arsvendg/Stirling-PDF
1
0
Fork 0
mirror of https://github.com/arsvendg/Stirling-PDF.git synced 2026-07-15 02:54:06 +02:00
Code Issues Actions 6 Packages Projects Releases 1 Wiki Activity

refactor: standardize MIME handling via Spring MediaType (#4389)

Browse Source
This commit is contained in:
Ludy
2025-09-05 11:08:24 +01:00
committed by GitHub
parent f14955a019
commit 9a39aff19f
82 changed files with 310 additions and 164 deletions
Download Patch File Download Diff File Expand all files Collapse all files
app/common/src/main/java/stirling/software/common/annotations/AutoJobPostMapping.java
+2 -1
View File
@@ -3,6 +3,7 @@ package stirling.software.common.annotations;
import java.lang.annotation.*;
import org.springframework.core.annotation.AliasFor;
import org.springframework.http.MediaType;
import org.springframework.web.bind.annotation.RequestMapping;
import org.springframework.web.bind.annotation.RequestMethod;
@@ -37,7 +38,7 @@ public @interface AutoJobPostMapping {
/** MIME types this endpoint accepts. Defaults to {@code multipart/form-data}. */
@AliasFor(annotation = RequestMapping.class, attribute = "consumes")
String[] consumes() default {"multipart/form-data"};
String[] consumes() default {MediaType.MULTIPART_FORM_DATA_VALUE};
/**
* Maximum execution time in milliseconds before the job is aborted. A negative value means "use
app/common/src/main/java/stirling/software/common/model/api/PDFFile.java
+2 -1
View File
@@ -1,5 +1,6 @@
package stirling.software.common.model.api;
import org.springframework.http.MediaType;
import org.springframework.web.multipart.MultipartFile;
import io.swagger.v3.oas.annotations.media.Schema;
@@ -14,7 +15,7 @@ import lombok.NoArgsConstructor;
public class PDFFile {
@Schema(
description = "The input PDF file",
contentMediaType = "application/pdf",
contentMediaType = MediaType.APPLICATION_PDF_VALUE,
format = "binary")
private MultipartFile fileInput;
app/common/src/main/java/stirling/software/common/service/JobExecutorService.java
+7 -8
View File
@@ -227,7 +227,8 @@ public class JobExecutorService {
if (result instanceof byte[]) {
// Store byte array directly to disk to avoid double memory consumption
String fileId = fileStorage.storeBytes((byte[]) result, "result.pdf");
taskManager.setFileResult(jobId, fileId, "result.pdf", "application/pdf");
taskManager.setFileResult(
jobId, fileId, "result.pdf", MediaType.APPLICATION_PDF_VALUE);
log.debug("Stored byte[] result with fileId: {}", fileId);
// Let the byte array get collected naturally in the next GC cycle
@@ -239,7 +240,7 @@ public class JobExecutorService {
if (body instanceof byte[]) {
// Extract filename from content-disposition header if available
String filename = "result.pdf";
String contentType = "application/pdf";
String contentType = MediaType.APPLICATION_PDF_VALUE;
if (response.getHeaders().getContentDisposition() != null) {
String disposition =
@@ -276,7 +277,7 @@ public class JobExecutorService {
if (fileId != null && !fileId.isEmpty()) {
// Try to get filename and content type
String filename = "result.pdf";
String contentType = "application/pdf";
String contentType = MediaType.APPLICATION_PDF_VALUE;
try {
java.lang.reflect.Method getOriginalFileName =
@@ -317,8 +318,7 @@ public class JobExecutorService {
// Store generic result
taskManager.setResult(jobId, body);
}
} else if (result instanceof MultipartFile) {
MultipartFile file = (MultipartFile) result;
} else if (result instanceof MultipartFile file) {
String fileId = fileStorage.storeFile(file);
taskManager.setFileResult(
jobId, fileId, file.getOriginalFilename(), file.getContentType());
@@ -335,7 +335,7 @@ public class JobExecutorService {
if (fileId != null && !fileId.isEmpty()) {
// Try to get filename and content type
String filename = "result.pdf";
String contentType = "application/pdf";
String contentType = MediaType.APPLICATION_PDF_VALUE;
try {
java.lang.reflect.Method getOriginalFileName =
@@ -398,9 +398,8 @@ public class JobExecutorService {
HttpHeaders.CONTENT_DISPOSITION,
"form-data; name=\"attachment\"; filename=\"result.pdf\"")
.body(result);
} else if (result instanceof MultipartFile) {
} else if (result instanceof MultipartFile file) {
// Return MultipartFile content
MultipartFile file = (MultipartFile) result;
return ResponseEntity.ok()
.contentType(MediaType.parseMediaType(file.getContentType()))
.header(
app/common/src/main/java/stirling/software/common/util/EmlParser.java
+7 -5
View File
@@ -12,6 +12,8 @@ import java.util.List;
import java.util.Properties;
import java.util.regex.Pattern;
import org.springframework.http.MediaType;
import lombok.Data;
import lombok.experimental.UtilityClass;
@@ -28,8 +30,8 @@ public class EmlParser {
Pattern.compile("=\\?([^?]+)\\?([BbQq])\\?([^?]*)\\?=");
private static final String DISPOSITION_ATTACHMENT = "attachment";
private static final String TEXT_PLAIN = "text/plain";
private static final String TEXT_HTML = "text/html";
private static final String TEXT_PLAIN = MediaType.TEXT_PLAIN_VALUE;
private static final String TEXT_HTML = MediaType.TEXT_HTML_VALUE;
private static final String MULTIPART_PREFIX = "multipart/";
private static final String HEADER_CONTENT_TYPE = "content-type:";
@@ -69,12 +71,12 @@ public class EmlParser {
if (isJakartaMailAvailable()) {
return extractEmailContentAdvanced(emlBytes, request, customHtmlSanitizer);
} else {
return extractEmailContentBasic(emlBytes, request, customHtmlSanitizer);
return extractEmailContentBasic(emlBytes, customHtmlSanitizer);
}
}
private static EmailContent extractEmailContentBasic(
byte[] emlBytes, EmlToPdfRequest request, CustomHtmlSanitizer customHtmlSanitizer) {
byte[] emlBytes, CustomHtmlSanitizer customHtmlSanitizer) {
String emlContent = new String(emlBytes, StandardCharsets.UTF_8);
EmailContent content = new EmailContent();
@@ -121,7 +123,7 @@ public class EmlParser {
return extractFromMimeMessage(message, request, customHtmlSanitizer);
} catch (ReflectiveOperationException e) {
return extractEmailContentBasic(emlBytes, request, customHtmlSanitizer);
return extractEmailContentBasic(emlBytes, customHtmlSanitizer);
}
}
app/common/src/main/java/stirling/software/common/util/EmlProcessingUtils.java
+9 -7
View File
@@ -8,6 +8,8 @@ import java.util.Map;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
import org.springframework.http.MediaType;
import lombok.experimental.UtilityClass;
import stirling.software.common.model.api.converters.EmlToPdfRequest;
@@ -33,10 +35,10 @@ public class EmlProcessingUtils {
// MIME type detection
private static final Map<String, String> EXTENSION_TO_MIME_TYPE =
Map.of(
".png", "image/png",
".jpg", "image/jpeg",
".jpeg", "image/jpeg",
".gif", "image/gif",
".png", MediaType.IMAGE_PNG_VALUE,
".jpg", MediaType.IMAGE_JPEG_VALUE,
".jpeg", MediaType.IMAGE_JPEG_VALUE,
".gif", MediaType.IMAGE_GIF_VALUE,
".bmp", "image/bmp",
".webp", "image/webp",
".svg", "image/svg+xml",
@@ -81,8 +83,8 @@ public class EmlProcessingUtils {
|| lowerContent.contains("bcc:");
boolean hasMimeStructure =
lowerContent.contains("multipart/")
|| lowerContent.contains("text/plain")
|| lowerContent.contains("text/html")
|| lowerContent.contains(MediaType.TEXT_PLAIN_VALUE)
|| lowerContent.contains(MediaType.TEXT_HTML_VALUE)
|| lowerContent.contains("boundary=");
int headerCount = 0;
@@ -464,7 +466,7 @@ public class EmlProcessingUtils {
}
}
return "image/png";
return MediaType.IMAGE_PNG_VALUE; // Default MIME type
}
public static String decodeUrlEncoded(String encoded) {
app/common/src/main/java/stirling/software/common/util/PDFToFile.java
+3 -3
View File
@@ -36,7 +36,7 @@ public class PDFToFile {
public ResponseEntity<byte[]> processPdfToMarkdown(MultipartFile inputFile)
throws IOException, InterruptedException {
if (!"application/pdf".equals(inputFile.getContentType())) {
if (!MediaType.APPLICATION_PDF_VALUE.equals(inputFile.getContentType())) {
return new ResponseEntity<>(HttpStatus.BAD_REQUEST);
}
@@ -153,7 +153,7 @@ public class PDFToFile {
public ResponseEntity<byte[]> processPdfToHtml(MultipartFile inputFile)
throws IOException, InterruptedException {
if (!"application/pdf".equals(inputFile.getContentType())) {
if (!MediaType.APPLICATION_PDF_VALUE.equals(inputFile.getContentType())) {
return new ResponseEntity<>(HttpStatus.BAD_REQUEST);
}
@@ -223,7 +223,7 @@ public class PDFToFile {
MultipartFile inputFile, String outputFormat, String libreOfficeFilter)
throws IOException, InterruptedException {
if (!"application/pdf".equals(inputFile.getContentType())) {
if (!MediaType.APPLICATION_PDF_VALUE.equals(inputFile.getContentType())) {
return new ResponseEntity<>(HttpStatus.BAD_REQUEST);
}
app/common/src/main/java/stirling/software/common/util/PdfAttachmentHandler.java
+2 -1
View File
@@ -37,6 +37,7 @@ import org.apache.pdfbox.pdmodel.interactive.annotation.PDAppearanceStream;
import org.apache.pdfbox.text.PDFTextStripper;
import org.apache.pdfbox.text.TextPosition;
import org.jetbrains.annotations.NotNull;
import org.springframework.http.MediaType;
import org.springframework.web.multipart.MultipartFile;
import lombok.Data;
@@ -118,7 +119,7 @@ public class PdfAttachmentHandler {
public String getContentType() {
return attachment.getContentType() != null
? attachment.getContentType()
: "application/octet-stream";
: MediaType.APPLICATION_OCTET_STREAM_VALUE;
}
@Override
app/common/src/main/java/stirling/software/common/util/PdfUtils.java
+19 -7
View File
@@ -29,6 +29,7 @@ import org.apache.pdfbox.pdmodel.graphics.image.PDImageXObject;
import org.apache.pdfbox.rendering.ImageType;
import org.apache.pdfbox.rendering.PDFRenderer;
import org.apache.pdfbox.text.PDFTextStripper;
import org.springframework.http.MediaType;
import org.springframework.web.multipart.MultipartFile;
import io.github.pixee.security.Filenames;
@@ -156,7 +157,8 @@ public class PdfUtils {
if (DPI > maxSafeDpi) {
throw ExceptionUtils.createIllegalArgumentException(
"error.dpiExceedsLimit",
"DPI value {0} exceeds maximum safe limit of {1}. High DPI values can cause memory issues and crashes. Please use a lower DPI value.",
"DPI value {0} exceeds maximum safe limit of {1}. High DPI values can cause"
+ " memory issues and crashes. Please use a lower DPI value.",
DPI,
maxSafeDpi);
}
@@ -196,7 +198,9 @@ public class PdfUtils {
.contains("Maximum size of image exceeded")) {
throw ExceptionUtils.createIllegalArgumentException(
"error.pageTooBigForDpi",
"PDF page {0} is too large to render at {1} DPI. Please try a lower DPI value (recommended: 150 or less).",
"PDF page {0} is too large to render at {1} DPI. Please"
+ " try a lower DPI value (recommended: 150 or"
+ " less).",
i + 1,
DPI);
}
@@ -241,7 +245,10 @@ public class PdfUtils {
.contains("Maximum size of image exceeded")) {
throw ExceptionUtils.createIllegalArgumentException(
"error.pageTooBigExceedsArray",
"PDF page {0} is too large to render at {1} DPI. The resulting image would exceed Java's maximum array size. Please try a lower DPI value (recommended: 150 or less).",
"PDF page {0} is too large to render at {1} DPI. The"
+ " resulting image would exceed Java's maximum"
+ " array size. Please try a lower DPI value"
+ " (recommended: 150 or less).",
i + 1,
DPI);
}
@@ -282,7 +289,9 @@ public class PdfUtils {
.contains("Maximum size of image exceeded")) {
throw ExceptionUtils.createIllegalArgumentException(
"error.pageTooBigForDpi",
"PDF page {0} is too large to render at {1} DPI. Please try a lower DPI value (recommended: 150 or less).",
"PDF page {0} is too large to render at {1} DPI. Please"
+ " try a lower DPI value (recommended: 150 or"
+ " less).",
i + 1,
DPI);
}
@@ -315,7 +324,8 @@ public class PdfUtils {
&& e.getMessage().contains("Maximum size of image exceeded")) {
throw ExceptionUtils.createIllegalArgumentException(
"error.pageTooBigForDpi",
"PDF page {0} is too large to render at {1} DPI. Please try a lower DPI value (recommended: 150 or less).",
"PDF page {0} is too large to render at {1} DPI. Please try"
+ " a lower DPI value (recommended: 150 or less).",
i + 1,
DPI);
}
@@ -366,7 +376,9 @@ public class PdfUtils {
&& e.getMessage().contains("Maximum size of image exceeded")) {
throw ExceptionUtils.createIllegalArgumentException(
"error.pageTooBigFor300Dpi",
"PDF page {0} is too large to render at 300 DPI. The resulting image would exceed Java's maximum array size. Please use a lower DPI value for PDF-to-image conversion.",
"PDF page {0} is too large to render at 300 DPI. The resulting image"
+ " would exceed Java's maximum array size. Please use a lower DPI"
+ " value for PDF-to-image conversion.",
page + 1);
}
throw e;
@@ -435,7 +447,7 @@ public class PdfUtils {
ImageProcessingUtils.convertColorType(image, colorType);
// Use JPEGFactory if it's JPEG since JPEG is lossy
PDImageXObject pdImage =
(contentType != null && "image/jpeg".equals(contentType))
(contentType != null && MediaType.IMAGE_JPEG_VALUE.equals(contentType))
? JPEGFactory.createFromImage(doc, convertedImage)
: LosslessFactory.createFromImage(doc, convertedImage);
addImageToDocument(doc, pdImage, fitOption, autoRotate);