@red-hat-developer-hub/backstage-plugin-intelligent-assistant-backend 3.0.0

package/dist/service/notebooks/documents/documentService.cjs.js

@@ -0,0 +1,189 @@
+'use strict';
+
+var errors = require('@backstage/errors');
+var constant = require('../../constant.cjs.js');
+var fileParser = require('./fileParser.cjs.js');
+
+class DocumentService {
+  logger;
+  client;
+  chunkingStrategy;
+  constructor(client, logger, config) {
+    this.client = client;
+    this.logger = logger;
+    const chunkingType = config?.getOptionalString(
+      "intelligent-assistant.notebooks.chunkingStrategy.type"
+    ) || constant.DEFAULT_CHUNKING_STRATEGY_TYPE;
+    if (chunkingType === "static") {
+      this.chunkingStrategy = {
+        type: "static",
+        static: {
+          max_chunk_size_tokens: config?.getOptionalNumber(
+            "intelligent-assistant.notebooks.chunkingStrategy.maxChunkSizeTokens"
+          ) || constant.DEFAULT_MAX_CHUNK_SIZE_TOKENS,
+          chunk_overlap_tokens: config?.getOptionalNumber(
+            "intelligent-assistant.notebooks.chunkingStrategy.chunkOverlapTokens"
+          ) || constant.DEFAULT_CHUNK_OVERLAP_TOKENS
+        }
+      };
+    } else {
+      this.chunkingStrategy = { type: "auto" };
+    }
+  }
+  /**
+   * Find a file by title in vector store
+   * @param sessionId - Vector store ID
+   * @param documentTitle - Document title to search for
+   * @returns File object if found, null otherwise
+   */
+  async findFileByTitle(sessionId, documentTitle) {
+    const filesResponse = await this.client.vectorStores.files.list(sessionId);
+    return filesResponse.data.find(
+      (f) => f.attributes?.title === documentTitle
+    ) || null;
+  }
+  /**
+   * Upload a file to the Files API
+   * @param content - File content as string
+   * @param title - File title/name
+   * @returns File ID from the Files API
+   * @throws Error if upload fails
+   */
+  async uploadFile(content, title) {
+    try {
+      const mimeType = "text/plain";
+      const txtFilename = `${title.replace(/\.[^.]+$/, "")}.txt`;
+      const file = await this.client.files.create({
+        file: await fileParser.toFile(Buffer.from(content, "utf-8"), txtFilename, {
+          type: mimeType
+        }),
+        purpose: "assistants"
+      });
+      this.logger.info(
+        `File created - id: ${file.id}, filename: ${file.filename}`
+      );
+      return file.id;
+    } catch (error) {
+      if (error instanceof Error) {
+        throw error;
+      }
+      throw new Error(`Failed to upload file: ${String(error)}`);
+    }
+  }
+  /**
+   * Upsert a document - create if it doesn't exist, update if it does
+   * @param sessionId - Vector store ID
+   * @param title - Original document title
+   * @param fileType - Document source type (text, pdf, url, etc.)
+   * @param fileId - File ID from Files API
+   * @param newTitle - New title for rename operation (optional)
+   * @returns Upsert result with document ID and status
+   * @throws ConflictError if newTitle conflicts with existing document
+   */
+  async upsertDocument(sessionId, title, fileType, fileId, newTitle) {
+    const existingFile = await this.findFileByTitle(sessionId, title);
+    const createdAt = existingFile?.attributes?.created_at || (/* @__PURE__ */ new Date()).toISOString();
+    if (newTitle && title !== newTitle) {
+      const conflictingFile = await this.findFileByTitle(sessionId, newTitle);
+      if (conflictingFile) {
+        throw new errors.ConflictError(
+          `A document with the title "${newTitle || title}" already exists in this session`
+        );
+      }
+    }
+    if (existingFile) {
+      await this.deleteDocument(sessionId, title);
+    }
+    const vectorStoreFile = await this.client.vectorStores.files.create(
+      sessionId,
+      {
+        file_id: fileId,
+        chunking_strategy: this.chunkingStrategy,
+        attributes: {
+          title: newTitle || title,
+          source_type: fileType,
+          created_at: createdAt,
+          updated_at: (/* @__PURE__ */ new Date()).toISOString()
+        }
+      }
+    );
+    this.logger.info(
+      `Document "${newTitle || title}" (ID: ${title}) upload started with file ${fileId}`
+    );
+    return {
+      document_id: newTitle || title,
+      file_id: fileId,
+      replaced: false,
+      status: vectorStoreFile.status
+    };
+  }
+  /**
+   * Get file processing status
+   * @param sessionId - Vector store ID
+   * @param documentTitle - Document title
+   * @returns File status including processing state, chunk count, and error if any
+   * @throws NotFoundError if document not found
+   */
+  async getFileStatus(sessionId, documentTitle) {
+    const file = await this.findFileByTitle(sessionId, documentTitle);
+    if (!file) {
+      throw new errors.NotFoundError(`Document not found: ${documentTitle}`);
+    }
+    return {
+      status: file.status,
+      chunks_count: file.chunks_count,
+      error: file.last_error?.message
+    };
+  }
+  /**
+   * List all documents in a session
+   * @param sessionId - Vector store ID
+   * @param fileTypeFilter - Optional filter by source type (text, pdf, url, etc.)
+   * @returns Array of session documents
+   */
+  async listDocuments(sessionId, fileTypeFilter) {
+    this.logger.info(`Listing documents for session ${sessionId}`);
+    const filesResponse = await this.client.vectorStores.files.list(sessionId);
+    if (!filesResponse.data || filesResponse.data.length === 0) {
+      return [];
+    }
+    const documents = filesResponse.data.filter((file) => {
+      if (fileTypeFilter && file.attributes?.source_type !== fileTypeFilter) {
+        return false;
+      }
+      return true;
+    }).map((file) => {
+      const attrs = file.attributes || {};
+      return {
+        document_id: attrs.title,
+        source_type: attrs.source_type || "text",
+        created_at: attrs.created_at,
+        updated_at: attrs.updated_at
+      };
+    });
+    this.logger.info(
+      `Found ${documents.length} documents in session ${sessionId}`
+    );
+    return documents;
+  }
+  /**
+   * Delete a document from the vector store and Files API
+   * @param sessionId - Vector store ID
+   * @param documentTitle - Document title to delete
+   * @throws NotFoundError if document not found
+   */
+  async deleteDocument(sessionId, documentTitle) {
+    this.logger.info(`Deleting document ${documentTitle} from ${sessionId}`);
+    const file = await this.findFileByTitle(sessionId, documentTitle);
+    if (!file) {
+      throw new errors.NotFoundError(`Document not found: ${documentTitle}`);
+    }
+    await this.client.vectorStores.files.delete(sessionId, file.id);
+    this.logger.info(
+      `Deleted document ${documentTitle} (file ${file.id}) from session ${sessionId}`
+    );
+  }
+}
+
+exports.DocumentService = DocumentService;
+//# sourceMappingURL=documentService.cjs.js.map

package/dist/service/notebooks/documents/documentService.cjs.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"documentService.cjs.js","sources":["../../../../src/service/notebooks/documents/documentService.ts"],"sourcesContent":["/*\n * Copyright Red Hat, Inc.\n *\n * Licensed under the Apache License, Version 2.0 (the \"License\");\n * you may not use this file except in compliance with the License.\n * You may obtain a copy of the License at\n *\n *     http://www.apache.org/licenses/LICENSE-2.0\n *\n * Unless required by applicable law or agreed to in writing, software\n * distributed under the License is distributed on an \"AS IS\" BASIS,\n * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n * See the License for the specific language governing permissions and\n * limitations under the License.\n */\n\nimport { LoggerService } from '@backstage/backend-plugin-api';\nimport { Config } from '@backstage/config';\nimport { ConflictError, NotFoundError } from '@backstage/errors';\n\nimport {\n  DEFAULT_CHUNK_OVERLAP_TOKENS,\n  DEFAULT_CHUNKING_STRATEGY_TYPE,\n  DEFAULT_MAX_CHUNK_SIZE_TOKENS,\n} from '../../constant';\nimport { SessionDocument, UpsertResult } from '../types/notebooksTypes';\nimport { VectorStoresOperator } from '../VectorStoresOperator';\nimport { toFile } from './fileParser';\n\n/**\n * Service for managing documents within notebook sessions using File-Based API\n * Each session has its own dedicated vector store\n * Uses VectorStoresOperator to proxy through lightspeed-core\n */\nexport class DocumentService {\n  private logger: LoggerService;\n  private client: VectorStoresOperator;\n  private chunkingStrategy: {\n    type: string;\n    static?: { max_chunk_size_tokens: number; chunk_overlap_tokens: number };\n  };\n\n  constructor(\n    client: VectorStoresOperator,\n    logger: LoggerService,\n    config?: Config,\n  ) {\n    this.client = client;\n    this.logger = logger;\n\n    // Chunking strategy configuration\n    const chunkingType =\n      config?.getOptionalString(\n        'intelligent-assistant.notebooks.chunkingStrategy.type',\n      ) || DEFAULT_CHUNKING_STRATEGY_TYPE;\n\n    if (chunkingType === 'static') {\n      this.chunkingStrategy = {\n        type: 'static',\n        static: {\n          max_chunk_size_tokens:\n            config?.getOptionalNumber(\n              'intelligent-assistant.notebooks.chunkingStrategy.maxChunkSizeTokens',\n            ) || DEFAULT_MAX_CHUNK_SIZE_TOKENS,\n          chunk_overlap_tokens:\n            config?.getOptionalNumber(\n              'intelligent-assistant.notebooks.chunkingStrategy.chunkOverlapTokens',\n            ) || DEFAULT_CHUNK_OVERLAP_TOKENS,\n        },\n      };\n    } else {\n      this.chunkingStrategy = { type: 'auto' };\n    }\n  }\n\n  /**\n   * Find a file by title in vector store\n   * @param sessionId - Vector store ID\n   * @param documentTitle - Document title to search for\n   * @returns File object if found, null otherwise\n   */\n  async findFileByTitle(\n    sessionId: string,\n    documentTitle: string,\n  ): Promise<any | null> {\n    const filesResponse = await this.client.vectorStores.files.list(sessionId);\n    return (\n      filesResponse.data.find(\n        (f: any) => f.attributes?.title === documentTitle,\n      ) || null\n    );\n  }\n\n  /**\n   * Upload a file to the Files API\n   * @param content - File content as string\n   * @param title - File title/name\n   * @returns File ID from the Files API\n   * @throws Error if upload fails\n   */\n  async uploadFile(content: string, title: string): Promise<string> {\n    try {\n      // Determine MIME type from file type or default to text/plain\n      const mimeType = 'text/plain';\n      const txtFilename = `${title.replace(/\\.[^.]+$/, '')}.txt`;\n      const file = await this.client.files.create({\n        file: await toFile(Buffer.from(content, 'utf-8'), txtFilename, {\n          type: mimeType,\n        }),\n        purpose: 'assistants',\n      });\n\n      this.logger.info(\n        `File created - id: ${file.id}, filename: ${file.filename}`,\n      );\n      return file.id;\n    } catch (error) {\n      // Preserve the original error type and message\n      if (error instanceof Error) {\n        throw error;\n      }\n      // For non-Error objects, wrap with context\n      throw new Error(`Failed to upload file: ${String(error)}`);\n    }\n  }\n\n  /**\n   * Upsert a document - create if it doesn't exist, update if it does\n   * @param sessionId - Vector store ID\n   * @param title - Original document title\n   * @param fileType - Document source type (text, pdf, url, etc.)\n   * @param fileId - File ID from Files API\n   * @param newTitle - New title for rename operation (optional)\n   * @returns Upsert result with document ID and status\n   * @throws ConflictError if newTitle conflicts with existing document\n   */\n  async upsertDocument(\n    sessionId: string,\n    title: string,\n    fileType: string,\n    fileId: string,\n    newTitle?: string,\n  ): Promise<UpsertResult> {\n    // Find existing file by document_id\n    const existingFile = await this.findFileByTitle(sessionId, title);\n    const createdAt =\n      (existingFile?.attributes?.created_at as string) ||\n      new Date().toISOString();\n\n    if (newTitle && title !== newTitle) {\n      // Check for title conflicts when renaming\n      const conflictingFile = await this.findFileByTitle(sessionId, newTitle);\n\n      if (conflictingFile) {\n        throw new ConflictError(\n          `A document with the title \"${newTitle || title}\" already exists in this session`,\n        );\n      }\n    }\n    if (existingFile) {\n      await this.deleteDocument(sessionId, title);\n    }\n\n    const vectorStoreFile = await this.client.vectorStores.files.create(\n      sessionId,\n      {\n        file_id: fileId,\n        chunking_strategy: this.chunkingStrategy,\n        attributes: {\n          title: newTitle || title,\n          source_type: fileType,\n          created_at: createdAt,\n          updated_at: new Date().toISOString(),\n        },\n      },\n    );\n\n    this.logger.info(\n      `Document \"${newTitle || title}\" (ID: ${title}) upload started with file ${fileId}`,\n    );\n\n    return {\n      document_id: newTitle || title,\n      file_id: fileId,\n      replaced: false,\n      status: vectorStoreFile.status,\n    };\n  }\n\n  /**\n   * Get file processing status\n   * @param sessionId - Vector store ID\n   * @param documentTitle - Document title\n   * @returns File status including processing state, chunk count, and error if any\n   * @throws NotFoundError if document not found\n   */\n  async getFileStatus(\n    sessionId: string,\n    documentTitle: string,\n  ): Promise<{\n    status: 'in_progress' | 'completed' | 'failed' | 'cancelled';\n    chunks_count: number;\n    error?: string;\n  }> {\n    const file = await this.findFileByTitle(sessionId, documentTitle);\n\n    if (!file) {\n      throw new NotFoundError(`Document not found: ${documentTitle}`);\n    }\n    return {\n      status: file.status,\n      chunks_count: file.chunks_count,\n      error: file.last_error?.message,\n    };\n  }\n\n  /**\n   * List all documents in a session\n   * @param sessionId - Vector store ID\n   * @param fileTypeFilter - Optional filter by source type (text, pdf, url, etc.)\n   * @returns Array of session documents\n   */\n  async listDocuments(\n    sessionId: string,\n    fileTypeFilter?: string,\n  ): Promise<SessionDocument[]> {\n    this.logger.info(`Listing documents for session ${sessionId}`);\n\n    // List all files in vector store\n    const filesResponse = await this.client.vectorStores.files.list(sessionId);\n\n    if (!filesResponse.data || filesResponse.data.length === 0) {\n      return [];\n    }\n\n    // Map files to SessionDocument format\n    const documents = filesResponse.data\n      .filter((file: any) => {\n        // Apply file type filter if provided\n        if (fileTypeFilter && file.attributes?.source_type !== fileTypeFilter) {\n          return false;\n        }\n        return true;\n      })\n      .map((file: any) => {\n        const attrs = file.attributes || {};\n        return {\n          document_id: attrs.title,\n          source_type:\n            (attrs.source_type as SessionDocument['source_type']) || 'text',\n          created_at: attrs.created_at,\n          updated_at: attrs.updated_at,\n        };\n      });\n\n    this.logger.info(\n      `Found ${documents.length} documents in session ${sessionId}`,\n    );\n    return documents;\n  }\n\n  /**\n   * Delete a document from the vector store and Files API\n   * @param sessionId - Vector store ID\n   * @param documentTitle - Document title to delete\n   * @throws NotFoundError if document not found\n   */\n  async deleteDocument(\n    sessionId: string,\n    documentTitle: string,\n  ): Promise<void> {\n    this.logger.info(`Deleting document ${documentTitle} from ${sessionId}`);\n\n    const file = await this.findFileByTitle(sessionId, documentTitle);\n\n    if (!file) {\n      throw new NotFoundError(`Document not found: ${documentTitle}`);\n    }\n\n    // Delete from vector store first\n    await this.client.vectorStores.files.delete(sessionId, file.id);\n\n    this.logger.info(\n      `Deleted document ${documentTitle} (file ${file.id}) from session ${sessionId}`,\n    );\n  }\n}\n"],"names":["DEFAULT_CHUNKING_STRATEGY_TYPE","DEFAULT_MAX_CHUNK_SIZE_TOKENS","DEFAULT_CHUNK_OVERLAP_TOKENS","toFile","ConflictError","NotFoundError"],"mappings":";;;;;;AAkCO,MAAM,eAAA,CAAgB;AAAA,EACnB,MAAA;AAAA,EACA,MAAA;AAAA,EACA,gBAAA;AAAA,EAKR,WAAA,CACE,MAAA,EACA,MAAA,EACA,MAAA,EACA;AACA,IAAA,IAAA,CAAK,MAAA,GAAS,MAAA;AACd,IAAA,IAAA,CAAK,MAAA,GAAS,MAAA;AAGd,IAAA,MAAM,eACJ,MAAA,EAAQ,iBAAA;AAAA,MACN;AAAA,KACF,IAAKA,uCAAA;AAEP,IAAA,IAAI,iBAAiB,QAAA,EAAU;AAC7B,MAAA,IAAA,CAAK,gBAAA,GAAmB;AAAA,QACtB,IAAA,EAAM,QAAA;AAAA,QACN,MAAA,EAAQ;AAAA,UACN,uBACE,MAAA,EAAQ,iBAAA;AAAA,YACN;AAAA,WACF,IAAKC,sCAAA;AAAA,UACP,sBACE,MAAA,EAAQ,iBAAA;AAAA,YACN;AAAA,WACF,IAAKC;AAAA;AACT,OACF;AAAA,IACF,CAAA,MAAO;AACL,MAAA,IAAA,CAAK,gBAAA,GAAmB,EAAE,IAAA,EAAM,MAAA,EAAO;AAAA,IACzC;AAAA,EACF;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA,EAQA,MAAM,eAAA,CACJ,SAAA,EACA,aAAA,EACqB;AACrB,IAAA,MAAM,gBAAgB,MAAM,IAAA,CAAK,OAAO,YAAA,CAAa,KAAA,CAAM,KAAK,SAAS,CAAA;AACzE,IAAA,OACE,cAAc,IAAA,CAAK,IAAA;AAAA,MACjB,CAAC,CAAA,KAAW,CAAA,CAAE,UAAA,EAAY,KAAA,KAAU;AAAA,KACtC,IAAK,IAAA;AAAA,EAET;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA,EASA,MAAM,UAAA,CAAW,OAAA,EAAiB,KAAA,EAAgC;AAChE,IAAA,IAAI;AAEF,MAAA,MAAM,QAAA,GAAW,YAAA;AACjB,MAAA,MAAM,cAAc,CAAA,EAAG,KAAA,CAAM,OAAA,CAAQ,UAAA,EAAY,EAAE,CAAC,CAAA,IAAA,CAAA;AACpD,MAAA,MAAM,IAAA,GAAO,MAAM,IAAA,CAAK,MAAA,CAAO,MAAM,MAAA,CAAO;AAAA,QAC1C,IAAA,EAAM,MAAMC,iBAAA,CAAO,MAAA,CAAO,KAAK,OAAA,EAAS,OAAO,GAAG,WAAA,EAAa;AAAA,UAC7D,IAAA,EAAM;AAAA,SACP,CAAA;AAAA,QACD,OAAA,EAAS;AAAA,OACV,CAAA;AAED,MAAA,IAAA,CAAK,MAAA,CAAO,IAAA;AAAA,QACV,CAAA,mBAAA,EAAsB,IAAA,CAAK,EAAE,CAAA,YAAA,EAAe,KAAK,QAAQ,CAAA;AAAA,OAC3D;AACA,MAAA,OAAO,IAAA,CAAK,EAAA;AAAA,IACd,SAAS,KAAA,EAAO;AAEd,MAAA,IAAI,iBAAiB,KAAA,EAAO;AAC1B,QAAA,MAAM,KAAA;AAAA,MACR;AAEA,MAAA,MAAM,IAAI,KAAA,CAAM,CAAA,uBAAA,EAA0B,MAAA,CAAO,KAAK,CAAC,CAAA,CAAE,CAAA;AAAA,IAC3D;AAAA,EACF;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA,EAYA,MAAM,cAAA,CACJ,SAAA,EACA,KAAA,EACA,QAAA,EACA,QACA,QAAA,EACuB;AAEvB,IAAA,MAAM,YAAA,GAAe,MAAM,IAAA,CAAK,eAAA,CAAgB,WAAW,KAAK,CAAA;AAChE,IAAA,MAAM,YACH,YAAA,EAAc,UAAA,EAAY,+BAC3B,IAAI,IAAA,IAAO,WAAA,EAAY;AAEzB,IAAA,IAAI,QAAA,IAAY,UAAU,QAAA,EAAU;AAElC,MAAA,MAAM,eAAA,GAAkB,MAAM,IAAA,CAAK,eAAA,CAAgB,WAAW,QAAQ,CAAA;AAEtE,MAAA,IAAI,eAAA,EAAiB;AACnB,QAAA,MAAM,IAAIC,oBAAA;AAAA,UACR,CAAA,2BAAA,EAA8B,YAAY,KAAK,CAAA,gCAAA;AAAA,SACjD;AAAA,MACF;AAAA,IACF;AACA,IAAA,IAAI,YAAA,EAAc;AAChB,MAAA,MAAM,IAAA,CAAK,cAAA,CAAe,SAAA,EAAW,KAAK,CAAA;AAAA,IAC5C;AAEA,IAAA,MAAM,eAAA,GAAkB,MAAM,IAAA,CAAK,MAAA,CAAO,aAAa,KAAA,CAAM,MAAA;AAAA,MAC3D,SAAA;AAAA,MACA;AAAA,QACE,OAAA,EAAS,MAAA;AAAA,QACT,mBAAmB,IAAA,CAAK,gBAAA;AAAA,QACxB,UAAA,EAAY;AAAA,UACV,OAAO,QAAA,IAAY,KAAA;AAAA,UACnB,WAAA,EAAa,QAAA;AAAA,UACb,UAAA,EAAY,SAAA;AAAA,UACZ,UAAA,EAAA,iBAAY,IAAI,IAAA,EAAK,EAAE,WAAA;AAAY;AACrC;AACF,KACF;AAEA,IAAA,IAAA,CAAK,MAAA,CAAO,IAAA;AAAA,MACV,aAAa,QAAA,IAAY,KAAK,CAAA,OAAA,EAAU,KAAK,8BAA8B,MAAM,CAAA;AAAA,KACnF;AAEA,IAAA,OAAO;AAAA,MACL,aAAa,QAAA,IAAY,KAAA;AAAA,MACzB,OAAA,EAAS,MAAA;AAAA,MACT,QAAA,EAAU,KAAA;AAAA,MACV,QAAQ,eAAA,CAAgB;AAAA,KAC1B;AAAA,EACF;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA,EASA,MAAM,aAAA,CACJ,SAAA,EACA,aAAA,EAKC;AACD,IAAA,MAAM,IAAA,GAAO,MAAM,IAAA,CAAK,eAAA,CAAgB,WAAW,aAAa,CAAA;AAEhE,IAAA,IAAI,CAAC,IAAA,EAAM;AACT,MAAA,MAAM,IAAIC,oBAAA,CAAc,CAAA,oBAAA,EAAuB,aAAa,CAAA,CAAE,CAAA;AAAA,IAChE;AACA,IAAA,OAAO;AAAA,MACL,QAAQ,IAAA,CAAK,MAAA;AAAA,MACb,cAAc,IAAA,CAAK,YAAA;AAAA,MACnB,KAAA,EAAO,KAAK,UAAA,EAAY;AAAA,KAC1B;AAAA,EACF;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA,EAQA,MAAM,aAAA,CACJ,SAAA,EACA,cAAA,EAC4B;AAC5B,IAAA,IAAA,CAAK,MAAA,CAAO,IAAA,CAAK,CAAA,8BAAA,EAAiC,SAAS,CAAA,CAAE,CAAA;AAG7D,IAAA,MAAM,gBAAgB,MAAM,IAAA,CAAK,OAAO,YAAA,CAAa,KAAA,CAAM,KAAK,SAAS,CAAA;AAEzE,IAAA,IAAI,CAAC,aAAA,CAAc,IAAA,IAAQ,aAAA,CAAc,IAAA,CAAK,WAAW,CAAA,EAAG;AAC1D,MAAA,OAAO,EAAC;AAAA,IACV;AAGA,IAAA,MAAM,SAAA,GAAY,aAAA,CAAc,IAAA,CAC7B,MAAA,CAAO,CAAC,IAAA,KAAc;AAErB,MAAA,IAAI,cAAA,IAAkB,IAAA,CAAK,UAAA,EAAY,WAAA,KAAgB,cAAA,EAAgB;AACrE,QAAA,OAAO,KAAA;AAAA,MACT;AACA,MAAA,OAAO,IAAA;AAAA,IACT,CAAC,CAAA,CACA,GAAA,CAAI,CAAC,IAAA,KAAc;AAClB,MAAA,MAAM,KAAA,GAAQ,IAAA,CAAK,UAAA,IAAc,EAAC;AAClC,MAAA,OAAO;AAAA,QACL,aAAa,KAAA,CAAM,KAAA;AAAA,QACnB,WAAA,EACG,MAAM,WAAA,IAAkD,MAAA;AAAA,QAC3D,YAAY,KAAA,CAAM,UAAA;AAAA,QAClB,YAAY,KAAA,CAAM;AAAA,OACpB;AAAA,IACF,CAAC,CAAA;AAEH,IAAA,IAAA,CAAK,MAAA,CAAO,IAAA;AAAA,MACV,CAAA,MAAA,EAAS,SAAA,CAAU,MAAM,CAAA,sBAAA,EAAyB,SAAS,CAAA;AAAA,KAC7D;AACA,IAAA,OAAO,SAAA;AAAA,EACT;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA,EAQA,MAAM,cAAA,CACJ,SAAA,EACA,aAAA,EACe;AACf,IAAA,IAAA,CAAK,OAAO,IAAA,CAAK,CAAA,kBAAA,EAAqB,aAAa,CAAA,MAAA,EAAS,SAAS,CAAA,CAAE,CAAA;AAEvE,IAAA,MAAM,IAAA,GAAO,MAAM,IAAA,CAAK,eAAA,CAAgB,WAAW,aAAa,CAAA;AAEhE,IAAA,IAAI,CAAC,IAAA,EAAM;AACT,MAAA,MAAM,IAAIA,oBAAA,CAAc,CAAA,oBAAA,EAAuB,aAAa,CAAA,CAAE,CAAA;AAAA,IAChE;AAGA,IAAA,MAAM,KAAK,MAAA,CAAO,YAAA,CAAa,MAAM,MAAA,CAAO,SAAA,EAAW,KAAK,EAAE,CAAA;AAE9D,IAAA,IAAA,CAAK,MAAA,CAAO,IAAA;AAAA,MACV,oBAAoB,aAAa,CAAA,OAAA,EAAU,IAAA,CAAK,EAAE,kBAAkB,SAAS,CAAA;AAAA,KAC/E;AAAA,EACF;AACF;;;;"}

package/dist/service/notebooks/documents/fileParser.cjs.js

@@ -0,0 +1,139 @@
+'use strict';
+
+var errors = require('@backstage/errors');
+var yaml = require('js-yaml');
+var pdfjsLib = require('pdfjs-dist');
+var stream = require('stream');
+var constant = require('../../constant.cjs.js');
+
+function _interopNamespaceCompat(e) {
+  if (e && typeof e === 'object' && 'default' in e) return e;
+  var n = Object.create(null);
+  if (e) {
+    Object.keys(e).forEach(function (k) {
+      if (k !== 'default') {
+        var d = Object.getOwnPropertyDescriptor(e, k);
+        Object.defineProperty(n, k, d.get ? d : {
+          enumerable: true,
+          get: function () { return e[k]; }
+        });
+      }
+    });
+  }
+  n.default = e;
+  return Object.freeze(n);
+}
+
+var yaml__namespace = /*#__PURE__*/_interopNamespaceCompat(yaml);
+var pdfjsLib__namespace = /*#__PURE__*/_interopNamespaceCompat(pdfjsLib);
+
+function parseTextFile(buffer, fileName, fileType) {
+  const content = buffer.toString("utf-8");
+  return {
+    content,
+    metadata: {
+      fileName,
+      fileType,
+      parseTimestamp: (/* @__PURE__ */ new Date()).toISOString()
+    }
+  };
+}
+function parseJSONFile(buffer, fileName, fileType) {
+  try {
+    const content = buffer.toString("utf-8");
+    JSON.parse(content);
+    return {
+      content,
+      metadata: {
+        fileName,
+        fileType,
+        parseTimestamp: (/* @__PURE__ */ new Date()).toISOString()
+      }
+    };
+  } catch (error) {
+    throw new errors.InputError(`Invalid JSON file: ${error}`);
+  }
+}
+function parseYAMLFile(buffer, fileName, fileType) {
+  try {
+    const content = buffer.toString("utf-8");
+    yaml__namespace.load(content);
+    return {
+      content,
+      metadata: {
+        fileName,
+        fileType,
+        parseTimestamp: (/* @__PURE__ */ new Date()).toISOString()
+      }
+    };
+  } catch (error) {
+    throw new errors.InputError(`Invalid YAML file: ${error}`);
+  }
+}
+async function parsePDFFile(buffer, fileName, fileType) {
+  try {
+    const loadingTask = pdfjsLib__namespace.getDocument({
+      data: new Uint8Array(buffer),
+      useSystemFonts: true
+    });
+    const pdf = await loadingTask.promise;
+    const textParts = [];
+    for (let pageNum = 1; pageNum <= pdf.numPages; pageNum++) {
+      const page = await pdf.getPage(pageNum);
+      const textContent = await page.getTextContent();
+      const pageText = textContent.items.map((item) => {
+        if ("str" in item) {
+          return item.str;
+        }
+        return "";
+      }).filter((str) => str.trim().length > 0).join(" ");
+      if (pageText.trim().length > 0) {
+        textParts.push(`--- Page ${pageNum} ---
+${pageText}`);
+      }
+    }
+    const content = textParts.join("\n\n");
+    return {
+      content,
+      metadata: {
+        fileName,
+        fileType,
+        pageCount: pdf.numPages,
+        parseTimestamp: (/* @__PURE__ */ new Date()).toISOString()
+      }
+    };
+  } catch (error) {
+    throw new errors.InputError(`Error parsing PDF: ${error}`);
+  }
+}
+async function parseFile(buffer, fileName, fileType) {
+  const normalizedType = fileType.toLowerCase().replace(/^\./, "");
+  switch (normalizedType) {
+    case constant.SupportedFileType.MARKDOWN:
+    case constant.SupportedFileType.TEXT:
+    case constant.SupportedFileType.LOG:
+      return parseTextFile(buffer, fileName, fileType);
+    case constant.SupportedFileType.JSON:
+      return parseJSONFile(buffer, fileName, fileType);
+    case constant.SupportedFileType.YAML:
+    case constant.SupportedFileType.YML:
+      return parseYAMLFile(buffer, fileName, fileType);
+    case constant.SupportedFileType.PDF:
+      return parsePDFFile(buffer, fileName, fileType);
+    default:
+      throw new errors.InputError(`Unsupported file type: ${fileType}`);
+  }
+}
+async function toFile(buffer, filename, options) {
+  const stream$1 = stream.Readable.from(buffer);
+  return {
+    name: filename,
+    stream: stream$1,
+    buffer,
+    type: options?.type || "application/octet-stream"
+  };
+}
+
+exports.parseFile = parseFile;
+exports.toFile = toFile;
+//# sourceMappingURL=fileParser.cjs.js.map

package/dist/service/notebooks/documents/fileParser.cjs.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"fileParser.cjs.js","sources":["../../../../src/service/notebooks/documents/fileParser.ts"],"sourcesContent":["/*\n * Copyright Red Hat, Inc.\n *\n * Licensed under the Apache License, Version 2.0 (the \"License\");\n * you may not use this file except in compliance with the License.\n * You may obtain a copy of the License at\n *\n *     http://www.apache.org/licenses/LICENSE-2.0\n *\n * Unless required by applicable law or agreed to in writing, software\n * distributed under the License is distributed on an \"AS IS\" BASIS,\n * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n * See the License for the specific language governing permissions and\n * limitations under the License.\n */\n\nimport { InputError } from '@backstage/errors';\n\nimport * as yaml from 'js-yaml';\nimport * as pdfjsLib from 'pdfjs-dist';\n\nimport { Readable } from 'stream';\n\nimport { SupportedFileType } from '../../constant';\n\nexport interface ParsedDocument {\n  content: string;\n  metadata: {\n    fileName: string;\n    fileType: string;\n    pageCount?: number;\n    parseTimestamp: string;\n  };\n}\n\n/**\n * Parse text-based files (md, txt, log)\n */\nfunction parseTextFile(\n  buffer: Buffer,\n  fileName: string,\n  fileType: string,\n): ParsedDocument {\n  const content = buffer.toString('utf-8');\n\n  return {\n    content,\n    metadata: {\n      fileName,\n      fileType,\n      parseTimestamp: new Date().toISOString(),\n    },\n  };\n}\n\n/**\n * Parse JSON files\n */\nfunction parseJSONFile(\n  buffer: Buffer,\n  fileName: string,\n  fileType: string,\n): ParsedDocument {\n  try {\n    const content = buffer.toString('utf-8');\n    // Validate JSON but keep original formatting\n    JSON.parse(content);\n\n    return {\n      content,\n      metadata: {\n        fileName,\n        fileType,\n        parseTimestamp: new Date().toISOString(),\n      },\n    };\n  } catch (error) {\n    throw new InputError(`Invalid JSON file: ${error}`);\n  }\n}\n\n/**\n * Parse YAML files\n */\nfunction parseYAMLFile(\n  buffer: Buffer,\n  fileName: string,\n  fileType: string,\n): ParsedDocument {\n  try {\n    const content = buffer.toString('utf-8');\n    // Validate YAML but keep original formatting and comments\n    yaml.load(content);\n\n    return {\n      content,\n      metadata: {\n        fileName,\n        fileType,\n        parseTimestamp: new Date().toISOString(),\n      },\n    };\n  } catch (error) {\n    throw new InputError(`Invalid YAML file: ${error}`);\n  }\n}\n\n/**\n * Parse PDF files\n * Extracts text content from PDF using PDF.js\n */\nasync function parsePDFFile(\n  buffer: Buffer,\n  fileName: string,\n  fileType: string,\n): Promise<ParsedDocument> {\n  try {\n    const loadingTask = pdfjsLib.getDocument({\n      data: new Uint8Array(buffer),\n      useSystemFonts: true,\n    });\n\n    const pdf = await loadingTask.promise;\n    const textParts: string[] = [];\n\n    // Extract text from each page\n    for (let pageNum = 1; pageNum <= pdf.numPages; pageNum++) {\n      const page = await pdf.getPage(pageNum);\n      const textContent = await page.getTextContent();\n\n      const pageText = textContent.items\n        .map((item: any) => {\n          if ('str' in item) {\n            return item.str;\n          }\n          return '';\n        })\n        .filter((str: string) => str.trim().length > 0)\n        .join(' ');\n\n      if (pageText.trim().length > 0) {\n        textParts.push(`--- Page ${pageNum} ---\\n${pageText}`);\n      }\n    }\n\n    const content = textParts.join('\\n\\n');\n\n    return {\n      content,\n      metadata: {\n        fileName,\n        fileType,\n        pageCount: pdf.numPages,\n        parseTimestamp: new Date().toISOString(),\n      },\n    };\n  } catch (error) {\n    throw new InputError(`Error parsing PDF: ${error}`);\n  }\n}\n\n/**\n * Parse file based on its type\n * @param buffer - File buffer\n * @param fileName - File name\n * @param fileType - File type (md, txt, pdf, json, yaml, yml, log)\n * @returns Parsed document with content and metadata\n */\nexport async function parseFile(\n  buffer: Buffer,\n  fileName: string,\n  fileType: string,\n): Promise<ParsedDocument> {\n  // Normalize file type: lowercase and remove leading dot\n  const normalizedType = fileType.toLowerCase().replace(/^\\./, '');\n\n  switch (normalizedType) {\n    case SupportedFileType.MARKDOWN:\n    case SupportedFileType.TEXT:\n    case SupportedFileType.LOG:\n      return parseTextFile(buffer, fileName, fileType);\n\n    case SupportedFileType.JSON:\n      return parseJSONFile(buffer, fileName, fileType);\n\n    case SupportedFileType.YAML:\n    case SupportedFileType.YML:\n      return parseYAMLFile(buffer, fileName, fileType);\n\n    case SupportedFileType.PDF:\n      return parsePDFFile(buffer, fileName, fileType);\n\n    default:\n      throw new InputError(`Unsupported file type: ${fileType}`);\n  }\n}\n\n/**\n * File-like object interface matching what toFile() returns\n */\nexport interface FileObject {\n  name: string;\n  stream: Readable;\n  buffer: Buffer;\n  type: string;\n}\n\n/**\n * Convert Buffer to File-like object for upload\n */\nexport async function toFile(\n  buffer: Buffer,\n  filename: string,\n  options?: { type?: string },\n): Promise<FileObject> {\n  const stream = Readable.from(buffer);\n\n  return {\n    name: filename,\n    stream,\n    buffer,\n    type: options?.type || 'application/octet-stream',\n  };\n}\n"],"names":["InputError","yaml","pdfjsLib","SupportedFileType","stream","Readable"],"mappings":";;;;;;;;;;;;;;;;;;;;;;;;;;;;;AAsCA,SAAS,aAAA,CACP,MAAA,EACA,QAAA,EACA,QAAA,EACgB;AAChB,EAAA,MAAM,OAAA,GAAU,MAAA,CAAO,QAAA,CAAS,OAAO,CAAA;AAEvC,EAAA,OAAO;AAAA,IACL,OAAA;AAAA,IACA,QAAA,EAAU;AAAA,MACR,QAAA;AAAA,MACA,QAAA;AAAA,MACA,cAAA,EAAA,iBAAgB,IAAI,IAAA,EAAK,EAAE,WAAA;AAAY;AACzC,GACF;AACF;AAKA,SAAS,aAAA,CACP,MAAA,EACA,QAAA,EACA,QAAA,EACgB;AAChB,EAAA,IAAI;AACF,IAAA,MAAM,OAAA,GAAU,MAAA,CAAO,QAAA,CAAS,OAAO,CAAA;AAEvC,IAAA,IAAA,CAAK,MAAM,OAAO,CAAA;AAElB,IAAA,OAAO;AAAA,MACL,OAAA;AAAA,MACA,QAAA,EAAU;AAAA,QACR,QAAA;AAAA,QACA,QAAA;AAAA,QACA,cAAA,EAAA,iBAAgB,IAAI,IAAA,EAAK,EAAE,WAAA;AAAY;AACzC,KACF;AAAA,EACF,SAAS,KAAA,EAAO;AACd,IAAA,MAAM,IAAIA,iBAAA,CAAW,CAAA,mBAAA,EAAsB,KAAK,CAAA,CAAE,CAAA;AAAA,EACpD;AACF;AAKA,SAAS,aAAA,CACP,MAAA,EACA,QAAA,EACA,QAAA,EACgB;AAChB,EAAA,IAAI;AACF,IAAA,MAAM,OAAA,GAAU,MAAA,CAAO,QAAA,CAAS,OAAO,CAAA;AAEvC,IAAAC,eAAA,CAAK,KAAK,OAAO,CAAA;AAEjB,IAAA,OAAO;AAAA,MACL,OAAA;AAAA,MACA,QAAA,EAAU;AAAA,QACR,QAAA;AAAA,QACA,QAAA;AAAA,QACA,cAAA,EAAA,iBAAgB,IAAI,IAAA,EAAK,EAAE,WAAA;AAAY;AACzC,KACF;AAAA,EACF,SAAS,KAAA,EAAO;AACd,IAAA,MAAM,IAAID,iBAAA,CAAW,CAAA,mBAAA,EAAsB,KAAK,CAAA,CAAE,CAAA;AAAA,EACpD;AACF;AAMA,eAAe,YAAA,CACb,MAAA,EACA,QAAA,EACA,QAAA,EACyB;AACzB,EAAA,IAAI;AACF,IAAA,MAAM,WAAA,GAAcE,oBAAS,WAAA,CAAY;AAAA,MACvC,IAAA,EAAM,IAAI,UAAA,CAAW,MAAM,CAAA;AAAA,MAC3B,cAAA,EAAgB;AAAA,KACjB,CAAA;AAED,IAAA,MAAM,GAAA,GAAM,MAAM,WAAA,CAAY,OAAA;AAC9B,IAAA,MAAM,YAAsB,EAAC;AAG7B,IAAA,KAAA,IAAS,OAAA,GAAU,CAAA,EAAG,OAAA,IAAW,GAAA,CAAI,UAAU,OAAA,EAAA,EAAW;AACxD,MAAA,MAAM,IAAA,GAAO,MAAM,GAAA,CAAI,OAAA,CAAQ,OAAO,CAAA;AACtC,MAAA,MAAM,WAAA,GAAc,MAAM,IAAA,CAAK,cAAA,EAAe;AAE9C,MAAA,MAAM,QAAA,GAAW,WAAA,CAAY,KAAA,CAC1B,GAAA,CAAI,CAAC,IAAA,KAAc;AAClB,QAAA,IAAI,SAAS,IAAA,EAAM;AACjB,UAAA,OAAO,IAAA,CAAK,GAAA;AAAA,QACd;AACA,QAAA,OAAO,EAAA;AAAA,MACT,CAAC,CAAA,CACA,MAAA,CAAO,CAAC,GAAA,KAAgB,GAAA,CAAI,IAAA,EAAK,CAAE,MAAA,GAAS,CAAC,CAAA,CAC7C,IAAA,CAAK,GAAG,CAAA;AAEX,MAAA,IAAI,QAAA,CAAS,IAAA,EAAK,CAAE,MAAA,GAAS,CAAA,EAAG;AAC9B,QAAA,SAAA,CAAU,IAAA,CAAK,YAAY,OAAO,CAAA;AAAA,EAAS,QAAQ,CAAA,CAAE,CAAA;AAAA,MACvD;AAAA,IACF;AAEA,IAAA,MAAM,OAAA,GAAU,SAAA,CAAU,IAAA,CAAK,MAAM,CAAA;AAErC,IAAA,OAAO;AAAA,MACL,OAAA;AAAA,MACA,QAAA,EAAU;AAAA,QACR,QAAA;AAAA,QACA,QAAA;AAAA,QACA,WAAW,GAAA,CAAI,QAAA;AAAA,QACf,cAAA,EAAA,iBAAgB,IAAI,IAAA,EAAK,EAAE,WAAA;AAAY;AACzC,KACF;AAAA,EACF,SAAS,KAAA,EAAO;AACd,IAAA,MAAM,IAAIF,iBAAA,CAAW,CAAA,mBAAA,EAAsB,KAAK,CAAA,CAAE,CAAA;AAAA,EACpD;AACF;AASA,eAAsB,SAAA,CACpB,MAAA,EACA,QAAA,EACA,QAAA,EACyB;AAEzB,EAAA,MAAM,iBAAiB,QAAA,CAAS,WAAA,EAAY,CAAE,OAAA,CAAQ,OAAO,EAAE,CAAA;AAE/D,EAAA,QAAQ,cAAA;AAAgB,IACtB,KAAKG,0BAAA,CAAkB,QAAA;AAAA,IACvB,KAAKA,0BAAA,CAAkB,IAAA;AAAA,IACvB,KAAKA,0BAAA,CAAkB,GAAA;AACrB,MAAA,OAAO,aAAA,CAAc,MAAA,EAAQ,QAAA,EAAU,QAAQ,CAAA;AAAA,IAEjD,KAAKA,0BAAA,CAAkB,IAAA;AACrB,MAAA,OAAO,aAAA,CAAc,MAAA,EAAQ,QAAA,EAAU,QAAQ,CAAA;AAAA,IAEjD,KAAKA,0BAAA,CAAkB,IAAA;AAAA,IACvB,KAAKA,0BAAA,CAAkB,GAAA;AACrB,MAAA,OAAO,aAAA,CAAc,MAAA,EAAQ,QAAA,EAAU,QAAQ,CAAA;AAAA,IAEjD,KAAKA,0BAAA,CAAkB,GAAA;AACrB,MAAA,OAAO,YAAA,CAAa,MAAA,EAAQ,QAAA,EAAU,QAAQ,CAAA;AAAA,IAEhD;AACE,MAAA,MAAM,IAAIH,iBAAA,CAAW,CAAA,uBAAA,EAA0B,QAAQ,CAAA,CAAE,CAAA;AAAA;AAE/D;AAeA,eAAsB,MAAA,CACpB,MAAA,EACA,QAAA,EACA,OAAA,EACqB;AACrB,EAAA,MAAMI,QAAA,GAASC,eAAA,CAAS,IAAA,CAAK,MAAM,CAAA;AAEnC,EAAA,OAAO;AAAA,IACL,IAAA,EAAM,QAAA;AAAA,YACND,QAAA;AAAA,IACA,MAAA;AAAA,IACA,IAAA,EAAM,SAAS,IAAA,IAAQ;AAAA,GACzB;AACF;;;;;"}