GitHub - Lulzx/zpdf: Zero-copy PDF text extraction library written in Zig. High-performance, memory-mapped parsing with SIMD acceleration.

zig build              # Build library and CLI
zig build test         # Run tests

const std = @import("std");
const zpdf = @import("zpdf");

pub fn main() !void {
    var gpa = std.heap.GeneralPurposeAllocator(.{}){};
    defer _ = gpa.deinit();
    const allocator = gpa.allocator();

    const doc = try zpdf.Document.open(allocator, "file.pdf");
    defer doc.close();

    var buf: [4096]u8 = undefined;
    var bw = std.fs.File.stdout().writer(&buf);
    const writer = &bw.interface;
    defer writer.flush() catch {};

    for (0..doc.pageCount()) |page_num| {
        try doc.extractText(page_num, writer);
    }
}

zpdf extract document.pdf              # Extract all pages (uses structure tree for reading order)
zpdf extract -p 1-10 document.pdf      # Extract pages 1-10
zpdf extract -o out.txt document.pdf   # Output to file
zpdf info document.pdf                 # Show document info
zpdf bench document.pdf                # Run benchmark

import zpdf

with zpdf.Document("file.pdf") as doc:
    print(doc.page_count)

    # Single page
    text = doc.extract_page(0)

    # All pages (accuracy mode is default)
    all_text = doc.extract_all()

    # Fast mode (higher throughput, stream-order extraction)
    fast_text = doc.extract_all(mode="fast")

    # Page info
    info = doc.get_page_info(0)
    print(f"{info.width}x{info.height}")

# Zero-copy memory open (unsafe semantics for other language bindings)
with zpdf.Document.open_memory_unsafe(open("file.pdf", "rb").read()) as doc:
    print(doc.page_count)

zig build -Doptimize=ReleaseFast
PYTHONPATH=python python3 examples/basic.py

src/
├── root.zig         # Document API and core types
├── main.zig         # CLI entry point
├── capi.zig         # C ABI exports for FFI
├── wapi.zig         # WASM API exports
├── parser.zig       # PDF object parser
├── xref.zig         # XRef table/stream parsing
├── pagetree.zig     # Page tree resolution
├── decompress.zig   # Stream decompression filters
├── encoding.zig     # Font encoding and CMap parsing
├── agl.zig          # Adobe Glyph List mappings
├── cff.zig          # CFF/Type1 font parsing
├── interpreter.zig  # Content stream interpreter
├── structtree.zig   # Structure tree parser (PDF/UA)
├── layout.zig       # Text layout and bounding boxes
├── markdown.zig     # Markdown export
└── simd.zig         # SIMD-accelerated parsing

python/zpdf/         # Python bindings (cffi)
examples/            # Usage examples