Lexesis/templates/c++/lexer.cpp

102 lines
2.8 KiB
C++

/*
* This software is provided 'as-is', without any express or implied warranty. In no event will the authors be held liable for any damages arising from the use of this software.
*
* Permission is granted to anyone to use this software for any purpose, including commercial applications, and to alter it and redistribute it freely, subject to the following restrictions:
*
* 1. The origin of this software must not be misrepresented; you must not claim that you wrote the original software. If you use this software in a product, an acknowledgment in the product documentation would be appreciated but is not required.
*
* 2. Altered source versions must be plainly marked as such, and must not be misrepresented as being the original software.
*
* 3. This notice may not be removed or altered from any source distribution.
*/
#include "{{name}}.h"
#include <sstream>
#include <iostream>
namespace { //The automaton data
typedef std::size_t State;
State REJECT = {{reject_state}};
unsigned char TRANS_IDX[256] = { {{#trans_idx}}{{trans}}, {{/trans_idx}} };
State TABLE[{{num_states}} - 1][{{num_transitions_per_state}}] = { {{#table}}
{ {{#row}} {{state}}, {{/row}} },
{{/table}} };
{{name}}::TokenType TOKENS[{{num_states}}] = { {{#tokens}} {{name}}::{{token}}, {{/tokens}} };
}
{{name}}::{{name}}(std::istream& in) : m_offset(0), m_input(in) {
}
{{name}}::~{{name}}() {
}
{{name}}::Token {{name}}::nextToken() {
TokenType type = ignore;
std::string token;
while (type == ignore) {
State state = 0;
std::size_t match_length = 0;
token = "";
while (!m_input.eof() && state != REJECT) {
char c = m_input.peek();
if (m_input.eof())
break;
token += c;
state = TABLE[state][TRANS_IDX[(unsigned char)c]];
if (TOKENS[state])
{
match_length = token.length();
type = TOKENS[state];
}
m_input.get();
++m_offset;
}
std::size_t sdiff = token.length() - match_length;
for (std::size_t i = 0; i < sdiff; i++)
{
m_input.putback(token[token.length() - i - 1]);
}
m_offset -= sdiff;
if (!type || !match_length) {
if (m_input.eof())
throw NoMoreTokens();
throw NoMatch();
}
token = token.substr(0, match_length);
}
Token t;
t.type = type;
t.content = token;
return t;
}
void {{name}}::skip(std::size_t n) {
for (size_t i = 0; i < n; i++) {
m_input.get();
++m_offset;
}
}
char {{name}}::peek() {
if (m_input.eof())
throw NoMoreTokens();
return m_input.peek();
}
std::size_t {{name}}::getByteOffset() {
return m_offset;
}