16 |
17 |
--------------------------------------------------------------------------------
/sonar-project.properties:
--------------------------------------------------------------------------------
1 | # must be unique in a given SonarQube instance
2 | sonar.projectKey=pdf-converter
3 | # this is the name and version displayed in the SonarQube UI. Was mandatory prior to SonarQube 6.1.
4 | #sonar.projectName=cron-utils
5 | #sonar.projectVersion=7.0.1-SNAPSHOT
6 |
7 | # Path is relative to the sonar-project.properties file. Replace "\" by "/" on Windows.
8 | # This property is optional if sonar.modules is set.
9 | sonar.sources=src/main/java
10 | sonar.tests=src/test/java
11 | sonar.java.binaries=target/classes
12 |
13 |
14 | # Encoding of the source code. Default is default system encoding
15 | sonar.sourceEncoding=UTF-8
16 |
--------------------------------------------------------------------------------
/src/main/resources/epub/index.html:
--------------------------------------------------------------------------------
1 |
2 |
3 |
4 | index
5 |
6 |
7 |
8 |
9 |
10 |
11 |
12 | $CONTENT
13 |
14 |
15 |
--------------------------------------------------------------------------------
/src/main/resources/epub/toc.ncx:
--------------------------------------------------------------------------------
1 |
2 |
3 |
4 |
5 |
6 |
7 |
8 |
9 |
10 |
11 | $TITLE
12 |
13 |
14 |
15 |
16 | Start
17 |
18 |
19 |
20 |
21 |
--------------------------------------------------------------------------------
/src/test/java/pdf/converter/PdfConverterTest.java:
--------------------------------------------------------------------------------
1 | package pdf.converter;
2 |
3 | import org.junit.Assert;
4 | import org.junit.Test;
5 |
6 | import java.io.File;
7 | import java.io.IOException;
8 | import java.nio.file.Files;
9 | import java.nio.file.Path;
10 | import java.nio.file.StandardCopyOption;
11 | import java.util.UUID;
12 |
13 | public class PdfConverterTest {
14 |
15 | @Test
16 | public void convert() throws Exception {
17 | Path path = copyToTmp();
18 | File dest = new File(path.toFile(), "mobydick.epub");
19 | PdfConverter
20 | .convert(new File(path.toFile(), "mobydick.pdf"))
21 | .intoEpub("Moby Dick", dest);
22 | Assert.assertTrue(dest.exists());
23 | }
24 |
25 | private Path copyToTmp() throws IOException {
26 | Path tmpdir = new File(String.format("/tmp/%s", UUID.randomUUID().toString())).toPath();
27 | System.out.println(tmpdir);
28 | Files.createDirectories(tmpdir);
29 | Path dest = new File(tmpdir.toFile(), "mobydick.pdf").toPath();
30 | ClassLoader classLoader = getClass().getClassLoader();
31 | Path file = new File(classLoader.getResource("mobydick.pdf").getFile()).toPath();
32 | Files.copy(file, dest, StandardCopyOption.REPLACE_EXISTING);
33 | return tmpdir;
34 | }
35 | }
--------------------------------------------------------------------------------
/src/main/resources/epub/content.opf:
--------------------------------------------------------------------------------
1 |
2 |
3 |
4 | en
5 | $AUTHOR
6 |
7 | $TITLE
8 |
9 | pdf-converter
10 | $UUID
11 |
12 |
13 |
14 | $CONTENT
15 |
16 |
17 |
18 |
19 |
20 |
21 |
22 |
23 |
24 |
25 |
26 |
27 |
28 |
--------------------------------------------------------------------------------
/src/main/java/pdf/converter/txt/TxtCreator.java:
--------------------------------------------------------------------------------
1 | package pdf.converter.txt;
2 |
3 | import org.apache.pdfbox.io.RandomAccessFile;
4 | import org.apache.pdfbox.pdmodel.PDDocument;
5 | import org.apache.pdfbox.text.PDFTextStripper;
6 | import org.slf4j.Logger;
7 | import org.slf4j.LoggerFactory;
8 |
9 | import java.io.File;
10 | import java.io.FileWriter;
11 | import java.io.IOException;
12 | import java.util.UUID;
13 |
14 | public class TxtCreator {
15 | private static final Logger log = LoggerFactory.getLogger(TxtCreator.class);
16 |
17 | public void process(File pdf, File output){
18 | PDDocument pdDoc;
19 | try {//Kudos for closing: http://stackoverflow.com/questions/156508/closing-a-java-fileinputstream
20 | pdDoc = PDDocument.load(pdf);
21 | FileWriter writer = new FileWriter(output);
22 | try {
23 | PDFTextStripper stripper = new PDFTextStripper();
24 | int numberOfPages = pdDoc.getNumberOfPages();
25 |
26 | for (int j = 1; j < numberOfPages+1; j++) {
27 | stripper.setStartPage(j);
28 | stripper.setEndPage(j);
29 | writer.write(stripper.getText(pdDoc));
30 | writer.flush();
31 | }
32 | } finally {
33 | pdDoc.close();
34 | writer.close();
35 | }
36 | } catch (IOException ioe) {
37 | log.warn(String.format("Failed to create txt for file: %s", pdf.getName()), ioe);
38 | }
39 | }
40 | }
41 |
--------------------------------------------------------------------------------
/src/main/java/pdf/converter/zip/ZipCreator.java:
--------------------------------------------------------------------------------
1 | package pdf.converter.zip;
2 | import org.slf4j.Logger;
3 | import org.slf4j.LoggerFactory;
4 |
5 | import java.io.*;
6 | import java.nio.file.Files;
7 | import java.nio.file.Path;
8 | import java.nio.file.Paths;
9 | import java.util.zip.ZipEntry;
10 | import java.util.zip.ZipOutputStream;
11 |
12 | public class ZipCreator {
13 | private static final Logger log = LoggerFactory.getLogger(ZipCreator.class);
14 |
15 | public void create(File imgsDir, File output) throws IOException {
16 | pack(imgsDir.getAbsolutePath(), output.getAbsolutePath());
17 | }
18 |
19 | private static void pack(String sourceDirPath, String zipFilePath) throws IOException {
20 | Path p = Files.createFile(Paths.get(zipFilePath));
21 | try (ZipOutputStream zs = new ZipOutputStream(Files.newOutputStream(p))) {
22 | Path pp = Paths.get(sourceDirPath);
23 | Files.walk(pp)
24 | .filter(path -> !Files.isDirectory(path))
25 | .forEach(path -> {
26 | ZipEntry zipEntry = new ZipEntry(pp.relativize(path).toString());
27 | try {
28 | zs.putNextEntry(zipEntry);
29 | zs.write(Files.readAllBytes(path));
30 | zs.closeEntry();
31 | } catch (Exception e) {
32 | log.warn("Failed to create zip file", e);
33 | }
34 | });
35 | }
36 | }
37 | }
38 |
39 |
40 |
--------------------------------------------------------------------------------
/src/main/resources/logback.xml:
--------------------------------------------------------------------------------
1 |
2 |
3 |
4 |
6 |
7 | %d{ISO8601} %p %t %c{0}.%M - %m%n
8 | utf8
9 |
10 |
11 |
12 |
13 | pdf-converter.log
14 |
15 |
16 | pdf-converter.%d{yyyy-MM-dd}.%i.log
17 |
19 |
20 | 50MB
21 |
22 |
23 |
24 | 7
25 |
26 |
27 | %d{ISO8601} %p %t %c{0}.%M - %m%n
28 | utf8
29 |
30 |
31 |
32 |
33 |
34 |
35 |
36 |
37 |
38 |
--------------------------------------------------------------------------------
/.travis.yml:
--------------------------------------------------------------------------------
1 | language: java
2 |
3 | branches:
4 | only:
5 | - master
6 |
7 | jdk:
8 | - oraclejdk11
9 |
10 | before_install: "git clone -b travis `git config --get remote.origin.url` target/travis"
11 |
12 | addons:
13 | apt:
14 | packages:
15 | - ghostscript
16 | sonarcloud:
17 | organization: "jmrozanec-github"
18 | token:
19 | secure: "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"
20 | script:
21 | - >
22 | if [ "$TRAVIS_PULL_REQUEST" != "false" ];then
23 | mvn org.jacoco:jacoco-maven-plugin:prepare-agent package --settings target/travis/settings.xml -Dsettings.security=target/travis/settings-security.xml -Dmaven.javadoc.skip=true;
24 | sonar-scanner
25 | fi
26 | - >
27 | if [ "$TRAVIS_PULL_REQUEST" = "false" ];then
28 | mvn org.jacoco:jacoco-maven-plugin:prepare-agent package deploy --settings target/travis/settings.xml -Dsettings.security=target/travis/settings-security.xml -Dmaven.javadoc.skip=true;
29 | sonar-scanner
30 | fi
31 |
32 | cache:
33 | directories:
34 | - '$HOME/.m2/repository'
35 | - '$HOME/.sonar/cache'
36 |
37 | after_success:
38 | - mvn cobertura:cobertura coveralls:cobertura
39 | - bash <(curl -s https://codecov.io/bash)
40 |
--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
1 | pdf-converter
2 | ===========
3 | A Java library to convert .pdf files into .epub, .txt, .png, .jpg, .zip formats. The project follows the [Semantic Versioning Convention](http://semver.org/) and uses Apache 2.0 license.
4 |
5 | [](https://gitter.im/pdf-converter/)
6 | [](https://travis-ci.org/jmrozanec/pdf-converter)
7 | [](https://coveralls.io/github/jmrozanec/pdf-converter?branch=master)
8 |
9 | **Download**
10 |
11 | pdf-converter is available on [Maven central](http://search.maven.org/#search%7Cga%7C1%7Cg%3A%22com.bit-scout%22) repository.
12 |
13 |
14 | com.bit-scout
15 | pdf-converter
16 | 1.0.2
17 |
18 |
19 | **Features**
20 |
21 | Any .pdf file can be converted to the following formats:
22 | * .epub: output file can either contain images of .pdf pages or their transcript.
23 | * .txt: contains the transcript of the .pdf file
24 | * .png: all pages converted to .png images
25 | * .jpg: all pages converted to .jpg images
26 | * .zip: contains images for all pages from the .pdf in the original resolution. Images can be either in .png or .jpg format.
27 |
28 |
29 | **Example**
30 |
31 | ```java
32 |
33 | PdfConverter
34 | .convert(new File(mobydick.pdf))
35 | .intoEpub("Moby Dick", new File("mobydick.epub"));
36 | ```
37 |
38 | **Contribute & Support!**
39 |
40 | Contributions are welcome! You can contribute by
41 | * starring and/or Flattring this repo!
42 | * requesting or adding new features.
43 | * enhancing existing code: ex.: provide more accurate description cases
44 | * testing
45 | * enhancing documentation
46 | * providing translations to support new locales
47 | * bringing suggestions and reporting bugs
48 | * spreading the word / telling us how you use it!
49 |
50 | Support us donating once or by subscription through Flattr!
51 |
52 | [](https://flattr.com/submit/auto?user_id=jmrozanec&url=https://github.com/jmrozanec/pdf-converter)
53 |
--------------------------------------------------------------------------------
/.github/workflows/codeql-analysis.yml:
--------------------------------------------------------------------------------
1 | # For most projects, this workflow file will not need changing; you simply need
2 | # to commit it to your repository.
3 | #
4 | # You may wish to alter this file to override the set of languages analyzed,
5 | # or to provide custom queries or build logic.
6 | name: "CodeQL"
7 |
8 | on:
9 | push:
10 | branches: [master]
11 | pull_request:
12 | # The branches below must be a subset of the branches above
13 | branches: [master]
14 | schedule:
15 | - cron: '0 14 * * 6'
16 |
17 | jobs:
18 | analyze:
19 | name: Analyze
20 | runs-on: ubuntu-latest
21 |
22 | strategy:
23 | fail-fast: false
24 | matrix:
25 | # Override automatic language detection by changing the below list
26 | # Supported options are ['csharp', 'cpp', 'go', 'java', 'javascript', 'python']
27 | language: ['java']
28 | # Learn more...
29 | # https://docs.github.com/en/github/finding-security-vulnerabilities-and-errors-in-your-code/configuring-code-scanning#overriding-automatic-language-detection
30 |
31 | steps:
32 | - name: Checkout repository
33 | uses: actions/checkout@v2
34 | with:
35 | # We must fetch at least the immediate parents so that if this is
36 | # a pull request then we can checkout the head.
37 | fetch-depth: 2
38 |
39 | # If this run was triggered by a pull request event, then checkout
40 | # the head of the pull request instead of the merge commit.
41 | - run: git checkout HEAD^2
42 | if: ${{ github.event_name == 'pull_request' }}
43 |
44 | # Initializes the CodeQL tools for scanning.
45 | - name: Initialize CodeQL
46 | uses: github/codeql-action/init@v1
47 | with:
48 | languages: ${{ matrix.language }}
49 | # If you wish to specify custom queries, you can do so here or in a config file.
50 | # By default, queries listed here will override any specified in a config file.
51 | # Prefix the list here with "+" to use these queries and those in the config file.
52 | # queries: ./path/to/local/query, your-org/your-repo/queries@main
53 |
54 | # Autobuild attempts to build any compiled languages (C/C++, C#, or Java).
55 | # If this step fails, then you should remove it and run the build manually (see below)
56 | - name: Autobuild
57 | uses: github/codeql-action/autobuild@v1
58 |
59 | # ℹ️ Command-line programs to run using the OS shell.
60 | # 📚 https://git.io/JvXDl
61 |
62 | # ✏️ If the Autobuild fails above, remove it and uncomment the following three lines
63 | # and modify them (or add more) to build your code if your project
64 | # uses a compiled language
65 |
66 | #- run: |
67 | # make bootstrap
68 | # make release
69 |
70 | - name: Perform CodeQL Analysis
71 | uses: github/codeql-action/analyze@v1
72 |
--------------------------------------------------------------------------------
/src/main/java/pdf/converter/img/ImgCreator.java:
--------------------------------------------------------------------------------
1 | package pdf.converter.img;
2 |
3 | import net.coobird.thumbnailator.Thumbnails;
4 | import org.apache.commons.io.FilenameUtils;
5 | import org.ghost4j.document.DocumentException;
6 | import org.ghost4j.document.PDFDocument;
7 | import org.ghost4j.renderer.RendererException;
8 | import org.ghost4j.renderer.SimpleRenderer;
9 | import org.slf4j.Logger;
10 | import org.slf4j.LoggerFactory;
11 |
12 | import javax.imageio.ImageIO;
13 | import java.awt.*;
14 | import java.awt.image.BufferedImage;
15 | import java.io.File;
16 | import java.io.IOException;
17 |
18 | public class ImgCreator {
19 | private static final Logger log = LoggerFactory.getLogger(ImgCreator.class);
20 |
21 | /**
22 | * @param pdf - File to be processed;
23 | * @param output - output directory, where images will be written;
24 | * @param resolution - output images resolution (usually 300+ for print quality, 72 for web);
25 | * @param extension - "png" or "jpg"
26 | *
27 | */
28 | public void process(File pdf, File output, int resolution, int width, int height, ImageFileExtension extension){
29 | PDFDocument document = new PDFDocument();
30 | try {
31 | document.load(pdf);
32 | for(int page=0; page images = renderer.render(document, page, page);
36 | if(!images.isEmpty()){
37 | persistImage(toBufferedImage(images.get(0)), width, height, new File(output, String.format("%05d.%s", page+1, extension.toString().toLowerCase())));
38 | }
39 | }
40 | } catch (IOException |RendererException |DocumentException e) {
41 | log.warn(String.format("Failed to create images for document: %s", pdf.getName()), e);
42 | }
43 | }
44 |
45 | /*
46 | * Kudos to: http://stackoverflow.com/questions/13605248/java-converting-image-to-bufferedimage
47 | */
48 | private BufferedImage toBufferedImage(Image img){
49 | if (img instanceof BufferedImage){
50 | return (BufferedImage) img;
51 | }
52 | // Create a buffered image with transparency
53 | BufferedImage bimage = new BufferedImage(img.getWidth(null), img.getHeight(null), BufferedImage.TYPE_INT_ARGB);
54 | // Draw the image on to the buffered image
55 | Graphics2D bGr = bimage.createGraphics();
56 | bGr.drawImage(img, 0, 0, null);
57 | bGr.dispose();
58 | // Return the buffered image
59 | return bimage;
60 | }
61 |
62 | private void persistImage(BufferedImage image, int width, int height, File output) throws IOException {
63 | System.out.println(output);
64 | output.getParentFile().mkdirs();
65 | ImageIO.write(Thumbnails.of(image).size(width, height).asBufferedImage(), FilenameUtils.getExtension(output.getAbsolutePath()), output);
66 | }
67 | }
68 |
--------------------------------------------------------------------------------
/src/main/java/pdf/converter/PdfConverter.java:
--------------------------------------------------------------------------------
1 | package pdf.converter;
2 |
3 | import org.apache.commons.io.FileUtils;
4 | import pdf.converter.epub.EpubCreator;
5 | import pdf.converter.img.ImageFileExtension;
6 | import pdf.converter.img.ImgCreator;
7 | import pdf.converter.zip.ZipCreator;
8 |
9 | import java.io.File;
10 | import java.io.IOException;
11 | import java.nio.file.Files;
12 | import java.nio.file.Path;
13 | import java.util.UUID;
14 |
15 | public class PdfConverter {
16 | private static final int RESOLUTION = 300;
17 | private static final int WIDTH = 600;
18 | private static final int HEIGHT = 800;
19 | private File pdf;
20 |
21 | private PdfConverter(File pdf){
22 | this.pdf = pdf;
23 | }
24 |
25 | public static PdfConverter convert(File pdf){
26 | return new PdfConverter(pdf);
27 | }
28 |
29 | public void intoImage(File output, int resolution, int width, int height, ImageFileExtension format){
30 | ImgCreator creator = new ImgCreator();
31 | creator.process(pdf, output, resolution, width, height, format);
32 | }
33 |
34 | public void intoEpub(String title, File output){
35 | try {
36 | //File imgsdir = File.createTempFile(UUID.randomUUID().toString(), "");
37 | Path imgsdir = new File(String.format("/tmp/%s", UUID.randomUUID().toString())).toPath();
38 | Files.createDirectories(imgsdir);
39 |
40 |
41 | ImgCreator creator = new ImgCreator();
42 | creator.process(pdf, imgsdir.toFile(), RESOLUTION, WIDTH, HEIGHT, ImageFileExtension.PNG);
43 | EpubCreator epubCreator = new EpubCreator();
44 | epubCreator.create(title, imgsdir.toFile(), output);
45 | FileUtils.deleteDirectory(imgsdir.toFile());
46 | } catch (IOException e) {
47 | e.printStackTrace();
48 | }
49 |
50 | }
51 |
52 | public void intoEpub(File imgsdir, String title, File output){
53 | EpubCreator epubCreator = new EpubCreator();
54 | try {
55 | epubCreator.create(title, imgsdir, output);
56 | } catch (IOException e) {
57 | e.printStackTrace();
58 | }
59 | }
60 |
61 | public void intoZip(String title, File output){
62 | try {
63 | File imgsdir = File.createTempFile(UUID.randomUUID().toString(), "");
64 | imgsdir.mkdirs();
65 | ImgCreator creator = new ImgCreator();
66 | creator.process(pdf, imgsdir, RESOLUTION, WIDTH, HEIGHT, ImageFileExtension.PNG);
67 | ZipCreator zipCreator = new ZipCreator();
68 | zipCreator.create(imgsdir, output);
69 | FileUtils.deleteDirectory(imgsdir);
70 | } catch (IOException e) {
71 | e.printStackTrace();
72 | }
73 |
74 | }
75 |
76 | public void intoZip(File imgsdir, String title, File output){
77 | ZipCreator zipCreator = new ZipCreator();
78 | try {
79 | zipCreator.create(imgsdir, output);
80 | } catch (IOException e) {
81 | e.printStackTrace();
82 | }
83 | }
84 | }
85 |
--------------------------------------------------------------------------------
/src/main/java/pdf/converter/epub/EpubCreator.java:
--------------------------------------------------------------------------------
1 | package pdf.converter.epub;
2 |
3 | import com.google.common.collect.Lists;
4 | import org.apache.commons.io.FileUtils;
5 | import org.apache.commons.io.IOUtils;
6 | import org.joda.time.DateTime;
7 | import org.joda.time.format.DateTimeFormat;
8 |
9 | import java.io.*;
10 | import java.nio.file.Files;
11 | import java.nio.file.Path;
12 | import java.nio.file.Paths;
13 | import java.util.*;
14 | import java.util.zip.ZipEntry;
15 | import java.util.zip.ZipOutputStream;
16 |
17 | public class EpubCreator {
18 | private String timestamp;
19 | private String uuid;
20 | private File basedir;
21 | private ClassLoader classLoader;
22 | private String title;
23 | private File imgsDir;
24 |
25 | public void create(String title, File imgsDir, File output) throws IOException {
26 | timestamp = DateTimeFormat.forPattern("yyyy-MM-dd'T'hh:mm:ssSZZ").print(DateTime.now());
27 | uuid = UUID.randomUUID().toString();
28 | this.title = title;
29 | this.imgsDir = imgsDir;
30 |
31 | try {
32 | basedir = File.createTempFile(uuid,"");
33 | basedir.delete();
34 | basedir.mkdirs();
35 | } catch (IOException e) {
36 | e.printStackTrace();
37 | }
38 | classLoader = getClass().getClassLoader();
39 |
40 | copyImages();
41 | copyStandardFilez();
42 | createOPFFile();
43 | createIndex();
44 | createTitlePage();
45 | createTOC();
46 | pack(basedir.getAbsolutePath(), output.getAbsolutePath());
47 | FileUtils.deleteDirectory(basedir);
48 | }
49 |
50 | private void copyImages() throws IOException {
51 | File imagesDir = new File(basedir, "images");
52 | imagesDir.mkdirs();
53 | for(File file : listFiles()){
54 | try(FileInputStream fileInputStream = new FileInputStream(file);
55 | FileOutputStream fileOutputStream = new FileOutputStream(new File(imagesDir, file.getName()))) {
56 | IOUtils.copy(fileInputStream, fileOutputStream);
57 | }
58 | }
59 | }
60 |
61 | private void copyStandardFilez() throws IOException {
62 | File metainf = new File(basedir, "META-INF");
63 | metainf.mkdirs();
64 | writeFile(new File(metainf, "container.xml"), readFileFromSrc("epub/META-INF/container.xml"));
65 |
66 | writeFile(new File(basedir, "mimetype"), readFileFromSrc("epub/mimetype"));
67 | writeFile(new File(basedir, "page_styles.css"), readFileFromSrc("epub/page_styles.css"));
68 | writeFile(new File(basedir, "stylesheet.css"), readFileFromSrc("epub/stylesheet.css"));
69 | }
70 |
71 | private void createOPFFile() throws IOException {
72 | StringBuilder content = new StringBuilder();
73 | for(File file : listFiles()){
74 | content.append(String.format("\n", file.getName(), idForImage(file.getName())));
75 | }
76 | String opf = readFileFromSrc("epub/content.opf");
77 | opf = opf
78 | .replace("$AUTHOR", "Unknown")
79 | .replace("$TIMESTAMP", timestamp)
80 | .replace("$TITLE", title)
81 | .replace("$UUID", uuid)
82 | .replace("$CONTENT", content.toString());
83 |
84 | writeFile(new File(basedir, "content.opf"), opf);
85 | }
86 |
87 | private void createIndex() throws IOException {
88 | StringBuilder content = new StringBuilder();
89 | for(File file : listFiles()){
90 | content.append(String.format("
\n", idForImage(file.getName()), file.getName()));
91 | }
92 | String index = readFileFromSrc("epub/index.html");
93 | index = index.replace("$CONTENT", content.toString());
94 |
95 | writeFile(new File(basedir, "index.html"), index);
96 | }
97 |
98 | private void createTitlePage() throws IOException {
99 | String pagetitle = readFileFromSrc("epub/titlepage.xhtml");
100 | pagetitle = pagetitle.replace("$TITLE", title);
101 |
102 | writeFile(new File(basedir, "titlepage.xhtml"), pagetitle);
103 | }
104 |
105 | private void createTOC() throws IOException {
106 | String toc = readFileFromSrc("epub/toc.ncx");
107 | toc = toc.replace("$TITLE", title);
108 |
109 | writeFile(new File(basedir, "toc.ncx"), toc);
110 | }
111 |
112 | private void writeFile(File dest, String content) throws IOException {
113 | FileWriter writer = new FileWriter(dest);
114 | writer.write(content);
115 | writer.flush();
116 | writer.close();
117 | }
118 |
119 | private String readFileFromSrc(String path) throws IOException {
120 | return IOUtils.toString(classLoader.getResourceAsStream(path));
121 | }
122 |
123 | private String idForImage(String name){
124 | return String.format("id%s", name.replace(".png", ""));
125 | }
126 |
127 | private static void pack(String sourceDirPath, String zipFilePath) throws IOException {
128 | Path p = Files.createFile(Paths.get(zipFilePath));
129 | try (ZipOutputStream zs = new ZipOutputStream(Files.newOutputStream(p))) {
130 | Path pp = Paths.get(sourceDirPath);
131 | Files.walk(pp)
132 | .filter(path -> !Files.isDirectory(path))
133 | .forEach(path -> {
134 | ZipEntry zipEntry = new ZipEntry(pp.relativize(path).toString());
135 | try {
136 | zs.putNextEntry(zipEntry);
137 | zs.write(Files.readAllBytes(path));
138 | zs.closeEntry();
139 | } catch (Exception e) {
140 | System.err.println(e);
141 | }
142 | });
143 | }
144 | }
145 |
146 | private List listFiles(){
147 | File[] files = imgsDir.listFiles((dir, name) -> name.toLowerCase().endsWith(".png"));
148 | List sorted = Lists.newArrayList(files);
149 | sorted.sort(Comparator.comparing(File::toString));
150 | return sorted;
151 | }
152 | }
153 |
--------------------------------------------------------------------------------
/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 {yyyy} {name of copyright owner}
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 |
--------------------------------------------------------------------------------
/pom.xml:
--------------------------------------------------------------------------------
1 |
3 | 4.0.0
4 |
5 |
6 | org.sonatype.oss
7 | oss-parent
8 | 7
9 |
10 |
11 | com.bit-scout
12 | pdf-converter
13 | 1.0.3-SNAPSHOT
14 |
15 | pdf-converter
16 | A Java library to convert .pdf files into .txt, .jpg, .png, .epub and .zip formats.
17 |
18 | http://bit-scout.com
19 |
20 |
21 |
22 | Apache 2.0
23 | http://www.apache.org/licenses/LICENSE-2.0.html
24 | repo
25 |
26 |
27 |
28 |
29 |
30 | jmrozanec
31 | https://github.com/jmrozanec
32 |
33 |
34 |
35 |
36 | https://github.com/jmrozanec/pdf-converter/issues
37 | GitHub Issues
38 |
39 |
40 |
41 | https://github.com/jmrozanec/pdf-converter
42 | scm:git:git@github.com:jmrozanec/pdf-converter.git
43 | scm:git:git@github.com:jmrozanec/pdf-converter.git
44 | HEAD
45 |
46 |
47 |
48 |
49 | ossrh
50 | Release Repository
51 | https://oss.sonatype.org/service/local/staging/deploy/maven2/
52 |
53 |
54 | ossrh
55 | Snapshots Repository
56 | https://oss.sonatype.org/content/repositories/snapshots/
57 |
58 |
59 |
60 |
61 | 1.7.12
62 | 1.2.17
63 | 4.13.1
64 | 3.5.13
65 | 2.0.7
66 | 30.1.1-jre
67 |
68 | github
69 | UTF-8
70 |
71 |
72 |
73 |
74 | org.slf4j
75 | slf4j-api
76 | ${slf4j.version}
77 |
78 |
79 | joda-time
80 | joda-time
81 | 2.9.7
82 |
83 |
84 | org.apache.commons
85 | commons-lang3
86 | 3.5
87 |
88 |
89 | commons-io
90 | commons-io
91 | 2.7
92 |
93 |
94 | org.ghost4j
95 | ghost4j
96 | 1.0.0
97 |
98 |
99 | org.apache.pdfbox
100 | pdfbox
101 | 2.0.24
102 |
103 |
104 | org.apache.commons
105 | commons-exec
106 | 1.3
107 |
108 |
109 | com.google.guava
110 | guava
111 | ${guava.version}
112 |
113 |
114 | net.coobird
115 | thumbnailator
116 | 0.4.8
117 |
118 |
119 |
120 | org.slf4j
121 | slf4j-log4j12
122 | ${slf4j.version}
123 | test
124 |
125 |
126 | log4j
127 | log4j
128 | ${log4j.version}
129 | test
130 |
131 |
132 | junit
133 | junit
134 | ${junit.version}
135 | test
136 |
137 |
138 | org.mockito
139 | mockito-core
140 | ${mockito.version}
141 | test
142 |
143 |
144 | org.powermock
145 | powermock-module-junit4
146 | ${powermock.version}
147 | test
148 |
149 |
150 | org.powermock
151 | powermock-api-mockito2
152 | ${powermock.version}
153 | test
154 |
155 |
156 |
157 |
158 |
159 |
160 | maven-assembly-plugin
161 |
162 |
163 |
164 |
165 |
166 |
167 | jar-with-dependencies
168 |
169 |
170 |
171 |
172 | make-assembly
173 | package
174 |
175 | single
176 |
177 |
178 |
179 |
180 |
181 | org.apache.maven.plugins
182 | maven-compiler-plugin
183 | 3.1
184 |
185 | 1.8
186 | 1.8
187 |
188 |
189 |
190 | org.apache.maven.plugins
191 | maven-source-plugin
192 | 2.2.1
193 |
194 |
195 | attach-sources
196 |
197 | jar
198 |
199 |
200 |
201 |
202 |
203 | org.apache.maven.plugins
204 | maven-clean-plugin
205 | 2.5
206 |
207 |
208 | org.apache.maven.plugins
209 | maven-install-plugin
210 | 2.5.1
211 |
212 |
213 | org.apache.maven.plugins
214 | maven-jar-plugin
215 | 2.4
216 |
217 |
218 | org.apache.maven.plugins
219 | maven-resources-plugin
220 | 2.6
221 |
222 |
223 | org.apache.maven.plugins
224 | maven-javadoc-plugin
225 | 2.9.1
226 |
227 |
228 | attach-javadocs
229 |
230 | jar
231 |
232 |
233 |
234 |
235 |
236 | org.codehaus.mojo
237 | sonar-maven-plugin
238 | 1.0
239 |
240 |
241 | org.apache.maven.plugins
242 | maven-surefire-plugin
243 | 2.17
244 |
245 |
246 | org.apache.maven.plugins
247 | maven-deploy-plugin
248 | 2.8.1
249 |
250 |
251 | org.sonatype.plugins
252 | nexus-staging-maven-plugin
253 | 1.6.2
254 | true
255 |
256 | ossrh
257 | https://oss.sonatype.org/
258 | true
259 |
260 |
261 |
262 | org.codehaus.mojo
263 | findbugs-maven-plugin
264 | 2.5.3
265 |
266 |
267 | org.codehaus.mojo
268 | clirr-maven-plugin
269 | 2.6.1
270 |
271 |
272 | org.codehaus.mojo
273 | versions-maven-plugin
274 | 2.1
275 |
276 |
277 |
278 |
279 | org.codehaus.mojo
280 | cobertura-maven-plugin
281 | 2.6
282 |
283 | xml
284 |
285 |
286 |
287 |
288 |
289 |
290 |
291 | org.apache.maven.wagon
292 | wagon-webdav
293 | 1.0-beta-2
294 |
295 |
296 |
297 |
298 |
299 |
300 | release-sign-artifacts
301 |
302 |
303 | performRelease
304 | true
305 |
306 |
307 |
308 |
309 |
310 | org.apache.maven.plugins
311 | maven-gpg-plugin
312 | 1.5
313 |
314 |
315 | sign-artifacts
316 | verify
317 |
318 | sign
319 |
320 |
321 |
322 |
323 |
324 |
325 |
326 |
327 |
328 |
329 | travis
330 |
331 |
332 | env.TRAVIS
333 | true
334 |
335 |
336 |
337 |
338 |
339 | org.eluder.coveralls
340 | coveralls-maven-plugin
341 | 2.2.0
342 |
343 |
344 |
345 |
346 |
347 |
348 |
349 |
--------------------------------------------------------------------------------