From 2fda1556ef7714d562317049f46db6ff59db5c2f Mon Sep 17 00:00:00 2001 From: "Kostis Anagnostopoulos @ STUW025" Date: Wed, 24 Sep 2014 03:20:07 +0200 Subject: [PATCH 1/7] 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 issue #158: Use try-finally to ensure resolver scopes_stack empty when iteration breaks (no detectable performance penalty). * Replace non-python-2.6 DefragResult with named-tuple. * Add test-case checking scopes_stack empty. Conflicts: jsonschema/tests/test_validators.py jsonschema/validators.py --- jsonschema/compat.py | 10 +++++-- jsonschema/validators.py | 58 +++++++++++++++++++++++++--------------- 2 files changed, 45 insertions(+), 23 deletions(-) diff --git a/jsonschema/compat.py b/jsonschema/compat.py index 6ca49ab..0afd9ea 100644 --- a/jsonschema/compat.py +++ b/jsonschema/compat.py @@ -1,6 +1,9 @@ from __future__ import unicode_literals -import sys + +from collections import namedtuple import operator +import sys + try: from collections import MutableMapping, Sequence # noqa @@ -40,6 +43,9 @@ def urlsplit(url): return SplitResult(scheme, netloc, path, query, fragment) +DefragResult = namedtuple('DefragResult', 'url fragment') + + def urldefrag(url): if "#" in url: s, n, p, q, frag = urlsplit(url) @@ -47,7 +53,7 @@ def urldefrag(url): else: defrag = url frag = '' - return defrag, frag + return DefragResult(defrag, frag) # flake8: noqa diff --git a/jsonschema/validators.py b/jsonschema/validators.py index c347bf1..8f48062 100644 --- a/jsonschema/validators.py +++ b/jsonschema/validators.py @@ -11,7 +11,8 @@ except ImportError: from jsonschema import _utils, _validators from jsonschema.compat import ( - Sequence, urljoin, urlsplit, urldefrag, unquote, urlopen, + Sequence, urljoin, urlsplit, urldefrag, unquote, urlopen, DefragResult, + str_types, int_types, iteritems, ) from jsonschema.exceptions import ErrorTree # Backwards compatibility # noqa @@ -79,7 +80,10 @@ def create(meta_schema, validators=(), version=None, default_types=None): # noq 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"$ref", ref)] @@ -103,6 +107,9 @@ def create(meta_schema, validators=(), version=None, default_types=None): # noq if k != u"$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): @@ -222,7 +229,7 @@ class RefResolver(object): :argument str base_uri: URI of the referring document :argument referrer: the actual referring document - :argument dict store: a mapping from URIs to documents to cache + :argument dict store: a mapping from URIs (without fragments!) to documents to cache :argument bool cache_remote: whether remote refs should be cached after first resolution :argument dict handlers: a mapping from URI schemes to functions that @@ -233,6 +240,7 @@ class RefResolver(object): def __init__( self, base_uri, referrer, store=(), cache_remote=True, handlers=(), ): + base_uri = urldefrag(base_uri) self.base_uri = base_uri self.resolution_scope = base_uri # This attribute is not used, it is for backwards compatibility @@ -240,12 +248,13 @@ class RefResolver(object): self.cache_remote = cache_remote self.handlers = dict(handlers) + self.scopes_stack = [] 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.store[base_uri.url] = referrer @classmethod def from_schema(cls, schema, *args, **kwargs): @@ -259,14 +268,19 @@ class RefResolver(object): return cls(schema.get(u"id", u""), schema, *args, **kwargs) - @contextlib.contextmanager - def in_scope(self, scope): + def push_scope(self, scope, is_defragged=False): old_scope = self.resolution_scope - self.resolution_scope = urljoin(old_scope, scope) - try: - yield - finally: - self.resolution_scope = old_scope + self.scopes_stack.append(old_scope) + if not is_defragged: + scope = urldefrag(scope) + self.resolution_scope = DefragResult( + urljoin(old_scope.url, scope.url, allow_fragments=False) + if scope.url else old_scope.url, + scope.fragment + ) + + def pop_scope(self): + self.resolution_scope = self.scopes_stack.pop() @contextlib.contextmanager def resolving(self, ref): @@ -278,24 +292,26 @@ class RefResolver(object): """ - full_uri = urljoin(self.resolution_scope, ref) - uri, fragment = urldefrag(full_uri) - if not uri: - uri = self.base_uri + ref = urldefrag(ref) - if uri in self.store: - document = self.store[uri] - else: + url = urljoin(self.resolution_scope.url, ref.url, allow_fragments=False) \ + if ref.url else self.resolution_scope.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) + uri = DefragResult(url, ref.fragment) old_base_uri, self.base_uri = self.base_uri, uri + self.push_scope(uri, is_defragged=True) try: - with self.in_scope(uri): - yield self.resolve_fragment(document, fragment) + yield self.resolve_fragment(document, ref.fragment) finally: + self.pop_scope() self.base_uri = old_base_uri def resolve_fragment(self, document, fragment): From 22701dc6526433201d2781b77566a6dba42768a8 Mon Sep 17 00:00:00 2001 From: Daniel Nephin Date: Fri, 27 Feb 2015 19:53:54 -0500 Subject: [PATCH 2/7] Fix test failures --- jsonschema/tests/test_validators.py | 4 ++-- jsonschema/validators.py | 13 +++++++++---- 2 files changed, 11 insertions(+), 6 deletions(-) diff --git a/jsonschema/tests/test_validators.py b/jsonschema/tests/test_validators.py index 2b14372..b3512ed 100644 --- a/jsonschema/tests/test_validators.py +++ b/jsonschema/tests/test_validators.py @@ -815,7 +815,7 @@ class TestRefResolver(unittest.TestCase): 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.base_uri.url, "foo") with resolver.resolving("") as resolved: self.assertEqual(resolved, schema) with resolver.resolving("#") as resolved: @@ -828,7 +828,7 @@ class TestRefResolver(unittest.TestCase): 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.base_uri.url, "") with resolver.resolving("") as resolved: self.assertEqual(resolved, schema) with resolver.resolving("#") as resolved: diff --git a/jsonschema/validators.py b/jsonschema/validators.py index 8f48062..d0431f3 100644 --- a/jsonschema/validators.py +++ b/jsonschema/validators.py @@ -229,7 +229,7 @@ class RefResolver(object): :argument str base_uri: URI of the referring document :argument referrer: the actual referring document - :argument dict store: a mapping from URIs (without fragments!) to documents to cache + :argument dict store: a mapping from URIs to documents to cache :argument bool cache_remote: whether remote refs should be cached after first resolution :argument dict handlers: a mapping from URI schemes to functions that @@ -275,7 +275,7 @@ class RefResolver(object): scope = urldefrag(scope) self.resolution_scope = DefragResult( urljoin(old_scope.url, scope.url, allow_fragments=False) - if scope.url else old_scope.url, + if scope.url else old_scope.url, scope.fragment ) @@ -294,8 +294,13 @@ class RefResolver(object): ref = urldefrag(ref) - url = urljoin(self.resolution_scope.url, ref.url, allow_fragments=False) \ - if ref.url else self.resolution_scope.url + if ref.url: + url = urljoin( + self.resolution_scope.url, + ref.url, + allow_fragments=False) + else: + url = self.resolution_scope.url try: document = self.store[url] From 812392bbd4359718eab86e892c32211823b229e5 Mon Sep 17 00:00:00 2001 From: Daniel Nephin Date: Sun, 1 Mar 2015 17:58:35 -0500 Subject: [PATCH 3/7] Add benchmark script. --- bench.py | 74 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 74 insertions(+) create mode 100644 bench.py diff --git a/bench.py b/bench.py new file mode 100644 index 0000000..e7318ed --- /dev/null +++ b/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() From 613cf3e1a0ed9c09f9a13634dd05416594694e40 Mon Sep 17 00:00:00 2001 From: Daniel Nephin Date: Fri, 27 Feb 2015 21:15:08 -0500 Subject: [PATCH 4/7] Perf improvements by using a cache. --- jsonschema/_utils.py | 16 +++++++ jsonschema/tests/test_validators.py | 12 ++--- jsonschema/validators.py | 73 +++++++++++++---------------- 3 files changed, 54 insertions(+), 47 deletions(-) diff --git a/jsonschema/_utils.py b/jsonschema/_utils.py index ae7e2b5..c13711c 100644 --- a/jsonschema/_utils.py +++ b/jsonschema/_utils.py @@ -38,6 +38,22 @@ class URIDict(MutableMapping): return repr(self.store) +class Cache(object): + """Cache the result of a function, using the arguments to the function as + the key. + """ + + def __init__(self, func): + self.func = func + self._cache = {} + + def __call__(self, *args): + if args in self._cache: + return self._cache[args] + self._cache[args] = value = self.func(*args) + return value + + class Unset(object): """ An as-of-yet unset attribute or unprovided default parameter. diff --git a/jsonschema/tests/test_validators.py b/jsonschema/tests/test_validators.py index b3512ed..0f4c825 100644 --- a/jsonschema/tests/test_validators.py +++ b/jsonschema/tests/test_validators.py @@ -775,11 +775,11 @@ class TestRefResolver(unittest.TestCase): 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 +815,7 @@ class TestRefResolver(unittest.TestCase): 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.url, "foo") + self.assertEqual(resolver.resolution_scope, "foo") with resolver.resolving("") as resolved: self.assertEqual(resolved, schema) with resolver.resolving("#") as resolved: @@ -828,7 +828,7 @@ class TestRefResolver(unittest.TestCase): 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.url, "") + self.assertEqual(resolver.resolution_scope, "") with resolver.resolving("") as resolved: self.assertEqual(resolved, schema) with resolver.resolving("#") as resolved: @@ -863,9 +863,7 @@ class TestRefResolver(unittest.TestCase): ) 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" diff --git a/jsonschema/validators.py b/jsonschema/validators.py index d0431f3..a69accb 100644 --- a/jsonschema/validators.py +++ b/jsonschema/validators.py @@ -11,8 +11,7 @@ except ImportError: from jsonschema import _utils, _validators from jsonschema.compat import ( - Sequence, urljoin, urlsplit, urldefrag, unquote, urlopen, DefragResult, - + Sequence, urljoin, urlsplit, urldefrag, unquote, urlopen, str_types, int_types, iteritems, ) from jsonschema.exceptions import ErrorTree # Backwards compatibility # noqa @@ -109,7 +108,7 @@ def create(meta_schema, validators=(), version=None, default_types=None): # noq yield error finally: if scope: - self.resolver.pop_scope() + self.resolver.scopes_stack.pop() def descend(self, instance, schema, path=None, schema_path=None): for error in self.iter_errors(instance, schema): @@ -240,21 +239,21 @@ class RefResolver(object): def __init__( self, base_uri, referrer, store=(), cache_remote=True, handlers=(), ): - base_uri = urldefrag(base_uri) - 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 = [] + 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.url] = referrer + self.store[base_uri] = referrer + + self.urljoin_cache = _utils.Cache(urljoin) + self.resolve_cache = _utils.Cache(self.resolve_from_url) @classmethod def from_schema(cls, schema, *args, **kwargs): @@ -268,19 +267,21 @@ class RefResolver(object): return cls(schema.get(u"id", u""), schema, *args, **kwargs) - def push_scope(self, scope, is_defragged=False): - old_scope = self.resolution_scope - self.scopes_stack.append(old_scope) - if not is_defragged: - scope = urldefrag(scope) - self.resolution_scope = DefragResult( - urljoin(old_scope.url, scope.url, allow_fragments=False) - if scope.url else old_scope.url, - scope.fragment - ) + def push_scope(self, scope): + self.scopes_stack.append( + self.urljoin_cache(self.resolution_scope, scope)) - def pop_scope(self): - self.resolution_scope = self.scopes_stack.pop() + @property + def resolution_scope(self): + return self.scopes_stack[-1] + + @contextlib.contextmanager + def in_scope(self, scope): + self.push_scope(scope) + try: + yield + finally: + self.scopes_stack.pop() @contextlib.contextmanager def resolving(self, ref): @@ -291,33 +292,25 @@ class RefResolver(object): :argument str ref: reference to resolve """ + url = self.urljoin_cache(self.resolution_scope, ref) - ref = urldefrag(ref) - - if ref.url: - url = urljoin( - self.resolution_scope.url, - ref.url, - allow_fragments=False) - else: - url = self.resolution_scope.url - + self.push_scope(url) try: - document = self.store[url] + yield self.resolve_cache(url) + finally: + self.scopes_stack.pop() + + def resolve_from_url(self, url): + ref = urldefrag(url) + try: + document = self.store[ref.url] except KeyError: try: - document = self.resolve_remote(url) + document = self.resolve_remote(ref.url) except Exception as exc: raise RefResolutionError(exc) - uri = DefragResult(url, ref.fragment) - old_base_uri, self.base_uri = self.base_uri, uri - self.push_scope(uri, is_defragged=True) - try: - yield self.resolve_fragment(document, ref.fragment) - finally: - self.pop_scope() - self.base_uri = old_base_uri + return self.resolve_fragment(document, ref.fragment) def resolve_fragment(self, document, fragment): """ From d1e24483aabea8844bf7498b52649498f6b3ff5a Mon Sep 17 00:00:00 2001 From: Daniel Nephin Date: Sun, 1 Mar 2015 20:52:20 -0500 Subject: [PATCH 5/7] Remove context manager from ref() validation. --- jsonschema/_validators.py | 7 ++++++- jsonschema/tests/test_validators.py | 8 ++------ jsonschema/validators.py | 27 +++++++++++++++++++-------- 3 files changed, 27 insertions(+), 15 deletions(-) diff --git a/jsonschema/_validators.py b/jsonschema/_validators.py index 7e5956d..a51681e 100644 --- a/jsonschema/_validators.py +++ b/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): diff --git a/jsonschema/tests/test_validators.py b/jsonschema/tests/test_validators.py index 0f4c825..f3bb854 100644 --- a/jsonschema/tests/test_validators.py +++ b/jsonschema/tests/test_validators.py @@ -633,12 +633,8 @@ class ValidatorTestMixin(object): 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) diff --git a/jsonschema/validators.py b/jsonschema/validators.py index a69accb..435b8db 100644 --- a/jsonschema/validators.py +++ b/jsonschema/validators.py @@ -108,7 +108,7 @@ def create(meta_schema, validators=(), version=None, default_types=None): # noq yield error finally: if scope: - self.resolver.scopes_stack.pop() + self.resolver.pop_scope() def descend(self, instance, schema, path=None, schema_path=None): for error in self.iter_errors(instance, schema): @@ -271,20 +271,36 @@ class RefResolver(object): self.scopes_stack.append( self.urljoin_cache(self.resolution_scope, scope)) + def pop_scope(self): + self.scopes_stack.pop() + @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): self.push_scope(scope) try: yield finally: - self.scopes_stack.pop() + 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. @@ -293,12 +309,7 @@ class RefResolver(object): """ url = self.urljoin_cache(self.resolution_scope, ref) - - self.push_scope(url) - try: - yield self.resolve_cache(url) - finally: - self.scopes_stack.pop() + return url, self.resolve_cache(url) def resolve_from_url(self, url): ref = urldefrag(url) From ca59f3fa87cda8b0f101d3997dcbc8711e5a19c2 Mon Sep 17 00:00:00 2001 From: Daniel Nephin Date: Tue, 3 Mar 2015 16:09:42 -0500 Subject: [PATCH 6/7] Remove DefragResult. --- jsonschema/compat.py | 6 +----- jsonschema/validators.py | 8 ++++---- 2 files changed, 5 insertions(+), 9 deletions(-) diff --git a/jsonschema/compat.py b/jsonschema/compat.py index 0afd9ea..b3156f9 100644 --- a/jsonschema/compat.py +++ b/jsonschema/compat.py @@ -1,6 +1,5 @@ from __future__ import unicode_literals -from collections import namedtuple import operator import sys @@ -43,9 +42,6 @@ def urlsplit(url): return SplitResult(scheme, netloc, path, query, fragment) -DefragResult = namedtuple('DefragResult', 'url fragment') - - def urldefrag(url): if "#" in url: s, n, p, q, frag = urlsplit(url) @@ -53,7 +49,7 @@ def urldefrag(url): else: defrag = url frag = '' - return DefragResult(defrag, frag) + return defrag, frag # flake8: noqa diff --git a/jsonschema/validators.py b/jsonschema/validators.py index 435b8db..2343908 100644 --- a/jsonschema/validators.py +++ b/jsonschema/validators.py @@ -312,16 +312,16 @@ class RefResolver(object): return url, self.resolve_cache(url) def resolve_from_url(self, url): - ref = urldefrag(url) + url, fragment = urldefrag(url) try: - document = self.store[ref.url] + document = self.store[url] except KeyError: try: - document = self.resolve_remote(ref.url) + document = self.resolve_remote(url) except Exception as exc: raise RefResolutionError(exc) - return self.resolve_fragment(document, ref.fragment) + return self.resolve_fragment(document, fragment) def resolve_fragment(self, document, fragment): """ From ee1a256fc856a616940fb1eddcb3f4d8f7cb2f22 Mon Sep 17 00:00:00 2001 From: Daniel Nephin Date: Wed, 4 Mar 2015 15:57:31 -0500 Subject: [PATCH 7/7] Use lru_cache --- jsonschema/__init__.py | 4 +--- jsonschema/_utils.py | 16 --------------- jsonschema/compat.py | 2 ++ jsonschema/tests/test_validators.py | 8 +++++++- jsonschema/validators.py | 32 +++++++++++++++++++---------- jsonschema/version.py | 1 + setup.py | 15 ++++++++++++-- 7 files changed, 45 insertions(+), 33 deletions(-) create mode 100644 jsonschema/version.py diff --git a/jsonschema/__init__.py b/jsonschema/__init__.py index 16c9843..e23168d 100644 --- a/jsonschema/__init__.py +++ b/jsonschema/__init__.py @@ -19,8 +19,6 @@ from jsonschema.validators import ( Draft3Validator, Draft4Validator, RefResolver, validate ) - -__version__ = "2.5.0-dev" - +from jsonschema.version import __version__ # flake8: noqa diff --git a/jsonschema/_utils.py b/jsonschema/_utils.py index c13711c..ae7e2b5 100644 --- a/jsonschema/_utils.py +++ b/jsonschema/_utils.py @@ -38,22 +38,6 @@ class URIDict(MutableMapping): return repr(self.store) -class Cache(object): - """Cache the result of a function, using the arguments to the function as - the key. - """ - - def __init__(self, func): - self.func = func - self._cache = {} - - def __call__(self, *args): - if args in self._cache: - return self._cache[args] - self._cache[args] = value = self.func(*args) - return value - - class Unset(object): """ An as-of-yet unset attribute or unprovided default parameter. diff --git a/jsonschema/compat.py b/jsonschema/compat.py index b3156f9..9f52ded 100644 --- a/jsonschema/compat.py +++ b/jsonschema/compat.py @@ -13,6 +13,7 @@ PY3 = sys.version_info[0] >= 3 if PY3: zip = zip + from functools import lru_cache from io import StringIO from urllib.parse import ( unquote, urljoin, urlunsplit, SplitResult, urlsplit as _urlsplit @@ -23,6 +24,7 @@ if PY3: 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 diff --git a/jsonschema/tests/test_validators.py b/jsonschema/tests/test_validators.py index f3bb854..1f03294 100644 --- a/jsonschema/tests/test_validators.py +++ b/jsonschema/tests/test_validators.py @@ -1,5 +1,4 @@ from collections import deque -from contextlib import contextmanager import json from jsonschema import FormatChecker, ValidationError @@ -870,6 +869,13 @@ class TestRefResolver(unittest.TestCase): 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): diff --git a/jsonschema/validators.py b/jsonschema/validators.py index 2343908..c84a3db 100644 --- a/jsonschema/validators.py +++ b/jsonschema/validators.py @@ -12,7 +12,7 @@ except ImportError: 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 @@ -233,18 +233,22 @@ 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, ): # 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._scopes_stack = [base_uri] self.store = _utils.URIDict( (id, validator.META_SCHEMA) for id, validator in iteritems(meta_schemas) @@ -252,8 +256,8 @@ class RefResolver(object): self.store.update(store) self.store[base_uri] = referrer - self.urljoin_cache = _utils.Cache(urljoin) - self.resolve_cache = _utils.Cache(self.resolve_from_url) + 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): @@ -268,15 +272,21 @@ class RefResolver(object): 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)) + self._scopes_stack.append( + self._urljoin_cache(self.resolution_scope, scope)) def pop_scope(self): - self.scopes_stack.pop() + 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] + return self._scopes_stack[-1] # Deprecated, this function is no longer used, but is preserved for @@ -308,8 +318,8 @@ class RefResolver(object): :argument str ref: reference to resolve """ - url = self.urljoin_cache(self.resolution_scope, ref) - return url, self.resolve_cache(url) + url = self._urljoin_cache(self.resolution_scope, ref) + return url, self._resolve_cache(url) def resolve_from_url(self, url): url, fragment = urldefrag(url) diff --git a/jsonschema/version.py b/jsonschema/version.py new file mode 100644 index 0000000..9509105 --- /dev/null +++ b/jsonschema/version.py @@ -0,0 +1 @@ +__version__ = "2.5.0-dev" diff --git a/setup.py b/setup.py index 6b47714..ffd61f1 100644 --- a/setup.py +++ b/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 @@ classifiers = [ "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 @@ setup( long_description=long_description, url="http://github.com/Julian/jsonschema", entry_points={"console_scripts": ["jsonschema = jsonschema.cli:main"]}, + install_requires=install_requires, )