Files
fil/docs/snippets/zig/metadata/page_tracking_basic.md
Henrik Jess Nielsen b4c07d3693
All checks were successful
Deploy fil (kreuzberg) / deploy (push) Successful in 49s
Nomad changes
2026-06-01 23:40:55 +02:00

60 lines
1.7 KiB
Markdown

```zig title="Zig"
const std = @import("std");
const kreuzberg = @import("kreuzberg");
pub fn main() !void {
var gpa = std.heap.GeneralPurposeAllocator(.{}){};
defer _ = gpa.deinit();
const allocator = gpa.allocator();
const config_json =
\\{
\\ "pages": {
\\ "extract_pages": true
\\ }
\\}
;
const result_json = try kreuzberg.extract_file_sync("document.pdf", null, config_json);
defer std.heap.c_allocator.free(result_json);
var parsed = try std.json.parseFromSlice(std.json.Value, allocator, result_json, .{});
defer parsed.deinit();
const root = parsed.value;
if (root != .object) return;
const stdout = std.io.getStdOut().writer();
const pages_val = root.object.get("pages") orelse return;
if (pages_val != .array) return;
for (pages_val.array.items) |page| {
if (page != .object) continue;
const page_number_val = page.object.get("page_number") orelse continue;
if (page_number_val != .integer) continue;
try stdout.print("Page {d}:\n", .{page_number_val.integer});
if (page.object.get("content")) |content_val| {
if (content_val == .string) {
try stdout.print(" Content: {d} chars\n", .{content_val.string.len});
}
}
if (page.object.get("tables")) |tables_val| {
if (tables_val == .array) {
try stdout.print(" Tables: {d}\n", .{tables_val.array.items.len});
}
}
if (page.object.get("images")) |images_val| {
if (images_val == .array) {
try stdout.print(" Images: {d}\n", .{images_val.array.items.len});
}
}
}
}
```