pdf_writer/lib.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
/*!
A step-by-step PDF writer.
The entry point into the API is the [`Pdf`] struct, which constructs the
document into one big internal buffer. The top-level writer has many methods to
create specialized writers for specific PDF objects. These all follow the same
general pattern: They borrow the main buffer mutably, expose a builder pattern
for writing individual fields in a strongly typed fashion and finish up the
object when dropped.
There are a few more top-level structs with internal buffers, like the
[`Content`] stream builder and the [`Chunk`], but wherever possible buffers
are borrowed from parent writers to minimize allocations.
# Writers
The writers contained is this crate fall roughly into two categories.
**Core writers** enable you to write arbitrary PDF objects.
- The [`Obj`] writer allows to write most fundamental PDF objects (numbers,
strings, arrays, dictionaries, ...). It is exposed through
[`Chunk::indirect`] to write top-level indirect objects and through
[`Array::push`] and [`Dict::insert`] to compose objects.
- Streams are exposed through a separate [`Chunk::stream`] method since
they _must_ be indirect objects.
**Specialized writers** for things like a _[page]_ or an _[image]_ expose the
core writer's capabilities in a strongly typed fashion.
- A [`Page`] writer, for example, is just a thin wrapper around a [`Dict`] and
it even derefs to a dictionary in case you need to write a field that is not
yet exposed by the typed API.
- Similarly, the [`ImageXObject`] derefs to a [`Stream`], so that the [`filter()`]
function can be shared by all kinds of streams. The [`Stream`] in turn derefs
to a [`Dict`] so that you can add arbitrary fields to the stream dictionary.
When you bind a writer to a variable instead of just writing a chained builder
pattern, you may need to manually drop it before starting a new object using
[`finish()`](Finish::finish) or [`drop()`].
# Minimal example
The following example creates a PDF with a single, empty A4 page.
```
use pdf_writer::{Pdf, Rect, Ref};
# fn main() -> std::io::Result<()> {
// Define some indirect reference ids we'll use.
let catalog_id = Ref::new(1);
let page_tree_id = Ref::new(2);
let page_id = Ref::new(3);
// Write a document catalog and a page tree with one A4 page that uses no resources.
let mut pdf = Pdf::new();
pdf.catalog(catalog_id).pages(page_tree_id);
pdf.pages(page_tree_id).kids([page_id]).count(1);
pdf.page(page_id)
.parent(page_tree_id)
.media_box(Rect::new(0.0, 0.0, 595.0, 842.0))
.resources();
// Finish with cross-reference table and trailer and write to file.
std::fs::write("target/empty.pdf", pdf.finish())?;
# Ok(())
# }
```
For more examples, check out the [examples folder] in the repository.
# Note
This crate is rather low-level. It does not allocate or validate indirect
reference IDs for you and it does not check whether you write all required
fields for an object. Refer to the [PDF specification] to make sure you create
valid PDFs.
[page]: writers::Page
[image]: writers::ImageXObject
[`filter()`]: Stream::filter
[examples folder]: https://github.com/typst/pdf-writer/tree/main/examples
[PDF specification]: https://opensource.adobe.com/dc-acrobat-sdk-docs/pdfstandards/PDF32000_2008.pdf
*/
#![forbid(unsafe_code)]
#![deny(missing_docs)]
#![allow(clippy::wrong_self_convention)]
#[macro_use]
mod macros;
mod actions;
mod annotations;
mod attributes;
mod buf;
mod chunk;
mod color;
mod content;
mod files;
mod font;
mod forms;
mod functions;
mod object;
mod renditions;
mod renumber;
mod structure;
mod transitions;
mod xobject;
/// Strongly typed writers for specific PDF structures.
pub mod writers {
use super::*;
pub use actions::{Action, AdditionalActions, Fields};
pub use annotations::{
Annotation, Appearance, AppearanceCharacteristics, AppearanceEntry, BorderStyle,
IconFit,
};
pub use attributes::{
Attributes, FieldAttributes, LayoutAttributes, ListAttributes, TableAttributes,
UserProperty,
};
pub use color::{
ColorSpace, DeviceN, DeviceNAttrs, DeviceNMixingHints, DeviceNProcess,
FunctionShading, IccProfile, OutputIntent, Separation, SeparationInfo,
ShadingPattern, StreamShading, StreamShadingType, TilingPattern,
};
pub use content::{
Artifact, ExtGraphicsState, MarkContent, Operation, PositionedItems,
PropertyList, Resources, ShowPositioned, SoftMask,
};
pub use files::{EmbeddedFile, EmbeddingParams, FileSpec};
pub use font::{
CidFont, Cmap, Differences, Encoding, FontDescriptor, FontDescriptorOverride,
Type0Font, Type1Font, Type3Font, WMode, Widths,
};
pub use forms::{Field, Form};
pub use functions::{
ExponentialFunction, PostScriptFunction, SampledFunction, StitchingFunction,
};
pub use object::{
DecodeParms, NameTree, NameTreeEntries, NumberTree, NumberTreeEntries,
};
pub use renditions::{MediaClip, MediaPermissions, MediaPlayParams, Rendition};
pub use structure::{
Catalog, ClassMap, Destination, DeveloperExtension, DocumentInfo, MarkInfo,
MarkedRef, Metadata, Names, ObjectRef, Outline, OutlineItem, Page, PageLabel,
Pages, RoleMap, StructChildren, StructElement, StructTreeRoot, ViewerPreferences,
};
pub use transitions::Transition;
pub use xobject::{FormXObject, Group, ImageXObject, Reference};
}
/// Types used by specific PDF structures.
pub mod types {
use super::*;
pub use actions::{ActionType, FormActionFlags, RenditionOperation};
pub use annotations::{
AnnotationFlags, AnnotationIcon, AnnotationType, BorderType, HighlightEffect,
IconScale, IconScaleType, TextPosition,
};
pub use attributes::{
AttributeOwner, BlockAlign, FieldRole, FieldState, InlineAlign,
LayoutBorderStyle, ListNumbering, Placement, RubyAlign, RubyPosition,
TableHeaderScope, TextAlign, TextDecorationType, WritingMode,
};
pub use color::{
DeviceNSubtype, FunctionShadingType, OutputIntentSubtype, PaintType, TilingType,
};
pub use content::{
ArtifactAttachment, ArtifactSubtype, ArtifactType, BlendMode, ColorSpaceOperand,
LineCapStyle, LineJoinStyle, MaskType, OverprintMode, ProcSet, RenderingIntent,
TextRenderingMode,
};
pub use files::AssociationKind;
pub use font::{
CidFontType, CjkClass, FontFlags, FontStretch, SystemInfo, UnicodeCmap,
};
pub use forms::{
CheckBoxState, ChoiceOptions, FieldFlags, FieldType, Quadding, SigFlags,
};
pub use functions::{InterpolationOrder, PostScriptOp};
pub use object::Predictor;
pub use renditions::{MediaClipType, RenditionType, TempFileType};
pub use structure::{
Direction, NumberingStyle, OutlineItemFlags, PageLayout, PageMode, StructRole,
TabOrder, TrappingStatus,
};
pub use transitions::{TransitionAngle, TransitionStyle};
pub use xobject::SMaskInData;
}
pub use self::chunk::Chunk;
pub use self::content::Content;
pub use self::object::{
Array, Date, Dict, Filter, Finish, Name, Null, Obj, Primitive, Rect, Ref, Rewrite,
Str, Stream, TextStr, TypedArray, TypedDict, Writer,
};
use std::fmt::{self, Debug, Formatter};
use std::io::Write;
use std::ops::{Deref, DerefMut};
use self::buf::BufExt;
use self::writers::*;
/// A builder for a PDF file.
///
/// This type constructs a PDF file in-memory. Aside from a few specific
/// structures, a PDF file mostly consists of indirect objects. For more
/// flexibility, you can write these objects either directly into a [`Pdf`] or
/// into a [`Chunk`], which you can add to the [`Pdf`] (or another chunk) later.
/// Therefore, most writing methods are exposed on the chunk type, which this
/// type dereferences to.
pub struct Pdf {
chunk: Chunk,
catalog_id: Option<Ref>,
info_id: Option<Ref>,
file_id: Option<(Vec<u8>, Vec<u8>)>,
}
impl Pdf {
/// Create a new PDF with the default buffer capacity (currently 8 KB).
#[allow(clippy::new_without_default)]
pub fn new() -> Self {
Self::with_capacity(8 * 1024)
}
/// Create a new PDF with the specified initial buffer capacity.
pub fn with_capacity(capacity: usize) -> Self {
let mut chunk = Chunk::with_capacity(capacity);
chunk.buf.extend(b"%PDF-1.7\n%\x80\x80\x80\x80\n\n");
Self {
chunk,
catalog_id: None,
info_id: None,
file_id: None,
}
}
/// Set the binary marker in the header of the PDF.
///
/// This can be useful if you want to ensure that your PDF consists of only
/// ASCII characters, as this is not the case by default.
///
/// _Default value_: \x80\x80\x80\x80
pub fn set_binary_marker(&mut self, marker: &[u8; 4]) {
self.chunk.buf[10..14].copy_from_slice(marker);
}
/// Set the PDF version.
///
/// The version is not semantically important to the crate, but must be
/// present in the output document.
///
/// _Default value_: 1.7.
pub fn set_version(&mut self, major: u8, minor: u8) {
if major < 10 {
self.chunk.buf[5] = b'0' + major;
}
if minor < 10 {
self.chunk.buf[7] = b'0' + minor;
}
}
/// Set the file identifier for the document.
///
/// The file identifier is a pair of two byte strings that shall be used to
/// uniquely identify a particular file. The first string should always stay
/// the same for a document, the second should change for each revision. It
/// is optional, but recommended. In PDF/A, this is required. PDF 1.1+.
pub fn set_file_id(&mut self, id: (Vec<u8>, Vec<u8>)) {
self.file_id = Some(id);
}
/// Start writing the document catalog. Required.
///
/// This will also register the document catalog with the file trailer,
/// meaning that you don't need to provide the given `id` anywhere else.
pub fn catalog(&mut self, id: Ref) -> Catalog<'_> {
self.catalog_id = Some(id);
self.indirect(id).start()
}
/// Start writing the document information.
///
/// This will also register the document information dictionary with the
/// file trailer, meaning that you don't need to provide the given `id`
/// anywhere else.
pub fn document_info(&mut self, id: Ref) -> DocumentInfo<'_> {
self.info_id = Some(id);
self.indirect(id).start()
}
/// Write the cross-reference table and file trailer and return the
/// underlying buffer.
///
/// Panics if any indirect reference id was used twice.
pub fn finish(self) -> Vec<u8> {
let Chunk { mut buf, mut offsets } = self.chunk;
offsets.sort();
let xref_len = 1 + offsets.last().map_or(0, |p| p.0.get());
let xref_offset = buf.len();
buf.extend(b"xref\n0 ");
buf.push_int(xref_len);
buf.push(b'\n');
if offsets.is_empty() {
write!(buf, "0000000000 65535 f\r\n").unwrap();
}
let mut written = 0;
for (i, (object_id, offset)) in offsets.iter().enumerate() {
if written > object_id.get() {
panic!("duplicate indirect reference id: {}", object_id.get());
}
// Fill in free list.
let start = written;
for free_id in start..object_id.get() {
let mut next = free_id + 1;
if next == object_id.get() {
// Find next free id.
for (used_id, _) in &offsets[i..] {
if next < used_id.get() {
break;
} else {
next = used_id.get() + 1;
}
}
}
let gen = if free_id == 0 { "65535" } else { "00000" };
write!(buf, "{:010} {} f\r\n", next % xref_len, gen).unwrap();
written += 1;
}
write!(buf, "{:010} 00000 n\r\n", offset).unwrap();
written += 1;
}
// Write the trailer dictionary.
buf.extend(b"trailer\n");
let mut trailer = Obj::direct(&mut buf, 0).dict();
trailer.pair(Name(b"Size"), xref_len);
if let Some(catalog_id) = self.catalog_id {
trailer.pair(Name(b"Root"), catalog_id);
}
if let Some(info_id) = self.info_id {
trailer.pair(Name(b"Info"), info_id);
}
if let Some(file_id) = self.file_id {
let mut ids = trailer.insert(Name(b"ID")).array();
ids.item(Str(&file_id.0));
ids.item(Str(&file_id.1));
}
trailer.finish();
// Write where the cross-reference table starts.
buf.extend(b"\nstartxref\n");
write!(buf, "{}", xref_offset).unwrap();
// Write the end of file marker.
buf.extend(b"\n%%EOF");
buf
}
}
impl Debug for Pdf {
fn fmt(&self, f: &mut Formatter<'_>) -> fmt::Result {
f.pad("Pdf(..)")
}
}
impl Deref for Pdf {
type Target = Chunk;
fn deref(&self) -> &Self::Target {
&self.chunk
}
}
impl DerefMut for Pdf {
fn deref_mut(&mut self) -> &mut Self::Target {
&mut self.chunk
}
}
#[cfg(test)]
mod tests {
use super::*;
/// Print a chunk.
#[allow(unused)]
pub fn print_chunk(chunk: &Chunk) {
println!("========== Chunk ==========");
for &(id, offset) in &chunk.offsets {
println!("[{}]: {}", id.get(), offset);
}
println!("---------------------------");
print!("{}", String::from_utf8_lossy(&chunk.buf));
println!("===========================");
}
/// Return the slice of bytes written during the execution of `f`.
pub fn slice<F>(f: F) -> Vec<u8>
where
F: FnOnce(&mut Pdf),
{
let mut w = Pdf::new();
let start = w.len();
f(&mut w);
let end = w.len();
let buf = w.finish();
buf[start..end].to_vec()
}
/// Return the slice of bytes written for an object.
pub fn slice_obj<F>(f: F) -> Vec<u8>
where
F: FnOnce(Obj<'_>),
{
let buf = slice(|w| f(w.indirect(Ref::new(1))));
buf[8..buf.len() - 9].to_vec()
}
#[test]
fn test_minimal() {
let w = Pdf::new();
test!(
w.finish(),
b"%PDF-1.7\n%\x80\x80\x80\x80\n",
b"xref\n0 1\n0000000000 65535 f\r",
b"trailer\n<<\n /Size 1\n>>",
b"startxref\n16\n%%EOF",
);
}
#[test]
fn test_xref_free_list_short() {
let mut w = Pdf::new();
w.indirect(Ref::new(1)).primitive(1);
w.indirect(Ref::new(2)).primitive(2);
test!(
w.finish(),
b"%PDF-1.7\n%\x80\x80\x80\x80\n",
b"1 0 obj\n1\nendobj\n",
b"2 0 obj\n2\nendobj\n",
b"xref",
b"0 3",
b"0000000000 65535 f\r",
b"0000000016 00000 n\r",
b"0000000034 00000 n\r",
b"trailer",
b"<<\n /Size 3\n>>",
b"startxref\n52\n%%EOF",
)
}
#[test]
fn test_xref_free_list_long() {
let mut w = Pdf::new();
w.set_version(1, 4);
w.indirect(Ref::new(1)).primitive(1);
w.indirect(Ref::new(2)).primitive(2);
w.indirect(Ref::new(5)).primitive(5);
test!(
w.finish(),
b"%PDF-1.4\n%\x80\x80\x80\x80\n",
b"1 0 obj\n1\nendobj\n",
b"2 0 obj\n2\nendobj\n",
b"5 0 obj\n5\nendobj\n",
b"xref",
b"0 6",
b"0000000003 65535 f\r",
b"0000000016 00000 n\r",
b"0000000034 00000 n\r",
b"0000000004 00000 f\r",
b"0000000000 00000 f\r",
b"0000000052 00000 n\r",
b"trailer",
b"<<\n /Size 6\n>>",
b"startxref\n70\n%%EOF",
)
}
#[test]
#[should_panic(expected = "duplicate indirect reference id: 3")]
fn test_xref_free_list_duplicate() {
let mut w = Pdf::new();
w.indirect(Ref::new(3)).primitive(1);
w.indirect(Ref::new(5)).primitive(2);
w.indirect(Ref::new(13)).primitive(1);
w.indirect(Ref::new(3)).primitive(1);
w.indirect(Ref::new(6)).primitive(2);
w.finish();
}
#[test]
fn test_binary_marker() {
let mut w = Pdf::new();
w.set_binary_marker(&[b'A', b'B', b'C', b'D']);
test!(
w.finish(),
b"%PDF-1.7\n%ABCD\n",
b"xref\n0 1\n0000000000 65535 f\r",
b"trailer\n<<\n /Size 1\n>>",
b"startxref\n16\n%%EOF",
);
}
}