parsing, but need to finish extended value validations for confparser and then get to work actually making the stuff go

bdisk/bdisk.xsd

@@ -645,6 +645,13 @@
                                     <xs:attribute name="keyid" type="t_gpg_keyid" use="required"/>
                                     <xs:attribute name="publish" type="xs:boolean" use="optional"/>
                                     <xs:attribute name="prompt_passphrase" type="xs:boolean" use="required"/>
+                                    <xs:attribute name="passphrase" use="optional">
+                                        <xs:simpleType>
+                                            <xs:restriction base="xs:string">
+                                                <xs:pattern value="[!&quot;#$%&amp;\\'\(\)\*\+,\-\./0123456789:;&lt;=&gt;\?@ABCDEFGHIJKLMNOPQRSTUVWXYZ\[\]\^_`abcdefghijklmnopqrstuvwxyz\{\|\}~ ]+"/>
+                                            </xs:restriction>
+                                        </xs:simpleType>
+                                    </xs:attribute>
                                     <xs:attribute name="gnupghome" use="optional">
                                         <xs:simpleType>
                                             <xs:restriction base="xs:string">

bdisk/confparse.py

@@ -56,7 +56,7 @@ class Conf(object):
         self.cfg = {}
         if validate_cfg:
             # Validation post-substitution
-            self.validate()
+            self.validate(parsed = False)
 
     def get_pki_obj(self, pki, pki_type):
         elem = {}
@@ -82,8 +82,7 @@ class Conf(object):
         return(elem)
 
     def get_source(self, source, item, _source):
-        _source_item = {'flags': [],
+        _source_item = {'flags': [], 'fname': None}
-                         'fname': None}
         elem = source.xpath('./{0}'.format(item))[0]
         if item == 'checksum':
             if elem.get('explicit', False):
@@ -132,6 +131,8 @@ class Conf(object):
         return(_source_item)
 
     def get_xsd(self):
+        if isinstance(self.xsd, lxml.etree.XMLSchema):
+            return(self.xsd)
         if not self.xsd:
             path = os.path.join(os.path.dirname(__file__), 'bdisk.xsd')
         else:
@@ -231,10 +232,12 @@ class Conf(object):
             for e in self.profile.xpath(_xpath):
                 for se in e:
                     if not isinstance(se, lxml.etree._Comment):
-                        self.cfg[t][se.tag] = se.text
+                        self.cfg[t][se.tag] = transform.xml2py(se.text,
+                                                               attrib = False)
         for e in ('desc', 'uri', 'ver', 'max_recurse'):
             _xpath = './meta/{0}/text()'.format(e)
-            self.cfg[e] = self.profile.xpath(_xpath)[0]
+            self.cfg[e] = transform.xml2py(self.profile.xpath(_xpath)[0],
+                                           attrib = False)
         # HERE is where we would handle regex patterns.
         # But we don't, because they're in self.xml_suppl.btags['regex'].
         #self.cfg['regexes'] = {}
@@ -249,7 +252,7 @@ class Conf(object):
         self.cfg['pki'] = {'clients': []}
         elem = self.profile.xpath('./pki')[0]
         self.cfg['pki']['overwrite'] = transform.xml2py(
-                                                elem.get('overwrite', 'no'))
+                                                elem.get('overwrite', 'false'))
         ca = elem.xpath('./ca')[0]
         clients = elem.xpath('./client')
         self.cfg['pki']['ca'] = self.get_pki_obj(ca, 'ca')
@@ -266,7 +269,9 @@ class Conf(object):
                                'uuid': None}
         for a in self.cfg['profile']:
             if a in self.profile.attrib:
-                self.cfg['profile'][a] = self.profile.attrib[a]
+                self.cfg['profile'][a] = transform.xml2py(
+                                                        self.profile.attrib[a],
+                                                        attrib = True)
         return()
 
     def parse_sources(self):
@@ -306,13 +311,49 @@ class Conf(object):
                                                         attrib = False)
         return()
 
-    def validate(self):
+    def validate(self, parsed = False):
-        # TODO: perform further validations that we can't do in XSD.
         xsd = self.get_xsd()
-        self.xsd = etree.XMLSchema(xsd)
+        if not isinstance(xsd, lxml.etree.XMLSchema):
+            self.xsd = etree.XMLSchema(xsd)
+        else:
+            pass
         # This would return a bool if it validates or not.
         #self.xsd.validate(self.xml)
         # We want to get a more detailed exception.
         xml = etree.fromstring(self.xml_suppl.return_full())
         self.xsd.assertValid(xml)
+        if parsed:
+            # TODO: perform further validations that we can't do in XSD.
+            # We wait until after it's parsed to evaluate because otherwise we
+            # can't use utils.valid().
+            # We only bother with stuff that would hinder building, though -
+            # e.g. we don't check that profile's UUID is a valid UUID4.
+            # URLs
+            for url in (self.cfg['uri'], self.cfg['dev']['website']):
+                if not valid.url(url):
+                    raise ValueError('{0} is not a valid URL.'.format(url))
+            # Emails
+            for k in self.cfg['gpg']['keys']:
+                if not valid.email(k['email']):
+                    raise ValueError(
+                            'GPG key {0}: {1} is not a valid email '
+                            'address'.format(k['name'], k['email']))
+            if not valid.email(self.cfg['dev']['email']):
+                raise ValueError('{0} is not a valid email address'.format(
+                                                    self.cfg['dev']['email']))
+            if self.cfg['pki']:
+                if 'subject' in self.cfg['pki']['ca']:
+                    if not valid.email(
+                            self.cfg['pki']['ca']['subject']['emailAddress']):
+                        raise ValueError('{0} is not a valid email '
+                                         'address'.format(
+                            self.cfg['pki']['ca']['subject']['emailAddress']))
+
+                    if not self.cfg['pki'][x]['subject']:
+                        continue
+                    if not valid.email(
+                            self.cfg['pki'][x]['subject']['emailAddress']):
+                        raise ValueError('{0} is not a valid email '
+                                         'address'.format(
+                                self.cfg['pki'][x]['subject']['email']))
         return()

bdisk/utils.py

@@ -77,6 +77,8 @@ class detect(object):
 
     def password_hash_salt(self, salted_hash):
         _hash_list = salted_hash.split('$')
+        if len(_hash_list) < 3:
+            return(None)
         salt = _hash_list[2]
         return(salt)
 
@@ -630,10 +632,28 @@ class transform(object):
                     if _hash:
                         acct['hash_algo'] = _hash
                     else:
-                        raise ValueError(
+                        acct['hash_algo'] = None
-                                'Invalid salted password hash: {0}'.format(
+                        # We no longer raise ValueError. Per shadow(5):
-                                        elem.text)
+                        #######################################################
-                                )
+                        # If the password field contains some string that is
+                        # not a valid result of crypt(3), for instance ! or *,
+                        # the user will not be able to use a unix password to
+                        # log in (but the user may log in the system by other
+                        # means).
+                        # This field may be empty, in which case no passwords
+                        # are required to authenticate as the specified login
+                        #  name. However, some applications which read the
+                        # /etc/shadow file may decide not to permit any access
+                        # at all if the password field is empty.
+                        # A password field which starts with an exclamation
+                        # mark means that the password is locked. The remaining
+                        # characters on the line represent the password field
+                        # before the password was locked.
+                        #######################################################
+                        # raise ValueError(
+                        #         'Invalid salted password hash: {0}'.format(
+                        #                 elem.text)
+                        #         )
                 acct['salt_hash'] = elem.text
                 acct['passphrase'] = None
             else:
@@ -873,13 +893,13 @@ class xml_supplicant(object):
         return(cfg)
 
     def _parse_regexes(self):
-        for regex in self.profile.xpath('//meta/regexes/pattern'):
+        for regex in self.profile.xpath('./meta/regexes/pattern'):
             _key = 'regex%{0}'.format(regex.attrib['id'])
             self.btags['regex'][_key] = regex.text
         return()
 
     def _parse_variables(self):
-        for variable in self.profile.xpath('//meta/variables/variable'):
+        for variable in self.profile.xpath('./meta/variables/variable'):
             self.btags['variable'][
                                 'variable%{0}'.format(variable.attrib['id'])
                                     ] = variable.text
@@ -976,7 +996,6 @@ class xml_supplicant(object):
         return(path)
 
     def return_full(self):
-        #nsmap = self.return_naked_ns()
         # https://stackoverflow.com/a/22553145/733214
         local_xml = lxml.etree.Element('bdisk',
                                        nsmap = self.orig_xml.nsmap,

bin/xmllint.sh

@@ -1,3 +1,3 @@
 #!/bin/bash
 
-xmllint -schema ../bdisk/bdisk.xsd ../docs/examples/multi_profile.xml --noout
+xmllint -schema /opt/dev/bdisk/bdisk/bdisk.xsd /opt/dev/bdisk/docs/examples/multi_profile.xml --noout

docs/examples/single_profile.xml

@@ -43,10 +43,10 @@
             <!-- Salted/hashed password is "test" -->
             <rootpass hashed="true">$6$7KfIdtHTcXwVrZAC$LZGNeMNz7v5o/cYuA48FAxtZynpIwO5B1CPGXnOW5kCTVpXVt4SypRqfM.AoKkFt/O7MZZ8ySXJmxpELKmdlF1</rootpass>
             <user sudo="true">
-                <username>{xpath%//meta/names/uxname/text()}</username>
+                <username>{xpath%../../../meta/names/uxname/text()}</username>
                 <!-- You can also use substitution from different profiles in this same configuration: -->
                 <!-- <username>{xpath%//profile[@name='another_profile']/meta/names/uxname"}</username> -->
-                <comment>{xpath%//meta/dev/author/text()}</comment>
+                <comment>{xpath%../../../meta/dev/author/text()}</comment>
                 <password hashed="false"
                           hash_algo="sha512"
                           salt="auto">testpassword</password>
@@ -153,7 +153,7 @@
                 </subject>
             </client>
         </pki>
-        <!-- If prompt_passphrase is "no" and passphrase attribute is not given for a gpg element, we will try to use a
+        <!-- If prompt_passphrase is "false" and passphrase attribute is not given for a gpg element, we will try to use a
              blank passphrase for all operations. -->
         <gpg keyid="none"
              gnupghome="none"