pdf_parser/server_documents/preliminary_response/utils.py

import re

def email_extraction(content: str) -> str:
    """
    Extracts emails from a document.
    """
    regex = r"(\w+\-)?\w+@[a-z]+\.[a-z]{2,3}"
    result = []
    emails = re.compile(regex, re.IGNORECASE)
    for email in emails.finditer(content):
        result.append(email.group())
    return result

def telephone_number_extraction(content: str) -> str:
    """
    Extracts telephone number[s?] from a document
    """
    regex = r"\(?\d{3}\)?[\-|\s]\d{3}[\s|\-]\d{4}"
    numbers = re.compile(regex, re.IGNORECASE)
    result = []
    for number in numbers.finditer(content):
        result.append(number.group())
    return result

def address_extraction(content: str) -> str:
    """
    extracts address from the documents.
    """
    regex_address = r"\w+.*\n\w+.*\n\w+.*\w{2,4}\s\d{5}"
    try:
        return re.search(regex_address, content).group(0)
    except:
        return "None"

def case_number_extraction(content: str) -> str:
    """
    Extracts the case number from the documents.
    """
    regex = r"Case\sNo\.\s(\d\:\d{2}\-\w{2}\-\d{5}\-\w{3})"
    results = set()
    case_number = re.compile(regex, re.IGNORECASE)
    for current in case_number.finditer(content):
        results.add(current.groups()[0])
    return list(results)

def plaintiff_extraction(content: str) -> str:
    """
    Extracts the plaintiff from the document
    """
    regex = r"(\w.*)\n\s?\n?\s?(Plaintiffs?|Petitioner)"
    try:
        return re.search(regex, content).group(1)
    except:
        return "None"

def defendent_extraction(content: str) -> str:
    """
    Extracts the defendant from the document
    """
    regex = r"(\w.*?)\n\s?\n?\s?\s?(Defendants|Patent\sOwners?)"
    try:
        return re.search(regex, content).group(1)
    except:
        return "None"

def patent_extraction(content: str) -> str:
    """
    Extracts patent numbers from the document
    """
    regex = r"\d{1,3}\,\d{1,3}\,\d{3}\,?"
    result = set()
    patent = re.compile(regex, re.IGNORECASE)
    for current in patent.finditer(content):
        result.add(current.group().replace(",", ""))
    return list(result)

def acronym_extraction(content: str) -> str:
    regex = r"\(\“([A-Z]{3,4})\”\)"
    results = set()
    acronym = re.compile(regex, re.IGNORECASE)
    for current in acronym.finditer(content):
        results.add(current.group(1))
    return list(results)