|
|
@@ -204,8 +204,8 @@ type := (ptype / ctype)
|
|
|
ptype := ("byte" / "boolean" / "int" |
|
|
|
"long" / "float" / "double"
|
|
|
"ustring" / "buffer")
|
|
|
-ctype := (("vector" "<" type ">") /
|
|
|
- ("map" "<" type "," type ">" ) ) / name)
|
|
|
+ctype := (("vector" "<" type ">") /
|
|
|
+ ("map" "<" type "," type ">" ) ) / name)
|
|
|
</code></pre>
|
|
|
|
|
|
A DDL file describes one or more record types. It begins with zero or
|
|
|
@@ -255,7 +255,7 @@ include "links.jr"
|
|
|
module outlinks {
|
|
|
class OutLinks {
|
|
|
ustring baseURL;
|
|
|
- vector<links.Link> outLinks;
|
|
|
+ vector<links.Link> outLinks;
|
|
|
};
|
|
|
}
|
|
|
</code></pre>
|
|
|
@@ -269,7 +269,7 @@ record description files as a mandatory argument and an
|
|
|
optional language argument (the default is Java) --language or
|
|
|
-l. Thus a typical invocation would look like:
|
|
|
<pre><code>
|
|
|
-$ rcc -l C++ <filename> ...
|
|
|
+$ rcc -l C++ <filename> ...
|
|
|
</code></pre>
|
|
|
|
|
|
|
|
|
@@ -306,7 +306,7 @@ namespace hadoop {
|
|
|
|
|
|
class IOError : public runtime_error {
|
|
|
public:
|
|
|
- explicit IOError(const std::string& msg);
|
|
|
+ explicit IOError(const std::string& msg);
|
|
|
};
|
|
|
|
|
|
class IArchive;
|
|
|
@@ -314,18 +314,18 @@ namespace hadoop {
|
|
|
|
|
|
class RecordReader {
|
|
|
public:
|
|
|
- RecordReader(InStream& in, RecFormat fmt);
|
|
|
+ RecordReader(InStream& in, RecFormat fmt);
|
|
|
virtual ~RecordReader(void);
|
|
|
|
|
|
- virtual void read(Record& rec);
|
|
|
+ virtual void read(Record& rec);
|
|
|
};
|
|
|
|
|
|
class RecordWriter {
|
|
|
public:
|
|
|
- RecordWriter(OutStream& out, RecFormat fmt);
|
|
|
+ RecordWriter(OutStream& out, RecFormat fmt);
|
|
|
virtual ~RecordWriter(void);
|
|
|
|
|
|
- virtual void write(Record& rec);
|
|
|
+ virtual void write(Record& rec);
|
|
|
};
|
|
|
|
|
|
|
|
|
@@ -337,10 +337,10 @@ namespace hadoop {
|
|
|
virtual bool validate(void) const = 0;
|
|
|
|
|
|
virtual void
|
|
|
- serialize(OArchive& oa, const std::string& tag) const = 0;
|
|
|
+ serialize(OArchive& oa, const std::string& tag) const = 0;
|
|
|
|
|
|
virtual void
|
|
|
- deserialize(IArchive& ia, const std::string& tag) = 0;
|
|
|
+ deserialize(IArchive& ia, const std::string& tag) = 0;
|
|
|
};
|
|
|
}
|
|
|
</code></pre>
|
|
|
@@ -445,11 +445,11 @@ private:
|
|
|
...
|
|
|
public:
|
|
|
|
|
|
- std::string& getMyBuf() {
|
|
|
+ std::string& getMyBuf() {
|
|
|
return mMyBuf;
|
|
|
};
|
|
|
|
|
|
- const std::string& getMyBuf() const {
|
|
|
+ const std::string& getMyBuf() const {
|
|
|
return mMyBuf;
|
|
|
};
|
|
|
...
|
|
|
@@ -474,7 +474,7 @@ and the testrec.jr file contains:
|
|
|
include "inclrec.jr"
|
|
|
module testrec {
|
|
|
class R {
|
|
|
- vector<float> VF;
|
|
|
+ vector<float> VF;
|
|
|
RI Rec;
|
|
|
buffer Buf;
|
|
|
};
|
|
|
@@ -511,8 +511,8 @@ namespace inclrec {
|
|
|
RI(void);
|
|
|
virtual ~RI(void);
|
|
|
|
|
|
- virtual bool operator==(const RI& peer) const;
|
|
|
- virtual bool operator<(const RI& peer) const;
|
|
|
+ virtual bool operator==(const RI& peer) const;
|
|
|
+ virtual bool operator<(const RI& peer) const;
|
|
|
|
|
|
virtual int32_t getI32(void) const { return I32; }
|
|
|
virtual void setI32(int32_t v) { I32 = v; }
|
|
|
@@ -520,16 +520,16 @@ namespace inclrec {
|
|
|
virtual double getD(void) const { return D; }
|
|
|
virtual void setD(double v) { D = v; }
|
|
|
|
|
|
- virtual std::string& getS(void) const { return S; }
|
|
|
- virtual const std::string& getS(void) const { return S; }
|
|
|
+ virtual std::string& getS(void) const { return S; }
|
|
|
+ virtual const std::string& getS(void) const { return S; }
|
|
|
|
|
|
virtual std::string type(void) const;
|
|
|
virtual std::string signature(void) const;
|
|
|
|
|
|
protected:
|
|
|
|
|
|
- virtual void serialize(hadoop::OArchive& a) const;
|
|
|
- virtual void deserialize(hadoop::IArchive& a);
|
|
|
+ virtual void serialize(hadoop::OArchive& a) const;
|
|
|
+ virtual void deserialize(hadoop::IArchive& a);
|
|
|
};
|
|
|
} // end namespace inclrec
|
|
|
|
|
|
@@ -552,7 +552,7 @@ namespace testrec {
|
|
|
|
|
|
private:
|
|
|
|
|
|
- std::vector<float> VF;
|
|
|
+ std::vector<float> VF;
|
|
|
inclrec::RI Rec;
|
|
|
std::string Buf;
|
|
|
|
|
|
@@ -561,20 +561,20 @@ namespace testrec {
|
|
|
R(void);
|
|
|
virtual ~R(void);
|
|
|
|
|
|
- virtual bool operator==(const R& peer) const;
|
|
|
- virtual bool operator<(const R& peer) const;
|
|
|
+ virtual bool operator==(const R& peer) const;
|
|
|
+ virtual bool operator<(const R& peer) const;
|
|
|
|
|
|
- virtual std::vector<float>& getVF(void) const;
|
|
|
- virtual const std::vector<float>& getVF(void) const;
|
|
|
+ virtual std::vector<float>& getVF(void) const;
|
|
|
+ virtual const std::vector<float>& getVF(void) const;
|
|
|
|
|
|
- virtual std::string& getBuf(void) const ;
|
|
|
- virtual const std::string& getBuf(void) const;
|
|
|
+ virtual std::string& getBuf(void) const ;
|
|
|
+ virtual const std::string& getBuf(void) const;
|
|
|
|
|
|
- virtual inclrec::RI& getRec(void) const;
|
|
|
- virtual const inclrec::RI& getRec(void) const;
|
|
|
+ virtual inclrec::RI& getRec(void) const;
|
|
|
+ virtual const inclrec::RI& getRec(void) const;
|
|
|
|
|
|
- virtual bool serialize(hadoop::OutArchive& a) const;
|
|
|
- virtual bool deserialize(hadoop::InArchive& a);
|
|
|
+ virtual bool serialize(hadoop::OutArchive& a) const;
|
|
|
+ virtual bool deserialize(hadoop::InArchive& a);
|
|
|
|
|
|
virtual std::string type(void) const;
|
|
|
virtual std::string signature(void) const;
|
|
|
@@ -619,8 +619,8 @@ double double double
|
|
|
ustring std::string java.lang.String
|
|
|
buffer std::string org.apache.hadoop.record.Buffer
|
|
|
class type class type class type
|
|
|
-vector<type> std::vector<type> java.util.ArrayList<type>
|
|
|
-map<type,type> std::map<type,type> java.util.TreeMap<type,type>
|
|
|
+vector<type> std::vector<type> java.util.ArrayList<type>
|
|
|
+map<type,type> std::map<type,type> java.util.TreeMap<type,type>
|
|
|
</code></pre>
|
|
|
|
|
|
<h2>Data encodings</h2>
|
|
|
@@ -651,7 +651,7 @@ Primitive types are serialized as follows:
|
|
|
<li> byte: Represented by 1 byte, as is.
|
|
|
<li> boolean: Represented by 1-byte (0 or 1)
|
|
|
<li> int/long: Integers and longs are serialized zero compressed.
|
|
|
-Represented as 1-byte if -120 <= value < 128. Otherwise, serialized as a
|
|
|
+Represented as 1-byte if -120 <= value < 128. Otherwise, serialized as a
|
|
|
sequence of 2-5 bytes for ints, 2-9 bytes for longs. The first byte represents
|
|
|
the number of trailing bytes, N, as the negative number (-120-N). For example,
|
|
|
the number 1024 (0x400) is represented by the byte sequence 'x86 x04 x00'.
|
|
|
@@ -741,7 +741,7 @@ replace CRLF sequences with line feeds. Programming languages that we work
|
|
|
with do not impose these restrictions on string types. To work around these
|
|
|
restrictions, disallowed characters and CRs are percent escaped in strings.
|
|
|
The '%' character is also percent escaped.
|
|
|
-<li> buffer: XML tag <string&>. Values: Arbitrary binary
|
|
|
+<li> buffer: XML tag <string>. Values: Arbitrary binary
|
|
|
data. Represented as hexBinary, each byte is replaced by its 2-byte
|
|
|
hexadecimal representation.
|
|
|
</ul>
|
|
|
@@ -755,7 +755,7 @@ element and a <value> element. The <name> is a string that must
|
|
|
match /[a-zA-Z][a-zA-Z0-9_]*/. The value of the member is represented
|
|
|
by a <value> element.
|
|
|
|
|
|
-<li> vector: XML tag <array<. An <array> contains a
|
|
|
+<li> vector: XML tag <array>. An <array> contains a
|
|
|
single <data> element. The <data> element is a sequence of
|
|
|
<value> elements each of which represents an element of the vector.
|
|
|
|
|
|
@@ -768,7 +768,7 @@ For example:
|
|
|
<pre><code>
|
|
|
class {
|
|
|
int MY_INT; // value 5
|
|
|
- vector<float> MY_VEC; // values 0.1, -0.89, 2.45e4
|
|
|
+ vector<float> MY_VEC; // values 0.1, -0.89, 2.45e4
|
|
|
buffer MY_BUF; // value '\00\n\tabc%'
|
|
|
}
|
|
|
</code></pre>
|
Akira Ajisaka