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

Comparing version 0.0.5 to 0.0.6

node-icu-charset-detector.js

package.json

		{
		"name" : "node-icu-charset-detector",
		"version" : "0.0.5",
		"main" : "./build/Release/node-icu-charset-detector",
		"version" : "0.0.6",
		"main" : "./node-icu-charset-detector.js",
		"description" : "Simple binding for ICU charset detector",
		@@ -6,0 +6,0 @@ "keywords" : ["charset-detection", "icu"],

README.md

		@@ -17,10 +17,2 @@ # ICU Character Set Detection for Node.js

		If you prefer to install the package by hand, try following commands.

		git clone git://github.com/mooz/node-icu-charset-detector.git
		cd node-icu-charset-detector
		node-waf configure
		node-waf build
		node-waf install

		## Usage
		@@ -30,35 +22,34 @@

		`node-icu-charset-detector` provides a class `CharsetMatch` which takes a instance of `Buffer` for the first argument of the constructor. A instance of `CharsetMatch` has three methods below.
		`node-icu-charset-detector` provides a function `detectCharset(buffer)`, where `buffer` is an instance of `Buffer` whose charset should be detected.

		- `CharsetMatch.prototype.getName()`
		- returns the name of detected character set.
		- `CharsetMatch.prototype.getLanguage()`
		- returns the language for detected character set.
		- `CharsetMatch.prototype.getConfidence()`
		- returns the confidence of detection.
		var charsetDetector = require("node-icu-charset-detector");

		Here is a simple usage of `node-icu-charset-detector`.

		var charsetDetector = require("node-icu-charset-detector");
		var CharsetMatch = charsetDetector.CharsetMatch;
		var buffer = fs.readFileSync("/path/to/the/file");
		var charset = charsetDetector.detectCharset(buffer);

		var byteArray = fs.readFileSync(path);
		var charsetMatch = new CharsetMatch(byteArray);

		var detectedCharsetName = charsetMatch.getName();
		var detectedLanguage = charsetMatch.getLanguage();
		var detectionConfidence = charsetMatch.getConfidence();
		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`:

		- `charset.language`
		- language name for the detected character set.
		- `charset.confidence`
		- confidence of the charset detection for `charset`.

		### Leveraging node-iconv

		Since ICU itself does not have a feature to convert character sets, you may need to use `node-iconv` (https://github.com/bnoordhuis/node-iconv) which has a powerful character sets converting feature.
		Since ICU itself does not have a feature to convert character sets, you may need to use `node-iconv` (https://github.com/bnoordhuis/node-iconv), which has a powerful character sets converting feature.

		Here is a simple example to leverage `node-iconv` to convert character sets which is not supported by native Node.js.
		Here is a simple example to leverage `node-iconv` to convert character sets not supported by Node itself.

		var Iconv = require("iconv").Iconv;

		function bufferToString(buffer, charset) {
		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");
		@@ -68,4 +59,4 @@ return charsetConverter.convert(buffer).toString();
		}

		var charsetMatch = new CharsetMatch(byteArray);
		var bufferString = bufferToString(byteArray, charsetMatch.getName());

		var buffer = fs.readFileSync("/path/to/the/file");
		var bufferString = bufferToString(buffer);

node-icu-charset-detector.cpp

Sorry, the diff of this file is not supported yet

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

New alerts

Fixed alerts

Improved metrics

Worsened metrics