2020-04-08 16:18:18 -04:00
|
|
|
// TAME compiler
|
|
|
|
//
|
2022-05-03 14:14:29 -04:00
|
|
|
// Copyright (C) 2014-2022 Ryan Specialty Group, LLC.
|
2020-04-08 16:18:18 -04:00
|
|
|
//
|
|
|
|
// This file is part of TAME.
|
|
|
|
//
|
|
|
|
// This program is free software: you can redistribute it and/or modify
|
|
|
|
// it under the terms of the GNU General Public License as published by
|
|
|
|
// the Free Software Foundation, either version 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 General Public License for more details.
|
|
|
|
//
|
|
|
|
// You should have received a copy of the GNU General Public License
|
|
|
|
// along with this program. If not, see <http://www.gnu.org/licenses/>.
|
|
|
|
|
2022-04-13 15:11:29 -04:00
|
|
|
//! This is the TAME compiler.
|
|
|
|
//!
|
|
|
|
//! `tamec` compiles source code into object files that are later linked
|
|
|
|
//! into a final executable using [`tameld`](../tameld).
|
2020-04-08 16:18:18 -04:00
|
|
|
|
|
|
|
extern crate tamer;
|
|
|
|
|
|
|
|
use getopts::{Fail, Options};
|
2022-04-13 15:11:29 -04:00
|
|
|
use std::{
|
|
|
|
env,
|
|
|
|
error::Error,
|
tamer: Introduce NIR (accepting only)
This introduces NIR, but only as an accepting grammar; it doesn't yet emit
the NIR IR, beyond TODOs.
This modifies `tamec` to, while copying XIR, also attempt to lower NIR to
produce parser errors, if any. It does not yet fail compilation, as I just
want to be cautious and observe that everything's working properly for a
little while as people use it, before I potentially break builds.
This is the culmination of months of supporting effort. The NIR grammar is
derived from our existing TAME sources internally, which I use for now as a
test case until I introduce test cases directly into TAMER later on (I'd do
it now, if I hadn't spent so much time on this; I'll start introducing tests
as I begin emitting NIR tokens). This is capable of fully parsing our
largest system with >900 packages, as well as `core`.
`tamec`'s lowering is a mess; that'll be cleaned up in future commits. The
same can be said about `tameld`.
NIR's grammar has some initial documentation, but this will improve over
time as well.
The generated docs still need some improvement, too, especially with
generated identifiers; I just want to get this out here for testing.
DEV-7145
2022-08-29 15:28:03 -04:00
|
|
|
fmt::{self, Display, Write},
|
2022-10-19 14:38:45 -04:00
|
|
|
fs::{self, File},
|
|
|
|
io::{self, BufReader, BufWriter},
|
2022-04-13 15:11:29 -04:00
|
|
|
path::Path,
|
|
|
|
};
|
|
|
|
use tamer::{
|
2022-12-13 13:34:52 -05:00
|
|
|
asg::{
|
2022-12-13 14:36:38 -05:00
|
|
|
air::{Air, AirAggregate},
|
2022-12-13 13:46:31 -05:00
|
|
|
AsgError, DefaultAsg,
|
2022-12-13 13:34:52 -05:00
|
|
|
},
|
2022-04-20 12:08:46 -04:00
|
|
|
diagnose::{
|
|
|
|
AnnotatedSpan, Diagnostic, FsSpanResolver, Reporter, VisualReporter,
|
|
|
|
},
|
2022-12-13 13:34:52 -05:00
|
|
|
nir::{
|
|
|
|
InterpError, InterpolateNir, Nir, NirToAir, NirToAirError, XirfToNir,
|
|
|
|
XirfToNirError,
|
|
|
|
},
|
2022-10-19 14:38:45 -04:00
|
|
|
parse::{
|
2022-12-13 13:46:31 -05:00
|
|
|
FinalizeError, Lower, ParseError, Parsed, ParsedObject, ParsedResult,
|
|
|
|
UnknownToken,
|
2022-10-19 14:38:45 -04:00
|
|
|
},
|
tamer: Introduce NIR (accepting only)
This introduces NIR, but only as an accepting grammar; it doesn't yet emit
the NIR IR, beyond TODOs.
This modifies `tamec` to, while copying XIR, also attempt to lower NIR to
produce parser errors, if any. It does not yet fail compilation, as I just
want to be cautious and observe that everything's working properly for a
little while as people use it, before I potentially break builds.
This is the culmination of months of supporting effort. The NIR grammar is
derived from our existing TAME sources internally, which I use for now as a
test case until I introduce test cases directly into TAMER later on (I'd do
it now, if I hadn't spent so much time on this; I'll start introducing tests
as I begin emitting NIR tokens). This is capable of fully parsing our
largest system with >900 packages, as well as `core`.
`tamec`'s lowering is a mess; that'll be cleaned up in future commits. The
same can be said about `tameld`.
NIR's grammar has some initial documentation, but this will improve over
time as well.
The generated docs still need some improvement, too, especially with
generated identifiers; I just want to get this out here for testing.
DEV-7145
2022-08-29 15:28:03 -04:00
|
|
|
xir::{
|
|
|
|
self,
|
|
|
|
flat::{RefinedText, XirToXirf, XirToXirfError, XirfToken},
|
2022-10-19 14:38:45 -04:00
|
|
|
reader::XmlXirReader,
|
tamer: Introduce NIR (accepting only)
This introduces NIR, but only as an accepting grammar; it doesn't yet emit
the NIR IR, beyond TODOs.
This modifies `tamec` to, while copying XIR, also attempt to lower NIR to
produce parser errors, if any. It does not yet fail compilation, as I just
want to be cautious and observe that everything's working properly for a
little while as people use it, before I potentially break builds.
This is the culmination of months of supporting effort. The NIR grammar is
derived from our existing TAME sources internally, which I use for now as a
test case until I introduce test cases directly into TAMER later on (I'd do
it now, if I hadn't spent so much time on this; I'll start introducing tests
as I begin emitting NIR tokens). This is capable of fully parsing our
largest system with >900 packages, as well as `core`.
`tamec`'s lowering is a mess; that'll be cleaned up in future commits. The
same can be said about `tameld`.
NIR's grammar has some initial documentation, but this will improve over
time as well.
The generated docs still need some improvement, too, especially with
generated identifiers; I just want to get this out here for testing.
DEV-7145
2022-08-29 15:28:03 -04:00
|
|
|
writer::XmlWriter,
|
2022-10-19 14:38:45 -04:00
|
|
|
DefaultEscaper, Error as XirError, Token as XirToken,
|
tamer: Introduce NIR (accepting only)
This introduces NIR, but only as an accepting grammar; it doesn't yet emit
the NIR IR, beyond TODOs.
This modifies `tamec` to, while copying XIR, also attempt to lower NIR to
produce parser errors, if any. It does not yet fail compilation, as I just
want to be cautious and observe that everything's working properly for a
little while as people use it, before I potentially break builds.
This is the culmination of months of supporting effort. The NIR grammar is
derived from our existing TAME sources internally, which I use for now as a
test case until I introduce test cases directly into TAMER later on (I'd do
it now, if I hadn't spent so much time on this; I'll start introducing tests
as I begin emitting NIR tokens). This is capable of fully parsing our
largest system with >900 packages, as well as `core`.
`tamec`'s lowering is a mess; that'll be cleaned up in future commits. The
same can be said about `tameld`.
NIR's grammar has some initial documentation, but this will improve over
time as well.
The generated docs still need some improvement, too, especially with
generated identifiers; I just want to get this out here for testing.
DEV-7145
2022-08-29 15:28:03 -04:00
|
|
|
},
|
2022-04-13 15:11:29 -04:00
|
|
|
};
|
tamer: Initial frontend concept
This introduces the beginnings of frontends for TAMER, gated behind a
`wip-features` flag.
This will be introduced in stages:
1. Replace the existing copy with a parser-based copy (echo back out the
tokens), when the flag is on.
2. Begin to parse portions of the source, augmenting the output xmlo (xmli
at the moment). The XSLT-based compiler will be modified to skip
compilation steps as necessary.
As portions of the compilation are implemented in TAMER, they'll be placed
behind their own feature flags and stabalized, which will incrementally
remove the compilation steps from the XSLT-based system. The result should
be substantial incremental performance improvements.
Short-term, the priorities are for loading identifiers into an IR
are (though the order may change):
1. Echo
2. Imports
3. Extern declarations.
4. Simple identifiers (e.g. param, const, template, etc).
5. Classifications.
6. Documentation expressions.
7. Calculation expressions.
8. Template applications.
9. Template definitions.
10. Inline templates.
After each of those are done, the resulting xmlo (xmli) will have fully
reconstructed the source document from the IR produced during parsing.
2021-07-23 22:24:08 -04:00
|
|
|
|
2020-04-08 16:18:18 -04:00
|
|
|
/// Types of commands
|
|
|
|
enum Command {
|
|
|
|
Compile(String, String, String),
|
|
|
|
Usage,
|
|
|
|
}
|
|
|
|
|
2022-10-19 14:38:45 -04:00
|
|
|
/// Create a [`XmlXirReader`] for a source file.
|
|
|
|
///
|
|
|
|
/// The provided escaper must be shared between all readers and writers in
|
|
|
|
/// order to benefit from its caching.
|
|
|
|
fn src_reader<'a>(
|
|
|
|
input: &'a String,
|
|
|
|
escaper: &'a DefaultEscaper,
|
2022-10-26 11:29:26 -04:00
|
|
|
) -> Result<XmlXirReader<'a, BufReader<File>>, UnrecoverableError> {
|
2022-10-19 14:38:45 -04:00
|
|
|
use tamer::fs::{File, PathFile};
|
|
|
|
|
|
|
|
let source = Path::new(input);
|
|
|
|
|
|
|
|
let PathFile(_, file, ctx): PathFile<BufReader<fs::File>> =
|
|
|
|
PathFile::open(source)?;
|
|
|
|
|
|
|
|
Ok(XmlXirReader::new(file, escaper, ctx))
|
|
|
|
}
|
|
|
|
|
|
|
|
/// Write each parsed token to the provided buffer.
|
|
|
|
///
|
|
|
|
/// This is intended to be a temporary function that exists during a
|
|
|
|
/// transition period between the XSLT-based TAME and TAMER.
|
|
|
|
/// Writing XIR proves that the source file is being successfully parsed and
|
|
|
|
/// helps to evaluate system performance.
|
|
|
|
fn copy_xml_to<'e, W: io::Write + 'e>(
|
|
|
|
mut fout: W,
|
|
|
|
escaper: &'e DefaultEscaper,
|
|
|
|
) -> impl FnMut(&ParsedResult<ParsedObject<XirToken, XirError>>) + 'e {
|
|
|
|
let mut xmlwriter = Default::default();
|
|
|
|
|
|
|
|
move |tok_result| match tok_result {
|
|
|
|
Ok(Parsed::Object(tok)) => {
|
|
|
|
xmlwriter = tok.write(&mut fout, xmlwriter, escaper).unwrap();
|
|
|
|
}
|
|
|
|
_ => (),
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2022-10-19 14:58:05 -04:00
|
|
|
/// Compile a source file,
|
|
|
|
/// writing to the provided destination path.
|
|
|
|
///
|
|
|
|
/// NB: Output is presently a _copy_ of the input,
|
|
|
|
/// with formatting partially removed.
|
|
|
|
fn compile<R: Reporter>(
|
|
|
|
src_path: &String,
|
|
|
|
dest_path: &String,
|
2022-10-25 23:44:53 -04:00
|
|
|
reporter: &mut R,
|
2022-10-26 11:29:26 -04:00
|
|
|
) -> Result<(), UnrecoverableError> {
|
2022-10-19 14:58:05 -04:00
|
|
|
let dest = Path::new(&dest_path);
|
|
|
|
let fout = BufWriter::new(fs::File::create(dest)?);
|
|
|
|
|
|
|
|
let escaper = DefaultEscaper::default();
|
|
|
|
|
2022-10-25 23:44:53 -04:00
|
|
|
let mut ebuf = String::new();
|
2022-10-19 14:58:05 -04:00
|
|
|
|
2022-10-25 23:35:57 -04:00
|
|
|
fn report_err<R: Reporter>(
|
2022-10-26 11:29:26 -04:00
|
|
|
e: &RecoverableError,
|
2022-10-25 23:44:53 -04:00
|
|
|
reporter: &mut R,
|
2022-10-20 15:38:59 -04:00
|
|
|
ebuf: &mut String,
|
2022-10-26 11:29:26 -04:00
|
|
|
) -> Result<(), UnrecoverableError> {
|
2022-10-20 15:38:59 -04:00
|
|
|
// See below note about buffering.
|
|
|
|
ebuf.clear();
|
|
|
|
writeln!(ebuf, "{}", reporter.render(e))?;
|
|
|
|
println!("{ebuf}");
|
|
|
|
|
|
|
|
Ok(())
|
|
|
|
}
|
|
|
|
|
2022-10-25 23:35:57 -04:00
|
|
|
// TODO: We're just echoing back out XIR,
|
|
|
|
// which will be the same sans some formatting.
|
|
|
|
let src = &mut src_reader(src_path, &escaper)?
|
|
|
|
.inspect(copy_xml_to(fout, &escaper))
|
2022-10-26 11:29:26 -04:00
|
|
|
.map(|result| result.map_err(RecoverableError::from));
|
2022-10-25 23:35:57 -04:00
|
|
|
|
2022-12-13 13:46:31 -05:00
|
|
|
// TODO: Determine a good default capacity once we have this populated
|
|
|
|
// and can come up with some heuristics.
|
|
|
|
let asg = DefaultAsg::with_capacity(1024, 2048);
|
|
|
|
|
2022-10-19 14:58:05 -04:00
|
|
|
let _ = Lower::<
|
|
|
|
ParsedObject<XirToken, XirError>,
|
|
|
|
XirToXirf<64, RefinedText>,
|
2022-10-25 23:35:57 -04:00
|
|
|
_,
|
2022-10-26 11:29:26 -04:00
|
|
|
>::lower::<_, UnrecoverableError>(src, |toks| {
|
tamer: NIR re-simplification
Alright, this has been a rather tortured experience. The previous commit
began to state what is going on.
This is reversing a lot of prior work, with the benefit of
hindsight. Little bit of history, for the people who will probably never
read this, but who knows:
As noted at the top of NIR, I've long wanted a very simple set of general
primitives where all desugaring is done by the template system---TAME is a
metalanguage after all. Therefore, I never intended on having any explicit
desugaring operations.
But I didn't have time to augment the template system to support parsing on
attribute strings (nor am I sure if I want to do such a thing), so it became
clear that interpolation would be a pass in the compiler. Which led me to
the idea of a desugaring pass.
That in turn spiraled into representing the status of whether NIR was
desugared, and separating primitives, etc, which lead to a lot of additional
complexity. The idea was to have a Sugared and Plan NIR, and further within
them have symbols that have latent types---if they require interpolation,
then those types would be deferred until after template expansion.
The obvious problem there is that now:
1. NIR has the complexity of various types; and
2. Types were tightly coupled with NIR and how it was defined in terms of
XML destructuring.
The first attempt at this didn't go well: it was clear that the symbol types
would make mapping from Sugared to Plain NIR very complicated. Further,
since NIR had any number of symbols per Sugared NIR token, interpolation was
a pain in the ass.
So that lead to the idea of interpolating at the _attribute_ level. That
seemed to be going well at first, until I realized that the token stream of
the attribute parser does not match that of the element parser, and so that
general solution fell apart. It wouldn't have been great anyway, since then
interpolation was _also_ coupled to the destructuring of the document.
Another goal of mine has been to decouple TAME from XML. Not because I want
to move away from XML (if I did, I'd want S-expressions, not YAML, but I
don't think the team would go for that). This decoupling would allow the
use of a subset of the syntax of TAME in other places, like CSVMs and YAML
test cases, for example, if appropriate.
This approach makes sense: the grammar of TAME isn't XML, it's _embedded
within_ XML. The XML layer has to be stripped to expose it.
And so that's what NIR is now evolving into---the stripped, bare
repsentation of TAME's language. That also has other benefits too down the
line, like a REPL where you can use any number of syntaxes. I intend for
NIR to be stack-based, which I'd find to be intuitive for manipulating and
querying packages, but it could have any number of grammars, including
Prolog-like for expressing Horn clauses and querying with a
Prolog/Datalog-like syntax. But that's for the future...
The next issue is that of attribute types. If we have a better language for
NIR, then the types can be associated with the NIR tokens, rather than
having to associate each symbol with raw type data, which doesn't make a
whole lot of sense. That also allows for AIR to better infer types and
determine what they ought to be, and further makes checking types after
template application natural, since it's not part of NIR at all. It also
means the template system can naturally apply to any sources.
Now, if we take that final step further, and make attributes streaming
instead of aggregating, we're back to a streaming pipeline where all
aggregation takes place on the ASG (which also resolves the memcpy concerns
worked around previously, also further simplifying `ele_parse` again, though
it sucks that I wasted that time). And, without the symbol types getting
in the way, since now NIR has types more fundamentally associated with
tokens, we're able to interpolate on a token stream using simple SPairs,
like I always hoped (and reverted back to in the previous commit).
Oh, and what about that desugaring pass? There's the issue of how to
represent such a thing in the type system---ideally we'd know statically
that desugaring always lowers into a more primitive NIR that reduces the
mapping that needs to be done to AIR. But that adds complexity, as
mentioned above. The alternative is to just use the templat system, as I
originally wanted to, and resolve shortcomings by augmenting the template
system to be able to handle it. That not only keeps NIR and the compiler
much simpler, but exposes more powerful tools to developers via TAME's
metalanguage, if such a thing is appropriate.
Anyway, this creates a system that's far more intuitive, and far
simpler. It does kick the can to AIR, but that's okay, since it's also
better positioned to deal with it.
Everything I wrote above is a thought dump and has not been proof-read, so
good luck! And lets hope this finally works out...it's actually feeling
good this time. The journey was necessary to discover and justify what came
out of it---everything I'm stripping away was like a cocoon, and within it
is a more beautiful and more elegant TAME.
DEV-13346
2022-11-28 13:35:10 -05:00
|
|
|
Lower::<XirToXirf<64, RefinedText>, XirfToNir, _>::lower(toks, |nir| {
|
2022-12-05 16:32:00 -05:00
|
|
|
Lower::<XirfToNir, InterpolateNir, _>::lower(nir, |nir| {
|
2022-12-13 13:34:52 -05:00
|
|
|
Lower::<InterpolateNir, NirToAir, _>::lower(nir, |air| {
|
2022-12-13 13:46:31 -05:00
|
|
|
Lower::<NirToAir, AirAggregate, _>::lower_with_context(
|
|
|
|
air,
|
|
|
|
asg,
|
|
|
|
|end| {
|
|
|
|
end.fold(Ok(()), |x, result| match result {
|
|
|
|
Ok(_) => x,
|
|
|
|
Err(e) => {
|
|
|
|
report_err(&e, reporter, &mut ebuf)?;
|
|
|
|
x
|
|
|
|
}
|
|
|
|
})
|
|
|
|
},
|
|
|
|
)
|
2022-12-05 16:32:00 -05:00
|
|
|
})
|
2022-10-25 23:35:57 -04:00
|
|
|
})
|
|
|
|
})
|
|
|
|
})?;
|
2022-10-19 14:58:05 -04:00
|
|
|
|
2022-10-26 11:29:26 -04:00
|
|
|
match reporter.has_errors() {
|
|
|
|
false => Ok(()),
|
|
|
|
true => Err(UnrecoverableError::ErrorsDuringLowering(
|
2022-10-21 15:35:27 -04:00
|
|
|
reporter.error_count(),
|
2022-10-26 11:29:26 -04:00
|
|
|
)),
|
2022-10-19 14:58:05 -04:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2020-04-08 16:18:18 -04:00
|
|
|
/// Entrypoint for the compiler
|
2022-10-26 11:29:26 -04:00
|
|
|
pub fn main() -> Result<(), UnrecoverableError> {
|
2020-04-08 16:18:18 -04:00
|
|
|
let args: Vec<String> = env::args().collect();
|
|
|
|
let program = &args[0];
|
|
|
|
let opts = get_opts();
|
|
|
|
let usage = opts.usage(&format!("Usage: {} [OPTIONS] INPUT", program));
|
|
|
|
|
|
|
|
match parse_options(opts, args) {
|
2022-10-19 14:58:05 -04:00
|
|
|
Ok(Command::Compile(src_path, _, dest_path)) => {
|
2022-10-25 23:44:53 -04:00
|
|
|
let mut reporter = VisualReporter::new(FsSpanResolver);
|
2020-04-08 16:18:18 -04:00
|
|
|
|
2022-10-25 23:44:53 -04:00
|
|
|
compile(&src_path, &dest_path, &mut reporter).or_else(
|
2022-10-26 11:29:26 -04:00
|
|
|
|e: UnrecoverableError| {
|
|
|
|
// Rendering to a string ensures buffering so that we
|
|
|
|
// don't interleave output between processes.
|
2022-04-27 14:58:50 -04:00
|
|
|
let report = reporter.render(&e).to_string();
|
2022-10-19 14:58:05 -04:00
|
|
|
println!(
|
|
|
|
"{report}\nfatal: failed to compile `{}`",
|
|
|
|
dest_path
|
|
|
|
);
|
2022-04-13 15:11:29 -04:00
|
|
|
|
|
|
|
std::process::exit(1);
|
2022-10-19 14:58:05 -04:00
|
|
|
},
|
|
|
|
)
|
2020-04-08 16:18:18 -04:00
|
|
|
}
|
|
|
|
Ok(Command::Usage) => {
|
|
|
|
println!("{}", usage);
|
|
|
|
std::process::exit(exitcode::OK);
|
|
|
|
}
|
|
|
|
Err(e) => {
|
|
|
|
eprintln!("{}", e);
|
|
|
|
println!("{}", usage);
|
|
|
|
std::process::exit(exitcode::USAGE);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
/// Get 'Options'
|
|
|
|
///
|
|
|
|
/// ```
|
|
|
|
/// use getopts::Options;
|
|
|
|
///
|
|
|
|
/// let opts = get_opts();
|
|
|
|
/// ```
|
|
|
|
fn get_opts() -> Options {
|
|
|
|
let mut opts = Options::new();
|
|
|
|
opts.optopt("o", "output", "set output file name", "NAME");
|
|
|
|
opts.optopt("", "emit", "set output type", "xmlo");
|
|
|
|
opts.optflag("h", "help", "print this help menu");
|
|
|
|
|
|
|
|
opts
|
|
|
|
}
|
|
|
|
|
|
|
|
/// Option parser
|
|
|
|
fn parse_options(opts: Options, args: Vec<String>) -> Result<Command, Fail> {
|
|
|
|
let matches = match opts.parse(&args[1..]) {
|
|
|
|
Ok(m) => m,
|
|
|
|
Err(f) => {
|
|
|
|
return Err(f);
|
|
|
|
}
|
|
|
|
};
|
|
|
|
|
|
|
|
if matches.opt_present("h") {
|
|
|
|
return Ok(Command::Usage);
|
|
|
|
}
|
|
|
|
|
|
|
|
let input = match matches.free.len() {
|
|
|
|
0 => return Err(Fail::OptionMissing(String::from("INPUT"))),
|
|
|
|
1 => matches.free[0].clone(),
|
|
|
|
_ => return Err(Fail::UnrecognizedOption(matches.free[1].clone())),
|
|
|
|
};
|
|
|
|
|
|
|
|
let emit = match matches.opt_str("emit") {
|
|
|
|
Some(m) => match &m[..] {
|
|
|
|
"xmlo" => m,
|
|
|
|
_ => {
|
|
|
|
return Err(Fail::ArgumentMissing(String::from("--emit xmlo")))
|
|
|
|
}
|
|
|
|
},
|
|
|
|
None => {
|
|
|
|
return Err(Fail::OptionMissing(String::from("--emit xmlo")));
|
|
|
|
}
|
|
|
|
};
|
|
|
|
|
|
|
|
let output = match matches.opt_str("o") {
|
|
|
|
Some(m) => m,
|
|
|
|
// we check that the extension is "xml" later
|
|
|
|
None => format!("{}o", input),
|
|
|
|
};
|
|
|
|
|
|
|
|
Ok(Command::Compile(input, emit, output))
|
|
|
|
}
|
|
|
|
|
2022-10-26 11:29:26 -04:00
|
|
|
/// Toplevel `tamec` error representing a failure to complete the requested
|
|
|
|
/// operation successfully.
|
|
|
|
///
|
|
|
|
/// These are errors that will result in aborting execution and exiting with
|
|
|
|
/// a non-zero status.
|
|
|
|
/// Contrast this with [`RecoverableError`],
|
|
|
|
/// which is reported real-time to the user and _does not_ cause the
|
|
|
|
/// program to abort until the end of the compilation unit.
|
|
|
|
#[derive(Debug)]
|
|
|
|
pub enum UnrecoverableError {
|
|
|
|
Io(io::Error),
|
|
|
|
Fmt(fmt::Error),
|
|
|
|
XirWriterError(xir::writer::Error),
|
|
|
|
ErrorsDuringLowering(ErrorCount),
|
2022-12-13 13:46:31 -05:00
|
|
|
FinalizeError(FinalizeError),
|
2022-10-26 11:29:26 -04:00
|
|
|
}
|
|
|
|
|
|
|
|
/// Number of errors that occurred during this compilation unit.
|
|
|
|
///
|
|
|
|
/// Let's hope that this is large enough for the number of errors you may
|
|
|
|
/// have in your code.
|
|
|
|
type ErrorCount = usize;
|
|
|
|
|
|
|
|
/// An error that occurs during the lowering pipeline that may be recovered
|
|
|
|
/// from to continue parsing and collection of additional errors.
|
2022-04-13 15:11:29 -04:00
|
|
|
///
|
|
|
|
/// This represents the aggregation of all possible errors that can occur
|
2022-10-26 11:29:26 -04:00
|
|
|
/// during lowering.
|
2022-04-13 15:11:29 -04:00
|
|
|
/// This cannot include panics,
|
|
|
|
/// but efforts have been made to reduce panics to situations that
|
|
|
|
/// represent the equivalent of assertions.
|
2022-10-26 11:29:26 -04:00
|
|
|
///
|
|
|
|
/// These errors are distinct from [`UnrecoverableError`],
|
|
|
|
/// which represents the errors that could be returned to the toplevel
|
|
|
|
/// `main`,
|
|
|
|
/// because these errors are intended to be reported to the user _and then
|
|
|
|
/// recovered from_ so that compilation may continue and more errors may
|
|
|
|
/// be collected;
|
|
|
|
/// nobody wants a compiler that reports one error at a time.
|
|
|
|
///
|
|
|
|
/// Note that an recoverable error,
|
|
|
|
/// under a normal compilation strategy,
|
|
|
|
/// will result in an [`UnrecoverableError::ErrorsDuringLowering`] at the
|
|
|
|
/// end of the compilation unit.
|
2022-04-13 15:11:29 -04:00
|
|
|
#[derive(Debug)]
|
2022-10-26 11:29:26 -04:00
|
|
|
pub enum RecoverableError {
|
2022-06-02 10:30:44 -04:00
|
|
|
XirParseError(ParseError<UnknownToken, xir::Error>),
|
tamer: Introduce NIR (accepting only)
This introduces NIR, but only as an accepting grammar; it doesn't yet emit
the NIR IR, beyond TODOs.
This modifies `tamec` to, while copying XIR, also attempt to lower NIR to
produce parser errors, if any. It does not yet fail compilation, as I just
want to be cautious and observe that everything's working properly for a
little while as people use it, before I potentially break builds.
This is the culmination of months of supporting effort. The NIR grammar is
derived from our existing TAME sources internally, which I use for now as a
test case until I introduce test cases directly into TAMER later on (I'd do
it now, if I hadn't spent so much time on this; I'll start introducing tests
as I begin emitting NIR tokens). This is capable of fully parsing our
largest system with >900 packages, as well as `core`.
`tamec`'s lowering is a mess; that'll be cleaned up in future commits. The
same can be said about `tameld`.
NIR's grammar has some initial documentation, but this will improve over
time as well.
The generated docs still need some improvement, too, especially with
generated identifiers; I just want to get this out here for testing.
DEV-7145
2022-08-29 15:28:03 -04:00
|
|
|
XirfParseError(ParseError<XirToken, XirToXirfError>),
|
|
|
|
NirParseError(ParseError<XirfToken<RefinedText>, XirfToNirError>),
|
2022-12-05 16:32:00 -05:00
|
|
|
InterpError(ParseError<Nir, InterpError>),
|
2022-12-13 13:34:52 -05:00
|
|
|
NirToAirError(ParseError<Nir, NirToAirError>),
|
|
|
|
AirAggregateError(ParseError<Air, AsgError>),
|
2022-04-13 15:11:29 -04:00
|
|
|
}
|
|
|
|
|
2022-10-26 11:29:26 -04:00
|
|
|
impl From<io::Error> for UnrecoverableError {
|
2022-04-13 15:11:29 -04:00
|
|
|
fn from(e: io::Error) -> Self {
|
|
|
|
Self::Io(e)
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2022-10-26 11:29:26 -04:00
|
|
|
impl From<fmt::Error> for UnrecoverableError {
|
|
|
|
fn from(e: fmt::Error) -> Self {
|
|
|
|
Self::Fmt(e)
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
impl From<xir::writer::Error> for UnrecoverableError {
|
|
|
|
fn from(e: xir::writer::Error) -> Self {
|
|
|
|
Self::XirWriterError(e)
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2022-12-13 13:46:31 -05:00
|
|
|
impl From<FinalizeError> for UnrecoverableError {
|
|
|
|
fn from(e: FinalizeError) -> Self {
|
|
|
|
Self::FinalizeError(e)
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2022-10-26 11:29:26 -04:00
|
|
|
impl From<ParseError<UnknownToken, xir::Error>> for RecoverableError {
|
2022-06-02 10:30:44 -04:00
|
|
|
fn from(e: ParseError<UnknownToken, xir::Error>) -> Self {
|
|
|
|
Self::XirParseError(e)
|
2022-04-13 15:11:29 -04:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2022-10-26 11:29:26 -04:00
|
|
|
impl From<ParseError<XirToken, XirToXirfError>> for RecoverableError {
|
tamer: Introduce NIR (accepting only)
This introduces NIR, but only as an accepting grammar; it doesn't yet emit
the NIR IR, beyond TODOs.
This modifies `tamec` to, while copying XIR, also attempt to lower NIR to
produce parser errors, if any. It does not yet fail compilation, as I just
want to be cautious and observe that everything's working properly for a
little while as people use it, before I potentially break builds.
This is the culmination of months of supporting effort. The NIR grammar is
derived from our existing TAME sources internally, which I use for now as a
test case until I introduce test cases directly into TAMER later on (I'd do
it now, if I hadn't spent so much time on this; I'll start introducing tests
as I begin emitting NIR tokens). This is capable of fully parsing our
largest system with >900 packages, as well as `core`.
`tamec`'s lowering is a mess; that'll be cleaned up in future commits. The
same can be said about `tameld`.
NIR's grammar has some initial documentation, but this will improve over
time as well.
The generated docs still need some improvement, too, especially with
generated identifiers; I just want to get this out here for testing.
DEV-7145
2022-08-29 15:28:03 -04:00
|
|
|
fn from(e: ParseError<XirToken, XirToXirfError>) -> Self {
|
|
|
|
Self::XirfParseError(e)
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2022-10-19 10:00:08 -04:00
|
|
|
impl From<ParseError<XirfToken<RefinedText>, XirfToNirError>>
|
|
|
|
for RecoverableError
|
|
|
|
{
|
tamer: Introduce NIR (accepting only)
This introduces NIR, but only as an accepting grammar; it doesn't yet emit
the NIR IR, beyond TODOs.
This modifies `tamec` to, while copying XIR, also attempt to lower NIR to
produce parser errors, if any. It does not yet fail compilation, as I just
want to be cautious and observe that everything's working properly for a
little while as people use it, before I potentially break builds.
This is the culmination of months of supporting effort. The NIR grammar is
derived from our existing TAME sources internally, which I use for now as a
test case until I introduce test cases directly into TAMER later on (I'd do
it now, if I hadn't spent so much time on this; I'll start introducing tests
as I begin emitting NIR tokens). This is capable of fully parsing our
largest system with >900 packages, as well as `core`.
`tamec`'s lowering is a mess; that'll be cleaned up in future commits. The
same can be said about `tameld`.
NIR's grammar has some initial documentation, but this will improve over
time as well.
The generated docs still need some improvement, too, especially with
generated identifiers; I just want to get this out here for testing.
DEV-7145
2022-08-29 15:28:03 -04:00
|
|
|
fn from(e: ParseError<XirfToken<RefinedText>, XirfToNirError>) -> Self {
|
|
|
|
Self::NirParseError(e)
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2022-12-05 16:32:00 -05:00
|
|
|
impl From<ParseError<Nir, InterpError>> for RecoverableError {
|
|
|
|
fn from(e: ParseError<Nir, InterpError>) -> Self {
|
|
|
|
Self::InterpError(e)
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2022-12-13 13:34:52 -05:00
|
|
|
impl From<ParseError<Nir, NirToAirError>> for RecoverableError {
|
|
|
|
fn from(e: ParseError<Nir, NirToAirError>) -> Self {
|
|
|
|
Self::NirToAirError(e)
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
impl From<ParseError<Air, AsgError>> for RecoverableError {
|
|
|
|
fn from(e: ParseError<Air, AsgError>) -> Self {
|
|
|
|
Self::AirAggregateError(e)
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2022-10-26 11:29:26 -04:00
|
|
|
impl Display for UnrecoverableError {
|
|
|
|
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
|
2022-12-13 13:46:31 -05:00
|
|
|
use UnrecoverableError::*;
|
|
|
|
|
2022-10-26 11:29:26 -04:00
|
|
|
match self {
|
2022-12-13 13:46:31 -05:00
|
|
|
Io(e) => Display::fmt(e, f),
|
|
|
|
Fmt(e) => Display::fmt(e, f),
|
|
|
|
XirWriterError(e) => Display::fmt(e, f),
|
|
|
|
FinalizeError(e) => Display::fmt(e, f),
|
2022-04-13 15:11:29 -04:00
|
|
|
|
2022-10-26 11:29:26 -04:00
|
|
|
// TODO: Use formatter for dynamic "error(s)"
|
2022-12-13 13:46:31 -05:00
|
|
|
ErrorsDuringLowering(err_count) => {
|
2022-10-26 11:29:26 -04:00
|
|
|
write!(f, "aborting due to previous {err_count} error(s)",)
|
|
|
|
}
|
|
|
|
}
|
2022-04-13 15:11:29 -04:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2022-10-26 11:29:26 -04:00
|
|
|
impl Display for RecoverableError {
|
2022-04-13 15:11:29 -04:00
|
|
|
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
|
2022-12-13 13:34:52 -05:00
|
|
|
use RecoverableError::*;
|
|
|
|
|
2022-04-13 15:11:29 -04:00
|
|
|
match self {
|
2022-12-13 13:34:52 -05:00
|
|
|
XirParseError(e) => Display::fmt(e, f),
|
|
|
|
XirfParseError(e) => Display::fmt(e, f),
|
|
|
|
NirParseError(e) => Display::fmt(e, f),
|
|
|
|
InterpError(e) => Display::fmt(e, f),
|
|
|
|
NirToAirError(e) => Display::fmt(e, f),
|
|
|
|
AirAggregateError(e) => Display::fmt(e, f),
|
2022-04-13 15:11:29 -04:00
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2022-10-26 11:29:26 -04:00
|
|
|
impl Error for UnrecoverableError {
|
2022-04-13 15:11:29 -04:00
|
|
|
fn source(&self) -> Option<&(dyn Error + 'static)> {
|
2022-12-13 13:46:31 -05:00
|
|
|
use UnrecoverableError::*;
|
|
|
|
|
2022-04-13 15:11:29 -04:00
|
|
|
match self {
|
2022-12-13 13:46:31 -05:00
|
|
|
Io(e) => Some(e),
|
|
|
|
Fmt(e) => Some(e),
|
|
|
|
XirWriterError(e) => Some(e),
|
|
|
|
ErrorsDuringLowering(_) => None,
|
|
|
|
FinalizeError(e) => Some(e),
|
2022-10-26 11:29:26 -04:00
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
impl Error for RecoverableError {
|
|
|
|
fn source(&self) -> Option<&(dyn Error + 'static)> {
|
2022-12-13 13:34:52 -05:00
|
|
|
use RecoverableError::*;
|
|
|
|
|
2022-10-26 11:29:26 -04:00
|
|
|
match self {
|
2022-12-13 13:34:52 -05:00
|
|
|
XirParseError(e) => Some(e),
|
|
|
|
XirfParseError(e) => Some(e),
|
|
|
|
NirParseError(e) => Some(e),
|
|
|
|
InterpError(e) => Some(e),
|
|
|
|
NirToAirError(e) => Some(e),
|
|
|
|
AirAggregateError(e) => Some(e),
|
2022-04-13 15:11:29 -04:00
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2022-10-26 11:29:26 -04:00
|
|
|
impl Diagnostic for UnrecoverableError {
|
|
|
|
fn describe(&self) -> Vec<AnnotatedSpan> {
|
2022-12-13 13:46:31 -05:00
|
|
|
use UnrecoverableError::*;
|
|
|
|
|
2022-10-26 11:29:26 -04:00
|
|
|
match self {
|
2022-12-13 13:46:31 -05:00
|
|
|
FinalizeError(e) => e.describe(),
|
|
|
|
|
2022-10-26 11:29:26 -04:00
|
|
|
// Fall back to `Display`
|
2022-12-13 13:46:31 -05:00
|
|
|
Io(_) | Fmt(_) | XirWriterError(_) | ErrorsDuringLowering(_) => {
|
|
|
|
vec![]
|
|
|
|
}
|
2022-10-26 11:29:26 -04:00
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
impl Diagnostic for RecoverableError {
|
2022-04-13 15:11:29 -04:00
|
|
|
fn describe(&self) -> Vec<AnnotatedSpan> {
|
2022-12-13 13:34:52 -05:00
|
|
|
use RecoverableError::*;
|
|
|
|
|
2022-04-13 15:11:29 -04:00
|
|
|
match self {
|
2022-12-13 13:34:52 -05:00
|
|
|
XirParseError(e) => e.describe(),
|
|
|
|
XirfParseError(e) => e.describe(),
|
|
|
|
NirParseError(e) => e.describe(),
|
|
|
|
InterpError(e) => e.describe(),
|
|
|
|
NirToAirError(e) => e.describe(),
|
|
|
|
AirAggregateError(e) => e.describe(),
|
2022-04-13 15:11:29 -04:00
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2020-04-08 16:18:18 -04:00
|
|
|
#[cfg(test)]
|
|
|
|
mod test {
|
|
|
|
use super::*;
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
fn parse_options_help() {
|
|
|
|
let opts = get_opts();
|
|
|
|
let result = parse_options(
|
|
|
|
opts,
|
|
|
|
vec![String::from("program"), String::from("-h")],
|
|
|
|
);
|
|
|
|
|
|
|
|
match result {
|
|
|
|
Ok(Command::Usage) => {}
|
|
|
|
_ => panic!("Long help option did not parse"),
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
fn parse_options_help_long() {
|
|
|
|
let opts = get_opts();
|
|
|
|
let result = parse_options(
|
|
|
|
opts,
|
|
|
|
vec![String::from("program"), String::from("--help")],
|
|
|
|
);
|
|
|
|
|
|
|
|
match result {
|
|
|
|
Ok(Command::Usage) => {}
|
|
|
|
_ => panic!("Help option did not parse"),
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
fn parse_options_invalid() {
|
|
|
|
let opts = get_opts();
|
|
|
|
let result = parse_options(
|
|
|
|
opts,
|
|
|
|
vec![String::from("program"), String::from("-q")],
|
|
|
|
);
|
|
|
|
|
|
|
|
match result {
|
|
|
|
Err(Fail::UnrecognizedOption(_)) => {}
|
|
|
|
_ => panic!("Invalid option not caught"),
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
fn parse_options_missing_input() {
|
|
|
|
let opts = get_opts();
|
|
|
|
let result = parse_options(opts, vec![String::from("program")]);
|
|
|
|
|
|
|
|
match result {
|
|
|
|
Err(Fail::OptionMissing(message)) => {
|
|
|
|
assert_eq!("INPUT", message);
|
|
|
|
}
|
|
|
|
_ => panic!("Missing input not caught"),
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
fn parse_options_missing_emit() {
|
|
|
|
let opts = get_opts();
|
|
|
|
let result = parse_options(
|
|
|
|
opts,
|
|
|
|
vec![String::from("program"), String::from("filename")],
|
|
|
|
);
|
|
|
|
|
|
|
|
match result {
|
|
|
|
Err(Fail::OptionMissing(message)) => {
|
|
|
|
assert_eq!("--emit xmlo", message);
|
|
|
|
}
|
|
|
|
_ => panic!("Missing emit not caught"),
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
fn parse_options_invalid_emit() {
|
|
|
|
let opts = get_opts();
|
|
|
|
let result = parse_options(
|
|
|
|
opts,
|
|
|
|
vec![
|
|
|
|
String::from("program"),
|
|
|
|
String::from("filename.xml"),
|
|
|
|
String::from("--emit"),
|
|
|
|
String::from("foo"),
|
|
|
|
],
|
|
|
|
);
|
|
|
|
|
|
|
|
match result {
|
|
|
|
Err(Fail::ArgumentMissing(message)) => {
|
|
|
|
assert_eq!("--emit xmlo", message);
|
|
|
|
}
|
|
|
|
_ => panic!("Invalid emit not caught"),
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
fn parse_options_too_many_args() {
|
|
|
|
let opts = get_opts();
|
|
|
|
let result = parse_options(
|
|
|
|
opts,
|
|
|
|
vec![
|
|
|
|
String::from("program"),
|
|
|
|
String::from("foo"),
|
|
|
|
String::from("--emit"),
|
|
|
|
String::from("bar"),
|
|
|
|
String::from("baz"),
|
|
|
|
],
|
|
|
|
);
|
|
|
|
|
|
|
|
match result {
|
|
|
|
Err(Fail::UnrecognizedOption(message)) => {
|
|
|
|
assert_eq!("baz", message);
|
|
|
|
}
|
|
|
|
_ => panic!("Extra option not caught"),
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
fn parse_options_valid() {
|
|
|
|
let opts = get_opts();
|
|
|
|
let xmlo = String::from("xmlo");
|
|
|
|
let result = parse_options(
|
|
|
|
opts,
|
|
|
|
vec![
|
|
|
|
String::from("program"),
|
|
|
|
String::from("foo.xml"),
|
|
|
|
String::from("--emit"),
|
|
|
|
xmlo,
|
|
|
|
],
|
|
|
|
);
|
|
|
|
|
|
|
|
match result {
|
|
|
|
Ok(Command::Compile(infile, xmlo, outfile)) => {
|
|
|
|
assert_eq!("foo.xml", infile);
|
|
|
|
assert_eq!("foo.xmlo", outfile);
|
|
|
|
assert_eq!("xmlo", xmlo);
|
|
|
|
}
|
|
|
|
_ => panic!("Unexpected result"),
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
fn parse_options_valid_custom_out() {
|
|
|
|
let opts = get_opts();
|
|
|
|
let xmlo = String::from("xmlo");
|
|
|
|
let result = parse_options(
|
|
|
|
opts,
|
|
|
|
vec![
|
|
|
|
String::from("program"),
|
|
|
|
String::from("foo.xml"),
|
|
|
|
String::from("--emit"),
|
|
|
|
xmlo,
|
|
|
|
String::from("-o"),
|
|
|
|
String::from("foo.xmli"),
|
|
|
|
],
|
|
|
|
);
|
|
|
|
|
|
|
|
match result {
|
|
|
|
Ok(Command::Compile(infile, xmlo, outfile)) => {
|
|
|
|
assert_eq!("foo.xml", infile);
|
|
|
|
assert_eq!("foo.xmli", outfile);
|
|
|
|
assert_eq!("xmlo", xmlo);
|
|
|
|
}
|
|
|
|
_ => panic!("Unexpected result"),
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
fn parse_options_valid_custom_out_long() {
|
|
|
|
let opts = get_opts();
|
|
|
|
let xmlo = String::from("xmlo");
|
|
|
|
let result = parse_options(
|
|
|
|
opts,
|
|
|
|
vec![
|
|
|
|
String::from("program"),
|
|
|
|
String::from("foo.xml"),
|
|
|
|
String::from("--emit"),
|
|
|
|
xmlo,
|
|
|
|
String::from("--output"),
|
|
|
|
String::from("foo.xmli"),
|
|
|
|
],
|
|
|
|
);
|
|
|
|
|
|
|
|
match result {
|
|
|
|
Ok(Command::Compile(infile, xmlo, outfile)) => {
|
|
|
|
assert_eq!("foo.xml", infile);
|
|
|
|
assert_eq!("foo.xmli", outfile);
|
|
|
|
assert_eq!("xmlo", xmlo);
|
|
|
|
}
|
|
|
|
_ => panic!("Unexpected result"),
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|