core/encoding/entity

encoding_unicode_entity

Types

Error :: enum u8 {
	None                    = 0,
	Tokenizer_Is_Nil        = 1,
	Illegal_NUL_Character   = 2,
	Illegal_UTF_Encoding    = 3,
	Illegal_BOM             = 4,
	CDATA_Not_Terminated    = 5,
	Comment_Not_Terminated  = 6,
	Invalid_Entity_Encoding = 7,
}

Source

Tokenizer :: struct {
	r:           rune,
	w:           int,
	src:         string,
	offset:      int,
	read_offset: int,
}

Source

XML_Decode_Option :: enum u8 {
	// Do not decode & entities. It decodes by default. If given, overrides `Decode_CDATA`.
	No_Entity_Decode     = 0,
	// CDATA is unboxed.
	Unbox_CDATA          = 1,
	// Unboxed CDATA is decoded as well. Ignored if `.Unbox_CDATA` is not given.
	Decode_CDATA         = 2,
	// Comments are stripped.
	Comment_Strip        = 3,
	// Normalize whitespace
	Normalize_Whitespace = 4,
}

Source

Default: CDATA and comments are passed through unchanged.

XML_Decode_Options :: bit_set[XML_Decode_Option; u8]Source

Constants

CDATA_END :: "]]>"Source

CDATA_START :: "<![CDATA["Source

COMMENT_END :: "-->"Source

COMMENT_START :: "<!--"Source

MAX_RUNE_CODEPOINT :: int = int(unicode.MAX_RUNE)Source

XML_NAME_TO_RUNE_MAX_LENGTH :: 31Source

&CounterClockwiseContourIntegral;

XML_NAME_TO_RUNE_MIN_LENGTH :: 2Source

------ GENERATED ------ DO NOT EDIT ------ GENERATED ------ DO NOT EDIT ------ GENERATED ------ This file is generated from "https://github.com/w3c/xml-entities/blob/gh-pages/unicode.xml".

UPDATE:
		- Ensure the XML file was downloaded using "tests\core\download_assets.py", given the path to the "tests\assets" directory.
		- Run "core/unicode/tools/generate_entity_table.odin"

	Odin unicode generated tables: https://github.com/odin-lang/Odin/tree/master/core/encoding/entity

		Copyright David Carlisle 1999-2025

		Use and distribution of this code are permitted under the terms of the
		W3C Software Notice and License.
		http://www.w3.org/Consortium/Legal/2002/copyright-software-20021231.html



		This file is a collection of information about how to map
		Unicode entities to LaTeX, and various SGML/XML entity
		sets (ISO and MathML/HTML). A Unicode character may be mapped
		to several entities.

		Originally designed by Sebastian Rahtz in conjunction with
		Barbara Beeton for the STIX project

	See also: LICENSE_table.md
`&lt;`

Procedures

advance :: proc(t: ^Tokenizer) -> (err: Error)Source

decode_xml :: proc(input: string, options: XML_Decode_Options = XML_Decode_Options{}, allocator: mem.Allocator = context.allocator) -> (decoded: string, err: Error)

Source

Decode a string that may include SGML/XML/HTML entities. The caller has to free the result.

escape_html :: proc(s: string, allocator: mem.Allocator = context.allocator, loc = #caller_location) -> (output: string, was_allocation: bool)

Source

escape_html escapes special characters like '&' to become '&'. It escapes only 5 different characters: & ' < > and "

named_xml_entity_to_rune :: proc(name: string) -> (decoded: [2]rune, rune_count: int, ok: bool)Source

Input:

	entity_name - a string, like "copy" that describes a user-encoded Unicode entity as used in XML.

	Returns:
		"decoded"    - The decoded runes if found by name, or all zero otherwise.
		"rune_count" - The number of decoded runes
		"ok"         - true if found, false if not.

	IMPORTANT: XML processors (including browsers) treat these names as case-sensitive. So do we.

unescape_entity :: proc(s: string) -> (b: [8]u8, w: int, j: int)Source

Returns an unescaped string of an encoded XML/HTML entity.

unescape_html :: proc(s: string, allocator: mem.Allocator = context.allocator, loc = #caller_location) -> (output: string, was_allocation: bool, err: runtime.Allocator_Error)

Source

write_rune :: proc(b: ^Builder, r: rune) -> (res: int, err: io.Error)Source

write_string :: proc(b: ^Builder, s: string, loc = #caller_location) -> (n: int)Source

xml_decode_entity :: proc(entity: string) -> (decoded: [2]rune, rune_count: int, ok: bool)Source

encoding_unicode_entity

Types

Constants

Procedures

Find anything

Settings