Skip to content

Harvest: support dx.doi.org url and http protocol #8738

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
tcoupin wants to merge 1 commit into from
Closed

Harvest: support dx.doi.org url and http protocol #8738

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions src/main/java/edu/harvard/iq/dataverse/GlobalId.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,6 +28,7 @@ public class GlobalId implements java.io.Serializable {
public static final String HDL_PROTOCOL = "hdl";
public static final String HDL_RESOLVER_URL = "https://hdl.handle.net/";
public static final String DOI_RESOLVER_URL = "https://doi.org/";
public static final String DXDOI_RESOLVER_URL = "https://dx.doi.org/";

public static Optional<GlobalId> parse(String identifierString) {
try {
Expand Down
26 changes: 23 additions & 3 deletions src/main/java/edu/harvard/iq/dataverse/api/imports/ImportGenericServiceBean.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -348,7 +348,10 @@ private String getOtherIdFromDTO(DatasetVersionDTO datasetVersionDTO) {
if (!otherIds.isEmpty()) {
// We prefer doi or hdl identifiers like "doi:10.7910/DVN/1HE30F"
for (String otherId : otherIds) {
if (otherId.startsWith(GlobalId.DOI_PROTOCOL) || otherId.startsWith(GlobalId.HDL_PROTOCOL) || otherId.startsWith(GlobalId.DOI_RESOLVER_URL) || otherId.startsWith(GlobalId.HDL_RESOLVER_URL)) {
if (otherId.startsWith(GlobalId.DOI_PROTOCOL) || otherId.startsWith(GlobalId.HDL_PROTOCOL) ||
otherId.startsWith(GlobalId.DOI_RESOLVER_URL) || otherId.startsWith(GlobalId.HDL_RESOLVER_URL) || otherId.startsWith(GlobalId.DXDOI_RESOLVER_URL) ||
otherId.startsWith(GlobalId.DOI_RESOLVER_URL.replace("https","http")) || otherId.startsWith(GlobalId.HDL_RESOLVER_URL.replace("https","http")) || otherId.startsWith(GlobalId.DXDOI_RESOLVER_URL.replace("https","http"))
) {
return otherId;
}
}
Expand Down Expand Up @@ -389,15 +392,32 @@ public String reassignIdentifierAsGlobalId(String identifierString, DatasetDTO d

// We also recognize global identifiers formatted as global resolver URLs:

if (identifierString.startsWith(GlobalId.HDL_RESOLVER_URL)) {
if (identifierString.startsWith(GlobalId.HDL_RESOLVER_URL) || identifierString.startsWith(GlobalId.HDL_RESOLVER_URL.replace("https", "http"))) {
logger.fine("Processing Handle identifier formatted as a resolver URL: "+identifierString);
protocol = GlobalId.HDL_PROTOCOL;
index1 = GlobalId.HDL_RESOLVER_URL.length() - 1;
if (!identifierString.startsWith("https")){
// http
index1--;
}
index2 = identifierString.indexOf("/", index1 + 1);
} else if (identifierString.startsWith(GlobalId.DOI_RESOLVER_URL)) {
} else if (identifierString.startsWith(GlobalId.DOI_RESOLVER_URL) || identifierString.startsWith(GlobalId.DOI_RESOLVER_URL.replace("https", "http"))) {
logger.fine("Processing DOI identifier formatted as a resolver URL: "+identifierString);
protocol = GlobalId.DOI_PROTOCOL;
index1 = GlobalId.DOI_RESOLVER_URL.length() - 1;
if (!identifierString.startsWith("https")){
// http
index1--;
}
index2 = identifierString.indexOf("/", index1 + 1);
} else if (identifierString.startsWith(GlobalId.DXDOI_RESOLVER_URL) || identifierString.startsWith(GlobalId.DXDOI_RESOLVER_URL.replace("https", "http"))) {
logger.fine("Processing DOI identifier formatted as a resolver URL: "+identifierString);
protocol = GlobalId.DOI_PROTOCOL;
index1 = GlobalId.DXDOI_RESOLVER_URL.length() - 1;
if (!identifierString.startsWith("https")){
// http
index1--;
}
index2 = identifierString.indexOf("/", index1 + 1);
} else {
logger.warning("HTTP Url in supplied as the identifier is neither a Handle nor DOI resolver: "+identifierString);
Expand Down