def invoke_semgrep(config: Path, targets: List[Path], **kwargs: Any) -> Any:
"""
Call semgrep with config on targets and return result as a json object
Uses default arguments of MAIN unless overwritten with a kwarg
"""
io_capture = StringIO()
output_handler = OutputHandler(
OutputSettings(
output_format=OutputFormat.JSON,
output_destination=None,
error_on_findings=False,
verbose_errors=False,
strict=False,
json_stats=False,
output_per_finding_max_lines_limit=None,
),
stdout=io_capture,
)
main(
output_handler=output_handler,
target=[str(t) for t in targets],
pattern="",
lang="",
configs=[str(config)],
**kwargs,
)
output_handler.close()
return json.loads(io_capture.getvalue())
def invoke_semgrep(
config: Path,
targets: List[Path],
output_settings: Optional[OutputSettings] = None,
**kwargs: Any,
) -> Union[Dict[str, Any], str]:
"""
Return Semgrep results of 'config' on 'targets' as a dict|str
Uses default arguments of 'semgrep_main.main' unless overwritten with 'kwargs'
"""
if output_settings is None:
output_settings = OutputSettings(output_format=OutputFormat.JSON)
io_capture = StringIO()
output_handler = OutputHandler(output_settings, stdout=io_capture)
main(
output_handler=output_handler,
target=[str(t) for t in targets],
pattern="",
lang="",
configs=[str(config)],
**kwargs,
)
output_handler.close()
result: Union[Dict[str, Any], str] = (json.loads(
io_capture.getvalue()) if output_settings.output_format.is_json() else
io_capture.getvalue())
return result
def invoke_semgrep(paths, scan_rules, **kwargs):
"""Call Semgrep."""
if platform.system() == 'Windows':
return None
from semgrep import semgrep_main, util
from semgrep.constants import OutputFormat
from semgrep.output import OutputHandler, OutputSettings
try:
cpu_count = multiprocessing.cpu_count()
except NotImplementedError:
cpu_count = 1 # CPU count is not implemented on Windows
util.set_flags(False, True, False) # Verbose, Quiet, Force_color
io_capture = StringIO()
output_handler = OutputHandler(
OutputSettings(
output_format=OutputFormat.JSON,
output_destination=None,
error_on_findings=False,
strict=False,
),
stdout=io_capture,
)
semgrep_main.main(
output_handler=output_handler,
target=[pt.as_posix() for pt in paths],
jobs=cpu_count,
pattern=None,
lang=None,
config=scan_rules,
**kwargs,
)
output_handler.close()
return json.loads(io_capture.getvalue())
def invoke_semgrep(paths, scan_rules, **kwargs):
"""Call Semgrep."""
if platform.system() == 'Windows':
return None
from semgrep import semgrep_main
from semgrep.state import get_state
from semgrep.constants import OutputFormat
from semgrep.output import OutputHandler, OutputSettings
try:
cpu_count = multiprocessing.cpu_count()
except NotImplementedError:
cpu_count = 1 # CPU count is not implemented on Windows
# Semgrep output formatting
state = get_state()
state.terminal.configure(
verbose=False,
debug=False,
quiet=True,
force_color=False,
)
logging.getLogger('semgrep').propagate = False
output_settings = OutputSettings(
output_format=OutputFormat.JSON,
output_destination=None,
output_per_finding_max_lines_limit=None,
output_per_line_max_chars_limit=None,
error_on_findings=False,
verbose_errors=False,
strict=False,
timeout_threshold=3,
)
output_handler = OutputHandler(output_settings)
(
filtered_matches_by_rule,
_,
_,
_,
_,
_,
_,
_,
) = semgrep_main.main(
output_handler=output_handler,
target=[pt.as_posix() for pt in paths],
jobs=cpu_count,
pattern=None,
lang=None,
configs=[scan_rules],
timeout=5,
timeout_threshold=3,
**kwargs,
)
output_handler.rule_matches = [
m for ms in filtered_matches_by_rule.values() for m in ms
]
return json.loads(output_handler._build_output())
def test_ignore_git_dir(tmp_path, monkeypatch):
"""
Ignores all files in .git directory when scanning generic
"""
foo = tmp_path / ".git"
foo.mkdir()
(foo / "bar").touch()
monkeypatch.chdir(tmp_path)
language = Language("generic")
output_settings = OutputSettings(
output_format=OutputFormat.TEXT,
output_destination=None,
error_on_findings=False,
verbose_errors=False,
strict=False,
json_stats=False,
output_time=False,
output_per_finding_max_lines_limit=None,
output_per_line_max_chars_limit=None,
)
defaulthandler = OutputHandler(output_settings)
assert [] == TargetManager([], [], 0, [foo], True, defaulthandler, False).get_files(
language, [], []
)
def Scan(self, filepath):
self.io_capture = StringIO()
self.output = OutputHandler(self.setting, stdout=self.io_capture)
semgrep_main.main(
output_handler=self.output,
target=[filepath],
jobs=1,
pattern=None,
lang=None,
configs=[self.ruleset],
timeout=5,
timeout_threshold=3,
)
self.output.close()
return self.format(filepath)
def test_explicit_path(tmp_path, monkeypatch):
foo = tmp_path / "foo"
foo.mkdir()
(foo / "a.go").touch()
(foo / "b.go").touch()
foo_noext = foo / "noext"
foo_noext.touch()
foo_a = foo / "a.py"
foo_a.touch()
foo_b = foo / "b.py"
foo_b.touch()
monkeypatch.chdir(tmp_path)
# Should include explicitly passed python file
foo_a = foo_a.relative_to(tmp_path)
output_settings = OutputSettings(
output_format=OutputFormat.TEXT,
output_destination=None,
error_on_findings=False,
strict=False,
)
defaulthandler = OutputHandler(output_settings)
python_language = Language("python")
assert foo_a in TargetManager([], [], ["foo/a.py"], False, defaulthandler,
False).get_files(python_language, [], [])
# Should include explicitly passed python file even if is in excludes
assert foo_a not in TargetManager([], ["foo/a.py"], ["."], False,
defaulthandler,
False).get_files(python_language, [], [])
assert foo_a in TargetManager([], ["foo/a.py"], [".", "foo/a.py"], False,
defaulthandler,
False).get_files(python_language, [], [])
# Should ignore expliclty passed .go file when requesting python
assert (TargetManager([], [], ["foo/a.go"], False, defaulthandler,
False).get_files(python_language, [], []) == [])
# Should include explicitly passed file with unknown extension if skip_unknown_extensions=False
assert cmp_path_sets(
set(
TargetManager([], [], ["foo/noext"], False, defaulthandler,
False).get_files(python_language, [], [])),
{foo_noext},
)
# Should not include explicitly passed file with unknown extension if skip_unknown_extensions=True
assert cmp_path_sets(
set(
TargetManager([], [], ["foo/noext"], False, defaulthandler,
True).get_files(python_language, [], [])),
set(),
)
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,
) -> 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,
)
# actually invoke semgrep
(
rule_matches_by_rule,
debug_steps_by_rule,
semgrep_errors,
all_targets,
profiler,
) = CoreRunner(
allow_exec=dangerously_allow_arbitrary_code_execution_from_rules,
jobs=jobs,
timeout=timeout,
max_memory=max_memory,
timeout_threshold=timeout_threshold,
).invoke_semgrep(target_manager, filtered_rules)
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)
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,
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,
config: 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 = 0,
) -> None:
if include is None:
include = []
if exclude is None:
exclude = []
valid_configs, config_errors = get_config(pattern, lang, config)
output_handler.handle_semgrep_errors(config_errors)
if config_errors and strict:
raise SemgrepError(
f"run with --strict and there were {len(config_errors)} errors loading configs",
code=MISSING_CONFIG_EXIT_CODE,
)
if not no_rewrite_rule_ids:
# re-write the configs to have the hierarchical rule ids
valid_configs = rename_rule_ids(valid_configs)
# extract just the rules from valid configs
all_rules = flatten_configs(valid_configs)
if not pattern:
plural = "s" if len(valid_configs) > 1 else ""
config_id_if_single = (list(valid_configs.keys())[0]
if len(valid_configs) == 1 else "")
invalid_msg = (f"({len(config_errors)} config files were invalid)"
if len(config_errors) else "")
logger.debug(
f"running {len(all_rules)} rules from {len(valid_configs)} config{plural} {config_id_if_single} {invalid_msg}"
)
notify_user_of_work(all_rules, include, exclude)
if len(valid_configs) == 0:
raise SemgrepError(
f"no valid configuration file found ({len(config_errors)} configs were invalid)",
code=MISSING_CONFIG_EXIT_CODE,
)
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,
)
# actually invoke semgrep
rule_matches_by_rule, debug_steps_by_rule, semgrep_errors = CoreRunner(
allow_exec=dangerously_allow_arbitrary_code_execution_from_rules,
jobs=jobs,
timeout=timeout,
).invoke_semgrep(target_manager, all_rules)
output_handler.handle_semgrep_errors(semgrep_errors)
if not disable_nosem:
rule_matches_by_rule = {
rule: [
rule_match for rule_match in rule_matches
if not rule_match_nosem(rule_match, strict)
]
for rule, rule_matches in rule_matches_by_rule.items()
}
output_handler.handle_semgrep_core_output(rule_matches_by_rule,
debug_steps_by_rule)
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,
testing: bool = False,
severity: Optional[List[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:
raise SemgrepError(
f"no valid configuration file found ({len(errors)} configs were invalid)",
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,
)
# actually invoke semgrep
rule_matches_by_rule, debug_steps_by_rule, semgrep_errors, num_targets = CoreRunner(
allow_exec=dangerously_allow_arbitrary_code_execution_from_rules,
jobs=jobs,
timeout=timeout,
max_memory=max_memory,
timeout_threshold=timeout_threshold,
testing=testing,
).invoke_semgrep(target_manager, filtered_rules)
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 {num_targets} files: {num_findings} findings"
output_handler.handle_semgrep_core_output(rule_matches_by_rule,
debug_steps_by_rule, stats_line)
if autofix:
apply_fixes(rule_matches_by_rule, dryrun)
class SGrep():
def __init__(self, ruleset):
self.ruleset = ruleset
util.set_flags(False, True, False)
try:
self.setting = OutputSettings(
output_format=OutputFormat.JSON,
output_destination=None,
error_on_findings=False,
verbose_errors=False,
strict=False,
timeout_threshold=3,
json_stats=False,
# json_time = False,
output_per_finding_max_lines_limit=None,
)
except:
self.setting = OutputSettings(
output_format=OutputFormat.JSON,
output_destination=None,
error_on_findings=False,
verbose_errors=False,
strict=False,
timeout_threshold=3,
json_stats=False,
json_time=False,
output_per_finding_max_lines_limit=None,
)
def Scan(self, filepath):
self.io_capture = StringIO()
self.output = OutputHandler(self.setting, stdout=self.io_capture)
semgrep_main.main(
output_handler=self.output,
target=[filepath],
jobs=1,
pattern=None,
lang=None,
configs=[self.ruleset],
timeout=5,
timeout_threshold=3,
)
self.output.close()
return self.format(filepath)
def format(self, filepath):
result = json.loads(self.io_capture.getvalue())
issues = []
for find in result['results']:
i = Issue(Info(find['extra']['message'], ""),
find['start']['line'],
find['start']['col'],
find['extra']['lines'],
lineEnd=find['end']['line'],
filename=filepath,
owasp=find['extra']['metadata']['owasp'],
cwe=find['extra']['metadata']['cwe'],
severity=find['extra']['severity'])
issues.append(i)
return issues
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)