Rietveld Code Review Tool
Help | Bug tracker | Discussion group | Source code | Sign in
(159)

Unified Diff: Lib/json/decoder.py

Issue 7311: [issue4136] merge json library with simplejson 2.0.3 Base URL: http://svn.python.org/view/*checkout*/python/trunk/
Patch Set: Created 5 years, 6 months ago , Downloaded from: http://bugs.python.org/file11822/json_issue4136_r66961.diff
Use n/p to move between diff chunks; N/P to move between comments. Please Sign in to add in-line comments.
Jump to:
View side-by-side diff with in-line comments
Download patch
« no previous file with comments | « Lib/json/__init__.py ('k') | Lib/json/encoder.py » ('j') | Modules/_json.c » ('J')
Expand Comments ('e') | Collapse Comments ('c') | Show Comments Hide Comments ('s')
Index: Lib/json/decoder.py
===================================================================
--- Lib/json/decoder.py (revision 66961)
+++ Lib/json/decoder.py (working copy)
@@ -3,8 +3,9 @@
import re
import sys
+import struct
-from json.scanner import Scanner, pattern
+from json.scanner import make_scanner
try:
from _json import scanstring as c_scanstring
except ImportError:
@@ -40,36 +41,8 @@
'-Infinity': NegInf,
'Infinity': PosInf,
'NaN': NaN,
- 'true': True,
- 'false': False,
- 'null': None,
}
-
-def JSONConstant(match, context, c=_CONSTANTS):
- s = match.group(0)
- fn = getattr(context, 'parse_constant', None)
- if fn is None:
- rval = c[s]
- else:
- rval = fn(s)
- return rval, None
-pattern('(-?Infinity|NaN|true|false|null)')(JSONConstant)
-
-
-def JSONNumber(match, context):
- match = JSONNumber.regex.match(match.string, *match.span())
- integer, frac, exp = match.groups()
- if frac or exp:
- fn = getattr(context, 'parse_float', None) or float
- res = fn(integer + (frac or '') + (exp or ''))
- else:
- fn = getattr(context, 'parse_int', None) or int
- res = fn(integer)
- return res, None
-pattern(r'(-?(?:0|[1-9]\d*))(\.\d+)?([eE][-+]?\d+)?')(JSONNumber)
-
-
STRINGCHUNK = re.compile(r'(.*?)(["\\\x00-\x1f])', FLAGS)
BACKSLASH = {
'"': u'"', '\\': u'\\', '/': u'/',
@@ -100,7 +73,7 @@
break
elif terminator != '\\':
if strict:
- msg = "Invalid control character {0!r} at".format(terminator)
+ msg = "Invalid control character {0!r} at".format(esc)
Martin v. Löwis 2009/01/04 13:22:29 esc isn't assigned until a few lines later. Is thi
bob.ippolito 2009/01/05 01:28:19 This is a bug in the exception handling code, fixe
raise ValueError(errmsg(msg, s, end))
else:
_append(terminator)
@@ -114,8 +87,8 @@
try:
m = _b[esc]
except KeyError:
- msg = "Invalid \\escape: {0!r}".format(esc)
- raise ValueError(errmsg(msg, s, end))
+ raise ValueError(
+ errmsg("Invalid \\escape: {0!r}".format(esc), s, end))
end += 1
else:
esc = s[end + 1:end + 5]
@@ -143,104 +116,121 @@
return u''.join(chunks), end
-# Use speedup
-if c_scanstring is not None:
- scanstring = c_scanstring
-else:
- scanstring = py_scanstring
+# Use speedup if available
+scanstring = c_scanstring or py_scanstring
-def JSONString(match, context):
- encoding = getattr(context, 'encoding', None)
- strict = getattr(context, 'strict', True)
- return scanstring(match.string, match.end(), encoding, strict)
-pattern(r'"')(JSONString)
+WHITESPACE = re.compile(r'[ \t\n\r]*', FLAGS)
+WHITESPACE_STR = ' \t\n\r'
-
-WHITESPACE = re.compile(r'\s*', FLAGS)
-
-
-def JSONObject(match, context, _w=WHITESPACE.match):
+def JSONObject((s, end), encoding, strict, scan_once, object_hook, _w=WHITESPACE.match, _ws=WHITESPACE_STR):
pairs = {}
- s = match.string
- end = _w(s, match.end()).end()
nextchar = s[end:end + 1]
Martin v. Löwis 2009/01/04 13:22:29 Why not s[end]? Add comment if this is necessary.
bob.ippolito 2009/01/05 01:28:19 commented in next patch (only once). s[end] can ra
- # Trivial empty object
- if nextchar == '}':
- return pairs, end + 1
+ # Normally we expect nextchar == '"'
if nextchar != '"':
- raise ValueError(errmsg("Expecting property name", s, end))
+ if nextchar in _ws:
+ end = _w(s, end).end()
+ nextchar = s[end:end + 1]
Martin v. Löwis 2009/01/04 13:22:29 Likewise. There are more places where it does slic
bob.ippolito 2009/01/05 01:28:19 commented in next patch (only once). s[end] can ra
+ # Trivial empty object
+ if nextchar == '}':
+ return pairs, end + 1
+ elif nextchar != '"':
+ raise ValueError(errmsg("Expecting property name", s, end))
end += 1
- encoding = getattr(context, 'encoding', None)
- strict = getattr(context, 'strict', True)
- iterscan = JSONScanner.iterscan
while True:
key, end = scanstring(s, end, encoding, strict)
- end = _w(s, end).end()
+
+ # To skip some function call overhead we optimize the fast paths where
+ # the JSON key separator is ": " or just ":".
if s[end:end + 1] != ':':
- raise ValueError(errmsg("Expecting : delimiter", s, end))
- end = _w(s, end + 1).end()
+ end = _w(s, end).end()
+ if s[end:end + 1] != ':':
+ raise ValueError(errmsg("Expecting : delimiter", s, end))
+
+ end += 1
+
try:
- value, end = iterscan(s, idx=end, context=context).next()
+ 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 ValueError(errmsg("Expecting object", s, end))
pairs[key] = value
- end = _w(s, end).end()
- nextchar = s[end:end + 1]
+
+ 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
- if nextchar != ',':
+ elif nextchar != ',':
raise ValueError(errmsg("Expecting , delimiter", s, end - 1))
- end = _w(s, end).end()
- nextchar = s[end: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 ValueError(errmsg("Expecting property name", s, end - 1))
- object_hook = getattr(context, 'object_hook', None)
+
if object_hook is not None:
pairs = object_hook(pairs)
return pairs, end
-pattern(r'{')(JSONObject)
-
-def JSONArray(match, context, _w=WHITESPACE.match):
+def JSONArray((s, end), scan_once, _w=WHITESPACE.match, _ws=WHITESPACE_STR):
values = []
- s = match.string
- end = _w(s, match.end()).end()
- # Look-ahead for trivial empty array
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
- iterscan = JSONScanner.iterscan
+ _append = values.append
while True:
try:
- value, end = iterscan(s, idx=end, context=context).next()
+ value, end = scan_once(s, end)
except StopIteration:
raise ValueError(errmsg("Expecting object", s, end))
- values.append(value)
- end = _w(s, end).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
- if nextchar != ',':
+ elif nextchar != ',':
raise ValueError(errmsg("Expecting , delimiter", s, end))
- end = _w(s, end).end()
- return values, end
-pattern(r'\[')(JSONArray)
+ try:
+ if s[end] in _ws:
+ end += 1
+ if s[end] in _ws:
+ end = _w(s, end + 1).end()
+ except IndexError:
+ pass
-ANYTHING = [
- JSONObject,
- JSONArray,
- JSONString,
- JSONConstant,
- JSONNumber,
-]
+ return values, end
-JSONScanner = Scanner(ANYTHING)
-
-
class JSONDecoder(object):
"""Simple JSON <http://json.org> decoder
@@ -270,7 +260,6 @@
their corresponding ``float`` values, which is outside the JSON spec.
"""
- _scanner = Scanner(ANYTHING)
__all__ = ['__init__', 'decode', 'raw_decode']
def __init__(self, encoding=None, object_hook=None, parse_float=None,
@@ -282,8 +271,8 @@
Note that currently only encodings that are a superset of ASCII work,
strings of other encodings should be passed in as ``unicode``.
- ``object_hook``, if specified, will be called with the result of
- every JSON object decoded and its return value will be used in
+ ``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 ``dict``. This can be used to provide custom
deserializations (e.g. to support JSON-RPC class hinting).
@@ -298,21 +287,24 @@
for JSON integers (e.g. float).
``parse_constant``, if specified, will be called with one of the
- following strings: -Infinity, Infinity, NaN, null, true, false.
+ following strings: -Infinity, Infinity, NaN.
Martin v. Löwis 2009/01/04 13:22:29 This sounds like an incompatible change.
bob.ippolito 2009/01/05 01:28:19 Not practically speaking. The documented purpose o
This can be used to raise an exception if invalid JSON numbers
are encountered.
"""
self.encoding = encoding
self.object_hook = object_hook
- self.parse_float = parse_float
- self.parse_int = parse_int
- self.parse_constant = parse_constant
+ 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.scan_once = make_scanner(self)
def decode(self, s, _w=WHITESPACE.match):
- """
- Return the Python representation of ``s`` (a ``str`` or ``unicode``
+ """Return the Python representation of ``s`` (a ``str`` or ``unicode``
instance containing a JSON document)
"""
@@ -322,7 +314,7 @@
raise ValueError(errmsg("Extra data", s, end, len(s)))
return obj
- def raw_decode(self, s, **kw):
+ def raw_decode(self, s, idx=0):
Martin v. Löwis 2009/01/04 13:22:29 That looks like an incompatible change
bob.ippolito 2009/01/05 01:28:19 It is a compatible change.
"""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.
@@ -331,9 +323,8 @@
have extraneous data at the end.
"""
- kw.setdefault('context', self)
try:
- obj, end = self._scanner.iterscan(s, **kw).next()
+ obj, end = self.scan_once(s, idx)
except StopIteration:
raise ValueError("No JSON object could be decoded")
return obj, end
« no previous file with comments | « Lib/json/__init__.py ('k') | Lib/json/encoder.py » ('j') | Modules/_json.c » ('J')

Powered by Google App Engine
RSS Feeds Recent Issues | This issue
This is Rietveld 1278:e6ce13d99bf5