From 5abf19a773fcf376fef017a5530648d171e65eea Mon Sep 17 00:00:00 2001 From: Kengo Seki Date: Mon, 16 Dec 2019 11:04:20 +0900 Subject: [PATCH] HADOOP-16764. Rewrite Python example codes using Python3 (#1762) (cherry picked from commit fd7de2b82a6b9d600b43909a0770a6b0afea899a) --- .../src/site/markdown/RackAwareness.md | 6 +++--- .../src/site/markdown/HadoopStreaming.md.vm | 17 +++++++++-------- 2 files changed, 12 insertions(+), 11 deletions(-) diff --git a/hadoop-common-project/hadoop-common/src/site/markdown/RackAwareness.md b/hadoop-common-project/hadoop-common/src/site/markdown/RackAwareness.md index 89946d18308..9b3b1d78ed1 100644 --- a/hadoop-common-project/hadoop-common/src/site/markdown/RackAwareness.md +++ b/hadoop-common-project/hadoop-common/src/site/markdown/RackAwareness.md @@ -64,7 +64,7 @@ rack and is unable to do so as there is only a single rack named python Example -------------- ```python -#!/usr/bin/python +#!/usr/bin/python3 # this script makes assumptions about the physical environment. # 1) each rack is its own layer 3 network with a /24 subnet, which # could be typical where each rack has its own @@ -94,9 +94,9 @@ for ip in sys.argv: # loop over lis address = '{0}/{1}'.format(ip, netmask) # format address string so it looks like 'ip/netmask' to make netaddr work try: network_address = netaddr.IPNetwork(address).network # calculate and print network address - print "/{0}".format(network_address) + print("/{0}".format(network_address)) except: - print "/rack-unknown" # print catch-all value if unable to calculate network address + print("/rack-unknown") # print catch-all value if unable to calculate network address ``` bash Example diff --git a/hadoop-tools/hadoop-streaming/src/site/markdown/HadoopStreaming.md.vm b/hadoop-tools/hadoop-streaming/src/site/markdown/HadoopStreaming.md.vm index 072a68be47c..f125b631b43 100644 --- a/hadoop-tools/hadoop-streaming/src/site/markdown/HadoopStreaming.md.vm +++ b/hadoop-tools/hadoop-streaming/src/site/markdown/HadoopStreaming.md.vm @@ -416,27 +416,28 @@ To use Aggregate, simply specify "-reducer aggregate": -output myOutputDir \ -mapper myAggregatorForKeyCount.py \ -reducer aggregate \ - -file myAggregatorForKeyCount.py \ + -file myAggregatorForKeyCount.py The python program myAggregatorForKeyCount.py looks like: - #!/usr/bin/python + #!/usr/bin/python3 - import sys; + import sys def generateLongCountToken(id): return "LongValueSum:" + id + "\t" + "1" def main(argv): - line = sys.stdin.readline(); + line = sys.stdin.readline() try: while line: - line = line[:-1]; - fields = line.split("\t"); - print generateLongCountToken(fields[0]); - line = sys.stdin.readline(); + line = line[:-1] + fields = line.split("\t") + print(generateLongCountToken(fields[0])) + line = sys.stdin.readline() except "end of file": return None + if __name__ == "__main__": main(sys.argv)