diff options
| author |  Titus Wormer <tituswormer@gmail.com> | 2022-08-11 13:45:24 +0200 |
|---|---|---|
| committer | Titus Wormer <tituswormer@gmail.com> | 2022-08-11 13:45:24 +0200 |
| commit | 6eb2f644057f371841fe25330a57ee185f91c7af (patch) | |
| tree | 7b4d02586339d1a7f82104b4473d9ac243b3abf9 /src/construct | |
| parent | 2d35cbfceace81a217cd0fbdae7a8777c7a6465e (diff) | |
| download | markdown-rs-6eb2f644057f371841fe25330a57ee185f91c7af.tar.gz markdown-rs-6eb2f644057f371841fe25330a57ee185f91c7af.tar.bz2 markdown-rs-6eb2f644057f371841fe25330a57ee185f91c7af.zip | |
Refactor to move some code to `state.rs`
Diffstat (limited to 'src/construct')
28 files changed, 468 insertions, 462 deletions
diff --git a/src/construct/attention.rs b/src/construct/attention.rs index d61813d..7e873ca 100644 --- a/src/construct/attention.rs +++ b/src/construct/attention.rs @@ -51,8 +51,9 @@ //! [html-em]: https://html.spec.whatwg.org/multipage/text-level-semantics.html#the-em-element //! [html-strong]: https://html.spec.whatwg.org/multipage/text-level-semantics.html#the-strong-element +use crate::state::{Name, State}; use crate::token::Token; -use crate::tokenizer::{Event, EventType, Point, State, StateName, Tokenizer}; +use crate::tokenizer::{Event, EventType, Point, Tokenizer}; use crate::unicode::PUNCTUATION; use crate::util::slice::Slice; @@ -120,7 +121,7 @@ pub fn start(tokenizer: &mut Tokenizer) -> State { Some(b'*' | b'_') if tokenizer.parse_state.constructs.attention => { tokenizer.tokenize_state.marker = tokenizer.current.unwrap(); tokenizer.enter(Token::AttentionSequence); - State::Retry(StateName::AttentionInside) + State::Retry(Name::AttentionInside) } _ => State::Nok, } @@ -136,7 +137,7 @@ pub fn inside(tokenizer: &mut Tokenizer) -> State { match tokenizer.current { Some(b'*' | b'_') if tokenizer.current.unwrap() == tokenizer.tokenize_state.marker => { tokenizer.consume(); - State::Next(StateName::AttentionInside) + State::Next(Name::AttentionInside) } _ => { tokenizer.exit(Token::AttentionSequence); diff --git a/src/construct/autolink.rs b/src/construct/autolink.rs index eef3840..b635d96 100644 --- a/src/construct/autolink.rs +++ b/src/construct/autolink.rs @@ -102,8 +102,9 @@ //! [html-a]: https://html.spec.whatwg.org/multipage/text-level-semantics.html#the-a-element use crate::constant::{AUTOLINK_DOMAIN_SIZE_MAX, AUTOLINK_SCHEME_SIZE_MAX}; +use crate::state::{Name, State}; use crate::token::Token; -use crate::tokenizer::{State, StateName, Tokenizer}; +use crate::tokenizer::Tokenizer; /// Start of an autolink. /// @@ -121,7 +122,7 @@ pub fn start(tokenizer: &mut Tokenizer) -> State { tokenizer.consume(); tokenizer.exit(Token::AutolinkMarker); tokenizer.enter(Token::AutolinkProtocol); - State::Next(StateName::AutolinkOpen) + State::Next(Name::AutolinkOpen) } _ => State::Nok, } @@ -140,9 +141,9 @@ pub fn open(tokenizer: &mut Tokenizer) -> State { // ASCII alphabetic. Some(b'A'..=b'Z' | b'a'..=b'z') => { tokenizer.consume(); - State::Next(StateName::AutolinkSchemeOrEmailAtext) + State::Next(Name::AutolinkSchemeOrEmailAtext) } - _ => State::Retry(StateName::AutolinkEmailAtext), + _ => State::Retry(Name::AutolinkEmailAtext), } } @@ -160,9 +161,9 @@ pub fn scheme_or_email_atext(tokenizer: &mut Tokenizer) -> State { Some(b'+' | b'-' | b'.' | b'0'..=b'9' | b'A'..=b'Z' | b'a'..=b'z') => { // Count the previous alphabetical from `open` too. tokenizer.tokenize_state.size = 1; - State::Retry(StateName::AutolinkSchemeInsideOrEmailAtext) + State::Retry(Name::AutolinkSchemeInsideOrEmailAtext) } - _ => State::Retry(StateName::AutolinkEmailAtext), + _ => State::Retry(Name::AutolinkEmailAtext), } } @@ -179,7 +180,7 @@ pub fn scheme_inside_or_email_atext(tokenizer: &mut Tokenizer) -> State { Some(b':') => { tokenizer.consume(); tokenizer.tokenize_state.size = 0; - State::Next(StateName::AutolinkUrlInside) + State::Next(Name::AutolinkUrlInside) } // ASCII alphanumeric and `+`, `-`, and `.`. Some(b'+' | b'-' | b'.' | b'0'..=b'9' | b'A'..=b'Z' | b'a'..=b'z') @@ -187,11 +188,11 @@ pub fn scheme_inside_or_email_atext(tokenizer: &mut Tokenizer) -> State { { tokenizer.tokenize_state.size += 1; tokenizer.consume(); - State::Next(StateName::AutolinkSchemeInsideOrEmailAtext) + State::Next(Name::AutolinkSchemeInsideOrEmailAtext) } _ => { tokenizer.tokenize_state.size = 0; - State::Retry(StateName::AutolinkEmailAtext) + State::Retry(Name::AutolinkEmailAtext) } } } @@ -216,7 +217,7 @@ pub fn url_inside(tokenizer: &mut Tokenizer) -> State { None | Some(b'\0'..=0x1F | b' ' | b'<' | 0x7F) => State::Nok, Some(_) => { tokenizer.consume(); - State::Next(StateName::AutolinkUrlInside) + State::Next(Name::AutolinkUrlInside) } } } @@ -231,7 +232,7 @@ pub fn email_atext(tokenizer: &mut Tokenizer) -> State { match tokenizer.current { Some(b'@') => { tokenizer.consume(); - State::Next(StateName::AutolinkEmailAtSignOrDot) + State::Next(Name::AutolinkEmailAtSignOrDot) } // ASCII atext. // @@ -254,7 +255,7 @@ pub fn email_atext(tokenizer: &mut Tokenizer) -> State { b'#'..=b'\'' | b'*' | b'+' | b'-'..=b'9' | b'=' | b'?' | b'A'..=b'Z' | b'^'..=b'~', ) => { tokenizer.consume(); - State::Next(StateName::AutolinkEmailAtext) + State::Next(Name::AutolinkEmailAtext) } _ => State::Nok, } @@ -269,9 +270,7 @@ pub fn email_atext(tokenizer: &mut Tokenizer) -> State { pub fn email_at_sign_or_dot(tokenizer: &mut Tokenizer) -> State { match tokenizer.current { // ASCII alphanumeric. - Some(b'0'..=b'9' | b'A'..=b'Z' | b'a'..=b'z') => { - State::Retry(StateName::AutolinkEmailValue) - } + Some(b'0'..=b'9' | b'A'..=b'Z' | b'a'..=b'z') => State::Retry(Name::AutolinkEmailValue), _ => State::Nok, } } @@ -287,7 +286,7 @@ pub fn email_label(tokenizer: &mut Tokenizer) -> State { Some(b'.') => { tokenizer.tokenize_state.size = 0; tokenizer.consume(); - State::Next(StateName::AutolinkEmailAtSignOrDot) + State::Next(Name::AutolinkEmailAtSignOrDot) } Some(b'>') => { tokenizer.tokenize_state.size = 0; @@ -302,7 +301,7 @@ pub fn email_label(tokenizer: &mut Tokenizer) -> State { tokenizer.exit(Token::Autolink); State::Ok } - _ => State::Retry(StateName::AutolinkEmailValue), + _ => State::Retry(Name::AutolinkEmailValue), } } @@ -321,9 +320,9 @@ pub fn email_value(tokenizer: &mut Tokenizer) -> State { if tokenizer.tokenize_state.size < AUTOLINK_DOMAIN_SIZE_MAX => { let name = if matches!(tokenizer.current, Some(b'-')) { - StateName::AutolinkEmailValue + Name::AutolinkEmailValue } else { - StateName::AutolinkEmailLabel + Name::AutolinkEmailLabel }; tokenizer.tokenize_state.size += 1; tokenizer.consume(); diff --git a/src/construct/blank_line.rs b/src/construct/blank_line.rs index d7d4817..e8a06e9 100644 --- a/src/construct/blank_line.rs +++ b/src/construct/blank_line.rs @@ -33,7 +33,8 @@ //! [flow]: crate::content::flow use crate::construct::partial_space_or_tab::space_or_tab; -use crate::tokenizer::{State, StateName, Tokenizer}; +use crate::state::{Name, State}; +use crate::tokenizer::Tokenizer; /// Start of a blank line. /// @@ -49,8 +50,8 @@ pub fn start(tokenizer: &mut Tokenizer) -> State { let name = space_or_tab(tokenizer); tokenizer.attempt( name, - State::Next(StateName::BlankLineAfter), - State::Next(StateName::BlankLineAfter), + State::Next(Name::BlankLineAfter), + State::Next(Name::BlankLineAfter), ) } diff --git a/src/construct/block_quote.rs b/src/construct/block_quote.rs index bbfad5b..7b8ce82 100644 --- a/src/construct/block_quote.rs +++ b/src/construct/block_quote.rs @@ -35,8 +35,9 @@ use crate::constant::TAB_SIZE; use crate::construct::partial_space_or_tab::space_or_tab_min_max; +use crate::state::{Name, State}; use crate::token::Token; -use crate::tokenizer::{State, StateName, Tokenizer}; +use crate::tokenizer::Tokenizer; /// Start of block quote. /// @@ -55,7 +56,7 @@ pub fn start(tokenizer: &mut Tokenizer) -> State { usize::MAX }, ); - tokenizer.attempt(name, State::Next(StateName::BlockQuoteBefore), State::Nok) + tokenizer.attempt(name, State::Next(Name::BlockQuoteBefore), State::Nok) } else { State::Nok } @@ -71,9 +72,9 @@ pub fn before(tokenizer: &mut Tokenizer) -> State { match tokenizer.current { Some(b'>') => { tokenizer.enter(Token::BlockQuote); - State::Retry(StateName::BlockQuoteContBefore) + State::Retry(Name::BlockQuoteContBefore) } - _ => State::Retry(StateName::BlockQuoteContBefore), + _ => State::Retry(Name::BlockQuoteContBefore), } } @@ -94,11 +95,7 @@ pub fn cont_start(tokenizer: &mut Tokenizer) -> State { usize::MAX }, ); - tokenizer.attempt( - name, - State::Next(StateName::BlockQuoteContBefore), - State::Nok, - ) + tokenizer.attempt(name, State::Next(Name::BlockQuoteContBefore), State::Nok) } /// After whitespace, before `>`. @@ -115,7 +112,7 @@ pub fn cont_before(tokenizer: &mut Tokenizer) -> State { tokenizer.enter(Token::BlockQuoteMarker); tokenizer.consume(); tokenizer.exit(Token::BlockQuoteMarker); - State::Next(StateName::BlockQuoteContAfter) + State::Next(Name::BlockQuoteContAfter) } _ => State::Nok, } diff --git a/src/construct/character_escape.rs b/src/construct/character_escape.rs index 52b2873..c3d5458 100644 --- a/src/construct/character_escape.rs +++ b/src/construct/character_escape.rs @@ -33,8 +33,9 @@ //! [character_reference]: crate::construct::character_reference //! [hard_break_escape]: crate::construct::hard_break_escape +use crate::state::{Name, State}; use crate::token::Token; -use crate::tokenizer::{State, StateName, Tokenizer}; +use crate::tokenizer::Tokenizer; /// Start of a character escape. /// @@ -49,7 +50,7 @@ pub fn start(tokenizer: &mut Tokenizer) -> State { tokenizer.enter(Token::CharacterEscapeMarker); tokenizer.consume(); tokenizer.exit(Token::CharacterEscapeMarker); - State::Next(StateName::CharacterEscapeInside) + State::Next(Name::CharacterEscapeInside) } _ => State::Nok, } @@ -61,7 +62,7 @@ pub fn start(tokenizer: &mut Tokenizer) -> State { /// > | a\*b /// ^ /// ``` -// StateName::CharacterEscapeInside +// Name::CharacterEscapeInside pub fn inside(tokenizer: &mut Tokenizer) -> State { match tokenizer.current { // ASCII punctuation. diff --git a/src/construct/character_reference.rs b/src/construct/character_reference.rs index e1c7e79..435c115 100644 --- a/src/construct/character_reference.rs +++ b/src/construct/character_reference.rs @@ -65,8 +65,9 @@ use crate::constant::{ CHARACTER_REFERENCES, CHARACTER_REFERENCE_DECIMAL_SIZE_MAX, CHARACTER_REFERENCE_HEXADECIMAL_SIZE_MAX, CHARACTER_REFERENCE_NAMED_SIZE_MAX, }; +use crate::state::{Name, State}; use crate::token::Token; -use crate::tokenizer::{State, StateName, Tokenizer}; +use crate::tokenizer::Tokenizer; use crate::util::slice::Slice; /// Start of a character reference. @@ -86,7 +87,7 @@ pub fn start(tokenizer: &mut Tokenizer) -> State { tokenizer.enter(Token::CharacterReferenceMarker); tokenizer.consume(); tokenizer.exit(Token::CharacterReferenceMarker); - State::Next(StateName::CharacterReferenceOpen) + State::Next(Name::CharacterReferenceOpen) } _ => State::Nok, } @@ -103,17 +104,17 @@ pub fn start(tokenizer: &mut Tokenizer) -> State { /// > | a	b /// ^ /// ``` -// StateName::CharacterReferenceOpen +// Name::CharacterReferenceOpen pub fn open(tokenizer: &mut Tokenizer) -> State { if let Some(b'#') = tokenizer.current { tokenizer.enter(Token::CharacterReferenceMarkerNumeric); tokenizer.consume(); tokenizer.exit(Token::CharacterReferenceMarkerNumeric); - State::Next(StateName::CharacterReferenceNumeric) + State::Next(Name::CharacterReferenceNumeric) } else { tokenizer.tokenize_state.marker = b'&'; tokenizer.enter(Token::CharacterReferenceValue); - State::Retry(StateName::CharacterReferenceValue) + State::Retry(Name::CharacterReferenceValue) } } @@ -126,7 +127,7 @@ pub fn open(tokenizer: &mut Tokenizer) -> State { /// > | a	b /// ^ /// ``` -// StateName::CharacterReferenceNumeric +// Name::CharacterReferenceNumeric pub fn numeric(tokenizer: &mut Tokenizer) -> State { if let Some(b'x' | b'X') = tokenizer.current { tokenizer.enter(Token::CharacterReferenceMarkerHexadecimal); @@ -134,11 +135,11 @@ pub fn numeric(tokenizer: &mut Tokenizer) -> State { tokenizer.exit(Token::CharacterReferenceMarkerHexadecimal); tokenizer.enter(Token::CharacterReferenceValue); tokenizer.tokenize_state.marker = b'x'; - State::Next(StateName::CharacterReferenceValue) + State::Next(Name::CharacterReferenceValue) } else { tokenizer.enter(Token::CharacterReferenceValue); tokenizer.tokenize_state.marker = b'#'; - State::Retry(StateName::CharacterReferenceValue) + State::Retry(Name::CharacterReferenceValue) } } @@ -202,7 +203,7 @@ pub fn value(tokenizer: &mut Tokenizer) -> State { if tokenizer.tokenize_state.size < max && test(&byte) { tokenizer.tokenize_state.size += 1; tokenizer.consume(); - return State::Next(StateName::CharacterReferenceValue); + return State::Next(Name::CharacterReferenceValue); } } diff --git a/src/construct/code_fenced.rs b/src/construct/code_fenced.rs index 26e1148..0ce8d02 100644 --- a/src/construct/code_fenced.rs +++ b/src/construct/code_fenced.rs @@ -103,8 +103,9 @@ use crate::constant::{CODE_FENCED_SEQUENCE_SIZE_MIN, TAB_SIZE}; use crate::construct::partial_space_or_tab::{space_or_tab, space_or_tab_min_max}; +use crate::state::{Name, State}; use crate::token::Token; -use crate::tokenizer::{ContentType, State, StateName, Tokenizer}; +use crate::tokenizer::{ContentType, Tokenizer}; use crate::util::slice::{Position, Slice}; /// Start of fenced code. @@ -130,7 +131,7 @@ pub fn start(tokenizer: &mut Tokenizer) -> State { ); tokenizer.attempt( name, - State::Next(StateName::CodeFencedBeforeSequenceOpen), + State::Next(Name::CodeFencedBeforeSequenceOpen), State::Nok, ) } else { @@ -164,7 +165,7 @@ pub fn before_sequence_open(tokenizer: &mut Tokenizer) -> State { tokenizer.tokenize_state.marker = tokenizer.current.unwrap(); tokenizer.tokenize_state.size_c = prefix; tokenizer.enter(Token::CodeFencedFenceSequence); - State::Retry(StateName::CodeFencedSequenceOpen) + State::Retry(Name::CodeFencedSequenceOpen) } else { State::Nok } @@ -183,15 +184,15 @@ pub fn sequence_open(tokenizer: &mut Tokenizer) -> State { Some(b'`' | b'~') if tokenizer.current.unwrap() == tokenizer.tokenize_state.marker => { tokenizer.tokenize_state.size += 1; tokenizer.consume(); - State::Next(StateName::CodeFencedSequenceOpen) + State::Next(Name::CodeFencedSequenceOpen) } _ if tokenizer.tokenize_state.size >= CODE_FENCED_SEQUENCE_SIZE_MIN => { tokenizer.exit(Token::CodeFencedFenceSequence); let name = space_or_tab(tokenizer); tokenizer.attempt( name, - State::Next(StateName::CodeFencedInfoBefore), - State::Next(StateName::CodeFencedInfoBefore), + State::Next(Name::CodeFencedInfoBefore), + State::Next(Name::CodeFencedInfoBefore), ) } _ => { @@ -218,15 +219,15 @@ pub fn info_before(tokenizer: &mut Tokenizer) -> State { // Do not form containers. tokenizer.concrete = true; tokenizer.check( - StateName::NonLazyContinuationStart, - State::Next(StateName::CodeFencedAtNonLazyBreak), - State::Next(StateName::CodeFencedAfter), + Name::NonLazyContinuationStart, + State::Next(Name::CodeFencedAtNonLazyBreak), + State::Next(Name::CodeFencedAfter), ) } _ => { tokenizer.enter(Token::CodeFencedFenceInfo); tokenizer.enter_with_content(Token::Data, Some(ContentType::String)); - State::Retry(StateName::CodeFencedInfo) + State::Retry(Name::CodeFencedInfo) } } } @@ -244,7 +245,7 @@ pub fn info(tokenizer: &mut Tokenizer) -> State { None | Some(b'\n') => { tokenizer.exit(Token::Data); tokenizer.exit(Token::CodeFencedFenceInfo); - State::Retry(StateName::CodeFencedInfoBefore) + State::Retry(Name::CodeFencedInfoBefore) } Some(b'\t' | b' ') => { tokenizer.exit(Token::Data); @@ -252,8 +253,8 @@ pub fn info(tokenizer: &mut Tokenizer) -> State { let name = space_or_tab(tokenizer); tokenizer.attempt( name, - State::Next(StateName::CodeFencedMetaBefore), - State::Next(StateName::CodeFencedMetaBefore), + State::Next(Name::CodeFencedMetaBefore), + State::Next(Name::CodeFencedMetaBefore), ) } Some(b'`') if tokenizer.tokenize_state.marker == b'`' => { @@ -265,7 +266,7 @@ pub fn info(tokenizer: &mut Tokenizer) -> State { } Some(_) => { tokenizer.consume(); - State::Next(StateName::CodeFencedInfo) + State::Next(Name::CodeFencedInfo) } } } @@ -280,11 +281,11 @@ pub fn info(tokenizer: &mut Tokenizer) -> State { /// ``` pub fn meta_before(tokenizer: &mut Tokenizer) -> State { match tokenizer.current { - None | Some(b'\n') => State::Retry(StateName::CodeFencedInfoBefore), + None | Some(b'\n') => State::Retry(Name::CodeFencedInfoBefore), _ => { tokenizer.enter(Token::CodeFencedFenceMeta); tokenizer.enter_with_content(Token::Data, Some(ContentType::String)); - State::Retry(StateName::CodeFencedMeta) + State::Retry(Name::CodeFencedMeta) } } } @@ -302,7 +303,7 @@ pub fn meta(tokenizer: &mut Tokenizer) -> State { None | Some(b'\n') => { tokenizer.exit(Token::Data); tokenizer.exit(Token::CodeFencedFenceMeta); - State::Retry(StateName::CodeFencedInfoBefore) + State::Retry(Name::CodeFencedInfoBefore) } Some(b'`') if tokenizer.tokenize_state.marker == b'`' => { tokenizer.concrete = false; @@ -313,7 +314,7 @@ pub fn meta(tokenizer: &mut Tokenizer) -> State { } _ => { tokenizer.consume(); - State::Next(StateName::CodeFencedMeta) + State::Next(Name::CodeFencedMeta) } } } @@ -329,9 +330,9 @@ pub fn meta(tokenizer: &mut Tokenizer) -> State { /// ``` pub fn at_non_lazy_break(tokenizer: &mut Tokenizer) -> State { tokenizer.attempt( - StateName::CodeFencedCloseBefore, - State::Next(StateName::CodeFencedAfter), - State::Next(StateName::CodeFencedContentBefore), + Name::CodeFencedCloseBefore, + State::Next(Name::CodeFencedAfter), + State::Next(Name::CodeFencedContentBefore), ) } @@ -349,7 +350,7 @@ pub fn close_before(tokenizer: &mut Tokenizer) -> State { tokenizer.enter(Token::LineEnding); tokenizer.consume(); tokenizer.exit(Token::LineEnding); - State::Next(StateName::CodeFencedCloseStart) + State::Next(Name::CodeFencedCloseStart) } _ => unreachable!("expected eol"), } @@ -376,7 +377,7 @@ pub fn close_start(tokenizer: &mut Tokenizer) -> State { ); tokenizer.attempt( name, - State::Next(StateName::CodeFencedBeforeSequenceClose), + State::Next(Name::CodeFencedBeforeSequenceClose), State::Nok, ) } @@ -393,7 +394,7 @@ pub fn before_sequence_close(tokenizer: &mut Tokenizer) -> State { match tokenizer.current { Some(b'`' | b'~') if tokenizer.current.unwrap() == tokenizer.tokenize_state.marker => { tokenizer.enter(Token::CodeFencedFenceSequence); - State::Retry(StateName::CodeFencedSequenceClose) + State::Retry(Name::CodeFencedSequenceClose) } _ => State::Nok, } @@ -412,7 +413,7 @@ pub fn sequence_close(tokenizer: &mut Tokenizer) -> State { Some(b'`' | b'~') if tokenizer.current.unwrap() == tokenizer.tokenize_state.marker => { tokenizer.tokenize_state.size_b += 1; tokenizer.consume(); - State::Next(StateName::CodeFencedSequenceClose) + State::Next(Name::CodeFencedSequenceClose) } _ if tokenizer.tokenize_state.size_b >= CODE_FENCED_SEQUENCE_SIZE_MIN && tokenizer.tokenize_state.size_b >= tokenizer.tokenize_state.size => @@ -422,8 +423,8 @@ pub fn sequence_close(tokenizer: &mut Tokenizer) -> State { let name = space_or_tab(tokenizer); tokenizer.attempt( name, - State::Next(StateName::CodeFencedAfterSequenceClose), - State::Next(StateName::CodeFencedAfterSequenceClose), + State::Next(Name::CodeFencedAfterSequenceClose), + State::Next(Name::CodeFencedAfterSequenceClose), ) } _ => { @@ -463,7 +464,7 @@ pub fn content_before(tokenizer: &mut Tokenizer) -> State { tokenizer.enter(Token::LineEnding); tokenizer.consume(); tokenizer.exit(Token::LineEnding); - State::Next(StateName::CodeFencedContentStart) + State::Next(Name::CodeFencedContentStart) } /// Before code content, definitely not before a closing fence. /// @@ -477,7 +478,7 @@ pub fn content_start(tokenizer: &mut Tokenizer) -> State { let name = space_or_tab_min_max(tokenizer, 0, tokenizer.tokenize_state.size_c); tokenizer.attempt( name, - State::Next(StateName::CodeFencedBeforeContentChunk), + State::Next(Name::CodeFencedBeforeContentChunk), State::Nok, ) } @@ -493,13 +494,13 @@ pub fn content_start(tokenizer: &mut Tokenizer) -> State { pub fn before_content_chunk(tokenizer: &mut Tokenizer) -> State { match tokenizer.current { None | Some(b'\n') => tokenizer.check( - StateName::NonLazyContinuationStart, - State::Next(StateName::CodeFencedAtNonLazyBreak), - State::Next(StateName::CodeFencedAfter), + Name::NonLazyContinuationStart, + State::Next(Name::CodeFencedAtNonLazyBreak), + State::Next(Name::CodeFencedAfter), ), _ => { tokenizer.enter(Token::CodeFlowChunk); - State::Retry(StateName::CodeFencedContentChunk) + State::Retry(Name::CodeFencedContentChunk) } } } @@ -516,11 +517,11 @@ pub fn content_chunk(tokenizer: &mut Tokenizer) -> State { match tokenizer.current { None | Some(b'\n') => { tokenizer.exit(Token::CodeFlowChunk); - State::Retry(StateName::CodeFencedBeforeContentChunk) + State::Retry(Name::CodeFencedBeforeContentChunk) } _ => { tokenizer.consume(); - State::Next(StateName::CodeFencedContentChunk) + State::Next(Name::CodeFencedContentChunk) } } } diff --git a/src/construct/code_indented.rs b/src/construct/code_indented.rs index 36ae4c6..f442f27 100644 --- a/src/construct/code_indented.rs +++ b/src/construct/code_indented.rs @@ -47,8 +47,9 @@ use super::partial_space_or_tab::{space_or_tab, space_or_tab_min_max}; use crate::constant::TAB_SIZE; +use crate::state::{Name, State}; use crate::token::Token; -use crate::tokenizer::{State, StateName, Tokenizer}; +use crate::tokenizer::Tokenizer; /// Start of code (indented). /// @@ -65,11 +66,7 @@ pub fn start(tokenizer: &mut Tokenizer) -> State { if !tokenizer.interrupt && tokenizer.parse_state.constructs.code_indented { tokenizer.enter(Token::CodeIndented); let name = space_or_tab_min_max(tokenizer, TAB_SIZE, TAB_SIZE); - tokenizer.attempt( - name, - State::Next(StateName::CodeIndentedAtBreak), - State::Nok, - ) + tokenizer.attempt(name, State::Next(Name::CodeIndentedAtBreak), State::Nok) } else { State::Nok } @@ -83,15 +80,15 @@ pub fn start(tokenizer: &mut Tokenizer) -> State { /// ``` pub fn at_break(tokenizer: &mut Tokenizer) -> State { match tokenizer.current { - None => State::Retry(StateName::CodeIndentedAfter), + None => State::Retry(Name::CodeIndentedAfter), Some(b'\n') => tokenizer.attempt( - StateName::CodeIndentedFurtherStart, - State::Next(StateName::CodeIndentedAtBreak), - State::Next(StateName::CodeIndentedAfter), + Name::CodeIndentedFurtherStart, + State::Next(Name::CodeIndentedAtBreak), + State::Next(Name::CodeIndentedAfter), ), _ => { tokenizer.enter(Token::CodeFlowChunk); - State::Retry(StateName::CodeIndentedInside) + State::Retry(Name::CodeIndentedInside) } } } @@ -106,11 +103,11 @@ pub fn inside(tokenizer: &mut Tokenizer) -> State { match tokenizer.current { None | Some(b'\n') => { tokenizer.exit(Token::CodeFlowChunk); - State::Retry(StateName::CodeIndentedAtBreak) + State::Retry(Name::CodeIndentedAtBreak) } _ => { tokenizer.consume(); - State::Next(StateName::CodeIndentedInside) + State::Next(Name::CodeIndentedInside) } } } @@ -141,14 +138,14 @@ pub fn further_start(tokenizer: &mut Tokenizer) -> State { tokenizer.enter(Token::LineEnding); tokenizer.consume(); tokenizer.exit(Token::LineEnding); - State::Next(StateName::CodeIndentedFurtherStart) + State::Next(Name::CodeIndentedFurtherStart) } _ if !tokenizer.lazy => { let name = space_or_tab_min_max(tokenizer, TAB_SIZE, TAB_SIZE); tokenizer.attempt( name, - State::Next(StateName::CodeIndentedFurtherEnd), - State::Next(StateName::CodeIndentedFurtherBegin), + State::Next(Name::CodeIndentedFurtherEnd), + State::Next(Name::CodeIndentedFurtherBegin), ) } _ => State::Nok, @@ -177,8 +174,8 @@ pub fn further_begin(tokenizer: &mut Tokenizer) -> State { let name = space_or_tab(tokenizer); tokenizer.attempt( name, - State::Next(StateName::CodeIndentedFurtherAfter), - State::Next(StateName::CodeIndentedFurtherAfter), + State::Next(Name::CodeIndentedFurtherAfter), + State::Next(Name::CodeIndentedFurtherAfter), ) } @@ -191,7 +188,7 @@ pub fn further_begin(tokenizer: &mut Tokenizer) -> State { /// ``` pub fn further_after(tokenizer: &mut Tokenizer) -> State { match tokenizer.current { - Some(b'\n') => State::Retry(StateName::CodeIndentedFurtherStart), + Some(b'\n') => State::Retry(Name::CodeIndentedFurtherStart), _ => State::Nok, } } diff --git a/src/construct/code_text.rs b/src/construct/code_text.rs index d7ada3d..f626cfb 100644 --- a/src/construct/code_text.rs +++ b/src/construct/code_text.rs @@ -83,8 +83,9 @@ //! [code_fenced]: crate::construct::code_fenced //! [html-code]: https://html.spec.whatwg.org/multipage/text-level-semantics.html#the-code-element +use crate::state::{Name, State}; use crate::token::Token; -use crate::tokenizer::{State, StateName, Tokenizer}; +use crate::tokenizer::Tokenizer; /// Start of code (text). /// @@ -105,7 +106,7 @@ pub fn start(tokenizer: &mut Tokenizer) -> State { { tokenizer.enter(Token::CodeText); tokenizer.enter(Token::CodeTextSequence); - State::Retry(StateName::CodeTextSequenceOpen) + State::Retry(Name::CodeTextSequenceOpen) } _ => State::Nok, } @@ -121,10 +122,10 @@ pub fn sequence_open(tokenizer: &mut Tokenizer) -> State { if let Some(b'`') = tokenizer.current { tokenizer.tokenize_state.size += 1; tokenizer.consume(); - State::Next(StateName::CodeTextSequenceOpen) + State::Next(Name::CodeTextSequenceOpen) } else { tokenizer.exit(Token::CodeTextSequence); - State::Retry(StateName::CodeTextBetween) + State::Retry(Name::CodeTextBetween) } } @@ -144,15 +145,15 @@ pub fn between(tokenizer: &mut Tokenizer) -> State { tokenizer.enter(Token::LineEnding); tokenizer.consume(); tokenizer.exit(Token::LineEnding); - State::Next(StateName::CodeTextBetween) + State::Next(Name::CodeTextBetween) } Some(b'`') => { tokenizer.enter(Token::CodeTextSequence); - State::Retry(StateName::CodeTextSequenceClose) + State::Retry(Name::CodeTextSequenceClose) } _ => { tokenizer.enter(Token::CodeTextData); - State::Retry(StateName::CodeTextData) + State::Retry(Name::CodeTextData) } } } @@ -167,11 +168,11 @@ pub fn data(tokenizer: &mut Tokenizer) -> State { match tokenizer.current { None | Some(b'\n' | b'`') => { tokenizer.exit(Token::CodeTextData); - State::Retry(StateName::CodeTextBetween) + State::Retry(Name::CodeTextBetween) } _ => { tokenizer.consume(); - State::Next(StateName::CodeTextData) + State::Next(Name::CodeTextData) } } } @@ -187,7 +188,7 @@ pub fn sequence_close(tokenizer: &mut Tokenizer) -> State { Some(b'`') => { tokenizer.tokenize_state.size_b += 1; tokenizer.consume(); - State::Next(StateName::CodeTextSequenceClose) + State::Next(Name::CodeTextSequenceClose) } _ => { if tokenizer.tokenize_state.size == tokenizer.tokenize_state.size_b { @@ -203,7 +204,7 @@ pub fn sequence_close(tokenizer: &mut Tokenizer) -> State { tokenizer.events[index - 1].token_type = Token::CodeTextData; tokenizer.events[index].token_type = Token::CodeTextData; tokenizer.tokenize_state.size_b = 0; - State::Retry(StateName::CodeTextBetween) + State::Retry(Name::CodeTextBetween) } } } diff --git a/src/construct/definition.rs b/src/construct/definition.rs index 5db611b..394375f 100644 --- a/src/construct/definition.rs +++ b/src/construct/definition.rs @@ -94,8 +94,9 @@ //! [html-img]: https://html.spec.whatwg.org/multipage/embedded-content.html#the-img-element use crate::construct::partial_space_or_tab::{space_or_tab, space_or_tab_eol}; +use crate::state::{Name, State}; use crate::token::Token; -use crate::tokenizer::{State, StateName, Tokenizer}; +use crate::tokenizer::Tokenizer; use crate::util::skip::opt_back as skip_opt_back; /// At the start of a definition. @@ -122,8 +123,8 @@ pub fn start(tokenizer: &mut Tokenizer) -> State { let name = space_or_tab(tokenizer); tokenizer.attempt( name, - State::Next(StateName::DefinitionBefore), - State::Next(StateName::DefinitionBefore), + State::Next(Name::DefinitionBefore), + State::Next(Name::DefinitionBefore), ) } else { State::Nok @@ -143,8 +144,8 @@ pub fn before(tokenizer: &mut Tokenizer) -> State { tokenizer.tokenize_state.token_2 = Token::DefinitionLabelMarker; tokenizer.tokenize_state.token_3 = Token::DefinitionLabelString; tokenizer.attempt( - StateName::LabelStart, - State::Next(StateName::DefinitionLabelAfter), + Name::LabelStart, + State::Next(Name::DefinitionLabelAfter), State::Nok, ) } @@ -168,7 +169,7 @@ pub fn label_after(tokenizer: &mut Tokenizer) -> State { tokenizer.enter(Token::DefinitionMarker); tokenizer.consume(); tokenizer.exit(Token::DefinitionMarker); - State::Next(StateName::DefinitionMarkerAfter) + State::Next(Name::DefinitionMarkerAfter) } _ => State::Nok, } @@ -184,8 +185,8 @@ pub fn marker_after(tokenizer: &mut Tokenizer) -> State { let name = space_or_tab_eol(tokenizer); tokenizer.attempt( name, - State::Next(StateName::DefinitionDestinationBefore), - State::Next(StateName::DefinitionDestinationBefore), + State::Next(Name::DefinitionDestinationBefore), + State::Next(Name::DefinitionDestinationBefore), ) } @@ -203,9 +204,9 @@ pub fn destination_before(tokenizer: &mut Tokenizer) -> State { tokenizer.tokenize_state.token_5 = Token::DefinitionDestinationString; tokenizer.tokenize_state.size_b = usize::MAX; tokenizer.attempt( - StateName::DestinationStart, - State::Next(StateName::DefinitionDestinationAfter), - State::Next(StateName::DefinitionDestinationMissing), + Name::DestinationStart, + State::Next(Name::DefinitionDestinationAfter), + State::Next(Name::DefinitionDestinationMissing), ) } @@ -223,9 +224,9 @@ pub fn destination_after(tokenizer: &mut Tokenizer) -> State { tokenizer.tokenize_state.token_5 = Token::Data; tokenizer.tokenize_state.size_b = 0; tokenizer.attempt( - StateName::DefinitionTitleBefore, - State::Next(StateName::DefinitionAfter), - State::Next(StateName::DefinitionAfter), + Name::DefinitionTitleBefore, + State::Next(Name::DefinitionAfter), + State::Next(Name::DefinitionAfter), ) } @@ -252,8 +253,8 @@ pub fn after(tokenizer: &mut Tokenizer) -> State { let name = space_or_tab(tokenizer); tokenizer.attempt( name, - State::Next(StateName::DefinitionAfterWhitespace), - State::Next(StateName::DefinitionAfterWhitespace), + State::Next(Name::DefinitionAfterWhitespace), + State::Next(Name::DefinitionAfterWhitespace), ) } @@ -289,7 +290,7 @@ pub fn title_before(tokenizer: &mut Tokenizer) -> State { let name = space_or_tab_eol(tokenizer); tokenizer.attempt( name, - State::Next(StateName::DefinitionTitleBeforeMarker), + State::Next(Name::DefinitionTitleBeforeMarker), State::Nok, ) } @@ -306,8 +307,8 @@ pub fn title_before_marker(tokenizer: &mut Tokenizer) -> State { tokenizer.tokenize_state.token_2 = Token::DefinitionTitleMarker; tokenizer.tokenize_state.token_3 = Token::DefinitionTitleString; tokenizer.attempt( - StateName::TitleStart, - State::Next(StateName::DefinitionTitleAfter), + Name::TitleStart, + State::Next(Name::DefinitionTitleAfter), State::Nok, ) } @@ -325,8 +326,8 @@ pub fn title_after(tokenizer: &mut Tokenizer) -> State { let name = space_or_tab(tokenizer); tokenizer.attempt( name, - State::Next(StateName::DefinitionTitleAfterOptionalWhitespace), - State::Next(StateName::DefinitionTitleAfterOptionalWhitespace), + State::Next(Name::DefinitionTitleAfterOptionalWhitespace), + State::Next(Name::DefinitionTitleAfterOptionalWhitespace), ) } diff --git a/src/construct/hard_break_escape.rs b/src/construct/hard_break_escape.rs index fc2cbdf..482648f 100644 --- a/src/construct/hard_break_escape.rs +++ b/src/construct/hard_break_escape.rs @@ -39,8 +39,9 @@ //! [hard_break_trailing]: crate::construct::partial_whitespace //! [html]: https://html.spec.whatwg.org/multipage/text-level-semantics.html#the-br-element +use crate::state::{Name, State}; use crate::token::Token; -use crate::tokenizer::{State, StateName, Tokenizer}; +use crate::tokenizer::Tokenizer; /// Start of a hard break (escape). /// @@ -54,7 +55,7 @@ pub fn start(tokenizer: &mut Tokenizer) -> State { Some(b'\\') if tokenizer.parse_state.constructs.hard_break_escape => { tokenizer.enter(Token::HardBreakEscape); tokenizer.consume(); - State::Next(StateName::HardBreakEscapeAfter) + State::Next(Name::HardBreakEscapeAfter) } _ => State::Nok, } diff --git a/src/construct/heading_atx.rs b/src/construct/heading_atx.rs index d70f7db..12bc5b1 100644 --- a/src/construct/heading_atx.rs +++ b/src/construct/heading_atx.rs @@ -54,10 +54,11 @@ //! [wiki-setext]: https://en.wikipedia.org/wiki/Setext //! [atx]: http://www.aaronsw.com/2002/atx/ -use super::partial_space_or_tab::{space_or_tab, space_or_tab_min_max}; use crate::constant::{HEADING_ATX_OPENING_FENCE_SIZE_MAX, TAB_SIZE}; +use crate::construct::partial_space_or_tab::{space_or_tab, space_or_tab_min_max}; +use crate::state::{Name, State}; use crate::token::Token; -use crate::tokenizer::{ContentType, Event, EventType, State, StateName, Tokenizer}; +use crate::tokenizer::{ContentType, Event, EventType, Tokenizer}; /// Start of a heading (atx). /// @@ -77,7 +78,7 @@ pub fn start(tokenizer: &mut Tokenizer) -> State { usize::MAX }, ); - tokenizer.attempt(name, State::Next(StateName::HeadingAtxBefore), State::Nok) + tokenizer.attempt(name, State::Next(Name::HeadingAtxBefore), State::Nok) } else { State::Nok } @@ -92,7 +93,7 @@ pub fn start(tokenizer: &mut Tokenizer) -> State { pub fn before(tokenizer: &mut Tokenizer) -> State { if Some(b'#') == tokenizer.current { tokenizer.enter(Token::HeadingAtxSequence); - State::Retry(StateName::HeadingAtxSequenceOpen) + State::Retry(Name::HeadingAtxSequenceOpen) } else { State::Nok } @@ -109,18 +110,18 @@ pub fn sequence_open(tokenizer: &mut Tokenizer) -> State { None | Some(b'\n') if tokenizer.tokenize_state.size > 0 => { tokenizer.tokenize_state.size = 0; tokenizer.exit(Token::HeadingAtxSequence); - State::Retry(StateName::HeadingAtxAtBreak) + State::Retry(Name::HeadingAtxAtBreak) } Some(b'#') if tokenizer.tokenize_state.size < HEADING_ATX_OPENING_FENCE_SIZE_MAX => { tokenizer.tokenize_state.size += 1; tokenizer.consume(); - State::Next(StateName::HeadingAtxSequenceOpen) + State::Next(Name::HeadingAtxSequenceOpen) } _ if tokenizer.tokenize_state.size > 0 => { tokenizer.tokenize_state.size = 0; tokenizer.exit(Token::HeadingAtxSequence); let name = space_or_tab(tokenizer); - tokenizer.attempt(name, State::Next(StateName::HeadingAtxAtBreak), State::Nok) + tokenizer.attempt(name, State::Next(Name::HeadingAtxAtBreak), State::Nok) } _ => { tokenizer.tokenize_state.size = 0; @@ -146,15 +147,15 @@ pub fn at_break(tokenizer: &mut Tokenizer) -> State { } Some(b'\t' | b' ') => { let name = space_or_tab(tokenizer); - tokenizer.attempt(name, State::Next(StateName::HeadingAtxAtBreak), State::Nok) + tokenizer.attempt(name, State::Next(Name::HeadingAtxAtBreak), State::Nok) } Some(b'#') => { tokenizer.enter(Token::HeadingAtxSequence); - State::Retry(StateName::HeadingAtxSequenceFurther) + State::Retry(Name::HeadingAtxSequenceFurther) } Some(_) => { tokenizer.enter_with_content(Token::Data, Some(ContentType::Text)); - State::Retry(StateName::HeadingAtxData) + State::Retry(Name::HeadingAtxData) } } } @@ -170,10 +171,10 @@ pub fn at_break(tokenizer: &mut Tokenizer) -> State { pub fn sequence_further(tokenizer: &mut Tokenizer) -> State { if let Some(b'#') = tokenizer.current { tokenizer.consume(); - State::Next(StateName::HeadingAtxSequenceFurther) + State::Next(Name::HeadingAtxSequenceFurther) } else { tokenizer.exit(Token::HeadingAtxSequence); - State::Retry(StateName::HeadingAtxAtBreak) + State::Retry(Name::HeadingAtxAtBreak) } } @@ -188,11 +189,11 @@ pub fn data(tokenizer: &mut Tokenizer) -> State { // Note: `#` for closing sequence must be preceded by whitespace, otherwise it’s just text. None | Some(b'\t' | b'\n' | b' ') => { tokenizer.exit(Token::Data); - State::Retry(StateName::HeadingAtxAtBreak) + State::Retry(Name::HeadingAtxAtBreak) } _ => { tokenizer.consume(); - State::Next(StateName::HeadingAtxData) + State::Next(Name::HeadingAtxData) } } } diff --git a/src/construct/heading_setext.rs b/src/construct/heading_setext.rs index f653d75..8b45fff 100644 --- a/src/construct/heading_setext.rs +++ b/src/construct/heading_setext.rs @@ -59,8 +59,9 @@ use crate::constant::TAB_SIZE; use crate::construct::partial_space_or_tab::{space_or_tab, space_or_tab_min_max}; +use crate::state::{Name, State}; use crate::token::Token; -use crate::tokenizer::{EventType, State, StateName, Tokenizer}; +use crate::tokenizer::{EventType, Tokenizer}; use crate::util::skip::opt_back as skip_opt_back; /// At a line ending, presumably an underline. @@ -93,11 +94,7 @@ pub fn start(tokenizer: &mut Tokenizer) -> State { }, ); - tokenizer.attempt( - name, - State::Next(StateName::HeadingSetextBefore), - State::Nok, - ) + tokenizer.attempt(name, State::Next(Name::HeadingSetextBefore), State::Nok) } else { State::Nok } @@ -115,7 +112,7 @@ pub fn before(tokenizer: &mut Tokenizer) -> State { Some(b'-' | b'=') => { tokenizer.tokenize_state.marker = tokenizer.current.unwrap(); tokenizer.enter(Token::HeadingSetextUnderline); - State::Retry(StateName::HeadingSetextInside) + State::Retry(Name::HeadingSetextInside) } _ => State::Nok, } @@ -132,7 +129,7 @@ pub fn inside(tokenizer: &mut Tokenizer) -> State { match tokenizer.current { Some(b'-' | b'=') if tokenizer.current.unwrap() == tokenizer.tokenize_state.marker => { tokenizer.consume(); - State::Next(StateName::HeadingSetextInside) + State::Next(Name::HeadingSetextInside) } _ => { tokenizer.tokenize_state.marker = 0; @@ -140,8 +137,8 @@ pub fn inside(tokenizer: &mut Tokenizer) -> State { let name = space_or_tab(tokenizer); tokenizer.attempt( name, - State::Next(StateName::HeadingSetextAfter), - State::Next(StateName::HeadingSetextAfter), + State::Next(Name::HeadingSetextAfter), + State::Next(Name::HeadingSetextAfter), ) } } diff --git a/src/construct/html_flow.rs b/src/construct/html_flow.rs index 7a346e9..c9f8610 100644 --- a/src/construct/html_flow.rs +++ b/src/construct/html_flow.rs @@ -104,8 +104,9 @@ use crate::constant::{ use crate::construct::partial_space_or_tab::{ space_or_tab_with_options, Options as SpaceOrTabOptions, }; +use crate::state::{Name, State}; use crate::token::Token; -use crate::tokenizer::{State, StateName, Tokenizer}; +use crate::tokenizer::Tokenizer; use crate::util::slice::Slice; /// Symbol for `<script>` (condition 1). @@ -147,7 +148,7 @@ pub fn start(tokenizer: &mut Tokenizer) -> State { }, ); - tokenizer.attempt(name, State::Next(StateName::HtmlFlowBefore), State::Nok) + tokenizer.attempt(name, State::Next(Name::HtmlFlowBefore), State::Nok) } else { State::Nok } @@ -163,7 +164,7 @@ pub fn before(tokenizer: &mut Tokenizer) -> State { if Some(b'<') == tokenizer.current { tokenizer.enter(Token::HtmlFlowData); tokenizer.consume(); - State::Next(StateName::HtmlFlowOpen) + State::Next(Name::HtmlFlowOpen) } else { State::Nok } @@ -183,13 +184,13 @@ pub fn open(tokenizer: &mut Tokenizer) -> State { match tokenizer.current { Some(b'!') => { tokenizer.consume(); - State::Next(StateName::HtmlFlowDeclarationOpen) + State::Next(Name::HtmlFlowDeclarationOpen) } Some(b'/') => { tokenizer.consume(); tokenizer.tokenize_state.seen = true; tokenizer.tokenize_state.start = tokenizer.point.index; - State::Next(StateName::HtmlFlowTagCloseStart) + State::Next(Name::HtmlFlowTagCloseStart) } Some(b'?') => { tokenizer.tokenize_state.marker = INSTRUCTION; @@ -198,12 +199,12 @@ pub fn open(tokenizer: &mut Tokenizer) -> State { tokenizer.concrete = true; // While we’re in an instruction instead of a declaration, we’re on a `?` // right now, so we do need to search for `>`, similar to declarations. - State::Next(StateName::HtmlFlowContinuationDeclarationInside) + State::Next(Name::HtmlFlowContinuationDeclarationInside) } // ASCII alphabetical. Some(b'A'..=b'Z' | b'a'..=b'z') => { tokenizer.tokenize_state.start = tokenizer.point.index; - State::Retry(StateName::HtmlFlowTagName) + State::Retry(Name::HtmlFlowTagName) } _ => State::Nok, } @@ -224,19 +225,19 @@ pub fn declaration_open(tokenizer: &mut Tokenizer) -> State { Some(b'-') => { tokenizer.consume(); tokenizer.tokenize_state.marker = COMMENT; - State::Next(StateName::HtmlFlowCommentOpenInside) + State::Next(Name::HtmlFlowCommentOpenInside) } Some(b'A'..=b'Z' | b'a'..=b'z') => { tokenizer.consume(); tokenizer.tokenize_state.marker = DECLARATION; // Do not form containers. tokenizer.concrete = true; - State::Next(StateName::HtmlFlowContinuationDeclarationInside) + State::Next(Name::HtmlFlowContinuationDeclarationInside) } Some(b'[') => { tokenizer.consume(); tokenizer.tokenize_state.marker = CDATA; - State::Next(StateName::HtmlFlowCdataOpenInside) + State::Next(Name::HtmlFlowCdataOpenInside) } _ => State::Nok, } @@ -253,7 +254,7 @@ pub fn comment_open_inside(tokenizer: &mut Tokenizer) -> State { tokenizer.consume(); // Do not form containers. tokenizer.concrete = true; - State::Next(StateName::HtmlFlowContinuationDeclarationInside) + State::Next(Name::HtmlFlowContinuationDeclarationInside) } else { tokenizer.tokenize_state.marker = 0; State::Nok @@ -275,9 +276,9 @@ pub fn cdata_open_inside(tokenizer: &mut Tokenizer) -> State { tokenizer.tokenize_state.size = 0; // Do not form containers. tokenizer.concrete = true; - State::Next(StateName::HtmlFlowContinuation) + State::Next(Name::HtmlFlowContinuation) } else { - State::Next(StateName::HtmlFlowCdataOpenInside) + State::Next(Name::HtmlFlowCdataOpenInside) } } else { tokenizer.tokenize_state.marker = 0; @@ -295,7 +296,7 @@ pub fn cdata_open_inside(tokenizer: &mut Tokenizer) -> State { pub fn tag_close_start(tokenizer: &mut Tokenizer) -> State { if let Some(b'A'..=b'Z' | b'a'..=b'z') = tokenizer.current { tokenizer.consume(); - State::Next(StateName::HtmlFlowTagName) + State::Next(Name::HtmlFlowTagName) } else { tokenizer.tokenize_state.seen = false; tokenizer.tokenize_state.start = 0; @@ -334,17 +335,17 @@ pub fn tag_name(tokenizer: &mut Tokenizer) -> State { tokenizer.tokenize_state.marker = RAW; // Do not form containers. tokenizer.concrete = true; - State::Retry(StateName::HtmlFlowContinuation) + State::Retry(Name::HtmlFlowContinuation) } else if HTML_BLOCK_NAMES.contains(&name.as_str()) { tokenizer.tokenize_state.marker = BASIC; if slash { tokenizer.consume(); - State::Next(StateName::HtmlFlowBasicSelfClosing) + State::Next(Name::HtmlFlowBasicSelfClosing) } else { // Do not form containers. tokenizer.concrete = true; - State::Retry(StateName::HtmlFlowContinuation) + State::Retry(Name::HtmlFlowContinuation) } } else { tokenizer.tokenize_state.marker = COMPLETE; @@ -354,16 +355,16 @@ pub fn tag_name(tokenizer: &mut Tokenizer) -> State { tokenizer.tokenize_state.marker = 0; State::Nok } else if closing_tag { - State::Retry(StateName::HtmlFlowCompleteClosingTagAfter) + State::Retry(Name::HtmlFlowCompleteClosingTagAfter) } else { - State::Retry(StateName::HtmlFlowCompleteAttributeNameBefore) + State::Retry(Name::HtmlFlowCompleteAttributeNameBefore) } } } // ASCII alphanumerical and `-`. Some(b'-' | b'0'..=b'9' | b'A'..=b'Z' | b'a'..=b'z') => { tokenizer.consume(); - State::Next(StateName::HtmlFlowTagName) + State::Next(Name::HtmlFlowTagName) } Some(_) => { tokenizer.tokenize_state.seen = false; @@ -383,7 +384,7 @@ pub fn basic_self_closing(tokenizer: &mut Tokenizer) -> State { tokenizer.consume(); // Do not form containers. tokenizer.concrete = true; - State::Next(StateName::HtmlFlowContinuation) + State::Next(Name::HtmlFlowContinuation) } else { tokenizer.tokenize_state.marker = 0; State::Nok @@ -400,9 +401,9 @@ pub fn complete_closing_tag_after(tokenizer: &mut Tokenizer) -> State { match tokenizer.current { Some(b'\t' | b' ') => { tokenizer.consume(); - State::Next(StateName::HtmlFlowCompleteClosingTagAfter) + State::Next(Name::HtmlFlowCompleteClosingTagAfter) } - _ => State::Retry(StateName::HtmlFlowCompleteEnd), + _ => State::Retry(Name::HtmlFlowCompleteEnd), } } @@ -429,18 +430,18 @@ pub fn complete_attribute_name_before(tokenizer: &mut Tokenizer) -> State { match tokenizer.current { Some(b'\t' | b' ') => { tokenizer.consume(); - State::Next(StateName::HtmlFlowCompleteAttributeNameBefore) + State::Next(Name::HtmlFlowCompleteAttributeNameBefore) } Some(b'/') => { tokenizer.consume(); - State::Next(StateName::HtmlFlowCompleteEnd) + State::Next(Name::HtmlFlowCompleteEnd) } // ASCII alphanumerical and `:` and `_`. Some(b'0'..=b'9' | b':' | b'A'..=b'Z' | b'_' | b'a'..=b'z') => { tokenizer.consume(); - State::Next(StateName::HtmlFlowCompleteAttributeName) + State::Next(Name::HtmlFlowCompleteAttributeName) } - _ => State::Retry(StateName::HtmlFlowCompleteEnd), + _ => State::Retry(Name::HtmlFlowCompleteEnd), } } @@ -459,9 +460,9 @@ pub fn complete_attribute_name(tokenizer: &mut Tokenizer) -> State { // ASCII alphanumerical and `-`, `.`, `:`, and `_`. Some(b'-' | b'.' | b'0'..=b'9' | b':' | b'A'..=b'Z' | b'_' | b'a'..=b'z') => { tokenizer.consume(); - State::Next(StateName::HtmlFlowCompleteAttributeName) + State::Next(Name::HtmlFlowCompleteAttributeName) } - _ => State::Retry(StateName::HtmlFlowCompleteAttributeNameAfter), + _ => State::Retry(Name::HtmlFlowCompleteAttributeNameAfter), } } @@ -478,13 +479,13 @@ pub fn complete_attribute_name_after(tokenizer: &mut Tokenizer) -> State { match tokenizer.current { Some(b'\t' | b' ') => { tokenizer.consume(); - State::Next(StateName::HtmlFlowCompleteAttributeNameAfter) + State::Next(Name::HtmlFlowCompleteAttributeNameAfter) } Some(b'=') => { tokenizer.consume(); - State::Next(StateName::HtmlFlowCompleteAttributeValueBefore) + State::Next(Name::HtmlFlowCompleteAttributeValueBefore) } - _ => State::Retry(StateName::HtmlFlowCompleteAttributeNameBefore), + _ => State::Retry(Name::HtmlFlowCompleteAttributeNameBefore), } } @@ -505,14 +506,14 @@ pub fn complete_attribute_value_before(tokenizer: &mut Tokenizer) -> State { } Some(b'\t' | b' ') => { tokenizer.consume(); - State::Next(StateName::HtmlFlowCompleteAttributeValueBefore) + State::Next(Name::HtmlFlowCompleteAttributeValueBefore) } Some(b'"' | b'\'') => { tokenizer.tokenize_state.marker_b = tokenizer.current.unwrap(); tokenizer.consume(); - State::Next(StateName::HtmlFlowCompleteAttributeValueQuoted) + State::Next(Name::HtmlFlowCompleteAttributeValueQuoted) } - _ => State::Retry(StateName::HtmlFlowCompleteAttributeValueUnquoted), + _ => State::Retry(Name::HtmlFlowCompleteAttributeValueUnquoted), } } @@ -534,11 +535,11 @@ pub fn complete_attribute_value_quoted(tokenizer: &mut Tokenizer) -> State { Some(b'"' | b'\'') if tokenizer.current.unwrap() == tokenizer.tokenize_state.marker_b => { tokenizer.tokenize_state.marker_b = 0; tokenizer.consume(); - State::Next(StateName::HtmlFlowCompleteAttributeValueQuotedAfter) + State::Next(Name::HtmlFlowCompleteAttributeValueQuotedAfter) } _ => { tokenizer.consume(); - State::Next(StateName::HtmlFlowCompleteAttributeValueQuoted) + State::Next(Name::HtmlFlowCompleteAttributeValueQuoted) } } } @@ -552,11 +553,11 @@ pub fn complete_attribute_value_quoted(tokenizer: &mut Tokenizer) -> State { pub fn complete_attribute_value_unquoted(tokenizer: &mut Tokenizer) -> State { match tokenizer.current { None | Some(b'\t' | b'\n' | b' ' | b'"' | b'\'' | b'/' | b'<' | b'=' | b'>' | b'`') => { - State::Retry(StateName::HtmlFlowCompleteAttributeNameAfter) + State::Retry(Name::HtmlFlowCompleteAttributeNameAfter) } Some(_) => { tokenizer.consume(); - State::Next(StateName::HtmlFlowCompleteAttributeValueUnquoted) + State::Next(Name::HtmlFlowCompleteAttributeValueUnquoted) } } } @@ -570,7 +571,7 @@ pub fn complete_attribute_value_unquoted(tokenizer: &mut Tokenizer) -> State { /// ``` pub fn complete_attribute_value_quoted_after(tokenizer: &mut Tokenizer) -> State { if let Some(b'\t' | b' ' | b'/' | b'>') = tokenizer.current { - State::Retry(StateName::HtmlFlowCompleteAttributeNameBefore) + State::Retry(Name::HtmlFlowCompleteAttributeNameBefore) } else { tokenizer.tokenize_state.marker = 0; State::Nok @@ -586,7 +587,7 @@ pub fn complete_attribute_value_quoted_after(tokenizer: &mut Tokenizer) -> State pub fn complete_end(tokenizer: &mut Tokenizer) -> State { if let Some(b'>') = tokenizer.current { tokenizer.consume(); - State::Next(StateName::HtmlFlowCompleteAfter) + State::Next(Name::HtmlFlowCompleteAfter) } else { tokenizer.tokenize_state.marker = 0; State::Nok @@ -604,11 +605,11 @@ pub fn complete_after(tokenizer: &mut Tokenizer) -> State { None | Some(b'\n') => { // Do not form containers. tokenizer.concrete = true; - State::Retry(StateName::HtmlFlowContinuation) + State::Retry(Name::HtmlFlowContinuation) } Some(b'\t' | b' ') => { tokenizer.consume(); - State::Next(StateName::HtmlFlowCompleteAfter) + State::Next(Name::HtmlFlowCompleteAfter) } Some(_) => { tokenizer.tokenize_state.marker = 0; @@ -631,39 +632,39 @@ pub fn continuation(tokenizer: &mut Tokenizer) -> State { { tokenizer.exit(Token::HtmlFlowData); tokenizer.check( - StateName::HtmlFlowBlankLineBefore, - State::Next(StateName::HtmlFlowContinuationAfter), - State::Next(StateName::HtmlFlowContinuationStart), + Name::HtmlFlowBlankLineBefore, + State::Next(Name::HtmlFlowContinuationAfter), + State::Next(Name::HtmlFlowContinuationStart), ) } // Note: important that this is after the basic/complete case. None | Some(b'\n') => { tokenizer.exit(Token::HtmlFlowData); - State::Retry(StateName::HtmlFlowContinuationStart) + State::Retry(Name::HtmlFlowContinuationStart) } Some(b'-') if tokenizer.tokenize_state.marker == COMMENT => { tokenizer.consume(); - State::Next(StateName::HtmlFlowContinuationCommentInside) + State::Next(Name::HtmlFlowContinuationCommentInside) } Some(b'<') if tokenizer.tokenize_state.marker == RAW => { tokenizer.consume(); - State::Next(StateName::HtmlFlowContinuationRawTagOpen) + State::Next(Name::HtmlFlowContinuationRawTagOpen) } Some(b'>') if tokenizer.tokenize_state.marker == DECLARATION => { tokenizer.consume(); - State::Next(StateName::HtmlFlowContinuationClose) + State::Next(Name::HtmlFlowContinuationClose) } Some(b'?') if tokenizer.tokenize_state.marker == INSTRUCTION => { tokenizer.consume(); - State::Next(StateName::HtmlFlowContinuationDeclarationInside) + State::Next(Name::HtmlFlowContinuationDeclarationInside) } Some(b']') if tokenizer.tokenize_state.marker == CDATA => { tokenizer.consume(); - State::Next(StateName::HtmlFlowContinuationCdataInside) + State::Next(Name::HtmlFlowContinuationCdataInside) } _ => { tokenizer.consume(); - State::Next(StateName::HtmlFlowContinuation) + State::Next(Name::HtmlFlowContinuation) } } } @@ -677,9 +678,9 @@ pub fn continuation(tokenizer: &mut Tokenizer) -> State { /// ``` pub fn continuation_start(tokenizer: &mut Tokenizer) -> State { tokenizer.check( - StateName::NonLazyContinuationStart, - State::Next(StateName::HtmlFlowContinuationStartNonLazy), - State::Next(StateName::HtmlFlowContinuationAfter), + Name::NonLazyContinuationStart, + State::Next(Name::HtmlFlowContinuationStartNonLazy), + State::Next(Name::HtmlFlowContinuationAfter), ) } @@ -696,7 +697,7 @@ pub fn continuation_start_non_lazy(tokenizer: &mut Tokenizer) -> State { tokenizer.enter(Token::LineEnding); tokenizer.consume(); tokenizer.exit(Token::LineEnding); - State::Next(StateName::HtmlFlowContinuationBefore) + State::Next(Name::HtmlFlowContinuationBefore) } _ => unreachable!("expected eol"), } @@ -711,10 +712,10 @@ pub fn continuation_start_non_lazy(tokenizer: &mut Tokenizer) -> State { /// ``` pub fn continuation_before(tokenizer: &mut Tokenizer) -> State { match tokenizer.current { - None | Some(b'\n') => State::Retry(StateName::HtmlFlowContinuationStart), + None | Some(b'\n') => State::Retry(Name::HtmlFlowContinuationStart), _ => { tokenizer.enter(Token::HtmlFlowData); - State::Retry(StateName::HtmlFlowContinuation) + State::Retry(Name::HtmlFlowContinuation) } } } @@ -729,9 +730,9 @@ pub fn continuation_comment_inside(tokenizer: &mut Tokenizer) -> State { match tokenizer.current { Some(b'-') => { tokenizer.consume(); - State::Next(StateName::HtmlFlowContinuationDeclarationInside) + State::Next(Name::HtmlFlowContinuationDeclarationInside) } - _ => State::Retry(StateName::HtmlFlowContinuation), + _ => State::Retry(Name::HtmlFlowContinuation), } } @@ -746,9 +747,9 @@ pub fn continuation_raw_tag_open(tokenizer: &mut Tokenizer) -> State { Some(b'/') => { tokenizer.consume(); tokenizer.tokenize_state.start = tokenizer.point.index; - State::Next(StateName::HtmlFlowContinuationRawEndTag) + State::Next(Name::HtmlFlowContinuationRawEndTag) } - _ => State::Retry(StateName::HtmlFlowContinuation), + _ => State::Retry(Name::HtmlFlowContinuation), } } @@ -773,20 +774,20 @@ pub fn continuation_raw_end_tag(tokenizer: &mut Tokenizer) -> State { if HTML_RAW_NAMES.contains(&name.as_str()) { tokenizer.consume(); - State::Next(StateName::HtmlFlowContinuationClose) + State::Next(Name::HtmlFlowContinuationClose) } else { - State::Retry(StateName::HtmlFlowContinuation) + State::Retry(Name::HtmlFlowContinuation) } } Some(b'A'..=b'Z' | b'a'..=b'z') if tokenizer.point.index - tokenizer.tokenize_state.start < HTML_RAW_SIZE_MAX => { tokenizer.consume(); - State::Next(StateName::HtmlFlowContinuationRawEndTag) + State::Next(Name::HtmlFlowContinuationRawEndTag) } _ => { tokenizer.tokenize_state.start = 0; - State::Retry(StateName::HtmlFlowContinuation) + State::Retry(Name::HtmlFlowContinuation) } } } @@ -801,9 +802,9 @@ pub fn continuation_cdata_inside(tokenizer: &mut Tokenizer) -> State { match tokenizer.current { Some(b']') => { tokenizer.consume(); - State::Next(StateName::HtmlFlowContinuationDeclarationInside) + State::Next(Name::HtmlFlowContinuationDeclarationInside) } - _ => State::Retry(StateName::HtmlFlowContinuation), + _ => State::Retry(Name::HtmlFlowContinuation), } } @@ -825,13 +826,13 @@ pub fn continuation_declaration_inside(tokenizer: &mut Tokenizer) -> State { match tokenizer.current { Some(b'>') => { tokenizer.consume(); - State::Next(StateName::HtmlFlowContinuationClose) + State::Next(Name::HtmlFlowContinuationClose) } Some(b'-') if tokenizer.tokenize_state.marker == COMMENT => { tokenizer.consume(); - State::Next(StateName::HtmlFlowContinuationDeclarationInside) + State::Next(Name::HtmlFlowContinuationDeclarationInside) } - _ => State::Retry(StateName::HtmlFlowContinuation), + _ => State::Retry(Name::HtmlFlowContinuation), } } @@ -845,11 +846,11 @@ pub fn continuation_close(tokenizer: &mut Tokenizer) -> State { match tokenizer.current { None | Some(b'\n') => { tokenizer.exit(Token::HtmlFlowData); - State::Retry(StateName::HtmlFlowContinuationAfter) + State::Retry(Name::HtmlFlowContinuationAfter) } _ => { tokenizer.consume(); - State::Next(StateName::HtmlFlowContinuationClose) + State::Next(Name::HtmlFlowContinuationClose) } } } @@ -881,5 +882,5 @@ pub fn blank_line_before(tokenizer: &mut Tokenizer) -> State { tokenizer.enter(Token::LineEnding); tokenizer.consume(); tokenizer.exit(Token::LineEnding); - State::Next(StateName::BlankLineStart) + State::Next(Name::BlankLineStart) } diff --git a/src/construct/html_text.rs b/src/construct/html_text.rs index 7474dbf..dd14e70 100644 --- a/src/construct/html_text.rs +++ b/src/construct/html_text.rs @@ -56,8 +56,9 @@ use crate::constant::HTML_CDATA_PREFIX; use crate::construct::partial_space_or_tab::space_or_tab; +use crate::state::{Name, State}; use crate::token::Token; -use crate::tokenizer::{State, StateName, Tokenizer}; +use crate::tokenizer::Tokenizer; /// Start of HTML (text) /// @@ -70,7 +71,7 @@ pub fn start(tokenizer: &mut Tokenizer) -> State { tokenizer.enter(Token::HtmlText); tokenizer.enter(Token::HtmlTextData); tokenizer.consume(); - State::Next(StateName::HtmlTextOpen) + State::Next(Name::HtmlTextOpen) } else { State::Nok } @@ -90,20 +91,20 @@ pub fn open(tokenizer: &mut Tokenizer) -> State { match tokenizer.current { Some(b'!') => { tokenizer.consume(); - State::Next(StateName::HtmlTextDeclarationOpen) + State::Next(Name::HtmlTextDeclarationOpen) } Some(b'/') => { tokenizer.consume(); - State::Next(StateName::HtmlTextTagCloseStart) + State::Next(Name::HtmlTextTagCloseStart) } Some(b'?') => { tokenizer.consume(); - State::Next(StateName::HtmlTextInstruction) + State::Next(Name::HtmlTextInstruction) } // ASCII alphabetical. Some(b'A'..=b'Z' | b'a'..=b'z') => { tokenizer.consume(); - State::Next(StateName::HtmlTextTagOpen) + State::Next(Name::HtmlTextTagOpen) } _ => State::Nok, } @@ -123,16 +124,16 @@ pub fn declaration_open(tokenizer: &mut Tokenizer) -> State { match tokenizer.current { Some(b'-') => { tokenizer.consume(); - State::Next(StateName::HtmlTextCommentOpenInside) + State::Next(Name::HtmlTextCommentOpenInside) } // ASCII alphabetical. Some(b'A'..=b'Z' | b'a'..=b'z') => { tokenizer.consume(); - State::Next(StateName::HtmlTextDeclaration) + State::Next(Name::HtmlTextDeclaration) } Some(b'[') => { tokenizer.consume(); - State::Next(StateName::HtmlTextCdataOpenInside) + State::Next(Name::HtmlTextCdataOpenInside) } _ => State::Nok, } @@ -148,7 +149,7 @@ pub fn comment_open_inside(tokenizer: &mut Tokenizer) -> State { match tokenizer.current { Some(b'-') => { tokenizer.consume(); - State::Next(StateName::HtmlTextCommentStart) + State::Next(Name::HtmlTextCommentStart) } _ => State::Nok, } @@ -172,9 +173,9 @@ pub fn comment_start(tokenizer: &mut Tokenizer) -> State { Some(b'>') => State::Nok, Some(b'-') => { tokenizer.consume(); - State::Next(StateName::HtmlTextCommentStartDash) + State::Next(Name::HtmlTextCommentStartDash) } - _ => State::Retry(StateName::HtmlTextComment), + _ => State::Retry(Name::HtmlTextComment), } } @@ -194,7 +195,7 @@ pub fn comment_start(tokenizer: &mut Tokenizer) -> State { pub fn comment_start_dash(tokenizer: &mut Tokenizer) -> State { match tokenizer.current { Some(b'>') => State::Nok, - _ => State::Retry(StateName::HtmlTextComment), + _ => State::Retry(Name::HtmlTextComment), } } @@ -208,17 +209,17 @@ pub fn comment(tokenizer: &mut Tokenizer) -> State { match tokenizer.current { None => State::Nok, Some(b'\n') => tokenizer.attempt( - StateName::HtmlTextLineEndingBefore, - State::Next(StateName::HtmlTextComment), + Name::HtmlTextLineEndingBefore, + State::Next(Name::HtmlTextComment), State::Nok, ), Some(b'-') => { tokenizer.consume(); - State::Next(StateName::HtmlTextCommentClose) + State::Next(Name::HtmlTextCommentClose) } _ => { tokenizer.consume(); - State::Next(StateName::HtmlTextComment) + State::Next(Name::HtmlTextComment) } } } @@ -233,9 +234,9 @@ pub fn comment_close(tokenizer: &mut Tokenizer) -> State { match tokenizer.current { Some(b'-') => { tokenizer.consume(); - State::Next(StateName::HtmlTextEnd) + State::Next(Name::HtmlTextEnd) } - _ => State::Retry(StateName::HtmlTextComment), + _ => State::Retry(Name::HtmlTextComment), } } @@ -252,9 +253,9 @@ pub fn cdata_open_inside(tokenizer: &mut Tokenizer) -> State { if tokenizer.tokenize_state.size == HTML_CDATA_PREFIX.len() { tokenizer.tokenize_state.size = 0; - State::Next(StateName::HtmlTextCdata) + State::Next(Name::HtmlTextCdata) } else { - State::Next(StateName::HtmlTextCdataOpenInside) + State::Next(Name::HtmlTextCdataOpenInside) } } else { State::Nok @@ -271,17 +272,17 @@ pub fn cdata(tokenizer: &mut Tokenizer) -> State { match tokenizer.current { None => State::Nok, Some(b'\n') => tokenizer.attempt( - StateName::HtmlTextLineEndingBefore, - State::Next(StateName::HtmlTextCdata), + Name::HtmlTextLineEndingBefore, + State::Next(Name::HtmlTextCdata), State::Nok, ), Some(b']') => { tokenizer.consume(); - State::Next(StateName::HtmlTextCdataClose) + State::Next(Name::HtmlTextCdataClose) } _ => { tokenizer.consume(); - State::Next(StateName::HtmlTextCdata) + State::Next(Name::HtmlTextCdata) } } } @@ -296,9 +297,9 @@ pub fn cdata_close(tokenizer: &mut Tokenizer) -> State { match tokenizer.current { Some(b']') => { tokenizer.consume(); - State::Next(StateName::HtmlTextCdataEnd) + State::Next(Name::HtmlTextCdataEnd) } - _ => State::Retry(StateName::HtmlTextCdata), + _ => State::Retry(Name::HtmlTextCdata), } } @@ -310,9 +311,9 @@ pub fn cdata_close(tokenizer: &mut Tokenizer) -> State { /// ``` pub fn cdata_end(tokenizer: &mut Tokenizer) -> State { match tokenizer.current { - Some(b'>') => State::Retry(StateName::HtmlTextEnd), - Some(b']') => State::Retry(StateName::HtmlTextCdataClose), - _ => State::Retry(StateName::HtmlTextCdata), + Some(b'>') => State::Retry(Name::HtmlTextEnd), + Some(b']') => State::Retry(Name::HtmlTextCdataClose), + _ => State::Retry(Name::HtmlTextCdata), } } @@ -324,15 +325,15 @@ pub fn cdata_end(tokenizer: &mut Tokenizer) -> State { /// ``` pub fn declaration(tokenizer: &mut Tokenizer) -> State { match tokenizer.current { - None | Some(b'>') => State::Retry(StateName::HtmlTextEnd), + None | Some(b'>') => State::Retry(Name::HtmlTextEnd), Some(b'\n') => tokenizer.attempt( - StateName::HtmlTextLineEndingBefore, - State::Next(StateName::HtmlTextDeclaration), + Name::HtmlTextLineEndingBefore, + State::Next(Name::HtmlTextDeclaration), State::Nok, ), _ => { tokenizer.consume(); - State::Next(StateName::HtmlTextDeclaration) + State::Next(Name::HtmlTextDeclaration) } } } @@ -347,17 +348,17 @@ pub fn instruction(tokenizer: &mut Tokenizer) -> State { match tokenizer.current { None => State::Nok, Some(b'\n') => tokenizer.attempt( - StateName::HtmlTextLineEndingBefore, - State::Next(StateName::HtmlTextInstruction), + Name::HtmlTextLineEndingBefore, + State::Next(Name::HtmlTextInstruction), State::Nok, ), Some(b'?') => { tokenizer.consume(); - State::Next(StateName::HtmlTextInstructionClose) + State::Next(Name::HtmlTextInstructionClose) } _ => { tokenizer.consume(); - State::Next(StateName::HtmlTextInstruction) + State::Next(Name::HtmlTextInstruction) } } } @@ -370,8 +371,8 @@ pub fn instruction(tokenizer: &mut Tokenizer) -> State { /// ``` pub fn instruction_close(tokenizer: &mut Tokenizer) -> State { match tokenizer.current { - Some(b'>') => State::Retry(StateName::HtmlTextEnd), - _ => State::Retry(StateName::HtmlTextInstruction), + Some(b'>') => State::Retry(Name::HtmlTextEnd), + _ => State::Retry(Name::HtmlTextInstruction), } } @@ -386,7 +387,7 @@ pub fn tag_close_start(tokenizer: &mut Tokenizer) -> State { // ASCII alphabetical. Some(b'A'..=b'Z' | b'a'..=b'z') => { tokenizer.consume(); - State::Next(StateName::HtmlTextTagClose) + State::Next(Name::HtmlTextTagClose) } _ => State::Nok, } @@ -403,9 +404,9 @@ pub fn tag_close(tokenizer: &mut Tokenizer) -> State { // ASCII alphanumerical and `-`. Some(b'-' | b'0'..=b'9' | b'A'..=b'Z' | b'a'..=b'z') => { tokenizer.consume(); - State::Next(StateName::HtmlTextTagClose) + State::Next(Name::HtmlTextTagClose) } - _ => State::Retry(StateName::HtmlTextTagCloseBetween), + _ => State::Retry(Name::HtmlTextTagCloseBetween), } } @@ -418,15 +419,15 @@ pub fn tag_close(tokenizer: &mut Tokenizer) -> State { pub fn tag_close_between(tokenizer: &mut Tokenizer) -> State { match tokenizer.current { Some(b'\n') => tokenizer.attempt( - StateName::HtmlTextLineEndingBefore, - State::Next(StateName::HtmlTextTagCloseBetween), + Name::HtmlTextLineEndingBefore, + State::Next(Name::HtmlTextTagCloseBetween), State::Nok, ), Some(b'\t' | b' ') => { tokenizer.consume(); - State::Next(StateName::HtmlTextTagCloseBetween) + State::Next(Name::HtmlTextTagCloseBetween) } - _ => State::Retry(StateName::HtmlTextEnd), + _ => State::Retry(Name::HtmlTextEnd), } } @@ -441,9 +442,9 @@ pub fn tag_open(tokenizer: &mut Tokenizer) -> State { // ASCII alphanumerical and `-`. Some(b'-' | b'0'..=b'9' | b'A'..=b'Z' | b'a'..=b'z') => { tokenizer.consume(); - State::Next(StateName::HtmlTextTagOpen) + State::Next(Name::HtmlTextTagOpen) } - Some(b'\t' | b'\n' | b' ' | b'/' | b'>') => State::Retry(StateName::HtmlTextTagOpenBetween), + Some(b'\t' | b'\n' | b' ' | b'/' | b'>') => State::Retry(Name::HtmlTextTagOpenBetween), _ => State::Nok, } } @@ -457,24 +458,24 @@ pub fn tag_open(tokenizer: &mut Tokenizer) -> State { pub fn tag_open_between(tokenizer: &mut Tokenizer) -> State { match tokenizer.current { Some(b'\n') => tokenizer.attempt( - StateName::HtmlTextLineEndingBefore, - State::Next(StateName::HtmlTextTagOpenBetween), + Name::HtmlTextLineEndingBefore, + State::Next(Name::HtmlTextTagOpenBetween), State::Nok, ), Some(b'\t' | b' ') => { tokenizer.consume(); - State::Next(StateName::HtmlTextTagOpenBetween) + State::Next(Name::HtmlTextTagOpenBetween) } Some(b'/') => { tokenizer.consume(); - State::Next(StateName::HtmlTextEnd) + State::Next(Name::HtmlTextEnd) } // ASCII alphabetical and `:` and `_`. Some(b':' | b'A'..=b'Z' | b'_' | b'a'..=b'z') => { tokenizer.consume(); - State::Next(StateName::HtmlTextTagOpenAttributeName) + State::Next(Name::HtmlTextTagOpenAttributeName) } - _ => State::Retry(StateName::HtmlTextEnd), + _ => State::Retry(Name::HtmlTextEnd), } } @@ -489,9 +490,9 @@ pub fn tag_open_attribute_name(tokenizer: &mut Tokenizer) -> State { // ASCII alphabetical and `-`, `.`, `:`, and `_`. Some(b'-' | b'.' | b'0'..=b'9' | b':' | b'A'..=b'Z' | b'_' | b'a'..=b'z') => { tokenizer.consume(); - State::Next(StateName::HtmlTextTagOpenAttributeName) + State::Next(Name::HtmlTextTagOpenAttributeName) } - _ => State::Retry(StateName::HtmlTextTagOpenAttributeNameAfter), + _ => State::Retry(Name::HtmlTextTagOpenAttributeNameAfter), } } @@ -505,19 +506,19 @@ pub fn tag_open_attribute_name(tokenizer: &mut Tokenizer) -> State { pub fn tag_open_attribute_name_after(tokenizer: &mut Tokenizer) -> State { match tokenizer.current { Some(b'\n') => tokenizer.attempt( - StateName::HtmlTextLineEndingBefore, - State::Next(StateName::HtmlTextTagOpenAttributeNameAfter), + Name::HtmlTextLineEndingBefore, + State::Next(Name::HtmlTextTagOpenAttributeNameAfter), State::Nok, ), Some(b'\t' | b' ') => { tokenizer.consume(); - State::Next(StateName::HtmlTextTagOpenAttributeNameAfter) + State::Next(Name::HtmlTextTagOpenAttributeNameAfter) } Some(b'=') => { tokenizer.consume(); - State::Next(StateName::HtmlTextTagOpenAttributeValueBefore) + State::Next(Name::HtmlTextTagOpenAttributeValueBefore) } - _ => State::Retry(StateName::HtmlTextTagOpenBetween), + _ => State::Retry(Name::HtmlTextTagOpenBetween), } } @@ -532,22 +533,22 @@ pub fn tag_open_attribute_value_before(tokenizer: &mut Tokenizer) -> State { match tokenizer.current { None | Some(b'<' | b'=' | b'>' | b'`') => State::Nok, Some(b'\n') => tokenizer.attempt( - StateName::HtmlTextLineEndingBefore, - State::Next(StateName::HtmlTextTagOpenAttributeValueBefore), + Name::HtmlTextLineEndingBefore, + State::Next(Name::HtmlTextTagOpenAttributeValueBefore), State::Nok, ), Some(b'\t' | b' ') => { tokenizer.consume(); - State::Next(StateName::HtmlTextTagOpenAttributeValueBefore) + State::Next(Name::HtmlTextTagOpenAttributeValueBefore) } Some(b'"' | b'\'') => { tokenizer.tokenize_state.marker = tokenizer.current.unwrap(); tokenizer.consume(); - State::Next(StateName::HtmlTextTagOpenAttributeValueQuoted) + State::Next(Name::HtmlTextTagOpenAttributeValueQuoted) } Some(_) => { tokenizer.consume(); - State::Next(StateName::HtmlTextTagOpenAttributeValueUnquoted) + State::Next(Name::HtmlTextTagOpenAttributeValueUnquoted) } } } @@ -565,18 +566,18 @@ pub fn tag_open_attribute_value_quoted(tokenizer: &mut Tokenizer) -> State { State::Nok } Some(b'\n') => tokenizer.attempt( - StateName::HtmlTextLineEndingBefore, - State::Next(StateName::HtmlTextTagOpenAttributeValueQuoted), + Name::HtmlTextLineEndingBefore, + State::Next(Name::HtmlTextTagOpenAttributeValueQuoted), State::Nok, ), Some(b'"' | b'\'') if tokenizer.current.unwrap() == tokenizer.tokenize_state.marker => { tokenizer.tokenize_state.marker = 0; tokenizer.consume(); - State::Next(StateName::HtmlTextTagOpenAttributeValueQuotedAfter) + State::Next(Name::HtmlTextTagOpenAttributeValueQuotedAfter) } _ => { tokenizer.consume(); - State::Next(StateName::HtmlTextTagOpenAttributeValueQuoted) + State::Next(Name::HtmlTextTagOpenAttributeValueQuoted) } } } @@ -590,10 +591,10 @@ pub fn tag_open_attribute_value_quoted(tokenizer: &mut Tokenizer) -> State { pub fn tag_open_attribute_value_unquoted(tokenizer: &mut Tokenizer) -> State { match tokenizer.current { None | Some(b'"' | b'\'' | b'<' | b'=' | b'`') => State::Nok, - Some(b'\t' | b'\n' | b' ' | b'/' | b'>') => State::Retry(StateName::HtmlTextTagOpenBetween), + Some(b'\t' | b'\n' | b' ' | b'/' | b'>') => State::Retry(Name::HtmlTextTagOpenBetween), Some(_) => { tokenizer.consume(); - State::Next(StateName::HtmlTextTagOpenAttributeValueUnquoted) + State::Next(Name::HtmlTextTagOpenAttributeValueUnquoted) } } } @@ -607,7 +608,7 @@ pub fn tag_open_attribute_value_unquoted(tokenizer: &mut Tokenizer) -> State { /// ``` pub fn tag_open_attribute_value_quoted_after(tokenizer: &mut Tokenizer) -> State { match tokenizer.current { - Some(b'\t' | b'\n' | b' ' | b'>' | b'/') => State::Retry(StateName::HtmlTextTagOpenBetween), + Some(b'\t' | b'\n' | b' ' | b'>' | b'/') => State::Retry(Name::HtmlTextTagOpenBetween), _ => State::Nok, } } @@ -647,7 +648,7 @@ pub fn line_ending_before(tokenizer: &mut Tokenizer) -> State { tokenizer.enter(Token::LineEnding); tokenizer.consume(); tokenizer.exit(Token::LineEnding); - State::Next(StateName::HtmlTextLineEndingAfter) + State::Next(Name::HtmlTextLineEndingAfter) } _ => unreachable!("expected eol"), } @@ -667,8 +668,8 @@ pub fn line_ending_after(tokenizer: &mut Tokenizer) -> State { let name = space_or_tab(tokenizer); tokenizer.attempt( name, - State::Next(StateName::HtmlTextLineEndingAfterPrefix), - State::Next(StateName::HtmlTextLineEndingAfterPrefix), + State::Next(Name::HtmlTextLineEndingAfterPrefix), + State::Next(Name::HtmlTextLineEndingAfterPrefix), ) } diff --git a/src/construct/label_end.rs b/src/construct/label_end.rs index a25f917..0607077 100644 --- a/src/construct/label_end.rs +++ b/src/construct/label_end.rs @@ -148,8 +148,9 @@ use crate::constant::RESOURCE_DESTINATION_BALANCE_MAX; use crate::construct::partial_space_or_tab::space_or_tab_eol; +use crate::state::{Name, State}; use crate::token::Token; -use crate::tokenizer::{Event, EventType, Media, State, StateName, Tokenizer}; +use crate::tokenizer::{Event, EventType, Media, Tokenizer}; use crate::util::{ normalize_identifier::normalize_identifier, skip, @@ -194,7 +195,7 @@ pub fn start(tokenizer: &mut Tokenizer) -> State { // Mark as balanced if the info is inactive. if label_start.inactive { - return State::Retry(StateName::LabelEndNok); + return State::Retry(Name::LabelEndNok); } tokenizer.enter(Token::LabelEnd); @@ -202,7 +203,7 @@ pub fn start(tokenizer: &mut Tokenizer) -> State { tokenizer.consume(); tokenizer.exit(Token::LabelMarker); tokenizer.exit(Token::LabelEnd); - return State::Next(StateName::LabelEndAfter); + return State::Next(Name::LabelEndAfter); } } @@ -239,29 +240,29 @@ pub fn after(tokenizer: &mut Tokenizer) -> State { match tokenizer.current { // Resource (`[asd](fgh)`)? Some(b'(') => tokenizer.attempt( - StateName::LabelEndResourceStart, - State::Next(StateName::LabelEndOk), + Name::LabelEndResourceStart, + State::Next(Name::LabelEndOk), State::Next(if defined { - StateName::LabelEndOk + Name::LabelEndOk } else { - StateName::LabelEndNok + Name::LabelEndNok }), ), // Full (`[asd][fgh]`) or collapsed (`[asd][]`) reference? Some(b'[') => tokenizer.attempt( - StateName::LabelEndReferenceFull, - State::Next(StateName::LabelEndOk), + Name::LabelEndReferenceFull, + State::Next(Name::LabelEndOk), State::Next(if defined { - StateName::LabelEndReferenceNotFull + Name::LabelEndReferenceNotFull } else { - StateName::LabelEndNok + Name::LabelEndNok }), ), // Shortcut (`[asd]`) reference? _ => State::Retry(if defined { - StateName::LabelEndOk + Name::LabelEndOk } else { - StateName::LabelEndNok + Name::LabelEndNok }), } } @@ -278,9 +279,9 @@ pub fn after(tokenizer: &mut Tokenizer) -> State { /// ``` pub fn reference_not_full(tokenizer: &mut Tokenizer) -> State { tokenizer.attempt( - StateName::LabelEndReferenceCollapsed, - State::Next(StateName::LabelEndOk), - State::Next(StateName::LabelEndNok), + Name::LabelEndReferenceCollapsed, + State::Next(Name::LabelEndOk), + State::Next(Name::LabelEndNok), ) } @@ -370,7 +371,7 @@ pub fn resource_start(tokenizer: &mut Tokenizer) -> State { tokenizer.enter(Token::ResourceMarker); tokenizer.consume(); tokenizer.exit(Token::ResourceMarker); - State::Next(StateName::LabelEndResourceBefore) + State::Next(Name::LabelEndResourceBefore) } _ => unreachable!("expected `(`"), } @@ -386,8 +387,8 @@ pub fn resource_before(tokenizer: &mut Tokenizer) -> State { let name = space_or_tab_eol(tokenizer); tokenizer.attempt( name, - State::Next(StateName::LabelEndResourceOpen), - State::Next(StateName::LabelEndResourceOpen), + State::Next(Name::LabelEndResourceOpen), + State::Next(Name::LabelEndResourceOpen), ) } @@ -399,7 +400,7 @@ pub fn resource_before(tokenizer: &mut Tokenizer) -> State { /// ``` pub fn resource_open(tokenizer: &mut Tokenizer) -> State { if let Some(b')') = tokenizer.current { - State::Retry(StateName::LabelEndResourceEnd) + State::Retry(Name::LabelEndResourceEnd) } else { tokenizer.tokenize_state.token_1 = Token::ResourceDestination; tokenizer.tokenize_state.token_2 = Token::ResourceDestinationLiteral; @@ -409,9 +410,9 @@ pub fn resource_open(tokenizer: &mut Tokenizer) -> State { tokenizer.tokenize_state.size_b = RESOURCE_DESTINATION_BALANCE_MAX; tokenizer.attempt( - StateName::DestinationStart, - State::Next(StateName::LabelEndResourceDestinationAfter), - State::Next(StateName::LabelEndResourceDestinationMissing), + Name::DestinationStart, + State::Next(Name::LabelEndResourceDestinationAfter), + State::Next(Name::LabelEndResourceDestinationMissing), ) } } @@ -432,8 +433,8 @@ pub fn resource_destination_after(tokenizer: &mut Tokenizer) -> State { let name = space_or_tab_eol(tokenizer); tokenizer.attempt( name, - State::Next(StateName::LabelEndResourceBetween), - State::Next(StateName::LabelEndResourceEnd), + State::Next(Name::LabelEndResourceBetween), + State::Next(Name::LabelEndResourceEnd), ) } @@ -461,12 +462,12 @@ pub fn resource_between(tokenizer: &mut Tokenizer) -> State { tokenizer.tokenize_state.token_2 = Token::ResourceTitleMarker; tokenizer.tokenize_state.token_3 = Token::ResourceTitleString; tokenizer.attempt( - StateName::TitleStart, - State::Next(StateName::LabelEndResourceTitleAfter), + Name::TitleStart, + State::Next(Name::LabelEndResourceTitleAfter), State::Nok, ) } - _ => State::Retry(StateName::LabelEndResourceEnd), + _ => State::Retry(Name::LabelEndResourceEnd), } } @@ -483,8 +484,8 @@ pub fn resource_title_after(tokenizer: &mut Tokenizer) -> State { let name = space_or_tab_eol(tokenizer); tokenizer.attempt( name, - State::Next(StateName::LabelEndResourceEnd), - State::Next(StateName::LabelEndResourceEnd), + State::Next(Name::LabelEndResourceEnd), + State::Next(Name::LabelEndResourceEnd), ) } @@ -520,8 +521,8 @@ pub fn reference_full(tokenizer: &mut Tokenizer) -> State { tokenizer.tokenize_state.token_2 = Token::ReferenceMarker; tokenizer.tokenize_state.token_3 = Token::ReferenceString; tokenizer.attempt( - StateName::LabelStart, - State::Next(StateName::LabelEndReferenceFullAfter), + Name::LabelStart, + State::Next(Name::LabelEndReferenceFullAfter), State::Nok, ) } @@ -580,7 +581,7 @@ pub fn reference_collapsed(tokenizer: &mut Tokenizer) -> State { tokenizer.enter(Token::ReferenceMarker); tokenizer.consume(); tokenizer.exit(Token::ReferenceMarker); - State::Next(StateName::LabelEndReferenceCollapsedOpen) + State::Next(Name::LabelEndReferenceCollapsedOpen) } _ => State::Nok, } diff --git a/src/construct/label_start_image.rs b/src/construct/label_start_image.rs index 629e836..7703ba4 100644 --- a/src/construct/label_start_image.rs +++ b/src/construct/label_start_image.rs @@ -29,8 +29,9 @@ //! [html-img]: https://html.spec.whatwg.org/multipage/embedded-content.html#the-img-element use super::label_end::resolve_media; +use crate::state::{Name, State}; use crate::token::Token; -use crate::tokenizer::{LabelStart, State, StateName, Tokenizer}; +use crate::tokenizer::{LabelStart, Tokenizer}; /// Start of label (image) start. /// @@ -45,7 +46,7 @@ pub fn start(tokenizer: &mut Tokenizer) -> State { tokenizer.enter(Token::LabelImageMarker); tokenizer.consume(); tokenizer.exit(Token::LabelImageMarker); - State::Next(StateName::LabelStartImageOpen) + State::Next(Name::LabelStartImageOpen) } _ => State::Nok, } diff --git a/src/construct/label_start_link.rs b/src/construct/label_start_link.rs index 6eb7b40..3ca51bf 100644 --- a/src/construct/label_start_link.rs +++ b/src/construct/label_start_link.rs @@ -28,8 +28,9 @@ //! [html-a]: https://html.spec.whatwg.org/multipage/text-level-semantics.html#the-a-element use super::label_end::resolve_media; +use crate::state::State; use crate::token::Token; -use crate::tokenizer::{LabelStart, State, Tokenizer}; +use crate::tokenizer::{LabelStart, Tokenizer}; /// Start of label (link) start. /// diff --git a/src/construct/list.rs b/src/construct/list.rs index d726c73..516cec7 100644 --- a/src/construct/list.rs +++ b/src/construct/list.rs @@ -46,8 +46,9 @@ use crate::constant::{LIST_ITEM_VALUE_SIZE_MAX, TAB_SIZE}; use crate::construct::partial_space_or_tab::space_or_tab_min_max; +use crate::state::{Name, State}; use crate::token::Token; -use crate::tokenizer::{EventType, State, StateName, Tokenizer}; +use crate::tokenizer::{EventType, Tokenizer}; use crate::util::{ skip, slice::{Position, Slice}, @@ -71,7 +72,7 @@ pub fn start(tokenizer: &mut Tokenizer) -> State { usize::MAX }, ); - tokenizer.attempt(name, State::Next(StateName::ListBefore), State::Nok) + tokenizer.attempt(name, State::Next(Name::ListBefore), State::Nok) } else { State::Nok } @@ -87,14 +88,14 @@ pub fn before(tokenizer: &mut Tokenizer) -> State { match tokenizer.current { // Unordered. Some(b'*' | b'-') => tokenizer.check( - StateName::ThematicBreakStart, - State::Next(StateName::ListNok), - State::Next(StateName::ListBeforeUnordered), + Name::ThematicBreakStart, + State::Next(Name::ListNok), + State::Next(Name::ListBeforeUnordered), ), - Some(b'+') => State::Retry(StateName::ListBeforeUnordered), + Some(b'+') => State::Retry(Name::ListBeforeUnordered), // Ordered. - Some(b'0'..=b'9') if !tokenizer.interrupt => State::Retry(StateName::ListBeforeOrdered), - Some(b'1') => State::Retry(StateName::ListBeforeOrdered), + Some(b'0'..=b'9') if !tokenizer.interrupt => State::Retry(Name::ListBeforeOrdered), + Some(b'1') => State::Retry(Name::ListBeforeOrdered), _ => State::Nok, } } @@ -109,7 +110,7 @@ pub fn before(tokenizer: &mut Tokenizer) -> State { /// ``` pub fn before_unordered(tokenizer: &mut Tokenizer) -> State { tokenizer.enter(Token::ListItemPrefix); - State::Retry(StateName::ListMarker) + State::Retry(Name::ListMarker) } /// Start of an ordered list item. @@ -121,7 +122,7 @@ pub fn before_unordered(tokenizer: &mut Tokenizer) -> State { pub fn before_ordered(tokenizer: &mut Tokenizer) -> State { tokenizer.enter(Token::ListItemPrefix); tokenizer.enter(Token::ListItemValue); - State::Retry(StateName::ListValue) + State::Retry(Name::ListValue) } /// In an ordered list item value. @@ -134,12 +135,12 @@ pub fn value(tokenizer: &mut Tokenizer) -> State { match tokenizer.current { Some(b'.' | b')') if !tokenizer.interrupt || tokenizer.tokenize_state.size < 2 => { tokenizer.exit(Token::ListItemValue); - State::Retry(StateName::ListMarker) + State::Retry(Name::ListMarker) } Some(b'0'..=b'9') if tokenizer.tokenize_state.size + 1 < LIST_ITEM_VALUE_SIZE_MAX => { tokenizer.tokenize_state.size += 1; tokenizer.consume(); - State::Next(StateName::ListValue) + State::Next(Name::ListValue) } _ => { tokenizer.tokenize_state.size = 0; @@ -160,7 +161,7 @@ pub fn marker(tokenizer: &mut Tokenizer) -> State { tokenizer.enter(Token::ListItemMarker); tokenizer.consume(); tokenizer.exit(Token::ListItemMarker); - State::Next(StateName::ListMarkerAfter) + State::Next(Name::ListMarkerAfter) } /// After a list item marker. @@ -174,9 +175,9 @@ pub fn marker(tokenizer: &mut Tokenizer) -> State { pub fn marker_after(tokenizer: &mut Tokenizer) -> State { tokenizer.tokenize_state.size = 1; tokenizer.check( - StateName::BlankLineStart, - State::Next(StateName::ListAfter), - State::Next(StateName::ListMarkerAfterFilled), + Name::BlankLineStart, + State::Next(Name::ListAfter), + State::Next(Name::ListMarkerAfterFilled), ) } @@ -191,9 +192,9 @@ pub fn marker_after_filled(tokenizer: &mut Tokenizer) -> State { // Attempt to parse up to the largest allowed indent, `nok` if there is more whitespace. tokenizer.attempt( - StateName::ListWhitespace, - State::Next(StateName::ListAfter), - State::Next(StateName::ListPrefixOther), + Name::ListWhitespace, + State::Next(Name::ListAfter), + State::Next(Name::ListPrefixOther), ) } @@ -205,11 +206,7 @@ pub fn marker_after_filled(tokenizer: &mut Tokenizer) -> State { /// ``` pub fn whitespace(tokenizer: &mut Tokenizer) -> State { let name = space_or_tab_min_max(tokenizer, 1, TAB_SIZE); - tokenizer.attempt( - name, - State::Next(StateName::ListWhitespaceAfter), - State::Nok, - ) + tokenizer.attempt(name, State::Next(Name::ListWhitespaceAfter), State::Nok) } /// After acceptable whitespace. @@ -238,7 +235,7 @@ pub fn prefix_other(tokenizer: &mut Tokenizer) -> State { tokenizer.enter(Token::SpaceOrTab); tokenizer.consume(); tokenizer.exit(Token::SpaceOrTab); - State::Next(StateName::ListAfter) + State::Next(Name::ListAfter) } _ => State::Nok, } @@ -296,9 +293,9 @@ pub fn after(tokenizer: &mut Tokenizer) -> State { /// ``` pub fn cont_start(tokenizer: &mut Tokenizer) -> State { tokenizer.check( - StateName::BlankLineStart, - State::Next(StateName::ListContBlank), - State::Next(StateName::ListContFilled), + Name::BlankLineStart, + State::Next(Name::ListContBlank), + State::Next(Name::ListContFilled), ) } @@ -320,7 +317,7 @@ pub fn cont_blank(tokenizer: &mut Tokenizer) -> State { } else { let name = space_or_tab_min_max(tokenizer, 0, size); // Consume, optionally, at most `size`. - tokenizer.attempt(name, State::Next(StateName::ListOk), State::Nok) + tokenizer.attempt(name, State::Next(Name::ListOk), State::Nok) } } @@ -340,7 +337,7 @@ pub fn cont_filled(tokenizer: &mut Tokenizer) -> State { // Consume exactly `size`. let name = space_or_tab_min_max(tokenizer, size, size); - tokenizer.attempt(name, State::Next(StateName::ListOk), State::Nok) + tokenizer.attempt(name, State::Next(Name::ListOk), State::Nok) } /// A state fn to yield [`State::Ok`]. diff --git a/src/construct/paragraph.rs b/src/construct/paragraph.rs index bac4369..dec25b8 100644 --- a/src/construct/paragraph.rs +++ b/src/construct/paragraph.rs @@ -32,8 +32,9 @@ //! [code_text]: crate::construct::code_text //! [html]: https://html.spec.whatwg.org/multipage/grouping-content.html#the-p-element +use crate::state::{Name, State}; use crate::token::Token; -use crate::tokenizer::{ContentType, EventType, State, StateName, Tokenizer}; +use crate::tokenizer::{ContentType, EventType, Tokenizer}; use crate::util::skip::opt as skip_opt; /// Before a paragraph. @@ -48,7 +49,7 @@ pub fn start(tokenizer: &mut Tokenizer) -> State { _ => { tokenizer.enter(Token::Paragraph); tokenizer.enter_with_content(Token::Data, Some(ContentType::Text)); - State::Retry(StateName::ParagraphInside) + State::Retry(Name::ParagraphInside) } } } @@ -71,7 +72,7 @@ pub fn inside(tokenizer: &mut Tokenizer) -> State { } _ => { tokenizer.consume(); - State::Next(StateName::ParagraphInside) + State::Next(Name::ParagraphInside) } } } diff --git a/src/construct/partial_bom.rs b/src/construct/partial_bom.rs index d20c2c7..cca0770 100644 --- a/src/construct/partial_bom.rs +++ b/src/construct/partial_bom.rs @@ -10,8 +10,9 @@ //! //! * [`micromark/lib/preprocess.js` in `micromark`](https://github.com/micromark/micromark/blob/ed23453/packages/micromark/dev/lib/preprocess.js#L54-L60) +use crate::state::{Name, State}; use crate::token::Token; -use crate::tokenizer::{State, StateName, Tokenizer}; +use crate::tokenizer::Tokenizer; const BOM: [u8; 3] = [0xEF, 0xBB, 0xBF]; @@ -24,7 +25,7 @@ const BOM: [u8; 3] = [0xEF, 0xBB, 0xBF]; pub fn start(tokenizer: &mut Tokenizer) -> State { if tokenizer.current == Some(BOM[0]) { tokenizer.enter(Token::ByteOrderMark); - State::Retry(StateName::BomInside) + State::Retry(Name::BomInside) } else { State::Nok } @@ -45,7 +46,7 @@ pub fn inside(tokenizer: &mut Tokenizer) -> State { tokenizer.tokenize_state.size = 0; State::Ok } else { - State::Next(StateName::BomInside) + State::Next(Name::BomInside) } } else { tokenizer.tokenize_state.size = 0; diff --git a/src/construct/partial_data.rs b/src/construct/partial_data.rs index 0ad67c5..c05aaa5 100644 --- a/src/construct/partial_data.rs +++ b/src/construct/partial_data.rs @@ -6,8 +6,9 @@ //! [string]: crate::content::string //! [text]: crate::content::text +use crate::state::{Name, State}; use crate::token::Token; -use crate::tokenizer::{EventType, State, StateName, Tokenizer}; +use crate::tokenizer::{EventType, Tokenizer}; /// At the beginning of data. /// @@ -21,9 +22,9 @@ pub fn start(tokenizer: &mut Tokenizer) -> State { Some(byte) if tokenizer.tokenize_state.markers.contains(&byte) => { tokenizer.enter(Token::Data); tokenizer.consume(); - State::Next(StateName::DataInside) + State::Next(Name::DataInside) } - _ => State::Retry(StateName::DataAtBreak), + _ => State::Retry(Name::DataAtBreak), } } @@ -40,7 +41,7 @@ pub fn at_break(tokenizer: &mut Tokenizer) -> State { tokenizer.enter(Token::LineEnding); tokenizer.consume(); tokenizer.exit(Token::LineEnding); - State::Next(StateName::DataAtBreak) + State::Next(Name::DataAtBreak) } Some(byte) if tokenizer.tokenize_state.markers.contains(&byte) => { tokenizer.register_resolver_before("data".to_string(), Box::new(resolve_data)); @@ -48,7 +49,7 @@ pub fn at_break(tokenizer: &mut Tokenizer) -> State { } _ => { tokenizer.enter(Token::Data); - State::Retry(StateName::DataInside) + State::Retry(Name::DataInside) } } } @@ -68,10 +69,10 @@ pub fn inside(tokenizer: &mut Tokenizer) -> State { if done { tokenizer.exit(Token::Data); - State::Retry(StateName::DataAtBreak) + State::Retry(Name::DataAtBreak) } else { tokenizer.consume(); - State::Next(StateName::DataInside) + State::Next(Name::DataInside) } } diff --git a/src/construct/partial_destination.rs b/src/construct/partial_destination.rs index 735fb38..5aa0539 100644 --- a/src/construct/partial_destination.rs +++ b/src/construct/partial_destination.rs @@ -71,8 +71,9 @@ //! [label_end]: crate::construct::label_end //! [sanitize_uri]: crate::util::sanitize_uri +use crate::state::{Name, State}; use crate::token::Token; -use crate::tokenizer::{ContentType, State, StateName, Tokenizer}; +use crate::tokenizer::{ContentType, Tokenizer}; /// Before a destination. /// @@ -90,7 +91,7 @@ pub fn start(tokenizer: &mut Tokenizer) -> State { tokenizer.enter(tokenizer.tokenize_state.token_3.clone()); tokenizer.consume(); tokenizer.exit(tokenizer.tokenize_state.token_3.clone()); - State::Next(StateName::DestinationEnclosedBefore) + State::Next(Name::DestinationEnclosedBefore) } // ASCII control, space, closing paren, but *not* `\0`. None | Some(0x01..=0x1F | b' ' | b')' | 0x7F) => State::Nok, @@ -99,7 +100,7 @@ pub fn start(tokenizer: &mut Tokenizer) -> State { tokenizer.enter(tokenizer.tokenize_state.token_4.clone()); tokenizer.enter(tokenizer.tokenize_state.token_5.clone()); tokenizer.enter_with_content(Token::Data, Some(ContentType::String)); - State::Retry(StateName::DestinationRaw) + State::Retry(Name::DestinationRaw) } } } @@ -121,7 +122,7 @@ pub fn enclosed_before(tokenizer: &mut Tokenizer) -> State { } else { tokenizer.enter(tokenizer.tokenize_state.token_5.clone()); tokenizer.enter_with_content(Token::Data, Some(ContentType::String)); - State::Retry(StateName::DestinationEnclosed) + State::Retry(Name::DestinationEnclosed) } } @@ -137,15 +138,15 @@ pub fn enclosed(tokenizer: &mut Tokenizer) -> State { Some(b'>') => { tokenizer.exit(Token::Data); tokenizer.exit(tokenizer.tokenize_state.token_5.clone()); - State::Retry(StateName::DestinationEnclosedBefore) + State::Retry(Name::DestinationEnclosedBefore) } Some(b'\\') => { tokenizer.consume(); - State::Next(StateName::DestinationEnclosedEscape) + State::Next(Name::DestinationEnclosedEscape) } _ => { tokenizer.consume(); - State::Next(StateName::DestinationEnclosed) + State::Next(Name::DestinationEnclosed) } } } @@ -160,9 +161,9 @@ pub fn enclosed_escape(tokenizer: &mut Tokenizer) -> State { match tokenizer.current { Some(b'<' | b'>' | b'\\') => { tokenizer.consume(); - State::Next(StateName::DestinationEnclosed) + State::Next(Name::DestinationEnclosed) } - _ => State::Retry(StateName::DestinationEnclosed), + _ => State::Retry(Name::DestinationEnclosed), } } @@ -185,7 +186,7 @@ pub fn raw(tokenizer: &mut Tokenizer) -> State { Some(b'(') if tokenizer.tokenize_state.size < tokenizer.tokenize_state.size_b => { tokenizer.consume(); tokenizer.tokenize_state.size += 1; - State::Next(StateName::DestinationRaw) + State::Next(Name::DestinationRaw) } // ASCII control (but *not* `\0`) and space and `(`. None | Some(0x01..=0x1F | b' ' | b'(' | 0x7F) => { @@ -195,15 +196,15 @@ pub fn raw(tokenizer: &mut Tokenizer) -> State { Some(b')') => { tokenizer.consume(); tokenizer.tokenize_state.size -= 1; - State::Next(StateName::DestinationRaw) + State::Next(Name::DestinationRaw) } Some(b'\\') => { tokenizer.consume(); - State::Next(StateName::DestinationRawEscape) + State::Next(Name::DestinationRawEscape) } Some(_) => { tokenizer.consume(); - State::Next(StateName::DestinationRaw) + State::Next(Name::DestinationRaw) } } } @@ -218,8 +219,8 @@ pub fn raw_escape(tokenizer: &mut Tokenizer) -> State { match tokenizer.current { Some(b'(' | b')' | b'\\') => { tokenizer.consume(); - State::Next(StateName::DestinationRaw) + State::Next(Name::DestinationRaw) } - _ => State::Retry(StateName::DestinationRaw), + _ => State::Retry(Name::DestinationRaw), } } diff --git a/src/construct/partial_label.rs b/src/construct/partial_label.rs index 6447961..6e7c843 100644 --- a/src/construct/partial_label.rs +++ b/src/construct/partial_label.rs @@ -60,9 +60,10 @@ use super::partial_space_or_tab::{space_or_tab_eol_with_options, EolOptions}; use crate::constant::LINK_REFERENCE_SIZE_MAX; +use crate::state::{Name, State}; use crate::subtokenize::link; use crate::token::Token; -use crate::tokenizer::{ContentType, State, StateName, Tokenizer}; +use crate::tokenizer::{ContentType, Tokenizer}; /// Before a label. /// @@ -78,7 +79,7 @@ pub fn start(tokenizer: &mut Tokenizer) -> State { tokenizer.consume(); tokenizer.exit(tokenizer.tokenize_state.token_2.clone()); tokenizer.enter(tokenizer.tokenize_state.token_3.clone()); - State::Next(StateName::LabelAtBreak) + State::Next(Name::LabelAtBreak) } _ => State::Nok, } @@ -111,8 +112,8 @@ pub fn at_break(tokenizer: &mut Tokenizer) -> State { ); tokenizer.attempt( name, - State::Next(StateName::LabelEolAfter), - State::Next(StateName::LabelAtBlankLine), + State::Next(Name::LabelEolAfter), + State::Next(Name::LabelAtBlankLine), ) } Some(b']') => { @@ -136,7 +137,7 @@ pub fn at_break(tokenizer: &mut Tokenizer) -> State { tokenizer.tokenize_state.connect = true; } - State::Retry(StateName::LabelInside) + State::Retry(Name::LabelInside) } } } @@ -151,7 +152,7 @@ pub fn at_break(tokenizer: &mut Tokenizer) -> State { /// ``` pub fn eol_after(tokenizer: &mut Tokenizer) -> State { tokenizer.tokenize_state.connect = true; - State::Retry(StateName::LabelAtBreak) + State::Retry(Name::LabelAtBreak) } /// In a label, at a blank line. @@ -178,12 +179,12 @@ pub fn inside(tokenizer: &mut Tokenizer) -> State { match tokenizer.current { None | Some(b'\n' | b'[' | b']') => { tokenizer.exit(Token::Data); - State::Retry(StateName::LabelAtBreak) + State::Retry(Name::LabelAtBreak) } Some(byte) => { if tokenizer.tokenize_state.size > LINK_REFERENCE_SIZE_MAX { tokenizer.exit(Token::Data); - State::Retry(StateName::LabelAtBreak) + State::Retry(Name::LabelAtBreak) } else { tokenizer.consume(); tokenizer.tokenize_state.size += 1; @@ -191,9 +192,9 @@ pub fn inside(tokenizer: &mut Tokenizer) -> State { tokenizer.tokenize_state.seen = true; } State::Next(if matches!(byte, b'\\') { - StateName::LabelEscape + Name::LabelEscape } else { - StateName::LabelInside + Name::LabelInside }) } } @@ -211,8 +212,8 @@ pub fn escape(tokenizer: &mut Tokenizer) -> State { Some(b'[' | b'\\' | b']') => { tokenizer.consume(); tokenizer.tokenize_state.size += 1; - State::Next(StateName::LabelInside) + State::Next(Name::LabelInside) } - _ => State::Retry(StateName::LabelInside), + _ => State::Retry(Name::LabelInside), } } diff --git a/src/construct/partial_non_lazy_continuation.rs b/src/construct/partial_non_lazy_continuation.rs index 9d19860..497c81e 100644 --- a/src/construct/partial_non_lazy_continuation.rs +++ b/src/construct/partial_non_lazy_continuation.rs @@ -10,8 +10,9 @@ //! [code_indented]: crate::construct::code_indented //! [html_flow]: crate::construct::html_flow +use crate::state::{Name, State}; use crate::token::Token; -use crate::tokenizer::{State, StateName, Tokenizer}; +use crate::tokenizer::Tokenizer; /// Start of continuation. /// @@ -26,7 +27,7 @@ pub fn start(tokenizer: &mut Tokenizer) -> State { tokenizer.enter(Token::LineEnding); tokenizer.consume(); tokenizer.exit(Token::LineEnding); - State::Next(StateName::NonLazyContinuationAfter) + State::Next(Name::NonLazyContinuationAfter) } _ => State::Nok, } diff --git a/src/construct/partial_space_or_tab.rs b/src/construct/partial_space_or_tab.rs index 5e8c212..a8e8f06 100644 --- a/src/construct/partial_space_or_tab.rs +++ b/src/construct/partial_space_or_tab.rs @@ -4,9 +4,10 @@ //! //! * [`micromark-factory-space/index.js` in `micromark`](https://github.com/micromark/micromark/blob/main/packages/micromark-factory-space/dev/index.js) +use crate::state::{Name, State}; use crate::subtokenize::link; use crate::token::Token; -use crate::tokenizer::{ContentType, State, StateName, Tokenizer}; +use crate::tokenizer::{ContentType, Tokenizer}; /// Options to parse `space_or_tab`. #[derive(Debug)] @@ -37,7 +38,7 @@ pub struct EolOptions { /// ```bnf /// space_or_tab ::= 1*( ' ' '\t' ) /// ``` -pub fn space_or_tab(tokenizer: &mut Tokenizer) -> StateName { +pub fn space_or_tab(tokenizer: &mut Tokenizer) -> Name { space_or_tab_min_max(tokenizer, 1, usize::MAX) } @@ -46,7 +47,7 @@ pub fn space_or_tab(tokenizer: &mut Tokenizer) -> StateName { /// ```bnf /// space_or_tab_min_max ::= x*y( ' ' '\t' ) /// ``` -pub fn space_or_tab_min_max(tokenizer: &mut Tokenizer, min: usize, max: usize) -> StateName { +pub fn space_or_tab_min_max(tokenizer: &mut Tokenizer, min: usize, max: usize) -> Name { space_or_tab_with_options( tokenizer, Options { @@ -60,13 +61,13 @@ pub fn space_or_tab_min_max(tokenizer: &mut Tokenizer, min: usize, max: usize) - } /// `space_or_tab`, with the given options. -pub fn space_or_tab_with_options(tokenizer: &mut Tokenizer, options: Options) -> StateName { +pub fn space_or_tab_with_options(tokenizer: &mut Tokenizer, options: Options) -> Name { tokenizer.tokenize_state.space_or_tab_connect = options.connect; tokenizer.tokenize_state.space_or_tab_content_type = options.content_type; tokenizer.tokenize_state.space_or_tab_min = options.min; tokenizer.tokenize_state.space_or_tab_max = options.max; tokenizer.tokenize_state.space_or_tab_token = options.kind; - StateName::SpaceOrTabStart + Name::SpaceOrTabStart } /// `space_or_tab`, or optionally `space_or_tab`, one `eol`, and @@ -75,7 +76,7 @@ pub fn space_or_tab_with_options(tokenizer: &mut Tokenizer, options: Options) -> /// ```bnf /// space_or_tab_eol ::= 1*( ' ' '\t' ) | 0*( ' ' '\t' ) eol 0*( ' ' '\t' ) /// ``` -pub fn space_or_tab_eol(tokenizer: &mut Tokenizer) -> StateName { +pub fn space_or_tab_eol(tokenizer: &mut Tokenizer) -> Name { space_or_tab_eol_with_options( tokenizer, EolOptions { @@ -86,10 +87,10 @@ pub fn space_or_tab_eol(tokenizer: &mut Tokenizer) -> StateName { } /// `space_or_tab_eol`, with the given options. -pub fn space_or_tab_eol_with_options(tokenizer: &mut Tokenizer, options: EolOptions) -> StateName { +pub fn space_or_tab_eol_with_options(tokenizer: &mut Tokenizer, options: EolOptions) -> Name { tokenizer.tokenize_state.space_or_tab_eol_content_type = options.content_type; tokenizer.tokenize_state.space_or_tab_eol_connect = options.connect; - StateName::SpaceOrTabEolStart + Name::SpaceOrTabEolStart } /// Before `space_or_tab`. @@ -113,9 +114,9 @@ pub fn start(tokenizer: &mut Tokenizer) -> State { tokenizer.tokenize_state.space_or_tab_connect = true; } - State::Retry(StateName::SpaceOrTabInside) + State::Retry(Name::SpaceOrTabInside) } - _ => State::Retry(StateName::SpaceOrTabAfter), + _ => State::Retry(Name::SpaceOrTabAfter), } } @@ -133,11 +134,11 @@ pub fn inside(tokenizer: &mut Tokenizer) -> State { { tokenizer.consume(); tokenizer.tokenize_state.space_or_tab_size += 1; - State::Next(StateName::SpaceOrTabInside) + State::Next(Name::SpaceOrTabInside) } _ => { tokenizer.exit(tokenizer.tokenize_state.space_or_tab_token.clone()); - State::Retry(StateName::SpaceOrTabAfter) + State::Retry(Name::SpaceOrTabAfter) } } } @@ -182,8 +183,8 @@ pub fn eol_start(tokenizer: &mut Tokenizer) -> State { tokenizer.attempt( name, - State::Next(StateName::SpaceOrTabEolAfterFirst), - State::Next(StateName::SpaceOrTabEolAtEol), + State::Next(Name::SpaceOrTabEolAfterFirst), + State::Next(Name::SpaceOrTabEolAtEol), ) } @@ -198,7 +199,7 @@ pub fn eol_after_first(tokenizer: &mut Tokenizer) -> State { tokenizer.tokenize_state.space_or_tab_eol_connect = true; } - State::Retry(StateName::SpaceOrTabEolAtEol) + State::Retry(Name::SpaceOrTabEolAtEol) } /// `space_or_tab_eol`: after optionally first `space_or_tab`. @@ -231,7 +232,7 @@ pub fn eol_at_eol(tokenizer: &mut Tokenizer) -> State { tokenizer.consume(); tokenizer.exit(Token::LineEnding); - State::Next(StateName::SpaceOrTabEolAfterEol) + State::Next(Name::SpaceOrTabEolAfterEol) } else { let ok = tokenizer.tokenize_state.space_or_tab_eol_ok; tokenizer.tokenize_state.space_or_tab_eol_content_type = None; @@ -269,8 +270,8 @@ pub fn eol_after_eol(tokenizer: &mut Tokenizer) -> State { ); tokenizer.attempt( name, - State::Next(StateName::SpaceOrTabEolAfterMore), - State::Next(StateName::SpaceOrTabEolAfterMore), + State::Next(Name::SpaceOrTabEolAfterMore), + State::Next(Name::SpaceOrTabEolAfterMore), ) } diff --git a/src/construct/partial_title.rs b/src/construct/partial_title.rs index 209240e..11c28bd 100644 --- a/src/construct/partial_title.rs +++ b/src/construct/partial_title.rs @@ -31,9 +31,10 @@ //! [label_end]: crate::construct::label_end use crate::construct::partial_space_or_tab::{space_or_tab_eol_with_options, EolOptions}; +use crate::state::{Name, State}; use crate::subtokenize::link; use crate::token::Token; -use crate::tokenizer::{ContentType, State, StateName, Tokenizer}; +use crate::tokenizer::{ContentType, Tokenizer}; /// Before a title. /// @@ -50,7 +51,7 @@ pub fn start(tokenizer: &mut Tokenizer) -> State { tokenizer.enter(tokenizer.tokenize_state.token_2.clone()); tokenizer.consume(); tokenizer.exit(tokenizer.tokenize_state.token_2.clone()); - State::Next(StateName::TitleBegin) + State::Next(Name::TitleBegin) } _ => State::Nok, } @@ -79,7 +80,7 @@ pub fn begin(tokenizer: &mut Tokenizer) -> State { } _ => { tokenizer.enter(tokenizer.tokenize_state.token_3.clone()); - State::Retry(StateName::TitleAtBreak) + State::Retry(Name::TitleAtBreak) } } } @@ -108,15 +109,15 @@ pub fn at_break(tokenizer: &mut Tokenizer) -> State { tokenizer.attempt( name, - State::Next(StateName::TitleAfterEol), - State::Next(StateName::TitleAtBlankLine), + State::Next(Name::TitleAfterEol), + State::Next(Name::TitleAtBlankLine), ) } Some(b'"' | b'\'' | b')') if tokenizer.current.unwrap() == tokenizer.tokenize_state.marker => { tokenizer.exit(tokenizer.tokenize_state.token_3.clone()); - State::Retry(StateName::TitleBegin) + State::Retry(Name::TitleBegin) } Some(_) => { tokenizer.enter_with_content(Token::Data, Some(ContentType::String)); @@ -128,7 +129,7 @@ pub fn at_break(tokenizer: &mut Tokenizer) -> State { tokenizer.tokenize_state.connect = true; } - State::Retry(StateName::TitleInside) + State::Retry(Name::TitleInside) } } } @@ -142,7 +143,7 @@ pub fn at_break(tokenizer: &mut Tokenizer) -> State { /// ``` pub fn after_eol(tokenizer: &mut Tokenizer) -> State { tokenizer.tokenize_state.connect = true; - State::Retry(StateName::TitleAtBreak) + State::Retry(Name::TitleAtBreak) } /// In a title, at a blank line. @@ -169,20 +170,20 @@ pub fn inside(tokenizer: &mut Tokenizer) -> State { match tokenizer.current { None | Some(b'\n') => { tokenizer.exit(Token::Data); - State::Retry(StateName::TitleAtBreak) + State::Retry(Name::TitleAtBreak) } Some(b'"' | b'\'' | b')') if tokenizer.current.unwrap() == tokenizer.tokenize_state.marker => { tokenizer.exit(Token::Data); - State::Retry(StateName::TitleAtBreak) + State::Retry(Name::TitleAtBreak) } Some(byte) => { tokenizer.consume(); State::Next(if matches!(byte, b'\\') { - StateName::TitleEscape + Name::TitleEscape } else { - StateName::TitleInside + Name::TitleInside }) } } @@ -198,8 +199,8 @@ pub fn escape(tokenizer: &mut Tokenizer) -> State { match tokenizer.current { Some(b'"' | b'\'' | b')') => { tokenizer.consume(); - State::Next(StateName::TitleInside) + State::Next(Name::TitleInside) } - _ => State::Retry(StateName::TitleInside), + _ => State::Retry(Name::TitleInside), } } diff --git a/src/construct/thematic_break.rs b/src/construct/thematic_break.rs index 288d818..fc71d73 100644 --- a/src/construct/thematic_break.rs +++ b/src/construct/thematic_break.rs @@ -50,8 +50,9 @@ use super::partial_space_or_tab::{space_or_tab, space_or_tab_min_max}; use crate::constant::{TAB_SIZE, THEMATIC_BREAK_MARKER_COUNT_MIN}; +use crate::state::{Name, State}; use crate::token::Token; -use crate::tokenizer::{State, StateName, Tokenizer}; +use crate::tokenizer::Tokenizer; /// Start of a thematic break. /// @@ -72,11 +73,7 @@ pub fn start(tokenizer: &mut Tokenizer) -> State { }, ); - tokenizer.attempt( - name, - State::Next(StateName::ThematicBreakBefore), - State::Nok, - ) + tokenizer.attempt(name, State::Next(Name::ThematicBreakBefore), State::Nok) } else { State::Nok } @@ -92,7 +89,7 @@ pub fn before(tokenizer: &mut Tokenizer) -> State { match tokenizer.current { Some(b'*' | b'-' | b'_') => { tokenizer.tokenize_state.marker = tokenizer.current.unwrap(); - State::Retry(StateName::ThematicBreakAtBreak) + State::Retry(Name::ThematicBreakAtBreak) } _ => State::Nok, } @@ -118,7 +115,7 @@ pub fn at_break(tokenizer: &mut Tokenizer) -> State { if tokenizer.current.unwrap() == tokenizer.tokenize_state.marker => { tokenizer.enter(Token::ThematicBreakSequence); - State::Retry(StateName::ThematicBreakSequence) + State::Retry(Name::ThematicBreakSequence) } _ => { tokenizer.tokenize_state.marker = 0; @@ -141,15 +138,15 @@ pub fn sequence(tokenizer: &mut Tokenizer) -> State { { tokenizer.consume(); tokenizer.tokenize_state.size += 1; - State::Next(StateName::ThematicBreakSequence) + State::Next(Name::ThematicBreakSequence) } _ => { tokenizer.exit(Token::ThematicBreakSequence); let name = space_or_tab(tokenizer); tokenizer.attempt( name, - State::Next(StateName::ThematicBreakAtBreak), - State::Next(StateName::ThematicBreakAtBreak), + State::Next(Name::ThematicBreakAtBreak), + State::Next(Name::ThematicBreakAtBreak), ) } } |