mirror of https://github.com/apache/lucene.git
fix some more broken links...
git-svn-id: https://svn.apache.org/repos/asf/lucene/dev/trunk@1328975 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
Michael McCandless
parent
5e94b7530c
commit
b534190141
|
|
@ -154,7 +154,26 @@ def checkAll(dirName):
|
|||
# TODO: normalize path sep for windows...
|
||||
if link.startswith('http://') or link.startswith('https://'):
|
||||
# don't check external links
|
||||
|
||||
if link.find('lucene.apache.org/java/docs/mailinglists.html') != -1:
|
||||
# OK
|
||||
pass
|
||||
elif link.find('lucene.apache.org/java/docs/discussion.html') != -1:
|
||||
# OK
|
||||
pass
|
||||
elif link.find('svn.apache.org') != -1 or link.find('lucene.apache.org') != -1:
|
||||
if not printed:
|
||||
printed = True
|
||||
print
|
||||
print fullPath
|
||||
print ' BAD EXTERNAL LINK: %s' % link
|
||||
elif link.startswith('mailto://'):
|
||||
if link.find('@lucene.apache.org') == -1 and link.find('@apache.org') != -1:
|
||||
if not printed:
|
||||
printed = True
|
||||
print
|
||||
print fullPath
|
||||
print ' BROKEN MAILTO (?): %s' % link
|
||||
elif link not in allFiles:
|
||||
# We only load HTML... so if the link is another resource (eg
|
||||
# SweetSpotSimilarity refs
|
||||
|
|
|
|||
|
|
@ -33,6 +33,8 @@ import org.apache.lucene.util.Version;
|
|||
/**
|
||||
* Base class for decomposition token filters.
|
||||
* <p>
|
||||
*
|
||||
* <a name="version"></a>
|
||||
* You must specify the required {@link Version} compatibility when creating
|
||||
* CompoundWordTokenFilterBase:
|
||||
* <ul>
|
||||
|
|
|
|||
|
|
@ -48,7 +48,7 @@ public class DictionaryCompoundWordTokenFilter extends CompoundWordTokenFilterBa
|
|||
* @param matchVersion
|
||||
* Lucene version to enable correct Unicode 4.0 behavior in the
|
||||
* dictionaries if Version > 3.0. See <a
|
||||
* href="CompoundWordTokenFilterBase#version"
|
||||
* href="CompoundWordTokenFilterBase.html#version"
|
||||
* >CompoundWordTokenFilterBase</a> for details.
|
||||
* @param input
|
||||
* the {@link TokenStream} to process
|
||||
|
|
@ -65,7 +65,7 @@ public class DictionaryCompoundWordTokenFilter extends CompoundWordTokenFilterBa
|
|||
* @param matchVersion
|
||||
* Lucene version to enable correct Unicode 4.0 behavior in the
|
||||
* dictionaries if Version > 3.0. See <a
|
||||
* href="CompoundWordTokenFilterBase#version"
|
||||
* href="CompoundWordTokenFilterBase.html#version"
|
||||
* >CompoundWordTokenFilterBase</a> for details.
|
||||
* @param input
|
||||
* the {@link TokenStream} to process
|
||||
|
|
|
|||
|
|
@ -52,7 +52,7 @@ public class HyphenationCompoundWordTokenFilter extends
|
|||
* @param matchVersion
|
||||
* Lucene version to enable correct Unicode 4.0 behavior in the
|
||||
* dictionaries if Version > 3.0. See <a
|
||||
* href="CompoundWordTokenFilterBase#version"
|
||||
* href="CompoundWordTokenFilterBase.html#version"
|
||||
* >CompoundWordTokenFilterBase</a> for details.
|
||||
* @param input
|
||||
* the {@link TokenStream} to process
|
||||
|
|
@ -73,7 +73,7 @@ public class HyphenationCompoundWordTokenFilter extends
|
|||
* @param matchVersion
|
||||
* Lucene version to enable correct Unicode 4.0 behavior in the
|
||||
* dictionaries if Version > 3.0. See <a
|
||||
* href="CompoundWordTokenFilterBase#version"
|
||||
* href="CompoundWordTokenFilterBase.html#version"
|
||||
* >CompoundWordTokenFilterBase</a> for details.
|
||||
* @param input
|
||||
* the {@link TokenStream} to process
|
||||
|
|
|
|||
|
|
@ -26,7 +26,7 @@ Fast, general-purpose grammar-based tokenizers.
|
|||
<p>The <code>org.apache.lucene.analysis.standard</code> package contains three
|
||||
fast grammar-based tokenizers constructed with JFlex:</p>
|
||||
<ul>
|
||||
<li><code><a href="StandardTokenizer.html">StandardTokenizer</a></code>:
|
||||
<li>{@link org.apache.lucene.analysis.standard.StandardTokenizer}:
|
||||
as of Lucene 3.1, implements the Word Break rules from the Unicode Text
|
||||
Segmentation algorithm, as specified in
|
||||
<a href="http://unicode.org/reports/tr29/">Unicode Standard Annex #29</a>.
|
||||
|
|
@ -34,35 +34,35 @@ Fast, general-purpose grammar-based tokenizers.
|
|||
<b>not</b> tokenized as single tokens, but are instead split up into
|
||||
tokens according to the UAX#29 word break rules.
|
||||
<br/>
|
||||
<code><a href="StandardAnalyzer">StandardAnalyzer</a></code> includes
|
||||
<code>StandardTokenizer</code>,
|
||||
<code><a href="StandardFilter">StandardFilter</a></code>,
|
||||
<code><a href="../../../../../../all/org/apache/lucene/analysis/LowerCaseFilter.html">LowerCaseFilter</a></code>
|
||||
and <code><a href="../../../../../../all/org/apache/lucene/analysis/StopFilter.html">StopFilter</a></code>.
|
||||
{@link org.apache.lucene.analysis.standard.StandardAnalyzer StandardAnalyzer} includes
|
||||
{@link org.apache.lucene.analysis.standard.StandardTokenizer StandardTokenizer},
|
||||
{@link org.apache.lucene.analysis.standard.StandardFilter StandardFilter},
|
||||
{@link org.apache.lucene.analysis.core.LowerCaseFilter LowerCaseFilter}
|
||||
and {@link org.apache.lucene.analysis.core.StopFilter StopFilter}.
|
||||
When the <code>Version</code> specified in the constructor is lower than
|
||||
3.1, the <code><a href="ClassicTokenizer.html">ClassicTokenizer</a></code>
|
||||
3.1, the {@link org.apache.lucene.analysis.standard.ClassicTokenizer ClassicTokenizer}
|
||||
implementation is invoked.</li>
|
||||
<li><code><a href="ClassicTokenizer.html">ClassicTokenizer</a></code>:
|
||||
<li>{@link org.apache.lucene.analysis.standard.ClassicTokenizer ClassicTokenizer}:
|
||||
this class was formerly (prior to Lucene 3.1) named
|
||||
<code>StandardTokenizer</code>. (Its tokenization rules are not
|
||||
based on the Unicode Text Segmentation algorithm.)
|
||||
<code><a href="ClassicAnalyzer">ClassicAnalyzer</a></code> includes
|
||||
<code>ClassicTokenizer</code>,
|
||||
<code><a href="StandardFilter">StandardFilter</a></code>,
|
||||
<code><a href="../../../../../../all/org/apache/lucene/analysis/LowerCaseFilter.html">LowerCaseFilter</a></code>
|
||||
and <code><a href="../../../../../../all/org/apache/lucene/analysis/StopFilter.html">StopFilter</a></code>.
|
||||
{@link org.apache.lucene.analysis.standard.ClassicAnalyzer ClassicAnalyzer} includes
|
||||
{@link org.apache.lucene.analysis.standard.ClassicTokenizer ClassicTokenizer},
|
||||
{@link org.apache.lucene.analysis.standard.StandardFilter StandardFilter},
|
||||
{@link org.apache.lucene.analysis.core.LowerCaseFilter LowerCaseFilter}
|
||||
and {@link org.apache.lucene.analysis.core.StopFilter StopFilter}.
|
||||
</li>
|
||||
<li><code><a href="UAX29URLEmailTokenizer.html">UAX29URLEmailTokenizer</a></code>:
|
||||
<li>{@link org.apache.lucene.analysis.standard.UAX29URLEmailTokenizer UAX29URLEmailTokenizer}:
|
||||
implements the Word Break rules from the Unicode Text Segmentation
|
||||
algorithm, as specified in
|
||||
<a href="http://unicode.org/reports/tr29/">Unicode Standard Annex #29</a>.
|
||||
URLs and email addresses are also tokenized according to the relevant RFCs.
|
||||
<br/>
|
||||
<code><a href="UAX29URLEmailAnalyzer">UAX29URLEmailAnalyzer</a></code> includes
|
||||
<code>UAX29URLEmailTokenizer</code>,
|
||||
<code><a href="StandardFilter">StandardFilter</a></code>,
|
||||
<code><a href="../../../../../../all/org/apache/lucene/analysis/LowerCaseFilter.html">LowerCaseFilter</a></code>
|
||||
and <code><a href="../../../../../../all/org/apache/lucene/analysis/StopFilter.html">StopFilter</a></code>.
|
||||
{@link org.apache.lucene.analysis.standard.UAX29URLEmailAnalyzer UAX29URLEmailAnalyzer} includes
|
||||
{@link org.apache.lucene.analysis.standard.UAX29URLEmailTokenizer UAX29URLEmailTokenizer},
|
||||
{@link org.apache.lucene.analysis.standard.StandardFilter StandardFilter},
|
||||
{@link org.apache.lucene.analysis.core.LowerCaseFilter LowerCaseFilter}
|
||||
and {@link org.apache.lucene.analysis.core.StopFilter StopFilter}.
|
||||
</li>
|
||||
</ul>
|
||||
</body>
|
||||
|
|
|
|||
|
|
@ -36,6 +36,8 @@ import org.apache.lucene.util.Version;
|
|||
* etc. It is designed to be quick to retrieve items
|
||||
* by char[] keys without the necessity of converting
|
||||
* to a String first.
|
||||
*
|
||||
* <a name="version"></a>
|
||||
* <p>You must specify the required {@link Version}
|
||||
* compatibility when creating {@link CharArrayMap}:
|
||||
* <ul>
|
||||
|
|
@ -120,12 +122,12 @@ public class CharArrayMap<V> extends AbstractMap<Object,V> {
|
|||
}
|
||||
|
||||
/** true if the <code>len</code> chars of <code>text</code> starting at <code>off</code>
|
||||
* are in the {@link #keySet} */
|
||||
* are in the {@link #keySet()} */
|
||||
public boolean containsKey(char[] text, int off, int len) {
|
||||
return keys[getSlot(text, off, len)] != null;
|
||||
}
|
||||
|
||||
/** true if the <code>CharSequence</code> is in the {@link #keySet} */
|
||||
/** true if the <code>CharSequence</code> is in the {@link #keySet()} */
|
||||
public boolean containsKey(CharSequence cs) {
|
||||
return keys[getSlot(cs)] != null;
|
||||
}
|
||||
|
|
|
|||
|
|
@ -33,6 +33,8 @@ import org.apache.lucene.util.Version;
|
|||
* etc. It is designed to be quick to test if a char[]
|
||||
* is in the set without the necessity of converting it
|
||||
* to a String first.
|
||||
*
|
||||
* <a name="version"></a>
|
||||
* <p>You must specify the required {@link Version}
|
||||
* compatibility when creating {@link CharArraySet}:
|
||||
* <ul>
|
||||
|
|
|
|||
|
|
@ -100,7 +100,7 @@ public final class JapaneseTokenizer extends Tokenizer {
|
|||
*/
|
||||
public static final Mode DEFAULT_MODE = Mode.SEARCH;
|
||||
|
||||
enum Type {
|
||||
public enum Type {
|
||||
KNOWN,
|
||||
UNKNOWN,
|
||||
USER
|
||||
|
|
|
|||
Loading…
Reference in New Issue