Merge branch 'master' into compiler-tests

This commit is contained in:
damirka 2021-05-12 20:02:03 +03:00
commit cb2bd62ea9
78 changed files with 768 additions and 524 deletions

28
Cargo.lock generated
View File

@ -424,10 +424,10 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ea221b5284a47e40033bf9b66f35f984ec0ea2931eb03505246cd27a963f981b"
[[package]]
name = "cpuid-bool"
version = "0.1.2"
name = "cpufeatures"
version = "0.1.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "8aebca1129a03dc6dc2b127edd729435bbc4a37e1d5f4d7513165089ceb02634"
checksum = "5cd5a7748210e7ec1a9696610b1015e6e31fbf58f77a160801f124bd1c36592a"
[[package]]
name = "crc32fast"
@ -2488,9 +2488,9 @@ dependencies = [
[[package]]
name = "self_update"
version = "0.26.0"
version = "0.27.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9031099ba3962ce8faaff991066bcbe6ec1f7ccb0be12a4b56733028ae090054"
checksum = "6fb85f1802f7b987237b8525c0fde86ea86f31c957c1875467c727d5b921179c"
dependencies = [
"hyper",
"indicatif",
@ -2616,13 +2616,13 @@ dependencies = [
[[package]]
name = "sha2"
version = "0.9.3"
version = "0.9.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "fa827a14b29ab7f44778d14a88d3cb76e949c45083f7dbfa507d0cb699dc12de"
checksum = "d8f6b75b17576b792bef0db1bcc4b8b8bcdf9506744cf34b974195487af6cff2"
dependencies = [
"block-buffer 0.9.0",
"cfg-if 1.0.0",
"cpuid-bool",
"cpufeatures",
"digest 0.9.0",
"opaque-debug 0.3.0",
]
@ -3136,9 +3136,9 @@ checksum = "360dfd1d6d30e05fda32ace2c8c70e9c0a9da713275777f5a4dbb8a1893930c6"
[[package]]
name = "tracing"
version = "0.1.25"
version = "0.1.26"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "01ebdc2bb4498ab1ab5f5b73c5803825e60199229ccba0698170e3be0e7f959f"
checksum = "09adeb8c97449311ccd28a427f96fb563e7fd31aabf994189879d9da2394b89d"
dependencies = [
"cfg-if 1.0.0",
"pin-project-lite",
@ -3159,9 +3159,9 @@ dependencies = [
[[package]]
name = "tracing-core"
version = "0.1.17"
version = "0.1.18"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "f50de3927f93d202783f4513cda820ab47ef17f624b03c096e86ef00c67e6b5f"
checksum = "a9ff14f98b1a4b289c6248a023c1c2fa1491062964e9fed67ab29c4e4da4a052"
dependencies = [
"lazy_static",
]
@ -3199,9 +3199,9 @@ dependencies = [
[[package]]
name = "tracing-subscriber"
version = "0.2.17"
version = "0.2.18"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "705096c6f83bf68ea5d357a6aa01829ddbdac531b357b45abeca842938085baa"
checksum = "aa5553bf0883ba7c9cbe493b085c29926bd41b66afc31ff72cf17ff4fb60dcd5"
dependencies = [
"ansi_term 0.12.1",
"chrono",

View File

@ -125,7 +125,7 @@ version = "0.11.3"
features = [ "blocking", "json", "multipart" ]
[dependencies.self_update]
version = "0.26.0"
version = "0.27.0"
features = [ "archive-zip" ]
[dependencies.serde]

View File

@ -105,7 +105,7 @@ fn resolve_import_package_access(
package: &PackageAccess,
) {
match package {
PackageAccess::Star(span) => {
PackageAccess::Star { span } => {
output.push((package_segments, ImportSymbol::All, span.clone()));
}
PackageAccess::SubPackage(subpackage) => {
@ -414,7 +414,7 @@ pub fn reform_ast<'a>(program: &Program<'a>) -> leo_ast::Program {
.map(|(module, _)| leo_ast::ImportStatement {
package_or_packages: leo_ast::PackageOrPackages::Package(leo_ast::Package {
name: Identifier::new(module.clone().into()),
access: leo_ast::PackageAccess::Star(Span::default()),
access: leo_ast::PackageAccess::Star { span: Span::default() },
span: Default::default(),
}),
span: Span::default(),

View File

@ -1,5 +1,5 @@
circuit Foo {
x: u32
x: u32;
}
function main() {

View File

@ -1,5 +1,5 @@
circuit Foo {
x: u32
x: u32;
}
function main() {

View File

@ -1,5 +1,5 @@
circuit Foo {
a: u8,
a: u8;
function bar() {}
}

View File

@ -1,5 +1,5 @@
circuit Foo {
a: u8,
a: u8;
function bar() {}

View File

@ -1,5 +1,5 @@
circuit Foo {
a: u8,
a: u8;
function bar() {}

View File

@ -1,5 +1,5 @@
circuit Foo {
a: u8,
a: u8;
function set_a(self, new: u8) {
self.a = new;

View File

@ -1,5 +1,5 @@
circuit Foo {
a: u8,
a: u8;
}
function main() {

View File

@ -1,5 +1,5 @@
circuit Foo {
f: u32,
f: u32;
function bar() -> u32 {
return f;

View File

@ -1,6 +1,6 @@
// Circuits are immutable by default.
circuit Foo {
x: u32
x: u32;
}
function main() {

View File

@ -1,5 +1,5 @@
circuit Foo {
a: u32,
a: u32;
}
circuit Bar {

View File

@ -1,5 +1,5 @@
circuit Foo {
x: u32
x: u32;
}
function main() {

View File

@ -1,5 +1,5 @@
circuit Foo {
x: u32,
x: u32;
function add_x(self, y: u32) -> u32 {
return self.x + y;

View File

@ -1,5 +1,5 @@
circuit Foo {
x: u32,
x: u32;
}
function main() {

View File

@ -1,5 +1,5 @@
circuit Foo {
foo: u32,
foo: u32;
function bar() -> u32 {
return 1u32;

View File

@ -1,5 +1,5 @@
circuit Foo {
a: u8,
a: u8;
function set_a(mut self, new: u8) {
self.a = new;

View File

@ -5,7 +5,7 @@ function main() {
}
circuit Foo {
a: u32
a: u32;
function bar(mut self) {
if true {

View File

@ -1,5 +1,5 @@
circuit Foo {
a: u8,
a: u8;
}
function main() {

View File

@ -1,5 +1,5 @@
circuit PedersenHash {
parameters: [u32; 512]
parameters: [u32; 512];
function new(const parameters: [u32; 512]) -> Self {
return Self { parameters: parameters };

View File

@ -1,5 +1,5 @@
circuit Foo {
f: u32,
f: u32;
function bar(self) -> u32 {
return self.f;

View File

@ -58,8 +58,8 @@ fn test_imports() {
let mut imports = crate::mocked_resolver(&context);
let test_import = r#"
circuit Point {
x: u32
y: u32
x: u32;
y: u32;
}
function foo() -> u32 {

View File

@ -1,3 +1,3 @@
circuit Bat {
t: u32
t: u32;
}

View File

@ -1,7 +1,7 @@
circuit Baz {
z: u32
z: u32;
}
circuit Bazzar {
a: u32
a: u32;
}

View File

@ -1,3 +1,3 @@
circuit Bar {
r: u32
r: u32;
}

View File

@ -1,3 +1,3 @@
circuit Car {
c: u32
c: u32;
}

View File

@ -1,6 +1,6 @@
circuit Point {
x: u32
y: u32
x: u32;
y: u32;
}
function foo() -> u32 {

View File

@ -1,6 +1,6 @@
// Adding the `mut` keyword makes a circuit variable mutable.
circuit Foo {
x: u32
x: u32;
}
function main() {

View File

@ -1,6 +1,6 @@
// Adding the `mut` keyword makes a circuit variable mutable.
circuit Foo {
x: u32
x: u32;
}
function main() {

View File

@ -36,7 +36,7 @@ impl CanonicalizeError {
}
pub fn invalid_array_dimension_size(span: &Span) -> Self {
let message = "recieved dimension size of 0, expected it to be 1 or larger.".to_string();
let message = "received dimension size of 0, expected it to be 1 or larger.".to_string();
Self::new_from_span(message, span)
}

View File

@ -21,7 +21,7 @@ use std::fmt;
#[derive(Clone, Eq, Hash, PartialEq, Serialize, Deserialize)]
pub enum PackageAccess {
Star(Span),
Star { span: Span },
SubPackage(Box<Package>),
Symbol(ImportSymbol),
Multiple(Packages),
@ -30,7 +30,7 @@ pub enum PackageAccess {
impl Node for PackageAccess {
fn span(&self) -> &Span {
match self {
PackageAccess::Star(span) => span,
PackageAccess::Star { span } => span,
PackageAccess::SubPackage(package) => &package.span,
PackageAccess::Symbol(package) => &package.span,
PackageAccess::Multiple(package) => &package.span,
@ -39,7 +39,7 @@ impl Node for PackageAccess {
fn set_span(&mut self, span: Span) {
match self {
PackageAccess::Star(package) => *package = span,
PackageAccess::Star { span } => *span = span.clone(),
PackageAccess::SubPackage(package) => package.span = span,
PackageAccess::Symbol(package) => package.span = span,
PackageAccess::Multiple(package) => package.span = span,
@ -50,7 +50,7 @@ impl Node for PackageAccess {
impl PackageAccess {
fn format(&self, f: &mut fmt::Formatter) -> fmt::Result {
match self {
PackageAccess::Star(ref _span) => write!(f, "*"),
PackageAccess::Star { .. } => write!(f, "*"),
PackageAccess::SubPackage(ref package) => write!(f, "{}", package),
PackageAccess::Symbol(ref symbol) => write!(f, "{}", symbol),
PackageAccess::Multiple(ref packages) => {

View File

@ -1,5 +1,5 @@
circuit Foo {
x: u32
x: u32;
function new() -> Self {
let new: Self = Self {

View File

@ -1,5 +1,5 @@
circuit Foo {
x: u32
x: u32;
function new() -> Self {
let new: Self = Self {

View File

@ -1,6 +1,6 @@
circuit Foo {
f: u8,
y: (u8, u8),
f: u8;
y: (u8, u8);
function z (mut self) -> u16 {
self.y.0 += 1u8;

View File

@ -21,20 +21,19 @@ DRAFT
The purpose of this proposal is to provide initial support for strings in Leo.
Since strings are sequences of characters,
the proposal inextricably also involves characters.
This proposal is described as 'initial,'
This proposal is described as initial,
because it provides some basic features that we may extend in the future;
the initial features should be sufficiently simple and conservative
that they should not limit the design of the future features.
This proposal adds a new scalar type for characters
This proposal adds a new scalar type for characters,
along with a new kind of literals to denote characters.
A string is then simply as an array of characters,
A string is then simply an array of characters,
but this proposal also adds a new kind of literals to denote strings
more directly than via character array construction expressions.
Along with equality and inequality, which always apply to every Leo type,
this proposal also introduces operations for
_[TODO: Summarize initial set of built-in or library operations
on characters and strings.]_.
this proposal also introduces some operations on characters and strings
that can be implemented over time.
By not prescribing a new type for strings,
this initial proposal leaves the door open
@ -48,25 +47,23 @@ simple ones like URLs and token ticker symbols,
and more complex ones like Bech32 encoding,
edit distance in strings representing proteins,
and zero-knowledge proofs of occurrences or absences of patterns in textual logs.
_[TODO: Add more use cases if needed.]_
# Design
Since strings are sequences of characters,
a design for strings inextricably also involves a design for characters.
Thus, we first present a design for characters, then for strings.
After that, we discuss the relation with Leo's existing format strings.
We conclude this design section
with a discussion of possible future extensions.
Thus, we first present a design for both characters and strings.
## Characters
We add a new scalar type, `char` for characters.
In accord with Leo's strong typing,
this new type is separate from all the other scalar types.
Type casts (a future feature of Leo) will be needed
to convert between `char` and other types.
The set of values of type `char` is isomorphic to
the set of Unicode code points from 0 to 10FFFFh (both inclusive).
the set of Unicode code points from 0 to 10FFFF (both inclusive).
That is, we support Unicode characters, more precisely code points
(this may include some invalid code points,
but it is simpler to allow every code point in that range).
@ -81,38 +78,73 @@ e.g. `'a'`, `'*'`, and `'"'`.
Single quotes must be escaped with a backslash, i.e. `'\''`;
backslashes must be escaped as well, i.e. `'\\'`
We allow other backslash escapes
for commonly used characters that are not otherwise easily denoted,
namely _[TODO: Decide which other escapes we want to allow, e.g. `'\n'`.]_
* `\n`
* `\r`
* `\t`
* `\0`
* `\'`
* `\"`
for commonly used characters that are not otherwise easily denoted.
This is the complete list of single-character backslash escapes:
* `\'` for code point 39 (single quote)
* `\"` for code point 34 (double quote)
* `\\` for code point 92 (backslash)
* `\n` for code point 10 (line feed)
* `\r` for code point 13 (carriage return)
* `\t` for core point 9 (horizontal tab)
* `\0` for code point 0 (the null character)
We also allow ASCII escapes of the form `\xOH`,
where `O` is an octal digit and `H` is a hexadecimal digit
(both uppercase and lowercase are allowed).
These represent ASCII code points, i.e. from 0 to 127 (both inclusive).
We also allow Unicode escapes of the form `'\u{X}'`,
where `X` is a sequence of one to six hex digits
(both uppercase and lowercase letters are allowed)
whose value must be between 0 and 10FFFF, inclusive.
Note that the literal character is assembled by the compiler---for
creating literals, there is no need for the circuit to know
which codepoints are disallowed.
_[TODO: Do we want a different notation for Unicode escapes?
Note that the `{` `}` delimiters are motivated by the fact that
there may be a varying number of hex digits in this notation.]_
This notation is supported by both Javascript and Rust.
which code points are disallowed.
_[TODO: Which (initial) built-in or library operations
do we want to provide for `char` values?]_
- [ ] is_alphabetic - Returns `true` if the `char` has the `Alphabetic` property.
- [ ] is_ascii - Returns `true` if the `char` is in the `ASCII` range.
- [ ] is_ascii_alphabetic - Returns `true` if the `char` is in the `ASCII Alphabetic` range.
- [ ] is_lowercase - Returns `true` if the `char` has the `Lowercase` property.
- [ ] is_numeric - Returns `true` if the `char` has one of the general categories for numbers.
- [ ] is_uppercase - Returns `true` if the `char` has the `Uppercase` property.
- [ ] is_whitespace - Returns `true` if the `char` has the `White_Space` property.
- [ ] to_digit - Converts the `char` to the given `radix` format.
The equality operators `==` and `!=` are automatically available for `char`.
Given that characters are essentially code points,
we may also support the ordering operators `<`, `<=`, `>`, and `>=`;
these may be useful to check whether a character is in certain range.
Below is a list of possible operations we could support on characters.
It should be fairly easy to add more.
- [ ] `is_alphabetic` - Returns `true` if the `char` has the `Alphabetic` property.
- [ ] `is_ascii` - Returns `true` if the `char` is in the `ASCII` range.
- [ ] `is_ascii_alphabetic` - Returns `true` if the `char` is in the `ASCII Alphabetic` range.
- [ ] `is_lowercase` - Returns `true` if the `char` has the `Lowercase` property.
- [ ] `is_numeric` - Returns `true` if the `char` has one of the general categories for numbers.
- [ ] `is_uppercase` - Returns `true` if the `char` has the `Uppercase` property.
- [ ] `is_whitespace` - Returns `true` if the `char` has the `White_Space` property.
- [ ] `to_digit` - Converts the `char` to the given `radix` format.
- [ ] `from_digit` - Inverse of to_digit.
- [ ] `to_uppercase` - Converts lowercase to uppercase, leaving others unchanged.
- [ ] `to_lowercase` - Converts uppercase to lowercase, leaving others unchanged.
It seems natural to convert between `char` values
and `u8` or `u16` or `u32` values, under suitable range conditions;
perhaps also between `char` values and
(non-negative) `i8` or `i16` or `i32` values.
This will be accomplished as part of the type casting extension of Leo.
The following code sample illustrates three ways of defining characters:
character literal, single-character escapes, and Unicode escapes.
```js
function main() -> [char; 5] {
// using char literals to form an array
const world: [char; 5] = ['w', 'o', 'r', 'l', 'd'];
// escaped characters
const escaped: [char; 4] = ['\n', '\t', '\\', '\''];
// unicode escapes - using emoji character 😊
const smiling_face: char = '\u{1F60A}';
return [smiling_face, ...escaped];
}
```
## Strings
@ -133,12 +165,6 @@ Double quotes must be escaped with a backslash, e.g. `"say \"hi\""`;
backslashes must be escaped as well, e.g. `"c:\\dir"`.
We allow the same backslash escapes allowed for character literals
(see the section on characters above).
_[TODO: There is a difference in the treatment of single and double quotes:
the former are allowed in string literals but not character literals,
while the latter are allowed in character literals but not string literals;
this asymmetry is also present in Java.
However, for simplicity, we may want to symmetrically disallow
both single and double quotes in both character and string literals.]_
We also allow the same Unicode escapes allowed in character literals
(described in the section on characters above).
In any case, the type of a string literal is `[char; N]`,
@ -160,30 +186,55 @@ in a future design iteration,
a richer type for strings,
as discussed in the section about future extensions below.
_[TODO: Which (initial) built-in or library operations
do we want to provide for `[char; N]` values that are not already
available with the existing array operations?]_
- [ ] `u8` to `[char; 2]` hexstring, .., `u128` to `[char; 32]` hexstring
- [ ] field element to `[char; 64]` hexstring. (Application can test leading zeros and slice them out if it needs to return, say, a 40-hex-digit string)
- [ ] len - Returns the length of the `string`.
- [ ] is_empty - Returns `true` if the `string` is empty.
- [ ] pop - Pops a `char` to the `string`.
- [ ] push - Pushes a `char` to the `string`.
- [ ] append - Appends a `string` to the `string`.
- [ ] clear - Empties the `string`.
- [ ] _[TODO: more?]_
Recall that empty arrays are disallowed in Leo.
(The reason is that arrays,
which must have a size known at compile time and are not resizable,
are flattened into their elements when compiling to R1CS;
thus, an empty array would be flattened into nothing.)
Therefore, in this initial design empty strings must be disallowed as well.
A future type of resizable strings will support empty strings.
## Input and Output of Literal Characters and Strings
Because array, and therefore string, sizes must be known at compile time,
there is no point to having an operation to return the length of a string.
This operation will be supported for a future type of resizable strings.
Since UTF-8 is a standard encoding, it would make sense for
the literal characters and strings in the `.in` file
to be automatically converted to UTF-32 by the Leo compiler.
However, the size of a string can be confusing since multiple
Unicode code points can be composed into a single glyph which
then appears to be a single character. If a parameter of type `[char; 10]`
[if that is the syntax we decide on] is passed a literal string
of a different size, the error message should explain that the
size must be the number of codepoints needed to encode the string.
Below are some examples of array operations
that are also common for strings in other programming languages:
* `[...s1, ...s2]` concatenates the strings `s1` and `s2`.
* `[c, ...s]` adds the character `c` in front of the string `s`.
* `s[i]` extracts the `i`-th character from the string `s`.
* `s[1..]` removes the first character from the string `s`.
Below is a list of possible operations we could support on strings.
It should be fairly easy to add more.
- [ ] `u8` to `[char; 2]` hexstring, .., `u128` to `[char; 32]` hexstring.
- [ ] Field element to `[char; 64]` hexstring. (Application can test leading zeros and slice them out if it needs to return, say, a 40-hex-digit string.)
- [ ] Apply `to_uppercase` (see above) to every character.
- [ ] Apply `to_lowercase` (see above) to every character.
Note that the latter two could be also realize via simple loops through the string.
Given the natural conversions between `char` values and integer values discussed earlier,
it may be natural to also support element-wise conversions between strings and arrays of integers.
This may be accomplished as part of the type casting extensions of Leo.
The following code shows a string literal and its actual transformation into an
array of characters as well as possible array-like operations on strings:
concatenation and comparison.
```js
function main() -> bool {
// double quotes create char array from string
let hello: [char; 5] = "hello";
let world: [char; 5] = ['w','o','r','l','d'];
// string concatenation can be performed using array syntax
let hello_world: [char; 11] = [...hello, ' ', ...world];
// string comparison is also implemented via array type
return hello_world == "hello world";
}
```
## Format Strings
@ -197,6 +248,38 @@ which will be interpreted as a format string
according to the semantics of console print calls.
The internal UTF-32 string will be translated to UTF-8 for output.
## Circuit Types for Character and String Operations
The operations on characters and lists described earlier, e.g. `is_ascii`,
are provided as static member functions of two new built-in or library circuit types `Char` and `String`.
Thus, an example call is `Char::is_ascii(c)`.
This seems a general good way to organize built-in or library operations,
and supports the use of the same name with different circuit types,
e.g. `Char::to_uppercase` and `String::to_uppercase`.
These circuit types could also include constants, e.g. for certain ASCII characters.
However, currently Leo does not support constants in circuit types,
so that would have to be added separately first.
These two circuit types are just meant to collect static member functions for characters and strings.
They are not meant to be the types of characters and strings:
as mentioned previously, `char` is a new scalar (not circuit) type (like `bool`, `address`, `u8`, etc.)
and there is no string type as such for now, but we use character arrays for strings.
In the future we may want all the Leo types to be circuit types of some sort,
but that is a separate feature that would have to be designed and developed independently.
## Input and Output of Literal Characters and Strings
Since UTF-8 is a standard encoding, it would make sense for
the literal characters and strings in the `.in` file
to be automatically converted to UTF-32 by the Leo compiler.
However, the size of a string can be confusing since multiple
Unicode code points can be composed into a single glyph which
then appears to be a single character. If a parameter of type `[char; 10]`
[if that is the syntax we decide on] is passed a literal string
of a different size, the error message should explain that the
size must be the number of codepoints needed to encode the string.
## Compilation to R1CS
So far, the discussion has been independent from R1CS
@ -209,10 +292,10 @@ This section discusses R1CS compilation considerations
for this proposal for characters and strings.
Values of type `char` can be represented directly as field elements,
since the prime of the field is (much) larger than 10FFFFh.
since the prime of the field is (much) larger than 10FFFF.
This is more efficient than using a bit representation of characters.
By construction, field elements that represent `char` values
are never above 10FFFFh.
are never above 10FFFF.
Note that `field` and `char` remain separate types in Leo:
it is only in the compilation to R1CS
that everything is reduced to field elements.
@ -226,6 +309,35 @@ applies to strings without exception.
String literals are just syntactic sugar for
suitable array inline construction expressions.
There are at least two approaches to implementing
ordering operations `<` and `<=` on `char` values.
Recalling that characters are represented as field values
that are (well) below `(p-1)/2` where `p` is the prime,
we can compare two field values `x` and `y`,
both below `(p-1)/2`, via the constraints
```
(2) (x - y) = (b0 + 2*b1 + 4*b2 + ...)
(b0) (1 - b0) = 0
(b1) (1 - b1) = 0
(b2) (1 - b2) = 0
...
```
that take the difference, double it, and convert to bits.
If `x >= y`, the difference is below `(p-1)/2`,
and doubling results in an even number below `p`,
with therefore `b0 = 0`.
If `x < y`, the difference is above `(p-1)/2` (when reduced modulo `p`),
and doubling results in an odd number when reduced modulo `p`,
with therefore `b0 = 1`.
Note that we need one variable and one constraint for every bit of `p`.
The other approach is to convert the `x` and `y` to bits
and compare them as integers;
in this case we only need 21 bits for each.
We need more analysis to determine which approach is more efficient.
The details of implementing other character and string operations in R1CS
will be fleshed out as each operation is added.
## Future Extensions
As alluded to in the section about design above,
@ -259,17 +371,18 @@ But the need to support characters and strings justifies the extra complexity.
With the ability of Leo programs to process strings,
it may be useful to have external tools that convert Leo strings
to/from common formats, e.g. UTF-8.
See the discussion of input files in the design section.
# Alternatives
We could avoid the new `char` type altogether,
and instead, rely on the existing `u32` to represent Unicode code points,
and provide character-oriented operations on `u32` values.
(Note that both `u8` and `u16` are too small for 10FFFFh,
(Note that both `u8` and `u16` are too small for 10FFFF,
and that signed integer types include negative integers
which are not Unicode code points:
this makes `u32` the obvious choice.)
However, many values of type `u32` are above 10FFFFh,
However, many values of type `u32` are above 10FFFF,
and many operations on `u32` do not really make sense on code points.
We would probably want a notation for character literals anyhow,
which could be (arguably mis)used for non-character unsigned integers.

View File

@ -1,5 +1,5 @@
circuit PedersenHash {
parameters: [group; 256],
parameters: [group; 256];
// Instantiates a Pedersen hash circuit
function new(parameters: [group; 256]) -> Self {

View File

@ -16,7 +16,7 @@
circuit SillySudoku {
// The starting grid values for the Sudoku puzzle.
// Unset cells on the puzzle grid are set to 0.
puzzle_grid: [u8; (3, 3)],
puzzle_grid: [u8; (3, 3)];
/**
* Returns true if a given Sudoku answer is correct.

View File

@ -476,7 +476,7 @@ Line terminators form whitespace, along with spaces and horizontal tabs.
whitespace = space / horizontal-tab / newline
```
Go to: _[space](#user-content-space), [newline](#user-content-newline), [horizontal-tab](#user-content-horizontal-tab)_;
Go to: _[newline](#user-content-newline), [space](#user-content-space), [horizontal-tab](#user-content-horizontal-tab)_;
There are two kinds of comments in Leo, as in other languages.
@ -494,7 +494,7 @@ the ones used in the Java language reference.
comment = block-comment / end-of-line-comment
```
Go to: _[block-comment](#user-content-block-comment), [end-of-line-comment](#user-content-end-of-line-comment)_;
Go to: _[end-of-line-comment](#user-content-end-of-line-comment), [block-comment](#user-content-block-comment)_;
<a name="block-comment"></a>
@ -511,7 +511,7 @@ rest-of-block-comment = "*" rest-of-block-comment-after-star
/ not-star rest-of-block-comment
```
Go to: _[rest-of-block-comment](#user-content-rest-of-block-comment), [rest-of-block-comment-after-star](#user-content-rest-of-block-comment-after-star), [not-star](#user-content-not-star)_;
Go to: _[rest-of-block-comment-after-star](#user-content-rest-of-block-comment-after-star), [rest-of-block-comment](#user-content-rest-of-block-comment), [not-star](#user-content-not-star)_;
<a name="rest-of-block-comment-after-star"></a>
@ -521,7 +521,7 @@ rest-of-block-comment-after-star = "/"
/ not-star-or-slash rest-of-block-comment
```
Go to: _[rest-of-block-comment](#user-content-rest-of-block-comment), [not-star-or-slash](#user-content-not-star-or-slash), [rest-of-block-comment-after-star](#user-content-rest-of-block-comment-after-star)_;
Go to: _[not-star-or-slash](#user-content-not-star-or-slash), [rest-of-block-comment](#user-content-rest-of-block-comment), [rest-of-block-comment-after-star](#user-content-rest-of-block-comment-after-star)_;
<a name="end-of-line-comment"></a>
@ -596,7 +596,7 @@ lowercase-letter = %x61-7A ; a-z
letter = uppercase-letter / lowercase-letter
```
Go to: _[lowercase-letter](#user-content-lowercase-letter), [uppercase-letter](#user-content-uppercase-letter)_;
Go to: _[uppercase-letter](#user-content-uppercase-letter), [lowercase-letter](#user-content-lowercase-letter)_;
An identifier is a non-empty sequence of letters, digits, and underscores,
@ -642,7 +642,7 @@ format-string-element = not-double-quote-or-open-brace
/ format-string-container
```
Go to: _[format-string-container](#user-content-format-string-container), [not-double-quote-or-open-brace](#user-content-not-double-quote-or-open-brace), [not-double-quote-or-close-brace](#user-content-not-double-quote-or-close-brace)_;
Go to: _[format-string-container](#user-content-format-string-container), [not-double-quote-or-close-brace](#user-content-not-double-quote-or-close-brace), [not-double-quote-or-open-brace](#user-content-not-double-quote-or-open-brace)_;
<a name="format-string"></a>
@ -767,7 +767,7 @@ atomic-literal = untyped-literal
/ address-literal
```
Go to: _[product-group-literal](#user-content-product-group-literal), [signed-literal](#user-content-signed-literal), [unsigned-literal](#user-content-unsigned-literal), [field-literal](#user-content-field-literal), [boolean-literal](#user-content-boolean-literal), [untyped-literal](#user-content-untyped-literal), [address-literal](#user-content-address-literal)_;
Go to: _[untyped-literal](#user-content-untyped-literal), [product-group-literal](#user-content-product-group-literal), [unsigned-literal](#user-content-unsigned-literal), [signed-literal](#user-content-signed-literal), [boolean-literal](#user-content-boolean-literal), [address-literal](#user-content-address-literal), [field-literal](#user-content-field-literal)_;
After defining the (mostly) alphanumeric tokens above,
@ -812,7 +812,7 @@ token = keyword
/ symbol
```
Go to: _[package-name](#user-content-package-name), [annotation-name](#user-content-annotation-name), [format-string](#user-content-format-string), [keyword](#user-content-keyword), [atomic-literal](#user-content-atomic-literal), [identifier](#user-content-identifier), [symbol](#user-content-symbol)_;
Go to: _[keyword](#user-content-keyword), [atomic-literal](#user-content-atomic-literal), [package-name](#user-content-package-name), [annotation-name](#user-content-annotation-name), [format-string](#user-content-format-string), [symbol](#user-content-symbol), [identifier](#user-content-identifier)_;
@ -848,7 +848,7 @@ signed-type = %s"i8" / %s"i16" / %s"i32" / %s"i64" / %s"i128"
integer-type = unsigned-type / signed-type
```
Go to: _[signed-type](#user-content-signed-type), [unsigned-type](#user-content-unsigned-type)_;
Go to: _[unsigned-type](#user-content-unsigned-type), [signed-type](#user-content-signed-type)_;
The integer types, along with the field and group types,
@ -869,7 +869,7 @@ group-type = %s"group"
arithmetic-type = integer-type / field-type / group-type
```
Go to: _[integer-type](#user-content-integer-type), [field-type](#user-content-field-type), [group-type](#user-content-group-type)_;
Go to: _[integer-type](#user-content-integer-type), [group-type](#user-content-group-type), [field-type](#user-content-field-type)_;
The arithmetic types, along with the boolean and address types,
@ -890,7 +890,7 @@ address-type = %s"address"
scalar-type = boolean-type / arithmetic-type / address-type
```
Go to: _[arithmetic-type](#user-content-arithmetic-type), [address-type](#user-content-address-type), [boolean-type](#user-content-boolean-type)_;
Go to: _[address-type](#user-content-address-type), [boolean-type](#user-content-boolean-type), [arithmetic-type](#user-content-arithmetic-type)_;
Circuit types are denoted by identifiers and the keyword `Self`.
@ -951,7 +951,7 @@ i.e. types whose values contain (sub-)values
aggregate-type = tuple-type / array-type / circuit-type
```
Go to: _[tuple-type](#user-content-tuple-type), [array-type](#user-content-array-type), [circuit-type](#user-content-circuit-type)_;
Go to: _[circuit-type](#user-content-circuit-type), [tuple-type](#user-content-tuple-type), [array-type](#user-content-array-type)_;
Scalar and aggregate types form all the types.
@ -997,7 +997,7 @@ A literal is either an atomic one or an affine group literal.
literal = atomic-literal / affine-group-literal
```
Go to: _[affine-group-literal](#user-content-affine-group-literal), [atomic-literal](#user-content-atomic-literal)_;
Go to: _[atomic-literal](#user-content-atomic-literal), [affine-group-literal](#user-content-affine-group-literal)_;
The following rule is not directly referenced in the rules for expressions
@ -1039,7 +1039,7 @@ primary-expression = identifier
/ circuit-expression
```
Go to: _[tuple-expression](#user-content-tuple-expression), [identifier](#user-content-identifier), [expression](#user-content-expression), [array-expression](#user-content-array-expression), [circuit-expression](#user-content-circuit-expression), [literal](#user-content-literal)_;
Go to: _[expression](#user-content-expression), [literal](#user-content-literal), [identifier](#user-content-identifier), [array-expression](#user-content-array-expression), [circuit-expression](#user-content-circuit-expression), [tuple-expression](#user-content-tuple-expression)_;
Tuple expressions construct tuples.
@ -1100,7 +1100,7 @@ Go to: _[expression](#user-content-expression), [array-dimensions](#user-content
array-construction = array-inline-construction / array-repeat-construction
```
Go to: _[array-repeat-construction](#user-content-array-repeat-construction), [array-inline-construction](#user-content-array-inline-construction)_;
Go to: _[array-inline-construction](#user-content-array-inline-construction), [array-repeat-construction](#user-content-array-repeat-construction)_;
<a name="array-expression"></a>
@ -1128,7 +1128,7 @@ circuit-construction = circuit-type "{"
"}"
```
Go to: _[circuit-inline-element](#user-content-circuit-inline-element), [circuit-type](#user-content-circuit-type)_;
Go to: _[circuit-type](#user-content-circuit-type), [circuit-inline-element](#user-content-circuit-inline-element)_;
<a name="circuit-inline-element"></a>
@ -1187,7 +1187,7 @@ postfix-expression = primary-expression
/ postfix-expression "[" [expression] ".." [expression] "]"
```
Go to: _[function-arguments](#user-content-function-arguments), [postfix-expression](#user-content-postfix-expression), [natural](#user-content-natural), [circuit-type](#user-content-circuit-type), [expression](#user-content-expression), [identifier](#user-content-identifier), [primary-expression](#user-content-primary-expression)_;
Go to: _[expression](#user-content-expression), [natural](#user-content-natural), [identifier](#user-content-identifier), [primary-expression](#user-content-primary-expression), [circuit-type](#user-content-circuit-type), [function-arguments](#user-content-function-arguments), [postfix-expression](#user-content-postfix-expression)_;
Unary operators have the highest operator precedence.
@ -1201,7 +1201,7 @@ unary-expression = postfix-expression
/ "-" unary-expression
```
Go to: _[postfix-expression](#user-content-postfix-expression), [unary-expression](#user-content-unary-expression)_;
Go to: _[unary-expression](#user-content-unary-expression), [postfix-expression](#user-content-postfix-expression)_;
Next in the operator precedence is exponentiation,
@ -1215,7 +1215,7 @@ exponential-expression = unary-expression
/ unary-expression "**" exponential-expression
```
Go to: _[unary-expression](#user-content-unary-expression), [exponential-expression](#user-content-exponential-expression)_;
Go to: _[exponential-expression](#user-content-exponential-expression), [unary-expression](#user-content-unary-expression)_;
Next in precedence come multiplication and division, both left-associative.
@ -1227,7 +1227,7 @@ multiplicative-expression = exponential-expression
/ multiplicative-expression "/" exponential-expression
```
Go to: _[exponential-expression](#user-content-exponential-expression), [multiplicative-expression](#user-content-multiplicative-expression)_;
Go to: _[multiplicative-expression](#user-content-multiplicative-expression), [exponential-expression](#user-content-exponential-expression)_;
Then there are addition and subtraction, both left-assocative.
@ -1239,7 +1239,7 @@ additive-expression = multiplicative-expression
/ additive-expression "-" multiplicative-expression
```
Go to: _[multiplicative-expression](#user-content-multiplicative-expression), [additive-expression](#user-content-additive-expression)_;
Go to: _[additive-expression](#user-content-additive-expression), [multiplicative-expression](#user-content-multiplicative-expression)_;
Next in the precedence order are ordering relations.
@ -1267,7 +1267,7 @@ equality-expression = ordering-expression
/ equality-expression "!=" ordering-expression
```
Go to: _[equality-expression](#user-content-equality-expression), [ordering-expression](#user-content-ordering-expression)_;
Go to: _[ordering-expression](#user-content-ordering-expression), [equality-expression](#user-content-equality-expression)_;
Next come conjunctive expressions, left-associative.
@ -1289,7 +1289,7 @@ disjunctive-expression = conjunctive-expression
/ disjunctive-expression "||" conjunctive-expression
```
Go to: _[disjunctive-expression](#user-content-disjunctive-expression), [conjunctive-expression](#user-content-conjunctive-expression)_;
Go to: _[conjunctive-expression](#user-content-conjunctive-expression), [disjunctive-expression](#user-content-disjunctive-expression)_;
Finally we have conditional expressions.
@ -1302,7 +1302,7 @@ conditional-expression = disjunctive-expression
":" conditional-expression
```
Go to: _[expression](#user-content-expression), [conditional-expression](#user-content-conditional-expression), [disjunctive-expression](#user-content-disjunctive-expression)_;
Go to: _[expression](#user-content-expression), [disjunctive-expression](#user-content-disjunctive-expression), [conditional-expression](#user-content-conditional-expression)_;
Those above are all the expressions.
@ -1335,7 +1335,7 @@ statement = expression-statement
/ block
```
Go to: _[expression-statement](#user-content-expression-statement), [return-statement](#user-content-return-statement), [assignment-statement](#user-content-assignment-statement), [block](#user-content-block), [loop-statement](#user-content-loop-statement), [constant-declaration](#user-content-constant-declaration), [conditional-statement](#user-content-conditional-statement), [console-statement](#user-content-console-statement), [variable-declaration](#user-content-variable-declaration)_;
Go to: _[block](#user-content-block), [constant-declaration](#user-content-constant-declaration), [variable-declaration](#user-content-variable-declaration), [return-statement](#user-content-return-statement), [expression-statement](#user-content-expression-statement), [loop-statement](#user-content-loop-statement), [conditional-statement](#user-content-conditional-statement), [assignment-statement](#user-content-assignment-statement), [console-statement](#user-content-console-statement)_;
<a name="block"></a>
@ -1378,7 +1378,7 @@ variable-declaration = %s"let" identifier-or-identifiers [ ":" type ]
"=" expression ";"
```
Go to: _[type](#user-content-type), [identifier-or-identifiers](#user-content-identifier-or-identifiers), [expression](#user-content-expression)_;
Go to: _[type](#user-content-type), [expression](#user-content-expression), [identifier-or-identifiers](#user-content-identifier-or-identifiers)_;
<a name="constant-declaration"></a>
@ -1387,7 +1387,7 @@ constant-declaration = %s"const" identifier-or-identifiers [ ":" type ]
"=" expression ";"
```
Go to: _[expression](#user-content-expression), [type](#user-content-type), [identifier-or-identifiers](#user-content-identifier-or-identifiers)_;
Go to: _[identifier-or-identifiers](#user-content-identifier-or-identifiers), [type](#user-content-type), [expression](#user-content-expression)_;
<a name="identifier-or-identifiers"></a>
@ -1420,7 +1420,7 @@ conditional-statement = branch
/ branch %s"else" conditional-statement
```
Go to: _[block](#user-content-block), [branch](#user-content-branch), [conditional-statement](#user-content-conditional-statement)_;
Go to: _[branch](#user-content-branch), [block](#user-content-block), [conditional-statement](#user-content-conditional-statement)_;
A loop statement implicitly defines a loop variable
@ -1432,7 +1432,7 @@ The body is a block.
loop-statement = %s"for" identifier %s"in" expression ".." expression block
```
Go to: _[identifier](#user-content-identifier), [expression](#user-content-expression), [block](#user-content-block)_;
Go to: _[expression](#user-content-expression), [identifier](#user-content-identifier), [block](#user-content-block)_;
An assignment statement is straightforward.
@ -1476,7 +1476,7 @@ console-call = assert-call
/ print-call
```
Go to: _[print-call](#user-content-print-call), [assert-call](#user-content-assert-call)_;
Go to: _[assert-call](#user-content-assert-call), [print-call](#user-content-print-call)_;
<a name="assert-call"></a>
@ -1535,7 +1535,7 @@ function-declaration = *annotation %s"function" identifier
block
```
Go to: _[block](#user-content-block), [identifier](#user-content-identifier), [function-parameters](#user-content-function-parameters), [type](#user-content-type)_;
Go to: _[type](#user-content-type), [block](#user-content-block), [identifier](#user-content-identifier), [function-parameters](#user-content-function-parameters)_;
<a name="function-parameters"></a>
@ -1545,7 +1545,7 @@ function-parameters = self-parameter
/ function-inputs
```
Go to: _[self-parameter](#user-content-self-parameter), [function-inputs](#user-content-function-inputs)_;
Go to: _[function-inputs](#user-content-function-inputs), [self-parameter](#user-content-self-parameter)_;
<a name="self-parameter"></a>
@ -1566,24 +1566,15 @@ Go to: _[function-input](#user-content-function-input)_;
function-input = [ %s"const" ] identifier ":" type
```
Go to: _[type](#user-content-type), [identifier](#user-content-identifier)_;
Go to: _[identifier](#user-content-identifier), [type](#user-content-type)_;
A circuit member variable declaration consists of an identifier and a type.
A circuit member function declaration consists of a function declaration.
<a name="member-declaration"></a>
<a name="member-variable-declarations"></a>
```abnf
member-declaration = member-variable-declaration
/ member-function-declaration
```
Go to: _[member-function-declaration](#user-content-member-function-declaration), [member-variable-declaration](#user-content-member-variable-declaration)_;
<a name="member-variable-declaration"></a>
```abnf
member-variable-declaration = identifier ":" type
member-variable-declarations = *(identifier ":" type ( "," / ";" )) identifier ":" type ( [ "," ] / ";" )
```
Go to: _[identifier](#user-content-identifier), [type](#user-content-type)_;
@ -1603,10 +1594,10 @@ as consisting of member variables and functions.
<a name="circuit-declaration"></a>
```abnf
circuit-declaration = *annotation %s"circuit" identifier
"{" member-declaration *( "," member-declaration ) "}"
"{" [ member-variable-declarations ] *member-function-declaration "}"
```
Go to: _[identifier](#user-content-identifier), [member-declaration](#user-content-member-declaration)_;
Go to: _[member-variable-declarations](#user-content-member-variable-declarations), [identifier](#user-content-identifier)_;
An import declaration consists of the `import` keyword
@ -1621,10 +1612,10 @@ to be followed by a comma, for convenience.
<a name="import-declaration"></a>
```abnf
import-declaration = %s"import" package-path ";"
import-declaration = %s"import" package-name "." package-path ";"
```
Go to: _[package-path](#user-content-package-path)_;
Go to: _[package-path](#user-content-package-path), [package-name](#user-content-package-name)_;
<a name="package-path"></a>
@ -1635,7 +1626,7 @@ package-path = "*"
/ "(" package-path *( "," package-path ) [","] ")"
```
Go to: _[identifier](#user-content-identifier), [package-path](#user-content-package-path), [package-name](#user-content-package-name)_;
Go to: _[package-name](#user-content-package-name), [identifier](#user-content-identifier), [package-path](#user-content-package-path)_;
Finally, we define a file as a sequence of zero or more declarations.
@ -1650,7 +1641,7 @@ declaration = import-declaration
/ constant-declaration
```
Go to: _[constant-declaration](#user-content-constant-declaration), [import-declaration](#user-content-import-declaration), [function-declaration](#user-content-function-declaration), [circuit-declaration](#user-content-circuit-declaration)_;
Go to: _[function-declaration](#user-content-function-declaration), [circuit-declaration](#user-content-circuit-declaration), [import-declaration](#user-content-import-declaration), [constant-declaration](#user-content-constant-declaration)_;
<a name="file"></a>

View File

@ -942,21 +942,35 @@ function-inputs = function-input *( "," function-input )
function-input = [ %s"const" ] identifier ":" type
; A circuit member variable declaration consists of an identifier and a type.
; A circuit member variable declaration consists of
; an identifier and a type, terminated by semicolon.
; For backward compatibility,
; member variable declarations may be alternatively followed by commas,
; and the last one may not be followed by anything:
; these are deprecated, and will be eventually removed,
; leaving only mandatory semicolons.
; Note that there is no rule for a single `member-variable-declaration`,
; but instead one for a sequence of them;
; see the rule `circuit-declaration`.
member-variable-declarations = *( identifier ":" type ( "," / ";" ) )
identifier ":" type ( [ "," ] / ";" )
; A circuit member function declaration consists of a function declaration.
member-declaration = member-variable-declaration
/ member-function-declaration
member-variable-declaration = identifier ":" type
member-function-declaration = function-declaration
; A circuit declaration defines a circuit type,
; as consisting of member variables and functions.
; To more simply accommodate the backward compatibility
; described for the rule `member-variable-declarations`,
; all the member variables must precede all the member functions;
; this may be relaxed after the backward compatibility is removed,
; allowing member variables and member functions to be intermixed.
circuit-declaration = *annotation %s"circuit" identifier
"{" member-declaration *( "," member-declaration ) "}"
"{" [ member-variable-declarations ]
*member-function-declaration "}"
; An import declaration consists of the `import` keyword
; followed by a package path, which may be one of the following:
@ -967,8 +981,12 @@ circuit-declaration = *annotation %s"circuit" identifier
; which are "fan out" of the initial path.
; Note that we allow the last element of the parenthesized list
; to be followed by a comma, for convenience.
; The package path in the import declaration must start with a package name
; (e.g. it cannot be a `*`):
; the rule for import declaration expresses this requirement
; by using an explicit package name before the package path.
import-declaration = %s"import" package-path ";"
import-declaration = %s"import" package-name "." package-path ";"
package-path = "*"
/ identifier [ %s"as" identifier ]

View File

@ -6,260 +6,260 @@ function main() {
}
circuit Foo {
x0: u8,
x1: u8,
x2: u8,
x3: u8,
x4: u8,
x5: u8,
x6: u8,
x7: u8,
x8: u8,
x9: u8,
x10: u8,
x11: u8,
x12: u8,
x13: u8,
x14: u8,
x15: u8,
x16: u8,
x17: u8,
x18: u8,
x19: u8,
x20: u8,
x21: u8,
x22: u8,
x23: u8,
x24: u8,
x25: u8,
x26: u8,
x27: u8,
x28: u8,
x29: u8,
x30: u8,
x31: u8,
x32: u8,
x33: u8,
x34: u8,
x35: u8,
x36: u8,
x37: u8,
x38: u8,
x39: u8,
x40: u8,
x41: u8,
x42: u8,
x43: u8,
x44: u8,
x45: u8,
x46: u8,
x47: u8,
x48: u8,
x49: u8,
x50: u8,
x51: u8,
x52: u8,
x53: u8,
x54: u8,
x55: u8,
x56: u8,
x57: u8,
x58: u8,
x59: u8,
x60: u8,
x61: u8,
x62: u8,
x63: u8,
x64: u8,
x65: u8,
x66: u8,
x67: u8,
x68: u8,
x69: u8,
x70: u8,
x71: u8,
x72: u8,
x73: u8,
x74: u8,
x75: u8,
x76: u8,
x77: u8,
x78: u8,
x79: u8,
x80: u8,
x81: u8,
x82: u8,
x83: u8,
x84: u8,
x85: u8,
x86: u8,
x87: u8,
x88: u8,
x89: u8,
x90: u8,
x91: u8,
x92: u8,
x93: u8,
x94: u8,
x95: u8,
x96: u8,
x97: u8,
x98: u8,
x99: u8,
x100: u8,
x101: u8,
x102: u8,
x103: u8,
x104: u8,
x105: u8,
x106: u8,
x107: u8,
x108: u8,
x109: u8,
x110: u8,
x111: u8,
x112: u8,
x113: u8,
x114: u8,
x115: u8,
x116: u8,
x117: u8,
x118: u8,
x119: u8,
x120: u8,
x121: u8,
x122: u8,
x123: u8,
x124: u8,
x125: u8,
x126: u8,
x127: u8,
x128: u8,
x129: u8,
x130: u8,
x131: u8,
x132: u8,
x133: u8,
x134: u8,
x135: u8,
x136: u8,
x137: u8,
x138: u8,
x139: u8,
x140: u8,
x141: u8,
x142: u8,
x143: u8,
x144: u8,
x145: u8,
x146: u8,
x147: u8,
x148: u8,
x149: u8,
x150: u8,
x151: u8,
x152: u8,
x153: u8,
x154: u8,
x155: u8,
x156: u8,
x157: u8,
x158: u8,
x159: u8,
x160: u8,
x161: u8,
x162: u8,
x163: u8,
x164: u8,
x165: u8,
x166: u8,
x167: u8,
x168: u8,
x169: u8,
x170: u8,
x171: u8,
x172: u8,
x173: u8,
x174: u8,
x175: u8,
x176: u8,
x177: u8,
x178: u8,
x179: u8,
x180: u8,
x181: u8,
x182: u8,
x183: u8,
x184: u8,
x185: u8,
x186: u8,
x187: u8,
x188: u8,
x189: u8,
x190: u8,
x191: u8,
x192: u8,
x193: u8,
x194: u8,
x195: u8,
x196: u8,
x197: u8,
x198: u8,
x199: u8,
x200: u8,
x201: u8,
x202: u8,
x203: u8,
x204: u8,
x205: u8,
x206: u8,
x207: u8,
x208: u8,
x209: u8,
x210: u8,
x211: u8,
x212: u8,
x213: u8,
x214: u8,
x215: u8,
x216: u8,
x217: u8,
x218: u8,
x219: u8,
x220: u8,
x221: u8,
x222: u8,
x223: u8,
x224: u8,
x225: u8,
x226: u8,
x227: u8,
x228: u8,
x229: u8,
x230: u8,
x231: u8,
x232: u8,
x233: u8,
x234: u8,
x235: u8,
x236: u8,
x237: u8,
x238: u8,
x239: u8,
x240: u8,
x241: u8,
x242: u8,
x243: u8,
x244: u8,
x245: u8,
x246: u8,
x247: u8,
x248: u8,
x249: u8,
x250: u8,
x251: u8,
x252: u8,
x253: u8,
x254: u8,
x255: u8
x0: u8;
x1: u8;
x2: u8;
x3: u8;
x4: u8;
x5: u8;
x6: u8;
x7: u8;
x8: u8;
x9: u8;
x10: u8;
x11: u8;
x12: u8;
x13: u8;
x14: u8;
x15: u8;
x16: u8;
x17: u8;
x18: u8;
x19: u8;
x20: u8;
x21: u8;
x22: u8;
x23: u8;
x24: u8;
x25: u8;
x26: u8;
x27: u8;
x28: u8;
x29: u8;
x30: u8;
x31: u8;
x32: u8;
x33: u8;
x34: u8;
x35: u8;
x36: u8;
x37: u8;
x38: u8;
x39: u8;
x40: u8;
x41: u8;
x42: u8;
x43: u8;
x44: u8;
x45: u8;
x46: u8;
x47: u8;
x48: u8;
x49: u8;
x50: u8;
x51: u8;
x52: u8;
x53: u8;
x54: u8;
x55: u8;
x56: u8;
x57: u8;
x58: u8;
x59: u8;
x60: u8;
x61: u8;
x62: u8;
x63: u8;
x64: u8;
x65: u8;
x66: u8;
x67: u8;
x68: u8;
x69: u8;
x70: u8;
x71: u8;
x72: u8;
x73: u8;
x74: u8;
x75: u8;
x76: u8;
x77: u8;
x78: u8;
x79: u8;
x80: u8;
x81: u8;
x82: u8;
x83: u8;
x84: u8;
x85: u8;
x86: u8;
x87: u8;
x88: u8;
x89: u8;
x90: u8;
x91: u8;
x92: u8;
x93: u8;
x94: u8;
x95: u8;
x96: u8;
x97: u8;
x98: u8;
x99: u8;
x100: u8;
x101: u8;
x102: u8;
x103: u8;
x104: u8;
x105: u8;
x106: u8;
x107: u8;
x108: u8;
x109: u8;
x110: u8;
x111: u8;
x112: u8;
x113: u8;
x114: u8;
x115: u8;
x116: u8;
x117: u8;
x118: u8;
x119: u8;
x120: u8;
x121: u8;
x122: u8;
x123: u8;
x124: u8;
x125: u8;
x126: u8;
x127: u8;
x128: u8;
x129: u8;
x130: u8;
x131: u8;
x132: u8;
x133: u8;
x134: u8;
x135: u8;
x136: u8;
x137: u8;
x138: u8;
x139: u8;
x140: u8;
x141: u8;
x142: u8;
x143: u8;
x144: u8;
x145: u8;
x146: u8;
x147: u8;
x148: u8;
x149: u8;
x150: u8;
x151: u8;
x152: u8;
x153: u8;
x154: u8;
x155: u8;
x156: u8;
x157: u8;
x158: u8;
x159: u8;
x160: u8;
x161: u8;
x162: u8;
x163: u8;
x164: u8;
x165: u8;
x166: u8;
x167: u8;
x168: u8;
x169: u8;
x170: u8;
x171: u8;
x172: u8;
x173: u8;
x174: u8;
x175: u8;
x176: u8;
x177: u8;
x178: u8;
x179: u8;
x180: u8;
x181: u8;
x182: u8;
x183: u8;
x184: u8;
x185: u8;
x186: u8;
x187: u8;
x188: u8;
x189: u8;
x190: u8;
x191: u8;
x192: u8;
x193: u8;
x194: u8;
x195: u8;
x196: u8;
x197: u8;
x198: u8;
x199: u8;
x200: u8;
x201: u8;
x202: u8;
x203: u8;
x204: u8;
x205: u8;
x206: u8;
x207: u8;
x208: u8;
x209: u8;
x210: u8;
x211: u8;
x212: u8;
x213: u8;
x214: u8;
x215: u8;
x216: u8;
x217: u8;
x218: u8;
x219: u8;
x220: u8;
x221: u8;
x222: u8;
x223: u8;
x224: u8;
x225: u8;
x226: u8;
x227: u8;
x228: u8;
x229: u8;
x230: u8;
x231: u8;
x232: u8;
x233: u8;
x234: u8;
x235: u8;
x236: u8;
x237: u8;
x238: u8;
x239: u8;
x240: u8;
x241: u8;
x242: u8;
x243: u8;
x244: u8;
x245: u8;
x246: u8;
x247: u8;
x248: u8;
x249: u8;
x250: u8;
x251: u8;
x252: u8;
x253: u8;
x254: u8;
x255: u8;
}

View File

@ -48,6 +48,10 @@ impl SyntaxError {
SyntaxError::Error(FormattedError::new_from_span(message, span))
}
pub fn invalid_import_list(span: &Span) -> Self {
Self::new_from_span("Cannot import empty list".to_string(), span)
}
pub fn unexpected_eof(span: &Span) -> Self {
Self::new_from_span("unexpected EOF".to_string(), span)
}
@ -74,6 +78,13 @@ impl SyntaxError {
)
}
pub fn mixed_commas_and_semicolons(span: &Span) -> Self {
Self::new_from_span(
"Cannot mix use of commas and semi-colons for circuit member variable declarations.".to_string(),
span,
)
}
pub fn unexpected_ident(got: &str, expected: &[&str], span: &Span) -> Self {
Self::new_from_span(
format!(

View File

@ -66,6 +66,13 @@ impl ParserContext {
SyntaxError::unexpected_eof(&self.end_span)
}
///
/// Returns a reference to the next next token or error if it does not exist.
///
pub fn peek_next(&self) -> SyntaxResult<&SpannedToken> {
self.tokens.get(self.tokens.len() - 2).ok_or_else(|| self.eof())
}
///
/// Returns a reference to the next token or error if it does not exist.
///

View File

@ -136,7 +136,7 @@ impl ParserContext {
/// Returns a vector of [`PackageAccess`] AST nodes if the next tokens represent package access
/// expressions within an import statement.
///
pub fn parse_package_accesses(&mut self) -> SyntaxResult<Vec<PackageAccess>> {
pub fn parse_package_accesses(&mut self, span: &Span) -> SyntaxResult<Vec<PackageAccess>> {
let mut out = Vec::new();
self.expect(Token::LeftParen)?;
while self.eat(Token::RightParen).is_none() {
@ -147,6 +147,11 @@ impl ParserContext {
break;
}
}
if out.is_empty() {
return Err(SyntaxError::invalid_import_list(span));
}
Ok(out)
}
@ -156,7 +161,7 @@ impl ParserContext {
///
pub fn parse_package_access(&mut self) -> SyntaxResult<PackageAccess> {
if let Some(SpannedToken { span, .. }) = self.eat(Token::Mul) {
Ok(PackageAccess::Star(span))
Ok(PackageAccess::Star { span })
} else {
let name = self.expect_ident()?;
if self.peek_token().as_ref() == &Token::Dot {
@ -247,7 +252,7 @@ impl ParserContext {
let package_name = self.parse_package_name()?;
self.expect(Token::Dot)?;
if self.peek()?.token == Token::LeftParen {
let accesses = self.parse_package_accesses()?;
let accesses = self.parse_package_accesses(&package_name.span)?;
Ok(PackageOrPackages::Packages(Packages {
span: &package_name.span + accesses.last().map(|x| x.span()).unwrap_or(&package_name.span),
name: package_name,
@ -280,18 +285,82 @@ impl ParserContext {
/// Returns a [`CircuitMember`] AST node if the next tokens represent a circuit member variable
/// or circuit member function.
///
pub fn parse_circuit_member(&mut self) -> SyntaxResult<CircuitMember> {
pub fn parse_circuit_declaration(&mut self) -> SyntaxResult<Vec<CircuitMember>> {
let mut members = Vec::new();
let peeked = &self.peek()?.token;
if peeked == &Token::Function || peeked == &Token::At {
let mut last_variable = peeked == &Token::Function || peeked == &Token::At;
let (mut semi_colons, mut commas) = (false, false);
while self.eat(Token::RightCurly).is_none() {
if !last_variable {
let (variable, last) = self.parse_member_variable_declaration()?;
members.push(variable);
let peeked = &self.peek()?;
if peeked.token == Token::Semicolon {
if commas {
return Err(SyntaxError::mixed_commas_and_semicolons(&peeked.span));
}
semi_colons = true;
self.expect(Token::Semicolon)?;
} else {
if semi_colons {
return Err(SyntaxError::mixed_commas_and_semicolons(&peeked.span));
}
commas = true;
self.eat(Token::Comma);
}
if last {
last_variable = last;
}
} else {
let function = self.parse_member_function_declaration()?;
members.push(function);
}
}
Ok(members)
}
///
/// Returns a [`CircuitMember`] AST node if the next tokens represent a circuit member variable.
///
pub fn parse_member_variable_declaration(&mut self) -> SyntaxResult<(CircuitMember, bool)> {
let name = self.expect_ident()?;
self.expect(Token::Colon)?;
let type_ = self.parse_type()?.0;
let peeked = &self.peek()?.token;
if peeked == &Token::Function || peeked == &Token::At || peeked == &Token::RightCurly {
return Ok((CircuitMember::CircuitVariable(name, type_), true));
} else if peeked == &Token::Comma || peeked == &Token::Semicolon {
let peeked = &self.peek_next()?.token;
if peeked == &Token::Function || peeked == &Token::At || peeked == &Token::RightCurly {
return Ok((CircuitMember::CircuitVariable(name, type_), true));
}
}
Ok((CircuitMember::CircuitVariable(name, type_), false))
}
///
/// Returns a [`CircuitMember`] AST node if the next tokens represent a circuit member function.
///
pub fn parse_member_function_declaration(&mut self) -> SyntaxResult<CircuitMember> {
let peeked = &self.peek()?;
let peeked_token = &peeked.token;
if peeked_token == &Token::Function || peeked_token == &Token::At {
let function = self.parse_function_declaration()?;
Ok(CircuitMember::CircuitFunction(function.1))
} else {
// circuit variable
let name = self.expect_ident()?;
self.expect(Token::Colon)?;
let type_ = self.parse_type()?.0;
self.eat(Token::Comma);
Ok(CircuitMember::CircuitVariable(name, type_))
Err(SyntaxError::unexpected(
peeked_token,
&[Token::Function, Token::At],
&peeked.span,
))
}
}
@ -303,11 +372,8 @@ impl ParserContext {
self.expect(Token::Circuit)?;
let name = self.expect_ident()?;
self.expect(Token::LeftCurly)?;
let mut members = Vec::new();
while self.eat(Token::RightCurly).is_none() {
let member = self.parse_circuit_member()?;
members.push(member);
}
let members = self.parse_circuit_declaration()?;
Ok((name.clone(), Circuit {
circuit_name: name,
members,

View File

@ -4,7 +4,7 @@ expectation: Pass
*/
circuit Foo {
a: u8,
a: u8;
function use_a(const self) -> u8 {
return self.a + 1;

View File

@ -4,7 +4,7 @@ expectation: Fail
*/
circuit Foo {
a: u8,
a: u8;
function set_a(const self, new: u8) {
self.a = new;

View File

@ -4,7 +4,7 @@ expectation: Fail
*/
circuit Foo {
x: u32
x: u32;
}
function main() {

View File

@ -4,7 +4,7 @@ expectation: Fail
*/
circuit Foo {
x: u8
x: u8;
}
function main() {

View File

@ -8,7 +8,7 @@ inputs:
*/
circuit Foo {
foo: u32,
foo: u32;
function bar() -> u32 {
return 1u32;

View File

@ -4,7 +4,7 @@ expectation: Fail
*/
circuit Foo {
x: u32
x: u32;
}
function main() {

View File

@ -4,7 +4,7 @@ expectation: Fail
*/
circuit Foo {
a: u8,
a: u8;
function bar() {}
}

View File

@ -4,7 +4,7 @@ expectation: Fail
*/
circuit Foo {
a: u8,
a: u8;
function bar() {}

View File

@ -4,7 +4,7 @@ expectation: Fail
*/
circuit Foo {
a: u8,
a: u8;
function bar() {}

View File

@ -4,7 +4,7 @@ expectation: Pass
*/
circuit Foo {
a: u8,
a: u8;
function set_a(mut self, new: u8) {
self.a = new;

View File

@ -4,7 +4,7 @@ expectation: Pass
*/
circuit Foo {
a: u8,
a: u8;
function set_a(mut self, condition: bool, new: u8) {
if condition {

View File

@ -10,7 +10,7 @@ function main() {
}
circuit Foo {
a: u32
a: u32;
function bar(mut self) {
if true {

View File

@ -4,7 +4,7 @@ expectation: Fail
*/
circuit Foo {
a: u8,
a: u8;
function set_a(self, new: u8) {
self.a = new;

View File

@ -4,7 +4,7 @@ expectation: Pass
*/
circuit Foo {
a: u8,
a: u8;
}
function main() {

View File

@ -4,7 +4,7 @@ expectation: Fail
*/
circuit Foo {
a: u8,
a: u8;
}
function main() {

View File

@ -4,7 +4,7 @@ expectation: Pass
*/
circuit TestMe {
x: u8,
x: u8;
function test_me(mut self) -> u8 {
self.x += 1;

View File

@ -11,7 +11,7 @@ inputs:
*/
circuit PedersenHash {
parameters: [u32; 512]
parameters: [u32; 512];
function new(parameters: [u32; 512]) -> Self {
return Self { parameters: parameters };

View File

@ -4,7 +4,7 @@ expectation: Pass
*/
circuit Foo {
f: u32,
f: u32;
function bar(self) -> u32 {
return self.f;

View File

@ -4,7 +4,7 @@ expectation: Fail
*/
circuit Foo {
f: u32,
f: u32;
function bar() -> u32 {
return f;

View File

@ -1,3 +1,3 @@
circuit Bat {
t: u32
t: u32;
}

View File

@ -1,7 +1,9 @@
circuit Baz {
z: u32
z: u32;
}
circuit Bazzar {
a: u32
}
a: u32;
}
const ONE: u8 = 1;

View File

@ -1,3 +1,3 @@
circuit Bar {
r: u32
r: u32;
}

View File

@ -1,3 +1,3 @@
circuit Car {
c: u32
c: u32;
}

View File

@ -4,7 +4,7 @@ expectation: Fail
*/
circuit Foo {
x: u32
x: u32;
}
// const variable is immutable

View File

@ -13,7 +13,7 @@ outputs:
- "{\"name\":\"x\",\"span\":\"{\\\"line_start\\\":4,\\\"line_stop\\\":4,\\\"col_start\\\":5,\\\"col_stop\\\":6,\\\"path\\\":\\\"test\\\",\\\"content\\\":\\\" x: u32,\\\"}\"}"
- IntegerType: U32
- CircuitVariable:
- "{\"name\":\"y\",\"span\":\"{\\\"line_start\\\":5,\\\"line_stop\\\":5,\\\"col_start\\\":5,\\\"col_stop\\\":6,\\\"path\\\":\\\"test\\\",\\\"content\\\":\\\" y: u32,\\\"}\"}"
- "{\"name\":\"y\",\"span\":\"{\\\"line_start\\\":5,\\\"line_stop\\\":5,\\\"col_start\\\":5,\\\"col_stop\\\":6,\\\"path\\\":\\\"test\\\",\\\"content\\\":\\\" y: u32\\\"}\"}"
- IntegerType: U32
- CircuitFunction:
annotations: []

View File

@ -10,10 +10,10 @@ outputs:
circuit_name: "{\"name\":\"X\",\"span\":\"{\\\"line_start\\\":3,\\\"line_stop\\\":3,\\\"col_start\\\":9,\\\"col_stop\\\":10,\\\"path\\\":\\\"test\\\",\\\"content\\\":\\\"circuit X {\\\"}\"}"
members:
- CircuitVariable:
- "{\"name\":\"x\",\"span\":\"{\\\"line_start\\\":4,\\\"line_stop\\\":4,\\\"col_start\\\":5,\\\"col_stop\\\":6,\\\"path\\\":\\\"test\\\",\\\"content\\\":\\\" x: u32,\\\"}\"}"
- "{\"name\":\"x\",\"span\":\"{\\\"line_start\\\":4,\\\"line_stop\\\":4,\\\"col_start\\\":5,\\\"col_stop\\\":6,\\\"path\\\":\\\"test\\\",\\\"content\\\":\\\" x: u32;\\\"}\"}"
- IntegerType: U32
- CircuitVariable:
- "{\"name\":\"y\",\"span\":\"{\\\"line_start\\\":5,\\\"line_stop\\\":5,\\\"col_start\\\":5,\\\"col_stop\\\":6,\\\"path\\\":\\\"test\\\",\\\"content\\\":\\\" y: u32,\\\"}\"}"
- "{\"name\":\"y\",\"span\":\"{\\\"line_start\\\":5,\\\"line_stop\\\":5,\\\"col_start\\\":5,\\\"col_stop\\\":6,\\\"path\\\":\\\"test\\\",\\\"content\\\":\\\" y: u32;\\\"}\"}"
- IntegerType: U32
global_consts: {}
functions: {}

View File

@ -0,0 +1,5 @@
---
namespace: Parse
expectation: Fail
outputs:
- " --> test:10:11\n |\n 10 | y: u32;\n | ^\n |\n = Cannot mix use of commas and semi-colons for circuit member variable declarations."

View File

@ -0,0 +1,5 @@
---
namespace: Parse
expectation: Fail
outputs:
- " --> test:3:8\n |\n 3 | import a.();\n | ^\n |\n = Cannot import empty list"

View File

@ -10,12 +10,13 @@ outputs:
name: "{\"name\":\"test-import\",\"span\":\"{\\\"line_start\\\":3,\\\"line_stop\\\":3,\\\"col_start\\\":8,\\\"col_stop\\\":19,\\\"path\\\":\\\"test\\\",\\\"content\\\":\\\"import test-import.*; // local import\\\"}\"}"
access:
Star:
line_start: 3
line_stop: 3
col_start: 20
col_stop: 21
path: test
content: import test-import.*; // local import
span:
line_start: 3
line_stop: 3
col_start: 20
col_stop: 21
path: test
content: import test-import.*; // local import
span:
line_start: 3
line_stop: 3
@ -35,12 +36,13 @@ outputs:
name: "{\"name\":\"bar\",\"span\":\"{\\\"line_start\\\":5,\\\"line_stop\\\":5,\\\"col_start\\\":8,\\\"col_stop\\\":11,\\\"path\\\":\\\"test\\\",\\\"content\\\":\\\"import bar.*; // imports directory import\\\"}\"}"
access:
Star:
line_start: 5
line_stop: 5
col_start: 12
col_stop: 13
path: test
content: import bar.*; // imports directory import
span:
line_start: 5
line_stop: 5
col_start: 12
col_stop: 13
path: test
content: import bar.*; // imports directory import
span:
line_start: 5
line_stop: 5
@ -63,12 +65,13 @@ outputs:
name: "{\"name\":\"baz\",\"span\":\"{\\\"line_start\\\":6,\\\"line_stop\\\":6,\\\"col_start\\\":12,\\\"col_stop\\\":15,\\\"path\\\":\\\"test\\\",\\\"content\\\":\\\"import bar.baz.*; // imports directory import\\\"}\"}"
access:
Star:
line_start: 6
line_stop: 6
col_start: 16
col_stop: 17
path: test
content: import bar.baz.*; // imports directory import
span:
line_start: 6
line_stop: 6
col_start: 16
col_stop: 17
path: test
content: import bar.baz.*; // imports directory import
span:
line_start: 6
line_stop: 6
@ -101,12 +104,13 @@ outputs:
name: "{\"name\":\"bat\",\"span\":\"{\\\"line_start\\\":7,\\\"line_stop\\\":7,\\\"col_start\\\":16,\\\"col_stop\\\":19,\\\"path\\\":\\\"test\\\",\\\"content\\\":\\\"import bar.bat.bat.*; // imports directory import\\\"}\"}"
access:
Star:
line_start: 7
line_stop: 7
col_start: 20
col_stop: 21
path: test
content: import bar.bat.bat.*; // imports directory import
span:
line_start: 7
line_stop: 7
col_start: 20
col_stop: 21
path: test
content: import bar.bat.bat.*; // imports directory import
span:
line_start: 7
line_stop: 7
@ -140,12 +144,13 @@ outputs:
name: "{\"name\":\"car\",\"span\":\"{\\\"line_start\\\":8,\\\"line_stop\\\":8,\\\"col_start\\\":8,\\\"col_stop\\\":11,\\\"path\\\":\\\"test\\\",\\\"content\\\":\\\"import car.*; // imports directory import\\\"}\"}"
access:
Star:
line_start: 8
line_stop: 8
col_start: 12
col_stop: 13
path: test
content: import car.*; // imports directory import
span:
line_start: 8
line_stop: 8
col_start: 12
col_stop: 13
path: test
content: import car.*; // imports directory import
span:
line_start: 8
line_stop: 8

View File

@ -10,12 +10,13 @@ outputs:
name: "{\"name\":\"test-import\",\"span\":\"{\\\"line_start\\\":3,\\\"line_stop\\\":3,\\\"col_start\\\":8,\\\"col_stop\\\":19,\\\"path\\\":\\\"test\\\",\\\"content\\\":\\\"import test-import.*;\\\"}\"}"
access:
Star:
line_start: 3
line_stop: 3
col_start: 20
col_stop: 21
path: test
content: import test-import.*;
span:
line_start: 3
line_stop: 3
col_start: 20
col_stop: 21
path: test
content: import test-import.*;
span:
line_start: 3
line_stop: 3

View File

@ -5,7 +5,7 @@ expectation: Pass
circuit X {
x: u32,
y: u32,
y: u32
function x() {
return ();
}

View File

@ -4,6 +4,6 @@ expectation: Pass
*/
circuit X {
x: u32,
y: u32,
x: u32;
y: u32;
}

View File

@ -0,0 +1,14 @@
/*
namespace: Parse
expectation: Fail
*/
circuit X {
x: u32
y: u32
}
circuit X {
x: u32,
y: u32;
}

View File

@ -0,0 +1,6 @@
/*
namespace: Parse
expectation: Fail
*/
import a.();