Merge branch 'main' into feature/fix-whitespace-before-offset

Author: thomaskrause

.github/workflows/release.yml

@@ -1,20 +1,19 @@
-# Copyright 2022-2023, axodotdev
+# 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 cargo-dist (archives, installers, hashes)
 # * uploads those artifacts to temporary workflow zip
-# * on success, uploads the artifacts to a Github Release
+# * on success, uploads the artifacts to a GitHub Release
 #
-# Note that the Github Release will be created with a generated
+# Note that the GitHub Release will be created with a generated
 # title/body based on your changelogs.
 
 name: Release
-
 permissions:
-  contents: write
+  "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.
@@ -31,22 +30,22 @@ permissions:
 # 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
+# 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:
       - '**[0-9]+.[0-9]+.[0-9]+*'
-  pull_request:
 
 jobs:
   # Run 'cargo dist plan' (or host) to determine what tasks we need to do
   plan:
-    runs-on: ubuntu-latest
+    runs-on: "ubuntu-20.04"
     outputs:
       val: ${{ steps.plan.outputs.manifest }}
       tag: ${{ !github.event.pull_request && github.ref_name || '' }}
@@ -62,7 +61,12 @@ jobs:
         # 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/v0.11.1/cargo-dist-installer.sh | sh"
+        run: "curl --proto '=https' --tlsv1.2 -LsSf https://github.com/axodotdev/cargo-dist/releases/download/v0.18.0/cargo-dist-installer.sh | sh"
+      - name: Cache cargo-dist
+        uses: actions/upload-artifact@v4
+        with:
+          name: cargo-dist-cache
+          path: ~/.cargo/bin/cargo-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.
@@ -105,10 +109,12 @@ jobs:
       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:
           submodules: recursive
-      - uses: swatinem/rust-cache@v2
       - name: Install cargo-dist
         run: ${{ matrix.install_dist }}
       # Get the dist-manifest
@@ -135,7 +141,7 @@ jobs:
         run: |
           # Parse out what we just built and upload it to scratch storage
           echo "paths<<EOF" >> "$GITHUB_OUTPUT"
-          jq --raw-output ".artifacts[]?.path | select( . != null )" dist-manifest.json >> "$GITHUB_OUTPUT"
+          jq --raw-output ".upload_files[]" dist-manifest.json >> "$GITHUB_OUTPUT"
           echo "EOF" >> "$GITHUB_OUTPUT"
 
           cp dist-manifest.json "$BUILD_MANIFEST_NAME"
@@ -160,9 +166,12 @@ jobs:
       - uses: actions/checkout@v4
         with:
           submodules: recursive
-      - name: Install cargo-dist
-        shell: bash
-        run: "curl --proto '=https' --tlsv1.2 -LsSf https://github.com/axodotdev/cargo-dist/releases/download/v0.11.1/cargo-dist-installer.sh | sh"
+      - name: Install cached cargo-dist
+        uses: actions/download-artifact@v4
+        with:
+          name: cargo-dist-cache
+          path: ~/.cargo/bin/
+      - run: chmod +x ~/.cargo/bin/cargo-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
@@ -178,7 +187,7 @@ jobs:
 
           # Parse out what we just built and upload it to scratch storage
           echo "paths<<EOF" >> "$GITHUB_OUTPUT"
-          jq --raw-output ".artifacts[]?.path | select( . != null )" dist-manifest.json >> "$GITHUB_OUTPUT"
+          jq --raw-output ".upload_files[]" dist-manifest.json >> "$GITHUB_OUTPUT"
           echo "EOF" >> "$GITHUB_OUTPUT"
 
           cp dist-manifest.json "$BUILD_MANIFEST_NAME"
@@ -206,16 +215,19 @@ jobs:
       - uses: actions/checkout@v4
         with:
           submodules: recursive
-      - name: Install cargo-dist
-        run: "curl --proto '=https' --tlsv1.2 -LsSf https://github.com/axodotdev/cargo-dist/releases/download/v0.11.1/cargo-dist-installer.sh | sh"
+      - name: Install cached cargo-dist
+        uses: actions/download-artifact@v4
+        with:
+          name: cargo-dist-cache
+          path: ~/.cargo/bin/
+      - run: chmod +x ~/.cargo/bin/cargo-dist
       # Fetch artifacts from scratch-storage
       - name: Fetch artifacts
         uses: actions/download-artifact@v4
         with:
           pattern: artifacts-*
           path: target/distrib/
           merge-multiple: true
-      # This is a harmless no-op for Github Releases, hosting for that happens in "announce"
       - id: host
         shell: bash
         run: |
@@ -229,8 +241,29 @@ jobs:
           # Overwrite the previous copy
           name: artifacts-dist-manifest
           path: dist-manifest.json
+      # Create a GitHub Release while uploading all files to it
+      - name: "Download GitHub Artifacts"
+        uses: actions/download-artifact@v4
+        with:
+          pattern: artifacts-*
+          path: artifacts
+          merge-multiple: true
+      - name: Cleanup
+        run: |
+          # Remove the granular manifests
+          rm -f artifacts/*-dist-manifest.json
+      - name: Create GitHub Release
+        env:
+          PRERELEASE_FLAG: "${{ 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/*
 
-  # Create a Github Release while uploading all files to it
   announce:
     needs:
       - plan
@@ -246,21 +279,3 @@ jobs:
       - uses: actions/checkout@v4
         with:
           submodules: recursive
-      - 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
-        uses: ncipollo/release-action@v1
-        with:
-          tag: ${{ needs.plan.outputs.tag }}
-          name: ${{ fromJson(needs.host.outputs.val).announcement_title }}
-          body: ${{ fromJson(needs.host.outputs.val).announcement_github_body }}
-          prerelease: ${{ fromJson(needs.host.outputs.val).announcement_is_prerelease }}
-          artifacts: "artifacts/*"

.github/workflows/release_capi.yml

@@ -1,12 +1,17 @@
 on:
   release:
     types: [published]
+  workflow_run:
+    workflows: 
+      - Release
+    types: 
+      - completed
   pull_request:
     types: [labeled]
 name: Append C-API artifact to latest release
 jobs:
   deploy_linux_binaries:
-    if: ${{ github.event.label.name == 'test-release-process' || github.event_name == 'release' }}
+    if: ${{ github.event.action == 'completed' || github.event.label.name == 'test-release-process' || (github.event_name == 'release' && github.event.action == 'published') }}
     runs-on: ubuntu-20.04
     env:
       GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
@@ -35,7 +40,7 @@ jobs:
           omitNameDuringUpdate: true
           omitPrereleaseDuringUpdate: true
   deploy_windows_binaries:
-    if: ${{ github.event.label.name == 'test-release-process' || github.event_name == 'release' }}
+    if: ${{ github.event.action == 'completed' || github.event.label.name == 'test-release-process' || (github.event_name == 'release' && github.event.action == 'published') }}
     runs-on: windows-2019
     steps:
       - id: latest-release
@@ -62,8 +67,8 @@ jobs:
           omitNameDuringUpdate: true
           omitPrereleaseDuringUpdate: true
   deploy_macos_binaries:
-    if: ${{ github.event.label.name == 'test-release-process' || github.event_name == 'release' }}
-    runs-on: macos-11
+    if: ${{ github.event.action == 'completed' || github.event.label.name == 'test-release-process' || (github.event_name == 'release' && github.event.action == 'published') }}
+    runs-on: macos-12
     steps:
       - id: latest-release
         uses: pozetroninc/github-action-get-latest-release@v0.7.0

.github/workflows/test.yml

@@ -36,7 +36,7 @@ jobs:
           RUST_LOG: debug
   test_mac:
     name: Execute automated tests on OSX
-    runs-on: macos-11
+    runs-on: macos-12
     steps:
       - uses: actions/checkout@v2
       - uses: actions-rust-lang/setup-rust-toolchain@v1.8.0

CHANGELOG.md

@@ -5,6 +5,11 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+### Fixed
+
+- Load existing components from the backup folder instead of the actual location
+  if a backup folder exists.
+
 ## [3.3.1] - 2024-06-04
 
 ### Fixed

Cargo.toml

@@ -12,9 +12,9 @@ resolver = "2"
 # Config for 'cargo dist'
 [workspace.metadata.dist]
 # The preferred cargo-dist version to use in CI (Cargo.toml SemVer syntax)
-cargo-dist-version = "0.11.1"
+cargo-dist-version = "0.18.0"
 # CI backends to support
-ci = ["github"]
+ci = "github"
 # The installers to generate for each app
 installers = []
 # Target platforms to build apps for (Rust target-triple syntax)

core/src/graph/mod.rs

@@ -99,8 +99,13 @@ fn component_path<CT: ComponentType>(
     match location {
         Some(ref loc) => {
             let mut p = PathBuf::from(loc);
-            // don't use the backup-folder per default
-            p.push("current");
+            // Check if we need to load the component from the backup folder
+            let backup = loc.join("backup");
+            if backup.exists() {
+                p.push("backup");
+            } else {
+                p.push("current");
+            }
             p.push(component_to_relative_path(c));
             Some(p)
         }
@@ -166,11 +171,12 @@ impl<CT: ComponentType> Graph<CT> {
         let location = PathBuf::from(location);
 
         self.set_location(location.as_path())?;
+
         let backup = location.join("backup");
 
-        let mut backup_was_loaded = false;
+        let mut load_from_backup = false;
         let dir2load = if backup.exists() && backup.is_dir() {
-            backup_was_loaded = true;
+            load_from_backup = true;
             backup.clone()
         } else {
             location.join("current")
@@ -207,7 +213,7 @@ impl<CT: ComponentType> Graph<CT> {
         self.find_components_from_disk(&dir2load)?;
 
         // If backup is active or a write log exists, always  a pre-load to get the complete corpus.
-        if preload | logfile_exists | backup_was_loaded {
+        if preload | logfile_exists | load_from_backup {
             self.ensure_loaded_all()?;
         }
 
@@ -220,7 +226,7 @@ impl<CT: ComponentType> Graph<CT> {
             self.current_change_id = 0;
         }
 
-        if backup_was_loaded {
+        if load_from_backup {
             // save the current corpus under the actual location
             self.save_to(&location.join("current"))?;
             // rename backup folder (renaming is atomic and deleting could leave an incomplete backup folder on disk)

graphannis/Cargo.toml

@@ -15,7 +15,7 @@ crate-type = ["lib"]
 [build-dependencies]
 csv = "1.1"
 file_diff = "1"
-lalrpop = {version = "0.20", default_features = false, features = ["lexer", "unicode"]}
+lalrpop = {version = "0.20", default-features = false, features = ["lexer", "unicode"]}
 regex = "1"
 
 [dependencies]

graphannis/src/annis/db/aql/conjunction.rs

@@ -64,7 +64,6 @@ pub struct NodeSearchSpecEntry {
     pub var: String,
     pub spec: NodeSearchSpec,
     pub optional: bool,
-    pub location: Option<LineColumnRange>,
 }
 
 #[derive(Debug)]
@@ -298,7 +297,6 @@ impl Conjunction {
             var: variable.clone(),
             spec: node,
             optional,
-            location: location.clone(),
         });
 
         if included_in_output && !optional {

graphannis/src/annis/db/aql/mod.rs

@@ -196,8 +196,6 @@ fn map_conjunction(
             if negated {
                 if !node_left.optional && !node_right.optional {
                     op_spec = Arc::new(NegatedOpSpec {
-                        spec_left: node_left.spec.clone(),
-                        spec_right: node_right.spec.clone(),
                         negated_op: op_spec,
                     });
                     q.add_operator_from_query(op_spec, &var_left, &var_right, op_pos, !quirks_mode)?

graphannis/src/annis/db/aql/operators/negated_op.rs

@@ -2,7 +2,7 @@ use std::{fmt::Display, sync::Arc};
 
 use crate::{
     annis::{
-        db::exec::{nodesearch::NodeSearchSpec, CostEstimate},
+        db::exec::CostEstimate,
         operator::{BinaryOperator, BinaryOperatorBase, BinaryOperatorSpec, EstimationType},
     },
     errors::Result,
@@ -12,8 +12,6 @@ use graphannis_core::annostorage::Match;
 
 #[derive(Debug)]
 pub struct NegatedOpSpec {
-    pub spec_left: NodeSearchSpec,
-    pub spec_right: NodeSearchSpec,
     pub negated_op: Arc<dyn BinaryOperatorSpec>,
 }