database

type Dimension struct {
	ID            int       `json:"id"`
	Name          string    `json:"name"`
	DisplayName   string    `json:"display_name"`
	Description   string    `json:"description,omitempty"`
	DimensionType string    `json:"dimension_type"` // 'single' or 'multiple'
	IsRequired    bool      `json:"is_required"`
	CreatedAt     time.Time `json:"created_at"`
	UpdatedAt     time.Time `json:"updated_at"`
}

type DimensionValue struct {
	ID          int       `json:"id"`
	DimensionID int       `json:"dimension_id"`
	Value       string    `json:"value"`
	DisplayName string    `json:"display_name"`
	Description string    `json:"description,omitempty"`
	Color       string    `json:"color"`
	SortOrder   int       `json:"sort_order"`
	CreatedAt   time.Time `json:"created_at"`
	UpdatedAt   time.Time `json:"updated_at"`
}

type DimensionWithValues struct {
	Dimension
	Values []DimensionValue `json:"values"`
}

type Document struct {
	ID           int        `json:"id"`
	Name         string     `json:"name"`
	Path         string     `json:"path"` // full path to the file
	IngressTime  time.Time  `json:"ingress_time"`
	Folder       string     `json:"folder"`
	Hash         string     `json:"hash"`
	ULID         ulid.ULID  `json:"ulid"`          // Have a smaller (than hash) id that can be used in URL's, hopefully speed things up
	DocumentType string     `json:"document_type"` // type of document (pdf, txt, etc)
	FullText     string     `json:"full_text"`
	URL          string     `json:"url"`
	DocumentDate *time.Time `json:"document_date,omitempty"` // user-assigned document date (e.g. invoice date)
	CreatedDate  *time.Time `json:"created_date,omitempty"`  // original creation date from source
	UpdatedDate  *time.Time `json:"updated_date,omitempty"`  // original modification date from source
	Author       string     `json:"author,omitempty"`        // note author
	SourceURL    string     `json:"source_url,omitempty"`    // original source URL
	Source       string     `json:"source,omitempty"`        // source system (e.g. "evernote")
}

type DocumentDimension struct {
	ID               int       `json:"id"`
	DocumentID       int       `json:"document_id"`
	DimensionID      int       `json:"dimension_id"`
	DimensionValueID int       `json:"dimension_value_id"`
	CreatedAt        time.Time `json:"created_at"`
	UpdatedAt        time.Time `json:"updated_at"`
}

type DocumentMetadataUpdate struct {
	CreatedDate *time.Time `json:"created_date,omitempty"`
	UpdatedDate *time.Time `json:"updated_date,omitempty"`
	Author      *string    `json:"author,omitempty"`
	SourceURL   *string    `json:"source_url,omitempty"`
	Source      *string    `json:"source,omitempty"`
}

type DocumentTag struct {
	DocumentID int       `json:"document_id"`
	TagID      int       `json:"tag_id"`
	CreatedAt  time.Time `json:"created_at"`
}

type DocumentTagsAndDimensions struct {
	Tags      []string          `json:"tags"`                 // Free tags (no group)
	TagGroups map[string]string `json:"tag_groups,omitempty"` // group_name -> tag_name (one per group)
}

type DocumentWithTagsAndDimensions struct {
	Document
	Tags       []Tag                     `json:"tags"`
	Dimensions map[string]DimensionValue `json:"dimensions"` // dimension_name -> value
}

type EphemeralPostgresDB struct {
	*PGDB
	// contains filtered or unexported fields
}

type Job struct {
	ID          ulid.ULID  `json:"id"`
	Type        JobType    `json:"type"`
	Status      JobStatus  `json:"status"`
	Progress    int        `json:"progress"`         // 0-100
	CurrentStep string     `json:"currentStep"`      // Human-readable current step
	TotalSteps  int        `json:"totalSteps"`       // Total number of steps
	Message     string     `json:"message"`          // Status message
	Error       string     `json:"error,omitempty"`  // Error message if failed
	Result      string     `json:"result,omitempty"` // JSON result data
	CreatedAt   time.Time  `json:"createdAt"`
	UpdatedAt   time.Time  `json:"updatedAt"`
	StartedAt   *time.Time `json:"startedAt,omitempty"`
	CompletedAt *time.Time `json:"completedAt,omitempty"`
}

type JobStatus string

type JobSummary struct {
	FilesProcessed int    `json:"filesProcessed"`
	FilesTotal     int    `json:"filesTotal"`
	BytesProcessed int64  `json:"bytesProcessed"`
	Errors         int    `json:"errors"`
	Details        string `json:"details,omitempty"`
}

type JobType string

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

type ParsedSearch struct {
	TextTerms   string     // Free text to search for
	IncludeTags []string   // Tags to include (prefixed with #)
	ExcludeTags []string   // Tags to exclude (prefixed with ~)
	IsUntagged  bool       // Special: show only untagged documents
	IsTagged    bool       // Special: show only tagged documents
	IsAllDocs   bool       // Special: show all documents
	AfterDate   *time.Time // Filter: document_date >= this (inclusive)
	BeforeDate  *time.Time // Filter: document_date <= this (inclusive)
}

type Repository interface {
	Close() error
	SaveDocument(doc *Document) error
	GetDocumentByID(id int) (*Document, error)
	GetDocumentByULID(ulid string) (*Document, error)
	GetDocumentByPath(path string) (*Document, error)
	GetDocumentByHash(hash string) (*Document, error)
	GetNewestDocuments(limit int) ([]Document, error)
	GetNewestDocumentsWithPagination(page int, pageSize int, showHidden ...bool) ([]Document, int, error)
	GetAllDocuments() ([]Document, error)
	GetDocumentsByFolder(folder string) ([]Document, error)
	DeleteDocument(ulid string) error
	UpdateDocumentURL(ulid string, url string) error
	UpdateDocumentPath(ulid string, path string, folder string) error
	UpdateDocumentFolder(ulid string, folder string) error
	UpdateDocumentDate(ulid string, date *time.Time) error
	UpdateDocumentFullText(ulid string, text string) error
	SaveConfig(config *config.ServerConfig) error
	GetConfig() (*config.ServerConfig, error)
	SearchDocuments(searchTerm string) ([]Document, error)
	ReindexSearchDocuments() (int, error)
	// Word cloud methods
	GetTopWords(limit int) ([]WordFrequency, error)
	GetWordCloudMetadata() (*WordCloudMetadata, error)
	RecalculateAllWordFrequencies() error
	UpdateWordFrequencies(docID string) error
	// Job tracking methods
	CreateJob(jobType JobType, message string) (*Job, error)
	UpdateJobProgress(jobID ulid.ULID, progress int, currentStep string) error
	UpdateJobStatus(jobID ulid.ULID, status JobStatus, message string) error
	UpdateJobError(jobID ulid.ULID, errorMsg string) error
	CompleteJob(jobID ulid.ULID, result string) error
	GetJob(jobID ulid.ULID) (*Job, error)
	GetRecentJobs(limit, offset int) ([]Job, error)
	GetActiveJobs() ([]Job, error)
	DeleteOldJobs(olderThan time.Duration) (int, error)
	// Tag methods
	CreateTag(tag *Tag) error
	GetAllTags() ([]Tag, error)
	GetTagByID(id int) (*Tag, error)
	GetTagByName(name string) (*Tag, error)
	UpdateTag(tag *Tag) error
	DeleteTag(id int) error
	GetTagsForDocument(documentID int) ([]Tag, error)
	AddTagToDocument(documentID int, tagID int) error
	RemoveTagFromDocument(documentID int, tagID int) error
	GetTagUsageCount(tagID int) (int, error)
	GetTagGroups() ([]string, error)
	// Dimension methods
	GetAllDimensions() ([]Dimension, error)
	GetDimensionByID(id int) (*Dimension, error)
	GetDimensionByName(name string) (*Dimension, error)
	GetDimensionValues(dimensionID int) ([]DimensionValue, error)
	GetDimensionValueByValue(dimensionID int, value string) (*DimensionValue, error)
	GetDocumentDimensions(documentID int) (map[string]DimensionValue, error)
	SetDocumentDimension(documentID int, dimensionID int, dimensionValueID int) error
	RemoveDocumentDimension(documentID int, dimensionID int) error
	// Schema version
	GetSchemaVersion() (string, error)
	// Saved search methods
	GetAllSavedSearches() ([]SavedSearch, error)
	GetSavedSearchByID(id int) (*SavedSearch, error)
	CreateSavedSearch(search *SavedSearch) error
	UpdateSavedSearch(search *SavedSearch) error
	DeleteSavedSearch(id int) error
	// Search execution methods
	GetDocumentsByTag(tagID int, page, pageSize int, showHidden ...bool) ([]Document, int, error)
	GetUntaggedDocuments(page, pageSize int, showHidden ...bool) ([]Document, int, error)
	GetTaggedDocuments(page, pageSize int, showHidden ...bool) ([]Document, int, error)
	ExecuteSearch(parsed *ParsedSearch, page, pageSize int, showHidden ...bool) ([]Document, int, error)
	// Story methods
	CreateStory(story *Story) error
	GetStoryByID(id int) (*Story, error)
	GetAllStories() ([]Story, error)
	GetStoriesWithMeta() ([]StoryWithMeta, error)
	UpdateStory(story *Story) error
	DeleteStory(id int) error
	GetStoryByTagID(tagID int) (*Story, error)
	GetStoryTags(storyID int) ([]Tag, error)
	AddStoryTag(storyID int, tagID int) error
	RemoveStoryTag(storyID int, tagID int) error
	AddDocumentToStory(documentID int, storyID int) error
	RemoveDocumentFromStory(documentID int, storyID int) error
	GetDocumentsWithoutStory(page, pageSize int, showHidden ...bool) ([]Document, int, error)
	UpdateDocumentMetadata(ulid string, meta DocumentMetadataUpdate) error
	ConvertTagToStory(tagID int) (*Story, error)
	ConvertStoryToTag(storyID int) error
}

type SavedSearch struct {
	ID          int       `json:"id"`
	Name        string    `json:"name"`
	Description string    `json:"description"`
	Query       string    `json:"query"`      // Unified search query (text #tag ~exclude)
	Icon        string    `json:"icon"`       // Emoji icon
	SortOrder   int       `json:"sort_order"` // Display order
	IsSystem    bool      `json:"is_system"`  // True for built-in searches
	CreatedAt   time.Time `json:"created_at"`
	UpdatedAt   time.Time `json:"updated_at"`
}

type SavedSearchWithCount struct {
	SavedSearch
	DocumentCount int `json:"document_count"`
}

type SearchResult struct {
	Document
	MatchScore float64 `json:"match_score,omitempty"`
}

type Story struct {
	ID          int        `json:"id"`
	Title       string     `json:"title"`
	Description string     `json:"description"`
	StartDate   *time.Time `json:"start_date,omitempty"`
	EndDate     *time.Time `json:"end_date,omitempty"`
	TagID       int        `json:"tag_id"` // references the story's own tag
	CreatedAt   time.Time  `json:"created_at"`
	UpdatedAt   time.Time  `json:"updated_at"`
}

type StoryWithMeta struct {
	Story
	Tag            Tag   // The story's own tag (has color, name etc.)
	AssociatedTags []Tag // Tags from story_tags junction
	DocumentCount  int
	StartDateFmt   string // Pre-formatted "2006-01-02" for templates (avoids *time.Time filter issues)
	EndDateFmt     string
}

type Tag struct {
	ID          int       `json:"id"`
	Name        string    `json:"name"`
	Color       string    `json:"color"`
	Description string    `json:"description,omitempty"`
	TagGroup    *string   `json:"tag_group,omitempty"`
	SortOrder   int       `json:"sort_order"`
	CreatedAt   time.Time `json:"created_at"`
	UpdatedAt   time.Time `json:"updated_at"`
}

type TagWithCount struct {
	Tag
	DocumentCount int `json:"document_count" db:"document_count"`
}

type WordCloudMetadata struct {
	LastCalculation    time.Time `json:"lastCalculation"`
	TotalDocsProcessed int       `json:"totalDocsProcessed"`
	TotalWordsIndexed  int       `json:"totalWordsIndexed"`
	Version            int       `json:"version"`
}

type WordFrequency struct {
	Word      string    `json:"word"`
	Frequency int       `json:"frequency"`
	Updated   time.Time `json:"updated"`
}

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