1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622
|
# python -m pytest sarif_test.py
import os
import json
import tempfile
import pytest
from testutils import cppcheck
__script_dir = os.path.dirname(os.path.abspath(__file__))
# Test code with various error types
TEST_CODE = """
#include <cstdio>
#include <cstdlib>
#include <cstring>
#include <iostream>
#include <vector>
#include <memory>
class TestClass {
public:
TestClass() : value(0) {}
~TestClass() { delete ptr; }
void setValue(int v) { value = v; }
int getValue() const { return value; }
private:
int value;
int* ptr = nullptr;
};
void testSecurityViolations() {
// Null pointer dereference
int* ptr = nullptr;
*ptr = 5;
// Array bounds violation
int array[5];
array[10] = 1;
// Memory leak
int* mem = (int*)malloc(sizeof(int) * 10);
// forgot to free mem
// Uninitialized variable
int x;
printf("%d", x);
// Double free
int* p = (int*)malloc(sizeof(int));
free(p);
free(p);
// Buffer overflow with strcpy
char buffer[10];
char source[20] = "This is too long";
strcpy(buffer, source);
// Use after free
int* freed = (int*)malloc(sizeof(int));
free(freed);
*freed = 42;
}
void testStyleAndPortabilityIssues() {
// Redundant assignment
int redundant = 5;
redundant = redundant;
// Unused variable
int unused = 42;
// Variable scope reduction
int i;
for (i = 0; i < 10; i++) {
// i could be declared in for loop
}
}
int main() {
testSecurityViolations();
testStyleAndPortabilityIssues();
return 0;
}
"""
BASIC_TEST_CODE = """
int main() {
int* p = nullptr;
*p = 5; // null pointer dereference
return 0;
}
"""
def create_test_file(tmp_path, filename="test.cpp", content=TEST_CODE):
"""Create a temporary test file with the given content."""
filepath = tmp_path / filename
filepath.write_text(content)
return str(filepath)
def run_sarif_check(code, extra_args=None):
"""Run cppcheck with SARIF output on the given code."""
with tempfile.TemporaryDirectory() as tmpdir:
tmp_path = os.path.join(tmpdir, "test.cpp")
with open(tmp_path, "w") as f:
f.write(code)
args = ["--output-format=sarif", "--enable=all", tmp_path]
if extra_args:
args.extend(extra_args)
_, _, stderr = cppcheck(args)
# SARIF output is in stderr
try:
sarif_data = json.loads(stderr)
return sarif_data
except json.JSONDecodeError as e:
pytest.fail(f"Failed to parse SARIF JSON: {e}\nOutput: {stderr}")
return None
def test_sarif_basic_structure():
"""Test that SARIF output has the correct basic structure."""
sarif = run_sarif_check(BASIC_TEST_CODE)
# Check required SARIF fields
assert sarif["version"] == "2.1.0"
assert "$schema" in sarif
assert "sarif-schema" in sarif["$schema"]
assert "runs" in sarif
assert len(sarif["runs"]) == 1
run = sarif["runs"][0]
assert "tool" in run
assert "results" in run
tool = run["tool"]
assert "driver" in tool
driver = tool["driver"]
assert driver["name"] == "Cppcheck"
assert "rules" in driver
assert "semanticVersion" in driver
def test_sarif_null_pointer():
"""Test SARIF output for null pointer dereference."""
sarif = run_sarif_check(BASIC_TEST_CODE)
run = sarif["runs"][0]
results = run["results"]
# Should have at least one result
assert len(results) > 0
# Find null pointer result
null_pointer_results = [r for r in results if r["ruleId"] == "nullPointer"]
assert len(null_pointer_results) > 0
result = null_pointer_results[0]
assert result["level"] == "error"
assert "message" in result
assert "text" in result["message"]
assert (
"null" in result["message"]["text"].lower()
or "nullptr" in result["message"]["text"].lower()
)
# Check location information
assert "locations" in result
assert len(result["locations"]) > 0
location = result["locations"][0]
assert "physicalLocation" in location
assert "artifactLocation" in location["physicalLocation"]
assert "region" in location["physicalLocation"]
region = location["physicalLocation"]["region"]
assert "startLine" in region
assert region["startLine"] > 0
assert "startColumn" in region
assert region["startColumn"] > 0
def test_sarif_security_rules():
"""Test that security-related rules have proper security properties."""
sarif = run_sarif_check(TEST_CODE)
run = sarif["runs"][0]
driver = run["tool"]["driver"]
rules = driver["rules"]
# Check for security-related rules
security_rule_ids = [
"nullPointer",
"arrayIndexOutOfBounds",
"memleak",
"uninitvar",
"doubleFree",
]
for rule_id in security_rule_ids:
matching_rules = [r for r in rules if r["id"] == rule_id]
if matching_rules:
rule = matching_rules[0]
props = rule.get("properties", {})
# Security rules should have security-severity
if "tags" in props and "security" in props["tags"]:
assert "security-severity" in props
assert float(props["security-severity"]) > 0
# Should have problem.severity
assert "problem.severity" in props
# Should have precision
assert "precision" in props
def test_sarif_rule_descriptions():
"""Test that rule descriptions are properly formatted."""
sarif = run_sarif_check(TEST_CODE)
run = sarif["runs"][0]
driver = run["tool"]["driver"]
rules = driver["rules"]
assert len(rules) > 0
for rule in rules:
# Each rule should have required fields
assert "id" in rule
assert "name" in rule
assert "shortDescription" in rule
assert "fullDescription" in rule
# Descriptions should be empty (allowing GitHub to use instance messages)
assert rule["name"] == ""
assert rule["shortDescription"]["text"] == ""
assert rule["fullDescription"]["text"] == ""
# Should have properties
assert "properties" in rule
def test_sarif_cwe_tags():
"""Test that CWE tags are properly formatted."""
sarif = run_sarif_check(TEST_CODE)
run = sarif["runs"][0]
driver = run["tool"]["driver"]
rules = driver["rules"]
# Find rules with CWE tags
rules_with_cwe = []
for rule in rules:
props = rule.get("properties", {})
tags = props.get("tags", [])
cwe_tags = [t for t in tags if t.startswith("external/cwe/cwe-")]
if cwe_tags:
rules_with_cwe.append((rule["id"], cwe_tags))
# Should have at least some rules with CWE tags
assert len(rules_with_cwe) > 0
# Validate CWE tag format
for _, cwe_tags in rules_with_cwe:
for tag in cwe_tags:
assert tag.startswith("external/cwe/cwe-")
cwe_num = tag[17:] # After 'external/cwe/cwe-'
assert cwe_num.isdigit()
assert int(cwe_num) > 0
def test_sarif_severity_levels():
"""Test that different severity levels are properly mapped."""
sarif = run_sarif_check(TEST_CODE)
run = sarif["runs"][0]
results = run["results"]
# Collect severity levels
levels = set()
for result in results:
levels.add(result["level"])
# Should have at least error level
assert "error" in levels
# Valid SARIF levels
valid_levels = {"error", "warning", "note", "none"}
for level in levels:
assert level in valid_levels
def test_sarif_instance_specific_messages():
"""Test that result messages contain instance-specific information."""
sarif = run_sarif_check(TEST_CODE)
run = sarif["runs"][0]
results = run["results"]
# Check that messages are instance-specific
found_specific_messages = False
for result in results:
message_text = result["message"]["text"]
rule_id = result["ruleId"]
# Skip system include warnings
if rule_id == "missingIncludeSystem":
continue
# Messages should not be empty
assert len(message_text) > 0
# Check for specific variable names or values from our test code
if rule_id == "nullPointer" and "ptr" in message_text:
found_specific_messages = True
elif rule_id == "arrayIndexOutOfBounds" and (
"array" in message_text or "10" in message_text
):
found_specific_messages = True
elif rule_id == "uninitvar" and "x" in message_text:
found_specific_messages = True
elif rule_id == "memleak" and "mem" in message_text:
found_specific_messages = True
elif rule_id == "doubleFree" and "p" in message_text:
found_specific_messages = True
assert (
found_specific_messages
), "Should find at least some instance-specific messages"
def test_sarif_location_info():
"""Test that location information is correct."""
sarif = run_sarif_check(BASIC_TEST_CODE)
run = sarif["runs"][0]
results = run["results"]
for result in results:
assert "locations" in result
locations = result["locations"]
assert len(locations) > 0
for location in locations:
assert "physicalLocation" in location
phys_loc = location["physicalLocation"]
assert "artifactLocation" in phys_loc
assert "uri" in phys_loc["artifactLocation"]
assert "region" in phys_loc
region = phys_loc["region"]
# SARIF requires line and column numbers >= 1
assert "startLine" in region
assert region["startLine"] >= 1
assert "startColumn" in region
assert region["startColumn"] >= 1
def test_sarif_with_multiple_files(tmp_path):
"""Test SARIF output with multiple source files."""
# Create two test files
file1_content = """
void test1() {
int* p = nullptr;
*p = 1;
}
"""
file2_content = """
void test2() {
int arr[5];
arr[10] = 2;
}
"""
file1 = tmp_path / "file1.cpp"
file2 = tmp_path / "file2.cpp"
file1.write_text(file1_content)
file2.write_text(file2_content)
args = ["--output-format=sarif", "--enable=all", str(tmp_path)]
_, _, stderr = cppcheck(args)
sarif = json.loads(stderr)
run = sarif["runs"][0]
results = run["results"]
# Should have results from both files
files = set()
for result in results:
if "locations" in result:
for location in result["locations"]:
uri = location["physicalLocation"]["artifactLocation"]["uri"]
files.add(os.path.basename(uri))
assert "file1.cpp" in files or "file2.cpp" in files
def test_sarif_default_configuration():
"""Test that rules have default configuration with level."""
sarif = run_sarif_check(BASIC_TEST_CODE)
run = sarif["runs"][0]
driver = run["tool"]["driver"]
rules = driver["rules"]
for rule in rules:
# Check for defaultConfiguration.level (#13885)
assert "defaultConfiguration" in rule
assert "level" in rule["defaultConfiguration"]
level = rule["defaultConfiguration"]["level"]
assert level in ["error", "warning", "note", "none"]
def test_sarif_rule_properties():
"""Test that rules have required properties."""
sarif = run_sarif_check(TEST_CODE)
run = sarif["runs"][0]
driver = run["tool"]["driver"]
rules = driver["rules"]
for rule in rules:
assert "properties" in rule
props = rule["properties"]
# Required properties
assert "precision" in props
assert props["precision"] in ["very-high", "high", "medium", "low"]
assert "problem.severity" in props
assert props["problem.severity"] in [
"error",
"warning",
"style",
"performance",
"portability",
"information",
"note",
]
def test_sarif_rule_coverage():
"""Test that a variety of rules are triggered by comprehensive test code."""
sarif = run_sarif_check(TEST_CODE)
run = sarif["runs"][0]
driver = run["tool"]["driver"]
rules = driver["rules"]
# Collect all rule IDs
rule_ids = set(rule["id"] for rule in rules)
# Should have at least 5 different rules triggered
assert (
len(rule_ids) >= 5
), f"Expected at least 5 rules, found {len(rule_ids)}: {rule_ids}"
# Check for some specific expected rules from different categories
expected_rules = [
"nullPointer", # Security
"arrayIndexOutOfBounds", # Security
"memleak", # Security
"uninitvar", # Security
"unusedVariable", # Style
"redundantAssignment", # Style
"unusedFunction", # Style (if enabled)
"constParameter", # Style/Performance
"cstyleCast", # Style
"variableScope", # Style
]
found_expected_rules = sum(1 for rule in expected_rules if rule in rule_ids)
# Should find at least 3 of our expected rules
assert (
found_expected_rules >= 3
), f"Expected at least 3 known rules, found {found_expected_rules}"
def test_sarif_generic_descriptions():
"""Test that ALL rule descriptions are empty for GitHub integration."""
sarif = run_sarif_check(TEST_CODE)
run = sarif["runs"][0]
driver = run["tool"]["driver"]
rules = driver["rules"]
assert len(rules) > 0, "Should have at least one rule"
# Verify that ALL rule descriptions are empty so GitHub uses instance-specific messages
for rule in rules:
rule_id = rule["id"]
# All rules must have these fields
assert "name" in rule, f"Rule {rule_id} missing 'name'"
assert "shortDescription" in rule, f"Rule {rule_id} missing 'shortDescription'"
assert "fullDescription" in rule, f"Rule {rule_id} missing 'fullDescription'"
# The key test: ALL descriptions should be empty
assert (
rule["name"] == ""
), f"Rule {rule_id} name should be empty, got: {rule['name']}"
assert (
rule["shortDescription"]["text"] == ""
), f"Rule {rule_id} shortDescription should be empty, got: {rule['shortDescription']['text']}"
assert (
rule["fullDescription"]["text"] == ""
), f"Rule {rule_id} fullDescription should be empty, got: {rule['fullDescription']['text']}"
def test_sarif_security_rules_classification():
"""Test that security classification is correctly based on CWE IDs."""
sarif = run_sarif_check(TEST_CODE)
run = sarif["runs"][0]
driver = run["tool"]["driver"]
rules = driver["rules"]
found_rule_with_cwe = False
found_rule_without_cwe = False
for rule in rules:
rule_id = rule["id"]
props = rule.get("properties", {})
tags = props.get("tags", [])
# Check if rule has CWE tag
cwe_tags = [t for t in tags if t.startswith("external/cwe/")]
has_cwe = len(cwe_tags) > 0
if has_cwe:
found_rule_with_cwe = True
# Rules with CWE should have security-severity and security tag
assert (
"security-severity" in props
), f"Rule {rule_id} with CWE should have security-severity"
assert (
float(props["security-severity"]) > 0
), f"Rule {rule_id} security-severity should be positive"
# Check for security tag
assert (
"security" in tags
), f"Rule {rule_id} with CWE should have 'security' tag"
else:
found_rule_without_cwe = True
# Rules without CWE should NOT have security-severity or security tag
assert (
"security-severity" not in props
), f"Rule {rule_id} without CWE should not have security-severity"
assert (
"security" not in tags
), f"Rule {rule_id} without CWE should not have 'security' tag"
# All rules should still have basic properties
assert "precision" in props, f"Rule {rule_id} missing 'precision'"
assert "problem.severity" in props, f"Rule {rule_id} missing 'problem.severity'"
# Should find at least some rules in test data
assert (
found_rule_with_cwe or found_rule_without_cwe
), "Should find at least some rules with or without CWE"
def test_sarif_results_consistency():
"""Test consistency between rule definitions and results."""
sarif = run_sarif_check(TEST_CODE)
run = sarif["runs"][0]
driver = run["tool"]["driver"]
rules = driver["rules"]
results = run["results"]
# Collect rule IDs from both rules and results
rule_ids_in_rules = set(rule["id"] for rule in rules)
rule_ids_in_results = set(result["ruleId"] for result in results)
# Every rule ID in results should have a corresponding rule definition
for result_rule_id in rule_ids_in_results:
assert (
result_rule_id in rule_ids_in_rules
), f"Result references undefined rule: {result_rule_id}"
# Verify severity level consistency
severity_levels = set()
for result in results:
level = result["level"]
severity_levels.add(level)
# Valid SARIF levels
assert level in [
"error",
"warning",
"note",
"none",
], f"Invalid severity level: {level}"
# Should have at least error level
assert "error" in severity_levels, "Should have at least one error"
# Should have multiple severity levels for comprehensive test
assert (
len(severity_levels) >= 2
), f"Expected multiple severity levels, found: {severity_levels}"
|