Initial commit

* CodepointIterator is a simple C++ iterator class which iterates through unicode codepoints in a UTF8-encoded string
* It is derived from std::iterator and implements the std::bidirectional_iterator_tag
* Dereferencing an instance of the class provides the codepoint as char32_t
* Tests require Google Test and use UTF8-samples from http://www.columbia.edu/~fdc/utf8/

1 files changed, 49 insertions, 0 deletions

diff --git a/src/codepoint_iterator.h b/src/codepoint_iterator.h
new file mode 100644
index 0000000..938f53d
--- /dev/null
+++ b/src/codepoint_iterator.h
@@ -0,0 +1,49 @@
+#ifndef CODEPOINT_ITERATOR_H_
+#define CODEPOINT_ITERATOR_H_
+
+#include <iterator>
+#include <string>
+#include <exception>
+
+namespace UTF8 {
+
+class CodepointIterator : public std::iterator<std::bidirectional_iterator_tag,
+                                               char32_t,
+                                               std::string::difference_type,
+                                               const char32_t*,
+                                               const char32_t&> {
+	public:
+		CodepointIterator(std::string::const_iterator);
+		CodepointIterator(const CodepointIterator&);
+
+		CodepointIterator& operator=(const CodepointIterator&);
+
+		bool operator==(const CodepointIterator&) const;
+		bool operator==(const std::string::const_iterator&) const;
+
+		bool operator!=(const CodepointIterator&) const;
+		bool operator!=(const std::string::const_iterator&) const;
+
+		char32_t operator*();
+
+		CodepointIterator& operator++();
+		CodepointIterator& operator--();
+
+		CodepointIterator operator++(int);
+		CodepointIterator operator--(int);
+
+	private:
+		std::string::const_iterator iterator_;
+		bool dereferenced_;
+		char32_t codepoint_;
+};
+
+class codepoint_invalid: public std::exception {
+	virtual const char* what() const throw() {
+		return "codepoint_invalid";
+	}
+};
+
+}
+
+#endif  // CODEPOINT_ITERATOR_H_