aboutsummaryrefslogtreecommitdiffstats
path: root/src/construct/partial_destination.rs
diff options
context:
space:
mode:
authorLibravatar Titus Wormer <tituswormer@gmail.com>2022-07-28 16:48:00 +0200
committerLibravatar Titus Wormer <tituswormer@gmail.com>2022-07-28 16:48:00 +0200
commitf7e5fb852dc9c416b9eeb1f0d4f2d51ba5b68456 (patch)
treec1ac3f22473bd79566d835b2474d2ae9e00d6c55 /src/construct/partial_destination.rs
parentd729b07712ca9cc91e68af1776dac9d7008a90cb (diff)
downloadmarkdown-rs-f7e5fb852dc9c416b9eeb1f0d4f2d51ba5b68456.tar.gz
markdown-rs-f7e5fb852dc9c416b9eeb1f0d4f2d51ba5b68456.tar.bz2
markdown-rs-f7e5fb852dc9c416b9eeb1f0d4f2d51ba5b68456.zip
Refactor to work on `char`s
Previously, a custom char implementation was used. This was easier to work with, as sometimes “virtual” characters are injected, or characters are ignored. This replaces that with working on actual `char`s. In the hope of in the future working on `u8`s, even. This simplifies the state machine somewhat, as only `\n` is fed, regardless of whether it was a CRLF, CR, or LF. It also feeds `' '` instead of virtual spaces. The BOM, if present, is now available as a `ByteOrderMark` event.
Diffstat (limited to '')
-rw-r--r--src/construct/partial_destination.rs39
1 files changed, 17 insertions, 22 deletions
diff --git a/src/construct/partial_destination.rs b/src/construct/partial_destination.rs
index 6a984e2..6447228 100644
--- a/src/construct/partial_destination.rs
+++ b/src/construct/partial_destination.rs
@@ -72,7 +72,7 @@
//! [sanitize_uri]: crate::util::sanitize_uri
use crate::token::Token;
-use crate::tokenizer::{Code, ContentType, State, Tokenizer};
+use crate::tokenizer::{ContentType, State, Tokenizer};
/// Configuration.
///
@@ -117,7 +117,7 @@ pub fn start(tokenizer: &mut Tokenizer, options: Options) -> State {
};
match tokenizer.current {
- Code::Char('<') => {
+ Some('<') => {
tokenizer.enter(info.options.destination.clone());
tokenizer.enter(info.options.literal.clone());
tokenizer.enter(info.options.marker.clone());
@@ -125,11 +125,9 @@ pub fn start(tokenizer: &mut Tokenizer, options: Options) -> State {
tokenizer.exit(info.options.marker.clone());
State::Fn(Box::new(|t| enclosed_before(t, info)))
}
- Code::None | Code::CarriageReturnLineFeed | Code::VirtualSpace | Code::Char(' ' | ')') => {
- State::Nok
- }
- Code::Char(char) if char.is_ascii_control() => State::Nok,
- Code::Char(_) => {
+ None | Some(' ' | ')') => State::Nok,
+ Some(char) if char.is_ascii_control() => State::Nok,
+ Some(_) => {
tokenizer.enter(info.options.destination.clone());
tokenizer.enter(info.options.raw.clone());
tokenizer.enter(info.options.string.clone());
@@ -146,7 +144,7 @@ pub fn start(tokenizer: &mut Tokenizer, options: Options) -> State {
/// ^
/// ```
fn enclosed_before(tokenizer: &mut Tokenizer, info: Info) -> State {
- if let Code::Char('>') = tokenizer.current {
+ if let Some('>') = tokenizer.current {
tokenizer.enter(info.options.marker.clone());
tokenizer.consume();
tokenizer.exit(info.options.marker.clone());
@@ -168,13 +166,13 @@ fn enclosed_before(tokenizer: &mut Tokenizer, info: Info) -> State {
/// ```
fn enclosed(tokenizer: &mut Tokenizer, info: Info) -> State {
match tokenizer.current {
- Code::Char('>') => {
+ Some('>') => {
tokenizer.exit(Token::Data);
tokenizer.exit(info.options.string.clone());
enclosed_before(tokenizer, info)
}
- Code::None | Code::CarriageReturnLineFeed | Code::Char('\n' | '\r' | '<') => State::Nok,
- Code::Char('\\') => {
+ None | Some('\n' | '<') => State::Nok,
+ Some('\\') => {
tokenizer.consume();
State::Fn(Box::new(|t| enclosed_escape(t, info)))
}
@@ -193,7 +191,7 @@ fn enclosed(tokenizer: &mut Tokenizer, info: Info) -> State {
/// ```
fn enclosed_escape(tokenizer: &mut Tokenizer, info: Info) -> State {
match tokenizer.current {
- Code::Char('<' | '>' | '\\') => {
+ Some('<' | '>' | '\\') => {
tokenizer.consume();
State::Fn(Box::new(|t| enclosed(t, info)))
}
@@ -209,7 +207,7 @@ fn enclosed_escape(tokenizer: &mut Tokenizer, info: Info) -> State {
/// ```
fn raw(tokenizer: &mut Tokenizer, mut info: Info) -> State {
match tokenizer.current {
- Code::Char('(') => {
+ Some('(') => {
if info.balance >= info.options.limit {
State::Nok
} else {
@@ -218,7 +216,7 @@ fn raw(tokenizer: &mut Tokenizer, mut info: Info) -> State {
State::Fn(Box::new(move |t| raw(t, info)))
}
}
- Code::Char(')') => {
+ Some(')') => {
if info.balance == 0 {
tokenizer.exit(Token::Data);
tokenizer.exit(info.options.string.clone());
@@ -231,10 +229,7 @@ fn raw(tokenizer: &mut Tokenizer, mut info: Info) -> State {
State::Fn(Box::new(move |t| raw(t, info)))
}
}
- Code::None
- | Code::CarriageReturnLineFeed
- | Code::VirtualSpace
- | Code::Char('\t' | '\n' | '\r' | ' ') => {
+ None | Some('\t' | '\n' | ' ') => {
if info.balance > 0 {
State::Nok
} else {
@@ -245,12 +240,12 @@ fn raw(tokenizer: &mut Tokenizer, mut info: Info) -> State {
State::Ok
}
}
- Code::Char(char) if char.is_ascii_control() => State::Nok,
- Code::Char('\\') => {
+ Some(char) if char.is_ascii_control() => State::Nok,
+ Some('\\') => {
tokenizer.consume();
State::Fn(Box::new(move |t| raw_escape(t, info)))
}
- Code::Char(_) => {
+ Some(_) => {
tokenizer.consume();
State::Fn(Box::new(move |t| raw(t, info)))
}
@@ -265,7 +260,7 @@ fn raw(tokenizer: &mut Tokenizer, mut info: Info) -> State {
/// ```
fn raw_escape(tokenizer: &mut Tokenizer, info: Info) -> State {
match tokenizer.current {
- Code::Char('(' | ')' | '\\') => {
+ Some('(' | ')' | '\\') => {
tokenizer.consume();
State::Fn(Box::new(move |t| raw(t, info)))
}