doczyai-pipelines/fieldExtraction/src/string_funcs.py

import json
import re
import warnings

import numpy as np
import pandas as pd

import claude_funcs
import config
import prompts
from enums.delimiters import Delimiter
from regex_patterns import (BACKTICK_PATTERN, PIPE_PATTERN,
                            TRIPLE_BACKTICK_PATTERN)


def extract_text_from_delimiters(
    raw_output: str, delimiter: Delimiter, match_index: int = -1
) -> str:
    """
    Extracts a match enclosed in specified delimiters from the raw output.
    This function searches for text enclosed by a specified delimiter in the given raw output string.
    It returns the match specified by the `which_match` index. If no match is found, it returns "N/A".

    - raw_output (str): The raw output string to search within.
    - which_match (int, optional): The index of the match to return. Defaults to -1, which returns the last match. If the index is out of range, the last match is returned.
    - str: The extracted text or "N/A" if no match is found.

    Raises:
        - TypeError: If `raw_output` is not a string or `delimiter` is not a Delimiter enum value.
        - ValueError: If an unsupported delimiter is provided.

    Returns:
        - str: The extracted answer or "N/A" if no match is found.
    """
    if not isinstance(raw_output, str):
        raise TypeError(
            "Expected a string for raw_output, got {0}.".format(
                type(raw_output).__name__
            )
        )

    if not isinstance(delimiter, Delimiter):
        raise TypeError(
            "Expected a Delimiter enum value, got {0}.".format(type(delimiter).__name__)
        )

    # Define a pattern based on the delimiter type
    if delimiter == Delimiter.PIPE:
        pattern = PIPE_PATTERN
    elif delimiter == Delimiter.BACKTICK:
        pattern = BACKTICK_PATTERN
    elif delimiter == Delimiter.TRIPLE_BACKTICK:
        pattern = TRIPLE_BACKTICK_PATTERN
    else:
        raise ValueError("Unsupported delimiter. Use one of the Delimiter enum values.")

    # Find all matches based on the pattern
    matches = re.findall(pattern=pattern, string=raw_output)

    if len(matches) == 0:
        return "N/A"

    # Adjust for negative indices
    if match_index < 0:
        match_index += len(matches)

    if not 0 <= match_index < len(matches):
        warnings.warn("Index out of range. Returning the last match by default.")
        match_index = -1

    return matches[match_index]


def json_parsing_search(response_text, field_list):
    try:
        if response_text.split("{", 1)[1].strip()[0] == '"':
            response_text = "{" + response_text.split("{", 1)[1]
        else:
            response_text = "{" + response_text
    except:
        response_text = "{" + response_text

    if len(response_text.split("}", 1)) > 1:
        if response_text.rsplit("}", 1)[0].strip()[-1] == '"':
            response_text = response_text.rsplit("}", 1)[0] + "}"
        elif response_text.rsplit("}", 1)[0].strip()[-1] == "}":
            response_text = response_text.rsplit("}", 1)[0]
    else:
        response_text = response_text.rstrip(",") + "}"
    field_l = []
    answer_l = []
    position_dict = {}
    for f in field_list:
        location = response_text.find('"' + f + '"')
        if location != -1:
            position_dict[location] = f
    field_list = list(dict(sorted(position_dict.items())).values())
    for f in field_list:
        if f in response_text:
            field_l.append(f)
            value = response_text.split('"' + f + '"')[0]
            response_text = response_text.split('"' + f + '"')[1]
            if f != field_list[0] and f != field_list[-1]:
                answer_l.append(
                    value.strip("\n")
                    .strip('"')
                    .strip(":")
                    .strip(" ")
                    .strip("\n")
                    .strip(" ")
                    .strip(",")
                    .strip('"')
                )
            elif f == field_list[-1]:
                answer_l.append(
                    value.strip("\n")
                    .strip('"')
                    .strip(":")
                    .strip(" ")
                    .strip("\n")
                    .strip(" ")
                    .strip(",")
                    .strip('"')
                )
                answer_l.append(
                    response_text.strip("\n")
                    .strip('"')
                    .strip(":")
                    .strip(" ")
                    .strip("}")
                    .strip("\n")
                    .strip(" ")
                    .strip('"')
                )

    return dict(zip(field_l, answer_l))


def secondary_string_to_dict(dict_string, filename):
    """
    Converts a string representation of a dictionary into an actual dictionary object, handling potential formatting issues.

    This function cleans the string by removing specific unwanted characters and markers that may interfere with JSON parsing.
    It then locates the substring that correctly forms a dictionary format, attempts to parse it as JSON, and handles common
    parsing errors by replacing problematic single quotes with double quotes before re-parsing.

    Parameters:
        dict_string (str): The string containing the dictionary-like content, potentially surrounded by extra text or characters.

    Returns:
        dict: The dictionary obtained from parsing the cleaned and corrected string.
    """
    start_index = dict_string.find("{")
    end_index = dict_string.rfind("}") + 1
    dict_substring = dict_string[start_index:end_index]
    try:
        result_dict = json.loads(dict_substring)
    except:
        try:
            dict_substring = dict_substring.replace("'", '"')
            result_dict = json.loads(dict_substring)
        except:
            try:
                prompt = prompts.FIX_JSON(dict_substring)
                dict_substring = claude_funcs.invoke_claude(
                    prompt, config.MODEL_ID_CLAUDE3_HAIKU, filename
                )
                result_dict = json.loads(dict_substring)
            except Exception as e:
                print(e)
                result_dict = {}
    return result_dict


def primary_string_to_dict(string_dict, filename):
    """
    Converts a dictionary of strings, where each string represents multiple dictionary entries, into a list of dictionaries,
    augmenting each with metadata such as page number and filename.

    This function iterates over each page number's string data, extracting and converting string representations of
    dictionaries into actual dictionary objects. It handles and cleans the string format to properly parse it into dictionaries.
    All dictionaries are then augmented with their respective page number and the filename before being compiled into a list.

    Parameters:
        string_dict (dict): A dictionary where keys are page numbers and values are strings containing multiple dictionary entries.
        filename (str): The filename associated with these entries, used to tag each resulting dictionary.

    Returns:
        list of dict: A list of dictionaries, each representing data extracted and converted from the input string, tagged with
                      their page number and filename.
    """
    data = []
    pattern = r"\{.*?\}"
    for page_num in string_dict.keys():
        primary_list = string_dict[page_num]
        dicts = primary_list.split("[")[1]  # Strip front
        dicts = dicts.split("]")[0]  # Strip back
        dicts = dicts.replace("\n", "")  # Remove new lines
        dicts = dicts.replace("<<<", "")
        dicts = dicts.replace(">>>", "")
        dicts = re.sub(r"(?<!\\)'([^']*?)'(?<!\\):", r'"\1":', dicts)
        dict_list = re.findall(pattern, dicts)
        dict_list = [secondary_string_to_dict(d, filename) for d in dict_list]
        for dict_ in dict_list:
            dict_["page_num"] = page_num
            dict_["Filename"] = filename
            data.append(dict_)
    return data


def contains_reimbursement(text, page="1"): # string_funcs.py
    if isinstance(text, dict):
        return page.isdigit() and (
            "%" in text[page]
            or "$" in text[page]
            or "percent " in text[page]
            or "compensation schedule" in text[page].lower()
            or "reimbursement schedule" in text[page].lower()
        )
    elif isinstance(text, str):
        return (
            "%" in text
            or "$" in text
            or "percent " in text
            or "compensation schedule" in text.lower()
            or "reimbursement schedule" in text.lower()
        )
    else:
        print("contains_reimbursement - Invalid data type")


def is_empty(value): # string_funcs.py
    if pd.isna(value):
        return True
    else:
        empty_values = [None, "", "N/A", "NA", "null", "none", "NaN", np.nan, "nan"]
        return value in empty_values