🏷️ RFC0003 - Simple node types (#43)

Author: rowanc1

.changeset/short-areas-spend.md

@@ -0,0 +1,5 @@
+---
+"oxa-types": patch
+---
+
+Add initial node types using RFC0003 (Code, InlineCode, Subscript, Superscript, ThematicBreak).

docs/schema/block.md

@@ -6,4 +6,4 @@
 Union of all block content types.
 
 
-Union of: @oxa:heading, @oxa:paragraph
+Union of: @oxa:code, @oxa:heading, @oxa:paragraph, @oxa:thematicbreak

docs/schema/code.md

@@ -0,0 +1,31 @@
+(oxa:code)=
+
+## Code
+
+
+A block of preformatted text, typically source code.
+
+
+__type__: _string_, ("Code")
+
+: The type discriminator for Code nodes.
+
+__id__: __string__
+
+: A unique identifier for the node.
+
+__classes__: __array__ ("string")
+
+: A list of class names for styling or semantics.
+
+__data__: __object__
+
+: Arbitrary key-value data attached to the node.
+
+__language__: __string__
+
+: The programming language of the code content.
+
+__value__: __string__
+
+: The code content.

docs/schema/inline.md

@@ -6,4 +6,4 @@
 Union of all inline content types.
 
 
-Union of: @oxa:text, @oxa:emphasis, @oxa:strong
+Union of: @oxa:text, @oxa:emphasis, @oxa:inlinecode, @oxa:strong, @oxa:subscript, @oxa:superscript

docs/schema/inlinecode.md

@@ -0,0 +1,31 @@
+(oxa:inlinecode)=
+
+## InlineCode
+
+
+Short fragments of code appearing within prose.
+
+
+__type__: _string_, ("InlineCode")
+
+: The type discriminator for InlineCode nodes.
+
+__id__: __string__
+
+: A unique identifier for the node.
+
+__classes__: __array__ ("string")
+
+: A list of class names for styling or semantics.
+
+__data__: __object__
+
+: Arbitrary key-value data attached to the node.
+
+__language__: __string__
+
+: The programming language of the code content.
+
+__value__: __string__
+
+: The code content.

docs/schema/subscript.md

@@ -0,0 +1,28 @@
+(oxa:subscript)=
+
+## Subscript
+
+
+Content rendered below the baseline (e.g. chemical formulae, variable indices).
+
+
+__type__: _string_, ("Subscript")
+
+: The type discriminator for Subscript nodes.
+
+__id__: __string__
+
+: A unique identifier for the node.
+
+__classes__: __array__ ("string")
+
+: A list of class names for styling or semantics.
+
+__data__: __object__
+
+: Arbitrary key-value data attached to the node.
+
+__children__: __array__ ("Inline")
+
+: The inline content to render as subscript.
+: See @oxa:inline

docs/schema/superscript.md

@@ -0,0 +1,28 @@
+(oxa:superscript)=
+
+## Superscript
+
+
+Content rendered above the baseline (e.g. exponents, ordinal suffixes).
+
+
+__type__: _string_, ("Superscript")
+
+: The type discriminator for Superscript nodes.
+
+__id__: __string__
+
+: A unique identifier for the node.
+
+__classes__: __array__ ("string")
+
+: A list of class names for styling or semantics.
+
+__data__: __object__
+
+: Arbitrary key-value data attached to the node.
+
+__children__: __array__ ("Inline")
+
+: The inline content to render as superscript.
+: See @oxa:inline

docs/schema/thematicbreak.md

@@ -0,0 +1,23 @@
+(oxa:thematicbreak)=
+
+## ThematicBreak
+
+
+A thematic or structural division between sections of content.
+
+
+__type__: _string_, ("ThematicBreak")
+
+: The type discriminator for ThematicBreak nodes.
+
+__id__: __string__
+
+: A unique identifier for the node.
+
+__classes__: __array__ ("string")
+
+: A list of class names for styling or semantics.
+
+__data__: __object__
+
+: Arbitrary key-value data attached to the node.

packages/oxa-types-py/src/oxa_types/__init__.py

@@ -12,6 +12,27 @@
 from pydantic import BaseModel, ConfigDict, Field
 
 
+class Code(BaseModel):
+    """A block of preformatted text, typically source code."""
+
+    model_config = ConfigDict(strict=True)
+
+    type: Literal["Code"] = "Code"
+    id: str | None = Field(
+        default=None, description="A unique identifier for the node."
+    )
+    classes: list[str] | None = Field(
+        default=None, description="A list of class names for styling or semantics."
+    )
+    data: dict[str, Any] | None = Field(
+        default=None, description="Arbitrary key-value data attached to the node."
+    )
+    language: str | None = Field(
+        default=None, description="The programming language of the code content."
+    )
+    value: str = Field(description="The code content.")
+
+
 class Document(BaseModel):
     """A document with metadata, title, and block content."""
 
@@ -73,6 +94,27 @@ class Heading(BaseModel):
     children: list["Inline"] = Field(description="The inline content of the heading.")
 
 
+class InlineCode(BaseModel):
+    """Short fragments of code appearing within prose."""
+
+    model_config = ConfigDict(strict=True)
+
+    type: Literal["InlineCode"] = "InlineCode"
+    id: str | None = Field(
+        default=None, description="A unique identifier for the node."
+    )
+    classes: list[str] | None = Field(
+        default=None, description="A list of class names for styling or semantics."
+    )
+    data: dict[str, Any] | None = Field(
+        default=None, description="Arbitrary key-value data attached to the node."
+    )
+    language: str | None = Field(
+        default=None, description="The programming language of the code content."
+    )
+    value: str = Field(description="The code content.")
+
+
 class Paragraph(BaseModel):
     """A paragraph of inline content."""
 
@@ -109,6 +151,46 @@ class Strong(BaseModel):
     children: list["Inline"] = Field(description="The inline content to emphasize.")
 
 
+class Subscript(BaseModel):
+    """Content rendered below the baseline (e.g. chemical formulae, variable indices)."""
+
+    model_config = ConfigDict(strict=True)
+
+    type: Literal["Subscript"] = "Subscript"
+    id: str | None = Field(
+        default=None, description="A unique identifier for the node."
+    )
+    classes: list[str] | None = Field(
+        default=None, description="A list of class names for styling or semantics."
+    )
+    data: dict[str, Any] | None = Field(
+        default=None, description="Arbitrary key-value data attached to the node."
+    )
+    children: list["Inline"] = Field(
+        description="The inline content to render as subscript."
+    )
+
+
+class Superscript(BaseModel):
+    """Content rendered above the baseline (e.g. exponents, ordinal suffixes)."""
+
+    model_config = ConfigDict(strict=True)
+
+    type: Literal["Superscript"] = "Superscript"
+    id: str | None = Field(
+        default=None, description="A unique identifier for the node."
+    )
+    classes: list[str] | None = Field(
+        default=None, description="A list of class names for styling or semantics."
+    )
+    data: dict[str, Any] | None = Field(
+        default=None, description="Arbitrary key-value data attached to the node."
+    )
+    children: list["Inline"] = Field(
+        description="The inline content to render as superscript."
+    )
+
+
 class Text(BaseModel):
     """A text node containing a string value."""
 
@@ -127,30 +209,62 @@ class Text(BaseModel):
     value: str = Field(description="The text content.")
 
 
+class ThematicBreak(BaseModel):
+    """A thematic or structural division between sections of content."""
+
+    model_config = ConfigDict(strict=True)
+
+    type: Literal["ThematicBreak"] = "ThematicBreak"
+    id: str | None = Field(
+        default=None, description="A unique identifier for the node."
+    )
+    classes: list[str] | None = Field(
+        default=None, description="A list of class names for styling or semantics."
+    )
+    data: dict[str, Any] | None = Field(
+        default=None, description="Arbitrary key-value data attached to the node."
+    )
+
+
 # Union of all block content types.
-Block = Annotated[Union[Heading, Paragraph], Field(discriminator="type")]
+Block = Annotated[
+    Union[Code, Heading, Paragraph, ThematicBreak], Field(discriminator="type")
+]
 
 
 # Union of all inline content types.
-Inline = Annotated[Union[Text, Emphasis, Strong], Field(discriminator="type")]
+Inline = Annotated[
+    Union[Text, Emphasis, InlineCode, Strong, Subscript, Superscript],
+    Field(discriminator="type"),
+]
 
 
 # Rebuild models to resolve forward references
+Code.model_rebuild()
 Document.model_rebuild()
 Emphasis.model_rebuild()
 Heading.model_rebuild()
+InlineCode.model_rebuild()
 Paragraph.model_rebuild()
 Strong.model_rebuild()
+Subscript.model_rebuild()
+Superscript.model_rebuild()
 Text.model_rebuild()
+ThematicBreak.model_rebuild()
 
 
 __all__ = [
     "Block",
+    "Code",
     "Document",
     "Emphasis",
     "Heading",
     "Inline",
+    "InlineCode",
     "Paragraph",
     "Strong",
+    "Subscript",
+    "Superscript",
     "Text",
+    "ThematicBreak",
 ]