	isblock = 0;
+	if (newblock)
+		p = begin;
+	else if (*begin == '\n')
+		p = begin + 1;
+	else
+		return 0;
+	q = p;
+	if (*p == '-' || *p == '*' || *p == '+') {
+		marker = *p;
+	} else {
+		num_start = p;
+		for (; p < end && *p >= '0' && *p <= '9'; p++);
+		if (p >= end || *p != '.')
+			return 0;
+		start_number = atoi(num_start);
+	}
+	p++;
+	if (p >= end || !(*p == ' ' || *p == '\t'))
+		return 0;
+
+	end_paragraph();
+
+	for (p++; p != end && (*p == ' ' || *p == '\t'); p++);
+	indent = p - q;
+	buffer = ereallocz(buffer, BUFSIZ);
+	if (!newblock)
+		fputc('\n', stdout);
+
+	if (marker) {
+		fputs("
    \n", stdout);
+	} else if (start_number == 1) {
+		fputs("
      \n", stdout);
+	} else {
+		printf("
        \n", start_number);
+	}
+	run = 1;
+	for (; p < end && run; p++) {
+		for (i = 0; p < end && run; p++, i++) {
+			if (*p == '\n') {
+				if (p + 1 == end)
+					break;
+				else {
+					/* Handle empty lines */
+					for (q = p + 1; (*q == ' ' || *q == '\t') && q < end; q++);
+					if (*q == '\n') {
+						ADDC(buffer, i) = '\n';
+						i++;
+						run = 0;
+						isblock++;
+						p = q;
+					}
+				}
+				q = p + 1;
+				j = 0;
+				if (marker && *q == marker)
+					j = 1;
+				else {
+					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;
+				}
+				else if (j < indent)
+					run = 0;
+			}
+			ADDC(buffer, i) = *p;
+		}
+		ADDC(buffer, i) = '\0';
+		fputs("
      1. ", stdout);
+		process(buffer, buffer + i, isblock > 1 || (isblock == 1 && run));
+		fputs("
        2. \n", stdout);
+	}
+	fputs(marker ? "
\n" : "\n", stdout);
+	free(buffer);
+	p--;
+	while (*(--p) == '\n');
+	return -(p - begin + 1);
+}
+
+/* smu table parser, Copyright(C) bzt 2022 MIT */
+
+static char intable = 0, inrow, incell;                         /* table state */
+static long int calign;
+
+int
+dotable(const char *begin, const char *end, int newblock) {
+    const char *p;
+    int i, l = (int)sizeof(calign) * 4;
+
+    if(*begin != '|')
+        return 0;
+    if(inrow && (begin + 1 >= end || begin[1] == '\n')) {       /* close cell and row and if ends, table too */
+        fprintf(stdout, "", inrow == -1 ? 'h' : 'd');
+        inrow = 0;
+        if(begin + 2 >= end || begin[2] == '\n') {
+            intable = 0;
+            fputs("\n", stdout);
+            return 2;
+        }
+        return 1;
+    }
+    if(begin < end && (begin[1] == '-' || begin[1] == ':')) {   /* only load cell aligns from 2nd line */
+        for(i = -1, p = begin; p < end && *p != '\n'; p++)
+            if(*p == '|') {
+                i++;
+                if(i < l && p[1] == ':') {
+                    calign |= 1 << (i * 2); p++;
+                }
+            } else
+            if(i < l && *p == ':')
+                calign |= 1 << (i * 2 + 1);
+        return p - begin + 1;
+    }
+    if(!intable) {                                              /* open table */
+        intable = 1; inrow = -1; incell = 0; calign = 0;
+        fputs("\n", stdout);
+    }
+    if(!inrow) {                                                /* open row */
+        inrow = 1; incell = 0;
+        fputs("", stdout);
+    }
+    if(incell)                                                  /* close cell */
+        fprintf(stdout, "", inrow == -1 ? 'h' : 'd');
+    l = incell < l ? (calign >> (incell * 2)) & 3 : 0;          /* open cell */
+    fprintf(stdout, "", inrow == -1 ? 'h' : 'd',
+        l == 2 ? " class=\"right\"" : (l == 3 ? " class=\"center\"" : ""));
+    incell++;
+    for(p = begin + 1; p < end && *p == ' '; p++);
+    return p - begin;
+}
+
+int
+doparagraph(const char *begin, const char *end, int newblock) {
+	const char *p;
+	regmatch_t match;
+
+	if (!newblock)
+		return 0;
+	if (regexec(&p_end_regex, begin + 1, 1, &match, 0)) {
+		p = end;
+	} else {
+		p = begin + 1 + match.rm_so;
+	}
+
+	fputs("
", stdout);
+	in_paragraph = 1;
+	process(begin, p, 0);
+	end_paragraph();
+
+	return -(p - begin);
+}
+
+int
+doreplace(const char *begin, const char *end, int newblock) {
+	unsigned int i, l;
+
+	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("", stdout);
+				for (c = begin + 1; *c != '>'; c++)
+					fprintf(stdout, "&#%u;", *c);
+			}
+			else {
+				hprint(begin + 1, p);
+				fputs("\">", stdout);
+				hprint(begin + 1, p);
+			}
+			fputs("", 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;
+		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);
+
+		/* Single space at start and end are ignored */
+		if (start[0] == ' ' && stop[-1] == ' ' && start < stop - 1) {
+			start++;
+			stop--;
+			l++;
+		}
+
+		if (surround[i].process)
+			process(start, stop, 0);
+		else
+			hprint(start, stop);
+		fputs(surround[i].after, stdout);
+		return stop - start + 2 * 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 >= 3) {
+			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;
+	res = realloc(p, size);
+	if (!res)
+		eprint("realloc: %zu 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("&", stdout);
+		else if (*p == '"')
+			fputs(""", stdout);
+		else if (*p == '>')
+			fputs(">", stdout);
+		else if (*p == '<')
+			fputs("<", stdout);
+		else
+			fputc(*p, stdout);
+	}
+}
+
+void
+process(const char *begin, const char *end, int newblock) {
+	const char *p;
+	int affected;
+	unsigned int i;
+
+	for (p = begin; p < end;) {
+		if (newblock)
+			while (*p == '\n')
+				if (++p == end)
+					return;
+
+		for (i = 0; i < LENGTH(parsers); i++)
+			if ((affected = parsers[i](p, end, newblock)))
+				break;
+		if (affected)
+			p += abs(affected);
+		else
+			fputc(*p++, stdout);
+
+		/* Don't print single newline at end */
+		if (p + 1 == end && *p == '\n')
+			return;
+
+		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;
+
+	regcomp(&p_end_regex, "(\n\n|(^|\n)```)", REG_EXTENDED);
+
+	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
new file mode 100644
index 0000000..6a54043
--- /dev/null
+++ b/smu.h
@@ -0,0 +1,19 @@
+/* libsmu - simple markup library
+ * Copyright (C) <2007, 2008> Enno Boland 
+ *
+ * See LICENSE for further informations
+ */
+#include 
+
+/**
+ * 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/tests/code_fence.html b/tests/code_fence.html
new file mode 100644
index 0000000..d0d3629
--- /dev/null
+++ b/tests/code_fence.html
@@ -0,0 +1,25 @@
+
code blocks can start in the first line
+

+
This is a code block

+
foo bar
+eggs bacon
+

+
They are allowed to start within a block:

+
foo
+

+
Code blocks can contain empty lines

+
before empty line
+
+after empty line
+

+
Language info strings will add a class to the code block

+
#!/bin/sh
+ls -la .
+

+
Accidental code fences can be avoided by escaping
+```
+like this.
+```

+
According to commonmark, a code block that is not terminated will continue until the end of file.

+
This is code.
+

diff --git a/tests/code_fence.text b/tests/code_fence.text
new file mode 100644
index 0000000..3e3b681
--- /dev/null
+++ b/tests/code_fence.text
@@ -0,0 +1,37 @@
+```
+code blocks can start in the first line
+```
+
+This is a code block
+
+```
+foo bar
+eggs bacon
+```
+
+They are allowed to start within a block:
+```
+foo
+```
+
+Code blocks can contain empty lines
+```
+before empty line
+
+after empty line
+```
+
+Language info strings will add a class to the code block
+```sh
+#!/bin/sh
+ls -la .
+```
+
+Accidental code fences can be avoided by escaping
+\`\`\`
+like this.
+\`\`\`
+
+According to commonmark, a code block that is not terminated will continue until the end of file.
+```
+This is code.
diff --git a/tests/commonmark/backslash_escapes.html b/tests/commonmark/backslash_escapes.html
new file mode 100644
index 0000000..0976aed
--- /dev/null
+++ b/tests/commonmark/backslash_escapes.html
@@ -0,0 +1,3 @@
+
Backslash escapes

+
https://spec.commonmark.org/0.29/#example-298

+
!"#$%&'()*+,-./:;<=>?@[\]^_`{|}~

diff --git a/tests/commonmark/backslash_escapes.text b/tests/commonmark/backslash_escapes.text
new file mode 100644
index 0000000..106551a
--- /dev/null
+++ b/tests/commonmark/backslash_escapes.text
@@ -0,0 +1,5 @@
+# [Backslash escapes](https://spec.commonmark.org/0.29/#backslash-escapes)
+
+
+
+\!\"\#\$\%\&\'\(\)\*\+\,\-\.\/\:\;\<\=\>\?\@\[\\\]\^\_\`\{\|\}\~
diff --git a/tests/html.html b/tests/html.html
new file mode 100644
index 0000000..0a5b69d
--- /dev/null
+++ b/tests/html.html
@@ -0,0 +1,7 @@
+
bold

+
text

+
title subtext

+
    
+	
  • One
+	
  • Two
+

diff --git a/tests/html.text b/tests/html.text
new file mode 100644
index 0000000..534bc83
--- /dev/null
+++ b/tests/html.text
@@ -0,0 +1,10 @@
+bold
+
+text
+
+
title subtext

+
+
    
+	
  • One
+	
  • Two
+

diff --git a/tests/linebreak.html b/tests/linebreak.html
new file mode 100644
index 0000000..38e27ac
--- /dev/null
+++ b/tests/linebreak.html
@@ -0,0 +1,2 @@
+
If a line ends with two space (like this line),

+a hard line brake is inserted

diff --git a/tests/linebreak.text b/tests/linebreak.text
new file mode 100644
index 0000000..17360db
--- /dev/null
+++ b/tests/linebreak.text
@@ -0,0 +1,2 @@
+If a line ends with two space (like this line),  
+a hard line brake is inserted
diff --git a/tests/lists.html b/tests/lists.html
new file mode 100644
index 0000000..6208fe7
--- /dev/null
+++ b/tests/lists.html
@@ -0,0 +1,14 @@
+
    
+
  1. One
    2. 
+
  2. Two
    3. 
+

+
Ordered lists will use the first number as start number and continue counting from there.

+
    
+
  1. Two
    2. 
+
  2. Three
    3. 
+

+
HTML does not allow lists in paragraphs, so the following should end the paragraph before starting the list:

+
+
    
+
  • bar
    • 
+

diff --git a/tests/lists.text b/tests/lists.text
new file mode 100644
index 0000000..71e2886
--- /dev/null
+++ b/tests/lists.text
@@ -0,0 +1,10 @@
+1. One
+1. Two
+
+Ordered lists will use the first number as start number and continue counting from there.
+
+2. Two
+4. Three
+
+HTML does not allow lists in paragraphs, so the following should end the paragraph before starting the list:
+- bar
diff --git a/tests/mdtest/Amps_and_angle_encoding.html b/tests/mdtest/Amps_and_angle_encoding.html
new file mode 100644
index 0000000..a3fd44a
--- /dev/null
+++ b/tests/mdtest/Amps_and_angle_encoding.html
@@ -0,0 +1,6 @@
+
AT&T has an ampersand in their name.

+
AT&T is another way to write it.

+
This & that.

+
4 < 5.

+
6 > 5.

+
Here's an inline link.

diff --git a/tests/mdtest/Amps_and_angle_encoding.text b/tests/mdtest/Amps_and_angle_encoding.text
new file mode 100644
index 0000000..5fe4125
--- /dev/null
+++ b/tests/mdtest/Amps_and_angle_encoding.text
@@ -0,0 +1,12 @@
+AT&T has an ampersand in their name.
+
+AT&T is another way to write it.
+
+This & that.
+
+4 < 5.
+
+6 > 5.
+
+Here's an inline [link](/script?foo=1&bar=2).
+
diff --git a/tests/mdtest/Auto_links.html b/tests/mdtest/Auto_links.html
new file mode 100644
index 0000000..8e85d01
--- /dev/null
+++ b/tests/mdtest/Auto_links.html
@@ -0,0 +1,12 @@
+
Link: http://example.com/.

+
With an ampersand: http://example.com/?foo=1&bar=2

+
+
Blockquoted: http://example.com/

+

+
Auto-links should not occur here: <http://example.com/>

+
or here: <http://example.com/>
+

diff --git a/tests/mdtest/Auto_links.text b/tests/mdtest/Auto_links.text
new file mode 100644
index 0000000..abbc488
--- /dev/null
+++ b/tests/mdtest/Auto_links.text
@@ -0,0 +1,13 @@
+Link: .
+
+With an ampersand: 
+
+* In a list?
+* 
+* It should.
+
+> Blockquoted: 
+
+Auto-links should not occur here: ``
+
+	or here: 
\ No newline at end of file
diff --git a/tests/mdtest/Blockquotes_with_code_blocks.html b/tests/mdtest/Blockquotes_with_code_blocks.html
new file mode 100644
index 0000000..87ea58a
--- /dev/null
+++ b/tests/mdtest/Blockquotes_with_code_blocks.html
@@ -0,0 +1,11 @@
+
Example:

+
sub status {
+    print "working";
+}
+

+
Or:

+
sub status {
+    return "working";
+}
+

+

diff --git a/tests/mdtest/Blockquotes_with_code_blocks.text b/tests/mdtest/Blockquotes_with_code_blocks.text
new file mode 100644
index 0000000..c31d171
--- /dev/null
+++ b/tests/mdtest/Blockquotes_with_code_blocks.text
@@ -0,0 +1,11 @@
+> Example:
+> 
+>     sub status {
+>         print "working";
+>     }
+> 
+> Or:
+> 
+>     sub status {
+>         return "working";
+>     }
diff --git a/tests/mdtest/Code_Blocks.html b/tests/mdtest/Code_Blocks.html
new file mode 100644
index 0000000..7d89615
--- /dev/null
+++ b/tests/mdtest/Code_Blocks.html
@@ -0,0 +1,12 @@
+
code block on the first line
+

+
Regular text.

+
code block indented by spaces
+

+
Regular text.

+
the lines in this block  
+all contain trailing spaces  
+

+
Regular Text.

+
code block on the last line
+

diff --git a/tests/mdtest/Code_Blocks.text b/tests/mdtest/Code_Blocks.text
new file mode 100644
index 0000000..b54b092
--- /dev/null
+++ b/tests/mdtest/Code_Blocks.text
@@ -0,0 +1,14 @@
+	code block on the first line
+	
+Regular text.
+
+    code block indented by spaces
+
+Regular text.
+
+	the lines in this block  
+	all contain trailing spaces  
+
+Regular Text.
+
+	code block on the last line
\ No newline at end of file
diff --git a/tests/mdtest/Code_Spans.html b/tests/mdtest/Code_Spans.html
new file mode 100644
index 0000000..27acea1
--- /dev/null
+++ b/tests/mdtest/Code_Spans.html
@@ -0,0 +1,3 @@
+
<test a=" content of attribute ">

+
Fix for backticks within HTML tag: like this

+
Here's how you put `backticks` in a code span.

diff --git a/tests/mdtest/Code_Spans.text b/tests/mdtest/Code_Spans.text
new file mode 100644
index 0000000..5c229c7
--- /dev/null
+++ b/tests/mdtest/Code_Spans.text
@@ -0,0 +1,5 @@
+``
+
+Fix for backticks within HTML tag: like this
+
+Here's how you put `` `backticks` `` in a code span.
\ No newline at end of file
diff --git a/tests/mdtest/Inline_HTML_comments.html b/tests/mdtest/Inline_HTML_comments.html
new file mode 100644
index 0000000..ebc4818
--- /dev/null
+++ b/tests/mdtest/Inline_HTML_comments.html
@@ -0,0 +1,8 @@
+
Paragraph one.

+
+
+
Paragraph two.

+
+
The end.

diff --git a/tests/mdtest/Inline_HTML_comments.text b/tests/mdtest/Inline_HTML_comments.text
new file mode 100644
index 0000000..99878b8
--- /dev/null
+++ b/tests/mdtest/Inline_HTML_comments.text
@@ -0,0 +1,13 @@
+Paragraph one.
+
+
+
+
+
+Paragraph two.
+
+
+
+The end.
diff --git a/tests/mdtest/LICENSE b/tests/mdtest/LICENSE
new file mode 100644
index 0000000..d511905
--- /dev/null
+++ b/tests/mdtest/LICENSE
@@ -0,0 +1,339 @@
+		    GNU GENERAL PUBLIC LICENSE
+		       Version 2, June 1991
+
+ Copyright (C) 1989, 1991 Free Software Foundation, Inc.,
+ 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
+ Everyone is permitted to copy and distribute verbatim copies
+ of this license document, but changing it is not allowed.
+
+			    Preamble
+
+  The licenses for most software are designed to take away your
+freedom to share and change it.  By contrast, the GNU General Public
+License is intended to guarantee your freedom to share and change free
+software--to make sure the software is free for all its users.  This
+General Public License applies to most of the Free Software
+Foundation's software and to any other program whose authors commit to
+using it.  (Some other Free Software Foundation software is covered by
+the GNU Lesser General Public License instead.)  You can apply it to
+your programs, too.
+
+  When we speak of free software, we are referring to freedom, not
+price.  Our General Public Licenses are designed to make sure that you
+have the freedom to distribute copies of free software (and charge for
+this service if you wish), that you receive source code or can get it
+if you want it, that you can change the software or use pieces of it
+in new free programs; and that you know you can do these things.
+
+  To protect your rights, we need to make restrictions that forbid
+anyone to deny you these rights or to ask you to surrender the rights.
+These restrictions translate to certain responsibilities for you if you
+distribute copies of the software, or if you modify it.
+
+  For example, if you distribute copies of such a program, whether
+gratis or for a fee, you must give the recipients all the rights that
+you have.  You must make sure that they, too, receive or can get the
+source code.  And you must show them these terms so they know their
+rights.
+
+  We protect your rights with two steps: (1) copyright the software, and
+(2) offer you this license which gives you legal permission to copy,
+distribute and/or modify the software.
+
+  Also, for each author's protection and ours, we want to make certain
+that everyone understands that there is no warranty for this free
+software.  If the software is modified by someone else and passed on, we
+want its recipients to know that what they have is not the original, so
+that any problems introduced by others will not reflect on the original
+authors' reputations.
+
+  Finally, any free program is threatened constantly by software
+patents.  We wish to avoid the danger that redistributors of a free
+program will individually obtain patent licenses, in effect making the
+program proprietary.  To prevent this, we have made it clear that any
+patent must be licensed for everyone's free use or not licensed at all.
+
+  The precise terms and conditions for copying, distribution and
+modification follow.
+
+		    GNU GENERAL PUBLIC LICENSE
+   TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION
+
+  0. This License applies to any program or other work which contains
+a notice placed by the copyright holder saying it may be distributed
+under the terms of this General Public License.  The "Program", below,
+refers to any such program or work, and a "work based on the Program"
+means either the Program or any derivative work under copyright law:
+that is to say, a work containing the Program or a portion of it,
+either verbatim or with modifications and/or translated into another
+language.  (Hereinafter, translation is included without limitation in
+the term "modification".)  Each licensee is addressed as "you".
+
+Activities other than copying, distribution and modification are not
+covered by this License; they are outside its scope.  The act of
+running the Program is not restricted, and the output from the Program
+is covered only if its contents constitute a work based on the
+Program (independent of having been made by running the Program).
+Whether that is true depends on what the Program does.
+
+  1. You may copy and distribute verbatim copies of the Program's
+source code as you receive it, in any medium, provided that you
+conspicuously and appropriately publish on each copy an appropriate
+copyright notice and disclaimer of warranty; keep intact all the
+notices that refer to this License and to the absence of any warranty;
+and give any other recipients of the Program a copy of this License
+along with the Program.
+
+You may charge a fee for the physical act of transferring a copy, and
+you may at your option offer warranty protection in exchange for a fee.
+
+  2. You may modify your copy or copies of the Program or any portion
+of it, thus forming a work based on the Program, and copy and
+distribute such modifications or work under the terms of Section 1
+above, provided that you also meet all of these conditions:
+
+    a) You must cause the modified files to carry prominent notices
+    stating that you changed the files and the date of any change.
+
+    b) You must cause any work that you distribute or publish, that in
+    whole or in part contains or is derived from the Program or any
+    part thereof, to be licensed as a whole at no charge to all third
+    parties under the terms of this License.
+
+    c) If the modified program normally reads commands interactively
+    when run, you must cause it, when started running for such
+    interactive use in the most ordinary way, to print or display an
+    announcement including an appropriate copyright notice and a
+    notice that there is no warranty (or else, saying that you provide
+    a warranty) and that users may redistribute the program under
+    these conditions, and telling the user how to view a copy of this
+    License.  (Exception: if the Program itself is interactive but
+    does not normally print such an announcement, your work based on
+    the Program is not required to print an announcement.)
+
+These requirements apply to the modified work as a whole.  If
+identifiable sections of that work are not derived from the Program,
+and can be reasonably considered independent and separate works in
+themselves, then this License, and its terms, do not apply to those
+sections when you distribute them as separate works.  But when you
+distribute the same sections as part of a whole which is a work based
+on the Program, the distribution of the whole must be on the terms of
+this License, whose permissions for other licensees extend to the
+entire whole, and thus to each and every part regardless of who wrote it.
+
+Thus, it is not the intent of this section to claim rights or contest
+your rights to work written entirely by you; rather, the intent is to
+exercise the right to control the distribution of derivative or
+collective works based on the Program.
+
+In addition, mere aggregation of another work not based on the Program
+with the Program (or with a work based on the Program) on a volume of
+a storage or distribution medium does not bring the other work under
+the scope of this License.
+
+  3. You may copy and distribute the Program (or a work based on it,
+under Section 2) in object code or executable form under the terms of
+Sections 1 and 2 above provided that you also do one of the following:
+
+    a) Accompany it with the complete corresponding machine-readable
+    source code, which must be distributed under the terms of Sections
+    1 and 2 above on a medium customarily used for software interchange; or,
+
+    b) Accompany it with a written offer, valid for at least three
+    years, to give any third party, for a charge no more than your
+    cost of physically performing source distribution, a complete
+    machine-readable copy of the corresponding source code, to be
+    distributed under the terms of Sections 1 and 2 above on a medium
+    customarily used for software interchange; or,
+
+    c) Accompany it with the information you received as to the offer
+    to distribute corresponding source code.  (This alternative is
+    allowed only for noncommercial distribution and only if you
+    received the program in object code or executable form with such
+    an offer, in accord with Subsection b above.)
+
+The source code for a work means the preferred form of the work for
+making modifications to it.  For an executable work, complete source
+code means all the source code for all modules it contains, plus any
+associated interface definition files, plus the scripts used to
+control compilation and installation of the executable.  However, as a
+special exception, the source code distributed need not include
+anything that is normally distributed (in either source or binary
+form) with the major components (compiler, kernel, and so on) of the
+operating system on which the executable runs, unless that component
+itself accompanies the executable.
+
+If distribution of executable or object code is made by offering
+access to copy from a designated place, then offering equivalent
+access to copy the source code from the same place counts as
+distribution of the source code, even though third parties are not
+compelled to copy the source along with the object code.
+
+  4. You may not copy, modify, sublicense, or distribute the Program
+except as expressly provided under this License.  Any attempt
+otherwise to copy, modify, sublicense or distribute the Program is
+void, and will automatically terminate your rights under this License.
+However, parties who have received copies, or rights, from you under
+this License will not have their licenses terminated so long as such
+parties remain in full compliance.
+
+  5. You are not required to accept this License, since you have not
+signed it.  However, nothing else grants you permission to modify or
+distribute the Program or its derivative works.  These actions are
+prohibited by law if you do not accept this License.  Therefore, by
+modifying or distributing the Program (or any work based on the
+Program), you indicate your acceptance of this License to do so, and
+all its terms and conditions for copying, distributing or modifying
+the Program or works based on it.
+
+  6. Each time you redistribute the Program (or any work based on the
+Program), the recipient automatically receives a license from the
+original licensor to copy, distribute or modify the Program subject to
+these terms and conditions.  You may not impose any further
+restrictions on the recipients' exercise of the rights granted herein.
+You are not responsible for enforcing compliance by third parties to
+this License.
+
+  7. If, as a consequence of a court judgment or allegation of patent
+infringement or for any other reason (not limited to patent issues),
+conditions are imposed on you (whether by court order, agreement or
+otherwise) that contradict the conditions of this License, they do not
+excuse you from the conditions of this License.  If you cannot
+distribute so as to satisfy simultaneously your obligations under this
+License and any other pertinent obligations, then as a consequence you
+may not distribute the Program at all.  For example, if a patent
+license would not permit royalty-free redistribution of the Program by
+all those who receive copies directly or indirectly through you, then
+the only way you could satisfy both it and this License would be to
+refrain entirely from distribution of the Program.
+
+If any portion of this section is held invalid or unenforceable under
+any particular circumstance, the balance of the section is intended to
+apply and the section as a whole is intended to apply in other
+circumstances.
+
+It is not the purpose of this section to induce you to infringe any
+patents or other property right claims or to contest validity of any
+such claims; this section has the sole purpose of protecting the
+integrity of the free software distribution system, which is
+implemented by public license practices.  Many people have made
+generous contributions to the wide range of software distributed
+through that system in reliance on consistent application of that
+system; it is up to the author/donor to decide if he or she is willing
+to distribute software through any other system and a licensee cannot
+impose that choice.
+
+This section is intended to make thoroughly clear what is believed to
+be a consequence of the rest of this License.
+
+  8. If the distribution and/or use of the Program is restricted in
+certain countries either by patents or by copyrighted interfaces, the
+original copyright holder who places the Program under this License
+may add an explicit geographical distribution limitation excluding
+those countries, so that distribution is permitted only in or among
+countries not thus excluded.  In such case, this License incorporates
+the limitation as if written in the body of this License.
+
+  9. The Free Software Foundation may publish revised and/or new versions
+of the General Public License from time to time.  Such new versions will
+be similar in spirit to the present version, but may differ in detail to
+address new problems or concerns.
+
+Each version is given a distinguishing version number.  If the Program
+specifies a version number of this License which applies to it and "any
+later version", you have the option of following the terms and conditions
+either of that version or of any later version published by the Free
+Software Foundation.  If the Program does not specify a version number of
+this License, you may choose any version ever published by the Free Software
+Foundation.
+
+  10. If you wish to incorporate parts of the Program into other free
+programs whose distribution conditions are different, write to the author
+to ask for permission.  For software which is copyrighted by the Free
+Software Foundation, write to the Free Software Foundation; we sometimes
+make exceptions for this.  Our decision will be guided by the two goals
+of preserving the free status of all derivatives of our free software and
+of promoting the sharing and reuse of software generally.
+
+			    NO WARRANTY
+
+  11. BECAUSE THE PROGRAM IS LICENSED FREE OF CHARGE, THERE IS NO WARRANTY
+FOR THE PROGRAM, TO THE EXTENT PERMITTED BY APPLICABLE LAW.  EXCEPT WHEN
+OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES
+PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED
+OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
+MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE.  THE ENTIRE RISK AS
+TO THE QUALITY AND PERFORMANCE OF THE PROGRAM IS WITH YOU.  SHOULD THE
+PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF ALL NECESSARY SERVICING,
+REPAIR OR CORRECTION.
+
+  12. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
+WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY AND/OR
+REDISTRIBUTE THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES,
+INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING
+OUT OF THE USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED
+TO LOSS OF DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY
+YOU OR THIRD PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER
+PROGRAMS), EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE
+POSSIBILITY OF SUCH DAMAGES.
+
+		     END OF TERMS AND CONDITIONS
+
+	    How to Apply These Terms to Your New Programs
+
+  If you develop a new program, and you want it to be of the greatest
+possible use to the public, the best way to achieve this is to make it
+free software which everyone can redistribute and change under these terms.
+
+  To do so, attach the following notices to the program.  It is safest
+to attach them to the start of each source file to most effectively
+convey the exclusion of warranty; and each file should have at least
+the "copyright" line and a pointer to where the full notice is found.
+
+    
+    Copyright (C)   
+
+    This program is free software; you can redistribute it and/or modify
+    it under the terms of the GNU General Public License as published by
+    the Free Software Foundation; either version 2 of the License, or
+    (at your option) any later version.
+
+    This program is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU General Public License for more details.
+
+    You should have received a copy of the GNU General Public License along
+    with this program; if not, write to the Free Software Foundation, Inc.,
+    51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
+
+Also add information on how to contact you by electronic and paper mail.
+
+If the program is interactive, make it output a short notice like this
+when it starts in an interactive mode:
+
+    Gnomovision version 69, Copyright (C) year name of author
+    Gnomovision comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
+    This is free software, and you are welcome to redistribute it
+    under certain conditions; type `show c' for details.
+
+The hypothetical commands `show w' and `show c' should show the appropriate
+parts of the General Public License.  Of course, the commands you use may
+be called something other than `show w' and `show c'; they could even be
+mouse-clicks or menu items--whatever suits your program.
+
+You should also get your employer (if you work as a programmer) or your
+school, if any, to sign a "copyright disclaimer" for the program, if
+necessary.  Here is a sample; alter the names:
+
+  Yoyodyne, Inc., hereby disclaims all copyright interest in the program
+  `Gnomovision' (which makes passes at compilers) written by James Hacker.
+
+  , 1 April 1989
+  Ty Coon, President of Vice
+
+This General Public License does not permit incorporating your program into
+proprietary programs.  If your program is a subroutine library, you may
+consider it more useful to permit linking proprietary applications with the
+library.  If this is what you want to do, use the GNU Lesser General
+Public License instead of this License.
diff --git a/tests/mdtest/Links,_inline_style.html b/tests/mdtest/Links,_inline_style.html
new file mode 100644
index 0000000..feb4637
--- /dev/null
+++ b/tests/mdtest/Links,_inline_style.html
@@ -0,0 +1,12 @@
+
Just a URL.

+
URL and title.

+
URL and title.

+
URL and title.

+
URL and title.

+
URL wrapped in angle brackets.

+
URL w/ angle brackets + title.

+
Empty.

+
With parens in the URL

+
(With outer parens and parens in url)

+
With parens in the URL

+
(With outer parens and parens in url)

diff --git a/tests/mdtest/Links,_inline_style.text b/tests/mdtest/Links,_inline_style.text
new file mode 100644
index 0000000..aba9658
--- /dev/null
+++ b/tests/mdtest/Links,_inline_style.text
@@ -0,0 +1,24 @@
+Just a [URL](/url/).
+
+[URL and title](/url/ "title").
+
+[URL and title](/url/  "title preceded by two spaces").
+
+[URL and title](/url/	"title preceded by a tab").
+
+[URL and title](/url/ "title has spaces afterward"  ).
+
+[URL wrapped in angle brackets]().
+
+[URL w/ angle brackets + title]( "Here's the title").
+
+[Empty]().
+
+[With parens in the URL](http://en.wikipedia.org/wiki/WIMP_(computing))
+
+(With outer parens and [parens in url](/foo(bar)))
+
+
+[With parens in the URL](/foo(bar) "and a title")
+
+(With outer parens and [parens in url](/foo(bar) "and a title"))
diff --git a/tests/mdtest/Literal_quotes_in_titles.html b/tests/mdtest/Literal_quotes_in_titles.html
new file mode 100644
index 0000000..94b80ae
--- /dev/null
+++ b/tests/mdtest/Literal_quotes_in_titles.html
@@ -0,0 +1 @@
+
Foo bar.

diff --git a/tests/mdtest/Literal_quotes_in_titles.text b/tests/mdtest/Literal_quotes_in_titles.text
new file mode 100644
index 0000000..ce74d90
--- /dev/null
+++ b/tests/mdtest/Literal_quotes_in_titles.text
@@ -0,0 +1 @@
+Foo [bar](/url/ "Title with "quotes" inside").
diff --git a/tests/mdtest/Nested_blockquotes.html b/tests/mdtest/Nested_blockquotes.html
new file mode 100644
index 0000000..d990034
--- /dev/null
+++ b/tests/mdtest/Nested_blockquotes.html
@@ -0,0 +1,5 @@
+
foo

+
bar

+

+
foo

+

diff --git a/tests/mdtest/Nested_blockquotes.text b/tests/mdtest/Nested_blockquotes.text
new file mode 100644
index 0000000..ed3c624
--- /dev/null
+++ b/tests/mdtest/Nested_blockquotes.text
@@ -0,0 +1,5 @@
+> foo
+>
+> > bar
+>
+> foo
diff --git a/tests/mdtest/Ordered_and_unordered_lists.html b/tests/mdtest/Ordered_and_unordered_lists.html
new file mode 100644
index 0000000..d516a55
--- /dev/null
+++ b/tests/mdtest/Ordered_and_unordered_lists.html
@@ -0,0 +1,129 @@
+
Unordered

+
Asterisks tight:

+
    
+
  • asterisk 1
    • 
+
  • asterisk 2
    • 
+
  • asterisk 3
    • 
+

+
Asterisks loose:

+
    
+
  • asterisk 1
    
+
    • 
+
  • asterisk 2
    
+
    • 
+
  • asterisk 3
    
+
    • 
+

+

+
Pluses tight:

+
    
+
  • Plus 1
    • 
+
  • Plus 2
    • 
+
  • Plus 3
    • 
+

+
Pluses loose:

+
    
+
  • Plus 1
    
+
    • 
+
  • Plus 2
    
+
    • 
+
  • Plus 3
    
+
    • 
+

+

+
Minuses tight:

+
    
+
  • Minus 1
    • 
+
  • Minus 2
    • 
+
  • Minus 3
    • 
+

+
Minuses loose:

+
    
+
  • Minus 1
    
+
    • 
+
  • Minus 2
    
+
    • 
+
  • Minus 3
    
+
    • 
+

+
Ordered

+
Tight:

+
    
+
  1. First
    2. 
+
  2. Second
    3. 
+
  3. Third
    4. 
+

+
and:

+
    
+
  1. One
    2. 
+
  2. Two
    3. 
+
  3. Three
    4. 
+

+
Loose using tabs:

+
    
+
  1. First
    
+
    2. 
+
  2. Second
    
+
    3. 
+
  3. Third
    
+
    4. 
+

+
and using spaces:

+
    
+
  1. One
    
+
    2. 
+
  2. Two
    
+
    3. 
+
  3. Three
    
+
    4. 
+

+
Multiple paragraphs:

+
    
+
  1. Item 1, graf one.
    
+
    Item 2. graf two. The quick brown fox jumped over the lazy dog's
+back.
    
+
    2. 
+
  2. Item 2.
    
+
    3. 
+
  3. Item 3.
    
+
    4. 
+

+
Nested

+
    
+
  • Tab
+
      
+
    • Tab
+
        
+
      • Tab
        • 
+
      
+
      • 
+
    
+
    • 
+

+
Here's another:

+
    
+
  1. First
    2. 
+
  2. Second:
+
      
+
    • Fee
      • 
+
    • Fie
      • 
+
    • Foe
      • 
+
    
+
    3. 
+
  3. Third
    4. 
+

+
Same thing but with paragraphs:

+
    
+
  1. First
    
+
    2. 
+
  2. Second:
    
+
+
      
+
    • Fee
      • 
+
    • Fie
      • 
+
    • Foe
      • 
+
    
+
    3. 
+
  3. Third
    
+
    4. 
+

diff --git a/tests/mdtest/Ordered_and_unordered_lists.text b/tests/mdtest/Ordered_and_unordered_lists.text
new file mode 100644
index 0000000..b7d9b23
--- /dev/null
+++ b/tests/mdtest/Ordered_and_unordered_lists.text
@@ -0,0 +1,122 @@
+## Unordered
+
+Asterisks tight:
+
+*	asterisk 1
+*	asterisk 2
+*	asterisk 3
+
+
+Asterisks loose:
+
+*	asterisk 1
+
+*	asterisk 2
+
+*	asterisk 3
+
+- - -
+
+Pluses tight:
+
++	Plus 1
++	Plus 2
++	Plus 3
+
+
+Pluses loose:
+
++	Plus 1
+
++	Plus 2
+
++	Plus 3
+
+- - -
+
+
+Minuses tight:
+
+-	Minus 1
+-	Minus 2
+-	Minus 3
+
+
+Minuses loose:
+
+-	Minus 1
+
+-	Minus 2
+
+-	Minus 3
+
+
+## Ordered
+
+Tight:
+
+1.	First
+2.	Second
+3.	Third
+
+and:
+
+1. One
+2. Two
+3. Three
+
+
+Loose using tabs:
+
+1.	First
+
+2.	Second
+
+3.	Third
+
+and using spaces:
+
+1. One
+
+2. Two
+
+3. Three
+
+Multiple paragraphs:
+
+1.    Item 1, graf one.
+
+      Item 2. graf two. The quick brown fox jumped over the lazy dog's
+      back.
+    
+2.    Item 2.
+
+3.    Item 3.
+
+
+
+## Nested
+
+*    Tab
+     *    Tab
+          *    Tab
+
+Here's another:
+
+1. First
+2. Second:
+   * Fee
+   * Fie
+   * Foe
+3. Third
+
+Same thing but with paragraphs:
+
+1. First
+
+2. Second:
+   * Fee
+   * Fie
+   * Foe
+
+3. Third
diff --git a/tests/mdtest/README.md b/tests/mdtest/README.md
new file mode 100644
index 0000000..4866f3e
--- /dev/null
+++ b/tests/mdtest/README.md
@@ -0,0 +1 @@
+Tests adapted from [MDTest](https://github.com/michelf/mdtest).
diff --git a/tests/mdtest/Strong_and_em_together.html b/tests/mdtest/Strong_and_em_together.html
new file mode 100644
index 0000000..2629594
--- /dev/null
+++ b/tests/mdtest/Strong_and_em_together.html
@@ -0,0 +1,4 @@
+
This is strong and em.

+
So is this word.

+
This is strong and em.

+
So is this word.

diff --git a/tests/mdtest/Strong_and_em_together.text b/tests/mdtest/Strong_and_em_together.text
new file mode 100644
index 0000000..95ee690
--- /dev/null
+++ b/tests/mdtest/Strong_and_em_together.text
@@ -0,0 +1,7 @@
+***This is strong and em.***
+
+So is ***this*** word.
+
+___This is strong and em.___
+
+So is ___this___ word.
diff --git a/tests/mdtest/Tabs.html b/tests/mdtest/Tabs.html
new file mode 100644
index 0000000..82110b9
--- /dev/null
+++ b/tests/mdtest/Tabs.html
@@ -0,0 +1,21 @@
+
    
+
  • this is a list item
+indented with tabs
    
+
    • 
+
  • this is a list item
+indented with spaces
    
+
    • 
+

+
Code:

+
this code block is indented by one tab
+

+
And:

+
	this code block is indented by two tabs
+

+
And:

+
+	this is an example list item
+	indented with tabs
+
++   this is an example list item
+    indented with spaces
+

diff --git a/tests/mdtest/Tabs.text b/tests/mdtest/Tabs.text
new file mode 100644
index 0000000..e93637f
--- /dev/null
+++ b/tests/mdtest/Tabs.text
@@ -0,0 +1,21 @@
++	this is a list item
+ 	indented with tabs
+
++ this is a list item
+  indented with spaces
+
+Code:
+
+	this code block is indented by one tab
+
+And:
+
+		this code block is indented by two tabs
+
+And:
+
+	+	this is an example list item
+		indented with tabs
+	
+	+   this is an example list item
+	    indented with spaces
diff --git a/tests/mdtest/Tidyness.html b/tests/mdtest/Tidyness.html
new file mode 100644
index 0000000..564644d
--- /dev/null
+++ b/tests/mdtest/Tidyness.html
@@ -0,0 +1,7 @@
+
A list within a blockquote:

+
    
+
  • asterisk 1
    • 
+
  • asterisk 2
    • 
+
  • asterisk 3
    • 
+

+

diff --git a/tests/mdtest/Tidyness.text b/tests/mdtest/Tidyness.text
new file mode 100644
index 0000000..5f18b8d
--- /dev/null
+++ b/tests/mdtest/Tidyness.text
@@ -0,0 +1,5 @@
+> A list within a blockquote:
+> 
+> *	asterisk 1
+> *	asterisk 2
+> *	asterisk 3
diff --git a/tests/nohtml/basic.html b/tests/nohtml/basic.html
new file mode 100644
index 0000000..8384b31
--- /dev/null
+++ b/tests/nohtml/basic.html
@@ -0,0 +1,7 @@
+
This document contains <html> elements, but they should not be interpreted, because smu is called with -n.

+
Here are <em>some</em> tags, they can also be uppercase <HTML>.

+
<p>
+

+
More tags <a href="">here</a>
+

+
<p>

diff --git a/tests/nohtml/basic.text b/tests/nohtml/basic.text
new file mode 100644
index 0000000..193fcda
--- /dev/null
+++ b/tests/nohtml/basic.text
@@ -0,0 +1,7 @@
+This document contains  elements, but they should not be interpreted, because smu is called with `-n`.
+
+Here are some tags, they can also be uppercase .
+
+

+	More tags here
+

diff --git a/tests/old_readme.html b/tests/old_readme.html
new file mode 100644
index 0000000..a7d4e47
--- /dev/null
+++ b/tests/old_readme.html
@@ -0,0 +1,220 @@
+
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.

+
Syntax

+
smu was started as a rewrite of
+markdown but became something
+more lightweight and consistent. It differs from CommonMark in the following ways:

+
    
+
  • No support for reference style links
    • 
+
  • Stricter indentation rules for lists
    • 
+
  • Lists don't end paragraphs by themselves (blank line needed)
    • 
+
  • Horizontal rules (<hr>) must use - - - as syntax
    • 
+
  • Code fences have stricter syntax
    • 
+

+
Patches that increase the CommonMark compatibility are welcome as long as they don't increase the code complexity significantly.

+
This project is a fork of the original smu by
+Enno Boland (gottox). The main differences to the
+original smu are:

+
    
+
  • Support for code fences
    • 
+
  • Improved CommonMark compatibility. E.g.
+
      
+
    • Code blocks need four spaces indentation instead of three
      • 
+
    • Skip empty lines at end of code blocks
      • 
+
    • Ignore single spaces around code spans
      • 
+
    • Keep HTML comments in output
      • 
+
    • Improved spec compliance for lists
      • 
+
    • Nesting code block in blockquotes works
      • 
+
    • "Empty" lines in lists behave identically, no matter how much whitespace they contain
      • 
+
    
+
    • 
+
  • Added a simple test suite to check for compliance and avoid regressions
    • 
+

+
Inline patterns

+
There are several patterns 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.
+
    
+
    Using ``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 a code block with a leading Tab or with 4 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.

+
Another way to write code blocks is to use code fences:

+
```json
+{"some": "code"}
+```
+

+
This has two advantages:

+
+
    
+
  • The optional language identifier will be turned into a language- class name
    • 
+
  • You can keep the original indentation which helps when doing copy & paste
    • 
+

+
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

+
You can include arbitrary HTML code in your documents. The HTML will be
+passed through to the resulting document without modification. This is a good
+way to work around features that are missing in smu. If you don't want this
+behaviour, use the -n flag when executing smu to stricly escape the HTML
+tags.

diff --git a/tests/old_readme.text b/tests/old_readme.text
new file mode 100644
index 0000000..0854b42
--- /dev/null
+++ b/tests/old_readme.text
@@ -0,0 +1,238 @@
+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.
+
+Syntax
+======
+
+smu was started as a rewrite of
+[markdown](http://daringfireball.net/projects/markdown/) but became something
+more lightweight and consistent. It differs from [CommonMark](https://commonmark.org/) in the following ways:
+
+* No support for _reference style links_
+* Stricter indentation rules for lists
+* Lists don't end paragraphs by themselves (blank line needed)
+* Horizontal rules (`
`) must use `- - -` as syntax
+* Code fences have stricter syntax
+
+Patches that increase the CommonMark compatibility are welcome as long as they don't increase the code complexity significantly.
+
+This project is a fork of the [original smu](https://github.com/gottox/smu) by
+[Enno Boland (gottox)](https://eboland.de). The main differences to the
+original smu are:
+
+* Support for code fences
+* Improved [CommonMark](https://commonmark.org/) compatibility. E.g.
+  * Code blocks need four spaces indentation instead of three
+  * Skip empty lines at end of code blocks
+  * Ignore single spaces around code spans
+  * Keep HTML comments in output
+  * Improved spec compliance for lists
+  * Nesting code block in blockquotes works
+  * "Empty" lines in lists behave identically, no matter how much whitespace they contain
+* Added a simple test suite to check for compliance and avoid regressions
+
+Inline patterns
+---------------
+
+There are several patterns 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.
+
+  Using ``` ``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:
+
+	
Heading

+	
Topic

+
+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 `<>`.
+
+	
+
+You can do the same for E-Mail addresses:
+
+	
+
+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
+
+	smu - simple mark up

+
+Lists
+-----
+
+Defining lists is very straightforward:
+
+	* Item 1
+	* Item 2
+	* Item 3
+
+Result:
+
+	
    
+	
  • Item 1
    • 
+	
  • Item 2
    • 
+	
  • Item 3
    • 
+	

+
+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:
+
+	
    
+	
  1. Item 1
    2. 
+	
  2. Item 2
    3. 
+	
  3. Item 3
    4. 
+	

+
+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:
+	

+	Hello
+	This is a quote with a link

+	

+
+
+You can define a code block with a leading Tab or with __4__ leading spaces
+
+		this.is(code)
+	
+	    this.is(code, too)
+
+Result:
+	
this.is(code)

+	
this.is(code, too)
+	

+
+Please note that you can't use HTML or smu syntax in a code block.
+
+Another way to write code blocks is to use code fences:
+
+	```json
+	{"some": "code"}
+	```
+
+This has two advantages:
+* The optional language identifier will be turned into a `language-` class name
+* You can keep the original indentation which helps when doing copy & paste
+
+Other interesting stuff
+-----------------------
+
+* to insert a horizontal rule simple add `- - -` into an empty line:
+
+  	Hello
+  	- - -
+  	Hello2
+
+  Result:
+  	

+  	Hello
+  	

+  	
+  	Hello2

+
+* 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
+----------
+
+You can include arbitrary HTML code in your documents. The HTML will be
+passed through to the resulting document without modification. This is a good
+way to work around features that are missing in smu. If you don't want this
+behaviour, use the `-n` flag when executing smu to stricly escape the HTML
+tags.
diff --git a/tests/ruler.html b/tests/ruler.html
new file mode 100644
index 0000000..ce18d20
--- /dev/null
+++ b/tests/ruler.html
@@ -0,0 +1,9 @@
+

+
+test
+

+
bar

+

+
foo
+

+

diff --git a/tests/ruler.text b/tests/ruler.text
new file mode 100644
index 0000000..83b395c
--- /dev/null
+++ b/tests/ruler.text
@@ -0,0 +1,11 @@
+- - -
+test
+- - -
+
+bar
+
+- - -
+
+foo
+- - -
+
diff --git a/tests/table.html b/tests/table.html
new file mode 100644
index 0000000..9c9aa78
--- /dev/null
+++ b/tests/table.html
@@ -0,0 +1,9 @@
+

+
+
+
1st field 2nd field 3rd field 
1st entry 2nd entry 3rd entry 

+
And here is another table

+
+
+
+
Heading 1 Some other heading 
I am a table cell. Me too! 

diff --git a/tests/table.text b/tests/table.text
new file mode 100644
index 0000000..0000c48
--- /dev/null
+++ b/tests/table.text
@@ -0,0 +1,10 @@
+| 1st field | 2nd field | 3rd field |
+| :--       |   :--:    |       --: |
+| 1st entry | 2nd entry | 3rd entry |
+
+And here is another table
+
+| Heading 1 | Some other heading |
+| --- | ------ |
+| I am a table cell. | Me too! |
+
diff --git a/tests/testdoc.html b/tests/testdoc.html
new file mode 100644
index 0000000..6a63329
--- /dev/null
+++ b/tests/testdoc.html
@@ -0,0 +1,72 @@
+
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. 
+
      2. d
        3. 
+
      
+
      • 
+
    • e
      • 
+
    
+
    • 
+
  • f
    • 
+

+
entity: &, <, >

+
code:
+

+
int powerof2(unsigned int n) {
+	return !((n - 1) & n) && n > 0;
+}
+

+
links

+
link: suckless

+
link with title: suckless

+
link with title (single quote): suckless

+
images

+
image: 

+
image with alt text: alt text

+
image with title: alt text

+
image with title (single quote): alt text

+
inline html

+

+	ABC
+

diff --git a/tests/testdoc.text b/tests/testdoc.text
new file mode 100644
index 0000000..65fef1b
--- /dev/null
+++ b/tests/testdoc.text
@@ -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
+-----------
+
+

+	ABC
+

diff --git a/tests/unicode.html b/tests/unicode.html
new file mode 100644
index 0000000..3570eca
--- /dev/null
+++ b/tests/unicode.html
@@ -0,0 +1,2 @@
+
👨‍👩‍👦 Family

+
👨‍👩‍👦

diff --git a/tests/unicode.text b/tests/unicode.text
new file mode 100644
index 0000000..e40dab5
--- /dev/null
+++ b/tests/unicode.text
@@ -0,0 +1,5 @@
+👨‍👩‍👦 Family
+=========
+
+👨‍👩‍👦
+---
-- 
2.45.2