Use*_*er1 246 c++ csv parsing text
我需要在C++中加载和使用CSV文件数据.此时它实际上只是一个以逗号分隔的解析器(即不用担心转义新行和逗号).主要需求是逐行解析器,每次调用方法时都会返回下一行的向量.
我发现这篇文章很有前途:http: //www.boost.org/doc/libs/1_35_0/libs/spirit/example/fundamental/list_parser.cpp
我从未使用过Boost的精神,但我愿意尝试.但只有在没有更直接的解决方案的情况下,我才会忽视.
Mar*_*ork 276
如果你不关心转义逗号和换行符,
你不能在引号中嵌入逗号和换行符(如果你不能逃避那么......)
那么它只有大约三行代码(OK 14 - >但它的只读15整个文件).
std::vector<std::string> getNextLineAndSplitIntoTokens(std::istream& str)
{
std::vector<std::string> result;
std::string line;
std::getline(str,line);
std::stringstream lineStream(line);
std::string cell;
while(std::getline(lineStream,cell, ','))
{
result.push_back(cell);
}
// This checks for a trailing comma with no data after it.
if (!lineStream && cell.empty())
{
// If there was a trailing comma then add an empty element.
result.push_back("");
}
return result;
}
Run Code Online (Sandbox Code Playgroud)
我只想创建一个代表一行的类.
然后流入该对象:
#include <iterator>
#include <iostream>
#include <fstream>
#include <sstream>
#include <vector>
#include <string>
class CSVRow
{
public:
std::string const& operator[](std::size_t index) const
{
return m_data[index];
}
std::size_t size() const
{
return m_data.size();
}
void readNextRow(std::istream& str)
{
std::string line;
std::getline(str, line);
std::stringstream lineStream(line);
std::string cell;
m_data.clear();
while(std::getline(lineStream, cell, ','))
{
m_data.push_back(cell);
}
// This checks for a trailing comma with no data after it.
if (!lineStream && cell.empty())
{
// If there was a trailing comma then add an empty element.
m_data.push_back("");
}
}
private:
std::vector<std::string> m_data;
};
std::istream& operator>>(std::istream& str, CSVRow& data)
{
data.readNextRow(str);
return str;
}
int main()
{
std::ifstream file("plop.csv");
CSVRow row;
while(file >> row)
{
std::cout << "4th Element(" << row[3] << ")\n";
}
}
Run Code Online (Sandbox Code Playgroud)
但是通过一些工作,我们可以在技术上创建一个迭代器:
class CSVIterator
{
public:
typedef std::input_iterator_tag iterator_category;
typedef CSVRow value_type;
typedef std::size_t difference_type;
typedef CSVRow* pointer;
typedef CSVRow& reference;
CSVIterator(std::istream& str) :m_str(str.good()?&str:NULL) { ++(*this); }
CSVIterator() :m_str(NULL) {}
// Pre Increment
CSVIterator& operator++() {if (m_str) { if (!((*m_str) >> m_row)){m_str = NULL;}}return *this;}
// Post increment
CSVIterator operator++(int) {CSVIterator tmp(*this);++(*this);return tmp;}
CSVRow const& operator*() const {return m_row;}
CSVRow const* operator->() const {return &m_row;}
bool operator==(CSVIterator const& rhs) {return ((this == &rhs) || ((this->m_str == NULL) && (rhs.m_str == NULL)));}
bool operator!=(CSVIterator const& rhs) {return !((*this) == rhs);}
private:
std::istream* m_str;
CSVRow m_row;
};
int main()
{
std::ifstream file("plop.csv");
for(CSVIterator loop(file); loop != CSVIterator(); ++loop)
{
std::cout << "4th Element(" << (*loop)[3] << ")\n";
}
}
Run Code Online (Sandbox Code Playgroud)
dtw*_*dtw 46
使用Boost Tokenizer的解决方案:
std::vector<std::string> vec;
using namespace boost;
tokenizer<escaped_list_separator<char> > tk(
line, escaped_list_separator<char>('\\', ',', '\"'));
for (tokenizer<escaped_list_separator<char> >::iterator i(tk.begin());
i!=tk.end();++i)
{
vec.push_back(*i);
}
Run Code Online (Sandbox Code Playgroud)
sas*_*nin 42
我的版本除了标准的C++ 11库之外没有使用任何东西.它很好地处理Excel CSV报价:
spam eggs,"foo,bar","""fizz buzz"""
1.23,4.567,-8.00E+09
Run Code Online (Sandbox Code Playgroud)
代码被编写为有限状态机,并且一次消耗一个字符.我认为这更容易推理.
#include <istream>
#include <string>
#include <vector>
enum class CSVState {
UnquotedField,
QuotedField,
QuotedQuote
};
std::vector<std::string> readCSVRow(const std::string &row) {
CSVState state = CSVState::UnquotedField;
std::vector<std::string> fields {""};
size_t i = 0; // index of the current field
for (char c : row) {
switch (state) {
case CSVState::UnquotedField:
switch (c) {
case ',': // end of field
fields.push_back(""); i++;
break;
case '"': state = CSVState::QuotedField;
break;
default: fields[i].push_back(c);
break; }
break;
case CSVState::QuotedField:
switch (c) {
case '"': state = CSVState::QuotedQuote;
break;
default: fields[i].push_back(c);
break; }
break;
case CSVState::QuotedQuote:
switch (c) {
case ',': // , after closing quote
fields.push_back(""); i++;
state = CSVState::UnquotedField;
break;
case '"': // "" -> "
fields[i].push_back('"');
state = CSVState::QuotedField;
break;
default: // end of quote
state = CSVState::UnquotedField;
break; }
break;
}
}
return fields;
}
/// Read CSV file, Excel dialect. Accept "quoted fields ""with quotes"""
std::vector<std::vector<std::string>> readCSV(std::istream &in) {
std::vector<std::vector<std::string>> table;
std::string row;
while (!in.eof()) {
std::getline(in, row);
if (in.bad() || in.fail()) {
break;
}
auto fields = readCSVRow(row);
table.push_back(fields);
}
return table;
}
Run Code Online (Sandbox Code Playgroud)
小智 31
在C++字符串工具箱库(StrTk)有一个令牌网类,允许你加载无论是从数据的文本文件,字符串或字符缓冲区,并在行列时尚解析/处理它们.
您可以指定行分隔符和列分隔符,也可以仅使用默认值.
void foo()
{
std::string data = "1,2,3,4,5\n"
"0,2,4,6,8\n"
"1,3,5,7,9\n";
strtk::token_grid grid(data,data.size(),",");
for(std::size_t i = 0; i < grid.row_count(); ++i)
{
strtk::token_grid::row_type r = grid.row(i);
for(std::size_t j = 0; j < r.size(); ++j)
{
std::cout << r.get<int>(j) << "\t";
}
std::cout << std::endl;
}
std::cout << std::endl;
}
Run Code Online (Sandbox Code Playgroud)
更多例子可以在这里找到
Joe*_*man 29
使用Spirit解析CSV并不过分.Spirit非常适合微解析任务.例如,使用Spirit 2.1,它就像:
bool r = phrase_parse(first, last,
// Begin grammar
(
double_ % ','
)
,
// End grammar
space, v);
Run Code Online (Sandbox Code Playgroud)
矢量v充满了这些值.在 Boost 1.41刚刚发布的新Spirit 2.1文档中有一系列的教程涉及到这一点.
教程从简单到复杂.CSV解析器位于中间的某个位置,并涉及使用Spirit的各种技术.生成的代码与手写代码一样紧密.看看生成的汇编程序!
ste*_*anB 29
您可以使用带有escaped_list_separator的Boost Tokenizer.
escaped_list_separator解析csv的超集.升压::标记生成器
这只使用Boost tokenizer头文件,没有链接到所需的boost库.
下面是一个示例(有关详细信息,请参阅使用C++中的Boost Tokenizer解析CSV文件Boost::tokenizer):
#include <iostream> // cout, endl
#include <fstream> // fstream
#include <vector>
#include <string>
#include <algorithm> // copy
#include <iterator> // ostream_operator
#include <boost/tokenizer.hpp>
int main()
{
using namespace std;
using namespace boost;
string data("data.csv");
ifstream in(data.c_str());
if (!in.is_open()) return 1;
typedef tokenizer< escaped_list_separator<char> > Tokenizer;
vector< string > vec;
string line;
while (getline(in,line))
{
Tokenizer tok(line);
vec.assign(tok.begin(),tok.end());
// vector now contains strings from one row, output to cout here
copy(vec.begin(), vec.end(), ostream_iterator<string>(cout, "|"));
cout << "\n----------------------" << endl;
}
}
Run Code Online (Sandbox Code Playgroud)
小智 17
如果你不要在意正确解析CSV,因为它的工作原理一个字符在同一时间,这将做...相对缓慢.
void ParseCSV(const string& csvSource, vector<vector<string> >& lines)
{
bool inQuote(false);
bool newLine(false);
string field;
lines.clear();
vector<string> line;
string::const_iterator aChar = csvSource.begin();
while (aChar != csvSource.end())
{
switch (*aChar)
{
case '"':
newLine = false;
inQuote = !inQuote;
break;
case ',':
newLine = false;
if (inQuote == true)
{
field += *aChar;
}
else
{
line.push_back(field);
field.clear();
}
break;
case '\n':
case '\r':
if (inQuote == true)
{
field += *aChar;
}
else
{
if (newLine == false)
{
line.push_back(field);
lines.push_back(line);
field.clear();
line.clear();
newLine = true;
}
}
break;
default:
newLine = false;
field.push_back(*aChar);
break;
}
aChar++;
}
if (field.size())
line.push_back(field);
if (line.size())
lines.push_back(line);
}
Run Code Online (Sandbox Code Playgroud)
Rol*_*sen 14
使用Boost Tokenizer escaped_list_separator获取CSV文件时,应该注意以下事项:
wiki指定的CSV格式声明数据字段可以包含引号中的分隔符(支持):
1997年,福特,E350,"超级豪华卡车"
wiki指定的CSV格式声明单引号应使用双引号处理(escaped_list_separator将删除所有引号字符):
1997年,福特,E350,"超级""豪华""卡车"
CSV格式未指定应删除任何反斜杠字符(escaped_list_separator将删除所有转义字符).
可能的解决方法是修复boost escaped_list_separator的默认行为:
这种解决方法具有副作用,即由双引号表示的空数据字段将转换为单引号令牌.迭代令牌时,必须检查令牌是否是单引号,并将其视为空字符串.
虽然引号内没有换行符,但不是很漂亮但它有效.
小智 7
您可能希望查看我的FOSS项目CSVfix(更新链接),它是一个用C++编写的CSV流编辑器.CSV解析器不是奖品,但是在没有编写任何代码的情况下,工作和整个软件包可以满足您的需求.
见alib/SRC/a_csv.cpp用于CSV解析器和csvlib/SRC/csved_ioman.cpp(IOManager::ReadCSV用于使用示例).
由于所有CSV问题似乎都被重定向到这里,我想我会在这里发布我的答案.这个答案没有直接解决提问者的问题.我希望能够读取已知为CSV格式的流,并且每个字段的类型也已知.当然,下面的方法可以用于将每个字段视为字符串类型.
作为我希望如何使用CSV输入流的示例,请考虑以下输入(取自维基百科的CSV页面):
const char input[] =
"Year,Make,Model,Description,Price\n"
"1997,Ford,E350,\"ac, abs, moon\",3000.00\n"
"1999,Chevy,\"Venture \"\"Extended Edition\"\"\",\"\",4900.00\n"
"1999,Chevy,\"Venture \"\"Extended Edition, Very Large\"\"\",\"\",5000.00\n"
"1996,Jeep,Grand Cherokee,\"MUST SELL!\n\
air, moon roof, loaded\",4799.00\n"
;
Run Code Online (Sandbox Code Playgroud)
然后,我希望能够读取这样的数据:
std::istringstream ss(input);
std::string title[5];
int year;
std::string make, model, desc;
float price;
csv_istream(ss)
>> title[0] >> title[1] >> title[2] >> title[3] >> title[4];
while (csv_istream(ss)
>> year >> make >> model >> desc >> price) {
//...do something with the record...
}
Run Code Online (Sandbox Code Playgroud)
这是我最终解决的问题.
struct csv_istream {
std::istream &is_;
csv_istream (std::istream &is) : is_(is) {}
void scan_ws () const {
while (is_.good()) {
int c = is_.peek();
if (c != ' ' && c != '\t') break;
is_.get();
}
}
void scan (std::string *s = 0) const {
std::string ws;
int c = is_.get();
if (is_.good()) {
do {
if (c == ',' || c == '\n') break;
if (s) {
ws += c;
if (c != ' ' && c != '\t') {
*s += ws;
ws.clear();
}
}
c = is_.get();
} while (is_.good());
if (is_.eof()) is_.clear();
}
}
template <typename T, bool> struct set_value {
void operator () (std::string in, T &v) const {
std::istringstream(in) >> v;
}
};
template <typename T> struct set_value<T, true> {
template <bool SIGNED> void convert (std::string in, T &v) const {
if (SIGNED) v = ::strtoll(in.c_str(), 0, 0);
else v = ::strtoull(in.c_str(), 0, 0);
}
void operator () (std::string in, T &v) const {
convert<is_signed_int<T>::val>(in, v);
}
};
template <typename T> const csv_istream & operator >> (T &v) const {
std::string tmp;
scan(&tmp);
set_value<T, is_int<T>::val>()(tmp, v);
return *this;
}
const csv_istream & operator >> (std::string &v) const {
v.clear();
scan_ws();
if (is_.peek() != '"') scan(&v);
else {
std::string tmp;
is_.get();
std::getline(is_, tmp, '"');
while (is_.peek() == '"') {
v += tmp;
v += is_.get();
std::getline(is_, tmp, '"');
}
v += tmp;
scan();
}
return *this;
}
template <typename T>
const csv_istream & operator >> (T &(*manip)(T &)) const {
is_ >> manip;
return *this;
}
operator bool () const { return !is_.fail(); }
};
Run Code Online (Sandbox Code Playgroud)
使用C++ 11中新的整数特征模板可以简化的以下助手:
template <typename T> struct is_signed_int { enum { val = false }; };
template <> struct is_signed_int<short> { enum { val = true}; };
template <> struct is_signed_int<int> { enum { val = true}; };
template <> struct is_signed_int<long> { enum { val = true}; };
template <> struct is_signed_int<long long> { enum { val = true}; };
template <typename T> struct is_unsigned_int { enum { val = false }; };
template <> struct is_unsigned_int<unsigned short> { enum { val = true}; };
template <> struct is_unsigned_int<unsigned int> { enum { val = true}; };
template <> struct is_unsigned_int<unsigned long> { enum { val = true}; };
template <> struct is_unsigned_int<unsigned long long> { enum { val = true}; };
template <typename T> struct is_int {
enum { val = (is_signed_int<T>::val || is_unsigned_int<T>::val) };
};
Run Code Online (Sandbox Code Playgroud)
您可以使用仅标头的Csv::Parser库。
std::string_view它支持在编译时读取 CSV 数据。这是 Unicode CSV 解析器的另一个实现(与 wchar_t 一起使用)。我写了其中的一部分,乔纳森·莱夫勒写了其余的部分。
注意:此解析器旨在尽可能地复制 Excel 的行为,特别是在导入损坏或格式错误的CSV 文件时。
这是最初的问题 - Parsing CSV file with multiline fields and escaped doublequotes
这是 SSCCE(简短、自包含、正确示例)的代码。
#include <stdbool.h>
#include <wchar.h>
#include <wctype.h>
extern const wchar_t *nextCsvField(const wchar_t *p, wchar_t sep, bool *newline);
// Returns a pointer to the start of the next field,
// or zero if this is the last field in the CSV
// p is the start position of the field
// sep is the separator used, i.e. comma or semicolon
// newline says whether the field ends with a newline or with a comma
const wchar_t *nextCsvField(const wchar_t *p, wchar_t sep, bool *newline)
{
// Parse quoted sequences
if ('"' == p[0]) {
p++;
while (1) {
// Find next double-quote
p = wcschr(p, L'"');
// If we don't find it or it's the last symbol
// then this is the last field
if (!p || !p[1])
return 0;
// Check for "", it is an escaped double-quote
if (p[1] != '"')
break;
// Skip the escaped double-quote
p += 2;
}
}
// Find next newline or comma.
wchar_t newline_or_sep[4] = L"\n\r ";
newline_or_sep[2] = sep;
p = wcspbrk(p, newline_or_sep);
// If no newline or separator, this is the last field.
if (!p)
return 0;
// Check if we had newline.
*newline = (p[0] == '\r' || p[0] == '\n');
// Handle "\r\n", otherwise just increment
if (p[0] == '\r' && p[1] == '\n')
p += 2;
else
p++;
return p;
}
static wchar_t *csvFieldData(const wchar_t *fld_s, const wchar_t *fld_e, wchar_t *buffer, size_t buflen)
{
wchar_t *dst = buffer;
wchar_t *end = buffer + buflen - 1;
const wchar_t *src = fld_s;
if (*src == L'"')
{
const wchar_t *p = src + 1;
while (p < fld_e && dst < end)
{
if (p[0] == L'"' && p+1 < fld_s && p[1] == L'"')
{
*dst++ = p[0];
p += 2;
}
else if (p[0] == L'"')
{
p++;
break;
}
else
*dst++ = *p++;
}
src = p;
}
while (src < fld_e && dst < end)
*dst++ = *src++;
if (dst >= end)
return 0;
*dst = L'\0';
return(buffer);
}
static void dissect(const wchar_t *line)
{
const wchar_t *start = line;
const wchar_t *next;
bool eol;
wprintf(L"Input %3zd: [%.*ls]\n", wcslen(line), wcslen(line)-1, line);
while ((next = nextCsvField(start, L',', &eol)) != 0)
{
wchar_t buffer[1024];
wprintf(L"Raw Field: [%.*ls] (eol = %d)\n", (next - start - eol), start, eol);
if (csvFieldData(start, next-1, buffer, sizeof(buffer)/sizeof(buffer[0])) != 0)
wprintf(L"Field %3zd: [%ls]\n", wcslen(buffer), buffer);
start = next;
}
}
static const wchar_t multiline[] =
L"First field of first row,\"This field is multiline\n"
"\n"
"but that's OK because it's enclosed in double quotes, and this\n"
"is an escaped \"\" double quote\" but this one \"\" is not\n"
" \"This is second field of second row, but it is not multiline\n"
" because it doesn't start \n"
" with an immediate double quote\"\n"
;
int main(void)
{
wchar_t line[1024];
while (fgetws(line, sizeof(line)/sizeof(line[0]), stdin))
dissect(line);
dissect(multiline);
return 0;
}
Run Code Online (Sandbox Code Playgroud)
我编写了仅标头的C ++ 11 CSV解析器。它经过了良好的测试,速度很快,支持整个CSV规范(带引号的字段,引号中的定界符/终止符,引号转义等),并且可以配置为解决不符合该规范的CSV。
通过流畅的界面进行配置:
// constructor accepts any input stream
CsvParser parser = CsvParser(std::cin)
.delimiter(';') // delimited by ; instead of ,
.quote('\'') // quoted fields use ' instead of "
.terminator('\0'); // terminated by \0 instead of by \r\n, \n, or \r
Run Code Online (Sandbox Code Playgroud)
解析只是基于for循环的范围:
#include <iostream>
#include "../parser.hpp"
using namespace aria::csv;
int main() {
std::ifstream f("some_file.csv");
CsvParser parser(f);
for (auto& row : parser) {
for (auto& field : row) {
std::cout << field << " | ";
}
std::cout << std::endl;
}
}
Run Code Online (Sandbox Code Playgroud)
可在此处找到另一个CSV I/O库:
http://code.google.com/p/fast-cpp-csv-parser/
#include "csv.h"
int main(){
io::CSVReader<3> in("ram.csv");
in.read_header(io::ignore_extra_column, "vendor", "size", "speed");
std::string vendor; int size; double speed;
while(in.read_row(vendor, size, speed)){
// do stuff with the data
}
}
Run Code Online (Sandbox Code Playgroud)
另一种解决方案类似于Loki Astari的答案,在C++ 11中.这里std::tuple的行是给定类型的.代码扫描一行,然后扫描直到每个分隔符,然后将值直接转换并转储到元组中(带有一些模板代码).
for (auto row : csv<std::string, int, float>(file, ',')) {
std::cout << "first col: " << std::get<0>(row) << std::endl;
}
Run Code Online (Sandbox Code Playgroud)
Advanges:
std::tuple<t1, ...>via operator>>.少了什么东西:
主要代码:
#include <iterator>
#include <sstream>
#include <string>
namespace csvtools {
/// Read the last element of the tuple without calling recursively
template <std::size_t idx, class... fields>
typename std::enable_if<idx >= std::tuple_size<std::tuple<fields...>>::value - 1>::type
read_tuple(std::istream &in, std::tuple<fields...> &out, const char delimiter) {
std::string cell;
std::getline(in, cell, delimiter);
std::stringstream cell_stream(cell);
cell_stream >> std::get<idx>(out);
}
/// Read the @p idx-th element of the tuple and then calls itself with @p idx + 1 to
/// read the next element of the tuple. Automatically falls in the previous case when
/// reaches the last element of the tuple thanks to enable_if
template <std::size_t idx, class... fields>
typename std::enable_if<idx < std::tuple_size<std::tuple<fields...>>::value - 1>::type
read_tuple(std::istream &in, std::tuple<fields...> &out, const char delimiter) {
std::string cell;
std::getline(in, cell, delimiter);
std::stringstream cell_stream(cell);
cell_stream >> std::get<idx>(out);
read_tuple<idx + 1, fields...>(in, out, delimiter);
}
}
/// Iterable csv wrapper around a stream. @p fields the list of types that form up a row.
template <class... fields>
class csv {
std::istream &_in;
const char _delim;
public:
typedef std::tuple<fields...> value_type;
class iterator;
/// Construct from a stream.
inline csv(std::istream &in, const char delim) : _in(in), _delim(delim) {}
/// Status of the underlying stream
/// @{
inline bool good() const {
return _in.good();
}
inline const std::istream &underlying_stream() const {
return _in;
}
/// @}
inline iterator begin();
inline iterator end();
private:
/// Reads a line into a stringstream, and then reads the line into a tuple, that is returned
inline value_type read_row() {
std::string line;
std::getline(_in, line);
std::stringstream line_stream(line);
std::tuple<fields...> retval;
csvtools::read_tuple<0, fields...>(line_stream, retval, _delim);
return retval;
}
};
/// Iterator; just calls recursively @ref csv::read_row and stores the result.
template <class... fields>
class csv<fields...>::iterator {
csv::value_type _row;
csv *_parent;
public:
typedef std::input_iterator_tag iterator_category;
typedef csv::value_type value_type;
typedef std::size_t difference_type;
typedef csv::value_type * pointer;
typedef csv::value_type & reference;
/// Construct an empty/end iterator
inline iterator() : _parent(nullptr) {}
/// Construct an iterator at the beginning of the @p parent csv object.
inline iterator(csv &parent) : _parent(parent.good() ? &parent : nullptr) {
++(*this);
}
/// Read one row, if possible. Set to end if parent is not good anymore.
inline iterator &operator++() {
if (_parent != nullptr) {
_row = _parent->read_row();
if (!_parent->good()) {
_parent = nullptr;
}
}
return *this;
}
inline iterator operator++(int) {
iterator copy = *this;
++(*this);
return copy;
}
inline csv::value_type const &operator*() const {
return _row;
}
inline csv::value_type const *operator->() const {
return &_row;
}
bool operator==(iterator const &other) {
return (this == &other) or (_parent == nullptr and other._parent == nullptr);
}
bool operator!=(iterator const &other) {
return not (*this == other);
}
};
template <class... fields>
typename csv<fields...>::iterator csv<fields...>::begin() {
return iterator(*this);
}
template <class... fields>
typename csv<fields...>::iterator csv<fields...>::end() {
return iterator();
}
Run Code Online (Sandbox Code Playgroud)
我在GitHub上放了一个小小的工作示例; 我一直用它来解析一些数值数据,并且它有用.