Skip to content

Changed auto generated index name #503

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
shubhamsrkdev wants to merge 6 commits into
base: main
Choose a base branch
from
Open

Changed auto generated index name #503

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
24b58c2
Changed auto generated file name
shubhamsrkdev Jan 6, 2026
8da5024
Added metadata check
shubhamsrkdev Jan 7, 2026
78ba5bc
Added hash in file name
shubhamsrkdev Jan 16, 2026
b25d1bb
Added extra parts
shubhamsrkdev Jan 16, 2026
5228e84
Fixed test
shubhamsrkdev Jan 16, 2026
bc0f3de
tidy
shubhamsrkdev Jan 16, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion scripts/nrt.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,7 @@
# /root/jdk1.6.0_31/bin/java -XX:+UnlockExperimentalVMOptions -XX:+UseG1GC

/opt/zing/zingLX-jdk1.6.0_31-5.2.0.0-18-x86_64/bin/java -verbose:gc -Xms40G -Xmx40G -cp .:$LUCENE_HOME/build/core/classes/java:$LUCENE_HOME/build/highlighter/classes/java:$LUCENE_HOME/build/test-framework/classes/java:$LUCENE_HOME/build/queryparser/classes/java:$LUCENE_HOME/build/suggest/classes/java:$LUCENE_HOME/build/analysis/common/classes/java:$LUCENE_HOME/build/grouping/classes/java perf.SearchPerfTest \
-indexPath /large/indices/wikimediumall.lucene4x.Lucene40.nd33.3326M/index \
-indexPath /large/indices/wikimediumall.lucene4x.nd33.3326M/index \
-dirImpl RAMDirectory \
-analyzer StandardAnalyzer \
-taskSource server:localhost:7777 \
Expand Down
2 changes: 1 addition & 1 deletion src/main/IndexToFST.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,7 +21,7 @@
import org.apache.lucene.util.fst.PositiveIntOutputs;
import org.apache.lucene.util.fst.Util;

// javac -cp lucene/core/build/libs/lucene-core-10.0.0-SNAPSHOT.jar IndexToFST.java; java -cp .:lucene/core/build/libs/lucene-core-10.0.0-SNAPSHOT.jar IndexToFST /l/indices/wikimediumall.trunk.facets.taxonomy:Date.taxonomy:Month.taxonomy:DayOfYear.taxonomy:RandomLabel.taxonomy.sortedset:Date.sortedset:Month.sortedset:DayOfYear.sortedset:RandomLabel.sortedset.Lucene90.Lucene90.dvfields.nd33.3326M/index
// javac -cp lucene/core/build/libs/lucene-core-10.0.0-SNAPSHOT.jar IndexToFST.java; java -cp .:lucene/core/build/libs/lucene-core-10.0.0-SNAPSHOT.jar IndexToFST /l/indices/wikimediumall.trunk.nd33.3326M/index

public class IndexToFST {

Expand Down
36 changes: 14 additions & 22 deletions src/python/competition.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -236,37 +236,29 @@ def getName(self):
if self.useCFS:
name.append("cfs")

# TODO: adding facets to filename makes it too long and runs into limits on some machines
# Can we remove this from file name and record it in a different logfile.
# Print index configuration instead of adding to filename
config_parts = []
if self.facets is not None:
name.append("facets")
for arg in self.facets:
name.append(arg[0])
name.append(self.facetDVFormat)

config_parts.append(f"facets: {[arg[0] for arg in self.facets]} (format: {self.facetDVFormat})")
if self.bodyTermVectors:
name.append("tv")

config_parts.append("bodyTermVectors: enabled")
if self.bodyStoredFields:
name.append("stored")

config_parts.append("bodyStoredFields: enabled")
if self.bodyPostingsOffsets:
name.append("offsets")

name.append(self.postingsFormat)
config_parts.append("bodyPostingsOffsets: enabled")
config_parts.append(f"postingsFormat: {self.postingsFormat}")
if self.postingsFormat != self.idFieldPostingsFormat:
name.append(self.idFieldPostingsFormat)

config_parts.append(f"idFieldPostingsFormat: {self.idFieldPostingsFormat}")
if self.addDVFields:
name.append("dvfields")

config_parts.append("addDVFields: enabled")
if self.indexSort:
name.append("sort=%s" % self.indexSort)

config_parts.append(f"indexSort: {self.indexSort}")
if self.vectorFile:
name.append("vectors=%d" % self.vectorDimension)
config_parts.append(f"vectors: dimension={self.vectorDimension}")
if self.quantizeKNNGraph:
name.append("int8-quantized")
config_parts.append("quantizeKNNGraph: enabled")
config_parts.append(f"numDocs: {self.numDocs / 1000000.0:.3f}M")
print(f"Index configuration for {'.'.join(name)}: {', '.join(config_parts)}")

name.append("nd%gM" % (self.numDocs / 1000000.0))
return ".".join(name)
Expand Down
2 changes: 1 addition & 1 deletion src/python/test_all_fst_sizes.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,7 +23,7 @@
while True:
print(f"\nTest ram_mb={ram_mb}")
stdout = subprocess.check_output(
f"java -cp .:lucene/core/build/libs/lucene-core-10.0.0-SNAPSHOT.jar IndexToFST /l/indices/wikimediumall.trunk.facets.taxonomy:Date.taxonomy:Month.taxonomy:DayOfYear.taxonomy:RandomLabel.taxonomy.sortedset:Date.sortedset:Month.sortedset:DayOfYear.sortedset:RandomLabel.sortedset.Lucene90.Lucene90.dvfields.nd33.3326M/index {ram_mb}",
f"java -cp .:lucene/core/build/libs/lucene-core-10.0.0-SNAPSHOT.jar IndexToFST /l/indices/wikimediumall.trunk.nd33.3326M/index {ram_mb}",
shell=True,
)

Expand Down
Loading