hjess/fil
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Nomad changes
All checks were successful
Deploy fil (kreuzberg) / deploy (push) Successful in 49s
Details

Browse Source
This commit is contained in:
Henrik Jess Nielsen
2026-06-01 23:40:55 +02:00
parent 72b1a0a6ed
commit b4c07d3693
5723 changed files with 1130655 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

30
docs/snippets/zig/ocr/cloud_ocr_backend.md Normal file
View File

@@ -0,0 +1,30 @@
```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();
// Cloud OCR backends are registered as custom plugins via the Rust core.
// From Zig, select a registered cloud backend by name through OcrConfig.
const config_json =
\\{
\\ "ocr": {
\\ "backend": "cloud-ocr",
\\ "language": "eng"
\\ }
\\}
;
const result_json = try kreuzberg.extract_file_sync("scanned.pdf", null, config_json);
defer std.heap.c_allocator.free(result_json);
const owned = try allocator.dupe(u8, result_json);
defer allocator.free(owned);
const stdout = std.io.getStdOut().writer();
try stdout.print("{s}\n", .{owned});
}
```

27
docs/snippets/zig/ocr/image_extraction.md Normal file
View File

@@ -0,0 +1,27 @@
```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 =
\\{
\\ "images": {
\\ "extract_images": true
\\ }
\\}
;
const result_json = try kreuzberg.extract_file_sync("document.pdf", null, config_json);
defer std.heap.c_allocator.free(result_json);
const owned = try allocator.dupe(u8, result_json);
defer allocator.free(owned);
const stdout = std.io.getStdOut().writer();
try stdout.print("{s}\n", .{owned});
}
```

32
docs/snippets/zig/ocr/image_preprocessing.md Normal file
View File

@@ -0,0 +1,32 @@
```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 =
\\{
\\ "images": {
\\ "extract_images": true,
\\ "target_dpi": 300,
\\ "max_image_dimension": 4096,
\\ "auto_adjust_dpi": true,
\\ "min_dpi": 150,
\\ "max_dpi": 600
\\ }
\\}
;
const result_json = try kreuzberg.extract_file_sync("document.pdf", null, config_json);
defer std.heap.c_allocator.free(result_json);
const owned = try allocator.dupe(u8, result_json);
defer allocator.free(owned);
const stdout = std.io.getStdOut().writer();
try stdout.print("{s}\n", .{owned});
}
```

28
docs/snippets/zig/ocr/ocr_easyocr.md Normal file
View File

@@ -0,0 +1,28 @@
```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 =
\\{
\\ "ocr": {
\\ "backend": "easyocr",
\\ "language": "en"
\\ }
\\}
;
const result_json = try kreuzberg.extract_file_sync("document.pdf", null, config_json);
defer std.heap.c_allocator.free(result_json);
const owned = try allocator.dupe(u8, result_json);
defer allocator.free(owned);
const stdout = std.io.getStdOut().writer();
try stdout.print("{s}\n", .{owned});
}
```

49
docs/snippets/zig/ocr/ocr_elements.md Normal file
View File

@@ -0,0 +1,49 @@
```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 =
\\{
\\ "ocr": {
\\ "backend": "paddleocr",
\\ "language": "en",
\\ "element_config": {
\\ "include_elements": true
\\ }
\\ }
\\}
;
const result_json = try kreuzberg.extract_file_sync("scanned.pdf", null, config_json);
defer std.heap.c_allocator.free(result_json);
const owned = try allocator.dupe(u8, result_json);
defer allocator.free(owned);
var parsed = try std.json.parseFromSlice(std.json.Value, allocator, owned, .{});
defer parsed.deinit();
const stdout = std.io.getStdOut().writer();
const root = parsed.value;
if (root != .object) return;
if (root.object.get("ocr_elements")) |elements_val| {
if (elements_val == .array) {
for (elements_val.array.items) |element| {
if (element != .object) continue;
if (element.object.get("text")) |text_val| {
if (text_val == .string) {
try stdout.print("Text: {s}\n", .{text_val.string});
}
}
}
}
}
}
```

28
docs/snippets/zig/ocr/ocr_extraction.md Normal file
View File

@@ -0,0 +1,28 @@
```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 =
\\{
\\ "ocr": {
\\ "backend": "tesseract",
\\ "language": "eng"
\\ }
\\}
;
const result_json = try kreuzberg.extract_file_sync("scanned.pdf", null, config_json);
defer std.heap.c_allocator.free(result_json);
const owned = try allocator.dupe(u8, result_json);
defer allocator.free(owned);
const stdout = std.io.getStdOut().writer();
try stdout.print("{s}\n", .{owned});
}
```

29
docs/snippets/zig/ocr/ocr_force_all_pages.md Normal file
View File

@@ -0,0 +1,29 @@
```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 =
\\{
\\ "force_ocr": true,
\\ "ocr": {
\\ "backend": "tesseract",
\\ "language": "eng"
\\ }
\\}
;
const result_json = try kreuzberg.extract_file_sync("document.pdf", null, config_json);
defer std.heap.c_allocator.free(result_json);
const owned = try allocator.dupe(u8, result_json);
defer allocator.free(owned);
const stdout = std.io.getStdOut().writer();
try stdout.print("{s}\n", .{owned});
}
```

28
docs/snippets/zig/ocr/ocr_multi_language.md Normal file
View File

@@ -0,0 +1,28 @@
```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 =
\\{
\\ "ocr": {
\\ "backend": "tesseract",
\\ "language": "eng+deu+fra"
\\ }
\\}
;
const result_json = try kreuzberg.extract_file_sync("multilingual.pdf", null, config_json);
defer std.heap.c_allocator.free(result_json);
const owned = try allocator.dupe(u8, result_json);
defer allocator.free(owned);
const stdout = std.io.getStdOut().writer();
try stdout.print("{s}\n", .{owned});
}
```

28
docs/snippets/zig/ocr/ocr_paddleocr.md Normal file
View File

@@ -0,0 +1,28 @@
```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 =
\\{
\\ "ocr": {
\\ "backend": "paddleocr",
\\ "language": "en"
\\ }
\\}
;
const result_json = try kreuzberg.extract_file_sync("document.pdf", null, config_json);
defer std.heap.c_allocator.free(result_json);
const owned = try allocator.dupe(u8, result_json);
defer allocator.free(owned);
const stdout = std.io.getStdOut().writer();
try stdout.print("{s}\n", .{owned});
}
```