Skip to content
This repository has been archived by the owner on Dec 22, 2022. It is now read-only.

switch to a valid path in ExampleArcMicroformat #4

Open
wants to merge 2 commits into
base: master
Choose a base branch
from
Open
Show file tree
Hide file tree
Changes from all commits
Commits
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
Original file line number Diff line number Diff line change
Expand Up @@ -180,7 +180,7 @@ public int run(String[] args)
configFile = args[1];

// For this example, only look at a single ARC files.
String inputPath = "s3n://aws-publicdatasets/common-crawl/parse-output/segment/1341690163490/1341782443295_1551.arc.gz";
String inputPath = "s3n://aws-publicdatasets/common-crawl/parse-output/segment/1346823845675/1346871947461_4036.arc.gz";

// Switch to this if you'd like to look at all ARC files. May take many minutes just to read the file listing.
//String inputPath = "s3n://aws-publicdatasets/common-crawl/parse-output/segment/*/*.arc.gz";
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -208,7 +208,7 @@ public int run(String[] args)

// If you would like to process all segments, comment this out and
// uncomment the block of code below
String inputPath = baseInputPath + "/1341690154994/metadata-00062";
String inputPath = baseInputPath + "/1346823845675/metadata-04379";

LOG.info("adding input path '" + inputPath + "'");
FileInputFormat.addInputPath(job, new Path(inputPath));
Expand Down