doczyai-pipelines/fieldExtraction/src/utils/io_utils.py

import os
from io import StringIO

import pandas as pd
from botocore.exceptions import ClientError
from pyxlsb import open_workbook

import src.tracking.tracking_utils as tracking_utils
from src import config


def read_local(file_path): # io_utils.py
    # Check if the file is a text file
    if os.path.isfile(file_path) and file_path.endswith(".txt"):
        try:
            # First attempt to open the file with UTF-8 encoding
            with open(file_path, "r", encoding="utf-8") as file:
                file_contents = file.read()
                return file_contents
        except UnicodeDecodeError:
            # If UTF-8 fails, try reading the file with ANSI encoding
            try:
                with open(file_path, "r", encoding="cp1252") as file:
                    file_contents = file.read()
                    return file_contents
            except UnicodeDecodeError:
                # If ANSI also fails, log an error message or handle it accordingly
                print(f"Failed to decode {file_path} with UTF-8 and cp1252 encodings.")

    if os.path.isfile(file_path) and file_path.endswith(".csv"):
        try:
            df = pd.read_csv(file_path)
            return df
        except Exception:
            print('Failed to read .csv file.')

    if os.path.isfile(file_path) and file_path.endswith(".xlsx"):
        try:
            df = pd.read_excel(file_path)
            return df
        except Exception:
            print('Failed to read .xlsx file.')


def list_s3_files(prefix=config.S3_PREFIX, bucket=config.S3_BUCKET): # io_utils.py
    """List all files in an S3 folder."""
    response = config.S3_CLIENT.list_objects_v2(Bucket=bucket, Prefix=prefix)
    return [item["Key"] for item in response.get("Contents", [])]


def read_s3():
    s3_client = config.S3_CLIENT
    bucket = config.S3_BUCKET
    prefix = config.S3_PREFIX

    file_list = []
    continuation_token = None

    while True:

        if continuation_token:
            response = s3_client.list_objects_v2(
                Bucket=bucket, Prefix=prefix, ContinuationToken=continuation_token
            )
        else:
            response = s3_client.list_objects_v2(Bucket=bucket, Prefix=prefix)

        file_list += [
            obj["Key"]
            for obj in response.get("Contents", [])
            if not obj["Key"].endswith("/")
        ]

        if response.get("IsTruncated"):
            continuation_token = response.get("NextContinuationToken")
        else:
            break

    contract_list = sorted(file_list)
    files = {}

    for contract in contract_list:
        print(f"Reading {contract}")
        try:
            data = s3_client.get_object(Bucket=bucket, Key=contract)
            if contract.endswith('.txt'):
                contents = data["Body"].read()
                context = contents.decode("utf-8")
                path, filename = os.path.split(contract)
                files[filename] = context
        except:
            pass

    return files


def read_s3_csv(csv_path): # io_utils.py
    s3_client = config.S3_CLIENT
    s3_parts = csv_path[5:].split("/", 1)
    bucket = s3_parts[0]
    prefix = s3_parts[1] if len(s3_parts) > 1 else ""
    try:
        for obj in s3_client.list_objects_v2(Bucket=bucket, Prefix=prefix)["Contents"]:
            key = obj["Key"]
            if key.endswith(".csv"):
                response = s3_client.get_object(Bucket=bucket, Key=key)
                df = pd.read_csv(StringIO(response["Body"].read().decode("utf-8")))
                return df
    except ClientError as e:
        print(f"Error listing S3 objects: {e}")


def read_input(local_path=config.LOCAL_PATH): # io_utils.py
    if config.READ_MODE == "local":
        files = {}
        for file in os.listdir(local_path):
            full_path = os.path.join(local_path, file)
            file_text = read_local(full_path)
            files[file] = file_text
        return files
    elif config.READ_MODE == "s3":
        return read_s3()


def read_input_csv(): # io_utils.py
    if config.DF_READ_MODE == "local":
        ac_df = read_local(config.AC_DF) if config.AC_DF else None
        b_df = read_local(config.B_DF) if config.B_DF else None
    elif config.DF_READ_MODE == "s3":
        ac_df =  read_s3_csv(config.AC_DF) if config.AC_DF else None
        b_df = read_s3_csv(config.B_DF) if config.B_DF else None

    return ac_df, b_df


def filter_already_processed(input_dict, input_dict_b): # io_utils.py
    """Filter out already processed files based on either local files or S3 master tracking"""
    if config.WRITE_TO_S3:
        # Get processed files from S3 master tracking for this specific batch
        already_processed_ac, already_processed_b = tracking_utils.get_already_processed_files(config.BATCH_ID)

        # Keep files that still need either AC or B processing
        input_dict_ac = {
            k: v for k, v in input_dict.items()
            if k not in already_processed_ac
        }

        input_dict_b = {
            k: v for k, v in input_dict_b.items()
            if k not in already_processed_b
        }

        print(f"Filtering based on S3 master tracking for batch {config.BATCH_ID}:")
        print(f"AC: Found {len(already_processed_ac)} already processed, {len(input_dict_ac)} remaining")
        print(f"B: Found {len(already_processed_b)} already processed, {len(input_dict_b)} remaining")

    else:
        # Original local directory checking logic
        already_processed_ac, already_processed_b = [], []
        for folder_name in os.listdir(config.OUTPUT_DIRECTORY):
            folder_path = os.path.join(config.OUTPUT_DIRECTORY, folder_name)
            if os.path.isdir(folder_path):
                if config.AC_RESULTS_NAME in os.listdir(folder_path):
                    already_processed_ac.append(folder_name + ".txt")
                if config.B_RESULTS_NAME in os.listdir(folder_path):
                    already_processed_b.append(folder_name + ".txt")

        input_dict_ac = {
            k: v for k, v in input_dict.items()
            if k not in already_processed_ac
        }

        input_dict_b = {
            k: v for k, v in input_dict_b.items()
            if k not in already_processed_b
        }

        print(f"Filtering based on local output directory:")
        print(f"AC: Found {len(already_processed_ac)} already processed, {len(input_dict_ac)} remaining")
        print(f"B: Found {len(already_processed_b)} already processed, {len(input_dict_b)} remaining")

    return input_dict_ac, input_dict_b


def remove_txt_extension(filename): # io_utils.py
    if isinstance(filename, str) and filename.lower().endswith(".txt"):
        return filename[:-4]
    return filename


def read_xlsb(path): # io_utils.py
    with open_workbook(path) as wb:
        with wb.get_sheet(1) as sheet:
            rows = []
            for row in sheet.rows():
                rows.append([item.v for item in row])  # Extracting cell values
            df = pd.DataFrame(rows[1:], columns=rows[0])  # Converting to DataFrame, assuming first row is header
    return df