pitrou commented on code in PR #38327:
URL: https://github.com/apache/arrow/pull/38327#discussion_r1365592454
##########
cpp/src/parquet/file_deserialize_test.cc:
##########
@@ -879,6 +879,45 @@ TEST_F(TestPageSerde, DataPageV2CrcCheckNonExistent) {
/* write_data_page_v2 */ true);
}
+TEST_F(TestPageSerde, BadCompressedPageSize) {
+ auto codec_types = GetSupportedCodecTypes();
+ const int data_page_bytes = 8192;
+ const int32_t num_rows = 32; // dummy value
+ data_page_header_.num_values = num_rows;
+ std::vector<uint8_t> faux_data;
+ // Resize and make all to 1 to make it well-compressed.
+ faux_data.resize(data_page_bytes, 1);
+ for (auto codec_type : codec_types) {
+ auto codec = GetCodec(codec_type);
+ std::vector<uint8_t> buffer;
+ const uint8_t* data = faux_data.data();
+ int data_size = static_cast<int>(faux_data.size());
+
+ int64_t max_compressed_size = codec->MaxCompressedLen(data_size, data);
+ buffer.resize(max_compressed_size);
+
+ int64_t actual_size;
+ ASSERT_OK_AND_ASSIGN(
+ actual_size, codec->Compress(data_size, data, max_compressed_size,
&buffer[0]));
+ ASSERT_NO_FATAL_FAILURE(WriteDataPageHeader(data_page_bytes, data_size + 1,
Review Comment:
```suggestion
// Write a data page header declaring a larger decompressed size than
actual
ASSERT_NO_FATAL_FAILURE(WriteDataPageHeader(data_page_bytes, data_size +
1,
```
##########
cpp/src/parquet/file_deserialize_test.cc:
##########
@@ -879,6 +879,45 @@ TEST_F(TestPageSerde, DataPageV2CrcCheckNonExistent) {
/* write_data_page_v2 */ true);
}
+TEST_F(TestPageSerde, BadCompressedPageSize) {
+ auto codec_types = GetSupportedCodecTypes();
+ const int data_page_bytes = 8192;
+ const int32_t num_rows = 32; // dummy value
+ data_page_header_.num_values = num_rows;
+ std::vector<uint8_t> faux_data;
+ // Resize and make all to 1 to make it well-compressed.
+ faux_data.resize(data_page_bytes, 1);
Review Comment:
Nit
```suggestion
// A well-compressible piece of data
std::vector<uint8_t> faux_data(data_page_bytes, 1);
```
##########
cpp/src/parquet/file_deserialize_test.cc:
##########
@@ -879,6 +879,45 @@ TEST_F(TestPageSerde, DataPageV2CrcCheckNonExistent) {
/* write_data_page_v2 */ true);
}
+TEST_F(TestPageSerde, BadCompressedPageSize) {
+ auto codec_types = GetSupportedCodecTypes();
Review Comment:
```suggestion
// GH-38326: an exception should be raised if a compressed data page
// decompresses to a smaller size than declared in the data page header.
auto codec_types = GetSupportedCodecTypes();
```
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
