You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@opennlp.apache.org by ma...@apache.org on 2025/12/27 13:13:36 UTC
(opennlp) branch OPENNLP-1792-Add-docbkx-plugin-config-to-produce-PDF-of-dev-manual created (now 2bd3085f)
This is an automated email from the ASF dual-hosted git repository.
mawiesne pushed a change to branch OPENNLP-1792-Add-docbkx-plugin-config-to-produce-PDF-of-dev-manual
in repository https://gitbox.apache.org/repos/asf/opennlp.git
at 2bd3085f OPENNLP-1792: Add docbkx plugin config to produce PDF of dev manual - modernizes xml files of the OpenNLP dev manual to use Docbook dtd in version 5.x - adds plugin configuration to produce the PDF as separate outcome - adds xsl file for customization of the layout of text in the PDF - adds hyphenation support for PDF version - introduces specific profiles for html, pdf, and potentially epub3 targets - fixes inconsistencies in dev manual's structure (duplicate ids...) - [...]
This branch includes the following new commits:
new 2bd3085f OPENNLP-1792: Add docbkx plugin config to produce PDF of dev manual - modernizes xml files of the OpenNLP dev manual to use Docbook dtd in version 5.x - adds plugin configuration to produce the PDF as separate outcome - adds xsl file for customization of the layout of text in the PDF - adds hyphenation support for PDF version - introduces specific profiles for html, pdf, and potentially epub3 targets - fixes inconsistencies in dev manual's structure (duplicate ids...) - [...]
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) 01/01: OPENNLP-1792: Add docbkx plugin config to produce PDF of dev manual - modernizes xml files of the OpenNLP dev manual to use Docbook dtd in version 5.x - adds plugin configuration to produce the PDF as separate outcome - adds xsl file for customization of the layout of text in the PDF - adds hyphenation support for PDF version - introduces specific profiles for html, pdf, and potentially epub3 targets - fixes inconsistencies in dev manual's structure (duplicate ids...) - fixes 'informaltabl [...]
Posted by ma...@apache.org.
This is an automated email from the ASF dual-hosted git repository.
mawiesne pushed a commit to branch OPENNLP-1792-Add-docbkx-plugin-config-to-produce-PDF-of-dev-manual
in repository https://gitbox.apache.org/repos/asf/opennlp.git
commit 2bd3085f00bc2ddeadcd6ac6ac12530c21fb77f7
Author: Martin Wiesner <ma...@hs-heilbronn.de>
AuthorDate: Sat Dec 27 14:13:27 2025 +0100
OPENNLP-1792: Add docbkx plugin config to produce PDF of dev manual
- modernizes xml files of the OpenNLP dev manual to use Docbook dtd in version 5.x
- adds plugin configuration to produce the PDF as separate outcome
- adds xsl file for customization of the layout of text in the PDF
- adds hyphenation support for PDF version
- introduces specific profiles for html, pdf, and potentially epub3 targets
- fixes inconsistencies in dev manual's structure (duplicate ids...)
- fixes 'informaltable' column counts, mainly in cli.xml
---
opennlp-docs/pom.xml | 151 ++++--
opennlp-docs/src/docbkx/chunker.xml | 4 +-
opennlp-docs/src/docbkx/cli.xml | 709 +++++++++++++++++++--------
opennlp-docs/src/docbkx/coref.xml | 4 +-
opennlp-docs/src/docbkx/corpora.xml | 4 +-
opennlp-docs/src/docbkx/doccat.xml | 6 +-
opennlp-docs/src/docbkx/evaltest.xml | 4 +-
opennlp-docs/src/docbkx/extension.xml | 4 +-
opennlp-docs/src/docbkx/introduction.xml | 6 +-
opennlp-docs/src/docbkx/langdetect.xml | 4 +-
opennlp-docs/src/docbkx/lemmatizer.xml | 4 +-
opennlp-docs/src/docbkx/machine-learning.xml | 4 +-
opennlp-docs/src/docbkx/model-loading.xml | 4 +-
opennlp-docs/src/docbkx/morfologik-addon.xml | 4 +-
opennlp-docs/src/docbkx/namefinder.xml | 6 +-
opennlp-docs/src/docbkx/opennlp.xml | 8 +-
opennlp-docs/src/docbkx/parser.xml | 4 +-
opennlp-docs/src/docbkx/postagger.xml | 4 +-
opennlp-docs/src/docbkx/sentdetect.xml | 4 +-
opennlp-docs/src/docbkx/tokenizer.xml | 4 +-
opennlp-docs/src/docbkx/uima-integration.xml | 4 +-
opennlp-docs/src/docbkx/xsl/docbook-fo.xsl | 54 ++
22 files changed, 717 insertions(+), 283 deletions(-)
diff --git a/opennlp-docs/pom.xml b/opennlp-docs/pom.xml
index 9d6c656e..ada724bd 100644
--- a/opennlp-docs/pom.xml
+++ b/opennlp-docs/pom.xml
@@ -31,46 +31,113 @@
<artifactId>opennlp-docs</artifactId>
<packaging>pom</packaging>
<name>Apache OpenNLP :: Documentation</name>
-
- <build>
- <plugins>
- <plugin>
- <groupId>com.agilejava.docbkx</groupId>
- <artifactId>docbkx-maven-plugin</artifactId>
- <version>2.0.17</version>
- <executions>
- <execution>
- <goals>
- <goal>generate-html</goal>
- </goals>
- <phase>package</phase>
- </execution>
- </executions>
- <dependencies>
- <dependency>
- <groupId>org.docbook</groupId>
- <artifactId>docbook-xml</artifactId>
- <version>4.4</version>
- </dependency>
- </dependencies>
- <configuration>
- <xincludeSupported>true</xincludeSupported>
- <includes>opennlp.xml</includes>
- <htmlStylesheet>css/opennlp-docs.css</htmlStylesheet>
- <highlightSource>1</highlightSource>
- <htmlCustomization>${project.basedir}/src/main/resources/xsl/html.xsl</htmlCustomization>
- <postProcess>
- <copy todir="${project.build.directory}/docbkx/html">
- <fileset dir="${project.basedir}/src/docbkx">
- <include name="**/*.css" />
- <include name="**/*.png" />
- <include name="**/*.gif" />
- <include name="**/*.jpg" />
- </fileset>
- </copy>
- </postProcess>
- </configuration>
- </plugin>
- </plugins>
- </build>
+
+ <profiles>
+ <profile>
+ <id>doc-manual-html</id>
+ <activation>
+ <activeByDefault>true</activeByDefault>
+ </activation>
+ <build>
+ <plugins>
+ <plugin>
+ <groupId>com.agilejava.docbkx</groupId>
+ <artifactId>docbkx-maven-plugin</artifactId>
+ <executions>
+ <execution>
+ <id>doc-manual-html</id>
+ <goals>
+ <goal>generate-html</goal>
+ </goals>
+ <phase>package</phase>
+ </execution>
+ </executions>
+ <configuration>
+ <xincludeSupported>true</xincludeSupported>
+ <includes>opennlp.xml</includes>
+ <htmlStylesheet>css/opennlp-docs.css</htmlStylesheet>
+ <highlightSource>1</highlightSource>
+ <htmlCustomization>${project.basedir}/src/main/resources/xsl/html.xsl</htmlCustomization>
+ <postProcess>
+ <copy todir="${project.build.directory}/docbkx/html">
+ <fileset dir="${project.basedir}/src/docbkx">
+ <include name="**/*.css" />
+ <include name="**/*.png" />
+ <include name="**/*.gif" />
+ <include name="**/*.jpg" />
+ </fileset>
+ </copy>
+ </postProcess>
+ </configuration>
+ </plugin>
+ </plugins>
+ </build>
+ </profile>
+ <profile>
+ <id>doc-manual-pdf</id>
+ <activation>
+ <activeByDefault>false</activeByDefault>
+ </activation>
+ <build>
+ <plugins>
+ <plugin>
+ <groupId>com.agilejava.docbkx</groupId>
+ <artifactId>docbkx-maven-plugin</artifactId>
+ <executions>
+ <execution>
+ <id>dev-manual-pdf</id>
+ <goals>
+ <goal>generate-pdf</goal>
+ </goals>
+ <phase>package</phase>
+ </execution>
+ </executions>
+ <configuration>
+ <xincludeSupported>true</xincludeSupported>
+ <includes>opennlp.xml</includes>
+ <foCustomization>src/docbkx/xsl/docbook-fo.xsl</foCustomization>
+ <highlightSource>1</highlightSource>
+ <hyphenate>true</hyphenate>
+ <hyphenateVerbatim>false</hyphenateVerbatim>
+ <showXslMessages>false</showXslMessages>
+ </configuration>
+ </plugin>
+ </plugins>
+ </build>
+ </profile>
+ </profiles>
+
+ <build>
+ <pluginManagement>
+ <plugins>
+ <plugin>
+ <groupId>com.agilejava.docbkx</groupId>
+ <artifactId>docbkx-maven-plugin</artifactId>
+ <version>2.0.17</version>
+ <dependencies>
+ <dependency>
+ <groupId>net.sf.docbook</groupId>
+ <artifactId>docbook-xml</artifactId>
+ <version>5.0-all</version>
+ <classifier>resources</classifier>
+ <type>zip</type>
+ <scope>runtime</scope>
+ </dependency>
+ <dependency>
+ <groupId>net.sf.xslthl</groupId>
+ <artifactId>xslthl</artifactId>
+ <version>2.0.1</version>
+ <scope>runtime</scope>
+ </dependency>
+ <dependency>
+ <groupId>net.sf.offo</groupId>
+ <artifactId>fop-hyph</artifactId>
+ <version>1.2</version>
+ <scope>runtime</scope>
+ </dependency>
+ </dependencies>
+ </plugin>
+ </plugins>
+ </pluginManagement>
+ </build>
</project>
diff --git a/opennlp-docs/src/docbkx/chunker.xml b/opennlp-docs/src/docbkx/chunker.xml
index 44481992..35679f68 100644
--- a/opennlp-docs/src/docbkx/chunker.xml
+++ b/opennlp-docs/src/docbkx/chunker.xml
@@ -1,6 +1,6 @@
<?xml version="1.0" encoding="UTF-8"?>
-<!DOCTYPE chapter PUBLIC "-//OASIS//DTD DocBook XML V4.4//EN"
-"http://www.oasis-open.org/docbook/xml/4.4/docbookx.dtd"[
+<!DOCTYPE chapter PUBLIC "-//OASIS//DTD DocBook XML V5.0//EN"
+"https://docbook.org/xml/5.0.1/dtd/docbook.dtd"[
]>
<!--
Licensed to the Apache Software Foundation (ASF) under one
diff --git a/opennlp-docs/src/docbkx/cli.xml b/opennlp-docs/src/docbkx/cli.xml
index adc6538d..7cf7f556 100644
--- a/opennlp-docs/src/docbkx/cli.xml
+++ b/opennlp-docs/src/docbkx/cli.xml
@@ -1,6 +1,6 @@
<?xml version="1.0" encoding="UTF-8"?>
-<!DOCTYPE chapter PUBLIC "-//OASIS//DTD DocBook XML V4.4//EN"
-"http://www.oasis-open.org/docbook/xml/4.4/docbookx.dtd"[
+<!DOCTYPE chapter PUBLIC "-//OASIS//DTD DocBook XML V5.0//EN"
+"https://docbook.org/xml/5.0.1/dtd/docbook.dtd"[
]>
<!--
Licensed to the Apache Software Foundation (ASF) under one
@@ -84,8 +84,18 @@ Arguments description:
</screen>
<para>The supported formats and arguments are:</para>
-<informaltable frame='all'><tgroup cols='4' align='left' colsep='1' rowsep='1'>
-<thead><row><entry>Format</entry><entry>Argument</entry><entry>Value</entry><entry>Optional</entry><entry>Description</entry></row></thead>
+<informaltable frame='all'>
+
+<tgroup cols='5' align='left' colsep='1' rowsep='1'>
+<thead>
+ <row>
+ <entry>Format</entry>
+ <entry>Argument</entry>
+ <entry>Value</entry>
+ <entry>Optional</entry>
+ <entry>Description</entry>
+ </row>
+</thead>
<tbody>
<row>
<entry morerows='1' valign='middle'>leipzig</entry>
@@ -113,8 +123,8 @@ Arguments description:
<screen>
<![CDATA[
-Usage: opennlp DoccatEvaluator[.leipzig] -model model [-misclassified true|false] [-reportOutputFile
- outputFile] -data sampleData [-encoding charsetName]
+Usage: opennlp DoccatEvaluator[.leipzig] -model model [-misclassified true|false] [-reportOutputFile
+ outputFile] -data sampleData [-encoding charsetName]
Arguments description:
-model model
the model file to be evaluated.
@@ -128,11 +138,20 @@ Arguments description:
encoding for reading and writing text, if absent the system default is used.
]]>
-</screen>
+</screen>
<para>The supported formats and arguments are:</para>
-<informaltable frame='all'><tgroup cols='4' align='left' colsep='1' rowsep='1'>
-<thead><row><entry>Format</entry><entry>Argument</entry><entry>Value</entry><entry>Optional</entry><entry>Description</entry></row></thead>
+<informaltable frame='all'>
+<tgroup cols='5' align='left' colsep='1' rowsep='1'>
+<thead>
+ <row>
+ <entry>Format</entry>
+ <entry>Argument</entry>
+ <entry>Value</entry>
+ <entry>Optional</entry>
+ <entry>Description</entry>
+ </row>
+</thead>
<tbody>
<row>
<entry morerows='1' valign='middle'>leipzig</entry>
@@ -160,9 +179,9 @@ Arguments description:
<screen>
<![CDATA[
-Usage: opennlp DoccatCrossValidator[.leipzig] [-misclassified true|false] [-folds num] [-factory factoryName]
- [-featureGenerators fg] [-tokenizer tokenizer] [-params paramsFile] -lang language [-reportOutputFile
- outputFile] -data sampleData [-encoding charsetName]
+Usage: opennlp DoccatCrossValidator[.leipzig] [-misclassified true|false] [-folds num] [-factory factoryName]
+ [-featureGenerators fg] [-tokenizer tokenizer] [-params paramsFile] -lang language [-reportOutputFile
+ outputFile] -data sampleData [-encoding charsetName]
Arguments description:
-misclassified true|false
if true will print false negatives and false positives.
@@ -186,11 +205,20 @@ Arguments description:
encoding for reading and writing text, if absent the system default is used.
]]>
-</screen>
+</screen>
<para>The supported formats and arguments are:</para>
-<informaltable frame='all'><tgroup cols='4' align='left' colsep='1' rowsep='1'>
-<thead><row><entry>Format</entry><entry>Argument</entry><entry>Value</entry><entry>Optional</entry><entry>Description</entry></row></thead>
+<informaltable frame='all'>
+<tgroup cols='5' align='left' colsep='1' rowsep='1'>
+<thead>
+ <row>
+ <entry>Format</entry>
+ <entry>Argument</entry>
+ <entry>Value</entry>
+ <entry>Optional</entry>
+ <entry>Description</entry>
+ </row>
+</thead>
<tbody>
<row>
<entry morerows='1' valign='middle'>leipzig</entry>
@@ -221,11 +249,20 @@ Arguments description:
Usage: opennlp DoccatConverter help|leipzig [help|options...]
]]>
-</screen>
+</screen>
<para>The supported formats and arguments are:</para>
-<informaltable frame='all'><tgroup cols='4' align='left' colsep='1' rowsep='1'>
-<thead><row><entry>Format</entry><entry>Argument</entry><entry>Value</entry><entry>Optional</entry><entry>Description</entry></row></thead>
+<informaltable frame='all'>
+<tgroup cols='5' align='left' colsep='1' rowsep='1'>
+<thead>
+ <row>
+ <entry>Format</entry>
+ <entry>Argument</entry>
+ <entry>Value</entry>
+ <entry>Optional</entry>
+ <entry>Description</entry>
+ </row>
+</thead>
<tbody>
<row>
<entry morerows='1' valign='middle'>leipzig</entry>
@@ -262,7 +299,7 @@ Usage: opennlp DoccatConverter help|leipzig [help|options...]
Usage: opennlp LanguageDetector model < documents
]]>
-</screen>
+</screen>
</section>
<section id='tools.cli.langdetect.LanguageDetectorTrainer'>
@@ -273,8 +310,8 @@ Usage: opennlp LanguageDetector model < documents
<screen>
<![CDATA[
-Usage: opennlp LanguageDetectorTrainer[.leipzig] -model modelFile [-params paramsFile] [-factory factoryName]
- -data sampleData [-encoding charsetName]
+Usage: opennlp LanguageDetectorTrainer[.leipzig] -model modelFile [-params paramsFile] [-factory factoryName]
+ -data sampleData [-encoding charsetName]
Arguments description:
-model modelFile
output model file.
@@ -288,11 +325,20 @@ Arguments description:
encoding for reading and writing text, if absent the system default is used.
]]>
-</screen>
+</screen>
<para>The supported formats and arguments are:</para>
-<informaltable frame='all'><tgroup cols='4' align='left' colsep='1' rowsep='1'>
-<thead><row><entry>Format</entry><entry>Argument</entry><entry>Value</entry><entry>Optional</entry><entry>Description</entry></row></thead>
+<informaltable frame='all'>
+<tgroup cols='5' align='left' colsep='1' rowsep='1'>
+<thead>
+ <row>
+ <entry>Format</entry>
+ <entry>Argument</entry>
+ <entry>Value</entry>
+ <entry>Optional</entry>
+ <entry>Description</entry>
+ </row>
+</thead>
<tbody>
<row>
<entry morerows='3' valign='middle'>leipzig</entry>
@@ -335,11 +381,20 @@ Arguments description:
Usage: opennlp LanguageDetectorConverter help|leipzig [help|options...]
]]>
-</screen>
+</screen>
<para>The supported formats and arguments are:</para>
-<informaltable frame='all'><tgroup cols='4' align='left' colsep='1' rowsep='1'>
-<thead><row><entry>Format</entry><entry>Argument</entry><entry>Value</entry><entry>Optional</entry><entry>Description</entry></row></thead>
+<informaltable frame='all'>
+<tgroup cols='5' align='left' colsep='1' rowsep='1'>
+<thead>
+ <row>
+ <entry>Format</entry>
+ <entry>Argument</entry>
+ <entry>Value</entry>
+ <entry>Optional</entry>
+ <entry>Description</entry>
+ </row>
+</thead>
<tbody>
<row>
<entry morerows='3' valign='middle'>leipzig</entry>
@@ -379,9 +434,9 @@ Usage: opennlp LanguageDetectorConverter help|leipzig [help|options...]
<screen>
<![CDATA[
-Usage: opennlp LanguageDetectorCrossValidator[.leipzig] [-misclassified true|false] [-folds num] [-factory
- factoryName] [-params paramsFile] [-reportOutputFile outputFile] -data sampleData [-encoding
- charsetName]
+Usage: opennlp LanguageDetectorCrossValidator[.leipzig] [-misclassified true|false] [-folds num] [-factory
+ factoryName] [-params paramsFile] [-reportOutputFile outputFile] -data sampleData [-encoding
+ charsetName]
Arguments description:
-misclassified true|false
if true will print false negatives and false positives.
@@ -399,11 +454,20 @@ Arguments description:
encoding for reading and writing text, if absent the system default is used.
]]>
-</screen>
+</screen>
<para>The supported formats and arguments are:</para>
-<informaltable frame='all'><tgroup cols='4' align='left' colsep='1' rowsep='1'>
-<thead><row><entry>Format</entry><entry>Argument</entry><entry>Value</entry><entry>Optional</entry><entry>Description</entry></row></thead>
+<informaltable frame='all'>
+<tgroup cols='5' align='left' colsep='1' rowsep='1'>
+<thead>
+ <row>
+ <entry>Format</entry>
+ <entry>Argument</entry>
+ <entry>Value</entry>
+ <entry>Optional</entry>
+ <entry>Description</entry>
+ </row>
+</thead>
<tbody>
<row>
<entry morerows='3' valign='middle'>leipzig</entry>
@@ -443,8 +507,8 @@ Arguments description:
<screen>
<![CDATA[
-Usage: opennlp LanguageDetectorEvaluator[.leipzig] -model model [-misclassified true|false]
- [-reportOutputFile outputFile] -data sampleData [-encoding charsetName]
+Usage: opennlp LanguageDetectorEvaluator[.leipzig] -model model [-misclassified true|false]
+ [-reportOutputFile outputFile] -data sampleData [-encoding charsetName]
Arguments description:
-model model
the model file to be evaluated.
@@ -458,11 +522,20 @@ Arguments description:
encoding for reading and writing text, if absent the system default is used.
]]>
-</screen>
+</screen>
<para>The supported formats and arguments are:</para>
-<informaltable frame='all'><tgroup cols='4' align='left' colsep='1' rowsep='1'>
-<thead><row><entry>Format</entry><entry>Argument</entry><entry>Value</entry><entry>Optional</entry><entry>Description</entry></row></thead>
+<informaltable frame='all'>
+<tgroup cols='5' align='left' colsep='1' rowsep='1'>
+<thead>
+ <row>
+ <entry>Format</entry>
+ <entry>Argument</entry>
+ <entry>Value</entry>
+ <entry>Optional</entry>
+ <entry>Description</entry>
+ </row>
+</thead>
<tbody>
<row>
<entry morerows='3' valign='middle'>leipzig</entry>
@@ -519,7 +592,7 @@ Arguments description:
encoding for reading and writing text, if absent the system default is used.
]]>
-</screen>
+</screen>
</section>
</section>
@@ -539,7 +612,7 @@ Arguments description:
Usage: opennlp SimpleTokenizer < sentences
]]>
-</screen>
+</screen>
</section>
<section id='tools.cli.tokenizer.TokenizerME'>
@@ -553,7 +626,7 @@ Usage: opennlp SimpleTokenizer < sentences
Usage: opennlp TokenizerME model < sentences
]]>
-</screen>
+</screen>
</section>
<section id='tools.cli.tokenizer.TokenizerTrainer'>
@@ -564,9 +637,9 @@ Usage: opennlp TokenizerME model < sentences
<screen>
<![CDATA[
-Usage: opennlp TokenizerTrainer[.irishsentencebank|.ad|.pos|.conllx|.namefinder|.parse|.conllu] [-factory
- factoryName] [-abbDict path] [-alphaNumOpt isAlphaNumOpt] [-params paramsFile] -lang language -model
- modelFile -data sampleData [-encoding charsetName]
+Usage: opennlp TokenizerTrainer[.irishsentencebank|.ad|.pos|.conllx|.namefinder|.parse|.conllu] [-factory
+ factoryName] [-abbDict path] [-alphaNumOpt isAlphaNumOpt] [-params paramsFile] -lang language -model
+ modelFile -data sampleData [-encoding charsetName]
Arguments description:
-factory factoryName
A sub-class of TokenizerFactory where to get implementation and resources.
@@ -586,11 +659,20 @@ Arguments description:
encoding for reading and writing text, if absent the system default is used.
]]>
-</screen>
+</screen>
<para>The supported formats and arguments are:</para>
-<informaltable frame='all'><tgroup cols='4' align='left' colsep='1' rowsep='1'>
-<thead><row><entry>Format</entry><entry>Argument</entry><entry>Value</entry><entry>Optional</entry><entry>Description</entry></row></thead>
+<informaltable frame='all'>
+<tgroup cols='5' align='left' colsep='1' rowsep='1'>
+<thead>
+ <row>
+ <entry>Format</entry>
+ <entry>Argument</entry>
+ <entry>Value</entry>
+ <entry>Optional</entry>
+ <entry>Description</entry>
+ </row>
+</thead>
<tbody>
<row>
<entry morerows='1' valign='middle'>irishsentencebank</entry>
@@ -738,8 +820,8 @@ Arguments description:
<screen>
<![CDATA[
-Usage: opennlp TokenizerMEEvaluator[.irishsentencebank|.ad|.pos|.conllx|.namefinder|.parse|.conllu] -model
- model [-misclassified true|false] -data sampleData [-encoding charsetName]
+Usage: opennlp TokenizerMEEvaluator[.irishsentencebank|.ad|.pos|.conllx|.namefinder|.parse|.conllu] -model
+ model [-misclassified true|false] -data sampleData [-encoding charsetName]
Arguments description:
-model model
the model file to be evaluated.
@@ -751,11 +833,20 @@ Arguments description:
encoding for reading and writing text, if absent the system default is used.
]]>
-</screen>
+</screen>
<para>The supported formats and arguments are:</para>
-<informaltable frame='all'><tgroup cols='4' align='left' colsep='1' rowsep='1'>
-<thead><row><entry>Format</entry><entry>Argument</entry><entry>Value</entry><entry>Optional</entry><entry>Description</entry></row></thead>
+<informaltable frame='all'>
+<tgroup cols='5' align='left' colsep='1' rowsep='1'>
+<thead>
+ <row>
+ <entry>Format</entry>
+ <entry>Argument</entry>
+ <entry>Value</entry>
+ <entry>Optional</entry>
+ <entry>Description</entry>
+ </row>
+</thead>
<tbody>
<row>
<entry morerows='1' valign='middle'>irishsentencebank</entry>
@@ -903,9 +994,9 @@ Arguments description:
<screen>
<![CDATA[
-Usage: opennlp TokenizerCrossValidator[.irishsentencebank|.ad|.pos|.conllx|.namefinder|.parse|.conllu]
- [-misclassified true|false] [-folds num] [-factory factoryName] [-abbDict path] [-alphaNumOpt
- isAlphaNumOpt] [-params paramsFile] -lang language -data sampleData [-encoding charsetName]
+Usage: opennlp TokenizerCrossValidator[.irishsentencebank|.ad|.pos|.conllx|.namefinder|.parse|.conllu]
+ [-misclassified true|false] [-folds num] [-factory factoryName] [-abbDict path] [-alphaNumOpt
+ isAlphaNumOpt] [-params paramsFile] -lang language -data sampleData [-encoding charsetName]
Arguments description:
-misclassified true|false
if true will print false negatives and false positives.
@@ -927,11 +1018,20 @@ Arguments description:
encoding for reading and writing text, if absent the system default is used.
]]>
-</screen>
+</screen>
<para>The supported formats and arguments are:</para>
-<informaltable frame='all'><tgroup cols='4' align='left' colsep='1' rowsep='1'>
-<thead><row><entry>Format</entry><entry>Argument</entry><entry>Value</entry><entry>Optional</entry><entry>Description</entry></row></thead>
+<informaltable frame='all'>
+<tgroup cols='5' align='left' colsep='1' rowsep='1'>
+<thead>
+ <row>
+ <entry>Format</entry>
+ <entry>Argument</entry>
+ <entry>Value</entry>
+ <entry>Optional</entry>
+ <entry>Description</entry>
+ </row>
+</thead>
<tbody>
<row>
<entry morerows='1' valign='middle'>irishsentencebank</entry>
@@ -1079,14 +1179,23 @@ Arguments description:
<screen>
<![CDATA[
-Usage: opennlp TokenizerConverter help|irishsentencebank|ad|pos|conllx|namefinder|parse|conllu
- [help|options...]
+Usage: opennlp TokenizerConverter help|irishsentencebank|ad|pos|conllx|namefinder|parse|conllu
+ [help|options...]
]]>
-</screen>
+</screen>
<para>The supported formats and arguments are:</para>
-<informaltable frame='all'><tgroup cols='4' align='left' colsep='1' rowsep='1'>
-<thead><row><entry>Format</entry><entry>Argument</entry><entry>Value</entry><entry>Optional</entry><entry>Description</entry></row></thead>
+<informaltable frame='all'>
+<tgroup cols='5' align='left' colsep='1' rowsep='1'>
+<thead>
+ <row>
+ <entry>Format</entry>
+ <entry>Argument</entry>
+ <entry>Value</entry>
+ <entry>Optional</entry>
+ <entry>Description</entry>
+ </row>
+</thead>
<tbody>
<row>
<entry morerows='1' valign='middle'>irishsentencebank</entry>
@@ -1237,7 +1346,7 @@ Usage: opennlp TokenizerConverter help|irishsentencebank|ad|pos|conllx|namefinde
Usage: opennlp DictionaryDetokenizer detokenizerDictionary
]]>
-</screen>
+</screen>
</section>
</section>
@@ -1257,7 +1366,7 @@ Usage: opennlp DictionaryDetokenizer detokenizerDictionary
Usage: opennlp SentenceDetector model < sentences
]]>
-</screen>
+</screen>
</section>
<section id='tools.cli.sentdetect.SentenceDetectorTrainer'>
@@ -1268,10 +1377,10 @@ Usage: opennlp SentenceDetector model < sentences
<screen>
<![CDATA[
-Usage: opennlp
- SentenceDetectorTrainer[.irishsentencebank|.ad|.pos|.conllx|.namefinder|.parse|.moses|.conllu|.letsmt]
- [-factory factoryName] [-eosChars string] [-abbDict path] [-params paramsFile] -lang language -model
- modelFile -data sampleData [-encoding charsetName]
+Usage: opennlp
+ SentenceDetectorTrainer[.irishsentencebank|.ad|.pos|.conllx|.namefinder|.parse|.moses|.conllu|.letsmt]
+ [-factory factoryName] [-eosChars string] [-abbDict path] [-params paramsFile] -lang language -model
+ modelFile -data sampleData [-encoding charsetName]
Arguments description:
-factory factoryName
A sub-class of SentenceDetectorFactory where to get implementation and resources.
@@ -1291,11 +1400,20 @@ Arguments description:
encoding for reading and writing text, if absent the system default is used.
]]>
-</screen>
+</screen>
<para>The supported formats and arguments are:</para>
-<informaltable frame='all'><tgroup cols='4' align='left' colsep='1' rowsep='1'>
-<thead><row><entry>Format</entry><entry>Argument</entry><entry>Value</entry><entry>Optional</entry><entry>Description</entry></row></thead>
+<informaltable frame='all'>
+<tgroup cols='5' align='left' colsep='1' rowsep='1'>
+<thead>
+ <row>
+ <entry>Format</entry>
+ <entry>Argument</entry>
+ <entry>Value</entry>
+ <entry>Optional</entry>
+ <entry>Description</entry>
+ </row>
+</thead>
<tbody>
<row>
<entry morerows='1' valign='middle'>irishsentencebank</entry>
@@ -1475,9 +1593,9 @@ Arguments description:
<screen>
<![CDATA[
-Usage: opennlp
- SentenceDetectorEvaluator[.irishsentencebank|.ad|.pos|.conllx|.namefinder|.parse|.moses|.conllu|.letsmt]
- -model model [-misclassified true|false] -data sampleData [-encoding charsetName]
+Usage: opennlp
+ SentenceDetectorEvaluator[.irishsentencebank|.ad|.pos|.conllx|.namefinder|.parse|.moses|.conllu|.letsmt]
+ -model model [-misclassified true|false] -data sampleData [-encoding charsetName]
Arguments description:
-model model
the model file to be evaluated.
@@ -1489,11 +1607,20 @@ Arguments description:
encoding for reading and writing text, if absent the system default is used.
]]>
-</screen>
+</screen>
<para>The supported formats and arguments are:</para>
-<informaltable frame='all'><tgroup cols='4' align='left' colsep='1' rowsep='1'>
-<thead><row><entry>Format</entry><entry>Argument</entry><entry>Value</entry><entry>Optional</entry><entry>Description</entry></row></thead>
+<informaltable frame='all'>
+<tgroup cols='5' align='left' colsep='1' rowsep='1'>
+<thead>
+ <row>
+ <entry>Format</entry>
+ <entry>Argument</entry>
+ <entry>Value</entry>
+ <entry>Optional</entry>
+ <entry>Description</entry>
+ </row>
+</thead>
<tbody>
<row>
<entry morerows='1' valign='middle'>irishsentencebank</entry>
@@ -1673,10 +1800,10 @@ Arguments description:
<screen>
<![CDATA[
-Usage: opennlp
- SentenceDetectorCrossValidator[.irishsentencebank|.ad|.pos|.conllx|.namefinder|.parse|.moses|.conllu|.letsmt]
- [-factory factoryName] [-eosChars string] [-abbDict path] [-params paramsFile] -lang language
- [-misclassified true|false] [-folds num] -data sampleData [-encoding charsetName]
+Usage: opennlp
+ SentenceDetectorCrossValidator[.irishsentencebank|.ad|.pos|.conllx|.namefinder|.parse|.moses|.conllu|.letsmt]
+ [-factory factoryName] [-eosChars string] [-abbDict path] [-params paramsFile] -lang language
+ [-misclassified true|false] [-folds num] -data sampleData [-encoding charsetName]
Arguments description:
-factory factoryName
A sub-class of SentenceDetectorFactory where to get implementation and resources.
@@ -1698,11 +1825,20 @@ Arguments description:
encoding for reading and writing text, if absent the system default is used.
]]>
-</screen>
+</screen>
<para>The supported formats and arguments are:</para>
-<informaltable frame='all'><tgroup cols='4' align='left' colsep='1' rowsep='1'>
-<thead><row><entry>Format</entry><entry>Argument</entry><entry>Value</entry><entry>Optional</entry><entry>Description</entry></row></thead>
+<informaltable frame='all'>
+<tgroup cols='5' align='left' colsep='1' rowsep='1'>
+<thead>
+ <row>
+ <entry>Format</entry>
+ <entry>Argument</entry>
+ <entry>Value</entry>
+ <entry>Optional</entry>
+ <entry>Description</entry>
+ </row>
+</thead>
<tbody>
<row>
<entry morerows='1' valign='middle'>irishsentencebank</entry>
@@ -1882,14 +2018,23 @@ Arguments description:
<screen>
<![CDATA[
-Usage: opennlp SentenceDetectorConverter
- help|irishsentencebank|ad|pos|conllx|namefinder|parse|moses|conllu|letsmt [help|options...]
+Usage: opennlp SentenceDetectorConverter
+ help|irishsentencebank|ad|pos|conllx|namefinder|parse|moses|conllu|letsmt [help|options...]
]]>
-</screen>
+</screen>
<para>The supported formats and arguments are:</para>
-<informaltable frame='all'><tgroup cols='4' align='left' colsep='1' rowsep='1'>
-<thead><row><entry>Format</entry><entry>Argument</entry><entry>Value</entry><entry>Optional</entry><entry>Description</entry></row></thead>
+<informaltable frame='all'>
+<tgroup cols='5' align='left' colsep='1' rowsep='1'>
+<thead>
+ <row>
+ <entry>Format</entry>
+ <entry>Argument</entry>
+ <entry>Value</entry>
+ <entry>Optional</entry>
+ <entry>Description</entry>
+ </row>
+</thead>
<tbody>
<row>
<entry morerows='1' valign='middle'>irishsentencebank</entry>
@@ -2078,7 +2223,7 @@ Usage: opennlp SentenceDetectorConverter
Usage: opennlp TokenNameFinder model1 model2 ... modelN < sentences
]]>
-</screen>
+</screen>
</section>
<section id='tools.cli.namefind.TokenNameFinderTrainer'>
@@ -2089,10 +2234,10 @@ Usage: opennlp TokenNameFinder model1 model2 ... modelN < sentences
<screen>
<![CDATA[
-Usage: opennlp TokenNameFinderTrainer[.evalita|.ad|.conll03|.bionlp2004|.conll02|.muc6|.ontonotes|.brat]
- [-factory factoryName] [-resources resourcesDir] [-type modelType] [-featuregen featuregenFile]
- [-nameTypes types] [-sequenceCodec codec] [-params paramsFile] -lang language -model modelFile -data
- sampleData [-encoding charsetName]
+Usage: opennlp TokenNameFinderTrainer[.evalita|.ad|.conll03|.bionlp2004|.conll02|.muc6|.ontonotes|.brat]
+ [-factory factoryName] [-resources resourcesDir] [-type modelType] [-featuregen featuregenFile]
+ [-nameTypes types] [-sequenceCodec codec] [-params paramsFile] -lang language -model modelFile -data
+ sampleData [-encoding charsetName]
Arguments description:
-factory factoryName
A sub-class of TokenNameFinderFactory
@@ -2118,11 +2263,20 @@ Arguments description:
encoding for reading and writing text, if absent the system default is used.
]]>
-</screen>
+</screen>
<para>The supported formats and arguments are:</para>
-<informaltable frame='all'><tgroup cols='4' align='left' colsep='1' rowsep='1'>
-<thead><row><entry>Format</entry><entry>Argument</entry><entry>Value</entry><entry>Optional</entry><entry>Description</entry></row></thead>
+<informaltable frame='all'>
+<tgroup cols='5' align='left' colsep='1' rowsep='1'>
+<thead>
+ <row>
+ <entry>Format</entry>
+ <entry>Argument</entry>
+ <entry>Value</entry>
+ <entry>Optional</entry>
+ <entry>Description</entry>
+ </row>
+</thead>
<tbody>
<row>
<entry morerows='3' valign='middle'>evalita</entry>
@@ -2319,9 +2473,9 @@ Arguments description:
<screen>
<![CDATA[
-Usage: opennlp TokenNameFinderEvaluator[.evalita|.ad|.conll03|.bionlp2004|.conll02|.muc6|.ontonotes|.brat]
- [-nameTypes types] -model model [-misclassified true|false] [-detailedF true|false]
- [-reportOutputFile outputFile] -data sampleData [-encoding charsetName]
+Usage: opennlp TokenNameFinderEvaluator[.evalita|.ad|.conll03|.bionlp2004|.conll02|.muc6|.ontonotes|.brat]
+ [-nameTypes types] -model model [-misclassified true|false] [-detailedF true|false]
+ [-reportOutputFile outputFile] -data sampleData [-encoding charsetName]
Arguments description:
-nameTypes types
name types to use for evaluation
@@ -2339,11 +2493,20 @@ Arguments description:
encoding for reading and writing text, if absent the system default is used.
]]>
-</screen>
+</screen>
<para>The supported formats and arguments are:</para>
-<informaltable frame='all'><tgroup cols='4' align='left' colsep='1' rowsep='1'>
-<thead><row><entry>Format</entry><entry>Argument</entry><entry>Value</entry><entry>Optional</entry><entry>Description</entry></row></thead>
+<informaltable frame='all'>
+<tgroup cols='5' align='left' colsep='1' rowsep='1'>
+<thead>
+ <row>
+ <entry>Format</entry>
+ <entry>Argument</entry>
+ <entry>Value</entry>
+ <entry>Optional</entry>
+ <entry>Description</entry>
+ </row>
+</thead>
<tbody>
<row>
<entry morerows='3' valign='middle'>evalita</entry>
@@ -2540,12 +2703,12 @@ Arguments description:
<screen>
<![CDATA[
-Usage: opennlp
- TokenNameFinderCrossValidator[.evalita|.ad|.conll03|.bionlp2004|.conll02|.muc6|.ontonotes|.brat]
- [-factory factoryName] [-resources resourcesDir] [-type modelType] [-featuregen featuregenFile]
- [-nameTypes types] [-sequenceCodec codec] [-params paramsFile] -lang language [-misclassified
- true|false] [-folds num] [-detailedF true|false] [-reportOutputFile outputFile] -data sampleData
- [-encoding charsetName]
+Usage: opennlp
+ TokenNameFinderCrossValidator[.evalita|.ad|.conll03|.bionlp2004|.conll02|.muc6|.ontonotes|.brat]
+ [-factory factoryName] [-resources resourcesDir] [-type modelType] [-featuregen featuregenFile]
+ [-nameTypes types] [-sequenceCodec codec] [-params paramsFile] -lang language [-misclassified
+ true|false] [-folds num] [-detailedF true|false] [-reportOutputFile outputFile] -data sampleData
+ [-encoding charsetName]
Arguments description:
-factory factoryName
A sub-class of TokenNameFinderFactory
@@ -2577,11 +2740,20 @@ Arguments description:
encoding for reading and writing text, if absent the system default is used.
]]>
-</screen>
+</screen>
<para>The supported formats and arguments are:</para>
-<informaltable frame='all'><tgroup cols='4' align='left' colsep='1' rowsep='1'>
-<thead><row><entry>Format</entry><entry>Argument</entry><entry>Value</entry><entry>Optional</entry><entry>Description</entry></row></thead>
+<informaltable frame='all'>
+<tgroup cols='5' align='left' colsep='1' rowsep='1'>
+<thead>
+ <row>
+ <entry>Format</entry>
+ <entry>Argument</entry>
+ <entry>Value</entry>
+ <entry>Optional</entry>
+ <entry>Description</entry>
+ </row>
+</thead>
<tbody>
<row>
<entry morerows='3' valign='middle'>evalita</entry>
@@ -2778,14 +2950,23 @@ Arguments description:
<screen>
<![CDATA[
-Usage: opennlp TokenNameFinderConverter help|evalita|ad|conll03|bionlp2004|conll02|muc6|ontonotes|brat
- [help|options...]
+Usage: opennlp TokenNameFinderConverter help|evalita|ad|conll03|bionlp2004|conll02|muc6|ontonotes|brat
+ [help|options...]
]]>
-</screen>
+</screen>
<para>The supported formats and arguments are:</para>
-<informaltable frame='all'><tgroup cols='4' align='left' colsep='1' rowsep='1'>
-<thead><row><entry>Format</entry><entry>Argument</entry><entry>Value</entry><entry>Optional</entry><entry>Description</entry></row></thead>
+<informaltable frame='all'>
+<tgroup cols='5' align='left' colsep='1' rowsep='1'>
+<thead>
+ <row>
+ <entry>Format</entry>
+ <entry>Argument</entry>
+ <entry>Value</entry>
+ <entry>Optional</entry>
+ <entry>Description</entry>
+ </row>
+</thead>
<tbody>
<row>
<entry morerows='3' valign='middle'>evalita</entry>
@@ -2991,7 +3172,7 @@ Arguments description:
-dict dict
]]>
-</screen>
+</screen>
</section>
</section>
@@ -3011,7 +3192,7 @@ Arguments description:
Usage: opennlp POSTagger model < sentences
]]>
-</screen>
+</screen>
</section>
<section id='tools.cli.postag.POSTaggerTrainer'>
@@ -3022,9 +3203,9 @@ Usage: opennlp POSTagger model < sentences
<screen>
<![CDATA[
-Usage: opennlp POSTaggerTrainer[.ad|.conllx|.parse|.ontonotes|.conllu] [-factory factoryName] [-resources
- resourcesDir] [-tagDictCutoff tagDictCutoff] [-featuregen featuregenFile] [-dict dictionaryPath]
- [-params paramsFile] -lang language -model modelFile -data sampleData [-encoding charsetName]
+Usage: opennlp POSTaggerTrainer[.ad|.conllx|.parse|.ontonotes|.conllu] [-factory factoryName] [-resources
+ resourcesDir] [-tagDictCutoff tagDictCutoff] [-featuregen featuregenFile] [-dict dictionaryPath]
+ [-params paramsFile] -lang language -model modelFile -data sampleData [-encoding charsetName]
Arguments description:
-factory factoryName
A sub-class of POSTaggerFactory where to get implementation and resources.
@@ -3048,11 +3229,20 @@ Arguments description:
encoding for reading and writing text, if absent the system default is used.
]]>
-</screen>
+</screen>
<para>The supported formats and arguments are:</para>
-<informaltable frame='all'><tgroup cols='4' align='left' colsep='1' rowsep='1'>
-<thead><row><entry>Format</entry><entry>Argument</entry><entry>Value</entry><entry>Optional</entry><entry>Description</entry></row></thead>
+<informaltable frame='all'>
+<tgroup cols='5' align='left' colsep='1' rowsep='1'>
+<thead>
+ <row>
+ <entry>Format</entry>
+ <entry>Argument</entry>
+ <entry>Value</entry>
+ <entry>Optional</entry>
+ <entry>Description</entry>
+ </row>
+</thead>
<tbody>
<row>
<entry morerows='4' valign='middle'>ad</entry>
@@ -3150,8 +3340,8 @@ Arguments description:
<screen>
<![CDATA[
-Usage: opennlp POSTaggerEvaluator[.ad|.conllx|.parse|.ontonotes|.conllu] -model model [-misclassified
- true|false] [-reportOutputFile outputFile] -data sampleData [-encoding charsetName]
+Usage: opennlp POSTaggerEvaluator[.ad|.conllx|.parse|.ontonotes|.conllu] -model model [-misclassified
+ true|false] [-reportOutputFile outputFile] -data sampleData [-encoding charsetName]
Arguments description:
-model model
the model file to be evaluated.
@@ -3165,11 +3355,20 @@ Arguments description:
encoding for reading and writing text, if absent the system default is used.
]]>
-</screen>
+</screen>
<para>The supported formats and arguments are:</para>
-<informaltable frame='all'><tgroup cols='4' align='left' colsep='1' rowsep='1'>
-<thead><row><entry>Format</entry><entry>Argument</entry><entry>Value</entry><entry>Optional</entry><entry>Description</entry></row></thead>
+<informaltable frame='all'>
+<tgroup cols='5' align='left' colsep='1' rowsep='1'>
+<thead>
+ <row>
+ <entry>Format</entry>
+ <entry>Argument</entry>
+ <entry>Value</entry>
+ <entry>Optional</entry>
+ <entry>Description</entry>
+ </row>
+</thead>
<tbody>
<row>
<entry morerows='4' valign='middle'>ad</entry>
@@ -3267,10 +3466,10 @@ Arguments description:
<screen>
<![CDATA[
-Usage: opennlp POSTaggerCrossValidator[.ad|.conllx|.parse|.ontonotes|.conllu] [-misclassified true|false]
- [-folds num] [-factory factoryName] [-resources resourcesDir] [-tagDictCutoff tagDictCutoff]
- [-featuregen featuregenFile] [-dict dictionaryPath] [-params paramsFile] -lang language
- [-reportOutputFile outputFile] -data sampleData [-encoding charsetName]
+Usage: opennlp POSTaggerCrossValidator[.ad|.conllx|.parse|.ontonotes|.conllu] [-misclassified true|false]
+ [-folds num] [-factory factoryName] [-resources resourcesDir] [-tagDictCutoff tagDictCutoff]
+ [-featuregen featuregenFile] [-dict dictionaryPath] [-params paramsFile] -lang language
+ [-reportOutputFile outputFile] -data sampleData [-encoding charsetName]
Arguments description:
-misclassified true|false
if true will print false negatives and false positives.
@@ -3298,11 +3497,20 @@ Arguments description:
encoding for reading and writing text, if absent the system default is used.
]]>
-</screen>
+</screen>
<para>The supported formats and arguments are:</para>
-<informaltable frame='all'><tgroup cols='4' align='left' colsep='1' rowsep='1'>
-<thead><row><entry>Format</entry><entry>Argument</entry><entry>Value</entry><entry>Optional</entry><entry>Description</entry></row></thead>
+<informaltable frame='all'>
+<tgroup cols='5' align='left' colsep='1' rowsep='1'>
+<thead>
+ <row>
+ <entry>Format</entry>
+ <entry>Argument</entry>
+ <entry>Value</entry>
+ <entry>Optional</entry>
+ <entry>Description</entry>
+ </row>
+</thead>
<tbody>
<row>
<entry morerows='4' valign='middle'>ad</entry>
@@ -3403,11 +3611,20 @@ Arguments description:
Usage: opennlp POSTaggerConverter help|ad|conllx|parse|ontonotes|conllu [help|options...]
]]>
-</screen>
+</screen>
<para>The supported formats and arguments are:</para>
-<informaltable frame='all'><tgroup cols='4' align='left' colsep='1' rowsep='1'>
-<thead><row><entry>Format</entry><entry>Argument</entry><entry>Value</entry><entry>Optional</entry><entry>Description</entry></row></thead>
+<informaltable frame='all'>
+<tgroup cols='5' align='left' colsep='1' rowsep='1'>
+<thead>
+ <row>
+ <entry>Format</entry>
+ <entry>Argument</entry>
+ <entry>Value</entry>
+ <entry>Optional</entry>
+ <entry>Description</entry>
+ </row>
+</thead>
<tbody>
<row>
<entry morerows='4' valign='middle'>ad</entry>
@@ -3514,7 +3731,7 @@ Usage: opennlp POSTaggerConverter help|ad|conllx|parse|ontonotes|conllu [help|op
Usage: opennlp LemmatizerME model < sentences
]]>
-</screen>
+</screen>
</section>
<section id='tools.cli.lemmatizer.LemmatizerTrainerME'>
@@ -3525,8 +3742,8 @@ Usage: opennlp LemmatizerME model < sentences
<screen>
<![CDATA[
-Usage: opennlp LemmatizerTrainerME[.conllu] [-factory factoryName] [-params paramsFile] -lang language -model
- modelFile -data sampleData [-encoding charsetName]
+Usage: opennlp LemmatizerTrainerME[.conllu] [-factory factoryName] [-params paramsFile] -lang language -model
+ modelFile -data sampleData [-encoding charsetName]
Arguments description:
-factory factoryName
A sub-class of LemmatizerFactory where to get implementation and resources.
@@ -3542,11 +3759,20 @@ Arguments description:
encoding for reading and writing text, if absent the system default is used.
]]>
-</screen>
+</screen>
<para>The supported formats and arguments are:</para>
-<informaltable frame='all'><tgroup cols='4' align='left' colsep='1' rowsep='1'>
-<thead><row><entry>Format</entry><entry>Argument</entry><entry>Value</entry><entry>Optional</entry><entry>Description</entry></row></thead>
+<informaltable frame='all'>
+<tgroup cols='5' align='left' colsep='1' rowsep='1'>
+<thead>
+ <row>
+ <entry>Format</entry>
+ <entry>Argument</entry>
+ <entry>Value</entry>
+ <entry>Optional</entry>
+ <entry>Description</entry>
+ </row>
+</thead>
<tbody>
<row>
<entry morerows='2' valign='middle'>conllu</entry>
@@ -3580,8 +3806,8 @@ Arguments description:
<screen>
<![CDATA[
-Usage: opennlp LemmatizerEvaluator[.conllu] -model model [-misclassified true|false] [-reportOutputFile
- outputFile] -data sampleData [-encoding charsetName]
+Usage: opennlp LemmatizerEvaluator[.conllu] -model model [-misclassified true|false] [-reportOutputFile
+ outputFile] -data sampleData [-encoding charsetName]
Arguments description:
-model model
the model file to be evaluated.
@@ -3595,11 +3821,20 @@ Arguments description:
encoding for reading and writing text, if absent the system default is used.
]]>
-</screen>
+</screen>
<para>The supported formats and arguments are:</para>
-<informaltable frame='all'><tgroup cols='4' align='left' colsep='1' rowsep='1'>
-<thead><row><entry>Format</entry><entry>Argument</entry><entry>Value</entry><entry>Optional</entry><entry>Description</entry></row></thead>
+<informaltable frame='all'>
+<tgroup cols='5' align='left' colsep='1' rowsep='1'>
+<thead>
+ <row>
+ <entry>Format</entry>
+ <entry>Argument</entry>
+ <entry>Value</entry>
+ <entry>Optional</entry>
+ <entry>Description</entry>
+ </row>
+</thead>
<tbody>
<row>
<entry morerows='2' valign='middle'>conllu</entry>
@@ -3642,7 +3877,7 @@ Arguments description:
Usage: opennlp ChunkerME model < sentences
]]>
-</screen>
+</screen>
</section>
<section id='tools.cli.chunker.ChunkerTrainerME'>
@@ -3653,8 +3888,8 @@ Usage: opennlp ChunkerME model < sentences
<screen>
<![CDATA[
-Usage: opennlp ChunkerTrainerME[.ad] [-factory factoryName] [-params paramsFile] -lang language -model
- modelFile -data sampleData [-encoding charsetName]
+Usage: opennlp ChunkerTrainerME[.ad] [-factory factoryName] [-params paramsFile] -lang language -model
+ modelFile -data sampleData [-encoding charsetName]
Arguments description:
-factory factoryName
A sub-class of ChunkerFactory where to get implementation and resources.
@@ -3670,11 +3905,20 @@ Arguments description:
encoding for reading and writing text, if absent the system default is used.
]]>
-</screen>
+</screen>
<para>The supported formats and arguments are:</para>
-<informaltable frame='all'><tgroup cols='4' align='left' colsep='1' rowsep='1'>
-<thead><row><entry>Format</entry><entry>Argument</entry><entry>Value</entry><entry>Optional</entry><entry>Description</entry></row></thead>
+<informaltable frame='all'>
+<tgroup cols='5' align='left' colsep='1' rowsep='1'>
+<thead>
+ <row>
+ <entry>Format</entry>
+ <entry>Argument</entry>
+ <entry>Value</entry>
+ <entry>Optional</entry>
+ <entry>Description</entry>
+ </row>
+</thead>
<tbody>
<row>
<entry morerows='4' valign='middle'>ad</entry>
@@ -3720,8 +3964,8 @@ Arguments description:
<screen>
<![CDATA[
-Usage: opennlp ChunkerEvaluator[.ad] -model model [-misclassified true|false] [-detailedF true|false] -data
- sampleData [-encoding charsetName]
+Usage: opennlp ChunkerEvaluator[.ad] -model model [-misclassified true|false] [-detailedF true|false] -data
+ sampleData [-encoding charsetName]
Arguments description:
-model model
the model file to be evaluated.
@@ -3735,11 +3979,20 @@ Arguments description:
encoding for reading and writing text, if absent the system default is used.
]]>
-</screen>
+</screen>
<para>The supported formats and arguments are:</para>
-<informaltable frame='all'><tgroup cols='4' align='left' colsep='1' rowsep='1'>
-<thead><row><entry>Format</entry><entry>Argument</entry><entry>Value</entry><entry>Optional</entry><entry>Description</entry></row></thead>
+<informaltable frame='all'>
+<tgroup cols='5' align='left' colsep='1' rowsep='1'>
+<thead>
+ <row>
+ <entry>Format</entry>
+ <entry>Argument</entry>
+ <entry>Value</entry>
+ <entry>Optional</entry>
+ <entry>Description</entry>
+ </row>
+</thead>
<tbody>
<row>
<entry morerows='4' valign='middle'>ad</entry>
@@ -3785,9 +4038,9 @@ Arguments description:
<screen>
<![CDATA[
-Usage: opennlp ChunkerCrossValidator[.ad] [-factory factoryName] [-params paramsFile] -lang language
- [-misclassified true|false] [-folds num] [-detailedF true|false] -data sampleData [-encoding
- charsetName]
+Usage: opennlp ChunkerCrossValidator[.ad] [-factory factoryName] [-params paramsFile] -lang language
+ [-misclassified true|false] [-folds num] [-detailedF true|false] -data sampleData [-encoding
+ charsetName]
Arguments description:
-factory factoryName
A sub-class of ChunkerFactory where to get implementation and resources.
@@ -3807,11 +4060,20 @@ Arguments description:
encoding for reading and writing text, if absent the system default is used.
]]>
-</screen>
+</screen>
<para>The supported formats and arguments are:</para>
-<informaltable frame='all'><tgroup cols='4' align='left' colsep='1' rowsep='1'>
-<thead><row><entry>Format</entry><entry>Argument</entry><entry>Value</entry><entry>Optional</entry><entry>Description</entry></row></thead>
+<informaltable frame='all'>
+<tgroup cols='5' align='left' colsep='1' rowsep='1'>
+<thead>
+ <row>
+ <entry>Format</entry>
+ <entry>Argument</entry>
+ <entry>Value</entry>
+ <entry>Optional</entry>
+ <entry>Description</entry>
+ </row>
+</thead>
<tbody>
<row>
<entry morerows='4' valign='middle'>ad</entry>
@@ -3860,11 +4122,20 @@ Arguments description:
Usage: opennlp ChunkerConverter help|ad [help|options...]
]]>
-</screen>
+</screen>
<para>The supported formats and arguments are:</para>
-<informaltable frame='all'><tgroup cols='4' align='left' colsep='1' rowsep='1'>
-<thead><row><entry>Format</entry><entry>Argument</entry><entry>Value</entry><entry>Optional</entry><entry>Description</entry></row></thead>
+<informaltable frame='all'>
+<tgroup cols='5' align='left' colsep='1' rowsep='1'>
+<thead>
+ <row>
+ <entry>Format</entry>
+ <entry>Argument</entry>
+ <entry>Value</entry>
+ <entry>Optional</entry>
+ <entry>Description</entry>
+ </row>
+</thead>
<tbody>
<row>
<entry morerows='4' valign='middle'>ad</entry>
@@ -3916,14 +4187,14 @@ Usage: opennlp ChunkerConverter help|ad [help|options...]
<screen>
<![CDATA[
-Usage: opennlp Parser [-bs n -ap n -k n -tk tok_model] model < sentences
+Usage: opennlp Parser [-bs n -ap n -k n -tk tok_model] model < sentences
-bs n: Use a beam size of n.
-ap f: Advance outcomes in with at least f% of the probability mass.
-k n: Show the top n parses. This will also display their log-probabilities.
-tk tok_model: Use the specified tokenizer model to tokenize the sentences. Defaults to a WhitespaceTokenizer.
]]>
-</screen>
+</screen>
</section>
<section id='tools.cli.parser.ParserTrainer'>
@@ -3934,9 +4205,9 @@ Usage: opennlp Parser [-bs n -ap n -k n -tk tok_model] model < sentences
<screen>
<![CDATA[
-Usage: opennlp ParserTrainer[.ontonotes|.frenchtreebank] [-headRulesSerializerImpl className] -headRules
- headRulesFile [-parserType CHUNKING|TREEINSERT] [-fun true|false] [-params paramsFile] -lang language
- -model modelFile [-encoding charsetName] -data sampleData
+Usage: opennlp ParserTrainer[.ontonotes|.frenchtreebank] [-headRulesSerializerImpl className] -headRules
+ headRulesFile [-parserType CHUNKING|TREEINSERT] [-fun true|false] [-params paramsFile] -lang language
+ -model modelFile [-encoding charsetName] -data sampleData
Arguments description:
-headRulesSerializerImpl className
head rules artifact serializer class name
@@ -3958,11 +4229,20 @@ Arguments description:
data to be used, usually a file name.
]]>
-</screen>
+</screen>
<para>The supported formats and arguments are:</para>
-<informaltable frame='all'><tgroup cols='4' align='left' colsep='1' rowsep='1'>
-<thead><row><entry>Format</entry><entry>Argument</entry><entry>Value</entry><entry>Optional</entry><entry>Description</entry></row></thead>
+<informaltable frame='all'>
+<tgroup cols='5' align='left' colsep='1' rowsep='1'>
+<thead>
+ <row>
+ <entry>Format</entry>
+ <entry>Argument</entry>
+ <entry>Value</entry>
+ <entry>Optional</entry>
+ <entry>Description</entry>
+ </row>
+</thead>
<tbody>
<row>
<entry morerows='0' valign='middle'>ontonotes</entry>
@@ -3997,8 +4277,8 @@ Arguments description:
<screen>
<![CDATA[
-Usage: opennlp ParserEvaluator[.ontonotes|.frenchtreebank] -model model [-misclassified true|false] -data
- sampleData [-encoding charsetName]
+Usage: opennlp ParserEvaluator[.ontonotes|.frenchtreebank] -model model [-misclassified true|false] -data
+ sampleData [-encoding charsetName]
Arguments description:
-model model
the model file to be evaluated.
@@ -4010,11 +4290,20 @@ Arguments description:
encoding for reading and writing text, if absent the system default is used.
]]>
-</screen>
+</screen>
<para>The supported formats and arguments are:</para>
-<informaltable frame='all'><tgroup cols='4' align='left' colsep='1' rowsep='1'>
-<thead><row><entry>Format</entry><entry>Argument</entry><entry>Value</entry><entry>Optional</entry><entry>Description</entry></row></thead>
+<informaltable frame='all'>
+<tgroup cols='5' align='left' colsep='1' rowsep='1'>
+<thead>
+ <row>
+ <entry>Format</entry>
+ <entry>Argument</entry>
+ <entry>Value</entry>
+ <entry>Optional</entry>
+ <entry>Description</entry>
+ </row>
+</thead>
<tbody>
<row>
<entry morerows='0' valign='middle'>ontonotes</entry>
@@ -4052,11 +4341,20 @@ Arguments description:
Usage: opennlp ParserConverter help|ontonotes|frenchtreebank [help|options...]
]]>
-</screen>
+</screen>
<para>The supported formats and arguments are:</para>
-<informaltable frame='all'><tgroup cols='4' align='left' colsep='1' rowsep='1'>
-<thead><row><entry>Format</entry><entry>Argument</entry><entry>Value</entry><entry>Optional</entry><entry>Description</entry></row></thead>
+<informaltable frame='all'>
+<tgroup cols='5' align='left' colsep='1' rowsep='1'>
+<thead>
+ <row>
+ <entry>Format</entry>
+ <entry>Argument</entry>
+ <entry>Value</entry>
+ <entry>Optional</entry>
+ <entry>Description</entry>
+ </row>
+</thead>
<tbody>
<row>
<entry morerows='0' valign='middle'>ontonotes</entry>
@@ -4091,8 +4389,8 @@ Usage: opennlp ParserConverter help|ontonotes|frenchtreebank [help|options...]
<screen>
<![CDATA[
-Usage: opennlp BuildModelUpdater[.ontonotes|.frenchtreebank] -model modelFile [-params paramsFile] -lang
- language -data sampleData [-encoding charsetName]
+Usage: opennlp BuildModelUpdater[.ontonotes|.frenchtreebank] -model modelFile [-params paramsFile] -lang
+ language -data sampleData [-encoding charsetName]
Arguments description:
-model modelFile
output model file.
@@ -4106,11 +4404,20 @@ Arguments description:
encoding for reading and writing text, if absent the system default is used.
]]>
-</screen>
+</screen>
<para>The supported formats and arguments are:</para>
-<informaltable frame='all'><tgroup cols='4' align='left' colsep='1' rowsep='1'>
-<thead><row><entry>Format</entry><entry>Argument</entry><entry>Value</entry><entry>Optional</entry><entry>Description</entry></row></thead>
+<informaltable frame='all'>
+<tgroup cols='5' align='left' colsep='1' rowsep='1'>
+<thead>
+ <row>
+ <entry>Format</entry>
+ <entry>Argument</entry>
+ <entry>Value</entry>
+ <entry>Optional</entry>
+ <entry>Description</entry>
+ </row>
+</thead>
<tbody>
<row>
<entry morerows='0' valign='middle'>ontonotes</entry>
@@ -4145,8 +4452,8 @@ Arguments description:
<screen>
<![CDATA[
-Usage: opennlp CheckModelUpdater[.ontonotes|.frenchtreebank] -model modelFile [-params paramsFile] -lang
- language -data sampleData [-encoding charsetName]
+Usage: opennlp CheckModelUpdater[.ontonotes|.frenchtreebank] -model modelFile [-params paramsFile] -lang
+ language -data sampleData [-encoding charsetName]
Arguments description:
-model modelFile
output model file.
@@ -4160,11 +4467,17 @@ Arguments description:
encoding for reading and writing text, if absent the system default is used.
]]>
-</screen>
+</screen>
<para>The supported formats and arguments are:</para>
-<informaltable frame='all'><tgroup cols='4' align='left' colsep='1' rowsep='1'>
-<thead><row><entry>Format</entry><entry>Argument</entry><entry>Value</entry><entry>Optional</entry><entry>Description</entry></row></thead>
+<informaltable frame='all'>
+<tgroup cols='5' align='left' colsep='1' rowsep='1'>
+<thead><row>
+ <entry>Format</entry>
+ <entry>Argument</entry>
+ <entry>Value</entry>
+ <entry>Optional</entry>
+ <entry>Description</entry></row></thead>
<tbody>
<row>
<entry morerows='0' valign='middle'>ontonotes</entry>
diff --git a/opennlp-docs/src/docbkx/coref.xml b/opennlp-docs/src/docbkx/coref.xml
index d28ce9c9..279a4215 100644
--- a/opennlp-docs/src/docbkx/coref.xml
+++ b/opennlp-docs/src/docbkx/coref.xml
@@ -1,6 +1,6 @@
<?xml version="1.0" encoding="UTF-8"?>
-<!DOCTYPE chapter PUBLIC "-//OASIS//DTD DocBook XML V4.4//EN"
-"http://www.oasis-open.org/docbook/xml/4.4/docbookx.dtd"[
+<!DOCTYPE chapter PUBLIC "-//OASIS//DTD DocBook XML V5.0//EN"
+"https://docbook.org/xml/5.0.1/dtd/docbook.dtd"[
]>
<!--
Licensed to the Apache Software Foundation (ASF) under one
diff --git a/opennlp-docs/src/docbkx/corpora.xml b/opennlp-docs/src/docbkx/corpora.xml
index d420ca74..4b6e0f73 100644
--- a/opennlp-docs/src/docbkx/corpora.xml
+++ b/opennlp-docs/src/docbkx/corpora.xml
@@ -1,6 +1,6 @@
<?xml version="1.0" encoding="UTF-8"?>
-<!DOCTYPE chapter PUBLIC "-//OASIS//DTD DocBook XML V4.4//EN"
-"http://www.oasis-open.org/docbook/xml/4.4/docbookx.dtd"[
+<!DOCTYPE chapter PUBLIC "-//OASIS//DTD DocBook XML V5.0//EN"
+"https://docbook.org/xml/5.0.1/dtd/docbook.dtd"[
]>
<!--
Licensed to the Apache Software Foundation (ASF) under one
diff --git a/opennlp-docs/src/docbkx/doccat.xml b/opennlp-docs/src/docbkx/doccat.xml
index 33ac04a2..16251122 100644
--- a/opennlp-docs/src/docbkx/doccat.xml
+++ b/opennlp-docs/src/docbkx/doccat.xml
@@ -1,6 +1,6 @@
<?xml version="1.0" encoding="UTF-8"?>
-<!DOCTYPE chapter PUBLIC "-//OASIS//DTD DocBook XML V4.4//EN"
-"http://www.oasis-open.org/docbook/xml/4.4/docbookx.dtd"[
+<!DOCTYPE chapter PUBLIC "-//OASIS//DTD DocBook XML V5.0//EN"
+"https://docbook.org/xml/5.0.1/dtd/docbook.dtd"[
]>
<!--
Licensed to the Apache Software Foundation (ASF) under one
@@ -88,7 +88,7 @@ double[] outcomes = myCategorizer.categorize(textTokens);
String category = myCategorizer.getBestCategory(outcomes);]]>
</programlisting>
</para>
- <section id="tools.namefind.api.onnx">
+ <section id="tools.doccat.api.onnx">
<title>Using an ONNX Model</title>
<para>
Using an ONNX model is similar, except we will utilize the <code>DocumentCategorizerDL</code> class instead.
diff --git a/opennlp-docs/src/docbkx/evaltest.xml b/opennlp-docs/src/docbkx/evaltest.xml
index 620a136f..8c836151 100644
--- a/opennlp-docs/src/docbkx/evaltest.xml
+++ b/opennlp-docs/src/docbkx/evaltest.xml
@@ -1,6 +1,6 @@
<?xml version="1.0" encoding="UTF-8"?>
-<!DOCTYPE chapter PUBLIC "-//OASIS//DTD DocBook XML V4.4//EN"
-"http://www.oasis-open.org/docbook/xml/4.4/docbookx.dtd"[
+<!DOCTYPE chapter PUBLIC "-//OASIS//DTD DocBook XML V5.0//EN"
+"https://docbook.org/xml/5.0.1/dtd/docbook.dtd"[
]>
<!--
Licensed to the Apache Software Foundation (ASF) under one
diff --git a/opennlp-docs/src/docbkx/extension.xml b/opennlp-docs/src/docbkx/extension.xml
index afd5b032..11be740f 100644
--- a/opennlp-docs/src/docbkx/extension.xml
+++ b/opennlp-docs/src/docbkx/extension.xml
@@ -1,6 +1,6 @@
<?xml version="1.0" encoding="UTF-8"?>
-<!DOCTYPE chapter PUBLIC "-//OASIS//DTD DocBook XML V4.4//EN"
-"http://www.oasis-open.org/docbook/xml/4.4/docbookx.dtd"[
+<!DOCTYPE chapter PUBLIC "-//OASIS//DTD DocBook XML V5.0//EN"
+"https://docbook.org/xml/5.0.1/dtd/docbook.dtd"[
]>
<!--
Licensed to the Apache Software Foundation (ASF) under one
diff --git a/opennlp-docs/src/docbkx/introduction.xml b/opennlp-docs/src/docbkx/introduction.xml
index 1aee630a..355e7917 100644
--- a/opennlp-docs/src/docbkx/introduction.xml
+++ b/opennlp-docs/src/docbkx/introduction.xml
@@ -1,6 +1,6 @@
<?xml version="1.0" encoding="UTF-8"?>
-<!DOCTYPE chapter PUBLIC "-//OASIS//DTD DocBook XML V4.4//EN"
-"http://www.oasis-open.org/docbook/xml/4.4/docbookx.dtd"[
+<!DOCTYPE chapter PUBLIC "-//OASIS//DTD DocBook XML V5.0//EN"
+"https://docbook.org/xml/5.0.1/dtd/docbook.dtd"[
]>
<!--
Licensed to the Apache Software Foundation (ASF) under one
@@ -55,7 +55,7 @@ under the License.
</section>
<section id="intro.api">
- <title>Application Program Interface (API). Generic Example</title>
+ <title>Application Program Interface <API></API></title>
<para>
OpenNLP components have similar APIs. Normally, to execute a task,
one should provide a model and an input.
diff --git a/opennlp-docs/src/docbkx/langdetect.xml b/opennlp-docs/src/docbkx/langdetect.xml
index 7e901714..5d577714 100644
--- a/opennlp-docs/src/docbkx/langdetect.xml
+++ b/opennlp-docs/src/docbkx/langdetect.xml
@@ -1,6 +1,6 @@
<?xml version="1.0" encoding="UTF-8"?>
-<!DOCTYPE chapter PUBLIC "-//OASIS//DTD DocBook XML V4.4//EN"
-"http://www.oasis-open.org/docbook/xml/4.4/docbookx.dtd"[
+<!DOCTYPE chapter PUBLIC "-//OASIS//DTD DocBook XML V5.0//EN"
+"https://docbook.org/xml/5.0.1/dtd/docbook.dtd"[
]>
<!--
Licensed to the Apache Software Foundation (ASF) under one
diff --git a/opennlp-docs/src/docbkx/lemmatizer.xml b/opennlp-docs/src/docbkx/lemmatizer.xml
index 90264dbe..ca7394b3 100644
--- a/opennlp-docs/src/docbkx/lemmatizer.xml
+++ b/opennlp-docs/src/docbkx/lemmatizer.xml
@@ -1,6 +1,6 @@
<?xml version="1.0" encoding="UTF-8"?>
-<!DOCTYPE chapter PUBLIC "-//OASIS//DTD DocBook XML V4.4//EN"
-"http://www.oasis-open.org/docbook/xml/4.4/docbookx.dtd"[
+<!DOCTYPE chapter PUBLIC "-//OASIS//DTD DocBook XML V5.0//EN"
+"https://docbook.org/xml/5.0.1/dtd/docbook.dtd"[
]>
<!-- Licensed to the Apache Software Foundation (ASF) under one or more contributor
license agreements. See the NOTICE file distributed with this work for additional
diff --git a/opennlp-docs/src/docbkx/machine-learning.xml b/opennlp-docs/src/docbkx/machine-learning.xml
index a42e7be1..69f70272 100644
--- a/opennlp-docs/src/docbkx/machine-learning.xml
+++ b/opennlp-docs/src/docbkx/machine-learning.xml
@@ -1,6 +1,6 @@
<?xml version="1.0" encoding="UTF-8"?>
-<!DOCTYPE chapter PUBLIC "-//OASIS//DTD DocBook XML V4.4//EN"
-"http://www.oasis-open.org/docbook/xml/4.4/docbookx.dtd"[
+<!DOCTYPE chapter PUBLIC "-//OASIS//DTD DocBook XML V5.0//EN"
+"https://docbook.org/xml/5.0.1/dtd/docbook.dtd"[
]>
<!--
Licensed to the Apache Software Foundation (ASF) under one
diff --git a/opennlp-docs/src/docbkx/model-loading.xml b/opennlp-docs/src/docbkx/model-loading.xml
index aec161cd..57812e5c 100644
--- a/opennlp-docs/src/docbkx/model-loading.xml
+++ b/opennlp-docs/src/docbkx/model-loading.xml
@@ -1,6 +1,6 @@
<?xml version="1.0" encoding="UTF-8"?>
-<!DOCTYPE chapter PUBLIC "-//OASIS//DTD DocBook XML V4.4//EN"
- "http://www.oasis-open.org/docbook/xml/4.4/docbookx.dtd"[
+<!DOCTYPE chapter PUBLIC "-//OASIS//DTD DocBook XML V5.0//EN"
+ "https://docbook.org/xml/5.0.1/dtd/docbook.dtd"[
]>
<!--
Licensed to the Apache Software Foundation (ASF) under one
diff --git a/opennlp-docs/src/docbkx/morfologik-addon.xml b/opennlp-docs/src/docbkx/morfologik-addon.xml
index 27c2dcd0..bdfaebc9 100644
--- a/opennlp-docs/src/docbkx/morfologik-addon.xml
+++ b/opennlp-docs/src/docbkx/morfologik-addon.xml
@@ -1,6 +1,6 @@
<?xml version="1.0" encoding="UTF-8"?>
-<!DOCTYPE chapter PUBLIC "-//OASIS//DTD DocBook XML V4.4//EN"
-"http://www.oasis-open.org/docbook/xml/4.4/docbookx.dtd"[
+<!DOCTYPE chapter PUBLIC "-//OASIS//DTD DocBook XML V5.0//EN"
+"https://docbook.org/xml/5.0.1/dtd/docbook.dtd"[
]>
<!-- Licensed to the Apache Software Foundation (ASF) under one or more contributor
license agreements. See the NOTICE file distributed with this work for additional
diff --git a/opennlp-docs/src/docbkx/namefinder.xml b/opennlp-docs/src/docbkx/namefinder.xml
index cdf77d3f..5288a7b0 100644
--- a/opennlp-docs/src/docbkx/namefinder.xml
+++ b/opennlp-docs/src/docbkx/namefinder.xml
@@ -1,6 +1,6 @@
<?xml version="1.0" encoding="UTF-8"?>
-<!DOCTYPE chapter PUBLIC "-//OASIS//DTD DocBook XML V4.4//EN"
-"http://www.oasis-open.org/docbook/xml/4.4/docbookx.dtd"[
+<!DOCTYPE chapter PUBLIC "-//OASIS//DTD DocBook XML V5.0//EN"
+"https://docbook.org/xml/5.0.1/dtd/docbook.dtd"[
]>
<!--
Licensed to the Apache Software Foundation (ASF) under one
@@ -506,7 +506,7 @@ Precision: 0.8005071889818507
Recall: 0.7450581122145297
F-Measure: 0.7717879983140168]]>
</screen>
- Note: The command line interface does not support cross evaluation in the current version.
+ <remark>Note</remark>: The command line interface does not support cross evaluation in the current version.
</para>
</section>
<section id="tools.namefind.eval.api">
diff --git a/opennlp-docs/src/docbkx/opennlp.xml b/opennlp-docs/src/docbkx/opennlp.xml
index f07769e1..37f4a6b9 100644
--- a/opennlp-docs/src/docbkx/opennlp.xml
+++ b/opennlp-docs/src/docbkx/opennlp.xml
@@ -1,6 +1,6 @@
<?xml version="1.0" encoding="UTF-8"?>
-<!DOCTYPE book PUBLIC "-//OASIS//DTD DocBook XML V4.4//EN"
-"http://www.oasis-open.org/docbook/xml/4.4/docbookx.dtd">
+<!DOCTYPE book PUBLIC "-//OASIS//DTD DocBook XML V5.0//EN"
+"https://docbook.org/xml/5.0.1/dtd/docbook.dtd">
<!--
Licensed to the Apache Software Foundation (ASF) under one
or more contributor license agreements. See the NOTICE file
@@ -20,7 +20,7 @@ specific language governing permissions and limitations
under the License.
-->
-<book lang="en">
+<book lang="en" xmlns="http://docbook.org/ns/docbook" version="5.0">
<bookinfo>
<releaseinfo>
Version <?eval ${project.version}?>
@@ -55,7 +55,7 @@ under the License.
<blockquote>
<para>
- <ulink url="http://www.apache.org/licenses/LICENSE-2.0" />
+ <ulink url="https://www.apache.org/licenses/LICENSE-2.0" />
</para>
</blockquote>
diff --git a/opennlp-docs/src/docbkx/parser.xml b/opennlp-docs/src/docbkx/parser.xml
index 2dc1ecd6..bdb592be 100644
--- a/opennlp-docs/src/docbkx/parser.xml
+++ b/opennlp-docs/src/docbkx/parser.xml
@@ -1,6 +1,6 @@
<?xml version="1.0" encoding="UTF-8"?>
-<!DOCTYPE chapter PUBLIC "-//OASIS//DTD DocBook XML V4.4//EN"
-"http://www.oasis-open.org/docbook/xml/4.4/docbookx.dtd"[
+<!DOCTYPE chapter PUBLIC "-//OASIS//DTD DocBook XML V5.0//EN"
+"https://docbook.org/xml/5.0.1/dtd/docbook.dtd"[
]>
<!--
Licensed to the Apache Software Foundation (ASF) under one
diff --git a/opennlp-docs/src/docbkx/postagger.xml b/opennlp-docs/src/docbkx/postagger.xml
index 38f4609a..95157c47 100644
--- a/opennlp-docs/src/docbkx/postagger.xml
+++ b/opennlp-docs/src/docbkx/postagger.xml
@@ -1,6 +1,6 @@
<?xml version="1.0" encoding="UTF-8"?>
-<!DOCTYPE chapter PUBLIC "-//OASIS//DTD DocBook XML V4.4//EN"
-"http://www.oasis-open.org/docbook/xml/4.4/docbookx.dtd"[
+<!DOCTYPE chapter PUBLIC "-//OASIS//DTD DocBook XML V5.0//EN"
+"https://docbook.org/xml/5.0.1/dtd/docbook.dtd"[
]>
<!--
Licensed to the Apache Software Foundation (ASF) under one
diff --git a/opennlp-docs/src/docbkx/sentdetect.xml b/opennlp-docs/src/docbkx/sentdetect.xml
index 8aea2b0f..7ded060f 100644
--- a/opennlp-docs/src/docbkx/sentdetect.xml
+++ b/opennlp-docs/src/docbkx/sentdetect.xml
@@ -1,6 +1,6 @@
<?xml version="1.0" encoding="UTF-8"?>
-<!DOCTYPE chapter PUBLIC "-//OASIS//DTD DocBook XML V4.4//EN"
-"http://www.oasis-open.org/docbook/xml/4.4/docbookx.dtd"[
+<!DOCTYPE chapter PUBLIC "-//OASIS//DTD DocBook XML V5.0//EN"
+"https://docbook.org/xml/5.0.1/dtd/docbook.dtd"[
]>
<!--
Licensed to the Apache Software Foundation (ASF) under one
diff --git a/opennlp-docs/src/docbkx/tokenizer.xml b/opennlp-docs/src/docbkx/tokenizer.xml
index 1582ef1a..5b21e3a5 100644
--- a/opennlp-docs/src/docbkx/tokenizer.xml
+++ b/opennlp-docs/src/docbkx/tokenizer.xml
@@ -1,6 +1,6 @@
<?xml version="1.0" encoding="UTF-8"?>
-<!DOCTYPE chapter PUBLIC "-//OASIS//DTD DocBook XML V4.4//EN"
-"http://www.oasis-open.org/docbook/xml/4.4/docbookx.dtd"[
+<!DOCTYPE chapter PUBLIC "-//OASIS//DTD DocBook XML V5.0//EN"
+"https://docbook.org/xml/5.0.1/dtd/docbook.dtd"[
]>
<!-- Licensed to the Apache Software Foundation (ASF) under one or more contributor
license agreements. See the NOTICE file distributed with this work for additional
diff --git a/opennlp-docs/src/docbkx/uima-integration.xml b/opennlp-docs/src/docbkx/uima-integration.xml
index e29162ce..6d7ef466 100644
--- a/opennlp-docs/src/docbkx/uima-integration.xml
+++ b/opennlp-docs/src/docbkx/uima-integration.xml
@@ -1,6 +1,6 @@
<?xml version="1.0" encoding="UTF-8"?>
-<!DOCTYPE chapter PUBLIC "-//OASIS//DTD DocBook XML V4.4//EN"
-"http://www.oasis-open.org/docbook/xml/4.4/docbookx.dtd"[
+<!DOCTYPE chapter PUBLIC "-//OASIS//DTD DocBook XML V5.0//EN"
+"https://docbook.org/xml/5.0.1/dtd/docbook.dtd"[
]>
<!--
Licensed to the Apache Software Foundation (ASF) under one
diff --git a/opennlp-docs/src/docbkx/xsl/docbook-fo.xsl b/opennlp-docs/src/docbkx/xsl/docbook-fo.xsl
new file mode 100644
index 00000000..86fc9103
--- /dev/null
+++ b/opennlp-docs/src/docbkx/xsl/docbook-fo.xsl
@@ -0,0 +1,54 @@
+<?xml version="1.0" encoding="utf-8"?>
+<!--
+Licensed to the Apache Software Foundation (ASF) under one
+or more contributor license agreements. See the NOTICE file
+distributed with this work for additional information
+regarding copyright ownership. The ASF licenses this file
+to you under the Apache License, Version 2.0 (the
+"License"); you may not use this file except in compliance
+with the License. You may obtain a copy of the License at
+
+ http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing,
+software distributed under the License is distributed on an
+"AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+KIND, either express or implied. See the License for the
+specific language governing permissions and limitations
+under the License.
+-->
+<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
+ xmlns:fo="http://www.w3.org/1999/XSL/Format"
+ version="1.0">
+ <xsl:import href="urn:docbkx:stylesheet"/>
+ <xsl:import href="urn:docbkx:stylesheet/highlight.xsl"/>
+
+ <xsl:param name="fop1.extensions" select="1"/>
+ <xsl:param name="tablecolumns.extension" select="1"/>
+ <xsl:param name="default.table.width">100%</xsl:param>
+ <xsl:param name="body.start.indent">0.5cm</xsl:param>
+
+ <xsl:attribute-set name="component.title.properties">
+ <xsl:attribute name="start-indent">0cm</xsl:attribute>
+ </xsl:attribute-set>
+ <xsl:attribute-set name="section.properties">
+ <xsl:attribute name="start-indent">0.0cm</xsl:attribute>
+ </xsl:attribute-set>
+ <xsl:attribute-set name="section.title.properties">
+ <xsl:attribute name="start-indent">0.0cm</xsl:attribute>
+ </xsl:attribute-set>
+ <xsl:attribute-set name="section.level1.properties">
+ <xsl:attribute name="start-indent">0.0cm</xsl:attribute>
+ </xsl:attribute-set>
+ <xsl:attribute-set name="section.title.level1.properties">
+ <xsl:attribute name="start-indent">0cm</xsl:attribute>
+ <xsl:attribute name="border-top">0.5pt solid black</xsl:attribute>
+ <xsl:attribute name="border-bottom">0.5pt solid black</xsl:attribute>
+ <xsl:attribute name="padding-top">6pt</xsl:attribute>
+ <xsl:attribute name="padding-bottom">6pt</xsl:attribute>
+ </xsl:attribute-set>
+ <xsl:attribute-set name="section.title.level2.properties">
+ <xsl:attribute name="start-indent">0cm</xsl:attribute>
+ </xsl:attribute-set>
+
+</xsl:stylesheet>
\ No newline at end of file