pdftract/crates/pdftract-libpdftract/tests/test_hash_direct.c
jedarden 9b5fbc9b5e feat(pdftract-bf-2y2rp): implement lazy stream decoding for PDF extraction
- Add decode_page_content_streams() function for per-page lazy decode
- Update extract_page_from_dict() to support lazy stream decoding
- Modify extract_pdf() and extract_pdf_ndjson() to enable lazy decoding
- Fix borrow checker issue in LazyPageIter::next()

This ensures content streams are decoded lazily per page and dropped
immediately after processing, keeping peak RSS flat across page count.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-23 12:30:26 -04:00

33 lines
871 B
C

#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include "../include/pdftract.h"
int main(int argc, char *argv[]) {
const char *pdf_path = "../../../tests/fixtures/valid-minimal.pdf";
if (argc > 1) {
pdf_path = argv[1];
}
printf("Testing pdftract_hash with: %s\n", pdf_path);
char *result = pdftract_hash(pdf_path);
if (result == NULL) {
const char *err = pdftract_last_error();
printf("ERROR: pdftract_hash returned NULL\n");
printf("Last error: %s\n", err ? err : "(null)");
return 1;
}
printf("Result: %s\n", result);
if (strstr(result, "\"fingerprint\"") == NULL) {
printf("FAIL: result does not contain fingerprint field\n");
pdftract_free(result);
return 1;
}
printf("PASS: fingerprint found\n");
pdftract_free(result);
return 0;
}