alanorth/cgspace-java-helpers
1
0
Fork 0
mirror of https://github.com/ilri/cgspace-java-helpers.git synced 2024-11-26 16:48:22 +01:00
Code Issues Projects Releases Wiki Activity

CountryCodeTagger.java: Refactor adding of alpha2 codes

Browse Source 
We can append the codes we will add to a List of Strings and then
actually apply them later in one addMetadata call, and update the
item with one item.update() call. This reduces identical code and
is more efficient.

Note that when testing this on a collection with thousands of items
I realized that it is really important to limit both the cache size
as well as set the database transaction model to be per object/item
or else you will crash due to Java heap issues. For example:

    $ ~/dspace/bin/dspace curate -t countrycodetagger -i 10568/3 -r - -l 500 -s object

See: https://wiki.lyrasis.org/display/DSPACE/Curation+Task+Cookbook
This commit is contained in:
Alan Orth 2020-08-02 18:33:32 +03:00
parent 1c866bdf64
commit e158e4bc98
Signed by: alanorth
GPG Key ID: 0FB860CC9C45B1B9
1 changed files with 21 additions and 28 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

41
src/main/java/org/cgiar/cgspace/ctasks/CountryCodeTagger.java
View File

@ -126,46 +126,39 @@ public class CountryCodeTagger extends AbstractCurationTask
Metadatum[] itemAlpha2CountryCodes = item.getMetadataByMetadataString(config.iso3166Alpha2Field);
if (itemAlpha2CountryCodes.length == 0) {
int addedCodeCount = 0;
List<String> newAlpha2Codes = new ArrayList<String>();
for (Metadatum itemCountry : itemCountries) {
//check ISO 3166-1 countries
for (CountriesVocabulary.Country country : isocodesCountriesJson.countries) {
if (itemCountry.value.equalsIgnoreCase(country.getName()) || itemCountry.value.equalsIgnoreCase(country.get_official_name()) || itemCountry.value.equalsIgnoreCase(country.get_common_name())) {
try {
item.addMetadata(iso3166Alpha2FieldParts[0], iso3166Alpha2FieldParts[1], iso3166Alpha2FieldParts[2], "en_US", country.getAlpha_2());
item.update();
newAlpha2Codes.add(country.getAlpha_2());
}
}
addedCodeCount++;
alpha2Result.setResult(itemHandle + ": added " + addedCodeCount + " country code(s)");
alpha2Result.setStatus(Curator.CURATE_SUCCESS);
} catch (SQLException | AuthorizeException sqle) {
config.log.debug(sqle.getMessage());
alpha2Result.setResult(itemHandle + ": error");
alpha2Result.setStatus(Curator.CURATE_ERROR);
}
}
}
//check CGSpace countries
for (CountriesVocabulary.Country country : cgspaceCountriesJson.countries) {
if (itemCountry.value.equalsIgnoreCase(country.getCgspace_name())) {
newAlpha2Codes.add(country.getAlpha_2());
}
}
}
if (newAlpha2Codes.size() > 0) {
try {
// we have the field as a string, so we need to split/tokenize it here actually
item.addMetadata(iso3166Alpha2FieldParts[0], iso3166Alpha2FieldParts[1], iso3166Alpha2FieldParts[2], "en_US", country.getAlpha_2());
// add metadata values (casting the List<String> to an array)
item.addMetadata(iso3166Alpha2FieldParts[0], iso3166Alpha2FieldParts[1], iso3166Alpha2FieldParts[2], "en_US", newAlpha2Codes.toArray(new String[0]));
item.update();
addedCodeCount++;
alpha2Result.setResult(itemHandle + ": added " + addedCodeCount + " country code(s)");
alpha2Result.setStatus(Curator.CURATE_SUCCESS);
} catch (SQLException | AuthorizeException sqle) {
config.log.debug(sqle.getMessage());
alpha2Result.setResult(itemHandle + ": error");
alpha2Result.setStatus(Curator.CURATE_ERROR);
}
alpha2Result.setResult(itemHandle + ": added " + newAlpha2Codes.size() + " alpha2 country code(s)");
} else {
alpha2Result.setResult(itemHandle + ": no matching countries found");
}
}
}
alpha2Result.setStatus(Curator.CURATE_SUCCESS);
} else {
alpha2Result.setResult(itemHandle + ": item has country codes, skipping");
alpha2Result.setStatus(Curator.CURATE_SKIP);