Class: Fluent::ODPSOutput::TableElement

Inherits:
Object
  • Object
show all
Includes:
Configurable
Defined in:
lib/fluent/plugin/out_aliyun_odps.rb

Overview

TODO: Merge SQLInput’s TableElement

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(pattern, log) ⇒ TableElement

Returns a new instance of TableElement.



66
67
68
69
70
 
# File 'lib/fluent/plugin/out_aliyun_odps.rb', line 66

def initialize(pattern, log)
  super()
  @pattern = MatchPattern.create(pattern)
  @log = log
end

Instance Attribute Details

#client ⇒ Object (readonly)

Returns the value of attribute client.



61
62
63
 
# File 'lib/fluent/plugin/out_aliyun_odps.rb', line 61

def client
  @client
end

#log ⇒ Object (readonly)

Returns the value of attribute log.



64
65
66
 
# File 'lib/fluent/plugin/out_aliyun_odps.rb', line 64

def log
  @log
end

#partitionList ⇒ Object

Returns the value of attribute partitionList.



60
61
62
 
# File 'lib/fluent/plugin/out_aliyun_odps.rb', line 60

def partitionList
  @partitionList
end

#pattern ⇒ Object (readonly)

Returns the value of attribute pattern.



63
64
65
 
# File 'lib/fluent/plugin/out_aliyun_odps.rb', line 63

def pattern
  @pattern
end

#writer ⇒ Object (readonly)

Returns the value of attribute writer.



62
63
64
 
# File 'lib/fluent/plugin/out_aliyun_odps.rb', line 62

def writer
  @writer
end

Instance Method Details

#close ⇒ Object 



281
282
283
 
# File 'lib/fluent/plugin/out_aliyun_odps.rb', line 281

def close()
  #@client.loadShard(0)

end

#configure(conf) ⇒ Object

初始化数据



73
74
75
76
77
78
79
80
81
82
83
84
85
 
# File 'lib/fluent/plugin/out_aliyun_odps.rb', line 73

def configure(conf)
  super
  @format_proc = Proc.new { |record|
    values = []
    @fields.split(',').each { |key|
      unless record.has_key?(key)
        @log.warn "the table  "+@table+"'s "+key+" field not has match key"
      end
      values << record[key]
    }
    values
  }
end

#import(chunk) ⇒ Object

import data



106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
 
# File 'lib/fluent/plugin/out_aliyun_odps.rb', line 106

def import(chunk)
  records = []
  partitions=Hash.new
  chunk.msgpack_each { |tag, time, data|
    begin
      #if partition is not empty

      unless @partition.blank? then
        begin
          #if partition has params in it

          if @partition.include? "=${"
            #split partition

            partition_arrays=@partition.split(',')
            partition_name=''
            i=1
            for p in partition_arrays do
              #if partition is time formated

              if p.include? "strftime"
                key=p[p.index("{")+1, p.index(".strftime")-1-p.index("{")]
                partition_column=p[0, p.index("=")]
                timeFormat=p[p.index("(")+2, p.index(")")-3-p.index("(")]
                if data.has_key?(key)
                  if time_format == nil
                    partition_value=Time.parse(data[key]).strftime(timeFormat)
                  else
                    partition_value=Time.strptime(data[key], time_format).strftime(timeFormat)
                  end
                  if i==1
                    partition_name+=partition_column+"="+partition_value
                  else
                    partition_name+=","+partition_column+"="+partition_value
                  end
                else
                  raise "partition has no corresponding source key or the partition expression is wrong,"+data.to_s
                end
              elsif p.include? "=${"
                key=p[p.index("{")+1, p.index("}")-1-p.index("{")]
                partition_column=p[0, p.index("=")]
                if data.has_key?(key)
                  partition_value=data[key]
                  if i==1
                    partition_name+=partition_column+"="+partition_value
                  else
                    partition_name+=","+partition_column+"="+partition_value
                  end
                else
                  raise "partition has no corresponding source key or the partition expression is wrong,"+data.to_s
                end
              else
                if i==1
                  partition_name+=p
                else
                  partition_name+=","+p
                end
              end
              i+=1
            end
          else
            partition_name=@partition
          end
          if partitions[partition_name]==nil
            partitions[partition_name]=[]
          end
          partitions[partition_name] << @format_proc.call(data)
        rescue => ex
          if (@abandon_mode)
            @log.error "Format partition failed, abandon this record. Msg:" +ex.message + " Table:" + @table
            @log.error "Drop data:" + data.to_s
          else
            raise e
          end
        end
      else
        records << @format_proc.call(data)
      end
    rescue => e
      raise "Failed to format the data:"+ e.message + " " +e.backtrace.inspect.to_s
    end
  }

  begin
    #multi thread

    sendThread = Array.new
    unless @partition.blank? then
      for thread in 0..@thread_number-1
        sendThread[thread] = Thread.start(thread) do |threadId|
          partitions.each { |k, v|
            retryTime = @retry_time
            begin
              sendCount = v.size/@thread_number
              restCount = 0
              if threadId == @thread_number-1
                restCount = v.size%@thread_number
              end
              @client.createStreamArrayWriter().write(v[sendCount*threadId..sendCount*(threadId+1)+restCount-1], k)
              @log.info "Successfully import "+(sendCount+restCount).to_s+" data to partition:"+k+",table:"+@table+" at threadId:"+threadId.to_s
            rescue => e
              @log.warn "Fail to write, error at threadId:"+threadId.to_s+" Msg:"+e.message + " partitions:" + k.to_s + " table:" + @table
              # reload shard

              if e.message.include? "ShardNotReady" or e.message.include? "InvalidShardId"
                @log.warn "Reload shard."
                @client.loadShard(@shard_number)
                @client.waitForShardLoad
              elsif e.message.include? "NoSuchPartition"
                begin
                  @client.addPartition(k)
                  @log.info "Add partition "+ k + " table:" + @table
                rescue => ex
                  @log.error "Add partition failed"+ ex.message + " partitions:" + k.to_s + " table:" + @table
                end
              end
              if retryTime > 0
                @log.info "Retry in " + @retry_interval.to_s + "sec. Partitions:" + k.to_s + " table:" + @table
                sleep(@retry_interval)
                retryTime -= 1
                retry
              else
                if (@abandon_mode)
                  @log.error "Retry failed, abandon this pack. Msg:" + e.message + " partitions:" + k.to_s + " table:" + @table
                  @log.error v[sendCount*threadId..sendCount*(threadId+1)+restCount-1]
                else
                  raise e
                end
              end
            end
          }
        end
      end
    else
      @log.info records.size.to_s+" records to be sent"
      for thread in 0..@thread_number-1
        sendThread[thread] = Thread.start(thread) do |threadId|
          retryTime = @retry_time
          #send data from sendCount*threadId to sendCount*(threadId+1)-1

          sendCount = records.size/@thread_number
          restCount = 0
          if threadId == @thread_number-1
            restCount = records.size%@thread_number
          end
          begin
            @client.createStreamArrayWriter().write(records[sendCount*threadId..sendCount*(threadId+1)+restCount-1])
            @log.info "Successfully import "+(sendCount+restCount).to_s+" data to table:"+@table+" at threadId:"+threadId.to_s
          rescue => e
            @log.warn "Fail to write, error at threadId:"+threadId.to_s+" Msg:"+e.message + " table:" + @table
            # reload shard

            if e.message.include? "ShardNotReady" or e.message.include? "InvalidShardId"
              @log.warn "Reload shard."
              @client.loadShard(@shard_number)
              @client.waitForShardLoad
            end
            if retryTime > 0
              @log.info "Retry in " + @retry_interval.to_s + "sec. Table:" + @table
              sleep(@retry_interval)
              retryTime -= 1
              retry
            else
              if (@abandon_mode)
                @log.error "Retry failed, abandon this pack. Msg:" + e.message + " Table:" + @table
                @log.error records[sendCount*threadId..sendCount*(threadId+1)+restCount-1]
              else
                raise e
              end
            end
          end
        end
      end
    end
    for thread in 0..@thread_number-1
      sendThread[thread].join
    end
  rescue => e
    # ignore other exceptions to use Fluentd retry

    raise "write records failed," + e.message + " " +e.backtrace.inspect.to_s
  end
end

#init(config) ⇒ Object 



87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
 
# File 'lib/fluent/plugin/out_aliyun_odps.rb', line 87

def init(config)
  odpsConfig = OdpsDatahub::OdpsConfig.new(config[:aliyun_access_id],
                                           config[:aliyun_access_key],
                                           config[:aliyun_odps_endpoint],
                                           config[:aliyun_odps_hub_endpoint],
                                           config[:project])
  if @shard_number<=0
    raise "shard number must more than 0"
  end
  begin
    @client = OdpsDatahub::StreamClient.new(odpsConfig, config[:project], @table)
    @client.loadShard(@shard_number)
    @client.waitForShardLoad
  rescue => e
    raise "loadShard failed,"+e.message
  end
end