jschardet - npm Package Compare versions

Comparing version 3.1.2 to 3.1.3

package.json

 {
     "name": "jschardet",
-    "version": "3.1.2",
+    "version": "3.1.3",
     "description": "Character encoding auto-detection in JavaScript (port of python's chardet)",
@@ -5,0 +5,0 @@ "author": "António Afonso",

src/universaldetector.js

@@ -238,11 +238,32 @@ /*
 
-        if( this._mInputState == _state.highbyte ) {
-            for( var i = 0, prober; prober = this._mCharsetProbers[i]; i++ ) {
-                if( !prober || !prober.getCharsetName() || !canDetectEncoding(prober.getCharsetName()) ) continue;
+        if (this._mInputState == _state.highbyte) {
+            let windows_1252_confidence = 0;
+            let windows_1250_detected = false;
+            for (var i = 0, prober; prober = this._mCharsetProbers[i]; i++) {
+                if (!prober) continue;
+                const charsetName = prober.getCharsetName();
+                const confidence = prober.getConfidence();
+                if (prober.getCharsetName() === "windows-1252") {
+                    windows_1252_confidence = confidence;
+                }
+                if (!charsetName || !canDetectEncoding(charsetName)) continue;
                 this.results.push({
                     "encoding": prober.getCharsetName(),
-                    "confidence": prober.getConfidence()
+                    "confidence": confidence
                 });
-                logger.log(prober.getCharsetName() + " confidence " + prober.getConfidence());
+                if (prober.getCharsetName() === "windows-1250") {
+                    windows_1250_detected = true;
+                }
+                logger.log(prober.getCharsetName() + " confidence " + confidence);
             }
+            // HACK: When windows-1252 is detected it's almost sure that it can
+            // also be windows-1250.
+            // https://en.wikipedia.org/wiki/Windows-1250 (Central European)
+            if (windows_1252_confidence && !windows_1250_detected && canDetectEncoding("windows-1250")) {
+                this.results.push({
+                    "encoding": "windows-1250",
+                    // Report the confidence just a bit under windows-1252's.
+                    "confidence": windows_1252_confidence - Math.pow(5/10, (String(windows_1252_confidence).length - 1)),
+                });
+            }
             this.results.sort(function(a, b) {
@@ -249,0 +270,0 @@ return b.confidence - a.confidence;

New alerts

License Policy Violation

License

This package is not allowed per your license policy. Review the package's license to ensure compliance.

Found 1 instance in 1 package

Fixed alerts

License Policy Violation

License

This package is not allowed per your license policy. Review the package's license to ensure compliance.

Found 1 instance in 1 package

Improved metrics

Total package byte prevSize

1320285

increased by0.18%

Lines of code

16300

increased by0.28%

No dependency changes