syntax/def.peg



# Subsets of Markdown syntax structure
# expressed in parsing expression grammar (PEG) notation.
#
# Copyright 2025, Jonas Smedegaard <dr@jones.dk>
# SPDX-License-Identifier: GPL-3+

# Document
Markdown       <- ('---' NEWLINE MetaBlock* '---' NEWLINE)? Block*

# Block elements
Block          <- Header
                / List
                / LinkDefinition
                / Paragraph
Header         <- '#'+ SPACE* !NEWLINE Words? SPACE* NEWLINE
List           <- ([-*]+ / [[:digit:]]+ [).]) (_ (List / Words))? NEWLINE
LinkDefinition <- LinkLabel ':' _? Uri (_ LinkTitle)? NEWLINE
Paragraph      <- Words (HardBreak Words)* NEWLINE+

# Inline elements
Words          <- StyledWords
                / LinkedWords
                / AnnotatedWords
                / PlainWords
StyledWords    <- '**' Words '**'
                / '*' Words '*'
                / '_' Words '_'
LinkedWords    <- '[' Words ']' '(' ((Uri _)? LinkTitle / Uri) ')'
                / '[' Words ']' LinkLabel
                / LinkLabel
AnnotatedWords <- '[' Words ']' '{' ![{}] PlainWords '}'
LinkLabel      <- '[' _? ![\[\]] PlainWords _? ']'
LinkTitle      <- '"' _? !'"' _? PlainWords _? '"'
                / "'" _? !"'" PlainWords _? "'"
                / "(" _? ![()] PlainWords _? ")"
PlainWords     <- PRINTABLES (_ PRINTABLES)*
Uri            <- '<' ![<>] PRINTABLES? '>'
                / ![<>] PRINTABLES
HardBreak      <- SPACE SPACE+ NEWLINE
_              <- SPACE+
                / SPACE? NEWLINE SPACE? SPACE? SPACE?

# Terminals
PRINTABLES     <- [[:graph:]]+
SPACE          <- ' '
NEWLINE        <- '\r\n'
                / '\n'
                / '\r'

# Semantic Markdown
AnnotatedWordsX <- '[' Words ']'
                   ('{' (SemWords / ![{}] PlainWords) '}')
SemWords        <- SEMPREFIX '<' ![<>] PRINTABLES '>'
                 / SEMPREFIX Curie
Curie           <- NAME? ':' NAME?
SEMPREFIX       <- [.#]