customtests

package

v0.10.0 Latest Latest Go to latest Published: Mar 7, 2026 License: AGPL-3.0 Imports: 8 Imported by: 0

Details

Valid go.mod file
Redistributable license
Tagged version
Stable version
Learn more about best practices

Repository

github.com/SEObserver/crawlobserver

Links

Open Source Insights

Documentation ¶

Index ¶

type PageHTMLRow
type PageTestResult
type RuleType
- func (r RuleType) IsClickHouseNative() bool
type Ruleset
type StorageInterface
type TestRule
type TestRunResult
- func RunTests(ctx context.Context, store StorageInterface, sessionID string, ...) (*TestRunResult, error)

Constants ¶

This section is empty.

Variables ¶

This section is empty.

Functions ¶

This section is empty.

Types ¶

type PageHTMLRow ¶

type PageHTMLRow struct {
	URL  string
	HTML string
}

PageHTMLRow mirrors storage.PageHTMLRow to avoid circular imports.

type PageTestResult ¶

type PageTestResult struct {
	URL     string            `json:"url"`
	Results map[string]string `json:"results"` // rule_id → "pass"/"fail"/extracted_value
}

PageTestResult holds the test results for a single page.

type RuleType ¶

type RuleType string

RuleType defines the kind of test rule.

const (
	StringContains    RuleType = "string_contains"
	StringNotContains RuleType = "string_not_contains"
	RegexMatch        RuleType = "regex_match"
	RegexNotMatch     RuleType = "regex_not_match"
	HeaderExists      RuleType = "header_exists"
	HeaderNotExists   RuleType = "header_not_exists"
	HeaderContains    RuleType = "header_contains"
	HeaderRegex       RuleType = "header_regex"
	CSSExists         RuleType = "css_exists"
	CSSNotExists      RuleType = "css_not_exists"
	CSSExtractText    RuleType = "css_extract_text"
	CSSExtractAttr    RuleType = "css_extract_attr"
	CSSExtractAllText RuleType = "css_extract_all_text"
	CSSExtractAllAttr RuleType = "css_extract_all_attr"
	RegexExtract      RuleType = "regex_extract"
	RegexExtractAll   RuleType = "regex_extract_all"
	XPathExtract      RuleType = "xpath_extract"
	XPathExtractAll   RuleType = "xpath_extract_all"
)

func (RuleType) IsClickHouseNative ¶

func (r RuleType) IsClickHouseNative() bool

IsClickHouseNative returns true if the rule can run as a ClickHouse SQL expression.

type Ruleset ¶

type Ruleset struct {
	ID        string     `json:"id"`
	Name      string     `json:"name"`
	CreatedAt time.Time  `json:"created_at"`
	UpdatedAt time.Time  `json:"updated_at"`
	Rules     []TestRule `json:"rules"`
	RuleCount int        `json:"rule_count,omitempty"`
}

Ruleset groups test rules under a named set.

type StorageInterface ¶

type StorageInterface interface {
	RunCustomTestsSQL(ctx context.Context, sessionID string, rules []TestRule) (map[string]map[string]string, error)
	StreamPagesHTML(ctx context.Context, sessionID string) (<-chan PageHTMLRow, error)
}

StorageInterface is the subset of storage.Store needed by the engine.

type TestRule ¶

type TestRule struct {
	ID        string   `json:"id"`
	RulesetID string   `json:"ruleset_id"`
	Type      RuleType `json:"type"`
	Name      string   `json:"name"`
	Value     string   `json:"value"`
	Extra     string   `json:"extra"`
	SortOrder int      `json:"sort_order"`
}

TestRule is a single test rule within a ruleset.

type TestRunResult ¶

type TestRunResult struct {
	RulesetID   string           `json:"ruleset_id"`
	RulesetName string           `json:"ruleset_name"`
	SessionID   string           `json:"session_id"`
	TotalPages  int              `json:"total_pages"`
	Rules       []TestRule       `json:"rules"`
	Pages       []PageTestResult `json:"pages"`
	Summary     map[string]int   `json:"summary"` // rule_id → count of passes
}

TestRunResult is the full output of running a ruleset against a session.

func RunTests ¶

func RunTests(ctx context.Context, store StorageInterface, sessionID string, ruleset *Ruleset) (*TestRunResult, error)

RunTests executes all rules from a ruleset against a crawl session.

Source Files ¶

View all Source files

?	: This menu
/	: Search site
f or F	: Jump to
y or Y	: Canonical URL