2022-11-17 10:48:43 +00:00
|
|
|
use std::collections::HashMap;
|
|
|
|
|
|
|
|
use nom::{
|
|
|
|
branch::alt,
|
|
|
|
bytes::complete::{tag, take_while, take_while1},
|
2022-11-17 13:58:27 +00:00
|
|
|
combinator::{map, opt},
|
2022-11-17 10:48:43 +00:00
|
|
|
multi::{separated_list0, separated_list1},
|
2022-11-17 13:58:27 +00:00
|
|
|
IResult, InputLength,
|
2022-11-17 10:48:43 +00:00
|
|
|
};
|
|
|
|
|
2022-11-17 13:58:27 +00:00
|
|
|
use crate::dec::{debug, AnyTerm, NonListTerm, Term};
|
2022-11-17 16:55:50 +00:00
|
|
|
use crate::{is_string_char, is_whitespace, DICT_ASSIGN, DICT_CLOSE, DICT_DELIM, DICT_OPEN};
|
2022-11-17 10:48:43 +00:00
|
|
|
|
|
|
|
// ----
|
|
|
|
|
2022-11-17 13:58:27 +00:00
|
|
|
/// The error kind returned by the `decode` function.
|
2022-11-17 10:48:43 +00:00
|
|
|
#[derive(Eq, PartialEq)]
|
2022-11-17 13:58:27 +00:00
|
|
|
pub enum DecodeError<'a> {
|
|
|
|
/// Indicates that there is trailing garbage at the end of the decoded string
|
2022-11-17 10:48:43 +00:00
|
|
|
Garbage(&'a [u8]),
|
2022-11-17 15:35:06 +00:00
|
|
|
/// Indicates that the entered string does not represent a complete nettext term
|
2022-11-17 10:48:43 +00:00
|
|
|
IncompleteInput,
|
2022-11-17 13:58:27 +00:00
|
|
|
/// Indicates a syntax error in the decoded term
|
2022-11-17 10:48:43 +00:00
|
|
|
NomError(&'a [u8], nom::error::ErrorKind),
|
|
|
|
}
|
|
|
|
|
2022-11-17 13:58:27 +00:00
|
|
|
impl<'a> std::fmt::Debug for DecodeError<'a> {
|
2022-11-17 10:48:43 +00:00
|
|
|
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::result::Result<(), std::fmt::Error> {
|
|
|
|
match self {
|
2022-11-17 13:58:27 +00:00
|
|
|
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)),
|
2022-11-17 10:48:43 +00:00
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2022-11-17 13:58:27 +00:00
|
|
|
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> {
|
2022-11-17 10:48:43 +00:00
|
|
|
match e {
|
2022-11-17 13:58:27 +00:00
|
|
|
nom::Err::Incomplete(_) => DecodeError::IncompleteInput,
|
|
|
|
nom::Err::Error(e) | nom::Err::Failure(e) => DecodeError::NomError(e.input, e.code),
|
2022-11-17 10:48:43 +00:00
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
// ----
|
|
|
|
|
2022-11-17 15:35:06 +00:00
|
|
|
/// Decodes a nettext string into the term it represents.
|
2022-11-17 16:55:50 +00:00
|
|
|
pub fn decode(input: &[u8]) -> std::result::Result<Term<'_, '_>, DecodeError<'_>> {
|
2022-11-17 10:48:43 +00:00
|
|
|
let (rest, term) = decode_term(input)?;
|
|
|
|
let (end, _) = take_while(is_whitespace)(rest)?;
|
|
|
|
if !end.is_empty() {
|
2022-11-17 13:58:27 +00:00
|
|
|
return Err(DecodeError::Garbage(end));
|
2022-11-17 10:48:43 +00:00
|
|
|
}
|
2022-11-17 13:58:27 +00:00
|
|
|
Ok(Term(term))
|
2022-11-17 10:48:43 +00:00
|
|
|
}
|
|
|
|
|
2022-11-17 16:55:50 +00:00
|
|
|
fn decode_term(input: &[u8]) -> IResult<&'_ [u8], AnyTerm<'_, '_>> {
|
2022-11-17 10:48:43 +00:00
|
|
|
let (start, _) = take_while(is_whitespace)(input)?;
|
|
|
|
let (rest, list) = separated_list1(take_while1(is_whitespace), decode_nonlist_term)(start)?;
|
|
|
|
|
|
|
|
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];
|
2022-11-17 13:58:27 +00:00
|
|
|
Ok((rest, AnyTerm::List(list_raw, list)))
|
2022-11-17 10:48:43 +00:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2022-11-17 16:55:50 +00:00
|
|
|
fn decode_nonlist_term(input: &[u8]) -> IResult<&'_ [u8], NonListTerm<'_, '_>> {
|
2022-11-17 10:48:43 +00:00
|
|
|
let (rest, term) = alt((
|
|
|
|
map(decode_str, NonListTerm::Str),
|
|
|
|
map(decode_dict, |(raw, d)| NonListTerm::Dict(raw, d)),
|
|
|
|
))(input)?;
|
|
|
|
Ok((rest, term))
|
|
|
|
}
|
|
|
|
|
2022-11-17 14:02:33 +00:00
|
|
|
fn decode_str(input: &[u8]) -> IResult<&'_ [u8], &'_ [u8]> {
|
2022-11-17 10:48:43 +00:00
|
|
|
let (rest, data) = take_while1(is_string_char)(input)?;
|
|
|
|
Ok((rest, data))
|
|
|
|
}
|
|
|
|
|
2022-11-17 16:55:50 +00:00
|
|
|
type DictType<'a> = (&'a [u8], HashMap<&'a [u8], AnyTerm<'a, 'a>>);
|
2022-11-17 10:48:43 +00:00
|
|
|
|
2022-11-17 14:02:33 +00:00
|
|
|
fn decode_dict(dict_begin: &[u8]) -> IResult<&'_ [u8], DictType<'_>> {
|
2022-11-17 16:55:50 +00:00
|
|
|
let (d, _) = tag(&[DICT_OPEN][..])(dict_begin)?;
|
2022-11-17 10:48:43 +00:00
|
|
|
let (d, items) = separated_list0(dict_separator, decode_dict_item)(d)?;
|
2022-11-17 13:58:27 +00:00
|
|
|
let (d, _) = opt(dict_separator)(d)?;
|
2022-11-17 10:48:43 +00:00
|
|
|
let (d, _) = take_while(is_whitespace)(d)?;
|
2022-11-17 16:55:50 +00:00
|
|
|
let (dict_end, _) = tag(&[DICT_CLOSE][..])(d)?;
|
2022-11-17 10:48:43 +00:00
|
|
|
|
|
|
|
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)))
|
|
|
|
}
|
|
|
|
|
2022-11-17 14:02:33 +00:00
|
|
|
fn dict_separator(d: &[u8]) -> IResult<&'_ [u8], ()> {
|
2022-11-17 10:48:43 +00:00
|
|
|
let (d, _) = take_while(is_whitespace)(d)?;
|
2022-11-17 16:55:50 +00:00
|
|
|
let (d, _) = tag(&[DICT_DELIM][..])(d)?;
|
2022-11-17 10:48:43 +00:00
|
|
|
Ok((d, ()))
|
|
|
|
}
|
|
|
|
|
2022-11-17 16:55:50 +00:00
|
|
|
fn decode_dict_item(d: &[u8]) -> IResult<&'_ [u8], (&'_ [u8], AnyTerm<'_, '_>)> {
|
2022-11-17 10:48:43 +00:00
|
|
|
let (d, _) = take_while(is_whitespace)(d)?;
|
|
|
|
let (d, key) = decode_str(d)?;
|
|
|
|
let (d, _) = take_while(is_whitespace)(d)?;
|
2022-11-17 16:55:50 +00:00
|
|
|
let (d, _) = tag(&[DICT_ASSIGN][..])(d)?;
|
2022-11-17 10:48:43 +00:00
|
|
|
let (d, value) = decode_term(d)?;
|
|
|
|
Ok((d, (key, value)))
|
|
|
|
}
|
|
|
|
|
|
|
|
// ----
|
|
|
|
|
|
|
|
#[cfg(test)]
|
|
|
|
mod tests {
|
|
|
|
use super::*;
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
fn simple_str() {
|
|
|
|
let bytes = b" plop ";
|
2022-11-17 13:58:27 +00:00
|
|
|
assert_eq!(decode(bytes), Ok(AnyTerm::Str(b"plop").into()));
|
2022-11-17 10:48:43 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
fn list_of_str_str() {
|
|
|
|
let bytes = b" plop plap plip ploup ";
|
|
|
|
assert_eq!(
|
|
|
|
decode(bytes),
|
2022-11-17 13:58:27 +00:00
|
|
|
Ok(AnyTerm::List(
|
2022-11-17 10:48:43 +00:00
|
|
|
b"plop plap plip ploup",
|
|
|
|
vec![
|
|
|
|
NonListTerm::Str(b"plop"),
|
|
|
|
NonListTerm::Str(b"plap"),
|
|
|
|
NonListTerm::Str(b"plip"),
|
|
|
|
NonListTerm::Str(b"ploup"),
|
|
|
|
]
|
2022-11-17 13:58:27 +00:00
|
|
|
)
|
|
|
|
.into())
|
2022-11-17 10:48:43 +00:00
|
|
|
);
|
|
|
|
}
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
fn simple_dict() {
|
|
|
|
let bytes = b" { aze = hello, by = bojzkz pipo, ccde = ke } ";
|
|
|
|
assert_eq!(
|
|
|
|
decode(bytes),
|
2022-11-17 13:58:27 +00:00
|
|
|
Ok(AnyTerm::Dict(
|
2022-11-17 10:48:43 +00:00
|
|
|
b"{ aze = hello, by = bojzkz pipo, ccde = ke }",
|
|
|
|
[
|
2022-11-17 13:58:27 +00:00
|
|
|
(&b"aze"[..], AnyTerm::Str(b"hello")),
|
2022-11-17 10:48:43 +00:00
|
|
|
(
|
|
|
|
&b"by"[..],
|
2022-11-17 13:58:27 +00:00
|
|
|
AnyTerm::List(
|
2022-11-17 10:48:43 +00:00
|
|
|
b"bojzkz pipo",
|
|
|
|
vec![NonListTerm::Str(b"bojzkz"), NonListTerm::Str(b"pipo")]
|
|
|
|
)
|
|
|
|
),
|
2022-11-17 13:58:27 +00:00
|
|
|
(&b"ccde"[..], AnyTerm::Str(b"ke")),
|
2022-11-17 10:48:43 +00:00
|
|
|
]
|
|
|
|
.into_iter()
|
|
|
|
.collect()
|
2022-11-17 13:58:27 +00:00
|
|
|
)
|
|
|
|
.into())
|
2022-11-17 10:48:43 +00:00
|
|
|
);
|
|
|
|
}
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
fn simple_dict_2() {
|
|
|
|
let bytes = b" { aze = hello, by = bojzkz pipo , ccde = ke , } ";
|
|
|
|
assert_eq!(
|
|
|
|
decode(bytes),
|
2022-11-17 13:58:27 +00:00
|
|
|
Ok(AnyTerm::Dict(
|
2022-11-17 10:48:43 +00:00
|
|
|
b"{ aze = hello, by = bojzkz pipo , ccde = ke , }",
|
|
|
|
[
|
2022-11-17 13:58:27 +00:00
|
|
|
(&b"aze"[..], AnyTerm::Str(b"hello")),
|
2022-11-17 10:48:43 +00:00
|
|
|
(
|
|
|
|
&b"by"[..],
|
2022-11-17 13:58:27 +00:00
|
|
|
AnyTerm::List(
|
2022-11-17 10:48:43 +00:00
|
|
|
b"bojzkz pipo",
|
|
|
|
vec![NonListTerm::Str(b"bojzkz"), NonListTerm::Str(b"pipo")]
|
|
|
|
)
|
|
|
|
),
|
2022-11-17 13:58:27 +00:00
|
|
|
(&b"ccde"[..], AnyTerm::Str(b"ke")),
|
2022-11-17 10:48:43 +00:00
|
|
|
]
|
|
|
|
.into_iter()
|
|
|
|
.collect()
|
2022-11-17 13:58:27 +00:00
|
|
|
)
|
|
|
|
.into())
|
2022-11-17 10:48:43 +00:00
|
|
|
);
|
|
|
|
}
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
fn real_world_1() {
|
|
|
|
let bytes = b"HEAD alexpubkey";
|
|
|
|
assert_eq!(
|
|
|
|
decode(bytes),
|
2022-11-17 13:58:27 +00:00
|
|
|
Ok(AnyTerm::List(
|
2022-11-17 10:48:43 +00:00
|
|
|
b"HEAD alexpubkey",
|
|
|
|
vec![NonListTerm::Str(b"HEAD"), NonListTerm::Str(b"alexpubkey")]
|
2022-11-17 13:58:27 +00:00
|
|
|
)
|
|
|
|
.into()),
|
2022-11-17 10:48:43 +00:00
|
|
|
);
|
|
|
|
}
|
|
|
|
|
|
|
|
#[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),
|
2022-11-17 13:58:27 +00:00
|
|
|
Ok(AnyTerm::List(
|
2022-11-17 10:48:43 +00:00
|
|
|
&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 } }",
|
|
|
|
[
|
2022-11-17 13:58:27 +00:00
|
|
|
(&b"author"[..], AnyTerm::Str(b"alexpubkey")),
|
|
|
|
(&b"height"[..], AnyTerm::Str(b"12")),
|
|
|
|
(&b"parent"[..], AnyTerm::Str(b"parenthash")),
|
|
|
|
(&b"data"[..], AnyTerm::List(
|
2022-11-17 10:48:43 +00:00
|
|
|
b"MESSAGE { text = hello }",
|
|
|
|
vec![
|
|
|
|
NonListTerm::Str(b"MESSAGE"),
|
|
|
|
NonListTerm::Dict(
|
|
|
|
b"{ text = hello }",
|
|
|
|
[
|
2022-11-17 13:58:27 +00:00
|
|
|
(&b"text"[..], AnyTerm::Str(b"hello")),
|
2022-11-17 10:48:43 +00:00
|
|
|
]
|
|
|
|
.into_iter()
|
|
|
|
.collect()
|
|
|
|
)
|
|
|
|
]
|
|
|
|
))
|
|
|
|
].into_iter().collect()
|
|
|
|
),
|
2022-11-17 13:58:27 +00:00
|
|
|
]).into(),
|
|
|
|
));
|
2022-11-17 10:48:43 +00:00
|
|
|
}
|
|
|
|
}
|