@credal/actions 0.2.44 → 0.2.46

package/dist/actions/providers/google-oauth/getDriveFileContentById.js

@@ -10,6 +10,7 @@ var __awaiter = (this && this.__awaiter) || function (thisArg, _arguments, P, ge
 import { axiosClient } from "../../util/axiosClient.js";
 import mammoth from "mammoth";
 import { MISSING_AUTH_TOKEN } from "../../util/missingAuthConstants.js";
+import { extractTextFromPdf } from "../../../utils/pdf.js";
 const getDriveFileContentById = (_a) => __awaiter(void 0, [_a], void 0, function* ({ params, authParams, }) {
     if (!authParams.authToken) {
         return { success: false, error: MISSING_AUTH_TOKEN };
@@ -75,10 +76,24 @@ const getDriveFileContentById = (_a) => __awaiter(void 0, [_a], void 0, function
             content = exportRes.data;
         }
         else if (mimeType === "application/pdf") {
-            return {
-                success: false,
-                error: `Failed to parse PDF file - currently unsupported`,
-            };
+            // PDF files - download and extract text using pdfjs-dist
+            const downloadUrl = `https://www.googleapis.com/drive/v3/files/${encodeURIComponent(fileId)}?alt=media${sharedDriveParams}`;
+            const downloadRes = yield axiosClient.get(downloadUrl, {
+                headers: {
+                    Authorization: `Bearer ${authParams.authToken}`,
+                },
+                responseType: "arraybuffer",
+            });
+            try {
+                content = yield extractTextFromPdf(downloadRes.data);
+            }
+            catch (e) {
+                return {
+                    success: false,
+                    error: `Failed to parse PDF document: ${e instanceof Error ? e.message : JSON.stringify(e)}`,
+                };
+            }
+            // Extract text from PDF
         }
         else if (mimeType === "application/vnd.openxmlformats-officedocument.wordprocessingml.document" ||
             mimeType === "application/msword") {
@@ -136,6 +151,8 @@ const getDriveFileContentById = (_a) => __awaiter(void 0, [_a], void 0, function
         if (limit && content.length > limit) {
             content = content.substring(0, limit);
         }
+        // Replace all newline characters with spaces, then collapse multiple spaces
+        content = content.replace(/\r?\n+/g, " ").replace(/ +/g, " ");
         return {
             success: true,
             content,

package/dist/actions/providers/google-oauth/searchDriveByQueryAndGetFileContent.js

@@ -25,33 +25,33 @@ const searchDriveByQueryAndGetFileContent = (_a) => __awaiter(void 0, [_a], void
     if (!searchResult.success) {
         return { success: false, error: searchResult.error, files: [] };
     }
-    // For each file, fetch its content
-    const filesWithContent = [];
+    // For each file, fetch its content in parallel
     const files = (_b = searchResult.files) !== null && _b !== void 0 ? _b : [];
-    for (const file of files) {
+    const contentPromises = files.map((file) => __awaiter(void 0, void 0, void 0, function* () {
         try {
             const contentResult = yield getDriveFileContentById({
                 params: { fileId: file.id, limit: fileSizeLimit !== null && fileSizeLimit !== void 0 ? fileSizeLimit : 1000 },
                 authParams,
             });
-            filesWithContent.push({
+            return {
                 id: file.id,
                 name: file.name,
                 mimeType: file.mimeType,
                 url: file.url,
                 content: contentResult.success ? contentResult.content : undefined,
-            });
+            };
         }
         catch (error) {
             console.error(`Error fetching content for file ${file.id}:`, error);
-            filesWithContent.push({
+            return {
                 id: file.id,
                 name: file.name,
                 mimeType: file.mimeType,
                 url: file.url,
-            });
+            };
         }
-    }
+    }));
+    const filesWithContent = yield Promise.all(contentPromises);
     // Return combined results
     return { success: true, files: filesWithContent };
 });

package/dist/utils/pdf.d.ts

@@ -0,0 +1 @@
+export declare function extractTextFromPdf(buffer: ArrayBuffer): Promise<string>;

package/dist/utils/pdf.js

@@ -0,0 +1,40 @@
+var __awaiter = (this && this.__awaiter) || function (thisArg, _arguments, P, generator) {
+    function adopt(value) { return value instanceof P ? value : new P(function (resolve) { resolve(value); }); }
+    return new (P || (P = Promise))(function (resolve, reject) {
+        function fulfilled(value) { try { step(generator.next(value)); } catch (e) { reject(e); } }
+        function rejected(value) { try { step(generator["throw"](value)); } catch (e) { reject(e); } }
+        function step(result) { result.done ? resolve(result.value) : adopt(result.value).then(fulfilled, rejected); }
+        step((generator = generator.apply(thisArg, _arguments || [])).next());
+    });
+};
+import PDFParser from "pdf2json";
+export function extractTextFromPdf(buffer) {
+    return __awaiter(this, void 0, void 0, function* () {
+        try {
+            const extractedText = yield new Promise((resolve, reject) => {
+                const pdfParser = new PDFParser();
+                pdfParser.on("pdfParser_dataError", (errData) => {
+                    reject(errData.parserError || new Error("PDF parsing failed"));
+                });
+                pdfParser.on("pdfParser_dataReady", (pdfData) => {
+                    try {
+                        const text = pdfData.Pages.map((page) => page.Texts.map((textItem) => {
+                            // Handle cases where R array might be empty or have multiple runs
+                            return textItem.R.map((run) => decodeURIComponent(run.T)).join("");
+                        }).join("")).join("\n");
+                        resolve(text);
+                    }
+                    catch (error) {
+                        reject(error);
+                    }
+                });
+                pdfParser.parseBuffer(Buffer.from(buffer));
+            });
+            return extractedText;
+        }
+        catch (error) {
+            console.error("Error extracting PDF text:", error);
+            throw error;
+        }
+    });
+}

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@credal/actions",
-  "version": "0.2.44",
+  "version": "0.2.46",
   "type": "module",
   "description": "AI Actions by Credal AI",
   "sideEffects": false,
@@ -61,6 +61,7 @@
     "mongodb": "^6.13.1",
     "node-forge": "^1.3.1",
     "octokit": "^4.1.2",
+    "pdf2json": "^3.1.6",
     "resend": "^4.1.2",
     "snowflake-sdk": "^2.0.2",
     "ts-node": "^10.9.2",