hdpws 0.6.25__tar.gz → 0.6.26__tar.gz

{hdpws-0.6.25 → hdpws-0.6.26}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.2
+Metadata-Version: 2.4
 Name: hdpws
-Version: 0.6.25
+Version: 0.6.26
 Summary: NASA's Heliophysics Data Portal Web Service Client Library
 Home-page: https://heliophysicsdata.gsfc.nasa.gov/WebServices
 Author: Bernie Harris
@@ -32,6 +32,7 @@ Dynamic: description-content-type
 Dynamic: home-page
 Dynamic: keywords
 Dynamic: license
+Dynamic: license-file
 Dynamic: requires-dist
 Dynamic: summary
 

{hdpws-0.6.25 → hdpws-0.6.26}/hdpws/__init__.py

@@ -41,7 +41,7 @@ the United States under Title 17, U.S.Code. All Other Rights Reserved.
 """
 
 
-__version__ = "0.6.25"
+__version__ = "0.6.26"
 
 
 #

{hdpws-0.6.25 → hdpws-0.6.26}/hdpws/hdpws.py

@@ -47,6 +47,7 @@ from dateutil import parser
 from hdpws import __version__, NAMESPACES as NS
 from hdpws.dateinterval import DateInterval
 from hdpws.resourcetype import ResourceType
+from hdpws.spasehtmlparser import SpaseHtmlParser
 
 
 #
@@ -594,7 +595,7 @@ class HdpWs:
             resource_id: str,
             **keywords: Union[
                 datetime]
-        ) -> str:
+        ) -> Dict:
         """
         Gets the an HTML representation of the specified SPASE document 
         from HDP.
@@ -658,6 +659,58 @@ class HdpWs:
         return result
 
 
+    def get_spase_json_ld(
+            self,
+            resource_id: str,
+            **keywords: Union[
+                datetime]
+        ) -> Dict:
+        """
+        Gets the an JSON-LD representation of the specified SPASE document 
+        from HDP.
+
+        Parameters
+        ----------
+        resource_id
+            SPASE ResourceID value of the document to get.
+        keywords
+            Optional keyword paramaters as follows:<br>
+            <b>if_modified_since</b> - conditional GET If-Modified-Since
+            datetime value.<br>
+
+        Returns
+        -------
+        Dict
+            Dictionary containing a 'Result' key whose value is the JSON-LD
+            representation of the specified SPASE document with the
+            addition of the following key/values:<br>
+            - HttpStatus: with the value of the HTTP status code.
+              Successful == 200.<br>
+            - Last-Modified: the value of the HTTP Last-Modified header
+              when available.<br>
+            When HttpStatus != 200:<br>
+            - HttpText: containing a string representation of the HTTP
+              entity body.<br>
+            When HttpText is a standard HDP WS error entity body the
+            following key/values (convenience to avoid parsing
+            HttpStatus):<br>
+            - ErrorMessage: value from HttpText.<br>
+            - ErrorDescription: value from HttpText.<br>
+        """
+
+        response = self.get_spase_html(resource_id, **keywords)
+
+        if response['HttpStatus'] != 200:
+            return response
+
+        spase_html_parser = SpaseHtmlParser()
+        spase_html_parser.feed(response['Result'])
+
+        response['Result'] = spase_html_parser.get_json_ld()
+
+        return response
+
+
     def get_spase_data(
             self,
             resource_types: List[ResourceType],

hdpws-0.6.26/hdpws/spasehtmlparser.py

@@ -0,0 +1,129 @@
+#!/usr/bin/env python3
+
+#
+# NOSA HEADER START
+#
+# The contents of this file are subject to the terms of the NASA Open
+# Source Agreement (NOSA), Version 1.3 only (the "Agreement").  You may
+# not use this file except in compliance with the Agreement.
+#
+# You can obtain a copy of the agreement at
+#   docs/NASA_Open_Source_Agreement_1.3.txt
+# or
+#   https://cdaweb.gsfc.nasa.gov/WebServices/NASA_Open_Source_Agreement_1.3.txt.
+#
+# See the Agreement for the specific language governing permissions
+# and limitations under the Agreement.
+#
+# When distributing Covered Code, include this NOSA HEADER in each
+# file and include the Agreement file at
+# docs/NASA_Open_Source_Agreement_1.3.txt.  If applicable, add the
+# following below this NOSA HEADER, with the fields enclosed by
+# brackets "[]" replaced with your own identifying information:
+# Portions Copyright [yyyy] [name of copyright owner]
+#
+# NOSA HEADER END
+#
+# Copyright (c) 2025 United States Government as represented by
+# the National Aeronautics and Space Administration. No copyright is
+# claimed in the United States under Title 17, U.S.Code. All Other
+# Rights Reserved.
+#
+
+
+"""
+Module defining a class to represent a SPASE HTML parser.  At present,
+its main function is to extract the JSON-LD embedded in an HTML
+representation of a SPASE XML document.  Any other information should
+be obtained from the original SPASE XML document.<br>
+
+Copyright &copy; 2025 United States Government as represented by the
+National Aeronautics and Space Administration. No copyright is claimed in
+the United States under Title 17, U.S.Code. All Other Rights Reserved.
+"""
+
+
+from html.parser import HTMLParser
+
+
+
+class SpaseHtmlParser(HTMLParser):
+    """
+    A class representing a SPASE HTML parser.
+
+    Parameters
+    ----------
+    json_ld_element
+        Flag indicating that we have encountered the json-ld element.
+        The value is set back to false when we encounter the end tag.
+    json_ld
+        The json-ld "data" extracted from the json-ld element.
+    """
+    def __init__(self):
+
+        super().__init__()
+
+        self._json_ld_element = False
+        self._json_ld = None
+
+
+    def handle_starttag(self, tag, attrs):
+        """
+        This method is called to handle the start tag of an element.
+
+        Parameters
+        ----------
+        tag
+            The name of the tag encountered.
+        attrs
+            List of (name, value) pairs containing the attributes found
+            inside the tag’s &lt;&gt; brackets. 
+        """
+
+        if tag == 'script':
+            for attr in attrs:
+                if attr[0] == 'type' and attr[1] == 'application/ld+json':
+                    self._json_ld_element = True
+
+
+    def handle_endtag(self, tag):
+        """
+        This method is called to handle the end tag of an element.
+
+        Parameters
+        ----------
+        tag
+            The name of the tag encountered.
+        """
+
+        self._json_ld_element = False
+
+
+    def handle_data(self, data):
+        """
+        This method is called to process arbitrary data (e.g. text nodes
+        and the content of &lt;script&gt;...&lt;/script&gt; and 
+        &lt;style&gt;...&lt;/style&gt;).
+
+        Parameters
+        ----------
+        data
+            The content of the element.
+        """
+
+        if self._json_ld_element:
+
+            self._json_ld = data
+
+
+    def get_json_ld(self) -> str:
+        """
+        Gets the JSON-LD from the SPASE HTML fed to this parser.
+
+        Returns:
+        --------
+        str
+            JSON-LD from the SPASE HTML or None.
+        """
+
+        return self._json_ld

{hdpws-0.6.25 → hdpws-0.6.26}/hdpws.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.2
+Metadata-Version: 2.4
 Name: hdpws
-Version: 0.6.25
+Version: 0.6.26
 Summary: NASA's Heliophysics Data Portal Web Service Client Library
 Home-page: https://heliophysicsdata.gsfc.nasa.gov/WebServices
 Author: Bernie Harris
@@ -32,6 +32,7 @@ Dynamic: description-content-type
 Dynamic: home-page
 Dynamic: keywords
 Dynamic: license
+Dynamic: license-file
 Dynamic: requires-dist
 Dynamic: summary
 

{hdpws-0.6.25 → hdpws-0.6.26}/hdpws.egg-info/SOURCES.txt

@@ -7,6 +7,7 @@ hdpws/dateinterval.py
 hdpws/hdpws.py
 hdpws/resourcetype.py
 hdpws/spase.py
+hdpws/spasehtmlparser.py
 hdpws.egg-info/PKG-INFO
 hdpws.egg-info/SOURCES.txt
 hdpws.egg-info/dependency_links.txt

{hdpws-0.6.25 → hdpws-0.6.26}/setup.py

@@ -10,7 +10,7 @@ README = (HERE / "README.md").read_text()
 # This call to setup() does all the work
 setup(
     name="hdpws",
-    version="0.6.25",
+    version="0.6.26",
     description="NASA's Heliophysics Data Portal Web Service Client Library",
     long_description=README,
     long_description_content_type="text/markdown",

{hdpws-0.6.25 → hdpws-0.6.26}/tests/test_hdpws.py

@@ -41,6 +41,7 @@ the United States under Title 17, U.S.Code. All Other Rights Reserved.
 import unittest
 import datetime
 import xml.etree.ElementTree as ET
+import json
 
 from context import hdpws  # pylint: disable=unused-import
 
@@ -316,6 +317,39 @@ class TestHdpWs(unittest.TestCase):
                          '{' + XHTML_NS + '}html')
 
 
+    def test_get_spase_json_ld(self):
+        """
+        Test for get_spase_json_ld function.
+        """
+
+        resource_id = 'spase://NASA/NumericalData/Wind/MFI/PT03S'
+
+        result = self._hdp.get_spase_json_ld(resource_id)
+
+        self.assertEqual(result['HttpStatus'], 200)
+
+        last_modified = result['Last-Modified']
+        self.assertIsNotNone(last_modified)
+
+        result = self._hdp.get_spase_json_ld(resource_id, 
+                                          if_modified_since=last_modified)
+
+        self.assertEqual(result['HttpStatus'], 304)
+
+        last_modified -= datetime.timedelta(seconds=5)
+        result = self._hdp.get_spase_json_ld(resource_id, 
+                                          if_modified_since=last_modified)
+
+        self.assertEqual(result['HttpStatus'], 200)
+        json_ld = json.loads(result['Result'])
+        self.assertEqual(json_ld['@context'], 'https://schema.org/')
+        self.assertEqual(json_ld['@type'], 'Dataset')
+#        print(result['Result'])
+#        result_element = ET.fromstring(result['Result'])
+#        self.assertEqual(result_element.tag, 
+#                         '{' + XHTML_NS + '}html')
+
+
     def test_get_spase_data(self):
         """
         Test for get_spase_data function.