gian/resync
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

pep8

Browse Source
This commit is contained in:
Simeon Warner 2016-05-08 16:58:14 -04:00
parent 32673becbd
commit b26ee622da
52 changed files with 2942 additions and 2498 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
.travis.yml
View File

@ -10,11 +10,12 @@ python:
install:
- pip install requests
- pip install python-dateutil
- pip install coveralls pep257 restructuredtext_lint testfixtures
- pip install coveralls pep8 pep257 restructuredtext_lint testfixtures
- python setup.py install
# command to run tests
script:
- python setup.py test
- pep8 --ignore=E501 resync tests bin/resync bin/resync-explorer
- pep257 resync
- rst-lint README
- coverage run --source=resync setup.py test

101
bin/resync
View File

@ -22,26 +22,27 @@ import sys
from resync import __version__
from resync.client import Client, ClientFatalError
from resync.client_utils import init_logging,count_true_args,parse_links,parse_capabilities,parse_capability_lists
from resync.client_utils import init_logging, count_true_args, parse_links, parse_capabilities, parse_capability_lists
DEFAULT_LOGFILE = 'resync-client.log'
def main():
if (sys.version_info < (2,6)):
if (sys.version_info < (2, 6)):
sys.exit("This program requires python version 2.6 or later")
# Options and arguments
p = optparse.OptionParser(description='ResourceSync command line client',
usage='usage: %prog [options] uri_path local_path (-h for help)',
version='%prog '+__version__ )
version='%prog ' + __version__)
# Modes
# a. modes using remote sitemap/resources
rem = p.add_option_group('REMOTE MODES',
'These modes use a remote source that is specified in a set of uri=path mappings '
'and potentially also using an explicit --sitemap location. The default mode is '
'--baseline. See also: resync-explorer for an interactive client.')
'These modes use a remote source that is specified in a set of uri=path mappings '
'and potentially also using an explicit --sitemap location. The default mode is '
'--baseline. See also: resync-explorer for an interactive client.')
rem.add_option('--baseline', '-b', action='store_true',
help='baseline sync of resources from remote source (src) to local filesystem (dst)')
rem.add_option('--incremental', '--inc', '-i', action='store_true',
@ -52,7 +53,7 @@ def main():
help="parse a remote sitemap/sitemapindex (from mapping or explicit --sitemap) and show summary information including document type and number of entries")
# b. modes based solely on files on local disk
loc = p.add_option_group('LOCAL MODES',
'These modes act on files on the local disk')
'These modes act on files on the local disk')
loc.add_option('--resourcelist', '--resource-list', '-r', action='store_true',
help="write a resource list based on files on disk using uri=path mappings "
"in reverse to calculate URIs from the local paths. Scans local disk "
@ -80,7 +81,8 @@ def main():
help="write a Resource Dump. Specify output file with --outfile and use other "
"options as for --changelist")
# Specification of map between remote URI and local file paths, and remote sitemap
# Specification of map between remote URI and local file paths, and remote
# sitemap
nam = p.add_option_group('FILE/URI NAMING OPTIONS')
nam.add_option('--outfile', type=str, action='store',
help="write output to specified file rather than STDOUT or default")
@ -94,7 +96,7 @@ def main():
help="reference sitemap name for --changelist calculation")
nam.add_option('--newreference', type=str, action='store',
help="updated reference sitemap name for --changelist calculation")
nam.add_option('--changelist-uri','--change-list-uri', type=str, action='store',
nam.add_option('--changelist-uri', '--change-list-uri', type=str, action='store',
help="explicitly set the changelist URI that will be use in --inc mode, "
"overrides process of getting this from the sitemap")
@ -105,16 +107,16 @@ def main():
"(repeat option for multiple links)")
lks.add_option('--describedby-link', type=str, action='store',
help="add an <rs:md rel=\"describedby\" link to "
"a description of the feed at the URI given")
lks.add_option('--sourcedescription-link', '--source-description-link',
"a description of the feed at the URI given")
lks.add_option('--sourcedescription-link', '--source-description-link',
type=str, action='store',
help="for a Capability List add a <rs:md rel=\"up\" link to the"
"Source Description document at the URI given, else ignored")
"Source Description document at the URI given, else ignored")
lks.add_option('--capabilitylist-link', '--capability-list-link',
type=str, action='store',
help="for all documents except a Capability List or a "
"Source Description, add an <rs:md rel=\"up\" link "
"to the Capability List at the URI given")
"to the Capability List at the URI given")
# Options that apply to multiple modes
opt = p.add_option_group('MISCELANEOUS OPTIONS')
@ -169,65 +171,65 @@ def main():
# Implement exclusive arguments and default --baseline (support for exclusive
# groups in argparse is incomplete is python2.6)
if (not args.baseline and not args.incremental and not args.audit and
not args.parse and not args.resourcelist and not args.changelist and
not args.capabilitylist and not args.sourcedescription and
not args.resourcedump and not args.changedump):
if (len(map)==0):
if (not args.baseline and not args.incremental and not args.audit and
not args.parse and not args.resourcelist and not args.changelist and
not args.capabilitylist and not args.sourcedescription and
not args.resourcedump and not args.changedump):
if (len(map) == 0):
# No args at all, show help
p.print_help()
return
else:
args.baseline=True
elif (count_true_args(args.baseline,args.incremental,args.audit,args.parse,
args.resourcelist,args.changelist,args.capabilitylist,
args.sourcedescription,args.resourcedump,args.changedump)>1):
args.baseline = True
elif (count_true_args(args.baseline, args.incremental, args.audit, args.parse,
args.resourcelist, args.changelist, args.capabilitylist,
args.sourcedescription, args.resourcedump, args.changedump) > 1):
p.error("Only one of --baseline, --incremental, --audit, --parse, --resourcelist, --changelist, --capabilitylist, --sourcedescription, --resourcedump, --changedump modes allowed")
# Configure logging module and create logger instance
init_logging( to_file=args.logger, logfile=args.logfile, default_logfile=DEFAULT_LOGFILE,
verbose=args.verbose, eval_mode=args.eval )
init_logging(to_file=args.logger, logfile=args.logfile, default_logfile=DEFAULT_LOGFILE,
verbose=args.verbose, eval_mode=args.eval)
c = Client( checksum=args.checksum,
verbose=args.verbose,
dryrun=args.dryrun )
c = Client(checksum=args.checksum,
verbose=args.verbose,
dryrun=args.dryrun)
try:
if (map):
# Mappings apply to (almost) everything
c.set_mappings(map)
if (args.sitemap):
c.sitemap_name=args.sitemap
c.sitemap_name = args.sitemap
if (args.warc):
c.dump_format='warc'
c.dump_format = 'warc'
if (args.exclude):
c.exclude_patterns=args.exclude
c.exclude_patterns = args.exclude
if (args.multifile):
c.allow_multifile=not args.multifile
c.allow_multifile = not args.multifile
if (args.noauth):
c.noauth=args.noauth
c.noauth = args.noauth
if (args.strictauth):
c.strictauth=args.strictauth
c.strictauth = args.strictauth
if (args.max_sitemap_entries):
c.max_sitemap_entries=args.max_sitemap_entries
c.max_sitemap_entries = args.max_sitemap_entries
if (args.ignore_failures):
c.ignore_failures=args.ignore_failures
c.ignore_failures = args.ignore_failures
# Links apply to anything that writes sitemaps
links = parse_links(args.link)
# Add specific links is appropriate cases
if (args.capabilitylist_link and
not args.capabilitylist and
not args.sourcedescription):
# rel="up" to Capability List in all but Capability List
if (args.capabilitylist_link and
not args.capabilitylist and
not args.sourcedescription):
# rel="up" to Capability List in all but Capability List
# and Source Description
links.insert(0,{'rel':'up','href':args.capabilitylist_link})
links.insert(0, {'rel': 'up', 'href': args.capabilitylist_link})
if (args.sourcedescription_link and args.capabilitylist):
# rel="up" to Source Description from Capability List
links.insert(0,{'rel':'up','href':args.sourcedescription_link})
links.insert(0, {'rel': 'up', 'href': args.sourcedescription_link})
if (args.describedby_link):
links.insert(0,{'rel':'describedby','href':args.describedby_link})
links.insert(0, {'rel': 'describedby',
'href': args.describedby_link})
# Finally, do something...
if (args.baseline or args.audit):
@ -246,9 +248,11 @@ def main():
dump=args.resourcedump)
elif (args.changelist or args.changedump):
if (not args.reference and not args.empty):
p.error("Must supply --reference sitemap for --changelist, or --empty")
p.error(
"Must supply --reference sitemap for --changelist, or --empty")
c.write_change_list(ref_sitemap=args.reference,
newref_sitemap=( args.newreference if (args.newreference) else None ),
newref_sitemap=(args.newreference if (
args.newreference) else None),
empty=args.empty,
paths=args.paths,
outfile=args.outfile,
@ -261,12 +265,13 @@ def main():
links=links)
elif (args.sourcedescription):
c.write_source_description(
capability_lists=parse_capability_lists(args.sourcedescription),
capability_lists=parse_capability_lists(
args.sourcedescription),
outfile=args.outfile,
links=links)
else:
p.error("Unknown mode requested")
# Any problem we expect will come as a ClientFatalError, anything else
# Any problem we expect will come as a ClientFatalError, anything else
# is... an exception ;-)
except ClientFatalError as e:
sys.stderr.write("\nFatalError: " + str(e) + "\n")

32
bin/resync-explorer
View File

@ -27,17 +27,19 @@ from resync.explorer import Explorer
DEFAULT_LOGFILE = 'resync-explorer.log'
def main():
if (sys.version_info < (2,6)):
if (sys.version_info < (2, 6)):
sys.exit("This program requires python version 2.6 or later")
# Options and arguments
p = optparse.OptionParser(description='ResourceSync explorer',
usage='usage: %prog [options] uri_path local_path (-h for help)',
version='%prog '+__version__ )
version='%prog ' + __version__)
# Specification of map between remote URI and local file paths, and remote sitemap
# Specification of map between remote URI and local file paths, and remote
# sitemap
nam = p.add_option_group('FILE/URI NAMING OPTIONS')
nam.add_option('--outfile', type=str, action='store',
help="write sitemap to specified file rather than STDOUT")
@ -53,7 +55,7 @@ def main():
help="updated reference sitemap name for --changelist calculation")
nam.add_option('--dump', metavar='DUMPFILE', type=str, action='store',
help="write dump to specified file for --resourcelist or --changelist")
nam.add_option('--changelist-uri','--change-list-uri', type=str, action='store',
nam.add_option('--changelist-uri', '--change-list-uri', type=str, action='store',
help="explicitly set the changelist URI that will be use in --inc mode, "
"overrides process of getting this from the sitemap")
@ -88,31 +90,31 @@ def main():
(args, map) = p.parse_args()
init_logging( to_file=args.logger, logfile=args.logfile, default_logfile=DEFAULT_LOGFILE,
verbose=args.verbose )
init_logging(to_file=args.logger, logfile=args.logfile, default_logfile=DEFAULT_LOGFILE,
verbose=args.verbose)
print("----- ResourceSync Explorer -----")
c = Explorer( checksum=args.checksum,
verbose=args.verbose )
c = Explorer(checksum=args.checksum,
verbose=args.verbose)
try:
if (map):
# Mappings apply to (almost) everything
c.set_mappings(map)
if (args.sitemap):
c.sitemap_name=args.sitemap
c.sitemap_name = args.sitemap
if (args.exclude):
c.exclude_patterns=args.exclude
c.exclude_patterns = args.exclude
if (args.multifile):
c.allow_multifile=not args.multifile
c.allow_multifile = not args.multifile
if (args.noauth):
c.noauth=args.noauth
c.noauth = args.noauth
if (args.max_sitemap_entries):
c.max_sitemap_entries=args.max_sitemap_entries
c.max_sitemap_entries = args.max_sitemap_entries
c.explore()
# Any problem we expect will come as a ClientFatalError, anything else
# Any problem we expect will come as a ClientFatalError, anything else
# is... an exception ;-)
except ClientFatalError as e:
sys.stderr.write("\nFatalError: " + str(e) + "\n")

3
resync/__init__.py
View File

@ -11,6 +11,5 @@ from resync.change_list import ChangeList
from resync.resource_dump import ResourceDump
from resync.resource_dump_manifest import ResourceDumpManifest
from resync.change_dump import ChangeDump
from resync.archives import ResourceListArchive,ResourceDumpArchive,ChangeListArchive,ChangeDumpArchive
from resync.archives import ResourceListArchive, ResourceDumpArchive, ChangeListArchive, ChangeDumpArchive
from resync.resource import Resource

14
resync/archives.py
View File

@ -2,22 +2,23 @@
The ResourceSync Archives specification
http://www.openarchives.org/rs/archives specifies capabilities
that provide archives of the 4 core capabilities. While some
that provide archives of the 4 core capabilities. While some
optional attributes are different the basic structure is the
same for the Resource List Archive, Change List Archive,
Resource Dump Archive, and Change Dump Archive.
same for the Resource List Archive, Change List Archive,
Resource Dump Archive, and Change Dump Archive.
"""
import collections
try: #python3
try: # python3
from urllib.request import URLopener
except ImportError: #python2
except ImportError: # python2
from urllib import URLopener
from .list_base_with_index import ListBaseWithIndex
from .resource import Resource
from .sitemap import Sitemap
class ResourceListArchive(ListBaseWithIndex):
"""Class representing an Resource List Archive."""
@ -30,6 +31,7 @@ class ResourceListArchive(ListBaseWithIndex):
super(ResourceListArchive, self).__init__(resources=resources, md=md, ln=ln, uri=uri,
capability_name='resourcelist-archive')
class ChangeListArchive(ListBaseWithIndex):
"""Class representing an Change List Archive."""
@ -39,6 +41,7 @@ class ChangeListArchive(ListBaseWithIndex):
super(ChangeListArchive, self).__init__(resources=resources, md=md, ln=ln, uri=uri,
capability_name='changelist-archive')
class ResourceDumpArchive(ListBaseWithIndex):
"""Class representing an Resource Dump Archive."""
@ -49,6 +52,7 @@ class ResourceDumpArchive(ListBaseWithIndex):
capability_name='resourcedump-archive',
resources_class=resources_class)
class ChangeDumpArchive(ListBaseWithIndex):
"""Class representing an Change Dump Archive."""

48
resync/capability_list.py
View File

@ -1,7 +1,7 @@
"""ResourceSync Capability List object.
An Capability List is a set of capabilitys with some metadata for
each capability. The Capability List object may also contain metadata
An Capability List is a set of capabilitys with some metadata for
each capability. The Capability List object may also contain metadata
and links like other lists.
"""
@ -12,26 +12,27 @@ from .resource_set import ResourceSet
from .list_base import ListBase
from .sitemap import Sitemap
class CapabilitySet(ResourceSet):
"""Class for storage of resources in a Capability List.
Extends the ResourceSet to add checks to ensure that there are
never two entries for the same resource, and that values are
Extends the ResourceSet to add checks to ensure that there are
never two entries for the same resource, and that values are
returned in the canonical order.
"""
def __init__(self):
"""Initialize CpabilitySet."""
self.order = [ 'resourcelist', 'resourcedump',
'changelist', 'changedump',
'resourcelist-archive', 'resourcedump-archive',
'changelist-archive', 'changedump-archive' ]
self.order = ['resourcelist', 'resourcedump',
'changelist', 'changedump',
'resourcelist-archive', 'resourcedump-archive',
'changelist-archive', 'changedump-archive']
def __iter__(self):
"""Iterator over all the resources in capability order.
Deals with the case of unknown capabilities or duplicate entries
by using uri order for duplicates and adding any unknown ones
by using uri order for duplicates and adding any unknown ones
at the end
"""
self._iter_next_list = []
@ -40,7 +41,7 @@ class CapabilitySet(ResourceSet):
for uri in self.keys():
cap = self[uri].capability
if (cap not in uris):
uris[cap]=[]
uris[cap] = []
uris[cap].append(uri)
# build list or uris in defined order for iterator
for cap in self.order:
@ -48,7 +49,8 @@ class CapabilitySet(ResourceSet):
for uri in sorted(uris[cap]):
self._iter_next_list.append(uri)
del uris[cap]
# add any left over capabilities we don't know about in alphabetical order
# add any left over capabilities we don't know about in alphabetical
# order
for cap in uris:
for uri in sorted(uris[cap]):
self._iter_next_list.append(uri)
@ -56,7 +58,7 @@ class CapabilitySet(ResourceSet):
return(iter(self._iter_next, None))
def _iter_next(self):
if (len(self._iter_next_list)>0):
if (len(self._iter_next_list) > 0):
return(self[self._iter_next_list.pop()])
else:
return(None)
@ -65,7 +67,7 @@ class CapabilitySet(ResourceSet):
class CapabilityList(ListBase):
"""Class representing a Capability List.
An Capability List will admit only one resource with any given
An Capability List will admit only one resource with any given
URI. The iterator over resources is expected to return them in
canonical order of capability names as defined in main specification
section 7 and archives specification section 6.
@ -88,15 +90,15 @@ class CapabilityList(ListBase):
"""
if isinstance(resource, collections.Iterable):
for r in resource:
self.resources.add(r,replace)
self.resources.add(r, replace)
else:
self.resources.add(resource,replace)
self.resources.add(resource, replace)
def add_capability(self,capability=None,uri=None,name=None):
def add_capability(self, capability=None, uri=None, name=None):
"""Specific add function for capabilities.
Takes either:
- a capability object (derived from ListBase) as the first argument
- a capability object (derived from ListBase) as the first argument
from which the capability name is extracted, and the URI if given
- or a plain name string
and
@ -105,14 +107,14 @@ class CapabilityList(ListBase):
if (capability is not None):
name = capability.capability_name
if (capability.uri is not None):
uri=capability.uri
self.add( Resource(uri=uri,capability=name) )
uri = capability.uri
self.add(Resource(uri=uri, capability=name))
def has_capability(self,name=None):
def has_capability(self, name=None):
"""True if the Capability List includes the named capability."""
return( self.capability_info(name) is not None )
return(self.capability_info(name) is not None)
def capability_info(self,name=None):
def capability_info(self, name=None):
"""Return information about the requested capability from this list.
Will return None if there is no information about the requested capability.

8
resync/change_dump.py
View File

@ -1,7 +1,7 @@
"""ResourceSync Change Dump object.
A Change Dump is a set of content dump package resources
with some metadata for each resource.
with some metadata for each resource.
The Change Dump may also contain metadata and links like
other ResourceSync documents.
@ -12,6 +12,7 @@ http://www.openarchives.org/rs/resourcesync#ChangeDump
from .resource_list import ResourceList
class ChangeDump(ResourceList):
"""Class representing an Change Dump.
@ -20,7 +21,8 @@ class ChangeDump(ResourceList):
and implemented as a sub-class of ResourceList.
"""
def __init__(self, resources=None, md=None, ln=None, uri=None, allow_multifile=None, mapper=None):
def __init__(self, resources=None, md=None, ln=None,
uri=None, allow_multifile=None, mapper=None):
"""Initialize ChangeDump.
Simply sets capability_name to 'changedump' when
@ -28,4 +30,4 @@ class ChangeDump(ResourceList):
"""
super(ChangeDump, self).__init__(resources=resources, md=md, ln=ln, uri=uri,
mapper=mapper)
self.capability_name='changedump'
self.capability_name = 'changedump'

14
resync/change_dump_manifest.py
View File

@ -1,10 +1,10 @@
"""ResourceSync ChangeDumpManifest object.
A ChangeDumpManifest lists the set of files/resources included
within a content package that is included in a ChangeDump.
A ChangeDumpManifest lists the set of files/resources included
within a content package that is included in a ChangeDump.
The ChangeeDumpManifest object will include the change type,
a path for each item (except in the case of "deleted"), and may
a path for each item (except in the case of "deleted"), and may
also contain metadata and links.
Described in specification at:
@ -13,6 +13,7 @@ http://www.openarchives.org/rs/resourcesync#ChangeDumpManifest
from .change_list import ChangeList
class ChangeDumpManifest(ChangeList):
"""Class representing a Change Dump Manifest.
@ -21,11 +22,14 @@ class ChangeDumpManifest(ChangeList):
and implemented as a sub-class of ChangeeList.
"""
def __init__(self, resources=None, md=None, ln=None, uri=None, allow_multifile=None, mapper=None):
def __init__(self, resources=None, md=None, ln=None,
uri=None, allow_multifile=None, mapper=None):
"""Initialize ChangeDumpManifest.
Simply sets capability_name to 'changedump-manifest' when
subclassing ChangeList.
"""
super(ChangeDumpManifest, self).__init__(resources=resources, md=md, ln=ln, uri=uri, mapper=mapper)
super(ChangeDumpManifest, self).__init__(
resources=resources, md=md, ln=ln,
uri=uri, mapper=mapper)
self.capability_name = 'changedump-manifest'

23
resync/change_list.py
View File

@ -8,23 +8,24 @@ are Resource objects.
Different from an resource_list, a change_list may include multiple
descriptions for the same resource. The change_list is ordered
from first entry to last entry.
from first entry to last entry.
Different from an resource_list, dereference by a URI yields a
ChangeList containing descriptions pertaining to that
Different from an resource_list, dereference by a URI yields a
ChangeList containing descriptions pertaining to that
particular resource.
"""
import collections
try: #python3
try: # python3
from urllib.request import URLopener
except ImportError: #python2
except ImportError: # python2
from urllib import URLopener
from .list_base_with_index import ListBaseWithIndex
from .resource import Resource,ChangeTypeError
from .resource import Resource, ChangeTypeError
from .sitemap import Sitemap
class ChangeList(ListBaseWithIndex):
"""Class representing an Change List."""
@ -38,14 +39,14 @@ class ChangeList(ListBaseWithIndex):
def add_if_changed(self, resource):
"""Add resource if change is not None else ChangeTypeError."""
if (resource.change is not None):
self.resources.append(resource)
self.resources.append(resource)
else:
raise ChangeTypeError(resource.change)
def add(self, resource):
"""Add a resource change or an iterable collection of them.
Allows multiple resource_change objects for the same
Allows multiple resource_change objects for the same
resource (ie. URI) and preserves the order of addition.
"""
if isinstance(resource, collections.Iterable):
@ -57,9 +58,9 @@ class ChangeList(ListBaseWithIndex):
def add_changed_resources(self, resources, change=None):
"""Add items from a ResourceContainer resources.
If change is specified then the attribute is set in the Resource
If change is specified then the attribute is set in the Resource
objects created.
"""
for resource in resources:
rc = Resource( resource=resource, change=change )
rc = Resource(resource=resource, change=change)
self.add(rc)

456
resync/client.py
View File

@ -1,15 +1,15 @@
"""ResourceSync client implementation."""
import sys
try: #python3
try: # python3
from urllib.request import urlretrieve
from urllib.parse import urlparse, urlunparse
except ImportError: #python2
except ImportError: # python2
from urllib import urlretrieve
from urlparse import urlparse, urlunparse
import os.path
import datetime
import distutils.dir_util
import distutils.dir_util
import re
import time
import logging
@ -29,7 +29,8 @@ from .utils import compute_md5_for_file
from .client_state import ClientState
from .client_utils import ClientFatalError, url_or_file_open
from .list_base_with_index import ListBaseIndexError
from .w3c_datetime import str_to_datetime,datetime_to_str
from .w3c_datetime import str_to_datetime, datetime_to_str
class Client(object):
"""Implementation of a ResourceSync client.
@ -65,17 +66,16 @@ class Client(object):
self.default_resource_dump = 'resourcedump.zip'
self.default_change_dump = 'changedump.zip'
def set_mappings(self,mappings):
def set_mappings(self, mappings):
"""Build and set Mapper object based on input mappings."""
self.mapper = Mapper(mappings, use_default_path=True)
def sitemap_uri(self,basename):
def sitemap_uri(self, basename):
"""Get full URI (filepath) for sitemap based on basename."""
if (re.match(r"\w+:",basename)):
if (re.match(r"\w+:", basename)):
# looks like URI
return(basename)
elif (re.match(r"/",basename)):
elif (re.match(r"/", basename)):
# looks like full path
return(basename)
else:
@ -97,21 +97,22 @@ class Client(object):
paths - override paths from mappings if specified
set_path - set true to set the path information for each resource
set_path - set true to set the path information for each resource
included. This is used to build a resource list as the basis
for creating a dump.
Return ResourceList. Uses existing self.mapper settings.
"""
# 0. Sanity checks, parse paths is specified
if (len(self.mapper)<1):
raise ClientFatalError("No source to destination mapping specified")
if (len(self.mapper) < 1):
raise ClientFatalError(
"No source to destination mapping specified")
if (paths is not None):
# Expect comma separated list of paths
paths=paths.split(',')
paths = paths.split(',')
# 1. Build from disk
rlb = ResourceListBuilder(set_md5=self.checksum,mapper=self.mapper)
rlb.set_path=set_path
rlb = ResourceListBuilder(set_md5=self.checksum, mapper=self.mapper)
rlb.set_path = set_path
try:
rlb.add_exclude_files(self.exclude_patterns)
rl = rlb.from_disk(paths=paths)
@ -127,137 +128,171 @@ class Client(object):
def log_event(self, change):
"""Log a Resource object as an event for automated analysis."""
self.logger.debug( "Event: "+repr(change) )
self.logger.debug("Event: " + repr(change))
def baseline_or_audit(self, allow_deletion=False, audit_only=False):
"""Baseline synchonization or audit.
Both functions implemented in this routine because audit is a prerequisite
for a baseline sync. In the case of baseline sync the last timestamp seen
is recorded as client state.
"""
action = ( 'audit' if (audit_only) else 'baseline sync' )
self.logger.debug("Starting "+action)
### 0. Sanity checks
if (len(self.mapper)<1):
raise ClientFatalError("No source to destination mapping specified")
action = ('audit' if (audit_only) else 'baseline sync')
self.logger.debug("Starting " + action)
# 0. Sanity checks
if (len(self.mapper) < 1):
raise ClientFatalError(
"No source to destination mapping specified")
if (not audit_only and self.mapper.unsafe()):
raise ClientFatalError("Source to destination mappings unsafe: %s" % str(self.mapper))
### 1. Get inventories from both src and dst
raise ClientFatalError(
"Source to destination mappings unsafe: %s" % str(
self.mapper))
# 1. Get inventories from both src and dst
# 1.a source resource list
try:
self.logger.info("Reading sitemap %s" % (self.sitemap))
src_resource_list = ResourceList(allow_multifile=self.allow_multifile, mapper=self.mapper)
src_resource_list = ResourceList(
allow_multifile=self.allow_multifile, mapper=self.mapper)
src_resource_list.read(uri=self.sitemap)
self.logger.debug("Finished reading sitemap")
except Exception as e:
raise ClientFatalError("Can't read source resource list from %s (%s)" % (self.sitemap,str(e)))
self.logger.info("Read source resource list, %d resources listed" % (len(src_resource_list)))
if (len(src_resource_list)==0):
raise ClientFatalError("Aborting as there are no resources to sync")
raise ClientFatalError(
"Can't read source resource list from %s (%s)" %
(self.sitemap, str(e)))
self.logger.info(
"Read source resource list, %d resources listed" %
(len(src_resource_list)))
if (len(src_resource_list) == 0):
raise ClientFatalError(
"Aborting as there are no resources to sync")
if (self.checksum and not src_resource_list.has_md5()):
self.checksum=False
self.logger.info("Not calculating checksums on destination as not present in source resource list")
self.checksum = False
self.logger.info(
"Not calculating checksums on destination as not present in source resource list")
# 1.b destination resource list mapped back to source URIs
rlb = ResourceListBuilder(set_md5=self.checksum, mapper=self.mapper)
dst_resource_list = rlb.from_disk()
### 2. Compare these resource lists respecting any comparison options
(same,updated,deleted,created)=dst_resource_list.compare(src_resource_list)
### 3. Report status and planned actions
self.log_status(in_sync=(len(updated)+len(deleted)+len(created)==0),
audit=True,same=len(same),created=len(created),
updated=len(updated),deleted=len(deleted))
if (audit_only or len(created)+len(updated)+len(deleted)==0):
self.logger.debug("Completed "+action)
# 2. Compare these resource lists respecting any comparison options
(same, updated, deleted, created) = dst_resource_list.compare(src_resource_list)
# 3. Report status and planned actions
self.log_status(in_sync=(len(updated) + len(deleted) + len(created) == 0),
audit=True, same=len(same), created=len(created),
updated=len(updated), deleted=len(deleted))
if (audit_only or len(created) + len(updated) + len(deleted) == 0):
self.logger.debug("Completed " + action)
return
### 4. Check that sitemap has authority over URIs listed
# 4. Check that sitemap has authority over URIs listed
if (not self.noauth):
uauth = UrlAuthority(self.sitemap, strict=self.strictauth)
for resource in src_resource_list:
if (not uauth.has_authority_over(resource.uri)):
raise ClientFatalError("Aborting as sitemap (%s) mentions resource at a location it does not have authority over (%s), override with --noauth" % (self.sitemap,resource.uri))
### 5. Grab files to do sync
delete_msg = (", and delete %d resources" % len(deleted)) if (allow_deletion) else ''
self.logger.warning("Will GET %d resources%s" % (len(created)+len(updated),delete_msg))
raise ClientFatalError(
"Aborting as sitemap (%s) mentions resource at a location it does not have authority over (%s), override with --noauth" %
(self.sitemap, resource.uri))
# 5. Grab files to do sync
delete_msg = (
", and delete %d resources" %
len(deleted)) if (allow_deletion) else ''
self.logger.warning(
"Will GET %d resources%s" %
(len(created) + len(updated), delete_msg))
self.last_timestamp = 0
num_created=0
num_updated=0
num_deleted=0
num_created = 0
num_updated = 0
num_deleted = 0
for resource in created:
uri = resource.uri
filename = self.mapper.src_to_dst(uri)
self.logger.info("created: %s -> %s" % (uri,filename))
num_created+=self.update_resource(resource,filename,'created')
self.logger.info("created: %s -> %s" % (uri, filename))
num_created += self.update_resource(resource, filename, 'created')
for resource in updated:
uri = resource.uri
filename = self.mapper.src_to_dst(uri)
self.logger.info("updated: %s -> %s" % (uri,filename))
num_updated+=self.update_resource(resource,filename,'updated')
self.logger.info("updated: %s -> %s" % (uri, filename))
num_updated += self.update_resource(resource, filename, 'updated')
for resource in deleted:
uri = resource.uri
filename = self.mapper.src_to_dst(uri)
num_deleted+=self.delete_resource(resource,filename,allow_deletion)
### 6. Store last timestamp to allow incremental sync
if (not audit_only and self.last_timestamp>0):
ClientState().set_state(self.sitemap,self.last_timestamp)
self.logger.info("Written last timestamp %s for incremental sync" % (datetime_to_str(self.last_timestamp)))
### 7. Done
self.log_status(in_sync=(len(updated)+len(deleted)+len(created)==0),
same=len(same),created=num_created,
updated=num_updated,deleted=num_deleted,to_delete=len(deleted))
num_deleted += self.delete_resource(resource,
filename, allow_deletion)
# 6. Store last timestamp to allow incremental sync
if (not audit_only and self.last_timestamp > 0):
ClientState().set_state(self.sitemap, self.last_timestamp)
self.logger.info(
"Written last timestamp %s for incremental sync" %
(datetime_to_str(
self.last_timestamp)))
# 7. Done
self.log_status(in_sync=(len(updated) + len(deleted) + len(created) == 0),
same=len(same), created=num_created,
updated=num_updated, deleted=num_deleted, to_delete=len(deleted))
self.logger.debug("Completed %s" % (action))
def incremental(self, allow_deletion=False, change_list_uri=None, from_datetime=None):
def incremental(self, allow_deletion=False,
change_list_uri=None, from_datetime=None):
"""Incremental synchronization.
Use Change List to do incremental sync
"""
self.logger.debug("Starting incremental sync")
### 0. Sanity checks
if (len(self.mapper)<1):
raise ClientFatalError("No source to destination mapping specified")
# 0. Sanity checks
if (len(self.mapper) < 1):
raise ClientFatalError(
"No source to destination mapping specified")
if (self.mapper.unsafe()):
raise ClientFatalError("Source to destination mappings unsafe: %s" % str(self.mapper))
raise ClientFatalError(
"Source to destination mappings unsafe: %s" % str(
self.mapper))
from_timestamp = None
if (from_datetime is not None):
try:
from_timestamp = str_to_datetime(from_datetime)
except ValueError:
raise ClientFatalError("Bad datetime in --from (%s)" % from_datetime)
### 1. Work out where to start from
raise ClientFatalError(
"Bad datetime in --from (%s)" %
from_datetime)
# 1. Work out where to start from
if (from_timestamp is None):
from_timestamp=ClientState().get_state(self.sitemap)
from_timestamp = ClientState().get_state(self.sitemap)
if (from_timestamp is None):
raise ClientFatalError("Cannot do incremental sync. No stored timestamp for this site, and no explicit --from.")
### 2. Get URI of change list, from sitemap or explicit
raise ClientFatalError(
"Cannot do incremental sync. No stored timestamp for this site, and no explicit --from.")
# 2. Get URI of change list, from sitemap or explicit
if (change_list_uri):
# Translate as necessary using maps
change_list = self.sitemap_uri(change_list_uri)
else:
# Try default name
change_list = self.sitemap_uri(self.change_list_name)
### 3. Read change list from source
# 3. Read change list from source
try:
self.logger.info("Reading change list %s" % (change_list))
src_change_list = ChangeList()
src_change_list.read(uri=change_list)
self.logger.debug("Finished reading change list")
except Exception as e:
raise ClientFatalError("Can't read source change list from %s (%s)" % (change_list,str(e)))
self.logger.info("Read source change list, %d changes listed" % (len(src_change_list)))
#if (len(src_change_list)==0):
raise ClientFatalError(
"Can't read source change list from %s (%s)" %
(change_list, str(e)))
self.logger.info(
"Read source change list, %d changes listed" %
(len(src_change_list)))
# if (len(src_change_list)==0):
# raise ClientFatalError("Aborting as there are no resources to sync")
if (self.checksum and not src_change_list.has_md5()):
self.checksum=False
self.logger.info("Not calculating checksums on destination as not present in source change list")
self.checksum = False
self.logger.info(
"Not calculating checksums on destination as not present in source change list")
# Check all changes have timestamp and record last
self.last_timestamp = 0
for resource in src_change_list:
if (resource.timestamp is None):
raise ClientFatalError("Aborting - missing timestamp for change in %s" % (uri))
raise ClientFatalError(
"Aborting - missing timestamp for change in %s" %
(uri))
if (resource.timestamp > self.last_timestamp):
self.last_timestamp = resource.timestamp
### 4. Check that the change list has authority over URIs listed
# 4. Check that the change list has authority over URIs listed
# FIXME - What does authority mean for change list? Here use both the
# change list URI and, if we used it, the sitemap URI
if (not self.noauth):
@ -265,15 +300,20 @@ class Client(object):
if (not change_list_uri):
uauth_sm = UrlAuthority(self.sitemap)
for resource in src_change_list:
if (not uauth_cs.has_authority_over(resource.uri) and
(change_list_uri or not uauth_sm.has_authority_over(resource.uri))):
raise ClientFatalError("Aborting as change list (%s) mentions resource at a location it does not have authority over (%s), override with --noauth" % (change_list,resource.uri))
### 5. Prune entries before starting timestamp and dupe changes for a resource
if (not uauth_cs.has_authority_over(resource.uri) and
(change_list_uri or not uauth_sm.has_authority_over(resource.uri))):
raise ClientFatalError(
"Aborting as change list (%s) mentions resource at a location it does not have authority over (%s), override with --noauth" %
(change_list, resource.uri))
# 5. Prune entries before starting timestamp and dupe changes for a
# resource
num_skipped = src_change_list.prune_before(from_timestamp)
if (num_skipped>0):
self.logger.info("Skipped %d changes before %s" % (num_skipped,datetime_to_str(from_timestamp)))
if (num_skipped > 0):
self.logger.info(
"Skipped %d changes before %s" %
(num_skipped, datetime_to_str(from_timestamp)))
num_dupes = src_change_list.prune_dupes()
if (num_dupes>0):
if (num_dupes > 0):
self.logger.info("Removed %d prior changes" % (num_dupes))
# Review and log status before
# FIXME - should at this stage prune the change list to pick out
@ -283,25 +323,29 @@ class Client(object):
to_delete = 0
for resource in src_change_list:
if (resource.change == 'updated'):
to_update+=1
to_update += 1
elif (resource.change == 'created'):
to_create+=1
to_create += 1
elif (resource.change == 'deleted'):
to_delete+=1
to_delete += 1
else:
raise ClientError("Unknown change type %s" % (resource.change) )
raise ClientError("Unknown change type %s" % (resource.change))
# Log status based on what we know from the Change List. Exit if
# either there are no changes or if there are only deletions and
# we don't allow deletion
in_sync = ((to_update+to_delete+to_create)==0)
self.log_status(in_sync=in_sync, incremental=True, created=to_create,
in_sync = ((to_update + to_delete + to_create) == 0)
self.log_status(in_sync=in_sync, incremental=True, created=to_create,
updated=to_update, deleted=to_delete)
if (in_sync or ((to_update+to_create)==0 and not allow_deletion)):
if (in_sync or ((to_update + to_create) == 0 and not allow_deletion)):
self.logger.debug("Completed incremental")
return
### 6. Apply changes at same time or after from_timestamp
delete_msg = (", and delete %d resources" % to_delete) if (allow_deletion) else ''
self.logger.warning("Will apply %d changes%s" % (len(src_change_list),delete_msg))
# 6. Apply changes at same time or after from_timestamp
delete_msg = (
", and delete %d resources" %
to_delete) if (allow_deletion) else ''
self.logger.warning(
"Will apply %d changes%s" %
(len(src_change_list), delete_msg))
num_updated = 0
num_deleted = 0
num_created = 0
@ -309,25 +353,29 @@ class Client(object):
uri = resource.uri
filename = self.mapper.src_to_dst(uri)
if (resource.change == 'updated'):
self.logger.info("updated: %s -> %s" % (uri,filename))
self.update_resource(resource,filename,'updated')
num_updated+=1
self.logger.info("updated: %s -> %s" % (uri, filename))
self.update_resource(resource, filename, 'updated')
num_updated += 1
elif (resource.change == 'created'):
self.logger.info("created: %s -> %s" % (uri,filename))
self.update_resource(resource,filename,'created')
num_created+=1
self.logger.info("created: %s -> %s" % (uri, filename))
self.update_resource(resource, filename, 'created')
num_created += 1
elif (resource.change == 'deleted'):
num_deleted+=self.delete_resource(resource,filename,allow_deletion)
num_deleted += self.delete_resource(
resource, filename, allow_deletion)
else:
raise ClientError("Unknown change type %s" % (resource.change) )
### 7. Report status and planned actions
self.log_status(incremental=True,created=num_created, updated=num_updated,
deleted=num_deleted,to_delete=to_delete)
### 8. Record last timestamp we have seen
if (self.last_timestamp>0):
ClientState().set_state(self.sitemap,self.last_timestamp)
self.logger.info("Written last timestamp %s for incremental sync" % (datetime_to_str(self.last_timestamp)))
### 9. Done
raise ClientError("Unknown change type %s" % (resource.change))
# 7. Report status and planned actions
self.log_status(incremental=True, created=num_created, updated=num_updated,
deleted=num_deleted, to_delete=to_delete)
# 8. Record last timestamp we have seen
if (self.last_timestamp > 0):
ClientState().set_state(self.sitemap, self.last_timestamp)
self.logger.info(
"Written last timestamp %s for incremental sync" %
(datetime_to_str(
self.last_timestamp)))
# 9. Done
self.logger.debug("Completed incremental sync")
def update_resource(self, resource, filename, change=None):
@ -336,8 +384,8 @@ class Client(object):
Update means three things:
1. GET resources
2. set mtime in local time to be equal to timestamp in UTC (should perhaps
or at least warn if different from LastModified from the GET response instead
but maybe warn if different (or just earlier than) the lastmod we expected
or at least warn if different from LastModified from the GET response instead
but maybe warn if different (or just earlier than) the lastmod we expected
from the resource list
3. check that resource matches expected information
@ -348,16 +396,18 @@ class Client(object):
"""
path = os.path.dirname(filename)
distutils.dir_util.mkpath(path)
num_updated=0
num_updated = 0
if (self.dryrun):
self.logger.info("dryrun: would GET %s --> %s" % (resource.uri,filename))
self.logger.info(
"dryrun: would GET %s --> %s" %
(resource.uri, filename))
else:
# 1. GET
try:
urlretrieve(resource.uri,filename)
num_updated+=1
urlretrieve(resource.uri, filename)
num_updated += 1
except IOError as e:
msg = "Failed to GET %s -- %s" % (resource.uri,str(e))
msg = "Failed to GET %s -- %s" % (resource.uri, str(e))
if (self.ignore_failures):
self.logger.warning(msg)
return(num_updated)
@ -365,62 +415,74 @@ class Client(object):
raise ClientFatalError(msg)
# 2. set timestamp if we have one
if (resource.timestamp is not None):
unixtime = int(resource.timestamp) #no fractional
os.utime(filename,(unixtime,unixtime))
unixtime = int(resource.timestamp) # no fractional
os.utime(filename, (unixtime, unixtime))
if (resource.timestamp > self.last_timestamp):
self.last_timestamp = resource.timestamp
self.log_event(Resource(resource=resource, change=change))
# 3. sanity check
length = os.stat(filename).st_size
if (resource.length is not None and resource.length != length):
self.logger.info("Downloaded size for %s of %d bytes does not match expected %d bytes" % (resource.uri,length,resource.length))
self.logger.info(
"Downloaded size for %s of %d bytes does not match expected %d bytes" %
(resource.uri, length, resource.length))
if (self.checksum and resource.md5 is not None):
file_md5 = compute_md5_for_file(filename)
if (resource.md5 != file_md5):
self.logger.info("MD5 mismatch for %s, got %s but expected %s bytes" % (resource.uri,file_md5,resource.md5))
self.logger.info(
"MD5 mismatch for %s, got %s but expected %s bytes" %
(resource.uri, file_md5, resource.md5))
return(num_updated)
def delete_resource(self, resource, filename, allow_deletion=False):
"""Delete copy of resource in filename on local system.
Will only actually do the deletion if allow_deletion is True. Regardless
of whether the deletion occurs, self.last_timestamp will be updated
Will only actually do the deletion if allow_deletion is True. Regardless
of whether the deletion occurs, self.last_timestamp will be updated
if the resource.timestamp is later than the current value.
Returns the number of files actually deleted (0 or 1).
"""
num_deleted=0
num_deleted = 0
uri = resource.uri
if (resource.timestamp is not None and
resource.timestamp > self.last_timestamp):
resource.timestamp > self.last_timestamp):
self.last_timestamp = resource.timestamp
if (allow_deletion):
if (self.dryrun):
self.logger.info("dryrun: would delete %s -> %s" % (uri,filename))
self.logger.info(
"dryrun: would delete %s -> %s" %
(uri, filename))
else:
try:
os.unlink(filename)
num_deleted+=1
self.logger.info("deleted: %s -> %s" % (uri,filename))
self.log_event(Resource(resource=resource, change="deleted"))
num_deleted += 1
self.logger.info("deleted: %s -> %s" % (uri, filename))
self.log_event(
Resource(
resource=resource,
change="deleted"))
except OSError as e:
msg = "Failed to DELETE %s -> %s : %s" % (uri,filename,str(e))
#if (self.ignore_failures):
msg = "Failed to DELETE %s -> %s : %s" % (
uri, filename, str(e))
# if (self.ignore_failures):
self.logger.warning(msg)
# return
#else:
# else:
# raise ClientFatalError(msg)
else:
self.logger.info("nodelete: would delete %s (--delete to enable)" % uri)
self.logger.info(
"nodelete: would delete %s (--delete to enable)" %
uri)
return(num_deleted)
def parse_document(self):
"""Parse any ResourceSync document and show information.
Will use sitemap URI taken either from explicit self.sitemap_name
or derived from the mappings supplied.
"""
s=Sitemap()
s = Sitemap()
self.logger.info("Reading sitemap(s) from %s ..." % (self.sitemap))
try:
list = s.parse_xml(url_or_file_open(self.sitemap))
@ -430,33 +492,36 @@ class Client(object):
capability = '(unknown capability)'
if ('capability' in list.md):
capability = list.md['capability']
print("Parsed %s document with %d entries" % (capability,num_entries))
print("Parsed %s document with %d entries" % (capability, num_entries))
if (self.verbose):
to_show = 100
override_str = ' (override with --max-sitemap-entries)'
if (self.max_sitemap_entries):
to_show = self.max_sitemap_entries
override_str = ''
if (num_entries>to_show):
print("Showing first %d entries sorted by URI%s..." % (to_show,override_str))
n=0
if (num_entries > to_show):
print(
"Showing first %d entries sorted by URI%s..." %
(to_show, override_str))
n = 0
for resource in list:
print('[%d] %s' % (n,str(resource)))
n+=1
if ( n >= to_show ):
print('[%d] %s' % (n, str(resource)))
n += 1
if (n >= to_show):
break
def write_resource_list(self,paths=None,outfile=None,links=None,dump=None):
def write_resource_list(
self, paths=None, outfile=None, links=None, dump=None):
"""Write a Resource List or a Resource Dump for files on local disk.
Set of resources included is based on paths setting or else the mappings.
Set of resources included is based on paths setting or else the mappings.
Optionally links can be added. Output will be to stdout unless outfile
is specified.
If dump is true then a Resource Dump is written instead of a Resource
List. If outfile is not set then self.default_resource_dump will be used.
"""
rl = self.build_resource_list(paths=paths,set_path=dump)
rl = self.build_resource_list(paths=paths, set_path=dump)
if (links is not None):
rl.ln = links
if (dump):
@ -470,15 +535,17 @@ class Client(object):
try:
print(rl.as_xml())
except ListBaseIndexError as e:
raise ClientFatalError("%s. Use --output option to specify base name for output files." % str(e))
raise ClientFatalError(
"%s. Use --output option to specify base name for output files." %
str(e))
else:
rl.write(basename=outfile)
def write_change_list(self,paths=None,outfile=None,ref_sitemap=None,newref_sitemap=None,
empty=None,links=None,dump=None):
def write_change_list(self, paths=None, outfile=None, ref_sitemap=None, newref_sitemap=None,
empty=None, links=None, dump=None):
"""Write a change list.
Unless the both ref_sitemap and newref_sitemap are specified then the Change
Unless the both ref_sitemap and newref_sitemap are specified then the Change
List is calculated between the reference an the current state of files on
disk. The files on disk are scanned based either on the paths setting or
else on the mappings.
@ -487,18 +554,19 @@ class Client(object):
if (not empty):
# 1. Get and parse reference sitemap
old_rl = self.read_reference_resource_list(ref_sitemap)
# 2. Depending on whether a newref_sitemap was specified, either read that
# 2. Depending on whether a newref_sitemap was specified, either read that
# or build resource list from files on disk
if (newref_sitemap is None):
# Get resource list from disk
new_rl = self.build_resource_list(paths=paths,set_path=dump)
new_rl = self.build_resource_list(paths=paths, set_path=dump)
else:
new_rl = self.read_reference_resource_list(newref_sitemap,name='new reference')
new_rl = self.read_reference_resource_list(
newref_sitemap, name='new reference')
# 3. Calculate change list
(same,updated,deleted,created)=old_rl.compare(new_rl)
cl.add_changed_resources( updated, change='updated' )
cl.add_changed_resources( deleted, change='deleted' )
cl.add_changed_resources( created, change='created' )
(same, updated, deleted, created) = old_rl.compare(new_rl)
cl.add_changed_resources(updated, change='updated')
cl.add_changed_resources(deleted, change='deleted')
cl.add_changed_resources(created, change='created')
# 4. Write out change list
cl.mapper = self.mapper
cl.pretty_xml = self.pretty_xml
@ -508,9 +576,10 @@ class Client(object):
print(cl.as_xml())
else:
cl.write(basename=outfile)
self.write_dump_if_requested(cl,dump)
self.write_dump_if_requested(cl, dump)
def write_capability_list(self,capabilities=None,outfile=None,links=None):
def write_capability_list(self, capabilities=None,
outfile=None, links=None):
"""Write a Capability List to outfile or STDOUT."""
capl = CapabilityList(ln=links)
capl.pretty_xml = self.pretty_xml
@ -522,7 +591,8 @@ class Client(object):
else:
capl.write(basename=outfile)
def write_source_description(self,capability_lists=None,outfile=None,links=None):
def write_source_description(
self, capability_lists=None, outfile=None, links=None):
"""Write a ResourceSync Description document to outfile or STDOUT."""
rsd = SourceDescription(ln=links)
rsd.pretty_xml = self.pretty_xml
@ -534,70 +604,76 @@ class Client(object):
else:
rsd.write(basename=outfile)
def write_dump_if_requested(self,resource_list,dump):
def write_dump_if_requested(self, resource_list, dump):
"""Write a dump to the file dump."""
if (dump is None):
return
print("OOPS - FIXME - Wrinting dump to %s not yet implemented" % (dump))
return(1)
def read_reference_resource_list(self,ref_sitemap,name='reference'):
def read_reference_resource_list(self, ref_sitemap, name='reference'):
"""Read reference resource list and return the ResourceList object.
The name parameter is used just in output messages to say what type
of resource list is being read.
"""
rl = ResourceList()
self.logger.info("Reading %s resource list from %s ..." % (name,ref_sitemap))
rl.mapper=self.mapper
rl.read(uri=ref_sitemap,index_only=(not self.allow_multifile))
self.logger.info(
"Reading %s resource list from %s ..." %
(name, ref_sitemap))
rl.mapper = self.mapper
rl.read(uri=ref_sitemap, index_only=(not self.allow_multifile))
num_entries = len(rl.resources)
self.logger.info("Read %s resource list with %d entries in %d sitemaps" % (name,num_entries,rl.num_files))
self.logger.info(
"Read %s resource list with %d entries in %d sitemaps" %
(name, num_entries, rl.num_files))
if (self.verbose):
to_show = 100
override_str = ' (override with --max-sitemap-entries)'
if (self.max_sitemap_entries):
to_show = self.max_sitemap_entries
override_str = ''
if (num_entries>to_show):
print("Showing first %d entries sorted by URI%s..." % (to_show,override_str))
n=0
if (num_entries > to_show):
print(
"Showing first %d entries sorted by URI%s..." %
(to_show, override_str))
n = 0
for r in rl.resources:
print(r)
n+=1
if ( n >= to_show ):
n += 1
if (n >= to_show):
break
return(rl)
def log_status(self, in_sync=True, incremental=False, audit=False,
same=None, created=0, updated=0, deleted=0, to_delete=0):
"""Write log message regarding status in standard form.
Split this off so all messages from baseline/audit/incremental
are written in a consistent form.
"""
if (audit):
words = { 'created': 'to create',
'updated': 'to update',
'deleted': 'to delete' }
words = {'created': 'to create',
'updated': 'to update',
'deleted': 'to delete'}
else:
words = { 'created': 'created',
'updated': 'updated',
'deleted': 'deleted' }
words = {'created': 'created',
'updated': 'updated',
'deleted': 'deleted'}
if in_sync:
# status rather than action
status = "NO CHANGES" if incremental else "IN SYNC"
status = "NO CHANGES" if incremental else "IN SYNC"
else:
if audit:
status = "NOT IN SYNC"
elif (to_delete>deleted):
#will need --delete
elif (to_delete > deleted):
# will need --delete
status = "PART APPLIED" if incremental else"PART SYNCED"
words['deleted']='to delete (--delete)'
deleted=to_delete
else:
words['deleted'] = 'to delete (--delete)'
deleted = to_delete
else:
status = "CHANGES APPLIED" if incremental else "SYNCED"
same = "" if (same is None) else ("same=%d, " % same)
self.logger.warning("Status: %15s (%s%s=%d, %s=%d, %s=%d)" %\
(status, same, words['created'], created,
words['updated'], updated, words['deleted'], deleted))
same = "" if (same is None) else ("same=%d, " % same)
self.logger.warning("Status: %15s (%s%s=%d, %s=%d, %s=%d)" %
(status, same, words['created'], created,
words['updated'], updated, words['deleted'], deleted))

28
resync/client_state.py
View File

@ -8,13 +8,13 @@ of the last change seen.
import sys
import os.path
import datetime
import distutils.dir_util
import distutils.dir_util
import re
import time
import logging
try: #python3
try: # python3
from configparser import ConfigParser, NoSectionError, NoOptionError
except ImportError: #python2
except ImportError: # python2
from ConfigParser import SafeConfigParser as ConfigParser, NoSectionError, NoOptionError
@ -25,9 +25,9 @@ class ClientState(object):
"""Initialize ClientState object with default status file name."""
self.status_file = '.resync-client-status.cfg'
def set_state(self,site,timestamp=None):
def set_state(self, site, timestamp=None):
"""Write status dict to client status file.
FIXME - should have some file lock to avoid race
"""
parser = ConfigParser()
@ -36,21 +36,29 @@ class ClientState(object):
if (not parser.has_section(status_section)):
parser.add_section(status_section)
if (timestamp is None):
parser.remove_option(status_section, self.config_site_to_name(site))
parser.remove_option(
status_section,
self.config_site_to_name(site))
else:
parser.set(status_section, self.config_site_to_name(site), str(timestamp))
parser.set(
status_section,
self.config_site_to_name(site),
str(timestamp))
with open(self.status_file, 'w') as configfile:
parser.write(configfile)
configfile.close()
def get_state(self,site):
def get_state(self, site):
"""Read client status file and return dict."""
parser = ConfigParser()
status_section = 'incremental'
parser.read(self.status_file)
timestamp = None
try:
timestamp = float(parser.get(status_section,self.config_site_to_name(site)))
timestamp = float(
parser.get(
status_section,
self.config_site_to_name(site)))
except NoSectionError as e:
pass
except NoOptionError as e:
@ -64,4 +72,4 @@ class ClientState(object):
lead to multiple site names mapping to one config name but
probably not too likely.
"""
return( re.sub(r"[^\w]",'_',name) )
return(re.sub(r"[^\w]", '_', name))

73
resync/client_utils.py
View File

@ -18,20 +18,22 @@ Copyright 2012-2016 Simeon Warner
limitations under the License
"""
try: #python3
try: # python3
from urllib.request import urlopen
except ImportError: #python2
except ImportError: # python2
from urllib import urlopen
import logging
import logging.config
from datetime import datetime
import re
class ClientFatalError(Exception):
"""Non-recoverable error in client, should include message to user."""
pass
class UTCFormatter(logging.Formatter):
"""Format datetime values as ISO8601 UTC Z form.
@ -43,8 +45,9 @@ class UTCFormatter(logging.Formatter):
timestamp = record.created
return datetime.utcfromtimestamp(timestamp).isoformat() + 'Z'
def init_logging(to_file=False, logfile=None, default_logfile='/tmp/resync.log',
human=True, verbose=False, eval_mode=False,
human=True, verbose=False, eval_mode=False,
default_logger='client', extra_loggers=None):
"""Initialize logging.
@ -53,116 +56,126 @@ def init_logging(to_file=False, logfile=None, default_logfile='/tmp/resync.log',
INFO - verbose, only seen by users if they ask for it (-v)
WARNING - messages output messages to console
Logging to a file: If to_file is True then output will be written to
Logging to a file: If to_file is True then output will be written to
a file. This will be logfile if set, else default_logfile (which may
also be overridden).
"""
fmt = '%(asctime)s | %(name)s | %(levelname)s | %(message)s'
formatter = UTCFormatter(fmt)
if human:
# Create a special handler designed just for human readable output
hh = logging.StreamHandler()
hh.setLevel( logging.INFO if (verbose) else logging.WARNING )
hh.setLevel(logging.INFO if (verbose) else logging.WARNING)
hh.setFormatter(logging.Formatter(fmt='%(message)s'))
if to_file:
if (logfile is None):
logfile = default_logfile
fh = logging.FileHandler(filename=logfile, mode='a')
fh.setFormatter(formatter)
fh.setLevel( logging.DEBUG if (eval_mode) else logging.INFO )
fh.setLevel(logging.DEBUG if (eval_mode) else logging.INFO)
loggers = [default_logger,'resync']
loggers = [default_logger, 'resync']
if (extra_loggers is not None):
for logger in extra_loggers:
loggers.append(logger)
for logger in loggers:
log = logging.getLogger(logger)
log.setLevel(logging.DEBUG) #control at handler instead
log.setLevel(logging.DEBUG) # control at handler instead
if human:
log.addHandler(hh)
if to_file:
log.addHandler(fh)
log=logging.getLogger(default_logger)
log = logging.getLogger(default_logger)
if (to_file):
log.info("Writing detailed log to %s" % (logfile))
def count_true_args(*args):
"""Count number of list of arguments that evaluate True."""
count=0
count = 0
for arg in args:
if (arg):
count+=1
count += 1
return(count)
def parse_links(args_link):
"""Parse --link options.
Uses parse_link() to parse each option.
"""
links=[]
links = []
if (args_link is not None):
for link_str in args_link:
try:
links.append(parse_link(link_str))
except ClientFatalError as e:
raise ClientFatalError("Bad --link option '%s' (%s)" % (link_str,str(e)))
raise ClientFatalError(
"Bad --link option '%s' (%s)" %
(link_str, str(e)))
return(links)
def parse_link(link_str):
"""Parse one --link option to add to <rs:ln> links.
Input string of the form: rel,href,att1=val1,att2=val2
"""
atts={}
help_str = "--link option '%s' (format rel,href,att1=val1...)"%(link_str)
atts = {}
help_str = "--link option '%s' (format rel,href,att1=val1...)" % (link_str)
try:
segs = link_str.split(',')
# First segments are relation and subject
atts['rel'] = segs.pop(0)
atts['href'] = segs.pop(0)
if (atts['href']==''):
if (atts['href'] == ''):
raise ClientFatalError("Missing uri in " + help_str)
# Remaining segments are attributes
for term in segs:
(k,v)=term.split('=')
if (k=='' or v==''):
raise ClientFatalError("Bad attribute (%s) in " % (term) + help_str)
atts[k]=v
(k, v) = term.split('=')
if (k == '' or v == ''):
raise ClientFatalError(
"Bad attribute (%s) in " %
(term) + help_str)
atts[k] = v
except ValueError as e:
raise ClientFatalError("Bad component of " + help_str)
except IndexError as e:
raise ClientFatalError("Incomplete component of " + help_str)
return(atts)
def parse_capabilities(caps_str):
"""Parse list of capabilities in --capabilitylist option.
Input string of the form: cap_name=uri,cap_name=uri
"""
capabilities={}
capabilities = {}
try:
segs = caps_str.split(',')
for term in segs:
(k,v)=term.split('=')
capabilities[k]=v
(k, v) = term.split('=')
capabilities[k] = v
except ValueError as e:
raise ClientFatalError("Bad component of --capabilitylist option '%s' (%s)"%(caps_str,str(e)))
raise ClientFatalError(
"Bad component of --capabilitylist option '%s' (%s)" %
(caps_str, str(e)))
return(capabilities)
def parse_capability_lists(cls_str):
"""Parse list of capability lists in --capabilitylistindex option.
Input string of the form: uri,uri
"""
return(cls_str.split(','))
def url_or_file_open(uri):
"""Wrapper around urlopen() to prepend file: if no scheme provided."""
if (not re.match(r'''\w+:''',uri)):
uri = 'file:'+uri
if (not re.match(r'''\w+:''', uri)):
uri = 'file:' + uri
return(urlopen(uri))

114
resync/dump.py
View File

@ -5,6 +5,7 @@ import os.path
from zipfile import ZipFile, ZIP_STORED, ZIP_DEFLATED
from resync.resource_dump_manifest import ResourceDumpManifest
class Dump(object):
"""Dump of content for a Resource Dump or Change Dump.
@ -25,31 +26,33 @@ class Dump(object):
self.resources = resources
self.format = ('zip' if (format is None) else format)
self.compress = compress
self.manifest_class = ResourceDumpManifest #FIXME
self.max_size = 100*1024*1024 #100MB
self.manifest_class = ResourceDumpManifest # FIXME
self.max_size = 100 * 1024 * 1024 # 100MB
self.max_files = 50000
self.path_prefix = None
self.logger = logging.getLogger('resync.dump')
def write(self, basename=None, write_separate_manifests=True):
"""Write one or more dump files to complete this dump.
Returns the number of dump/archive files written.
"""
self.check_files()
n=0
n = 0
for manifest in self.partition_dumps():
dumpbase="%s%05d" % (basename,n)
dumpfile="%s.%s" % (dumpbase,self.format)
dumpbase = "%s%05d" % (basename, n)
dumpfile = "%s.%s" % (dumpbase, self.format)
if (write_separate_manifests):
manifest.write(basename=dumpbase+'.xml')
manifest.write(basename=dumpbase + '.xml')
if (self.format == 'zip'):
self.write_zip(manifest.resources,dumpfile)
self.write_zip(manifest.resources, dumpfile)
elif (self.format == 'warc'):
self.write_warc(manifest.resources,dumpfile)
self.write_warc(manifest.resources, dumpfile)
else:
raise DumpError("Unknown dump format requested (%s)" % (self.format))
n+=1
raise DumpError(
"Unknown dump format requested (%s)" %
(self.format))
n += 1
self.logger.info("Wrote %d dump files" % (n))
return(n)
@ -60,8 +63,12 @@ class Dump(object):
a manifest file manifest.xml (written first). No checks on the size of files
or total size are performed, this is expected to have been done beforehand.
"""
compression = ( ZIP_DEFLATED if self.compress else ZIP_STORED )
zf = ZipFile(dumpfile, mode="w", compression=compression, allowZip64=True)
compression = (ZIP_DEFLATED if self.compress else ZIP_STORED)
zf = ZipFile(
dumpfile,
mode="w",
compression=compression,
allowZip64=True)
# Write resources first
rdm = ResourceDumpManifest(resources=resources)
real_path = {}
@ -69,24 +76,26 @@ class Dump(object):
archive_path = self.archive_path(resource.path)
real_path[archive_path] = resource.path
resource.path = archive_path
zf.writestr('manifest.xml',rdm.as_xml())
zf.writestr('manifest.xml', rdm.as_xml())
# Add all files in the resources
for resource in resources:
zf.write(real_path[resource.path], arcname=resource.path)
zf.close()
zipsize = os.path.getsize(dumpfile)
self.logger.info("Wrote ZIP file dump %s with size %d bytes" % (dumpfile,zipsize))
self.logger.info(
"Wrote ZIP file dump %s with size %d bytes" %
(dumpfile, zipsize))
def write_warc(self, resources=None, dumpfile=None):
"""Write a WARC dump file.
WARC support is not part of ResourceSync v1.0 (Z39.99 2014) but is left
in this library for experimentation.
"""
# Load library late as we want to be able to run rest of code
# Load library late as we want to be able to run rest of code
# without this installed
try:
from warc import WARCFile,WARCHeader,WARCRecord
from warc import WARCFile, WARCHeader, WARCRecord
except:
raise DumpError("Failed to load WARC library")
wf = WARCFile(dumpfile, mode="w", compress=self.compress)
@ -100,46 +109,56 @@ class Dump(object):
wh.result_code = 200
wh.checksum = 'aabbcc'
wh.location = self.archive_path(resource.path)
wf.write_record( WARCRecord( header=wh, payload=resource.path ) )
wf.write_record(WARCRecord(header=wh, payload=resource.path))
wf.close()
warcsize = os.path.getsize(dumpfile)
self.logging.info("Wrote WARC file dump %s with size %d bytes" % (dumpfile,warcsize))
def check_files(self,set_length=True,check_length=True):
self.logging.info(
"Wrote WARC file dump %s with size %d bytes" %
(dumpfile, warcsize))
def check_files(self, set_length=True, check_length=True):
"""Check all files in self.resources, find longest common prefix.
Go though and check all files in self.resources, add up size, and find
longest common path that can be used when writing the dump file. Saved in
longest common path that can be used when writing the dump file. Saved in
self.path_prefix.
Parameters set_length and check_length control control whether then set_length
attribute should be set from the file size if not specified, and whether any
attribute should be set from the file size if not specified, and whether any
length specified should be checked. By default both are True. In any event, the
total size calculated is the size of files on disk.
"""
total_size = 0 #total size of all files in bytes
total_size = 0 # total size of all files in bytes
path_prefix = None
for resource in self.resources:
if (resource.path is None):
#explicit test because exception raised by getsize otherwise confusing
raise DumpError("No file path defined for resource %s" % resource.uri)
# explicit test because exception raised by getsize otherwise
# confusing
raise DumpError(
"No file path defined for resource %s" %
resource.uri)
if (path_prefix is None):
path_prefix = os.path.dirname(resource.path)
else:
path_prefix = os.path.commonprefix( [ path_prefix, os.path.dirname(resource.path) ])
path_prefix = os.path.commonprefix(
[path_prefix, os.path.dirname(resource.path)])
size = os.path.getsize(resource.path)
if (resource.length is not None):
if (check_length and resource.length!=size):
if (check_length and resource.length != size):
raise DumpError("Size of resource %s is %d on disk, not %d as specified" %
(resource.uri, size, resource.length) )
(resource.uri, size, resource.length))
elif (set_length):
resource.length = size
if (size > self.max_size):
raise DumpError("Size of file (%s, %d) exceeds maximum (%d) dump size" % (resource.path,size,self.max_size))
raise DumpError(
"Size of file (%s, %d) exceeds maximum (%d) dump size" %
(resource.path, size, self.max_size))
total_size += size
self.path_prefix = path_prefix
self.total_size = total_size
self.logger.info("Total size of files to include in dump %d bytes" % (total_size))
self.logger.info(
"Total size of files to include in dump %d bytes" %
(total_size))
return True
def partition_dumps(self):
@ -147,27 +166,26 @@ class Dump(object):
Simply adds resources/files to a manifest until their are either the
the correct number of files or the size limit is exceeded, then yields
that manifest.
that manifest.
"""
manifest=self.manifest_class()
manifest_size=0
manifest_files=0
manifest = self.manifest_class()
manifest_size = 0
manifest_files = 0
for resource in self.resources:
manifest.add(resource)
manifest_size+=resource.length
manifest_files+=1
if (manifest_size>=self.max_size or
manifest_files>=self.max_files):
manifest_size += resource.length
manifest_files += 1
if (manifest_size >= self.max_size or
manifest_files >= self.max_files):
yield(manifest)
# Need to start a new manifest
manifest=self.manifest_class()
manifest_size=0
manifest_files=0
if (manifest_files>0):
manifest = self.manifest_class()
manifest_size = 0
manifest_files = 0
if (manifest_files > 0):
yield(manifest)
def archive_path(self,real_path):
def archive_path(self, real_path):
"""Return the archive path for file with real_path.
Mapping is based on removal of self.path_prefix which is determined
@ -176,10 +194,10 @@ class Dump(object):
if (not self.path_prefix):
return(real_path)
else:
return( os.path.relpath(real_path,self.path_prefix) )
return(os.path.relpath(real_path, self.path_prefix))
class DumpError(Exception):
"""Error class used by Dump() objects."""
pass

257
resync/explorer.py
View File

@ -1,19 +1,19 @@
"""ResourceSync explorer.
This is the guts of a client designed to 'explore' the ResourceSync
facilities offered by a source. Will use standard practices to
facilities offered by a source. Will use standard practices to
look for and interpret capabilities.
"""
import sys
try: #python3
try: # python3
from urllib.parse import urlparse, urlunparse, urljoin
except ImportError: #python2
except ImportError: # python2
from urlparse import urlparse, urlunparse, urljoin
input = raw_input
import os.path
import datetime
import distutils.dir_util
import distutils.dir_util
import re
import time
import logging
@ -21,23 +21,24 @@ import requests
from .mapper import Mapper
from .sitemap import Sitemap
from .client import Client,ClientFatalError
from .client import Client, ClientFatalError
from .client_state import ClientState
from .client_utils import ClientFatalError, url_or_file_open
from .resource import Resource
from .w3c_datetime import str_to_datetime,datetime_to_str
from .w3c_datetime import str_to_datetime, datetime_to_str
class Explorer(Client):
"""Extension of the client code to explore a ResourceSync source.
Designed to support a text-based command-line client that starts from
a given URI, server, or local file, and then allows interactive
a given URI, server, or local file, and then allows interactive
exploration of ResourceSync capabilities offered by the source.
"""
def explore(self):
"""INTERACTIVE exploration source capabilities.
Will use sitemap URI taken either from explicit self.sitemap_name
or derived from the mappings supplied.
"""
@ -47,57 +48,67 @@ class Explorer(Client):
starts = []
if (self.sitemap_name is not None):
print("Starting from explicit --sitemap %s" % (self.sitemap_name))
starts.append( XResource(self.sitemap_name) )
elif (len(self.mapper)>0):
starts.append(XResource(self.sitemap_name))
elif (len(self.mapper) > 0):
uri = self.mapper.default_src_uri()
(scheme, netloc, path, params, query, fragment) = urlparse(uri)
if (not scheme and not netloc):
if (os.path.isdir(path)):
# have a dir, look for 'likely' file names
print("Looking for capability documents in local directory %s" % (path))
for name in ['resourcesync','capabilities.xml',
'resourcelist.xml','changelist.xml']:
file = os.path.join(path,name)
print(
"Looking for capability documents in local directory %s" %
(path))
for name in ['resourcesync', 'capabilities.xml',
'resourcelist.xml', 'changelist.xml']:
file = os.path.join(path, name)
if (os.path.isfile(file)):
starts.append( XResource(file) )
if (len(starts)==0):
raise ClientFatalError( "No likely capability files found in local directory %s" %
(path) )
starts.append(XResource(file))
if (len(starts) == 0):
raise ClientFatalError("No likely capability files found in local directory %s" %
(path))
else:
# local file, might be anything (or not exist)
print("Starting from local file %s" % (path))
starts.append( XResource(path) )
starts.append(XResource(path))
else:
# remote, can't tell whether we have a sitemap or a server name or something
# remote, can't tell whether we have a sitemap or a server name or something
# else, build list of options depending on whether there is a path and whether
# there is an extension/name
well_known = urlunparse( [ scheme,netloc,'/.well-known/resourcesync','','','' ] )
well_known = urlunparse(
[scheme, netloc, '/.well-known/resourcesync', '', '', ''])
if (not path):
# root, just look for .well-known
starts.append( XResource(well_known, ['capabilitylist','capabilitylistindex']) )
starts.append(
XResource(
well_known, [
'capabilitylist', 'capabilitylistindex']))
else:
starts.append( XResource(uri) )
starts.append( XResource(well_known, ['capabilitylist','capabilitylistindex']) )
starts.append(XResource(uri))
starts.append(
XResource(
well_known, [
'capabilitylist', 'capabilitylistindex']))
print("Looking for discovery information based on mappings")
else:
raise ClientFatalError("No source information (server base uri or capability uri) specified, use -h for help")
#
raise ClientFatalError(
"No source information (server base uri or capability uri) specified, use -h for help")
#
# Have list of one or more possible starting point, try them in turn
try:
for start in starts:
# For each starting point we create a fresh history
history = [ start ]
history = [start]
input = None
while (len(history)>0):
while (len(history) > 0):
print()
xr = history.pop()
new_xr = self.explore_uri(xr,len(history)>0)
new_xr = self.explore_uri(xr, len(history) > 0)
if (new_xr):
# Add current and new to history
history.append( xr )
history.append( new_xr )
history.append(xr)
history.append(new_xr)
except ExplorerQuit:
pass # expected way to exit
pass # expected way to exit
print("\nresync-explorer done, bye...\n")
def explore_uri(self, explorer_resource, show_back=True):
@ -109,31 +120,32 @@ class Explorer(Client):
caps = explorer_resource.acceptable_capabilities
checks = explorer_resource.checks
print("Reading %s" % (uri))
options={}
capability=None
options = {}
capability = None
try:
if (caps=='resource'):
if (caps == 'resource'):
# Not expecting a capability document
self.explore_show_head(uri,check_headers=checks)
else:
s=Sitemap()
self.explore_show_head(uri, check_headers=checks)
else:
s = Sitemap()
list = s.parse_xml(url_or_file_open(uri))
(options,capability)=self.explore_show_summary(list,s.parsed_index,caps,context=uri)
(options, capability) = self.explore_show_summary(
list, s.parsed_index, caps, context=uri)
except IOError as e:
print("Cannot read %s (%s)" % (uri,str(e)))
print("Cannot read %s (%s)" % (uri, str(e)))
except Exception as e:
print("Cannot parse %s (%s)" % (uri,str(e)))
print("Cannot parse %s (%s)" % (uri, str(e)))
#
# Loop until we have some valid input
#
while (True):
# don't offer number option for no resources/capabilities
num_prompt = '' if (len(options)==0) else 'number, '
num_prompt = '' if (len(options) == 0) else 'number, '
up_prompt = 'b(ack), ' if (show_back) else ''
if (self.fake_input):
inp = self.fake_input
else:
inp = input( "Follow [%s%sq(uit)]?" % (num_prompt,up_prompt) )
inp = input("Follow [%s%sq(uit)]?" % (num_prompt, up_prompt))
if (inp in options.keys()):
break
if (inp == 'q'):
@ -145,9 +157,9 @@ class Explorer(Client):
#
checks = {}
r = options[inp]
if ( r.capability is None ):
if (capability in ['resourcelist','changelist',
'resourcedump','changedump']):
if (r.capability is None):
if (capability in ['resourcelist', 'changelist',
'resourcedump', 'changedump']):
caps = 'resource'
else:
caps = self.allowed_entries(capability)
@ -157,21 +169,22 @@ class Explorer(Client):
caps = [r.capability]
# Record anything we know about the resource to check
if (r.length is not None):
checks['content-length']=r.length
checks['content-length'] = r.length
if (r.lastmod is not None):
checks['last-modified']=r.lastmod
checks['last-modified'] = r.lastmod
if (r.mime_type is not None):
checks['content-type']=r.mime_type
checks['content-type'] = r.mime_type
# FIXME - could add fixity checks here too
return( XResource(r.uri, caps, checks) )
return(XResource(r.uri, caps, checks))
def explore_show_summary(self, list, index=False, expected=None, context=None):
def explore_show_summary(self, list, index=False,
expected=None, context=None):
"""Show summary of one capability document.
Given a capability document or index (in list, index True if it is an
index), write out a simply textual summary of the document with all
related documents shown as numbered options (of the form
[#] ...description...) which will then form a menu for the next
Given a capability document or index (in list, index True if it is an
index), write out a simply textual summary of the document with all
related documents shown as numbered options (of the form
[#] ...description...) which will then form a menu for the next
exploration.
If expected is not None then it should be a list of expected document
@ -186,75 +199,79 @@ class Explorer(Client):
capability = list.md['capability']
if (index):
capability += 'index'
print("Parsed %s document with %d entries:" % (capability,num_entries))
print(
"Parsed %s document with %d entries:" %
(capability, num_entries))
if (expected is not None and capability not in expected):
print("WARNING - expected a %s document" % (','.join(expected)))
if (capability not in ['description','descriptionoindex','capabilitylist',
'resourcelist','resourcelistindex','changelist','changelistindex',
'resourcedump','resourcedumpindex','changedump','changedumpindex',
if (capability not in ['description', 'descriptionoindex', 'capabilitylist',
'resourcelist', 'resourcelistindex', 'changelist', 'changelistindex',
'resourcedump', 'resourcedumpindex', 'changedump', 'changedumpindex',
'resourcelist-archive', 'resourcedump-archive',
'changelist-archive', 'changedump-archive']):
print("WARNING - unknown %s document type" % (capability))
to_show = num_entries
if (num_entries>21):
if (num_entries > 21):
to_show = 20
# What capability entries are allowed/expected?
entry_caps = self.allowed_entries(capability);
# What capability entries are allowed/expected?
entry_caps = self.allowed_entries(capability)
options = {}
n=0
n = 0
# Look for <rs:ln> elements in this document
ln_describedby = list.link('describedby')
if (ln_describedby):
if ('href' in ln_describedby):
uri = ln_describedby['href']
print("[%s] rel='describedby' link to %s" % ('d',uri))
uri = self.expand_relative_uri(context,uri)
options['d']=Resource(uri,capability='resource')
print("[%s] rel='describedby' link to %s" % ('d', uri))
uri = self.expand_relative_uri(context, uri)
options['d'] = Resource(uri, capability='resource')
else:
print("WARNING - describedby link with no href, ignoring")
ln_up = list.link('up')
if (ln_up):
if ('href' in ln_up):
uri = ln_up['href']
print("[%s] rel='up' link to %s" % ('u',uri))
uri = self.expand_relative_uri(context,uri)
options['u']=Resource(uri)
print("[%s] rel='up' link to %s" % ('u', uri))
uri = self.expand_relative_uri(context, uri)
options['u'] = Resource(uri)
else:
print("WARNING - up link with no href, ignoring")
ln_index = list.link('index')
if (ln_index):
if ('href' in ln_index):
uri = ln_index['href']
print("[%s] rel='index' link to %s" % ('i',uri))
uri = self.expand_relative_uri(context,uri)
options['i']=Resource(uri)
print("[%s] rel='index' link to %s" % ('i', uri))
uri = self.expand_relative_uri(context, uri)
options['i'] = Resource(uri)
else:
print("WARNING - index link with no href, ignoring")
# Show listed resources as numbered options
for r in list.resources:
if (n>=to_show):
print("(not showing remaining %d entries)" % (num_entries-n))
if (n >= to_show):
print("(not showing remaining %d entries)" % (num_entries - n))
break
n+=1
options[str(n)]=r
print("[%d] %s" % (n,r.uri))
n += 1
options[str(n)] = r
print("[%d] %s" % (n, r.uri))
if (self.verbose):
print(" " + str(r))
r.uri = self.expand_relative_uri(context,r.uri)
r.uri = self.expand_relative_uri(context, r.uri)
if (r.capability is not None):
warning = ''
if (r.capability not in entry_caps):
warning = " (EXPECTED %s)" % (' or '.join(entry_caps))
print(" %s%s" % (r.capability,warning))
elif (len(entry_caps)==1):
r.capability=entry_caps[0]
print(" capability not specified, should be %s" % (r.capability))
return(options,capability)
print(" %s%s" % (r.capability, warning))
elif (len(entry_caps) == 1):
r.capability = entry_caps[0]
print(
" capability not specified, should be %s" %
(r.capability))
return(options, capability)
def explore_show_head(self,uri,check_headers=None):
def explore_show_head(self, uri, check_headers=None):
"""Do HEAD on uri and show infomation.
Will also check headers against any values specified in
Will also check headers against any values specified in
check_headers.
"""
print("HEAD %s" % (uri))
@ -265,44 +282,49 @@ class Explorer(Client):
# Mock up response if we have a local file
response = self.head_on_file(uri)
print(" status: %s" % (response.status_code))
if (response.status_code=='200'):
if (response.status_code == '200'):
# print some of the headers
for header in ['content-length','last-modified','lastmod','content-type','etag']:
for header in ['content-length', 'last-modified',
'lastmod', 'content-type', 'etag']:
if header in response.headers:
check_str=''
check_str = ''
if (check_headers is not None and
header in check_headers):
header in check_headers):
if (response.headers[header] == check_headers[header]):
check_str=' MATCHES EXPECTED VALUE'
check_str = ' MATCHES EXPECTED VALUE'
else:
check_str=' EXPECTED %s' % (check_headers[header])
print(" %s: %s%s" % (header, response.headers[header], check_str))
check_str = ' EXPECTED %s' % (
check_headers[header])
print(
" %s: %s%s" %
(header, response.headers[header], check_str))
def head_on_file(self,file):
def head_on_file(self, file):
"""Mock up requests.head(..) response on local file."""
response = HeadResponse()
if (not os.path.isfile(file)):
response.status_code='404'
response.status_code = '404'
else:
response.status_code='200'
response.headers['last-modified']=datetime_to_str(os.path.getmtime(file))
response.headers['content-length']=os.path.getsize(file)
response.status_code = '200'
response.headers[
'last-modified'] = datetime_to_str(os.path.getmtime(file))
response.headers['content-length'] = os.path.getsize(file)
return(response)
def allowed_entries(self,capability):
def allowed_entries(self, capability):
"""Return list of allowed entries for given capability document.
Includes handling of capability = *index where the only acceptable
Includes handling of capability = *index where the only acceptable
entries are *.
"""
index = re.match(r'(.+)index$',capability)
archive = re.match(r'(.+)\-archive$',capability)
index = re.match(r'(.+)index$', capability)
archive = re.match(r'(.+)\-archive$', capability)
if (capability == 'capabilitylistindex'):
return([]) #not allowed so no valid references
return([]) # not allowed so no valid references
elif (index):
return([index.group(1)]) #name without index ending
return([index.group(1)]) # name without index ending
elif (archive):
return([archive.group(1)]) #name without -archive ending
return([archive.group(1)]) # name without -archive ending
elif (capability == 'description'):
return(['capabilitylist'])
elif (capability == 'capabilitylist'):
@ -312,12 +334,12 @@ class Explorer(Client):
'changelist-archive', 'changedump-archive'])
return([])
def expand_relative_uri(self,context,uri):
def expand_relative_uri(self, context, uri):
"""If uri is relative then expand in context.
Prints warning if expansion happens.
"""
full_uri = urljoin(context,uri)
full_uri = urljoin(context, uri)
if (full_uri != uri):
print(" WARNING - expanded relative URI to %s" % (full_uri))
uri = full_uri
@ -328,20 +350,21 @@ class XResource(object):
"""Information about a resource for the explorer.
Must have a uri but may also store:
acceptable_capabilities - None for any acceptable, 'resource' if a
resource rather than a capability document is expected, else
acceptable_capabilities - None for any acceptable, 'resource' if a
resource rather than a capability document is expected, else
a list of capability names
checks - a set of information to check when then XResource is inspected
base_uri - on creation interpret any relative URI specified in the
base_uri - on creation interpret any relative URI specified in the
context of base_uri, store the resulting full URI
"""
def __init__(self, uri, acceptable_capabilities=None, checks=None, context=None):
def __init__(self, uri, acceptable_capabilities=None,
checks=None, context=None):
"""Initialize XResource object."""
self.uri=urljoin(context,uri)
self.acceptable_capabilities=acceptable_capabilities
self.checks=checks
self.uri = urljoin(context, uri)
self.acceptable_capabilities = acceptable_capabilities
self.checks = checks
class HeadResponse(object):
@ -349,8 +372,8 @@ class HeadResponse(object):
def __init__(self):
"""Initialize with no status_code and no headers."""
self.status_code=None
self.headers={}
self.status_code = None
self.headers = {}
class ExplorerQuit(Exception):

54
resync/list_base.py
View File

@ -10,38 +10,39 @@ import os
from datetime import datetime
import re
import sys
try: #python2
try: # python2
# Must try this first as io also exists in python2
# but in the wrong one!
import StringIO as io
except ImportError: #python3
except ImportError: # python3
import io
import logging
try: #python3
try: # python3
from urllib.request import URLopener
except ImportError: #python2
except ImportError: # python2
from urllib import URLopener
from .resource_container import ResourceContainer
from .sitemap import Sitemap
class ListBase(ResourceContainer):
"""Class that adds Sitemap based IO to ResourceContainer.
resources - an iterable of resources
count - add optional explicit setting of the number of items in
count - add optional explicit setting of the number of items in
resources which is useful when this is an iterator/generator.
Is used instead of trying len(resources)
md - metadata information for the list (<rs:md>)
ln - link information for the list (<rs:ln>)
sitemapindex - defaults to False, set True if this is an index object
"""
def __init__(self, resources=None, count=None, md=None, ln=None, uri=None,
def __init__(self, resources=None, count=None, md=None, ln=None, uri=None,
capability_name='unknown'):
"""Initialize ListBase."""
super(ListBase, self).__init__(resources=resources, md=md, ln=ln, uri=uri,
@ -73,9 +74,9 @@ class ListBase(ResourceContainer):
return(self.count)
return(len(self.resources))
##### INPUT #####
# INPUT
def read(self,uri=None):
def read(self, uri=None):
"""Default case is just to parse document at this URI.
Intention is that the read() method may be overridden to support reading
@ -83,10 +84,10 @@ class ListBase(ResourceContainer):
"""
self.parse(uri=uri)
def parse(self,uri=None,fh=None,str_data=None,**kwargs):
def parse(self, uri=None, fh=None, str_data=None, **kwargs):
"""Parse a single XML document for this list.
Accepts either a uri (uri or default if parameter not specified),
Accepts either a uri (uri or default if parameter not specified),
or a filehandle (fh) or a string (str_data). Note that this method
does not handle the case of a sitemapindex+sitemaps.
@ -97,45 +98,52 @@ class ListBase(ResourceContainer):
try:
fh = URLopener().open(uri)
except IOError as e:
raise Exception("Failed to load sitemap/sitemapindex from %s (%s)" % (uri,str(e)))
raise Exception(
"Failed to load sitemap/sitemapindex from %s (%s)" %
(uri, str(e)))
elif (str_data is not None):
fh=io.StringIO(str_data)
fh = io.StringIO(str_data)
elif ('str' in kwargs):
# Legacy support for str argument, see
# https://github.com/resync/resync/pull/21
# One test for this in tests/test_list_base.py
self.logger.warn("Legacy parse(str=...), use parse(str_data=...) instead")
self.logger.warn(
"Legacy parse(str=...), use parse(str_data=...) instead")
fh = io.StringIO(kwargs['str'])
if (fh is None):
raise Exception("Nothing to parse")
s = self.new_sitemap()
s.parse_xml(fh=fh,resources=self,capability=self.capability_name,sitemapindex=False)
s.parse_xml(
fh=fh,
resources=self,
capability=self.capability_name,
sitemapindex=False)
self.parsed_index = s.parsed_index
##### OUTPUT #####
# OUTPUT
def as_xml(self):
"""Return XML serialization of this list.
This code does not support the case where the list is too big for
This code does not support the case where the list is too big for
a single XML document.
"""
self.default_capability()
s = self.new_sitemap()
return s.resources_as_xml(self,sitemapindex=self.sitemapindex)
return s.resources_as_xml(self, sitemapindex=self.sitemapindex)
def write(self,basename="/tmp/resynclist.xml"):
def write(self, basename="/tmp/resynclist.xml"):
"""Write a single sitemap or sitemapindex XML document.
Must be overridden to support multi-file lists.
"""
self.default_capability()
fh = open(basename,'w')
fh = open(basename, 'w')
s = self.new_sitemap()
s.resources_as_xml(self,fh=fh,sitemapindex=self.sitemapindex)
s.resources_as_xml(self, fh=fh, sitemapindex=self.sitemapindex)
fh.close()
##### UTILITY #####
# UTILITY
def new_sitemap(self):
"""Create new Sitemap object with default settings."""

206
resync/list_base_with_index.py
View File

@ -5,15 +5,15 @@ sitemapindexes. Extends ListBase to add the support for sitemapindexes.
"""
import collections
import math
import math
import os
from datetime import datetime
import re
import sys
import itertools
try: #python3
try: # python3
from urllib.request import URLopener
except ImportError: #python2
except ImportError: # python2
from urllib import URLopener
from .list_base import ListBase
@ -23,6 +23,7 @@ from .mapper import Mapper, MapperError
from .url_authority import UrlAuthority
from .utils import compute_md5_for_file
class ListBaseWithIndex(ListBase):
"""Class that add handling of sitemapindexes to ListBase.
@ -49,25 +50,27 @@ class ListBaseWithIndex(ListBase):
to those that the component sitemap files will be exposed as
"""
def __init__(self, resources=None, count=None, md=None, ln=None, uri=None,
def __init__(self, resources=None, count=None, md=None, ln=None, uri=None,
capability_name='unknown', allow_multifile=None, mapper=None,
resources_class=None):
"""Initialize ListBaseWithIndex."""
self.resources_class = list if resources_class is None else resources_class
if (resources is None):
resources = self.resources_class()
super(ListBaseWithIndex, self).__init__(resources=resources, count=count, md=md, ln=ln,
super(ListBaseWithIndex, self).__init__(resources=resources, count=count, md=md, ln=ln,
uri=uri, capability_name=capability_name)
# specific to lists with indexes
self.max_sitemap_entries=50000
self.max_sitemap_entries = 50000
self.mapper = mapper
self.allow_multifile = (True if (allow_multifile is None) else allow_multifile)
self.allow_multifile = (
True if (
allow_multifile is None) else allow_multifile)
self.check_url_authority = False
self.content_length = 0
self.num_files = 0 # Number of files read
self.bytes_read = 0 # Aggregate of content_length values
##### INPUT #####
# INPUT
def read(self, uri=None, resources=None, index_only=False):
"""Read sitemap from a URI including handling sitemapindexes.
@ -76,7 +79,7 @@ class ListBaseWithIndex(ListBase):
will not be read. This will result in no resources being returned and is
useful only to read the metadata and links listed in the sitemapindex.
Includes the subtlety that if the input URI is a local file and is a
Includes the subtlety that if the input URI is a local file and is a
sitemapindex which contains URIs for the individual sitemaps, then these
are mapped to the filesystem also.
"""
@ -84,63 +87,81 @@ class ListBaseWithIndex(ListBase):
fh = URLopener().open(uri)
self.num_files += 1
except IOError as e:
raise IOError("Failed to load sitemap/sitemapindex from %s (%s)" % (uri,str(e)))
raise IOError(
"Failed to load sitemap/sitemapindex from %s (%s)" %
(uri, str(e)))
# Get the Content-Length if we can (works fine for local files)
try:
self.content_length = int(fh.info()['Content-Length'])
self.bytes_read += self.content_length
self.logger.debug( "Read %d bytes from %s" % (self.content_length,uri) )
self.logger.debug(
"Read %d bytes from %s" %
(self.content_length, uri))
except KeyError:
# If we don't get a length then c'est la vie
self.logger.debug( "Read ????? bytes from %s" % (uri) )
self.logger.debug("Read ????? bytes from %s" % (uri))
pass
self.logger.info( "Read sitemap/sitemapindex from %s" % (uri) )
self.logger.info("Read sitemap/sitemapindex from %s" % (uri))
s = self.new_sitemap()
s.parse_xml(fh=fh,resources=self,capability=self.capability_name)
s.parse_xml(fh=fh, resources=self, capability=self.capability_name)
# what did we read? sitemap or sitemapindex?
if (s.parsed_index):
# sitemapindex
if (not self.allow_multifile):
raise ListBaseIndexError("Got sitemapindex from %s but support for sitemapindex disabled" % (uri))
self.logger.info( "Parsed as sitemapindex, %d sitemaps" % (len(self.resources)) )
raise ListBaseIndexError(
"Got sitemapindex from %s but support for sitemapindex disabled" %
(uri))
self.logger.info(
"Parsed as sitemapindex, %d sitemaps" %
(len(
self.resources)))
sitemapindex_is_file = self.is_file_uri(uri)
if (index_only):
# don't read the component sitemaps
self.sitemapindex = True
return
# now loop over all entries to read each sitemap and add to resources
# now loop over all entries to read each sitemap and add to
# resources
sitemaps = self.resources
self.resources = self.resources_class()
self.logger.info( "Now reading %d sitemaps" % len(sitemaps.uris()) )
self.logger.info("Now reading %d sitemaps" % len(sitemaps.uris()))
for sitemap_uri in sorted(sitemaps.uris()):
self.read_component_sitemap(uri,sitemap_uri,s,sitemapindex_is_file)
self.read_component_sitemap(
uri, sitemap_uri, s, sitemapindex_is_file)
else:
# sitemap
self.logger.info( "Parsed as sitemap, %d resources" % (len(self.resources)) )
self.logger.info("Parsed as sitemap, %d resources" %
(len(self.resources)))
def read_component_sitemap(self, sitemapindex_uri, sitemap_uri, sitemap, sitemapindex_is_file):
def read_component_sitemap(
self, sitemapindex_uri, sitemap_uri, sitemap, sitemapindex_is_file):
"""Read a component sitemap of a Resource List with index.
Each component must be a sitemap with the
Each component must be a sitemap with the
"""
if (sitemapindex_is_file):
if (not self.is_file_uri(sitemap_uri)):
# Attempt to map URI to local file
remote_uri = sitemap_uri
sitemap_uri = self.mapper.src_to_dst(remote_uri)
self.logger.info("Mapped %s to local file %s" % (remote_uri, sitemap_uri))
self.logger.info(
"Mapped %s to local file %s" %
(remote_uri, sitemap_uri))
else:
# The individual sitemaps should be at a URL (scheme/server/path)
# that the sitemapindex URL can speak authoritatively about
if (self.check_url_authority and
not UrlAuthority(sitemapindex_uri).has_authority_over(sitemap_uri)):
raise ListBaseIndexError("The sitemapindex (%s) refers to sitemap at a location it does not have authority over (%s)" % (sitemapindex_uri,sitemap_uri))
not UrlAuthority(sitemapindex_uri).has_authority_over(sitemap_uri)):
raise ListBaseIndexError(
"The sitemapindex (%s) refers to sitemap at a location it does not have authority over (%s)" %
(sitemapindex_uri, sitemap_uri))
try:
fh = URLopener().open(sitemap_uri)
self.num_files += 1
except IOError as e:
raise ListBaseIndexError("Failed to load sitemap from %s listed in sitemap index %s (%s)" % (sitemap_uri,sitemapindex_uri,str(e)))
raise ListBaseIndexError(
"Failed to load sitemap from %s listed in sitemap index %s (%s)" %
(sitemap_uri, sitemapindex_uri, str(e)))
# Get the Content-Length if we can (works fine for local files)
try:
self.content_length = int(fh.info()['Content-Length'])
@ -148,34 +169,36 @@ class ListBaseWithIndex(ListBase):
except KeyError:
# If we don't get a length then c'est la vie
pass
self.logger.info( "Reading sitemap from %s (%d bytes)" % (sitemap_uri,self.content_length) )
component = sitemap.parse_xml( fh=fh, sitemapindex=False )
self.logger.info(
"Reading sitemap from %s (%d bytes)" %
(sitemap_uri, self.content_length))
component = sitemap.parse_xml(fh=fh, sitemapindex=False)
# Copy resources into self, check any metadata
for r in component:
self.resources.add(r)
# FIXME - if rel="up" check it goes to correct place
# FIXME - check capability
##### OUTPUT #####
# OUTPUT
def requires_multifile(self):
"""Return False or the number of component sitemaps required.
In the case that no len() is available for self.resources then
then self.count must be set beforehand to avoid an exception.
"""
if (self.max_sitemap_entries is None or
len(self)<=self.max_sitemap_entries):
len(self) <= self.max_sitemap_entries):
return(False)
return( int( math.ceil( len(self) / float(self.max_sitemap_entries) ) ) )
return(int(math.ceil(len(self) / float(self.max_sitemap_entries))))
def as_xml(self, allow_multifile=False, basename="/tmp/sitemap.xml"):
"""Return XML serialization of this list.
If this list can be serialized as a single sitemap then the
If this list can be serialized as a single sitemap then the
superclass method is used.
If there is no single XML serialization (in the case that the
If there is no single XML serialization (in the case that the
number of list resources is more than is allowed in a single sitemap)
then raise an exception unless allow_multifile is set True.
If allow_multifile is set True then will return the sitemapindex
@ -186,55 +209,65 @@ class ListBaseWithIndex(ListBase):
elif (allow_multifile):
return self.as_xml_index(basename)
else:
raise ListBaseIndexError("Attempt to write single XML string for list with %d entries when max_sitemap_entries is set to %d" % (len(self),self.max_sitemap_entries))
raise ListBaseIndexError(
"Attempt to write single XML string for list with %d entries when max_sitemap_entries is set to %d" %
(len(self), self.max_sitemap_entries))
def as_xml_index(self, basename="/tmp/sitemap.xml"):
"""Return a string of the index for a large list that is split.
All we need to do is determine the number of component sitemaps will
be is and generate their URIs based on a pattern.
Q - should there be a flag to select generation of each component sitemap
in order to calculate the md5sum?
Q - what timestamp should be used?
"""
num_parts = self.requires_multifile()
if (not num_parts):
raise ListBaseIndexError("Request for sitemapindex for list with only %d entries when max_sitemap_entries is set to %s" % (len(self),str(self.max_sitemap_entries)))
index=ListBase()
index.sitemapindex=True
raise ListBaseIndexError(
"Request for sitemapindex for list with only %d entries when max_sitemap_entries is set to %s" %
(len(self), str(
self.max_sitemap_entries)))
index = ListBase()
index.sitemapindex = True
index.capability_name = self.capability_name
index.default_capability()
for n in range(num_parts):
r = Resource( uri = self.part_name(basename,n) )
r = Resource(uri=self.part_name(basename, n))
index.add(r)
return( index.as_xml() )
return(index.as_xml())
def as_xml_part(self, basename="/tmp/sitemap.xml", part_number=0):
"""Return a string of component sitemap number part_number.
Used in the case of a large list that is split into component
sitemaps.
basename is used to create "index" links to the sitemapindex
Q - what timestamp should be used?
"""
if (not self.requires_multifile()):
raise ListBaseIndexError("Request for component sitemap for list with only %d entries when max_sitemap_entries is set to %s" % (len(self),str(self.max_sitemap_entries)))
raise ListBaseIndexError(
"Request for component sitemap for list with only %d entries when max_sitemap_entries is set to %s" %
(len(self), str(
self.max_sitemap_entries)))
start = part_number * self.max_sitemap_entries
if (start>len(self)):
raise ListBaseIndexError("Request for component sitemap with part_number too high, would start at entry %d yet the list has only %d entries" % (start,len(self)))
if (start > len(self)):
raise ListBaseIndexError(
"Request for component sitemap with part_number too high, would start at entry %d yet the list has only %d entries" %
(start, len(self)))
stop = start + self.max_sitemap_entries
if (stop>len(self)):
stop=len(self)
part = ListBase( itertools.islice(self.resources,start,stop) )
if (stop > len(self)):
stop = len(self)
part = ListBase(itertools.islice(self.resources, start, stop))
part.capability_name = self.capability_name
part.default_capability()
part.index = basename
s = self.new_sitemap()
return( s.resources_as_xml(part) )
return(s.resources_as_xml(part))
def write(self, basename='/tmp/sitemap.xml'):
"""Write one or a set of sitemap files to disk.
@ -243,43 +276,47 @@ class ListBaseWithIndex(ListBase):
a ChangeList. This may be a generator so data is read as needed
and length is determined at the end.
basename is used as the name of the single sitemap file or the
basename is used as the name of the single sitemap file or the
sitemapindex for a set of sitemap files.
Uses self.max_sitemap_entries to determine whether the resource_list can
be written as one sitemap. If there are more entries and
self.allow_multifile is set True then a set of sitemap files,
Uses self.max_sitemap_entries to determine whether the resource_list can
be written as one sitemap. If there are more entries and
self.allow_multifile is set True then a set of sitemap files,
with an sitemapindex, will be written.
"""
# Access resources through iterator only
resources_iter = iter(self.resources)
( chunk, nxt ) = self.get_resources_chunk(resources_iter)
(chunk, nxt) = self.get_resources_chunk(resources_iter)
s = self.new_sitemap()
if (nxt is not None):
# Have more than self.max_sitemap_entries => sitemapindex
if (not self.allow_multifile):
raise ListBaseIndexError("Too many entries for a single sitemap but multifile disabled")
raise ListBaseIndexError(
"Too many entries for a single sitemap but multifile disabled")
# Work out URI of sitemapindex so that we can link up to
# it from the individual sitemap files
try:
index_uri = self.mapper.dst_to_src(basename)
except MapperError as e:
raise ListBaseIndexError("Cannot map sitemapindex filename to URI (%s)" % str(e))
raise ListBaseIndexError(
"Cannot map sitemapindex filename to URI (%s)" %
str(e))
# Use iterator over all resources and count off sets of
# max_sitemap_entries to go into each sitemap, store the
# names of the sitemaps as we go. Copy md from self into
# the index and use this for all chunks also
index=ListBase(md=self.md.copy(), ln=list(self.ln))
index = ListBase(md=self.md.copy(), ln=list(self.ln))
index.capability_name = self.capability_name
index.default_capability()
while (len(chunk)>0):
file = self.part_name(basename,len(index))
while (len(chunk) > 0):
file = self.part_name(basename, len(index))
# Check that we can map the filename of this sitemap into
# URI space for the sitemapindex
try:
uri = self.mapper.dst_to_src(file)
except MapperError as e:
raise ListBaseIndexError("Cannot map sitemap filename to URI (%s)" % str(e))
raise ListBaseIndexError(
"Cannot map sitemap filename to URI (%s)" % str(e))
self.logger.info("Writing sitemap %s..." % (file))
f = open(file, 'w')
chunk.index = index_uri
@ -287,16 +324,16 @@ class ListBaseWithIndex(ListBase):
s.resources_as_xml(chunk, fh=f)
f.close()
# Record information about this sitemap for index
r = Resource( uri = uri,
timestamp = os.stat(file).st_mtime,
md5 = compute_md5_for_file(file) )
r = Resource(uri=uri,
timestamp=os.stat(file).st_mtime,
md5=compute_md5_for_file(file))
index.add(r)
# Get next chunk
( chunk, nxt ) = self.get_resources_chunk(resources_iter,nxt)
(chunk, nxt) = self.get_resources_chunk(resources_iter, nxt)
self.logger.info("Wrote %d sitemaps" % (len(index)))
f = open(basename, 'w')
self.logger.info("Writing sitemapindex %s..." % (basename))
s.resources_as_xml(index,sitemapindex=True,fh=f)
s.resources_as_xml(index, sitemapindex=True, fh=f)
f.close()
self.logger.info("Wrote sitemapindex %s" % (basename))
else:
@ -310,62 +347,63 @@ class ListBaseWithIndex(ListBase):
"""XML serialization of this list taken to be sitemapindex entries."""
self.default_capability()
s = self.new_sitemap()
return s.resources_as_xml(self,sitemapindex=True)
return s.resources_as_xml(self, sitemapindex=True)
##### Utility #####
# Utility
def get_resources_chunk(self, resource_iter, first=None):
"""Return next chunk of resources from resource_iter, and next item.
If first parameter is specified then this will be prepended to
the list.
The chunk will contain self.max_sitemap_entries if the iterator
The chunk will contain self.max_sitemap_entries if the iterator
returns that many. next will have the value of the next value from
the iterator, providing indication of whether more is available.
the iterator, providing indication of whether more is available.
Use this as first when asking for the following chunk.
"""
chunk = ListBase( md=self.md.copy(), ln=list(self.ln) )
chunk = ListBase(md=self.md.copy(), ln=list(self.ln))
chunk.capability_name = self.capability_name
chunk.default_capability()
if (first is not None):
chunk.add(first)
for r in resource_iter:
chunk.add(r)
if (len(chunk)>=self.max_sitemap_entries):
if (len(chunk) >= self.max_sitemap_entries):
break
# Get next to see whether there are more resources
try:
nxt = next(resource_iter)
except StopIteration:
nxt = None
return(chunk,nxt)
return(chunk, nxt)
def part_name(self, basename='/tmp/sitemap.xml', part_number=0):
"""Name (file or URI) for one component sitemap.
Works for both filenames and URIs because manipulates only the end
of the string.
Abstracting this into a function that starts from the basename to get
prefix and suffix each time seems a bit wasteful but perhaps not worth
worrying about. Allows same code to be used for the write() and
worrying about. Allows same code to be used for the write() and
as_xml_index() cases.
"""
# Work out how to name the sitemaps, attempt to add %05d before ".xml$", else append
# Work out how to name the sitemaps, attempt to add %05d before
# ".xml$", else append
sitemap_prefix = basename
sitemap_suffix = '.xml'
if (basename[-4:] == '.xml'):
sitemap_prefix = basename[:-4]
return( sitemap_prefix + ( "%05d" % (part_number) ) + sitemap_suffix )
return(sitemap_prefix + ("%05d" % (part_number)) + sitemap_suffix)
def is_file_uri(self, uri):
"""Return true if uri looks like a local file URI, false otherwise.
Test is to see whether have either an explicit file: URI or whether
there is no scheme name.
"""
return(re.match('file:',uri) or not re.match('\w{3,4}:',uri))
return(re.match('file:', uri) or not re.match('\w{3,4}:', uri))
class ListBaseIndexError(Exception):

8
resync/resource.py
View File

@ -250,11 +250,11 @@ class Resource(object):
"""
hashvals = []
if (self.md5 is not None):
hashvals.append('md5:'+self.md5)
hashvals.append('md5:' + self.md5)
if (self.sha1 is not None):
hashvals.append('sha-1:'+self.sha1)
hashvals.append('sha-1:' + self.sha1)
if (self.sha256 is not None):
hashvals.append('sha-256:'+self.sha256)
hashvals.append('sha-256:' + self.sha256)
if (len(hashvals) > 0):
return(' '.join(hashvals))
return(None)
@ -424,7 +424,7 @@ class Resource(object):
# not equal if only one timestamp specified
if (self.timestamp is None or
other.timestamp is None or
abs(self.timestamp-other.timestamp) >= delta):
abs(self.timestamp - other.timestamp) >= delta):
return(False)
if ((self.md5 is not None and other.md5 is not None) and
self.md5 != other.md5):

80
resync/resource_container.py
View File

@ -2,7 +2,7 @@
All documents in ResourceSync have the same types of information:
they have some top-level metadata and links, and then a list of
resources, each of which may also have metadata and links. This
resources, each of which may also have metadata and links. This
class implements this model.
This is a base class for the ListBase class which is in turn the
@ -13,6 +13,7 @@ adds IO.
import collections
from .w3c_datetime import datetime_to_str
class ResourceContainer(object):
"""Class containing resource-like objects.
@ -30,13 +31,14 @@ class ResourceContainer(object):
should use only the core functionality.
"""
def __init__(self, resources=None, md=None, ln=None, uri=None, capability_name=None):
def __init__(self, resources=None, md=None, ln=None,
uri=None, capability_name=None):
"""Initialize ResourceContainer."""
self.resources=(resources if (resources is not None) else [])
self.md=(md if (md is not None) else {})
self.ln=(ln if (ln is not None) else [])
self.uri=uri
self.capability_name=capability_name
self.resources = (resources if (resources is not None) else [])
self.md = (md if (md is not None) else {})
self.ln = (ln if (ln is not None) else [])
self.uri = uri
self.capability_name = capability_name
def __iter__(self):
"""Iterator over all the resources in this resource list.
@ -45,7 +47,7 @@ class ResourceContainer(object):
"""
return(iter(self.resources))
def __getitem__(self,index):
def __getitem__(self, index):
"""Feed through for __getitem__ of resources property."""
return(self.resources[index])
@ -58,8 +60,8 @@ class ResourceContainer(object):
return(None)
@capability.setter
def capability(self,capability):
self.md['capability']=capability
def capability(self, capability):
self.md['capability'] = capability
@property
def md_from(self):
@ -70,8 +72,8 @@ class ResourceContainer(object):
return(None)
@md_from.setter
def md_from(self,md_from):
self.md['md_from']=self._str_datetime_now(md_from)
def md_from(self, md_from):
self.md['md_from'] = self._str_datetime_now(md_from)
@property
def md_until(self):
@ -82,8 +84,8 @@ class ResourceContainer(object):
return(None)
@md_until.setter
def md_until(self,md_until):
self.md['md_until']=self._str_datetime_now(md_until)
def md_until(self, md_until):
self.md['md_until'] = self._str_datetime_now(md_until)
@property
def md_at(self):
@ -94,8 +96,8 @@ class ResourceContainer(object):
return(None)
@md_at.setter
def md_at(self,md_at):
self.md['md_at']=self._str_datetime_now(md_at)
def md_at(self, md_at):
self.md['md_at'] = self._str_datetime_now(md_at)
@property
def md_completed(self):
@ -106,29 +108,29 @@ class ResourceContainer(object):
return(None)
@md_completed.setter
def md_completed(self,md_completed):
self.md['md_completed']=self._str_datetime_now(md_completed)
def md_completed(self, md_completed):
self.md['md_completed'] = self._str_datetime_now(md_completed)
def link(self,rel):
def link(self, rel):
"""Look for link with specified rel, return else None."""
for link in self.ln:
if ('rel' in link and
link['rel']==rel):
link['rel'] == rel):
return(link)
return(None)
def link_href(self,rel):
def link_href(self, rel):
"""Look for link with specified rel, return href from it or None."""
link = self.link(rel)
if (link is not None):
link = link['href']
return(link)
def link_set(self,rel,href,**atts):
def link_set(self, rel, href, **atts):
"""Set/create link with specified rel, set href and any other attributes.
Any link element must have both rel and href values, the specification
also defines the type attributes and others are permitted also. See
also defines the type attributes and others are permitted also. See
description of allowed formats in
http://www.openarchives.org/rs/resourcesync.html#DocumentFormats
@ -139,7 +141,7 @@ class ResourceContainer(object):
link['href'] = href
else:
# create new link
link = {'rel':rel,'href':href}
link = {'rel': rel, 'href': href}
self.ln.append(link)
for k in atts:
link[k] = atts[k]
@ -150,9 +152,9 @@ class ResourceContainer(object):
return(self.link_href('describedby'))
@describedby.setter
def describedby(self,uri):
def describedby(self, uri):
"""Set ResourceSync Description link to given URI."""
self.link_set('describedby',uri)
self.link_set('describedby', uri)
@property
def up(self):
@ -160,9 +162,9 @@ class ResourceContainer(object):
return(self.link_href('up'))
@up.setter
def up(self,uri):
def up(self, uri):
"""Set ResourceSync rel="up" link to given URI."""
self.link_set('up',uri)
self.link_set('up', uri)
@property
def index(self):
@ -170,9 +172,9 @@ class ResourceContainer(object):
return(self.link_href('index'))
@index.setter
def index(self,uri):
def index(self, uri):
"""Set index link to given URI."""
self.link_set('index',uri)
self.link_set('index', uri)
def default_capability(self):
"""Set capability name in md.
@ -181,7 +183,7 @@ class ResourceContainer(object):
capability attributes.
"""
if ('capability' not in self.md and self.capability_name is not None):
self.md['capability']=self.capability_name
self.md['capability'] = self.capability_name
def add(self, resource):
"""Add a resource or an iterable collection of resources to this container.
@ -203,7 +205,7 @@ class ResourceContainer(object):
def prune_before(self, timestamp):
"""Remove all resources with timestamp earlier than that given.
Returns the number of entries removed. Will raise an excpetion
if there are any entries without a timestamp.
"""
@ -221,8 +223,8 @@ class ResourceContainer(object):
def prune_dupes(self):
"""Remove all but the last entry for a given resource URI.
Returns the number of entries removed. Also removes all entries for a
Returns the number of entries removed. Also removes all entries for a
given URI where the first entry is a create and the last entry is a
delete.
"""
@ -234,12 +236,12 @@ class ResourceContainer(object):
if (r.uri in seen):
n += 1
if (r.uri in deletes):
deletes[r.uri]=r.change
deletes[r.uri] = r.change
else:
pruned1.append(r)
seen.add(r.uri)
if (r.change == 'deleted'):
deletes[r.uri]=r.change
deletes[r.uri] = r.change
# go through all deletes and prune if first was create
pruned2 = []
for r in reversed(pruned1):
@ -247,7 +249,7 @@ class ResourceContainer(object):
n += 1
else:
pruned2.append(r)
self.resources=pruned2
self.resources = pruned2
return(n)
def __str__(self):
@ -259,7 +261,7 @@ class ResourceContainer(object):
def _str_datetime_now(self, x=None):
"""Return datetime string for use with time attributes.
Handling depends on input:
'now' - returns datetime for now
number - assume datetime values, generate string
@ -267,7 +269,7 @@ class ResourceContainer(object):
"""
if (x == 'now'):
# Now, this is wht datetime_to_str() with no arg gives
return( datetime_to_str() )
return(datetime_to_str())
try:
# Test for number
junk = x + 0.0

15
resync/resource_dump_manifest.py
View File

@ -1,6 +1,6 @@
"""ResourceSync ResourceDumpManifest object.
A ResourceDumpManifest lists the set of files/resources included
A ResourceDumpManifest lists the set of files/resources included
within a content package that is included in a ResourceDump.
The ResourceDumpManifest object may also contain metadata and links.
@ -11,6 +11,7 @@ http://www.openarchives.org/rs/resourcesync#ResourceDumpManifest
from .resource_list import ResourceList
class ResourceDumpManifest(ResourceList):
"""Class representing a Resource Dump Manifest.
@ -19,7 +20,15 @@ class ResourceDumpManifest(ResourceList):
and implemented as a sub-class of ResourceList.
"""
def __init__(self, resources=None, md=None, ln=None, uri=None, allow_multifile=None, mapper=None):
def __init__(self, resources=None, md=None, ln=None,
uri=None, allow_multifile=None, mapper=None):
"""Initialize ResourceDumpManifest."""
super(ResourceDumpManifest, self).__init__(resources=resources, md=md, ln=ln, uri=uri, mapper=mapper)
super(
ResourceDumpManifest,
self).__init__(
resources=resources,
md=md,
ln=ln,
uri=uri,
mapper=mapper)
self.capability_name = 'resourcedump-manifest'

83
resync/resource_list.py
View File

@ -1,16 +1,16 @@
"""ResourceSync Resource List object.
A Resource List is a set of resources with some metadata for
each resource. Comparison of resource lists from a source and
A Resource List is a set of resources with some metadata for
each resource. Comparison of resource lists from a source and
a destination allows understanding of whether the two are in
sync or whether some resources need to be updated at the
destination.
There may also be metadata about the Resource List, and links
to other ResourceSync documents. Metadata include the
timestamp of the Resource List (md_at) and, optionally, the
to other ResourceSync documents. Metadata include the
timestamp of the Resource List (md_at) and, optionally, the
timestamp when creation of the Resource List was completed
(md_completed).at the top level. These include a creation timestamp
(md_completed).at the top level. These include a creation timestamp
(from) and links to the Capability List.
Described in specification at:
@ -22,9 +22,9 @@ import os
from datetime import datetime
import re
import sys
try: #python3
try: # python3
from urllib.request import URLopener
except ImportError: #python2
except ImportError: # python2
from urllib import URLopener
from .list_base_with_index import ListBaseWithIndex
@ -48,7 +48,7 @@ class ResourceListDict(dict):
return(iter(self._iter_next, None))
def _iter_next(self):
if (len(self._iter_next_list)>0):
if (len(self._iter_next_list) > 0):
return(self[self._iter_next_list.pop()])
else:
return(None)
@ -61,13 +61,15 @@ class ResourceListDict(dict):
"""Add just a single resource."""
uri = resource.uri
if (uri in self and not replace):
raise ResourceListDupeError("Attempt to add resource already in resource_list")
self[uri]=resource
raise ResourceListDupeError(
"Attempt to add resource already in resource_list")
self[uri] = resource
class ResourceListOrdered(list):
"""Alternative implementation of class to store resources in ResourceList.
FIXME - This is a rather inefficient implementation which involves
FIXME - This is a rather inefficient implementation which involves
scanning all resources to check for duplicates. Designed just to enable
re-creation of examples in the spec. Something dictionary based would
likely be better. Might be best to use OrderedDict but that is available
@ -91,18 +93,21 @@ class ResourceListOrdered(list):
for r in self:
if (uri == r.uri):
if (replace):
r=resource
r = resource
return
else:
raise ResourceListDupeError("Attempt to add resource already in resource_list")
raise ResourceListDupeError(
"Attempt to add resource already in resource_list")
# didn't find it in list, add to end
self.append(resource)
class ResourceListDupeError(Exception):
"""Exception in case of duplicate resource."""
pass
class ResourceList(ListBaseWithIndex):
"""Class representing a ResourceList.
@ -114,22 +119,22 @@ class ResourceList(ListBaseWithIndex):
A ResourceList will admit only one resource with any given URI.
Typical usage for a small ResourceList is:
rl = ResourceList()
rl.add( Resource(...) )
rl.add( Resource(...) )
print rl.as_xml()
The default storage is unordered but the iterator imposes a canonical
order which is alphabetical by URI. If it is desired to have
The default storage is unordered but the iterator imposes a canonical
order which is alphabetical by URI. If it is desired to have
resources listed in the order they are added then the ResourceDictOrdered
class may be specified on creation:
rl = ResourceList( resources_class=ResourceDictOrdered )
In normal use it is expected that any Resource List Index will be
created automatically when writing out a large Resource List in
multiple sitemap files. However, should it be necessary to
multiple sitemap files. However, should it be necessary to
explicitly create an index then this may be specified with:
rli = ResourceList( resources_class=ResourceDictOrdered )
@ -138,11 +143,11 @@ class ResourceList(ListBaseWithIndex):
See additional descriptions in ListBaseWithIndex and ListBase.
"""
def __init__(self, resources=None, count=None, md=None, ln=None, uri=None,
def __init__(self, resources=None, count=None, md=None, ln=None, uri=None,
allow_multifile=None, mapper=None, resources_class=ResourceListDict):
"""Initialize ResourceList."""
super(ResourceList, self).__init__(resources=resources, count=count, md=md, ln=ln, uri=uri,
capability_name = 'resourcelist',
capability_name='resourcelist',
allow_multifile=allow_multifile, mapper=mapper,
resources_class=resources_class)
@ -154,15 +159,15 @@ class ResourceList(ListBaseWithIndex):
"""
if isinstance(resource, collections.Iterable):
for r in resource:
self.resources.add(r,replace)
self.resources.add(r, replace)
else:
self.resources.add(resource,replace)
self.resources.add(resource, replace)
def compare(self,src):
def compare(self, src):
"""Compare this ResourceList object with that specified as src.
The parameter src must also be a ResourceList object, it is assumed
to be the source, and the current object is the destination. This
to be the source, and the current object is the destination. This
written to work for any objects in self and sc, provided that the
== operator can be used to compare them.
@ -171,38 +176,38 @@ class ResourceList(ListBaseWithIndex):
"""
dst_iter = iter(self.resources)
src_iter = iter(src.resources)
same=ResourceList()
updated=ResourceList()
deleted=ResourceList()
created=ResourceList()
dst_cur=next(dst_iter,None)
src_cur=next(src_iter,None)
same = ResourceList()
updated = ResourceList()
deleted = ResourceList()
created = ResourceList()
dst_cur = next(dst_iter, None)
src_cur = next(src_iter, None)
while ((dst_cur is not None) and (src_cur is not None)):
#print 'dst='+dst_cur+' src='+src_cur
# print 'dst='+dst_cur+' src='+src_cur
if (dst_cur.uri == src_cur.uri):
if (dst_cur==src_cur):
if (dst_cur == src_cur):
same.add(dst_cur)
else:
updated.add(src_cur)
dst_cur=next(dst_iter,None)
src_cur=next(src_iter,None)
dst_cur = next(dst_iter, None)
src_cur = next(src_iter, None)
elif (not src_cur or dst_cur.uri < src_cur.uri):
deleted.add(dst_cur)
dst_cur=next(dst_iter,None)
dst_cur = next(dst_iter, None)
elif (not dst_cur or dst_cur.uri > src_cur.uri):
created.add(src_cur)
src_cur=next(src_iter,None)
src_cur = next(src_iter, None)
else:
raise Exception("this should not be possible")
# what do we have leftover in src or dst lists?
while (dst_cur is not None):
deleted.add(dst_cur)
dst_cur=next(dst_iter,None)
dst_cur = next(dst_iter, None)
while (src_cur is not None):
created.add(src_cur)
src_cur=next(src_iter,None)
src_cur = next(src_iter, None)
# have now gone through both lists
return(same,updated,deleted,created)
return(same, updated, deleted, created)
def has_md5(self):
"""Return true if at least one contained resource-like object has md5 data."""

73
resync/resource_list_builder.py
View File

@ -5,9 +5,9 @@ import os.path
import re
import time
import logging
try: #python3
try: # python3
from urllib.request import URLopener
except ImportError: #python2
except ImportError: # python2
from urllib import URLopener
from defusedxml.ElementTree import parse
@ -17,10 +17,11 @@ from .sitemap import Sitemap
from .utils import compute_md5_for_file
from .w3c_datetime import datetime_to_str
class ResourceListBuilder():
"""ResourceListBuilder to create ResourceList objects.
Currently implements build from files on disk only.
Currently implements build from files on disk only.
Attributes:
- set_path set true to add path attribute for each resource
@ -33,16 +34,17 @@ class ResourceListBuilder():
alternatives to md5.
"""
def __init__(self, mapper=None, set_md5=False, set_length=True, set_path=False):
def __init__(self, mapper=None, set_md5=False,
set_length=True, set_path=False):
"""Create ResourceListBuilder object, optionally set options.
The mapper attribute must be set before a call to from_disk() in order to
map between local filenames and URIs.
The following attributes may be set to determine information added to
The following attributes may be set to determine information added to
each Resource object based on the disk scan:
- set_md5 - True to add md5 digests for each resource. This may add
significant time to the scan process as each file has to be read to
- set_md5 - True to add md5 digests for each resource. This may add
significant time to the scan process as each file has to be read to
compute the sum
- set_length - False to not add length for each resources
- set_path - True to add local path information for each file/resource
@ -52,7 +54,7 @@ class ResourceListBuilder():
self.set_md5 = set_md5
self.set_length = set_length
self.exclude_files = ['sitemap\d{0,5}.xml']
self.exclude_dirs = ['CVS','.git']
self.exclude_dirs = ['CVS', '.git']
self.include_symlinks = False
# Used internally only:
self.logger = logging.getLogger('resync.resource_list_builder')
@ -70,7 +72,8 @@ class ResourceListBuilder():
try:
self.compiled_exclude_files.append(re.compile(pattern))
except re.error as e:
raise ValueError("Bad python regex in exclude '%s': %s" % (pattern,str(e)))
raise ValueError(
"Bad python regex in exclude '%s': %s" % (pattern, str(e)))
def exclude_file(self, file):
"""True if file should be exclude based on name pattern."""
@ -82,18 +85,18 @@ class ResourceListBuilder():
def from_disk(self, resource_list=None, paths=None):
"""Create or extend resource_list with resources from disk scan.
Assumes very simple disk path to URL mapping (in self.mapping): chop
Assumes very simple disk path to URL mapping (in self.mapping): chop
path and replace with url_path. Returns the new or extended ResourceList
object.
If a resource_list is specified then items are added to that rather
than creating a new one.
If paths is specified then these are used instead of the set
If paths is specified then these are used instead of the set
of local paths in self.mapping.
Example usage with mapping start paths:
mapper=Mapper('http://example.org/path','/path/to/files')
rlb = ResourceListBuilder(mapper=mapper)
m = rlb.from_disk()
@ -104,7 +107,7 @@ class ResourceListBuilder():
rlb = ResourceListBuilder(mapper=mapper)
m = rlb.from_disk(paths=['/path/to/files/a','/path/to/files/b'])
"""
num=0
num = 0
# Either use resource_list passed in or make a new one
if (resource_list is None):
resource_list = ResourceList()
@ -112,10 +115,11 @@ class ResourceListBuilder():
self.compile_excludes()
# Work out start paths from map if not explicitly specified
if (paths is None):
paths=[]
paths = []
for map in self.mapper.mappings:
paths.append(map.dst_path)
# Set start time unless already set (perhaps because building in chunks)
# Set start time unless already set (perhaps because building in
# chunks)
if (resource_list.md_at is None):
resource_list.md_at = datetime_to_str()
# Run for each map in the mappings
@ -131,16 +135,18 @@ class ResourceListBuilder():
# sanity
if (path is None or resource_list is None or self.mapper is None):
raise ValueError("Must specify path, resource_list and mapper")
# is path a directory or a file? for each file: create Resource object,
# is path a directory or a file? for each file: create Resource object,
# add, increment counter
if os.path.isdir(path):
num_files=0
for dirpath, dirs, files in os.walk(path,topdown=True):
num_files = 0
for dirpath, dirs, files in os.walk(path, topdown=True):
for file_in_dirpath in files:
num_files+=1
if (num_files%50000 == 0):
self.logger.info("ResourceListBuilder.from_disk_add_path: %d files..." % (num_files))
self.add_file(resource_list=resource_list,dir=dirpath,file=file_in_dirpath)
num_files += 1
if (num_files % 50000 == 0):
self.logger.info(
"ResourceListBuilder.from_disk_add_path: %d files..." % (num_files))
self.add_file(resource_list=resource_list,
dir=dirpath, file=file_in_dirpath)
# prune list of dirs based on self.exclude_dirs
for exclude in self.exclude_dirs:
if exclude in dirs:
@ -148,11 +154,11 @@ class ResourceListBuilder():
dirs.remove(exclude)
else:
# single file
self.add_file(resource_list=resource_list,file=path)
self.add_file(resource_list=resource_list, file=path)
def add_file(self, resource_list=None, dir=None, file=None):
"""Add a single file to resource_list.
Follows object settings of set_path, set_md5 and set_length.
"""
try:
@ -161,25 +167,26 @@ class ResourceListBuilder():
return
# get abs filename and also URL
if (dir is not None):
file = os.path.join(dir,file)
if (not os.path.isfile(file) or not (self.include_symlinks or not os.path.islink(file))):
file = os.path.join(dir, file)
if (not os.path.isfile(file) or not (
self.include_symlinks or not os.path.islink(file))):
return
uri = self.mapper.dst_to_src(file)
if (uri is None):
raise Exception("Internal error, mapping failed")
file_stat=os.stat(file)
file_stat = os.stat(file)
except OSError as e:
sys.stderr.write("Ignoring file %s (error: %s)" % (file,str(e)))
sys.stderr.write("Ignoring file %s (error: %s)" % (file, str(e)))
return
timestamp = file_stat.st_mtime #UTC
r = Resource(uri=uri,timestamp=timestamp)
timestamp = file_stat.st_mtime # UTC
r = Resource(uri=uri, timestamp=timestamp)
if (self.set_path):
# add full local path
r.path=file
r.path = file
if (self.set_md5):
# add md5
r.md5=compute_md5_for_file(file)
r.md5 = compute_md5_for_file(file)
if (self.set_length):
# add length
r.length=file_stat.st_size
r.length = file_stat.st_size
resource_list.add(r)

13
resync/resource_set.py
View File

@ -1,13 +1,14 @@
"""Base class representing a set of Resource objects."""
class ResourceSet(dict):
"""Base class representing a set of Resource objects.
The ResourceSet class is used for Capability List Indexes and
The ResourceSet class is used for Capability List Indexes and
ResourceSync Description documents.
Ordering of Resources is currently alphanumeric (using sorted(..))
on the uri which is the key.
on the uri which is the key.
Key properties of this class are:
- has add(resource) method
@ -21,7 +22,7 @@ class ResourceSet(dict):
return(iter(self._iter_next, None))
def _iter_next(self):
if (len(self._iter_next_list)>0):
if (len(self._iter_next_list) > 0):
return(self[self._iter_next_list.pop()])
else:
return(None)
@ -30,8 +31,10 @@ class ResourceSet(dict):
"""Add just a single resource."""
uri = resource.uri
if (uri in self and not replace):
raise ResourceSetDupeError("Attempt to add resource already in this set")
self[uri]=resource
raise ResourceSetDupeError(
"Attempt to add resource already in this set")
self[uri] = resource
class ResourceSetDupeError(Exception):
"""Exception for case of attempt to add duplicate resource."""

308
resync/sitemap.py
View File

@ -6,11 +6,11 @@ import sys
import logging
from defusedxml.ElementTree import parse
from xml.etree.ElementTree import ElementTree, Element, tostring
try: #python2
try: # python2
# Must try this first as io also exists in python2
# but in the wrong one!
import StringIO as io
except ImportError: #python3
except ImportError: # python3
import io
from .resource import Resource
@ -27,6 +27,7 @@ XML_ATT_NAME = {
'md_until': 'until'
}
class SitemapIndexError(Exception):
"""Exception if sitemapindex read instead of sitemap or vice-versa.
@ -43,21 +44,24 @@ class SitemapIndexError(Exception):
"""Return just the message attribute."""
return(self.message)
class SitemapParseError(Exception):
"""Exception for sitemap parsing structural error."""
pass
class SitemapDupeError(Exception):
"""Exception for case of duplicate resources in sitemap."""
pass
class Sitemap(object):
"""Read and write sitemaps.
Implemented as a separate class that uses ResourceContainer
(ResourceList or ChangeList) and Resource classes as data objects.
Implemented as a separate class that uses ResourceContainer
(ResourceList or ChangeList) and Resource classes as data objects.
Reads and write sitemaps, including multiple file sitemaps.
This class does not automatically handle the reading or writing
@ -69,19 +73,18 @@ class Sitemap(object):
def __init__(self, pretty_xml=False):
"""Initialize Sitemap object."""
self.logger = logging.getLogger('resync.sitemap')
self.pretty_xml=pretty_xml
self.pretty_xml = pretty_xml
# Classes used when parsing
self.resource_class=Resource
self.resource_class = Resource
# Information recorded for logging
self.resources_created=0 # Set during parsing sitemap
self.parsed_index=None # Set True for sitemapindex, False for sitemap
self.resources_created = 0 # Set during parsing sitemap
self.parsed_index = None # Set True for sitemapindex, False for sitemap
##### Write the XML for a sitemap or sitemapindex #####
# Write the XML for a sitemap or sitemapindex
def resources_as_xml(self, resources, sitemapindex=False, fh=None):
"""Write or return XML for a set of resources in sitemap format.
Arguments:
- resources - either an iterable or iterator of Resource objects;
if there an md attribute this will go to <rs:md>
@ -90,51 +93,59 @@ class Sitemap(object):
- fh - write to filehandle fh instead of returning string
"""
# element names depending on sitemapindex or not
root_element = ( 'sitemapindex' if (sitemapindex) else 'urlset' )
item_element = ( 'sitemap' if (sitemapindex) else 'url')
root_element = ('sitemapindex' if (sitemapindex) else 'urlset')
item_element = ('sitemap' if (sitemapindex) else 'url')
# namespaces and other settings
namespaces = { 'xmlns': SITEMAP_NS, 'xmlns:rs': RS_NS }
namespaces = {'xmlns': SITEMAP_NS, 'xmlns:rs': RS_NS}
root = Element(root_element, namespaces)
if (self.pretty_xml):
root.text="\n"
root.text = "\n"
# <rs:ln>
if (hasattr(resources,'ln')):
if (hasattr(resources, 'ln')):
for ln in resources.ln:
self.add_element_with_atts_to_etree(root,'rs:ln',ln)
self.add_element_with_atts_to_etree(root, 'rs:ln', ln)
# <rs:md>
if (hasattr(resources,'md')):
self.add_element_with_atts_to_etree(root,'rs:md',resources.md)
if (hasattr(resources, 'md')):
self.add_element_with_atts_to_etree(root, 'rs:md', resources.md)
# <url> entries from either an iterable or an iterator
for r in resources:
e=self.resource_etree_element(r, element_name=item_element)
e = self.resource_etree_element(r, element_name=item_element)
root.append(e)
# have tree, now serialize
tree = ElementTree(root);
xml_buf=None
tree = ElementTree(root)
xml_buf = None
if (fh is None):
xml_buf=io.StringIO()
fh=xml_buf
if (sys.version_info < (2,7)):
tree.write(fh,encoding='UTF-8')
elif (sys.version_info < (3,0)):
tree.write(fh,encoding='UTF-8',xml_declaration=True,method='xml')
xml_buf = io.StringIO()
fh = xml_buf
if (sys.version_info < (2, 7)):
tree.write(fh, encoding='UTF-8')
elif (sys.version_info < (3, 0)):
tree.write(
fh,
encoding='UTF-8',
xml_declaration=True,
method='xml')
else:
tree.write(fh,encoding="unicode",xml_declaration=True,method='xml')
tree.write(
fh,
encoding="unicode",
xml_declaration=True,
method='xml')
if (xml_buf is not None):
return(xml_buf.getvalue())
# Read/parse an XML sitemap or sitemapindex
##### Read/parse an XML sitemap or sitemapindex #####
def parse_xml(self, fh=None, etree=None, resources=None, capability=None, sitemapindex=None):
def parse_xml(self, fh=None, etree=None, resources=None,
capability=None, sitemapindex=None):
"""Parse XML Sitemap and add to resources object.
Reads from fh or etree and adds resources to a resorces object
Reads from fh or etree and adds resources to a resorces object
(which must support the add method). Returns the resources object.
Also sets self.resources_created to be the number of resources created.
We adopt a very lax approach here. The parsing is properly namespace
aware but we search just for the elements wanted and leave everything
Also sets self.resources_created to be the number of resources created.
We adopt a very lax approach here. The parsing is properly namespace
aware but we search just for the elements wanted and leave everything
else alone.
This method will read either sitemap or sitemapindex documents. Behavior
@ -143,34 +154,38 @@ class Sitemap(object):
- False - SitemapIndexError exception if sitemapindex detected
- True - SitemapIndexError exception if sitemap detected
Will set self.parsed_index based on whether a sitemap or sitemapindex
Will set self.parsed_index based on whether a sitemap or sitemapindex
document was read:
- False - sitemap
- True - sitemapindex
"""
if (resources is None):
resources=ResourceContainer()
resources = ResourceContainer()
if (fh is not None):
etree=parse(fh)
etree = parse(fh)
elif (etree is None):
raise ValueError("Neither fh or etree set")
# check root element: urlset (for sitemap), sitemapindex or bad
root_tag = etree.getroot().tag
resource_tag = None # will be <url> or <sitemap> depending on type
resource_tag = None # will be <url> or <sitemap> depending on type
self.parsed_index = None
if (root_tag == '{'+SITEMAP_NS+"}urlset"):
if (root_tag == '{' + SITEMAP_NS + "}urlset"):
self.parsed_index = False
if (sitemapindex is not None and sitemapindex):
raise SitemapIndexError("Got sitemap when expecting sitemapindex",etree)
resource_tag = '{'+SITEMAP_NS+"}url"
elif (root_tag == '{'+SITEMAP_NS+"}sitemapindex"):
raise SitemapIndexError(
"Got sitemap when expecting sitemapindex", etree)
resource_tag = '{' + SITEMAP_NS + "}url"
elif (root_tag == '{' + SITEMAP_NS + "}sitemapindex"):
self.parsed_index = True
if (sitemapindex is not None and not sitemapindex):
raise SitemapIndexError("Got sitemapindex when expecting sitemap",etree)
resource_tag = '{'+SITEMAP_NS+"}sitemap"
raise SitemapIndexError(
"Got sitemapindex when expecting sitemap", etree)
resource_tag = '{' + SITEMAP_NS + "}sitemap"
else:
raise SitemapParseError("XML is not sitemap or sitemapindex (root element is <%s>)" % root_tag)
raise SitemapParseError(
"XML is not sitemap or sitemapindex (root element is <%s>)" %
root_tag)
# have what we expect, read it
in_preamble = True
self.resources_created = 0
@ -179,27 +194,32 @@ class Sitemap(object):
# look for <rs:md> and <rs:ln>, first <url> ends
# then look for resources in <url> blocks
if (e.tag == resource_tag):
in_preamble = False #any later rs:md or rs:ln is error
in_preamble = False # any later rs:md or rs:ln is error
r = self.resource_from_etree(e, self.resource_class)
try:
resources.add( r )
resources.add(r)
except SitemapDupeError:
self.logger.warning("dupe of: %s (lastmod=%s)" % (r.uri,r.lastmod))
self.resources_created+=1
elif (e.tag == "{"+RS_NS+"}md"):
self.logger.warning(
"dupe of: %s (lastmod=%s)" %
(r.uri, r.lastmod))
self.resources_created += 1
elif (e.tag == "{" + RS_NS + "}md"):
if (in_preamble):
if (seen_top_level_md):
raise SitemapParseError("Multiple <rs:md> at top level of sitemap")
raise SitemapParseError(
"Multiple <rs:md> at top level of sitemap")
else:
resources.md = self.md_from_etree(e,'preamble')
resources.md = self.md_from_etree(e, 'preamble')
seen_top_level_md = True
else:
raise SitemapParseError("Found <rs:md> after first <url> in sitemap")
elif (e.tag == "{"+RS_NS+"}ln"):
raise SitemapParseError(
"Found <rs:md> after first <url> in sitemap")
elif (e.tag == "{" + RS_NS + "}ln"):
if (in_preamble):
resources.ln.append(self.ln_from_etree(e,'preamble'))
resources.ln.append(self.ln_from_etree(e, 'preamble'))
else:
raise SitemapParseError("Found <rs:ln> after first <url> in sitemap")
raise SitemapParseError(
"Found <rs:ln> after first <url> in sitemap")
else:
# element we don't recognize, ignore
pass
@ -207,71 +227,71 @@ class Sitemap(object):
if (capability is not None):
if ('capability' not in resources.md):
if (capability == 'resourcelist'):
self.logger.warning('No capability specified in sitemap, assuming resourcelist')
self.logger.warning(
'No capability specified in sitemap, assuming resourcelist')
resources.md['capability'] = 'resourcelist'
else:
raise SitemapParseError("Expected to read a %s document, but no capability specified in sitemap" %
(capability))
(capability))
if (resources.md['capability'] != capability):
raise SitemapParseError("Expected to read a %s document, got %s" %
(capability,resources.md['capability']))
(capability, resources.md['capability']))
# return the resource container object
return(resources)
##### Resource methods #####
# Resource methods
def resource_etree_element(self, resource, element_name='url'):
"""Return xml.etree.ElementTree.Element representing the resource.
Returns and element for the specified resource, of the form <url>
Returns and element for the specified resource, of the form <url>
with enclosed properties that are based on the sitemap with extensions
for ResourceSync.
"""
e = Element(element_name)
sub = Element('loc')
sub.text=resource.uri
sub.text = resource.uri
e.append(sub)
if (resource.timestamp is not None):
# Create appriate element for timestamp
sub = Element('lastmod')
sub.text = str(resource.lastmod) #W3C Datetime in UTC
sub.text = str(resource.lastmod) # W3C Datetime in UTC
e.append(sub)
md_atts = {}
for att in ('capability','change','hash','length','path','mime_type',
'md_at','md_completed','md_from','md_until'):
val = getattr(resource,att,None)
for att in ('capability', 'change', 'hash', 'length', 'path', 'mime_type',
'md_at', 'md_completed', 'md_from', 'md_until'):
val = getattr(resource, att, None)
if (val is not None):
md_atts[self._xml_att_name(att)] = str(val)
if (len(md_atts)>0):
md = Element('rs:md',md_atts)
if (len(md_atts) > 0):
md = Element('rs:md', md_atts)
e.append(md)
# add any <rs:ln>
if (hasattr(resource,'ln') and
resource.ln is not None):
if (hasattr(resource, 'ln') and
resource.ln is not None):
for ln in resource.ln:
self.add_element_with_atts_to_etree(e,'rs:ln',ln)
self.add_element_with_atts_to_etree(e, 'rs:ln', ln)
if (self.pretty_xml):
e.tail="\n"
e.tail = "\n"
return(e)
def resource_as_xml(self,resource):
def resource_as_xml(self, resource):
"""Return string for the resource as part of an XML sitemap.
Returns a string with the XML snippet representing the resource,
without any XML declaration.
"""
e = self.resource_etree_element(resource)
if (sys.version_info > (3,0)):
if (sys.version_info > (3, 0)):
# python3.x
return(tostring(e, encoding='unicode', method='xml'))
elif (sys.version_info >= (2,7)):
elif (sys.version_info >= (2, 7)):
s = tostring(e, encoding='UTF-8', method='xml')
else:
#must not specify method='xml' in python2.6
# must not specify method='xml' in python2.6
s = tostring(e, encoding='UTF-8')
# Chop off XML declaration that is added in 2.x... sigh
return(s.replace("<?xml version='1.0' encoding='UTF-8'?>\n",''))
return(s.replace("<?xml version='1.0' encoding='UTF-8'?>\n", ''))
def resource_from_etree(self, etree, resource_class):
"""Construct a Resource from an etree.
@ -280,56 +300,61 @@ class Sitemap(object):
etree - the etree to parse
resource_class - class of Resource object to create
The parsing is properly namespace aware but we search just
for the elements wanted and leave everything else alone. Will
The parsing is properly namespace aware but we search just
for the elements wanted and leave everything else alone. Will
raise an error if there are multiple <loc> or multiple <lastmod>
elements. Otherwise, provided there is a <loc> element then will
elements. Otherwise, provided there is a <loc> element then will
go ahead and extract as much as possible.
All errors raised are SitemapParseError with messages intended
to help debug problematic sitemap XML.
"""
loc_elements = etree.findall('{'+SITEMAP_NS+"}loc")
if (len(loc_elements)>1):
raise SitemapParseError("Multiple <loc> elements while parsing <url> in sitemap");
elif (len(loc_elements)==0):
raise SitemapParseError("Missing <loc> element while parsing <url> in sitemap")
loc_elements = etree.findall('{' + SITEMAP_NS + "}loc")
if (len(loc_elements) > 1):
raise SitemapParseError(
"Multiple <loc> elements while parsing <url> in sitemap")
elif (len(loc_elements) == 0):
raise SitemapParseError(
"Missing <loc> element while parsing <url> in sitemap")
else:
loc = loc_elements[0].text
if (loc is None or loc==''):
raise SitemapParseError("Bad <loc> element with no content while parsing <url> in sitemap")
if (loc is None or loc == ''):
raise SitemapParseError(
"Bad <loc> element with no content while parsing <url> in sitemap")
# must at least have a URI, make this object
resource=resource_class(uri=loc)
resource = resource_class(uri=loc)
# and hopefully a lastmod datetime (but none is OK)
lastmod_elements = etree.findall('{'+SITEMAP_NS+"}lastmod")
if (len(lastmod_elements)>1):
raise SitemapParseError("Multiple <lastmod> elements while parsing <url> in sitemap");
elif (len(lastmod_elements)==1):
resource.lastmod=lastmod_elements[0].text
lastmod_elements = etree.findall('{' + SITEMAP_NS + "}lastmod")
if (len(lastmod_elements) > 1):
raise SitemapParseError(
"Multiple <lastmod> elements while parsing <url> in sitemap")
elif (len(lastmod_elements) == 1):
resource.lastmod = lastmod_elements[0].text
# proceed to look for other resource attributes in an rs:md element
md_elements = etree.findall('{'+RS_NS+"}md")
if (len(md_elements)>1):
raise SitemapParseError("Found multiple (%d) <rs:md> elements for %s", (len(md_elements),loc))
elif (len(md_elements)==1):
md_elements = etree.findall('{' + RS_NS + "}md")
if (len(md_elements) > 1):
raise SitemapParseError(
"Found multiple (%d) <rs:md> elements for %s", (len(md_elements), loc))
elif (len(md_elements) == 1):
# have on element, look at attributes
md = self.md_from_etree(md_elements[0],context=loc)
md = self.md_from_etree(md_elements[0], context=loc)
# simple attributes that map directly to Resource object attributes
for att in ('capability','change','length','path','mime_type'):
for att in ('capability', 'change', 'length', 'path', 'mime_type'):
if (att in md):
setattr(resource,att,md[att])
setattr(resource, att, md[att])
# The ResourceSync beta spec lists md5, sha-1 and sha-256 fixity
# digest types. Parse and warn of errors ignored.
if ('hash' in md):
try:
resource.hash = md['hash']
except ValueError as e:
self.logger.warning("%s in <rs:md> for %s" % (str(e),loc))
self.logger.warning("%s in <rs:md> for %s" % (str(e), loc))
# look for rs:ln elements (optional)
ln_elements = etree.findall('{'+RS_NS+"}ln")
if (len(ln_elements)>0):
ln_elements = etree.findall('{' + RS_NS + "}ln")
if (len(ln_elements) > 0):
resource.ln = []
for ln_element in ln_elements:
resource.ln.append(self.ln_from_etree(ln_element,loc))
resource.ln.append(self.ln_from_etree(ln_element, loc))
return(resource)
def md_from_etree(self, md_element, context=''):
@ -341,31 +366,36 @@ class Sitemap(object):
"""
md = {}
# grab all understood attributes into md dict
for att in ('capability','change','hash','length','path','mime_type',
'md_at','md_completed','md_from','md_until'):
for att in ('capability', 'change', 'hash', 'length', 'path', 'mime_type',
'md_at', 'md_completed', 'md_from', 'md_until'):
xml_att = self._xml_att_name(att)
val = md_element.attrib.get(xml_att,None)
val = md_element.attrib.get(xml_att, None)
if (val is not None):
md[att] = val
# capability. Allow this to be missing but do a very simple syntax
# check on plausible values if present
if ('capability' in md):
if (re.match(r"^[\w\-]+$", md['capability']) is None):
raise SitemapParseError("Bad capability name '%s' in %s" % (capability,context))
raise SitemapParseError(
"Bad capability name '%s' in %s" %
(capability, context))
# change should be one of defined values
if ('change' in md):
if (md['change'] not in ['created','updated','deleted'] ):
self.logger.warning("Bad change attribute in <rs:md> for %s" % (context))
if (md['change'] not in ['created', 'updated', 'deleted']):
self.logger.warning(
"Bad change attribute in <rs:md> for %s" %
(context))
# length should be an integer
if ('length' in md):
try:
md['length']=int(md['length'])
md['length'] = int(md['length'])
except ValueError as e:
raise SitemapParseError("Invalid length element in <rs:md> for %s" % (context))
raise SitemapParseError(
"Invalid length element in <rs:md> for %s" %
(context))
return(md)
def ln_from_etree(self,ln_element,context=''):
def ln_from_etree(self, ln_element, context=''):
"""Parse rs:ln element from an etree, returning a dict of the data.
Parameters:
@ -374,36 +404,44 @@ class Sitemap(object):
"""
ln = {}
# grab all understood attributes into ln dict
for att in ('hash','href','length','modified','path','rel','pri','mime_type'):
for att in ('hash', 'href', 'length', 'modified',
'path', 'rel', 'pri', 'mime_type'):
xml_att = self._xml_att_name(att)
val = ln_element.attrib.get(xml_att,None)
val = ln_element.attrib.get(xml_att, None)
if (val is not None):
ln[att] = val
# now do some checks and conversions...
# href (MANDATORY)
if ('href' not in ln):
raise SitemapParseError("Missing href in <rs:ln> in %s" % (context))
raise SitemapParseError(
"Missing href in <rs:ln> in %s" %
(context))
# rel (MANDATORY)
if ('rel' not in ln):
raise SitemapParseError("Missing rel in <rs:ln> in %s" % (context))
# length in bytes
if ('length' in ln):
try:
ln['length']=int(ln['length'])
ln['length'] = int(ln['length'])
except ValueError as e:
raise SitemapParseError("Invalid length attribute value in <rs:ln> for %s" % (context))
raise SitemapParseError(
"Invalid length attribute value in <rs:ln> for %s" %
(context))
# pri - priority, must be a number between 1 and 999999
if ('pri' in ln):
try:
ln['pri']=int(ln['pri'])
ln['pri'] = int(ln['pri'])
except ValueError as e:
raise SitemapParseError("Invalid pri attribute in <rs:ln> for %s" % (context))
if (ln['pri']<1 or ln['pri']>999999):
raise SitemapParseError("Bad pri attribute value in <rs:ln> for %s" % (context))
raise SitemapParseError(
"Invalid pri attribute in <rs:ln> for %s" %
(context))
if (ln['pri'] < 1 or ln['pri'] > 999999):
raise SitemapParseError(
"Bad pri attribute value in <rs:ln> for %s" %
(context))
return(ln)
##### Metadata and link elements #####
# Metadata and link elements
def add_element_with_atts_to_etree(self, etree, name, atts):
"""Add element with name and atts to etree iff there are any atts.
@ -418,18 +456,18 @@ class Sitemap(object):
val = atts[att]
if (val is not None):
xml_atts[self._xml_att_name(att)] = str(val)
if (len(xml_atts)>0):
e = Element(name,xml_atts)
if (len(xml_atts) > 0):
e = Element(name, xml_atts)
if (self.pretty_xml):
e.tail="\n"
e.tail = "\n"
etree.append(e)
def _xml_att_name(self,att):
def _xml_att_name(self, att):
"""Get XML attribute name corresponding to supplied Resource object attribute.
We cannot use the XML attribute names in Python because 'from' and others
conflict with Python reserved words. To be consistent all the extra timestamps
are prefixed with md_. Assumption is that attibute name is same unless
are prefixed with md_. Assumption is that attibute name is same unless
specified in XML_ATT_NAME.
"""
return XML_ATT_NAME.get(att,att)
return XML_ATT_NAME.get(att, att)

35
resync/source_description.py
View File

@ -1,17 +1,17 @@
"""ResourceSync Source Description object.
A ResourceSync Source Description enumerates the Capability
Lists offered by a Source. Since a Source has one Capability
List per set of resources that it distinguishes, the
ResourceSync Source Description will enumerate as many
A ResourceSync Source Description enumerates the Capability
Lists offered by a Source. Since a Source has one Capability
List per set of resources that it distinguishes, the
ResourceSync Source Description will enumerate as many
Capability Lists as the Source has distinct sets of resources.
The ResourceSync Source Description is based on the <urlset>
format. The specification allows for a very large Source Descriptions
to use and index based on a <sitemapindex>, though this is probably
to use and index based on a <sitemapindex>, though this is probably
rarely necessary!
There is no meaning in the order of description of sets of resources
There is no meaning in the order of description of sets of resources
in a Source Description so the default is to store these descriptions
as a set (ResourceSet).
@ -27,6 +27,7 @@ from resync.resource import Resource
from resync.resource_set import ResourceSet
from resync.list_base_with_index import ListBaseWithIndex
class SourceDescription(ListBaseWithIndex):
"""Class representing the set of Capability Lists supported.
@ -42,7 +43,7 @@ class SourceDescription(ListBaseWithIndex):
super(SourceDescription, self).__init__(resources=resources, md=md, ln=ln,
capability_name='description',
resources_class=ResourceSet)
self.md['from']=None #usually don't want a from date
self.md['from'] = None # usually don't want a from date
def add(self, resource, replace=False):
"""Add a resource or an iterable collection of resources.
@ -52,23 +53,23 @@ class SourceDescription(ListBaseWithIndex):
"""
if isinstance(resource, collections.Iterable):
for r in resource:
self.resources.add(r,replace)
self.resources.add(r, replace)
else:
self.resources.add(resource,replace)
self.resources.add(resource, replace)
def add_capability_list(self,capability_list=None):
def add_capability_list(self, capability_list=None):
"""Add a capability list.
Adds either a CapabiltyList object specified in capability_list
or else creates a Resource with the URI given in capability_list
and adds that to the Source Description
"""
if (hasattr(capability_list,'uri')):
r = Resource( uri=capability_list.uri,
capability=capability_list.capability_name )
if (hasattr(capability_list, 'uri')):
r = Resource(uri=capability_list.uri,
capability=capability_list.capability_name)
if (capability_list.describedby is not None):
r.link_set( rel='describedby', href=capability_list.describedby )
r.link_set(rel='describedby', href=capability_list.describedby)
else:
r = Resource( uri=capability_list,
capability='capabilitylist')
self.add( r )
r = Resource(uri=capability_list,
capability='capabilitylist')
self.add(r)

2
resync/w3c_datetime.py
View File

@ -113,7 +113,7 @@ def str_to_datetime(s, context='datetime'):
mm = int(m.group(6))
if (hh > 23 or mm > 59):
raise ValueError("Bad timezone offset (%s)" % s)
offset_seconds = hh*3600 + mm*60
offset_seconds = hh * 3600 + mm * 60
if (m.group(4) == '-'):
offset_seconds = -offset_seconds
# timetuple() ignores timezone information so we have to add in

13
tests/capture_stdout.py
View File

@ -1,17 +1,22 @@
"""Provide capture_stdout as contect manager."""
import sys, contextlib
try: #python2
import sys
import contextlib
try: # python2
# Must try this first as io also exists in python2
# but in the wrong one!
import StringIO as io
except ImportError: #python3
except ImportError: # python3
import io
# From http://stackoverflow.com/questions/2654834/capturing-stdout-within-the-same-process-in-python
# From
# http://stackoverflow.com/questions/2654834/capturing-stdout-within-the-same-process-in-python
class Data(object):
pass
@contextlib.contextmanager
def capture_stdout():
old = sys.stdout

57
tests/test_capability_list.py
View File

@ -6,56 +6,61 @@ from resync.resource_set import ResourceSetDupeError
from resync.change_list import ChangeList
from resync.capability_list import CapabilityList
class TestCapabilityList(unittest.TestCase):
def test01_add(self):
# one
caps = CapabilityList()
r1 = Resource( uri='http://example.org/r1' )
caps.add( r1 )
self.assertEqual( len(caps), 1 )
r1 = Resource(uri='http://example.org/r1')
caps.add(r1)
self.assertEqual(len(caps), 1)
# dupe
self.assertRaises( ResourceSetDupeError, caps.add, r1 )
self.assertEqual( len(caps), 1 )
self.assertRaises(ResourceSetDupeError, caps.add, r1)
self.assertEqual(len(caps), 1)
# dupe with replace
caps = CapabilityList()
caps.add( [r1,r1], replace=True )
self.assertEqual( len(caps), 1 )
caps.add([r1, r1], replace=True)
self.assertEqual(len(caps), 1)
# diff
caps = CapabilityList()
r2 = ChangeList( uri='http://example.org/r2' )
caps.add( [r1,r2] )
self.assertEqual( len(caps), 2 )
r2 = ChangeList(uri='http://example.org/r2')
caps.add([r1, r2])
self.assertEqual(len(caps), 2)
def test02_resourcelist(self):
rl = ResourceList()
caps = CapabilityList()
caps.add_capability( rl, "http://example.org/resourcelist.xml" )
caps.add_capability(rl, "http://example.org/resourcelist.xml")
caps.md['from'] = "2013-02-07T22:39:00"
self.assertEqual( len(caps), 1 )
self.assertEqual( caps.as_xml(), '<?xml version=\'1.0\' encoding=\'UTF-8\'?>\n<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9" xmlns:rs="http://www.openarchives.org/rs/terms/"><rs:md capability="capabilitylist" from="2013-02-07T22:39:00" /><url><loc>http://example.org/resourcelist.xml</loc><rs:md capability="resourcelist" /></url></urlset>' )
self.assertEqual(len(caps), 1)
self.assertEqual(caps.as_xml(), '<?xml version=\'1.0\' encoding=\'UTF-8\'?>\n<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9" xmlns:rs="http://www.openarchives.org/rs/terms/"><rs:md capability="capabilitylist" from="2013-02-07T22:39:00" /><url><loc>http://example.org/resourcelist.xml</loc><rs:md capability="resourcelist" /></url></urlset>')
def test03_multiple(self):
caps = CapabilityList()
rl = ResourceList()
caps.add_capability( rl, "rl.xml" )
caps.add_capability(rl, "rl.xml")
cl = ChangeList()
caps.add_capability( cl, "cl.xml" )
self.assertEqual( len(caps), 2 )
caps.add_capability(cl, "cl.xml")
self.assertEqual(len(caps), 2)
xml = caps.as_xml()
self.assertTrue( re.search( r'<loc>rl.xml</loc><rs:md capability="resourcelist" />', xml ) )
self.assertTrue( re.search( r'<loc>cl.xml</loc><rs:md capability="changelist" />', xml) )
self.assertTrue(
re.search(r'<loc>rl.xml</loc><rs:md capability="resourcelist" />', xml))
self.assertTrue(
re.search(r'<loc>cl.xml</loc><rs:md capability="changelist" />', xml))
def test04_parse(self):
xml='<?xml version=\'1.0\' encoding=\'UTF-8\'?>\n<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9" xmlns:rs="http://www.openarchives.org/rs/terms/"><rs:md capability="capabilitylist" from="2013-02-07T22:39:00" /><url><loc>http://example.org/resourcelist.xml</loc><rs:md capability="resourcelist" /></url></urlset>'
cl=CapabilityList()
xml = '<?xml version=\'1.0\' encoding=\'UTF-8\'?>\n<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9" xmlns:rs="http://www.openarchives.org/rs/terms/"><rs:md capability="capabilitylist" from="2013-02-07T22:39:00" /><url><loc>http://example.org/resourcelist.xml</loc><rs:md capability="resourcelist" /></url></urlset>'
cl = CapabilityList()
cl.parse(str_data=xml)
self.assertEqual( cl.capability, 'capabilitylist')
self.assertEqual( len(cl.resources), 1, 'got 1 resource')
self.assertEqual(cl.capability, 'capabilitylist')
self.assertEqual(len(cl.resources), 1, 'got 1 resource')
[r] = cl.resources
self.assertEqual( r.uri, 'http://example.org/resourcelist.xml', 'resourcelist uri')
self.assertEqual( r.capability, 'resourcelist')
self.assertEqual(
r.uri, 'http://example.org/resourcelist.xml', 'resourcelist uri')
self.assertEqual(r.capability, 'resourcelist')
if __name__ == '__main__':
suite = unittest.defaultTestLoader.loadTestsFromTestCase(TestCapabilityList)
suite = unittest.defaultTestLoader.loadTestsFromTestCase(
TestCapabilityList)
unittest.TextTestRunner().run(suite)

47
tests/test_change_dump.py
View File

@ -1,9 +1,9 @@
import unittest
try: #python2
try: # python2
# Must try this first as io also exists in python2
# but in the wrong one!
import StringIO as io
except ImportError: #python3
except ImportError: # python3
import io
import re
@ -11,53 +11,56 @@ from resync.resource import Resource
from resync.change_dump import ChangeDump
from resync.sitemap import SitemapParseError
class TestChangeDump(unittest.TestCase):
def test01_as_xml(self):
rd = ChangeDump()
rd.add( Resource('a.zip',timestamp=1) )
rd.add( Resource('b.zip',timestamp=2) )
rd.add(Resource('a.zip', timestamp=1))
rd.add(Resource('b.zip', timestamp=2))
xml = rd.as_xml()
#print(xml)
self.assertTrue( re.search(r'<rs:md .*capability="changedump"', xml), 'XML has capability' )
self.assertTrue( re.search(r'<url><loc>a.zip</loc><lastmod>1970-01-01T00:00:01Z</lastmod></url>', xml), 'XML has resource a' )
# print(xml)
self.assertTrue(
re.search(r'<rs:md .*capability="changedump"', xml), 'XML has capability')
self.assertTrue(re.search(
r'<url><loc>a.zip</loc><lastmod>1970-01-01T00:00:01Z</lastmod></url>', xml), 'XML has resource a')
def test10_parse(self):
xml='<?xml version=\'1.0\' encoding=\'UTF-8\'?>\n\
xml = '<?xml version=\'1.0\' encoding=\'UTF-8\'?>\n\
<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9" xmlns:rs="http://www.openarchives.org/rs/terms/">\
<rs:md capability="changedump" from="2013-01-01"/>\
<url><loc>http://example.com/a.zip</loc><lastmod>2012-03-14T18:37:36Z</lastmod><rs:md length="12345" /></url>\
<url><loc>http://example.com/b.zip</loc><lastmod>2012-03-14T18:37:36Z</lastmod><rs:md length="56789" /></url>\
</urlset>'
rd=ChangeDump()
rd = ChangeDump()
rd.parse(fh=io.StringIO(xml))
self.assertEqual( len(rd.resources), 2, 'got 2 resource dumps')
self.assertEqual( rd.md['capability'], 'changedump', 'capability set' )
self.assertEqual( rd.md_from, '2013-01-01' )
self.assertTrue( 'http://example.com/a.zip' in rd.resources )
self.assertTrue( rd.resources['http://example.com/a.zip'].length, 12345 )
self.assertTrue( 'http://example.com/b.zip' in rd.resources )
self.assertTrue( rd.resources['http://example.com/b.zip'].length, 56789 )
self.assertEqual(len(rd.resources), 2, 'got 2 resource dumps')
self.assertEqual(rd.md['capability'], 'changedump', 'capability set')
self.assertEqual(rd.md_from, '2013-01-01')
self.assertTrue('http://example.com/a.zip' in rd.resources)
self.assertTrue(rd.resources['http://example.com/a.zip'].length, 12345)
self.assertTrue('http://example.com/b.zip' in rd.resources)
self.assertTrue(rd.resources['http://example.com/b.zip'].length, 56789)
def test11_parse_no_capability(self):
# For a resource dump this should be an error
xml='<?xml version=\'1.0\' encoding=\'UTF-8\'?>\n\
xml = '<?xml version=\'1.0\' encoding=\'UTF-8\'?>\n\
<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9" xmlns:rs="http://www.openarchives.org/rs/terms/">\
<rs:md at="2013-01-01"/>\
<url><loc>http://example.com/a.zip</loc><lastmod>2012-03-14T18:37:36Z</lastmod><rs:md length="12" /></url>\
</urlset>'
rd=ChangeDump()
self.assertRaises( SitemapParseError, rd.parse, fh=io.StringIO(xml) )
rd = ChangeDump()
self.assertRaises(SitemapParseError, rd.parse, fh=io.StringIO(xml))
def test12_parse_bad_capability(self):
# the <rs:md capability="bad_capability".. should give error
xml='<?xml version=\'1.0\' encoding=\'UTF-8\'?>\n\
xml = '<?xml version=\'1.0\' encoding=\'UTF-8\'?>\n\
<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9" xmlns:rs="http://www.openarchives.org/rs/terms/">\
<rs:md capability="bad_capability" from="2013-01-01"/>\
<url><loc>http://example.com/bad_res_1</loc><lastmod>2012-03-14T18:37:36Z</lastmod></url>\
</urlset>'
rd=ChangeDump()
self.assertRaises( SitemapParseError, rd.parse, fh=io.StringIO(xml) )
rd = ChangeDump()
self.assertRaises(SitemapParseError, rd.parse, fh=io.StringIO(xml))
if __name__ == '__main__':
suite = unittest.defaultTestLoader.loadTestsFromTestCase(TestChangeDump)

115
tests/test_change_list.py
View File

@ -1,9 +1,9 @@
import unittest
try: #python2
try: # python2
# Must try this first as io also exists in python2
# but in the wrong one!
import StringIO as io
except ImportError: #python3
except ImportError: # python3
import io
import re
@ -12,86 +12,90 @@ from resync.change_list import ChangeList, ChangeTypeError
from resync.resource_list import ResourceList
from resync.sitemap import SitemapParseError
class TestChangeList(unittest.TestCase):
def test01_add_if_changed(self):
cl = ChangeList()
cl.add_if_changed( Resource('a',timestamp=1,change='updated') )
self.assertEqual( len(cl), 1 )
self.assertRaises( ChangeTypeError, cl.add_if_changed,
Resource('c',timestamp=3) )
cl.add_if_changed(Resource('a', timestamp=1, change='updated'))
self.assertEqual(len(cl), 1)
self.assertRaises(ChangeTypeError, cl.add_if_changed,
Resource('c', timestamp=3))
def test02_set_with_repeats(self):
cl = ChangeList()
cl.add( Resource('a',timestamp=1,change='updated') )
cl.add( Resource('b',timestamp=1,change='created') )
cl.add( Resource('c',timestamp=1,change='deleted') )
cl.add( Resource('a',timestamp=2,change='deleted') )
cl.add( Resource('b',timestamp=2,change='updated') )
cl.add(Resource('a', timestamp=1, change='updated'))
cl.add(Resource('b', timestamp=1, change='created'))
cl.add(Resource('c', timestamp=1, change='deleted'))
cl.add(Resource('a', timestamp=2, change='deleted'))
cl.add(Resource('b', timestamp=2, change='updated'))
self.assertEqual(len(cl), 5, "5 changes in change_list")
def test03_with_repeats_again(self):
r1 = Resource(uri='a',length=1,change='created')
r2 = Resource(uri='b',length=2,change='created')
r1 = Resource(uri='a', length=1, change='created')
r2 = Resource(uri='b', length=2, change='created')
i = ChangeList()
i.add(r1)
i.add(r2)
self.assertEqual( len(i), 2 )
self.assertEqual(len(i), 2)
# Can add another Resource with same URI
r1d = Resource(uri='a',length=10,change='created')
r1d = Resource(uri='a', length=10, change='created')
i.add(r1d)
self.assertEqual( len(i), 3 )
self.assertEqual(len(i), 3)
def test04_change_list(self):
cl = ChangeList()
cl.add( Resource('a',timestamp=1,change='created') )
cl.add( Resource('b',timestamp=2,change='created') )
cl.add( Resource('c',timestamp=3,change='created') )
cl.add( Resource('d',timestamp=4,change='created') )
cl.add( Resource('e',timestamp=5,change='created') )
cl.add(Resource('a', timestamp=1, change='created'))
cl.add(Resource('b', timestamp=2, change='created'))
cl.add(Resource('c', timestamp=3, change='created'))
cl.add(Resource('d', timestamp=4, change='created'))
cl.add(Resource('e', timestamp=5, change='created'))
self.assertEqual(len(cl), 5, "5 things in src")
def test05_iter(self):
i = ChangeList()
i.add( Resource('a',timestamp=1,change='created') )
i.add( Resource('b',timestamp=2,change='created') )
i.add( Resource('c',timestamp=3,change='created') )
i.add( Resource('d',timestamp=4,change='created') )
resources=[]
i.add(Resource('a', timestamp=1, change='created'))
i.add(Resource('b', timestamp=2, change='created'))
i.add(Resource('c', timestamp=3, change='created'))
i.add(Resource('d', timestamp=4, change='created'))
resources = []
for r in i:
resources.append(r)
self.assertEqual(len(resources), 4)
self.assertEqual( resources[0].uri, 'a')
self.assertEqual( resources[3].uri, 'd')
self.assertEqual(resources[0].uri, 'a')
self.assertEqual(resources[3].uri, 'd')
def test06_add_changed_resources(self):
added = ResourceList()
added.add( Resource('a',timestamp=1,change='created') )
added.add( Resource('d',timestamp=4,change='created') )
added.add(Resource('a', timestamp=1, change='created'))
added.add(Resource('d', timestamp=4, change='created'))
self.assertEqual(len(added), 2, "2 things in added resource_list")
changes = ChangeList()
changes.add_changed_resources( added, change='created' )
changes.add_changed_resources(added, change='created')
self.assertEqual(len(changes), 2, "2 things added")
i = iter(changes)
first = next(i)
self.assertEqual(first.uri, 'a', "changes[0].uri=a")
self.assertEqual(first.timestamp, 1, "changes[0].timestamp=1")
self.assertEqual(first.change, 'created') #, "changes[0].change=createdd")
# , "changes[0].change=createdd")
self.assertEqual(first.change, 'created')
second = next(i)
self.assertEqual(second.timestamp, 4, "changes[1].timestamp=4")
self.assertEqual(second.change, 'created', "changes[1].change=createdd")
self.assertEqual(second.change, 'created',
"changes[1].change=createdd")
# Now add some with updated (one same, one diff)
updated = ResourceList()
updated.add( Resource('a',timestamp=5,change='created') )
updated.add( Resource('b',timestamp=6,change='created') )
updated.add(Resource('a', timestamp=5, change='created'))
updated.add(Resource('b', timestamp=6, change='created'))
self.assertEqual(len(updated), 2, "2 things in updated resource_list")
changes.add_changed_resources( updated, change='updated' )
changes.add_changed_resources(updated, change='updated')
self.assertEqual(len(changes), 4, "4 = 2 old + 2 things updated")
# Make new resource_list from the changes which should not have dupes
dst = ResourceList()
dst.add( changes, replace=True )
dst.add(changes, replace=True)
self.assertEqual(len(dst), 3, "3 unique resources")
self.assertEqual(dst.resources['a'].timestamp, 5 ) # 5 was later in last the 1
# 5 was later in last the 1
self.assertEqual(dst.resources['a'].timestamp, 5)
self.assertEqual(dst.resources['a'].change, 'updated')
self.assertEqual(dst.resources['b'].timestamp, 6)
self.assertEqual(dst.resources['b'].change, 'updated')
@ -101,44 +105,47 @@ class TestChangeList(unittest.TestCase):
def test07_as_xml(self):
cl = ChangeList()
cl.md_from = '1970-01-01T00:00:00Z'
cl.add( Resource('a',timestamp=1,change='updated') )
cl.add( Resource('b',timestamp=2,change='updated') )
cl.add(Resource('a', timestamp=1, change='updated'))
cl.add(Resource('b', timestamp=2, change='updated'))
xml = cl.as_xml()
self.assertTrue( re.search(r'<rs:md .*capability="changelist"', xml), 'XML has capability' )
self.assertTrue( re.search(r'<rs:md .*from="\d\d\d\d\-\d\d\-\d\dT\d\d:\d\d:\d\dZ"', xml), 'XML has from to seconds precision (and not more)' )
self.assertTrue( re.search(r'<url><loc>a</loc><lastmod>1970-01-01T00:00:01Z</lastmod>', xml), 'XML has resource a' )
self.assertTrue(
re.search(r'<rs:md .*capability="changelist"', xml), 'XML has capability')
self.assertTrue(re.search(r'<rs:md .*from="\d\d\d\d\-\d\d\-\d\dT\d\d:\d\d:\d\dZ"',
xml), 'XML has from to seconds precision (and not more)')
self.assertTrue(re.search(
r'<url><loc>a</loc><lastmod>1970-01-01T00:00:01Z</lastmod>', xml), 'XML has resource a')
def test08_parse(self):
xml='<?xml version=\'1.0\' encoding=\'UTF-8\'?>\n\
xml = '<?xml version=\'1.0\' encoding=\'UTF-8\'?>\n\
<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9" xmlns:rs="http://www.openarchives.org/rs/terms/">\
<rs:md capability="changelist" from="2013-01-01"/>\
<url><loc>/tmp/rs_test/src/file_a</loc><lastmod>2012-03-14T18:37:36Z</lastmod><rs:md change="updated" length="12" /></url>\
<url><loc>/tmp/rs_test/src/file_b</loc><lastmod>2012-03-14T18:37:36Z</lastmod><rs:md change="deleted" length="32" /></url>\
</urlset>'
cl=ChangeList()
cl = ChangeList()
cl.parse(fh=io.StringIO(xml))
self.assertEqual( len(cl.resources), 2, 'got 2 resources')
self.assertEqual( cl.md['capability'], 'changelist', 'capability set' )
self.assertEqual( cl.md['md_from'], '2013-01-01' )
self.assertEqual(len(cl.resources), 2, 'got 2 resources')
self.assertEqual(cl.md['capability'], 'changelist', 'capability set')
self.assertEqual(cl.md['md_from'], '2013-01-01')
def test09_parse_no_capability(self):
# missing capability is an error for changelist
xml='<?xml version=\'1.0\' encoding=\'UTF-8\'?>\n\
xml = '<?xml version=\'1.0\' encoding=\'UTF-8\'?>\n\
<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9" xmlns:rs="http://www.openarchives.org/rs/terms/">\
<url><loc>http://example.com/res1</loc><lastmod>2012-03-14T18:37:36Z</lastmod><rs:md change="updated"/></url>\
</urlset>'
cl=ChangeList()
self.assertRaises( SitemapParseError, cl.parse, fh=io.StringIO(xml) )
cl = ChangeList()
self.assertRaises(SitemapParseError, cl.parse, fh=io.StringIO(xml))
def test10_parse_bad_capability(self):
# the <rs:md capability="bad_capability".. should give error
xml='<?xml version=\'1.0\' encoding=\'UTF-8\'?>\n\
xml = '<?xml version=\'1.0\' encoding=\'UTF-8\'?>\n\
<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9" xmlns:rs="http://www.openarchives.org/rs/terms/">\
<rs:md capability="bad_capability" from="2013-01-01"/>\
<url><loc>http://example.com/bad_res_1</loc><lastmod>2012-03-14T18:37:36Z</lastmod><rs:md change="updated"/></url>\
</urlset>'
cl=ChangeList()
self.assertRaises( SitemapParseError, cl.parse, fh=io.StringIO(xml) )
cl = ChangeList()
self.assertRaises(SitemapParseError, cl.parse, fh=io.StringIO(xml))
if __name__ == '__main__':
suite = unittest.defaultTestLoader.loadTestsFromTestCase(TestChangeList)

369
tests/test_client.py
View File

@ -15,323 +15,366 @@ from resync.change_list import ChangeList
logging.basicConfig(level=logging.INFO)
class TestClient(TestCase):
def test01_make_resource_list_empty(self):
c = Client()
# No mapping is an error
self.assertRaises( ClientFatalError, c.build_resource_list )
self.assertRaises(ClientFatalError, c.build_resource_list)
def test02_bad_source_uri(self):
c = Client()
self.assertRaises( ClientFatalError, c.baseline_or_audit )
c.set_mappings( ['http://example.org/bbb','/tmp/this_does_not_exist'] )
self.assertRaises( ClientFatalError, c.baseline_or_audit )
self.assertRaises(ClientFatalError, c.baseline_or_audit)
c.set_mappings(['http://example.org/bbb', '/tmp/this_does_not_exist'])
self.assertRaises(ClientFatalError, c.baseline_or_audit)
def test03_sitemap_uri(self):
c = Client()
c.set_mappings( ['http://example.org/c','/tmp/not_there_at_all'] )
self.assertEqual( c.sitemap_uri('abcd1'), 'http://example.org/c/abcd1' )
self.assertEqual( c.sitemap_uri('/abcd2'), '/abcd2' )
self.assertEqual( c.sitemap_uri('scheme:/abcd3'), 'scheme:/abcd3' )
c.set_mappings(['http://example.org/c', '/tmp/not_there_at_all'])
self.assertEqual(c.sitemap_uri('abcd1'), 'http://example.org/c/abcd1')
self.assertEqual(c.sitemap_uri('/abcd2'), '/abcd2')
self.assertEqual(c.sitemap_uri('scheme:/abcd3'), 'scheme:/abcd3')
def test10_baseline_or_audit(self):
# FIXME - this is the guts of the client, tough to test, need to work through more cases...
# FIXME - this is the guts of the client, tough to test, need to work
# through more cases...
c = Client()
dst = os.path.join(self.tmpdir,'dst_dir1')
c.set_mappings( ['file:tests/testdata/client/dir1',dst] )
dst = os.path.join(self.tmpdir, 'dst_dir1')
c.set_mappings(['file:tests/testdata/client/dir1', dst])
# audit with empty dst, should say 3 to create
with LogCapture() as lc:
c.baseline_or_audit(audit_only=True)
self.assertTrue( re.match(r'Status:\s+NOT IN SYNC.*to create=3', lc.records[-2].msg) )
self.assertEqual( lc.records[-1].msg, 'Completed audit' )
self.assertTrue(
re.match(r'Status:\s+NOT IN SYNC.*to create=3', lc.records[-2].msg))
self.assertEqual(lc.records[-1].msg, 'Completed audit')
# now do the sync
with LogCapture() as lc:
c.baseline_or_audit()
self.assertTrue( re.match(r'Status:\s+SYNCED.*created=3', lc.records[-2].msg) )
self.assertEqual( lc.records[-1].msg, 'Completed baseline sync' )
self.assertTrue(
re.match(r'Status:\s+SYNCED.*created=3', lc.records[-2].msg))
self.assertEqual(lc.records[-1].msg, 'Completed baseline sync')
def test18_update_resource(self):
c = Client()
resource = Resource(uri='http://example.org/dir/2')
filename = os.path.join(self.tmpdir,'dir/resource2')
filename = os.path.join(self.tmpdir, 'dir/resource2')
# dryrun
with LogCapture() as lc:
c.dryrun = True
c.logger = logging.getLogger('resync.client')
n = c.update_resource( resource, filename )
self.assertEqual( n, 0 )
self.assertTrue( lc.records[-1].msg.startswith('dryrun: would GET http://example.org/dir/2 ') )
c.logger = logging.getLogger('resync.client')
n = c.update_resource(resource, filename)
self.assertEqual(n, 0)
self.assertTrue(
lc.records[-1].msg.startswith('dryrun: would GET http://example.org/dir/2 '))
c.dryrun = False
# get from file uri that does not exist
resource = Resource(uri='file:tests/testdata/i_do_not_exist')
self.assertRaises( ClientFatalError, c.update_resource, resource, filename )
# get from file uri that does not exist but with c.ignore_failures to log
self.assertRaises(ClientFatalError,
c.update_resource, resource, filename)
# get from file uri that does not exist but with c.ignore_failures to
# log
resource = Resource(uri='file:tests/testdata/i_do_not_exist')
with LogCapture() as lc:
c.logger = logging.getLogger('resync.client')
c.logger = logging.getLogger('resync.client')
c.ignore_failures = True
n = c.update_resource( resource, filename )
self.assertEqual( n, 0 )
self.assertTrue( lc.records[-1].msg.startswith('Failed to GET file:tests/testdata/i_do_not_exist ') )
n = c.update_resource(resource, filename)
self.assertEqual(n, 0)
self.assertTrue(
lc.records[-1].msg.startswith('Failed to GET file:tests/testdata/i_do_not_exist '))
# get from file uri
resource = Resource(uri='file:tests/testdata/examples_from_spec/resourcesync_ex_1.xml',
length=355, md5='abc',
timestamp=10)
c.last_timestamp = 0
with LogCapture() as lc:
c.logger = logging.getLogger('resync.client')
n = c.update_resource( resource, filename )
self.assertEqual( n, 1 )
self.assertTrue( lc.records[-1].msg.startswith('Event: {') )
c.logger = logging.getLogger('resync.client')
n = c.update_resource(resource, filename)
self.assertEqual(n, 1)
self.assertTrue(lc.records[-1].msg.startswith('Event: {'))
# get from file uri with length and md5 warnings
resource = Resource(uri='file:tests/testdata/examples_from_spec/resourcesync_ex_1.xml',
length=111, md5='abc',
timestamp=10)
c.last_timestamp = 0
with LogCapture() as lc:
c.logger = logging.getLogger('resync.client')
c.logger = logging.getLogger('resync.client')
c.checksum = True
n = c.update_resource( resource, filename )
self.assertEqual( n, 1 )
self.assertTrue( lc.records[-1].msg.startswith('MD5 mismatch ') )
self.assertTrue( lc.records[-2].msg.startswith('Downloaded size for ') )
self.assertTrue( lc.records[-3].msg.startswith('Event: {') )
n = c.update_resource(resource, filename)
self.assertEqual(n, 1)
self.assertTrue(lc.records[-1].msg.startswith('MD5 mismatch '))
self.assertTrue(
lc.records[-2].msg.startswith('Downloaded size for '))
self.assertTrue(lc.records[-3].msg.startswith('Event: {'))
def test19_delete_resource(self):
c = Client()
resource = Resource(uri='http://example.org/1')
filename = os.path.join(self.tmpdir,'resource1')
filename = os.path.join(self.tmpdir, 'resource1')
c.last_timestamp = 5
# no delete, no timestamp update
with LogCapture() as lc:
c.logger = logging.getLogger('resync.client')
n = c.delete_resource( resource, filename )
self.assertEqual( n, 0 )
self.assertEqual( lc.records[-1].msg,
'nodelete: would delete http://example.org/1 (--delete to enable)' )
self.assertEqual( c.last_timestamp, 5 )
c.logger = logging.getLogger('resync.client')
n = c.delete_resource(resource, filename)
self.assertEqual(n, 0)
self.assertEqual(lc.records[-1].msg,
'nodelete: would delete http://example.org/1 (--delete to enable)')
self.assertEqual(c.last_timestamp, 5)
# no delete but timestamp update
resource.timestamp = 10
with LogCapture() as lc:
c.logger = logging.getLogger('resync.client')
n = c.delete_resource( resource, filename )
self.assertEqual( n, 0 )
self.assertEqual( lc.records[-1].msg,
'nodelete: would delete http://example.org/1 (--delete to enable)' )
self.assertEqual( c.last_timestamp, 10 )
c.logger = logging.getLogger('resync.client')
n = c.delete_resource(resource, filename)
self.assertEqual(n, 0)
self.assertEqual(lc.records[-1].msg,
'nodelete: would delete http://example.org/1 (--delete to enable)')
self.assertEqual(c.last_timestamp, 10)
# allow delete but dryrun
with LogCapture() as lc:
c.dryrun = True
c.logger = logging.getLogger('resync.client')
n = c.delete_resource( resource, filename, allow_deletion=True )
self.assertEqual( n, 0 )
self.assertTrue( lc.records[-1].msg.startswith('dryrun: would delete http://example.org/1') )
c.logger = logging.getLogger('resync.client')
n = c.delete_resource(resource, filename, allow_deletion=True)
self.assertEqual(n, 0)
self.assertTrue(
lc.records[-1].msg.startswith('dryrun: would delete http://example.org/1'))
c.dryrun = False
# allow delete but no resource present
with LogCapture() as lc:
c.logger = logging.getLogger('resync.client')
n = c.delete_resource( resource, filename, allow_deletion=True )
self.assertEqual( n, 0 )
self.assertTrue( lc.records[-1].msg.startswith('Failed to DELETE http://example.org/1') )
c.logger = logging.getLogger('resync.client')
n = c.delete_resource(resource, filename, allow_deletion=True)
self.assertEqual(n, 0)
self.assertTrue(
lc.records[-1].msg.startswith('Failed to DELETE http://example.org/1'))
# successful deletion, first make file...
with open(filename, 'w') as fh:
fh.write('delete me')
fh.close()
with LogCapture() as lc:
c.logger = logging.getLogger('resync.client')
n = c.delete_resource( resource, filename, allow_deletion=True )
self.assertEqual( n, 1 )
self.assertTrue( lc.records[-1].msg.startswith('Event: {') )
self.assertTrue( lc.records[-2].msg.startswith('deleted: http://example.org/1 ->') )
c.logger = logging.getLogger('resync.client')
n = c.delete_resource(resource, filename, allow_deletion=True)
self.assertEqual(n, 1)
self.assertTrue(lc.records[-1].msg.startswith('Event: {'))
self.assertTrue(
lc.records[-2].msg.startswith('deleted: http://example.org/1 ->'))
def test20_parse_document(self):
# Key property of the parse_document() method is that it parses the
# document and identifies its type
c = Client()
with capture_stdout() as capturer:
c.sitemap_name='tests/testdata/examples_from_spec/resourcesync_ex_1.xml'
c.sitemap_name = 'tests/testdata/examples_from_spec/resourcesync_ex_1.xml'
c.parse_document()
self.assertTrue( re.search(r'Parsed resourcelist document with 2 entries',capturer.result) )
self.assertTrue(
re.search(r'Parsed resourcelist document with 2 entries', capturer.result))
with capture_stdout() as capturer:
c.sitemap_name='tests/testdata/examples_from_spec/resourcesync_ex_17.xml'
c.sitemap_name = 'tests/testdata/examples_from_spec/resourcesync_ex_17.xml'
c.parse_document()
self.assertTrue( re.search(r'Parsed resourcedump document with 3 entries',capturer.result) )
self.assertTrue(
re.search(r'Parsed resourcedump document with 3 entries', capturer.result))
with capture_stdout() as capturer:
c.sitemap_name='tests/testdata/examples_from_spec/resourcesync_ex_19.xml'
c.sitemap_name = 'tests/testdata/examples_from_spec/resourcesync_ex_19.xml'
c.parse_document()
self.assertTrue( re.search(r'Parsed changelist document with 4 entries',capturer.result) )
self.assertTrue(
re.search(r'Parsed changelist document with 4 entries', capturer.result))
with capture_stdout() as capturer:
c.sitemap_name='tests/testdata/examples_from_spec/resourcesync_ex_22.xml'
c.sitemap_name = 'tests/testdata/examples_from_spec/resourcesync_ex_22.xml'
c.parse_document()
self.assertTrue( re.search(r'Parsed changedump document with 3 entries',capturer.result) )
self.assertTrue(
re.search(r'Parsed changedump document with 3 entries', capturer.result))
# Document that doesn't exist
c.sitemap_name='/does_not_exist'
self.assertRaises( ClientFatalError, c.parse_document )
c.sitemap_name = '/does_not_exist'
self.assertRaises(ClientFatalError, c.parse_document)
# and verbose with truncation...
with capture_stdout() as capturer:
c.verbose = True
c.sitemap_name = 'tests/testdata/examples_from_spec/resourcesync_ex_1.xml'
c.max_sitemap_entries = 1
c.max_sitemap_entries = 1
c.parse_document()
self.assertTrue( re.search(r'Showing first 1 entries', capturer.result ) )
self.assertTrue( re.search(r'\[0\] ', capturer.result ) )
self.assertFalse( re.search(r'\[1\] ', capturer.result ) )
self.assertTrue(re.search(r'Showing first 1 entries', capturer.result))
self.assertTrue(re.search(r'\[0\] ', capturer.result))
self.assertFalse(re.search(r'\[1\] ', capturer.result))
def test40_write_resource_list_mappings(self):
c = Client()
c.set_mappings( ['http://example.org/','tests/testdata/'] )
c.set_mappings(['http://example.org/', 'tests/testdata/'])
# with no explicit paths seting the mapping will be used
with capture_stdout() as capturer:
c.write_resource_list()
#sys.stderr.write(capturer.result)
self.assertTrue( re.search(r'<rs:md at="\S+" capability="resourcelist"', capturer.result ) )
self.assertTrue( re.search(r'<url><loc>http://example.org/dir1/file_a</loc>', capturer.result ) )
self.assertTrue( re.search(r'<url><loc>http://example.org/dir1/file_b</loc>', capturer.result ) )
self.assertTrue( re.search(r'<url><loc>http://example.org/dir2/file_x</loc>', capturer.result ) )
# sys.stderr.write(capturer.result)
self.assertTrue(
re.search(r'<rs:md at="\S+" capability="resourcelist"', capturer.result))
self.assertTrue(
re.search(r'<url><loc>http://example.org/dir1/file_a</loc>', capturer.result))
self.assertTrue(
re.search(r'<url><loc>http://example.org/dir1/file_b</loc>', capturer.result))
self.assertTrue(
re.search(r'<url><loc>http://example.org/dir2/file_x</loc>', capturer.result))
def test41_write_resource_list_path(self):
c = Client()
c.set_mappings( ['http://example.org/','tests/testdata/'] )
links=[{'rel':'uri_c','href':'uri_d'}]
# with an explicit paths setting only the specified paths will be included
c.set_mappings(['http://example.org/', 'tests/testdata/'])
links = [{'rel': 'uri_c', 'href': 'uri_d'}]
# with an explicit paths setting only the specified paths will be
# included
with capture_stdout() as capturer:
c.write_resource_list(paths='tests/testdata/dir1', links=links)
self.assertTrue( re.search(r'<rs:md at="\S+" capability="resourcelist"', capturer.result ) )
self.assertTrue( re.search(r'<url><loc>http://example.org/dir1/file_a</loc>', capturer.result ) )
self.assertTrue( re.search(r'<url><loc>http://example.org/dir1/file_b</loc>', capturer.result ) )
self.assertFalse( re.search(r'<url><loc>http://example.org/dir2/file_x</loc>', capturer.result ) )
self.assertTrue(
re.search(r'<rs:md at="\S+" capability="resourcelist"', capturer.result))
self.assertTrue(
re.search(r'<url><loc>http://example.org/dir1/file_a</loc>', capturer.result))
self.assertTrue(
re.search(r'<url><loc>http://example.org/dir1/file_b</loc>', capturer.result))
self.assertFalse(
re.search(r'<url><loc>http://example.org/dir2/file_x</loc>', capturer.result))
# check link present
self.assertTrue( re.search(r'rel="uri_c"', capturer.result ) )
self.assertTrue( re.search(r'href="uri_d"', capturer.result ) )
self.assertTrue(re.search(r'rel="uri_c"', capturer.result))
self.assertTrue(re.search(r'href="uri_d"', capturer.result))
# Travis CI does not preserve timestamps from github so test here for the file
# size but not the datestamp
#self.assertTrue( re.search(r'<url><loc>http://example.org/dir1/file_a</loc><lastmod>[\w\-:]+</lastmod><rs:md length="20" /></url>', capturer.result ) )
#self.assertTrue( re.search(r'<url><loc>http://example.org/dir1/file_b</loc><lastmod>[\w\-:]+</lastmod><rs:md length="45" /></url>', capturer.result ) )
# to file
outfile = os.path.join(self.tmpdir,'rl_out.xml')
# self.assertTrue( re.search(r'<url><loc>http://example.org/dir1/file_a</loc><lastmod>[\w\-:]+</lastmod><rs:md length="20" /></url>', capturer.result ) )
# self.assertTrue( re.search(r'<url><loc>http://example.org/dir1/file_b</loc><lastmod>[\w\-:]+</lastmod><rs:md length="45" /></url>', capturer.result ) )
# to file
outfile = os.path.join(self.tmpdir, 'rl_out.xml')
c.write_resource_list(paths='tests/testdata/dir1', outfile=outfile)
self.assertTrue( os.path.getsize(outfile)>100 )
self.assertTrue(os.path.getsize(outfile) > 100)
# dump instead (default file)
c.default_resource_dump = os.path.join(self.tmpdir,'rl_out_dump_def')
outfile = c.default_resource_dump+'00000.zip'
self.assertFalse( os.path.exists(outfile) )
c.default_resource_dump = os.path.join(self.tmpdir, 'rl_out_dump_def')
outfile = c.default_resource_dump + '00000.zip'
self.assertFalse(os.path.exists(outfile))
c.write_resource_list(paths='tests/testdata/dir1', dump=True)
self.assertTrue( os.path.getsize(outfile)>100 )
self.assertTrue(os.path.getsize(outfile) > 100)
# (specific file)
outbase = os.path.join(self.tmpdir,'rl_out_dump')
outfile = outbase+'00000.zip'
self.assertFalse( os.path.exists(outfile) )
c.write_resource_list(paths='tests/testdata/dir1', dump=True, outfile=outbase)
self.assertTrue( os.path.getsize(outfile)>100 )
outbase = os.path.join(self.tmpdir, 'rl_out_dump')
outfile = outbase + '00000.zip'
self.assertFalse(os.path.exists(outfile))
c.write_resource_list(paths='tests/testdata/dir1',
dump=True, outfile=outbase)
self.assertTrue(os.path.getsize(outfile) > 100)
def test45_write_change_list(self):
c = Client()
ex1 = 'tests/testdata/examples_from_spec/resourcesync_ex_1.xml'
with capture_stdout() as capturer:
c.write_change_list(ref_sitemap=ex1, newref_sitemap=ex1)
self.assertTrue( re.search(r'<rs:md capability="changelist"', capturer.result) )
self.assertTrue(
re.search(r'<rs:md capability="changelist"', capturer.result))
# compare ex1 with testdata on disk
c.set_mappings( ['http://example.org/','tests/testdata/'] )
c.set_mappings(['http://example.org/', 'tests/testdata/'])
with capture_stdout() as capturer:
c.write_change_list(ref_sitemap=ex1, paths='tests/testdata/dir1')
self.assertTrue( re.search(r'<rs:md capability="changelist"', capturer.result) )
self.assertTrue( re.search(r'<url><loc>http://example.com/res1</loc><rs:md change="deleted" /></url>', capturer.result) )
# to file
outfile = os.path.join(self.tmpdir,'cl_out.xml')
c.write_change_list(ref_sitemap=ex1, newref_sitemap=ex1, outfile=outfile)
self.assertTrue( os.path.getsize(outfile)>100 )
self.assertTrue(
re.search(r'<rs:md capability="changelist"', capturer.result))
self.assertTrue(re.search(
r'<url><loc>http://example.com/res1</loc><rs:md change="deleted" /></url>', capturer.result))
# to file
outfile = os.path.join(self.tmpdir, 'cl_out.xml')
c.write_change_list(
ref_sitemap=ex1, newref_sitemap=ex1, outfile=outfile)
self.assertTrue(os.path.getsize(outfile) > 100)
def test46_write_capability_list(self):
c = Client()
caps = { 'a':'uri_a', 'b':'uri_b' }
caps = {'a': 'uri_a', 'b': 'uri_b'}
# simple case to STDOUT
with capture_stdout() as capturer:
c.write_capability_list( caps )
self.assertTrue( re.search(r'<urlset ',capturer.result) )
self.assertTrue( re.search(r'<rs:md capability="capabilitylist" />',capturer.result) )
self.assertTrue( re.search(r'<url><loc>uri_a</loc><rs:md capability="a"',capturer.result) )
self.assertTrue( re.search(r'<url><loc>uri_b</loc><rs:md capability="b"',capturer.result) )
c.write_capability_list(caps)
self.assertTrue(re.search(r'<urlset ', capturer.result))
self.assertTrue(
re.search(r'<rs:md capability="capabilitylist" />', capturer.result))
self.assertTrue(
re.search(r'<url><loc>uri_a</loc><rs:md capability="a"', capturer.result))
self.assertTrue(
re.search(r'<url><loc>uri_b</loc><rs:md capability="b"', capturer.result))
# to file (just check that something is written)
outfile = os.path.join(self.tmpdir,'caps_out.xml')
outfile = os.path.join(self.tmpdir, 'caps_out.xml')
c.write_capability_list(capabilities=caps, outfile=outfile)
self.assertTrue( os.path.getsize(outfile)>100 )
self.assertTrue(os.path.getsize(outfile) > 100)
def test47_write_source_description(self):
c = Client()
# simple case to STDOUT
with capture_stdout() as capturer:
c.write_source_description( [ 'a','b','c' ] )
self.assertTrue( re.search(r'<urlset ',capturer.result) )
self.assertTrue( re.search(r'<rs:md capability="description" />',capturer.result) )
self.assertTrue( re.search(r'<url><loc>a</loc><rs:md capability="capabilitylist" /></url>',capturer.result) )
self.assertTrue( re.search(r'<url><loc>b</loc><rs:md capability="capabilitylist" /></url>',capturer.result) )
c.write_source_description(['a', 'b', 'c'])
self.assertTrue(re.search(r'<urlset ', capturer.result))
self.assertTrue(
re.search(r'<rs:md capability="description" />', capturer.result))
self.assertTrue(re.search(
r'<url><loc>a</loc><rs:md capability="capabilitylist" /></url>', capturer.result))
self.assertTrue(re.search(
r'<url><loc>b</loc><rs:md capability="capabilitylist" /></url>', capturer.result))
# more complex case to STDOUT
with capture_stdout() as capturer:
c.write_source_description(capability_lists=['http://a.b/'], links=[{'rel':'c','href':'d'}])
self.assertTrue( re.search(r'http://a.b/', capturer.result ) )
c.write_source_description(
capability_lists=['http://a.b/'], links=[{'rel': 'c', 'href': 'd'}])
self.assertTrue(re.search(r'http://a.b/', capturer.result))
# to file (just check that something is written)
outfile = os.path.join(self.tmpdir,'sd_out.xml')
c.write_source_description(capability_lists=['http://a.b/'], outfile=outfile, links=[{'rel':'c','href':'d'}])
self.assertTrue( os.path.getsize(outfile)>100 )
outfile = os.path.join(self.tmpdir, 'sd_out.xml')
c.write_source_description(capability_lists=[
'http://a.b/'], outfile=outfile, links=[{'rel': 'c', 'href': 'd'}])
self.assertTrue(os.path.getsize(outfile) > 100)
def test48_write_dump_if_requested(self):
c = Client()
# no dump file
self.assertFalse( c.write_dump_if_requested( ChangeList(), None ) )
self.assertFalse(c.write_dump_if_requested(ChangeList(), None))
# with dump file
with capture_stdout() as capturer:
c.write_dump_if_requested(ChangeList(),'/tmp/a_file')
self.assertTrue( re.search(r'FIXME', capturer.result) )
c.write_dump_if_requested(ChangeList(), '/tmp/a_file')
self.assertTrue(re.search(r'FIXME', capturer.result))
def test49_read_reference_resource_list(self):
c = Client()
with capture_stdout() as capturer:
rl = c.read_reference_resource_list('tests/testdata/examples_from_spec/resourcesync_ex_1.xml')
self.assertEqual( len(rl), 2 )
self.assertEqual( '', capturer.result )
rl = c.read_reference_resource_list(
'tests/testdata/examples_from_spec/resourcesync_ex_1.xml')
self.assertEqual(len(rl), 2)
self.assertEqual('', capturer.result)
c.verbose = True
with capture_stdout() as capturer:
rl = c.read_reference_resource_list('tests/testdata/examples_from_spec/resourcesync_ex_1.xml')
self.assertEqual( len(rl), 2 )
self.assertTrue( re.search(r'http://example.com/res2', capturer.result) )
rl = c.read_reference_resource_list(
'tests/testdata/examples_from_spec/resourcesync_ex_1.xml')
self.assertEqual(len(rl), 2)
self.assertTrue(re.search(r'http://example.com/res2', capturer.result))
c.verbose = True
c.max_sitemap_entries = 1
with capture_stdout() as capturer:
rl = c.read_reference_resource_list('tests/testdata/examples_from_spec/resourcesync_ex_1.xml')
self.assertEqual( len(rl), 2 )
self.assertTrue( re.search(r'http://example.com/res1', capturer.result) )
self.assertTrue( re.search(r'Showing first 1 entries', capturer.result) )
self.assertFalse( re.search(r'http://example.com/res2', capturer.result) )
rl = c.read_reference_resource_list(
'tests/testdata/examples_from_spec/resourcesync_ex_1.xml')
self.assertEqual(len(rl), 2)
self.assertTrue(re.search(r'http://example.com/res1', capturer.result))
self.assertTrue(re.search(r'Showing first 1 entries', capturer.result))
self.assertFalse(
re.search(r'http://example.com/res2', capturer.result))
def test50_log_status(self):
c = Client()
with LogCapture() as lc:
c.logger = logging.getLogger('resync.client')
c.log_status()
self.assertEqual( lc.records[-1].msg,
'Status: IN SYNC (created=0, updated=0, deleted=0)' )
c.log_status(created=123,updated=456,deleted=789)
self.assertEqual( lc.records[-1].msg,
'Status: IN SYNC (created=123, updated=456, deleted=789)' )
self.assertEqual(lc.records[-1].msg,
'Status: IN SYNC (created=0, updated=0, deleted=0)')
c.log_status(created=123, updated=456, deleted=789)
self.assertEqual(lc.records[-1].msg,
'Status: IN SYNC (created=123, updated=456, deleted=789)')
c.log_status(incremental=True)
self.assertEqual( lc.records[-1].msg,
'Status: NO CHANGES (created=0, updated=0, deleted=0)' )
self.assertEqual(lc.records[-1].msg,
'Status: NO CHANGES (created=0, updated=0, deleted=0)')
c.log_status(audit=True)
self.assertEqual( lc.records[-1].msg,
'Status: IN SYNC (to create=0, to update=0, to delete=0)' )
self.assertEqual(lc.records[-1].msg,
'Status: IN SYNC (to create=0, to update=0, to delete=0)')
c.log_status(in_sync=False, audit=True)
self.assertEqual( lc.records[-1].msg,
'Status: NOT IN SYNC (to create=0, to update=0, to delete=0)' )
self.assertEqual(lc.records[-1].msg,
'Status: NOT IN SYNC (to create=0, to update=0, to delete=0)')
c.log_status(in_sync=False, audit=False, to_delete=1)
self.assertEqual( lc.records[-1].msg,
'Status: PART SYNCED (created=0, updated=0, to delete (--delete)=1)' )
c.log_status(in_sync=False, audit=False, to_delete=1, incremental=1)
self.assertEqual( lc.records[-1].msg,
'Status: PART APPLIED (created=0, updated=0, to delete (--delete)=1)' )
self.assertEqual(lc.records[-1].msg,
'Status: PART SYNCED (created=0, updated=0, to delete (--delete)=1)')
c.log_status(in_sync=False, audit=False,
to_delete=1, incremental=1)
self.assertEqual(lc.records[-1].msg,
'Status: PART APPLIED (created=0, updated=0, to delete (--delete)=1)')
c.log_status(in_sync=False)
self.assertEqual( lc.records[-1].msg,
'Status: SYNCED (created=0, updated=0, deleted=0)' )
self.assertEqual(lc.records[-1].msg,
'Status: SYNCED (created=0, updated=0, deleted=0)')
if __name__ == '__main__':
suite = unittest.TestLoader().loadTestsFromTestCase(TestClient)

44
tests/test_client_link_options.py
View File

@ -1,14 +1,12 @@
import sys
import unittest
try: #python2
try: # python2
# Must try this first as io also exists in python2
# but in the wrong one!
import BytesIO as io
except ImportError: #python3
except ImportError: # python3
import io
sys.path.insert(0, '.')
from resync.resource import Resource
from resync.resource_list import ResourceList
from resync.capability_list import CapabilityList
@ -16,49 +14,51 @@ from resync.sitemap import Sitemap, SitemapIndexError, SitemapParseError
import subprocess
def run_resync(args):
args.insert(0,'bin/resync')
args.insert(0, 'bin/resync')
proc = subprocess.Popen(args, stdout=subprocess.PIPE)
(out, err) = proc.communicate()
return(out)
class TestClientLinkOptions(unittest.TestCase):
def test01_no_links(self):
xml = run_resync(['--resourcelist',
'http://example.org/t','tests/testdata/dir1'])
'http://example.org/t', 'tests/testdata/dir1'])
rl = ResourceList()
rl.parse(fh=io.BytesIO(xml))
self.assertEqual( len(rl), 2 )
self.assertEqual( rl.link('describedby'), None )
self.assertEqual(len(rl), 2)
self.assertEqual(rl.link('describedby'), None)
def test02_resource_list_links(self):
xml = run_resync(['--resourcelist',
'--describedby-link=a',
'--sourcedescription-link=b', #will be ignored
'--sourcedescription-link=b', # will be ignored
'--capabilitylist-link=c',
'http://example.org/t','tests/testdata/dir1'])
'http://example.org/t', 'tests/testdata/dir1'])
rl = ResourceList()
rl.parse(fh=io.BytesIO(xml))
self.assertEqual( len(rl), 2 )
self.assertNotEqual( rl.link('describedby'), None )
self.assertEqual( rl.link('describedby')['href'], 'a' )
self.assertNotEqual( rl.link('up'), None )
self.assertEqual( rl.link('up')['href'], 'c' )
self.assertEqual(len(rl), 2)
self.assertNotEqual(rl.link('describedby'), None)
self.assertEqual(rl.link('describedby')['href'], 'a')
self.assertNotEqual(rl.link('up'), None)
self.assertEqual(rl.link('up')['href'], 'c')
def test03_capability_list_links(self):
xml = run_resync(['--capabilitylist=resourcelist=rl,changedump=cd',
'--describedby-link=a',
'--sourcedescription-link=b',
'--capabilitylist-link=c' ]) #will be ignored
'--capabilitylist-link=c']) # will be ignored
capl = CapabilityList()
capl.parse(fh=io.BytesIO(xml))
self.assertEqual( len(capl), 2 )
self.assertNotEqual( capl.link('describedby'), None )
self.assertEqual( capl.link('describedby')['href'], 'a' )
self.assertNotEqual( capl.link('up'), None )
self.assertEqual( capl.link('up')['href'], 'b' )
self.assertEqual(len(capl), 2)
self.assertNotEqual(capl.link('describedby'), None)
self.assertEqual(capl.link('describedby')['href'], 'a')
self.assertNotEqual(capl.link('up'), None)
self.assertEqual(capl.link('up')['href'], 'b')
if __name__ == '__main__':
if __name__ == '__main__':
suite = unittest.TestLoader().loadTestsFromTestCase(TestClientLinkOptions)
unittest.TextTestRunner(verbosity=2).run(suite)

15
tests/test_client_state.py
View File

@ -3,22 +3,23 @@ import os.path
import unittest
from resync.client_state import ClientState
class TestClientState(TestCase):
def test01_set_and_get(self):
cs = ClientState()
self.assertEqual( cs.status_file, '.resync-client-status.cfg')
cs.status_file = os.path.join(self.tmpdir,cs.status_file)
self.assertEqual(cs.status_file, '.resync-client-status.cfg')
cs.status_file = os.path.join(self.tmpdir, cs.status_file)
# Get state
site = 'https://this.site/'
self.assertEqual( cs.get_state(site), None )
self.assertEqual(cs.get_state(site), None)
cs.set_state(site, 123)
self.assertEqual( cs.get_state(site), 123 )
self.assertEqual(cs.get_state(site), 123)
cs.set_state(site, 456)
self.assertEqual( cs.get_state(site), 456 )
self.assertEqual(cs.get_state(site), 456)
cs.set_state(site)
self.assertEqual( cs.get_state(site), None )
self.assertEqual(cs.get_state(site), None)
if __name__ == '__main__':
suite = unittest.defaultTestLoader.loadTestsFromTestCase(TestClientUtils)
unittest.TextTestRunner(verbosity=2).run(suite)

88
tests/test_client_utils.py
View File

@ -4,71 +4,77 @@ import logging
import os.path
import re
import unittest
from resync.client_utils import init_logging,count_true_args,parse_links,parse_link,parse_capabilities,parse_capability_lists
from resync.client_utils import init_logging, count_true_args, parse_links, parse_link, parse_capabilities, parse_capability_lists
from resync.client import ClientFatalError
class TestClientUtils(TestCase):
def test01_init_logging(self):
#to_file=False, logfile=None, default_logfile='/tmp/resync.log',
# human=True, verbose=False, eval_mode=False,
# to_file=False, logfile=None, default_logfile='/tmp/resync.log',
# human=True, verbose=False, eval_mode=False,
# default_logger='client', extra_loggers=None):
tmplog = os.path.join(self.tmpdir,'tmp.log')
init_logging( to_file=True, default_logfile=tmplog, extra_loggers=['x1','x2'] )
tmplog = os.path.join(self.tmpdir, 'tmp.log')
init_logging(to_file=True, default_logfile=tmplog,
extra_loggers=['x1', 'x2'])
# check x1 and x2 set, not x3 (can tell by level)
self.assertTrue( logging.getLogger('x1').level, logging.DEBUG )
self.assertTrue( logging.getLogger('x2').level, logging.DEBUG )
self.assertEqual( logging.getLogger('x3').level, 0 )
self.assertTrue(logging.getLogger('x1').level, logging.DEBUG)
self.assertTrue(logging.getLogger('x2').level, logging.DEBUG)
self.assertEqual(logging.getLogger('x3').level, 0)
# write something, check goes to file
log = logging.getLogger('resync')
log.warning('PIGS MIGHT FLY')
logtxt = open(tmplog,'r').read()
self.assertTrue( re.search(r'WARNING \| PIGS MIGHT FLY', logtxt) )
logtxt = open(tmplog, 'r').read()
self.assertTrue(re.search(r'WARNING \| PIGS MIGHT FLY', logtxt))
def test02_count_true_args(self):
self.assertEqual( count_true_args(), 0 )
self.assertEqual( count_true_args(True), 1 )
self.assertEqual( count_true_args(False), 0 )
self.assertEqual( count_true_args(0,1,2,3), 3 )
self.assertEqual(count_true_args(), 0)
self.assertEqual(count_true_args(True), 1)
self.assertEqual(count_true_args(False), 0)
self.assertEqual(count_true_args(0, 1, 2, 3), 3)
def test03_parse_links(self):
self.assertEqual( parse_links( [] ), [] )
self.assertEqual( parse_links( ['u,h'] ), [{'href': 'h', 'rel': 'u'}] )
self.assertEqual( parse_links( ['u,h','v,i'] ), [{'href': 'h', 'rel': 'u'},{'href': 'i', 'rel': 'v'}] )
self.assertRaises( ClientFatalError, parse_links, 'xx' )
self.assertRaises( ClientFatalError, parse_links, ['u'] )
self.assertRaises( ClientFatalError, parse_links, ['u,h','u'] )
self.assertEqual(parse_links([]), [])
self.assertEqual(parse_links(['u,h']), [{'href': 'h', 'rel': 'u'}])
self.assertEqual(parse_links(['u,h', 'v,i']), [
{'href': 'h', 'rel': 'u'}, {'href': 'i', 'rel': 'v'}])
self.assertRaises(ClientFatalError, parse_links, 'xx')
self.assertRaises(ClientFatalError, parse_links, ['u'])
self.assertRaises(ClientFatalError, parse_links, ['u,h', 'u'])
def test04_parse_link(self):
# Input string of the form: rel,href,att1=val1,att2=val2
self.assertEqual( parse_link('u,h'), {'href': 'h', 'rel': 'u'} )
self.assertEqual( parse_link('u,h,a=b'), {'a': 'b', 'href': 'h', 'rel': 'u'} )
self.assertEqual( parse_link('u,h,a=b,c=d'), {'a': 'b', 'c': 'd', 'href': 'h', 'rel': 'u'} )
self.assertEqual( parse_link('u,h,a=b,a=d'), {'a': 'd', 'href': 'h', 'rel': 'u'} ) # desired??
self.assertRaises( ClientFatalError, parse_link, '' )
self.assertRaises( ClientFatalError, parse_link, 'u' )
self.assertRaises( ClientFatalError, parse_link, 'u,' )
self.assertRaises( ClientFatalError, parse_link, 'u,h,,' )
self.assertRaises( ClientFatalError, parse_link, 'u,h,a' )
self.assertRaises( ClientFatalError, parse_link, 'u,h,a=' )
self.assertRaises( ClientFatalError, parse_link, 'u,h,a=b,=c' )
self.assertEqual(parse_link('u,h'), {'href': 'h', 'rel': 'u'})
self.assertEqual(parse_link('u,h,a=b'), {
'a': 'b', 'href': 'h', 'rel': 'u'})
self.assertEqual(parse_link('u,h,a=b,c=d'), {
'a': 'b', 'c': 'd', 'href': 'h', 'rel': 'u'})
self.assertEqual(parse_link('u,h,a=b,a=d'), {
'a': 'd', 'href': 'h', 'rel': 'u'}) # desired??
self.assertRaises(ClientFatalError, parse_link, '')
self.assertRaises(ClientFatalError, parse_link, 'u')
self.assertRaises(ClientFatalError, parse_link, 'u,')
self.assertRaises(ClientFatalError, parse_link, 'u,h,,')
self.assertRaises(ClientFatalError, parse_link, 'u,h,a')
self.assertRaises(ClientFatalError, parse_link, 'u,h,a=')
self.assertRaises(ClientFatalError, parse_link, 'u,h,a=b,=c')
def test05_parse_capabilities(self):
# Input string of the form: cap_name=uri,cap_name=uri
# Input string of the form: cap_name=uri,cap_name=uri
# good
c = parse_capabilities( 'a=' )
self.assertEqual( len(c), 1 )
self.assertEqual( c['a'], '' )
c = parse_capabilities( 'a=b,c=' )
self.assertEqual( len(c), 2 )
self.assertEqual( c['a'], 'b' )
c = parse_capabilities('a=')
self.assertEqual(len(c), 1)
self.assertEqual(c['a'], '')
c = parse_capabilities('a=b,c=')
self.assertEqual(len(c), 2)
self.assertEqual(c['a'], 'b')
# bad
self.assertRaises( ClientFatalError, parse_capabilities, 'a' )
self.assertRaises( ClientFatalError, parse_capabilities, 'a=b,' )
self.assertRaises(ClientFatalError, parse_capabilities, 'a')
self.assertRaises(ClientFatalError, parse_capabilities, 'a=b,')
def test06_parse_capability_lists(self):
# Input string of the form: uri,uri
self.assertEqual( parse_capability_lists('a,b'), ['a','b'] )
self.assertEqual(parse_capability_lists('a,b'), ['a', 'b'])
if __name__ == '__main__':
suite = unittest.defaultTestLoader.loadTestsFromTestCase(TestClientUtils)

219
tests/test_dump.py
View File

@ -12,151 +12,158 @@ from resync.resource import Resource
from resync.resource_dump_manifest import ResourceDumpManifest
from resync.change_dump_manifest import ChangeDumpManifest
class TestDump(TestCase):
def test00_dump_zip_resource_list(self):
rl=ResourceDumpManifest()
rl.add( Resource('http://ex.org/a', length=7, path='tests/testdata/a') )
rl.add( Resource('http://ex.org/b', length=21, path='tests/testdata/b') )
d=Dump()
zipf=os.path.join(self.tmpdir,"test00_dump.zip")
d.write_zip(resources=rl,dumpfile=zipf) # named args
self.assertTrue( os.path.exists(zipf) )
self.assertTrue( zipfile.is_zipfile(zipf) )
zo=zipfile.ZipFile(zipf,'r')
self.assertEqual( len(zo.namelist()), 3 )
rl = ResourceDumpManifest()
rl.add(Resource('http://ex.org/a', length=7, path='tests/testdata/a'))
rl.add(Resource('http://ex.org/b', length=21, path='tests/testdata/b'))
d = Dump()
zipf = os.path.join(self.tmpdir, "test00_dump.zip")
d.write_zip(resources=rl, dumpfile=zipf) # named args
self.assertTrue(os.path.exists(zipf))
self.assertTrue(zipfile.is_zipfile(zipf))
zo = zipfile.ZipFile(zipf, 'r')
self.assertEqual(len(zo.namelist()), 3)
zo.close()
os.unlink(zipf)
def test01_dump_zip_change_list(self):
cl=ChangeDumpManifest()
cl.add( Resource('http://ex.org/a', length=7, path='tests/testdata/a', change="updated") )
cl.add( Resource('http://ex.org/b', length=21, path='tests/testdata/b', change="updated") )
d=Dump()
zipf=os.path.join(self.tmpdir,"test01_dump.zip")
d.write_zip(cl,zipf) # positional args
self.assertTrue( os.path.exists(zipf) )
self.assertTrue( zipfile.is_zipfile(zipf) )
zo=zipfile.ZipFile(zipf,'r')
self.assertEqual( len(zo.namelist()), 3 )
cl = ChangeDumpManifest()
cl.add(Resource('http://ex.org/a', length=7,
path='tests/testdata/a', change="updated"))
cl.add(Resource('http://ex.org/b', length=21,
path='tests/testdata/b', change="updated"))
d = Dump()
zipf = os.path.join(self.tmpdir, "test01_dump.zip")
d.write_zip(cl, zipf) # positional args
self.assertTrue(os.path.exists(zipf))
self.assertTrue(zipfile.is_zipfile(zipf))
zo = zipfile.ZipFile(zipf, 'r')
self.assertEqual(len(zo.namelist()), 3)
zo.close()
os.unlink(zipf)
def test02_dump_check_files(self):
cl=ChangeList()
cl.add( Resource('http://ex.org/a', length=7, path='tests/testdata/a', change="updated") )
cl.add( Resource('http://ex.org/b', length=21, path='tests/testdata/b', change="updated") )
d=Dump(resources=cl)
cl = ChangeList()
cl.add(Resource('http://ex.org/a', length=7,
path='tests/testdata/a', change="updated"))
cl.add(Resource('http://ex.org/b', length=21,
path='tests/testdata/b', change="updated"))
d = Dump(resources=cl)
self.assertTrue(d.check_files())
self.assertEqual(d.total_size, 28)
def test03_dump_multi_file_max_size(self):
rl=ResourceList()
for letter in map(chr,range(ord('a'),ord('l')+1)):
uri='http://ex.org/%s' % (letter)
fname='tests/testdata/a_to_z/%s' % (letter)
rl.add( Resource(uri, path=fname) )
self.assertEqual( len(rl), 12 )
#d=Dump(rl)
#tmpdir=tempfile.mkdtemp()
#tmpbase=os.path.join(tmpdir,'base')
#d.max_size=2000 # start new zip after size exceeds 2000 bytes
#n=d.write(tmpbase)
#self.assertEqual( n, 2, 'expect to write 2 dump files' )
#
rl = ResourceList()
for letter in map(chr, range(ord('a'), ord('l') + 1)):
uri = 'http://ex.org/%s' % (letter)
fname = 'tests/testdata/a_to_z/%s' % (letter)
rl.add(Resource(uri, path=fname))
self.assertEqual(len(rl), 12)
# d=Dump(rl)
# tmpdir=tempfile.mkdtemp()
# tmpbase=os.path.join(tmpdir,'base')
# d.max_size=2000 # start new zip after size exceeds 2000 bytes
# n=d.write(tmpbase)
# self.assertEqual( n, 2, 'expect to write 2 dump files' )
#
# Now repeat with large size limit but small number of files limit
d2=Dump(rl)
tmpbase=os.path.join(self.tmpdir,'test03_')
d2.max_files=4
n=d2.write(tmpbase)
self.assertEqual( n, 3, 'expect to write 3 dump files' )
self.assertTrue( os.path.isfile(tmpbase+'00000.zip') )
self.assertTrue( os.path.isfile(tmpbase+'00001.zip') )
self.assertTrue( os.path.isfile(tmpbase+'00002.zip') )
d2 = Dump(rl)
tmpbase = os.path.join(self.tmpdir, 'test03_')
d2.max_files = 4
n = d2.write(tmpbase)
self.assertEqual(n, 3, 'expect to write 3 dump files')
self.assertTrue(os.path.isfile(tmpbase + '00000.zip'))
self.assertTrue(os.path.isfile(tmpbase + '00001.zip'))
self.assertTrue(os.path.isfile(tmpbase + '00002.zip'))
# Look at the first file in detail
zipf=tmpbase+'00000.zip'
zo=zipfile.ZipFile(zipf,'r')
self.assertEqual( zo.namelist(), ['manifest.xml','a','b','c','d'] )
#self.assertEqual( zo.getinfo('manifest.xml').file_size, 470 )
self.assertEqual( zo.getinfo('a').file_size, 9 )
self.assertEqual( zo.getinfo('b').file_size, 1116 )
self.assertEqual( zo.getinfo('c').file_size, 32 )
self.assertEqual( zo.getinfo('d').file_size, 13 )
zipf = tmpbase + '00000.zip'
zo = zipfile.ZipFile(zipf, 'r')
self.assertEqual(zo.namelist(), ['manifest.xml', 'a', 'b', 'c', 'd'])
# self.assertEqual( zo.getinfo('manifest.xml').file_size, 470 )
self.assertEqual(zo.getinfo('a').file_size, 9)
self.assertEqual(zo.getinfo('b').file_size, 1116)
self.assertEqual(zo.getinfo('c').file_size, 32)
self.assertEqual(zo.getinfo('d').file_size, 13)
zo.close()
os.unlink(zipf)
# Check second and third files have expected contents
zipf=tmpbase+'00001.zip'
zo=zipfile.ZipFile(zipf,'r')
self.assertEqual( zo.namelist(), ['manifest.xml','e','f','g','h'] )
zipf = tmpbase + '00001.zip'
zo = zipfile.ZipFile(zipf, 'r')
self.assertEqual(zo.namelist(), ['manifest.xml', 'e', 'f', 'g', 'h'])
zo.close()
os.unlink(zipf)
zipf=tmpbase+'00002.zip'
zo=zipfile.ZipFile(zipf,'r')
self.assertEqual( zo.namelist(), ['manifest.xml','i','j','k','l'] )
zipf = tmpbase + '00002.zip'
zo = zipfile.ZipFile(zipf, 'r')
self.assertEqual(zo.namelist(), ['manifest.xml', 'i', 'j', 'k', 'l'])
zo.close()
os.unlink(zipf)
def test04_dump_multi_file_max_size(self):
rl=ResourceList()
for letter in map(chr,range(ord('a'),ord('l')+1)):
uri='http://ex.org/%s' % (letter)
fname='tests/testdata/a_to_z/%s' % (letter)
rl.add( Resource(uri, path=fname) )
self.assertEqual( len(rl), 12 )
d2=Dump(rl)
tmpbase=os.path.join(self.tmpdir,'test0f_')
d2.max_size=2000
n=d2.write(tmpbase)
self.assertEqual( n, 2, 'expect to write 2 dump files' )
self.assertTrue( os.path.isfile(tmpbase+'00000.zip') )
self.assertTrue( os.path.isfile(tmpbase+'00001.zip') )
rl = ResourceList()
for letter in map(chr, range(ord('a'), ord('l') + 1)):
uri = 'http://ex.org/%s' % (letter)
fname = 'tests/testdata/a_to_z/%s' % (letter)
rl.add(Resource(uri, path=fname))
self.assertEqual(len(rl), 12)
d2 = Dump(rl)
tmpbase = os.path.join(self.tmpdir, 'test0f_')
d2.max_size = 2000
n = d2.write(tmpbase)
self.assertEqual(n, 2, 'expect to write 2 dump files')
self.assertTrue(os.path.isfile(tmpbase + '00000.zip'))
self.assertTrue(os.path.isfile(tmpbase + '00001.zip'))
# Look at the first file in detail
zipf=tmpbase+'00000.zip'
zo=zipfile.ZipFile(zipf,'r')
self.assertEqual( zo.namelist(), ['manifest.xml','a','b','c','d','e','f'] )
#self.assertEqual( zo.getinfo('manifest.xml').file_size, 470 )
self.assertEqual( zo.getinfo('a').file_size, 9 )
self.assertEqual( zo.getinfo('b').file_size, 1116 )
self.assertEqual( zo.getinfo('c').file_size, 32 )
self.assertEqual( zo.getinfo('d').file_size, 13 )
self.assertEqual( zo.getinfo('e').file_size, 20 )
self.assertEqual( zo.getinfo('f').file_size, 1625 )
zipf = tmpbase + '00000.zip'
zo = zipfile.ZipFile(zipf, 'r')
self.assertEqual(
zo.namelist(), ['manifest.xml', 'a', 'b', 'c', 'd', 'e', 'f'])
# self.assertEqual( zo.getinfo('manifest.xml').file_size, 470 )
self.assertEqual(zo.getinfo('a').file_size, 9)
self.assertEqual(zo.getinfo('b').file_size, 1116)
self.assertEqual(zo.getinfo('c').file_size, 32)
self.assertEqual(zo.getinfo('d').file_size, 13)
self.assertEqual(zo.getinfo('e').file_size, 20)
self.assertEqual(zo.getinfo('f').file_size, 1625)
zo.close()
os.unlink(zipf)
# Check second and third files have expected contents
zipf=tmpbase+'00001.zip'
zo=zipfile.ZipFile(zipf,'r')
self.assertEqual( zo.namelist(), ['manifest.xml','g','h','i','j','k','l'] )
zipf = tmpbase + '00001.zip'
zo = zipfile.ZipFile(zipf, 'r')
self.assertEqual(
zo.namelist(), ['manifest.xml', 'g', 'h', 'i', 'j', 'k', 'l'])
zo.close()
os.unlink(zipf)
def test10_no_path(self):
rl=ResourceList()
rl.add( Resource('http://ex.org/a', length=7, path='tests/testdata/a') )
rl.add( Resource('http://ex.org/b', length=21 ) )
d=Dump(rl)
self.assertRaises( DumpError, d.check_files )
rl = ResourceList()
rl.add(Resource('http://ex.org/a', length=7, path='tests/testdata/a'))
rl.add(Resource('http://ex.org/b', length=21))
d = Dump(rl)
self.assertRaises(DumpError, d.check_files)
def test11_bad_size(self):
rl=ResourceList()
rl.add( Resource('http://ex.org/a', length=9999, path='tests/testdata/a') )
d=Dump(rl)
self.assertTrue( d.check_files(check_length=False) )
self.assertRaises( DumpError, d.check_files )
rl = ResourceList()
rl.add(Resource('http://ex.org/a', length=9999, path='tests/testdata/a'))
d = Dump(rl)
self.assertTrue(d.check_files(check_length=False))
self.assertRaises(DumpError, d.check_files)
def test10_no_path(self):
rl=ResourceList()
rl.add( Resource('http://ex.org/a', length=7, path='tests/testdata/a') )
rl.add( Resource('http://ex.org/b', length=21 ) )
d=Dump(rl)
self.assertRaises( DumpError, d.check_files )
rl = ResourceList()
rl.add(Resource('http://ex.org/a', length=7, path='tests/testdata/a'))
rl.add(Resource('http://ex.org/b', length=21))
d = Dump(rl)
self.assertRaises(DumpError, d.check_files)
def test11_bad_size(self):
rl=ResourceList()
rl.add( Resource('http://ex.org/a', length=9999, path='tests/testdata/a') )
d=Dump(rl)
self.assertTrue( d.check_files(check_length=False) )
self.assertRaises( DumpError, d.check_files )
rl = ResourceList()
rl.add(Resource('http://ex.org/a', length=9999, path='tests/testdata/a'))
d = Dump(rl)
self.assertTrue(d.check_files(check_length=False))
self.assertRaises(DumpError, d.check_files)
if __name__ == '__main__':
suite = unittest.defaultTestLoader.loadTestsFromTestCase(TestDump)

878
tests/test_examples_from_spec.py
View File

File diff suppressed because it is too large Load Diff

111
tests/test_explorer.py
View File

@ -21,23 +21,23 @@ class TestExplorer(unittest.TestCase):
def test01_create(self):
# dumb test that we can create Exporer object
e = Explorer()
self.assertTrue( e )
self.assertTrue(e)
def test01_xresource(self):
x = XResource( uri='abc', acceptable_capabilities=[1,2],
checks=[3,4], context='http://example.org/def' )
self.assertEqual( x.uri, 'http://example.org/abc' )
self.assertEqual( x.acceptable_capabilities, [1,2] )
self.assertEqual( x.checks, [3,4] )
x = XResource(uri='abc', acceptable_capabilities=[1, 2],
checks=[3, 4], context='http://example.org/def')
self.assertEqual(x.uri, 'http://example.org/abc')
self.assertEqual(x.acceptable_capabilities, [1, 2])
self.assertEqual(x.checks, [3, 4])
def test02_head_response(self):
hr = HeadResponse()
self.assertEqual( hr.status_code, None )
self.assertEqual( len(hr.headers), 0)
self.assertEqual(hr.status_code, None)
self.assertEqual(len(hr.headers), 0)
def test03_explorer_quit(self):
eq = ExplorerQuit()
self.assertTrue( isinstance(eq, Exception) )
self.assertTrue(isinstance(eq, Exception))
def test04_explore(self):
e = Explorer()
@ -46,81 +46,90 @@ class TestExplorer(unittest.TestCase):
# IOError generated from attempt to read stdin
e.fake_input = 'q'
e.explore()
self.assertTrue( re.search(r'resync-explorer done', capturer.result) )
self.assertTrue(re.search(r'resync-explorer done', capturer.result))
def test05_explore_uri(self):
e = Explorer()
with capture_stdout() as capturer:
e.fake_input = 'q'
self.assertRaises( ExplorerQuit, e.explore_uri,
XResource('tests/testdata/explore1/caps1.xml') )
self.assertTrue( re.search(r'Reading tests/testdata/explore1/caps1.xml',
capturer.result) )
self.assertTrue( re.search(r'Parsed capabilitylist document with 4 entries:',
capturer.result) )
self.assertRaises(ExplorerQuit, e.explore_uri,
XResource('tests/testdata/explore1/caps1.xml'))
self.assertTrue(re.search(r'Reading tests/testdata/explore1/caps1.xml',
capturer.result))
self.assertTrue(re.search(r'Parsed capabilitylist document with 4 entries:',
capturer.result))
def test06_explore_show_summary(self):
e = Explorer()
# file that exists with matching
with capture_stdout() as capturer:
e.explore_show_summary( list=CapabilityList() )
self.assertTrue( re.search(r'Parsed \(unknown capability\) document with 0 entries:',
capturer.result) )
e.explore_show_summary(list=CapabilityList())
self.assertTrue(re.search(r'Parsed \(unknown capability\) document with 0 entries:',
capturer.result))
# dummy capabilities object and display
cl = CapabilityList()
cl.add( Resource('uri:resourcelist') )
cl.add( Resource('uri:changelist') )
cl.add(Resource('uri:resourcelist'))
cl.add(Resource('uri:changelist'))
with capture_stdout() as capturer:
e.explore_show_summary(cl,False,[])
self.assertTrue( re.search(r'Parsed \(unknown capability\) document with 2 entries:',capturer.result) )
self.assertTrue( re.search(r'\[1\] uri:changelist',capturer.result) )
self.assertTrue( re.search(r'\[2\] uri:resourcelist',capturer.result) )
e.explore_show_summary(cl, False, [])
self.assertTrue(re.search(
r'Parsed \(unknown capability\) document with 2 entries:', capturer.result))
self.assertTrue(re.search(r'\[1\] uri:changelist', capturer.result))
self.assertTrue(re.search(r'\[2\] uri:resourcelist', capturer.result))
def test07_explore_show_head(self):
e = Explorer()
# file that exists with matching
with capture_stdout() as capturer:
e.explore_show_head( uri='tests/testdata/dir1/file_a',
check_headers={ 'content-length': 20,
'unknown': 'abc' } )
self.assertTrue( re.search(r'HEAD tests/testdata/dir1/file_a', capturer.result) )
self.assertTrue( re.search(r'content-length: 20 MATCHES EXPECTED VALUE', capturer.result) )
e.explore_show_head(uri='tests/testdata/dir1/file_a',
check_headers={'content-length': 20,
'unknown': 'abc'})
self.assertTrue(
re.search(r'HEAD tests/testdata/dir1/file_a', capturer.result))
self.assertTrue(
re.search(r'content-length: 20 MATCHES EXPECTED VALUE', capturer.result))
# same file, bad header check
with capture_stdout() as capturer:
e.explore_show_head( 'tests/testdata/dir1/file_a',
check_headers={ 'content-length': 99 } )
self.assertTrue( re.search(r'HEAD tests/testdata/dir1/file_a', capturer.result) )
self.assertTrue( re.search(r'content-length: 20 EXPECTED 99', capturer.result) )
e.explore_show_head('tests/testdata/dir1/file_a',
check_headers={'content-length': 99})
self.assertTrue(
re.search(r'HEAD tests/testdata/dir1/file_a', capturer.result))
self.assertTrue(
re.search(r'content-length: 20 EXPECTED 99', capturer.result))
# file that does not exist
with capture_stdout() as capturer:
e.explore_show_head( 'tests/testdata/does_not_exist' )
self.assertTrue( re.search(r'HEAD tests/testdata/does_not_exist', capturer.result) )
self.assertTrue( re.search(r'status: 404', capturer.result) )
e.explore_show_head('tests/testdata/does_not_exist')
self.assertTrue(
re.search(r'HEAD tests/testdata/does_not_exist', capturer.result))
self.assertTrue(re.search(r'status: 404', capturer.result))
def test08_head_on_file(self):
e = Explorer()
r1 = e.head_on_file('tests/testdata/does_not_exist')
self.assertEqual( r1.status_code, '404' )
self.assertEqual(r1.status_code, '404')
r2 = e.head_on_file('tests/testdata/dir1/file_a')
self.assertEqual( r2.status_code, '200' )
self.assertTrue( re.match(r'^\d\d\d\d\-\d\d\-\d\d', r2.headers['last-modified']) )
self.assertEqual( r2.headers['content-length'], 20 )
self.assertEqual(r2.status_code, '200')
self.assertTrue(re.match(r'^\d\d\d\d\-\d\d\-\d\d',
r2.headers['last-modified']))
self.assertEqual(r2.headers['content-length'], 20)
def test09_allowed_entries(self):
e = Explorer()
self.assertEqual( e.allowed_entries('capabilitylistindex'), [] )
self.assertEqual( e.allowed_entries('resourcelistindex'), ['resourcelist'] )
self.assertEqual( e.allowed_entries('changelist-archive'), ['changelist'] )
self.assertEqual( e.allowed_entries('description'),['capabilitylist'] )
self.assertEqual( len(e.allowed_entries('capabilitylist')), 8 )
self.assertEqual( e.allowed_entries('unknown'),[] )
self.assertEqual(e.allowed_entries('capabilitylistindex'), [])
self.assertEqual(e.allowed_entries(
'resourcelistindex'), ['resourcelist'])
self.assertEqual(e.allowed_entries(
'changelist-archive'), ['changelist'])
self.assertEqual(e.allowed_entries('description'), ['capabilitylist'])
self.assertEqual(len(e.allowed_entries('capabilitylist')), 8)
self.assertEqual(e.allowed_entries('unknown'), [])
def test10_expand_relative_uri(self):
e = Explorer()
with capture_stdout() as capturer:
uri = e.expand_relative_uri('https://example.org/ctx','abc')
self.assertEqual( uri, 'https://example.org/abc' )
self.assertTrue( re.search(r'expanded relative URI', capturer.result) )
uri = e.expand_relative_uri('https://example.org/ctx', 'abc')
self.assertEqual(uri, 'https://example.org/abc')
self.assertTrue(re.search(r'expanded relative URI', capturer.result))
if __name__ == '__main__':
suite = unittest.TestLoader().loadTestsFromTestCase(TestExplorer)

67
tests/test_list_base.py
View File

@ -3,11 +3,11 @@ from tests.testcase_with_tmpdir import TestCase
import sys
import os.path
import unittest
try: #python2
try: # python2
# Must try this first as io also exists in python2
# but in the wrong one!
import StringIO as io
except ImportError: #python3
except ImportError: # python3
import io
from resync.resource import Resource
@ -16,38 +16,39 @@ from resync.sitemap import Sitemap, SitemapIndexError
# etree gives ParseError in 2.7, ExpatError in 2.6
etree_error_class = None
if (sys.version_info < (2,7)):
if (sys.version_info < (2, 7)):
from xml.parsers.expat import ExpatError
etree_error_class = ExpatError
else:
from xml.etree.ElementTree import ParseError
etree_error_class = ParseError
class TestListBase(TestCase):
def test01_len_count(self):
# count sets explicit number of resources, len(resources) not used
lb = ListBase()
self.assertEqual( len(lb), 0 )
self.assertEqual(len(lb), 0)
lb.add(Resource('a'))
self.assertEqual( len(lb), 1 )
lb = ListBase( count=100 )
self.assertEqual( len(lb), 100 )
self.assertEqual(len(lb), 1)
lb = ListBase(count=100)
self.assertEqual(len(lb), 100)
def test02_print(self):
lb = ListBase()
lb.add( Resource(uri='a',lastmod='2001-01-01',length=1234) )
lb.add( Resource(uri='b',lastmod='2002-02-02',length=56789) )
lb.add( Resource(uri='c',lastmod='2003-03-03',length=0) )
lb.md['from']=None #avoid now being added
lb.add(Resource(uri='a', lastmod='2001-01-01', length=1234))
lb.add(Resource(uri='b', lastmod='2002-02-02', length=56789))
lb.add(Resource(uri='c', lastmod='2003-03-03', length=0))
lb.md['from'] = None # avoid now being added
x = lb.as_xml()
self.assertEqual( x, '<?xml version=\'1.0\' encoding=\'UTF-8\'?>\n<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9" xmlns:rs="http://www.openarchives.org/rs/terms/"><rs:md capability="unknown" /><url><loc>a</loc><lastmod>2001-01-01T00:00:00Z</lastmod><rs:md length="1234" /></url><url><loc>b</loc><lastmod>2002-02-02T00:00:00Z</lastmod><rs:md length="56789" /></url><url><loc>c</loc><lastmod>2003-03-03T00:00:00Z</lastmod><rs:md length="0" /></url></urlset>' )
self.assertEqual(x, '<?xml version=\'1.0\' encoding=\'UTF-8\'?>\n<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9" xmlns:rs="http://www.openarchives.org/rs/terms/"><rs:md capability="unknown" /><url><loc>a</loc><lastmod>2001-01-01T00:00:00Z</lastmod><rs:md length="1234" /></url><url><loc>b</loc><lastmod>2002-02-02T00:00:00Z</lastmod><rs:md length="56789" /></url><url><loc>c</loc><lastmod>2003-03-03T00:00:00Z</lastmod><rs:md length="0" /></url></urlset>')
def test03_read(self):
# just does parse
lb=ListBase()
lb = ListBase()
lb.read(uri='tests/testdata/unknown/unknown1.xml')
self.assertEqual( len(lb.resources), 2 )
self.assertEqual(len(lb.resources), 2)
def test04_parse(self):
xml = '<?xml version=\'1.0\' encoding=\'UTF-8\'?>\n\
@ -57,38 +58,38 @@ class TestListBase(TestCase):
<url><loc>/tmp/rs_test/src/file_b</loc><lastmod>2012-03-14T18:37:36Z</lastmod><rs:md length="32" /></url>\
</urlset>'
# parse from string
lb1=ListBase()
lb1 = ListBase()
lb1.parse(str_data=xml)
self.assertEqual( len(lb1.resources), 2, 'got 2 resources')
self.assertEqual(len(lb1.resources), 2, 'got 2 resources')
# parse from fh
lb2=ListBase()
lb2 = ListBase()
lb2.parse(fh=io.StringIO(xml))
self.assertEqual( len(lb2.resources), 2, 'got 2 resources')
self.assertEqual(len(lb2.resources), 2, 'got 2 resources')
# parse from string (LEGACY parameter name, to be removed)
lb3=ListBase()
lb3 = ListBase()
lb3.parse(str=xml)
self.assertEqual( len(lb3.resources), 2, 'got 2 resources')
self.assertEqual(len(lb3.resources), 2, 'got 2 resources')
# file that doesn't exits
lb4 = ListBase()
self.assertRaises( Exception, lb4.parse,
uri='tests/testdata/does_not_exist' )
self.assertRaises(Exception, lb4.parse,
uri='tests/testdata/does_not_exist')
# nothing
self.assertRaises( Exception, lb4.parse )
self.assertRaises(Exception, lb4.parse)
def test04_write(self):
lb = ListBase(capability_name = 'special')
lb.add( Resource(uri='http://example.org/lemon') )
lb.add( Resource(uri='http://example.org/orange') )
basename = os.path.join(self.tmpdir,'lb.xml')
lb = ListBase(capability_name='special')
lb.add(Resource(uri='http://example.org/lemon'))
lb.add(Resource(uri='http://example.org/orange'))
basename = os.path.join(self.tmpdir, 'lb.xml')
lb.write(basename=basename)
self.assertTrue( os.path.exists(basename) )
self.assertTrue(os.path.exists(basename))
# and now parse back
fh = open(basename,'r')
lb2 = ListBase(capability_name = 'special')
fh = open(basename, 'r')
lb2 = ListBase(capability_name='special')
lb2.parse(fh=fh)
self.assertEqual( lb2.capability, 'special' )
self.assertEqual( len(lb2), 2 )
self.assertEqual(lb2.capability, 'special')
self.assertEqual(len(lb2), 2)
if __name__ == '__main__':
if __name__ == '__main__':
suite = unittest.TestLoader().loadTestsFromTestCase(TestListBase)
unittest.TextTestRunner(verbosity=2).run(suite)

130
tests/test_list_base_with_index.py
View File

@ -1,11 +1,11 @@
import re
import sys
import unittest
try: #python2
try: # python2
# Must try this first as io also exists in python2
# but in the wrong one!
import StringIO as io
except ImportError: #python3
except ImportError: # python3
import io
from resync.resource import Resource
@ -14,118 +14,122 @@ from resync.sitemap import Sitemap, SitemapIndexError
# etree gives ParseError in 2.7, ExpatError in 2.6
etree_error_class = None
if (sys.version_info < (2,7)):
if (sys.version_info < (2, 7)):
from xml.parsers.expat import ExpatError
etree_error_class = ExpatError
else:
from xml.etree.ElementTree import ParseError
etree_error_class = ParseError
class TestListBaseWithIndex(unittest.TestCase):
def test01_print(self):
lb = ListBaseWithIndex()
lb.add( Resource(uri='a',lastmod='2001-01-01',length=1234) )
lb.add( Resource(uri='b',lastmod='2002-02-02',length=56789) )
lb.add( Resource(uri='c',lastmod='2003-03-03',length=0) )
lb.md['from']=None #avoid now being added
self.assertEqual( lb.as_xml(), '<?xml version=\'1.0\' encoding=\'UTF-8\'?>\n<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9" xmlns:rs="http://www.openarchives.org/rs/terms/"><rs:md capability="unknown" /><url><loc>a</loc><lastmod>2001-01-01T00:00:00Z</lastmod><rs:md length="1234" /></url><url><loc>b</loc><lastmod>2002-02-02T00:00:00Z</lastmod><rs:md length="56789" /></url><url><loc>c</loc><lastmod>2003-03-03T00:00:00Z</lastmod><rs:md length="0" /></url></urlset>' )
lb.add(Resource(uri='a', lastmod='2001-01-01', length=1234))
lb.add(Resource(uri='b', lastmod='2002-02-02', length=56789))
lb.add(Resource(uri='c', lastmod='2003-03-03', length=0))
lb.md['from'] = None # avoid now being added
self.assertEqual(lb.as_xml(), '<?xml version=\'1.0\' encoding=\'UTF-8\'?>\n<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9" xmlns:rs="http://www.openarchives.org/rs/terms/"><rs:md capability="unknown" /><url><loc>a</loc><lastmod>2001-01-01T00:00:00Z</lastmod><rs:md length="1234" /></url><url><loc>b</loc><lastmod>2002-02-02T00:00:00Z</lastmod><rs:md length="56789" /></url><url><loc>c</loc><lastmod>2003-03-03T00:00:00Z</lastmod><rs:md length="0" /></url></urlset>')
def test02_print_iter(self):
r = [ Resource(uri='a',lastmod='2001-01-01',length=1234),
Resource(uri='b',lastmod='2002-02-02',length=56789),
Resource(uri='c',lastmod='2003-03-03',length=0) ]
r = [Resource(uri='a', lastmod='2001-01-01', length=1234),
Resource(uri='b', lastmod='2002-02-02', length=56789),
Resource(uri='c', lastmod='2003-03-03', length=0)]
# without setting count will barf on len() attempt
lb = ListBaseWithIndex( resources=iter(r) )
self.assertRaises( TypeError, lb.as_xml )
# set explicit count larger than max_sitemap_entiries and as_xml will throw exception
lb = ListBaseWithIndex( resources=iter(r), count=3 )
lb = ListBaseWithIndex(resources=iter(r))
self.assertRaises(TypeError, lb.as_xml)
# set explicit count larger than max_sitemap_entiries and as_xml will
# throw exception
lb = ListBaseWithIndex(resources=iter(r), count=3)
lb.max_sitemap_entries = 2
self.assertRaises( ListBaseIndexError, lb.as_xml )
self.assertRaises(ListBaseIndexError, lb.as_xml)
# set explicit count and all will be OK
lb = ListBaseWithIndex( resources=iter(r), count=3 )
lb.md['from']=None #avoid now being added
self.assertEqual( lb.as_xml(), '<?xml version=\'1.0\' encoding=\'UTF-8\'?>\n<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9" xmlns:rs="http://www.openarchives.org/rs/terms/"><rs:md capability="unknown" /><url><loc>a</loc><lastmod>2001-01-01T00:00:00Z</lastmod><rs:md length="1234" /></url><url><loc>b</loc><lastmod>2002-02-02T00:00:00Z</lastmod><rs:md length="56789" /></url><url><loc>c</loc><lastmod>2003-03-03T00:00:00Z</lastmod><rs:md length="0" /></url></urlset>' )
lb = ListBaseWithIndex(resources=iter(r), count=3)
lb.md['from'] = None # avoid now being added
self.assertEqual(lb.as_xml(), '<?xml version=\'1.0\' encoding=\'UTF-8\'?>\n<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9" xmlns:rs="http://www.openarchives.org/rs/terms/"><rs:md capability="unknown" /><url><loc>a</loc><lastmod>2001-01-01T00:00:00Z</lastmod><rs:md length="1234" /></url><url><loc>b</loc><lastmod>2002-02-02T00:00:00Z</lastmod><rs:md length="56789" /></url><url><loc>c</loc><lastmod>2003-03-03T00:00:00Z</lastmod><rs:md length="0" /></url></urlset>')
def test03_parse_2(self):
xml='<?xml version=\'1.0\' encoding=\'UTF-8\'?>\n\
xml = '<?xml version=\'1.0\' encoding=\'UTF-8\'?>\n\
<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9" xmlns:rs="http://www.openarchives.org/rs/terms/">\
<rs:md capability="unknown" from="2013-02-12T14:09:00Z" />\
<url><loc>/tmp/rs_test/src/file_a</loc><lastmod>2012-03-14T18:37:36Z</lastmod><rs:md length="12" /></url>\
<url><loc>/tmp/rs_test/src/file_b</loc><lastmod>2012-03-14T18:37:36Z</lastmod><rs:md length="32" /></url>\
</urlset>'
lb=ListBaseWithIndex()
lb = ListBaseWithIndex()
lb.parse(fh=io.StringIO(xml))
self.assertEqual( len(lb.resources), 2, 'got 2 resources')
self.assertEqual(len(lb.resources), 2, 'got 2 resources')
def test16_as_xml(self):
r = [ Resource(uri='a',lastmod='2014-04-14',length=14),
Resource(uri='b',lastmod='2015-05-15',length=15),
Resource(uri='c',lastmod='2016-06-16',length=16) ]
lb=ListBaseWithIndex( resources=r )
r = [Resource(uri='a', lastmod='2014-04-14', length=14),
Resource(uri='b', lastmod='2015-05-15', length=15),
Resource(uri='c', lastmod='2016-06-16', length=16)]
lb = ListBaseWithIndex(resources=r)
lb.max_sitemap_entries = 3
# One file
xml = lb.as_xml()
self.assertTrue( re.search(r'<urlset ',xml) )
self.assertTrue( re.search(r'<loc>a</loc>',xml) )
self.assertTrue( re.search(r'<loc>b</loc>',xml) )
self.assertTrue( re.search(r'<loc>c</loc>',xml) )
self.assertTrue(re.search(r'<urlset ', xml))
self.assertTrue(re.search(r'<loc>a</loc>', xml))
self.assertTrue(re.search(r'<loc>b</loc>', xml))
self.assertTrue(re.search(r'<loc>c</loc>', xml))
# Needs multifile bit not allowed
lb.max_sitemap_entries = 1
self.assertRaises( ListBaseIndexError, lb.as_xml )
self.assertRaises(ListBaseIndexError, lb.as_xml)
# Allow multifile...
xml = lb.as_xml( allow_multifile=True )
self.assertTrue( re.search(r'<sitemapindex', xml) )
self.assertTrue( re.search(r'<loc>/tmp/sitemap00001.xml</loc>', xml) )
self.assertTrue( re.search(r'<loc>/tmp/sitemap00002.xml</loc>', xml) )
self.assertFalse( re.search(r'<loc>/tmp/sitemap00003.xml</loc>', xml) )
xml = lb.as_xml(allow_multifile=True)
self.assertTrue(re.search(r'<sitemapindex', xml))
self.assertTrue(re.search(r'<loc>/tmp/sitemap00001.xml</loc>', xml))
self.assertTrue(re.search(r'<loc>/tmp/sitemap00002.xml</loc>', xml))
self.assertFalse(re.search(r'<loc>/tmp/sitemap00003.xml</loc>', xml))
def test17_as_xml_index(self):
r = [ Resource(uri='a',lastmod='2006-01-01',length=12),
Resource(uri='b',lastmod='2007-02-02',length=34),
Resource(uri='c',lastmod='2008-03-03',length=56) ]
lb=ListBaseWithIndex( resources=r )
r = [Resource(uri='a', lastmod='2006-01-01', length=12),
Resource(uri='b', lastmod='2007-02-02', length=34),
Resource(uri='c', lastmod='2008-03-03', length=56)]
lb = ListBaseWithIndex(resources=r)
lb.max_sitemap_entries = 2
xml = lb.as_xml_index()
self.assertTrue( re.search(r'<loc>/tmp/sitemap00001.xml</loc>', xml) )
self.assertFalse( re.search(r'<loc>/tmp/sitemap00002.xml</loc>', xml) )
self.assertTrue(re.search(r'<loc>/tmp/sitemap00001.xml</loc>', xml))
self.assertFalse(re.search(r'<loc>/tmp/sitemap00002.xml</loc>', xml))
# Index not required
lb.max_sitemap_entries = 3
self.assertRaises( ListBaseIndexError, lb.as_xml_index )
self.assertRaises(ListBaseIndexError, lb.as_xml_index)
def test18_as_xml_part(self):
r = [ Resource(uri='a',lastmod='2006-01-01',length=12),
Resource(uri='b',lastmod='2007-02-02',length=34),
Resource(uri='c',lastmod='2008-03-03',length=56) ]
lb=ListBaseWithIndex( resources=r )
r = [Resource(uri='a', lastmod='2006-01-01', length=12),
Resource(uri='b', lastmod='2007-02-02', length=34),
Resource(uri='c', lastmod='2008-03-03', length=56)]
lb = ListBaseWithIndex(resources=r)
# Allow unlimited entries, part makes no sense
lb.max_sitemap_entries = None
self.assertRaises( ListBaseIndexError, lb.as_xml_part )
self.assertRaises(ListBaseIndexError, lb.as_xml_part)
# Request after end
lb.max_sitemap_entries = 1
self.assertRaises( ListBaseIndexError, lb.as_xml_part, part_number=9 )
self.assertRaises(ListBaseIndexError, lb.as_xml_part, part_number=9)
# Allow only 1 entry
lb.max_sitemap_entries = 1
xml = lb.as_xml_part( part_number=1 )
self.assertFalse( re.search(r'<loc>a</loc>',xml) )
self.assertTrue( re.search(r'<loc>b</loc>',xml) )
self.assertFalse( re.search(r'<loc>c</loc>',xml) )
xml = lb.as_xml_part(part_number=1)
self.assertFalse(re.search(r'<loc>a</loc>', xml))
self.assertTrue(re.search(r'<loc>b</loc>', xml))
self.assertFalse(re.search(r'<loc>c</loc>', xml))
# Request truncated
lb.max_sitemap_entries = 2
xml = lb.as_xml_part( part_number=1 )
self.assertFalse( re.search(r'<loc>a</loc>',xml) )
self.assertFalse( re.search(r'<loc>b</loc>',xml) )
self.assertTrue( re.search(r'<loc>c</loc>',xml) )
xml = lb.as_xml_part(part_number=1)
self.assertFalse(re.search(r'<loc>a</loc>', xml))
self.assertFalse(re.search(r'<loc>b</loc>', xml))
self.assertTrue(re.search(r'<loc>c</loc>', xml))
def test20_index_as_xml(self):
# Check XML for empty case
lb=ListBaseWithIndex()
self.assertEqual( lb.index_as_xml(), '<?xml version=\'1.0\' encoding=\'UTF-8\'?>\n<sitemapindex xmlns="http://www.sitemaps.org/schemas/sitemap/0.9" xmlns:rs="http://www.openarchives.org/rs/terms/"><rs:md capability="unknown" /></sitemapindex>' )
lb = ListBaseWithIndex()
self.assertEqual(lb.index_as_xml(
), '<?xml version=\'1.0\' encoding=\'UTF-8\'?>\n<sitemapindex xmlns="http://www.sitemaps.org/schemas/sitemap/0.9" xmlns:rs="http://www.openarchives.org/rs/terms/"><rs:md capability="unknown" /></sitemapindex>')
# Add a resource and make sure we find that
lb.add( Resource(uri='a',lastmod='2001-01-01',length=1234) )
lb.add(Resource(uri='a', lastmod='2001-01-01', length=1234))
xml = lb.index_as_xml()
self.assertTrue( re.search(r'<loc>a</loc><lastmod>2001-01-01T00:00:00Z</lastmod>',xml) )
self.assertTrue(
re.search(r'<loc>a</loc><lastmod>2001-01-01T00:00:00Z</lastmod>', xml))
if __name__ == '__main__':
if __name__ == '__main__':
suite = unittest.TestLoader().loadTestsFromTestCase(TestListBaseWithIndex)
unittest.TextTestRunner(verbosity=2).run(suite)

4
tests/test_mapper.py
View File

@ -25,8 +25,8 @@ class TestMapper(unittest.TestCase):
self.assertRaises(MapperError, m6.parse, ['a=b=c'])
self.assertRaises(MapperError, m6.parse, ['a=b=c=d'])
# dupes
self.assertRaises(MapperError, m6.parse, ['a=b','a=c'])
self.assertRaises(MapperError, m6.parse, ['x=z','y=z'])
self.assertRaises(MapperError, m6.parse, ['a=b', 'a=c'])
self.assertRaises(MapperError, m6.parse, ['x=z', 'y=z'])
def test01_mapper_src_to_dst(self):
m = Mapper(['http://e.org/p/', '/tmp/q/'])

177
tests/test_resource.py
View File

@ -2,19 +2,20 @@ import unittest
import re
from resync.resource import Resource, ChangeTypeError
class TestResource(unittest.TestCase):
def test01a_same(self):
r1 = Resource('a')
r2 = Resource('a')
self.assertEqual( r1, r1 )
self.assertEqual( r1, r2 )
self.assertEqual(r1, r1)
self.assertEqual(r1, r2)
def test01b_same(self):
r1 = Resource(uri='a',timestamp=1234.0)
r2 = Resource(uri='a',timestamp=1234.0)
self.assertEqual( r1, r1 )
self.assertEqual( r1, r2 )
r1 = Resource(uri='a', timestamp=1234.0)
r2 = Resource(uri='a', timestamp=1234.0)
self.assertEqual(r1, r1)
self.assertEqual(r1, r2)
def test01c_same(self):
"""Same with lastmod instead of direct timestamp"""
@ -29,128 +30,132 @@ class TestResource(unittest.TestCase):
'2012-01-01T00:00:00Z',
'2012-01-01T00:00:00.000000Z',
'2012-01-01T00:00:00.000000000000Z',
'2012-01-01T00:00:00.000000000001Z', #below resolution
'2012-01-01T00:00:00.000000000001Z', # below resolution
'2012-01-01T00:00:00.00+00:00',
'2012-01-01T00:00:00.00-00:00',
'2012-01-01T02:00:00.00-02:00',
'2011-12-31T23:00:00.00+01:00'
):
r2.lastmod = r2lm
self.assertEqual( r1.timestamp, r2.timestamp, ('%s (%f) == %s (%f)' % (r1lm,r1.timestamp,r2lm,r2.timestamp)) )
self.assertEqual( r1, r2 )
self.assertEqual(r1.timestamp, r2.timestamp, ('%s (%f) == %s (%f)' % (
r1lm, r1.timestamp, r2lm, r2.timestamp)))
self.assertEqual(r1, r2)
def test01d_same(self):
"""Same with slight timestamp diff"""
r1 = Resource('a')
r1.lastmod='2012-01-02T01:02:03Z'
r1.lastmod = '2012-01-02T01:02:03Z'
r2 = Resource('a')
r2.lastmod='2012-01-02T01:02:03.99Z'
self.assertNotEqual( r1.timestamp, r2.timestamp )
self.assertEqual( r1, r2 )
r2.lastmod = '2012-01-02T01:02:03.99Z'
self.assertNotEqual(r1.timestamp, r2.timestamp)
self.assertEqual(r1, r2)
def test02a_diff(self):
r1 = Resource('a')
r2 = Resource('b')
self.assertNotEqual(r1,r2)
self.assertNotEqual(r1, r2)
def test02b_diff(self):
r1 = Resource('a',lastmod='2012-01-11')
r2 = Resource('a',lastmod='2012-01-22')
#print 'r1 == r2 : '+str(r1==r2)
self.assertNotEqual( r1, r2 )
r1 = Resource('a', lastmod='2012-01-11')
r2 = Resource('a', lastmod='2012-01-22')
# print 'r1 == r2 : '+str(r1==r2)
self.assertNotEqual(r1, r2)
def test04_bad_lastmod(self):
def setlastmod(r,v):
r.lastmod=v
def setlastmod(r, v):
r.lastmod = v
r = Resource('4')
# Bad formats
self.assertRaises( ValueError, setlastmod, r, "bad_lastmod" )
self.assertRaises( ValueError, setlastmod, r, "" )
self.assertRaises( ValueError, setlastmod, r, "2012-13-01" )
self.assertRaises( ValueError, setlastmod, r, "2012-12-32" )
self.assertRaises( ValueError, setlastmod, r, "2012-11-01T10:10:60" )
self.assertRaises( ValueError, setlastmod, r, "2012-11-01T10:10:59.9x" )
self.assertRaises(ValueError, setlastmod, r, "bad_lastmod")
self.assertRaises(ValueError, setlastmod, r, "")
self.assertRaises(ValueError, setlastmod, r, "2012-13-01")
self.assertRaises(ValueError, setlastmod, r, "2012-12-32")
self.assertRaises(ValueError, setlastmod, r, "2012-11-01T10:10:60")
self.assertRaises(ValueError, setlastmod, r, "2012-11-01T10:10:59.9x")
# Valid ISO8601 but not alloed in W3C Datetime
self.assertRaises( ValueError, setlastmod, r, "2012-11-01T01:01:01" )
self.assertRaises( ValueError, setlastmod, r, "2012-11-01 01:01:01Z" )
self.assertRaises( ValueError, setlastmod, r, "2012-11-01T01:01:01+0000" )
self.assertRaises( ValueError, setlastmod, r, "2012-11-01T01:01:01-1000" )
self.assertRaises(ValueError, setlastmod, r, "2012-11-01T01:01:01")
self.assertRaises(ValueError, setlastmod, r, "2012-11-01 01:01:01Z")
self.assertRaises(ValueError, setlastmod, r,
"2012-11-01T01:01:01+0000")
self.assertRaises(ValueError, setlastmod, r,
"2012-11-01T01:01:01-1000")
def test05_lastmod_roundtrips(self):
r = Resource('a')
r.lastmod='2012-03-14'
self.assertEqual( r.lastmod, '2012-03-14T00:00:00Z' )
r.lastmod='2012-03-14T00:00:00+00:00'
#print r.timestamp
self.assertEqual( r.lastmod, '2012-03-14T00:00:00Z' )
r.lastmod='2012-03-14T00:00:00-00:00'
#print r.timestamp
self.assertEqual( r.lastmod, '2012-03-14T00:00:00Z' )
r.lastmod='2012-03-14T18:37:36Z'
#print r.timestamp
self.assertEqual( r.lastmod, '2012-03-14T18:37:36Z' )
r.lastmod = '2012-03-14'
self.assertEqual(r.lastmod, '2012-03-14T00:00:00Z')
r.lastmod = '2012-03-14T00:00:00+00:00'
# print r.timestamp
self.assertEqual(r.lastmod, '2012-03-14T00:00:00Z')
r.lastmod = '2012-03-14T00:00:00-00:00'
# print r.timestamp
self.assertEqual(r.lastmod, '2012-03-14T00:00:00Z')
r.lastmod = '2012-03-14T18:37:36Z'
# print r.timestamp
self.assertEqual(r.lastmod, '2012-03-14T18:37:36Z')
def test06_str(self):
r1 = Resource('abc',lastmod='2012-01-01')
self.assertTrue( re.match( r"\[ abc \| 2012-01-01T", str(r1) ) )
r1 = Resource('abc', lastmod='2012-01-01')
self.assertTrue(re.match(r"\[ abc \| 2012-01-01T", str(r1)))
def test07_repr(self):
r1 = Resource('def',lastmod='2012-01-01')
self.assertEqual( repr(r1), "{'uri': 'def', 'timestamp': 1325376000}" )
r1 = Resource('def', lastmod='2012-01-01')
self.assertEqual(repr(r1), "{'uri': 'def', 'timestamp': 1325376000}")
def test08_multiple_hashes(self):
r1 = Resource('abcd')
r1.md5 = "some_md5"
r1.sha1 = "some_sha1"
r1.sha256 = "some_sha256"
self.assertEqual( r1.md5, "some_md5" )
self.assertEqual( r1.sha1, "some_sha1" )
self.assertEqual( r1.sha256, "some_sha256" )
self.assertEqual( r1.hash, "md5:some_md5 sha-1:some_sha1 sha-256:some_sha256" )
self.assertEqual(r1.md5, "some_md5")
self.assertEqual(r1.sha1, "some_sha1")
self.assertEqual(r1.sha256, "some_sha256")
self.assertEqual(
r1.hash, "md5:some_md5 sha-1:some_sha1 sha-256:some_sha256")
r2 = Resource('def')
r2.hash = "md5:ddd"
self.assertEqual( r2.md5, 'ddd' )
self.assertEqual( r2.sha1, None )
self.assertEqual(r2.md5, 'ddd')
self.assertEqual(r2.sha1, None)
r2.hash = "sha-1:eee"
self.assertEqual( r2.md5, None )
self.assertEqual( r2.sha1, 'eee' )
self.assertEqual(r2.md5, None)
self.assertEqual(r2.sha1, 'eee')
r2.hash = "md5:fff sha-1:eee sha-256:ggg"
self.assertEqual( r2.md5, 'fff' )
self.assertEqual( r2.sha1, 'eee' )
self.assertEqual( r2.sha256, 'ggg' )
self.assertEqual(r2.md5, 'fff')
self.assertEqual(r2.sha1, 'eee')
self.assertEqual(r2.sha256, 'ggg')
def test09_changetypeerror(self):
r1 = Resource('a')
self.assertEqual( r1.change, None )
self.assertEqual(r1.change, None)
r1.change = 'deleted'
self.assertEqual( r1.change, 'deleted' )
self.assertRaises( ChangeTypeError, Resource, 'a', change="bad" )
self.assertEqual(r1.change, 'deleted')
self.assertRaises(ChangeTypeError, Resource, 'a', change="bad")
# disable checking
Resource.CHANGE_TYPES = False
r1 = Resource( 'a', change="bad" )
self.assertEqual( r1.change, 'bad' )
r1 = Resource('a', change="bad")
self.assertEqual(r1.change, 'bad')
def test10_md_at_roundtrips(self):
r = Resource('a')
r.md_at='2013-03-14'
self.assertEqual( r.md_at, '2013-03-14T00:00:00Z' )
r.md_at='2013-03-14T00:00:00+00:00'
self.assertEqual( r.md_at, '2013-03-14T00:00:00Z' )
r.md_at='2013-03-14T00:00:00-00:00'
self.assertEqual( r.md_at, '2013-03-14T00:00:00Z' )
r.md_at='2013-03-14T18:37:36Z'
self.assertEqual( r.md_at, '2013-03-14T18:37:36Z' )
r.md_at = '2013-03-14'
self.assertEqual(r.md_at, '2013-03-14T00:00:00Z')
r.md_at = '2013-03-14T00:00:00+00:00'
self.assertEqual(r.md_at, '2013-03-14T00:00:00Z')
r.md_at = '2013-03-14T00:00:00-00:00'
self.assertEqual(r.md_at, '2013-03-14T00:00:00Z')
r.md_at = '2013-03-14T18:37:36Z'
self.assertEqual(r.md_at, '2013-03-14T18:37:36Z')
def test11_md_completed_roundtrips(self):
r = Resource('a')
r.md_completed='2013-04-14'
self.assertEqual( r.md_completed, '2013-04-14T00:00:00Z' )
r.md_completed='2013-04-14T00:00:00+00:00'
self.assertEqual( r.md_completed, '2013-04-14T00:00:00Z' )
r.md_completed='2013-04-14T00:00:00-00:00'
self.assertEqual( r.md_completed, '2013-04-14T00:00:00Z' )
r.md_completed='2013-04-14T18:37:36Z'
self.assertEqual( r.md_completed, '2013-04-14T18:37:36Z' )
r.md_completed = '2013-04-14'
self.assertEqual(r.md_completed, '2013-04-14T00:00:00Z')
r.md_completed = '2013-04-14T00:00:00+00:00'
self.assertEqual(r.md_completed, '2013-04-14T00:00:00Z')
r.md_completed = '2013-04-14T00:00:00-00:00'
self.assertEqual(r.md_completed, '2013-04-14T00:00:00Z')
r.md_completed = '2013-04-14T18:37:36Z'
self.assertEqual(r.md_completed, '2013-04-14T18:37:36Z')
def test12_timevalues(self):
r = Resource(uri='tv',
@ -159,19 +164,19 @@ class TestResource(unittest.TestCase):
md_completed="2000-01-03",
md_from="2000-01-04",
md_until="2000-01-05")
self.assertEqual( r.lastmod, '2000-01-01T00:00:00Z' )
self.assertEqual( r.md_at, '2000-01-02T00:00:00Z' )
self.assertEqual( r.md_completed, '2000-01-03T00:00:00Z' )
self.assertEqual( r.md_from, '2000-01-04T00:00:00Z' )
self.assertEqual( r.md_until, '2000-01-05T00:00:00Z' )
self.assertEqual(r.lastmod, '2000-01-01T00:00:00Z')
self.assertEqual(r.md_at, '2000-01-02T00:00:00Z')
self.assertEqual(r.md_completed, '2000-01-03T00:00:00Z')
self.assertEqual(r.md_from, '2000-01-04T00:00:00Z')
self.assertEqual(r.md_until, '2000-01-05T00:00:00Z')
def test13_mime_type(self):
r = Resource(uri='tv1', mime_type='text/plain')
self.assertEqual( r.mime_type, 'text/plain' )
self.assertEqual(r.mime_type, 'text/plain')
r.mime_type = None
self.assertEqual( r.mime_type, None )
self.assertEqual(r.mime_type, None)
r = Resource(uri='tv2')
self.assertEqual( r.mime_type, None )
self.assertEqual(r.mime_type, None)
if __name__ == '__main__':
suite = unittest.TestLoader().loadTestsFromTestCase(TestResource)

126
tests/test_resource_container.py
View File

@ -2,118 +2,120 @@ import unittest
from resync.resource import Resource
from resync.resource_container import ResourceContainer
class TestResourceContainer(unittest.TestCase):
def test01_create_and_add(self):
rc = ResourceContainer( resources=[] )
self.assertEqual( len(rc.resources), 0, "empty" )
rc.resources.append( Resource('a',timestamp=1) )
rc.resources.append( Resource('b',timestamp=2) )
self.assertEqual( len(rc.resources), 2, "two resources" )
rc = ResourceContainer(resources=[])
self.assertEqual(len(rc.resources), 0, "empty")
rc.resources.append(Resource('a', timestamp=1))
rc.resources.append(Resource('b', timestamp=2))
self.assertEqual(len(rc.resources), 2, "two resources")
def test02_iter(self):
rc = ResourceContainer( resources=[] )
rc.resources.append( Resource('a',timestamp=1) )
rc.resources.append( Resource('b',timestamp=2) )
rc.resources.append( Resource('c',timestamp=3) )
rc.resources.append( Resource('d',timestamp=4) )
resources=[]
rc = ResourceContainer(resources=[])
rc.resources.append(Resource('a', timestamp=1))
rc.resources.append(Resource('b', timestamp=2))
rc.resources.append(Resource('c', timestamp=3))
rc.resources.append(Resource('d', timestamp=4))
resources = []
for r in rc:
resources.append(r)
self.assertEqual(len(resources), 4)
self.assertEqual( resources[0].uri, 'a')
self.assertEqual( resources[3].uri, 'd')
self.assertEqual(resources[0].uri, 'a')
self.assertEqual(resources[3].uri, 'd')
def test03_prune_before(self):
rc = ResourceContainer()
rc.resources.append( Resource('a',timestamp=1) )
rc.resources.append( Resource('b',timestamp=2) )
rc.resources.append( Resource('c',timestamp=3) )
rc.resources.append( Resource('d',timestamp=4) )
rc.resources.append(Resource('a', timestamp=1))
rc.resources.append(Resource('b', timestamp=2))
rc.resources.append(Resource('c', timestamp=3))
rc.resources.append(Resource('d', timestamp=4))
rc.prune_before(3)
self.assertEqual( len(rc.resources), 2 )
self.assertEqual(len(rc.resources), 2)
i = iter(rc)
self.assertEqual( next(i).uri, 'c' )
self.assertEqual( next(i).uri, 'd' )
self.assertEqual(next(i).uri, 'c')
self.assertEqual(next(i).uri, 'd')
# put some more back out of order
rc.resources.append( Resource('a',timestamp=1) )
rc.resources.append( Resource('b',timestamp=2) )
rc.resources.append( Resource('e',timestamp=1000) )
rc.resources.append(Resource('a', timestamp=1))
rc.resources.append(Resource('b', timestamp=2))
rc.resources.append(Resource('e', timestamp=1000))
rc.prune_before(3.5)
self.assertEqual( len(rc.resources), 2 )
self.assertEqual(len(rc.resources), 2)
i = iter(rc)
self.assertEqual( next(i).uri, 'd' )
self.assertEqual( next(i).uri, 'e' )
self.assertEqual(next(i).uri, 'd')
self.assertEqual(next(i).uri, 'e')
def test04_prune_dupes(self):
rc = ResourceContainer()
rc.resources.append( Resource('a',timestamp=1, change='created') )
rc.resources.append( Resource('b',timestamp=2, change='created') )
rc.resources.append( Resource('c',timestamp=3, change='updated') )
rc.resources.append( Resource('d',timestamp=4, change='deleted') )
rc.resources.append( Resource('a',timestamp=4, change='updated') )
rc.resources.append( Resource('b',timestamp=4, change='deleted') )
rc.resources.append( Resource('b',timestamp=5, change='created') )
rc.resources.append( Resource('b',timestamp=6, change='deleted') )
rc.resources.append( Resource('c',timestamp=7, change='deleted') )
rc.resources.append( Resource('d',timestamp=8, change='created') )
rc.resources.append(Resource('a', timestamp=1, change='created'))
rc.resources.append(Resource('b', timestamp=2, change='created'))
rc.resources.append(Resource('c', timestamp=3, change='updated'))
rc.resources.append(Resource('d', timestamp=4, change='deleted'))
rc.resources.append(Resource('a', timestamp=4, change='updated'))
rc.resources.append(Resource('b', timestamp=4, change='deleted'))
rc.resources.append(Resource('b', timestamp=5, change='created'))
rc.resources.append(Resource('b', timestamp=6, change='deleted'))
rc.resources.append(Resource('c', timestamp=7, change='deleted'))
rc.resources.append(Resource('d', timestamp=8, change='created'))
rc.prune_dupes()
self.assertEqual( len(rc.resources), 3 )
self.assertEqual(len(rc.resources), 3)
i = iter(rc)
i1 = next(i)
self.assertEqual( i1.uri, 'a' )
self.assertEqual( i1.change, 'updated' )
self.assertEqual(i1.uri, 'a')
self.assertEqual(i1.change, 'updated')
i2 = next(i)
self.assertEqual( i2.uri, 'c' )
self.assertEqual( i2.change, 'deleted' )
self.assertEqual(i2.uri, 'c')
self.assertEqual(i2.change, 'deleted')
i3 = next(i)
self.assertEqual( i3.uri, 'd' )
self.assertEqual( i3.change, 'created' )
self.assertEqual(i3.uri, 'd')
self.assertEqual(i3.change, 'created')
def test05_from_until(self):
rc = ResourceContainer()
# via convenience methods
self.assertEqual( rc.md_from, None )
self.assertEqual( rc.md_until, None )
self.assertEqual(rc.md_from, None)
self.assertEqual(rc.md_until, None)
rc.md_from = "ftime"
rc.md_until = "utime"
self.assertEqual( rc.md_from, "ftime" )
self.assertEqual( rc.md_until, "utime" )
self.assertEqual(rc.md_from, "ftime")
self.assertEqual(rc.md_until, "utime")
# via underlying dict
rc.md['md_from'] = "ftime2"
rc.md['md_until'] = "utime2too"
self.assertEqual( rc.md_from, "ftime2" )
self.assertEqual( rc.md_until, "utime2too" )
self.assertEqual(rc.md_from, "ftime2")
self.assertEqual(rc.md_until, "utime2too")
def test06_source_description(self):
# up links used to point to the source description
rc = ResourceContainer()
# via convenience methods
self.assertEqual( rc.up, None )
# via convenience methods
self.assertEqual(rc.up, None)
rc.up = "well-known"
self.assertEqual( rc.up, "well-known" )
self.assertEqual(rc.up, "well-known")
rc.up = "well-known2"
self.assertEqual( rc.up, "well-known2" )
self.assertEqual(rc.up, "well-known2")
# via link
link = rc.link("up")
self.assertEqual( link['href'], "well-known2" )
self.assertEqual(link['href'], "well-known2")
link['href'] = "wk3"
self.assertEqual( rc.up, "wk3" )
self.assertEqual(rc.up, "wk3")
def test07_describedby(self):
rc = ResourceContainer()
# via convenience methods
self.assertEqual( rc.describedby, None )
# via convenience methods
self.assertEqual(rc.describedby, None)
rc.describedby = "db_uri"
self.assertEqual( rc.describedby, "db_uri" )
self.assertEqual(rc.describedby, "db_uri")
def test08_up(self):
rc = ResourceContainer()
# via convenience methods
self.assertEqual( rc.up, None )
# via convenience methods
self.assertEqual(rc.up, None)
rc.up = "up_uri"
self.assertEqual( rc.up, "up_uri" )
self.assertEqual(rc.up, "up_uri")
if __name__ == '__main__':
suite = unittest.defaultTestLoader.loadTestsFromTestCase(TestResourceContainer)
suite = unittest.defaultTestLoader.loadTestsFromTestCase(
TestResourceContainer)
unittest.TextTestRunner().run(suite)

51
tests/test_resource_dump_manifest.py
View File

@ -1,9 +1,9 @@
import unittest
try: #python2
try: # python2
# Must try this first as io also exists in python2
# but in the wrong one!
import StringIO as io
except ImportError: #python3
except ImportError: # python3
import io
import re
@ -11,55 +11,60 @@ from resync.resource import Resource
from resync.resource_dump_manifest import ResourceDumpManifest
from resync.sitemap import SitemapParseError
class TestResourceDumpManifest(unittest.TestCase):
def test01_as_xml(self):
rdm = ResourceDumpManifest()
rdm.add( Resource('a.zip',timestamp=1) )
rdm.add( Resource('b.zip',timestamp=2) )
rdm.add(Resource('a.zip', timestamp=1))
rdm.add(Resource('b.zip', timestamp=2))
xml = rdm.as_xml()
self.assertTrue( re.search(r'<rs:md .*capability="resourcedump-manifest"', xml), 'XML has capability' )
self.assertTrue( re.search(r'<url><loc>a.zip</loc><lastmod>1970-01-01T00:00:01Z</lastmod></url>', xml), 'XML has resource a' )
self.assertTrue(re.search(
r'<rs:md .*capability="resourcedump-manifest"', xml), 'XML has capability')
self.assertTrue(re.search(
r'<url><loc>a.zip</loc><lastmod>1970-01-01T00:00:01Z</lastmod></url>', xml), 'XML has resource a')
def test10_parse(self):
xml='<?xml version=\'1.0\' encoding=\'UTF-8\'?>\n\
xml = '<?xml version=\'1.0\' encoding=\'UTF-8\'?>\n\
<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9" xmlns:rs="http://www.openarchives.org/rs/terms/">\
<rs:md at="2013-08-08" capability="resourcedump-manifest"/>\
<url><loc>http://example.com/res1</loc><lastmod>2012-03-14T18:37:36Z</lastmod><rs:md length="12" path="/res1" /></url>\
<url><loc>http://example.com/res2</loc><lastmod>2012-03-14T18:37:36Z</lastmod><rs:md length="32" path="/res2"/></url>\
</urlset>'
rdm=ResourceDumpManifest()
rdm = ResourceDumpManifest()
rdm.parse(fh=io.StringIO(xml))
self.assertEqual( len(rdm.resources), 2, 'got 2 resource dumps')
self.assertEqual( rdm.capability, 'resourcedump-manifest', 'capability set' )
self.assertEqual( rdm.md_at, '2013-08-08' )
self.assertTrue( 'http://example.com/res1' in rdm.resources )
self.assertTrue( rdm.resources['http://example.com/res1'].length, 12 )
self.assertTrue( rdm.resources['http://example.com/res1'].path, '/res1' )
self.assertTrue( 'http://example.com/res2' in rdm.resources )
self.assertTrue( rdm.resources['http://example.com/res2'].path, '/res2' )
self.assertEqual(len(rdm.resources), 2, 'got 2 resource dumps')
self.assertEqual(
rdm.capability, 'resourcedump-manifest', 'capability set')
self.assertEqual(rdm.md_at, '2013-08-08')
self.assertTrue('http://example.com/res1' in rdm.resources)
self.assertTrue(rdm.resources['http://example.com/res1'].length, 12)
self.assertTrue(rdm.resources['http://example.com/res1'].path, '/res1')
self.assertTrue('http://example.com/res2' in rdm.resources)
self.assertTrue(rdm.resources['http://example.com/res2'].path, '/res2')
def test11_parse_no_capability(self):
# For a resource dump this should be an error
xml='<?xml version=\'1.0\' encoding=\'UTF-8\'?>\n\
xml = '<?xml version=\'1.0\' encoding=\'UTF-8\'?>\n\
<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9" xmlns:rs="http://www.openarchives.org/rs/terms/">\
<rs:md from="2013-01-01"/>\
<url><loc>http://example.com/res1</loc><lastmod>2012-03-14T18:37:36Z</lastmod><rs:md length="12" path="/res1" /></url>\
<url><loc>http://example.com/res2</loc><lastmod>2012-03-14T18:37:36Z</lastmod><rs:md length="32" path="/res2"/></url>\
</urlset>'
rdm=ResourceDumpManifest()
self.assertRaises( SitemapParseError, rdm.parse, fh=io.StringIO(xml) )
rdm = ResourceDumpManifest()
self.assertRaises(SitemapParseError, rdm.parse, fh=io.StringIO(xml))
def test12_parse_bad_capability(self):
# the <rs:md capability="bad_capability".. should give error
xml='<?xml version=\'1.0\' encoding=\'UTF-8\'?>\n\
xml = '<?xml version=\'1.0\' encoding=\'UTF-8\'?>\n\
<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9" xmlns:rs="http://www.openarchives.org/rs/terms/">\
<rs:md capability="bad_capability" from="2013-01-01"/>\
<url><loc>http://example.com/a.zip</loc><lastmod>2012-03-14T18:37:36Z</lastmod><rs:md length="12" /></url>\
</urlset>'
rdm=ResourceDumpManifest()
self.assertRaises( SitemapParseError, rdm.parse, fh=io.StringIO(xml) )
rdm = ResourceDumpManifest()
self.assertRaises(SitemapParseError, rdm.parse, fh=io.StringIO(xml))
if __name__ == '__main__':
suite = unittest.defaultTestLoader.loadTestsFromTestCase(TestResourceDumpManifest)
suite = unittest.defaultTestLoader.loadTestsFromTestCase(
TestResourceDumpManifest)
unittest.TextTestRunner().run(suite)

196
tests/test_resource_list.py
View File

@ -1,9 +1,9 @@
import unittest
try: #python2
try: # python2
# Must try this first as io also exists in python2
# but in the wrong one!
import StringIO as io
except ImportError: #python3
except ImportError: # python3
import io
import re
@ -11,169 +11,173 @@ from resync.resource import Resource
from resync.resource_list import ResourceList, ResourceListDupeError
from resync.sitemap import SitemapParseError
class TestResourceList(unittest.TestCase):
def test01_same(self):
src = ResourceList()
src.add( Resource('a',timestamp=1) )
src.add( Resource('b',timestamp=2) )
src.add(Resource('a', timestamp=1))
src.add(Resource('b', timestamp=2))
dst = ResourceList()
dst.add( Resource('a',timestamp=1) )
dst.add( Resource('b',timestamp=2) )
( same, changed, deleted, added ) = dst.compare(src)
self.assertEqual( len(same), 2, "2 things unchanged" )
dst.add(Resource('a', timestamp=1))
dst.add(Resource('b', timestamp=2))
(same, changed, deleted, added) = dst.compare(src)
self.assertEqual(len(same), 2, "2 things unchanged")
i = iter(same)
self.assertEqual( next(i).uri, 'a', "first was a" )
self.assertEqual( next(i).uri, 'b', "second was b" )
self.assertEqual( len(changed), 0, "nothing changed" )
self.assertEqual( len(deleted), 0, "nothing deleted" )
self.assertEqual( len(added), 0, "nothing added" )
self.assertEqual(next(i).uri, 'a', "first was a")
self.assertEqual(next(i).uri, 'b', "second was b")
self.assertEqual(len(changed), 0, "nothing changed")
self.assertEqual(len(deleted), 0, "nothing deleted")
self.assertEqual(len(added), 0, "nothing added")
def test02_changed(self):
src = ResourceList()
src.add( Resource('a',timestamp=1) )
src.add( Resource('b',timestamp=2) )
src.add(Resource('a', timestamp=1))
src.add(Resource('b', timestamp=2))
dst = ResourceList()
dst.add( Resource('a',timestamp=3) )
dst.add( Resource('b',timestamp=4) )
( same, changed, deleted, added ) = dst.compare(src)
self.assertEqual( len(same), 0, "0 things unchanged" )
self.assertEqual( len(changed), 2, "2 things changed" )
dst.add(Resource('a', timestamp=3))
dst.add(Resource('b', timestamp=4))
(same, changed, deleted, added) = dst.compare(src)
self.assertEqual(len(same), 0, "0 things unchanged")
self.assertEqual(len(changed), 2, "2 things changed")
i = iter(changed)
self.assertEqual( next(i).uri, 'a', "first was a" )
self.assertEqual( next(i).uri, 'b', "second was b" )
self.assertEqual( len(deleted), 0, "nothing deleted" )
self.assertEqual( len(added), 0, "nothing added" )
self.assertEqual(next(i).uri, 'a', "first was a")
self.assertEqual(next(i).uri, 'b', "second was b")
self.assertEqual(len(deleted), 0, "nothing deleted")
self.assertEqual(len(added), 0, "nothing added")
def test03_deleted(self):
src = ResourceList()
src.add( Resource('a',timestamp=1) )
src.add( Resource('b',timestamp=2) )
src.add(Resource('a', timestamp=1))
src.add(Resource('b', timestamp=2))
dst = ResourceList()
dst.add( Resource('a',timestamp=1) )
dst.add( Resource('b',timestamp=2) )
dst.add( Resource('c',timestamp=3) )
dst.add( Resource('d',timestamp=4) )
( same, changed, deleted, added ) = dst.compare(src)
self.assertEqual( len(same), 2, "2 things unchanged" )
self.assertEqual( len(changed), 0, "nothing changed" )
self.assertEqual( len(deleted), 2, "c and d deleted" )
dst.add(Resource('a', timestamp=1))
dst.add(Resource('b', timestamp=2))
dst.add(Resource('c', timestamp=3))
dst.add(Resource('d', timestamp=4))
(same, changed, deleted, added) = dst.compare(src)
self.assertEqual(len(same), 2, "2 things unchanged")
self.assertEqual(len(changed), 0, "nothing changed")
self.assertEqual(len(deleted), 2, "c and d deleted")
i = iter(deleted)
self.assertEqual( next(i).uri, 'c', "first was c" )
self.assertEqual( next(i).uri, 'd', "second was d" )
self.assertEqual( len(added), 0, "nothing added" )
self.assertEqual(next(i).uri, 'c', "first was c")
self.assertEqual(next(i).uri, 'd', "second was d")
self.assertEqual(len(added), 0, "nothing added")
def test04_added(self):
src = ResourceList()
src.add( Resource('a',timestamp=1) )
src.add( Resource('b',timestamp=2) )
src.add( Resource('c',timestamp=3) )
src.add( Resource('d',timestamp=4) )
src.add(Resource('a', timestamp=1))
src.add(Resource('b', timestamp=2))
src.add(Resource('c', timestamp=3))
src.add(Resource('d', timestamp=4))
dst = ResourceList()
dst.add( Resource('a',timestamp=1) )
dst.add( Resource('c',timestamp=3) )
( same, changed, deleted, added ) = dst.compare(src)
self.assertEqual( len(same), 2, "2 things unchanged" )
self.assertEqual( len(changed), 0, "nothing changed" )
self.assertEqual( len(deleted), 0, "nothing deleted" )
self.assertEqual( len(added), 2, "b and d added" )
dst.add(Resource('a', timestamp=1))
dst.add(Resource('c', timestamp=3))
(same, changed, deleted, added) = dst.compare(src)
self.assertEqual(len(same), 2, "2 things unchanged")
self.assertEqual(len(changed), 0, "nothing changed")
self.assertEqual(len(deleted), 0, "nothing deleted")
self.assertEqual(len(added), 2, "b and d added")
i = iter(added)
self.assertEqual( next(i).uri, 'b', "first was b" )
self.assertEqual( next(i).uri, 'd', "second was d" )
self.assertEqual(next(i).uri, 'b', "first was b")
self.assertEqual(next(i).uri, 'd', "second was d")
def test05_add(self):
r1 = Resource(uri='a',length=1)
r2 = Resource(uri='b',length=2)
r1 = Resource(uri='a', length=1)
r2 = Resource(uri='b', length=2)
i = ResourceList()
i.add(r1)
self.assertRaises( ResourceListDupeError, i.add, r1)
self.assertRaises(ResourceListDupeError, i.add, r1)
i.add(r2)
self.assertRaises( ResourceListDupeError, i.add, r2)
self.assertRaises(ResourceListDupeError, i.add, r2)
# allow dupes
r1d = Resource(uri='a',length=10)
i.add(r1d,replace=True)
self.assertEqual( len(i), 2 )
self.assertEqual( i.resources['a'].length, 10 )
r1d = Resource(uri='a', length=10)
i.add(r1d, replace=True)
self.assertEqual(len(i), 2)
self.assertEqual(i.resources['a'].length, 10)
def test06_add_iterable(self):
r1 = Resource(uri='a',length=1)
r2 = Resource(uri='b',length=2)
r1 = Resource(uri='a', length=1)
r2 = Resource(uri='b', length=2)
i = ResourceList()
i.add( [r1,r2] )
self.assertRaises( ResourceListDupeError, i.add, r1)
self.assertRaises( ResourceListDupeError, i.add, r2)
i.add([r1, r2])
self.assertRaises(ResourceListDupeError, i.add, r1)
self.assertRaises(ResourceListDupeError, i.add, r2)
# allow dupes
r1d = Resource(uri='a',length=10)
i.add( [r1d] ,replace=True)
self.assertEqual( len(i), 2 )
self.assertEqual( i.resources['a'].length, 10 )
r1d = Resource(uri='a', length=10)
i.add([r1d], replace=True)
self.assertEqual(len(i), 2)
self.assertEqual(i.resources['a'].length, 10)
def test07_has_md5(self):
r1 = Resource(uri='a')
r2 = Resource(uri='b')
i = ResourceList()
self.assertFalse( i.has_md5() )
self.assertFalse(i.has_md5())
i.add(r1)
i.add(r2)
self.assertFalse( i.has_md5() )
r1.md5="aabbcc"
self.assertTrue( i.has_md5() )
self.assertFalse(i.has_md5())
r1.md5 = "aabbcc"
self.assertTrue(i.has_md5())
def test08_iter(self):
i = ResourceList()
i.add( Resource('a',timestamp=1) )
i.add( Resource('b',timestamp=2) )
i.add( Resource('c',timestamp=3) )
i.add( Resource('d',timestamp=4) )
resources=[]
i.add(Resource('a', timestamp=1))
i.add(Resource('b', timestamp=2))
i.add(Resource('c', timestamp=3))
i.add(Resource('d', timestamp=4))
resources = []
for r in i:
resources.append(r)
self.assertEqual(len(resources), 4)
self.assertEqual( resources[0].uri, 'a')
self.assertEqual( resources[3].uri, 'd')
self.assertEqual(resources[0].uri, 'a')
self.assertEqual(resources[3].uri, 'd')
def test20_as_xml(self):
rl = ResourceList()
rl.add( Resource('a',timestamp=1) )
rl.add( Resource('b',timestamp=2) )
rl.add(Resource('a', timestamp=1))
rl.add(Resource('b', timestamp=2))
xml = rl.as_xml()
self.assertTrue( re.search(r'<rs:md .*capability="resourcelist"', xml), 'XML has capability' )
self.assertTrue( re.search(r'<url><loc>a</loc><lastmod>1970-01-01T00:00:01Z</lastmod></url>', xml), 'XML has resource a' )
self.assertTrue(
re.search(r'<rs:md .*capability="resourcelist"', xml), 'XML has capability')
self.assertTrue(re.search(
r'<url><loc>a</loc><lastmod>1970-01-01T00:00:01Z</lastmod></url>', xml), 'XML has resource a')
def test30_parse(self):
xml='<?xml version=\'1.0\' encoding=\'UTF-8\'?>\n\
xml = '<?xml version=\'1.0\' encoding=\'UTF-8\'?>\n\
<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9" xmlns:rs="http://www.openarchives.org/rs/terms/">\
<rs:md at="2013-08-07" capability="resourcelist" completed="2013-08-08" />\
<url><loc>/tmp/rs_test/src/file_a</loc><lastmod>2012-03-14T18:37:36Z</lastmod><rs:md change="updated" length="12" /></url>\
<url><loc>/tmp/rs_test/src/file_b</loc><lastmod>2012-03-14T18:37:36Z</lastmod><rs:md length="32" /></url>\
</urlset>'
rl=ResourceList()
rl = ResourceList()
rl.parse(fh=io.StringIO(xml))
self.assertEqual( len(rl.resources), 2, 'got 2 resources')
self.assertEqual( rl.md['capability'], 'resourcelist', 'capability set' )
self.assertEqual( rl.md_at, '2013-08-07' )
self.assertEqual( rl.md_completed, '2013-08-08' )
self.assertEqual(len(rl.resources), 2, 'got 2 resources')
self.assertEqual(rl.md['capability'], 'resourcelist', 'capability set')
self.assertEqual(rl.md_at, '2013-08-07')
self.assertEqual(rl.md_completed, '2013-08-08')
def test31_parse_no_capability(self):
xml='<?xml version=\'1.0\' encoding=\'UTF-8\'?>\n\
xml = '<?xml version=\'1.0\' encoding=\'UTF-8\'?>\n\
<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">\
<url><loc>http://example.com/res1</loc><lastmod>2012-03-14T18:37:36Z</lastmod></url>\
</urlset>'
rl=ResourceList()
rl = ResourceList()
rl.parse(fh=io.StringIO(xml))
self.assertEqual( len(rl.resources), 1, 'got 1 resource')
self.assertEqual( rl.md['capability'], 'resourcelist', 'capability set by reading routine' )
self.assertFalse( 'from' in rl.md )
self.assertEqual(len(rl.resources), 1, 'got 1 resource')
self.assertEqual(rl.md['capability'], 'resourcelist',
'capability set by reading routine')
self.assertFalse('from' in rl.md)
def test32_parse_bad_capability(self):
# the <rs:md capability="bad_capability".. should give error
xml='<?xml version=\'1.0\' encoding=\'UTF-8\'?>\n\
xml = '<?xml version=\'1.0\' encoding=\'UTF-8\'?>\n\
<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9" xmlns:rs="http://www.openarchives.org/rs/terms/">\
<rs:md capability="bad_capability" from="2013-01-01"/>\
<url><loc>http://example.com/bad_res_1</loc><lastmod>2012-03-14T18:37:36Z</lastmod></url>\
</urlset>'
rl=ResourceList()
self.assertRaises( SitemapParseError, rl.parse, fh=io.StringIO(xml) )
rl = ResourceList()
self.assertRaises(SitemapParseError, rl.parse, fh=io.StringIO(xml))
if __name__ == '__main__':
suite = unittest.defaultTestLoader.loadTestsFromTestCase(TestResourceList)

129
tests/test_resource_list_builder.py
View File

@ -5,6 +5,7 @@ import time
from resync.resource_list_builder import ResourceListBuilder
from resync.mapper import Mapper
class TestResourceListBuilder(unittest.TestCase):
def setUp(self):
@ -12,111 +13,113 @@ class TestResourceListBuilder(unittest.TestCase):
# in UTC so no conversion issues.
# Test case file_a: 1343236426 = 2012-07-25T17:13:46Z
# Test case file_b: 1000000000 = 2001-09-09T01:46:40Z
os.utime( "tests/testdata/dir1/file_a", (0, 1343236426 ) )
os.utime( "tests/testdata/dir1/file_b", (0, 1000000000 ) )
os.utime("tests/testdata/dir1/file_a", (0, 1343236426))
os.utime("tests/testdata/dir1/file_b", (0, 1000000000))
def test01_simple_scan(self):
rlb = ResourceListBuilder()
rlb.mapper = Mapper(['http://example.org/t','tests/testdata/dir1'])
rlb.mapper = Mapper(['http://example.org/t', 'tests/testdata/dir1'])
rl = rlb.from_disk()
self.assertEqual( len(rl), 2 )
self.assertEqual(len(rl), 2)
rli = iter(rl)
r = next(rli)
self.assertEqual( r.uri, 'http://example.org/t/file_a' )
self.assertEqual( r.lastmod, '2012-07-25T17:13:46Z' )
self.assertEqual( r.md5, None )
self.assertEqual( r.length, 20 )
self.assertEqual( r.path, None )
self.assertEqual(r.uri, 'http://example.org/t/file_a')
self.assertEqual(r.lastmod, '2012-07-25T17:13:46Z')
self.assertEqual(r.md5, None)
self.assertEqual(r.length, 20)
self.assertEqual(r.path, None)
r = next(rli)
self.assertEqual( r.uri, 'http://example.org/t/file_b' )
self.assertEqual( r.lastmod, '2001-09-09T01:46:40Z' )
self.assertEqual( r.md5, None )
self.assertEqual( r.length, 45 )
self.assertEqual( r.path, None )
self.assertEqual(r.uri, 'http://example.org/t/file_b')
self.assertEqual(r.lastmod, '2001-09-09T01:46:40Z')
self.assertEqual(r.md5, None)
self.assertEqual(r.length, 45)
self.assertEqual(r.path, None)
# Make sure at and completed were set
self.assertTrue( rl.md_at is not None )
self.assertTrue( rl.md_completed is not None )
self.assertTrue(rl.md_at is not None)
self.assertTrue(rl.md_completed is not None)
def test02_no_length(self):
rlb = ResourceListBuilder(set_length=False)
rlb.mapper = Mapper(['http://example.org/t','tests/testdata/dir1'])
rlb.mapper = Mapper(['http://example.org/t', 'tests/testdata/dir1'])
rl = rlb.from_disk()
self.assertEqual( len(rl), 2 )
self.assertEqual(len(rl), 2)
rli = iter(rl)
r = next(rli)
self.assertEqual( r.uri, 'http://example.org/t/file_a' )
self.assertEqual( r.lastmod, '2012-07-25T17:13:46Z' )
self.assertEqual( r.md5, None )
self.assertEqual( r.length, None )
self.assertEqual( r.path, None )
self.assertEqual(r.uri, 'http://example.org/t/file_a')
self.assertEqual(r.lastmod, '2012-07-25T17:13:46Z')
self.assertEqual(r.md5, None)
self.assertEqual(r.length, None)
self.assertEqual(r.path, None)
r = next(rli)
self.assertEqual( r.uri, 'http://example.org/t/file_b' )
self.assertEqual( r.lastmod, '2001-09-09T01:46:40Z' )
self.assertEqual( r.md5, None )
self.assertEqual( r.length, None )
self.assertEqual( r.path, None )
self.assertEqual(r.uri, 'http://example.org/t/file_b')
self.assertEqual(r.lastmod, '2001-09-09T01:46:40Z')
self.assertEqual(r.md5, None)
self.assertEqual(r.length, None)
self.assertEqual(r.path, None)
def test03_set_md5(self):
rlb = ResourceListBuilder(set_md5=True)
rlb.mapper = Mapper(['http://example.org/t','tests/testdata/dir1'])
rlb.mapper = Mapper(['http://example.org/t', 'tests/testdata/dir1'])
rl = rlb.from_disk()
self.assertEqual( len(rl), 2 )
self.assertEqual(len(rl), 2)
rli = iter(rl)
r = next(rli)
self.assertEqual( r.uri, 'http://example.org/t/file_a' )
self.assertEqual( r.lastmod, '2012-07-25T17:13:46Z' )
self.assertEqual( r.md5, 'a/Jv1mYBtSjS4LR+qoft/Q==' )
self.assertEqual( r.length, 20 )
self.assertEqual( r.path, None )
self.assertEqual(r.uri, 'http://example.org/t/file_a')
self.assertEqual(r.lastmod, '2012-07-25T17:13:46Z')
self.assertEqual(r.md5, 'a/Jv1mYBtSjS4LR+qoft/Q==')
self.assertEqual(r.length, 20)
self.assertEqual(r.path, None)
r = next(rli)
self.assertEqual( r.uri, 'http://example.org/t/file_b' )
self.assertEqual( r.lastmod, '2001-09-09T01:46:40Z' )
self.assertEqual( r.md5, 'RS5Uva4WJqxdbnvoGzneIQ==' )
self.assertEqual( r.length, 45 )
self.assertEqual( r.path, None )
self.assertEqual(r.uri, 'http://example.org/t/file_b')
self.assertEqual(r.lastmod, '2001-09-09T01:46:40Z')
self.assertEqual(r.md5, 'RS5Uva4WJqxdbnvoGzneIQ==')
self.assertEqual(r.length, 45)
self.assertEqual(r.path, None)
def test04_data(self):
rlb = ResourceListBuilder(set_path=True,set_md5=True)
rlb.mapper = Mapper(['http://example.org/t','tests/testdata/dir1'])
rlb = ResourceListBuilder(set_path=True, set_md5=True)
rlb.mapper = Mapper(['http://example.org/t', 'tests/testdata/dir1'])
rl = rlb.from_disk()
self.assertEqual( len(rl), 2)
self.assertEqual(len(rl), 2)
r = rl.resources.get('http://example.org/t/file_a')
self.assertTrue( r is not None )
self.assertEqual( r.uri, 'http://example.org/t/file_a' )
self.assertEqual( r.lastmod, '2012-07-25T17:13:46Z' )
self.assertEqual( r.md5, 'a/Jv1mYBtSjS4LR+qoft/Q==' )
self.assertEqual( r.path, 'tests/testdata/dir1/file_a' )
self.assertTrue(r is not None)
self.assertEqual(r.uri, 'http://example.org/t/file_a')
self.assertEqual(r.lastmod, '2012-07-25T17:13:46Z')
self.assertEqual(r.md5, 'a/Jv1mYBtSjS4LR+qoft/Q==')
self.assertEqual(r.path, 'tests/testdata/dir1/file_a')
def test05_from_disk_paths(self):
rlb = ResourceListBuilder()
rlb.mapper = Mapper(['http://example.org/t','tests/testdata/dir1'])
rlb.mapper = Mapper(['http://example.org/t', 'tests/testdata/dir1'])
# no path, should get no resources
rl = rlb.from_disk(paths=[])
self.assertEqual( len(rl), 0)
self.assertEqual(len(rl), 0)
# full path, 2 resources
rl = rlb.from_disk(paths=['tests/testdata/dir1'])
self.assertEqual( len(rl), 2)
self.assertEqual(len(rl), 2)
# new object with mapper covering larger space of disk
rlb = ResourceListBuilder(set_path=True)
rlb.mapper = Mapper(['http://example.org/t','tests/testdata'])
rlb.mapper = Mapper(['http://example.org/t', 'tests/testdata'])
# same path with 2 resources
rl = rlb.from_disk(paths=['tests/testdata/dir1'])
self.assertEqual( len(rl), 2)
self.assertEqual(len(rl), 2)
# same path with 2 resources
rl = rlb.from_disk(paths=['tests/testdata/dir1','tests/testdata/dir2'])
self.assertEqual( len(rl), 3)
rl = rlb.from_disk(
paths=['tests/testdata/dir1', 'tests/testdata/dir2'])
self.assertEqual(len(rl), 3)
# path that is just a single file
rl = rlb.from_disk(paths=['tests/testdata/dir1/file_a'])
self.assertEqual( len(rl), 1)
self.assertEqual(len(rl), 1)
rli = iter(rl)
r = next(rli)
self.assertTrue( r is not None )
self.assertEqual( r.uri, 'http://example.org/t/dir1/file_a' )
self.assertEqual( r.lastmod, '2012-07-25T17:13:46Z' )
self.assertEqual( r.md5, None )
self.assertEqual( r.length, 20 )
self.assertEqual( r.path, 'tests/testdata/dir1/file_a' )
self.assertTrue(r is not None)
self.assertEqual(r.uri, 'http://example.org/t/dir1/file_a')
self.assertEqual(r.lastmod, '2012-07-25T17:13:46Z')
self.assertEqual(r.md5, None)
self.assertEqual(r.length, 20)
self.assertEqual(r.path, 'tests/testdata/dir1/file_a')
if __name__ == '__main__':
suite = unittest.defaultTestLoader.loadTestsFromTestCase(TestResourceListBuilder)
suite = unittest.defaultTestLoader.loadTestsFromTestCase(
TestResourceListBuilder)
unittest.TextTestRunner(verbosity=2).run(suite)

94
tests/test_resource_list_multifile.py
View File

@ -11,91 +11,95 @@ from resync.mapper import Mapper
# etree gives ParseError in 2.7, ExpatError in 2.6
etree_error_class = None
if (sys.version_info < (2,7)):
if (sys.version_info < (2, 7)):
from xml.parsers.expat import ExpatError
etree_error_class = ExpatError
else:
from xml.etree.ElementTree import ParseError
etree_error_class = ParseError
class TestResourceListMultifile(unittest.TestCase):
def test_01_read_local_filenames(self):
rl = ResourceList()
rl.read('tests/testdata/sitemapindex2/sitemap.xml')
self.assertEqual( len(rl.resources), 17, '17 resources from 3 sitemaps listed')
self.assertEqual(len(rl.resources), 17,
'17 resources from 3 sitemaps listed')
sr = sorted(rl.uris())
self.assertEqual( sr[0], 'http://localhost:8888/resources/1' )
self.assertEqual( sr[1], 'http://localhost:8888/resources/10' )
self.assertEqual( sr[2], 'http://localhost:8888/resources/100' )
self.assertEqual( sr[3], 'http://localhost:8888/resources/1000' )
self.assertEqual( sr[16], 'http://localhost:8888/resources/826' )
self.assertEqual(sr[0], 'http://localhost:8888/resources/1')
self.assertEqual(sr[1], 'http://localhost:8888/resources/10')
self.assertEqual(sr[2], 'http://localhost:8888/resources/100')
self.assertEqual(sr[3], 'http://localhost:8888/resources/1000')
self.assertEqual(sr[16], 'http://localhost:8888/resources/826')
def test_02_read_with_mapper(self):
rl = ResourceList()
rl.mapper = Mapper(['http://localhost/=tests/testdata/sitemapindex2/'])
rl.read('tests/testdata/sitemapindex2/sitemap_mapper.xml')
self.assertEqual( len(rl.resources), 17, '17 resources from 3 sitemaps listed')
self.assertEqual(len(rl.resources), 17,
'17 resources from 3 sitemaps listed')
sr = sorted(rl.uris())
self.assertEqual( sr[0], 'http://localhost:8888/resources/1' )
self.assertEqual( sr[1], 'http://localhost:8888/resources/10' )
self.assertEqual( sr[2], 'http://localhost:8888/resources/100' )
self.assertEqual( sr[3], 'http://localhost:8888/resources/1000' )
self.assertEqual( sr[16], 'http://localhost:8888/resources/826' )
self.assertEqual(sr[0], 'http://localhost:8888/resources/1')
self.assertEqual(sr[1], 'http://localhost:8888/resources/10')
self.assertEqual(sr[2], 'http://localhost:8888/resources/100')
self.assertEqual(sr[3], 'http://localhost:8888/resources/1000')
self.assertEqual(sr[16], 'http://localhost:8888/resources/826')
def test_11_write_multifile(self):
tempdir = tempfile.mkdtemp(prefix='test_resource_list_multifile')
rl = ResourceList()
rl.mapper = Mapper(['http://localhost/=%s/' % (tempdir)])
rl.add( Resource( uri='http://localhost/a' ) )
rl.add( Resource( uri='http://localhost/b' ) )
rl.add( Resource( uri='http://localhost/c' ) )
rl.add( Resource( uri='http://localhost/d' ) )
rl.add(Resource(uri='http://localhost/a'))
rl.add(Resource(uri='http://localhost/b'))
rl.add(Resource(uri='http://localhost/c'))
rl.add(Resource(uri='http://localhost/d'))
rl.max_sitemap_entries = 2
# first try writing without mutlifile allowed
rl.allow_multifile = False
self.assertRaises( ListBaseIndexError, rl.write, basename=os.path.join(tempdir,'sitemap.xml') )
self.assertRaises(ListBaseIndexError, rl.write,
basename=os.path.join(tempdir, 'sitemap.xml'))
# second actually do it
rl.allow_multifile = True
rl.write( basename = os.path.join(tempdir,'sitemap.xml') )
rl.write(basename=os.path.join(tempdir, 'sitemap.xml'))
# check the two component sitemaps
rl1 = ResourceList()
rl1.read( os.path.join(tempdir,'sitemap00000.xml') )
self.assertEquals( len(rl1), 2 )
self.assertEquals( rl1.capability, 'resourcelist' )
self.assertFalse( rl1.sitemapindex )
rl1.read(os.path.join(tempdir, 'sitemap00000.xml'))
self.assertEquals(len(rl1), 2)
self.assertEquals(rl1.capability, 'resourcelist')
self.assertFalse(rl1.sitemapindex)
i = iter(rl1)
self.assertEquals( next(i).uri, 'http://localhost/a' )
self.assertEquals( next(i).uri, 'http://localhost/b' )
self.assertEquals(next(i).uri, 'http://localhost/a')
self.assertEquals(next(i).uri, 'http://localhost/b')
rl2 = ResourceList()
rl2.read( os.path.join(tempdir,'sitemap00001.xml') )
self.assertEquals( len(rl2), 2 )
rl2.read(os.path.join(tempdir, 'sitemap00001.xml'))
self.assertEquals(len(rl2), 2)
i = iter(rl2)
self.assertEquals( next(i).uri, 'http://localhost/c' )
self.assertEquals( next(i).uri, 'http://localhost/d' )
self.assertEquals(next(i).uri, 'http://localhost/c')
self.assertEquals(next(i).uri, 'http://localhost/d')
# check the sitemapindex (read just as index)
rli = ResourceList()
rli.read( os.path.join(tempdir,'sitemap.xml'), index_only=True )
self.assertEquals( len(rli), 2 )
rli.read(os.path.join(tempdir, 'sitemap.xml'), index_only=True)
self.assertEquals(len(rli), 2)
i = iter(rli)
self.assertEquals( rli.capability, 'resourcelist' )
self.assertTrue( rli.sitemapindex )
self.assertEquals( next(i).uri, 'http://localhost/sitemap00000.xml' )
self.assertEquals( next(i).uri, 'http://localhost/sitemap00001.xml' )
self.assertEquals(rli.capability, 'resourcelist')
self.assertTrue(rli.sitemapindex)
self.assertEquals(next(i).uri, 'http://localhost/sitemap00000.xml')
self.assertEquals(next(i).uri, 'http://localhost/sitemap00001.xml')
# check the sitemapindex and components
rli = ResourceList( mapper=rl.mapper )
rli.read( os.path.join(tempdir,'sitemap.xml') )
self.assertEquals( len(rli), 4 )
self.assertEquals( rli.capability, 'resourcelist' )
self.assertFalse( rli.sitemapindex )
rli = ResourceList(mapper=rl.mapper)
rli.read(os.path.join(tempdir, 'sitemap.xml'))
self.assertEquals(len(rli), 4)
self.assertEquals(rli.capability, 'resourcelist')
self.assertFalse(rli.sitemapindex)
i = iter(rli)
self.assertEquals( next(i).uri, 'http://localhost/a' )
self.assertEquals( next(i).uri, 'http://localhost/b' )
self.assertEquals( next(i).uri, 'http://localhost/c' )
self.assertEquals( next(i).uri, 'http://localhost/d' )
self.assertEquals(next(i).uri, 'http://localhost/a')
self.assertEquals(next(i).uri, 'http://localhost/b')
self.assertEquals(next(i).uri, 'http://localhost/c')
self.assertEquals(next(i).uri, 'http://localhost/d')
# cleanup tempdir
shutil.rmtree(tempdir)
if __name__ == '__main__':
if __name__ == '__main__':
suite = unittest.TestLoader().loadTestsFromTestCase(TestResourceListMultifile)
unittest.TextTestRunner(verbosity=2).run(suite)

39
tests/test_resource_set.py
View File

@ -1,37 +1,38 @@
import unittest
import re
from resync.resource import Resource
from resync.resource_set import ResourceSet,ResourceSetDupeError
from resync.resource_set import ResourceSet, ResourceSetDupeError
class TestResourceSet(unittest.TestCase):
def test01_add(self):
rs = ResourceSet()
self.assertEqual( len(rs), 0 )
rs.add( Resource('a') )
self.assertEqual( len(rs), 1 )
rs.add( Resource('b') )
self.assertEqual( len(rs), 2 )
rs.add( Resource('c') )
self.assertEqual( len(rs), 3 )
self.assertEqual(len(rs), 0)
rs.add(Resource('a'))
self.assertEqual(len(rs), 1)
rs.add(Resource('b'))
self.assertEqual(len(rs), 2)
rs.add(Resource('c'))
self.assertEqual(len(rs), 3)
def test02_order(self):
rs = ResourceSet()
rs.add( Resource('a2') )
rs.add( Resource('a3') )
rs.add( Resource('a1') )
rs.add(Resource('a2'))
rs.add(Resource('a3'))
rs.add(Resource('a1'))
i = iter(rs)
self.assertEqual( next(i).uri, 'a1' )
self.assertEqual( next(i).uri, 'a2' )
self.assertEqual( next(i).uri, 'a3' )
self.assertRaises( StopIteration, next, i )
self.assertEqual(next(i).uri, 'a1')
self.assertEqual(next(i).uri, 'a2')
self.assertEqual(next(i).uri, 'a3')
self.assertRaises(StopIteration, next, i)
def test03_dupe(self):
rs = ResourceSet()
self.assertEqual( len(rs), 0 )
rs.add( Resource('a') )
self.assertEqual( len(rs), 1 )
self.assertRaises( ResourceSetDupeError, rs.add, Resource('a') )
self.assertEqual(len(rs), 0)
rs.add(Resource('a'))
self.assertEqual(len(rs), 1)
self.assertRaises(ResourceSetDupeError, rs.add, Resource('a'))
if __name__ == '__main__':

315
tests/test_sitemap.py
View File

@ -1,10 +1,10 @@
import sys
import unittest
try: #python2
try: # python2
# Must try this first as io also exists in python2
# but in the wrong one!
import StringIO as io
except ImportError: #python3
except ImportError: # python3
import io
from resync.resource import Resource
@ -13,159 +13,173 @@ from resync.sitemap import Sitemap, SitemapIndexError, SitemapParseError
# etree gives ParseError in 2.7,3.x; ExpatError in 2.6
etree_error_class = None
if (sys.version_info < (2,7)):
if (sys.version_info < (2, 7)):
from xml.parsers.expat import ExpatError
etree_error_class = ExpatError
else:
#In python3 this seems only to work with the full class name??
#from xml.etree.ElementTree import ParseError
# In python3 this seems only to work with the full class name??
# from xml.etree.ElementTree import ParseError
import xml.etree.ElementTree
etree_error_class = xml.etree.ElementTree.ParseError
class TestSitemap(unittest.TestCase):
def test_01_resource_str(self):
r1 = Resource('a3')
r1.lastmod='2012-01-11T01:02:03Z'
self.assertEqual( Sitemap().resource_as_xml(r1), "<url><loc>a3</loc><lastmod>2012-01-11T01:02:03Z</lastmod></url>" )
r1.lastmod = '2012-01-11T01:02:03Z'
self.assertEqual(Sitemap().resource_as_xml(
r1), "<url><loc>a3</loc><lastmod>2012-01-11T01:02:03Z</lastmod></url>")
def test_02_resource_str(self):
r1 = Resource('3b',1234.1,9999,'ab54de')
self.assertEqual( Sitemap().resource_as_xml(r1), "<url><loc>3b</loc><lastmod>1970-01-01T00:20:34.100000Z</lastmod><rs:md hash=\"md5:ab54de\" length=\"9999\" /></url>" )
r1 = Resource('3b', 1234.1, 9999, 'ab54de')
self.assertEqual(Sitemap().resource_as_xml(
r1), "<url><loc>3b</loc><lastmod>1970-01-01T00:20:34.100000Z</lastmod><rs:md hash=\"md5:ab54de\" length=\"9999\" /></url>")
def test_03_resource_str_hashes(self):
r1 = Resource('03hashes',1234.1)
r1 = Resource('03hashes', 1234.1)
r1.md5 = 'aaa'
r1.sha1 = 'bbb'
self.assertEqual( Sitemap().resource_as_xml(r1), "<url><loc>03hashes</loc><lastmod>1970-01-01T00:20:34.100000Z</lastmod><rs:md hash=\"md5:aaa sha-1:bbb\" /></url>" )
self.assertEqual(Sitemap().resource_as_xml(
r1), "<url><loc>03hashes</loc><lastmod>1970-01-01T00:20:34.100000Z</lastmod><rs:md hash=\"md5:aaa sha-1:bbb\" /></url>")
r1.sha256 = 'ccc'
self.assertEqual( Sitemap().resource_as_xml(r1), "<url><loc>03hashes</loc><lastmod>1970-01-01T00:20:34.100000Z</lastmod><rs:md hash=\"md5:aaa sha-1:bbb sha-256:ccc\" /></url>" )
self.assertEqual(Sitemap().resource_as_xml(
r1), "<url><loc>03hashes</loc><lastmod>1970-01-01T00:20:34.100000Z</lastmod><rs:md hash=\"md5:aaa sha-1:bbb sha-256:ccc\" /></url>")
r1.sha1 = None
self.assertEqual( Sitemap().resource_as_xml(r1), "<url><loc>03hashes</loc><lastmod>1970-01-01T00:20:34.100000Z</lastmod><rs:md hash=\"md5:aaa sha-256:ccc\" /></url>" )
self.assertEqual(Sitemap().resource_as_xml(
r1), "<url><loc>03hashes</loc><lastmod>1970-01-01T00:20:34.100000Z</lastmod><rs:md hash=\"md5:aaa sha-256:ccc\" /></url>")
def test_04_resource_str(self):
r1 = Resource(uri='4a',lastmod="2013-01-02",length=9999,md5='ab54de')
r1.ln = [{ 'rel':'duplicate',
'pri':'1',
'href':'http://mirror1.example.com/res1',
'modified':'2013-01-02T18:00:00Z' }]
self.assertEqual( Sitemap().resource_as_xml(r1), "<url><loc>4a</loc><lastmod>2013-01-02T00:00:00Z</lastmod><rs:md hash=\"md5:ab54de\" length=\"9999\" /><rs:ln href=\"http://mirror1.example.com/res1\" modified=\"2013-01-02T18:00:00Z\" pri=\"1\" rel=\"duplicate\" /></url>" )
r1 = Resource(uri='4a', lastmod="2013-01-02",
length=9999, md5='ab54de')
r1.ln = [{'rel': 'duplicate',
'pri': '1',
'href': 'http://mirror1.example.com/res1',
'modified': '2013-01-02T18:00:00Z'}]
self.assertEqual(Sitemap().resource_as_xml(
r1), "<url><loc>4a</loc><lastmod>2013-01-02T00:00:00Z</lastmod><rs:md hash=\"md5:ab54de\" length=\"9999\" /><rs:ln href=\"http://mirror1.example.com/res1\" modified=\"2013-01-02T18:00:00Z\" pri=\"1\" rel=\"duplicate\" /></url>")
# add another two rs:ln's
r1.ln.append( { 'rel':'num2' } )
r1.ln.append( { 'rel':'num3' } )
self.assertEqual( Sitemap().resource_as_xml(r1), "<url><loc>4a</loc><lastmod>2013-01-02T00:00:00Z</lastmod><rs:md hash=\"md5:ab54de\" length=\"9999\" /><rs:ln href=\"http://mirror1.example.com/res1\" modified=\"2013-01-02T18:00:00Z\" pri=\"1\" rel=\"duplicate\" /><rs:ln rel=\"num2\" /><rs:ln rel=\"num3\" /></url>" )
r1.ln.append({'rel': 'num2'})
r1.ln.append({'rel': 'num3'})
self.assertEqual(Sitemap().resource_as_xml(
r1), "<url><loc>4a</loc><lastmod>2013-01-02T00:00:00Z</lastmod><rs:md hash=\"md5:ab54de\" length=\"9999\" /><rs:ln href=\"http://mirror1.example.com/res1\" modified=\"2013-01-02T18:00:00Z\" pri=\"1\" rel=\"duplicate\" /><rs:ln rel=\"num2\" /><rs:ln rel=\"num3\" /></url>")
def test_08_print(self):
r1 = Resource(uri='a',lastmod='2001-01-01',length=1234)
r2 = Resource(uri='b',lastmod='2002-02-02',length=56789)
r3 = Resource(uri='c',lastmod='2003-03-03',length=0)
m = ResourceList(md={'capability':'resourcelist','modified':None})
r1 = Resource(uri='a', lastmod='2001-01-01', length=1234)
r2 = Resource(uri='b', lastmod='2002-02-02', length=56789)
r3 = Resource(uri='c', lastmod='2003-03-03', length=0)
m = ResourceList(md={'capability': 'resourcelist', 'modified': None})
m.add(r1)
m.add(r2)
m.add(r3)
#print m
self.assertEqual( Sitemap().resources_as_xml(m), "<?xml version='1.0' encoding='UTF-8'?>\n<urlset xmlns=\"http://www.sitemaps.org/schemas/sitemap/0.9\" xmlns:rs=\"http://www.openarchives.org/rs/terms/\"><rs:md capability=\"resourcelist\" /><url><loc>a</loc><lastmod>2001-01-01T00:00:00Z</lastmod><rs:md length=\"1234\" /></url><url><loc>b</loc><lastmod>2002-02-02T00:00:00Z</lastmod><rs:md length=\"56789\" /></url><url><loc>c</loc><lastmod>2003-03-03T00:00:00Z</lastmod><rs:md length=\"0\" /></url></urlset>")
# print m
self.assertEqual(Sitemap().resources_as_xml(m), "<?xml version='1.0' encoding='UTF-8'?>\n<urlset xmlns=\"http://www.sitemaps.org/schemas/sitemap/0.9\" xmlns:rs=\"http://www.openarchives.org/rs/terms/\"><rs:md capability=\"resourcelist\" /><url><loc>a</loc><lastmod>2001-01-01T00:00:00Z</lastmod><rs:md length=\"1234\" /></url><url><loc>b</loc><lastmod>2002-02-02T00:00:00Z</lastmod><rs:md length=\"56789\" /></url><url><loc>c</loc><lastmod>2003-03-03T00:00:00Z</lastmod><rs:md length=\"0\" /></url></urlset>")
def test_09_print_from_iter(self):
r1 = Resource(uri='a',lastmod='2001-01-01',length=1234)
r2 = Resource(uri='b',lastmod='2002-02-02',length=56789)
def test_09_print_from_iter(self):
r1 = Resource(uri='a', lastmod='2001-01-01', length=1234)
r2 = Resource(uri='b', lastmod='2002-02-02', length=56789)
m = ResourceList()
m.add(r1)
m.add(r2)
i = iter(m)
self.assertEqual( Sitemap().resources_as_xml(i), "<?xml version='1.0' encoding='UTF-8'?>\n<urlset xmlns=\"http://www.sitemaps.org/schemas/sitemap/0.9\" xmlns:rs=\"http://www.openarchives.org/rs/terms/\"><url><loc>a</loc><lastmod>2001-01-01T00:00:00Z</lastmod><rs:md length=\"1234\" /></url><url><loc>b</loc><lastmod>2002-02-02T00:00:00Z</lastmod><rs:md length=\"56789\" /></url></urlset>")
self.assertEqual(Sitemap().resources_as_xml(i), "<?xml version='1.0' encoding='UTF-8'?>\n<urlset xmlns=\"http://www.sitemaps.org/schemas/sitemap/0.9\" xmlns:rs=\"http://www.openarchives.org/rs/terms/\"><url><loc>a</loc><lastmod>2001-01-01T00:00:00Z</lastmod><rs:md length=\"1234\" /></url><url><loc>b</loc><lastmod>2002-02-02T00:00:00Z</lastmod><rs:md length=\"56789\" /></url></urlset>")
def test_10_sitemap(self):
xml='<?xml version=\'1.0\' encoding=\'UTF-8\'?>\n\
xml = '<?xml version=\'1.0\' encoding=\'UTF-8\'?>\n\
<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9" xmlns:rs="http://www.openarchives.org/rs/terms/">\
<url><loc>http://e.com/a</loc><lastmod>2012-03-14T18:37:36Z</lastmod><rs:md hash="md5:Q2hlY2sgSW50ZWdyaXR5IQ==" length=\"12\" /></url>\
</urlset>'
s=Sitemap()
i=s.parse_xml(fh=io.StringIO(xml))
self.assertFalse( s.parsed_index, 'was a sitemap')
self.assertEqual( s.resources_created, 1, 'got 1 resources')
s = Sitemap()
i = s.parse_xml(fh=io.StringIO(xml))
self.assertFalse(s.parsed_index, 'was a sitemap')
self.assertEqual(s.resources_created, 1, 'got 1 resources')
for r in i.resources:
self.assertTrue( r is not None, 'got the uri expected')
self.assertEqual( r.uri, 'http://e.com/a' )
self.assertEqual( r.lastmod, '2012-03-14T18:37:36Z' )
self.assertEqual( r.length, 12 )
self.assertEqual( r.md5, 'Q2hlY2sgSW50ZWdyaXR5IQ==' )
self.assertTrue(r is not None, 'got the uri expected')
self.assertEqual(r.uri, 'http://e.com/a')
self.assertEqual(r.lastmod, '2012-03-14T18:37:36Z')
self.assertEqual(r.length, 12)
self.assertEqual(r.md5, 'Q2hlY2sgSW50ZWdyaXR5IQ==')
def test_11_parse_2(self):
xml='<?xml version=\'1.0\' encoding=\'UTF-8\'?>\n\
xml = '<?xml version=\'1.0\' encoding=\'UTF-8\'?>\n\
<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9" xmlns:rs="http://www.openarchives.org/rs/terms/">\
<url><loc>/tmp/rs_test/src/file_a</loc><lastmod>2012-03-14T18:37:36Z</lastmod><rs:md length=\"12\" /></url>\
<url><loc>/tmp/rs_test/src/file_b</loc><lastmod>2012-03-14T18:37:36Z</lastmod><rs:md length=\"32\" /></url>\
</urlset>'
s=Sitemap()
i=s.parse_xml(fh=io.StringIO(xml))
self.assertFalse( s.parsed_index, 'was a sitemap')
self.assertEqual( s.resources_created, 2, 'got 2 resources')
s = Sitemap()
i = s.parse_xml(fh=io.StringIO(xml))
self.assertFalse(s.parsed_index, 'was a sitemap')
self.assertEqual(s.resources_created, 2, 'got 2 resources')
def test_12_parse_multi_loc(self):
xml_start='<?xml version=\'1.0\' encoding=\'UTF-8\'?>\n\
xml_start = '<?xml version=\'1.0\' encoding=\'UTF-8\'?>\n\
<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9" xmlns:rs="http://www.openarchives.org/rs/terms/">\
<url>'
xml_end='<lastmod>2012-03-14T18:37:36Z</lastmod></url></urlset>'
s=Sitemap()
two_loc='<loc>/tmp/rs_test/src/file_a</loc><loc>/tmp/rs_test/src/file_b</loc>'
self.assertRaises( SitemapParseError, s.parse_xml,
io.StringIO(xml_start+two_loc+xml_end))
mt_loc='<loc></loc>'
self.assertRaises( SitemapParseError, s.parse_xml,
io.StringIO(xml_start+mt_loc+xml_end))
mt_loc_att='<loc att="value"/>'
self.assertRaises( SitemapParseError, s.parse_xml,
io.StringIO(xml_start+mt_loc_att+xml_end))
xml_end = '<lastmod>2012-03-14T18:37:36Z</lastmod></url></urlset>'
s = Sitemap()
two_loc = '<loc>/tmp/rs_test/src/file_a</loc><loc>/tmp/rs_test/src/file_b</loc>'
self.assertRaises(SitemapParseError, s.parse_xml,
io.StringIO(xml_start + two_loc + xml_end))
mt_loc = '<loc></loc>'
self.assertRaises(SitemapParseError, s.parse_xml,
io.StringIO(xml_start + mt_loc + xml_end))
mt_loc_att = '<loc att="value"/>'
self.assertRaises(SitemapParseError, s.parse_xml,
io.StringIO(xml_start + mt_loc_att + xml_end))
def test_13_parse_multi_lastmod(self):
xml_start='<?xml version=\'1.0\' encoding=\'UTF-8\'?>\n\
xml_start = '<?xml version=\'1.0\' encoding=\'UTF-8\'?>\n\
<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9" xmlns:rs="http://www.openarchives.org/rs/terms/">\
<url><loc>uri:a</loc>'
xml_end='</url></urlset>'
s=Sitemap()
two_lastmod='<lastmod>2013-01-01</lastmod><lastmod>2013-01-02</lastmod>'
self.assertRaises( SitemapParseError, s.parse_xml,
io.StringIO(xml_start+two_lastmod+xml_end))
xml_end = '</url></urlset>'
s = Sitemap()
two_lastmod = '<lastmod>2013-01-01</lastmod><lastmod>2013-01-02</lastmod>'
self.assertRaises(SitemapParseError, s.parse_xml,
io.StringIO(xml_start + two_lastmod + xml_end))
# While it not ideal to omit, <lastmod> is not required and
# thus either empty lastmod or lastmod with just an attribute
# and no content are not ambiguous and thus should be accepted
# with resulting None for resource.lastmod
mt_lastmod='<lastmod></lastmod>'
i=s.parse_xml(fh=io.StringIO(xml_start+mt_lastmod+xml_end))
self.assertEqual( s.resources_created, 1 )
self.assertEqual( i.resources[0].lastmod, None )
mt_lastmod_att='<lastmod att="value"/>'
i=s.parse_xml(fh=io.StringIO(xml_start+mt_lastmod_att+xml_end))
self.assertEqual( s.resources_created, 1 )
self.assertEqual( i.resources[0].lastmod, None )
mt_lastmod = '<lastmod></lastmod>'
i = s.parse_xml(fh=io.StringIO(xml_start + mt_lastmod + xml_end))
self.assertEqual(s.resources_created, 1)
self.assertEqual(i.resources[0].lastmod, None)
mt_lastmod_att = '<lastmod att="value"/>'
i = s.parse_xml(fh=io.StringIO(xml_start + mt_lastmod_att + xml_end))
self.assertEqual(s.resources_created, 1)
self.assertEqual(i.resources[0].lastmod, None)
def test_14_parse_multi(self):
xml_start='<?xml version=\'1.0\' encoding=\'UTF-8\'?>\n\
xml_start = '<?xml version=\'1.0\' encoding=\'UTF-8\'?>\n\
<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9" xmlns:rs="http://www.openarchives.org/rs/terms/">'
xml_end='<url><loc>uri:a</loc></url></urlset>'
s=Sitemap()
two_md='<rs:md capability="resourcelist"/><rs:md capability="resourcelist"/>'
self.assertRaises( SitemapParseError, s.parse_xml,
io.StringIO(xml_start+two_md+xml_end))
xml_end = '<url><loc>uri:a</loc></url></urlset>'
s = Sitemap()
two_md = '<rs:md capability="resourcelist"/><rs:md capability="resourcelist"/>'
self.assertRaises(SitemapParseError, s.parse_xml,
io.StringIO(xml_start + two_md + xml_end))
def test_15_parse_illformed(self):
s=Sitemap()
s = Sitemap()
# ExpatError in python2.6, ParserError in 2.7,3.x
self.assertRaises( etree_error_class, s.parse_xml, io.StringIO('not xml') )
self.assertRaises( etree_error_class, s.parse_xml, io.StringIO('<urlset><url>something</urlset>') )
self.assertRaises(etree_error_class, s.parse_xml,
io.StringIO('not xml'))
self.assertRaises(etree_error_class, s.parse_xml,
io.StringIO('<urlset><url>something</urlset>'))
def test_16_parse_valid_xml_but_other(self):
s=Sitemap()
self.assertRaises( SitemapParseError, s.parse_xml, io.StringIO('<urlset xmlns="http://example.org/other_namespace"> </urlset>') )
self.assertRaises( SitemapParseError, s.parse_xml, io.StringIO('<other xmlns="http://www.sitemaps.org/schemas/sitemap/0.9"> </other>') )
s = Sitemap()
self.assertRaises(SitemapParseError, s.parse_xml, io.StringIO(
'<urlset xmlns="http://example.org/other_namespace"> </urlset>'))
self.assertRaises(SitemapParseError, s.parse_xml, io.StringIO(
'<other xmlns="http://www.sitemaps.org/schemas/sitemap/0.9"> </other>'))
def test_17_parse_sitemapindex_as_sitemap(self):
s=Sitemap()
self.assertRaises( SitemapIndexError, s.parse_xml, io.StringIO('<sitemapindex xmlns="http://www.sitemaps.org/schemas/sitemap/0.9"> </sitemapindex>'), sitemapindex=False )
s = Sitemap()
self.assertRaises(SitemapIndexError, s.parse_xml, io.StringIO(
'<sitemapindex xmlns="http://www.sitemaps.org/schemas/sitemap/0.9"> </sitemapindex>'), sitemapindex=False)
def test_18_parse_with_rs_ln_on_resource(self):
xml='<?xml version=\'1.0\' encoding=\'UTF-8\'?>\n\
xml = '<?xml version=\'1.0\' encoding=\'UTF-8\'?>\n\
<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9" xmlns:rs="http://www.openarchives.org/rs/terms/">\
<rs:md capability=\"resourcelist\"/>\
<url>\
@ -180,103 +194,108 @@ class TestSitemap(unittest.TestCase):
<rs:md length=\"32\" />\
</url>\
</urlset>'
s=Sitemap()
rc=s.parse_xml(fh=io.StringIO(xml))
self.assertFalse( s.parsed_index, 'was a sitemap')
self.assertEqual( s.resources_created, 2, 'got 2 resources')
s = Sitemap()
rc = s.parse_xml(fh=io.StringIO(xml))
self.assertFalse(s.parsed_index, 'was a sitemap')
self.assertEqual(s.resources_created, 2, 'got 2 resources')
i = iter(rc)
r1 = next(i)
r2 = next(i)
self.assertEqual( r1.uri, 'http://example.com/file_a' )
self.assertEqual( r1.ln[0]['rel'], 'duplicate' )
self.assertEqual( r1.ln[0]['href'], 'http://mirror1.example.com/res1' )
self.assertEqual( r1.ln[0]['modified'], '2013-01-02' )
self.assertEqual( r1.ln[0]['pri'], 1 )
self.assertEqual( r2.uri, 'http://example.com/file_b' )
self.assertEqual(r1.uri, 'http://example.com/file_a')
self.assertEqual(r1.ln[0]['rel'], 'duplicate')
self.assertEqual(r1.ln[0]['href'], 'http://mirror1.example.com/res1')
self.assertEqual(r1.ln[0]['modified'], '2013-01-02')
self.assertEqual(r1.ln[0]['pri'], 1)
self.assertEqual(r2.uri, 'http://example.com/file_b')
def test_19_parse_with_bad_rs_ln(self):
xmlstart='<?xml version=\'1.0\' encoding=\'UTF-8\'?>\n\
xmlstart = '<?xml version=\'1.0\' encoding=\'UTF-8\'?>\n\
<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9" xmlns:rs="http://www.openarchives.org/rs/terms/">\
<rs:md capability="resourcelist"/>\
<url><loc>http://example.com/file_a</loc>'
xmlend='</url></urlset>'
s=Sitemap()
xmlend = '</url></urlset>'
s = Sitemap()
#
# missing href
xml=xmlstart+'<rs:ln rel="duplicate"/>'+xmlend
self.assertRaises( SitemapParseError, s.parse_xml, fh=io.StringIO(xml))
xml = xmlstart + '<rs:ln rel="duplicate"/>' + xmlend
self.assertRaises(SitemapParseError, s.parse_xml, fh=io.StringIO(xml))
# missing rel
xml=xmlstart+'<rs:ln href="http://example.com/"/>'+xmlend
self.assertRaises( SitemapParseError, s.parse_xml, fh=io.StringIO(xml))
xml = xmlstart + '<rs:ln href="http://example.com/"/>' + xmlend
self.assertRaises(SitemapParseError, s.parse_xml, fh=io.StringIO(xml))
# bad length
xml=xmlstart+'<rs:ln rel="duplicate" href="http://example.com/" length="a"/>'+xmlend
self.assertRaises( SitemapParseError, s.parse_xml, fh=io.StringIO(xml))
xml = xmlstart + '<rs:ln rel="duplicate" href="http://example.com/" length="a"/>' + xmlend
self.assertRaises(SitemapParseError, s.parse_xml, fh=io.StringIO(xml))
# bad pri
xml=xmlstart+'<rs:ln rel="duplicate" href="http://example.com/" pri="fff"/>'+xmlend
self.assertRaises( SitemapParseError, s.parse_xml, fh=io.StringIO(xml))
xml=xmlstart+'<rs:ln rel="duplicate" href="http://example.com/" pri="0"/>'+xmlend
self.assertRaises( SitemapParseError, s.parse_xml, fh=io.StringIO(xml))
xml=xmlstart+'<rs:ln rel="duplicate" href="http://example.com/" pri="1000000"/>'+xmlend
self.assertRaises( SitemapParseError, s.parse_xml, fh=io.StringIO(xml))
xml = xmlstart + '<rs:ln rel="duplicate" href="http://example.com/" pri="fff"/>' + xmlend
self.assertRaises(SitemapParseError, s.parse_xml, fh=io.StringIO(xml))
xml = xmlstart + '<rs:ln rel="duplicate" href="http://example.com/" pri="0"/>' + xmlend
self.assertRaises(SitemapParseError, s.parse_xml, fh=io.StringIO(xml))
xml = xmlstart + '<rs:ln rel="duplicate" href="http://example.com/" pri="1000000"/>' + xmlend
self.assertRaises(SitemapParseError, s.parse_xml, fh=io.StringIO(xml))
# and finally OK with errors fixes
xml=xmlstart+'<rs:ln rel="duplicate" href="http://example.com/" length="12345" pri="1" other="whatever"/>'+xmlend
xml = xmlstart + '<rs:ln rel="duplicate" href="http://example.com/" length="12345" pri="1" other="whatever"/>' + xmlend
rc = s.parse_xml(fh=io.StringIO(xml))
self.assertEqual( len(rc.resources), 1, 'good at last, extra attribute ignored' )
self.assertEqual(len(rc.resources), 1,
'good at last, extra attribute ignored')
def test_20_parse_sitemapindex_empty(self):
s=Sitemap()
si = s.parse_xml( fh=io.StringIO('<sitemapindex xmlns="http://www.sitemaps.org/schemas/sitemap/0.9"> </sitemapindex>'), sitemapindex=True )
self.assertTrue( s.parsed_index, 'was a sitemapindex')
self.assertEqual( len(si.resources), 0, '0 sitemaps')
s = Sitemap()
si = s.parse_xml(fh=io.StringIO(
'<sitemapindex xmlns="http://www.sitemaps.org/schemas/sitemap/0.9"> </sitemapindex>'), sitemapindex=True)
self.assertTrue(s.parsed_index, 'was a sitemapindex')
self.assertEqual(len(si.resources), 0, '0 sitemaps')
def test_21_parse_sitemapindex(self):
s=Sitemap()
si = s.parse_xml( fh=io.StringIO('<sitemapindex xmlns="http://www.sitemaps.org/schemas/sitemap/0.9"><sitemap><loc>aaa</loc></sitemap><sitemap><loc>bbb</loc></sitemap></sitemapindex>'), sitemapindex=True )
self.assertEqual( len(si.resources), 2, '2 sitemaps')
s = Sitemap()
si = s.parse_xml(fh=io.StringIO(
'<sitemapindex xmlns="http://www.sitemaps.org/schemas/sitemap/0.9"><sitemap><loc>aaa</loc></sitemap><sitemap><loc>bbb</loc></sitemap></sitemapindex>'), sitemapindex=True)
self.assertEqual(len(si.resources), 2, '2 sitemaps')
sms = sorted(si.uris())
self.assertEqual( sms, ['aaa','bbb'] )
self.assertEqual(sms, ['aaa', 'bbb'])
# add a couple more
s.parse_xml( fh=io.StringIO('<sitemapindex xmlns="http://www.sitemaps.org/schemas/sitemap/0.9"><sitemap><loc>cc</loc></sitemap><sitemap><loc>dd</loc></sitemap></sitemapindex>'), resources=si )
self.assertTrue( s.parsed_index, 'was a sitemapindex')
self.assertEqual( len(si.resources), 4, '4 sitemaps total')
s.parse_xml(fh=io.StringIO(
'<sitemapindex xmlns="http://www.sitemaps.org/schemas/sitemap/0.9"><sitemap><loc>cc</loc></sitemap><sitemap><loc>dd</loc></sitemap></sitemapindex>'), resources=si)
self.assertTrue(s.parsed_index, 'was a sitemapindex')
self.assertEqual(len(si.resources), 4, '4 sitemaps total')
sms = sorted(si.uris())
self.assertEqual( sms, ['aaa','bbb', 'cc', 'dd'] )
self.assertEqual(sms, ['aaa', 'bbb', 'cc', 'dd'])
def test_22_parse_sitemapindex_file(self):
s=Sitemap()
fh=open('tests/testdata/sitemapindex1/sitemap.xml','r')
si = s.parse_xml( fh=fh, sitemapindex=True )
self.assertTrue( s.parsed_index, 'was a sitemapindex')
self.assertEqual( len(si.resources), 3, '3 sitemaps')
s = Sitemap()
fh = open('tests/testdata/sitemapindex1/sitemap.xml', 'r')
si = s.parse_xml(fh=fh, sitemapindex=True)
self.assertTrue(s.parsed_index, 'was a sitemapindex')
self.assertEqual(len(si.resources), 3, '3 sitemaps')
sms = sorted(si.uris())
self.assertEqual( sms, ['http://localhost:8888/sitemap00000.xml','http://localhost:8888/sitemap00001.xml','http://localhost:8888/sitemap00002.xml'] )
#self.assertEqual( si.resources['http://localhost:8888/sitemap00000.xml'].lastmod, '2012-06-13T18:09:13Z' )
self.assertEqual(sms, ['http://localhost:8888/sitemap00000.xml',
'http://localhost:8888/sitemap00001.xml', 'http://localhost:8888/sitemap00002.xml'])
# self.assertEqual( si.resources['http://localhost:8888/sitemap00000.xml'].lastmod, '2012-06-13T18:09:13Z' )
def test_21_parse_multi_sitemapindex(self):
s = Sitemap()
fh=open('tests/testdata/sitemapindex2/sitemap.xml','r')
si = s.parse_xml( fh=fh, sitemapindex=True )
self.assertTrue( s.parsed_index, 'was a sitemapindex')
self.assertEqual( len(si.resources), 3, '3 sitemaps listed')
fh = open('tests/testdata/sitemapindex2/sitemap.xml', 'r')
si = s.parse_xml(fh=fh, sitemapindex=True)
self.assertTrue(s.parsed_index, 'was a sitemapindex')
self.assertEqual(len(si.resources), 3, '3 sitemaps listed')
def test_30_parse_change_list(self):
xml='<?xml version=\'1.0\' encoding=\'UTF-8\'?>\n\
xml = '<?xml version=\'1.0\' encoding=\'UTF-8\'?>\n\
<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9" xmlns:rs="http://www.openarchives.org/rs/terms/">\
<url><loc>/tmp/rs_test/src/file_a</loc><lastmod>2012-03-14T18:37:36Z</lastmod><rs:md change="updated" length="12" /></url>\
<url><loc>/tmp/rs_test/src/file_b</loc><lastmod>2012-03-14T18:37:36Z</lastmod><rs:md length="32" /></url>\
</urlset>'
s=Sitemap()
s.resource_class=Resource
c=s.parse_xml(fh=io.StringIO(xml))
self.assertEqual( s.resources_created, 2, 'got 2 resources')
s = Sitemap()
s.resource_class = Resource
c = s.parse_xml(fh=io.StringIO(xml))
self.assertEqual(s.resources_created, 2, 'got 2 resources')
i = iter(c)
r1 = next(i)
self.assertEqual( r1.uri, '/tmp/rs_test/src/file_a' )
self.assertEqual( r1.change, 'updated' )
self.assertEqual(r1.uri, '/tmp/rs_test/src/file_a')
self.assertEqual(r1.change, 'updated')
r2 = next(i)
self.assertEqual( r2.uri, '/tmp/rs_test/src/file_b' )
self.assertEqual( r2.change, None )
self.assertEqual(r2.uri, '/tmp/rs_test/src/file_b')
self.assertEqual(r2.change, None)
if __name__ == '__main__':
if __name__ == '__main__':
suite = unittest.TestLoader().loadTestsFromTestCase(TestSitemap)
unittest.TextTestRunner(verbosity=2).run(suite)

38
tests/test_source_description.py
View File

@ -3,46 +3,48 @@ import re
from resync.resource import Resource
from resync.source_description import SourceDescription
class TestSourceDescription(unittest.TestCase):
def test01_empty(self):
rsd = SourceDescription()
rsd.describedby = "http://example.org/about"
self.assertEqual( len(rsd), 0 )
self.assertEqual(len(rsd), 0)
rsd.md_at = None
self.assertEqual( rsd.as_xml(), '<?xml version=\'1.0\' encoding=\'UTF-8\'?>\n<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9" xmlns:rs="http://www.openarchives.org/rs/terms/"><rs:ln href="http://example.org/about" rel="describedby" /><rs:md capability="description" /></urlset>' )
self.assertEqual(rsd.as_xml(), '<?xml version=\'1.0\' encoding=\'UTF-8\'?>\n<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9" xmlns:rs="http://www.openarchives.org/rs/terms/"><rs:ln href="http://example.org/about" rel="describedby" /><rs:md capability="description" /></urlset>')
def test02_one_caplist(self):
rsd = SourceDescription()
rsd.describedby = "http://example.org/about"
self.assertEqual( len(rsd), 0 )
self.assertEqual(len(rsd), 0)
rsd.md_at = None
rsd.add_capability_list("http://example.org/ds1/cl.xml")
self.assertEqual( len(rsd), 1 )
self.assertEqual( rsd.as_xml(), '<?xml version=\'1.0\' encoding=\'UTF-8\'?>\n<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9" xmlns:rs="http://www.openarchives.org/rs/terms/"><rs:ln href="http://example.org/about" rel="describedby" /><rs:md capability="description" /><url><loc>http://example.org/ds1/cl.xml</loc><rs:md capability="capabilitylist" /></url></urlset>' )
self.assertEqual(len(rsd), 1)
self.assertEqual(rsd.as_xml(), '<?xml version=\'1.0\' encoding=\'UTF-8\'?>\n<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9" xmlns:rs="http://www.openarchives.org/rs/terms/"><rs:ln href="http://example.org/about" rel="describedby" /><rs:md capability="description" /><url><loc>http://example.org/ds1/cl.xml</loc><rs:md capability="capabilitylist" /></url></urlset>')
def test03_a_bunch(self):
rsd = SourceDescription()
rsd.describedby = "http://example.org/about"
self.assertEqual( len(rsd), 0 )
self.assertEqual(len(rsd), 0)
rsd.add_capability_list("http://example.org/ds1/cl.xml")
rsd.add_capability_list("http://example.org/ds2/cl.xml")
rsd.add_capability_list("http://example.org/ds3/cl.xml")
self.assertEqual( len(rsd), 3 )
self.assertEqual( rsd.as_xml(), '<?xml version=\'1.0\' encoding=\'UTF-8\'?>\n<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9" xmlns:rs="http://www.openarchives.org/rs/terms/"><rs:ln href="http://example.org/about" rel="describedby" /><rs:md capability="description" /><url><loc>http://example.org/ds1/cl.xml</loc><rs:md capability="capabilitylist" /></url><url><loc>http://example.org/ds2/cl.xml</loc><rs:md capability="capabilitylist" /></url><url><loc>http://example.org/ds3/cl.xml</loc><rs:md capability="capabilitylist" /></url></urlset>' )
self.assertEqual(len(rsd), 3)
self.assertEqual(rsd.as_xml(), '<?xml version=\'1.0\' encoding=\'UTF-8\'?>\n<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9" xmlns:rs="http://www.openarchives.org/rs/terms/"><rs:ln href="http://example.org/about" rel="describedby" /><rs:md capability="description" /><url><loc>http://example.org/ds1/cl.xml</loc><rs:md capability="capabilitylist" /></url><url><loc>http://example.org/ds2/cl.xml</loc><rs:md capability="capabilitylist" /></url><url><loc>http://example.org/ds3/cl.xml</loc><rs:md capability="capabilitylist" /></url></urlset>')
def test04_parse(self):
xml='<?xml version=\'1.0\' encoding=\'UTF-8\'?>\n<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9" xmlns:rs="http://www.openarchives.org/rs/terms/"><rs:ln href="http://example.org/about" rel="describedby" /><rs:md capability="description" /><url><loc>http://example.org/ds1/cl.xml</loc><rs:md capability="capabilitylist" /></url><url><loc>http://example.org/ds2/cl.xml</loc><rs:md capability="capabilitylist" /></url><url><loc>http://example.org/ds3/cl.xml</loc><rs:md capability="capabilitylist" /></url></urlset>'
sd=SourceDescription()
xml = '<?xml version=\'1.0\' encoding=\'UTF-8\'?>\n<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9" xmlns:rs="http://www.openarchives.org/rs/terms/"><rs:ln href="http://example.org/about" rel="describedby" /><rs:md capability="description" /><url><loc>http://example.org/ds1/cl.xml</loc><rs:md capability="capabilitylist" /></url><url><loc>http://example.org/ds2/cl.xml</loc><rs:md capability="capabilitylist" /></url><url><loc>http://example.org/ds3/cl.xml</loc><rs:md capability="capabilitylist" /></url></urlset>'
sd = SourceDescription()
sd.parse(str_data=xml)
self.assertEqual( sd.link_href('describedby'), 'http://example.org/about',
'describedby link' )
self.assertEqual( sd.capability, 'description' )
self.assertEqual( len(sd.resources), 3, 'got 3 capacility lists' )
[r1,r2,r3]=sd.resources
self.assertEqual( r1.uri, 'http://example.org/ds1/cl.xml' )
self.assertEqual( r1.capability, 'capabilitylist' )
self.assertEqual(sd.link_href('describedby'), 'http://example.org/about',
'describedby link')
self.assertEqual(sd.capability, 'description')
self.assertEqual(len(sd.resources), 3, 'got 3 capacility lists')
[r1, r2, r3] = sd.resources
self.assertEqual(r1.uri, 'http://example.org/ds1/cl.xml')
self.assertEqual(r1.capability, 'capabilitylist')
if __name__ == '__main__':
suite = unittest.defaultTestLoader.loadTestsFromTestCase(TestSourceDescription)
suite = unittest.defaultTestLoader.loadTestsFromTestCase(
TestSourceDescription)
unittest.TextTestRunner().run(suite)

1
tests/test_url_authority.py
View File

@ -3,6 +3,7 @@ import unittest
from resync.url_authority import UrlAuthority
class TestUrlAuthority(unittest.TestCase):
def test01_strict_authority(self):

9
tests/test_utils.py
View File

@ -1,16 +1,17 @@
import unittest
import resync.utils
class TestUtill(unittest.TestCase):
def test1_string(self):
self.assertEqual( resync.utils.compute_md5_for_string('A file\n'),
'j912liHgA/48DCHpkptJHg==')
self.assertEqual(resync.utils.compute_md5_for_string('A file\n'),
'j912liHgA/48DCHpkptJHg==')
def test2_file(self):
# Should be same as the string above
self.assertEqual( resync.utils.compute_md5_for_file('tests/testdata/a'),
'j912liHgA/48DCHpkptJHg==')
self.assertEqual(resync.utils.compute_md5_for_file('tests/testdata/a'),
'j912liHgA/48DCHpkptJHg==')
if __name__ == '__main__':
unittest.main()

50
tests/test_w3c_datetime.py
View File

@ -12,20 +12,27 @@ class TestW3cDatetime(unittest.TestCase):
def test01_datetime_to_str(self):
"""Writing."""
self.assertEqual(datetime_to_str(0), "1970-01-01T00:00:00Z")
self.assertEqual(datetime_to_str(0),
"1970-01-01T00:00:00Z")
self.assertEqual(datetime_to_str(0.000001),
"1970-01-01T00:00:00.000001Z")
self.assertEqual(datetime_to_str(0.1), "1970-01-01T00:00:00.100000Z")
self.assertEqual(datetime_to_str(1), "1970-01-01T00:00:01Z")
self.assertEqual(datetime_to_str(60), "1970-01-01T00:01:00Z")
self.assertEqual(datetime_to_str(60 * 60), "1970-01-01T01:00:00Z")
self.assertEqual(datetime_to_str(60 * 60 * 24), "1970-01-02T00:00:00Z")
self.assertEqual(datetime_to_str(0.1),
"1970-01-01T00:00:00.100000Z")
self.assertEqual(datetime_to_str(1),
"1970-01-01T00:00:01Z")
self.assertEqual(datetime_to_str(60),
"1970-01-01T00:01:00Z")
self.assertEqual(datetime_to_str(60 * 60),
"1970-01-01T01:00:00Z")
self.assertEqual(datetime_to_str(60 * 60 * 24),
"1970-01-02T00:00:00Z")
self.assertEqual(datetime_to_str(60 * 60 * 24 * 31),
"1970-02-01T00:00:00Z")
self.assertEqual(datetime_to_str(60 * 60 * 24 * 365),
"1971-01-01T00:00:00Z")
#
self.assertEqual(datetime_to_str(1234567890), "2009-02-13T23:31:30Z")
# Random other datetime
self.assertEqual(datetime_to_str(1234567890),
"2009-02-13T23:31:30Z")
# Rounding issues
self.assertEqual(datetime_to_str(0.199999),
"1970-01-01T00:00:00.199999Z")
@ -42,11 +49,12 @@ class TestW3cDatetime(unittest.TestCase):
self.assertEqual(datetime_to_str(0.200001),
"1970-01-01T00:00:00.200001Z")
# No fractions
self.assertEqual(datetime_to_str(100, True), "1970-01-01T00:01:40Z")
self.assertEqual(datetime_to_str(100, True),
"1970-01-01T00:01:40Z")
self.assertEqual(datetime_to_str(0.2000009, True),
"1970-01-01T00:00:00Z")
self.assertEqual(datetime_to_str(
0.200001, no_fractions=True), "1970-01-01T00:00:00Z")
self.assertEqual(datetime_to_str(0.200001, no_fractions=True),
"1970-01-01T00:00:00Z")
def test02_str_to_datetime(self):
"""Reading."""
@ -54,11 +62,10 @@ class TestW3cDatetime(unittest.TestCase):
self.assertEqual(str_to_datetime("1970-01-01T00:00:00.000Z"), 0)
self.assertEqual(str_to_datetime("1970-01-01T00:00:00+00:00"), 0)
self.assertEqual(str_to_datetime("1970-01-01T00:00:00-00:00"), 0)
self.assertEqual(str_to_datetime(
"1970-01-01T00:00:00.000001Z"), 0.000001)
self.assertEqual(str_to_datetime("1970-01-01T00:00:00.000001Z"), 0.000001)
self.assertEqual(str_to_datetime("1970-01-01T00:00:00.1Z"), 0.1)
self.assertEqual(str_to_datetime("1970-01-01T00:00:00.100000Z"), 0.1)
#
# Random other datetime
self.assertEqual(str_to_datetime("2009-02-13T23:31:30Z"), 1234567890)
def test03_same(self):
@ -88,15 +95,12 @@ class TestW3cDatetime(unittest.TestCase):
self.assertRaises(ValueError, str_to_datetime, "2012-13-01")
self.assertRaises(ValueError, str_to_datetime, "2012-12-32")
self.assertRaises(ValueError, str_to_datetime, "2012-11-01T10:10:60")
self.assertRaises(ValueError, str_to_datetime,
"2012-11-01T10:10:59.9x")
self.assertRaises(ValueError, str_to_datetime, "2012-11-01T10:10:59.9x")
# Valid ISO8601 but not allowed in W3C Datetime
self.assertRaises(ValueError, str_to_datetime, "2012-11-01T01:01:01")
self.assertRaises(ValueError, str_to_datetime, "2012-11-01 01:01:01Z")
self.assertRaises(ValueError, str_to_datetime,
"2012-11-01T01:01:01+0000")
self.assertRaises(ValueError, str_to_datetime,
"2012-11-01T01:01:01-1000")
self.assertRaises(ValueError, str_to_datetime, "2012-11-01T01:01:01+0000")
self.assertRaises(ValueError, str_to_datetime, "2012-11-01T01:01:01-1000")
# Bad values
self.assertRaises(ValueError, str_to_datetime, "2012-00-01T01:01:01Z")
self.assertRaises(ValueError, str_to_datetime, "2012-13-01T01:01:01Z")
@ -105,10 +109,8 @@ class TestW3cDatetime(unittest.TestCase):
self.assertRaises(ValueError, str_to_datetime, "2012-13-01T24:01:01Z")
self.assertRaises(ValueError, str_to_datetime, "2012-13-01T00:60:01Z")
self.assertRaises(ValueError, str_to_datetime, "2012-13-01T00:00:60Z")
self.assertRaises(ValueError, str_to_datetime,
"2012-11-01T01:01:01+99:00")
self.assertRaises(ValueError, str_to_datetime,
"2012-11-01T01:01:01-25:00")
self.assertRaises(ValueError, str_to_datetime, "2012-11-01T01:01:01+99:00")
self.assertRaises(ValueError, str_to_datetime, "2012-11-01T01:01:01-25:00")
def test05_roundtrips(self):
"""Round trips."""

7
tests/testcase_with_tmpdir.py
View File

@ -5,15 +5,16 @@ import unittest
import tempfile
import shutil
class TestCase(unittest.TestCase):
"""Adds setUpClass an tearDownClass that create and destroy tmpdir."""
_tmpdir=None
_tmpdir = None
@classmethod
def setUpClass(cls):
# Create tmp dir to write to and check
cls._tmpdir=tempfile.mkdtemp()
cls._tmpdir = tempfile.mkdtemp()
if (not os.path.isdir(cls._tmpdir)):
raise Exception("Failed to create tempdir to use for dump tests")
try:
@ -39,6 +40,6 @@ class TestCase(unittest.TestCase):
# FIXME - Hack to work on python2.6 where setUpClass is not called, will
# FIXME - not have proper tidy as tearDownClass will not be called.
# FIXME - Remove when 2.6 no longer supported
if (not self._tmpdir and sys.version_info < (2,7)):
if (not self._tmpdir and sys.version_info < (2, 7)):
self.setUpClass()
return(self._tmpdir)