Merge branch 'master' of /repos/git/LanguageModels/kenlm.latest

htetaung04 · Apr 24, 2014 · ef2d806 · ef2d806
2 parents da19b44 + cf2440a
commit ef2d806
Show file tree

Hide file tree

Showing 2 changed files with 7 additions and 6 deletions.
diff --git a/lm/builder/lmplz_main.cc b/lm/builder/lmplz_main.cc
@@ -95,7 +95,7 @@ int main(int argc, char *argv[]) {
       ("block_count", po::value<std::size_t>(&pipeline.block_count)->default_value(2), "Block count (per order)")
       ("vocab_estimate", po::value<lm::WordIndex>(&pipeline.vocab_estimate)->default_value(1000000), "Assume this vocabulary size for purposes of calculating memory in step 1 (corpus count) and pre-sizing the hash table")
       ("vocab_file", po::value<std::string>(&pipeline.vocab_file)->default_value(""), "Location to write a file containing the unique vocabulary strings delimited by null bytes")
-      ("vocab_pad", po::value<std::size_t>(&pipeline.vocab_size_for_unk)->default_value(0), "If the vocabulary is smaller than this value, pad with <unk> to reach this size. Requires --interpolate_unigrams")
+      ("vocab_pad", po::value<uint64_t>(&pipeline.vocab_size_for_unk)->default_value(0), "If the vocabulary is smaller than this value, pad with <unk> to reach this size. Requires --interpolate_unigrams")
       ("verbose_header", po::bool_switch(&pipeline.verbose_header), "Add a verbose header to the ARPA file that includes information such as token count, smoothing type, etc.")
       ("text", po::value<std::string>(&text), "Read text from a file instead of stdin")
       ("arpa", po::value<std::string>(&arpa), "Write ARPA to a file instead of stdout")

diff --git a/util/file.cc b/util/file.cc
@@ -5,28 +5,29 @@
 
 #include "util/exception.hh"
 
+#include <algorithm>
 #include <cstdlib>
 #include <cstdio>
-#include <sstream>
 #include <iostream>
+#include <limits>
+#include <sstream>
+
 
 #include <assert.h>
 #include <errno.h>
+#include <limits.h>
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <fcntl.h>
 #include <stdint.h>
 
-#if defined __MINGW32__
+#if defined(__MINGW32__)
 #include <windows.h>
 #include <unistd.h>
 #warning "The file functions on MinGW have not been tested for file sizes above 2^31 - 1.  Please read https://stackoverflow.com/questions/12539488/determine-64-bit-file-size-in-c-on-mingw-32-bit and fix"
 #elif defined(_WIN32) || defined(_WIN64)
 #include <windows.h>
 #include <io.h>
-#include <algorithm>
-#include <limits.h>
-#include <limits>
 #else
 #include <unistd.h>
 #endif