node-icu-charset-detector - npm Package Compare versions

Comparing version 0.0.6 to 0.0.7

node-icu-charset-detector.js

@@ -6,2 +6,6 @@ var CharsetMatch = require("./build/Release/node-icu-charset-detector").CharsetMatch;
 
+  if (charsetMatch.getName() === null) {
+    return null;
+  }
+
   var charset = new String(charsetMatch.getName());
@@ -14,3 +18,28 @@ charset.language = charsetMatch.getLanguage();
 
+function detectCharsetStream(stream, onDetectionFinish) {
+  var buffer = null;
+  var finished = false;
+
+  function onChunkArrives(chunk) {
+    buffer = buffer ? Buffer.concat(buffer, chunk) : chunk;
+
+    var charset = detectCharset(buffer);
+    if (charset !== null) {
+      // detection succeed. stop reading chunks.
+      stream.removeListener("data", onChunkArrives);
+      finished = true;
+      onDetectionFinish(charset);
+    }
+  }
+
+  stream.on("data", onChunkArrives);
+  stream.on("end", function () {
+    if (!finished) {
+      onDetectionFinish(null);
+    }
+  });
+}
+
 exports.detectCharset = detectCharset;
+exports.detectCharsetStream = detectCharsetStream;
 exports.CharsetMatch = CharsetMatch;

package.json

 {
-  "name"        : "node-icu-charset-detector",
-  "version"     : "0.0.6",
-  "main"        : "./node-icu-charset-detector.js",
-  "description" : "Simple binding for ICU charset detector",
-  "keywords"    : ["charset-detection", "icu"],
+  "name": "node-icu-charset-detector",
+  "version": "0.0.7",
+  "main": "./node-icu-charset-detector.js",
+  "description": "Simple binding for ICU charset detector",
+  "keywords": [
+    "charset-detection",
+    "icu"
+  ],
   "repository": {
@@ -19,3 +22,5 @@ "type": "git",
   "licenses": [
-    { "type": "MIT" }
+    {
+      "type": "MIT"
+    }
   ],
@@ -22,0 +27,0 @@ "engines": {

README.md

@@ -9,10 +9,45 @@ # ICU Character Set Detection for Node.js
 
-At first, install `libicu` into your system. Debian users can install `libicu` by `apt-get` easily.
+At first, install `libicu` into your system (See [this instruction](#installing-icu) for details).
 
-    sudo apt-get install libicu-dev
-
 After that, install `node-icu-charset-detector` from npm.
 
-    npm install node-icu-charset-detector
+    ```npm install node-icu-charset-detector```
 
+### Installing ICU
+
+#### Linux
+
+* Debian (Ubuntu)
+
+    ```apt-get install libicu-dev```
+
+* Gentoo
+
+    ```emerge icu```
+
+#### OSX
+
+* MacPorts
+
+    ```port install icu +devel```
+
+* Homebrew
+
+    ```shell
+    brew install icu4c
+    ln -s /usr/local/Cellar/icu4c/<VERSION>/bin/icu-config /usr/local/bin/icu-config
+    ln -s /usr/local/Cellar/icu4c/<VERSION>/include/unicode /usr/local/include
+    ```
+
+If experiencing issues with 'homebrew' installing version 50.1 of icu4c, try the following:
+
+    ```shell
+    brew search icu4c
+    brew tap homebrew/versions
+    brew versions icu4c
+    cd $(brew --prefix) && git pull --rebase
+    git checkout c25fd2f $(brew --prefix)/Library/Formula/icu4c.rb
+    brew install icu4c
+    ```
+
 ## Usage
@@ -24,11 +59,13 @@
 
-    var charsetDetector = require("node-icu-charset-detector");
+```javascript
+var charsetDetector = require("node-icu-charset-detector");
 
-    var buffer = fs.readFileSync("/path/to/the/file");
-    var charset = charsetDetector.detectCharset(buffer);
-    
-    console.log("charset name: " + charset.toString());
-    console.log("language: " + charset.language);
-    console.log("detection confidence: " + charset.confidence);
+var buffer = fs.readFileSync("/path/to/the/file");
+var charset = charsetDetector.detectCharset(buffer);
 
+console.log("charset name: " + charset.toString());
+console.log("language: " + charset.language);
+console.log("detection confidence: " + charset.confidence);
+```
+
 `detectCharset(buffer)` returns the detected charset name for `buffer`, and the returned charset name has two extra properties `language` and `confidence`:
@@ -47,16 +84,18 @@
 
-    function bufferToString(buffer) {
-      var charsetDetector = require("node-icu-charset-detector");
-      var charset = charsetDetector.detectCharset(buffer).toString();
+```javascript
+function bufferToString(buffer) {
+  var charsetDetector = require("node-icu-charset-detector");
+  var charset = charsetDetector.detectCharset(buffer).toString();
 
-      try {
-        return buffer.toString(charset);
-      } catch (x) {
-        var Iconv = require("iconv").Iconv;
-        var charsetConverter = new Iconv(charset, "utf8");
-        return charsetConverter.convert(buffer).toString();
-      }
-    }
+  try {
+    return buffer.toString(charset);
+  } catch (x) {
+    var Iconv = require("iconv").Iconv;
+    var charsetConverter = new Iconv(charset, "utf8");
+    return charsetConverter.convert(buffer).toString();
+  }
+}
 
-    var buffer = fs.readFileSync("/path/to/the/file");
-    var bufferString = bufferToString(buffer);
+var buffer = fs.readFileSync("/path/to/the/file");
+var bufferString = bufferToString(buffer);
+```

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

Trivial Package

Supply chain risk

Packages less than 10 lines of code are easily copied into your own project and may not warrant the additional supply chain risk of an external dependency.

Found 1 instance in 1 package

Improved metrics

Total package byte prevSize

10866

increased by18.3%

Lines of code

34

increased by240%

Number of lines in readme file

99

increased by65%

Number of medium supply chain risk alerts

1

decreased by-50%

No dependency changes