--- cdli/cdli_files.py	2006/12/22 20:35:33	1.55
+++ cdli/cdli_files.py	2007/01/09 16:06:09	1.57
@@ -22,6 +22,7 @@ from ZPublisher.HTTPResponse import HTTP
 from ZPublisher.BaseRequest import RequestContainer
 import threading
 from BTrees.OOBTree import OOBTree
+import logging
 
 def unique(s):
     """Return a list of the elements in s, but without duplicates.
@@ -1932,30 +1933,64 @@ class CDLIRoot(Folder):
     meta_type="CDLIRoot"
     downloadCounterBaskets=0# counts the current basket downloads if counter > 10 no downloads are possible
     
+    def findWordRegExp(self,searchTerm):
+        """find all words in index which match regexp in SearchTerm"""
+        ret=[]
+        for x in self.lineIndex.iterkeys():
+            if re.match(searchTerm,x):
+                ret.append(x)
+        return ret
+    
+    def searchRegExpInLineIndexDocs(self,searchTerm):
+        """search in inLineIndex with regexp"""
+        if not searchTerm:
+            return []
+        ret=[]
+        words=self.findWordRegExp(searchTerm) # suche nach allen Treffern
+        logging.info("wd:%s"%words)
+        for word in words:
+            ret+=self.searchInLineIndexDocs(word)
+        
+        return unique(ret)
+        
     def showInLineIndex(self):
         """get the index for debug purposes"""
         print "show"
         for x in self.lineIndex.iterkeys():
-            print "word:",x
-            for y in self.lineIndex[x].iterkeys():
-                print "doc",y,self.lineIndex[x][y]
+            logging.info("word:%s"%repr(x))
+            #for y in self.lineIndex[x].iterkeys():
+            #    print "doc",repr(y),repr(self.lineIndex[x][y])
                 
         return self.lineIndex
         
-    def searchInLineIndexDocs(self,word,uniq=True):
+    def searchInLineIndexDocs(self,word,uniq=True,regExp=False):
         """search occurences"""
+
+        if regExp:
+            return self.searchRegExpInLineIndexDocs(word)
         
-            
-        lst=list(self.lineIndex.get(word.upper()).keys())
+        try:    
+        	lst=list(self.lineIndex.get(word).keys())
+        except:
+            lst=[]
         if uniq:
             return unique(lst)
         else:
             return lst
         
-    def getLinesFromIndex(self,word,doc):
+    def getLinesFromIndex(self,word,doc,regExp=False):
         """get lines"""
-        return self.lineIndex[word][doc]
-
+        if not regExp:
+            return self.lineIndex.get(word)[doc]
+        else: # wenn regexp, suche welches word
+            for w in self.findWordRegExp(word):
+                if self.lineIndex.get(w): # ein word in im dex gefunden
+                    try:    
+                        dc=self.lineIndex.get(word)[doc]
+                        return dc # und ein document dann gib es zurueck
+                    except:
+                         pass #andernfalls weiter
+                     
     def cleanInLineIndex(self):
         """delete InlineIndex"""
         for x in list(self.lineIndex.keys()):
@@ -2000,18 +2035,69 @@ class CDLIRoot(Folder):
         
         return f[0].getObject().getLastVersionFormattedData()
     
-    def showLineFromFile(self,fileId,lineNum):
+    def showLineFromFile(self,fileId,lineNum,word):
         """get line lineNum fromFileId"""
         
         file=self.showFile(fileId)
-        str="^%s\.(.*)"%lineNum
-       
-        m=re.search(str,file,flags=re.M)
-        if m:
-            return m.group(1)
-        else:
-            return ""
+        #str="^%s\.[^%s\.]*%s[^\n]*\n"%(lineNum,lineNum,word)
+	#str="^%s\..*?%s[^\n]*\n"%(lineNum,word)
         
+	#print str
+        #m=re.search(str,file,flags=re.M|re.DOTALL)
+        #if m:
+        #    return m.group()
+        #else:
+        #    	return ""
+	#ret=lineNum+"."
+        #splitted=file.split(lineNum+".")
+	#if len(splitted)>1:
+		#for part in splitted[1:]:
+			#if part.find(word)>-1:
+			 # for x in part.split("\n"):
+				#ret+=x
+				#if x.find(word)>-1:
+					#break
+			  #break;
+	#return ret
+
+    def showWordInFile(self,fileId,word,lineList=None):
+        """get lines with word  fromFileId"""
+        
+        file=self.showFile(fileId)
+
+	ret=[]
+	for line in file.split("\n"):
+		if line.find(word)>-1:
+			if lineList: #liste of moeglichen Zeilennummern
+				num=line.split(".")[0] #Zeilenummer ist alles vor dem . in der Zeile
+
+				if num in lineList: 
+
+					ret.append(line)
+			else: # nimm alles ohne line check
+				ret.append(line)
+	return ret
+
+    def tagWordInFile(self,fileId,word,lineList=None):
+        """get lines with word  fromFileId"""
+        
+        file=self.showFile(fileId)
+	tagStr="""<span class="found">%s</span>"""
+	ret=[]
+	for line in file.split("\n"):
+		if line.find(word)>-1:
+			if lineList: #liste of moeglichen Zeilennummern
+				num=line.split(".")[0] #Zeilenummer ist alles vor dem . in der Zeile
+
+				if num in lineList: 
+
+					ret.append(line.replace(word,tagStr%word))
+			else: # nimm alles ohne line check
+				ret.append(line.replace(word,tagStr%word))
+		else:
+			ret.append(line)
+	return "<br>\n".join(ret)
+
     def URLquote(self,str):
         """quote url"""
         return urllib.quote(str)