diff --git a/LICENSE.md b/LICENSE.md
new file mode 100644
index 0000000000000000000000000000000000000000..9359f208e4f070e6353fc7e655afd927af905e03
--- /dev/null
+++ b/LICENSE.md
@@ -0,0 +1,22 @@
+Copyright (c) 2006-2013 Bryan Tong Minh
+
+Permission is hereby granted, free of charge, to any person
+obtaining a copy of this software and associated documentation
+files (the "Software"), to deal in the Software without
+restriction, including without limitation the rights to use,
+copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the
+Software is furnished to do so, subject to the following
+conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+OTHER DEALINGS IN THE SOFTWARE.
diff --git a/README.md b/README.md
deleted file mode 100644
index ef5eec6b3eced68591d3c03e479fe0228a7b5a65..0000000000000000000000000000000000000000
--- a/README.md
+++ /dev/null
@@ -1,99 +0,0 @@
-> *This file describes the latest stable version of mwclient: version 0.6.5, released 6 May 2011*
-> **([download 0.6.5](https://github.com/btongminh/mwclient/archive/REL_0_6_5.zip)).**
-> *The development version is available in the*
-> *[github repository](https://github.com/btongminh/mwclient)*
-> **([download latest](https://github.com/btongminh/mwclient/archive/master.zip)).**
-
-Mwclient is a client to the [MediaWiki API](http://mediawiki.org/wiki/API)
-and allows access to almost all implemented API functions.
-Mwclient requires Python 2.4.
-This version supports MediaWiki 1.11 and above.
-However, for functions not available in the current MediaWiki,
-a `MediaWikiVersionError` is raised.
-
-This framework is written by Bryan Tong Minh and serves most of his bots.
-The framework and this documentation are primarily written for personal use
-and may or may not work for you.
-In case it doesn't, Bryan can be contacted on btongminh@users.sourceforge.net.
-
-This framework heavily depends on Bob Ippolito's
-[simplejson](https://github.com/simplejson/simplejson).
-
-
-## Implementation notes ##
-Most properties and generators accept the same parameters as the API,
-without their two letter prefix.
-Exceptions to this rule:
-* `Image.imageinfo` is the imageinfo of the latest image. Earlier versions can be
- fetched using `imagehistory()`
-* `Site.all*`: parameter `[ap]from` renamed to `start`
-* `categorymembers` is implemented as `Category.members`
-* `deletedrevs` is `deletedrevisions`
-* `usercontribs` is `usercontributions`
-* First parameters of `search` and `usercontributions` are `search` and `user`
- respectively
-
-Properties and generators are implemented as Python generators.
-Their limit parameter is only an indication of the number of items in one chunk.
-It is not the total limit.
-Doing `list(generator(limit = limit))` will return ALL items of generator,
-and not be limited by the limit value.
-Default chunk size is generally the maximum chunk size.
-
-
-## HTTPS ##
-To use https, specify the host as a tuple in the form of `('https', hostname)`.
-
-
-## Example ##
-```python
-## For more information, see REFERENCE.md
-# Init site object
-import mwclient
-site = mwclient.Site('commons.wikimedia.org')
-site.login(username, password) # Optional
-
-# Edit page
-page = site.Pages['Commons:Sandbox']
-text = page.edit()
-print 'Text in sandbox:', text.encode('utf-8')
-page.save(text + u'\nExtra data', summary = 'Test edit')
-
-# Printing imageusage
-image = site.Images['Example.jpg']
-print 'Image', image.name.encode('utf-8'), 'usage:'
-for page in image.imageusage():
- print 'Used:', page.name.encode('utf-8'), '; namespace', page.namespace
- print 'Image info:', image.imageinfo
-
-# Uploading a file
-site.upload(open('file.jpg'), 'destination.jpg', 'Image description')
-
-# Listing all categories (don't do this in reality)
-for category in site.allcategories():
- print category
-```
-
-## License ##
- Copyright (c) 2006-2013 Bryan Tong Minh
-
- Permission is hereby granted, free of charge, to any person
- obtaining a copy of this software and associated documentation
- files (the "Software"), to deal in the Software without
- restriction, including without limitation the rights to use,
- copy, modify, merge, publish, distribute, sublicense, and/or sell
- copies of the Software, and to permit persons to whom the
- Software is furnished to do so, subject to the following
- conditions:
-
- The above copyright notice and this permission notice shall be
- included in all copies or substantial portions of the Software.
-
- THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
- OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
- HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
- WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
- OTHER DEALINGS IN THE SOFTWARE.
diff --git a/README.rst b/README.rst
new file mode 100644
index 0000000000000000000000000000000000000000..e56ef3561c82e8a8d987abd19d094ccb1913f3e8
--- /dev/null
+++ b/README.rst
@@ -0,0 +1,85 @@
+mwclient
+========
+
+Mwclient is a client to the `MediaWiki API`_ which provides access to most
+API functionality. It depends heavily on Bob Ippolito's SimpleJSON_,
+requires Python 2.4 and supports MediaWiki 1.11 and above. For functions not
+available in the current MediaWiki, a ``MediaWikiVersionError`` is raised.
+
+This framework was written by Bryan Tong Minh, who released the latest stable
+`version 0.6.5`_ at 6 May 2011. The current `development version`_ can be
+installed directly off github:
+
+.. code-block:: console
+
+ $ pip install git+git://github.com/btongminh/mwclient.git
+
+Please see `release notes`_ for a list of changes.
+
+Implementation notes
+--------------------
+
+Most properties and generators accept the same parameters as the API, without
+their two letter prefix. Exceptions to this rule:
+
+* ``Image.imageinfo`` is the imageinfo of the latest image. Earlier versions can be
+ fetched using ``imagehistory()``
+* ``Site.all*``: parameter ``[ap]from`` renamed to ``start``
+* ``categorymembers`` is implemented as ``Category.members``
+* ``deletedrevs`` is ``deletedrevisions``
+* ``usercontribs`` is ``usercontributions``
+* First parameters of ``search`` and ``usercontributions`` are ``search`` and ``user``
+ respectively
+
+Properties and generators are implemented as Python generators.
+Their limit parameter is only an indication of the number of items in one chunk.
+It is not the total limit.
+Doing ``list(generator(limit = limit))`` will return ALL items of generator,
+and not be limited by the limit value.
+Default chunk size is generally the maximum chunk size.
+
+
+HTTPS
+-----
+
+To use https, specify the host as a tuple in the form of ``('https', hostname)``.
+
+
+Example
+-------
+
+For more information, see `REFERENCE.md <REFERENCE.md>`_.
+
+.. code-block:: python
+
+ # Initialize Site object
+ import mwclient
+ site = mwclient.Site('commons.wikimedia.org')
+ site.login(username, password) # Optional
+
+ # Edit page
+ page = site.Pages['Commons:Sandbox']
+ text = page.edit()
+ print 'Text in sandbox:', text.encode('utf-8')
+ page.save(text + u'\nExtra data', summary = 'Test edit')
+
+ # Printing imageusage
+ image = site.Images['Example.jpg']
+ print 'Image', image.name.encode('utf-8'), 'usage:'
+ for page in image.imageusage():
+ print 'Used:', page.name.encode('utf-8'), '; namespace', page.namespace
+ print 'Image info:', image.imageinfo
+
+ # Uploading a file
+ site.upload(open('file.jpg'), 'destination.jpg', 'Image description')
+
+ # Listing all categories (don't do this in reality)
+ for category in site.allcategories():
+ print category
+
+
+.. _`MediaWiki API`: http://mediawiki.org/wiki/API
+.. _SimpleJSON: //github.com/simplejson/simplejson
+.. _`version 0.6.5`: //github.com/btongminh/mwclient/archive/REL_0_6_5.zip
+.. _`development version`: //github.com/btongminh/mwclient
+.. _`release notes`: //github.com/btongminh/mwclient/blob/master/RELEASE-NOTES.md
diff --git a/distribute_setup.py b/distribute_setup.py
new file mode 100644
index 0000000000000000000000000000000000000000..3ea2e667f1eda6cf54465a0acccfdff587a60663
--- /dev/null
+++ b/distribute_setup.py
@@ -0,0 +1,485 @@
+#!python
+"""Bootstrap distribute installation
+
+If you want to use setuptools in your package's setup.py, just include this
+file in the same directory with it, and add this to the top of your setup.py::
+
+ from distribute_setup import use_setuptools
+ use_setuptools()
+
+If you want to require a specific version of setuptools, set a download
+mirror, or use an alternate download directory, you can do so by supplying
+the appropriate options to ``use_setuptools()``.
+
+This file can also be run as a script to install or upgrade setuptools.
+"""
+import os
+import sys
+import time
+import fnmatch
+import tempfile
+import tarfile
+from distutils import log
+
+try:
+ from site import USER_SITE
+except ImportError:
+ USER_SITE = None
+
+try:
+ import subprocess
+
+ def _python_cmd(*args):
+ args = (sys.executable,) + args
+ return subprocess.call(args) == 0
+
+except ImportError:
+ # will be used for python 2.3
+ def _python_cmd(*args):
+ args = (sys.executable,) + args
+ # quoting arguments if windows
+ if sys.platform == 'win32':
+ def quote(arg):
+ if ' ' in arg:
+ return '"%s"' % arg
+ return arg
+ args = [quote(arg) for arg in args]
+ return os.spawnl(os.P_WAIT, sys.executable, *args) == 0
+
+DEFAULT_VERSION = "0.6.14"
+DEFAULT_URL = "http://pypi.python.org/packages/source/d/distribute/"
+SETUPTOOLS_FAKED_VERSION = "0.6c11"
+
+SETUPTOOLS_PKG_INFO = """\
+Metadata-Version: 1.0
+Name: setuptools
+Version: %s
+Summary: xxxx
+Home-page: xxx
+Author: xxx
+Author-email: xxx
+License: xxx
+Description: xxx
+""" % SETUPTOOLS_FAKED_VERSION
+
+
+def _install(tarball):
+ # extracting the tarball
+ tmpdir = tempfile.mkdtemp()
+ log.warn('Extracting in %s', tmpdir)
+ old_wd = os.getcwd()
+ try:
+ os.chdir(tmpdir)
+ tar = tarfile.open(tarball)
+ _extractall(tar)
+ tar.close()
+
+ # going in the directory
+ subdir = os.path.join(tmpdir, os.listdir(tmpdir)[0])
+ os.chdir(subdir)
+ log.warn('Now working in %s', subdir)
+
+ # installing
+ log.warn('Installing Distribute')
+ if not _python_cmd('setup.py', 'install'):
+ log.warn('Something went wrong during the installation.')
+ log.warn('See the error message above.')
+ finally:
+ os.chdir(old_wd)
+
+
+def _build_egg(egg, tarball, to_dir):
+ # extracting the tarball
+ tmpdir = tempfile.mkdtemp()
+ log.warn('Extracting in %s', tmpdir)
+ old_wd = os.getcwd()
+ try:
+ os.chdir(tmpdir)
+ tar = tarfile.open(tarball)
+ _extractall(tar)
+ tar.close()
+
+ # going in the directory
+ subdir = os.path.join(tmpdir, os.listdir(tmpdir)[0])
+ os.chdir(subdir)
+ log.warn('Now working in %s', subdir)
+
+ # building an egg
+ log.warn('Building a Distribute egg in %s', to_dir)
+ _python_cmd('setup.py', '-q', 'bdist_egg', '--dist-dir', to_dir)
+
+ finally:
+ os.chdir(old_wd)
+ # returning the result
+ log.warn(egg)
+ if not os.path.exists(egg):
+ raise IOError('Could not build the egg.')
+
+
+def _do_download(version, download_base, to_dir, download_delay):
+ egg = os.path.join(to_dir, 'distribute-%s-py%d.%d.egg'
+ % (version, sys.version_info[0], sys.version_info[1]))
+ if not os.path.exists(egg):
+ tarball = download_setuptools(version, download_base,
+ to_dir, download_delay)
+ _build_egg(egg, tarball, to_dir)
+ sys.path.insert(0, egg)
+ import setuptools
+ setuptools.bootstrap_install_from = egg
+
+
+def use_setuptools(version=DEFAULT_VERSION, download_base=DEFAULT_URL,
+ to_dir=os.curdir, download_delay=15, no_fake=True):
+ # making sure we use the absolute path
+ to_dir = os.path.abspath(to_dir)
+ was_imported = 'pkg_resources' in sys.modules or \
+ 'setuptools' in sys.modules
+ try:
+ try:
+ import pkg_resources
+ if not hasattr(pkg_resources, '_distribute'):
+ if not no_fake:
+ _fake_setuptools()
+ raise ImportError
+ except ImportError:
+ return _do_download(version, download_base, to_dir, download_delay)
+ try:
+ pkg_resources.require("distribute>="+version)
+ return
+ except pkg_resources.VersionConflict:
+ e = sys.exc_info()[1]
+ if was_imported:
+ sys.stderr.write(
+ "The required version of distribute (>=%s) is not available,\n"
+ "and can't be installed while this script is running. Please\n"
+ "install a more recent version first, using\n"
+ "'easy_install -U distribute'."
+ "\n\n(Currently using %r)\n" % (version, e.args[0]))
+ sys.exit(2)
+ else:
+ del pkg_resources, sys.modules['pkg_resources'] # reload ok
+ return _do_download(version, download_base, to_dir,
+ download_delay)
+ except pkg_resources.DistributionNotFound:
+ return _do_download(version, download_base, to_dir,
+ download_delay)
+ finally:
+ if not no_fake:
+ _create_fake_setuptools_pkg_info(to_dir)
+
+def download_setuptools(version=DEFAULT_VERSION, download_base=DEFAULT_URL,
+ to_dir=os.curdir, delay=15):
+ """Download distribute from a specified location and return its filename
+
+ `version` should be a valid distribute version number that is available
+ as an egg for download under the `download_base` URL (which should end
+ with a '/'). `to_dir` is the directory where the egg will be downloaded.
+ `delay` is the number of seconds to pause before an actual download
+ attempt.
+ """
+ # making sure we use the absolute path
+ to_dir = os.path.abspath(to_dir)
+ try:
+ from urllib.request import urlopen
+ except ImportError:
+ from urllib2 import urlopen
+ tgz_name = "distribute-%s.tar.gz" % version
+ url = download_base + tgz_name
+ saveto = os.path.join(to_dir, tgz_name)
+ src = dst = None
+ if not os.path.exists(saveto): # Avoid repeated downloads
+ try:
+ log.warn("Downloading %s", url)
+ src = urlopen(url)
+ # Read/write all in one block, so we don't create a corrupt file
+ # if the download is interrupted.
+ data = src.read()
+ dst = open(saveto, "wb")
+ dst.write(data)
+ finally:
+ if src:
+ src.close()
+ if dst:
+ dst.close()
+ return os.path.realpath(saveto)
+
+def _no_sandbox(function):
+ def __no_sandbox(*args, **kw):
+ try:
+ from setuptools.sandbox import DirectorySandbox
+ if not hasattr(DirectorySandbox, '_old'):
+ def violation(*args):
+ pass
+ DirectorySandbox._old = DirectorySandbox._violation
+ DirectorySandbox._violation = violation
+ patched = True
+ else:
+ patched = False
+ except ImportError:
+ patched = False
+
+ try:
+ return function(*args, **kw)
+ finally:
+ if patched:
+ DirectorySandbox._violation = DirectorySandbox._old
+ del DirectorySandbox._old
+
+ return __no_sandbox
+
+def _patch_file(path, content):
+ """Will backup the file then patch it"""
+ existing_content = open(path).read()
+ if existing_content == content:
+ # already patched
+ log.warn('Already patched.')
+ return False
+ log.warn('Patching...')
+ _rename_path(path)
+ f = open(path, 'w')
+ try:
+ f.write(content)
+ finally:
+ f.close()
+ return True
+
+_patch_file = _no_sandbox(_patch_file)
+
+def _same_content(path, content):
+ return open(path).read() == content
+
+def _rename_path(path):
+ new_name = path + '.OLD.%s' % time.time()
+ log.warn('Renaming %s into %s', path, new_name)
+ os.rename(path, new_name)
+ return new_name
+
+def _remove_flat_installation(placeholder):
+ if not os.path.isdir(placeholder):
+ log.warn('Unkown installation at %s', placeholder)
+ return False
+ found = False
+ for file in os.listdir(placeholder):
+ if fnmatch.fnmatch(file, 'setuptools*.egg-info'):
+ found = True
+ break
+ if not found:
+ log.warn('Could not locate setuptools*.egg-info')
+ return
+
+ log.warn('Removing elements out of the way...')
+ pkg_info = os.path.join(placeholder, file)
+ if os.path.isdir(pkg_info):
+ patched = _patch_egg_dir(pkg_info)
+ else:
+ patched = _patch_file(pkg_info, SETUPTOOLS_PKG_INFO)
+
+ if not patched:
+ log.warn('%s already patched.', pkg_info)
+ return False
+ # now let's move the files out of the way
+ for element in ('setuptools', 'pkg_resources.py', 'site.py'):
+ element = os.path.join(placeholder, element)
+ if os.path.exists(element):
+ _rename_path(element)
+ else:
+ log.warn('Could not find the %s element of the '
+ 'Setuptools distribution', element)
+ return True
+
+_remove_flat_installation = _no_sandbox(_remove_flat_installation)
+
+def _after_install(dist):
+ log.warn('After install bootstrap.')
+ placeholder = dist.get_command_obj('install').install_purelib
+ _create_fake_setuptools_pkg_info(placeholder)
+
+def _create_fake_setuptools_pkg_info(placeholder):
+ if not placeholder or not os.path.exists(placeholder):
+ log.warn('Could not find the install location')
+ return
+ pyver = '%s.%s' % (sys.version_info[0], sys.version_info[1])
+ setuptools_file = 'setuptools-%s-py%s.egg-info' % \
+ (SETUPTOOLS_FAKED_VERSION, pyver)
+ pkg_info = os.path.join(placeholder, setuptools_file)
+ if os.path.exists(pkg_info):
+ log.warn('%s already exists', pkg_info)
+ return
+
+ log.warn('Creating %s', pkg_info)
+ f = open(pkg_info, 'w')
+ try:
+ f.write(SETUPTOOLS_PKG_INFO)
+ finally:
+ f.close()
+
+ pth_file = os.path.join(placeholder, 'setuptools.pth')
+ log.warn('Creating %s', pth_file)
+ f = open(pth_file, 'w')
+ try:
+ f.write(os.path.join(os.curdir, setuptools_file))
+ finally:
+ f.close()
+
+_create_fake_setuptools_pkg_info = _no_sandbox(_create_fake_setuptools_pkg_info)
+
+def _patch_egg_dir(path):
+ # let's check if it's already patched
+ pkg_info = os.path.join(path, 'EGG-INFO', 'PKG-INFO')
+ if os.path.exists(pkg_info):
+ if _same_content(pkg_info, SETUPTOOLS_PKG_INFO):
+ log.warn('%s already patched.', pkg_info)
+ return False
+ _rename_path(path)
+ os.mkdir(path)
+ os.mkdir(os.path.join(path, 'EGG-INFO'))
+ pkg_info = os.path.join(path, 'EGG-INFO', 'PKG-INFO')
+ f = open(pkg_info, 'w')
+ try:
+ f.write(SETUPTOOLS_PKG_INFO)
+ finally:
+ f.close()
+ return True
+
+_patch_egg_dir = _no_sandbox(_patch_egg_dir)
+
+def _before_install():
+ log.warn('Before install bootstrap.')
+ _fake_setuptools()
+
+
+def _under_prefix(location):
+ if 'install' not in sys.argv:
+ return True
+ args = sys.argv[sys.argv.index('install')+1:]
+ for index, arg in enumerate(args):
+ for option in ('--root', '--prefix'):
+ if arg.startswith('%s=' % option):
+ top_dir = arg.split('root=')[-1]
+ return location.startswith(top_dir)
+ elif arg == option:
+ if len(args) > index:
+ top_dir = args[index+1]
+ return location.startswith(top_dir)
+ if arg == '--user' and USER_SITE is not None:
+ return location.startswith(USER_SITE)
+ return True
+
+
+def _fake_setuptools():
+ log.warn('Scanning installed packages')
+ try:
+ import pkg_resources
+ except ImportError:
+ # we're cool
+ log.warn('Setuptools or Distribute does not seem to be installed.')
+ return
+ ws = pkg_resources.working_set
+ try:
+ setuptools_dist = ws.find(pkg_resources.Requirement.parse('setuptools',
+ replacement=False))
+ except TypeError:
+ # old distribute API
+ setuptools_dist = ws.find(pkg_resources.Requirement.parse('setuptools'))
+
+ if setuptools_dist is None:
+ log.warn('No setuptools distribution found')
+ return
+ # detecting if it was already faked
+ setuptools_location = setuptools_dist.location
+ log.warn('Setuptools installation detected at %s', setuptools_location)
+
+ # if --root or --preix was provided, and if
+ # setuptools is not located in them, we don't patch it
+ if not _under_prefix(setuptools_location):
+ log.warn('Not patching, --root or --prefix is installing Distribute'
+ ' in another location')
+ return
+
+ # let's see if its an egg
+ if not setuptools_location.endswith('.egg'):
+ log.warn('Non-egg installation')
+ res = _remove_flat_installation(setuptools_location)
+ if not res:
+ return
+ else:
+ log.warn('Egg installation')
+ pkg_info = os.path.join(setuptools_location, 'EGG-INFO', 'PKG-INFO')
+ if (os.path.exists(pkg_info) and
+ _same_content(pkg_info, SETUPTOOLS_PKG_INFO)):
+ log.warn('Already patched.')
+ return
+ log.warn('Patching...')
+ # let's create a fake egg replacing setuptools one
+ res = _patch_egg_dir(setuptools_location)
+ if not res:
+ return
+ log.warn('Patched done.')
+ _relaunch()
+
+
+def _relaunch():
+ log.warn('Relaunching...')
+ # we have to relaunch the process
+ # pip marker to avoid a relaunch bug
+ if sys.argv[:3] == ['-c', 'install', '--single-version-externally-managed']:
+ sys.argv[0] = 'setup.py'
+ args = [sys.executable] + sys.argv
+ sys.exit(subprocess.call(args))
+
+
+def _extractall(self, path=".", members=None):
+ """Extract all members from the archive to the current working
+ directory and set owner, modification time and permissions on
+ directories afterwards. `path' specifies a different directory
+ to extract to. `members' is optional and must be a subset of the
+ list returned by getmembers().
+ """
+ import copy
+ import operator
+ from tarfile import ExtractError
+ directories = []
+
+ if members is None:
+ members = self
+
+ for tarinfo in members:
+ if tarinfo.isdir():
+ # Extract directories with a safe mode.
+ directories.append(tarinfo)
+ tarinfo = copy.copy(tarinfo)
+ tarinfo.mode = 448 # decimal for oct 0700
+ self.extract(tarinfo, path)
+
+ # Reverse sort directories.
+ if sys.version_info < (2, 4):
+ def sorter(dir1, dir2):
+ return cmp(dir1.name, dir2.name)
+ directories.sort(sorter)
+ directories.reverse()
+ else:
+ directories.sort(key=operator.attrgetter('name'), reverse=True)
+
+ # Set correct owner, mtime and filemode on directories.
+ for tarinfo in directories:
+ dirpath = os.path.join(path, tarinfo.name)
+ try:
+ self.chown(tarinfo, dirpath)
+ self.utime(tarinfo, dirpath)
+ self.chmod(tarinfo, dirpath)
+ except ExtractError:
+ e = sys.exc_info()[1]
+ if self.errorlevel > 1:
+ raise
+ else:
+ self._dbg(1, "tarfile: %s" % e)
+
+
+def main(argv, version=DEFAULT_VERSION):
+ """Install or upgrade setuptools and EasyInstall"""
+ tarball = download_setuptools()
+ _install(tarball)
+
+
+if __name__ == '__main__':
+ main(sys.argv[1:])
diff --git a/ez_setup.py b/ez_setup.py
new file mode 100644
index 0000000000000000000000000000000000000000..3ea2e667f1eda6cf54465a0acccfdff587a60663
--- /dev/null
+++ b/ez_setup.py
@@ -0,0 +1,485 @@
+#!python
+"""Bootstrap distribute installation
+
+If you want to use setuptools in your package's setup.py, just include this
+file in the same directory with it, and add this to the top of your setup.py::
+
+ from distribute_setup import use_setuptools
+ use_setuptools()
+
+If you want to require a specific version of setuptools, set a download
+mirror, or use an alternate download directory, you can do so by supplying
+the appropriate options to ``use_setuptools()``.
+
+This file can also be run as a script to install or upgrade setuptools.
+"""
+import os
+import sys
+import time
+import fnmatch
+import tempfile
+import tarfile
+from distutils import log
+
+try:
+ from site import USER_SITE
+except ImportError:
+ USER_SITE = None
+
+try:
+ import subprocess
+
+ def _python_cmd(*args):
+ args = (sys.executable,) + args
+ return subprocess.call(args) == 0
+
+except ImportError:
+ # will be used for python 2.3
+ def _python_cmd(*args):
+ args = (sys.executable,) + args
+ # quoting arguments if windows
+ if sys.platform == 'win32':
+ def quote(arg):
+ if ' ' in arg:
+ return '"%s"' % arg
+ return arg
+ args = [quote(arg) for arg in args]
+ return os.spawnl(os.P_WAIT, sys.executable, *args) == 0
+
+DEFAULT_VERSION = "0.6.14"
+DEFAULT_URL = "http://pypi.python.org/packages/source/d/distribute/"
+SETUPTOOLS_FAKED_VERSION = "0.6c11"
+
+SETUPTOOLS_PKG_INFO = """\
+Metadata-Version: 1.0
+Name: setuptools
+Version: %s
+Summary: xxxx
+Home-page: xxx
+Author: xxx
+Author-email: xxx
+License: xxx
+Description: xxx
+""" % SETUPTOOLS_FAKED_VERSION
+
+
+def _install(tarball):
+ # extracting the tarball
+ tmpdir = tempfile.mkdtemp()
+ log.warn('Extracting in %s', tmpdir)
+ old_wd = os.getcwd()
+ try:
+ os.chdir(tmpdir)
+ tar = tarfile.open(tarball)
+ _extractall(tar)
+ tar.close()
+
+ # going in the directory
+ subdir = os.path.join(tmpdir, os.listdir(tmpdir)[0])
+ os.chdir(subdir)
+ log.warn('Now working in %s', subdir)
+
+ # installing
+ log.warn('Installing Distribute')
+ if not _python_cmd('setup.py', 'install'):
+ log.warn('Something went wrong during the installation.')
+ log.warn('See the error message above.')
+ finally:
+ os.chdir(old_wd)
+
+
+def _build_egg(egg, tarball, to_dir):
+ # extracting the tarball
+ tmpdir = tempfile.mkdtemp()
+ log.warn('Extracting in %s', tmpdir)
+ old_wd = os.getcwd()
+ try:
+ os.chdir(tmpdir)
+ tar = tarfile.open(tarball)
+ _extractall(tar)
+ tar.close()
+
+ # going in the directory
+ subdir = os.path.join(tmpdir, os.listdir(tmpdir)[0])
+ os.chdir(subdir)
+ log.warn('Now working in %s', subdir)
+
+ # building an egg
+ log.warn('Building a Distribute egg in %s', to_dir)
+ _python_cmd('setup.py', '-q', 'bdist_egg', '--dist-dir', to_dir)
+
+ finally:
+ os.chdir(old_wd)
+ # returning the result
+ log.warn(egg)
+ if not os.path.exists(egg):
+ raise IOError('Could not build the egg.')
+
+
+def _do_download(version, download_base, to_dir, download_delay):
+ egg = os.path.join(to_dir, 'distribute-%s-py%d.%d.egg'
+ % (version, sys.version_info[0], sys.version_info[1]))
+ if not os.path.exists(egg):
+ tarball = download_setuptools(version, download_base,
+ to_dir, download_delay)
+ _build_egg(egg, tarball, to_dir)
+ sys.path.insert(0, egg)
+ import setuptools
+ setuptools.bootstrap_install_from = egg
+
+
+def use_setuptools(version=DEFAULT_VERSION, download_base=DEFAULT_URL,
+ to_dir=os.curdir, download_delay=15, no_fake=True):
+ # making sure we use the absolute path
+ to_dir = os.path.abspath(to_dir)
+ was_imported = 'pkg_resources' in sys.modules or \
+ 'setuptools' in sys.modules
+ try:
+ try:
+ import pkg_resources
+ if not hasattr(pkg_resources, '_distribute'):
+ if not no_fake:
+ _fake_setuptools()
+ raise ImportError
+ except ImportError:
+ return _do_download(version, download_base, to_dir, download_delay)
+ try:
+ pkg_resources.require("distribute>="+version)
+ return
+ except pkg_resources.VersionConflict:
+ e = sys.exc_info()[1]
+ if was_imported:
+ sys.stderr.write(
+ "The required version of distribute (>=%s) is not available,\n"
+ "and can't be installed while this script is running. Please\n"
+ "install a more recent version first, using\n"
+ "'easy_install -U distribute'."
+ "\n\n(Currently using %r)\n" % (version, e.args[0]))
+ sys.exit(2)
+ else:
+ del pkg_resources, sys.modules['pkg_resources'] # reload ok
+ return _do_download(version, download_base, to_dir,
+ download_delay)
+ except pkg_resources.DistributionNotFound:
+ return _do_download(version, download_base, to_dir,
+ download_delay)
+ finally:
+ if not no_fake:
+ _create_fake_setuptools_pkg_info(to_dir)
+
+def download_setuptools(version=DEFAULT_VERSION, download_base=DEFAULT_URL,
+ to_dir=os.curdir, delay=15):
+ """Download distribute from a specified location and return its filename
+
+ `version` should be a valid distribute version number that is available
+ as an egg for download under the `download_base` URL (which should end
+ with a '/'). `to_dir` is the directory where the egg will be downloaded.
+ `delay` is the number of seconds to pause before an actual download
+ attempt.
+ """
+ # making sure we use the absolute path
+ to_dir = os.path.abspath(to_dir)
+ try:
+ from urllib.request import urlopen
+ except ImportError:
+ from urllib2 import urlopen
+ tgz_name = "distribute-%s.tar.gz" % version
+ url = download_base + tgz_name
+ saveto = os.path.join(to_dir, tgz_name)
+ src = dst = None
+ if not os.path.exists(saveto): # Avoid repeated downloads
+ try:
+ log.warn("Downloading %s", url)
+ src = urlopen(url)
+ # Read/write all in one block, so we don't create a corrupt file
+ # if the download is interrupted.
+ data = src.read()
+ dst = open(saveto, "wb")
+ dst.write(data)
+ finally:
+ if src:
+ src.close()
+ if dst:
+ dst.close()
+ return os.path.realpath(saveto)
+
+def _no_sandbox(function):
+ def __no_sandbox(*args, **kw):
+ try:
+ from setuptools.sandbox import DirectorySandbox
+ if not hasattr(DirectorySandbox, '_old'):
+ def violation(*args):
+ pass
+ DirectorySandbox._old = DirectorySandbox._violation
+ DirectorySandbox._violation = violation
+ patched = True
+ else:
+ patched = False
+ except ImportError:
+ patched = False
+
+ try:
+ return function(*args, **kw)
+ finally:
+ if patched:
+ DirectorySandbox._violation = DirectorySandbox._old
+ del DirectorySandbox._old
+
+ return __no_sandbox
+
+def _patch_file(path, content):
+ """Will backup the file then patch it"""
+ existing_content = open(path).read()
+ if existing_content == content:
+ # already patched
+ log.warn('Already patched.')
+ return False
+ log.warn('Patching...')
+ _rename_path(path)
+ f = open(path, 'w')
+ try:
+ f.write(content)
+ finally:
+ f.close()
+ return True
+
+_patch_file = _no_sandbox(_patch_file)
+
+def _same_content(path, content):
+ return open(path).read() == content
+
+def _rename_path(path):
+ new_name = path + '.OLD.%s' % time.time()
+ log.warn('Renaming %s into %s', path, new_name)
+ os.rename(path, new_name)
+ return new_name
+
+def _remove_flat_installation(placeholder):
+ if not os.path.isdir(placeholder):
+ log.warn('Unkown installation at %s', placeholder)
+ return False
+ found = False
+ for file in os.listdir(placeholder):
+ if fnmatch.fnmatch(file, 'setuptools*.egg-info'):
+ found = True
+ break
+ if not found:
+ log.warn('Could not locate setuptools*.egg-info')
+ return
+
+ log.warn('Removing elements out of the way...')
+ pkg_info = os.path.join(placeholder, file)
+ if os.path.isdir(pkg_info):
+ patched = _patch_egg_dir(pkg_info)
+ else:
+ patched = _patch_file(pkg_info, SETUPTOOLS_PKG_INFO)
+
+ if not patched:
+ log.warn('%s already patched.', pkg_info)
+ return False
+ # now let's move the files out of the way
+ for element in ('setuptools', 'pkg_resources.py', 'site.py'):
+ element = os.path.join(placeholder, element)
+ if os.path.exists(element):
+ _rename_path(element)
+ else:
+ log.warn('Could not find the %s element of the '
+ 'Setuptools distribution', element)
+ return True
+
+_remove_flat_installation = _no_sandbox(_remove_flat_installation)
+
+def _after_install(dist):
+ log.warn('After install bootstrap.')
+ placeholder = dist.get_command_obj('install').install_purelib
+ _create_fake_setuptools_pkg_info(placeholder)
+
+def _create_fake_setuptools_pkg_info(placeholder):
+ if not placeholder or not os.path.exists(placeholder):
+ log.warn('Could not find the install location')
+ return
+ pyver = '%s.%s' % (sys.version_info[0], sys.version_info[1])
+ setuptools_file = 'setuptools-%s-py%s.egg-info' % \
+ (SETUPTOOLS_FAKED_VERSION, pyver)
+ pkg_info = os.path.join(placeholder, setuptools_file)
+ if os.path.exists(pkg_info):
+ log.warn('%s already exists', pkg_info)
+ return
+
+ log.warn('Creating %s', pkg_info)
+ f = open(pkg_info, 'w')
+ try:
+ f.write(SETUPTOOLS_PKG_INFO)
+ finally:
+ f.close()
+
+ pth_file = os.path.join(placeholder, 'setuptools.pth')
+ log.warn('Creating %s', pth_file)
+ f = open(pth_file, 'w')
+ try:
+ f.write(os.path.join(os.curdir, setuptools_file))
+ finally:
+ f.close()
+
+_create_fake_setuptools_pkg_info = _no_sandbox(_create_fake_setuptools_pkg_info)
+
+def _patch_egg_dir(path):
+ # let's check if it's already patched
+ pkg_info = os.path.join(path, 'EGG-INFO', 'PKG-INFO')
+ if os.path.exists(pkg_info):
+ if _same_content(pkg_info, SETUPTOOLS_PKG_INFO):
+ log.warn('%s already patched.', pkg_info)
+ return False
+ _rename_path(path)
+ os.mkdir(path)
+ os.mkdir(os.path.join(path, 'EGG-INFO'))
+ pkg_info = os.path.join(path, 'EGG-INFO', 'PKG-INFO')
+ f = open(pkg_info, 'w')
+ try:
+ f.write(SETUPTOOLS_PKG_INFO)
+ finally:
+ f.close()
+ return True
+
+_patch_egg_dir = _no_sandbox(_patch_egg_dir)
+
+def _before_install():
+ log.warn('Before install bootstrap.')
+ _fake_setuptools()
+
+
+def _under_prefix(location):
+ if 'install' not in sys.argv:
+ return True
+ args = sys.argv[sys.argv.index('install')+1:]
+ for index, arg in enumerate(args):
+ for option in ('--root', '--prefix'):
+ if arg.startswith('%s=' % option):
+ top_dir = arg.split('root=')[-1]
+ return location.startswith(top_dir)
+ elif arg == option:
+ if len(args) > index:
+ top_dir = args[index+1]
+ return location.startswith(top_dir)
+ if arg == '--user' and USER_SITE is not None:
+ return location.startswith(USER_SITE)
+ return True
+
+
+def _fake_setuptools():
+ log.warn('Scanning installed packages')
+ try:
+ import pkg_resources
+ except ImportError:
+ # we're cool
+ log.warn('Setuptools or Distribute does not seem to be installed.')
+ return
+ ws = pkg_resources.working_set
+ try:
+ setuptools_dist = ws.find(pkg_resources.Requirement.parse('setuptools',
+ replacement=False))
+ except TypeError:
+ # old distribute API
+ setuptools_dist = ws.find(pkg_resources.Requirement.parse('setuptools'))
+
+ if setuptools_dist is None:
+ log.warn('No setuptools distribution found')
+ return
+ # detecting if it was already faked
+ setuptools_location = setuptools_dist.location
+ log.warn('Setuptools installation detected at %s', setuptools_location)
+
+ # if --root or --preix was provided, and if
+ # setuptools is not located in them, we don't patch it
+ if not _under_prefix(setuptools_location):
+ log.warn('Not patching, --root or --prefix is installing Distribute'
+ ' in another location')
+ return
+
+ # let's see if its an egg
+ if not setuptools_location.endswith('.egg'):
+ log.warn('Non-egg installation')
+ res = _remove_flat_installation(setuptools_location)
+ if not res:
+ return
+ else:
+ log.warn('Egg installation')
+ pkg_info = os.path.join(setuptools_location, 'EGG-INFO', 'PKG-INFO')
+ if (os.path.exists(pkg_info) and
+ _same_content(pkg_info, SETUPTOOLS_PKG_INFO)):
+ log.warn('Already patched.')
+ return
+ log.warn('Patching...')
+ # let's create a fake egg replacing setuptools one
+ res = _patch_egg_dir(setuptools_location)
+ if not res:
+ return
+ log.warn('Patched done.')
+ _relaunch()
+
+
+def _relaunch():
+ log.warn('Relaunching...')
+ # we have to relaunch the process
+ # pip marker to avoid a relaunch bug
+ if sys.argv[:3] == ['-c', 'install', '--single-version-externally-managed']:
+ sys.argv[0] = 'setup.py'
+ args = [sys.executable] + sys.argv
+ sys.exit(subprocess.call(args))
+
+
+def _extractall(self, path=".", members=None):
+ """Extract all members from the archive to the current working
+ directory and set owner, modification time and permissions on
+ directories afterwards. `path' specifies a different directory
+ to extract to. `members' is optional and must be a subset of the
+ list returned by getmembers().
+ """
+ import copy
+ import operator
+ from tarfile import ExtractError
+ directories = []
+
+ if members is None:
+ members = self
+
+ for tarinfo in members:
+ if tarinfo.isdir():
+ # Extract directories with a safe mode.
+ directories.append(tarinfo)
+ tarinfo = copy.copy(tarinfo)
+ tarinfo.mode = 448 # decimal for oct 0700
+ self.extract(tarinfo, path)
+
+ # Reverse sort directories.
+ if sys.version_info < (2, 4):
+ def sorter(dir1, dir2):
+ return cmp(dir1.name, dir2.name)
+ directories.sort(sorter)
+ directories.reverse()
+ else:
+ directories.sort(key=operator.attrgetter('name'), reverse=True)
+
+ # Set correct owner, mtime and filemode on directories.
+ for tarinfo in directories:
+ dirpath = os.path.join(path, tarinfo.name)
+ try:
+ self.chown(tarinfo, dirpath)
+ self.utime(tarinfo, dirpath)
+ self.chmod(tarinfo, dirpath)
+ except ExtractError:
+ e = sys.exc_info()[1]
+ if self.errorlevel > 1:
+ raise
+ else:
+ self._dbg(1, "tarfile: %s" % e)
+
+
+def main(argv, version=DEFAULT_VERSION):
+ """Install or upgrade setuptools and EasyInstall"""
+ tarball = download_setuptools()
+ _install(tarball)
+
+
+if __name__ == '__main__':
+ main(sys.argv[1:])
diff --git a/__init__.py b/mwclient/__init__.py
similarity index 90%
rename from __init__.py
rename to mwclient/__init__.py
index 07139f06176ce4fedefa524f600557d322bcdc35..afc17bfa0912cde0b2251bd59074561c844fa29e 100644
--- a/__init__.py
+++ b/mwclient/__init__.py
@@ -23,11 +23,6 @@
OTHER DEALINGS IN THE SOFTWARE.
"""
-import sys as _sys
-import os as _os
-_path = _os.path.dirname(__file__)
-_sys.path.insert(0, _os.path.abspath(_path))
-
from errors import *
from client import Site, __ver__
-import ex
\ No newline at end of file
+import ex
diff --git a/client.py b/mwclient/client.py
similarity index 100%
rename from client.py
rename to mwclient/client.py
diff --git a/compatibility.py b/mwclient/compatibility.py
similarity index 100%
rename from compatibility.py
rename to mwclient/compatibility.py
diff --git a/errors.py b/mwclient/errors.py
similarity index 100%
rename from errors.py
rename to mwclient/errors.py
diff --git a/ex.py b/mwclient/ex.py
similarity index 100%
rename from ex.py
rename to mwclient/ex.py
diff --git a/http.py b/mwclient/http.py
similarity index 100%
rename from http.py
rename to mwclient/http.py
diff --git a/listing.py b/mwclient/listing.py
similarity index 100%
rename from listing.py
rename to mwclient/listing.py
diff --git a/page.py b/mwclient/page.py
similarity index 100%
rename from page.py
rename to mwclient/page.py
diff --git a/page_nowriteapi.py b/mwclient/page_nowriteapi.py
similarity index 100%
rename from page_nowriteapi.py
rename to mwclient/page_nowriteapi.py
diff --git a/upload.py b/mwclient/upload.py
similarity index 100%
rename from upload.py
rename to mwclient/upload.py
diff --git a/setup.py b/setup.py
new file mode 100644
index 0000000000000000000000000000000000000000..627beb219ea6f824a0644f9042e59cbeb722d1a5
--- /dev/null
+++ b/setup.py
@@ -0,0 +1,30 @@
+#!/usr/bin/env python
+#encoding=utf-8
+
+# Bootstrap setuptools
+from ez_setup import use_setuptools
+use_setuptools()
+
+from setuptools import setup
+import os
+
+here = os.path.abspath(os.path.dirname(__file__))
+README = open(os.path.join(here, 'README.rst')).read()
+
+setup(name='mwclient',
+ version='0.7dev',
+ description='MediaWiki API client',
+ long_description=README,
+ classifiers=[
+ 'Programming Language :: Python',
+ 'Programming Language :: Python :: 2.6',
+ 'Programming Language :: Python :: 2.7'
+ ],
+ keywords='mediawiki wikipedia',
+ author='Bryan Tong Minh',
+ author_email='bryan.tongminh@gmail.com',
+ url='https://github.com/btongminh/mwclient',
+ license='MIT',
+ packages=['mwclient'],
+ install_requires=['simplejson']
+ )
diff --git a/simplejson/__init__.py b/simplejson/__init__.py
deleted file mode 100644
index c36be23c074fa51ec30458fa1f8fe40fce3c9911..0000000000000000000000000000000000000000
--- a/simplejson/__init__.py
+++ /dev/null
@@ -1,438 +0,0 @@
-r"""JSON (JavaScript Object Notation) <http://json.org> is a subset of
-JavaScript syntax (ECMA-262 3rd edition) used as a lightweight data
-interchange format.
-
-:mod:`simplejson` exposes an API familiar to users of the standard library
-:mod:`marshal` and :mod:`pickle` modules. It is the externally maintained
-version of the :mod:`json` library contained in Python 2.6, but maintains
-compatibility with Python 2.4 and Python 2.5 and (currently) has
-significant performance advantages, even without using the optional C
-extension for speedups.
-
-Encoding basic Python object hierarchies::
-
- >>> import simplejson as json
- >>> json.dumps(['foo', {'bar': ('baz', None, 1.0, 2)}])
- '["foo", {"bar": ["baz", null, 1.0, 2]}]'
- >>> print json.dumps("\"foo\bar")
- "\"foo\bar"
- >>> print json.dumps(u'\u1234')
- "\u1234"
- >>> print json.dumps('\\')
- "\\"
- >>> print json.dumps({"c": 0, "b": 0, "a": 0}, sort_keys=True)
- {"a": 0, "b": 0, "c": 0}
- >>> from StringIO import StringIO
- >>> io = StringIO()
- >>> json.dump(['streaming API'], io)
- >>> io.getvalue()
- '["streaming API"]'
-
-Compact encoding::
-
- >>> import simplejson as json
- >>> json.dumps([1,2,3,{'4': 5, '6': 7}], separators=(',',':'))
- '[1,2,3,{"4":5,"6":7}]'
-
-Pretty printing::
-
- >>> import simplejson as json
- >>> s = json.dumps({'4': 5, '6': 7}, sort_keys=True, indent=' ')
- >>> print '\n'.join([l.rstrip() for l in s.splitlines()])
- {
- "4": 5,
- "6": 7
- }
-
-Decoding JSON::
-
- >>> import simplejson as json
- >>> obj = [u'foo', {u'bar': [u'baz', None, 1.0, 2]}]
- >>> json.loads('["foo", {"bar":["baz", null, 1.0, 2]}]') == obj
- True
- >>> json.loads('"\\"foo\\bar"') == u'"foo\x08ar'
- True
- >>> from StringIO import StringIO
- >>> io = StringIO('["streaming API"]')
- >>> json.load(io)[0] == 'streaming API'
- True
-
-Specializing JSON object decoding::
-
- >>> import simplejson as json
- >>> def as_complex(dct):
- ... if '__complex__' in dct:
- ... return complex(dct['real'], dct['imag'])
- ... return dct
- ...
- >>> json.loads('{"__complex__": true, "real": 1, "imag": 2}',
- ... object_hook=as_complex)
- (1+2j)
- >>> from decimal import Decimal
- >>> json.loads('1.1', parse_float=Decimal) == Decimal('1.1')
- True
-
-Specializing JSON object encoding::
-
- >>> import simplejson as json
- >>> def encode_complex(obj):
- ... if isinstance(obj, complex):
- ... return [obj.real, obj.imag]
- ... raise TypeError(repr(o) + " is not JSON serializable")
- ...
- >>> json.dumps(2 + 1j, default=encode_complex)
- '[2.0, 1.0]'
- >>> json.JSONEncoder(default=encode_complex).encode(2 + 1j)
- '[2.0, 1.0]'
- >>> ''.join(json.JSONEncoder(default=encode_complex).iterencode(2 + 1j))
- '[2.0, 1.0]'
-
-
-Using simplejson.tool from the shell to validate and pretty-print::
-
- $ echo '{"json":"obj"}' | python -m simplejson.tool
- {
- "json": "obj"
- }
- $ echo '{ 1.2:3.4}' | python -m simplejson.tool
- Expecting property name: line 1 column 2 (char 2)
-"""
-__version__ = '2.1.3'
-__all__ = [
- 'dump', 'dumps', 'load', 'loads',
- 'JSONDecoder', 'JSONDecodeError', 'JSONEncoder',
- 'OrderedDict',
-]
-
-__author__ = 'Bob Ippolito <bob@redivi.com>'
-
-from decimal import Decimal
-
-from decoder import JSONDecoder, JSONDecodeError
-from encoder import JSONEncoder
-def _import_OrderedDict():
- import collections
- try:
- return collections.OrderedDict
- except AttributeError:
- import ordered_dict
- return ordered_dict.OrderedDict
-OrderedDict = _import_OrderedDict()
-
-def _import_c_make_encoder():
- try:
- from simplejson._speedups import make_encoder
- return make_encoder
- except ImportError:
- return None
-
-_default_encoder = JSONEncoder(
- skipkeys=False,
- ensure_ascii=True,
- check_circular=True,
- allow_nan=True,
- indent=None,
- separators=None,
- encoding='utf-8',
- default=None,
- use_decimal=False,
-)
-
-def dump(obj, fp, skipkeys=False, ensure_ascii=True, check_circular=True,
- allow_nan=True, cls=None, indent=None, separators=None,
- encoding='utf-8', default=None, use_decimal=False, **kw):
- """Serialize ``obj`` as a JSON formatted stream to ``fp`` (a
- ``.write()``-supporting file-like object).
-
- If ``skipkeys`` is true then ``dict`` keys that are not basic types
- (``str``, ``unicode``, ``int``, ``long``, ``float``, ``bool``, ``None``)
- will be skipped instead of raising a ``TypeError``.
-
- If ``ensure_ascii`` is false, then the some chunks written to ``fp``
- may be ``unicode`` instances, subject to normal Python ``str`` to
- ``unicode`` coercion rules. Unless ``fp.write()`` explicitly
- understands ``unicode`` (as in ``codecs.getwriter()``) this is likely
- to cause an error.
-
- If ``check_circular`` is false, then the circular reference check
- for container types will be skipped and a circular reference will
- result in an ``OverflowError`` (or worse).
-
- If ``allow_nan`` is false, then it will be a ``ValueError`` to
- serialize out of range ``float`` values (``nan``, ``inf``, ``-inf``)
- in strict compliance of the JSON specification, instead of using the
- JavaScript equivalents (``NaN``, ``Infinity``, ``-Infinity``).
-
- If *indent* is a string, then JSON array elements and object members
- will be pretty-printed with a newline followed by that string repeated
- for each level of nesting. ``None`` (the default) selects the most compact
- representation without any newlines. For backwards compatibility with
- versions of simplejson earlier than 2.1.0, an integer is also accepted
- and is converted to a string with that many spaces.
-
- If ``separators`` is an ``(item_separator, dict_separator)`` tuple
- then it will be used instead of the default ``(', ', ': ')`` separators.
- ``(',', ':')`` is the most compact JSON representation.
-
- ``encoding`` is the character encoding for str instances, default is UTF-8.
-
- ``default(obj)`` is a function that should return a serializable version
- of obj or raise TypeError. The default simply raises TypeError.
-
- If *use_decimal* is true (default: ``False``) then decimal.Decimal
- will be natively serialized to JSON with full precision.
-
- To use a custom ``JSONEncoder`` subclass (e.g. one that overrides the
- ``.default()`` method to serialize additional types), specify it with
- the ``cls`` kwarg.
-
- """
- # cached encoder
- if (not skipkeys and ensure_ascii and
- check_circular and allow_nan and
- cls is None and indent is None and separators is None and
- encoding == 'utf-8' and default is None and not use_decimal
- and not kw):
- iterable = _default_encoder.iterencode(obj)
- else:
- if cls is None:
- cls = JSONEncoder
- iterable = cls(skipkeys=skipkeys, ensure_ascii=ensure_ascii,
- check_circular=check_circular, allow_nan=allow_nan, indent=indent,
- separators=separators, encoding=encoding,
- default=default, use_decimal=use_decimal, **kw).iterencode(obj)
- # could accelerate with writelines in some versions of Python, at
- # a debuggability cost
- for chunk in iterable:
- fp.write(chunk)
-
-
-def dumps(obj, skipkeys=False, ensure_ascii=True, check_circular=True,
- allow_nan=True, cls=None, indent=None, separators=None,
- encoding='utf-8', default=None, use_decimal=False, **kw):
- """Serialize ``obj`` to a JSON formatted ``str``.
-
- If ``skipkeys`` is false then ``dict`` keys that are not basic types
- (``str``, ``unicode``, ``int``, ``long``, ``float``, ``bool``, ``None``)
- will be skipped instead of raising a ``TypeError``.
-
- If ``ensure_ascii`` is false, then the return value will be a
- ``unicode`` instance subject to normal Python ``str`` to ``unicode``
- coercion rules instead of being escaped to an ASCII ``str``.
-
- If ``check_circular`` is false, then the circular reference check
- for container types will be skipped and a circular reference will
- result in an ``OverflowError`` (or worse).
-
- If ``allow_nan`` is false, then it will be a ``ValueError`` to
- serialize out of range ``float`` values (``nan``, ``inf``, ``-inf``) in
- strict compliance of the JSON specification, instead of using the
- JavaScript equivalents (``NaN``, ``Infinity``, ``-Infinity``).
-
- If ``indent`` is a string, then JSON array elements and object members
- will be pretty-printed with a newline followed by that string repeated
- for each level of nesting. ``None`` (the default) selects the most compact
- representation without any newlines. For backwards compatibility with
- versions of simplejson earlier than 2.1.0, an integer is also accepted
- and is converted to a string with that many spaces.
-
- If ``separators`` is an ``(item_separator, dict_separator)`` tuple
- then it will be used instead of the default ``(', ', ': ')`` separators.
- ``(',', ':')`` is the most compact JSON representation.
-
- ``encoding`` is the character encoding for str instances, default is UTF-8.
-
- ``default(obj)`` is a function that should return a serializable version
- of obj or raise TypeError. The default simply raises TypeError.
-
- If *use_decimal* is true (default: ``False``) then decimal.Decimal
- will be natively serialized to JSON with full precision.
-
- To use a custom ``JSONEncoder`` subclass (e.g. one that overrides the
- ``.default()`` method to serialize additional types), specify it with
- the ``cls`` kwarg.
-
- """
- # cached encoder
- if (not skipkeys and ensure_ascii and
- check_circular and allow_nan and
- cls is None and indent is None and separators is None and
- encoding == 'utf-8' and default is None and not use_decimal
- and not kw):
- return _default_encoder.encode(obj)
- if cls is None:
- cls = JSONEncoder
- return cls(
- skipkeys=skipkeys, ensure_ascii=ensure_ascii,
- check_circular=check_circular, allow_nan=allow_nan, indent=indent,
- separators=separators, encoding=encoding, default=default,
- use_decimal=use_decimal, **kw).encode(obj)
-
-
-_default_decoder = JSONDecoder(encoding=None, object_hook=None,
- object_pairs_hook=None)
-
-
-def load(fp, encoding=None, cls=None, object_hook=None, parse_float=None,
- parse_int=None, parse_constant=None, object_pairs_hook=None,
- use_decimal=False, **kw):
- """Deserialize ``fp`` (a ``.read()``-supporting file-like object containing
- a JSON document) to a Python object.
-
- *encoding* determines the encoding used to interpret any
- :class:`str` objects decoded by this instance (``'utf-8'`` by
- default). It has no effect when decoding :class:`unicode` objects.
-
- Note that currently only encodings that are a superset of ASCII work,
- strings of other encodings should be passed in as :class:`unicode`.
-
- *object_hook*, if specified, will be called with the result of every
- JSON object decoded and its return value will be used in place of the
- given :class:`dict`. This can be used to provide custom
- deserializations (e.g. to support JSON-RPC class hinting).
-
- *object_pairs_hook* is an optional function that will be called with
- the result of any object literal decode with an ordered list of pairs.
- The return value of *object_pairs_hook* will be used instead of the
- :class:`dict`. This feature can be used to implement custom decoders
- that rely on the order that the key and value pairs are decoded (for
- example, :func:`collections.OrderedDict` will remember the order of
- insertion). If *object_hook* is also defined, the *object_pairs_hook*
- takes priority.
-
- *parse_float*, if specified, will be called with the string of every
- JSON float to be decoded. By default, this is equivalent to
- ``float(num_str)``. This can be used to use another datatype or parser
- for JSON floats (e.g. :class:`decimal.Decimal`).
-
- *parse_int*, if specified, will be called with the string of every
- JSON int to be decoded. By default, this is equivalent to
- ``int(num_str)``. This can be used to use another datatype or parser
- for JSON integers (e.g. :class:`float`).
-
- *parse_constant*, if specified, will be called with one of the
- following strings: ``'-Infinity'``, ``'Infinity'``, ``'NaN'``. This
- can be used to raise an exception if invalid JSON numbers are
- encountered.
-
- If *use_decimal* is true (default: ``False``) then it implies
- parse_float=decimal.Decimal for parity with ``dump``.
-
- To use a custom ``JSONDecoder`` subclass, specify it with the ``cls``
- kwarg.
-
- """
- return loads(fp.read(),
- encoding=encoding, cls=cls, object_hook=object_hook,
- parse_float=parse_float, parse_int=parse_int,
- parse_constant=parse_constant, object_pairs_hook=object_pairs_hook,
- use_decimal=use_decimal, **kw)
-
-
-def loads(s, encoding=None, cls=None, object_hook=None, parse_float=None,
- parse_int=None, parse_constant=None, object_pairs_hook=None,
- use_decimal=False, **kw):
- """Deserialize ``s`` (a ``str`` or ``unicode`` instance containing a JSON
- document) to a Python object.
-
- *encoding* determines the encoding used to interpret any
- :class:`str` objects decoded by this instance (``'utf-8'`` by
- default). It has no effect when decoding :class:`unicode` objects.
-
- Note that currently only encodings that are a superset of ASCII work,
- strings of other encodings should be passed in as :class:`unicode`.
-
- *object_hook*, if specified, will be called with the result of every
- JSON object decoded and its return value will be used in place of the
- given :class:`dict`. This can be used to provide custom
- deserializations (e.g. to support JSON-RPC class hinting).
-
- *object_pairs_hook* is an optional function that will be called with
- the result of any object literal decode with an ordered list of pairs.
- The return value of *object_pairs_hook* will be used instead of the
- :class:`dict`. This feature can be used to implement custom decoders
- that rely on the order that the key and value pairs are decoded (for
- example, :func:`collections.OrderedDict` will remember the order of
- insertion). If *object_hook* is also defined, the *object_pairs_hook*
- takes priority.
-
- *parse_float*, if specified, will be called with the string of every
- JSON float to be decoded. By default, this is equivalent to
- ``float(num_str)``. This can be used to use another datatype or parser
- for JSON floats (e.g. :class:`decimal.Decimal`).
-
- *parse_int*, if specified, will be called with the string of every
- JSON int to be decoded. By default, this is equivalent to
- ``int(num_str)``. This can be used to use another datatype or parser
- for JSON integers (e.g. :class:`float`).
-
- *parse_constant*, if specified, will be called with one of the
- following strings: ``'-Infinity'``, ``'Infinity'``, ``'NaN'``. This
- can be used to raise an exception if invalid JSON numbers are
- encountered.
-
- If *use_decimal* is true (default: ``False``) then it implies
- parse_float=decimal.Decimal for parity with ``dump``.
-
- To use a custom ``JSONDecoder`` subclass, specify it with the ``cls``
- kwarg.
-
- """
- if (cls is None and encoding is None and object_hook is None and
- parse_int is None and parse_float is None and
- parse_constant is None and object_pairs_hook is None
- and not use_decimal and not kw):
- return _default_decoder.decode(s)
- if cls is None:
- cls = JSONDecoder
- if object_hook is not None:
- kw['object_hook'] = object_hook
- if object_pairs_hook is not None:
- kw['object_pairs_hook'] = object_pairs_hook
- if parse_float is not None:
- kw['parse_float'] = parse_float
- if parse_int is not None:
- kw['parse_int'] = parse_int
- if parse_constant is not None:
- kw['parse_constant'] = parse_constant
- if use_decimal:
- if parse_float is not None:
- raise TypeError("use_decimal=True implies parse_float=Decimal")
- kw['parse_float'] = Decimal
- return cls(encoding=encoding, **kw).decode(s)
-
-
-def _toggle_speedups(enabled):
- import simplejson.decoder as dec
- import simplejson.encoder as enc
- import simplejson.scanner as scan
- c_make_encoder = _import_c_make_encoder()
- if enabled:
- dec.scanstring = dec.c_scanstring or dec.py_scanstring
- enc.c_make_encoder = c_make_encoder
- enc.encode_basestring_ascii = (enc.c_encode_basestring_ascii or
- enc.py_encode_basestring_ascii)
- scan.make_scanner = scan.c_make_scanner or scan.py_make_scanner
- else:
- dec.scanstring = dec.py_scanstring
- enc.c_make_encoder = None
- enc.encode_basestring_ascii = enc.py_encode_basestring_ascii
- scan.make_scanner = scan.py_make_scanner
- dec.make_scanner = scan.make_scanner
- global _default_decoder
- _default_decoder = JSONDecoder(
- encoding=None,
- object_hook=None,
- object_pairs_hook=None,
- )
- global _default_encoder
- _default_encoder = JSONEncoder(
- skipkeys=False,
- ensure_ascii=True,
- check_circular=True,
- allow_nan=True,
- indent=None,
- separators=None,
- encoding='utf-8',
- default=None,
- )
diff --git a/simplejson/_speedups.c b/simplejson/_speedups.c
deleted file mode 100644
index e43ae7cfb6c6b4ed97ef26ed24f27ce3f721ac12..0000000000000000000000000000000000000000
--- a/simplejson/_speedups.c
+++ /dev/null
@@ -1,2602 +0,0 @@
-#include "Python.h"
-#include "structmember.h"
-#if PY_VERSION_HEX < 0x02070000 && !defined(PyOS_string_to_double)
-#define PyOS_string_to_double json_PyOS_string_to_double
-static double
-json_PyOS_string_to_double(const char *s, char **endptr, PyObject *overflow_exception);
-static double
-json_PyOS_string_to_double(const char *s, char **endptr, PyObject *overflow_exception) {
- double x;
- assert(endptr == NULL);
- assert(overflow_exception == NULL);
- PyFPE_START_PROTECT("json_PyOS_string_to_double", return -1.0;)
- x = PyOS_ascii_atof(s);
- PyFPE_END_PROTECT(x)
- return x;
-}
-#endif
-#if PY_VERSION_HEX < 0x02060000 && !defined(Py_TYPE)
-#define Py_TYPE(ob) (((PyObject*)(ob))->ob_type)
-#endif
-#if PY_VERSION_HEX < 0x02050000 && !defined(PY_SSIZE_T_MIN)
-typedef int Py_ssize_t;
-#define PY_SSIZE_T_MAX INT_MAX
-#define PY_SSIZE_T_MIN INT_MIN
-#define PyInt_FromSsize_t PyInt_FromLong
-#define PyInt_AsSsize_t PyInt_AsLong
-#endif
-#ifndef Py_IS_FINITE
-#define Py_IS_FINITE(X) (!Py_IS_INFINITY(X) && !Py_IS_NAN(X))
-#endif
-
-#ifdef __GNUC__
-#define UNUSED __attribute__((__unused__))
-#else
-#define UNUSED
-#endif
-
-#define DEFAULT_ENCODING "utf-8"
-
-#define PyScanner_Check(op) PyObject_TypeCheck(op, &PyScannerType)
-#define PyScanner_CheckExact(op) (Py_TYPE(op) == &PyScannerType)
-#define PyEncoder_Check(op) PyObject_TypeCheck(op, &PyEncoderType)
-#define PyEncoder_CheckExact(op) (Py_TYPE(op) == &PyEncoderType)
-#define Decimal_Check(op) (PyObject_TypeCheck(op, DecimalTypePtr))
-
-static PyTypeObject PyScannerType;
-static PyTypeObject PyEncoderType;
-static PyTypeObject *DecimalTypePtr;
-
-typedef struct _PyScannerObject {
- PyObject_HEAD
- PyObject *encoding;
- PyObject *strict;
- PyObject *object_hook;
- PyObject *pairs_hook;
- PyObject *parse_float;
- PyObject *parse_int;
- PyObject *parse_constant;
- PyObject *memo;
-} PyScannerObject;
-
-static PyMemberDef scanner_members[] = {
- {"encoding", T_OBJECT, offsetof(PyScannerObject, encoding), READONLY, "encoding"},
- {"strict", T_OBJECT, offsetof(PyScannerObject, strict), READONLY, "strict"},
- {"object_hook", T_OBJECT, offsetof(PyScannerObject, object_hook), READONLY, "object_hook"},
- {"object_pairs_hook", T_OBJECT, offsetof(PyScannerObject, pairs_hook), READONLY, "object_pairs_hook"},
- {"parse_float", T_OBJECT, offsetof(PyScannerObject, parse_float), READONLY, "parse_float"},
- {"parse_int", T_OBJECT, offsetof(PyScannerObject, parse_int), READONLY, "parse_int"},
- {"parse_constant", T_OBJECT, offsetof(PyScannerObject, parse_constant), READONLY, "parse_constant"},
- {NULL}
-};
-
-typedef struct _PyEncoderObject {
- PyObject_HEAD
- PyObject *markers;
- PyObject *defaultfn;
- PyObject *encoder;
- PyObject *indent;
- PyObject *key_separator;
- PyObject *item_separator;
- PyObject *sort_keys;
- PyObject *skipkeys;
- PyObject *key_memo;
- int fast_encode;
- int allow_nan;
- int use_decimal;
-} PyEncoderObject;
-
-static PyMemberDef encoder_members[] = {
- {"markers", T_OBJECT, offsetof(PyEncoderObject, markers), READONLY, "markers"},
- {"default", T_OBJECT, offsetof(PyEncoderObject, defaultfn), READONLY, "default"},
- {"encoder", T_OBJECT, offsetof(PyEncoderObject, encoder), READONLY, "encoder"},
- {"indent", T_OBJECT, offsetof(PyEncoderObject, indent), READONLY, "indent"},
- {"key_separator", T_OBJECT, offsetof(PyEncoderObject, key_separator), READONLY, "key_separator"},
- {"item_separator", T_OBJECT, offsetof(PyEncoderObject, item_separator), READONLY, "item_separator"},
- {"sort_keys", T_OBJECT, offsetof(PyEncoderObject, sort_keys), READONLY, "sort_keys"},
- {"skipkeys", T_OBJECT, offsetof(PyEncoderObject, skipkeys), READONLY, "skipkeys"},
- {"key_memo", T_OBJECT, offsetof(PyEncoderObject, key_memo), READONLY, "key_memo"},
- {NULL}
-};
-
-static Py_ssize_t
-ascii_escape_char(Py_UNICODE c, char *output, Py_ssize_t chars);
-static PyObject *
-ascii_escape_unicode(PyObject *pystr);
-static PyObject *
-ascii_escape_str(PyObject *pystr);
-static PyObject *
-py_encode_basestring_ascii(PyObject* self UNUSED, PyObject *pystr);
-void init_speedups(void);
-static PyObject *
-scan_once_str(PyScannerObject *s, PyObject *pystr, Py_ssize_t idx, Py_ssize_t *next_idx_ptr);
-static PyObject *
-scan_once_unicode(PyScannerObject *s, PyObject *pystr, Py_ssize_t idx, Py_ssize_t *next_idx_ptr);
-static PyObject *
-_build_rval_index_tuple(PyObject *rval, Py_ssize_t idx);
-static PyObject *
-scanner_new(PyTypeObject *type, PyObject *args, PyObject *kwds);
-static int
-scanner_init(PyObject *self, PyObject *args, PyObject *kwds);
-static void
-scanner_dealloc(PyObject *self);
-static int
-scanner_clear(PyObject *self);
-static PyObject *
-encoder_new(PyTypeObject *type, PyObject *args, PyObject *kwds);
-static int
-encoder_init(PyObject *self, PyObject *args, PyObject *kwds);
-static void
-encoder_dealloc(PyObject *self);
-static int
-encoder_clear(PyObject *self);
-static int
-encoder_listencode_list(PyEncoderObject *s, PyObject *rval, PyObject *seq, Py_ssize_t indent_level);
-static int
-encoder_listencode_obj(PyEncoderObject *s, PyObject *rval, PyObject *obj, Py_ssize_t indent_level);
-static int
-encoder_listencode_dict(PyEncoderObject *s, PyObject *rval, PyObject *dct, Py_ssize_t indent_level);
-static PyObject *
-_encoded_const(PyObject *obj);
-static void
-raise_errmsg(char *msg, PyObject *s, Py_ssize_t end);
-static PyObject *
-encoder_encode_string(PyEncoderObject *s, PyObject *obj);
-static int
-_convertPyInt_AsSsize_t(PyObject *o, Py_ssize_t *size_ptr);
-static PyObject *
-_convertPyInt_FromSsize_t(Py_ssize_t *size_ptr);
-static PyObject *
-encoder_encode_float(PyEncoderObject *s, PyObject *obj);
-
-#define S_CHAR(c) (c >= ' ' && c <= '~' && c != '\\' && c != '"')
-#define IS_WHITESPACE(c) (((c) == ' ') || ((c) == '\t') || ((c) == '\n') || ((c) == '\r'))
-
-#define MIN_EXPANSION 6
-#ifdef Py_UNICODE_WIDE
-#define MAX_EXPANSION (2 * MIN_EXPANSION)
-#else
-#define MAX_EXPANSION MIN_EXPANSION
-#endif
-
-static int
-_convertPyInt_AsSsize_t(PyObject *o, Py_ssize_t *size_ptr)
-{
- /* PyObject to Py_ssize_t converter */
- *size_ptr = PyInt_AsSsize_t(o);
- if (*size_ptr == -1 && PyErr_Occurred())
- return 0;
- return 1;
-}
-
-static PyObject *
-_convertPyInt_FromSsize_t(Py_ssize_t *size_ptr)
-{
- /* Py_ssize_t to PyObject converter */
- return PyInt_FromSsize_t(*size_ptr);
-}
-
-static Py_ssize_t
-ascii_escape_char(Py_UNICODE c, char *output, Py_ssize_t chars)
-{
- /* Escape unicode code point c to ASCII escape sequences
- in char *output. output must have at least 12 bytes unused to
- accommodate an escaped surrogate pair "\uXXXX\uXXXX" */
- output[chars++] = '\\';
- switch (c) {
- case '\\': output[chars++] = (char)c; break;
- case '"': output[chars++] = (char)c; break;
- case '\b': output[chars++] = 'b'; break;
- case '\f': output[chars++] = 'f'; break;
- case '\n': output[chars++] = 'n'; break;
- case '\r': output[chars++] = 'r'; break;
- case '\t': output[chars++] = 't'; break;
- default:
-#ifdef Py_UNICODE_WIDE
- if (c >= 0x10000) {
- /* UTF-16 surrogate pair */
- Py_UNICODE v = c - 0x10000;
- c = 0xd800 | ((v >> 10) & 0x3ff);
- output[chars++] = 'u';
- output[chars++] = "0123456789abcdef"[(c >> 12) & 0xf];
- output[chars++] = "0123456789abcdef"[(c >> 8) & 0xf];
- output[chars++] = "0123456789abcdef"[(c >> 4) & 0xf];
- output[chars++] = "0123456789abcdef"[(c ) & 0xf];
- c = 0xdc00 | (v & 0x3ff);
- output[chars++] = '\\';
- }
-#endif
- output[chars++] = 'u';
- output[chars++] = "0123456789abcdef"[(c >> 12) & 0xf];
- output[chars++] = "0123456789abcdef"[(c >> 8) & 0xf];
- output[chars++] = "0123456789abcdef"[(c >> 4) & 0xf];
- output[chars++] = "0123456789abcdef"[(c ) & 0xf];
- }
- return chars;
-}
-
-static PyObject *
-ascii_escape_unicode(PyObject *pystr)
-{
- /* Take a PyUnicode pystr and return a new ASCII-only escaped PyString */
- Py_ssize_t i;
- Py_ssize_t input_chars;
- Py_ssize_t output_size;
- Py_ssize_t max_output_size;
- Py_ssize_t chars;
- PyObject *rval;
- char *output;
- Py_UNICODE *input_unicode;
-
- input_chars = PyUnicode_GET_SIZE(pystr);
- input_unicode = PyUnicode_AS_UNICODE(pystr);
-
- /* One char input can be up to 6 chars output, estimate 4 of these */
- output_size = 2 + (MIN_EXPANSION * 4) + input_chars;
- max_output_size = 2 + (input_chars * MAX_EXPANSION);
- rval = PyString_FromStringAndSize(NULL, output_size);
- if (rval == NULL) {
- return NULL;
- }
- output = PyString_AS_STRING(rval);
- chars = 0;
- output[chars++] = '"';
- for (i = 0; i < input_chars; i++) {
- Py_UNICODE c = input_unicode[i];
- if (S_CHAR(c)) {
- output[chars++] = (char)c;
- }
- else {
- chars = ascii_escape_char(c, output, chars);
- }
- if (output_size - chars < (1 + MAX_EXPANSION)) {
- /* There's more than four, so let's resize by a lot */
- Py_ssize_t new_output_size = output_size * 2;
- /* This is an upper bound */
- if (new_output_size > max_output_size) {
- new_output_size = max_output_size;
- }
- /* Make sure that the output size changed before resizing */
- if (new_output_size != output_size) {
- output_size = new_output_size;
- if (_PyString_Resize(&rval, output_size) == -1) {
- return NULL;
- }
- output = PyString_AS_STRING(rval);
- }
- }
- }
- output[chars++] = '"';
- if (_PyString_Resize(&rval, chars) == -1) {
- return NULL;
- }
- return rval;
-}
-
-static PyObject *
-ascii_escape_str(PyObject *pystr)
-{
- /* Take a PyString pystr and return a new ASCII-only escaped PyString */
- Py_ssize_t i;
- Py_ssize_t input_chars;
- Py_ssize_t output_size;
- Py_ssize_t chars;
- PyObject *rval;
- char *output;
- char *input_str;
-
- input_chars = PyString_GET_SIZE(pystr);
- input_str = PyString_AS_STRING(pystr);
-
- /* Fast path for a string that's already ASCII */
- for (i = 0; i < input_chars; i++) {
- Py_UNICODE c = (Py_UNICODE)(unsigned char)input_str[i];
- if (!S_CHAR(c)) {
- /* If we have to escape something, scan the string for unicode */
- Py_ssize_t j;
- for (j = i; j < input_chars; j++) {
- c = (Py_UNICODE)(unsigned char)input_str[j];
- if (c > 0x7f) {
- /* We hit a non-ASCII character, bail to unicode mode */
- PyObject *uni;
- uni = PyUnicode_DecodeUTF8(input_str, input_chars, "strict");
- if (uni == NULL) {
- return NULL;
- }
- rval = ascii_escape_unicode(uni);
- Py_DECREF(uni);
- return rval;
- }
- }
- break;
- }
- }
-
- if (i == input_chars) {
- /* Input is already ASCII */
- output_size = 2 + input_chars;
- }
- else {
- /* One char input can be up to 6 chars output, estimate 4 of these */
- output_size = 2 + (MIN_EXPANSION * 4) + input_chars;
- }
- rval = PyString_FromStringAndSize(NULL, output_size);
- if (rval == NULL) {
- return NULL;
- }
- output = PyString_AS_STRING(rval);
- output[0] = '"';
-
- /* We know that everything up to i is ASCII already */
- chars = i + 1;
- memcpy(&output[1], input_str, i);
-
- for (; i < input_chars; i++) {
- Py_UNICODE c = (Py_UNICODE)(unsigned char)input_str[i];
- if (S_CHAR(c)) {
- output[chars++] = (char)c;
- }
- else {
- chars = ascii_escape_char(c, output, chars);
- }
- /* An ASCII char can't possibly expand to a surrogate! */
- if (output_size - chars < (1 + MIN_EXPANSION)) {
- /* There's more than four, so let's resize by a lot */
- output_size *= 2;
- if (output_size > 2 + (input_chars * MIN_EXPANSION)) {
- output_size = 2 + (input_chars * MIN_EXPANSION);
- }
- if (_PyString_Resize(&rval, output_size) == -1) {
- return NULL;
- }
- output = PyString_AS_STRING(rval);
- }
- }
- output[chars++] = '"';
- if (_PyString_Resize(&rval, chars) == -1) {
- return NULL;
- }
- return rval;
-}
-
-static void
-raise_errmsg(char *msg, PyObject *s, Py_ssize_t end)
-{
- /* Use the Python function simplejson.decoder.errmsg to raise a nice
- looking ValueError exception */
- static PyObject *JSONDecodeError = NULL;
- PyObject *exc;
- if (JSONDecodeError == NULL) {
- PyObject *decoder = PyImport_ImportModule("simplejson.decoder");
- if (decoder == NULL)
- return;
- JSONDecodeError = PyObject_GetAttrString(decoder, "JSONDecodeError");
- Py_DECREF(decoder);
- if (JSONDecodeError == NULL)
- return;
- }
- exc = PyObject_CallFunction(JSONDecodeError, "(zOO&)", msg, s, _convertPyInt_FromSsize_t, &end);
- if (exc) {
- PyErr_SetObject(JSONDecodeError, exc);
- Py_DECREF(exc);
- }
-}
-
-static PyObject *
-join_list_unicode(PyObject *lst)
-{
- /* return u''.join(lst) */
- static PyObject *joinfn = NULL;
- if (joinfn == NULL) {
- PyObject *ustr = PyUnicode_FromUnicode(NULL, 0);
- if (ustr == NULL)
- return NULL;
-
- joinfn = PyObject_GetAttrString(ustr, "join");
- Py_DECREF(ustr);
- if (joinfn == NULL)
- return NULL;
- }
- return PyObject_CallFunctionObjArgs(joinfn, lst, NULL);
-}
-
-static PyObject *
-join_list_string(PyObject *lst)
-{
- /* return ''.join(lst) */
- static PyObject *joinfn = NULL;
- if (joinfn == NULL) {
- PyObject *ustr = PyString_FromStringAndSize(NULL, 0);
- if (ustr == NULL)
- return NULL;
-
- joinfn = PyObject_GetAttrString(ustr, "join");
- Py_DECREF(ustr);
- if (joinfn == NULL)
- return NULL;
- }
- return PyObject_CallFunctionObjArgs(joinfn, lst, NULL);
-}
-
-static PyObject *
-_build_rval_index_tuple(PyObject *rval, Py_ssize_t idx) {
- /* return (rval, idx) tuple, stealing reference to rval */
- PyObject *tpl;
- PyObject *pyidx;
- /*
- steal a reference to rval, returns (rval, idx)
- */
- if (rval == NULL) {
- return NULL;
- }
- pyidx = PyInt_FromSsize_t(idx);
- if (pyidx == NULL) {
- Py_DECREF(rval);
- return NULL;
- }
- tpl = PyTuple_New(2);
- if (tpl == NULL) {
- Py_DECREF(pyidx);
- Py_DECREF(rval);
- return NULL;
- }
- PyTuple_SET_ITEM(tpl, 0, rval);
- PyTuple_SET_ITEM(tpl, 1, pyidx);
- return tpl;
-}
-
-#define APPEND_OLD_CHUNK \
- if (chunk != NULL) { \
- if (chunks == NULL) { \
- chunks = PyList_New(0); \
- if (chunks == NULL) { \
- goto bail; \
- } \
- } \
- if (PyList_Append(chunks, chunk)) { \
- goto bail; \
- } \
- Py_CLEAR(chunk); \
- }
-
-static PyObject *
-scanstring_str(PyObject *pystr, Py_ssize_t end, char *encoding, int strict, Py_ssize_t *next_end_ptr)
-{
- /* Read the JSON string from PyString pystr.
- end is the index of the first character after the quote.
- encoding is the encoding of pystr (must be an ASCII superset)
- if strict is zero then literal control characters are allowed
- *next_end_ptr is a return-by-reference index of the character
- after the end quote
-
- Return value is a new PyString (if ASCII-only) or PyUnicode
- */
- PyObject *rval;
- Py_ssize_t len = PyString_GET_SIZE(pystr);
- Py_ssize_t begin = end - 1;
- Py_ssize_t next = begin;
- int has_unicode = 0;
- char *buf = PyString_AS_STRING(pystr);
- PyObject *chunks = NULL;
- PyObject *chunk = NULL;
-
- if (end < 0 || len <= end) {
- PyErr_SetString(PyExc_ValueError, "end is out of bounds");
- goto bail;
- }
- while (1) {
- /* Find the end of the string or the next escape */
- Py_UNICODE c = 0;
- for (next = end; next < len; next++) {
- c = (unsigned char)buf[next];
- if (c == '"' || c == '\\') {
- break;
- }
- else if (strict && c <= 0x1f) {
- raise_errmsg("Invalid control character at", pystr, next);
- goto bail;
- }
- else if (c > 0x7f) {
- has_unicode = 1;
- }
- }
- if (!(c == '"' || c == '\\')) {
- raise_errmsg("Unterminated string starting at", pystr, begin);
- goto bail;
- }
- /* Pick up this chunk if it's not zero length */
- if (next != end) {
- PyObject *strchunk;
- APPEND_OLD_CHUNK
- strchunk = PyString_FromStringAndSize(&buf[end], next - end);
- if (strchunk == NULL) {
- goto bail;
- }
- if (has_unicode) {
- chunk = PyUnicode_FromEncodedObject(strchunk, encoding, NULL);
- Py_DECREF(strchunk);
- if (chunk == NULL) {
- goto bail;
- }
- }
- else {
- chunk = strchunk;
- }
- }
- next++;
- if (c == '"') {
- end = next;
- break;
- }
- if (next == len) {
- raise_errmsg("Unterminated string starting at", pystr, begin);
- goto bail;
- }
- c = buf[next];
- if (c != 'u') {
- /* Non-unicode backslash escapes */
- end = next + 1;
- switch (c) {
- case '"': break;
- case '\\': break;
- case '/': break;
- case 'b': c = '\b'; break;
- case 'f': c = '\f'; break;
- case 'n': c = '\n'; break;
- case 'r': c = '\r'; break;
- case 't': c = '\t'; break;
- default: c = 0;
- }
- if (c == 0) {
- raise_errmsg("Invalid \\escape", pystr, end - 2);
- goto bail;
- }
- }
- else {
- c = 0;
- next++;
- end = next + 4;
- if (end >= len) {
- raise_errmsg("Invalid \\uXXXX escape", pystr, next - 1);
- goto bail;
- }
- /* Decode 4 hex digits */
- for (; next < end; next++) {
- Py_UNICODE digit = buf[next];
- c <<= 4;
- switch (digit) {
- case '0': case '1': case '2': case '3': case '4':
- case '5': case '6': case '7': case '8': case '9':
- c |= (digit - '0'); break;
- case 'a': case 'b': case 'c': case 'd': case 'e':
- case 'f':
- c |= (digit - 'a' + 10); break;
- case 'A': case 'B': case 'C': case 'D': case 'E':
- case 'F':
- c |= (digit - 'A' + 10); break;
- default:
- raise_errmsg("Invalid \\uXXXX escape", pystr, end - 5);
- goto bail;
- }
- }
-#ifdef Py_UNICODE_WIDE
- /* Surrogate pair */
- if ((c & 0xfc00) == 0xd800) {
- Py_UNICODE c2 = 0;
- if (end + 6 >= len) {
- raise_errmsg("Unpaired high surrogate", pystr, end - 5);
- goto bail;
- }
- if (buf[next++] != '\\' || buf[next++] != 'u') {
- raise_errmsg("Unpaired high surrogate", pystr, end - 5);
- goto bail;
- }
- end += 6;
- /* Decode 4 hex digits */
- for (; next < end; next++) {
- c2 <<= 4;
- Py_UNICODE digit = buf[next];
- switch (digit) {
- case '0': case '1': case '2': case '3': case '4':
- case '5': case '6': case '7': case '8': case '9':
- c2 |= (digit - '0'); break;
- case 'a': case 'b': case 'c': case 'd': case 'e':
- case 'f':
- c2 |= (digit - 'a' + 10); break;
- case 'A': case 'B': case 'C': case 'D': case 'E':
- case 'F':
- c2 |= (digit - 'A' + 10); break;
- default:
- raise_errmsg("Invalid \\uXXXX escape", pystr, end - 5);
- goto bail;
- }
- }
- if ((c2 & 0xfc00) != 0xdc00) {
- raise_errmsg("Unpaired high surrogate", pystr, end - 5);
- goto bail;
- }
- c = 0x10000 + (((c - 0xd800) << 10) | (c2 - 0xdc00));
- }
- else if ((c & 0xfc00) == 0xdc00) {
- raise_errmsg("Unpaired low surrogate", pystr, end - 5);
- goto bail;
- }
-#endif
- }
- if (c > 0x7f) {
- has_unicode = 1;
- }
- APPEND_OLD_CHUNK
- if (has_unicode) {
- chunk = PyUnicode_FromUnicode(&c, 1);
- if (chunk == NULL) {
- goto bail;
- }
- }
- else {
- char c_char = Py_CHARMASK(c);
- chunk = PyString_FromStringAndSize(&c_char, 1);
- if (chunk == NULL) {
- goto bail;
- }
- }
- }
-
- if (chunks == NULL) {
- if (chunk != NULL)
- rval = chunk;
- else
- rval = PyString_FromStringAndSize("", 0);
- }
- else {
- APPEND_OLD_CHUNK
- rval = join_list_string(chunks);
- if (rval == NULL) {
- goto bail;
- }
- Py_CLEAR(chunks);
- }
-
- *next_end_ptr = end;
- return rval;
-bail:
- *next_end_ptr = -1;
- Py_XDECREF(chunk);
- Py_XDECREF(chunks);
- return NULL;
-}
-
-
-static PyObject *
-scanstring_unicode(PyObject *pystr, Py_ssize_t end, int strict, Py_ssize_t *next_end_ptr)
-{
- /* Read the JSON string from PyUnicode pystr.
- end is the index of the first character after the quote.
- if strict is zero then literal control characters are allowed
- *next_end_ptr is a return-by-reference index of the character
- after the end quote
-
- Return value is a new PyUnicode
- */
- PyObject *rval;
- Py_ssize_t len = PyUnicode_GET_SIZE(pystr);
- Py_ssize_t begin = end - 1;
- Py_ssize_t next = begin;
- const Py_UNICODE *buf = PyUnicode_AS_UNICODE(pystr);
- PyObject *chunks = NULL;
- PyObject *chunk = NULL;
-
- if (end < 0 || len <= end) {
- PyErr_SetString(PyExc_ValueError, "end is out of bounds");
- goto bail;
- }
- while (1) {
- /* Find the end of the string or the next escape */
- Py_UNICODE c = 0;
- for (next = end; next < len; next++) {
- c = buf[next];
- if (c == '"' || c == '\\') {
- break;
- }
- else if (strict && c <= 0x1f) {
- raise_errmsg("Invalid control character at", pystr, next);
- goto bail;
- }
- }
- if (!(c == '"' || c == '\\')) {
- raise_errmsg("Unterminated string starting at", pystr, begin);
- goto bail;
- }
- /* Pick up this chunk if it's not zero length */
- if (next != end) {
- APPEND_OLD_CHUNK
- chunk = PyUnicode_FromUnicode(&buf[end], next - end);
- if (chunk == NULL) {
- goto bail;
- }
- }
- next++;
- if (c == '"') {
- end = next;
- break;
- }
- if (next == len) {
- raise_errmsg("Unterminated string starting at", pystr, begin);
- goto bail;
- }
- c = buf[next];
- if (c != 'u') {
- /* Non-unicode backslash escapes */
- end = next + 1;
- switch (c) {
- case '"': break;
- case '\\': break;
- case '/': break;
- case 'b': c = '\b'; break;
- case 'f': c = '\f'; break;
- case 'n': c = '\n'; break;
- case 'r': c = '\r'; break;
- case 't': c = '\t'; break;
- default: c = 0;
- }
- if (c == 0) {
- raise_errmsg("Invalid \\escape", pystr, end - 2);
- goto bail;
- }
- }
- else {
- c = 0;
- next++;
- end = next + 4;
- if (end >= len) {
- raise_errmsg("Invalid \\uXXXX escape", pystr, next - 1);
- goto bail;
- }
- /* Decode 4 hex digits */
- for (; next < end; next++) {
- Py_UNICODE digit = buf[next];
- c <<= 4;
- switch (digit) {
- case '0': case '1': case '2': case '3': case '4':
- case '5': case '6': case '7': case '8': case '9':
- c |= (digit - '0'); break;
- case 'a': case 'b': case 'c': case 'd': case 'e':
- case 'f':
- c |= (digit - 'a' + 10); break;
- case 'A': case 'B': case 'C': case 'D': case 'E':
- case 'F':
- c |= (digit - 'A' + 10); break;
- default:
- raise_errmsg("Invalid \\uXXXX escape", pystr, end - 5);
- goto bail;
- }
- }
-#ifdef Py_UNICODE_WIDE
- /* Surrogate pair */
- if ((c & 0xfc00) == 0xd800) {
- Py_UNICODE c2 = 0;
- if (end + 6 >= len) {
- raise_errmsg("Unpaired high surrogate", pystr, end - 5);
- goto bail;
- }
- if (buf[next++] != '\\' || buf[next++] != 'u') {
- raise_errmsg("Unpaired high surrogate", pystr, end - 5);
- goto bail;
- }
- end += 6;
- /* Decode 4 hex digits */
- for (; next < end; next++) {
- c2 <<= 4;
- Py_UNICODE digit = buf[next];
- switch (digit) {
- case '0': case '1': case '2': case '3': case '4':
- case '5': case '6': case '7': case '8': case '9':
- c2 |= (digit - '0'); break;
- case 'a': case 'b': case 'c': case 'd': case 'e':
- case 'f':
- c2 |= (digit - 'a' + 10); break;
- case 'A': case 'B': case 'C': case 'D': case 'E':
- case 'F':
- c2 |= (digit - 'A' + 10); break;
- default:
- raise_errmsg("Invalid \\uXXXX escape", pystr, end - 5);
- goto bail;
- }
- }
- if ((c2 & 0xfc00) != 0xdc00) {
- raise_errmsg("Unpaired high surrogate", pystr, end - 5);
- goto bail;
- }
- c = 0x10000 + (((c - 0xd800) << 10) | (c2 - 0xdc00));
- }
- else if ((c & 0xfc00) == 0xdc00) {
- raise_errmsg("Unpaired low surrogate", pystr, end - 5);
- goto bail;
- }
-#endif
- }
- APPEND_OLD_CHUNK
- chunk = PyUnicode_FromUnicode(&c, 1);
- if (chunk == NULL) {
- goto bail;
- }
- }
-
- if (chunks == NULL) {
- if (chunk != NULL)
- rval = chunk;
- else
- rval = PyUnicode_FromUnicode(NULL, 0);
- }
- else {
- APPEND_OLD_CHUNK
- rval = join_list_unicode(chunks);
- if (rval == NULL) {
- goto bail;
- }
- Py_CLEAR(chunks);
- }
- *next_end_ptr = end;
- return rval;
-bail:
- *next_end_ptr = -1;
- Py_XDECREF(chunk);
- Py_XDECREF(chunks);
- return NULL;
-}
-
-PyDoc_STRVAR(pydoc_scanstring,
- "scanstring(basestring, end, encoding, strict=True) -> (str, end)\n"
- "\n"
- "Scan the string s for a JSON string. End is the index of the\n"
- "character in s after the quote that started the JSON string.\n"
- "Unescapes all valid JSON string escape sequences and raises ValueError\n"
- "on attempt to decode an invalid string. If strict is False then literal\n"
- "control characters are allowed in the string.\n"
- "\n"
- "Returns a tuple of the decoded string and the index of the character in s\n"
- "after the end quote."
-);
-
-static PyObject *
-py_scanstring(PyObject* self UNUSED, PyObject *args)
-{
- PyObject *pystr;
- PyObject *rval;
- Py_ssize_t end;
- Py_ssize_t next_end = -1;
- char *encoding = NULL;
- int strict = 1;
- if (!PyArg_ParseTuple(args, "OO&|zi:scanstring", &pystr, _convertPyInt_AsSsize_t, &end, &encoding, &strict)) {
- return NULL;
- }
- if (encoding == NULL) {
- encoding = DEFAULT_ENCODING;
- }
- if (PyString_Check(pystr)) {
- rval = scanstring_str(pystr, end, encoding, strict, &next_end);
- }
- else if (PyUnicode_Check(pystr)) {
- rval = scanstring_unicode(pystr, end, strict, &next_end);
- }
- else {
- PyErr_Format(PyExc_TypeError,
- "first argument must be a string, not %.80s",
- Py_TYPE(pystr)->tp_name);
- return NULL;
- }
- return _build_rval_index_tuple(rval, next_end);
-}
-
-PyDoc_STRVAR(pydoc_encode_basestring_ascii,
- "encode_basestring_ascii(basestring) -> str\n"
- "\n"
- "Return an ASCII-only JSON representation of a Python string"
-);
-
-static PyObject *
-py_encode_basestring_ascii(PyObject* self UNUSED, PyObject *pystr)
-{
- /* Return an ASCII-only JSON representation of a Python string */
- /* METH_O */
- if (PyString_Check(pystr)) {
- return ascii_escape_str(pystr);
- }
- else if (PyUnicode_Check(pystr)) {
- return ascii_escape_unicode(pystr);
- }
- else {
- PyErr_Format(PyExc_TypeError,
- "first argument must be a string, not %.80s",
- Py_TYPE(pystr)->tp_name);
- return NULL;
- }
-}
-
-static void
-scanner_dealloc(PyObject *self)
-{
- /* Deallocate scanner object */
- scanner_clear(self);
- Py_TYPE(self)->tp_free(self);
-}
-
-static int
-scanner_traverse(PyObject *self, visitproc visit, void *arg)
-{
- PyScannerObject *s;
- assert(PyScanner_Check(self));
- s = (PyScannerObject *)self;
- Py_VISIT(s->encoding);
- Py_VISIT(s->strict);
- Py_VISIT(s->object_hook);
- Py_VISIT(s->pairs_hook);
- Py_VISIT(s->parse_float);
- Py_VISIT(s->parse_int);
- Py_VISIT(s->parse_constant);
- Py_VISIT(s->memo);
- return 0;
-}
-
-static int
-scanner_clear(PyObject *self)
-{
- PyScannerObject *s;
- assert(PyScanner_Check(self));
- s = (PyScannerObject *)self;
- Py_CLEAR(s->encoding);
- Py_CLEAR(s->strict);
- Py_CLEAR(s->object_hook);
- Py_CLEAR(s->pairs_hook);
- Py_CLEAR(s->parse_float);
- Py_CLEAR(s->parse_int);
- Py_CLEAR(s->parse_constant);
- Py_CLEAR(s->memo);
- return 0;
-}
-
-static PyObject *
-_parse_object_str(PyScannerObject *s, PyObject *pystr, Py_ssize_t idx, Py_ssize_t *next_idx_ptr) {
- /* Read a JSON object from PyString pystr.
- idx is the index of the first character after the opening curly brace.
- *next_idx_ptr is a return-by-reference index to the first character after
- the closing curly brace.
-
- Returns a new PyObject (usually a dict, but object_hook or
- object_pairs_hook can change that)
- */
- char *str = PyString_AS_STRING(pystr);
- Py_ssize_t end_idx = PyString_GET_SIZE(pystr) - 1;
- PyObject *rval = NULL;
- PyObject *pairs = NULL;
- PyObject *item;
- PyObject *key = NULL;
- PyObject *val = NULL;
- char *encoding = PyString_AS_STRING(s->encoding);
- int strict = PyObject_IsTrue(s->strict);
- int has_pairs_hook = (s->pairs_hook != Py_None);
- Py_ssize_t next_idx;
- if (has_pairs_hook) {
- pairs = PyList_New(0);
- if (pairs == NULL)
- return NULL;
- }
- else {
- rval = PyDict_New();
- if (rval == NULL)
- return NULL;
- }
-
- /* skip whitespace after { */
- while (idx <= end_idx && IS_WHITESPACE(str[idx])) idx++;
-
- /* only loop if the object is non-empty */
- if (idx <= end_idx && str[idx] != '}') {
- while (idx <= end_idx) {
- PyObject *memokey;
-
- /* read key */
- if (str[idx] != '"') {
- raise_errmsg("Expecting property name", pystr, idx);
- goto bail;
- }
- key = scanstring_str(pystr, idx + 1, encoding, strict, &next_idx);
- if (key == NULL)
- goto bail;
- memokey = PyDict_GetItem(s->memo, key);
- if (memokey != NULL) {
- Py_INCREF(memokey);
- Py_DECREF(key);
- key = memokey;
- }
- else {
- if (PyDict_SetItem(s->memo, key, key) < 0)
- goto bail;
- }
- idx = next_idx;
-
- /* skip whitespace between key and : delimiter, read :, skip whitespace */
- while (idx <= end_idx && IS_WHITESPACE(str[idx])) idx++;
- if (idx > end_idx || str[idx] != ':') {
- raise_errmsg("Expecting : delimiter", pystr, idx);
- goto bail;
- }
- idx++;
- while (idx <= end_idx && IS_WHITESPACE(str[idx])) idx++;
-
- /* read any JSON data type */
- val = scan_once_str(s, pystr, idx, &next_idx);
- if (val == NULL)
- goto bail;
-
- if (has_pairs_hook) {
- item = PyTuple_Pack(2, key, val);
- if (item == NULL)
- goto bail;
- Py_CLEAR(key);
- Py_CLEAR(val);
- if (PyList_Append(pairs, item) == -1) {
- Py_DECREF(item);
- goto bail;
- }
- Py_DECREF(item);
- }
- else {
- if (PyDict_SetItem(rval, key, val) < 0)
- goto bail;
- Py_CLEAR(key);
- Py_CLEAR(val);
- }
- idx = next_idx;
-
- /* skip whitespace before } or , */
- while (idx <= end_idx && IS_WHITESPACE(str[idx])) idx++;
-
- /* bail if the object is closed or we didn't get the , delimiter */
- if (idx > end_idx) break;
- if (str[idx] == '}') {
- break;
- }
- else if (str[idx] != ',') {
- raise_errmsg("Expecting , delimiter", pystr, idx);
- goto bail;
- }
- idx++;
-
- /* skip whitespace after , delimiter */
- while (idx <= end_idx && IS_WHITESPACE(str[idx])) idx++;
- }
- }
- /* verify that idx < end_idx, str[idx] should be '}' */
- if (idx > end_idx || str[idx] != '}') {
- raise_errmsg("Expecting object", pystr, end_idx);
- goto bail;
- }
-
- /* if pairs_hook is not None: rval = object_pairs_hook(pairs) */
- if (s->pairs_hook != Py_None) {
- val = PyObject_CallFunctionObjArgs(s->pairs_hook, pairs, NULL);
- if (val == NULL)
- goto bail;
- Py_DECREF(pairs);
- *next_idx_ptr = idx + 1;
- return val;
- }
-
- /* if object_hook is not None: rval = object_hook(rval) */
- if (s->object_hook != Py_None) {
- val = PyObject_CallFunctionObjArgs(s->object_hook, rval, NULL);
- if (val == NULL)
- goto bail;
- Py_DECREF(rval);
- rval = val;
- val = NULL;
- }
- *next_idx_ptr = idx + 1;
- return rval;
-bail:
- Py_XDECREF(rval);
- Py_XDECREF(key);
- Py_XDECREF(val);
- Py_XDECREF(pairs);
- return NULL;
-}
-
-static PyObject *
-_parse_object_unicode(PyScannerObject *s, PyObject *pystr, Py_ssize_t idx, Py_ssize_t *next_idx_ptr) {
- /* Read a JSON object from PyUnicode pystr.
- idx is the index of the first character after the opening curly brace.
- *next_idx_ptr is a return-by-reference index to the first character after
- the closing curly brace.
-
- Returns a new PyObject (usually a dict, but object_hook can change that)
- */
- Py_UNICODE *str = PyUnicode_AS_UNICODE(pystr);
- Py_ssize_t end_idx = PyUnicode_GET_SIZE(pystr) - 1;
- PyObject *rval = NULL;
- PyObject *pairs = NULL;
- PyObject *item;
- PyObject *key = NULL;
- PyObject *val = NULL;
- int strict = PyObject_IsTrue(s->strict);
- int has_pairs_hook = (s->pairs_hook != Py_None);
- Py_ssize_t next_idx;
-
- if (has_pairs_hook) {
- pairs = PyList_New(0);
- if (pairs == NULL)
- return NULL;
- }
- else {
- rval = PyDict_New();
- if (rval == NULL)
- return NULL;
- }
-
- /* skip whitespace after { */
- while (idx <= end_idx && IS_WHITESPACE(str[idx])) idx++;
-
- /* only loop if the object is non-empty */
- if (idx <= end_idx && str[idx] != '}') {
- while (idx <= end_idx) {
- PyObject *memokey;
-
- /* read key */
- if (str[idx] != '"') {
- raise_errmsg("Expecting property name", pystr, idx);
- goto bail;
- }
- key = scanstring_unicode(pystr, idx + 1, strict, &next_idx);
- if (key == NULL)
- goto bail;
- memokey = PyDict_GetItem(s->memo, key);
- if (memokey != NULL) {
- Py_INCREF(memokey);
- Py_DECREF(key);
- key = memokey;
- }
- else {
- if (PyDict_SetItem(s->memo, key, key) < 0)
- goto bail;
- }
- idx = next_idx;
-
- /* skip whitespace between key and : delimiter, read :, skip whitespace */
- while (idx <= end_idx && IS_WHITESPACE(str[idx])) idx++;
- if (idx > end_idx || str[idx] != ':') {
- raise_errmsg("Expecting : delimiter", pystr, idx);
- goto bail;
- }
- idx++;
- while (idx <= end_idx && IS_WHITESPACE(str[idx])) idx++;
-
- /* read any JSON term */
- val = scan_once_unicode(s, pystr, idx, &next_idx);
- if (val == NULL)
- goto bail;
-
- if (has_pairs_hook) {
- item = PyTuple_Pack(2, key, val);
- if (item == NULL)
- goto bail;
- Py_CLEAR(key);
- Py_CLEAR(val);
- if (PyList_Append(pairs, item) == -1) {
- Py_DECREF(item);
- goto bail;
- }
- Py_DECREF(item);
- }
- else {
- if (PyDict_SetItem(rval, key, val) < 0)
- goto bail;
- Py_CLEAR(key);
- Py_CLEAR(val);
- }
- idx = next_idx;
-
- /* skip whitespace before } or , */
- while (idx <= end_idx && IS_WHITESPACE(str[idx])) idx++;
-
- /* bail if the object is closed or we didn't get the , delimiter */
- if (idx > end_idx) break;
- if (str[idx] == '}') {
- break;
- }
- else if (str[idx] != ',') {
- raise_errmsg("Expecting , delimiter", pystr, idx);
- goto bail;
- }
- idx++;
-
- /* skip whitespace after , delimiter */
- while (idx <= end_idx && IS_WHITESPACE(str[idx])) idx++;
- }
- }
-
- /* verify that idx < end_idx, str[idx] should be '}' */
- if (idx > end_idx || str[idx] != '}') {
- raise_errmsg("Expecting object", pystr, end_idx);
- goto bail;
- }
-
- /* if pairs_hook is not None: rval = object_pairs_hook(pairs) */
- if (s->pairs_hook != Py_None) {
- val = PyObject_CallFunctionObjArgs(s->pairs_hook, pairs, NULL);
- if (val == NULL)
- goto bail;
- Py_DECREF(pairs);
- *next_idx_ptr = idx + 1;
- return val;
- }
-
- /* if object_hook is not None: rval = object_hook(rval) */
- if (s->object_hook != Py_None) {
- val = PyObject_CallFunctionObjArgs(s->object_hook, rval, NULL);
- if (val == NULL)
- goto bail;
- Py_DECREF(rval);
- rval = val;
- val = NULL;
- }
- *next_idx_ptr = idx + 1;
- return rval;
-bail:
- Py_XDECREF(rval);
- Py_XDECREF(key);
- Py_XDECREF(val);
- Py_XDECREF(pairs);
- return NULL;
-}
-
-static PyObject *
-_parse_array_str(PyScannerObject *s, PyObject *pystr, Py_ssize_t idx, Py_ssize_t *next_idx_ptr) {
- /* Read a JSON array from PyString pystr.
- idx is the index of the first character after the opening brace.
- *next_idx_ptr is a return-by-reference index to the first character after
- the closing brace.
-
- Returns a new PyList
- */
- char *str = PyString_AS_STRING(pystr);
- Py_ssize_t end_idx = PyString_GET_SIZE(pystr) - 1;
- PyObject *val = NULL;
- PyObject *rval = PyList_New(0);
- Py_ssize_t next_idx;
- if (rval == NULL)
- return NULL;
-
- /* skip whitespace after [ */
- while (idx <= end_idx && IS_WHITESPACE(str[idx])) idx++;
-
- /* only loop if the array is non-empty */
- if (idx <= end_idx && str[idx] != ']') {
- while (idx <= end_idx) {
-
- /* read any JSON term and de-tuplefy the (rval, idx) */
- val = scan_once_str(s, pystr, idx, &next_idx);
- if (val == NULL) {
- if (PyErr_ExceptionMatches(PyExc_StopIteration)) {
- PyErr_Clear();
- raise_errmsg("Expecting object", pystr, idx);
- }
- goto bail;
- }
-
- if (PyList_Append(rval, val) == -1)
- goto bail;
-
- Py_CLEAR(val);
- idx = next_idx;
-
- /* skip whitespace between term and , */
- while (idx <= end_idx && IS_WHITESPACE(str[idx])) idx++;
-
- /* bail if the array is closed or we didn't get the , delimiter */
- if (idx > end_idx) break;
- if (str[idx] == ']') {
- break;
- }
- else if (str[idx] != ',') {
- raise_errmsg("Expecting , delimiter", pystr, idx);
- goto bail;
- }
- idx++;
-
- /* skip whitespace after , */
- while (idx <= end_idx && IS_WHITESPACE(str[idx])) idx++;
- }
- }
-
- /* verify that idx < end_idx, str[idx] should be ']' */
- if (idx > end_idx || str[idx] != ']') {
- raise_errmsg("Expecting object", pystr, end_idx);
- goto bail;
- }
- *next_idx_ptr = idx + 1;
- return rval;
-bail:
- Py_XDECREF(val);
- Py_DECREF(rval);
- return NULL;
-}
-
-static PyObject *
-_parse_array_unicode(PyScannerObject *s, PyObject *pystr, Py_ssize_t idx, Py_ssize_t *next_idx_ptr) {
- /* Read a JSON array from PyString pystr.
- idx is the index of the first character after the opening brace.
- *next_idx_ptr is a return-by-reference index to the first character after
- the closing brace.
-
- Returns a new PyList
- */
- Py_UNICODE *str = PyUnicode_AS_UNICODE(pystr);
- Py_ssize_t end_idx = PyUnicode_GET_SIZE(pystr) - 1;
- PyObject *val = NULL;
- PyObject *rval = PyList_New(0);
- Py_ssize_t next_idx;
- if (rval == NULL)
- return NULL;
-
- /* skip whitespace after [ */
- while (idx <= end_idx && IS_WHITESPACE(str[idx])) idx++;
-
- /* only loop if the array is non-empty */
- if (idx <= end_idx && str[idx] != ']') {
- while (idx <= end_idx) {
-
- /* read any JSON term */
- val = scan_once_unicode(s, pystr, idx, &next_idx);
- if (val == NULL) {
- if (PyErr_ExceptionMatches(PyExc_StopIteration)) {
- PyErr_Clear();
- raise_errmsg("Expecting object", pystr, idx);
- }
- goto bail;
- }
-
- if (PyList_Append(rval, val) == -1)
- goto bail;
-
- Py_CLEAR(val);
- idx = next_idx;
-
- /* skip whitespace between term and , */
- while (idx <= end_idx && IS_WHITESPACE(str[idx])) idx++;
-
- /* bail if the array is closed or we didn't get the , delimiter */
- if (idx > end_idx) break;
- if (str[idx] == ']') {
- break;
- }
- else if (str[idx] != ',') {
- raise_errmsg("Expecting , delimiter", pystr, idx);
- goto bail;
- }
- idx++;
-
- /* skip whitespace after , */
- while (idx <= end_idx && IS_WHITESPACE(str[idx])) idx++;
- }
- }
-
- /* verify that idx < end_idx, str[idx] should be ']' */
- if (idx > end_idx || str[idx] != ']') {
- raise_errmsg("Expecting object", pystr, end_idx);
- goto bail;
- }
- *next_idx_ptr = idx + 1;
- return rval;
-bail:
- Py_XDECREF(val);
- Py_DECREF(rval);
- return NULL;
-}
-
-static PyObject *
-_parse_constant(PyScannerObject *s, char *constant, Py_ssize_t idx, Py_ssize_t *next_idx_ptr) {
- /* Read a JSON constant from PyString pystr.
- constant is the constant string that was found
- ("NaN", "Infinity", "-Infinity").
- idx is the index of the first character of the constant
- *next_idx_ptr is a return-by-reference index to the first character after
- the constant.
-
- Returns the result of parse_constant
- */
- PyObject *cstr;
- PyObject *rval;
- /* constant is "NaN", "Infinity", or "-Infinity" */
- cstr = PyString_InternFromString(constant);
- if (cstr == NULL)
- return NULL;
-
- /* rval = parse_constant(constant) */
- rval = PyObject_CallFunctionObjArgs(s->parse_constant, cstr, NULL);
- idx += PyString_GET_SIZE(cstr);
- Py_DECREF(cstr);
- *next_idx_ptr = idx;
- return rval;
-}
-
-static PyObject *
-_match_number_str(PyScannerObject *s, PyObject *pystr, Py_ssize_t start, Py_ssize_t *next_idx_ptr) {
- /* Read a JSON number from PyString pystr.
- idx is the index of the first character of the number
- *next_idx_ptr is a return-by-reference index to the first character after
- the number.
-
- Returns a new PyObject representation of that number:
- PyInt, PyLong, or PyFloat.
- May return other types if parse_int or parse_float are set
- */
- char *str = PyString_AS_STRING(pystr);
- Py_ssize_t end_idx = PyString_GET_SIZE(pystr) - 1;
- Py_ssize_t idx = start;
- int is_float = 0;
- PyObject *rval;
- PyObject *numstr;
-
- /* read a sign if it's there, make sure it's not the end of the string */
- if (str[idx] == '-') {
- idx++;
- if (idx > end_idx) {
- PyErr_SetNone(PyExc_StopIteration);
- return NULL;
- }
- }
-
- /* read as many integer digits as we find as long as it doesn't start with 0 */
- if (str[idx] >= '1' && str[idx] <= '9') {
- idx++;
- while (idx <= end_idx && str[idx] >= '0' && str[idx] <= '9') idx++;
- }
- /* if it starts with 0 we only expect one integer digit */
- else if (str[idx] == '0') {
- idx++;
- }
- /* no integer digits, error */
- else {
- PyErr_SetNone(PyExc_StopIteration);
- return NULL;
- }
-
- /* if the next char is '.' followed by a digit then read all float digits */
- if (idx < end_idx && str[idx] == '.' && str[idx + 1] >= '0' && str[idx + 1] <= '9') {
- is_float = 1;
- idx += 2;
- while (idx <= end_idx && str[idx] >= '0' && str[idx] <= '9') idx++;
- }
-
- /* if the next char is 'e' or 'E' then maybe read the exponent (or backtrack) */
- if (idx < end_idx && (str[idx] == 'e' || str[idx] == 'E')) {
-
- /* save the index of the 'e' or 'E' just in case we need to backtrack */
- Py_ssize_t e_start = idx;
- idx++;
-
- /* read an exponent sign if present */
- if (idx < end_idx && (str[idx] == '-' || str[idx] == '+')) idx++;
-
- /* read all digits */
- while (idx <= end_idx && str[idx] >= '0' && str[idx] <= '9') idx++;
-
- /* if we got a digit, then parse as float. if not, backtrack */
- if (str[idx - 1] >= '0' && str[idx - 1] <= '9') {
- is_float = 1;
- }
- else {
- idx = e_start;
- }
- }
-
- /* copy the section we determined to be a number */
- numstr = PyString_FromStringAndSize(&str[start], idx - start);
- if (numstr == NULL)
- return NULL;
- if (is_float) {
- /* parse as a float using a fast path if available, otherwise call user defined method */
- if (s->parse_float != (PyObject *)&PyFloat_Type) {
- rval = PyObject_CallFunctionObjArgs(s->parse_float, numstr, NULL);
- }
- else {
- /* rval = PyFloat_FromDouble(PyOS_ascii_atof(PyString_AS_STRING(numstr))); */
- double d = PyOS_string_to_double(PyString_AS_STRING(numstr),
- NULL, NULL);
- if (d == -1.0 && PyErr_Occurred())
- return NULL;
- rval = PyFloat_FromDouble(d);
- }
- }
- else {
- /* parse as an int using a fast path if available, otherwise call user defined method */
- if (s->parse_int != (PyObject *)&PyInt_Type) {
- rval = PyObject_CallFunctionObjArgs(s->parse_int, numstr, NULL);
- }
- else {
- rval = PyInt_FromString(PyString_AS_STRING(numstr), NULL, 10);
- }
- }
- Py_DECREF(numstr);
- *next_idx_ptr = idx;
- return rval;
-}
-
-static PyObject *
-_match_number_unicode(PyScannerObject *s, PyObject *pystr, Py_ssize_t start, Py_ssize_t *next_idx_ptr) {
- /* Read a JSON number from PyUnicode pystr.
- idx is the index of the first character of the number
- *next_idx_ptr is a return-by-reference index to the first character after
- the number.
-
- Returns a new PyObject representation of that number:
- PyInt, PyLong, or PyFloat.
- May return other types if parse_int or parse_float are set
- */
- Py_UNICODE *str = PyUnicode_AS_UNICODE(pystr);
- Py_ssize_t end_idx = PyUnicode_GET_SIZE(pystr) - 1;
- Py_ssize_t idx = start;
- int is_float = 0;
- PyObject *rval;
- PyObject *numstr;
-
- /* read a sign if it's there, make sure it's not the end of the string */
- if (str[idx] == '-') {
- idx++;
- if (idx > end_idx) {
- PyErr_SetNone(PyExc_StopIteration);
- return NULL;
- }
- }
-
- /* read as many integer digits as we find as long as it doesn't start with 0 */
- if (str[idx] >= '1' && str[idx] <= '9') {
- idx++;
- while (idx <= end_idx && str[idx] >= '0' && str[idx] <= '9') idx++;
- }
- /* if it starts with 0 we only expect one integer digit */
- else if (str[idx] == '0') {
- idx++;
- }
- /* no integer digits, error */
- else {
- PyErr_SetNone(PyExc_StopIteration);
- return NULL;
- }
-
- /* if the next char is '.' followed by a digit then read all float digits */
- if (idx < end_idx && str[idx] == '.' && str[idx + 1] >= '0' && str[idx + 1] <= '9') {
- is_float = 1;
- idx += 2;
- while (idx <= end_idx && str[idx] >= '0' && str[idx] <= '9') idx++;
- }
-
- /* if the next char is 'e' or 'E' then maybe read the exponent (or backtrack) */
- if (idx < end_idx && (str[idx] == 'e' || str[idx] == 'E')) {
- Py_ssize_t e_start = idx;
- idx++;
-
- /* read an exponent sign if present */
- if (idx < end_idx && (str[idx] == '-' || str[idx] == '+')) idx++;
-
- /* read all digits */
- while (idx <= end_idx && str[idx] >= '0' && str[idx] <= '9') idx++;
-
- /* if we got a digit, then parse as float. if not, backtrack */
- if (str[idx - 1] >= '0' && str[idx - 1] <= '9') {
- is_float = 1;
- }
- else {
- idx = e_start;
- }
- }
-
- /* copy the section we determined to be a number */
- numstr = PyUnicode_FromUnicode(&str[start], idx - start);
- if (numstr == NULL)
- return NULL;
- if (is_float) {
- /* parse as a float using a fast path if available, otherwise call user defined method */
- if (s->parse_float != (PyObject *)&PyFloat_Type) {
- rval = PyObject_CallFunctionObjArgs(s->parse_float, numstr, NULL);
- }
- else {
- rval = PyFloat_FromString(numstr, NULL);
- }
- }
- else {
- /* no fast path for unicode -> int, just call */
- rval = PyObject_CallFunctionObjArgs(s->parse_int, numstr, NULL);
- }
- Py_DECREF(numstr);
- *next_idx_ptr = idx;
- return rval;
-}
-
-static PyObject *
-scan_once_str(PyScannerObject *s, PyObject *pystr, Py_ssize_t idx, Py_ssize_t *next_idx_ptr)
-{
- /* Read one JSON term (of any kind) from PyString pystr.
- idx is the index of the first character of the term
- *next_idx_ptr is a return-by-reference index to the first character after
- the number.
-
- Returns a new PyObject representation of the term.
- */
- char *str = PyString_AS_STRING(pystr);
- Py_ssize_t length = PyString_GET_SIZE(pystr);
- if (idx >= length) {
- PyErr_SetNone(PyExc_StopIteration);
- return NULL;
- }
- switch (str[idx]) {
- case '"':
- /* string */
- return scanstring_str(pystr, idx + 1,
- PyString_AS_STRING(s->encoding),
- PyObject_IsTrue(s->strict),
- next_idx_ptr);
- case '{':
- /* object */
- return _parse_object_str(s, pystr, idx + 1, next_idx_ptr);
- case '[':
- /* array */
- return _parse_array_str(s, pystr, idx + 1, next_idx_ptr);
- case 'n':
- /* null */
- if ((idx + 3 < length) && str[idx + 1] == 'u' && str[idx + 2] == 'l' && str[idx + 3] == 'l') {
- Py_INCREF(Py_None);
- *next_idx_ptr = idx + 4;
- return Py_None;
- }
- break;
- case 't':
- /* true */
- if ((idx + 3 < length) && str[idx + 1] == 'r' && str[idx + 2] == 'u' && str[idx + 3] == 'e') {
- Py_INCREF(Py_True);
- *next_idx_ptr = idx + 4;
- return Py_True;
- }
- break;
- case 'f':
- /* false */
- if ((idx + 4 < length) && str[idx + 1] == 'a' && str[idx + 2] == 'l' && str[idx + 3] == 's' && str[idx + 4] == 'e') {
- Py_INCREF(Py_False);
- *next_idx_ptr = idx + 5;
- return Py_False;
- }
- break;
- case 'N':
- /* NaN */
- if ((idx + 2 < length) && str[idx + 1] == 'a' && str[idx + 2] == 'N') {
- return _parse_constant(s, "NaN", idx, next_idx_ptr);
- }
- break;
- case 'I':
- /* Infinity */
- if ((idx + 7 < length) && str[idx + 1] == 'n' && str[idx + 2] == 'f' && str[idx + 3] == 'i' && str[idx + 4] == 'n' && str[idx + 5] == 'i' && str[idx + 6] == 't' && str[idx + 7] == 'y') {
- return _parse_constant(s, "Infinity", idx, next_idx_ptr);
- }
- break;
- case '-':
- /* -Infinity */
- if ((idx + 8 < length) && str[idx + 1] == 'I' && str[idx + 2] == 'n' && str[idx + 3] == 'f' && str[idx + 4] == 'i' && str[idx + 5] == 'n' && str[idx + 6] == 'i' && str[idx + 7] == 't' && str[idx + 8] == 'y') {
- return _parse_constant(s, "-Infinity", idx, next_idx_ptr);
- }
- break;
- }
- /* Didn't find a string, object, array, or named constant. Look for a number. */
- return _match_number_str(s, pystr, idx, next_idx_ptr);
-}
-
-static PyObject *
-scan_once_unicode(PyScannerObject *s, PyObject *pystr, Py_ssize_t idx, Py_ssize_t *next_idx_ptr)
-{
- /* Read one JSON term (of any kind) from PyUnicode pystr.
- idx is the index of the first character of the term
- *next_idx_ptr is a return-by-reference index to the first character after
- the number.
-
- Returns a new PyObject representation of the term.
- */
- Py_UNICODE *str = PyUnicode_AS_UNICODE(pystr);
- Py_ssize_t length = PyUnicode_GET_SIZE(pystr);
- if (idx >= length) {
- PyErr_SetNone(PyExc_StopIteration);
- return NULL;
- }
- switch (str[idx]) {
- case '"':
- /* string */
- return scanstring_unicode(pystr, idx + 1,
- PyObject_IsTrue(s->strict),
- next_idx_ptr);
- case '{':
- /* object */
- return _parse_object_unicode(s, pystr, idx + 1, next_idx_ptr);
- case '[':
- /* array */
- return _parse_array_unicode(s, pystr, idx + 1, next_idx_ptr);
- case 'n':
- /* null */
- if ((idx + 3 < length) && str[idx + 1] == 'u' && str[idx + 2] == 'l' && str[idx + 3] == 'l') {
- Py_INCREF(Py_None);
- *next_idx_ptr = idx + 4;
- return Py_None;
- }
- break;
- case 't':
- /* true */
- if ((idx + 3 < length) && str[idx + 1] == 'r' && str[idx + 2] == 'u' && str[idx + 3] == 'e') {
- Py_INCREF(Py_True);
- *next_idx_ptr = idx + 4;
- return Py_True;
- }
- break;
- case 'f':
- /* false */
- if ((idx + 4 < length) && str[idx + 1] == 'a' && str[idx + 2] == 'l' && str[idx + 3] == 's' && str[idx + 4] == 'e') {
- Py_INCREF(Py_False);
- *next_idx_ptr = idx + 5;
- return Py_False;
- }
- break;
- case 'N':
- /* NaN */
- if ((idx + 2 < length) && str[idx + 1] == 'a' && str[idx + 2] == 'N') {
- return _parse_constant(s, "NaN", idx, next_idx_ptr);
- }
- break;
- case 'I':
- /* Infinity */
- if ((idx + 7 < length) && str[idx + 1] == 'n' && str[idx + 2] == 'f' && str[idx + 3] == 'i' && str[idx + 4] == 'n' && str[idx + 5] == 'i' && str[idx + 6] == 't' && str[idx + 7] == 'y') {
- return _parse_constant(s, "Infinity", idx, next_idx_ptr);
- }
- break;
- case '-':
- /* -Infinity */
- if ((idx + 8 < length) && str[idx + 1] == 'I' && str[idx + 2] == 'n' && str[idx + 3] == 'f' && str[idx + 4] == 'i' && str[idx + 5] == 'n' && str[idx + 6] == 'i' && str[idx + 7] == 't' && str[idx + 8] == 'y') {
- return _parse_constant(s, "-Infinity", idx, next_idx_ptr);
- }
- break;
- }
- /* Didn't find a string, object, array, or named constant. Look for a number. */
- return _match_number_unicode(s, pystr, idx, next_idx_ptr);
-}
-
-static PyObject *
-scanner_call(PyObject *self, PyObject *args, PyObject *kwds)
-{
- /* Python callable interface to scan_once_{str,unicode} */
- PyObject *pystr;
- PyObject *rval;
- Py_ssize_t idx;
- Py_ssize_t next_idx = -1;
- static char *kwlist[] = {"string", "idx", NULL};
- PyScannerObject *s;
- assert(PyScanner_Check(self));
- s = (PyScannerObject *)self;
- if (!PyArg_ParseTupleAndKeywords(args, kwds, "OO&:scan_once", kwlist, &pystr, _convertPyInt_AsSsize_t, &idx))
- return NULL;
-
- if (PyString_Check(pystr)) {
- rval = scan_once_str(s, pystr, idx, &next_idx);
- }
- else if (PyUnicode_Check(pystr)) {
- rval = scan_once_unicode(s, pystr, idx, &next_idx);
- }
- else {
- PyErr_Format(PyExc_TypeError,
- "first argument must be a string, not %.80s",
- Py_TYPE(pystr)->tp_name);
- return NULL;
- }
- PyDict_Clear(s->memo);
- return _build_rval_index_tuple(rval, next_idx);
-}
-
-static PyObject *
-scanner_new(PyTypeObject *type, PyObject *args, PyObject *kwds)
-{
- PyScannerObject *s;
- s = (PyScannerObject *)type->tp_alloc(type, 0);
- if (s != NULL) {
- s->encoding = NULL;
- s->strict = NULL;
- s->object_hook = NULL;
- s->pairs_hook = NULL;
- s->parse_float = NULL;
- s->parse_int = NULL;
- s->parse_constant = NULL;
- }
- return (PyObject *)s;
-}
-
-static int
-scanner_init(PyObject *self, PyObject *args, PyObject *kwds)
-{
- /* Initialize Scanner object */
- PyObject *ctx;
- static char *kwlist[] = {"context", NULL};
- PyScannerObject *s;
-
- assert(PyScanner_Check(self));
- s = (PyScannerObject *)self;
-
- if (!PyArg_ParseTupleAndKeywords(args, kwds, "O:make_scanner", kwlist, &ctx))
- return -1;
-
- if (s->memo == NULL) {
- s->memo = PyDict_New();
- if (s->memo == NULL)
- goto bail;
- }
-
- /* PyString_AS_STRING is used on encoding */
- s->encoding = PyObject_GetAttrString(ctx, "encoding");
- if (s->encoding == NULL)
- goto bail;
- if (s->encoding == Py_None) {
- Py_DECREF(Py_None);
- s->encoding = PyString_InternFromString(DEFAULT_ENCODING);
- }
- else if (PyUnicode_Check(s->encoding)) {
- PyObject *tmp = PyUnicode_AsEncodedString(s->encoding, NULL, NULL);
- Py_DECREF(s->encoding);
- s->encoding = tmp;
- }
- if (s->encoding == NULL || !PyString_Check(s->encoding))
- goto bail;
-
- /* All of these will fail "gracefully" so we don't need to verify them */
- s->strict = PyObject_GetAttrString(ctx, "strict");
- if (s->strict == NULL)
- goto bail;
- s->object_hook = PyObject_GetAttrString(ctx, "object_hook");
- if (s->object_hook == NULL)
- goto bail;
- s->pairs_hook = PyObject_GetAttrString(ctx, "object_pairs_hook");
- if (s->pairs_hook == NULL)
- goto bail;
- s->parse_float = PyObject_GetAttrString(ctx, "parse_float");
- if (s->parse_float == NULL)
- goto bail;
- s->parse_int = PyObject_GetAttrString(ctx, "parse_int");
- if (s->parse_int == NULL)
- goto bail;
- s->parse_constant = PyObject_GetAttrString(ctx, "parse_constant");
- if (s->parse_constant == NULL)
- goto bail;
-
- return 0;
-
-bail:
- Py_CLEAR(s->encoding);
- Py_CLEAR(s->strict);
- Py_CLEAR(s->object_hook);
- Py_CLEAR(s->pairs_hook);
- Py_CLEAR(s->parse_float);
- Py_CLEAR(s->parse_int);
- Py_CLEAR(s->parse_constant);
- return -1;
-}
-
-PyDoc_STRVAR(scanner_doc, "JSON scanner object");
-
-static
-PyTypeObject PyScannerType = {
- PyObject_HEAD_INIT(NULL)
- 0, /* tp_internal */
- "simplejson._speedups.Scanner", /* tp_name */
- sizeof(PyScannerObject), /* tp_basicsize */
- 0, /* tp_itemsize */
- scanner_dealloc, /* tp_dealloc */
- 0, /* tp_print */
- 0, /* tp_getattr */
- 0, /* tp_setattr */
- 0, /* tp_compare */
- 0, /* tp_repr */
- 0, /* tp_as_number */
- 0, /* tp_as_sequence */
- 0, /* tp_as_mapping */
- 0, /* tp_hash */
- scanner_call, /* tp_call */
- 0, /* tp_str */
- 0,/* PyObject_GenericGetAttr, */ /* tp_getattro */
- 0,/* PyObject_GenericSetAttr, */ /* tp_setattro */
- 0, /* tp_as_buffer */
- Py_TPFLAGS_DEFAULT | Py_TPFLAGS_HAVE_GC, /* tp_flags */
- scanner_doc, /* tp_doc */
- scanner_traverse, /* tp_traverse */
- scanner_clear, /* tp_clear */
- 0, /* tp_richcompare */
- 0, /* tp_weaklistoffset */
- 0, /* tp_iter */
- 0, /* tp_iternext */
- 0, /* tp_methods */
- scanner_members, /* tp_members */
- 0, /* tp_getset */
- 0, /* tp_base */
- 0, /* tp_dict */
- 0, /* tp_descr_get */
- 0, /* tp_descr_set */
- 0, /* tp_dictoffset */
- scanner_init, /* tp_init */
- 0,/* PyType_GenericAlloc, */ /* tp_alloc */
- scanner_new, /* tp_new */
- 0,/* PyObject_GC_Del, */ /* tp_free */
-};
-
-static PyObject *
-encoder_new(PyTypeObject *type, PyObject *args, PyObject *kwds)
-{
- PyEncoderObject *s;
- s = (PyEncoderObject *)type->tp_alloc(type, 0);
- if (s != NULL) {
- s->markers = NULL;
- s->defaultfn = NULL;
- s->encoder = NULL;
- s->indent = NULL;
- s->key_separator = NULL;
- s->item_separator = NULL;
- s->sort_keys = NULL;
- s->skipkeys = NULL;
- s->key_memo = NULL;
- }
- return (PyObject *)s;
-}
-
-static int
-encoder_init(PyObject *self, PyObject *args, PyObject *kwds)
-{
- /* initialize Encoder object */
- static char *kwlist[] = {"markers", "default", "encoder", "indent", "key_separator", "item_separator", "sort_keys", "skipkeys", "allow_nan", "key_memo", "use_decimal", NULL};
-
- PyEncoderObject *s;
- PyObject *markers, *defaultfn, *encoder, *indent, *key_separator;
- PyObject *item_separator, *sort_keys, *skipkeys, *allow_nan, *key_memo, *use_decimal;
-
- assert(PyEncoder_Check(self));
- s = (PyEncoderObject *)self;
-
- if (!PyArg_ParseTupleAndKeywords(args, kwds, "OOOOOOOOOOO:make_encoder", kwlist,
- &markers, &defaultfn, &encoder, &indent, &key_separator, &item_separator,
- &sort_keys, &skipkeys, &allow_nan, &key_memo, &use_decimal))
- return -1;
-
- s->markers = markers;
- s->defaultfn = defaultfn;
- s->encoder = encoder;
- s->indent = indent;
- s->key_separator = key_separator;
- s->item_separator = item_separator;
- s->sort_keys = sort_keys;
- s->skipkeys = skipkeys;
- s->key_memo = key_memo;
- s->fast_encode = (PyCFunction_Check(s->encoder) && PyCFunction_GetFunction(s->encoder) == (PyCFunction)py_encode_basestring_ascii);
- s->allow_nan = PyObject_IsTrue(allow_nan);
- s->use_decimal = PyObject_IsTrue(use_decimal);
-
- Py_INCREF(s->markers);
- Py_INCREF(s->defaultfn);
- Py_INCREF(s->encoder);
- Py_INCREF(s->indent);
- Py_INCREF(s->key_separator);
- Py_INCREF(s->item_separator);
- Py_INCREF(s->sort_keys);
- Py_INCREF(s->skipkeys);
- Py_INCREF(s->key_memo);
- return 0;
-}
-
-static PyObject *
-encoder_call(PyObject *self, PyObject *args, PyObject *kwds)
-{
- /* Python callable interface to encode_listencode_obj */
- static char *kwlist[] = {"obj", "_current_indent_level", NULL};
- PyObject *obj;
- PyObject *rval;
- Py_ssize_t indent_level;
- PyEncoderObject *s;
- assert(PyEncoder_Check(self));
- s = (PyEncoderObject *)self;
- if (!PyArg_ParseTupleAndKeywords(args, kwds, "OO&:_iterencode", kwlist,
- &obj, _convertPyInt_AsSsize_t, &indent_level))
- return NULL;
- rval = PyList_New(0);
- if (rval == NULL)
- return NULL;
- if (encoder_listencode_obj(s, rval, obj, indent_level)) {
- Py_DECREF(rval);
- return NULL;
- }
- return rval;
-}
-
-static PyObject *
-_encoded_const(PyObject *obj)
-{
- /* Return the JSON string representation of None, True, False */
- if (obj == Py_None) {
- static PyObject *s_null = NULL;
- if (s_null == NULL) {
- s_null = PyString_InternFromString("null");
- }
- Py_INCREF(s_null);
- return s_null;
- }
- else if (obj == Py_True) {
- static PyObject *s_true = NULL;
- if (s_true == NULL) {
- s_true = PyString_InternFromString("true");
- }
- Py_INCREF(s_true);
- return s_true;
- }
- else if (obj == Py_False) {
- static PyObject *s_false = NULL;
- if (s_false == NULL) {
- s_false = PyString_InternFromString("false");
- }
- Py_INCREF(s_false);
- return s_false;
- }
- else {
- PyErr_SetString(PyExc_ValueError, "not a const");
- return NULL;
- }
-}
-
-static PyObject *
-encoder_encode_float(PyEncoderObject *s, PyObject *obj)
-{
- /* Return the JSON representation of a PyFloat */
- double i = PyFloat_AS_DOUBLE(obj);
- if (!Py_IS_FINITE(i)) {
- if (!s->allow_nan) {
- PyErr_SetString(PyExc_ValueError, "Out of range float values are not JSON compliant");
- return NULL;
- }
- if (i > 0) {
- return PyString_FromString("Infinity");
- }
- else if (i < 0) {
- return PyString_FromString("-Infinity");
- }
- else {
- return PyString_FromString("NaN");
- }
- }
- /* Use a better float format here? */
- return PyObject_Repr(obj);
-}
-
-static PyObject *
-encoder_encode_string(PyEncoderObject *s, PyObject *obj)
-{
- /* Return the JSON representation of a string */
- if (s->fast_encode)
- return py_encode_basestring_ascii(NULL, obj);
- else
- return PyObject_CallFunctionObjArgs(s->encoder, obj, NULL);
-}
-
-static int
-_steal_list_append(PyObject *lst, PyObject *stolen)
-{
- /* Append stolen and then decrement its reference count */
- int rval = PyList_Append(lst, stolen);
- Py_DECREF(stolen);
- return rval;
-}
-
-static int
-encoder_listencode_obj(PyEncoderObject *s, PyObject *rval, PyObject *obj, Py_ssize_t indent_level)
-{
- /* Encode Python object obj to a JSON term, rval is a PyList */
- PyObject *newobj;
- int rv;
-
- if (obj == Py_None || obj == Py_True || obj == Py_False) {
- PyObject *cstr = _encoded_const(obj);
- if (cstr == NULL)
- return -1;
- return _steal_list_append(rval, cstr);
- }
- else if (PyString_Check(obj) || PyUnicode_Check(obj))
- {
- PyObject *encoded = encoder_encode_string(s, obj);
- if (encoded == NULL)
- return -1;
- return _steal_list_append(rval, encoded);
- }
- else if (PyInt_Check(obj) || PyLong_Check(obj)) {
- PyObject *encoded = PyObject_Str(obj);
- if (encoded == NULL)
- return -1;
- return _steal_list_append(rval, encoded);
- }
- else if (PyFloat_Check(obj)) {
- PyObject *encoded = encoder_encode_float(s, obj);
- if (encoded == NULL)
- return -1;
- return _steal_list_append(rval, encoded);
- }
- else if (PyList_Check(obj) || PyTuple_Check(obj)) {
- return encoder_listencode_list(s, rval, obj, indent_level);
- }
- else if (PyDict_Check(obj)) {
- return encoder_listencode_dict(s, rval, obj, indent_level);
- }
- else if (s->use_decimal && Decimal_Check(obj)) {
- PyObject *encoded = PyObject_Str(obj);
- if (encoded == NULL)
- return -1;
- return _steal_list_append(rval, encoded);
- }
- else {
- PyObject *ident = NULL;
- if (s->markers != Py_None) {
- int has_key;
- ident = PyLong_FromVoidPtr(obj);
- if (ident == NULL)
- return -1;
- has_key = PyDict_Contains(s->markers, ident);
- if (has_key) {
- if (has_key != -1)
- PyErr_SetString(PyExc_ValueError, "Circular reference detected");
- Py_DECREF(ident);
- return -1;
- }
- if (PyDict_SetItem(s->markers, ident, obj)) {
- Py_DECREF(ident);
- return -1;
- }
- }
- newobj = PyObject_CallFunctionObjArgs(s->defaultfn, obj, NULL);
- if (newobj == NULL) {
- Py_XDECREF(ident);
- return -1;
- }
- rv = encoder_listencode_obj(s, rval, newobj, indent_level);
- Py_DECREF(newobj);
- if (rv) {
- Py_XDECREF(ident);
- return -1;
- }
- if (ident != NULL) {
- if (PyDict_DelItem(s->markers, ident)) {
- Py_XDECREF(ident);
- return -1;
- }
- Py_XDECREF(ident);
- }
- return rv;
- }
-}
-
-static int
-encoder_listencode_dict(PyEncoderObject *s, PyObject *rval, PyObject *dct, Py_ssize_t indent_level)
-{
- /* Encode Python dict dct a JSON term, rval is a PyList */
- static PyObject *open_dict = NULL;
- static PyObject *close_dict = NULL;
- static PyObject *empty_dict = NULL;
- static PyObject *iteritems = NULL;
- PyObject *kstr = NULL;
- PyObject *ident = NULL;
- PyObject *iter = NULL;
- PyObject *item = NULL;
- PyObject *items = NULL;
- PyObject *encoded = NULL;
- int skipkeys;
- Py_ssize_t idx;
-
- if (open_dict == NULL || close_dict == NULL || empty_dict == NULL || iteritems == NULL) {
- open_dict = PyString_InternFromString("{");
- close_dict = PyString_InternFromString("}");
- empty_dict = PyString_InternFromString("{}");
- iteritems = PyString_InternFromString("iteritems");
- if (open_dict == NULL || close_dict == NULL || empty_dict == NULL || iteritems == NULL)
- return -1;
- }
- if (PyDict_Size(dct) == 0)
- return PyList_Append(rval, empty_dict);
-
- if (s->markers != Py_None) {
- int has_key;
- ident = PyLong_FromVoidPtr(dct);
- if (ident == NULL)
- goto bail;
- has_key = PyDict_Contains(s->markers, ident);
- if (has_key) {
- if (has_key != -1)
- PyErr_SetString(PyExc_ValueError, "Circular reference detected");
- goto bail;
- }
- if (PyDict_SetItem(s->markers, ident, dct)) {
- goto bail;
- }
- }
-
- if (PyList_Append(rval, open_dict))
- goto bail;
-
- if (s->indent != Py_None) {
- /* TODO: DOES NOT RUN */
- indent_level += 1;
- /*
- newline_indent = '\n' + (_indent * _current_indent_level)
- separator = _item_separator + newline_indent
- buf += newline_indent
- */
- }
-
- if (PyObject_IsTrue(s->sort_keys)) {
- /* First sort the keys then replace them with (key, value) tuples. */
- Py_ssize_t i, nitems;
- if (PyDict_CheckExact(dct))
- items = PyDict_Keys(dct);
- else
- items = PyMapping_Keys(dct);
- if (items == NULL)
- goto bail;
- if (!PyList_Check(items)) {
- PyErr_SetString(PyExc_ValueError, "keys must return list");
- goto bail;
- }
- if (PyList_Sort(items) < 0)
- goto bail;
- nitems = PyList_GET_SIZE(items);
- for (i = 0; i < nitems; i++) {
- PyObject *key, *value;
- key = PyList_GET_ITEM(items, i);
- value = PyDict_GetItem(dct, key);
- item = PyTuple_Pack(2, key, value);
- if (item == NULL)
- goto bail;
- PyList_SET_ITEM(items, i, item);
- Py_DECREF(key);
- }
- }
- else {
- if (PyDict_CheckExact(dct))
- items = PyDict_Items(dct);
- else
- items = PyMapping_Items(dct);
- }
- if (items == NULL)
- goto bail;
- iter = PyObject_GetIter(items);
- Py_DECREF(items);
- if (iter == NULL)
- goto bail;
-
- skipkeys = PyObject_IsTrue(s->skipkeys);
- idx = 0;
- while ((item = PyIter_Next(iter))) {
- PyObject *encoded, *key, *value;
- if (!PyTuple_Check(item) || Py_SIZE(item) != 2) {
- PyErr_SetString(PyExc_ValueError, "items must return 2-tuples");
- goto bail;
- }
- key = PyTuple_GET_ITEM(item, 0);
- if (key == NULL)
- goto bail;
- value = PyTuple_GET_ITEM(item, 1);
- if (value == NULL)
- goto bail;
-
- encoded = PyDict_GetItem(s->key_memo, key);
- if (encoded != NULL) {
- Py_INCREF(encoded);
- }
- else if (PyString_Check(key) || PyUnicode_Check(key)) {
- Py_INCREF(key);
- kstr = key;
- }
- else if (PyFloat_Check(key)) {
- kstr = encoder_encode_float(s, key);
- if (kstr == NULL)
- goto bail;
- }
- else if (key == Py_True || key == Py_False || key == Py_None) {
- /* This must come before the PyInt_Check because
- True and False are also 1 and 0.*/
- kstr = _encoded_const(key);
- if (kstr == NULL)
- goto bail;
- }
- else if (PyInt_Check(key) || PyLong_Check(key)) {
- kstr = PyObject_Str(key);
- if (kstr == NULL)
- goto bail;
- }
- else if (skipkeys) {
- Py_DECREF(item);
- continue;
- }
- else {
- /* TODO: include repr of key */
- PyErr_SetString(PyExc_TypeError, "keys must be a string");
- goto bail;
- }
-
- if (idx) {
- if (PyList_Append(rval, s->item_separator))
- goto bail;
- }
-
- if (encoded == NULL) {
- encoded = encoder_encode_string(s, kstr);
- Py_CLEAR(kstr);
- if (encoded == NULL)
- goto bail;
- if (PyDict_SetItem(s->key_memo, key, encoded))
- goto bail;
- }
- if (PyList_Append(rval, encoded)) {
- goto bail;
- }
- Py_CLEAR(encoded);
- if (PyList_Append(rval, s->key_separator))
- goto bail;
- if (encoder_listencode_obj(s, rval, value, indent_level))
- goto bail;
- Py_CLEAR(item);
- idx += 1;
- }
- Py_CLEAR(iter);
- if (PyErr_Occurred())
- goto bail;
- if (ident != NULL) {
- if (PyDict_DelItem(s->markers, ident))
- goto bail;
- Py_CLEAR(ident);
- }
- if (s->indent != Py_None) {
- /* TODO: DOES NOT RUN */
- indent_level -= 1;
- /*
- yield '\n' + (_indent * _current_indent_level)
- */
- }
- if (PyList_Append(rval, close_dict))
- goto bail;
- return 0;
-
-bail:
- Py_XDECREF(encoded);
- Py_XDECREF(items);
- Py_XDECREF(iter);
- Py_XDECREF(kstr);
- Py_XDECREF(ident);
- return -1;
-}
-
-
-static int
-encoder_listencode_list(PyEncoderObject *s, PyObject *rval, PyObject *seq, Py_ssize_t indent_level)
-{
- /* Encode Python list seq to a JSON term, rval is a PyList */
- static PyObject *open_array = NULL;
- static PyObject *close_array = NULL;
- static PyObject *empty_array = NULL;
- PyObject *ident = NULL;
- PyObject *iter = NULL;
- PyObject *obj = NULL;
- int is_true;
- int i = 0;
-
- if (open_array == NULL || close_array == NULL || empty_array == NULL) {
- open_array = PyString_InternFromString("[");
- close_array = PyString_InternFromString("]");
- empty_array = PyString_InternFromString("[]");
- if (open_array == NULL || close_array == NULL || empty_array == NULL)
- return -1;
- }
- ident = NULL;
- is_true = PyObject_IsTrue(seq);
- if (is_true == -1)
- return -1;
- else if (is_true == 0)
- return PyList_Append(rval, empty_array);
-
- if (s->markers != Py_None) {
- int has_key;
- ident = PyLong_FromVoidPtr(seq);
- if (ident == NULL)
- goto bail;
- has_key = PyDict_Contains(s->markers, ident);
- if (has_key) {
- if (has_key != -1)
- PyErr_SetString(PyExc_ValueError, "Circular reference detected");
- goto bail;
- }
- if (PyDict_SetItem(s->markers, ident, seq)) {
- goto bail;
- }
- }
-
- iter = PyObject_GetIter(seq);
- if (iter == NULL)
- goto bail;
-
- if (PyList_Append(rval, open_array))
- goto bail;
- if (s->indent != Py_None) {
- /* TODO: DOES NOT RUN */
- indent_level += 1;
- /*
- newline_indent = '\n' + (_indent * _current_indent_level)
- separator = _item_separator + newline_indent
- buf += newline_indent
- */
- }
- while ((obj = PyIter_Next(iter))) {
- if (i) {
- if (PyList_Append(rval, s->item_separator))
- goto bail;
- }
- if (encoder_listencode_obj(s, rval, obj, indent_level))
- goto bail;
- i++;
- Py_CLEAR(obj);
- }
- Py_CLEAR(iter);
- if (PyErr_Occurred())
- goto bail;
- if (ident != NULL) {
- if (PyDict_DelItem(s->markers, ident))
- goto bail;
- Py_CLEAR(ident);
- }
- if (s->indent != Py_None) {
- /* TODO: DOES NOT RUN */
- indent_level -= 1;
- /*
- yield '\n' + (_indent * _current_indent_level)
- */
- }
- if (PyList_Append(rval, close_array))
- goto bail;
- return 0;
-
-bail:
- Py_XDECREF(obj);
- Py_XDECREF(iter);
- Py_XDECREF(ident);
- return -1;
-}
-
-static void
-encoder_dealloc(PyObject *self)
-{
- /* Deallocate Encoder */
- encoder_clear(self);
- Py_TYPE(self)->tp_free(self);
-}
-
-static int
-encoder_traverse(PyObject *self, visitproc visit, void *arg)
-{
- PyEncoderObject *s;
- assert(PyEncoder_Check(self));
- s = (PyEncoderObject *)self;
- Py_VISIT(s->markers);
- Py_VISIT(s->defaultfn);
- Py_VISIT(s->encoder);
- Py_VISIT(s->indent);
- Py_VISIT(s->key_separator);
- Py_VISIT(s->item_separator);
- Py_VISIT(s->sort_keys);
- Py_VISIT(s->skipkeys);
- Py_VISIT(s->key_memo);
- return 0;
-}
-
-static int
-encoder_clear(PyObject *self)
-{
- /* Deallocate Encoder */
- PyEncoderObject *s;
- assert(PyEncoder_Check(self));
- s = (PyEncoderObject *)self;
- Py_CLEAR(s->markers);
- Py_CLEAR(s->defaultfn);
- Py_CLEAR(s->encoder);
- Py_CLEAR(s->indent);
- Py_CLEAR(s->key_separator);
- Py_CLEAR(s->item_separator);
- Py_CLEAR(s->sort_keys);
- Py_CLEAR(s->skipkeys);
- Py_CLEAR(s->key_memo);
- return 0;
-}
-
-PyDoc_STRVAR(encoder_doc, "_iterencode(obj, _current_indent_level) -> iterable");
-
-static
-PyTypeObject PyEncoderType = {
- PyObject_HEAD_INIT(NULL)
- 0, /* tp_internal */
- "simplejson._speedups.Encoder", /* tp_name */
- sizeof(PyEncoderObject), /* tp_basicsize */
- 0, /* tp_itemsize */
- encoder_dealloc, /* tp_dealloc */
- 0, /* tp_print */
- 0, /* tp_getattr */
- 0, /* tp_setattr */
- 0, /* tp_compare */
- 0, /* tp_repr */
- 0, /* tp_as_number */
- 0, /* tp_as_sequence */
- 0, /* tp_as_mapping */
- 0, /* tp_hash */
- encoder_call, /* tp_call */
- 0, /* tp_str */
- 0, /* tp_getattro */
- 0, /* tp_setattro */
- 0, /* tp_as_buffer */
- Py_TPFLAGS_DEFAULT | Py_TPFLAGS_HAVE_GC, /* tp_flags */
- encoder_doc, /* tp_doc */
- encoder_traverse, /* tp_traverse */
- encoder_clear, /* tp_clear */
- 0, /* tp_richcompare */
- 0, /* tp_weaklistoffset */
- 0, /* tp_iter */
- 0, /* tp_iternext */
- 0, /* tp_methods */
- encoder_members, /* tp_members */
- 0, /* tp_getset */
- 0, /* tp_base */
- 0, /* tp_dict */
- 0, /* tp_descr_get */
- 0, /* tp_descr_set */
- 0, /* tp_dictoffset */
- encoder_init, /* tp_init */
- 0, /* tp_alloc */
- encoder_new, /* tp_new */
- 0, /* tp_free */
-};
-
-static PyMethodDef speedups_methods[] = {
- {"encode_basestring_ascii",
- (PyCFunction)py_encode_basestring_ascii,
- METH_O,
- pydoc_encode_basestring_ascii},
- {"scanstring",
- (PyCFunction)py_scanstring,
- METH_VARARGS,
- pydoc_scanstring},
- {NULL, NULL, 0, NULL}
-};
-
-PyDoc_STRVAR(module_doc,
-"simplejson speedups\n");
-
-void
-init_speedups(void)
-{
- PyObject *m, *decimal;
- PyScannerType.tp_new = PyType_GenericNew;
- if (PyType_Ready(&PyScannerType) < 0)
- return;
- PyEncoderType.tp_new = PyType_GenericNew;
- if (PyType_Ready(&PyEncoderType) < 0)
- return;
-
- decimal = PyImport_ImportModule("decimal");
- if (decimal == NULL)
- return;
- DecimalTypePtr = (PyTypeObject*)PyObject_GetAttrString(decimal, "Decimal");
- Py_DECREF(decimal);
- if (DecimalTypePtr == NULL)
- return;
-
- m = Py_InitModule3("_speedups", speedups_methods, module_doc);
- Py_INCREF((PyObject*)&PyScannerType);
- PyModule_AddObject(m, "make_scanner", (PyObject*)&PyScannerType);
- Py_INCREF((PyObject*)&PyEncoderType);
- PyModule_AddObject(m, "make_encoder", (PyObject*)&PyEncoderType);
-}
diff --git a/simplejson/decoder.py b/simplejson/decoder.py
deleted file mode 100644
index e5496d6e7f1e282a1837984898aa8a256651e83c..0000000000000000000000000000000000000000
--- a/simplejson/decoder.py
+++ /dev/null
@@ -1,421 +0,0 @@
-"""Implementation of JSONDecoder
-"""
-import re
-import sys
-import struct
-
-from simplejson.scanner import make_scanner
-def _import_c_scanstring():
- try:
- from simplejson._speedups import scanstring
- return scanstring
- except ImportError:
- return None
-c_scanstring = _import_c_scanstring()
-
-__all__ = ['JSONDecoder']
-
-FLAGS = re.VERBOSE | re.MULTILINE | re.DOTALL
-
-def _floatconstants():
- _BYTES = '7FF80000000000007FF0000000000000'.decode('hex')
- # The struct module in Python 2.4 would get frexp() out of range here
- # when an endian is specified in the format string. Fixed in Python 2.5+
- if sys.byteorder != 'big':
- _BYTES = _BYTES[:8][::-1] + _BYTES[8:][::-1]
- nan, inf = struct.unpack('dd', _BYTES)
- return nan, inf, -inf
-
-NaN, PosInf, NegInf = _floatconstants()
-
-
-class JSONDecodeError(ValueError):
- """Subclass of ValueError with the following additional properties:
-
- msg: The unformatted error message
- doc: The JSON document being parsed
- pos: The start index of doc where parsing failed
- end: The end index of doc where parsing failed (may be None)
- lineno: The line corresponding to pos
- colno: The column corresponding to pos
- endlineno: The line corresponding to end (may be None)
- endcolno: The column corresponding to end (may be None)
-
- """
- def __init__(self, msg, doc, pos, end=None):
- ValueError.__init__(self, errmsg(msg, doc, pos, end=end))
- self.msg = msg
- self.doc = doc
- self.pos = pos
- self.end = end
- self.lineno, self.colno = linecol(doc, pos)
- if end is not None:
- self.endlineno, self.endcolno = linecol(doc, end)
- else:
- self.endlineno, self.endcolno = None, None
-
-
-def linecol(doc, pos):
- lineno = doc.count('\n', 0, pos) + 1
- if lineno == 1:
- colno = pos
- else:
- colno = pos - doc.rindex('\n', 0, pos)
- return lineno, colno
-
-
-def errmsg(msg, doc, pos, end=None):
- # Note that this function is called from _speedups
- lineno, colno = linecol(doc, pos)
- if end is None:
- #fmt = '{0}: line {1} column {2} (char {3})'
- #return fmt.format(msg, lineno, colno, pos)
- fmt = '%s: line %d column %d (char %d)'
- return fmt % (msg, lineno, colno, pos)
- endlineno, endcolno = linecol(doc, end)
- #fmt = '{0}: line {1} column {2} - line {3} column {4} (char {5} - {6})'
- #return fmt.format(msg, lineno, colno, endlineno, endcolno, pos, end)
- fmt = '%s: line %d column %d - line %d column %d (char %d - %d)'
- return fmt % (msg, lineno, colno, endlineno, endcolno, pos, end)
-
-
-_CONSTANTS = {
- '-Infinity': NegInf,
- 'Infinity': PosInf,
- 'NaN': NaN,
-}
-
-STRINGCHUNK = re.compile(r'(.*?)(["\\\x00-\x1f])', FLAGS)
-BACKSLASH = {
- '"': u'"', '\\': u'\\', '/': u'/',
- 'b': u'\b', 'f': u'\f', 'n': u'\n', 'r': u'\r', 't': u'\t',
-}
-
-DEFAULT_ENCODING = "utf-8"
-
-def py_scanstring(s, end, encoding=None, strict=True,
- _b=BACKSLASH, _m=STRINGCHUNK.match):
- """Scan the string s for a JSON string. End is the index of the
- character in s after the quote that started the JSON string.
- Unescapes all valid JSON string escape sequences and raises ValueError
- on attempt to decode an invalid string. If strict is False then literal
- control characters are allowed in the string.
-
- Returns a tuple of the decoded string and the index of the character in s
- after the end quote."""
- if encoding is None:
- encoding = DEFAULT_ENCODING
- chunks = []
- _append = chunks.append
- begin = end - 1
- while 1:
- chunk = _m(s, end)
- if chunk is None:
- raise JSONDecodeError(
- "Unterminated string starting at", s, begin)
- end = chunk.end()
- content, terminator = chunk.groups()
- # Content is contains zero or more unescaped string characters
- if content:
- if not isinstance(content, unicode):
- content = unicode(content, encoding)
- _append(content)
- # Terminator is the end of string, a literal control character,
- # or a backslash denoting that an escape sequence follows
- if terminator == '"':
- break
- elif terminator != '\\':
- if strict:
- msg = "Invalid control character %r at" % (terminator,)
- #msg = "Invalid control character {0!r} at".format(terminator)
- raise JSONDecodeError(msg, s, end)
- else:
- _append(terminator)
- continue
- try:
- esc = s[end]
- except IndexError:
- raise JSONDecodeError(
- "Unterminated string starting at", s, begin)
- # If not a unicode escape sequence, must be in the lookup table
- if esc != 'u':
- try:
- char = _b[esc]
- except KeyError:
- msg = "Invalid \\escape: " + repr(esc)
- raise JSONDecodeError(msg, s, end)
- end += 1
- else:
- # Unicode escape sequence
- esc = s[end + 1:end + 5]
- next_end = end + 5
- if len(esc) != 4:
- msg = "Invalid \\uXXXX escape"
- raise JSONDecodeError(msg, s, end)
- uni = int(esc, 16)
- # Check for surrogate pair on UCS-4 systems
- if 0xd800 <= uni <= 0xdbff and sys.maxunicode > 65535:
- msg = "Invalid \\uXXXX\\uXXXX surrogate pair"
- if not s[end + 5:end + 7] == '\\u':
- raise JSONDecodeError(msg, s, end)
- esc2 = s[end + 7:end + 11]
- if len(esc2) != 4:
- raise JSONDecodeError(msg, s, end)
- uni2 = int(esc2, 16)
- uni = 0x10000 + (((uni - 0xd800) << 10) | (uni2 - 0xdc00))
- next_end += 6
- char = unichr(uni)
- end = next_end
- # Append the unescaped character
- _append(char)
- return u''.join(chunks), end
-
-
-# Use speedup if available
-scanstring = c_scanstring or py_scanstring
-
-WHITESPACE = re.compile(r'[ \t\n\r]*', FLAGS)
-WHITESPACE_STR = ' \t\n\r'
-
-def JSONObject((s, end), encoding, strict, scan_once, object_hook,
- object_pairs_hook, memo=None,
- _w=WHITESPACE.match, _ws=WHITESPACE_STR):
- # Backwards compatibility
- if memo is None:
- memo = {}
- memo_get = memo.setdefault
- pairs = []
- # Use a slice to prevent IndexError from being raised, the following
- # check will raise a more specific ValueError if the string is empty
- nextchar = s[end:end + 1]
- # Normally we expect nextchar == '"'
- if nextchar != '"':
- if nextchar in _ws:
- end = _w(s, end).end()
- nextchar = s[end:end + 1]
- # Trivial empty object
- if nextchar == '}':
- if object_pairs_hook is not None:
- result = object_pairs_hook(pairs)
- return result, end + 1
- pairs = {}
- if object_hook is not None:
- pairs = object_hook(pairs)
- return pairs, end + 1
- elif nextchar != '"':
- raise JSONDecodeError("Expecting property name", s, end)
- end += 1
- while True:
- key, end = scanstring(s, end, encoding, strict)
- key = memo_get(key, key)
-
- # To skip some function call overhead we optimize the fast paths where
- # the JSON key separator is ": " or just ":".
- if s[end:end + 1] != ':':
- end = _w(s, end).end()
- if s[end:end + 1] != ':':
- raise JSONDecodeError("Expecting : delimiter", s, end)
-
- end += 1
-
- try:
- if s[end] in _ws:
- end += 1
- if s[end] in _ws:
- end = _w(s, end + 1).end()
- except IndexError:
- pass
-
- try:
- value, end = scan_once(s, end)
- except StopIteration:
- raise JSONDecodeError("Expecting object", s, end)
- pairs.append((key, value))
-
- try:
- nextchar = s[end]
- if nextchar in _ws:
- end = _w(s, end + 1).end()
- nextchar = s[end]
- except IndexError:
- nextchar = ''
- end += 1
-
- if nextchar == '}':
- break
- elif nextchar != ',':
- raise JSONDecodeError("Expecting , delimiter", s, end - 1)
-
- try:
- nextchar = s[end]
- if nextchar in _ws:
- end += 1
- nextchar = s[end]
- if nextchar in _ws:
- end = _w(s, end + 1).end()
- nextchar = s[end]
- except IndexError:
- nextchar = ''
-
- end += 1
- if nextchar != '"':
- raise JSONDecodeError("Expecting property name", s, end - 1)
-
- if object_pairs_hook is not None:
- result = object_pairs_hook(pairs)
- return result, end
- pairs = dict(pairs)
- if object_hook is not None:
- pairs = object_hook(pairs)
- return pairs, end
-
-def JSONArray((s, end), scan_once, _w=WHITESPACE.match, _ws=WHITESPACE_STR):
- values = []
- nextchar = s[end:end + 1]
- if nextchar in _ws:
- end = _w(s, end + 1).end()
- nextchar = s[end:end + 1]
- # Look-ahead for trivial empty array
- if nextchar == ']':
- return values, end + 1
- _append = values.append
- while True:
- try:
- value, end = scan_once(s, end)
- except StopIteration:
- raise JSONDecodeError("Expecting object", s, end)
- _append(value)
- nextchar = s[end:end + 1]
- if nextchar in _ws:
- end = _w(s, end + 1).end()
- nextchar = s[end:end + 1]
- end += 1
- if nextchar == ']':
- break
- elif nextchar != ',':
- raise JSONDecodeError("Expecting , delimiter", s, end)
-
- try:
- if s[end] in _ws:
- end += 1
- if s[end] in _ws:
- end = _w(s, end + 1).end()
- except IndexError:
- pass
-
- return values, end
-
-class JSONDecoder(object):
- """Simple JSON <http://json.org> decoder
-
- Performs the following translations in decoding by default:
-
- +---------------+-------------------+
- | JSON | Python |
- +===============+===================+
- | object | dict |
- +---------------+-------------------+
- | array | list |
- +---------------+-------------------+
- | string | unicode |
- +---------------+-------------------+
- | number (int) | int, long |
- +---------------+-------------------+
- | number (real) | float |
- +---------------+-------------------+
- | true | True |
- +---------------+-------------------+
- | false | False |
- +---------------+-------------------+
- | null | None |
- +---------------+-------------------+
-
- It also understands ``NaN``, ``Infinity``, and ``-Infinity`` as
- their corresponding ``float`` values, which is outside the JSON spec.
-
- """
-
- def __init__(self, encoding=None, object_hook=None, parse_float=None,
- parse_int=None, parse_constant=None, strict=True,
- object_pairs_hook=None):
- """
- *encoding* determines the encoding used to interpret any
- :class:`str` objects decoded by this instance (``'utf-8'`` by
- default). It has no effect when decoding :class:`unicode` objects.
-
- Note that currently only encodings that are a superset of ASCII work,
- strings of other encodings should be passed in as :class:`unicode`.
-
- *object_hook*, if specified, will be called with the result of every
- JSON object decoded and its return value will be used in place of the
- given :class:`dict`. This can be used to provide custom
- deserializations (e.g. to support JSON-RPC class hinting).
-
- *object_pairs_hook* is an optional function that will be called with
- the result of any object literal decode with an ordered list of pairs.
- The return value of *object_pairs_hook* will be used instead of the
- :class:`dict`. This feature can be used to implement custom decoders
- that rely on the order that the key and value pairs are decoded (for
- example, :func:`collections.OrderedDict` will remember the order of
- insertion). If *object_hook* is also defined, the *object_pairs_hook*
- takes priority.
-
- *parse_float*, if specified, will be called with the string of every
- JSON float to be decoded. By default, this is equivalent to
- ``float(num_str)``. This can be used to use another datatype or parser
- for JSON floats (e.g. :class:`decimal.Decimal`).
-
- *parse_int*, if specified, will be called with the string of every
- JSON int to be decoded. By default, this is equivalent to
- ``int(num_str)``. This can be used to use another datatype or parser
- for JSON integers (e.g. :class:`float`).
-
- *parse_constant*, if specified, will be called with one of the
- following strings: ``'-Infinity'``, ``'Infinity'``, ``'NaN'``. This
- can be used to raise an exception if invalid JSON numbers are
- encountered.
-
- *strict* controls the parser's behavior when it encounters an
- invalid control character in a string. The default setting of
- ``True`` means that unescaped control characters are parse errors, if
- ``False`` then control characters will be allowed in strings.
-
- """
- self.encoding = encoding
- self.object_hook = object_hook
- self.object_pairs_hook = object_pairs_hook
- self.parse_float = parse_float or float
- self.parse_int = parse_int or int
- self.parse_constant = parse_constant or _CONSTANTS.__getitem__
- self.strict = strict
- self.parse_object = JSONObject
- self.parse_array = JSONArray
- self.parse_string = scanstring
- self.memo = {}
- self.scan_once = make_scanner(self)
-
- def decode(self, s, _w=WHITESPACE.match):
- """Return the Python representation of ``s`` (a ``str`` or ``unicode``
- instance containing a JSON document)
-
- """
- obj, end = self.raw_decode(s, idx=_w(s, 0).end())
- end = _w(s, end).end()
- if end != len(s):
- raise JSONDecodeError("Extra data", s, end, len(s))
- return obj
-
- def raw_decode(self, s, idx=0):
- """Decode a JSON document from ``s`` (a ``str`` or ``unicode``
- beginning with a JSON document) and return a 2-tuple of the Python
- representation and the index in ``s`` where the document ended.
-
- This can be used to decode a JSON document from a string that may
- have extraneous data at the end.
-
- """
- try:
- obj, end = self.scan_once(s, idx)
- except StopIteration:
- raise JSONDecodeError("No JSON object could be decoded", s, idx)
- return obj, end
diff --git a/simplejson/encoder.py b/simplejson/encoder.py
deleted file mode 100644
index 468d1bd82e59fba7afa177ee722efbf200892cc2..0000000000000000000000000000000000000000
--- a/simplejson/encoder.py
+++ /dev/null
@@ -1,501 +0,0 @@
-"""Implementation of JSONEncoder
-"""
-import re
-from decimal import Decimal
-
-def _import_speedups():
- try:
- from simplejson import _speedups
- return _speedups.encode_basestring_ascii, _speedups.make_encoder
- except ImportError:
- return None, None
-c_encode_basestring_ascii, c_make_encoder = _import_speedups()
-
-from simplejson.decoder import PosInf
-
-ESCAPE = re.compile(r'[\x00-\x1f\\"\b\f\n\r\t]')
-ESCAPE_ASCII = re.compile(r'([\\"]|[^\ -~])')
-HAS_UTF8 = re.compile(r'[\x80-\xff]')
-ESCAPE_DCT = {
- '\\': '\\\\',
- '"': '\\"',
- '\b': '\\b',
- '\f': '\\f',
- '\n': '\\n',
- '\r': '\\r',
- '\t': '\\t',
-}
-for i in range(0x20):
- #ESCAPE_DCT.setdefault(chr(i), '\\u{0:04x}'.format(i))
- ESCAPE_DCT.setdefault(chr(i), '\\u%04x' % (i,))
-
-FLOAT_REPR = repr
-
-def encode_basestring(s):
- """Return a JSON representation of a Python string
-
- """
- if isinstance(s, str) and HAS_UTF8.search(s) is not None:
- s = s.decode('utf-8')
- def replace(match):
- return ESCAPE_DCT[match.group(0)]
- return u'"' + ESCAPE.sub(replace, s) + u'"'
-
-
-def py_encode_basestring_ascii(s):
- """Return an ASCII-only JSON representation of a Python string
-
- """
- if isinstance(s, str) and HAS_UTF8.search(s) is not None:
- s = s.decode('utf-8')
- def replace(match):
- s = match.group(0)
- try:
- return ESCAPE_DCT[s]
- except KeyError:
- n = ord(s)
- if n < 0x10000:
- #return '\\u{0:04x}'.format(n)
- return '\\u%04x' % (n,)
- else:
- # surrogate pair
- n -= 0x10000
- s1 = 0xd800 | ((n >> 10) & 0x3ff)
- s2 = 0xdc00 | (n & 0x3ff)
- #return '\\u{0:04x}\\u{1:04x}'.format(s1, s2)
- return '\\u%04x\\u%04x' % (s1, s2)
- return '"' + str(ESCAPE_ASCII.sub(replace, s)) + '"'
-
-
-encode_basestring_ascii = (
- c_encode_basestring_ascii or py_encode_basestring_ascii)
-
-class JSONEncoder(object):
- """Extensible JSON <http://json.org> encoder for Python data structures.
-
- Supports the following objects and types by default:
-
- +-------------------+---------------+
- | Python | JSON |
- +===================+===============+
- | dict | object |
- +-------------------+---------------+
- | list, tuple | array |
- +-------------------+---------------+
- | str, unicode | string |
- +-------------------+---------------+
- | int, long, float | number |
- +-------------------+---------------+
- | True | true |
- +-------------------+---------------+
- | False | false |
- +-------------------+---------------+
- | None | null |
- +-------------------+---------------+
-
- To extend this to recognize other objects, subclass and implement a
- ``.default()`` method with another method that returns a serializable
- object for ``o`` if possible, otherwise it should call the superclass
- implementation (to raise ``TypeError``).
-
- """
- item_separator = ', '
- key_separator = ': '
- def __init__(self, skipkeys=False, ensure_ascii=True,
- check_circular=True, allow_nan=True, sort_keys=False,
- indent=None, separators=None, encoding='utf-8', default=None,
- use_decimal=False):
- """Constructor for JSONEncoder, with sensible defaults.
-
- If skipkeys is false, then it is a TypeError to attempt
- encoding of keys that are not str, int, long, float or None. If
- skipkeys is True, such items are simply skipped.
-
- If ensure_ascii is true, the output is guaranteed to be str
- objects with all incoming unicode characters escaped. If
- ensure_ascii is false, the output will be unicode object.
-
- If check_circular is true, then lists, dicts, and custom encoded
- objects will be checked for circular references during encoding to
- prevent an infinite recursion (which would cause an OverflowError).
- Otherwise, no such check takes place.
-
- If allow_nan is true, then NaN, Infinity, and -Infinity will be
- encoded as such. This behavior is not JSON specification compliant,
- but is consistent with most JavaScript based encoders and decoders.
- Otherwise, it will be a ValueError to encode such floats.
-
- If sort_keys is true, then the output of dictionaries will be
- sorted by key; this is useful for regression tests to ensure
- that JSON serializations can be compared on a day-to-day basis.
-
- If indent is a string, then JSON array elements and object members
- will be pretty-printed with a newline followed by that string repeated
- for each level of nesting. ``None`` (the default) selects the most compact
- representation without any newlines. For backwards compatibility with
- versions of simplejson earlier than 2.1.0, an integer is also accepted
- and is converted to a string with that many spaces.
-
- If specified, separators should be a (item_separator, key_separator)
- tuple. The default is (', ', ': '). To get the most compact JSON
- representation you should specify (',', ':') to eliminate whitespace.
-
- If specified, default is a function that gets called for objects
- that can't otherwise be serialized. It should return a JSON encodable
- version of the object or raise a ``TypeError``.
-
- If encoding is not None, then all input strings will be
- transformed into unicode using that encoding prior to JSON-encoding.
- The default is UTF-8.
-
- If use_decimal is true (not the default), ``decimal.Decimal`` will
- be supported directly by the encoder. For the inverse, decode JSON
- with ``parse_float=decimal.Decimal``.
-
- """
-
- self.skipkeys = skipkeys
- self.ensure_ascii = ensure_ascii
- self.check_circular = check_circular
- self.allow_nan = allow_nan
- self.sort_keys = sort_keys
- self.use_decimal = use_decimal
- if isinstance(indent, (int, long)):
- indent = ' ' * indent
- self.indent = indent
- if separators is not None:
- self.item_separator, self.key_separator = separators
- if default is not None:
- self.default = default
- self.encoding = encoding
-
- def default(self, o):
- """Implement this method in a subclass such that it returns
- a serializable object for ``o``, or calls the base implementation
- (to raise a ``TypeError``).
-
- For example, to support arbitrary iterators, you could
- implement default like this::
-
- def default(self, o):
- try:
- iterable = iter(o)
- except TypeError:
- pass
- else:
- return list(iterable)
- return JSONEncoder.default(self, o)
-
- """
- raise TypeError(repr(o) + " is not JSON serializable")
-
- def encode(self, o):
- """Return a JSON string representation of a Python data structure.
-
- >>> from simplejson import JSONEncoder
- >>> JSONEncoder().encode({"foo": ["bar", "baz"]})
- '{"foo": ["bar", "baz"]}'
-
- """
- # This is for extremely simple cases and benchmarks.
- if isinstance(o, basestring):
- if isinstance(o, str):
- _encoding = self.encoding
- if (_encoding is not None
- and not (_encoding == 'utf-8')):
- o = o.decode(_encoding)
- if self.ensure_ascii:
- return encode_basestring_ascii(o)
- else:
- return encode_basestring(o)
- # This doesn't pass the iterator directly to ''.join() because the
- # exceptions aren't as detailed. The list call should be roughly
- # equivalent to the PySequence_Fast that ''.join() would do.
- chunks = self.iterencode(o, _one_shot=True)
- if not isinstance(chunks, (list, tuple)):
- chunks = list(chunks)
- if self.ensure_ascii:
- return ''.join(chunks)
- else:
- return u''.join(chunks)
-
- def iterencode(self, o, _one_shot=False):
- """Encode the given object and yield each string
- representation as available.
-
- For example::
-
- for chunk in JSONEncoder().iterencode(bigobject):
- mysocket.write(chunk)
-
- """
- if self.check_circular:
- markers = {}
- else:
- markers = None
- if self.ensure_ascii:
- _encoder = encode_basestring_ascii
- else:
- _encoder = encode_basestring
- if self.encoding != 'utf-8':
- def _encoder(o, _orig_encoder=_encoder, _encoding=self.encoding):
- if isinstance(o, str):
- o = o.decode(_encoding)
- return _orig_encoder(o)
-
- def floatstr(o, allow_nan=self.allow_nan,
- _repr=FLOAT_REPR, _inf=PosInf, _neginf=-PosInf):
- # Check for specials. Note that this type of test is processor
- # and/or platform-specific, so do tests which don't depend on
- # the internals.
-
- if o != o:
- text = 'NaN'
- elif o == _inf:
- text = 'Infinity'
- elif o == _neginf:
- text = '-Infinity'
- else:
- return _repr(o)
-
- if not allow_nan:
- raise ValueError(
- "Out of range float values are not JSON compliant: " +
- repr(o))
-
- return text
-
-
- key_memo = {}
- if (_one_shot and c_make_encoder is not None
- and self.indent is None):
- _iterencode = c_make_encoder(
- markers, self.default, _encoder, self.indent,
- self.key_separator, self.item_separator, self.sort_keys,
- self.skipkeys, self.allow_nan, key_memo, self.use_decimal)
- else:
- _iterencode = _make_iterencode(
- markers, self.default, _encoder, self.indent, floatstr,
- self.key_separator, self.item_separator, self.sort_keys,
- self.skipkeys, _one_shot, self.use_decimal)
- try:
- return _iterencode(o, 0)
- finally:
- key_memo.clear()
-
-
-class JSONEncoderForHTML(JSONEncoder):
- """An encoder that produces JSON safe to embed in HTML.
-
- To embed JSON content in, say, a script tag on a web page, the
- characters &, < and > should be escaped. They cannot be escaped
- with the usual entities (e.g. &) because they are not expanded
- within <script> tags.
- """
-
- def encode(self, o):
- # Override JSONEncoder.encode because it has hacks for
- # performance that make things more complicated.
- chunks = self.iterencode(o, True)
- if self.ensure_ascii:
- return ''.join(chunks)
- else:
- return u''.join(chunks)
-
- def iterencode(self, o, _one_shot=False):
- chunks = super(JSONEncoderForHTML, self).iterencode(o, _one_shot)
- for chunk in chunks:
- chunk = chunk.replace('&', '\\u0026')
- chunk = chunk.replace('<', '\\u003c')
- chunk = chunk.replace('>', '\\u003e')
- yield chunk
-
-
-def _make_iterencode(markers, _default, _encoder, _indent, _floatstr,
- _key_separator, _item_separator, _sort_keys, _skipkeys, _one_shot,
- _use_decimal,
- ## HACK: hand-optimized bytecode; turn globals into locals
- False=False,
- True=True,
- ValueError=ValueError,
- basestring=basestring,
- Decimal=Decimal,
- dict=dict,
- float=float,
- id=id,
- int=int,
- isinstance=isinstance,
- list=list,
- long=long,
- str=str,
- tuple=tuple,
- ):
-
- def _iterencode_list(lst, _current_indent_level):
- if not lst:
- yield '[]'
- return
- if markers is not None:
- markerid = id(lst)
- if markerid in markers:
- raise ValueError("Circular reference detected")
- markers[markerid] = lst
- buf = '['
- if _indent is not None:
- _current_indent_level += 1
- newline_indent = '\n' + (_indent * _current_indent_level)
- separator = _item_separator + newline_indent
- buf += newline_indent
- else:
- newline_indent = None
- separator = _item_separator
- first = True
- for value in lst:
- if first:
- first = False
- else:
- buf = separator
- if isinstance(value, basestring):
- yield buf + _encoder(value)
- elif value is None:
- yield buf + 'null'
- elif value is True:
- yield buf + 'true'
- elif value is False:
- yield buf + 'false'
- elif isinstance(value, (int, long)):
- yield buf + str(value)
- elif isinstance(value, float):
- yield buf + _floatstr(value)
- elif _use_decimal and isinstance(value, Decimal):
- yield buf + str(value)
- else:
- yield buf
- if isinstance(value, (list, tuple)):
- chunks = _iterencode_list(value, _current_indent_level)
- elif isinstance(value, dict):
- chunks = _iterencode_dict(value, _current_indent_level)
- else:
- chunks = _iterencode(value, _current_indent_level)
- for chunk in chunks:
- yield chunk
- if newline_indent is not None:
- _current_indent_level -= 1
- yield '\n' + (_indent * _current_indent_level)
- yield ']'
- if markers is not None:
- del markers[markerid]
-
- def _iterencode_dict(dct, _current_indent_level):
- if not dct:
- yield '{}'
- return
- if markers is not None:
- markerid = id(dct)
- if markerid in markers:
- raise ValueError("Circular reference detected")
- markers[markerid] = dct
- yield '{'
- if _indent is not None:
- _current_indent_level += 1
- newline_indent = '\n' + (_indent * _current_indent_level)
- item_separator = _item_separator + newline_indent
- yield newline_indent
- else:
- newline_indent = None
- item_separator = _item_separator
- first = True
- if _sort_keys:
- items = dct.items()
- items.sort(key=lambda kv: kv[0])
- else:
- items = dct.iteritems()
- for key, value in items:
- if isinstance(key, basestring):
- pass
- # JavaScript is weakly typed for these, so it makes sense to
- # also allow them. Many encoders seem to do something like this.
- elif isinstance(key, float):
- key = _floatstr(key)
- elif key is True:
- key = 'true'
- elif key is False:
- key = 'false'
- elif key is None:
- key = 'null'
- elif isinstance(key, (int, long)):
- key = str(key)
- elif _skipkeys:
- continue
- else:
- raise TypeError("key " + repr(key) + " is not a string")
- if first:
- first = False
- else:
- yield item_separator
- yield _encoder(key)
- yield _key_separator
- if isinstance(value, basestring):
- yield _encoder(value)
- elif value is None:
- yield 'null'
- elif value is True:
- yield 'true'
- elif value is False:
- yield 'false'
- elif isinstance(value, (int, long)):
- yield str(value)
- elif isinstance(value, float):
- yield _floatstr(value)
- elif _use_decimal and isinstance(value, Decimal):
- yield str(value)
- else:
- if isinstance(value, (list, tuple)):
- chunks = _iterencode_list(value, _current_indent_level)
- elif isinstance(value, dict):
- chunks = _iterencode_dict(value, _current_indent_level)
- else:
- chunks = _iterencode(value, _current_indent_level)
- for chunk in chunks:
- yield chunk
- if newline_indent is not None:
- _current_indent_level -= 1
- yield '\n' + (_indent * _current_indent_level)
- yield '}'
- if markers is not None:
- del markers[markerid]
-
- def _iterencode(o, _current_indent_level):
- if isinstance(o, basestring):
- yield _encoder(o)
- elif o is None:
- yield 'null'
- elif o is True:
- yield 'true'
- elif o is False:
- yield 'false'
- elif isinstance(o, (int, long)):
- yield str(o)
- elif isinstance(o, float):
- yield _floatstr(o)
- elif isinstance(o, (list, tuple)):
- for chunk in _iterencode_list(o, _current_indent_level):
- yield chunk
- elif isinstance(o, dict):
- for chunk in _iterencode_dict(o, _current_indent_level):
- yield chunk
- elif _use_decimal and isinstance(o, Decimal):
- yield str(o)
- else:
- if markers is not None:
- markerid = id(o)
- if markerid in markers:
- raise ValueError("Circular reference detected")
- markers[markerid] = o
- o = _default(o)
- for chunk in _iterencode(o, _current_indent_level):
- yield chunk
- if markers is not None:
- del markers[markerid]
-
- return _iterencode
diff --git a/simplejson/ordered_dict.py b/simplejson/ordered_dict.py
deleted file mode 100644
index 87ad8882482ca02970df711f4aa1039bece45cb9..0000000000000000000000000000000000000000
--- a/simplejson/ordered_dict.py
+++ /dev/null
@@ -1,119 +0,0 @@
-"""Drop-in replacement for collections.OrderedDict by Raymond Hettinger
-
-http://code.activestate.com/recipes/576693/
-
-"""
-from UserDict import DictMixin
-
-# Modified from original to support Python 2.4, see
-# http://code.google.com/p/simplejson/issues/detail?id=53
-try:
- all
-except NameError:
- def all(seq):
- for elem in seq:
- if not elem:
- return False
- return True
-
-class OrderedDict(dict, DictMixin):
-
- def __init__(self, *args, **kwds):
- if len(args) > 1:
- raise TypeError('expected at most 1 arguments, got %d' % len(args))
- try:
- self.__end
- except AttributeError:
- self.clear()
- self.update(*args, **kwds)
-
- def clear(self):
- self.__end = end = []
- end += [None, end, end] # sentinel node for doubly linked list
- self.__map = {} # key --> [key, prev, next]
- dict.clear(self)
-
- def __setitem__(self, key, value):
- if key not in self:
- end = self.__end
- curr = end[1]
- curr[2] = end[1] = self.__map[key] = [key, curr, end]
- dict.__setitem__(self, key, value)
-
- def __delitem__(self, key):
- dict.__delitem__(self, key)
- key, prev, next = self.__map.pop(key)
- prev[2] = next
- next[1] = prev
-
- def __iter__(self):
- end = self.__end
- curr = end[2]
- while curr is not end:
- yield curr[0]
- curr = curr[2]
-
- def __reversed__(self):
- end = self.__end
- curr = end[1]
- while curr is not end:
- yield curr[0]
- curr = curr[1]
-
- def popitem(self, last=True):
- if not self:
- raise KeyError('dictionary is empty')
- # Modified from original to support Python 2.4, see
- # http://code.google.com/p/simplejson/issues/detail?id=53
- if last:
- key = reversed(self).next()
- else:
- key = iter(self).next()
- value = self.pop(key)
- return key, value
-
- def __reduce__(self):
- items = [[k, self[k]] for k in self]
- tmp = self.__map, self.__end
- del self.__map, self.__end
- inst_dict = vars(self).copy()
- self.__map, self.__end = tmp
- if inst_dict:
- return (self.__class__, (items,), inst_dict)
- return self.__class__, (items,)
-
- def keys(self):
- return list(self)
-
- setdefault = DictMixin.setdefault
- update = DictMixin.update
- pop = DictMixin.pop
- values = DictMixin.values
- items = DictMixin.items
- iterkeys = DictMixin.iterkeys
- itervalues = DictMixin.itervalues
- iteritems = DictMixin.iteritems
-
- def __repr__(self):
- if not self:
- return '%s()' % (self.__class__.__name__,)
- return '%s(%r)' % (self.__class__.__name__, self.items())
-
- def copy(self):
- return self.__class__(self)
-
- @classmethod
- def fromkeys(cls, iterable, value=None):
- d = cls()
- for key in iterable:
- d[key] = value
- return d
-
- def __eq__(self, other):
- if isinstance(other, OrderedDict):
- return len(self)==len(other) and \
- all(p==q for p, q in zip(self.items(), other.items()))
- return dict.__eq__(self, other)
-
- def __ne__(self, other):
- return not self == other
diff --git a/simplejson/scanner.py b/simplejson/scanner.py
deleted file mode 100644
index 54593a371e2b281d8a16cb9a7856857a29abacf5..0000000000000000000000000000000000000000
--- a/simplejson/scanner.py
+++ /dev/null
@@ -1,77 +0,0 @@
-"""JSON token scanner
-"""
-import re
-def _import_c_make_scanner():
- try:
- from simplejson._speedups import make_scanner
- return make_scanner
- except ImportError:
- return None
-c_make_scanner = _import_c_make_scanner()
-
-__all__ = ['make_scanner']
-
-NUMBER_RE = re.compile(
- r'(-?(?:0|[1-9]\d*))(\.\d+)?([eE][-+]?\d+)?',
- (re.VERBOSE | re.MULTILINE | re.DOTALL))
-
-def py_make_scanner(context):
- parse_object = context.parse_object
- parse_array = context.parse_array
- parse_string = context.parse_string
- match_number = NUMBER_RE.match
- encoding = context.encoding
- strict = context.strict
- parse_float = context.parse_float
- parse_int = context.parse_int
- parse_constant = context.parse_constant
- object_hook = context.object_hook
- object_pairs_hook = context.object_pairs_hook
- memo = context.memo
-
- def _scan_once(string, idx):
- try:
- nextchar = string[idx]
- except IndexError:
- raise StopIteration
-
- if nextchar == '"':
- return parse_string(string, idx + 1, encoding, strict)
- elif nextchar == '{':
- return parse_object((string, idx + 1), encoding, strict,
- _scan_once, object_hook, object_pairs_hook, memo)
- elif nextchar == '[':
- return parse_array((string, idx + 1), _scan_once)
- elif nextchar == 'n' and string[idx:idx + 4] == 'null':
- return None, idx + 4
- elif nextchar == 't' and string[idx:idx + 4] == 'true':
- return True, idx + 4
- elif nextchar == 'f' and string[idx:idx + 5] == 'false':
- return False, idx + 5
-
- m = match_number(string, idx)
- if m is not None:
- integer, frac, exp = m.groups()
- if frac or exp:
- res = parse_float(integer + (frac or '') + (exp or ''))
- else:
- res = parse_int(integer)
- return res, m.end()
- elif nextchar == 'N' and string[idx:idx + 3] == 'NaN':
- return parse_constant('NaN'), idx + 3
- elif nextchar == 'I' and string[idx:idx + 8] == 'Infinity':
- return parse_constant('Infinity'), idx + 8
- elif nextchar == '-' and string[idx:idx + 9] == '-Infinity':
- return parse_constant('-Infinity'), idx + 9
- else:
- raise StopIteration
-
- def scan_once(string, idx):
- try:
- return _scan_once(string, idx)
- finally:
- memo.clear()
-
- return scan_once
-
-make_scanner = c_make_scanner or py_make_scanner
diff --git a/simplejson/tests/__init__.py b/simplejson/tests/__init__.py
deleted file mode 100644
index d7135218af83324b505e351ae4b3b6d2633a1715..0000000000000000000000000000000000000000
--- a/simplejson/tests/__init__.py
+++ /dev/null
@@ -1,64 +0,0 @@
-import unittest
-import doctest
-
-
-class OptionalExtensionTestSuite(unittest.TestSuite):
- def run(self, result):
- import simplejson
- run = unittest.TestSuite.run
- run(self, result)
- simplejson._toggle_speedups(False)
- run(self, result)
- simplejson._toggle_speedups(True)
- return result
-
-
-def additional_tests(suite=None):
- import simplejson
- import simplejson.encoder
- import simplejson.decoder
- if suite is None:
- suite = unittest.TestSuite()
- for mod in (simplejson, simplejson.encoder, simplejson.decoder):
- suite.addTest(doctest.DocTestSuite(mod))
- suite.addTest(doctest.DocFileSuite('../../index.rst'))
- return suite
-
-
-def all_tests_suite():
- suite = unittest.TestLoader().loadTestsFromNames([
- 'simplejson.tests.test_check_circular',
- 'simplejson.tests.test_decode',
- 'simplejson.tests.test_default',
- 'simplejson.tests.test_dump',
- 'simplejson.tests.test_encode_basestring_ascii',
- 'simplejson.tests.test_encode_for_html',
- 'simplejson.tests.test_errors',
- 'simplejson.tests.test_fail',
- 'simplejson.tests.test_float',
- 'simplejson.tests.test_indent',
- 'simplejson.tests.test_pass1',
- 'simplejson.tests.test_pass2',
- 'simplejson.tests.test_pass3',
- 'simplejson.tests.test_recursion',
- 'simplejson.tests.test_scanstring',
- 'simplejson.tests.test_separators',
- 'simplejson.tests.test_speedups',
- 'simplejson.tests.test_unicode',
- 'simplejson.tests.test_decimal',
- ])
- suite = additional_tests(suite)
- return OptionalExtensionTestSuite([suite])
-
-
-def main():
- runner = unittest.TextTestRunner()
- suite = all_tests_suite()
- runner.run(suite)
-
-
-if __name__ == '__main__':
- import os
- import sys
- sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))))
- main()
diff --git a/simplejson/tests/test_check_circular.py b/simplejson/tests/test_check_circular.py
deleted file mode 100644
index af6463d6d88f8178ac0a6e07662650c9a623bc48..0000000000000000000000000000000000000000
--- a/simplejson/tests/test_check_circular.py
+++ /dev/null
@@ -1,30 +0,0 @@
-from unittest import TestCase
-import simplejson as json
-
-def default_iterable(obj):
- return list(obj)
-
-class TestCheckCircular(TestCase):
- def test_circular_dict(self):
- dct = {}
- dct['a'] = dct
- self.assertRaises(ValueError, json.dumps, dct)
-
- def test_circular_list(self):
- lst = []
- lst.append(lst)
- self.assertRaises(ValueError, json.dumps, lst)
-
- def test_circular_composite(self):
- dct2 = {}
- dct2['a'] = []
- dct2['a'].append(dct2)
- self.assertRaises(ValueError, json.dumps, dct2)
-
- def test_circular_default(self):
- json.dumps([set()], default=default_iterable)
- self.assertRaises(TypeError, json.dumps, [set()])
-
- def test_circular_off_default(self):
- json.dumps([set()], default=default_iterable, check_circular=False)
- self.assertRaises(TypeError, json.dumps, [set()], check_circular=False)
diff --git a/simplejson/tests/test_decimal.py b/simplejson/tests/test_decimal.py
deleted file mode 100644
index 6b4b8f353b413f02895edc8f529431deab43d7af..0000000000000000000000000000000000000000
--- a/simplejson/tests/test_decimal.py
+++ /dev/null
@@ -1,50 +0,0 @@
-from decimal import Decimal
-from unittest import TestCase
-from StringIO import StringIO
-
-import simplejson as json
-
-class TestDecimal(TestCase):
- NUMS = "1.0", "10.00", "1.1", "1234567890.1234567890", "500"
- def dumps(self, obj, **kw):
- sio = StringIO()
- json.dump(obj, sio, **kw)
- res = json.dumps(obj, **kw)
- self.assertEquals(res, sio.getvalue())
- return res
-
- def loads(self, s, **kw):
- sio = StringIO(s)
- res = json.loads(s, **kw)
- self.assertEquals(res, json.load(sio, **kw))
- return res
-
- def test_decimal_encode(self):
- for d in map(Decimal, self.NUMS):
- self.assertEquals(self.dumps(d, use_decimal=True), str(d))
-
- def test_decimal_decode(self):
- for s in self.NUMS:
- self.assertEquals(self.loads(s, parse_float=Decimal), Decimal(s))
-
- def test_decimal_roundtrip(self):
- for d in map(Decimal, self.NUMS):
- # The type might not be the same (int and Decimal) but they
- # should still compare equal.
- self.assertEquals(
- self.loads(
- self.dumps(d, use_decimal=True), parse_float=Decimal),
- d)
- self.assertEquals(
- self.loads(
- self.dumps([d], use_decimal=True), parse_float=Decimal),
- [d])
-
- def test_decimal_defaults(self):
- d = Decimal(1)
- sio = StringIO()
- # use_decimal=False is the default
- self.assertRaises(TypeError, json.dumps, d, use_decimal=False)
- self.assertRaises(TypeError, json.dumps, d)
- self.assertRaises(TypeError, json.dump, d, sio, use_decimal=False)
- self.assertRaises(TypeError, json.dump, d, sio)
\ No newline at end of file
diff --git a/simplejson/tests/test_decode.py b/simplejson/tests/test_decode.py
deleted file mode 100644
index a140a1306053b455591555ec78ecfa070d7ee733..0000000000000000000000000000000000000000
--- a/simplejson/tests/test_decode.py
+++ /dev/null
@@ -1,83 +0,0 @@
-import decimal
-from unittest import TestCase
-from StringIO import StringIO
-
-import simplejson as json
-from simplejson import OrderedDict
-
-class TestDecode(TestCase):
- if not hasattr(TestCase, 'assertIs'):
- def assertIs(self, a, b):
- self.assertTrue(a is b, '%r is %r' % (a, b))
-
- def test_decimal(self):
- rval = json.loads('1.1', parse_float=decimal.Decimal)
- self.assertTrue(isinstance(rval, decimal.Decimal))
- self.assertEquals(rval, decimal.Decimal('1.1'))
-
- def test_float(self):
- rval = json.loads('1', parse_int=float)
- self.assertTrue(isinstance(rval, float))
- self.assertEquals(rval, 1.0)
-
- def test_decoder_optimizations(self):
- # Several optimizations were made that skip over calls to
- # the whitespace regex, so this test is designed to try and
- # exercise the uncommon cases. The array cases are already covered.
- rval = json.loads('{ "key" : "value" , "k":"v" }')
- self.assertEquals(rval, {"key":"value", "k":"v"})
-
- def test_empty_objects(self):
- s = '{}'
- self.assertEqual(json.loads(s), eval(s))
- s = '[]'
- self.assertEqual(json.loads(s), eval(s))
- s = '""'
- self.assertEqual(json.loads(s), eval(s))
-
- def test_object_pairs_hook(self):
- s = '{"xkd":1, "kcw":2, "art":3, "hxm":4, "qrt":5, "pad":6, "hoy":7}'
- p = [("xkd", 1), ("kcw", 2), ("art", 3), ("hxm", 4),
- ("qrt", 5), ("pad", 6), ("hoy", 7)]
- self.assertEqual(json.loads(s), eval(s))
- self.assertEqual(json.loads(s, object_pairs_hook=lambda x: x), p)
- self.assertEqual(json.load(StringIO(s),
- object_pairs_hook=lambda x: x), p)
- od = json.loads(s, object_pairs_hook=OrderedDict)
- self.assertEqual(od, OrderedDict(p))
- self.assertEqual(type(od), OrderedDict)
- # the object_pairs_hook takes priority over the object_hook
- self.assertEqual(json.loads(s,
- object_pairs_hook=OrderedDict,
- object_hook=lambda x: None),
- OrderedDict(p))
-
- def check_keys_reuse(self, source, loads):
- rval = loads(source)
- (a, b), (c, d) = sorted(rval[0]), sorted(rval[1])
- self.assertIs(a, c)
- self.assertIs(b, d)
-
- def test_keys_reuse_str(self):
- s = u'[{"a_key": 1, "b_\xe9": 2}, {"a_key": 3, "b_\xe9": 4}]'.encode('utf8')
- self.check_keys_reuse(s, json.loads)
-
- def test_keys_reuse_unicode(self):
- s = u'[{"a_key": 1, "b_\xe9": 2}, {"a_key": 3, "b_\xe9": 4}]'
- self.check_keys_reuse(s, json.loads)
-
- def test_empty_strings(self):
- self.assertEqual(json.loads('""'), "")
- self.assertEqual(json.loads(u'""'), u"")
- self.assertEqual(json.loads('[""]'), [""])
- self.assertEqual(json.loads(u'[""]'), [u""])
-
- def test_raw_decode(self):
- cls = json.decoder.JSONDecoder
- self.assertEqual(
- ({'a': {}}, 9),
- cls().raw_decode("{\"a\": {}}"))
- # http://code.google.com/p/simplejson/issues/detail?id=85
- self.assertEqual(
- ({'a': {}}, 9),
- cls(object_pairs_hook=dict).raw_decode("{\"a\": {}}"))
diff --git a/simplejson/tests/test_default.py b/simplejson/tests/test_default.py
deleted file mode 100644
index 139e42bf4acaa4927ec9be1ec55a252b97d3f1e2..0000000000000000000000000000000000000000
--- a/simplejson/tests/test_default.py
+++ /dev/null
@@ -1,9 +0,0 @@
-from unittest import TestCase
-
-import simplejson as json
-
-class TestDefault(TestCase):
- def test_default(self):
- self.assertEquals(
- json.dumps(type, default=repr),
- json.dumps(repr(type)))
diff --git a/simplejson/tests/test_dump.py b/simplejson/tests/test_dump.py
deleted file mode 100644
index 8b340046794f8b29462e4dbc9905ea488a90e4ae..0000000000000000000000000000000000000000
--- a/simplejson/tests/test_dump.py
+++ /dev/null
@@ -1,27 +0,0 @@
-from unittest import TestCase
-from cStringIO import StringIO
-
-import simplejson as json
-
-class TestDump(TestCase):
- def test_dump(self):
- sio = StringIO()
- json.dump({}, sio)
- self.assertEquals(sio.getvalue(), '{}')
-
- def test_dumps(self):
- self.assertEquals(json.dumps({}), '{}')
-
- def test_encode_truefalse(self):
- self.assertEquals(json.dumps(
- {True: False, False: True}, sort_keys=True),
- '{"false": true, "true": false}')
- self.assertEquals(json.dumps(
- {2: 3.0, 4.0: 5L, False: 1, 6L: True, "7": 0}, sort_keys=True),
- '{"false": 1, "2": 3.0, "4.0": 5, "6": true, "7": 0}')
-
- def test_ordered_dict(self):
- # http://bugs.python.org/issue6105
- items = [('one', 1), ('two', 2), ('three', 3), ('four', 4), ('five', 5)]
- s = json.dumps(json.OrderedDict(items))
- self.assertEqual(s, '{"one": 1, "two": 2, "three": 3, "four": 4, "five": 5}')
\ No newline at end of file
diff --git a/simplejson/tests/test_encode_basestring_ascii.py b/simplejson/tests/test_encode_basestring_ascii.py
deleted file mode 100644
index 6c40961dd547ad94369a25da6d64c2b30e6f4332..0000000000000000000000000000000000000000
--- a/simplejson/tests/test_encode_basestring_ascii.py
+++ /dev/null
@@ -1,46 +0,0 @@
-from unittest import TestCase
-
-import simplejson.encoder
-
-CASES = [
- (u'/\\"\ucafe\ubabe\uab98\ufcde\ubcda\uef4a\x08\x0c\n\r\t`1~!@#$%^&*()_+-=[]{}|;:\',./<>?', '"/\\\\\\"\\ucafe\\ubabe\\uab98\\ufcde\\ubcda\\uef4a\\b\\f\\n\\r\\t`1~!@#$%^&*()_+-=[]{}|;:\',./<>?"'),
- (u'\u0123\u4567\u89ab\ucdef\uabcd\uef4a', '"\\u0123\\u4567\\u89ab\\ucdef\\uabcd\\uef4a"'),
- (u'controls', '"controls"'),
- (u'\x08\x0c\n\r\t', '"\\b\\f\\n\\r\\t"'),
- (u'{"object with 1 member":["array with 1 element"]}', '"{\\"object with 1 member\\":[\\"array with 1 element\\"]}"'),
- (u' s p a c e d ', '" s p a c e d "'),
- (u'\U0001d120', '"\\ud834\\udd20"'),
- (u'\u03b1\u03a9', '"\\u03b1\\u03a9"'),
- ('\xce\xb1\xce\xa9', '"\\u03b1\\u03a9"'),
- (u'\u03b1\u03a9', '"\\u03b1\\u03a9"'),
- ('\xce\xb1\xce\xa9', '"\\u03b1\\u03a9"'),
- (u'\u03b1\u03a9', '"\\u03b1\\u03a9"'),
- (u'\u03b1\u03a9', '"\\u03b1\\u03a9"'),
- (u"`1~!@#$%^&*()_+-={':[,]}|;.</>?", '"`1~!@#$%^&*()_+-={\':[,]}|;.</>?"'),
- (u'\x08\x0c\n\r\t', '"\\b\\f\\n\\r\\t"'),
- (u'\u0123\u4567\u89ab\ucdef\uabcd\uef4a', '"\\u0123\\u4567\\u89ab\\ucdef\\uabcd\\uef4a"'),
-]
-
-class TestEncodeBaseStringAscii(TestCase):
- def test_py_encode_basestring_ascii(self):
- self._test_encode_basestring_ascii(simplejson.encoder.py_encode_basestring_ascii)
-
- def test_c_encode_basestring_ascii(self):
- if not simplejson.encoder.c_encode_basestring_ascii:
- return
- self._test_encode_basestring_ascii(simplejson.encoder.c_encode_basestring_ascii)
-
- def _test_encode_basestring_ascii(self, encode_basestring_ascii):
- fname = encode_basestring_ascii.__name__
- for input_string, expect in CASES:
- result = encode_basestring_ascii(input_string)
- #self.assertEquals(result, expect,
- # '{0!r} != {1!r} for {2}({3!r})'.format(
- # result, expect, fname, input_string))
- self.assertEquals(result, expect,
- '%r != %r for %s(%r)' % (result, expect, fname, input_string))
-
- def test_sorted_dict(self):
- items = [('one', 1), ('two', 2), ('three', 3), ('four', 4), ('five', 5)]
- s = simplejson.dumps(dict(items), sort_keys=True)
- self.assertEqual(s, '{"five": 5, "four": 4, "one": 1, "three": 3, "two": 2}')
diff --git a/simplejson/tests/test_encode_for_html.py b/simplejson/tests/test_encode_for_html.py
deleted file mode 100644
index c2d5f8015169e64d022db8920fb921bc14189f2c..0000000000000000000000000000000000000000
--- a/simplejson/tests/test_encode_for_html.py
+++ /dev/null
@@ -1,32 +0,0 @@
-import unittest
-
-import simplejson.decoder
-import simplejson.encoder
-
-
-class TestEncodeForHTML(unittest.TestCase):
-
- def setUp(self):
- self.decoder = simplejson.decoder.JSONDecoder()
- self.encoder = simplejson.encoder.JSONEncoderForHTML()
-
- def test_basic_encode(self):
- self.assertEqual(r'"\u0026"', self.encoder.encode('&'))
- self.assertEqual(r'"\u003c"', self.encoder.encode('<'))
- self.assertEqual(r'"\u003e"', self.encoder.encode('>'))
-
- def test_basic_roundtrip(self):
- for char in '&<>':
- self.assertEqual(
- char, self.decoder.decode(
- self.encoder.encode(char)))
-
- def test_prevent_script_breakout(self):
- bad_string = '</script><script>alert("gotcha")</script>'
- self.assertEqual(
- r'"\u003c/script\u003e\u003cscript\u003e'
- r'alert(\"gotcha\")\u003c/script\u003e"',
- self.encoder.encode(bad_string))
- self.assertEqual(
- bad_string, self.decoder.decode(
- self.encoder.encode(bad_string)))
diff --git a/simplejson/tests/test_errors.py b/simplejson/tests/test_errors.py
deleted file mode 100644
index c8b836a1ca81c6779113966aa450181466339928..0000000000000000000000000000000000000000
--- a/simplejson/tests/test_errors.py
+++ /dev/null
@@ -1,21 +0,0 @@
-from unittest import TestCase
-
-import simplejson as json
-
-class TestErrors(TestCase):
- def test_string_keys_error(self):
- data = [{'a': 'A', 'b': (2, 4), 'c': 3.0, ('d',): 'D tuple'}]
- self.assertRaises(TypeError, json.dumps, data)
-
- def test_decode_error(self):
- err = None
- try:
- json.loads('{}\na\nb')
- except json.JSONDecodeError, e:
- err = e
- else:
- self.fail('Expected JSONDecodeError')
- self.assertEquals(err.lineno, 2)
- self.assertEquals(err.colno, 1)
- self.assertEquals(err.endlineno, 3)
- self.assertEquals(err.endcolno, 2)
diff --git a/simplejson/tests/test_fail.py b/simplejson/tests/test_fail.py
deleted file mode 100644
index 646c0f44293daced2e31bc0ac6eccb0f72947c5d..0000000000000000000000000000000000000000
--- a/simplejson/tests/test_fail.py
+++ /dev/null
@@ -1,91 +0,0 @@
-from unittest import TestCase
-
-import simplejson as json
-
-# Fri Dec 30 18:57:26 2005
-JSONDOCS = [
- # http://json.org/JSON_checker/test/fail1.json
- '"A JSON payload should be an object or array, not a string."',
- # http://json.org/JSON_checker/test/fail2.json
- '["Unclosed array"',
- # http://json.org/JSON_checker/test/fail3.json
- '{unquoted_key: "keys must be quoted}',
- # http://json.org/JSON_checker/test/fail4.json
- '["extra comma",]',
- # http://json.org/JSON_checker/test/fail5.json
- '["double extra comma",,]',
- # http://json.org/JSON_checker/test/fail6.json
- '[ , "<-- missing value"]',
- # http://json.org/JSON_checker/test/fail7.json
- '["Comma after the close"],',
- # http://json.org/JSON_checker/test/fail8.json
- '["Extra close"]]',
- # http://json.org/JSON_checker/test/fail9.json
- '{"Extra comma": true,}',
- # http://json.org/JSON_checker/test/fail10.json
- '{"Extra value after close": true} "misplaced quoted value"',
- # http://json.org/JSON_checker/test/fail11.json
- '{"Illegal expression": 1 + 2}',
- # http://json.org/JSON_checker/test/fail12.json
- '{"Illegal invocation": alert()}',
- # http://json.org/JSON_checker/test/fail13.json
- '{"Numbers cannot have leading zeroes": 013}',
- # http://json.org/JSON_checker/test/fail14.json
- '{"Numbers cannot be hex": 0x14}',
- # http://json.org/JSON_checker/test/fail15.json
- '["Illegal backslash escape: \\x15"]',
- # http://json.org/JSON_checker/test/fail16.json
- '["Illegal backslash escape: \\\'"]',
- # http://json.org/JSON_checker/test/fail17.json
- '["Illegal backslash escape: \\017"]',
- # http://json.org/JSON_checker/test/fail18.json
- '[[[[[[[[[[[[[[[[[[[["Too deep"]]]]]]]]]]]]]]]]]]]]',
- # http://json.org/JSON_checker/test/fail19.json
- '{"Missing colon" null}',
- # http://json.org/JSON_checker/test/fail20.json
- '{"Double colon":: null}',
- # http://json.org/JSON_checker/test/fail21.json
- '{"Comma instead of colon", null}',
- # http://json.org/JSON_checker/test/fail22.json
- '["Colon instead of comma": false]',
- # http://json.org/JSON_checker/test/fail23.json
- '["Bad value", truth]',
- # http://json.org/JSON_checker/test/fail24.json
- "['single quote']",
- # http://code.google.com/p/simplejson/issues/detail?id=3
- u'["A\u001FZ control characters in string"]',
-]
-
-SKIPS = {
- 1: "why not have a string payload?",
- 18: "spec doesn't specify any nesting limitations",
-}
-
-class TestFail(TestCase):
- def test_failures(self):
- for idx, doc in enumerate(JSONDOCS):
- idx = idx + 1
- if idx in SKIPS:
- json.loads(doc)
- continue
- try:
- json.loads(doc)
- except json.JSONDecodeError:
- pass
- else:
- #self.fail("Expected failure for fail{0}.json: {1!r}".format(idx, doc))
- self.fail("Expected failure for fail%d.json: %r" % (idx, doc))
-
- def test_array_decoder_issue46(self):
- # http://code.google.com/p/simplejson/issues/detail?id=46
- for doc in [u'[,]', '[,]']:
- try:
- json.loads(doc)
- except json.JSONDecodeError, e:
- self.assertEquals(e.pos, 1)
- self.assertEquals(e.lineno, 1)
- self.assertEquals(e.colno, 1)
- except Exception, e:
- self.fail("Unexpected exception raised %r %s" % (e, e))
- else:
- self.fail("Unexpected success parsing '[,]'")
\ No newline at end of file
diff --git a/simplejson/tests/test_float.py b/simplejson/tests/test_float.py
deleted file mode 100644
index 94502c68b61e9b71f87d4a60a16cebdf8e266425..0000000000000000000000000000000000000000
--- a/simplejson/tests/test_float.py
+++ /dev/null
@@ -1,19 +0,0 @@
-import math
-from unittest import TestCase
-
-import simplejson as json
-
-class TestFloat(TestCase):
- def test_floats(self):
- for num in [1617161771.7650001, math.pi, math.pi**100,
- math.pi**-100, 3.1]:
- self.assertEquals(float(json.dumps(num)), num)
- self.assertEquals(json.loads(json.dumps(num)), num)
- self.assertEquals(json.loads(unicode(json.dumps(num))), num)
-
- def test_ints(self):
- for num in [1, 1L, 1<<32, 1<<64]:
- self.assertEquals(json.dumps(num), str(num))
- self.assertEquals(int(json.dumps(num)), num)
- self.assertEquals(json.loads(json.dumps(num)), num)
- self.assertEquals(json.loads(unicode(json.dumps(num))), num)
diff --git a/simplejson/tests/test_indent.py b/simplejson/tests/test_indent.py
deleted file mode 100644
index 75a2f6e059f666c1b61db8c1face3b35f147fb89..0000000000000000000000000000000000000000
--- a/simplejson/tests/test_indent.py
+++ /dev/null
@@ -1,69 +0,0 @@
-from unittest import TestCase
-
-import simplejson as json
-import textwrap
-from StringIO import StringIO
-
-class TestIndent(TestCase):
- def test_indent(self):
- h = [['blorpie'], ['whoops'], [], 'd-shtaeou', 'd-nthiouh',
- 'i-vhbjkhnth',
- {'nifty': 87}, {'field': 'yes', 'morefield': False} ]
-
- expect = textwrap.dedent("""\
- [
- \t[
- \t\t"blorpie"
- \t],
- \t[
- \t\t"whoops"
- \t],
- \t[],
- \t"d-shtaeou",
- \t"d-nthiouh",
- \t"i-vhbjkhnth",
- \t{
- \t\t"nifty": 87
- \t},
- \t{
- \t\t"field": "yes",
- \t\t"morefield": false
- \t}
- ]""")
-
-
- d1 = json.dumps(h)
- d2 = json.dumps(h, indent='\t', sort_keys=True, separators=(',', ': '))
- d3 = json.dumps(h, indent=' ', sort_keys=True, separators=(',', ': '))
- d4 = json.dumps(h, indent=2, sort_keys=True, separators=(',', ': '))
-
- h1 = json.loads(d1)
- h2 = json.loads(d2)
- h3 = json.loads(d3)
- h4 = json.loads(d4)
-
- self.assertEquals(h1, h)
- self.assertEquals(h2, h)
- self.assertEquals(h3, h)
- self.assertEquals(h4, h)
- self.assertEquals(d3, expect.replace('\t', ' '))
- self.assertEquals(d4, expect.replace('\t', ' '))
- # NOTE: Python 2.4 textwrap.dedent converts tabs to spaces,
- # so the following is expected to fail. Python 2.4 is not a
- # supported platform in simplejson 2.1.0+.
- self.assertEquals(d2, expect)
-
- def test_indent0(self):
- h = {3: 1}
- def check(indent, expected):
- d1 = json.dumps(h, indent=indent)
- self.assertEquals(d1, expected)
-
- sio = StringIO()
- json.dump(h, sio, indent=indent)
- self.assertEquals(sio.getvalue(), expected)
-
- # indent=0 should emit newlines
- check(0, '{\n"3": 1\n}')
- # indent=None is more compact
- check(None, '{"3": 1}')
diff --git a/simplejson/tests/test_pass1.py b/simplejson/tests/test_pass1.py
deleted file mode 100644
index c3d6302d68dc58652f8dc178e4e8092a08e46093..0000000000000000000000000000000000000000
--- a/simplejson/tests/test_pass1.py
+++ /dev/null
@@ -1,76 +0,0 @@
-from unittest import TestCase
-
-import simplejson as json
-
-# from http://json.org/JSON_checker/test/pass1.json
-JSON = r'''
-[
- "JSON Test Pattern pass1",
- {"object with 1 member":["array with 1 element"]},
- {},
- [],
- -42,
- true,
- false,
- null,
- {
- "integer": 1234567890,
- "real": -9876.543210,
- "e": 0.123456789e-12,
- "E": 1.234567890E+34,
- "": 23456789012E666,
- "zero": 0,
- "one": 1,
- "space": " ",
- "quote": "\"",
- "backslash": "\\",
- "controls": "\b\f\n\r\t",
- "slash": "/ & \/",
- "alpha": "abcdefghijklmnopqrstuvwyz",
- "ALPHA": "ABCDEFGHIJKLMNOPQRSTUVWYZ",
- "digit": "0123456789",
- "special": "`1~!@#$%^&*()_+-={':[,]}|;.</>?",
- "hex": "\u0123\u4567\u89AB\uCDEF\uabcd\uef4A",
- "true": true,
- "false": false,
- "null": null,
- "array":[ ],
- "object":{ },
- "address": "50 St. James Street",
- "url": "http://www.JSON.org/",
- "comment": "// /* <!-- --",
- "# -- --> */": " ",
- " s p a c e d " :[1,2 , 3
-
-,
-
-4 , 5 , 6 ,7 ],
- "compact": [1,2,3,4,5,6,7],
- "jsontext": "{\"object with 1 member\":[\"array with 1 element\"]}",
- "quotes": "" \u0022 %22 0x22 034 "",
- "\/\\\"\uCAFE\uBABE\uAB98\uFCDE\ubcda\uef4A\b\f\n\r\t`1~!@#$%^&*()_+-=[]{}|;:',./<>?"
-: "A key can be any string"
- },
- 0.5 ,98.6
-,
-99.44
-,
-
-1066
-
-
-,"rosebud"]
-'''
-
-class TestPass1(TestCase):
- def test_parse(self):
- # test in/out equivalence and parsing
- res = json.loads(JSON)
- out = json.dumps(res)
- self.assertEquals(res, json.loads(out))
- try:
- json.dumps(res, allow_nan=False)
- except ValueError:
- pass
- else:
- self.fail("23456789012E666 should be out of range")
diff --git a/simplejson/tests/test_pass2.py b/simplejson/tests/test_pass2.py
deleted file mode 100644
index de4ee00bc60479c0e076a276ab85747d8419d860..0000000000000000000000000000000000000000
--- a/simplejson/tests/test_pass2.py
+++ /dev/null
@@ -1,14 +0,0 @@
-from unittest import TestCase
-import simplejson as json
-
-# from http://json.org/JSON_checker/test/pass2.json
-JSON = r'''
-[[[[[[[[[[[[[[[[[[["Not too deep"]]]]]]]]]]]]]]]]]]]
-'''
-
-class TestPass2(TestCase):
- def test_parse(self):
- # test in/out equivalence and parsing
- res = json.loads(JSON)
- out = json.dumps(res)
- self.assertEquals(res, json.loads(out))
diff --git a/simplejson/tests/test_pass3.py b/simplejson/tests/test_pass3.py
deleted file mode 100644
index f591aba983a476a6e552f7dc4895e35886705d04..0000000000000000000000000000000000000000
--- a/simplejson/tests/test_pass3.py
+++ /dev/null
@@ -1,20 +0,0 @@
-from unittest import TestCase
-
-import simplejson as json
-
-# from http://json.org/JSON_checker/test/pass3.json
-JSON = r'''
-{
- "JSON Test Pattern pass3": {
- "The outermost value": "must be an object or array.",
- "In this test": "It is an object."
- }
-}
-'''
-
-class TestPass3(TestCase):
- def test_parse(self):
- # test in/out equivalence and parsing
- res = json.loads(JSON)
- out = json.dumps(res)
- self.assertEquals(res, json.loads(out))
diff --git a/simplejson/tests/test_recursion.py b/simplejson/tests/test_recursion.py
deleted file mode 100644
index 83a1d887f42e804668c74c315d8f974501d6f2e6..0000000000000000000000000000000000000000
--- a/simplejson/tests/test_recursion.py
+++ /dev/null
@@ -1,67 +0,0 @@
-from unittest import TestCase
-
-import simplejson as json
-
-class JSONTestObject:
- pass
-
-
-class RecursiveJSONEncoder(json.JSONEncoder):
- recurse = False
- def default(self, o):
- if o is JSONTestObject:
- if self.recurse:
- return [JSONTestObject]
- else:
- return 'JSONTestObject'
- return json.JSONEncoder.default(o)
-
-
-class TestRecursion(TestCase):
- def test_listrecursion(self):
- x = []
- x.append(x)
- try:
- json.dumps(x)
- except ValueError:
- pass
- else:
- self.fail("didn't raise ValueError on list recursion")
- x = []
- y = [x]
- x.append(y)
- try:
- json.dumps(x)
- except ValueError:
- pass
- else:
- self.fail("didn't raise ValueError on alternating list recursion")
- y = []
- x = [y, y]
- # ensure that the marker is cleared
- json.dumps(x)
-
- def test_dictrecursion(self):
- x = {}
- x["test"] = x
- try:
- json.dumps(x)
- except ValueError:
- pass
- else:
- self.fail("didn't raise ValueError on dict recursion")
- x = {}
- y = {"a": x, "b": x}
- # ensure that the marker is cleared
- json.dumps(y)
-
- def test_defaultrecursion(self):
- enc = RecursiveJSONEncoder()
- self.assertEquals(enc.encode(JSONTestObject), '"JSONTestObject"')
- enc.recurse = True
- try:
- enc.encode(JSONTestObject)
- except ValueError:
- pass
- else:
- self.fail("didn't raise ValueError on default recursion")
diff --git a/simplejson/tests/test_scanstring.py b/simplejson/tests/test_scanstring.py
deleted file mode 100644
index a7fcd468085c8a017d21ef04cf04da9233790ac2..0000000000000000000000000000000000000000
--- a/simplejson/tests/test_scanstring.py
+++ /dev/null
@@ -1,117 +0,0 @@
-import sys
-from unittest import TestCase
-
-import simplejson as json
-import simplejson.decoder
-
-class TestScanString(TestCase):
- def test_py_scanstring(self):
- self._test_scanstring(simplejson.decoder.py_scanstring)
-
- def test_c_scanstring(self):
- if not simplejson.decoder.c_scanstring:
- return
- self._test_scanstring(simplejson.decoder.c_scanstring)
-
- def _test_scanstring(self, scanstring):
- self.assertEquals(
- scanstring('"z\\ud834\\udd20x"', 1, None, True),
- (u'z\U0001d120x', 16))
-
- if sys.maxunicode == 65535:
- self.assertEquals(
- scanstring(u'"z\U0001d120x"', 1, None, True),
- (u'z\U0001d120x', 6))
- else:
- self.assertEquals(
- scanstring(u'"z\U0001d120x"', 1, None, True),
- (u'z\U0001d120x', 5))
-
- self.assertEquals(
- scanstring('"\\u007b"', 1, None, True),
- (u'{', 8))
-
- self.assertEquals(
- scanstring('"A JSON payload should be an object or array, not a string."', 1, None, True),
- (u'A JSON payload should be an object or array, not a string.', 60))
-
- self.assertEquals(
- scanstring('["Unclosed array"', 2, None, True),
- (u'Unclosed array', 17))
-
- self.assertEquals(
- scanstring('["extra comma",]', 2, None, True),
- (u'extra comma', 14))
-
- self.assertEquals(
- scanstring('["double extra comma",,]', 2, None, True),
- (u'double extra comma', 21))
-
- self.assertEquals(
- scanstring('["Comma after the close"],', 2, None, True),
- (u'Comma after the close', 24))
-
- self.assertEquals(
- scanstring('["Extra close"]]', 2, None, True),
- (u'Extra close', 14))
-
- self.assertEquals(
- scanstring('{"Extra comma": true,}', 2, None, True),
- (u'Extra comma', 14))
-
- self.assertEquals(
- scanstring('{"Extra value after close": true} "misplaced quoted value"', 2, None, True),
- (u'Extra value after close', 26))
-
- self.assertEquals(
- scanstring('{"Illegal expression": 1 + 2}', 2, None, True),
- (u'Illegal expression', 21))
-
- self.assertEquals(
- scanstring('{"Illegal invocation": alert()}', 2, None, True),
- (u'Illegal invocation', 21))
-
- self.assertEquals(
- scanstring('{"Numbers cannot have leading zeroes": 013}', 2, None, True),
- (u'Numbers cannot have leading zeroes', 37))
-
- self.assertEquals(
- scanstring('{"Numbers cannot be hex": 0x14}', 2, None, True),
- (u'Numbers cannot be hex', 24))
-
- self.assertEquals(
- scanstring('[[[[[[[[[[[[[[[[[[[["Too deep"]]]]]]]]]]]]]]]]]]]]', 21, None, True),
- (u'Too deep', 30))
-
- self.assertEquals(
- scanstring('{"Missing colon" null}', 2, None, True),
- (u'Missing colon', 16))
-
- self.assertEquals(
- scanstring('{"Double colon":: null}', 2, None, True),
- (u'Double colon', 15))
-
- self.assertEquals(
- scanstring('{"Comma instead of colon", null}', 2, None, True),
- (u'Comma instead of colon', 25))
-
- self.assertEquals(
- scanstring('["Colon instead of comma": false]', 2, None, True),
- (u'Colon instead of comma', 25))
-
- self.assertEquals(
- scanstring('["Bad value", truth]', 2, None, True),
- (u'Bad value', 12))
-
- def test_issue3623(self):
- self.assertRaises(ValueError, json.decoder.scanstring, "xxx", 1,
- "xxx")
- self.assertRaises(UnicodeDecodeError,
- json.encoder.encode_basestring_ascii, "xx\xff")
-
- def test_overflow(self):
- # Python 2.5 does not have maxsize
- maxsize = getattr(sys, 'maxsize', sys.maxint)
- self.assertRaises(OverflowError, json.decoder.scanstring, "xxx",
- maxsize + 1)
-
diff --git a/simplejson/tests/test_separators.py b/simplejson/tests/test_separators.py
deleted file mode 100644
index cbda93cd9d7f6890dcbf18d04c5e350b3befa3fe..0000000000000000000000000000000000000000
--- a/simplejson/tests/test_separators.py
+++ /dev/null
@@ -1,42 +0,0 @@
-import textwrap
-from unittest import TestCase
-
-import simplejson as json
-
-
-class TestSeparators(TestCase):
- def test_separators(self):
- h = [['blorpie'], ['whoops'], [], 'd-shtaeou', 'd-nthiouh', 'i-vhbjkhnth',
- {'nifty': 87}, {'field': 'yes', 'morefield': False} ]
-
- expect = textwrap.dedent("""\
- [
- [
- "blorpie"
- ] ,
- [
- "whoops"
- ] ,
- [] ,
- "d-shtaeou" ,
- "d-nthiouh" ,
- "i-vhbjkhnth" ,
- {
- "nifty" : 87
- } ,
- {
- "field" : "yes" ,
- "morefield" : false
- }
- ]""")
-
-
- d1 = json.dumps(h)
- d2 = json.dumps(h, indent=' ', sort_keys=True, separators=(' ,', ' : '))
-
- h1 = json.loads(d1)
- h2 = json.loads(d2)
-
- self.assertEquals(h1, h)
- self.assertEquals(h2, h)
- self.assertEquals(d2, expect)
diff --git a/simplejson/tests/test_speedups.py b/simplejson/tests/test_speedups.py
deleted file mode 100644
index 825ecf26f949ce6ec412c13c3cb10d5f8b399564..0000000000000000000000000000000000000000
--- a/simplejson/tests/test_speedups.py
+++ /dev/null
@@ -1,20 +0,0 @@
-from unittest import TestCase
-
-from simplejson import encoder, scanner
-
-def has_speedups():
- return encoder.c_make_encoder is not None
-
-class TestDecode(TestCase):
- def test_make_scanner(self):
- if not has_speedups():
- return
- self.assertRaises(AttributeError, scanner.c_make_scanner, 1)
-
- def test_make_encoder(self):
- if not has_speedups():
- return
- self.assertRaises(TypeError, encoder.c_make_encoder,
- None,
- "\xCD\x7D\x3D\x4E\x12\x4C\xF9\x79\xD7\x52\xBA\x82\xF2\x27\x4A\x7D\xA0\xCA\x75",
- None)
diff --git a/simplejson/tests/test_unicode.py b/simplejson/tests/test_unicode.py
deleted file mode 100644
index f73e5bfa9700cd4b4cdfe40b8976cb6923234da6..0000000000000000000000000000000000000000
--- a/simplejson/tests/test_unicode.py
+++ /dev/null
@@ -1,99 +0,0 @@
-from unittest import TestCase
-
-import simplejson as json
-
-class TestUnicode(TestCase):
- def test_encoding1(self):
- encoder = json.JSONEncoder(encoding='utf-8')
- u = u'\N{GREEK SMALL LETTER ALPHA}\N{GREEK CAPITAL LETTER OMEGA}'
- s = u.encode('utf-8')
- ju = encoder.encode(u)
- js = encoder.encode(s)
- self.assertEquals(ju, js)
-
- def test_encoding2(self):
- u = u'\N{GREEK SMALL LETTER ALPHA}\N{GREEK CAPITAL LETTER OMEGA}'
- s = u.encode('utf-8')
- ju = json.dumps(u, encoding='utf-8')
- js = json.dumps(s, encoding='utf-8')
- self.assertEquals(ju, js)
-
- def test_encoding3(self):
- u = u'\N{GREEK SMALL LETTER ALPHA}\N{GREEK CAPITAL LETTER OMEGA}'
- j = json.dumps(u)
- self.assertEquals(j, '"\\u03b1\\u03a9"')
-
- def test_encoding4(self):
- u = u'\N{GREEK SMALL LETTER ALPHA}\N{GREEK CAPITAL LETTER OMEGA}'
- j = json.dumps([u])
- self.assertEquals(j, '["\\u03b1\\u03a9"]')
-
- def test_encoding5(self):
- u = u'\N{GREEK SMALL LETTER ALPHA}\N{GREEK CAPITAL LETTER OMEGA}'
- j = json.dumps(u, ensure_ascii=False)
- self.assertEquals(j, u'"' + u + u'"')
-
- def test_encoding6(self):
- u = u'\N{GREEK SMALL LETTER ALPHA}\N{GREEK CAPITAL LETTER OMEGA}'
- j = json.dumps([u], ensure_ascii=False)
- self.assertEquals(j, u'["' + u + u'"]')
-
- def test_big_unicode_encode(self):
- u = u'\U0001d120'
- self.assertEquals(json.dumps(u), '"\\ud834\\udd20"')
- self.assertEquals(json.dumps(u, ensure_ascii=False), u'"\U0001d120"')
-
- def test_big_unicode_decode(self):
- u = u'z\U0001d120x'
- self.assertEquals(json.loads('"' + u + '"'), u)
- self.assertEquals(json.loads('"z\\ud834\\udd20x"'), u)
-
- def test_unicode_decode(self):
- for i in range(0, 0xd7ff):
- u = unichr(i)
- #s = '"\\u{0:04x}"'.format(i)
- s = '"\\u%04x"' % (i,)
- self.assertEquals(json.loads(s), u)
-
- def test_object_pairs_hook_with_unicode(self):
- s = u'{"xkd":1, "kcw":2, "art":3, "hxm":4, "qrt":5, "pad":6, "hoy":7}'
- p = [(u"xkd", 1), (u"kcw", 2), (u"art", 3), (u"hxm", 4),
- (u"qrt", 5), (u"pad", 6), (u"hoy", 7)]
- self.assertEqual(json.loads(s), eval(s))
- self.assertEqual(json.loads(s, object_pairs_hook=lambda x: x), p)
- od = json.loads(s, object_pairs_hook=json.OrderedDict)
- self.assertEqual(od, json.OrderedDict(p))
- self.assertEqual(type(od), json.OrderedDict)
- # the object_pairs_hook takes priority over the object_hook
- self.assertEqual(json.loads(s,
- object_pairs_hook=json.OrderedDict,
- object_hook=lambda x: None),
- json.OrderedDict(p))
-
-
- def test_default_encoding(self):
- self.assertEquals(json.loads(u'{"a": "\xe9"}'.encode('utf-8')),
- {'a': u'\xe9'})
-
- def test_unicode_preservation(self):
- self.assertEquals(type(json.loads(u'""')), unicode)
- self.assertEquals(type(json.loads(u'"a"')), unicode)
- self.assertEquals(type(json.loads(u'["a"]')[0]), unicode)
-
- def test_ensure_ascii_false_returns_unicode(self):
- # http://code.google.com/p/simplejson/issues/detail?id=48
- self.assertEquals(type(json.dumps([], ensure_ascii=False)), unicode)
- self.assertEquals(type(json.dumps(0, ensure_ascii=False)), unicode)
- self.assertEquals(type(json.dumps({}, ensure_ascii=False)), unicode)
- self.assertEquals(type(json.dumps("", ensure_ascii=False)), unicode)
-
- def test_ensure_ascii_false_bytestring_encoding(self):
- # http://code.google.com/p/simplejson/issues/detail?id=48
- doc1 = {u'quux': 'Arr\xc3\xaat sur images'}
- doc2 = {u'quux': u'Arr\xeat sur images'}
- doc_ascii = '{"quux": "Arr\\u00eat sur images"}'
- doc_unicode = u'{"quux": "Arr\xeat sur images"}'
- self.assertEquals(json.dumps(doc1), doc_ascii)
- self.assertEquals(json.dumps(doc2), doc_ascii)
- self.assertEquals(json.dumps(doc1, ensure_ascii=False), doc_unicode)
- self.assertEquals(json.dumps(doc2, ensure_ascii=False), doc_unicode)
diff --git a/simplejson/tool.py b/simplejson/tool.py
deleted file mode 100644
index 73370db55ed37b7f290fcd69fb8b8ee4df460879..0000000000000000000000000000000000000000
--- a/simplejson/tool.py
+++ /dev/null
@@ -1,39 +0,0 @@
-r"""Command-line tool to validate and pretty-print JSON
-
-Usage::
-
- $ echo '{"json":"obj"}' | python -m simplejson.tool
- {
- "json": "obj"
- }
- $ echo '{ 1.2:3.4}' | python -m simplejson.tool
- Expecting property name: line 1 column 2 (char 2)
-
-"""
-import sys
-import simplejson as json
-
-def main():
- if len(sys.argv) == 1:
- infile = sys.stdin
- outfile = sys.stdout
- elif len(sys.argv) == 2:
- infile = open(sys.argv[1], 'rb')
- outfile = sys.stdout
- elif len(sys.argv) == 3:
- infile = open(sys.argv[1], 'rb')
- outfile = open(sys.argv[2], 'wb')
- else:
- raise SystemExit(sys.argv[0] + " [infile [outfile]]")
- try:
- obj = json.load(infile,
- object_pairs_hook=json.OrderedDict,
- use_decimal=True)
- except ValueError, e:
- raise SystemExit(e)
- json.dump(obj, outfile, sort_keys=True, indent=' ', use_decimal=True)
- outfile.write('\n')
-
-
-if __name__ == '__main__':
- main()