Skip to content

lucene improvements #71

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Feb 29, 2024
Merged

lucene improvements #71

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 4 additions & 1 deletion translator/app/translator/platforms/base/lucene/mapping.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,7 +22,10 @@ def prepare_log_source_signature(self, mapping: dict) -> LuceneLogSourceSignatur
return LuceneLogSourceSignature(indices=indices, default_source=default_log_source)

def get_suitable_source_mappings(
self, field_names: list[str], index: Optional[list[str]] = None
self,
field_names: list[str],
index: Optional[list[str]] = None,
**kwargs, # noqa: ARG002
) -> list[SourceMapping]:
suitable_source_mappings = []
for source_mapping in self._source_mappings.values():
Expand Down
29 changes: 18 additions & 11 deletions translator/app/translator/platforms/base/lucene/renders/lucene.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -42,13 +42,13 @@ def _pre_process_values_list(
) -> list[str]:
value_type = self.__get_value_type(field, value_type)
processed = []
for v in values:
if isinstance(v, StrValue):
processed.append(self.str_value_manager.from_container_to_str(v, value_type))
elif isinstance(v, str):
processed.append(self.str_value_manager.escape_manager.escape(v, value_type))
for val in values:
if isinstance(val, StrValue):
processed.append(self.str_value_manager.from_container_to_str(val, value_type))
elif isinstance(val, str):
processed.append(self.str_value_manager.escape_manager.escape(val, value_type))
else:
processed.append(str(v))
processed.append(str(val))
return processed

def _pre_process_value(
Expand Down Expand Up @@ -87,25 +87,32 @@ def not_equal_modifier(self, field: str, value: DEFAULT_VALUE_TYPE) -> str:

def contains_modifier(self, field: str, value: DEFAULT_VALUE_TYPE) -> str:
if isinstance(value, list):
values = self.or_token.join(f"*{v}*" for v in self._pre_process_values_list(field, value))
values = self.or_token.join(f"*{val}*" for val in self._pre_process_values_list(field, value))
return f"{field}:({values})"
return f"{field}:*{self._pre_process_value(field, value)}*"

def endswith_modifier(self, field: str, value: DEFAULT_VALUE_TYPE) -> str:
if isinstance(value, list):
values = self.or_token.join(f"*{v}" for v in self._pre_process_values_list(field, value))
values = self.or_token.join(f"*{val}" for val in self._pre_process_values_list(field, value))
return f"{field}:({values})"
return f"{field}:*{self._pre_process_value(field, value)}"

def startswith_modifier(self, field: str, value: DEFAULT_VALUE_TYPE) -> str:
if isinstance(value, list):
values = self.or_token.join(f"{v}*" for v in self._pre_process_values_list(field, value))
values = self.or_token.join(f"{val}*" for val in self._pre_process_values_list(field, value))
return f"{field}:({values})"
return f"{field}:{self._pre_process_value(field, value)}*"

def regex_modifier(self, field: str, value: DEFAULT_VALUE_TYPE) -> str:
if isinstance(value, list):
return f"({self.or_token.join(self.regex_modifier(field=field, value=v) for v in value)})"
values = []
for val in value:
values.append(
f"/{self._pre_process_value(field, val, value_type=ValueType.regex_value)}/"
if isinstance(val, StrValue)
else f"/{val}/"
)
return f"{field}:({self.or_token.join(values)})"

if isinstance(value, StrValue):
return f"{field}:/{self._pre_process_value(field, value, value_type=ValueType.regex_value)}/"
Expand All @@ -114,7 +121,7 @@ def regex_modifier(self, field: str, value: DEFAULT_VALUE_TYPE) -> str:

def keywords(self, field: str, value: DEFAULT_VALUE_TYPE) -> str:
if isinstance(value, list):
return f"({self.or_token.join(self.keywords(field=field, value=v) for v in value)})"
return f"({self.or_token.join(self.keywords(field=field, value=val) for val in value)})"
return f"*{self._pre_process_value(field, value)}*"


Expand Down
2 changes: 1 addition & 1 deletion translator/app/translator/platforms/base/spl/tokenizer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -42,7 +42,7 @@ class SplTokenizer(QueryTokenizer, ANDLogicOperatorMixin):

field_pattern = r"(?P<field_name>[a-zA-Z0-9\.\-_\{\}]+)"
num_value_pattern = rf"(?P<{ValueType.number_value}>\d+(?:\.\d+)*)(?=$|\s|\))"
double_quotes_value_pattern = rf'"(?P<{ValueType.double_quotes_value}>(?:[:a-zA-Z\*0-9=+%#\-_/,;`\?~‘○×\'\.<>$&^@!\]\[\(\)\{{\}}\s]|\\\"|\\)*)"\s*' # noqa: E501
double_quotes_value_pattern = rf'"(?P<{ValueType.double_quotes_value}>(?:[:a-zA-Z\*0-9=+%#\-_/,;`\?~‘○×\'\.<>$&^@!\]\[\(\)\{{\}}\s]|\\\"|\\)*)"\s*' # noqa: E501, RUF001
single_quotes_value_pattern = (
rf"'(?P<{ValueType.single_quotes_value}>(?:[:a-zA-Z\*0-9=+%#\-_/,;\"\.<>$&^@!\(\)\{{\}}\s]|\\\'|\\)*)'\s*"
)
Expand Down
5 changes: 3 additions & 2 deletions translator/app/translator/platforms/elasticsearch/renders/detection_rule.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,9 +18,10 @@
"""

import copy
import json
from typing import Optional, Union

import ujson

from app.translator.core.mapping import SourceMapping
from app.translator.core.mitre import MitreConfig
from app.translator.core.models.parser_output import MetaInfoContainer
Expand Down Expand Up @@ -113,7 +114,7 @@ def finalize_query(
"false_positives": meta_info.false_positives,
}
)
rule_str = json.dumps(rule, indent=4, sort_keys=False, ensure_ascii=False)
rule_str = ujson.dumps(rule, indent=4, sort_keys=False, ensure_ascii=False)
if not_supported_functions:
rendered_not_supported = self.render_not_supported_functions(not_supported_functions)
return rule_str + rendered_not_supported
Expand Down
7 changes: 4 additions & 3 deletions translator/app/translator/platforms/elasticsearch/renders/kibana.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,9 +17,10 @@
-----------------------------------------------------------------
"""
import copy
import json
from typing import Optional

import ujson

from app.translator.core.mapping import SourceMapping
from app.translator.core.models.parser_output import MetaInfoContainer
from app.translator.core.models.platform_details import PlatformDetails
Expand Down Expand Up @@ -56,7 +57,7 @@ def finalize_query(
query = super().finalize_query(prefix=prefix, query=query, functions=functions)
search_source = copy.deepcopy(KIBANA_SEARCH_SOURCE_JSON)
search_source["query"]["query_string"]["query"] = query
dumped_rule = json.dumps(search_source, sort_keys=False)
dumped_rule = ujson.dumps(search_source, sort_keys=False, escape_forward_slashes=False)
rule = copy.deepcopy(KIBANA_RULE)
rule["_source"]["kibanaSavedObjectMeta"]["searchSourceJSON"] = dumped_rule
rule["_source"]["title"] = meta_info.title
Expand All @@ -67,7 +68,7 @@ def finalize_query(
license_=meta_info.license,
references=meta_info.references,
)
rule_str = json.dumps(rule, indent=4, sort_keys=False)
rule_str = ujson.dumps(rule, indent=4, sort_keys=False)
if not_supported_functions:
rendered_not_supported = self.render_not_supported_functions(not_supported_functions)
return rule_str + rendered_not_supported
Expand Down
5 changes: 3 additions & 2 deletions translator/app/translator/platforms/elasticsearch/renders/xpack_watcher.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,9 +17,10 @@
-----------------------------------------------------------------
"""
import copy
import json
from typing import Optional

import ujson

from app.translator.core.mapping import SourceMapping
from app.translator.core.models.parser_output import MetaInfoContainer
from app.translator.core.models.platform_details import PlatformDetails
Expand Down Expand Up @@ -72,7 +73,7 @@ def finalize_query(
indices = source_mapping and [str(source_mapping.log_source_signature)] or []
rule["input"]["search"]["request"]["indices"] = indices
rule["actions"]["send_email"]["email"]["subject"] = meta_info.title
rule_str = json.dumps(rule, indent=4, sort_keys=False)
rule_str = ujson.dumps(rule, indent=4, sort_keys=False)
if not_supported_functions:
rendered_not_supported = self.render_not_supported_functions(not_supported_functions)
return rule_str + rendered_not_supported
Expand Down
28 changes: 20 additions & 8 deletions translator/app/translator/platforms/opensearch/renders/opensearch.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,6 +21,7 @@
from app.translator.const import DEFAULT_VALUE_TYPE
from app.translator.core.custom_types.values import ValueType
from app.translator.core.models.platform_details import PlatformDetails
from app.translator.core.str_value_manager import StrValue
from app.translator.platforms.base.lucene.renders.lucene import LuceneFieldValue, LuceneQueryRender
from app.translator.platforms.opensearch.const import opensearch_query_details
from app.translator.platforms.opensearch.mapping import OpenSearchMappings, opensearch_mappings
Expand All @@ -31,7 +32,7 @@ class OpenSearchFieldValue(LuceneFieldValue):

def equal_modifier(self, field: str, value: DEFAULT_VALUE_TYPE) -> str:
if isinstance(value, list):
values = self.or_token.join(f'"{v}"' for v in self._pre_process_values_list(field, value))
values = self.or_token.join(f'"{val}"' for val in self._pre_process_values_list(field, value))
return f"{field}:({values})"
return f'{field}:"{self._pre_process_value(field, value)}"'

Expand All @@ -49,36 +50,47 @@ def greater_or_equal_modifier(self, field: str, value: Union[int, str]) -> str:

def not_equal_modifier(self, field: str, value: DEFAULT_VALUE_TYPE) -> str:
if isinstance(value, list):
values = self.or_token.join(f'"{v}"' for v in self._pre_process_values_list(field, value))
values = self.or_token.join(f'"{val}"' for val in self._pre_process_values_list(field, value))
return f"NOT ({field} = ({values})"
return f'NOT ({field} = "{self._pre_process_value(field, value)}")'

def contains_modifier(self, field: str, value: DEFAULT_VALUE_TYPE) -> str:
if isinstance(value, list):
values = self.or_token.join(f'"*{v}*"' for v in self._pre_process_values_list(field, value))
values = self.or_token.join(f'"*{val}*"' for val in self._pre_process_values_list(field, value))
return f"{field}:({values})"
return f'{field}:"*{self._pre_process_value(field, value)}*"'

def endswith_modifier(self, field: str, value: DEFAULT_VALUE_TYPE) -> str:
if isinstance(value, list):
values = self.or_token.join(f'"*{v}"' for v in self._pre_process_values_list(field, value))
values = self.or_token.join(f'"*{val}"' for val in self._pre_process_values_list(field, value))
return f"{field}:({values})"
return f'{field}:"*{self._pre_process_value(field, value)}"'

def startswith_modifier(self, field: str, value: DEFAULT_VALUE_TYPE) -> str:
if isinstance(value, list):
values = self.or_token.join(f'"{v}*"' for v in self._pre_process_values_list(field, value))
values = self.or_token.join(f'"{val}*"' for val in self._pre_process_values_list(field, value))
return f"{field}:({values})"
return f'{field}:"{self._pre_process_value(field, value)}*"'

def regex_modifier(self, field: str, value: DEFAULT_VALUE_TYPE) -> str:
if isinstance(value, list):
return f"({self.or_token.join(self.regex_modifier(field=field, value=v) for v in value)})"
return f'{field}:"/{self._pre_process_value(field, value, value_type=ValueType.regex_value)}/"'
values = []
for val in value:
values.append(
f'"/{self._pre_process_value(field, val, value_type=ValueType.regex_value)}/"'
if isinstance(val, StrValue)
else f'"/{val}/"'
)
return f"{field}:({self.or_token.join(values)})"

if isinstance(value, StrValue):
return f'{field}:"/{self._pre_process_value(field, value, value_type=ValueType.regex_value)}/"'

return f'{field}:"/{value}/"'

def keywords(self, field: str, value: DEFAULT_VALUE_TYPE) -> str:
if isinstance(value, list):
return f"({self.or_token.join(self.keywords(field=field, value=v) for v in value)})"
return f"({self.or_token.join(self.keywords(field=field, value=val) for val in value)})"
return f'"*{self._pre_process_value(field, value)}*"'


Expand Down
5 changes: 3 additions & 2 deletions translator/app/translator/platforms/opensearch/renders/opensearch_rule.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,9 +17,10 @@
-----------------------------------------------------------------
"""
import copy
import json
from typing import Optional

import ujson

from app.translator.core.custom_types.meta_info import SeverityType
from app.translator.core.mapping import SourceMapping
from app.translator.core.models.parser_output import MetaInfoContainer
Expand Down Expand Up @@ -63,7 +64,7 @@ def finalize_query(
rule["inputs"][0]["search"]["query"]["query"]["bool"]["must"][0]["query_string"]["query"] = query
rule["triggers"][0]["name"] = meta_info.title
rule["triggers"][0]["severity"] = _SEVERITIES_MAP[meta_info.severity]
rule_str = json.dumps(rule, indent=4, sort_keys=False)
rule_str = ujson.dumps(rule, indent=4, sort_keys=False)
if not_supported_functions:
rendered_not_supported = self.render_not_supported_functions(not_supported_functions)
return rule_str + rendered_not_supported
Expand Down
1 change: 1 addition & 0 deletions translator/requirements.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,3 +4,4 @@ pydantic~=1.10.13
PyYAML~=6.0.1
colorama~=0.4.6
ruff==0.1.13
ujson==5.9.0
pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy