Disambiguate dummy symbols (#107)

* Disambiguate dummy symbols

* Small formatting improvement

* Put HashMap logic into symbol creation

.github/workflows/build.yaml

@@ -9,8 +9,9 @@ on:
   workflow_dispatch:
 
 env:
-  CARGO_BIN_NAME: objdiff
+  BUILD_PROFILE: release-lto
   CARGO_TARGET_DIR: target
+  CARGO_INCREMENTAL: 0
 
 jobs:
   check:
@@ -24,15 +25,31 @@ jobs:
           sudo apt-get update
           sudo apt-get -y install libgtk-3-dev
       - name: Checkout
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
       - name: Setup Rust toolchain
         uses: dtolnay/rust-toolchain@stable
         with:
-          components: rustfmt, clippy
+          components: clippy
       - name: Cargo check
-        run: cargo check --all-features
+        run: cargo check --all-features --all-targets
       - name: Cargo clippy
-        run: cargo clippy --all-features
+        run: cargo clippy --all-features --all-targets
+
+  fmt:
+    name: Format
+    runs-on: ubuntu-latest
+    env:
+      RUSTFLAGS: -D warnings
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+      - name: Setup Rust toolchain
+        # We use nightly options in rustfmt.toml
+        uses: dtolnay/rust-toolchain@nightly
+        with:
+          components: rustfmt
+      - name: Cargo fmt
+        run: cargo fmt --all --check
 
   deny:
     name: Deny
@@ -45,13 +62,14 @@ jobs:
     # Prevent new advisories from failing CI
     continue-on-error: ${{ matrix.checks == 'advisories' }}
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
       - uses: EmbarkStudios/cargo-deny-action@v1
         with:
           command: check ${{ matrix.checks }}
 
   test:
     name: Test
+    if: 'false' # No tests yet
     strategy:
       matrix:
         platform: [ ubuntu-latest, windows-latest, macos-latest ]
@@ -64,14 +82,93 @@ jobs:
           sudo apt-get update
           sudo apt-get -y install libgtk-3-dev
       - name: Checkout
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
       - name: Setup Rust toolchain
         uses: dtolnay/rust-toolchain@stable
       - name: Cargo test
         run: cargo test --release --all-features
 
-  build:
-    name: Build
+  build-cli:
+    name: Build objdiff-cli
+    env:
+      CARGO_BIN_NAME: objdiff-cli
+    strategy:
+      matrix:
+        include:
+          - platform: ubuntu-latest
+            target: x86_64-unknown-linux-musl
+            name: linux-x86_64
+            build: zigbuild
+            features: default
+          - platform: ubuntu-latest
+            target: i686-unknown-linux-musl
+            name: linux-i686
+            build: zigbuild
+            features: default
+          - platform: ubuntu-latest
+            target: aarch64-unknown-linux-musl
+            name: linux-aarch64
+            build: zigbuild
+            features: default
+          - platform: ubuntu-latest
+            target: armv7-unknown-linux-musleabi
+            name: linux-armv7l
+            build: zigbuild
+            features: default
+          - platform: windows-latest
+            target: i686-pc-windows-msvc
+            name: windows-x86
+            build: build
+            features: default
+          - platform: windows-latest
+            target: x86_64-pc-windows-msvc
+            name: windows-x86_64
+            build: build
+            features: default
+          - platform: windows-latest
+            target: aarch64-pc-windows-msvc
+            name: windows-arm64
+            build: build
+            features: default
+          - platform: macos-latest
+            target: x86_64-apple-darwin
+            name: macos-x86_64
+            build: build
+            features: default
+          - platform: macos-latest
+            target: aarch64-apple-darwin
+            name: macos-arm64
+            build: build
+            features: default
+      fail-fast: false
+    runs-on: ${{ matrix.platform }}
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+      - name: Install cargo-zigbuild
+        if: matrix.build == 'zigbuild'
+        run: pip install ziglang==0.13.0 cargo-zigbuild==0.19.1
+      - name: Setup Rust toolchain
+        uses: dtolnay/rust-toolchain@stable
+        with:
+          targets: ${{ matrix.target }}
+      - name: Cargo build
+        run: >
+          cargo ${{ matrix.build }} --profile ${{ env.BUILD_PROFILE }} --target ${{ matrix.target }} 
+          --bin ${{ env.CARGO_BIN_NAME }} --features ${{ matrix.features }}
+      - name: Upload artifacts
+        uses: actions/upload-artifact@v4
+        with:
+          name: ${{ env.CARGO_BIN_NAME }}-${{ matrix.name }}
+          path: |
+            ${{ env.CARGO_TARGET_DIR }}/${{ matrix.target }}/${{ env.BUILD_PROFILE }}/${{ env.CARGO_BIN_NAME }}
+            ${{ env.CARGO_TARGET_DIR }}/${{ matrix.target }}/${{ env.BUILD_PROFILE }}/${{ env.CARGO_BIN_NAME }}.exe
+          if-no-files-found: error
+
+  build-gui:
+    name: Build objdiff-gui
+    env:
+      CARGO_BIN_NAME: objdiff
     strategy:
       matrix:
         include:
@@ -79,15 +176,19 @@ jobs:
             target: x86_64-unknown-linux-gnu
             name: linux-x86_64
             packages: libgtk-3-dev
+            features: default
           - platform: windows-latest
             target: x86_64-pc-windows-msvc
             name: windows-x86_64
+            features: default
           - platform: macos-latest
             target: x86_64-apple-darwin
             name: macos-x86_64
+            features: default
           - platform: macos-latest
             target: aarch64-apple-darwin
             name: macos-arm64
+            features: default
       fail-fast: false
     runs-on: ${{ matrix.platform }}
     steps:
@@ -97,43 +198,75 @@ jobs:
           sudo apt-get update
           sudo apt-get -y install ${{ matrix.packages }}
       - name: Checkout
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
       - name: Setup Rust toolchain
         uses: dtolnay/rust-toolchain@stable
         with:
           targets: ${{ matrix.target }}
       - name: Cargo build
-        run: cargo build --release --all-features --target ${{ matrix.target }} --bin ${{ env.CARGO_BIN_NAME }}
+        run: >
+          cargo build --profile ${{ env.BUILD_PROFILE }} --target ${{ matrix.target }} 
+          --bin ${{ env.CARGO_BIN_NAME }} --features ${{ matrix.features }}
       - name: Upload artifacts
-        uses: actions/upload-artifact@v3
+        uses: actions/upload-artifact@v4
         with:
-          name: ${{ matrix.name }}
+          name: ${{ env.CARGO_BIN_NAME }}-${{ matrix.name }}
           path: |
-            ${{ env.CARGO_TARGET_DIR }}/release/${{ env.CARGO_BIN_NAME }}
-            ${{ env.CARGO_TARGET_DIR }}/release/${{ env.CARGO_BIN_NAME }}.exe
-            ${{ env.CARGO_TARGET_DIR }}/${{ matrix.target }}/release/${{ env.CARGO_BIN_NAME }}
-            ${{ env.CARGO_TARGET_DIR }}/${{ matrix.target }}/release/${{ env.CARGO_BIN_NAME }}.exe
+            ${{ env.CARGO_TARGET_DIR }}/${{ matrix.target }}/${{ env.BUILD_PROFILE }}/${{ env.CARGO_BIN_NAME }}
+            ${{ env.CARGO_TARGET_DIR }}/${{ matrix.target }}/${{ env.BUILD_PROFILE }}/${{ env.CARGO_BIN_NAME }}.exe
           if-no-files-found: error
 
   release:
     name: Release
     if: startsWith(github.ref, 'refs/tags/')
     runs-on: ubuntu-latest
-    needs: [ build ]
+    needs: [ build-cli, build-gui ]
+    permissions:
+      contents: write
     steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+      - name: Check git tag against Cargo version
+        shell: bash
+        run: |
+          set -eou pipefail
+          tag='${{github.ref}}'
+          tag="${tag#refs/tags/}"
+          version=$(grep '^version' Cargo.toml | head -1 | awk -F' = ' '{print $2}' | tr -d '"')
+          version="v$version"
+          if [ "$tag" != "$version" ]; then
+            echo "::error::Git tag doesn't match the Cargo version! ($tag != $version)"
+            exit 1
+          fi
       - name: Download artifacts
-        uses: actions/download-artifact@v3
+        uses: actions/download-artifact@v4
         with:
           path: artifacts
       - name: Rename artifacts
         working-directory: artifacts
         run: |
+          set -euo pipefail
           mkdir ../out
-          for i in */*/release/$CARGO_BIN_NAME*; do
-            mv "$i" "../out/$(sed -E "s/([^/]+)\/[^/]+\/release\/($CARGO_BIN_NAME)/\2-\1/" <<< "$i")"
+          for dir in */; do
+            for file in "$dir"*; do
+              base=$(basename "$file")
+              name="${base%.*}"
+              ext="${base##*.}"
+              if [ "$ext" = "$base" ]; then
+                  ext=""
+              else
+                  ext=".$ext"
+              fi
+              arch="${dir%/}" # remove trailing slash
+              arch="${arch##"$name-"}" # remove bin name
+              dst="../out/${name}-${arch}${ext}"
+              mv "$file" "$dst"
+            done
           done
           ls -R ../out
       - name: Release
-        uses: softprops/action-gh-release@v1
+        uses: softprops/action-gh-release@v2
         with:
           files: out/*
+          draft: true
+          generate_release_notes: true

.gitignore

@@ -22,3 +22,4 @@ android.keystore
 *.frag
 *.vert
 *.metal
+.vscode/launch.json

Cargo.toml

@@ -1,87 +1,21 @@
-[package]
-name = "objdiff"
-version = "0.4.1"
-edition = "2021"
-rust-version = "1.65"
+[workspace]
+members = [
+    "objdiff-cli",
+    "objdiff-core",
+    "objdiff-gui",
+]
+resolver = "2"
+
+[profile.release-lto]
+inherits = "release"
+lto = "fat"
+strip = "debuginfo"
+codegen-units = 1
+
+[workspace.package]
+version = "2.1.0"
 authors = ["Luke Street <luke@street.dev>"]
+edition = "2021"
 license = "MIT OR Apache-2.0"
 repository = "https://github.com/encounter/objdiff"
-readme = "README.md"
-description = """
-A local diffing tool for decompilation projects.
-"""
-publish = false
-build = "build.rs"
-
-[profile.release]
-lto = "thin"
-strip = "debuginfo"
-
-[features]
-default = []
-wgpu = ["eframe/wgpu"]
-
-[dependencies]
-anyhow = "1.0.71"
-byteorder = "1.4.3"
-bytes = "1.4.0"
-cfg-if = "1.0.0"
-const_format = "0.2.31"
-cwdemangle = "0.1.6"
-dirs = "5.0.1"
-eframe = { version = "0.22.0", features = ["persistence"] }
-egui = "0.22.0"
-egui_extras = "0.22.0"
-flagset = "0.4.3"
-globset = { version = "0.4.13", features = ["serde1"] }
-log = "0.4.19"
-memmap2 = "0.7.1"
-notify = "6.0.1"
-object = { version = "0.31.1", features = ["read_core", "std", "elf"], default-features = false }
-png = "0.17.9"
-ppc750cl = { git = "https://github.com/terorie/ppc750cl", rev = "9ae36eef34aa6d74e00972c7671f547a2acfd0aa" }
-rabbitizer = "1.7.4"
-rfd = { version = "0.11.4" } #, default-features = false, features = ['xdg-portal']
-ron = "0.8.0"
-semver = "1.0.17"
-serde = { version = "1", features = ["derive"] }
-serde_json = "1.0.104"
-serde_yaml = "0.9.25"
-tempfile = "3.6.0"
-thiserror = "1.0.41"
-time = { version = "0.3.22", features = ["formatting", "local-offset"] }
-toml = "0.7.6"
-twox-hash = "1.6.3"
-
-# For Linux static binaries, use rustls
-[target.'cfg(target_os = "linux")'.dependencies]
-reqwest = { version = "0.11.18", default-features = false, features = ["blocking", "json", "rustls"] }
-self_update = { version = "0.37.0", default-features = false, features = ["rustls"] }
-
-# For all other platforms, use native TLS
-[target.'cfg(not(target_os = "linux"))'.dependencies]
-reqwest = "0.11.18"
-self_update = "0.37.0"
-
-[target.'cfg(windows)'.dependencies]
-path-slash = "0.2.1"
-winapi = "0.3.9"
-
-[target.'cfg(windows)'.build-dependencies]
-winres = "0.1.12"
-
-[target.'cfg(unix)'.dependencies]
-exec = "0.3.1"
-
-# native:
-[target.'cfg(not(target_arch = "wasm32"))'.dependencies]
-tracing-subscriber = "0.3"
-
-# web:
-[target.'cfg(target_arch = "wasm32")'.dependencies]
-console_error_panic_hook = "0.1.7"
-tracing-wasm = "0.2"
-
-[build-dependencies]
-anyhow = "1.0.71"
-vergen = { version = "8.2.4", features = ["build", "cargo", "git", "gitcl"] }
+rust-version = "1.74"

README.md

@@ -3,14 +3,45 @@
 [Build Status]: https://github.com/encounter/objdiff/actions/workflows/build.yaml/badge.svg
 [actions]: https://github.com/encounter/objdiff/actions
 
-A local diffing tool for decompilation projects.
+A local diffing tool for decompilation projects. Inspired by [decomp.me](https://decomp.me) and [asm-differ](https://github.com/simonlindholm/asm-differ).
+
+Features:
+
+- Compare entire object files: functions and data.
+- Built-in symbol demangling for C++. (CodeWarrior, Itanium & MSVC)
+- Automatic rebuild on source file changes.
+- Project integration via [configuration file](#configuration).
+- Search and filter all of a project's objects and quickly switch.
+- Click to highlight all instances of values and registers.
 
 Supports:
-- PowerPC 750CL (GameCube & Wii)
-- MIPS (Nintendo 64)
+
+- PowerPC 750CL (GameCube, Wii)
+- MIPS (N64, PS1, PS2, PSP)
+- x86 (COFF only at the moment)
+- ARM (GBA, DS, 3DS)
 
 See [Usage](#usage) for more information.
 
+## Downloads
+
+To build from source, see [Building](#building).
+
+### GUI
+
+- [Windows (x86_64)](https://github.com/encounter/objdiff/releases/latest/download/objdiff-windows-x86_64.exe)
+- [Linux (x86_64)](https://github.com/encounter/objdiff/releases/latest/download/objdiff-linux-x86_64)
+- [macOS (arm64)](https://github.com/encounter/objdiff/releases/latest/download/objdiff-macos-arm64)
+- [macOS (x86_64)](https://github.com/encounter/objdiff/releases/latest/download/objdiff-macos-x86_64)
+
+For Linux and macOS, run `chmod +x objdiff-*` to make the binary executable.
+
+### CLI
+
+CLI binaries can be found on the [releases page](https://github.com/encounter/objdiff/releases).
+
+## Screenshots
+
 ![Symbol Screenshot](assets/screen-symbols.png)
 ![Diff Screenshot](assets/screen-diff.png)
 
@@ -39,57 +70,60 @@ See [Configuration](#configuration) for more information.
 
 ## Configuration
 
-While **not required** (most settings can be specified in the UI), projects can add an `objdiff.json` (or
-`objdiff.yaml`, `objdiff.yml`) file to configure the tool automatically. The configuration file must be located in
+While **not required** (most settings can be specified in the UI), projects can add an `objdiff.json` file to configure the tool automatically. The configuration file must be located in
 the root project directory.
 
 If your project has a generator script (e.g. `configure.py`), it's recommended to generate the objdiff configuration
 file as well. You can then add `objdiff.json` to your `.gitignore` to prevent it from being committed.
 
-```json5
-// objdiff.json
+```json
 {
+  "$schema": "https://raw.githubusercontent.com/encounter/objdiff/main/config.schema.json",
   "custom_make": "ninja",
-
-  // Only required if objects use "path" instead of "target_path" and "base_path".
-  "target_dir": "build/asm",
-  "base_dir": "build/src",
-
-  "build_target": true,
+  "custom_args": [
+    "-d",
+    "keeprsp"
+  ],
+  "build_target": false,
+  "build_base": true,
   "watch_patterns": [
     "*.c",
     "*.cp",
     "*.cpp",
+    "*.cxx",
     "*.h",
+    "*.hp",
     "*.hpp",
-    "*.py"
+    "*.hxx",
+    "*.s",
+    "*.S",
+    "*.asm",
+    "*.inc",
+    "*.py",
+    "*.yml",
+    "*.txt",
+    "*.json"
   ],
-  "objects": [
+  "units": [
     {
       "name": "main/MetroTRK/mslsupp",
-
-      // Option 1: Relative to target_dir and base_dir
-      "path": "MetroTRK/mslsupp.o",
-      // Option 2: Explicit paths from project root
-      // Useful for more complex directory layouts
       "target_path": "build/asm/MetroTRK/mslsupp.o",
       "base_path": "build/src/MetroTRK/mslsupp.o",
-      
-      "reverse_fn_order": false
-    },
-    // ...
+      "metadata": {}
+    }
   ]
 }
 ```
 
+### Schema
+
+View [config.schema.json](config.schema.json) for all available options. The below list is a summary of the most important options.
+
 `custom_make` _(optional)_: By default, objdiff will use `make` to build the project.  
-If the project uses a different build system (e.g. `ninja`), specify it here.
+If the project uses a different build system (e.g. `ninja`), specify it here.  
+The build command will be `[custom_make] [custom_args] path/to/object.o`.
 
-`target_dir` _(optional)_: Relative from the root of the project, this where the "target" or "expected" objects are located.  
-These are the **intended result** of the match.
-
-`base_dir` _(optional)_: Relative from the root of the project, this is where the "base" or "actual" objects are located.  
-These are objects built from the **current source code**.
+`custom_args` _(optional)_: Additional arguments to pass to the build command prior to the object path.
 
 `build_target`: If true, objdiff will tell the build system to build the target objects before diffing (e.g.
   `make path/to/target.o`).  
@@ -97,35 +131,53 @@ This is useful if the target objects are not built by default or can change base
 to assembly files.  
 Requires the build system to be configured properly.
 
+`build_base`: If true, objdiff will tell the build system to build the base objects before diffing (e.g. `make path/to/base.o`).  
+It's unlikely you'll want to disable this, unless you're using an external tool to rebuild the base object on source file changes.
+
 `watch_patterns` _(optional)_: A list of glob patterns to watch for changes.
 ([Supported syntax](https://docs.rs/globset/latest/globset/#syntax))  
 If any of these files change, objdiff will automatically rebuild the objects and re-compare them.  
 If not specified, objdiff will use the default patterns listed above.
 
-`objects` _(optional)_: If specified, objdiff will display a list of objects in the sidebar for easy navigation.
+`units` _(optional)_: If specified, objdiff will display a list of objects in the sidebar for easy navigation.
 
 > `name` _(optional)_: The name of the object in the UI. If not specified, the object's `path` will be used.
 > 
-> `path`: Relative path to the object from the `target_dir` and `base_dir`.  
-> Requires `target_dir` and `base_dir` to be specified.
+> `target_path`: Path to the "target" or "expected" object from the project root.  
+> This object is the **intended result** of the match.
 > 
-> `target_path`: Path to the target object from the project root.  
-> Required if `path` is not specified.
+> `base_path`: Path to the "base" or "actual" object from the project root.  
+> This object is built from the **current source code**.
 > 
-> `base_path`: Path to the base object from the project root.  
-> Required if `path` is not specified.
+> `metadata.auto_generated` _(optional)_: Hides the object from the object list, but still includes it in reports.
 > 
-> `reverse_fn_order` _(optional)_: Displays function symbols in reversed order.  
-Used to support MWCC's `-inline deferred` option, which reverses the order of functions in the object file.
+> `metadata.complete` _(optional)_: Marks the object as "complete" (or "linked") in the object list.  
+> This is useful for marking objects that are fully decompiled. A value of `false` will mark the object as "incomplete".
 
+## Building
 
+Install Rust via [rustup](https://rustup.rs).
+
+```shell
+$ git clone https://github.com/encounter/objdiff.git
+$ cd objdiff
+$ cargo run --release
+```
+
+Or using `cargo install`.
+
+```shell
+$ cargo install --locked --git https://github.com/encounter/objdiff.git objdiff-gui objdiff-cli
+```
+
+The binaries will be installed to `~/.cargo/bin` as `objdiff` and `objdiff-cli`.
 
 ## License
 
 Licensed under either of
 
-* Apache License, Version 2.0, ([LICENSE-APACHE](LICENSE-APACHE) or http://www.apache.org/licenses/LICENSE-2.0)
-* MIT license ([LICENSE-MIT](LICENSE-MIT) or http://opensource.org/licenses/MIT)
+- Apache License, Version 2.0, ([LICENSE-APACHE](LICENSE-APACHE) or <http://www.apache.org/licenses/LICENSE-2.0>)
+- MIT license ([LICENSE-MIT](LICENSE-MIT) or <http://opensource.org/licenses/MIT>)
 
 at your option.
 

build.rs

@@ -1,10 +0,0 @@
-use anyhow::Result;
-use vergen::EmitBuilder;
-
-fn main() -> Result<()> {
-    #[cfg(windows)]
-    {
-        winres::WindowsResource::new().set_icon("assets/icon.ico").compile()?;
-    }
-    EmitBuilder::builder().fail_on_error().all_build().all_cargo().all_git().emit()
-}

config.schema.json

@@ -0,0 +1,221 @@
+{
+  "$schema": "https://json-schema.org/draft-07/schema",
+  "$id": "https://raw.githubusercontent.com/encounter/objdiff/main/config.schema.json",
+  "title": "objdiff configuration",
+  "description": "Configuration file for objdiff",
+  "type": "object",
+  "properties": {
+    "min_version": {
+      "type": "string",
+      "description": "Minimum version of objdiff required to load this configuration file.",
+      "examples": [
+        "1.0.0",
+        "2.0.0-beta.1"
+      ]
+    },
+    "custom_make": {
+      "type": "string",
+      "description": "By default, objdiff will use make to build the project.\nIf the project uses a different build system (e.g. ninja), specify it here.\nThe build command will be `[custom_make] [custom_args] path/to/object.o`.",
+      "examples": [
+        "make",
+        "ninja"
+      ],
+      "default": "make"
+    },
+    "custom_args": {
+      "type": "array",
+      "description": "Additional arguments to pass to the build command prior to the object path.",
+      "items": {
+        "type": "string"
+      }
+    },
+    "target_dir": {
+      "type": "string",
+      "description": "Relative from the root of the project, this where the \"target\" or \"expected\" objects are located.\nThese are the intended result of the match.",
+      "deprecated": true
+    },
+    "base_dir": {
+      "type": "string",
+      "description": "Relative from the root of the project, this is where the \"base\" or \"actual\" objects are located.\nThese are objects built from the current source code.",
+      "deprecated": true
+    },
+    "build_target": {
+      "type": "boolean",
+      "description": "If true, objdiff will tell the build system to build the target objects before diffing (e.g. `make path/to/target.o`).\nThis is useful if the target objects are not built by default or can change based on project configuration or edits to assembly files.\nRequires the build system to be configured properly.",
+      "default": false
+    },
+    "build_base": {
+      "type": "boolean",
+      "description": "If true, objdiff will tell the build system to build the base objects before diffing (e.g. `make path/to/base.o`).\nIt's unlikely you'll want to disable this, unless you're using an external tool to rebuild the base object on source file changes.",
+      "default": true
+    },
+    "watch_patterns": {
+      "type": "array",
+      "description": "List of glob patterns to watch for changes in the project.\nIf any of these files change, objdiff will automatically rebuild the objects and re-compare them.\nSupported syntax: https://docs.rs/globset/latest/globset/#syntax",
+      "items": {
+        "type": "string"
+      },
+      "default": [
+        "*.c",
+        "*.cp",
+        "*.cpp",
+        "*.cxx",
+        "*.h",
+        "*.hp",
+        "*.hpp",
+        "*.hxx",
+        "*.s",
+        "*.S",
+        "*.asm",
+        "*.inc",
+        "*.py",
+        "*.yml",
+        "*.txt",
+        "*.json"
+      ]
+    },
+    "objects": {
+      "type": "array",
+      "description": "Use units instead.",
+      "deprecated": true,
+      "items": {
+        "$ref": "#/$defs/unit"
+      }
+    },
+    "units": {
+      "type": "array",
+      "description": "If specified, objdiff will display a list of objects in the sidebar for easy navigation.",
+      "items": {
+        "$ref": "#/$defs/unit"
+      }
+    },
+    "progress_categories": {
+      "type": "array",
+      "description": "Progress categories used for objdiff-cli report.",
+      "items": {
+        "$ref": "#/$defs/progress_category"
+      }
+    }
+  },
+  "$defs": {
+    "unit": {
+      "type": "object",
+      "properties": {
+        "name": {
+          "type": "string",
+          "description": "The name of the object in the UI. If not specified, the object's path will be used."
+        },
+        "path": {
+          "type": "string",
+          "description": "Relative path to the object from the target_dir and base_dir.\nRequires target_dir and base_dir to be specified.",
+          "deprecated": true
+        },
+        "target_path": {
+          "type": "string",
+          "description": "Path to the target object from the project root.\nRequired if path is not specified."
+        },
+        "base_path": {
+          "type": "string",
+          "description": "Path to the base object from the project root.\nRequired if path is not specified."
+        },
+        "reverse_fn_order": {
+          "type": "boolean",
+          "description": "Displays function symbols in reversed order.\nUsed to support MWCC's -inline deferred option, which reverses the order of functions in the object file.",
+          "deprecated": true
+        },
+        "complete": {
+          "type": "boolean",
+          "description": "Marks the object as \"complete\" (or \"linked\") in the object list.\nThis is useful for marking objects that are fully decompiled. A value of `false` will mark the object as \"incomplete\".",
+          "deprecated": true
+        },
+        "scratch": {
+          "ref": "#/$defs/scratch"
+        },
+        "metadata": {
+          "ref": "#/$defs/metadata"
+        }
+      }
+    },
+    "scratch": {
+      "type": "object",
+      "description": "If present, objdiff will display a button to create a decomp.me scratch.",
+      "properties": {
+        "platform": {
+          "type": "string",
+          "description": "The decomp.me platform ID to use for the scratch.",
+          "examples": [
+            "gc_wii",
+            "n64"
+          ]
+        },
+        "compiler": {
+          "type": "string",
+          "description": "The decomp.me compiler ID to use for the scratch.",
+          "examples": [
+            "mwcc_242_81",
+            "ido7.1"
+          ]
+        },
+        "c_flags": {
+          "type": "string",
+          "description": "C flags to use for the scratch. Exclude any include paths."
+        },
+        "ctx_path": {
+          "type": "string",
+          "description": "Path to the context file to use for the scratch."
+        },
+        "build_ctx": {
+          "type": "boolean",
+          "description": "If true, objdiff will run the build command with the context file as an argument to generate it.",
+          "default": false
+        }
+      },
+      "required": [
+        "platform",
+        "compiler"
+      ]
+    },
+    "metadata": {
+      "type": "object",
+      "properties": {
+        "complete": {
+          "type": "boolean",
+          "description": "Marks the object as \"complete\" (or \"linked\") in the object list.\nThis is useful for marking objects that are fully decompiled. A value of `false` will mark the object as \"incomplete\"."
+        },
+        "reverse_fn_order": {
+          "type": "boolean",
+          "description": "Displays function symbols in reversed order.\nUsed to support MWCC's -inline deferred option, which reverses the order of functions in the object file."
+        },
+        "source_path": {
+          "type": "string",
+          "description": "Path to the source file that generated the object."
+        },
+        "progress_categories": {
+          "type": "array",
+          "description": "Progress categories used for objdiff-cli report.",
+          "items": {
+            "type": "string",
+            "description": "Unique identifier for the category. (See progress_categories)"
+          }
+        },
+        "auto_generated": {
+          "type": "boolean",
+          "description": "Hides the object from the object list by default, but still includes it in reports."
+        }
+      }
+    },
+    "progress_category": {
+      "type": "object",
+      "properties": {
+        "id": {
+          "type": "string",
+          "description": "Unique identifier for the category."
+        },
+        "name": {
+          "type": "string",
+          "description": "Human-readable name of the category."
+        }
+      }
+    }
+  }
+}

deny.toml

@@ -9,6 +9,11 @@
 # The values provided in this template are the default values that will be used
 # when any section or field is not specified in your own configuration
 
+# Root options
+
+# The graph table configures how the dependency graph is constructed and thus
+# which crates the checks are performed against
+[graph]
 # If 1 or more target triples (and optionally, target_features) are specified,
 # only the specified targets will be checked when running `cargo deny check`.
 # This means, if a particular package is only ever used as a target specific
@@ -20,62 +25,73 @@
 targets = [
     # The triple can be any string, but only the target triples built in to
     # rustc (as of 1.40) can be checked against actual config expressions
-    #{ triple = "x86_64-unknown-linux-musl" },
+    #"x86_64-unknown-linux-musl",
     # You can also specify which target_features you promise are enabled for a
     # particular target. target_features are currently not validated against
     # the actual valid features supported by the target architecture.
     #{ triple = "wasm32-unknown-unknown", features = ["atomics"] },
 ]
+# When creating the dependency graph used as the source of truth when checks are
+# executed, this field can be used to prune crates from the graph, removing them
+# from the view of cargo-deny. This is an extremely heavy hammer, as if a crate
+# is pruned from the graph, all of its dependencies will also be pruned unless
+# they are connected to another crate in the graph that hasn't been pruned,
+# so it should be used with care. The identifiers are [Package ID Specifications]
+# (https://doc.rust-lang.org/cargo/reference/pkgid-spec.html)
+#exclude = []
+# If true, metadata will be collected with `--all-features`. Note that this can't
+# be toggled off if true, if you want to conditionally enable `--all-features` it
+# is recommended to pass `--all-features` on the cmd line instead
+all-features = false
+# If true, metadata will be collected with `--no-default-features`. The same
+# caveat with `all-features` applies
+no-default-features = false
+# If set, these feature will be enabled when collecting metadata. If `--features`
+# is specified on the cmd line they will take precedence over this option.
+#features = []
+
+# The output table provides options for how/if diagnostics are outputted
+[output]
+# When outputting inclusion graphs in diagnostics that include features, this
+# option can be used to specify the depth at which feature edges will be added.
+# This option is included since the graphs can be quite large and the addition
+# of features from the crate(s) to all of the graph roots can be far too verbose.
+# This option can be overridden via `--feature-depth` on the cmd line
+feature-depth = 1
 
 # This section is considered when running `cargo deny check advisories`
 # More documentation for the advisories section can be found here:
 # https://embarkstudios.github.io/cargo-deny/checks/advisories/cfg.html
 [advisories]
-# The path where the advisory database is cloned/fetched into
-db-path = "~/.cargo/advisory-db"
+# The path where the advisory databases are cloned/fetched into
+#db-path = "$CARGO_HOME/advisory-dbs"
 # The url(s) of the advisory databases to use
-db-urls = ["https://github.com/rustsec/advisory-db"]
-# The lint level for security vulnerabilities
-vulnerability = "deny"
-# The lint level for unmaintained crates
-unmaintained = "warn"
-# The lint level for crates that have been yanked from their source registry
-yanked = "warn"
-# The lint level for crates with security notices. Note that as of
-# 2019-12-17 there are no security notice advisories in
-# https://github.com/rustsec/advisory-db
-notice = "warn"
+#db-urls = ["https://github.com/rustsec/advisory-db"]
 # A list of advisory IDs to ignore. Note that ignored advisories will still
 # output a note when they are encountered.
 ignore = [
-    "RUSTSEC-2023-0022",
-    "RUSTSEC-2023-0023",
-    "RUSTSEC-2023-0024",
-    "RUSTSEC-2023-0034",
-    "RUSTSEC-2023-0044",
+    "RUSTSEC-2024-0370",
+    #{ id = "RUSTSEC-0000-0000", reason = "you can specify a reason the advisory is ignored" },
+    #"a-crate-that-is-yanked@0.1.1", # you can also ignore yanked crate versions if you wish
+    #{ crate = "a-crate-that-is-yanked@0.1.1", reason = "you can specify why you are ignoring the yanked crate" },
 ]
-# Threshold for security vulnerabilities, any vulnerability with a CVSS score
-# lower than the range specified will be ignored. Note that ignored advisories
-# will still output a note when they are encountered.
-# * None - CVSS Score 0.0
-# * Low - CVSS Score 0.1 - 3.9
-# * Medium - CVSS Score 4.0 - 6.9
-# * High - CVSS Score 7.0 - 8.9
-# * Critical - CVSS Score 9.0 - 10.0
-#severity-threshold =
+# If this is true, then cargo deny will use the git executable to fetch advisory database.
+# If this is false, then it uses a built-in git library.
+# Setting this to true can be helpful if you have special authentication requirements that cargo-deny does not support.
+# See Git Authentication for more information about setting up git authentication.
+#git-fetch-with-cli = true
 
 # This section is considered when running `cargo deny check licenses`
 # More documentation for the licenses section can be found here:
 # https://embarkstudios.github.io/cargo-deny/checks/licenses/cfg.html
 [licenses]
-# The lint level for crates which do not have a detectable license
-unlicensed = "deny"
-# List of explictly allowed licenses
+# List of explicitly allowed licenses
 # See https://spdx.org/licenses/ for list of possible licenses
 # [possible values: any SPDX 3.11 short identifier (+ optional exception)].
 allow = [
     "MIT",
     "Apache-2.0",
+    "Apache-2.0 WITH LLVM-exception",
     "ISC",
     "BSD-2-Clause",
     "BSD-3-Clause",
@@ -88,28 +104,7 @@ allow = [
     "OFL-1.1",
     "LicenseRef-UFL-1.0",
     "OpenSSL",
-    "GPL-3.0",
 ]
-# List of explictly disallowed licenses
-# See https://spdx.org/licenses/ for list of possible licenses
-# [possible values: any SPDX 3.11 short identifier (+ optional exception)].
-deny = [
-    #"Nokia",
-]
-# Lint level for licenses considered copyleft
-copyleft = "warn"
-# Blanket approval or denial for OSI-approved or FSF Free/Libre licenses
-# * both - The license will be approved if it is both OSI-approved *AND* FSF
-# * either - The license will be approved if it is either OSI-approved *OR* FSF
-# * osi-only - The license will be approved if is OSI-approved *AND NOT* FSF
-# * fsf-only - The license will be approved if is FSF *AND NOT* OSI-approved
-# * neither - This predicate is ignored and the default lint level is used
-allow-osi-fsf-free = "neither"
-# Lint level used when no other predicates are matched
-# 1. License isn't in the allow or deny lists
-# 2. License isn't copyleft
-# 3. License isn't OSI/FSF, or allow-osi-fsf-free = "neither"
-default = "deny"
 # The confidence threshold for detecting a license from license text.
 # The higher the value, the more closely the license text must be to the
 # canonical license text of a valid SPDX license file.
@@ -120,17 +115,15 @@ confidence-threshold = 0.8
 exceptions = [
     # Each entry is the crate and version constraint, and its specific allow
     # list
-    #{ allow = ["Zlib"], name = "adler32", version = "*" },
+    #{ allow = ["Zlib"], crate = "adler32" },
 ]
 
 # Some crates don't have (easily) machine readable licensing information,
 # adding a clarification entry for it allows you to manually specify the
 # licensing information
 [[licenses.clarify]]
-# The name of the crate the clarification applies to
-name = "ring"
-# The optional version constraint for the crate
-version = "*"
+# The package spec the clarification applies to
+crate = "ring"
 # The SPDX expression for the license requirements of the crate
 expression = "MIT AND ISC AND OpenSSL"
 # One or more files in the crate's source used as the "source of truth" for
@@ -145,7 +138,9 @@ license-files = [
 
 [licenses.private]
 # If true, ignores workspace crates that aren't published, or are only
-# published to private registries
+# published to private registries.
+# To see how to mark a crate as unpublished (to the official registry),
+# visit https://doc.rust-lang.org/cargo/reference/manifest.html#the-publish-field.
 ignore = false
 # One or more private registries that you might publish crates to, if a crate
 # is only published to private registries, and ignore is true, the crate will
@@ -159,7 +154,7 @@ registries = [
 # https://embarkstudios.github.io/cargo-deny/checks/bans/cfg.html
 [bans]
 # Lint level for when multiple versions of the same crate are detected
-multiple-versions = "warn"
+multiple-versions = "allow"
 # Lint level for when a crate version requirement is `*`
 wildcards = "allow"
 # The graph highlighting used when creating dotgraphs for crates
@@ -168,30 +163,63 @@ wildcards = "allow"
 # * simplest-path - The path to the version with the fewest edges is highlighted
 # * all - Both lowest-version and simplest-path are used
 highlight = "all"
+# The default lint level for `default` features for crates that are members of
+# the workspace that is being checked. This can be overridden by allowing/denying
+# `default` on a crate-by-crate basis if desired.
+workspace-default-features = "allow"
+# The default lint level for `default` features for external crates that are not
+# members of the workspace. This can be overridden by allowing/denying `default`
+# on a crate-by-crate basis if desired.
+external-default-features = "allow"
 # List of crates that are allowed. Use with care!
 allow = [
-    #{ name = "ansi_term", version = "=0.11.0" },
+    #"ansi_term@0.11.0",
+    #{ crate = "ansi_term@0.11.0", reason = "you can specify a reason it is allowed" },
 ]
 # List of crates to deny
 deny = [
-    # Each entry the name of a crate and a version range. If version is
-    # not specified, all versions will be matched.
-    #{ name = "ansi_term", version = "=0.11.0" },
-    #
+    #"ansi_term@0.11.0",
+    #{ crate = "ansi_term@0.11.0", reason = "you can specify a reason it is banned" },
     # Wrapper crates can optionally be specified to allow the crate when it
     # is a direct dependency of the otherwise banned crate
-    #{ name = "ansi_term", version = "=0.11.0", wrappers = [] },
+    #{ crate = "ansi_term@0.11.0", wrappers = ["this-crate-directly-depends-on-ansi_term"] },
 ]
+
+# List of features to allow/deny
+# Each entry the name of a crate and a version range. If version is
+# not specified, all versions will be matched.
+#[[bans.features]]
+#crate = "reqwest"
+# Features to not allow
+#deny = ["json"]
+# Features to allow
+#allow = [
+#    "rustls",
+#    "__rustls",
+#    "__tls",
+#    "hyper-rustls",
+#    "rustls",
+#    "rustls-pemfile",
+#    "rustls-tls-webpki-roots",
+#    "tokio-rustls",
+#    "webpki-roots",
+#]
+# If true, the allowed features must exactly match the enabled feature set. If
+# this is set there is no point setting `deny`
+#exact = true
+
 # Certain crates/versions that will be skipped when doing duplicate detection.
 skip = [
-    #{ name = "ansi_term", version = "=0.11.0" },
+    #"ansi_term@0.11.0",
+    #{ crate = "ansi_term@0.11.0", reason = "you can specify a reason why it can't be updated/removed" },
 ]
 # Similarly to `skip` allows you to skip certain crates during duplicate
 # detection. Unlike skip, it also includes the entire tree of transitive
 # dependencies starting at the specified crate, up to a certain depth, which is
-# by default infinite
+# by default infinite.
 skip-tree = [
-    #{ name = "ansi_term", version = "=0.11.0", depth = 20 },
+    #"ansi_term@0.11.0", # will be skipped along with _all_ of its direct and transitive dependencies
+    #{ crate = "ansi_term@0.11.0", depth = 20 },
 ]
 
 # This section is considered when running `cargo deny check sources`.
@@ -211,9 +239,9 @@ allow-registry = ["https://github.com/rust-lang/crates.io-index"]
 allow-git = []
 
 [sources.allow-org]
-# 1 or more github.com organizations to allow git sources for
+# github.com organizations to allow git sources for
 github = ["encounter"]
-# 1 or more gitlab.com organizations to allow git sources for
-#gitlab = [""]
-# 1 or more bitbucket.org organizations to allow git sources for
-#bitbucket = [""]
+# gitlab.com organizations to allow git sources for
+gitlab = []
+# bitbucket.org organizations to allow git sources for
+bitbucket = []

objdiff-cli/Cargo.toml

@@ -0,0 +1,30 @@
+[package]
+name = "objdiff-cli"
+version.workspace = true
+edition.workspace = true
+rust-version.workspace = true
+authors.workspace = true
+license.workspace = true
+repository.workspace = true
+readme = "../README.md"
+description = """
+A local diffing tool for decompilation projects.
+"""
+publish = false
+
+[dependencies]
+anyhow = "1.0"
+argp = "0.3"
+crossterm = "0.28"
+enable-ansi-support = "0.2"
+memmap2 = "0.9"
+objdiff-core = { path = "../objdiff-core", features = ["all"] }
+prost = "0.13"
+ratatui = "0.28"
+rayon = "1.10"
+serde = { version = "1.0", features = ["derive"] }
+serde_json = "1.0"
+supports-color = "3.0"
+time = { version = "0.3", features = ["formatting", "local-offset"] }
+tracing = "0.1"
+tracing-subscriber = { version = "0.3", features = ["env-filter"] }

objdiff-cli/src/argp_version.rs

@@ -0,0 +1,63 @@
+// Originally from https://gist.github.com/suluke/e0c672492126be0a4f3b4f0e1115d77c
+//! Extend `argp` to be better integrated with the `cargo` ecosystem
+//!
+//! For now, this only adds a --version/-V option which causes early-exit.
+use std::ffi::OsStr;
+
+use argp::{parser::ParseGlobalOptions, EarlyExit, FromArgs, TopLevelCommand};
+
+struct ArgsOrVersion<T>(T)
+where T: FromArgs;
+
+impl<T> TopLevelCommand for ArgsOrVersion<T> where T: FromArgs {}
+
+impl<T> FromArgs for ArgsOrVersion<T>
+where T: FromArgs
+{
+    fn _from_args(
+        command_name: &[&str],
+        args: &[&OsStr],
+        parent: Option<&mut dyn ParseGlobalOptions>,
+    ) -> Result<Self, EarlyExit> {
+        /// Also use argp for catching `--version`-only invocations
+        #[derive(FromArgs)]
+        struct Version {
+            /// Print version information and exit.
+            #[argp(switch, short = 'V')]
+            pub version: bool,
+        }
+
+        match Version::from_args(command_name, args) {
+            Ok(v) => {
+                if v.version {
+                    println!(
+                        "{} {}",
+                        command_name.first().unwrap_or(&""),
+                        env!("CARGO_PKG_VERSION"),
+                    );
+                    std::process::exit(0);
+                } else {
+                    // Pass through empty arguments
+                    T::_from_args(command_name, args, parent).map(Self)
+                }
+            }
+            Err(exit) => match exit {
+                EarlyExit::Help(_help) => {
+                    // TODO: Chain help info from Version
+                    // For now, we just put the switch on T as well
+                    T::from_args(command_name, &["--help"]).map(Self)
+                }
+                EarlyExit::Err(_) => T::_from_args(command_name, args, parent).map(Self),
+            },
+        }
+    }
+}
+
+/// Create a `FromArgs` type from the current process’s `env::args`.
+///
+/// This function will exit early from the current process if argument parsing was unsuccessful or if information like `--help` was requested.
+/// Error messages will be printed to stderr, and `--help` output to stdout.
+pub fn from_env<T>() -> T
+where T: TopLevelCommand {
+    argp::parse_args_or_exit::<ArgsOrVersion<T>>(argp::DEFAULT).0
+}

objdiff-cli/src/cmd/mod.rs

@@ -0,0 +1,2 @@
+pub mod diff;
+pub mod report;

objdiff-cli/src/cmd/report.rs

@@ -0,0 +1,423 @@
+use std::{
+    collections::HashSet,
+    fs::File,
+    io::Read,
+    path::{Path, PathBuf},
+    time::Instant,
+};
+
+use anyhow::{bail, Context, Result};
+use argp::FromArgs;
+use objdiff_core::{
+    bindings::report::{
+        ChangeItem, ChangeItemInfo, ChangeUnit, Changes, ChangesInput, Measures, Report,
+        ReportCategory, ReportItem, ReportItemMetadata, ReportUnit, ReportUnitMetadata,
+        REPORT_VERSION,
+    },
+    config::ProjectObject,
+    diff, obj,
+    obj::{ObjSectionKind, ObjSymbolFlags},
+};
+use prost::Message;
+use rayon::iter::{IntoParallelRefMutIterator, ParallelIterator};
+use tracing::{info, warn};
+
+use crate::util::output::{write_output, OutputFormat};
+
+#[derive(FromArgs, PartialEq, Debug)]
+/// Generate a progress report for a project.
+#[argp(subcommand, name = "report")]
+pub struct Args {
+    #[argp(subcommand)]
+    command: SubCommand,
+}
+
+#[derive(FromArgs, PartialEq, Debug)]
+#[argp(subcommand)]
+pub enum SubCommand {
+    Generate(GenerateArgs),
+    Changes(ChangesArgs),
+}
+
+#[derive(FromArgs, PartialEq, Debug)]
+/// Generate a progress report for a project.
+#[argp(subcommand, name = "generate")]
+pub struct GenerateArgs {
+    #[argp(option, short = 'p')]
+    /// Project directory
+    project: Option<PathBuf>,
+    #[argp(option, short = 'o')]
+    /// Output file
+    output: Option<PathBuf>,
+    #[argp(switch, short = 'd')]
+    /// Deduplicate global and weak symbols (runs single-threaded)
+    deduplicate: bool,
+    #[argp(option, short = 'f')]
+    /// Output format (json, json-pretty, proto) (default: json)
+    format: Option<String>,
+}
+
+#[derive(FromArgs, PartialEq, Debug)]
+/// List any changes from a previous report.
+#[argp(subcommand, name = "changes")]
+pub struct ChangesArgs {
+    #[argp(positional)]
+    /// Previous report file
+    previous: PathBuf,
+    #[argp(positional)]
+    /// Current report file
+    current: PathBuf,
+    #[argp(option, short = 'o')]
+    /// Output file
+    output: Option<PathBuf>,
+    #[argp(option, short = 'f')]
+    /// Output format (json, json-pretty, proto) (default: json)
+    format: Option<String>,
+}
+
+pub fn run(args: Args) -> Result<()> {
+    match args.command {
+        SubCommand::Generate(args) => generate(args),
+        SubCommand::Changes(args) => changes(args),
+    }
+}
+
+fn generate(args: GenerateArgs) -> Result<()> {
+    let output_format = OutputFormat::from_option(args.format.as_deref())?;
+    let project_dir = args.project.as_deref().unwrap_or_else(|| Path::new("."));
+    info!("Loading project {}", project_dir.display());
+
+    let mut project = match objdiff_core::config::try_project_config(project_dir) {
+        Some((Ok(config), _)) => config,
+        Some((Err(err), _)) => bail!("Failed to load project configuration: {}", err),
+        None => bail!("No project configuration found"),
+    };
+    info!(
+        "Generating report for {} units (using {} threads)",
+        project.objects.len(),
+        if args.deduplicate { 1 } else { rayon::current_num_threads() }
+    );
+
+    let start = Instant::now();
+    let mut units = vec![];
+    let mut existing_functions: HashSet<String> = HashSet::new();
+    if args.deduplicate {
+        // If deduplicating, we need to run single-threaded
+        for object in &mut project.objects {
+            if let Some(unit) = report_object(
+                object,
+                project_dir,
+                project.target_dir.as_deref(),
+                project.base_dir.as_deref(),
+                Some(&mut existing_functions),
+            )? {
+                units.push(unit);
+            }
+        }
+    } else {
+        let vec = project
+            .objects
+            .par_iter_mut()
+            .map(|object| {
+                report_object(
+                    object,
+                    project_dir,
+                    project.target_dir.as_deref(),
+                    project.base_dir.as_deref(),
+                    None,
+                )
+            })
+            .collect::<Result<Vec<Option<ReportUnit>>>>()?;
+        units = vec.into_iter().flatten().collect();
+    }
+    let measures = units.iter().flat_map(|u| u.measures.into_iter()).collect();
+    let mut categories = Vec::new();
+    for category in &project.progress_categories {
+        categories.push(ReportCategory {
+            id: category.id.clone(),
+            name: category.name.clone(),
+            measures: Some(Default::default()),
+        });
+    }
+    let mut report =
+        Report { measures: Some(measures), units, version: REPORT_VERSION, categories };
+    report.calculate_progress_categories();
+    let duration = start.elapsed();
+    info!("Report generated in {}.{:03}s", duration.as_secs(), duration.subsec_millis());
+    write_output(&report, args.output.as_deref(), output_format)?;
+    Ok(())
+}
+
+fn report_object(
+    object: &mut ProjectObject,
+    project_dir: &Path,
+    target_dir: Option<&Path>,
+    base_dir: Option<&Path>,
+    mut existing_functions: Option<&mut HashSet<String>>,
+) -> Result<Option<ReportUnit>> {
+    object.resolve_paths(project_dir, target_dir, base_dir);
+    match (&object.target_path, &object.base_path) {
+        (None, Some(_)) if !object.complete().unwrap_or(false) => {
+            warn!("Skipping object without target: {}", object.name());
+            return Ok(None);
+        }
+        (None, None) => {
+            warn!("Skipping object without target or base: {}", object.name());
+            return Ok(None);
+        }
+        _ => {}
+    }
+    let config = diff::DiffObjConfig { relax_reloc_diffs: true, ..Default::default() };
+    let target = object
+        .target_path
+        .as_ref()
+        .map(|p| {
+            obj::read::read(p, &config).with_context(|| format!("Failed to open {}", p.display()))
+        })
+        .transpose()?;
+    let base = object
+        .base_path
+        .as_ref()
+        .map(|p| {
+            obj::read::read(p, &config).with_context(|| format!("Failed to open {}", p.display()))
+        })
+        .transpose()?;
+    let result = diff::diff_objs(&config, target.as_ref(), base.as_ref(), None)?;
+
+    let metadata = ReportUnitMetadata {
+        complete: object.complete(),
+        module_name: target
+            .as_ref()
+            .and_then(|o| o.split_meta.as_ref())
+            .and_then(|m| m.module_name.clone()),
+        module_id: target.as_ref().and_then(|o| o.split_meta.as_ref()).and_then(|m| m.module_id),
+        source_path: object.metadata.as_ref().and_then(|m| m.source_path.clone()),
+        progress_categories: object
+            .metadata
+            .as_ref()
+            .and_then(|m| m.progress_categories.clone())
+            .unwrap_or_default(),
+        auto_generated: object.metadata.as_ref().and_then(|m| m.auto_generated),
+    };
+    let mut measures = Measures::default();
+    let mut sections = vec![];
+    let mut functions = vec![];
+
+    let obj = target.as_ref().or(base.as_ref()).unwrap();
+    let obj_diff = result.left.as_ref().or(result.right.as_ref()).unwrap();
+    for (section, section_diff) in obj.sections.iter().zip(&obj_diff.sections) {
+        let section_match_percent = section_diff.match_percent.unwrap_or_else(|| {
+            // Support cases where we don't have a target object,
+            // assume complete means 100% match
+            if object.complete().unwrap_or(false) {
+                100.0
+            } else {
+                0.0
+            }
+        });
+        sections.push(ReportItem {
+            name: section.name.clone(),
+            fuzzy_match_percent: section_match_percent,
+            size: section.size,
+            metadata: Some(ReportItemMetadata {
+                demangled_name: None,
+                virtual_address: section.virtual_address,
+            }),
+        });
+
+        match section.kind {
+            ObjSectionKind::Data | ObjSectionKind::Bss => {
+                measures.total_data += section.size;
+                if section_match_percent == 100.0 {
+                    measures.matched_data += section.size;
+                }
+                continue;
+            }
+            ObjSectionKind::Code => (),
+        }
+
+        for (symbol, symbol_diff) in section.symbols.iter().zip(&section_diff.symbols) {
+            if symbol.size == 0 || symbol.flags.0.contains(ObjSymbolFlags::Hidden) {
+                continue;
+            }
+            if let Some(existing_functions) = &mut existing_functions {
+                if (symbol.flags.0.contains(ObjSymbolFlags::Global)
+                    || symbol.flags.0.contains(ObjSymbolFlags::Weak))
+                    && !existing_functions.insert(symbol.name.clone())
+                {
+                    continue;
+                }
+            }
+            let match_percent = symbol_diff.match_percent.unwrap_or_else(|| {
+                // Support cases where we don't have a target object,
+                // assume complete means 100% match
+                if object.complete().unwrap_or(false) {
+                    100.0
+                } else {
+                    0.0
+                }
+            });
+            measures.fuzzy_match_percent += match_percent * symbol.size as f32;
+            measures.total_code += symbol.size;
+            if match_percent == 100.0 {
+                measures.matched_code += symbol.size;
+            }
+            functions.push(ReportItem {
+                name: symbol.name.clone(),
+                size: symbol.size,
+                fuzzy_match_percent: match_percent,
+                metadata: Some(ReportItemMetadata {
+                    demangled_name: symbol.demangled_name.clone(),
+                    virtual_address: symbol.virtual_address,
+                }),
+            });
+            if match_percent == 100.0 {
+                measures.matched_functions += 1;
+            }
+            measures.total_functions += 1;
+        }
+    }
+    if metadata.complete.unwrap_or(false) {
+        measures.complete_code = measures.total_code;
+        measures.complete_data = measures.total_data;
+    }
+    measures.calc_fuzzy_match_percent();
+    measures.calc_matched_percent();
+    Ok(Some(ReportUnit {
+        name: object.name().to_string(),
+        measures: Some(measures),
+        sections,
+        functions,
+        metadata: Some(metadata),
+    }))
+}
+
+fn changes(args: ChangesArgs) -> Result<()> {
+    let output_format = OutputFormat::from_option(args.format.as_deref())?;
+    let (previous, current) = if args.previous == Path::new("-") && args.current == Path::new("-") {
+        // Special case for comparing two reports from stdin
+        let mut data = vec![];
+        std::io::stdin().read_to_end(&mut data)?;
+        let input = ChangesInput::decode(data.as_slice())?;
+        (input.from.unwrap(), input.to.unwrap())
+    } else {
+        let previous = read_report(&args.previous)?;
+        let current = read_report(&args.current)?;
+        (previous, current)
+    };
+    let mut changes = Changes { from: previous.measures, to: current.measures, units: vec![] };
+    for prev_unit in &previous.units {
+        let curr_unit = current.units.iter().find(|u| u.name == prev_unit.name);
+        let sections = process_items(prev_unit, curr_unit, |u| &u.sections);
+        let functions = process_items(prev_unit, curr_unit, |u| &u.functions);
+
+        let prev_measures = prev_unit.measures;
+        let curr_measures = curr_unit.and_then(|u| u.measures);
+        if !functions.is_empty() || prev_measures != curr_measures {
+            changes.units.push(ChangeUnit {
+                name: prev_unit.name.clone(),
+                from: prev_measures,
+                to: curr_measures,
+                sections,
+                functions,
+                metadata: curr_unit
+                    .as_ref()
+                    .and_then(|u| u.metadata.clone())
+                    .or_else(|| prev_unit.metadata.clone()),
+            });
+        }
+    }
+    for curr_unit in &current.units {
+        if !previous.units.iter().any(|u| u.name == curr_unit.name) {
+            changes.units.push(ChangeUnit {
+                name: curr_unit.name.clone(),
+                from: None,
+                to: curr_unit.measures,
+                sections: process_new_items(&curr_unit.sections),
+                functions: process_new_items(&curr_unit.functions),
+                metadata: curr_unit.metadata.clone(),
+            });
+        }
+    }
+    write_output(&changes, args.output.as_deref(), output_format)?;
+    Ok(())
+}
+
+fn process_items<F: Fn(&ReportUnit) -> &Vec<ReportItem>>(
+    prev_unit: &ReportUnit,
+    curr_unit: Option<&ReportUnit>,
+    getter: F,
+) -> Vec<ChangeItem> {
+    let prev_items = getter(prev_unit);
+    let mut items = vec![];
+    if let Some(curr_unit) = curr_unit {
+        let curr_items = getter(curr_unit);
+        for prev_func in prev_items {
+            let prev_func_info = ChangeItemInfo::from(prev_func);
+            let curr_func = curr_items.iter().find(|f| f.name == prev_func.name);
+            let curr_func_info = curr_func.map(ChangeItemInfo::from);
+            if let Some(curr_func_info) = curr_func_info {
+                if prev_func_info != curr_func_info {
+                    items.push(ChangeItem {
+                        name: prev_func.name.clone(),
+                        from: Some(prev_func_info),
+                        to: Some(curr_func_info),
+                        metadata: curr_func.as_ref().unwrap().metadata.clone(),
+                    });
+                }
+            } else {
+                items.push(ChangeItem {
+                    name: prev_func.name.clone(),
+                    from: Some(prev_func_info),
+                    to: None,
+                    metadata: prev_func.metadata.clone(),
+                });
+            }
+        }
+        for curr_func in curr_items {
+            if !prev_items.iter().any(|f| f.name == curr_func.name) {
+                items.push(ChangeItem {
+                    name: curr_func.name.clone(),
+                    from: None,
+                    to: Some(ChangeItemInfo::from(curr_func)),
+                    metadata: curr_func.metadata.clone(),
+                });
+            }
+        }
+    } else {
+        for prev_func in prev_items {
+            items.push(ChangeItem {
+                name: prev_func.name.clone(),
+                from: Some(ChangeItemInfo::from(prev_func)),
+                to: None,
+                metadata: prev_func.metadata.clone(),
+            });
+        }
+    }
+    items
+}
+
+fn process_new_items(items: &[ReportItem]) -> Vec<ChangeItem> {
+    items
+        .iter()
+        .map(|item| ChangeItem {
+            name: item.name.clone(),
+            from: None,
+            to: Some(ChangeItemInfo::from(item)),
+            metadata: item.metadata.clone(),
+        })
+        .collect()
+}
+
+fn read_report(path: &Path) -> Result<Report> {
+    if path == Path::new("-") {
+        let mut data = vec![];
+        std::io::stdin().read_to_end(&mut data)?;
+        return Report::parse(&data).with_context(|| "Failed to load report from stdin");
+    }
+    let file = File::open(path).with_context(|| format!("Failed to open {}", path.display()))?;
+    let mmap = unsafe { memmap2::Mmap::map(&file) }
+        .with_context(|| format!("Failed to map {}", path.display()))?;
+    Report::parse(mmap.as_ref())
+        .with_context(|| format!("Failed to load report {}", path.display()))
+}

objdiff-cli/src/main.rs

@@ -0,0 +1,141 @@
+mod argp_version;
+mod cmd;
+mod util;
+
+use std::{env, ffi::OsStr, fmt::Display, path::PathBuf, str::FromStr};
+
+use anyhow::{Error, Result};
+use argp::{FromArgValue, FromArgs};
+use enable_ansi_support::enable_ansi_support;
+use supports_color::Stream;
+use tracing_subscriber::{filter::LevelFilter, EnvFilter};
+
+#[derive(Debug, Eq, PartialEq, Copy, Clone)]
+enum LogLevel {
+    Error,
+    Warn,
+    Info,
+    Debug,
+    Trace,
+}
+
+impl FromStr for LogLevel {
+    type Err = ();
+
+    fn from_str(s: &str) -> Result<Self, Self::Err> {
+        Ok(match s {
+            "error" => Self::Error,
+            "warn" => Self::Warn,
+            "info" => Self::Info,
+            "debug" => Self::Debug,
+            "trace" => Self::Trace,
+            _ => return Err(()),
+        })
+    }
+}
+
+impl Display for LogLevel {
+    fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
+        f.write_str(match self {
+            LogLevel::Error => "error",
+            LogLevel::Warn => "warn",
+            LogLevel::Info => "info",
+            LogLevel::Debug => "debug",
+            LogLevel::Trace => "trace",
+        })
+    }
+}
+
+impl FromArgValue for LogLevel {
+    fn from_arg_value(value: &OsStr) -> Result<Self, String> {
+        String::from_arg_value(value)
+            .and_then(|s| Self::from_str(&s).map_err(|_| "Invalid log level".to_string()))
+    }
+}
+
+#[derive(FromArgs, PartialEq, Debug)]
+/// A local diffing tool for decompilation projects.
+struct TopLevel {
+    #[argp(subcommand)]
+    command: SubCommand,
+    #[argp(option, short = 'C')]
+    /// Change working directory.
+    chdir: Option<PathBuf>,
+    #[argp(option, short = 'L')]
+    /// Minimum logging level. (Default: info)
+    /// Possible values: error, warn, info, debug, trace
+    log_level: Option<LogLevel>,
+    /// Print version information and exit.
+    #[argp(switch, short = 'V')]
+    version: bool,
+    /// Disable color output. (env: NO_COLOR)
+    #[argp(switch)]
+    no_color: bool,
+}
+
+#[derive(FromArgs, PartialEq, Debug)]
+#[argp(subcommand)]
+enum SubCommand {
+    Diff(cmd::diff::Args),
+    Report(cmd::report::Args),
+}
+
+// Duplicated from supports-color so we can check early.
+fn env_no_color() -> bool {
+    match env::var("NO_COLOR").as_deref() {
+        Ok("") | Ok("0") | Err(_) => false,
+        Ok(_) => true,
+    }
+}
+
+fn main() {
+    let args: TopLevel = argp_version::from_env();
+    let use_colors = if args.no_color || env_no_color() {
+        false
+    } else {
+        // Try to enable ANSI support on Windows.
+        let _ = enable_ansi_support();
+        // Disable isatty check for supports-color. (e.g. when used with ninja)
+        unsafe { env::set_var("IGNORE_IS_TERMINAL", "1") };
+        supports_color::on(Stream::Stdout).is_some_and(|c| c.has_basic)
+    };
+
+    let format =
+        tracing_subscriber::fmt::format().with_ansi(use_colors).with_target(false).without_time();
+    let builder = tracing_subscriber::fmt().event_format(format).with_writer(std::io::stderr);
+    if let Some(level) = args.log_level {
+        builder
+            .with_max_level(match level {
+                LogLevel::Error => LevelFilter::ERROR,
+                LogLevel::Warn => LevelFilter::WARN,
+                LogLevel::Info => LevelFilter::INFO,
+                LogLevel::Debug => LevelFilter::DEBUG,
+                LogLevel::Trace => LevelFilter::TRACE,
+            })
+            .init();
+    } else {
+        builder
+            .with_env_filter(
+                EnvFilter::builder()
+                    .with_default_directive(LevelFilter::INFO.into())
+                    .from_env_lossy(),
+            )
+            .init();
+    }
+
+    let mut result = Ok(());
+    if let Some(dir) = &args.chdir {
+        result = env::set_current_dir(dir).map_err(|e| {
+            Error::new(e)
+                .context(format!("Failed to change working directory to '{}'", dir.display()))
+        });
+    }
+    result = result.and_then(|_| match args.command {
+        SubCommand::Diff(c_args) => cmd::diff::run(c_args),
+        SubCommand::Report(c_args) => cmd::report::run(c_args),
+    });
+    if let Err(e) = result {
+        eprintln!("Failed: {e:?}");
+        std::process::exit(1);
+    }
+}

objdiff-cli/src/util/mod.rs

@@ -0,0 +1,2 @@
+pub mod output;
+pub mod term;

objdiff-cli/src/util/output.rs

@@ -0,0 +1,84 @@
+use std::{
+    fs::File,
+    io::{BufWriter, Write},
+    ops::DerefMut,
+    path::Path,
+};
+
+use anyhow::{bail, Context, Result};
+use tracing::info;
+
+#[derive(Debug, Copy, Clone, PartialEq, Eq, Default)]
+pub enum OutputFormat {
+    #[default]
+    Json,
+    JsonPretty,
+    Proto,
+}
+
+impl OutputFormat {
+    pub fn from_str(s: &str) -> Result<Self> {
+        match s.to_ascii_lowercase().as_str() {
+            "json" => Ok(Self::Json),
+            "json-pretty" | "json_pretty" => Ok(Self::JsonPretty),
+            "binpb" | "pb" | "proto" | "protobuf" => Ok(Self::Proto),
+            _ => bail!("Invalid output format: {}", s),
+        }
+    }
+
+    pub fn from_option(s: Option<&str>) -> Result<Self> {
+        match s {
+            Some(s) => Self::from_str(s),
+            None => Ok(Self::default()),
+        }
+    }
+}
+
+pub fn write_output<T>(input: &T, output: Option<&Path>, format: OutputFormat) -> Result<()>
+where T: serde::Serialize + prost::Message {
+    match output {
+        Some(output) if output != Path::new("-") => {
+            info!("Writing to {}", output.display());
+            let file = File::options()
+                .read(true)
+                .write(true)
+                .create(true)
+                .truncate(true)
+                .open(output)
+                .with_context(|| format!("Failed to create file {}", output.display()))?;
+            match format {
+                OutputFormat::Json => {
+                    let mut output = BufWriter::new(file);
+                    serde_json::to_writer(&mut output, input)
+                        .context("Failed to write output file")?;
+                    output.flush().context("Failed to flush output file")?;
+                }
+                OutputFormat::JsonPretty => {
+                    let mut output = BufWriter::new(file);
+                    serde_json::to_writer_pretty(&mut output, input)
+                        .context("Failed to write output file")?;
+                    output.flush().context("Failed to flush output file")?;
+                }
+                OutputFormat::Proto => {
+                    file.set_len(input.encoded_len() as u64)?;
+                    let map = unsafe { memmap2::Mmap::map(&file) }
+                        .context("Failed to map output file")?;
+                    let mut output = map.make_mut().context("Failed to remap output file")?;
+                    input.encode(&mut output.deref_mut()).context("Failed to encode output")?;
+                }
+            }
+        }
+        _ => match format {
+            OutputFormat::Json => {
+                serde_json::to_writer(std::io::stdout(), input)?;
+            }
+            OutputFormat::JsonPretty => {
+                serde_json::to_writer_pretty(std::io::stdout(), input)?;
+            }
+            OutputFormat::Proto => {
+                std::io::stdout().write_all(&input.encode_to_vec())?;
+            }
+        },
+    }
+    Ok(())
+}

objdiff-cli/src/util/term.rs

@@ -0,0 +1,16 @@
+use std::{io::stdout, panic};
+
+use crossterm::{
+    cursor::Show,
+    event::DisableMouseCapture,
+    terminal::{disable_raw_mode, LeaveAlternateScreen},
+};
+
+pub fn crossterm_panic_handler() {
+    let original_hook = panic::take_hook();
+    panic::set_hook(Box::new(move |panic_info| {
+        let _ = crossterm::execute!(stdout(), LeaveAlternateScreen, DisableMouseCapture, Show);
+        let _ = disable_raw_mode();
+        original_hook(panic_info);
+    }));
+}

objdiff-core/Cargo.toml

@@ -0,0 +1,80 @@
+[package]
+name = "objdiff-core"
+version.workspace = true
+edition.workspace = true
+rust-version.workspace = true
+authors.workspace = true
+license.workspace = true
+repository.workspace = true
+readme = "README.md"
+description = """
+A local diffing tool for decompilation projects.
+"""
+documentation = "https://docs.rs/objdiff-core"
+
+[lib]
+crate-type = ["cdylib", "rlib"]
+
+[features]
+all = ["config", "dwarf", "mips", "ppc", "x86", "arm", "bindings"]
+any-arch = [] # Implicit, used to check if any arch is enabled
+config = ["globset", "semver", "serde_json", "serde_yaml"]
+dwarf = ["gimli"]
+mips = ["any-arch", "rabbitizer"]
+ppc = ["any-arch", "cwdemangle", "cwextab", "ppc750cl"]
+x86 = ["any-arch", "cpp_demangle", "iced-x86", "msvc-demangler"]
+arm = ["any-arch", "cpp_demangle", "unarm", "arm-attr"]
+bindings = ["serde_json", "prost", "pbjson"]
+wasm = ["bindings", "console_error_panic_hook", "console_log"]
+
+[package.metadata.docs.rs]
+features = ["all"]
+
+[dependencies]
+anyhow = "1.0"
+byteorder = "1.5"
+filetime = "0.2"
+flagset = "0.4"
+log = "0.4"
+memmap2 = "0.9"
+num-traits = "0.2"
+object = { version = "0.36", features = ["read_core", "std", "elf", "pe"], default-features = false }
+pbjson = { version = "0.7", optional = true }
+prost = { version = "0.13", optional = true }
+serde = { version = "1.0", features = ["derive"] }
+similar = { version = "2.6", default-features = false }
+strum = { version = "0.26", features = ["derive"] }
+wasm-bindgen = "0.2"
+tsify-next = { version = "0.5", default-features = false, features = ["js"] }
+console_log = { version = "1.0", optional = true }
+console_error_panic_hook = { version = "0.1", optional = true }
+
+# config
+globset = { version = "0.4", features = ["serde1"], optional = true }
+semver = { version = "1.0", optional = true }
+serde_json = { version = "1.0", optional = true }
+serde_yaml = { version = "0.9", optional = true }
+
+# dwarf
+gimli = { version = "0.31", default-features = false, features = ["read-all"], optional = true }
+
+# ppc
+cwdemangle = { version = "1.0", optional = true }
+cwextab = { version = "0.3", optional = true }
+ppc750cl = { version = "0.3", optional = true }
+
+# mips
+rabbitizer = { version = "1.12", optional = true }
+
+# x86
+cpp_demangle = { version = "0.4", optional = true }
+iced-x86 = { version = "1.21", default-features = false, features = ["std", "decoder", "intel", "gas", "masm", "nasm", "exhaustive_enums"], optional = true }
+msvc-demangler = { version = "0.10", optional = true }
+
+# arm
+unarm = { version = "1.6", optional = true }
+arm-attr = { version = "0.1", optional = true }
+
+[build-dependencies]
+prost-build = "0.13"
+pbjson-build = "0.7"

objdiff-core/README.md

@@ -0,0 +1,14 @@
+# objdiff-core
+
+objdiff-core contains the core functionality of [objdiff](https://github.com/encounter/objdiff), a tool for comparing object files in decompilation projects. See the main repository for more information.
+
+## Crate feature flags
+
+- **`all`**: Enables all main features.
+- **`config`**: Enables objdiff configuration file support.
+- **`dwarf`**: Enables extraction of line number information from DWARF debug sections.
+- **`mips`**: Enables the MIPS backend powered by [rabbitizer](https://github.com/Decompollaborate/rabbitizer). (Note: C library with Rust bindings)
+- **`ppc`**: Enables the PowerPC backend powered by [ppc750cl](https://github.com/encounter/ppc750cl).
+- **`x86`**: Enables the x86 backend powered by [iced-x86](https://crates.io/crates/iced-x86).
+- **`arm`**: Enables the ARM backend powered by [unarm](https://github.com/AetiasHax/unarm).
+- **`bindings`**: Enables serialization and deserialization of objdiff data structures.

objdiff-core/build.rs

@@ -0,0 +1,54 @@
+use std::path::{Path, PathBuf};
+
+fn main() {
+    let root = PathBuf::from(env!("CARGO_MANIFEST_DIR")).join("protos");
+    let descriptor_path = root.join("proto_descriptor.bin");
+    println!("cargo:rerun-if-changed={}", descriptor_path.display());
+    let descriptor_mtime = std::fs::metadata(&descriptor_path)
+        .map(|m| m.modified().unwrap())
+        .unwrap_or(std::time::SystemTime::UNIX_EPOCH);
+    let mut run_protoc = false;
+    let proto_files = vec![root.join("diff.proto"), root.join("report.proto")];
+    for proto_file in &proto_files {
+        println!("cargo:rerun-if-changed={}", proto_file.display());
+        let mtime = match std::fs::metadata(proto_file) {
+            Ok(m) => m.modified().unwrap(),
+            Err(e) => panic!("Failed to stat proto file {}: {:?}", proto_file.display(), e),
+        };
+        if mtime > descriptor_mtime {
+            run_protoc = true;
+        }
+    }
+
+    fn prost_config(descriptor_path: &Path, run_protoc: bool) -> prost_build::Config {
+        let mut config = prost_build::Config::new();
+        config.file_descriptor_set_path(descriptor_path);
+        // If our cached descriptor is up-to-date, we don't need to run protoc.
+        // This is helpful so that users don't need to have protoc installed
+        // unless they're updating the protos.
+        if !run_protoc {
+            config.skip_protoc_run();
+        }
+        config
+    }
+    if let Err(e) =
+        prost_config(&descriptor_path, run_protoc).compile_protos(&proto_files, &[root.as_path()])
+    {
+        if e.kind() == std::io::ErrorKind::NotFound && e.to_string().contains("protoc") {
+            eprintln!("protoc not found, skipping protobuf compilation");
+            prost_config(&descriptor_path, false)
+                .compile_protos(&proto_files, &[root.as_path()])
+                .expect("Failed to compile protos");
+        } else {
+            panic!("Failed to compile protos: {e:?}");
+        }
+    }
+
+    let descriptor_set = std::fs::read(descriptor_path).expect("Failed to read descriptor set");
+    pbjson_build::Builder::new()
+        .register_descriptors(&descriptor_set)
+        .expect("Failed to register descriptors")
+        .preserve_proto_field_names()
+        .build(&[".objdiff"])
+        .expect("Failed to build pbjson");
+}