Task 6

.editorconfig

@@ -6,11 +6,10 @@ root = true
 end_of_line = lf
 insert_final_newline = true
 
-# LF: not sure about this
-# [*.java]
-# charset = utf-8
-# indent_style = space
-# indent_size = 4
+[*.java]
+charset = utf-8
+indent_style = space
+indent_size = 4
 
 [Makefile]
 indent_style = tab

.github/ci-build-unstable.yml → .github/workflows/ci-build-unstable.yml

@@ -14,8 +14,8 @@ jobs:
         with:
           java-version: '11'
           distribution: 'temurin'
-          cache: 'mvn'
-      - name: Build with Gradle
+          cache: maven
+      - name: Build with Maven
         run: mvn -B clean compile
       - name: Check with spotless
-        run: mvn spotless:check
+        run: mvn spotless:check

Makefile

@@ -1,71 +1,68 @@
 build:
 	mvn clean package
 
-iterate: build
-	@echo iterating over all of the local warcs:
+cdxj: build ensure_jwarc
+	@echo "creating *.cdxj index files from the local warcs"
+	java -jar jwarc.jar cdxj data/whirlwind.warc.gz > whirlwind.warc.cdxj
+	mvn -q exec:java -Dexec.mainClass=org.commoncrawl.whirlwind.CdxjIndexer -Dexec.args="data/whirlwind.warc.wet.gz --records conversion" > whirlwind.warc.wet.cdxj
+	mvn -q exec:java -Dexec.mainClass=org.commoncrawl.whirlwind.CdxjIndexer -Dexec.args="data/whirlwind.warc.wat.gz --records metadata" > whirlwind.warc.wat.cdxj
+
+extract:
+	@echo "creating extraction.* from local warcs, the offset numbers are from the cdxj index"
+	java -jar jwarc.jar extract --payload data/whirlwind.warc.gz 1023 > extraction.html
+	java -jar jwarc.jar extract --payload data/whirlwind.warc.wet.gz 466 > extraction.txt
+	java -jar jwarc.jar extract --payload data/whirlwind.warc.wat.gz 443 > extraction.json
+	@echo "hint: python -m json.tool extraction.json"
+
+cdx_toolkit:
+	@echo demonstrate that we have this entry in the index
+	curl 'https://index.commoncrawl.org/CC-MAIN-2024-22-index?url=an.wikipedia.org/wiki/Escopete&output=json&from=20240518015810&to=20240518015810'
 	@echo
-	@echo warc:
-	mvn -q exec:java -Dexec.mainClass=org.commoncrawl.whirlwind.ReadWARC -Dexec.args="data/whirlwind.warc.gz"
+	@echo cleanup previous work
+	rm -f TEST-000000.extracted.warc.gz
+	@echo retrieve the content from the commoncrawl data server
+	curl --request GET --url 'https://data.commoncrawl.org/crawl-data/CC-MAIN-2024-22/segments/1715971057216.39/warc/CC-MAIN-20240517233122-20240518023122-00000.warc.gz' --header 'Range: bytes=80610731-80628153' > TEST-000000.extracted.warc.gz
 	@echo
-	@echo wet:
-	mvn -q exec:java -Dexec.mainClass=org.commoncrawl.whirlwind.ReadWARC -Dexec.args="data/whirlwind.warc.wet.gz"
+	@echo index this new warc
+	java -jar jwarc.jar cdxj TEST-000000.extracted.warc.gz  > TEST-000000.extracted.warc.cdxj
+	cat TEST-000000.extracted.warc.cdxj
 	@echo
-	@echo wat:
-	mvn -q exec:java -Dexec.mainClass=org.commoncrawl.whirlwind.ReadWARC -Dexec.args="data/whirlwind.warc.wat.gz"
+	@echo iterate this new warc
+	java -jar jwarc.jar ls TEST-000000.extracted.warc.gz
 	@echo
 
-# cdxj:
-# 	@echo "creating *.cdxj index files from the local warcs"
-# 	cdxj-indexer whirlwind.warc.gz > whirlwind.warc.cdxj
-# 	cdxj-indexer --records conversion whirlwind.warc.wet.gz > whirlwind.warc.wet.cdxj
-# 	cdxj-indexer whirlwind.warc.wat.gz > whirlwind.warc.wat.cdxj
+download_collinfo:
+	@echo "downloading collinfo.json so we can find out the crawl name"
+	curl -O https://index.commoncrawl.org/collinfo.json
+
+CC-MAIN-2024-22.warc.paths.gz:
+	@echo "downloading the list from s3, requires s3 auth even though it is free"
+	@echo "note that this file should be in the repo"
+	 aws s3 ls s3://commoncrawl/cc-index/table/cc-main/warc/crawl=CC-MAIN-2024-22/subset=warc/ | awk '{print $$4}' | gzip -9 > CC-MAIN-2024-22.warc.paths.gz
+
+duck_ccf_local_files: build
+	@echo "warning! only works on Common Crawl Foundadtion's development machine"
+	mvn -q exec:java -Dexec.mainClass=org.commoncrawl.whirlwind.Duck -Dexec.args"ccf_local_files"
+
+duck_cloudfront: build
+	@echo "warning! this might take 1-10 minutes"
+	mvn -q exec:java -Dexec.mainClass=org.commoncrawl.whirlwind.Duck -Dexec.args"cloudfront"
+
+
+ensure_jwarc:
+	@echo "Ensuring JWarc JAR is present"
+	@if [ ! -f jwarc.jar ] ; then \
+	  echo "jwarc.jar not found, downloading..." ; \
+	  curl -fL -o jwarc.jar https://github.com/iipc/jwarc/releases/download/v0.33.0/jwarc-0.33.0.jar ; \
+	else \
+	  echo "jwarc.jar found." ; \
+	fi
+
+get_jwarc:
+	@echo "downloading JWarc JAR"
+	curl -fL -o jwarc.jar https://github.com/iipc/jwarc/releases/download/v0.33.0/jwarc-0.33.0.jar
 
-# extract:
-# 	@echo "creating extraction.* from local warcs, the offset numbers are from the cdxj index"
-# 	warcio extract --payload whirlwind.warc.gz 1023 > extraction.html
-# 	warcio extract --payload whirlwind.warc.wet.gz 466 > extraction.txt
-# 	warcio extract --payload whirlwind.warc.wat.gz 443 > extraction.json
-# 	@echo "hint: python -m json.tool extraction.json"
-#
-# cdx_toolkit:
-# 	@echo demonstrate that we have this entry in the index
-# 	cdxt --crawl CC-MAIN-2024-22 --from 20240518015810 --to 20240518015810 iter an.wikipedia.org/wiki/Escopete
-# 	@echo
-# 	@echo cleanup previous work
-# 	rm -f TEST-000000.extracted.warc.gz
-# 	@echo retrieve the content from the commoncrawl s3 bucket
-# 	cdxt --crawl CC-MAIN-2024-22 --from 20240518015810 --to 20240518015810 warc an.wikipedia.org/wiki/Escopete
-# 	@echo
-# 	@echo index this new warc
-# 	cdxj-indexer TEST-000000.extracted.warc.gz  > TEST-000000.extracted.warc.cdxj
-# 	cat TEST-000000.extracted.warc.cdxj
-# 	@echo
-# 	@echo iterate this new warc
-# 	python ./warcio-iterator.py TEST-000000.extracted.warc.gz
-# 	@echo
-#
-# download_collinfo:
-# 	@echo "downloading collinfo.json so we can find out the crawl name"
-# 	curl -O https://index.commoncrawl.org/collinfo.json
-#
-# CC-MAIN-2024-22.warc.paths.gz:
-# 	@echo "downloading the list from s3, requires s3 auth even though it is free"
-# 	@echo "note that this file should be in the repo"
-# 	 aws s3 ls s3://commoncrawl/cc-index/table/cc-main/warc/crawl=CC-MAIN-2024-22/subset=warc/ | awk '{print $$4}' | gzip -9 > CC-MAIN-2024-22.warc.paths.gz
-#
-# duck_local_files:
-# 	@echo "warning! 300 gigabyte download"
-# 	python duck.py local_files
-#
-# duck_ccf_local_files:
-# 	@echo "warning! only works on Common Crawl Foundadtion's development machine"
-# 	python duck.py ccf_local_files
-#
-# duck_cloudfront:
-# 	@echo "warning! this might take 1-10 minutes"
-# 	python duck.py cloudfront
-#
-wreck_the_warc: build
+wreck_the_warc: build ensure_jwarc
 	@echo
 	@echo we will break and then fix this warc
 	cp data/whirlwind.warc.gz data/testing.warc.gz