base

type BrowserCoverageMetadata struct {
	RawCoverageFilenames []string `json:"raw_coverage_filenames"`
	TotalRegions         int      `json:"total_regions"`
	CoveredRegions       int      `json:"covered_regions""`
}

type BrowserSettings struct {
	BrowserBinary       *string              `json:"browser_binary,omitempty"`       // The binary for the browser (e.g., "/path/to/chrome.exe")
	UserDataDirectory   *string              `json:"user_data_directory,omitempty"`  // Path to user data directory to use
	AddBrowserFlags     *[]string            `json:"add_browser_flags,omitempty"`    // Flags to be added to default browser flags
	RemoveBrowserFlags  *[]string            `json:"remove_browser_flags,omitempty"` // Flags to be removed from default browser flags
	SetBrowserFlags     *[]string            `json:"set_browser_flags,omitempty"`    // Flags to use to override default browser flags
	Extensions          *[]string            `json:"extensions,omitempty"`           // Paths to browser extensions to be used for the crawl
	InteractionSettings *InteractionSettings `json:"interaction_settings"`           // Settings describing how the browser will interact with the page
}

type CompletionCondition string

type CompletionSettings struct {
	CompletionCondition *CompletionCondition `json:"completion_condition"`      // Condition under which crawl will complete
	Timeout             *int                 `json:"timeout,omitempty"`         // Maximum amount of time the browser will remain open
	TimeAfterLoad       *int                 `json:"time_after_load,omitempty"` // Maximum amount of time the browser will remain open after page load
}

type CompressedTaskSet struct {
	URL *[]string `json:"url"` // List of URLs to be visited

	Browser    *BrowserSettings    `json:"browser_settings"`    // Settings for launching the browser
	Completion *CompletionSettings `json:"completion_settings"` // Settings for when the site visit will complete
	Data       *DataSettings       `json:"data_settings"`       // Settings for what data will be collected from the site
	Output     *OutputSettings     `json:"output_settings"`     // Settings for what/how results will be saved

	Repeat *int `json:"repeat"` // Number of times to repeat the crawl after it finishes successfully
}

type CrawlerInfo struct {
	Browser        string `json:"browser"`         // Name of the browser itself
	BrowserVersion string `json:"browser_version"` // Version of the browser we are using
	UserAgent      string `json:"user_agent"`      // User agent we are using
	JSVersion      string `json:"js_version"`      // JS version
}

type DTResource struct {
	Requests []*network.EventRequestWillBeSent `json:"requests"`  // All requests sent for this particular request
	Response *network.EventResponseReceived    `json:"responses"` // All responses received for this particular request
}

type DataSettings struct {
	AllResources     *bool `json:"all_resources,omitempty"`     // Save all resource files
	AllScripts       *bool `json:"all_scripts,omitempty"`       // Save all scripts parsed by browser
	Cookies          *bool `json:"cookies,omitempty"`           // Save cookies set by page
	DOM              *bool `json:"dom,omitempty"`               // Collect JSON representation of the DOM
	ResourceMetadata *bool `json:"resource_metadata,omitempty"` // Save extensive metadata about each resource
	Screenshot       *bool `json:"screenshot,omitempty"`        // Save a screenshot from the web page
	ScriptMetadata   *bool `json:"script_metadata,omitempty"`   // Save metadata on scripts parsed by browser

	BrowserCoverage *bool `json:"browser_coverage"` // Whether to gather code coverage data from the browser
	RawCovFiles     *bool `json:"raw_cov_files"`    // Raw profraw files from browser
	CovTxtFile      *bool `json:"cov_txt_file"`     // llvm-cov-custom generated text file containing coverage
	CovTreeSummary  *bool `json:"cov_tree_summary"` // CSV summary of code coverage for file tree
}

type DevToolsNetworkRawData struct {
	RequestWillBeSent map[string][]*network.EventRequestWillBeSent
	ResponseReceived  map[string]*network.EventResponseReceived
}

type DevToolsRawData struct {
	Network DevToolsNetworkRawData
	Cookies []*network.Cookie
	DOM     *cdp.Node
	Scripts DevToolsScriptRawData
}

type DevToolsScriptRawData []*debugger.EventScriptParsed

type FinalResult struct {
	Summary            TaskSummary                            `json:"stats"`   // Statistics on timing and resource usage for the crawl
	DTCookies          []*network.Cookie                      `json:"cookies"` // Cookies collected from DevTools protocol
	DTDOM              *cdp.Node                              `json:"dom"`
	DTResourceMetadata map[string]DTResource                  `json:"resource_metadata"` // Metadata on each resource loaded
	DTScriptMetadata   map[string]*debugger.EventScriptParsed `json:"script_metadata"`   // Metadata on each script parsed
}

type InteractionSettings struct {
	LockNavigation        *bool `json:"lock_navigation"`
	BasicInteraction      *bool `json:"basic_interaction"`
	Gremlins              *bool `json:"gremlins"`
	TriggerEventListeners *bool `json:"event_listeners"`
}

type LocalOutputSettings struct {
	Enable *bool         `json:"enable,omitmepty"`        // Whether this storage method is enabled
	Path   *string       `json:"path,omitempty"`          // Path over the overarching results directory to be written
	DS     *DataSettings `json:"data_settings,omitempty"` // Data settings for output to local filesystem
}

type OutputSettings struct {
	LocalOut  *LocalOutputSettings `json:"local_output_settings,omitempty"` // Output settings for the local filesystem
	SftpOut   *SftpOutputSettings  `json:"sftp_output_settings,omitempty"`  // Output settings for the remote filesystem
	PostQueue *string              `json:"post_queue,omitempty"`            // AMQP queue in which we should put metadata for crawl once complete
}

type RawResult struct {
	TaskSummary TaskSummary     // Summary information about the task, not necessarily complete in RawResult
	DevTools    DevToolsRawData // Struct Containing Raw Data gathered from a DevTools site visit
	sync.Mutex
}

type RawTask struct {
	URL *string `json:"url"` // The URL to be visited

	Browser    *BrowserSettings    `json:"browser_settings"`    // Settings for launching the browser
	Completion *CompletionSettings `json:"completion_settings"` // Settings for when the site visit will complete
	Data       *DataSettings       `json:"data_settings"`       // Settings for what data will be collected from the site
	Output     *OutputSettings     `json:"output_settings"`     // Settings for what/how results will be saved
}

type SanitizedTask struct {
	URL string

	BrowserBinaryPath string   // Full path to the browser binary we use for the crawl
	BrowserFlags      []string // List of flags we will use when opening the browser (does not include --remote-debugging-port or similar)
	UserDataDirectory string   // Full path to the user data directory for the task

	CS  CompletionSettings  // Task completion settings for the task
	DS  DataSettings        // Data Gathering Settings for the task
	IS  InteractionSettings // Settings on how the browser will interact with the page
	OPS OutputSettings      // Output settings for the task
}

type SftpOutputSettings struct {
	Enable         *bool         `json:"enable,omitempty"`           // Whether this storage method is enabled
	Host           *string       `json:"host,omitempty"`             // IP address or domain name of host to store to
	Port           *int          `json:"port,omitempty"`             // Port to initiate SSH/SFTP connection
	Path           *string       `json:"path,omitempty"`             // Path of the overarching results directory to be written
	UserName       *string       `json:"user_name,omitempty"`        // User name we should use for accessing the host
	PrivateKeyFile *string       `json:"private_key_file,omitempty"` // Path to the private key file we should use for accessing the host
	DS             *DataSettings `json:"data_settings,omitempty"`    // Data settings for output via SSH/SFTP
}

type TaskSet []RawTask

type TaskSummary struct {
	NavURL string `json:"nav_url"`
	UUID   string `json:"uuid"`

	Success       bool   `json:"success"`                  // True if the task did not fail
	FailureReason string `json:"failure_reason,omitempty"` // Holds the failure code for the task

	TaskWrapper *TaskWrapper `json:"-"`            // Wrapper containing the full task
	TaskTiming  TaskTiming   `json:"task_timing"`  // Timing data for the task
	CrawlerInfo CrawlerInfo  `json:"crawler_info"` // Information about the infrastructure used to visit the site

	OutputHost string `json:"output_host,omitempty"` // Host to which results were stored via SFTP
	OutputPath string `json:"output_path,omitempty"` // Path to the results of the crawl on the applicable host (after storage)

	NumResources int `json:"num_resources"` // Number of resources the browser downloaded
	NumScripts   int `json:"num_scripts"`   // Number of scripts the browser parsed

	NavHistory []page.NavigationEntry `json:"nav_history"`

	BrowserCovData BrowserCoverageMetadata `json:"browser_cov_data"`
}

type TaskTiming struct {
	BrowserOpen           time.Time `json:"browser_open"`
	ConnectionEstablished time.Time `json:"connection_established"`
	LoadEvent             time.Time `json:"load_event"`
	BrowserClose          time.Time `json:"browser_close"`
	BeginPostprocess      time.Time `json:"begin_postprocess"`
	EndPostprocess        time.Time `json:"end_postprocess"`
	BeginStorage          time.Time `json:"begin_storage"`
	EndStorage            time.Time `json:"-"`
}

type TaskWrapper struct {
	RawTask       RawTask       // A pointer to a MIDA task
	SanitizedTask SanitizedTask // A sanitized MIDA task

	UUID    uuid.UUID
	TempDir string // Temporary directory where results are stored. Can be the same as the UserDataDir in some cases.

	// Dynamic fields
	Log     *logrus.Logger
	LogFile *os.File
}