Add AST and parser tests

This commit is contained in:
Kenn Knowles 2013-02-09 00:30:42 -05:00
parent 9c88079576
commit 08c7fc9fcf
6 changed files with 740 additions and 0 deletions

202
LICENSE Normal file
View File

@ -0,0 +1,202 @@
Apache License
Version 2.0, January 2004
http://www.apache.org/licenses/
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
1. Definitions.
"License" shall mean the terms and conditions for use, reproduction,
and distribution as defined by Sections 1 through 9 of this document.
"Licensor" shall mean the copyright owner or entity authorized by
the copyright owner that is granting the License.
"Legal Entity" shall mean the union of the acting entity and all
other entities that control, are controlled by, or are under common
control with that entity. For the purposes of this definition,
"control" means (i) the power, direct or indirect, to cause the
direction or management of such entity, whether by contract or
otherwise, or (ii) ownership of fifty percent (50%) or more of the
outstanding shares, or (iii) beneficial ownership of such entity.
"You" (or "Your") shall mean an individual or Legal Entity
exercising permissions granted by this License.
"Source" form shall mean the preferred form for making modifications,
including but not limited to software source code, documentation
source, and configuration files.
"Object" form shall mean any form resulting from mechanical
transformation or translation of a Source form, including but
not limited to compiled object code, generated documentation,
and conversions to other media types.
"Work" shall mean the work of authorship, whether in Source or
Object form, made available under the License, as indicated by a
copyright notice that is included in or attached to the work
(an example is provided in the Appendix below).
"Derivative Works" shall mean any work, whether in Source or Object
form, that is based on (or derived from) the Work and for which the
editorial revisions, annotations, elaborations, or other modifications
represent, as a whole, an original work of authorship. For the purposes
of this License, Derivative Works shall not include works that remain
separable from, or merely link (or bind by name) to the interfaces of,
the Work and Derivative Works thereof.
"Contribution" shall mean any work of authorship, including
the original version of the Work and any modifications or additions
to that Work or Derivative Works thereof, that is intentionally
submitted to Licensor for inclusion in the Work by the copyright owner
or by an individual or Legal Entity authorized to submit on behalf of
the copyright owner. For the purposes of this definition, "submitted"
means any form of electronic, verbal, or written communication sent
to the Licensor or its representatives, including but not limited to
communication on electronic mailing lists, source code control systems,
and issue tracking systems that are managed by, or on behalf of, the
Licensor for the purpose of discussing and improving the Work, but
excluding communication that is conspicuously marked or otherwise
designated in writing by the copyright owner as "Not a Contribution."
"Contributor" shall mean Licensor and any individual or Legal Entity
on behalf of whom a Contribution has been received by Licensor and
subsequently incorporated within the Work.
2. Grant of Copyright License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
copyright license to reproduce, prepare Derivative Works of,
publicly display, publicly perform, sublicense, and distribute the
Work and such Derivative Works in Source or Object form.
3. Grant of Patent License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
(except as stated in this section) patent license to make, have made,
use, offer to sell, sell, import, and otherwise transfer the Work,
where such license applies only to those patent claims licensable
by such Contributor that are necessarily infringed by their
Contribution(s) alone or by combination of their Contribution(s)
with the Work to which such Contribution(s) was submitted. If You
institute patent litigation against any entity (including a
cross-claim or counterclaim in a lawsuit) alleging that the Work
or a Contribution incorporated within the Work constitutes direct
or contributory patent infringement, then any patent licenses
granted to You under this License for that Work shall terminate
as of the date such litigation is filed.
4. Redistribution. You may reproduce and distribute copies of the
Work or Derivative Works thereof in any medium, with or without
modifications, and in Source or Object form, provided that You
meet the following conditions:
(a) You must give any other recipients of the Work or
Derivative Works a copy of this License; and
(b) You must cause any modified files to carry prominent notices
stating that You changed the files; and
(c) You must retain, in the Source form of any Derivative Works
that You distribute, all copyright, patent, trademark, and
attribution notices from the Source form of the Work,
excluding those notices that do not pertain to any part of
the Derivative Works; and
(d) If the Work includes a "NOTICE" text file as part of its
distribution, then any Derivative Works that You distribute must
include a readable copy of the attribution notices contained
within such NOTICE file, excluding those notices that do not
pertain to any part of the Derivative Works, in at least one
of the following places: within a NOTICE text file distributed
as part of the Derivative Works; within the Source form or
documentation, if provided along with the Derivative Works; or,
within a display generated by the Derivative Works, if and
wherever such third-party notices normally appear. The contents
of the NOTICE file are for informational purposes only and
do not modify the License. You may add Your own attribution
notices within Derivative Works that You distribute, alongside
or as an addendum to the NOTICE text from the Work, provided
that such additional attribution notices cannot be construed
as modifying the License.
You may add Your own copyright statement to Your modifications and
may provide additional or different license terms and conditions
for use, reproduction, or distribution of Your modifications, or
for any such Derivative Works as a whole, provided Your use,
reproduction, and distribution of the Work otherwise complies with
the conditions stated in this License.
5. Submission of Contributions. Unless You explicitly state otherwise,
any Contribution intentionally submitted for inclusion in the Work
by You to the Licensor shall be under the terms and conditions of
this License, without any additional terms or conditions.
Notwithstanding the above, nothing herein shall supersede or modify
the terms of any separate license agreement you may have executed
with Licensor regarding such Contributions.
6. Trademarks. This License does not grant permission to use the trade
names, trademarks, service marks, or product names of the Licensor,
except as required for reasonable and customary use in describing the
origin of the Work and reproducing the content of the NOTICE file.
7. Disclaimer of Warranty. Unless required by applicable law or
agreed to in writing, Licensor provides the Work (and each
Contributor provides its Contributions) on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
implied, including, without limitation, any warranties or conditions
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
PARTICULAR PURPOSE. You are solely responsible for determining the
appropriateness of using or redistributing the Work and assume any
risks associated with Your exercise of permissions under this License.
8. Limitation of Liability. In no event and under no legal theory,
whether in tort (including negligence), contract, or otherwise,
unless required by applicable law (such as deliberate and grossly
negligent acts) or agreed to in writing, shall any Contributor be
liable to You for damages, including any direct, indirect, special,
incidental, or consequential damages of any character arising as a
result of this License or out of the use or inability to use the
Work (including but not limited to damages for loss of goodwill,
work stoppage, computer failure or malfunction, or any and all
other commercial damages or losses), even if such Contributor
has been advised of the possibility of such damages.
9. Accepting Warranty or Additional Liability. While redistributing
the Work or Derivative Works thereof, You may choose to offer,
and charge a fee for, acceptance of support, warranty, indemnity,
or other liability obligations and/or rights consistent with this
License. However, in accepting such obligations, You may act only
on Your own behalf and on Your sole responsibility, not on behalf
of any other Contributor, and only if You agree to indemnify,
defend, and hold each Contributor harmless for any liability
incurred by, or claims asserted against, such Contributor by reason
of your accepting any such warranty or additional liability.
END OF TERMS AND CONDITIONS
APPENDIX: How to apply the Apache License to your work.
To apply the Apache License to your work, attach the following
boilerplate notice, with the fields enclosed by brackets "[]"
replaced with your own identifying information. (Don't include
the brackets!) The text should be enclosed in the appropriate
comment syntax for the file format. We also recommend that a
file or class name and description of purpose be included on the
same "printed page" as the copyright notice for easier
identification within third-party archives.
Copyright [yyyy] [name of copyright owner]
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.

2
jsonpath_rw/__init__.py Normal file
View File

@ -0,0 +1,2 @@
from jsonpath import *
from parser import parse

283
jsonpath_rw/jsonpath.py Normal file
View File

@ -0,0 +1,283 @@
import logging
from itertools import *
logger = logging.getLogger(__name__)
class JSONPath(object):
"""
The base class for JSONPath abstract syntax; those
methods stubbed here are the interface to supported
JSONPath semantics.
"""
def find(self, data):
"All JSONPath"
raise NotImplementedError()
def update(self, data, val):
"Returns `data` with the specified path replaced by `val`"
raise NotImplementedError()
class Root(JSONPath):
"""
The JSONPath referring to the root object. Concrete syntax is '$'.
WARNING! Currently synonymous with '@' because this library does not
keep track of parent pointers or any such thing.
"""
def find(self, data):
return [data]
def update(self, data, val):
return val
def __str__(self):
return '$'
class This(JSONPath):
"""
The JSONPath referring to the current datum. Concrete syntax is '@'.
"""
def find(self, data):
return [data]
def update(self, data, val):
return val
def __str__(self):
return '@'
class Child(JSONPath):
"""
JSONPath that first matches the left, then the right.
Concrete syntax is <left> '.' <right>
"""
def __init__(self, left, right):
self.left = left
self.right = right
def find(self, data):
return chain(*[self.right.find(subdata) for subdata in self.left.find(data)])
def __eq__(self, other):
return isinstance(other, Child) and self.left == other.left and self.right == other.right
def __str__(self):
return '%s.%s' % (self.left, self.right)
class Where(JSONPath):
"""
JSONPath that first matches the left, and then
filters for only those nodes that have
a match on the right.
WARNING: Subject to change. May want to have "contains"
or some other better word for it.
"""
def __init__(self, left, right):
self.left = left
self.right = right
def find(self, data):
return [subdata for subdata in self.left.find(data) if self.right.find(data)]
def __str__(self):
return '%s where %s' % (self.left, self.right)
def __eq__(self, other):
return isinstance(other, Where) and other.left == self.left and other.right == self.right
class Descendants(JSONPath):
"""
JSONPath that matches first the left expression then any descendant
of it which matches the right expression.
"""
def __init__(self, left, right):
self.left = left
self.right = right
def find(self, data):
# <left> .. <right> ==> <left> . (<right> | *..<right> | [*]..<right>)
#
# With with a wonky caveat that since Slice() has funky coercions
# we cannot just delegate to that equivalence or we'll hit an
# infinite loop. So right here we implement the coercion-free version.
# Get all left matches into a list
left_matches = self.left.find(data)
if not isinstance(left_matches, list):
left_matches = [left_matches]
def match_recursively(data):
right_matches = self.right.find(data)
# Manually do the * or [*] to avoid coercion and recurse just the right-hand pattern
if isinstance(data, list):
recursive_matches = chain(*[match_recursively(subdata) for subdata in data])
elif isinstance(data, dict):
recursive_matches = chain(*[match_recursively(subdata) for subdata in data.values()])
else:
recursive_matches = []
return right_matches + list(recursive_matches)
# TODO: repeatable iterator instead of list?
return list(chain(*[match_recursively(left_match) for left_match in left_matches]))
def is_singular():
return False
def __str__(self):
return '%s..%s' % (self.left, self.right)
def __eq__(self, other):
return isinstance(other, Descendants) and self.left == other.left and self.right == other.right
class Union(JSONPath):
"""
JSONPath that returns the union of the results of each match.
This is pretty shoddily implemented for now. The nicest semantics
in case of mismatched bits (list vs atomic) is to put
them all in a list, but I haven't done that yet.
WARNING: Any appearance of this being the _concatenation_ is
coincidence. It may even be a bug! (or laziness)
"""
def __init__(self, left, right):
self.left = left
self.right = right
def is_singular(self):
return False
def find(self, data):
return self.left.find(data) + self.right.find(data)
class Intersect(JSONPath):
"""
JSONPath for bits that match *both* patterns.
This can be accomplished a couple of ways. The most
efficient is to actually build the intersected
AST as in building a state machine for matching the
intersection of regular languages. The next
idea is to build a filtered data and match against
that.
"""
def __init__(self, left, right):
self.left = left
self.right = right
def is_singular(self):
return False
def find(self, data):
raise NotImplementedError()
class Fields(JSONPath):
"""
JSONPath referring to some field of the current object.
Concrete syntax ix comma-separated field names.
WARNING: If '*' is any of the field names, then they will
all be returned.
"""
def __init__(self, *fields):
self.fields = fields
def safe_get(self, val, field):
try:
return val.get(field)
except AttributeError:
return None
def find(self, data):
if '*' in self.fields:
try:
return data.values()
except AttributeError:
return []
else:
return filter(lambda x: x != None, [self.safe_get(data, field) for field in self.fields])
def __str__(self):
return ','.join(self.fields)
def __eq__(self, other):
return isinstance(other, Fields) and self.fields == other.fields
class Index(JSONPath):
"""
JSONPath that matches indices of the current datum, or none if not large enough.
Concrete syntax is brackets.
WARNING: If the datum is not long enough, it will not crash but will not match anything.
NOTE: For the concrete syntax of `[*]`, the abstract syntax is a Slice() with no parameters (equiv to `[:]`
"""
# TODO: multiple and/or range slices
def __init__(self, index):
self.index = index
def find(self, data):
if len(data) > self.index:
return [data[self.index]]
else:
return []
def __eq__(self, other):
return isinstance(other, Index) and self.index == other.index
class Slice(JSONPath):
"""
JSONPath matching a slice of an array.
Because of a mismatch between JSON and XML when schema-unaware,
this always returns an iterable; if the incoming data
was not a list, then it returns a one element list _containing_ that
data.
Consider these two docs, and their schema-unaware translation to JSON:
<a><b>hello</b></a> ==> {"a": {"b": "hello"}}
<a><b>hello</b><b>goodbye</b></a> ==> {"a": {"b": ["hello", "goodbye"]}}
If there were a schema, it would be known that "b" should always be an
array (unless the schema were wonky, but that is too much to fix here)
so when querying with JSON if the one writing the JSON knows that it
should be an array, they can write a slice operator and it will coerce
a non-array value to an array.
This may be a bit unfortunate because it would be nice to always have
an iterator, but dictionaries and other objects may also be iterable,
so this is the compromise.
"""
def __init__(self, start=None, end=None, step=None):
self.start = start
self.end = end
self.step = step
def find(self, data):
# Here's the hack. If not a list, try again as though it were.
if not isinstance(data, list):
return self.find([data])
return data[self.start:self.end:self.step]
def __str__(self):
if self.start == None and self.end == None and self.step == None:
return '[*]'
else:
return '[%s%s%s]' % (self.start or '',
':%d'%self.end if self.end else '',
':%d'%self.step if self.step else '')
def __eq__(self, other):
return isinstance(other, Slice) and other.start == self.start and self.end == other.end and other.step == self.step

174
jsonpath_rw/parser.py Normal file
View File

@ -0,0 +1,174 @@
import sys
import os.path
import logging
import ply.yacc
from jsonpath_rw.jsonpath import *
from jsonpath_rw.lexer import JsonPathLexer
logger = logging.getLogger(__name__)
def parse(string):
return JsonPathParser().parse(string)
class JsonPathParser(object):
tokens = JsonPathLexer.tokens
def __init__(self, debug=False, lexer_class=None):
self.debug = debug
self.lexer_class = lexer_class or JsonPathLexer # Crufty but works around statefulness in PLY
def parse(self, string, lexer = None):
lexer = lexer or self.lexer_class()
return self.parse_token_stream(lexer.tokenize(string))
def parse_token_stream(self, token_iterator, start_symbol='jsonpath'):
# Since PLY has some crufty aspects and dumps files, we try to keep them local
# However, we need to derive the name of the output Python file :-/
output_directory = os.path.dirname(__file__)
try:
module_name = os.path.splitext(os.path.split(__file__)[1])[0]
except:
module_name = __name__
parsing_table_module = '_'.join([module_name, start_symbol, 'parsetab'])
# And we regenerate the parse table every time; it doesn't actually take that long!
new_parser = ply.yacc.yacc(module=self,
debug=self.debug,
tabmodule = parsing_table_module,
outputdir = output_directory,
write_tables=0,
start = start_symbol,
errorlog = logger)
return new_parser.parse(lexer = IteratorToTokenStream(token_iterator))
# ===================== PLY Parser specification =====================
precedence = [
('left', ','),
('left', 'DOUBLEDOT'),
('left', '.'),
('left', '|'),
('left', '&'),
('left', 'WHERE'),
]
def p_error(self, t):
raise Exception('Parse error at %s:%s near token %s (%s)' % (t.lineno, t.col, t.value, t.type))
def p_jsonpath_binop(self, p):
"""jsonpath : jsonpath '.' jsonpath
| jsonpath DOUBLEDOT jsonpath
| jsonpath WHERE jsonpath
| jsonpath '|' jsonpath
| jsonpath '&' jsonpath"""
op = p[2]
if op == '.':
p[0] = Child(p[1], p[3])
elif op == '..':
p[0] = Descendants(p[1], p[3])
elif op == 'where':
p[0] = Where(p[1], p[3])
elif op == '|':
p[0] = Union(p[1], p[3])
elif op == '&':
p[0] = Intersect(p[1], p[3])
def p_jsonpath_fields(self, p):
"jsonpath : fields_or_any"
p[0] = Fields(*p[1])
def p_jsonpath_this(self, p):
"jsonpath : '@'"
p[0] = This()
def p_jsonpath_root(self, p):
"jsonpath : '$'"
p[0] = Root()
def p_jsonpath_idx(self, p):
"jsonpath : '[' idx ']'"
p[0] = p[2]
def p_jsonpath_slice(self, p):
"jsonpath : '[' slice ']'"
p[0] = p[2]
def p_jsonpath_fieldbrackets(self, p):
"jsonpath : '[' fields ']'"
p[0] = Fields(*p[2])
def p_jsonpath_child_fieldbrackets(self, p):
"jsonpath : jsonpath '[' fields ']'"
p[0] = Child(p[1], Fields(*p[3]))
def p_jsonpath_child_idxbrackets(self, p):
"jsonpath : jsonpath '[' idx ']'"
p[0] = Child(p[1], p[3])
def p_jsonpath_child_slicebrackets(self, p):
"jsonpath : jsonpath '[' slice ']'"
p[0] = Child(p[1], p[3])
def p_jsonpath_parens(self, p):
"jsonpath : '(' jsonpath ')'"
p[0] = p[2]
# Because fields in brackets cannot be '*' - that is reserved for array indices
def p_fields_or_any(self, p):
"""fields_or_any : fields
| '*' """
if p[1] == '*':
p[0] = ['*']
else:
p[0] = p[1]
def p_fields_id(self, p):
"fields : ID"
p[0] = [p[1]]
def p_fields_comma(self, p):
"fields : fields ',' fields"
p[0] = p[1] + p[3]
def p_idx(self, p):
"idx : NUMBER"
p[0] = Index(p[1])
def p_slice_any(self, p):
"slice : '*'"
p[0] = Slice()
def p_slice(self, p): # Currently does not support `step`
"slice : maybe_int ':' maybe_int"
p[0] = Slice(start=p[1], end=p[3])
def p_maybe_int(self, p):
"""maybe_int : NUMBER
| empty"""
p[0] = p[1]
def p_empty(self, p):
'empty :'
p[0] = None
class IteratorToTokenStream(object):
def __init__(self, iterator):
self.iterator = iterator
def token(self):
try:
return self.iterator.next()
except StopIteration:
return None
if __name__ == '__main__':
logging.basicConfig()
parser = JsonPathParser(debug=True)
print parser.parse(sys.stdin.read())

42
tests/test_jsonpath.py Normal file
View File

@ -0,0 +1,42 @@
import unittest
from jsonpath_rw.parser import parse
from jsonpath_rw.jsonpath import *
class TestJsonPath(unittest.TestCase):
@classmethod
def setup_class(cls):
logging.basicConfig()
def check_cases(self, test_cases):
# Note that just manually building an AST would avoid this dep and isolate the tests, but that would suck a bit
# Also, we coerce iterables, etc, into the desired target type
for string, data, target in test_cases:
print 'parse("%s").find(%s) =?= %s' % (string, data, target)
result = parse(string).find(data)
if isinstance(target, list):
assert list(result) == target
else:
assert result == target
def test_fields(self):
self.check_cases([ ('foo', {'foo': 'baz'}, ['baz']),
('foo,baz', {'foo': 1, 'baz': 2}, [1, 2]),
('*', {'foo': 1, 'baz': 2}, [1, 2]) ])
def test_index(self):
self.check_cases([('[0]', [42], [42]),
('[2]', [34, 65, 29, 59], [29])])
def test_slice(self):
self.check_cases([('[*]', [1, 2, 3], [1, 2, 3]),
('[1:]', [1, 2, 3, 4], [2, 3, 4]),
('[:2]', [1, 2, 3, 4], [1, 2])])
def test_child(self):
self.check_cases([('foo.baz', {'foo': {'baz': 3}}, [3]),
('foo.baz.bizzle', {'foo': {'baz': {'bizzle': 5}}}, [5])])
def test_descendants(self):
self.check_cases([('foo..baz', {'foo': {'baz': 1, 'bing': {'baz': 2}}}, [1, 2] )])

37
tests/test_parser.py Normal file
View File

@ -0,0 +1,37 @@
import unittest
from jsonpath_rw.lexer import JsonPathLexer
from jsonpath_rw.parser import JsonPathParser
from jsonpath_rw.jsonpath import *
class TestParser(unittest.TestCase):
# TODO: This will be much more effective with a few regression tests and `arbitrary` parse . pretty testing
@classmethod
def setup_class(cls):
logging.basicConfig()
def check_parse_cases(self, test_cases):
parser = JsonPathParser(debug=True, lexer_class=lambda:JsonPathLexer(debug=False)) # Note that just manually passing token streams avoids this dep, but that sucks
for string, parsed in test_cases:
print string, '=?=', parsed # pytest captures this and we see it only on a failure, for debugging
assert parser.parse(string) == parsed
def test_atomic(self):
self.check_parse_cases([('foo', Fields('foo')),
('*', Fields('*')),
('baz,bizzle', Fields('baz','bizzle')),
('[1]', Index(1)),
('[1:]', Slice(start=1)),
('[:]', Slice()),
('[*]', Slice()),
('[:2]', Slice(end=2)),
('[1:2]', Slice(start=1, end=2))])
def test_nested(self):
self.check_parse_cases([('foo.baz', Child(Fields('foo'), Fields('baz'))),
('foo.baz,bizzle', Child(Fields('foo'), Fields('baz', 'bizzle'))),
('foo where baz', Where(Fields('foo'), Fields('baz'))),
('foo..baz', Descendants(Fields('foo'), Fields('baz'))),
('foo..baz.bing', Descendants(Fields('foo'), Child(Fields('baz'), Fields('bing'))))])