scripts/local/bin/j2y

88 lines
2.4 KiB
Python
Executable file

#!/usr/bin/env python3
from yaml import dump
try:
from yaml import CDumper as Dumper
except ImportError:
from yaml import Dumper
import json, re, sys
def dict_representer(dumper, d):
node = dumper.represent_dict(d)
# Don't use YAML flow style for large dicts, because the flow style output
# only really looks good with a very small number of keys.
if len(d) > 5 or sum(len(v) for v in d.values()) > 30:
node.flow_style = False
return node
Dumper.add_representer(dict, dict_representer)
def cat(files):
usedStdin = False
for f in files:
if f == '-':
if usedStdin: continue
usedStdin = True
with open(f) if f != '-' else sys.stdin as s:
for line in s: yield line
# http://stackoverflow.com/a/7795029/1208816
braces = '{}[]'
whitespace_esc = ' \t'
braces_esc = '\\' + '\\'.join(braces)
braces_pat = '[' + braces_esc + ']'
no_braces_pat = '[^' + braces_esc + ']*'
until_braces_pat = re.compile(no_braces_pat + braces_pat)
balance_map = dict(zip(braces, [1, -1, 1, -1]))
def streamingfinditer(pat, stream):
for s in stream:
while True:
m = pat.search(s)
if not m:
yield (0,s)
break
yield (1, m.group())
s = pat.split(s, 1)[1]
def simpleorcompoundobjects(stream):
obj = ""
unbalanced = 0
for (c, m) in streamingfinditer(until_braces_pat, stream):
if (c == 0): # remainder of line returned, nothing interesting
if (unbalanced == 0):
yield (0, m)
else:
obj += m
if (c == 1): # match returned
if (unbalanced == 0):
yield (0, m[:-1])
obj += m[-1]
else:
obj += m
unbalanced += balance_map[m[-1]]
if (unbalanced == 0):
yield (1, obj)
obj = ""
def streamingiterload(stream):
for c,o in simpleorcompoundobjects(stream):
for x in iterload(o):
yield x
# http://stackoverflow.com/a/6886743/1208816
def iterload(string_or_fp, cls=json.JSONDecoder, **kwargs):
try:
string = string_or_fp.read()
except AttributeError:
string = str(string_or_fp)
decoder = cls(**kwargs)
idx = json.decoder.WHITESPACE.match(string, 0).end()
while idx < len(string):
obj, end = decoder.raw_decode(string, idx)
yield obj
idx = json.decoder.WHITESPACE.match(string, end).end()
files = sys.argv[1:] or ('-',)
for obj in streamingiterload(cat(files)):
print(dump(obj, Dumper=Dumper, explicit_start=True), end='', flush=True)