KenLM f81d02792087a837ea17e6ce2b33f9b7aaecca68 should fix segfault with ArrayTrie

lm/bhiksha.hh

@@ -13,14 +13,16 @@
 #ifndef LM_BHIKSHA_H
 #define LM_BHIKSHA_H
 
-#include <stdint.h>
-#include <assert.h>
-
 #include "lm/model_type.hh"
 #include "lm/trie.hh"
 #include "util/bit_packing.hh"
 #include "util/sorted_uniform.hh"
 
+#include <algorithm>
+
+#include <stdint.h>
+#include <assert.h>
+
 namespace lm {
 namespace ngram {
 struct Config;
@@ -73,15 +75,24 @@ class ArrayBhiksha {
     ArrayBhiksha(void *base, uint64_t max_offset, uint64_t max_value, const Config &config);
 
     void ReadNext(const void *base, uint64_t bit_offset, uint64_t index, uint8_t total_bits, NodeRange &out) const {
-      const uint64_t *begin_it = util::BinaryBelow(util::IdentityAccessor<uint64_t>(), offset_begin_, offset_end_, index);
+      // Some assertions are commented out because they are expensive.
+      // assert(*offset_begin_ == 0);
+      // std::upper_bound returns the first element that is greater.  Want the
+      // last element that is <= to the index.
+      const uint64_t *begin_it = std::upper_bound(offset_begin_, offset_end_, index) - 1;
+      // Since *offset_begin_ == 0, the position should be in range.
+      // assert(begin_it >= offset_begin_);
       const uint64_t *end_it;
-      for (end_it = begin_it; (end_it < offset_end_) && (*end_it <= index + 1); ++end_it) {}
+      for (end_it = begin_it + 1; (end_it < offset_end_) && (*end_it <= index + 1); ++end_it) {}
+      // assert(end_it == std::upper_bound(offset_begin_, offset_end_, index + 1));
       --end_it;
+      // assert(end_it >= begin_it);
       out.begin = ((begin_it - offset_begin_) << next_inline_.bits) | 
         util::ReadInt57(base, bit_offset, next_inline_.bits, next_inline_.mask);
       out.end = ((end_it - offset_begin_) << next_inline_.bits) | 
         util::ReadInt57(base, bit_offset + total_bits, next_inline_.bits, next_inline_.mask);
-      //assert(out.end >= out.begin);
+      // If this fails, consider rebuilding your model using KenLM after 1e333d786b748555e8f368d2bbba29a016c98052
+      assert(out.end >= out.begin);
     }
 
     void WriteNext(void *base, uint64_t bit_offset, uint64_t index, uint64_t value) {

lm/trie.cc

@@ -99,8 +99,11 @@ template <class Bhiksha> util::BitAddress BitPackedMiddle<Bhiksha>::Find(WordInd
 }
 
 template <class Bhiksha> void BitPackedMiddle<Bhiksha>::FinishedLoading(uint64_t next_end, const Config &config) {
-  uint64_t last_next_write = (insert_index_ + 1) * total_bits_ - bhiksha_.InlineBits();
-  bhiksha_.WriteNext(base_, last_next_write, insert_index_ + 1, next_end);
+  // Write at insert_index. . .
+  uint64_t last_next_write = insert_index_ * total_bits_ + 
+    // at the offset where the next pointers are stored.
+    (total_bits_ - bhiksha_.InlineBits());
+  bhiksha_.WriteNext(base_, last_next_write, insert_index_, next_end);
   bhiksha_.FinishedLoading(config);
 }
 

util/sorted_uniform.hh

@@ -101,27 +101,6 @@ template <class Iterator, class Accessor, class Pivot> bool SortedUniformFind(co
   return BoundedSortedUniformFind<Iterator, Accessor, Pivot>(accessor, begin, below, end, above, key, out);
 }
 
-// May return begin - 1.
-template <class Iterator, class Accessor> Iterator BinaryBelow(
-    const Accessor &accessor,
-    Iterator begin,
-    Iterator end,
-    const typename Accessor::Key key) {
-  while (end > begin) {
-    Iterator pivot(begin + (end - begin) / 2);
-    typename Accessor::Key mid(accessor(pivot));
-    if (mid < key) {
-      begin = pivot + 1;
-    } else if (mid > key) {
-      end = pivot;
-    } else {
-      for (++pivot; (pivot < end) && accessor(pivot) == mid; ++pivot) {}
-      return pivot - 1;
-    }
-  }
-  return begin - 1;
-}
-
 } // namespace util
 
 #endif // UTIL_SORTED_UNIFORM_H