Skip to content

Commit b951939

Browse files
gremidgremid
committed
Unified code formatting; made editor configuration explicit
1 parent cf8b959 commit b951939

File tree

110 files changed

+11253
-11924
lines changed

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

110 files changed

+11253
-11924
lines changed

‎.editorconfig

+11
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,11 @@
1+
# http://editorconfig.org/
2+
3+
root = true
4+
5+
[*]
6+
charset = utf-8
7+
end_of_line = lf
8+
trim_trailing_whitespace = true
9+
insert_final_newline = false
10+
indent_style = space
11+
indent_size = 4

‎collatex-core/pom.xml

+2-1
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,6 @@
11
<?xml version="1.0" encoding="UTF-8"?>
2-
<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
2+
<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
3+
xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
34
<modelVersion>4.0.0</modelVersion>
45
<parent>
56
<groupId>eu.interedition</groupId>

‎collatex-core/src/main/java/eu/interedition/collatex/CollationAlgorithm.java

+180-180
Original file line numberDiff line numberDiff line change
@@ -1,180 +1,180 @@
1-
/*
2-
* Copyright (c) 2013 The Interedition Development Group.
3-
*
4-
* This file is part of CollateX.
5-
*
6-
* CollateX is free software: you can redistribute it and/or modify
7-
* it under the terms of the GNU General Public License as published by
8-
* the Free Software Foundation, either version 3 of the License, or
9-
* (at your option) any later version.
10-
*
11-
* CollateX is distributed in the hope that it will be useful,
12-
* but WITHOUT ANY WARRANTY; without even the implied warranty of
13-
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
14-
* GNU General Public License for more details.
15-
*
16-
* You should have received a copy of the GNU General Public License
17-
* along with CollateX. If not, see <http://www.gnu.org/licenses/>.
18-
*/
19-
20-
package eu.interedition.collatex;
21-
22-
import eu.interedition.collatex.dekker.Match;
23-
import eu.interedition.collatex.needlemanwunsch.NeedlemanWunschAlgorithm;
24-
import eu.interedition.collatex.needlemanwunsch.NeedlemanWunschScorer;
25-
import eu.interedition.collatex.util.VertexMatch;
26-
27-
import java.util.Arrays;
28-
import java.util.Collections;
29-
import java.util.Comparator;
30-
import java.util.HashMap;
31-
import java.util.HashSet;
32-
import java.util.List;
33-
import java.util.Map;
34-
import java.util.Set;
35-
import java.util.SortedSet;
36-
import java.util.TreeSet;
37-
import java.util.logging.Level;
38-
import java.util.logging.Logger;
39-
import java.util.stream.Collectors;
40-
import java.util.stream.StreamSupport;
41-
42-
/**
43-
* @author <a href="http://gregor.middell.net/" title="Homepage">Gregor Middell</a>
44-
*/
45-
public interface CollationAlgorithm {
46-
47-
void collate(VariantGraph against, Iterable<Token> witness);
48-
49-
void collate(VariantGraph against, Iterable<Token>... witnesses);
50-
51-
void collate(VariantGraph against, List<? extends Iterable<Token>> witnesses);
52-
53-
abstract class Base implements CollationAlgorithm {
54-
protected final Logger LOG = Logger.getLogger(getClass().getName());
55-
protected Map<Token, VariantGraph.Vertex> witnessTokenVertices;
56-
57-
@Override
58-
public void collate(VariantGraph against, Iterable<Token>... witnesses) {
59-
collate(against, Arrays.asList(witnesses));
60-
}
61-
62-
@Override
63-
public void collate(VariantGraph against, List<? extends Iterable<Token>> witnesses) {
64-
for (Iterable<Token> witness : witnesses) {
65-
if (LOG.isLoggable(Level.FINE)) {
66-
LOG.log(Level.FINE, "heap space: {0}/{1}", new Object[] {
67-
Runtime.getRuntime().totalMemory(),
68-
Runtime.getRuntime().maxMemory()
69-
});
70-
}
71-
collate(against, witness);
72-
}
73-
}
74-
75-
protected void merge(VariantGraph into, Iterable<Token> witnessTokens, Map<Token, VariantGraph.Vertex> alignments) {
76-
final Witness witness = StreamSupport.stream(witnessTokens.spliterator(), false)
77-
.findFirst()
78-
.map(Token::getWitness)
79-
.orElseThrow(() -> new IllegalArgumentException("Empty witness"));
80-
81-
if (LOG.isLoggable(Level.FINE)) {
82-
LOG.log(Level.FINE, "{0} + {1}: Merge comparand into graph", new Object[] { into, witness });
83-
}
84-
witnessTokenVertices = new HashMap<>();
85-
VariantGraph.Vertex last = into.getStart();
86-
final Set<Witness> witnessSet = Collections.singleton(witness);
87-
for (Token token : witnessTokens) {
88-
VariantGraph.Vertex matchingVertex = alignments.get(token);
89-
if (matchingVertex == null) {
90-
matchingVertex = into.add(token);
91-
} else {
92-
if (LOG.isLoggable(Level.FINE)) {
93-
LOG.log(Level.FINE, "Match: {0} to {1}", new Object[] { matchingVertex, token });
94-
}
95-
matchingVertex.add(Collections.singleton(token));
96-
}
97-
witnessTokenVertices.put(token, matchingVertex);
98-
99-
into.connect(last, matchingVertex, witnessSet);
100-
last = matchingVertex;
101-
}
102-
into.connect(last, into.getEnd(), witnessSet);
103-
}
104-
105-
protected void mergeTranspositions(VariantGraph into, Iterable<SortedSet<VertexMatch.WithToken>> transpositions) {
106-
for (SortedSet<VertexMatch.WithToken> transposedPhrase : transpositions) {
107-
if (LOG.isLoggable(Level.FINE)) {
108-
LOG.log(Level.FINE, "Transposition: {0}", transposedPhrase);
109-
}
110-
final Set<VariantGraph.Vertex> transposed = new HashSet<>();
111-
for (VertexMatch.WithToken match : transposedPhrase) {
112-
transposed.add(witnessTokenVertices.get(match.token));
113-
transposed.add(match.vertex);
114-
}
115-
into.transpose(transposed);
116-
}
117-
}
118-
119-
protected void mergeTranspositions(VariantGraph into, List<List<Match>> transpositions) {
120-
for (List<Match> transposedPhrase : transpositions) {
121-
if (LOG.isLoggable(Level.FINE)) {
122-
LOG.log(Level.FINE, "Transposition: {0}", transposedPhrase);
123-
}
124-
final Set<VariantGraph.Vertex> transposed = new HashSet<>();
125-
for (Match match : transposedPhrase) {
126-
transposed.add(witnessTokenVertices.get(match.token));
127-
transposed.add(match.vertex);
128-
}
129-
into.transpose(transposed);
130-
}
131-
}
132-
133-
protected void merge(VariantGraph graph, VariantGraph.Vertex[][] vertices, Token[] tokens, SortedSet<SortedSet<VertexMatch.WithTokenIndex>> matches) {
134-
@SuppressWarnings("unchecked")
135-
final SortedSet<VertexMatch.WithTokenIndex>[] matchesVertexOrder = matches.toArray(new SortedSet[matches.size()]);
136-
final SortedSet<VertexMatch.WithTokenIndex>[] matchesTokenOrder = Arrays.copyOf(matchesVertexOrder, matchesVertexOrder.length);
137-
138-
Arrays.sort(matchesTokenOrder, Comparator.comparing(m -> m.first().token));
139-
140-
final Set<SortedSet<VertexMatch.WithTokenIndex>> alignedMatches = NeedlemanWunschAlgorithm.align(
141-
matchesVertexOrder,
142-
matchesTokenOrder,
143-
new MatchPhraseAlignmentScorer(Math.max(tokens.length, vertices.length))
144-
).keySet();
145-
146-
final Map<Token, VariantGraph.Vertex> alignments = matches.stream()
147-
.filter(alignedMatches::contains)
148-
.flatMap(Set::stream)
149-
.collect(Collectors.toMap(m -> tokens[m.token], m -> m.vertex));
150-
151-
final List<SortedSet<VertexMatch.WithToken>> transpositions = matches.stream()
152-
.filter(m -> !alignedMatches.contains(m))
153-
.map(t -> t.stream().map(m -> new VertexMatch.WithToken(m.vertex, m.vertexRank, tokens[m.token])).collect(Collectors.toCollection(TreeSet::new)))
154-
.collect(Collectors.toList());
155-
156-
merge(graph, Arrays.asList(tokens), alignments);
157-
mergeTranspositions(graph, transpositions);
158-
}
159-
}
160-
161-
static class MatchPhraseAlignmentScorer implements NeedlemanWunschScorer<SortedSet<VertexMatch.WithTokenIndex>, SortedSet<VertexMatch.WithTokenIndex>> {
162-
163-
private final int maxWitnessLength;
164-
165-
public MatchPhraseAlignmentScorer(int maxWitnessLength) {
166-
this.maxWitnessLength = maxWitnessLength;
167-
}
168-
169-
@Override
170-
public float score(SortedSet<VertexMatch.WithTokenIndex> a, SortedSet<VertexMatch.WithTokenIndex> b) {
171-
return (a.equals(b) ? 1 : -maxWitnessLength);
172-
}
173-
174-
@Override
175-
public float gap() {
176-
return -(1 / (maxWitnessLength * 1.0f));
177-
}
178-
179-
}
180-
}
1+
/*
2+
* Copyright (c) 2013 The Interedition Development Group.
3+
*
4+
* This file is part of CollateX.
5+
*
6+
* CollateX is free software: you can redistribute it and/or modify
7+
* it under the terms of the GNU General Public License as published by
8+
* the Free Software Foundation, either version 3 of the License, or
9+
* (at your option) any later version.
10+
*
11+
* CollateX is distributed in the hope that it will be useful,
12+
* but WITHOUT ANY WARRANTY; without even the implied warranty of
13+
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
14+
* GNU General Public License for more details.
15+
*
16+
* You should have received a copy of the GNU General Public License
17+
* along with CollateX. If not, see <http://www.gnu.org/licenses/>.
18+
*/
19+
20+
package eu.interedition.collatex;
21+
22+
import eu.interedition.collatex.dekker.Match;
23+
import eu.interedition.collatex.needlemanwunsch.NeedlemanWunschAlgorithm;
24+
import eu.interedition.collatex.needlemanwunsch.NeedlemanWunschScorer;
25+
import eu.interedition.collatex.util.VertexMatch;
26+
27+
import java.util.Arrays;
28+
import java.util.Collections;
29+
import java.util.Comparator;
30+
import java.util.HashMap;
31+
import java.util.HashSet;
32+
import java.util.List;
33+
import java.util.Map;
34+
import java.util.Set;
35+
import java.util.SortedSet;
36+
import java.util.TreeSet;
37+
import java.util.logging.Level;
38+
import java.util.logging.Logger;
39+
import java.util.stream.Collectors;
40+
import java.util.stream.StreamSupport;
41+
42+
/**
43+
* @author <a href="http://gregor.middell.net/" title="Homepage">Gregor Middell</a>
44+
*/
45+
public interface CollationAlgorithm {
46+
47+
void collate(VariantGraph against, Iterable<Token> witness);
48+
49+
void collate(VariantGraph against, Iterable<Token>... witnesses);
50+
51+
void collate(VariantGraph against, List<? extends Iterable<Token>> witnesses);
52+
53+
abstract class Base implements CollationAlgorithm {
54+
protected final Logger LOG = Logger.getLogger(getClass().getName());
55+
protected Map<Token, VariantGraph.Vertex> witnessTokenVertices;
56+
57+
@Override
58+
public void collate(VariantGraph against, Iterable<Token>... witnesses) {
59+
collate(against, Arrays.asList(witnesses));
60+
}
61+
62+
@Override
63+
public void collate(VariantGraph against, List<? extends Iterable<Token>> witnesses) {
64+
for (Iterable<Token> witness : witnesses) {
65+
if (LOG.isLoggable(Level.FINE)) {
66+
LOG.log(Level.FINE, "heap space: {0}/{1}", new Object[]{
67+
Runtime.getRuntime().totalMemory(),
68+
Runtime.getRuntime().maxMemory()
69+
});
70+
}
71+
collate(against, witness);
72+
}
73+
}
74+
75+
protected void merge(VariantGraph into, Iterable<Token> witnessTokens, Map<Token, VariantGraph.Vertex> alignments) {
76+
final Witness witness = StreamSupport.stream(witnessTokens.spliterator(), false)
77+
.findFirst()
78+
.map(Token::getWitness)
79+
.orElseThrow(() -> new IllegalArgumentException("Empty witness"));
80+
81+
if (LOG.isLoggable(Level.FINE)) {
82+
LOG.log(Level.FINE, "{0} + {1}: Merge comparand into graph", new Object[]{into, witness});
83+
}
84+
witnessTokenVertices = new HashMap<>();
85+
VariantGraph.Vertex last = into.getStart();
86+
final Set<Witness> witnessSet = Collections.singleton(witness);
87+
for (Token token : witnessTokens) {
88+
VariantGraph.Vertex matchingVertex = alignments.get(token);
89+
if (matchingVertex == null) {
90+
matchingVertex = into.add(token);
91+
} else {
92+
if (LOG.isLoggable(Level.FINE)) {
93+
LOG.log(Level.FINE, "Match: {0} to {1}", new Object[]{matchingVertex, token});
94+
}
95+
matchingVertex.add(Collections.singleton(token));
96+
}
97+
witnessTokenVertices.put(token, matchingVertex);
98+
99+
into.connect(last, matchingVertex, witnessSet);
100+
last = matchingVertex;
101+
}
102+
into.connect(last, into.getEnd(), witnessSet);
103+
}
104+
105+
protected void mergeTranspositions(VariantGraph into, Iterable<SortedSet<VertexMatch.WithToken>> transpositions) {
106+
for (SortedSet<VertexMatch.WithToken> transposedPhrase : transpositions) {
107+
if (LOG.isLoggable(Level.FINE)) {
108+
LOG.log(Level.FINE, "Transposition: {0}", transposedPhrase);
109+
}
110+
final Set<VariantGraph.Vertex> transposed = new HashSet<>();
111+
for (VertexMatch.WithToken match : transposedPhrase) {
112+
transposed.add(witnessTokenVertices.get(match.token));
113+
transposed.add(match.vertex);
114+
}
115+
into.transpose(transposed);
116+
}
117+
}
118+
119+
protected void mergeTranspositions(VariantGraph into, List<List<Match>> transpositions) {
120+
for (List<Match> transposedPhrase : transpositions) {
121+
if (LOG.isLoggable(Level.FINE)) {
122+
LOG.log(Level.FINE, "Transposition: {0}", transposedPhrase);
123+
}
124+
final Set<VariantGraph.Vertex> transposed = new HashSet<>();
125+
for (Match match : transposedPhrase) {
126+
transposed.add(witnessTokenVertices.get(match.token));
127+
transposed.add(match.vertex);
128+
}
129+
into.transpose(transposed);
130+
}
131+
}
132+
133+
protected void merge(VariantGraph graph, VariantGraph.Vertex[][] vertices, Token[] tokens, SortedSet<SortedSet<VertexMatch.WithTokenIndex>> matches) {
134+
@SuppressWarnings("unchecked")
135+
final SortedSet<VertexMatch.WithTokenIndex>[] matchesVertexOrder = matches.toArray(new SortedSet[matches.size()]);
136+
final SortedSet<VertexMatch.WithTokenIndex>[] matchesTokenOrder = Arrays.copyOf(matchesVertexOrder, matchesVertexOrder.length);
137+
138+
Arrays.sort(matchesTokenOrder, Comparator.comparing(m -> m.first().token));
139+
140+
final Set<SortedSet<VertexMatch.WithTokenIndex>> alignedMatches = NeedlemanWunschAlgorithm.align(
141+
matchesVertexOrder,
142+
matchesTokenOrder,
143+
new MatchPhraseAlignmentScorer(Math.max(tokens.length, vertices.length))
144+
).keySet();
145+
146+
final Map<Token, VariantGraph.Vertex> alignments = matches.stream()
147+
.filter(alignedMatches::contains)
148+
.flatMap(Set::stream)
149+
.collect(Collectors.toMap(m -> tokens[m.token], m -> m.vertex));
150+
151+
final List<SortedSet<VertexMatch.WithToken>> transpositions = matches.stream()
152+
.filter(m -> !alignedMatches.contains(m))
153+
.map(t -> t.stream().map(m -> new VertexMatch.WithToken(m.vertex, m.vertexRank, tokens[m.token])).collect(Collectors.toCollection(TreeSet::new)))
154+
.collect(Collectors.toList());
155+
156+
merge(graph, Arrays.asList(tokens), alignments);
157+
mergeTranspositions(graph, transpositions);
158+
}
159+
}
160+
161+
static class MatchPhraseAlignmentScorer implements NeedlemanWunschScorer<SortedSet<VertexMatch.WithTokenIndex>, SortedSet<VertexMatch.WithTokenIndex>> {
162+
163+
private final int maxWitnessLength;
164+
165+
public MatchPhraseAlignmentScorer(int maxWitnessLength) {
166+
this.maxWitnessLength = maxWitnessLength;
167+
}
168+
169+
@Override
170+
public float score(SortedSet<VertexMatch.WithTokenIndex> a, SortedSet<VertexMatch.WithTokenIndex> b) {
171+
return (a.equals(b) ? 1 : -maxWitnessLength);
172+
}
173+
174+
@Override
175+
public float gap() {
176+
return -(1 / (maxWitnessLength * 1.0f));
177+
}
178+
179+
}
180+
}

0 commit comments

Comments
 (0)