Merge pull request #64 from lsst-sitcom/tickets/DM-41062

DM-41062: Add topic finding to efdUtils

python/lsst/summit/utils/efdUtils.py

@@ -25,6 +25,8 @@
 import datetime
 import logging
 import pandas as pd
+import re
+from deprecated.sphinx import deprecated
 
 from .utils import getSite
 
@@ -46,7 +48,8 @@
     'getDayObsStartTime',
     'getDayObsEndTime',
     'getDayObsForTime',
-    'getSubTopics',
+    'getSubTopics',  # deprecated, being removed in w_2023_50
+    'getTopics',
 ]
 
 
@@ -530,6 +533,12 @@ def getDayObsForTime(time):
     return int((time + offset).utc.isot[:10].replace('-', ''))
 
 
+@deprecated(
+    reason="getSubTopics() has been replaced by getTopics() and using wildcards. "
+           "Will be removed after w_2023_50.",
+    version="w_2023_40",
+    category=FutureWarning,
+)
 def getSubTopics(client, topic):
     """Get all the sub topics within a given topic.
 
@@ -553,3 +562,42 @@ def getSubTopics(client, topic):
     loop = asyncio.get_event_loop()
     topics = loop.run_until_complete(client.get_topics())
     return sorted([t for t in topics if t.startswith(topic)])
+
+
+def getTopics(client, toFind, caseSensitive=False):
+    """Return all the strings in topics which match the topic query string.
+
+    Supports wildcards, which are denoted as `*``, as per shell globs.
+
+    Example:
+    >>> # assume topics are ['apple', 'banana', 'grape']
+    >>> getTopics(, 'a*p*')
+    ['apple', 'grape']
+
+    Parameters
+    ----------
+    client : `lsst_efd_client.efd_helper.EfdClient`
+        The EFD client to use.
+    toFind : `str`
+        The query string, with optional wildcards denoted as *.
+    caseSensitive : `bool`, optional
+        If ``True``, the query is case sensitive. Defaults to ``False``.
+
+    Returns
+    -------
+    matches : `list` of `str`
+        The list of matching topics.
+    """
+    loop = asyncio.get_event_loop()
+    topics = loop.run_until_complete(client.get_topics())
+
+    # Replace wildcard with regex equivalent
+    pattern = toFind.replace('*', '.*')
+    flags = re.IGNORECASE if not caseSensitive else 0
+
+    matches = []
+    for topic in topics:
+        if re.match(pattern, topic, flags):
+            matches.append(topic)
+
+    return matches

tests/test_butlerUtils.py

@@ -59,6 +59,7 @@
                                            )
 from lsst.summit.utils.butlerUtils import removeDataProduct  # noqa: F401
 import lsst.daf.butler as dafButler
+from lsst.daf.butler import DatasetRef, NamedKeyMapping
 from lsst.resources import ResourcePath
 
 
@@ -108,10 +109,7 @@ def setUp(self):
         self.dataCoordFullView = self.butler.registry.expandDataId(self.rawDataIdNoDayObSeqNum,
                                                                    detector=0).full
         self.assertIsInstance(self.dataCoordMinimal, dafButler.dimensions.DataCoordinate)
-        # NB the type check below is currently using a non-public API, but
-        # at present there isn't a good alternative
-        viewType = dafButler.core.dimensions._coordinate._DataCoordinateFullView
-        self.assertIsInstance(self.dataCoordFullView, viewType)
+        self.assertIsInstance(self.dataCoordFullView, NamedKeyMapping)
 
     def test_getLatissDefaultCollections(self):
         defaultCollections = getLatissDefaultCollections()
@@ -178,14 +176,14 @@ def test_getMostRecentDataId(self):
 
     def test_getDatasetRefForDataId(self):
         dRef = getDatasetRefForDataId(self.butler, 'raw', self.rawDataId)
-        self.assertIsInstance(dRef, lsst.daf.butler.core.datasets.ref.DatasetRef)
+        self.assertIsInstance(dRef, DatasetRef)
 
         dRef = getDatasetRefForDataId(self.butler, 'raw', self.rawDataIdNoDayObSeqNum)
-        self.assertIsInstance(dRef, lsst.daf.butler.core.datasets.ref.DatasetRef)
+        self.assertIsInstance(dRef, DatasetRef)
         dRef = getDatasetRefForDataId(self.butler, 'raw', self.dataCoordMinimal)
-        self.assertIsInstance(dRef, lsst.daf.butler.core.datasets.ref.DatasetRef)
+        self.assertIsInstance(dRef, DatasetRef)
         dRef = getDatasetRefForDataId(self.butler, 'raw', self.dataCoordFullView)
-        self.assertIsInstance(dRef, lsst.daf.butler.core.datasets.ref.DatasetRef)
+        self.assertIsInstance(dRef, DatasetRef)
 
     def test__dayobs_present(self):
         goods = [{'day_obs': 123}, {'exposure.day_obs': 234}, {'day_obs': 345, 'otherkey': -1}]

tests/test_efdUtils.py

@@ -41,7 +41,7 @@
     getDayObsStartTime,
     getDayObsEndTime,
     getDayObsForTime,
-    getSubTopics,
+    getTopics,
 )
 
 from utils import getVcr
@@ -118,14 +118,24 @@ def test_getDayObsAsTimes(self):
             self.assertEqual(dayEnd.jd, dayStart.jd + 1)
 
     @vcr.use_cassette()
-    def test_getSubTopics(self):
-        subTopics = getSubTopics(self.client, 'lsst.sal.MTMount')
-        self.assertIsInstance(subTopics, list)
-        self.assertGreater(len(subTopics), 0)
-
-        subTopics = getSubTopics(self.client, 'fake.topics.does.not.exist')
-        self.assertIsInstance(subTopics, list)
-        self.assertEqual(len(subTopics), 0)
+    def test_getTopics(self):
+        topics = getTopics(self.client, 'lsst.sal.MTMount*')
+        self.assertIsInstance(topics, list)
+        self.assertGreater(len(topics), 0)
+
+        topics = getTopics(self.client, '*fake.topics.does.not.exist*')
+        self.assertIsInstance(topics, list)
+        self.assertEqual(len(topics), 0)
+
+        # check we can find the mount with a preceding wildcard
+        topics = getTopics(self.client, '*mTmoUnt*')
+        self.assertIsInstance(topics, list)
+        self.assertGreater(len(topics), 0)
+
+        # check it fails if we don't allow case insensitivity
+        topics = getTopics(self.client, '*mTmoUnt*', caseSensitive=True)
+        self.assertIsInstance(topics, list)
+        self.assertEqual(len(topics), 0)
 
     @vcr.use_cassette()
     def test_getEfdData(self):