File tree Expand file tree Collapse file tree
Expand file tree Collapse file tree Original file line number Diff line number Diff line change 11build :
22 mvn clean package
33
4- iterate : build
5- @echo iterating over all of the local warcs:
6- @echo
7- @echo warc:
8- mvn -q exec:java -Dexec.mainClass=org.commoncrawl.whirlwind.ReadWARC -Dexec.args=" data/whirlwind.warc.gz"
9- @echo
10- @echo wet:
11- mvn -q exec:java -Dexec.mainClass=org.commoncrawl.whirlwind.ReadWARC -Dexec.args=" data/whirlwind.warc.wet.gz"
12- @echo
13- @echo wat:
14- mvn -q exec:java -Dexec.mainClass=org.commoncrawl.whirlwind.ReadWARC -Dexec.args=" data/whirlwind.warc.wat.gz"
15- @echo
16-
174# cdxj:
185# @echo "creating *.cdxj index files from the local warcs"
196# cdxj-indexer whirlwind.warc.gz > whirlwind.warc.cdxj
@@ -67,7 +54,7 @@ iterate: build
6754#
6855get_jwarc :
6956 @echo " downloading JWarc JAR"
70- curl -fL -o jwarc-0.33.0 .jar https://github.com/iipc/jwarc/releases/download/v0.33.0/jwarc-0.33.0.jar
57+ curl -fL -o jwarc.jar https://github.com/iipc/jwarc/releases/download/v0.33.0/jwarc-0.33.0.jar
7158
7259wreck_the_warc : build get_jwarc
7360 @echo
You can’t perform that action at this time.
0 commit comments