1 package jalview.ws.dbsources;
3 import jalview.ws.uimodel.PDBRestRequest;
4 import jalview.ws.uimodel.PDBRestResponse;
5 import jalview.ws.uimodel.PDBRestResponse.PDBResponseSummary;
7 import java.util.ArrayList;
8 import java.util.Collection;
9 import java.util.Iterator;
10 import java.util.List;
12 import javax.ws.rs.core.MediaType;
14 import org.json.simple.JSONArray;
15 import org.json.simple.JSONObject;
16 import org.json.simple.parser.JSONParser;
17 import org.json.simple.parser.ParseException;
19 import com.sun.jersey.api.client.Client;
20 import com.sun.jersey.api.client.ClientResponse;
21 import com.sun.jersey.api.client.WebResource;
22 import com.sun.jersey.api.client.config.ClientConfig;
23 import com.sun.jersey.api.client.config.DefaultClientConfig;
27 * A rest client for querying the Search endpoing of the PDB REST API
32 public class PDBRestClient
34 public static final String PDB_SEARCH_ENDPOINT = "http://www.ebi.ac.uk/pdbe/search/pdb/select?";
36 private static int DEFAULT_RESPONSE_SIZE = 200;
39 * Takes a PDBRestRequest object and returns a response upon execution
41 * @param pdbRestRequest
42 * the PDBRestRequest instance to be processed
43 * @return the pdbResponse object for the given request
46 public PDBRestResponse executeRequest(PDBRestRequest pdbRestRequest)
51 ClientConfig clientConfig = new DefaultClientConfig();
52 Client client = Client.create(clientConfig);
54 String wantedFields = getPDBDocFieldsAsCommaDelimitedString(pdbRestRequest
56 int responseSize = (pdbRestRequest.getResponseSize() == 0) ? DEFAULT_RESPONSE_SIZE
57 : pdbRestRequest.getResponseSize();
58 String sortParam = (pdbRestRequest.getFieldToSortBy() == null || pdbRestRequest
59 .getFieldToSortBy().trim().isEmpty()) ? "" : (pdbRestRequest
60 .getFieldToSortBy() + (pdbRestRequest.isAscending() ? " asc"
62 // Build request parameters for the REST Request
63 WebResource webResource = client.resource(PDB_SEARCH_ENDPOINT)
64 .queryParam("wt", "json").queryParam("fl", wantedFields)
65 .queryParam("rows", String.valueOf(responseSize))
66 .queryParam("q", pdbRestRequest.getQuery())
67 .queryParam("sort", sortParam);
69 // Execute the REST request
70 ClientResponse clientResponse = webResource.accept(
71 MediaType.APPLICATION_JSON).get(ClientResponse.class);
73 // Get the JSON string from the response object
74 String responseString = clientResponse.getEntity(String.class);
76 // Check the response status and report exception if one occurs
77 if (clientResponse.getStatus() != 200)
79 String errorMessage = "";
80 if (clientResponse.getStatus() == 400)
82 errorMessage = parseJsonExceptionString(responseString);
83 throw new Exception(errorMessage);
87 errorMessage = getMessageByHTTPStatusCode(clientResponse
89 throw new Exception(errorMessage);
93 // Make redundant objects eligible for garbage collection to conserve
95 clientResponse = null;
98 // Process the response and return the result to the caller.
99 return parsePDBJsonResponse(responseString, pdbRestRequest);
100 } catch (Exception e)
102 String exceptionMsg = e.getMessage();
103 if (exceptionMsg.contains("SocketException"))
106 "Jalview is unable to detect an internet connection");
107 // No internet connection
109 else if (exceptionMsg.contains("UnknownHostException"))
112 "Jalview is unable to reach the host server \'www.ebi.ac.uk\'. "
113 + "\nPlease ensure that you are connected to the internet and try again.");
114 // The server 'www.ebi.ac.uk' is unreachable
123 public String getMessageByHTTPStatusCode(int code)
129 message = "PDB Rest Service no longer exists!";
133 message = "The requested resource could not be found";
143 message = "There seems to be an error from the PDB Rest API server.";
153 * Process error response from PDB server if/when one occurs.
155 * @param jsonResponse
156 * the JSON string containing error message from the server
157 * @return the processed error message from the JSON string
159 public static String parseJsonExceptionString(String jsonErrorResponse)
161 StringBuilder errorMessage = new StringBuilder(
162 "\n============= PDB Rest Client RunTime error =============\n");
166 JSONParser jsonParser = new JSONParser();
167 JSONObject jsonObj = (JSONObject) jsonParser.parse(jsonErrorResponse);
168 JSONObject errorResponse = (JSONObject) jsonObj.get("error");
170 JSONObject responseHeader = (JSONObject) jsonObj
171 .get("responseHeader");
172 JSONObject paramsObj = (JSONObject) responseHeader.get("params");
173 String status = responseHeader.get("status").toString();
174 String message = errorResponse.get("msg").toString();
175 String query = paramsObj.get("q").toString();
176 String fl = paramsObj.get("fl").toString();
178 errorMessage.append("Status: ").append(status).append("\n");
179 errorMessage.append("Message: ").append(message).append("\n");
180 errorMessage.append("query: ").append(query).append("\n");
181 errorMessage.append("fl: ").append(fl).append("\n");
183 } catch (ParseException e)
187 return errorMessage.toString();
191 * Parses the JSON response string from PDB REST API. The response is dynamic
192 * hence, only fields specifically requested for in the 'wantedFields'
193 * parameter is fetched/processed
195 * @param pdbJsonResponseString
196 * the JSON string to be parsed
197 * @param pdbRestRequest
198 * the request object which contains parameters used to process the
202 @SuppressWarnings("unchecked")
203 public static PDBRestResponse parsePDBJsonResponse(
204 String pdbJsonResponseString, PDBRestRequest pdbRestRequest)
206 PDBRestResponse searchResult = new PDBRestResponse();
207 List<PDBResponseSummary> result = null;
210 JSONParser jsonParser = new JSONParser();
211 JSONObject jsonObj = (JSONObject) jsonParser
212 .parse(pdbJsonResponseString);
214 JSONObject pdbResponse = (JSONObject) jsonObj.get("response");
215 String queryTime = ((JSONObject) jsonObj.get("responseHeader")).get(
217 int numFound = Integer
218 .valueOf(pdbResponse.get("numFound").toString());
221 result = new ArrayList<PDBResponseSummary>();
222 JSONArray docs = (JSONArray) pdbResponse.get("docs");
223 for (Iterator<JSONObject> docIter = docs.iterator(); docIter
226 JSONObject doc = docIter.next();
227 result.add(searchResult.new PDBResponseSummary(doc,
230 searchResult.setNumberOfItemsFound(numFound);
231 searchResult.setResponseTime(queryTime);
232 searchResult.setSearchSummary(result);
234 } catch (ParseException e)
242 * Takes a collection of PDBDocField and converts its 'code' Field values into
243 * a comma delimited string.
245 * @param pdbDocfields
246 * the collection of PDBDocField to process
247 * @return the comma delimited string from the pdbDocFields collection
249 public static String getPDBDocFieldsAsCommaDelimitedString(
250 Collection<PDBDocField> pdbDocfields)
253 if (pdbDocfields != null && !pdbDocfields.isEmpty())
255 StringBuilder returnedFields = new StringBuilder();
256 for (PDBDocField field : pdbDocfields)
258 returnedFields.append(",").append(field.getCode());
260 returnedFields.deleteCharAt(0);
261 result = returnedFields.toString();
267 * Determines the column index for 'PDB Id' Fields in the dynamic summary
268 * table. The PDB Id serves as a unique identifier for a given row in the
271 * @param wantedFields
272 * the available table columns in no particular order
273 * @return the pdb id field column index
275 public static int getPDBIdColumIndex(
276 Collection<PDBDocField> wantedFields, boolean hasRefSeq)
279 // If a reference sequence is attached then start counting from 1 else
281 int pdbFieldIndexCounter = hasRefSeq ? 1 : 0;
283 for (PDBDocField field : wantedFields)
285 if (field.equals(PDBDocField.PDB_ID))
287 break; // Once PDB Id index is determined exit iteration
289 ++pdbFieldIndexCounter;
291 return pdbFieldIndexCounter;
295 * This enum represents the fields available in the PDB JSON response
298 public enum PDBDocField
300 PDB_ID("PDB Id", "pdb_id"), TITLE("Title", "title"), MOLECULE_NAME(
301 "Molecule", "molecule_name"), MOLECULE_TYPE("Molecule Type",
302 "molecule_type"), MOLECULE_SEQUENCE("Sequence",
303 "molecule_sequence"), PFAM_ACCESSION("PFAM Accession",
304 "pfam_accession"), PFAM_NAME("PFAM Name", "pfam_name"), INTERPRO_NAME(
305 "InterPro Name", "interpro_name"), INTERPRO_ACCESSION(
306 "InterPro Accession", "interpro_accession"), UNIPROT_ID(
307 "UniProt Id", "uniprot_id"), UNIPROT_ACCESSION(
308 "UniProt Accession", "uniprot_accession"), UNIPROT_COVERAGE(
309 "UniProt Coverage", "uniprot_coverage"), UNIPROT_FEATURES(
310 "Uniprot Features", "uniprot_features"), R_FACTOR("R Factor",
311 "r_factor"), RESOLUTION("Resolution", "resolution"), DATA_QUALITY(
312 "Data Quality", "data_quality"), OVERALL_QUALITY(
313 "Overall Quality", "overall_quality"), POLYMER_COUNT(
314 "Number of Polymers", "number_of_polymers"), PROTEIN_CHAIN_COUNT(
315 "Number of Protein Chains", "number_of_protein_chains"), BOUND_MOLECULE_COUNT(
316 "Number of Bound Molecule", "number_of_bound_molecules"), POLYMER_RESIDUE_COUNT(
317 "Number of Polymer Residue", "number_of_polymer_residues"), GENUS(
318 "GENUS", "genus"), GENE_NAME("Gene Name", "gene_name"), EXPERIMENTAL_METHOD(
319 "Experimental Method", "experimental_method"), GO_ID("GO Id",
320 "go_id"), ASSEMBLY_ID("Assembly Id", "assembly_form"), ASSEMBLY_FORM(
321 "Assembly Form", "assembly_id"), ASSEMBLY_TYPE("Assembly Type",
322 "assembly_type"), SPACE_GROUP("Space Group", "spacegroup"), CATH_CODE(
323 "Cath Code", "cath_code"), TAX_ID("Tax Id", "tax_id"), TAX_QUERY(
324 "Tax Query", "tax_query"), INTERACTING_ENTRY_ID(
325 "Interacting Entry Id", "interacting_entry_id"), INTERACTING_ENTITY_ID(
326 "Interacting Entity Id", "interacting_entity_id"), INTERACTING_MOLECULES(
327 "Interacting Molecules", "interacting_molecules"), PUBMED_ID(
328 "Pubmed Id", "pubmed_id"), STATUS("Status", "status"), MODEL_QUALITY(
329 "Model Quality", "model_quality"), PIVOT_RESOLUTION(
330 "Pivot Resolution", "pivot_resolution"), DATA_REDUCTION_SOFTWARE(
331 "Data reduction software", "data_reduction_software"), MAX_OBSERVED_RES(
332 "Max observed residues", "max_observed_residues"), ORG_SCI_NAME(
333 "Organism scientific name", "organism_scientific_name"), SUPER_KINGDOM(
334 "Super kingdom", "superkingdom"), RANK("Rank", "rank"), CRYSTALLISATION_PH(
335 "Crystallisation Ph", "crystallisation_ph"), BIOLOGICAL_FUNCTION(
336 "Biological Function", "biological_function"), BIOLOGICAL_PROCESS(
337 "Biological Process", "biological_process"), BIOLOGICAL_CELL_COMPONENT(
338 "Biological Cell Component", "biological_cell_component"), COMPOUND_NAME(
339 "Compound Name", "compound_name"), COMPOUND_ID("Compound Id",
340 "compound_id"), COMPOUND_WEIGHT("Compound Weight",
341 "compound_weight"), COMPOUND_SYSTEMATIC_NAME(
342 "Compound Systematic Name", "compound_systematic_name"), INTERACTING_LIG(
343 "Interacting Ligands", "interacting_ligands"), JOURNAL(
344 "Journal", "journal"), ALL_AUTHORS("All Authors", "all_authors"), EXPERIMENTAL_DATA_AVAILABLE(
345 "Experiment Data Available", "experiment_data_available"), DIFFRACTION_PROTOCOL(
346 "Diffraction Protocol", "diffraction_protocol"), REFINEMENT_SOFTWARE(
347 "Refinement Software", "refinement_software"), STRUCTURE_DETERMINATION_METHOD(
348 "Structure Determination Method",
349 "structure_determination_method"), SYNCHROTON_SITE(
350 "Synchrotron Site", "synchrotron_site"), SAMPLE_PREP_METHOD(
351 "Sample Preparation Method", "sample_preparation_method"), ENTRY_AUTHORS(
352 "Entry Authors", "entry_authors"), CITATION_TITLE(
353 "Citation Title", "citation_title"), STRUCTURE_SOLUTION_SOFTWARE(
354 "Structure Solution Software", "structure_solution_software"), ENTRY_ENTITY(
355 "Entry Entity", "entry_entity"), R_FREE("R Free", "r_free"), NO_OF_POLYMER_ENTITIES(
356 "Number of Polymer Entities", "number_of_polymer_entities"), NO_OF_BOUND_ENTITIES(
357 "Number of Bound Entities", "number_of_bound_entities"), CRYSTALLISATION_RESERVOIR(
358 "Crystallisation Reservoir", "crystallisation_reservoir"), DATA_SCALING_SW(
359 "Data Scalling Software", "data_scaling_software"), DETECTOR(
360 "Detector", "detector"), DETECTOR_TYPE("Detector Type",
361 "detector_type"), MODIFIED_RESIDUE_FLAG(
362 "Modified Residue Flag", "modified_residue_flag"), NUMBER_OF_COPIES(
363 "Number of Copies", "number_of_copies"), STRUCT_ASYM_ID(
364 "Struc Asym Id", "struct_asym_id"), HOMOLOGUS_PDB_ENTITY_ID(
365 "Homologus PDB Entity Id", "homologus_pdb_entity_id"), MOLECULE_SYNONYM(
366 "Molecule Synonym", "molecule_synonym"), DEPOSITION_SITE(
367 "Deposition Site", "deposition_site"), SYNCHROTRON_BEAMLINE(
368 "Synchrotron Beamline", "synchrotron_beamline"), ENTITY_ID(
369 "Entity Id", "entity_id"), BEAM_SOURCE_NAME("Beam Source Name",
370 "beam_source_name"), PROCESSING_SITE("Processing Site",
371 "processing_site"), ENTITY_WEIGHT("Entity Weight",
372 "entity_weight"), VERSION("Version", "_version_"), ALL("ALL",
379 PDBDocField(String name, String code)
385 public String getName()
390 public String getCode()
395 public String toString()