rizin/test/unit/test_base85.c
Ahmed Mohamed Ibrahim 38a530dbe3
librz/util: base64, base85, base36, base32, base16 support and refactor (#5216) (#5271)
* Rename librz/util/ubase64.c into librz/util/base64.c for consistency #5216

* Add Doxygen documentation to function in librz/util/base85.c #5216

* Add unit-tests for librz/util/base85.c #5216

* Refactor base85 API and internal functions #5216

base85 was using a FILE as an input and it used to print its result to
STDOUT, which was very bad for having unit-testing or to use it to
extend rz-hash functionality, since the solution I really had was
through using pipes which isn't ideal as much as the refactoring one.

* Extend rz-hash with base85 #5126

* Fix formatting #5216

* Extract base36 decoding function from subprojects/rzwinkd/iob_net.c to librz/util/base36.c #5216

- Also, added Doxygen docs to rz_base36_decode function

* Added rz_base36_encode_dyn #5216

- this function encode a u64 value to it's char[13+1] base36 counterpart
- later, it will be helpful in expanding the funcitionality of rz-hash
- added its Doxygen docs

* Expand rz-hash with base36 encoding/decoding #5216

* Refactor rz_base36_decode to return a suitable error code like -1 #5216

- that should help testing it later for valid and invalid decodings
- keeping the original behaviour as it was in
subprojects/rzwinkd/iob_net.c

* Add unit-tests for base36 encoding & decoding functions #5216

* Fix formatting #5216

* Fix base36.h header file guards #5216

* Add base32 encoding & decoding #5216

added their Doxygen Docs as well

* Add base32 encoding and decoding unti-tests #5216

* Expand rz-hash with base32 encoding/decoding functionality #5216

* Fix formatting #5216

* Fix add base32 to codec_name_bytes #5216

* Fix base32 docs #5216

* Add base16 encoding/decoding functions #5216

- added their Doxygen docs as well.

* Add base16 unit-tests #5216

* Fix test_base85 conversions warnings #5216

* Expand rz-hash with base16 encoding/decoding functionality #5216

* Fix formatting #5216

* Fix doxygen docs #5216

* Restore subprojects/rizin-shell-parser/parser.c to match origin/dev

* Fix the order by baseXX

* Fix base16 - invert the logic in calculate_src_length

* Fix base16 - intialize variables in rz_base16_encode

* Fix base16 - null terminate the output buffer of rz_base16_encode_dyn

* Fix base16 - get rid of unnecessary else in rz_base16_decode

* Fix base16 - use `len & 1` instead of `(len % 2) != 0`

* Fix base32 - invert the logic in calculate_src_length

* Fix base32 - compress two return statments by using `rz_return_val_if_fail(src && dest, 0);`

* Fix base32 - null terminate the output of rz_base32_encode

* Fix base32 - get rid of unnecessary else in rz_base32_decode

add more parentheses to split addition from mult for better clarity

* Fix base32 - intialize variables in rz_base32_encode_dyn

* Fix base36 - intialize `tmp` variable in rz_base36_encode_dyn

* Fix base36 - use RZ_LOG_ERROR instead of eprintf

* Fix base36 - use RZ_NULLABLE for the API interface

* Fix base85 - use RZ_OUT & RZ_NULLABLE for the API interface

* Fix base85 - use RZ_LOG_ERROR instead of eprintf

* Fix base85 - use size_t instead of int for decode_tuple_buf

* Fix base85 - remove unused varaible, `out_len`, in rz_base85_encode_dyn

* Fix base85 - correct decode buffer size calculation

The previous rz_base85_dec_buflen() underestimated the worst‑case output
size (3 bytes per 4 input chars), causing overflows when using ‘z’/’y’
abbreviations. Update it to allocate 4 bytes per input character plus
one for the NUL terminator, eliminating heap-buffer-overflow errors.

* Fix formatting

* Fix base85-test - use `newlines` variable to make sure line breaks were inserted as expected

* Fix base85-test - remove unnecessary includes

* Fix rz-hash test - updated rz-hash -L expected result

* Fix crypto_base36 - use RZ_LOG_ERROR instead of eprintf

* Fix base16 - compress rz_return_val_if_fail statements and move before locals

* Update base16 - use hex.c existing encoding/decoding logic

- base16.c encoding/decoding functions are now wrappers for hex.c
  `rz_hex_bin2str` and `rz_hex_str2bin` functions
- updated related base16 unit testing and documentation
- updated the integraion with rz-hash binary (or crypto_base16)

* Fix formatting

* Add documentation to rz_hex_bin2str

* Fix base85 - add missing `reutrn` docs to rz_base85_encode function

* Fix base85 - use RZ_NONNULL for dest and src function instead of RZ_NULLABLE

* Fix base36 - use RZ_NONNULL for dest and src function instead of RZ_NULLABLE

* Fix base16 - use RZ_NONNULL for dest and src function instead of RZ_NULLABLE

* Fix base32 - use RZ_NONNULL for dest and src function instead of RZ_NULLABLE

* Fix base16 - add missig checks for invalid inputs in rz_base16_encode & rz_base16_encode_dyn

* Fix base32 - add missing checks for bad encoding

* Fix - add missing SPDX

* Fix Formatting

* Add rz_base36_encode & rz_base36_decode_dyn functions to base36 API
2025-08-17 15:26:25 +08:00

119 lines
3.5 KiB
C
Raw Permalink Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

// SPDX-FileCopyrightText: 2025 Ahmed Ibrahim <a.ibrahim8686@gmail.com>
// SPDX-License-Identifier: LGPL-3.0-only
#include <rz_util.h>
#include "minunit.h"
bool test_rz_base85_encode_dyn_nodelims(void) {
const char *src = "hello, ascii85";
char *dest = rz_base85_encode_dyn(src, strlen(src), 0, 0, 1);
mu_assert_streq(dest, "BOu!rD_*#>F(8ou3&L", "ascii85 encode mismatch");
free(dest);
mu_end;
}
bool test_rz_base85_encode_dyn_delims(void) {
const char *src = "hello, ascii85";
char *dest = rz_base85_encode_dyn(src, strlen(src), 1, 0, 1);
mu_assert_streq(dest, "<~BOu!rD_*#>F(8ou3&L~>", "ascii85 encode mismatch");
free(dest);
mu_end;
}
bool test_rz_base85_decode_dyn_nodelims(void) {
const char *src = "BOu!rD_*#>F(8ou3&L";
char *dest = rz_base85_decode_dyn(src, strlen(src), 0, 0, NULL);
mu_assert_streq(dest, "hello, ascii85", "decoder output mismatch");
free(dest);
mu_end;
}
bool test_rz_base85_decode_dyn_delims(void) {
const char *src = "<~BOu!rD_*#>F(8ou3&L~>";
char *dest = rz_base85_decode_dyn(src, strlen(src), 1, 0, NULL);
mu_assert_streq(dest, "hello, ascii85", "ascii85 decode with delimiters mismatch");
free(dest);
mu_end;
}
bool test_rz_base85_encode_decode_wrap10(void) {
char src[51];
memset(src, 'A', 50);
src[50] = '\0';
char *encoded = rz_base85_encode_dyn(src, strlen(src), 0, 10, 0);
int col = 0, newlines = 0;
for (size_t i = 0; encoded[i]; i++) {
if (encoded[i] == '\n') {
mu_assert_eq(col, 10, "line length before \\n not 10");
col = 0;
newlines++;
} else {
col++;
}
}
mu_assert_true(col <= 10, "final line exceeds wrap length");
mu_assert_true(newlines > 0, "no line breaks were inserted");
size_t decoded_len;
char *decoded = rz_base85_decode_dyn(encoded, strlen(encoded), 0, 0, &decoded_len);
mu_assert_eq(decoded_len, 50U, "decoded length mismatch");
mu_assert_true(memcmp(decoded, src, 50) == 0, "decoded data mismatch");
free(encoded);
free(decoded);
mu_end;
}
bool test_rz_base85_encode_decode_z_abbrev(void) {
const ut8 zeros[4] = { 0, 0, 0, 0 };
char *enc = rz_base85_encode_dyn((const char *)zeros, 4, 0, 0, 0);
mu_assert_notnull(enc, "rz_base85_encode_dyn returned NULL");
mu_assert_streq(enc, "z", "encode zeros should be 'z'");
size_t decoded_len;
char *decoded = rz_base85_decode_dyn("zz", -1, 0, 0, &decoded_len);
mu_assert_notnull(decoded, "rz_base85_decode_dyn returned NULL");
mu_assert_eq(decoded_len, 8U, "decoded length != 8");
for (size_t i = 0; i < decoded_len; i++) {
mu_assert_eq(decoded[i], '\0', "decoded byte nonzero");
}
free(enc);
free(decoded);
mu_end;
}
bool test_rz_base85_decode_invalid_strict_vs_lenient(void) {
const char bad[] = "FCfN8v";
size_t decoded_len;
char *strict_out = rz_base85_decode_dyn(bad, -1, 0, 0, &decoded_len);
mu_assert_true(strict_out == NULL, "decoder accepted garbage in strict mode");
char *lenient_out = rz_base85_decode_dyn(bad, -1, 0, 1, &decoded_len);
mu_assert_notnull(lenient_out, "lenient decode returned NULL");
mu_assert_eq(decoded_len, 4U, "decoded length != 4");
mu_assert_true(memcmp(lenient_out, "test", 4) == 0, "lenient decode produced wrong bytes");
free(lenient_out);
mu_end;
}
int all_tests(void) {
mu_run_test(test_rz_base85_encode_dyn_nodelims);
mu_run_test(test_rz_base85_decode_dyn_nodelims);
mu_run_test(test_rz_base85_encode_dyn_delims);
mu_run_test(test_rz_base85_decode_dyn_delims);
mu_run_test(test_rz_base85_encode_decode_wrap10);
mu_run_test(test_rz_base85_encode_decode_z_abbrev);
mu_run_test(test_rz_base85_decode_invalid_strict_vs_lenient);
return tests_passed != tests_run;
}
mu_main(all_tests)