This is an automated email from the ASF dual-hosted git repository.
panxiaolei 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 71fa00d1298 [Chore](column) enable sanity_check for
ColumnNullable/ColumnArray/ColumnMap/ColumnStruct (#51858)
71fa00d1298 is described below
commit 71fa00d1298307720b5ad2cf592e463699cb6286
Author: Pxl <[email protected]>
AuthorDate: Wed Jun 25 11:09:41 2025 +0800
[Chore](column) enable sanity_check for
ColumnNullable/ColumnArray/ColumnMap/ColumnStruct (#51858)
### What problem does this PR solve?
enable sanity_check for
ColumnNullable/ColumnArray/ColumnMap/ColumnStruct
### Check List (For Author)
- Test <!-- At least one of them must be included. -->
- [ ] Regression test
- [ ] Unit Test
- [ ] Manual test (add detailed scripts or steps below)
- [x] No need to test or manual test. Explain why:
- [ ] This is a refactor/code format and no logic has been changed.
- [x] Previous test can cover this change.
- [ ] No code files have been changed.
- [ ] Other reason <!-- Add your reason? -->
- Behavior changed:
- [x] No.
- [ ] Yes. <!-- Explain the behavior change -->
- Does this need documentation?
- [x] No.
- [ ] Yes. <!-- Add document PR link here. eg:
https://github.com/apache/doris-website/pull/1214 -->
### Check List (For Reviewer who merge this PR)
- [ ] Confirm the release note
- [ ] Confirm test cases
- [ ] Confirm document
- [ ] Add branch pick label <!-- Add branch pick label that this PR
should merge into -->
---
be/src/vec/columns/column.h | 5 +++++
be/src/vec/columns/column_array.h | 5 +++++
be/src/vec/columns/column_map.h | 6 ++++++
be/src/vec/columns/column_nullable.h | 9 +++++++++
be/src/vec/columns/column_string.h | 4 ++--
be/src/vec/columns/column_struct.h | 12 ++++++++++++
be/src/vec/exprs/vexpr_context.cpp | 5 +----
7 files changed, 40 insertions(+), 6 deletions(-)
diff --git a/be/src/vec/columns/column.h b/be/src/vec/columns/column.h
index 7828ac46445..dcdce26ae68 100644
--- a/be/src/vec/columns/column.h
+++ b/be/src/vec/columns/column.h
@@ -72,6 +72,11 @@ public:
/// Name of a Column. It is used in info messages.
virtual std::string get_name() const = 0;
+ // used to check the column data is valid or not.
+ virtual void sanity_check() const {
+ // do nothing by default, but some column may need to check
+ }
+
/** If column isn't constant, returns nullptr (or itself).
* If column is constant, transforms constant to full column (if column
type allows such transform) and return it.
*/
diff --git a/be/src/vec/columns/column_array.h
b/be/src/vec/columns/column_array.h
index 5511e0504c6..072c4098771 100644
--- a/be/src/vec/columns/column_array.h
+++ b/be/src/vec/columns/column_array.h
@@ -111,6 +111,11 @@ public:
return Base::create(std::forward<Args>(args)...);
}
+ void sanity_check() const override {
+ data->sanity_check();
+ offsets->sanity_check();
+ }
+
void shrink_padding_chars() override;
/** On the index i there is an offset to the beginning of the i + 1 -th
element. */
diff --git a/be/src/vec/columns/column_map.h b/be/src/vec/columns/column_map.h
index ada5ff70441..70aece03c79 100644
--- a/be/src/vec/columns/column_map.h
+++ b/be/src/vec/columns/column_map.h
@@ -79,6 +79,12 @@ public:
callback(offsets_column);
}
+ void sanity_check() const override {
+ keys_column->sanity_check();
+ values_column->sanity_check();
+ offsets_column->sanity_check();
+ }
+
void clear() override {
keys_column->clear();
values_column->clear();
diff --git a/be/src/vec/columns/column_nullable.h
b/be/src/vec/columns/column_nullable.h
index 321b78b1aa8..8a06a85262b 100644
--- a/be/src/vec/columns/column_nullable.h
+++ b/be/src/vec/columns/column_nullable.h
@@ -143,6 +143,15 @@ public:
return Base::create(std::forward<Args>(args)...);
}
+ void sanity_check() const override {
+ if (nested_column->size() != get_null_map_data().size()) {
+ throw doris::Exception(ErrorCode::INTERNAL_ERROR,
+ "Size of nested column {} is not equal to
size of null map {}",
+ nested_column->size(),
get_null_map_data().size());
+ }
+ nested_column->sanity_check();
+ }
+
void shrink_padding_chars() override;
bool is_variable_length() const override { return
nested_column->is_variable_length(); }
diff --git a/be/src/vec/columns/column_string.h
b/be/src/vec/columns/column_string.h
index 07aaee81fe7..77546ee1207 100644
--- a/be/src/vec/columns/column_string.h
+++ b/be/src/vec/columns/column_string.h
@@ -109,8 +109,8 @@ private:
public:
bool is_variable_length() const override { return true; }
- // used in string ut testd
- void sanity_check() const;
+
+ void sanity_check() const override;
void sanity_check_simple() const;
std::string get_name() const override { return "String"; }
diff --git a/be/src/vec/columns/column_struct.h
b/be/src/vec/columns/column_struct.h
index eb7dba98c9a..8fd020f6af4 100644
--- a/be/src/vec/columns/column_struct.h
+++ b/be/src/vec/columns/column_struct.h
@@ -85,6 +85,18 @@ public:
MutableColumnPtr clone_resized(size_t size) const override;
size_t size() const override { return columns.at(0)->size(); }
+ void sanity_check() const override {
+ for (size_t i = 0; i < columns.size(); ++i) {
+ columns[i]->sanity_check();
+ if (i != 0 && columns[i]->size() != columns[0]->size()) {
+ throw doris::Exception(
+ ErrorCode::INTERNAL_ERROR,
+ "Size of sub column({}) is not equal to size of first
column({})",
+ columns[i]->size(), columns[0]->size());
+ }
+ }
+ }
+
bool is_variable_length() const override { return true; }
bool is_exclusive() const override {
diff --git a/be/src/vec/exprs/vexpr_context.cpp
b/be/src/vec/exprs/vexpr_context.cpp
index ae277dd848e..82db6838d04 100644
--- a/be/src/vec/exprs/vexpr_context.cpp
+++ b/be/src/vec/exprs/vexpr_context.cpp
@@ -63,10 +63,7 @@ Status VExprContext::execute(vectorized::Block* block, int*
result_column_id) {
_last_result_column_id = *result_column_id;
// We should first check the status, as some expressions might
incorrectly set result_column_id, even if the st is not ok.
if (st.ok() && _last_result_column_id != -1) {
- if (const auto* column_str = check_and_get_column<ColumnString>(
-
block->get_by_position(*result_column_id).column.get())) {
- column_str->sanity_check();
- }
+ block->get_by_position(*result_column_id).column->sanity_check();
}
});
return st;
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
