This commit is contained in:
44
docs/snippets/c/config/tesseract_config.md
Normal file
44
docs/snippets/c/config/tesseract_config.md
Normal file
@@ -0,0 +1,44 @@
|
||||
```c title="C"
|
||||
#include "kreuzberg.h"
|
||||
#include <stdio.h>
|
||||
|
||||
int main(void) {
|
||||
const char *config_json =
|
||||
"{"
|
||||
"\"ocr\": {"
|
||||
"\"backend\": \"tesseract\","
|
||||
"\"language\": \"eng+deu\","
|
||||
"\"tesseract_config\": {"
|
||||
"\"psm\": 6,"
|
||||
"\"oem\": 3"
|
||||
"}"
|
||||
"}"
|
||||
"}";
|
||||
|
||||
KREUZBERGExtractionConfig *config = kreuzberg_extraction_config_from_json(config_json);
|
||||
if (!config) {
|
||||
fprintf(stderr, "config parse failed (code %d): %s\n",
|
||||
kreuzberg_last_error_code(),
|
||||
kreuzberg_last_error_context());
|
||||
return 1;
|
||||
}
|
||||
|
||||
KREUZBERGExtractionResult *result =
|
||||
kreuzberg_extract_file_sync("scanned.pdf", NULL, config);
|
||||
if (!result) {
|
||||
fprintf(stderr, "extraction failed (code %d): %s\n",
|
||||
kreuzberg_last_error_code(),
|
||||
kreuzberg_last_error_context());
|
||||
kreuzberg_extraction_config_free(config);
|
||||
return 1;
|
||||
}
|
||||
|
||||
char *content = kreuzberg_extraction_result_content(result);
|
||||
printf("%s\n", content ? content : "(empty)");
|
||||
kreuzberg_free_string(content);
|
||||
|
||||
kreuzberg_extraction_result_free(result);
|
||||
kreuzberg_extraction_config_free(config);
|
||||
return 0;
|
||||
}
|
||||
```
|
||||
Reference in New Issue
Block a user