Remove -optimize option for regression test (castorini#393)

vincent-4 · Aug 9, 2018 · 6b19d37 · 6b19d37
1 parent 81582f8
commit 6b19d37
Showing 17 changed files with 12 additions and 20 deletions.
diff --git a/docs/experiments-car17.md b/docs/experiments-car17.md
@@ -7,8 +7,8 @@ Typical indexing command:
 ```
 nohup sh target/appassembler/bin/IndexCollection -collection CarCollection \
 -generator LuceneDocumentGenerator -threads 40 -input /path/to/car17 -index \
-lucene-index.car17.pos+docvectors -storeRawDocs -storePositions -storeDocvectors \
--optimize >& log.car17.pos+docvectors+rawdocs &
+lucene-index.car17.pos+docvectors -storePositions -storeDocvectors -storeRawDocs \
+>& log.car17.pos+docvectors+rawdocs &
 ```
 
 The directory `/path/to/Car17` should be the root directory of Car17 collection, i.e., `ls /path/to/Car17` should bring up a list of `.cbor` files.

diff --git a/docs/experiments-core17.md b/docs/experiments-core17.md
@@ -8,7 +8,7 @@ Typical indexing command:
 nohup sh target/appassembler/bin/IndexCollection -collection \
 NewYorkTimesCollection -generator JsoupGenerator -threads 16 -input \
 /path/to/core17 -index lucene-index.core17.pos+docvectors -storePositions \
--storeDocvectors -storeRawDocs -optimize >& log.core17.pos+docvectors+rawdocs &
+-storeDocvectors -storeRawDocs >& log.core17.pos+docvectors+rawdocs &
 ```
 
 The directory `/path/to/nyt_corpus/` should be the root directory of TREC Core collection, i.e., `ls /path/to/nyt_corpus/`

diff --git a/docs/experiments-disk12.md b/docs/experiments-disk12.md
@@ -8,7 +8,7 @@ Typical indexing command:
 nohup sh target/appassembler/bin/IndexCollection -collection TrecCollection \
 -generator JsoupGenerator -threads 16 -input /path/to/disk12 -index \
 lucene-index.disk12.pos+docvectors -storePositions -storeDocvectors \
--storeRawDocs -optimize >& log.disk12.pos+docvectors+rawdocs &
+-storeRawDocs >& log.disk12.pos+docvectors+rawdocs &
 ```
 
 The directory `/path/to/disk12/` should be the root directory of the Disk12 collection, i.e., `ls /path/to/disk12/` should bring up subdirectories like `doe`, `wsj`.

diff --git a/docs/experiments-gov2.md b/docs/experiments-gov2.md
@@ -8,7 +8,7 @@ Typical indexing command:
 nohup sh target/appassembler/bin/IndexCollection -collection TrecwebCollection \
 -generator JsoupGenerator -threads 44 -input /path/to/gov2 -index \
 lucene-index.gov2.pos+docvectors -storePositions -storeDocvectors -storeRawDocs \
--optimize >& log.gov2.pos+docvectors+rawdocs &
+>& log.gov2.pos+docvectors+rawdocs &
 ```
 
 The directory `/path/to/gov2/` should be the root directory of Gov2 collection, i.e., `ls /path/to/gov2/` should bring up a bunch of subdirectories, `GX000` to `GX272`.

diff --git a/docs/experiments-mb11.md b/docs/experiments-mb11.md
@@ -13,8 +13,8 @@ Indexing the Tweets2011 collection:
 nohup sh target/appassembler/bin/IndexCollection -collection TweetCollection \
 -generator TweetGenerator -threads 44 -input /path/to/mb11 -index \
 lucene-index.mb11.pos+docvectors -storePositions -storeDocvectors -storeRawDocs \
--optimize -uniqueDocid -tweet.keepUrls -tweet.stemming >& \
-log.mb11.pos+docvectors+rawdocs &
+-uniqueDocid -tweet.keepUrls -tweet.stemming >& log.mb11.pos+docvectors+rawdocs \
+&
 ```
 __NB:__ The process is backgrounded
 

diff --git a/docs/experiments-mb13.md b/docs/experiments-mb13.md
@@ -13,8 +13,8 @@ Indexing the Tweets2013 collection:
 nohup sh target/appassembler/bin/IndexCollection -collection TweetCollection \
 -generator TweetGenerator -threads 44 -input /path/to/mb13 -index \
 lucene-index.mb13.pos+docvectors -storePositions -storeDocvectors -storeRawDocs \
--optimize -uniqueDocid -tweet.keepUrls -tweet.stemming >& \
-log.mb13.pos+docvectors+rawdocs &
+-uniqueDocid -tweet.keepUrls -tweet.stemming >& log.mb13.pos+docvectors+rawdocs \
+&
 ```
 __NB:__ The process is backgrounded
 

diff --git a/docs/experiments-robust04.md b/docs/experiments-robust04.md
@@ -8,7 +8,7 @@ Typical indexing command:
 nohup sh target/appassembler/bin/IndexCollection -collection TrecCollection \
 -generator JsoupGenerator -threads 16 -input /path/to/robust04 -index \
 lucene-index.robust04.pos+docvectors -storePositions -storeDocvectors \
--storeRawDocs -optimize >& log.robust04.pos+docvectors+rawdocs &
+-storeRawDocs >& log.robust04.pos+docvectors+rawdocs &
 ```
 
 The directory `/path/to/disk45/` should be the root directory of Disk4 and Disk5 collection; inside each there should be subdirectories like `ft`, `fr94`.

diff --git a/docs/experiments-robust05.md b/docs/experiments-robust05.md
@@ -8,7 +8,7 @@ Typical indexing command:
 nohup sh target/appassembler/bin/IndexCollection -collection TrecCollection \
 -generator JsoupGenerator -threads 16 -input /path/to/robust05 -index \
 lucene-index.robust05.pos+docvectors -storePositions -storeDocvectors \
--storeRawDocs -optimize >& log.robust05.pos+docvectors+rawdocs &
+-storeRawDocs >& log.robust05.pos+docvectors+rawdocs &
 ```
 
 The directory `/path/to/aquaint/` should be the root directory of AQUAINT collection; under subdirectory `disk1/` there should be `NYT/` and under subdirectory `disk2/` there should be `APW/` and `XIE/`.

diff --git a/docs/experiments-wt10g.md b/docs/experiments-wt10g.md
@@ -8,7 +8,7 @@ Typical indexing command:
 nohup sh target/appassembler/bin/IndexCollection -collection TrecwebCollection \
 -generator JsoupGenerator -threads 16 -input /path/to/wt10g -index \
 lucene-index.wt10g.pos+docvectors -storePositions -storeDocvectors -storeRawDocs \
--optimize >& log.wt10g.pos+docvectors+rawdocs &
+>& log.wt10g.pos+docvectors+rawdocs &
 ```
 
 The directory `/path/to/wt10g/` should be the root directory of Wt10g collection, containing a bunch of subdirectories, `WTX001` to `WTX104`.

diff --git a/src/main/resources/regression/core17.yaml b/src/main/resources/regression/core17.yaml
@@ -13,7 +13,6 @@ index_options:
   - -storePositions
   - -storeDocvectors
   - -storeRawDocs
-  - -optimize
 topic_reader: Trec
 input: /tuna1/collections/newswire/NYTcorpus/
 index_path: "/tuna1/indexes/lucene-index.core17.pos+docvectors+rawdocs" # path to the existing index, used in regression test if `--index` option is absent

diff --git a/src/main/resources/regression/disk12.yaml b/src/main/resources/regression/disk12.yaml
@@ -14,7 +14,6 @@ index_options:
   - -storePositions
   - -storeDocvectors
   - -storeRawDocs
-  - -optimize
 topic_reader: Trec
 evals:
   - command: eval/trec_eval.9.0/trec_eval

diff --git a/src/main/resources/regression/gov2.yaml b/src/main/resources/regression/gov2.yaml
@@ -16,7 +16,6 @@ index_options:
   - -storePositions
   - -storeDocvectors
   - -storeRawDocs
-  - -optimize
 topic_reader: Trec
 evals:
   - command: eval/trec_eval.9.0/trec_eval

diff --git a/src/main/resources/regression/mb11.yaml b/src/main/resources/regression/mb11.yaml
@@ -16,7 +16,6 @@ index_options:
   - -storePositions
   - -storeDocvectors
   - -storeRawDocs
-  - -optimize
   - -uniqueDocid
   - -tweet.keepUrls
   - -tweet.stemming

diff --git a/src/main/resources/regression/mb13.yaml b/src/main/resources/regression/mb13.yaml
@@ -16,7 +16,6 @@ index_options:
   - -storePositions
   - -storeDocvectors
   - -storeRawDocs
-  - -optimize
   - -uniqueDocid
   - -tweet.keepUrls
   - -tweet.stemming

diff --git a/src/main/resources/regression/robust04.yaml b/src/main/resources/regression/robust04.yaml
@@ -14,7 +14,6 @@ index_options:
   - -storePositions
   - -storeDocvectors
   - -storeRawDocs
-  - -optimize
 topic_reader: Trec
 evals:
   - command: eval/trec_eval.9.0/trec_eval

diff --git a/src/main/resources/regression/robust05.yaml b/src/main/resources/regression/robust05.yaml
@@ -14,7 +14,6 @@ index_options:
   - -storePositions
   - -storeDocvectors
   - -storeRawDocs
-  - -optimize
 topic_reader: Trec
 evals:
   - command: eval/trec_eval.9.0/trec_eval

diff --git a/src/main/resources/regression/wt10g.yaml b/src/main/resources/regression/wt10g.yaml
@@ -14,7 +14,6 @@ index_options:
   - -storePositions
   - -storeDocvectors
   - -storeRawDocs
-  - -optimize
 topic_reader: Trec
 evals:
   - command: eval/trec_eval.9.0/trec_eval