更新libclamav库1.0.0版本

This commit is contained in:
2023-01-14 18:28:39 +08:00
parent b879ee0b2e
commit 45fe15f472
8531 changed files with 1222046 additions and 177272 deletions

View File

@@ -0,0 +1 @@
{"files":{"Cargo.toml":"3300e6f2f5fc184c613a78251df3d1333530c9b54193e137b75c88f6db5a6fa6","LICENSE-APACHE":"a60eea817514531668d7e00765731449fe14d059d3249e0bc93b36de45f759f2","LICENSE-MIT":"d9771b8c6cf4426d3846de54c1febe20907f1eeadf7adfb5ade89a83bd9ea77f","bors.toml":"1c81ede536a37edd30fe4e622ff0531b25372403ac9475a5d6c50f14156565a2","rustfmt.toml":"d8e7f616455a670ba75e3e94bf6f88f4c168c481664d12501820c7dfff5c3cc2","src/expr.rs":"dad9327dac3af9d2f5818937aac91000e02d835dc600da6185c06e9e12047b1e","src/lib.rs":"ff218b9b734ab2eaef813a6ee3a907cb5cd71d483dfaa28d44926824a5b6d804","src/literal.rs":"6fdefc0357b8a14444df21b05c90556861dc0466e63a57669786f3ef3a3dc1c3","src/token.rs":"cd1ba6315b0137de9a0711670dd1840ac76c41f3b88dcd1a93ad77e1800c703f","tests/clang.rs":"5bb9807f35f760065d15cb9dfb7d8b79c2f734aef7ba5fe3737154155ed8ee73","tests/input/chars.h":"69c8141870872b795b5174bad125b748732c2b01d0e98ffcfc37b19f3f791f69","tests/input/fail.h":"b0b6cffd2dd17410b5eb02ee79ab75754820480b960db8a9866cc9983bd36b65","tests/input/floats.h":"28ec664e793c494e1a31f3bc5b790014e9921fc741bf475a86319b9a9eee5915","tests/input/int_signed.h":"934199eded85dd7820ca08c0beb1381ee6d9339970d2720a69c23025571707ce","tests/input/int_unsigned.h":"7b8023ba468ec76b184912692bc40e8fbcdd92ad86ec5a7c0dbcb02f2b8d961d","tests/input/strings.h":"2dd11bc066f34e8cb1916a28353e9e9a3a21cd406651b2f94fc47e89c95d9cba","tests/input/test_llvm_bug_9069.h":"8d9ae1d1eadc8f6d5c14296f984547fe894d0f2ce5cd6d7aa8caad40a56bc5e1"},"package":"6fac387a98bb7c37292057cffc56d62ecb629900026402633ae9160df93a8766"}

View File

@@ -0,0 +1,29 @@
# THIS FILE IS AUTOMATICALLY GENERATED BY CARGO
#
# When uploading crates to the registry Cargo will automatically
# "normalize" Cargo.toml files for maximal compatibility
# with all versions of Cargo and also rewrite `path` dependencies
# to registry (e.g., crates.io) dependencies.
#
# If you are reading this file be aware that the original Cargo.toml
# will likely look very different (and much more reasonable).
# See Cargo.toml.orig for the original contents.
[package]
edition = "2018"
name = "cexpr"
version = "0.6.0"
authors = ["Jethro Beekman <jethro@jbeekman.nl>"]
description = "A C expression parser and evaluator"
documentation = "https://docs.rs/cexpr/"
keywords = ["C", "expression", "parser"]
license = "Apache-2.0/MIT"
repository = "https://github.com/jethrogb/rust-cexpr"
[dependencies.nom]
version = "7"
features = ["std"]
default-features = false
[dev-dependencies.clang-sys]
version = ">= 0.13.0, < 0.29.0"
[badges.travis-ci]
repository = "jethrogb/rust-cexpr"

View File

@@ -0,0 +1,201 @@
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.

View File

@@ -0,0 +1,25 @@
(C) Copyright 2016 Jethro G. Beekman
Permission is hereby granted, free of charge, to any
person obtaining a copy of this software and associated
documentation files (the "Software"), to deal in the
Software without restriction, including without
limitation the rights to use, copy, modify, merge,
publish, distribute, sublicense, and/or sell copies of
the Software, and to permit persons to whom the Software
is furnished to do so, subject to the following
conditions:
The above copyright notice and this permission notice
shall be included in all copies or substantial portions
of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF
ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED
TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A
PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT
SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY
CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR
IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
DEALINGS IN THE SOFTWARE.

View File

@@ -0,0 +1,3 @@
status = [
"continuous-integration/travis-ci/push",
]

View File

@@ -0,0 +1 @@
edition = "2018"

View File

@@ -0,0 +1,610 @@
// (C) Copyright 2016 Jethro G. Beekman
//
// Licensed under the Apache License, Version 2.0 <LICENSE-APACHE or
// http://www.apache.org/licenses/LICENSE-2.0> or the MIT license
// <LICENSE-MIT or http://opensource.org/licenses/MIT>, at your
// option. This file may not be copied, modified, or distributed
// except according to those terms.
//! Evaluating C expressions from tokens.
//!
//! Numerical operators are supported. All numerical values are treated as
//! `i64` or `f64`. Type casting is not supported. `i64` are converted to
//! `f64` when used in conjunction with a `f64`. Right shifts are always
//! arithmetic shifts.
//!
//! The `sizeof` operator is not supported.
//!
//! String concatenation is supported, but width prefixes are ignored; all
//! strings are treated as narrow strings.
//!
//! Use the `IdentifierParser` to substitute identifiers found in expressions.
use std::collections::HashMap;
use std::num::Wrapping;
use std::ops::{
AddAssign, BitAndAssign, BitOrAssign, BitXorAssign, DivAssign, MulAssign, RemAssign, ShlAssign,
ShrAssign, SubAssign,
};
use crate::literal::{self, CChar};
use crate::token::{Kind as TokenKind, Token};
use crate::ToCexprResult;
use nom::branch::alt;
use nom::combinator::{complete, map, map_opt};
use nom::multi::{fold_many0, many0, separated_list0};
use nom::sequence::{delimited, pair, preceded};
use nom::*;
/// Expression parser/evaluator that supports identifiers.
#[derive(Debug)]
pub struct IdentifierParser<'ident> {
identifiers: &'ident HashMap<Vec<u8>, EvalResult>,
}
#[derive(Copy, Clone)]
struct PRef<'a>(&'a IdentifierParser<'a>);
/// A shorthand for the type of cexpr expression evaluation results.
pub type CResult<'a, R> = IResult<&'a [Token], R, crate::Error<&'a [Token]>>;
/// The result of parsing a literal or evaluating an expression.
#[derive(Debug, Clone, PartialEq)]
#[allow(missing_docs)]
pub enum EvalResult {
Int(Wrapping<i64>),
Float(f64),
Char(CChar),
Str(Vec<u8>),
Invalid,
}
macro_rules! result_opt (
(fn $n:ident: $e:ident -> $t:ty) => (
#[allow(dead_code)]
#[allow(clippy::wrong_self_convention)]
fn $n(self) -> Option<$t> {
if let EvalResult::$e(v) = self {
Some(v)
} else {
None
}
}
);
);
impl EvalResult {
result_opt!(fn as_int: Int -> Wrapping<i64>);
result_opt!(fn as_float: Float -> f64);
result_opt!(fn as_char: Char -> CChar);
result_opt!(fn as_str: Str -> Vec<u8>);
#[allow(clippy::wrong_self_convention)]
fn as_numeric(self) -> Option<EvalResult> {
match self {
EvalResult::Int(_) | EvalResult::Float(_) => Some(self),
_ => None,
}
}
}
impl From<Vec<u8>> for EvalResult {
fn from(s: Vec<u8>) -> EvalResult {
EvalResult::Str(s)
}
}
// ===========================================
// ============= Clang tokens ================
// ===========================================
macro_rules! exact_token (
($k:ident, $c:expr) => ({
move |input: &[Token]| {
if input.is_empty() {
let res: CResult<'_, &[u8]> = Err(crate::nom::Err::Incomplete(Needed::new($c.len())));
res
} else {
if input[0].kind==TokenKind::$k && &input[0].raw[..]==$c {
Ok((&input[1..], &input[0].raw[..]))
} else {
Err(crate::nom::Err::Error((input, crate::ErrorKind::ExactToken(TokenKind::$k,$c)).into()))
}
}
}
});
);
fn identifier_token(input: &[Token]) -> CResult<'_, &[u8]> {
if input.is_empty() {
let res: CResult<'_, &[u8]> = Err(nom::Err::Incomplete(Needed::new(1)));
res
} else {
if input[0].kind == TokenKind::Identifier {
Ok((&input[1..], &input[0].raw[..]))
} else {
Err(crate::nom::Err::Error((input, crate::ErrorKind::TypedToken(TokenKind::Identifier)).into()))
}
}
}
fn p(c: &'static str) -> impl Fn(&[Token]) -> CResult<'_, &[u8]> {
exact_token!(Punctuation, c.as_bytes())
}
fn one_of_punctuation(c: &'static [&'static str]) -> impl Fn(&[Token]) -> CResult<'_, &[u8]> {
move |input| {
if input.is_empty() {
let min = c
.iter()
.map(|opt| opt.len())
.min()
.expect("at least one option");
Err(crate::nom::Err::Incomplete(Needed::new(min)))
} else if input[0].kind == TokenKind::Punctuation
&& c.iter().any(|opt| opt.as_bytes() == &input[0].raw[..])
{
Ok((&input[1..], &input[0].raw[..]))
} else {
Err(crate::nom::Err::Error(
(
input,
crate::ErrorKind::ExactTokens(TokenKind::Punctuation, c),
)
.into(),
))
}
}
}
// ==================================================
// ============= Numeric expressions ================
// ==================================================
impl<'a> AddAssign<&'a EvalResult> for EvalResult {
fn add_assign(&mut self, rhs: &'a EvalResult) {
use self::EvalResult::*;
*self = match (&*self, rhs) {
(&Int(a), &Int(b)) => Int(a + b),
(&Float(a), &Int(b)) => Float(a + (b.0 as f64)),
(&Int(a), &Float(b)) => Float(a.0 as f64 + b),
(&Float(a), &Float(b)) => Float(a + b),
_ => Invalid,
};
}
}
impl<'a> BitAndAssign<&'a EvalResult> for EvalResult {
fn bitand_assign(&mut self, rhs: &'a EvalResult) {
use self::EvalResult::*;
*self = match (&*self, rhs) {
(&Int(a), &Int(b)) => Int(a & b),
_ => Invalid,
};
}
}
impl<'a> BitOrAssign<&'a EvalResult> for EvalResult {
fn bitor_assign(&mut self, rhs: &'a EvalResult) {
use self::EvalResult::*;
*self = match (&*self, rhs) {
(&Int(a), &Int(b)) => Int(a | b),
_ => Invalid,
};
}
}
impl<'a> BitXorAssign<&'a EvalResult> for EvalResult {
fn bitxor_assign(&mut self, rhs: &'a EvalResult) {
use self::EvalResult::*;
*self = match (&*self, rhs) {
(&Int(a), &Int(b)) => Int(a ^ b),
_ => Invalid,
};
}
}
impl<'a> DivAssign<&'a EvalResult> for EvalResult {
fn div_assign(&mut self, rhs: &'a EvalResult) {
use self::EvalResult::*;
*self = match (&*self, rhs) {
(&Int(a), &Int(b)) => Int(a / b),
(&Float(a), &Int(b)) => Float(a / (b.0 as f64)),
(&Int(a), &Float(b)) => Float(a.0 as f64 / b),
(&Float(a), &Float(b)) => Float(a / b),
_ => Invalid,
};
}
}
impl<'a> MulAssign<&'a EvalResult> for EvalResult {
fn mul_assign(&mut self, rhs: &'a EvalResult) {
use self::EvalResult::*;
*self = match (&*self, rhs) {
(&Int(a), &Int(b)) => Int(a * b),
(&Float(a), &Int(b)) => Float(a * (b.0 as f64)),
(&Int(a), &Float(b)) => Float(a.0 as f64 * b),
(&Float(a), &Float(b)) => Float(a * b),
_ => Invalid,
};
}
}
impl<'a> RemAssign<&'a EvalResult> for EvalResult {
fn rem_assign(&mut self, rhs: &'a EvalResult) {
use self::EvalResult::*;
*self = match (&*self, rhs) {
(&Int(a), &Int(b)) => Int(a % b),
(&Float(a), &Int(b)) => Float(a % (b.0 as f64)),
(&Int(a), &Float(b)) => Float(a.0 as f64 % b),
(&Float(a), &Float(b)) => Float(a % b),
_ => Invalid,
};
}
}
impl<'a> ShlAssign<&'a EvalResult> for EvalResult {
fn shl_assign(&mut self, rhs: &'a EvalResult) {
use self::EvalResult::*;
*self = match (&*self, rhs) {
(&Int(a), &Int(b)) => Int(a << (b.0 as usize)),
_ => Invalid,
};
}
}
impl<'a> ShrAssign<&'a EvalResult> for EvalResult {
fn shr_assign(&mut self, rhs: &'a EvalResult) {
use self::EvalResult::*;
*self = match (&*self, rhs) {
(&Int(a), &Int(b)) => Int(a >> (b.0 as usize)),
_ => Invalid,
};
}
}
impl<'a> SubAssign<&'a EvalResult> for EvalResult {
fn sub_assign(&mut self, rhs: &'a EvalResult) {
use self::EvalResult::*;
*self = match (&*self, rhs) {
(&Int(a), &Int(b)) => Int(a - b),
(&Float(a), &Int(b)) => Float(a - (b.0 as f64)),
(&Int(a), &Float(b)) => Float(a.0 as f64 - b),
(&Float(a), &Float(b)) => Float(a - b),
_ => Invalid,
};
}
}
fn unary_op(input: (&[u8], EvalResult)) -> Option<EvalResult> {
use self::EvalResult::*;
assert_eq!(input.0.len(), 1);
match (input.0[0], input.1) {
(b'+', i) => Some(i),
(b'-', Int(i)) => Some(Int(Wrapping(i.0.wrapping_neg()))), // impl Neg for Wrapping not until rust 1.10...
(b'-', Float(i)) => Some(Float(-i)),
(b'-', _) => unreachable!("non-numeric unary op"),
(b'~', Int(i)) => Some(Int(!i)),
(b'~', Float(_)) => None,
(b'~', _) => unreachable!("non-numeric unary op"),
_ => unreachable!("invalid unary op"),
}
}
fn numeric<I: Clone, E: nom::error::ParseError<I>, F>(
f: F,
) -> impl FnMut(I) -> nom::IResult<I, EvalResult, E>
where
F: FnMut(I) -> nom::IResult<I, EvalResult, E>,
{
nom::combinator::map_opt(f, EvalResult::as_numeric)
}
impl<'a> PRef<'a> {
fn unary(self, input: &'_ [Token]) -> CResult<'_, EvalResult> {
alt((
delimited(p("("), |i| self.numeric_expr(i), p(")")),
numeric(|i| self.literal(i)),
numeric(|i| self.identifier(i)),
map_opt(
pair(one_of_punctuation(&["+", "-", "~"][..]), |i| self.unary(i)),
unary_op,
),
))(input)
}
fn mul_div_rem(self, input: &'_ [Token]) -> CResult<'_, EvalResult> {
let (input, acc) = self.unary(input)?;
fold_many0(
pair(complete(one_of_punctuation(&["*", "/", "%"][..])), |i| {
self.unary(i)
}),
move || acc.clone(),
|mut acc, (op, val): (&[u8], EvalResult)| {
match op[0] as char {
'*' => acc *= &val,
'/' => acc /= &val,
'%' => acc %= &val,
_ => unreachable!(),
};
acc
},
)(input)
}
fn add_sub(self, input: &'_ [Token]) -> CResult<'_, EvalResult> {
let (input, acc) = self.mul_div_rem(input)?;
fold_many0(
pair(complete(one_of_punctuation(&["+", "-"][..])), |i| {
self.mul_div_rem(i)
}),
move || acc.clone(),
|mut acc, (op, val): (&[u8], EvalResult)| {
match op[0] as char {
'+' => acc += &val,
'-' => acc -= &val,
_ => unreachable!(),
};
acc
},
)(input)
}
fn shl_shr(self, input: &'_ [Token]) -> CResult<'_, EvalResult> {
let (input, acc) = self.add_sub(input)?;
numeric(fold_many0(
pair(complete(one_of_punctuation(&["<<", ">>"][..])), |i| {
self.add_sub(i)
}),
move || acc.clone(),
|mut acc, (op, val): (&[u8], EvalResult)| {
match op {
b"<<" => acc <<= &val,
b">>" => acc >>= &val,
_ => unreachable!(),
};
acc
},
))(input)
}
fn and(self, input: &'_ [Token]) -> CResult<'_, EvalResult> {
let (input, acc) = self.shl_shr(input)?;
numeric(fold_many0(
preceded(complete(p("&")), |i| self.shl_shr(i)),
move || acc.clone(),
|mut acc, val: EvalResult| {
acc &= &val;
acc
},
))(input)
}
fn xor(self, input: &'_ [Token]) -> CResult<'_, EvalResult> {
let (input, acc) = self.and(input)?;
numeric(fold_many0(
preceded(complete(p("^")), |i| self.and(i)),
move || acc.clone(),
|mut acc, val: EvalResult| {
acc ^= &val;
acc
},
))(input)
}
fn or(self, input: &'_ [Token]) -> CResult<'_, EvalResult> {
let (input, acc) = self.xor(input)?;
numeric(fold_many0(
preceded(complete(p("|")), |i| self.xor(i)),
move || acc.clone(),
|mut acc, val: EvalResult| {
acc |= &val;
acc
},
))(input)
}
#[inline(always)]
fn numeric_expr(self, input: &'_ [Token]) -> CResult<'_, EvalResult> {
self.or(input)
}
}
// =======================================================
// ============= Literals and identifiers ================
// =======================================================
impl<'a> PRef<'a> {
fn identifier(self, input: &'_ [Token]) -> CResult<'_, EvalResult> {
match input.split_first() {
None => Err(Err::Incomplete(Needed::new(1))),
Some((
&Token {
kind: TokenKind::Identifier,
ref raw,
},
rest,
)) => {
if let Some(r) = self.identifiers.get(&raw[..]) {
Ok((rest, r.clone()))
} else {
Err(Err::Error(
(input, crate::ErrorKind::UnknownIdentifier).into(),
))
}
}
Some(_) => Err(Err::Error(
(input, crate::ErrorKind::TypedToken(TokenKind::Identifier)).into(),
)),
}
}
fn literal(self, input: &'_ [Token]) -> CResult<'_, EvalResult> {
match input.split_first() {
None => Err(Err::Incomplete(Needed::new(1))),
Some((
&Token {
kind: TokenKind::Literal,
ref raw,
},
rest,
)) => match literal::parse(raw) {
Ok((_, result)) => Ok((rest, result)),
_ => Err(Err::Error((input, crate::ErrorKind::InvalidLiteral).into())),
},
Some(_) => Err(Err::Error(
(input, crate::ErrorKind::TypedToken(TokenKind::Literal)).into(),
)),
}
}
fn string(self, input: &'_ [Token]) -> CResult<'_, Vec<u8>> {
alt((
map_opt(|i| self.literal(i), EvalResult::as_str),
map_opt(|i| self.identifier(i), EvalResult::as_str),
))(input)
.to_cexpr_result()
}
// "string1" "string2" etc...
fn concat_str(self, input: &'_ [Token]) -> CResult<'_, EvalResult> {
map(
pair(|i| self.string(i), many0(complete(|i| self.string(i)))),
|(first, v)| {
Vec::into_iter(v)
.fold(first, |mut s, elem| {
Vec::extend_from_slice(&mut s, Vec::<u8>::as_slice(&elem));
s
})
.into()
},
)(input)
.to_cexpr_result()
}
fn expr(self, input: &'_ [Token]) -> CResult<'_, EvalResult> {
alt((
|i| self.numeric_expr(i),
delimited(p("("), |i| self.expr(i), p(")")),
|i| self.concat_str(i),
|i| self.literal(i),
|i| self.identifier(i),
))(input)
.to_cexpr_result()
}
fn macro_definition(self, input: &'_ [Token]) -> CResult<'_, (&'_ [u8], EvalResult)> {
pair(identifier_token, |i| self.expr(i))(input)
}
}
impl<'a> ::std::ops::Deref for PRef<'a> {
type Target = IdentifierParser<'a>;
fn deref(&self) -> &IdentifierParser<'a> {
self.0
}
}
impl<'ident> IdentifierParser<'ident> {
fn as_ref(&self) -> PRef<'_> {
PRef(self)
}
/// Create a new `IdentifierParser` with a set of known identifiers. When
/// a known identifier is encountered during parsing, it is substituted
/// for the value specified.
pub fn new(identifiers: &HashMap<Vec<u8>, EvalResult>) -> IdentifierParser<'_> {
IdentifierParser { identifiers }
}
/// Parse and evaluate an expression of a list of tokens.
///
/// Returns an error if the input is not a valid expression or if the token
/// stream contains comments, keywords or unknown identifiers.
pub fn expr<'a>(&self, input: &'a [Token]) -> CResult<'a, EvalResult> {
self.as_ref().expr(input)
}
/// Parse and evaluate a macro definition from a list of tokens.
///
/// Returns the identifier for the macro and its replacement evaluated as an
/// expression. The input should not include `#define`.
///
/// Returns an error if the replacement is not a valid expression, if called
/// on most function-like macros, or if the token stream contains comments,
/// keywords or unknown identifiers.
///
/// N.B. This is intended to fail on function-like macros, but if it the
/// macro takes a single argument, the argument name is defined as an
/// identifier, and the macro otherwise parses as an expression, it will
/// return a result even on function-like macros.
///
/// ```c
/// // will evaluate into IDENTIFIER
/// #define DELETE(IDENTIFIER)
/// // will evaluate into IDENTIFIER-3
/// #define NEGATIVE_THREE(IDENTIFIER) -3
/// ```
pub fn macro_definition<'a>(&self, input: &'a [Token]) -> CResult<'a, (&'a [u8], EvalResult)> {
crate::assert_full_parse(self.as_ref().macro_definition(input))
}
}
/// Parse and evaluate an expression of a list of tokens.
///
/// Returns an error if the input is not a valid expression or if the token
/// stream contains comments, keywords or identifiers.
pub fn expr(input: &[Token]) -> CResult<'_, EvalResult> {
IdentifierParser::new(&HashMap::new()).expr(input)
}
/// Parse and evaluate a macro definition from a list of tokens.
///
/// Returns the identifier for the macro and its replacement evaluated as an
/// expression. The input should not include `#define`.
///
/// Returns an error if the replacement is not a valid expression, if called
/// on a function-like macro, or if the token stream contains comments,
/// keywords or identifiers.
pub fn macro_definition(input: &[Token]) -> CResult<'_, (&'_ [u8], EvalResult)> {
IdentifierParser::new(&HashMap::new()).macro_definition(input)
}
/// Parse a functional macro declaration from a list of tokens.
///
/// Returns the identifier for the macro and the argument list (in order). The
/// input should not include `#define`. The actual definition is not parsed and
/// may be obtained from the unparsed data returned.
///
/// Returns an error if the input is not a functional macro or if the token
/// stream contains comments.
///
/// # Example
/// ```
/// use cexpr::expr::{IdentifierParser, EvalResult, fn_macro_declaration};
/// use cexpr::assert_full_parse;
/// use cexpr::token::Kind::*;
/// use cexpr::token::Token;
///
/// // #define SUFFIX(arg) arg "suffix"
/// let tokens = vec![
/// (Identifier, &b"SUFFIX"[..]).into(),
/// (Punctuation, &b"("[..]).into(),
/// (Identifier, &b"arg"[..]).into(),
/// (Punctuation, &b")"[..]).into(),
/// (Identifier, &b"arg"[..]).into(),
/// (Literal, &br#""suffix""#[..]).into(),
/// ];
///
/// // Try to parse the functional part
/// let (expr, (ident, args)) = fn_macro_declaration(&tokens).unwrap();
/// assert_eq!(ident, b"SUFFIX");
///
/// // Create dummy arguments
/// let idents = args.into_iter().map(|arg|
/// (arg.to_owned(), EvalResult::Str(b"test".to_vec()))
/// ).collect();
///
/// // Evaluate the macro
/// let (_, evaluated) = assert_full_parse(IdentifierParser::new(&idents).expr(expr)).unwrap();
/// assert_eq!(evaluated, EvalResult::Str(b"testsuffix".to_vec()));
/// ```
pub fn fn_macro_declaration(input: &[Token]) -> CResult<'_, (&[u8], Vec<&[u8]>)> {
pair(
identifier_token,
delimited(
p("("),
separated_list0(p(","), identifier_token),
p(")"),
),
)(input)
}

View File

@@ -0,0 +1,149 @@
// (C) Copyright 2016 Jethro G. Beekman
//
// Licensed under the Apache License, Version 2.0 <LICENSE-APACHE or
// http://www.apache.org/licenses/LICENSE-2.0> or the MIT license
// <LICENSE-MIT or http://opensource.org/licenses/MIT>, at your
// option. This file may not be copied, modified, or distributed
// except according to those terms.
//! A C expression parser and evaluator.
//!
//! This crate provides methods for parsing and evaluating simple C expressions. In general, the
//! crate can handle most arithmetic expressions that would appear in macros or the definition of
//! constants, as well as string and character constants.
//!
//! The main entry point for is [`token::parse`], which parses a byte string and returns its
//! evaluated value.
#![warn(rust_2018_idioms)]
#![warn(missing_docs)]
#![allow(deprecated)]
pub mod nom {
//! nom's result types, re-exported.
pub use nom::{error::ErrorKind, error::Error, Err, IResult, Needed};
}
pub mod expr;
pub mod literal;
pub mod token;
/// Parsing errors specific to C parsing
#[derive(Debug)]
pub enum ErrorKind {
/// Expected the specified token
ExactToken(token::Kind, &'static [u8]),
/// Expected one of the specified tokens
ExactTokens(token::Kind, &'static [&'static str]),
/// Expected a token of the specified kind
TypedToken(token::Kind),
/// An unknown identifier was encountered
UnknownIdentifier,
/// An invalid literal was encountered.
///
/// When encountered, this generally means a bug exists in the data that
/// was passed in or the parsing logic.
InvalidLiteral,
/// A full parse was requested, but data was left over after parsing finished.
Partial,
/// An error occurred in an underlying nom parser.
Parser(nom::ErrorKind),
}
impl From<nom::ErrorKind> for ErrorKind {
fn from(k: nom::ErrorKind) -> Self {
ErrorKind::Parser(k)
}
}
impl From<u32> for ErrorKind {
fn from(_: u32) -> Self {
ErrorKind::InvalidLiteral
}
}
/// Parsing errors specific to C parsing.
///
/// This is a superset of `(I, nom::ErrorKind)` that includes the additional errors specified by
/// [`ErrorKind`].
#[derive(Debug)]
pub struct Error<I> {
/// The remainder of the input stream at the time of the error.
pub input: I,
/// The error that occurred.
pub error: ErrorKind,
}
impl<I> From<(I, nom::ErrorKind)> for Error<I> {
fn from(e: (I, nom::ErrorKind)) -> Self {
Self::from((e.0, ErrorKind::from(e.1)))
}
}
impl<I> From<(I, ErrorKind)> for Error<I> {
fn from(e: (I, ErrorKind)) -> Self {
Self {
input: e.0,
error: e.1,
}
}
}
impl<I> From<::nom::error::Error<I>> for Error<I> {
fn from(e: ::nom::error::Error<I>) -> Self {
Self {
input: e.input,
error: e.code.into(),
}
}
}
impl<I> ::nom::error::ParseError<I> for Error<I> {
fn from_error_kind(input: I, kind: nom::ErrorKind) -> Self {
Self {
input,
error: kind.into(),
}
}
fn append(_: I, _: nom::ErrorKind, other: Self) -> Self {
other
}
}
// in lieu of https://github.com/Geal/nom/issues/1010
trait ToCexprResult<I, O> {
fn to_cexpr_result(self) -> nom::IResult<I, O, Error<I>>;
}
impl<I, O, E> ToCexprResult<I, O> for nom::IResult<I, O, E>
where
Error<I>: From<E>,
{
fn to_cexpr_result(self) -> nom::IResult<I, O, Error<I>> {
match self {
Ok(v) => Ok(v),
Err(nom::Err::Incomplete(n)) => Err(nom::Err::Incomplete(n)),
Err(nom::Err::Error(e)) => Err(nom::Err::Error(e.into())),
Err(nom::Err::Failure(e)) => Err(nom::Err::Failure(e.into())),
}
}
}
/// If the input result indicates a succesful parse, but there is data left,
/// return an `Error::Partial` instead.
pub fn assert_full_parse<'i, I: 'i, O, E>(
result: nom::IResult<&'i [I], O, E>,
) -> nom::IResult<&'i [I], O, Error<&'i [I]>>
where
Error<&'i [I]>: From<E>,
{
match result.to_cexpr_result() {
Ok((rem, output)) => {
if rem.is_empty() {
Ok((rem, output))
} else {
Err(nom::Err::Error((rem, ErrorKind::Partial).into()))
}
}
Err(nom::Err::Incomplete(n)) => Err(nom::Err::Incomplete(n)),
Err(nom::Err::Failure(e)) => Err(nom::Err::Failure(e)),
Err(nom::Err::Error(e)) => Err(nom::Err::Error(e)),
}
}

View File

@@ -0,0 +1,361 @@
// (C) Copyright 2016 Jethro G. Beekman
//
// Licensed under the Apache License, Version 2.0 <LICENSE-APACHE or
// http://www.apache.org/licenses/LICENSE-2.0> or the MIT license
// <LICENSE-MIT or http://opensource.org/licenses/MIT>, at your
// option. This file may not be copied, modified, or distributed
// except according to those terms.
//! Parsing C literals from byte slices.
//!
//! This will parse a representation of a C literal into a Rust type.
//!
//! # characters
//! Character literals are stored into the `CChar` type, which can hold values
//! that are not valid Unicode code points. ASCII characters are represented as
//! `char`, literal bytes with the high byte set are converted into the raw
//! representation. Escape sequences are supported. If hex and octal escapes
//! map to an ASCII character, that is used, otherwise, the raw encoding is
//! used, including for values over 255. Unicode escapes are checked for
//! validity and mapped to `char`. Character sequences are not supported. Width
//! prefixes are ignored.
//!
//! # strings
//! Strings are interpreted as byte vectors. Escape sequences are supported. If
//! hex and octal escapes map onto multi-byte characters, they are truncated to
//! one 8-bit character. Unicode escapes are converted into their UTF-8
//! encoding. Width prefixes are ignored.
//!
//! # integers
//! Integers are read into `i64`. Binary, octal, decimal and hexadecimal are
//! all supported. If the literal value is between `i64::MAX` and `u64::MAX`,
//! it is bit-cast to `i64`. Values over `u64::MAX` cannot be parsed. Width and
//! sign suffixes are ignored. Sign prefixes are not supported.
//!
//! # real numbers
//! Reals are read into `f64`. Width suffixes are ignored. Sign prefixes are
//! not supported in the significand. Hexadecimal floating points are not
//! supported.
use std::char;
use std::str::{self, FromStr};
use nom::branch::alt;
use nom::bytes::complete::is_not;
use nom::bytes::complete::tag;
use nom::character::complete::{char, one_of};
use nom::combinator::{complete, map, map_opt, opt, recognize};
use nom::multi::{fold_many0, many0, many1, many_m_n};
use nom::sequence::{delimited, pair, preceded, terminated, tuple};
use nom::*;
use crate::expr::EvalResult;
use crate::ToCexprResult;
#[derive(Debug, Copy, Clone, PartialEq, Eq)]
/// Representation of a C character
pub enum CChar {
/// A character that can be represented as a `char`
Char(char),
/// Any other character (8-bit characters, unicode surrogates, etc.)
Raw(u64),
}
impl From<u8> for CChar {
fn from(i: u8) -> CChar {
match i {
0..=0x7f => CChar::Char(i as u8 as char),
_ => CChar::Raw(i as u64),
}
}
}
// A non-allocating version of this would be nice...
impl std::convert::Into<Vec<u8>> for CChar {
fn into(self) -> Vec<u8> {
match self {
CChar::Char(c) => {
let mut s = String::with_capacity(4);
s.extend(&[c]);
s.into_bytes()
}
CChar::Raw(i) => {
let mut v = Vec::with_capacity(1);
v.push(i as u8);
v
}
}
}
}
/// ensures the child parser consumes the whole input
pub fn full<I: Clone, O, F>(
f: F,
) -> impl Fn(I) -> nom::IResult<I, O>
where
I: nom::InputLength,
F: Fn(I) -> nom::IResult<I, O>,
{
move |input| {
let res = f(input);
match res {
Ok((i, o)) => {
if i.input_len() == 0 {
Ok((i, o))
} else {
Err(nom::Err::Error(nom::error::Error::new(i, nom::error::ErrorKind::Complete)))
}
}
r => r,
}
}
}
// =================================
// ======== matching digits ========
// =================================
macro_rules! byte {
($($p: pat)|* ) => {{
fn parser(i: &[u8]) -> crate::nom::IResult<&[u8], u8> {
match i.split_first() {
$(Some((&c @ $p,rest)))|* => Ok((rest,c)),
Some(_) => Err(nom::Err::Error(nom::error::Error::new(i, nom::error::ErrorKind::OneOf))),
None => Err(nom::Err::Incomplete(Needed::new(1))),
}
}
parser
}}
}
fn binary(i: &[u8]) -> nom::IResult<&[u8], u8> {
byte!(b'0'..=b'1')(i)
}
fn octal(i: &[u8]) -> nom::IResult<&[u8], u8> {
byte!(b'0'..=b'7')(i)
}
fn decimal(i: &[u8]) -> nom::IResult<&[u8], u8> {
byte!(b'0'..=b'9')(i)
}
fn hexadecimal(i: &[u8]) -> nom::IResult<&[u8], u8> {
byte!(b'0' ..= b'9' | b'a' ..= b'f' | b'A' ..= b'F')(i)
}
// ========================================
// ======== characters and strings ========
// ========================================
fn escape2char(c: char) -> CChar {
CChar::Char(match c {
'a' => '\x07',
'b' => '\x08',
'f' => '\x0c',
'n' => '\n',
'r' => '\r',
't' => '\t',
'v' => '\x0b',
_ => unreachable!("invalid escape {}", c),
})
}
fn c_raw_escape(n: Vec<u8>, radix: u32) -> Option<CChar> {
str::from_utf8(&n)
.ok()
.and_then(|i| u64::from_str_radix(i, radix).ok())
.map(|i| match i {
0..=0x7f => CChar::Char(i as u8 as char),
_ => CChar::Raw(i),
})
}
fn c_unicode_escape(n: Vec<u8>) -> Option<CChar> {
str::from_utf8(&n)
.ok()
.and_then(|i| u32::from_str_radix(i, 16).ok())
.and_then(char::from_u32)
.map(CChar::Char)
}
fn escaped_char(i: &[u8]) -> nom::IResult<&[u8], CChar> {
preceded(
char('\\'),
alt((
map(one_of(r#"'"?\"#), CChar::Char),
map(one_of("abfnrtv"), escape2char),
map_opt(many_m_n(1, 3, octal), |v| c_raw_escape(v, 8)),
map_opt(preceded(char('x'), many1(hexadecimal)), |v| {
c_raw_escape(v, 16)
}),
map_opt(
preceded(char('u'), many_m_n(4, 4, hexadecimal)),
c_unicode_escape,
),
map_opt(
preceded(char('U'), many_m_n(8, 8, hexadecimal)),
c_unicode_escape,
),
)),
)(i)
}
fn c_width_prefix(i: &[u8]) -> nom::IResult<&[u8], &[u8]> {
alt((tag("u8"), tag("u"), tag("U"), tag("L")))(i)
}
fn c_char(i: &[u8]) -> nom::IResult<&[u8], CChar> {
delimited(
terminated(opt(c_width_prefix), char('\'')),
alt((
escaped_char,
map(byte!(0 ..= 91 /* \=92 */ | 93 ..= 255), CChar::from),
)),
char('\''),
)(i)
}
fn c_string(i: &[u8]) -> nom::IResult<&[u8], Vec<u8>> {
delimited(
alt((preceded(c_width_prefix, char('"')), char('"'))),
fold_many0(
alt((
map(escaped_char, |c: CChar| c.into()),
map(is_not([b'\\', b'"']), |c: &[u8]| c.into()),
)),
Vec::new,
|mut v: Vec<u8>, res: Vec<u8>| {
v.extend_from_slice(&res);
v
},
),
char('"'),
)(i)
}
// ================================
// ======== parse integers ========
// ================================
fn c_int_radix(n: Vec<u8>, radix: u32) -> Option<u64> {
str::from_utf8(&n)
.ok()
.and_then(|i| u64::from_str_radix(i, radix).ok())
}
fn take_ul(input: &[u8]) -> IResult<&[u8], &[u8]> {
let r = input.split_at_position(|c| c != b'u' && c != b'U' && c != b'l' && c != b'L');
match r {
Err(Err::Incomplete(_)) => Ok((&input[input.len()..], input)),
res => res,
}
}
fn c_int(i: &[u8]) -> nom::IResult<&[u8], i64> {
map(
terminated(
alt((
map_opt(preceded(tag("0x"), many1(complete(hexadecimal))), |v| {
c_int_radix(v, 16)
}),
map_opt(preceded(tag("0X"), many1(complete(hexadecimal))), |v| {
c_int_radix(v, 16)
}),
map_opt(preceded(tag("0b"), many1(complete(binary))), |v| {
c_int_radix(v, 2)
}),
map_opt(preceded(tag("0B"), many1(complete(binary))), |v| {
c_int_radix(v, 2)
}),
map_opt(preceded(char('0'), many1(complete(octal))), |v| {
c_int_radix(v, 8)
}),
map_opt(many1(complete(decimal)), |v| c_int_radix(v, 10)),
|input| Err(crate::nom::Err::Error(nom::error::Error::new(input, crate::nom::ErrorKind::Fix))),
)),
opt(take_ul),
),
|i| i as i64,
)(i)
}
// ==============================
// ======== parse floats ========
// ==============================
fn float_width(i: &[u8]) -> nom::IResult<&[u8], u8> {
nom::combinator::complete(byte!(b'f' | b'l' | b'F' | b'L'))(i)
}
fn float_exp(i: &[u8]) -> nom::IResult<&[u8], (Option<u8>, Vec<u8>)> {
preceded(
byte!(b'e' | b'E'),
pair(opt(byte!(b'-' | b'+')), many1(complete(decimal))),
)(i)
}
fn c_float(i: &[u8]) -> nom::IResult<&[u8], f64> {
map_opt(
alt((
terminated(
recognize(tuple((
many1(complete(decimal)),
byte!(b'.'),
many0(complete(decimal)),
))),
opt(float_width),
),
terminated(
recognize(tuple((
many0(complete(decimal)),
byte!(b'.'),
many1(complete(decimal)),
))),
opt(float_width),
),
terminated(
recognize(tuple((
many0(complete(decimal)),
opt(byte!(b'.')),
many1(complete(decimal)),
float_exp,
))),
opt(float_width),
),
terminated(
recognize(tuple((
many1(complete(decimal)),
opt(byte!(b'.')),
many0(complete(decimal)),
float_exp,
))),
opt(float_width),
),
terminated(recognize(many1(complete(decimal))), float_width),
)),
|v| str::from_utf8(v).ok().and_then(|i| f64::from_str(i).ok()),
)(i)
}
// ================================
// ======== main interface ========
// ================================
fn one_literal(input: &[u8]) -> nom::IResult<&[u8], EvalResult, crate::Error<&[u8]>> {
alt((
map(full(c_char), EvalResult::Char),
map(full(c_int), |i| EvalResult::Int(::std::num::Wrapping(i))),
map(full(c_float), EvalResult::Float),
map(full(c_string), EvalResult::Str),
))(input)
.to_cexpr_result()
}
/// Parse a C literal.
///
/// The input must contain exactly the representation of a single literal
/// token, and in particular no whitespace or sign prefixes.
pub fn parse(input: &[u8]) -> IResult<&[u8], EvalResult, crate::Error<&[u8]>> {
crate::assert_full_parse(one_literal(input))
}

View File

@@ -0,0 +1,44 @@
// (C) Copyright 2016 Jethro G. Beekman
//
// Licensed under the Apache License, Version 2.0 <LICENSE-APACHE or
// http://www.apache.org/licenses/LICENSE-2.0> or the MIT license
// <LICENSE-MIT or http://opensource.org/licenses/MIT>, at your
// option. This file may not be copied, modified, or distributed
// except according to those terms.
//! Representation of a C token
//!
//! This is designed to map onto a libclang CXToken.
#[derive(Debug, Copy, Clone, PartialEq, Eq)]
#[allow(missing_docs)]
pub enum Kind {
Punctuation,
Keyword,
Identifier,
Literal,
Comment,
}
/// A single token in a C expression.
#[derive(Debug, Clone, PartialEq, Eq)]
pub struct Token {
/// The type of this token.
pub kind: Kind,
/// The bytes that make up the token.
pub raw: Box<[u8]>,
}
impl<'a> From<(Kind, &'a [u8])> for Token {
fn from((kind, value): (Kind, &'a [u8])) -> Token {
Token {
kind,
raw: value.to_owned().into_boxed_slice(),
}
}
}
/// Remove all comment tokens from a vector of tokens
pub fn remove_comments(v: &mut Vec<Token>) -> &mut Vec<Token> {
v.retain(|t| t.kind != Kind::Comment);
v
}

View File

@@ -0,0 +1,339 @@
// (C) Copyright 2016 Jethro G. Beekman
//
// Licensed under the Apache License, Version 2.0 <LICENSE-APACHE or
// http://www.apache.org/licenses/LICENSE-2.0> or the MIT license
// <LICENSE-MIT or http://opensource.org/licenses/MIT>, at your
// option. This file may not be copied, modified, or distributed
// except according to those terms.
extern crate cexpr;
extern crate clang_sys;
use std::collections::HashMap;
use std::io::Write;
use std::str::{self, FromStr};
use std::{char, ffi, mem, ptr, slice};
use cexpr::assert_full_parse;
use cexpr::expr::{fn_macro_declaration, EvalResult, IdentifierParser};
use cexpr::literal::CChar;
use cexpr::token::Token;
use clang_sys::*;
// main testing routine
fn test_definition(
ident: Vec<u8>,
tokens: &[Token],
idents: &mut HashMap<Vec<u8>, EvalResult>,
) -> bool {
fn bytes_to_int(value: &[u8]) -> Option<EvalResult> {
str::from_utf8(value)
.ok()
.map(|s| s.replace("n", "-"))
.map(|s| s.replace("_", ""))
.and_then(|v| i64::from_str(&v).ok())
.map(::std::num::Wrapping)
.map(Int)
}
use cexpr::expr::EvalResult::*;
let display_name = String::from_utf8_lossy(&ident).into_owned();
let functional;
let test = {
// Split name such as Str_test_string into (Str,test_string)
let pos = ident
.iter()
.position(|c| *c == b'_')
.expect(&format!("Invalid definition in testcase: {}", display_name));
let mut expected = &ident[..pos];
let mut value = &ident[(pos + 1)..];
functional = expected == b"Fn";
if functional {
let ident = value;
let pos = ident
.iter()
.position(|c| *c == b'_')
.expect(&format!("Invalid definition in testcase: {}", display_name));
expected = &ident[..pos];
value = &ident[(pos + 1)..];
}
if expected == b"Str" {
let mut splits = value.split(|c| *c == b'U');
let mut s = Vec::with_capacity(value.len());
s.extend_from_slice(splits.next().unwrap());
for split in splits {
let (chr, rest) = split.split_at(6);
let chr = u32::from_str_radix(str::from_utf8(chr).unwrap(), 16).unwrap();
write!(s, "{}", char::from_u32(chr).unwrap()).unwrap();
s.extend_from_slice(rest);
}
Some(Str(s))
} else if expected == b"Int" {
bytes_to_int(value)
} else if expected == b"Float" {
str::from_utf8(value)
.ok()
.map(|s| s.replace("n", "-").replace("p", "."))
.and_then(|v| f64::from_str(&v).ok())
.map(Float)
} else if expected == b"CharRaw" {
str::from_utf8(value)
.ok()
.and_then(|v| u64::from_str(v).ok())
.map(CChar::Raw)
.map(Char)
} else if expected == b"CharChar" {
str::from_utf8(value)
.ok()
.and_then(|v| u32::from_str(v).ok())
.and_then(char::from_u32)
.map(CChar::Char)
.map(Char)
} else {
Some(Invalid)
}
.expect(&format!("Invalid definition in testcase: {}", display_name))
};
let result = if functional {
let mut fnidents;
let expr_tokens;
match fn_macro_declaration(&tokens) {
Ok((rest, (_, args))) => {
fnidents = idents.clone();
expr_tokens = rest;
for arg in args {
let val = match test {
Int(_) => bytes_to_int(&arg),
Str(_) => Some(Str(arg.to_owned())),
_ => unimplemented!(),
}
.expect(&format!(
"Invalid argument in functional macro testcase: {}",
display_name
));
fnidents.insert(arg.to_owned(), val);
}
}
e => {
println!(
"Failed test for {}, unable to parse functional macro declaration: {:?}",
display_name, e
);
return false;
}
}
assert_full_parse(IdentifierParser::new(&fnidents).expr(&expr_tokens))
} else {
IdentifierParser::new(idents)
.macro_definition(&tokens)
.map(|(i, (_, val))| (i, val))
};
match result {
Ok((_, val)) => {
if val == test {
if let Some(_) = idents.insert(ident, val) {
panic!("Duplicate definition for testcase: {}", display_name);
}
true
} else {
println!(
"Failed test for {}, expected {:?}, got {:?}",
display_name, test, val
);
false
}
}
e => {
if test == Invalid {
true
} else {
println!(
"Failed test for {}, expected {:?}, got {:?}",
display_name, test, e
);
false
}
}
}
}
// support code for the clang lexer
unsafe fn clang_str_to_vec(s: CXString) -> Vec<u8> {
let vec = ffi::CStr::from_ptr(clang_getCString(s))
.to_bytes()
.to_owned();
clang_disposeString(s);
vec
}
#[allow(non_upper_case_globals)]
unsafe fn token_clang_to_cexpr(tu: CXTranslationUnit, orig: &CXToken) -> Token {
Token {
kind: match clang_getTokenKind(*orig) {
CXToken_Comment => cexpr::token::Kind::Comment,
CXToken_Identifier => cexpr::token::Kind::Identifier,
CXToken_Keyword => cexpr::token::Kind::Keyword,
CXToken_Literal => cexpr::token::Kind::Literal,
CXToken_Punctuation => cexpr::token::Kind::Punctuation,
_ => panic!("invalid token kind: {:?}", *orig),
},
raw: clang_str_to_vec(clang_getTokenSpelling(tu, *orig)).into_boxed_slice(),
}
}
extern "C" fn visit_children_thunk<F>(
cur: CXCursor,
parent: CXCursor,
closure: CXClientData,
) -> CXChildVisitResult
where
F: FnMut(CXCursor, CXCursor) -> CXChildVisitResult,
{
unsafe { (&mut *(closure as *mut F))(cur, parent) }
}
unsafe fn visit_children<F>(cursor: CXCursor, mut f: F)
where
F: FnMut(CXCursor, CXCursor) -> CXChildVisitResult,
{
clang_visitChildren(
cursor,
visit_children_thunk::<F> as _,
&mut f as *mut F as CXClientData,
);
}
unsafe fn location_in_scope(r: CXSourceRange) -> bool {
let start = clang_getRangeStart(r);
let mut file = ptr::null_mut();
clang_getSpellingLocation(
start,
&mut file,
ptr::null_mut(),
ptr::null_mut(),
ptr::null_mut(),
);
clang_Location_isFromMainFile(start) != 0
&& clang_Location_isInSystemHeader(start) == 0
&& file != ptr::null_mut()
}
/// tokenize_range_adjust can be used to work around LLVM bug 9069
/// https://bugs.llvm.org//show_bug.cgi?id=9069
fn file_visit_macros<F: FnMut(Vec<u8>, Vec<Token>)>(
file: &str,
tokenize_range_adjust: bool,
mut visitor: F,
) {
unsafe {
let tu = {
let index = clang_createIndex(true as _, false as _);
let cfile = ffi::CString::new(file).unwrap();
let mut tu = mem::MaybeUninit::uninit();
assert!(
clang_parseTranslationUnit2(
index,
cfile.as_ptr(),
[b"-std=c11\0".as_ptr() as *const ::std::os::raw::c_char].as_ptr(),
1,
ptr::null_mut(),
0,
CXTranslationUnit_DetailedPreprocessingRecord,
&mut *tu.as_mut_ptr()
) == CXError_Success,
"Failure reading test case {}",
file
);
tu.assume_init()
};
visit_children(clang_getTranslationUnitCursor(tu), |cur, _parent| {
if cur.kind == CXCursor_MacroDefinition {
let mut range = clang_getCursorExtent(cur);
if !location_in_scope(range) {
return CXChildVisit_Continue;
}
range.end_int_data -= if tokenize_range_adjust { 1 } else { 0 };
let mut token_ptr = ptr::null_mut();
let mut num = 0;
clang_tokenize(tu, range, &mut token_ptr, &mut num);
if token_ptr != ptr::null_mut() {
let tokens = slice::from_raw_parts(token_ptr, num as usize);
let tokens: Vec<_> = tokens
.iter()
.filter_map(|t| {
if clang_getTokenKind(*t) != CXToken_Comment {
Some(token_clang_to_cexpr(tu, t))
} else {
None
}
})
.collect();
clang_disposeTokens(tu, token_ptr, num);
visitor(clang_str_to_vec(clang_getCursorSpelling(cur)), tokens)
}
}
CXChildVisit_Continue
});
clang_disposeTranslationUnit(tu);
};
}
fn test_file(file: &str) -> bool {
let mut idents = HashMap::new();
let mut all_succeeded = true;
file_visit_macros(file, fix_bug_9069(), |ident, tokens| {
all_succeeded &= test_definition(ident, &tokens, &mut idents)
});
all_succeeded
}
fn fix_bug_9069() -> bool {
fn check_bug_9069() -> bool {
let mut token_sets = vec![];
file_visit_macros(
"tests/input/test_llvm_bug_9069.h",
false,
|ident, tokens| {
assert_eq!(&ident, b"A");
token_sets.push(tokens);
},
);
assert_eq!(token_sets.len(), 2);
token_sets[0] != token_sets[1]
}
use std::sync::atomic::{AtomicBool, Ordering};
use std::sync::Once;
static CHECK_FIX: Once = Once::new();
static FIX: AtomicBool = AtomicBool::new(false);
CHECK_FIX.call_once(|| FIX.store(check_bug_9069(), Ordering::SeqCst));
FIX.load(Ordering::SeqCst)
}
macro_rules! test_file {
($f:ident) => {
#[test]
fn $f() {
assert!(
test_file(concat!("tests/input/", stringify!($f), ".h")),
"test_file"
)
}
};
}
test_file!(floats);
test_file!(chars);
test_file!(strings);
test_file!(int_signed);
test_file!(int_unsigned);
test_file!(fail);

View File

@@ -0,0 +1,3 @@
#define CharChar_65 'A'
#define CharChar_127849 '\U0001f369' // 🍩
#define CharRaw_255 U'\xff'

View File

@@ -0,0 +1,9 @@
#define FAIL_function_like(x) 3
#define FAIL_empty
#define FAIL_invalid_for_radix 0b2
#define FAIL_shift_by_float 3<<1f
#define FAIL_unknown_identifier UNKNOWN
#define Int_0 0
#define Str_str "str"
#define FAIL_concat_integer "test" Str_str Int_0
#define FAIL_too_large_int 18446744073709551616

View File

@@ -0,0 +1,8 @@
#define Float_0 0.
#define Float_1 1f
#define Float_p1 .1
#define Float_2 2.0
#define Float_1000 1e3
#define Float_2000 2e+3
#define Float_p001 1e-3
#define Float_80 10.0*(1<<3)

View File

@@ -0,0 +1,3 @@
#define Int_n3 -(-(-3))
#define Int_n5 -3-2
#define Int_n9223372036854775808 -9223372036854775808

View File

@@ -0,0 +1,29 @@
#define Int_456 456
#define Int_0 0
#define Int_1 0b1
#define Int_2 0x2
#define Int_3 3L
#define Int_4 0X4
#define Int_5 0B101
#define Int_63 077
#define Int_123 123
#define Int_124 124u
#define Int_125 125uL
#define Int_126 126LuL
#define Int_16 (((1)<<4ULL))/*comment*/
#define Int_13 1|8^6&2<<1
#define Int_47 32|15
#define Int_38 (32|15)^9
#define Int_6 ((32|15)^9)&7
#define Int_12 (((32|15)^9)&7)<<1
#define Int_17 ((((32|15)^9)&7)<<1)+5
#define Int_15 (((((32|15)^9)&7)<<1)+5)-2
#define Int_60 ((((((32|15)^9)&7)<<1)+5)-2)*4
#define Int_30 (((((((32|15)^9)&7)<<1)+5)-2)*4)/2
#define Int_39 32|15^9&7<<1+5-2*4/2
#define Int_n1 18446744073709551615 /*2^64-1*/
#define Int_n9223372036854775808 9223372036854775808
#define Fn_Int_9(_3) _3*3

View File

@@ -0,0 +1,17 @@
#define Str_ ""
#define Str_str "str"
#define Str_unicode u"unicode"
#define Str_long L"long"
#define Str_concat u"con" L"cat"
#define Str_concat_parens ("concat" U"_parens")
#define Str_concat_identifier (Str_concat L"_identifier")
#define Str_hex_escape_all "\x68\x65\x78\x5f\x65\x73\x63\x61\x70\x65\x5f\x61\x6c\x6c"
#define Str_hex_escape_hex "h\x65x_\x65s\x63\x61p\x65_h\x65x"
#define Str_quote_U000022_escape "quote_\"_escape"
#define Str_Fly_away_in_my_space_U01F680_You_no_need_put_U01F4B5_in_my_pocket \
u8"Fly_away_in_my_space_🚀_You_no_need_put_💵_in_my_pocket"
#define Fn_Str_no_args() "no_args"
#define Fn_Str_no_args_concat() "no_args_" Str_concat
#define Fn_Str_prepend_arg(arg) "prepend_" arg
#define Fn_Str_two_args(two, args) two "_" args
#define Fn_Str_three_args(three, _, args) three _ args

View File

@@ -0,0 +1,4 @@
// The following two definitions should yield the same list of tokens.
// If https://bugs.llvm.org//show_bug.cgi?id=9069 is not fixed, they don't.
#define A 1
#define A 1