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

@ -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