OCR/spec.md at 57070af3075ff036cb43e99a14ad2e096fbd892f

egg/OCR

Files

egg 8d9b69ba93 feat: add document translation via DIFY AI API

Implement document translation feature using DIFY AI API with batch processing:

Backend:
- Add DIFY client with batch translation support (5000 chars, 20 items per batch)
- Add translation service with element extraction and result building
- Add translation router with start/status/result/list/delete endpoints
- Add translation schemas (TranslationRequest, TranslationStatus, etc.)

Frontend:
- Enable translation UI in TaskDetailPage
- Add translation API methods to apiV2.ts
- Add translation types

Features:
- Batch translation with numbered markers [1], [2], [3]...
- Support for text, title, header, footer, paragraph, footnote, table cells
- Translation result JSON with statistics (tokens, latency, batch_count)
- Background task processing with progress tracking

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

Co-Authored-By: Claude <noreply@anthropic.com>

2025-12-02 11:57:02 +08:00

2.3 KiB

Raw Blame History

ADDED Requirements

Requirement: Translation Result JSON Export

The system SHALL support exporting translation results as independent JSON files following a defined schema.

Scenario: Export translation result JSON

WHEN translation completes for a document
THEN system SHALL save translation to {filename}_translated_{lang}.json
AND file SHALL be stored alongside original {filename}_result.json
AND original result file SHALL remain unchanged

Scenario: Translation JSON schema compliance

WHEN translation result is saved
THEN JSON SHALL include schema_version field ("1.0.0")
AND SHALL include source_document reference
AND SHALL include source_lang and target_lang
AND SHALL include provider identifier (e.g., "dify")
AND SHALL include translated_at timestamp
AND SHALL include translations dict mapping element_id to translated content

Scenario: Translation statistics in export

WHEN translation result is saved
THEN JSON SHALL include statistics object with:
- total_elements: count of all elements in document
- translated_elements: count of successfully translated elements
- skipped_elements: count of non-translatable elements (images, charts, etc.)
- total_characters: character count of translated text
- processing_time_seconds: translation duration

Scenario: Table cell translation in export

WHEN document contains tables

THEN translation JSON SHALL represent table translations as:

{
  "table_1_0": {
    "cells": [
      {"row": 0, "col": 0, "content": "Translated cell text"},
      {"row": 0, "col": 1, "content": "Another cell"}
    ]
  }
}

AND row/col positions SHALL match original table structure

Scenario: Download translation result via API

WHEN GET request to /api/v2/translate/{task_id}/result?lang={lang}
THEN system SHALL return translation JSON content
AND Content-Type SHALL be application/json
AND response SHALL include appropriate cache headers

Scenario: List available translations

WHEN GET request to /api/v2/tasks/{task_id}/translations
THEN system SHALL return list of available translation languages
AND include translation metadata (translated_at, provider, statistics)

2.3 KiB Raw Blame History