113 lines
3.7 KiB
C++
113 lines
3.7 KiB
C++
#include "lex_foundation.h"
|
|
#include "token_impls.h"
|
|
#include <QTextStream>
|
|
#include <tuple>
|
|
|
|
using namespace Lex;
|
|
|
|
TokenReader::TokenReader(QList<TokenDef *> sequence, const QFileInfo &target)
|
|
: line_number(0), target_info(target), bin_source(nullptr), content_stack(""), line_source(nullptr), analysis_sequences(sequence) {
|
|
this->bin_source = new QFile(target.absoluteFilePath());
|
|
if (!this->bin_source->open(QIODevice::ReadOnly | QIODevice::Text))
|
|
throw new WsBaseException("指定源文件无法打开！");
|
|
|
|
this->line_source = new QTextStream(this->bin_source);
|
|
}
|
|
|
|
TokenReader::TokenReader(QList<TokenDef *> sequence, const QFileInfo &target, const QString &content)
|
|
: line_number(0), target_info(target), bin_source(nullptr), content_stack(content), line_source(nullptr), analysis_sequences(sequence) {
|
|
this->line_source = new QTextStream(&content_stack, QIODevice::ReadOnly);
|
|
}
|
|
|
|
TokenReader::~TokenReader() {
|
|
for (auto &ins : tokens_buffer)
|
|
delete ins;
|
|
for (auto &ins : analysis_sequences)
|
|
delete ins;
|
|
|
|
delete line_source;
|
|
delete bin_source;
|
|
}
|
|
|
|
Token *TokenReader::read() {
|
|
if (this->tokens_buffer.count() < 1)
|
|
this->tokens_buffer.append(get_tokens_of_line(this->target_info, *this->line_source));
|
|
|
|
if (this->tokens_buffer.count() < 1)
|
|
return nullptr;
|
|
|
|
return this->tokens_buffer.takeAt(0);
|
|
}
|
|
|
|
void TokenReader::tokenRemove(uint index) {
|
|
if (this->tokens_buffer.count() <= index)
|
|
throw new WsBaseException("索引超出当前序列最大容量");
|
|
|
|
delete this->tokens_buffer.takeAt(index);
|
|
}
|
|
|
|
Token *TokenReader::tokenPeak(uint index) {
|
|
if (this->tokens_buffer.count() <= index)
|
|
this->tokens_buffer.append(get_tokens_of_line(this->target_info, *this->line_source));
|
|
|
|
if (this->tokens_buffer.count() <= index)
|
|
throw new WsBaseException("目标获取数量超出最大能力");
|
|
|
|
return this->tokens_buffer.at(index);
|
|
}
|
|
|
|
QList<Token *> TokenReader::get_tokens_of_line(const QFileInfo &associate, QTextStream &lines_source) {
|
|
const QString line = line_source->readLine();
|
|
auto split_seqs = line.split(QRegExp("\\s\\t"), QString::SplitBehavior::SkipEmptyParts);
|
|
split_seqs.append("\n");
|
|
auto batch_column = 0;
|
|
|
|
// 转换单行的内容为词组列表
|
|
QList<WordBase *> word_source;
|
|
for (auto &it : split_seqs) {
|
|
auto inst = new TokenWord(associate.canonicalFilePath());
|
|
word_source.append(inst);
|
|
|
|
auto start_index = line.indexOf(it, batch_column);
|
|
inst->reset(it, line_number, start_index);
|
|
batch_column = start_index + it.length();
|
|
}
|
|
|
|
// 对单行的所有的内容进行解析
|
|
QList<Token *> token_results;
|
|
for (auto idx = 0; idx < word_source.size(); ++idx) {
|
|
// 对单个词语进行解析
|
|
auto inst = word_source[idx];
|
|
|
|
auto retv = get_token(*inst);
|
|
token_results.append(retv);
|
|
|
|
// 如果存在未解析的剩余的内容
|
|
if (retv->remains())
|
|
word_source.insert(idx + 1, retv->remains());
|
|
}
|
|
|
|
// 删除所有的词元列表
|
|
for (auto &token_ins : word_source)
|
|
delete token_ins;
|
|
|
|
line_number++;
|
|
return token_results;
|
|
}
|
|
|
|
Token *TokenReader::get_token(const WordBase &word) {
|
|
for (auto &it : analysis_sequences) {
|
|
auto lex_result = it->analysis(word);
|
|
if (lex_result)
|
|
return lex_result;
|
|
}
|
|
|
|
throw new WsBaseException(QString("指定的词语无法解析：%1 <row:%2,col:%3>").arg(word.content()).arg(word.row()).arg(word.column()));
|
|
}
|
|
|
|
WsBaseException::WsBaseException(const QString &msg) { this->msg_store = msg; }
|
|
|
|
QString WsBaseException::message() const { return msg_store; }
|
|
|
|
const char *WsBaseException::what() const { return msg_store.toLocal8Bit(); }
|