Mirrors/Stirling-PDF
Mirrors/Stirling-PDF
1
0
Fork 0
mirror of https://github.com/Frooodle/Stirling-PDF.git synced 2025-03-20 00:17:10 +01:00
Code Issues Packages Projects Releases Wiki Activity

Pdf to markdown (#2730)

Browse Source 
# Description

Please provide a summary of the changes, including relevant motivation
and context.

Closes #(issue_number)

## Checklist

- [ ] I have read the [Contribution
Guidelines](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/CONTRIBUTING.md)
- [ ] I have performed a self-review of my own code
- [ ] I have attached images of the change if it is UI based
- [ ] I have commented my code, particularly in hard-to-understand areas
- [ ] If my code has heavily changed functionality I have updated
relevant docs on [Stirling-PDFs doc
repo](https://github.com/Stirling-Tools/Stirling-Tools.github.io/blob/main/docs/)
- [ ] My changes generate no new warnings
- [ ] I have read the section [Add New Translation
Tags](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/HowToAddNewLanguage.md#add-new-translation-tags)
(for new translation tags only)

---------

Co-authored-by: a <a>
This commit is contained in:
Anthony Stirling 2025-01-17 22:18:55 +00:00 committed by GitHub
parent a64acb3126
commit a46a570c8a
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
15 changed files with 1990 additions and 1723 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
DeveloperGuide.md
View File

@ -592,7 +592,7 @@ dependencies {
2. Generate new verification metadata and keys:
```bash
# Generate verification metadata with signatures and checksums
./gradlew clean dependencies buildEnvironment --write-verification-metadata sha256,pgp
./gradlew clean dependencies buildEnvironment spotlessApply --write-verification-metadata sha256,pgp
# Export the .keys file
./gradlew --export-keys

10
build.gradle
View File

@ -5,7 +5,7 @@ plugins {
id "org.springdoc.openapi-gradle-plugin" version "1.8.0"
id "io.swagger.swaggerhub" version "1.3.2"
id "edu.sc.seis.launch4j" version "3.0.6"
id "com.diffplug.spotless" version "7.0.1"
id "com.diffplug.spotless" version "7.0.2"
id "com.github.jk1.dependency-license-report" version "2.9"
//id "nebula.lint" version "19.0.3"
id("org.panteleyev.jpackageplugin") version "1.6.0"
@ -267,7 +267,7 @@ spotless {
importOrder("java", "javax", "org", "com", "net", "io")
toggleOffOn()
trimTrailingWhitespace()
indentWithSpaces()
leadingTabsToSpaces()
endWithNewline()
}
}
@ -397,8 +397,8 @@ dependencies {
// https://mvnrepository.com/artifact/com.bucket4j/bucket4j_jdk17
implementation "com.bucket4j:bucket4j_jdk17-core:8.14.0"
implementation "com.fathzer:javaluator:3.0.5"
implementation 'org.jsoup:jsoup:1.18.3'
implementation 'com.vladsch.flexmark:flexmark-html2md-converter:0.64.8'
developmentOnly("org.springframework.boot:spring-boot-devtools:$springBootVersion")
compileOnly "org.projectlombok:lombok:$lombokVersion"
@ -454,4 +454,4 @@ task printMacVersion {
doLast {
println getMacVersion(project.version.toString())
}
}
}

8
cucumber/features/external.feature
View File

@ -204,4 +204,12 @@ Feature: API Validation
Then the response status code should be 200
And the response file should have size greater than 100
And the response file should have extension ".pdf"
Scenario: Convert PDF to Markdown format
Given I generate a PDF file as "fileInput"
And the pdf contains 3 pages with random text
When I send the API request to the endpoint "/api/v1/convert/pdf/markdown"
Then the response status code should be 200
And the response file should have size greater than 100
And the response file should have extension ".md"

1
cucumber/webpage_urls.txt
View File

@ -12,7 +12,6 @@
/extract-page
/pdf-to-single-page
/img-to-pdf
/markdown-to-pdf
/pdf-to-img
/pdf-to-text
/pdf-to-csv

3394
gradle/verification-keyring.keys
View File

File diff suppressed because it is too large Load Diff

78
gradle/verification-metadata.xml
View File

@ -5,10 +5,14 @@
<verify-signatures>true</verify-signatures>
<keyring-format>armored</keyring-format>
<trusted-artifacts>
<trust group="com.datastax.oss" name="java-driver-bom" version="4.15.0"/>
<trust group="io.dropwizard.metrics" name="metrics-bom" reason="BOM file, safe to trust"/>
<trust group="io.dropwizard.metrics" name="metrics-parent" reason="BOM parent, https://github.com/gradle/gradle/issues/20194"/>
<trust group="org.springframework" name="spring-framework-bom" reason="Spring BOM file, safe to trust"/>
</trusted-artifacts>
<ignored-keys>
<ignored-key id="436902AF59EDF60E" reason="Key couldn't be downloaded from any key server"/>
</ignored-keys>
<trusted-keys>
<trusted-key id="015479E1055341431B4545AB72475FD306B9CAB7" group="com.googlecode.javaewah" name="JavaEWAH" version="1.2.3"/>
<trusted-key id="042B29E928995B9DB963C636C7CA19B7B620D787" group="com.github.stephenc.jcip" name="jcip-annotations" version="1.0-1"/>
@ -43,10 +47,6 @@
<trusted-key id="19BEAB2D799C020F17C69126B16698A4ADF4D638" group="org.checkerframework" name="checker-qual"/>
<trusted-key id="1AA8CF92D409A73393D0B736BFF2EE42C8282E76" group="org.apache.activemq" name="activemq-bom" version="6.1.4"/>
<trusted-key id="1D04A424F505394DBED15D451D0690E353BE126D" group="net.minidev"/>
<trusted-key id="1D2C7EF8ADA0F794B58C7C63436902AF59EDF60E">
<trusting group="dev.equo.ide" name="solstice" version="1.7.5"/>
<trusting group="dev.equo.ide" name="solstice" version="1.8.0"/>
</trusted-key>
<trusted-key id="20FC6EC5F628F0EB66F157B8DC97B815CAC4E847" group="io.github.pixee" name="java-security-toolkit" version="1.2.1"/>
<trusted-key id="2518174F4111F02779592A6F9757D7E7E06DD2AC" group="io.prometheus"/>
<trusted-key id="2655176F748FD83725B4805FF2A01147D830C125" group="org.testcontainers" name="testcontainers-bom"/>
@ -56,7 +56,7 @@
<trusted-key id="2B34821418CF19CF1F2A8352953E02E4F573B46F" group="jakarta.platform"/>
<trusted-key id="2BCBDD0F23EA1CAFCC11D4860374CF2E8DD1BDFD" group="net.java"/>
<trusted-key id="2DB4F1EF0FA761ECC4EA935C86FDC7E2A11262CB">
<trusting group="commons-beanutils" name="commons-beanutils" version="1.10.0"/>
<trusting group="commons-beanutils"/>
<trusting group="commons-codec"/>
<trusting group="commons-io"/>
<trusting group="commons-logging"/>
@ -67,12 +67,14 @@
<trusted-key id="2E3A1AFFE42B5F53AF19F780BCF4173966770193" group="org.jetbrains" name="annotations" version="13.0"/>
<trusted-key id="2FC53E6B1F681184F4CCD637F5C81DE10A0B8ECC" group="org.yaml" name="snakeyaml" version="2.3"/>
<trusted-key id="3262A061C42FC4C7BBB5C25C1CF0293FA53CA458" group="org.apache.tomcat.embed"/>
<trusted-key id="33FD4BFD33554634053D73C0C2148900BCD3C2AF" group="org.jetbrains" name="annotations" version="24.0.1"/>
<trusted-key id="34441E504A937F43EB0DAEF96A65176A0FB1CD0B" group="org.apache.groovy" name="groovy-bom"/>
<trusted-key id="3690C240CE51B4670D30AD1C38EE757D69184620" group="org.tukaani" name="xz" version="1.9"/>
<trusted-key id="3750777B9C4B7D233B9D0C40307A96FBA0292109" group="org.postgresql" name="postgresql" version="42.7.4"/>
<trusted-key id="38319E05F62674572CDF886170B2EBE96C112CC9" group="org.cryptacular" name="cryptacular" version="1.2.5"/>
<trusted-key id="3E61D8C230332482009D7F0EDB901B24CAD38BC4" group="io.swagger.core.v3"/>
<trusted-key id="3F05DDA9F317301E927136D417A27CE7A60FF5F0" group="io.opentelemetry" name="opentelemetry-bom"/>
<trusted-key id="4008F9DFF7DBC968F35F9E712642156411CCE8B3" group="com.vladsch.flexmark"/>
<trusted-key id="4021EEEAFF5DE8404DCD0A270AA3E5C3D232E79B">
<trusting group="jakarta.enterprise"/>
<trusting group="jakarta.inject"/>
@ -138,10 +140,7 @@
<trusted-key id="9790B1EC52577244529621F38C77ED250E495230" group="com.bucket4j" name="bucket4j_jdk17-core" version="8.14.0"/>
<trusted-key id="982C26A0C156D986CC2AD19E3FBA8E8E719022D7" group="org.jboss" name="jboss-parent" version="39"/>
<trusted-key id="9B32CBC0F3F6BA4C13D611FC21871D2A9AB66A31" group="io.rsocket" name="rsocket-bom" version="1.1.3"/>
<trusted-key id="9E3044071B758EBCB7E45673700E4F39BC05364B">
<trusting group="org.eclipse.platform" name="org.eclipse.osgi" version="3.18.300"/>
<trusting group="org.eclipse.platform" name="org.eclipse.osgi" version="3.18.500"/>
</trusted-key>
<trusted-key id="9E3044071B758EBCB7E45673700E4F39BC05364B" group="org.eclipse.platform" name="org.eclipse.osgi" version="3.18.500"/>
<trusted-key id="A41A5960555F8CBBC7D8B2D7787F3A057B828D36" group="org.springdoc"/>
<trusted-key id="A5BD02B93E7A40482EB1D66A5F69AD087600B22C" group="org.ow2.asm"/>
<trusted-key id="A602970FE1BF5C9C8A9491B97A3C9FE21DFDBF44" group="org.apache.pdfbox"/>
@ -150,15 +149,9 @@
<trusted-key id="A7892505CF1A58076453E52D7999BEFBA1039E8B" group="net.bytebuddy"/>
<trusted-key id="A9789342F598AD5B1175EF357EB97D110DFADD60" group="com.googlecode.concurrent-trees" name="concurrent-trees" version="2.6.1"/>
<trusted-key id="AA70C7C433D501636392EC02153E7A3C2B4E5118" group="org.eclipse.ee4j" name="project"/>
<trusted-key id="AB1DC33940689C44669107094989E0E939C2999B">
<trusting group="com.opencsv" name="opencsv" version="5.10"/>
<trusting group="com.opencsv" name="opencsv" version="5.9"/>
</trusted-key>
<trusted-key id="AB1DC33940689C44669107094989E0E939C2999B" group="com.opencsv" name="opencsv" version="5.10"/>
<trusted-key id="B1F250C1F371EBF0E31E86E30E31BBB30C940D01" group="com.posthog.java" name="posthog" version="1.1.1"/>
<trusted-key id="B6E73D84EA4FCC47166087253FAAD2CD5ECBB314">
<trusting group="commons-beanutils"/>
<trusting group="org.apache.commons"/>
</trusted-key>
<trusted-key id="B6E73D84EA4FCC47166087253FAAD2CD5ECBB314" group="org.apache.commons" name="commons-parent"/>
<trusted-key id="BA926F64CA647B6D853A38672E2010F8A7FF4A41" group="org.apache" name="apache" version="7"/>
<trusted-key id="BB785E0400E71390977E4D1ADF3CC7C64D56297B" group="jakarta.interceptor" name="jakarta.interceptor-api" version="2.1.0"/>
<trusted-key id="BCA1F17506AF088F3A964A9C0459A2B383ED8C11" group="org.eclipse.angus"/>
@ -204,7 +197,7 @@
<trusted-key id="F046369B06B761AC86D9849F71B329993BFFCFDD" group="com.oracle.database.jdbc" name="ojdbc-bom" version="21.9.0.0"/>
<trusted-key id="F0E31196852A34F8855710BD4A6CE7EBC7F4F54B" group="io.prometheus"/>
<trusted-key id="F1232CDCD94176E7FBA9CFE289A2C76A5EE16E57" group="technology.tabula" name="tabula" version="1.0.5"/>
<trusted-key id="F3184BCD55F4D016E30D4C9BF42E87F9665015C9" group="org.jsoup" name="jsoup" version="1.18.3"/>
<trusted-key id="F3184BCD55F4D016E30D4C9BF42E87F9665015C9" group="org.jsoup" name="jsoup" version="1.15.4"/>
<trusted-key id="F55EF5BB19F52A250FEDC0DF39450183608E49D4" group="com.googlecode.owasp-java-html-sanitizer"/>
<trusted-key id="F5FEBA84EB26C56457B2CF819E31AB27445478DB" group="org.infinispan"/>
<trusted-key id="F60649A7F36F9FBEE21D9AA08AC0378EC753063D" group="com.fathzer"/>
@ -220,14 +213,9 @@
</trusted-keys>
</configuration>
<components>
<component group="com.diffplug.spotless" name="com.diffplug.spotless.gradle.plugin" version="6.25.0">
<artifact name="com.diffplug.spotless.gradle.plugin-6.25.0.pom">
<sha256 value="f45c82b12faacd85acd474eba699322fa5dea88408b247d0e4bde9412908223a" origin="Generated by Gradle" reason="Artifact is not signed"/>
</artifact>
</component>
<component group="com.diffplug.spotless" name="com.diffplug.spotless.gradle.plugin" version="7.0.1">
<artifact name="com.diffplug.spotless.gradle.plugin-7.0.1.pom">
<sha256 value="d967a0f74c203ddcc5700947aab40f4be2a5a9f7b8d32aab7fc412b2030e7dfc" origin="Generated by Gradle" reason="Artifact is not signed"/>
<component group="com.diffplug.spotless" name="com.diffplug.spotless.gradle.plugin" version="7.0.2">
<artifact name="com.diffplug.spotless.gradle.plugin-7.0.2.pom">
<sha256 value="ed1ded77a296a6fe21a50279c926c07be14af7c08c2437d3685c70fcf6bba02d" origin="Generated by Gradle" reason="Artifact is not signed"/>
</artifact>
</component>
<component group="com.github.Carleslc.Simple-YAML" name="Simple-Configuration" version="1.8.4">
@ -272,11 +260,6 @@
<sha256 value="7b239eb029b2e4cab00dddf1df204ef4bbf88e78a43619c26fbb1e49bc53c642" origin="Generated by Gradle" reason="Artifact is not signed"/>
</artifact>
</component>
<component group="com.google.guava" name="guava-parent" version="33.3.1-jre">
<artifact name="guava-parent-33.3.1-jre.pom">
<sha256 value="55441db27e8869dfefe053059bdf478bdc7e95585642bf391f0023345fd56287" origin="Generated by Gradle"/>
</artifact>
</component>
<component group="com.martiansoftware" name="jsap" version="2.1">
<artifact name="jsap-2.1.jar">
<sha256 value="331746fa62cfbc3368260c5a2e660936ad11be612308c120a044e120361d474e" origin="Generated by Gradle" reason="Artifact is not signed"/>
@ -290,6 +273,14 @@
<sha256 value="65d310509352b5425118225ee600a01f83ba72142d035014b5d164bc04b2d284" origin="Generated by Gradle" reason="Artifact is not signed"/>
</artifact>
</component>
<component group="dev.equo.ide" name="solstice" version="1.8.1">
<artifact name="solstice-1.8.1.jar">
<sha256 value="6e5ba2cce813be1d71ccdc2ecf3e49271b14e691bfbbb1a114cf3a30e773b10d" origin="Generated by Gradle" reason="A key couldn't be downloaded"/>
</artifact>
<artifact name="solstice-1.8.1.module">
<sha256 value="a676039ea6af08f257b46e07c2bf1571a46a4d4b5b9ccb86c3fc98d07fafea1b" origin="Generated by Gradle" reason="A key couldn't be downloaded"/>
</artifact>
</component>
<component group="edu.sc.seis.launch4j" name="edu.sc.seis.launch4j.gradle.plugin" version="3.0.6">
<artifact name="edu.sc.seis.launch4j.gradle.plugin-3.0.6.pom">
<sha256 value="62a4f6752190b9ebf30869e092e4154e41a2c5cd96048ae98a01916f2684465a" origin="Generated by Gradle" reason="Artifact is not signed"/>
@ -342,21 +333,6 @@
<sha256 value="7a24e2700485eea087370f1dca6fe0291d7893d38c11aabfe977784fd93b808c" origin="Generated by Gradle" reason="Artifact is not signed"/>
</artifact>
</component>
<component group="org.apache" name="apache" version="27">
<artifact name="apache-27.pom">
<sha256 value="b2b0fc69e22a650c3892f1c366d77076f29575c6738df4c7a70a44844484cdf9" origin="Generated by Gradle"/>
</artifact>
</component>
<component group="org.apache" name="apache" version="33">
<artifact name="apache-33.pom">
<sha256 value="d78bd8524c5f8380a190a6525686629a95dfe512df21111383a6d8c0923a4415" origin="Generated by Gradle"/>
</artifact>
</component>
<component group="org.apache.commons" name="commons-parent" version="78">
<artifact name="commons-parent-78.pom">
<sha256 value="022d202e655edd04f2a10ecbe453d92977924d38380a4ca8c359f1817a80320e" origin="Generated by Gradle"/>
</artifact>
</component>
<component group="org.hibernate.common" name="hibernate-commons-annotations" version="7.0.3.Final">
<artifact name="hibernate-commons-annotations-7.0.3.Final.jar">
<sha256 value="0db2fd57d5e43688ac6ed5cdf36deaf05d84340dcc24c2dd2a2114de38e5175d" origin="Generated by Gradle" reason="Artifact is not signed"/>
@ -391,11 +367,6 @@
<sha256 value="9972c894749cda355766217d43ded7009b1eeb26e0301c30914a2db253dd685b" origin="Generated by Gradle" reason="Artifact is not signed"/>
</artifact>
</component>
<component group="org.junit" name="junit-bom" version="5.11.2">
<artifact name="junit-bom-5.11.2.pom">
<sha256 value="f48e88538aac145eb3ae0345a9ebd055b28f329a35dce8d1e9281325ca9b0ea2" origin="Generated by Gradle"/>
</artifact>
</component>
<component group="org.opensaml" name="opensaml-bom" version="4.3.0">
<artifact name="opensaml-bom-4.3.0.pom">
<sha256 value="4dfcc7cd96a2645c6e28df9f166f0e5b2b1a44aa109b3100cdb0ee17e01e02d2" origin="Generated by Gradle" reason="Artifact is not signed"/>
@ -406,11 +377,6 @@
<sha256 value="5e9db2f2dc3938835a76f5334997d79c8781511c8b68c1f6df6b384306900319" origin="Generated by Gradle" reason="Artifact is not signed"/>
</artifact>
</component>
<component group="org.ow2" name="ow2" version="1.5.1">
<artifact name="ow2-1.5.1.pom">
<sha256 value="321ddbb7ee6fe4f53dea6b4cd6db74154d6bfa42391c1f763b361b9f485acf05" origin="Generated by Gradle"/>
</artifact>
</component>
<component group="org.panteleyev" name="jpackage-gradle-plugin" version="1.6.0">
<artifact name="jpackage-gradle-plugin-1.6.0.jar">
<sha256 value="a8a588ff44a62db1aee62d3da117d2632a7f9a107709ca201da2a59dcb500175" origin="Generated by Gradle" reason="Artifact is not signed"/>

4
src/main/java/stirling/software/SPDF/config/EndpointConfiguration.java
View File

@ -126,6 +126,7 @@ public class EndpointConfiguration {
addEndpointToGroup("Convert", "url-to-pdf");
addEndpointToGroup("Convert", "markdown-to-pdf");
addEndpointToGroup("Convert", "pdf-to-csv");
addEndpointToGroup("Convert", "pdf-to-markdown");
// Adding endpoints to "Security" group
addEndpointToGroup("Security", "add-password");
@ -243,6 +244,7 @@ public class EndpointConfiguration {
addEndpointToGroup("Java", REMOVE_BLANKS);
addEndpointToGroup("Java", "pdf-to-text");
addEndpointToGroup("Java", "remove-image-pdf");
addEndpointToGroup("Java", "pdf-to-markdown");
// Javascript
addEndpointToGroup("Javascript", "pdf-organizer");
@ -258,9 +260,11 @@ public class EndpointConfiguration {
// Weasyprint dependent endpoints
addEndpointToGroup("Weasyprint", "html-to-pdf");
addEndpointToGroup("Weasyprint", "url-to-pdf");
addEndpointToGroup("Weasyprint", "markdown-to-pdf");
// Pdftohtml dependent endpoints
addEndpointToGroup("Pdftohtml", "pdf-to-html");
addEndpointToGroup("Pdftohtml", "pdf-to-markdown");
// disabled for now while we resolve issues
disableEndpoint("pdf-to-pdfa");

7
src/main/java/stirling/software/SPDF/controller/web/ConverterWebController.java
View File

@ -44,6 +44,13 @@ public class ConverterWebController {
return "convert/markdown-to-pdf";
}
@GetMapping("/pdf-to-markdown")
@Hidden
public String convertPdfToMarkdownForm(Model model) {
model.addAttribute("currentPage", "pdf-to-markdown");
return "convert/pdf-to-markdown";
}
@GetMapping("/url-to-pdf")
@Hidden
public String convertURLToPdfForm(Model model) {

32
src/main/java/stirling/software/SPDF/model/api/converters/ConvertPDFToMarkdown.java Normal file
View File

@ -0,0 +1,32 @@
package stirling.software.SPDF.model.api.converters;
import org.springframework.http.ResponseEntity;
import org.springframework.web.bind.annotation.ModelAttribute;
import org.springframework.web.bind.annotation.PostMapping;
import org.springframework.web.bind.annotation.RequestMapping;
import org.springframework.web.bind.annotation.RestController;
import org.springframework.web.multipart.MultipartFile;
import io.swagger.v3.oas.annotations.Operation;
import io.swagger.v3.oas.annotations.tags.Tag;
import stirling.software.SPDF.model.api.PDFFile;
import stirling.software.SPDF.utils.PDFToFile;
@RestController
@Tag(name = "Convert", description = "Convert APIs")
@RequestMapping("/api/v1/convert")
public class ConvertPDFToMarkdown {
@PostMapping(consumes = "multipart/form-data", value = "/pdf/markdown")
@Operation(
summary = "Convert PDF to Markdown",
description =
"This endpoint converts a PDF file to Markdown format. Input:PDF Output:Markdown Type:SISO")
public ResponseEntity<byte[]> processPdfToMarkdown(@ModelAttribute PDFFile request)
throws Exception {
MultipartFile inputFile = request.getFileInput();
PDFToFile pdfToFile = new PDFToFile();
return pdfToFile.processPdfToMarkdown(inputFile);
}
}

120
src/main/java/stirling/software/SPDF/utils/PDFToFile.java
View File

@ -20,6 +20,9 @@ import org.springframework.http.MediaType;
import org.springframework.http.ResponseEntity;
import org.springframework.web.multipart.MultipartFile;
import com.vladsch.flexmark.html2md.converter.FlexmarkHtmlConverter;
import com.vladsch.flexmark.util.data.MutableDataSet;
import io.github.pixee.security.Filenames;
import lombok.extern.slf4j.Slf4j;
@ -28,6 +31,123 @@ import stirling.software.SPDF.utils.ProcessExecutor.ProcessExecutorResult;
@Slf4j
public class PDFToFile {
public ResponseEntity<byte[]> processPdfToMarkdown(MultipartFile inputFile)
throws IOException, InterruptedException {
if (!"application/pdf".equals(inputFile.getContentType())) {
return new ResponseEntity<>(HttpStatus.BAD_REQUEST);
}
MutableDataSet options =
new MutableDataSet()
.set(
FlexmarkHtmlConverter.MAX_BLANK_LINES,
2) // Control max consecutive blank lines
.set(
FlexmarkHtmlConverter.MAX_TRAILING_BLANK_LINES,
1) // Control trailing blank lines
.set(
FlexmarkHtmlConverter.SETEXT_HEADINGS,
true) // Use Setext headings for h1 and h2
.set(
FlexmarkHtmlConverter.OUTPUT_UNKNOWN_TAGS,
false) // Don't output HTML for unknown tags
.set(
FlexmarkHtmlConverter.TYPOGRAPHIC_QUOTES,
true) // Convert quotation marks
.set(
FlexmarkHtmlConverter.BR_AS_PARA_BREAKS,
true) // Convert <br> to paragraph breaks
.set(FlexmarkHtmlConverter.CODE_INDENT, " "); // Indent for code blocks
FlexmarkHtmlConverter htmlToMarkdownConverter =
FlexmarkHtmlConverter.builder(options).build();
String originalPdfFileName = Filenames.toSimpleFileName(inputFile.getOriginalFilename());
String pdfBaseName = originalPdfFileName;
if (originalPdfFileName.contains(".")) {
pdfBaseName = originalPdfFileName.substring(0, originalPdfFileName.lastIndexOf('.'));
}
Path tempInputFile = null;
Path tempOutputDir = null;
byte[] fileBytes;
String fileName = "temp.file";
try {
tempInputFile = Files.createTempFile("input_", ".pdf");
inputFile.transferTo(tempInputFile);
tempOutputDir = Files.createTempDirectory("output_");
List<String> command =
new ArrayList<>(
Arrays.asList(
"pdftohtml",
"-s",
"-noframes",
"-c",
tempInputFile.toString(),
pdfBaseName));
ProcessExecutorResult returnCode =
ProcessExecutor.getInstance(ProcessExecutor.Processes.PDFTOHTML)
.runCommandWithOutputHandling(command, tempOutputDir.toFile());
// Process HTML files to Markdown
File[] outputFiles = Objects.requireNonNull(tempOutputDir.toFile().listFiles());
List<File> markdownFiles = new ArrayList<>();
// Convert HTML files to Markdown
for (File outputFile : outputFiles) {
if (outputFile.getName().endsWith(".html")) {
String html = Files.readString(outputFile.toPath());
String markdown = htmlToMarkdownConverter.convert(html);
String mdFileName = outputFile.getName().replace(".html", ".md");
File mdFile = new File(tempOutputDir.toFile(), mdFileName);
Files.writeString(mdFile.toPath(), markdown);
markdownFiles.add(mdFile);
}
}
// If there's only one markdown file, return it directly
if (markdownFiles.size() == 1) {
fileName = pdfBaseName + ".md";
fileBytes = Files.readAllBytes(markdownFiles.get(0).toPath());
} else {
// Multiple files - create a zip
fileName = pdfBaseName + "ToMarkdown.zip";
ByteArrayOutputStream byteArrayOutputStream = new ByteArrayOutputStream();
try (ZipOutputStream zipOutputStream = new ZipOutputStream(byteArrayOutputStream)) {
// Add markdown files
for (File mdFile : markdownFiles) {
ZipEntry mdEntry = new ZipEntry(mdFile.getName());
zipOutputStream.putNextEntry(mdEntry);
Files.copy(mdFile.toPath(), zipOutputStream);
zipOutputStream.closeEntry();
}
// Add images and other assets
for (File file : outputFiles) {
if (!file.getName().endsWith(".html") && !file.getName().endsWith(".md")) {
ZipEntry assetEntry = new ZipEntry(file.getName());
zipOutputStream.putNextEntry(assetEntry);
Files.copy(file.toPath(), zipOutputStream);
zipOutputStream.closeEntry();
}
}
}
fileBytes = byteArrayOutputStream.toByteArray();
}
} finally {
if (tempInputFile != null) Files.deleteIfExists(tempInputFile);
if (tempOutputDir != null) FileUtils.deleteDirectory(tempOutputDir.toFile());
}
return WebResponseUtils.bytesToWebResponse(
fileBytes, fileName, MediaType.APPLICATION_OCTET_STREAM);
}
public ResponseEntity<byte[]> processPdfToHtml(MultipartFile inputFile)
throws IOException, InterruptedException {
if (!"application/pdf".equals(inputFile.getContentType())) {

10
src/main/resources/messages_en_GB.properties
View File

@ -450,8 +450,11 @@ HTMLToPDF.tags=markup,web-content,transformation,convert
home.MarkdownToPDF.title=Markdown to PDF
home.MarkdownToPDF.desc=Converts any Markdown file to PDF
MarkdownToPDF.tags=markup,web-content,transformation,convert
MarkdownToPDF.tags=markup,web-content,transformation,convert,md
home.PDFToMarkdown.title=PDF to Markdown
home.PDFToMarkdown.desc=Converts any PDF to Markdown
PDFToMarkdown.tags=markup,web-content,transformation,convert,md
home.getPdfInfo.title=Get ALL Info on PDF
home.getPdfInfo.desc=Grabs any and all information possible on PDFs
@ -646,6 +649,11 @@ MarkdownToPDF.help=Work in progress
MarkdownToPDF.credit=Uses WeasyPrint
#pdf-to-markdown
PDFToMarkdown.title=PDF To Markdown
PDFToMarkdown.header=PDF To Markdown
PDFToMarkdown.submit=Convert
#url-to-pdf
URLToPDF.title=URL To PDF

10
src/main/resources/messages_en_US.properties
View File

@ -450,8 +450,11 @@ HTMLToPDF.tags=markup,web-content,transformation,convert
home.MarkdownToPDF.title=Markdown to PDF
home.MarkdownToPDF.desc=Converts any Markdown file to PDF
MarkdownToPDF.tags=markup,web-content,transformation,convert
MarkdownToPDF.tags=markup,web-content,transformation,convert,md
home.PDFToMarkdown.title=PDF to Markdown
home.PDFToMarkdown.desc=Converts any PDF to Markdown
PDFToMarkdown.tags=markup,web-content,transformation,convert,md
home.getPdfInfo.title=Get ALL Info on PDF
home.getPdfInfo.desc=Grabs any and all information possible on PDFs
@ -646,6 +649,11 @@ MarkdownToPDF.help=Work in progress
MarkdownToPDF.credit=Uses WeasyPrint
#pdf-to-markdown
PDFToMarkdown.title=PDF To Markdown
PDFToMarkdown.header=PDF To Markdown
PDFToMarkdown.submit=Convert
#url-to-pdf
URLToPDF.title=URL To PDF

31
src/main/resources/templates/convert/pdf-to-markdown.html Normal file
View File

@ -0,0 +1,31 @@
<!DOCTYPE html>
<html th:lang="${#locale.language}" th:dir="#{language.direction}" th:data-language="${#locale.toString()}" xmlns:th="https://www.thymeleaf.org">
<head>
<th:block th:insert="~{fragments/common :: head(title=#{PDFToMarkdown.title}, header=#{PDFToMarkdown.header})}"></th:block>
</head>
<body>
<th:block th:insert="~{fragments/common :: game}"></th:block>
<div id="page-container">
<div id="content-wrap">
<th:block th:insert="~{fragments/navbar.html :: navbar}"></th:block>
<br><br>
<div class="container">
<div class="row justify-content-center">
<div class="col-md-6 bg-card">
<div class="tool-header">
<span class="material-symbols-rounded tool-header-icon convert">markdown_copy</span>
<span class="tool-header-text" th:text="#{PDFToMarkdown.header}"></span>
</div>
<form method="post" enctype="multipart/form-data" th:action="@{'/api/v1/convert/pdf/markdown'}">
<div th:replace="~{fragments/common :: fileSelector(name='fileInput', multipleInputsForSingleRequest=false, accept='.pdf')}"></div>
<button type="submit" id="submitBtn" class="btn btn-primary" th:text="#{PDFToMarkdown.submit}"></button>
</form>
</div>
</div>
</div>
</div>
<th:block th:insert="~{fragments/footer.html :: footer}"></th:block>
</div>
</body>
</html>

3
src/main/resources/templates/fragments/navbar.html
View File

@ -136,6 +136,9 @@
<div
th:replace="~{fragments/navbarEntry :: navbarEntry ('pdf-to-book', 'book', 'home.PDFToBook.title', 'home.PDFToBook.desc', 'PDFToBook.tags', 'convert')}">
</div>
<div
th:replace="~{fragments/navbarEntry :: navbarEntry ('pdf-to-markdown', 'markdown_copy', 'home.PDFToMarkdown.title', 'home.PDFToMarkdown.desc', 'PDFToMarkdown.tags', 'convert')}">
</div>
</div>
</div>
<!-- Security menu items -->

3
src/main/resources/templates/home.html
View File

@ -192,6 +192,9 @@
<div
th:replace="~{fragments/card :: card(id='pdf-to-book', cardTitle=#{home.PDFToBook.title}, cardText=#{home.PDFToBook.desc}, cardLink='pdf-to-book', toolIcon='book', tags=#{PDFToBook.tags}, toolGroup='convert')}">
</div>
<div
th:replace="~{fragments/card :: card(id='pdf-to-markdown', cardTitle=#{home.PDFToMarkdown.title}, cardText=#{home.PDFToMarkdown.desc}, cardLink='pdf-to-markdown', toolIcon='markdown_copy', tags=#{PDFToMarkdown.tags}, toolGroup='convert')}">
</div>
</div>
</div>