Hi,
I use hbase client 0.92.1 to get the row, but when Get add all the columns
and qualifiers, a filed (f:ts) is always return nothing. If Get not add
column mk or ft , it works right. Is it a bug?
The schema as follow:
<table name="webpage">
<family name="p" maxVersions="1"/> <!-- This can also have params like
compression, bloom filters -->
<family name="f" maxVersions="1"/>
<family name="s" maxVersions="1"/>
<family name="il" maxVersions="1"/>
<family name="ol" maxVersions="1"/>
<family name="h" maxVersions="1"/>
<family name="mtdt" maxVersions="1"/>
<family name="mk" maxVersions="1"/>
<family name="ft" maxVersions="1"/>
</table>
<class table="webpage" keyClass="java.lang.String"
name="org.apache.nutch.storage.WebPage">
<!-- fetch fields -->
<field name="baseUrl" family="f" qualifier="bas"/>
<field name="status" family="f" qualifier="st"/>
<field name="prevFetchTime" family="f" qualifier="pts"/>
<field name="fetchTime" family="f" qualifier="ts"/>
<field name="fetchInterval" family="f" qualifier="fi"/>
<field name="retriesSinceFetch" family="f" qualifier="rsf"/>
<field name="reprUrl" family="f" qualifier="rpr"/>
<field name="content" family="f" qualifier="cnt"/>
<field name="contentType" family="f" qualifier="typ"/>
<field name="protocolStatus" family="f" qualifier="prot"/>
<field name="modifiedTime" family="f" qualifier="mod"/>
<field name="pageType" family="f" qualifier="ptyp"/>
<field name="level" family="f" qualifier="l"/>
<field name="lastFetchInterval" family="f" qualifier="lfi"/>
<field name="newsTime" family="f" qualifier="nts"/>
<field name="findTime" family="f" qualifier="fts"/>
<field name="title" family="p" qualifier="t"/>
<field name="text" family="p" qualifier="c"/>
<field name="parseStatus" family="p" qualifier="st"/>
<field name="signature" family="p" qualifier="sig"/>
<field name="prevSignature" family="p" qualifier="psig"/>
<!-- score fields -->
<field name="score" family="s" qualifier="s"/>
<field name="headers" family="h"/>
<field name="inlinks" family="il"/>
<field name="outlinks" family="ol"/>
<field name="metadata" family="mtdt"/>
<field name="markers" family="mk"/>
<field name="features" family="ft"/>
</class>
{"name": "WebPage",
"type": "record",
"namespace": "org.apache.nutch.storage",
"fields": [
{"name": "baseUrl", "type": "string"},
{"name": "status", "type": "int"},
{"name": "fetchTime", "type": "long"},
{"name": "prevFetchTime", "type": "long"},
{"name": "fetchInterval", "type": "int"},
{"name": "retriesSinceFetch", "type": "int"},
{"name": "modifiedTime", "type": "long"},
{"name": "protocolStatus", "type": {
"name": "ProtocolStatus",
"type": "record",
"namespace": "org.apache.nutch.storage",
"fields": [
{"name": "code", "type": "int"},
{"name": "args", "type": {"type": "array", "items": "string"}},
{"name": "lastModified", "type": "long"}
]
}},
{"name": "content", "type": "bytes"},
{"name": "contentType", "type": "string"},
{"name": "prevSignature", "type": "bytes"},
{"name": "signature", "type": "bytes"},
{"name": "title", "type": "string"},
{"name": "text", "type": "string"},
{"name": "parseStatus", "type": {
"name": "ParseStatus",
"type": "record",
"namespace": "org.apache.nutch.storage",
"fields": [
{"name": "majorCode", "type": "int"},
{"name": "minorCode", "type": "int"},
{"name": "args", "type": {"type": "array", "items": "string"}}
]
}},
{"name": "score", "type": "float"},
{"name": "reprUrl", "type": "string"},
{"name": "headers", "type": {"type": "map", "values": "string"}},
{"name": "outlinks", "type": {"type": "map", "values": "string"}},
{"name": "inlinks", "type": {"type": "map", "values": "string"}},
{"name": "markers", "type": {"type": "map", "values": "string"}},
{"name": "metadata", "type": {"type": "map", "values": "bytes"}},
{"name": "features", "type": {"type": "map", "values": "bytes"}},
{"name": "pageType", "type": "int"},
{"name": "newsTime", "type": "long"},
{"name": "level", "type": "int"},
{"name": "lastFetchInterval", "type":"int"},
{"name": "findTime", "type":"long"}
]
}