mooncakes.io

cli
→
cmd
→
core
→
dom
→
linkify
→
markdown
→
parser
→
sanitize
→
selector
→
serializer
→
stream
→
tokenizer
→
transform
→
README
U
CliReadPlan
U
CliResult
U
DecideAction
U
DisallowedTagHandling
U
DoctypeInfo
U
FragmentContext
U
HtmlContext
U
HtmlError
U
HtmlToken
U
LinkMatch
U
LinkifyConfig
U
Node
U
NodeKind
U
ParseError
U
ParsedHtml
U
SanitizationPolicy
U
SanitizeTransformObserver
U
SelectorLimits
U
StreamDoctypeEvent
U
StreamEvent
U
StreamSink
U
StreamStartEvent
U
TagKind
U
TagToken
U
TokenizedHtml
U
TransformSpec
U
UnsafeHandling
U
UrlFilter
U
UrlHandling
U
UrlPolicy
U
UrlPolicyRule
U
UrlProxy
U
UrlRule
V
apply_transforms
V
cli_help
V
cli_read_plan
V
comment
V
css_preset_text
V
default_document_sanitization_policy
V
default_sanitization_policy
V
doctype
V
document
V
element
V
find_links
V
find_links_with_config
V
fragment
V
linkify_dom
V
matches
V
parse
V
parse_bytes
V
parse_fragment
V
query
V
query_one
V
run_cli_bytes
V
run_cli_with_reader
V
sanitize_dom
V
stream
V
stream_bytes
V
stream_bytes_each
V
stream_each
V
text
V
to_html
V
to_markdown
V
to_test_format
V
to_text
V
tokenize

README

bobzhang/html_parser/parser does not have a README file

#
FragmentContext

pub(all) struct FragmentContext {
  tag_name : String
  ns : String?
} derive(Eq, @moonbitlang/core/debug.Debug
Debug)

Context element used when parsing an HTML fragment.

The tag name is normalized to lowercase. ns can be used for foreign content contexts such as SVG or MathML.

#
FragmentContext::new

source

fn FragmentContext::new(tag_name : StringView, ns? : String) -> FragmentContext

Construct a fragment parsing context.

#
ParsedHtml

source

pub struct ParsedHtml {
  root : @bobzhang/html_parser/dom.Node
Node
  errors : Array[@bobzhang/html_parser/core.ParseError
ParseError]
  encoding : String?
} derive(@moonbitlang/core/debug.Debug
Debug)

Result of parsing HTML.

root is the document or fragment root. errors is populated when collect_errors=true or strict parsing observes an error. encoding is set by byte parsing APIs.

#
ParsedHtml::query

source

fn ParsedHtml::query(self : ParsedHtml, selector : StringView) -> Array[@bobzhang/html_parser/dom.Node
Node]

Return all descendants of the parsed root that match a CSS selector.

#
ParsedHtml::query_one

source

fn ParsedHtml::query_one(self : ParsedHtml, selector : StringView) -> @bobzhang/html_parser/dom.Node
Node?

Return the first descendant of the parsed root that matches a CSS selector.

#
ParsedHtml::to_html

source

fn ParsedHtml::to_html(self : ParsedHtml, pretty? : Bool, indent_size? : Int, context? : @bobzhang/html_parser/serializer.HtmlContext
HtmlContext, quote? : Char) -> String raise @bobzhang/html_parser/core.HtmlError
HtmlError

Serialize the parsed root node back to HTML.

This forwards to to_html on self.root.

#
ParsedHtml::to_markdown

source

fn ParsedHtml::to_markdown(self : ParsedHtml, html_passthrough? : Bool) -> String raise @bobzhang/html_parser/core.HtmlError
HtmlError

Render the parsed document or fragment root as Markdown.

This is equivalent to calling to_markdown on self.root.

#
ParsedHtml::to_text

source

fn ParsedHtml::to_text(self : ParsedHtml, separator? : String, strip? : Bool, separator_blocks_only? : Bool) -> String

Extract text from the parsed root node.

This forwards to to_text on self.root.

#
parse

source

fn parse(html : StringView, sanitize? : Bool, collect_errors? : Bool, strict? : Bool, scripting_enabled? : Bool, xml_coercion? : Bool, track_node_locations? : Bool) -> ParsedHtml raise @bobzhang/html_parser/core.HtmlError
HtmlError

Parse a full HTML document from a string.

The returned root is a document node with the usual html, head, and body scaffolding. Set sanitize=true to apply the default document sanitizer after parsing, collect_errors=true to keep parse diagnostics, and strict=true to raise @core.HtmlError::StrictMode on the first parse error.

#
parse_bytes

source

fn parse_bytes(input : BytesView, encoding? : String, sanitize? : Bool, collect_errors? : Bool, strict? : Bool, scripting_enabled? : Bool, xml_coercion? : Bool, track_node_locations? : Bool) -> ParsedHtml raise @bobzhang/html_parser/core.HtmlError
HtmlError

Decode and parse an HTML byte stream.

When encoding is absent, BOMs and <meta charset> declarations are sniffed before falling back to Windows-1252. The detected or requested encoding is stored in ParsedHtml.encoding.

#
parse_fragment

source

fn parse_fragment(html : StringView, context? : FragmentContext, sanitize? : Bool, collect_errors? : Bool, strict? : Bool, scripting_enabled? : Bool, xml_coercion? : Bool, track_node_locations? : Bool) -> ParsedHtml raise @bobzhang/html_parser/core.HtmlError
HtmlError

Parse an HTML fragment from a string.

context controls the fragment context element used by the tree builder. Without a context, the fragment is parsed into a generic fragment root. sanitize, collect_errors, strict, scripting_enabled, xml_coercion, and track_node_locations have the same meaning as in parse.