Versions in this module Expand all Collapse all v0 v0.3.0 Mar 22, 2024 Changes in this version + const APILimit + const WikidataReference + const WikimediaCommonsCategoryReference + const WikimediaCommonsEntityReference + const WikimediaCommonsFileReference + const WikimediaCommonsTemplateReference + const WikipediaCategoryReference + const WikipediaTemplateReference + var ErrNotFound = errors.Base("not found") + var ErrSilentSkipped = errors.BaseWrap(ErrSkipped, "silent skipped") + var ErrSkipped = errors.Base("skipped") + var ErrWikimediaCommonsFile = errors.Base("file is from Wikimedia Commons error") + var NameSpaceWikidata = uuid.MustParse("8f8ba777-bcce-4e45-8dd4-a328e6722c82") + var NameSpaceWikimediaCommonsFile = uuid.MustParse("31974ea8-ab0c-466d-9aaa-e1bf3c959edc") + var NameSpaceWikipediaFile = uuid.MustParse("94b1c372-bc28-454c-a45a-2e4d29d15146") + func ConvertArticleInCategories(logger zerolog.Logger, namespace uuid.UUID, mnemonicPrefix, id string, ...) errors.E + func ConvertArticleRedirects(logger zerolog.Logger, namespace uuid.UUID, id string, ...) errors.E + func ConvertArticleUsedTemplates(logger zerolog.Logger, namespace uuid.UUID, mnemonicPrefix, id string, ...) errors.E + func ConvertCategoryDescription(id, from, html string, doc *peerdb.Document) errors.E + func ConvertEntity(ctx context.Context, index string, logger zerolog.Logger, ...) (*peerdb.Document, errors.E) + func ConvertFileDescription(namespace uuid.UUID, id, from, html string, doc *peerdb.Document) errors.E + func ConvertPageInCategories(logger zerolog.Logger, namespace uuid.UUID, mnemonicPrefix, id string, ...) errors.E + func ConvertPageRedirects(logger zerolog.Logger, namespace uuid.UUID, id string, page AllPagesPage, ...) errors.E + func ConvertPageUsedTemplates(logger zerolog.Logger, namespace uuid.UUID, mnemonicPrefix, id string, ...) errors.E + func ConvertTemplateDescription(id, from string, html string, doc *peerdb.Document) errors.E + func ConvertWikimediaCommonsImage(ctx context.Context, logger zerolog.Logger, httpClient *retryablehttp.Client, ...) (*peerdb.Document, errors.E) + func ConvertWikipediaArticle(id, html string, doc *peerdb.Document) errors.E + func ConvertWikipediaImage(ctx context.Context, logger zerolog.Logger, httpClient *retryablehttp.Client, ...) (*peerdb.Document, errors.E) + func ExtractArticle(input string) (string, *goquery.Document, errors.E) + func ExtractArticleSummary(doc *goquery.Document) (string, errors.E) + func ExtractCategoryDescription(input string) (string, errors.E) + func ExtractFileDescriptions(input string) ([]string, errors.E) + func ExtractTemplateDescription(input string) (string, errors.E) + func FirstUpperCase(str string) string + func GetMediawikiFilePrefix(filename string) string + func GetPageHTML(ctx context.Context, httpClient *retryablehttp.Client, site, title string) (string, errors.E) + func GetWikidataDocumentID(id string) identifier.Identifier + func GetWikidataItem(ctx context.Context, index string, esClient *elastic.Client, id string) (*peerdb.Document, *elastic.SearchHit, errors.E) + func GetWikimediaCommonsFile(ctx context.Context, index string, esClient *elastic.Client, name string) (*peerdb.Document, *elastic.SearchHit, errors.E) + func GetWikipediaFile(ctx context.Context, index string, esClient *elastic.Client, name string) (*peerdb.Document, *elastic.SearchHit, errors.E) + func ListAllPages(ctx context.Context, httpClient *retryablehttp.Client, namespaces []int, ...) errors.E + func SetPageID(namespace uuid.UUID, mnemonicPrefix string, id string, pageID int64, ...) errors.E + func UpdateEmbeddedDocuments(ctx context.Context, index string, logger zerolog.Logger, ...) (bool, errors.E) + type AllPagesPage struct + Categories []PageReference + Identifier int64 + Namespace int + Properties map[string]string + Redirects []PageReference + Templates []PageReference + Title string + type Image struct + ActorID int64 + Bits int64 + DescriptionID int64 + Height int64 + MajorMIME string + MediaType string + Metadata map[string]interface{} + MinorMIME string + Name string + SHA1 string + Size int64 + Timestamp time.Time + Width int64 + func (i *Image) UnmarshalJSON(b []byte) error + type ImageInfo struct + DescriptionShortURL string + DescriptionURL string + Duration float64 + Height int + Mime string + PageCount int + Redirect string + Size int + URL string + Width int + func GetImageInfo(ctx context.Context, httpClient *retryablehttp.Client, site, token string, ...) (ImageInfo, errors.E) + type PageReference struct + Identifier int64 + Namespace int + Title string