feat: expand ContentCategory to universal 6-category set for highlight()
Replace document-centric categories (prose/heading/code/label) with a universal set that works across documents, code, and UI: - title: headings, identifiers, labels, JSON keys - annotation: comments, docstrings, captions, alt text - content: paragraphs, list items, flowing text - value: string literals, numbers, form values - code: unparsed code blocks - structural: keywords, operators, punctuation Built-in extractors now produce title/content/code. All 6 categories are available for custom parsers (e.g. tree-sitter). Also adds inline code detection in Markdown: backtick spans within prose lines are split into separate code/content segments.
This commit is contained in:
parent
6c27f9f7fd
commit
ff80b87a0a
6 changed files with 699 additions and 651 deletions
File diff suppressed because it is too large
Load diff
354
src/brainy.ts
354
src/brainy.ts
File diff suppressed because it is too large
Load diff
|
|
@ -83,11 +83,12 @@ export interface Result<T = any> {
|
||||||
// Score transparency
|
// Score transparency
|
||||||
explanation?: ScoreExplanation
|
explanation?: ScoreExplanation
|
||||||
|
|
||||||
// Match visibility (v7.8.0) - shows what matched in hybrid search
|
// Match visibility - shows what matched in hybrid search
|
||||||
textMatches?: string[] // Query words found in entity (e.g., ["david", "warrior"])
|
textMatches?: string[] // Query words found in entity (e.g., ["david", "warrior"])
|
||||||
textScore?: number // Normalized text match score (0-1)
|
textScore?: number // Normalized text match score (0-1)
|
||||||
semanticScore?: number // Semantic similarity score (0-1)
|
semanticScore?: number // Semantic similarity score (0-1)
|
||||||
matchSource?: 'text' | 'semantic' | 'both' // Where this result came from
|
matchSource?: 'text' | 'semantic' | 'both' // Where this result came from
|
||||||
|
rrfScore?: number // Raw RRF fusion score (for advanced ranking analysis)
|
||||||
}
|
}
|
||||||
|
|
||||||
/**
|
/**
|
||||||
|
|
@ -188,7 +189,7 @@ export interface FindParams<T = any> {
|
||||||
offset?: number // Skip N results
|
offset?: number // Skip N results
|
||||||
cursor?: string // Cursor-based pagination
|
cursor?: string // Cursor-based pagination
|
||||||
|
|
||||||
// Sorting (v4.5.4)
|
// Sorting
|
||||||
orderBy?: string // Field to sort by (e.g., 'createdAt', 'title', 'metadata.priority')
|
orderBy?: string // Field to sort by (e.g., 'createdAt', 'title', 'metadata.priority')
|
||||||
order?: 'asc' | 'desc' // Sort direction: 'asc' (default) or 'desc'
|
order?: 'asc' | 'desc' // Sort direction: 'asc' (default) or 'desc'
|
||||||
|
|
||||||
|
|
@ -196,10 +197,10 @@ export interface FindParams<T = any> {
|
||||||
mode?: SearchMode // Search strategy
|
mode?: SearchMode // Search strategy
|
||||||
explain?: boolean // Return scoring explanation
|
explain?: boolean // Return scoring explanation
|
||||||
includeRelations?: boolean // Include entity relationships
|
includeRelations?: boolean // Include entity relationships
|
||||||
excludeVFS?: boolean // v4.7.0: Exclude VFS entities from results (default: false - VFS included)
|
excludeVFS?: boolean // Exclude VFS entities from results (default: false - VFS included)
|
||||||
service?: string // Multi-tenancy filter
|
service?: string // Multi-tenancy filter
|
||||||
|
|
||||||
// Hybrid search options (v7.7.0)
|
// Hybrid search options
|
||||||
searchMode?: 'auto' | 'text' | 'semantic' | 'vector' | 'hybrid' // Search strategy: auto (default), text-only, semantic/vector-only, or explicit hybrid
|
searchMode?: 'auto' | 'text' | 'semantic' | 'vector' | 'hybrid' // Search strategy: auto (default), text-only, semantic/vector-only, or explicit hybrid
|
||||||
hybridAlpha?: number // Weight between text (0.0) and semantic (1.0) search, default: auto-detected by query length
|
hybridAlpha?: number // Weight between text (0.0) and semantic (1.0) search, default: auto-detected by query length
|
||||||
|
|
||||||
|
|
@ -252,7 +253,7 @@ export interface SimilarParams<T = any> {
|
||||||
type?: NounType | NounType[] // Restrict to types
|
type?: NounType | NounType[] // Restrict to types
|
||||||
where?: Partial<T> // Additional filters
|
where?: Partial<T> // Additional filters
|
||||||
service?: string // Multi-tenancy
|
service?: string // Multi-tenancy
|
||||||
excludeVFS?: boolean // v4.7.0: Exclude VFS entities (default: false - VFS included)
|
excludeVFS?: boolean // Exclude VFS entities (default: false - VFS included)
|
||||||
}
|
}
|
||||||
|
|
||||||
/**
|
/**
|
||||||
|
|
@ -289,8 +290,8 @@ export interface SimilarParams<T = any> {
|
||||||
* })
|
* })
|
||||||
* ```
|
* ```
|
||||||
*
|
*
|
||||||
* @since v4.1.3 - Fixed bug where calling without parameters returned empty array
|
* Fixed bug where calling without parameters returned empty array
|
||||||
* @since v4.1.3 - Added string ID shorthand syntax
|
* Added string ID shorthand syntax
|
||||||
*/
|
*/
|
||||||
export interface GetRelationsParams {
|
export interface GetRelationsParams {
|
||||||
/**
|
/**
|
||||||
|
|
@ -376,7 +377,7 @@ export interface DeleteManyParams {
|
||||||
where?: any // Delete by metadata
|
where?: any // Delete by metadata
|
||||||
limit?: number // Max to delete (safety)
|
limit?: number // Max to delete (safety)
|
||||||
onProgress?: (done: number, total: number) => void
|
onProgress?: (done: number, total: number) => void
|
||||||
continueOnError?: boolean // v6.2.0: Continue processing if a delete fails
|
continueOnError?: boolean // Continue processing if a delete fails
|
||||||
}
|
}
|
||||||
|
|
||||||
/**
|
/**
|
||||||
|
|
@ -403,7 +404,7 @@ export interface BatchResult<T = any> {
|
||||||
duration: number // Time taken in ms
|
duration: number // Time taken in ms
|
||||||
}
|
}
|
||||||
|
|
||||||
// ============= Import Progress (v4.5.0) =============
|
// ============= Import Progress =============
|
||||||
|
|
||||||
/**
|
/**
|
||||||
* Import stage enumeration
|
* Import stage enumeration
|
||||||
|
|
@ -435,7 +436,6 @@ export type ImportStatus =
|
||||||
* - Time estimates
|
* - Time estimates
|
||||||
* - Performance metrics
|
* - Performance metrics
|
||||||
*
|
*
|
||||||
* @since v4.5.0
|
|
||||||
*/
|
*/
|
||||||
export interface ImportProgress {
|
export interface ImportProgress {
|
||||||
// Overall Progress
|
// Overall Progress
|
||||||
|
|
@ -540,7 +540,7 @@ export interface ImportResult {
|
||||||
/**
|
/**
|
||||||
* Options for brain.get() entity retrieval
|
* Options for brain.get() entity retrieval
|
||||||
*
|
*
|
||||||
* **Performance Optimization (v5.11.1)**:
|
* **Performance Optimization**:
|
||||||
* By default, brain.get() loads ONLY metadata (not vectors), resulting in:
|
* By default, brain.get() loads ONLY metadata (not vectors), resulting in:
|
||||||
* - **76-81% faster** reads (10ms vs 43ms for metadata-only)
|
* - **76-81% faster** reads (10ms vs 43ms for metadata-only)
|
||||||
* - **95% less bandwidth** (300 bytes vs 6KB per entity)
|
* - **95% less bandwidth** (300 bytes vs 6KB per entity)
|
||||||
|
|
@ -573,7 +573,6 @@ export interface ImportResult {
|
||||||
* await vfs.readFile('/file.txt') // 53ms → 10ms (81% faster)
|
* await vfs.readFile('/file.txt') // 53ms → 10ms (81% faster)
|
||||||
* ```
|
* ```
|
||||||
*
|
*
|
||||||
* @since v5.11.1
|
|
||||||
*/
|
*/
|
||||||
export interface GetOptions {
|
export interface GetOptions {
|
||||||
/**
|
/**
|
||||||
|
|
@ -635,7 +634,7 @@ export type AggregateMetric =
|
||||||
// ============= Configuration =============
|
// ============= Configuration =============
|
||||||
|
|
||||||
/**
|
/**
|
||||||
* Integration Hub configuration (v7.4.0)
|
* Integration Hub configuration
|
||||||
*
|
*
|
||||||
* Enables external tool integrations: Excel, Power BI, Google Sheets, etc.
|
* Enables external tool integrations: Excel, Power BI, Google Sheets, etc.
|
||||||
* Works in all environments with zero external dependencies.
|
* Works in all environments with zero external dependencies.
|
||||||
|
|
@ -722,18 +721,18 @@ export interface BrainyConfig {
|
||||||
batchWrites?: boolean // Enable write batching for better performance
|
batchWrites?: boolean // Enable write batching for better performance
|
||||||
maxConcurrentOperations?: number // Limit concurrent file operations
|
maxConcurrentOperations?: number // Limit concurrent file operations
|
||||||
|
|
||||||
// HNSW persistence mode (v6.2.8)
|
// HNSW persistence mode
|
||||||
// Controls when HNSW graph connections are persisted to storage
|
// Controls when HNSW graph connections are persisted to storage
|
||||||
// - 'immediate': Persist on every add (slow but durable, default for filesystem)
|
// - 'immediate': Persist on every add (slow but durable, default for filesystem)
|
||||||
// - 'deferred': Persist only on flush/close (fast, default for cloud storage)
|
// - 'deferred': Persist only on flush/close (fast, default for cloud storage)
|
||||||
// Cloud storage (GCS/S3/R2/Azure) should use 'deferred' for 30-50× faster adds
|
// Cloud storage (GCS/S3/R2/Azure) should use 'deferred' for 30-50× faster adds
|
||||||
hnswPersistMode?: 'immediate' | 'deferred'
|
hnswPersistMode?: 'immediate' | 'deferred'
|
||||||
|
|
||||||
// Memory management options (v5.11.0)
|
// Memory management options
|
||||||
maxQueryLimit?: number // Override auto-detected query result limit (max: 100000)
|
maxQueryLimit?: number // Override auto-detected query result limit (max: 100000)
|
||||||
reservedQueryMemory?: number // Memory reserved for queries in bytes (e.g., 1073741824 = 1GB)
|
reservedQueryMemory?: number // Memory reserved for queries in bytes (e.g., 1073741824 = 1GB)
|
||||||
|
|
||||||
// Embedding initialization (v7.1.2)
|
// Embedding initialization
|
||||||
// Controls when the WASM embedding engine is initialized
|
// Controls when the WASM embedding engine is initialized
|
||||||
// - false (default): Lazy initialization on first embed() call
|
// - false (default): Lazy initialization on first embed() call
|
||||||
// - true: Eager initialization during brain.init()
|
// - true: Eager initialization during brain.init()
|
||||||
|
|
@ -745,7 +744,7 @@ export interface BrainyConfig {
|
||||||
verbose?: boolean // Enable verbose logging
|
verbose?: boolean // Enable verbose logging
|
||||||
silent?: boolean // Suppress all logging output
|
silent?: boolean // Suppress all logging output
|
||||||
|
|
||||||
// Integration Hub (v7.4.0)
|
// Integration Hub
|
||||||
// Enable external tool integrations: Excel, Power BI, Google Sheets, etc.
|
// Enable external tool integrations: Excel, Power BI, Google Sheets, etc.
|
||||||
// - true: Enable all integrations with default paths
|
// - true: Enable all integrations with default paths
|
||||||
// - false/undefined: Disable integrations (default)
|
// - false/undefined: Disable integrations (default)
|
||||||
|
|
@ -789,54 +788,55 @@ export interface NeuralAnomalyParams {
|
||||||
returnScores?: boolean // Return anomaly scores
|
returnScores?: boolean // Return anomaly scores
|
||||||
}
|
}
|
||||||
|
|
||||||
// ============= Content Extraction Types (v7.9.0) =============
|
// ============= Content Extraction Types =============
|
||||||
|
|
||||||
/**
|
/**
|
||||||
* Detected content type for smart text extraction
|
* Detected content type for smart text extraction
|
||||||
*
|
*
|
||||||
* @since v7.9.0
|
|
||||||
*/
|
*/
|
||||||
export type ContentType = 'plaintext' | 'richtext-json' | 'html' | 'markdown'
|
export type ContentType = 'plaintext' | 'richtext-json' | 'html' | 'markdown'
|
||||||
|
|
||||||
/**
|
/**
|
||||||
* Content category for extracted segments
|
* Content category for extracted segments
|
||||||
*
|
*
|
||||||
* Allows UI to apply different styling based on content role:
|
* Universal categories that work across documents, code, and UI:
|
||||||
* - 'prose': Regular text content (paragraphs, list items)
|
* - 'title': Names the subject — headings, identifiers, labels, JSON keys
|
||||||
* - 'heading': Heading/title text (h1-h6)
|
* - 'annotation': Human explanation — comments, docstrings, captions, alt text
|
||||||
* - 'code': Code blocks or inline code
|
* - 'content': Body substance — paragraphs, list items, flowing text
|
||||||
* - 'label': Labels, captions, or metadata-like text
|
* - 'value': Data literals — strings, numbers, form values, error messages
|
||||||
|
* - 'code': Unparsed code blocks (custom parsers decompose into above)
|
||||||
|
* - 'structural': Boilerplate — keywords, operators, punctuation, formatting
|
||||||
*
|
*
|
||||||
* @since v7.9.0
|
* Built-in extractors produce: 'title', 'content', 'code'.
|
||||||
|
* All 6 categories are available for custom parsers.
|
||||||
*/
|
*/
|
||||||
export type ContentCategory = 'prose' | 'heading' | 'code' | 'label'
|
export type ContentCategory = 'title' | 'annotation' | 'content' | 'value' | 'code' | 'structural'
|
||||||
|
|
||||||
/**
|
/**
|
||||||
* A segment of extracted text with its content category
|
* A segment of extracted text with its content category
|
||||||
*
|
*
|
||||||
* @since v7.9.0
|
|
||||||
*/
|
*/
|
||||||
export interface ExtractedSegment {
|
export interface ExtractedSegment {
|
||||||
/** The extracted text content */
|
/** The extracted text content */
|
||||||
text: string
|
text: string
|
||||||
/** What role this text plays in the document */
|
/** What role this text plays: 'title' | 'annotation' | 'content' | 'value' | 'code' | 'structural' */
|
||||||
contentCategory: ContentCategory
|
contentCategory: ContentCategory
|
||||||
}
|
}
|
||||||
|
|
||||||
// ============= Semantic Highlighting Types (v7.8.0) =============
|
// ============= Semantic Highlighting Types =============
|
||||||
|
|
||||||
/**
|
/**
|
||||||
* Parameters for hybrid highlighting (v7.8.0, enhanced v7.9.0)
|
* Parameters for hybrid highlighting
|
||||||
*
|
*
|
||||||
* Zero-config highlighting that returns both text (exact) and semantic (concept) matches.
|
* Zero-config highlighting that returns both text (exact) and semantic (concept) matches.
|
||||||
* Perfect for UI highlighting at different levels.
|
* Perfect for UI highlighting at different levels.
|
||||||
*
|
*
|
||||||
* v7.9.0: Added contentType hint and contentExtractor callback for structured text
|
* Added contentType hint and contentExtractor callback for structured text
|
||||||
* (rich-text JSON, HTML, Markdown). Auto-detects format when not specified.
|
* (rich-text JSON, HTML, Markdown). Auto-detects format when not specified.
|
||||||
*
|
*
|
||||||
* @example
|
* @example
|
||||||
* ```typescript
|
* ```typescript
|
||||||
* // Plain text (unchanged from v7.8.0)
|
* // Plain text
|
||||||
* const highlights = await brain.highlight({
|
* const highlights = await brain.highlight({
|
||||||
* query: "david the warrior",
|
* query: "david the warrior",
|
||||||
* text: "David Smith is a brave fighter who battles dragons"
|
* text: "David Smith is a brave fighter who battles dragons"
|
||||||
|
|
@ -872,7 +872,6 @@ export interface HighlightParams {
|
||||||
/**
|
/**
|
||||||
* Optional content type hint to skip auto-detection.
|
* Optional content type hint to skip auto-detection.
|
||||||
* When omitted, the content type is detected from the text content.
|
* When omitted, the content type is detected from the text content.
|
||||||
* @since v7.9.0
|
|
||||||
*/
|
*/
|
||||||
contentType?: ContentType
|
contentType?: ContentType
|
||||||
|
|
||||||
|
|
@ -880,7 +879,6 @@ export interface HighlightParams {
|
||||||
* Optional custom content extractor function.
|
* Optional custom content extractor function.
|
||||||
* When provided, bypasses built-in detection and extraction entirely.
|
* When provided, bypasses built-in detection and extraction entirely.
|
||||||
* Use this to plug in custom parsers (tree-sitter, Monaco, proprietary formats).
|
* Use this to plug in custom parsers (tree-sitter, Monaco, proprietary formats).
|
||||||
* @since v7.9.0
|
|
||||||
*/
|
*/
|
||||||
contentExtractor?: (text: string) => ExtractedSegment[]
|
contentExtractor?: (text: string) => ExtractedSegment[]
|
||||||
}
|
}
|
||||||
|
|
@ -906,9 +904,8 @@ export interface Highlight {
|
||||||
matchType: 'text' | 'semantic'
|
matchType: 'text' | 'semantic'
|
||||||
|
|
||||||
/**
|
/**
|
||||||
* Content category of the source segment (heading, code, prose, label).
|
* Content category of the source segment: 'title' | 'annotation' | 'content' | 'value' | 'code' | 'structural'.
|
||||||
* Present when the input text was structured (JSON, HTML, Markdown).
|
* Present when the input text was structured (JSON, HTML, Markdown).
|
||||||
* @since v7.9.0
|
|
||||||
*/
|
*/
|
||||||
contentCategory?: ContentCategory
|
contentCategory?: ContentCategory
|
||||||
}
|
}
|
||||||
|
|
|
||||||
|
|
@ -1,8 +1,8 @@
|
||||||
/**
|
/**
|
||||||
* Content Extractor (v7.9.0)
|
* Content Extractor
|
||||||
*
|
*
|
||||||
* Detects content type (plaintext, rich-text JSON, HTML, Markdown) and extracts
|
* Detects content type (plaintext, rich-text JSON, HTML, Markdown) and extracts
|
||||||
* text segments with content categories (prose, heading, code, label).
|
* text segments with content categories (title, content, code, etc.).
|
||||||
*
|
*
|
||||||
* Supports common rich-text editor formats:
|
* Supports common rich-text editor formats:
|
||||||
* - TipTap / ProseMirror: { type: 'doc', content: [...] }
|
* - TipTap / ProseMirror: { type: 'doc', content: [...] }
|
||||||
|
|
@ -12,7 +12,7 @@
|
||||||
* - Quill Delta: { ops: [{ insert }] }
|
* - Quill Delta: { ops: [{ insert }] }
|
||||||
*
|
*
|
||||||
* Falls back gracefully: structured text that doesn't match known patterns
|
* Falls back gracefully: structured text that doesn't match known patterns
|
||||||
* is extracted as plain prose via recursive text collection.
|
* is extracted as plain content via recursive text collection.
|
||||||
*/
|
*/
|
||||||
|
|
||||||
import type { ContentType, ContentCategory, ExtractedSegment } from '../types/brainy.types.js'
|
import type { ContentType, ContentCategory, ExtractedSegment } from '../types/brainy.types.js'
|
||||||
|
|
@ -65,7 +65,7 @@ export function extractForHighlighting(
|
||||||
return extractFromMarkdown(text)
|
return extractFromMarkdown(text)
|
||||||
case 'plaintext':
|
case 'plaintext':
|
||||||
default:
|
default:
|
||||||
return [{ text, contentCategory: 'prose' }]
|
return [{ text, contentCategory: 'content' }]
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|
@ -81,7 +81,7 @@ function extractFromJson(text: string): ExtractedSegment[] {
|
||||||
parsed = JSON.parse(text.trim())
|
parsed = JSON.parse(text.trim())
|
||||||
} catch {
|
} catch {
|
||||||
// Invalid JSON — treat as plain text
|
// Invalid JSON — treat as plain text
|
||||||
return [{ text, contentCategory: 'prose' }]
|
return [{ text, contentCategory: 'content' }]
|
||||||
}
|
}
|
||||||
|
|
||||||
const segments = walkRichTextNodes(parsed)
|
const segments = walkRichTextNodes(parsed)
|
||||||
|
|
@ -94,7 +94,7 @@ function extractFromJson(text: string): ExtractedSegment[] {
|
||||||
// Fallback: collect all string values from the JSON
|
// Fallback: collect all string values from the JSON
|
||||||
const fallbackText = extractTextFromJsonValue(parsed)
|
const fallbackText = extractTextFromJsonValue(parsed)
|
||||||
if (fallbackText.trim()) {
|
if (fallbackText.trim()) {
|
||||||
return [{ text: fallbackText, contentCategory: 'prose' }]
|
return [{ text: fallbackText, contentCategory: 'content' }]
|
||||||
}
|
}
|
||||||
|
|
||||||
return []
|
return []
|
||||||
|
|
@ -121,13 +121,13 @@ function walkRichTextNodes(node: any): ExtractedSegment[] {
|
||||||
|
|
||||||
// Leaf: text content (TipTap/ProseMirror/Lexical/Slate)
|
// Leaf: text content (TipTap/ProseMirror/Lexical/Slate)
|
||||||
if (typeof node.text === 'string' && node.text.length > 0) {
|
if (typeof node.text === 'string' && node.text.length > 0) {
|
||||||
segments.push({ text: node.text, contentCategory: 'prose' })
|
segments.push({ text: node.text, contentCategory: 'content' })
|
||||||
return segments
|
return segments
|
||||||
}
|
}
|
||||||
|
|
||||||
// Leaf: Quill Delta insert
|
// Leaf: Quill Delta insert
|
||||||
if (typeof node.insert === 'string' && node.insert.length > 0) {
|
if (typeof node.insert === 'string' && node.insert.length > 0) {
|
||||||
segments.push({ text: node.insert, contentCategory: 'prose' })
|
segments.push({ text: node.insert, contentCategory: 'content' })
|
||||||
return segments
|
return segments
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|
@ -146,8 +146,8 @@ function walkRichTextNodes(node: any): ExtractedSegment[] {
|
||||||
if (Array.isArray(children)) {
|
if (Array.isArray(children)) {
|
||||||
for (const child of children) {
|
for (const child of children) {
|
||||||
const childSegments = walkRichTextNodes(child)
|
const childSegments = walkRichTextNodes(child)
|
||||||
// Apply parent's category if it's more specific than 'prose'
|
// Apply parent's category if it's more specific than 'content'
|
||||||
if (category !== 'prose') {
|
if (category !== 'content') {
|
||||||
childSegments.forEach(s => { s.contentCategory = category })
|
childSegments.forEach(s => { s.contentCategory = category })
|
||||||
}
|
}
|
||||||
segments.push(...childSegments)
|
segments.push(...childSegments)
|
||||||
|
|
@ -166,11 +166,11 @@ function walkRichTextNodes(node: any): ExtractedSegment[] {
|
||||||
* Categorize a node type string into a ContentCategory
|
* Categorize a node type string into a ContentCategory
|
||||||
*/
|
*/
|
||||||
function categorizeNodeType(type?: string): ContentCategory {
|
function categorizeNodeType(type?: string): ContentCategory {
|
||||||
if (!type) return 'prose'
|
if (!type) return 'content'
|
||||||
const t = type.toLowerCase()
|
const t = type.toLowerCase()
|
||||||
if (t === 'heading' || /^h[1-6]$/.test(t)) return 'heading'
|
if (t === 'heading' || /^h[1-6]$/.test(t)) return 'title'
|
||||||
if (t === 'code' || t === 'codeblock' || t === 'code_block') return 'code'
|
if (t === 'code' || t === 'codeblock' || t === 'code_block') return 'code'
|
||||||
return 'prose'
|
return 'content'
|
||||||
}
|
}
|
||||||
|
|
||||||
/**
|
/**
|
||||||
|
|
@ -201,7 +201,7 @@ function extractTextFromJsonValue(value: any): string {
|
||||||
function extractFromHtml(html: string): ExtractedSegment[] {
|
function extractFromHtml(html: string): ExtractedSegment[] {
|
||||||
const segments: ExtractedSegment[] = []
|
const segments: ExtractedSegment[] = []
|
||||||
let current = ''
|
let current = ''
|
||||||
let currentCategory: ContentCategory = 'prose'
|
let currentCategory: ContentCategory = 'content'
|
||||||
let i = 0
|
let i = 0
|
||||||
let insideTag = false
|
let insideTag = false
|
||||||
let tagName = ''
|
let tagName = ''
|
||||||
|
|
@ -304,10 +304,10 @@ function extractFromHtml(html: string): ExtractedSegment[] {
|
||||||
function getCategoryFromTagStack(stack: string[]): ContentCategory {
|
function getCategoryFromTagStack(stack: string[]): ContentCategory {
|
||||||
for (let i = stack.length - 1; i >= 0; i--) {
|
for (let i = stack.length - 1; i >= 0; i--) {
|
||||||
const tag = stack[i]
|
const tag = stack[i]
|
||||||
if (/^h[1-6]$/.test(tag)) return 'heading'
|
if (/^h[1-6]$/.test(tag)) return 'title'
|
||||||
if (tag === 'code' || tag === 'pre') return 'code'
|
if (tag === 'code' || tag === 'pre') return 'code'
|
||||||
}
|
}
|
||||||
return 'prose'
|
return 'content'
|
||||||
}
|
}
|
||||||
|
|
||||||
/**
|
/**
|
||||||
|
|
@ -328,6 +328,41 @@ function decodeHtmlEntity(entity: string): string {
|
||||||
|
|
||||||
// ============= Markdown Extraction =============
|
// ============= Markdown Extraction =============
|
||||||
|
|
||||||
|
/**
|
||||||
|
* Split a prose line into alternating content/code segments based on
|
||||||
|
* backtick-delimited inline code spans. Lines without backticks return
|
||||||
|
* a single 'content' segment.
|
||||||
|
*/
|
||||||
|
function splitInlineCode(line: string): ExtractedSegment[] {
|
||||||
|
const segments: ExtractedSegment[] = []
|
||||||
|
const pattern = /`([^`]+)`/g
|
||||||
|
let lastIndex = 0
|
||||||
|
let match: RegExpExecArray | null
|
||||||
|
|
||||||
|
while ((match = pattern.exec(line)) !== null) {
|
||||||
|
// Text before the backtick span
|
||||||
|
if (match.index > lastIndex) {
|
||||||
|
const before = line.substring(lastIndex, match.index).trim()
|
||||||
|
if (before.length > 0) {
|
||||||
|
segments.push({ text: before, contentCategory: 'content' })
|
||||||
|
}
|
||||||
|
}
|
||||||
|
// The code span (without backticks)
|
||||||
|
segments.push({ text: match[1], contentCategory: 'code' })
|
||||||
|
lastIndex = match.index + match[0].length
|
||||||
|
}
|
||||||
|
|
||||||
|
// Remaining text after last backtick span (or entire line if no backticks)
|
||||||
|
if (lastIndex < line.length) {
|
||||||
|
const remaining = line.substring(lastIndex).trim()
|
||||||
|
if (remaining.length > 0) {
|
||||||
|
segments.push({ text: remaining, contentCategory: 'content' })
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
return segments
|
||||||
|
}
|
||||||
|
|
||||||
/**
|
/**
|
||||||
* Extract text from Markdown with category detection
|
* Extract text from Markdown with category detection
|
||||||
*/
|
*/
|
||||||
|
|
@ -381,14 +416,14 @@ function extractFromMarkdown(text: string): ExtractedSegment[] {
|
||||||
// Heading (# style)
|
// Heading (# style)
|
||||||
const headingMatch = line.match(/^#{1,6}\s+(.+)$/)
|
const headingMatch = line.match(/^#{1,6}\s+(.+)$/)
|
||||||
if (headingMatch) {
|
if (headingMatch) {
|
||||||
segments.push({ text: headingMatch[1].trim(), contentCategory: 'heading' })
|
segments.push({ text: headingMatch[1].trim(), contentCategory: 'title' })
|
||||||
i++
|
i++
|
||||||
continue
|
continue
|
||||||
}
|
}
|
||||||
|
|
||||||
// Regular prose line
|
// Regular content line — split out inline code spans
|
||||||
if (line.trim().length > 0) {
|
if (line.trim().length > 0) {
|
||||||
segments.push({ text: line.trim(), contentCategory: 'prose' })
|
segments.push(...splitInlineCode(line.trim()))
|
||||||
}
|
}
|
||||||
|
|
||||||
i++
|
i++
|
||||||
|
|
|
||||||
|
|
@ -769,7 +769,7 @@ describe('Hybrid Search (v7.7.0)', () => {
|
||||||
expect(warriorMatch).toBeDefined()
|
expect(warriorMatch).toBeDefined()
|
||||||
expect(warriorMatch?.matchType).toBe('text')
|
expect(warriorMatch?.matchType).toBe('text')
|
||||||
// Should annotate heading content
|
// Should annotate heading content
|
||||||
expect(warriorMatch?.contentCategory).toBe('heading')
|
expect(warriorMatch?.contentCategory).toBe('title')
|
||||||
})
|
})
|
||||||
|
|
||||||
it('should extract text from Slate.js JSON', async () => {
|
it('should extract text from Slate.js JSON', async () => {
|
||||||
|
|
@ -799,7 +799,7 @@ describe('Hybrid Search (v7.7.0)', () => {
|
||||||
const introMatch = highlights.find(h => h.text === 'Introduction')
|
const introMatch = highlights.find(h => h.text === 'Introduction')
|
||||||
expect(introMatch).toBeDefined()
|
expect(introMatch).toBeDefined()
|
||||||
expect(introMatch?.matchType).toBe('text')
|
expect(introMatch?.matchType).toBe('text')
|
||||||
expect(introMatch?.contentCategory).toBe('heading')
|
expect(introMatch?.contentCategory).toBe('title')
|
||||||
})
|
})
|
||||||
|
|
||||||
it('should extract text from Quill Delta JSON', async () => {
|
it('should extract text from Quill Delta JSON', async () => {
|
||||||
|
|
@ -856,12 +856,12 @@ describe('Hybrid Search (v7.7.0)', () => {
|
||||||
// Should find "Warrior" from heading
|
// Should find "Warrior" from heading
|
||||||
const warriorMatch = highlights.find(h => h.text.toLowerCase() === 'warrior')
|
const warriorMatch = highlights.find(h => h.text.toLowerCase() === 'warrior')
|
||||||
expect(warriorMatch).toBeDefined()
|
expect(warriorMatch).toBeDefined()
|
||||||
expect(warriorMatch?.contentCategory).toBe('heading')
|
expect(warriorMatch?.contentCategory).toBe('title')
|
||||||
|
|
||||||
// Should find "fighter" from paragraph
|
// Should find "fighter" from paragraph
|
||||||
const fighterMatch = highlights.find(h => h.text.toLowerCase() === 'fighter')
|
const fighterMatch = highlights.find(h => h.text.toLowerCase() === 'fighter')
|
||||||
expect(fighterMatch).toBeDefined()
|
expect(fighterMatch).toBeDefined()
|
||||||
expect(fighterMatch?.contentCategory).toBe('prose')
|
expect(fighterMatch?.contentCategory).toBe('content')
|
||||||
})
|
})
|
||||||
|
|
||||||
it('should extract text from Markdown with headings and code', async () => {
|
it('should extract text from Markdown with headings and code', async () => {
|
||||||
|
|
@ -876,8 +876,8 @@ describe('Hybrid Search (v7.7.0)', () => {
|
||||||
|
|
||||||
expect(highlights.length).toBeGreaterThan(0)
|
expect(highlights.length).toBeGreaterThan(0)
|
||||||
// Should find text from heading
|
// Should find text from heading
|
||||||
const headingMatch = highlights.find(h => h.text === 'Guide' && h.contentCategory === 'heading')
|
const headingMatch = highlights.find(h => h.text === 'Guide' && h.contentCategory === 'title')
|
||||||
|| highlights.find(h => h.text === 'Warrior' && h.contentCategory === 'heading')
|
|| highlights.find(h => h.text === 'Warrior' && h.contentCategory === 'title')
|
||||||
expect(headingMatch).toBeDefined()
|
expect(headingMatch).toBeDefined()
|
||||||
})
|
})
|
||||||
|
|
||||||
|
|
@ -896,8 +896,8 @@ describe('Hybrid Search (v7.7.0)', () => {
|
||||||
expect(warriorMatch).toBeDefined()
|
expect(warriorMatch).toBeDefined()
|
||||||
expect(warriorMatch?.matchType).toBe('text')
|
expect(warriorMatch?.matchType).toBe('text')
|
||||||
expect(warriorMatch?.score).toBe(1.0)
|
expect(warriorMatch?.score).toBe(1.0)
|
||||||
// Plain text gets 'prose' category
|
// Plain text gets 'content' category
|
||||||
expect(warriorMatch?.contentCategory).toBe('prose')
|
expect(warriorMatch?.contentCategory).toBe('content')
|
||||||
})
|
})
|
||||||
|
|
||||||
it('should use contentType hint to skip auto-detection', async () => {
|
it('should use contentType hint to skip auto-detection', async () => {
|
||||||
|
|
@ -920,7 +920,7 @@ describe('Hybrid Search (v7.7.0)', () => {
|
||||||
it('should use custom contentExtractor when provided', async () => {
|
it('should use custom contentExtractor when provided', async () => {
|
||||||
const customExtractor = (text: string) => {
|
const customExtractor = (text: string) => {
|
||||||
return [
|
return [
|
||||||
{ text: 'custom extracted warrior content', contentCategory: 'prose' as const },
|
{ text: 'custom extracted warrior content', contentCategory: 'content' as const },
|
||||||
{ text: 'Code Section', contentCategory: 'code' as const }
|
{ text: 'Code Section', contentCategory: 'code' as const }
|
||||||
]
|
]
|
||||||
}
|
}
|
||||||
|
|
@ -937,8 +937,9 @@ describe('Hybrid Search (v7.7.0)', () => {
|
||||||
const warriorMatch = highlights.find(h => h.text.toLowerCase() === 'warrior')
|
const warriorMatch = highlights.find(h => h.text.toLowerCase() === 'warrior')
|
||||||
expect(warriorMatch).toBeDefined()
|
expect(warriorMatch).toBeDefined()
|
||||||
expect(warriorMatch?.matchType).toBe('text')
|
expect(warriorMatch?.matchType).toBe('text')
|
||||||
expect(warriorMatch?.contentCategory).toBe('prose')
|
expect(warriorMatch?.contentCategory).toBe('content')
|
||||||
})
|
})
|
||||||
|
|
||||||
})
|
})
|
||||||
|
|
||||||
describe('Timeout Protection (v7.9.0)', () => {
|
describe('Timeout Protection (v7.9.0)', () => {
|
||||||
|
|
|
||||||
|
|
@ -75,10 +75,10 @@ describe('Content Extractor (v7.9.0)', () => {
|
||||||
expect(segments.length).toBe(3)
|
expect(segments.length).toBe(3)
|
||||||
|
|
||||||
expect(segments[0].text).toBe('My Heading')
|
expect(segments[0].text).toBe('My Heading')
|
||||||
expect(segments[0].contentCategory).toBe('heading')
|
expect(segments[0].contentCategory).toBe('title')
|
||||||
|
|
||||||
expect(segments[1].text).toBe('Regular paragraph text')
|
expect(segments[1].text).toBe('Regular paragraph text')
|
||||||
expect(segments[1].contentCategory).toBe('prose')
|
expect(segments[1].contentCategory).toBe('content')
|
||||||
|
|
||||||
expect(segments[2].text).toBe('const x = 1')
|
expect(segments[2].text).toBe('const x = 1')
|
||||||
expect(segments[2].contentCategory).toBe('code')
|
expect(segments[2].contentCategory).toBe('code')
|
||||||
|
|
@ -124,9 +124,9 @@ describe('Content Extractor (v7.9.0)', () => {
|
||||||
const segments = extractForHighlighting(doc)
|
const segments = extractForHighlighting(doc)
|
||||||
expect(segments.length).toBe(3)
|
expect(segments.length).toBe(3)
|
||||||
expect(segments[0].text).toBe('Slate Heading')
|
expect(segments[0].text).toBe('Slate Heading')
|
||||||
expect(segments[0].contentCategory).toBe('heading')
|
expect(segments[0].contentCategory).toBe('title')
|
||||||
expect(segments[1].text).toBe('First part ')
|
expect(segments[1].text).toBe('First part ')
|
||||||
expect(segments[1].contentCategory).toBe('prose')
|
expect(segments[1].contentCategory).toBe('content')
|
||||||
})
|
})
|
||||||
})
|
})
|
||||||
|
|
||||||
|
|
@ -150,9 +150,9 @@ describe('Content Extractor (v7.9.0)', () => {
|
||||||
const segments = extractForHighlighting(doc)
|
const segments = extractForHighlighting(doc)
|
||||||
expect(segments.length).toBe(2)
|
expect(segments.length).toBe(2)
|
||||||
expect(segments[0].text).toBe('Lexical Heading')
|
expect(segments[0].text).toBe('Lexical Heading')
|
||||||
expect(segments[0].contentCategory).toBe('heading')
|
expect(segments[0].contentCategory).toBe('title')
|
||||||
expect(segments[1].text).toBe('Lexical body text')
|
expect(segments[1].text).toBe('Lexical body text')
|
||||||
expect(segments[1].contentCategory).toBe('prose')
|
expect(segments[1].contentCategory).toBe('content')
|
||||||
})
|
})
|
||||||
})
|
})
|
||||||
|
|
||||||
|
|
@ -223,11 +223,11 @@ describe('Content Extractor (v7.9.0)', () => {
|
||||||
|
|
||||||
const headingSegment = segments.find(s => s.text === 'Title')
|
const headingSegment = segments.find(s => s.text === 'Title')
|
||||||
expect(headingSegment).toBeDefined()
|
expect(headingSegment).toBeDefined()
|
||||||
expect(headingSegment?.contentCategory).toBe('heading')
|
expect(headingSegment?.contentCategory).toBe('title')
|
||||||
|
|
||||||
const bodySegment = segments.find(s => s.text === 'Body text here.')
|
const bodySegment = segments.find(s => s.text === 'Body text here.')
|
||||||
expect(bodySegment).toBeDefined()
|
expect(bodySegment).toBeDefined()
|
||||||
expect(bodySegment?.contentCategory).toBe('prose')
|
expect(bodySegment?.contentCategory).toBe('content')
|
||||||
|
|
||||||
const codeSegment = segments.find(s => s.text === 'let x = 1')
|
const codeSegment = segments.find(s => s.text === 'let x = 1')
|
||||||
expect(codeSegment).toBeDefined()
|
expect(codeSegment).toBeDefined()
|
||||||
|
|
@ -257,7 +257,7 @@ describe('Content Extractor (v7.9.0)', () => {
|
||||||
const segments = extractForHighlighting(html)
|
const segments = extractForHighlighting(html)
|
||||||
const heading = segments.find(s => s.text === 'Nested Heading')
|
const heading = segments.find(s => s.text === 'Nested Heading')
|
||||||
expect(heading).toBeDefined()
|
expect(heading).toBeDefined()
|
||||||
expect(heading?.contentCategory).toBe('heading')
|
expect(heading?.contentCategory).toBe('title')
|
||||||
})
|
})
|
||||||
})
|
})
|
||||||
|
|
||||||
|
|
@ -271,11 +271,11 @@ describe('Content Extractor (v7.9.0)', () => {
|
||||||
const body = segments.find(s => s.text === 'Some body text')
|
const body = segments.find(s => s.text === 'Some body text')
|
||||||
|
|
||||||
expect(heading1).toBeDefined()
|
expect(heading1).toBeDefined()
|
||||||
expect(heading1?.contentCategory).toBe('heading')
|
expect(heading1?.contentCategory).toBe('title')
|
||||||
expect(heading2).toBeDefined()
|
expect(heading2).toBeDefined()
|
||||||
expect(heading2?.contentCategory).toBe('heading')
|
expect(heading2?.contentCategory).toBe('title')
|
||||||
expect(body).toBeDefined()
|
expect(body).toBeDefined()
|
||||||
expect(body?.contentCategory).toBe('prose')
|
expect(body?.contentCategory).toBe('content')
|
||||||
})
|
})
|
||||||
|
|
||||||
it('should extract fenced code blocks', () => {
|
it('should extract fenced code blocks', () => {
|
||||||
|
|
@ -296,16 +296,51 @@ describe('Content Extractor (v7.9.0)', () => {
|
||||||
expect(code).toBeDefined()
|
expect(code).toBeDefined()
|
||||||
expect(code?.text).toContain('code line 1')
|
expect(code?.text).toContain('code line 1')
|
||||||
})
|
})
|
||||||
|
|
||||||
|
it('should split inline code spans into separate segments', () => {
|
||||||
|
const md = '# Title\n\nUse the `authenticate()` function to verify users'
|
||||||
|
|
||||||
|
const segments = extractForHighlighting(md)
|
||||||
|
// Should have: title segment, content "Use the", code "authenticate()", content "function to verify users"
|
||||||
|
const codeSegment = segments.find(s => s.text === 'authenticate()' && s.contentCategory === 'code')
|
||||||
|
expect(codeSegment).toBeDefined()
|
||||||
|
|
||||||
|
const beforeCode = segments.find(s => s.text === 'Use the' && s.contentCategory === 'content')
|
||||||
|
expect(beforeCode).toBeDefined()
|
||||||
|
|
||||||
|
const afterCode = segments.find(s => s.text === 'function to verify users' && s.contentCategory === 'content')
|
||||||
|
expect(afterCode).toBeDefined()
|
||||||
|
})
|
||||||
|
|
||||||
|
it('should handle multiple inline code spans in a single line', () => {
|
||||||
|
const md = '# API\n\nCall `foo()` then `bar()` for results'
|
||||||
|
|
||||||
|
const segments = extractForHighlighting(md, 'markdown')
|
||||||
|
const fooSegment = segments.find(s => s.text === 'foo()' && s.contentCategory === 'code')
|
||||||
|
const barSegment = segments.find(s => s.text === 'bar()' && s.contentCategory === 'code')
|
||||||
|
expect(fooSegment).toBeDefined()
|
||||||
|
expect(barSegment).toBeDefined()
|
||||||
|
})
|
||||||
|
|
||||||
|
it('should not split backticks inside fenced code blocks', () => {
|
||||||
|
const md = '# Title\n\n```\nconst x = `template`\n```'
|
||||||
|
|
||||||
|
const segments = extractForHighlighting(md)
|
||||||
|
const code = segments.find(s => s.contentCategory === 'code')
|
||||||
|
expect(code).toBeDefined()
|
||||||
|
// The fenced block content should be intact, not split by backticks
|
||||||
|
expect(code?.text).toContain('const x = `template`')
|
||||||
|
})
|
||||||
})
|
})
|
||||||
|
|
||||||
describe('extractForHighlighting() — Plaintext', () => {
|
describe('extractForHighlighting() — Plaintext', () => {
|
||||||
it('should return single prose segment for plain text', () => {
|
it('should return single content segment for plain text', () => {
|
||||||
const text = 'Just some plain text content'
|
const text = 'Just some plain text content'
|
||||||
const segments = extractForHighlighting(text)
|
const segments = extractForHighlighting(text)
|
||||||
|
|
||||||
expect(segments.length).toBe(1)
|
expect(segments.length).toBe(1)
|
||||||
expect(segments[0].text).toBe(text)
|
expect(segments[0].text).toBe(text)
|
||||||
expect(segments[0].contentCategory).toBe('prose')
|
expect(segments[0].contentCategory).toBe('content')
|
||||||
})
|
})
|
||||||
|
|
||||||
it('should respect contentType override', () => {
|
it('should respect contentType override', () => {
|
||||||
|
|
@ -315,7 +350,7 @@ describe('Content Extractor (v7.9.0)', () => {
|
||||||
|
|
||||||
expect(segments.length).toBe(1)
|
expect(segments.length).toBe(1)
|
||||||
expect(segments[0].text).toBe(html) // Raw HTML, not extracted
|
expect(segments[0].text).toBe(html) // Raw HTML, not extracted
|
||||||
expect(segments[0].contentCategory).toBe('prose')
|
expect(segments[0].contentCategory).toBe('content')
|
||||||
})
|
})
|
||||||
})
|
})
|
||||||
})
|
})
|
||||||
|
|
|
||||||
Loading…
Add table
Add a link
Reference in a new issue