ansible-core 2.18.7rc1__py3-none-any.whl → 2.19.0__py3-none-any.whl

ansible/modules/find.py

@@ -9,7 +9,7 @@
 from __future__ import annotations
 
 
-DOCUMENTATION = r'''
+DOCUMENTATION = r"""
 ---
 module: find
 author: Brian Coca (@bcoca)
@@ -29,6 +29,10 @@ options:
             - You can choose seconds, minutes, hours, days, or weeks by specifying the
               first letter of any of those words (e.g., "1w").
         type: str
+    get_checksum:
+        default: false
+    checksum_algorithm:
+        version_added: "2.19"
     patterns:
         default: []
         description:
@@ -132,11 +136,6 @@ options:
             - Set this to V(true) to follow symlinks in path for systems with python 2.6+.
         type: bool
         default: no
-    get_checksum:
-        description:
-            - Set this to V(true) to retrieve a file's SHA1 checksum.
-        type: bool
-        default: no
     use_regex:
         description:
             - If V(false), the patterns are file globs (shell).
@@ -163,7 +162,7 @@ options:
             - Default is unlimited matches.
         type: int
         version_added: "2.18"
-extends_documentation_fragment: action_common_attributes
+extends_documentation_fragment: [action_common_attributes, checksum_common]
 attributes:
     check_mode:
         details: since this action does not modify the target it just executes normally during check mode
@@ -174,10 +173,10 @@ attributes:
         platforms: posix
 seealso:
 - module: ansible.windows.win_find
-'''
+"""
 
 
-EXAMPLES = r'''
+EXAMPLES = r"""
 - name: Recursively find /tmp files older than 2 days
   ansible.builtin.find:
     paths: /tmp
@@ -246,9 +245,9 @@ EXAMPLES = r'''
     use_regex: true
     recurse: true
     limit: 1
-'''
+"""
 
-RETURN = r'''
+RETURN = r"""
 files:
     description: All matches found with the specified criteria (see stat module for full output of each dictionary)
     returned: success
@@ -279,7 +278,7 @@ skipped_paths:
     type: dict
     sample: {"/laskdfj": "'/laskdfj' is not a directory"}
     version_added: '2.12'
-'''
+"""
 
 import errno
 import fnmatch
@@ -302,7 +301,7 @@ class _Object:
 
 
 def pfilter(f, patterns=None, excludes=None, use_regex=False):
-    '''filter using glob patterns'''
+    """filter using glob patterns"""
     if not patterns and not excludes:
         return True
 
@@ -341,7 +340,7 @@ def pfilter(f, patterns=None, excludes=None, use_regex=False):
 
 
 def agefilter(st, now, age, timestamp):
-    '''filter files older than age'''
+    """filter files older than age"""
     if age is None:
         return True
     elif age >= 0 and now - getattr(st, "st_%s" % timestamp) >= abs(age):
@@ -352,7 +351,7 @@ def agefilter(st, now, age, timestamp):
 
 
 def sizefilter(st, size):
-    '''filter files greater than size'''
+    """filter files greater than size"""
     if size is None:
         return True
     elif size >= 0 and st.st_size >= abs(size):
@@ -482,6 +481,9 @@ def main():
             hidden=dict(type='bool', default=False),
             follow=dict(type='bool', default=False),
             get_checksum=dict(type='bool', default=False),
+            checksum_algorithm=dict(type='str', default='sha1',
+                                    choices=['md5', 'sha1', 'sha224', 'sha256', 'sha384', 'sha512'],
+                                    aliases=['checksum', 'checksum_algo']),
             use_regex=dict(type='bool', default=False),
             depth=dict(type='int'),
             mode=dict(type='raw'),
@@ -569,9 +571,9 @@ def main():
 
                     try:
                         st = os.lstat(fsname)
-                    except (IOError, OSError) as e:
-                        module.warn("Skipped entry '%s' due to this access issue: %s\n" % (fsname, to_text(e)))
-                        skipped[fsname] = to_text(e)
+                    except OSError as ex:
+                        module.error_as_warning(f"Skipped entry {fsname!r} due to access issue.", exception=ex)
+                        skipped[fsname] = str(ex)
                         has_warnings = True
                         continue
 
@@ -583,7 +585,7 @@ def main():
 
                             r.update(statinfo(st))
                             if stat.S_ISREG(st.st_mode) and params['get_checksum']:
-                                r['checksum'] = module.sha1(fsname)
+                                r['checksum'] = module.digest_from_file(fsname, params['checksum_algorithm'])
 
                             if stat.S_ISREG(st.st_mode):
                                 if sizefilter(st, size):
@@ -608,7 +610,7 @@ def main():
 
                             r.update(statinfo(st))
                             if params['get_checksum']:
-                                r['checksum'] = module.sha1(fsname)
+                                r['checksum'] = module.digest_from_file(fsname, params['checksum_algorithm'])
                             filelist.append(r)
 
                     elif stat.S_ISLNK(st.st_mode) and params['file_type'] == 'link':

ansible/modules/gather_facts.py

@@ -1,11 +1,11 @@
 # -*- coding: utf-8 -*-
-# Copyright (c) 2017 Ansible Project
+# Copyright: Contributors to the Ansible project
 # GNU General Public License v3.0+ (see COPYING or https://www.gnu.org/licenses/gpl-3.0.txt)
 
 from __future__ import annotations
 
 
-DOCUMENTATION = '''
+DOCUMENTATION = """
 ---
 module: gather_facts
 version_added: 2.8
@@ -57,7 +57,7 @@ notes:
       Order is not guaranteed, when doing parallel gathering on multiple modules.
 author:
     - "Ansible Core Team"
-'''
+"""
 
 RETURN = """
 # depends on the fact module called

ansible/modules/get_url.py

@@ -6,7 +6,7 @@
 from __future__ import annotations
 
 
-DOCUMENTATION = r'''
+DOCUMENTATION = r"""
 ---
 module: get_url
 short_description: Downloads files from HTTP, HTTPS, or FTP to node
@@ -87,7 +87,7 @@ options:
       - 'If a checksum is passed to this parameter, the digest of the
         destination file will be calculated after it is downloaded to ensure
         its integrity and verify that the transfer completed successfully.
-        Format: <algorithm>:<checksum|url>, for example C(checksum="sha256:D98291AC[...]B6DC7B97",
+        Format: <algorithm>:<checksum|url>, for example C(checksum="sha256:D98291AC[...]B6DC7B97"),
         C(checksum="sha256:http://example.com/path/sha256sum.txt").'
       - If you worry about portability, only the sha1 algorithm is available
         on all platforms and python versions.
@@ -219,9 +219,9 @@ seealso:
 - module: ansible.windows.win_get_url
 author:
 - Jan-Piet Mens (@jpmens)
-'''
+"""
 
-EXAMPLES = r'''
+EXAMPLES = r"""
 - name: Download foo.conf
   ansible.builtin.get_url:
     url: http://example.com/path/file.conf
@@ -272,9 +272,9 @@ EXAMPLES = r'''
     dest: /etc/foo.conf
     username: bar
     password: '{{ mysecret }}'
-'''
+"""
 
-RETURN = r'''
+RETURN = r"""
 backup_file:
     description: name of backup file created after download
     returned: changed and if backup=yes
@@ -365,17 +365,18 @@ url:
     returned: always
     type: str
     sample: https://www.ansible.com/
-'''
+"""
 
+import email.message
 import os
 import re
 import shutil
 import tempfile
-import traceback
+
+from datetime import datetime, timezone
 
 from ansible.module_utils.basic import AnsibleModule
 from ansible.module_utils.six.moves.urllib.parse import urlsplit
-from ansible.module_utils.compat.datetime import utcnow, utcfromtimestamp
 from ansible.module_utils.common.text.converters import to_native
 from ansible.module_utils.urls import fetch_url, url_argument_spec
 
@@ -398,10 +399,10 @@ def url_get(module, url, dest, use_proxy, last_mod_time, force, timeout=10, head
     Return (tempfile, info about the request)
     """
 
-    start = utcnow()
+    start = datetime.now(timezone.utc)
     rsp, info = fetch_url(module, url, use_proxy=use_proxy, force=force, last_mod_time=last_mod_time, timeout=timeout, headers=headers, method=method,
                           unredirected_headers=unredirected_headers, decompress=decompress, ciphers=ciphers, use_netrc=use_netrc)
-    elapsed = (utcnow() - start).seconds
+    elapsed = (datetime.now(timezone.utc) - start).seconds
 
     if info['status'] == 304:
         module.exit_json(url=url, dest=dest, changed=False, msg=info.get('msg', ''), status_code=info['status'], elapsed=elapsed)
@@ -432,30 +433,40 @@ def url_get(module, url, dest, use_proxy, last_mod_time, force, timeout=10, head
         shutil.copyfileobj(rsp, f)
     except Exception as e:
         os.remove(tempname)
-        module.fail_json(msg="failed to create temporary content file: %s" % to_native(e), elapsed=elapsed, exception=traceback.format_exc())
+        module.fail_json(msg="failed to create temporary content file: %s" % to_native(e), elapsed=elapsed)
     f.close()
     rsp.close()
-    return tempname, info
 
+    # Since shutil.copyfileobj() will read from HTTPResponse in chunks, HTTPResponse.read() will not recognize
+    # if the entire content-length of data was not read. We need to do that validation here, unless a 'chunked'
+    # transfer-encoding was used, in which case we will not know content-length because it will not be returned.
+    # But in that case, HTTPResponse will behave correctly and recognize an IncompleteRead.
 
-def extract_filename_from_headers(headers):
-    """
-    Extracts a filename from the given dict of HTTP headers.
+    is_gzip = info.get('content-encoding') == 'gzip'
 
-    Looks for the content-disposition header and applies a regex.
-    Returns the filename if successful, else None."""
-    cont_disp_regex = 'attachment; ?filename="?([^"]+)'
-    res = None
+    if not module.check_mode and 'content-length' in info:
+        # If data is decompressed, then content-length won't match the amount of data we've read, so skip.
+        if not is_gzip or (is_gzip and not decompress):
+            st = os.stat(tempname)
+            cl = int(info['content-length'])
+            if st.st_size != cl:
+                diff = cl - st.st_size
+                module.fail_json(msg=f'Incomplete read, ({rsp.length=}, {cl=}, {st.st_size=}) failed to read remaining {diff} bytes')
 
-    if 'content-disposition' in headers:
-        cont_disp = headers['content-disposition']
-        match = re.match(cont_disp_regex, cont_disp)
-        if match:
-            res = match.group(1)
-            # Try preventing any funny business.
-            res = os.path.basename(res)
+    return tempname, info
+
+
+def extract_filename_from_headers(headers):
+    """Extracts a filename from the given dict of HTTP headers.
 
-    return res
+    Returns the filename if successful, else None.
+    """
+    msg = email.message.Message()
+    msg['content-disposition'] = headers.get('content-disposition', '')
+    if filename := msg.get_param('filename', header='content-disposition'):
+        # Avoid directory traversal
+        filename = os.path.basename(filename)
+    return filename
 
 
 def is_url(checksum):
@@ -466,6 +477,37 @@ def is_url(checksum):
     return urlsplit(checksum).scheme in supported_schemes
 
 
+def parse_digest_lines(filename, lines):
+    """Returns a list of tuple containing the filename and digest depending upon
+      the lines provided
+
+    Args:
+        filename (str): Name of the filename, used only when the digest is one-liner
+        lines (list): A list of lines containing filenames and checksums
+    """
+    checksum_map = []
+    BSD_DIGEST_LINE = re.compile(r'^(\w+) ?\((?P<path>.+)\) ?= (?P<digest>[\w.]+)$')
+    GNU_DIGEST_LINE = re.compile(r'^(?P<digest>[\w.]+) ([ *])(?P<path>.+)$')
+
+    if len(lines) == 1 and len(lines[0].split()) == 1:
+        # Only a single line with a single string
+        # treat it as a checksum only file
+        checksum_map.append((lines[0], filename))
+        return checksum_map
+    # The assumption here is the file is in the format of
+    # checksum filename
+    for line in lines:
+        match = BSD_DIGEST_LINE.match(line)
+        if match:
+            checksum_map.append((match.group('digest'), match.group('path')))
+        else:
+            match = GNU_DIGEST_LINE.match(line)
+            if match:
+                checksum_map.append((match.group('digest'), match.group('path').lstrip("./")))
+
+    return checksum_map
+
+
 # ==============================================================
 # main
 
@@ -533,31 +575,13 @@ def main():
         if is_url(checksum):
             checksum_url = checksum
             # download checksum file to checksum_tmpsrc
-            checksum_tmpsrc, checksum_info = url_get(module, checksum_url, dest, use_proxy, last_mod_time, force, timeout, headers, tmp_dest,
-                                                     unredirected_headers=unredirected_headers, ciphers=ciphers, use_netrc=use_netrc)
+            checksum_tmpsrc, _dummy = url_get(module, checksum_url, dest, use_proxy, last_mod_time, force, timeout, headers, tmp_dest,
+                                              unredirected_headers=unredirected_headers, ciphers=ciphers, use_netrc=use_netrc)
             with open(checksum_tmpsrc) as f:
                 lines = [line.rstrip('\n') for line in f]
             os.remove(checksum_tmpsrc)
-            checksum_map = []
             filename = url_filename(url)
-            if len(lines) == 1 and len(lines[0].split()) == 1:
-                # Only a single line with a single string
-                # treat it as a checksum only file
-                checksum_map.append((lines[0], filename))
-            else:
-                # The assumption here is the file is in the format of
-                # checksum filename
-                for line in lines:
-                    # Split by one whitespace to keep the leading type char ' ' (whitespace) for text and '*' for binary
-                    parts = line.split(" ", 1)
-                    if len(parts) == 2:
-                        # Remove the leading type char, we expect
-                        if parts[1].startswith((" ", "*",)):
-                            parts[1] = parts[1][1:]
-
-                        # Append checksum and path without potential leading './'
-                        checksum_map.append((parts[0], parts[1].lstrip("./")))
-
+            checksum_map = parse_digest_lines(filename=filename, lines=lines)
             # Look through each line in the checksum file for a hash corresponding to
             # the filename in the url, returning the first hash that is found.
             for cksum in (s for (s, f) in checksum_map if f == filename):
@@ -601,7 +625,7 @@ def main():
         # If the file already exists, prepare the last modified time for the
         # request.
         mtime = os.path.getmtime(dest)
-        last_mod_time = utcfromtimestamp(mtime)
+        last_mod_time = datetime.fromtimestamp(mtime, timezone.utc)
 
         # If the checksum does not match we have to force the download
         # because last_mod_time may be newer than on remote
@@ -609,11 +633,11 @@ def main():
             force = True
 
     # download to tmpsrc
-    start = utcnow()
+    start = datetime.now(timezone.utc)
     method = 'HEAD' if module.check_mode else 'GET'
     tmpsrc, info = url_get(module, url, dest, use_proxy, last_mod_time, force, timeout, headers, tmp_dest, method,
                            unredirected_headers=unredirected_headers, decompress=decompress, ciphers=ciphers, use_netrc=use_netrc)
-    result['elapsed'] = (utcnow() - start).seconds
+    result['elapsed'] = (datetime.now(timezone.utc) - start).seconds
     result['src'] = tmpsrc
 
     # Now the request has completed, we can finally generate the final
@@ -683,8 +707,7 @@ def main():
         except Exception as e:
             if os.path.exists(tmpsrc):
                 os.remove(tmpsrc)
-            module.fail_json(msg="failed to copy %s to %s: %s" % (tmpsrc, dest, to_native(e)),
-                             exception=traceback.format_exc(), **result)
+            module.fail_json(msg="failed to copy %s to %s: %s" % (tmpsrc, dest, to_native(e)), **result)
         result['changed'] = True
     else:
         result['changed'] = False

ansible/modules/getent.py

@@ -6,7 +6,7 @@
 from __future__ import annotations
 
 
-DOCUMENTATION = r'''
+DOCUMENTATION = r"""
 ---
 module: getent
 short_description: A wrapper to the unix getent utility
@@ -58,9 +58,9 @@ notes:
    - Not all databases support enumeration, check system documentation for details.
 author:
 - Brian Coca (@bcoca)
-'''
+"""
 
-EXAMPLES = '''
+EXAMPLES = """
 - name: Get root user info
   ansible.builtin.getent:
     database: passwd
@@ -97,9 +97,9 @@ EXAMPLES = '''
 - ansible.builtin.debug:
     var: ansible_facts.getent_shadow
 
-'''
+"""
 
-RETURN = '''
+RETURN = """
 ansible_facts:
   description: Facts to add to ansible_facts.
   returned: always
@@ -112,9 +112,7 @@ ansible_facts:
         - Starting at 2.11 it now returns multiple duplicate entries, previously it only returned the last one
       returned: always
       type: list
-'''
-
-import traceback
+"""
 
 from ansible.module_utils.basic import AnsibleModule
 from ansible.module_utils.common.text.converters import to_native
@@ -156,7 +154,7 @@ def main():
     try:
         rc, out, err = module.run_command(cmd)
     except Exception as e:
-        module.fail_json(msg=to_native(e), exception=traceback.format_exc())
+        module.fail_json(msg=to_native(e))
 
     msg = "Unexpected failure!"
     dbtree = 'getent_%s' % database