Merge pull request #111 from simongog/tutorial

Tutorial

Author: simongog

README.md

@@ -6,8 +6,7 @@ What is it?
 
 The Succinct Data Structure Library (SDSL) is a powerful and flexible C++11
 library implementing succinct data structures. In total, the library contains
-the highlights of 40 [research publications](https://github.com/simongog/sdsl-lite/wiki/Literature).
-Succinct data structures
+the highlights of 40 [research publications][SDSLLIT] Succinct data structures
 can represent an object (such as a bitvector or a tree) in space close the
 information-theoretic lower bound of the object while supporting operations
 of the original object efficiently. The theoretical time complexity of an
@@ -51,7 +50,7 @@ data structure to their full potential.
     features provided by the library.
   * All data structures are tested for correctness using a unit-testing framework.
   * We provide a large collection of supporting documentation consisting of examples,
-    [cheat sheet][SDSLCS], tutorial slides and walk-through.
+    [cheat sheet][SDSLCS], [tutorial slides and walk-through][TUT].
 
 The library contains many succinct data structures from the following categories:
 
@@ -145,7 +144,7 @@ To compile the program using `g++` run:
 g++ -std=c++11 -O3 -I ~/include -L ~/lib program.cpp -o lsdsl
 ```
 
-Next we suggest you look at the comprehensive [tutorial][TUT] of Simon Gog which describes
+Next we suggest you look at the comprehensive [tutorial][TUT] which describes
 all major features of the library or look at some of the provided [examples](examples).
 
 Test
@@ -203,7 +202,9 @@ more information see the COPYING file in the library directory.
 Lots of time was spent implementing the many features of the library. If you
 use the library in an academic setting please cite the following paper:
 
-_Simon Gog, Matthias Petri: Optimized Succinct Data Structures for Massive Data, Accepted for publication in Software, Practice and Experience_.
+Simon Gog, Matthias Petri: 
+[Optimized Succinct Data Structures for Massive Data][SPE], 
+Accepted for publication in Software, Practice and Experience.
 
 ## External Resources used in SDSL
 
@@ -212,7 +213,7 @@ construction algorithms.
 
 * Yuta Mori's incredible fast suffix [libdivsufsort][DIVSUF]
   algorithm (version 2.0.1) for byte-alphabets.
-* An adapted version of Jesper Larsson's implementation of the
+* An adapted version of Jesper Larsson's [implementation][QSUFIMPL] of the
   algorithm of [Larson and Sadakane][LS] for integer-alphabets.
 
 Additionally, we use the [googletest][GTEST] framework to provide unit tests.
@@ -252,3 +253,6 @@ Feel free to contact any of the authors or create an issue on the
 [LS]: http://www.sciencedirect.com/science/article/pii/S0304397507005257 "Larson & Sadakane Algorithm"
 [GTEST]: https://code.google.com/p/googletest/ "Google C++ Testing Framework"
 [SDSLCS]: http://simongog.github.io/assets/data/sdsl-cheatsheet.pdf "SDSL Cheat Sheet"
+[SDSLLIT]: https://github.com/simongog/sdsl-lite/wiki/Literature "Succinct Data Structure Literature"
+[TUT]: http://simongog.github.io/assets/data/sdsl-slides/tutorial "Tutorial"
+[QSUFIMPL]: http://www.larsson.dogma.net/qsufsort.c "Original Qsufsort Implementation"

include/sdsl/enc_vector.hpp

@@ -56,7 +56,7 @@ struct enc_vector_trait<64> {
  * @ingroup int_vector
  */
 template<class t_coder=coder::elias_delta,
-         uint32_t t_dens = 8, uint8_t t_width=0>
+         uint32_t t_dens = 128, uint8_t t_width=0>
 class enc_vector
 {
     private:

include/sdsl/rrr_vector.hpp

@@ -69,7 +69,7 @@ class select_support_rrr;                // in rrr_vector
  *    In this version the block size can be adjust by the template parameter t_bs!
  *    \sa sdsl::rrr_vector for a specialized version for block_size=15
  */
-template<uint16_t t_bs=15, class t_rac=int_vector<>, uint16_t t_k=32>
+template<uint16_t t_bs=63, class t_rac=int_vector<>, uint16_t t_k=32>
 class rrr_vector
 {
         static_assert(t_bs >= 3 and t_bs <= 256 , "rrr_vector: block size t_bs must be 3 <= t_bs <= 256.");

include/sdsl/vlc_vector.hpp

@@ -43,11 +43,11 @@ struct vlc_vector_trait<32> {
 /*! The values of a vlc_vector are immutable after the constructor call. The class
  *   could be parametrized with a self-delimiting code t_coder and the sample density.
  *  \tparam t_coder Type of self-delimiting coder.
- *  \tparam t_dens  Sampling density of stored absolute values.
- *  \tparam t_width Width of the underlying int_vector for the absolute samples.
+ *  \tparam t_dens  Sampling density of pointers into the stream of self-delimiting coded numbers.
+ *  \tparam t_width Width of the underlying int_vector for the pointers.
  */
 template<class    t_coder = coder::elias_delta,
-         uint32_t t_dens  = 16,
+         uint32_t t_dens  = 128,
          uint8_t  t_width = 0>
 class vlc_vector
 {

tutorial/expl-02.cpp

@@ -6,10 +6,10 @@ using namespace sdsl;
 
 int main()
 {
-    int_vector<> v(10000000);
+    int_vector<> v(10*(1<<20));
     for (size_t i=0; i<10; ++i)
-        for (size_t j=0; j<1000000; ++j)
-            v[i*1000000+j] = j;
+        for (size_t j=0; j < 1U<<20; ++j)
+            v[i*(1<<20)+j] = j;
     cout << size_in_mega_bytes(v) << endl;
     util::bit_compress(v);
     cout << size_in_mega_bytes(v) << endl;

tutorial/expl-03.cpp

@@ -6,7 +6,7 @@ using namespace sdsl;
 
 int main()
 {
-    int_vector<> v(10000000, 3);
+    int_vector<> v(10*(1<<20), 0);
     v[0] = 1ULL<<63;
     util::bit_compress(v);
     cout << size_in_mega_bytes(v) << endl;

tutorial/expl-04.cpp

@@ -8,7 +8,7 @@ int main()
 {
     bit_vector b = {1,1,0,1,0,0,1};
     cout << b << endl;
-    b = bit_vector(80000000, 0);
+    b = bit_vector(80*(1<<20), 0);
     for (size_t i=0; i < b.size(); i+=100)
         b[i] = 1;
     cout << size_in_mega_bytes(b) << endl;

tutorial/expl-05.cpp

@@ -6,7 +6,7 @@ using namespace sdsl;
 
 int main()
 {
-    bit_vector b = bit_vector(80000000, 0);
+    bit_vector b = bit_vector(80*(1<<20), 0);
     for (size_t i=0; i < b.size(); i+=100)
         b[i] = 1;
     cout << size_in_mega_bytes(b) << endl;

tutorial/expl-06.cpp

@@ -6,7 +6,7 @@ using namespace sdsl;
 
 int main()
 {
-    bit_vector b = bit_vector(80000000, 0);
+    bit_vector b = bit_vector(80*(1<<20), 0);
     for (size_t i=0; i < b.size(); i+=100)
         b[i] = 1;
     sd_vector<> sdb(b);

tutorial/expl-14.cpp

@@ -7,7 +7,7 @@ using namespace sdsl;
 int main()
 {
     wt_hutu<rrr_vector<63>> wt;
-    construct_im(wt, "ハローワールド！", 1);
+    construct_im(wt, "こんにちは世界", 1);
     for (size_t i=0; i < wt.size(); ++i)
         cout << wt[i];
     cout << endl;