(sedona) branch master updated: [GH-2036] update more robust instream count for Geography decode (#2305)

[jiayu]

This is an automated email from the ASF dual-hosted git repository.

jiayu pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/sedona.git


The following commit(s) were added to refs/heads/master by this push:
     new 6bc52c38ca [GH-2036] update more robust instream count for Geography 
decode (#2305)
6bc52c38ca is described below

commit 6bc52c38ca1726c7a0c679e4d1086a312a2eaabd
Author: Zhuocheng Shang <122398181+zhuochengsh...@users.noreply.github.com>
AuthorDate: Wed Aug 20 21:17:24 2025 -0700

    [GH-2036] update more robust instream count for Geography decode (#2305)
    
    * update to more robust check instream count
    
    * empty commit to retrigger ci
---
 .../common/S2Geography/GeographyCollection.java    | 29 ++++++++++++--------
 .../common/S2Geography/PolylineGeography.java      | 32 ++++++++++++----------
 2 files changed, 35 insertions(+), 26 deletions(-)

diff --git 
a/common/src/main/java/org/apache/sedona/common/S2Geography/GeographyCollection.java
 
b/common/src/main/java/org/apache/sedona/common/S2Geography/GeographyCollection.java
index 71e9f84624..85e23c935e 100644
--- 
a/common/src/main/java/org/apache/sedona/common/S2Geography/GeographyCollection.java
+++ 
b/common/src/main/java/org/apache/sedona/common/S2Geography/GeographyCollection.java
@@ -135,20 +135,25 @@ public class GeographyCollection extends Geography {
     // Skip any covering data
     tag.skipCovering(in);
 
-    // 3) Ensure we have at least 4 bytes for the count
-    if (in.available() < Integer.BYTES) {
-      throw new IOException("GeographyCollection.decodeTagged error: 
insufficient header bytes");
-    }
+    try {
+      int count = in.readInt();
+      if (count < 0) {
+        throw new IOException("GeographyCollection.decodeTagged error: 
negative count: " + count);
+      }
+
+      for (int i = 0; i < count; i++) {
+        tag = EncodeTag.decode(in);
+        // avoid creating new stream, directly call S2Geography.decode
+        Geography feature = Geography.decode(in, tag);
+        geo.features.add(feature);
+      }
+      geo.countShapes();
 
-    // Read feature count
-    int n = in.readInt();
-    for (int i = 0; i < n; i++) {
-      tag = EncodeTag.decode(in);
-      // avoid creating new stream, directly call S2Geography.decode
-      Geography feature = Geography.decode(in, tag);
-      geo.features.add(feature);
+    } catch (EOFException e) {
+      throw new IOException(
+          "GeographyCollection.decodeTagged error: insufficient data to decode 
all parts of the geography.",
+          e);
     }
-    geo.countShapes();
     return geo;
   }
 
diff --git 
a/common/src/main/java/org/apache/sedona/common/S2Geography/PolylineGeography.java
 
b/common/src/main/java/org/apache/sedona/common/S2Geography/PolylineGeography.java
index a8bb1638f8..6e71072889 100644
--- 
a/common/src/main/java/org/apache/sedona/common/S2Geography/PolylineGeography.java
+++ 
b/common/src/main/java/org/apache/sedona/common/S2Geography/PolylineGeography.java
@@ -138,22 +138,26 @@ public class PolylineGeography extends Geography {
     // 2) Skip past any covering cell-IDs written by encodeTagged
     tag.skipCovering(in);
 
-    // 3) Ensure we have at least 4 bytes for the count
-    if (in.available() < Integer.BYTES) {
-      throw new IOException("PolylineGeography.decodeTagged error: 
insufficient header bytes");
-    }
-
-    // 5) Read the number of polylines (4-byte)
-    int count = in.readInt();
+    // 3) Read the number of polylines (4-byte)
+    try {
+      int count = in.readInt();
+      if (count < 0) {
+        throw new IOException("PolylineGeography.decodeTagged error: negative 
count: " + count);
+      }
+      if (tag.getKind() == GeographyKind.SINGLEPOLYLINE) {
+        return new SinglePolylineGeography(S2Polyline.decode(in));
+      }
 
-    if (tag.getKind() == GeographyKind.SINGLEPOLYLINE) {
-      return new SinglePolylineGeography(S2Polyline.decode(in));
-    }
+      // 4) For each polyline, read its block and let 
S2Polyline.decode(InputStream) do the rest
+      for (int i = 0; i < count; i++) {
+        S2Polyline pl = S2Polyline.decode(in);
+        geo.polylines.add(pl);
+      }
 
-    // 6) For each polyline, read its block and let 
S2Polyline.decode(InputStream) do the rest
-    for (int i = 0; i < count; i++) {
-      S2Polyline pl = S2Polyline.decode(in);
-      geo.polylines.add(pl);
+    } catch (EOFException e) {
+      throw new IOException(
+          "PolylineGeography.decodeTagged error: insufficient data to decode 
all parts of the geography.",
+          e);
     }
     return geo;
   }