storage

package
v0.0.0-...-25d9ce1 Latest Latest
Warning

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

 Go to latest Published: Aug 25, 2026 License: MIT Imports: 8 Imported by: 0

Documentation

Index

Constants

This section is empty.

Variables

This section is empty.

Functions

func CalculateResourcePaths 

func CalculateResourcePaths(docID string, parsedItem *models.ParsedItem) []string

CalculateResourcePaths generates all available resource URIs for a parsed document. Returns a slice of resource paths based on the content available in the parsed item.

func GenerateDocumentID 

func GenerateDocumentID(sourceInfo *models.SourceInfo, documentData models.DocumentData) string

GenerateDocumentID creates a unique document ID from source info and document data. This function can be called before parsing to check if a document already exists. Priority: Zotero ID > URL hash > document data hash

Types

type SQLiteStore 

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

SQLiteStore implements the Store interface using SQLite

func NewSQLiteStore 

func NewSQLiteStore(dbPath string, log logger.Logger) (*SQLiteStore, error)

NewSQLiteStore creates a new SQLite store

func (*SQLiteStore) Close 

func (s *SQLiteStore) Close() error

Close closes the database connection

func (*SQLiteStore) DeleteDocument 

func (s *SQLiteStore) DeleteDocument(ctx context.Context, docID string) error

DeleteDocument removes a document and all associated data

func (*SQLiteStore) DocumentExists 

func (s *SQLiteStore) DocumentExists(ctx context.Context, docID string) (bool, error)

DocumentExists checks if a document with the given ID already exists

func (*SQLiteStore) GetCitekeyMap 

func (s *SQLiteStore) GetCitekeyMap(ctx context.Context) (map[string]string, error)

GetCitekeyMap retrieves all docID→citekey mappings

func (*SQLiteStore) GetDocumentByCitekey 

func (s *SQLiteStore) GetDocumentByCitekey(ctx context.Context, citekey string) (string, error)

GetDocumentByCitekey retrieves a document ID by its citekey

func (*SQLiteStore) GetEndnote 

func (s *SQLiteStore) GetEndnote(ctx context.Context, docID string, endnoteIndex int) (*models.Endnote, error)

GetEndnote retrieves a specific endnote by index (0-indexed)

func (*SQLiteStore) GetEndnotes 

func (s *SQLiteStore) GetEndnotes(ctx context.Context, docID string) ([]models.Endnote, error)

GetEndnotes retrieves all endnotes for a document

func (*SQLiteStore) GetFootnote 

func (s *SQLiteStore) GetFootnote(ctx context.Context, docID string, footnoteIndex int) (*models.Footnote, error)

GetFootnote retrieves a specific footnote by index (0-indexed)

func (*SQLiteStore) GetFootnotes 

func (s *SQLiteStore) GetFootnotes(ctx context.Context, docID string) ([]models.Footnote, error)

GetFootnotes retrieves all footnotes for a document

func (*SQLiteStore) GetImage 

func (s *SQLiteStore) GetImage(ctx context.Context, docID string, imageIndex int) (*models.Image, error)

GetImage retrieves a specific image by index (0-indexed)

func (*SQLiteStore) GetImages 

func (s *SQLiteStore) GetImages(ctx context.Context, docID string) ([]models.Image, error)

GetImages retrieves all images for a document

func (*SQLiteStore) GetMetadata 

func (s *SQLiteStore) GetMetadata(ctx context.Context, docID string) (*models.ItemMetadata, error)

GetMetadata retrieves metadata for a document by ID

func (*SQLiteStore) GetPage 

func (s *SQLiteStore) GetPage(ctx context.Context, docID string, pageNum int) (string, error)

GetPage retrieves a specific page by document ID and page number (1-indexed sequential)

func (*SQLiteStore) GetPageBySourceNumber 

func (s *SQLiteStore) GetPageBySourceNumber(ctx context.Context, docID string, sourcePageNum string) (string, error)

GetPageBySourceNumber retrieves a page by its source page number (e.g., "125", "iv")

func (*SQLiteStore) GetPageMapping 

func (s *SQLiteStore) GetPageMapping(ctx context.Context, docID string) (map[string]int, error)

GetPageMapping returns a map of source page numbers to sequential page numbers

func (*SQLiteStore) GetPages 

func (s *SQLiteStore) GetPages(ctx context.Context, docID string) ([]string, error)

GetPages retrieves all pages for a document

func (*SQLiteStore) GetParsedItem 

func (s *SQLiteStore) GetParsedItem(ctx context.Context, docID string) (*models.ParsedItem, error)

GetParsedItem retrieves a complete ParsedItem for a document by ID

func (*SQLiteStore) GetQuotation 

func (s *SQLiteStore) GetQuotation(ctx context.Context, docID string, quotationIndex int) (*models.Quotation, error)

GetQuotation retrieves a specific quotation by index (0-indexed)

func (*SQLiteStore) GetQuotations 

func (s *SQLiteStore) GetQuotations(ctx context.Context, docID string) ([]models.Quotation, error)

GetQuotations retrieves all quotations for a document

func (*SQLiteStore) GetReference 

func (s *SQLiteStore) GetReference(ctx context.Context, docID string, refIndex int) (*models.Reference, error)

GetReference retrieves a specific reference by index (0-indexed)

func (*SQLiteStore) GetReferences 

func (s *SQLiteStore) GetReferences(ctx context.Context, docID string) ([]models.Reference, error)

GetReferences retrieves all references for a document

func (*SQLiteStore) GetSummary 

func (s *SQLiteStore) GetSummary(ctx context.Context, docID string) (string, error)

GetSummary retrieves the summary for a document by ID

func (*SQLiteStore) GetTable 

func (s *SQLiteStore) GetTable(ctx context.Context, docID string, tableIndex int) (*models.Table, error)

GetTable retrieves a specific table by index (0-indexed)

func (*SQLiteStore) GetTables 

func (s *SQLiteStore) GetTables(ctx context.Context, docID string) ([]models.Table, error)

GetTables retrieves all tables for a document

func (*SQLiteStore) ListDocuments 

func (s *SQLiteStore) ListDocuments(ctx context.Context) ([]models.DocumentInfo, error)

ListDocuments returns a list of all stored document IDs with their metadata

func (*SQLiteStore) StoreParsedItem 

func (s *SQLiteStore) StoreParsedItem(ctx context.Context, docID string, item *models.ParsedItem, sourceInfo *models.SourceInfo) error

StoreParsedItem stores a parsed PDF with the provided document ID

type Store 

type Store interface {
	// StoreParsedItem stores a parsed PDF with the provided document ID
	StoreParsedItem(ctx context.Context, docID string, item *models.ParsedItem, sourceInfo *models.SourceInfo) error

	// GetMetadata retrieves metadata for a document by ID
	GetMetadata(ctx context.Context, docID string) (*models.ItemMetadata, error)

	// GetPage retrieves a specific page by document ID and page number (1-indexed sequential)
	GetPage(ctx context.Context, docID string, pageNum int) (string, error)

	// GetPageBySourceNumber retrieves a page by its source page number (e.g., "125", "iv")
	GetPageBySourceNumber(ctx context.Context, docID string, sourcePageNum string) (string, error)

	// GetPages retrieves all pages for a document
	GetPages(ctx context.Context, docID string) ([]string, error)

	// GetPageMapping returns a map of source page numbers to sequential page numbers
	GetPageMapping(ctx context.Context, docID string) (map[string]int, error)

	// GetReferences retrieves all references for a document
	GetReferences(ctx context.Context, docID string) ([]models.Reference, error)

	// GetReference retrieves a specific reference by index (0-indexed)
	GetReference(ctx context.Context, docID string, refIndex int) (*models.Reference, error)

	// GetImages retrieves all images for a document
	GetImages(ctx context.Context, docID string) ([]models.Image, error)

	// GetImage retrieves a specific image by index (0-indexed)
	GetImage(ctx context.Context, docID string, imageIndex int) (*models.Image, error)

	// GetTables retrieves all tables for a document
	GetTables(ctx context.Context, docID string) ([]models.Table, error)

	// GetTable retrieves a specific table by index (0-indexed)
	GetTable(ctx context.Context, docID string, tableIndex int) (*models.Table, error)

	// GetFootnotes retrieves all footnotes for a document
	GetFootnotes(ctx context.Context, docID string) ([]models.Footnote, error)

	// GetFootnote retrieves a specific footnote by index (0-indexed)
	GetFootnote(ctx context.Context, docID string, footnoteIndex int) (*models.Footnote, error)

	// GetEndnotes retrieves all endnotes for a document
	GetEndnotes(ctx context.Context, docID string) ([]models.Endnote, error)

	// GetEndnote retrieves a specific endnote by index (0-indexed)
	GetEndnote(ctx context.Context, docID string, endnoteIndex int) (*models.Endnote, error)

	// GetQuotations retrieves all quotations for a document
	GetQuotations(ctx context.Context, docID string) ([]models.Quotation, error)

	// GetQuotation retrieves a specific quotation by index (0-indexed)
	GetQuotation(ctx context.Context, docID string, quotationIndex int) (*models.Quotation, error)

	// ListDocuments returns a list of all stored document IDs with their metadata
	ListDocuments(ctx context.Context) ([]models.DocumentInfo, error)

	// DeleteDocument removes a document and all associated data
	DeleteDocument(ctx context.Context, docID string) error

	// DocumentExists checks if a document with the given ID already exists
	DocumentExists(ctx context.Context, docID string) (bool, error)

	// GetParsedItem retrieves a complete ParsedItem for a document by ID
	GetParsedItem(ctx context.Context, docID string) (*models.ParsedItem, error)

	// GetCitekeyMap retrieves all docID→citekey mappings
	GetCitekeyMap(ctx context.Context) (map[string]string, error)

	// GetDocumentByCitekey retrieves a document ID by its citekey
	GetDocumentByCitekey(ctx context.Context, citekey string) (string, error)

	// Close closes the database connection
	Close() error
}

Store defines the interface for storing and retrieving parsed PDF data

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.