Merge branch 'development'
This commit is contained in:
commit
216f4229fc
|
@ -603,6 +603,7 @@ dependencies = [
|
|||
"cfg-if",
|
||||
"itoa",
|
||||
"ryu",
|
||||
"serde",
|
||||
"static_assertions",
|
||||
]
|
||||
|
||||
|
@ -1507,6 +1508,22 @@ dependencies = [
|
|||
"serde_json",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "magnetar_mmm_parser"
|
||||
version = "0.2.1-alpha"
|
||||
dependencies = [
|
||||
"compact_str",
|
||||
"either",
|
||||
"emojis",
|
||||
"nom",
|
||||
"nom_locate",
|
||||
"quick-xml",
|
||||
"serde",
|
||||
"strum",
|
||||
"tracing",
|
||||
"unicode-segmentation",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "magnetar_nodeinfo"
|
||||
version = "0.2.1-alpha"
|
||||
|
@ -1521,6 +1538,7 @@ version = "0.2.1-alpha"
|
|||
dependencies = [
|
||||
"chrono",
|
||||
"http",
|
||||
"magnetar_mmm_parser",
|
||||
"magnetar_sdk_macros",
|
||||
"serde",
|
||||
"serde_json",
|
||||
|
@ -1640,19 +1658,6 @@ dependencies = [
|
|||
"windows-sys",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "mmm_parser"
|
||||
version = "0.2.1-alpha"
|
||||
dependencies = [
|
||||
"compact_str",
|
||||
"either",
|
||||
"emojis",
|
||||
"nom",
|
||||
"nom_locate",
|
||||
"tracing",
|
||||
"unicode-segmentation",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "nom"
|
||||
version = "7.1.3"
|
||||
|
@ -2070,6 +2075,16 @@ dependencies = [
|
|||
"syn 1.0.109",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "quick-xml"
|
||||
version = "0.31.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "1004a344b30a54e2ee58d66a71b32d2db2feb0a31f9a2d302bf0536f15de2a33"
|
||||
dependencies = [
|
||||
"memchr",
|
||||
"serde",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "quote"
|
||||
version = "1.0.32"
|
||||
|
|
|
@ -43,6 +43,7 @@ miette = "5.9"
|
|||
nom = "7"
|
||||
nom_locate = "4"
|
||||
percent-encoding = "2.2"
|
||||
quick-xml = "0.31"
|
||||
redis = "0.23"
|
||||
regex = "1.9"
|
||||
reqwest = "0.11"
|
||||
|
|
|
@ -1,14 +1,21 @@
|
|||
[package]
|
||||
name = "mmm_parser"
|
||||
name = "magnetar_mmm_parser"
|
||||
version.workspace = true
|
||||
edition.workspace = true
|
||||
license = "MIT OR Apache-2.0"
|
||||
|
||||
[features]
|
||||
default = ["xml"]
|
||||
xml = ["dep:quick-xml"]
|
||||
|
||||
[dependencies]
|
||||
either = { workspace = true }
|
||||
emojis = { workspace = true }
|
||||
nom = { workspace = true }
|
||||
nom_locate = { workspace = true }
|
||||
compact_str = { workspace = true }
|
||||
compact_str = { workspace = true, features = ["serde"] }
|
||||
serde = { workspace = true, features = ["derive"] }
|
||||
strum = { workspace = true, features = ["derive"] }
|
||||
tracing = { workspace = true }
|
||||
unicode-segmentation = { workspace = true }
|
||||
quick-xml = { workspace = "true", optional = true, features = ["serialize"] }
|
||||
|
|
|
@ -8,17 +8,24 @@ use nom::character::complete::{
|
|||
};
|
||||
use nom::combinator::{eof, fail, map, not, opt, peek, recognize};
|
||||
use nom::error::ErrorKind;
|
||||
use nom::multi::{many0, many0_count, many1, many1_count, many_till, separated_list1};
|
||||
use nom::multi::{many0_count, many1, many1_count, many_till, separated_list1};
|
||||
use nom::sequence::tuple;
|
||||
use nom::{IResult, Offset, Parser, Slice};
|
||||
use nom_locate::LocatedSpan;
|
||||
use quick_xml::events::{BytesText, Event};
|
||||
use serde::{Deserialize, Serialize};
|
||||
use std::collections::HashMap;
|
||||
use std::convert::{identity, Infallible};
|
||||
use std::io::{Cursor, Write};
|
||||
use std::marker::PhantomData;
|
||||
use strum::IntoStaticStr;
|
||||
use tracing::trace;
|
||||
use unicode_segmentation::UnicodeSegmentation;
|
||||
|
||||
#[derive(Copy, Clone, Debug, Eq, PartialEq)]
|
||||
#[derive(Copy, Clone, Debug, Eq, PartialEq, Deserialize, Serialize, IntoStaticStr)]
|
||||
// The alternative would be to implement a serde serializer for this one enum, but that's disgusting
|
||||
#[strum(serialize_all = "snake_case")]
|
||||
#[serde(rename_all = "snake_case")]
|
||||
pub enum MentionType {
|
||||
Community,
|
||||
User,
|
||||
|
@ -33,7 +40,7 @@ impl MentionType {
|
|||
}
|
||||
}
|
||||
|
||||
#[derive(Clone, Debug, Eq, PartialEq)]
|
||||
#[derive(Clone, Debug, Eq, PartialEq, Deserialize, Serialize)]
|
||||
pub enum Token {
|
||||
PlainText(CompactString),
|
||||
Sequence(Vec<Token>),
|
||||
|
@ -216,6 +223,161 @@ impl Token {
|
|||
other => other.clone(),
|
||||
}
|
||||
}
|
||||
|
||||
fn write<T: Write>(&self, writer: &mut quick_xml::Writer<T>) -> quick_xml::Result<()> {
|
||||
match self {
|
||||
Token::PlainText(plain) => {
|
||||
writer.write_event(Event::Text(BytesText::new(plain.as_str())))?;
|
||||
}
|
||||
Token::Sequence(sequence) => {
|
||||
sequence.iter().try_for_each(|item| item.write(writer))?;
|
||||
}
|
||||
Token::Quote(inner) => {
|
||||
writer
|
||||
.create_element("quote")
|
||||
.write_inner_content(|w| inner.write(w))?;
|
||||
}
|
||||
Token::Small(inner) => {
|
||||
writer
|
||||
.create_element("small")
|
||||
.write_inner_content(|w| inner.write(w))?;
|
||||
}
|
||||
Token::BoldItalic(inner) => {
|
||||
writer
|
||||
.create_element("b")
|
||||
.write_inner_content::<_, quick_xml::Error>(|w| {
|
||||
w.create_element("i")
|
||||
.write_inner_content(|w| inner.write(w))?;
|
||||
|
||||
Ok(())
|
||||
})?;
|
||||
}
|
||||
Token::Bold(inner) => {
|
||||
writer
|
||||
.create_element("b")
|
||||
.write_inner_content(|w| inner.write(w))?;
|
||||
}
|
||||
Token::Italic(inner) => {
|
||||
writer
|
||||
.create_element("i")
|
||||
.write_inner_content(|w| inner.write(w))?;
|
||||
}
|
||||
Token::Center(inner) => {
|
||||
writer
|
||||
.create_element("center")
|
||||
.write_inner_content(|w| inner.write(w))?;
|
||||
}
|
||||
Token::Strikethrough(inner) => {
|
||||
writer
|
||||
.create_element("s")
|
||||
.write_inner_content(|w| inner.write(w))?;
|
||||
}
|
||||
Token::PlainTag(plain) => {
|
||||
writer.write_event(Event::Text(BytesText::new(plain.as_str())))?;
|
||||
}
|
||||
Token::InlineCode(code) => {
|
||||
writer
|
||||
.create_element("inline-code")
|
||||
.write_text_content(BytesText::new(code))?;
|
||||
}
|
||||
Token::InlineMath(math) => {
|
||||
writer
|
||||
.create_element("inline-math")
|
||||
.write_text_content(BytesText::new(math))?;
|
||||
}
|
||||
Token::UrlRaw(url) => {
|
||||
writer
|
||||
.create_element("a")
|
||||
.with_attribute(("href", url.as_str()))
|
||||
.write_text_content(BytesText::new(url))?;
|
||||
}
|
||||
Token::UrlNoEmbed(url) => {
|
||||
writer
|
||||
.create_element("a")
|
||||
.with_attribute(("href", url.as_str()))
|
||||
.with_attribute(("embed", "false"))
|
||||
.write_text_content(BytesText::new(url))?;
|
||||
}
|
||||
Token::Link { label, href, embed } => {
|
||||
writer
|
||||
.create_element("a")
|
||||
.with_attribute(("href", href.as_str()))
|
||||
.with_attribute(("embed", if *embed { "true" } else { "false" }))
|
||||
.write_inner_content(|w| label.write(w))?;
|
||||
}
|
||||
Token::BlockCode { inner, lang } => {
|
||||
let mut ew = writer.create_element("code");
|
||||
|
||||
if let Some(language) = lang {
|
||||
ew = ew.with_attribute(("lang", language.as_str()));
|
||||
}
|
||||
|
||||
ew.write_text_content(BytesText::new(inner))?;
|
||||
}
|
||||
Token::BlockMath(math) => {
|
||||
writer
|
||||
.create_element("math")
|
||||
.write_text_content(BytesText::new(math))?;
|
||||
}
|
||||
Token::Function {
|
||||
inner,
|
||||
name,
|
||||
params,
|
||||
} => {
|
||||
let mut ew = writer
|
||||
.create_element("fn")
|
||||
.with_attribute(("name", name.as_str()));
|
||||
|
||||
for (k, v) in params {
|
||||
ew = ew
|
||||
.with_attribute((format!("arg-{k}").as_str(), v.as_deref().unwrap_or("")));
|
||||
}
|
||||
|
||||
ew.write_inner_content(|w| inner.write(w))?;
|
||||
}
|
||||
Token::Mention {
|
||||
name,
|
||||
host,
|
||||
mention_type,
|
||||
} => {
|
||||
let mut ew = writer
|
||||
.create_element("mention")
|
||||
.with_attribute(("name", name.as_str()))
|
||||
.with_attribute(("type", mention_type.into()));
|
||||
|
||||
if let Some(host) = host {
|
||||
ew = ew.with_attribute(("host", host.as_str()));
|
||||
}
|
||||
|
||||
ew.write_empty()?;
|
||||
}
|
||||
Token::UnicodeEmoji(text) => {
|
||||
writer
|
||||
.create_element("ue")
|
||||
.write_text_content(BytesText::new(text))?;
|
||||
}
|
||||
Token::ShortcodeEmoji(shortcode) => {
|
||||
writer
|
||||
.create_element("ee")
|
||||
.write_text_content(BytesText::new(shortcode))?;
|
||||
}
|
||||
Token::Hashtag(tag) => {
|
||||
writer
|
||||
.create_element("hashtag")
|
||||
.with_attribute(("tag", tag.as_str()));
|
||||
}
|
||||
}
|
||||
|
||||
Ok(())
|
||||
}
|
||||
}
|
||||
|
||||
pub fn to_xml_string(token: &Token) -> quick_xml::Result<String> {
|
||||
let mut writer = quick_xml::Writer::new(Cursor::new(Vec::new()));
|
||||
writer
|
||||
.create_element("mmm")
|
||||
.write_inner_content(|writer| token.write(writer))?;
|
||||
Ok(String::from_utf8(writer.into_inner().into_inner())?)
|
||||
}
|
||||
|
||||
#[derive(Debug, Default, Copy, Clone)]
|
||||
|
@ -315,11 +477,11 @@ fn spliced<'a>(
|
|||
type NE<E> = nom::Err<E>;
|
||||
type NomError<'x> = nom::error::Error<Span<'x>>;
|
||||
|
||||
let quote_span = Span::new_extra(
|
||||
let spliced_span = Span::new_extra(
|
||||
&combined,
|
||||
segments.first().map_or(SpanMeta::new(0), |s| s.extra),
|
||||
);
|
||||
let (input, inner) = match func(quote_span) {
|
||||
let (input, inner) = match func(spliced_span) {
|
||||
Ok(s) => s,
|
||||
Err(e) => {
|
||||
return match e {
|
||||
|
@ -689,7 +851,7 @@ impl Context {
|
|||
|
||||
let (input, _) = delim(input)?;
|
||||
let (input, lang) = opt(map(
|
||||
recognize(many1(tuple((not(delim), not_line_ending)))),
|
||||
recognize(many1(tuple((not(delim), not(line_ending), anychar)))),
|
||||
Span::into_fragment,
|
||||
))(input)?;
|
||||
let (input, _) = line_ending(input)?;
|
||||
|
@ -704,8 +866,10 @@ impl Context {
|
|||
|
||||
let (input, _) = line_ending(input)?;
|
||||
let (input, _) = delim(input)?;
|
||||
let (input, _) = many0(space)(input)?;
|
||||
let (input, _) = not(not(line_ending))(input)?;
|
||||
// Trailing whitespace after the triple backtick
|
||||
let (input, _) = opt(space1_unicode)(input)?;
|
||||
// If we got this far, the next character should be a line ending
|
||||
let (input, _) = not(tuple((not(line_ending), anychar)))(input)?;
|
||||
let (input, _) = opt(line_ending)(input)?;
|
||||
|
||||
Ok((
|
||||
|
@ -737,8 +901,10 @@ impl Context {
|
|||
|
||||
let (input, _) = opt(line_ending)(input)?;
|
||||
let (input, _) = end(input)?;
|
||||
let (input, _) = many0(space)(input)?;
|
||||
let (input, _) = not(not_line_ending)(input)?;
|
||||
// Trailing whitespace after the closing delim
|
||||
let (input, _) = opt(space1_unicode)(input)?;
|
||||
// If we got this far, the next character should be a line ending
|
||||
let (input, _) = not(tuple((not(line_ending), anychar)))(input)?;
|
||||
let (input, _) = opt(line_ending)(input)?;
|
||||
|
||||
Ok((
|
||||
|
@ -874,7 +1040,7 @@ impl Context {
|
|||
)))(input)
|
||||
};
|
||||
|
||||
let param_value = recognize(many1_count(alt((
|
||||
let arg_value = recognize(many1_count(alt((
|
||||
alphanumeric1,
|
||||
tag("."),
|
||||
tag("-"),
|
||||
|
@ -883,7 +1049,7 @@ impl Context {
|
|||
|
||||
let (input, func_name) = map(func_ident, Span::into_fragment)(input)?;
|
||||
|
||||
let arg = tuple((func_ident, opt(tuple((tag("="), param_value)))));
|
||||
let arg = tuple((func_ident, opt(tuple((tag("="), arg_value)))));
|
||||
|
||||
let (input, args) =
|
||||
opt(tuple((one_char('.'), separated_list1(one_char(','), arg))))(input)?;
|
||||
|
@ -1427,7 +1593,7 @@ impl Context {
|
|||
|
||||
#[cfg(test)]
|
||||
mod test {
|
||||
use crate::{Context, Span, SpanMeta, Token, DEFAULT_DEPTH_LIMIT};
|
||||
use crate::{to_xml_string, Context, Span, SpanMeta, Token, DEFAULT_DEPTH_LIMIT};
|
||||
use nom::bytes::complete::tag;
|
||||
use std::collections::HashMap;
|
||||
|
||||
|
@ -1583,10 +1749,58 @@ mod test {
|
|||
"bold italic".into()
|
||||
)))))
|
||||
);
|
||||
|
||||
assert_eq!(
|
||||
parse_full("~~*hello\nworld*"),
|
||||
Token::PlainText("~~*hello\nworld*".into())
|
||||
)
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn parse_complex() {
|
||||
assert_eq!(
|
||||
parse_full(r"\( nya^3 \)"),
|
||||
Token::InlineMath(" nya^3 ".to_string())
|
||||
);
|
||||
|
||||
assert_eq!(
|
||||
parse_full("\\( nya^3 \n \\)"),
|
||||
Token::PlainText("\\( nya^3 \n \\)".into())
|
||||
);
|
||||
|
||||
assert_eq!(
|
||||
parse_full(r"`AbstractProxyFactoryBean`"),
|
||||
Token::InlineCode("AbstractProxyFactoryBean".to_string())
|
||||
);
|
||||
|
||||
assert_eq!(
|
||||
parse_full("`let x = \n 5;`"),
|
||||
Token::PlainText("`let x = \n 5;`".into())
|
||||
);
|
||||
|
||||
assert_eq!(
|
||||
parse_full(
|
||||
r#"
|
||||
```js
|
||||
var x = undefined;
|
||||
```"#
|
||||
),
|
||||
Token::BlockCode {
|
||||
lang: Some("js".to_string()),
|
||||
inner: "var x = undefined;".to_string(),
|
||||
}
|
||||
);
|
||||
|
||||
assert_eq!(
|
||||
parse_full(
|
||||
r"
|
||||
\[
|
||||
a^2 + b^2 = c^2
|
||||
\]"
|
||||
),
|
||||
Token::BlockMath("a^2 + b^2 = c^2".to_string())
|
||||
);
|
||||
|
||||
assert_eq!(
|
||||
parse_full(
|
||||
r#"<center>centered
|
||||
|
@ -2004,4 +2218,31 @@ text</center>"#
|
|||
])
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn xml_serialization() {
|
||||
assert_eq!(
|
||||
&to_xml_string(&parse_full("***nyaaa***")).unwrap(),
|
||||
r#"<mmm><b><i>nyaaa</i></b></mmm>"#
|
||||
);
|
||||
|
||||
assert_eq!(
|
||||
&to_xml_string(&parse_full(
|
||||
"@natty $[spin.speed=0.5s 🥺]:cat_attack: <plain>test</plain>"
|
||||
))
|
||||
.unwrap(),
|
||||
r#"<mmm><mention name="natty" type="user"/> <fn name="spin" arg-speed="0.5s"><ue>🥺</ue></fn><ee>cat_attack</ee> test</mmm>"#
|
||||
);
|
||||
|
||||
assert_eq!(
|
||||
&to_xml_string(&parse_full(
|
||||
r#"
|
||||
```js
|
||||
var x = undefined;
|
||||
``` "#
|
||||
))
|
||||
.unwrap(),
|
||||
"<mmm><code lang=\"js\">var x = undefined;</code></mmm>"
|
||||
);
|
||||
}
|
||||
}
|
||||
|
|
|
@ -5,6 +5,7 @@ edition.workspace = true
|
|||
license = "MIT OR Apache-2.0"
|
||||
|
||||
[dependencies]
|
||||
magnetar_mmm_parser = { path = "../magnetar_mmm_parser" }
|
||||
magnetar_sdk_macros = { path = "./macros" }
|
||||
|
||||
chrono = { workspace = true, features = ["serde"] }
|
||||
|
@ -15,4 +16,4 @@ serde_json = { workspace = true }
|
|||
|
||||
ts-rs = { workspace = true, features = ["chrono", "chrono-impl"] }
|
||||
|
||||
unicode-segmentation = { workspace = true }
|
||||
unicode-segmentation = { workspace = true }
|
||||
|
|
|
@ -1,6 +1,7 @@
|
|||
use serde::{Deserialize, Serialize};
|
||||
use ts_rs::TS;
|
||||
|
||||
pub use magnetar_mmm_parser as mmm;
|
||||
pub mod endpoints;
|
||||
pub mod types;
|
||||
pub mod util_types;
|
||||
|
|
Loading…
Reference in New Issue