├── .github └── workflows │ └── build_fatJAR.yml ├── .gitignore ├── CHANGELOG.md ├── LICENSE ├── README.md ├── build.gradle.kts ├── gradle.properties ├── gradle └── wrapper │ ├── gradle-wrapper.jar │ └── gradle-wrapper.properties ├── gradlew ├── gradlew.bat ├── settings.gradle.kts ├── src ├── main │ └── java │ │ └── io │ │ └── shubham0204 │ │ └── text2summary │ │ ├── EnglishStopWords.kt │ │ ├── TFIDFSummarizer.kt │ │ ├── Text2Summary.kt │ │ └── Tokenizer.kt └── test │ └── java │ └── Text2SummaryTests.kt └── text2summary_banner.png /.github/workflows/build_fatJAR.yml: -------------------------------------------------------------------------------- 1 | name: Build Fat JAR and Release 2 | 3 | on: 4 | push: 5 | tags: 6 | - 'v*' 7 | 8 | jobs: 9 | build_jar: 10 | name: Build Fat JAR and Release 11 | runs-on: ubuntu-latest 12 | steps: 13 | - name: Checkout project source code 14 | uses: actions/checkout@v4 15 | 16 | - name: Set up JDK 21 17 | uses: actions/setup-java@v4.2.1 18 | with: 19 | java-version: '21' 20 | distribution: 'corretto' 21 | cache: gradle 22 | 23 | - name: Grant execute permission for gradlew 24 | run: chmod +x gradlew 25 | 26 | - name: Build with Gradle 27 | run: ./gradlew build 28 | 29 | - name: Build Fat JAR 30 | run: ./gradlew shadowJar --stacktrace 31 | 32 | - name: Create a release 33 | uses: actions/create-release@v1 34 | id: create_release 35 | with: 36 | draft: false 37 | prerelease: false 38 | release_name: Text2Summary - ${{ github.ref }} 39 | tag_name: ${{ github.ref }} 40 | body_path: CHANGELOG.md 41 | env: 42 | GITHUB_TOKEN: ${{ github.token }} 43 | 44 | - name: Upload fatJar to release 45 | uses: actions/upload-release-asset@v1 46 | env: 47 | GITHUB_TOKEN: ${{ github.token }} 48 | with: 49 | upload_url: ${{ steps.create_release.outputs.upload_url }} 50 | asset_path: build/libs/Text2Summary-0.0.1-all.jar 51 | asset_name: Text2Summary-0.0.1-all.jar 52 | asset_content_type: application/java-archive -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- 1 | *.iml 2 | .gradle 3 | /local.properties 4 | /.idea/caches 5 | /.idea/libraries 6 | /.idea/modules.xml 7 | /.idea/workspace.xml 8 | /.idea/navEditor.xml 9 | /.idea/assetWizardSettings.xml 10 | .DS_Store 11 | /build 12 | /captures 13 | .externalNativeBuild 14 | .cxx 15 | -------------------------------------------------------------------------------- /CHANGELOG.md: -------------------------------------------------------------------------------- 1 | Initial release of `Text2Summary-Android` -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "[]" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright 2025 Shubham Panchal 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. 202 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | 2 | # Text2Summary - Text Summarization with TFIDF in Kotlin 3 | 4 | ![](text2summary_banner.png) 5 | 6 | [![](https://jitpack.io/v/shubham0204/Text2Summary-Android.svg)](https://jitpack.io/#shubham0204/Text2Summary-Android) 7 | 8 | [![forthebadge](https://forthebadge.com/images/badges/built-for-android.svg)](https://forthebadge.com) 9 | 10 | Text2Summary API uses on-device methods to perform text summarization on Android applications. It uses extractive text summarization 11 | to give you the most important sentences from a given text. 12 | 13 | You may [read the story of Text2Summary on Medium](https://medium.com/@equipintelligence/introducing-text2summary-text-summarization-on-android-674b62419019). 14 | 15 | * [Installation](#installation) 16 | * [Usage](#usage) 17 | * [More on Text2Summary](#more-on-text2summary) 18 | * [Contribute](#contribute) 19 | 20 | 21 | ## Installation 22 | 23 | For the latest fat JAR, see [Releases](https://github.com/shubham0204/Text2Summary-Android/releases). 24 | 25 | ## Usage 26 | 27 | The text which needs to be summarized has to be a `String` object. Then, 28 | use `Text2Summary.summarize()` method to generate the summary. 29 | 30 | `Text2Summary.summarize()` is a suspend function and hence it should be called within a `CoroutineContext`. 31 | 32 | ```kotlin 33 | 34 | runBlocking { 35 | var summary = Text2Summary.summarize(someLongText, compressionRate = 0.7) 36 | } 37 | ``` 38 | The number `0.7` is referred as the compression factor. Meaning, given a text of 10 sentences, a summary of 7 sentences will be 39 | produced. This number must lie in the interval `( 0 , 1 )`. 40 | 41 | You may extract text from a file and then pass it to Text2Summary, 42 | 43 | ```kotlin 44 | 45 | val bufferedReader: BufferedReader = File( "poems.txt" ).bufferedReader() 46 | val text = bufferedReader.use{ it.readText() } 47 | val summary = Text2Summary.summarize( text , 0.7 ) 48 | 49 | ``` 50 | 51 | The `summarizeAsync()` method internally calls the `summarize()` method itself wrapped in a `AsyncTask`. 52 | 53 | ## More on Text2Summary 54 | 55 | Text2Summary uses the TF-IDF algorithm for extractive text summarization. Note, this is not abstractive text summarization which 56 | use neural networks like the Seq2Seq model. As TensorFlow Lite does not support fully the conversion of `Embedding` and `LSTM` 57 | layers, we need to use the TF-IDF algorithm. 58 | 59 | 1. The `text` which is given to `TextSummary.summarize()` is broken down into sentences. These sentences are further brought down 60 | to words ( tokens ). 61 | 2. Using TF-IDF algorithm, a TF-IDF score is calculated for each word. 62 | 3. Next, we take the sum of such scores for all words present in the sentence. 63 | 4. Finally, we take the top N highest scores. The corresponding sentences hold most of the information present in the text. These 64 | sentences are then concatenated and returned as the summary. 65 | 66 | ## Contribute 67 | 68 | If you are facing any issues, [open an issue](https://github.com/shubham0204/Text2Summary/issues) on the repository. 69 | 70 | 71 | 72 | 73 | -------------------------------------------------------------------------------- /build.gradle.kts: -------------------------------------------------------------------------------- 1 | plugins { 2 | kotlin("jvm") version "2.0.0" 3 | id("com.github.johnrengelman.shadow") version "8.1.1" 4 | id("maven-publish") 5 | } 6 | 7 | group = "io.shubham0204" 8 | version = "0.0.1" 9 | 10 | repositories { 11 | mavenCentral() 12 | } 13 | 14 | dependencies { 15 | implementation("org.jetbrains.kotlinx:kotlinx-coroutines-core:1.10.1") 16 | implementation("org.jetbrains.kotlinx:kotlinx-coroutines-core-jvm:1.10.1") 17 | testImplementation(kotlin("test")) 18 | } 19 | 20 | kotlin { 21 | jvmToolchain(21) 22 | } 23 | 24 | tasks.test { 25 | useJUnitPlatform() 26 | } 27 | 28 | publishing { 29 | publications { 30 | create("release", MavenPublication::class.java) { 31 | from(components["java"]) 32 | groupId = "io.shubham0204" 33 | artifactId = "text2summary" 34 | version = version 35 | } 36 | } 37 | } 38 | -------------------------------------------------------------------------------- /gradle.properties: -------------------------------------------------------------------------------- 1 | kotlin.code.style=official 2 | -------------------------------------------------------------------------------- /gradle/wrapper/gradle-wrapper.jar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shubham0204/Text2Summary-Android/749bd6512b2583554b2b5d1a99ccaaf0c9911b6d/gradle/wrapper/gradle-wrapper.jar -------------------------------------------------------------------------------- /gradle/wrapper/gradle-wrapper.properties: -------------------------------------------------------------------------------- 1 | #Sat Feb 01 09:40:30 IST 2025 2 | distributionBase=GRADLE_USER_HOME 3 | distributionPath=wrapper/dists 4 | distributionUrl=https\://services.gradle.org/distributions/gradle-8.9-bin.zip 5 | zipStoreBase=GRADLE_USER_HOME 6 | zipStorePath=wrapper/dists 7 | -------------------------------------------------------------------------------- /gradlew: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env sh 2 | 3 | ############################################################################## 4 | ## 5 | ## Gradle start up script for UN*X 6 | ## 7 | ############################################################################## 8 | 9 | # Attempt to set APP_HOME 10 | # Resolve links: $0 may be a link 11 | PRG="$0" 12 | # Need this for relative symlinks. 13 | while [ -h "$PRG" ]; do 14 | ls=$(ls -ld "$PRG") 15 | link=$(expr "$ls" : '.*-> \(.*\)$') 16 | if expr "$link" : '/.*' >/dev/null; then 17 | PRG="$link" 18 | else 19 | PRG=$(dirname "$PRG")"/$link" 20 | fi 21 | done 22 | SAVED="$(pwd)" 23 | cd "$(dirname \"$PRG\")/" >/dev/null 24 | APP_HOME="$(pwd -P)" 25 | cd "$SAVED" >/dev/null 26 | 27 | APP_NAME="Gradle" 28 | APP_BASE_NAME=$(basename "$0") 29 | 30 | # Add default JVM options here. You can also use JAVA_OPTS and GRADLE_OPTS to pass JVM options to this script. 31 | DEFAULT_JVM_OPTS="" 32 | 33 | # Use the maximum available, or set MAX_FD != -1 to use that value. 34 | MAX_FD="maximum" 35 | 36 | warn() { 37 | echo "$*" 38 | } 39 | 40 | die() { 41 | echo 42 | echo "$*" 43 | echo 44 | exit 1 45 | } 46 | 47 | # OS specific support (must be 'true' or 'false'). 48 | cygwin=false 49 | msys=false 50 | darwin=false 51 | nonstop=false 52 | case "$(uname)" in 53 | CYGWIN*) 54 | cygwin=true 55 | ;; 56 | Darwin*) 57 | darwin=true 58 | ;; 59 | MINGW*) 60 | msys=true 61 | ;; 62 | NONSTOP*) 63 | nonstop=true 64 | ;; 65 | esac 66 | 67 | CLASSPATH=$APP_HOME/gradle/wrapper/gradle-wrapper.jar 68 | 69 | # Determine the Java command to use to start the JVM. 70 | if [ -n "$JAVA_HOME" ]; then 71 | if [ -x "$JAVA_HOME/jre/sh/java" ]; then 72 | # IBM's JDK on AIX uses strange locations for the executables 73 | JAVACMD="$JAVA_HOME/jre/sh/java" 74 | else 75 | JAVACMD="$JAVA_HOME/bin/java" 76 | fi 77 | if [ ! -x "$JAVACMD" ]; then 78 | die "ERROR: JAVA_HOME is set to an invalid directory: $JAVA_HOME 79 | 80 | Please set the JAVA_HOME variable in your environment to match the 81 | location of your Java installation." 82 | fi 83 | else 84 | JAVACMD="java" 85 | which java >/dev/null 2>&1 || die "ERROR: JAVA_HOME is not set and no 'java' command could be found in your PATH. 86 | 87 | Please set the JAVA_HOME variable in your environment to match the 88 | location of your Java installation." 89 | fi 90 | 91 | # Increase the maximum file descriptors if we can. 92 | if [ "$cygwin" = "false" -a "$darwin" = "false" -a "$nonstop" = "false" ]; then 93 | MAX_FD_LIMIT=$(ulimit -H -n) 94 | if [ $? -eq 0 ]; then 95 | if [ "$MAX_FD" = "maximum" -o "$MAX_FD" = "max" ]; then 96 | MAX_FD="$MAX_FD_LIMIT" 97 | fi 98 | ulimit -n $MAX_FD 99 | if [ $? -ne 0 ]; then 100 | warn "Could not set maximum file descriptor limit: $MAX_FD" 101 | fi 102 | else 103 | warn "Could not query maximum file descriptor limit: $MAX_FD_LIMIT" 104 | fi 105 | fi 106 | 107 | # For Darwin, add options to specify how the application appears in the dock 108 | if $darwin; then 109 | GRADLE_OPTS="$GRADLE_OPTS \"-Xdock:name=$APP_NAME\" \"-Xdock:icon=$APP_HOME/media/gradle.icns\"" 110 | fi 111 | 112 | # For Cygwin, switch paths to Windows format before running java 113 | if $cygwin; then 114 | APP_HOME=$(cygpath --path --mixed "$APP_HOME") 115 | CLASSPATH=$(cygpath --path --mixed "$CLASSPATH") 116 | JAVACMD=$(cygpath --unix "$JAVACMD") 117 | 118 | # We build the pattern for arguments to be converted via cygpath 119 | ROOTDIRSRAW=$(find -L / -maxdepth 1 -mindepth 1 -type d 2>/dev/null) 120 | SEP="" 121 | for dir in $ROOTDIRSRAW; do 122 | ROOTDIRS="$ROOTDIRS$SEP$dir" 123 | SEP="|" 124 | done 125 | OURCYGPATTERN="(^($ROOTDIRS))" 126 | # Add a user-defined pattern to the cygpath arguments 127 | if [ "$GRADLE_CYGPATTERN" != "" ]; then 128 | OURCYGPATTERN="$OURCYGPATTERN|($GRADLE_CYGPATTERN)" 129 | fi 130 | # Now convert the arguments - kludge to limit ourselves to /bin/sh 131 | i=0 132 | for arg in "$@"; do 133 | CHECK=$(echo "$arg" | egrep -c "$OURCYGPATTERN" -) 134 | CHECK2=$(echo "$arg" | egrep -c "^-") ### Determine if an option 135 | 136 | if [ $CHECK -ne 0 ] && [ $CHECK2 -eq 0 ]; then ### Added a condition 137 | eval $(echo args$i)=$(cygpath --path --ignore --mixed "$arg") 138 | else 139 | eval $(echo args$i)="\"$arg\"" 140 | fi 141 | i=$((i + 1)) 142 | done 143 | case $i in 144 | 0) set -- ;; 145 | 1) set -- "$args0" ;; 146 | 2) set -- "$args0" "$args1" ;; 147 | 3) set -- "$args0" "$args1" "$args2" ;; 148 | 4) set -- "$args0" "$args1" "$args2" "$args3" ;; 149 | 5) set -- "$args0" "$args1" "$args2" "$args3" "$args4" ;; 150 | 6) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" ;; 151 | 7) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" "$args6" ;; 152 | 8) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" "$args6" "$args7" ;; 153 | 9) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" "$args6" "$args7" "$args8" ;; 154 | esac 155 | fi 156 | 157 | # Escape application args 158 | save() { 159 | for i; do printf %s\\n "$i" | sed "s/'/'\\\\''/g;1s/^/'/;\$s/\$/' \\\\/"; done 160 | echo " " 161 | } 162 | APP_ARGS=$(save "$@") 163 | 164 | # Collect all arguments for the java command, following the shell quoting and substitution rules 165 | eval set -- $DEFAULT_JVM_OPTS $JAVA_OPTS $GRADLE_OPTS "\"-Dorg.gradle.appname=$APP_BASE_NAME\"" -classpath "\"$CLASSPATH\"" org.gradle.wrapper.GradleWrapperMain "$APP_ARGS" 166 | 167 | # by default we should be in the correct project dir, but when run from Finder on Mac, the cwd is wrong 168 | if [ "$(uname)" = "Darwin" ] && [ "$HOME" = "$PWD" ]; then 169 | cd "$(dirname "$0")" 170 | fi 171 | 172 | exec "$JAVACMD" "$@" 173 | -------------------------------------------------------------------------------- /gradlew.bat: -------------------------------------------------------------------------------- 1 | @if "%DEBUG%" == "" @echo off 2 | @rem ########################################################################## 3 | @rem 4 | @rem Gradle startup script for Windows 5 | @rem 6 | @rem ########################################################################## 7 | 8 | @rem Set local scope for the variables with windows NT shell 9 | if "%OS%"=="Windows_NT" setlocal 10 | 11 | set DIRNAME=%~dp0 12 | if "%DIRNAME%" == "" set DIRNAME=. 13 | set APP_BASE_NAME=%~n0 14 | set APP_HOME=%DIRNAME% 15 | 16 | @rem Add default JVM options here. You can also use JAVA_OPTS and GRADLE_OPTS to pass JVM options to this script. 17 | set DEFAULT_JVM_OPTS= 18 | 19 | @rem Find java.exe 20 | if defined JAVA_HOME goto findJavaFromJavaHome 21 | 22 | set JAVA_EXE=java.exe 23 | %JAVA_EXE% -version >NUL 2>&1 24 | if "%ERRORLEVEL%" == "0" goto init 25 | 26 | echo. 27 | echo ERROR: JAVA_HOME is not set and no 'java' command could be found in your PATH. 28 | echo. 29 | echo Please set the JAVA_HOME variable in your environment to match the 30 | echo location of your Java installation. 31 | 32 | goto fail 33 | 34 | :findJavaFromJavaHome 35 | set JAVA_HOME=%JAVA_HOME:"=% 36 | set JAVA_EXE=%JAVA_HOME%/bin/java.exe 37 | 38 | if exist "%JAVA_EXE%" goto init 39 | 40 | echo. 41 | echo ERROR: JAVA_HOME is set to an invalid directory: %JAVA_HOME% 42 | echo. 43 | echo Please set the JAVA_HOME variable in your environment to match the 44 | echo location of your Java installation. 45 | 46 | goto fail 47 | 48 | :init 49 | @rem Get command-line arguments, handling Windows variants 50 | 51 | if not "%OS%" == "Windows_NT" goto win9xME_args 52 | 53 | :win9xME_args 54 | @rem Slurp the command line arguments. 55 | set CMD_LINE_ARGS= 56 | set _SKIP=2 57 | 58 | :win9xME_args_slurp 59 | if "x%~1" == "x" goto execute 60 | 61 | set CMD_LINE_ARGS=%* 62 | 63 | :execute 64 | @rem Setup the command line 65 | 66 | set CLASSPATH=%APP_HOME%\gradle\wrapper\gradle-wrapper.jar 67 | 68 | @rem Execute Gradle 69 | "%JAVA_EXE%" %DEFAULT_JVM_OPTS% %JAVA_OPTS% %GRADLE_OPTS% "-Dorg.gradle.appname=%APP_BASE_NAME%" -classpath "%CLASSPATH%" org.gradle.wrapper.GradleWrapperMain %CMD_LINE_ARGS% 70 | 71 | :end 72 | @rem End local scope for the variables with windows NT shell 73 | if "%ERRORLEVEL%"=="0" goto mainEnd 74 | 75 | :fail 76 | rem Set variable GRADLE_EXIT_CONSOLE if you need the _script_ return code instead of 77 | rem the _cmd.exe /c_ return code! 78 | if not "" == "%GRADLE_EXIT_CONSOLE%" exit 1 79 | exit /b 1 80 | 81 | :mainEnd 82 | if "%OS%"=="Windows_NT" endlocal 83 | 84 | :omega 85 | -------------------------------------------------------------------------------- /settings.gradle.kts: -------------------------------------------------------------------------------- 1 | plugins { 2 | id("org.gradle.toolchains.foojay-resolver-convention") version "0.5.0" 3 | } 4 | rootProject.name = "Text2Summary" 5 | -------------------------------------------------------------------------------- /src/main/java/io/shubham0204/text2summary/EnglishStopWords.kt: -------------------------------------------------------------------------------- 1 | /* 2 | * Copyright (C) 2025 Shubham Panchal 3 | * 4 | * Licensed under the Apache License, Version 2.0 (the "License"); 5 | * you may not use this file except in compliance with the License. 6 | * You may obtain a copy of the License at 7 | * 8 | * http://www.apache.org/licenses/LICENSE-2.0 9 | * 10 | * Unless required by applicable law or agreed to in writing, software 11 | * distributed under the License is distributed on an "AS IS" BASIS, 12 | * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 13 | * See the License for the specific language governing permissions and 14 | * limitations under the License. 15 | */ 16 | 17 | package io.shubham0204.text2summary 18 | 19 | // English Stop words taken from here -> https://gist.github.com/sebleier/554280 20 | val ENGLISH_STOP_WORDS = 21 | arrayOf( 22 | "i", 23 | "me", 24 | "my", 25 | "myself", 26 | "we", 27 | "our", 28 | "ours", 29 | "ourselves", 30 | "you", 31 | "your", 32 | "yours", 33 | "yourself", 34 | "yourselves", 35 | "he", 36 | "him", 37 | "his", 38 | "himself", 39 | "she", 40 | "her", 41 | "hers", 42 | "herself", 43 | "it", 44 | "its", 45 | "itself", 46 | "they", 47 | "them", 48 | "their", 49 | "theirs", 50 | "themselves", 51 | "what", 52 | "which", 53 | "who", 54 | "whom", 55 | "this", 56 | "that", 57 | "these", 58 | "those", 59 | "am", 60 | "is", 61 | "are", 62 | "was", 63 | "were", 64 | "be", 65 | "been", 66 | "being", 67 | "have", 68 | "has", 69 | "had", 70 | "having", 71 | "do", 72 | "does", 73 | "did", 74 | "doing", 75 | "a", 76 | "an", 77 | "the", 78 | "and", 79 | "but", 80 | "if", 81 | "or", 82 | "because", 83 | "as", 84 | "until", 85 | "while", 86 | "of", 87 | "at", 88 | "by", 89 | "for", 90 | "with", 91 | "about", 92 | "against", 93 | "between", 94 | "into", 95 | "through", 96 | "during", 97 | "before", 98 | "after", 99 | "above", 100 | "below", 101 | "to", 102 | "from", 103 | "up", 104 | "down", 105 | "in", 106 | "out", 107 | "on", 108 | "off", 109 | "over", 110 | "under", 111 | "again", 112 | "further", 113 | "then", 114 | "once", 115 | "here", 116 | "there", 117 | "when", 118 | "where", 119 | "why", 120 | "how", 121 | "all", 122 | "any", 123 | "both", 124 | "each", 125 | "few", 126 | "more", 127 | "most", 128 | "other", 129 | "some", 130 | "such", 131 | "no", 132 | "nor", 133 | "not", 134 | "only", 135 | "own", 136 | "same", 137 | "so", 138 | "than", 139 | "too", 140 | "very", 141 | "s", 142 | "t", 143 | "can", 144 | "will", 145 | "just", 146 | "don", 147 | "should", 148 | "now", 149 | ) 150 | -------------------------------------------------------------------------------- /src/main/java/io/shubham0204/text2summary/TFIDFSummarizer.kt: -------------------------------------------------------------------------------- 1 | /* 2 | * Copyright (C) 2025 Shubham Panchal 3 | * 4 | * Licensed under the Apache License, Version 2.0 (the "License"); 5 | * you may not use this file except in compliance with the License. 6 | * You may obtain a copy of the License at 7 | * 8 | * http://www.apache.org/licenses/LICENSE-2.0 9 | * 10 | * Unless required by applicable law or agreed to in writing, software 11 | * distributed under the License is distributed on an "AS IS" BASIS, 12 | * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 13 | * See the License for the specific language governing permissions and 14 | * limitations under the License. 15 | */ 16 | 17 | package io.shubham0204.text2summary 18 | 19 | import kotlinx.coroutines.CoroutineScope 20 | import kotlinx.coroutines.Dispatchers 21 | import kotlinx.coroutines.joinAll 22 | import kotlinx.coroutines.launch 23 | import kotlinx.coroutines.sync.Mutex 24 | import kotlinx.coroutines.sync.withLock 25 | import java.lang.Exception 26 | import kotlin.collections.ArrayList 27 | import kotlin.collections.HashMap 28 | import kotlin.math.floor 29 | import kotlin.math.log10 30 | 31 | // Uses Term Frequency-Inverse Document Frequency ( TF-IDF ) to summarize texts. First, we vectorize the sentences, 32 | // such that each token has its own TF-IDF score. We take the sum of all TF-IDF scores in a sentence. The sentences with 33 | // top N highest sums are included in the summary. 34 | class TFIDFSummarizer { 35 | // Returns the indices of sentences of a summary of the given text. Here, rate is the fraction of the text whose length equals the summary length. 36 | // For instance, a rate of 0.7 means that the summary will consist of 7 sentences given 10 sentences of text. 37 | suspend fun compute( 38 | text: String, 39 | rate: Float, 40 | ): Array { 41 | // Check whether the rate lies in the given range. 42 | if (!Tokenizer.checkRate(rate)) { 43 | throw Exception("The compression rate must lie in the interval ( 0 , 1 ).") 44 | } 45 | 46 | // Get sentences from the text. 47 | val sentences = Tokenizer.textToSentences(Tokenizer.removeLineBreaks(text)) 48 | val sentenceTokens = sentences.map { Tokenizer.sentenceToTokens(it) } 49 | val tokensList = ArrayList() 50 | 51 | // Collect all the words present in the text. 52 | sentenceTokens.forEach { 53 | tokensList.addAll(it) 54 | } 55 | 56 | // Create a ( word , frequency ) vocab. 57 | val vocab = Tokenizer.buildVocab(tokensList.toTypedArray()) 58 | val tfidfSumList = ArrayList>() 59 | val tfidfSumListMutex = Mutex() 60 | 61 | // For each sentence, calculate TF, IDF and then TFIDF. Take the sum of all TF-IDF scores for all words in the 62 | // sentence and append it to a list. 63 | sentenceTokens 64 | .mapIndexed { idx, tokenizedSentence -> 65 | CoroutineScope(Dispatchers.Default).launch { 66 | val termFrequency = computeTermFrequency(tokenizedSentence, vocab) 67 | val inverseDocumentFrequency = 68 | computeInverseDocumentFrequency(termFrequency, sentenceTokens.toTypedArray()) 69 | val tfIDF = computeTFIDF(termFrequency, inverseDocumentFrequency) 70 | tfidfSumListMutex.withLock { 71 | tfidfSumList.add(Pair(idx, tfIDF.values.sum())) 72 | } 73 | } 74 | }.joinAll() 75 | tfidfSumList.sortBy { it.first } 76 | val sentenceTFIDFScores = tfidfSumList.map { it.second }.toTypedArray() 77 | 78 | // Get the indices of top N maximum values from `weightedFreqSums`. 79 | val n = floor((sentences.size * rate).toDouble()).toInt() 80 | val topNIndices = 81 | Tokenizer.getTopNIndices( 82 | sentenceTFIDFScores, 83 | sentenceTFIDFScores.apply { 84 | sort() 85 | reverse() 86 | }, 87 | n, 88 | ) 89 | return topNIndices 90 | } 91 | 92 | // Computes the Term Frequency for a given sentence. For a token in a sentence, term frequency equals, 93 | // term_frequency = frequency_in_sentence / num_tokens_in_sentence 94 | private fun computeTermFrequency( 95 | s: Array, 96 | vocab: Map, 97 | ): Map { 98 | val freqMatrix = HashMap() 99 | for (word in vocab.keys) { 100 | freqMatrix[word] = 0f 101 | } 102 | for (word in s) { 103 | freqMatrix[word] = freqMatrix[word]!! + 1f 104 | } 105 | val tfFreqMatrix = HashMap() 106 | for ((word, count) in freqMatrix) { 107 | tfFreqMatrix[word] = count / s.size.toFloat() // Calculation of TF 108 | } 109 | return tfFreqMatrix 110 | } 111 | 112 | // Computes Inverse Document Frequency ( IDF ). It calculates the frequency of a tokens in all documents ( sentences ). 113 | // The IDF value is given by, 114 | // IDF = log10( num_docs / frequency_in_docs ) 115 | private fun computeInverseDocumentFrequency( 116 | freqMatrix: Map, 117 | docs: Array>, 118 | ): HashMap { 119 | val freqInDocMap = HashMap() 120 | for (word in freqMatrix.keys) { 121 | freqInDocMap[word] = 0f 122 | } 123 | for (doc in docs) { 124 | for (word in freqMatrix.keys) { 125 | if (doc.contains(word)) { 126 | freqInDocMap[ word ] = freqInDocMap[ word ]!! + 1f 127 | } 128 | } 129 | } 130 | val numDocs = docs.size.toFloat() 131 | val idfMap = HashMap() 132 | for ((word, freqInDoc) in freqInDocMap) { 133 | idfMap[ word ] = log10(numDocs.toDouble() / freqInDoc.toDouble()).toFloat() 134 | } 135 | return idfMap 136 | } 137 | 138 | // Calculate the final product of the TF and IDF scores. 139 | private fun computeTFIDF( 140 | tfMatrix: Map, 141 | idfMatrix: Map, 142 | ): HashMap { 143 | val tfidfMatrix = HashMap() 144 | for (word in tfMatrix.keys) { 145 | tfidfMatrix[word] = tfMatrix[ word ]!! * idfMatrix[ word ]!! 146 | } 147 | return tfidfMatrix 148 | } 149 | } 150 | -------------------------------------------------------------------------------- /src/main/java/io/shubham0204/text2summary/Text2Summary.kt: -------------------------------------------------------------------------------- 1 | /* 2 | * Copyright (C) 2025 Shubham Panchal 3 | * 4 | * Licensed under the Apache License, Version 2.0 (the "License"); 5 | * you may not use this file except in compliance with the License. 6 | * You may obtain a copy of the License at 7 | * 8 | * http://www.apache.org/licenses/LICENSE-2.0 9 | * 10 | * Unless required by applicable law or agreed to in writing, software 11 | * distributed under the License is distributed on an "AS IS" BASIS, 12 | * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 13 | * See the License for the specific language governing permissions and 14 | * limitations under the License. 15 | */ 16 | 17 | package io.shubham0204.text2summary 18 | 19 | // The Text2Summary API for Android. 20 | class Text2Summary { 21 | companion object { 22 | // Summarizes the given text. Note, this method should be used whe you're dealing with long texts. 23 | // It performs the summarization on the background thread. Once the process is complete the summary is 24 | // passed to the SummaryCallback.onSummaryProduced callback. 25 | @JvmStatic 26 | suspend fun summarize( 27 | text: String, 28 | compressionRate: Float, 29 | ): String { 30 | val sentences = Tokenizer.textToSentences(Tokenizer.removeLineBreaks(text)) 31 | val tfidfSummarizer = TFIDFSummarizer() 32 | val summarySentenceIndices = tfidfSummarizer.compute(text, compressionRate) 33 | return buildString(sentences, summarySentenceIndices).trim() 34 | } 35 | 36 | // Fetchs the sentences from topNValues and concatenates them to produce a complete. String. 37 | private fun buildString( 38 | sentences: Array, 39 | topNValues: Array, 40 | ): String { 41 | var summary = "" 42 | topNValues.forEach { 43 | summary += sentences[it] + " " 44 | } 45 | return summary 46 | } 47 | } 48 | } 49 | -------------------------------------------------------------------------------- /src/main/java/io/shubham0204/text2summary/Tokenizer.kt: -------------------------------------------------------------------------------- 1 | /* 2 | * Copyright (C) 2025 Shubham Panchal 3 | * 4 | * Licensed under the Apache License, Version 2.0 (the "License"); 5 | * you may not use this file except in compliance with the License. 6 | * You may obtain a copy of the License at 7 | * 8 | * http://www.apache.org/licenses/LICENSE-2.0 9 | * 10 | * Unless required by applicable law or agreed to in writing, software 11 | * distributed under the License is distributed on an "AS IS" BASIS, 12 | * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 13 | * See the License for the specific language governing permissions and 14 | * limitations under the License. 15 | */ 16 | 17 | package io.shubham0204.text2summary 18 | 19 | import java.util.regex.Pattern 20 | import kotlin.collections.ArrayList 21 | import kotlin.collections.HashMap 22 | 23 | // Helper class which transforms texts to tokens, builds ( word , frequency ) HashMaps. 24 | class Tokenizer { 25 | companion object { 26 | // Returns a list of sentences from the given paragraph. 27 | fun textToSentences(para: String): Array { 28 | val text = para.trim() 29 | val pattern = 30 | Pattern.compile( 31 | "[^.!?\\s][^.!?]*(?:[.!?](?!['\"]?\\s|$)[^.!?]*)*[.!?]?['\"]?(?=\\s|$)", 32 | Pattern.MULTILINE or Pattern.COMMENTS, 33 | ) 34 | val matcher = pattern.matcher(text) 35 | val sentences = ArrayList() 36 | while (matcher.find()) { 37 | sentences.add(matcher.group()) 38 | } 39 | return sentences.toTypedArray() 40 | } 41 | 42 | // Returns a list of tokens ( words ) from a given sentence ( seq of words ). 43 | fun sentenceToTokens(s: String): Array { 44 | val sentence = s.trim().toLowerCase() 45 | var tokens = sentence.split(" ") 46 | tokens = tokens.map { Regex("[^A-Za-z0-9 ]").replace(it, "") } 47 | tokens = tokens.filter { !ENGLISH_STOP_WORDS.contains(it.trim()) } 48 | tokens = tokens.filter { it.trim().isNotEmpty() and it.trim().isNotBlank() } 49 | return tokens.toTypedArray() 50 | } 51 | 52 | // Builds a ( word , frequency ) HashMap. 53 | fun buildVocab(words: Array): Map { 54 | val sortedWords = words.toSet() 55 | val vocab = HashMap() 56 | for (word in sortedWords) { 57 | vocab[word] = words.count { it.equals(word) } 58 | } 59 | return vocab 60 | } 61 | 62 | // Builds a ( word , weighted_frequency ) HashMap. 63 | fun getWeightedVocab(vocab: Map): Map { 64 | val maxFreq = vocab.values.max().toFloat() 65 | val weightedFreqHashMap = HashMap() 66 | vocab.entries.forEach { 67 | weightedFreqHashMap.put(it.key, it.value.toFloat() / maxFreq) 68 | } 69 | return weightedFreqHashMap 70 | } 71 | 72 | // Removes \n and \r from the given String. 73 | fun removeLineBreaks(para: String): String = 74 | para 75 | .replace("\n", " ") 76 | .replace("\r", " ") 77 | 78 | // Checks if the compression rate lie in ( 0 , 1 ]. 79 | fun checkRate(rate: Float): Boolean = rate > 0.0 && rate < 1.0 80 | 81 | // Get the indices of top N maximum values in X. 82 | fun getTopNIndices( 83 | x: Array, 84 | xSorted: Array, 85 | N: Int, 86 | ): Array { 87 | val topN = xSorted.take(N) 88 | val topNIndices = ArrayList() 89 | for (i in topN) { 90 | topNIndices.add(x.indexOf(i)) 91 | } 92 | topNIndices.sort() 93 | return topNIndices.distinct().toTypedArray() 94 | } 95 | } 96 | } 97 | -------------------------------------------------------------------------------- /src/test/java/Text2SummaryTests.kt: -------------------------------------------------------------------------------- 1 | import io.shubham0204.text2summary.Text2Summary 2 | import kotlinx.coroutines.runBlocking 3 | import org.junit.jupiter.api.assertThrows 4 | import kotlin.test.Test 5 | import kotlin.test.assertEquals 6 | 7 | class Text2SummaryTests { 8 | private val text = 9 | "Flowers are nature's vibrant masterpieces, adorning the world with their diverse colors, shapes, and fragrances. " + 10 | "They play a crucial role in ecosystems, attracting pollinators like bees and butterflies, which help plants reproduce. " + 11 | "Beyond their ecological significance, flowers hold deep cultural and emotional meanings, often symbolizing love, beauty, and " + 12 | "renewal across various societies. From the delicate petals of a rose to the bold, sunlit blooms of a sunflower, each " + 13 | "flower carries its unique charm and message. Whether used in gardens, bouquets, or ceremonies, flowers have an " + 14 | "undeniable ability to uplift spirits and connect people through shared appreciation for their natural elegance." 15 | 16 | private val expectedSummary06 = 17 | "Flowers are nature's vibrant masterpieces, adorning the world with their diverse colors, shapes, and fragrances. Beyond their ecological significance, flowers hold deep cultural and emotional meanings, often symbolizing love, beauty, and renewal across various societies." 18 | 19 | private val expectedSummary02 = 20 | "Flowers are nature's vibrant masterpieces, adorning the world with their diverse colors, shapes, and fragrances." 21 | 22 | @Test 23 | fun summarize_works() = 24 | runBlocking { 25 | val predictedSummary06 = Text2Summary.summarize(text, compressionRate = 0.6f) 26 | assertEquals(expectedSummary06, predictedSummary06) 27 | val predictedSummary02 = Text2Summary.summarize(text, compressionRate = 0.2f) 28 | assertEquals(expectedSummary02, predictedSummary02) 29 | } 30 | 31 | @Test 32 | fun invalidCompressRatio_throws() = 33 | runBlocking { 34 | val exception = 35 | assertThrows { 36 | Text2Summary.summarize(text, compressionRate = 1.0f) 37 | } 38 | assertEquals("The compression rate must lie in the interval ( 0 , 1 ).", exception.message) 39 | } 40 | } 41 | -------------------------------------------------------------------------------- /text2summary_banner.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shubham0204/Text2Summary-Android/749bd6512b2583554b2b5d1a99ccaaf0c9911b6d/text2summary_banner.png --------------------------------------------------------------------------------