[17/50] [abbrv] opennlp git commit: OPENNLP-983: Make suffix/prefix length configurable
OPENNLP-983: Make suffix/prefix length configurable This closes #121 Project: http://git-wip-us.apache.org/repos/asf/opennlp/repo Commit: http://git-wip-us.apache.org/repos/asf/opennlp/commit/dc91b254 Tree: http://git-wip-us.apache.org/repos/asf/opennlp/tree/dc91b254 Diff: http://git-wip-us.apache.org/repos/asf/opennlp/diff/dc91b254 Branch: refs/heads/parser_regression Commit: dc91b254adfd2bcb5aa4525a30162979f0e1fde3 Parents: 733d27d Author: jzonthemtnAuthored: Mon Feb 13 07:57:21 2017 -0500 Committer: Jörn Kottmann Committed: Thu Apr 20 12:40:20 2017 +0200 -- .../tools/util/featuregen/GeneratorFactory.java | 22 - .../util/featuregen/PrefixFeatureGenerator.java | 32 +-- .../util/featuregen/SuffixFeatureGenerator.java | 33 +-- .../featuregen/PrefixFeatureGeneratorTest.java | 92 .../featuregen/SuffixFeatureGeneratorTest.java | 92 5 files changed, 251 insertions(+), 20 deletions(-) -- http://git-wip-us.apache.org/repos/asf/opennlp/blob/dc91b254/opennlp-tools/src/main/java/opennlp/tools/util/featuregen/GeneratorFactory.java -- diff --git a/opennlp-tools/src/main/java/opennlp/tools/util/featuregen/GeneratorFactory.java b/opennlp-tools/src/main/java/opennlp/tools/util/featuregen/GeneratorFactory.java index fa97f43..ef08cfb 100644 --- a/opennlp-tools/src/main/java/opennlp/tools/util/featuregen/GeneratorFactory.java +++ b/opennlp-tools/src/main/java/opennlp/tools/util/featuregen/GeneratorFactory.java @@ -555,7 +555,16 @@ public class GeneratorFactory { public AdaptiveFeatureGenerator create(Element generatorElement, FeatureGeneratorResourceProvider resourceManager) { - return new PrefixFeatureGenerator(); + + String attribute = generatorElement.getAttribute("length"); + + int prefixLength = PrefixFeatureGenerator.DEFAULT_MAX_LENGTH; + + if (!Objects.equals(attribute, "")) { +prefixLength = Integer.parseInt(attribute); + } + + return new PrefixFeatureGenerator(prefixLength); } static void register(Map factoryMap) { @@ -570,7 +579,16 @@ public class GeneratorFactory { public AdaptiveFeatureGenerator create(Element generatorElement, FeatureGeneratorResourceProvider resourceManager) { - return new SuffixFeatureGenerator(); + + String attribute = generatorElement.getAttribute("length"); + + int suffixLength = SuffixFeatureGenerator.DEFAULT_MAX_LENGTH; + + if (!Objects.equals(attribute, "")) { +suffixLength = Integer.parseInt(attribute); + } + + return new SuffixFeatureGenerator(suffixLength); } static void register(Map factoryMap) { http://git-wip-us.apache.org/repos/asf/opennlp/blob/dc91b254/opennlp-tools/src/main/java/opennlp/tools/util/featuregen/PrefixFeatureGenerator.java -- diff --git a/opennlp-tools/src/main/java/opennlp/tools/util/featuregen/PrefixFeatureGenerator.java b/opennlp-tools/src/main/java/opennlp/tools/util/featuregen/PrefixFeatureGenerator.java index 8cdd48f..04fcd15 100644 --- a/opennlp-tools/src/main/java/opennlp/tools/util/featuregen/PrefixFeatureGenerator.java +++ b/opennlp-tools/src/main/java/opennlp/tools/util/featuregen/PrefixFeatureGenerator.java @@ -21,21 +21,35 @@ import java.util.List; public class PrefixFeatureGenerator implements AdaptiveFeatureGenerator { - private static final int PREFIX_LENGTH = 4; - - private static String[] getPrefixes(String lex) { -String[] prefs = new String[PREFIX_LENGTH]; -for (int li = 0; li < PREFIX_LENGTH; li++) { - prefs[li] = lex.substring(0, Math.min(li + 1, lex.length())); -} -return prefs; + static final int DEFAULT_MAX_LENGTH = 4; + + private final int prefixLength; + + public PrefixFeatureGenerator() { +prefixLength = DEFAULT_MAX_LENGTH; + } + + public PrefixFeatureGenerator(int prefixLength) { +this.prefixLength = prefixLength; } + @Override public void createFeatures(List features, String[] tokens, int index, String[] previousOutcomes) { -String[] prefs = PrefixFeatureGenerator.getPrefixes(tokens[index]); +String[] prefs = getPrefixes(tokens[index]); for (String pref : prefs) { features.add("pre=" + pref); } } + + private String[] getPrefixes(String lex) { + +int prefixes = Math.min(prefixLength, lex.length()); + +String[] prefs = new String[prefixes]; +for (int li = 0; li < prefixes; li++) { + prefs[li] = lex.substring(0, Math.min(li + 1, lex.length())); +} +return prefs;
[15/50] [abbrv] opennlp git commit: OPENNLP-983: Make suffix/prefix length configurable
OPENNLP-983: Make suffix/prefix length configurable This closes #121 Project: http://git-wip-us.apache.org/repos/asf/opennlp/repo Commit: http://git-wip-us.apache.org/repos/asf/opennlp/commit/1cd2658d Tree: http://git-wip-us.apache.org/repos/asf/opennlp/tree/1cd2658d Diff: http://git-wip-us.apache.org/repos/asf/opennlp/diff/1cd2658d Branch: refs/heads/parser_regression Commit: 1cd2658d0179afcf982229fab9c24da62f944c58 Parents: fc3b12f Author: jzonthemtnAuthored: Mon Feb 13 07:57:21 2017 -0500 Committer: Jörn Kottmann Committed: Sun Apr 16 19:24:53 2017 +0200 -- .../tools/util/featuregen/GeneratorFactory.java | 22 - .../util/featuregen/PrefixFeatureGenerator.java | 32 +-- .../util/featuregen/SuffixFeatureGenerator.java | 33 +-- .../featuregen/PrefixFeatureGeneratorTest.java | 92 .../featuregen/SuffixFeatureGeneratorTest.java | 92 5 files changed, 251 insertions(+), 20 deletions(-) -- http://git-wip-us.apache.org/repos/asf/opennlp/blob/1cd2658d/opennlp-tools/src/main/java/opennlp/tools/util/featuregen/GeneratorFactory.java -- diff --git a/opennlp-tools/src/main/java/opennlp/tools/util/featuregen/GeneratorFactory.java b/opennlp-tools/src/main/java/opennlp/tools/util/featuregen/GeneratorFactory.java index fa97f43..ef08cfb 100644 --- a/opennlp-tools/src/main/java/opennlp/tools/util/featuregen/GeneratorFactory.java +++ b/opennlp-tools/src/main/java/opennlp/tools/util/featuregen/GeneratorFactory.java @@ -555,7 +555,16 @@ public class GeneratorFactory { public AdaptiveFeatureGenerator create(Element generatorElement, FeatureGeneratorResourceProvider resourceManager) { - return new PrefixFeatureGenerator(); + + String attribute = generatorElement.getAttribute("length"); + + int prefixLength = PrefixFeatureGenerator.DEFAULT_MAX_LENGTH; + + if (!Objects.equals(attribute, "")) { +prefixLength = Integer.parseInt(attribute); + } + + return new PrefixFeatureGenerator(prefixLength); } static void register(Map factoryMap) { @@ -570,7 +579,16 @@ public class GeneratorFactory { public AdaptiveFeatureGenerator create(Element generatorElement, FeatureGeneratorResourceProvider resourceManager) { - return new SuffixFeatureGenerator(); + + String attribute = generatorElement.getAttribute("length"); + + int suffixLength = SuffixFeatureGenerator.DEFAULT_MAX_LENGTH; + + if (!Objects.equals(attribute, "")) { +suffixLength = Integer.parseInt(attribute); + } + + return new SuffixFeatureGenerator(suffixLength); } static void register(Map factoryMap) { http://git-wip-us.apache.org/repos/asf/opennlp/blob/1cd2658d/opennlp-tools/src/main/java/opennlp/tools/util/featuregen/PrefixFeatureGenerator.java -- diff --git a/opennlp-tools/src/main/java/opennlp/tools/util/featuregen/PrefixFeatureGenerator.java b/opennlp-tools/src/main/java/opennlp/tools/util/featuregen/PrefixFeatureGenerator.java index 8cdd48f..04fcd15 100644 --- a/opennlp-tools/src/main/java/opennlp/tools/util/featuregen/PrefixFeatureGenerator.java +++ b/opennlp-tools/src/main/java/opennlp/tools/util/featuregen/PrefixFeatureGenerator.java @@ -21,21 +21,35 @@ import java.util.List; public class PrefixFeatureGenerator implements AdaptiveFeatureGenerator { - private static final int PREFIX_LENGTH = 4; - - private static String[] getPrefixes(String lex) { -String[] prefs = new String[PREFIX_LENGTH]; -for (int li = 0; li < PREFIX_LENGTH; li++) { - prefs[li] = lex.substring(0, Math.min(li + 1, lex.length())); -} -return prefs; + static final int DEFAULT_MAX_LENGTH = 4; + + private final int prefixLength; + + public PrefixFeatureGenerator() { +prefixLength = DEFAULT_MAX_LENGTH; + } + + public PrefixFeatureGenerator(int prefixLength) { +this.prefixLength = prefixLength; } + @Override public void createFeatures(List features, String[] tokens, int index, String[] previousOutcomes) { -String[] prefs = PrefixFeatureGenerator.getPrefixes(tokens[index]); +String[] prefs = getPrefixes(tokens[index]); for (String pref : prefs) { features.add("pre=" + pref); } } + + private String[] getPrefixes(String lex) { + +int prefixes = Math.min(prefixLength, lex.length()); + +String[] prefs = new String[prefixes]; +for (int li = 0; li < prefixes; li++) { + prefs[li] = lex.substring(0, Math.min(li + 1, lex.length())); +} +return prefs;
[03/24] opennlp git commit: OPENNLP-983: Make suffix/prefix length configurable
OPENNLP-983: Make suffix/prefix length configurable This closes #121 Project: http://git-wip-us.apache.org/repos/asf/opennlp/repo Commit: http://git-wip-us.apache.org/repos/asf/opennlp/commit/b7d3abce Tree: http://git-wip-us.apache.org/repos/asf/opennlp/tree/b7d3abce Diff: http://git-wip-us.apache.org/repos/asf/opennlp/diff/b7d3abce Branch: refs/heads/OPENNLP-778 Commit: b7d3abce569b5a4bf0ae39b24c6ac9920032db01 Parents: 929595d Author: jzonthemtnAuthored: Mon Feb 13 07:57:21 2017 -0500 Committer: Jörn Kottmann Committed: Thu Feb 16 10:04:08 2017 +0100 -- .../tools/util/featuregen/GeneratorFactory.java | 22 - .../util/featuregen/PrefixFeatureGenerator.java | 32 +-- .../util/featuregen/SuffixFeatureGenerator.java | 33 +-- .../featuregen/PrefixFeatureGeneratorTest.java | 92 .../featuregen/SuffixFeatureGeneratorTest.java | 92 5 files changed, 251 insertions(+), 20 deletions(-) -- http://git-wip-us.apache.org/repos/asf/opennlp/blob/b7d3abce/opennlp-tools/src/main/java/opennlp/tools/util/featuregen/GeneratorFactory.java -- diff --git a/opennlp-tools/src/main/java/opennlp/tools/util/featuregen/GeneratorFactory.java b/opennlp-tools/src/main/java/opennlp/tools/util/featuregen/GeneratorFactory.java index fa97f43..ef08cfb 100644 --- a/opennlp-tools/src/main/java/opennlp/tools/util/featuregen/GeneratorFactory.java +++ b/opennlp-tools/src/main/java/opennlp/tools/util/featuregen/GeneratorFactory.java @@ -555,7 +555,16 @@ public class GeneratorFactory { public AdaptiveFeatureGenerator create(Element generatorElement, FeatureGeneratorResourceProvider resourceManager) { - return new PrefixFeatureGenerator(); + + String attribute = generatorElement.getAttribute("length"); + + int prefixLength = PrefixFeatureGenerator.DEFAULT_MAX_LENGTH; + + if (!Objects.equals(attribute, "")) { +prefixLength = Integer.parseInt(attribute); + } + + return new PrefixFeatureGenerator(prefixLength); } static void register(Map factoryMap) { @@ -570,7 +579,16 @@ public class GeneratorFactory { public AdaptiveFeatureGenerator create(Element generatorElement, FeatureGeneratorResourceProvider resourceManager) { - return new SuffixFeatureGenerator(); + + String attribute = generatorElement.getAttribute("length"); + + int suffixLength = SuffixFeatureGenerator.DEFAULT_MAX_LENGTH; + + if (!Objects.equals(attribute, "")) { +suffixLength = Integer.parseInt(attribute); + } + + return new SuffixFeatureGenerator(suffixLength); } static void register(Map factoryMap) { http://git-wip-us.apache.org/repos/asf/opennlp/blob/b7d3abce/opennlp-tools/src/main/java/opennlp/tools/util/featuregen/PrefixFeatureGenerator.java -- diff --git a/opennlp-tools/src/main/java/opennlp/tools/util/featuregen/PrefixFeatureGenerator.java b/opennlp-tools/src/main/java/opennlp/tools/util/featuregen/PrefixFeatureGenerator.java index 8cdd48f..04fcd15 100644 --- a/opennlp-tools/src/main/java/opennlp/tools/util/featuregen/PrefixFeatureGenerator.java +++ b/opennlp-tools/src/main/java/opennlp/tools/util/featuregen/PrefixFeatureGenerator.java @@ -21,21 +21,35 @@ import java.util.List; public class PrefixFeatureGenerator implements AdaptiveFeatureGenerator { - private static final int PREFIX_LENGTH = 4; - - private static String[] getPrefixes(String lex) { -String[] prefs = new String[PREFIX_LENGTH]; -for (int li = 0; li < PREFIX_LENGTH; li++) { - prefs[li] = lex.substring(0, Math.min(li + 1, lex.length())); -} -return prefs; + static final int DEFAULT_MAX_LENGTH = 4; + + private final int prefixLength; + + public PrefixFeatureGenerator() { +prefixLength = DEFAULT_MAX_LENGTH; + } + + public PrefixFeatureGenerator(int prefixLength) { +this.prefixLength = prefixLength; } + @Override public void createFeatures(List features, String[] tokens, int index, String[] previousOutcomes) { -String[] prefs = PrefixFeatureGenerator.getPrefixes(tokens[index]); +String[] prefs = getPrefixes(tokens[index]); for (String pref : prefs) { features.add("pre=" + pref); } } + + private String[] getPrefixes(String lex) { + +int prefixes = Math.min(prefixLength, lex.length()); + +String[] prefs = new String[prefixes]; +for (int li = 0; li < prefixes; li++) { + prefs[li] = lex.substring(0, Math.min(li + 1, lex.length())); +} +return prefs; + }
opennlp git commit: OPENNLP-983: Make suffix/prefix length configurable
Repository: opennlp Updated Branches: refs/heads/master 929595d2f -> b7d3abce5 OPENNLP-983: Make suffix/prefix length configurable This closes #121 Project: http://git-wip-us.apache.org/repos/asf/opennlp/repo Commit: http://git-wip-us.apache.org/repos/asf/opennlp/commit/b7d3abce Tree: http://git-wip-us.apache.org/repos/asf/opennlp/tree/b7d3abce Diff: http://git-wip-us.apache.org/repos/asf/opennlp/diff/b7d3abce Branch: refs/heads/master Commit: b7d3abce569b5a4bf0ae39b24c6ac9920032db01 Parents: 929595d Author: jzonthemtnAuthored: Mon Feb 13 07:57:21 2017 -0500 Committer: Jörn Kottmann Committed: Thu Feb 16 10:04:08 2017 +0100 -- .../tools/util/featuregen/GeneratorFactory.java | 22 - .../util/featuregen/PrefixFeatureGenerator.java | 32 +-- .../util/featuregen/SuffixFeatureGenerator.java | 33 +-- .../featuregen/PrefixFeatureGeneratorTest.java | 92 .../featuregen/SuffixFeatureGeneratorTest.java | 92 5 files changed, 251 insertions(+), 20 deletions(-) -- http://git-wip-us.apache.org/repos/asf/opennlp/blob/b7d3abce/opennlp-tools/src/main/java/opennlp/tools/util/featuregen/GeneratorFactory.java -- diff --git a/opennlp-tools/src/main/java/opennlp/tools/util/featuregen/GeneratorFactory.java b/opennlp-tools/src/main/java/opennlp/tools/util/featuregen/GeneratorFactory.java index fa97f43..ef08cfb 100644 --- a/opennlp-tools/src/main/java/opennlp/tools/util/featuregen/GeneratorFactory.java +++ b/opennlp-tools/src/main/java/opennlp/tools/util/featuregen/GeneratorFactory.java @@ -555,7 +555,16 @@ public class GeneratorFactory { public AdaptiveFeatureGenerator create(Element generatorElement, FeatureGeneratorResourceProvider resourceManager) { - return new PrefixFeatureGenerator(); + + String attribute = generatorElement.getAttribute("length"); + + int prefixLength = PrefixFeatureGenerator.DEFAULT_MAX_LENGTH; + + if (!Objects.equals(attribute, "")) { +prefixLength = Integer.parseInt(attribute); + } + + return new PrefixFeatureGenerator(prefixLength); } static void register(Map factoryMap) { @@ -570,7 +579,16 @@ public class GeneratorFactory { public AdaptiveFeatureGenerator create(Element generatorElement, FeatureGeneratorResourceProvider resourceManager) { - return new SuffixFeatureGenerator(); + + String attribute = generatorElement.getAttribute("length"); + + int suffixLength = SuffixFeatureGenerator.DEFAULT_MAX_LENGTH; + + if (!Objects.equals(attribute, "")) { +suffixLength = Integer.parseInt(attribute); + } + + return new SuffixFeatureGenerator(suffixLength); } static void register(Map factoryMap) { http://git-wip-us.apache.org/repos/asf/opennlp/blob/b7d3abce/opennlp-tools/src/main/java/opennlp/tools/util/featuregen/PrefixFeatureGenerator.java -- diff --git a/opennlp-tools/src/main/java/opennlp/tools/util/featuregen/PrefixFeatureGenerator.java b/opennlp-tools/src/main/java/opennlp/tools/util/featuregen/PrefixFeatureGenerator.java index 8cdd48f..04fcd15 100644 --- a/opennlp-tools/src/main/java/opennlp/tools/util/featuregen/PrefixFeatureGenerator.java +++ b/opennlp-tools/src/main/java/opennlp/tools/util/featuregen/PrefixFeatureGenerator.java @@ -21,21 +21,35 @@ import java.util.List; public class PrefixFeatureGenerator implements AdaptiveFeatureGenerator { - private static final int PREFIX_LENGTH = 4; - - private static String[] getPrefixes(String lex) { -String[] prefs = new String[PREFIX_LENGTH]; -for (int li = 0; li < PREFIX_LENGTH; li++) { - prefs[li] = lex.substring(0, Math.min(li + 1, lex.length())); -} -return prefs; + static final int DEFAULT_MAX_LENGTH = 4; + + private final int prefixLength; + + public PrefixFeatureGenerator() { +prefixLength = DEFAULT_MAX_LENGTH; + } + + public PrefixFeatureGenerator(int prefixLength) { +this.prefixLength = prefixLength; } + @Override public void createFeatures(List features, String[] tokens, int index, String[] previousOutcomes) { -String[] prefs = PrefixFeatureGenerator.getPrefixes(tokens[index]); +String[] prefs = getPrefixes(tokens[index]); for (String pref : prefs) { features.add("pre=" + pref); } } + + private String[] getPrefixes(String lex) { + +int prefixes = Math.min(prefixLength, lex.length()); + +String[] prefs = new String[prefixes]; +for (int li = 0; li < prefixes; li++) { + prefs[li] =