documents

Documentation

Overview

Copyright 2025 National Technology and Engineering Solutions of Sandia SPDX-License-Identifier: BSD-3-Clause

Copyright 2025 National Technology and Engineering Solutions of Sandia SPDX-License-Identifier: BSD-3-Clause

Copyright 2025 National Technology and Engineering Solutions of Sandia SPDX-License-Identifier: BSD-3-Clause

Copyright 2025 National Technology and Engineering Solutions of Sandia SPDX-License-Identifier: BSD-3-Clause

Index

• func PDFPageCount(pdf []byte) (int, error)
• func PDFSlicePages(pdf []byte, startPage, endPage int) ([]byte, error)
• type Bibliography
  • func (b *Bibliography) Content() (string, error)
• type EntryFromBibliographyExtractor
• type EntryFromRawExtractor
• type MetaExtractor
• type Metadata
  • func (m *Metadata) ToString() string

Functions

func PDFPageCount

func PDFPageCount(pdf []byte) (int, error)

func PDFSlicePages

func PDFSlicePages(pdf []byte, startPage, endPage int) ([]byte, error)

Types

type Bibliography

type Bibliography struct {
	PDF       []byte
	Text      string
	StartPage int
	EndPage   int
}

func (*Bibliography) Content

func (b *Bibliography) Content() (string, error)

type EntryFromBibliographyExtractor

type EntryFromBibliographyExtractor interface {
	// Retrieve bib entry `id` from a prepared bibliography artifact.
	EntryFromBibliography(b *Bibliography, id int) (string, error)
}

type EntryFromRawExtractor

type EntryFromRawExtractor interface {
	// Retrieve bib entry `id` from `b64` base-64 encoded PDF file
	EntryFromRaw(b64 string, id int) (string, error)
}

type MetaExtractor

type MetaExtractor interface {
	PDFMetadata(content []byte) (*Metadata, error)
	HTMLMetadata(content []byte) (*Metadata, error)
}

type Metadata

type Metadata struct {
	Title           string   `json:"title"`
	Authors         []string `json:"authors"`
	PublicationDate string   `json:"publication_date"`
}

func (*Metadata) ToString

func (m *Metadata) ToString() string