probe

package
v0.4.6 Latest Latest
Warning

This package is not in the latest version of its module.

 Go to latest Published: Nov 8, 2026 License: Apache-2.0 Imports: 15 Imported by: 0

Documentation

Index

Constants

View Source 
const (
	ReadStrategyFixedWindow   = "fixed_window"
	ReadStrategyUntilResolved = "until_resolved"

	DefaultChunkBytes int64 = 64 * 1024

	OnMissingFail       = "fail"
	OnMissingQuarantine = "quarantine"

	TransformSubstring    = "substring"
	TransformRegexCapture = "regex_capture"
	TransformFormat       = "format"
	TransformPad          = "pad"
	TransformLowercase    = "lowercase"
	TransformUppercase    = "uppercase"
	TransformLookup       = "lookup"

	LookupMatchModeRegex  = "regex"
	LookupMatchModePrefix = "prefix"
	LookupMatchModeExact  = "exact"

	MaxPadWidth = 1024
)
View Source 
const (
	TerminationAllRequiredResolved = "all_required_resolved"
	TerminationMaxBytesReached     = "max_bytes_reached"
	TerminationStreamExhausted     = "stream_exhausted"
	TerminationParseError          = "parse_error"
	TerminationFixedWindow         = "fixed_window"
)
View Source 
const SummaryRecordType = "gonimbus.content.probe.summary.v1"

SummaryRecordType identifies terminal content-probe control evidence.

Variables

This section is empty.

Functions

func FinalizeAuditForTermination 

func FinalizeAuditForTermination(audit *ProbeAudit)

func KnownErrorCode 

func KnownErrorCode(code string) bool

KnownErrorCode bounds the published histogram vocabulary. Rejected codes must not be echoed into a diagnostic or used as a map key.

Types

type Config 

type Config struct {
	ReadStrategy     ReadStrategyConfig `json:"read_strategy,omitempty" yaml:"read_strategy,omitempty"`
	QuarantinePrefix string             `json:"quarantine_prefix,omitempty" yaml:"quarantine_prefix,omitempty"`
	Extract          []ExtractorConfig  `json:"extract" yaml:"extract"`
	Derived          []DerivedConfig    `json:"derived,omitempty" yaml:"derived,omitempty"`
}

Config controls content probing and derived field extraction.

The intent is to support generic extraction without embedding dataset-specific logic. Extractors are applied to the provided byte window (usually a header read).

func (*Config) Validate 

func (c *Config) Validate() error

func (*Config) ValidateWithRewriteCaptures 

func (c *Config) ValidateWithRewriteCaptures(rewriteCaptures []string) error

type DerivationError 

type DerivationError struct {
	Field     string
	From      string
	Transform string
	Detail    string
}

func (*DerivationError) Error 

func (e *DerivationError) Error() string

type DerivedConfig 

type DerivedConfig struct {
	Name      string         `json:"name" yaml:"name"`
	From      string         `json:"from" yaml:"from"`
	Transform string         `json:"transform" yaml:"transform"`
	Args      map[string]any `json:"args,omitempty" yaml:"args,omitempty"`
	Required  *bool          `json:"required,omitempty" yaml:"required,omitempty"`
	OnMissing string         `json:"on_missing,omitempty" yaml:"on_missing,omitempty"`
	// contains filtered or unexported fields
}

func (DerivedConfig) RequiredValue 

func (d DerivedConfig) RequiredValue() bool

type EmittedCounts 

type EmittedCounts struct {
	ReflowInput int64 `json:"reflow_input"`
	Probe       int64 `json:"probe"`
}

type ExtractorAudit 

type ExtractorAudit struct {
	Name              string `json:"name"`
	Type              string `json:"type"`
	Resolved          bool   `json:"resolved"`
	Required          bool   `json:"required"`
	OnMissing         string `json:"on_missing,omitempty"`
	BytesAtResolution *int64 `json:"bytes_at_resolution"`
	ResolvedPriority  *int   `json:"resolved_priority,omitempty"`
	ResolvedXPath     string `json:"resolved_xpath,omitempty"`
	TruncatedFallback bool   `json:"truncated_fallback,omitempty"`
}

type ExtractorConfig 

type ExtractorConfig struct {
	Name      string `json:"name" yaml:"name"`
	Type      string `json:"type" yaml:"type"`
	Required  bool   `json:"required,omitempty" yaml:"required,omitempty"`
	OnMissing string `json:"on_missing,omitempty" yaml:"on_missing,omitempty"`

	// For type=xml_xpath.
	XPath         string   `json:"xpath" yaml:"xpath"`
	XPathPriority []string `json:"xpath_priority,omitempty" yaml:"xpath_priority,omitempty"`

	// For type=regex.
	Pattern string `json:"pattern" yaml:"pattern"`
	Group   int    `json:"group" yaml:"group"`

	// For type=json_path.
	JSONPath string `json:"json_path" yaml:"json_path"`
}

type JSONPath 

type JSONPath struct {
	// contains filtered or unexported fields
}

JSONPath is a small JSON path selector.

Supported forms: - $.a.b.c - a.b.c - a[0].b

This is intentionally minimal for v0.1.x.

func CompileJSONPath 

func CompileJSONPath(expr string) (*JSONPath, error)

func (*JSONPath) Eval 

func (p *JSONPath) Eval(v any) (any, bool)

type ProbeAudit 

type ProbeAudit struct {
	Extractors             []ExtractorAudit `json:"extractors"`
	BytesRead              int64            `json:"bytes_read"`
	TerminationReason      string           `json:"termination_reason"`
	TruncatedFallbackCount int              `json:"truncated_fallback_count,omitempty"`
}

type Prober 

type Prober struct {
	// contains filtered or unexported fields
}

Prober executes configured extractors against a byte window.

func New 

func New(cfg Config) (*Prober, error)

func NewNormalizedWithRewriteCaptures 

func NewNormalizedWithRewriteCaptures(cfg *Config, rewriteCaptures []string) (*Prober, error)

NewNormalizedWithRewriteCaptures validates cfg in place and builds a prober from the normalized config. Callers that need config-derived runtime values after construction, such as read_strategy byte limits, should use this form.

func NewWithRewriteCaptures 

func NewWithRewriteCaptures(cfg Config, rewriteCaptures []string) (*Prober, error)

func (*Prober) AllRequiredResolved 

func (p *Prober) AllRequiredResolved(vars map[string]string) bool

func (*Prober) ApplyMissingPolicies 

func (p *Prober) ApplyMissingPolicies(vars map[string]string, audit *ProbeAudit) (routingClass string, requiredFailed bool)

func (*Prober) ApplyMissingPoliciesDetailed 

func (p *Prober) ApplyMissingPoliciesDetailed(vars map[string]string, audit *ProbeAudit, failures map[string]error) (routingClass string, requiredFailed bool, failureErr error)

func (*Prober) HasPriorityExtractors 

func (p *Prober) HasPriorityExtractors() bool

func (*Prober) HasRequiredExtractors 

func (p *Prober) HasRequiredExtractors() bool

func (*Prober) Probe 

func (p *Prober) Probe(data []byte) (map[string]string, error)

Probe returns derived fields. Missing fields are omitted.

func (*Prober) ProbeDetailed 

func (p *Prober) ProbeDetailed(data []byte, bytesRead int64, terminationReason string) (*Result, error)

func (*Prober) ProbeDetailedAllowIncomplete 

func (p *Prober) ProbeDetailedAllowIncomplete(data []byte, bytesRead int64, terminationReason string, incomplete func(error) bool) (*Result, error)

func (*Prober) ProbeDetailedAllowIncompleteWithVars 

func (p *Prober) ProbeDetailedAllowIncompleteWithVars(data []byte, bytesRead int64, terminationReason string, initialVars map[string]string, incomplete func(error) bool) (*Result, error)

func (*Prober) ProbeDetailedWithVars 

func (p *Prober) ProbeDetailedWithVars(data []byte, bytesRead int64, terminationReason string, initialVars map[string]string) (*Result, error)

func (*Prober) RequiredResolvedForTermination 

func (p *Prober) RequiredResolvedForTermination(res *Result) bool

func (*Prober) UnresolvedResult 

func (p *Prober) UnresolvedResult(bytesRead int64, terminationReason string) *Result

type ReadStrategyConfig 

type ReadStrategyConfig struct {
	Mode       string `json:"mode,omitempty" yaml:"mode,omitempty"`
	MaxBytes   string `json:"max_bytes,omitempty" yaml:"max_bytes,omitempty"`
	ChunkBytes string `json:"chunk_bytes,omitempty" yaml:"chunk_bytes,omitempty"`

	MaxBytesValue   int64 `json:"-" yaml:"-"`
	ChunkBytesValue int64 `json:"-" yaml:"-"`
}

type Result 

type Result struct {
	Vars     map[string]string
	Audit    ProbeAudit
	Failures map[string]error
}

type RoutingCounts 

type RoutingCounts struct {
	Normal     int64 `json:"normal"`
	Quarantine int64 `json:"quarantine"`
}

type Summary 

type Summary struct {
	Inputs        int64            `json:"inputs"`
	Enumerated    int64            `json:"enumerated"`
	Processed     int64            `json:"processed"`
	Emitted       EmittedCounts    `json:"emitted"`
	Routing       RoutingCounts    `json:"routing"`
	Errors        int64            `json:"errors"`
	ErrorsByCode  map[string]int64 `json:"errors_by_code"`
	InvalidInputs int64            `json:"invalid_inputs"`
	Termination   string           `json:"termination"`
	ExitCode      int              `json:"exit_code"`
	BytesRead     int64            `json:"bytes_read"`
	WallMS        int64            `json:"wall_ms"`
}

Summary reports handled termination, not provider custody or pipeline success. All counters are present even for empty or failed invocations.

func ParseSummary 

func ParseSummary(raw json.RawMessage) (Summary, error)

ParseSummary validates the exact control payload without treating it as an object or accepting arbitrary unknown record types. Errors never echo data.

func (Summary) Validate 

func (s Summary) Validate() error

type XMLXPath 

type XMLXPath struct {
	// contains filtered or unexported fields
}

XMLXPath is a deliberately small XPath-like selector.

Supported forms: - //TagName (match any element with local name TagName) - /a/b/c (match exact element path)

Predicates, attributes, and namespaces are not supported.

func CompileXMLXPath 

func CompileXMLXPath(expr string) (*XMLXPath, error)

func (*XMLXPath) FindFirstText 

func (x *XMLXPath) FindFirstText(xmlBytes []byte) (string, bool, error)

Source Files

View all Source files

Jump to

Keyboard shortcuts

? : This menu
/ : Search site
f or F : Jump to
y or Y : Canonical URL
go.dev uses cookies from Google to deliver and enhance the quality of its services and to analyze traffic. Learn more.