@juspay/neurolink 9.1.1 → 9.2.0

package/dist/processors/markup/TextProcessor.d.ts

@@ -0,0 +1,135 @@
+/**
+ * Plain Text File Processor
+ *
+ * Processes plain text files (.txt, .text, .log) with line and word counting,
+ * encoding detection, and automatic truncation for large files.
+ *
+ * Priority: 110 (lower priority - catch-all for text files)
+ *
+ * @module processors/markup/TextProcessor
+ *
+ * @example
+ * ```typescript
+ * import { textProcessor, processText, isTextFile } from "./markup/TextProcessor.js";
+ *
+ * // Check if file is a plain text file
+ * if (isTextFile(mimetype, filename)) {
+ *   const result = await processText(fileInfo);
+ *   if (result.success) {
+ *     console.log('Content:', result.data.content);
+ *     console.log('Lines:', result.data.lineCount);
+ *     console.log('Words:', result.data.wordCount);
+ *     if (result.data.truncated) {
+ *       console.warn('File was truncated due to size');
+ *     }
+ *   }
+ * }
+ * ```
+ */
+import { BaseFileProcessor } from "../base/BaseFileProcessor.js";
+import type { FileInfo, FileProcessingResult, ProcessOptions } from "../base/types.js";
+export type { ProcessedText } from "../base/types.js";
+import type { ProcessedText } from "../base/types.js";
+/**
+ * Text Processor - handles plain text files.
+ *
+ * Features:
+ * - Line and word counting
+ * - Automatic truncation for large files
+ * - UTF-8 encoding support
+ *
+ * Priority: 110 (lower priority - catch-all for text files)
+ *
+ * @example
+ * ```typescript
+ * const processor = new TextProcessor();
+ *
+ * const result = await processor.processFile({
+ *   id: 'txt-123',
+ *   name: 'readme.txt',
+ *   mimetype: 'text/plain',
+ *   size: 1024,
+ *   url: 'https://example.com/readme.txt',
+ * });
+ *
+ * if (result.success) {
+ *   console.log('Content:', result.data.content);
+ *   console.log('Lines:', result.data.lineCount);
+ * }
+ * ```
+ */
+export declare class TextProcessor extends BaseFileProcessor<ProcessedText> {
+    constructor();
+    /**
+     * Build processed text result with content analysis.
+     * Counts lines and words, and truncates if necessary.
+     *
+     * @param buffer - Downloaded file content
+     * @param fileInfo - Original file information
+     * @returns Processed text result with content analysis
+     */
+    protected buildProcessedResult(buffer: Buffer, fileInfo: FileInfo): ProcessedText;
+}
+/**
+ * Singleton text processor instance.
+ * Use this for most processing needs.
+ *
+ * @example
+ * ```typescript
+ * import { textProcessor } from "./markup/TextProcessor.js";
+ *
+ * const result = await textProcessor.processFile(fileInfo);
+ * ```
+ */
+export declare const textProcessor: TextProcessor;
+/**
+ * Check if a file is a plain text file.
+ *
+ * @param mimetype - MIME type of the file
+ * @param filename - Filename (for extension-based detection)
+ * @returns true if the file is a plain text file
+ *
+ * @example
+ * ```typescript
+ * if (isTextFile('text/plain', 'readme.txt')) {
+ *   // Handle as plain text
+ * }
+ *
+ * // Also works with just filename
+ * if (isTextFile('', 'debug.log')) {
+ *   // Handle as text based on extension
+ * }
+ * ```
+ */
+export declare function isTextFile(mimetype: string, filename: string): boolean;
+/**
+ * Process a single plain text file.
+ * Convenience function that uses the singleton processor.
+ *
+ * @param fileInfo - File information (can include URL or buffer)
+ * @param options - Optional processing options (auth headers, timeout, retry config)
+ * @returns Processing result with text content and analysis
+ *
+ * @example
+ * ```typescript
+ * const result = await processText({
+ *   id: 'txt-123',
+ *   name: 'notes.txt',
+ *   mimetype: 'text/plain',
+ *   size: 2048,
+ *   buffer: textBuffer,
+ * });
+ *
+ * if (result.success) {
+ *   console.log('Content:', result.data.content);
+ *   console.log('Lines:', result.data.lineCount);
+ *   console.log('Words:', result.data.wordCount);
+ *   if (result.data.truncated) {
+ *     console.warn('Content was truncated');
+ *   }
+ * } else {
+ *   console.error('Processing failed:', result.error.userMessage);
+ * }
+ * ```
+ */
+export declare function processText(fileInfo: FileInfo, options?: ProcessOptions): Promise<FileProcessingResult<ProcessedText>>;

package/dist/processors/markup/TextProcessor.js

@@ -0,0 +1,188 @@
+/**
+ * Plain Text File Processor
+ *
+ * Processes plain text files (.txt, .text, .log) with line and word counting,
+ * encoding detection, and automatic truncation for large files.
+ *
+ * Priority: 110 (lower priority - catch-all for text files)
+ *
+ * @module processors/markup/TextProcessor
+ *
+ * @example
+ * ```typescript
+ * import { textProcessor, processText, isTextFile } from "./markup/TextProcessor.js";
+ *
+ * // Check if file is a plain text file
+ * if (isTextFile(mimetype, filename)) {
+ *   const result = await processText(fileInfo);
+ *   if (result.success) {
+ *     console.log('Content:', result.data.content);
+ *     console.log('Lines:', result.data.lineCount);
+ *     console.log('Words:', result.data.wordCount);
+ *     if (result.data.truncated) {
+ *       console.warn('File was truncated due to size');
+ *     }
+ *   }
+ * }
+ * ```
+ */
+import { BaseFileProcessor } from "../base/BaseFileProcessor.js";
+import { SIZE_LIMITS } from "../config/index.js";
+// =============================================================================
+// CONSTANTS
+// =============================================================================
+/** Plain text MIME types */
+const SUPPORTED_TEXT_TYPES = ["text/plain"];
+/** Plain text file extensions */
+const SUPPORTED_TEXT_EXTENSIONS = [".txt", ".text", ".log"];
+// =============================================================================
+// TEXT PROCESSOR
+// =============================================================================
+/**
+ * Text Processor - handles plain text files.
+ *
+ * Features:
+ * - Line and word counting
+ * - Automatic truncation for large files
+ * - UTF-8 encoding support
+ *
+ * Priority: 110 (lower priority - catch-all for text files)
+ *
+ * @example
+ * ```typescript
+ * const processor = new TextProcessor();
+ *
+ * const result = await processor.processFile({
+ *   id: 'txt-123',
+ *   name: 'readme.txt',
+ *   mimetype: 'text/plain',
+ *   size: 1024,
+ *   url: 'https://example.com/readme.txt',
+ * });
+ *
+ * if (result.success) {
+ *   console.log('Content:', result.data.content);
+ *   console.log('Lines:', result.data.lineCount);
+ * }
+ * ```
+ */
+export class TextProcessor extends BaseFileProcessor {
+    constructor() {
+        super({
+            maxSizeMB: SIZE_LIMITS.TEXT_MAX_MB,
+            timeoutMs: 30000,
+            supportedMimeTypes: [...SUPPORTED_TEXT_TYPES],
+            supportedExtensions: [...SUPPORTED_TEXT_EXTENSIONS],
+            fileTypeName: "Text",
+            defaultFilename: "document.txt",
+        });
+    }
+    /**
+     * Build processed text result with content analysis.
+     * Counts lines and words, and truncates if necessary.
+     *
+     * @param buffer - Downloaded file content
+     * @param fileInfo - Original file information
+     * @returns Processed text result with content analysis
+     */
+    buildProcessedResult(buffer, fileInfo) {
+        const content = buffer.toString("utf-8");
+        const lines = content.split("\n");
+        const words = content.split(/\s+/).filter((w) => w.length > 0);
+        const filename = this.getFilename(fileInfo);
+        // Truncate if too many lines
+        let finalContent = content;
+        let truncated = false;
+        if (lines.length > SIZE_LIMITS.MAX_SOURCE_CODE_LINES) {
+            truncated = true;
+            finalContent = lines
+                .slice(0, SIZE_LIMITS.MAX_SOURCE_CODE_LINES)
+                .join("\n");
+            finalContent += `\n\n... [Truncated: ${lines.length - SIZE_LIMITS.MAX_SOURCE_CODE_LINES} more lines]`;
+        }
+        return {
+            content: finalContent,
+            lineCount: lines.length,
+            wordCount: words.length,
+            encoding: "utf-8",
+            truncated,
+            buffer,
+            mimetype: fileInfo.mimetype || "text/plain",
+            size: fileInfo.size,
+            filename,
+        };
+    }
+}
+// =============================================================================
+// SINGLETON INSTANCE
+// =============================================================================
+/**
+ * Singleton text processor instance.
+ * Use this for most processing needs.
+ *
+ * @example
+ * ```typescript
+ * import { textProcessor } from "./markup/TextProcessor.js";
+ *
+ * const result = await textProcessor.processFile(fileInfo);
+ * ```
+ */
+export const textProcessor = new TextProcessor();
+// =============================================================================
+// HELPER FUNCTIONS
+// =============================================================================
+/**
+ * Check if a file is a plain text file.
+ *
+ * @param mimetype - MIME type of the file
+ * @param filename - Filename (for extension-based detection)
+ * @returns true if the file is a plain text file
+ *
+ * @example
+ * ```typescript
+ * if (isTextFile('text/plain', 'readme.txt')) {
+ *   // Handle as plain text
+ * }
+ *
+ * // Also works with just filename
+ * if (isTextFile('', 'debug.log')) {
+ *   // Handle as text based on extension
+ * }
+ * ```
+ */
+export function isTextFile(mimetype, filename) {
+    return textProcessor.isFileSupported(mimetype, filename);
+}
+/**
+ * Process a single plain text file.
+ * Convenience function that uses the singleton processor.
+ *
+ * @param fileInfo - File information (can include URL or buffer)
+ * @param options - Optional processing options (auth headers, timeout, retry config)
+ * @returns Processing result with text content and analysis
+ *
+ * @example
+ * ```typescript
+ * const result = await processText({
+ *   id: 'txt-123',
+ *   name: 'notes.txt',
+ *   mimetype: 'text/plain',
+ *   size: 2048,
+ *   buffer: textBuffer,
+ * });
+ *
+ * if (result.success) {
+ *   console.log('Content:', result.data.content);
+ *   console.log('Lines:', result.data.lineCount);
+ *   console.log('Words:', result.data.wordCount);
+ *   if (result.data.truncated) {
+ *     console.warn('Content was truncated');
+ *   }
+ * } else {
+ *   console.error('Processing failed:', result.error.userMessage);
+ * }
+ * ```
+ */
+export async function processText(fileInfo, options) {
+    return textProcessor.processFile(fileInfo, options);
+}

package/dist/processors/markup/index.d.ts

@@ -0,0 +1,66 @@
+/**
+ * Markup Processors Module
+ *
+ * Processors for markup-based file formats that are processed as TEXT
+ * rather than binary data. This includes:
+ * - SVG files (XML-based, despite being in image/* MIME type)
+ * - HTML files (web pages with text extraction)
+ * - Markdown files (documentation with structure analysis)
+ *
+ * @module processors/markup
+ *
+ * @example
+ * ```typescript
+ * import {
+ *   // SVG Processor
+ *   SvgProcessor,
+ *   svgProcessor,
+ *   isSvgFile,
+ *   processSvg,
+ *   type ProcessedSvg,
+ *
+ *   // HTML Processor
+ *   HtmlProcessor,
+ *   htmlProcessor,
+ *   isHtmlFile,
+ *   processHtml,
+ *   type ProcessedHtml,
+ *
+ *   // Markdown Processor
+ *   MarkdownProcessor,
+ *   markdownProcessor,
+ *   isMarkdownFile,
+ *   processMarkdown,
+ *   type ProcessedMarkdown,
+ * } from "./markup/index.js";
+ *
+ * // Process an SVG file
+ * if (isSvgFile(mimetype, filename)) {
+ *   const result = await processSvg(fileInfo);
+ *   if (result.success) {
+ *     console.log(result.data.textContent);
+ *   }
+ * }
+ *
+ * // Process an HTML file
+ * if (isHtmlFile(mimetype, filename)) {
+ *   const result = await processHtml(fileInfo);
+ *   if (result.success) {
+ *     console.log('Title:', result.data.title);
+ *     console.log('Text:', result.data.textContent);
+ *   }
+ * }
+ *
+ * // Process a Markdown file
+ * if (isMarkdownFile(mimetype, filename)) {
+ *   const result = await processMarkdown(fileInfo);
+ *   if (result.success) {
+ *     console.log('Headings:', result.data.headings);
+ *   }
+ * }
+ * ```
+ */
+export { isSvgFile, type ProcessedSvg, processSvg, SvgProcessor, svgProcessor, validateSvgSize, } from "./SvgProcessor.js";
+export { HtmlProcessor, htmlProcessor, isHtmlFile, type ProcessedHtml, processHtml, validateHtmlSize, } from "./HtmlProcessor.js";
+export { isMarkdownFile, MarkdownProcessor, markdownProcessor, type ProcessedMarkdown, processMarkdown, validateMarkdownSize, } from "./MarkdownProcessor.js";
+export { isTextFile, type ProcessedText, processText, TextProcessor, textProcessor, } from "./TextProcessor.js";

package/dist/processors/markup/index.js

@@ -0,0 +1,102 @@
+/**
+ * Markup Processors Module
+ *
+ * Processors for markup-based file formats that are processed as TEXT
+ * rather than binary data. This includes:
+ * - SVG files (XML-based, despite being in image/* MIME type)
+ * - HTML files (web pages with text extraction)
+ * - Markdown files (documentation with structure analysis)
+ *
+ * @module processors/markup
+ *
+ * @example
+ * ```typescript
+ * import {
+ *   // SVG Processor
+ *   SvgProcessor,
+ *   svgProcessor,
+ *   isSvgFile,
+ *   processSvg,
+ *   type ProcessedSvg,
+ *
+ *   // HTML Processor
+ *   HtmlProcessor,
+ *   htmlProcessor,
+ *   isHtmlFile,
+ *   processHtml,
+ *   type ProcessedHtml,
+ *
+ *   // Markdown Processor
+ *   MarkdownProcessor,
+ *   markdownProcessor,
+ *   isMarkdownFile,
+ *   processMarkdown,
+ *   type ProcessedMarkdown,
+ * } from "./markup/index.js";
+ *
+ * // Process an SVG file
+ * if (isSvgFile(mimetype, filename)) {
+ *   const result = await processSvg(fileInfo);
+ *   if (result.success) {
+ *     console.log(result.data.textContent);
+ *   }
+ * }
+ *
+ * // Process an HTML file
+ * if (isHtmlFile(mimetype, filename)) {
+ *   const result = await processHtml(fileInfo);
+ *   if (result.success) {
+ *     console.log('Title:', result.data.title);
+ *     console.log('Text:', result.data.textContent);
+ *   }
+ * }
+ *
+ * // Process a Markdown file
+ * if (isMarkdownFile(mimetype, filename)) {
+ *   const result = await processMarkdown(fileInfo);
+ *   if (result.success) {
+ *     console.log('Headings:', result.data.headings);
+ *   }
+ * }
+ * ```
+ */
+// =============================================================================
+// SVG PROCESSOR
+// =============================================================================
+export { 
+// Helper functions
+isSvgFile, processSvg, 
+// Processor class
+SvgProcessor, 
+// Singleton instance
+svgProcessor, validateSvgSize, } from "./SvgProcessor.js";
+// =============================================================================
+// HTML PROCESSOR
+// =============================================================================
+export { 
+// Processor class
+HtmlProcessor, 
+// Singleton instance
+htmlProcessor, 
+// Helper functions
+isHtmlFile, processHtml, validateHtmlSize, } from "./HtmlProcessor.js";
+// =============================================================================
+// MARKDOWN PROCESSOR
+// =============================================================================
+export { 
+// Helper functions
+isMarkdownFile, 
+// Processor class
+MarkdownProcessor, 
+// Singleton instance
+markdownProcessor, processMarkdown, validateMarkdownSize, } from "./MarkdownProcessor.js";
+// =============================================================================
+// TEXT PROCESSOR
+// =============================================================================
+export { 
+// Helper functions
+isTextFile, processText, 
+// Processor class
+TextProcessor, 
+// Singleton instance
+textProcessor, } from "./TextProcessor.js";