add raw option to xml parser for _ attribute prefix

docs/parsers/xml.md

@@ -5,6 +5,11 @@
 
 jc - JSON Convert `XML` file parser
 
+This parser adds a `@` prefix to attributes by default. This can be changed
+to a `_` prefix by using the `-r` (cli) or `raw=True` (module) option.
+
+Text values for nodes will have the key-name of `#text`.
+
 Usage (cli):
 
     $ cat foo.xml | jc --xml
@@ -93,4 +98,4 @@ Returns:
 ### Parser Information
 Compatibility:  linux, darwin, cygwin, win32, aix, freebsd
 
-Version 1.6 by Kelly Brazil (kellyjonbrazil@gmail.com)
+Version 1.7 by Kelly Brazil (kellyjonbrazil@gmail.com)

jc/parsers/xml.py

@@ -1,5 +1,10 @@
 """jc - JSON Convert `XML` file parser
 
+This parser adds a `@` prefix to attributes by default. This can be changed
+to a `_` prefix by using the `-r` (cli) or `raw=True` (module) option.
+
+Text values for nodes will have the key-name of `#text`.
+
 Usage (cli):
 
     $ cat foo.xml | jc --xml
@@ -68,10 +73,15 @@ Examples:
 import jc.utils
 from jc.exceptions import LibraryNotInstalled
 
+try:
+    import xmltodict
+except Exception:
+    raise LibraryNotInstalled('The xmltodict library is not installed.')
+
 
 class info():
     """Provides parser metadata (version, author, etc.)"""
-    version = '1.6'
+    version = '1.7'
     description = 'XML file parser'
     author = 'Kelly Brazil'
     author_email = 'kellyjonbrazil@gmail.com'
@@ -82,7 +92,7 @@ class info():
 __version__ = info.version
 
 
-def _process(proc_data):
+def _process(proc_data, has_data=False):
     """
     Final processing to conform to the schema.
 
@@ -94,9 +104,13 @@ def _process(proc_data):
 
         Dictionary representing an XML document.
     """
+    raw_output = []
 
-    # No further processing
+    if has_data:
-    return proc_data
+        # standard output with @ prefix for attributes
+        raw_output = xmltodict.parse(proc_data)
+
+    return raw_output
 
 
 def parse(data, raw=False, quiet=False):
@@ -113,22 +127,19 @@ def parse(data, raw=False, quiet=False):
 
         Dictionary. Raw or processed structured data.
     """
-    # check if xml library is installed and fail gracefully if it is not
-    try:
-        import xmltodict
-    except Exception:
-        raise LibraryNotInstalled('The xmltodict library is not installed.')
-
     jc.utils.compatibility(__name__, info.compatible, quiet)
     jc.utils.input_type_check(data)
 
     raw_output = []
+    has_data = False
 
     if jc.utils.has_data(data):
+        has_data = True
 
-        raw_output = xmltodict.parse(data)
+        # modified output with _ prefix for attributes
+        raw_output = xmltodict.parse(data, attr_prefix='_')
 
     if raw:
         return raw_output
     else:
-        return _process(raw_output)
+        return _process(data, has_data)

tests/fixtures/generic/xml-nmap-raw.json

@@ -0,0 +1 @@
+{"nmaprun":{"_scanner":"nmap","_args":"nmap -oX - -p 443 galaxy.ansible.com","_start":"1666781498","_startstr":"Wed Oct 26 11:51:38 2022","_version":"7.92","_xmloutputversion":"1.05","scaninfo":{"_type":"connect","_protocol":"tcp","_numservices":"1","_services":"443"},"verbose":{"_level":"0"},"debugging":{"_level":"0"},"hosthint":{"status":{"_state":"up","_reason":"unknown-response","_reason_ttl":"0"},"address":{"_addr":"172.67.68.251","_addrtype":"ipv4"},"hostnames":{"hostname":{"_name":"galaxy.ansible.com","_type":"user"}}},"host":{"_starttime":"1666781498","_endtime":"1666781498","status":{"_state":"up","_reason":"syn-ack","_reason_ttl":"0"},"address":{"_addr":"172.67.68.251","_addrtype":"ipv4"},"hostnames":{"hostname":[{"_name":"galaxy.ansible.com","_type":"user"},{"_name":"galaxy.ansible.com","_type":"PTR"}]},"ports":{"port":{"_protocol":"tcp","_portid":"443","state":{"_state":"open","_reason":"syn-ack","_reason_ttl":"0"},"service":{"_name":"https","_method":"table","_conf":"3"}}},"times":{"_srtt":"12260","_rttvar":"9678","_to":"100000"}},"runstats":{"finished":{"_time":"1666781498","_timestr":"Wed Oct 26 11:51:38 2022","_summary":"Nmap done at Wed Oct 26 11:51:38 2022; 1 IP address (1 host up) scanned in 0.10 seconds","_elapsed":"0.10","_exit":"success"},"hosts":{"_up":"1","_down":"0","_total":"1"}}}}

tests/fixtures/generic/xml-nmap.json

@@ -0,0 +1 @@
+{"nmaprun":{"@scanner":"nmap","@args":"nmap -oX - -p 443 galaxy.ansible.com","@start":"1666781498","@startstr":"Wed Oct 26 11:51:38 2022","@version":"7.92","@xmloutputversion":"1.05","scaninfo":{"@type":"connect","@protocol":"tcp","@numservices":"1","@services":"443"},"verbose":{"@level":"0"},"debugging":{"@level":"0"},"hosthint":{"status":{"@state":"up","@reason":"unknown-response","@reason_ttl":"0"},"address":{"@addr":"172.67.68.251","@addrtype":"ipv4"},"hostnames":{"hostname":{"@name":"galaxy.ansible.com","@type":"user"}}},"host":{"@starttime":"1666781498","@endtime":"1666781498","status":{"@state":"up","@reason":"syn-ack","@reason_ttl":"0"},"address":{"@addr":"172.67.68.251","@addrtype":"ipv4"},"hostnames":{"hostname":[{"@name":"galaxy.ansible.com","@type":"user"},{"@name":"galaxy.ansible.com","@type":"PTR"}]},"ports":{"port":{"@protocol":"tcp","@portid":"443","state":{"@state":"open","@reason":"syn-ack","@reason_ttl":"0"},"service":{"@name":"https","@method":"table","@conf":"3"}}},"times":{"@srtt":"12260","@rttvar":"9678","@to":"100000"}},"runstats":{"finished":{"@time":"1666781498","@timestr":"Wed Oct 26 11:51:38 2022","@summary":"Nmap done at Wed Oct 26 11:51:38 2022; 1 IP address (1 host up) scanned in 0.10 seconds","@elapsed":"0.10","@exit":"success"},"hosts":{"@up":"1","@down":"0","@total":"1"}}}}

tests/fixtures/generic/xml-nmap.xml

@@ -0,0 +1,36 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE nmaprun>
+<?xml-stylesheet href="file:///usr/bin/../share/nmap/nmap.xsl" type="text/xsl"?>
+<!-- Nmap 7.92 scan initiated Wed Oct 26 11:51:38 2022 as: nmap -oX - -p 443 galaxy.ansible.com -->
+<nmaprun scanner="nmap" args="nmap -oX - -p 443 galaxy.ansible.com" start="1666781498" startstr="Wed Oct 26 11:51:38 2022" version="7.92" xmloutputversion="1.05">
+  <scaninfo type="connect" protocol="tcp" numservices="1" services="443"/>
+  <verbose level="0"/>
+  <debugging level="0"/>
+  <hosthint>
+    <status state="up" reason="unknown-response" reason_ttl="0"/>
+    <address addr="172.67.68.251" addrtype="ipv4"/>
+    <hostnames>
+      <hostname name="galaxy.ansible.com" type="user"/>
+    </hostnames>
+  </hosthint>
+  <host starttime="1666781498" endtime="1666781498">
+    <status state="up" reason="syn-ack" reason_ttl="0"/>
+    <address addr="172.67.68.251" addrtype="ipv4"/>
+    <hostnames>
+      <hostname name="galaxy.ansible.com" type="user"/>
+      <hostname name="galaxy.ansible.com" type="PTR"/>
+    </hostnames>
+    <ports>
+      <port protocol="tcp" portid="443">
+        <state state="open" reason="syn-ack" reason_ttl="0"/>
+        <service name="https" method="table" conf="3"/>
+      </port>
+    </ports>
+    <times srtt="12260" rttvar="9678" to="100000"/>
+  </host>
+  <runstats>
+    <finished time="1666781498" timestr="Wed Oct 26 11:51:38 2022" summary="Nmap done at Wed Oct 26 11:51:38 2022; 1 IP address (1 host up) scanned in 0.10 seconds" elapsed="0.10" exit="success"/>
+    <hosts up="1" down="0" total="1"/>
+  </runstats>
+</nmaprun>
+

tests/test_xml.py

@@ -15,6 +15,9 @@ class MyTests(unittest.TestCase):
     with open(os.path.join(THIS_DIR, os.pardir, 'tests/fixtures/generic/xml-foodmenu.xml'), 'r', encoding='utf-8') as f:
         generic_xml_foodmenu = f.read()
 
+    with open(os.path.join(THIS_DIR, os.pardir, 'tests/fixtures/generic/xml-nmap.xml'), 'r', encoding='utf-8') as f:
+        generic_xml_nmap = f.read()
+
     # output
     with open(os.path.join(THIS_DIR, os.pardir, 'tests/fixtures/generic/xml-cd_catalog.json'), 'r', encoding='utf-8') as f:
         generic_xml_cd_catalog_json = json.loads(f.read())
@@ -22,6 +25,12 @@ class MyTests(unittest.TestCase):
     with open(os.path.join(THIS_DIR, os.pardir, 'tests/fixtures/generic/xml-foodmenu.json'), 'r', encoding='utf-8') as f:
         generic_xml_foodmenu_json = json.loads(f.read())
 
+    with open(os.path.join(THIS_DIR, os.pardir, 'tests/fixtures/generic/xml-nmap.json'), 'r', encoding='utf-8') as f:
+        generic_xml_nmap_json = json.loads(f.read())
+
+    with open(os.path.join(THIS_DIR, os.pardir, 'tests/fixtures/generic/xml-nmap-raw.json'), 'r', encoding='utf-8') as f:
+        generic_xml_nmap_r_json = json.loads(f.read())
+
 
     def test_xml_nodata(self):
         """
@@ -29,6 +38,12 @@ class MyTests(unittest.TestCase):
         """
         self.assertEqual(jc.parsers.xml.parse('', quiet=True), [])
 
+    def test_xml_nodata_r(self):
+        """
+        Test xml parser with no data and raw output
+        """
+        self.assertEqual(jc.parsers.xml.parse('', raw=True, quiet=True), [])
+
     def test_xml_cd_catalog(self):
         """
         Test the cd catalog xml file
@@ -41,6 +56,18 @@ class MyTests(unittest.TestCase):
         """
         self.assertEqual(jc.parsers.xml.parse(self.generic_xml_foodmenu, quiet=True), self.generic_xml_foodmenu_json)
 
+    def test_xml_nmap(self):
+        """
+        Test nmap xml output
+        """
+        self.assertEqual(jc.parsers.xml.parse(self.generic_xml_nmap, quiet=True), self.generic_xml_nmap_json)
+
+    def test_xml_nmap_r(self):
+        """
+        Test nmap xml raw output
+        """
+        self.assertEqual(jc.parsers.xml.parse(self.generic_xml_nmap, raw=True, quiet=True), self.generic_xml_nmap_r_json)
+
 
 if __name__ == '__main__':
     unittest.main()