Find map + tests

resync/client.py

@@ -97,9 +97,8 @@ class Client(object):
                                          mapper=self.mapper)
             resource_list.read(uri=uri)
         except Exception as e:
-            raise ClientFatalError(
-                "Can't read source resource list from %s (%s)" %
-                (uri, str(e)))
+            raise ClientError("Can't read source resource list from %s (%s)" %
+                              (uri, str(e)))
         self.logger.debug("Finished reading resource list")
         return(resource_list)
 
@@ -110,7 +109,7 @@ class Client(object):
         source description in another location, but a ClientFatalError if
         a source description is found but there is some problem using it.
         """
-        self.logger.info("Reading capability list %s" % (uri))
+        self.logger.info("Reading source description %s" % (uri))
         try:
             sd = SourceDescription()
             sd.read(uri=uri)
@@ -125,11 +124,25 @@ class Client(object):
             raise ClientFatalError(
                 "Source description %s has multiple sources" % (uri))
         self.logger.info("Finished reading source description")
-        raise ClientFatalError('debug')
-        return(cl)
+        # Now read capability list
+        cluri = sd.resources.first().uri
+        uri = urljoin(uri, cluri)  # FIXME - Should relative URI handling be elsewhere?
+        self.logger.info("Reading capability list %s" % (uri))
+        try:
+            cl = CapabilityList()
+            cl.read(uri=uri)
+        except Exception as e:
+            raise ClientError(
+                "Can't read capability list from %s (%s)" %
+                (uri, str(e)))
+        if (not cl.has_capability('resourcelist')):
+            raise ClientFatalError(
+                "Capability list %s does not describe a resource list" % (uri))
+        rluri = cl.capability_info('resourcelist').uri
+        return(urljoin(uri, rluri))
 
     def find_resource_list(self):
-        """Look for resource list by hueristics.
+        """Finf resource list by hueristics, returns ResourceList object.
 
         1. Use explicitly specified self.sitemap_name (and
             fail if that doesn't work)
@@ -146,23 +159,28 @@ class Client(object):
             return(self.read_resource_list(self.sitemap_name))
         # 2 & 3
         parts = urlsplit(self.sitemap)
-        uri_host = urlunsplit([parts[0],parts[1],'','',''])
+        uri_host = urlunsplit([parts[0], parts[1], '', '', ''])
+        errors = []
         for uri in [urljoin(self.sitemap, '.well-known/resourcesync'),
                     urljoin(uri_host, '.well-known/resourcesync')]:
+            uri = uri.lstrip('file:///')  # urljoin adds this for local files
             try:
-                return(self.find_resource_list_from_source_description(uri))
+                rluri = self.find_resource_list_from_source_description(uri)
+                return(self.read_resource_list(rluri))
             except ClientError as e:
-                pass
+                errors.append(str(e))
         # 4, 5 & 6
         for uri in [urljoin(self.sitemap, 'resourcelist.xml'),
                     urljoin(self.sitemap, 'sitemap.xml'),
                     urljoin(uri_host, 'sitemap.xml')]:
+            uri = uri.lstrip('file:///')  # urljoin adds this for local files
             try:
                 return(self.read_resource_list(uri))
             except ClientError as e:
-                pass
+                errors.append(str(e))
         raise ClientFatalError(
-                "Failed to find source resource list from common patterns")
+            "Failed to find source resource list from common patterns (%s)" %
+            ". ".join(errors))
 
     def build_resource_list(self, paths=None, set_path=False):
         """Return a resource list for files on local disk.

resync/resource_set.py

@@ -35,6 +35,10 @@ class ResourceSet(dict):
                 "Attempt to add resource already in this set")
         self[uri] = resource
 
+    def first(self):
+        """First item obtained from iterator."""
+        return(next(iter(self)))
+
 
 class ResourceSetDupeError(Exception):
     """Exception for case of attempt to add duplicate resource."""

tests/test_client.py

@@ -1,5 +1,6 @@
 from tests.testcase_with_tmpdir import TestCase
 from tests.capture_stdout import capture_stdout
+from tests.webserver_context import webserver
 
 import unittest
 import re
@@ -8,7 +9,7 @@ from testfixtures import LogCapture
 import sys
 import os.path
 
-from resync.client import Client, ClientFatalError
+from resync.client import Client, ClientError, ClientFatalError
 from resync.resource import Resource
 from resync.resource_list import ResourceList
 from resync.change_list import ChangeList
@@ -36,6 +37,41 @@ class TestClient(TestCase):
         self.assertEqual(c.sitemap_uri('/abcd2'), '/abcd2')
         self.assertEqual(c.sitemap_uri('scheme:/abcd3'), 'scheme:/abcd3')
 
+    def test04_read_resource_list(self):
+        c = Client()
+        rl = c.read_resource_list('tests/testdata/client/dir1/resourcelist.xml')
+        self.assertEqual(len(rl), 3)
+        rl = c.read_resource_list('file:tests/testdata/client/dir1/resourcelist.xml')
+        self.assertEqual(len(rl), 3)
+        self.assertEqual(len(rl), 3)
+        self.assertRaises(ClientError, c.read_resource_list, 'file://tests/testdata/client/dir1/resourcelist.xml')
+        self.assertRaises(ClientError, c.read_resource_list, 'file:///tests/testdata/client/dir1/resourcelist.xml')
+        self.assertRaises(ClientError, c.read_resource_list, 'DOES_NOT_EXIST')
+
+    def test05_find_resource_list(self):
+        c = Client()
+        # Filesystem tests
+        c.set_mappings(['tests/testdata/find/find1', 'xxx'])
+        self.assertEqual(c.find_resource_list().up, 'find1')
+        c.set_mappings(['tests/testdata/find/find2', 'xxx'])
+        self.assertEqual(c.find_resource_list().up, 'find2')
+        c.set_mappings(['tests/testdata/find/find3', 'xxx'])
+        self.assertEqual(c.find_resource_list().up, 'find3')
+        # Tests requiring a server
+        with webserver('tests/testdata/find', 'localhost', 9999):
+            c.set_mappings(['http://localhost:9999/find1', 'xxx'])
+            self.assertEqual(c.find_resource_list().up, 'find1')
+            c.set_mappings(['http://localhost:9999/find2', 'xxx'])
+            self.assertEqual(c.find_resource_list().up, 'find2')
+            c.set_mappings(['http://localhost:9999/find3', 'xxx'])
+            self.assertEqual(c.find_resource_list().up, 'find3')
+        with webserver('tests/testdata/find/find1', 'localhost', 9999):
+            c.set_mappings(['http://localhost:9999/data', 'xxx'])
+            self.assertEqual(c.find_resource_list().up, 'find1')
+        with webserver('tests/testdata/find/find3', 'localhost', 9999):
+            c.set_mappings(['http://localhost:9999/data/data1', 'xxx'])
+            self.assertEqual(c.find_resource_list().up, 'find3')
+
     def test10_baseline_or_audit(self):
         # FIXME - this is the guts of the client, tough to test, need to work
         # through more cases...

tests/testcase_with_tmpdir.py

@@ -26,7 +26,7 @@ class TestCase(unittest.TestCase):
     def tearDownClass(cls):
         # Cleanup
         if (not os.path.isdir(cls._tmpdir)):
-            raise Exception("Ooops, no tempdir (%s) to clean up?" % (tmpdir))
+            raise Exception("Ooops, no tempdir (%s) to clean up?" % (cls._tmpdir))
         shutil.rmtree(cls._tmpdir)
         try:
             cls.extraTearUpClass()

tests/testdata/client/dir1/resourcelist.xml

@@ -1,7 +1,7 @@
 <?xml version="1.0" encoding="UTF-8"?>
 <urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9"
         xmlns:rs="http://www.openarchives.org/rs/terms/">
-  <rs:ln rel="resourcesync"
+  <rs:ln rel="up"
          href="file:tests/testdata/client/dir1/caps1.xml"/>
   <rs:md capability="resourcelist"
          modified="2013-01-03T15:00:00Z"/>

tests/testdata/find/find1/.well-known/resourcelist.xml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9"
+        xmlns:rs="http://www.openarchives.org/rs/terms/">
+  <rs:ln rel="up"
+         href="find1"/>
+  <rs:md capability="resourcelist"
+         modified="2017-04-11T10:00:00Z"/>
+</urlset>

tests/testdata/find/find1/.well-known/resourcesync

@@ -0,0 +1,11 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9"
+        xmlns:rs="http://www.openarchives.org/rs/terms/">
+  <rs:ln rel="describedby"
+         href="http://resync.library.cornell.edu/"/>
+  <rs:md capability="description"/>
+  <url>
+    <loc>../data/capabilitylist.xml</loc>
+    <rs:md capability="capabilitylist"/>
+  </url>
+</urlset>

tests/testdata/find/find1/data/capabilitylist.xml

@@ -0,0 +1,9 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9"
+        xmlns:rs="http://www.openarchives.org/rs/terms/">
+  <rs:md capability="capabilitylist"/>
+  <url>
+    <loc>resourcelist.xml</loc>
+    <rs:md capability="resourcelist"/>
+  </url>
+</urlset>

tests/testdata/find/find1/data/resourcelist.xml

@@ -0,0 +1,11 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9"
+        xmlns:rs="http://www.openarchives.org/rs/terms/">
+  <rs:ln rel="up" href="find1"/>
+  <rs:md capability="resourcelist"
+         modified="2017-04-11T11:22:33Z"/>
+  <url>
+      <loc>a_resource</loc>
+      <lastmod>2017-05-28T00:00:00Z</lastmod>
+  </url>
+</urlset>

tests/testdata/find/find2/resourcelist.xml

@@ -0,0 +1,11 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9"
+        xmlns:rs="http://www.openarchives.org/rs/terms/">
+  <rs:ln rel="up" href="find2"/>
+  <rs:md capability="resourcelist"
+         modified="2017-04-11T11:22:33Z"/>
+  <url>
+      <loc>a_resource</loc>
+      <lastmod>2017-05-28T00:00:00Z</lastmod>
+  </url>
+</urlset>

tests/testdata/find/find3/data/data1/res.txt

@@ -0,0 +1 @@
+Text

tests/testdata/find/find3/sitemap.xml

@@ -0,0 +1,11 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9"
+        xmlns:rs="http://www.openarchives.org/rs/terms/">
+  <rs:ln rel="up" href="find3"/>
+  <rs:md capability="resourcelist"
+         modified="2017-04-11T11:22:33Z"/>
+  <url>
+      <loc>a_resource</loc>
+      <lastmod>2017-05-28T00:00:00Z</lastmod>
+  </url>
+</urlset>

tests/webserver_context.py

@@ -0,0 +1,88 @@
+"""Provides content manager that runs local webserver."""
+import contextlib
+import os
+import posixpath
+import requests
+import signal
+import time
+from multiprocessing import Process
+from http.server import HTTPServer, SimpleHTTPRequestHandler
+try:  # python3
+    from urllib.parse import unquote
+except ImportError:  # python2
+    from urlparse import unquote
+
+
+class MyHTTPRequestHandler(SimpleHTTPRequestHandler):
+    """Copy of SimpleHTTPRequestHandler with cls._base_path setting."""
+
+    _base_path = '/'
+
+    def translate_path(self, path):
+        """Translate a /-separated PATH to the local filename syntax.
+
+        Components that mean special things to the local file system
+        (e.g. drive or directory names) are ignored.  (XXX They should
+        probably be diagnosed.)
+
+        **Copied from http.server.SimpleHTTPRequestHandler with modification
+        of path**
+        """
+        # abandon query parameters
+        path = path.split('?', 1)[0]
+        path = path.split('#', 1)[0]
+        # Don't forget explicit trailing slash when normalizing. Issue17324
+        trailing_slash = path.rstrip().endswith('/')
+        try:
+            path = unquote(path, errors='surrogatepass')
+        except UnicodeDecodeError:
+            path = unquote(path)
+        path = posixpath.normpath(path)
+        words = path.split('/')
+        words = filter(None, words)
+        path = self._base_path
+        for word in words:
+            if os.path.dirname(word) or word in (os.curdir, os.pardir):
+                # Ignore components that are not a simple file/directory name
+                continue
+            path = os.path.join(path, word)
+        if trailing_slash:
+            path += '/'
+        return path
+
+
+def run_webserver(host='', port=9999):
+    """Run webserver at given host & port."""
+    server_address = (host, port)
+    httpd = HTTPServer(server_address, MyHTTPRequestHandler)
+    httpd.serve_forever()
+
+
+@contextlib.contextmanager
+def webserver(dir='/tmp', host='', port=9999):
+    """Context Manager that provides a webserver serving files from dir."""
+    MyHTTPRequestHandler._base_path = dir
+    p = Process(target=run_webserver, args=(host, port))
+    p.start()
+
+    # Wait for the server to be launched
+    for j in range(0, 10):
+        try:
+            requests.get("http://localhost:9999/", timeout=0.1)
+            break
+        except requests.exceptions.ConnectionError:
+            pass
+        time.sleep(0.1)
+
+    try:
+        yield
+    finally:
+        # Closing the server
+        p.terminate()
+
+
+if __name__ == '__main__':
+    with webserver():
+        print('Started server...')
+        # Things with server go in here
+    print('Exited server')