This is an automated email from the ASF dual-hosted git repository.
dsmiley pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/solr.git
The following commit(s) were added to refs/heads/main by this push:
new 9dee381 SOLR-15259: hl.fragAlignRatio now defaults to 0.33 (#573)
9dee381 is described below
commit 9dee3815edb07de3081a4d6f9f558e00c5adc6f6
Author: David Smiley <[email protected]>
AuthorDate: Sat Feb 5 16:42:55 2022 -0500
SOLR-15259: hl.fragAlignRatio now defaults to 0.33 (#573)
to be faster and maybe looks nicer.
---
solr/CHANGES.txt | 3 +++
.../solr/highlight/UnifiedSolrHighlighter.java | 2 +-
.../solr/highlight/TestUnifiedSolrHighlighter.java | 24 +++++++++++++---------
solr/solr-ref-guide/src/highlighting.adoc | 4 ++--
.../src/major-changes-in-solr-9.adoc | 2 ++
5 files changed, 22 insertions(+), 13 deletions(-)
diff --git a/solr/CHANGES.txt b/solr/CHANGES.txt
index d2929c7..1b9b051 100644
--- a/solr/CHANGES.txt
+++ b/solr/CHANGES.txt
@@ -600,6 +600,9 @@ Bug Fixes
* SOLR-15919: Replace File with Path for many ZK operations (Mike Drob)
+
+* SOLR-15259: hl.fragAlignRatio now defaults to 0.33 to be faster and maybe
looks nicer. (David Smiley)
+
* SOLR-13138: Removed deprecated hl.method=postings highlighter, deprecated in
7.0. (David Smiley)
* SOLR-15944: The Tagger's JSON response format now always uses an object/map
to represent each tag instead of an
diff --git
a/solr/core/src/java/org/apache/solr/highlight/UnifiedSolrHighlighter.java
b/solr/core/src/java/org/apache/solr/highlight/UnifiedSolrHighlighter.java
index 4c56200..8d25d31 100644
--- a/solr/core/src/java/org/apache/solr/highlight/UnifiedSolrHighlighter.java
+++ b/solr/core/src/java/org/apache/solr/highlight/UnifiedSolrHighlighter.java
@@ -329,7 +329,7 @@ public class UnifiedSolrHighlighter extends SolrHighlighter
implements PluginInf
return baseBI;
}
- float fragalign = params.getFieldFloat(field,
HighlightParams.FRAGALIGNRATIO, 0.5f);
+ float fragalign = params.getFieldFloat(field,
HighlightParams.FRAGALIGNRATIO, 0.33f);
if (params.getFieldBool(field, HighlightParams.FRAGSIZEISMINIMUM, true))
{
return LengthGoalBreakIterator.createMinLength(baseBI, fragsize,
fragalign);
}
diff --git
a/solr/core/src/test/org/apache/solr/highlight/TestUnifiedSolrHighlighter.java
b/solr/core/src/test/org/apache/solr/highlight/TestUnifiedSolrHighlighter.java
index 3a2a70e..07b6d30 100644
---
a/solr/core/src/test/org/apache/solr/highlight/TestUnifiedSolrHighlighter.java
+++
b/solr/core/src/test/org/apache/solr/highlight/TestUnifiedSolrHighlighter.java
@@ -246,24 +246,26 @@ public class TestUnifiedSolrHighlighter extends
SolrTestCaseJ4 {
assertU(adoc("text", "This document contains # special characters, while
the other document contains the same # special character.", "id", "103"));
assertU(adoc("text", "While the other document contains the same # special
character.", "id", "104"));
assertU(commit());
+ // Set hl.fragAlignRatio because this test was written when it had a
middle default
+ String[] defParams = {"q", "text:document", "sort", "id asc", "hl",
"true", "hl.method", "unified", "hl.bs.type",
"SEPARATOR","hl.bs.separator","#", "hl.fragAlignRatio", "0.5"};
assertQ("CUSTOM breakiterator",
- req("q", "text:document", "sort", "id asc", "hl", "true",
"hl.bs.type", "SEPARATOR","hl.bs.separator","#","hl.fragsize", "-1"),
+ req(defParams,"hl.fragsize", "-1"),
"//lst[@name='highlighting']/lst[@name='103']/arr[@name='text']/str='This
<em>document</em> contains #'");
assertQ("different breakiterator",
- req("q", "text:document", "sort", "id asc", "hl", "true",
"hl.bs.type", "SEPARATOR","hl.bs.separator","#","hl.fragsize", "-1"),
+ req(defParams,"hl.fragsize", "-1"),
"//lst[@name='highlighting']/lst[@name='104']/arr[@name='text']/str='While the
other <em>document</em> contains the same #'");
assertQ("CUSTOM breakiterator with fragsize 70 minimum",
- req("q", "text:document", "sort", "id asc", "hl", "true",
"hl.bs.type", "SEPARATOR","hl.bs.separator","#","hl.fragsize", "70",
"hl.fragsizeIsMinimum", "true"),
+ req(defParams,"hl.fragsize", "70", "hl.fragsizeIsMinimum", "true"),
"//lst[@name='highlighting']/lst[@name='103']/arr[@name='text']/str='This
<em>document</em> contains # special characters, while the other
<em>document</em> contains the same #'");
assertQ("CUSTOM breakiterator with fragsize 70 avg",
- req("q", "text:document", "sort", "id asc", "hl", "true",
"hl.bs.type", "SEPARATOR","hl.bs.separator","#","hl.fragsize", "70",
"hl.fragsizeIsMinimum", "false"),
+ req(defParams,"hl.fragsize", "70", "hl.fragsizeIsMinimum", "false"),
"//lst[@name='highlighting']/lst[@name='103']/arr[@name='text']/str='This
<em>document</em> contains #'");
assertQ("CUSTOM breakiterator with fragsize 90 avg",
- req("q", "text:document", "sort", "id asc", "hl", "true",
"hl.bs.type", "SEPARATOR","hl.bs.separator","#","hl.fragsize", "90",
"hl.fragsizeIsMinimum", "false"),
+ req(defParams,"hl.fragsize", "90", "hl.fragsizeIsMinimum", "false"),
"//lst[@name='highlighting']/lst[@name='103']/arr[@name='text']/str='This
<em>document</em> contains #'");
assertQ("CUSTOM breakiterator with fragsize 100 avg",
- req("q", "text:document", "sort", "id asc", "hl", "true",
"hl.bs.type", "SEPARATOR","hl.bs.separator","#","hl.fragsize", "100",
"hl.fragsizeIsMinimum", "false"),
+ req(defParams,"hl.fragsize", "100", "hl.fragsizeIsMinimum", "false"),
"//lst[@name='highlighting']/lst[@name='103']/arr[@name='text']/str='This
<em>document</em> contains # special characters, while the other
<em>document</em> contains the same #'");
}
@@ -272,17 +274,19 @@ public class TestUnifiedSolrHighlighter extends
SolrTestCaseJ4 {
clearIndex();
assertU(adoc("id", "10", "text", "This is a sentence just under seventy
chars in length blah blah. Next sentence is here."));
assertU(commit());
+ // Set hl.fragAlignRatio because this test was written when it had a
middle default
+ String[] defParams = {"q", "text:seventy", "hl", "true", "hl.method",
"unified", "hl.fragAlignRatio", "0.5"};
assertQ("default fragsize",
- req("q", "text:seventy", "hl", "true", "hl.fragsizeIsMinimum", "true"),
+ req(defParams, "hl.fragsizeIsMinimum", "true"),
"//lst[@name='highlighting']/lst[@name='10']/arr[@name='text']/str='This is a
sentence just under <em>seventy</em> chars in length blah blah. Next sentence
is here.'");
assertQ("default fragsize",
- req("q", "text:seventy", "hl", "true", "hl.fragsizeIsMinimum", "true",
"hl.fragsize", "60"),
+ req(defParams, "hl.fragsizeIsMinimum", "true", "hl.fragsize", "60"),
"//lst[@name='highlighting']/lst[@name='10']/arr[@name='text']/str='This is a
sentence just under <em>seventy</em> chars in length blah blah. '");
assertQ("smaller fragsize",
- req("q", "text:seventy", "hl", "true", "hl.fragsizeIsMinimum",
"false"),
+ req(defParams, "hl.fragsizeIsMinimum", "false"),
"//lst[@name='highlighting']/lst[@name='10']/arr[@name='text']/str='This is a
sentence just under <em>seventy</em> chars in length blah blah. '");
assertQ("default fragsize",
- req("q", "text:seventy", "hl", "true", "hl.fragsize", "90",
"hl.fragsizeIsMinimum", "false"),
+ req(defParams, "hl.fragsize", "90", "hl.fragsizeIsMinimum", "false"),
"//lst[@name='highlighting']/lst[@name='10']/arr[@name='text']/str='This is a
sentence just under <em>seventy</em> chars in length blah blah. Next sentence
is here.'");
}
diff --git a/solr/solr-ref-guide/src/highlighting.adoc
b/solr/solr-ref-guide/src/highlighting.adoc
index 3306c3f..38976d0 100644
--- a/solr/solr-ref-guide/src/highlighting.adoc
+++ b/solr/solr-ref-guide/src/highlighting.adoc
@@ -359,12 +359,12 @@ The offset source can be explicitly configured to one of:
`ANALYSIS`, `POSTINGS`
+
[%autowidth,frame=none]
|===
-|Optional |Default: `0.5`
+|Optional |Default: `0.33`
|===
+
This parameter influences where the first match (i.e., highlighted text) in a
passage is positioned.
+
-The default value of `0.5` means to align the match to the middle.
+The default value of `0.33` means to align the match to the left third.
A value of `0.0` means to align the match to the left, while `1.0` to align it
to the right.
This setting is a best-effort hint, as there are a variety of factors.
When there's lots of text to be highlighted, lowering this number can help
performance a lot.
diff --git a/solr/solr-ref-guide/src/major-changes-in-solr-9.adoc
b/solr/solr-ref-guide/src/major-changes-in-solr-9.adoc
index 7e9e83a..17611da 100644
--- a/solr/solr-ref-guide/src/major-changes-in-solr-9.adoc
+++ b/solr/solr-ref-guide/src/major-changes-in-solr-9.adoc
@@ -155,6 +155,8 @@ Currently this change should only effect compatibility of
custom code overriding
* SOLR-14510: The `writeStartDocumentList` in `TextResponseWriter` now
receives an extra boolean parameter representing the "exactness" of the
`numFound` value (exact vs approximation).
Any custom response writer extending `TextResponseWriter` will need to
implement this abstract method now (instead previous with the same name but
without the new boolean parameter).
+* SOLR-15259: hl.fragAlignRatio now defaults to 0.33 to be faster and maybe
looks nicer.
+
* SOLR-9376: The response format for field values serialized as raw XML (via
the `[xml]` raw value DocTransformer
and `wt=xml`) has changed. Previously, values were dropped in directly as
top-level child elements of each `<doc>`,
obscuring associated field names and yielding inconsistent `<doc>` structure.
As of version 9.0, raw values are
