Related
I just discovered the json_normalize function which works great in taking a JSON object and giving me a pandas Dataframe. Now I want the reverse operation which takes that same Dataframe and gives me a json (or json-like dictionary which I can easily turn to json) with the same structure as the original json.
Here's an example: https://hackersandslackers.com/json-into-pandas-dataframes/.
They take a JSON object (or JSON-like python dictionary) and turn it into a dataframe, but I now want to take that dataframe and turn it back into a JSON-like dictionary (to later dump to json file).
I implemented it with a couple functions
def set_for_keys(my_dict, key_arr, val):
"""
Set val at path in my_dict defined by the string (or serializable object) array key_arr
"""
current = my_dict
for i in range(len(key_arr)):
key = key_arr[i]
if key not in current:
if i==len(key_arr)-1:
current[key] = val
else:
current[key] = {}
else:
if type(current[key]) is not dict:
print("Given dictionary is not compatible with key structure requested")
raise ValueError("Dictionary key already occupied")
current = current[key]
return my_dict
def to_formatted_json(df, sep="."):
result = []
for _, row in df.iterrows():
parsed_row = {}
for idx, val in row.iteritems():
keys = idx.split(sep)
parsed_row = set_for_keys(parsed_row, keys, val)
result.append(parsed_row)
return result
#Where df was parsed from json-dict using json_normalize
to_formatted_json(df, sep=".")
A simpler approach:
Uses only 1 function...
def df_to_formatted_json(df, sep="."):
"""
The opposite of json_normalize
"""
result = []
for idx, row in df.iterrows():
parsed_row = {}
for col_label,v in row.items():
keys = col_label.split(sep)
current = parsed_row
for i, k in enumerate(keys):
if i==len(keys)-1:
current[k] = v
else:
if k not in current.keys():
current[k] = {}
current = current[k]
# save
result.append(parsed_row)
return result
df.to_json(path)
or
df.to_dict()
I just implemented this using 2 functions.
Get a full list of fields from the DataFrame that are part of a nested field. Only the parent i.e. if location.city.code fits the criteria, we only care about location.city. Sort it by the deepest level of nesting, i.e. location.city is nested further than location.
Starting with the deepest nested parent field, find all child fields by searching in the column name. Create a field in the DataFrame for the parent field, which is a combination of all child fields (renamed so that they lose the nesting structure, e.g. location.city.code becomes code) converted to JSON and then loaded to a dictionary value. Finally, drop all of the child fields.
def _get_nested_fields(df: pd.DataFrame) -> List[str]:
"""Return a list of nested fields, sorted by the deepest level of nesting first."""
nested_fields = [*{field.rsplit(".", 1)[0] for field in df.columns if "." in field}]
nested_fields.sort(key=lambda record: len(record.split(".")), reverse=True)
return nested_fields
def df_denormalize(df: pd.DataFrame) -> pd.DataFrame:
"""
Convert a normalised DataFrame into a nested structure.
Fields separated by '.' are considered part of a nested structure.
"""
nested_fields = _get_nested_fields(df)
for field in nested_fields:
list_of_children = [column for column in df.columns if field in column]
rename = {
field_name: field_name.rsplit(".", 1)[1] for field_name in list_of_children
}
renamed_fields = df[list_of_children].rename(columns=rename)
df[field] = json.loads(renamed_fields.to_json(orient="records"))
df.drop(list_of_children, axis=1, inplace=True)
return df
let me throw in my two cents
after backward converting you might need to drop empty columns from your generated jsons
therefore, i checked if val != np.nan. but u cant directly do it, instead you need to check val == val or not, because np.nan != itself.
my version:
def to_formatted_json(df, sep="."):
result = []
for _, row in df.iterrows():
parsed_row = {}
for idx, val in row.iteritems():
if val == val:
keys = idx.split(sep)
parsed_row = set_for_keys(parsed_row, keys, val)
result.append(parsed_row)
return result
This is a solution which looks working to me. It is designed to work on a dataframe with one line, but it can be easily looped over large dataframes.
class JsonRecreate():
def __init__(self, df):
self.df = df
def pandas_to_json(self):
df = self.df
# determine the number of nesting levels
number_levels = np.max([len(i.split('.')) for i in df.columns])
# put all the nesting levels in an a list
levels = []
for level_idx in np.arange(number_levels):
levels.append(np.array([i.split('.')[level_idx] if len(i.split('.')) > level_idx else ''
for i in df.columns.tolist()]))
self.levels = levels
return self.create_dict(upper_bound = self.levels[0].shape[0])
def create_dict(self, level_idx = 0, lower_bound = 0, upper_bound = 100):
''' Function to create the dictionary starting from a pandas dataframe generated by json_normalize '''
levels = self.levels
dict_ = {}
# current nesting level
level = levels[level_idx]
# loop over all the relevant elements of the level (relevant w.r.t. its parent)
for key in [i for i in np.unique(level[lower_bound: upper_bound]) if i != '']:
# find where a particular key occurs in the level
correspondence = np.where(level[lower_bound: upper_bound] == key)[0] + lower_bound
# check if the value(s) corresponding to the key appears once (multiple times)
if correspondence.shape[0] == 1:
# if the occurence is unique, append the value to the dictionary
dict_[key] = self.df.values[0][correspondence[0]]
else:
# otherwhise, redefine the relevant bounds and call the function recursively
lower_bound_, upper_bound_ = correspondence.min(), correspondence.max() + 1
dict_[key] = self.create_dict(level_idx + 1, lower_bound_, upper_bound_)
return dict_
I tested it with a simple dataframe such as:
df = pd.DataFrame({'a.b': [1], 'a.c.d': [2], 'a.c.e': [3], 'a.z.h1': [-1], 'a.z.h2': [-2], 'f': [4], 'g.h': [5], 'g.i.l': [6], 'g.i.m': [7], 'g.z.h1': [-3], 'g.z.h2': [-4]})
The order in the json is not exactly preserved in the resulting json, but it can be easily handled if needed.
I've got an Athena table where some fields have a fairly complex nested format. The backing records in S3 are JSON. Along these lines (but we have several more levels of nesting):
CREATE EXTERNAL TABLE IF NOT EXISTS test (
timestamp double,
stats array<struct<time:double, mean:double, var:double>>,
dets array<struct<coords: array<double>, header:struct<frame:int,
seq:int, name:string>>>,
pos struct<x:double, y:double, theta:double>
)
ROW FORMAT SERDE 'org.openx.data.jsonserde.JsonSerDe'
WITH SERDEPROPERTIES ('ignore.malformed.json'='true')
LOCATION 's3://test-bucket/test-folder/'
Now we need to be able to query the data and import the results into Python for analysis. Because of security restrictions I can't connect directly to Athena; I need to be able to give someone the query and then they will give me the CSV results.
If we just do a straight select * we get back the struct/array columns in a format that isn't quite JSON.
Here's a sample input file entry:
{"timestamp":1520640777.666096,"stats":[{"time":15,"mean":45.23,"var":0.31},{"time":19,"mean":17.315,"var":2.612}],"dets":[{"coords":[2.4,1.7,0.3], "header":{"frame":1,"seq":1,"name":"hello"}}],"pos": {"x":5,"y":1.4,"theta":0.04}}
And example output:
select * from test
"timestamp","stats","dets","pos"
"1.520640777666096E9","[{time=15.0, mean=45.23, var=0.31}, {time=19.0, mean=17.315, var=2.612}]","[{coords=[2.4, 1.7, 0.3], header={frame=1, seq=1, name=hello}}]","{x=5.0, y=1.4, theta=0.04}"
I was hoping to get those nested fields exported in a more convenient format - getting them in JSON would be great.
Unfortunately it seems that cast to JSON only works for maps, not structs, because it just flattens everything into arrays:
SELECT timestamp, cast(stats as JSON) as stats, cast(dets as JSON) as dets, cast(pos as JSON) as pos FROM "sampledb"."test"
"timestamp","stats","dets","pos"
"1.520640777666096E9","[[15.0,45.23,0.31],[19.0,17.315,2.612]]","[[[2.4,1.7,0.3],[1,1,""hello""]]]","[5.0,1.4,0.04]"
Is there a good way to convert to JSON (or another easy-to-import format) or should I just go ahead and do a custom parsing function?
I have skimmed through all the documentation and unfortunately there seems to be no way to do this as of now. The only possible workaround is
converting a struct to a json when querying athena
SELECT
my_field,
my_field.a,
my_field.b,
my_field.c.d,
my_field.c.e
FROM
my_table
Or I would convert the data to json using post processing. Below script shows how
#!/usr/bin/env python
import io
import re
pattern1 = re.compile(r'(?<={)([a-z]+)=', re.I)
pattern2 = re.compile(r':([a-z][^,{}. [\]]+)', re.I)
pattern3 = re.compile(r'\\"', re.I)
with io.open("test.csv") as f:
headers = list(map(lambda f: f.strip(), f.readline().split(",")))
for line in f.readlines():
orig_line = line
data = []
for i, l in enumerate(line.split('","')):
data.append(headers[i] + ":" + re.sub('^"|"$', "", l))
line = "{" + ','.join(data) + "}"
line = pattern1.sub(r'"\1":', line)
line = pattern2.sub(r':"\1"', line)
print(line)
The output on your input data is
{"timestamp":1.520640777666096E9,"stats":[{"time":15.0, "mean":45.23, "var":0.31}, {"time":19.0, "mean":17.315, "var":2.612}],"dets":[{"coords":[2.4, 1.7, 0.3], "header":{"frame":1, "seq":1, "name":"hello"}}],"pos":{"x":5.0, "y":1.4, "theta":0.04}
}
Which is a valid JSON
The python code from #tarun almost got me there, but I had to modify it in several ways due to my data. In particular, I have:
json structures saved in Athena as strings
Strings that contain multiple words, and therefore need to be in between double quotes. Some of them contain "[]" and "{}" symbols.
Here is the code that worked for me, hopefully will be useful for others:
#!/usr/bin/env python
import io
import re, sys
pattern1 = re.compile(r'(?<={)([a-z]+)=', re.I)
pattern2 = re.compile(r':([a-z][^,{}. [\]]+)', re.I)
pattern3 = re.compile(r'\\"', re.I)
with io.open(sys.argv[1]) as f:
headers = list(map(lambda f: f.strip(), f.readline().split(",")))
print(headers)
for line in f.readlines():
orig_line = line
#save the double quote cases, which mean there is a string with quotes inside
line = re.sub('""', "#", orig_line)
data = []
for i, l in enumerate(line.split('","')):
item = re.sub('^"|"$', "", l.rstrip())
if (item[0] == "{" and item[-1] == "}") or (item[0] == "[" and item[-1] == "]"):
data.append(headers[i] + ":" + item)
else: #we have a string
data.append(headers[i] + ": \"" + item + "\"")
line = "{" + ','.join(data) + "}"
line = pattern1.sub(r'"\1":', line)
line = pattern2.sub(r':"\1"', line)
#restate the double quotes to single ones, once inside the json
line = re.sub("#", '"', line)
print(line)
This method is not by modifying the Query.
Its by Post Processing For Javascript/Nodejs we can use the npm package athena-struct-parser.
Detailed Answer with Example
https://stackoverflow.com/a/67899845/6662952
Reference - https://www.npmjs.com/package/athena-struct-parser
I used a simple approach to get around the struct -> json Athena limitation. I created a second table where the json columns were saved as raw strings. Using presto json and array functions I was able to query the data and return the valid json string to my program:
--Array transform functions too
select
json_extract_scalar(dd, '$.timestamp') as timestamp,
transform(cast(json_extract(json_parse(dd), '$.stats') as ARRAY<JSON>), x -> json_extract_scalar(x, '$.time')) as arr_stats_time,
transform(cast(json_extract(json_parse(dd), '$.stats') as ARRAY<JSON>), x -> json_extract_scalar(x, '$.mean')) as arr_stats_mean,
transform(cast(json_extract(json_parse(dd), '$.stats') as ARRAY<JSON>), x -> json_extract_scalar(x, '$.var')) as arr_stats_var
from
(select '{"timestamp":1520640777.666096,"stats":[{"time":15,"mean":45.23,"var":0.31},{"time":19,"mean":17.315,"var":2.612}],"dets":[{"coords":[2.4,1.7,0.3], "header":{"frame":1,"seq":1,"name":"hello"}}],"pos": {"x":5,"y":1.4,"theta":0.04}}' as dd);
I know the query will take longer to execute but there are ways to optimize.
I worked around this by creating a second table using the same S3 location, but changed the field's data type to string. The resulting CSV then had the string that Athena pulled from the object in the JSON file and I was able to parse the result.
I also had to adjust the #tarun code, because I had more complex data and nested structures. Here is the solution I've got, I hope it helps:
import re
import json
import numpy as np
pattern1 = re.compile(r'(?<=[{,\[])\s*([^{}\[\],"=]+)=')
pattern2 = re.compile(r':([^{}\[\],"]+|()(?![{\[]))')
pattern3 = re.compile(r'"null"')
def convert_metadata_to_json(value):
if type(value) is str:
value = pattern1.sub('"\\1":', value)
value = pattern2.sub(': "\\1"', value)
value = pattern3.sub('null', value)
elif np.isnan(value):
return None
return json.loads(value)
df = pd.read_csv('test.csv')
df['metadata_json'] = df.metadata.apply(convert_metadata_to_json)
As mentioned in the title, i'm trying to make a simple py script that can be run from terminal to do the following:
Find all JSON files in current working directory and nested folders (this part works well)
Load said files
Recursively search them for a specific value or a substring
If the value is matching, replace it with a new established value by the user
Once finished, save all modified json files to a "converted" folder in the current directory.
That said, the issue is when i try the recursive search method posted below, since i'm pretty much new to python i would appreciate any help with this issue, what i suppose it is... either the json files i'm using or the search method i'm employing.
Simplifying the issue, the value i search for never matches with anything inside the object, be that a key or purely some string value. Tried multiple methods to perform a recursive search but can't get a match.
For example: taking in account the sample json, i want to replace the value "selectable_parts" or "static_parts" or even deeper in the structure "1h_mod310_door_00" but seems like my method of searching can't reach this value in "object[object][children][0][children][5][name]" (hope this helps).
Sample JSON: (https://drive.google.com/open?id=0B2-Bn2b0ujjVdW5YVGg3REg3OWs)
"""KEYWORD REPLACING MODULE."""
import os
import json
# functions
def get_files():
"""lists files"""
exclude = set(['.vscode', 'sample'])
json_files = []
for root, dirs, files in os.walk(os.getcwd(), topdown=True):
dirs[:] = [d for d in dirs if d not in exclude]
for name in files:
if name.endswith('.json'):
json_files.append(os.path.join(root, name))
return json_files
def load_files(json_files):
"""works files"""
for js_file in json_files:
with open(js_file) as json_file:
loaded_json = json.load(json_file)
replace_key_value(loaded_json, os.path.basename(js_file))
def write_file(data_file, new_file_name):
"""writes the file"""
if not os.path.exists('converted'):
os.makedirs('converted')
with open('converted/' + new_file_name, 'w') as json_file:
json.dump(data_file, json_file)
def replace_key_value(js_file, js_file_name):
"""replace and initiate save"""
recursive_replace(js_file, SKEY, '')
# write_file(js_file, js_file_name)
def recursive_replace(data, match, repl):
"""search for needed value and replace its value"""
for key, value in data.items():
if value == match:
print data[key]
print "AHHHHHHHH"
elif isinstance(value, dict):
recursive_replace(value, match, repl)
# main
print "\n" + '- on ' + os.getcwd()
NEW_DIR = raw_input('Work dir (leave empty if current): ')
if not NEW_DIR:
print NEW_DIR
NEW_DIR = os.getcwd()
else:
print NEW_DIR
os.chdir(NEW_DIR)
# get_files()
JS_FILES = get_files()
print '- files on ' + os.getcwd()
# print "\n".join(JS_FILES)
SKEY = raw_input('Value to search: ')
RKEY = raw_input('Replacement value: ')
load_files(JS_FILES)
The issue was the way i navigated the json obj because the method didn't considerate if it was a dict or a list (i believe...).
So to answer my own question here's the recursive search i'm using to check the values:
def get_recursively(search_dict, field):
"""
Takes a dict with nested lists and dicts,
and searches all dicts for a key of the field
provided.
"""
fields_found = []
for key, value in search_dict.iteritems():
if key == field:
print value
fields_found.append(value)
elif isinstance(value, dict):
results = get_recursively(value, field)
for result in results:
if SEARCH_KEY in result:
fields_found.append(result)
elif isinstance(value, list):
for item in value:
if isinstance(item, dict):
more_results = get_recursively(item, field)
for another_result in more_results:
if SEARCH_KEY in another_result:
fields_found.append(another_result)
return fields_found
# write_file(js_file, js_file_name)
Hope this helps someone.
I have .csv file with integer values, that can have NA value which represents missing data.
Example file:
-9882,-9585,-9179
-9883,-9587,NA
-9882,-9585,-9179
When trying to read it with
import tensorflow as tf
reader = tf.TextLineReader(skip_header_lines=1)
key, value = reader.read_up_to(filename_queue, 1)
record_defaults = [[0], [0], [0]]
data, ABL_E, ABL_N = tf.decode_csv(value, record_defaults=record_defaults)
It throws following error later on sess.run(_) on the 2nd iteration
InvalidArgumentError (see above for traceback): Field 5 in record 32400 is not a valid int32: NA
Is there a way to interpret string "NA" while reading csv as NaN or similar value in TensorFlow?
I recently ran into the same problem. I solved it by reading the CSV as strings, replacing every occurrence of "NA" with some valid value, then converting it to float
# Set up reading from CSV files
filename_queue = tf.train.string_input_producer([filename])
reader = tf.TextLineReader()
key, value = reader.read(filename_queue)
NUM_COLUMNS = XX # Specify number of expected columns
# Read values as string, set "NA" for missing values.
record_defaults = [[tf.cast("NA", tf.string)]] * NUM_COLUMNS
decoded = tf.decode_csv(value, record_defaults=record_defaults, field_delim="\t")
# Replace every occurrence of "NA" with "-1"
no_nan = tf.where(tf.equal(decoded, "NA"), ["-1"]*NUM_COLUMNS, decoded)
# Convert to float, combine to a single tensor with stack.
float_row = tf.stack(tf.string_to_number(no_nan, tf.float32))
But long term I plan switching to tfrecords because reading csv is too slow for my needs
I am writing record to Kinesis Firehose stream that is eventually written to a S3 file by Amazon Kinesis Firehose.
My record object looks like
ItemPurchase {
String personId,
String itemId
}
The data is written to S3 looks like:
{"personId":"p-111","itemId":"i-111"}{"personId":"p-222","itemId":"i-222"}{"personId":"p-333","itemId":"i-333"}
NO COMMA SEPERATION.
NO STARTING BRACKET as in a Json Array
[
NO ENDING BRACKET as in a Json Array
]
I want to read this data get a list of ItemPurchase objects.
List<ItemPurchase> purchases = getPurchasesFromS3(IOUtils.toString(s3ObjectContent))
What is the correct way to read this data?
It boggles my mind that Amazon Firehose dumps JSON messages to S3 in this manner, and doesn't allow you to set a delimiter or anything.
Ultimately, the trick I found to deal with the problem was to process the text file using the JSON raw_decode method
This will allow you to read a bunch of concatenated JSON records without any delimiters between them.
Python code:
import json
decoder = json.JSONDecoder()
with open('giant_kinesis_s3_text_file_with_concatenated_json_blobs.txt', 'r') as content_file:
content = content_file.read()
content_length = len(content)
decode_index = 0
while decode_index < content_length:
try:
obj, decode_index = decoder.raw_decode(content, decode_index)
print("File index:", decode_index)
print(obj)
except JSONDecodeError as e:
print("JSONDecodeError:", e)
# Scan forward and keep trying to decode
decode_index += 1
I also had the same problem, here is how I solved.
replace "}{" with "}\n{"
line split by "\n".
input_json_rdd.map(lambda x : re.sub("}{", "}\n{", x, flags=re.UNICODE))
.flatMap(lambda line: line.split("\n"))
A nested json object has several "}"s, so split line by "}" doesn't solve the problem.
I've had the same issue.
It would have been better if AWS allowed us to set a delimiter but we can do it on our own.
In my use case, I've been listening on a stream of tweets, and once receiving a new tweet I immediately put it to Firehose.
This, of course, resulted in a 1-line file which could not be parsed.
So, to solve this, I have concatenated the tweet's JSON with a \n.
This, in turn, let me use some packages that can output lines when reading stream contents, and parse the file easily.
Hope this helps you.
I think the best ways to tackle this is to first create a properly formatted json file containing well separated json objects within them. In my case I added ',' to the events which was pushed into the firehose. Then After a file is saved in s3, all the files will contain json object separated by some delimitter(comma- in our case). Another thing that must be added are '[' and ']' at the beginning and end of the file. Then you have a proper json file containing multiple json objects. Parsing them will be possible now.
If the input source for the firehose is an Analytics application, this concatenated JSON without a delimiter is a known issue as cited here. You should have a lambda function as here that outputs JSON objects in multiple lines.
I used a transformation Lambda to add a line break at the end of every record
def lambda_handler(event, context):
output = []
for record in event['records']:
# Decode from base64 (Firehose records are base64 encoded)
payload = base64.b64decode(record['data'])
# Read json as utf-8
json_string = payload.decode("utf-8")
# Add a line break
output_json_with_line_break = json_string + "\n"
# Encode the data
encoded_bytes = base64.b64encode(bytearray(output_json_with_line_break, 'utf-8'))
encoded_string = str(encoded_bytes, 'utf-8')
# Create a deep copy of the record and append to output with transformed data
output_record = copy.deepcopy(record)
output_record['data'] = encoded_string
output_record['result'] = 'Ok'
output.append(output_record)
print('Successfully processed {} records.'.format(len(event['records'])))
return {'records': output}
Use this simple Python code.
input_str = '''{"personId":"p-111","itemId":"i-111"}{"personId":"p-222","itemId":"i-222"}{"personId":"p-333","itemId":"i-333"}'''
data_str = "[{}]".format(input_str.replace("}{","},{"))
data_json = json.loads(data_str)
And then (if you want) convert to Pandas.
import pandas as pd
df = pd.DataFrame().from_records(data_json)
print(df)
And this is result
itemId personId
0 i-111 p-111
1 i-222 p-222
2 i-333 p-333
If there's a way to change the way data is written, please separate all the records by a line. That way you can read the data simply, line by line. If not, then simply build a scanner object which takes "}" as a delimiter and use the scanner to read. That would do the job.
You can find the each valid JSON by counting the brackets. Assuming the file starts with a { this python snippet should work:
import json
def read_block(stream):
open_brackets = 0
block = ''
while True:
c = stream.read(1)
if not c:
break
if c == '{':
open_brackets += 1
elif c == '}':
open_brackets -= 1
block += c
if open_brackets == 0:
yield block
block = ''
if __name__ == "__main__":
c = 0
with open('firehose_json_blob', 'r') as f:
for block in read_block(f):
record = json.loads(block)
print(record)
This problem can be solved with a JSON parser that consumes objects one at a time from a stream. The raw_decode method of the JSONDecoder exposes just such a parser, but I've written a library that makes it straightforward to do this with a one-liner.
from firehose_sipper import sip
for entry in sip(bucket=..., key=...):
do_something_with(entry)
I've added some more details in this blog post
In Spark, we had the same problem. We're using the following:
from pyspark.sql.functions import *
#udf
def concatenated_json_to_array(text):
final = "["
separator = ""
for part in text.split("}{"):
final += separator + part
separator = "}{" if re.search(r':\s*"([^"]|(\\"))*$', final) else "},{"
return final + "]"
def read_concatenated_json(path, schema):
return (spark.read
.option("lineSep", None)
.text(path)
.withColumn("value", concatenated_json_to_array("value"))
.withColumn("value", from_json("value", schema))
.withColumn("value", explode("value"))
.select("value.*"))
It works as follows:
Read the data as one string per file (no delimiters!)
Use a UDF to introduce the JSON array and split the JSON objects by introducing a comma. Note: be careful not to break any strings with }{ in them!
Parse the JSON with a schema into DataFrame fields.
Explode the array into separate rows
Expand the value object into column.
Use it like this:
from pyspark.sql.types import *
schema = ArrayType(
StructType([
StructField("type", StringType(), True),
StructField("value", StructType([
StructField("id", IntegerType(), True),
StructField("joke", StringType(), True),
StructField("categories", ArrayType(StringType()), True)
]), True)
])
)
path = '/mnt/my_bucket_name/messages/*/*/*/*/'
df = read_concatenated_json(path, schema)
I've written more details and considerations here: Parsing JSON data from S3 (Kinesis) with Spark. Do not just split by }{, as it can mess up your string data! For example: { "line": "a\"r}{t" }.
You can use below script.
If streamed data size is not over buffer size that you set, each file of s3 have one pair of brackets([]) and comma.
import base64
print('Loading function')
def lambda_handler(event, context):
output = []
for record in event['records']:
print(record['recordId'])
payload = base64.b64decode(record['data']).decode('utf-8')+',\n'
# Do custom processing on the payload here
output_record = {
'recordId': record['recordId'],
'result': 'Ok',
'data': base64.b64encode(payload.encode('utf-8'))
}
output.append(output_record)
last = len(event['records'])-1
print('Successfully processed {} records.'.format(len(event['records'])))
start = '['+base64.b64decode(output[0]['data']).decode('utf-8')
end = base64.b64decode(output[last]['data']).decode('utf-8')+']'
output[0]['data'] = base64.b64encode(start.encode('utf-8'))
output[last]['data'] = base64.b64encode(end.encode('utf-8'))
return {'records': output}
Using JavaScript Regex.
JSON.parse(`[${item.replace(/}\s*{/g, '},{')}]`);