This is an automated email from the ASF dual-hosted git repository. krickert pushed a commit to branch light-stemmers in repository https://gitbox.apache.org/repos/asf/opennlp.git
commit 539ec4826fa7263e855b787cc215daab069946ca Author: Kristian Rickert <[email protected]> AuthorDate: Sun Jul 12 15:28:06 2026 -0400 OPENNLP-1886: Trim commentary and tighten javadoc per review conventions --- .../tools/stemmer/light/EnglishMinimalStemmer.java | 2 ++ .../opennlp/tools/stemmer/light/FinnishLightStemmer.java | 2 ++ .../opennlp/tools/stemmer/light/FrenchLightStemmer.java | 2 ++ .../opennlp/tools/stemmer/light/FrenchMinimalStemmer.java | 2 ++ .../opennlp/tools/stemmer/light/GermanLightStemmer.java | 2 ++ .../opennlp/tools/stemmer/light/GermanMinimalStemmer.java | 2 ++ .../tools/stemmer/light/HungarianLightStemmer.java | 2 ++ .../opennlp/tools/stemmer/light/ItalianLightStemmer.java | 2 ++ .../tools/stemmer/light/NorwegianLightStemmer.java | 2 ++ .../tools/stemmer/light/NorwegianMinimalStemmer.java | 2 ++ .../tools/stemmer/light/PortugueseLightStemmer.java | 2 ++ .../opennlp/tools/stemmer/light/RussianLightStemmer.java | 2 ++ .../opennlp/tools/stemmer/light/SpanishLightStemmer.java | 2 ++ .../tools/stemmer/light/SpanishMinimalStemmer.java | 2 ++ .../opennlp/tools/stemmer/light/SwedishLightStemmer.java | 2 ++ .../tools/stemmer/light/SwedishMinimalStemmer.java | 2 ++ .../test/resources/opennlp/tools/stemmer/light/README.txt | 15 ++++----------- 17 files changed, 36 insertions(+), 11 deletions(-) diff --git a/opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/stemmer/light/EnglishMinimalStemmer.java b/opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/stemmer/light/EnglishMinimalStemmer.java index 71c3c983e..d1f9bb6f8 100644 --- a/opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/stemmer/light/EnglishMinimalStemmer.java +++ b/opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/stemmer/light/EnglishMinimalStemmer.java @@ -32,6 +32,7 @@ import opennlp.tools.stemmer.StemmerFactory; */ @ThreadSafe public final class EnglishMinimalStemmer implements Stemmer, StemmerFactory { + /** {@inheritDoc} */ @Override public CharSequence stem(CharSequence word) { if (word == null) { @@ -46,6 +47,7 @@ public final class EnglishMinimalStemmer implements Stemmer, StemmerFactory { return new String(buffer, 0, stemmedLength); } + /** {@inheritDoc} */ @Override public Stemmer newStemmer() { return this; diff --git a/opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/stemmer/light/FinnishLightStemmer.java b/opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/stemmer/light/FinnishLightStemmer.java index 04e002853..b1035ace6 100644 --- a/opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/stemmer/light/FinnishLightStemmer.java +++ b/opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/stemmer/light/FinnishLightStemmer.java @@ -70,6 +70,7 @@ import static opennlp.tools.stemmer.light.StemmerUtil.endsWith; */ @ThreadSafe public final class FinnishLightStemmer implements Stemmer, StemmerFactory { + /** {@inheritDoc} */ @Override public CharSequence stem(CharSequence word) { if (word == null) { @@ -84,6 +85,7 @@ public final class FinnishLightStemmer implements Stemmer, StemmerFactory { return new String(buffer, 0, stemmedLength); } + /** {@inheritDoc} */ @Override public Stemmer newStemmer() { return this; diff --git a/opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/stemmer/light/FrenchLightStemmer.java b/opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/stemmer/light/FrenchLightStemmer.java index db307f875..38f11138a 100644 --- a/opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/stemmer/light/FrenchLightStemmer.java +++ b/opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/stemmer/light/FrenchLightStemmer.java @@ -70,6 +70,7 @@ import static opennlp.tools.stemmer.light.StemmerUtil.endsWith; */ @ThreadSafe public final class FrenchLightStemmer implements Stemmer, StemmerFactory { + /** {@inheritDoc} */ @Override public CharSequence stem(CharSequence word) { if (word == null) { @@ -84,6 +85,7 @@ public final class FrenchLightStemmer implements Stemmer, StemmerFactory { return new String(buffer, 0, stemmedLength); } + /** {@inheritDoc} */ @Override public Stemmer newStemmer() { return this; diff --git a/opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/stemmer/light/FrenchMinimalStemmer.java b/opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/stemmer/light/FrenchMinimalStemmer.java index f34aaa12a..88ddde778 100644 --- a/opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/stemmer/light/FrenchMinimalStemmer.java +++ b/opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/stemmer/light/FrenchMinimalStemmer.java @@ -67,6 +67,7 @@ import opennlp.tools.stemmer.StemmerFactory; */ @ThreadSafe public final class FrenchMinimalStemmer implements Stemmer, StemmerFactory { + /** {@inheritDoc} */ @Override public CharSequence stem(CharSequence word) { if (word == null) { @@ -81,6 +82,7 @@ public final class FrenchMinimalStemmer implements Stemmer, StemmerFactory { return new String(buffer, 0, stemmedLength); } + /** {@inheritDoc} */ @Override public Stemmer newStemmer() { return this; diff --git a/opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/stemmer/light/GermanLightStemmer.java b/opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/stemmer/light/GermanLightStemmer.java index 3a94508cf..e1daca454 100644 --- a/opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/stemmer/light/GermanLightStemmer.java +++ b/opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/stemmer/light/GermanLightStemmer.java @@ -67,6 +67,7 @@ import opennlp.tools.stemmer.StemmerFactory; */ @ThreadSafe public final class GermanLightStemmer implements Stemmer, StemmerFactory { + /** {@inheritDoc} */ @Override public CharSequence stem(CharSequence word) { if (word == null) { @@ -81,6 +82,7 @@ public final class GermanLightStemmer implements Stemmer, StemmerFactory { return new String(buffer, 0, stemmedLength); } + /** {@inheritDoc} */ @Override public Stemmer newStemmer() { return this; diff --git a/opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/stemmer/light/GermanMinimalStemmer.java b/opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/stemmer/light/GermanMinimalStemmer.java index b166de31b..fe711a2ed 100644 --- a/opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/stemmer/light/GermanMinimalStemmer.java +++ b/opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/stemmer/light/GermanMinimalStemmer.java @@ -67,6 +67,7 @@ import opennlp.tools.stemmer.StemmerFactory; */ @ThreadSafe public final class GermanMinimalStemmer implements Stemmer, StemmerFactory { + /** {@inheritDoc} */ @Override public CharSequence stem(CharSequence word) { if (word == null) { @@ -81,6 +82,7 @@ public final class GermanMinimalStemmer implements Stemmer, StemmerFactory { return new String(buffer, 0, stemmedLength); } + /** {@inheritDoc} */ @Override public Stemmer newStemmer() { return this; diff --git a/opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/stemmer/light/HungarianLightStemmer.java b/opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/stemmer/light/HungarianLightStemmer.java index 07ed9ab6d..cb8fed7c6 100644 --- a/opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/stemmer/light/HungarianLightStemmer.java +++ b/opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/stemmer/light/HungarianLightStemmer.java @@ -69,6 +69,7 @@ import static opennlp.tools.stemmer.light.StemmerUtil.endsWith; */ @ThreadSafe public final class HungarianLightStemmer implements Stemmer, StemmerFactory { + /** {@inheritDoc} */ @Override public CharSequence stem(CharSequence word) { if (word == null) { @@ -83,6 +84,7 @@ public final class HungarianLightStemmer implements Stemmer, StemmerFactory { return new String(buffer, 0, stemmedLength); } + /** {@inheritDoc} */ @Override public Stemmer newStemmer() { return this; diff --git a/opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/stemmer/light/ItalianLightStemmer.java b/opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/stemmer/light/ItalianLightStemmer.java index 1714bdcf6..2664775df 100644 --- a/opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/stemmer/light/ItalianLightStemmer.java +++ b/opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/stemmer/light/ItalianLightStemmer.java @@ -67,6 +67,7 @@ import opennlp.tools.stemmer.StemmerFactory; */ @ThreadSafe public final class ItalianLightStemmer implements Stemmer, StemmerFactory { + /** {@inheritDoc} */ @Override public CharSequence stem(CharSequence word) { if (word == null) { @@ -81,6 +82,7 @@ public final class ItalianLightStemmer implements Stemmer, StemmerFactory { return new String(buffer, 0, stemmedLength); } + /** {@inheritDoc} */ @Override public Stemmer newStemmer() { return this; diff --git a/opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/stemmer/light/NorwegianLightStemmer.java b/opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/stemmer/light/NorwegianLightStemmer.java index 3a640f457..4caeb4815 100644 --- a/opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/stemmer/light/NorwegianLightStemmer.java +++ b/opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/stemmer/light/NorwegianLightStemmer.java @@ -70,6 +70,7 @@ import static opennlp.tools.stemmer.light.StemmerUtil.endsWith; */ @ThreadSafe public final class NorwegianLightStemmer implements Stemmer, StemmerFactory { + /** {@inheritDoc} */ @Override public CharSequence stem(CharSequence word) { if (word == null) { @@ -84,6 +85,7 @@ public final class NorwegianLightStemmer implements Stemmer, StemmerFactory { return new String(buffer, 0, stemmedLength); } + /** {@inheritDoc} */ @Override public Stemmer newStemmer() { return this; diff --git a/opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/stemmer/light/NorwegianMinimalStemmer.java b/opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/stemmer/light/NorwegianMinimalStemmer.java index c28eff35f..e079491fd 100644 --- a/opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/stemmer/light/NorwegianMinimalStemmer.java +++ b/opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/stemmer/light/NorwegianMinimalStemmer.java @@ -69,6 +69,7 @@ import static opennlp.tools.stemmer.light.StemmerUtil.endsWith; */ @ThreadSafe public final class NorwegianMinimalStemmer implements Stemmer, StemmerFactory { + /** {@inheritDoc} */ @Override public CharSequence stem(CharSequence word) { if (word == null) { @@ -83,6 +84,7 @@ public final class NorwegianMinimalStemmer implements Stemmer, StemmerFactory { return new String(buffer, 0, stemmedLength); } + /** {@inheritDoc} */ @Override public Stemmer newStemmer() { return this; diff --git a/opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/stemmer/light/PortugueseLightStemmer.java b/opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/stemmer/light/PortugueseLightStemmer.java index 48ab8688e..bf85bbb26 100644 --- a/opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/stemmer/light/PortugueseLightStemmer.java +++ b/opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/stemmer/light/PortugueseLightStemmer.java @@ -69,6 +69,7 @@ import static opennlp.tools.stemmer.light.StemmerUtil.endsWith; */ @ThreadSafe public final class PortugueseLightStemmer implements Stemmer, StemmerFactory { + /** {@inheritDoc} */ @Override public CharSequence stem(CharSequence word) { if (word == null) { @@ -83,6 +84,7 @@ public final class PortugueseLightStemmer implements Stemmer, StemmerFactory { return new String(buffer, 0, stemmedLength); } + /** {@inheritDoc} */ @Override public Stemmer newStemmer() { return this; diff --git a/opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/stemmer/light/RussianLightStemmer.java b/opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/stemmer/light/RussianLightStemmer.java index ffa6016d1..2089b00c2 100644 --- a/opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/stemmer/light/RussianLightStemmer.java +++ b/opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/stemmer/light/RussianLightStemmer.java @@ -69,6 +69,7 @@ import static opennlp.tools.stemmer.light.StemmerUtil.endsWith; */ @ThreadSafe public final class RussianLightStemmer implements Stemmer, StemmerFactory { + /** {@inheritDoc} */ @Override public CharSequence stem(CharSequence word) { if (word == null) { @@ -83,6 +84,7 @@ public final class RussianLightStemmer implements Stemmer, StemmerFactory { return new String(buffer, 0, stemmedLength); } + /** {@inheritDoc} */ @Override public Stemmer newStemmer() { return this; diff --git a/opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/stemmer/light/SpanishLightStemmer.java b/opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/stemmer/light/SpanishLightStemmer.java index 669dcb248..0645593da 100644 --- a/opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/stemmer/light/SpanishLightStemmer.java +++ b/opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/stemmer/light/SpanishLightStemmer.java @@ -67,6 +67,7 @@ import opennlp.tools.stemmer.StemmerFactory; */ @ThreadSafe public final class SpanishLightStemmer implements Stemmer, StemmerFactory { + /** {@inheritDoc} */ @Override public CharSequence stem(CharSequence word) { if (word == null) { @@ -81,6 +82,7 @@ public final class SpanishLightStemmer implements Stemmer, StemmerFactory { return new String(buffer, 0, stemmedLength); } + /** {@inheritDoc} */ @Override public Stemmer newStemmer() { return this; diff --git a/opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/stemmer/light/SpanishMinimalStemmer.java b/opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/stemmer/light/SpanishMinimalStemmer.java index 58959e0a2..b14ad4996 100644 --- a/opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/stemmer/light/SpanishMinimalStemmer.java +++ b/opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/stemmer/light/SpanishMinimalStemmer.java @@ -30,6 +30,7 @@ import opennlp.tools.stemmer.StemmerFactory; @Deprecated @ThreadSafe public final class SpanishMinimalStemmer implements Stemmer, StemmerFactory { + /** {@inheritDoc} */ @Override public CharSequence stem(CharSequence word) { if (word == null) { @@ -44,6 +45,7 @@ public final class SpanishMinimalStemmer implements Stemmer, StemmerFactory { return new String(buffer, 0, stemmedLength); } + /** {@inheritDoc} */ @Override public Stemmer newStemmer() { return this; diff --git a/opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/stemmer/light/SwedishLightStemmer.java b/opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/stemmer/light/SwedishLightStemmer.java index 464586db2..8f835c1a2 100644 --- a/opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/stemmer/light/SwedishLightStemmer.java +++ b/opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/stemmer/light/SwedishLightStemmer.java @@ -69,6 +69,7 @@ import static opennlp.tools.stemmer.light.StemmerUtil.endsWith; */ @ThreadSafe public final class SwedishLightStemmer implements Stemmer, StemmerFactory { + /** {@inheritDoc} */ @Override public CharSequence stem(CharSequence word) { if (word == null) { @@ -83,6 +84,7 @@ public final class SwedishLightStemmer implements Stemmer, StemmerFactory { return new String(buffer, 0, stemmedLength); } + /** {@inheritDoc} */ @Override public Stemmer newStemmer() { return this; diff --git a/opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/stemmer/light/SwedishMinimalStemmer.java b/opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/stemmer/light/SwedishMinimalStemmer.java index 9f3d76d93..1eb2f6454 100644 --- a/opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/stemmer/light/SwedishMinimalStemmer.java +++ b/opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/stemmer/light/SwedishMinimalStemmer.java @@ -70,6 +70,7 @@ import static opennlp.tools.stemmer.light.StemmerUtil.endsWith; */ @ThreadSafe public final class SwedishMinimalStemmer implements Stemmer, StemmerFactory { + /** {@inheritDoc} */ @Override public CharSequence stem(CharSequence word) { if (word == null) { @@ -84,6 +85,7 @@ public final class SwedishMinimalStemmer implements Stemmer, StemmerFactory { return new String(buffer, 0, stemmedLength); } + /** {@inheritDoc} */ @Override public Stemmer newStemmer() { return this; diff --git a/opennlp-core/opennlp-runtime/src/test/resources/opennlp/tools/stemmer/light/README.txt b/opennlp-core/opennlp-runtime/src/test/resources/opennlp/tools/stemmer/light/README.txt index 078e0be03..34bb91bd6 100644 --- a/opennlp-core/opennlp-runtime/src/test/resources/opennlp/tools/stemmer/light/README.txt +++ b/opennlp-core/opennlp-runtime/src/test/resources/opennlp/tools/stemmer/light/README.txt @@ -1,17 +1,10 @@ Parity fixtures for the light and minimal stemmers. -Each <name>.tsv holds word<TAB>expected-stem pairs. The pairs were generated by running the -original Apache Lucene analysis-common stemmer implementations (the code these classes are -adapted from) over the vocabulary word lists of Lucene's own stemmer test data, then sampling -up to 1500 pairs where the stem differs from the word plus 500 where it does not. The Norwegian -files are complete copies of Lucene's small vocabulary lists, split by written standard, and are -generated with the matching variety flag. +Each <name>.tsv holds word<TAB>expected-stem pairs produced by the original Apache Lucene +analysis-common stemmers (the code these classes are adapted from). Each file samples up to 1500 +pairs where the stem differs from the word plus 500 where it does not; the Norwegian files are +complete copies of Lucene's small vocabulary lists, split by written standard. The vocabulary word lists trace back to Jacques Savoy's CLEF resources (http://members.unine.ch/jacques.savoy/clef/index.html), BSD-licensed; see the notice carried in the stemmer sources and the distribution LICENSE. - -To regenerate: compile the Lucene stemmer classes standalone together with a small reflection -driver that reads a word list and writes word<TAB>stem lines, run it per algorithm (Norwegian -with flags 1 for Bokmaal and 2 for Nynorsk), and re-sample. Any behavior difference against the -originals then shows up as a parity test failure, which is the point of these fixtures.
