\r
#define NULLT -1\r
\r
+#define PERM_SAMPLE 10\r
+\r
// sets bit p in e\r
#define bitset(e,p) ((e)[(p)/W] |= (1<<((p)%W)))\r
// cleans bit p in e\r
static_bitsequence_rrr02 *EBVector; \r
\r
/** Tag sequence represented with a data structure for rank and select */\r
- static_sequence_wvtree *Tags;\r
+ static_sequence *Tags;\r
\r
/** The texts in the XML document */\r
TextCollection *Text;\r
pb *par_aux;\r
TagType *tags_aux;\r
int npar;\r
+ int parArraySize;\r
int ntagnames;\r
unsigned int *empty_texts_aux;\r
+ bool found_attributes;\r
+ bool disable_tc;\r
\r
public:\r
\r
/** ParentNode(d): returns the parent node of document identifier d. */\r
treeNode ParentNode(DocID d);\r
\r
- /** OpenDocument(empty_texts,sample_rate_text): initilizes the construction\r
+ /** OpenDocument(empty_texts,sample_rate_text,dtc): initilizes the construction\r
* of the data structure for the XML document. Parameter empty_texts \r
* indicates whether we index empty texts in document or not. Parameter \r
* sample_rate_text indicates the sampling rate for the text searching data\r
* structures (small values get faster searching but a bigger space \r
- * requirement). Returns a non-zero value upon success, NULLT in case of \r
+ * requirement). dtc disable the use of the TextCollection\r
+ * (i.e. everything is considered an empty text *)\r
+ * Returns a non-zero value upon success, NULLT in case of \r
* error. */\r
- int OpenDocument(bool empty_texts, int sample_rate_text);\r
+ int OpenDocument(bool empty_texts, int sample_rate_text, bool dtc);\r
\r
/** CloseDocument(): finishes the construction of the data structure for \r
* the XML document. Tree and tags are represented in the final form, \r
* Returns NULL in case that the tag identifier is not valid.*/\r
unsigned char *GetTagName(TagType tagid);\r
\r
+\r
+ TagType RegisterTag(unsigned char *tagname);\r
+\r
+ bool EmptyText(DocID i) {\r
+ return Text->EmptyText(i);\r
+ }\r
/** Prefix(s): search for texts prefixed by string s. */\r
TextCollection::document_result Prefix(uchar const *s) {\r
return Text->Prefix(s);\r
/** GetText(d): returns the text corresponding to document with\r
* id d. */\r
uchar* GetText(DocID d) {\r
- Text->GetText(d);\r
+ return Text->GetText(d);\r
}\r
\r
+ TextCollection *getTextCollection() {\r
+ return Text;\r
+ }\r
/** Save: saves XML tree data structure to file. */\r
void Save(unsigned char *filename);\r
\r