List of usage examples for org.dom4j Node selectNodes
List<Node> selectNodes(String xpathExpression);
selectNodes
evaluates an XPath expression and returns the result as a List
of Node
instances or String
instances depending on the XPath expression.
From source file:edu.scripps.fl.pubchem.EUtilsFactory.java
License:Apache License
public List<Relation> getRelations(Document document) { String fromDb = document.selectSingleNode("/eLinkResult/LinkSet/DbFrom").getText(); String idStr = document.selectSingleNode("/eLinkResult/LinkSet/IdList/Id").getText(); Long id = Long.parseLong(idStr); List<Node> linkSetDbs = document.selectNodes("/eLinkResult/LinkSet/LinkSetDb"); ArrayList<Relation> list = new ArrayList<Relation>(); for (Node linkSetDb : linkSetDbs) { String toDb = linkSetDb.selectSingleNode("DbTo").getText(); String linkName = linkSetDb.selectSingleNode("LinkName").getText(); List<Node> ids = linkSetDb.selectNodes("Link/Id"); list.ensureCapacity(list.size() + ids.size()); for (Node idNode : ids) { long relatedId = Long.parseLong(idNode.getText()); if (id == relatedId) continue; Relation relation = new Relation(); relation.setRelationName(linkName); relation.setFromDb(fromDb);/*from w w w . j av a2 s .co m*/ relation.setFromId(id); relation.setToDb(toDb); relation.setToId(relatedId); list.add(relation); } } return list; }
From source file:edu.scripps.fl.pubchem.EUtilsFactory.java
License:Apache License
public Collection<Long> getIds(Long id, String fromDb, String toDb) throws Exception { Document document = EUtilsFactory.getInstance().getDocument( "http://eutils.ncbi.nlm.nih.gov/entrez/eutils/elink.fcgi", "dbfrom", fromDb, "db", toDb, "id", "" + id); List<Node> linkSetDbs = document.selectNodes("/eLinkResult/LinkSet/LinkSetDb"); Set<Long> relatedIds = new HashSet<Long>(); for (Node linkSetDb : linkSetDbs) { String linkName = linkSetDb.selectSingleNode("LinkName").getText(); List<Node> ids = linkSetDb.selectNodes("Link/Id"); for (Node idNode : ids) { long relatedId = Long.parseLong(idNode.getText()); if (id.equals(relatedId)) continue; relatedIds.add(relatedId);/*from w ww . j a v a 2s . c om*/ } } return relatedIds; }
From source file:edu.scripps.fl.pubchem.PubChemFactory.java
License:Apache License
public void populateAssayFromSummaryDocument(PCAssay assay, Node docSumNode) throws Exception { Node errorNode = docSumNode.selectSingleNode("error"); if (errorNode != null) throw new Exception("Entrez error: " + errorNode.getText()); List<Node> list = docSumNode.selectNodes("*"); String uid = docSumNode.valueOf("@uid"); assay.setAID(Integer.parseInt(uid)); for (Node node : list) { String name = node.getName(); Object value = node.getText(); if (node.selectNodes("*").size() > 0) { } else {/*from w ww . ja v a 2s . co m*/ String property = propMap.getProperty(name); if (null != property) { Class clazz = PropertyUtils.getPropertyType(assay, property); if (clazz.isAssignableFrom(Date.class)) value = parseDate(value); BeanUtils.setProperty(assay, property, value); } else { if (!unprocessedProperties.containsKey(name)) { unprocessedProperties.put(name, ""); log.warn(String.format("Cannot determine PCAssay bean property '%s'", name)); } } } } String desc = assay.getDescription(); // eutils summary description doesn't contain new lines // so don't update it if it already has a value (when we populate via xml first). if (desc == null || "".equals(desc) || !desc.contains("\n")) { Node node = docSumNode.selectSingleNode("AssayDescription"); assay.setDescription(node.getText()); } return; }
From source file:edu.scripps.fl.pubchem.PubChemFactory.java
License:Apache License
public int populateRelations(Session session, Document document) throws IOException, DocumentException { String fromDb = document.selectSingleNode("/eLinkResult/LinkSet/DbFrom").getText(); String idStr = document.selectSingleNode("/eLinkResult/LinkSet/IdList/Id").getText(); Long id = Long.parseLong(idStr); List<Node> linkSetDbs = document.selectNodes("/eLinkResult/LinkSet/LinkSetDb"); Transaction trx = session.beginTransaction(); int counter = 0; for (Node linkSetDb : linkSetDbs) { String toDb = linkSetDb.selectSingleNode("DbTo").getText(); String linkName = linkSetDb.selectSingleNode("LinkName").getText(); List<Node> ids = linkSetDb.selectNodes("Link/Id"); for (Node idNode : ids) { long relatedId = Long.parseLong(idNode.getText()); if (id == relatedId) continue; Relation relation = new Relation(); relation.setRelationName(linkName); relation.setFromDb(fromDb);//w w w. jav a 2 s . co m relation.setFromId(id); relation.setToDb(toDb); relation.setToId(relatedId); session.save(relation); if (counter++ % 100 == 0) { trx.commit(); session.clear(); // cache grows hugely during very large // inserts trx = session.beginTransaction(); } } } trx.commit(); return counter; }
From source file:edu.scripps.fl.pubchem.PubChemFactory.java
License:Apache License
public Collection<Long> getNeighbors(Long id) throws Exception { Document document = EUtilsWebSession.getInstance().getDocument( "http://eutils.ncbi.nlm.nih.gov/entrez/eutils/elink.fcgi", "dbfrom", "pcassay", "id", "" + id, "linkname", "pcassay_pcassay_neighbor_list"); List<Node> linkSetDbs = document.selectNodes("/eLinkResult/LinkSet/LinkSetDb"); Set<Long> relatedIds = new HashSet(); int counter = 0; for (Node linkSetDb : linkSetDbs) { String linkName = linkSetDb.selectSingleNode("LinkName").getText(); List<Node> ids = linkSetDb.selectNodes("Link/Id"); for (Node idNode : ids) { Long relatedId = Long.parseLong(idNode.getText()); relatedIds.add(relatedId);// w w w .j a v a2s . co m } } return relatedIds; }
From source file:edu.scripps.fl.pubchem.PubChemFactory.java
License:Apache License
public List<Relation> getRelations(Document document) { String fromDb = document.selectSingleNode("/eLinkResult/LinkSet/DbFrom").getText(); String idStr = document.selectSingleNode("/eLinkResult/LinkSet/IdList/Id").getText(); Long id = Long.parseLong(idStr); List<Node> linkSetDbs = document.selectNodes("/eLinkResult/LinkSet/LinkSetDb"); ArrayList<Relation> list = new ArrayList(); for (Node linkSetDb : linkSetDbs) { String toDb = linkSetDb.selectSingleNode("DbTo").getText(); String linkName = linkSetDb.selectSingleNode("LinkName").getText(); List<Node> ids = linkSetDb.selectNodes("Link/Id"); list.ensureCapacity(list.size() + ids.size()); for (Node idNode : ids) { long relatedId = Long.parseLong(idNode.getText()); if (id == relatedId) continue; Relation relation = new Relation(); relation.setRelationName(linkName); relation.setFromDb(fromDb);//from ww w. j ava 2 s .co m relation.setFromId(id); relation.setToDb(toDb); relation.setToId(relatedId); list.add(relation); } } return list; }
From source file:edu.scripps.fl.pubchem.PubChemXMLParserFactory.java
License:Apache License
protected void populateAssayResultsFromXML(PCAssay assay, Node assayDescriptionNode) throws Exception { List<PCAssayResult> results = null; List<Node> assayResultNodes = assayDescriptionNode .selectNodes("../../../PC-AssaySubmit_data/PC-AssayResults"); if (assayResultNodes.size() == 0) return;/*from w w w.j ava2s . c om*/ else results = new ArrayList<PCAssayResult>(assayResultNodes.size()); List<PCAssayColumn> testedCols = assay.getTestedColumns(); PCAssayColumn activeColumn = assay.getActiveColumn(); for (Node resultNode : assayResultNodes) { PCAssayResult result = new PCAssayResult(); String val = resultNode.selectSingleNode("PC-AssayResults_sid").valueOf("text()"); result.setSID(Long.parseLong(val)); val = resultNode.selectSingleNode("PC-AssayResults_outcome").valueOf("@value"); val = val.substring(0, 1).toUpperCase() + val.substring(1); result.setOutcome(val); val = resultNode.selectSingleNode("PC-AssayResults_rank").valueOf("text()"); result.setRankScore(Integer.parseInt(val)); List<Node> assayDataNodes = resultNode.selectNodes("PC-AssayResults_data/PC-AssayData"); List<String> all = GrowthList.decorate(new ArrayList(assay.getColumns().size() - 2)); result.setAllValues(all); for (Node node : assayDataNodes) { val = node.valueOf("PC-AssayData_tid/text()"); int index = Integer.parseInt(val) - 1; val = node.selectSingleNode(".//*[starts-with(name(),'PC-AssayData_value_')]").getText(); all.set(index, val); } // if a dose response assay with a marked activeConcentration if ("confirmatory".equals(assay.getActivityOutcomeMethod()) && activeColumn != null) { String actConc = all.get(activeColumn.getTID() - 1); if (null != actConc && !"".equals(actConc)) { result.setPrimaryValue(Double.valueOf(actConc)); result.setPrimaryColumn(activeColumn); PCAssayColumn qualCol = assay.getQualifierColumn(); if (qualCol != null) { String qual = all.get(qualCol.getTID() - 1); if (!"".equals(qual)) result.setQualifier(qual); } } } else if ("screening".equals(assay.getActivityOutcomeMethod()) && testedCols.size() > 0) { PCAssayColumn testedCol = testedCols.get(0); String value = all.get(testedCol.getTID() - 1); result.setPrimaryColumn(testedCol); if (null != value && !"".equals(value)) if ("float".equals(testedCol.getType()) || "int".equals(testedCol.getType())) result.setPrimaryValue(Double.parseDouble(value)); else result.setPrimaryValueAsString(value); } // put all testedConcentration columns into an ordered array. Interested in numbers here only. result.getTestedValues().clear(); for (int ii = 0; ii < testedCols.size(); ii++) { PCAssayColumn testedCol = testedCols.get(ii); String value = all.get(testedCol.getTID() - 1); if (null != value && !"".equals(value)) { try { Double dbl = Double.parseDouble(value); result.getTestedValues().set(ii, dbl); } catch (NumberFormatException ex) { // if not a number then don't worry about it. } } } assay.getResults().add(result); } }
From source file:edu.scripps.fl.pubchem.PubChemXMLParserFactory.java
License:Apache License
protected PCAssay populateAssayFromXMLNode(Node topNode) throws Exception { // String assayDescPath = "PC-AssaySubmit_assay/PC-AssaySubmit_assay_descr/PC-AssayDescription"; Node assayDescNode = null; if (topNode.getName().equals("PC-AssayDescription")) assayDescNode = topNode;/*from w w w .ja v a 2s .c o m*/ else { assayDescNode = topNode.selectSingleNode(".//PC-AssayDescription"); } if (assayDescNode == null) throw new Exception( String.format("Cannot find PC-AssayDescription node in provided node %s", topNode.getPath())); Node node = assayDescNode.selectSingleNode("PC-AssayDescription_aid/PC-ID/PC-ID_id"); Integer aid = new Integer(node.getText()); try { PCAssay assay = new PCAssay(); if (aid > 0) assay.setAID(aid); node = assayDescNode.selectSingleNode("PC-AssayDescription_aid/PC-ID/PC-ID_version"); Integer version = new Integer(node.getText()); assay.setVersion(version); node = assayDescNode.selectSingleNode("PC-AssayDescription_revision"); Integer revision = new Integer(node.getText()); assay.setRevision(revision); Node trackingNode = assayDescNode .selectSingleNode("PC-AssayDescription_aid-source/PC-Source/PC-Source_db/PC-DBTracking"); node = trackingNode.selectSingleNode("PC-DBTracking_name"); assay.setSourceName(node.getText()); node = trackingNode.selectSingleNode("PC-DBTracking_source-id/Object-id/Object-id_str"); assay.setExtRegId(node.getText()); // hold until date node = trackingNode.selectSingleNode("PC-DBTracking_date"); if (node != null) { String year = node.selectSingleNode("Date/Date_std/Date-std/Date-std_year").getText(); String month = node.selectSingleNode("Date/Date_std/Date-std/Date-std_month").getText(); String day = node.selectSingleNode("Date/Date_std/Date-std/Date-std_day").getText(); if (DEBUGGING) log.info("year: " + year + " month: " + month + " day: " + day); Calendar calendar = Calendar.getInstance(); calendar.set(Integer.parseInt(year), Integer.parseInt(month) - 1, Integer.parseInt(day)); assay.setHoldUntilDate(calendar.getTime()); if (DEBUGGING) log.info(calendar.getTime().toString()); } node = assayDescNode.selectSingleNode("PC-AssayDescription_name"); assay.setName(node.getText()); List<Node> nodes = assayDescNode .selectNodes("PC-AssayDescription_description/PC-AssayDescription_description_E"); assay.setDescription(join(nodes, separator)); nodes = assayDescNode.selectNodes("PC-AssayDescription_protocol/PC-AssayDescription_protocol_E"); assay.setProtocol(join(nodes, separator)); nodes = assayDescNode.selectNodes("PC-AssayDescription_comment/PC-AssayDescription_comment_E"); assay.setComment(join(nodes, separator)); node = assayDescNode.selectSingleNode("PC-AssayDescription_activity-outcome-method"); if (node != null) assay.setActivityOutcomeMethod(node.valueOf("@value")); node = assayDescNode .selectSingleNode("PC-AssayDescription_grant-number/PC-AssayDescription_grant-number_E"); if (node != null) assay.setGrantNumber(node.getText()); node = assayDescNode.selectSingleNode("PC-AssayDescription_project-category"); if (node != null) assay.setProjectCategory(node.valueOf("@value")); assay.getAssayXRefs().removeAll(assay.getAssayXRefs()); nodes = assayDescNode.selectNodes("PC-AssayDescription_xref/PC-AnnotatedXRef"); handleXRefs(assay, null, nodes); nodes = assayDescNode.selectNodes("PC-AssayDescription_target/PC-AssayTargetInfo"); handleTargetXRefs(assay, null, nodes); handlePanels(assay, assayDescNode); handleColumns(assay, assayDescNode); handleComments(assay, assayDescNode); return assay; } catch (Exception ex) { throw new RuntimeException("Problem with AID " + aid, ex); } }
From source file:edu.scripps.fl.pubchem.PubChemXMLParserFactory.java
License:Apache License
protected void handleColumns(PCAssay assay, Node assayDescNode) { Map<Integer, PCAssayColumn> map = new HashMap(); for (PCAssayColumn col : assay.getColumns()) map.put(col.getTID(), col);//from w w w. j a v a 2 s . c om ensureColumn(assay, -1, "Outcome", "string"); ensureColumn(assay, 0, "Score", "float"); Map<Integer, PCAssayPanel> mapPanels = new HashMap(); for (PCAssayPanel panel : assay.getPanels()) mapPanels.put(panel.getPanelNumber(), panel); List<Node> nodes = assayDescNode.selectNodes("PC-AssayDescription_results/PC-ResultType"); for (Node n : nodes) { String tid = n.selectSingleNode("PC-ResultType_tid").getText(); String name = n.selectSingleNode("PC-ResultType_name").getText(); String type = n.selectSingleNode("PC-ResultType_type").valueOf("@value"); PCAssayColumn column = ensureColumn(assay, Integer.parseInt(tid), name, type); Node node = n.selectSingleNode("PC-ResultType_unit"); if (node != null) column.setUnit(node.valueOf("@value")); List<Node> descNodes = n.selectNodes("PC-ResultType_description/PC-ResultType_description_E"); column.setDescription(join(descNodes, separator)); if (DEBUGGING) log.info("Column description: " + join(descNodes, separator)); node = n.selectSingleNode("PC-ResultType_ac"); if (node != null) column.setActiveConcentration("true".equals(node.valueOf("@value"))); node = n.selectSingleNode("PC-ResultType_tc"); if (node != null) { Node node2 = node.selectSingleNode("PC-ConcentrationAttr/PC-ConcentrationAttr_dr-id"); if (node2 != null) { column.setCurvePlotLabel(Integer.parseInt(node2.getText())); } String testedConc = node.selectSingleNode("PC-ConcentrationAttr/PC-ConcentrationAttr_concentration") .getText(); column.setTestedConcentration(Double.parseDouble(testedConc)); String testedUnit = node.selectSingleNode("PC-ConcentrationAttr/PC-ConcentrationAttr_unit") .valueOf("@value"); column.setTestedConcentrationUnit(testedUnit); } node = n.selectSingleNode("PC-ResultType_panel-info/PC-AssayPanelTestResult"); if (node != null) { String panelId = node.selectSingleNode("PC-AssayPanelTestResult_mid").getText(); PCAssayPanel panel = mapPanels.get(Integer.parseInt(panelId)); column.setPanel(panel); String panelColumnType = node.selectSingleNode("PC-AssayPanelTestResult_readout-annot") .valueOf("@value"); column.setPanelReadoutType(panelColumnType); } } }
From source file:edu.scripps.fl.pubchem.web.pug.PUGRequest.java
License:Apache License
private static void setResponseIds2(Document document, Type type, Collection<Object> ids) throws Exception { Node node = document.selectSingleNode("//PCT-ID-List_db"); node.setText(type.getDatabase());// w ww .ja v a 2s . c o m node = document.selectSingleNode(".//PCT-ID-List_uids"); for (Node child : (List<Node>) node.selectNodes("*")) child.detach(); for (Object id : ids) { Element aidElem = DocumentHelper.createElement("PCT-ID-List_uids_E"); aidElem.setText(id.toString()); ((Element) node).add(aidElem); } }