crossref

Documentation

Overview

Copyright 2015 by Leipzig University Library, http://ub.uni-leipzig.de
                  The Finc Authors, http://finc.info
                  Martin Czygan, <martin.czygan@uni-leipzig.de>

This file is part of some open source application.

Some open source application is free software: you can redistribute it and/or modify it under the terms of the GNU General Public License as published by the Free Software Foundation, either version 3 of the License, or (at your option) any later version.

Some open source application is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details.

You should have received a copy of the GNU General Public License along with Foobar. If not, see <http://www.gnu.org/licenses/>.

@license GPL-3.0+ <http://spdx.org/licenses/GPL-3.0+>

Index

• Constants
• Variables
• type BulkResponse
• type DateField
  • func (d *DateField) Date() (t time.Time, err error)
• type DatePart
• type Document
  • func (doc *Document) Authors() (authors []finc.Author)
  • func (doc *Document) CombinedTitle() string
  • func (doc *Document) FindLanguages() []string
  • func (doc *Document) FindShortTitle() (s string)
  • func (doc *Document) ID() string
  • func (doc *Document) PageInfo() PageInfo
  • func (doc *Document) ToIntermediateSchema() (*finc.IntermediateSchema, error)
• type PageInfo
  • func (pi *PageInfo) PageCount() int

Constants

const (
	// Internal bookkeeping.
	SourceID = "49"
)

Variables

var (
	DefaultFormat = "ElectronicArticle"

	// Load assets
	Formats  = assetutil.MustLoadStringMap("assets/crossref/formats.json")
	Genres   = assetutil.MustLoadStringMap("assets/crossref/genres.json")
	RefTypes = assetutil.MustLoadStringMap("assets/crossref/reftypes.json")

	// AuthorReplacer is a special cleaner for author names.
	AuthorReplacer = strings.NewReplacer("#", "", "--", "", "*", "", "|", "", "&NA;", "", "\u0026NA;", "", "\u0026", "")

	// ArticleTitleBlocker will trigger skips, if article title matches exactly.
	ArticleTitleBlocker = []string{"Titelei", "Front Matter", "Advertisement", "Advertisement:"}

	// ArticleTitleCleanerPatterns removes matching parts.
	ArticleTitleCleanerPatterns = []*regexp.Regexp{

		regexp.MustCompile(`[?]{6,}`),
	}

	// Future ends soon.
	Future = time.Now().Add(time.Hour * 24 * 365 * 2)
)

Types

type BulkResponse

type BulkResponse struct {
	Status         string `json:"status"`
	MessageType    string `json:"message-type"`
	MessageVersion string `json:"message-version"`
	Message        struct {
		NextCursor   string     `json:"next-cursor"`
		TotalResults int        `json:"total-results"`
		Items        []Document `json:"items"`
	} `json:"message"`
}

BulkResponse for a bulk request containing multiple items.

type DateField

type DateField struct {
	DateParts []DatePart `json:"date-parts"`
	DateTime  string     `json:"date-time"`
	Timestamp int64      `json:"timestamp"`
}

DateField contains two representations of one value.

func (*DateField) Date

func (d *DateField) Date() (t time.Time, err error)

Date returns a time.Date in a best effort manner. Date parts seem to be always present in the source document, while timestamp is only present if dateparts consist of all three: year, month and day. It is an error, if no valid date can be extracted.

type DatePart

type DatePart []int

DatePart consists of up to three int, representing year, month, day.

type Document

type Document struct {
	Abstract string `json:"abstract"`
	Author   []struct {
		Family string `json:"family"`
		Given  string `json:"given"`
	} `json:"author"`
	ContainerTitle []string `json:"container-title"`
	ContentDomain  struct {
		CrossmarkRestriction bool          `json:"crossmark-restriction"`
		Domain               []interface{} `json:"domain"`
	} `json:"content-domain"`
	Created             DateField `json:"created"`
	DOI                 string
	Deposited           DateField `json:"deposited"`
	ISBN                []string
	ISSN                []string
	Indexed             DateField `json:"indexed"`
	IsReferencedByCount int64     `json:"is-referenced-by-count"`
	IsbnType            []struct {
		Type  string `json:"type"`
		Value string `json:"value"`
	} `json:"isbn-type"`
	IssnType []struct {
		Type  string `json:"type"`
		Value string `json:"value"`
	} `json:"issn-type"`
	Issue        string    `json:"issue"`
	Issued       DateField `json:"issued"`
	JournalIssue struct {
		Issue          string    `json:"issue"`
		PublishedPrint DateField `json:"published-print"`
	} `json:"journal-issue"`
	Language string `json:"language"`
	License  []struct {
		ContentVersion string    `json:"content-version"`
		DelayInDays    int64     `json:"delay-in-days"`
		Start          DateField `json:"start"`
		URL            string
	} `json:"license"`
	Link []struct {
		ContentType         string `json:"content-type"`
		ContentVersion      string `json:"content-version"`
		IntendedApplication string `json:"intended-application"`
		URL                 string
	} `json:"link"`
	Member          string        `json:"member"`
	OriginalTitle   []interface{} `json:"original-title"`
	Page            string        `json:"page"`
	Prefix          string        `json:"prefix"`
	PublishedPrint  DateField     `json:"published-print"`
	Publisher       string        `json:"publisher"`
	ReferenceCount  int64         `json:"reference-count"`
	ReferencesCount int64         `json:"references-count"`
	Relation        struct {
	} `json:"relation"`
	Score               float64     `json:"score"`
	ShortContainerTitle []string    `json:"short-container-title"`
	ShortTitle          interface{} `json:"short-title"`
	Source              string      `json:"source"`
	Subject             []string    `json:"subject"`
	Subtitle            []string    `json:"subtitle"`
	Title               []string    `json:"title"`
	Type                string      `json:"type"`
	URL                 string      `json:"URL"`
	Volume              string      `json:"volume"`
}

Document is an updated v1 crossref API message.

func (*Document) Authors

func (doc *Document) Authors() (authors []finc.Author)

func (*Document) CombinedTitle

func (doc *Document) CombinedTitle() string

CombinedTitle returns a longish title.

func (*Document) FindLanguages

func (doc *Document) FindLanguages() []string

FindLanguages tries to find language, falls back to English.

func (*Document) FindShortTitle

func (doc *Document) FindShortTitle() (s string)

FindShortTitle returns the first main title only.

func (*Document) ID

func (doc *Document) ID() string

ID is of the form <kind>-<source-id>-<id-base64-unpadded> We simple map any primary key of the source (preferably a URL) to a safer alphabet. Since the base64 part is not meant to be decoded we drop the padding. It is simple enough to recover the original value.

func (*Document) PageInfo

func (doc *Document) PageInfo() PageInfo

PageInfo parses a page specfication in a best effort manner into a PageInfo struct.

func (*Document) ToIntermediateSchema

func (doc *Document) ToIntermediateSchema() (*finc.IntermediateSchema, error)

ToIntermediateSchema converts a crossref document into IS. XXX: Use a canonical publisher, based on doi prefix, /cc @ad.

type PageInfo

type PageInfo struct {
	RawMessage string
	StartPage  int
	EndPage    int
}

PageInfo holds various page related data.

func (*PageInfo) PageCount

func (pi *PageInfo) PageCount() int

PageCount returns the number of pages, or zero if this cannot be determined.