fix(compression-coordinator): Restrict Zstandard detection to RFC-compliant .zst suffixes (fixes #2414); match suffixes case-insensitively.

components/clp-py-utils/clp_py_utils/core.py

@@ -15,13 +15,10 @@ def __init__(self, path: pathlib.Path, size: int):
         self.size = size
         self.estimated_uncompressed_size = size
 
-        filename = path.name
-        if any(filename.endswith(extension) for extension in [".gz", ".gzip", ".tgz", ".tar.gz"]):
+        filename = path.name.lower()
+        if any(filename.endswith(extension) for extension in [".gz", ".gzip", ".tgz"]):
             self.estimated_uncompressed_size *= 13
-        elif any(
-            filename.endswith(extension)
-            for extension in [".zstd", ".zstandard", ".tar.zstd", ".tar.zstandard"]
-        ):
+        elif filename.endswith(".zst"):
             self.estimated_uncompressed_size *= 8
 
 

components/compression-coordinator/src/partition.rs

@@ -240,19 +240,30 @@ impl Iterator for RoundRobinIterator {
 /// The estimated uncompressed size.
 fn estimate_uncompressed_size(key: &str, size: u64) -> u64 {
     const GZIP_COMPRESSION_RATIO_ESTIMATE: u64 = 13;
-    const GZIP_SUFFIXES: &[&str] = &[".gz", ".gzip", ".tgz", ".tar.gz"];
+    const GZIP_SUFFIXES: &[&str] = &[".gz", ".gzip", ".tgz"];
     const ZSTD_COMPRESSION_RATIO_ESTIMATE: u64 = 8;
-    const ZSTD_SUFFIXES: &[&str] = &[".zstd", ".zstandard", ".tar.zstd", ".tar.zstandard"];
 
-    if GZIP_SUFFIXES.iter().any(|suffix| key.ends_with(suffix)) {
+    if GZIP_SUFFIXES
+        .iter()
+        .any(|suffix| ends_with_ignore_ascii_case(key, suffix))
+    {
         size * GZIP_COMPRESSION_RATIO_ESTIMATE
-    } else if ZSTD_SUFFIXES.iter().any(|suffix| key.ends_with(suffix)) {
+    } else if ends_with_ignore_ascii_case(key, ".zst") {
         size * ZSTD_COMPRESSION_RATIO_ESTIMATE
     } else {
         size
     }
 }
 
+/// # Returns
+///
+/// Whether `key` ends with `suffix` using ASCII case-insensitive match.
+fn ends_with_ignore_ascii_case(key: &str, suffix: &str) -> bool {
+    let suffix_start = key.len().saturating_sub(suffix.len());
+    let key_suffix = key.get(suffix_start..);
+    key_suffix.is_some_and(|key_suffix| key_suffix.eq_ignore_ascii_case(suffix))
+}
+
 /// Gets the filename portion of an S3 object's key.
 ///
 /// # Returns
@@ -393,6 +404,38 @@ mod tests {
         }
     }
 
+    #[test]
+    fn test_estimate_uncompressed_size_for_gzip_suffix() {
+        const FILE_SIZE: u64 = 100;
+
+        for path in [
+            "logs/app.log.gz",
+            "logs/app.log.GZ",
+            "logs/app.log.gzip",
+            "logs/app.log.GZIP",
+            "logs/app.log.tgz",
+            "logs/app.log.TGZ",
+            "logs/app.log.tar.gz",
+            "logs/app.log.TAR.GZ",
+        ] {
+            assert_eq!(FILE_SIZE * 13, estimate_uncompressed_size(path, FILE_SIZE));
+        }
+    }
+
+    #[test]
+    fn test_estimate_uncompressed_size_for_zstandard_suffix() {
+        const FILE_SIZE: u64 = 100;
+
+        for path in [
+            "logs/app.log.zst",
+            "logs/app.log.clp.zst",
+            "logs/app.log.tar.zst",
+            "logs/app.log.ZST",
+        ] {
+            assert_eq!(FILE_SIZE * 8, estimate_uncompressed_size(path, FILE_SIZE));
+        }
+    }
+
     #[test]
     fn test_partition_on_flush() {
         const TARGET_ARCHIVE_SIZE: u64 = 1000;

integration-tests/tests/test_clp_native_py_project_imports.py

@@ -1,8 +1,11 @@
 """Smoke tests to validate that CLP Python projects can be imported without errors."""
 
+from pathlib import Path
+
 from clp_mcp_server.constants import QueryJobType
 from clp_package_utils.general import JobType
 from clp_py_utils.clp_config import StorageEngine
+from clp_py_utils.core import FileMetadata
 from job_orchestration.scheduler.constants import CompressionJobStatus
 
 
@@ -20,3 +23,33 @@ def test_clp_native_py_project_enum_classes() -> None:
     assert JobType.COMPRESSION == JobType("compression")
     assert StorageEngine.CLP == StorageEngine("clp")
     assert CompressionJobStatus.PENDING == CompressionJobStatus(0)
+
+
+def test_file_metadata_estimates_zstandard_file_sizes() -> None:
+    """Tests case-insensitive recognition of the standard Zstandard file extension."""
+    file_size = 100
+
+    for path in [
+        Path("app.log.zst"),
+        Path("app.log.clp.zst"),
+        Path("app.log.tar.zst"),
+        Path("app.log.ZST"),
+    ]:
+        assert file_size * 8 == FileMetadata(path, file_size).estimated_uncompressed_size
+
+
+def test_file_metadata_estimates_gzip_file_sizes() -> None:
+    """Tests case-insensitive recognition of the supported gzip file extensions."""
+    file_size = 100
+
+    for path in [
+        Path("app.log.gz"),
+        Path("app.log.GZ"),
+        Path("app.log.gzip"),
+        Path("app.log.GZIP"),
+        Path("app.log.tgz"),
+        Path("app.log.TGZ"),
+        Path("app.log.tar.gz"),
+        Path("app.log.TAR.GZ"),
+    ]:
+        assert file_size * 13 == FileMetadata(path, file_size).estimated_uncompressed_size