@jbctechsolutions/mcp-office365 2.5.1

package/dist/parsers/html-stripper.js

@@ -0,0 +1,179 @@
+/**
+ * Copyright (c) 2026 JBC Tech Solutions, LLC
+ * Licensed under the MIT License. See LICENSE file in the project root.
+ */
+/**
+ * Simple HTML to plain text converter.
+ *
+ * Uses regex-based approach to avoid heavy dependencies.
+ * Handles common HTML patterns found in emails.
+ */
+/**
+ * Named HTML entities and their text equivalents.
+ */
+const HTML_ENTITIES = {
+    ' ': ' ',
+    '&': '&',
+    '&lt;': '<',
+    '&gt;': '>',
+    '&quot;': '"',
+    '&apos;': "'",
+    '&#39;': "'",
+    '&copy;': '\u00A9',
+    '&reg;': '\u00AE',
+    '&trade;': '\u2122',
+    '&mdash;': '\u2014',
+    '&ndash;': '\u2013',
+    '&hellip;': '\u2026',
+    '&lsquo;': '\u2018',
+    '&rsquo;': '\u2019',
+    '&ldquo;': '\u201C',
+    '&rdquo;': '\u201D',
+    '&bull;': '\u2022',
+    '&middot;': '\u00B7',
+    '&euro;': '\u20AC',
+    '&pound;': '\u00A3',
+    '&yen;': '\u00A5',
+    '&cent;': '\u00A2',
+};
+/**
+ * Tags that should add a newline when stripped.
+ */
+const BLOCK_TAGS = new Set([
+    'p',
+    'div',
+    'br',
+    'hr',
+    'h1',
+    'h2',
+    'h3',
+    'h4',
+    'h5',
+    'h6',
+    'li',
+    'tr',
+    'blockquote',
+    'pre',
+    'article',
+    'section',
+    'header',
+    'footer',
+    'nav',
+    'aside',
+    'table',
+    'thead',
+    'tbody',
+    'tfoot',
+]);
+/**
+ * Tags whose content should be completely removed.
+ */
+const INVISIBLE_TAGS = new Set(['script', 'style', 'head', 'meta', 'link', 'noscript']);
+/**
+ * Strips HTML tags and converts to plain text.
+ *
+ * @param html - The HTML string to convert
+ * @param options - Optional configuration
+ * @returns Plain text string
+ */
+export function stripHtml(html, options = {}) {
+    if (html == null || html === '') {
+        return '';
+    }
+    const { preserveWhitespace = false, maxLength = 0 } = options;
+    let text = html;
+    // Remove invisible tag content (script, style, etc.)
+    for (const tag of INVISIBLE_TAGS) {
+        const regex = new RegExp(`<${tag}[^>]*>[\\s\\S]*?</${tag}>`, 'gi');
+        text = text.replace(regex, '');
+    }
+    // Remove HTML comments
+    text = text.replace(/<!--[\s\S]*?-->/g, '');
+    // Remove CDATA sections
+    text = text.replace(/<!\[CDATA\[[\s\S]*?\]\]>/g, '');
+    // Handle list items with bullets (before block element processing)
+    text = text.replace(/<li[^>]*>/gi, '\n\u2022 ');
+    text = text.replace(/<\/li>/gi, '');
+    // Add newlines for block elements (excluding li which is handled above)
+    for (const tag of BLOCK_TAGS) {
+        if (tag === 'li')
+            continue;
+        // Opening tags
+        text = text.replace(new RegExp(`<${tag}[^>]*>`, 'gi'), '\n');
+        // Self-closing tags (like <br />)
+        text = text.replace(new RegExp(`<${tag}[^>]*/>`, 'gi'), '\n');
+        // Closing tags
+        text = text.replace(new RegExp(`</${tag}>`, 'gi'), '\n');
+    }
+    // Remove all remaining HTML tags
+    text = text.replace(/<[^>]+>/g, '');
+    // Decode numeric HTML entities
+    text = text.replace(/&#(\d+);/g, (_, code) => {
+        const num = parseInt(code, 10);
+        return String.fromCharCode(num);
+    });
+    // Decode hex HTML entities
+    text = text.replace(/&#x([a-fA-F0-9]+);/g, (_, code) => {
+        const num = parseInt(code, 16);
+        return String.fromCharCode(num);
+    });
+    // Decode named HTML entities
+    for (const [entity, replacement] of Object.entries(HTML_ENTITIES)) {
+        text = text.split(entity).join(replacement);
+    }
+    if (!preserveWhitespace) {
+        // Normalize whitespace
+        text = text
+            // Replace tabs with spaces
+            .replace(/\t/g, ' ')
+            // Replace multiple spaces with single space
+            .replace(/ +/g, ' ')
+            // Replace multiple newlines with double newline (preserve paragraphs)
+            .replace(/\n\s*\n/g, '\n\n')
+            // Remove leading/trailing whitespace from lines
+            .replace(/^[ \t]+/gm, '')
+            .replace(/[ \t]+$/gm, '')
+            // Trim overall
+            .trim();
+    }
+    // Apply max length if specified
+    if (maxLength > 0 && text.length > maxLength) {
+        text = text.substring(0, maxLength - 3) + '...';
+    }
+    return text;
+}
+/**
+ * Checks if a string appears to contain HTML.
+ *
+ * @param text - The string to check
+ * @returns True if the string appears to contain HTML tags
+ */
+export function containsHtml(text) {
+    if (text == null || text === '') {
+        return false;
+    }
+    // Check for common HTML patterns
+    return /<[a-zA-Z][^>]*>/.test(text);
+}
+/**
+ * Extracts plain text from an email body, detecting HTML automatically.
+ *
+ * @param body - The email body (HTML or plain text)
+ * @param options - Optional configuration
+ * @returns Plain text string
+ */
+export function extractPlainText(body, options = {}) {
+    if (body == null || body === '') {
+        return '';
+    }
+    if (containsHtml(body)) {
+        return stripHtml(body, options);
+    }
+    // Already plain text, just apply max length if needed
+    const { maxLength = 0 } = options;
+    if (maxLength > 0 && body.length > maxLength) {
+        return body.substring(0, maxLength - 3) + '...';
+    }
+    return body;
+}
+//# sourceMappingURL=html-stripper.js.map

package/dist/parsers/html-stripper.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"html-stripper.js","sourceRoot":"","sources":["../../src/parsers/html-stripper.ts"],"names":[],"mappings":"AAAA;;;GAGG;AAEH;;;;;GAKG;AAEH;;GAEG;AACH,MAAM,aAAa,GAA2B;IAC5C,QAAQ,EAAE,GAAG;IACb,OAAO,EAAE,GAAG;IACZ,MAAM,EAAE,GAAG;IACX,MAAM,EAAE,GAAG;IACX,QAAQ,EAAE,GAAG;IACb,QAAQ,EAAE,GAAG;IACb,OAAO,EAAE,GAAG;IACZ,QAAQ,EAAE,QAAQ;IAClB,OAAO,EAAE,QAAQ;IACjB,SAAS,EAAE,QAAQ;IACnB,SAAS,EAAE,QAAQ;IACnB,SAAS,EAAE,QAAQ;IACnB,UAAU,EAAE,QAAQ;IACpB,SAAS,EAAE,QAAQ;IACnB,SAAS,EAAE,QAAQ;IACnB,SAAS,EAAE,QAAQ;IACnB,SAAS,EAAE,QAAQ;IACnB,QAAQ,EAAE,QAAQ;IAClB,UAAU,EAAE,QAAQ;IACpB,QAAQ,EAAE,QAAQ;IAClB,SAAS,EAAE,QAAQ;IACnB,OAAO,EAAE,QAAQ;IACjB,QAAQ,EAAE,QAAQ;CACnB,CAAC;AAEF;;GAEG;AACH,MAAM,UAAU,GAAG,IAAI,GAAG,CAAC;IACzB,GAAG;IACH,KAAK;IACL,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,YAAY;IACZ,KAAK;IACL,SAAS;IACT,SAAS;IACT,QAAQ;IACR,QAAQ;IACR,KAAK;IACL,OAAO;IACP,OAAO;IACP,OAAO;IACP,OAAO;IACP,OAAO;CACR,CAAC,CAAC;AAEH;;GAEG;AACH,MAAM,cAAc,GAAG,IAAI,GAAG,CAAC,CAAC,QAAQ,EAAE,OAAO,EAAE,MAAM,EAAE,MAAM,EAAE,MAAM,EAAE,UAAU,CAAC,CAAC,CAAC;AAiBxF;;;;;;GAMG;AACH,MAAM,UAAU,SAAS,CAAC,IAA+B,EAAE,UAA4B,EAAE;IACvF,IAAI,IAAI,IAAI,IAAI,IAAI,IAAI,KAAK,EAAE,EAAE,CAAC;QAChC,OAAO,EAAE,CAAC;IACZ,CAAC;IAED,MAAM,EAAE,kBAAkB,GAAG,KAAK,EAAE,SAAS,GAAG,CAAC,EAAE,GAAG,OAAO,CAAC;IAE9D,IAAI,IAAI,GAAG,IAAI,CAAC;IAEhB,qDAAqD;IACrD,KAAK,MAAM,GAAG,IAAI,cAAc,EAAE,CAAC;QACjC,MAAM,KAAK,GAAG,IAAI,MAAM,CAAC,IAAI,GAAG,qBAAqB,GAAG,GAAG,EAAE,IAAI,CAAC,CAAC;QACnE,IAAI,GAAG,IAAI,CAAC,OAAO,CAAC,KAAK,EAAE,EAAE,CAAC,CAAC;IACjC,CAAC;IAED,uBAAuB;IACvB,IAAI,GAAG,IAAI,CAAC,OAAO,CAAC,kBAAkB,EAAE,EAAE,CAAC,CAAC;IAE5C,wBAAwB;IACxB,IAAI,GAAG,IAAI,CAAC,OAAO,CAAC,2BAA2B,EAAE,EAAE,CAAC,CAAC;IAErD,mEAAmE;IACnE,IAAI,GAAG,IAAI,CAAC,OAAO,CAAC,aAAa,EAAE,WAAW,CAAC,CAAC;IAChD,IAAI,GAAG,IAAI,CAAC,OAAO,CAAC,UAAU,EAAE,EAAE,CAAC,CAAC;IAEpC,wEAAwE;IACxE,KAAK,MAAM,GAAG,IAAI,UAAU,EAAE,CAAC;QAC7B,IAAI,GAAG,KAAK,IAAI;YAAE,SAAS;QAC3B,eAAe;QACf,IAAI,GAAG,IAAI,CAAC,OAAO,CAAC,IAAI,MAAM,CAAC,IAAI,GAAG,QAAQ,EAAE,IAAI,CAAC,EAAE,IAAI,CAAC,CAAC;QAC7D,kCAAkC;QAClC,IAAI,GAAG,IAAI,CAAC,OAAO,CAAC,IAAI,MAAM,CAAC,IAAI,GAAG,SAAS,EAAE,IAAI,CAAC,EAAE,IAAI,CAAC,CAAC;QAC9D,eAAe;QACf,IAAI,GAAG,IAAI,CAAC,OAAO,CAAC,IAAI,MAAM,CAAC,KAAK,GAAG,GAAG,EAAE,IAAI,CAAC,EAAE,IAAI,CAAC,CAAC;IAC3D,CAAC;IAED,iCAAiC;IACjC,IAAI,GAAG,IAAI,CAAC,OAAO,CAAC,UAAU,EAAE,EAAE,CAAC,CAAC;IAEpC,+BAA+B;IAC/B,IAAI,GAAG,IAAI,CAAC,OAAO,CAAC,WAAW,EAAE,CAAC,CAAC,EAAE,IAAY,EAAE,EAAE;QACnD,MAAM,GAAG,GAAG,QAAQ,CAAC,IAAI,EAAE,EAAE,CAAC,CAAC;QAC/B,OAAO,MAAM,CAAC,YAAY,CAAC,GAAG,CAAC,CAAC;IAClC,CAAC,CAAC,CAAC;IAEH,2BAA2B;IAC3B,IAAI,GAAG,IAAI,CAAC,OAAO,CAAC,qBAAqB,EAAE,CAAC,CAAC,EAAE,IAAY,EAAE,EAAE;QAC7D,MAAM,GAAG,GAAG,QAAQ,CAAC,IAAI,EAAE,EAAE,CAAC,CAAC;QAC/B,OAAO,MAAM,CAAC,YAAY,CAAC,GAAG,CAAC,CAAC;IAClC,CAAC,CAAC,CAAC;IAEH,6BAA6B;IAC7B,KAAK,MAAM,CAAC,MAAM,EAAE,WAAW,CAAC,IAAI,MAAM,CAAC,OAAO,CAAC,aAAa,CAAC,EAAE,CAAC;QAClE,IAAI,GAAG,IAAI,CAAC,KAAK,CAAC,MAAM,CAAC,CAAC,IAAI,CAAC,WAAW,CAAC,CAAC;IAC9C,CAAC;IAED,IAAI,CAAC,kBAAkB,EAAE,CAAC;QACxB,uBAAuB;QACvB,IAAI,GAAG,IAAI;YACT,2BAA2B;aAC1B,OAAO,CAAC,KAAK,EAAE,GAAG,CAAC;YACpB,4CAA4C;aAC3C,OAAO,CAAC,KAAK,EAAE,GAAG,CAAC;YACpB,sEAAsE;aACrE,OAAO,CAAC,UAAU,EAAE,MAAM,CAAC;YAC5B,gDAAgD;aAC/C,OAAO,CAAC,WAAW,EAAE,EAAE,CAAC;aACxB,OAAO,CAAC,WAAW,EAAE,EAAE,CAAC;YACzB,eAAe;aACd,IAAI,EAAE,CAAC;IACZ,CAAC;IAED,gCAAgC;IAChC,IAAI,SAAS,GAAG,CAAC,IAAI,IAAI,CAAC,MAAM,GAAG,SAAS,EAAE,CAAC;QAC7C,IAAI,GAAG,IAAI,CAAC,SAAS,CAAC,CAAC,EAAE,SAAS,GAAG,CAAC,CAAC,GAAG,KAAK,CAAC;IAClD,CAAC;IAED,OAAO,IAAI,CAAC;AACd,CAAC;AAED;;;;;GAKG;AACH,MAAM,UAAU,YAAY,CAAC,IAA+B;IAC1D,IAAI,IAAI,IAAI,IAAI,IAAI,IAAI,KAAK,EAAE,EAAE,CAAC;QAChC,OAAO,KAAK,CAAC;IACf,CAAC;IACD,iCAAiC;IACjC,OAAO,iBAAiB,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;AACtC,CAAC;AAED;;;;;;GAMG;AACH,MAAM,UAAU,gBAAgB,CAC9B,IAA+B,EAC/B,UAA4B,EAAE;IAE9B,IAAI,IAAI,IAAI,IAAI,IAAI,IAAI,KAAK,EAAE,EAAE,CAAC;QAChC,OAAO,EAAE,CAAC;IACZ,CAAC;IAED,IAAI,YAAY,CAAC,IAAI,CAAC,EAAE,CAAC;QACvB,OAAO,SAAS,CAAC,IAAI,EAAE,OAAO,CAAC,CAAC;IAClC,CAAC;IAED,sDAAsD;IACtD,MAAM,EAAE,SAAS,GAAG,CAAC,EAAE,GAAG,OAAO,CAAC;IAClC,IAAI,SAAS,GAAG,CAAC,IAAI,IAAI,CAAC,MAAM,GAAG,SAAS,EAAE,CAAC;QAC7C,OAAO,IAAI,CAAC,SAAS,CAAC,CAAC,EAAE,SAAS,GAAG,CAAC,CAAC,GAAG,KAAK,CAAC;IAClD,CAAC;IAED,OAAO,IAAI,CAAC;AACd,CAAC"}

package/dist/parsers/index.d.ts

@@ -0,0 +1,12 @@
+/**
+ * Copyright (c) 2026 JBC Tech Solutions, LLC
+ * Licensed under the MIT License. See LICENSE file in the project root.
+ */
+/**
+ * Parsers for Outlook content.
+ *
+ * Re-exports all parsers for convenient importing.
+ */
+export { stripHtml, containsHtml, extractPlainText, type StripHtmlOptions, } from './html-stripper.js';
+export { parseOlk15File, getDefaultDataPath, Olk15EmailContentReader, Olk15EventContentReader, Olk15ContactContentReader, Olk15TaskContentReader, Olk15NoteContentReader, createContentReaders, createDefaultContentReaders, type Olk15ParseResult, type ContentReaders, } from './olk15.js';
+//# sourceMappingURL=index.d.ts.map

package/dist/parsers/index.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../../src/parsers/index.ts"],"names":[],"mappings":"AAAA;;;GAGG;AAEH;;;;GAIG;AAEH,OAAO,EACL,SAAS,EACT,YAAY,EACZ,gBAAgB,EAChB,KAAK,gBAAgB,GACtB,MAAM,oBAAoB,CAAC;AAE5B,OAAO,EACL,cAAc,EACd,kBAAkB,EAClB,uBAAuB,EACvB,uBAAuB,EACvB,yBAAyB,EACzB,sBAAsB,EACtB,sBAAsB,EACtB,oBAAoB,EACpB,2BAA2B,EAC3B,KAAK,gBAAgB,EACrB,KAAK,cAAc,GACpB,MAAM,YAAY,CAAC"}

package/dist/parsers/index.js

@@ -0,0 +1,12 @@
+/**
+ * Copyright (c) 2026 JBC Tech Solutions, LLC
+ * Licensed under the MIT License. See LICENSE file in the project root.
+ */
+/**
+ * Parsers for Outlook content.
+ *
+ * Re-exports all parsers for convenient importing.
+ */
+export { stripHtml, containsHtml, extractPlainText, } from './html-stripper.js';
+export { parseOlk15File, getDefaultDataPath, Olk15EmailContentReader, Olk15EventContentReader, Olk15ContactContentReader, Olk15TaskContentReader, Olk15NoteContentReader, createContentReaders, createDefaultContentReaders, } from './olk15.js';
+//# sourceMappingURL=index.js.map

package/dist/parsers/index.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"index.js","sourceRoot":"","sources":["../../src/parsers/index.ts"],"names":[],"mappings":"AAAA;;;GAGG;AAEH;;;;GAIG;AAEH,OAAO,EACL,SAAS,EACT,YAAY,EACZ,gBAAgB,GAEjB,MAAM,oBAAoB,CAAC;AAE5B,OAAO,EACL,cAAc,EACd,kBAAkB,EAClB,uBAAuB,EACvB,uBAAuB,EACvB,yBAAyB,EACzB,sBAAsB,EACtB,sBAAsB,EACtB,oBAAoB,EACpB,2BAA2B,GAG5B,MAAM,YAAY,CAAC"}

package/dist/parsers/olk15.d.ts

@@ -0,0 +1,87 @@
+/**
+ * Copyright (c) 2026 JBC Tech Solutions, LLC
+ * Licensed under the MIT License. See LICENSE file in the project root.
+ */
+import type { IContentReader } from '../tools/mail.js';
+import type { IEventContentReader, EventDetails } from '../tools/calendar.js';
+import type { IContactContentReader, ContactDetails } from '../tools/contacts.js';
+import type { ITaskContentReader, TaskDetails } from '../tools/tasks.js';
+import type { INoteContentReader, NoteDetails } from '../tools/notes.js';
+/**
+ * Default profile data directory path.
+ */
+export declare function getDefaultDataPath(profileName?: string): string;
+/**
+ * Result of parsing an OLK15 file.
+ */
+export interface Olk15ParseResult {
+    readonly success: boolean;
+    readonly text: string | null;
+    readonly html: string | null;
+    readonly error?: string;
+}
+/**
+ * Parses an OLK15 file and extracts text content.
+ */
+export declare function parseOlk15File(filePath: string): Olk15ParseResult;
+/**
+ * OLK15 content reader for email bodies.
+ */
+export declare class Olk15EmailContentReader implements IContentReader {
+    private readonly dataPath;
+    constructor(dataPath: string);
+    readEmailBody(dataFilePath: string | null): string | null;
+}
+/**
+ * OLK15 content reader for calendar events.
+ */
+export declare class Olk15EventContentReader implements IEventContentReader {
+    private readonly dataPath;
+    constructor(dataPath: string);
+    readEventDetails(dataFilePath: string | null): EventDetails | null;
+    private extractTitle;
+    private extractField;
+}
+/**
+ * OLK15 content reader for contacts.
+ */
+export declare class Olk15ContactContentReader implements IContactContentReader {
+    private readonly dataPath;
+    constructor(dataPath: string);
+    readContactDetails(dataFilePath: string | null): ContactDetails | null;
+}
+/**
+ * OLK15 content reader for tasks.
+ */
+export declare class Olk15TaskContentReader implements ITaskContentReader {
+    private readonly dataPath;
+    constructor(dataPath: string);
+    readTaskDetails(dataFilePath: string | null): TaskDetails | null;
+}
+/**
+ * OLK15 content reader for notes.
+ */
+export declare class Olk15NoteContentReader implements INoteContentReader {
+    private readonly dataPath;
+    constructor(dataPath: string);
+    readNoteDetails(dataFilePath: string | null): NoteDetails | null;
+}
+/**
+ * Creates all content readers for a given data path.
+ */
+export interface ContentReaders {
+    readonly email: IContentReader;
+    readonly event: IEventContentReader;
+    readonly contact: IContactContentReader;
+    readonly task: ITaskContentReader;
+    readonly note: INoteContentReader;
+}
+/**
+ * Creates content readers for all Outlook data types.
+ */
+export declare function createContentReaders(dataPath: string): ContentReaders;
+/**
+ * Creates content readers using the default profile path.
+ */
+export declare function createDefaultContentReaders(profileName?: string): ContentReaders;
+//# sourceMappingURL=olk15.d.ts.map

package/dist/parsers/olk15.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"olk15.d.ts","sourceRoot":"","sources":["../../src/parsers/olk15.ts"],"names":[],"mappings":"AAAA;;;GAGG;AAqBH,OAAO,KAAK,EAAE,cAAc,EAAE,MAAM,kBAAkB,CAAC;AACvD,OAAO,KAAK,EAAE,mBAAmB,EAAE,YAAY,EAAE,MAAM,sBAAsB,CAAC;AAC9E,OAAO,KAAK,EAAE,qBAAqB,EAAE,cAAc,EAAE,MAAM,sBAAsB,CAAC;AAClF,OAAO,KAAK,EAAE,kBAAkB,EAAE,WAAW,EAAE,MAAM,mBAAmB,CAAC;AACzE,OAAO,KAAK,EAAE,kBAAkB,EAAE,WAAW,EAAE,MAAM,mBAAmB,CAAC;AAMzE;;GAEG;AACH,wBAAgB,kBAAkB,CAAC,WAAW,GAAE,MAAuB,GAAG,MAAM,CAQ/E;AAqJD;;GAEG;AACH,MAAM,WAAW,gBAAgB;IAC/B,QAAQ,CAAC,OAAO,EAAE,OAAO,CAAC;IAC1B,QAAQ,CAAC,IAAI,EAAE,MAAM,GAAG,IAAI,CAAC;IAC7B,QAAQ,CAAC,IAAI,EAAE,MAAM,GAAG,IAAI,CAAC;IAC7B,QAAQ,CAAC,KAAK,CAAC,EAAE,MAAM,CAAC;CACzB;AAED;;GAEG;AACH,wBAAgB,cAAc,CAAC,QAAQ,EAAE,MAAM,GAAG,gBAAgB,CAiCjE;AAMD;;GAEG;AACH,qBAAa,uBAAwB,YAAW,cAAc;IAChD,OAAO,CAAC,QAAQ,CAAC,QAAQ;gBAAR,QAAQ,EAAE,MAAM;IAE7C,aAAa,CAAC,YAAY,EAAE,MAAM,GAAG,IAAI,GAAG,MAAM,GAAG,IAAI;CAc1D;AAED;;GAEG;AACH,qBAAa,uBAAwB,YAAW,mBAAmB;IACrD,OAAO,CAAC,QAAQ,CAAC,QAAQ;gBAAR,QAAQ,EAAE,MAAM;IAE7C,gBAAgB,CAAC,YAAY,EAAE,MAAM,GAAG,IAAI,GAAG,YAAY,GAAG,IAAI;IAwBlE,OAAO,CAAC,YAAY;IAYpB,OAAO,CAAC,YAAY;CAKrB;AAED;;GAEG;AACH,qBAAa,yBAA0B,YAAW,qBAAqB;IACzD,OAAO,CAAC,QAAQ,CAAC,QAAQ;gBAAR,QAAQ,EAAE,MAAM;IAE7C,kBAAkB,CAAC,YAAY,EAAE,MAAM,GAAG,IAAI,GAAG,cAAc,GAAG,IAAI;CA4BvE;AAED;;GAEG;AACH,qBAAa,sBAAuB,YAAW,kBAAkB;IACnD,OAAO,CAAC,QAAQ,CAAC,QAAQ;gBAAR,QAAQ,EAAE,MAAM;IAE7C,eAAe,CAAC,YAAY,EAAE,MAAM,GAAG,IAAI,GAAG,WAAW,GAAG,IAAI;CAmBjE;AAED;;GAEG;AACH,qBAAa,sBAAuB,YAAW,kBAAkB;IACnD,OAAO,CAAC,QAAQ,CAAC,QAAQ;gBAAR,QAAQ,EAAE,MAAM;IAE7C,eAAe,CAAC,YAAY,EAAE,MAAM,GAAG,IAAI,GAAG,WAAW,GAAG,IAAI;CAuBjE;AAMD;;GAEG;AACH,MAAM,WAAW,cAAc;IAC7B,QAAQ,CAAC,KAAK,EAAE,cAAc,CAAC;IAC/B,QAAQ,CAAC,KAAK,EAAE,mBAAmB,CAAC;IACpC,QAAQ,CAAC,OAAO,EAAE,qBAAqB,CAAC;IACxC,QAAQ,CAAC,IAAI,EAAE,kBAAkB,CAAC;IAClC,QAAQ,CAAC,IAAI,EAAE,kBAAkB,CAAC;CACnC;AAED;;GAEG;AACH,wBAAgB,oBAAoB,CAAC,QAAQ,EAAE,MAAM,GAAG,cAAc,CAQrE;AAED;;GAEG;AACH,wBAAgB,2BAA2B,CAAC,WAAW,CAAC,EAAE,MAAM,GAAG,cAAc,CAGhF"}

package/dist/parsers/olk15.js

@@ -0,0 +1,368 @@
+/**
+ * Copyright (c) 2026 JBC Tech Solutions, LLC
+ * Licensed under the MIT License. See LICENSE file in the project root.
+ */
+/**
+ * OLK15 binary file parser.
+ *
+ * Parses Outlook for Mac's proprietary binary content files.
+ * These files contain email bodies, event details, contact information, etc.
+ *
+ * File types:
+ * - .olk15MsgSource / .olk15Message - Email content
+ * - .olk15Event - Calendar event details
+ * - .olk15Contact - Contact information
+ * - .olk15Note - Note content
+ * - .olk15Task - Task details
+ *
+ * The format is proprietary and not documented. This parser uses heuristics
+ * to extract text content and provides graceful fallbacks when parsing fails.
+ */
+import { readFileSync, existsSync } from 'node:fs';
+import { join } from 'node:path';
+// =============================================================================
+// Configuration
+// =============================================================================
+/**
+ * Default profile data directory path.
+ */
+export function getDefaultDataPath(profileName = 'Main Profile') {
+    const home = process.env.HOME ?? '';
+    return join(home, 'Library/Group Containers/UBF8T346G9.Office/Outlook/Outlook 15 Profiles', profileName, 'Data');
+}
+// =============================================================================
+// Binary Parsing Utilities
+// =============================================================================
+/**
+ * Finds UTF-16LE encoded text in binary data.
+ * OLK15 files often store text as UTF-16LE.
+ */
+function findUtf16Text(buffer, minLength = 10) {
+    const results = [];
+    let start = -1;
+    let chars = [];
+    for (let i = 0; i < buffer.length - 1; i += 2) {
+        const char = buffer.readUInt16LE(i);
+        // Check if it's a printable character or common whitespace
+        if ((char >= 0x20 && char < 0x7f) || char === 0x0a || char === 0x0d || char === 0x09) {
+            if (start === -1)
+                start = i;
+            chars.push(String.fromCharCode(char));
+        }
+        else if (char === 0) {
+            // Null character - end of string
+            if (chars.length >= minLength) {
+                results.push(chars.join(''));
+            }
+            chars = [];
+            start = -1;
+        }
+        else {
+            // Non-printable, non-null - might be end of text section
+            if (chars.length >= minLength) {
+                results.push(chars.join(''));
+            }
+            chars = [];
+            start = -1;
+        }
+    }
+    // Don't forget the last string
+    if (chars.length >= minLength) {
+        results.push(chars.join(''));
+    }
+    return results;
+}
+/**
+ * Finds UTF-8 encoded text in binary data.
+ */
+function findUtf8Text(buffer, minLength = 10) {
+    const results = [];
+    let start = -1;
+    let chars = [];
+    for (let i = 0; i < buffer.length; i++) {
+        const byte = buffer[i];
+        if (byte !== undefined) {
+            // Check if it's a printable ASCII or common whitespace
+            if ((byte >= 0x20 && byte < 0x7f) || byte === 0x0a || byte === 0x0d || byte === 0x09) {
+                if (start === -1)
+                    start = i;
+                chars.push(byte);
+            }
+            else if (byte === 0) {
+                // Null terminator
+                if (chars.length >= minLength) {
+                    results.push(Buffer.from(chars).toString('utf8'));
+                }
+                chars = [];
+                start = -1;
+            }
+            else if (byte >= 0x80) {
+                // UTF-8 multi-byte - try to include
+                chars.push(byte);
+            }
+            else {
+                // Control character - end of text
+                if (chars.length >= minLength) {
+                    results.push(Buffer.from(chars).toString('utf8'));
+                }
+                chars = [];
+                start = -1;
+            }
+        }
+    }
+    if (chars.length >= minLength) {
+        results.push(Buffer.from(chars).toString('utf8'));
+    }
+    return results;
+}
+/**
+ * Extracts the longest text block that looks like content.
+ */
+function extractPrimaryText(buffer) {
+    // Try UTF-16LE first (common in OLK15)
+    const utf16Texts = findUtf16Text(buffer, 20);
+    // Try UTF-8 as fallback
+    const utf8Texts = findUtf8Text(buffer, 20);
+    // Combine and find the longest meaningful text
+    const allTexts = [...utf16Texts, ...utf8Texts]
+        .filter((t) => t.trim().length > 0)
+        // eslint-disable-next-line no-control-regex
+        .filter((t) => !t.match(/^[\x00-\x1f\x7f-\x9f]+$/)) // Filter control chars
+        .sort((a, b) => b.length - a.length);
+    return allTexts[0] ?? null;
+}
+/**
+ * Checks if text looks like HTML content.
+ */
+function looksLikeHtml(text) {
+    return /<\/?[a-z][\s\S]*>/i.test(text);
+}
+/**
+ * Finds HTML content in buffer.
+ */
+function findHtmlContent(buffer) {
+    const text = buffer.toString('utf8', 0, Math.min(buffer.length, 1024 * 1024));
+    // Look for HTML patterns
+    const htmlStart = text.search(/<html[^>]*>/i);
+    if (htmlStart >= 0) {
+        const htmlEnd = text.indexOf('</html>', htmlStart);
+        if (htmlEnd > htmlStart) {
+            return text.substring(htmlStart, htmlEnd + 7);
+        }
+    }
+    // Look for body content
+    const bodyStart = text.search(/<body[^>]*>/i);
+    if (bodyStart >= 0) {
+        const bodyEnd = text.indexOf('</body>', bodyStart);
+        if (bodyEnd > bodyStart) {
+            return text.substring(bodyStart, bodyEnd + 7);
+        }
+    }
+    return null;
+}
+/**
+ * Parses an OLK15 file and extracts text content.
+ */
+export function parseOlk15File(filePath) {
+    try {
+        if (!existsSync(filePath)) {
+            return { success: false, text: null, html: null, error: 'File not found' };
+        }
+        const buffer = readFileSync(filePath);
+        if (buffer.length === 0) {
+            return { success: false, text: null, html: null, error: 'Empty file' };
+        }
+        // Try to find HTML content first
+        const html = findHtmlContent(buffer);
+        if (html != null) {
+            return { success: true, text: null, html };
+        }
+        // Extract text content
+        const text = extractPrimaryText(buffer);
+        if (text != null) {
+            // Check if the text is actually HTML
+            if (looksLikeHtml(text)) {
+                return { success: true, text: null, html: text };
+            }
+            return { success: true, text, html: null };
+        }
+        return { success: false, text: null, html: null, error: 'No text content found' };
+    }
+    catch (error) {
+        const message = error instanceof Error ? error.message : 'Unknown error';
+        return { success: false, text: null, html: null, error: message };
+    }
+}
+// =============================================================================
+// Content Reader Implementations
+// =============================================================================
+/**
+ * OLK15 content reader for email bodies.
+ */
+export class Olk15EmailContentReader {
+    dataPath;
+    constructor(dataPath) {
+        this.dataPath = dataPath;
+    }
+    readEmailBody(dataFilePath) {
+        if (dataFilePath == null) {
+            return null;
+        }
+        const fullPath = join(this.dataPath, dataFilePath);
+        const result = parseOlk15File(fullPath);
+        if (result.success) {
+            return result.html ?? result.text;
+        }
+        return null;
+    }
+}
+/**
+ * OLK15 content reader for calendar events.
+ */
+export class Olk15EventContentReader {
+    dataPath;
+    constructor(dataPath) {
+        this.dataPath = dataPath;
+    }
+    readEventDetails(dataFilePath) {
+        if (dataFilePath == null) {
+            return null;
+        }
+        const fullPath = join(this.dataPath, dataFilePath);
+        const result = parseOlk15File(fullPath);
+        if (!result.success) {
+            return null;
+        }
+        const text = result.text ?? result.html ?? '';
+        // Basic extraction - can be improved with format knowledge
+        return {
+            title: this.extractTitle(text),
+            location: this.extractField(text, 'Location'),
+            description: text,
+            organizer: this.extractField(text, 'Organizer'),
+            attendees: [],
+        };
+    }
+    extractTitle(text) {
+        // Try to find a subject/title line
+        const subjectMatch = text.match(/Subject:\s*(.+?)(?:\r?\n|$)/i);
+        if (subjectMatch?.[1] != null && subjectMatch[1].length > 0) {
+            return subjectMatch[1].trim();
+        }
+        // Use first line as title
+        const firstLine = text.split(/\r?\n/)[0]?.trim();
+        return firstLine != null && firstLine.length > 0 ? firstLine : null;
+    }
+    extractField(text, fieldName) {
+        const regex = new RegExp(`${fieldName}:\\s*(.+?)(?:\\r?\\n|$)`, 'i');
+        const match = text.match(regex);
+        return match?.[1]?.trim() ?? null;
+    }
+}
+/**
+ * OLK15 content reader for contacts.
+ */
+export class Olk15ContactContentReader {
+    dataPath;
+    constructor(dataPath) {
+        this.dataPath = dataPath;
+    }
+    readContactDetails(dataFilePath) {
+        if (dataFilePath == null) {
+            return null;
+        }
+        const fullPath = join(this.dataPath, dataFilePath);
+        const result = parseOlk15File(fullPath);
+        if (!result.success) {
+            return null;
+        }
+        // Contact parsing would require understanding the binary format
+        // For now, return a basic structure
+        return {
+            firstName: null,
+            lastName: null,
+            middleName: null,
+            nickname: null,
+            company: null,
+            jobTitle: null,
+            department: null,
+            emails: [],
+            phones: [],
+            addresses: [],
+            notes: result.text,
+        };
+    }
+}
+/**
+ * OLK15 content reader for tasks.
+ */
+export class Olk15TaskContentReader {
+    dataPath;
+    constructor(dataPath) {
+        this.dataPath = dataPath;
+    }
+    readTaskDetails(dataFilePath) {
+        if (dataFilePath == null) {
+            return null;
+        }
+        const fullPath = join(this.dataPath, dataFilePath);
+        const result = parseOlk15File(fullPath);
+        if (!result.success) {
+            return null;
+        }
+        return {
+            body: result.text ?? result.html,
+            completedDate: null,
+            reminderDate: null,
+            categories: [],
+        };
+    }
+}
+/**
+ * OLK15 content reader for notes.
+ */
+export class Olk15NoteContentReader {
+    dataPath;
+    constructor(dataPath) {
+        this.dataPath = dataPath;
+    }
+    readNoteDetails(dataFilePath) {
+        if (dataFilePath == null) {
+            return null;
+        }
+        const fullPath = join(this.dataPath, dataFilePath);
+        const result = parseOlk15File(fullPath);
+        if (!result.success) {
+            return null;
+        }
+        const body = result.text ?? result.html ?? '';
+        const lines = body.split(/\r?\n/).filter((l) => l.trim().length > 0);
+        return {
+            title: lines[0] ?? null,
+            body,
+            preview: body.substring(0, 200),
+            createdDate: null,
+            categories: [],
+        };
+    }
+}
+/**
+ * Creates content readers for all Outlook data types.
+ */
+export function createContentReaders(dataPath) {
+    return {
+        email: new Olk15EmailContentReader(dataPath),
+        event: new Olk15EventContentReader(dataPath),
+        contact: new Olk15ContactContentReader(dataPath),
+        task: new Olk15TaskContentReader(dataPath),
+        note: new Olk15NoteContentReader(dataPath),
+    };
+}
+/**
+ * Creates content readers using the default profile path.
+ */
+export function createDefaultContentReaders(profileName) {
+    const dataPath = getDefaultDataPath(profileName);
+    return createContentReaders(dataPath);
+}
+//# sourceMappingURL=olk15.js.map