277 lines
8.5 KiB
Rust
277 lines
8.5 KiB
Rust
use std::collections::HashMap;
|
|
|
|
use nom::{
|
|
branch::alt,
|
|
bytes::complete::{tag, take_while, take_while1},
|
|
combinator::{map, opt},
|
|
multi::{separated_list0, separated_list1},
|
|
IResult, InputLength,
|
|
};
|
|
|
|
use crate::dec::{debug, AnyTerm, NonListTerm, Term};
|
|
|
|
const DICT_OPEN: &[u8] = b"{";
|
|
const DICT_CLOSE: &[u8] = b"}";
|
|
const DICT_ASSIGN: &[u8] = b"=";
|
|
const DICT_DELIM: &[u8] = b",";
|
|
const STR_EXTRA_CHARS: &[u8] = b"._-*?";
|
|
|
|
// ----
|
|
|
|
/// The error kind returned by the `decode` function.
|
|
#[derive(Eq, PartialEq)]
|
|
pub enum DecodeError<'a> {
|
|
/// Indicates that there is trailing garbage at the end of the decoded string
|
|
Garbage(&'a [u8]),
|
|
/// Indicates that the entered string does not represent a complete NetText term
|
|
IncompleteInput,
|
|
/// Indicates a syntax error in the decoded term
|
|
NomError(&'a [u8], nom::error::ErrorKind),
|
|
}
|
|
|
|
impl<'a> std::fmt::Debug for DecodeError<'a> {
|
|
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::result::Result<(), std::fmt::Error> {
|
|
match self {
|
|
DecodeError::Garbage(g) => write!(f, "Garbage: `{}`", debug(g)),
|
|
DecodeError::IncompleteInput => write!(f, "Incomplete input"),
|
|
DecodeError::NomError(s, e) => write!(f, "Nom: {:?}, at: `{}`", e, debug(s)),
|
|
}
|
|
}
|
|
}
|
|
|
|
/// The result type returned by the `decode` function
|
|
pub type DecodeResult<'a, T> = std::result::Result<T, DecodeError<'a>>;
|
|
|
|
impl<'a> From<nom::Err<nom::error::Error<&'a [u8]>>> for DecodeError<'a> {
|
|
fn from(e: nom::Err<nom::error::Error<&'a [u8]>>) -> DecodeError<'a> {
|
|
match e {
|
|
nom::Err::Incomplete(_) => DecodeError::IncompleteInput,
|
|
nom::Err::Error(e) | nom::Err::Failure(e) => DecodeError::NomError(e.input, e.code),
|
|
}
|
|
}
|
|
}
|
|
|
|
// ----
|
|
|
|
/// Decodes a NetText string into the term it represents.
|
|
pub fn decode<'a>(input: &'a [u8]) -> DecodeResult<'a, Term<'a, 'static>> {
|
|
let (rest, term) = decode_term(input)?;
|
|
let (end, _) = take_while(is_whitespace)(rest)?;
|
|
if !end.is_empty() {
|
|
return Err(DecodeError::Garbage(end));
|
|
}
|
|
Ok(Term(term))
|
|
}
|
|
|
|
fn decode_term<'a>(input: &'a [u8]) -> IResult<&'a [u8], AnyTerm<'a, 'static>> {
|
|
eprintln!("DT: `{}`", debug(input));
|
|
let (start, _) = take_while(is_whitespace)(input)?;
|
|
eprintln!("DT2: `{}`", debug(start));
|
|
let (rest, list) = separated_list1(take_while1(is_whitespace), decode_nonlist_term)(start)?;
|
|
eprintln!("DT3: `{}`", debug(rest));
|
|
|
|
if list.len() == 1 {
|
|
Ok((rest, list.into_iter().next().unwrap().into()))
|
|
} else {
|
|
let raw_len = start.input_len() - rest.input_len();
|
|
let list_raw = &start[..raw_len];
|
|
Ok((rest, AnyTerm::List(list_raw, list)))
|
|
}
|
|
}
|
|
|
|
fn decode_nonlist_term<'a>(input: &'a [u8]) -> IResult<&'a [u8], NonListTerm<'a, 'static>> {
|
|
eprintln!("DNLT: `{}`", debug(input));
|
|
let (rest, term) = alt((
|
|
map(decode_str, NonListTerm::Str),
|
|
map(decode_dict, |(raw, d)| NonListTerm::Dict(raw, d)),
|
|
))(input)?;
|
|
eprintln!("DNLTend: `{}` {:?}", debug(rest), term);
|
|
Ok((rest, term))
|
|
}
|
|
|
|
fn decode_str<'a>(input: &'a [u8]) -> IResult<&'a [u8], &'a [u8]> {
|
|
eprintln!("DS: `{}`", debug(input));
|
|
let (rest, data) = take_while1(is_string_char)(input)?;
|
|
Ok((rest, data))
|
|
}
|
|
|
|
type DictType<'a> = (&'a [u8], HashMap<&'a [u8], AnyTerm<'a, 'static>>);
|
|
|
|
fn decode_dict<'a>(dict_begin: &'a [u8]) -> IResult<&'a [u8], DictType<'a>> {
|
|
eprintln!("DDbegin: `{}`", debug(dict_begin));
|
|
let (d, _) = tag(DICT_OPEN)(dict_begin)?;
|
|
eprintln!("DD2: `{}`", debug(d));
|
|
let (d, items) = separated_list0(dict_separator, decode_dict_item)(d)?;
|
|
eprintln!("DD3: `{}`", debug(d));
|
|
let (d, _) = opt(dict_separator)(d)?;
|
|
let (d, _) = take_while(is_whitespace)(d)?;
|
|
eprintln!("DD4: `{}`", debug(d));
|
|
let (dict_end, _) = tag(DICT_CLOSE)(d)?;
|
|
eprintln!("DDend: `{}`", debug(dict_end));
|
|
|
|
let dict = items.into_iter().collect::<HashMap<_, _>>();
|
|
|
|
let raw_len = dict_begin.input_len() - dict_end.input_len();
|
|
let dict_raw = &dict_begin[..raw_len];
|
|
|
|
Ok((dict_end, (dict_raw, dict)))
|
|
}
|
|
|
|
fn dict_separator<'a>(d: &'a [u8]) -> IResult<&'a [u8], ()> {
|
|
let (d, _) = take_while(is_whitespace)(d)?;
|
|
let (d, _) = tag(DICT_DELIM)(d)?;
|
|
Ok((d, ()))
|
|
}
|
|
|
|
fn decode_dict_item<'a>(d: &'a [u8]) -> IResult<&'a [u8], (&'a [u8], AnyTerm<'a, 'static>)> {
|
|
eprintln!("DDI: `{}`", debug(d));
|
|
let (d, _) = take_while(is_whitespace)(d)?;
|
|
eprintln!("DDI1: `{}`", debug(d));
|
|
let (d, key) = decode_str(d)?;
|
|
eprintln!("DDI2: `{}`", debug(d));
|
|
let (d, _) = take_while(is_whitespace)(d)?;
|
|
let (d, _) = tag(DICT_ASSIGN)(d)?;
|
|
eprintln!("DDI3: `{}`", debug(d));
|
|
let (d, value) = decode_term(d)?;
|
|
eprintln!("DDI4: `{}`", debug(d));
|
|
Ok((d, (key, value)))
|
|
}
|
|
|
|
fn is_string_char(c: u8) -> bool {
|
|
c.is_ascii_alphanumeric() || STR_EXTRA_CHARS.contains(&c)
|
|
}
|
|
|
|
fn is_whitespace(c: u8) -> bool {
|
|
c.is_ascii_whitespace()
|
|
}
|
|
|
|
// ----
|
|
|
|
#[cfg(test)]
|
|
mod tests {
|
|
use super::*;
|
|
|
|
#[test]
|
|
fn simple_str() {
|
|
let bytes = b" plop ";
|
|
assert_eq!(decode(bytes), Ok(AnyTerm::Str(b"plop").into()));
|
|
}
|
|
|
|
#[test]
|
|
fn list_of_str_str() {
|
|
let bytes = b" plop plap plip ploup ";
|
|
assert_eq!(
|
|
decode(bytes),
|
|
Ok(AnyTerm::List(
|
|
b"plop plap plip ploup",
|
|
vec![
|
|
NonListTerm::Str(b"plop"),
|
|
NonListTerm::Str(b"plap"),
|
|
NonListTerm::Str(b"plip"),
|
|
NonListTerm::Str(b"ploup"),
|
|
]
|
|
)
|
|
.into())
|
|
);
|
|
}
|
|
|
|
#[test]
|
|
fn simple_dict() {
|
|
let bytes = b" { aze = hello, by = bojzkz pipo, ccde = ke } ";
|
|
assert_eq!(
|
|
decode(bytes),
|
|
Ok(AnyTerm::Dict(
|
|
b"{ aze = hello, by = bojzkz pipo, ccde = ke }",
|
|
[
|
|
(&b"aze"[..], AnyTerm::Str(b"hello")),
|
|
(
|
|
&b"by"[..],
|
|
AnyTerm::List(
|
|
b"bojzkz pipo",
|
|
vec![NonListTerm::Str(b"bojzkz"), NonListTerm::Str(b"pipo")]
|
|
)
|
|
),
|
|
(&b"ccde"[..], AnyTerm::Str(b"ke")),
|
|
]
|
|
.into_iter()
|
|
.collect()
|
|
)
|
|
.into())
|
|
);
|
|
}
|
|
|
|
#[test]
|
|
fn simple_dict_2() {
|
|
let bytes = b" { aze = hello, by = bojzkz pipo , ccde = ke , } ";
|
|
assert_eq!(
|
|
decode(bytes),
|
|
Ok(AnyTerm::Dict(
|
|
b"{ aze = hello, by = bojzkz pipo , ccde = ke , }",
|
|
[
|
|
(&b"aze"[..], AnyTerm::Str(b"hello")),
|
|
(
|
|
&b"by"[..],
|
|
AnyTerm::List(
|
|
b"bojzkz pipo",
|
|
vec![NonListTerm::Str(b"bojzkz"), NonListTerm::Str(b"pipo")]
|
|
)
|
|
),
|
|
(&b"ccde"[..], AnyTerm::Str(b"ke")),
|
|
]
|
|
.into_iter()
|
|
.collect()
|
|
)
|
|
.into())
|
|
);
|
|
}
|
|
|
|
#[test]
|
|
fn real_world_1() {
|
|
let bytes = b"HEAD alexpubkey";
|
|
assert_eq!(
|
|
decode(bytes),
|
|
Ok(AnyTerm::List(
|
|
b"HEAD alexpubkey",
|
|
vec![NonListTerm::Str(b"HEAD"), NonListTerm::Str(b"alexpubkey")]
|
|
)
|
|
.into()),
|
|
);
|
|
}
|
|
|
|
#[test]
|
|
fn real_world_2() {
|
|
let bytes = b"STANCE sthash stsign { author = alexpubkey, height = 12, parent = parenthash, data = MESSAGE { text = hello } }";
|
|
assert_eq!(
|
|
decode(bytes),
|
|
Ok(AnyTerm::List(
|
|
&bytes[..],
|
|
vec![
|
|
NonListTerm::Str(b"STANCE"),
|
|
NonListTerm::Str(b"sthash"),
|
|
NonListTerm::Str(b"stsign"),
|
|
NonListTerm::Dict(b"{ author = alexpubkey, height = 12, parent = parenthash, data = MESSAGE { text = hello } }",
|
|
[
|
|
(&b"author"[..], AnyTerm::Str(b"alexpubkey")),
|
|
(&b"height"[..], AnyTerm::Str(b"12")),
|
|
(&b"parent"[..], AnyTerm::Str(b"parenthash")),
|
|
(&b"data"[..], AnyTerm::List(
|
|
b"MESSAGE { text = hello }",
|
|
vec![
|
|
NonListTerm::Str(b"MESSAGE"),
|
|
NonListTerm::Dict(
|
|
b"{ text = hello }",
|
|
[
|
|
(&b"text"[..], AnyTerm::Str(b"hello")),
|
|
]
|
|
.into_iter()
|
|
.collect()
|
|
)
|
|
]
|
|
))
|
|
].into_iter().collect()
|
|
),
|
|
]).into(),
|
|
));
|
|
}
|
|
}
|