zoekt

type Document struct {
	Name              string
	Content           []byte
	Branches          []string
	SubRepositoryPath string
	Language          string

	// If set, something is wrong with the file contents, and this
	// is the reason it wasn't indexed.
	SkipReason string

	// Document sections for symbols. Offsets should use bytes.
	Symbols []DocumentSection
}

type DocumentSection struct {
	Start, End uint32
}

type FileMatch struct {
	// Ranking; the higher, the better.
	Score float64 // TODO - hide this field?

	// For debugging. Needs DebugScore set, but public so tests in
	// other packages can print some diagnostics.
	Debug string

	FileName string

	// Repository is the globally unique name of the repo of the
	// match
	Repository  string
	Branches    []string
	LineMatches []LineMatch

	// Only set if requested
	Content []byte

	// Checksum of the content.
	Checksum []byte

	// Detected language of the result.
	Language string

	// SubRepositoryName is the globally unique name of the repo,
	// if it came from a subrepository
	SubRepositoryName string

	// SubRepositoryPath holds the prefix where the subrepository
	// was mounted.
	SubRepositoryPath string

	// Commit SHA1 (hex) of the (sub)repo holding the file.
	Version string
}

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

type IndexFile interface {
	Read(off uint32, sz uint32) ([]byte, error)
	Size() (uint32, error)
	Close()
	Name() string
}

type IndexMetadata struct {
	IndexFormatVersion    int
	IndexFeatureVersion   int
	IndexMinReaderVersion int
	IndexTime             time.Time
	PlainASCII            bool
	LanguageMap           map[string]byte
	ZoektVersion          string
}

type LineFragmentMatch struct {
	// Offset within the line, in bytes.
	LineOffset int

	// Offset from file start, in bytes.
	Offset uint32

	// Number bytes that match.
	MatchLength int
}

type LineMatch struct {
	// The line in which a match was found.
	Line       []byte
	LineStart  int
	LineEnd    int
	LineNumber int

	// If set, this was a match on the filename.
	FileName bool

	// The higher the better. Only ranks the quality of the match
	// within the file, does not take rank of file into account
	Score         float64
	LineFragments []LineFragmentMatch
}

type RepoList struct {
	Repos   []*RepoListEntry
	Crashes int
}

type RepoListEntry struct {
	Repository    Repository
	IndexMetadata IndexMetadata
	Stats         RepoStats
}

type RepoStats struct {
	// Repos is used for aggregrating the number of repositories.
	Repos int

	// Shards is the total number of search shards.
	Shards int

	// Documents holds the number of documents or files.
	Documents int

	// IndexBytes is the amount of RAM used for index overhead.
	IndexBytes int64

	// ContentBytes is the amount of RAM used for raw content.
	ContentBytes int64
}

type Repository struct {
	// The repository name
	Name string

	// The repository URL.
	URL string

	// The physical source where this repo came from, eg. full
	// path to the zip filename or git repository directory. This
	// will not be exposed in the UI, but can be used to detect
	// orphaned index shards.
	Source string

	// The branches indexed in this repo.
	Branches []RepositoryBranch

	// Nil if this is not the super project.
	SubRepoMap map[string]*Repository

	// URL template to link to the commit of a branch
	CommitURLTemplate string

	// The repository URL for getting to a file.  Has access to
	// {{Branch}}, {{Path}}
	FileURLTemplate string

	// The URL fragment to add to a file URL for line numbers. has
	// access to {{LineNumber}}. The fragment should include the
	// separator, generally '#' or ';'.
	LineFragmentTemplate string

	// All zoekt.* configuration settings.
	RawConfig map[string]string

	// Importance of the repository, bigger is more important
	Rank uint16

	// IndexOptions is a hash of the options used to create the index for the
	// repo.
	IndexOptions string
}

type RepositoryBranch struct {
	Name    string
	Version string
}

type SearchOptions struct {
	// Return an upper-bound estimate of eligible documents in
	// stats.ShardFilesConsidered.
	EstimateDocCount bool

	// Return the whole file.
	Whole bool

	// Maximum number of matches: skip all processing an index
	// shard after we found this many non-overlapping matches.
	ShardMaxMatchCount int

	// Maximum number of matches: stop looking for more matches
	// once we have this many matches across shards.
	TotalMaxMatchCount int

	// Maximum number of important matches: skip processing
	// shard after we found this many important matches.
	ShardMaxImportantMatch int

	// Maximum number of important matches across shards.
	TotalMaxImportantMatch int

	// Abort the search after this much time has passed.
	MaxWallTime time.Duration

	// Trim the number of results after collating and sorting the
	// results
	MaxDocDisplayCount int
}

type SearchResult struct {
	Stats
	Files []FileMatch

	// RepoURLs holds a repo => template string map.
	RepoURLs map[string]string

	// FragmentNames holds a repo => template string map, for
	// the line number fragment.
	LineFragments map[string]string
}

type Searcher interface {
	Search(ctx context.Context, q query.Q, opts *SearchOptions) (*SearchResult, error)

	// List lists repositories. The query `q` can only contain
	// query.Repo atoms.
	List(ctx context.Context, q query.Q) (*RepoList, error)
	Close()

	// Describe the searcher for debug messages.
	String() string
}

type Stats struct {
	// Amount of I/O for reading contents.
	ContentBytesLoaded int64

	// Amount of I/O for reading from index.
	IndexBytesLoaded int64

	// Number of search shards that had a crash.
	Crashes int

	// Wall clock time for this search
	Duration time.Duration

	// Number of files containing a match.
	FileCount int

	// Number of files in shards that we considered.
	ShardFilesConsidered int

	// Files that we evaluated. Equivalent to files for which all
	// atom matches (including negations) evaluated to true.
	FilesConsidered int

	// Files for which we loaded file content to verify substring matches
	FilesLoaded int

	// Candidate files whose contents weren't examined because we
	// gathered enough matches.
	FilesSkipped int

	// Shards that we did not process because a query was canceled.
	ShardsSkipped int

	// Number of non-overlapping matches
	MatchCount int

	// Number of candidate matches as a result of searching ngrams.
	NgramMatches int

	// Wall clock time for queued search.
	Wait time.Duration

	// Number of times regexp was called on files that we evaluated.
	RegexpsConsidered int
}