ef3d0c3e/nml
1
1
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Compare commits

base: ef3d0c3e:8bd4f9716bfc3247b979b960817d4e049ba9e44f
Branches Tags
ef3d0c3e:master
ef3d0c3e:parser-refactor
ef3d0c3e:batch
..
compare: ef3d0c3e:461738dab93ed1587419dfd5c440a606644e36b1
Branches Tags
ef3d0c3e:master
ef3d0c3e:parser-refactor
ef3d0c3e:batch

No commits in common. "8bd4f9716bfc3247b979b960817d4e049ba9e44f" and "461738dab93ed1587419dfd5c440a606644e36b1" have entirely different histories.
8bd4f9716b ... 461738dab9

42 changed files with 1699 additions and 4440 deletions
Show stats Expand all files Collapse all files

651
LICENSE.md
View file

@ -1,651 +0,0 @@
GNU Affero General Public License
=================================
_Version 3, 19 November 2007_
_Copyright © 2007 Free Software Foundation, Inc. <http://fsf.org/>_
Everyone is permitted to copy and distribute verbatim copies
of this license document, but changing it is not allowed.
## Preamble
The GNU Affero General Public License is a free, copyleft license for
software and other kinds of works, specifically designed to ensure
cooperation with the community in the case of network server software.
The licenses for most software and other practical works are designed
to take away your freedom to share and change the works. By contrast,
our General Public Licenses are intended to guarantee your freedom to
share and change all versions of a program--to make sure it remains free
software for all its users.
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
them 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.
Developers that use our General Public Licenses protect your rights
with two steps: **(1)** assert copyright on the software, and **(2)** offer
you this License which gives you legal permission to copy, distribute
and/or modify the software.
A secondary benefit of defending all users' freedom is that
improvements made in alternate versions of the program, if they
receive widespread use, become available for other developers to
incorporate. Many developers of free software are heartened and
encouraged by the resulting cooperation. However, in the case of
software used on network servers, this result may fail to come about.
The GNU General Public License permits making a modified version and
letting the public access it on a server without ever releasing its
source code to the public.
The GNU Affero General Public License is designed specifically to
ensure that, in such cases, the modified source code becomes available
to the community. It requires the operator of a network server to
provide the source code of the modified version running there to the
users of that server. Therefore, public use of a modified version, on
a publicly accessible server, gives the public access to the source
code of the modified version.
An older license, called the Affero General Public License and
published by Affero, was designed to accomplish similar goals. This is
a different license, not a version of the Affero GPL, but Affero has
released a new version of the Affero GPL which permits relicensing under
this license.
The precise terms and conditions for copying, distribution and
modification follow.
## TERMS AND CONDITIONS
### 0. Definitions
“This License” refers to version 3 of the GNU Affero General Public License.
“Copyright” also means copyright-like laws that apply to other kinds of
works, such as semiconductor masks.
“The Program” refers to any copyrightable work licensed under this
License. Each licensee is addressed as “you”. “Licensees” and
“recipients” may be individuals or organizations.
To “modify” a work means to copy from or adapt all or part of the work
in a fashion requiring copyright permission, other than the making of an
exact copy. The resulting work is called a “modified version” of the
earlier work or a work “based on” the earlier work.
A “covered work” means either the unmodified Program or a work based
on the Program.
To “propagate” a work means to do anything with it that, without
permission, would make you directly or secondarily liable for
infringement under applicable copyright law, except executing it on a
computer or modifying a private copy. Propagation includes copying,
distribution (with or without modification), making available to the
public, and in some countries other activities as well.
To “convey” a work means any kind of propagation that enables other
parties to make or receive copies. Mere interaction with a user through
a computer network, with no transfer of a copy, is not conveying.
An interactive user interface displays “Appropriate Legal Notices”
to the extent that it includes a convenient and prominently visible
feature that **(1)** displays an appropriate copyright notice, and **(2)**
tells the user that there is no warranty for the work (except to the
extent that warranties are provided), that licensees may convey the
work under this License, and how to view a copy of this License. If
the interface presents a list of user commands or options, such as a
menu, a prominent item in the list meets this criterion.
### 1. Source Code
The “source code” for a work means the preferred form of the work
for making modifications to it. “Object code” means any non-source
form of a work.
A “Standard Interface” means an interface that either is an official
standard defined by a recognized standards body, or, in the case of
interfaces specified for a particular programming language, one that
is widely used among developers working in that language.
The “System Libraries” of an executable work include anything, other
than the work as a whole, that **(a)** is included in the normal form of
packaging a Major Component, but which is not part of that Major
Component, and **(b)** serves only to enable use of the work with that
Major Component, or to implement a Standard Interface for which an
implementation is available to the public in source code form. A
“Major Component”, in this context, means a major essential component
(kernel, window system, and so on) of the specific operating system
(if any) on which the executable work runs, or a compiler used to
produce the work, or an object code interpreter used to run it.
The “Corresponding Source” for a work in object code form means all
the source code needed to generate, install, and (for an executable
work) run the object code and to modify the work, including scripts to
control those activities. However, it does not include the work's
System Libraries, or general-purpose tools or generally available free
programs which are used unmodified in performing those activities but
which are not part of the work. For example, Corresponding Source
includes interface definition files associated with source files for
the work, and the source code for shared libraries and dynamically
linked subprograms that the work is specifically designed to require,
such as by intimate data communication or control flow between those
subprograms and other parts of the work.
The Corresponding Source need not include anything that users
can regenerate automatically from other parts of the Corresponding
Source.
The Corresponding Source for a work in source code form is that
same work.
### 2. Basic Permissions
All rights granted under this License are granted for the term of
copyright on the Program, and are irrevocable provided the stated
conditions are met. This License explicitly affirms your unlimited
permission to run the unmodified Program. The output from running a
covered work is covered by this License only if the output, given its
content, constitutes a covered work. This License acknowledges your
rights of fair use or other equivalent, as provided by copyright law.
You may make, run and propagate covered works that you do not
convey, without conditions so long as your license otherwise remains
in force. You may convey covered works to others for the sole purpose
of having them make modifications exclusively for you, or provide you
with facilities for running those works, provided that you comply with
the terms of this License in conveying all material for which you do
not control copyright. Those thus making or running the covered works
for you must do so exclusively on your behalf, under your direction
and control, on terms that prohibit them from making any copies of
your copyrighted material outside their relationship with you.
Conveying under any other circumstances is permitted solely under
the conditions stated below. Sublicensing is not allowed; section 10
makes it unnecessary.
### 3. Protecting Users' Legal Rights From Anti-Circumvention Law
No covered work shall be deemed part of an effective technological
measure under any applicable law fulfilling obligations under article
11 of the WIPO copyright treaty adopted on 20 December 1996, or
similar laws prohibiting or restricting circumvention of such
measures.
When you convey a covered work, you waive any legal power to forbid
circumvention of technological measures to the extent such circumvention
is effected by exercising rights under this License with respect to
the covered work, and you disclaim any intention to limit operation or
modification of the work as a means of enforcing, against the work's
users, your or third parties' legal rights to forbid circumvention of
technological measures.
### 4. Conveying Verbatim Copies
You may convey 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;
keep intact all notices stating that this License and any
non-permissive terms added in accord with section 7 apply to the code;
keep intact all notices of the absence of any warranty; and give all
recipients a copy of this License along with the Program.
You may charge any price or no price for each copy that you convey,
and you may offer support or warranty protection for a fee.
### 5. Conveying Modified Source Versions
You may convey a work based on the Program, or the modifications to
produce it from the Program, in the form of source code under the
terms of section 4, provided that you also meet all of these conditions:
* **a)** The work must carry prominent notices stating that you modified
it, and giving a relevant date.
* **b)** The work must carry prominent notices stating that it is
released under this License and any conditions added under section 7.
This requirement modifies the requirement in section 4 to
“keep intact all notices”.
* **c)** You must license the entire work, as a whole, under this
License to anyone who comes into possession of a copy. This
License will therefore apply, along with any applicable section 7
additional terms, to the whole of the work, and all its parts,
regardless of how they are packaged. This License gives no
permission to license the work in any other way, but it does not
invalidate such permission if you have separately received it.
* **d)** If the work has interactive user interfaces, each must display
Appropriate Legal Notices; however, if the Program has interactive
interfaces that do not display Appropriate Legal Notices, your
work need not make them do so.
A compilation of a covered work with other separate and independent
works, which are not by their nature extensions of the covered work,
and which are not combined with it such as to form a larger program,
in or on a volume of a storage or distribution medium, is called an
“aggregate” if the compilation and its resulting copyright are not
used to limit the access or legal rights of the compilation's users
beyond what the individual works permit. Inclusion of a covered work
in an aggregate does not cause this License to apply to the other
parts of the aggregate.
### 6. Conveying Non-Source Forms
You may convey a covered work in object code form under the terms
of sections 4 and 5, provided that you also convey the
machine-readable Corresponding Source under the terms of this License,
in one of these ways:
* **a)** Convey the object code in, or embodied in, a physical product
(including a physical distribution medium), accompanied by the
Corresponding Source fixed on a durable physical medium
customarily used for software interchange.
* **b)** Convey the object code in, or embodied in, a physical product
(including a physical distribution medium), accompanied by a
written offer, valid for at least three years and valid for as
long as you offer spare parts or customer support for that product
model, to give anyone who possesses the object code either **(1)** a
copy of the Corresponding Source for all the software in the
product that is covered by this License, on a durable physical
medium customarily used for software interchange, for a price no
more than your reasonable cost of physically performing this
conveying of source, or **(2)** access to copy the
Corresponding Source from a network server at no charge.
* **c)** Convey individual copies of the object code with a copy of the
written offer to provide the Corresponding Source. This
alternative is allowed only occasionally and noncommercially, and
only if you received the object code with such an offer, in accord
with subsection 6b.
* **d)** Convey the object code by offering access from a designated
place (gratis or for a charge), and offer equivalent access to the
Corresponding Source in the same way through the same place at no
further charge. You need not require recipients to copy the
Corresponding Source along with the object code. If the place to
copy the object code is a network server, the Corresponding Source
may be on a different server (operated by you or a third party)
that supports equivalent copying facilities, provided you maintain
clear directions next to the object code saying where to find the
Corresponding Source. Regardless of what server hosts the
Corresponding Source, you remain obligated to ensure that it is
available for as long as needed to satisfy these requirements.
* **e)** Convey the object code using peer-to-peer transmission, provided
you inform other peers where the object code and Corresponding
Source of the work are being offered to the general public at no
charge under subsection 6d.
A separable portion of the object code, whose source code is excluded
from the Corresponding Source as a System Library, need not be
included in conveying the object code work.
A “User Product” is either **(1)** a “consumer product”, which means any
tangible personal property which is normally used for personal, family,
or household purposes, or **(2)** anything designed or sold for incorporation
into a dwelling. In determining whether a product is a consumer product,
doubtful cases shall be resolved in favor of coverage. For a particular
product received by a particular user, “normally used” refers to a
typical or common use of that class of product, regardless of the status
of the particular user or of the way in which the particular user
actually uses, or expects or is expected to use, the product. A product
is a consumer product regardless of whether the product has substantial
commercial, industrial or non-consumer uses, unless such uses represent
the only significant mode of use of the product.
“Installation Information” for a User Product means any methods,
procedures, authorization keys, or other information required to install
and execute modified versions of a covered work in that User Product from
a modified version of its Corresponding Source. The information must
suffice to ensure that the continued functioning of the modified object
code is in no case prevented or interfered with solely because
modification has been made.
If you convey an object code work under this section in, or with, or
specifically for use in, a User Product, and the conveying occurs as
part of a transaction in which the right of possession and use of the
User Product is transferred to the recipient in perpetuity or for a
fixed term (regardless of how the transaction is characterized), the
Corresponding Source conveyed under this section must be accompanied
by the Installation Information. But this requirement does not apply
if neither you nor any third party retains the ability to install
modified object code on the User Product (for example, the work has
been installed in ROM).
The requirement to provide Installation Information does not include a
requirement to continue to provide support service, warranty, or updates
for a work that has been modified or installed by the recipient, or for
the User Product in which it has been modified or installed. Access to a
network may be denied when the modification itself materially and
adversely affects the operation of the network or violates the rules and
protocols for communication across the network.
Corresponding Source conveyed, and Installation Information provided,
in accord with this section must be in a format that is publicly
documented (and with an implementation available to the public in
source code form), and must require no special password or key for
unpacking, reading or copying.
### 7. Additional Terms
“Additional permissions” are terms that supplement the terms of this
License by making exceptions from one or more of its conditions.
Additional permissions that are applicable to the entire Program shall
be treated as though they were included in this License, to the extent
that they are valid under applicable law. If additional permissions
apply only to part of the Program, that part may be used separately
under those permissions, but the entire Program remains governed by
this License without regard to the additional permissions.
When you convey a copy of a covered work, you may at your option
remove any additional permissions from that copy, or from any part of
it. (Additional permissions may be written to require their own
removal in certain cases when you modify the work.) You may place
additional permissions on material, added by you to a covered work,
for which you have or can give appropriate copyright permission.
Notwithstanding any other provision of this License, for material you
add to a covered work, you may (if authorized by the copyright holders of
that material) supplement the terms of this License with terms:
* **a)** Disclaiming warranty or limiting liability differently from the
terms of sections 15 and 16 of this License; or
* **b)** Requiring preservation of specified reasonable legal notices or
author attributions in that material or in the Appropriate Legal
Notices displayed by works containing it; or
* **c)** Prohibiting misrepresentation of the origin of that material, or
requiring that modified versions of such material be marked in
reasonable ways as different from the original version; or
* **d)** Limiting the use for publicity purposes of names of licensors or
authors of the material; or
* **e)** Declining to grant rights under trademark law for use of some
trade names, trademarks, or service marks; or
* **f)** Requiring indemnification of licensors and authors of that
material by anyone who conveys the material (or modified versions of
it) with contractual assumptions of liability to the recipient, for
any liability that these contractual assumptions directly impose on
those licensors and authors.
All other non-permissive additional terms are considered “further
restrictions” within the meaning of section 10. If the Program as you
received it, or any part of it, contains a notice stating that it is
governed by this License along with a term that is a further
restriction, you may remove that term. If a license document contains
a further restriction but permits relicensing or conveying under this
License, you may add to a covered work material governed by the terms
of that license document, provided that the further restriction does
not survive such relicensing or conveying.
If you add terms to a covered work in accord with this section, you
must place, in the relevant source files, a statement of the
additional terms that apply to those files, or a notice indicating
where to find the applicable terms.
Additional terms, permissive or non-permissive, may be stated in the
form of a separately written license, or stated as exceptions;
the above requirements apply either way.
### 8. Termination
You may not propagate or modify a covered work except as expressly
provided under this License. Any attempt otherwise to propagate or
modify it is void, and will automatically terminate your rights under
this License (including any patent licenses granted under the third
paragraph of section 11).
However, if you cease all violation of this License, then your
license from a particular copyright holder is reinstated **(a)**
provisionally, unless and until the copyright holder explicitly and
finally terminates your license, and **(b)** permanently, if the copyright
holder fails to notify you of the violation by some reasonable means
prior to 60 days after the cessation.
Moreover, your license from a particular copyright holder is
reinstated permanently if the copyright holder notifies you of the
violation by some reasonable means, this is the first time you have
received notice of violation of this License (for any work) from that
copyright holder, and you cure the violation prior to 30 days after
your receipt of the notice.
Termination of your rights under this section does not terminate the
licenses of parties who have received copies or rights from you under
this License. If your rights have been terminated and not permanently
reinstated, you do not qualify to receive new licenses for the same
material under section 10.
### 9. Acceptance Not Required for Having Copies
You are not required to accept this License in order to receive or
run a copy of the Program. Ancillary propagation of a covered work
occurring solely as a consequence of using peer-to-peer transmission
to receive a copy likewise does not require acceptance. However,
nothing other than this License grants you permission to propagate or
modify any covered work. These actions infringe copyright if you do
not accept this License. Therefore, by modifying or propagating a
covered work, you indicate your acceptance of this License to do so.
### 10. Automatic Licensing of Downstream Recipients
Each time you convey a covered work, the recipient automatically
receives a license from the original licensors, to run, modify and
propagate that work, subject to this License. You are not responsible
for enforcing compliance by third parties with this License.
An “entity transaction” is a transaction transferring control of an
organization, or substantially all assets of one, or subdividing an
organization, or merging organizations. If propagation of a covered
work results from an entity transaction, each party to that
transaction who receives a copy of the work also receives whatever
licenses to the work the party's predecessor in interest had or could
give under the previous paragraph, plus a right to possession of the
Corresponding Source of the work from the predecessor in interest, if
the predecessor has it or can get it with reasonable efforts.
You may not impose any further restrictions on the exercise of the
rights granted or affirmed under this License. For example, you may
not impose a license fee, royalty, or other charge for exercise of
rights granted under this License, and you may not initiate litigation
(including a cross-claim or counterclaim in a lawsuit) alleging that
any patent claim is infringed by making, using, selling, offering for
sale, or importing the Program or any portion of it.
### 11. Patents
A “contributor” is a copyright holder who authorizes use under this
License of the Program or a work on which the Program is based. The
work thus licensed is called the contributor's “contributor version”.
A contributor's “essential patent claims” are all patent claims
owned or controlled by the contributor, whether already acquired or
hereafter acquired, that would be infringed by some manner, permitted
by this License, of making, using, or selling its contributor version,
but do not include claims that would be infringed only as a
consequence of further modification of the contributor version. For
purposes of this definition, “control” includes the right to grant
patent sublicenses in a manner consistent with the requirements of
this License.
Each contributor grants you a non-exclusive, worldwide, royalty-free
patent license under the contributor's essential patent claims, to
make, use, sell, offer for sale, import and otherwise run, modify and
propagate the contents of its contributor version.
In the following three paragraphs, a “patent license” is any express
agreement or commitment, however denominated, not to enforce a patent
(such as an express permission to practice a patent or covenant not to
sue for patent infringement). To “grant” such a patent license to a
party means to make such an agreement or commitment not to enforce a
patent against the party.
If you convey a covered work, knowingly relying on a patent license,
and the Corresponding Source of the work is not available for anyone
to copy, free of charge and under the terms of this License, through a
publicly available network server or other readily accessible means,
then you must either **(1)** cause the Corresponding Source to be so
available, or **(2)** arrange to deprive yourself of the benefit of the
patent license for this particular work, or **(3)** arrange, in a manner
consistent with the requirements of this License, to extend the patent
license to downstream recipients. “Knowingly relying” means you have
actual knowledge that, but for the patent license, your conveying the
covered work in a country, or your recipient's use of the covered work
in a country, would infringe one or more identifiable patents in that
country that you have reason to believe are valid.
If, pursuant to or in connection with a single transaction or
arrangement, you convey, or propagate by procuring conveyance of, a
covered work, and grant a patent license to some of the parties
receiving the covered work authorizing them to use, propagate, modify
or convey a specific copy of the covered work, then the patent license
you grant is automatically extended to all recipients of the covered
work and works based on it.
A patent license is “discriminatory” if it does not include within
the scope of its coverage, prohibits the exercise of, or is
conditioned on the non-exercise of one or more of the rights that are
specifically granted under this License. You may not convey a covered
work if you are a party to an arrangement with a third party that is
in the business of distributing software, under which you make payment
to the third party based on the extent of your activity of conveying
the work, and under which the third party grants, to any of the
parties who would receive the covered work from you, a discriminatory
patent license **(a)** in connection with copies of the covered work
conveyed by you (or copies made from those copies), or **(b)** primarily
for and in connection with specific products or compilations that
contain the covered work, unless you entered into that arrangement,
or that patent license was granted, prior to 28 March 2007.
Nothing in this License shall be construed as excluding or limiting
any implied license or other defenses to infringement that may
otherwise be available to you under applicable patent law.
### 12. No Surrender of Others' Freedom
If 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 convey a
covered work so as to satisfy simultaneously your obligations under this
License and any other pertinent obligations, then as a consequence you may
not convey it at all. For example, if you agree to terms that obligate you
to collect a royalty for further conveying from those to whom you convey
the Program, the only way you could satisfy both those terms and this
License would be to refrain entirely from conveying the Program.
### 13. Remote Network Interaction; Use with the GNU General Public License
Notwithstanding any other provision of this License, if you modify the
Program, your modified version must prominently offer all users
interacting with it remotely through a computer network (if your version
supports such interaction) an opportunity to receive the Corresponding
Source of your version by providing access to the Corresponding Source
from a network server at no charge, through some standard or customary
means of facilitating copying of software. This Corresponding Source
shall include the Corresponding Source for any work covered by version 3
of the GNU General Public License that is incorporated pursuant to the
following paragraph.
Notwithstanding any other provision of this License, you have
permission to link or combine any covered work with a work licensed
under version 3 of the GNU General Public License into a single
combined work, and to convey the resulting work. The terms of this
License will continue to apply to the part which is the covered work,
but the work with which it is combined will remain governed by version
3 of the GNU General Public License.
### 14. Revised Versions of this License
The Free Software Foundation may publish revised and/or new versions of
the GNU Affero 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 that a certain numbered version of the GNU Affero General
Public License “or any later version” applies to it, you have the
option of following the terms and conditions either of that numbered
version or of any later version published by the Free Software
Foundation. If the Program does not specify a version number of the
GNU Affero General Public License, you may choose any version ever published
by the Free Software Foundation.
If the Program specifies that a proxy can decide which future
versions of the GNU Affero General Public License can be used, that proxy's
public statement of acceptance of a version permanently authorizes you
to choose that version for the Program.
Later license versions may give you additional or different
permissions. However, no additional obligations are imposed on any
author or copyright holder as a result of your choosing to follow a
later version.
### 15. Disclaimer of Warranty
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.
### 16. Limitation of Liability
IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS
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.
### 17. Interpretation of Sections 15 and 16
If the disclaimer of warranty and limitation of liability provided
above cannot be given local legal effect according to their terms,
reviewing courts shall apply local law that most closely approximates
an absolute waiver of all civil liability in connection with the
Program, unless a warranty or assumption of liability accompanies a
copy of the Program in return for a fee.
_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
state the exclusion of warranty; and each file should have at least
the “copyright” line and a pointer to where the full notice is found.
<one line to give the program's name and a brief idea of what it does.>
Copyright (C) <year> <name of author>
This program is free software: you can redistribute it and/or modify
it under the terms of the GNU Affero General Public License as published by
the Free Software Foundation, either version 3 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 Affero General Public License for more details.
You should have received a copy of the GNU Affero General Public License
along with this program. If not, see <http://www.gnu.org/licenses/>.
Also add information on how to contact you by electronic and paper mail.
If your software can interact with users remotely through a computer
network, you should also make sure that it provides a way for users to
get its source. For example, if your program is a web application, its
interface could display a “Source” link that leads users to an archive
of the code. There are many ways you could offer source, and different
solutions will be better for different programs; see section 13 for the
specific requirements.
You should also get your employer (if you work as a programmer) or school,
if any, to sign a “copyright disclaimer” for the program, if necessary.
For more information on this, and how to apply and follow the GNU AGPL, see
<http://www.gnu.org/licenses/>

48
README.md
View file

@ -1,48 +0,0 @@
# NML -- Not a markup language!
Currently a work in progress, expect features and fixes to arrive soon!
# Requirements
Some features requires external dependencies to work.
## LaTeX rendering for HTML
We ship a modified version of `latex2svg` by Matthias C. Hormann.
The modified program can be found in [third/latex2svg](third/latex2svg) and is licensed under MIT.
The installation instructions specified on [latex2svg's repository](https://github.com/Moonbase59/latex2svg).
## Graphviz rendering
To render Graphviz graph `[graph]...[/graph]`
You need to install the `dot` program from [Graphviz](https://graphviz.org/) in order to render graphs.
## Lua kernels
To execute Lua kernels you need to install `liblua` version 5.4.
Support for a statically linked Lua may be added in the future.
# Compiling
```
cargo build --release --bin nml
```
# Features roadmap
- [x] Paragraphs
- [x] LaTeX rendering
- [x] Graphviz rendering
- [x] Media
- [ ] References
- [ ] Complete Lua api
- [ ] Documentation
- [ ] Table
- [ ] LaTeX output
- [ ] LSP
# License
NML is licensed under the GNU AGPL version 3 or later. See [LICENSE.md](LICENSE.md) for more information.
License for third-party dependencies can be accessed via `cargo license`

48
readme.nml
View file

@ -3,7 +3,7 @@
@'html.css = style.css
@tex.main.fontsize = 9
@tex.main.preamble = \usepackage{xcolor, amsmath} \\
@tex.main.preamble = \usepackage{xcolor} \\
\definecolor{__color1}{HTML}{d5d5d5} \\
\everymath{\color{__color1}\displaystyle}
@tex.main.block_prepend = \color{__color1}
@ -77,52 +77,10 @@ end
Evaluating `!` from a kernel: `\%<![kernel] eval>\%`
* `\%<[example]! make_bold("Hello, World!")>\%` → %<[example]! make_bold("Hello, World!")>%
* `\%<![example] make_bold("Hello, World!")>\%` → %<![example] make_bold("Hello, World!")>%
# Latex
## Support for inline maths:
# Support for inline maths:
* $\sum^{\infty}_{k=1} \frac{1}{k^2} = \frac{\pi^2}{6}$
* $n! = \int_0^\infty t^n e^{-t} \text{ d}t$
# Graphs
NML adds support for *Graphviz* graphs.
[graph][
width=600px,
layout=neato
]
digraph g {
bgcolor="transparent"
fontname="Helvetica,Arial,sans-serif"
node [fontname="Helvetica,Arial,sans-serif"]
edge [fontname="Helvetica,Arial,sans-serif"]
graph [fontsize=30 labelloc="t" label="" splines=true overlap=false rankdir = "LR"];
"state0" [ style = "filled, bold" penwidth = 5 fillcolor = "white" fontname = "Courier New" shape = "Mrecord" label =<<table border="0" cellborder="0" cellpadding="3" bgcolor="white"><tr><td bgcolor="black" align="center" colspan="2"><font color="white">State #0</font></td></tr><tr><td align="left" port="r0">&#40;0&#41; s -&gt; &bull;e $ </td></tr><tr><td align="left" port="r1">&#40;1&#41; e -&gt; &bull;l '=' r </td></tr><tr><td align="left" port="r2">&#40;2&#41; e -&gt; &bull;r </td></tr><tr><td align="left" port="r3">&#40;3&#41; l -&gt; &bull;'*' r </td></tr><tr><td align="left" port="r4">&#40;4&#41; l -&gt; &bull;'n' </td></tr><tr><td align="left" port="r5">&#40;5&#41; r -&gt; &bull;l </td></tr></table>> ];
"state1" [ style = "filled" penwidth = 1 fillcolor = "white" fontname = "Courier New" shape = "Mrecord" label =<<table border="0" cellborder="0" cellpadding="3" bgcolor="white"><tr><td bgcolor="black" align="center" colspan="2"><font color="white">State #1</font></td></tr><tr><td align="left" port="r3">&#40;3&#41; l -&gt; &bull;'*' r </td></tr><tr><td align="left" port="r3">&#40;3&#41; l -&gt; '*' &bull;r </td></tr><tr><td align="left" port="r4">&#40;4&#41; l -&gt; &bull;'n' </td></tr><tr><td align="left" port="r5">&#40;5&#41; r -&gt; &bull;l </td></tr></table>> ];
"state2" [ style = "filled" penwidth = 1 fillcolor = "white" fontname = "Courier New" shape = "Mrecord" label =<<table border="0" cellborder="0" cellpadding="3" bgcolor="white"><tr><td bgcolor="black" align="center" colspan="2"><font color="white">State #2</font></td></tr><tr><td align="left" port="r4">&#40;4&#41; l -&gt; 'n' &bull;</td><td bgcolor="grey" align="right">=$</td></tr></table>> ];
"state3" [ style = "filled" penwidth = 1 fillcolor = "white" fontname = "Courier New" shape = "Mrecord" label =<<table border="0" cellborder="0" cellpadding="3" bgcolor="white"><tr><td bgcolor="black" align="center" colspan="2"><font color="white">State #3</font></td></tr><tr><td align="left" port="r5">&#40;5&#41; r -&gt; l &bull;</td><td bgcolor="grey" align="right">=$</td></tr></table>> ];
"state4" [ style = "filled" penwidth = 1 fillcolor = "white" fontname = "Courier New" shape = "Mrecord" label =<<table border="0" cellborder="0" cellpadding="3" bgcolor="white"><tr><td bgcolor="black" align="center" colspan="2"><font color="white">State #4</font></td></tr><tr><td align="left" port="r3">&#40;3&#41; l -&gt; '*' r &bull;</td><td bgcolor="grey" align="right">=$</td></tr></table>> ];
"state5" [ style = "filled" penwidth = 1 fillcolor = "black" fontname = "Courier New" shape = "Mrecord" label =<<table border="0" cellborder="0" cellpadding="3" bgcolor="black"><tr><td bgcolor="black" align="center" colspan="2"><font color="white">State #5</font></td></tr><tr><td align="left" port="r0"><font color="white">&#40;0&#41; s -&gt; e &bull;$ </font></td></tr></table>> ];
"state6" [ style = "filled" penwidth = 1 fillcolor = "white" fontname = "Courier New" shape = "Mrecord" label =<<table border="0" cellborder="0" cellpadding="3" bgcolor="white"><tr><td bgcolor="black" align="center" colspan="2"><font color="white">State #6</font></td></tr><tr><td align="left" port="r1">&#40;1&#41; e -&gt; l &bull;'=' r </td></tr><tr><td align="left" port="r5">&#40;5&#41; r -&gt; l &bull;</td><td bgcolor="grey" align="right">$</td></tr></table>> ];
"state7" [ style = "filled" penwidth = 1 fillcolor = "white" fontname = "Courier New" shape = "Mrecord" label =<<table border="0" cellborder="0" cellpadding="3" bgcolor="white"><tr><td bgcolor="black" align="center" colspan="2"><font color="white">State #7</font></td></tr><tr><td align="left" port="r1">&#40;1&#41; e -&gt; l '=' &bull;r </td></tr><tr><td align="left" port="r3">&#40;3&#41; l -&gt; &bull;'*' r </td></tr><tr><td align="left" port="r4">&#40;4&#41; l -&gt; &bull;'n' </td></tr><tr><td align="left" port="r5">&#40;5&#41; r -&gt; &bull;l </td></tr></table>> ];
"state8" [ style = "filled" penwidth = 1 fillcolor = "white" fontname = "Courier New" shape = "Mrecord" label =<<table border="0" cellborder="0" cellpadding="3" bgcolor="white"><tr><td bgcolor="black" align="center" colspan="2"><font color="white">State #8</font></td></tr><tr><td align="left" port="r1">&#40;1&#41; e -&gt; l '=' r &bull;</td><td bgcolor="grey" align="right">$</td></tr></table>> ];
"state9" [ style = "filled" penwidth = 1 fillcolor = "white" fontname = "Courier New" shape = "Mrecord" label =<<table border="0" cellborder="0" cellpadding="3" bgcolor="white"><tr><td bgcolor="black" align="center" colspan="2"><font color="white">State #9</font></td></tr><tr><td align="left" port="r2">&#40;2&#41; e -&gt; r &bull;</td><td bgcolor="grey" align="right">$</td></tr></table>> ];
state0 -> state5 [ penwidth = 5 fontsize = 28 fontcolor = "black" label = "e" ];
state0 -> state6 [ penwidth = 5 fontsize = 28 fontcolor = "black" label = "l" ];
state0 -> state9 [ penwidth = 5 fontsize = 28 fontcolor = "black" label = "r" ];
state0 -> state1 [ penwidth = 1 fontsize = 14 fontcolor = "grey28" label = "'*'" ];
state0 -> state2 [ penwidth = 1 fontsize = 14 fontcolor = "grey28" label = "'n'" ];
state1 -> state1 [ penwidth = 1 fontsize = 14 fontcolor = "grey28" label = "'*'" ];
state1 -> state4 [ penwidth = 5 fontsize = 28 fontcolor = "black" label = "r" ];
state1 -> state2 [ penwidth = 1 fontsize = 14 fontcolor = "grey28" label = "'n'" ];
state1 -> state3 [ penwidth = 5 fontsize = 28 fontcolor = "black" label = "l" ];
state6 -> state7 [ penwidth = 1 fontsize = 14 fontcolor = "grey28" label = "'='" ];
state7 -> state8 [ penwidth = 5 fontsize = 28 fontcolor = "black" label = "r" ];
state7 -> state1 [ penwidth = 1 fontsize = 14 fontcolor = "grey28" label = "'*'" ];
state7 -> state2 [ penwidth = 1 fontsize = 14 fontcolor = "grey28" label = "'n'" ];
state7 -> state3 [ penwidth = 5 fontsize = 28 fontcolor = "black" label = "l" ];
}
[/graph]

79
src/cache/cache.rs vendored
View file

@ -1,13 +1,29 @@
use rusqlite::types::FromSql;
use rusqlite::Connection;
use rusqlite::ToSql;
use std::{error::Error, path::PathBuf};
pub enum CachedError<E> {
SqlErr(rusqlite::Error),
GenErr(E),
use rusqlite::{types::FromSql, Connection, Params, ToSql};
struct Cache {
con: Connection
}
pub trait Cached {
impl Cache {
fn new(file: PathBuf) -> Result<Self, String> {
match Connection::open(file)
{
Err(e) => return Err(format!("Could not connect to cache database: {}", e.to_string())),
Ok(con) => Ok(Self { con })
}
}
}
pub enum CachedError<E>
{
SqlErr(rusqlite::Error),
GenErr(E)
}
pub trait Cached
{
type Key;
type Value;
@ -23,8 +39,10 @@ pub trait Cached {
fn key(&self) -> <Self as Cached>::Key;
fn init(con: &mut Connection) -> Result<(), rusqlite::Error> {
con.execute(<Self as Cached>::sql_table(), ()).map(|_| ())
fn init(con: &mut Connection) -> Result<(), rusqlite::Error>
{
con.execute(<Self as Cached>::sql_table(), ())
.map(|_| ())
}
/// Attempts to retrieve a cached element from the compilation database
@ -36,11 +54,8 @@ pub trait Cached {
/// or if not cached, an error from the generator [`f`]
///
/// Note that on error, [`f`] may still have been called
fn cached<E, F>(
&self,
con: &mut Connection,
f: F,
) -> Result<<Self as Cached>::Value, CachedError<E>>
fn cached<E, F>(&self, con: &mut Connection, f: F)
-> Result<<Self as Cached>::Value, CachedError<E>>
where
<Self as Cached>::Key: ToSql,
<Self as Cached>::Value: FromSql + ToSql,
@ -49,36 +64,42 @@ pub trait Cached {
let key = self.key();
// Find in cache
let mut query = match con.prepare(<Self as Cached>::sql_get_query()) {
let mut query = match con.prepare(<Self as Cached>::sql_get_query())
{
Ok(query) => query,
Err(e) => return Err(CachedError::SqlErr(e)),
Err(e) => return Err(CachedError::SqlErr(e))
};
let value = query
.query_row([&key], |row| {
let value = query.query_row([&key], |row|
{
Ok(row.get_unwrap::<_, <Self as Cached>::Value>(0))
})
.ok();
}).ok();
if let Some(value) = value {
if let Some(value) = value
{
// Found in cache
return Ok(value);
} else {
return Ok(value)
}
else
{
// Compute a value
let value = match f(&self) {
let value = match f(&self)
{
Ok(val) => val,
Err(e) => return Err(CachedError::GenErr(e)),
Err(e) => return Err(CachedError::GenErr(e))
};
// Try to insert
let mut query = match con.prepare(<Self as Cached>::sql_insert_query()) {
let mut query = match con.prepare(<Self as Cached>::sql_insert_query())
{
Ok(query) => query,
Err(e) => return Err(CachedError::SqlErr(e)),
Err(e) => return Err(CachedError::SqlErr(e))
};
match query.execute((&key, &value)) {
match query.execute((&key, &value))
{
Ok(_) => Ok(value),
Err(e) => Err(CachedError::SqlErr(e)),
Err(e) => Err(CachedError::SqlErr(e))
}
}
}

14
src/compiler/compiler.rs
View file

@ -62,12 +62,12 @@ impl Compiler
}
}
pub fn header(&self, document: &dyn Document) -> String
pub fn header(&self, document: &Document) -> String
{
pub fn get_variable_or_error(document: &dyn Document, var_name: &'static str) -> Option<Rc<dyn Variable>>
pub fn get_variable_or_error(document: &Document, var_name: &'static str) -> Option<Rc<dyn Variable>>
{
document.get_variable(var_name)
.and_then(|var| Some(var))
.and_then(|(_, var)| Some(var))
.or_else(|| {
println!("Missing variable `{var_name}` in {}", document.source().name());
None
@ -85,7 +85,7 @@ impl Compiler
result += format!("<title>{}</title>", self.sanitize(page_title.to_string())).as_str();
}
if let Some(css) = document.get_variable("html.css")
if let Some((_, css)) = document.get_variable("html.css")
{
result += format!("<link rel=\"stylesheet\" href=\"{}\">", self.sanitize(css.to_string())).as_str();
}
@ -101,7 +101,7 @@ impl Compiler
result
}
pub fn footer(&self, _document: &dyn Document) -> String
pub fn footer(&self, _document: &Document) -> String
{
let mut result = String::new();
match self.target()
@ -116,10 +116,10 @@ impl Compiler
result
}
pub fn compile(&self, document: &dyn Document) -> String
pub fn compile(&self, document: &Document) -> String
{
let mut out = String::new();
let borrow = document.content().borrow();
let borrow = document.content.borrow();
// Header
out += self.header(document).as_str();

232
src/document/document.rs
View file

@ -1,6 +1,4 @@
use std::cell::Ref;
use std::cell::RefCell;
use std::cell::RefMut;
use std::cell::{Ref, RefCell, RefMut};
use std::collections::hash_map::HashMap;
use std::rc::Rc;
@ -9,9 +7,7 @@ use crate::parser::source::Source;
use super::element::Element;
use super::variable::Variable;
// TODO: Referenceable rework
// Usize based referencing is not an acceptable method
// if we want to support deltas for the lsp
#[derive(Debug)]
pub struct Scope {
/// List of all referenceable elements in current scope.
@ -21,137 +17,168 @@ pub struct Scope {
}
impl Scope {
pub fn new() -> Self {
fn new() -> Self {
Self {
referenceable: HashMap::new(),
variables: HashMap::new(),
}
}
pub fn merge(&mut self, other: &mut Scope, merge_as: &String, ref_offset: usize) {
match merge_as.is_empty() {
pub fn merge(&mut self, other: &mut Scope, merge_as: &String, ref_offset: usize)
{
match merge_as.is_empty()
{
true => {
// References
self.referenceable.extend(
other
.referenceable
.drain()
.map(|(name, idx)| (name, idx + ref_offset)),
);
self.referenceable.extend(other.referenceable.drain()
.map(|(name, idx)|
(name, idx+ref_offset)));
// Variables
self.variables
.extend(other.variables.drain().map(|(name, var)| (name, var)));
}
self.variables.extend(other.variables.drain()
.map(|(name, var)|
(name, var)));
},
false => {
// References
self.referenceable.extend(
other
.referenceable
.drain()
.map(|(name, idx)| (format!("{merge_as}.{name}"), idx + ref_offset)),
);
self.referenceable.extend(other.referenceable.drain()
.map(|(name, idx)|
(format!("{merge_as}.{name}"), idx+ref_offset)));
// Variables
self.variables.extend(
other
.variables
.drain()
.map(|(name, var)| (format!("{merge_as}.{name}"), var)),
);
self.variables.extend(other.variables.drain()
.map(|(name, var)|
(format!("{merge_as}.{name}"), var)));
}
}
}
}
pub trait Document<'a>: core::fmt::Debug {
/// Gets the document [`Source`]
fn source(&self) -> Rc<dyn Source>;
#[derive(Debug)]
pub struct Document<'a> {
source: Rc<dyn Source>,
parent: Option<&'a Document<'a>>, /// Document's parent
/// Gets the document parent (if it exists)
fn parent(&self) -> Option<&'a dyn Document<'a>>;
// FIXME: Render these fields private
pub content: RefCell<Vec<Box<dyn Element>>>,
pub scope: RefCell<Scope>,
}
/// Gets the document content
/// The content is essentially the AST for the document
fn content(&self) -> &RefCell<Vec<Box<dyn Element>>>;
/// Gets the document [`Scope`]
fn scope(&self) -> &RefCell<Scope>;
/// Pushes a new element into the document's content
fn push(&self, elem: Box<dyn Element>) {
// TODO: RefTable
self.content().borrow_mut().push(elem);
impl<'a> Document<'a> {
pub fn new(source: Rc<dyn Source>, parent: Option<&'a Document<'a>>) -> Self
{
Self {
source: source,
parent: parent,
content: RefCell::new(Vec::new()),
scope: RefCell::new(Scope::new()),
}
}
/*
fn last_element(&'a self, recurse: bool) -> Option<Ref<'_, dyn Element>>
{
let elem = Ref::filter_map(self.content().borrow(),
|content| content.last()
.and_then(|last| last.downcast_ref::<Element>())
).ok();
pub fn source(&self) -> Rc<dyn Source> { self.source.clone() }
pub fn parent(&self) -> Option<&Document> { self.parent }
/// Push an element [`elem`] to content. [`in_paragraph`] is true if a paragraph is active
pub fn push(&self, elem: Box<dyn Element>)
{
// Add index of current element to scope's reference table
if let Some(referenceable) = elem.as_referenceable()
{
// Only add if referenceable holds a reference
if let Some(ref_name) = referenceable.reference_name()
{
self.scope.borrow_mut().referenceable.insert(ref_name.clone(), self.content.borrow().len());
}
}
self.content.borrow_mut().push(elem);
}
pub fn last_element<T: Element>(&self, recurse: bool) -> Option<Ref<'_, T>>
{
let elem = Ref::filter_map(self.content.borrow(),
|content| content.last()
.and_then(|last| last.downcast_ref::<T>())).ok();
if elem.is_some() || !recurse { return elem }
match self.parent()
match self.parent
{
None => None,
Some(parent) => parent.last_element(true),
}
}
fn last_element_mut(&'a self, recurse: bool) -> Option<RefMut<'_, dyn Element>>
pub fn last_element_mut<T: Element>(&self, recurse: bool) -> Option<RefMut<'_, T>>
{
let elem = RefMut::filter_map(self.content().borrow_mut(),
|content| content.last_mut()).ok();
let elem = RefMut::filter_map(self.content.borrow_mut(),
|content| content.last_mut()
.and_then(|last| last.downcast_mut::<T>())).ok();
if elem.is_some() || !recurse { return elem }
match self.parent()
match self.parent
{
None => None,
Some(parent) => parent.last_element_mut(true),
}
}
*/
fn add_variable(&self, variable: Rc<dyn Variable>) {
self.scope()
.borrow_mut()
.variables
.insert(variable.name().to_string(), variable);
}
fn get_variable(&self, name: &str) -> Option<Rc<dyn Variable>> {
match self.scope().borrow().variables.get(name) {
Some(variable) => {
return Some(variable.clone());
}
pub fn get_reference(&self, ref_name: &str) -> Option<(&Document<'a>, std::cell::Ref<'_, Box<dyn Element>>)> {
match self.scope.borrow().referenceable.get(ref_name) {
// Return if found
Some(elem) => {
return Some((&self,
std::cell::Ref::map(self.content.borrow(),
|m| &m[*elem])))
},
// Continue search recursively
None => match self.parent() {
None => match self.parent {
Some(parent) => return parent.get_reference(ref_name),
// Not found
None => return None,
}
}
}
pub fn add_variable(&self, variable: Rc<dyn Variable>)
{
self.scope.borrow_mut().variables.insert(
variable.name().to_string(),
variable);
}
pub fn get_variable<S: AsRef<str>>(&self, name: S) -> Option<(&Document<'a>, Rc<dyn Variable>)>
{
match self.scope.borrow().variables.get(name.as_ref())
{
Some(variable) => {
return Some((&self, variable.clone()));
},
// Continue search recursively
None => match self.parent {
Some(parent) => return parent.get_variable(name),
// Not found
None => return None,
},
}
}
}
/*
fn remove_variable(&self, name: &str) -> Option<Rc<dyn Variable>>
pub fn remove_variable<S: AsRef<str>>(&self, name: S) -> Option<(&Document<'a>, Rc<dyn Variable>)>
{
match self.scope().borrow_mut().variables.remove(name)
match self.scope.borrow_mut().variables.remove(name.as_ref())
{
Some(variable) => {
return Some(variable.clone());
return Some((&self, variable.clone()));
},
// Continue search recursively
None => match self.parent() {
None => match self.parent {
Some(parent) => return parent.remove_variable(name),
// Not found
@ -159,48 +186,25 @@ pub trait Document<'a>: core::fmt::Debug {
}
}
}
*/
/// Merges [`other`] into [`self`]
fn merge(
&self,
content: &RefCell<Vec<Box<dyn Element>>>,
scope: &RefCell<Scope>,
merge_as: Option<&String>,
) {
match merge_as {
Some(merge_as) => self.scope().borrow_mut().merge(
&mut *scope.borrow_mut(),
pub fn merge(&self, other: Document, merge_as: Option<&String>)
{
match merge_as
{
Some(merge_as) => self.scope.borrow_mut()
.merge(
&mut *other.scope.borrow_mut(),
merge_as,
self.content().borrow().len() + 1,
),
_ => {}
self.content.borrow().len()+1),
_ => {},
}
// Content
self.content()
.borrow_mut()
.extend((content.borrow_mut()).drain(..).map(|value| value));
self.content.borrow_mut().extend((other.content.borrow_mut())
.drain(..)
.map(|value| value));
}
}
pub trait DocumentAccessors<'a> {
fn last_element<T: Element>(&self) -> Option<Ref<'_, T>>;
fn last_element_mut<T: Element>(&self) -> Option<RefMut<'_, T>>;
}
impl<'a> DocumentAccessors<'a> for dyn Document<'a> + '_ {
fn last_element<T: Element>(&self) -> Option<Ref<'_, T>> {
Ref::filter_map(self.content().borrow(), |content| {
content.last().and_then(|last| last.downcast_ref::<T>())
})
.ok()
}
fn last_element_mut<T: Element>(&self) -> Option<RefMut<'_, T>> {
RefMut::filter_map(self.content().borrow_mut(), |content| {
content.last_mut().and_then(|last| last.downcast_mut::<T>())
})
.ok()
}
}

2
src/document/element.rs
View file

@ -48,7 +48,7 @@ pub trait Element: Downcast
fn as_referenceable(&self) -> Option<&dyn ReferenceableElement> { None }
/// Compiles element
fn compile(&self, compiler: &Compiler, document: &dyn Document) -> Result<String, String>;
fn compile(&self, compiler: &Compiler, document: &Document) -> Result<String, String>;
}
impl_downcast!(Element);

38
src/document/langdocument.rs
View file

@ -1,38 +0,0 @@
use std::{cell::RefCell, rc::Rc};
use crate::parser::source::Source;
use super::{document::{Document, Scope}, element::Element};
#[derive(Debug)]
pub struct LangDocument<'a> {
source: Rc<dyn Source>,
parent: Option<&'a dyn Document<'a>>, /// Document's parent
// FIXME: Render these fields private
pub content: RefCell<Vec<Box<dyn Element>>>,
pub scope: RefCell<Scope>,
}
impl<'a> LangDocument<'a>
{
pub fn new(source: Rc<dyn Source>, parent: Option<&'a dyn Document<'a>>) -> Self
{
Self {
source: source,
parent: parent,
content: RefCell::new(Vec::new()),
scope: RefCell::new(Scope::new()),
}
}
}
impl<'a> Document<'a> for LangDocument<'a> {
fn source(&self) -> Rc<dyn Source> { self.source.clone() }
fn parent(&self) -> Option<&'a dyn Document<'a>> { self.parent.and_then(|p| Some(p as &dyn Document<'a>)) }
fn content(&self) -> &RefCell<Vec<Box<dyn Element>>> { &self.content }
fn scope(&self) -> &RefCell<Scope> { &self.scope }
}

2
src/document/mod.rs
View file

@ -1,5 +1,3 @@
pub mod document;
pub mod references;
pub mod langdocument;
pub mod element;
pub mod variable;

28
src/document/references.rs
View file

@ -1,28 +0,0 @@
pub fn validate_refname(name: &str) -> Result<&str, String> {
let trimmed = name.trim_start().trim_end();
if trimmed.is_empty() {
return Err("Refname cannot be empty".to_string());
}
for c in trimmed.chars() {
if c.is_ascii_punctuation() {
return Err(format!(
"Refname `{trimmed}` cannot contain punctuation codepoint: `{c}`"
));
}
if c.is_whitespace() {
return Err(format!(
"Refname `{trimmed}` cannot contain whitespaces: `{c}`"
));
}
if c.is_control() {
return Err(format!(
"Refname `{trimmed}` cannot contain control codepoint: `{c}`"
));
}
}
Ok(trimmed)
}

12
src/document/variable.rs
View file

@ -1,6 +1,6 @@
use std::{path::PathBuf, rc::Rc};
use crate::{elements::text::Text, parser::{parser::Parser, source::{Source, Token, VirtualSource}}};
use super::document::Document;
use super::{document::Document};
// TODO enforce to_string(from_string(to_string())) == to_string()
@ -15,7 +15,7 @@ pub trait Variable
/// Converts variable to a string
fn to_string(&self) -> String;
fn parse<'a>(&self, location: Token, parser: &dyn Parser, document: &'a dyn Document<'a>);
fn parse<'a>(&self, location: Token, parser: &dyn Parser, document: &'a Document);
}
impl core::fmt::Debug for dyn Variable
@ -52,7 +52,7 @@ impl Variable for BaseVariable
fn to_string(&self) -> String { self.value.clone() }
fn parse<'a>(&self, _location: Token, parser: &dyn Parser, document: &'a dyn Document<'a>) {
fn parse<'a>(&self, _location: Token, parser: &dyn Parser, document: &'a Document) {
let source = Rc::new(VirtualSource::new(
self.location().clone(),
self.name().to_string(),
@ -90,12 +90,12 @@ impl Variable for PathVariable
fn to_string(&self) -> String { self.path.to_str().unwrap().to_string() }
fn parse<'a>(&self, location: Token, parser: &dyn Parser, document: &'a dyn Document) {
// TODO: Avoid copying the content...
fn parse<'a>(&self, location: Token, parser: &dyn Parser, document: &'a Document){
// TODO: Avoid copying the location twice...
// Maybe create a special VirtualSource where the `content()` method
// calls `Variable::to_string()`
let source = Rc::new(VirtualSource::new(
location,
location.clone(),
self.name().to_string(),
self.to_string()));

422
src/elements/code.rs
View file

@ -1,48 +1,25 @@
use std::collections::HashMap;
use std::ops::Range;
use std::rc::Rc;
use std::sync::Once;
use std::{collections::HashMap, ops::Range, rc::Rc, sync::Once};
use ariadne::Fmt;
use ariadne::Label;
use ariadne::Report;
use ariadne::ReportKind;
use crypto::digest::Digest;
use crypto::sha2::Sha512;
use mlua::Function;
use mlua::Lua;
use regex::Captures;
use regex::Regex;
use syntect::easy::HighlightLines;
use syntect::highlighting::ThemeSet;
use syntect::parsing::SyntaxSet;
use ariadne::{Fmt, Label, Report, ReportKind};
use crypto::{digest::Digest, sha2::Sha512};
use mlua::{Function, Lua};
use regex::{Captures, Regex};
use syntect::{easy::HighlightLines, highlighting::ThemeSet, parsing::SyntaxSet};
use crate::cache::cache::Cached;
use crate::cache::cache::CachedError;
use crate::compiler::compiler::Compiler;
use crate::compiler::compiler::Target;
use crate::document::document::Document;
use crate::document::element::ElemKind;
use crate::document::element::Element;
use crate::parser::parser::Parser;
use crate::parser::rule::RegexRule;
use crate::parser::source::Source;
use crate::parser::source::Token;
use crate::parser::util::Property;
use crate::parser::util::PropertyMapError;
use crate::parser::util::PropertyParser;
use crate::parser::util::{self};
use crate::{cache::cache::{Cached, CachedError}, compiler::compiler::{Compiler, Target}, document::{document::Document, element::{ElemKind, Element}}, parser::{parser::Parser, rule::RegexRule, source::{Source, Token}, util::{self, Property, PropertyParser}}};
use lazy_static::lazy_static;
#[derive(Clone, Copy, Debug, PartialEq, Eq)]
enum CodeKind {
enum CodeKind
{
FullBlock,
MiniBlock,
Inline,
}
#[derive(Debug)]
struct Code {
struct Code
{
location: Token,
block: CodeKind,
language: String,
@ -53,91 +30,57 @@ struct Code {
}
impl Code {
fn new(
location: Token,
block: CodeKind,
language: String,
name: Option<String>,
code: String,
theme: Option<String>,
line_offset: usize,
) -> Self {
Self {
location,
block,
language,
name,
code,
theme,
line_offset,
}
fn new(location: Token, block: CodeKind, language: String, name: Option<String>, code: String, theme: Option<String>, line_offset: usize) -> Self {
Self { location, block, language, name, code, theme, line_offset }
}
fn highlight_html(&self, compiler: &Compiler) -> Result<String, String> {
fn highlight_html(&self, compiler: &Compiler) -> Result<String, String>
{
lazy_static! {
static ref syntax_set: SyntaxSet = SyntaxSet::load_defaults_newlines();
static ref theme_set: ThemeSet = ThemeSet::load_defaults();
static ref syntax_set : SyntaxSet = SyntaxSet::load_defaults_newlines();
static ref theme_set : ThemeSet = ThemeSet::load_defaults();
}
let syntax = match syntax_set.find_syntax_by_name(self.language.as_str()) {
let syntax = match syntax_set.find_syntax_by_name(self.language.as_str())
{
Some(syntax) => syntax,
None => {
return Err(format!(
"Unable to find syntax for language: {}",
self.language
))
}
None => return Err(format!("Unable to find syntax for language: {}", self.language))
};
let theme_string = match self.theme.as_ref() {
let theme_string = match self.theme.as_ref()
{
Some(theme) => theme.as_str(),
None => "base16-ocean.dark",
};
let mut h = HighlightLines::new(syntax, &theme_set.themes[theme_string]);
let mut result = String::new();
if self.block == CodeKind::FullBlock {
if self.block == CodeKind::FullBlock
{
result += "<div class=\"code-block\">";
if let Some(name) = &self.name {
result += format!(
"<div class=\"code-block-title\">{}</div>",
compiler.sanitize(name.as_str())
)
.as_str();
if let Some(name) = &self.name
{
result += format!("<div class=\"code-block-title\">{}</div>",
compiler.sanitize(name.as_str())).as_str();
}
result +=
format!("<div class=\"code-block-content\"><table cellspacing=\"0\">").as_str();
for (line_id, line) in self.code.split(|c| c == '\n').enumerate() {
result += format!("<div class=\"code-block-content\"><table cellspacing=\"0\">").as_str();
for (line_id, line) in self.code.split(|c| c == '\n').enumerate()
{
result += "<tr><td class=\"code-block-gutter\">";
// Line number
result +=
format!("<pre><span>{}</span></pre>", line_id + self.line_offset).as_str();
result += format!("<pre><span>{}</span></pre>", line_id+self.line_offset).as_str();
// Code
result += "</td><td class=\"code-block-line\"><pre>";
match h.highlight_line(line, &syntax_set) {
Err(e) => {
return Err(format!(
"Error highlighting line `{line}`: {}",
e.to_string()
))
}
match h.highlight_line(line, &syntax_set)
{
Err(e) => return Err(format!("Error highlighting line `{line}`: {}", e.to_string())),
Ok(regions) => {
match syntect::html::styled_line_to_highlighted_html(
&regions[..],
syntect::html::IncludeBackground::No,
) {
Err(e) => {
return Err(format!("Error highlighting code: {}", e.to_string()))
}
Ok(highlighted) => {
result += if highlighted.is_empty() {
"<br>"
} else {
highlighted.as_str()
}
}
match syntect::html::styled_line_to_highlighted_html(&regions[..], syntect::html::IncludeBackground::No)
{
Err(e) => return Err(format!("Error highlighting code: {}", e.to_string())),
Ok(highlighted) => result += if highlighted.is_empty() { "<br>" } else { highlighted.as_str() }
}
}
}
@ -145,59 +88,41 @@ impl Code {
}
result += "</table></div></div>";
} else if self.block == CodeKind::MiniBlock {
}
else if self.block == CodeKind::MiniBlock
{
result += "<div class=\"code-block\"><div class=\"code-block-content\"><table cellspacing=\"0\">";
for line in self.code.split(|c| c == '\n') {
for line in self.code.split(|c| c == '\n')
{
result += "<tr><td class=\"code-block-line\"><pre>";
// Code
match h.highlight_line(line, &syntax_set) {
Err(e) => {
return Err(format!(
"Error highlighting line `{line}`: {}",
e.to_string()
))
}
match h.highlight_line(line, &syntax_set)
{
Err(e) => return Err(format!("Error highlighting line `{line}`: {}", e.to_string())),
Ok(regions) => {
match syntect::html::styled_line_to_highlighted_html(
&regions[..],
syntect::html::IncludeBackground::No,
) {
Err(e) => {
return Err(format!("Error highlighting code: {}", e.to_string()))
}
Ok(highlighted) => {
result += if highlighted.is_empty() {
"<br>"
} else {
highlighted.as_str()
}
}
match syntect::html::styled_line_to_highlighted_html(&regions[..], syntect::html::IncludeBackground::No)
{
Err(e) => return Err(format!("Error highlighting code: {}", e.to_string())),
Ok(highlighted) => result += if highlighted.is_empty() { "<br>" } else { highlighted.as_str() }
}
}
}
result += "</pre></td></tr>";
}
result += "</table></div></div>";
} else if self.block == CodeKind::Inline {
}
else if self.block == CodeKind::Inline
{
result += "<a class=\"inline-code\"><code>";
match h.highlight_line(self.code.as_str(), &syntax_set) {
Err(e) => {
return Err(format!(
"Error highlighting line `{}`: {}",
self.code,
e.to_string()
))
}
match h.highlight_line(self.code.as_str(), &syntax_set)
{
Err(e) => return Err(format!("Error highlighting line `{}`: {}", self.code, e.to_string())),
Ok(regions) => {
match syntect::html::styled_line_to_highlighted_html(
&regions[..],
syntect::html::IncludeBackground::No,
) {
Err(e) => {
return Err(format!("Error highlighting code: {}", e.to_string()))
}
Ok(highlighted) => result += highlighted.as_str(),
match syntect::html::styled_line_to_highlighted_html(&regions[..], syntect::html::IncludeBackground::No)
{
Err(e) => return Err(format!("Error highlighting code: {}", e.to_string())),
Ok(highlighted) => result += highlighted.as_str()
}
}
}
@ -208,7 +133,8 @@ impl Code {
}
}
impl Cached for Code {
impl Cached for Code
{
type Key = String;
type Value = String;
@ -218,7 +144,9 @@ impl Cached for Code {
highlighted BLOB NOT NULL);"
}
fn sql_get_query() -> &'static str { "SELECT highlighted FROM cached_code WHERE digest = (?1)" }
fn sql_get_query() -> &'static str {
"SELECT highlighted FROM cached_code WHERE digest = (?1)"
}
fn sql_insert_query() -> &'static str {
"INSERT INTO cached_code (digest, highlighted) VALUES (?1, ?2)"
@ -228,9 +156,7 @@ impl Cached for Code {
let mut hasher = Sha512::new();
hasher.input((self.block as usize).to_be_bytes().as_slice());
hasher.input((self.line_offset as usize).to_be_bytes().as_slice());
self.theme
.as_ref()
.map(|theme| hasher.input(theme.as_bytes()));
self.theme.as_ref().map(|theme| hasher.input(theme.as_bytes()));
self.name.as_ref().map(|name| hasher.input(name.as_bytes()));
hasher.input(self.language.as_bytes());
hasher.input(self.code.as_bytes());
@ -242,47 +168,44 @@ impl Cached for Code {
impl Element for Code {
fn location(&self) -> &Token { &self.location }
fn kind(&self) -> ElemKind {
if self.block == CodeKind::Inline {
ElemKind::Inline
} else {
ElemKind::Block
}
}
fn kind(&self) -> ElemKind { if self.block == CodeKind::Inline { ElemKind::Inline } else { ElemKind::Block } }
fn element_name(&self) -> &'static str { "Code Block" }
fn to_string(&self) -> String { format!("{self:#?}") }
fn compile(&self, compiler: &Compiler, _document: &dyn Document) -> Result<String, String> {
match compiler.target() {
fn compile(&self, compiler: &Compiler, _document: &Document)
-> Result<String, String> {
match compiler.target()
{
Target::HTML => {
static CACHE_INIT: Once = Once::new();
CACHE_INIT.call_once(|| {
if let Some(mut con) = compiler.cache() {
if let Err(e) = Code::init(&mut con) {
static CACHE_INIT : Once = Once::new();
CACHE_INIT.call_once(|| if let Some(mut con) = compiler.cache() {
if let Err(e) = Code::init(&mut con)
{
eprintln!("Unable to create cache table: {e}");
}
}
});
if let Some(mut con) = compiler.cache() {
match self.cached(&mut con, |s| s.highlight_html(compiler)) {
if let Some(mut con) = compiler.cache()
{
match self.cached(&mut con, |s| s.highlight_html(compiler))
{
Ok(s) => Ok(s),
Err(e) => match e {
CachedError::SqlErr(e) => {
Err(format!("Querying the cache failed: {e}"))
Err(e) => match e
{
CachedError::SqlErr(e) => Err(format!("Querying the cache failed: {e}")),
CachedError::GenErr(e) => Err(e)
}
CachedError::GenErr(e) => Err(e),
},
}
} else {
}
else
{
self.highlight_html(compiler)
}
}
Target::LATEX => {
todo!("")
}
Target::LATEX => { todo!("") }
}
}
}
@ -295,46 +218,33 @@ pub struct CodeRule {
impl CodeRule {
pub fn new() -> Self {
let mut props = HashMap::new();
props.insert(
"line_offset".to_string(),
props.insert("line_offset".to_string(),
Property::new(
true,
"Line number offset".to_string(),
Some("1".to_string()),
),
);
Some("1".to_string())));
Self {
re: [
Regex::new(
r"(?:^|\n)```(?:\[((?:\\.|[^\\\\])*?)\])?(.*?)(?:,(.*))?\n((?:\\(?:.|\n)|[^\\\\])*?)```",
)
.unwrap(),
Regex::new(
r"``(?:\[((?:\\.|[^\[\]\\])*?)\])?(?:(.*?)(?:\n|,))?((?:\\(?:.|\n)|[^\\\\])*?)``",
)
.unwrap(),
Regex::new(r"(?:^|\n)```(?:\[((?:\\.|[^\\\\])*?)\])?(.*?)(?:,(.*))?\n((?:\\(?:.|\n)|[^\\\\])*?)```").unwrap(),
Regex::new(r"``(?:\[((?:\\.|[^\[\]\\])*?)\])?(?:(.*)(?:\n|,))?((?:\\(?:.|\n)|[^\\\\])*?)``").unwrap(),
],
properties: PropertyParser::new(props),
properties: PropertyParser::new(props)
}
}
}
impl RegexRule for CodeRule {
impl RegexRule for CodeRule
{
fn name(&self) -> &'static str { "Code" }
fn regexes(&self) -> &[regex::Regex] { &self.re }
fn on_regex_match<'a>(
&self,
index: usize,
parser: &dyn Parser,
document: &'a dyn Document,
token: Token,
matches: Captures,
) -> Vec<Report<'_, (Rc<dyn Source>, Range<usize>)>> {
fn on_regex_match(&self, index: usize, parser: &dyn Parser, document: &Document, token: Token, matches: Captures)
-> Vec<Report<'_, (Rc<dyn Source>, Range<usize>)>> {
let mut reports = vec![];
let properties = match matches.get(1) {
let properties = match matches.get(1)
{
None => match self.properties.default() {
Ok(properties) => properties,
Err(e) => {
@ -344,17 +254,16 @@ impl RegexRule for CodeRule {
.with_label(
Label::new((token.source().clone(), token.range.clone()))
.with_message(format!("Code is missing properties: {e}"))
.with_color(parser.colors().error),
)
.finish(),
);
.with_color(parser.colors().error))
.finish());
return reports;
}
},
}
Some(props) => {
let processed =
util::process_escaped('\\', "]", props.as_str().trim_start().trim_end());
match self.properties.parse(processed.as_str()) {
let processed = util::process_escaped('\\', "]",
props.as_str().trim_start().trim_end());
match self.properties.parse(processed.as_str())
{
Err(e) => {
reports.push(
Report::build(ReportKind::Error, token.source(), props.start())
@ -362,32 +271,30 @@ impl RegexRule for CodeRule {
.with_label(
Label::new((token.source().clone(), props.range()))
.with_message(e)
.with_color(parser.colors().error),
)
.finish(),
);
.with_color(parser.colors().error))
.finish());
return reports;
}
Ok(properties) => properties,
Ok(properties) => properties
}
}
};
let code_lang = match matches.get(2) {
let code_lang = match matches.get(2)
{
None => "Plain Text".to_string(),
Some(lang) => {
let code_lang = lang.as_str().trim_end().trim_start().to_string();
if code_lang.is_empty() {
if code_lang.is_empty()
{
reports.push(
Report::build(ReportKind::Error, token.source(), lang.start())
.with_message("Missing code language")
.with_label(
Label::new((token.source().clone(), lang.range()))
.with_message("No language specified")
.with_color(parser.colors().error),
)
.finish(),
);
.with_color(parser.colors().error))
.finish());
return reports;
}
@ -398,50 +305,43 @@ impl RegexRule for CodeRule {
}
};
let mut code_content = if index == 0 {
util::process_escaped('\\', "```", matches.get(4).unwrap().as_str())
} else {
util::process_escaped('\\', "``", matches.get(3).unwrap().as_str())
};
if code_content.bytes().last() == Some('\n' as u8)
// Remove newline
let mut code_content = if index == 0
{ util::process_escaped('\\',"```", matches.get(4).unwrap().as_str()) }
else
{ util::process_escaped('\\',"``", matches.get(3).unwrap().as_str()) };
if code_content.bytes().last() == Some('\n' as u8) // Remove newline
{
code_content.pop();
}
if code_content.is_empty() {
if code_content.is_empty()
{
reports.push(
Report::build(ReportKind::Error, token.source(), token.start())
.with_message("Missing code content")
.with_label(
Label::new((token.source().clone(), token.range.clone()))
.with_message("Code content cannot be empty")
.with_color(parser.colors().error),
)
.finish(),
);
.with_color(parser.colors().error))
.finish());
return reports;
}
let theme = document
.get_variable("code.theme")
.and_then(|var| Some(var.to_string()));
let theme = document.get_variable("code.theme")
.and_then(|(_doc, var)| Some(var.to_string()));
if index == 0
// Block
if index == 0 // Block
{
let code_name = matches.get(3).and_then(|name| {
let code_name = matches.get(3)
.and_then(|name| {
let code_name = name.as_str().trim_end().trim_start().to_string();
(!code_name.is_empty()).then_some(code_name)
});
let line_offset =
match properties.get("line_offset", |prop, value| {
value.parse::<usize>().map_err(|e| (prop, e))
}) {
let line_offset = match properties.get("line_offset",
|prop, value| value.parse::<usize>().map_err(|e| (prop, e)))
{
Ok((_prop, offset)) => offset,
Err(e) => {
match e {
PropertyMapError::ParseError((prop, err)) => {
Err((prop, e)) => {
reports.push(
Report::build(ReportKind::Error, token.source(), token.start())
.with_message("Invalid Code Property")
@ -449,58 +349,32 @@ impl RegexRule for CodeRule {
Label::new((token.source().clone(), token.start()+1..token.end()))
.with_message(format!("Property `line_offset: {}` cannot be converted: {}",
prop.fg(parser.colors().info),
err.fg(parser.colors().error)))
e.fg(parser.colors().error)))
.with_color(parser.colors().warning))
.finish());
return reports;
}
PropertyMapError::NotFoundError(err) => {
reports.push(
Report::build(ReportKind::Error, token.source(), token.start())
.with_message("Invalid Code Property")
.with_label(
Label::new((
token.source().clone(),
token.start() + 1..token.end(),
))
.with_message(format!(
"Property `{}` doesn't exist",
err.fg(parser.colors().info)
))
.with_color(parser.colors().warning),
)
.finish(),
);
return reports;
}
}
}
};
parser.push(
document,
Box::new(Code::new(
parser.push(document, Box::new(
Code::new(
token.clone(),
CodeKind::FullBlock,
code_lang,
code_name,
code_content,
theme,
line_offset,
)),
);
} else
// Maybe inline
line_offset
)
));
}
else // Maybe inline
{
let block = if code_content.contains('\n') {
CodeKind::MiniBlock
} else {
CodeKind::Inline
};
let block = if code_content.contains('\n') { CodeKind::MiniBlock }
else { CodeKind::Inline };
parser.push(
document,
Box::new(Code::new(
parser.push(document, Box::new(
Code::new(
token.clone(),
block,
code_lang,
@ -508,8 +382,8 @@ impl RegexRule for CodeRule {
code_content,
theme,
1,
)),
);
)
));
}
reports

8
src/elements/comment.rs
View file

@ -1,8 +1,8 @@
use mlua::{Function, Lua};
use regex::{Captures, Regex};
use crate::{document::document::Document, parser::{parser::Parser, rule::RegexRule, source::{Source, Token}}};
use crate::parser::{parser::Parser, rule::RegexRule, source::{Source, Token}};
use ariadne::{Report, Label, ReportKind};
use crate::{compiler::compiler::Compiler, document::element::{ElemKind, Element}};
use crate::{compiler::compiler::Compiler, document::{document::Document, element::{ElemKind, Element}}};
use std::{ops::Range, rc::Rc};
#[derive(Debug)]
@ -24,7 +24,7 @@ impl Element for Comment
fn kind(&self) -> ElemKind { ElemKind::Invisible }
fn element_name(&self) -> &'static str { "Comment" }
fn to_string(&self) -> String { format!("{self:#?}") }
fn compile(&self, _compiler: &Compiler, _document: &dyn Document)
fn compile(&self, _compiler: &Compiler, _document: &Document)
-> Result<String, String> {
Ok("".to_string())
}
@ -45,7 +45,7 @@ impl RegexRule for CommentRule {
fn regexes(&self) -> &[Regex] { &self.re }
fn on_regex_match<'a>(&self, _: usize, parser: &dyn Parser, document: &'a dyn Document, token: Token, matches: Captures)
fn on_regex_match(&self, _: usize, parser: &dyn Parser, document: &Document, token: Token, matches: Captures)
-> Vec<Report<'_, (Rc<dyn Source>, Range<usize>)>> {
let mut reports = vec![];

375
src/elements/graphviz.rs
View file

@ -1,375 +0,0 @@
use std::collections::HashMap;
use std::ops::Range;
use std::rc::Rc;
use std::sync::Once;
use crate::parser::util::Property;
use crate::parser::util::PropertyMapError;
use crate::parser::util::PropertyParser;
use ariadne::Fmt;
use ariadne::Label;
use ariadne::Report;
use ariadne::ReportKind;
use crypto::digest::Digest;
use crypto::sha2::Sha512;
use graphviz_rust::cmd::Format;
use graphviz_rust::cmd::Layout;
use graphviz_rust::exec_dot;
use mlua::Function;
use mlua::Lua;
use regex::Captures;
use regex::Regex;
use crate::cache::cache::Cached;
use crate::cache::cache::CachedError;
use crate::compiler::compiler::Compiler;
use crate::compiler::compiler::Target;
use crate::document::document::Document;
use crate::document::element::ElemKind;
use crate::document::element::Element;
use crate::parser::parser::Parser;
use crate::parser::rule::RegexRule;
use crate::parser::source::Source;
use crate::parser::source::Token;
use crate::parser::util;
#[derive(Debug)]
struct Graphviz {
pub location: Token,
pub dot: String,
pub layout: Layout,
pub width: String,
pub caption: Option<String>,
}
fn layout_from_str(value: &str) -> Result<Layout, String> {
match value {
"dot" => Ok(Layout::Dot),
"neato" => Ok(Layout::Neato),
"fdp" => Ok(Layout::Fdp),
"sfdp" => Ok(Layout::Sfdp),
"circo" => Ok(Layout::Circo),
"twopi" => Ok(Layout::Twopi),
"osage" => Ok(Layout::Asage), // typo in graphviz_rust ?
"patchwork" => Ok(Layout::Patchwork),
_ => Err(format!("Unknown layout: {value}")),
}
}
impl Graphviz {
/// Renders dot to svg
fn dot_to_svg(&self) -> Result<String, String> {
print!("Rendering Graphviz `{}`... ", self.dot);
let svg = match exec_dot(
self.dot.clone(),
vec![self.layout.into(), Format::Svg.into()],
) {
Ok(svg) => {
let out = String::from_utf8_lossy(svg.as_slice());
let svg_start = out.find("<svg").unwrap(); // Remove svg header
let split_at = out.split_at(svg_start).1.find('\n').unwrap();
let mut result = format!("<svg width=\"{}\"", self.width);
result.push_str(out.split_at(svg_start+split_at).1);
result
}
Err(e) => return Err(format!("Unable to execute dot: {e}")),
};
println!("Done!");
Ok(svg)
}
}
impl Cached for Graphviz {
type Key = String;
type Value = String;
fn sql_table() -> &'static str {
"CREATE TABLE IF NOT EXISTS cached_dot (
digest TEXT PRIMARY KEY,
svg BLOB NOT NULL);"
}
fn sql_get_query() -> &'static str { "SELECT svg FROM cached_dot WHERE digest = (?1)" }
fn sql_insert_query() -> &'static str { "INSERT INTO cached_dot (digest, svg) VALUES (?1, ?2)" }
fn key(&self) -> <Self as Cached>::Key {
let mut hasher = Sha512::new();
hasher.input((self.layout as usize).to_be_bytes().as_slice());
hasher.input(self.dot.as_bytes());
hasher.result_str()
}
}
impl Element for Graphviz {
fn location(&self) -> &Token { &self.location }
fn kind(&self) -> ElemKind { ElemKind::Block }
fn element_name(&self) -> &'static str { "Graphviz" }
fn to_string(&self) -> String { format!("{self:#?}") }
fn compile(&self, compiler: &Compiler, _document: &dyn Document) -> Result<String, String> {
match compiler.target() {
Target::HTML => {
static CACHE_INIT: Once = Once::new();
CACHE_INIT.call_once(|| {
if let Some(mut con) = compiler.cache() {
if let Err(e) = Graphviz::init(&mut con) {
eprintln!("Unable to create cache table: {e}");
}
}
});
// TODO: Format svg in a div
if let Some(mut con) = compiler.cache() {
match self.cached(&mut con, |s| s.dot_to_svg()) {
Ok(s) => Ok(s),
Err(e) => match e {
CachedError::SqlErr(e) => {
Err(format!("Querying the cache failed: {e}"))
}
CachedError::GenErr(e) => Err(e),
},
}
} else {
match self.dot_to_svg() {
Ok(svg) => Ok(svg),
Err(e) => Err(e),
}
}
}
_ => todo!("Unimplemented"),
}
}
}
pub struct GraphRule {
re: [Regex; 1],
properties: PropertyParser,
}
impl GraphRule {
pub fn new() -> Self {
let mut props = HashMap::new();
props.insert(
"layout".to_string(),
Property::new(
true,
"Graphviz layout engine see <https://graphviz.org/docs/layouts/>".to_string(),
Some("dot".to_string()),
),
);
props.insert(
"width".to_string(),
Property::new(
true,
"SVG width".to_string(),
Some("100%".to_string()),
),
);
Self {
re: [Regex::new(
r"\[graph\](?:\[((?:\\.|[^\[\]\\])*?)\])?(?:((?:\\.|[^\\\\])*?)\[/graph\])?",
)
.unwrap()],
properties: PropertyParser::new(props),
}
}
}
impl RegexRule for GraphRule {
fn name(&self) -> &'static str { "Graph" }
fn regexes(&self) -> &[regex::Regex] { &self.re }
fn on_regex_match(
&self,
_: usize,
parser: &dyn Parser,
document: &dyn Document,
token: Token,
matches: Captures,
) -> Vec<Report<'_, (Rc<dyn Source>, Range<usize>)>> {
let mut reports = vec![];
let graph_content = match matches.get(2) {
// Unterminated `[graph]`
None => {
reports.push(
Report::build(ReportKind::Error, token.source(), token.start())
.with_message("Unterminated Graph Code")
.with_label(
Label::new((token.source().clone(), token.range.clone()))
.with_message(format!(
"Missing terminating `{}` after first `{}`",
"[/graph]".fg(parser.colors().info),
"[graph]".fg(parser.colors().info)
))
.with_color(parser.colors().error),
)
.finish(),
);
return reports;
}
Some(content) => {
let processed = util::process_escaped(
'\\',
"[/graph]",
content.as_str().trim_start().trim_end(),
);
if processed.is_empty() {
reports.push(
Report::build(ReportKind::Error, token.source(), content.start())
.with_message("Empty Graph Code")
.with_label(
Label::new((token.source().clone(), content.range()))
.with_message("Graph code is empty")
.with_color(parser.colors().error),
)
.finish(),
);
return reports;
}
processed
}
};
// Properties
let properties = match matches.get(1) {
None => match self.properties.default() {
Ok(properties) => properties,
Err(e) => {
reports.push(
Report::build(ReportKind::Error, token.source(), token.start())
.with_message("Invalid Graph")
.with_label(
Label::new((token.source().clone(), token.range.clone()))
.with_message(format!("Graph is missing property: {e}"))
.with_color(parser.colors().error),
)
.finish(),
);
return reports;
}
},
Some(props) => {
let processed =
util::process_escaped('\\', "]", props.as_str().trim_start().trim_end());
match self.properties.parse(processed.as_str()) {
Err(e) => {
reports.push(
Report::build(ReportKind::Error, token.source(), props.start())
.with_message("Invalid Graph Properties")
.with_label(
Label::new((token.source().clone(), props.range()))
.with_message(e)
.with_color(parser.colors().error),
)
.finish(),
);
return reports;
}
Ok(properties) => properties,
}
}
};
// Property "layout"
let graph_layout = match properties.get("layout", |prop, value| {
layout_from_str(value.as_str()).map_err(|e| (prop, e))
}) {
Ok((_prop, kind)) => kind,
Err(e) => match e {
PropertyMapError::ParseError((prop, err)) => {
reports.push(
Report::build(ReportKind::Error, token.source(), token.start())
.with_message("Invalid Graph Property")
.with_label(
Label::new((token.source().clone(), token.range.clone()))
.with_message(format!(
"Property `layout: {}` cannot be converted: {}",
prop.fg(parser.colors().info),
err.fg(parser.colors().error)
))
.with_color(parser.colors().warning),
)
.finish(),
);
return reports;
}
PropertyMapError::NotFoundError(err) => {
reports.push(
Report::build(ReportKind::Error, token.source(), token.start())
.with_message("Invalid Graph Property")
.with_label(
Label::new((
token.source().clone(),
token.start() + 1..token.end(),
))
.with_message(err)
.with_color(parser.colors().warning),
)
.finish(),
);
return reports;
}
},
};
// FIXME: You can escape html, make sure we escape single "
// Property "width"
let graph_width = match properties.get("width", |_, value| -> Result<String, ()> {
Ok(value.clone())
}) {
Ok((_, kind)) => kind,
Err(e) => match e {
PropertyMapError::NotFoundError(err) => {
reports.push(
Report::build(ReportKind::Error, token.source(), token.start())
.with_message("Invalid Graph Property")
.with_label(
Label::new((
token.source().clone(),
token.start() + 1..token.end(),
))
.with_message(format!(
"Property `{}` is missing",
err.fg(parser.colors().info)
))
.with_color(parser.colors().warning),
)
.finish(),
);
return reports;
}
_ => panic!("Unknown error")
},
};
// TODO: Caption
parser.push(
document,
Box::new(Graphviz {
location: token,
dot: graph_content,
layout: graph_layout,
width: graph_width,
caption: None,
}),
);
reports
}
// TODO
fn lua_bindings<'lua>(&self, _lua: &'lua Lua) -> Vec<(String, Function<'lua>)> { vec![] }
}

17
src/elements/import.rs
View file

@ -1,7 +1,8 @@
use mlua::{Function, Lua};
use regex::{Captures, Regex};
use crate::{document::document::{DocumentAccessors, Document}, parser::{parser::{Parser, ReportColors}, rule::RegexRule, source::{Source, SourceFile, Token}}};
use regex::Regex;
use crate::parser::{parser::{Parser, ReportColors}, rule::RegexRule, source::{Source, SourceFile, Token}};
use ariadne::{Report, Fmt, Label, ReportKind};
use crate::document::document::Document;
use std::{ops::Range, rc::Rc};
use super::paragraph::Paragraph;
@ -34,8 +35,8 @@ impl RegexRule for ImportRule {
fn regexes(&self) -> &[Regex] { &self.re }
fn on_regex_match<'a>(&self, _: usize, parser: &dyn Parser, document: &'a dyn Document<'a>, token: Token, matches: Captures)
-> Vec<Report<'_, (Rc<dyn Source>, Range<usize>)>> {
fn on_regex_match(&self, _: usize, parser: &dyn Parser, document: &Document, token: Token, matches: regex::Captures) -> Vec<Report<'_, (Rc<dyn Source>, Range<usize>)>>
{
let mut result = vec![];
// Path
@ -137,11 +138,13 @@ impl RegexRule for ImportRule {
}
};
let import_doc = parser.parse(import, Some(document));
document.merge(import_doc.content(), import_doc.scope(), Some(&import_as));
// TODO
let import_doc = parser.parse(import, Some(&document));
document.merge(import_doc, Some(&import_as));
// Close paragraph
if document.last_element::<Paragraph>().is_some()
if document.last_element::<Paragraph>(false).is_some()
{
parser.push(document, Box::new(Paragraph::new(
Token::new(token.end()..token.end(), token.source())

133
src/elements/link.rs
View file

@ -1,23 +1,10 @@
use crate::compiler::compiler::Compiler;
use crate::compiler::compiler::Target;
use crate::document::document::Document;
use crate::document::element::ElemKind;
use crate::document::element::Element;
use crate::parser::parser::Parser;
use crate::parser::rule::RegexRule;
use crate::parser::source::Source;
use crate::parser::source::Token;
use crate::parser::util;
use ariadne::Fmt;
use ariadne::Label;
use ariadne::Report;
use ariadne::ReportKind;
use mlua::Function;
use mlua::Lua;
use regex::Captures;
use mlua::{Function, Lua};
use regex::Regex;
use std::ops::Range;
use std::rc::Rc;
use serde::{Deserialize, Serialize};
use crate::parser::{parser::Parser, rule::RegexRule, source::{Source, Token}, util};
use ariadne::{Report, Fmt, Label, ReportKind};
use crate::{compiler::compiler::{Compiler, Target}, document::{document::Document, element::{ElemKind, Element}}};
use std::{ops::Range, rc::Rc};
#[derive(Debug)]
pub struct Link {
@ -26,33 +13,34 @@ pub struct Link {
url: String, // Link url
}
impl Link {
impl Link
{
pub fn new(location: Token, name: String, url: String) -> Self {
Self {
location: location,
name,
url,
}
Self { location: location, name, url }
}
}
impl Element for Link {
impl Element for Link
{
fn location(&self) -> &Token { &self.location }
fn kind(&self) -> ElemKind { ElemKind::Inline }
fn element_name(&self) -> &'static str { "Link" }
fn to_string(&self) -> String { format!("{self:#?}") }
fn compile(&self, compiler: &Compiler, _document: &dyn Document) -> Result<String, String> {
match compiler.target() {
Target::HTML => Ok(format!(
"<a href=\"{}\">{}</a>",
fn compile(&self, compiler: &Compiler, _document: &Document) -> Result<String, String> {
match compiler.target()
{
Target::HTML => {
Ok(format!("<a href=\"{}\">{}</a>",
compiler.sanitize(self.url.as_str()),
compiler.sanitize(self.name.as_str()),
)),
Target::LATEX => Ok(format!(
"\\href{{{}}}{{{}}}",
))
},
Target::LATEX => {
Ok(format!("\\href{{{}}}{{{}}}",
compiler.sanitize(self.url.as_str()),
compiler.sanitize(self.name.as_str()),
)),
))
},
}
}
}
@ -63,9 +51,7 @@ pub struct LinkRule {
impl LinkRule {
pub fn new() -> Self {
Self {
re: [Regex::new(r"\[((?:\\.|[^\\\\])*?)\]\(((?:\\.|[^\\\\])*?)\)").unwrap()],
}
Self { re: [Regex::new(r"(?:^|\n)```(.*?)(?:,(.*))?\n((?:\\.|[^\[\]\\])*?)```").unwrap()] }
}
}
@ -74,98 +60,91 @@ impl RegexRule for LinkRule {
fn regexes(&self) -> &[Regex] { &self.re }
fn on_regex_match<'a>(
&self,
_: usize,
parser: &dyn Parser,
document: &'a dyn Document,
token: Token,
matches: Captures,
) -> Vec<Report<'_, (Rc<dyn Source>, Range<usize>)>> {
fn on_regex_match(&self, _: usize, parser: &dyn Parser, document: &Document, token: Token, matches: regex::Captures) -> Vec<Report<'_, (Rc<dyn Source>, Range<usize>)>>
{
let mut result = vec![];
let link_name = match matches.get(1) {
let link_name = match matches.get(1)
{
Some(name) => {
if name.as_str().is_empty() {
if name.as_str().is_empty()
{
result.push(
Report::build(ReportKind::Error, token.source(), name.start())
.with_message("Empty link name")
.with_label(
Label::new((token.source().clone(), name.range()))
.with_message("Link name is empty")
.with_color(parser.colors().error),
)
.finish(),
);
.with_color(parser.colors().error))
.finish());
return result;
}
// TODO: process into separate document...
let text_content = util::process_text(document, name.as_str());
if text_content.as_str().is_empty() {
if text_content.as_str().is_empty()
{
result.push(
Report::build(ReportKind::Error, token.source(), name.start())
.with_message("Empty link name")
.with_label(
Label::new((token.source(), name.range()))
.with_message(format!(
"Link name is empty. Once processed, `{}` yields `{}`",
.with_message(format!("Link name is empty. Once processed, `{}` yields `{}`",
name.as_str().fg(parser.colors().highlight),
text_content.as_str().fg(parser.colors().highlight),
))
.with_color(parser.colors().error),
)
.finish(),
);
.with_color(parser.colors().error))
.finish());
return result;
}
text_content
}
},
_ => panic!("Empty link name"),
};
let link_url = match matches.get(2) {
let link_url = match matches.get(2)
{
Some(url) => {
if url.as_str().is_empty() {
if url.as_str().is_empty()
{
result.push(
Report::build(ReportKind::Error, token.source(), url.start())
.with_message("Empty link url")
.with_label(
Label::new((token.source(), url.range()))
.with_message("Link url is empty")
.with_color(parser.colors().error),
)
.finish(),
);
.with_color(parser.colors().error))
.finish());
return result;
}
let text_content = util::process_text(document, url.as_str());
if text_content.as_str().is_empty() {
if text_content.as_str().is_empty()
{
result.push(
Report::build(ReportKind::Error, token.source(), url.start())
.with_message("Empty link url")
.with_label(
Label::new((token.source(), url.range()))
.with_message(format!(
"Link url is empty. Once processed, `{}` yields `{}`",
.with_message(format!("Link url is empty. Once processed, `{}` yields `{}`",
url.as_str().fg(parser.colors().highlight),
text_content.as_str().fg(parser.colors().highlight),
))
.with_color(parser.colors().error),
)
.finish(),
);
.with_color(parser.colors().error))
.finish());
return result;
}
text_content
}
},
_ => panic!("Empty link url"),
};
parser.push(
document,
Box::new(Link::new(token.clone(), link_name, link_url)),
);
parser.push(document, Box::new(
Link::new(
token.clone(),
link_name,
link_url
)
));
return result;
}

22
src/elements/list.rs
View file

@ -1,6 +1,6 @@
use std::{any::Any, cell::Ref, ops::Range, rc::Rc};
use crate::{compiler::compiler::{Compiler, Target}, document::{document::{Document, DocumentAccessors}, element::{ElemKind, Element}}, parser::{parser::Parser, rule::Rule, source::{Cursor, Source, Token, VirtualSource}}};
use crate::{compiler::compiler::{Compiler, Target}, document::{document::Document, element::{ElemKind, Element}}, parser::{parser::Parser, rule::Rule, source::{Cursor, Source, Token, VirtualSource}}};
use ariadne::{Label, Report, ReportKind};
use mlua::{Function, Lua};
use regex::Regex;
@ -57,7 +57,7 @@ impl Element for List
fn to_string(&self) -> String { format!("{self:#?}") }
fn compile(&self, compiler: &Compiler, document: &dyn Document) -> Result<String, String> {
fn compile(&self, compiler: &Compiler, document: &Document) -> Result<String, String> {
match compiler.target()
{
Target::HTML => {
@ -95,7 +95,7 @@ impl Element for List
match_stack(&mut result, &ent.numbering);
result.push_str("<li>");
match ent.content.iter().enumerate()
.try_for_each(|(_idx, elem)| {
.try_for_each(|(idx, elem)| {
match elem.compile(compiler, document) {
Err(e) => Err(e),
Ok(s) => { result.push_str(s.as_str()); Ok(()) }
@ -196,11 +196,10 @@ impl ListRule {
}
fn parse_depth(depth: &str, document: &dyn Document) -> Vec<(bool, usize)>
fn parse_depth(depth: &str, document: &Document) -> Vec<(bool, usize)>
{
let mut parsed = vec![];
// FIXME: Previous iteration used to recursively retrieve the list indent
let prev_entry = document.last_element::<List>()
let prev_entry = document.last_element::<List>(true)
.and_then(|list| Ref::filter_map(list, |m| m.entries.last() ).ok() )
.and_then(|entry| Ref::filter_map(entry, |e| Some(&e.numbering)).ok() );
@ -247,8 +246,7 @@ impl Rule for ListRule
|m| Some((m.start(), Box::new([false;0]) as Box<dyn Any>)) )
}
fn on_match<'a>(&self, parser: &dyn Parser, document: &'a dyn Document<'a>, cursor: Cursor, _match_data: Option<Box<dyn Any>>)
-> (Cursor, Vec<Report<'_, (Rc<dyn Source>, Range<usize>)>>) {
fn on_match<'a>(&self, parser: &dyn Parser, document: &'a Document<'a>, cursor: Cursor, _match_data: Option<Box<dyn Any>>) -> (Cursor, Vec<Report<'_, (Rc<dyn Source>, Range<usize>)>>) {
let mut reports = vec![];
let content = cursor.source.content();
let (end_cursor, numbering, source) = match self.start_re.captures_at(content, cursor.pos) {
@ -312,8 +310,8 @@ impl Rule for ListRule
},
};
let parsed_entry = parser.parse(Rc::new(source), Some(document));
let mut parsed_paragraph = parsed_entry.last_element_mut::<Paragraph>().unwrap(); // Extract content from paragraph
let parsed_entry = parser.parse(Rc::new(source), Some(&document));
let mut parsed_paragraph = parsed_entry.last_element_mut::<Paragraph>(false).unwrap(); // Extract content from paragraph
let entry = ListEntry::new(
Token::new(cursor.pos..end_cursor.pos, cursor.source.clone()),
numbering,
@ -321,14 +319,14 @@ impl Rule for ListRule
);
// Ger previous list, if none insert a new list
let mut list = match document.last_element_mut::<List>()
let mut list = match document.last_element_mut::<List>(false)
{
Some(last) => last,
None => {
parser.push(document,
Box::new(List::new(
Token::new(cursor.pos..end_cursor.pos, cursor.source.clone()))));
document.last_element_mut::<List>().unwrap()
document.last_element_mut::<List>(false).unwrap()
}
};
list.push(entry);

462
src/elements/media.rs
View file

@ -1,462 +0,0 @@
use std::collections::HashMap;
use std::ops::Range;
use std::rc::Rc;
use std::str::FromStr;
use ariadne::Fmt;
use ariadne::Label;
use ariadne::Report;
use ariadne::ReportKind;
use regex::Captures;
use regex::Match;
use regex::Regex;
use regex::RegexBuilder;
use crate::compiler::compiler::Compiler;
use crate::compiler::compiler::Target;
use crate::document::document::Document;
use crate::document::document::DocumentAccessors;
use crate::document::element::ElemKind;
use crate::document::element::Element;
use crate::document::references::validate_refname;
use crate::parser::parser::ReportColors;
use crate::parser::rule::RegexRule;
use crate::parser::source::Source;
use crate::parser::source::Token;
use crate::parser::source::VirtualSource;
use crate::parser::util;
use crate::parser::util::parse_paragraph;
use crate::parser::util::Property;
use crate::parser::util::PropertyMap;
use crate::parser::util::PropertyMapError;
use crate::parser::util::PropertyParser;
use super::paragraph::Paragraph;
#[derive(Debug)]
pub enum MediaType {
IMAGE,
VIDEO,
AUDIO,
}
impl FromStr for MediaType {
type Err = String;
fn from_str(s: &str) -> Result<Self, Self::Err> {
match s {
"image" => Ok(MediaType::IMAGE),
"video" => Ok(MediaType::VIDEO),
"audio" => Ok(MediaType::AUDIO),
_ => Err(format!("Unknown media type: {s}")),
}
}
}
#[derive(Debug)]
struct MediaGroup {
pub(self) location: Token,
pub(self) media: Vec<Media>,
}
impl MediaGroup {
fn push(&mut self, media: Media) -> Result<(), String> {
if self.location.source() != media.location.source() {
return Err(format!(
"Attempted to insert media from {} into MediaGroup from {}",
self.location.source(),
media.location.source()
));
}
self.location.range = self.location.start()..media.location.end();
self.media.push(media);
Ok(())
}
}
impl Element for MediaGroup {
fn location(&self) -> &Token { &self.location }
fn kind(&self) -> ElemKind { ElemKind::Block }
fn element_name(&self) -> &'static str { "Media Group" }
fn to_string(&self) -> String { format!("{self:#?}") }
fn compile(&self, compiler: &Compiler, document: &dyn Document) -> Result<String, String> {
match compiler.target() {
Target::HTML => {
let mut result = String::new();
result.push_str("<div class=\"media\">");
for medium in &self.media {
match medium.compile(compiler, document) {
Ok(r) => result.push_str(r.as_str()),
Err(e) => return Err(e),
}
}
result.push_str("</div>");
Ok(result)
}
_ => todo!(""),
}
}
}
#[derive(Debug)]
struct Media {
pub(self) location: Token,
pub(self) reference: String,
pub(self) uri: String,
pub(self) media_type: MediaType,
pub(self) width: Option<String>,
pub(self) caption: Option<String>,
pub(self) description: Option<Paragraph>,
}
impl Element for Media {
fn location(&self) -> &Token { &self.location }
fn kind(&self) -> ElemKind { ElemKind::Block }
fn element_name(&self) -> &'static str { "Media" }
fn to_string(&self) -> String { format!("{self:#?}") }
fn compile(&self, compiler: &Compiler, document: &dyn Document) -> Result<String, String> {
match compiler.target() {
Target::HTML => {
let mut result = String::new();
let width = self
.width
.as_ref()
.map_or(String::new(), |w| format!(r#" style="width:{w};""#));
result.push_str(format!(r#"<div class="medium" {width}>"#).as_str());
match self.media_type {
MediaType::IMAGE => result.push_str(
format!(r#"<a href="{0}"><img src="{0}"></a>"#, self.uri).as_str(),
),
MediaType::VIDEO => todo!(),
MediaType::AUDIO => todo!(),
}
result.push_str(format!(r#"<p class="medium-refname">{}</p>"#, "TODO").as_str());
if let Some(paragraph) = self.description.as_ref() {
match paragraph.compile(compiler, document) {
Ok(res) => result.push_str(res.as_str()),
Err(err) => return Err(err),
}
}
result.push_str("</div>");
Ok(result)
}
_ => todo!(""),
}
}
}
pub struct MediaRule {
re: [Regex; 1],
properties: PropertyParser,
}
impl MediaRule {
pub fn new() -> Self {
let mut props = HashMap::new();
props.insert(
"type".to_string(),
Property::new(
false,
"Override for the media type detection".to_string(),
None,
),
);
props.insert(
"width".to_string(),
Property::new(false, "Override for the media width".to_string(), None),
);
Self {
re: [RegexBuilder::new(
r"^!\[(.*)\]\(((?:\\.|[^\\\\])*?)\)(?:\[((?:\\.|[^\\\\])*?)\])?((?:\\(?:.|\n)|[^\\\\])*?$)?",
)
.multi_line(true)
.build()
.unwrap()],
properties: PropertyParser::new(props),
}
}
fn validate_uri(uri: &str) -> Result<&str, String> {
let trimmed = uri.trim_start().trim_end();
if trimmed.is_empty() {
return Err("URIs is empty".to_string());
}
Ok(trimmed)
}
fn parse_properties(
&self,
colors: &ReportColors,
token: &Token,
m: &Option<Match>,
) -> Result<PropertyMap, Report<'_, (Rc<dyn Source>, Range<usize>)>> {
match m {
None => match self.properties.default() {
Ok(properties) => Ok(properties),
Err(e) => Err(
Report::build(ReportKind::Error, token.source(), token.start())
.with_message("Invalid Media Properties")
.with_label(
Label::new((token.source().clone(), token.range.clone()))
.with_message(format!("Media is missing required property: {e}"))
.with_color(colors.error),
)
.finish(),
),
},
Some(props) => {
let processed =
util::process_escaped('\\', "]", props.as_str().trim_start().trim_end());
match self.properties.parse(processed.as_str()) {
Err(e) => Err(
Report::build(ReportKind::Error, token.source(), props.start())
.with_message("Invalid Media Properties")
.with_label(
Label::new((token.source().clone(), props.range()))
.with_message(e)
.with_color(colors.error),
)
.finish(),
),
Ok(properties) => Ok(properties),
}
}
}
}
fn detect_filetype(filename: &str) -> Option<MediaType> {
let sep = match filename.rfind('.') {
Some(pos) => pos,
None => return None,
};
// TODO: https://developer.mozilla.org/en-US/docs/Web/Media/Formats/Containers
match filename.split_at(sep + 1).1.to_ascii_lowercase().as_str() {
"png" | "apng" | "avif" | "gif" | "webp" | "svg" | "bmp" | "jpg" | "jpeg" | "jfif"
| "pjpeg" | "pjp" => Some(MediaType::IMAGE),
_ => None,
}
}
}
impl RegexRule for MediaRule {
fn name(&self) -> &'static str { "Media" }
fn regexes(&self) -> &[regex::Regex] { &self.re }
fn on_regex_match<'a>(
&self,
_: usize,
parser: &dyn crate::parser::parser::Parser,
document: &'a (dyn Document<'a> + 'a),
token: Token,
matches: Captures,
) -> Vec<Report<'_, (Rc<dyn Source>, Range<usize>)>> {
let mut reports = vec![];
let refname = match (
matches.get(1).unwrap(),
validate_refname(matches.get(1).unwrap().as_str()),
) {
(_, Ok(refname)) => refname.to_string(),
(m, Err(err)) => {
reports.push(
Report::build(ReportKind::Error, token.source(), m.start())
.with_message("Invalid Media Refname")
.with_label(
Label::new((token.source().clone(), m.range())).with_message(err),
)
.finish(),
);
return reports;
}
};
let uri = match (
matches.get(2).unwrap(),
MediaRule::validate_uri(matches.get(2).unwrap().as_str()),
) {
(_, Ok(uri)) => uri.to_string(),
(m, Err(err)) => {
reports.push(
Report::build(ReportKind::Error, token.source(), m.start())
.with_message("Invalid Media URI")
.with_label(
Label::new((token.source().clone(), m.range())).with_message(err),
)
.finish(),
);
return reports;
}
};
// Properties
let properties = match self.parse_properties(parser.colors(), &token, &matches.get(3)) {
Ok(pm) => pm,
Err(report) => {
reports.push(report);
return reports;
}
};
let media_type =
match Self::detect_filetype(uri.as_str()) {
Some(media_type) => media_type,
None => match properties.get("type", |prop, value| {
MediaType::from_str(value.as_str()).map_err(|e| (prop, e))
}) {
Ok((_prop, kind)) => kind,
Err(e) => match e {
PropertyMapError::ParseError((prop, err)) => {
reports.push(
Report::build(ReportKind::Error, token.source(), token.start())
.with_message("Invalid Media Property")
.with_label(
Label::new((token.source().clone(), token.range.clone()))
.with_message(format!(
"Property `type: {}` cannot be converted: {}",
prop.fg(parser.colors().info),
err.fg(parser.colors().error)
))
.with_color(parser.colors().warning),
)
.finish(),
);
return reports;
}
PropertyMapError::NotFoundError(err) => {
reports.push(
Report::build(ReportKind::Error, token.source(), token.start())
.with_message("Invalid Media Property")
.with_label(
Label::new((
token.source().clone(),
token.start() + 1..token.end(),
))
.with_message(format!("{err}. Required because mediatype could not be detected"))
.with_color(parser.colors().error),
)
.finish(),
);
return reports;
}
},
},
};
let width = properties
.get("width", |_, value| -> Result<String, ()> {
Ok(value.clone())
})
.ok()
.and_then(|(_, s)| Some(s));
let description = match matches.get(4) {
Some(content) => {
let source = Rc::new(VirtualSource::new(
Token::new(content.range(), token.source()),
format!("Media[{refname}] description"),
content.as_str().trim_start().trim_end().to_string(),
));
if source.content().is_empty() {
None
} else {
match parse_paragraph(parser, source, document) {
Ok(paragraph) => Some(*paragraph),
Err(err) => {
reports.push(
Report::build(ReportKind::Error, token.source(), content.start())
.with_message("Invalid Media Description")
.with_label(
Label::new((token.source().clone(), content.range()))
.with_message(format!(
"Could not parse description: {err}"
))
.with_color(parser.colors().error),
)
.finish(),
);
return reports;
}
}
}
}
None => panic!("Unknown error"),
};
// TODO: caption
let mut group = match document.last_element_mut::<MediaGroup>() {
Some(group) => group,
None => {
parser.push(
document,
Box::new(MediaGroup {
location: token.clone(),
media: vec![],
}),
);
document.last_element_mut::<MediaGroup>().unwrap()
}
};
if let Err(err) = group.push(Media {
location: token.clone(),
reference: refname,
uri,
media_type,
width,
caption: None,
description,
}) {
reports.push(
Report::build(ReportKind::Error, token.source(), token.start())
.with_message("Invalid Media")
.with_label(
Label::new((token.source().clone(), token.range.clone()))
.with_message(err)
.with_color(parser.colors().error),
)
.finish(),
);
}
reports
}
fn lua_bindings<'lua>(&self, _lua: &'lua mlua::Lua) -> Vec<(String, mlua::Function<'lua>)> {
vec![]
}
}
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn regex() {
let rule = MediaRule::new();
let re = &rule.regexes()[0];
assert!(re.is_match("![refname](some path...)[some properties] some description"));
assert!(re.is_match(
r"![refname](some p\)ath...\\)[some propert\]ies\\\\] some description\\nanother line"
));
assert!(re.is_match_at("![r1](uri1)[props1] desc1\n![r2](uri2)[props2] desc2", 26));
}
}

2
src/elements/mod.rs
View file

@ -11,6 +11,4 @@ pub mod section;
pub mod link;
pub mod code;
pub mod tex;
pub mod graphviz;
pub mod raw;
pub mod media;

120
src/elements/paragraph.rs
View file

@ -1,22 +1,10 @@
use std::any::Any;
use std::ops::Range;
use std::rc::Rc;
use std::{any::Any, ops::Range, rc::Rc};
use ariadne::Report;
use mlua::Function;
use mlua::Lua;
use mlua::{Function, Lua};
use regex::Regex;
use crate::compiler::compiler::Compiler;
use crate::compiler::compiler::Target;
use crate::document::document::Document;
use crate::document::element::ElemKind;
use crate::document::element::Element;
use crate::parser::parser::Parser;
use crate::parser::rule::Rule;
use crate::parser::source::Cursor;
use crate::parser::source::Source;
use crate::parser::source::Token;
use crate::{compiler::compiler::{Compiler, Target}, document::{document::Document, element::{ElemKind, Element}}, parser::{parser::Parser, rule::Rule, source::{Cursor, Source, Token}}};
// TODO: Full refactor
// Problem is that document parsed from other sources i.e by variables
@ -26,37 +14,38 @@ use crate::parser::source::Token;
// The issue is that this would break the current `Token` implementation
// Which would need to be reworked
#[derive(Debug)]
pub struct Paragraph {
pub struct Paragraph
{
location: Token,
pub content: Vec<Box<dyn Element>>,
pub content: Vec<Box<dyn Element>>
}
impl Paragraph {
impl Paragraph
{
pub fn new(location: Token) -> Self {
Self {
location,
content: Vec::new(),
}
Self { location, content: Vec::new() }
}
pub fn is_empty(&self) -> bool { self.content.is_empty() }
pub fn push(&mut self, elem: Box<dyn Element>) {
if elem.location().source() == self.location().source() {
self.location.range = self.location.start()..elem.location().end();
pub fn push(&mut self, elem: Box<dyn Element>)
{
if elem.location().source() == self.location().source()
{
self.location.range = self.location.start() .. elem.location().end();
}
self.content.push(elem);
}
pub fn find_back<P: FnMut(&&Box<dyn Element + 'static>) -> bool>(
&self,
predicate: P,
) -> Option<&Box<dyn Element>> {
self.content.iter().rev().find(predicate)
pub fn find_back<P: FnMut(&&Box<dyn Element + 'static>) -> bool>(&self, mut predicate: P)
-> Option<&Box<dyn Element>> {
self.content.iter().rev()
.find(predicate)
}
}
impl Element for Paragraph {
impl Element for Paragraph
{
fn location(&self) -> &Token { &self.location }
fn kind(&self) -> ElemKind { ElemKind::Special }
@ -65,85 +54,74 @@ impl Element for Paragraph {
fn to_string(&self) -> String { format!("{:#?}", self) }
fn compile(&self, compiler: &Compiler, document: &dyn Document) -> Result<String, String> {
if self.content.is_empty() {
return Ok(String::new());
}
fn compile(&self, compiler: &Compiler, document: &Document) -> Result<String, String> {
if self.content.is_empty() { return Ok(String::new()) }
match compiler.target() {
match compiler.target()
{
Target::HTML => {
let mut result = String::new();
//if prev.is_none() || prev.unwrap().downcast_ref::<Paragraph>().is_none()
{
result.push_str("<p>");
}
{ result.push_str("<p>"); }
//else
//{ result.push_str(" "); }
let err = self.content.iter().try_for_each(|elem| {
match elem.compile(compiler, document) {
match elem.compile(compiler, document)
{
Err(e) => return Err(e),
Ok(content) => {
result.push_str(content.as_str());
Ok(())
}
Ok(content) => { result.push_str(content.as_str()); Ok(()) },
}
});
//if next.is_none() || next.unwrap().downcast_ref::<Paragraph>().is_none()
{
result.push_str("</p>");
}
{ result.push_str("</p>"); }
match err {
match err
{
Err(e) => Err(e),
Ok(()) => Ok(result),
}
}
Target::LATEX => todo!("Unimplemented compiler"),
Target::LATEX => todo!("Unimplemented compiler")
}
}
}
pub struct ParagraphRule {
pub struct ParagraphRule
{
re: Regex,
}
impl ParagraphRule {
pub fn new() -> Self {
Self {
re: Regex::new(r"\n{2,}").unwrap(),
re: Regex::new(r"\n{2,}").unwrap()
}
}
}
impl Rule for ParagraphRule {
impl Rule for ParagraphRule
{
fn name(&self) -> &'static str { "Paragraphing" }
fn next_match(&self, cursor: &Cursor) -> Option<(usize, Box<dyn Any>)> {
self.re
.find_at(cursor.source.content(), cursor.pos)
.and_then(|m| Some((m.start(), Box::new([false; 0]) as Box<dyn Any>)))
self.re.find_at(cursor.source.content(), cursor.pos)
.and_then(|m| Some((m.start(), Box::new([false;0]) as Box<dyn Any>)) )
}
fn on_match(
&self,
parser: &dyn Parser,
document: &dyn Document,
cursor: Cursor,
_match_data: Option<Box<dyn Any>>,
) -> (Cursor, Vec<Report<'_, (Rc<dyn Source>, Range<usize>)>>) {
let end_cursor = match self.re.captures_at(cursor.source.content(), cursor.pos) {
fn on_match(&self, parser: &dyn Parser, document: &Document, cursor: Cursor, _match_data: Option<Box<dyn Any>>)
-> (Cursor, Vec<Report<'_, (Rc<dyn Source>, Range<usize>)>>) {
let end_cursor = match self.re.captures_at(cursor.source.content(), cursor.pos)
{
None => panic!("Unknown error"),
Some(capture) => cursor.at(capture.get(0).unwrap().end() - 1),
Some(capture) =>
cursor.at(capture.get(0).unwrap().end()-1)
};
parser.push(
document,
Box::new(Paragraph::new(Token::new(
cursor.pos..end_cursor.pos,
cursor.source.clone(),
))),
);
parser.push(document, Box::new(Paragraph::new(
Token::new(cursor.pos..end_cursor.pos, cursor.source.clone())
)));
(end_cursor, Vec::new())
}

221
src/elements/raw.rs
View file

@ -1,45 +1,20 @@
use crate::compiler::compiler::Compiler;
use mlua::{Function, Lua};
use regex::{Captures, Regex};
use crate::{compiler::compiler::Compiler, document::element::{ElemKind, Element}, parser::{parser::Parser, rule::RegexRule, source::{Source, Token}, util::{self, Property, PropertyParser}}};
use ariadne::{Fmt, Label, Report, ReportKind};
use crate::document::document::Document;
use crate::document::element::ElemKind;
use crate::document::element::Element;
use crate::lua::kernel::CTX;
use crate::parser::parser::Parser;
use crate::parser::rule::RegexRule;
use crate::parser::source::Source;
use crate::parser::source::Token;
use crate::parser::util::Property;
use crate::parser::util::PropertyMapError;
use crate::parser::util::PropertyParser;
use crate::parser::util::{self};
use ariadne::Fmt;
use ariadne::Label;
use ariadne::Report;
use ariadne::ReportKind;
use mlua::Error::BadArgument;
use mlua::Function;
use mlua::Lua;
use regex::Captures;
use regex::Regex;
use std::collections::HashMap;
use std::ops::Range;
use std::rc::Rc;
use std::str::FromStr;
use std::sync::Arc;
use std::{collections::HashMap, ops::Range, rc::Rc, str::FromStr};
#[derive(Debug)]
struct Raw {
pub(self) location: Token,
pub(self) kind: ElemKind,
pub(self) content: String,
location: Token,
kind: ElemKind,
content: String,
}
impl Raw {
fn new(location: Token, kind: ElemKind, content: String) -> Self {
Self {
location,
kind,
content,
}
Self { location, kind, content }
}
}
@ -51,7 +26,7 @@ impl Element for Raw {
fn to_string(&self) -> String { format!("{self:#?}") }
fn compile(&self, _compiler: &Compiler, _document: &dyn Document) -> Result<String, String> {
fn compile(&self, compiler: &Compiler, _document: &Document) -> Result<String, String> {
Ok(self.content.clone())
}
}
@ -64,40 +39,32 @@ pub struct RawRule {
impl RawRule {
pub fn new() -> Self {
let mut props = HashMap::new();
props.insert(
"kind".to_string(),
props.insert("kind".to_string(),
Property::new(
true,
"Element display kind".to_string(),
Some("inline".to_string()),
),
);
Some("inline".to_string())));
Self {
re: [
Regex::new(r"\{\?(?:\[((?:\\.|[^\[\]\\])*?)\])?(?:((?:\\.|[^\\\\])*?)(\?\}))?")
.unwrap(),
Regex::new(r"\{\?(?:\[((?:\\.|[^\[\]\\])*?)\])?(?:((?:\\.|[^\\\\])*?)(\?\}))?").unwrap()
],
properties: PropertyParser::new(props),
properties: PropertyParser::new(props)
}
}
}
impl RegexRule for RawRule {
impl RegexRule for RawRule
{
fn name(&self) -> &'static str { "Raw" }
fn regexes(&self) -> &[regex::Regex] { &self.re }
fn on_regex_match(
&self,
_index: usize,
parser: &dyn Parser,
document: &dyn Document,
token: Token,
matches: Captures,
) -> Vec<Report<'_, (Rc<dyn Source>, Range<usize>)>> {
fn on_regex_match(&self, _index: usize, parser: &dyn Parser, document: &Document, token: Token, matches: Captures)
-> Vec<Report<'_, (Rc<dyn Source>, Range<usize>)>> {
let mut reports = vec![];
let raw_content = match matches.get(2) {
let raw_content = match matches.get(2)
{
// Unterminated
None => {
reports.push(
@ -105,38 +72,34 @@ impl RegexRule for RawRule {
.with_message("Unterminated Raw Code")
.with_label(
Label::new((token.source().clone(), token.range.clone()))
.with_message(format!(
"Missing terminating `{}` after first `{}`",
.with_message(format!("Missing terminating `{}` after first `{}`",
"?}".fg(parser.colors().info),
"{?".fg(parser.colors().info)
))
.with_color(parser.colors().error),
)
.finish(),
);
"{?".fg(parser.colors().info)))
.with_color(parser.colors().error))
.finish());
return reports;
}
Some(content) => {
let processed =
util::process_escaped('\\', "?}", content.as_str().trim_start().trim_end());
let processed = util::process_escaped('\\', "?}",
content.as_str().trim_start().trim_end());
if processed.is_empty() {
if processed.is_empty()
{
reports.push(
Report::build(ReportKind::Warning, token.source(), content.start())
.with_message("Empty Raw Code")
.with_label(
Label::new((token.source().clone(), content.range()))
.with_message("Raw code is empty")
.with_color(parser.colors().warning),
)
.finish(),
);
.with_color(parser.colors().warning))
.finish());
}
processed
}
};
let properties = match matches.get(1) {
let properties = match matches.get(1)
{
None => match self.properties.default() {
Ok(properties) => properties,
Err(e) => {
@ -146,17 +109,16 @@ impl RegexRule for RawRule {
.with_label(
Label::new((token.source().clone(), token.range.clone()))
.with_message(format!("Raw code is missing properties: {e}"))
.with_color(parser.colors().error),
)
.finish(),
);
.with_color(parser.colors().error))
.finish());
return reports;
}
},
}
Some(props) => {
let processed =
util::process_escaped('\\', "]", props.as_str().trim_start().trim_end());
match self.properties.parse(processed.as_str()) {
let processed = util::process_escaped('\\', "]",
props.as_str().trim_start().trim_end());
match self.properties.parse(processed.as_str())
{
Err(e) => {
reports.push(
Report::build(ReportKind::Error, token.source(), props.start())
@ -164,112 +126,43 @@ impl RegexRule for RawRule {
.with_label(
Label::new((token.source().clone(), props.range()))
.with_message(e)
.with_color(parser.colors().error),
)
.finish(),
);
.with_color(parser.colors().error))
.finish());
return reports;
}
Ok(properties) => properties,
Ok(properties) => properties
}
}
};
let raw_kind: ElemKind = match properties.get("kind", |prop, value| {
ElemKind::from_str(value.as_str()).map_err(|e| (prop, e))
}) {
let raw_kind : ElemKind = match properties.get("kind",
|prop, value| ElemKind::from_str(value.as_str()).map_err(|e| (prop, e)))
{
Ok((_prop, kind)) => kind,
Err(e) => match e {
PropertyMapError::ParseError((prop, err)) => {
Err((prop, e)) => {
reports.push(
Report::build(ReportKind::Error, token.source(), token.start())
.with_message("Invalid Raw Code Property")
.with_label(
Label::new((token.source().clone(), token.range.clone()))
.with_message(format!(
"Property `kind: {}` cannot be converted: {}",
.with_message(format!("Property `kind: {}` cannot be converted: {}",
prop.fg(parser.colors().info),
err.fg(parser.colors().error)
))
.with_color(parser.colors().warning),
)
.finish(),
);
e.fg(parser.colors().error)))
.with_color(parser.colors().warning))
.finish());
return reports;
}
PropertyMapError::NotFoundError(err) => {
reports.push(
Report::build(ReportKind::Error, token.source(), token.start())
.with_message("Invalid Code Property")
.with_label(
Label::new((
token.source().clone(),
token.start() + 1..token.end(),
))
.with_message(format!(
"Property `{}` is missing",
err.fg(parser.colors().info)
))
.with_color(parser.colors().warning),
)
.finish(),
);
return reports;
}
},
};
parser.push(
document,
Box::new(Raw {
location: token.clone(),
kind: raw_kind,
content: raw_content,
}),
);
parser.push(document, Box::new(Raw::new(
token.clone(),
raw_kind,
raw_content
)));
reports
}
fn lua_bindings<'lua>(&self, lua: &'lua Lua) -> Vec<(String, Function<'lua>)> {
let mut bindings = vec![];
bindings.push((
"push".to_string(),
lua.create_function(|_, (kind, content): (String, String)| {
// Validate kind
let kind = match ElemKind::from_str(kind.as_str()) {
Ok(kind) => kind,
Err(e) => {
return Err(BadArgument {
to: Some("push".to_string()),
pos: 1,
name: Some("kind".to_string()),
cause: Arc::new(mlua::Error::external(format!(
"Wrong section kind specified: {e}"
))),
})
}
};
CTX.with_borrow(|ctx| {
ctx.as_ref().map(|ctx| {
ctx.parser.push(
ctx.document,
Box::new(Raw {
location: ctx.location.clone(),
kind,
content,
}),
);
})
});
Ok(())
})
.unwrap(),
));
bindings
}
// TODO
fn lua_bindings<'lua>(&self, _lua: &'lua Lua) -> Vec<(String, Function<'lua>)> { vec![] }
}

51
src/elements/registrar.rs
View file

@ -1,38 +1,23 @@
use crate::parser::parser::Parser;
use super::code::CodeRule;
use super::comment::CommentRule;
use super::graphviz::GraphRule;
use super::import::ImportRule;
use super::link::LinkRule;
use super::list::ListRule;
use super::media::MediaRule;
use super::paragraph::ParagraphRule;
use super::raw::RawRule;
use super::script::ScriptRule;
use super::section::SectionRule;
use super::style::StyleRule;
use super::tex::TexRule;
use super::text::TextRule;
use super::variable::VariableRule;
use super::variable::VariableSubstitutionRule;
use super::{code::CodeRule, comment::CommentRule, import::ImportRule, link::LinkRule, list::ListRule, paragraph::ParagraphRule, raw::RawRule, script::ScriptRule, section::SectionRule, style::StyleRule, tex::TexRule, text::TextRule, variable::{VariableRule, VariableSubstitutionRule}};
pub fn register<P: Parser>(parser: &mut P) {
parser.add_rule(Box::new(CommentRule::new()), None).unwrap();
parser.add_rule(Box::new(ParagraphRule::new()), None).unwrap();
parser.add_rule(Box::new(ImportRule::new()), None).unwrap();
parser.add_rule(Box::new(ScriptRule::new()), None).unwrap();
parser.add_rule(Box::new(VariableRule::new()), None).unwrap();
parser.add_rule(Box::new(VariableSubstitutionRule::new()), None).unwrap();
parser.add_rule(Box::new(RawRule::new()), None).unwrap();
parser.add_rule(Box::new(ListRule::new()), None).unwrap();
parser.add_rule(Box::new(CodeRule::new()), None).unwrap();
parser.add_rule(Box::new(TexRule::new()), None).unwrap();
parser.add_rule(Box::new(GraphRule::new()), None).unwrap();
parser.add_rule(Box::new(MediaRule::new()), None).unwrap();
parser.add_rule(Box::new(StyleRule::new()), None).unwrap();
parser.add_rule(Box::new(SectionRule::new()), None).unwrap();
parser.add_rule(Box::new(LinkRule::new()), None).unwrap();
parser.add_rule(Box::new(TextRule::default()), None).unwrap();
pub fn register<P: Parser>(parser: &mut P)
{
parser.add_rule(Box::new(CommentRule::new()), None);
parser.add_rule(Box::new(ParagraphRule::new()), None);
parser.add_rule(Box::new(ImportRule::new()), None);
parser.add_rule(Box::new(ScriptRule::new()), None);
parser.add_rule(Box::new(VariableRule::new()), None);
parser.add_rule(Box::new(VariableSubstitutionRule::new()), None);
parser.add_rule(Box::new(RawRule::new()), None);
parser.add_rule(Box::new(ListRule::new()), None);
parser.add_rule(Box::new(CodeRule::new()), None);
parser.add_rule(Box::new(TexRule::new()), None);
parser.add_rule(Box::new(StyleRule::new()), None);
parser.add_rule(Box::new(SectionRule::new()), None);
parser.add_rule(Box::new(LinkRule::new()), None);
parser.add_rule(Box::new(TextRule::default()), None);
}

234
src/elements/script.rs
View file

@ -1,29 +1,16 @@
use mlua::{Function, Lua};
use regex::{Captures, Regex};
use crate::{lua::kernel::{Kernel, KernelContext, KernelHolder}, parser::{parser::{Parser, ReportColors}, rule::RegexRule, source::{Source, Token, VirtualSource}, util}};
use ariadne::{Fmt, Label, Report, ReportKind};
use crate::document::document::Document;
use crate::lua::kernel::Kernel;
use crate::lua::kernel::KernelContext;
use crate::parser::parser::Parser;
use crate::parser::parser::ReportColors;
use crate::parser::rule::RegexRule;
use crate::parser::source::Source;
use crate::parser::source::Token;
use crate::parser::source::VirtualSource;
use crate::parser::util;
use ariadne::Fmt;
use ariadne::Label;
use ariadne::Report;
use ariadne::ReportKind;
use mlua::Function;
use mlua::Lua;
use regex::Captures;
use regex::Regex;
use std::ops::Range;
use std::rc::Rc;
use std::{ops::Range, rc::Rc};
use super::text::Text;
pub struct ScriptRule {
pub struct ScriptRule
{
re: [Regex; 2],
eval_kinds: [(&'static str, &'static str); 3],
eval_kinds: [(&'static str, &'static str); 3]
}
impl ScriptRule {
@ -31,69 +18,57 @@ impl ScriptRule {
Self {
re: [
Regex::new(r"(?:^|\n)@<(?:(.*)\n?)((?:\\.|[^\\\\])*?)(?:\n?)>@").unwrap(),
Regex::new(r"%<(?:\[(.*?)\])?([^\s[:alpha:]])?((?:\\.|[^\\\\])*?)(?:\n?)>%")
.unwrap(),
Regex::new(r"%<([^\s[:alpha:]])?(?:\[(.*?)\])?((?:\\.|[^\\\\])*?)(?:\n?)>%").unwrap()
],
eval_kinds: [
("", "Eval"),
("\"", "Eval to text"),
("!", "Eval and parse"),
],
]
}
}
fn validate_kernel_name(colors: &ReportColors, name: &str) -> Result<String, String> {
fn validate_kernel_name(colors: &ReportColors, name: &str)
-> Result<String, String> {
let trimmed = name.trim_end().trim_start();
if trimmed.is_empty() {
return Ok("main".to_string());
} else if trimmed.find(|c: char| c.is_whitespace()).is_some() {
return Err(format!(
"Kernel name `{}` contains whitespaces",
trimmed.fg(colors.highlight)
));
if trimmed.is_empty() { return Ok("main".to_string()) }
else if trimmed.find(|c: char| c.is_whitespace()).is_some() {
return Err(format!("Kernel name `{}` contains whitespaces",
trimmed.fg(colors.highlight)))
}
Ok(trimmed.to_string())
}
fn validate_kind(&self, colors: &ReportColors, kind: &str) -> Result<usize, String> {
match self
.eval_kinds
.iter()
.position(|(kind_symbol, _)| kind == *kind_symbol)
fn validate_kind(&self, colors: &ReportColors, kind: &str)
-> Result<usize, String> {
match self.eval_kinds.iter().position(|(kind_symbol, _)| kind == *kind_symbol)
{
Some(id) => Ok(id),
None => Err(format!(
"Unable to find eval kind `{}`. Available kinds:{}",
None => Err(format!("Unable to find eval kind `{}`. Available kinds:{}",
kind.fg(colors.highlight),
self.eval_kinds
.iter()
.fold(String::new(), |out, (symbol, name)| {
self.eval_kinds.iter().fold(String::new(), |out, (symbol, name)| {
out + format!("\n - '{symbol}' => {name}").as_str()
})
)),
})))
}
}
}
impl RegexRule for ScriptRule {
impl RegexRule for ScriptRule
{
fn name(&self) -> &'static str { "Script" }
fn regexes(&self) -> &[regex::Regex] { &self.re }
fn on_regex_match<'a>(
&self,
index: usize,
parser: &dyn Parser,
document: &'a dyn Document<'a>,
token: Token,
matches: Captures,
) -> Vec<Report<'_, (Rc<dyn Source>, Range<usize>)>> {
fn on_regex_match(&self, index: usize, parser: &dyn Parser, document: &Document, token: Token, matches: Captures)
-> Vec<Report<'_, (Rc<dyn Source>, Range<usize>)>> {
let mut reports = vec![];
let kernel_name = match matches.get(1) {
let kernel_name = match matches.get(if index == 0 {1} else {2}) {
None => "main".to_string(),
Some(name) => match ScriptRule::validate_kernel_name(parser.colors(), name.as_str()) {
Some(name) => {
match ScriptRule::validate_kernel_name(parser.colors(), name.as_str())
{
Ok(name) => name,
Err(e) => {
reports.push(
@ -102,83 +77,77 @@ impl RegexRule for ScriptRule {
.with_label(
Label::new((token.source(), name.range()))
.with_message(e)
.with_color(parser.colors().error),
)
.finish(),
);
.with_color(parser.colors().error))
.finish());
return reports;
}
},
}
}
};
let kernel = parser
.get_kernel(kernel_name.as_str())
.unwrap_or_else(|| parser.insert_kernel(kernel_name.to_string(), Kernel::new(parser)));
let kernel_name = matches.get(if index == 0 {1} else {2})
.and_then(|name| {
let trimmed = name.as_str().trim_start().trim_end();
(!trimmed.is_empty()).then_some(trimmed)
})
.unwrap_or("main");
let kernel = parser.get_kernel(kernel_name).unwrap_or_else(|| {
parser.insert_kernel(kernel_name.to_string(), Kernel::new(parser))
});
let kernel_data = matches
.get(if index == 0 { 2 } else { 3 })
let kernel_data = matches.get(if index == 0 {2} else {3})
.and_then(|code| {
let trimmed = code.as_str().trim_start().trim_end();
(!trimmed.is_empty()).then_some((trimmed, code.range()))
})
.or_else(|| {
}).or_else(|| {
reports.push(
Report::build(ReportKind::Warning, token.source(), token.start())
.with_message("Invalid kernel code")
.with_label(
Label::new((token.source(), token.start() + 1..token.end()))
Label::new((token.source(), token.start()+1..token.end()))
.with_message("Kernel code is empty")
.with_color(parser.colors().warning),
)
.finish(),
);
.with_color(parser.colors().warning))
.finish());
None
});
if kernel_data.is_none() {
return reports;
}
if kernel_data.is_none() { return reports; }
let (kernel_content, kernel_range) = kernel_data.unwrap();
let source = Rc::new(VirtualSource::new(
Token::new(kernel_range, token.source()),
format!(
"{}#{}:lua_kernel@{kernel_name}",
token.source().name(),
matches.get(0).unwrap().start()
),
util::process_escaped('\\', ">@", kernel_content),
format!("{}#{}:lua_kernel@{kernel_name}", token.source().name(), matches.get(0).unwrap().start()),
util::process_escaped('\\', ">@", kernel_content)
)) as Rc<dyn Source>;
let execute = |lua: &Lua| {
let chunk = lua.load(source.content()).set_name(kernel_name);
if index == 0
// Exec
let execute = |lua: &Lua|
{
let chunk = lua.load(source.content())
.set_name(kernel_name);
if index == 0 // Exec
{
if let Err(e) = chunk.exec()
{
if let Err(e) = chunk.exec() {
reports.push(
Report::build(ReportKind::Error, source.clone(), 0)
.with_message("Invalid kernel code")
.with_label(
Label::new((source.clone(), 0..source.content().len()))
.with_message(format!(
"Kernel execution failed:\n{}",
e.to_string()
))
.with_color(parser.colors().error),
)
.finish(),
);
.with_message(format!("Kernel execution failed:\n{}", e.to_string()))
.with_color(parser.colors().error))
.finish());
return reports;
}
} else
// Eval
}
else // Eval
{
// Validate kind
let kind = match matches.get(2) {
let kind = match matches.get(1) {
None => 0,
Some(kind) => match self.validate_kind(parser.colors(), kind.as_str()) {
Some(kind) => {
match self.validate_kind(parser.colors(), kind.as_str())
{
Ok(kind) => kind,
Err(msg) => {
reports.push(
@ -187,76 +156,63 @@ impl RegexRule for ScriptRule {
.with_label(
Label::new((token.source(), kind.range()))
.with_message(msg)
.with_color(parser.colors().error),
)
.finish(),
);
.with_color(parser.colors().error))
.finish());
return reports;
}
},
}
}
};
if kind == 0
// Eval
if kind == 0 // Eval
{
if let Err(e) = chunk.eval::<()>()
{
if let Err(e) = chunk.eval::<()>() {
reports.push(
Report::build(ReportKind::Error, source.clone(), 0)
.with_message("Invalid kernel code")
.with_label(
Label::new((source.clone(), 0..source.content().len()))
.with_message(format!(
"Kernel evaluation failed:\n{}",
e.to_string()
))
.with_color(parser.colors().error),
)
.finish(),
);
.with_message(format!("Kernel evaluation failed:\n{}", e.to_string()))
.with_color(parser.colors().error))
.finish());
}
} else
// Eval to string
}
else // Eval to string
{
match chunk.eval::<String>()
{
match chunk.eval::<String>() {
Ok(result) => {
if kind == 1
// Eval to text
if kind == 1 // Eval to text
{
if !result.is_empty() {
parser.push(
document,
Box::new(Text::new(
if !result.is_empty()
{
parser.push(document, Box::new(Text::new(
Token::new(1..source.content().len(), source.clone()),
util::process_text(document, result.as_str()),
)),
);
)));
}
} else if kind == 2
// Eval and Parse
}
else if kind == 2 // Eval and Parse
{
let parse_source = Rc::new(VirtualSource::new(
Token::new(0..source.content().len(), source.clone()),
format!("parse({})", source.name()),
result,
result
)) as Rc<dyn Source>;
parser.parse_into(parse_source, document);
}
}
},
Err(e) => {
reports.push(
Report::build(ReportKind::Error, source.clone(), 0)
.with_message("Invalid kernel code")
.with_label(
Label::new((source.clone(), 0..source.content().len()))
.with_message(format!(
"Kernel evaluation failed:\n{}",
e.to_string()
))
.with_color(parser.colors().error),
)
.finish(),
);
.with_message(format!("Kernel evaluation failed:\n{}", e.to_string()))
.with_color(parser.colors().error))
.finish());
}
}
}
@ -268,7 +224,7 @@ impl RegexRule for ScriptRule {
let ctx = KernelContext {
location: Token::new(0..source.content().len(), source.clone()),
parser,
document,
document
};
kernel.run_with_context(ctx, execute)

10
src/elements/section.rs
View file

@ -1,8 +1,8 @@
use mlua::{Error::BadArgument, Function, Lua};
use regex::Regex;
use crate::{compiler::compiler::Target, document::document::Document, lua::kernel::CTX, parser::{parser::Parser, rule::RegexRule, source::{Source, Token}}};
use crate::{compiler::compiler::Target, lua::kernel::CTX, parser::{parser::Parser, rule::RegexRule, source::{Source, Token}}};
use ariadne::{Report, Fmt, Label, ReportKind};
use crate::{compiler::compiler::Compiler, document::element::{ElemKind, Element, ReferenceableElement}};
use crate::{compiler::compiler::Compiler, document::{document::Document, element::{ElemKind, Element, ReferenceableElement}}};
use std::{ops::Range, rc::Rc, sync::Arc};
#[derive(Debug)]
@ -21,7 +21,7 @@ impl Element for Section
fn element_name(&self) -> &'static str { "Section" }
fn to_string(&self) -> String { format!("{self:#?}") }
fn as_referenceable(&self) -> Option<&dyn ReferenceableElement> { Some(self) }
fn compile(&self, compiler: &Compiler, _document: &dyn Document) -> Result<String, String> {
fn compile(&self, compiler: &Compiler, _document: &Document) -> Result<String, String> {
match compiler.target()
{
Target::HTML => {
@ -61,7 +61,7 @@ impl RegexRule for SectionRule {
fn regexes(&self) -> &[Regex] { &self.re }
fn on_regex_match(&self, _: usize, parser: &dyn Parser, document: &dyn Document, token: Token, matches: regex::Captures) -> Vec<Report<'_, (Rc<dyn Source>, Range<usize>)>>
fn on_regex_match(&self, _: usize, parser: &dyn Parser, document: &Document, token: Token, matches: regex::Captures) -> Vec<Report<'_, (Rc<dyn Source>, Range<usize>)>>
{
let mut result = vec![];
let section_depth = match matches.get(1)
@ -89,7 +89,6 @@ impl RegexRule for SectionRule {
// [Optional] Reference name
let section_refname = matches.get(2).map_or_else(|| None,
|refname| {
/* TODO: Wait for reference rework
// Check for duplicate reference
if let Some((ref_doc, reference)) = document.get_reference(refname.as_str())
{
@ -113,7 +112,6 @@ impl RegexRule for SectionRule {
.with_note(format!("Previous reference was overwritten"))
.finish());
}
*/
Some(refname.as_str().to_string())
});

11
src/elements/style.rs
View file

@ -1,7 +1,8 @@
use mlua::{Function, Lua};
use regex::{Captures, Regex};
use crate::{compiler::compiler::{Compiler, Target}, document::{document::{DocumentAccessors, Document}, element::{ElemKind, Element}}, parser::{parser::Parser, rule::RegexRule, source::{Source, Token}, state::State}};
use crate::{compiler::compiler::{Compiler, Target}, document::element::{ElemKind, Element}, parser::{parser::Parser, rule::RegexRule, source::{Source, Token}, state::State}};
use ariadne::{Fmt, Label, Report, ReportKind};
use crate::document::document::Document;
use crate::parser::state::Scope;
use std::{cell::RefCell, ops::Range, rc::Rc};
use lazy_static::lazy_static;
@ -28,7 +29,7 @@ impl Element for Style
fn kind(&self) -> ElemKind { ElemKind::Inline }
fn element_name(&self) -> &'static str { "Section" }
fn to_string(&self) -> String { format!("{self:#?}") }
fn compile(&self, compiler: &Compiler, _document: &dyn Document) -> Result<String, String> {
fn compile(&self, compiler: &Compiler, _document: &Document) -> Result<String, String> {
match compiler.target()
{
Target::HTML => {
@ -65,7 +66,7 @@ impl State for StyleState
{
fn scope(&self) -> Scope { Scope::PARAGRAPH }
fn on_remove<'a>(&self, parser: &dyn Parser, document: &dyn Document) -> Vec<Report<'a, (Rc<dyn Source>, Range<usize>)>> {
fn on_remove<'a>(&self, parser: &dyn Parser, document: &Document) -> Vec<Report<'a, (Rc<dyn Source>, Range<usize>)>> {
let mut result = Vec::new();
self.toggled
.iter()
@ -79,7 +80,7 @@ impl State for StyleState
//let active_range = range.start .. paragraph.location().end()-1;
let paragraph = document.last_element::<Paragraph>().unwrap();
let paragraph = document.last_element::<Paragraph>(false).unwrap();
let paragraph_end = paragraph.content.last()
.and_then(|last| Some((last.location().source(), last.location().end()-1 .. last.location().end())))
.unwrap();
@ -144,7 +145,7 @@ impl RegexRule for StyleRule
fn regexes(&self) -> &[regex::Regex] { &self.re }
fn on_regex_match(&self, index: usize, parser: &dyn Parser, document: &dyn Document, token: Token, _matches: Captures) -> Vec<Report<(Rc<dyn Source>, Range<usize>)>> {
fn on_regex_match(&self, index: usize, parser: &dyn Parser, document: &Document, token: Token, _matches: Captures) -> Vec<Report<(Rc<dyn Source>, Range<usize>)>> {
let result = vec![];
let query = parser.state().query(&STATE_NAME);

254
src/elements/tex.rs
View file

@ -1,52 +1,32 @@
use std::io::Read;
use std::io::Write;
use std::ops::Range;
use std::process::Command;
use std::process::Stdio;
use std::rc::Rc;
use std::sync::Once;
use std::{io::{Read, Write}, ops::Range, process::{Command, Stdio}, rc::Rc, sync::Once};
use ariadne::Fmt;
use ariadne::Label;
use ariadne::Report;
use ariadne::ReportKind;
use crypto::digest::Digest;
use crypto::sha2::Sha512;
use mlua::Function;
use mlua::Lua;
use regex::Captures;
use regex::Regex;
use ariadne::{Fmt, Label, Report, ReportKind};
use crypto::{digest::Digest, sha2::Sha512};
use mlua::{Function, Lua};
use regex::{Captures, Regex};
use crate::cache::cache::Cached;
use crate::cache::cache::CachedError;
use crate::compiler::compiler::Compiler;
use crate::compiler::compiler::Target;
use crate::document::document::Document;
use crate::document::element::ElemKind;
use crate::document::element::Element;
use crate::parser::parser::Parser;
use crate::parser::rule::RegexRule;
use crate::parser::source::Source;
use crate::parser::source::Token;
use crate::parser::util;
use crate::{cache::cache::{Cached, CachedError}, compiler::compiler::{Compiler, Target}, document::{document::Document, element::{ElemKind, Element}}, parser::{parser::Parser, rule::RegexRule, source::{Source, Token}, util}};
#[derive(Debug, PartialEq, Eq)]
enum TexKind {
enum TexKind
{
Block,
Inline,
}
impl From<&TexKind> for ElemKind {
impl From<&TexKind> for ElemKind
{
fn from(value: &TexKind) -> Self {
match value {
TexKind::Inline => ElemKind::Inline,
_ => ElemKind::Block,
_ => ElemKind::Block
}
}
}
#[derive(Debug)]
struct Tex {
struct Tex
{
location: Token,
block: TexKind,
env: String,
@ -55,59 +35,49 @@ struct Tex {
}
impl Tex {
fn new(
location: Token,
block: TexKind,
env: String,
tex: String,
caption: Option<String>,
) -> Self {
Self {
location,
block,
env,
tex,
caption,
}
fn new(location: Token, block: TexKind, env: String, tex: String, caption: Option<String>) -> Self {
Self { location, block, env, tex, caption }
}
fn format_latex(fontsize: &String, preamble: &String, tex: &String) -> FormattedTex {
FormattedTex(format!(
r"\documentclass[{}pt,preview]{{standalone}}
fn format_latex(fontsize: &String, preamble: &String, tex: &String) -> FormattedTex
{
FormattedTex(format!(r"\documentclass[{}pt,preview]{{standalone}}
{}
\begin{{document}}
\begin{{preview}}
{}
\end{{preview}}
\end{{document}}",
fontsize, preamble, tex
))
fontsize, preamble, tex))
}
}
struct FormattedTex(String);
impl FormattedTex {
impl FormattedTex
{
/// Renders latex to svg
fn latex_to_svg(&self, exec: &String, fontsize: &String) -> Result<String, String> {
fn latex_to_svg(&self, exec: &String, fontsize: &String) -> Result<String, String>
{
print!("Rendering LaTex `{}`... ", self.0);
let process = match Command::new(exec)
.arg("--fontsize")
.arg(fontsize)
.arg("--fontsize").arg(fontsize)
.stdout(Stdio::piped())
.stdin(Stdio::piped())
.spawn()
{
Err(e) => return Err(format!("Could not spawn `{exec}`: {}", e)),
Ok(process) => process,
Ok(process) => process
};
if let Err(e) = process.stdin.unwrap().write_all(self.0.as_bytes()) {
if let Err(e) = process.stdin.unwrap().write_all(self.0.as_bytes())
{
panic!("Unable to write to `latex2svg`'s stdin: {}", e);
}
let mut result = String::new();
match process.stdout.unwrap().read_to_string(&mut result) {
match process.stdout.unwrap().read_to_string(&mut result)
{
Err(e) => panic!("Unable to read `latex2svg` stdout: {}", e),
Ok(_) => {}
}
@ -117,7 +87,8 @@ impl FormattedTex {
}
}
impl Cached for FormattedTex {
impl Cached for FormattedTex
{
type Key = String;
type Value = String;
@ -144,74 +115,71 @@ impl Cached for FormattedTex {
}
impl Element for Tex {
fn location(&self) -> &Token {
&self.location
}
fn location(&self) -> &Token { &self.location }
fn kind(&self) -> ElemKind {
(&self.block).into()
}
fn kind(&self) -> ElemKind { (&self.block).into() }
fn element_name(&self) -> &'static str {
"LaTeX"
}
fn element_name(&self) -> &'static str { "LaTeX" }
fn to_string(&self) -> String {
format!("{self:#?}")
}
fn to_string(&self) -> String { format!("{self:#?}") }
fn compile(&self, compiler: &Compiler, document: &Document)
-> Result<String, String> {
fn compile(&self, compiler: &Compiler, document: &dyn Document) -> Result<String, String> {
match compiler.target() {
Target::HTML => {
static CACHE_INIT: Once = Once::new();
CACHE_INIT.call_once(|| {
if let Some(mut con) = compiler.cache() {
if let Err(e) = FormattedTex::init(&mut con) {
static CACHE_INIT : Once = Once::new();
CACHE_INIT.call_once(|| if let Some(mut con) = compiler.cache() {
if let Err(e) = FormattedTex::init(&mut con)
{
eprintln!("Unable to create cache table: {e}");
}
}
});
let exec = document
.get_variable(format!("tex.{}.exec", self.env).as_str())
.map_or("latex2svg".to_string(), |var| var.to_string());
let exec = document.get_variable(format!("tex.{}.exec", self.env))
.map_or("latex2svg".to_string(), |(_, var)| var.to_string());
// FIXME: Because fontsize is passed as an arg, verify that it cannot be used to execute python/shell code
let fontsize = document
.get_variable(format!("tex.{}.fontsize", self.env).as_str())
.map_or("12".to_string(), |var| var.to_string());
let preamble = document
.get_variable(format!("tex.{}.preamble", self.env).as_str())
.map_or("".to_string(), |var| var.to_string());
let prepend = if self.block == TexKind::Inline {
"".to_string()
} else {
document
.get_variable(format!("tex.{}.block_prepend", self.env).as_str())
.map_or("".to_string(), |var| var.to_string() + "\n")
let fontsize = document.get_variable(format!("tex.{}.fontsize", self.env))
.map_or("12".to_string(), |(_, var)| var.to_string());
let preamble = document.get_variable(format!("tex.{}.preamble", self.env))
.map_or("".to_string(), |(_, var)| var.to_string());
let prepend = if self.block == TexKind::Inline { "".to_string() }
else
{
document.get_variable(format!("tex.{}.block_prepend", self.env))
.map_or("".to_string(), |(_, var)| var.to_string()+"\n")
};
let latex = match self.block {
TexKind::Inline => {
Tex::format_latex(&fontsize, &preamble, &format!("${{{}}}$", self.tex))
}
_ => Tex::format_latex(&fontsize, &preamble, &format!("{prepend}{}", self.tex)),
let latex = match self.block
{
TexKind::Inline => Tex::format_latex(
&fontsize,
&preamble,
&format!("${{{}}}$", self.tex)),
_ => Tex::format_latex(
&fontsize,
&preamble,
&format!("{prepend}{}", self.tex))
};
if let Some(mut con) = compiler.cache() {
match latex.cached(&mut con, |s| s.latex_to_svg(&exec, &fontsize)) {
if let Some(mut con) = compiler.cache()
{
match latex.cached(&mut con, |s| s.latex_to_svg(&exec, &fontsize))
{
Ok(s) => Ok(s),
Err(e) => match e {
CachedError::SqlErr(e) => {
Err(format!("Querying the cache failed: {e}"))
Err(e) => match e
{
CachedError::SqlErr(e) => Err(format!("Querying the cache failed: {e}")),
CachedError::GenErr(e) => Err(e)
}
CachedError::GenErr(e) => Err(e),
},
}
} else {
}
else
{
latex.latex_to_svg(&exec, &fontsize)
}
}
_ => todo!("Unimplemented"),
_ => todo!("Unimplemented")
}
}
}
@ -231,32 +199,23 @@ impl TexRule {
}
}
impl RegexRule for TexRule {
fn name(&self) -> &'static str {
"Tex"
}
impl RegexRule for TexRule
{
fn name(&self) -> &'static str { "Tex" }
fn regexes(&self) -> &[regex::Regex] {
&self.re
}
fn regexes(&self) -> &[regex::Regex] { &self.re }
fn on_regex_match(
&self,
index: usize,
parser: &dyn Parser,
document: &dyn Document,
token: Token,
matches: Captures,
) -> Vec<Report<'_, (Rc<dyn Source>, Range<usize>)>> {
fn on_regex_match(&self, index: usize, parser: &dyn Parser, document: &Document, token: Token, matches: Captures)
-> Vec<Report<'_, (Rc<dyn Source>, Range<usize>)>> {
let mut reports = vec![];
let tex_env = matches
.get(1)
let tex_env = matches.get(1)
.and_then(|env| Some(env.as_str().trim_start().trim_end()))
.and_then(|env| (!env.is_empty()).then_some(env))
.unwrap_or("main");
let tex_content = match matches.get(2) {
let tex_content = match matches.get(2)
{
// Unterminated `$`
None => {
reports.push(
@ -264,35 +223,27 @@ impl RegexRule for TexRule {
.with_message("Unterminated Tex Code")
.with_label(
Label::new((token.source().clone(), token.range.clone()))
.with_message(format!(
"Missing terminating `{}` after first `{}`",
.with_message(format!("Missing terminating `{}` after first `{}`",
["|$", "$"][index].fg(parser.colors().info),
["$|", "$"][index].fg(parser.colors().info)
))
.with_color(parser.colors().error),
)
.finish(),
);
["$|", "$"][index].fg(parser.colors().info)))
.with_color(parser.colors().error))
.finish());
return reports;
}
Some(content) => {
let processed = util::process_escaped(
'\\',
["|$", "$"][index],
content.as_str().trim_start().trim_end(),
);
let processed = util::process_escaped('\\', ["|$", "$"][index],
content.as_str().trim_start().trim_end());
if processed.is_empty() {
if processed.is_empty()
{
reports.push(
Report::build(ReportKind::Warning, token.source(), content.start())
.with_message("Empty Tex Code")
.with_label(
Label::new((token.source().clone(), content.range()))
.with_message("Tex code is empty")
.with_color(parser.colors().warning),
)
.finish(),
);
.with_color(parser.colors().warning))
.finish());
}
processed
}
@ -300,26 +251,17 @@ impl RegexRule for TexRule {
// TODO: Caption
parser.push(
document,
Box::new(Tex::new(
parser.push(document, Box::new(Tex::new(
token,
if index == 1 {
TexKind::Inline
} else {
TexKind::Block
},
if index == 1 { TexKind::Inline } else { TexKind::Block },
tex_env.to_string(),
tex_content,
None,
)),
);
)));
reports
}
// TODO
fn lua_bindings<'lua>(&self, _lua: &'lua Lua) -> Vec<(String, Function<'lua>)> {
vec![]
}
fn lua_bindings<'lua>(&self, _lua: &'lua Lua) -> Vec<(String, Function<'lua>)> { vec![] }
}

73
src/elements/text.rs
View file

@ -1,44 +1,33 @@
use std::any::Any;
use std::ops::Range;
use std::rc::Rc;
use mlua::{Function, Lua};
use ariadne::Report;
use mlua::Function;
use mlua::Lua;
use crate::compiler::compiler::Compiler;
use crate::document::document::Document;
use crate::document::element::ElemKind;
use crate::document::element::Element;
use crate::lua::kernel::CTX;
use crate::parser::parser::Parser;
use crate::parser::rule::Rule;
use crate::parser::source::Cursor;
use crate::parser::source::Source;
use crate::parser::source::Token;
use crate::{compiler::compiler::Compiler, document::{document::Document, element::{ElemKind, Element}}, lua::kernel::CTX, parser::{rule::Rule, source::Token}};
#[derive(Debug)]
pub struct Text {
pub struct Text
{
pub(self) location: Token,
pub(self) content: String,
}
impl Text {
pub fn new(location: Token, content: String) -> Text {
impl Text
{
pub fn new(location: Token, content: String) -> Text
{
Text {
location: location,
content: content,
content: content
}
}
}
impl Element for Text {
impl Element for Text
{
fn location(&self) -> &Token { &self.location }
fn kind(&self) -> ElemKind { ElemKind::Inline }
fn element_name(&self) -> &'static str { "Text" }
fn to_string(&self) -> String { format!("{self:#?}") }
fn compile(&self, compiler: &Compiler, _document: &dyn Document) -> Result<String, String> {
fn compile(&self, compiler: &Compiler, _document: &Document) -> Result<String, String> {
Ok(compiler.sanitize(self.content.as_str()))
}
}
@ -46,42 +35,28 @@ impl Element for Text {
#[derive(Default)]
pub struct TextRule;
impl Rule for TextRule {
impl Rule for TextRule
{
fn name(&self) -> &'static str { "Text" }
fn next_match(&self, _cursor: &Cursor) -> Option<(usize, Box<dyn Any>)> { None }
fn next_match(&self, cursor: &crate::parser::source::Cursor) -> Option<(usize, Box<dyn std::any::Any>)> { None }
fn on_match(
&self,
_parser: &dyn Parser,
_document: &dyn Document,
_cursor: Cursor,
_match_data: Option<Box<dyn Any>>,
) -> (Cursor, Vec<Report<'_, (Rc<dyn Source>, Range<usize>)>>) {
panic!("Text cannot match");
}
fn on_match(&self, parser: &dyn crate::parser::parser::Parser, document: &crate::document::document::Document, cursor: crate::parser::source::Cursor, match_data: Option<Box<dyn std::any::Any>>) -> (crate::parser::source::Cursor, Vec<ariadne::Report<'_, (std::rc::Rc<dyn crate::parser::source::Source>, std::ops::Range<usize>)>>) { panic!("Text canno match"); }
fn lua_bindings<'lua>(&self, lua: &'lua Lua) -> Vec<(String, Function<'lua>)> {
let mut bindings = vec![];
bindings.push((
"push".to_string(),
lua.create_function(|_, content: String| {
CTX.with_borrow(|ctx| {
ctx.as_ref().map(|ctx| {
ctx.parser.push(
ctx.document,
Box::new(Text {
bindings.push(("push".to_string(), lua.create_function(
|_, content: String| {
CTX.with_borrow(|ctx| ctx.as_ref().map(|ctx| {
ctx.parser.push(ctx.document, Box::new(Text {
location: ctx.location.clone(),
content,
}),
);
})
});
}));
}));
Ok(())
})
.unwrap(),
));
}).unwrap()));
bindings
}

24
src/elements/variable.rs
View file

@ -1,8 +1,8 @@
use mlua::{Function, Lua};
use regex::Regex;
use crate::{document::document::Document, parser::{parser::{Parser, ReportColors}, rule::RegexRule, source::{Source, Token}}};
use crate::parser::{parser::{Parser, ReportColors}, rule::RegexRule, source::{Source, Token}};
use ariadne::{Report, Fmt, Label, ReportKind};
use crate::document::variable::{BaseVariable, PathVariable, Variable};
use crate::document::{document::Document, variable::{BaseVariable, PathVariable, Variable}};
use std::{ops::Range, rc::Rc};
pub struct VariableRule {
@ -91,7 +91,7 @@ impl RegexRule for VariableRule {
fn on_regex_match<'a>(&self, _: usize, parser: &dyn Parser, document: &'a dyn Document, token: Token, matches: regex::Captures) -> Vec<Report<'_, (Rc<dyn Source>, Range<usize>)>>
fn on_regex_match(&self, _: usize, parser: &dyn Parser, document: &Document, token: Token, matches: regex::Captures) -> Vec<Report<'_, (Rc<dyn Source>, Range<usize>)>>
{
let mut result = vec![];
// [Optional] variable kind
@ -223,7 +223,7 @@ impl RegexRule for VariableSubstitutionRule
fn regexes(&self) -> &[regex::Regex] { &self.re }
fn on_regex_match<'a>(&self, _index: usize, parser: &dyn Parser, document: &'a dyn Document<'a>, token: Token, matches: regex::Captures) -> Vec<Report<'_, (Rc<dyn Source>, Range<usize>)>> {
fn on_regex_match(&self, _index: usize, parser: &dyn Parser, document: &Document, token: Token, matches: regex::Captures) -> Vec<Report<'_, (Rc<dyn Source>, Range<usize>)>> {
let mut result = vec![];
let variable = match matches.get(1)
@ -307,13 +307,27 @@ impl RegexRule for VariableSubstitutionRule
.finish());
return result;
}
Some(var) => var,
Some((_, var)) => var,
}
},
_ => panic!("Unknown error")
};
variable.parse(token, parser, document);
//let parsed = variable.parse(
// token,
// parser,
// document
//);
////document.merge(parsed, None);
//parsed.content.borrow_mut()
// .drain(..)
// .for_each(|elem| parser.push(document, elem));
//parser.push(document, )
// TODO: Full rework of document
// parser shound parse into previous document, and not into a new document
// This should prevent having to sue `recurse: bool` in the last_element getters
return result;
}

76
src/lsp/parser.rs
View file

@ -1,6 +1,6 @@
use std::{cell::{RefCell, RefMut}, collections::HashMap, rc::Rc};
use std::rc::Rc;
use crate::{document::{document::Document, element::Element}, lua::kernel::{Kernel, KernelHolder}, parser::{parser::{Parser, ReportColors}, rule::Rule, source::{Cursor, Source}, state::StateHolder}};
use crate::parser::source::{Cursor, Source};
#[derive(Debug, Clone)]
pub struct LineCursor
@ -56,6 +56,26 @@ impl LineCursor
//eprintln!("({}, {c:#?}) ({} {})", self.pos, self.line, self.line_pos);
prev = Some(c);
}
/*
self.source.content()
.as_str()[start..pos+1]
.char_indices()
.for_each(|(at, c)| {
self.pos = at+start;
if c == '\n'
{
self.line += 1;
self.line_pos = 0;
}
else
{
self.line_pos += c.len_utf8();
}
});
*/
}
else if pos < self.pos
{
@ -94,55 +114,3 @@ impl From<&LineCursor> for Cursor
}
}
}
#[derive(Debug)]
pub struct LsParser
{
rules: Vec<Box<dyn Rule>>,
colors: ReportColors,
// Parser state
pub state: RefCell<StateHolder>,
pub kernels: RefCell<HashMap<String, Kernel>>,
}
impl Parser for LsParser
{
fn colors(&self) -> &ReportColors { &self.colors }
fn rules(&self) -> &Vec<Box<dyn Rule>> { &self.rules }
fn rules_mut(&mut self) -> &mut Vec<Box<dyn Rule>> { &mut self.rules }
fn state(&self) -> std::cell::Ref<'_, StateHolder> { self.state.borrow() }
fn state_mut(&self) -> std::cell::RefMut<'_, StateHolder> { self.state.borrow_mut() }
fn has_error(&self) -> bool { true }
fn push<'a>(&self, doc: &dyn Document, elem: Box<dyn Element>) {
todo!()
}
fn parse<'a>(&self, source: Rc<dyn Source>, parent: Option<&'a dyn Document<'a>>) -> Box<dyn Document<'a>+'a> {
todo!()
}
fn parse_into<'a>(&self, source: Rc<dyn Source>, document: &'a dyn Document<'a>) {
todo!()
}
}
impl KernelHolder for LsParser
{
fn get_kernel(&self, name: &str)
-> Option<RefMut<'_, Kernel>> {
RefMut::filter_map(self.kernels.borrow_mut(),
|map| map.get_mut(name)).ok()
}
fn insert_kernel(&self, name: String, kernel: Kernel)
-> RefMut<'_, Kernel> {
//TODO do not get
self.kernels.borrow_mut()
.insert(name.clone(), kernel);
self.get_kernel(name.as_str()).unwrap()
}
}

44
src/lsp/semantic.rs
View file

@ -59,7 +59,7 @@ pub fn provide(semantic_tokens: &mut Vec<SemanticToken>, cursor: &mut LineCursor
}
}
pub fn semantic_token_from_document(document: &dyn Document) -> Vec<SemanticToken>
pub fn semantic_token_from_document(document: &Document) -> Vec<SemanticToken>
{
let mut semantic_tokens = vec![];
@ -71,36 +71,20 @@ pub fn semantic_token_from_document(document: &dyn Document) -> Vec<SemanticToke
source: source.clone()
};
semantic_tokens.push(SemanticToken {
delta_line: 1,
delta_start: 1,
length: 5,
token_type: 0,
token_modifiers_bitset: 0,
document.content.borrow()
.iter()
.for_each(|elem| {
if let Some(paragraph) = elem.downcast_ref::<Paragraph>()
{
paragraph.content
.iter()
.for_each(|elem| provide(&mut semantic_tokens, &mut cursor, elem));
}
else
{
provide(&mut semantic_tokens, &mut cursor, elem);
}
});
semantic_tokens.push(SemanticToken {
delta_line: 1,
delta_start: 1,
length: 5,
token_type: 1,
token_modifiers_bitset: 0,
});
//document.content.borrow()
// .iter()
// .for_each(|elem| {
// if let Some(paragraph) = elem.downcast_ref::<Paragraph>()
// {
// paragraph.content
// .iter()
// .for_each(|elem| provide(&mut semantic_tokens, &mut cursor, elem));
// }
// else
// {
// provide(&mut semantic_tokens, &mut cursor, elem);
// }
// });
semantic_tokens
}

11
src/lua/kernel.rs
View file

@ -1,19 +1,19 @@
use std::cell::{RefCell, RefMut};
use std::{cell::{RefCell, RefMut}, rc::Rc};
use mlua::Lua;
use mlua::{Error, FromLua, Lua, UserData, UserDataMethods};
use crate::{document::document::Document, parser::{parser::Parser, source::Token}};
pub struct KernelContext<'a, 'b>
pub struct KernelContext<'a>
{
pub location: Token,
pub parser: &'a dyn Parser,
pub document: &'b dyn Document<'b>,
pub document: &'a Document<'a>,
//pub parser: &'a dyn Parser,
}
thread_local! {
pub static CTX: RefCell<Option<KernelContext<'static, 'static>>> = RefCell::new(None);
pub static CTX: RefCell<Option<KernelContext<'static>>> = RefCell::new(None);
}
#[derive(Debug)]
@ -23,6 +23,7 @@ pub struct Kernel
}
impl Kernel {
// TODO: Take parser as arg and
// iterate over the rules
// to find export the bindings (if some)

72
src/main.rs
View file

@ -1,18 +1,16 @@
#![feature(char_indices_offset)]
mod cache;
mod compiler;
mod document;
mod compiler;
mod parser;
mod elements;
mod lua;
mod parser;
mod cache;
use std::env;
use std::rc::Rc;
use std::{env, rc::Rc};
use compiler::compiler::Compiler;
use getopts::Options;
use parser::langparser::LangParser;
use parser::parser::Parser;
use parser::{langparser::LangParser, parser::Parser};
use crate::parser::source::SourceFile;
extern crate getopts;
@ -22,9 +20,9 @@ fn print_usage(program: &str, opts: Options) {
print!("{}", opts.usage(&brief));
}
fn print_version() {
print!(
"NML -- Not a Markup Language
fn print_version()
{
print!("NML -- Not a Markup Language
Copyright (c) 2024
NML is licensed under the GNU Affero General Public License version 3 (AGPLv3),
under the terms of the Free Software Foundation <https://www.gnu.org/licenses/agpl-3.0.en.html>.
@ -32,8 +30,7 @@ under the terms of the Free Software Foundation <https://www.gnu.org/licenses/ag
This program is free software; you may modify and redistribute it.
There is NO WARRANTY, to the extent permitted by law.
NML version: 0.4\n"
);
NML version: 0.4\n");
}
fn main() {
@ -48,12 +45,11 @@ fn main() {
opts.optflag("v", "version", "Print program version and licenses");
let matches = match opts.parse(&args[1..]) {
Ok(m) => m,
Err(f) => {
panic!("{}", f.to_string())
}
Ok(m) => { m }
Err(f) => { panic!("{}", f.to_string()) }
};
if matches.opt_present("v") {
if matches.opt_present("v")
{
print_version();
return;
}
@ -76,41 +72,39 @@ fn main() {
let source = SourceFile::new(input.to_string(), None).unwrap();
let doc = parser.parse(Rc::new(source), None);
if debug_opts.contains(&"ast".to_string()) {
if debug_opts.contains(&"ast".to_string())
{
println!("-- BEGIN AST DEBUGGING --");
doc.content()
.borrow()
.iter()
.for_each(|elem| println!("{}", (elem).to_string()));
doc.content.borrow().iter().for_each(|elem| {
println!("{}", (elem).to_string())
});
println!("-- END AST DEBUGGING --");
}
// TODO
//if debug_opts.contains(&"ref".to_string())
//{
// println!("-- BEGIN REFERENCES DEBUGGING --");
// let sc = doc.scope.borrow();
// sc.referenceable.iter().for_each(|(name, pos)| {
// println!(" - {name}: `{:#?}`", doc.content.borrow()[*pos]);
// });
// println!("-- END REFERENCES DEBUGGING --");
//}
if debug_opts.contains(&"var".to_string()) {
if debug_opts.contains(&"ref".to_string())
{
println!("-- BEGIN REFERENCES DEBUGGING --");
let sc = doc.scope.borrow();
sc.referenceable.iter().for_each(|(name, pos)| {
println!(" - {name}: `{:#?}`", doc.content.borrow()[*pos]);
});
println!("-- END REFERENCES DEBUGGING --");
}
if debug_opts.contains(&"var".to_string())
{
println!("-- BEGIN VARIABLES DEBUGGING --");
let sc = doc.scope().borrow();
let sc = doc.scope.borrow();
sc.variables.iter().for_each(|(_name, var)| {
println!(" - `{:#?}`", var);
});
println!("-- END VARIABLES DEBUGGING --");
}
if parser.has_error() {
println!("Compilation aborted due to errors while parsing");
return;
}
let compiler = Compiler::new(compiler::compiler::Target::HTML, db_path);
let out = compiler.compile(doc.as_ref());
let out = compiler.compile(&doc);
std::fs::write("a.html", out).unwrap();
}

268
src/parser/langparser.rs
View file

@ -1,38 +1,15 @@
use std::cell::RefCell;
use std::cell::RefMut;
use std::collections::HashMap;
use std::collections::HashSet;
use std::ops::Range;
use std::rc::Rc;
use std::{cell::{RefCell, RefMut}, collections::{HashMap, HashSet}, ops::Range, rc::Rc};
use ariadne::Label;
use ariadne::Report;
use ariadne::{Label, Report};
use crate::document::document::Document;
use crate::document::document::DocumentAccessors;
use crate::document::element::ElemKind;
use crate::document::element::Element;
use crate::document::langdocument::LangDocument;
use crate::elements::paragraph::Paragraph;
use crate::elements::registrar::register;
use crate::elements::text::Text;
use crate::lua::kernel::Kernel;
use crate::lua::kernel::KernelHolder;
use crate::parser::source::SourceFile;
use crate::parser::source::VirtualSource;
use crate::{document::{document::Document, element::{ElemKind, Element}}, elements::{paragraph::Paragraph, registrar::register, text::Text}, lua::kernel::{Kernel, KernelHolder}, parser::source::{SourceFile, VirtualSource}};
use super::parser::Parser;
use super::parser::ReportColors;
use super::rule::Rule;
use super::source::Cursor;
use super::source::Source;
use super::source::Token;
use super::state::StateHolder;
use super::util;
use super::{parser::{Parser, ReportColors}, rule::Rule, source::{Cursor, Source, Token}, state::StateHolder, util};
/// Parser for the language
#[derive(Debug)]
pub struct LangParser {
pub struct LangParser
{
rules: Vec<Box<dyn Rule>>,
colors: ReportColors,
@ -42,8 +19,10 @@ pub struct LangParser {
pub kernels: RefCell<HashMap<String, Kernel>>,
}
impl LangParser {
pub fn default() -> Self {
impl LangParser
{
pub fn default() -> Self
{
let mut s = Self {
rules: vec![],
colors: ReportColors::with_colors(),
@ -53,25 +32,24 @@ impl LangParser {
};
register(&mut s);
s.kernels
.borrow_mut()
s.kernels.borrow_mut()
.insert("main".to_string(), Kernel::new(&s));
s
}
fn handle_reports<'a>(
&self,
_source: Rc<dyn Source>,
reports: Vec<Report<'a, (Rc<dyn Source>, Range<usize>)>>,
) {
for mut report in reports {
fn handle_reports<'a>(&self, _source: Rc<dyn Source>, reports: Vec<Report<'a, (Rc<dyn Source>, Range<usize>)>>)
{
for mut report in reports
{
let mut sources: HashSet<Rc<dyn Source>> = HashSet::new();
fn recurse_source(sources: &mut HashSet<Rc<dyn Source>>, source: Rc<dyn Source>) {
sources.insert(source.clone());
match source.location() {
match source.location()
{
Some(parent) => {
let parent_source = parent.source();
if sources.get(&parent_source).is_none() {
if sources.get(&parent_source).is_none()
{
recurse_source(sources, parent_source);
}
}
@ -83,31 +61,32 @@ impl LangParser {
recurse_source(&mut sources, label.span.0.clone());
});
let cache = sources
.iter()
let cache = sources.iter()
.map(|source| (source.clone(), source.content().clone()))
.collect::<Vec<(Rc<dyn Source>, String)>>();
cache.iter().for_each(|(source, _)| {
if let Some(location) = source.location() {
if let Some(_s) = source.downcast_ref::<SourceFile>() {
cache.iter()
.for_each(|(source, _)| {
if let Some (location) = source.location()
{
if let Some(_s) = source.downcast_ref::<SourceFile>()
{
report.labels.push(
Label::new((location.source(), location.start() + 1..location.end()))
Label::new((location.source(), location.start()+1 .. location.end()))
.with_message("In file included from here")
.with_order(-1),
.with_order(-1)
);
};
if let Some(_s) = source.downcast_ref::<VirtualSource>() {
let start = location.start()
+ (location.source().content().as_bytes()[location.start()]
== '\n' as u8)
if let Some(_s) = source.downcast_ref::<VirtualSource>()
{
let start = location.start() + (location.source().content().as_bytes()[location.start()] == '\n' as u8)
.then_some(1)
.unwrap_or(0);
report.labels.push(
Label::new((location.source(), start..location.end()))
Label::new((location.source(), start .. location.end()))
.with_message("In evaluation of")
.with_order(-1),
.with_order(-1)
);
};
}
@ -117,59 +96,71 @@ impl LangParser {
}
}
impl Parser for LangParser {
fn colors(&self) -> &ReportColors {
&self.colors
impl Parser for LangParser
{
fn colors(&self) -> &ReportColors { &self.colors }
fn rules(&self) -> &Vec<Box<dyn Rule>> { &self.rules }
fn add_rule(&mut self, rule: Box<dyn Rule>, after: Option<&'static str>)
{
// Error on duplicate rule
let rule_name = (*rule).name();
self.rules.iter().for_each(|rule| {
if (*rule).name() != rule_name { return; }
panic!("Attempted to introduce duplicate rule: `{rule_name}`");
});
match after
{
Some(name) => {
let before = self.rules.iter()
.enumerate()
.find(|(_pos, r)| (r).name() == name);
match before
{
Some((pos, _)) => self.rules.insert(pos+1, rule),
_ => panic!("Unable to find rule named `{name}`, to insert rule `{}` after it", rule.name())
}
}
_ => self.rules.push(rule)
}
}
fn rules(&self) -> &Vec<Box<dyn Rule>> {
&self.rules
}
fn rules_mut(&mut self) -> &mut Vec<Box<dyn Rule>> {
&mut self.rules
}
fn state(&self) -> std::cell::Ref<'_, StateHolder> {
self.state.borrow()
}
fn state_mut(&self) -> std::cell::RefMut<'_, StateHolder> {
self.state.borrow_mut()
}
fn has_error(&self) -> bool { *self.err_flag.borrow() }
fn state(&self) -> std::cell::Ref<'_, StateHolder> { self.state.borrow() }
fn state_mut(&self) -> std::cell::RefMut<'_, StateHolder> { self.state.borrow_mut() }
/// Add an [`Element`] to the [`Document`]
fn push<'a>(&self, doc: &dyn Document, elem: Box<dyn Element>) {
if elem.kind() == ElemKind::Inline || elem.kind() == ElemKind::Invisible {
let mut paragraph = doc
.last_element_mut::<Paragraph>()
fn push<'a>(&self, doc: &'a Document<'a>, elem: Box<dyn Element>)
{
if elem.kind() == ElemKind::Inline || elem.kind() == ElemKind::Invisible
{
let mut paragraph = doc.last_element_mut::<Paragraph>(false)
.or_else(|| {
doc.push(Box::new(Paragraph::new(elem.location().clone())));
doc.last_element_mut::<Paragraph>()
})
.unwrap();
doc.last_element_mut::<Paragraph>(false)
}).unwrap();
paragraph.push(elem);
} else {
}
else
{
// Process paragraph events
if doc.last_element::<Paragraph>().is_some_and(|_| true) {
self.handle_reports(
doc.source(),
self.state_mut()
.on_scope_end(self, doc, super::state::Scope::PARAGRAPH),
);
if doc.last_element_mut::<Paragraph>(false)
.is_some_and(|_| true)
{
self.handle_reports(doc.source(),
self.state_mut().on_scope_end(self, &doc, super::state::Scope::PARAGRAPH));
}
doc.push(elem);
}
}
fn parse<'a>(
&self,
source: Rc<dyn Source>,
parent: Option<&'a dyn Document<'a>>,
) -> Box<dyn Document<'a> + 'a> {
let doc = LangDocument::new(source.clone(), parent);
fn parse<'a>(&self, source: Rc<dyn Source>, parent: Option<&'a Document<'a>>) -> Document<'a>
{
let doc = Document::new(source.clone(), parent);
let mut matches = Vec::new();
for _ in 0..self.rules.len() {
matches.push((0usize, None));
@ -178,59 +169,52 @@ impl Parser for LangParser {
let content = source.content();
let mut cursor = Cursor::new(0usize, doc.source()); // Cursor in file
if let Some(parent) = parent
// Terminate parent's paragraph state
if parent.is_some() // Terminate parent's paragraph state
{
self.handle_reports(
parent.source(),
self.state_mut()
.on_scope_end(self, parent, super::state::Scope::PARAGRAPH),
);
self.handle_reports(parent.as_ref().unwrap().source(),
self.state_mut().on_scope_end(self, parent.as_ref().unwrap(), super::state::Scope::PARAGRAPH));
}
loop {
loop
{
let (rule_pos, rule, match_data) = self.update_matches(&cursor, &mut matches);
// Unmatched content
let text_content =
util::process_text(&doc, &content.as_str()[cursor.pos..rule_pos.pos]);
if !text_content.is_empty() {
self.push(
&doc,
Box::new(Text::new(
let text_content = util::process_text(&doc, &content.as_str()[cursor.pos..rule_pos.pos]);
if !text_content.is_empty()
{
self.push(&doc, Box::new(Text::new(
Token::new(cursor.pos..rule_pos.pos, source.clone()),
text_content,
)),
);
text_content
)));
}
if let Some(rule) = rule {
if let Some(rule) = rule
{
// Rule callback
let dd: &'a dyn Document = unsafe { std::mem::transmute(&doc as &dyn Document) };
let (new_cursor, reports) = rule.on_match(self, dd, rule_pos, match_data);
let (new_cursor, reports) = (*rule).on_match(self, &doc, rule_pos, match_data);
self.handle_reports(doc.source(), reports);
// Advance
cursor = new_cursor;
} else
// No rules left
}
else // No rules left
{
break;
}
}
// State
self.handle_reports(
doc.source(),
self.state_mut()
.on_scope_end(self, &doc, super::state::Scope::DOCUMENT),
);
self.handle_reports(doc.source(),
self.state_mut().on_scope_end(self, &doc, super::state::Scope::DOCUMENT));
return Box::new(doc);
return doc;
}
fn parse_into<'a>(&self, source: Rc<dyn Source>, document: &'a dyn Document<'a>) {
fn parse_into<'a>(&self, source: Rc<dyn Source>, document: &'a Document<'a>)
{
let mut matches = Vec::new();
for _ in 0..self.rules.len() {
matches.push((0usize, None));
@ -239,32 +223,31 @@ impl Parser for LangParser {
let content = source.content();
let mut cursor = Cursor::new(0usize, source.clone());
loop {
loop
{
let (rule_pos, rule, match_data) = self.update_matches(&cursor, &mut matches);
// Unmatched content
let text_content =
util::process_text(document, &content.as_str()[cursor.pos..rule_pos.pos]);
if !text_content.is_empty() {
self.push(
document,
Box::new(Text::new(
let text_content = util::process_text(&document, &content.as_str()[cursor.pos..rule_pos.pos]);
if !text_content.is_empty()
{
self.push(&document, Box::new(Text::new(
Token::new(cursor.pos..rule_pos.pos, source.clone()),
text_content,
)),
);
text_content
)));
}
if let Some(rule) = rule {
if let Some(rule) = rule
{
// Rule callback
let (new_cursor, reports) = (*rule).on_match(self, document, rule_pos, match_data);
let (new_cursor, reports) = (*rule).on_match(self, &document, rule_pos, match_data);
self.handle_reports(document.source(), reports);
// Advance
cursor = new_cursor;
} else
// No rules left
}
else // No rules left
{
break;
}
@ -278,14 +261,19 @@ impl Parser for LangParser {
}
}
impl KernelHolder for LangParser {
fn get_kernel(&self, name: &str) -> Option<RefMut<'_, Kernel>> {
RefMut::filter_map(self.kernels.borrow_mut(), |map| map.get_mut(name)).ok()
impl KernelHolder for LangParser
{
fn get_kernel(&self, name: &str)
-> Option<RefMut<'_, Kernel>> {
RefMut::filter_map(self.kernels.borrow_mut(),
|map| map.get_mut(name)).ok()
}
fn insert_kernel(&self, name: String, kernel: Kernel) -> RefMut<'_, Kernel> {
fn insert_kernel(&self, name: String, kernel: Kernel)
-> RefMut<'_, Kernel> {
//TODO do not get
self.kernels.borrow_mut().insert(name.clone(), kernel);
self.kernels.borrow_mut()
.insert(name.clone(), kernel);
self.get_kernel(name.as_str()).unwrap()
}
}

6
src/parser/mod.rs
View file

@ -1,6 +1,6 @@
pub mod langparser;
pub mod parser;
pub mod rule;
pub mod source;
pub mod parser;
pub mod langparser;
pub mod rule;
pub mod state;
pub mod util;

126
src/parser/parser.rs
View file

@ -1,20 +1,19 @@
use std::any::Any;
use std::cell::Ref;
use std::cell::RefMut;
use std::cell::{Ref, RefMut};
use std::rc::Rc;
use unicode_segmentation::UnicodeSegmentation;
use super::rule::Rule;
use super::source::Cursor;
use super::source::Source;
use super::source::{Cursor, Source};
use super::state::StateHolder;
use crate::document::document::Document;
use crate::document::element::Element;
use crate::lua::kernel::KernelHolder;
use ariadne::Color;
use crate::lua::kernel::KernelHolder;
#[derive(Debug)]
pub struct ReportColors {
pub struct ReportColors
{
pub error: Color,
pub warning: Color,
pub info: Color,
@ -41,102 +40,56 @@ impl ReportColors {
}
}
pub trait Parser: KernelHolder {
pub trait Parser: KernelHolder
{
/// Gets the colors for formatting errors
///
/// When colors are disabled, all colors should resolve to empty string
fn colors(&self) -> &ReportColors;
fn rules(&self) -> &Vec<Box<dyn Rule>>;
fn rules_mut(&mut self) -> &mut Vec<Box<dyn Rule>>;
fn add_rule(&mut self, rule: Box<dyn Rule>, after: Option<&'static str>) -> Result<(), String> {
// Error on duplicate rule
let rule_name = (*rule).name();
if let Err(e) = self.rules().iter().try_for_each(|rule| {
if (*rule).name() != rule_name {
return Ok(());
}
return Err(format!(
"Attempted to introduce duplicate rule: `{rule_name}`"
));
}) {
return Err(e);
}
match after {
Some(name) => {
let before = self
.rules()
.iter()
.enumerate()
.find(|(_pos, r)| (r).name() == name);
match before {
Some((pos, _)) => self.rules_mut().insert(pos + 1, rule),
_ => {
return Err(format!(
"Unable to find rule named `{name}`, to insert rule `{}` after it",
rule.name()
))
}
}
}
_ => self.rules_mut().push(rule),
}
Ok(())
}
fn add_rule(&mut self, rule: Box<dyn Rule>, after: Option<&'static str>);
fn state(&self) -> Ref<'_, StateHolder>;
fn state_mut(&self) -> RefMut<'_, StateHolder>;
fn has_error(&self) -> bool;
// Update [`matches`] and returns the position of the next matched rule.
// If rule is empty, it means that there are no rules left to parse (i.e
// end of document).
fn update_matches(
&self,
cursor: &Cursor,
matches: &mut Vec<(usize, Option<Box<dyn Any>>)>,
) -> (Cursor, Option<&Box<dyn Rule>>, Option<Box<dyn Any>>) {
fn update_matches(&self, cursor: &Cursor, matches: &mut Vec<(usize, Option<Box<dyn Any>>)>)
-> (Cursor, Option<&Box<dyn Rule>>, Option<Box<dyn Any>>)
{
// Update matches
// TODO: Trivially parellalizable
self.rules()
.iter()
.zip(matches.iter_mut())
.for_each(|(rule, (matched_at, match_data))| {
self.rules().iter().zip(matches.iter_mut()).for_each(
|(rule, (matched_at, match_data))| {
// Don't upate if not stepped over yet
if *matched_at > cursor.pos {
return;
}
if *matched_at > cursor.pos { return }
(*matched_at, *match_data) = match rule.next_match(cursor) {
(*matched_at, *match_data) = match rule.next_match(cursor)
{
None => (usize::MAX, None),
Some((mut pos, mut data)) => {
Some((mut pos, mut data)) =>
{
// Check if escaped
while pos != usize::MAX {
while pos != usize::MAX
{
let content = cursor.source.content().as_str();
let mut graphemes = content[0..pos].graphemes(true);
let mut graphemes = content[0 .. pos].graphemes(true);
let mut escaped = false;
'inner: loop {
'inner: loop
{
let g = graphemes.next_back();
if !g.is_some() || g.unwrap() != "\\" {
break 'inner;
}
if !g.is_some() || g.unwrap() != "\\" { break 'inner; }
escaped = !escaped;
}
if !escaped {
break;
}
if !escaped { break; }
// Find next potential match
(pos, data) = match rule.next_match(&cursor.at(pos + 1)) {
(pos, data) = match rule.next_match(&cursor.at(pos+1)) {
Some((new_pos, new_data)) => (new_pos, new_data),
None => (usize::MAX, data), // Stop iterating
None => (usize::MAX, data) // Stop iterating
}
}
@ -146,36 +99,27 @@ pub trait Parser: KernelHolder {
});
// Get winning match
let (winner, (next_pos, _match_data)) = matches
.iter()
let (winner, (next_pos, _match_data)) = matches.iter()
.enumerate()
.min_by_key(|(_, (pos, _match_data))| pos)
.unwrap();
if *next_pos == usize::MAX
// No rule has matched
.min_by_key(|(_, (pos, _match_data))| pos).unwrap();
if *next_pos == usize::MAX // No rule has matched
{
let content = cursor.source.content();
// No winners, i.e no matches left
return (cursor.at(content.len()), None, None);
}
(
cursor.at(*next_pos),
(cursor.at(*next_pos),
Some(&self.rules()[winner]),
std::mem::replace(&mut matches[winner].1, None),
)
std::mem::replace(&mut matches[winner].1, None))
}
/// Add an [`Element`] to the [`Document`]
fn push<'a>(&self, doc: &dyn Document, elem: Box<dyn Element>);
fn push<'a>(&self, doc: &'a Document<'a>, elem: Box<dyn Element>);
/// Parse [`Source`] into a new [`Document`]
fn parse<'a>(
&self,
source: Rc<dyn Source>,
parent: Option<&'a dyn Document<'a>>,
) -> Box<dyn Document<'a> + 'a>;
fn parse<'a>(&self, source: Rc<dyn Source>, parent: Option<&'a Document<'a>>) -> Document<'a>;
/// Parse [`Source`] into an already existing [`Document`]
fn parse_into<'a>(&self, source: Rc<dyn Source>, document: &'a dyn Document<'a>);
fn parse_into<'a>(&self, source: Rc<dyn Source>, document: &'a Document<'a>);
}

79
src/parser/rule.rs
View file

@ -1,11 +1,8 @@
use super::parser::Parser;
use super::source::Cursor;
use super::source::Source;
use super::source::Token;
use crate::document::document::Document;
use super::source::{Cursor, Source, Token};
use ariadne::Report;
use mlua::Function;
use mlua::Lua;
use mlua::{Function, Lua};
use crate::document::document::Document;
use std::any::Any;
use std::ops::Range;
@ -17,18 +14,13 @@ pub trait Rule {
/// Finds the next match starting from [`cursor`]
fn next_match(&self, cursor: &Cursor) -> Option<(usize, Box<dyn Any>)>;
/// Callback when rule matches
fn on_match<'a>(
&self,
parser: &dyn Parser,
document: &'a (dyn Document<'a> + 'a),
cursor: Cursor,
match_data: Option<Box<dyn Any>>,
) -> (Cursor, Vec<Report<'_, (Rc<dyn Source>, Range<usize>)>>);
fn on_match(&self, parser: &dyn Parser, document: &Document, cursor: Cursor, match_data: Option<Box<dyn Any>>) -> (Cursor, Vec<Report<'_, (Rc<dyn Source>, Range<usize>)>>);
/// Export bindings to lua
fn lua_bindings<'lua>(&self, _lua: &'lua Lua) -> Vec<(String, Function<'lua>)>;
}
impl core::fmt::Debug for dyn Rule {
impl core::fmt::Debug for dyn Rule
{
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
write!(f, "Rule{{{}}}", self.name())
}
@ -73,78 +65,53 @@ impl<T: RegexRule> Rule for T {
}
*/
pub trait RegexRule {
pub trait RegexRule
{
fn name(&self) -> &'static str;
/// Returns the rule's regexes
fn regexes(&self) -> &[regex::Regex];
/// Callback on regex rule match
fn on_regex_match<'a>(
&self,
index: usize,
parser: &dyn Parser,
document: &'a (dyn Document<'a> + 'a),
token: Token,
matches: regex::Captures,
) -> Vec<Report<'_, (Rc<dyn Source>, Range<usize>)>>;
fn on_regex_match(&self, index: usize, parser: &dyn Parser, document: &Document, token: Token, matches: regex::Captures) -> Vec<Report<'_, (Rc<dyn Source>, Range<usize>)>>;
fn lua_bindings<'lua>(&self, _lua: &'lua Lua) -> Vec<(String, Function<'lua>)>;
}
impl<T: RegexRule> Rule for T {
fn name(&self) -> &'static str {
RegexRule::name(self)
}
fn name(&self) -> &'static str { RegexRule::name(self) }
/// Finds the next match starting from [`cursor`]
fn next_match(&self, cursor: &Cursor) -> Option<(usize, Box<dyn Any>)> {
fn next_match(&self, cursor: &Cursor)
-> Option<(usize, Box<dyn Any>)> {
let content = cursor.source.content();
let mut found: Option<(usize, usize)> = None;
self.regexes().iter().enumerate().for_each(|(id, re)| {
if let Some(m) = re.find_at(content.as_str(), cursor.pos) {
if let Some(m) = re.find_at(content.as_str(), cursor.pos)
{
found = found
.and_then(|(f_pos, f_id)| {
if f_pos > m.start() {
Some((m.start(), id))
} else {
Some((f_pos, f_id))
}
})
.and_then(|(f_pos, f_id)|
if f_pos > m.start() { Some((m.start(), id)) } else { Some((f_pos, f_id)) } )
.or(Some((m.start(), id)));
}
});
return found.map(|(pos, id)| (pos, Box::new(id) as Box<dyn Any>));
return found.map(|(pos, id)|
(pos, Box::new(id) as Box<dyn Any>));
}
fn on_match<'a>(
&self,
parser: &dyn Parser,
document: &'a (dyn Document<'a> + 'a),
cursor: Cursor,
match_data: Option<Box<dyn Any>>,
) -> (Cursor, Vec<Report<'_, (Rc<dyn Source>, Range<usize>)>>) {
fn on_match(&self, parser: &dyn Parser, document: &Document, cursor: Cursor, match_data: Option<Box<dyn Any>>)
-> (Cursor, Vec<Report<'_, (Rc<dyn Source>, Range<usize>)>>) {
let content = cursor.source.content();
let index = unsafe {
match_data
.unwrap_unchecked()
.downcast::<usize>()
.unwrap_unchecked()
};
let index = unsafe { match_data.unwrap_unchecked().downcast::<usize>().unwrap_unchecked() };
let re = &self.regexes()[*index];
let captures = re.captures_at(content.as_str(), cursor.pos).unwrap();
let token = Token::new(captures.get(0).unwrap().range(), cursor.source.clone());
let token_end = token.end();
return (
cursor.at(token_end),
self.on_regex_match(*index, parser, document, token, captures),
);
return (cursor.at(token_end), self.on_regex_match(*index, parser, document, token, captures));
}
fn lua_bindings<'lua>(&self, lua: &'lua Lua) -> Vec<(String, Function<'lua>)> {
self.lua_bindings(lua)
}
fn lua_bindings<'lua>(&self, lua: &'lua Lua) -> Vec<(String, Function<'lua>)> { self.lua_bindings(lua) }
}

126
src/parser/source.rs
View file

@ -1,13 +1,12 @@
use std::{fs, ops::Range, rc::Rc};
use core::fmt::Debug;
use std::fs;
use std::ops::Range;
use std::rc::Rc;
use downcast_rs::impl_downcast;
use downcast_rs::Downcast;
use downcast_rs::{impl_downcast, Downcast};
use serde::{Deserialize, Serialize};
/// Trait for source content
pub trait Source: Downcast {
pub trait Source: Downcast
{
/// Gets the source's location
fn location(&self) -> Option<&Token>;
/// Gets the source's name
@ -17,20 +16,23 @@ pub trait Source: Downcast {
}
impl_downcast!(Source);
impl core::fmt::Display for dyn Source {
impl core::fmt::Display for dyn Source
{
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
write!(f, "{}", self.name())
}
}
impl core::fmt::Debug for dyn Source {
impl core::fmt::Debug for dyn Source
{
// TODO
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
write!(f, "Source{{{}}}", self.name())
}
}
impl std::cmp::PartialEq for dyn Source {
impl std::cmp::PartialEq for dyn Source
{
fn eq(&self, other: &Self) -> bool {
self.name() == other.name()
}
@ -38,29 +40,30 @@ impl std::cmp::PartialEq for dyn Source {
impl std::cmp::Eq for dyn Source {}
impl std::hash::Hash for dyn Source {
impl std::hash::Hash for dyn Source
{
fn hash<H: std::hash::Hasher>(&self, state: &mut H) {
self.name().hash(state)
}
}
pub struct SourceFile {
pub struct SourceFile
{
location: Option<Token>,
path: String,
content: String,
}
impl SourceFile {
impl SourceFile
{
// TODO: Create a SourceFileRegistry holding already loaded files to avoid reloading them
pub fn new(path: String, location: Option<Token>) -> Result<Self, String> {
match fs::read_to_string(&path) {
Err(_) => {
return Err(String::from(format!(
"Unable to read file content: `{}`",
path
)))
}
Ok(content) => Ok(Self {
pub fn new(path: String, location: Option<Token>) -> Result<Self, String>
{
match fs::read_to_string(&path)
{
Err(_) => return Err(String::from(format!("Unable to read file content: `{}`", path))),
Ok(content) => Ok(Self{
location,
path,
content,
@ -68,7 +71,8 @@ impl SourceFile {
}
}
pub fn with_content(path: String, content: String, location: Option<Token>) -> Self {
pub fn with_content(path: String, content: String, location: Option<Token>) -> Self
{
Self {
location: location,
path: path,
@ -77,48 +81,38 @@ impl SourceFile {
}
}
impl Source for SourceFile {
fn location(&self) -> Option<&Token> {
self.location.as_ref()
}
fn name(&self) -> &String {
&self.path
}
fn content(&self) -> &String {
&self.content
}
impl Source for SourceFile
{
fn location(&self) -> Option<&Token> { self.location.as_ref() }
fn name(&self) -> &String { &self.path }
fn content(&self) -> &String { &self.content }
}
pub struct VirtualSource {
pub struct VirtualSource
{
location: Token,
name: String,
content: String,
}
impl VirtualSource {
pub fn new(location: Token, name: String, content: String) -> Self {
Self {
location,
name,
content,
}
impl VirtualSource
{
pub fn new(location: Token, name: String, content: String) -> Self
{
Self { location, name, content }
}
}
impl Source for VirtualSource {
fn location(&self) -> Option<&Token> {
Some(&self.location)
}
fn name(&self) -> &String {
&self.name
}
fn content(&self) -> &String {
&self.content
}
impl Source for VirtualSource
{
fn location(&self) -> Option<&Token> { Some(&self.location) }
fn name(&self) -> &String { &self.name }
fn content(&self) -> &String { &self.content }
}
#[derive(Debug)]
pub struct Cursor {
pub struct Cursor
{
pub pos: usize,
pub source: Rc<dyn Source>,
}
@ -129,7 +123,8 @@ impl Cursor {
}
/// Creates [`cursor`] at [`new_pos`] in the same [`file`]
pub fn at(&self, new_pos: usize) -> Self {
pub fn at(&self, new_pos: usize) -> Self
{
Self {
pos: new_pos,
source: self.source.clone(),
@ -137,7 +132,8 @@ impl Cursor {
}
}
impl Clone for Cursor {
impl Clone for Cursor
{
fn clone(&self) -> Self {
Self {
pos: self.pos,
@ -151,35 +147,41 @@ impl Clone for Cursor {
}
#[derive(Debug, Clone)]
pub struct Token {
pub struct Token
{
pub range: Range<usize>,
source: Rc<dyn Source>,
}
impl Token {
impl Token
{
pub fn new(range: Range<usize>, source: Rc<dyn Source>) -> Self {
Self { range, source }
}
pub fn source(&self) -> Rc<dyn Source> {
return self.source.clone();
pub fn source(&self) -> Rc<dyn Source>
{
return self.source.clone()
}
/// Construct Token from a range
pub fn from(start: &Cursor, end: &Cursor) -> Self {
pub fn from(start: &Cursor, end: &Cursor) -> Self
{
assert!(Rc::ptr_eq(&start.source, &end.source));
Self {
range: start.pos..end.pos,
source: start.source.clone(),
range: start.pos .. end.pos,
source: start.source.clone()
}
}
pub fn start(&self) -> usize {
pub fn start(&self) -> usize
{
return self.range.start;
}
pub fn end(&self) -> usize {
pub fn end(&self) -> usize
{
return self.range.end;
}
}

76
src/parser/state.rs
View file

@ -1,20 +1,16 @@
use std::cell::RefCell;
use std::collections::HashMap;
use std::ops::Range;
use std::rc::Rc;
use std::{cell::RefCell, collections::HashMap, ops::Range, rc::Rc};
use ariadne::Report;
use downcast_rs::impl_downcast;
use downcast_rs::Downcast;
use downcast_rs::{impl_downcast, Downcast};
use crate::document::document::Document;
use super::parser::Parser;
use super::source::Source;
use super::{parser::Parser, source::Source};
/// Scope for state objects
#[derive(PartialEq, PartialOrd, Debug)]
pub enum Scope {
pub enum Scope
{
/// Global state
GLOBAL = 0,
/// Document-local state
@ -25,20 +21,18 @@ pub enum Scope {
PARAGRAPH = 2,
}
pub trait State: Downcast {
pub trait State: Downcast
{
/// Returns the state's [`Scope`]
fn scope(&self) -> Scope;
/// Callback called when state goes out of scope
fn on_remove<'a>(
&self,
parser: &dyn Parser,
document: &dyn Document,
) -> Vec<Report<'a, (Rc<dyn Source>, Range<usize>)>>;
fn on_remove<'a>(&self, parser: &dyn Parser, document: &Document) -> Vec<Report<'a, (Rc<dyn Source>, Range<usize>)>>;
}
impl_downcast!(State);
impl core::fmt::Debug for dyn State {
impl core::fmt::Debug for dyn State
{
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
write!(f, "State{{Scope: {:#?}}}", self.scope())
}
@ -46,11 +40,13 @@ impl core::fmt::Debug for dyn State {
/// Object owning all the states
#[derive(Debug)]
pub struct StateHolder {
data: HashMap<String, Rc<RefCell<dyn State>>>,
pub struct StateHolder
{
data: HashMap<String, Rc<RefCell<dyn State>>>
}
impl StateHolder {
impl StateHolder
{
pub fn new() -> Self {
Self {
data: HashMap::new(),
@ -58,38 +54,38 @@ impl StateHolder {
}
// Attempts to push [`state`]. On collision, returns an error with the already present state
pub fn insert(
&mut self,
name: String,
state: Rc<RefCell<dyn State>>,
) -> Result<Rc<RefCell<dyn State>>, Rc<RefCell<dyn State>>> {
match self.data.insert(name, state.clone()) {
pub fn insert(&mut self, name: String, state: Rc<RefCell<dyn State>>) -> Result<Rc<RefCell<dyn State>>, Rc<RefCell<dyn State>>>
{
match self.data.insert(name, state.clone())
{
Some(state) => Err(state),
_ => Ok(state),
_ => Ok(state)
}
}
pub fn query(&self, name: &String) -> Option<Rc<RefCell<dyn State>>> {
self.data.get(name).map_or(None, |st| Some(st.clone()))
pub fn query(&self, name: &String) -> Option<Rc<RefCell<dyn State>>>
{
self.data
.get(name)
.map_or(None, |st| Some(st.clone()))
}
pub fn on_scope_end(
&mut self,
parser: &dyn Parser,
document: &dyn Document,
scope: Scope,
) -> Vec<Report<'_, (Rc<dyn Source>, Range<usize>)>> {
pub fn on_scope_end(&mut self, parser: &dyn Parser, document: &Document, scope: Scope) -> Vec<Report<'_, (Rc<dyn Source>, Range<usize>)>>
{
let mut result = vec![];
self.data.retain(|_name, state| {
if state.borrow().scope() >= scope {
state
.borrow()
.on_remove(parser, document)
self.data
.retain(|_name, state|
{
if state.borrow().scope() >= scope
{
state.borrow().on_remove(parser, document)
.drain(..)
.for_each(|report| result.push(report));
false
} else {
}
else
{
true
}
});

426
src/parser/util.rs
View file

@ -1,43 +1,38 @@
use std::collections::HashMap;
use std::rc::Rc;
use unicode_segmentation::UnicodeSegmentation;
use crate::document::document::Document;
use crate::document::document::DocumentAccessors;
use crate::document::element::ElemKind;
use crate::elements::paragraph::Paragraph;
use super::parser::Parser;
use super::source::Source;
use crate::{document::{document::Document, element::ElemKind}, elements::paragraph::Paragraph};
/// Processes text for escape characters and paragraphing
pub fn process_text(document: &dyn Document, content: &str) -> String {
pub fn process_text(document: &Document, content: &str) -> String
{
let mut escaped = false;
let mut newlines = 0usize; // Consecutive newlines
//println!("Processing: [{content}]");
let processed = content
.graphemes(true)
.fold((String::new(), None), |(mut out, prev), g| {
if newlines != 0 && g != "\n" {
.grapheme_indices(true)
.fold((String::new(), None),
|(mut out, prev), (_pos, g)| {
if newlines != 0 && g != "\n"
{
newlines = 0;
// Add a whitespace if necessary
match out.chars().last() {
match out.chars().last()
{
Some(c) => {
// NOTE: \n is considered whitespace, so previous codepoint can be \n
// (Which can only be done by escaping it)
if !c.is_whitespace() || c == '\n' {
if !c.is_whitespace() || c == '\n'
{
out += " ";
}
}
None => {
if document
.last_element::<Paragraph>()
.and_then(|par| {
par.find_back(|e| e.kind() != ElemKind::Invisible)
.and_then(|e| Some(e.kind() == ElemKind::Inline))
})
if document.last_element::<Paragraph>(false)
.and_then(|par| par.find_back(|e| e.kind() != ElemKind::Invisible)
.and_then(|e| Some(e.kind() == ElemKind::Inline)))
.unwrap_or(false)
{
out += " ";
@ -47,42 +42,48 @@ pub fn process_text(document: &dyn Document, content: &str) -> String {
}
// Output grapheme literally when escaped
if escaped {
if escaped
{
escaped = false;
return (out + g, Some(g));
}
// Increment newlines counter
else if g == "\n" {
else if g == "\n"
{
newlines += 1;
return (out, Some(g));
}
// Determine if escaped
else if g == "\\" {
else if g == "\\"
{
escaped = !escaped;
return (out, Some(g));
}
// Whitespaces
else if g.chars().count() == 1 && g.chars().last().unwrap().is_whitespace() {
else if g.chars().count() == 1 && g.chars().last().unwrap().is_whitespace()
{
// Content begins with whitespace
if prev.is_none() {
if document.last_element::<Paragraph>().is_some() {
return (out + g, Some(g));
} else {
if prev.is_none()
{
if document.last_element::<Paragraph>(false).is_some()
{
return (out+g, Some(g));
}
else
{
return (out, Some(g));
}
}
// Consecutive whitespaces are converted to a single whitespace
else if prev.unwrap().chars().count() == 1
&& prev.unwrap().chars().last().unwrap().is_whitespace()
else if prev.unwrap().chars().count() == 1 &&
prev.unwrap().chars().last().unwrap().is_whitespace()
{
return (out, Some(g));
}
}
return (out + g, Some(g));
})
.0
.to_string();
}).0.to_string();
return processed;
}
@ -93,32 +94,39 @@ pub fn process_text(document: &dyn Document, content: &str) -> String {
/// # Example
/// ```
/// assert_eq!(process_escaped('\\', "%", "escaped: \\%, also escaped: \\\\\\%, untouched: \\a"),
/// "escaped: %, also escaped: \\%, untouched: \\a");
/// "escaped: %, also escaped: \\%, untouched \\a");
/// ```
pub fn process_escaped<S: AsRef<str>>(escape: char, token: &'static str, content: S) -> String {
pub fn process_escaped<S: AsRef<str>>(escape: char, token: &'static str, content: S) -> String
{
let mut processed = String::new();
let mut escaped = 0;
let mut token_it = token.chars().peekable();
for c in content
.as_ref()
.chars()
for c in content.as_ref().chars()
.as_str()
.trim_start()
.trim_end()
.chars()
{
if c == escape {
if c == escape
{
escaped += 1;
} else if escaped % 2 == 1 && token_it.peek().map_or(false, |p| *p == c) {
}
else if escaped % 2 == 1 && token_it.peek().map_or(false, |p| *p == c)
{
let _ = token_it.next();
if token_it.peek() == None {
(0..(escaped / 2)).for_each(|_| processed.push(escape));
if token_it.peek() == None
{
(0..((escaped-1)/2))
.for_each(|_| processed.push(escape));
escaped = 0;
token_it = token.chars().peekable();
processed.push_str(token);
}
} else {
if escaped != 0 {
}
else
{
if escaped != 0
{
// Add untouched escapes
(0..escaped).for_each(|_| processed.push('\\'));
token_it = token.chars().peekable();
@ -133,28 +141,9 @@ pub fn process_escaped<S: AsRef<str>>(escape: char, token: &'static str, content
processed
}
/// Parses source into a single paragraph
/// If source contains anything but a single paragraph, an error is returned
pub fn parse_paragraph<'a>(
parser: &dyn Parser,
source: Rc<dyn Source>,
document: &'a dyn Document<'a>,
) -> Result<Box<Paragraph>, &'static str> {
let parsed = parser.parse(source.clone(), Some(document));
if parsed.content().borrow().len() > 1 {
return Err("Parsed document contains more than a single paragraph");
} else if parsed.content().borrow().len() == 0 {
return Err("Parser document is empty");
} else if parsed.last_element::<Paragraph>().is_none() {
return Err("Parsed element is not a paragraph");
}
let paragraph = parsed.content().borrow_mut().pop().unwrap();
Ok(paragraph.downcast::<Paragraph>().unwrap())
}
#[derive(Debug)]
pub struct Property {
pub struct Property
{
required: bool,
description: String,
default: Option<String>,
@ -162,70 +151,42 @@ pub struct Property {
impl Property {
pub fn new(required: bool, description: String, default: Option<String>) -> Self {
Self {
required,
description,
default,
}
Self { required, description, default }
}
}
impl core::fmt::Display for Property {
impl core::fmt::Display for Property
{
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
match self.default.as_ref() {
None => write!(
f,
"{} {}",
match self.default.as_ref()
{
None => write!(f, "{} {}",
["[Opt]", "[Req]"][self.required as usize],
self.description
),
Some(default) => write!(
f,
"{} {} (Deafult: {})",
self.description),
Some(default) => write!(f, "{} {} (Deafult: {})",
["[Opt]", "[Req]"][self.required as usize],
self.description,
default
),
default)
}
}
}
#[derive(Debug)]
pub enum PropertyMapError<E> {
ParseError(E),
NotFoundError(String),
}
#[derive(Debug)]
pub struct PropertyMap<'a> {
pub(crate) properties: HashMap<String, (&'a Property, String)>,
pub struct PropertyMap<'a>
{
pub(crate) properties: HashMap<String, (&'a Property, String)>
}
impl<'a> PropertyMap<'a> {
pub fn new() -> Self {
Self {
properties: HashMap::new(),
}
Self { properties: HashMap::new() }
}
pub fn get<T, Error, F: FnOnce(&'a Property, &String) -> Result<T, Error>>(
&self,
name: &str,
f: F,
) -> Result<(&'a Property, T), PropertyMapError<Error>> {
let (prop, value) = match self.properties.get(name) {
Some(found) => found,
None => {
return Err(PropertyMapError::NotFoundError(format!(
"Property `{name}` not found"
)))
}
};
pub fn get<T, Error, F: FnOnce(&'a Property, &String) -> Result<T, Error>>(&self, name: &str, f: F)
-> Result<(&'a Property, T), Error> {
let (prop, value) = self.properties.get(name).unwrap();
match f(prop, value) {
Ok(parsed) => Ok((*prop, parsed)),
Err(err) => Err(PropertyMapError::ParseError(err)),
}
f(prop, value).and_then(|value| Ok((*prop, value)))
}
}
@ -234,7 +195,9 @@ pub struct PropertyParser {
}
impl PropertyParser {
pub fn new(properties: HashMap<String, Property>) -> Self { Self { properties } }
pub fn new(properties: HashMap<String, Property>) -> Self {
Self { properties }
}
/// Attempts to build a default propertymap
///
@ -242,14 +205,17 @@ impl PropertyParser {
pub fn default(&self) -> Result<PropertyMap<'_>, String> {
let mut properties = PropertyMap::new();
for (name, prop) in &self.properties {
match (prop.required, prop.default.as_ref()) {
for (name, prop) in &self.properties
{
match (prop.required, prop.default.as_ref())
{
(true, None) => return Err(format!("Missing property `{name}` {prop}")),
(false, None) => {}
(false, None) => {},
(_, Some(default)) => {
properties
.properties
.insert(name.clone(), (prop, default.clone()));
properties.properties.insert(
name.clone(),
(prop, default.clone())
);
}
}
}
@ -267,14 +233,13 @@ impl PropertyParser {
/// # Example
///
/// ```
/// let mut properties = HashMap::new();
/// properties.insert("width".to_string(),
/// Property::new(true, "Width of the element in em".to_string(), None));
/// let properties = HashMap::new();
/// properties.insert("width", Property::new(true, "Width of the element in em", None));
///
/// let parser = PropertyParser::new(properties);
/// let pm = parser.parse("width=15").unwrap();
///
/// assert_eq!(pm.get("width", |_, s| s.parse::<i32>()).unwrap().1, 15);
/// assert!(pm.get("width", |_, val| val.parse::<i32>()) == Ok(15));
/// ```
/// # Return value
///
@ -286,7 +251,8 @@ impl PropertyParser {
/// Note: Only ',' inside values can be escaped, other '\' are treated literally
pub fn parse(&self, content: &str) -> Result<PropertyMap<'_>, String> {
let mut properties = PropertyMap::new();
let mut try_insert = |name: &String, value: &String| -> Result<(), String> {
let mut try_insert = |name: &String, value: &String|
-> Result<(), String> {
let trimmed_name = name.trim_end().trim_start();
let trimmed_value = value.trim_end().trim_start();
let prop = match self.properties.get(trimmed_name)
@ -297,11 +263,11 @@ impl PropertyParser {
Some(prop) => prop
};
if let Some((_, previous)) = properties
.properties
.insert(trimmed_name.to_string(), (prop, trimmed_value.to_string()))
if let Some((_, previous)) = properties.properties.insert(
trimmed_name.to_string(),
(prop, trimmed_value.to_string()))
{
return Err(format!("Duplicate property `{trimmed_name}`, previous value: `{previous}` current value: `{trimmed_value}`"));
return Err(format!("Duplicate property `{trimmed_name}`, previous value: `{previous}` current value: `{trimmed_value}`"))
}
Ok(())
@ -311,213 +277,67 @@ impl PropertyParser {
let mut name = String::new();
let mut value = String::new();
let mut escaped = 0usize;
for c in content.chars() {
if c == '\\' {
for c in content.chars()
{
if c == '\\'
{
escaped += 1;
} else if c == '=' && in_name {
}
else if c == '=' && in_name
{
in_name = false;
(0..escaped).for_each(|_| name.push('\\'));
escaped = 0;
} else if c == ',' && !in_name {
if escaped % 2 == 0
// Not escaped
}
else if c == ',' && !in_name
{
(0..escaped / 2).for_each(|_| value.push('\\'));
if escaped % 2 == 0 // Not escaped
{
(0..escaped/2).for_each(|_| value.push('\\'));
escaped = 0;
in_name = true;
if let Err(e) = try_insert(&name, &value) {
return Err(e);
return Err(e)
}
name.clear();
value.clear();
} else {
(0..(escaped - 1) / 2).for_each(|_| value.push('\\'));
}
else
{
(0..(escaped-1)/2).for_each(|_| value.push('\\'));
value.push(',');
escaped = 0;
}
} else {
}
else
{
if in_name {
(0..escaped).for_each(|_| name.push('\\'));
name.push(c)
} else {
}
else {
(0..escaped).for_each(|_| value.push('\\'));
value.push(c)
}
escaped = 0;
}
}
if !in_name && value.trim_end().trim_start().is_empty() {
return Err("Expected a value after last `=`".to_string());
} else if name.is_empty() || value.is_empty() {
if !in_name && value.trim_end().trim_start().is_empty()
{
return Err("Expected a value after last `=`".to_string())
}
else if name.is_empty() || value.is_empty()
{
return Err("Expected non empty property list.".to_string());
}
if let Err(e) = try_insert(&name, &value) {
return Err(e);
return Err(e)
}
if let Err(e) = self.properties.iter().try_for_each(|(key, prop)| {
if !properties.properties.contains_key(key) {
if let Some(default) = &prop.default {
properties
.properties
.insert(key.clone(), (prop, default.clone()));
} else if prop.required {
return Err(format!("Missing required property: {prop}"));
}
}
Ok(())
}) {
Err(e)
} else {
// TODO: Missing properties
Ok(properties)
}
}
}
#[cfg(test)]
mod tests {
use super::*;
use crate::document::langdocument::LangDocument;
use crate::elements::comment::Comment;
use crate::elements::style::Style;
use crate::elements::text::Text;
use crate::parser::source::SourceFile;
use crate::parser::source::Token;
use std::rc::Rc;
#[test]
fn process_text_tests() {
let source = Rc::new(SourceFile::with_content(
"".to_string(),
"".to_string(),
None,
));
let doc = LangDocument::new(source.clone(), None);
assert_eq!(process_text(&doc, "a\nb"), "a b");
assert_eq!(process_text(&doc, "a\n\nb"), "a b"); // Should never happen but why not
assert_eq!(process_text(&doc, "a\\b"), "ab");
assert_eq!(process_text(&doc, "a\\\nb"), "a\nb");
assert_eq!(process_text(&doc, "a\\\\b"), "a\\b");
assert_eq!(process_text(&doc, "a\\\\\nb"), "a\\ b");
assert_eq!(process_text(&doc, "\na"), "a");
let tok = Token::new(0..0, source);
doc.push(Box::new(Paragraph::new(tok.clone())));
// Comments are ignored (kind => Invisible)
(&doc as &dyn Document)
.last_element_mut::<Paragraph>()
.unwrap()
.push(Box::new(Comment::new(tok.clone(), "COMMENT".to_string())));
assert_eq!(process_text(&doc, "\na"), "a");
// A space is appended as previous element is inline
(&doc as &dyn Document)
.last_element_mut::<Paragraph>()
.unwrap()
.push(Box::new(Text::new(tok.clone(), "TEXT".to_string())));
assert_eq!(process_text(&doc, "\na"), " a");
(&doc as &dyn Document)
.last_element_mut::<Paragraph>()
.unwrap()
.push(Box::new(Style::new(tok.clone(), 0, false)));
assert_eq!(process_text(&doc, "\na"), " a");
}
#[test]
fn process_escaped_tests() {
assert_eq!(
process_escaped(
'\\',
"%",
"escaped: \\%, also escaped: \\\\\\%, untouched: \\a"
),
"escaped: %, also escaped: \\%, untouched: \\a"
);
assert_eq!(
process_escaped('"', "><)))°>", "Escaped fish: \"><)))°>"),
"Escaped fish: ><)))°>".to_string()
);
assert_eq!(
process_escaped('\\', "]", "Escaped \\]"),
"Escaped ]".to_string()
);
assert_eq!(
process_escaped('\\', "]", "Unescaped \\\\]"),
"Unescaped \\\\]".to_string()
);
assert_eq!(
process_escaped('\\', "]", "Escaped \\\\\\]"),
"Escaped \\]".to_string()
);
assert_eq!(
process_escaped('\\', "]", "Unescaped \\\\\\\\]"),
"Unescaped \\\\\\\\]".to_string()
);
}
#[test]
fn property_parser_tests() {
let mut properties = HashMap::new();
properties.insert(
"width".to_string(),
Property::new(true, "Width of the element in em".to_string(), None),
);
properties.insert(
"length".to_string(),
Property::new(false, "Length in cm".to_string(), None),
);
properties.insert(
"angle".to_string(),
Property::new(
true,
"Angle in degrees".to_string(),
Some("180".to_string()),
),
);
properties.insert(
"weight".to_string(),
Property::new(false, "Weight in %".to_string(), Some("0.42".to_string())),
);
let parser = PropertyParser::new(properties);
let pm = parser.parse("width=15,length=-10").unwrap();
// Ok
assert_eq!(pm.get("width", |_, s| s.parse::<i32>()).unwrap().1, 15);
assert_eq!(pm.get("length", |_, s| s.parse::<i32>()).unwrap().1, -10);
assert_eq!(pm.get("angle", |_, s| s.parse::<f64>()).unwrap().1, 180f64);
assert_eq!(pm.get("angle", |_, s| s.parse::<i32>()).unwrap().1, 180);
assert_eq!(
pm.get("weight", |_, s| s.parse::<f32>()).unwrap().1,
0.42f32
);
assert_eq!(
pm.get("weight", |_, s| s.parse::<f64>()).unwrap().1,
0.42f64
);
// Error
assert!(pm.get("length", |_, s| s.parse::<u32>()).is_err());
assert!(pm.get("height", |_, s| s.parse::<f64>()).is_err());
// Missing property
assert!(parser.parse("length=15").is_err());
// Defaults
assert!(parser.parse("width=15").is_ok());
assert_eq!(
parser
.parse("width=0,weight=0.15")
.unwrap()
.get("weight", |_, s| s.parse::<f32>())
.unwrap()
.1,
0.15f32
);
}
}

6
src/server.rs
View file

@ -51,9 +51,9 @@ impl Backend {
let parser = LangParser::default();
let doc = parser.parse(Rc::new(source), None);
//let semantic_tokens = semantic_token_from_document(&doc);
//self.semantic_token_map
// .insert(params.uri.to_string(), semantic_tokens);
let semantic_tokens = semantic_token_from_document(&doc);
self.semantic_token_map
.insert(params.uri.to_string(), semantic_tokens);
}
}

110
style.css
View file

@ -1,110 +0,0 @@
body {
background-color: #1b1b1d;
color: #c5c5c5;
font-family: sans-serif;
max-width: 90ch;
margin: 0 auto;
}
em {
padding-left: .1em;
padding-right: .1em;
border-radius: 3px;
border: solid 1px #100c1e;
color: #ffb454;
background-color: #191f26;
}
/* Styles */
a.inline-code
{
padding-left: .1em;
padding-right: .1em;
border-radius: 1px;
background-color: #191f26;
}
/* Code blocks */
div.code-block-title {
background-color: #20202a;
padding-left: .3em;
}
div.code-block-content {
max-height: 20em;
margin-bottom: 0.2em;
width: auto;
overflow: auto;
background-color: #0f141a;
}
div.code-block-content td {
border: 0;
padding: 0;
}
div.code-block-content pre {
border: 0;
margin: 0;
}
div.code-block-content .code-block-gutter {
-moz-user-select: none;
-ms-user-select: none;
-webkit-user-select: none;
user-select: none;
padding-left: .1em;
padding-right: .2em;
text-align: right;
border-right: solid #2a2e3e 1px;
background: #222d3a;
}
div.code-block-content .code-block-line {
padding-left: .1em;
}
/* Media */
.media {
max-width: 85ch;
margin: auto;
text-align: center;
}
.medium {
padding-top: 1em;
display: inline-block;
vertical-align: middle;
margin-left: .5em;
margin-right: .5em;
}
.medium img {
max-width: 100%;
}
div.medium p.medium-refname {
margin: 0;
text-align: center;
font-weight: bold;
color: #9424af;
}
div.medium p {
padding: 0;
margin-top: 0;
margin-left: 1em;
margin-right: 1em;
text-align: justify;
}

268
third/latex2svg
View file

@ -1,268 +0,0 @@
#!/usr/bin/env python3
"""latex2svg
Read LaTeX code from stdin and render a SVG using LaTeX, dvisvgm and svgo.
Returns a minified SVG with `width`, `height` and `style="vertical-align:"`
attribues whose values are in `em` units. The SVG will have (pseudo-)unique
IDs in case more than one is used on the same HTML page.
Based on [original work](https://github.com/tuxu/latex2svg) by Tino Wagner.
"""
__version__ = '0.2.1'
__author__ = 'Matthias C. Hormann'
__email__ = 'mhormann@gmx.de'
__license__ = 'MIT'
__copyright__ = 'Copyright (c) 2022, Matthias C. Hormann'
import os
import sys
import subprocess
import shlex
import re
from tempfile import TemporaryDirectory
from ctypes.util import find_library
default_template = r"""
\documentclass[{{ fontsize }}pt,preview]{standalone}
{{ preamble }}
\begin{document}
\begin{preview}
{{ code }}
\end{preview}
\end{document}
"""
default_preamble = r"""
\usepackage[utf8x]{inputenc}
\usepackage{amsmath}
\usepackage{amsfonts}
\usepackage{amssymb}
\usepackage{amstext}
\usepackage{newtxtext}
\usepackage[libertine]{newtxmath}
% prevent errors from old font commands
\DeclareOldFontCommand{\rm}{\normalfont\rmfamily}{\mathrm}
\DeclareOldFontCommand{\sf}{\normalfont\sffamily}{\mathsf}
\DeclareOldFontCommand{\tt}{\normalfont\ttfamily}{\mathtt}
\DeclareOldFontCommand{\bf}{\normalfont\bfseries}{\mathbf}
\DeclareOldFontCommand{\it}{\normalfont\itshape}{\mathit}
\DeclareOldFontCommand{\sl}{\normalfont\slshape}{\@nomath\sl}
\DeclareOldFontCommand{\sc}{\normalfont\scshape}{\@nomath\sc}
% prevent errors from undefined shortcuts
\newcommand{\N}{\mathbb{N}}
\newcommand{\R}{\mathbb{R}}
\newcommand{\Z}{\mathbb{Z}}
"""
default_svgo_config = r"""
module.exports = {
plugins: [
{
// use default preset (almost)
name: 'preset-default',
params: {
overrides: {
// viewbox required to resize SVGs with CSS, disable removal
removeViewBox: false,
},
},
// enable prefixIds
name: 'prefixIds',
params: {
prefix: '{{ prefix }}',
delim: '_',
},
},
],
};
"""
latex_cmd = 'latex -interaction nonstopmode -halt-on-error'
dvisvgm_cmd = 'dvisvgm --no-fonts'
svgo_cmd = 'svgo'
default_params = {
'fontsize': 12, # TeX pt
'template': default_template,
'preamble': default_preamble,
'latex_cmd': latex_cmd,
'dvisvgm_cmd': dvisvgm_cmd,
'svgo_cmd': svgo_cmd,
'svgo_config': default_svgo_config,
'libgs': None,
}
if not hasattr(os.environ, 'LIBGS') and not find_library('gs'):
if sys.platform == 'darwin':
# Fallback to homebrew Ghostscript on macOS
homebrew_libgs = '/usr/local/opt/ghostscript/lib/libgs.dylib'
if os.path.exists(homebrew_libgs):
default_params['libgs'] = homebrew_libgs
if not default_params['libgs']:
print('Warning: libgs not found', file=sys.stderr)
def latex2svg(code, params=default_params, working_directory=None):
"""Convert LaTeX to SVG using dvisvgm and svgo.
Parameters
----------
code : str
LaTeX code to render.
params : dict
Conversion parameters.
working_directory : str or None
Working directory for external commands and place for temporary files.
Returns
-------
dict
Dictionary of SVG output and output information:
* `svg`: SVG data
* `width`: image width in *em*
* `height`: image height in *em*
* `valign`: baseline offset in *em*
"""
if working_directory is None:
with TemporaryDirectory() as tmpdir:
return latex2svg(code, params, working_directory=tmpdir)
# Caution: TeX & dvisvgm work with TeX pt (1/72.27"), but we need DTP pt (1/72")
# so we need a scaling factor for correct output sizes
scaling = 1.00375 # (1/72)/(1/72.27)
fontsize = params['fontsize']
document = code
with open(os.path.join(working_directory, 'code.tex'), 'w') as f:
f.write(document)
# Run LaTeX and create DVI file
try:
ret = subprocess.run(shlex.split(params['latex_cmd']+' code.tex'),
stdout=subprocess.PIPE, stderr=subprocess.PIPE,
cwd=working_directory)
ret.check_returncode()
except FileNotFoundError:
raise RuntimeError('latex not found')
# Add LIBGS to environment if supplied
env = os.environ.copy()
if params['libgs']:
env['LIBGS'] = params['libgs']
# Convert DVI to SVG
try:
ret = subprocess.run(shlex.split(params['dvisvgm_cmd']+' code.dvi'),
stdout=subprocess.PIPE, stderr=subprocess.PIPE,
cwd=working_directory, env=env)
ret.check_returncode()
except FileNotFoundError:
raise RuntimeError('dvisvgm not found')
# Parse dvisvgm output for size and alignment
def get_size(output):
regex = r'\b([0-9.]+)pt x ([0-9.]+)pt'
match = re.search(regex, output)
if match:
return (float(match.group(1)) / fontsize * scaling,
float(match.group(2)) / fontsize * scaling)
else:
return None, None
def get_measure(output, name):
regex = r'\b%s=([0-9.e-]+)pt' % name
match = re.search(regex, output)
if match:
return float(match.group(1)) / fontsize * scaling
else:
return None
output = ret.stderr.decode('utf-8')
width, height = get_size(output)
depth = get_measure(output, 'depth')
# Modify SVG attributes, to a get a self-contained, scaling SVG
from lxml import etree
# read SVG, discarding all comments ("<-- Generated by… -->")
parser = etree.XMLParser(remove_comments=True)
xml = etree.parse(os.path.join(working_directory, 'code.svg'), parser)
svg = xml.getroot()
svg.set('width', f'{width:.6f}em')
svg.set('height', f'{height:.6f}em')
svg.set('style', f'vertical-align:{-depth:.6f}em')
xml.write(os.path.join(working_directory, 'code.svg'))
# Run svgo to get a minified oneliner with (pseudo-)unique Ids
# generate random prefix using ASCII letters (ID may not start with a digit)
import random, string
prefix = ''.join(random.choice(string.ascii_letters) for n in range(4))
svgo_config = (params['svgo_config']
.replace('{{ prefix }}', prefix))
# write svgo params file
with open(os.path.join(working_directory, 'svgo.config.js'), 'w') as f:
f.write(svgo_config)
try:
ret = subprocess.run(shlex.split(params['svgo_cmd']+' code.svg'),
stdout=subprocess.PIPE, stderr=subprocess.PIPE,
cwd=working_directory, env=env)
ret.check_returncode()
except FileNotFoundError:
raise RuntimeError('svgo not found')
with open(os.path.join(working_directory, 'code.svg'), 'r') as f:
svg = f.read()
return {'svg': svg, 'valign': round(-depth,6),
'width': round(width,6), 'height': round(height,6)}
def main():
"""Simple command line interface to latex2svg.
- Read from `stdin`.
- Write SVG to `stdout`.
- On error: write error messages to `stderr` and return with error code.
"""
import json
import argparse
parser = argparse.ArgumentParser(description="""
Render LaTeX code from stdin as SVG to stdout. Writes metadata (baseline
offset, width, height in em units) into the SVG attributes.
""")
parser.add_argument('--version', action='version',
version='%(prog)s {version}'.format(version=__version__))
parser.add_argument('--preamble',
help="LaTeX preamble code to read from file")
parser.add_argument('--fontsize',
help="LaTeX fontsize in pt")
args = parser.parse_args()
preamble = default_preamble
if args.preamble is not None:
with open(args.preamble) as f:
preamble = f.read()
fontsize = 12
if args.fontsize is not None:
fontsize = int(args.fontsize)
latex = sys.stdin.read()
try:
params = default_params.copy()
params['preamble'] = preamble
params['fontsize'] = fontsize
out = latex2svg(latex, params)
sys.stdout.write(out['svg'])
except subprocess.CalledProcessError as exc:
# LaTeX prints errors on stdout instead of stderr (stderr is empty),
# dvisvgm to stderr, so print both (to stderr)
print(exc.output.decode('utf-8'), file=sys.stderr)
print(exc.stderr.decode('utf-8'), file=sys.stderr)
sys.exit(exc.returncode)
if __name__ == '__main__':
main()