[
https://issues.apache.org/jira/browse/BEAM-7018?focusedWorklogId=287873&page=com.atlassian.jira.plugin.system.issuetabpanels:worklog-tabpanel#worklog-287873
]
ASF GitHub Bot logged work on BEAM-7018:
----------------------------------------
Author: ASF GitHub Bot
Created on: 02/Aug/19 12:01
Start Date: 02/Aug/19 12:01
Worklog Time Spent: 10m
Work Description: robertwb commented on pull request #8859: [BEAM-7018]
Added Regex transform for PythonSDK
URL: https://github.com/apache/beam/pull/8859#discussion_r310096231
##########
File path: sdks/python/apache_beam/transforms/util.py
##########
@@ -865,3 +868,220 @@ def add_window_info(element,
timestamp=DoFn.TimestampParam,
def expand(self, pcoll):
return pcoll | ParDo(self.add_window_info)
+
+
+class Regex(object):
+ """
+ PTransform to use Regular Expression to process the elements in a
+ PCollection.
+ """
+
+ ALL = "__regex_all_groups"
+
+ @staticmethod
+ def _regex_compile(regex):
+ """Return re.compile if the regex has a string value"""
+ if isinstance(regex, str):
+ regex = re.compile(regex)
+ return regex
+
+ @staticmethod
+ @typehints.with_input_types(str)
+ @typehints.with_output_types(str)
+ @ptransform_fn
+ def matches(pcoll, regex, group=0):
+ """
+ Returns the matches (group 0 by default) if zero or more characters at the
+ beginning of string match the regular expression. To match the entire
+ string, add "$" sign at the end of regex expression.
+
+ Group can be integer value or a string value.
+
+ Args:
+ regex: the regular expression string or (re.compile) pattern.
+ group: (optional) name/number of the group, it can be integer or a string
+ value.
+ """
+ regex = Regex._regex_compile(regex)
+
+ def _process(element):
+ m = regex.match(element)
+ if m:
+ yield m.group(group)
+ return pcoll | FlatMap(_process)
+
+ @staticmethod
+ @typehints.with_input_types(str)
+ @typehints.with_output_types(typing.List[str])
+ @ptransform_fn
+ def all_matches(pcoll, regex):
+ """
+ Returns all matches (groups) if zero or more characters at the beginning
+ of string match the regular expression.
+
+ Args:
+ regex: the regular expression string or (re.compile) pattern.
+ """
+ regex = Regex._regex_compile(regex)
+
+ def _process(element):
+ m = regex.match(element)
+ if m:
+ yield [m.group(ix) for ix in range(m.lastindex + 1)]
+
+ return pcoll | FlatMap(_process)
+
+ @staticmethod
+ @typehints.with_input_types(str)
+ @typehints.with_output_types(typing.Tuple[str, str])
+ @ptransform_fn
+ def matches_kv(pcoll, regex, keyGroup, valueGroup):
+ """
+ Returns the KV pairs if the string matches the regular expression, deriving
+ the key & value from the specified group of the regular expression.
+
+ Args:
+ regex: the regular expression string or (re.compile) pattern.
+ keyGroup: The Regex group to use as the key. Can be int or str.
+ valueGroup: The Regex group to use the value. Can be int or str.
+ """
+ regex = Regex._regex_compile(regex)
+
+ def _process(element):
+ match = regex.match(element)
+ if match:
+ yield (match.group(keyGroup), match.group(valueGroup))
+ return pcoll | FlatMap(_process)
+
+ @staticmethod
+ @typehints.with_input_types(str)
+ @typehints.with_output_types(str)
+ @ptransform_fn
+ def find(pcoll, regex, group=0):
+ """
+ Returns the matches if a portion of the line matches the Regex. Returns
+ the entire group (group 0 by default). Group can be integer value or a
+ string value.
+
+ Args:
+ regex: the regular expression string or (re.compile) pattern.
+ group: (optional) name of the group, it can be integer or a string value.
+ """
+ regex = Regex._regex_compile(regex)
+
+ def _process(element):
+ r = regex.search(element)
+ if r:
+ yield r.group(group)
+ return pcoll | FlatMap(_process)
+
+ @staticmethod
+ @typehints.with_input_types(str)
+ @typehints.with_output_types(typing.Union[typing.List[str],
+ typing.Tuple[str, str]])
+ @ptransform_fn
+ def find_all(pcoll, regex, group=0, outputEmpty=True):
+ """
+ Returns the matches if a portion of the line matches the Regex. By default,
+ list of group 0 will return with empty items. To get all groups, pass the
+ `Regex.ALL` flag in the `group` parameter which returns all the groups in
+ the tuple format.
+
+ Args:
+ regex: the regular expression string or (re.compile) pattern.
+ group: (optional) name of the group, it can be integer or a string value.
+ outputEmpty: (optional) Should empty be output. True to output empties
+ and false if not.
+ """
+ regex = Regex._regex_compile(regex)
+
+ def _process(element):
+ matches = regex.finditer(element)
+ if group == Regex.ALL:
+ yield [(m.group(), m.groups()[0]) for m in matches if outputEmpty is
+ True or m.groups()[0]]
+ else:
+ yield [m.group(group) for m in matches if outputEmpty is True or
Review comment:
"is True" can be omitted. (Similarly above.)
----------------------------------------------------------------
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.
For queries about this service, please contact Infrastructure at:
[email protected]
Issue Time Tracking
-------------------
Worklog Id: (was: 287873)
Time Spent: 10h 40m (was: 10.5h)
> Regex transform for Python SDK
> ------------------------------
>
> Key: BEAM-7018
> URL: https://issues.apache.org/jira/browse/BEAM-7018
> Project: Beam
> Issue Type: New Feature
> Components: sdk-py-core
> Reporter: Rose Nguyen
> Assignee: Shehzaad Nakhoda
> Priority: Minor
> Time Spent: 10h 40m
> Remaining Estimate: 0h
>
> PTransorms to use Regular Expressions to process elements in a PCollection
> It should offer the same API as its Java counterpart:
> [https://github.com/apache/beam/blob/11a977b8b26eff2274d706541127c19dc93131a2/sdks/java/core/src/main/java/org/apache/beam/sdk/transforms/Regex.java]
--
This message was sent by Atlassian JIRA
(v7.6.14#76016)
