Create urlsplit filter (#28537)

* Improve tests for uri filter

* Create URL Split docs

* Add urlsplit filter

* Py3 compatibility

* Use helper method and eliminate query options

* Add options, cleanup output, fix tests

* Update docs

* Add parenthesis to boilerplate import

* Add debug task to tests

* Use exclude option to filter returned values

* Filter out additional option for Python 3

docs/docsite/rst/playbooks_filters.rst

@@ -594,6 +594,56 @@ which will produce this output:
 
 .. _other_useful_filters:
 
+URL Split Filter
+`````````````````
+
+.. versionadded:: 2.4
+
+The ``urlsplit`` filter extracts the fragment, hostname, netloc, password, path, port, query, scheme, and username from an URL. With no arguments, returns a dictionary of all the fields::
+
+    {{ "http://user:password@www.acme.com:9000/dir/index.html?query=term#frament" | urlsplit('hostname') }}
+    # => 'www.acme.com'
+
+    {{ "http://user:password@www.acme.com:9000/dir/index.html?query=term#frament" | urlsplit('netloc') }}
+    # => 'user:password@www.acme.com:9000'
+
+    {{ "http://user:password@www.acme.com:9000/dir/index.html?query=term#frament" | urlsplit('username') }}
+    # => 'user'
+
+    {{ "http://user:password@www.acme.com:9000/dir/index.html?query=term#frament" | urlsplit('password') }}
+    # => 'password'
+
+    {{ "http://user:password@www.acme.com:9000/dir/index.html?query=term#frament" | urlsplit('path') }}
+    # => '/dir/index.html'
+
+    {{ "http://user:password@www.acme.com:9000/dir/index.html?query=term#frament" | urlsplit('port') }}
+    # => '9000'
+
+    {{ "http://user:password@www.acme.com:9000/dir/index.html?query=term#frament" | urlsplit('scheme') }}
+    # => 'http'
+
+    {{ "http://user:password@www.acme.com:9000/dir/index.html?query=term#frament" | urlsplit('query') }}
+    # => 'query=term'
+
+    {{ "http://user:password@www.acme.com:9000/dir/index.html?query=term#frament" | urlsplit('fragment') }}
+    # => 'fragment'
+
+    {{ "http://user:password@www.acme.com:9000/dir/index.html?query=term#frament" | urlsplit }}
+    # =>
+    #   {
+    #       "fragment": "fragment",
+    #       "hostname": "www.acme.com",
+    #       "netloc": "user:password@www.acme.com:9000",
+    #       "password": "password",
+    #       "path": "/dir/index.html",
+    #       "port": 9000,
+    #       "query": "query=term",
+    #       "scheme": "http",
+    #       "username": "user"
+    #   }
+
+
+
 Other Useful Filters
 ````````````````````
 
@@ -717,26 +767,26 @@ To get permutations of a list::
     - name: give me largest permutations (order matters)
       debug: msg="{{ [1,2,3,4,5]|permutations|list }}"
 
-    - name: give me permutations of sets of 3
+    - name: give me permutations of sets of three
       debug: msg="{{ [1,2,3,4,5]|permutations(3)|list }}"
 
 Combinations always require a set size::
 
-    - name: give me combinations for sets of 2
+    - name: give me combinations for sets of two
       debug: msg="{{ [1,2,3,4,5]|combinations(2)|list }}"
 
 
 To get a list combining the elements of other lists use ``zip``::
 
-    - name: give me list combo of 2 lists 
+    - name: give me list combo of two lists
       debug: msg="{{ [1,2,3,4,5]|zip(['a','b','c','d','e','f'])|list }}"
 
-    - name: give me shortest combo of 2 lists
+    - name: give me shortest combo of two lists
       debug: msg="{{ [1,2,3]|zip(['a','b','c','d','e','f'])|list }}"
 
 To always exhaust all list use ``zip_longest``::
 
-    - name: give me longest combo of 3 lists , fill with X
+    - name: give me longest combo of three lists , fill with X
       debug: msg="{{ [1,2,3]|zip_longest(['a','b','c','d','e','f'], [21, 22, 23], fillvalue='X')|list }}"
 
 

lib/ansible/plugins/filter/urlsplit.py

@@ -0,0 +1,42 @@
+# Copyright (c) 2017 Ansible Project
+# GNU General Public License v3.0+ (see COPYING or https://www.gnu.org/licenses/gpl-3.0.txt)
+
+
+from __future__ import (absolute_import, division, print_function)
+__metaclass__ = type
+
+
+ANSIBLE_METADATA = {
+    'metadata_version': '1.1',
+    'status': ['preview'],
+    'supported_by': 'community'
+}
+
+
+from ansible.errors import AnsibleFilterError
+from ansible.module_utils.six.moves.urllib.parse import urlsplit
+from ansible.utils import helpers
+
+
+def split_url(value, query='', alias='urlsplit'):
+
+    results = helpers.object_to_dict(urlsplit(value), exclude=['count', 'index', 'geturl', 'encode'])
+
+    # If a query is supplied, make sure it's valid then return the results.
+    # If no option is supplied, return the entire dictionary.
+    if query:
+        if query not in results:
+            raise AnsibleFilterError(alias + ': unknown URL component: %s' % query)
+        return results[query]
+    else:
+        return results
+
+
+# ---- Ansible filters ----
+class FilterModule(object):
+    ''' URI filter '''
+
+    def filters(self):
+        return {
+            'urlsplit': split_url
+        }

test/integration/targets/filters/tasks/main.yml

@@ -20,10 +20,14 @@
   shell: echo hi
   register: some_registered_var
 
-- debug: var=some_registered_var
+- debug:
+    var: some_registered_var
 
 - name: Verify that we workaround a py26 json bug
-  template: src=py26json.j2 dest={{output_dir}}/py26json.templated mode=0644
+  template:
+    src: py26json.j2
+    dest: "{{ output_dir }}/py26json.templated"
+    mode: 0644
 
 - name: 9851 - Verify that we don't trigger https://github.com/ansible/ansible/issues/9851
   copy:
@@ -33,7 +37,9 @@
   - {"k": "Quotes \"'\n"}
 
 - name: 9851 - copy known good output into place
-  copy: src=9851.txt dest={{output_dir}}/9851.txt
+  copy:
+    src: 9851.txt
+    dest: "{{ output_dir }}/9851.txt"
 
 - name: 9851 - Compare generated json to known good
   shell: diff -w {{ output_dir }}/9851.out {{ output_dir }}/9851.txt
@@ -45,11 +51,16 @@
         - 'diff_result_9851.stdout == ""'
 
 - name: fill in a basic template
-  template: src=foo.j2 dest={{output_dir}}/foo.templated mode=0644
+  template:
+    src: foo.j2
+    dest: "{{ output_dir }}/foo.templated"
+    mode: 0644
   register: template_result
 
 - name: copy known good into place
-  copy: src=foo.txt dest={{output_dir}}/foo.txt
+  copy:
+    src: foo.txt
+    dest: "{{ output_dir }}/foo.txt"
 
 - name: compare templated file to known good
   shell: diff -w {{ output_dir }}/foo.templated {{ output_dir }}/foo.txt
@@ -85,15 +96,16 @@
       - "{{'10.00 Kb'|human_to_bytes(isbits=True)}} == 10240"
 
 - name: Verify human_to_bytes (bad string)
-  tags: "human_to_bytes"
-  set_fact: bad_string="{{'10.00 foo'|human_to_bytes}}"
+  set_fact:
+    bad_string: "{{ '10.00 foo' | human_to_bytes }}"
   ignore_errors: yes
-  register: _
+  tags: human_to_bytes
+  register: _human_bytes_test
 
 - name: Verify human_to_bytes (bad string)
-  tags: "human_to_bytes"
+  tags: human_to_bytes
   assert:
-    that: "{{_.failed}}"
+    that: "{{_human_bytes_test.failed}}"
 
 - name: Test extract
   assert:
@@ -120,22 +132,40 @@
     that:
       - "users | json_query('[*].hosts[].host') == ['host_a', 'host_b', 'host_c', 'host_d']"
 
-- name: "20379 - set_fact app_var_git_branch "
-  set_fact:
-    app_var_git_branch: multi-deployment-400-743
+- name: Test hash filter
+  assert:
+    that:
+      - '"{{ "hash" | hash("sha1") }}" == "2346ad27d7568ba9896f1b7da6b5991251debdf2"'
+      - '"{{ "café" | hash("sha1") }}" == "f424452a9673918c6f09b0cdd35b20be8e6ae7d7"'
 
-- name: "20379 - trigger a error in jmespath via json_query filter to test error handling"
-  debug:
-    msg: "{{ example_20379 | json_query('ApplicationVersions[].VersionLabel[] | [?starts_with(@, `multi`)]') }}"
-  ignore_errors: true
+- debug:
+    var: "'http://mary:MySecret@www.acme.com:9000/dir/index.html?query=term#fragment' | urlsplit"
+    verbosity: 1
+  tags: debug
 
-- name: "20379 - Test errors related to https://github.com/ansible/ansible/issues/20379"
+- name: Test urlsplit filter
   assert:
-    that: "example_20379 | json_query('ApplicationVersions[].VersionLabel[] | [?starts_with(@, '+app_var_git_branch+')] | [2:]') == multisdfsdf"
-  ignore_errors: true
+    that:
+      - "'http://mary:MySecret@www.acme.com:9000/dir/index.html?query=term#fragment' | urlsplit('fragment') == 'fragment'"
+      - "'http://mary:MySecret@www.acme.com:9000/dir/index.html?query=term#fragment' | urlsplit('hostname') == 'www.acme.com'"
+      - "'http://mary:MySecret@www.acme.com:9000/dir/index.html?query=term#fragment' | urlsplit('netloc') == 'mary:MySecret@www.acme.com:9000'"
+      - "'http://mary:MySecret@www.acme.com:9000/dir/index.html?query=term#fragment' | urlsplit('path') == '/dir/index.html'"
+      - "'http://mary:MySecret@www.acme.com:9000/dir/index.html?query=term#fragment' | urlsplit('port') == 9000"
+      - "'http://mary:MySecret@www.acme.com:9000/dir/index.html?query=term#fragment' | urlsplit('query') == 'query=term'"
+      - "'http://mary:MySecret@www.acme.com:9000/dir/index.html?query=term#fragment' | urlsplit('scheme') == 'http'"
+      - "'http://mary:MySecret@www.acme.com:9000/dir/index.html?query=term#fragment' | urlsplit('username') == 'mary'"
+      - "'http://mary:MySecret@www.acme.com:9000/dir/index.html?query=term#fragment' | urlsplit('password') == 'MySecret'"
+      - "'http://mary:MySecret@www.acme.com:9000/dir/index.html?query=term#fragment' | urlsplit == { 'fragment': 'fragment', 'hostname': 'www.acme.com', 'netloc': 'mary:MySecret@www.acme.com:9000', 'password': 'MySecret', 'path': '/dir/index.html', 'port': 9000, 'query': 'query=term', 'scheme': 'http', 'username': 'mary' }"
+
+
+- name: Test urlsplit filter bad argument
+  debug:
+    var: "'http://www.acme.com:9000/dir/index.html' | urlsplit('bad_filter')"
+  register: _bad_urlsplit_filter
+  ignore_errors: yes
 
-- name: Test hash filter
+- name: Verify urlsplit filter showed an error message
   assert:
     that:
-      - '"{{ "hash" | hash("sha1") }}" == "2346ad27d7568ba9896f1b7da6b5991251debdf2"'
-      - '"{{ "café" | hash("sha1") }}" == "f424452a9673918c6f09b0cdd35b20be8e6ae7d7"'
+      - _bad_urlsplit_filter | failed
+      - "'unknown URL component' in _bad_urlsplit_filter.msg"