X-Git-Url: http://git.nguyen.vg/gitweb/?a=blobdiff_plain;f=XMLTree.h;h=7407014e7bd17c0870ad9eee0e43e1d0db3eb6bd;hb=60f0f1a447b2b89ca99589c68333d72bcdeb263d;hp=bb1dbbbfa0f75640ee9a071f25662b824d19c5c4;hpb=ac626dacdd094e0dc9fbc3302fec0020cf97942c;p=SXSI%2FXMLTree.git

diff --git a/XMLTree.h b/XMLTree.h
index bb1dbbb..7407014 100644
--- a/XMLTree.h
+++ b/XMLTree.h
@@ -21,22 +21,24 @@
 
 #ifndef XMLTREE_H_
 #define XMLTREE_H_
-
+#include "TextCollection/TextCollection.h"
 #include <stdio.h>
 #include <stdlib.h>
+#include <cstring>
 #include "bp.h"
-#include "libcds/includes/static_bitsequence.h"
-#include "libcds/includes/alphabet_mapper.h"
-#include "libcds/includes/static_sequence.h"
+#include <static_bitsequence.h>
+#include <alphabet_mapper.h>
+#include <static_sequence.h>
+using SXSI::TextCollection;
 
-//#include "TextCollection/TextCollection.h"
-//using SXSI::TextCollection;
 
 // this constant is used to efficiently compute the child operation in the tree
 #define OPTD 10
 
 #define NULLT -1
 
+#define PERM_SAMPLE 10
+
         // sets bit p in e
 #define bitset(e,p) ((e)[(p)/W] |= (1<<((p)%W)))
         // cleans bit p in e
@@ -67,10 +69,10 @@ class XMLTree {
    static_bitsequence_rrr02 *EBVector;  
 		      
    /** Tag sequence represented with a data structure for rank and select */
-   static_sequence_wvtree *Tags;
+   static_sequence *Tags;
 
    /** The texts in the XML document */
-   //TextCollection *Text;
+   TextCollection *Text;
    
    /** Flag indicating whether the whole data structure has been constructed or 
     * not. If the value is true, you cannot add more texts, nodes, etc. */
@@ -85,6 +87,7 @@ class XMLTree {
    pb *par_aux;
    TagType *tags_aux;
    int npar;
+   int parArraySize;
    int ntagnames;
    unsigned int *empty_texts_aux;
    
@@ -251,14 +254,99 @@ public:
     * Returns NULL in case that the tag identifier is not valid.*/
    unsigned char *GetTagName(TagType tagid);
 
-   /** saveXMLTree: saves XML tree data structure to file. Every component of 
-    * the collection is stored in different files (same name, different file 
-    * extensions). */
+   /** Prefix(s): search for texts prefixed by string s. */
+   TextCollection::document_result Prefix(uchar const *s) {
+      return Text->Prefix(s);
+   }
+
+   /** Suffix(s): search for texts having string s as a suffix. */
+   TextCollection::document_result Suffix(uchar const *s) {
+      return Text->Suffix(s);
+   }
+
+   /** Equal(s): search for texts equal to string s. */
+   TextCollection::document_result Equal(uchar const *s) {
+      return Text->Equal(s);
+   }
+
+   /** Contains(s): search for texts containing string s.  */
+   TextCollection::document_result Contains(uchar const *s) {
+      return Text->Contains(s);
+   }
+
+   /** LessThan(s): returns document identifiers for the texts that
+    * are lexicographically smaller than string s. */
+   TextCollection::document_result LessThan(uchar const *s) {
+      return Text->LessThan(s);
+   }
+   
+   /** IsPrefix(x): returns true if there is a text prefixed by string s. */
+   bool IsPrefix(uchar const *s) {
+      return Text->IsPrefix(s);
+   }          
+   
+   /** IsSuffix(s): returns true if there is a text having string s as a 
+    * suffix.*/
+   bool IsSuffix(uchar const *s) {
+      return Text->IsSuffix(s);
+   }
+   
+   /** IsEqual(s): returns true if there is a text that equals given 
+    * string s. */
+   bool IsEqual(uchar const *s) {
+      return Text->IsEqual(s);
+   }
+   
+   /** IsContains(s): returns true if there is a text containing string s. */
+   bool IsContains(uchar const *s) {
+      return Text->IsContains(s);
+   }
+   
+   /** IsLessThan(s): returns true if there is at least a text that is 
+    * lexicographically smaller than string s. */
+   bool IsLessThan(uchar const *s) {
+      return Text->IsLessThan(s);
+   }
+
+   /** CountPrefix(s): counting version of Prefix(s). */
+   unsigned CountPrefix(uchar const *s) {
+      return Text->CountPrefix(s);
+   }
+   
+   /** CountSuffix(s): counting version of Suffix(s). */
+   unsigned CountSuffix(uchar const *s) {
+      return Text->CountSuffix(s);
+   }
+   
+   /** CountEqual(s): counting version of Equal(s). */
+   unsigned CountEqual(uchar const *s) {
+      return Text->CountEqual(s);
+   }
+   
+   /** CountContains(s): counting version of Contains(s). */
+   unsigned CountContains(uchar const *s) {
+      return Text->CountContains(s);
+   }
+   
+   /** CountLessThan(s): counting version of LessThan(s). */
+   unsigned CountLessThan(uchar const *s) {
+      return CountLessThan(s);
+   }
+   
+   /** GetText(d): returns the text corresponding to document with
+    * id d. */
+   uchar* GetText(DocID d) {
+      return Text->GetText(d);
+   }
+   
+   TextCollection *getTextCollection() {
+      return Text;
+   }
+   /** Save: saves XML tree data structure to file. */
    void Save(unsigned char *filename);
       
-   /** load: loads XML tree data structure from file. */
+   /** Load: loads XML tree data structure from file. sample_rate_text 
+    * indicates the sample rate for the text search data structure. */
    static XMLTree *Load(unsigned char *filename, int sample_rate_text);   
 };
-
-
 #endif