Basic impl

mapleFU · Sep 26, 2023 · 824f808 · 824f808
1 parent 5978729
commit 824f808
Showing 1 changed file with 11 additions and 0 deletions.
diff --git a/cpp/src/parquet/encoding.cc b/cpp/src/parquet/encoding.cc
@@ -3369,6 +3369,9 @@ class DeltaByteArrayDecoderImpl : public DecoderImpl, virtual public TypedDecode
       if (ARROW_PREDICT_FALSE(prefix_len_ptr[i] < 0)) {
         throw ParquetException("negative prefix length in DELTA_BYTE_ARRAY");
       }
+      if (buffer[i].len == 0 || prefix_len_ptr[i] == 0) {
+        continue;
+      }
       if (ARROW_PREDICT_FALSE(AddWithOverflow(data_size, prefix_len_ptr[i], &data_size) ||
                               AddWithOverflow(data_size, buffer[i].len, &data_size))) {
         throw ParquetException("excess expansion in DELTA_BYTE_ARRAY");
@@ -3382,6 +3385,14 @@ class DeltaByteArrayDecoderImpl : public DecoderImpl, virtual public TypedDecode
       if (ARROW_PREDICT_FALSE(static_cast<size_t>(prefix_len_ptr[i]) > prefix.length())) {
         throw ParquetException("prefix length too large in DELTA_BYTE_ARRAY");
       }
+      if (prefix_len_ptr[i] == 0) {
+        prefix = std::string_view{buffer[i]};
+        continue;
+      }
+      if (buffer[i].len == 0) {
+        buffer[i] = prefix;
+        continue;
+      }
       memcpy(data_ptr, prefix.data(), prefix_len_ptr[i]);
       // buffer[i] currently points to the string suffix
       memcpy(data_ptr + prefix_len_ptr[i], buffer[i].ptr, buffer[i].len);