typlite/writer/docx/writer.rs
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644
//! DOCX document writer implementation
use base64::Engine;
use cmark_writer::ast::{ListItem, Node};
use docx_rs::*;
use ecow::EcoString;
use std::fs;
use std::io::Cursor;
use crate::common::{FigureNode, FormatWriter};
use crate::Result;
use super::image_processor::DocxImageProcessor;
use super::numbering::DocxNumbering;
use super::styles::DocxStyles;
/// DOCX writer that generates DOCX directly from AST (without intermediate representation)
pub struct DocxWriter {
styles: DocxStyles,
numbering: DocxNumbering,
list_level: usize,
list_numbering_count: usize,
image_processor: DocxImageProcessor,
}
impl Default for DocxWriter {
fn default() -> Self {
Self::new()
}
}
impl DocxWriter {
pub fn new() -> Self {
Self {
styles: DocxStyles::new(),
numbering: DocxNumbering::new(),
list_level: 0,
list_numbering_count: 0,
image_processor: DocxImageProcessor::new(),
}
}
/// Process image node
fn process_image(&self, docx: Docx, url: &str, alt_nodes: &[Node]) -> Result<Docx> {
// Build alt text
let alt_text = if !alt_nodes.is_empty() {
let mut text = String::new();
for node in alt_nodes {
if let Node::Text(content) = node {
text.push_str(content);
}
}
Some(text)
} else {
None
};
// Try reading image file
if let Ok(img_data) = fs::read(url) {
Ok(self
.image_processor
.process_image_data(docx, &img_data, alt_text.as_deref(), None))
} else {
let placeholder = format!("[Image not found: {}]", url);
let para = Paragraph::new().add_run(Run::new().add_text(placeholder));
Ok(docx.add_paragraph(para))
}
}
/// Process figure node (image with caption)
fn process_figure(&mut self, mut docx: Docx, figure_node: &FigureNode) -> Result<Docx> {
// First handle the figure body (typically an image)
match &*figure_node.body {
Node::Paragraph(content) => {
for node in content {
if let Node::Image {
url,
title: _,
alt: _,
} = node
{
// Process the image
if let Ok(img_data) = fs::read(url) {
let alt_text = figure_node.caption.clone();
// Add the image with caption
docx = self.image_processor.process_image_data(
docx,
&img_data,
Some(&alt_text),
None,
);
// Add caption as a separate paragraph with Caption style
if !figure_node.caption.is_empty() {
let caption_text = format!("Figure: {}", figure_node.caption);
let caption_para = Paragraph::new()
.style("Caption")
.add_run(Run::new().add_text(caption_text));
docx = docx.add_paragraph(caption_para);
}
} else {
// Image not found, show placeholder
let placeholder = format!("[Image not found: {}]", url);
let para = Paragraph::new().add_run(Run::new().add_text(placeholder));
docx = docx.add_paragraph(para);
// Still add caption
if !figure_node.caption.is_empty() {
let caption_para = Paragraph::new()
.style("Caption")
.add_run(Run::new().add_text(&figure_node.caption));
docx = docx.add_paragraph(caption_para);
}
}
} else {
// Handle non-image content
let mut para = Paragraph::new();
let run = Run::new();
let run = self.process_inline_to_run(run, node)?;
if !run.children.is_empty() {
para = para.add_run(run);
docx = docx.add_paragraph(para);
}
// Add caption as a separate paragraph
if !figure_node.caption.is_empty() {
let caption_para = Paragraph::new()
.style("Caption")
.add_run(Run::new().add_text(&figure_node.caption));
docx = docx.add_paragraph(caption_para);
}
}
}
}
// Handle other content types within figure
_ => {
// Process the content using standard node processing
docx = self.process_node(docx, &figure_node.body)?;
// Add caption as a separate paragraph
if !figure_node.caption.is_empty() {
let caption_para = Paragraph::new()
.style("Caption")
.add_run(Run::new().add_text(&figure_node.caption));
docx = docx.add_paragraph(caption_para);
}
}
}
Ok(docx)
}
/// Process inline element and add to Run
fn process_inline_to_run(&self, mut run: Run, node: &Node) -> Result<Run> {
match node {
Node::Text(text) => {
run = run.add_text(text);
}
Node::Strong(content) => {
run = run.style("Strong");
for child in content {
run = self.process_inline_to_run(run, child)?;
}
}
Node::Emphasis(content) => {
run = run.style("Emphasis");
for child in content {
run = self.process_inline_to_run(run, child)?;
}
}
Node::Strikethrough(content) => {
run = run.strike();
for child in content {
run = self.process_inline_to_run(run, child)?;
}
}
Node::Link {
url: _,
title: _,
content,
} => {
// Hyperlinks need to be processed at paragraph level, only handle content here
run = run.style("Hyperlink");
for child in content {
run = self.process_inline_to_run(run, child)?;
}
}
Node::Image {
url,
title: _,
alt: _,
} => {
if let Ok(img_data) = fs::read(url) {
run = self.image_processor.process_inline_image(run, &img_data)?;
} else {
run = run.add_text(format!("[Image not found: {}]", url));
}
}
Node::HtmlElement(element) => {
// Handle special HTML elements
if element.tag == "mark" {
run = run.style("Highlight");
for child in &element.children {
run = self.process_inline_to_run(run, child)?;
}
} else if element.tag == "img" && element.self_closing {
let is_typst_block = element
.attributes
.iter()
.any(|a| a.name == "alt" && a.value == "typst-block");
let src = element
.attributes
.iter()
.find(|a| a.name == "src")
.map(|a| a.value.as_str())
.unwrap_or("");
if src.starts_with("data:image/") {
run = self.image_processor.process_data_url_image(
run,
src,
is_typst_block,
)?;
}
} else {
// Standard element content processing
for child in &element.children {
run = self.process_inline_to_run(run, child)?;
}
}
}
Node::InlineCode(code) => {
run = run.style("CodeInline").add_text(code);
}
Node::HardBreak => {
run = run.add_break(BreakType::TextWrapping);
}
Node::SoftBreak => {
run = run.add_text(" ");
}
// Other inline element types
_ => {}
}
Ok(run)
}
/// Process paragraph and add to document
fn process_paragraph(
&self,
mut docx: Docx,
content: &[Node],
style: Option<&str>,
) -> Result<Docx> {
let mut para = Paragraph::new();
// Apply style
if let Some(style_name) = style {
para = para.style(style_name);
}
// Extract all link nodes
let mut links = Vec::new();
for (i, node) in content.iter().enumerate() {
if let Node::Link {
url,
title: _,
content: _,
} = node
{
links.push((i, url.clone()));
}
}
// If no links, process paragraph normally
if links.is_empty() {
// Process paragraph content
for node in content {
let run = Run::new();
let run = self.process_inline_to_run(run, node)?;
if !run.children.is_empty() {
para = para.add_run(run);
}
}
} else {
// If links exist, we need to process in segments
let mut last_idx = 0;
for (idx, url) in links {
// Process content before the link
for item in content.iter().take(idx).skip(last_idx) {
let run = Run::new();
let run = self.process_inline_to_run(run, item)?;
if !run.children.is_empty() {
para = para.add_run(run);
}
}
// Process link
if let Node::Link {
url: _,
title: _,
content: link_content,
} = &content[idx]
{
let mut hyperlink_run = Run::new().style("Hyperlink");
for child in link_content {
hyperlink_run = self.process_inline_to_run(hyperlink_run, child)?;
}
// Create and add hyperlink
if !hyperlink_run.children.is_empty() {
let hyperlink =
Hyperlink::new(&url, HyperlinkType::External).add_run(hyperlink_run);
para = para.add_hyperlink(hyperlink);
}
}
last_idx = idx + 1;
}
// Process content after the last link
for item in content.iter().skip(last_idx) {
let run = Run::new();
let run = self.process_inline_to_run(run, item)?;
if !run.children.is_empty() {
para = para.add_run(run);
}
}
}
// Only add when paragraph has content
if !para.children.is_empty() {
docx = docx.add_paragraph(para);
}
Ok(docx)
}
/// Process node and add to document
fn process_node(&mut self, mut docx: Docx, node: &Node) -> Result<Docx> {
match node {
Node::Document(blocks) => {
for block in blocks {
docx = self.process_node(docx, block)?;
}
}
Node::Paragraph(content) => {
docx = self.process_paragraph(docx, content, None)?;
}
Node::Heading {
level,
content,
heading_type: _,
} => {
// Determine heading style name
let style_name = match level {
1 => "Heading1",
2 => "Heading2",
3 => "Heading3",
4 => "Heading4",
5 => "Heading5",
_ => "Heading6",
};
docx = self.process_paragraph(docx, content, Some(style_name))?;
}
Node::BlockQuote(content) => {
for block in content {
if let Node::Paragraph(inline) = block {
docx = self.process_paragraph(docx, inline, Some("Blockquote"))?;
} else {
docx = self.process_node(docx, block)?;
}
}
}
Node::CodeBlock {
language,
content,
block_type: _,
} => {
// Add language information
if let Some(lang) = language {
if !lang.is_empty() {
let lang_para = Paragraph::new()
.style("CodeBlock")
.add_run(Run::new().add_text(lang));
docx = docx.add_paragraph(lang_para);
}
}
// Process code line by line, preserving line breaks
let lines: Vec<&str> = content.split('\n').collect();
for line in lines {
let code_para = Paragraph::new()
.style("CodeBlock")
.add_run(Run::new().add_text(line));
docx = docx.add_paragraph(code_para);
}
}
Node::OrderedList { start: _, items } => {
docx = self.process_ordered_list(docx, items)?;
}
Node::UnorderedList(items) => {
docx = self.process_unordered_list(docx, items)?;
}
Node::Table {
headers,
rows,
alignments: _,
} => {
docx = self.process_table(docx, headers, rows)?;
}
Node::Image { url, title: _, alt } => {
docx = self.process_image(docx, url, alt)?;
}
Node::Custom(custom_node) => {
if let Some(figure_node) = custom_node.as_any().downcast_ref::<FigureNode>() {
// Process figure node with special handling
docx = self.process_figure(docx, figure_node)?;
} else if let Some(external_frame) = custom_node
.as_any()
.downcast_ref::<crate::common::ExternalFrameNode>(
) {
let data = base64::engine::general_purpose::STANDARD
.decode(&external_frame.svg_data)
.map_err(|e| format!("Failed to decode SVG data: {}", e))?;
docx = self.image_processor.process_image_data(
docx,
&data,
Some(&external_frame.alt_text),
None,
);
} else {
// Fallback for unknown custom nodes - ignore or add placeholder
let placeholder = "[Unknown custom content]";
let para = Paragraph::new().add_run(Run::new().add_text(placeholder));
docx = docx.add_paragraph(para);
}
}
Node::ThematicBreak => {
// Add horizontal line as specially formatted paragraph
let hr_para = Paragraph::new()
.style("HorizontalLine")
.add_run(Run::new().add_text(""));
docx = docx.add_paragraph(hr_para);
}
// Inline elements should not be processed here individually
_ => {}
}
Ok(docx)
}
/// Process ordered list
fn process_ordered_list(&mut self, mut docx: Docx, items: &[ListItem]) -> Result<Docx> {
// Enter deeper list level
self.list_level += 1;
let current_level = self.list_level - 1;
// Create new ordered list numbering definition
let (doc, num_id) = self.numbering.create_ordered_numbering(docx);
docx = doc;
// Process list items
for item in items {
if let ListItem::Ordered { content, .. } = item {
docx = self.process_list_item_content(docx, content, num_id, current_level)?;
}
}
// Exit list level
self.list_level -= 1;
Ok(docx)
}
/// Process unordered list
fn process_unordered_list(&mut self, mut docx: Docx, items: &[ListItem]) -> Result<Docx> {
// Enter deeper list level
self.list_level += 1;
let current_level = self.list_level - 1;
// Create new unordered list numbering definition
let (doc, num_id) = self.numbering.create_unordered_numbering(docx);
docx = doc;
// Process list items
for item in items {
if let ListItem::Unordered { content } = item {
docx = self.process_list_item_content(docx, content, num_id, current_level)?;
}
}
// Exit list level
self.list_level -= 1;
Ok(docx)
}
/// Helper function to process list item content
fn process_list_item_content(
&mut self,
mut docx: Docx,
content: &[Node],
num_id: usize,
level: usize,
) -> Result<Docx> {
// If content is empty, add empty paragraph
if content.is_empty() {
let empty_para = Paragraph::new()
.numbering(NumberingId::new(num_id), IndentLevel::new(level))
.add_run(Run::new().add_text(""));
return Ok(docx.add_paragraph(empty_para));
}
// Process content
for block in content {
match block {
Node::Paragraph(inline) => {
let mut para = Paragraph::new()
.numbering(NumberingId::new(num_id), IndentLevel::new(level));
// Process paragraph content
for node in inline {
let run = Run::new();
let run = self.process_inline_to_run(run, node)?;
if !run.children.is_empty() {
para = para.add_run(run);
}
}
docx = docx.add_paragraph(para);
}
// Recursively process nested lists
Node::OrderedList { start: _, items: _ } | Node::UnorderedList(_) => {
docx = self.process_node(docx, block)?;
}
_ => {
docx = self.process_node(docx, block)?;
}
}
}
Ok(docx)
}
/// Process table
fn process_table(&self, mut docx: Docx, headers: &[Node], rows: &[Vec<Node>]) -> Result<Docx> {
let mut table = Table::new(vec![]).style("Table");
// Process table headers
if !headers.is_empty() {
let mut cells = Vec::new();
for header_node in headers {
let mut table_cell = TableCell::new();
let mut para = Paragraph::new();
let run = Run::new();
let run = self.process_inline_to_run(run, header_node)?;
if !run.children.is_empty() {
para = para.add_run(run);
}
if !para.children.is_empty() {
table_cell = table_cell.add_paragraph(para);
}
cells.push(table_cell);
}
if !cells.is_empty() {
let header_row = TableRow::new(cells);
table = table.add_row(header_row);
}
}
// Process table rows
for row in rows {
let mut cells = Vec::new();
for cell_node in row {
let mut table_cell = TableCell::new();
let mut para = Paragraph::new();
let run = Run::new();
let run = self.process_inline_to_run(run, cell_node)?;
if !run.children.is_empty() {
para = para.add_run(run);
}
if !para.children.is_empty() {
table_cell = table_cell.add_paragraph(para);
}
cells.push(table_cell);
}
if !cells.is_empty() {
let data_row = TableRow::new(cells);
table = table.add_row(data_row);
}
}
// Add table to document
docx = docx.add_table(table);
Ok(docx)
}
/// Generate DOCX document
pub fn generate_docx(&mut self, doc: &Node) -> Result<Vec<u8>> {
// Create DOCX document and initialize styles
let mut docx = Docx::new();
docx = self.styles.initialize_styles(docx);
// Process document content
docx = self.process_node(docx, doc)?;
// Initialize numbering definitions
docx = self.numbering.initialize_numbering(docx);
// Build and pack document
let docx_built = docx.build();
let mut buffer = Vec::new();
docx_built
.pack(&mut Cursor::new(&mut buffer))
.map_err(|e| format!("Failed to pack DOCX: {}", e))?;
Ok(buffer)
}
}
impl FormatWriter for DocxWriter {
fn write_vec(&mut self, document: &Node) -> Result<Vec<u8>> {
self.list_level = 0;
self.list_numbering_count = 0;
self.generate_docx(document)
}
fn write_eco(&mut self, _document: &Node, _output: &mut EcoString) -> Result<()> {
Err("DOCX format does not support EcoString output".into())
}
}