import_fdsnws_eq: Local file parsing and test code

- Allow operating on a local QuakeML event file.
- Add unit tests for this.

shakyground2/import_fdsnws_eq.py

@@ -4,7 +4,7 @@
 #
 # Author: Peter L. Evans <pevans@gfz-potsdam.de>
 #
-# Copyright (C) 2018 Helmholtz-Zentrum Potsdam - Deutsches GeoForschungsZentrum GFZ
+# Copyright (C) 2021 Helmholtz-Zentrum Potsdam - Deutsches GeoForschungsZentrum GFZ
 #
 # This software is free software and comes with ABSOLUTELY NO WARRANTY.
 #
@@ -18,6 +18,7 @@ Can run standalone:
 """
 
 import datetime
+import os
 import sys
 import urllib.request as ul
 from xml.etree import ElementTree as ET
@@ -33,9 +34,9 @@ def fetch_fm(root, ns, preferredfmID):
     Extract interesting properties from the focal mechanism with
     the given publicID.
 
-    root - ElementTree root element.
-    ns - string, its namespace.
-    preferredfmID - string, the focal mechanism to hunt for.
+    root: ElementTree root element.
+    ns (string): string, its namespace.
+    preferredfmID (string): the focal mechanism to hunt for.
 
     """
     for fm in root[0][0].findall("ns:focalMechanism", ns):
@@ -82,9 +83,9 @@ def fetch_origin(root, ns, preferredoriginID):
     """
     Extract interesting properties from the origin with given publicID.
 
-    root - ElementTree root element.
-    ns - string, its namespace.
-    preferredoriginID - string, the origin to hunt for.
+    root: ElementTree root element.
+    ns (string): the XML object's namespace.
+    preferredoriginID (string): the origin to hunt for.
     """
     for o in root[0][0].findall("ns:origin", ns):
         if o.attrib["publicID"] != preferredoriginID:
@@ -107,14 +108,13 @@ def fetch_origin(root, ns, preferredoriginID):
     return d
 
 
-def fetch_quakeml(evid):
+def fetch_quakeml_ws(evid):
     """
-    Query fdsnws-event web service, and prepare a dictionary with the
-    interesting things found by reading the QuakeML file served for a given event.
+    Query fdsnws-event web service, and return string
+    to fetch_quakeml() for parsing.
 
-    If there is no focal mechanism, return None where that would otherwise go.
+    evid (string): the event ID to query for.
 
-    evid - string, the event ID to query for.
     """
     url = (
         FDSNWS_ENDPOINT
@@ -136,10 +136,45 @@ def fetch_quakeml(evid):
     print("Got", len(buf), "char(s).")
     with open("tmp.xml", "w") as fid:
         fid.write(str(buf))
+    return buf
+
+
+def fetch_quakeml(path):
+    """
+    Prepare a dictionary holding the interesting things found by
+    reading the QuakeML file served for a given event.
+
+    If there is no focal mechanism, return None where that would otherwise go.
+
+    path (string): Either a local file name, or a GEOFON event ID
+                   such as 'gfz2044sqpr'.
+
+    """
+    if os.path.exists(path):
+        with open(path) as fid:
+            buf = fid.read()
+    elif path.startswith("gfz") and len(path) == len("gfz2044sqpr"):
+        buf = fetch_quakeml_ws(path)
+    else:
+        raise IOError("Not a local path or a GEOFON event ID")
 
     root = ET.fromstring(buf)
     ns = QUAKEML_NS
 
+    event = root[0][0]
+    # .find("ns:event", ns)
+    if not event:
+        print("Couldn't get an event!")
+        return None
+    if "{" + ns["ns"] + "}event" != event.tag:
+        print("Got a", event.tag, "but expected an event")
+        return None
+    try:
+        # e.g. "smi:org.gfz-potsdam.de/geofon/gfz2021ekhv"
+        evid = event.attrib["publicID"].split("/")[-1]
+    except AttributeError:
+        print("Oops")
+
     preferredoriginID = root[0][0].find("ns:preferredOriginID", ns).text
     preferredmagID = root[0][0].find("ns:preferredMagnitudeID", ns).text
     try:

tests/data/gfz2021ekhv.xml

+<?xml version="1.0" encoding="UTF-8"?><q:quakeml xmlns="http://quakeml.org/xmlns/bed/1.2" xmlns:q="http://quakeml.org/xmlns/quakeml/1.2"><eventParameters publicID="smi:org.gfz-potsdam.de/geofon/EventParameters"><event publicID="smi:org.gfz-potsdam.de/geofon/gfz2021ekhv"><description><text>Off E. Coast of N. Island, N.Z.</text><type>region name</type></description><creationInfo><agencyID>GFZ</agencyID><creationTime>2021-03-04T13:33:25.96342Z</creationTime></creationInfo><focalMechanism publicID="smi:org.gfz-potsdam.de/geofon/FocalMechanism/20210304152924.36933.1998992"><momentTensor publicID="smi:org.gfz-potsdam.de/geofon/MomentTensor/20210304152924.369853.1998995"><scalarMoment><value>7.705753735e+19</value></scalarMoment><tensor><Mrr><value>1.744746227e+19</value></Mrr><Mtt><value>-7.84343467e+19</value></Mtt><Mpp><value>6.098688444e+19</value></Mpp><Mrt><value>-1.125507602e+19</value></Mrt><Mrp><value>2.367758042e+19</value></Mrp><Mtp><value>-1.275457308e+19</value></Mtp></tensor><varianceReduction>0.9360097745</varianceReduction><doubleCouple>0.8172941413</doubleCouple><clvd>0.1827058587</clvd><creationInfo><agencyID>GFZ</agencyID><creationTime>2021-03-04T15:29:24.368901Z</creationTime></creationInfo><derivedOriginID>smi:org.gfz-potsdam.de/geofon/Origin/20210304152924.369602.1998993</derivedOriginID><momentMagnitudeID>smi:org.gfz-potsdam.de/geofon/Magnitude/20210304152924.369708.1998994</momentMagnitudeID><greensFunctionID>smi:org.gfz-potsdam.de/geofon/saul_/gemini-prem</greensFunctionID><filterID>smi:org.gfz-potsdam.de/geofon/BP_200s-600s</filterID></momentTensor><nodalPlanes><nodalPlane1><strike><value>307.1772288</value></strike><dip><value>77.29754332</value></dip><rake><value>158.5867752</value></rake></nodalPlane1><nodalPlane2><strike><value>42.10575122</value></strike><dip><value>69.13568422</value></dip><rake><value>13.6104104</value></rake></nodalPlane2></nodalPlanes><principalAxes><tAxis><azimuth><value>263.2979461</value></azimuth><plunge><value>24.03688788</value></plunge><length><value>7.311853502e+19</value></length></tAxis><pAxis><azimuth><value>355.7725032</value></azimuth><plunge><value>5.529375306</value></plunge><length><value>-8.046967561e+19</value></length></pAxis><nAxis><azimuth><value>97.89756857</value></azimuth><plunge><value>65.25588231</value></plunge><length><value>7.351140591e+18</value></length></nAxis></principalAxes><azimuthalGap>26.47275083</azimuthalGap><misfit>0.0639902255</misfit><creationInfo><agencyID>GFZ</agencyID><creationTime>2021-03-04T15:29:24.368901Z</creationTime></creationInfo><triggeringOriginID>smi:org.gfz-potsdam.de/geofon/Origin/20210304151039.157235.2466933</triggeringOriginID></focalMechanism><magnitude publicID="smi:org.gfz-potsdam.de/geofon/Magnitude/20210304152924.369708.1998994"><stationCount>106</stationCount><azimuthalGap>26.47275083</azimuthalGap><creationInfo><agencyID>GFZ</agencyID><creationTime>2021-03-04T15:29:24.368901Z</creationTime></creationInfo><mag><value>7.191210084</value></mag><type>Mw</type><methodID>smi:org.gfz-potsdam.de/geofon/MT</methodID></magnitude><origin publicID="smi:org.gfz-potsdam.de/geofon/Origin/20210304155627.269946.2475276"><time><value>2021-03-04T13:27:38.607455Z</value><uncertainty>0.7365945187</uncertainty></time><longitude><value>179.3604736</value><uncertainty>1.763208609</uncertainty></longitude><latitude><value>-37.37611389</value><uncertainty>1.978016315</uncertainty></latitude><quality><associatedPhaseCount>564</associatedPhaseCount><usedPhaseCount>186</usedPhaseCount><associatedStationCount>561</associatedStationCount><usedStationCount>186</usedStationCount><depthPhaseCount>0</depthPhaseCount><standardError>1.592724088</standardError><azimuthalGap>23.19470215</azimuthalGap><maximumDistance>114.4872208</maximumDistance><minimumDistance>1.98769486</minimumDistance><medianDistance>77.20787048</medianDistance></quality><evaluationMode>manual</evaluationMode><creationInfo><agencyID>GFZ</agencyID><creationTime>2021-03-04T15:56:27.282369Z</creationTime></creationInfo><depth><value>34801.78452</value><uncertainty>5773.60202</uncertainty></depth><originUncertainty><minHorizontalUncertainty>3743.951082</minHorizontalUncertainty><maxHorizontalUncertainty>4381.9561</maxHorizontalUncertainty><azimuthMaxHorizontalUncertainty>21.41514397</azimuthMaxHorizontalUncertainty><preferredDescription>horizontal uncertainty</preferredDescription></originUncertainty><methodID>smi:org.gfz-potsdam.de/geofon/LOCSAT</methodID><earthModelID>smi:org.gfz-potsdam.de/geofon/iasp91</earthModelID><evaluationStatus>confirmed</evaluationStatus></origin><preferredOriginID>smi:org.gfz-potsdam.de/geofon/Origin/20210304155627.269946.2475276</preferredOriginID><preferredMagnitudeID>smi:org.gfz-potsdam.de/geofon/Magnitude/20210304152924.369708.1998994</preferredMagnitudeID><preferredFocalMechanismID>smi:org.gfz-potsdam.de/geofon/FocalMechanism/20210304152924.36933.1998992</preferredFocalMechanismID><type>earthquake</type></event></eventParameters></q:quakeml>

tests/test_quakexml.py

+#
+# Author: Peter L. Evans <pevans@gfz-potsdam.de>
+#
+# Copyright (C) 2021 Helmholtz-Zentrum Potsdam - Deutsches GeoForschungsZentrum GFZ
+#
+# This software is free software and comes with ABSOLUTELY NO WARRANTY.
+#
+# ----------------------------------------------------------------------
+import os
+import unittest
+from shakyground2.import_fdsnws_eq import fetch_quakeml
+
+
+class QuakeMLReadTestCase(unittest.TestCase):
+    """Test on digesting QuakeML from GEOFON.
+
+    Beyond the basic test (read in QuakeML, export YAML), this would
+    also test the tricker input files: no focal mech available, focal
+    mech missing, multiple FMs, bad or incomplete XML, non-existent or
+    unreadable input files, and so on.
+
+    """
+
+    outfile = "data/testoutput.yaml"
+
+    def test_read_good_file(self):
+        infile = "data/gfz2021ekhv.xml"
+        result = fetch_quakeml(infile)
+        self.assertTrue(isinstance(result, dict))
+        self.assertEqual(result["id"], "gfz2021ekhv")
+
+    def test_read_good_eventid(self):
+        """
+        Might fail if the GEOFON fdsnws-event webservice is unavailable.
+        """
+        evid = "gfz2021ekhv"
+        result = fetch_quakeml(evid)
+        self.assertTrue(isinstance(result, dict))
+
+    def test_read_no_eventid(self):
+        """
+        The function is given a string which isn't a file and isn't an
+        event id other. So raise an error.
+        """
+        infile = "/no/such/file"
+        with self.assertRaises(IOError):
+            result = fetch_quakeml(infile)
+
+    def tearDown(self):
+        try:
+            os.unlink(self.outfile)
+        except FileNotFoundError:
+            pass
+
+
+if __name__ == "__main__":
+    unittest.main()