Pdf box memory usage (#918)

* Encode with UTF-8 if getString has funny characters * Fix streams concurrency issues Issue:202643 * Bump PDFBox to 3.0.3 and improve memory usage Issue:202734 * Fix font loading --------- Co-authored-by: iroqueta <[email protected]>
genexuslabs · Dec 17, 2024 · a48753c · a48753c
1 parent 7cabd4b
commit a48753c
Show file tree

Hide file tree

Showing 3 changed files with 123 additions and 109 deletions.
diff --git a/java/pom.xml b/java/pom.xml
@@ -120,7 +120,7 @@
 		<dependency>
     		<groupId>org.apache.pdfbox</groupId>
     		<artifactId>pdfbox</artifactId>
-    		<version>2.0.27</version>
+    		<version>3.0.3</version>
 		</dependency>
 		<dependency>
     		<groupId>org.jsoup</groupId>

diff --git a/java/src/main/java/com/genexus/internet/HttpClientJavaLib.java b/java/src/main/java/com/genexus/internet/HttpClientJavaLib.java
@@ -718,23 +718,16 @@ public String getString() {
 			return "";
 		try {
 			this.setEntity();
-			ContentType contentType = ContentType.getOrDefault(entity);
-			Charset charset;
-			if (contentType.equals(ContentType.DEFAULT_TEXT)) {
-				charset = StandardCharsets.UTF_8;
-			} else {
-				charset = contentType.getCharset();
-				if (charset == null) {
-					charset = StandardCharsets.UTF_8;
-				}
-			}
+			Charset charset = ContentType.getOrDefault(entity).getCharset();
 			String res = EntityUtils.toString(entity, charset);
+			if (res.matches(".*[Ã-ÿ].*")) {
+				res = EntityUtils.toString(entity, StandardCharsets.UTF_8);
+			}
 			eof = true;
 			return res;
 		} catch (IOException e) {
 			setExceptionsCatch(e);
-		} catch (IllegalArgumentException e) {
-		}
+		} catch (IllegalArgumentException e) {}
 		return "";
 	}