[doris] branch master updated: [Fix](orc-reader) Check hasNulls() firstly when use notNull data in ColumnVectorBatch. #18674

[yiguolei]

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

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


The following commit(s) were added to refs/heads/master by this push:
     new cc4778a271 [Fix](orc-reader) Check hasNulls() firstly when use notNull 
data in ColumnVectorBatch. #18674
cc4778a271 is described below

commit cc4778a271111fcb2d4027a3d5831bfc9c6a730c
Author: Qi Chen <kaka11.c...@gmail.com>
AuthorDate: Sat Apr 15 19:48:31 2023 +0800

    [Fix](orc-reader) Check hasNulls() firstly when use notNull data in 
ColumnVectorBatch. #18674
---
 be/src/vec/exec/format/orc/vorc_reader.cpp | 35 ++++++++++++++++++++----------
 1 file changed, 24 insertions(+), 11 deletions(-)

diff --git a/be/src/vec/exec/format/orc/vorc_reader.cpp 
b/be/src/vec/exec/format/orc/vorc_reader.cpp
index c4fd3c2409..ada1284f21 100644
--- a/be/src/vec/exec/format/orc/vorc_reader.cpp
+++ b/be/src/vec/exec/format/orc/vorc_reader.cpp
@@ -660,23 +660,36 @@ Status OrcReader::_decode_string_column(const 
std::string& col_name,
     string_values.reserve(num_values);
     if (type_kind == orc::TypeKind::CHAR) {
         // Possibly there are some zero padding characters in CHAR type, we 
have to strip them off.
-        for (int i = 0; i < num_values; ++i) {
-            if (cvb->notNull[i]) {
+        if (cvb->hasNulls) {
+            for (int i = 0; i < num_values; ++i) {
+                if (cvb->notNull[i]) {
+                    string_values.emplace_back(data->data[i],
+                                               trim_right(data->data[i], 
data->length[i]));
+                } else {
+                    // Orc doesn't fill null values in new batch, but the 
former batch has been release.
+                    // Other types like int/long/timestamp... are flat types 
without pointer in them,
+                    // so other types do not need to be handled separately 
like string.
+                    string_values.emplace_back(empty_string.data(), 0);
+                }
+            }
+        } else {
+            for (int i = 0; i < num_values; ++i) {
                 string_values.emplace_back(data->data[i],
                                            trim_right(data->data[i], 
data->length[i]));
-            } else {
-                // Orc doesn't fill null values in new batch, but the former 
batch has been release.
-                // Other types like int/long/timestamp... are flat types 
without pointer in them,
-                // so other types do not need to be handled separately like 
string.
-                string_values.emplace_back(empty_string.data(), 0);
             }
         }
     } else {
-        for (int i = 0; i < num_values; ++i) {
-            if (cvb->notNull[i]) {
+        if (cvb->hasNulls) {
+            for (int i = 0; i < num_values; ++i) {
+                if (cvb->notNull[i]) {
+                    string_values.emplace_back(data->data[i], data->length[i]);
+                } else {
+                    string_values.emplace_back(empty_string.data(), 0);
+                }
+            }
+        } else {
+            for (int i = 0; i < num_values; ++i) {
                 string_values.emplace_back(data->data[i], data->length[i]);
-            } else {
-                string_values.emplace_back(empty_string.data(), 0);
             }
         }
     }


---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscr...@doris.apache.org
For additional commands, e-mail: commits-h...@doris.apache.org