summaryrefslogtreecommitdiff
path: root/src/core/utils/CodeTokenizer.hpp
diff options
context:
space:
mode:
authorBenjamin Paassen <bpaassen@techfak.uni-bielefeld.de>2014-11-14 17:41:03 +0100
committerBenjamin Paassen <bpaassen@techfak.uni-bielefeld.de>2014-11-14 17:41:03 +0100
commit165cf9a5c6ab03dab64d5eb5a5577f8c216bb832 (patch)
tree8ab8fd9baa491d92d9f21f2e9257450adab4f75f /src/core/utils/CodeTokenizer.hpp
parente3cf0a9d726c9d76f4938590691336fbf2e9f6d5 (diff)
implemented tokenizer test and started implementing CodeTokenizer under supervision of Maester Stoeckel.
Diffstat (limited to 'src/core/utils/CodeTokenizer.hpp')
-rw-r--r--src/core/utils/CodeTokenizer.hpp83
1 files changed, 83 insertions, 0 deletions
diff --git a/src/core/utils/CodeTokenizer.hpp b/src/core/utils/CodeTokenizer.hpp
new file mode 100644
index 0000000..f26a74c
--- /dev/null
+++ b/src/core/utils/CodeTokenizer.hpp
@@ -0,0 +1,83 @@
+/*
+ Ousía
+ Copyright (C) 2014 Benjamin Paaßen, Andreas Stöckel
+
+ This program is free software: you can redistribute it and/or modify
+ it under the terms of the GNU General Public License as published by
+ the Free Software Foundation, either version 3 of the License, or
+ (at your option) any later version.
+
+ This program 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 General Public License for more details.
+
+ You should have received a copy of the GNU General Public License
+ along with this program. If not, see <http://www.gnu.org/licenses/>.
+*/
+
+#ifndef _OUSIA_UTILS_CODE_TOKENIZER_HPP_
+#define _OUSIA_UTILS_CODE_TOKENIZER_HPP_
+
+#include <map>
+#include <sstream>
+
+#include "BufferedCharReader.hpp"
+#include "Tokenizer.hpp"
+
+namespace ousia {
+namespace utils {
+
+enum class CodeTokenMode {
+ STRING_START_END,
+ LINE_COMMENT,
+ BLOCK_COMMENT_START,
+ BLOCK_COMMENT_END,
+ LINEBREAK,
+ ESCAPE,
+ NONE
+};
+
+struct CodeTokenDescriptor {
+ CodeTokenMode mode;
+ int id;
+
+ CodeTokenDescriptor(CodeTokenMode mode, int id) : mode(mode), id(id) {}
+};
+
+
+enum class CodeTokenizerState {
+ NORMAL,
+ IN_BLOCK_COMMENT,
+ IN_LINE_COMMENT,
+ IN_STRING
+};
+
+class CodeTokenizer : public Tokenizer {
+private:
+ std::map<int, CodeTokenDescriptor> descriptors;
+ CodeTokenizerState state;
+ std::stringstream buf;
+ Token startToken;
+ int returnTokenId;
+ bool escaped = false;
+
+ Token constructToken(const Token& t);
+ void buffer(const Token& t);
+
+protected:
+ bool doPrepare(const Token &t, std::deque<Token> &peeked) override;
+
+public:
+ bool ignoreComments = false;
+
+ CodeTokenizer(BufferedCharReader &input, const TokenTreeNode &root,
+ std::map<int, CodeTokenDescriptor> descriptors)
+ : Tokenizer(input, root), descriptors(descriptors)
+ {
+ }
+};
+}
+}
+
+#endif