You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@opennlp.apache.org by rz...@apache.org on 2024/05/27 15:03:35 UTC
(opennlp-models) branch OPENNLP-1561 created (now f2f0b52)
This is an automated email from the ASF dual-hosted git repository.
rzo1 pushed a change to branch OPENNLP-1561
in repository https://gitbox.apache.org/repos/asf/opennlp-models.git
at f2f0b52 OPENNLP-1561 - Add Tokzenizer Models
This branch includes the following new commits:
new f2f0b52 OPENNLP-1561 - Add Tokzenizer Models
The 1 revisions listed above as "new" are entirely new to this
repository and will be described in separate emails. The revisions
listed as "add" were already present in the repository and have only
been added to this reference.
(opennlp-models) 01/01: OPENNLP-1561 - Add Tokzenizer Models
Posted by rz...@apache.org.
This is an automated email from the ASF dual-hosted git repository.
rzo1 pushed a commit to branch OPENNLP-1561
in repository https://gitbox.apache.org/repos/asf/opennlp-models.git
commit f2f0b52aacd51cd180c5f04f5cc4dd0b99acc238
Author: Richard Zowalla <rz...@apache.org>
AuthorDate: Mon May 27 17:03:28 2024 +0200
OPENNLP-1561 - Add Tokzenizer Models
---
opennlp-models-test/pom.xml | 84 ++++++++++++++++++++++
.../src/main/resources/expected-models.txt | 7 +-
.../opennlp-models-tokenizer-de}/pom.xml | 52 +++++++++-----
.../src/main/resources/model.properties | 9 +--
.../opennlp-models-tokenizer-en}/pom.xml | 52 +++++++++-----
.../src/main/resources/model.properties | 9 +--
.../opennlp-models-tokenizer-fr}/pom.xml | 52 +++++++++-----
.../src/main/resources/model.properties | 9 +--
.../opennlp-models-tokenizer-it}/pom.xml | 52 +++++++++-----
.../src/main/resources/model.properties | 9 +--
.../opennlp-models-tokenizer-nl}/pom.xml | 52 +++++++++-----
.../src/main/resources/model.properties | 9 +--
.../pom.xml | 40 ++++-------
pom.xml | 1 +
14 files changed, 290 insertions(+), 147 deletions(-)
diff --git a/opennlp-models-test/pom.xml b/opennlp-models-test/pom.xml
index 43ac0ef..3c125b3 100644
--- a/opennlp-models-test/pom.xml
+++ b/opennlp-models-test/pom.xml
@@ -32,6 +32,90 @@ under the License.
<artifactId>opennlp-models-test</artifactId>
<name>Apache OpenNLP Models :: Tests</name>
+ <dependencies>
+ <!-- These dependencies are added here to influence Maven build order. Test module needs to build last! -->
+ <dependency>
+ <groupId>org.apache.opennlp</groupId>
+ <artifactId>opennlp-models-sentdetect-de</artifactId>
+ <version>${project.version}</version>
+ </dependency>
+ <dependency>
+ <groupId>org.apache.opennlp</groupId>
+ <artifactId>opennlp-models-sentdetect-en</artifactId>
+ <version>${project.version}</version>
+ </dependency>
+ <dependency>
+ <groupId>org.apache.opennlp</groupId>
+ <artifactId>opennlp-models-sentdetect-it</artifactId>
+ <version>${project.version}</version>
+ </dependency>
+ <dependency>
+ <groupId>org.apache.opennlp</groupId>
+ <artifactId>opennlp-models-sentdetect-nl</artifactId>
+ <version>${project.version}</version>
+ </dependency>
+ <dependency>
+ <groupId>org.apache.opennlp</groupId>
+ <artifactId>opennlp-models-sentdetect-fr</artifactId>
+ <version>${project.version}</version>
+ </dependency>
+ <dependency>
+ <groupId>org.apache.opennlp</groupId>
+ <artifactId>opennlp-models-tokenizer-de</artifactId>
+ <version>${project.version}</version>
+ </dependency>
+ <dependency>
+ <groupId>org.apache.opennlp</groupId>
+ <artifactId>opennlp-models-tokenizer-en</artifactId>
+ <version>${project.version}</version>
+ </dependency>
+ <dependency>
+ <groupId>org.apache.opennlp</groupId>
+ <artifactId>opennlp-models-tokenizer-it</artifactId>
+ <version>${project.version}</version>
+ </dependency>
+ <dependency>
+ <groupId>org.apache.opennlp</groupId>
+ <artifactId>opennlp-models-tokenizer-nl</artifactId>
+ <version>${project.version}</version>
+ </dependency>
+ <dependency>
+ <groupId>org.apache.opennlp</groupId>
+ <artifactId>opennlp-models-tokenizer-fr</artifactId>
+ <version>${project.version}</version>
+ </dependency>
+ <dependency>
+ <groupId>org.apache.opennlp</groupId>
+ <artifactId>opennlp-models-pos-de</artifactId>
+ <version>${project.version}</version>
+ </dependency>
+ <dependency>
+ <groupId>org.apache.opennlp</groupId>
+ <artifactId>opennlp-models-pos-en</artifactId>
+ <version>${project.version}</version>
+ </dependency>
+ <dependency>
+ <groupId>org.apache.opennlp</groupId>
+ <artifactId>opennlp-models-pos-it</artifactId>
+ <version>${project.version}</version>
+ </dependency>
+ <dependency>
+ <groupId>org.apache.opennlp</groupId>
+ <artifactId>opennlp-models-pos-nl</artifactId>
+ <version>${project.version}</version>
+ </dependency>
+ <dependency>
+ <groupId>org.apache.opennlp</groupId>
+ <artifactId>opennlp-models-pos-fr</artifactId>
+ <version>${project.version}</version>
+ </dependency>
+ <dependency>
+ <groupId>org.apache.opennlp</groupId>
+ <artifactId>opennlp-models-langdetect</artifactId>
+ <version>${project.version}</version>
+ </dependency>
+ </dependencies>
+
<build>
<plugins>
<plugin>
diff --git a/opennlp-models-test/src/main/resources/expected-models.txt b/opennlp-models-test/src/main/resources/expected-models.txt
index 68c678a..e4ff90e 100644
--- a/opennlp-models-test/src/main/resources/expected-models.txt
+++ b/opennlp-models-test/src/main/resources/expected-models.txt
@@ -18,4 +18,9 @@ opennlp-de-ud-gsd-sentence-1.0-1.9.3.bin
opennlp-en-ud-ewt-sentence-1.0-1.9.3.bin
opennlp-1.0-1.9.3fr-ud-ftb-sentence-1.0-1.9.3.bin
opennlp-nl-ud-alpino-sentence-1.0-1.9.3.bin
-opennlp-nl-ud-alpino-sentence-1.0-1.9.3.bin
\ No newline at end of file
+opennlp-nl-ud-alpino-sentence-1.0-1.9.3.bin
+opennlp-de-ud-gsd-tokens-1.0-1.9.3.bin
+opennlp-en-ud-ewt-tokens-1.0-1.9.3.bin
+opennlp-fr-ud-ftb-tokens-1.0-1.9.3.bin
+opennlp-it-ud-vit-tokens-1.0-1.9.3.bin
+opennlp-nl-ud-alpino-tokens-1.0-1.9.3.bin
\ No newline at end of file
diff --git a/opennlp-models-test/pom.xml b/opennlp-models-tokenizer/opennlp-models-tokenizer-de/pom.xml
similarity index 50%
copy from opennlp-models-test/pom.xml
copy to opennlp-models-tokenizer/opennlp-models-tokenizer-de/pom.xml
index 43ac0ef..eb51ff4 100644
--- a/opennlp-models-test/pom.xml
+++ b/opennlp-models-tokenizer/opennlp-models-tokenizer-de/pom.xml
@@ -25,34 +25,50 @@ under the License.
<modelVersion>4.0.0</modelVersion>
<parent>
<groupId>org.apache.opennlp</groupId>
- <artifactId>opennlp-models</artifactId>
+ <artifactId>opennlp-models-tokenizer</artifactId>
<version>0.1-SNAPSHOT</version>
</parent>
- <artifactId>opennlp-models-test</artifactId>
- <name>Apache OpenNLP Models :: Tests</name>
+ <artifactId>opennlp-models-tokenizer-de</artifactId>
+
+ <name>Apache OpenNLP Models :: Tokenizer :: German</name>
+
+ <properties>
+ <dist.base>${asf.dist.base}</dist.base>
+ <model.family>ud-models-1.0</model.family>
+ <model.name>opennlp-de-ud-gsd-tokens-1.0-1.9.3.bin</model.name>
+ <model.version>1.9.3</model.version>
+ <model.sha256>26ad9f6ed7ee9485b99e0d9785301c8cefe223870dadb5dacb47b07becf28640</model.sha256>
+ </properties>
<build>
+ <resources>
+ <resource>
+ <directory>src/main/resources</directory>
+ <filtering>true</filtering>
+ <includes>
+ <include>**/model.properties</include>
+ </includes>
+ </resource>
+ <resource>
+ <directory>src/main/resources</directory>
+ <includes>
+ <include>**/*.bin</include>
+ </includes>
+ </resource>
+ </resources>
<plugins>
<plugin>
- <groupId>org.codehaus.mojo</groupId>
- <artifactId>exec-maven-plugin</artifactId>
- <version>${exec.plugin.version}</version>
- <executions>
- <execution>
- <phase>verify</phase>
- <goals>
- <goal>java</goal>
- </goals>
- </execution>
- </executions>
+ <groupId>com.googlecode.maven-download-plugin</groupId>
+ <artifactId>download-maven-plugin</artifactId>
<configuration>
- <mainClass>org.apache.opennlp.ModelValidator</mainClass>
- <arguments>
- <argument>${project.basedir}</argument>
- </arguments>
+ <url>${dist.base}/${model.family}/${model.name}</url>
</configuration>
</plugin>
+ <plugin>
+ <groupId>org.codehaus.mojo</groupId>
+ <artifactId>build-helper-maven-plugin</artifactId>
+ </plugin>
</plugins>
</build>
diff --git a/opennlp-models-test/src/main/resources/expected-models.txt b/opennlp-models-tokenizer/opennlp-models-tokenizer-de/src/main/resources/model.properties
similarity index 76%
copy from opennlp-models-test/src/main/resources/expected-models.txt
copy to opennlp-models-tokenizer/opennlp-models-tokenizer-de/src/main/resources/model.properties
index 68c678a..4089d05 100644
--- a/opennlp-models-test/src/main/resources/expected-models.txt
+++ b/opennlp-models-tokenizer/opennlp-models-tokenizer-de/src/main/resources/model.properties
@@ -13,9 +13,6 @@
# See the License for the specific language governing permissions and
# limitations under the License.
-langdetect-183.bin
-opennlp-de-ud-gsd-sentence-1.0-1.9.3.bin
-opennlp-en-ud-ewt-sentence-1.0-1.9.3.bin
-opennlp-1.0-1.9.3fr-ud-ftb-sentence-1.0-1.9.3.bin
-opennlp-nl-ud-alpino-sentence-1.0-1.9.3.bin
-opennlp-nl-ud-alpino-sentence-1.0-1.9.3.bin
\ No newline at end of file
+model.name=${model.name}
+model.version=${model.version}
+model.sha256=${model.sha256}
\ No newline at end of file
diff --git a/opennlp-models-test/pom.xml b/opennlp-models-tokenizer/opennlp-models-tokenizer-en/pom.xml
similarity index 50%
copy from opennlp-models-test/pom.xml
copy to opennlp-models-tokenizer/opennlp-models-tokenizer-en/pom.xml
index 43ac0ef..77d0015 100644
--- a/opennlp-models-test/pom.xml
+++ b/opennlp-models-tokenizer/opennlp-models-tokenizer-en/pom.xml
@@ -25,34 +25,50 @@ under the License.
<modelVersion>4.0.0</modelVersion>
<parent>
<groupId>org.apache.opennlp</groupId>
- <artifactId>opennlp-models</artifactId>
+ <artifactId>opennlp-models-tokenizer</artifactId>
<version>0.1-SNAPSHOT</version>
</parent>
- <artifactId>opennlp-models-test</artifactId>
- <name>Apache OpenNLP Models :: Tests</name>
+ <artifactId>opennlp-models-tokenizer-en</artifactId>
+
+ <name>Apache OpenNLP Models :: Tokenizer :: English</name>
+
+ <properties>
+ <dist.base>${asf.dist.base}</dist.base>
+ <model.family>ud-models-1.0</model.family>
+ <model.name>opennlp-en-ud-ewt-tokens-1.0-1.9.3.bin</model.name>
+ <model.version>1.9.3</model.version>
+ <model.sha256>9df0730d5e54ec6673d46b565a623ea56c2d7caa8aa153eb72b59b1a53de8488</model.sha256>
+ </properties>
<build>
+ <resources>
+ <resource>
+ <directory>src/main/resources</directory>
+ <filtering>true</filtering>
+ <includes>
+ <include>**/model.properties</include>
+ </includes>
+ </resource>
+ <resource>
+ <directory>src/main/resources</directory>
+ <includes>
+ <include>**/*.bin</include>
+ </includes>
+ </resource>
+ </resources>
<plugins>
<plugin>
- <groupId>org.codehaus.mojo</groupId>
- <artifactId>exec-maven-plugin</artifactId>
- <version>${exec.plugin.version}</version>
- <executions>
- <execution>
- <phase>verify</phase>
- <goals>
- <goal>java</goal>
- </goals>
- </execution>
- </executions>
+ <groupId>com.googlecode.maven-download-plugin</groupId>
+ <artifactId>download-maven-plugin</artifactId>
<configuration>
- <mainClass>org.apache.opennlp.ModelValidator</mainClass>
- <arguments>
- <argument>${project.basedir}</argument>
- </arguments>
+ <url>${dist.base}/${model.family}/${model.name}</url>
</configuration>
</plugin>
+ <plugin>
+ <groupId>org.codehaus.mojo</groupId>
+ <artifactId>build-helper-maven-plugin</artifactId>
+ </plugin>
</plugins>
</build>
diff --git a/opennlp-models-test/src/main/resources/expected-models.txt b/opennlp-models-tokenizer/opennlp-models-tokenizer-en/src/main/resources/model.properties
similarity index 76%
copy from opennlp-models-test/src/main/resources/expected-models.txt
copy to opennlp-models-tokenizer/opennlp-models-tokenizer-en/src/main/resources/model.properties
index 68c678a..4089d05 100644
--- a/opennlp-models-test/src/main/resources/expected-models.txt
+++ b/opennlp-models-tokenizer/opennlp-models-tokenizer-en/src/main/resources/model.properties
@@ -13,9 +13,6 @@
# See the License for the specific language governing permissions and
# limitations under the License.
-langdetect-183.bin
-opennlp-de-ud-gsd-sentence-1.0-1.9.3.bin
-opennlp-en-ud-ewt-sentence-1.0-1.9.3.bin
-opennlp-1.0-1.9.3fr-ud-ftb-sentence-1.0-1.9.3.bin
-opennlp-nl-ud-alpino-sentence-1.0-1.9.3.bin
-opennlp-nl-ud-alpino-sentence-1.0-1.9.3.bin
\ No newline at end of file
+model.name=${model.name}
+model.version=${model.version}
+model.sha256=${model.sha256}
\ No newline at end of file
diff --git a/opennlp-models-test/pom.xml b/opennlp-models-tokenizer/opennlp-models-tokenizer-fr/pom.xml
similarity index 50%
copy from opennlp-models-test/pom.xml
copy to opennlp-models-tokenizer/opennlp-models-tokenizer-fr/pom.xml
index 43ac0ef..674bfb0 100644
--- a/opennlp-models-test/pom.xml
+++ b/opennlp-models-tokenizer/opennlp-models-tokenizer-fr/pom.xml
@@ -25,34 +25,50 @@ under the License.
<modelVersion>4.0.0</modelVersion>
<parent>
<groupId>org.apache.opennlp</groupId>
- <artifactId>opennlp-models</artifactId>
+ <artifactId>opennlp-models-tokenizer</artifactId>
<version>0.1-SNAPSHOT</version>
</parent>
- <artifactId>opennlp-models-test</artifactId>
- <name>Apache OpenNLP Models :: Tests</name>
+ <artifactId>opennlp-models-tokenizer-fr</artifactId>
+
+ <name>Apache OpenNLP Models :: Tokenizer :: French</name>
+
+ <properties>
+ <dist.base>${asf.dist.base}</dist.base>
+ <model.family>ud-models-1.0</model.family>
+ <model.name>opennlp-fr-ud-ftb-tokens-1.0-1.9.3.bin</model.name>
+ <model.version>1.9.3</model.version>
+ <model.sha256>a7be8bf3705b25bb473fbb2db4f07588ab1d8869554f772617800e5e3e829e63</model.sha256>
+ </properties>
<build>
+ <resources>
+ <resource>
+ <directory>src/main/resources</directory>
+ <filtering>true</filtering>
+ <includes>
+ <include>**/model.properties</include>
+ </includes>
+ </resource>
+ <resource>
+ <directory>src/main/resources</directory>
+ <includes>
+ <include>**/*.bin</include>
+ </includes>
+ </resource>
+ </resources>
<plugins>
<plugin>
- <groupId>org.codehaus.mojo</groupId>
- <artifactId>exec-maven-plugin</artifactId>
- <version>${exec.plugin.version}</version>
- <executions>
- <execution>
- <phase>verify</phase>
- <goals>
- <goal>java</goal>
- </goals>
- </execution>
- </executions>
+ <groupId>com.googlecode.maven-download-plugin</groupId>
+ <artifactId>download-maven-plugin</artifactId>
<configuration>
- <mainClass>org.apache.opennlp.ModelValidator</mainClass>
- <arguments>
- <argument>${project.basedir}</argument>
- </arguments>
+ <url>${dist.base}/${model.family}/${model.name}</url>
</configuration>
</plugin>
+ <plugin>
+ <groupId>org.codehaus.mojo</groupId>
+ <artifactId>build-helper-maven-plugin</artifactId>
+ </plugin>
</plugins>
</build>
diff --git a/opennlp-models-test/src/main/resources/expected-models.txt b/opennlp-models-tokenizer/opennlp-models-tokenizer-fr/src/main/resources/model.properties
similarity index 76%
copy from opennlp-models-test/src/main/resources/expected-models.txt
copy to opennlp-models-tokenizer/opennlp-models-tokenizer-fr/src/main/resources/model.properties
index 68c678a..4089d05 100644
--- a/opennlp-models-test/src/main/resources/expected-models.txt
+++ b/opennlp-models-tokenizer/opennlp-models-tokenizer-fr/src/main/resources/model.properties
@@ -13,9 +13,6 @@
# See the License for the specific language governing permissions and
# limitations under the License.
-langdetect-183.bin
-opennlp-de-ud-gsd-sentence-1.0-1.9.3.bin
-opennlp-en-ud-ewt-sentence-1.0-1.9.3.bin
-opennlp-1.0-1.9.3fr-ud-ftb-sentence-1.0-1.9.3.bin
-opennlp-nl-ud-alpino-sentence-1.0-1.9.3.bin
-opennlp-nl-ud-alpino-sentence-1.0-1.9.3.bin
\ No newline at end of file
+model.name=${model.name}
+model.version=${model.version}
+model.sha256=${model.sha256}
\ No newline at end of file
diff --git a/opennlp-models-test/pom.xml b/opennlp-models-tokenizer/opennlp-models-tokenizer-it/pom.xml
similarity index 50%
copy from opennlp-models-test/pom.xml
copy to opennlp-models-tokenizer/opennlp-models-tokenizer-it/pom.xml
index 43ac0ef..1deeef5 100644
--- a/opennlp-models-test/pom.xml
+++ b/opennlp-models-tokenizer/opennlp-models-tokenizer-it/pom.xml
@@ -25,34 +25,50 @@ under the License.
<modelVersion>4.0.0</modelVersion>
<parent>
<groupId>org.apache.opennlp</groupId>
- <artifactId>opennlp-models</artifactId>
+ <artifactId>opennlp-models-tokenizer</artifactId>
<version>0.1-SNAPSHOT</version>
</parent>
- <artifactId>opennlp-models-test</artifactId>
- <name>Apache OpenNLP Models :: Tests</name>
+ <artifactId>opennlp-models-tokenizer-it</artifactId>
+
+ <name>Apache OpenNLP Models :: Tokenizer :: Italian</name>
+
+ <properties>
+ <dist.base>${asf.dist.base}</dist.base>
+ <model.family>ud-models-1.0</model.family>
+ <model.name>opennlp-it-ud-vit-tokens-1.0-1.9.3.bin</model.name>
+ <model.version>1.9.3</model.version>
+ <model.sha256>933cea412fe026e815d7a618d54c1431154731d2541e604c3a53c70c036a0102</model.sha256>
+ </properties>
<build>
+ <resources>
+ <resource>
+ <directory>src/main/resources</directory>
+ <filtering>true</filtering>
+ <includes>
+ <include>**/model.properties</include>
+ </includes>
+ </resource>
+ <resource>
+ <directory>src/main/resources</directory>
+ <includes>
+ <include>**/*.bin</include>
+ </includes>
+ </resource>
+ </resources>
<plugins>
<plugin>
- <groupId>org.codehaus.mojo</groupId>
- <artifactId>exec-maven-plugin</artifactId>
- <version>${exec.plugin.version}</version>
- <executions>
- <execution>
- <phase>verify</phase>
- <goals>
- <goal>java</goal>
- </goals>
- </execution>
- </executions>
+ <groupId>com.googlecode.maven-download-plugin</groupId>
+ <artifactId>download-maven-plugin</artifactId>
<configuration>
- <mainClass>org.apache.opennlp.ModelValidator</mainClass>
- <arguments>
- <argument>${project.basedir}</argument>
- </arguments>
+ <url>${dist.base}/${model.family}/${model.name}</url>
</configuration>
</plugin>
+ <plugin>
+ <groupId>org.codehaus.mojo</groupId>
+ <artifactId>build-helper-maven-plugin</artifactId>
+ </plugin>
</plugins>
</build>
diff --git a/opennlp-models-test/src/main/resources/expected-models.txt b/opennlp-models-tokenizer/opennlp-models-tokenizer-it/src/main/resources/model.properties
similarity index 76%
copy from opennlp-models-test/src/main/resources/expected-models.txt
copy to opennlp-models-tokenizer/opennlp-models-tokenizer-it/src/main/resources/model.properties
index 68c678a..4089d05 100644
--- a/opennlp-models-test/src/main/resources/expected-models.txt
+++ b/opennlp-models-tokenizer/opennlp-models-tokenizer-it/src/main/resources/model.properties
@@ -13,9 +13,6 @@
# See the License for the specific language governing permissions and
# limitations under the License.
-langdetect-183.bin
-opennlp-de-ud-gsd-sentence-1.0-1.9.3.bin
-opennlp-en-ud-ewt-sentence-1.0-1.9.3.bin
-opennlp-1.0-1.9.3fr-ud-ftb-sentence-1.0-1.9.3.bin
-opennlp-nl-ud-alpino-sentence-1.0-1.9.3.bin
-opennlp-nl-ud-alpino-sentence-1.0-1.9.3.bin
\ No newline at end of file
+model.name=${model.name}
+model.version=${model.version}
+model.sha256=${model.sha256}
\ No newline at end of file
diff --git a/opennlp-models-test/pom.xml b/opennlp-models-tokenizer/opennlp-models-tokenizer-nl/pom.xml
similarity index 50%
copy from opennlp-models-test/pom.xml
copy to opennlp-models-tokenizer/opennlp-models-tokenizer-nl/pom.xml
index 43ac0ef..680268b 100644
--- a/opennlp-models-test/pom.xml
+++ b/opennlp-models-tokenizer/opennlp-models-tokenizer-nl/pom.xml
@@ -25,34 +25,50 @@ under the License.
<modelVersion>4.0.0</modelVersion>
<parent>
<groupId>org.apache.opennlp</groupId>
- <artifactId>opennlp-models</artifactId>
+ <artifactId>opennlp-models-tokenizer</artifactId>
<version>0.1-SNAPSHOT</version>
</parent>
- <artifactId>opennlp-models-test</artifactId>
- <name>Apache OpenNLP Models :: Tests</name>
+ <artifactId>opennlp-models-tokenizer-nl</artifactId>
+
+ <name>Apache OpenNLP Models :: Tokenizer :: Dutch</name>
+
+ <properties>
+ <dist.base>${asf.dist.base}</dist.base>
+ <model.family>ud-models-1.0</model.family>
+ <model.name>opennlp-nl-ud-alpino-tokens-1.0-1.9.3.bin</model.name>
+ <model.version>1.9.3</model.version>
+ <model.sha256>5b2d215c73a9bd2939e988ffea34a2c2cd212931a074187916530f59d6f19caf</model.sha256>
+ </properties>
<build>
+ <resources>
+ <resource>
+ <directory>src/main/resources</directory>
+ <filtering>true</filtering>
+ <includes>
+ <include>**/model.properties</include>
+ </includes>
+ </resource>
+ <resource>
+ <directory>src/main/resources</directory>
+ <includes>
+ <include>**/*.bin</include>
+ </includes>
+ </resource>
+ </resources>
<plugins>
<plugin>
- <groupId>org.codehaus.mojo</groupId>
- <artifactId>exec-maven-plugin</artifactId>
- <version>${exec.plugin.version}</version>
- <executions>
- <execution>
- <phase>verify</phase>
- <goals>
- <goal>java</goal>
- </goals>
- </execution>
- </executions>
+ <groupId>com.googlecode.maven-download-plugin</groupId>
+ <artifactId>download-maven-plugin</artifactId>
<configuration>
- <mainClass>org.apache.opennlp.ModelValidator</mainClass>
- <arguments>
- <argument>${project.basedir}</argument>
- </arguments>
+ <url>${dist.base}/${model.family}/${model.name}</url>
</configuration>
</plugin>
+ <plugin>
+ <groupId>org.codehaus.mojo</groupId>
+ <artifactId>build-helper-maven-plugin</artifactId>
+ </plugin>
</plugins>
</build>
diff --git a/opennlp-models-test/src/main/resources/expected-models.txt b/opennlp-models-tokenizer/opennlp-models-tokenizer-nl/src/main/resources/model.properties
similarity index 76%
copy from opennlp-models-test/src/main/resources/expected-models.txt
copy to opennlp-models-tokenizer/opennlp-models-tokenizer-nl/src/main/resources/model.properties
index 68c678a..4089d05 100644
--- a/opennlp-models-test/src/main/resources/expected-models.txt
+++ b/opennlp-models-tokenizer/opennlp-models-tokenizer-nl/src/main/resources/model.properties
@@ -13,9 +13,6 @@
# See the License for the specific language governing permissions and
# limitations under the License.
-langdetect-183.bin
-opennlp-de-ud-gsd-sentence-1.0-1.9.3.bin
-opennlp-en-ud-ewt-sentence-1.0-1.9.3.bin
-opennlp-1.0-1.9.3fr-ud-ftb-sentence-1.0-1.9.3.bin
-opennlp-nl-ud-alpino-sentence-1.0-1.9.3.bin
-opennlp-nl-ud-alpino-sentence-1.0-1.9.3.bin
\ No newline at end of file
+model.name=${model.name}
+model.version=${model.version}
+model.sha256=${model.sha256}
\ No newline at end of file
diff --git a/opennlp-models-test/pom.xml b/opennlp-models-tokenizer/pom.xml
similarity index 56%
copy from opennlp-models-test/pom.xml
copy to opennlp-models-tokenizer/pom.xml
index 43ac0ef..d30e2d7 100644
--- a/opennlp-models-test/pom.xml
+++ b/opennlp-models-tokenizer/pom.xml
@@ -29,31 +29,19 @@ under the License.
<version>0.1-SNAPSHOT</version>
</parent>
- <artifactId>opennlp-models-test</artifactId>
- <name>Apache OpenNLP Models :: Tests</name>
-
- <build>
- <plugins>
- <plugin>
- <groupId>org.codehaus.mojo</groupId>
- <artifactId>exec-maven-plugin</artifactId>
- <version>${exec.plugin.version}</version>
- <executions>
- <execution>
- <phase>verify</phase>
- <goals>
- <goal>java</goal>
- </goals>
- </execution>
- </executions>
- <configuration>
- <mainClass>org.apache.opennlp.ModelValidator</mainClass>
- <arguments>
- <argument>${project.basedir}</argument>
- </arguments>
- </configuration>
- </plugin>
- </plugins>
- </build>
+ <artifactId>opennlp-models-tokenizer</artifactId>
+
+ <name>Apache OpenNLP Models :: Tokenizer</name>
+
+ <packaging>pom</packaging>
+
+ <modules>
+ <module>opennlp-models-tokenizer-de</module>
+ <module>opennlp-models-tokenizer-en</module>
+ <module>opennlp-models-tokenizer-fr</module>
+ <module>opennlp-models-tokenizer-it</module>
+ <module>opennlp-models-tokenizer-nl</module>
+ </modules>
+
</project>
\ No newline at end of file
diff --git a/pom.xml b/pom.xml
index a5221d8..51b494a 100644
--- a/pom.xml
+++ b/pom.xml
@@ -254,6 +254,7 @@
<module>opennlp-models-langdetect</module>
<module>opennlp-models-sentdetect</module>
<module>opennlp-models-test</module>
+ <module>opennlp-models-tokenizer</module>
</modules>
</project>