Skip to content

Commit f098575

Browse files
Deeguezhangyizhong03
Deegue
and
zhangyizhong03
authored
[AURON #2503] Rename blaze to auron (#2504)
# Which issue does this PR close? Closes #2503 # Rationale for this change Wrong naming. # What changes are included in this PR? Rename blaze to auron. # Are there any user-facing changes? No. # How was this patch tested? UTs. # Was this patch authored or co-authored using generative AI tooling? - [ ] Yes - [x] No Co-authored-by: zhangyizhong03 <zhangyizhong03@kuaishou.com>
1 parent ffc6a27 commit f098575

27 files changed

Lines changed: 62 additions & 62 deletions

File tree

‎Cargo.toml‎

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -202,7 +202,7 @@ zstd = "0.13.3"
202202
rdkafka = { version = "0.36.0", features = ["tokio"] }
203203

204204
[patch.crates-io]
205-
# datafusion: branch=v49.0.0-blaze
205+
# datafusion: branch=v49.0.0-auron
206206
datafusion = { path = "./dev/vendors/packages/datafusion/datafusion/core"}
207207
datafusion-common = { path = "./dev/vendors/packages/datafusion/datafusion/common"}
208208
datafusion-expr = { path = "./dev/vendors/packages/datafusion/datafusion/expr"}
@@ -214,7 +214,7 @@ datafusion-physical-expr = { path = "./dev/vendors/packages/datafusion/datafusio
214214
datafusion-spark = { path = "./dev/vendors/packages/datafusion/datafusion/spark"}
215215
orc-rust = { path = "./dev/vendors/packages/orc-rust"}
216216

217-
# arrow: branch=v55.2.0-blaze
217+
# arrow: branch=v55.2.0-auron
218218
arrow = { path = "./dev/vendors/packages/arrow-rs/arrow"}
219219
arrow-arith = { path = "./dev/vendors/packages/arrow-rs/arrow-arith"}
220220
arrow-array = { path = "./dev/vendors/packages/arrow-rs/arrow-array"}
@@ -229,5 +229,5 @@ arrow-select = { path = "./dev/vendors/packages/arrow-rs/arrow-select"}
229229
arrow-string = { path = "./dev/vendors/packages/arrow-rs/arrow-string"}
230230
parquet = { path = "./dev/vendors/packages/arrow-rs/parquet"}
231231

232-
# serde_json: branch=v1.0.96-blaze
232+
# serde_json: branch=v1.0.96-auron
233233
serde_json = { path = "./dev/vendors/packages/serde_json" }

dev/vendors/patches/arrow-rs/0001-blaze-fix-NaN-comparison-semantic.patch renamed to dev/vendors/patches/arrow-rs/0001-auron-fix-NaN-comparison-semantic.patch

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -1,7 +1,7 @@
11
From ed4ace347da4acfe0c3453e1b34ede067de894e2 Mon Sep 17 00:00:00 2001
22
From: zhangli20 <zhangli20@kuaishou.com>
33
Date: Sun, 15 Sep 2024 20:54:37 +0800
4-
Subject: [PATCH] blaze: fix NaN comparison semantic
4+
Subject: [PATCH] auron: fix NaN comparison semantic
55

66
---
77
arrow-array/src/arithmetic.rs | 19 ++++++++++++++++++-
@@ -16,7 +16,7 @@ index b5f4a106f..c4e88b91a 100644
1616
#[inline]
1717
fn compare(self, rhs: Self) -> Ordering {
1818
- <$t>::total_cmp(&self, &rhs)
19-
+ // blaze:
19+
+ // auron:
2020
+ // nan-safe version according to semantics where NaN == NaN and
2121
+ // NaN is greater than any non-NaN double.
2222
+ if self.is_nan() && rhs.is_nan() {
@@ -35,7 +35,7 @@ index b5f4a106f..c4e88b91a 100644
3535
// Equivalent to `self.total_cmp(&rhs).is_eq()`
3636
// but LLVM isn't able to realise this is bitwise equality
3737
// https://rust.godbolt.org/z/347nWGxoW
38-
+ // blaze:
38+
+ // auron:
3939
+ // nan-safe version according to semantics where NaN == NaN and
4040
+ // NaN is greater than any non-NaN double.
4141
+ if self.is_nan() && rhs.is_nan() {

dev/vendors/patches/arrow-rs/0002-blaze-add-get_dictionary.patch renamed to dev/vendors/patches/arrow-rs/0002-auron-add-get_dictionary.patch

Lines changed: 10 additions & 10 deletions
Original file line numberDiff line numberDiff line change
@@ -1,17 +1,17 @@
11
From 83e2918853b9519b669a3143293943df9626fd6b Mon Sep 17 00:00:00 2001
22
From: zhangli20 <zhangli20@kuaishou.com>
33
Date: Sun, 15 Sep 2024 21:00:43 +0800
4-
Subject: [PATCH] blaze: add get_dictionary
4+
Subject: [PATCH] auron: add get_dictionary
55

66
---
77
parquet/src/arrow/array_reader/mod.rs | 2 +-
88
parquet/src/arrow/async_reader/mod.rs | 12 +-
99
parquet/src/arrow/mod.rs | 4 +-
10-
parquet/src/blaze.rs | 274 ++++++++++++++++++++++++++
10+
parquet/src/auron.rs | 274 ++++++++++++++++++++++++++
1111
parquet/src/column/reader.rs | 2 +-
1212
parquet/src/lib.rs | 4 +
1313
6 files changed, 293 insertions(+), 5 deletions(-)
14-
create mode 100644 parquet/src/blaze.rs
14+
create mode 100644 parquet/src/auron.rs
1515

1616
diff --git a/parquet/src/arrow/array_reader/mod.rs b/parquet/src/arrow/array_reader/mod.rs
1717
index 94d61c9ea..06b06c9de 100644
@@ -36,9 +36,9 @@ index 611d6999e..248de5be3 100644
3636
) -> BoxFuture<'a, Result<Arc<ParquetMetaData>>>;
3737
+
3838
+ /// Sync version of get_bytes
39-
+ /// this is only used by blaze, for reading dictionary values for row group pruning
39+
+ /// this is only used by auron, for reading dictionary values for row group pruning
4040
+ fn get_bytes_sync(&mut self, range: Range<u64>) -> Result<Bytes> {
41-
+ unimplemented!("blaze only")
41+
+ unimplemented!("auron only")
4242
+ }
4343
}
4444

@@ -71,11 +71,11 @@ index e33d6a05a..4afcb9464 100644
7171
mod decoder;
7272

7373
#[cfg(feature = "async")]
74-
diff --git a/parquet/src/blaze.rs b/parquet/src/blaze.rs
74+
diff --git a/parquet/src/auron.rs b/parquet/src/auron.rs
7575
new file mode 100644
7676
index 000000000..88ab30d1e
7777
--- /dev/null
78-
+++ b/parquet/src/blaze.rs
78+
+++ b/parquet/src/auron.rs
7979
@@ -0,0 +1,274 @@
8080
+use std::io::Read;
8181
+use std::sync::{Arc, Mutex};
@@ -285,7 +285,7 @@ index 000000000..88ab30d1e
285285
+ use crate::arrow::arrow_reader::ArrowReaderOptions;
286286
+ use crate::arrow::async_reader::AsyncFileReader;
287287
+ use crate::arrow::ParquetRecordBatchStreamBuilder;
288-
+ use crate::blaze::get_dictionary_for_pruning;
288+
+ use crate::auron::get_dictionary_for_pruning;
289289
+ use crate::errors::ParquetError;
290290
+ use crate::file::footer::{decode_footer, decode_metadata};
291291
+ use crate::file::FOOTER_SIZE;
@@ -325,7 +325,7 @@ index 000000000..88ab30d1e
325325
+ #[tokio::test]
326326
+ async fn test_get_dictionary() -> crate::errors::Result<()> {
327327
+ let input = AsyncLocalFileReader(
328-
+ File::open("/Volumes/Workspace/blaze-init/arrow-rs/with-dict-2.parquet")?
328+
+ File::open("/Volumes/Workspace/auron-init/arrow-rs/with-dict-2.parquet")?
329329
+ );
330330
+ let mut builder = ParquetRecordBatchStreamBuilder::new_with_options(
331331
+ input,
@@ -375,7 +375,7 @@ index f814ddeb0..b69d85ba8 100644
375375
+
376376
+#[cfg(feature = "arrow")]
377377
+#[cfg(feature = "async")]
378-
+pub mod blaze;
378+
+pub mod auron;
379379
--
380380
2.50.1
381381

dev/vendors/patches/arrow-rs/0003-blaze-skip-parquet-utf-8-validating.patch renamed to dev/vendors/patches/arrow-rs/0003-auron-skip-parquet-utf-8-validating.patch

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -1,7 +1,7 @@
11
From 0ed0f11556f78301050d71d4c40b77d46ecba52a Mon Sep 17 00:00:00 2001
22
From: zhangli20 <zhangli20@kuaishou.com>
33
Date: Sun, 15 Sep 2024 21:14:08 +0800
4-
Subject: [PATCH] blaze: skip parquet utf-8 validating
4+
Subject: [PATCH] auron: skip parquet utf-8 validating
55

66
---
77
arrow-array/src/types.rs | 40 +++++++++++------------
@@ -114,7 +114,7 @@ index 5051dce12..802df6ed0 100644
114114
/// [`Self::try_push`] can perform this validation check on insertion
115115
pub fn check_valid_utf8(&self, start_offset: usize) -> Result<()> {
116116
- check_valid_utf8(&self.values.as_slice()[start_offset..])
117-
+ // blaze: ignore utf8 validation
117+
+ // auron: ignore utf8 validation
118118
+ // check_valid_utf8(&self.values.as_slice()[start_offset..])
119119
+ Ok(())
120120
}

dev/vendors/patches/arrow-rs/0004-blaze-map-field-name-fixed-to-entries.patch renamed to dev/vendors/patches/arrow-rs/0004-auron-map-field-name-fixed-to-entries.patch

Lines changed: 4 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -1,7 +1,7 @@
11
From ac1cb670bf1d82289c9a7aacca46a438905a8fcd Mon Sep 17 00:00:00 2001
22
From: zhangli20 <zhangli20@kuaishou.com>
33
Date: Sun, 15 Sep 2024 21:21:14 +0800
4-
Subject: [PATCH] blaze: map_field's name fixed to 'entries'
4+
Subject: [PATCH] auron: map_field's name fixed to 'entries'
55

66
---
77
parquet/src/arrow/async_reader/metadata.rs | 6 ++++++
@@ -18,9 +18,9 @@ index e0f7bdbbe..9a985e885 100644
1818
fn fetch_suffix(&mut self, suffix: usize) -> BoxFuture<'_, Result<Bytes>>;
1919
+
2020
+ /// Sync version of get_bytes
21-
+ /// this is only used by blaze, for reading dictionary values for row group pruning
21+
+ /// this is only used by auron, for reading dictionary values for row group pruning
2222
+ fn get_bytes_sync(&mut self, range: Range<usize>) -> Result<Bytes> {
23-
+ unimplemented!("blaze only")
23+
+ unimplemented!("auron only")
2424
+ }
2525
}
2626

@@ -34,7 +34,7 @@ index 16d46bd85..af70b8684 100644
3434

3535
let map_field = Field::new_struct(
3636
- map_key_value.name(),
37-
+ "entries", // blaze: map_field's name fixed to 'entries'
37+
+ "entries", // auron: map_field's name fixed to 'entries'
3838
[key_field, value_field],
3939
false, // The inner map field is always non-nullable (#1697)
4040
)

dev/vendors/patches/arrow-rs/0005-blaze-fix-statistics-null-count-is-negative-error.patch renamed to dev/vendors/patches/arrow-rs/0005-auron-fix-statistics-null-count-is-negative-error.patch

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -1,7 +1,7 @@
11
From 308b3c77cd28c654a84b38df46871cf0a88444f3 Mon Sep 17 00:00:00 2001
22
From: zhangli20 <zhangli20@kuaishou.com>
33
Date: Sun, 15 Sep 2024 21:24:51 +0800
4-
Subject: [PATCH] blaze: fix 'Statistics null count is negative (-1)' error
4+
Subject: [PATCH] auron: fix 'Statistics null count is negative (-1)' error
55

66
---
77
parquet/src/file/statistics.rs | 3 ++-
@@ -17,7 +17,7 @@ index b7522a76f..b7849e4f9 100644
1717
// see https://github.com/apache/arrow-rs/pull/6216/files
1818
- let null_count = stats.null_count.unwrap_or(0);
1919
+ let null_count = stats.null_count.unwrap_or(0)
20-
+ .max(0); // blaze - fix 'Statistics null count is negative (-1)' error
20+
+ .max(0); // auron - fix 'Statistics null count is negative (-1)' error
2121

2222
if null_count < 0 {
2323
return Err(ParquetError::General(format!(

dev/vendors/patches/arrow-rs/0006-blaze-expose-fields-of-AsyncReader-ArrowReaderBuilder-to-pub.patch renamed to dev/vendors/patches/arrow-rs/0006-auron-expose-fields-of-AsyncReader-ArrowReaderBuilder-to-pub.patch

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,7 +1,7 @@
11
From 0f9132f81a3a6d69ed2b893a5bc5d7820f819a4d Mon Sep 17 00:00:00 2001
22
From: zhangli20 <zhangli20@kuaishou.com>
33
Date: Mon, 16 Sep 2024 00:16:57 +0800
4-
Subject: [PATCH] blaze: expose fields of AsyncReader/ArrowReaderBuilder to
4+
Subject: [PATCH] auron: expose fields of AsyncReader/ArrowReaderBuilder to
55
public
66

77
---

dev/vendors/patches/arrow-rs/0007-blaze-use-bufreader-to-read-page-header-avoid-reading-in-fragments.patch renamed to dev/vendors/patches/arrow-rs/0007-auron-use-bufreader-to-read-page-header-avoid-reading-in-fragments.patch

Lines changed: 4 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -1,7 +1,7 @@
11
From 417f165b72b99a25cc8f910fde9b43c1d5e06587 Mon Sep 17 00:00:00 2001
22
From: zhangli20 <zhangli20@kuaishou.com>
33
Date: Tue, 19 Nov 2024 10:52:22 +0800
4-
Subject: [PATCH] blaze: use bufreader to read page header, avoid reading in
4+
Subject: [PATCH] auron: use bufreader to read page header, avoid reading in
55
fragments
66

77
---
@@ -16,10 +16,10 @@ index 9a985e885..2c994b9f0 100644
1616
@@ -87,7 +87,7 @@ pub trait MetadataSuffixFetch: MetadataFetch {
1717

1818
/// Sync version of get_bytes
19-
/// this is only used by blaze, for reading dictionary values for row group pruning
19+
/// this is only used by auron, for reading dictionary values for row group pruning
2020
- fn get_bytes_sync(&mut self, range: Range<usize>) -> Result<Bytes> {
2121
+ fn get_bytes_sync(&mut self, range: Range<u64>) -> Result<Bytes> {
22-
unimplemented!("blaze only")
22+
unimplemented!("auron only")
2323
}
2424
}
2525
diff --git a/parquet/src/bin/parquet-layout.rs b/parquet/src/bin/parquet-layout.rs
@@ -31,7 +31,7 @@ index 46a231a7d..26e22e1b2 100644
3131
}
3232

3333
- let input = reader.get_read(offset)?;
34-
+ // blaze: use BufReader to avoid reading in fragments
34+
+ // auron: use BufReader to avoid reading in fragments
3535
+ let input = std::io::BufReader::new(reader.get_read(offset)?);
3636
let mut tracked = TrackedRead(input, 0);
3737
let mut prot = TCompactInputProtocol::new(&mut tracked);

dev/vendors/patches/arrow-rs/0008-blaze-parquet-supports-processing-old-style-array-struct.patch renamed to dev/vendors/patches/arrow-rs/0008-auron-parquet-supports-processing-old-style-array-struct.patch

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -1,7 +1,7 @@
11
From 5de02520ca6c9f8f092b4b364906dc0507002cbb Mon Sep 17 00:00:00 2001
22
From: zhangli20 <zhangli20@kuaishou.com>
33
Date: Sat, 21 Dec 2024 02:16:53 +0800
4-
Subject: [PATCH] blaze: parquet supports processing old-style
4+
Subject: [PATCH] auron: parquet supports processing old-style
55
array<struct<..>> represented as `REPEATED group field_nme {..}`
66

77
---
@@ -20,7 +20,7 @@ index af70b8684..bf497fb77 100644
2020
- "incompatible arrow schema, expected struct got {}",
2121
- d
2222
- ))
23-
+ // blaze: match old-style array<struct<..>> represented as
23+
+ // auron: match old-style array<struct<..>> represented as
2424
+ // `REPEATED group field_nme {..}`
2525
+ let mut old_style_fields = None;
2626
+ if let DataType::List(f) = d {

dev/vendors/patches/datafusion/0001-blaze-update-arrow-dependency.patch renamed to dev/vendors/patches/datafusion/0001-auron-update-arrow-dependency.patch

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -1,7 +1,7 @@
11
From 0015 Mon Sep 17 00:00:00 2001
2-
From: blaze <blaze@example.com>
2+
From: auron <auron@example.com>
33
Date: Mon, 27 Jul 2026 02:26:00 +0800
4-
Subject: [PATCH] blaze: update arrow dependency to vendored v55.2.0-blaze
4+
Subject: [PATCH] auron: update arrow dependency to vendored v55.2.0-auron
55

66
---
77
Cargo.toml | 16 ++++++++++++++++
@@ -17,7 +17,7 @@ index 11cd3c637..b2fbf0df3 100644
1717
unused_qualifications = "deny"
1818
+
1919
+[patch.crates-io]
20-
+# arrow: vendored from v55.2.0-blaze
20+
+# arrow: vendored from v55.2.0-auron
2121
+arrow = { path = "../arrow-rs/arrow" }
2222
+arrow-arith = { path = "../arrow-rs/arrow-arith" }
2323
+arrow-array = { path = "../arrow-rs/arrow-array" }

0 commit comments

Comments
 (0)