Docx Generator

#!/usr/bin/env -S deno run --allow-read

/**
 * analyze-template.ts - Extract text content and structure from DOCX files
 *
 * Extracts paragraphs, tables, headers, footers, and placeholders from Word documents
 * for template analysis and content replacement planning.
 *
 * Usage:
 *   deno run --allow-read scripts/analyze-template.ts <input.docx> [options]
 *
 * Options:
 *   -h, --help       Show help
 *   -v, --verbose    Enable verbose output
 *   --pretty         Pretty-print JSON output
 *
 * Permissions:
 *   --allow-read: Read DOCX file
 */

import { parseArgs } from "jsr:@std/cli@1.0.9/parse-args";
import { basename } from "jsr:@std/path@1.0.8";
import JSZip from "npm:jszip@3.10.1";
import { DOMParser } from "npm:@xmldom/xmldom@0.9.6";

// === Types ===
export interface TextRun {
  text: string;
  bold?: boolean;
  italic?: boolean;
  underline?: boolean;
  fontSize?: number;
  fontFamily?: string;
  color?: string;
}

export interface ParagraphInfo {
  index: number;
  style?: string;
  alignment?: "left" | "center" | "right" | "justify";
  runs: TextRun[];
  fullText: string;
  isListItem: boolean;
  listLevel?: number;
}

export interface TableCellInfo {
  row: number;
  col: number;
  text: string;
  paragraphs: ParagraphInfo[];
}

export interface TableInfo {
  index: number;
  rows: number;
  cols: number;
  cells: TableCellInfo[];
}

export interface HeaderFooterInfo {
  type: "header" | "footer";
  section: "default" | "first" | "even";
  paragraphs: ParagraphInfo[];
}

export interface PlaceholderInfo {
  tag: string;
  location: string;
  paragraphIndex?: number;
  tableIndex?: number;
  cellLocation?: string;
}

export interface DocumentInventory {
  filename: string;
  paragraphCount: number;
  tableCount: number;
  imageCount: number;
  paragraphs: ParagraphInfo[];
  tables: TableInfo[];
  headersFooters: HeaderFooterInfo[];
  placeholders: PlaceholderInfo[];
  styles: string[];
}

interface ParsedArgs {
  help: boolean;
  verbose: boolean;
  pretty: boolean;
  _: (string | number)[];
}

// === Constants ===
const VERSION = "1.0.0";
const SCRIPT_NAME = "analyze-template";

const NS = {
  w: "http://schemas.openxmlformats.org/wordprocessingml/2006/main",
  r: "http://schemas.openxmlformats.org/officeDocument/2006/relationships",
};

// Placeholder pattern: {{PLACEHOLDER}} or ${placeholder}
const PLACEHOLDER_REGEX = /\{\{([^}]+)\}\}|\$\{([^}]+)\}/g;

// === Help Text ===
function printHelp(): void {
  console.log(`
${SCRIPT_NAME} v${VERSION} - Extract text content from DOCX templates

Usage:
  deno run --allow-read scripts/${SCRIPT_NAME}.ts <input.docx> [options]

Arguments:
  <input.docx>     Path to the Word document to analyze

Options:
  -h, --help       Show this help message
  -v, --verbose    Enable verbose output (to stderr)
  --pretty         Pretty-print JSON output (default: compact)

Examples:
  # Analyze document
  deno run --allow-read scripts/${SCRIPT_NAME}.ts template.docx > inventory.json

  # With verbose output
  deno run --allow-read scripts/${SCRIPT_NAME}.ts template.docx -v --pretty
`);
}

// === Utility Functions ===
// deno-lint-ignore no-explicit-any
function getElementsByTagNameNS(parent: any, ns: string, localName: string): any[] {
  const elements = parent.getElementsByTagNameNS(ns, localName);
  // deno-lint-ignore no-explicit-any
  return Array.from(elements) as any[];
}

// deno-lint-ignore no-explicit-any
function getTextContent(element: any): string {
  const textElements = getElementsByTagNameNS(element, NS.w, "t");
  return textElements.map((t) => t.textContent || "").join("");
}

// === Parsing Functions ===
// deno-lint-ignore no-explicit-any
function parseTextRun(rElement: any): TextRun {
  const run: TextRun = {
    text: getTextContent(rElement),
  };

  const rPr = getElementsByTagNameNS(rElement, NS.w, "rPr")[0];
  if (rPr) {
    // Bold
    if (getElementsByTagNameNS(rPr, NS.w, "b").length > 0) {
      run.bold = true;
    }
    // Italic
    if (getElementsByTagN