diff options
author | Titus Wormer <tituswormer@gmail.com> | 2022-08-11 13:31:20 +0200 |
---|---|---|
committer | Titus Wormer <tituswormer@gmail.com> | 2022-08-11 13:31:20 +0200 |
commit | 2d35cbfceace81a217cd0fbdae7a8777c7a6465e (patch) | |
tree | e5e69d44c5c00d1dc70f4e3a227f67fd5c771389 /src/content | |
parent | 053a2603e4bd5ec9caf40617b52136e5ef3fcf0a (diff) | |
download | markdown-rs-2d35cbfceace81a217cd0fbdae7a8777c7a6465e.tar.gz markdown-rs-2d35cbfceace81a217cd0fbdae7a8777c7a6465e.tar.bz2 markdown-rs-2d35cbfceace81a217cd0fbdae7a8777c7a6465e.zip |
Refactor internal docs, code style of tokenizer
Diffstat (limited to '')
-rw-r--r-- | src/content/document.rs | 42 | ||||
-rw-r--r-- | src/content/string.rs | 2 | ||||
-rw-r--r-- | src/content/text.rs | 10 |
3 files changed, 30 insertions, 24 deletions
diff --git a/src/content/document.rs b/src/content/document.rs index 98f8a7d..49ca919 100644 --- a/src/content/document.rs +++ b/src/content/document.rs @@ -59,7 +59,7 @@ pub fn document(parse_state: &mut ParseState, point: Point) -> Vec<Event> { let state = tokenizer.push( (0, 0), (parse_state.bytes.len(), 0), - StateName::DocumentStart, + State::Next(StateName::DocumentStart), ); tokenizer.flush(state, true); @@ -105,7 +105,7 @@ pub fn document(parse_state: &mut ParseState, point: Point) -> Vec<Event> { /// ^ /// ``` pub fn start(tokenizer: &mut Tokenizer) -> State { - tokenizer.tokenize_state.child_tokenizer = Some(Box::new(Tokenizer::new( + tokenizer.tokenize_state.document_child = Some(Box::new(Tokenizer::new( tokenizer.point.clone(), tokenizer.parse_state, ))); @@ -173,7 +173,7 @@ pub fn container_new_before(tokenizer: &mut Tokenizer) -> State { if tokenizer.tokenize_state.document_continued == tokenizer.tokenize_state.document_container_stack.len() { - let child = tokenizer.tokenize_state.child_tokenizer.as_ref().unwrap(); + let child = tokenizer.tokenize_state.document_child.as_ref().unwrap(); tokenizer.interrupt = child.interrupt; @@ -209,7 +209,12 @@ pub fn container_new_before(tokenizer: &mut Tokenizer) -> State { ) } -/// To do. +/// Maybe before a new container, but not a block quote. +// +/// ```markdown +/// > | * a +/// ^ +/// ``` pub fn container_new_before_not_block_quote(tokenizer: &mut Tokenizer) -> State { // List item? // We replace the empty block quote container for this new list one. @@ -227,7 +232,12 @@ pub fn container_new_before_not_block_quote(tokenizer: &mut Tokenizer) -> State ) } -/// To do. +/// Maybe before a new container, but not a list. +// +/// ```markdown +/// > | a +/// ^ +/// ``` pub fn container_new_before_not_list(tokenizer: &mut Tokenizer) -> State { // It wasn’t a new block quote or a list. // Swap the new container (in the middle) with the existing one (at the end). @@ -283,7 +293,7 @@ pub fn container_new_after(tokenizer: &mut Tokenizer) -> State { /// ^ /// ``` pub fn containers_after(tokenizer: &mut Tokenizer) -> State { - let child = tokenizer.tokenize_state.child_tokenizer.as_mut().unwrap(); + let child = tokenizer.tokenize_state.document_child.as_mut().unwrap(); child.lazy = tokenizer.tokenize_state.document_continued != tokenizer.tokenize_state.document_container_stack.len(); @@ -312,7 +322,12 @@ pub fn containers_after(tokenizer: &mut Tokenizer) -> State { } } -/// To do. +/// In flow. +// +/// ```markdown +/// > | * ab +/// ^ +/// ``` pub fn flow_inside(tokenizer: &mut Tokenizer) -> State { match tokenizer.current { None => { @@ -340,23 +355,18 @@ pub fn flow_inside(tokenizer: &mut Tokenizer) -> State { /// ^ ^ /// ``` pub fn flow_end(tokenizer: &mut Tokenizer) -> State { - let child = tokenizer.tokenize_state.child_tokenizer.as_mut().unwrap(); + let child = tokenizer.tokenize_state.document_child.as_mut().unwrap(); let state = tokenizer .tokenize_state .document_child_state .unwrap_or(State::Next(StateName::FlowStart)); - let name = match state { - State::Next(name) => name, - _ => unreachable!("expected state name"), - }; - tokenizer.tokenize_state.document_exits.push(None); let state = child.push( (child.point.index, child.point.vs), (tokenizer.point.index, tokenizer.point.vs), - name, + state, ); let paragraph = matches!(state, State::Next(StateName::ParagraphInside)) @@ -403,7 +413,7 @@ fn exit_containers(tokenizer: &mut Tokenizer, phase: &Phase) { .document_container_stack .split_off(tokenizer.tokenize_state.document_continued); - let child = tokenizer.tokenize_state.child_tokenizer.as_mut().unwrap(); + let child = tokenizer.tokenize_state.document_child.as_mut().unwrap(); // Flush if needed. if *phase != Phase::After { @@ -463,7 +473,7 @@ fn exit_containers(tokenizer: &mut Tokenizer, phase: &Phase) { // Inject everything together. fn resolve(tokenizer: &mut Tokenizer) { - let child = tokenizer.tokenize_state.child_tokenizer.as_mut().unwrap(); + let child = tokenizer.tokenize_state.document_child.as_mut().unwrap(); // First, add the container exits into `child`. let mut child_index = 0; diff --git a/src/content/string.rs b/src/content/string.rs index 75cd56a..5dfceb0 100644 --- a/src/content/string.rs +++ b/src/content/string.rs @@ -20,7 +20,7 @@ const MARKERS: [u8; 2] = [b'&', b'\\']; /// Start of string. pub fn start(tokenizer: &mut Tokenizer) -> State { tokenizer.register_resolver("whitespace".to_string(), Box::new(resolve)); - tokenizer.tokenize_state.stop = &MARKERS; + tokenizer.tokenize_state.markers = &MARKERS; State::Retry(StateName::StringBefore) } diff --git a/src/content/text.rs b/src/content/text.rs index ee70f33..4e93779 100644 --- a/src/content/text.rs +++ b/src/content/text.rs @@ -38,7 +38,7 @@ const MARKERS: [u8; 9] = [ /// Start of text. pub fn start(tokenizer: &mut Tokenizer) -> State { tokenizer.register_resolver("whitespace".to_string(), Box::new(resolve)); - tokenizer.tokenize_state.stop = &MARKERS; + tokenizer.tokenize_state.markers = &MARKERS; State::Retry(StateName::TextBefore) } @@ -91,7 +91,7 @@ pub fn before(tokenizer: &mut Tokenizer) -> State { } } -/// To do. +/// At `<`, which wasn’t an autolink: before HTML? pub fn before_html(tokenizer: &mut Tokenizer) -> State { tokenizer.attempt( StateName::HtmlTextStart, @@ -100,7 +100,7 @@ pub fn before_html(tokenizer: &mut Tokenizer) -> State { ) } -/// To do. +/// At `\`, which wasn’t a character escape: before a hard break? pub fn before_hard_break_escape(tokenizer: &mut Tokenizer) -> State { tokenizer.attempt( StateName::HardBreakEscapeStart, @@ -110,10 +110,6 @@ pub fn before_hard_break_escape(tokenizer: &mut Tokenizer) -> State { } /// At data. -/// -/// ```markdown -/// |qwe -/// ``` pub fn before_data(tokenizer: &mut Tokenizer) -> State { tokenizer.attempt( StateName::DataStart, |