zhconv-rs-opencc 0.3.3__tar.gz → 0.4.1__tar.gz

{zhconv_rs_opencc-0.3.3 → zhconv_rs_opencc-0.4.1}/.cloudflare/setup-pages-env.sh

@@ -1,10 +1,12 @@
 #!/bin/sh
 set -eu
-npm install --global yarn || true
+# In Pages build environment version 3, the default is yarn berry. 
+# npm install --global yarn || true
+yarn --version
 
 curl -o rustup.sh https://sh.rustup.rs
 chmod +x rustup.sh
-./rustup.sh -y --default-toolchain 1.81.0 # blocked by https://github.com/rustwasm/wasm-bindgen/issues/4211
+./rustup.sh -y # --default-toolchain 1.81.0
 
 . $HOME/.cargo/env
 curl -o wasm-init.sh https://rustwasm.github.io/wasm-pack/installer/init.sh

zhconv_rs_opencc-0.4.1/.deepsource.toml

@@ -0,0 +1,19 @@
+version = 1
+
+[[analyzers]]
+name = "python"
+
+  [analyzers.meta]
+  runtime_version = "3.x.x"
+
+[[analyzers]]
+name = "rust"
+
+  [analyzers.meta]
+  msrv = "stable"
+
+[[code_formatters]]
+name = "black"
+
+[[code_formatters]]
+name = "rustfmt"

{zhconv_rs_opencc-0.3.3 → zhconv_rs_opencc-0.4.1}/.gitattributes

@@ -6,3 +6,7 @@ data/*.txt linguist-vendored binary
 data/cgroups/*.json linguist-vendored
 web/public/cgroups.json linguist-vendored
 benches/*.txt linguist-vendored
+
+# disable CRLF conversion
+data/ZhConversion.php binary
+data/*.txt binary

zhconv_rs_opencc-0.4.1/.github/workflows/main.yml

@@ -0,0 +1,111 @@
+name: CI
+
+on:
+  push:
+  pull_request:
+
+env:
+  CARGO_TERM_COLOR: always
+
+jobs:
+  build-main:
+    strategy:
+      matrix:
+        featureset:
+          - flag: ""
+          - flag: "--all-features"
+          - flag: "--no-default-features"
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v2
+      - name: Build lib
+        run: |
+          cargo --version
+          cargo build --verbose ${{ matrix.featureset.flag }}
+      - name: Build bin
+        if: matrix.featureset.flag == ''
+        run: |
+          cargo build --features bin-build --bin zhconv --verbose
+      - name: Test
+        run: |
+          # comment out benchmark-only dependencies, which require opencc installation
+          sed -i -E 's/^(ferrous-opencc|opencc-rust|fast2s|opencc-fmmseg)/#\1/' Cargo.toml
+          # and disable the relevant benchmark to avoid clippy warnings
+          perl -0777 -i -pe 's/\[\[bench\]\]\s*\n\s*harness\s*=\s*false\s*\n\s*name\s*=\s*"compare_benchmark"\s*\nrequired-features\s*=\s*\["bench"\]?//s' Cargo.toml
+          echo "" > benches/compare_benchmark.rs
+
+          cargo test --workspace ${{ matrix.featureset.flag }} --verbose
+      - name: Check Format
+        run: cargo fmt -- --check
+      - name: Clippy
+        run: cargo clippy --workspace --all-targets ${{ matrix.featureset.flag }} -- -D warnings
+
+  build-pyo3:
+    needs: build-main
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - name: Symlink README
+        run: |
+          cd pyo3/
+          ln -s ../README.md ./
+      - uses: messense/maturin-action@v1
+        with:
+          manylinux: auto
+          command: build
+          args: --release --sdist -o pyo3/dist --find-interpreter -m pyo3/Cargo.toml
+
+  build-typst:
+    needs: build-main
+    runs-on: ubuntu-latest
+    defaults:
+      run:
+        working-directory: typst/
+    steps:
+      - uses: actions/checkout@v3
+      - name: Install Wasm target for Rust
+        run: rustup target add wasm32-unknown-unknown
+      - name: Install Typst
+        run: |
+          curl -fsSL -O https://github.com/typst/typst/releases/download/v0.14.0/typst-x86_64-unknown-linux-musl.tar.xz
+          tar xf typst-x86_64-unknown-linux-musl.tar.xz
+          mv typst-x86_64-unknown-linux-musl/typst /home/runner/
+        working-directory: /tmp
+      - name: Build
+        run: |
+          cargo --version
+          cargo build --release --verbose --target wasm32-unknown-unknown
+      - name: Typst Compile
+        run: |
+          cp target/wasm32-unknown-unknown/release/zhconv_typst.wasm ./
+          /home/runner/typst --version
+          /home/runner/typst compile example.typ
+      - name: Clippy
+        run: cargo clippy --target wasm32-unknown-unknown --all-features -- -D warnings
+      - name: Check Format
+        run: cargo fmt -- --check
+
+  # now Pages.dev do this for us
+  # build-web:
+  #   needs: build-main
+  #   runs-on: ubuntu-latest
+  #   steps:
+  #     - uses: actions/checkout@v2
+  #     - uses: actions/setup-node@v1
+  #       with:
+  #         node-version: "16"
+  #     - name: Init web
+  #       working-directory: web/
+  #       run: |
+  #         node --version
+  #         yarn --version
+  #         yarn install
+  #     - name: Build
+  #       working-directory: web/
+  #       run: yarn build
+  # - name: Test
+  #   working-directory: web/
+  #   run: yarn test # no effective test so far
+# adapted from: https://github.com/Gowee/cidr-aggregator/blob/9c02241ab64e5cf62e33375e55e09502385bdc61/.github/workflows/main.yml#L1
+# which is in turn adapted from:
+# https://github.com/Gowee/json2pyi/blob/4e13b4767f97d79e90ecf19a0cb21b1e799d7d48/.github/workflows/main.yml

{zhconv_rs_opencc-0.3.3 → zhconv_rs_opencc-0.4.1}/.github/workflows/npm.yml

@@ -14,10 +14,10 @@ jobs:
           toolchain: stable
       - name: Install wasm-pack
         run: |
-          curl https://rustwasm.github.io/wasm-pack/installer/init.sh -sSf | sh 
+          curl https://rustwasm.github.io/wasm-pack/installer/init.sh -sSf | sh
       - name: Build pkg
         run: |
-          wasm-pack build --release -d pkg-bundler &&  wasm-pack build --release -d pkg-web -t web
+          wasm-pack build --release -d pkg-bundler -- --features wasm  && wasm-pack build --release -d pkg-web -t web -- --features wasm
       - name: Upload pkg
         uses: actions/upload-artifact@v4
         with:
@@ -31,7 +31,7 @@ jobs:
     environment: npm
     runs-on: ubuntu-latest
     if: "startsWith(github.ref, 'refs/tags/')"
-    needs: [ build ]
+    needs: [build]
     steps:
       - uses: actions/setup-node@v3
         with:

{zhconv_rs_opencc-0.3.3 → zhconv_rs_opencc-0.4.1}/.github/workflows/pyo3.yml

@@ -165,9 +165,9 @@ jobs:
     strategy:
       matrix:
         platform:
-          - runner: macos-13
+          - runner: macos-15-intel
             target: x86_64
-          - runner: macos-14
+          - runner: macos-latest
             target: aarch64
     steps:
       - uses: actions/checkout@v4

zhconv_rs_opencc-0.4.1/.github/workflows/release.yml

@@ -0,0 +1,86 @@
+name: "Release"
+
+on:
+  push:
+    branches:
+      - main
+      - test
+    tags:
+      - v*
+  # release:
+  #   types: [created]
+
+jobs:
+  build:
+    name: build ${{ matrix.target }}
+    runs-on: ${{ matrix.os }}
+    strategy:
+      fail-fast: false
+      matrix:
+        include:
+          - target: x86_64-pc-windows-gnu
+            os: windows-2025
+            cargo: cargo
+            binext: .exe # binary extension
+            # archive: zip
+          - target: x86_64-unknown-linux-musl
+            os: ubuntu-latest
+            cargo: cargo
+            binext: ""
+            # archive: tar.gz tar.xz
+          - target: aarch64-unknown-linux-musl
+            os: ubuntu-latest
+            cargo: cross
+            binext: ""
+          - target: x86_64-apple-darwin
+            os: macos-latest
+            cargo: cargo
+            binext: ""
+            # archive: zip
+    steps:
+      - uses: actions/checkout@v3
+      - uses: actions-rs/toolchain@v1
+        with:
+          toolchain: stable
+          target: ${{ matrix.target }}
+          override: true
+          profile: minimal
+      - name: Install cross
+        run: |
+          cargo install cross --git https://github.com/cross-rs/cross.git
+        if: matrix.cargo == 'cross'
+      - name: Build and strip
+        shell: bash # on win, the default is ps
+        run: |
+          mkdir bin
+          ${{ matrix.cargo }} build --features bin-build --bin zhconv --release --target ${{ matrix.target }}
+          mv target/${{ matrix.target }}/release/zhconv${{ matrix.binext }} "bin/zhconv-${{ matrix.target }}${{ matrix.binext }}"
+          ${{ matrix.cargo }} build --features bin-build --features opencc --bin zhconv --release --target ${{ matrix.target }}
+          mv target/${{ matrix.target }}/release/zhconv${{ matrix.binext }} "bin/zhconv-opencc-${{ matrix.target }}${{ matrix.binext }}"
+          strip -v "$f" || echo "strip failed"
+          # if [ "${{ matrix.os }}" = "windows-2025" ]; then
+          #   7z a "$staging.zip" "$staging"
+          # else
+          #   tar czf "$staging.tar.gz" "$staging"
+          # fi
+      - name: Upload artifact
+        uses: actions/upload-artifact@v4
+        with:
+          name: binaries-${{ matrix.target }}
+          path: bin/
+
+  release:
+    runs-on: ubuntu-latest
+    # trigger real release only on tag push
+    if: "startsWith(github.ref, 'refs/tags/')"
+    needs: [build]
+    steps:
+      - uses: actions/download-artifact@v4
+        with:
+          pattern: binaries-*
+          merge-multiple: true
+      - name: Release
+        uses: softprops/action-gh-release@v2
+        with:
+          files: |
+            *

{zhconv_rs_opencc-0.3.3 → zhconv_rs_opencc-0.4.1}/.github/workflows/worker.yml

@@ -35,7 +35,6 @@ jobs:
           apiToken: ${{ secrets.CF_API_TOKEN }}
           accountId: ${{ secrets.CF_ACCOUNT_ID }}
           workingDirectory: worker
-
 # Note:
 # To activate authentication, set the `API_TOKEN` secret, via the CF dashboard or `wrangler secret put API_TOKEN`.
 # To change the 2MiB default request body limit, set the `BODY_LIMIT` envvar, via the dashboard or wrangler.toml.

zhconv_rs_opencc-0.4.1/CHANGELOG.md

@@ -0,0 +1,66 @@
+# Changelog
+
+All notable changes to this project will be documented in this file. 
+(CAUTION: primarily vibed by Gemini)
+
+## v0.4.1 (2026-02-05)
+
+### Core & CLI
+- **Simplified Conversion Optimizations**: Omit "!HKVariants" and "!TWVariants" from OpenCC cofnig when targeting Simplified Chinese to avoid misconversion.
+- **Improved Variant Inference**: Enhanced accuracy by omitting no-op pairs during character counting.
+- **Fine-grained Feature Gating**: Refactored conversion table features for granular control over ruleset inclusion.
+- **Dependency Cleanup**: Removed `once_cell` in favor of standard library features.
+- **Data Sync**: Synchronized conversion tables with the latest upstream rules.
+
+### Web Application
+- **Frontend Modernization**: Upgraded the stack to **React 19**, **Material UI v7**, and **Vite**.
+- **Enhanced Ruleset Selection**: Added support for toggling between MediaWiki and OpenCC rulesets, or using both concurrently.
+- **Dynamic Variant Filtering**: Automatically hides target variants unsupported by the current ruleset.
+- **File Conversion**: Added the ability to convert local text files directly in the browser.
+- **Refactor Codebase**: Refactored the codebase with ContextProvider to improve performance and maintainability.
+- **Infrastructure**: Migrated to **Yarn Berry (v4)** and enforced stricter ESLint/Prettier rules.
+
+## v0.4.0 (2025-12-02)
+
+- **Feature Gating**: Disabled WASM feature by default to be friendly as a library.
+- **OpenCC Integration**: Bundled OpenCC binaries in releases and fixed CI build issues.
+- **Benchmarking**: Added comprehensive benchmark comparisons with other conversion crates.
+- **Maintenance**: Updated rulesets from upstream and fixed outdated CI configurations.
+
+## v0.3.3 (2025-01-15)
+
+- **MediaWiki Alignment**: Fixed nested rules handling to better match MediaWiki's behavior.
+- **Worker Enhancements**: Made request body limit configurable and optimized API query parameter representation.
+- **Wasm/Web**: Added conversion triggers upon option changes.
+
+## v0.3.2 (2024-11-27)
+
+- **New Platform**: Initialized **Typst** integration with kebab-case function naming.
+- **PyO3**: Refined CI and module naming for Python bindings.
+- **Bug Fixes**: Resolved panics in `convert_to_with` when skipping characters at boundaries.
+
+## v0.3.1 (2024-03-22)
+
+- **Optional Rulesets**: Made OpenCC optional in WASM builds.
+- **Conversion Safety**: Applied more conservative rules for one-to-many conversions.
+- **Performance**: Documented build size changes and performance improvements in the v0.3 series.
+
+## v0.3.0 (2023-07-05)
+
+- **Performance Engine**: Switched to `daachorse` (Aho-Corasick) for significantly faster linear-time conversions.
+- **Compression**: Implemented ruleset compression to reduce binary size.
+- **Variant Inference**: Introduced a more intuitive method for `infer_variant_confidence`.
+- **MediaWiki Support**: Added a secondary automaton to handle complex global rules in wikitext.
+
+## v0.2.0 (2023-05-15)
+
+- **Ruleset Expansion**: Introduced OpenCC rulesets in addition to MediaWiki rules.
+- **Regional Support**: Added ruleset precedence for regional variants (TW/HK/CN).
+- **Web App**: Implemented localStorage persistence for selected variants.
+
+## v0.1.0 (2022-09-08)
+
+- **Initial Release**: First stable release of `zhconv-rs`.
+- **Multi-Platform**: Support for CLI, WASM, and Python (PyO3).
+- **MediaWiki Core**: Integrated core conversion rules from MediaWiki.
+- **Relicensing**: Switched project license to GPL-2.0-or-later for better compatibility.