Skip to content

chore: Adds SerializedFileReader::new_with_metadata to avoid reading metadata from file on every invocation #3 #4

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
cristipp merged 8 commits into from
Apr 26, 2022
Merged

chore: Adds SerializedFileReader::new_with_metadata to avoid reading metadata from file on every invocation #3 #4

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
4fa2c17
ok
cristipp Mar 31, 2022
05010e9
ok
cristipp Mar 31, 2022
d75ea46
ok
cristipp Mar 31, 2022
5dbc9fd
ok
cristipp Mar 31, 2022
9c870d4
ok
cristipp Mar 31, 2022
b259d1e
ok
cristipp Mar 31, 2022
933188d
ok
cristipp Mar 31, 2022
f485d75
ok
cristipp Apr 26, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 7 additions & 7 deletions .github/workflows/rust.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -31,7 +31,7 @@ jobs:
strategy:
matrix:
arch: [amd64]
rust: [stable]
rust: [nightly-2021-07-04]
container:
image: ${{ matrix.arch }}/rust
env:
Expand Down Expand Up @@ -73,7 +73,7 @@ jobs:
strategy:
matrix:
arch: [amd64]
rust: [stable]
rust: [nightly-2021-07-04]
container:
image: ${{ matrix.arch }}/rust
env:
Expand Down Expand Up @@ -126,7 +126,7 @@ jobs:
strategy:
matrix:
arch: [amd64]
rust: [nightly-2021-07-04]
rust: []
container:
image: ${{ matrix.arch }}/rust
env:
Expand Down Expand Up @@ -174,7 +174,7 @@ jobs:
strategy:
matrix:
os: [windows-latest, macos-latest]
rust: [stable]
rust: [nightly-2021-07-04]
steps:
- uses: actions/checkout@v2
with:
Expand Down Expand Up @@ -202,7 +202,7 @@ jobs:
strategy:
matrix:
arch: [amd64]
rust: [stable]
rust: [nightly-2021-07-04]
container:
image: ${{ matrix.arch }}/rust
env:
Expand Down Expand Up @@ -257,7 +257,7 @@ jobs:
strategy:
matrix:
arch: [amd64]
rust: [stable]
rust: [nightly-2021-07-04]
steps:
- uses: actions/checkout@v2
with:
Expand Down Expand Up @@ -341,7 +341,7 @@ jobs:
strategy:
matrix:
arch: [amd64]
rust: [stable]
rust: [nightly-2021-07-04]
container:
image: ${{ matrix.arch }}/rust
env:
Expand Down
60 changes: 40 additions & 20 deletions arrow/src/compute/kernels/comparison.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -262,18 +262,28 @@ fn like_utf8_impl<OffsetSize: StringOffsetSizeTrait>(
regex
} else {
let mut prev_char = None;
let mut re_pattern = pat.replace(|c| {
let res = c == '%' && prev_char != Some('\\');
prev_char = Some(c);
res
}, ".*").replace("\\%", "%");
let mut re_pattern = pat
.replace(
|c| {
let res = c == '%' && prev_char != Some('\\');
prev_char = Some(c);
res
},
".*",
)
.replace("\\%", "%");

let mut prev_char = None;
re_pattern = re_pattern.replace(|c| {
let res = c == '_' && prev_char != Some('\\');
prev_char = Some(c);
res
}, ".").replace("\\_", "_");
re_pattern = re_pattern
.replace(
|c| {
let res = c == '_' && prev_char != Some('\\');
prev_char = Some(c);
res
},
".",
)
.replace("\\_", "_");
let re = RegexBuilder::new(&format!("^{}$", re_pattern))
.case_insensitive(!case_sensitive)
.build()
Expand Down Expand Up @@ -383,18 +393,28 @@ fn like_utf8_scalar_impl<OffsetSize: StringOffsetSizeTrait>(
}
} else {
let mut prev_char = None;
let mut re_pattern = right.replace(|c| {
let res = c == '%' && prev_char != Some('\\');
prev_char = Some(c);
res
}, ".*").replace("\\%", "%");
let mut re_pattern = right
.replace(
|c| {
let res = c == '%' && prev_char != Some('\\');
prev_char = Some(c);
res
},
".*",
)
.replace("\\%", "%");

let mut prev_char = None;
re_pattern = re_pattern.replace(|c| {
let res = c == '_' && prev_char != Some('\\');
prev_char = Some(c);
res
}, ".").replace("\\_", "_");
re_pattern = re_pattern
.replace(
|c| {
let res = c == '_' && prev_char != Some('\\');
prev_char = Some(c);
res
},
".",
)
.replace("\\_", "_");
let re = RegexBuilder::new(&format!("^{}$", re_pattern))
.case_insensitive(!case_sensitive)
.build()
Expand Down
8 changes: 8 additions & 0 deletions parquet/src/file/serialized_reader.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -138,6 +138,14 @@ impl<R: 'static + ChunkReader> SerializedFileReader<R> {
})
}

/// Creates file reader from a Parquet file, using pre-read metadata.
pub fn new_with_metadata(chunk_reader: R, metadata: ParquetMetaData) -> Self {
Self {
chunk_reader: Arc::new(chunk_reader),
metadata,
}
}

/// Filters row group metadata to only those row groups,
/// for which the predicate function returns true
pub fn filter_row_groups(
Expand Down