Add support for reading PDF and docx files

src/ClaudeDev.ts

@@ -27,6 +27,7 @@ import { ClaudeAskResponse } from "./shared/WebviewMessage"
 import { findLast, findLastIndex } from "./utils"
 import { truncateHalfConversation } from "./utils/context-management"
 import { regexSearchFiles } from "./utils/ripgrep"
+import { extractTextFromFile } from "./utils/extract-text"
 
 const SYSTEM_PROMPT =
 	() => `You are Claude Dev, a highly skilled software developer with extensive knowledge in many programming languages, frameworks, design patterns, and best practices.
@@ -924,7 +925,7 @@ export class ClaudeDev {
 		}
 		try {
 			const absolutePath = path.resolve(cwd, relPath)
-			const content = await fs.readFile(absolutePath, "utf-8")
+			const content = await extractTextFromFile(absolutePath)
 
 			const message = JSON.stringify({
 				tool: "readFile",

src/utils/extract-text.ts

@@ -0,0 +1,38 @@
+import * as path from "path"
+import pdf from "pdf-parse"
+import mammoth from "mammoth"
+import { isBinaryFile } from "isbinaryfile"
+import fs from "fs/promises"
+
+export async function extractTextFromFile(filePath: string): Promise<string> {
+	try {
+		await fs.access(filePath)
+	} catch (error) {
+		throw new Error(`File not found: ${filePath}`)
+	}
+	const fileExtension = path.extname(filePath).toLowerCase()
+	switch (fileExtension) {
+		case ".pdf":
+			return extractTextFromPDF(filePath)
+		case ".docx":
+			return extractTextFromDOCX(filePath)
+		default:
+			const isBinary = await isBinaryFile(filePath)
+			if (!isBinary) {
+				return await fs.readFile(filePath, "utf8")
+			} else {
+				throw new Error(`Unsupported file type: ${fileExtension}`)
+			}
+	}
+}
+
+async function extractTextFromPDF(filePath: string): Promise<string> {
+	const dataBuffer = await fs.readFile(filePath)
+	const data = await pdf(dataBuffer)
+	return data.text
+}
+
+async function extractTextFromDOCX(filePath: string): Promise<string> {
+	const result = await mammoth.extractRawText({ path: filePath })
+	return result.value
+}