io_utils.py

import yaml

YAML_PATH = "./config.yaml"

class Dumper(yaml.Dumper):
    def increase_indent(self, flow=False, *args, **kwargs):
        return super().increase_indent(flow=flow, indentless=False)
    
# read scanners from yaml file
# return a list of scanners
def read_scanners(path):
    scanners = []
    with open(path, "r") as f:
        config = yaml.load(f, Loader=yaml.FullLoader)
        scanners = config.get("detectors", [])
    return scanners

# convert a list of scanners to yaml file
def write_scanners(scanners):
    print(scanners)
    with open(YAML_PATH, "r+") as f:
        config = yaml.load(f, Loader=yaml.FullLoader)
        if config:
            config["detectors"] = scanners
            # save scanners to detectors in yaml
            yaml.dump(config, f, Dumper=Dumper)

# read model_type from yaml file
def read_inference_type(path):
    inference_type = ""
    with open(path, "r") as f:
        config = yaml.load(f, Loader=yaml.FullLoader)
        inference_type = config.get("inference_type", "")
    return inference_type

# write model_type to yaml file
def write_inference_type(use_inference):
    with open(YAML_PATH, "r+") as f:
        config = yaml.load(f, Loader=yaml.FullLoader)
    if use_inference:
        config["inference_type"] = 'hf_inference_api'
    else:
        config["inference_type"] = 'hf_pipeline'
    # save inference_type to inference_type in yaml
    yaml.dump(config, f, Dumper=Dumper)

# read column mapping from yaml file
def read_column_mapping(path):
    column_mapping = {}
    with open(path, "r") as f:
        config = yaml.load(f, Loader=yaml.FullLoader)
        column_mapping = config.get("column_mapping", dict())
    return column_mapping

# write column mapping to yaml file
def write_column_mapping(mapping):
    with open(YAML_PATH, "r") as f:
        config = yaml.load(f, Loader=yaml.FullLoader)
    if mapping is None:
        del config["column_mapping"]
    else:
        config["column_mapping"] = mapping
    with open(YAML_PATH, "w") as f:
        # save column_mapping to column_mapping in yaml
        yaml.dump(config, f, Dumper=Dumper)

# convert column mapping dataframe to json
def convert_column_mapping_to_json(df, label=""):
    column_mapping = {}
    column_mapping[label] = []
    for _, row in df.iterrows():
        column_mapping[label].append(row.tolist())
    return column_mapping