Created
May 14, 2017 23:01
-
-
Save zerok/0a39f63cb3ad337bf3b2e40ce2a43975 to your computer and use it in GitHub Desktop.
Converter for WTD data from JSON to YAML
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
""" | |
This script is used to convert the JSON data we have on each conference into | |
YAML. | |
""" | |
import collections | |
import glob | |
import io | |
import json | |
import yaml | |
import os.path | |
# Title should be listed before the abstract and other things to make | |
# collapsing content in editor that support it much more usable. | |
order = ['title', 'name', 'abstract', 'speakers', 'youtubeId'] | |
# Source: http://stackoverflow.com/a/16782282 | |
def represent_ordereddict(dumper, data): | |
result = [] | |
for item_key, item_value in data.items(): | |
node_key = dumper.represent_data(item_key) | |
node_value = dumper.represent_data(item_value) | |
result.append((node_key, node_value)) | |
return yaml.nodes.MappingNode(u'tag:yaml.org,2002:map', result) | |
yaml.add_representer(collections.OrderedDict, represent_ordereddict) | |
def create_sorted_item(item): | |
result = [] | |
found = set() | |
for key in order: | |
if key in item: | |
result.append((key, item[key])) | |
found.add(key) | |
for key, value in item.items(): | |
if key not in found: | |
result.append((key, item[key])) | |
return collections.OrderedDict(result) | |
for json_file in glob.glob('_data/*.json'): | |
basename = os.path.basename(json_file) | |
folder = os.path.dirname(json_file) | |
target_file = os.path.join(folder, "{}.yaml".format(os.path.splitext(basename)[0])) | |
print("{} -> {}".format(json_file, target_file)) | |
with io.open(json_file) as fp: | |
data = json.load(fp) | |
converted_data = [] | |
if isinstance(data, list): | |
for item in data: | |
converted_data.append(create_sorted_item(item)) | |
else: | |
converted_data = data | |
with io.open(target_file, "w+") as out: | |
output = yaml.dump(converted_data, default_flow_style=False) | |
final_output = [] | |
for line in output.split('\n'): | |
# Remove EOL characters like \ | |
final_output.append(line.rstrip('\\').replace('\\ ', '')) | |
out.write('\n'.join(final_output)) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment