-
Notifications
You must be signed in to change notification settings - Fork 5
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Merge branch 'develop' into add-regex-extract-text-kotlin-sample
- Loading branch information
Showing
7 changed files
with
635 additions
and
1 deletion.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
14 changes: 14 additions & 0 deletions
14
RegexTextSearch/.idea/runConfigurations/RegexTextSearch.xml
Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.
Oops, something went wrong.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,231 @@ | ||
<?xml version="1.0" encoding="UTF-8"?> | ||
<project xmlns="http://maven.apache.org/POM/4.0.0" | ||
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" | ||
xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd"> | ||
<modelVersion>4.0.0</modelVersion> | ||
<groupId>com.datalogics.pdfl.samples</groupId> | ||
<artifactId>RegexTextSearch</artifactId> | ||
<version>1.0-SNAPSHOT</version> | ||
|
||
<repositories> | ||
<repository> | ||
<id>mavenCentral</id> | ||
<url>https://repo1.maven.org/maven2/</url> | ||
</repository> | ||
</repositories> | ||
|
||
<properties> | ||
<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding> | ||
<kotlin.code.style>official</kotlin.code.style> | ||
<kotlin.compiler.jvmTarget>1.8</kotlin.compiler.jvmTarget> | ||
<maven.compiler.source>1.8</maven.compiler.source> | ||
<maven.compiler.target>1.8</maven.compiler.target> | ||
</properties> | ||
|
||
<profiles> | ||
<profile> | ||
<id>Windows64</id> | ||
<activation> | ||
<os> | ||
<family>windows</family> | ||
<arch>amd64</arch> | ||
</os> | ||
</activation> | ||
<properties> | ||
<jni.classifier>win-x86-64-jni</jni.classifier> | ||
</properties> | ||
</profile> | ||
<profile> | ||
<id>MacArm</id> | ||
<activation> | ||
<os> | ||
<family>mac</family> | ||
<arch>aarch64</arch> | ||
</os> | ||
</activation> | ||
<properties> | ||
<jni.classifier>mac-arm-64-jni</jni.classifier> | ||
</properties> | ||
</profile> | ||
<profile> | ||
<id>Linux64</id> | ||
<activation> | ||
<os> | ||
<!-- Use OS <name> instead of <family> because the "unix" <family> also includes Mac --> | ||
<name>Linux</name> | ||
<arch>amd64</arch> | ||
</os> | ||
</activation> | ||
<properties> | ||
<jni.classifier>linux-x86-64-jni</jni.classifier> | ||
</properties> | ||
</profile> | ||
</profiles> | ||
|
||
<dependencies> | ||
<dependency> | ||
<groupId>org.jetbrains.kotlin</groupId> | ||
<artifactId>kotlin-stdlib-jdk8</artifactId> | ||
<version>1.9.21</version> | ||
</dependency> | ||
<dependency> | ||
<groupId>com.datalogics.pdfl</groupId> | ||
<artifactId>pdfl</artifactId> | ||
<version>18.31.0</version> | ||
<type>pom</type> | ||
</dependency> | ||
<dependency> | ||
<groupId>com.datalogics.pdfl</groupId> | ||
<artifactId>pdfl</artifactId> | ||
<version>18.31.0</version> | ||
</dependency> | ||
<dependency> | ||
<groupId>com.datalogics.pdfl</groupId> | ||
<artifactId>pdfl</artifactId> | ||
<version>18.31.0</version> | ||
<type>zip</type> | ||
<classifier>${jni.classifier}</classifier> | ||
</dependency> | ||
<dependency> | ||
<groupId>com.datalogics.pdfl</groupId> | ||
<artifactId>pdfl</artifactId> | ||
<version>18.31.0</version> | ||
<type>zip</type> | ||
<classifier>resources</classifier> | ||
</dependency> | ||
<dependency> | ||
<groupId>com.datalogics.pdfl</groupId> | ||
<artifactId>pdfl</artifactId> | ||
<version>18.31.0</version> | ||
<classifier>javadoc</classifier> | ||
</dependency> | ||
</dependencies> | ||
|
||
<build> | ||
<sourceDirectory>src/main/kotlin</sourceDirectory> | ||
<plugins> | ||
<plugin> | ||
<groupId>org.jetbrains.kotlin</groupId> | ||
<artifactId>kotlin-maven-plugin</artifactId> | ||
<version>1.9.21</version> | ||
<executions> | ||
<execution> | ||
<id>compile</id> | ||
<phase>compile</phase> | ||
<goals> | ||
<goal>compile</goal> | ||
</goals> | ||
</execution> | ||
</executions> | ||
</plugin> | ||
<plugin> | ||
<artifactId>maven-surefire-plugin</artifactId> | ||
<version>2.22.2</version> | ||
</plugin> | ||
<plugin> | ||
<artifactId>maven-failsafe-plugin</artifactId> | ||
<version>2.22.2</version> | ||
</plugin> | ||
<plugin> | ||
<groupId>org.codehaus.mojo</groupId> | ||
<artifactId>exec-maven-plugin</artifactId> | ||
<version>1.6.0</version> | ||
<configuration> | ||
<mainClass>RegexTextSearch</mainClass> | ||
</configuration> | ||
</plugin> | ||
<plugin> | ||
<groupId>org.apache.maven.plugins</groupId> | ||
<artifactId>maven-dependency-plugin</artifactId> | ||
<executions> | ||
<execution> | ||
<id>unpack-resources</id> | ||
<phase>generate-resources</phase> | ||
<goals> | ||
<goal>unpack</goal> | ||
</goals> | ||
<configuration> | ||
<artifactItems> | ||
<artifactItem> | ||
<groupId>com.datalogics.pdfl</groupId> | ||
<artifactId>pdfl</artifactId> | ||
<classifier>resources</classifier> | ||
<type>zip</type> | ||
<outputDirectory>${project.build.directory}/lib/Resources</outputDirectory> | ||
</artifactItem> | ||
</artifactItems> | ||
</configuration> | ||
</execution> | ||
<execution> | ||
<id>unpack-jni</id> | ||
<phase>generate-resources</phase> | ||
<goals> | ||
<goal>unpack</goal> | ||
</goals> | ||
<configuration> | ||
<artifactItems> | ||
<artifactItem> | ||
<groupId>com.datalogics.pdfl</groupId> | ||
<artifactId>pdfl</artifactId> | ||
<classifier>${jni.classifier}</classifier> | ||
<type>zip</type> | ||
<outputDirectory>${project.build.directory}/lib</outputDirectory> | ||
</artifactItem> | ||
</artifactItems> | ||
</configuration> | ||
</execution> | ||
<execution> | ||
<id>unpack-license</id> | ||
<phase>generate-resources</phase> | ||
<goals> | ||
<goal>unpack</goal> | ||
</goals> | ||
<configuration> | ||
<artifactItems> | ||
<artifactItem> | ||
<groupId>com.datalogics.pdfl</groupId> | ||
<artifactId>pdfl</artifactId> | ||
<classifier>license</classifier> | ||
<type>zip</type> | ||
<outputDirectory>${project.build.directory}/lib</outputDirectory> | ||
</artifactItem> | ||
</artifactItems> | ||
</configuration> | ||
</execution> | ||
</executions> | ||
</plugin> | ||
<plugin> | ||
<artifactId>maven-assembly-plugin</artifactId> | ||
<executions> | ||
<execution> | ||
<phase>package</phase> | ||
<goals> | ||
<goal>single</goal> | ||
</goals> | ||
</execution> | ||
</executions> | ||
<configuration> | ||
<archive> | ||
<manifest> | ||
<addClasspath>true</addClasspath> | ||
<mainClass>com.datalogics.pdfl.samples.RegexTextSearchKt</mainClass> | ||
</manifest> | ||
</archive> | ||
<descriptorRefs> | ||
<descriptorRef>jar-with-dependencies</descriptorRef> | ||
</descriptorRefs> | ||
</configuration> | ||
</plugin> | ||
</plugins> | ||
<pluginManagement> | ||
<plugins> | ||
<plugin> | ||
<groupId>org.apache.maven.plugins</groupId> | ||
<artifactId>maven-dependency-plugin</artifactId> | ||
<version>3.0.2</version> | ||
</plugin> | ||
</plugins> | ||
</pluginManagement> | ||
</build> | ||
|
||
</project> |
74 changes: 74 additions & 0 deletions
74
RegexTextSearch/src/main/kotlin/com/datalogics/pdfl/samples/RegexTextSearch.kt
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,74 @@ | ||
package com.datalogics.pdfl.samples | ||
|
||
import com.datalogics.PDFL.* | ||
import java.util.* | ||
|
||
/* | ||
* | ||
* This sample shows how to search a PDF document using regex pattern matching. The program opens an input PDF, searches for | ||
* words using the DocTextFinder, and then prints these words to the console. | ||
* | ||
* Copyright (c) 2024, Datalogics, Inc. All rights reserved. | ||
* | ||
*/ | ||
|
||
fun main(args: Array<String>) { | ||
println("RegexTextSearch sample:") | ||
val lib = Library() | ||
|
||
try { | ||
val sInput: String = | ||
if (args.isNotEmpty()) { | ||
args[0] | ||
} else { | ||
Library.getResourceDirectory() + "Sample_Input/RegexTextSearch.pdf" | ||
} | ||
|
||
val sOutput = "RegexTextSearch-out.pdf" | ||
|
||
// Highlight occurrences of the words that match this regular expression. | ||
// Phone numbers | ||
val sRegex = "((1-)?(\\()?\\d{3}(\\))?(\\s)?(-)?\\d{3}-\\d{4})" | ||
// Email addresses | ||
//val sRegex = "(\\b[\\w.!#$%&'*+\\/=?^`{|}~-]+@[\\w-]+(?:\\.[\\w-]+)*\\b)" | ||
// URLs | ||
//val sRegex = "((https?:\\/\\/(?:www\\.|(?!www))[a-zA-Z0-9][a-zA-Z0-9-]+[a-zA-Z0-9]\\.[^\\s]{2,}|www\\.[a-zA-Z0-9][a-zA-Z0-9-]+[a-zA-Z0-9]\\.[^\\s]{2,}|https?:\\/\\/(?:www\\.|(?!www))[a-zA-Z0-9]+\\.[^\\s]{2,}|www\\.[a-zA-Z0-9]+\\.[^\\s]{2,}))" | ||
|
||
println("Reading $sInput") | ||
|
||
val doc = Document(sInput) | ||
val nPages = doc.numPages | ||
println("Opened document $sInput") | ||
|
||
val wordConfig = WordFinderConfig() | ||
|
||
// Need to set this to true so phrases will be concatenated properly | ||
wordConfig.noHyphenDetection = true | ||
|
||
val docTextFinder = DocTextFinder(doc, wordConfig) | ||
val docMatches = docTextFinder.getMatchList(0, nPages - 1, sRegex) | ||
|
||
for (wInfo in docMatches) { | ||
// Show the matching phrase | ||
val s = wInfo.matchString | ||
println(s) | ||
|
||
// Get the word quads | ||
val quadList = wInfo.quadInfo | ||
|
||
// Iterate through the quad info and create highlights | ||
for (qInfo in quadList) { | ||
val docPage = doc.getPage(qInfo.pageNum) | ||
val highlight = HighlightAnnotation(docPage, qInfo.quads) | ||
highlight.normalAppearance = highlight.generateAppearance() | ||
} | ||
} | ||
|
||
// Save the document with the highlighted matched strings | ||
doc.save(EnumSet.of(SaveFlags.FULL), sOutput) | ||
doc.close() | ||
|
||
} finally { | ||
lib.delete() | ||
} | ||
} |
Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.
Oops, something went wrong.
Oops, something went wrong.