pdf_parser/expert_report/parse_expert_pdf_utils.py

from collections import defaultdict
import re
from distutils.filelist import findall


def date_extraction(content):
    regex = r"((\d{2}\/\d{3}\,\d{3}\s)\d{1,2}\/\d{2}\/\d{4}|(Entered\:\s|:Filing\sDate\:\s|Date\:\s)[A-Z]\w+\s\d{1,2}\,\s\d{4})"
    date = re.search(regex, content).groups()[0]
    return date.strip()

def address_extraction(content):
    regex = r"Address\:([\s\S].*)\s\d{6}\-\d{4}\swww" 
    data = re.search(regex, content).groups()[0]
    if data == None:
        print("N")
    return data.strip()

def case_number_extraction(content):
    # dict_case_numbers = defaultdict(int)
    # case_number_info = re.findall("Case\sNo\.\s(\d\:\d{2}\-\w{2}\-\d{5}\-\w{3})", content)
    # case_number = ""
    # for element in case_number_info:
    #     dict_case_numbers[element] += 1
    # for mykey, value in dict_case_numbers.items():
    #     case_number = mykey
    # return case_number
    regex = r"Case\sNo\.\s(\d\:\d{2}\-\w{2}\-\d{5}\-\w{3})"  # Case\sNo\.\s(\d\:\d{2}\-\w{2}\-\d{5}\-\w{3})
    results = []
    case_number = re.compile(regex, re.IGNORECASE)
    for current in case_number.finditer(content):
        results.append(current.groups()[0])
    return list(set(results))


def expert_name_extraction(content):
    regex = r"\bEXPERT\sREPORT\sOF\s(.*?),.*(REGARDING|Invalidity)?"  # "\bEXPERT\sREPORT\sOF\s(.+?),"
    results = []
    expert_name = re.compile(regex, re.IGNORECASE)
    for current in expert_name.finditer(content):
        results.append(current.groups()[0])
    return list(set(results))


def plaintiff_extraction(content):
    regex = r"\bDIVISION([\s\S]*?)Plaintiff\,"  # "OF\s\w+(\s.*?)\,.*Plaintiff"  # "(.*)\s\nPlaintiff,"
    results = []
    plaintiff = re.compile(regex, re.IGNORECASE)
    for current in plaintiff.finditer(content):
        results.append(current.groups()[0].strip())
    return results


def defendent_extraction(content):
    # "Plaintiff.*\n.*v\.([\s\S]*?)Defendant"   # "\bv\.([\s\S]*?)Defendant"
    regex = r"Plaintiff.*v\.([\s\S]*?)Defendant"
    results = []
    defendent = re.compile(regex, re.IGNORECASE)
    for current in defendent.finditer(content):
        results.append(current.groups()[0].strip())
    return results


def patent_extraction(content):
    regex = r"(U\.S\.\sPATENT\sNO.\s\d\,\d{3}\,\d{3})"  # "U\.S\.\sPATENT\sNO.*\d{1,2}\,\d{3}\,\d{3}"
    # results = []
    # patent = re.compile(regex, re.IGNORECASE)
    # for current in patent.finditer(content):
    #     results.append(current.groups())
    # patent_info = re.search(regex, content).groups()[0].strip()
    patent_info = re.findall(regex, content)
    return patent_info


def law_firm_extraction(content):
    regex = r""
    results = []
    firm = re.compile(regex, re.IGNORECASE)
    for current in firm.finditer(content):
        results.append(current.groups()[0].strip())
    return results


def on_behalf_of_extraction(content):
    regex = "on\sbehalf\sof(.*?)(C|c)ase"
    on_behalf_of = re.search(regex, content).groups()[0].strip()
    return on_behalf_of


def hourly_compensation(content):
    regex = "\$\s\d+"
    pay = re.findall(regex, content)
    return pay


def ref_patents(content):
    return


def acronym_extraction(content):
    regex = r"\([A-Z]+\)"
    # results = []
    # acronym = re.compile(regex, re.IGNORECASE)
    # for current in acronym.finditer(content):
    #     results.append(current)
    acronym = re.findall(regex, content)
    return list(set(acronym))