tqchen a16289b204 Squashed 'subtree/rabit/' changes from fa99857..e81a11d
e81a11d Merge pull request #25 from daiyl0320/master
35c3b37 add retry mechanism to ConnectTracker and modify Listen backlog to 128 in rabit_traker.py
c71ed6f try deply doxygen
62e5647 try deply doxygen
732f1c6 try
2fa6e02 ok
0537665 minor
7b59dcb minor
5934950 new doc
f538187 ok
44b6049 new doc
387339b add more
9d4397a chg
2879a48 chg
30e3110 ok
9ff0301 add link translation
6b629c2 k
32e1955 ok
8f4839d fix
93137b2 ok
7eeeb79 reload recommonmark
a8f00cc minor
19b0f01 ok
dd01184 minor
c1cdc19 minor
fcf0f43 try rst
cbc21ae try
62ddfa7 tiny
aefc05c final change
2aee9b4 minor
fe4e7c2 ok
8001983 change to subtitle
5ca33e4 ok
88f7d24 update guide
29d43ab add code
fe8bb3b minor hack for readthedocs
229c71d Merge branch 'master' of ssh://github.com/dmlc/rabit
7424218 ok
d1d45bb Update README.md
1e8813f Update README.md
1ccc990 Update README.md
0323e06 remove readme
679a835 remove theme
7ea5b7c remove numpydoc to napoleon
b73e2be Merge branch 'master' of ssh://github.com/dmlc/rabit
1742283 ok
1838e25 Update python-requirements.txt
bc4e957 ok
fba6fc2 ok
0251101 ok
d50b905 ok
d4f2509 ok
cdf401a ok
fef0ef2 new doc
cef360d ok
c125d2a ok
270a49e add requirments
744f901 get the basic doc
1cb5cad Merge branch 'master' of ssh://github.com/dmlc/rabit
8cc07ba minor
d74f126 Update .travis.yml
52b3dcd Update .travis.yml
099581b Update .travis.yml
1258046 Update .travis.yml
7addac9 Update Makefile
0ea7adf Update .travis.yml
f858856 Update travis_script.sh
d8eac4a Update README.md
3cc49ad lint and travis
ceedf4e fix
fd8920c fix win32
8bbed35 modify
9520b90 Merge pull request #14 from dmlc/hjk41
df14bb1 fix type
f441dc7 replace tab with blankspace
2467942 remove unnecessary include
181ef47 defined long long and ulonglong
1582180 use int32_t to define int and int64_t to define long. in VC long is 32bit
e0b7da0 fix

git-subtree-dir: subtree/rabit
git-subtree-split: e81a11dd7ee3cff87a38a42901315821df018bae
2015-10-20 19:37:47 -07:00

424 lines
12 KiB
C++

/*!
* Copyright (c) 2015 by Contributors
* \file io.h
* \brief defines serializable interface of dmlc
*/
#ifndef DMLC_IO_H_
#define DMLC_IO_H_
#include <cstdio>
#include <string>
#include <vector>
#include <istream>
#include <ostream>
#include <streambuf>
// include uint64_t only to make io standalone
#ifdef _MSC_VER
/*! \brief uint64 */
typedef unsigned __int64 uint64_t;
#else
#include <inttypes.h>
#endif
/*! \brief namespace for dmlc */
namespace dmlc {
/*!
* \brief interface of stream I/O for serialization
*/
class Stream { // NOLINT(*)
public:
/*!
* \brief reads data from a stream
* \param ptr pointer to a memory buffer
* \param size block size
* \return the size of data read
*/
virtual size_t Read(void *ptr, size_t size) = 0;
/*!
* \brief writes data to a stream
* \param ptr pointer to a memory buffer
* \param size block size
*/
virtual void Write(const void *ptr, size_t size) = 0;
/*! \brief virtual destructor */
virtual ~Stream(void) {}
/*!
* \brief generic factory function
* create an stream, the stream will close the underlying files upon deletion
*
* \param uri the uri of the input currently we support
* hdfs://, s3://, and file:// by default file:// will be used
* \param flag can be "w", "r", "a"
* \param allow_null whether NULL can be returned, or directly report error
* \return the created stream, can be NULL when allow_null == true and file do not exist
*/
static Stream *Create(const char *uri,
const char* const flag,
bool allow_null = false);
// helper functions to write/read different data structures
/*!
* \brief writes a vector
* \param vec vector to be written/serialized
*/
template<typename T>
inline void Write(const std::vector<T> &vec);
/*!
* \brief loads a vector
* \param out_vec vector to be loaded/deserialized
* \return whether the load was successful
*/
template<typename T>
inline bool Read(std::vector<T> *out_vec);
/*!
* \brief writes a string
* \param str the string to be written/serialized
*/
inline void Write(const std::string &str);
/*!
* \brief loads a string
* \param out_str string to be loaded/deserialized
* \return whether the load/deserialization was successful
*/
inline bool Read(std::string *out_str);
};
/*! \brief interface of i/o stream that support seek */
class SeekStream: public Stream {
public:
// virtual destructor
virtual ~SeekStream(void) {}
/*! \brief seek to certain position of the file */
virtual void Seek(size_t pos) = 0;
/*! \brief tell the position of the stream */
virtual size_t Tell(void) = 0;
/*!
* \brief generic factory function
* create an SeekStream for read only,
* the stream will close the underlying files upon deletion
* error will be reported and the system will exit when create failed
* \param uri the uri of the input currently we support
* hdfs://, s3://, and file:// by default file:// will be used
* \param allow_null whether NULL can be returned, or directly report error
* \return the created stream, can be NULL when allow_null == true and file do not exist
*/
static SeekStream *CreateForRead(const char *uri,
bool allow_null = false);
};
/*! \brief interface for serializable objects */
class Serializable {
public:
/*!
* \brief load the model from a stream
* \param fi stream where to load the model from
*/
virtual void Load(Stream *fi) = 0;
/*!
* \brief saves the model to a stream
* \param fo stream where to save the model to
*/
virtual void Save(Stream *fo) const = 0;
};
/*!
* \brief input split creates that allows reading
* of records from split of data,
* independent part that covers all the dataset
*
* see InputSplit::Create for definition of record
*/
class InputSplit {
public:
/*! \brief a blob of memory region */
struct Blob {
/*! \brief points to start of the memory region */
void *dptr;
/*! \brief size of the memory region */
size_t size;
};
/*!
* \brief hint the inputsplit how large the chunk size
* it should return when implementing NextChunk
* this is a hint so may not be enforced,
* but InputSplit will try adjust its internal buffer
* size to the hinted value
* \param chunk_size the chunk size
*/
virtual void HintChunkSize(size_t chunk_size) {}
/*! \brief reset the position of InputSplit to beginning */
virtual void BeforeFirst(void) = 0;
/*!
* \brief get the next record, the returning value
* is valid until next call to NextRecord or NextChunk
* caller can modify the memory content of out_rec
*
* For text, out_rec contains a single line
* For recordio, out_rec contains one record content(with header striped)
*
* \param out_rec used to store the result
* \return true if we can successfully get next record
* false if we reached end of split
* \sa InputSplit::Create for definition of record
*/
virtual bool NextRecord(Blob *out_rec) = 0;
/*!
* \brief get a chunk of memory that can contain multiple records,
* the caller needs to parse the content of the resulting chunk,
* for text file, out_chunk can contain data of multiple lines
* for recordio, out_chunk can contain multiple records(including headers)
*
* This function ensures there won't be partial record in the chunk
* caller can modify the memory content of out_chunk,
* the memory is valid until next call to NextRecord or NextChunk
*
* Usually NextRecord is sufficient, NextChunk can be used by some
* multi-threaded parsers to parse the input content
*
* \param out_chunk used to store the result
* \return true if we can successfully get next record
* false if we reached end of split
* \sa InputSplit::Create for definition of record
* \sa RecordIOChunkReader to parse recordio content from out_chunk
*/
virtual bool NextChunk(Blob *out_chunk) = 0;
/*! \brief destructor*/
virtual ~InputSplit(void) {}
/*!
* \brief factory function:
* create input split given a uri
* \param uri the uri of the input, can contain hdfs prefix
* \param part_index the part id of current input
* \param num_parts total number of splits
* \param type type of record
* List of possible types: "text", "recordio"
* - "text":
* text file, each line is treated as a record
* input split will split on '\\n' or '\\r'
* - "recordio":
* binary recordio file, see recordio.h
* \return a new input split
* \sa InputSplit::Type
*/
static InputSplit* Create(const char *uri,
unsigned part_index,
unsigned num_parts,
const char *type);
};
/*!
* \brief a std::ostream class that can can wrap Stream objects,
* can use ostream with that output to underlying Stream
*
* Usage example:
* \code
*
* Stream *fs = Stream::Create("hdfs:///test.txt", "w");
* dmlc::ostream os(fs);
* os << "hello world" << std::endl;
* delete fs;
* \endcode
*/
class ostream : public std::basic_ostream<char> {
public:
/*!
* \brief construct std::ostream type
* \param stream the Stream output to be used
* \param buffer_size internal streambuf size
*/
explicit ostream(Stream *stream,
size_t buffer_size = (1 << 10))
: std::basic_ostream<char>(NULL), buf_(buffer_size) {
this->set_stream(stream);
}
// explictly synchronize the buffer
virtual ~ostream() {
buf_.pubsync();
}
/*!
* \brief set internal stream to be stream, reset states
* \param stream new stream as output
*/
inline void set_stream(Stream *stream) {
buf_.set_stream(stream);
this->rdbuf(&buf_);
}
private:
// internal streambuf
class OutBuf : public std::streambuf {
public:
explicit OutBuf(size_t buffer_size)
: stream_(NULL), buffer_(buffer_size) {
if (buffer_size == 0) buffer_.resize(2);
}
// set stream to the buffer
inline void set_stream(Stream *stream);
private:
/*! \brief internal stream by StreamBuf */
Stream *stream_;
/*! \brief internal buffer */
std::vector<char> buffer_;
// override sync
inline int_type sync(void);
// override overflow
inline int_type overflow(int c);
};
/*! \brief buffer of the stream */
OutBuf buf_;
};
/*!
* \brief a std::istream class that can can wrap Stream objects,
* can use istream with that output to underlying Stream
*
* Usage example:
* \code
*
* Stream *fs = Stream::Create("hdfs:///test.txt", "r");
* dmlc::istream is(fs);
* is >> mydata;
* delete fs;
* \endcode
*/
class istream : public std::basic_istream<char> {
public:
/*!
* \brief construct std::ostream type
* \param stream the Stream output to be used
* \param buffer_size internal buffer size
*/
explicit istream(Stream *stream,
size_t buffer_size = (1 << 10))
: std::basic_istream<char>(NULL), buf_(buffer_size) {
this->set_stream(stream);
}
virtual ~istream() {}
/*!
* \brief set internal stream to be stream, reset states
* \param stream new stream as output
*/
inline void set_stream(Stream *stream) {
buf_.set_stream(stream);
this->rdbuf(&buf_);
}
/*! \return how many bytes we read so far */
inline size_t bytes_read(void) const {
return buf_.bytes_read();
}
private:
// internal streambuf
class InBuf : public std::streambuf {
public:
explicit InBuf(size_t buffer_size)
: stream_(NULL), bytes_read_(0),
buffer_(buffer_size) {
if (buffer_size == 0) buffer_.resize(2);
}
// set stream to the buffer
inline void set_stream(Stream *stream);
// return how many bytes read so far
inline size_t bytes_read(void) const {
return bytes_read_;
}
private:
/*! \brief internal stream by StreamBuf */
Stream *stream_;
/*! \brief how many bytes we read so far */
size_t bytes_read_;
/*! \brief internal buffer */
std::vector<char> buffer_;
// override underflow
inline int_type underflow();
};
/*! \brief input buffer */
InBuf buf_;
};
// implementations of inline functions
template<typename T>
inline void Stream::Write(const std::vector<T> &vec) {
uint64_t sz = static_cast<uint64_t>(vec.size());
this->Write(&sz, sizeof(sz));
if (sz != 0) {
this->Write(&vec[0], sizeof(T) * vec.size());
}
}
template<typename T>
inline bool Stream::Read(std::vector<T> *out_vec) {
uint64_t sz;
if (this->Read(&sz, sizeof(sz)) == 0) return false;
size_t size = static_cast<size_t>(sz);
out_vec->resize(size);
if (sz != 0) {
if (this->Read(&(*out_vec)[0], sizeof(T) * size) == 0) return false;
}
return true;
}
inline void Stream::Write(const std::string &str) {
uint64_t sz = static_cast<uint64_t>(str.length());
this->Write(&sz, sizeof(sz));
if (sz != 0) {
this->Write(&str[0], sizeof(char) * str.length());
}
}
inline bool Stream::Read(std::string *out_str) {
uint64_t sz;
if (this->Read(&sz, sizeof(sz)) == 0) return false;
size_t size = static_cast<size_t>(sz);
out_str->resize(size);
if (sz != 0) {
if (this->Read(&(*out_str)[0], sizeof(char) * size) == 0) {
return false;
}
}
return true;
}
// implementations for ostream
inline void ostream::OutBuf::set_stream(Stream *stream) {
if (stream_ != NULL) this->pubsync();
this->stream_ = stream;
this->setp(&buffer_[0], &buffer_[0] + buffer_.size() - 1);
}
inline int ostream::OutBuf::sync(void) {
if (stream_ == NULL) return -1;
std::ptrdiff_t n = pptr() - pbase();
stream_->Write(pbase(), n);
this->pbump(-static_cast<int>(n));
return 0;
}
inline int ostream::OutBuf::overflow(int c) {
*(this->pptr()) = c;
std::ptrdiff_t n = pptr() - pbase();
this->pbump(-static_cast<int>(n));
if (c == EOF) {
stream_->Write(pbase(), n);
} else {
stream_->Write(pbase(), n + 1);
}
return c;
}
// implementations for istream
inline void istream::InBuf::set_stream(Stream *stream) {
stream_ = stream;
this->setg(&buffer_[0], &buffer_[0], &buffer_[0]);
}
inline int istream::InBuf::underflow() {
char *bhead = &buffer_[0];
if (this->gptr() == this->egptr()) {
size_t sz = stream_->Read(bhead, buffer_.size());
this->setg(bhead, bhead, bhead + sz);
bytes_read_ += sz;
}
if (this->gptr() == this->egptr()) {
return traits_type::eof();
} else {
return traits_type::to_int_type(*gptr());
}
}
} // namespace dmlc
#endif // DMLC_IO_H_