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 d44ec74988 [Enhancement](column) optimize for
ColumnString::insert_many_dict_data (#12636)
d44ec74988 is described below
commit d44ec749887b058c3ca0a19d6deffb1e1c396976
Author: Pxl <pxl...@qq.com>
AuthorDate: Fri Sep 16 10:23:04 2022 +0800
[Enhancement](column) optimize for ColumnString::insert_many_dict_data
(#12636)
optimize for ColumnString::insert_many_dict_data
---
be/src/vec/columns/column_string.h | 24 ++++++++++++++++++++----
1 file changed, 20 insertions(+), 4 deletions(-)
diff --git a/be/src/vec/columns/column_string.h
b/be/src/vec/columns/column_string.h
index 8dc597e18c..2adb32dd99 100644
--- a/be/src/vec/columns/column_string.h
+++ b/be/src/vec/columns/column_string.h
@@ -191,17 +191,33 @@ public:
uint32_t len = strings[i].size;
if (len) {
memcpy(data + offset, strings[i].data, len);
+ offset += len;
}
- offset += len;
offsets.push_back(offset);
}
}
void insert_many_dict_data(const int32_t* data_array, size_t start_index,
const StringRef* dict,
size_t num, uint32_t /*dict_num*/) override {
- for (size_t end_index = start_index + num; start_index < end_index;
++start_index) {
- int32_t codeword = data_array[start_index];
- insert_data(dict[codeword].data, dict[codeword].size);
+ size_t new_size = 0;
+ for (size_t i = start_index; i < start_index + num; i++) {
+ int32_t codeword = data_array[i];
+ new_size += dict[codeword].size;
+ }
+
+ const size_t old_size = chars.size();
+ chars.resize(old_size + new_size);
+
+ Char* data = chars.data();
+ size_t offset = old_size;
+ for (size_t i = start_index; i < start_index + num; i++) {
+ int32_t codeword = data_array[i];
+ uint32_t len = dict[codeword].size;
+ if (len) {
+ memcpy(data + offset, dict[codeword].data, len);
+ offset += len;
+ }
+ offsets.push_back(offset);
}
}
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscr...@doris.apache.org
For additional commands, e-mail: commits-h...@doris.apache.org
