Annotation Extraction
PDF Oxide provides access to all annotation types defined in the PDF specification (ISO 32000-1:2008, Section 12.5), including text notes, hyperlinks, highlights, stamps, ink annotations, and more. The document outline (bookmarks) is also accessible for building navigation structures.
Use get_annotations() on PdfDocument for raw annotation data, or the PdfPage DOM API for a unified AnnotationWrapper interface that supports both reading and writing.
Binding coverage. Annotation extraction is available in Python (
doc.get_annotations(page)), Rust (doc.get_annotations(page)), WASM (doc.getAnnotations(page)), and Go (doc.Annotations(page)). The C# public API does not yet expose aGetAnnotationswrapper — the native FFI method exists (PdfDocumentGetPageAnnotations) but is unwrapped. For annotation extraction from C#, either use the Rust CLI (pdf-oxide annotations doc.pdf) or callPdfPageGetAnnotationsCount/pdf_get_annotations_by_typedirectly via P/Invoke until a public wrapper lands.
Quick Example
Python
from pdf_oxide import PdfDocument
doc = PdfDocument("annotated.pdf")
page = doc.page(0)
for annot in page.annotations():
print(f"{annot.subtype}: {annot.contents}")
Node.js
const { PdfDocument } = require("pdf-oxide");
const doc = new PdfDocument("annotated.pdf");
const annotations = doc.getPageAnnotations(0);
for (const annot of annotations) {
console.log(`${annot.subtype}: ${annot.contents}`);
}
doc.close();
Go
import pdfoxide "github.com/yfedoseev/pdf_oxide/go"
doc, _ := pdfoxide.Open("annotated.pdf")
defer doc.Close()
annotations, _ := doc.Annotations(0)
for _, annot := range annotations {
fmt.Printf("%s: %s\n", annot.Subtype, annot.Content)
}
<!-- C#: no equivalent on PdfDocument — annotations not exposed on csharp/PdfOxide/Core/PdfDocument.cs -->
WASM
const doc = new WasmPdfDocument(bytes);
const annotations = doc.getAnnotations(0);
for (const annot of annotations) {
console.log(`${annot.subtype}: ${annot.contents}`);
}
Rust
use pdf_oxide::PdfDocument;
let mut doc = PdfDocument::open("annotated.pdf")?;
let annotations = doc.get_annotations(0)?;
for annot in &annotations {
println!("{:?}: {:?}", annot.subtype_enum, annot.contents);
}
Java
import fyi.oxide.pdf.*;
import fyi.oxide.pdf.annotation.Annotation;
import java.nio.file.Path;
try (PdfDocument doc = PdfDocument.open(Path.of("annotated.pdf"))) {
for (Annotation annot : doc.page(0).annotations()) {
System.out.println(annot.type() + ": " + annot.contents().orElse(""));
}
}
C++
#include <pdf_oxide/pdf_oxide.hpp>
auto doc = pdf_oxide::Document::open("annotated.pdf");
for (const auto& annot : doc.page_annotations(0)) {
std::cout << annot.subtype << ": " << annot.content << "\n";
}
Swift
import PdfOxide
let doc = try Document.open("annotated.pdf")
for annot in try doc.pageAnnotations(0) {
print("\(annot.subtype): \(annot.content)")
}
Kotlin
import fyi.oxide.pdf.*
PdfDocument.open(java.nio.file.Path.of("annotated.pdf")).use { doc ->
for (annot in doc.page(0).annotations()) {
println("${annot.type()}: ${annot.contents().orElse("")}")
}
}
Dart
import 'package:pdf_oxide/pdf_oxide.dart';
final doc = PdfDocument.open('annotated.pdf');
for (final annot in doc.pageAnnotations(0)) {
print('${annot.subtype}: ${annot.content}');
}
doc.close();
R
library(pdfoxide)
doc <- pdf_open("annotated.pdf")
for (annot in pdf_page_annotations(doc, 0)) {
cat(sprintf("%s: %s\n", annot$subtype, annot$content))
}
Julia
using PdfOxide
doc = open_document("annotated.pdf")
for annot in page_annotations(doc, 0)
println("$(annot.subtype): $(annot.content)")
end
Zig
const pdf_oxide = @import("pdf_oxide");
const a = std.heap.page_allocator;
var doc = try pdf_oxide.Document.open("annotated.pdf");
defer doc.deinit();
const annotations = try doc.pageAnnotations(a, 0);
defer pdf_oxide.Document.freeAnnotations(a, annotations);
for (annotations) |annot| {
std.debug.print("{s}: {s}\n", .{ annot.subtype, annot.content });
}
Scala
import fyi.oxide.pdf.{PdfDocument, annotationsSeq, contentsOption}
import scala.util.Using
Using.resource(PdfDocument.open("annotated.pdf")) { doc =>
for (annot <- doc.page(0).annotationsSeq) {
println(s"${annot.`type`()}: ${annot.contentsOption.getOrElse("")}")
}
}
Clojure
(require '[pdf-oxide.core :as pdf])
(with-open [d (pdf/open "annotated.pdf")]
(doseq [annot (pdf/annotations (pdf/page d 0))]
(println (str (.type annot) ": " (.orElse (.contents annot) "")))))
Objective-C
#import "POXPdfOxide.h"
NSError *err = nil;
POXDocument *doc = [POXDocument openPath:@"annotated.pdf" error:&err];
for (POXAnnotation *annot in [doc pageAnnotations:0 error:&err]) {
NSLog(@"%@: %@", annot.subtype, annot.content);
}
Elixir
{:ok, doc} = PdfOxide.open("annotated.pdf")
{:ok, annots} = PdfOxide.page_annotations(doc, 0)
Enum.each(annots, fn a -> IO.puts("#{a.subtype}: #{a.content}") end)
API Reference
get_annotations(page_index) -> Vec<Annotation>
Extract raw annotations from a specific page. Returns all annotation types present on the page.
| Parameter | Type | Description |
|---|---|---|
page_index |
usize |
Zero-based page index |
Returns: A vector of Annotation objects.
Annotation Fields
| Field | Type | Description |
|---|---|---|
annotation_type |
String |
Always "Annot" |
subtype |
Option<String> |
Raw subtype string (e.g., "Text", "Highlight") |
subtype_enum |
AnnotationSubtype |
Parsed subtype enum |
contents |
Option<String> |
Text contents of the annotation |
rect |
Option<[f64; 4]> |
Bounding rectangle [x1, y1, x2, y2] |
author |
Option<String> |
Author/creator (/T entry) |
creation_date |
Option<String> |
Creation date |
modification_date |
Option<String> |
Last modification date |
subject |
Option<String> |
Subject of the annotation |
destination |
Option<LinkDestination> |
Link destination (for Link annotations) |
action |
Option<LinkAction> |
Link action (for Link annotations) |
color |
Option<Vec<f64>> |
Annotation color components |
flags |
Option<AnnotationFlags> |
Annotation flags (invisible, hidden, print, etc.) |
AnnotationSubtype Variants
| Variant | Description |
|---|---|
Text |
Sticky note annotation |
Link |
Hyperlink annotation |
FreeText |
Text box annotation |
Line |
Line shape annotation |
Square |
Rectangle shape annotation |
Circle |
Ellipse shape annotation |
Polygon |
Polygon shape annotation |
PolyLine |
Polyline shape annotation |
Highlight |
Text highlight markup |
Underline |
Text underline markup |
Squiggly |
Squiggly underline markup |
StrikeOut |
Strikethrough markup |
Stamp |
Rubber stamp annotation |
Ink |
Freehand drawing annotation |
Popup |
Pop-up note associated with another annotation |
FileAttachment |
Embedded file annotation |
Sound |
Sound annotation |
Movie |
Movie annotation |
Screen |
Screen annotation |
Widget |
Form field widget |
PrinterMark |
Printer’s mark annotation |
TrapNet |
Trap network annotation |
Watermark |
Watermark annotation |
ThreeDimensional |
3D annotation |
Redact |
Redaction annotation |
Caret |
Caret annotation (insertion point) |
RichMedia |
Rich media annotation |
Unknown |
Unrecognized annotation type |
get_outline() -> Option<Vec<OutlineItem>>
Get the document outline (bookmarks) if present. Returns a hierarchical tree of outline items that can be used for document navigation.
Returns:
Some(Vec<OutlineItem>)– Bookmarks found and parsedNone– No bookmarks in the document
OutlineItem Fields
| Field | Type | Description |
|---|---|---|
title |
String |
Bookmark title text |
dest |
Option<Destination> |
Navigation destination |
children |
Vec<OutlineItem> |
Nested child bookmarks |
Destination Variants
| Variant | Description |
|---|---|
PageIndex(usize) |
Direct page reference (0-based index) |
Named(String) |
Named destination identifier |
Rust
let mut doc = PdfDocument::open("book.pdf")?;
if let Some(outline) = doc.get_outline()? {
for item in &outline {
println!(" {}", item.title);
for child in &item.children {
println!(" {}", child.title);
}
}
} else {
println!("No bookmarks found.");
}
C++
#include <pdf_oxide/pdf_oxide.hpp>
auto doc = pdf_oxide::Document::open("book.pdf");
std::string outline = doc.get_outline(); // JSON tree of bookmarks
std::cout << outline << "\n";
Swift
import PdfOxide
let doc = try Document.open("book.pdf")
let outline = try doc.outline() // JSON tree of bookmarks
print(outline)
Dart
import 'package:pdf_oxide/pdf_oxide.dart';
final doc = PdfDocument.open('book.pdf');
final outline = doc.getOutline(); // JSON tree of bookmarks
print(outline);
doc.close();
R
library(pdfoxide)
doc <- pdf_open("book.pdf")
outline <- pdf_get_outline(doc) # JSON tree of bookmarks
cat(outline, "\n")
Julia
using PdfOxide
doc = open_document("book.pdf")
outline = get_outline(doc) # JSON tree of bookmarks
println(outline)
Zig
const pdf_oxide = @import("pdf_oxide");
const a = std.heap.page_allocator;
var doc = try pdf_oxide.Document.open("book.pdf");
defer doc.deinit();
const outline = try doc.outline(a); // JSON tree of bookmarks; caller owns it
defer a.free(outline);
std.debug.print("{s}\n", .{outline});
Objective-C
#import "POXPdfOxide.h"
NSError *err = nil;
POXDocument *doc = [POXDocument openPath:@"book.pdf" error:&err];
NSString *outline = [doc outlineWithError:&err]; // JSON tree of bookmarks
NSLog(@"%@", outline);
Elixir
{:ok, doc} = PdfOxide.open("book.pdf")
{:ok, outline} = PdfOxide.outline(doc) # JSON tree of bookmarks
IO.puts(outline)
PdfPage Annotation API (DOM)
The PdfPage object from the DocumentEditor provides a higher-level AnnotationWrapper interface that supports both reading existing annotations and adding new ones.
page.annotations() -> &[AnnotationWrapper]
Get all annotations on the page as wrapped objects.
page.find_annotations_by_type(subtype) -> Vec<&AnnotationWrapper>
Find annotations of a specific type.
page.add_annotation(annotation)
Add a new annotation to the page.
page.remove_annotation(index) -> Option<AnnotationWrapper>
Remove an annotation by index.
page.find_annotations_in_region(rect) -> Vec<&AnnotationWrapper>
Find annotations whose bounding boxes intersect a given region.
AnnotationWrapper Methods
| Method | Returns | Description |
|---|---|---|
id() |
AnnotationId |
Unique session ID |
subtype() |
AnnotationSubtype |
Annotation type |
rect() |
Rect |
Bounding rectangle |
contents() |
Option<&str> |
Text contents |
color() |
Option<(f32, f32, f32)> |
RGB color (0.0–1.0) |
is_modified() |
bool |
Whether annotation has been changed |
Python
doc = PdfDocument("annotated.pdf")
page = doc.page(0)
# List all annotations
for annot in page.annotations():
print(f"[{annot.subtype}] {annot.contents} at {annot.rect}")
# Find highlights
highlights = [a for a in page.annotations() if a.subtype == "Highlight"]
print(f"Found {len(highlights)} highlights")
Node.js
const doc = new PdfDocument("annotated.pdf");
const annotations = doc.getPageAnnotations(0);
// List all annotations
for (const annot of annotations) {
console.log(`[${annot.subtype}] ${annot.contents}`);
}
// Find highlights
const highlights = annotations.filter(a => a.subtype === "Highlight");
console.log(`Found ${highlights.length} highlights`);
doc.close();
Go
doc, _ := pdfoxide.Open("annotated.pdf")
defer doc.Close()
annotations, _ := doc.Annotations(0)
// List all annotations
for _, annot := range annotations {
fmt.Printf("[%s] %s\n", annot.Subtype, annot.Content)
}
// Find highlights
highlights := 0
for _, a := range annotations {
if a.Subtype == "Highlight" {
highlights++
}
}
fmt.Printf("Found %d highlights\n", highlights)
<!-- C#: no equivalent on PdfDocument — annotations not exposed on csharp/PdfOxide/Core/PdfDocument.cs -->
WASM
const doc = new WasmPdfDocument(bytes);
const annotations = doc.getAnnotations(0);
// List all annotations
for (const annot of annotations) {
console.log(`[${annot.subtype}] ${annot.contents}`);
}
// Find highlights
const highlights = annotations.filter(a => a.subtype === "Highlight");
console.log(`Found ${highlights.length} highlights`);
Rust
use pdf_oxide::editor::{DocumentEditor, EditableDocument};
use pdf_oxide::annotation_types::AnnotationSubtype;
let mut editor = DocumentEditor::open("annotated.pdf")?;
let page = editor.get_page(0)?;
// Find all highlight annotations
let highlights = page.find_annotations_by_type(AnnotationSubtype::Highlight);
for h in &highlights {
println!("Highlight at {:?}: {:?}", h.rect(), h.contents());
}
Java
import fyi.oxide.pdf.*;
import fyi.oxide.pdf.annotation.Annotation;
import fyi.oxide.pdf.annotation.AnnotationType;
import java.nio.file.Path;
try (PdfDocument doc = PdfDocument.open(Path.of("annotated.pdf"))) {
var annotations = doc.page(0).annotations();
// List all annotations
for (Annotation annot : annotations) {
System.out.println("[" + annot.type() + "] " + annot.contents().orElse(""));
}
// Find highlights
long highlights = annotations.stream()
.filter(a -> a.type() == AnnotationType.HIGHLIGHT).count();
System.out.println("Found " + highlights + " highlights");
}
C++
#include <pdf_oxide/pdf_oxide.hpp>
auto doc = pdf_oxide::Document::open("annotated.pdf");
auto annotations = doc.page_annotations(0);
// List all annotations
for (const auto& annot : annotations) {
std::cout << "[" << annot.subtype << "] " << annot.content << "\n";
}
// Find highlights
int highlights = 0;
for (const auto& a : annotations) {
if (a.subtype == "Highlight") highlights++;
}
std::cout << "Found " << highlights << " highlights\n";
Swift
import PdfOxide
let doc = try Document.open("annotated.pdf")
let annotations = try doc.pageAnnotations(0)
// List all annotations
for annot in annotations {
print("[\(annot.subtype)] \(annot.content)")
}
// Find highlights
let highlights = annotations.filter { $0.subtype == "Highlight" }
print("Found \(highlights.count) highlights")
Kotlin
import fyi.oxide.pdf.*
import fyi.oxide.pdf.annotation.AnnotationType
PdfDocument.open(java.nio.file.Path.of("annotated.pdf")).use { doc ->
val annotations = doc.page(0).annotations()
// List all annotations
for (annot in annotations) {
println("[${annot.type()}] ${annot.contents().orElse("")}")
}
// Find highlights
val highlights = annotations.count { it.type() == AnnotationType.HIGHLIGHT }
println("Found $highlights highlights")
}
Dart
import 'package:pdf_oxide/pdf_oxide.dart';
final doc = PdfDocument.open('annotated.pdf');
final annotations = doc.pageAnnotations(0);
// List all annotations
for (final annot in annotations) {
print('[${annot.subtype}] ${annot.content}');
}
// Find highlights
final highlights = annotations.where((a) => a.subtype == 'Highlight');
print('Found ${highlights.length} highlights');
doc.close();
R
library(pdfoxide)
doc <- pdf_open("annotated.pdf")
annotations <- pdf_page_annotations(doc, 0)
# List all annotations
for (annot in annotations) {
cat(sprintf("[%s] %s\n", annot$subtype, annot$content))
}
# Find highlights
highlights <- Filter(function(a) a$subtype == "Highlight", annotations)
cat(sprintf("Found %d highlights\n", length(highlights)))
Julia
using PdfOxide
doc = open_document("annotated.pdf")
annotations = page_annotations(doc, 0)
# List all annotations
for annot in annotations
println("[$(annot.subtype)] $(annot.content)")
end
# Find highlights
highlights = filter(a -> a.subtype == "Highlight", annotations)
println("Found $(length(highlights)) highlights")
Zig
const pdf_oxide = @import("pdf_oxide");
const a = std.heap.page_allocator;
var doc = try pdf_oxide.Document.open("annotated.pdf");
defer doc.deinit();
const annotations = try doc.pageAnnotations(a, 0);
defer pdf_oxide.Document.freeAnnotations(a, annotations);
// List all annotations
for (annotations) |annot| {
std.debug.print("[{s}] {s}\n", .{ annot.subtype, annot.content });
}
// Find highlights
var highlights: usize = 0;
for (annotations) |annot| {
if (std.mem.eql(u8, annot.subtype, "Highlight")) highlights += 1;
}
std.debug.print("Found {d} highlights\n", .{highlights});
Scala
import fyi.oxide.pdf.{PdfDocument, annotationsSeq, contentsOption}
import fyi.oxide.pdf.annotation.AnnotationType
import scala.util.Using
Using.resource(PdfDocument.open("annotated.pdf")) { doc =>
val annotations = doc.page(0).annotationsSeq
// List all annotations
for (annot <- annotations) {
println(s"[${annot.`type`()}] ${annot.contentsOption.getOrElse("")}")
}
// Find highlights
val highlights = annotations.count(_.`type`() == AnnotationType.HIGHLIGHT)
println(s"Found $highlights highlights")
}
Clojure
(require '[pdf-oxide.core :as pdf])
(import 'fyi.oxide.pdf.annotation.AnnotationType)
(with-open [d (pdf/open "annotated.pdf")]
(let [annotations (pdf/annotations (pdf/page d 0))]
;; List all annotations
(doseq [annot annotations]
(println (str "[" (.type annot) "] " (.orElse (.contents annot) ""))))
;; Find highlights
(let [highlights (count (filter #(= (.type %) AnnotationType/HIGHLIGHT) annotations))]
(println (str "Found " highlights " highlights")))))
Objective-C
#import "POXPdfOxide.h"
NSError *err = nil;
POXDocument *doc = [POXDocument openPath:@"annotated.pdf" error:&err];
NSArray<POXAnnotation*> *annotations = [doc pageAnnotations:0 error:&err];
// List all annotations
for (POXAnnotation *annot in annotations) {
NSLog(@"[%@] %@", annot.subtype, annot.content);
}
// Find highlights
NSPredicate *p = [NSPredicate predicateWithFormat:@"subtype == %@", @"Highlight"];
NSUInteger highlights = [annotations filteredArrayUsingPredicate:p].count;
NSLog(@"Found %lu highlights", (unsigned long)highlights);
Elixir
{:ok, doc} = PdfOxide.open("annotated.pdf")
{:ok, annotations} = PdfOxide.page_annotations(doc, 0)
# List all annotations
Enum.each(annotations, fn a -> IO.puts("[#{a.subtype}] #{a.content}") end)
# Find highlights
highlights = Enum.count(annotations, &(&1.subtype == "Highlight"))
IO.puts("Found #{highlights} highlights")
annotations_to_json — serialize a page’s annotations
annotations_to_json serializes a whole annotation list to a JSON array in a single FFI call. The Go binding uses it internally to materialize []Annotation; Swift exposes it directly as annotationsToJson. The C ABI signature is:
char *pdf_oxide_annotations_to_json(const FfiAnnotationList *annotations, int32_t *error_code);
The returned UTF-8 string is caller-owned (free with free_string). Its schema matches the Go Annotation struct — type, subtype, content, x, y, width, height, author, borderWidth, color, creationDate, modificationDate, linkURI, textIconName, isHidden, isPrintable, isReadOnly, isMarkedDeleted.
Swift
import PdfOxide
let doc = try Document.open("annotated.pdf")
let json = try doc.annotationsToJson(0) // String of JSON
print(json)
C ABI
#include "pdf_oxide.h"
int32_t err = 0;
FfiAnnotationList *list = pdf_document_get_page_annotations(doc, /*page=*/0, &err);
char *json = pdf_oxide_annotations_to_json(list, &err);
printf("%s\n", json);
free_string(json);
pdf_oxide_annotation_list_free(list);
C++
#include <pdf_oxide/pdf_oxide.hpp>
auto doc = pdf_oxide::Document::open("annotated.pdf");
std::string json = doc.annotations_to_json(0); // JSON string
std::cout << json << "\n";
Dart
import 'package:pdf_oxide/pdf_oxide.dart';
final doc = PdfDocument.open('annotated.pdf');
final json = doc.annotationsToJson(0); // JSON string
print(json);
doc.close();
R
library(pdfoxide)
doc <- pdf_open("annotated.pdf")
json <- pdf_annotations_to_json(doc, 0) # JSON string
cat(json, "\n")
Julia
using PdfOxide
doc = open_document("annotated.pdf")
json = annotations_to_json(doc, 0) # JSON string
println(json)
Zig
const pdf_oxide = @import("pdf_oxide");
const a = std.heap.page_allocator;
var doc = try pdf_oxide.Document.open("annotated.pdf");
defer doc.deinit();
var list = try doc.annotationList(0);
defer list.deinit();
const json = try list.toJson(a); // caller owns the slice
defer a.free(json);
std.debug.print("{s}\n", .{json});
Objective-C
#import "POXPdfOxide.h"
NSError *err = nil;
POXDocument *doc = [POXDocument openPath:@"annotated.pdf" error:&err];
NSString *json = [doc annotationsJson:0 error:&err]; // JSON string
NSLog(@"%@", json);
Elixir
{:ok, doc} = PdfOxide.open("annotated.pdf")
{:ok, json} = PdfOxide.annotations_to_json(doc, 0) # JSON string
IO.puts(json)
Binding coverage.
annotations_to_jsonis exposed directly in Swift (doc.annotationsToJson(page)), C++ (doc.annotations_to_json(page)), Dart (doc.annotationsToJson(page)), R (pdf_annotations_to_json(doc, page)), Julia (annotations_to_json(doc, page)), Zig (doc.annotationList(page).toJson(...)), Objective-C ([doc annotationsJson:page error:]), Elixir (PdfOxide.annotations_to_json(doc, page)), and the C ABI (pdf_oxide_annotations_to_json); the Go binding calls it internally to decodedoc.Annotations(page)into typed structs. It is compiled out of the WASM target.
annotation_extras — extended annotation attributes
annotation_extras reads the extended attributes of a single annotation that are not part of the core Annotation view: color, creation/modification timestamps, the four visibility flags (hidden, marked-deleted, printable, read-only), a link annotation’s URI, a text annotation’s icon name, and the quad points of a highlight/markup annotation.
In Swift, these are returned together as an AnnotationExtras struct via annotationExtras(page, index:). In Go, the same fields are folded directly into the Annotation struct (Color, CreationDate, ModificationDate, LinkURI, TextIconName, IsHidden, IsPrintable, IsReadOnly, IsMarkedDeleted). Under the hood, both call the pdf_oxide_annotation_get_* / pdf_oxide_*_annotation_get_* C ABI accessor family.
Swift
import PdfOxide
let doc = try Document.open("annotated.pdf")
let extras = try doc.annotationExtras(0, index: 0) // AnnotationExtras
print("color=\(extras.color) created=\(extras.creationDate)")
print("hidden=\(extras.hidden) printable=\(extras.printable) readOnly=\(extras.readOnly)")
if !extras.uri.isEmpty { print("link URI: \(extras.uri)") }
if !extras.iconName.isEmpty { print("icon: \(extras.iconName)") }
for q in extras.quadPoints {
print("quad: (\(q.x1),\(q.y1)) (\(q.x2),\(q.y2)) (\(q.x3),\(q.y3)) (\(q.x4),\(q.y4))")
}
Go
import pdfoxide "github.com/yfedoseev/pdf_oxide/go"
doc, _ := pdfoxide.Open("annotated.pdf")
defer doc.Close()
annotations, _ := doc.Annotations(0)
a := annotations[0]
fmt.Printf("color=%d created=%d modified=%d\n", a.Color, a.CreationDate, a.ModificationDate)
fmt.Printf("hidden=%v printable=%v readOnly=%v deleted=%v\n",
a.IsHidden, a.IsPrintable, a.IsReadOnly, a.IsMarkedDeleted)
if a.LinkURI != "" {
fmt.Printf("link URI: %s\n", a.LinkURI)
}
if a.TextIconName != "" {
fmt.Printf("icon: %s\n", a.TextIconName)
}
C++
#include <pdf_oxide/pdf_oxide.hpp>
auto doc = pdf_oxide::Document::open("annotated.pdf");
std::cout << "color=" << doc.annotation_get_color(0, 0)
<< " created=" << doc.annotation_get_creation_date(0, 0) << "\n";
std::cout << "hidden=" << doc.annotation_is_hidden(0, 0)
<< " printable=" << doc.annotation_is_printable(0, 0)
<< " readOnly=" << doc.annotation_is_read_only(0, 0) << "\n";
auto uri = doc.link_annotation_get_uri(0, 0);
if (!uri.empty()) std::cout << "link URI: " << uri << "\n";
auto icon = doc.text_annotation_get_icon_name(0, 0);
if (!icon.empty()) std::cout << "icon: " << icon << "\n";
Dart
import 'package:pdf_oxide/pdf_oxide.dart';
final doc = PdfDocument.open('annotated.pdf');
final a = doc.pageAnnotationDetails(0)[0]; // AnnotationDetails
print('color=${a.color} created=${a.creationDate} modified=${a.modificationDate}');
print('hidden=${a.hidden} printable=${a.printable} readOnly=${a.readOnly}');
if (a.linkUri.isNotEmpty) print('link URI: ${a.linkUri}');
if (a.iconName.isNotEmpty) print('icon: ${a.iconName}');
doc.close();
R
library(pdfoxide)
doc <- pdf_open("annotated.pdf")
cat(sprintf("color=%d created=%d\n",
pdf_annotation_get_color(doc, 0, 0),
pdf_annotation_get_creation_date(doc, 0, 0)))
cat(sprintf("hidden=%s printable=%s readOnly=%s\n",
pdf_annotation_is_hidden(doc, 0, 0),
pdf_annotation_is_printable(doc, 0, 0),
pdf_annotation_is_read_only(doc, 0, 0)))
uri <- pdf_link_annotation_get_uri(doc, 0, 0)
if (nzchar(uri)) cat(sprintf("link URI: %s\n", uri))
icon <- pdf_text_annotation_get_icon_name(doc, 0, 0)
if (nzchar(icon)) cat(sprintf("icon: %s\n", icon))
Julia
using PdfOxide
doc = open_document("annotated.pdf")
println("color=$(annotation_get_color(doc, 0, 0)) created=$(annotation_creation_date(doc, 0, 0))")
println("hidden=$(annotation_is_hidden(doc, 0, 0)) printable=$(annotation_is_printable(doc, 0, 0)) readOnly=$(annotation_is_read_only(doc, 0, 0))")
uri = link_annotation_uri(doc, 0, 0)
isempty(uri) || println("link URI: $uri")
icon = text_annotation_icon_name(doc, 0, 0)
isempty(icon) || println("icon: $icon")
Zig
const pdf_oxide = @import("pdf_oxide");
const a = std.heap.page_allocator;
var doc = try pdf_oxide.Document.open("annotated.pdf");
defer doc.deinit();
var list = try doc.annotationList(0);
defer list.deinit();
std.debug.print("color={d} created={d}\n", .{ try list.getColor(0), try list.getCreationDate(0) });
std.debug.print("hidden={} printable={} readOnly={}\n", .{ try list.isHidden(0), try list.isPrintable(0), try list.isReadOnly(0) });
const uri = try list.linkUri(a, 0);
defer a.free(uri);
if (uri.len != 0) std.debug.print("link URI: {s}\n", .{uri});
const icon = try list.textIconName(a, 0);
defer a.free(icon);
if (icon.len != 0) std.debug.print("icon: {s}\n", .{icon});
Objective-C
#import "POXPdfOxide.h"
NSError *err = nil;
POXDocument *doc = [POXDocument openPath:@"annotated.pdf" error:&err];
POXAnnotation *a = [doc pageAnnotations:0 error:&err].firstObject;
NSLog(@"color=%u created=%lld modified=%lld", a.color, a.creationDate, a.modificationDate);
NSLog(@"hidden=%d printable=%d readOnly=%d", a.hidden, a.printable, a.readOnly);
if (a.linkUri.length) NSLog(@"link URI: %@", a.linkUri);
if (a.iconName.length) NSLog(@"icon: %@", a.iconName);
Elixir
{:ok, doc} = PdfOxide.open("annotated.pdf")
{:ok, color} = PdfOxide.annotation_color(doc, 0, 0)
{:ok, created} = PdfOxide.annotation_creation_date(doc, 0, 0)
IO.puts("color=#{color} created=#{created}")
{:ok, hidden} = PdfOxide.annotation_hidden?(doc, 0, 0)
{:ok, printable} = PdfOxide.annotation_printable?(doc, 0, 0)
{:ok, read_only} = PdfOxide.annotation_read_only?(doc, 0, 0)
IO.puts("hidden=#{hidden} printable=#{printable} readOnly=#{read_only}")
{:ok, uri} = PdfOxide.link_annotation_uri(doc, 0, 0)
if uri != "", do: IO.puts("link URI: #{uri}")
{:ok, icon} = PdfOxide.text_annotation_icon_name(doc, 0, 0)
if icon != "", do: IO.puts("icon: #{icon}")
AnnotationExtras fields (Swift)
| Field | Type | Description |
|---|---|---|
color |
UInt32 |
Packed annotation color |
creationDate |
Int64 |
Creation timestamp |
modificationDate |
Int64 |
Modification timestamp |
hidden |
Bool |
Hidden flag |
markedDeleted |
Bool |
Marked-deleted flag |
printable |
Bool |
Print flag |
readOnly |
Bool |
Read-only flag |
uri |
String |
Link annotation URI (empty if none) |
iconName |
String |
Text annotation icon name (empty if none) |
quadPoints |
[QuadPoint] |
Highlight/markup quadrilaterals (4 corners each) |
Binding coverage.
annotation_extrasis exposed as a dedicatedAnnotationExtrasstruct in Swift (doc.annotationExtras(page, index:)) and via thepdf_oxide_annotation_get_*C ABI accessor family. The same per-index accessor family is wrapped in C++ (doc.annotation_get_*), R (pdf_annotation_get_*), Julia (annotation_*), Zig (AnnotationList.getColor/isHidden/...), and Elixir (PdfOxide.annotation_color/...). In Go, Dart (doc.pageAnnotationDetails(page)), and Objective-C (inline onPOXAnnotation), the same attributes are materialized inline on each annotation. The accessors are compiled out of the WASM target.
Advanced Examples
Build a table of contents from bookmarks
use pdf_oxide::PdfDocument;
use pdf_oxide::outline::Destination;
let mut doc = PdfDocument::open("book.pdf")?;
fn print_toc(items: &[pdf_oxide::outline::OutlineItem], depth: usize) {
for item in items {
let indent = " ".repeat(depth);
let page = match &item.dest {
Some(Destination::PageIndex(p)) => format!("page {}", p + 1),
Some(Destination::Named(n)) => format!("dest '{}'", n),
None => "no dest".to_string(),
};
println!("{}{} ({})", indent, item.title, page);
print_toc(&item.children, depth + 1);
}
}
if let Some(outline) = doc.get_outline()? {
println!("Table of Contents:");
print_toc(&outline, 0);
}
Extract all comments (Text annotations)
use pdf_oxide::PdfDocument;
use pdf_oxide::annotation_types::AnnotationSubtype;
let mut doc = PdfDocument::open("reviewed.pdf")?;
let page_count = doc.page_count()?;
for page_idx in 0..page_count {
let annotations = doc.get_annotations(page_idx)?;
let comments: Vec<_> = annotations.iter()
.filter(|a| a.subtype_enum == AnnotationSubtype::Text)
.collect();
if !comments.is_empty() {
println!("Page {}:", page_idx + 1);
for c in &comments {
let author = c.author.as_deref().unwrap_or("Unknown");
let text = c.contents.as_deref().unwrap_or("");
println!(" [{}] {}", author, text);
}
}
}
Extract all hyperlinks
use pdf_oxide::PdfDocument;
use pdf_oxide::annotation_types::AnnotationSubtype;
let mut doc = PdfDocument::open("report.pdf")?;
let annotations = doc.get_annotations(0)?;
let links: Vec<_> = annotations.iter()
.filter(|a| a.subtype_enum == AnnotationSubtype::Link)
.collect();
for link in &links {
if let Some(ref action) = link.action {
println!("Link: {:?}", action);
}
if let Some(ref dest) = link.destination {
println!("Internal link: {:?}", dest);
}
}
FAQ
What is the difference between get_annotations and annotation_extras?
get_annotations returns the core annotation view (subtype, contents, rect, author, dates, color, flags). annotation_extras adds the extended attributes — packed color, timestamps, the four visibility flags, a link URI, a text-annotation icon name, and highlight quad points. In Go these are merged into one Annotation; in Swift they are a separate AnnotationExtras struct.
What JSON schema does annotations_to_json produce?
A JSON array matching the Go Annotation struct: type, subtype, content, x, y, width, height, author, borderWidth, color, creationDate, modificationDate, linkURI, textIconName, isHidden, isPrintable, isReadOnly, isMarkedDeleted.
Why are link URIs and icon names sometimes empty?
Those fields only apply to specific subtypes — uri to Link annotations and iconName to Text (sticky-note) annotations. For other subtypes they come back as empty strings.
Is annotation extraction fast? Yes. PDF Oxide’s extraction core runs at roughly 0.8 ms mean / 9 ms p99 with a 100% pass rate on the benchmark corpus.
Related Pages
- Form Data Extraction – Extract form fields (Widget annotations)
- Text Extraction – Extract text content from pages
- Metadata & XMP – Read document properties and bookmarks
- Image Extraction – Embedded images and page-elements accessor