Merge with upstream

1 files changed, 18 insertions, 13 deletions

diff --git a/klm/lm/read_arpa.hh b/klm/lm/read_arpa.hh
index 234d130c..64eeef30 100644
--- a/klm/lm/read_arpa.hh
+++ b/klm/lm/read_arpa.hh
@@ -1,5 +1,5 @@
-#ifndef LM_READ_ARPA__
-#define LM_READ_ARPA__
+#ifndef LM_READ_ARPA_H
+#define LM_READ_ARPA_H
 
 #include "lm/lm_exception.hh"
 #include "lm/word_index.hh"
@@ -28,7 +28,7 @@ void ReadEnd(util::FilePiece &in);
 
 extern const bool kARPASpaces[256];
 
-// Positive log probability warning.  
+// Positive log probability warning.
 class PositiveProbWarn {
   public:
     PositiveProbWarn() : action_(THROW_UP) {}
@@ -48,17 +48,17 @@ template <class Voc, class Weights> void Read1Gram(util::FilePiece &f, Voc &voca
       warn.Warn(prob);
       prob = 0.0;
     }
-    if (f.get() != '\t') UTIL_THROW(FormatLoadException, "Expected tab after probability");
-    Weights &value = unigrams[vocab.Insert(f.ReadDelimited(kARPASpaces))];
-    value.prob = prob;
-    ReadBackoff(f, value);
+    UTIL_THROW_IF(f.get() != '\t', FormatLoadException, "Expected tab after probability");
+    WordIndex word = vocab.Insert(f.ReadDelimited(kARPASpaces));
+    Weights &w = unigrams[word];
+    w.prob = prob;
+    ReadBackoff(f, w);
   } catch(util::Exception &e) {
     e << " in the 1-gram at byte " << f.Offset();
     throw;
   }
 }
 
-// Return true if a positive log probability came out.
 template <class Voc, class Weights> void Read1Grams(util::FilePiece &f, std::size_t count, Voc &vocab, Weights *unigrams, PositiveProbWarn &warn) {
   ReadNGramHeader(f, 1);
   for (std::size_t i = 0; i < count; ++i) {
@@ -67,16 +67,21 @@ template <class Voc, class Weights> void Read1Grams(util::FilePiece &f, std::siz
   vocab.FinishedLoading(unigrams);
 }
 
-// Return true if a positive log probability came out.
-template <class Voc, class Weights> void ReadNGram(util::FilePiece &f, const unsigned char n, const Voc &vocab, WordIndex *const reverse_indices, Weights &weights, PositiveProbWarn &warn) {
+// Read ngram, write vocab ids to indices_out.
+template <class Voc, class Weights, class Iterator> void ReadNGram(util::FilePiece &f, const unsigned char n, const Voc &vocab, Iterator indices_out, Weights &weights, PositiveProbWarn &warn) {
   try {
     weights.prob = f.ReadFloat();
     if (weights.prob > 0.0) {
       warn.Warn(weights.prob);
       weights.prob = 0.0;
     }
-    for (WordIndex *vocab_out = reverse_indices + n - 1; vocab_out >= reverse_indices; --vocab_out) {
-      *vocab_out = vocab.Index(f.ReadDelimited(kARPASpaces));
+    for (unsigned char i = 0; i < n; ++i, ++indices_out) {
+      StringPiece word(f.ReadDelimited(kARPASpaces));
+      WordIndex index = vocab.Index(word);
+      *indices_out = index;
+      // Check for words mapped to <unk> that are not the string <unk>.
+      UTIL_THROW_IF(index == 0 /* mapped to <unk> */ && (word != StringPiece("<unk>", 5)) && (word != StringPiece("<UNK>", 5)),
+          FormatLoadException, "Word " << word << " was not seen in the unigrams (which are supposed to list the entire vocabulary) but appears");
     }
     ReadBackoff(f, weights);
   } catch(util::Exception &e) {
@@ -87,4 +92,4 @@ template <class Voc, class Weights> void ReadNGram(util::FilePiece &f, const uns
 
 } // namespace lm
 
-#endif // LM_READ_ARPA__
+#endif // LM_READ_ARPA_H