moved crates in lib/ to src/, renamed crates, modified some files' text (#660)

moved crates in lib/ to src/, renamed crates, modified some files' text (#660)
This commit is contained in:
lazypassion
2019-01-28 18:56:54 -05:00
committed by Dan Gohman
parent 54959cf5bb
commit 747ad3c4c5
508 changed files with 94 additions and 92 deletions

View File

@@ -0,0 +1,18 @@
[package]
authors = ["The Cranelift Project Developers"]
name = "cranelift-reader"
version = "0.28.0"
description = "Cranelift textual IR reader"
license = "Apache-2.0 WITH LLVM-exception"
documentation = "https://cranelift.readthedocs.io/"
repository = "https://github.com/CraneStation/cranelift"
readme = "README.md"
edition = "2018"
[dependencies]
cranelift-codegen = { path = "../cranelift-codegen", version = "0.28.0" }
target-lexicon = "0.2.0"
[badges]
maintenance = { status = "experimental" }
travis-ci = { repository = "CraneStation/cranelift" }

220
cranelift/reader/LICENSE Normal file
View File

@@ -0,0 +1,220 @@
Apache License
Version 2.0, January 2004
http://www.apache.org/licenses/
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
1. Definitions.
"License" shall mean the terms and conditions for use, reproduction,
and distribution as defined by Sections 1 through 9 of this document.
"Licensor" shall mean the copyright owner or entity authorized by
the copyright owner that is granting the License.
"Legal Entity" shall mean the union of the acting entity and all
other entities that control, are controlled by, or are under common
control with that entity. For the purposes of this definition,
"control" means (i) the power, direct or indirect, to cause the
direction or management of such entity, whether by contract or
otherwise, or (ii) ownership of fifty percent (50%) or more of the
outstanding shares, or (iii) beneficial ownership of such entity.
"You" (or "Your") shall mean an individual or Legal Entity
exercising permissions granted by this License.
"Source" form shall mean the preferred form for making modifications,
including but not limited to software source code, documentation
source, and configuration files.
"Object" form shall mean any form resulting from mechanical
transformation or translation of a Source form, including but
not limited to compiled object code, generated documentation,
and conversions to other media types.
"Work" shall mean the work of authorship, whether in Source or
Object form, made available under the License, as indicated by a
copyright notice that is included in or attached to the work
(an example is provided in the Appendix below).
"Derivative Works" shall mean any work, whether in Source or Object
form, that is based on (or derived from) the Work and for which the
editorial revisions, annotations, elaborations, or other modifications
represent, as a whole, an original work of authorship. For the purposes
of this License, Derivative Works shall not include works that remain
separable from, or merely link (or bind by name) to the interfaces of,
the Work and Derivative Works thereof.
"Contribution" shall mean any work of authorship, including
the original version of the Work and any modifications or additions
to that Work or Derivative Works thereof, that is intentionally
submitted to Licensor for inclusion in the Work by the copyright owner
or by an individual or Legal Entity authorized to submit on behalf of
the copyright owner. For the purposes of this definition, "submitted"
means any form of electronic, verbal, or written communication sent
to the Licensor or its representatives, including but not limited to
communication on electronic mailing lists, source code control systems,
and issue tracking systems that are managed by, or on behalf of, the
Licensor for the purpose of discussing and improving the Work, but
excluding communication that is conspicuously marked or otherwise
designated in writing by the copyright owner as "Not a Contribution."
"Contributor" shall mean Licensor and any individual or Legal Entity
on behalf of whom a Contribution has been received by Licensor and
subsequently incorporated within the Work.
2. Grant of Copyright License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
copyright license to reproduce, prepare Derivative Works of,
publicly display, publicly perform, sublicense, and distribute the
Work and such Derivative Works in Source or Object form.
3. Grant of Patent License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
(except as stated in this section) patent license to make, have made,
use, offer to sell, sell, import, and otherwise transfer the Work,
where such license applies only to those patent claims licensable
by such Contributor that are necessarily infringed by their
Contribution(s) alone or by combination of their Contribution(s)
with the Work to which such Contribution(s) was submitted. If You
institute patent litigation against any entity (including a
cross-claim or counterclaim in a lawsuit) alleging that the Work
or a Contribution incorporated within the Work constitutes direct
or contributory patent infringement, then any patent licenses
granted to You under this License for that Work shall terminate
as of the date such litigation is filed.
4. Redistribution. You may reproduce and distribute copies of the
Work or Derivative Works thereof in any medium, with or without
modifications, and in Source or Object form, provided that You
meet the following conditions:
(a) You must give any other recipients of the Work or
Derivative Works a copy of this License; and
(b) You must cause any modified files to carry prominent notices
stating that You changed the files; and
(c) You must retain, in the Source form of any Derivative Works
that You distribute, all copyright, patent, trademark, and
attribution notices from the Source form of the Work,
excluding those notices that do not pertain to any part of
the Derivative Works; and
(d) If the Work includes a "NOTICE" text file as part of its
distribution, then any Derivative Works that You distribute must
include a readable copy of the attribution notices contained
within such NOTICE file, excluding those notices that do not
pertain to any part of the Derivative Works, in at least one
of the following places: within a NOTICE text file distributed
as part of the Derivative Works; within the Source form or
documentation, if provided along with the Derivative Works; or,
within a display generated by the Derivative Works, if and
wherever such third-party notices normally appear. The contents
of the NOTICE file are for informational purposes only and
do not modify the License. You may add Your own attribution
notices within Derivative Works that You distribute, alongside
or as an addendum to the NOTICE text from the Work, provided
that such additional attribution notices cannot be construed
as modifying the License.
You may add Your own copyright statement to Your modifications and
may provide additional or different license terms and conditions
for use, reproduction, or distribution of Your modifications, or
for any such Derivative Works as a whole, provided Your use,
reproduction, and distribution of the Work otherwise complies with
the conditions stated in this License.
5. Submission of Contributions. Unless You explicitly state otherwise,
any Contribution intentionally submitted for inclusion in the Work
by You to the Licensor shall be under the terms and conditions of
this License, without any additional terms or conditions.
Notwithstanding the above, nothing herein shall supersede or modify
the terms of any separate license agreement you may have executed
with Licensor regarding such Contributions.
6. Trademarks. This License does not grant permission to use the trade
names, trademarks, service marks, or product names of the Licensor,
except as required for reasonable and customary use in describing the
origin of the Work and reproducing the content of the NOTICE file.
7. Disclaimer of Warranty. Unless required by applicable law or
agreed to in writing, Licensor provides the Work (and each
Contributor provides its Contributions) on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
implied, including, without limitation, any warranties or conditions
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
PARTICULAR PURPOSE. You are solely responsible for determining the
appropriateness of using or redistributing the Work and assume any
risks associated with Your exercise of permissions under this License.
8. Limitation of Liability. In no event and under no legal theory,
whether in tort (including negligence), contract, or otherwise,
unless required by applicable law (such as deliberate and grossly
negligent acts) or agreed to in writing, shall any Contributor be
liable to You for damages, including any direct, indirect, special,
incidental, or consequential damages of any character arising as a
result of this License or out of the use or inability to use the
Work (including but not limited to damages for loss of goodwill,
work stoppage, computer failure or malfunction, or any and all
other commercial damages or losses), even if such Contributor
has been advised of the possibility of such damages.
9. Accepting Warranty or Additional Liability. While redistributing
the Work or Derivative Works thereof, You may choose to offer,
and charge a fee for, acceptance of support, warranty, indemnity,
or other liability obligations and/or rights consistent with this
License. However, in accepting such obligations, You may act only
on Your own behalf and on Your sole responsibility, not on behalf
of any other Contributor, and only if You agree to indemnify,
defend, and hold each Contributor harmless for any liability
incurred by, or claims asserted against, such Contributor by reason
of your accepting any such warranty or additional liability.
END OF TERMS AND CONDITIONS
APPENDIX: How to apply the Apache License to your work.
To apply the Apache License to your work, attach the following
boilerplate notice, with the fields enclosed by brackets "[]"
replaced with your own identifying information. (Don't include
the brackets!) The text should be enclosed in the appropriate
comment syntax for the file format. We also recommend that a
file or class name and description of purpose be included on the
same "printed page" as the copyright notice for easier
identification within third-party archives.
Copyright [yyyy] [name of copyright owner]
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.
--- LLVM Exceptions to the Apache 2.0 License ----
As an exception, if, as a result of your compiling your source code, portions
of this Software are embedded into an Object form of such source code, you
may redistribute such embedded portions in such Object form without complying
with the conditions of Sections 4(a), 4(b) and 4(d) of the License.
In addition, if you combine or link compiled forms of this Software with
software that is licensed under the GPLv2 ("Combined Software") and if a
court of competent jurisdiction determines that the patent provision (Section
3), the indemnity provision (Section 9) or other Section of the License
conflicts with the conditions of the GPLv2, you may retroactively and
prospectively choose to deem waived or otherwise exclude such Section(s) of
the License, but only in their entirety and only with respect to the Combined
Software.

View File

@@ -0,0 +1,3 @@
This crate library supports reading .clif files. This functionality is needed
for testing [Cranelift](https://crates.io/crates/cranelift), but is not essential
for a JIT compiler.

View File

@@ -0,0 +1,52 @@
//! Define the `Location`, `ParseError`, and `ParseResult` types.
#![macro_use]
use std::fmt;
/// The location of a `Token` or `Error`.
#[derive(Debug, Clone, Copy, PartialEq, Eq, Default)]
pub struct Location {
/// Line number. Command-line arguments are line 0 and source file
/// lines start from 1.
pub line_number: usize,
}
/// A parse error is returned when the parse failed.
#[derive(Debug)]
pub struct ParseError {
/// Location of the error.
pub location: Location,
/// Error message.
pub message: String,
}
impl fmt::Display for ParseError {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
if self.location.line_number == 0 {
write!(f, "command-line arguments: {}", self.message)
} else {
write!(f, "{}: {}", self.location.line_number, self.message)
}
}
}
/// Result of a parser operation. The `ParseError` variant includes a location.
pub type ParseResult<T> = Result<T, ParseError>;
// Create an `Err` variant of `ParseResult<X>` from a location and `format!` args.
macro_rules! err {
( $loc:expr, $msg:expr ) => {
Err($crate::ParseError {
location: $loc.clone(),
message: $msg.to_string(),
})
};
( $loc:expr, $fmt:expr, $( $arg:expr ),+ ) => {
Err($crate::ParseError {
location: $loc.clone(),
message: format!( $fmt, $( $arg ),+ ),
})
};
}

View File

@@ -0,0 +1,65 @@
//! Parsed representation of `set` and `isa` commands.
//!
//! A test case file can contain `set` commands that set ISA-independent settings, and it can
//! contain `isa` commands that select an ISA and applies ISA-specific settings.
//!
//! If a test case file contains `isa` commands, the tests will only be run against the specified
//! ISAs. If the file contains no `isa` commands, the tests will be run against all supported ISAs.
use crate::error::{Location, ParseResult};
use crate::testcommand::TestOption;
use cranelift_codegen::isa::TargetIsa;
use cranelift_codegen::settings::{Configurable, Flags, SetError};
/// The ISA specifications in a `.clif` file.
pub enum IsaSpec {
/// The parsed file does not contain any `isa` commands, but it may contain `set` commands
/// which are reflected in the finished `Flags` object.
None(Flags),
/// The parsed file does contains `isa` commands.
/// Each `isa` command is used to configure a `TargetIsa` trait object.
Some(Vec<Box<TargetIsa>>),
}
impl IsaSpec {
/// If the `IsaSpec` contains exactly 1 `TargetIsa` we return a reference to it
pub fn unique_isa(&self) -> Option<&TargetIsa> {
if let IsaSpec::Some(ref isa_vec) = *self {
if isa_vec.len() == 1 {
return Some(&*isa_vec[0]);
}
}
None
}
}
/// Parse an iterator of command line options and apply them to `config`.
pub fn parse_options<'a, I>(iter: I, config: &mut Configurable, loc: Location) -> ParseResult<()>
where
I: Iterator<Item = &'a str>,
{
for opt in iter.map(TestOption::new) {
match opt {
TestOption::Flag(name) => match config.enable(name) {
Ok(_) => {}
Err(SetError::BadName(name)) => return err!(loc, "unknown flag '{}'", name),
Err(_) => return err!(loc, "not a boolean flag: '{}'", opt),
},
TestOption::Value(name, value) => match config.set(name, value) {
Ok(_) => {}
Err(SetError::BadName(name)) => return err!(loc, "unknown setting '{}'", name),
Err(SetError::BadType) => return err!(loc, "invalid setting type: '{}'", opt),
Err(SetError::BadValue(expected)) => {
return err!(
loc,
"invalid setting value for '{}', expected {}",
opt,
expected
);
}
},
}
}
Ok(())
}

View File

@@ -0,0 +1,646 @@
//! Lexical analysis for .clif files.
use crate::error::Location;
use cranelift_codegen::ir::types;
use cranelift_codegen::ir::{Ebb, Value};
#[allow(unused_imports, deprecated)]
use std::ascii::AsciiExt;
use std::str::CharIndices;
use std::u16;
/// A Token returned from the `Lexer`.
///
/// Some variants may contains references to the original source text, so the `Token` has the same
/// lifetime as the source.
#[derive(Debug, PartialEq, Eq, Clone, Copy)]
pub enum Token<'a> {
Comment(&'a str),
LPar, // '('
RPar, // ')'
LBrace, // '{'
RBrace, // '}'
LBracket, // '['
RBracket, // ']'
Minus, // '-'
Plus, // '+'
Comma, // ','
Dot, // '.'
Colon, // ':'
Equal, // '='
Arrow, // '->'
Float(&'a str), // Floating point immediate
Integer(&'a str), // Integer immediate
Type(types::Type), // i32, f32, b32x4, ...
Value(Value), // v12, v7
Ebb(Ebb), // ebb3
StackSlot(u32), // ss3
GlobalValue(u32), // gv3
Heap(u32), // heap2
Table(u32), // table2
JumpTable(u32), // jt2
FuncRef(u32), // fn2
SigRef(u32), // sig2
UserRef(u32), // u345
Name(&'a str), // %9arbitrary_alphanum, %x3, %0, %function ...
HexSequence(&'a str), // #89AF
Identifier(&'a str), // Unrecognized identifier (opcode, enumerator, ...)
SourceLoc(&'a str), // @00c7
}
/// A `Token` with an associated location.
#[derive(Debug, PartialEq, Eq)]
pub struct LocatedToken<'a> {
pub token: Token<'a>,
pub location: Location,
}
/// Wrap up a `Token` with the given location.
fn token(token: Token, loc: Location) -> Result<LocatedToken, LocatedError> {
Ok(LocatedToken {
token,
location: loc,
})
}
/// An error from the lexical analysis.
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
pub enum LexError {
InvalidChar,
}
/// A `LexError` with an associated Location.
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
pub struct LocatedError {
pub error: LexError,
pub location: Location,
}
/// Wrap up a `LexError` with the given location.
fn error<'a>(error: LexError, loc: Location) -> Result<LocatedToken<'a>, LocatedError> {
Err(LocatedError {
error,
location: loc,
})
}
/// Get the number of decimal digits at the end of `s`.
fn trailing_digits(s: &str) -> usize {
// It's faster to iterate backwards over bytes, and we're only counting ASCII digits.
s.as_bytes()
.iter()
.rev()
.take_while(|&&b| b'0' <= b && b <= b'9')
.count()
}
/// Pre-parse a supposed entity name by splitting it into two parts: A head of lowercase ASCII
/// letters and numeric tail.
pub fn split_entity_name(name: &str) -> Option<(&str, u32)> {
let (head, tail) = name.split_at(name.len() - trailing_digits(name));
if tail.len() > 1 && tail.starts_with('0') {
None
} else {
tail.parse().ok().map(|n| (head, n))
}
}
/// Lexical analysis.
///
/// A `Lexer` reads text from a `&str` and provides a sequence of tokens.
///
/// Also keep track of a line number for error reporting.
///
pub struct Lexer<'a> {
// Complete source being processed.
source: &'a str,
// Iterator into `source`.
chars: CharIndices<'a>,
// Next character to be processed, or `None` at the end.
lookahead: Option<char>,
// Index into `source` of lookahead character.
pos: usize,
// Current line number.
line_number: usize,
}
impl<'a> Lexer<'a> {
pub fn new(s: &'a str) -> Self {
let mut lex = Self {
source: s,
chars: s.char_indices(),
lookahead: None,
pos: 0,
line_number: 1,
};
// Advance to the first char.
lex.next_ch();
lex
}
// Advance to the next character.
// Return the next lookahead character, or None when the end is encountered.
// Always update cur_ch to reflect
fn next_ch(&mut self) -> Option<char> {
if self.lookahead == Some('\n') {
self.line_number += 1;
}
match self.chars.next() {
Some((idx, ch)) => {
self.pos = idx;
self.lookahead = Some(ch);
}
None => {
self.pos = self.source.len();
self.lookahead = None;
}
}
self.lookahead
}
// Get the location corresponding to `lookahead`.
fn loc(&self) -> Location {
Location {
line_number: self.line_number,
}
}
// Starting from `lookahead`, are we looking at `prefix`?
fn looking_at(&self, prefix: &str) -> bool {
self.source[self.pos..].starts_with(prefix)
}
// Starting from `lookahead`, are we looking at a number?
fn looking_at_numeric(&self) -> bool {
if let Some(c) = self.lookahead {
if c.is_digit(10) {
return true;
}
match c {
'-' => return true,
'+' => return true,
'.' => return true,
_ => {}
}
if self.looking_at("NaN") || self.looking_at("Inf") || self.looking_at("sNaN") {
return true;
}
}
false
}
// Scan a single-char token.
fn scan_char(&mut self, tok: Token<'a>) -> Result<LocatedToken<'a>, LocatedError> {
assert_ne!(self.lookahead, None);
let loc = self.loc();
self.next_ch();
token(tok, loc)
}
// Scan a multi-char token.
fn scan_chars(
&mut self,
count: usize,
tok: Token<'a>,
) -> Result<LocatedToken<'a>, LocatedError> {
let loc = self.loc();
for _ in 0..count {
assert_ne!(self.lookahead, None);
self.next_ch();
}
token(tok, loc)
}
/// Get the rest of the current line.
/// The next token returned by `next()` will be from the following lines.
pub fn rest_of_line(&mut self) -> &'a str {
let begin = self.pos;
loop {
match self.next_ch() {
None | Some('\n') => return &self.source[begin..self.pos],
_ => {}
}
}
}
// Scan a comment extending to the end of the current line.
fn scan_comment(&mut self) -> Result<LocatedToken<'a>, LocatedError> {
let loc = self.loc();
let text = self.rest_of_line();
token(Token::Comment(text), loc)
}
// Scan a number token which can represent either an integer or floating point number.
//
// Accept the following forms:
//
// - `10`: Integer
// - `-10`: Integer
// - `0xff_00`: Integer
// - `0.0`: Float
// - `0x1.f`: Float
// - `-0x2.4`: Float
// - `0x0.4p-34`: Float
//
// This function does not filter out all invalid numbers. It depends in the context-sensitive
// decoding of the text for that. For example, the number of allowed digits in an `Ieee32` and
// an `Ieee64` constant are different.
fn scan_number(&mut self) -> Result<LocatedToken<'a>, LocatedError> {
let begin = self.pos;
let loc = self.loc();
let mut is_float = false;
// Skip a leading sign.
match self.lookahead {
Some('-') => {
self.next_ch();
if !self.looking_at_numeric() {
// If the next characters won't parse as a number, we return Token::Minus
return token(Token::Minus, loc);
}
}
Some('+') => {
self.next_ch();
if !self.looking_at_numeric() {
// If the next characters won't parse as a number, we return Token::Minus
return token(Token::Plus, loc);
}
}
_ => {}
}
// Check for NaNs with payloads.
if self.looking_at("NaN:") || self.looking_at("sNaN:") {
// Skip the `NaN:` prefix, the loop below won't accept it.
// We expect a hexadecimal number to follow the colon.
while self.next_ch() != Some(':') {}
is_float = true;
} else if self.looking_at("NaN") || self.looking_at("Inf") {
// This is Inf or a default quiet NaN.
is_float = true;
}
// Look for the end of this number. Detect the radix point if there is one.
loop {
match self.next_ch() {
Some('-') | Some('_') => {}
Some('.') => is_float = true,
Some(ch) if ch.is_alphanumeric() => {}
_ => break,
}
}
let text = &self.source[begin..self.pos];
if is_float {
token(Token::Float(text), loc)
} else {
token(Token::Integer(text), loc)
}
}
// Scan a 'word', which is an identifier-like sequence of characters beginning with '_' or an
// alphabetic char, followed by zero or more alphanumeric or '_' characters.
fn scan_word(&mut self) -> Result<LocatedToken<'a>, LocatedError> {
let begin = self.pos;
let loc = self.loc();
assert!(self.lookahead == Some('_') || self.lookahead.unwrap().is_alphabetic());
loop {
match self.next_ch() {
Some('_') => {}
Some(ch) if ch.is_alphanumeric() => {}
_ => break,
}
}
let text = &self.source[begin..self.pos];
// Look for numbered well-known entities like ebb15, v45, ...
token(
split_entity_name(text)
.and_then(|(prefix, number)| {
Self::numbered_entity(prefix, number)
.or_else(|| Self::value_type(text, prefix, number))
})
.unwrap_or_else(|| match text {
"iflags" => Token::Type(types::IFLAGS),
"fflags" => Token::Type(types::FFLAGS),
_ => Token::Identifier(text),
}),
loc,
)
}
// If prefix is a well-known entity prefix and suffix is a valid entity number, return the
// decoded token.
fn numbered_entity(prefix: &str, number: u32) -> Option<Token<'a>> {
match prefix {
"v" => Value::with_number(number).map(Token::Value),
"ebb" => Ebb::with_number(number).map(Token::Ebb),
"ss" => Some(Token::StackSlot(number)),
"gv" => Some(Token::GlobalValue(number)),
"heap" => Some(Token::Heap(number)),
"table" => Some(Token::Table(number)),
"jt" => Some(Token::JumpTable(number)),
"fn" => Some(Token::FuncRef(number)),
"sig" => Some(Token::SigRef(number)),
"u" => Some(Token::UserRef(number)),
_ => None,
}
}
// Recognize a scalar or vector type.
fn value_type(text: &str, prefix: &str, number: u32) -> Option<Token<'a>> {
let is_vector = prefix.ends_with('x');
let scalar = if is_vector {
&prefix[0..prefix.len() - 1]
} else {
text
};
let base_type = match scalar {
"i8" => types::I8,
"i16" => types::I16,
"i32" => types::I32,
"i64" => types::I64,
"f32" => types::F32,
"f64" => types::F64,
"b1" => types::B1,
"b8" => types::B8,
"b16" => types::B16,
"b32" => types::B32,
"b64" => types::B64,
_ => return None,
};
if is_vector {
if number <= u32::from(u16::MAX) {
base_type.by(number as u16).map(Token::Type)
} else {
None
}
} else {
Some(Token::Type(base_type))
}
}
fn scan_name(&mut self) -> Result<LocatedToken<'a>, LocatedError> {
let loc = self.loc();
let begin = self.pos + 1;
assert_eq!(self.lookahead, Some('%'));
while let Some(c) = self.next_ch() {
if !(c.is_ascii() && c.is_alphanumeric() || c == '_') {
break;
}
}
let end = self.pos;
token(Token::Name(&self.source[begin..end]), loc)
}
fn scan_hex_sequence(&mut self) -> Result<LocatedToken<'a>, LocatedError> {
let loc = self.loc();
let begin = self.pos + 1;
assert_eq!(self.lookahead, Some('#'));
while let Some(c) = self.next_ch() {
if !char::is_digit(c, 16) {
break;
}
}
let end = self.pos;
token(Token::HexSequence(&self.source[begin..end]), loc)
}
fn scan_srcloc(&mut self) -> Result<LocatedToken<'a>, LocatedError> {
let loc = self.loc();
let begin = self.pos + 1;
assert_eq!(self.lookahead, Some('@'));
while let Some(c) = self.next_ch() {
if !char::is_digit(c, 16) {
break;
}
}
let end = self.pos;
token(Token::SourceLoc(&self.source[begin..end]), loc)
}
/// Get the next token or a lexical error.
///
/// Return None when the end of the source is encountered.
pub fn next(&mut self) -> Option<Result<LocatedToken<'a>, LocatedError>> {
loop {
let loc = self.loc();
return match self.lookahead {
None => None,
Some(';') => Some(self.scan_comment()),
Some('(') => Some(self.scan_char(Token::LPar)),
Some(')') => Some(self.scan_char(Token::RPar)),
Some('{') => Some(self.scan_char(Token::LBrace)),
Some('}') => Some(self.scan_char(Token::RBrace)),
Some('[') => Some(self.scan_char(Token::LBracket)),
Some(']') => Some(self.scan_char(Token::RBracket)),
Some(',') => Some(self.scan_char(Token::Comma)),
Some('.') => Some(self.scan_char(Token::Dot)),
Some(':') => Some(self.scan_char(Token::Colon)),
Some('=') => Some(self.scan_char(Token::Equal)),
Some('+') => Some(self.scan_number()),
Some('-') => {
if self.looking_at("->") {
Some(self.scan_chars(2, Token::Arrow))
} else {
Some(self.scan_number())
}
}
Some(ch) if ch.is_digit(10) => Some(self.scan_number()),
Some(ch) if ch.is_alphabetic() => Some(self.scan_word()),
Some('%') => Some(self.scan_name()),
Some('#') => Some(self.scan_hex_sequence()),
Some('@') => Some(self.scan_srcloc()),
Some(ch) if ch.is_whitespace() => {
self.next_ch();
continue;
}
_ => {
// Skip invalid char, return error.
self.next_ch();
Some(error(LexError::InvalidChar, loc))
}
};
}
}
}
#[cfg(test)]
mod tests {
use super::trailing_digits;
use super::*;
use crate::error::Location;
use cranelift_codegen::ir::types;
use cranelift_codegen::ir::{Ebb, Value};
#[test]
fn digits() {
assert_eq!(trailing_digits(""), 0);
assert_eq!(trailing_digits("x"), 0);
assert_eq!(trailing_digits("0x"), 0);
assert_eq!(trailing_digits("x1"), 1);
assert_eq!(trailing_digits("1x1"), 1);
assert_eq!(trailing_digits("1x01"), 2);
}
#[test]
fn entity_name() {
assert_eq!(split_entity_name(""), None);
assert_eq!(split_entity_name("x"), None);
assert_eq!(split_entity_name("x+"), None);
assert_eq!(split_entity_name("x+1"), Some(("x+", 1)));
assert_eq!(split_entity_name("x-1"), Some(("x-", 1)));
assert_eq!(split_entity_name("1"), Some(("", 1)));
assert_eq!(split_entity_name("x1"), Some(("x", 1)));
assert_eq!(split_entity_name("xy0"), Some(("xy", 0)));
// Reject this non-canonical form.
assert_eq!(split_entity_name("inst01"), None);
}
fn token<'a>(token: Token<'a>, line: usize) -> Option<Result<LocatedToken<'a>, LocatedError>> {
Some(super::token(token, Location { line_number: line }))
}
fn error<'a>(error: LexError, line: usize) -> Option<Result<LocatedToken<'a>, LocatedError>> {
Some(super::error(error, Location { line_number: line }))
}
#[test]
fn make_lexer() {
let mut l1 = Lexer::new("");
let mut l2 = Lexer::new(" ");
let mut l3 = Lexer::new("\n ");
assert_eq!(l1.next(), None);
assert_eq!(l2.next(), None);
assert_eq!(l3.next(), None);
}
#[test]
fn lex_comment() {
let mut lex = Lexer::new("; hello");
assert_eq!(lex.next(), token(Token::Comment("; hello"), 1));
assert_eq!(lex.next(), None);
lex = Lexer::new("\n ;hello\n;foo");
assert_eq!(lex.next(), token(Token::Comment(";hello"), 2));
assert_eq!(lex.next(), token(Token::Comment(";foo"), 3));
assert_eq!(lex.next(), None);
// Scan a comment after an invalid char.
let mut lex = Lexer::new("$; hello");
assert_eq!(lex.next(), error(LexError::InvalidChar, 1));
assert_eq!(lex.next(), token(Token::Comment("; hello"), 1));
assert_eq!(lex.next(), None);
}
#[test]
fn lex_chars() {
let mut lex = Lexer::new("(); hello\n = :{, }.");
assert_eq!(lex.next(), token(Token::LPar, 1));
assert_eq!(lex.next(), token(Token::RPar, 1));
assert_eq!(lex.next(), token(Token::Comment("; hello"), 1));
assert_eq!(lex.next(), token(Token::Equal, 2));
assert_eq!(lex.next(), token(Token::Colon, 2));
assert_eq!(lex.next(), token(Token::LBrace, 2));
assert_eq!(lex.next(), token(Token::Comma, 2));
assert_eq!(lex.next(), token(Token::RBrace, 2));
assert_eq!(lex.next(), token(Token::Dot, 2));
assert_eq!(lex.next(), None);
}
#[test]
fn lex_numbers() {
let mut lex = Lexer::new(" 0 2_000 -1,0xf -0x0 0.0 0x0.4p-34 +5");
assert_eq!(lex.next(), token(Token::Integer("0"), 1));
assert_eq!(lex.next(), token(Token::Integer("2_000"), 1));
assert_eq!(lex.next(), token(Token::Integer("-1"), 1));
assert_eq!(lex.next(), token(Token::Comma, 1));
assert_eq!(lex.next(), token(Token::Integer("0xf"), 1));
assert_eq!(lex.next(), token(Token::Integer("-0x0"), 1));
assert_eq!(lex.next(), token(Token::Float("0.0"), 1));
assert_eq!(lex.next(), token(Token::Float("0x0.4p-34"), 1));
assert_eq!(lex.next(), token(Token::Integer("+5"), 1));
assert_eq!(lex.next(), None);
}
#[test]
fn lex_identifiers() {
let mut lex = Lexer::new(
"v0 v00 vx01 ebb1234567890 ebb5234567890 v1x vx1 vxvx4 \
function0 function b1 i32x4 f32x5 \
iflags fflags iflagss",
);
assert_eq!(
lex.next(),
token(Token::Value(Value::with_number(0).unwrap()), 1)
);
assert_eq!(lex.next(), token(Token::Identifier("v00"), 1));
assert_eq!(lex.next(), token(Token::Identifier("vx01"), 1));
assert_eq!(
lex.next(),
token(Token::Ebb(Ebb::with_number(1234567890).unwrap()), 1)
);
assert_eq!(lex.next(), token(Token::Identifier("ebb5234567890"), 1));
assert_eq!(lex.next(), token(Token::Identifier("v1x"), 1));
assert_eq!(lex.next(), token(Token::Identifier("vx1"), 1));
assert_eq!(lex.next(), token(Token::Identifier("vxvx4"), 1));
assert_eq!(lex.next(), token(Token::Identifier("function0"), 1));
assert_eq!(lex.next(), token(Token::Identifier("function"), 1));
assert_eq!(lex.next(), token(Token::Type(types::B1), 1));
assert_eq!(lex.next(), token(Token::Type(types::I32X4), 1));
assert_eq!(lex.next(), token(Token::Identifier("f32x5"), 1));
assert_eq!(lex.next(), token(Token::Type(types::IFLAGS), 1));
assert_eq!(lex.next(), token(Token::Type(types::FFLAGS), 1));
assert_eq!(lex.next(), token(Token::Identifier("iflagss"), 1));
assert_eq!(lex.next(), None);
}
#[test]
fn lex_hex_sequences() {
let mut lex = Lexer::new("#0 #DEADbeef123 #789");
assert_eq!(lex.next(), token(Token::HexSequence("0"), 1));
assert_eq!(lex.next(), token(Token::HexSequence("DEADbeef123"), 1));
assert_eq!(lex.next(), token(Token::HexSequence("789"), 1));
}
#[test]
fn lex_names() {
let mut lex = Lexer::new("%0 %x3 %function %123_abc %ss0 %v3 %ebb11 %_");
assert_eq!(lex.next(), token(Token::Name("0"), 1));
assert_eq!(lex.next(), token(Token::Name("x3"), 1));
assert_eq!(lex.next(), token(Token::Name("function"), 1));
assert_eq!(lex.next(), token(Token::Name("123_abc"), 1));
assert_eq!(lex.next(), token(Token::Name("ss0"), 1));
assert_eq!(lex.next(), token(Token::Name("v3"), 1));
assert_eq!(lex.next(), token(Token::Name("ebb11"), 1));
assert_eq!(lex.next(), token(Token::Name("_"), 1));
}
#[test]
fn lex_userrefs() {
let mut lex = Lexer::new("u0 u1 u234567890 u9:8765");
assert_eq!(lex.next(), token(Token::UserRef(0), 1));
assert_eq!(lex.next(), token(Token::UserRef(1), 1));
assert_eq!(lex.next(), token(Token::UserRef(234567890), 1));
assert_eq!(lex.next(), token(Token::UserRef(9), 1));
assert_eq!(lex.next(), token(Token::Colon, 1));
assert_eq!(lex.next(), token(Token::Integer("8765"), 1));
assert_eq!(lex.next(), None);
}
}

View File

@@ -0,0 +1,42 @@
//! Cranelift file reader library.
//!
//! The `cranelift_reader` library supports reading .clif files. This functionality is needed for
//! testing Cranelift, but is not essential for a JIT compiler.
#![deny(
missing_docs,
trivial_numeric_casts,
unused_extern_crates,
unstable_features
)]
#![warn(unused_import_braces)]
#![cfg_attr(feature = "clippy", plugin(clippy(conf_file = "../../clippy.toml")))]
#![cfg_attr(feature = "cargo-clippy", allow(clippy::new_without_default))]
#![cfg_attr(
feature = "cargo-clippy",
warn(
clippy::float_arithmetic,
clippy::mut_mut,
clippy::nonminimal_bool,
clippy::option_map_unwrap_or,
clippy::option_map_unwrap_or_else,
clippy::print_stdout,
clippy::unicode_not_nfc,
clippy::use_self
)
)]
pub use crate::error::{Location, ParseError, ParseResult};
pub use crate::isaspec::{parse_options, IsaSpec};
pub use crate::parser::{parse_functions, parse_test};
pub use crate::sourcemap::SourceMap;
pub use crate::testcommand::{TestCommand, TestOption};
pub use crate::testfile::{Comment, Details, TestFile};
mod error;
mod isaspec;
mod lexer;
mod parser;
mod sourcemap;
mod testcommand;
mod testfile;

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1,240 @@
//! Source map associating entities with their source locations.
//!
//! When the parser reads in a source file, it records the locations of the
//! definitions of entities like instructions, EBBs, and values.
//!
//! The `SourceMap` struct defined in this module makes this mapping available
//! to parser clients.
use crate::error::{Location, ParseResult};
use crate::lexer::split_entity_name;
use cranelift_codegen::ir::entities::AnyEntity;
use cranelift_codegen::ir::{
Ebb, FuncRef, GlobalValue, Heap, JumpTable, SigRef, StackSlot, Table, Value,
};
use std::collections::HashMap;
/// Mapping from entity names to source locations.
#[derive(Debug, Default)]
pub struct SourceMap {
// Store locations for entities, including instructions.
locations: HashMap<AnyEntity, Location>,
}
/// Read-only interface which is exposed outside the parser crate.
impl SourceMap {
/// Look up a value entity.
pub fn contains_value(&self, v: Value) -> bool {
self.locations.contains_key(&v.into())
}
/// Look up a EBB entity.
pub fn contains_ebb(&self, ebb: Ebb) -> bool {
self.locations.contains_key(&ebb.into())
}
/// Look up a stack slot entity.
pub fn contains_ss(&self, ss: StackSlot) -> bool {
self.locations.contains_key(&ss.into())
}
/// Look up a global value entity.
pub fn contains_gv(&self, gv: GlobalValue) -> bool {
self.locations.contains_key(&gv.into())
}
/// Look up a heap entity.
pub fn contains_heap(&self, heap: Heap) -> bool {
self.locations.contains_key(&heap.into())
}
/// Look up a table entity.
pub fn contains_table(&self, table: Table) -> bool {
self.locations.contains_key(&table.into())
}
/// Look up a signature entity.
pub fn contains_sig(&self, sig: SigRef) -> bool {
self.locations.contains_key(&sig.into())
}
/// Look up a function entity.
pub fn contains_fn(&self, fn_: FuncRef) -> bool {
self.locations.contains_key(&fn_.into())
}
/// Look up a jump table entity.
pub fn contains_jt(&self, jt: JumpTable) -> bool {
self.locations.contains_key(&jt.into())
}
/// Look up an entity by source name.
/// Returns the entity reference corresponding to `name`, if it exists.
pub fn lookup_str(&self, name: &str) -> Option<AnyEntity> {
split_entity_name(name).and_then(|(ent, num)| match ent {
"v" => Value::with_number(num).and_then(|v| {
if !self.contains_value(v) {
None
} else {
Some(v.into())
}
}),
"ebb" => Ebb::with_number(num).and_then(|ebb| {
if !self.contains_ebb(ebb) {
None
} else {
Some(ebb.into())
}
}),
"ss" => StackSlot::with_number(num).and_then(|ss| {
if !self.contains_ss(ss) {
None
} else {
Some(ss.into())
}
}),
"gv" => GlobalValue::with_number(num).and_then(|gv| {
if !self.contains_gv(gv) {
None
} else {
Some(gv.into())
}
}),
"heap" => Heap::with_number(num).and_then(|heap| {
if !self.contains_heap(heap) {
None
} else {
Some(heap.into())
}
}),
"table" => Table::with_number(num).and_then(|table| {
if !self.contains_table(table) {
None
} else {
Some(table.into())
}
}),
"sig" => SigRef::with_number(num).and_then(|sig| {
if !self.contains_sig(sig) {
None
} else {
Some(sig.into())
}
}),
"fn" => FuncRef::with_number(num).and_then(|fn_| {
if !self.contains_fn(fn_) {
None
} else {
Some(fn_.into())
}
}),
"jt" => JumpTable::with_number(num).and_then(|jt| {
if !self.contains_jt(jt) {
None
} else {
Some(jt.into())
}
}),
_ => None,
})
}
/// Get the source location where an entity was defined.
pub fn location(&self, entity: AnyEntity) -> Option<Location> {
self.locations.get(&entity).cloned()
}
}
impl SourceMap {
/// Create a new empty `SourceMap`.
pub fn new() -> Self {
Self {
locations: HashMap::new(),
}
}
/// Define the value `entity`.
pub fn def_value(&mut self, entity: Value, loc: Location) -> ParseResult<()> {
self.def_entity(entity.into(), loc)
}
/// Define the ebb `entity`.
pub fn def_ebb(&mut self, entity: Ebb, loc: Location) -> ParseResult<()> {
self.def_entity(entity.into(), loc)
}
/// Define the stack slot `entity`.
pub fn def_ss(&mut self, entity: StackSlot, loc: Location) -> ParseResult<()> {
self.def_entity(entity.into(), loc)
}
/// Define the global value `entity`.
pub fn def_gv(&mut self, entity: GlobalValue, loc: Location) -> ParseResult<()> {
self.def_entity(entity.into(), loc)
}
/// Define the heap `entity`.
pub fn def_heap(&mut self, entity: Heap, loc: Location) -> ParseResult<()> {
self.def_entity(entity.into(), loc)
}
/// Define the table `entity`.
pub fn def_table(&mut self, entity: Table, loc: Location) -> ParseResult<()> {
self.def_entity(entity.into(), loc)
}
/// Define the signature `entity`.
pub fn def_sig(&mut self, entity: SigRef, loc: Location) -> ParseResult<()> {
self.def_entity(entity.into(), loc)
}
/// Define the external function `entity`.
pub fn def_fn(&mut self, entity: FuncRef, loc: Location) -> ParseResult<()> {
self.def_entity(entity.into(), loc)
}
/// Define the jump table `entity`.
pub fn def_jt(&mut self, entity: JumpTable, loc: Location) -> ParseResult<()> {
self.def_entity(entity.into(), loc)
}
/// Define an entity. This can be used for instructions whose numbers never
/// appear in source, or implicitly defined signatures.
pub fn def_entity(&mut self, entity: AnyEntity, loc: Location) -> ParseResult<()> {
if self.locations.insert(entity, loc).is_some() {
err!(loc, "duplicate entity: {}", entity)
} else {
Ok(())
}
}
}
#[cfg(test)]
mod tests {
use crate::parse_test;
#[test]
fn details() {
let tf = parse_test(
"function %detail() {
ss10 = incoming_arg 13
jt10 = jump_table [ebb0]
ebb0(v4: i32, v7: i32):
v10 = iadd v4, v7
}",
None,
None,
)
.unwrap();
let map = &tf.functions[0].1.map;
assert_eq!(map.lookup_str("v0"), None);
assert_eq!(map.lookup_str("ss1"), None);
assert_eq!(map.lookup_str("ss10").unwrap().to_string(), "ss10");
assert_eq!(map.lookup_str("jt10").unwrap().to_string(), "jt10");
assert_eq!(map.lookup_str("ebb0").unwrap().to_string(), "ebb0");
assert_eq!(map.lookup_str("v4").unwrap().to_string(), "v4");
assert_eq!(map.lookup_str("v7").unwrap().to_string(), "v7");
assert_eq!(map.lookup_str("v10").unwrap().to_string(), "v10");
}
}

View File

@@ -0,0 +1,103 @@
//! Test commands.
//!
//! A `.clif` file can begin with one or more *test commands* which specify what is to be tested.
//! The general syntax is:
//!
//! <pre>
//! test <i>&lt;command&gt;</i> </i>[options]</i>...
//! </pre>
//!
//! The options are either a single identifier flag, or setting values like `identifier=value`.
//!
//! The parser does not understand the test commands or which options are valid. It simply parses
//! the general format into a `TestCommand` data structure.
use std::fmt::{self, Display, Formatter};
/// A command appearing in a test file.
#[derive(Clone, PartialEq, Eq, Debug)]
pub struct TestCommand<'a> {
/// The command name as a string.
pub command: &'a str,
/// The options following the command name.
pub options: Vec<TestOption<'a>>,
}
/// An option on a test command.
#[derive(Clone, PartialEq, Eq, Debug)]
pub enum TestOption<'a> {
/// Single identifier flag: `foo`.
Flag(&'a str),
/// A value assigned to an identifier: `foo=bar`.
Value(&'a str, &'a str),
}
impl<'a> TestCommand<'a> {
/// Create a new TestCommand by parsing `s`.
/// The returned command contains references into `s`.
pub fn new(s: &'a str) -> Self {
let mut parts = s.split_whitespace();
let cmd = parts.next().unwrap_or("");
Self {
command: cmd,
options: parts
.filter(|s| !s.is_empty())
.map(TestOption::new)
.collect(),
}
}
}
impl<'a> Display for TestCommand<'a> {
fn fmt(&self, f: &mut Formatter) -> fmt::Result {
write!(f, "{}", self.command)?;
for opt in &self.options {
write!(f, " {}", opt)?;
}
writeln!(f)
}
}
impl<'a> TestOption<'a> {
/// Create a new TestOption by parsing `s`.
/// The returned option contains references into `s`.
pub fn new(s: &'a str) -> Self {
match s.find('=') {
None => TestOption::Flag(s),
Some(p) => TestOption::Value(&s[0..p], &s[p + 1..]),
}
}
}
impl<'a> Display for TestOption<'a> {
fn fmt(&self, f: &mut Formatter) -> fmt::Result {
match *self {
TestOption::Flag(s) => write!(f, "{}", s),
TestOption::Value(s, v) => write!(f, "{}={}", s, v),
}
}
}
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn parse_option() {
assert_eq!(TestOption::new(""), TestOption::Flag(""));
assert_eq!(TestOption::new("foo"), TestOption::Flag("foo"));
assert_eq!(TestOption::new("foo=bar"), TestOption::Value("foo", "bar"));
}
#[test]
fn parse_command() {
assert_eq!(&TestCommand::new("").to_string(), "\n");
assert_eq!(&TestCommand::new("cat").to_string(), "cat\n");
assert_eq!(&TestCommand::new("cat ").to_string(), "cat\n");
assert_eq!(&TestCommand::new("cat 1 ").to_string(), "cat 1\n");
assert_eq!(
&TestCommand::new("cat one=4 two t").to_string(),
"cat one=4 two t\n"
);
}
}

View File

@@ -0,0 +1,57 @@
//! Data structures representing a parsed test file.
//!
//! A test file is a `.clif` file which contains test commands and settings for running a
//! file-based test case.
//!
use crate::error::Location;
use crate::isaspec::IsaSpec;
use crate::sourcemap::SourceMap;
use crate::testcommand::TestCommand;
use cranelift_codegen::ir::entities::AnyEntity;
use cranelift_codegen::ir::Function;
/// A parsed test case.
///
/// This is the result of parsing a `.clif` file which contains a number of test commands and ISA
/// specs followed by the functions that should be tested.
pub struct TestFile<'a> {
/// `test foo ...` lines.
pub commands: Vec<TestCommand<'a>>,
/// `isa bar ...` lines.
pub isa_spec: IsaSpec,
/// Comments appearing before the first function.
/// These are all tagged as 'Function' scope for lack of a better entity.
pub preamble_comments: Vec<Comment<'a>>,
/// Parsed functions and additional details about each function.
pub functions: Vec<(Function, Details<'a>)>,
}
/// Additional details about a function parsed from a text string.
/// These are useful for detecting test commands embedded in comments etc.
/// The details to not affect the semantics of the function.
#[derive(Debug)]
pub struct Details<'a> {
/// Location of the `function` keyword that begins this function.
pub location: Location,
/// Annotation comments that appeared inside or after the function.
pub comments: Vec<Comment<'a>>,
/// Mapping of entity numbers to source locations.
pub map: SourceMap,
}
/// A comment in a parsed function.
///
/// The comment belongs to the immediately preceding entity, whether that is an EBB header, and
/// instruction, or one of the preamble declarations.
///
/// Comments appearing inside the function but before the preamble, as well as comments appearing
/// after the function are tagged as `AnyEntity::Function`.
#[derive(Clone, PartialEq, Eq, Debug)]
pub struct Comment<'a> {
/// The entity this comment is attached to.
/// Comments always follow their entity.
pub entity: AnyEntity,
/// Text of the comment, including the leading `;`.
pub text: &'a str,
}