def invoke_semgrep(
self,
target_manager: TargetManager,
rules: List[Rule],
) -> Tuple[
Dict[Rule, List[RuleMatch]],
Dict[Rule, List[Dict[str, Any]]],
List[SemgrepError],
Set[Path],
ProfileManager,
]:
"""
Takes in rules and targets and retuns object with findings
"""
start = datetime.now()
profiler = ProfileManager()
findings_by_rule, debug_steps_by_rule, errors, all_targets = self._run_rules(
rules, target_manager, profiler
)
logger.debug(
f"semgrep ran in {datetime.now() - start} on {len(all_targets)} files"
)
by_severity = collections.defaultdict(list)
for rule, findings in findings_by_rule.items():
by_severity[rule.severity.lower()].extend(findings)
by_sev_strings = [
f"{len(findings)} {sev}" for sev, findings in by_severity.items()
]
logger.debug(f'findings summary: {", ".join(by_sev_strings)}')
return findings_by_rule, debug_steps_by_rule, errors, all_targets, profiler
def invoke_semgrep(
self,
target_manager: TargetManager,
rules: List[Rule],
experimental: bool = False,
) -> Tuple[
Dict[Rule, List[RuleMatch]],
Dict[Rule, List[Dict[str, Any]]],
List[SemgrepError],
Set[Path],
ProfileManager,
Dict[Tuple[str, str], float],
]:
"""
Takes in rules and targets and retuns object with findings
"""
start = datetime.now()
profiler = ProfileManager()
runner_fxn = (
self._run_rules_direct_to_semgrep_core if experimental else self._run_rules
)
(
findings_by_rule,
debug_steps_by_rule,
errors,
all_targets,
match_time_matrix,
) = runner_fxn(rules, target_manager, profiler)
logger.debug(
f"semgrep ran in {datetime.now() - start} on {len(all_targets)} files"
)
by_severity = collections.defaultdict(list)
for rule, findings in findings_by_rule.items():
by_severity[rule.severity.lower()].extend(findings)
by_sev_strings = [
f"{len(findings)} {sev}" for sev, findings in by_severity.items()
]
logger.debug(f'findings summary: {", ".join(by_sev_strings)}')
return (
findings_by_rule,
debug_steps_by_rule,
errors,
all_targets,
profiler,
match_time_matrix,
)
def _run_rule(
self,
rule: Rule,
target_manager: TargetManager,
cache_dir: str,
max_timeout_files: List[Path],
profiler: ProfileManager,
match_time_matrix: Dict[Tuple[str, str], float],
) -> Tuple[List[RuleMatch], List[Dict[str, Any]], List[SemgrepError], Set[Path]]:
"""
Run all rules on targets and return list of all places that match patterns, ... todo errors
"""
outputs: List[PatternMatch] = [] # multiple invocations per language
errors: List[SemgrepError] = []
all_targets: Set[Path] = set()
for language, all_patterns_for_language in self._group_patterns_by_language(
rule
).items():
targets = self.get_files_for_language(language, rule, target_manager)
targets = [target for target in targets if target not in max_timeout_files]
all_targets = all_targets.union(targets)
if not targets:
continue
if rule.mode == TAINT_MODE:
pattern_json = rule._raw.copy()
del pattern_json["mode"]
pattern = Pattern(
0, rule.expression, rule.severity, language, rule._yaml.span
)
output_json = profiler.track(
rule.id,
self._run_core_command,
[pattern_json],
[pattern],
targets,
language,
rule,
"-tainting_rules_file",
cache_dir,
report_time=self._report_time,
)
else:
# semgrep-core doesn't know about OPERATORS.REGEX - this is
# strictly a semgrep Python feature. Regex filtering is
# performed purely in Python code then compared against
# semgrep-core's results for other patterns.
patterns_regex, patterns = partition(
lambda p: p.expression.operator == OPERATORS.REGEX
or p.expression.operator == OPERATORS.NOT_REGEX,
all_patterns_for_language,
)
if patterns_regex:
self.handle_regex_patterns(outputs, patterns_regex, targets)
# regex-only rules only support OPERATORS.REGEX.
# Skip passing this rule to semgrep-core.
if language in REGEX_ONLY_LANGUAGE_KEYS:
continue
# semgrep-core doesn't know about the following operators -
# they are strictly semgrep Python features:
# - OPERATORS.METAVARIABLE_REGEX
# - OPERATORS.METAVARIABLE_COMPARISON
patterns = [
pattern
for pattern in patterns
if pattern.expression.operator
not in [
OPERATORS.METAVARIABLE_REGEX,
OPERATORS.METAVARIABLE_COMPARISON,
]
]
patterns_json = [p.to_json() for p in patterns]
if language == GENERIC_LANGUAGE:
output_json = profiler.track(
rule.id,
run_spacegrep,
rule.id,
patterns,
targets,
timeout=self._timeout,
report_time=self._report_time,
)
else: # Run semgrep-core
output_json = profiler.track(
rule.id,
self._run_core_command,
patterns_json,
patterns,
targets,
language,
rule,
"-rules_file",
cache_dir,
report_time=self._report_time,
)
errors.extend(
CoreException.from_json(e, language, rule.id).into_semgrep_error()
for e in output_json["errors"]
)
outputs.extend(PatternMatch(m) for m in output_json["matches"])
if "time" in output_json:
self._add_match_times(rule, match_time_matrix, output_json["time"])
# group output; we want to see all of the same rule ids on the same file path
by_rule_index: Dict[
Rule, Dict[Path, List[PatternMatch]]
] = collections.defaultdict(lambda: collections.defaultdict(list))
for pattern_match in outputs:
by_rule_index[rule][pattern_match.path].append(pattern_match)
findings = []
debugging_steps: List[Any] = []
for rule, paths in by_rule_index.items():
for filepath, pattern_matches in paths.items():
logger.debug(
f"--> rule ({rule.id}) has findings on filepath: {filepath}"
)
findings_for_rule, debugging_steps = evaluate(
rule, pattern_matches, self._allow_exec
)
findings.extend(findings_for_rule)
findings = dedup_output(findings)
logger.debug(f"...ran on {len(all_targets)} files")
# debugging steps are only tracked for a single file, just overwrite
return findings, debugging_steps, errors, all_targets
def main(
output_handler: OutputHandler,
target: List[str],
pattern: str,
lang: str,
configs: List[str],
no_rewrite_rule_ids: bool = False,
jobs: int = 1,
include: Optional[List[str]] = None,
exclude: Optional[List[str]] = None,
strict: bool = False,
autofix: bool = False,
dryrun: bool = False,
disable_nosem: bool = False,
dangerously_allow_arbitrary_code_execution_from_rules: bool = False,
no_git_ignore: bool = False,
timeout: int = DEFAULT_TIMEOUT,
max_memory: int = 0,
max_target_bytes: int = 0,
timeout_threshold: int = 0,
skip_unknown_extensions: bool = False,
severity: Optional[List[str]] = None,
optimizations: str = "none",
) -> None:
if include is None:
include = []
if exclude is None:
exclude = []
configs_obj, errors = get_config(pattern, lang, configs)
all_rules = configs_obj.get_rules(no_rewrite_rule_ids)
if severity is None or severity == []:
filtered_rules = all_rules
else:
filtered_rules = [
rule for rule in all_rules if rule.severity in severity
]
output_handler.handle_semgrep_errors(errors)
if errors and strict:
raise SemgrepError(
f"run with --strict and there were {len(errors)} errors loading configs",
code=MISSING_CONFIG_EXIT_CODE,
)
if not pattern:
plural = "s" if len(configs_obj.valid) > 1 else ""
config_id_if_single = (list(configs_obj.valid.keys())[0]
if len(configs_obj.valid) == 1 else "")
invalid_msg = (f"({len(errors)} config files were invalid)"
if len(errors) else "")
logger.verbose(
f"running {len(filtered_rules)} rules from {len(configs_obj.valid)} config{plural} {config_id_if_single} {invalid_msg}"
)
if len(configs_obj.valid) == 0:
if len(errors) > 0:
raise SemgrepError(
f"no valid configuration file found ({len(errors)} configs were invalid)",
code=MISSING_CONFIG_EXIT_CODE,
)
else:
raise SemgrepError(
"""You need to specify a config with --config=<semgrep.dev config name|localfile|localdirectory|url>.
If you're looking for a config to start with, there are thousands at: https://semgrep.dev
The two most popular are:
--config=p/ci # find logic bugs, and high-confidence security vulnerabilities; recommended for CI
--config=p/security-audit # find security audit points; noisy, not recommended for CI
""",
code=MISSING_CONFIG_EXIT_CODE,
)
notify_user_of_work(filtered_rules, include, exclude)
respect_git_ignore = not no_git_ignore
target_manager = TargetManager(
includes=include,
excludes=exclude,
max_target_bytes=max_target_bytes,
targets=target,
respect_git_ignore=respect_git_ignore,
output_handler=output_handler,
skip_unknown_extensions=skip_unknown_extensions,
)
profiler = ProfileManager()
# # Turn off optimizations if using features not supported yet
if optimizations == "all":
# taint mode rules not yet supported
if any(rule.mode == TAINT_MODE for rule in filtered_rules):
logger.info("Running without optimizations since taint rule found")
optimizations = "none"
# step by step evaluation output not yet supported
elif output_handler.settings.debug:
logger.info(
"Running without optimizations since step-by-step evaluation output desired"
)
optimizations = "none"
elif any(rule.has_pattern_where_python() for rule in filtered_rules):
logger.info(
"Running without optimizations since running pattern-where-python rules"
)
optimizations = "none"
start_time = time.time()
# actually invoke semgrep
(
rule_matches_by_rule,
debug_steps_by_rule,
semgrep_errors,
all_targets,
profiling_data,
) = CoreRunner(
output_settings=output_handler.settings,
allow_exec=dangerously_allow_arbitrary_code_execution_from_rules,
jobs=jobs,
timeout=timeout,
max_memory=max_memory,
timeout_threshold=timeout_threshold,
optimizations=optimizations,
).invoke_semgrep(target_manager, profiler, filtered_rules)
profiler.save("total_time", start_time)
output_handler.handle_semgrep_errors(semgrep_errors)
nosem_errors = []
for rule, rule_matches in rule_matches_by_rule.items():
evolved_rule_matches = []
for rule_match in rule_matches:
ignored, returned_errors = rule_match_nosem(rule_match, strict)
evolved_rule_matches.append(
attr.evolve(rule_match, is_ignored=ignored))
nosem_errors.extend(returned_errors)
rule_matches_by_rule[rule] = evolved_rule_matches
output_handler.handle_semgrep_errors(nosem_errors)
num_findings_nosem = 0
if not disable_nosem:
filtered_rule_matches_by_rule = {}
for rule, rule_matches in rule_matches_by_rule.items():
filtered_rule_matches = []
for rule_match in rule_matches:
if rule_match._is_ignored:
num_findings_nosem += 1
else:
filtered_rule_matches.append(rule_match)
filtered_rule_matches_by_rule[rule] = filtered_rule_matches
rule_matches_by_rule = filtered_rule_matches_by_rule
num_findings = sum(len(v) for v in rule_matches_by_rule.values())
stats_line = f"ran {len(filtered_rules)} rules on {len(all_targets)} files: {num_findings} findings"
if metric_manager.is_enabled:
project_url = None
try:
project_url = sub_check_output(
["git", "ls-remote", "--get-url"],
encoding="utf-8",
stderr=subprocess.DEVNULL,
)
except Exception as e:
logger.debug(
f"Failed to get project url from 'git ls-remote': {e}")
try:
# add \n to match urls from git ls-remote (backwards compatability)
project_url = manually_search_file(".git/config", ".com", "\n")
except Exception as e:
logger.debug(
f"Failed to get project url from .git/config: {e}")
metric_manager.set_project_hash(project_url)
metric_manager.set_configs_hash(configs)
metric_manager.set_rules_hash(filtered_rules)
metric_manager.set_num_rules(len(filtered_rules))
metric_manager.set_num_targets(len(all_targets))
metric_manager.set_num_findings(num_findings)
metric_manager.set_num_ignored(num_findings_nosem)
metric_manager.set_run_time(profiler.calls["total_time"][0])
total_bytes_scanned = sum(t.stat().st_size for t in all_targets)
metric_manager.set_total_bytes_scanned(total_bytes_scanned)
metric_manager.set_errors(
list(type(e).__name__ for e in semgrep_errors))
metric_manager.set_run_timings(profiling_data, all_targets,
filtered_rules)
output_handler.handle_semgrep_core_output(
rule_matches_by_rule,
debug_steps_by_rule,
stats_line,
all_targets,
profiler,
filtered_rules,
profiling_data,
)
if autofix:
apply_fixes(rule_matches_by_rule, dryrun)
def main(
output_handler: OutputHandler,
target: List[str],
pattern: str,
lang: str,
configs: List[str],
no_rewrite_rule_ids: bool = False,
jobs: int = 1,
include: Optional[List[str]] = None,
exclude: Optional[List[str]] = None,
strict: bool = False,
autofix: bool = False,
dryrun: bool = False,
disable_nosem: bool = False,
dangerously_allow_arbitrary_code_execution_from_rules: bool = False,
no_git_ignore: bool = False,
timeout: int = DEFAULT_TIMEOUT,
max_memory: int = 0,
timeout_threshold: int = 0,
skip_unknown_extensions: bool = False,
severity: Optional[List[str]] = None,
report_time: bool = False,
optimizations: str = "none",
) -> None:
if include is None:
include = []
if exclude is None:
exclude = []
configs_obj, errors = get_config(pattern, lang, configs)
all_rules = configs_obj.get_rules(no_rewrite_rule_ids)
if severity is None or severity == []:
filtered_rules = all_rules
else:
filtered_rules = [rule for rule in all_rules if rule.severity in severity]
output_handler.handle_semgrep_errors(errors)
if errors and strict:
raise SemgrepError(
f"run with --strict and there were {len(errors)} errors loading configs",
code=MISSING_CONFIG_EXIT_CODE,
)
if not pattern:
plural = "s" if len(configs_obj.valid) > 1 else ""
config_id_if_single = (
list(configs_obj.valid.keys())[0] if len(configs_obj.valid) == 1 else ""
)
invalid_msg = (
f"({len(errors)} config files were invalid)" if len(errors) else ""
)
logger.debug(
f"running {len(filtered_rules)} rules from {len(configs_obj.valid)} config{plural} {config_id_if_single} {invalid_msg}"
)
if len(configs_obj.valid) == 0:
if len(errors) > 0:
raise SemgrepError(
f"no valid configuration file found ({len(errors)} configs were invalid)",
code=MISSING_CONFIG_EXIT_CODE,
)
else:
raise SemgrepError(
"""You need to specify a config with --config=<semgrep.dev config name|localfile|localdirectory|url>.
If you're looking for a config to start with, there are thousands at: https://semgrep.dev
The two most popular are:
--config=p/ci # find logic bugs, and high-confidence security vulnerabilities; recommended for CI
--config=p/security-audit # find security audit points; noisy, not recommended for CI
""",
code=MISSING_CONFIG_EXIT_CODE,
)
notify_user_of_work(filtered_rules, include, exclude)
respect_git_ignore = not no_git_ignore
target_manager = TargetManager(
includes=include,
excludes=exclude,
targets=target,
respect_git_ignore=respect_git_ignore,
output_handler=output_handler,
skip_unknown_extensions=skip_unknown_extensions,
)
profiler = ProfileManager()
start_time = time.time()
# actually invoke semgrep
(
rule_matches_by_rule,
debug_steps_by_rule,
semgrep_errors,
all_targets,
match_time_matrix,
) = CoreRunner(
allow_exec=dangerously_allow_arbitrary_code_execution_from_rules,
jobs=jobs,
timeout=timeout,
max_memory=max_memory,
timeout_threshold=timeout_threshold,
report_time=report_time,
).invoke_semgrep(
target_manager, profiler, filtered_rules, optimizations
)
profiler.save("total_time", start_time)
output_handler.handle_semgrep_errors(semgrep_errors)
rule_matches_by_rule = {
rule: [
attr.evolve(rule_match, is_ignored=rule_match_nosem(rule_match, strict))
for rule_match in rule_matches
]
for rule, rule_matches in rule_matches_by_rule.items()
}
if not disable_nosem:
rule_matches_by_rule = {
rule: [
rule_match for rule_match in rule_matches if not rule_match._is_ignored
]
for rule, rule_matches in rule_matches_by_rule.items()
}
num_findings = sum(len(v) for v in rule_matches_by_rule.values())
stats_line = f"ran {len(filtered_rules)} rules on {len(all_targets)} files: {num_findings} findings"
output_handler.handle_semgrep_core_output(
rule_matches_by_rule,
debug_steps_by_rule,
stats_line,
all_targets,
profiler,
filtered_rules,
match_time_matrix,
)
if autofix:
apply_fixes(rule_matches_by_rule, dryrun)
def main(
*,
output_handler: OutputHandler,
target: Sequence[str],
pattern: Optional[str],
lang: Optional[str],
configs: Sequence[str],
no_rewrite_rule_ids: bool = False,
jobs: int = 1,
include: Optional[Sequence[str]] = None,
exclude: Optional[Sequence[str]] = None,
strict: bool = False,
autofix: bool = False,
replacement: Optional[str] = None,
dryrun: bool = False,
disable_nosem: bool = False,
no_git_ignore: bool = False,
timeout: int = DEFAULT_TIMEOUT,
max_memory: int = 0,
max_target_bytes: int = 0,
timeout_threshold: int = 0,
skip_unknown_extensions: bool = False,
severity: Optional[Sequence[str]] = None,
optimizations: str = "none",
) -> None:
if include is None:
include = []
if exclude is None:
exclude = []
configs_obj, errors = get_config(pattern, lang, configs, replacement)
all_rules = configs_obj.get_rules(no_rewrite_rule_ids)
if not severity:
filtered_rules = all_rules
else:
filtered_rules = [
rule for rule in all_rules if rule.severity.value in severity
]
output_handler.handle_semgrep_errors(errors)
if errors and strict:
raise SemgrepError(
f"run with --strict and there were {len(errors)} errors loading configs",
code=MISSING_CONFIG_EXIT_CODE,
)
if not pattern:
plural = "s" if len(configs_obj.valid) > 1 else ""
config_id_if_single = (list(configs_obj.valid.keys())[0]
if len(configs_obj.valid) == 1 else "")
invalid_msg = (f"({len(errors)} config files were invalid)"
if len(errors) else "")
logger.verbose(
f"running {len(filtered_rules)} rules from {len(configs_obj.valid)} config{plural} {config_id_if_single} {invalid_msg}"
.strip())
if len(configs_obj.valid) == 0:
if len(errors) > 0:
raise SemgrepError(
f"no valid configuration file found ({len(errors)} configs were invalid)",
code=MISSING_CONFIG_EXIT_CODE,
)
else:
raise SemgrepError(
"""You need to specify a config with --config=<semgrep.dev config name|localfile|localdirectory|url>.
If you're looking for a config to start with, there are thousands at: https://semgrep.dev
The two most popular are:
--config=p/ci # find logic bugs, and high-confidence security vulnerabilities; recommended for CI
--config=p/security-audit # find security audit points; noisy, not recommended for CI
""",
code=MISSING_CONFIG_EXIT_CODE,
)
notify_user_of_work(filtered_rules, include, exclude)
respect_git_ignore = not no_git_ignore
target_manager = TargetManager(
includes=include,
excludes=exclude,
max_target_bytes=max_target_bytes,
targets=target,
respect_git_ignore=respect_git_ignore,
output_handler=output_handler,
skip_unknown_extensions=skip_unknown_extensions,
)
profiler = ProfileManager()
join_rules, rest_of_the_rules = partition(
lambda rule: rule.mode == JOIN_MODE,
filtered_rules,
)
filtered_rules = rest_of_the_rules
start_time = time.time()
# actually invoke semgrep
(
rule_matches_by_rule,
debug_steps_by_rule,
semgrep_errors,
all_targets,
profiling_data,
) = CoreRunner(
jobs=jobs,
timeout=timeout,
max_memory=max_memory,
timeout_threshold=timeout_threshold,
optimizations=optimizations,
).invoke_semgrep(target_manager, profiler, filtered_rules)
if join_rules:
import semgrep.join_rule as join_rule
for rule in join_rules:
join_rule_matches, join_rule_errors = join_rule.run_join_rule(
rule.raw, [Path(t) for t in target_manager.targets])
join_rule_matches_by_rule = {
Rule.from_json(rule.raw): join_rule_matches
}
rule_matches_by_rule.update(join_rule_matches_by_rule)
output_handler.handle_semgrep_errors(join_rule_errors)
profiler.save("total_time", start_time)
filtered_matches = process_ignores(rule_matches_by_rule,
output_handler,
strict=strict,
disable_nosem=disable_nosem)
output_handler.handle_semgrep_errors(semgrep_errors)
output_handler.handle_semgrep_errors(filtered_matches.errors)
num_findings = sum(len(v) for v in filtered_matches.matches.values())
stats_line = f"ran {len(filtered_rules)} rules on {len(all_targets)} files: {num_findings} findings"
if metric_manager.is_enabled:
project_url = None
try:
project_url = sub_check_output(
["git", "ls-remote", "--get-url"],
encoding="utf-8",
stderr=subprocess.DEVNULL,
)
except Exception as e:
logger.debug(
f"Failed to get project url from 'git ls-remote': {e}")
try:
# add \n to match urls from git ls-remote (backwards compatability)
project_url = manually_search_file(".git/config", ".com", "\n")
except Exception as e:
logger.debug(
f"Failed to get project url from .git/config: {e}")
metric_manager.set_project_hash(project_url)
metric_manager.set_configs_hash(configs)
metric_manager.set_rules_hash(filtered_rules)
metric_manager.set_num_rules(len(filtered_rules))
metric_manager.set_num_targets(len(all_targets))
metric_manager.set_num_findings(num_findings)
metric_manager.set_num_ignored(filtered_matches.num_matches)
metric_manager.set_run_time(profiler.calls["total_time"][0])
total_bytes_scanned = sum(t.stat().st_size for t in all_targets)
metric_manager.set_total_bytes_scanned(total_bytes_scanned)
metric_manager.set_errors(
list(type(e).__name__ for e in semgrep_errors))
metric_manager.set_run_timings(profiling_data, list(all_targets),
filtered_rules)
output_handler.handle_semgrep_core_output(
filtered_matches.matches,
debug_steps_by_rule,
stats_line,
all_targets,
profiler,
filtered_rules,
profiling_data,
)
if autofix:
apply_fixes(filtered_matches.matches, dryrun)