googlecloud 0.0.4 → 0.0.6

data/packages/gsutil/boto/boto/cloudsearch/layer2.py

@@ -0,0 +1,67 @@
+# Copyright (c) 2012 Mitch Garnaat http://garnaat.org/
+# Copyright (c) 2012 Amazon.com, Inc. or its affiliates.
+# All Rights Reserved
+#
+# Permission is hereby granted, free of charge, to any person obtaining a
+# copy of this software and associated documentation files (the
+# "Software"), to deal in the Software without restriction, including
+# without limitation the rights to use, copy, modify, merge, publish, dis-
+# tribute, sublicense, and/or sell copies of the Software, and to permit
+# persons to whom the Software is furnished to do so, subject to the fol-
+# lowing conditions:
+#
+# The above copyright notice and this permission notice shall be included
+# in all copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
+# OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABIL-
+# ITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT
+# SHALL THE AUTHOR BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+# WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+# IN THE SOFTWARE.
+#
+
+from .layer1 import Layer1
+from .domain import Domain
+
+
+class Layer2(object):
+
+    def __init__(self, aws_access_key_id=None, aws_secret_access_key=None,
+                 is_secure=True, port=None, proxy=None, proxy_port=None,
+                 host=None, debug=0, session_token=None, region=None,
+                 validate_certs=True):
+        self.layer1 = Layer1(aws_access_key_id, aws_secret_access_key,
+                             is_secure, port, proxy, proxy_port,
+                             host, debug, session_token, region,
+                             validate_certs=validate_certs)
+
+    def list_domains(self, domain_names=None):
+        """
+        Return a list of :class:`boto.cloudsearch.domain.Domain`
+        objects for each domain defined in the current account.
+        """
+        domain_data = self.layer1.describe_domains(domain_names)
+        return [Domain(self.layer1, data) for data in domain_data]
+
+    def create_domain(self, domain_name):
+        """
+        Create a new CloudSearch domain and return the corresponding
+        :class:`boto.cloudsearch.domain.Domain` object.
+        """
+        data = self.layer1.create_domain(domain_name)
+        return Domain(self.layer1, data)
+
+    def lookup(self, domain_name):
+        """
+        Lookup a single domain
+        :param domain_name: The name of the domain to look up
+        :type domain_name: str
+
+        :return: Domain object, or None if the domain isn't found
+        :rtype: :class:`boto.cloudsearch.domain.Domain`
+        """
+        domains = self.list_domains(domain_names=[domain_name])
+        if len(domains) > 0:
+            return domains[0]

data/packages/gsutil/boto/boto/cloudsearch/optionstatus.py

@@ -0,0 +1,248 @@
+# Copyright (c) 2012 Mitch Garnaat http://garnaat.org/
+# Copyright (c) 2012 Amazon.com, Inc. or its affiliates.
+# All Rights Reserved
+#
+# Permission is hereby granted, free of charge, to any person obtaining a
+# copy of this software and associated documentation files (the
+# "Software"), to deal in the Software without restriction, including
+# without limitation the rights to use, copy, modify, merge, publish, dis-
+# tribute, sublicense, and/or sell copies of the Software, and to permit
+# persons to whom the Software is furnished to do so, subject to the fol-
+# lowing conditions:
+#
+# The above copyright notice and this permission notice shall be included
+# in all copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
+# OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABIL-
+# ITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT
+# SHALL THE AUTHOR BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+# WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+# IN THE SOFTWARE.
+#
+
+import time
+from boto.compat import json
+
+
+class OptionStatus(dict):
+    """
+    Presents a combination of status field (defined below) which are
+    accessed as attributes and option values which are stored in the
+    native Python dictionary.  In this class, the option values are
+    merged from a JSON object that is stored as the Option part of
+    the object.
+
+    :ivar domain_name: The name of the domain this option is associated with.
+    :ivar create_date: A timestamp for when this option was created.
+    :ivar state: The state of processing a change to an option.
+        Possible values:
+
+        * RequiresIndexDocuments: the option's latest value will not
+          be visible in searches until IndexDocuments has been called
+          and indexing is complete.
+        * Processing: the option's latest value is not yet visible in
+          all searches but is in the process of being activated.
+        * Active: the option's latest value is completely visible.
+
+    :ivar update_date: A timestamp for when this option was updated.
+    :ivar update_version: A unique integer that indicates when this
+        option was last updated.
+    """
+
+    def __init__(self, domain, data=None, refresh_fn=None, save_fn=None):
+        self.domain = domain
+        self.refresh_fn = refresh_fn
+        self.save_fn = save_fn
+        self.refresh(data)
+
+    def _update_status(self, status):
+        self.creation_date = status['creation_date']
+        self.status = status['state']
+        self.update_date = status['update_date']
+        self.update_version = int(status['update_version'])
+
+    def _update_options(self, options):
+        if options:
+            self.update(json.loads(options))
+
+    def refresh(self, data=None):
+        """
+        Refresh the local state of the object.  You can either pass
+        new state data in as the parameter ``data`` or, if that parameter
+        is omitted, the state data will be retrieved from CloudSearch.
+        """
+        if not data:
+            if self.refresh_fn:
+                data = self.refresh_fn(self.domain.name)
+        if data:
+            self._update_status(data['status'])
+            self._update_options(data['options'])
+
+    def to_json(self):
+        """
+        Return the JSON representation of the options as a string.
+        """
+        return json.dumps(self)
+
+    def startElement(self, name, attrs, connection):
+        return None
+
+    def endElement(self, name, value, connection):
+        if name == 'CreationDate':
+            self.created = value
+        elif name == 'State':
+            self.state = value
+        elif name == 'UpdateDate':
+            self.updated = value
+        elif name == 'UpdateVersion':
+            self.update_version = int(value)
+        elif name == 'Options':
+            self.update_from_json_doc(value)
+        else:
+            setattr(self, name, value)
+
+    def save(self):
+        """
+        Write the current state of the local object back to the
+        CloudSearch service.
+        """
+        if self.save_fn:
+            data = self.save_fn(self.domain.name, self.to_json())
+            self.refresh(data)
+
+    def wait_for_state(self, state):
+        """
+        Performs polling of CloudSearch to wait for the ``state``
+        of this object to change to the provided state.
+        """
+        while self.state != state:
+            time.sleep(5)
+            self.refresh()
+
+
+class IndexFieldStatus(OptionStatus):
+
+    def _update_options(self, options):
+        self.update(options)
+
+    def save(self):
+        pass
+
+
+class RankExpressionStatus(IndexFieldStatus):
+
+    pass
+
+class ServicePoliciesStatus(OptionStatus):
+
+    def new_statement(self, arn, ip):
+        """
+        Returns a new policy statement that will allow
+        access to the service described by ``arn`` by the
+        ip specified in ``ip``.
+
+        :type arn: string
+        :param arn: The Amazon Resource Notation identifier for the
+            service you wish to provide access to.  This would be
+            either the search service or the document service.
+
+        :type ip: string
+        :param ip: An IP address or CIDR block you wish to grant access
+            to.
+        """
+        return {
+                    "Effect":"Allow",
+                    "Action":"*",  # Docs say use GET, but denies unless *
+                    "Resource": arn,
+                    "Condition": {
+                        "IpAddress": {
+                            "aws:SourceIp": [ip]
+                            }
+                        }
+                    }
+
+    def _allow_ip(self, arn, ip):
+        if 'Statement' not in self:
+            s = self.new_statement(arn, ip)
+            self['Statement'] = [s]
+            self.save()
+        else:
+            add_statement = True
+            for statement in self['Statement']:
+                if statement['Resource'] == arn:
+                    for condition_name in statement['Condition']:
+                        if condition_name == 'IpAddress':
+                            add_statement = False
+                            condition = statement['Condition'][condition_name]
+                            if ip not in condition['aws:SourceIp']:
+                                condition['aws:SourceIp'].append(ip)
+
+            if add_statement:
+                s = self.new_statement(arn, ip)
+                self['Statement'].append(s)
+            self.save()
+
+    def allow_search_ip(self, ip):
+        """
+        Add the provided ip address or CIDR block to the list of
+        allowable address for the search service.
+
+        :type ip: string
+        :param ip: An IP address or CIDR block you wish to grant access
+            to.
+        """
+        arn = self.domain.search_service_arn
+        self._allow_ip(arn, ip)
+
+    def allow_doc_ip(self, ip):
+        """
+        Add the provided ip address or CIDR block to the list of
+        allowable address for the document service.
+
+        :type ip: string
+        :param ip: An IP address or CIDR block you wish to grant access
+            to.
+        """
+        arn = self.domain.doc_service_arn
+        self._allow_ip(arn, ip)
+
+    def _disallow_ip(self, arn, ip):
+        if 'Statement' not in self:
+            return
+        need_update = False
+        for statement in self['Statement']:
+            if statement['Resource'] == arn:
+                for condition_name in statement['Condition']:
+                    if condition_name == 'IpAddress':
+                        condition = statement['Condition'][condition_name]
+                        if ip in condition['aws:SourceIp']:
+                            condition['aws:SourceIp'].remove(ip)
+                            need_update = True
+        if need_update:
+            self.save()
+
+    def disallow_search_ip(self, ip):
+        """
+        Remove the provided ip address or CIDR block from the list of
+        allowable address for the search service.
+
+        :type ip: string
+        :param ip: An IP address or CIDR block you wish to grant access
+            to.
+        """
+        arn = self.domain.search_service_arn
+        self._disallow_ip(arn, ip)
+
+    def disallow_doc_ip(self, ip):
+        """
+        Remove the provided ip address or CIDR block from the list of
+        allowable address for the document service.
+
+        :type ip: string
+        :param ip: An IP address or CIDR block you wish to grant access
+            to.
+        """
+        arn = self.domain.doc_service_arn
+        self._disallow_ip(arn, ip)

data/packages/gsutil/boto/boto/cloudsearch/search.py

@@ -0,0 +1,365 @@
+# Copyright (c) 2012 Mitch Garnaat http://garnaat.org/
+# Copyright (c) 2012 Amazon.com, Inc. or its affiliates.
+# All Rights Reserved
+#
+# Permission is hereby granted, free of charge, to any person obtaining a
+# copy of this software and associated documentation files (the
+# "Software"), to deal in the Software without restriction, including
+# without limitation the rights to use, copy, modify, merge, publish, dis-
+# tribute, sublicense, and/or sell copies of the Software, and to permit
+# persons to whom the Software is furnished to do so, subject to the fol-
+# lowing conditions:
+#
+# The above copyright notice and this permission notice shall be included
+# in all copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
+# OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABIL-
+# ITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT
+# SHALL THE AUTHOR BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+# WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+# IN THE SOFTWARE.
+#
+from math import ceil
+import time
+import json
+import boto
+import requests
+
+
+class SearchServiceException(Exception):
+    pass
+
+
+class CommitMismatchError(Exception):
+    pass
+
+
+class SearchResults(object):
+    
+    def __init__(self, **attrs):
+        self.rid = attrs['info']['rid']
+        # self.doc_coverage_pct = attrs['info']['doc-coverage-pct']
+        self.cpu_time_ms = attrs['info']['cpu-time-ms']
+        self.time_ms = attrs['info']['time-ms']
+        self.hits = attrs['hits']['found']
+        self.docs = attrs['hits']['hit']
+        self.start = attrs['hits']['start']
+        self.rank = attrs['rank']
+        self.match_expression = attrs['match-expr']
+        self.query = attrs['query']
+        self.search_service = attrs['search_service']
+
+        self.facets = {}
+        if 'facets' in attrs:
+            for (facet, values) in attrs['facets'].iteritems():
+                self.facets[facet] = dict((k, v) for (k, v) in map(lambda x: (x['value'], x['count']), values['constraints']))
+
+        self.num_pages_needed = ceil(self.hits / self.query.real_size)
+
+    def __len__(self):
+        return len(self.docs)
+
+    def __iter__(self):
+        return iter(self.docs)
+
+    def next_page(self):
+        """Call Cloudsearch to get the next page of search results
+
+        :rtype: :class:`boto.cloudsearch.search.SearchResults`
+        :return: the following page of search results
+        """
+        if self.query.page <= self.num_pages_needed:
+            self.query.start += self.query.real_size
+            self.query.page += 1
+            return self.search_service(self.query)
+        else:
+            raise StopIteration
+
+
+class Query(object):
+    
+    RESULTS_PER_PAGE = 500
+
+    def __init__(self, q=None, bq=None, rank=None,
+                 return_fields=None, size=10,
+                 start=0, facet=None, facet_constraints=None,
+                 facet_sort=None, facet_top_n=None, t=None):
+
+        self.q = q
+        self.bq = bq
+        self.rank = rank or []
+        self.return_fields = return_fields or []
+        self.start = start
+        self.facet = facet or []
+        self.facet_constraints = facet_constraints or {}
+        self.facet_sort = facet_sort or {}
+        self.facet_top_n = facet_top_n or {}
+        self.t = t or {}
+        self.page = 0
+        self.update_size(size)
+
+    def update_size(self, new_size):
+        self.size = new_size
+        self.real_size = Query.RESULTS_PER_PAGE if (self.size >
+            Query.RESULTS_PER_PAGE or self.size == 0) else self.size
+
+    def to_params(self):
+        """Transform search parameters from instance properties to a dictionary
+
+        :rtype: dict
+        :return: search parameters
+        """
+        params = {'start': self.start, 'size': self.real_size}
+
+        if self.q:
+            params['q'] = self.q
+
+        if self.bq:
+            params['bq'] = self.bq
+
+        if self.rank:
+            params['rank'] = ','.join(self.rank)
+
+        if self.return_fields:
+            params['return-fields'] = ','.join(self.return_fields)
+
+        if self.facet:
+            params['facet'] = ','.join(self.facet)
+
+        if self.facet_constraints:
+            for k, v in self.facet_constraints.iteritems():
+                params['facet-%s-constraints' % k] = v
+
+        if self.facet_sort:
+            for k, v in self.facet_sort.iteritems():
+                params['facet-%s-sort' % k] = v
+
+        if self.facet_top_n:
+            for k, v in self.facet_top_n.iteritems():
+                params['facet-%s-top-n' % k] = v
+
+        if self.t:
+            for k, v in self.t.iteritems():
+                params['t-%s' % k] = v
+        return params
+
+
+class SearchConnection(object):
+    
+    def __init__(self, domain=None, endpoint=None):
+        self.domain = domain
+        self.endpoint = endpoint
+        if not endpoint:
+            self.endpoint = domain.search_service_endpoint
+
+    def build_query(self, q=None, bq=None, rank=None, return_fields=None,
+                    size=10, start=0, facet=None, facet_constraints=None,
+                    facet_sort=None, facet_top_n=None, t=None):
+        return Query(q=q, bq=bq, rank=rank, return_fields=return_fields,
+                     size=size, start=start, facet=facet,
+                     facet_constraints=facet_constraints,
+                     facet_sort=facet_sort, facet_top_n=facet_top_n, t=t)
+
+    def search(self, q=None, bq=None, rank=None, return_fields=None,
+               size=10, start=0, facet=None, facet_constraints=None,
+               facet_sort=None, facet_top_n=None, t=None):
+        """
+        Send a query to CloudSearch
+
+        Each search query should use at least the q or bq argument to specify
+        the search parameter. The other options are used to specify the
+        criteria of the search.
+
+        :type q: string
+        :param q: A string to search the default search fields for.
+
+        :type bq: string
+        :param bq: A string to perform a Boolean search. This can be used to
+            create advanced searches.
+
+        :type rank: List of strings
+        :param rank: A list of fields or rank expressions used to order the
+            search results. A field can be reversed by using the - operator.
+            ``['-year', 'author']``
+
+        :type return_fields: List of strings
+        :param return_fields: A list of fields which should be returned by the
+            search. If this field is not specified, only IDs will be returned.
+            ``['headline']``
+
+        :type size: int
+        :param size: Number of search results to specify
+
+        :type start: int
+        :param start: Offset of the first search result to return (can be used
+            for paging)
+
+        :type facet: list
+        :param facet: List of fields for which facets should be returned
+            ``['colour', 'size']``
+
+        :type facet_constraints: dict
+        :param facet_constraints: Use to limit facets to specific values
+            specified as comma-delimited strings in a Dictionary of facets
+            ``{'colour': "'blue','white','red'", 'size': "big"}``
+
+        :type facet_sort: dict
+        :param facet_sort: Rules used to specify the order in which facet
+            values should be returned. Allowed values are *alpha*, *count*,
+            *max*, *sum*. Use *alpha* to sort alphabetical, and *count* to sort
+            the facet by number of available result. 
+            ``{'color': 'alpha', 'size': 'count'}``
+
+        :type facet_top_n: dict
+        :param facet_top_n: Dictionary of facets and number of facets to
+            return.
+            ``{'colour': 2}``
+
+        :type t: dict
+        :param t: Specify ranges for specific fields
+            ``{'year': '2000..2005'}``
+
+        :rtype: :class:`boto.cloudsearch.search.SearchResults`
+        :return: Returns the results of this search
+
+        The following examples all assume we have indexed a set of documents
+        with fields: *author*, *date*, *headline*
+
+        A simple search will look for documents whose default text search
+        fields will contain the search word exactly:
+
+        >>> search(q='Tim') # Return documents with the word Tim in them (but not Timothy)
+
+        A simple search with more keywords will return documents whose default
+        text search fields contain the search strings together or separately.
+
+        >>> search(q='Tim apple') # Will match "tim" and "apple"
+
+        More complex searches require the boolean search operator.
+
+        Wildcard searches can be used to search for any words that start with
+        the search string.
+
+        >>> search(bq="'Tim*'") # Return documents with words like Tim or Timothy)
+        
+        Search terms can also be combined. Allowed operators are "and", "or",
+        "not", "field", "optional", "token", "phrase", or "filter"
+        
+        >>> search(bq="(and 'Tim' (field author 'John Smith'))")
+
+        Facets allow you to show classification information about the search
+        results. For example, you can retrieve the authors who have written
+        about Tim:
+
+        >>> search(q='Tim', facet=['Author'])
+
+        With facet_constraints, facet_top_n and facet_sort more complicated
+        constraints can be specified such as returning the top author out of
+        John Smith and Mark Smith who have a document with the word Tim in it.
+        
+        >>> search(q='Tim', 
+        ...     facet=['Author'], 
+        ...     facet_constraints={'author': "'John Smith','Mark Smith'"}, 
+        ...     facet=['author'], 
+        ...     facet_top_n={'author': 1}, 
+        ...     facet_sort={'author': 'count'})
+        """
+
+        query = self.build_query(q=q, bq=bq, rank=rank,
+                                 return_fields=return_fields,
+                                 size=size, start=start, facet=facet,
+                                 facet_constraints=facet_constraints,
+                                 facet_sort=facet_sort,
+                                 facet_top_n=facet_top_n, t=t)
+        return self(query)
+
+    def __call__(self, query):
+        """Make a call to CloudSearch
+
+        :type query: :class:`boto.cloudsearch.search.Query`
+        :param query: A group of search criteria
+
+        :rtype: :class:`boto.cloudsearch.search.SearchResults`
+        :return: search results
+        """
+        url = "http://%s/2011-02-01/search" % (self.endpoint)
+        params = query.to_params()
+
+        r = requests.get(url, params=params)
+        data = json.loads(r.content)
+        data['query'] = query
+        data['search_service'] = self
+
+        if 'messages' in data and 'error' in data:
+            for m in data['messages']:
+                if m['severity'] == 'fatal':
+                    raise SearchServiceException("Error processing search %s "
+                        "=> %s" % (params, m['message']), query)
+        elif 'error' in data:
+            raise SearchServiceException("Unknown error processing search %s"
+                % (params), query)
+
+        return SearchResults(**data)
+
+    def get_all_paged(self, query, per_page):
+        """Get a generator to iterate over all pages of search results
+
+        :type query: :class:`boto.cloudsearch.search.Query`
+        :param query: A group of search criteria
+
+        :type per_page: int
+        :param per_page: Number of docs in each :class:`boto.cloudsearch.search.SearchResults` object.
+
+        :rtype: generator
+        :return: Generator containing :class:`boto.cloudsearch.search.SearchResults`
+        """
+        query.update_size(per_page)
+        page = 0
+        num_pages_needed = 0
+        while page <= num_pages_needed:
+            results = self(query)
+            num_pages_needed = results.num_pages_needed
+            yield results
+            query.start += query.real_size
+            page += 1
+
+    def get_all_hits(self, query):
+        """Get a generator to iterate over all search results
+
+        Transparently handles the results paging from Cloudsearch
+        search results so even if you have many thousands of results
+        you can iterate over all results in a reasonably efficient
+        manner.
+
+        :type query: :class:`boto.cloudsearch.search.Query`
+        :param query: A group of search criteria
+
+        :rtype: generator
+        :return: All docs matching query
+        """
+        page = 0
+        num_pages_needed = 0
+        while page <= num_pages_needed:
+            results = self(query)
+            num_pages_needed = results.num_pages_needed
+            for doc in results:
+                yield doc
+            query.start += query.real_size
+            page += 1
+
+    def get_num_hits(self, query):
+        """Return the total number of hits for query
+
+        :type query: :class:`boto.cloudsearch.search.Query`
+        :param query: a group of search criteria
+
+        :rtype: int
+        :return: Total number of hits for query
+        """
+        query.update_size(1)
+        return self(query).hits
+
+
+