hohn/codeql
1
0
Fork 0
mirror of https://github.com/github/codeql.git synced 2026-05-01 03:35:13 +02:00
Code Issues Packages Projects Releases Wiki Activity

Make function body features library independent of CodeToFeatures AST

Browse Source
This commit is contained in:
Henry Mercer
2022-01-11 19:30:34 +00:00
parent 9e50ce873d
commit 957e34d8a7
2 changed files with 9 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
javascript/ql/experimental/adaptivethreatmodeling/lib/experimental/adaptivethreatmodeling/EndpointFeatures.qll
View File

@@ -31,7 +31,7 @@ private string getTokenFeature(DataFlow::Node endpoint, string featureName) {
featureName = "enclosingFunctionBody" and
result =
strictconcat(string token, Location l |
FunctionBodyFeatures::bodyTokens(entity, l, token)
FunctionBodyFeatures::bodyTokens(entity.getDefinedFunction(), l, token)
|
token, " "
order by

17
javascript/ql/experimental/adaptivethreatmodeling/lib/experimental/adaptivethreatmodeling/FunctionBodyFeatures.qll
View File

@@ -5,7 +5,6 @@
*/
import javascript
private import CodeToFeatures
private import FeaturizationConfig
string getTokenizedAstNode(ASTNode node) {
@@ -36,8 +35,8 @@ ASTNode getAnASTNodeToFeaturize(Function f) {
}
/**
* Get a function containing the endpoint that is suitable for featurization. In general,
* this associates an endpoint to multiple functions, since there may be more than one multiple entities to a single endpoint.
* Get a function containing the endpoint that is suitable for featurization. In general, this
* can associate an endpoint to multiple functions, since functions can be nested in JavaScript.
*/
Function getAFunctionForEndpoint(DataFlow::Node endpoint) {
result = endpoint.getContainer().getEnclosingContainer*()
@@ -108,19 +107,19 @@ Function getRepresentativeFunctionForEndpoint(DataFlow::Node endpoint) {
)
}
/** Holds if `location` is the location of an AST node within the entity `entity` and `token` is a node attribute associated with that AST node. */
predicate bodyTokens(DatabaseFeatures::Entity entity, Location location, string token) {
// Performance optimization: Restrict the set of entities to those containing an endpoint to featurize.
entity.getDefinedFunction() =
/** Holds if `location` is the location of an AST node within the function `function` and `token` is a node attribute associated with that AST node. */
predicate bodyTokens(Function function, Location location, string token) {
// Performance optimization: Restrict the set of functions to those containing an endpoint to featurize.
function =
getRepresentativeFunctionForEndpoint(any(FeaturizationConfig cfg).getAnEndpointToFeaturize()) and
// Performance optimization: If a function has more than 256 body subtokens, then featurize it as absent. This
// approximates the behavior of the classifer on non-generic body features where large body
// features are replaced by the absent token.
//
// We count nodes instead of tokens because tokens are often not unique.
strictcount(getAnASTNodeToFeaturize(entity.getDefinedFunction())) <= 256 and
strictcount(getAnASTNodeToFeaturize(function)) <= 256 and
exists(ASTNode node |
node = getAnASTNodeToFeaturize(entity.getDefinedFunction()) and
node = getAnASTNodeToFeaturize(function) and
token = getTokenizedAstNode(node) and
location = node.getLocation()
)