mirror of
https://github.com/ultimatepp/ultimatepp.git
synced 2026-05-21 06:45:39 -06:00
plugin/md (thanks Oblivion), ide: UppHub now interprets .md correctly
git-svn-id: svn://ultimatepp.org/upp/trunk@15737 f0d560ea-af0d-0410-9eb7-867de7ffcac7
This commit is contained in:
cxl
parent
6c19de028b
commit
8c4cb75eb5
13 changed files with 7881 additions and 1 deletions
|
|
@ -98,6 +98,8 @@ void UppHubDlg::Readme()
|
|||
if(s.GetCount()) {
|
||||
if(n->readme.EndsWith(".qtf"))
|
||||
PromptOK(s);
|
||||
if(n->readme.EndsWith(".md"))
|
||||
PromptOK(MarkdownConverter().Tables().ToQtf(s));
|
||||
else
|
||||
PromptOK("\1" + s);
|
||||
}
|
||||
|
|
|
|||
|
|
@ -17,6 +17,7 @@
|
|||
#include <TextDiffCtrl/TextDiffCtrl.h>
|
||||
#include <ide/Designers/Designers.h>
|
||||
#include <ide/Android/Android.h>
|
||||
#include <plugin/md/Markdown.h>
|
||||
|
||||
#include "About.h"
|
||||
#include "MethodsCtrls.h"
|
||||
|
|
|
|||
|
|
@ -20,7 +20,8 @@ uses
|
|||
ide/Java,
|
||||
ide/MacroManager,
|
||||
Report,
|
||||
Core/SSL;
|
||||
Core/SSL,
|
||||
plugin/md;
|
||||
|
||||
file
|
||||
IDE readonly separator,
|
||||
|
|
|
|||
22
uppsrc/plugin/md/Copying
Normal file
22
uppsrc/plugin/md/Copying
Normal file
|
|
@ -0,0 +1,22 @@
|
|||
Copyright (c) 1998, 2021, The U++ Project
|
||||
All rights reserved.
|
||||
|
||||
Redistribution and use in source and binary forms, with or without modification, are permitted
|
||||
provided that the following conditions are met:
|
||||
|
||||
1. Redistributions of source code must retain the above copyright notice, this list of
|
||||
conditions and the following disclaimer.
|
||||
|
||||
2. Redistributions in binary form must reproduce the above copyright notice, this list of
|
||||
conditions and the following disclaimer in the documentation and/or other materials provided
|
||||
with the distribution.
|
||||
|
||||
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND ANY EXPRESS OR
|
||||
IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY
|
||||
AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR
|
||||
CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
|
||||
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
|
||||
SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
|
||||
THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
|
||||
OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
|
||||
POSSIBILITY OF SUCH DAMAGE.
|
||||
362
uppsrc/plugin/md/MD4C/CHANGELOG.md
Normal file
362
uppsrc/plugin/md/MD4C/CHANGELOG.md
Normal file
|
|
@ -0,0 +1,362 @@
|
|||
|
||||
# MD4C Change Log
|
||||
|
||||
|
||||
## Version 0.4.7
|
||||
|
||||
Changes:
|
||||
|
||||
* Add `MD_TABLE_DETAIL` structure into the API. The structure describes column
|
||||
count and row count of the table, and pointer to it is passed into the
|
||||
application-provided block callback with the `MD_BLOCK_TABLE` block type.
|
||||
|
||||
Fixes:
|
||||
|
||||
* [#131](https://github.com/mity/md4c/issues/131):
|
||||
Fix handling of a reference image nested in a reference link.
|
||||
|
||||
* [#135](https://github.com/mity/md4c/issues/135):
|
||||
Handle unmatched parenthesis pairs inside a permissive URL and WWW auto-links
|
||||
in a way more compatible with the GFM.
|
||||
|
||||
* [#138](https://github.com/mity/md4c/issues/138):
|
||||
The tag `<tbody></tbody>` is now suppressed whenever the table has zero body
|
||||
rows.
|
||||
|
||||
* [#139](https://github.com/mity/md4c/issues/139):
|
||||
Recognize a list item mark even when EOF follows it.
|
||||
|
||||
* [#142](https://github.com/mity/md4c/issues/142):
|
||||
Fix reference link definition label matching in a case when the label ends
|
||||
with a Unicode character with non-trivial case folding mapping.
|
||||
|
||||
|
||||
## Version 0.4.6
|
||||
|
||||
Fixes:
|
||||
|
||||
* [#130](https://github.com/mity/md4c/issues/130):
|
||||
Fix `ISANYOF` macro, which could provide unexpected results when encountering
|
||||
zero byte in the input text; in some cases leading to broken internal state
|
||||
of the parser.
|
||||
|
||||
The bug could result in denial of service and possibly also to other security
|
||||
implications. Applications are advised to update to 0.4.6.
|
||||
|
||||
|
||||
## Version 0.4.5
|
||||
|
||||
Fixes:
|
||||
|
||||
* [#118](https://github.com/mity/md4c/issues/118):
|
||||
Fix HTML renderer's `MD_HTML_FLAG_VERBATIM_ENTITIES` flag, exposed in the
|
||||
`md2html` utility via `--fverbatim-entities`.
|
||||
|
||||
* [#124](https://github.com/mity/md4c/issues/124):
|
||||
Fix handling of indentation of 16 or more spaces in the fenced code blocks.
|
||||
|
||||
|
||||
## Version 0.4.4
|
||||
|
||||
Changes:
|
||||
|
||||
* Make Unicode-specific code compliant to Unicode 13.0.
|
||||
|
||||
New features:
|
||||
|
||||
* The HTML renderer, developed originally as the heart of the `md2html`
|
||||
utility, is now built as a standalone library, in order to simplify its
|
||||
reuse in applications.
|
||||
|
||||
* With `MD_HTML_FLAG_SKIP_UTF8_BOM`, the HTML renderer now skips UTF-8 byte
|
||||
order mark (BOM) if the input begins with it, before passing to the Markdown
|
||||
parser.
|
||||
|
||||
`md2html` utility automatically enables the flag (unless it is custom-built
|
||||
with `-DMD4C_USE_ASCII`).
|
||||
|
||||
* With `MD_HTML_FLAG_XHTML`, The HTML renderer generates XHTML instead of
|
||||
HTML.
|
||||
|
||||
This effectively means `<br />` instead of `<br>`, `<hr />` instead of
|
||||
`<hr>`, and `<img ... />` instead of `<img ...>`.
|
||||
|
||||
`md2html` utility now understands the command line option `-x` or `--xhtml`
|
||||
enabling the XHTML mode.
|
||||
|
||||
Fixes:
|
||||
|
||||
* [#113](https://github.com/mity/md4c/issues/113):
|
||||
Add missing folding info data for the following Unicode characters:
|
||||
`U+0184`, `U+018a`, `U+01b2`, `U+01b5`, `U+01f4`, `U+0372`, `U+038f`,
|
||||
`U+1c84`, `U+1fb9`, `U+1fbb`, `U+1fd9`, `U+1fdb`, `U+1fe9`, `U+1feb`,
|
||||
`U+1ff9`, `U+1ffb`, `U+2c7f`, `U+2ced`, `U+a77b`, `U+a792`, `U+a7c9`.
|
||||
|
||||
Due the bug, the link definition label matching did not work in the case
|
||||
insensitive way for these characters.
|
||||
|
||||
|
||||
## Version 0.4.3
|
||||
|
||||
New features:
|
||||
|
||||
* With `MD_FLAG_UNDERLINE`, spans enclosed in underscore (`_foo_`) are seen
|
||||
as underline (`MD_SPAN_UNDERLINE`) rather than an ordinary emphasis or
|
||||
strong emphasis.
|
||||
|
||||
Changes:
|
||||
|
||||
* The implementation of wiki-links extension (with `MD_FLAG_WIKILINKS`) has
|
||||
been simplified.
|
||||
|
||||
- A noticeable increase of MD4C's memory footprint introduced by the
|
||||
extension implementation in 0.4.0 has been removed.
|
||||
- The priority handling towards other inline elements have been unified.
|
||||
(This affects an obscure case where syntax of an image was in place of
|
||||
wiki-link destination made the wiki-link invalid. Now *all* inline spans
|
||||
in the wiki-link destination, including the images, is suppressed.)
|
||||
- The length limitation of 100 characters now always applies to wiki-link
|
||||
destination.
|
||||
|
||||
* Recognition of strike-through spans (with the flag `MD_FLAG_STRIKETHROUGH`)
|
||||
has become much stricter and, arguably, reasonable.
|
||||
|
||||
- Only single tildes (`~`) and double tildes (`~~`) are recognized as
|
||||
strike-through marks. Longer ones are not anymore.
|
||||
- The length of the opener and closer marks have to be the same.
|
||||
- The tildes cannot open a strike-through span if a whitespace follows.
|
||||
- The tildes cannot close a strike-through span if a whitespace precedes.
|
||||
|
||||
This change follows the changes of behavior in cmark-gfm some time ago, so
|
||||
it is also beneficial from compatibility point of view.
|
||||
|
||||
* When building MD4C by hand instead of using its CMake-based build, the UTF-8
|
||||
support was by default disabled, unless explicitly asked for by defining
|
||||
a preprocessor macro `MD4C_USE_UTF8`.
|
||||
|
||||
This has been changed and the UTF-8 mode now becomes the default, no matter
|
||||
how `md4c.c` is compiled. If you need to disable it and use the ASCII-only
|
||||
mode, you have explicitly define macro `MD4C_USE_ASCII` when compiling it.
|
||||
|
||||
(The CMake-based build as provided in our repository explicitly asked for
|
||||
the UTF-8 support with `-DMD4C_USE_UTF8`. I.e. if you are using MD4C library
|
||||
built with our vanilla `CMakeLists.txt` files, this change should not affect
|
||||
you.)
|
||||
|
||||
Fixes:
|
||||
|
||||
* Fixed some string length handling in the special `MD4C_USE_UTF16` build.
|
||||
|
||||
(This does not affect you unless you are on Windows and explicitly define
|
||||
the macro when building MD4C.)
|
||||
|
||||
* [#100](https://github.com/mity/md4c/issues/100):
|
||||
Fixed an off-by-one error in the maximal length limit of some segments
|
||||
of e-mail addresses used in autolinks.
|
||||
|
||||
* [#107](https://github.com/mity/md4c/issues/107):
|
||||
Fix mis-detection of asterisk-encoded emphasis in some corner cases when
|
||||
length of the opener and closer differs, as in `***foo *bar baz***`.
|
||||
|
||||
|
||||
## Version 0.4.2
|
||||
|
||||
Fixes:
|
||||
|
||||
* [#98](https://github.com/mity/md4c/issues/98):
|
||||
Fix mis-detection of asterisk-encoded emphasis in some corner cases when
|
||||
length of the opener and closer differs, as in `**a *b c** d*`.
|
||||
|
||||
|
||||
## Version 0.4.1
|
||||
|
||||
Unfortunately, 0.4.0 has been released with badly updated ChangeLog. Fixing
|
||||
this is the only change on 0.4.1.
|
||||
|
||||
|
||||
## Version 0.4.0
|
||||
|
||||
New features:
|
||||
|
||||
* With `MD_FLAG_LATEXMATHSPANS`, LaTeX math spans (`$...$`) and LaTeX display
|
||||
math spans (`$$...$$`) are now recognized. (Note though that the HTML
|
||||
renderer outputs them verbatim in a custom `<x-equation>` tag.)
|
||||
|
||||
Contributed by [Tilman Roeder](https://github.com/dyedgreen).
|
||||
|
||||
* With `MD_FLAG_WIKILINKS`, Wiki-style links (`[[...]]`) are now recognized.
|
||||
(Note though that the HTML renderer renders them as a custom `<x-wikilink>`
|
||||
tag.)
|
||||
|
||||
Contributed by [Nils Blomqvist](https://github.com/niblo).
|
||||
|
||||
Changes:
|
||||
|
||||
* Parsing of tables (with `MD_FLAG_TABLES`) is now closer to the way how
|
||||
cmark-gfm parses tables as we do not require every row of the table to
|
||||
contain a pipe `|` anymore.
|
||||
|
||||
As a consequence, paragraphs now cannot interrupt tables. A paragraph which
|
||||
follows the table has to be delimited with a blank line.
|
||||
|
||||
Fixes:
|
||||
|
||||
* [#94](https://github.com/mity/md4c/issues/94):
|
||||
`md_build_ref_def_hashtable()`: Do not allocate more memory than strictly
|
||||
needed.
|
||||
|
||||
* [#95](https://github.com/mity/md4c/issues/95):
|
||||
`md_is_container_mark()`: Ordered list mark requires at least one digit.
|
||||
|
||||
* [#96](https://github.com/mity/md4c/issues/96):
|
||||
Some fixes for link label comparison.
|
||||
|
||||
|
||||
## Version 0.3.4
|
||||
|
||||
Changes:
|
||||
|
||||
* Make Unicode-specific code compliant to Unicode 12.1.
|
||||
|
||||
* Structure `MD_BLOCK_CODE_DETAIL` got new member `fenced_char`. Application
|
||||
can use it to detect character used to form the block fences (`` ` `` or
|
||||
`~`). In the case of indented code block, it is set to zero.
|
||||
|
||||
Fixes:
|
||||
|
||||
* [#77](https://github.com/mity/md4c/issues/77):
|
||||
Fix maximal count of digits for numerical character references, as requested
|
||||
by CommonMark specification 0.29.
|
||||
|
||||
* [#78](https://github.com/mity/md4c/issues/78):
|
||||
Fix link reference definition label matching for Unicode characters where
|
||||
the folding mapping leads to multiple codepoints, as e.g. in `ẞ` -> `SS`.
|
||||
|
||||
* [#83](https://github.com/mity/md4c/issues/83):
|
||||
Fix recognition of an empty blockquote which interrupts a paragraph.
|
||||
|
||||
|
||||
## Version 0.3.3
|
||||
|
||||
Changes:
|
||||
|
||||
* Make permissive URL autolink and permissive WWW autolink extensions stricter.
|
||||
|
||||
This brings the behavior closer to GFM and mitigates risk of false positives.
|
||||
In particular, the domain has to contain at least one dot and parenthesis
|
||||
can be part of the link destination only if `(` and `)` are balanced.
|
||||
|
||||
Fixes:
|
||||
|
||||
* [#73](https://github.com/mity/md4c/issues/73):
|
||||
Some raw HTML inputs could lead to quadratic parsing times.
|
||||
|
||||
* [#74](https://github.com/mity/md4c/issues/74):
|
||||
Fix input leading to a crash. Found by fuzzing.
|
||||
|
||||
* [#76](https://github.com/mity/md4c/issues/76):
|
||||
Fix handling of parenthesis in some corner cases of permissive URL autolink
|
||||
and permissive WWW autolink extensions.
|
||||
|
||||
|
||||
## Version 0.3.2
|
||||
|
||||
Changes:
|
||||
|
||||
* Changes mandated by CommonMark specification 0.29.
|
||||
|
||||
Most importantly, the white-space trimming rules for code spans have changed.
|
||||
At most one space/newline is trimmed from beginning/end of the code span
|
||||
(if the code span contains some non-space contents, and if it begins and
|
||||
ends with space at the same time). In all other cases the spaces in the code
|
||||
span are now left intact.
|
||||
|
||||
Other changes in behavior are in corner cases only. Refer to [CommonMark
|
||||
0.29 notes](https://github.com/commonmark/commonmark-spec/releases/tag/0.29)
|
||||
for more info.
|
||||
|
||||
Fixes:
|
||||
|
||||
* [#68](https://github.com/mity/md4c/issues/68):
|
||||
Some specific HTML blocks were not recognized when EOF follows without any
|
||||
end-of-line character.
|
||||
|
||||
* [#69](https://github.com/mity/md4c/issues/69):
|
||||
Strike-through span not working correctly when its opener mark is directly
|
||||
followed by other opener mark; or when other closer mark directly precedes
|
||||
its closer mark.
|
||||
|
||||
|
||||
## Version 0.3.1
|
||||
|
||||
Fixes:
|
||||
|
||||
* [#58](https://github.com/mity/md4c/issues/58),
|
||||
[#59](https://github.com/mity/md4c/issues/59),
|
||||
[#60](https://github.com/mity/md4c/issues/60),
|
||||
[#63](https://github.com/mity/md4c/issues/63),
|
||||
[#66](https://github.com/mity/md4c/issues/66):
|
||||
Some inputs could lead to quadratic parsing times. Thanks to Anders Kaseorg
|
||||
for finding all those issues.
|
||||
|
||||
* [#61](https://github.com/mity/md4c/issues/59):
|
||||
Flag `MD_FLAG_NOHTMLSPANS` erroneously affected also recognition of
|
||||
CommonMark autolinks.
|
||||
|
||||
|
||||
## Version 0.3.0
|
||||
|
||||
New features:
|
||||
|
||||
* Add extension for GitHub-style task lists:
|
||||
|
||||
```
|
||||
* [x] foo
|
||||
* [x] bar
|
||||
* [ ] baz
|
||||
```
|
||||
|
||||
(It has to be explicitly enabled with `MD_FLAG_TASKLISTS`.)
|
||||
|
||||
* Added support for building as a shared library. On non-Windows platforms,
|
||||
this is now default behavior; on Windows static library is still the default.
|
||||
The CMake option `BUILD_SHARED_LIBS` can be used to request one or the other
|
||||
explicitly.
|
||||
|
||||
Contributed by Lisandro Damián Nicanor Pérez Meyer.
|
||||
|
||||
* Renamed structure `MD_RENDERER` to `MD_PARSER` and refactorize its contents
|
||||
a little bit. Note this is source-level incompatible and initialization code
|
||||
in apps may need to be updated.
|
||||
|
||||
The aim of the change is to be more friendly for long-term ABI compatibility
|
||||
we shall maintain, starting with this release.
|
||||
|
||||
* Added `CHANGELOG.md` (this file).
|
||||
|
||||
* Make sure `md_process_table_row()` reports the same count of table cells for
|
||||
all table rows, no matter how broken the input is. The cell count is derived
|
||||
from table underline line. Bogus cells in other rows are silently ignored.
|
||||
Missing cells in other rows are reported as empty ones.
|
||||
|
||||
Fixes:
|
||||
|
||||
* CID 1475544:
|
||||
Calling `md_free_attribute()` on uninitialized data.
|
||||
|
||||
* [#47](https://github.com/mity/md4c/issues/47):
|
||||
Using bad offsets in `md_is_entity_str()`, in some cases leading to buffer
|
||||
overflow.
|
||||
|
||||
* [#51](https://github.com/mity/md4c/issues/51):
|
||||
Segfault in `md_process_table_cell()`.
|
||||
|
||||
* [#53](https://github.com/mity/md4c/issues/53):
|
||||
With `MD_FLAG_PERMISSIVEURLAUTOLINKS` or `MD_FLAG_PERMISSIVEWWWAUTOLINKS`
|
||||
we could generate bad output for ordinary Markdown links, if a non-space
|
||||
character immediately follows like e.g. in `[link](http://github.com)X`.
|
||||
|
||||
|
||||
## Version 0.2.7
|
||||
|
||||
This was the last version before the changelog has been added.
|
||||
22
uppsrc/plugin/md/MD4C/LICENSE.md
Normal file
22
uppsrc/plugin/md/MD4C/LICENSE.md
Normal file
|
|
@ -0,0 +1,22 @@
|
|||
|
||||
# The MIT License (MIT)
|
||||
|
||||
Copyright © 2016-2020 Martin Mitáš
|
||||
|
||||
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.
|
||||
297
uppsrc/plugin/md/MD4C/README.md
Normal file
297
uppsrc/plugin/md/MD4C/README.md
Normal file
|
|
@ -0,0 +1,297 @@
|
|||
[](https://travis-ci.com/mity/md4c)
|
||||
[](https://ci.appveyor.com/project/mity/md4c/branch/master)
|
||||
[](https://codecov.io/github/mity/md4c)
|
||||
[](https://scan.coverity.com/projects/mity-md4c)
|
||||
|
||||
|
||||
# MD4C Readme
|
||||
|
||||
* Home: http://github.com/mity/md4c
|
||||
* Wiki: http://github.com/mity/md4c/wiki
|
||||
* Issue tracker: http://github.com/mity/md4c/issues
|
||||
|
||||
MD4C stands for "Markdown for C" and that's exactly what this project is about.
|
||||
|
||||
|
||||
## What is Markdown
|
||||
|
||||
In short, Markdown is the markup language this `README.md` file is written in.
|
||||
|
||||
The following resources can explain more if you are unfamiliar with it:
|
||||
* [Wikipedia article](http://en.wikipedia.org/wiki/Markdown)
|
||||
* [CommonMark site](http://commonmark.org)
|
||||
|
||||
|
||||
## What is MD4C
|
||||
|
||||
MD4C is Markdown parser implementation in C, with the following features:
|
||||
|
||||
* **Compliance:** Generally, MD4C aims to be compliant to the latest version of
|
||||
[CommonMark specification](http://spec.commonmark.org/). Currently, we are
|
||||
fully compliant to CommonMark 0.29.
|
||||
|
||||
* **Extensions:** MD4C supports some commonly requested and accepted extensions.
|
||||
See below.
|
||||
|
||||
* **Performance:** MD4C is [very fast](https://talk.commonmark.org/t/2520).
|
||||
|
||||
* **Compactness:** MD4C parser is implemented in one source file and one header
|
||||
file. There are no dependencies other than standard C library.
|
||||
|
||||
* **Embedding:** MD4C parser is easy to reuse in other projects, its API is
|
||||
very straightforward: There is actually just one function, `md_parse()`.
|
||||
|
||||
* **Push model:** MD4C parses the complete document and calls few callback
|
||||
functions provided by the application to inform it about a start/end of
|
||||
every block, a start/end of every span, and with any textual contents.
|
||||
|
||||
* **Portability:** MD4C builds and works on Windows and POSIX-compliant OSes.
|
||||
(It should be simple to make it run also on most other platforms, at least as
|
||||
long as the platform provides C standard library, including a heap memory
|
||||
management.)
|
||||
|
||||
* **Encoding:** MD4C by default expects UTF-8 encoding of the input document.
|
||||
But it can be compiled to recognize ASCII-only control characters (i.e. to
|
||||
disable all Unicode-specific code), or (on Windows) to expect UTF-16 (i.e.
|
||||
what is on Windows commonly called just "Unicode"). See more details below.
|
||||
|
||||
* **Permissive license:** MD4C is available under the [MIT license](LICENSE.md).
|
||||
|
||||
|
||||
## Using MD4C
|
||||
|
||||
### Parsing Markdown
|
||||
|
||||
If you need just to parse a Markdown document, you need to include `md4c.h`
|
||||
and link against MD4C library (`-lmd4c`); or alternatively add `md4c.[hc]`
|
||||
directly to your code base as the parser is only implemented in the single C
|
||||
source file.
|
||||
|
||||
The main provided function is `md_parse()`. It takes a text in the Markdown
|
||||
syntax and a pointer to a structure which provides pointers to several callback
|
||||
functions.
|
||||
|
||||
As `md_parse()` processes the input, it calls the callbacks (when entering or
|
||||
leaving any Markdown block or span; and when outputting any textual content of
|
||||
the document), allowing application to convert it into another format or render
|
||||
it onto the screen.
|
||||
|
||||
|
||||
### Converting to HTML
|
||||
|
||||
If you need to convert Markdown to HTML, include `md4c-html.h` and link against
|
||||
MD4C-HTML library (`-lmd4c-html`); or alternatively add the sources `md4c.[hc]`,
|
||||
`md4c-html.[hc]` and `entity.[hc]` into your code base.
|
||||
|
||||
To convert a Markdown input, call `md_html()` function. It takes the Markdown
|
||||
input and calls the provided callback function. The callback is fed with
|
||||
chunks of the HTML output. Typical callback implementation just appends the
|
||||
chunks into a buffer or writes them to a file.
|
||||
|
||||
|
||||
## Markdown Extensions
|
||||
|
||||
The default behavior is to recognize only Markdown syntax defined by the
|
||||
[CommonMark specification](http://spec.commonmark.org/).
|
||||
|
||||
However, with appropriate flags, the behavior can be tuned to enable some
|
||||
extensions:
|
||||
|
||||
* With the flag `MD_FLAG_COLLAPSEWHITESPACE`, a non-trivial whitespace is
|
||||
collapsed into a single space.
|
||||
|
||||
* With the flag `MD_FLAG_TABLES`, GitHub-style tables are supported.
|
||||
|
||||
* With the flag `MD_FLAG_TASKLISTS`, GitHub-style task lists are supported.
|
||||
|
||||
* With the flag `MD_FLAG_STRIKETHROUGH`, strike-through spans are enabled
|
||||
(text enclosed in tilde marks, e.g. `~foo bar~`).
|
||||
|
||||
* With the flag `MD_FLAG_PERMISSIVEURLAUTOLINKS` permissive URL autolinks
|
||||
(not enclosed in `<` and `>`) are supported.
|
||||
|
||||
* With the flag `MD_FLAG_PERMISSIVEEMAILAUTOLINKS`, permissive e-mail
|
||||
autolinks (not enclosed in `<` and `>`) are supported.
|
||||
|
||||
* With the flag `MD_FLAG_PERMISSIVEWWWAUTOLINKS` permissive WWW autolinks
|
||||
without any scheme specified (e.g. `www.example.com`) are supported. MD4C
|
||||
then assumes `http:` scheme.
|
||||
|
||||
* With the flag `MD_FLAG_LATEXMATHSPANS` LaTeX math spans (`$...$`) and
|
||||
LaTeX display math spans (`$$...$$`) are supported. (Note though that the
|
||||
HTML renderer outputs them verbatim in a custom tag `<x-equation>`.)
|
||||
|
||||
* With the flag `MD_FLAG_WIKILINKS`, wiki-style links (`[[link label]]` and
|
||||
`[[target article|link label]]`) are supported. (Note that the HTML renderer
|
||||
outputs them in a custom tag `<x-wikilink>`.)
|
||||
|
||||
* With the flag `MD_FLAG_UNDERLINE`, underscore (`_`) denotes an underline
|
||||
instead of an ordinary emphasis or strong emphasis.
|
||||
|
||||
Few features of CommonMark (those some people see as mis-features) may be
|
||||
disabled with the following flags:
|
||||
|
||||
* With the flag `MD_FLAG_NOHTMLSPANS` or `MD_FLAG_NOHTMLBLOCKS`, raw inline
|
||||
HTML or raw HTML blocks respectively are disabled.
|
||||
|
||||
* With the flag `MD_FLAG_NOINDENTEDCODEBLOCKS`, indented code blocks are
|
||||
disabled.
|
||||
|
||||
|
||||
## Input/Output Encoding
|
||||
|
||||
The CommonMark specification declares that any sequence of Unicode code points
|
||||
is a valid CommonMark document.
|
||||
|
||||
But, under a closer inspection, Unicode plays any role in few very specific
|
||||
situations when parsing Markdown documents:
|
||||
|
||||
1. For detection of word boundaries when processing emphasis and strong
|
||||
emphasis, some classification of Unicode characters (whether it is
|
||||
a whitespace or a punctuation) is needed.
|
||||
|
||||
2. For (case-insensitive) matching of a link reference label with the
|
||||
corresponding link reference definition, Unicode case folding is used.
|
||||
|
||||
3. For translating HTML entities (e.g. `&`) and numeric character
|
||||
references (e.g. `#` or `ಫ`) into their Unicode equivalents.
|
||||
|
||||
However note MD4C leaves this translation on the renderer/application; as
|
||||
the renderer is supposed to really know output encoding and whether it
|
||||
really needs to perform this kind of translation. (For example, when the
|
||||
renderer outputs HTML, it may leave the entities untranslated and defer the
|
||||
work to a web browser.)
|
||||
|
||||
MD4C relies on this property of the CommonMark and the implementation is, to
|
||||
a large degree, encoding-agnostic. Most of MD4C code only assumes that the
|
||||
encoding of your choice is compatible with ASCII. I.e. that the codepoints
|
||||
below 128 have the same numeric values as ASCII.
|
||||
|
||||
Any input MD4C does not understand is simply seen as part of the document text
|
||||
and sent to the renderer's callback functions unchanged.
|
||||
|
||||
The two situations (word boundary detection and link reference matching) where
|
||||
MD4C has to understand Unicode are handled as specified by the following
|
||||
preprocessor macros (as specified at the time MD4C is being built):
|
||||
|
||||
* If preprocessor macro `MD4C_USE_UTF8` is defined, MD4C assumes UTF-8 for the
|
||||
word boundary detection and for the case-insensitive matching of link labels.
|
||||
|
||||
When none of these macros is explicitly used, this is the default behavior.
|
||||
|
||||
* On Windows, if preprocessor macro `MD4C_USE_UTF16` is defined, MD4C uses
|
||||
`WCHAR` instead of `char` and assumes UTF-16 encoding in those situations.
|
||||
(UTF-16 is what Windows developers usually call just "Unicode" and what
|
||||
Win32API generally works with.)
|
||||
|
||||
Note that because this macro affects also the types in `md4c.h`, you have
|
||||
to define the macro both when building MD4C as well as when including
|
||||
`md4c.h`.
|
||||
|
||||
Also note this is only supported in the parser (`md4c.[hc]`). The HTML
|
||||
renderer does not support this and you will have to write your own custom
|
||||
renderer to use this feature.
|
||||
|
||||
* If preprocessor macro `MD4C_USE_ASCII` is defined, MD4C assumes nothing but
|
||||
an ASCII input.
|
||||
|
||||
That effectively means that non-ASCII whitespace or punctuation characters
|
||||
won't be recognized as such and that link reference matching will work in
|
||||
a case-insensitive way only for ASCII letters (`[a-zA-Z]`).
|
||||
|
||||
|
||||
## Documentation
|
||||
|
||||
The API of the parser is quite well documented in the comments in the `md4c.h`.
|
||||
Similarly, the markdown-to-html API is described in its header `md4c-html.h`.
|
||||
|
||||
There is also [project wiki](http://github.com/mity/md4c/wiki) which provides
|
||||
some more comprehensive documentation. However note it is incomplete and some
|
||||
details may be somewhat outdated.
|
||||
|
||||
|
||||
## FAQ
|
||||
|
||||
**Q: How does MD4C compare to a parser XY?**
|
||||
|
||||
**A:** Some other implementations combine Markdown parser and HTML generator
|
||||
into a single entangled code hidden behind an interface which just allows the
|
||||
conversion from Markdown to HTML. They are often unusable if you want to
|
||||
process the input in any other way.
|
||||
|
||||
Even when the parsing is available as a standalone feature, most parsers (if
|
||||
not all of them; at least within the scope of C/C++ language) are full DOM-like
|
||||
parsers: They construct abstract syntax tree (AST) representation of the whole
|
||||
Markdown document. That takes time and it leads to bigger memory footprint.
|
||||
|
||||
It's completely fine as long as you really need it. If you don't need the full
|
||||
AST, there is a very high chance that using MD4C will be substantially faster
|
||||
and less hungry in terms of memory consumption.
|
||||
|
||||
Last but not least, some Markdown parsers are implemented in a naive way. When
|
||||
fed with a [smartly crafted input pattern](test/pathological_tests.py), they
|
||||
may exhibit quadratic (or even worse) parsing times. What MD4C can still parse
|
||||
in a fraction of second may turn into long minutes or possibly hours with them.
|
||||
Hence, when such a naive parser is used to process an input from an untrusted
|
||||
source, the possibility of denial-of-service attacks becomes a real danger.
|
||||
|
||||
A lot of our effort went into providing linear parsing times no matter what
|
||||
kind of crazy input MD4C parser is fed with. (If you encounter an input pattern
|
||||
which leads to a sub-linear parsing times, please do not hesitate and report it
|
||||
as a bug.)
|
||||
|
||||
**Q: Does MD4C perform any input validation?**
|
||||
|
||||
**A:** No. And we are proud of it. :-)
|
||||
|
||||
CommonMark specification states that any sequence of Unicode characters is
|
||||
a valid Markdown document. (In practice, this more or less always means UTF-8
|
||||
encoding.)
|
||||
|
||||
In other words, according to the specification, it does not matter whether some
|
||||
Markdown syntax construction is in some way broken or not. If it is broken, it
|
||||
will simply not be recognized and the parser should see it just as a verbatim
|
||||
text.
|
||||
|
||||
MD4C takes this a step further: It sees any sequence of bytes as a valid input,
|
||||
following completely the GIGO philosophy (garbage in, garbage out). I.e. any
|
||||
ill-formed UTF-8 byte sequence will propagate to the respective callback as
|
||||
a part of the text.
|
||||
|
||||
If you need to validate that the input is, say, a well-formed UTF-8 document,
|
||||
you have to do it on your own. The easiest way how to do this is to simply
|
||||
validate the whole document before passing it to the MD4C parser.
|
||||
|
||||
|
||||
## License
|
||||
|
||||
MD4C is covered with MIT license, see the file `LICENSE.md`.
|
||||
|
||||
|
||||
## Links to Related Projects
|
||||
|
||||
Ports and bindings to other languages:
|
||||
|
||||
* [commonmark-d](https://github.com/AuburnSounds/commonmark-d):
|
||||
Port of MD4C to D language.
|
||||
|
||||
* [markdown-wasm](https://github.com/rsms/markdown-wasm):
|
||||
Port of MD4C to WebAssembly.
|
||||
|
||||
* [PyMD4C](https://github.com/dominickpastore/pymd4c):
|
||||
Python bindings for MD4C
|
||||
|
||||
Software using MD4C:
|
||||
|
||||
* [QOwnNotes](https://www.qownnotes.org/):
|
||||
A plain-text file notepad and todo-list manager with markdown support and
|
||||
ownCloud / Nextcloud integration.
|
||||
|
||||
* [Qt](https://www.qt.io/):
|
||||
Cross-platform C++ GUI framework.
|
||||
|
||||
* [Textosaurus](https://github.com/martinrotter/textosaurus):
|
||||
Cross-platform text editor based on Qt and Scintilla.
|
||||
|
||||
* [8th](https://8th-dev.com/):
|
||||
Cross-platform concatenative programming language.
|
||||
6343
uppsrc/plugin/md/MD4C/md4c.c
Normal file
6343
uppsrc/plugin/md/MD4C/md4c.c
Normal file
File diff suppressed because it is too large
Load diff
405
uppsrc/plugin/md/MD4C/md4c.h
Normal file
405
uppsrc/plugin/md/MD4C/md4c.h
Normal file
|
|
@ -0,0 +1,405 @@
|
|||
/*
|
||||
* MD4C: Markdown parser for C
|
||||
* (http://github.com/mity/md4c)
|
||||
*
|
||||
* Copyright (c) 2016-2020 Martin Mitas
|
||||
*
|
||||
* 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.
|
||||
*/
|
||||
|
||||
#ifndef MD4C_H
|
||||
#define MD4C_H
|
||||
|
||||
#ifdef __cplusplus
|
||||
extern "C" {
|
||||
#endif
|
||||
|
||||
#if defined MD4C_USE_UTF16
|
||||
/* Magic to support UTF-16. Note that in order to use it, you have to define
|
||||
* the macro MD4C_USE_UTF16 both when building MD4C as well as when
|
||||
* including this header in your code. */
|
||||
#ifdef _WIN32
|
||||
#include <windows.h>
|
||||
typedef WCHAR MD_CHAR;
|
||||
#else
|
||||
#error MD4C_USE_UTF16 is only supported on Windows.
|
||||
#endif
|
||||
#else
|
||||
typedef char MD_CHAR;
|
||||
#endif
|
||||
|
||||
typedef unsigned MD_SIZE;
|
||||
typedef unsigned MD_OFFSET;
|
||||
|
||||
|
||||
/* Block represents a part of document hierarchy structure like a paragraph
|
||||
* or list item.
|
||||
*/
|
||||
typedef enum MD_BLOCKTYPE {
|
||||
/* <body>...</body> */
|
||||
MD_BLOCK_DOC = 0,
|
||||
|
||||
/* <blockquote>...</blockquote> */
|
||||
MD_BLOCK_QUOTE,
|
||||
|
||||
/* <ul>...</ul>
|
||||
* Detail: Structure MD_BLOCK_UL_DETAIL. */
|
||||
MD_BLOCK_UL,
|
||||
|
||||
/* <ol>...</ol>
|
||||
* Detail: Structure MD_BLOCK_OL_DETAIL. */
|
||||
MD_BLOCK_OL,
|
||||
|
||||
/* <li>...</li>
|
||||
* Detail: Structure MD_BLOCK_LI_DETAIL. */
|
||||
MD_BLOCK_LI,
|
||||
|
||||
/* <hr> */
|
||||
MD_BLOCK_HR,
|
||||
|
||||
/* <h1>...</h1> (for levels up to 6)
|
||||
* Detail: Structure MD_BLOCK_H_DETAIL. */
|
||||
MD_BLOCK_H,
|
||||
|
||||
/* <pre><code>...</code></pre>
|
||||
* Note the text lines within code blocks are terminated with '\n'
|
||||
* instead of explicit MD_TEXT_BR. */
|
||||
MD_BLOCK_CODE,
|
||||
|
||||
/* Raw HTML block. This itself does not correspond to any particular HTML
|
||||
* tag. The contents of it _is_ raw HTML source intended to be put
|
||||
* in verbatim form to the HTML output. */
|
||||
MD_BLOCK_HTML,
|
||||
|
||||
/* <p>...</p> */
|
||||
MD_BLOCK_P,
|
||||
|
||||
/* <table>...</table> and its contents.
|
||||
* Detail: Structure MD_BLOCK_TABLE_DETAIL (for MD_BLOCK_TABLE),
|
||||
* structure MD_BLOCK_TD_DETAIL (for MD_BLOCK_TH and MD_BLOCK_TD)
|
||||
* Note all of these are used only if extension MD_FLAG_TABLES is enabled. */
|
||||
MD_BLOCK_TABLE,
|
||||
MD_BLOCK_THEAD,
|
||||
MD_BLOCK_TBODY,
|
||||
MD_BLOCK_TR,
|
||||
MD_BLOCK_TH,
|
||||
MD_BLOCK_TD
|
||||
} MD_BLOCKTYPE;
|
||||
|
||||
/* Span represents an in-line piece of a document which should be rendered with
|
||||
* the same font, color and other attributes. A sequence of spans forms a block
|
||||
* like paragraph or list item. */
|
||||
typedef enum MD_SPANTYPE {
|
||||
/* <em>...</em> */
|
||||
MD_SPAN_EM,
|
||||
|
||||
/* <strong>...</strong> */
|
||||
MD_SPAN_STRONG,
|
||||
|
||||
/* <a href="xxx">...</a>
|
||||
* Detail: Structure MD_SPAN_A_DETAIL. */
|
||||
MD_SPAN_A,
|
||||
|
||||
/* <img src="xxx">...</a>
|
||||
* Detail: Structure MD_SPAN_IMG_DETAIL.
|
||||
* Note: Image text can contain nested spans and even nested images.
|
||||
* If rendered into ALT attribute of HTML <IMG> tag, it's responsibility
|
||||
* of the parser to deal with it.
|
||||
*/
|
||||
MD_SPAN_IMG,
|
||||
|
||||
/* <code>...</code> */
|
||||
MD_SPAN_CODE,
|
||||
|
||||
/* <del>...</del>
|
||||
* Note: Recognized only when MD_FLAG_STRIKETHROUGH is enabled.
|
||||
*/
|
||||
MD_SPAN_DEL,
|
||||
|
||||
/* For recognizing inline ($) and display ($$) equations
|
||||
* Note: Recognized only when MD_FLAG_LATEXMATHSPANS is enabled.
|
||||
*/
|
||||
MD_SPAN_LATEXMATH,
|
||||
MD_SPAN_LATEXMATH_DISPLAY,
|
||||
|
||||
/* Wiki links
|
||||
* Note: Recognized only when MD_FLAG_WIKILINKS is enabled.
|
||||
*/
|
||||
MD_SPAN_WIKILINK,
|
||||
|
||||
/* <u>...</u>
|
||||
* Note: Recognized only when MD_FLAG_UNDERLINE is enabled. */
|
||||
MD_SPAN_U
|
||||
} MD_SPANTYPE;
|
||||
|
||||
/* Text is the actual textual contents of span. */
|
||||
typedef enum MD_TEXTTYPE {
|
||||
/* Normal text. */
|
||||
MD_TEXT_NORMAL = 0,
|
||||
|
||||
/* NULL character. CommonMark requires replacing NULL character with
|
||||
* the replacement char U+FFFD, so this allows caller to do that easily. */
|
||||
MD_TEXT_NULLCHAR,
|
||||
|
||||
/* Line breaks.
|
||||
* Note these are not sent from blocks with verbatim output (MD_BLOCK_CODE
|
||||
* or MD_BLOCK_HTML). In such cases, '\n' is part of the text itself. */
|
||||
MD_TEXT_BR, /* <br> (hard break) */
|
||||
MD_TEXT_SOFTBR, /* '\n' in source text where it is not semantically meaningful (soft break) */
|
||||
|
||||
/* Entity.
|
||||
* (a) Named entity, e.g.
|
||||
* (Note MD4C does not have a list of known entities.
|
||||
* Anything matching the regexp /&[A-Za-z][A-Za-z0-9]{1,47};/ is
|
||||
* treated as a named entity.)
|
||||
* (b) Numerical entity, e.g. Ӓ
|
||||
* (c) Hexadecimal entity, e.g. ካ
|
||||
*
|
||||
* As MD4C is mostly encoding agnostic, application gets the verbatim
|
||||
* entity text into the MD_PARSER::text_callback(). */
|
||||
MD_TEXT_ENTITY,
|
||||
|
||||
/* Text in a code block (inside MD_BLOCK_CODE) or inlined code (`code`).
|
||||
* If it is inside MD_BLOCK_CODE, it includes spaces for indentation and
|
||||
* '\n' for new lines. MD_TEXT_BR and MD_TEXT_SOFTBR are not sent for this
|
||||
* kind of text. */
|
||||
MD_TEXT_CODE,
|
||||
|
||||
/* Text is a raw HTML. If it is contents of a raw HTML block (i.e. not
|
||||
* an inline raw HTML), then MD_TEXT_BR and MD_TEXT_SOFTBR are not used.
|
||||
* The text contains verbatim '\n' for the new lines. */
|
||||
MD_TEXT_HTML,
|
||||
|
||||
/* Text is inside an equation. This is processed the same way as inlined code
|
||||
* spans (`code`). */
|
||||
MD_TEXT_LATEXMATH
|
||||
} MD_TEXTTYPE;
|
||||
|
||||
|
||||
/* Alignment enumeration. */
|
||||
typedef enum MD_ALIGN {
|
||||
MD_ALIGN_DEFAULT = 0, /* When unspecified. */
|
||||
MD_ALIGN_LEFT,
|
||||
MD_ALIGN_CENTER,
|
||||
MD_ALIGN_RIGHT
|
||||
} MD_ALIGN;
|
||||
|
||||
|
||||
/* String attribute.
|
||||
*
|
||||
* This wraps strings which are outside of a normal text flow and which are
|
||||
* propagated within various detailed structures, but which still may contain
|
||||
* string portions of different types like e.g. entities.
|
||||
*
|
||||
* So, for example, lets consider this image:
|
||||
*
|
||||
* ![image alt text](http://example.org/image.png 'foo " bar')
|
||||
*
|
||||
* The image alt text is propagated as a normal text via the MD_PARSER::text()
|
||||
* callback. However, the image title ('foo " bar') is propagated as
|
||||
* MD_ATTRIBUTE in MD_SPAN_IMG_DETAIL::title.
|
||||
*
|
||||
* Then the attribute MD_SPAN_IMG_DETAIL::title shall provide the following:
|
||||
* -- [0]: "foo " (substr_types[0] == MD_TEXT_NORMAL; substr_offsets[0] == 0)
|
||||
* -- [1]: """ (substr_types[1] == MD_TEXT_ENTITY; substr_offsets[1] == 4)
|
||||
* -- [2]: " bar" (substr_types[2] == MD_TEXT_NORMAL; substr_offsets[2] == 10)
|
||||
* -- [3]: (n/a) (n/a ; substr_offsets[3] == 14)
|
||||
*
|
||||
* Note that these invariants are always guaranteed:
|
||||
* -- substr_offsets[0] == 0
|
||||
* -- substr_offsets[LAST+1] == size
|
||||
* -- Currently, only MD_TEXT_NORMAL, MD_TEXT_ENTITY, MD_TEXT_NULLCHAR
|
||||
* substrings can appear. This could change only of the specification
|
||||
* changes.
|
||||
*/
|
||||
typedef struct MD_ATTRIBUTE {
|
||||
const MD_CHAR* text;
|
||||
MD_SIZE size;
|
||||
const MD_TEXTTYPE* substr_types;
|
||||
const MD_OFFSET* substr_offsets;
|
||||
} MD_ATTRIBUTE;
|
||||
|
||||
|
||||
/* Detailed info for MD_BLOCK_UL. */
|
||||
typedef struct MD_BLOCK_UL_DETAIL {
|
||||
int is_tight; /* Non-zero if tight list, zero if loose. */
|
||||
MD_CHAR mark; /* Item bullet character in MarkDown source of the list, e.g. '-', '+', '*'. */
|
||||
} MD_BLOCK_UL_DETAIL;
|
||||
|
||||
/* Detailed info for MD_BLOCK_OL. */
|
||||
typedef struct MD_BLOCK_OL_DETAIL {
|
||||
unsigned start; /* Start index of the ordered list. */
|
||||
int is_tight; /* Non-zero if tight list, zero if loose. */
|
||||
MD_CHAR mark_delimiter; /* Character delimiting the item marks in MarkDown source, e.g. '.' or ')' */
|
||||
} MD_BLOCK_OL_DETAIL;
|
||||
|
||||
/* Detailed info for MD_BLOCK_LI. */
|
||||
typedef struct MD_BLOCK_LI_DETAIL {
|
||||
int is_task; /* Can be non-zero only with MD_FLAG_TASKLISTS */
|
||||
MD_CHAR task_mark; /* If is_task, then one of 'x', 'X' or ' '. Undefined otherwise. */
|
||||
MD_OFFSET task_mark_offset; /* If is_task, then offset in the input of the char between '[' and ']'. */
|
||||
} MD_BLOCK_LI_DETAIL;
|
||||
|
||||
/* Detailed info for MD_BLOCK_H. */
|
||||
typedef struct MD_BLOCK_H_DETAIL {
|
||||
unsigned level; /* Header level (1 - 6) */
|
||||
} MD_BLOCK_H_DETAIL;
|
||||
|
||||
/* Detailed info for MD_BLOCK_CODE. */
|
||||
typedef struct MD_BLOCK_CODE_DETAIL {
|
||||
MD_ATTRIBUTE info;
|
||||
MD_ATTRIBUTE lang;
|
||||
MD_CHAR fence_char; /* The character used for fenced code block; or zero for indented code block. */
|
||||
} MD_BLOCK_CODE_DETAIL;
|
||||
|
||||
/* Detailed info for MD_BLOCK_TABLE. */
|
||||
typedef struct MD_BLOCK_TABLE_DETAIL {
|
||||
unsigned col_count; /* Count of columns in the table. */
|
||||
unsigned head_row_count; /* Count of rows in the table header (currently always 1) */
|
||||
unsigned body_row_count; /* Count of rows in the table body */
|
||||
} MD_BLOCK_TABLE_DETAIL;
|
||||
|
||||
/* Detailed info for MD_BLOCK_TH and MD_BLOCK_TD. */
|
||||
typedef struct MD_BLOCK_TD_DETAIL {
|
||||
MD_ALIGN align;
|
||||
} MD_BLOCK_TD_DETAIL;
|
||||
|
||||
/* Detailed info for MD_SPAN_A. */
|
||||
typedef struct MD_SPAN_A_DETAIL {
|
||||
MD_ATTRIBUTE href;
|
||||
MD_ATTRIBUTE title;
|
||||
} MD_SPAN_A_DETAIL;
|
||||
|
||||
/* Detailed info for MD_SPAN_IMG. */
|
||||
typedef struct MD_SPAN_IMG_DETAIL {
|
||||
MD_ATTRIBUTE src;
|
||||
MD_ATTRIBUTE title;
|
||||
} MD_SPAN_IMG_DETAIL;
|
||||
|
||||
/* Detailed info for MD_SPAN_WIKILINK. */
|
||||
typedef struct MD_SPAN_WIKILINK {
|
||||
MD_ATTRIBUTE target;
|
||||
} MD_SPAN_WIKILINK_DETAIL;
|
||||
|
||||
/* Flags specifying extensions/deviations from CommonMark specification.
|
||||
*
|
||||
* By default (when MD_PARSER::flags == 0), we follow CommonMark specification.
|
||||
* The following flags may allow some extensions or deviations from it.
|
||||
*/
|
||||
#define MD_FLAG_COLLAPSEWHITESPACE 0x0001 /* In MD_TEXT_NORMAL, collapse non-trivial whitespace into single ' ' */
|
||||
#define MD_FLAG_PERMISSIVEATXHEADERS 0x0002 /* Do not require space in ATX headers ( ###header ) */
|
||||
#define MD_FLAG_PERMISSIVEURLAUTOLINKS 0x0004 /* Recognize URLs as autolinks even without '<', '>' */
|
||||
#define MD_FLAG_PERMISSIVEEMAILAUTOLINKS 0x0008 /* Recognize e-mails as autolinks even without '<', '>' and 'mailto:' */
|
||||
#define MD_FLAG_NOINDENTEDCODEBLOCKS 0x0010 /* Disable indented code blocks. (Only fenced code works.) */
|
||||
#define MD_FLAG_NOHTMLBLOCKS 0x0020 /* Disable raw HTML blocks. */
|
||||
#define MD_FLAG_NOHTMLSPANS 0x0040 /* Disable raw HTML (inline). */
|
||||
#define MD_FLAG_TABLES 0x0100 /* Enable tables extension. */
|
||||
#define MD_FLAG_STRIKETHROUGH 0x0200 /* Enable strikethrough extension. */
|
||||
#define MD_FLAG_PERMISSIVEWWWAUTOLINKS 0x0400 /* Enable WWW autolinks (even without any scheme prefix, if they begin with 'www.') */
|
||||
#define MD_FLAG_TASKLISTS 0x0800 /* Enable task list extension. */
|
||||
#define MD_FLAG_LATEXMATHSPANS 0x1000 /* Enable $ and $$ containing LaTeX equations. */
|
||||
#define MD_FLAG_WIKILINKS 0x2000 /* Enable wiki links extension. */
|
||||
#define MD_FLAG_UNDERLINE 0x4000 /* Enable underline extension (and disables '_' for normal emphasis). */
|
||||
|
||||
#define MD_FLAG_PERMISSIVEAUTOLINKS (MD_FLAG_PERMISSIVEEMAILAUTOLINKS | MD_FLAG_PERMISSIVEURLAUTOLINKS | MD_FLAG_PERMISSIVEWWWAUTOLINKS)
|
||||
#define MD_FLAG_NOHTML (MD_FLAG_NOHTMLBLOCKS | MD_FLAG_NOHTMLSPANS)
|
||||
|
||||
/* Convenient sets of flags corresponding to well-known Markdown dialects.
|
||||
*
|
||||
* Note we may only support subset of features of the referred dialect.
|
||||
* The constant just enables those extensions which bring us as close as
|
||||
* possible given what features we implement.
|
||||
*
|
||||
* ABI compatibility note: Meaning of these can change in time as new
|
||||
* extensions, bringing the dialect closer to the original, are implemented.
|
||||
*/
|
||||
#define MD_DIALECT_COMMONMARK 0
|
||||
#define MD_DIALECT_GITHUB (MD_FLAG_PERMISSIVEAUTOLINKS | MD_FLAG_TABLES | MD_FLAG_STRIKETHROUGH | MD_FLAG_TASKLISTS)
|
||||
|
||||
/* Parser structure.
|
||||
*/
|
||||
typedef struct MD_PARSER {
|
||||
/* Reserved. Set to zero.
|
||||
*/
|
||||
unsigned abi_version;
|
||||
|
||||
/* Dialect options. Bitmask of MD_FLAG_xxxx values.
|
||||
*/
|
||||
unsigned flags;
|
||||
|
||||
/* Caller-provided rendering callbacks.
|
||||
*
|
||||
* For some block/span types, more detailed information is provided in a
|
||||
* type-specific structure pointed by the argument 'detail'.
|
||||
*
|
||||
* The last argument of all callbacks, 'userdata', is just propagated from
|
||||
* md_parse() and is available for any use by the application.
|
||||
*
|
||||
* Note any strings provided to the callbacks as their arguments or as
|
||||
* members of any detail structure are generally not zero-terminated.
|
||||
* Application has to take the respective size information into account.
|
||||
*
|
||||
* Any rendering callback may abort further parsing of the document by
|
||||
* returning non-zero.
|
||||
*/
|
||||
int (*enter_block)(MD_BLOCKTYPE /*type*/, void* /*detail*/, void* /*userdata*/);
|
||||
int (*leave_block)(MD_BLOCKTYPE /*type*/, void* /*detail*/, void* /*userdata*/);
|
||||
|
||||
int (*enter_span)(MD_SPANTYPE /*type*/, void* /*detail*/, void* /*userdata*/);
|
||||
int (*leave_span)(MD_SPANTYPE /*type*/, void* /*detail*/, void* /*userdata*/);
|
||||
|
||||
int (*text)(MD_TEXTTYPE /*type*/, const MD_CHAR* /*text*/, MD_SIZE /*size*/, void* /*userdata*/);
|
||||
|
||||
/* Debug callback. Optional (may be NULL).
|
||||
*
|
||||
* If provided and something goes wrong, this function gets called.
|
||||
* This is intended for debugging and problem diagnosis for developers;
|
||||
* it is not intended to provide any errors suitable for displaying to an
|
||||
* end user.
|
||||
*/
|
||||
void (*debug_log)(const char* /*msg*/, void* /*userdata*/);
|
||||
|
||||
/* Reserved. Set to NULL.
|
||||
*/
|
||||
void (*syntax)(void);
|
||||
} MD_PARSER;
|
||||
|
||||
|
||||
/* For backward compatibility. Do not use in new code.
|
||||
*/
|
||||
typedef MD_PARSER MD_RENDERER;
|
||||
|
||||
|
||||
/* Parse the Markdown document stored in the string 'text' of size 'size'.
|
||||
* The parser provides callbacks to be called during the parsing so the
|
||||
* caller can render the document on the screen or convert the Markdown
|
||||
* to another format.
|
||||
*
|
||||
* Zero is returned on success. If a runtime error occurs (e.g. a memory
|
||||
* fails), -1 is returned. If the processing is aborted due any callback
|
||||
* returning non-zero, the return value of the callback is returned.
|
||||
*/
|
||||
int md_parse(const MD_CHAR* text, MD_SIZE size, const MD_PARSER* parser, void* userdata);
|
||||
|
||||
|
||||
#ifdef __cplusplus
|
||||
} /* extern "C" { */
|
||||
#endif
|
||||
|
||||
#endif /* MD4C_H */
|
||||
362
uppsrc/plugin/md/Markdown.cpp
Normal file
362
uppsrc/plugin/md/Markdown.cpp
Normal file
|
|
@ -0,0 +1,362 @@
|
|||
#include "Markdown.h"
|
||||
|
||||
#define LLOG(x) // DLOG("MarkdownConverter: " << x)
|
||||
|
||||
namespace Upp {
|
||||
|
||||
class sMarkdownContext : NoCopy {
|
||||
struct Block
|
||||
{
|
||||
MD_BLOCKTYPE type;
|
||||
String text;
|
||||
Value data;
|
||||
int level;
|
||||
Block *parent;
|
||||
Array<Block> children;
|
||||
Block(MD_BLOCKTYPE t, Block *p);
|
||||
};
|
||||
|
||||
enum NestedBlockPosition {
|
||||
BLOCK_IN_OLIST = 1,
|
||||
BLOCK_IN_ULIST = 2,
|
||||
BLOCK_IN_QUOTE = 4,
|
||||
BLOCK_IN_THEAD = 8,
|
||||
BLOCK_IN_TBODY = 16
|
||||
};
|
||||
|
||||
Array<Block> document;
|
||||
Block* current_block;
|
||||
int current_level;
|
||||
|
||||
String Compose(const Array<Block>& doc, int data = 0, bool notext = false, dword flags = 0) const;
|
||||
|
||||
public:
|
||||
void BeginBlock(MD_BLOCKTYPE type, void *detail);
|
||||
void EndBlock(MD_BLOCKTYPE type, void *detail);
|
||||
|
||||
String ToQtf() { return Compose(document); }
|
||||
|
||||
sMarkdownContext& operator<<(const String& s) { ASSERT(current_block); current_block->text << s; return *this; }
|
||||
sMarkdownContext& operator<<(const char *s) { ASSERT(current_block); current_block->text << s; return *this; }
|
||||
|
||||
|
||||
sMarkdownContext()
|
||||
: current_block(nullptr)
|
||||
, current_level(0)
|
||||
{}
|
||||
};
|
||||
|
||||
sMarkdownContext::Block::Block(MD_BLOCKTYPE t, Block *p)
|
||||
: type(t)
|
||||
, level(0)
|
||||
, parent(p)
|
||||
{
|
||||
}
|
||||
|
||||
void sMarkdownContext::BeginBlock(MD_BLOCKTYPE type, void *detail)
|
||||
{
|
||||
if(!current_block) {
|
||||
current_block = &document.Create<Block>(type, current_block);
|
||||
}
|
||||
else {
|
||||
current_block = ¤t_block->children.Create<Block>(type, current_block);
|
||||
}
|
||||
|
||||
switch(type) {
|
||||
case MD_BLOCK_UL:
|
||||
current_block->data = reinterpret_cast<MD_BLOCK_UL_DETAIL*>(detail)->mark;
|
||||
current_block->level = ++current_level;
|
||||
break;
|
||||
case MD_BLOCK_OL:
|
||||
current_block->data = '1';
|
||||
current_block->level = ++current_level;
|
||||
break;
|
||||
case MD_BLOCK_H:
|
||||
current_block->data = (int) reinterpret_cast<MD_BLOCK_H_DETAIL*>(detail)->level;
|
||||
current_block->level = current_level;
|
||||
break;
|
||||
default:
|
||||
current_block->level = current_level;
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
void sMarkdownContext::EndBlock(MD_BLOCKTYPE type, void *detail)
|
||||
{
|
||||
if(findarg(type, MD_BLOCK_UL, MD_BLOCK_OL) >= 0)
|
||||
--current_level;
|
||||
|
||||
if(current_block)
|
||||
current_block = current_block->parent;
|
||||
}
|
||||
|
||||
String sMarkdownContext::Compose(const Array<Block>& doc, int data, bool notext, dword flags) const
|
||||
{
|
||||
// TODO:
|
||||
// 1) Refactor this method.
|
||||
// 2) Make certain block styles and page properties (e.g. margins, indentation, etc.) configurable.
|
||||
|
||||
String txt;
|
||||
|
||||
for(int i = 0; i < doc.GetCount(); i++) {
|
||||
const Block& b = doc[i];
|
||||
switch(b.type) {
|
||||
case MD_BLOCK_DOC:
|
||||
{
|
||||
txt << "[G;2;# "
|
||||
<< Compose(b.children, data, false, flags)
|
||||
<< "&]";
|
||||
break;
|
||||
}
|
||||
case MD_BLOCK_HR:
|
||||
{
|
||||
txt << "[H1;L0;h(220.220.220) &]";
|
||||
break;
|
||||
}
|
||||
case MD_BLOCK_H:
|
||||
{
|
||||
txt << "&[*;"
|
||||
<< clamp(6 - b.data.To<int>(), 1, 6)
|
||||
<< " "
|
||||
<< b.text
|
||||
<< "&]";
|
||||
break;
|
||||
}
|
||||
case MD_BLOCK_UL:
|
||||
{
|
||||
txt << Compose(b.children, b.data, false, flags|BLOCK_IN_ULIST);
|
||||
break;
|
||||
}
|
||||
case MD_BLOCK_OL:
|
||||
{
|
||||
txt << "[N! "
|
||||
<< Compose(b.children, b.data, false, flags|BLOCK_IN_OLIST)
|
||||
<< "&]";
|
||||
break;
|
||||
}
|
||||
case MD_BLOCK_LI:
|
||||
{
|
||||
bool q = b.text.IsEmpty();
|
||||
if(!q) {
|
||||
txt << "[a20;b20;l"
|
||||
<< b.level * ((flags & BLOCK_IN_QUOTE) ? 100 : 200)
|
||||
<< ";i200;"
|
||||
<< decode(data, '*', "OO ", '-', "O1 ", '+', "O2 ", "N1 ")
|
||||
<< b.text
|
||||
<< "&]";
|
||||
}
|
||||
txt << Compose(b.children, data, q, flags);
|
||||
break;
|
||||
}
|
||||
case MD_BLOCK_P:
|
||||
{
|
||||
if(!b.level) {
|
||||
txt << "[a50;b50 " << b.text << " &]";
|
||||
}
|
||||
else
|
||||
if(notext && !i) {
|
||||
txt << "[a20;b20;l"
|
||||
<< b.level * ((flags & BLOCK_IN_QUOTE) ? 20 : 200)
|
||||
<< ";i200;"
|
||||
<< decode(data, '*', "OO ", '-', "O1 ", '+', "O2 ", "N1 ")
|
||||
<< b.text
|
||||
<< "&]";
|
||||
}
|
||||
else {
|
||||
txt << "[a20;b20;l"
|
||||
<< b.level * ((flags & BLOCK_IN_QUOTE) ? 40 : 400)
|
||||
<< ";O_ "
|
||||
<< b.text
|
||||
<< "&]";
|
||||
}
|
||||
break;
|
||||
}
|
||||
case MD_BLOCK_CODE:
|
||||
case MD_BLOCK_HTML: // Treat HTML as code block....
|
||||
{
|
||||
txt << "{{10000;<"
|
||||
<< b.level * ((flags & BLOCK_IN_QUOTE) ? 10 : 400)
|
||||
<< ";@(250.250.250);F(230.230.230) [i10;C;1;@5;< "
|
||||
<< b.text
|
||||
<< " ]}}&";
|
||||
break;
|
||||
}
|
||||
case MD_BLOCK_QUOTE:
|
||||
{
|
||||
txt << "{{1:500;G4;g20;F0;f0;<"
|
||||
<< b.level * ((flags & BLOCK_IN_QUOTE) ? 10 : 400)
|
||||
<< " :: [i10;<; "
|
||||
<< Nvl(b.text, "")
|
||||
<< Compose(b.children, data, false, flags|BLOCK_IN_QUOTE)
|
||||
<< " ]}}&";
|
||||
break;
|
||||
}
|
||||
case MD_BLOCK_TABLE:
|
||||
{
|
||||
txt << "{{"
|
||||
<< Compose(b.children, data, false, flags)
|
||||
<< "}}&";
|
||||
break;
|
||||
}
|
||||
case MD_BLOCK_THEAD:
|
||||
{
|
||||
txt << Compose(b.children, data, false, flags|BLOCK_IN_THEAD);
|
||||
break;
|
||||
}
|
||||
case MD_BLOCK_TBODY:
|
||||
{
|
||||
txt << Compose(b.children, data, false, flags|BLOCK_IN_TBODY);
|
||||
break;
|
||||
}
|
||||
case MD_BLOCK_TR:
|
||||
{
|
||||
int n = b.children.GetCount();
|
||||
if(flags & BLOCK_IN_THEAD) {
|
||||
for(int j = 0; j < n; j++) {
|
||||
txt << '1';
|
||||
if(j < n - 1)
|
||||
txt << ':';
|
||||
else {
|
||||
txt << "@(220.225.230);G(220.220.220);<"
|
||||
<< b.level * ((flags & BLOCK_IN_QUOTE) ? 10 : 400)
|
||||
<< " ";
|
||||
}
|
||||
}
|
||||
}
|
||||
for(int j = 0; j < n; j++) {
|
||||
const Block& bb = b.children[j];
|
||||
if(j == 0 && bb.type == MD_BLOCK_TD)
|
||||
txt << "::@2 ";
|
||||
txt << bb.text;
|
||||
if(j < n - 1)
|
||||
txt << "||";
|
||||
}
|
||||
break;
|
||||
}
|
||||
default:
|
||||
//txt << b.text;
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
return txt;
|
||||
}
|
||||
|
||||
static String sDeQtfMd(const char *s)
|
||||
{
|
||||
// Here we duplicate DeQtf() function, because we don't want to bring in the RichText package.
|
||||
|
||||
StringBuffer r;
|
||||
for(; *s; s++) {
|
||||
if(*s == '\n')
|
||||
r.Cat('&');
|
||||
else {
|
||||
if((byte) *s > ' ' && !IsDigit(*s) && !IsAlpha(*s) && (byte) *s < 128)
|
||||
r.Cat('`');
|
||||
r.Cat(*s);
|
||||
}
|
||||
}
|
||||
return String(r); // Make compilers happy...
|
||||
}
|
||||
|
||||
String MarkdownConverter::ToQtf(const String& mdtext)
|
||||
{
|
||||
MD_PARSER parser;
|
||||
parser.abi_version = 0;
|
||||
parser.flags = flags;
|
||||
parser.debug_log = nullptr;
|
||||
parser.syntax = nullptr;
|
||||
|
||||
parser.enter_block = [](MD_BLOCKTYPE type, void *detail, void *udata) -> int
|
||||
{
|
||||
reinterpret_cast<sMarkdownContext*>(udata)->BeginBlock(type, detail);
|
||||
return 0;
|
||||
};
|
||||
|
||||
parser.leave_block = [](MD_BLOCKTYPE type, void *detail, void *udata) -> int
|
||||
{
|
||||
reinterpret_cast<sMarkdownContext*>(udata)->EndBlock(type, detail);
|
||||
return 0;
|
||||
};
|
||||
|
||||
parser.enter_span = [](MD_SPANTYPE type, void *detail, void *udata) -> int
|
||||
{
|
||||
auto& ctx = *reinterpret_cast<sMarkdownContext*>(udata);
|
||||
|
||||
switch(type) {
|
||||
case MD_SPAN_A:
|
||||
{
|
||||
auto *q = reinterpret_cast<MD_SPAN_A_DETAIL*>(detail);
|
||||
ctx << "[^" << String(q->href.text, q->href.size) << "^ ";
|
||||
break;
|
||||
}
|
||||
case MD_SPAN_IMG:
|
||||
{
|
||||
auto *q = reinterpret_cast<MD_SPAN_IMG_DETAIL*>(detail);
|
||||
ctx << "[^" << String(q->src.text, q->src.size) << "^ ";
|
||||
break;
|
||||
}
|
||||
case MD_SPAN_WIKILINK:
|
||||
{
|
||||
auto *q = reinterpret_cast<MD_SPAN_WIKILINK_DETAIL*>(detail);
|
||||
ctx << "[^" << String(q->target.text, q->target.size) << "^ ";
|
||||
break;
|
||||
}
|
||||
default:
|
||||
{
|
||||
ctx << decode(type,
|
||||
MD_SPAN_U, "[_ ",
|
||||
MD_SPAN_EM, "[/ ",
|
||||
MD_SPAN_DEL, "[- ",
|
||||
MD_SPAN_CODE, "[C;@5;$(245.245.245) ",
|
||||
MD_SPAN_STRONG, "[* ", "");
|
||||
break;
|
||||
}}
|
||||
return 0;
|
||||
};
|
||||
|
||||
parser.leave_span = [](MD_SPANTYPE type, void *detail, void *udata) -> int
|
||||
{
|
||||
auto& ctx = *reinterpret_cast<sMarkdownContext*>(udata);
|
||||
|
||||
if(findarg(type,
|
||||
MD_SPAN_A,
|
||||
MD_SPAN_U,
|
||||
MD_SPAN_EM,
|
||||
MD_SPAN_IMG,
|
||||
MD_SPAN_DEL,
|
||||
MD_SPAN_CODE,
|
||||
MD_SPAN_STRONG,
|
||||
MD_SPAN_WIKILINK) >= 0)
|
||||
ctx << "]";
|
||||
|
||||
return 0;
|
||||
};
|
||||
|
||||
parser.text = [](MD_TEXTTYPE type, const MD_CHAR *text, MD_SIZE size, void* udata) -> int
|
||||
{
|
||||
auto& ctx = *reinterpret_cast<sMarkdownContext*>(udata);
|
||||
|
||||
ctx << decode(type,
|
||||
MD_TEXT_NULLCHAR, "?",
|
||||
MD_TEXT_BR, "&",
|
||||
MD_TEXT_SOFTBR, " ", // TODO: See if there is a way to properly imitate this in qtf...
|
||||
(const char*) ~sDeQtfMd(String((const char*) text, size)));
|
||||
|
||||
return 0;
|
||||
};
|
||||
|
||||
#ifdef _DEBUG
|
||||
parser.debug_log = [](const char *msg, void *udata) -> void
|
||||
{
|
||||
LLOG(msg);
|
||||
};
|
||||
#endif
|
||||
|
||||
sMarkdownContext ctx;
|
||||
|
||||
int rc = md_parse((const MD_CHAR*)~mdtext, (MD_SIZE) mdtext.GetLength(), &parser, &ctx);
|
||||
return rc ? String::GetVoid() : ctx.ToQtf();
|
||||
}
|
||||
|
||||
}
|
||||
37
uppsrc/plugin/md/Markdown.h
Normal file
37
uppsrc/plugin/md/Markdown.h
Normal file
|
|
@ -0,0 +1,37 @@
|
|||
#ifndef Upp_Markdown_h
|
||||
#define Upp_Markdown_h
|
||||
|
||||
#include <Core/Core.h>
|
||||
#include "MD4C/md4c.h"
|
||||
|
||||
namespace Upp {
|
||||
|
||||
class MarkdownConverter {
|
||||
public:
|
||||
MarkdownConverter() : flags(MD_DIALECT_COMMONMARK) {}
|
||||
|
||||
MarkdownConverter& CollapseWhitespaces(bool b = true) { if(b) flags |= MD_FLAG_COLLAPSEWHITESPACE; else flags &= ~MD_FLAG_COLLAPSEWHITESPACE; return *this; }
|
||||
MarkdownConverter& NoIndentedCodeblocks(bool b = true) { if(b) flags |= MD_FLAG_NOINDENTEDCODEBLOCKS; else flags &= ~MD_FLAG_NOINDENTEDCODEBLOCKS; return *this; }
|
||||
MarkdownConverter& Tables(bool b = true) { if(b) flags |= MD_FLAG_TABLES; else flags &= ~MD_FLAG_TABLES; return *this; }
|
||||
MarkdownConverter& WikiLinks(bool b = true) { if(b) flags |= MD_FLAG_WIKILINKS; else flags &= ~MD_FLAG_WIKILINKS; return *this; }
|
||||
MarkdownConverter& Strikeout(bool b = true) { if(b) flags |= MD_FLAG_STRIKETHROUGH; else flags &= ~MD_FLAG_STRIKETHROUGH; return *this; }
|
||||
MarkdownConverter& Underline(bool b = true) { if(b) flags |= MD_FLAG_UNDERLINE; else flags &= ~MD_FLAG_UNDERLINE; return *this; }
|
||||
MarkdownConverter& NoHtmlBlocks(bool b = true) { if(b) flags |= MD_FLAG_NOHTMLBLOCKS; else flags &= ~MD_FLAG_NOHTMLBLOCKS; return *this; }
|
||||
MarkdownConverter& NoHtmlSpans(bool b = true) { if(b) flags |= MD_FLAG_NOHTMLSPANS; else flags &= ~MD_FLAG_NOHTMLSPANS; return *this; }
|
||||
MarkdownConverter& NoHtml(bool b = true) { if(b) flags |= MD_FLAG_NOHTML; else flags &= ~MD_FLAG_NOHTML; return *this; }
|
||||
MarkdownConverter& PermissiveAtxHeaders(bool b = true) { if(b) flags |= MD_FLAG_PERMISSIVEATXHEADERS; else flags &= ~MD_FLAG_PERMISSIVEATXHEADERS; return *this; }
|
||||
MarkdownConverter& PermissiveUrlAutolinks(bool b = true) { if(b) flags |= MD_FLAG_PERMISSIVEURLAUTOLINKS; else flags &= ~MD_FLAG_PERMISSIVEURLAUTOLINKS; return *this; }
|
||||
MarkdownConverter& PermissiveWWWAutolinks(bool b = true) { if(b) flags |= MD_FLAG_PERMISSIVEWWWAUTOLINKS; else flags &= ~MD_FLAG_PERMISSIVEWWWAUTOLINKS; return *this; }
|
||||
MarkdownConverter& PermissiveAutolinks(bool b = true) { if(b) flags |= MD_FLAG_PERMISSIVEAUTOLINKS; else flags &= ~MD_FLAG_PERMISSIVEAUTOLINKS; return *this; }
|
||||
|
||||
MarkdownConverter& CommonMarkDialect() { flags = MD_DIALECT_COMMONMARK; return *this; }
|
||||
MarkdownConverter& GitHubDialect() { flags = MD_DIALECT_GITHUB; return *this; }
|
||||
|
||||
String ToQtf(const String& markdown_text);
|
||||
|
||||
private:
|
||||
dword flags;
|
||||
};
|
||||
|
||||
}
|
||||
#endif
|
||||
12
uppsrc/plugin/md/issues
Normal file
12
uppsrc/plugin/md/issues
Normal file
|
|
@ -0,0 +1,12 @@
|
|||
# Markdown package (Scheduled for: Ultimate++ release 2021.1)
|
||||
|
||||
## TODO:
|
||||
|
||||
- Image handling is yet to be implemented.
|
||||
- Task lists are yet to be implemented.
|
||||
|
||||
## Remaining issues:
|
||||
|
||||
- Block elements don't have configurable style.
|
||||
- Page properties (margins, indentation, etc.) are not configurable.
|
||||
- Soft break is not handled very well.
|
||||
14
uppsrc/plugin/md/md.upp
Normal file
14
uppsrc/plugin/md/md.upp
Normal file
|
|
@ -0,0 +1,14 @@
|
|||
description "Markdown to QTF converter, based on MD4C library\377";
|
||||
|
||||
uses
|
||||
Core;
|
||||
|
||||
file
|
||||
Markdown.h,
|
||||
Markdown.cpp,
|
||||
Info readonly separator,
|
||||
Copying,
|
||||
issues,
|
||||
Library readonly separator,
|
||||
MD4C/md4c.h,
|
||||
MD4C/md4c.c;
|
||||
Loading…
Add table
Add a link
Reference in a new issue