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", None)
    return scanners

# convert a list of scanners to yaml file
def write_scanners(scanners):
    with open(YAML_PATH, "r") as f:
        config = yaml.load(f, Loader=yaml.FullLoader)

    config["detectors"] = scanners
    with open(YAML_PATH, "w") as f:
        # save scanners to detectors in yaml
        yaml.dump(config, f, Dumper=Dumper)

# read model_type from yaml file
def read_model_type(path):
    model_type = ""
    with open(path, "r") as f:
        config = yaml.load(f, Loader=yaml.FullLoader)
        model_type = config.get("model_type", None)
    return model_type

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