From dc16aa2accc7d9033d9c31c7bbc5e581d43a5101 Mon Sep 17 00:00:00 2001
From: Kenneth Heafield <github@kheafield.com>
Date: Sun, 20 Jan 2013 12:31:03 +0000
Subject: Better delimiters, cross-platform fixes

---
 klm/lm/builder/corpus_count.cc | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'klm/lm/builder')

diff --git a/klm/lm/builder/corpus_count.cc b/klm/lm/builder/corpus_count.cc
index 8c3de57d..abea4ed0 100644
--- a/klm/lm/builder/corpus_count.cc
+++ b/klm/lm/builder/corpus_count.cc
@@ -202,11 +202,12 @@ void CorpusCount::Run(const util::stream::ChainPosition &position) {
   const WordIndex end_sentence = vocab.Lookup("</s>");
   Writer writer(NGram::OrderFromSize(position.GetChain().EntrySize()), position, dedupe_mem_.get(), dedupe_mem_size_);
   uint64_t count = 0;
+  StringPiece delimiters("\0\t\r ", 4);
   try {
     while(true) {
       StringPiece line(from_.ReadLine());
       writer.StartSentence();
-      for (util::TokenIter<util::AnyCharacter, true> w(line, " \t"); w; ++w) {
+      for (util::TokenIter<util::AnyCharacter, true> w(line, delimiters); w; ++w) {
         WordIndex word = vocab.Lookup(*w);
         UTIL_THROW_IF(word <= 2, FormatLoadException, "Special word " << *w << " is not allowed in the corpus.  I plan to support models containing <unk> in the future.");
         writer.Append(word);
-- 
cgit v1.2.3