Skip to content

Add AST-based test detection for documentation formats #69

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
Copilot wants to merge 6 commits into
base: main
Choose a base branch
from
Draft

Add AST-based test detection for documentation formats #69

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
98b5744
Initial plan
Copilot Dec 5, 2025
e2f132f
Add AST-based test detection for documentation formats
Copilot Dec 5, 2025
e822963
Fix code review issues in AST-based detection
Copilot Dec 5, 2025
5a0f37c
Fix schema dereferencing for recursive AST schemas
Copilot Dec 5, 2025
70abaaf
Fix schema dereferencing for recursive AST schemas
Copilot Dec 5, 2025
e66b149
Optimize AST matching by pre-compiling regex patterns
Copilot Dec 5, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
343 changes: 343 additions & 0 deletions common/dist/schemas/config_v3.schema.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -707,11 +707,107 @@
"minItems": 1,
"items": {
"type": "object",
"anyOf": [
{
"required": [
"ast"
]
},
{
"required": [
"regex"
]
}
],
"properties": {
"name": {
"description": "Name of the markup definition",
"type": "string"
},
"ast": {
"description": "AST node matching configuration. When specified with regex, AST identifies candidate nodes first, then regex filters matched node content (AND operation).",
"type": "object",
"properties": {
"nodeType": {
"description": "The type of AST node to match (e.g., 'code', 'element', 'listing'). Can be a string or array of strings.",
"anyOf": [
{
"type": "string"
},
{
"type": "array",
"items": {
"type": "string"
}
}
]
},
"attributes": {
"description": "Attribute matchers. Values can be: exact string, regex pattern (/pattern/), array of options (any-of), or boolean (true=exists, false=not exists).",
"type": "object",
"additionalProperties": {
"anyOf": [
{
"type": "string"
},
{
"type": "boolean"
},
{
"type": "array",
"items": {
"type": "string"
}
}
]
}
},
"content": {
"description": "Pattern to match against the node's text content. Can be exact string or regex pattern.",
"anyOf": [
{
"type": "string"
},
{
"type": "boolean"
}
]
},
"children": {
"description": "Nested matchers for child nodes. All child matchers must match at least one child.",
"type": "array",
"items": {
"type": "object",
"description": "Configuration for matching AST nodes. Supports node type, attribute, content, and child matching.",
"properties": {
"nodeType": {},
"attributes": {},
"content": {},
"children": {},
"extract": {}
},
"title": "AST node match configuration"
}
},
"extract": {
"description": "Maps capture group variables ($1, $2, etc.) to node paths for value extraction.",
"type": "object",
"additionalProperties": {
"type": "string"
},
"examples": [
{
"$1": "attributes.lang",
"$2": "value"
},
{
"$1": "content"
}
]
}
},
"title": "AST node match configuration"
},
"regex": {
"description": "Regular expressions to match the markup type.",
"anyOf": [
Expand Down Expand Up @@ -8615,11 +8711,107 @@
},
"markupDefinition": {
"type": "object",
"anyOf": [
{
"required": [
"ast"
]
},
{
"required": [
"regex"
]
}
],
"properties": {
"name": {
"description": "Name of the markup definition",
"type": "string"
},
"ast": {
"description": "AST node matching configuration. When specified with regex, AST identifies candidate nodes first, then regex filters matched node content (AND operation).",
"type": "object",
"properties": {
"nodeType": {
"description": "The type of AST node to match (e.g., 'code', 'element', 'listing'). Can be a string or array of strings.",
"anyOf": [
{
"type": "string"
},
{
"type": "array",
"items": {
"type": "string"
}
}
]
},
"attributes": {
"description": "Attribute matchers. Values can be: exact string, regex pattern (/pattern/), array of options (any-of), or boolean (true=exists, false=not exists).",
"type": "object",
"additionalProperties": {
"anyOf": [
{
"type": "string"
},
{
"type": "boolean"
},
{
"type": "array",
"items": {
"type": "string"
}
}
]
}
},
"content": {
"description": "Pattern to match against the node's text content. Can be exact string or regex pattern.",
"anyOf": [
{
"type": "string"
},
{
"type": "boolean"
}
]
},
"children": {
"description": "Nested matchers for child nodes. All child matchers must match at least one child.",
"type": "array",
"items": {
"type": "object",
"description": "Configuration for matching AST nodes. Supports node type, attribute, content, and child matching.",
"properties": {
"nodeType": {},
"attributes": {},
"content": {},
"children": {},
"extract": {}
},
"title": "AST node match configuration"
}
},
"extract": {
"description": "Maps capture group variables ($1, $2, etc.) to node paths for value extraction.",
"type": "object",
"additionalProperties": {
"type": "string"
},
"examples": [
{
"$1": "attributes.lang",
"$2": "value"
},
{
"$1": "content"
}
]
}
},
"title": "AST node match configuration"
},
"regex": {
"description": "Regular expressions to match the markup type.",
"anyOf": [
Expand Down Expand Up @@ -15918,6 +16110,84 @@
},
"title": "Markup definition"
},
"astNodeMatch": {
"type": "object",
"description": "Configuration for matching AST nodes. Supports node type, attribute, content, and child matching.",
"properties": {
"nodeType": {
"description": "The type of AST node to match (e.g., 'code', 'element', 'listing'). Can be a string or array of strings.",
"anyOf": [
{
"type": "string"
},
{
"type": "array",
"items": {
"type": "string"
}
}
]
},
"attributes": {
"description": "Attribute matchers. Values can be: exact string, regex pattern (/pattern/), array of options (any-of), or boolean (true=exists, false=not exists).",
"type": "object",
"additionalProperties": {
"anyOf": [
{
"type": "string"
},
{
"type": "boolean"
},
{
"type": "array",
"items": {
"type": "string"
}
}
]
}
},
"content": {
"description": "Pattern to match against the node's text content. Can be exact string or regex pattern.",
"anyOf": [
{
"type": "string"
},
{
"type": "boolean"
}
]
},
"children": {
"description": "Nested matchers for child nodes. All child matchers must match at least one child.",
"type": "array",
"items": {
"type": "object",
"description": "Configuration for matching AST nodes. Supports node type, attribute, content, and child matching.",
"properties": {},
"title": "AST node match configuration"
}
},
"extract": {
"description": "Maps capture group variables ($1, $2, etc.) to node paths for value extraction.",
"type": "object",
"additionalProperties": {
"type": "string"
},
"examples": [
{
"$1": "attributes.lang",
"$2": "value"
},
{
"$1": "content"
}
]
}
},
"title": "AST node match configuration"
},
"markupActionString": {
"type": "string",
"enum": [
Expand Down Expand Up @@ -16159,6 +16429,79 @@
},
{
"crawl": true
},
{
"fileTypes": [
{
"extends": "markdown",
"extensions": [
"md"
],
"markup": [
{
"name": "bashCodeBlock",
"ast": {
"nodeType": "code",
"attributes": {
"lang": [
"bash",
"sh"
]
},
"extract": {
"$1": "attributes.lang",
"$2": "value"
}
},
"actions": [
{
"runCode": {
"language": "$1",
"code": "$2"
}
}
]
}
]
}
]
},
{
"fileTypes": [
{
"extends": "dita",
"extensions": [
"dita",
"xml"
],
"markup": [
{
"name": "ditaCodeblock",
"ast": {
"nodeType": "element",
"attributes": {
"tagName": "codeblock",
"outputclass": [
"bash",
"shell"
]
},
"extract": {
"$1": "attributes.outputclass",
"$2": "content"
}
},
"actions": [
{
"runShell": {
"command": "$2"
}
}
]
}
]
}
]
}
]
}
Loading