charlespnh commented on code in PR #35151: URL: https://github.com/apache/beam/pull/35151#discussion_r2132993912
########## sdks/python/apache_beam/yaml/examples/streaming_wordcount.yaml: ########## @@ -0,0 +1,97 @@ +# coding=utf-8 +# +# Licensed to the Apache Software Foundation (ASF) under one or more +# contributor license agreements. See the NOTICE file distributed with +# this work for additional information regarding copyright ownership. +# The ASF licenses this file to You under the Apache License, Version 2.0 +# (the "License"); you may not use this file except in compliance with +# the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. +# + +pipeline: + type: chain + transforms: + # Assuming the given topic exists with the following message JSON schema, + # read the records from Kafka + - type: ReadFromKafka + config: + format: JSON + schema: | + { + "type": "object", + "properties": { + "value": {"type": "string"} + } + } + topic: {{ TOPIC }} + bootstrap_servers: {{ BOOTSTRAP_SERVERS }} + auto_offset_reset_config: earliest + consumer_config: + sasl.jaas.config: "org.apache.kafka.common.security.plain.PlainLoginModule required \ + username={{ USERNAME }} \ + password={{ PASSWORD }};" + security.protocol: "SASL_PLAINTEXT" + sasl.mechanism: "PLAIN" + + # Split line field in each row into list of words. + - type: MapToFields + config: + language: python + fields: + words: + callable: | + import re + def my_mapping(row): + return re.findall(r"[A-Za-z\']+", row.value.lower()) + + # Explode each list of words into separate rows. + - type: Explode + config: + fields: words + + # Since each word is now distinct row, rename field to "word". + - type: MapToFields + config: + fields: + word: words + + # With an unbounded source such as Kafka, a window is required for + # any subsequent GroupBy transform. + - type: WindowInto + name: Windowing + windowing: + type: fixed + size: 3s + + # Group by distinct words in the collection and add field "count" that + # contains number of instances, or count, for each word in the collection. + - type: Combine + config: + language: python + group_by: word + combine: + count: + value: word + fn: count + + - type: LogForTesting + +# Expected: +# Row(word='king', count=311) Review Comment: Based on discussion this streaming wordcount example is removed. There're already kafka.yaml and wordcount_minimal.yaml examples that can be referenced. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
