This is an automated email from the ASF dual-hosted git repository.
dongjoon pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/orc-format.git
The following commit(s) were added to refs/heads/main by this push:
new 3fecd70 MINOR: Add missing proto definition to spec (#22)
3fecd70 is described below
commit 3fecd7005111119bf873c128c81ee8f72823c989
Author: Gang Wu <[email protected]>
AuthorDate: Wed Apr 9 11:05:33 2025 +0800
MINOR: Add missing proto definition to spec (#22)
### What changes were proposed in this pull request?
- Add missing proto definitions to v1/v2 spec doc.
- Fix alignment of type kind.
### Why are the changes needed?
Just to be consistent with the protobuf definition
### How was this patch tested?
N/A
---
specification/ORCv0.md | 36 ++++++++++++++++++------------------
specification/ORCv1.md | 40 +++++++++++++++++++++-------------------
specification/ORCv2.md | 40 +++++++++++++++++++++-------------------
3 files changed, 60 insertions(+), 56 deletions(-)
diff --git a/specification/ORCv0.md b/specification/ORCv0.md
index 5c36cf6..daccb58 100644
--- a/specification/ORCv0.md
+++ b/specification/ORCv0.md
@@ -180,24 +180,24 @@ that contains the list of their children's type ids.
```
message Type {
enum Kind {
- BOOLEAN = 0;
- BYTE = 1;
- SHORT = 2;
- INT = 3;
- LONG = 4;
- FLOAT = 5;
- DOUBLE = 6;
- STRING = 7;
- BINARY = 8;
- TIMESTAMP = 9;
- LIST = 10;
- MAP = 11;
- STRUCT = 12;
- UNION = 13;
- DECIMAL = 14;
- DATE = 15;
- VARCHAR = 16;
- CHAR = 17;
+ BOOLEAN = 0;
+ BYTE = 1;
+ SHORT = 2;
+ INT = 3;
+ LONG = 4;
+ FLOAT = 5;
+ DOUBLE = 6;
+ STRING = 7;
+ BINARY = 8;
+ TIMESTAMP = 9;
+ LIST = 10;
+ MAP = 11;
+ STRUCT = 12;
+ UNION = 13;
+ DECIMAL = 14;
+ DATE = 15;
+ VARCHAR = 16;
+ CHAR = 17;
}
// the kind of this type
required Kind kind = 1;
diff --git a/specification/ORCv1.md b/specification/ORCv1.md
index a6b12d6..83b1357 100644
--- a/specification/ORCv1.md
+++ b/specification/ORCv1.md
@@ -222,25 +222,25 @@ that contains the list of their children's type ids.
```
message Type {
enum Kind {
- BOOLEAN = 0;
- BYTE = 1;
- SHORT = 2;
- INT = 3;
- LONG = 4;
- FLOAT = 5;
- DOUBLE = 6;
- STRING = 7;
- BINARY = 8;
- TIMESTAMP = 9;
- LIST = 10;
- MAP = 11;
- STRUCT = 12;
- UNION = 13;
- DECIMAL = 14;
- DATE = 15;
- VARCHAR = 16;
- CHAR = 17;
- TIMESTAMP_INSTANT = 18;
+ BOOLEAN = 0;
+ BYTE = 1;
+ SHORT = 2;
+ INT = 3;
+ LONG = 4;
+ FLOAT = 5;
+ DOUBLE = 6;
+ STRING = 7;
+ BINARY = 8;
+ TIMESTAMP = 9;
+ LIST = 10;
+ MAP = 11;
+ STRUCT = 12;
+ UNION = 13;
+ DECIMAL = 14;
+ DATE = 15;
+ VARCHAR = 16;
+ CHAR = 17;
+ TIMESTAMP_INSTANT = 18;
}
// the kind of this type
required Kind kind = 1;
@@ -281,6 +281,8 @@ message ColumnStatistics {
optional BinaryStatistics binaryStatistics = 8;
optional TimestampStatistics timestampStatistics = 9;
optional bool hasNull = 10;
+ optional uint64 bytes_on_disk = 11;
+ optional CollectionStatistics collection_statistics = 12;
}
```
diff --git a/specification/ORCv2.md b/specification/ORCv2.md
index 3411485..73daf6e 100644
--- a/specification/ORCv2.md
+++ b/specification/ORCv2.md
@@ -242,25 +242,25 @@ that contains the list of their children's type ids.
```
message Type {
enum Kind {
- BOOLEAN = 0;
- BYTE = 1;
- SHORT = 2;
- INT = 3;
- LONG = 4;
- FLOAT = 5;
- DOUBLE = 6;
- STRING = 7;
- BINARY = 8;
- TIMESTAMP = 9;
- LIST = 10;
- MAP = 11;
- STRUCT = 12;
- UNION = 13;
- DECIMAL = 14;
- DATE = 15;
- VARCHAR = 16;
- CHAR = 17;
- TIMESTAMP_INSTANT = 18;
+ BOOLEAN = 0;
+ BYTE = 1;
+ SHORT = 2;
+ INT = 3;
+ LONG = 4;
+ FLOAT = 5;
+ DOUBLE = 6;
+ STRING = 7;
+ BINARY = 8;
+ TIMESTAMP = 9;
+ LIST = 10;
+ MAP = 11;
+ STRUCT = 12;
+ UNION = 13;
+ DECIMAL = 14;
+ DATE = 15;
+ VARCHAR = 16;
+ CHAR = 17;
+ TIMESTAMP_INSTANT = 18;
}
// the kind of this type
required Kind kind = 1;
@@ -301,6 +301,8 @@ message ColumnStatistics {
optional BinaryStatistics binaryStatistics = 8;
optional TimestampStatistics timestampStatistics = 9;
optional bool hasNull = 10;
+ optional uint64 bytes_on_disk = 11;
+ optional CollectionStatistics collection_statistics = 12;
}
```
