diff --git a/.github/workflows/rust/sift_cli/v-release.yml b/.github/workflows/rust/sift_cli/v-release.yml new file mode 100644 index 0000000000..169a516d1e --- /dev/null +++ b/.github/workflows/rust/sift_cli/v-release.yml @@ -0,0 +1,296 @@ +# This file was autogenerated by dist: https://axodotdev.github.io/cargo-dist +# +# Copyright 2022-2024, axodotdev +# SPDX-License-Identifier: MIT or Apache-2.0 +# +# CI that: +# +# * checks for a Git Tag that looks like a release +# * builds artifacts with dist (archives, installers, hashes) +# * uploads those artifacts to temporary workflow zip +# * on success, uploads the artifacts to a GitHub Release +# +# Note that the GitHub Release will be created with a generated +# title/body based on your changelogs. + +name: Release +permissions: + "contents": "write" + +# This task will run whenever you push a git tag that looks like a version +# like "1.0.0", "v0.1.0-prerelease.1", "my-app/0.1.0", "releases/v1.0.0", etc. +# Various formats will be parsed into a VERSION and an optional PACKAGE_NAME, where +# PACKAGE_NAME must be the name of a Cargo package in your workspace, and VERSION +# must be a Cargo-style SemVer Version (must have at least major.minor.patch). +# +# If PACKAGE_NAME is specified, then the announcement will be for that +# package (erroring out if it doesn't have the given version or isn't dist-able). +# +# If PACKAGE_NAME isn't specified, then the announcement will be for all +# (dist-able) packages in the workspace with that version (this mode is +# intended for workspaces with only one dist-able package, or with all dist-able +# packages versioned/released in lockstep). +# +# If you push multiple tags at once, separate instances of this workflow will +# spin up, creating an independent announcement for each one. However, GitHub +# will hard limit this to 3 tags per commit, as it will assume more tags is a +# mistake. +# +# If there's a prerelease-style suffix to the version, then the release(s) +# will be marked as a prerelease. +on: + pull_request: + push: + tags: + - 'rust/sift_cli/v**[0-9]+.[0-9]+.[0-9]+*' + +jobs: + # Run 'dist plan' (or host) to determine what tasks we need to do + plan: + runs-on: "ubuntu-22.04" + outputs: + val: ${{ steps.plan.outputs.manifest }} + tag: ${{ !github.event.pull_request && github.ref_name || '' }} + tag-flag: ${{ !github.event.pull_request && format('--tag={0}', github.ref_name) || '' }} + publishing: ${{ !github.event.pull_request }} + env: + GH_TOKEN: ${{ secrets.GITHUB_TOKEN }} + steps: + - uses: actions/checkout@v4 + with: + persist-credentials: false + submodules: recursive + - name: Install dist + # we specify bash to get pipefail; it guards against the `curl` command + # failing. otherwise `sh` won't catch that `curl` returned non-0 + shell: bash + run: "curl --proto '=https' --tlsv1.2 -LsSf https://github.com/axodotdev/cargo-dist/releases/download/v0.29.0/cargo-dist-installer.sh | sh" + - name: Cache dist + uses: actions/upload-artifact@v4 + with: + name: cargo-dist-cache + path: ~/.cargo/bin/dist + # sure would be cool if github gave us proper conditionals... + # so here's a doubly-nested ternary-via-truthiness to try to provide the best possible + # functionality based on whether this is a pull_request, and whether it's from a fork. + # (PRs run on the *source* but secrets are usually on the *target* -- that's *good* + # but also really annoying to build CI around when it needs secrets to work right.) + - id: plan + run: | + dist ${{ (!github.event.pull_request && format('host --steps=create --tag={0}', github.ref_name)) || 'plan' }} --output-format=json > plan-dist-manifest.json + echo "dist ran successfully" + cat plan-dist-manifest.json + echo "manifest=$(jq -c "." plan-dist-manifest.json)" >> "$GITHUB_OUTPUT" + - name: "Upload dist-manifest.json" + uses: actions/upload-artifact@v4 + with: + name: artifacts-plan-dist-manifest + path: plan-dist-manifest.json + + # Build and packages all the platform-specific things + build-local-artifacts: + name: build-local-artifacts (${{ join(matrix.targets, ', ') }}) + # Let the initial task tell us to not run (currently very blunt) + needs: + - plan + if: ${{ fromJson(needs.plan.outputs.val).ci.github.artifacts_matrix.include != null && (needs.plan.outputs.publishing == 'true' || fromJson(needs.plan.outputs.val).ci.github.pr_run_mode == 'upload') }} + strategy: + fail-fast: false + # Target platforms/runners are computed by dist in create-release. + # Each member of the matrix has the following arguments: + # + # - runner: the github runner + # - dist-args: cli flags to pass to dist + # - install-dist: expression to run to install dist on the runner + # + # Typically there will be: + # - 1 "global" task that builds universal installers + # - N "local" tasks that build each platform's binaries and platform-specific installers + matrix: ${{ fromJson(needs.plan.outputs.val).ci.github.artifacts_matrix }} + runs-on: ${{ matrix.runner }} + container: ${{ matrix.container && matrix.container.image || null }} + env: + GH_TOKEN: ${{ secrets.GITHUB_TOKEN }} + BUILD_MANIFEST_NAME: target/distrib/${{ join(matrix.targets, '-') }}-dist-manifest.json + steps: + - name: enable windows longpaths + run: | + git config --global core.longpaths true + - uses: actions/checkout@v4 + with: + persist-credentials: false + submodules: recursive + - name: Install Rust non-interactively if not already installed + if: ${{ matrix.container }} + run: | + if ! command -v cargo > /dev/null 2>&1; then + curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y + echo "$HOME/.cargo/bin" >> $GITHUB_PATH + fi + - name: Install dist + run: ${{ matrix.install_dist.run }} + # Get the dist-manifest + - name: Fetch local artifacts + uses: actions/download-artifact@v4 + with: + pattern: artifacts-* + path: target/distrib/ + merge-multiple: true + - name: Install dependencies + run: | + ${{ matrix.packages_install }} + - name: Build artifacts + run: | + # Actually do builds and make zips and whatnot + dist build ${{ needs.plan.outputs.tag-flag }} --print=linkage --output-format=json ${{ matrix.dist_args }} > dist-manifest.json + echo "dist ran successfully" + - id: cargo-dist + name: Post-build + # We force bash here just because github makes it really hard to get values up + # to "real" actions without writing to env-vars, and writing to env-vars has + # inconsistent syntax between shell and powershell. + shell: bash + run: | + # Parse out what we just built and upload it to scratch storage + echo "paths<> "$GITHUB_OUTPUT" + dist print-upload-files-from-manifest --manifest dist-manifest.json >> "$GITHUB_OUTPUT" + echo "EOF" >> "$GITHUB_OUTPUT" + + cp dist-manifest.json "$BUILD_MANIFEST_NAME" + - name: "Upload artifacts" + uses: actions/upload-artifact@v4 + with: + name: artifacts-build-local-${{ join(matrix.targets, '_') }} + path: | + ${{ steps.cargo-dist.outputs.paths }} + ${{ env.BUILD_MANIFEST_NAME }} + + # Build and package all the platform-agnostic(ish) things + build-global-artifacts: + needs: + - plan + - build-local-artifacts + runs-on: "ubuntu-22.04" + env: + GH_TOKEN: ${{ secrets.GITHUB_TOKEN }} + BUILD_MANIFEST_NAME: target/distrib/global-dist-manifest.json + steps: + - uses: actions/checkout@v4 + with: + persist-credentials: false + submodules: recursive + - name: Install cached dist + uses: actions/download-artifact@v4 + with: + name: cargo-dist-cache + path: ~/.cargo/bin/ + - run: chmod +x ~/.cargo/bin/dist + # Get all the local artifacts for the global tasks to use (for e.g. checksums) + - name: Fetch local artifacts + uses: actions/download-artifact@v4 + with: + pattern: artifacts-* + path: target/distrib/ + merge-multiple: true + - id: cargo-dist + shell: bash + run: | + dist build ${{ needs.plan.outputs.tag-flag }} --output-format=json "--artifacts=global" > dist-manifest.json + echo "dist ran successfully" + + # Parse out what we just built and upload it to scratch storage + echo "paths<> "$GITHUB_OUTPUT" + jq --raw-output ".upload_files[]" dist-manifest.json >> "$GITHUB_OUTPUT" + echo "EOF" >> "$GITHUB_OUTPUT" + + cp dist-manifest.json "$BUILD_MANIFEST_NAME" + - name: "Upload artifacts" + uses: actions/upload-artifact@v4 + with: + name: artifacts-build-global + path: | + ${{ steps.cargo-dist.outputs.paths }} + ${{ env.BUILD_MANIFEST_NAME }} + # Determines if we should publish/announce + host: + needs: + - plan + - build-local-artifacts + - build-global-artifacts + # Only run if we're "publishing", and only if local and global didn't fail (skipped is fine) + if: ${{ always() && needs.plan.outputs.publishing == 'true' && (needs.build-global-artifacts.result == 'skipped' || needs.build-global-artifacts.result == 'success') && (needs.build-local-artifacts.result == 'skipped' || needs.build-local-artifacts.result == 'success') }} + env: + GH_TOKEN: ${{ secrets.GITHUB_TOKEN }} + runs-on: "ubuntu-22.04" + outputs: + val: ${{ steps.host.outputs.manifest }} + steps: + - uses: actions/checkout@v4 + with: + persist-credentials: false + submodules: recursive + - name: Install cached dist + uses: actions/download-artifact@v4 + with: + name: cargo-dist-cache + path: ~/.cargo/bin/ + - run: chmod +x ~/.cargo/bin/dist + # Fetch artifacts from scratch-storage + - name: Fetch artifacts + uses: actions/download-artifact@v4 + with: + pattern: artifacts-* + path: target/distrib/ + merge-multiple: true + - id: host + shell: bash + run: | + dist host ${{ needs.plan.outputs.tag-flag }} --steps=upload --steps=release --output-format=json > dist-manifest.json + echo "artifacts uploaded and released successfully" + cat dist-manifest.json + echo "manifest=$(jq -c "." dist-manifest.json)" >> "$GITHUB_OUTPUT" + - name: "Upload dist-manifest.json" + uses: actions/upload-artifact@v4 + with: + # Overwrite the previous copy + name: artifacts-dist-manifest + path: dist-manifest.json + # Create a GitHub Release while uploading all files to it + - name: "Download GitHub Artifacts" + uses: actions/download-artifact@v4 + with: + pattern: artifacts-* + path: artifacts + merge-multiple: true + - name: Cleanup + run: | + # Remove the granular manifests + rm -f artifacts/*-dist-manifest.json + - name: Create GitHub Release + env: + PRERELEASE_FLAG: "${{ fromJson(steps.host.outputs.manifest).announcement_is_prerelease && '--prerelease' || '' }}" + ANNOUNCEMENT_TITLE: "${{ fromJson(steps.host.outputs.manifest).announcement_title }}" + ANNOUNCEMENT_BODY: "${{ fromJson(steps.host.outputs.manifest).announcement_github_body }}" + RELEASE_COMMIT: "${{ github.sha }}" + run: | + # Write and read notes from a file to avoid quoting breaking things + echo "$ANNOUNCEMENT_BODY" > $RUNNER_TEMP/notes.txt + + gh release create "${{ needs.plan.outputs.tag }}" --target "$RELEASE_COMMIT" $PRERELEASE_FLAG --title "$ANNOUNCEMENT_TITLE" --notes-file "$RUNNER_TEMP/notes.txt" artifacts/* + + announce: + needs: + - plan + - host + # use "always() && ..." to allow us to wait for all publish jobs while + # still allowing individual publish jobs to skip themselves (for prereleases). + # "host" however must run to completion, no skipping allowed! + if: ${{ always() && needs.host.result == 'success' }} + runs-on: "ubuntu-22.04" + env: + GH_TOKEN: ${{ secrets.GITHUB_TOKEN }} + steps: + - uses: actions/checkout@v4 + with: + persist-credentials: false + submodules: recursive diff --git a/.github/workflows/sift_cli_release.yaml b/.github/workflows/sift_cli_release.yaml new file mode 100644 index 0000000000..cb94357b63 --- /dev/null +++ b/.github/workflows/sift_cli_release.yaml @@ -0,0 +1,204 @@ +name: sift_cli release +permissions: + contents: write + +on: + pull_request: + push: + tags: + - 'rust/sift_cli/v*.*.*' + - 'rust/sift_cli/v*.*.*-*' + +jobs: + plan: + runs-on: ubuntu-22.04 + outputs: + val: ${{ steps.plan.outputs.manifest }} + tag: ${{ !github.event.pull_request && github.ref_name || '' }} + tag-flag: ${{ !github.event.pull_request && format('--tag={0}', github.ref_name) || '' }} + publishing: ${{ !github.event.pull_request }} + env: + GH_TOKEN: ${{ secrets.GITHUB_TOKEN }} + steps: + - uses: actions/checkout@v4 + with: + persist-credentials: false + submodules: recursive + + - name: Install dist + run: curl --proto '=https' --tlsv1.2 -LsSf https://github.com/axodotdev/cargo-dist/releases/download/v0.29.0/cargo-dist-installer.sh | sh + + - id: plan + name: Run dist plan + working-directory: rust + run: dist ${{ (!github.event.pull_request && format('host --steps=create --tag={0}', github.ref_name)) || 'plan' }} --output-format=json > plan-dist-manifest.json + shell: bash + + - name: Upload dist-manifest.json + uses: actions/upload-artifact@v4 + with: + name: artifacts-plan-dist-manifest + path: rust/plan-dist-manifest.json + + build-local-artifacts: + name: build-local-artifacts (${{ join(matrix.targets, ', ') }}) + needs: [plan] + if: ${{ fromJson(needs.plan.outputs.val).ci.github.artifacts_matrix.include != null && (needs.plan.outputs.publishing == 'true' || fromJson(needs.plan.outputs.val).ci.github.pr_run_mode == 'upload') }} + strategy: + fail-fast: false + matrix: ${{ fromJson(needs.plan.outputs.val).ci.github.artifacts_matrix }} + runs-on: ${{ matrix.runner }} + container: ${{ matrix.container && matrix.container.image || null }} + env: + GH_TOKEN: ${{ secrets.GITHUB_TOKEN }} + BUILD_MANIFEST_NAME: target/distrib/${{ join(matrix.targets, '-') }}-dist-manifest.json + steps: + - name: enable windows longpaths + run: git config --global core.longpaths true + + - uses: actions/checkout@v4 + with: + persist-credentials: false + submodules: recursive + + - name: Install Rust non-interactively if not already installed + if: ${{ matrix.container }} + run: | + if ! command -v cargo > /dev/null 2>&1; then + curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y + echo "$HOME/.cargo/bin" >> $GITHUB_PATH + fi + + - name: Install dist + run: curl --proto '=https' --tlsv1.2 -LsSf https://github.com/axodotdev/cargo-dist/releases/download/v0.29.0/cargo-dist-installer.sh | sh + + - name: Fetch local artifacts + uses: actions/download-artifact@v4 + with: + pattern: artifacts-* + path: target/distrib/ + merge-multiple: true + + - name: Install dependencies + run: ${{ matrix.packages_install }} + + - name: Build artifacts + working-directory: rust + run: dist build ${{ needs.plan.outputs.tag-flag }} --print=linkage --output-format=json ${{ matrix.dist_args }} > dist-manifest.json + shell: bash + + - id: cargo-dist + name: Post-build + shell: bash + working-directory: rust + run: | + echo "paths<> "$GITHUB_OUTPUT" + dist print-upload-files-from-manifest --manifest dist-manifest.json >> "$GITHUB_OUTPUT" + echo "EOF" >> "$GITHUB_OUTPUT" + cp dist-manifest.json "$BUILD_MANIFEST_NAME" + + - name: Upload artifacts + uses: actions/upload-artifact@v4 + with: + name: artifacts-build-local-${{ join(matrix.targets, '_') }} + path: | + rust/${{ steps.cargo-dist.outputs.paths }} + rust/${{ env.BUILD_MANIFEST_NAME }} + + build-global-artifacts: + needs: [plan, build-local-artifacts] + runs-on: ubuntu-22.04 + env: + GH_TOKEN: ${{ secrets.GITHUB_TOKEN }} + BUILD_MANIFEST_NAME: target/distrib/global-dist-manifest.json + steps: + - uses: actions/checkout@v4 + with: + persist-credentials: false + submodules: recursive + + - name: Install dist + run: curl --proto '=https' --tlsv1.2 -LsSf https://github.com/axodotdev/cargo-dist/releases/download/v0.29.0/cargo-dist-installer.sh | sh + + - name: Fetch local artifacts + uses: actions/download-artifact@v4 + with: + pattern: artifacts-* + path: target/distrib/ + merge-multiple: true + + - id: cargo-dist + shell: bash + working-directory: rust + run: dist build ${{ needs.plan.outputs.tag-flag }} --output-format=json "--artifacts=global" > dist-manifest.json + env: + GH_TOKEN: ${{ secrets.GITHUB_TOKEN }} + + - name: Upload artifacts + uses: actions/upload-artifact@v4 + with: + name: artifacts-build-global + path: | + rust/${{ steps.cargo-dist.outputs.paths }} + rust/${{ env.BUILD_MANIFEST_NAME }} + + host: + needs: [plan, build-local-artifacts, build-global-artifacts] + if: ${{ always() && needs.plan.outputs.publishing == 'true' && (needs.build-global-artifacts.result == 'skipped' || needs.build-global-artifacts.result == 'success') && (needs.build-local-artifacts.result == 'skipped' || needs.build-local-artifacts.result == 'success') }} + runs-on: ubuntu-22.04 + env: + GH_TOKEN: ${{ secrets.GITHUB_TOKEN }} + outputs: + val: ${{ steps.host.outputs.manifest }} + steps: + - uses: actions/checkout@v4 + with: + persist-credentials: false + submodules: recursive + + - name: Install dist + run: curl --proto '=https' --tlsv1.2 -LsSf https://github.com/axodotdev/cargo-dist/releases/download/v0.29.0/cargo-dist-installer.sh | sh + + - name: Fetch artifacts + uses: actions/download-artifact@v4 + with: + pattern: artifacts-* + path: target/distrib/ + merge-multiple: true + + - id: host + shell: bash + working-directory: rust + run: dist host ${{ needs.plan.outputs.tag-flag }} --steps=upload --steps=release --output-format=json > dist-manifest.json + + - name: Upload dist-manifest.json + uses: actions/upload-artifact@v4 + with: + name: artifacts-dist-manifest + path: rust/dist-manifest.json + + - name: Create GitHub Release + working-directory: rust + run: | + PRERELEASE_FLAG=$(jq -r '.announcement_is_prerelease | if . then "--prerelease" else "" end' dist-manifest.json) + ANNOUNCEMENT_TITLE=$(jq -r '.announcement_title' dist-manifest.json) + ANNOUNCEMENT_BODY=$(jq -r '.announcement_github_body' dist-manifest.json) + RELEASE_COMMIT="${{ github.sha }}" + NOTES_FILE="$(mktemp)" + echo "$ANNOUNCEMENT_BODY" > "$NOTES_FILE" + gh release create "${{ needs.plan.outputs.tag }}" --target "$RELEASE_COMMIT" $PRERELEASE_FLAG --title "$ANNOUNCEMENT_TITLE" --notes-file "$NOTES_FILE" target/distrib/* + + announce: + needs: [plan, host] + if: ${{ always() && needs.host.result == 'success' }} + runs-on: ubuntu-22.04 + env: + GH_TOKEN: ${{ secrets.GITHUB_TOKEN }} + steps: + - uses: actions/checkout@v4 + with: + persist-credentials: false + submodules: recursive + - name: Announce dist + working-directory: rust + run: echo "Announcement completed (placeholder step)" diff --git a/rust/Cargo.lock b/rust/Cargo.lock index b30eb07e15..7fc8c694c9 100644 --- a/rust/Cargo.lock +++ b/rust/Cargo.lock @@ -2960,7 +2960,7 @@ dependencies = [ [[package]] name = "sift_cli" -version = "0.6.0" +version = "0.1.0-alpha.1" dependencies = [ "anyhow", "chrono", diff --git a/rust/Cargo.toml b/rust/Cargo.toml index 339e2dfe81..32021df2b3 100644 --- a/rust/Cargo.toml +++ b/rust/Cargo.toml @@ -15,8 +15,8 @@ authors = ["Sift Software Engineers "] version = "0.6.0" edition = "2024" categories = ["aerospace", "science::robotics"] -homepage = "https://github.com/sift-stack/sift/tree/main/rust" -repository = "https://github.com/sift-stack/sift/tree/main/rust" +homepage = "https://github.com/sift-stack/sift" +repository = "https://github.com/sift-stack/sift" keywords = ["sift", "siftstack", "sift-stack", "sift_rs", "telemetry"] readme = "README.md" license = "MIT" @@ -32,3 +32,8 @@ sift_error = { version = "0.6.0", path = "crates/sift_error" } sift_stream = { version = "0.6.0", path = "crates/sift_stream" } sift_stream_bindings = { version = "0.1.0", path = "crates/sift_stream_bindings" } + +# The profile that 'dist' will build with +[profile.dist] +inherits = "release" +lto = "thin" diff --git a/rust/README.md b/rust/README.md new file mode 100644 index 0000000000..ab16f5c790 --- /dev/null +++ b/rust/README.md @@ -0,0 +1 @@ +# Sift Crates diff --git a/rust/crates/sift_cli/Cargo.toml b/rust/crates/sift_cli/Cargo.toml index 218f906ef6..008f21273e 100644 --- a/rust/crates/sift_cli/Cargo.toml +++ b/rust/crates/sift_cli/Cargo.toml @@ -1,7 +1,7 @@ [package] name = "sift_cli" -authors.workspace = true -version.workspace = true +version = "0.1.0-alpha.1" +uthors.workspace = true edition.workspace = true categories.workspace = true homepage.workspace = true diff --git a/rust/crates/sift_cli/src/cmd/import/parquet/mod.rs b/rust/crates/sift_cli/src/cmd/import/parquet/mod.rs index ae18fb6c84..123d716f49 100644 --- a/rust/crates/sift_cli/src/cmd/import/parquet/mod.rs +++ b/rust/crates/sift_cli/src/cmd/import/parquet/mod.rs @@ -1,57 +1,126 @@ -use anyhow::{Result, anyhow}; -use std::{ - fs::File, - io::{Read, Seek, SeekFrom}, - os::unix::fs::FileExt, -}; +#[cfg(not(target_os = "windows"))] +use unix::{FooterMetadata, get_footer}; + +#[cfg(target_os = "windows")] +use windows::{FooterMetadata, get_footer}; pub mod flat_dataset; -/// Metadata about the Parquet's footer -#[derive(Copy, Clone)] -struct FooterMetadata { - /// Offset to the Parquet file's footer - offset: u64, - /// Length of the Parquet file's footer - length: u64, -} +#[cfg(not(target_os = "windows"))] +mod unix { + use anyhow::{Result, anyhow}; + use std::{ + fs::File, + io::{Read, Seek, SeekFrom}, + os::unix::fs::FileExt, + }; -fn get_footer(file: &mut File, footer_metadata: FooterMetadata) -> Result> { - let FooterMetadata { length, offset } = footer_metadata; - let mut buf = vec![0u8; length as usize]; - file.read_exact_at(&mut buf, offset)?; - Ok(buf) -} + /// Metadata about the Parquet's footer + #[derive(Copy, Clone)] + pub struct FooterMetadata { + /// Offset to the Parquet file's footer + pub offset: u64, + /// Length of the Parquet file's footer + pub length: u64, + } + + pub fn get_footer(file: &mut File, footer_metadata: FooterMetadata) -> Result> { + let FooterMetadata { length, offset } = footer_metadata; + let mut buf = vec![0u8; length as usize]; + file.read_exact_at(&mut buf, offset)?; + Ok(buf) + } + + /// Note that this will advance the cursor. + impl TryFrom<&mut File> for FooterMetadata { + type Error = anyhow::Error; + + fn try_from(file: &mut File) -> Result { + file.seek(SeekFrom::End(-8))?; -/// Note that this will advance the cursor. -impl TryFrom<&mut File> for FooterMetadata { - type Error = anyhow::Error; + let footer_len = { + let mut buf = [0u8; 4]; + file.read_exact(&mut buf)?; + u32::from_le_bytes(buf) + }; - fn try_from(file: &mut File) -> Result { - file.seek(SeekFrom::End(-8))?; + let mut magic = [0u8; 4]; + file.read_exact(&mut magic)?; + if &magic != b"PAR1" { + return Err(anyhow!("invalid Parquet magic bytes")); + } - let footer_len = { - let mut buf = [0u8; 4]; - file.read_exact(&mut buf)?; - u32::from_le_bytes(buf) - }; + let file_len = file.metadata()?.len(); + if u64::from(footer_len) + 8 > file_len { + return Err(anyhow!( + "footer length ({footer_len}) exceeds file size ({file_len})", + )); + } - let mut magic = [0u8; 4]; - file.read_exact(&mut magic)?; - if &magic != b"PAR1" { - return Err(anyhow!("invalid Parquet magic bytes")); + Ok(Self { + offset: file_len - u64::from(footer_len) - 8, + length: u64::from(footer_len), + }) } + } +} - let file_len = file.metadata()?.len(); - if u64::from(footer_len) + 8 > file_len { - return Err(anyhow!( - "footer length ({footer_len}) exceeds file size ({file_len})", - )); +#[cfg(target_os = "windows")] +mod windows { + use anyhow::{Result, anyhow}; + use std::{ + fs::File, + io::{Read, Seek, SeekFrom}, + os::windows::fs::FileExt, + }; + + /// Metadata about the Parquet's footer + #[derive(Copy, Clone)] + pub struct FooterMetadata { + pub offset: u64, + pub length: u64, + } + + pub fn get_footer(file: &mut File, footer_metadata: FooterMetadata) -> Result> { + let FooterMetadata { length, offset } = footer_metadata; + let mut buf = vec![0u8; length as usize]; + // On Windows, use `seek_read` to read without moving the main file cursor + let bytes_read = file.seek_read(&mut buf, offset)?; + if bytes_read != buf.len() { + return Err(anyhow!("incomplete footer read")); } + Ok(buf) + } + + impl TryFrom<&mut File> for FooterMetadata { + type Error = anyhow::Error; - Ok(Self { - offset: file_len - u64::from(footer_len) - 8, - length: u64::from(footer_len), - }) + fn try_from(file: &mut File) -> Result { + file.seek(SeekFrom::End(-8))?; + + let footer_len = { + let mut buf = [0u8; 4]; + file.read_exact(&mut buf)?; + u32::from_le_bytes(buf) + }; + + let mut magic = [0u8; 4]; + file.read_exact(&mut magic)?; + if &magic != b"PAR1" { + return Err(anyhow!("invalid Parquet magic bytes")); + } + + let file_len = file.metadata()?.len(); + if u64::from(footer_len) + 8 > file_len { + return Err(anyhow!( + "footer length ({footer_len}) exceeds file size ({file_len})", + )); + } + + Ok(Self { + offset: file_len - u64::from(footer_len) - 8, + length: u64::from(footer_len), + }) + } } } diff --git a/rust/dist-workspace.toml b/rust/dist-workspace.toml new file mode 100644 index 0000000000..cea19c0933 --- /dev/null +++ b/rust/dist-workspace.toml @@ -0,0 +1,19 @@ +[workspace] +members = ["cargo:crates/sift_cli"] + +[dist] +cargo-dist-version = "0.29.0" +tag-namespace = "rust/sift_cli/v" +ci = "github" +installers = ["shell"] +targets = [ + "aarch64-apple-darwin", + "x86_64-apple-darwin", + "x86_64-pc-windows-msvc", + "x86_64-unknown-linux-gnu", + + # Unfortunately we need openssl: https://github.com/axodotdev/cargo-dist/issues/786 + # "aarch64-unknown-linux-gnu", +] +install-path = "CARGO_HOME" +install-updater = false