aboutsummaryrefslogtreecommitdiffstats
path: root/src/parser.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/parser.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 'src/parser.rs')
-rw-r--r--src/parser.rs14
1 files changed, 7 insertions, 7 deletions
diff --git a/src/parser.rs b/src/parser.rs
index 0f71daf..cc9c256 100644
--- a/src/parser.rs
+++ b/src/parser.rs
@@ -1,19 +1,18 @@
//! Turn a string of markdown into events.
use crate::content::document::document;
-use crate::tokenizer::{Code, Event, Point};
-use crate::util::codes::parse as parse_codes;
+use crate::tokenizer::{Event, Point};
use crate::{Constructs, Options};
/// Information needed, in all content types, when parsing markdown.
///
/// Importantly, this contains a set of known definitions.
-/// It also references the input value as [`Code`][]s.
+/// It also references the input value as a `Vec<char>`.
#[derive(Debug)]
pub struct ParseState<'a> {
pub constructs: &'a Constructs,
- /// List of codes.
- pub codes: Vec<Code>,
+ /// List of chars.
+ pub chars: Vec<char>,
/// Set of defined identifiers.
pub definitions: Vec<String>,
}
@@ -24,7 +23,8 @@ pub struct ParseState<'a> {
pub fn parse<'a>(value: &str, options: &'a Options) -> (Vec<Event>, ParseState<'a>) {
let mut parse_state = ParseState {
constructs: &options.constructs,
- codes: parse_codes(value),
+ // To do: change to `u8`s?
+ chars: value.chars().collect::<_>(),
definitions: vec![],
};
@@ -33,8 +33,8 @@ pub fn parse<'a>(value: &str, options: &'a Options) -> (Vec<Event>, ParseState<'
Point {
line: 1,
column: 1,
- offset: 0,
index: 0,
+ vs: 0,
},
);