aboutsummaryrefslogtreecommitdiffstats
path: root/src/content/content.rs
diff options
context:
space:
mode:
Diffstat (limited to 'src/content/content.rs')
-rw-r--r--src/content/content.rs84
1 files changed, 84 insertions, 0 deletions
diff --git a/src/content/content.rs b/src/content/content.rs
new file mode 100644
index 0000000..7bf692f
--- /dev/null
+++ b/src/content/content.rs
@@ -0,0 +1,84 @@
+//! The `content`, ahum, content type.
+//!
+//! **Content** is zero or more definitions, and then zero or one paragraph.
+//! It’s a weird one, and needed to make certain edge cases around definitions
+//! spec compliant.
+//! Definitions are unlike other things in markdown, in that they behave like
+//! **text** in that they can contain arbitrary line endings, but *have* to end
+//! at a line ending.
+//! If they end in something else, the whole definition instead is seen as a
+//! paragraph.
+//!
+//! The constructs found in content are:
+//!
+//! * Definition
+//! * Paragraph
+
+use crate::tokenizer::{Code, State, StateFnResult, TokenType, Tokenizer};
+
+/// Before content.
+///
+/// ```markdown
+/// |[x]: y
+/// |asd
+/// ```
+pub fn start(tokenizer: &mut Tokenizer, code: Code) -> StateFnResult {
+ match code {
+ Code::None | Code::CarriageReturnLineFeed | Code::Char('\n' | '\r') => {
+ unreachable!("expected non-eol/eof");
+ }
+ _ => paragraph_initial(tokenizer, code)
+ // To do: definition.
+ // _ => tokenizer.attempt(definition, |ok| {
+ // Box::new(if ok {
+ // a
+ // } else {
+ // b
+ // })
+ // })(tokenizer, code),
+ }
+}
+
+/// Before a paragraph.
+///
+/// ```markdown
+/// |asd
+/// ```
+fn paragraph_initial(tokenizer: &mut Tokenizer, code: Code) -> StateFnResult {
+ match code {
+ Code::None | Code::CarriageReturnLineFeed | Code::Char('\n' | '\r') => {
+ unreachable!("expected non-eol/eof");
+ }
+ _ => {
+ tokenizer.enter(TokenType::Paragraph);
+ tokenizer.enter(TokenType::ChunkText);
+ data(tokenizer, code)
+ }
+ }
+}
+
+/// In a line in a paragraph.
+///
+/// ```markdown
+/// |\&
+/// |qwe
+/// ```
+fn data(tokenizer: &mut Tokenizer, code: Code) -> StateFnResult {
+ match code {
+ Code::None => {
+ tokenizer.exit(TokenType::ChunkText);
+ tokenizer.exit(TokenType::Paragraph);
+ (State::Ok, None)
+ }
+ Code::CarriageReturnLineFeed | Code::Char('\n' | '\r') => {
+ tokenizer.consume(code);
+ tokenizer.exit(TokenType::ChunkText);
+ tokenizer.enter(TokenType::ChunkText);
+ (State::Fn(Box::new(data)), None)
+ }
+ _ => {
+ tokenizer.consume(code);
+ (State::Fn(Box::new(data)), None)
+ }
+ }
+}