Fix UTF-8 encoding issue (#900)

* Force UTF-8 generation.

* Rebuilt UTF-8 clean.

* Force reading in utf-8.

scalene/scalene-gui/package.json

@@ -24,6 +24,7 @@
     "process": "^0.11.10",
     "stream-browserify": "^3.0.0",
     "stream-http": "^3.2.0",
+    "terser-webpack-plugin": "^5.3.11",
     "url": "^0.11.4",
     "util": "^0.12.5",
     "webpack": "^5.96.1",

scalene/scalene-gui/webpack.config.js

@@ -1,5 +1,6 @@
 const path = require('path');
 const webpack = require('webpack');
+const TerserPlugin = require('terser-webpack-plugin');
 
 module.exports = {
   entry: './scalene-gui.js',
@@ -11,30 +12,43 @@ module.exports = {
   },
   resolve: {
     fallback: {
-      "crypto": require.resolve("crypto-browserify"),
-      "stream": require.resolve("stream-browserify"),
-      "buffer": require.resolve("buffer"),
-      "util": require.resolve("util"),
-      "assert": require.resolve("assert"),
-      "os": require.resolve("os-browserify/browser"),
-      "http": require.resolve("stream-http"),
-      "https": require.resolve("https-browserify"),
-      "url": require.resolve("url/"),
-      "zlib": require.resolve("browserify-zlib"),
-      "path": require.resolve("path-browserify"),
-      "fs": false,
+      crypto: require.resolve('crypto-browserify'),
+      stream: require.resolve('stream-browserify'),
+      buffer: require.resolve('buffer'),
+      util: require.resolve('util'),
+      assert: require.resolve('assert'),
+      os: require.resolve('os-browserify/browser'),
+      http: require.resolve('stream-http'),
+      https: require.resolve('https-browserify'),
+      url: require.resolve('url/'),
+      zlib: require.resolve('browserify-zlib'),
+      path: require.resolve('path-browserify'),
+      fs: false,
     },
   },
   plugins: [
     new webpack.ProvidePlugin({
       process: 'process/browser',
     }),
+    new webpack.DefinePlugin({
+      'process.env.LANG': JSON.stringify('en_US.UTF-8'),
+    }),
   ],
   optimization: {
-    minimize: true,            // Enable minimization
-    usedExports: false,         // Disable tree shaking
-    sideEffects: false,         // Include all files, assuming they have side effects
-    concatenateModules: false,  // Disable module concatenation (scope hoisting)
-    innerGraph: false,          // Disable inner graph analysis
+    minimize: true,
+    minimizer: [
+      new TerserPlugin({
+        terserOptions: {
+          output: {
+            ascii_only: true, // Escape non-ASCII characters
+          },
+        },
+      }),
+    ],
+    usedExports: false,
+    sideEffects: false,
+    concatenateModules: false,
+    innerGraph: false,
   },
+  devtool: 'source-map', // Enable debugging via source maps
 };

scalene/scalene_utility.py

@@ -110,12 +110,26 @@ def read_file_content(
         directory: str, subdirectory: str, filename: str
     ) -> str:
         file_path = os.path.join(directory, subdirectory, filename)
-        return pathlib.Path(file_path).read_text()
+        file_content = ""
+        try:
+            file_content = pathlib.Path(file_path).read_text(encoding="utf-8")
+        except UnicodeDecodeError as e:
+            raise UnicodeDecodeError(
+                f"Failed to decode file {file_path}. Ensure the file is UTF-8 encoded."
+            ) from e
+        return file_content
 
     try:
         # Load the profile
         profile_file = pathlib.Path(profile_fname)
-        profile = profile_file.read_text()
+        profile = ""
+        try:
+            profile = profile_file.read_text(encoding="utf-8")
+        except UnicodeDecodeError as e:
+            raise UnicodeDecodeError(
+                f"Failed to decode file {profile_file}. Ensure the file is UTF-8 encoded."
+            ) from e
+
     except FileNotFoundError:
         assert profile_fname == "demo"
         profile = ""