Merge branch 'master' into jdk-21-fix-for-regex

.circleci.settings.xml

@@ -25,5 +25,9 @@
       <username>${env.ARTIFACTORY_USERNAME}</username>
       <password>${env.ARTIFACTORY_API_TOKEN}</password>
     </server>
+    <server>
+      <id>nvdApiServerId</id>
+      <password>${env.nvdApiKey}</password>
+    </server>
   </servers>
 </settings>

.circleci/config.yml

@@ -46,7 +46,7 @@ jobs:
   security-scan:
     resource_class: medium
     executor:
-      name: docker-openjdk11
+      name: docker-openjdk17
     environment:
       MAVEN_OPTS: -Xmx3500m
     steps:
@@ -60,7 +60,7 @@ jobs:
   test-and-deploy-full:
     resource_class: medium+
     executor:
-      name: docker-openjdk11
+      name: docker-openjdk17
     environment:
       MAVEN_OPTS: -Xmx3500m
     steps:
@@ -82,7 +82,7 @@ jobs:
   test-and-deploy-partial:
     resource_class: medium+
     executor: 
-      name: docker-openjdk11
+      name: docker-openjdk17
     environment: 
       MAVEN_OPTS: -Xmx3500m
     steps:
@@ -196,6 +196,6 @@ commands:
           command: |
             cd $CIRCLE_WORKING_DIRECTORY && .circleci/kick_off_premium.sh
 executors:
-  docker-openjdk11:
+  docker-openjdk17:
     docker:
-      - image: cimg/openjdk:11.0
+      - image: cimg/openjdk:17.0

.gitignore

@@ -6,13 +6,15 @@
 .class
 .classpath
 .idea
+.run
 .ignore
 .project
 .settings
 .metadata
 .vscode/
 build
 target
+target-ide
 atomFeedChecksDB
 derby.log
 .surefire-*

README.md

@@ -5,6 +5,7 @@ Portuguese, Polish, Dutch, and [more than 20 other languages](https://languageto
 It finds many errors that a simple spell checker cannot detect.
 
 * **[Jobs at LanguageTool](https://languagetool.org/careers)**
+* [LanguageTool Forum](https://forum.languagetool.org)
 * [How to run your own LanguageTool server](https://dev.languagetool.org/http-server)
 * [HTTP API documentation](https://languagetool.org/http-api/swagger-ui/#!/default/post_check)
 * [How to use our public server via HTTP](https://dev.languagetool.org/public-http-api)
@@ -33,13 +34,13 @@ For more technical details, see [our dev pages](https://dev.languagetool.org).
 
 ## Scripted installation and building
 To install or build using a script, simply type:
-```
+```bash
 curl -L https://raw.githubusercontent.com/languagetool-org/languagetool/master/install.sh | sudo bash <options>
 ```
 
 If you wish to have more options, download the `install.sh` script. Usage options follow:
 
-```
+```bash
 sudo bash install.sh <options>
 
 Usage: install.sh <option> <package>
@@ -92,10 +93,6 @@ Test the result in `languagetool-standalone/target/`.
 
 Test the result in `languagetool-wikipedia/target`.
 
-    ./build.sh languagetool-office-extension package -DskipTests
-
-Test the result in `languagetool-office-extension/target`, rename the `*.zip` to `*.oxt` to install it in LibreOffice/OpenOffice.
-
 Now you can use the bleeding edge development copy of LanguageTool `*.jar` files, be aware that it might contain regressions.
 
 

build-zip.sh

@@ -1,4 +1,4 @@
 #!/bin/sh
 # fast way to build the ZIP for testing an deployment
 
-mvn -pl '!languagetool-http-client,!languagetool-wikipedia,!languagetool-office-extension,!languagetool-dev' clean package -DskipTests
+mvn -pl '!languagetool-http-client,!languagetool-wikipedia,!languagetool-dev' clean package -DskipTests

build.sh

@@ -1,30 +1,34 @@
-#!/bin/bash
+#!/usr/bin/env bash
 
-if [ $# -lt 2 ]
-then
+self=$(basename $0)
+
+if [ $# -lt 2 ]; then
   echo "Helps building parts of LanguageTool - for a complete build, run mvn directly"
-  echo "Usage: `basename $0` <project> <goals...>"
+  echo "Usage: $self <project> <goals...>"
   echo "Examples:"
-  echo "  ./`basename $0` languagetool-standalone clean package (will package the standalone module)"
-  echo "  ./`basename $0` languagetool-standalone clean package -DskipTests (as above but without running tests)"
-  echo "  ./`basename $0` en clean test (will test the English module)"
+  echo "  ./$self languagetool-standalone clean package (will package the standalone module)"
+  echo "  ./$self languagetool-standalone clean package -DskipTests (as above but without running tests)"
+  echo "  ./$self en clean test (will test the English module)"
   exit 1
 fi
 
-MODULE=$1
+module=$1
 
-if [ \! -d $MODULE ]
-then
-  MODULE="languagetool-language-modules/$MODULE"
+if [ ! -d $module ]; then
+  module_path="languagetool-language-modules/$module"
+else
+  module_path="$module"
 fi
 
-COMMAND="mvn --projects $MODULE --also-make ${@:2}"
-echo "Running: $COMMAND"
+command="mvn --projects $module_path --also-make ${@:2}"
+echo "Running: $command"
+
+$command
+exitcode=$?
 
-$COMMAND
-BUILDEXITCODE=$?
 # these don't work on their own, so delete them to avoid confusion:
 rm languagetool-standalone/target/languagetool-standalone-*.jar 2> /dev/null
 rm languagetool-wikipedia/target/languagetool-wikipedia-*.jar 2> /dev/null
 rm languagetool-commandline/target/languagetool-commandline-*.jar 2> /dev/null
-exit $BUILDEXITCODE
+
+exit $exitcode

install.sh

@@ -191,7 +191,6 @@ build () {
     else
         ./build.sh languagetool-standalone package
         ./build.sh languagetool-wikipedia package -DskipTests
-        ./build.sh languagetool-office-extension package -DskipTests
     fi
 }
 
@@ -215,7 +214,6 @@ build_quiet () {
     else
         ./build.sh languagetool-standalone package
         ./build.sh languagetool-wikipedia package -DskipTests
-        ./build.sh languagetool-office-extension package -DskipTests
     fi
 }
 

languagetool-client-example/pom.xml

@@ -15,16 +15,16 @@
 
     <properties>
         <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
-        <maven.compiler.source>1.8</maven.compiler.source>
-        <maven.compiler.target>1.8</maven.compiler.target>
+        <maven.compiler.source>17</maven.compiler.source>
+        <maven.compiler.target>17</maven.compiler.target>
         <maven.build.timestamp.format>yyyy-MM-dd HH:mm</maven.build.timestamp.format>
     </properties>
 
     <dependencies>
         <dependency>
             <groupId>org.languagetool</groupId>
             <artifactId>language-all</artifactId>
-            <version>5.9</version>
+            <version>6.5</version>
         </dependency>
         <!--
         <dependency>

languagetool-commandline/src/main/java/org/languagetool/commandline/CommandLineTools.java

@@ -179,7 +179,7 @@ public static void printMatches(List<RuleMatch> ruleMatches,
       }
       if (verbose && rule instanceof AbstractPatternRule) {
         AbstractPatternRule pRule = (AbstractPatternRule) rule;
-        output += " line=" + pRule.getXmlLineNumber();
+        output += " (line " + pRule.getXmlLineNumber()+")";
       }
       System.out.println(output);
       String msg = lang.toAdvancedTypography(match.getMessage()); //.replaceAll("<suggestion>", lang.getOpeningDoubleQuote()).replaceAll("</suggestion>", lang.getClosingDoubleQuote())

languagetool-core/pom.xml

@@ -57,6 +57,10 @@
             <groupId>com.google.guava</groupId>
             <artifactId>guava</artifactId>
         </dependency>
+        <dependency>
+            <groupId>com.google.protobuf</groupId>
+            <artifactId>protobuf-java</artifactId>
+        </dependency>
         <dependency>
             <groupId>com.hankcs</groupId>
             <artifactId>aho-corasick-double-array-trie</artifactId>
@@ -65,10 +69,6 @@
             <groupId>com.optimaize.languagedetector</groupId>
             <artifactId>language-detector</artifactId>
         </dependency>
-        <dependency>
-            <groupId>com.vdurmont</groupId>
-            <artifactId>emoji-java</artifactId>
-        </dependency>
         <dependency>
             <groupId>commons-logging</groupId>
             <artifactId>commons-logging</artifactId>
@@ -315,20 +315,6 @@
                 </plugins>
             </build>
         </profile>
-        <profile>
-            <id>jdk8</id>
-            <activation>
-                <jdk>(,8)</jdk>
-            </activation>
-            <build>
-                <plugins>
-                    <plugin>
-                        <groupId>pl.project13.maven</groupId>
-                        <artifactId>git-commit-id-plugin</artifactId>
-                    </plugin>
-                </plugins>
-            </build>
-        </profile>
         <profile>
             <id>protoc</id>
             <build>

languagetool-core/src/main/java/org/languagetool/AnalyzedSentence.java

@@ -163,6 +163,14 @@ public AnalyzedTokenReadings[] getTokensWithoutWhitespace() {
     return nonBlankTokens.clone();
   }
 
+  /**
+   * Get the length of the array returned by {@link #getTokensWithoutWhitespace()} without additional allocations.
+   */
+  @ApiStatus.Internal
+  public int getNonWhitespaceTokenCount() {
+    return nonBlankTokens.length;
+  }
+
   /**
    * @since 4.5
    */

languagetool-core/src/main/java/org/languagetool/AnalyzedTokenReadings.java

@@ -297,6 +297,15 @@ public AnalyzedToken readingWithTagRegex(String posTagRegex) {
     }
     return null;
   }
+
+  public AnalyzedToken readingWithTagRegex(Pattern pattern) {
+    for (AnalyzedToken reading : anTokReadings) {
+      if (reading.getPOSTag() != null && pattern.matcher(reading.getPOSTag()).matches()) {
+        return reading;
+      }
+    }
+    return null;
+  }
 
   /**
    * Returns the first reading that matches a given lemma.