README
- ::slugAlertKind::slug
T
Block
T
BulletMarker
T
CodeBlockInfo
T
DefinitionItem
T
Document
T
EmphasisMarker
T
FenceMarker
T
Frontmatter
T
HardBreakStyle
T
HeadingStyle
T
Inline
T
LinkDefinition
T
ListItem
T
MarkdownAttribute
T
OrderedDelimiter
T
ParseResult
T
ReferenceStyle
- ::defaultRenderOptions::default
- ::with_highlighterRenderOptions::with_highlighter
- ::with_math_block_rendererRenderOptions::with_math_block_renderer
- ::with_simple_highlighterRenderOptions::with_simple_highlighter
- ::advanceScanner::advance
- ::consumeScanner::consume
- ::consume_strScanner::consume_str
- ::count_charScanner::count_char
- ::count_leading_spacesScanner::count_leading_spaces
- ::is_blank_lineScanner::is_blank_line
- ::is_eofScanner::is_eof
- ::matchesScanner::matches
- ::newScanner::new
- ::peekScanner::peek
- ::peek_atScanner::peek_at
- ::read_lineScanner::read_line
- ::remainingScanner::remaining
- ::restoreScanner::restore
- ::saveScanner::save
- ::skip_lineScanner::skip_line
- ::skip_spacesScanner::skip_spaces
- ::substringScanner::substring
- ::emptySpan::empty
- ::newSpan::new
T
TableAlign
T
TableCell
- ::emptyTrivia::empty
- ::newTrivia::new
V
char_is
V
char_is_digit
V
is_alphanumeric
V
is_digit
V
is_letter
V
is_punctuation
V
is_unicode_punctuation
V
is_unicode_whitespace
V
is_whitespace
V
parse
V
parse_code_block_info
V
parse_inlines

mdparse

Markdown 语法解析：把 Markdown 源文解析成 AST（fork 自 mizchi/markdown，仅保留解析链路）

Download zip

Author

NoahLiu

Version

0.1.0

License

MIT

Repository

github.com/lb091188/moonbit-native-gui

Last updated

8 hours ago

Downloads

#mdparse — Markdown 语法解析

把 Markdown 源文解析成 AST。只做解析：不含渲染、序列化、HTML 输出、增量解析。

派生自 mizchi/markdown 0.8.3，保留其解析链路。来源、删改范围与授权见 NOTICE.md 与 LICENSE。

#用法

作为模块依赖：

import {
  "NoahLiu/mdparse@0.1.0",
}

///|
fn example() -> Unit {
  let res = @mdparse.parse("# 标题\n\n段落含 **粗体** 与 [链接](https://example.com)。\n")
  for block in res.document.children {
    println(block)
  }
  // 引用式链接的文档级定义：label → url
  for def in res.definitions {
    println("\{def.label} => \{def.url}")
  }
}

parse(source, wikilinks? = false) 返回 ParseResult：

字段	类型	含义
document	Document	文档根，children : Array[Block]
definitions	Array[LinkDefinition]	引用式链接/图片的文档级定义（label、url）

#支持的语法

块级：ATX/Setext 标题、围栏代码（info 串）、缩进代码、引用、GFM 提示块、有序/无序列表（含 start）、任务列表、表格（列对齐）、定义列表、分隔线、脚注定义、数学块、HTML 块、:::name 指令块、frontmatter
行内：粗体、斜体、删除线、行内代码、链接、引用式链接、自动链接、图片、引用式图片、脚注引用、软/硬换行、行内 HTML、行内数学、[[WikiLink]]、行内指令

#AST

Block 与 Inline 两个枚举是解析结果的全部形态；渲染、遍历、测试都按它们模式匹配。字段以 types.mbt 为准。

#平台

supported_targets = "js+wasm+wasm-gc+native"，与上游一致。纯 MoonBit，无第三方依赖（只用 moonbitlang/core），不依赖任何宿主能力，可作为通用 Markdown 解析层单独发布或复用到其他项目。

AlertKind

source

pub(all) enum AlertKind {
  Note
  Tip
  Important
  Warning
  Caution
} derive(Eq, @moonbitlang/core/debug.Debug
Debug)

GitHub alert kind (> [!NOTE], etc.).

impl Show for AlertKind

AlertKind::slug

source

fn AlertKind::slug(self : AlertKind) -> String

Stable lowercase name used by renderers and JSON APIs.

Block

source

pub(all) enum Block {
  ThematicBreak(marker~ : Char, count~ : Int, span~ : Span, leading_trivia~ : Trivia, trailing_trivia~ : Trivia)
  Heading(level~ : Int, style~ : HeadingStyle, children~ : Array[Inline], closing_hashes~ : Int, span~ : Span, leading_trivia~ : Trivia, trailing_trivia~ : Trivia)
  Paragraph(children~ : Array[Inline], span~ : Span, leading_trivia~ : Trivia, trailing_trivia~ : Trivia)
  FencedCode(fence_marker~ : FenceMarker, fence_length~ : Int, info~ : String, code~ : String, indent~ : Int, span~ : Span, leading_trivia~ : Trivia, trailing_trivia~ : Trivia)
  MathBlock(value~ : String, fence_length~ : Int, span~ : Span, leading_trivia~ : Trivia, trailing_trivia~ : Trivia)
  Directive(name~ : String, meta~ : String, children~ : Array[Block], fence_length~ : Int, span~ : Span, leading_trivia~ : Trivia, trailing_trivia~ : Trivia)
  DefinitionList(items~ : Array[DefinitionItem], span~ : Span, leading_trivia~ : Trivia, trailing_trivia~ : Trivia)
  Attributed(block~ : Block, attributes~ : Array[MarkdownAttribute], span~ : Span)
  IndentedCode(code~ : String, span~ : Span, leading_trivia~ : Trivia, trailing_trivia~ : Trivia)
  Blockquote(children~ : Array[Block], span~ : Span, leading_trivia~ : Trivia, trailing_trivia~ : Trivia)
  Alert(kind~ : AlertKind, children~ : Array[Block], span~ : Span, leading_trivia~ : Trivia, trailing_trivia~ : Trivia)
  BulletList(marker~ : BulletMarker, tight~ : Bool, items~ : Array[ListItem], span~ : Span, leading_trivia~ : Trivia, trailing_trivia~ : Trivia)
  OrderedList(start~ : Int, delimiter~ : OrderedDelimiter, tight~ : Bool, items~ : Array[ListItem], span~ : Span, leading_trivia~ : Trivia, trailing_trivia~ : Trivia)
  HtmlBlock(html~ : String, span~ : Span, leading_trivia~ : Trivia, trailing_trivia~ : Trivia)
  Table(header~ : Array[TableCell], alignments~ : Array[TableAlign], rows~ : Array[Array[TableCell]], span~ : Span, leading_trivia~ : Trivia, trailing_trivia~ : Trivia)
  BlankLines(count~ : Int, span~ : Span)
  FootnoteDefinition(label~ : String, children~ : Array[Block], span~ : Span, leading_trivia~ : Trivia, trailing_trivia~ : Trivia)
}

Block-level nodes

BulletMarker

source

pub(all) enum BulletMarker {
  Dash
  Asterisk
  Plus
} derive(Eq, @moonbitlang/core/debug.Debug
Debug)

List marker for unordered lists: -, *, +

impl Show for BulletMarker

CodeBlockInfo

source

pub(all) struct CodeBlockInfo {
  lang : String
  filename : String
  meta : String
}

Parsed info string from code block fence.

Format: "lang:filename {meta}"

Examples:

"javascript" → { lang: "javascript", filename: "", meta: "" }
"js:app.js" → { lang: "js", filename: "app.js", meta: "" }
"ts:index.ts {highlight=[1,3]}" → { lang: "ts", filename: "index.ts", meta: "{highlight=[1,3]}" }

DefinitionItem

source

pub(all) struct DefinitionItem {
  term : Array[Inline]
  definitions : Array[Array[Inline]]
}

One term and one or more inline definitions in a definition list.

Document

source

pub(all) struct Document {
  frontmatter : Frontmatter?
  children : Array[Block]
  definitions : Array[LinkDefinition]
  span : Span
}

Document root

EmphasisMarker

source

pub(all) enum EmphasisMarker {
  Asterisk
  Underscore
} derive(Eq, @moonbitlang/core/debug.Debug
Debug)

Emphasis marker: * or _

impl Show for EmphasisMarker

FenceMarker

source

pub(all) enum FenceMarker {
  Backtick
  Tilde
} derive(Eq, @moonbitlang/core/debug.Debug
Debug)

Fence marker for code blocks: ``` or ~~~

impl Show for FenceMarker

Frontmatter

source

pub(all) struct Frontmatter {
  raw : String
  entries : Array[(String, String)]
  span : Span
}

Frontmatter (YAML)

HardBreakStyle

source

pub(all) enum HardBreakStyle {
  TwoSpaces
  Backslash
} derive(Eq, @moonbitlang/core/debug.Debug
Debug)

Hard break style

impl Show for HardBreakStyle

HeadingStyle

source

pub(all) enum HeadingStyle {
  Atx
  Setext
} derive(Eq, @moonbitlang/core/debug.Debug
Debug)

Heading style

impl Show for HeadingStyle

Inline

source

pub(all) enum Inline {
  Text(content~ : String, span~ : Span)
  SoftBreak(span~ : Span)
  HardBreak(style~ : HardBreakStyle, span~ : Span)
  Emphasis(marker~ : EmphasisMarker, children~ : Array[Inline], span~ : Span)
  Strong(marker~ : EmphasisMarker, children~ : Array[Inline], span~ : Span)
  Strikethrough(children~ : Array[Inline], span~ : Span)
  Code(content~ : String, backtick_count~ : Int, span~ : Span)
  Directive(name~ : String, label~ : String, attributes~ : Array[MarkdownAttribute], span~ : Span)
  WikiLink(target~ : String, label~ : String, fragment~ : String, span~ : Span)
  Link(children~ : Array[Inline], url~ : String, title~ : String, span~ : Span)
  RefLink(children~ : Array[Inline], label~ : String, style~ : ReferenceStyle, span~ : Span)
  Autolink(url~ : String, is_email~ : Bool, span~ : Span)
  Image(alt~ : String, url~ : String, title~ : String, span~ : Span)
  RefImage(alt~ : String, label~ : String, style~ : ReferenceStyle, span~ : Span)
  HtmlInline(html~ : String, span~ : Span)
  FootnoteReference(label~ : String, span~ : Span)
}

Inline-level nodes

LinkDefinition

source

pub(all) struct LinkDefinition {
  label : String
  url : String
  title : String
  span : Span
}

Link reference definition [label]: url "title"

ListItem

source

pub(all) struct ListItem {
  children : Array[Block]
  checked : Bool?
  marker_offset : Int
  content_offset : Int
  span : Span
}

List item

MarkdownAttribute

source

pub(all) struct MarkdownAttribute {
  name : String
  value : String
} derive(Eq, @moonbitlang/core/debug.Debug
Debug)

One normalized block attribute from {#id .class key=value}.

OrderedDelimiter

source

pub(all) enum OrderedDelimiter {
  Dot
  Paren
} derive(Eq, @moonbitlang/core/debug.Debug
Debug)

Ordered list delimiter: . or )

impl Show for OrderedDelimiter

ParseResult

source

pub(all) struct ParseResult {
  document : Document
  definitions : Array[LinkDefinition]
}

Parse result

ReferenceStyle

source

pub(all) enum ReferenceStyle {
  Full
  Collapsed
  Shortcut
} derive(Eq, @moonbitlang/core/debug.Debug
Debug)

Syntax used by a link or image reference.

RenderOptions

source

pub struct RenderOptions {
  code_highlighter : (CodeBlockInfo, String) -> String?
  math_block_renderer : (String) -> String?
}

Render options with plugin support

RenderOptions::default

source

fn RenderOptions::default() -> RenderOptions

Create default render options

RenderOptions::with_highlighter

source

fn RenderOptions::with_highlighter(highlighter : (CodeBlockInfo, String) -> String) -> RenderOptions

Create render options with code highlighter

RenderOptions::with_math_block_renderer

source

fn RenderOptions::with_math_block_renderer(self : RenderOptions, renderer : (String) -> String) -> RenderOptions

The hook result is treated as trusted HTML; escaping belongs to the hook.

RenderOptions::with_simple_highlighter

source

fn RenderOptions::with_simple_highlighter(highlighter : (String, String) -> String) -> RenderOptions

Create render options with simple highlighter (lang, code) -> String

Scanner

source

pub(all) struct Scanner {
  source : String
  chars : Array[Char]
  pos : Int
  len : Int
  utf16_offsets : Array[Int]?
}

Scanner state - uses UTF-16 indexing directly for BMP input and Array[Char] for non-BMP input. Handles Unicode correctly by tracking UTF-16 offsets for non-BMP characters.

Scanner::advance

source

fn Scanner::advance(self : Scanner, n : Int) -> Unit

Advance position by n characters

Scanner::consume

source

fn Scanner::consume(self : Scanner) -> Char?

Consume and return current character (O(1))

Scanner::consume_str

source

fn Scanner::consume_str(self : Scanner, s : String) -> Bool

Match and consume a string

Scanner::count_char

source

fn Scanner::count_char(self : Scanner, c : Char) -> Int

Count consecutive occurrences of a character from current position - O(1) per char

Scanner::count_leading_spaces

source

fn Scanner::count_leading_spaces(self : Scanner) -> Int

Count leading spaces (without advancing) - O(1) per char

Scanner::is_blank_line

source

fn Scanner::is_blank_line(self : Scanner) -> Bool

Check if current line is blank (only whitespace) - O(1) per char

Scanner::is_eof

source

fn Scanner::is_eof(self : Scanner) -> Bool

Check if at end of input

Scanner::matches

source

fn Scanner::matches(self : Scanner, s : String) -> Bool

Match a string at current position - optimized with Array[Char]

Scanner::new

source

fn Scanner::new(source : String) -> Scanner

Create a new scanner

Scanner::peek

source

fn Scanner::peek(self : Scanner) -> Char?

Peek current character (O(1) with Array[Char])

Scanner::peek_at

source

fn Scanner::peek_at(self : Scanner, offset : Int) -> Char?

Peek character at offset from current position (O(1))

Scanner::read_line

source

fn Scanner::read_line(self : Scanner) -> String

Read until end of line (not consuming newline) - O(1) per char

Scanner::remaining

source

fn Scanner::remaining(self : Scanner) -> String

Get remaining substring from current position

Scanner::restore

source

fn Scanner::restore(self : Scanner, pos : Int) -> Unit

Restore to saved position

Scanner::save

source

fn Scanner::save(self : Scanner) -> Int

Save current position

Scanner::skip_line

source

fn Scanner::skip_line(self : Scanner) -> Unit

Skip to next line (consuming newline if present) - O(1) per char

Scanner::skip_spaces

source

fn Scanner::skip_spaces(self : Scanner) -> Int

Skip whitespace (space and tab only) - O(1) per char

Scanner::substring

source

fn Scanner::substring(self : Scanner, start : Int, end : Int) -> String

Get substring from start to end position (code point indices)

Span

source

pub(all) struct Span {
  from : Int
  to : Int
} derive(Eq, @moonbitlang/core/debug.Debug
Debug)

Using #valtype to avoid heap allocation for this frequently-used small struct

impl Show for Span

Span::empty

source

fn Span::empty() -> Span

Empty span (for synthetic nodes)

Span::new

source

fn Span::new(from : Int, to : Int) -> Span

Create a span

TableAlign

source

pub(all) enum TableAlign {
  Left
  Center
  Right
  None
} derive(Eq, @moonbitlang/core/debug.Debug
Debug)

Table alignment

impl Show for TableAlign

TableCell

source

pub(all) struct TableCell {
  children : Array[Inline]
  span : Span
}

Table cell

Trivia

source

pub(all) struct Trivia {
  content : String
} derive(Eq, @moonbitlang/core/debug.Debug
Debug)

Trivia represents non-semantic characters that should be preserved

impl Show for Trivia

Trivia::empty

source

fn Trivia::empty() -> Trivia

Trivia::new

source

fn Trivia::new(content : String) -> Trivia

char_is

source

fn char_is(opt : Char?, c : Char) -> Bool

Check if char option matches specific char

char_is_digit

source

fn char_is_digit(opt : Char?) -> Bool

Check if char option is a digit

is_alphanumeric

source

fn is_alphanumeric(c : Char) -> Bool

Check if character is alphanumeric

is_digit

source

fn is_digit(c : Char) -> Bool

Check if character is a digit

is_letter

source

fn is_letter(c : Char) -> Bool

Check if character is ASCII letter

is_punctuation

source

fn is_punctuation(c : Char) -> Bool

Check if character is a punctuation mark

is_unicode_punctuation

source

fn is_unicode_punctuation(c : Char) -> Bool

A "Unicode punctuation character" as CommonMark 0.31.2 defines it: anything in a punctuation (P*) or symbol (S*) general category.

The ranges below cover the blocks that actually carry punctuation and symbols; letters, digits and marks are deliberately excluded so that flanking is decided correctly for ordinary text.

is_unicode_whitespace

source

fn is_unicode_whitespace(c : Char) -> Bool

A "Unicode whitespace character" as CommonMark defines it: anything in the Zs general category, plus tab, line feed, form feed and carriage return.

is_whitespace

source

fn is_whitespace(c : Char) -> Bool

Check if character is ASCII whitespace

parse

source

fn parse(source : String, strict? : Bool, wikilinks? : Bool) -> ParseResult

Parse markdown source into CST.

strict is accepted for backwards compatibility; the parser always follows the CommonMark rules now.

parse_code_block_info

source

fn parse_code_block_info(info : String) -> CodeBlockInfo

Parse code block info string into components

parse_inlines

source

fn parse_inlines(text : String, strict? : Bool, wikilinks? : Bool) -> Array[Inline]

Parse inline content from text.

strict is accepted for backwards compatibility; the parser now always follows the CommonMark algorithm.

Site source Report issue Packages Build queue Skills Statistics

mdparse

#mdparse — Markdown 语法解析

#用法

#支持的语法

#AST

#平台

#AlertKind

#AlertKind::slug

#Block

#BulletMarker

#CodeBlockInfo

#DefinitionItem

#Document

#EmphasisMarker

#FenceMarker

#Frontmatter

#HardBreakStyle

#HeadingStyle

#Inline

#LinkDefinition

#ListItem

#MarkdownAttribute

#OrderedDelimiter

#ParseResult

#ReferenceStyle

#RenderOptions

#RenderOptions::default

#RenderOptions::with_highlighter

#RenderOptions::with_math_block_renderer

#RenderOptions::with_simple_highlighter

#Scanner

#Scanner::advance

#Scanner::consume

#Scanner::consume_str

#Scanner::count_char

#Scanner::count_leading_spaces

#Scanner::is_blank_line

#Scanner::is_eof

#Scanner::matches

#Scanner::new

#Scanner::peek

#Scanner::peek_at

#Scanner::read_line

#Scanner::remaining

#Scanner::restore

#Scanner::save

#Scanner::skip_line

#Scanner::skip_spaces

#Scanner::substring

#Span

#Span::empty

#Span::new

#TableAlign

#TableCell

#Trivia

#Trivia::empty

#Trivia::new

#char_is

#char_is_digit

#is_alphanumeric

#is_digit

#is_letter

#is_punctuation

#is_unicode_punctuation

#is_unicode_whitespace

#is_whitespace

#parse

#parse_code_block_info

#parse_inlines

Source Files

AlertKind

AlertKind::slug

Block

BulletMarker

CodeBlockInfo

DefinitionItem

Document

EmphasisMarker

FenceMarker

Frontmatter

HardBreakStyle

HeadingStyle

Inline

LinkDefinition

ListItem

MarkdownAttribute

OrderedDelimiter

ParseResult

ReferenceStyle

RenderOptions

RenderOptions::default

RenderOptions::with_highlighter

RenderOptions::with_math_block_renderer

RenderOptions::with_simple_highlighter

Scanner

Scanner::advance

Scanner::consume

Scanner::consume_str

Scanner::count_char

Scanner::count_leading_spaces

Scanner::is_blank_line

Scanner::is_eof

Scanner::matches

Scanner::new

Scanner::peek

Scanner::peek_at

Scanner::read_line

Scanner::remaining

Scanner::restore

Scanner::save

Scanner::skip_line

Scanner::skip_spaces

Scanner::substring

Span

Span::empty

Span::new

TableAlign

TableCell

Trivia

Trivia::empty

Trivia::new

char_is

char_is_digit

is_alphanumeric

is_digit

is_letter

is_punctuation

is_unicode_punctuation

is_unicode_whitespace

is_whitespace

parse

parse_code_block_info

parse_inlines