Merge branch 'master' of github.com:moses-smt/mosesdecoder

phrase-extract/SentenceAlignmentWithSyntax.h

@@ -28,7 +28,7 @@
 
 #include "RuleExtractionOptions.h"
 #include "SentenceAlignment.h"
-#include "SyntaxTree.h"
+#include "SyntaxNodeCollection.h"
 
 namespace MosesTraining
 {
@@ -36,8 +36,8 @@ namespace MosesTraining
 class SentenceAlignmentWithSyntax : public SentenceAlignment
 {
 public:
-  SyntaxTree targetTree;
-  SyntaxTree sourceTree;
+  SyntaxNodeCollection targetTree;
+  SyntaxNodeCollection sourceTree;
   std::set<std::string> & m_targetLabelCollection;
   std::set<std::string> & m_sourceLabelCollection;
   std::map<std::string, int> & m_targetTopLabelCollection;

phrase-extract/SyntaxNode.h

@@ -0,0 +1,75 @@
+/***********************************************************************
+  Moses - factored phrase-based language decoder
+  Copyright (C) 2009 University of Edinburgh
+
+  This library is free software; you can redistribute it and/or
+  modify it under the terms of the GNU Lesser General Public
+  License as published by the Free Software Foundation; either
+  version 2.1 of the License, or (at your option) any later version.
+
+  This library is distributed in the hope that it will be useful,
+  but WITHOUT ANY WARRANTY; without even the implied warranty of
+  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+  Lesser General Public License for more details.
+
+  You should have received a copy of the GNU Lesser General Public
+  License along with this library; if not, write to the Free Software
+  Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301  USA
+ ***********************************************************************/
+
+#pragma once
+
+#include <map>
+#include <sstream>
+#include <string>
+#include <vector>
+
+namespace MosesTraining
+{
+
+class SyntaxNode
+{
+protected:
+  int m_start, m_end;
+  std::string m_label;
+  std::vector< SyntaxNode* > m_children;
+  SyntaxNode* m_parent;
+  float m_pcfgScore;
+public:
+  SyntaxNode( int startPos, int endPos, std::string label )
+    :m_start(startPos)
+    ,m_end(endPos)
+    ,m_label(label)
+    ,m_parent(0)
+    ,m_pcfgScore(0.0f) {
+  }
+  int GetStart() const {
+    return m_start;
+  }
+  int GetEnd() const {
+    return m_end;
+  }
+  std::string GetLabel() const {
+    return m_label;
+  }
+  float GetPcfgScore() const {
+    return m_pcfgScore;
+  }
+  void SetPcfgScore(float score) {
+    m_pcfgScore = score;
+  }
+  SyntaxNode *GetParent() {
+    return m_parent;
+  }
+  void SetParent(SyntaxNode *parent) {
+    m_parent = parent;
+  }
+  void AddChild(SyntaxNode* child) {
+    m_children.push_back(child);
+  }
+  const std::vector< SyntaxNode* > &GetChildren() const {
+    return m_children;
+  }
+};
+
+}  // namespace MosesTraining

phrase-extract/SyntaxNodeCollection.cpp

@@ -1,6 +1,3 @@
-// $Id: SyntaxTree.cpp 1960 2008-12-15 12:52:38Z phkoehn $
-// vim:tabstop=2
-
 /***********************************************************************
   Moses - factored phrase-based language decoder
   Copyright (C) 2009 University of Edinburgh
@@ -21,7 +18,7 @@
  ***********************************************************************/
 
 
-#include "SyntaxTree.h"
+#include "SyntaxNodeCollection.h"
 
 #include <cassert>
 #include <iostream>
@@ -29,12 +26,12 @@
 namespace MosesTraining
 {
 
-SyntaxTree::~SyntaxTree()
+SyntaxNodeCollection::~SyntaxNodeCollection()
 {
   Clear();
 }
 
-void SyntaxTree::Clear()
+void SyntaxNodeCollection::Clear()
 {
   m_top = 0;
   // loop through all m_nodes, delete them
@@ -45,7 +42,8 @@ void SyntaxTree::Clear()
   m_index.clear();
 }
 
-SyntaxNode *SyntaxTree::AddNode( int startPos, int endPos, std::string label )
+SyntaxNode *SyntaxNodeCollection::AddNode(int startPos, int endPos,
+                                          const std::string &label)
 {
   SyntaxNode* newNode = new SyntaxNode( startPos, endPos, label );
   m_nodes.push_back( newNode );
@@ -54,7 +52,7 @@ SyntaxNode *SyntaxTree::AddNode( int startPos, int endPos, std::string label )
   return newNode;
 }
 
-ParentNodes SyntaxTree::Parse()
+ParentNodes SyntaxNodeCollection::Parse()
 {
   ParentNodes parents;
 
@@ -94,12 +92,12 @@ ParentNodes SyntaxTree::Parse()
   return parents;
 }
 
-bool SyntaxTree::HasNode( int startPos, int endPos ) const
+bool SyntaxNodeCollection::HasNode( int startPos, int endPos ) const
 {
   return GetNodes( startPos, endPos).size() > 0;
 }
 
-const std::vector< SyntaxNode* >& SyntaxTree::GetNodes( int startPos, int endPos ) const
+const std::vector< SyntaxNode* >& SyntaxNodeCollection::GetNodes( int startPos, int endPos ) const
 {
   SyntaxTreeIndexIterator startIndex = m_index.find( startPos );
   if (startIndex == m_index.end() )
@@ -112,15 +110,7 @@ const std::vector< SyntaxNode* >& SyntaxTree::GetNodes( int startPos, int endPos
   return endIndex->second;
 }
 
-// for printing out tree
-std::string SyntaxTree::ToString() const
-{
-  std::stringstream out;
-  out << *this;
-  return out.str();
-}
-
-void SyntaxTree::ConnectNodes()
+void SyntaxNodeCollection::ConnectNodes()
 {
   typedef SyntaxTreeIndex2::const_reverse_iterator InnerIterator;
 
@@ -162,27 +152,4 @@ void SyntaxTree::ConnectNodes()
   }
 }
 
-std::ostream& operator<<(std::ostream& os, const SyntaxTree& t)
-{
-  size_t size = t.m_index.size();
-  for(size_t length=1; length<=size; length++) {
-    for(size_t space=0; space<length; space++) {
-      os << "    ";
-    }
-    for(size_t start=0; start<=size-length; start++) {
-
-      if (t.HasNode( start, start+(length-1) )) {
-        std::string label = t.GetNodes( start, start+(length-1) )[0]->GetLabel() + "#######";
-
-        os << label.substr(0,7) << " ";
-      } else {
-        os << "------- ";
-      }
-    }
-    os << std::endl;
-  }
-  return os;
-}
-
-}
-
+}  // namespace MosesTraining

phrase-extract/SyntaxNodeCollection.h

@@ -1,6 +1,3 @@
-// $Id: SyntaxTree.h 1960 2008-12-15 12:52:38Z phkoehn $
-// vim:tabstop=2
-
 /***********************************************************************
   Moses - factored phrase-based language decoder
   Copyright (C) 2009 University of Edinburgh
@@ -20,66 +17,22 @@
   Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301  USA
  ***********************************************************************/
 
-
 #pragma once
-#include <string>
-#include <vector>
+
 #include <map>
 #include <sstream>
+#include <string>
+#include <vector>
+
+#include "SyntaxNode.h"
 
 namespace MosesTraining
 {
 
-class SyntaxNode
-{
-protected:
-  int m_start, m_end;
-  std::string m_label;
-  std::vector< SyntaxNode* > m_children;
-  SyntaxNode* m_parent;
-  float m_pcfgScore;
-public:
-  SyntaxNode( int startPos, int endPos, std::string label )
-    :m_start(startPos)
-    ,m_end(endPos)
-    ,m_label(label)
-    ,m_parent(0)
-    ,m_pcfgScore(0.0f) {
-  }
-  int GetStart() const {
-    return m_start;
-  }
-  int GetEnd() const {
-    return m_end;
-  }
-  std::string GetLabel() const {
-    return m_label;
-  }
-  float GetPcfgScore() const {
-    return m_pcfgScore;
-  }
-  void SetPcfgScore(float score) {
-    m_pcfgScore = score;
-  }
-  SyntaxNode *GetParent() {
-    return m_parent;
-  }
-  void SetParent(SyntaxNode *parent) {
-    m_parent = parent;
-  }
-  void AddChild(SyntaxNode* child) {
-    m_children.push_back(child);
-  }
-  const std::vector< SyntaxNode* > &GetChildren() const {
-    return m_children;
-  }
-};
-
-
 typedef std::vector< int > SplitPoints;
 typedef std::vector< SplitPoints > ParentNodes;
 
-class SyntaxTree
+class SyntaxNodeCollection
 {
 protected:
   std::vector< SyntaxNode* > m_nodes;
@@ -93,16 +46,14 @@ protected:
   int m_size;
   std::vector< SyntaxNode* > m_emptyNode;
 
-  friend std::ostream& operator<<(std::ostream&, const SyntaxTree&);
-
 public:
-  SyntaxTree()
+  SyntaxNodeCollection()
     : m_top(0)  // m_top doesn't get set unless ConnectNodes is called.
     , m_size(0) {}
 
-  ~SyntaxTree();
+  ~SyntaxNodeCollection();
 
-  SyntaxNode *AddNode( int startPos, int endPos, std::string label );
+  SyntaxNode *AddNode( int startPos, int endPos, const std::string &label );
 
   SyntaxNode *GetTop() {
     return m_top;
@@ -119,10 +70,6 @@ public:
   }
   void ConnectNodes();
   void Clear();
-  std::string ToString() const;
 };
 
-std::ostream& operator<<(std::ostream&, const SyntaxTree&);
-
-}
-
+}  // namespace MosesTraining

phrase-extract/XmlTree.cpp

@@ -1,6 +1,3 @@
-// $Id: XmlOption.cpp 1960 2008-12-15 12:52:38Z phkoehn $
-// vim:tabstop=2
-
 /***********************************************************************
   Moses - factored phrase-based language decoder
   Copyright (C) 2006 University of Edinburgh
@@ -27,7 +24,8 @@
 #include <iostream>
 #include <cstdlib>
 #include <sstream>
-#include "SyntaxTree.h"
+
+#include "SyntaxNodeCollection.h"
 #include "XmlException.h"
 
 using namespace std;
@@ -228,7 +226,10 @@ vector<string> TokenizeXml(const string& str)
 	parse because we don't have the completed source parsed until after this function
 	removes all the markup from it (CreateFromString in Sentence::Read).
 */
-bool ProcessAndStripXMLTags(string &line, SyntaxTree &tree, set< string > &labelCollection, map< string, int > &topLabelCollection, bool unescapeSpecialChars )
+bool ProcessAndStripXMLTags(string &line, SyntaxNodeCollection &nodeCollection,
+                            set< string > &labelCollection,
+                            map< string, int > &topLabelCollection,
+                            bool unescapeSpecialChars )
 {
   //parse XML markup in translation line
 
@@ -374,7 +375,7 @@ bool ProcessAndStripXMLTags(string &line, SyntaxTree &tree, set< string > &label
           cerr << "XML TAG LABEL IS: '" << label << "'" << endl;
           cerr << "XML SPAN IS: " << startPos << "-" << (endPos-1) << endl;
         }
-        SyntaxNode *node = tree.AddNode( startPos, endPos-1, label );
+        SyntaxNode *node = nodeCollection.AddNode( startPos, endPos-1, label );
         node->SetPcfgScore(pcfgScore);
       }
     }
@@ -386,7 +387,7 @@ bool ProcessAndStripXMLTags(string &line, SyntaxTree &tree, set< string > &label
   }
 
   // collect top labels
-  const vector< SyntaxNode* >& topNodes = tree.GetNodes( 0, wordPos-1 );
+  const vector< SyntaxNode* >& topNodes = nodeCollection.GetNodes( 0, wordPos-1 );
   for( vector< SyntaxNode* >::const_iterator node = topNodes.begin(); node != topNodes.end(); node++ ) {
     SyntaxNode *n = *node;
     const string &label = n->GetLabel();

phrase-extract/XmlTree.h

@@ -1,6 +1,3 @@
-// $Id: XmlOption.cpp 1960 2008-12-15 12:52:38Z phkoehn $
-// vim:tabstop=2
-
 /***********************************************************************
   Moses - factored phrase-based language decoder
   Copyright (C) 2006 University of Edinburgh
@@ -21,11 +18,13 @@
  ***********************************************************************/
 
 #pragma once
+
 #include <string>
 #include <vector>
 #include <set>
 #include <map>
-#include "SyntaxTree.h"
+
+#include "SyntaxNodeCollection.h"
 
 namespace MosesTraining
 {
@@ -35,9 +34,8 @@ std::string Trim(const std::string& str, const std::string dropChars = " \t\n\r"
 std::string TrimXml(const std::string& str);
 bool isXmlTag(const std::string& tag);
 std::vector<std::string> TokenizeXml(const std::string& str);
-bool ProcessAndStripXMLTags(std::string &line, SyntaxTree &tree, std::set< std::string > &labelCollection, std::map< std::string, int > &topLabelCollection, bool unescape = true);
+bool ProcessAndStripXMLTags(std::string &line, SyntaxNodeCollection &tree, std::set< std::string > &labelCollection, std::map< std::string, int > &topLabelCollection, bool unescape = true);
 std::string unescape(const std::string &str);
 
 
-} // namespace
-
+} // namespace MosesTraining

phrase-extract/extract-ghkm/ExtractGHKM.cpp

@@ -33,7 +33,8 @@
 #include "Span.h"
 #include "StsgRule.h"
 #include "StsgRuleWriter.h"
-#include "SyntaxTree.h"
+#include "SyntaxNode.h"
+#include "SyntaxNodeCollection.h"
 #include "tables-core.h"
 #include "XmlException.h"
 #include "XmlTree.h"
@@ -172,7 +173,7 @@ int ExtractGHKM::Main(int argc, char *argv[])
 
 
     // Parse source tree and construct a SyntaxTree object.
-    MosesTraining::SyntaxTree sourceSyntaxTree;
+    MosesTraining::SyntaxNodeCollection sourceSyntaxTree;
     MosesTraining::SyntaxNode *sourceSyntaxTreeRoot=NULL;
 
     if (options.sourceLabels) {
@@ -196,7 +197,7 @@ int ExtractGHKM::Main(int argc, char *argv[])
     // Read source tokens.
     std::vector<std::string> sourceTokens(ReadTokens(sourceLine));
 
-    // Construct a source ParseTree object from the SyntaxTree object.
+    // Construct a source ParseTree object from the SyntaxNodeCollection object.
     std::auto_ptr<ParseTree> sourceParseTree;
 
     if (options.sourceLabels) {

phrase-extract/extract-ghkm/ScfgRule.cpp

@@ -19,11 +19,12 @@
 
 #include "ScfgRule.h"
 
+#include <algorithm>
+
 #include "Node.h"
 #include "Subgraph.h"
-#include "SyntaxTree.h"
-
-#include <algorithm>
+#include "SyntaxNode.h"
+#include "SyntaxNodeCollection.h"
 
 namespace Moses
 {
@@ -31,7 +32,7 @@ namespace GHKM
 {
 
 ScfgRule::ScfgRule(const Subgraph &fragment,
-                   const MosesTraining::SyntaxTree *sourceSyntaxTree)
+                   const MosesTraining::SyntaxNodeCollection *sourceSyntaxTree)
   : m_graphFragment(fragment)
   , m_sourceLHS("X", NonTerminal)
   , m_targetLHS(fragment.GetRoot()->GetLabel(), NonTerminal)
@@ -133,9 +134,9 @@ ScfgRule::ScfgRule(const Subgraph &fragment,
   }
 }
 
-void ScfgRule::PushSourceLabel(const MosesTraining::SyntaxTree *sourceSyntaxTree,
-                               const Node *node,
-                               const std::string &nonMatchingLabel)
+void ScfgRule::PushSourceLabel(
+    const MosesTraining::SyntaxNodeCollection *sourceSyntaxTree,
+    const Node *node, const std::string &nonMatchingLabel)
 {
   ContiguousSpan span = Closure(node->GetSpan());
   if (sourceSyntaxTree->HasNode(span.first,span.second)) { // does a source constituent match the span?

phrase-extract/extract-ghkm/ScfgRule.h

@@ -19,16 +19,16 @@
 
 #pragma once
 
-#include "Alignment.h"
-#include "Rule.h"
-#include "SyntaxTree.h"
-
 #include <string>
 #include <vector>
 #include <list>
 #include <memory>
 #include <iostream>
 
+#include "Alignment.h"
+#include "Rule.h"
+#include "SyntaxNodeCollection.h"
+
 namespace Moses
 {
 namespace GHKM
@@ -41,7 +41,7 @@ class ScfgRule : public Rule
 {
 public:
   ScfgRule(const Subgraph &fragment,
-           const MosesTraining::SyntaxTree *sourceSyntaxTree = 0);
+           const MosesTraining::SyntaxNodeCollection *sourceSyntaxTree = 0);
 
   const Subgraph &GetGraphFragment() const {
     return m_graphFragment;
@@ -78,9 +78,9 @@ public:
   }
 
 private:
-  void PushSourceLabel(const MosesTraining::SyntaxTree *sourceSyntaxTree,
-                       const Node *node,
-                       const std::string &nonMatchingLabel);
+  void PushSourceLabel(
+      const MosesTraining::SyntaxNodeCollection *sourceSyntaxTree,
+      const Node *node, const std::string &nonMatchingLabel);
 
   const Subgraph& m_graphFragment;
   Symbol m_sourceLHS;
@@ -95,4 +95,3 @@ private:
 
 }  // namespace GHKM
 }  // namespace Moses
-

phrase-extract/extract-ghkm/XmlTreeParser.h

@@ -23,14 +23,15 @@
 
 #include "Exception.h"
 
-#include "SyntaxTree.h"
-
 #include <map>
 #include <memory>
 #include <set>
 #include <string>
 #include <vector>
 
+#include "SyntaxNode.h"
+#include "SyntaxNodeCollection.h"
+
 namespace Moses
 {
 namespace GHKM
@@ -58,7 +59,7 @@ private:
   std::set<std::string> &m_labelSet;
   std::map<std::string, int> &m_topLabelSet;
   std::string m_line;
-  MosesTraining::SyntaxTree m_tree;
+  MosesTraining::SyntaxNodeCollection m_tree;
   std::vector<std::string> m_words;
 };
 

phrase-extract/extract-rules-main.cpp

@@ -41,7 +41,7 @@
 #include "HoleCollection.h"
 #include "RuleExist.h"
 #include "SentenceAlignmentWithSyntax.h"
-#include "SyntaxTree.h"
+#include "SyntaxNode.h"
 #include "tables-core.h"
 #include "XmlTree.h"
 #include "InputFileStream.h"

phrase-extract/pcfg-common/xml_tree_parser.h

@@ -28,7 +28,8 @@
 #include <vector>
 
 #include "pcfg_tree.h"
-#include "SyntaxTree.h"
+#include "SyntaxNode.h"
+#include "SyntaxNodeCollection.h"
 
 namespace MosesTraining {
 namespace Syntax {
@@ -47,7 +48,7 @@ class XmlTreeParser {
   std::set<std::string> m_labelSet;
   std::map<std::string, int> m_topLabelSet;
   std::string m_line;
-  MosesTraining::SyntaxTree m_tree;
+  MosesTraining::SyntaxNodeCollection m_tree;
   std::vector<std::string> m_words;
 };
 

phrase-extract/relax-parse-main.cpp

@@ -43,7 +43,7 @@ int main(int argc, char* argv[])
     // process into syntax tree representation
     set< string > labelCollection;         // set of labels, not used
     map< string, int > topLabelCollection; // count of top labels, not used
-    SyntaxTree tree;
+    SyntaxNodeCollection tree;
     ProcessAndStripXMLTags( inBufferString, tree, labelCollection, topLabelCollection, false );
     const vector< string > inWords = util::tokenize( inBufferString );
 
@@ -105,7 +105,7 @@ void init(int argc, char* argv[])
   }
 }
 
-void store( SyntaxTree &tree, const vector< string > &words )
+void store( SyntaxNodeCollection &tree, const vector< string > &words )
 {
   // output words
   for( size_t i=0; i<words.size(); i++ ) {
@@ -126,7 +126,7 @@ void store( SyntaxTree &tree, const vector< string > &words )
   cout << endl;
 }
 
-void LeftBinarize( SyntaxTree &tree, ParentNodes &parents )
+void LeftBinarize( SyntaxNodeCollection &tree, ParentNodes &parents )
 {
   for(ParentNodes::const_iterator p = parents.begin(); p != parents.end(); p++) {
     const SplitPoints &point = *p;
@@ -143,7 +143,7 @@ void LeftBinarize( SyntaxTree &tree, ParentNodes &parents )
   }
 }
 
-void RightBinarize( SyntaxTree &tree, ParentNodes &parents )
+void RightBinarize( SyntaxNodeCollection &tree, ParentNodes &parents )
 {
   for(ParentNodes::const_iterator p = parents.begin(); p != parents.end(); p++) {
     const SplitPoints &point = *p;
@@ -161,11 +161,11 @@ void RightBinarize( SyntaxTree &tree, ParentNodes &parents )
   }
 }
 
-void SAMT( SyntaxTree &tree, ParentNodes &parents )
+void SAMT( SyntaxNodeCollection &tree, ParentNodes &parents )
 {
   int numWords = tree.GetNumWords();
 
-  SyntaxTree newTree; // to store new nodes
+  SyntaxNodeCollection newTree; // to store new nodes
 
   // look through parents to combine children
   for(ParentNodes::const_iterator p = parents.begin(); p != parents.end(); p++) {

phrase-extract/relax-parse.h

@@ -28,7 +28,7 @@
 #include <algorithm>
 #include <cstring>
 
-#include "SyntaxTree.h"
+#include "SyntaxNodeCollection.h"
 #include "XmlTree.h"
 
 #define LINE_MAX_LENGTH 1000000
@@ -39,8 +39,8 @@ char SAMTLevel = 0;
 
 // functions
 void init(int argc, char* argv[]);
-void store( MosesTraining::SyntaxTree &tree, const std::vector<std::string> &words );
-void LeftBinarize( MosesTraining::SyntaxTree &tree, MosesTraining::ParentNodes &parents );
-void RightBinarize( MosesTraining::SyntaxTree &tree, MosesTraining::ParentNodes &parents );
-void SAMT( MosesTraining::SyntaxTree &tree, MosesTraining::ParentNodes &parents );
+void store( MosesTraining::SyntaxNodeCollection &tree, const std::vector<std::string> &words );
+void LeftBinarize( MosesTraining::SyntaxNodeCollection &tree, MosesTraining::ParentNodes &parents );
+void RightBinarize( MosesTraining::SyntaxNodeCollection &tree, MosesTraining::ParentNodes &parents );
+void SAMT( MosesTraining::SyntaxNodeCollection &tree, MosesTraining::ParentNodes &parents );
 

phrase-extract/syntax-common/xml_tree_parser.cc

@@ -13,17 +13,17 @@ namespace Syntax {
 
 StringTree *XmlTreeParser::Parse(const std::string &line) {
   line_ = line;
-  tree_.Clear();
+  node_collection_.Clear();
   try {
-    if (!ProcessAndStripXMLTags(line_, tree_, label_set_, top_label_set_,
-                                false)) {
+    if (!ProcessAndStripXMLTags(line_, node_collection_, label_set_,
+                                top_label_set_, false)) {
       throw Exception("");
     }
   } catch (const XmlException &e) {
     throw Exception(e.getMsg());
   }
-  tree_.ConnectNodes();
-  SyntaxNode *root = tree_.GetTop();
+  node_collection_.ConnectNodes();
+  SyntaxNode *root = node_collection_.GetTop();
   assert(root);
   words_ = util::tokenize(line_);
   return ConvertTree(*root, words_);

phrase-extract/syntax-common/xml_tree_parser.h

@@ -5,7 +5,8 @@
 #include <string>
 #include <vector>
 
-#include "SyntaxTree.h"
+#include "SyntaxNode.h"
+#include "SyntaxNodeCollection.h"
 
 #include "exception.h"
 #include "string_tree.h"
@@ -26,7 +27,7 @@ class XmlTreeParser {
   std::set<std::string> label_set_;
   std::map<std::string, int> top_label_set_;
   std::string line_;
-  MosesTraining::SyntaxTree tree_;
+  MosesTraining::SyntaxNodeCollection node_collection_;
   std::vector<std::string> words_;
 };
 

scripts/OSM/OSM-Train.perl

@@ -1,4 +1,7 @@
 #!/usr/bin/env perl
+#
+# This file is part of moses.  Its use is licensed under the GNU Lesser General
+# Public License version 2.1 or, at your option, any later version.
 
 use warnings;
 use strict;

scripts/OSM/extract-singletons.perl

@@ -1,4 +1,7 @@
 #!/usr/bin/env perl
+#
+# This file is part of moses.  Its use is licensed under the GNU Lesser General
+# Public License version 2.1 or, at your option, any later version.
 
 #use strict;
 use warnings;

scripts/OSM/flipAlignment.perl

@@ -1,4 +1,7 @@
 #!/usr/bin/env perl
+#
+# This file is part of moses.  Its use is licensed under the GNU Lesser General
+# Public License version 2.1 or, at your option, any later version.
 
 use warnings;
 use strict;

scripts/Transliteration/clean.pl

@@ -1,4 +1,7 @@
 #!/usr/bin/env perl
+#
+# This file is part of moses.  Its use is licensed under the GNU Lesser General
+# Public License version 2.1 or, at your option, any later version.
 
 #input hindi word urdu word, delete all those entries that have number on any side
 use warnings;
@@ -314,4 +317,4 @@ sub charFreqFilter{
 		}
 	}
   }
-}
+}

scripts/Transliteration/corpusCreator.pl

@@ -1,4 +1,7 @@
 #!/usr/bin/env perl
+#
+# This file is part of moses.  Its use is licensed under the GNU Lesser General
+# Public License version 2.1 or, at your option, any later version.
 
 use warnings;
 use strict;

scripts/Transliteration/in-decoding-transliteration.pl

@@ -1,4 +1,7 @@
 #!/usr/bin/env perl
+#
+# This file is part of moses.  Its use is licensed under the GNU Lesser General
+# Public License version 2.1 or, at your option, any later version.
 
 use warnings;
 use strict;

scripts/Transliteration/post-decoding-transliteration.pl

@@ -1,4 +1,7 @@
 #!/usr/bin/env perl
+#
+# This file is part of moses.  Its use is licensed under the GNU Lesser General
+# Public License version 2.1 or, at your option, any later version.
 
 use warnings;
 use strict;

scripts/Transliteration/prepare-transliteration-phrase-table.pl

@@ -1,4 +1,7 @@
 #!/usr/bin/env perl
+#
+# This file is part of moses.  Its use is licensed under the GNU Lesser General
+# Public License version 2.1 or, at your option, any later version.
 
 use warnings;
 use strict;

scripts/Transliteration/threshold.pl

@@ -1,4 +1,7 @@
 #!/usr/bin/env perl
+#
+# This file is part of moses.  Its use is licensed under the GNU Lesser General
+# Public License version 2.1 or, at your option, any later version.
 
 use warnings;
 use utf8;

scripts/Transliteration/train-transliteration-module.pl

@@ -1,4 +1,7 @@
 #!/usr/bin/env perl
+#
+# This file is part of moses.  Its use is licensed under the GNU Lesser General
+# Public License version 2.1 or, at your option, any later version.
 
 use warnings;
 use utf8;

scripts/analysis/bootstrap-hypothesis-difference-significance.pl

@@ -1,4 +1,7 @@
 #!/usr/bin/env perl
+#
+# This file is part of moses.  Its use is licensed under the GNU Lesser General
+# Public License version 2.1 or, at your option, any later version.
 use utf8;
 
 ###############################################

scripts/analysis/extract-target-trees.py

@@ -1,9 +1,13 @@
 #!/usr/bin/env python
-
-# Usage: extract-target-trees.py [FILE]
 #
-# Reads moses-chart's -T output from FILE or standard input and writes trees to
-# standard output in Moses' XML tree format.
+# This file is part of moses.  Its use is licensed under the GNU Lesser General
+# Public License version 2.1 or, at your option, any later version.
+
+"""Usage: extract-target-trees.py [FILE]
+
+Reads moses-chart's -T output from FILE or standard input and writes trees to
+standard output in Moses' XML tree format.
+"""
 
 import re
 import sys

scripts/analysis/nontranslated_words.pl

@@ -1,4 +1,7 @@
 #!/usr/bin/env perl
+#
+# This file is part of moses.  Its use is licensed under the GNU Lesser General
+# Public License version 2.1 or, at your option, any later version.
 
 # $Id$
 # Reads a source and hypothesis file and counts equal tokens. Some of these

scripts/analysis/oov.pl

@@ -1,6 +1,9 @@
 #!/usr/bin/env perl
 # Display OOV rate of a test set against a training corpus or a phrase table.
 # Ondrej Bojar
+#
+# This file is part of moses.  Its use is licensed under the GNU Lesser General
+# Public License version 2.1 or, at your option, any later version.
 
 use strict;
 use warnings;

scripts/analysis/sentence-by-sentence.pl

@@ -1,4 +1,7 @@
 #!/usr/bin/env perl
+#
+# This file is part of moses.  Its use is licensed under the GNU Lesser General
+# Public License version 2.1 or, at your option, any later version.
 
 # $Id$
 #sentence-by-sentence: take in a system output, with any number of factors, and a reference translation, also maybe with factors, and show each sentence and its errors

scripts/analysis/sg2dot.perl

@@ -3,6 +3,8 @@
 # Author : Loic BARRAULT
 # Script to convert MOSES searchgraph to DOT format
 #
+# This file is part of moses.  Its use is licensed under the GNU Lesser General
+# Public License version 2.1 or, at your option, any later version.
 
 use warnings;
 use strict;

scripts/analysis/show-phrases-used.pl

@@ -1,4 +1,7 @@
 #!/usr/bin/env perl
+#
+# This file is part of moses.  Its use is licensed under the GNU Lesser General
+# Public License version 2.1 or, at your option, any later version.
 
 # $Id$
 #show-phrases-used: display all source and target phrases for each sentence in a corpus, and give average phrase length used

scripts/analysis/smtgui/Corpus.pm

@@ -1,5 +1,8 @@
 #package Corpus: hold a bunch of sentences in any language, with translation factors and stats about individual sentences and the corpus as a whole
 #Evan Herbst, 7 / 25 / 06
+#
+# This file is part of moses.  Its use is licensed under the GNU Lesser General
+# Public License version 2.1 or, at your option, any later version.
 
 package Corpus;
 BEGIN

scripts/analysis/smtgui/filter-phrase-table.pl

@@ -1,4 +1,7 @@
 #!/usr/bin/env perl
+#
+# This file is part of moses.  Its use is licensed under the GNU Lesser General
+# Public License version 2.1 or, at your option, any later version.
 
 # $Id$
 #by Philipp Koehn, de-augmented by Evan Herbst

scripts/analysis/smtgui/newsmtgui.cgi

@@ -1,4 +1,7 @@
 #!/usr/bin/perl -w
+#
+# This file is part of moses.  Its use is licensed under the GNU Lesser General
+# Public License version 2.1 or, at your option, any later version.
 
 # $Id$
 use strict;

scripts/analysis/suspicious_tokenization.pl

@@ -2,6 +2,9 @@
 # Collects and prints all n-grams that appear in the given corpus both
 # tokenized as well as untokenized.
 # Ondrej Bojar
+#
+# This file is part of moses.  Its use is licensed under the GNU Lesser General
+# Public License version 2.1 or, at your option, any later version.
 
 use strict;
 use warnings;

scripts/analysis/weight-scan-summarize.sh

@@ -1,4 +1,8 @@
 #!/bin/bash
+#
+# This file is part of moses.  Its use is licensed under the GNU Lesser General
+# Public License version 2.1 or, at your option, any later version.
+
 # Hackish summarization of weight-scan.pl results, heavily relies on tools by
 # Ondrej Bojar (bojar@ufal.mff.cuni.cz), some of which need Mercury; beware.
 

scripts/analysis/weight-scan.pl

@@ -1,4 +1,8 @@
 #!/usr/bin/env perl
+#
+# This file is part of moses.  Its use is licensed under the GNU Lesser General
+# Public License version 2.1 or, at your option, any later version.
+
 # runs Moses many times changing the values of one weight, all others fixed
 # nbest lists are always produced to allow for comparison of real and
 # 'projected' BLEU (BLEU estimated from n-best lists collected at a neighouring

scripts/ems/experiment.perl

@@ -1,4 +1,7 @@
 #!/usr/bin/env perl
+#
+# This file is part of moses.  Its use is licensed under the GNU Lesser General
+# Public License version 2.1 or, at your option, any later version.
 
 # Experiment Management System
 # Documentation at http://www.statmt.org/moses/?n=FactoredTraining.EMS

scripts/ems/fix-info.perl

@@ -1,4 +1,7 @@
 #!/usr/bin/env perl
+#
+# This file is part of moses.  Its use is licensed under the GNU Lesser General
+# Public License version 2.1 or, at your option, any later version.
 
 use warnings;
 use strict;

scripts/ems/support/analysis.perl

@@ -1,4 +1,7 @@
 #!/usr/bin/env perl
+#
+# This file is part of moses.  Its use is licensed under the GNU Lesser General
+# Public License version 2.1 or, at your option, any later version.
 
 use warnings;
 use strict;

scripts/ems/support/berkeley-process.sh

@@ -1,4 +1,7 @@
 #!/bin/sh
+#
+# This file is part of moses.  Its use is licensed under the GNU Lesser General
+# Public License version 2.1 or, at your option, any later version.
 
 if [ $# -lt 8 ]
 	then

scripts/ems/support/berkeley-train.sh

@@ -1,4 +1,7 @@
 #!/bin/sh
+#
+# This file is part of moses.  Its use is licensed under the GNU Lesser General
+# Public License version 2.1 or, at your option, any later version.
 
 if [ $# -lt 6 ]
 	then

scripts/ems/support/build-domain-file-from-subcorpora.perl

@@ -1,4 +1,7 @@
 #!/usr/bin/env perl
+#
+# This file is part of moses.  Its use is licensed under the GNU Lesser General
+# Public License version 2.1 or, at your option, any later version.
 
 use warnings;
 use strict;

scripts/ems/support/build-sparse-features.perl

@@ -1,4 +1,7 @@
 #!/usr/bin/env perl
+#
+# This file is part of moses.  Its use is licensed under the GNU Lesser General
+# Public License version 2.1 or, at your option, any later version.
 
 use warnings;
 use strict;

scripts/ems/support/consolidate-training-data.perl

@@ -1,4 +1,7 @@
 #!/usr/bin/env perl
+#
+# This file is part of moses.  Its use is licensed under the GNU Lesser General
+# Public License version 2.1 or, at your option, any later version.
 
 # $Id: consolidate-training-data.perl 928 2009-09-02 02:58:01Z philipp $
 

scripts/ems/support/defaultconfig.py

@@ -1,4 +1,7 @@
 #!/usr/bin/env python2
+#
+# This file is part of moses.  Its use is licensed under the GNU Lesser General
+# Public License version 2.1 or, at your option, any later version.
 
 """Version of ConfigParser which accepts default values."""
 

scripts/ems/support/fast-align-in-parts.perl

@@ -1,4 +1,7 @@
 #!/usr/bin/env perl
+#
+# This file is part of moses.  Its use is licensed under the GNU Lesser General
+# Public License version 2.1 or, at your option, any later version.
 
 #######################
 # Revision history

scripts/ems/support/generic-multicore-parallelizer.perl

@@ -1,4 +1,7 @@
 #!/usr/bin/env perl
+#
+# This file is part of moses.  Its use is licensed under the GNU Lesser General
+# Public License version 2.1 or, at your option, any later version.
 
 use warnings;
 use strict;

scripts/ems/support/generic-parallelizer.perl

@@ -1,4 +1,7 @@
 #!/usr/bin/env perl
+#
+# This file is part of moses.  Its use is licensed under the GNU Lesser General
+# Public License version 2.1 or, at your option, any later version.
 
 use warnings;
 use strict;

scripts/ems/support/input-from-sgm.perl

@@ -1,4 +1,7 @@
 #!/usr/bin/env perl
+#
+# This file is part of moses.  Its use is licensed under the GNU Lesser General
+# Public License version 2.1 or, at your option, any later version.
 
 use warnings;
 use strict;

scripts/ems/support/interpolate-lm.perl

@@ -1,4 +1,7 @@
 #!/usr/bin/env perl
+#
+# This file is part of moses.  Its use is licensed under the GNU Lesser General
+# Public License version 2.1 or, at your option, any later version.
 
 use warnings;
 use strict;

scripts/ems/support/lmplz-wrapper.perl

@@ -1,4 +1,7 @@
 #!/usr/bin/env perl
+#
+# This file is part of moses.  Its use is licensed under the GNU Lesser General
+# Public License version 2.1 or, at your option, any later version.
 
 use warnings;
 use strict;

scripts/ems/support/mml-filter.perl

@@ -1,4 +1,7 @@
 #!/usr/bin/env perl
+#
+# This file is part of moses.  Its use is licensed under the GNU Lesser General
+# Public License version 2.1 or, at your option, any later version.
 
 use warnings;
 use strict;

scripts/ems/support/mml-score.perl

@@ -1,4 +1,7 @@
 #!/usr/bin/env perl
+#
+# This file is part of moses.  Its use is licensed under the GNU Lesser General
+# Public License version 2.1 or, at your option, any later version.
 
 use warnings;
 use strict;

scripts/ems/support/mml-train.perl

@@ -1,4 +1,7 @@
 #!/usr/bin/env perl
+#
+# This file is part of moses.  Its use is licensed under the GNU Lesser General
+# Public License version 2.1 or, at your option, any later version.
 
 use warnings;
 use strict;

scripts/ems/support/prepare-fast-align.perl

@@ -1,4 +1,7 @@
 #!/usr/bin/env perl
+#
+# This file is part of moses.  Its use is licensed under the GNU Lesser General
+# Public License version 2.1 or, at your option, any later version.
 
 use warnings;
 use strict;

scripts/ems/support/reference-from-sgm.perl

@@ -1,4 +1,7 @@
 #!/usr/bin/env perl
+#
+# This file is part of moses.  Its use is licensed under the GNU Lesser General
+# Public License version 2.1 or, at your option, any later version.
 
 use warnings;
 use strict;

scripts/ems/support/remove-segmentation-markup.perl

@@ -1,4 +1,7 @@
 #!/usr/bin/env perl
+#
+# This file is part of moses.  Its use is licensed under the GNU Lesser General
+# Public License version 2.1 or, at your option, any later version.
 
 use warnings;
 use strict;

scripts/ems/support/report-experiment-scores.perl

@@ -1,4 +1,7 @@
 #!/usr/bin/env perl
+#
+# This file is part of moses.  Its use is licensed under the GNU Lesser General
+# Public License version 2.1 or, at your option, any later version.
 
 # $Id: report-experiment-scores.perl 407 2008-11-10 14:43:31Z philipp $
 

scripts/ems/support/run-command-on-multiple-refsets.perl

@@ -1,4 +1,7 @@
 #!/usr/bin/env perl
+#
+# This file is part of moses.  Its use is licensed under the GNU Lesser General
+# Public License version 2.1 or, at your option, any later version.
 
 use warnings;
 use strict;

scripts/ems/support/run-wade.perl

@@ -1,4 +1,7 @@
 #!/usr/bin/env perl
+#
+# This file is part of moses.  Its use is licensed under the GNU Lesser General
+# Public License version 2.1 or, at your option, any later version.
 
 use warnings;
 use strict;

scripts/ems/support/split-sentences.perl

@@ -1,4 +1,7 @@
 #!/usr/bin/env perl
+#
+# This file is part of moses.  Its use is licensed under the GNU Lesser General
+# Public License version 2.1 or, at your option, any later version.
 
 # Based on Preprocessor written by Philipp Koehn
 

scripts/ems/support/submit-grid.perl

@@ -1,4 +1,7 @@
 #!/usr/bin/env perl
+#
+# This file is part of moses.  Its use is licensed under the GNU Lesser General
+# Public License version 2.1 or, at your option, any later version.
 
 use warnings;
 use strict;

scripts/ems/support/substitute-filtered-tables-and-weights.perl

@@ -1,4 +1,7 @@
 #!/usr/bin/env perl
+#
+# This file is part of moses.  Its use is licensed under the GNU Lesser General
+# Public License version 2.1 or, at your option, any later version.
 
 use warnings;
 use strict;

scripts/ems/support/substitute-filtered-tables.perl

@@ -1,4 +1,7 @@
 #!/usr/bin/env perl
+#
+# This file is part of moses.  Its use is licensed under the GNU Lesser General
+# Public License version 2.1 or, at your option, any later version.
 
 use warnings;
 

scripts/ems/support/substitute-weights.perl

@@ -1,4 +1,7 @@
 #!/usr/bin/env perl
+#
+# This file is part of moses.  Its use is licensed under the GNU Lesser General
+# Public License version 2.1 or, at your option, any later version.
 
 use warnings;
 

scripts/ems/support/symmetrize-fast-align.perl

@@ -1,4 +1,7 @@
 #!/usr/bin/env perl
+#
+# This file is part of moses.  Its use is licensed under the GNU Lesser General
+# Public License version 2.1 or, at your option, any later version.
 
 use warnings;
 use strict;

scripts/ems/support/thot-lm-wrapper.perl

@@ -1,4 +1,7 @@
 #!/usr/bin/env perl
+#
+# This file is part of moses.  Its use is licensed under the GNU Lesser General
+# Public License version 2.1 or, at your option, any later version.
 
 use warnings;
 use strict;

scripts/ems/support/tree-converter-wrapper.perl

@@ -1,4 +1,7 @@
 #!/usr/bin/env perl
+#
+# This file is part of moses.  Its use is licensed under the GNU Lesser General
+# Public License version 2.1 or, at your option, any later version.
 
 use warnings;
 use strict;

scripts/ems/support/wrap-xml.perl

@@ -1,4 +1,7 @@
 #!/usr/bin/env perl
+#
+# This file is part of moses.  Its use is licensed under the GNU Lesser General
+# Public License version 2.1 or, at your option, any later version.
 
 use warnings;
 use strict;

scripts/ems/web/analysis.php

@@ -1,5 +1,10 @@
 <?php
 
+/*
+This file is part of moses.  Its use is licensed under the GNU Lesser General
+Public License version 2.1 or, at your option, any later version.
+*/
+
 # main page frame, triggers the loading of parts
 function show_analysis() {
   global $task,$user,$setup,$id,$set;

scripts/ems/web/analysis_diff.php

@@ -1,5 +1,9 @@
 <?php
 
+/*
+This file is part of moses.  Its use is licensed under the GNU Lesser General
+Public License version 2.1 or, at your option, any later version.
+*/
 function diff_analysis() {
   global $task,$user,$setup,$id,$id2,$set;
   global $comment,$dir;

scripts/ems/web/diff.php

@@ -1,5 +1,10 @@
 <?php
 
+/*
+This file is part of moses.  Its use is licensed under the GNU Lesser General
+Public License version 2.1 or, at your option, any later version.
+*/
+
 function diff() {
   global $experiment;
   $display = $_GET["run"];

scripts/ems/web/hierarchical-segmentation.js

@@ -1,3 +1,7 @@
+/*
+This file is part of moses.  Its use is licensed under the GNU Lesser General
+Public License version 2.1 or, at your option, any later version.
+*/
 var nodeIn = [];
 var nodeOut = [];
 var nodeChildren = [];

scripts/ems/web/index.php

@@ -1,5 +1,10 @@
 <?php
 
+/*
+This file is part of moses.  Its use is licensed under the GNU Lesser General
+Public License version 2.1 or, at your option, any later version.
+*/
+
 require("lib.php");
 require("overview.php");
 require("analysis.php");

scripts/ems/web/lib.php

@@ -1,5 +1,10 @@
 <?php
 
+/*
+This file is part of moses.  Its use is licensed under the GNU Lesser General
+Public License version 2.1 or, at your option, any later version.
+*/
+
 function load_experiment_info() {
   global $dir,$task,$user,$setup;
   global $evalset;

scripts/ems/web/overview.php

@@ -1,5 +1,9 @@
 <?php
 
+/*
+This file is part of moses.  Its use is licensed under the GNU Lesser General
+Public License version 2.1 or, at your option, any later version.
+*/
 
 function setup() {
   $setup = file("setup");

scripts/ems/web/progress.perl

@@ -1,4 +1,7 @@
 #!/usr/bin/env perl
+#
+# This file is part of moses.  Its use is licensed under the GNU Lesser General
+# Public License version 2.1 or, at your option, any later version.
 
 use warnings;
 use strict;

scripts/ems/web/sgviz.js

@@ -1,3 +1,7 @@
+/*
+This file is part of moses.  Its use is licensed under the GNU Lesser General
+Public License version 2.1 or, at your option, any later version.
+*/
 var xmlns="http://www.w3.org/2000/svg";
 var RECOMBINED = 0;
 var FROM = 1;

scripts/ems/web/sgviz.php

@@ -1,4 +1,10 @@
 <?php
+
+/*
+This file is part of moses.  Its use is licensed under the GNU Lesser General
+Public License version 2.1 or, at your option, any later version.
+*/
+
 function sgviz($sentence) {
   global $setup,$dir,$id,$set;
 ?><html><head><title>Search Graph Visualization, Sentence <?php $sentence ?></title>

scripts/fuzzy-match/create_xml.perl

@@ -1,4 +1,7 @@
 #!/usr/bin/env perl
+#
+# This file is part of moses.  Its use is licensed under the GNU Lesser General
+# Public License version 2.1 or, at your option, any later version.
 
 binmode( STDIN,  ":utf8" );
 binmode( STDOUT, ":utf8" );

scripts/generic/bsbleu.py

@@ -1,6 +1,9 @@
 #!/usr/bin/env python
 # compute Bleu scores with confidence intervals via boostrap resampling
 # written by Ulrich Germann
+#
+# This file is part of moses.  Its use is licensed under the GNU Lesser General
+# Public License version 2.1 or, at your option, any later version.
 
 from argparse import ArgumentParser
 import math

scripts/generic/compound-splitter.perl

@@ -1,4 +1,7 @@
 #!/usr/bin/env perl
+#
+# This file is part of moses.  Its use is licensed under the GNU Lesser General
+# Public License version 2.1 or, at your option, any later version.
 
 use warnings;
 use strict;

scripts/generic/extract-factors.pl

@@ -1,4 +1,7 @@
 #!/usr/bin/env perl
+#
+# This file is part of moses.  Its use is licensed under the GNU Lesser General
+# Public License version 2.1 or, at your option, any later version.
 
 # $Id$
 #extract-factors.pl: extract only the desired factors from a factored corpus

scripts/generic/extract-parallel.perl

@@ -1,4 +1,7 @@
 #!/usr/bin/env perl
+#
+# This file is part of moses.  Its use is licensed under the GNU Lesser General
+# Public License version 2.1 or, at your option, any later version.
 
 # example
 #  ./extract-parallel.perl 8 ./coreutils-8.9/src/split "./coreutils-8.9/src/sort --batch-size=253" ./extract ./corpus.5.en ./corpus.5.ar ./align.ar-en.grow-diag-final-and ./extracted 7 --NoFileLimit orientation --GZOutput

scripts/generic/fsa2fsal.pl

@@ -4,6 +4,9 @@
 # ' ' to delimit nodes (i.e. original lines).
 # Some rudimentary sanity checks are done on the fly.
 # Ondrej Bojar, bojar@ufal.mff.cuni.cz
+#
+# This file is part of moses.  Its use is licensed under the GNU Lesser General
+# Public License version 2.1 or, at your option, any later version.
 
 use warnings;
 use strict;

scripts/generic/fsa2plf.pl

@@ -7,6 +7,9 @@
 # final nodes.
 # Note that the output format may not contain any spaces.
 # Ondrej Bojar, bojar@ufal.mff.cuni.cz
+#
+# This file is part of moses.  Its use is licensed under the GNU Lesser General
+# Public License version 2.1 or, at your option, any later version.
 
 use warnings;
 use strict;

scripts/generic/fsal2fsa.pl

@@ -1,6 +1,9 @@
 #!/usr/bin/env perl
 # A very simple script that converts fsal back to fsa format (openfst lattices)
 # Ondrej Bojar, bojar@ufal.mff.cuni.cz
+#
+# This file is part of moses.  Its use is licensed under the GNU Lesser General
+# Public License version 2.1 or, at your option, any later version.
 
 use warnings;
 use strict;

scripts/generic/generic-parallel.perl

@@ -1,4 +1,7 @@
 #!/usr/bin/env perl
+#
+# This file is part of moses.  Its use is licensed under the GNU Lesser General
+# Public License version 2.1 or, at your option, any later version.
 
 use warnings;
 use strict;

scripts/generic/giza-parallel.perl

@@ -1,4 +1,7 @@
 #!/usr/bin/env perl
+#
+# This file is part of moses.  Its use is licensed under the GNU Lesser General
+# Public License version 2.1 or, at your option, any later version.
 
 # example
 # ~/giza-parallel.perl 10 split ~/workspace/sourceforge/trunk/scripts/training/train-model.perl ar en train align

scripts/generic/lopar2pos.pl

@@ -1,4 +1,7 @@
 #!/usr/bin/env perl
+#
+# This file is part of moses.  Its use is licensed under the GNU Lesser General
+# Public License version 2.1 or, at your option, any later version.
 
 # $Id$
 #lopar2pos: extract POSs from LOPAR output

scripts/generic/moses-parallel.pl

@@ -1,4 +1,7 @@
 #!/usr/bin/env perl
+#
+# This file is part of moses.  Its use is licensed under the GNU Lesser General
+# Public License version 2.1 or, at your option, any later version.
 
 # $Id$
 #######################

scripts/generic/moses_sim_pe.py

@@ -1,20 +1,25 @@
 #!/usr/bin/env python
 
 # Written by Michael Denkowski
+#
+# This file is part of moses.  Its use is licensed under the GNU Lesser General
+# Public License version 2.1 or, at your option, any later version.
 
-# This script parallelizes decoding with simulated post-editing via moses XML
-# input (XML entities need to be escaped in tokenization).  Memory mapped
-# dynamic phrase tables (Ulrich Germann,
-# www.statmt.org/moses/?n=Moses.AdvancedFeatures#ntoc40) and language models
-# (Kenneth Heafield,
-# http://www.statmt.org/moses/?n=FactoredTraining.BuildingLanguageModel#ntoc19)
-# facilitate memory efficient multi process decoding.  Input is divided into
-# batches, each of which is decoded sequentially.  Each batch pre-loads the
-# data from previous batches.
+"""Parallelize decoding with simulated post-editing via moses XML input.
 
-# To use in tuning, run mert-moses.pl with --sim-pe=SYMAL where SYMAL is the
-# alignment from input to references.  Specify the number of jobs with
-# --decoder-flags="-threads N".
+(XML entities need to be escaped in tokenization).  Memory mapped
+dynamic phrase tables (Ulrich Germann,
+www.statmt.org/moses/?n=Moses.AdvancedFeatures#ntoc40) and language models
+(Kenneth Heafield,
+http://www.statmt.org/moses/?n=FactoredTraining.BuildingLanguageModel#ntoc19)
+facilitate memory efficient multi process decoding.  Input is divided into
+batches, each of which is decoded sequentially.  Each batch pre-loads the
+data from previous batches.
+
+To use in tuning, run mert-moses.pl with --sim-pe=SYMAL where SYMAL is the
+alignment from input to references.  Specify the number of jobs with
+--decoder-flags="-threads N".
+"""
 
 import gzip
 import itertools

scripts/generic/mteval-v12.pl

@@ -1,4 +1,7 @@
 #!/usr/bin/env perl
+#
+# This file is part of moses.  Its use is licensed under the GNU Lesser General
+# Public License version 2.1 or, at your option, any later version.
 
 use warnings;
 use strict;

scripts/generic/mteval-v13a.pl

@@ -1,4 +1,7 @@
 #!/usr/bin/env perl
+#
+# This file is part of moses.  Its use is licensed under the GNU Lesser General
+# Public License version 2.1 or, at your option, any later version.
 
 use warnings;
 use strict;

scripts/generic/multi-bleu.perl

@@ -1,4 +1,7 @@
 #!/usr/bin/env perl
+#
+# This file is part of moses.  Its use is licensed under the GNU Lesser General
+# Public License version 2.1 or, at your option, any later version.
 
 # $Id$
 use warnings;

scripts/generic/ph_numbers.perl

@@ -6,6 +6,9 @@ package ph_numbers;
 # and decoder input
 #
 # (c) 2013 TAUS
+#
+# This file is part of moses.  Its use is licensed under the GNU Lesser General
+# Public License version 2.1 or, at your option, any later version.
 
 use warnings;
 use strict;

scripts/generic/qsub-wrapper.pl

@@ -1,4 +1,7 @@
 #!/usr/bin/env perl
+#
+# This file is part of moses.  Its use is licensed under the GNU Lesser General
+# Public License version 2.1 or, at your option, any later version.
 
 # $Id$
 use warnings;