Merge remote-tracking branch 'dnephin/perf_cache_resolving'

* dnephin/perf_cache_resolving:
  Use lru_cache
  Remove DefragResult.
  Remove context manager from ref() validation.
  Perf improvements by using a cache.
  Add benchmark script.
  Fix test failures
  issue #158: TRY to speed-up scope & $ref url-handling by keeping fragments separated from URL (and avoid redunant frag/defrag). Conflicts: 	jsonschema/tests/test_benchmarks.py

Author: Julian

bench.py

@@ -0,0 +1,74 @@
+#!/usr/env/bin python
+"""
+Benchmark the performance of jsonschema.
+
+Example benchmark:
+
+    wget http://swagger.io/v2/schema.json
+    wget http://petstore.swagger.io/v2/swagger.json
+    python bench.py -r 5 schema.json swagger.json
+
+"""
+from __future__ import print_function
+import argparse
+import cProfile
+import json
+import time
+
+import jsonschema
+
+
+def parse_args():
+    parser = argparse.ArgumentParser()
+    parser.add_argument('schema', help="path to a schema used to benchmark")
+    parser.add_argument('document', help="document to validate with schema")
+    parser.add_argument('-r', '--repeat', type=int, help="number of iterations")
+    parser.add_argument('--profile',
+                        help="Enable profiling, write profile to this filepath")
+    return parser.parse_args()
+
+
+def run(filename, schema, document):
+    resolver = jsonschema.RefResolver(
+        'file://{0}'.format(filename),
+        schema,
+        store={schema['id']: schema})
+    jsonschema.validate(document, schema, resolver=resolver)
+
+
+def format_time(time_):
+    return "%.3fms" % (time_ * 1000)
+
+
+def run_timeit(schema_filename, document_filename, repeat, profile):
+    with open(schema_filename) as schema_file:
+        schema = json.load(schema_file)
+
+    with open(document_filename) as fh:
+        document = json.load(fh)
+
+    if profile:
+        profiler = cProfile.Profile()
+        profiler.enable()
+
+    times = []
+    for _ in range(repeat):
+        start_time = time.time()
+        run(schema_filename, schema, document)
+        times.append(time.time() - start_time)
+
+    if profile:
+        profiler.disable()
+        profiler.dump_stats(profile)
+
+    print(", ".join(map(format_time, sorted(times))))
+    print("Mean: {0}".format(format_time(sum(times) / repeat)))
+
+
+def main():
+    args = parse_args()
+    run_timeit(args.schema, args.document, args.repeat, args.profile)
+
+
+if __name__ == "__main__":
+    main()

jsonschema/__init__.py

@@ -19,8 +19,6 @@
     Draft3Validator, Draft4Validator, RefResolver, validate
 )
 
-
-__version__ = "2.5.0-dev"
-
+from jsonschema.version import __version__
 
 # flake8: noqa

jsonschema/_validators.py

@@ -190,9 +190,14 @@ def enum(validator, enums, instance, schema):
 
 
 def ref(validator, ref, instance, schema):
-    with validator.resolver.resolving(ref) as resolved:
+    scope, resolved = validator.resolver.resolve(ref)
+    validator.resolver.push_scope(scope)
+
+    try:
         for error in validator.descend(instance, resolved):
             yield error
+    finally:
+        validator.resolver.pop_scope()
 
 
 def type_draft3(validator, types, instance, schema):

jsonschema/compat.py

@@ -1,6 +1,8 @@
 from __future__ import unicode_literals
-import sys
+
 import operator
+import sys
+
 
 try:
     from collections import MutableMapping, Sequence  # noqa
@@ -11,6 +13,7 @@
 
 if PY3:
     zip = zip
+    from functools import lru_cache
     from io import StringIO
     from urllib.parse import (
         unquote, urljoin, urlunsplit, SplitResult, urlsplit as _urlsplit
@@ -21,6 +24,7 @@
     iteritems = operator.methodcaller("items")
 else:
     from itertools import izip as zip  # noqa
+    from repoze.lru import lru_cache
     from StringIO import StringIO
     from urlparse import (
         urljoin, urlunsplit, SplitResult, urlsplit as _urlsplit # noqa

jsonschema/tests/test_validators.py

@@ -1,5 +1,4 @@
 from collections import deque
-from contextlib import contextmanager
 import json
 
 from jsonschema import FormatChecker, ValidationError
@@ -633,12 +632,8 @@ def test_it_delegates_to_a_ref_resolver(self):
         resolver = RefResolver("", {})
         schema = {"$ref" : mock.Mock()}
 
-        @contextmanager
-        def resolving():
-            yield {"type": "integer"}
-
-        with mock.patch.object(resolver, "resolving") as resolve:
-            resolve.return_value = resolving()
+        with mock.patch.object(resolver, "resolve") as resolve:
+            resolve.return_value = "url", {"type": "integer"}
             with self.assertRaises(ValidationError):
                 self.validator_class(schema, resolver=resolver).validate(None)
 
@@ -775,11 +770,11 @@ def test_it_resolves_local_refs(self):
             self.assertEqual(resolved, self.referrer["properties"]["foo"])
 
     def test_it_resolves_local_refs_with_id(self):
-        schema = {"id": "foo://bar/schema#", "a": {"foo": "bar"}}
+        schema = {"id": "http://bar/schema#", "a": {"foo": "bar"}}
         resolver = RefResolver.from_schema(schema)
         with resolver.resolving("#/a") as resolved:
             self.assertEqual(resolved, schema["a"])
-        with resolver.resolving("foo://bar/schema#/a") as resolved:
+        with resolver.resolving("http://bar/schema#/a") as resolved:
             self.assertEqual(resolved, schema["a"])
 
     def test_it_retrieves_stored_refs(self):
@@ -815,7 +810,7 @@ def test_it_retrieves_unstored_refs_via_urlopen(self):
     def test_it_can_construct_a_base_uri_from_a_schema(self):
         schema = {"id" : "foo"}
         resolver = RefResolver.from_schema(schema)
-        self.assertEqual(resolver.base_uri, "foo")
+        self.assertEqual(resolver.resolution_scope, "foo")
         with resolver.resolving("") as resolved:
             self.assertEqual(resolved, schema)
         with resolver.resolving("#") as resolved:
@@ -828,7 +823,7 @@ def test_it_can_construct_a_base_uri_from_a_schema(self):
     def test_it_can_construct_a_base_uri_from_a_schema_without_id(self):
         schema = {}
         resolver = RefResolver.from_schema(schema)
-        self.assertEqual(resolver.base_uri, "")
+        self.assertEqual(resolver.resolution_scope, "")
         with resolver.resolving("") as resolved:
             self.assertEqual(resolved, schema)
         with resolver.resolving("#") as resolved:
@@ -863,9 +858,7 @@ def test_cache_remote_off(self):
         )
         with resolver.resolving(ref):
             pass
-        with resolver.resolving(ref):
-            pass
-        self.assertEqual(foo_handler.call_count, 2)
+        self.assertEqual(foo_handler.call_count, 1)
 
     def test_if_you_give_it_junk_you_get_a_resolution_error(self):
         ref = "foo://bar"
@@ -876,6 +869,13 @@ def test_if_you_give_it_junk_you_get_a_resolution_error(self):
                 pass
         self.assertEqual(str(err.exception), "Oh no! What's this?")
 
+    def test_helpful_error_message_on_failed_pop_scope(self):
+        resolver = RefResolver("", {})
+        resolver.pop_scope()
+        with self.assertRaises(RefResolutionError) as exc:
+            resolver.pop_scope()
+        self.assertIn("Failed to pop the scope", str(exc.exception))
+
 
 def sorted_errors(errors):
     def key(error):

jsonschema/validators.py

@@ -12,7 +12,7 @@
 from jsonschema import _utils, _validators
 from jsonschema.compat import (
     Sequence, urljoin, urlsplit, urldefrag, unquote, urlopen,
-    str_types, int_types, iteritems,
+    str_types, int_types, iteritems, lru_cache,
 )
 from jsonschema.exceptions import ErrorTree  # Backwards compatibility  # noqa
 from jsonschema.exceptions import RefResolutionError, SchemaError, UnknownType
@@ -79,7 +79,10 @@ def iter_errors(self, instance, _schema=None):
             if _schema is None:
                 _schema = self.schema
 
-            with self.resolver.in_scope(_schema.get(u"id", u"")):
+            scope = _schema.get(u"id")
+            if scope:
+                self.resolver.push_scope(scope)
+            try:
                 ref = _schema.get(u"$ref")
                 if ref is not None:
                     validators = [(u"$ref", ref)]
@@ -103,6 +106,9 @@ def iter_errors(self, instance, _schema=None):
                         if k != u"$ref":
                             error.schema_path.appendleft(k)
                         yield error
+            finally:
+                if scope:
+                    self.resolver.pop_scope()
 
         def descend(self, instance, schema, path=None, schema_path=None):
             for error in self.iter_errors(instance, schema):
@@ -227,26 +233,32 @@ class RefResolver(object):
         first resolution
     :argument dict handlers: a mapping from URI schemes to functions that
         should be used to retrieve them
-
+    :arguments callable cache_func: a function decorator used to cache
+        expensive calls. Should support the `functools.lru_cache` interface.
+    :argument int cache_maxsize: number of items to store in the cache. Set
+        this to 0 to disable caching. Defaults to 1000.
     """
 
     def __init__(
         self, base_uri, referrer, store=(), cache_remote=True, handlers=(),
+        cache_func=lru_cache, cache_maxsize=1000,
     ):
-        self.base_uri = base_uri
-        self.resolution_scope = base_uri
         # This attribute is not used, it is for backwards compatibility
         self.referrer = referrer
         self.cache_remote = cache_remote
         self.handlers = dict(handlers)
 
+        self._scopes_stack = [base_uri]
         self.store = _utils.URIDict(
             (id, validator.META_SCHEMA)
             for id, validator in iteritems(meta_schemas)
         )
         self.store.update(store)
         self.store[base_uri] = referrer
 
+        self._urljoin_cache = cache_func(cache_maxsize)(urljoin)
+        self._resolve_cache = cache_func(cache_maxsize)(self.resolve_from_url)
+
     @classmethod
     def from_schema(cls, schema, *args, **kwargs):
         """
@@ -259,44 +271,67 @@ def from_schema(cls, schema, *args, **kwargs):
 
         return cls(schema.get(u"id", u""), schema, *args, **kwargs)
 
+    def push_scope(self, scope):
+        self._scopes_stack.append(
+            self._urljoin_cache(self.resolution_scope, scope))
+
+    def pop_scope(self):
+        try:
+            self._scopes_stack.pop()
+        except IndexError:
+            raise RefResolutionError(
+                "Failed to pop the scope from an empty stack. "
+                "`pop_scope()` should only be called once for every "
+                "`push_scope()`")
+
+    @property
+    def resolution_scope(self):
+        return self._scopes_stack[-1]
+
+
+    # Deprecated, this function is no longer used, but is preserved for
+    # backwards compatibility
     @contextlib.contextmanager
     def in_scope(self, scope):
-        old_scope = self.resolution_scope
-        self.resolution_scope = urljoin(old_scope, scope)
+        self.push_scope(scope)
         try:
             yield
         finally:
-            self.resolution_scope = old_scope
+            self.pop_scope()
 
+    # Deprecated, this function is no longer used, but is preserved for
+    # backwards compatibility
     @contextlib.contextmanager
     def resolving(self, ref):
+        url, resolved = self.resolve(ref)
+        self.push_scope(url)
+        try:
+            yield resolved
+        finally:
+            self.pop_scope()
+
+    def resolve(self, ref):
         """
         Context manager which resolves a JSON ``ref`` and enters the
         resolution scope of this ref.
 
         :argument str ref: reference to resolve
 
         """
+        url = self._urljoin_cache(self.resolution_scope, ref)
+        return url, self._resolve_cache(url)
 
-        full_uri = urljoin(self.resolution_scope, ref)
-        uri, fragment = urldefrag(full_uri)
-        if not uri:
-            uri = self.base_uri
-
-        if uri in self.store:
-            document = self.store[uri]
-        else:
+    def resolve_from_url(self, url):
+        url, fragment = urldefrag(url)
+        try:
+            document = self.store[url]
+        except KeyError:
             try:
-                document = self.resolve_remote(uri)
+                document = self.resolve_remote(url)
             except Exception as exc:
                 raise RefResolutionError(exc)
 
-        old_base_uri, self.base_uri = self.base_uri, uri
-        try:
-            with self.in_scope(uri):
-                yield self.resolve_fragment(document, fragment)
-        finally:
-            self.base_uri = old_base_uri
+        return self.resolve_fragment(document, fragment)
 
     def resolve_fragment(self, document, fragment):
         """

jsonschema/version.py

@@ -0,0 +1 @@
+__version__ = "2.5.0-dev"

setup.py

@@ -1,7 +1,12 @@
+import os.path
 from setuptools import setup
+import sys
 
-from jsonschema import __version__
-
+# Load __version__ info globals without importing anything
+with open(
+    os.path.join(os.path.dirname(__file__), 'jsonschema', 'version.py')
+) as fh:
+    exec(fh.read())
 
 with open("README.rst") as readme:
     long_description = readme.read()
@@ -21,6 +26,11 @@
     "Programming Language :: Python :: Implementation :: PyPy",
 ]
 
+install_requires = []
+
+if sys.version_info < (3, 2):
+    install_requires.append('repoze.lru >= 0.6')
+
 setup(
     name="jsonschema",
     version=__version__,
@@ -34,4 +44,5 @@
     long_description=long_description,
     url="https://github.com/Julian/jsonschema",
     entry_points={"console_scripts": ["jsonschema = jsonschema.cli:main"]},
+    install_requires=install_requires,
 )