Revision: 19516
http://sourceforge.net/p/gate/code/19516
Author: markagreenwood
Date: 2016-08-19 10:54:30 +0000 (Fri, 19 Aug 2016)
Log Message:
-----------
started to clean up the javadoc so that the build will pass
Modified Paths:
--------------
gate/branches/sawdust2/plugins/ANNIE/pom.xml
gate/branches/sawdust2/plugins/ANNIE/src/main/java/com/ontotext/gate/gazetteer/HashGazetteer.java
gate/branches/sawdust2/plugins/ANNIE/src/main/java/gate/creole/gazetteer/Gazetteer.java
gate/branches/sawdust2/plugins/ANNIE/src/main/java/gate/fsm/FSM.java
gate/branches/sawdust2/plugins/ANNIE/src/main/java/gate/fsm/FSMInstance.java
Modified: gate/branches/sawdust2/plugins/ANNIE/pom.xml
===================================================================
--- gate/branches/sawdust2/plugins/ANNIE/pom.xml 2016-08-19 10:39:39 UTC
(rev 19515)
+++ gate/branches/sawdust2/plugins/ANNIE/pom.xml 2016-08-19 10:54:30 UTC
(rev 19516)
@@ -9,7 +9,6 @@
<artifactId>base-plugin</artifactId>
<!-- this should be the version of GATE you wish to build
against -->
<version>9.0-SNAPSHOT</version>
- <relativePath>../../build/Plugin_Base</relativePath>
</parent>
<!-- this is the description of this plugin -->
Modified:
gate/branches/sawdust2/plugins/ANNIE/src/main/java/com/ontotext/gate/gazetteer/HashGazetteer.java
===================================================================
---
gate/branches/sawdust2/plugins/ANNIE/src/main/java/com/ontotext/gate/gazetteer/HashGazetteer.java
2016-08-19 10:39:39 UTC (rev 19515)
+++
gate/branches/sawdust2/plugins/ANNIE/src/main/java/com/ontotext/gate/gazetteer/HashGazetteer.java
2016-08-19 10:54:30 UTC (rev 19516)
@@ -1,7 +1,6 @@
/**
* (c) Copyright Ontotext Lab, Sirma Group Corp 2004
*/
-
package com.ontotext.gate.gazetteer;
import gate.AnnotationSet;
@@ -32,7 +31,7 @@
import java.util.Map;
import java.util.Set;
-@CreoleResource(name="Hash Gazetteer", icon="gazetteer", comment="A list
lookup component implemented by OntoText Lab. The licence information is also
available in licence.ontotext.html in the lib folder of GATE",
helpURL="http://www.ontotext.com/downloads/index.html#gazetteer";)
+@CreoleResource(name = "Hash Gazetteer", icon = "gazetteer", comment = "A list
lookup component implemented by OntoText Lab. The licence information is also
available in licence.ontotext.html in the lib folder of GATE", helpURL =
"http://www.ontotext.com/downloads/index.html#gazetteer";)
public class HashGazetteer extends AbstractGazetteer {
private static final long serialVersionUID = -4603155688378104052L;
@@ -45,15 +44,14 @@
private AnnotationSet annotationSet = null;
@Override
- @SuppressWarnings({"unchecked","rawtypes"})
+ @SuppressWarnings({"unchecked", "rawtypes"})
public Resource init() throws ResourceInstantiationException {
if(mapsList != null) {
// this is a duplicate - nothing to do
} else {
if(listsURL == null)
throw new ResourceInstantiationException(
- "No URL provided for gazetteer creation!");
-
+ "No URL provided for gazetteer creation!");
try {
mapsList = new HashMap[1000];
definition = new LinearDefinition();
@@ -70,10 +68,8 @@
fireStatusChanged("Reading " + linearnode.toString());
fireProgressChanged((++j * 100) / i);
}
-
fireProcessFinished();
- }
- catch(Exception exception) {
+ } catch(Exception exception) {
throw new ResourceInstantiationException(exception);
}
}
@@ -94,28 +90,22 @@
public void execute() throws ExecutionException {
if(document == null) throw new ExecutionException("Document is null!");
annotationSet = document.getAnnotations(annotationSetName);
-
String s = document.getContent().toString() + " ";
if(!super.caseSensitive.booleanValue()) {
s = s.toUpperCase();
}
-
int documentLength = s.length();
int j = 0;
int k = 0;
-
StringBuffer stringbuffer = new StringBuffer();
boolean prevIsSymbol = false;
boolean prevIsDigit = false;
boolean prevIsLetter = false;
-
// TODO what does this do, as it is only ever set to false
boolean flag11 = false;
-
String s3 = "";
int i1 = 0;
int j1 = 0;
-
for(int position = 0; position < documentLength; position++) {
char c = s.charAt(position);
boolean currIsWhitespace = Character.isWhitespace(c);
@@ -135,11 +125,10 @@
boolean currIsSymbol = !currIsWhitespace && !currIsLetter &&
!currIsDigit;
boolean currIsLowerCase = Character.isLowerCase(c);
if(k <= j
- && (currIsWhitespace || currIsSymbol || flag11
- && !currIsLowerCase || !prevIsLetter && currIsLetter))
- k = position;
- boolean flag13 = prevIsLetter
- && (currIsDigit || currIsSymbol || currIsWhitespace)
+ && (currIsWhitespace || currIsSymbol || flag11 && !currIsLowerCase
|| !prevIsLetter
+ && currIsLetter)) k = position;
+ boolean flag13 =
+ prevIsLetter && (currIsDigit || currIsSymbol || currIsWhitespace)
|| prevIsLetter && currIsLetter && flag11 && !currIsLowerCase
|| prevIsDigit
&& (currIsLetter || currIsSymbol || currIsWhitespace)
@@ -175,7 +164,6 @@
prevIsLetter = currIsLetter;
prevIsSymbol = currIsSymbol;
}
-
fireProcessFinished();
fireStatusChanged("Hash Gazetteer processing finished!");
}
@@ -185,18 +173,14 @@
if(!super.caseSensitive.booleanValue()) {
word = word.toUpperCase();
}
-
String s2 = removeTrailingSymbols(word);
if(!s2.equals(word)) add(s2, lookup1);
String s3 = word + " ";
-
List<Lookup> arraylist = null;
int j = s3.length();
-
boolean prevIsLetter = false;
boolean prevIsDigit = false;
boolean prevIsLowercase = false;
-
String s4 = "";
Map<String, List<Lookup>> hashmap = null;
for(int k = 0; k < j; k++) {
@@ -206,40 +190,33 @@
boolean currIsLetter = Character.isLetter(c);
boolean currIsSymbol = !currIsWhitespace && !currIsDigit &&
!currIsLetter;
boolean currIsLowercase = Character.isLowerCase(c);
- boolean flag18 = prevIsLetter
- && (currIsDigit || currIsSymbol || currIsWhitespace)
+ boolean flag18 =
+ prevIsLetter && (currIsDigit || currIsSymbol || currIsWhitespace)
|| prevIsLetter && currIsLetter && prevIsLowercase
&& !currIsLowercase || prevIsDigit
&& (currIsLetter || currIsSymbol || currIsWhitespace);
-
- //if we are on the last character
+ // if we are on the last character
if(k + 1 == j) flag18 = true;
-
if(flag18) {
s4 = normalizeWhitespace(s3.substring(0, k));
int i = s4.length();
if(mapsList[i] == null) {
hashmap = new HashMap<String, List<Lookup>>();
mapsList[i] = hashmap;
- }
- else {
+ } else {
hashmap = mapsList[i];
}
if(!hashmap.containsKey(s4)) hashmap.put(s4, null);
}
prevIsDigit = currIsDigit;
prevIsLetter = currIsLetter;
-
prevIsLowercase = currIsLowercase;
-
}
-
arraylist = hashmap.get(s4);
if(null == arraylist) {
arraylist = new ArrayList<Lookup>(1);
arraylist.add(lookup1);
- }
- else if(!arraylist.contains(lookup1)) arraylist.add(lookup1);
+ } else if(!arraylist.contains(lookup1)) arraylist.add(lookup1);
hashmap.put(s4, arraylist);
return true;
}
@@ -253,22 +230,20 @@
Map<String, List<Lookup>> hashmap = mapsList[i];
if(hashmap == null) {
return set;
- }
- else {
+ } else {
Set<Lookup> hashset = new HashSet<Lookup>(hashmap.get(s1));
return hashset;
}
}
- private boolean annotate(String word, int i, int documentPosition, int
wordLength) {
+ private boolean annotate(String word, int i, int documentPosition,
+ int wordLength) {
if(wordLength >= mapsList.length) return false;
Map<String, List<Lookup>> hashmap = mapsList[wordLength];
if(hashmap == null) return false;
if(!hashmap.containsKey(word)) return false;
List<Lookup> arraylist = hashmap.get(word);
-
// TODO shouldn't this return false if arraylist is null?
-
if(null != arraylist) {
for(Iterator<Lookup> iterator = arraylist.iterator();
iterator.hasNext();) {
Lookup lookup1 = iterator.next();
@@ -284,27 +259,25 @@
featuremap.put("language", lookup1.languages);
}
try {
- annotationSet.add(new Long(i), new Long(documentPosition), "Lookup",
featuremap);
- }
- catch(InvalidOffsetException invalidoffsetexception) {
+ annotationSet.add(new Long(i), new Long(documentPosition), "Lookup",
+ featuremap);
+ } catch(InvalidOffsetException invalidoffsetexception) {
throw new LuckyException(invalidoffsetexception.toString());
}
}
-
}
-
return true;
}
/**
* Removes a string from the gazetteer
*
- * @param s the item to remove
+ * @param s
+ * the item to remove
* @return true if the operation was successful
*/
@Override
public boolean remove(String s) {
-
String s1 = a(s);
int i = s1.length();
if(i > mapsList.length) return false;
@@ -318,11 +291,12 @@
}
/**
- * Works backwards through the String parameter removing each
- * character until it encounters a letter, digit, or whitespace at
- * which point it returns the truncated string.
+ * Works backwards through the String parameter removing each character until
+ * it encounters a letter, digit, or whitespace at which point it returns the
+ * truncated string.
*
- * @param s the String you wish to remove trailing symbols from
+ * @param s
+ * the String you wish to remove trailing symbols from
* @return the truncated String that now ends in a letter, digit, or
* whitespace character
*/
@@ -330,26 +304,24 @@
for(int i = s.length() - 1; i >= 0; i--) {
char c = s.charAt(i);
if(!Character.isLetter(c) && !Character.isDigit(c)
- && !Character.isWhitespace(c))
+ && !Character.isWhitespace(c))
s = s.substring(0, i);
else return s;
}
-
return s;
}
/**
- * Normalizes the whitespace within the String instance by replacing
- * any sequence of one or more whitespace characters with a single
- * space. Not that any leading/trailing whitespace is also removed.
+ * Normalizes the whitespace within the String instance by replacing any
+ * sequence of one or more whitespace characters with a single space. Not
that
+ * any leading/trailing whitespace is also removed.
*
- * @param s the String to normalize
+ * @param s
+ * the String to normalize
* @return the normalized String
*/
private String normalizeWhitespace(String s) {
-
// this seems to be the same as String.replaceAll("\\s+", " ")
-
StringBuffer stringbuffer = new StringBuffer();
s = s.trim();
char ac[] = s.toCharArray();
@@ -357,16 +329,12 @@
boolean prevWasWhitespace = false;
for(int j = 0; j < i; j++) {
char c = ac[j];
-
boolean currIsWhitespace = Character.isWhitespace(c);
-
if(currIsWhitespace && !prevWasWhitespace)
stringbuffer.append(' ');
else if(!currIsWhitespace) stringbuffer.append(c);
-
prevWasWhitespace = currIsWhitespace;
}
-
return stringbuffer.toString();
}
@@ -377,26 +345,24 @@
char ac[] = s.toCharArray();
int i = s.length();
if(i <= 1) return s;
-
char firstCharacter = ac[0];
stringbuffer.append(firstCharacter);
boolean flag2 = true;
boolean prevIsLetter = Character.isLetter(firstCharacter);
boolean prevNotLetterOrDigit = !Character.isLetterOrDigit(firstCharacter);
-
boolean flag10 = true;
char c2 = 'p';
-
for(int j = 1; j < i; j++) {
char currentCharacter = ac[j];
- boolean currNotLetterOrDigit =
!Character.isLetterOrDigit(currentCharacter);
+ boolean currNotLetterOrDigit =
+ !Character.isLetterOrDigit(currentCharacter);
boolean currIsWhitespace = Character.isWhitespace(currentCharacter);
boolean currIsLetter = Character.isLetter(currentCharacter);
boolean currIsDigit = Character.isDigit(currentCharacter);
-
if(flag2) {
if(prevNotLetterOrDigit && currIsWhitespace) continue;
- flag2 = prevIsLetter && currNotLetterOrDigit || prevNotLetterOrDigit
+ flag2 =
+ prevIsLetter && currNotLetterOrDigit || prevNotLetterOrDigit
&& currIsLetter;
if(currNotLetterOrDigit) {
if(c2 == 'p') c2 = currentCharacter;
@@ -408,39 +374,31 @@
stringbuffer.append(Character.toLowerCase(c3));
}
}
-
if(currIsLetter || currIsDigit) {
- if(currIsLetter) allLettersUppercase &=
Character.isUpperCase(currentCharacter);
+ if(currIsLetter)
+ allLettersUppercase &= Character.isUpperCase(currentCharacter);
if(!flag10) currentCharacter = Character.toLowerCase(currentCharacter);
stringbuffer.append(currentCharacter);
- }
- else if(!flag2) flag10 = false;
-
+ } else if(!flag2) flag10 = false;
prevIsLetter = currIsLetter;
prevNotLetterOrDigit = currNotLetterOrDigit;
}
-
String s1 = stringbuffer.toString();
if(allLettersUppercase) s1 = s1.toUpperCase();
return s1;
}
private void readList(LinearNode linearnode) throws GazetteerException {
-
if(linearnode == null)
throw new GazetteerException("LinearNode node is null");
-
GazetteerList gazetteerlist = listsByNode.get(linearnode);
if(gazetteerlist == null)
throw new GazetteerException("gazetteer list not found by node");
-
String s = linearnode.getList();
String majorType = linearnode.getMajorType();
String minorType = linearnode.getMinorType();
String language = linearnode.getLanguage();
-
Lookup lookup1 = new Lookup(s, majorType, minorType, language);
-
if(mappingDefinition != null) {
MappingNode mappingnode = mappingDefinition.getNodeByList(s);
if(null != mappingnode) {
@@ -448,62 +406,48 @@
lookup1.ontology = mappingnode.getOntologyID();
}
}
-
lookup1.list = s;
categoryList.add(lookup1);
-
Iterator<GazetteerNode> iterator = gazetteerlist.iterator();
String normalisedWord = null;
-
for(; iterator.hasNext(); add(normalisedWord, lookup1)) {
String word = iterator.next().toString();
int wordLength = word.length();
for(int j = 0; j < wordLength; j++) {
- if(j + 1 != wordLength && !Character.isWhitespace(word.charAt(j)))
continue;
+ if(j + 1 != wordLength && !Character.isWhitespace(word.charAt(j)))
+ continue;
if(j + 1 == wordLength) j = wordLength;
normalisedWord = word.substring(0, j).trim();
}
}
}
-
+
@Override
@HiddenCreoleParameter
public void setWholeWordsOnly(Boolean wholeWordsOnly) {
super.setWholeWordsOnly(wholeWordsOnly);
}
-
+
@Override
@HiddenCreoleParameter
public void setLongestMatchOnly(Boolean longestMatchOnly) {
super.setLongestMatchOnly(longestMatchOnly);
}
-
- /**
- * For internal use by the duplication mechanism.
- */
+
@Sharable
public void setMapsList(Map<String, List<Lookup>> mapsList[]) {
this.mapsList = mapsList;
}
- /**
- * For internal use by the duplication mechanism.
- */
public Map<String, List<Lookup>>[] getMapsList() {
return mapsList;
}
- /**
- * For internal use by the duplication mechanism.
- */
@Sharable
public void setCategoryList(ArrayList<Lookup> categoryList) {
this.categoryList = categoryList;
}
- /**
- * For internal use by the duplication mechanism.
- */
public ArrayList<Lookup> getCategoryList() {
return categoryList;
}
Modified:
gate/branches/sawdust2/plugins/ANNIE/src/main/java/gate/creole/gazetteer/Gazetteer.java
===================================================================
---
gate/branches/sawdust2/plugins/ANNIE/src/main/java/gate/creole/gazetteer/Gazetteer.java
2016-08-19 10:39:39 UTC (rev 19515)
+++
gate/branches/sawdust2/plugins/ANNIE/src/main/java/gate/creole/gazetteer/Gazetteer.java
2016-08-19 10:54:30 UTC (rev 19516)
@@ -89,7 +89,7 @@
/**
* Adds a new string to the gazetteer
- * @param singleItem
+ * @param singleItem the text of the lookup to add
* @param lookup the lookup to be associated with the new string
* @return true if the operation was successful
*/
@@ -97,7 +97,7 @@
/**
* Removes a string from the gazetteer
- * @param singleItem
+ * @param singleItem the text of the lookup to remove
* @return true if the operation was successful
*/
boolean remove(String singleItem);
Modified: gate/branches/sawdust2/plugins/ANNIE/src/main/java/gate/fsm/FSM.java
===================================================================
--- gate/branches/sawdust2/plugins/ANNIE/src/main/java/gate/fsm/FSM.java
2016-08-19 10:39:39 UTC (rev 19515)
+++ gate/branches/sawdust2/plugins/ANNIE/src/main/java/gate/fsm/FSM.java
2016-08-19 10:54:30 UTC (rev 19516)
@@ -75,6 +75,7 @@
/**
* Do the work involved in creating an FSM from a PrioritisedRuleList.
+ * @param rules the rules list from which the FSM is to be built
*/
protected void addRules(PrioritisedRuleList rules) {
Iterator<Rule> rulesEnum = rules.iterator();
@@ -108,6 +109,7 @@
/**
* Do the work involved in creating an FSM from a Rule.
+ * @param rule the rule to builf the FSM from
*/
protected void setRule(Rule rule) {
@@ -211,6 +213,8 @@
/**
* A factory method for new FSMs like this one, given a Rule object.
+ * @param r create a new FSM from this rule
+ * @return the new FSM
*/
protected FSM spawn(Rule r) {
return new FSM(r);
@@ -219,6 +223,8 @@
/**
* A factory method for new FSMs like this one, given a ComplexPatternElement
* object.
+ * @param currentPattern create a new FSM from this pattern
+ * @return the new FSM
*/
protected FSM spawn(ComplexPatternElement currentPattern) {
return new FSM(currentPattern);
@@ -579,6 +585,7 @@
/**
* Iterates over all the states in this FSM, setting currentState and
* currentTransition, then calling the given Runnable callback.
+ * @param r the runnable to call
*/
protected void forEachState (java.lang.Runnable r) {
Set<State> stackToProcess = new HashSet<State>();
@@ -649,6 +656,7 @@
* @param includeConstraints
* whether to include a stringified representation of each
transition
* object as part of its label. The default is false.
+ * @return the GraphViz representation of this FSM
*/
public String asGraphViz(boolean includeConstraints) {
StringBuffer result = new StringBuffer();
@@ -712,6 +720,7 @@
/**
* Returns a GML (Graph Modelling Language) representation of the transition
* graph of this FSM.
+ * @return the GML representation of this FSM
*/
public String getGML() {
Modified:
gate/branches/sawdust2/plugins/ANNIE/src/main/java/gate/fsm/FSMInstance.java
===================================================================
---
gate/branches/sawdust2/plugins/ANNIE/src/main/java/gate/fsm/FSMInstance.java
2016-08-19 10:39:39 UTC (rev 19515)
+++
gate/branches/sawdust2/plugins/ANNIE/src/main/java/gate/fsm/FSMInstance.java
2016-08-19 10:54:30 UTC (rev 19516)
@@ -82,6 +82,7 @@
/** Sets the position in the support transition graph for this FSM instance
* Convenience method for when the state is not known at construction time.
+ * @param the state to use
*/
public void setFSMPosition(State newFSMPos) {
FSMPosition = newFSMPos;
@@ -295,6 +296,19 @@
* basic object pooling in order to reuse the FSMInstance objects.
* This is considered to be a good idea because during jape transducing
* a large number of FSMIntances are needed for short periods.
+ * @param supportGraph the transition graph of the FSM
+ * @param FSMPosition the state this instance will be in
+ * @param startNode the node in the AnnotationSet where this FSM instance
+ * started the matching
+ * @param AGPosition the node in the AnnotationSet up to which this FSM
Instance
+ * advanced during the matching.
+ * @param bindings a HashMap that maps from labels (objects of type String)
+ * to sets of annotations (objects of type AnnotationSet). This map stores
+ * all the bindings that took place during the matching process.
+ * This FSMInstance started the matching on an AnnotationSet from
"startNode"
+ * and advanced to "AGPosition"; during this process it traversed the path
in
+ * the transition graph "supportGraph" from the initial state to
+ * "FSMPosition" and made the bindings stored in "bindings".
*/
public static FSMInstance getNewInstance(FSM supportGraph, State FSMPosition,
Node startNode, Node AGPosition,
This was sent by the SourceForge.net collaborative development platform, the
world's largest Open Source development site.
------------------------------------------------------------------------------
_______________________________________________
GATE-cvs mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/gate-cvs
