3 files changed, 118 insertions, 0 deletions
diff --git a/silpa/utils/__init__.py b/silpa/utils/__init__.py
new file mode 100644
index 0000000..b7b55b1
--- /dev/null
+++ b/silpa/utils/__init__.py
@@ -0,0 +1,4 @@
+#! /usr/bin/env python
+# -*- coding: utf-8 -*-
+from  silpautils import *
+from langdetect import *
diff --git a/silpa/utils/langdetect.py b/silpa/utils/langdetect.py
new file mode 100644
index 0000000..727ea6d
--- /dev/null
+++ b/silpa/utils/langdetect.py
@@ -0,0 +1,79 @@
+#  Spellchecker with language detection
+#  coding: utf-8
+#
+#  Copyright © 2008  Santhosh Thottingal
+#  Released under the GPLV3+ license
+
+from common import *
+
+class LangDetect(SilpaModule):
+		
+	def detect_lang(self, text):
+		words=text.split(" ")
+		word_count=len(words)
+		word_iter=0
+		word=""
+		result_dict=dict()
+		while word_iter < word_count:
+			word=words[word_iter]
+			if(word):
+				length = len(word)
+				index = 0
+				while index < length:
+					letter=word[index]
+					if ((letter >= u'ം') &  (letter <=u'൯')):
+						result_dict[word]= "ml_IN"
+					if ((letter >= u'ঁ') &  (letter <= u'৺')):
+						result_dict[word]= "bn_IN"
+					if ((letter >= u'ँ') &  (letter <= u'ॿ')):
+						result_dict[word]= "hi_IN"
+					if ((letter >=u'ઁ') &  (letter <= u'૱')):
+						result_dict[word]= "gu_IN"
+					if ((letter >= u'ਁ') &  (letter <=u'ੴ')):
+						result_dict[word]= "pa_IN"
+					if ((letter >= u'ಂ') &  (letter <=u'ೲ')):
+						result_dict[word]= "ka_IN"
+					if ((letter >= u'ଁ') &  (letter <= u'ୱ')):
+						result_dict[word]= "or_IN"
+					if ((letter >=u'ஂ') &  (letter <= u'௺')):
+						result_dict[word]= "ta_IN"
+					if ((letter >=u'ఁ') &  (letter <= u'౯')):
+						result_dict[word]= "te_IN"
+					if ((letter <= u'z')):
+						result_dict[word]= "en_US"
+						
+					index=index+1	
+			word_iter=word_iter+1	
+		return result_dict
+	def process(self,form):
+		response = """
+		<h2>Language Detection</h2></hr>
+		<p>Enter the text for detecting the language in the below text area.
+		 Language of each  word will be detected. 
+		 You can give the text in any language and even with mixed language
+		</p>
+		<form action="" method="post">
+		<textarea cols='100' rows='25' name='input_text' id='id1'>%s</textarea>
+		<input  type="submit" id="Detect Language" value="Detect Language"  name="action" style="width:12em;"/>
+		<input type="reset" value="Clear" style="width:12em;"/>
+		</br>
+		</form>
+		"""
+		if(form.has_key('input_text')):
+			text = action=form['input_text'].value	.decode('utf-8')
+			response=response % text
+			detected_lang_dict = self.detect_lang(text)
+			response = response+"<h2>Language Detection Results</h2></hr>"
+			response = response+"<table class=\"table1\"><tr><th>Word</th><th>Language</th></tr>"
+			for key in detected_lang_dict:
+				response = response+"<tr><td>"+key+"</td><td>"+detected_lang_dict[key]+"</td></tr>"
+			response = response+"</table>	"
+		else:
+			response=response % ""	
+		return response
+	def get_module_name(self):
+		return "Indian Language Detector"
+	def get_info(self):
+		return 	"Detects the language of the given text word by word. Supports only Indian Language"	
+def getInstance():
+	return LangDetect()
diff --git a/silpa/utils/silpautils.py b/silpa/utils/silpautils.py
new file mode 100644
index 0000000..02556af
--- /dev/null
+++ b/silpa/utils/silpautils.py
@@ -0,0 +1,35 @@
+#! /usr/bin/env python
+# -*- coding: utf-8 -*-
+import codecs
+def getTemplate():
+	return open(getTemplateName()).read()
+def getTemplateName():
+	return loadConfiguration()["SILPA_TEMPLATE"]	
+def getCopyrightInfo():
+	return loadConfiguration()["SILPA_SITE_COPYRIGHT"]		
+def getModulesList():
+	conf_dict=loadConfiguration()
+	action_dict={}
+	for item in conf_dict	:
+		if(item.startswith("SILPA_ACTION.")):
+			action_dict[item.replace("SILPA_ACTION.","")]=conf_dict[item]
+	return 	action_dict	
+def loadConfiguration():
+	conf_dict={}
+	conffile = codecs. open("silpa.conf",encoding='utf-8', errors='ignore')
+	while 1:
+		text = unicode( conffile.readline())
+		if text == "":
+			  break
+		line = text.split("#")[0].strip()
+		if(line == ""):
+			  continue 
+		try:	  
+			lhs = line.split("=") [ 0 ]  
+			rhs = line.split("=") [ 1 ]  
+			conf_dict[lhs]=rhs
+		except:
+			pass	
+	return conf_dict
+if __name__ == '__main__':
+	print getModulesList()