def read_yaml(yaml_path):
import yaml
import re
with open(yaml_path, mode='r') as f:
try:
# use SafeLoader's over Loader to prevent against arbitrary python object execution
# Use C loaders if possible, faster
from yaml import CSafeLoader as Loader # CLoader
except ImportError:
from yaml import SafeLoader as Loader # Loader
_mapping_tag = yaml.resolver.BaseResolver.DEFAULT_MAPPING_TAG
def dict_constructor(loader, node):
return OrderedDict(loader.construct_pairs(node))
Loader.add_constructor(_mapping_tag, dict_constructor)
# compiled resolver to correctly parse scientific notation numbers
Loader.add_implicit_resolver(
u'tag:yaml.org,2002:float',
re.compile(u'''^(?:
[-+]?(?:[0-9][0-9_]*)\\.[0-9_]*(?:[eE][-+]?[0-9]+)?
|[-+]?(?:[0-9][0-9_]*)(?:[eE][-+]?[0-9]+)
|\\.[0-9_]+(?:[eE][-+]?[0-9]+)?
|[-+]?[0-9][0-9_]*(?::[0-5]?[0-9])+\\.[0-9_]*
|[-+]?\\.(?:inf|Inf|INF)
|\\.(?:nan|NaN|NAN))$''', re.X),
list(u'-+0123456789.'))
return yaml.load(f, Loader=Loader)
from yaml import SafeLoader as Loader #pragma: no cover
from hepdata_validator import LATEST_SCHEMA_VERSION
from hepdata_validator.submission_file_validator import SubmissionFileValidator
from hepdata_validator.data_file_validator import DataFileValidator
from hepdata_converter.parsers import Parser, ParsedData, Table
import os, re
# Allow for a bug in PyYAML where numbers like 1e+04 are parsed as strings not as floats.
# See https://stackoverflow.com/a/30462009
# Try replacing PyYAML by ruamel.yaml in future?
Loader.add_implicit_resolver(
u'tag:yaml.org,2002:float',
re.compile(
u'''^(?:
[-+]?(?:[0-9][0-9_]*)\\.[0-9_]*(?:[eE][-+]?[0-9]+)?
|[-+]?(?:[0-9][0-9_]*)(?:[eE][-+]?[0-9]+)
|\\.[0-9_]+(?:[eE][-+][0-9]+)?
|[-+]?[0-9][0-9_]*(?::[0-5]?[0-9])+\\.[0-9_]*
|[-+]?\\.(?:inf|Inf|INF)
|\\.(?:nan|NaN|NAN))$''', re.X), list(u'-+0123456789.'))
class YAML(Parser):
help = 'Parses New HEPData YAML format. Input parameter should be path to ' \
'the directory where submission.yaml file ' \
'is present (or direct filepath to the submission.yaml file)'
def __init__(self, *args, **kwargs):
super(YAML, self).__init__(*args, **kwargs)
self.validator_schema_version = kwargs.get('validator_schema_version',
LATEST_SCHEMA_VERSION)
