Fix bug (#18355) where encrypted inventories fail 18355 (#18373)

* Fix bug (#18355) where encrypted inventories fail

This is first part of fix for #18355
* Make DataLoader._get_file_contents return bytes

The issue #18355 is caused by a change to inventory to
stop using _get_file_contents so that it can handle text
encoding itself to better protect against harmless text
encoding errors in ini files (invalid unicode text in
comment fields).

So this makes _get_file_contents return bytes so it and other
callers can handle the to_text().

The data returned by _get_file_contents() is now a bytes object
instead of a text object. The callers of _get_file_contents() have
been updated to call to_text() themselves on the results.

Previously, the ini parser attempted to work around
ini files that potentially include non-vailid unicode
in comment lines. To do this, it stopped using
DataLoader._get_file_contents() which does the decryption of
files if vault encrypted. It didn't use that because _get_file_contents
previously did to_text() on the read data itself.

_get_file_contents() returns a bytestring now, so ini.py
can call it and still special case ini file comments when
converting to_text(). That also means encrypted inventory files
are decrypted first.

Fixes #18355

lib/ansible/inventory/ini.py

@@ -51,18 +51,21 @@ class InventoryParser(object):
 
         # Read in the hosts, groups, and variables defined in the
         # inventory file.
+        if loader:
+            (b_data, private) = loader._get_file_contents(filename)
+        else:
+            with open(filename, 'rb') as fh:
+                b_data = fh.read()
 
-        with open(filename, 'rb') as fh:
-            data = fh.read()
-            try:
-                # Faster to do to_text once on a long string than many
-                # times on smaller strings
-                data = to_text(data, errors='surrogate_or_strict')
-                data = [line for line in data.splitlines() if not (line.startswith(u';') or line.startswith(u'#'))]
-            except UnicodeError:
-                # Skip comment lines here to avoid potential undecodable
-                # errors in comments: https://github.com/ansible/ansible/issues/17593
-                data = [to_text(line, errors='surrogate_or_strict') for line in data.splitlines() if not (line.startswith(b';') or line.startswith(b'#'))]
+        try:
+            # Faster to do to_text once on a long string than many
+            # times on smaller strings
+            data = to_text(b_data, errors='surrogate_or_strict')
+            data = [line for line in data.splitlines() if not (line.startswith(u';') or line.startswith(u'#'))]
+        except UnicodeError:
+            # Skip comment lines here to avoid potential undecodable
+            # errors in comments: https://github.com/ansible/ansible/issues/17593
+            data = [to_text(line, errors='surrogate_or_strict') for line in b_data.splitlines() if not (line.startswith(b';') or line.startswith(b'#'))]
 
         self._parse(data)
 

lib/ansible/parsing/dataloader.py

@@ -116,7 +116,9 @@ class DataLoader():
             parsed_data = self._FILE_CACHE[file_name]
         else:
             # read the file contents and load the data structure from them
-            (file_data, show_content) = self._get_file_contents(file_name)
+            (b_file_data, show_content) = self._get_file_contents(file_name)
+
+            file_data = to_text(b_file_data, errors='surrogate_or_strict')
             parsed_data = self.load(data=file_data, file_name=file_name, show_content=show_content)
 
             # cache the file contents for next time
@@ -178,7 +180,6 @@ class DataLoader():
                     data = self._vault.decrypt(data, filename=b_file_name)
                     show_content = False
 
-            data = to_text(data, errors='surrogate_or_strict')
             return (data, show_content)
 
         except (IOError, OSError) as e:

lib/ansible/plugins/action/include_vars.py

@@ -22,7 +22,7 @@ from os import path, walk
 import re
 
 from ansible.errors import AnsibleError
-from ansible.module_utils._text import to_native
+from ansible.module_utils._text import to_native, to_text
 from ansible.plugins.action import ActionBase
 
 
@@ -245,7 +245,9 @@ class ActionModule(ActionBase):
             )
             return failed, err_msg, results
 
-        data, show_content = self._loader._get_file_contents(filename)
+        b_data, show_content = self._loader._get_file_contents(filename)
+        data = to_text(b_data, errors='surrogate_or_strict')
+
         self.show_content = show_content
         data = self._loader.load(data, show_content)
         if not data:

lib/ansible/plugins/lookup/file.py

@@ -19,6 +19,7 @@ __metaclass__ = type
 
 from ansible.errors import AnsibleError, AnsibleParserError
 from ansible.plugins.lookup import LookupBase
+from ansible.module_utils._text import to_text
 
 try:
     from __main__ import display
@@ -41,7 +42,8 @@ class LookupModule(LookupBase):
             display.vvvv(u"File lookup using %s as file" % lookupfile)
             try:
                 if lookupfile:
-                    contents, show_data = self._loader._get_file_contents(lookupfile)
+                    b_contents, show_data = self._loader._get_file_contents(lookupfile)
+                    contents = to_text(b_contents, errors='surrogate_or_strict')
                     ret.append(contents.rstrip())
                 else:
                     raise AnsibleParserError()