kou commented on code in PR #216:
URL: https://github.com/apache/arrow-go/pull/216#discussion_r1884703053
##########
arrow/ipc/file_reader.go:
##########
@@ -33,16 +33,166 @@ import (
"github.com/apache/arrow-go/v18/arrow/memory"
)
-// FileReader is an Arrow file reader.
-type FileReader struct {
+type readerImpl interface {
+ getFooterEnd() (int64, error)
+ readFooter(*footerBlock) error
+ dict(memory.Allocator, *footerBlock, int) (dataBlock, error)
+ block(memory.Allocator, *footerBlock, int) (dataBlock, error)
+}
+
+type footerBlock struct {
+ offset int64
+ buffer *memory.Buffer
+ data *flatbuf.Footer
+}
+
+type dataBlock interface {
+ Offset() int64
+ Meta() int32
+ Body() int64
+ NewMessage() (*Message, error)
+}
+
+type basicReaderImpl struct {
r ReadAtSeeker
+}
- footer struct {
- offset int64
- buffer *memory.Buffer
- data *flatbuf.Footer
+func (r *basicReaderImpl) getFooterEnd() (int64, error) {
+ return r.r.Seek(0, io.SeekEnd)
+}
+
+func (r *basicReaderImpl) readFooter(f *footerBlock) error {
+ var err error
+
+ if f.offset <= int64(len(Magic)*2+4) {
Review Comment:
Can we give `4` a name something like `footerSizeLen` or something?
##########
arrow/ipc/file_reader.go:
##########
@@ -33,16 +33,166 @@ import (
"github.com/apache/arrow-go/v18/arrow/memory"
)
-// FileReader is an Arrow file reader.
-type FileReader struct {
+type readerImpl interface {
+ getFooterEnd() (int64, error)
+ readFooter(*footerBlock) error
+ dict(memory.Allocator, *footerBlock, int) (dataBlock, error)
+ block(memory.Allocator, *footerBlock, int) (dataBlock, error)
+}
+
+type footerBlock struct {
+ offset int64
+ buffer *memory.Buffer
+ data *flatbuf.Footer
+}
+
+type dataBlock interface {
+ Offset() int64
+ Meta() int32
+ Body() int64
+ NewMessage() (*Message, error)
+}
+
+type basicReaderImpl struct {
r ReadAtSeeker
+}
- footer struct {
- offset int64
- buffer *memory.Buffer
- data *flatbuf.Footer
+func (r *basicReaderImpl) getFooterEnd() (int64, error) {
+ return r.r.Seek(0, io.SeekEnd)
+}
+
+func (r *basicReaderImpl) readFooter(f *footerBlock) error {
+ var err error
+
+ if f.offset <= int64(len(Magic)*2+4) {
Review Comment:
Can we add a variable for `len(Magic)*2+4` because we use this minimum size
multiple times in this file?
##########
arrow/ipc/file_reader.go:
##########
@@ -33,16 +33,166 @@ import (
"github.com/apache/arrow-go/v18/arrow/memory"
)
-// FileReader is an Arrow file reader.
-type FileReader struct {
+type readerImpl interface {
+ getFooterEnd() (int64, error)
+ readFooter(*footerBlock) error
+ dict(memory.Allocator, *footerBlock, int) (dataBlock, error)
+ block(memory.Allocator, *footerBlock, int) (dataBlock, error)
+}
+
+type footerBlock struct {
+ offset int64
+ buffer *memory.Buffer
+ data *flatbuf.Footer
+}
+
+type dataBlock interface {
+ Offset() int64
+ Meta() int32
+ Body() int64
+ NewMessage() (*Message, error)
+}
+
+type basicReaderImpl struct {
r ReadAtSeeker
+}
- footer struct {
- offset int64
- buffer *memory.Buffer
- data *flatbuf.Footer
+func (r *basicReaderImpl) getFooterEnd() (int64, error) {
+ return r.r.Seek(0, io.SeekEnd)
+}
+
+func (r *basicReaderImpl) readFooter(f *footerBlock) error {
+ var err error
+
+ if f.offset <= int64(len(Magic)*2+4) {
+ return fmt.Errorf("arrow/ipc: file too small (size=%d)",
f.offset)
+ }
+
+ eof := int64(len(Magic) + 4)
+ buf := make([]byte, eof)
+ n, err := r.r.ReadAt(buf, f.offset-eof)
+ if err != nil {
+ return fmt.Errorf("arrow/ipc: could not read footer: %w", err)
+ }
+ if n != len(buf) {
+ return fmt.Errorf("arrow/ipc: could not read %d bytes from end
of file", len(buf))
+ }
+
+ if !bytes.Equal(buf[4:], Magic) {
+ return errNotArrowFile
+ }
+
+ size := int64(binary.LittleEndian.Uint32(buf[:4]))
+ if size <= 0 || size+int64(len(Magic)*2+4) > f.offset {
+ return errInconsistentFileMetadata
+ }
+
+ buf = make([]byte, size)
+ n, err = r.r.ReadAt(buf, f.offset-size-eof)
+ if err != nil {
+ return fmt.Errorf("arrow/ipc: could not read footer data: %w",
err)
+ }
+ if n != len(buf) {
+ return fmt.Errorf("arrow/ipc: could not read %d bytes from
footer data", len(buf))
+ }
+
+ f.buffer = memory.NewBufferBytes(buf)
+ f.data = flatbuf.GetRootAsFooter(buf, 0)
+ return err
+}
+
+func (r *basicReaderImpl) block(mem memory.Allocator, f *footerBlock, i int)
(dataBlock, error) {
+ var blk flatbuf.Block
+ if !f.data.RecordBatches(&blk, i) {
+ return fileBlock{}, fmt.Errorf("arrow/ipc: could not extract
file block %d", i)
}
+ return fileBlock{
+ offset: blk.Offset(),
+ meta: blk.MetaDataLength(),
+ body: blk.BodyLength(),
+ r: r.r,
+ mem: mem,
+ }, nil
+}
+
+func (r *basicReaderImpl) dict(mem memory.Allocator, f *footerBlock, i int)
(dataBlock, error) {
+ var blk flatbuf.Block
+ if !f.data.Dictionaries(&blk, i) {
+ return fileBlock{}, fmt.Errorf("arrow/ipc: could not extract
dictionary block %d", i)
+ }
+
+ return fileBlock{
+ offset: blk.Offset(),
+ meta: blk.MetaDataLength(),
+ body: blk.BodyLength(),
+ r: r.r,
+ mem: mem,
+ }, nil
+}
+
+type mappedReaderImpl struct {
+ data []byte
+}
+
+func (r *mappedReaderImpl) getFooterEnd() (int64, error) { return
int64(len(r.data)), nil }
+
+func (r *mappedReaderImpl) readFooter(f *footerBlock) error {
Review Comment:
Can we unify more codes in this function with
`basicReaderImple.readFooter()`?
It seems that they have many similar codes.
##########
arrow/ipc/file_reader.go:
##########
@@ -768,3 +867,44 @@ func readDictionary(memo *dictutils.Memo, meta
*memory.Buffer, body ReadAtSeeker
}
return dictutils.KindReplacement, nil
}
+
+type mappedFileBlock struct {
+ offset int64
+ meta int32
+ body int64
+
+ data []byte
+}
+
+func (blk mappedFileBlock) Offset() int64 { return blk.offset }
+func (blk mappedFileBlock) Meta() int32 { return blk.meta }
+func (blk mappedFileBlock) Body() int64 { return blk.body }
+
+func (blk mappedFileBlock) section() []byte {
+ return blk.data[blk.offset : blk.offset+int64(blk.meta)+blk.body]
+}
+
+func (blk mappedFileBlock) NewMessage() (*Message, error) {
+ var (
+ body *memory.Buffer
+ meta *memory.Buffer
+ buf = blk.section()
+ )
+
+ metaBytes := buf[:blk.meta]
+
+ prefix := 0
+ switch binary.LittleEndian.Uint32(metaBytes) {
Review Comment:
int32 not uint32?
https://github.com/apache/arrow/blob/313d11aa94c2be71142b55e3d8bb166d780c19c7/format/File.fbs#L45
> metaDataLength: int;
##########
arrow/ipc/file_reader.go:
##########
@@ -33,16 +33,166 @@ import (
"github.com/apache/arrow-go/v18/arrow/memory"
)
-// FileReader is an Arrow file reader.
-type FileReader struct {
+type readerImpl interface {
+ getFooterEnd() (int64, error)
+ readFooter(*footerBlock) error
+ dict(memory.Allocator, *footerBlock, int) (dataBlock, error)
+ block(memory.Allocator, *footerBlock, int) (dataBlock, error)
+}
+
+type footerBlock struct {
+ offset int64
+ buffer *memory.Buffer
+ data *flatbuf.Footer
+}
+
+type dataBlock interface {
+ Offset() int64
+ Meta() int32
+ Body() int64
+ NewMessage() (*Message, error)
+}
+
+type basicReaderImpl struct {
r ReadAtSeeker
+}
- footer struct {
- offset int64
- buffer *memory.Buffer
- data *flatbuf.Footer
+func (r *basicReaderImpl) getFooterEnd() (int64, error) {
+ return r.r.Seek(0, io.SeekEnd)
+}
+
+func (r *basicReaderImpl) readFooter(f *footerBlock) error {
+ var err error
+
+ if f.offset <= int64(len(Magic)*2+4) {
+ return fmt.Errorf("arrow/ipc: file too small (size=%d)",
f.offset)
+ }
+
+ eof := int64(len(Magic) + 4)
+ buf := make([]byte, eof)
+ n, err := r.r.ReadAt(buf, f.offset-eof)
+ if err != nil {
+ return fmt.Errorf("arrow/ipc: could not read footer: %w", err)
+ }
+ if n != len(buf) {
+ return fmt.Errorf("arrow/ipc: could not read %d bytes from end
of file", len(buf))
+ }
+
+ if !bytes.Equal(buf[4:], Magic) {
+ return errNotArrowFile
+ }
+
+ size := int64(binary.LittleEndian.Uint32(buf[:4]))
+ if size <= 0 || size+int64(len(Magic)*2+4) > f.offset {
+ return errInconsistentFileMetadata
+ }
+
+ buf = make([]byte, size)
+ n, err = r.r.ReadAt(buf, f.offset-size-eof)
+ if err != nil {
+ return fmt.Errorf("arrow/ipc: could not read footer data: %w",
err)
+ }
+ if n != len(buf) {
+ return fmt.Errorf("arrow/ipc: could not read %d bytes from
footer data", len(buf))
+ }
+
+ f.buffer = memory.NewBufferBytes(buf)
+ f.data = flatbuf.GetRootAsFooter(buf, 0)
+ return err
+}
+
+func (r *basicReaderImpl) block(mem memory.Allocator, f *footerBlock, i int)
(dataBlock, error) {
+ var blk flatbuf.Block
+ if !f.data.RecordBatches(&blk, i) {
+ return fileBlock{}, fmt.Errorf("arrow/ipc: could not extract
file block %d", i)
}
+ return fileBlock{
+ offset: blk.Offset(),
+ meta: blk.MetaDataLength(),
+ body: blk.BodyLength(),
+ r: r.r,
+ mem: mem,
+ }, nil
+}
+
+func (r *basicReaderImpl) dict(mem memory.Allocator, f *footerBlock, i int)
(dataBlock, error) {
+ var blk flatbuf.Block
+ if !f.data.Dictionaries(&blk, i) {
+ return fileBlock{}, fmt.Errorf("arrow/ipc: could not extract
dictionary block %d", i)
+ }
+
+ return fileBlock{
+ offset: blk.Offset(),
+ meta: blk.MetaDataLength(),
+ body: blk.BodyLength(),
+ r: r.r,
+ mem: mem,
+ }, nil
+}
+
+type mappedReaderImpl struct {
+ data []byte
+}
+
+func (r *mappedReaderImpl) getFooterEnd() (int64, error) { return
int64(len(r.data)), nil }
+
+func (r *mappedReaderImpl) readFooter(f *footerBlock) error {
+ if f.offset <= int64(len(Magic)*2+4) {
+ return fmt.Errorf("arrow/ipc: file too small (size=%d)",
f.offset)
+ }
+
+ eof := int64((len(Magic) + 4))
+ buf := r.data[f.offset-eof:]
+ if !bytes.Equal(buf[4:], Magic) {
+ return errNotArrowFile
+ }
+
+ size := int64(binary.LittleEndian.Uint32(buf[:4]))
Review Comment:
ditto.
##########
arrow/ipc/file_reader.go:
##########
@@ -33,16 +33,166 @@ import (
"github.com/apache/arrow-go/v18/arrow/memory"
)
-// FileReader is an Arrow file reader.
-type FileReader struct {
+type readerImpl interface {
+ getFooterEnd() (int64, error)
+ readFooter(*footerBlock) error
+ dict(memory.Allocator, *footerBlock, int) (dataBlock, error)
+ block(memory.Allocator, *footerBlock, int) (dataBlock, error)
+}
+
+type footerBlock struct {
+ offset int64
+ buffer *memory.Buffer
+ data *flatbuf.Footer
+}
+
+type dataBlock interface {
+ Offset() int64
+ Meta() int32
+ Body() int64
+ NewMessage() (*Message, error)
+}
+
+type basicReaderImpl struct {
r ReadAtSeeker
+}
- footer struct {
- offset int64
- buffer *memory.Buffer
- data *flatbuf.Footer
+func (r *basicReaderImpl) getFooterEnd() (int64, error) {
+ return r.r.Seek(0, io.SeekEnd)
+}
+
+func (r *basicReaderImpl) readFooter(f *footerBlock) error {
+ var err error
+
+ if f.offset <= int64(len(Magic)*2+4) {
+ return fmt.Errorf("arrow/ipc: file too small (size=%d)",
f.offset)
+ }
+
+ eof := int64(len(Magic) + 4)
+ buf := make([]byte, eof)
+ n, err := r.r.ReadAt(buf, f.offset-eof)
+ if err != nil {
+ return fmt.Errorf("arrow/ipc: could not read footer: %w", err)
+ }
+ if n != len(buf) {
+ return fmt.Errorf("arrow/ipc: could not read %d bytes from end
of file", len(buf))
+ }
+
+ if !bytes.Equal(buf[4:], Magic) {
+ return errNotArrowFile
+ }
+
+ size := int64(binary.LittleEndian.Uint32(buf[:4]))
Review Comment:
I think that this should be int32 not uint32:
https://arrow.apache.org/docs/format/Columnar.html#ipc-file-format
> `<FOOTER SIZE: int32>`
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
