feat: import DOCX/PDF/scanned templates via DeepSeek recognition

Backend pipeline: - POST /api/templates/import (multipart, max 25 MB) - extract.ts: DOCX→mammoth, PDF→pdf-parse, fallback to OCR via tesseract+poppler-utils (pdftoppm renders pages to PNG, tesseract reads with rus+eng) - deepseek.ts: chat completions client with strict JSON response_format - recognize.ts: structured prompt that produces simplified DocBody (string text), postprocessor wraps text in TipTap-compatible JSON, validates with zod schema - prompt enforces placeholder substitution: {{customer.*}}, {{executor.*}}, {{contract.number}}, {{contract.date}}, {{today}} - error codes: NO_OCR / NO_DEEPSEEK_KEY / UNSUPPORTED_MIME / INVALID_DOC_BODY Dockerfile: apk add tesseract-ocr (+rus +eng data), poppler-utils, imagemagick Frontend: - Templates page: ⤴ Загрузить документ → file picker (.docx,.pdf,.png,.jpg) - doc type selector (contract/invoice/act/upd) - import-banner with spinner shows uploading→analyzing stages - on success navigates to /templates/:id (TemplateEdit) for review Reuses DEEPSEEK_API_KEY pattern from Hall-planer. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-01 11:40:28 +03:00
parent 624d378bb5
commit e768d30fb6
13 changed files with 1114 additions and 7 deletions
@@ -0,0 +1,95 @@
+import type { FastifyInstance } from 'fastify';
+import { Prisma } from '@prisma/client';
+import { prisma } from '../../db.js';
+import { getOrganizationId } from '../../lib/org.js';
+import { extractText } from './extract.js';
+import { recognizeTemplate } from './recognize.js';
+
+const MAX_BYTES = 20 * 1024 * 1024; // 20 MB
+
+export async function templatesImportRoutes(app: FastifyInstance) {
+  app.post(
+    '/api/templates/import',
+    { preHandler: app.requireDocPermission('user') },
+    async (req, reply) => {
+      const orgId = getOrganizationId(req);
+      const file = await req.file({ limits: { fileSize: MAX_BYTES } });
+      if (!file) {
+        reply.code(400).send({ error: 'no_file' });
+        return;
+      }
+      const buf = await file.toBuffer();
+      const filename = file.filename || 'template';
+      const mime = file.mimetype || '';
+
+      // Опц. имя/тип передаются полями формы; если нет — определит LLM
+      const fields = (file.fields ?? {}) as Record<string, { value?: string }>;
+      const userName = typeof fields.name?.value === 'string' ? fields.name.value : null;
+      const userDocType = typeof fields.docType?.value === 'string' ? fields.docType.value : null;
+
+      try {
+        // 1) Извлекаем текст
+        const extracted = await extractText(buf, mime, filename);
+        if (extracted.text.trim().length < 30) {
+          reply.code(422).send({
+            error: 'empty_extracted_text',
+            message: 'Не удалось извлечь читаемый текст. Возможно, скан плохого качества.',
+            source: extracted.source,
+          });
+          return;
+        }
+
+        // 2) Распознаём через DeepSeek
+        const recognized = await recognizeTemplate(extracted.text);
+        const docType = (userDocType as 'contract' | 'invoice' | 'act' | 'upd') ?? recognized.docType;
+        const name = userName?.trim() || recognized.title || `Импорт ${new Date().toLocaleDateString('ru-RU')}`;
+
+        const created = await prisma.documentTemplate.create({
+          data: {
+            organizationId: orgId,
+            docType,
+            name,
+            body: recognized.docBody as Prisma.InputJsonValue,
+          },
+        });
+
+        reply.code(201).send({
+          template: created,
+          extractedFrom: extracted.source,
+          textLength: extracted.text.length,
+        });
+      } catch (e) {
+        const err = e as { code?: string; message?: string; status?: number };
+        if (err.code === 'NO_DEEPSEEK_KEY') {
+          reply.code(503).send({ error: 'no_deepseek_key', message: err.message });
+          return;
+        }
+        if (err.code === 'NO_OCR') {
+          reply.code(503).send({ error: 'no_ocr', message: err.message });
+          return;
+        }
+        if (err.code === 'UNSUPPORTED_MIME') {
+          reply.code(415).send({ error: 'unsupported_mime', message: err.message });
+          return;
+        }
+        if (err.code === 'INVALID_DOC_BODY') {
+          reply.code(502).send({
+            error: 'invalid_doc_body',
+            message: 'LLM вернула структуру, не прошедшую валидацию. Попробуйте загрузить ещё раз или отредактировать вручную.',
+          });
+          return;
+        }
+        if (err.code === 'DEEPSEEK_HTTP_ERROR') {
+          reply.code(502).send({
+            error: 'deepseek_error',
+            message: err.message,
+            status: err.status ?? 502,
+          });
+          return;
+        }
+        app.log.error({ err: e }, 'template import failed');
+        reply.code(500).send({ error: 'import_failed', message: err.message ?? 'unknown' });
+      }
+    },
+  );
+}