Deleted stuff we don't need; minor fixes, some related to Valgrind issues and others cosmetic.

git-svn-id: https://svn.code.sf.net/p/kaldi/code/trunk@16 5e6a8d80-dfce-4ca6-a32a-6e07a63d50c8

COPYING

@@ -42,9 +42,8 @@ Other Source Material
   current copyright holder, Henrique S. Malvar, has given his permission for the
   release of this modified version under the Apache License 2.0.
   
-  This file includes material from the OpenFST Library v1.2.7 available at 
-  http://www.openfst.org/twiki/bin/view/FST/WebHome and released under the 
-  Apache License v. 2.0.   
+  This project includes material from the OpenFST Library v1.2.7 available at 
+  http://www.openfst.org and released under the Apache License v. 2.0.   
 
   [OpenFst COPYING file begins here]
 

src/INSTALL

 
-These instructions are valid for UNIX-like systems (tested on 
-various Linux distributions; Darwin; Cygwin).  For native Windows
+These instructions are valid for UNIX-like systems (these steps have
+been run on various Linux distributions; Darwin; Cygwin).  For native Windows
 compilation, see ../windows/INSTALL.
 
-You must first have completed the installation steps in ../tools/INSTALL
-(compiling OpenFst; getting ATLAS and CLAPACK headers).
+You must first have completed the installation steps in ../tools/INSTALL or by
+running ../tools/install.sh (compiling OpenFst; getting ATLAS and CLAPACK
+headers).
 
 The installation instructions are:
 ./configure
@@ -14,6 +15,6 @@ make
 Note that "make" takes a long time; you can speed it up by running make
 in parallel, for instance "make -j 4"
 
-For more information, see documentation at http://merlin.fit.vutbr.cz/kaldi/
+For more information, see documentation at http://kaldi.sf.net/
 and click on "The build process (how Kaldi is compiled)".
 

src/NOTES

 
+
 Example of debug command with valgrind:
 in matrix/
  valgrind  ./matrix-lib-test
@@ -13,15 +14,15 @@ looking at valgrind.out in the last directory, and looking for the last
 filename *-test that was printed).
 
 
+---
+ For emacs users:
+  ensure proper indentation it may be helpful to copy
+     http://google-styleguide.googlecode.com/svn/trunk/google-c-style.el
+  to your home directory as ".google-c-style.el", and add to your .emacs file the lines:
+\verbatim
+  (load-file "~/.google-c-style.el")
+  (add-hook 'c-mode-common-hook 'google-set-c-style)
+  (add-hook 'c-mode-common-hook 'google-make-newline-indent)
+\endverbatim
 
-----
-notes on potential install problems:
-if you get errors like:
-.../matrix/kaldi-matrix.cc:43: undefined reference to `clapack_sgetrf'
-then you may be linking with a version of the library liblapack.a that
-does not have this type of symbol: on UToronto's machines that library did
-not export that symbol but there was a newer one called liblapack-3.a that
-did.
-
-If you get errors about not being able to find files in various system directories,
-try typing 'make depend'.
+--

src/TODO

@@ -4,12 +4,14 @@
   - Try to run the scripts and compile on various platforms, and
     report problems.
 
- TODO items (mainly for Dan to do, some for Arnab):
-
-  Check the clapack configuration in the configure script.
+ TODO items (Arnab):
+  Check the clapack configuration in the configure script... not clear
+     what the purpose of CLAPACK_ROOT is.  I think the configure script
+     should create a Makefile that doesn't depend on external variables (Dan)
   Add separate min-count at root of tree for regression-tree fMLLR/MLLR
-  Add fMLLR scripts for SGMM, and also use deeper trees.
-  Document configure script.
+  Add fMLLR scripts for SGMM.
+
+ TODO items (Dan):
   Remove cpplint.py from distribution.
   Remove feat/test_data/ (or Karel to get other data?).
   Remove non-Kaldi code from decoder/

src/doc/dependencies.dox

@@ -24,8 +24,6 @@
 
     - Subversion (svn): this is needed to download Kaldi and other software that it depends on.
     - wget is required for the installation of some non-Kaldi components described below
-    - automake (and aclocal): required to install IRSTLM which some of our scripts use
-      (see below).
     - doxygen: this is the program we use to generate html documentation from 
       the C++ source (which has been marked up according to doxygen requirements).
       If you will be changing the source significantly, this might be useful.
@@ -39,6 +37,8 @@
       - IRSTLM: this a language modeling toolkit.  Some of the example scripts require it but 
         it is not tightly integrated with Kaldi; we can convert any Arpa format
         language model to an FST.
+        - The IRSTLM build process requires automake, aclocal, and libtoolize
+          (the corresponding packages are automake and libtool).
       - sph2pipe: this is for converting sph format files into other formats such
         as wav.  It's needed for the example scripts that use LDC data.
       - sclite: this is for scoring and is not necessary as we have our own, simple

src/gmm/am-diag-gmm.cc

@@ -355,6 +355,7 @@ void ClusterGaussiansToUbm(const AmDiagGmm& am,
       tmp_vars.CopyRowFromVec(tmp_vec, gauss_index);
       gauss_index++;
     }
+    DeletePointers(&(gauss_clusters_out[clust_index]));
   }
   tmp_gmm.Resize(opts.intermediate_numcomps, dim);
   tmp_weights.Scale(1.0/tmp_weights.Sum());

src/tree/cluster-utils.cc

@@ -434,9 +434,8 @@ class CompartmentalizedBottomUpClusterer {
                     vector< vector<int32> > *assignments_out);
   ~CompartmentalizedBottomUpClusterer() {
     for (vector< vector<Clusterable*> >::iterator itr = clusters_.begin(),
-         end = clusters_.end(); itr != end; ++itr) {
+         end = clusters_.end(); itr != end; ++itr)
       DeletePointers(&(*itr));
-    }
   }
 
  private:
@@ -568,7 +567,7 @@ bool CompartmentalizedBottomUpClusterer::CanMerge(int32 comp, int32 i, int32 j,
 }
 
 BaseFloat CompartmentalizedBottomUpClusterer::MergeClusters(int32 comp, int32 i,
-                                                       int32 j) {
+                                                            int32 j) {
   KALDI_ASSERT(comp < ncompartments_ && i < npoints_[comp] && j < i);
   clusters_[comp][i]->Add(*(clusters_[comp][j]));
   delete clusters_[comp][j];

src/tree/cluster-utils.h

@@ -113,6 +113,7 @@ BaseFloat ClusterBottomUp(const std::vector<Clusterable*> &points,
 /// of compartments, such that only points in the same compartment are
 /// clustered together. The compartment and pair of points with the smallest
 /// merge cost are clustered.
+/// The clusters in "clusters_out" are newly allocated and owned by the caller.
 BaseFloat ClusterBottomUpCompartmentalized(
     const std::vector< std::vector<Clusterable*> > &points, BaseFloat thresh,
     int32 min_clust, std::vector< std::vector<Clusterable*> > *clusters_out,

src/tree/event-map.cc

@@ -77,7 +77,7 @@ void TableEventMap::Write(std::ostream &os, bool binary) {
     EventMap::Write(os, binary, table_[t]);
   }
   WriteMarker(os, binary, ")");
-  if(!binary) os << '\n';
+  if (!binary) os << '\n';
   if (os.fail()) {
     KALDI_ERR << "TableEventMap::Write(), could not write to stream.";
   }
@@ -174,8 +174,9 @@ std::string EventTypeToString(const EventType &evec) {
 
 size_t EventMapVectorHash::operator ()(const EventType &vec) {
   EventType::const_iterator iter = vec.begin(), end = vec.end();
-  size_t ans = 0; const size_t kPrime1=47087, kPrime2=1321;
-  for (; iter!= end; ++iter) {
+  size_t ans = 0;
+  const size_t kPrime1=47087, kPrime2=1321;
+  for (; iter != end; ++iter) {
 #ifdef KALDI_PARANOID // Check names are distinct and increasing.
     EventType::const_iterator iter2=iter; iter2++;
     if (iter2 != end) { assert(iter->first < iter2->first); }