feat: comprehensive import progress tracking for all 7 formats

Add real-time progress reporting throughout the entire import pipeline
with a standardized API that works across all supported formats.

Workshop Team Feature Request:
- Eliminates "0% complete" hangs during AI extraction
- Shows continuous progress with entities/sec, throughput, ETA
- Reports contextual messages ("Processing page 5 of 23")
- Standardized progress API for CSV, PDF, Excel, JSON, Markdown, YAML, DOCX

Core Changes:
- Add FormatHandlerProgressHooks interface for extensible progress
- Wire up all 3 binary format handlers (CSV, PDF, Excel) with 7+ progress points
- Wire up all 4 text format importers (JSON, Markdown, YAML, DOCX)
- Add ImportProgress interface with stage, message, counts, throughput, ETA
- ImportCoordinator normalizes all format progress to standard interface

CLI Improvements:
- Import command now uses brain.import() directly with full progress
- Add --include-vfs flag to find command (v4.4.0 compatibility)
- Add --confidence and --weight options to add command

Documentation:
- docs/guides/standard-import-progress.md - Universal API guide
- docs/guides/import-progress-implementation.md - Developer guide
- docs/guides/import-progress-examples.md - Practical examples
- JSDoc on brain.import() with universal handler examples

Result: ONE progress handler works for ALL 7 formats with zero format-specific code!

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
David Snelling 2025-10-24 14:45:46 -07:00
parent e7ea9c4e4b
commit d5576ffb56
20 changed files with 3967 additions and 52 deletions

View file

@ -34,9 +34,19 @@ export class CSVHandler extends BaseFormatHandler {
async process(data: Buffer | string, options: FormatHandlerOptions): Promise<ProcessedData> {
const startTime = Date.now()
const progressHooks = options.progressHooks
// Convert to buffer if string
const buffer = Buffer.isBuffer(data) ? data : Buffer.from(data, 'utf-8')
const totalBytes = buffer.length
// v4.5.0: Report total bytes for progress tracking
if (progressHooks?.onBytesProcessed) {
progressHooks.onBytesProcessed(0)
}
if (progressHooks?.onCurrentItem) {
progressHooks.onCurrentItem('Detecting CSV encoding and delimiter...')
}
// Detect encoding
const detectedEncoding = options.encoding || this.detectEncodingSafe(buffer)
@ -45,6 +55,11 @@ export class CSVHandler extends BaseFormatHandler {
// Detect delimiter if not specified
const delimiter = options.csvDelimiter || this.detectDelimiter(text)
// v4.5.0: Report progress - parsing started
if (progressHooks?.onCurrentItem) {
progressHooks.onCurrentItem(`Parsing CSV rows (delimiter: "${delimiter}")...`)
}
// Parse CSV
const hasHeaders = options.csvHeaders !== false
const maxRows = options.maxRows
@ -60,23 +75,47 @@ export class CSVHandler extends BaseFormatHandler {
cast: false // We'll do type inference ourselves
})
// v4.5.0: Report bytes processed (entire file parsed)
if (progressHooks?.onBytesProcessed) {
progressHooks.onBytesProcessed(totalBytes)
}
// Convert to array of objects
const data = Array.isArray(records) ? records : [records]
// v4.5.0: Report data extraction progress
if (progressHooks?.onDataExtracted) {
progressHooks.onDataExtracted(data.length, data.length)
}
if (progressHooks?.onCurrentItem) {
progressHooks.onCurrentItem(`Extracted ${data.length} rows, inferring types...`)
}
// Infer types and convert values
const fields = data.length > 0 ? Object.keys(data[0]) : []
const types = this.inferFieldTypes(data)
const convertedData = data.map(row => {
const convertedData = data.map((row, index) => {
const converted: Record<string, any> = {}
for (const [key, value] of Object.entries(row)) {
converted[key] = this.convertValue(value, types[key] || 'string')
}
// v4.5.0: Report progress every 1000 rows
if (progressHooks?.onCurrentItem && index > 0 && index % 1000 === 0) {
progressHooks.onCurrentItem(`Converting types: ${index}/${data.length} rows...`)
}
return converted
})
const processingTime = Date.now() - startTime
// v4.5.0: Final progress update
if (progressHooks?.onCurrentItem) {
progressHooks.onCurrentItem(`CSV processing complete: ${convertedData.length} rows`)
}
return {
format: this.format,
data: convertedData,

View file

@ -21,9 +21,19 @@ export class ExcelHandler extends BaseFormatHandler {
async process(data: Buffer | string, options: FormatHandlerOptions): Promise<ProcessedData> {
const startTime = Date.now()
const progressHooks = options.progressHooks
// Convert to buffer if string (though Excel should always be binary)
const buffer = Buffer.isBuffer(data) ? data : Buffer.from(data, 'binary')
const totalBytes = buffer.length
// v4.5.0: Report start
if (progressHooks?.onBytesProcessed) {
progressHooks.onBytesProcessed(0)
}
if (progressHooks?.onCurrentItem) {
progressHooks.onCurrentItem('Loading Excel workbook...')
}
try {
// Read workbook
@ -37,11 +47,25 @@ export class ExcelHandler extends BaseFormatHandler {
// Determine which sheets to process
const sheetsToProcess = this.getSheetsToProcess(workbook, options)
// v4.5.0: Report workbook loaded
if (progressHooks?.onCurrentItem) {
progressHooks.onCurrentItem(`Processing ${sheetsToProcess.length} sheets...`)
}
// Extract data from sheets
const allData: Array<Record<string, any>> = []
const sheetMetadata: Record<string, any> = {}
for (const sheetName of sheetsToProcess) {
for (let sheetIndex = 0; sheetIndex < sheetsToProcess.length; sheetIndex++) {
const sheetName = sheetsToProcess[sheetIndex]
// v4.5.0: Report current sheet
if (progressHooks?.onCurrentItem) {
progressHooks.onCurrentItem(
`Reading sheet: ${sheetName} (${sheetIndex + 1}/${sheetsToProcess.length})`
)
}
const sheet = workbook.Sheets[sheetName]
if (!sheet) continue
@ -92,6 +116,25 @@ export class ExcelHandler extends BaseFormatHandler {
columnCount: headers.length,
headers
}
// v4.5.0: Estimate bytes processed (sheets are sequential)
const bytesProcessed = Math.floor(((sheetIndex + 1) / sheetsToProcess.length) * totalBytes)
if (progressHooks?.onBytesProcessed) {
progressHooks.onBytesProcessed(bytesProcessed)
}
// v4.5.0: Report extraction progress
if (progressHooks?.onDataExtracted) {
progressHooks.onDataExtracted(allData.length, undefined) // Total unknown until complete
}
}
// v4.5.0: Report data extraction complete
if (progressHooks?.onCurrentItem) {
progressHooks.onCurrentItem(`Extracted ${allData.length} rows, inferring types...`)
}
if (progressHooks?.onDataExtracted) {
progressHooks.onDataExtracted(allData.length, allData.length)
}
// Infer types (excluding _sheet field)
@ -99,7 +142,7 @@ export class ExcelHandler extends BaseFormatHandler {
const types = this.inferFieldTypes(allData)
// Convert values to appropriate types
const convertedData = allData.map(row => {
const convertedData = allData.map((row, index) => {
const converted: Record<string, any> = {}
for (const [key, value] of Object.entries(row)) {
if (key === '_sheet') {
@ -108,11 +151,29 @@ export class ExcelHandler extends BaseFormatHandler {
converted[key] = this.convertValue(value, types[key] || 'string')
}
}
// v4.5.0: Report progress every 1000 rows (avoid spam)
if (progressHooks?.onCurrentItem && index > 0 && index % 1000 === 0) {
progressHooks.onCurrentItem(`Converting types: ${index}/${allData.length} rows...`)
}
return converted
})
// v4.5.0: Final progress - all bytes processed
if (progressHooks?.onBytesProcessed) {
progressHooks.onBytesProcessed(totalBytes)
}
const processingTime = Date.now() - startTime
// v4.5.0: Report completion
if (progressHooks?.onCurrentItem) {
progressHooks.onCurrentItem(
`Excel complete: ${sheetsToProcess.length} sheets, ${convertedData.length} rows`
)
}
return {
format: this.format,
data: convertedData,

View file

@ -46,9 +46,19 @@ export class PDFHandler extends BaseFormatHandler {
async process(data: Buffer | string, options: FormatHandlerOptions): Promise<ProcessedData> {
const startTime = Date.now()
const progressHooks = options.progressHooks
// Convert to buffer
const buffer = Buffer.isBuffer(data) ? data : Buffer.from(data, 'binary')
const totalBytes = buffer.length
// v4.5.0: Report start
if (progressHooks?.onBytesProcessed) {
progressHooks.onBytesProcessed(0)
}
if (progressHooks?.onCurrentItem) {
progressHooks.onCurrentItem('Loading PDF document...')
}
try {
// Load PDF document
@ -64,12 +74,22 @@ export class PDFHandler extends BaseFormatHandler {
const metadata = await pdfDoc.getMetadata()
const numPages = pdfDoc.numPages
// v4.5.0: Report document loaded
if (progressHooks?.onCurrentItem) {
progressHooks.onCurrentItem(`Processing ${numPages} pages...`)
}
// Extract text and structure from all pages
const allData: Array<Record<string, any>> = []
let totalTextLength = 0
let detectedTables = 0
for (let pageNum = 1; pageNum <= numPages; pageNum++) {
// v4.5.0: Report current page
if (progressHooks?.onCurrentItem) {
progressHooks.onCurrentItem(`Processing page ${pageNum} of ${numPages}`)
}
const page = await pdfDoc.getPage(pageNum)
const textContent = await page.getTextContent()
@ -110,10 +130,36 @@ export class PDFHandler extends BaseFormatHandler {
})
}
}
// v4.5.0: Estimate bytes processed (pages are sequential)
const bytesProcessed = Math.floor((pageNum / numPages) * totalBytes)
if (progressHooks?.onBytesProcessed) {
progressHooks.onBytesProcessed(bytesProcessed)
}
// v4.5.0: Report extraction progress
if (progressHooks?.onDataExtracted) {
progressHooks.onDataExtracted(allData.length, undefined) // Total unknown until complete
}
}
// v4.5.0: Final progress - all bytes processed
if (progressHooks?.onBytesProcessed) {
progressHooks.onBytesProcessed(totalBytes)
}
if (progressHooks?.onDataExtracted) {
progressHooks.onDataExtracted(allData.length, allData.length)
}
const processingTime = Date.now() - startTime
// v4.5.0: Report completion
if (progressHooks?.onCurrentItem) {
progressHooks.onCurrentItem(
`PDF complete: ${numPages} pages, ${allData.length} items extracted`
)
}
// Get all unique fields (excluding metadata fields)
const fields = allData.length > 0
? Object.keys(allData[0]).filter(k => !k.startsWith('_'))

View file

@ -3,6 +3,34 @@
* Handles Excel, PDF, and CSV import with intelligent extraction
*/
import { ImportProgressTracker } from '../../utils/import-progress-tracker.js'
/**
* Progress hooks for format handlers
*
* Handlers call these hooks to report progress during processing.
* This enables real-time progress tracking for any file format.
*/
export interface FormatHandlerProgressHooks {
/**
* Report bytes processed
* Call this as you read/parse the file
*/
onBytesProcessed?: (bytes: number) => void
/**
* Set current processing context
* Examples: "Processing page 5", "Reading sheet: Q2 Sales"
*/
onCurrentItem?: (item: string) => void
/**
* Report structured data extraction progress
* Examples: "Extracted 100 rows", "Parsed 50 paragraphs"
*/
onDataExtracted?: (count: number, total?: number) => void
}
export interface FormatHandler {
/**
* Format name (e.g., 'csv', 'xlsx', 'pdf')
@ -58,6 +86,18 @@ export interface FormatHandlerOptions {
/** Whether to stream large files */
streaming?: boolean
/**
* Progress hooks (v4.5.0)
* Handlers call these to report progress during processing
*/
progressHooks?: FormatHandlerProgressHooks
/**
* Total file size in bytes (v4.5.0)
* Used for progress percentage calculation
*/
totalBytes?: number
}
export interface ProcessedData {

View file

@ -2039,9 +2039,27 @@ export class Brainy<T = any> implements BrainyInterface<T> {
* groupBy: 'type', // Organize by entity type
* preserveSource: true, // Keep original file
*
* // Progress tracking
* onProgress: (p) => console.log(p.message)
* // Progress tracking (v4.5.0 - STANDARDIZED FOR ALL 7 FORMATS!)
* onProgress: (p) => {
* console.log(`[${p.stage}] ${p.message}`)
* console.log(`Entities: ${p.entities || 0}, Rels: ${p.relationships || 0}`)
* if (p.throughput) console.log(`Rate: ${p.throughput.toFixed(1)}/sec`)
* }
* })
* // THIS SAME HANDLER WORKS FOR CSV, PDF, Excel, JSON, Markdown, YAML, DOCX!
* ```
*
* @example Universal Progress Handler (v4.5.0)
* ```typescript
* // ONE handler for ALL 7 formats - no format-specific code needed!
* const universalProgress = (p) => {
* updateUI(p.stage, p.message, p.entities, p.relationships)
* }
*
* await brain.import(csvBuffer, { onProgress: universalProgress })
* await brain.import(pdfBuffer, { onProgress: universalProgress })
* await brain.import(excelBuffer, { onProgress: universalProgress })
* // Works for JSON, Markdown, YAML, DOCX too!
* ```
*
* @example Performance Tuning (Large Files)
@ -2066,6 +2084,7 @@ export class Brainy<T = any> implements BrainyInterface<T> {
*
* @see {@link https://brainy.dev/docs/api/import API Documentation}
* @see {@link https://brainy.dev/docs/guides/migrating-to-v4 Migration Guide}
* @see {@link https://brainy.dev/docs/guides/standard-import-progress Standard Progress API (v4.5.0)}
*
* @remarks
* ** Breaking Changes from v3.x:**
@ -2098,7 +2117,7 @@ export class Brainy<T = any> implements BrainyInterface<T> {
async import(
source: Buffer | string | object,
options?: {
format?: 'excel' | 'pdf' | 'csv' | 'json' | 'markdown'
format?: 'excel' | 'pdf' | 'csv' | 'json' | 'markdown' | 'yaml' | 'docx'
vfsPath?: string
groupBy?: 'type' | 'sheet' | 'flat' | 'custom'
customGrouping?: (entity: any) => string

View file

@ -21,6 +21,8 @@ interface AddOptions extends CoreOptions {
id?: string
metadata?: string
type?: string
confidence?: string
weight?: string
}
interface SearchOptions extends CoreOptions {
@ -35,6 +37,7 @@ interface SearchOptions extends CoreOptions {
via?: string
explain?: boolean
includeRelations?: boolean
includeVfs?: boolean
fusion?: string
vectorWeight?: string
graphWeight?: string
@ -163,24 +166,40 @@ export const coreCommands = {
}
// Add with explicit type
const result = await brain.add({
const addParams: any = {
data: text,
type: nounType,
metadata
})
}
// v4.3.x: Add confidence and weight if provided
if (options.confidence) {
addParams.confidence = parseFloat(options.confidence)
}
if (options.weight) {
addParams.weight = parseFloat(options.weight)
}
const result = await brain.add(addParams)
spinner.succeed('Added successfully')
if (!options.json) {
console.log(chalk.green(`✓ Added with ID: ${result}`))
if (options.type) {
console.log(chalk.dim(` Type: ${options.type}`))
}
if (options.confidence) {
console.log(chalk.dim(` Confidence: ${options.confidence}`))
}
if (options.weight) {
console.log(chalk.dim(` Weight: ${options.weight}`))
}
if (Object.keys(metadata).length > 0) {
console.log(chalk.dim(` Metadata: ${JSON.stringify(metadata)}`))
}
} else {
formatOutput({ id: result, metadata }, options)
formatOutput({ id: result, metadata, confidence: addParams.confidence, weight: addParams.weight }, options)
}
} catch (error: any) {
if (spinner) spinner.fail('Failed to add data')
@ -328,6 +347,11 @@ export const coreCommands = {
searchParams.includeRelations = true
}
// Include VFS files (v4.4.0 - find excludes VFS by default)
if (options.includeVfs) {
searchParams.includeVFS = true
}
// Triple Intelligence Fusion - custom weighting
if (options.fusion || options.vectorWeight || options.graphWeight || options.fieldWeight) {
searchParams.fusion = {

View file

@ -149,23 +149,28 @@ export const importCommands = {
options.recursive = answer.recursive
}
spinner = ora('Initializing neural import...').start()
spinner = ora('Initializing import...').start()
const brain = getBrainy()
// Load UniversalImportAPI
const { UniversalImportAPI } = await import('../../api/UniversalImportAPI.js')
const universalImport = new UniversalImportAPI(brain)
await universalImport.init()
spinner.text = 'Processing import...'
// Handle different source types
let result: any
if (isURL) {
// URL import
// URL import - fetch first
spinner.text = `Fetching from ${source}...`
result = await universalImport.importFromURL(source)
const response = await fetch(source)
const buffer = Buffer.from(await response.arrayBuffer())
spinner.text = 'Importing...'
result = await brain.import(buffer, {
enableNeuralExtraction: options.extractEntities !== false,
enableRelationshipInference: options.detectRelationships !== false,
enableConceptExtraction: options.extractConcepts || false,
confidenceThreshold: options.confidence ? parseFloat(options.confidence) : 0.6,
onProgress: options.progress ? (p) => {
spinner.text = `${p.message}${p.entities ? ` (${p.entities} entities)` : ''}`
} : undefined
})
} else if (isDirectory) {
// Directory import - process each file
spinner.text = `Scanning directory: ${source}...`
@ -202,34 +207,45 @@ export const importCommands = {
spinner.succeed(`Found ${files.length} files`)
// Process files in batches
const batchSize = options.batchSize ? parseInt(options.batchSize) : 100
// Process files with progress
let totalEntities = 0
let totalRelationships = 0
let filesProcessed = 0
for (let i = 0; i < files.length; i += batchSize) {
const batch = files.slice(i, i + batchSize)
for (const file of files) {
try {
if (options.progress) {
spinner = ora(`[${filesProcessed + 1}/${files.length}] Importing ${file}...`).start()
}
if (options.progress) {
spinner = ora(`Processing batch ${Math.floor(i / batchSize) + 1}/${Math.ceil(files.length / batchSize)} (${filesProcessed}/${files.length} files)...`).start()
}
const fileResult = await brain.import(file, {
enableNeuralExtraction: options.extractEntities !== false,
enableRelationshipInference: options.detectRelationships !== false,
enableConceptExtraction: options.extractConcepts || false,
confidenceThreshold: options.confidence ? parseFloat(options.confidence) : 0.6,
onProgress: options.progress ? (p) => {
spinner.text = `[${filesProcessed + 1}/${files.length}] ${p.message}`
} : undefined
})
for (const file of batch) {
try {
const fileResult = await universalImport.importFromFile(file)
totalEntities += fileResult.stats.entitiesCreated
totalRelationships += fileResult.stats.relationshipsCreated
filesProcessed++
} catch (error: any) {
if (options.verbose) {
console.log(chalk.yellow(`⚠️ Failed to import ${file}: ${error.message}`))
}
totalEntities += fileResult.entities.length
totalRelationships += fileResult.relationships.length
filesProcessed++
if (options.progress) {
spinner.succeed(`[${filesProcessed}/${files.length}] ${file}`)
}
} catch (error: any) {
if (options.verbose) {
if (spinner) spinner.fail(`Failed: ${file}`)
console.log(chalk.yellow(`⚠️ ${error.message}`))
}
}
}
result = {
entities: [],
relationships: [],
stats: {
filesProcessed,
entitiesCreated: totalEntities,
@ -238,10 +254,22 @@ export const importCommands = {
}
}
spinner.succeed('Directory import complete')
spinner = ora().succeed(`Directory import complete: ${filesProcessed} files`)
} else {
// File import
result = await universalImport.importFromFile(source)
// File import with progress
result = await brain.import(source, {
format: options.format as any,
enableNeuralExtraction: options.extractEntities !== false,
enableRelationshipInference: options.detectRelationships !== false,
enableConceptExtraction: options.extractConcepts || false,
confidenceThreshold: options.confidence ? parseFloat(options.confidence) : 0.6,
onProgress: options.progress ? (p) => {
spinner.text = `${p.message}${p.entities ? ` (${p.entities} entities, ${p.relationships || 0} relationships)` : ''}`
if (p.throughput && p.eta) {
spinner.text += ` - ${p.throughput.toFixed(1)}/sec, ETA: ${Math.round(p.eta / 1000)}s`
}
} : undefined
})
}
spinner.succeed('Import complete')
@ -323,18 +351,26 @@ export const importCommands = {
console.log(chalk.cyan('\n📊 Import Results:\n'))
console.log(chalk.bold('Statistics:'))
console.log(` Entities created: ${chalk.green(result.stats.entitiesCreated)}`)
const entitiesCount = result.stats?.entitiesCreated || result.entities?.length || 0
const relationshipsCount = result.stats?.relationshipsCreated || result.relationships?.length || 0
if (result.stats.relationshipsCreated > 0) {
console.log(` Relationships created: ${chalk.green(result.stats.relationshipsCreated)}`)
console.log(` Entities created: ${chalk.green(entitiesCount)}`)
if (relationshipsCount > 0) {
console.log(` Relationships created: ${chalk.green(relationshipsCount)}`)
}
if (result.stats.filesProcessed) {
if (result.stats?.filesProcessed) {
console.log(` Files processed: ${chalk.green(result.stats.filesProcessed)}`)
}
console.log(` Average confidence: ${chalk.yellow((result.stats.averageConfidence * 100).toFixed(1))}%`)
console.log(` Processing time: ${chalk.dim(result.stats.processingTimeMs)}ms`)
if (result.stats?.averageConfidence) {
console.log(` Average confidence: ${chalk.yellow((result.stats.averageConfidence * 100).toFixed(1))}%`)
}
if (result.stats?.processingTimeMs) {
console.log(` Processing time: ${chalk.dim(result.stats.processingTimeMs)}ms`)
}
if (options.verbose && result.entities && result.entities.length > 0) {
console.log(chalk.bold('\n📦 Imported Entities (first 10):'))

View file

@ -169,10 +169,44 @@ export class SmartCSVImporter {
}
// Parse CSV using existing handler
// v4.5.0: Pass progress hooks to handler for file parsing progress
const processedData = await this.csvHandler.process(buffer, {
...options,
csvDelimiter: opts.csvDelimiter,
csvHeaders: opts.csvHeaders
csvHeaders: opts.csvHeaders,
totalBytes: buffer.length,
progressHooks: {
onBytesProcessed: (bytes) => {
// Handler reports bytes processed during parsing
opts.onProgress?.({
processed: 0,
total: 0,
entities: 0,
relationships: 0,
phase: `Parsing CSV (${Math.round((bytes / buffer.length) * 100)}%)`
})
},
onCurrentItem: (message) => {
// Handler reports current processing step
opts.onProgress?.({
processed: 0,
total: 0,
entities: 0,
relationships: 0,
phase: message
})
},
onDataExtracted: (count, total) => {
// Handler reports rows extracted
opts.onProgress?.({
processed: 0,
total: total || count,
entities: 0,
relationships: 0,
phase: `Extracted ${count} rows`
})
}
}
})
const rows = processedData.data

View file

@ -187,12 +187,26 @@ export class SmartDOCXImporter {
await this.init()
}
// v4.5.0: Report parsing start
options.onProgress?.({
processed: 0,
entities: 0,
relationships: 0
})
// Extract raw text for entity extraction
const textResult = await mammoth.extractRawText({ buffer })
// Extract HTML for structure analysis (headings, tables)
const htmlResult = await mammoth.convertToHtml({ buffer })
// v4.5.0: Report parsing complete
options.onProgress?.({
processed: 0,
entities: 0,
relationships: 0
})
// Process the document
const result = await this.extractFromContent(
textResult.value,

View file

@ -184,7 +184,43 @@ export class SmartExcelImporter {
}
// Parse Excel using existing handler
const processedData = await this.excelHandler.process(buffer, options)
// v4.5.0: Pass progress hooks to handler for file parsing progress
const processedData = await this.excelHandler.process(buffer, {
...options,
totalBytes: buffer.length,
progressHooks: {
onBytesProcessed: (bytes) => {
// Handler reports bytes processed during parsing
opts.onProgress?.({
processed: 0,
total: 0,
entities: 0,
relationships: 0,
phase: `Parsing Excel (${Math.round((bytes / buffer.length) * 100)}%)`
})
},
onCurrentItem: (message) => {
// Handler reports current processing step (e.g., "Reading sheet: Sales (1/3)")
opts.onProgress?.({
processed: 0,
total: 0,
entities: 0,
relationships: 0,
phase: message
})
},
onDataExtracted: (count, total) => {
// Handler reports rows extracted
opts.onProgress?.({
processed: 0,
total: total || count,
entities: 0,
relationships: 0,
phase: `Extracted ${count} rows from Excel`
})
}
}
})
const rows = processedData.data
if (rows.length === 0) {

View file

@ -167,6 +167,13 @@ export class SmartJSONImporter {
...options
}
// v4.5.0: Report parsing start
opts.onProgress({
processed: 0,
entities: 0,
relationships: 0
})
// Parse JSON if string
let jsonData: any
if (typeof data === 'string') {
@ -179,6 +186,13 @@ export class SmartJSONImporter {
jsonData = data
}
// v4.5.0: Report parsing complete, starting traversal
opts.onProgress({
processed: 0,
entities: 0,
relationships: 0
})
// Traverse and extract
const entities: ExtractedJSONEntity[] = []
const relationships: ExtractedJSONRelationship[] = []
@ -214,6 +228,13 @@ export class SmartJSONImporter {
}
)
// v4.5.0: Report completion
opts.onProgress({
processed: nodesProcessed,
entities: entities.length,
relationships: relationships.length
})
return {
nodesProcessed,
entitiesExtracted: entities.length,

View file

@ -174,9 +174,25 @@ export class SmartMarkdownImporter {
...options
}
// v4.5.0: Report parsing start
opts.onProgress({
processed: 0,
total: 0,
entities: 0,
relationships: 0
})
// Parse markdown into sections
const parsedSections = this.parseMarkdown(markdown, opts)
// v4.5.0: Report parsing complete
opts.onProgress({
processed: 0,
total: parsedSections.length,
entities: 0,
relationships: 0
})
// Process each section
const sections: MarkdownSection[] = []
const entityMap = new Map<string, string>()
@ -202,10 +218,20 @@ export class SmartMarkdownImporter {
})
}
// v4.5.0: Report completion
const totalEntities = sections.reduce((sum, s) => sum + s.entities.length, 0)
const totalRelationships = sections.reduce((sum, s) => sum + s.relationships.length, 0)
opts.onProgress({
processed: sections.length,
total: sections.length,
entities: totalEntities,
relationships: totalRelationships
})
return {
sectionsProcessed: sections.length,
entitiesExtracted: sections.reduce((sum, s) => sum + s.entities.length, 0),
relationshipsInferred: sections.reduce((sum, s) => sum + s.relationships.length, 0),
entitiesExtracted: totalEntities,
relationshipsInferred: totalRelationships,
sections,
entityMap,
processingTime: Date.now() - startTime,

View file

@ -181,7 +181,43 @@ export class SmartPDFImporter {
}
// Parse PDF using existing handler
const processedData = await this.pdfHandler.process(buffer, options)
// v4.5.0: Pass progress hooks to handler for file parsing progress
const processedData = await this.pdfHandler.process(buffer, {
...options,
totalBytes: buffer.length,
progressHooks: {
onBytesProcessed: (bytes) => {
// Handler reports bytes processed during parsing
opts.onProgress?.({
processed: 0,
total: 0,
entities: 0,
relationships: 0,
phase: `Parsing PDF (${Math.round((bytes / buffer.length) * 100)}%)`
})
},
onCurrentItem: (message) => {
// Handler reports current processing step (e.g., "Processing page 5 of 23")
opts.onProgress?.({
processed: 0,
total: 0,
entities: 0,
relationships: 0,
phase: message
})
},
onDataExtracted: (count, total) => {
// Handler reports items extracted (paragraphs + tables)
opts.onProgress?.({
processed: 0,
total: total || count,
entities: 0,
relationships: 0,
phase: `Extracted ${count} items from PDF`
})
}
}
})
const data = processedData.data
const pdfMetadata = processedData.metadata.additionalInfo?.pdfMetadata || {}

View file

@ -159,6 +159,13 @@ export class SmartYAMLImporter {
): Promise<SmartYAMLResult> {
const startTime = Date.now()
// v4.5.0: Report parsing start
options.onProgress?.({
processed: 0,
entities: 0,
relationships: 0
})
// Parse YAML to JavaScript object
const yamlString = typeof yamlContent === 'string'
? yamlContent
@ -171,6 +178,13 @@ export class SmartYAMLImporter {
throw new Error(`Failed to parse YAML: ${error.message}`)
}
// v4.5.0: Report parsing complete
options.onProgress?.({
processed: 0,
entities: 0,
relationships: 0
})
// Process as JSON-like structure
const result = await this.extractFromData(data, options)
result.processingTime = Date.now() - startTime

View file

@ -385,6 +385,138 @@ export interface BatchResult<T = any> {
duration: number // Time taken in ms
}
// ============= Import Progress (v4.5.0) =============
/**
* Import stage enumeration
*/
export type ImportStage =
| 'detecting' // Detecting file format
| 'reading' // Reading file from disk/network
| 'parsing' // Parsing file structure (CSV rows, PDF pages, Excel sheets)
| 'extracting' // Extracting entities using AI
| 'indexing' // Creating graph nodes and relationships
| 'completing' // Final cleanup and stats
/**
* Overall import status
*/
export type ImportStatus =
| 'starting' // Initializing import
| 'processing' // Actively importing
| 'completing' // Finalizing
| 'done' // Complete
/**
* Comprehensive import progress information
*
* Provides multi-dimensional progress tracking:
* - Bytes processed (always deterministic)
* - Entities extracted and indexed
* - Stage-specific progress
* - Time estimates
* - Performance metrics
*
* @since v4.5.0
*/
export interface ImportProgress {
// Overall Progress
overall_progress: number // 0-100 weighted estimate across all stages
overall_status: ImportStatus // High-level status
// Current Stage
stage: ImportStage // What's happening now
stage_progress: number // 0-100 within current stage (0 if unknown)
stage_message: string // Human-readable: "Extracting entities from PDF..."
// Bytes (Always Available - most deterministic metric)
bytes_processed: number // Bytes read/processed so far
total_bytes: number // Total file size (0 if streaming/unknown)
bytes_percentage: number // Convenience: bytes_processed / total_bytes * 100
bytes_per_second?: number // Processing rate (relevant during parsing)
// Entities (Available when extraction starts)
entities_extracted: number // Entities found during AI extraction
entities_indexed: number // Entities added to Brainy graph
entities_per_second?: number // Entities/sec (relevant during extraction/indexing)
estimated_total_entities?: number // Estimated final count
estimation_confidence?: number // 0-1 confidence in estimation
// Timing
elapsed_ms: number // Time since import started
estimated_remaining_ms?: number // Estimated time remaining
estimated_total_ms?: number // Estimated total time
// Context (helps users understand what's happening)
current_item?: string // "Processing page 5 of 23"
current_file?: string // "Sheet: Q2 Sales Data"
file_number?: number // 3 (when importing multiple files)
total_files?: number // 10
// Performance Metrics (for debugging/optimization)
metrics?: {
parsing_rate_mbps?: number // MB/s during parsing
extraction_rate_entities_per_sec?: number // Entities/s during extraction
indexing_rate_entities_per_sec?: number // Entities/s during indexing
memory_usage_mb?: number // Current memory usage
peak_memory_mb?: number // Peak memory usage
}
// Backwards Compatibility (for legacy code)
current: number // Alias for entities_indexed
total: number // Alias for estimated_total_entities or 0
}
/**
* Import progress callback - backwards compatible
*
* Supports both legacy (current, total) and new (ImportProgress object) signatures
*/
export type ImportProgressCallback =
| ((progress: ImportProgress) => void)
| ((current: number, total: number) => void)
/**
* Stage weight configuration for overall progress calculation
*
* These weights reflect the typical time distribution across stages.
* Extraction is typically the slowest stage (60% of time).
*/
export interface StageWeights {
detecting: number // Default: 0.01 (1%)
reading: number // Default: 0.05 (5%)
parsing: number // Default: 0.10 (10%)
extracting: number // Default: 0.60 (60% - slowest!)
indexing: number // Default: 0.20 (20%)
completing: number // Default: 0.04 (4%)
}
/**
* Import result statistics
*/
export interface ImportStats {
graphNodesCreated: number // Entities added to graph
graphEdgesCreated: number // Relationships created
vfsFilesCreated: number // VFS files created
duration: number // Total time in ms
bytesProcessed: number // Total bytes read
averageRate: number // Average entities/sec
peakMemoryMB?: number // Peak memory usage
}
/**
* Import operation result
*/
export interface ImportResult {
success: boolean
stats: ImportStats
errors?: Array<{
stage: ImportStage
message: string
error?: any
}>
}
// ============= Advanced Operations =============
/**

View file

@ -0,0 +1,541 @@
/**
* Import Progress Tracker (v4.5.0)
*
* Comprehensive progress tracking for imports with:
* - Multi-dimensional progress (bytes, entities, stages, timing)
* - Smart estimation (entity count, time remaining)
* - Stage-specific metrics (bytes/sec vs entities/sec)
* - Throttled callbacks (avoid spam)
* - Weighted overall progress
*
* @since v4.5.0
*/
import {
ImportProgress,
ImportStage,
ImportStatus,
StageWeights,
ImportProgressCallback
} from '../types/brainy.types.js'
/**
* Default stage weights (reflect typical time distribution)
*/
const DEFAULT_STAGE_WEIGHTS: StageWeights = {
detecting: 0.01, // 1% - very fast
reading: 0.05, // 5% - reading file
parsing: 0.10, // 10% - parsing structure
extracting: 0.60, // 60% - AI extraction (slowest!)
indexing: 0.20, // 20% - creating graph
completing: 0.04 // 4% - cleanup
}
/**
* Stage ordering for progress calculation
*/
const STAGE_ORDER: ImportStage[] = [
'detecting',
'reading',
'parsing',
'extracting',
'indexing',
'completing'
]
/**
* Progress tracker for imports
*/
export class ImportProgressTracker {
// Configuration
private readonly stageWeights: StageWeights
private readonly throttleMs: number
private readonly callback?: ImportProgressCallback
// Tracking state
private startTime: number
private lastEmitTime: number = 0
private currentStage: ImportStage = 'detecting'
private completedStages: Set<ImportStage> = new Set()
// Metrics
private totalBytes: number = 0
private bytesProcessed: number = 0
private entitiesExtracted: number = 0
private entitiesIndexed: number = 0
private parseStartTime?: number
private extractStartTime?: number
private indexStartTime?: number
// Estimation
private lastBytesCheckpoint: number = 0
private lastBytesCheckpointTime: number = 0
private lastEntitiesCheckpoint: number = 0
private lastEntitiesCheckpointTime: number = 0
// Context
private currentItem?: string
private currentFile?: string
private fileNumber?: number
private totalFiles?: number
// Memory tracking
private peakMemoryMB: number = 0
constructor(options: {
totalBytes?: number
stageWeights?: Partial<StageWeights>
throttleMs?: number
callback?: ImportProgressCallback
} = {}) {
this.stageWeights = { ...DEFAULT_STAGE_WEIGHTS, ...options.stageWeights }
this.throttleMs = options.throttleMs ?? 100 // 100ms default
this.callback = options.callback
this.totalBytes = options.totalBytes ?? 0
this.startTime = Date.now()
this.lastBytesCheckpointTime = this.startTime
this.lastEntitiesCheckpointTime = this.startTime
}
/**
* Set total file size (if known later)
*/
setTotalBytes(bytes: number): void {
this.totalBytes = bytes
}
/**
* Update current stage
*/
setStage(stage: ImportStage, message?: string): void {
// Mark previous stage as complete
if (this.currentStage !== stage) {
this.completedStages.add(this.currentStage)
}
this.currentStage = stage
if (message) {
this.setStageMessage(message)
}
// Track stage start times
const now = Date.now()
switch (stage) {
case 'parsing':
this.parseStartTime = now
break
case 'extracting':
this.extractStartTime = now
break
case 'indexing':
this.indexStartTime = now
break
}
// Force emit on stage change
this.emit(true)
}
/**
* Update bytes processed
*/
updateBytes(bytes: number): void {
this.bytesProcessed = bytes
this.emit()
}
/**
* Increment bytes processed
*/
addBytes(bytes: number): void {
this.bytesProcessed += bytes
this.emit()
}
/**
* Update entities extracted
*/
updateEntitiesExtracted(count: number): void {
this.entitiesExtracted = count
this.emit()
}
/**
* Increment entities extracted
*/
addEntitiesExtracted(count: number): void {
this.entitiesExtracted += count
this.emit()
}
/**
* Update entities indexed
*/
updateEntitiesIndexed(count: number): void {
this.entitiesIndexed = count
this.emit()
}
/**
* Increment entities indexed
*/
addEntitiesIndexed(count: number): void {
this.entitiesIndexed += count
this.emit()
}
/**
* Set context information
*/
setContext(context: {
currentItem?: string
currentFile?: string
fileNumber?: number
totalFiles?: number
}): void {
if (context.currentItem !== undefined) this.currentItem = context.currentItem
if (context.currentFile !== undefined) this.currentFile = context.currentFile
if (context.fileNumber !== undefined) this.fileNumber = context.fileNumber
if (context.totalFiles !== undefined) this.totalFiles = context.totalFiles
this.emit()
}
/**
* Set stage message
*/
private setStageMessage(message: string): void {
this.currentItem = message
}
/**
* Calculate stage progress (0-100 within current stage)
*/
private calculateStageProgress(): number {
switch (this.currentStage) {
case 'detecting':
case 'completing':
// These are quick, assume 100% once started
return 100
case 'reading':
case 'parsing':
// Use bytes as proxy for progress
if (this.totalBytes === 0) return 0
return Math.min(100, (this.bytesProcessed / this.totalBytes) * 100)
case 'extracting':
// Extraction progress is hard to estimate (AI is unpredictable)
// We can't reliably say % complete, so return 0
return 0
case 'indexing':
// If we have estimated total entities, use that
if (this.entitiesExtracted > 0) {
return Math.min(100, (this.entitiesIndexed / this.entitiesExtracted) * 100)
}
return 0
default:
return 0
}
}
/**
* Calculate overall progress (0-100 weighted across all stages)
*/
private calculateOverallProgress(): number {
// Calculate progress of completed stages
let completedWeight = 0
for (const stage of this.completedStages) {
completedWeight += this.stageWeights[stage]
}
// Calculate progress of current stage
const stageProgress = this.calculateStageProgress()
const currentStageContribution = this.stageWeights[this.currentStage] * (stageProgress / 100)
// Overall = completed stages + current stage contribution
const overall = (completedWeight + currentStageContribution) * 100
return Math.min(100, Math.max(0, overall))
}
/**
* Calculate bytes per second
*/
private calculateBytesPerSecond(): number | undefined {
const now = Date.now()
const elapsed = now - this.lastBytesCheckpointTime
// Need at least 1 second of data
if (elapsed < 1000) return undefined
const bytesDelta = this.bytesProcessed - this.lastBytesCheckpoint
const bytesPerSec = (bytesDelta / elapsed) * 1000
// Update checkpoint
this.lastBytesCheckpoint = this.bytesProcessed
this.lastBytesCheckpointTime = now
return bytesPerSec > 0 ? bytesPerSec : undefined
}
/**
* Calculate entities per second
*/
private calculateEntitiesPerSecond(): number | undefined {
const now = Date.now()
const elapsed = now - this.lastEntitiesCheckpointTime
// Need at least 1 second of data
if (elapsed < 1000) return undefined
// Use appropriate counter based on stage
const currentCount = this.currentStage === 'indexing'
? this.entitiesIndexed
: this.entitiesExtracted
const entitiesDelta = currentCount - this.lastEntitiesCheckpoint
const entitiesPerSec = (entitiesDelta / elapsed) * 1000
// Update checkpoint
this.lastEntitiesCheckpoint = currentCount
this.lastEntitiesCheckpointTime = now
return entitiesPerSec > 0 ? entitiesPerSec : undefined
}
/**
* Estimate total entities
*/
private estimateTotalEntities(): { count: number, confidence: number } | undefined {
// Only estimate if we've processed some bytes and extracted some entities
if (this.bytesProcessed === 0 || this.entitiesExtracted === 0 || this.totalBytes === 0) {
return undefined
}
// Estimate based on entities per byte
const bytesPercentage = this.bytesProcessed / this.totalBytes
const estimatedTotal = Math.ceil(this.entitiesExtracted / bytesPercentage)
// Confidence increases with more data
const confidence = Math.min(0.95, bytesPercentage)
return { count: estimatedTotal, confidence }
}
/**
* Estimate remaining time
*/
private estimateRemainingTime(): number | undefined {
const now = Date.now()
const elapsed = now - this.startTime
// Need at least 5 seconds of data for reasonable estimate
if (elapsed < 5000) return undefined
const overallProgress = this.calculateOverallProgress()
if (overallProgress === 0) return undefined
// Estimate total time based on current progress
const estimatedTotalMs = (elapsed / overallProgress) * 100
const remainingMs = estimatedTotalMs - elapsed
return remainingMs > 0 ? remainingMs : undefined
}
/**
* Get current memory usage
*/
private getCurrentMemoryMB(): number | undefined {
if (typeof process === 'undefined' || !process.memoryUsage) return undefined
const usage = process.memoryUsage()
const currentMB = usage.heapUsed / 1024 / 1024
// Track peak
this.peakMemoryMB = Math.max(this.peakMemoryMB, currentMB)
return currentMB
}
/**
* Build complete progress object
*/
private buildProgress(): ImportProgress {
const now = Date.now()
const elapsed = now - this.startTime
const stageProgress = this.calculateStageProgress()
const overallProgress = this.calculateOverallProgress()
const bytesPerSec = this.calculateBytesPerSecond()
const entitiesPerSec = this.calculateEntitiesPerSecond()
const entityEstimate = this.estimateTotalEntities()
const remainingMs = this.estimateRemainingTime()
const currentMemoryMB = this.getCurrentMemoryMB()
// Determine overall status
let overallStatus: ImportStatus
if (overallProgress === 0) {
overallStatus = 'starting'
} else if (overallProgress === 100) {
overallStatus = 'done'
} else if (this.currentStage === 'completing') {
overallStatus = 'completing'
} else {
overallStatus = 'processing'
}
// Stage message
let stageMessage: string
if (this.currentItem) {
stageMessage = this.currentItem
} else {
// Default messages
switch (this.currentStage) {
case 'detecting':
stageMessage = 'Detecting file format...'
break
case 'reading':
stageMessage = 'Reading file...'
break
case 'parsing':
stageMessage = 'Parsing file structure...'
break
case 'extracting':
stageMessage = 'Extracting entities using AI...'
break
case 'indexing':
stageMessage = 'Creating graph nodes...'
break
case 'completing':
stageMessage = 'Finalizing import...'
break
default:
stageMessage = 'Processing...'
}
}
// Calculate bytes percentage
const bytesPercentage = this.totalBytes > 0
? (this.bytesProcessed / this.totalBytes) * 100
: 0
// Build metrics object
const metrics: ImportProgress['metrics'] = {
parsing_rate_mbps: this.currentStage === 'parsing' && bytesPerSec
? bytesPerSec / 1_000_000
: undefined,
extraction_rate_entities_per_sec: this.currentStage === 'extracting'
? entitiesPerSec
: undefined,
indexing_rate_entities_per_sec: this.currentStage === 'indexing'
? entitiesPerSec
: undefined,
memory_usage_mb: currentMemoryMB,
peak_memory_mb: this.peakMemoryMB > 0 ? this.peakMemoryMB : undefined
}
const progress: ImportProgress = {
// Overall
overall_progress: overallProgress,
overall_status: overallStatus,
// Stage
stage: this.currentStage,
stage_progress: stageProgress,
stage_message: stageMessage,
// Bytes
bytes_processed: this.bytesProcessed,
total_bytes: this.totalBytes,
bytes_percentage: bytesPercentage,
bytes_per_second: bytesPerSec,
// Entities
entities_extracted: this.entitiesExtracted,
entities_indexed: this.entitiesIndexed,
entities_per_second: entitiesPerSec,
estimated_total_entities: entityEstimate?.count,
estimation_confidence: entityEstimate?.confidence,
// Timing
elapsed_ms: elapsed,
estimated_remaining_ms: remainingMs,
estimated_total_ms: remainingMs ? elapsed + remainingMs : undefined,
// Context
current_item: this.currentItem,
current_file: this.currentFile,
file_number: this.fileNumber,
total_files: this.totalFiles,
// Metrics
metrics,
// Backwards compatibility
current: this.entitiesIndexed,
total: entityEstimate?.count ?? 0
}
return progress
}
/**
* Emit progress (throttled)
*/
private emit(force: boolean = false): void {
if (!this.callback) return
const now = Date.now()
const timeSinceLastEmit = now - this.lastEmitTime
// Throttle unless forced
if (!force && timeSinceLastEmit < this.throttleMs) {
return
}
const progress = this.buildProgress()
// Handle both callback types (legacy and new)
if (this.callback.length === 2) {
// Legacy callback: (current, total) => void
;(this.callback as (current: number, total: number) => void)(
progress.current,
progress.total
)
} else {
// New callback: (progress: ImportProgress) => void
;(this.callback as (progress: ImportProgress) => void)(progress)
}
this.lastEmitTime = now
}
/**
* Force emit (for completion or critical updates)
*/
forceEmit(): void {
this.emit(true)
}
/**
* Get current progress (without emitting)
*/
getProgress(): ImportProgress {
return this.buildProgress()
}
/**
* Mark import as complete
*/
complete(): ImportProgress {
this.currentStage = 'completing'
this.completedStages.add('completing')
const progress = this.buildProgress()
this.forceEmit()
return progress
}
}