1 | <!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd"> |
---|
2 | <!--NewPage--> |
---|
3 | <HTML> |
---|
4 | <HEAD> |
---|
5 | <!-- Generated by javadoc (build 1.6.0_24) on Mon Jun 25 15:26:26 EDT 2012 --> |
---|
6 | <META http-equiv="Content-Type" content="text/html; charset=utf-8"> |
---|
7 | <TITLE> |
---|
8 | ExtractingParams (Solr 4.0.0-ALPHA API) |
---|
9 | </TITLE> |
---|
10 | |
---|
11 | <META NAME="date" CONTENT="2012-06-25"> |
---|
12 | |
---|
13 | <LINK REL ="stylesheet" TYPE="text/css" HREF="../../../../../stylesheet.css" TITLE="Style"> |
---|
14 | |
---|
15 | <SCRIPT type="text/javascript"> |
---|
16 | function windowTitle() |
---|
17 | { |
---|
18 | if (location.href.indexOf('is-external=true') == -1) { |
---|
19 | parent.document.title="ExtractingParams (Solr 4.0.0-ALPHA API)"; |
---|
20 | } |
---|
21 | } |
---|
22 | </SCRIPT> |
---|
23 | <NOSCRIPT> |
---|
24 | </NOSCRIPT> |
---|
25 | |
---|
26 | </HEAD> |
---|
27 | |
---|
28 | <BODY BGCOLOR="white" onload="windowTitle();"> |
---|
29 | <HR> |
---|
30 | |
---|
31 | |
---|
32 | <!-- ========= START OF TOP NAVBAR ======= --> |
---|
33 | <A NAME="navbar_top"><!-- --></A> |
---|
34 | <A HREF="#skip-navbar_top" title="Skip navigation links"></A> |
---|
35 | <TABLE BORDER="0" WIDTH="100%" CELLPADDING="1" CELLSPACING="0" SUMMARY=""> |
---|
36 | <TR> |
---|
37 | <TD COLSPAN=2 BGCOLOR="#EEEEFF" CLASS="NavBarCell1"> |
---|
38 | <A NAME="navbar_top_firstrow"><!-- --></A> |
---|
39 | <TABLE BORDER="0" CELLPADDING="0" CELLSPACING="3" SUMMARY=""> |
---|
40 | <TR ALIGN="center" VALIGN="top"> |
---|
41 | <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1"> <A HREF="../../../../../overview-summary.html"><FONT CLASS="NavBarFont1"><B>Overview</B></FONT></A> </TD> |
---|
42 | <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1"> <A HREF="package-summary.html"><FONT CLASS="NavBarFont1"><B>Package</B></FONT></A> </TD> |
---|
43 | <TD BGCOLOR="#FFFFFF" CLASS="NavBarCell1Rev"> <FONT CLASS="NavBarFont1Rev"><B>Class</B></FONT> </TD> |
---|
44 | <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1"> <A HREF="class-use/ExtractingParams.html"><FONT CLASS="NavBarFont1"><B>Use</B></FONT></A> </TD> |
---|
45 | <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1"> <A HREF="package-tree.html"><FONT CLASS="NavBarFont1"><B>Tree</B></FONT></A> </TD> |
---|
46 | <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1"> <A HREF="../../../../../deprecated-list.html"><FONT CLASS="NavBarFont1"><B>Deprecated</B></FONT></A> </TD> |
---|
47 | <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1"> <A HREF="../../../../../help-doc.html"><FONT CLASS="NavBarFont1"><B>Help</B></FONT></A> </TD> |
---|
48 | </TR> |
---|
49 | </TABLE> |
---|
50 | </TD> |
---|
51 | <TD ALIGN="right" VALIGN="top" ROWSPAN=3><EM> |
---|
52 | </EM> |
---|
53 | </TD> |
---|
54 | </TR> |
---|
55 | |
---|
56 | <TR> |
---|
57 | <TD BGCOLOR="white" CLASS="NavBarCell2"><FONT SIZE="-2"> |
---|
58 | <A HREF="../../../../../org/apache/solr/handler/extraction/ExtractingMetadataConstants.html" title="interface in org.apache.solr.handler.extraction"><B>PREV CLASS</B></A> |
---|
59 | <A HREF="../../../../../org/apache/solr/handler/extraction/ExtractingRequestHandler.html" title="class in org.apache.solr.handler.extraction"><B>NEXT CLASS</B></A></FONT></TD> |
---|
60 | <TD BGCOLOR="white" CLASS="NavBarCell2"><FONT SIZE="-2"> |
---|
61 | <A HREF="../../../../../index.html?org/apache/solr/handler/extraction/ExtractingParams.html" target="_top"><B>FRAMES</B></A> |
---|
62 | <A HREF="ExtractingParams.html" target="_top"><B>NO FRAMES</B></A> |
---|
63 | <SCRIPT type="text/javascript"> |
---|
64 | <!-- |
---|
65 | if(window==top) { |
---|
66 | document.writeln('<A HREF="../../../../../allclasses-noframe.html"><B>All Classes</B></A>'); |
---|
67 | } |
---|
68 | //--> |
---|
69 | </SCRIPT> |
---|
70 | <NOSCRIPT> |
---|
71 | <A HREF="../../../../../allclasses-noframe.html"><B>All Classes</B></A> |
---|
72 | </NOSCRIPT> |
---|
73 | |
---|
74 | |
---|
75 | </FONT></TD> |
---|
76 | </TR> |
---|
77 | <TR> |
---|
78 | <TD VALIGN="top" CLASS="NavBarCell3"><FONT SIZE="-2"> |
---|
79 | SUMMARY: NESTED | <A HREF="#field_summary">FIELD</A> | CONSTR | METHOD</FONT></TD> |
---|
80 | <TD VALIGN="top" CLASS="NavBarCell3"><FONT SIZE="-2"> |
---|
81 | DETAIL: <A HREF="#field_detail">FIELD</A> | CONSTR | METHOD</FONT></TD> |
---|
82 | </TR> |
---|
83 | </TABLE> |
---|
84 | <A NAME="skip-navbar_top"></A> |
---|
85 | <!-- ========= END OF TOP NAVBAR ========= --> |
---|
86 | |
---|
87 | <HR> |
---|
88 | <!-- ======== START OF CLASS DATA ======== --> |
---|
89 | <H2> |
---|
90 | <FONT SIZE="-1"> |
---|
91 | org.apache.solr.handler.extraction</FONT> |
---|
92 | <BR> |
---|
93 | Interface ExtractingParams</H2> |
---|
94 | <DL> |
---|
95 | <DT><B>All Known Implementing Classes:</B> <DD><A HREF="../../../../../org/apache/solr/handler/extraction/SolrContentHandler.html" title="class in org.apache.solr.handler.extraction">SolrContentHandler</A></DD> |
---|
96 | </DL> |
---|
97 | <HR> |
---|
98 | <DL> |
---|
99 | <DT><PRE>public interface <B>ExtractingParams</B></DL> |
---|
100 | </PRE> |
---|
101 | |
---|
102 | <P> |
---|
103 | The various Solr Parameters names to use when extracting content. |
---|
104 | <P> |
---|
105 | |
---|
106 | <P> |
---|
107 | <HR> |
---|
108 | |
---|
109 | <P> |
---|
110 | <!-- =========== FIELD SUMMARY =========== --> |
---|
111 | |
---|
112 | <A NAME="field_summary"><!-- --></A> |
---|
113 | <TABLE BORDER="1" WIDTH="100%" CELLPADDING="3" CELLSPACING="0" SUMMARY=""> |
---|
114 | <TR BGCOLOR="#CCCCFF" CLASS="TableHeadingColor"> |
---|
115 | <TH ALIGN="left" COLSPAN="2"><FONT SIZE="+2"> |
---|
116 | <B>Field Summary</B></FONT></TH> |
---|
117 | </TR> |
---|
118 | <TR BGCOLOR="white" CLASS="TableRowColor"> |
---|
119 | <TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1"> |
---|
120 | <CODE>static <A HREF="http://download.oracle.com/javase/6/docs/api/java/lang/String.html?is-external=true" title="class or interface in java.lang">String</A></CODE></FONT></TD> |
---|
121 | <TD><CODE><B><A HREF="../../../../../org/apache/solr/handler/extraction/ExtractingParams.html#BOOST_PREFIX">BOOST_PREFIX</A></B></CODE> |
---|
122 | |
---|
123 | <BR> |
---|
124 | The boost value for the name of the field.</TD> |
---|
125 | </TR> |
---|
126 | <TR BGCOLOR="white" CLASS="TableRowColor"> |
---|
127 | <TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1"> |
---|
128 | <CODE>static <A HREF="http://download.oracle.com/javase/6/docs/api/java/lang/String.html?is-external=true" title="class or interface in java.lang">String</A></CODE></FONT></TD> |
---|
129 | <TD><CODE><B><A HREF="../../../../../org/apache/solr/handler/extraction/ExtractingParams.html#CAPTURE_ATTRIBUTES">CAPTURE_ATTRIBUTES</A></B></CODE> |
---|
130 | |
---|
131 | <BR> |
---|
132 | Capture attributes separately according to the name of the element, instead of just adding them to the string buffer</TD> |
---|
133 | </TR> |
---|
134 | <TR BGCOLOR="white" CLASS="TableRowColor"> |
---|
135 | <TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1"> |
---|
136 | <CODE>static <A HREF="http://download.oracle.com/javase/6/docs/api/java/lang/String.html?is-external=true" title="class or interface in java.lang">String</A></CODE></FONT></TD> |
---|
137 | <TD><CODE><B><A HREF="../../../../../org/apache/solr/handler/extraction/ExtractingParams.html#CAPTURE_ELEMENTS">CAPTURE_ELEMENTS</A></B></CODE> |
---|
138 | |
---|
139 | <BR> |
---|
140 | Capture the specified fields (and everything included below it that isn't capture by some other capture field) separately from the default.</TD> |
---|
141 | </TR> |
---|
142 | <TR BGCOLOR="white" CLASS="TableRowColor"> |
---|
143 | <TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1"> |
---|
144 | <CODE>static <A HREF="http://download.oracle.com/javase/6/docs/api/java/lang/String.html?is-external=true" title="class or interface in java.lang">String</A></CODE></FONT></TD> |
---|
145 | <TD><CODE><B><A HREF="../../../../../org/apache/solr/handler/extraction/ExtractingParams.html#DEFAULT_FIELD">DEFAULT_FIELD</A></B></CODE> |
---|
146 | |
---|
147 | <BR> |
---|
148 | Optional.</TD> |
---|
149 | </TR> |
---|
150 | <TR BGCOLOR="white" CLASS="TableRowColor"> |
---|
151 | <TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1"> |
---|
152 | <CODE>static <A HREF="http://download.oracle.com/javase/6/docs/api/java/lang/String.html?is-external=true" title="class or interface in java.lang">String</A></CODE></FONT></TD> |
---|
153 | <TD><CODE><B><A HREF="../../../../../org/apache/solr/handler/extraction/ExtractingParams.html#EXTRACT_FORMAT">EXTRACT_FORMAT</A></B></CODE> |
---|
154 | |
---|
155 | <BR> |
---|
156 | Content output format if extractOnly is true.</TD> |
---|
157 | </TR> |
---|
158 | <TR BGCOLOR="white" CLASS="TableRowColor"> |
---|
159 | <TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1"> |
---|
160 | <CODE>static <A HREF="http://download.oracle.com/javase/6/docs/api/java/lang/String.html?is-external=true" title="class or interface in java.lang">String</A></CODE></FONT></TD> |
---|
161 | <TD><CODE><B><A HREF="../../../../../org/apache/solr/handler/extraction/ExtractingParams.html#EXTRACT_ONLY">EXTRACT_ONLY</A></B></CODE> |
---|
162 | |
---|
163 | <BR> |
---|
164 | Only extract and return the content, do not index it.</TD> |
---|
165 | </TR> |
---|
166 | <TR BGCOLOR="white" CLASS="TableRowColor"> |
---|
167 | <TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1"> |
---|
168 | <CODE>static <A HREF="http://download.oracle.com/javase/6/docs/api/java/lang/String.html?is-external=true" title="class or interface in java.lang">String</A></CODE></FONT></TD> |
---|
169 | <TD><CODE><B><A HREF="../../../../../org/apache/solr/handler/extraction/ExtractingParams.html#IGNORE_TIKA_EXCEPTION">IGNORE_TIKA_EXCEPTION</A></B></CODE> |
---|
170 | |
---|
171 | <BR> |
---|
172 | if true, ignore TikaException (give up to extract text but index meta data)</TD> |
---|
173 | </TR> |
---|
174 | <TR BGCOLOR="white" CLASS="TableRowColor"> |
---|
175 | <TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1"> |
---|
176 | <CODE>static <A HREF="http://download.oracle.com/javase/6/docs/api/java/lang/String.html?is-external=true" title="class or interface in java.lang">String</A></CODE></FONT></TD> |
---|
177 | <TD><CODE><B><A HREF="../../../../../org/apache/solr/handler/extraction/ExtractingParams.html#LITERALS_PREFIX">LITERALS_PREFIX</A></B></CODE> |
---|
178 | |
---|
179 | <BR> |
---|
180 | Pass in literal values to be added to the document, as in</TD> |
---|
181 | </TR> |
---|
182 | <TR BGCOLOR="white" CLASS="TableRowColor"> |
---|
183 | <TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1"> |
---|
184 | <CODE>static <A HREF="http://download.oracle.com/javase/6/docs/api/java/lang/String.html?is-external=true" title="class or interface in java.lang">String</A></CODE></FONT></TD> |
---|
185 | <TD><CODE><B><A HREF="../../../../../org/apache/solr/handler/extraction/ExtractingParams.html#LOWERNAMES">LOWERNAMES</A></B></CODE> |
---|
186 | |
---|
187 | <BR> |
---|
188 | Map all generated attribute names to field names with lowercase and underscores.</TD> |
---|
189 | </TR> |
---|
190 | <TR BGCOLOR="white" CLASS="TableRowColor"> |
---|
191 | <TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1"> |
---|
192 | <CODE>static <A HREF="http://download.oracle.com/javase/6/docs/api/java/lang/String.html?is-external=true" title="class or interface in java.lang">String</A></CODE></FONT></TD> |
---|
193 | <TD><CODE><B><A HREF="../../../../../org/apache/solr/handler/extraction/ExtractingParams.html#MAP_PREFIX">MAP_PREFIX</A></B></CODE> |
---|
194 | |
---|
195 | <BR> |
---|
196 | The param prefix for mapping Tika metadata to Solr fields.</TD> |
---|
197 | </TR> |
---|
198 | <TR BGCOLOR="white" CLASS="TableRowColor"> |
---|
199 | <TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1"> |
---|
200 | <CODE>static <A HREF="http://download.oracle.com/javase/6/docs/api/java/lang/String.html?is-external=true" title="class or interface in java.lang">String</A></CODE></FONT></TD> |
---|
201 | <TD><CODE><B><A HREF="../../../../../org/apache/solr/handler/extraction/ExtractingParams.html#RESOURCE_NAME">RESOURCE_NAME</A></B></CODE> |
---|
202 | |
---|
203 | <BR> |
---|
204 | Optional.</TD> |
---|
205 | </TR> |
---|
206 | <TR BGCOLOR="white" CLASS="TableRowColor"> |
---|
207 | <TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1"> |
---|
208 | <CODE>static <A HREF="http://download.oracle.com/javase/6/docs/api/java/lang/String.html?is-external=true" title="class or interface in java.lang">String</A></CODE></FONT></TD> |
---|
209 | <TD><CODE><B><A HREF="../../../../../org/apache/solr/handler/extraction/ExtractingParams.html#STREAM_TYPE">STREAM_TYPE</A></B></CODE> |
---|
210 | |
---|
211 | <BR> |
---|
212 | The type of the stream.</TD> |
---|
213 | </TR> |
---|
214 | <TR BGCOLOR="white" CLASS="TableRowColor"> |
---|
215 | <TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1"> |
---|
216 | <CODE>static <A HREF="http://download.oracle.com/javase/6/docs/api/java/lang/String.html?is-external=true" title="class or interface in java.lang">String</A></CODE></FONT></TD> |
---|
217 | <TD><CODE><B><A HREF="../../../../../org/apache/solr/handler/extraction/ExtractingParams.html#UNKNOWN_FIELD_PREFIX">UNKNOWN_FIELD_PREFIX</A></B></CODE> |
---|
218 | |
---|
219 | <BR> |
---|
220 | Optional.</TD> |
---|
221 | </TR> |
---|
222 | <TR BGCOLOR="white" CLASS="TableRowColor"> |
---|
223 | <TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1"> |
---|
224 | <CODE>static <A HREF="http://download.oracle.com/javase/6/docs/api/java/lang/String.html?is-external=true" title="class or interface in java.lang">String</A></CODE></FONT></TD> |
---|
225 | <TD><CODE><B><A HREF="../../../../../org/apache/solr/handler/extraction/ExtractingParams.html#XPATH_EXPRESSION">XPATH_EXPRESSION</A></B></CODE> |
---|
226 | |
---|
227 | <BR> |
---|
228 | Restrict the extracted parts of a document to be indexed |
---|
229 | by passing in an XPath expression.</TD> |
---|
230 | </TR> |
---|
231 | </TABLE> |
---|
232 | |
---|
233 | <P> |
---|
234 | |
---|
235 | <!-- ============ FIELD DETAIL =========== --> |
---|
236 | |
---|
237 | <A NAME="field_detail"><!-- --></A> |
---|
238 | <TABLE BORDER="1" WIDTH="100%" CELLPADDING="3" CELLSPACING="0" SUMMARY=""> |
---|
239 | <TR BGCOLOR="#CCCCFF" CLASS="TableHeadingColor"> |
---|
240 | <TH ALIGN="left" COLSPAN="1"><FONT SIZE="+2"> |
---|
241 | <B>Field Detail</B></FONT></TH> |
---|
242 | </TR> |
---|
243 | </TABLE> |
---|
244 | |
---|
245 | <A NAME="LOWERNAMES"><!-- --></A><H3> |
---|
246 | LOWERNAMES</H3> |
---|
247 | <PRE> |
---|
248 | static final <A HREF="http://download.oracle.com/javase/6/docs/api/java/lang/String.html?is-external=true" title="class or interface in java.lang">String</A> <B>LOWERNAMES</B></PRE> |
---|
249 | <DL> |
---|
250 | <DD>Map all generated attribute names to field names with lowercase and underscores. |
---|
251 | <P> |
---|
252 | <DL> |
---|
253 | <DT><B>See Also:</B><DD><A HREF="../../../../../constant-values.html#org.apache.solr.handler.extraction.ExtractingParams.LOWERNAMES">Constant Field Values</A></DL> |
---|
254 | </DL> |
---|
255 | <HR> |
---|
256 | |
---|
257 | <A NAME="IGNORE_TIKA_EXCEPTION"><!-- --></A><H3> |
---|
258 | IGNORE_TIKA_EXCEPTION</H3> |
---|
259 | <PRE> |
---|
260 | static final <A HREF="http://download.oracle.com/javase/6/docs/api/java/lang/String.html?is-external=true" title="class or interface in java.lang">String</A> <B>IGNORE_TIKA_EXCEPTION</B></PRE> |
---|
261 | <DL> |
---|
262 | <DD>if true, ignore TikaException (give up to extract text but index meta data) |
---|
263 | <P> |
---|
264 | <DL> |
---|
265 | <DT><B>See Also:</B><DD><A HREF="../../../../../constant-values.html#org.apache.solr.handler.extraction.ExtractingParams.IGNORE_TIKA_EXCEPTION">Constant Field Values</A></DL> |
---|
266 | </DL> |
---|
267 | <HR> |
---|
268 | |
---|
269 | <A NAME="MAP_PREFIX"><!-- --></A><H3> |
---|
270 | MAP_PREFIX</H3> |
---|
271 | <PRE> |
---|
272 | static final <A HREF="http://download.oracle.com/javase/6/docs/api/java/lang/String.html?is-external=true" title="class or interface in java.lang">String</A> <B>MAP_PREFIX</B></PRE> |
---|
273 | <DL> |
---|
274 | <DD>The param prefix for mapping Tika metadata to Solr fields. |
---|
275 | <p/> |
---|
276 | To map a field, add a name like: |
---|
277 | <pre>fmap.title=solr.title</pre> |
---|
278 | |
---|
279 | In this example, the tika "title" metadata value will be added to a Solr field named "solr.title" |
---|
280 | <P> |
---|
281 | <DL> |
---|
282 | <DT><B>See Also:</B><DD><A HREF="../../../../../constant-values.html#org.apache.solr.handler.extraction.ExtractingParams.MAP_PREFIX">Constant Field Values</A></DL> |
---|
283 | </DL> |
---|
284 | <HR> |
---|
285 | |
---|
286 | <A NAME="BOOST_PREFIX"><!-- --></A><H3> |
---|
287 | BOOST_PREFIX</H3> |
---|
288 | <PRE> |
---|
289 | static final <A HREF="http://download.oracle.com/javase/6/docs/api/java/lang/String.html?is-external=true" title="class or interface in java.lang">String</A> <B>BOOST_PREFIX</B></PRE> |
---|
290 | <DL> |
---|
291 | <DD>The boost value for the name of the field. The boost can be specified by a name mapping. |
---|
292 | <p/> |
---|
293 | For example |
---|
294 | <pre> |
---|
295 | map.title=solr.title |
---|
296 | boost.solr.title=2.5 |
---|
297 | </pre> |
---|
298 | will boost the solr.title field for this document by 2.5 |
---|
299 | <P> |
---|
300 | <DL> |
---|
301 | <DT><B>See Also:</B><DD><A HREF="../../../../../constant-values.html#org.apache.solr.handler.extraction.ExtractingParams.BOOST_PREFIX">Constant Field Values</A></DL> |
---|
302 | </DL> |
---|
303 | <HR> |
---|
304 | |
---|
305 | <A NAME="LITERALS_PREFIX"><!-- --></A><H3> |
---|
306 | LITERALS_PREFIX</H3> |
---|
307 | <PRE> |
---|
308 | static final <A HREF="http://download.oracle.com/javase/6/docs/api/java/lang/String.html?is-external=true" title="class or interface in java.lang">String</A> <B>LITERALS_PREFIX</B></PRE> |
---|
309 | <DL> |
---|
310 | <DD>Pass in literal values to be added to the document, as in |
---|
311 | <pre> |
---|
312 | literal.myField=Foo |
---|
313 | </pre> |
---|
314 | <P> |
---|
315 | <DL> |
---|
316 | <DT><B>See Also:</B><DD><A HREF="../../../../../constant-values.html#org.apache.solr.handler.extraction.ExtractingParams.LITERALS_PREFIX">Constant Field Values</A></DL> |
---|
317 | </DL> |
---|
318 | <HR> |
---|
319 | |
---|
320 | <A NAME="XPATH_EXPRESSION"><!-- --></A><H3> |
---|
321 | XPATH_EXPRESSION</H3> |
---|
322 | <PRE> |
---|
323 | static final <A HREF="http://download.oracle.com/javase/6/docs/api/java/lang/String.html?is-external=true" title="class or interface in java.lang">String</A> <B>XPATH_EXPRESSION</B></PRE> |
---|
324 | <DL> |
---|
325 | <DD>Restrict the extracted parts of a document to be indexed |
---|
326 | by passing in an XPath expression. All content that satisfies the XPath expr. |
---|
327 | will be passed to the <A HREF="../../../../../org/apache/solr/handler/extraction/SolrContentHandler.html" title="class in org.apache.solr.handler.extraction"><CODE>SolrContentHandler</CODE></A>. |
---|
328 | <p/> |
---|
329 | See Tika's docs for what the extracted document looks like. |
---|
330 | <p/> |
---|
331 | <P> |
---|
332 | <DL> |
---|
333 | <DT><B>See Also:</B><DD><A HREF="../../../../../org/apache/solr/handler/extraction/ExtractingParams.html#CAPTURE_ELEMENTS"><CODE>CAPTURE_ELEMENTS</CODE></A>, |
---|
334 | <A HREF="../../../../../constant-values.html#org.apache.solr.handler.extraction.ExtractingParams.XPATH_EXPRESSION">Constant Field Values</A></DL> |
---|
335 | </DL> |
---|
336 | <HR> |
---|
337 | |
---|
338 | <A NAME="EXTRACT_ONLY"><!-- --></A><H3> |
---|
339 | EXTRACT_ONLY</H3> |
---|
340 | <PRE> |
---|
341 | static final <A HREF="http://download.oracle.com/javase/6/docs/api/java/lang/String.html?is-external=true" title="class or interface in java.lang">String</A> <B>EXTRACT_ONLY</B></PRE> |
---|
342 | <DL> |
---|
343 | <DD>Only extract and return the content, do not index it. |
---|
344 | <P> |
---|
345 | <DL> |
---|
346 | <DT><B>See Also:</B><DD><A HREF="../../../../../constant-values.html#org.apache.solr.handler.extraction.ExtractingParams.EXTRACT_ONLY">Constant Field Values</A></DL> |
---|
347 | </DL> |
---|
348 | <HR> |
---|
349 | |
---|
350 | <A NAME="EXTRACT_FORMAT"><!-- --></A><H3> |
---|
351 | EXTRACT_FORMAT</H3> |
---|
352 | <PRE> |
---|
353 | static final <A HREF="http://download.oracle.com/javase/6/docs/api/java/lang/String.html?is-external=true" title="class or interface in java.lang">String</A> <B>EXTRACT_FORMAT</B></PRE> |
---|
354 | <DL> |
---|
355 | <DD>Content output format if extractOnly is true. Default is "xml", alternative is "text". |
---|
356 | <P> |
---|
357 | <DL> |
---|
358 | <DT><B>See Also:</B><DD><A HREF="../../../../../constant-values.html#org.apache.solr.handler.extraction.ExtractingParams.EXTRACT_FORMAT">Constant Field Values</A></DL> |
---|
359 | </DL> |
---|
360 | <HR> |
---|
361 | |
---|
362 | <A NAME="CAPTURE_ATTRIBUTES"><!-- --></A><H3> |
---|
363 | CAPTURE_ATTRIBUTES</H3> |
---|
364 | <PRE> |
---|
365 | static final <A HREF="http://download.oracle.com/javase/6/docs/api/java/lang/String.html?is-external=true" title="class or interface in java.lang">String</A> <B>CAPTURE_ATTRIBUTES</B></PRE> |
---|
366 | <DL> |
---|
367 | <DD>Capture attributes separately according to the name of the element, instead of just adding them to the string buffer |
---|
368 | <P> |
---|
369 | <DL> |
---|
370 | <DT><B>See Also:</B><DD><A HREF="../../../../../constant-values.html#org.apache.solr.handler.extraction.ExtractingParams.CAPTURE_ATTRIBUTES">Constant Field Values</A></DL> |
---|
371 | </DL> |
---|
372 | <HR> |
---|
373 | |
---|
374 | <A NAME="CAPTURE_ELEMENTS"><!-- --></A><H3> |
---|
375 | CAPTURE_ELEMENTS</H3> |
---|
376 | <PRE> |
---|
377 | static final <A HREF="http://download.oracle.com/javase/6/docs/api/java/lang/String.html?is-external=true" title="class or interface in java.lang">String</A> <B>CAPTURE_ELEMENTS</B></PRE> |
---|
378 | <DL> |
---|
379 | <DD>Capture the specified fields (and everything included below it that isn't capture by some other capture field) separately from the default. This is different |
---|
380 | then the case of passing in an XPath expression. |
---|
381 | <p/> |
---|
382 | The Capture field is based on the localName returned to the <A HREF="../../../../../org/apache/solr/handler/extraction/SolrContentHandler.html" title="class in org.apache.solr.handler.extraction"><CODE>SolrContentHandler</CODE></A> |
---|
383 | by Tika, not to be confused by the mapped field. The field name can then |
---|
384 | be mapped into the index schema. |
---|
385 | <p/> |
---|
386 | For instance, a Tika document may look like: |
---|
387 | <pre> |
---|
388 | <html> |
---|
389 | ... |
---|
390 | <body> |
---|
391 | <p>some text here. <div>more text</div></p> |
---|
392 | Some more text |
---|
393 | </body> |
---|
394 | </pre> |
---|
395 | By passing in the p tag, you could capture all P tags separately from the rest of the t |
---|
396 | Thus, in the example, the capture of the P tag would be: "some text here. more text" |
---|
397 | <P> |
---|
398 | <DL> |
---|
399 | <DT><B>See Also:</B><DD><A HREF="../../../../../constant-values.html#org.apache.solr.handler.extraction.ExtractingParams.CAPTURE_ELEMENTS">Constant Field Values</A></DL> |
---|
400 | </DL> |
---|
401 | <HR> |
---|
402 | |
---|
403 | <A NAME="STREAM_TYPE"><!-- --></A><H3> |
---|
404 | STREAM_TYPE</H3> |
---|
405 | <PRE> |
---|
406 | static final <A HREF="http://download.oracle.com/javase/6/docs/api/java/lang/String.html?is-external=true" title="class or interface in java.lang">String</A> <B>STREAM_TYPE</B></PRE> |
---|
407 | <DL> |
---|
408 | <DD>The type of the stream. If not specified, Tika will use mime type detection. |
---|
409 | <P> |
---|
410 | <DL> |
---|
411 | <DT><B>See Also:</B><DD><A HREF="../../../../../constant-values.html#org.apache.solr.handler.extraction.ExtractingParams.STREAM_TYPE">Constant Field Values</A></DL> |
---|
412 | </DL> |
---|
413 | <HR> |
---|
414 | |
---|
415 | <A NAME="RESOURCE_NAME"><!-- --></A><H3> |
---|
416 | RESOURCE_NAME</H3> |
---|
417 | <PRE> |
---|
418 | static final <A HREF="http://download.oracle.com/javase/6/docs/api/java/lang/String.html?is-external=true" title="class or interface in java.lang">String</A> <B>RESOURCE_NAME</B></PRE> |
---|
419 | <DL> |
---|
420 | <DD>Optional. The file name. If specified, Tika can take this into account while |
---|
421 | guessing the MIME type. |
---|
422 | <P> |
---|
423 | <DL> |
---|
424 | <DT><B>See Also:</B><DD><A HREF="../../../../../constant-values.html#org.apache.solr.handler.extraction.ExtractingParams.RESOURCE_NAME">Constant Field Values</A></DL> |
---|
425 | </DL> |
---|
426 | <HR> |
---|
427 | |
---|
428 | <A NAME="UNKNOWN_FIELD_PREFIX"><!-- --></A><H3> |
---|
429 | UNKNOWN_FIELD_PREFIX</H3> |
---|
430 | <PRE> |
---|
431 | static final <A HREF="http://download.oracle.com/javase/6/docs/api/java/lang/String.html?is-external=true" title="class or interface in java.lang">String</A> <B>UNKNOWN_FIELD_PREFIX</B></PRE> |
---|
432 | <DL> |
---|
433 | <DD>Optional. If specified, the prefix will be prepended to all Metadata, such that it would be possible |
---|
434 | to setup a dynamic field to automatically capture it |
---|
435 | <P> |
---|
436 | <DL> |
---|
437 | <DT><B>See Also:</B><DD><A HREF="../../../../../constant-values.html#org.apache.solr.handler.extraction.ExtractingParams.UNKNOWN_FIELD_PREFIX">Constant Field Values</A></DL> |
---|
438 | </DL> |
---|
439 | <HR> |
---|
440 | |
---|
441 | <A NAME="DEFAULT_FIELD"><!-- --></A><H3> |
---|
442 | DEFAULT_FIELD</H3> |
---|
443 | <PRE> |
---|
444 | static final <A HREF="http://download.oracle.com/javase/6/docs/api/java/lang/String.html?is-external=true" title="class or interface in java.lang">String</A> <B>DEFAULT_FIELD</B></PRE> |
---|
445 | <DL> |
---|
446 | <DD>Optional. If specified and the name of a potential field cannot be determined, the default Field specified |
---|
447 | will be used instead. |
---|
448 | <P> |
---|
449 | <DL> |
---|
450 | <DT><B>See Also:</B><DD><A HREF="../../../../../constant-values.html#org.apache.solr.handler.extraction.ExtractingParams.DEFAULT_FIELD">Constant Field Values</A></DL> |
---|
451 | </DL> |
---|
452 | <!-- ========= END OF CLASS DATA ========= --> |
---|
453 | <HR> |
---|
454 | |
---|
455 | |
---|
456 | <!-- ======= START OF BOTTOM NAVBAR ====== --> |
---|
457 | <A NAME="navbar_bottom"><!-- --></A> |
---|
458 | <A HREF="#skip-navbar_bottom" title="Skip navigation links"></A> |
---|
459 | <TABLE BORDER="0" WIDTH="100%" CELLPADDING="1" CELLSPACING="0" SUMMARY=""> |
---|
460 | <TR> |
---|
461 | <TD COLSPAN=2 BGCOLOR="#EEEEFF" CLASS="NavBarCell1"> |
---|
462 | <A NAME="navbar_bottom_firstrow"><!-- --></A> |
---|
463 | <TABLE BORDER="0" CELLPADDING="0" CELLSPACING="3" SUMMARY=""> |
---|
464 | <TR ALIGN="center" VALIGN="top"> |
---|
465 | <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1"> <A HREF="../../../../../overview-summary.html"><FONT CLASS="NavBarFont1"><B>Overview</B></FONT></A> </TD> |
---|
466 | <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1"> <A HREF="package-summary.html"><FONT CLASS="NavBarFont1"><B>Package</B></FONT></A> </TD> |
---|
467 | <TD BGCOLOR="#FFFFFF" CLASS="NavBarCell1Rev"> <FONT CLASS="NavBarFont1Rev"><B>Class</B></FONT> </TD> |
---|
468 | <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1"> <A HREF="class-use/ExtractingParams.html"><FONT CLASS="NavBarFont1"><B>Use</B></FONT></A> </TD> |
---|
469 | <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1"> <A HREF="package-tree.html"><FONT CLASS="NavBarFont1"><B>Tree</B></FONT></A> </TD> |
---|
470 | <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1"> <A HREF="../../../../../deprecated-list.html"><FONT CLASS="NavBarFont1"><B>Deprecated</B></FONT></A> </TD> |
---|
471 | <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1"> <A HREF="../../../../../help-doc.html"><FONT CLASS="NavBarFont1"><B>Help</B></FONT></A> </TD> |
---|
472 | </TR> |
---|
473 | </TABLE> |
---|
474 | </TD> |
---|
475 | <TD ALIGN="right" VALIGN="top" ROWSPAN=3><EM> |
---|
476 | </EM> |
---|
477 | </TD> |
---|
478 | </TR> |
---|
479 | |
---|
480 | <TR> |
---|
481 | <TD BGCOLOR="white" CLASS="NavBarCell2"><FONT SIZE="-2"> |
---|
482 | <A HREF="../../../../../org/apache/solr/handler/extraction/ExtractingMetadataConstants.html" title="interface in org.apache.solr.handler.extraction"><B>PREV CLASS</B></A> |
---|
483 | <A HREF="../../../../../org/apache/solr/handler/extraction/ExtractingRequestHandler.html" title="class in org.apache.solr.handler.extraction"><B>NEXT CLASS</B></A></FONT></TD> |
---|
484 | <TD BGCOLOR="white" CLASS="NavBarCell2"><FONT SIZE="-2"> |
---|
485 | <A HREF="../../../../../index.html?org/apache/solr/handler/extraction/ExtractingParams.html" target="_top"><B>FRAMES</B></A> |
---|
486 | <A HREF="ExtractingParams.html" target="_top"><B>NO FRAMES</B></A> |
---|
487 | <SCRIPT type="text/javascript"> |
---|
488 | <!-- |
---|
489 | if(window==top) { |
---|
490 | document.writeln('<A HREF="../../../../../allclasses-noframe.html"><B>All Classes</B></A>'); |
---|
491 | } |
---|
492 | //--> |
---|
493 | </SCRIPT> |
---|
494 | <NOSCRIPT> |
---|
495 | <A HREF="../../../../../allclasses-noframe.html"><B>All Classes</B></A> |
---|
496 | </NOSCRIPT> |
---|
497 | |
---|
498 | |
---|
499 | </FONT></TD> |
---|
500 | </TR> |
---|
501 | <TR> |
---|
502 | <TD VALIGN="top" CLASS="NavBarCell3"><FONT SIZE="-2"> |
---|
503 | SUMMARY: NESTED | <A HREF="#field_summary">FIELD</A> | CONSTR | METHOD</FONT></TD> |
---|
504 | <TD VALIGN="top" CLASS="NavBarCell3"><FONT SIZE="-2"> |
---|
505 | DETAIL: <A HREF="#field_detail">FIELD</A> | CONSTR | METHOD</FONT></TD> |
---|
506 | </TR> |
---|
507 | </TABLE> |
---|
508 | <A NAME="skip-navbar_bottom"></A> |
---|
509 | <!-- ======== END OF BOTTOM NAVBAR ======= --> |
---|
510 | |
---|
511 | <HR> |
---|
512 | |
---|
513 | <address>Copyright © 2000-2012 Apache Software Foundation. All Rights Reserved.</address> |
---|
514 | <script src='../../../../../prettify.js' type='text/javascript'></script> |
---|
515 | <script type='text/javascript'> |
---|
516 | (function(){ |
---|
517 | var oldonload = window.onload; |
---|
518 | if (typeof oldonload != 'function') { |
---|
519 | window.onload = prettyPrint; |
---|
520 | } else { |
---|
521 | window.onload = function() { |
---|
522 | oldonload(); |
---|
523 | prettyPrint(); |
---|
524 | } |
---|
525 | } |
---|
526 | })(); |
---|
527 | </script> |
---|
528 | |
---|
529 | </BODY> |
---|
530 | </HTML> |
---|