bug:SP-3626 Fixes winnowing parsing issue

Author: agustingroh

CHANGELOG.md

@@ -10,10 +10,14 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 ### Added
 
 - Upcoming changes...
+
+## [0.12.0] - 2025-11-03
 ### Added
 - `calculateOppositeLineEndingHash()` method in `WinnowingUtils` to compute hash with opposite line endings (Unix ↔ Windows)
 - FH2 hash included in WFP output format as `fh2=<hash>`
 - Support for detecting CRLF (Windows), LF (Unix), and CR (legacy Mac) line endings
+### Fixed
+- Fixed WFP parsing issue
 
 ## [0.11.0] - 2025-05-26
 ### Added
@@ -126,4 +130,5 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 [0.9.0]: https://github.com/scanoss/scanoss.java/compare/v0.8.1...v0.9.0
 [0.10.0]: https://github.com/scanoss/scanoss.java/compare/v0.9.0...v0.10.0
 [0.10.1]: https://github.com/scanoss/scanoss.java/compare/v0.10.0...v0.10.1
-[0.11.0]: https://github.com/scanoss/scanoss.java/compare/v0.10.1...v0.11.0
+[0.11.0]: https://github.com/scanoss/scanoss.java/compare/v0.10.1...v0.11.0
+[0.12.0]: https://github.com/scanoss/scanoss.java/compare/v0.11.0...v0.12.0

pom.xml

@@ -6,7 +6,7 @@
 
     <groupId>com.scanoss</groupId>
     <artifactId>scanoss</artifactId>
-    <version>0.11.0</version>
+    <version>0.12.0</version>
     <packaging>jar</packaging>
     <name>scanoss.java</name>
     <url>https://github.com/scanoss/scanoss.java</url>

src/main/java/com/scanoss/Winnowing.java

@@ -194,11 +194,7 @@ public String wfpForContents(@NonNull String filename, Boolean binFile, byte[] c
                             if (lastLine != line) {
                                 int obLength = outputBuilder.length();
                                 if (obLength > 0) {
-                                    if (snippetLimit > 0 && obLength > snippetLimit) {
-                                        log.debug("Skipping snippet line as it's too big ({}): {}", filename, outputBuilder);
-                                    } else {
-                                        wfpBuilder.append(outputBuilder).append("\n");
-                                    }
+                                    wfpBuilder.append(outputBuilder).append("\n");
                                 }
                                 outputBuilder.delete(0, obLength);
                                 outputBuilder.append(String.format("%d=%s", line, minHashHex));
@@ -216,11 +212,7 @@ public String wfpForContents(@NonNull String filename, Boolean binFile, byte[] c
         }
         int obLength = outputBuilder.length();
         if (obLength > 0) {
-            if (snippetLimit > 0 && obLength > snippetLimit) {
-                log.debug("Skipping snippet line as it's too big ({}) {} - {}: {}", filename, snippetLimit, obLength, outputBuilder);
-            } else {
-                wfpBuilder.append(outputBuilder).append("\n");
-            }
+            wfpBuilder.append(outputBuilder).append("\n");
         }
         return wfpBuilder.toString();
     }
@@ -288,6 +280,21 @@ private Boolean skipSnippets(@NonNull String filename, char[] contents) {
                 }
             }
         }
+        // Check if first line is too long (matches Python implementation)
+        int firstLineEnd = 0;
+        for (int i = 0; i < contents.length; i++) {
+            if (contents[i] == '\n') {
+                firstLineEnd = i;
+                break;
+            }
+        }
+        if (firstLineEnd == 0) {
+            firstLineEnd = contents.length;  // No newline found, use entire content length
+        }
+        if (snippetLimit > 0 && firstLineEnd > snippetLimit) {
+            log.trace("Skipping snippets due to first line being too long: {} - {} chars", filename, firstLineEnd);
+            return true;
+        }
         return false;
     }