Merge branch 'main' into netflow-receiver-implementation

.chloggen/logs-for-libhoneyreceiver.yaml

@@ -0,0 +1,27 @@
+# Use this changelog template to create an entry for release notes.
+
+# One of 'breaking', 'deprecation', 'new_component', 'enhancement', 'bug_fix'
+change_type: enhancement
+
+# The name of the component, or a single word describing the area of concern, (e.g. filelogreceiver)
+component: libhoneyreceiver
+
+# A brief description of the change.  Surround your text with quotes ("") if it needs to start with a backtick (`).
+note: Implement log signal for libhoney receiver
+
+# Mandatory: One or more tracking issues related to the change. You can use the PR number here if no issue exists.
+issues: [36693]
+
+# (Optional) One or more lines of additional information to render under the primary note.
+# These lines will be padded with 2 spaces and then inserted directly into the document.
+# Use pipe (|) for multiline entries.
+subtext:
+
+# If your change doesn't affect end users or the exported elements of any package,
+# you should instead start your pull request title with [chore] or use the "Skip Changelog" label.
+# Optional: The change log or logs in which this entry should be included.
+# e.g. '[user]' or '[user, api]'
+# Include 'user' if the change is relevant to end users.
+# Include 'api' if there is a change to a library API.
+# Default: '[user]'
+change_logs: [user]

pkg/ottl/context_inferrer.go

@@ -3,75 +3,234 @@
 
 package ottl // import "github.com/open-telemetry/opentelemetry-collector-contrib/pkg/ottl"
 
-import "math"
+import (
+	"cmp"
+	"math"
+	"slices"
+)
 
 var defaultContextInferPriority = []string{
 	"log",
-	"metric",
 	"datapoint",
+	"metric",
 	"spanevent",
 	"span",
 	"resource",
 	"scope",
 	"instrumentation_scope",
 }
 
-// contextInferrer is an interface used to infer the OTTL context from statements paths.
+// contextInferrer is an interface used to infer the OTTL context from statements.
 type contextInferrer interface {
-	// infer returns the OTTL context inferred from the given statements paths.
+	// infer returns the OTTL context inferred from the given statements.
 	infer(statements []string) (string, error)
 }
 
 type priorityContextInferrer struct {
-	contextPriority map[string]int
+	contextPriority  map[string]int
+	contextCandidate map[string]*priorityContextInferrerCandidate
+}
+
+type priorityContextInferrerCandidate struct {
+	hasEnumSymbol    func(enum *EnumSymbol) bool
+	hasFunctionName  func(name string) bool
+	getLowerContexts func(context string) []string
+}
+
+type priorityContextInferrerOption func(*priorityContextInferrer)
+
+// newPriorityContextInferrer creates a new priority-based context inferrer. To infer the context,
+// it uses a slice of priorities (withContextInferrerPriorities) and a set of hints extracted from
+// the parsed statements.
+//
+// To be eligible, a context must support all functions and enums symbols present on the statements.
+// If the path context with the highest priority does not meet this requirement, it falls back to its
+// lower contexts, testing them with the same logic and choosing the first one that meets all requirements.
+//
+// If non-prioritized contexts are found on the statements, they get assigned the lowest possible priority,
+// and are only selected if no other prioritized context is found.
+func newPriorityContextInferrer(contextsCandidate map[string]*priorityContextInferrerCandidate, options ...priorityContextInferrerOption) contextInferrer {
+	c := &priorityContextInferrer{
+		contextCandidate: contextsCandidate,
+	}
+	for _, opt := range options {
+		opt(c)
+	}
+	if len(c.contextPriority) == 0 {
+		withContextInferrerPriorities(defaultContextInferPriority)(c)
+	}
+	return c
+}
+
+// withContextInferrerPriorities sets the contexts candidates priorities. The lower the
+// context position is in the array, the more priority it will have over other items.
+func withContextInferrerPriorities(priorities []string) priorityContextInferrerOption {
+	return func(c *priorityContextInferrer) {
+		contextPriority := map[string]int{}
+		for pri, context := range priorities {
+			contextPriority[context] = pri
+		}
+		c.contextPriority = contextPriority
+	}
 }
 
 func (s *priorityContextInferrer) infer(statements []string) (string, error) {
+	requiredFunctions := map[string]struct{}{}
+	requiredEnums := map[enumSymbol]struct{}{}
+
 	var inferredContext string
 	var inferredContextPriority int
-
 	for _, statement := range statements {
 		parsed, err := parseStatement(statement)
 		if err != nil {
-			return inferredContext, err
+			return "", err
 		}
 
-		for _, p := range getParsedStatementPaths(parsed) {
-			pathContextPriority, ok := s.contextPriority[p.Context]
+		statementPaths, statementFunctions, statementEnums := s.getParsedStatementHints(parsed)
+		for _, p := range statementPaths {
+			candidate := p.Context
+			candidatePriority, ok := s.contextPriority[candidate]
 			if !ok {
-				// Lowest priority
-				pathContextPriority = math.MaxInt
+				candidatePriority = math.MaxInt
 			}
-
-			if inferredContext == "" || pathContextPriority < inferredContextPriority {
-				inferredContext = p.Context
-				inferredContextPriority = pathContextPriority
+			if inferredContext == "" || candidatePriority < inferredContextPriority {
+				inferredContext = candidate
+				inferredContextPriority = candidatePriority
 			}
 		}
+		for function := range statementFunctions {
+			requiredFunctions[function] = struct{}{}
+		}
+		for enum := range statementEnums {
+			requiredEnums[enum] = struct{}{}
+		}
+	}
+	// No inferred context or nothing left to verify.
+	if inferredContext == "" || (len(requiredFunctions) == 0 && len(requiredEnums) == 0) {
+		return inferredContext, nil
+	}
+	ok := s.validateContextCandidate(inferredContext, requiredFunctions, requiredEnums)
+	if ok {
+		return inferredContext, nil
+	}
+	return s.inferFromLowerContexts(inferredContext, requiredFunctions, requiredEnums), nil
+}
+
+// validateContextCandidate checks if the given context candidate has all required functions names
+// and enums symbols. The functions arity are not verified.
+func (s *priorityContextInferrer) validateContextCandidate(
+	context string,
+	requiredFunctions map[string]struct{},
+	requiredEnums map[enumSymbol]struct{},
+) bool {
+	candidate, ok := s.contextCandidate[context]
+	if !ok {
+		return false
+	}
+	if len(requiredFunctions) == 0 && len(requiredEnums) == 0 {
+		return true
+	}
+	for function := range requiredFunctions {
+		if !candidate.hasFunctionName(function) {
+			return false
+		}
+	}
+	for enum := range requiredEnums {
+		if !candidate.hasEnumSymbol((*EnumSymbol)(&enum)) {
+			return false
+		}
 	}
+	return true
+}
+
+// inferFromLowerContexts returns the first lower context that supports all required functions
+// and enum symbols used on the statements.
+// If no lower context meets the requirements, or if the context candidate is unknown, it
+// returns an empty string.
+func (s *priorityContextInferrer) inferFromLowerContexts(
+	context string,
+	requiredFunctions map[string]struct{},
+	requiredEnums map[enumSymbol]struct{},
+) string {
+	inferredContextCandidate, ok := s.contextCandidate[context]
+	if !ok {
+		return ""
+	}
+
+	lowerContextCandidates := inferredContextCandidate.getLowerContexts(context)
+	if len(lowerContextCandidates) == 0 {
+		return ""
+	}
+
+	s.sortContextCandidates(lowerContextCandidates)
+	for _, lowerCandidate := range lowerContextCandidates {
+		ok = s.validateContextCandidate(lowerCandidate, requiredFunctions, requiredEnums)
+		if ok {
+			return lowerCandidate
+		}
+	}
+	return ""
+}
+
+// sortContextCandidates sorts the slice candidates using the priorityContextInferrer.contextsPriority order.
+func (s *priorityContextInferrer) sortContextCandidates(candidates []string) {
+	slices.SortFunc(candidates, func(l, r string) int {
+		lp, ok := s.contextPriority[l]
+		if !ok {
+			lp = math.MaxInt
+		}
+		rp, ok := s.contextPriority[r]
+		if !ok {
+			rp = math.MaxInt
+		}
+		return cmp.Compare(lp, rp)
+	})
+}
 
-	return inferredContext, nil
+// getParsedStatementHints extracts all path, function names (editor and converter), and enumSymbol
+// from the given parsed statements. These values are used by the context inferrer as hints to
+// select a context in which the function/enum are supported.
+func (s *priorityContextInferrer) getParsedStatementHints(parsed *parsedStatement) ([]path, map[string]struct{}, map[enumSymbol]struct{}) {
+	visitor := newGrammarContextInferrerVisitor()
+	parsed.Editor.accept(&visitor)
+	if parsed.WhereClause != nil {
+		parsed.WhereClause.accept(&visitor)
+	}
+	return visitor.paths, visitor.functions, visitor.enumsSymbols
 }
 
-// defaultPriorityContextInferrer is like newPriorityContextInferrer, but using the default
-// context priorities and ignoring unknown/non-prioritized contexts.
-func defaultPriorityContextInferrer() contextInferrer {
-	return newPriorityContextInferrer(defaultContextInferPriority)
+// priorityContextInferrerHintsVisitor is a grammarVisitor implementation that collects
+// all path, function names (converter.Function and editor.Function), and enumSymbol.
+type priorityContextInferrerHintsVisitor struct {
+	paths        []path
+	functions    map[string]struct{}
+	enumsSymbols map[enumSymbol]struct{}
 }
 
-// newPriorityContextInferrer creates a new priority-based context inferrer.
-// To infer the context, it compares all [ottl.Path.Context] values, prioritizing them based
-// on the provide contextsPriority argument, the lower the context position is in the array,
-// the more priority it will have over other items.
-// If unknown/non-prioritized contexts are found on the statements, they can be either ignored
-// or considered when no other prioritized context is found. To skip unknown contexts, the
-// ignoreUnknownContext argument must be set to false.
-func newPriorityContextInferrer(contextsPriority []string) contextInferrer {
-	contextPriority := make(map[string]int, len(contextsPriority))
-	for i, ctx := range contextsPriority {
-		contextPriority[ctx] = i
+func newGrammarContextInferrerVisitor() priorityContextInferrerHintsVisitor {
+	return priorityContextInferrerHintsVisitor{
+		paths:        []path{},
+		functions:    make(map[string]struct{}),
+		enumsSymbols: make(map[enumSymbol]struct{}),
 	}
-	return &priorityContextInferrer{
-		contextPriority: contextPriority,
+}
+
+func (v *priorityContextInferrerHintsVisitor) visitMathExprLiteral(_ *mathExprLiteral) {}
+
+func (v *priorityContextInferrerHintsVisitor) visitEditor(e *editor) {
+	v.functions[e.Function] = struct{}{}
+}
+
+func (v *priorityContextInferrerHintsVisitor) visitConverter(c *converter) {
+	v.functions[c.Function] = struct{}{}
+}
+
+func (v *priorityContextInferrerHintsVisitor) visitValue(va *value) {
+	if va.Enum != nil {
+		v.enumsSymbols[*va.Enum] = struct{}{}
 	}
 }
+
+func (v *priorityContextInferrerHintsVisitor) visitPath(value *path) {
+	v.paths = append(v.paths, *value)
+}