grep_AW.py

# grep_AW.py

import re, sys

def urls(line):
    if "}}}" in line:
        idx = line.find('}}}')
        line = line[:idx]
        idx = line.rfind('http:')
        url_ = line[idx:]
        return url_
    else:
        return ""

def clean(line, chr_):
    """
    Cleans lines in RTF files such as those above. Heavy lifting is done when line has a URL.
    If a line has a URL at the end, it first extracts the URL, cleans the line,
    then returns the cleaned line with the URL replaced at the end.

    If there are one or more strings in line beginning with chr_ (e.g., '\\',
    """
    url_ = urls(line)
    if '{' in line:
        idx = line.find('{')
        return line[:idx] + url_
    n = None
    while True:
        if chr_ in line:
            idx = line.find(chr_)
            n = idx + 1
            # return if end of line is reached
            if n >= len(line):
                return line
            while True:
                if n < len(line) and line[n] != ' ':
                    str_ = line[idx:n]
                # remove str_ and return line + _url, if space char reached in line
                else:
                    str_ = line[idx:n]
                    line = line.replace(str_, "")
                    return line + url_
                n += 1
        else:
            return line + url_

def clean_file(path):
    f = open(path, 'r')
    line_list = []
    for line in f:
        line_list.append(clean(line, '\\'))
    f.close()
    return line_list

def print_instructions():
    print("Key (ignoring quotes): ' ' is a space, 'x' means any char except ' ' or '='")
    print("If 1st 2 chars are:")
    print("'=x' --> case insensitive, word")
    print("' =' --> case sensitive, word")
    print("' x' --> case sensitive, string")
    print("'xx' --> case insensitive, string")
    print("'==' --> start a new search of same file")

def print_searching(count):
    if count == 0:
        print("Searching", filename)
    else:
        print("Searching", filename, "within hits so far,")

def grep_line_list(line_list, line_list0, filename):
    search = input("Enter search string or word; enter nothing to quit: ")
    if search == '==':
        line_list = line_list0
        print()
        print("Starting a fresh search of", filename)
        search = input("Enter search string or word; enter nothing to quit: ")
    if not search:
        print("Bye")
        sys.exit()
    #'x': case insensitive
    elif search[0] != ' ':
        #'xx': case insensitive; not word
        if search[0] != '=':
            p = re.compile(search, re.I)
        #'x=': case insensitive; word
        else:
            search = "\\b" + search[1:] + "\\b"
            p = re.compile(search, re.I)
    #' ': case sensitive
    else:
        #' x': case sensitive; not word
        if search[1] != '=':
            search = search[1:]
            p = re.compile(search)
        #' =': case sensitive; word
        else:
            search = search[2:]
            search = "\\b" + search + "\\b"
            p = re.compile(search)

    line_list2 = []
    count = 0
    for line in line_list:
        if p.search(line):
            line_list2.append(line)
            count += 1
    line_list = line_list2
    return line_list, count

def print_results(line_list, count):
    print("==================================")
    print_count_only = input("print hits plus count? Enter nothing; print count only? Enter anything: ")

    if print_count_only == "":
        print("Printing hits and count:")
        line_list.sort()
        for line in line_list:
            print()
            print(line)
        print()
        print("count =", count)
    else:
        print("Printing count only:")
        print()
        print("count =", count)
    print()

def main():
    count = 0
    line_list0 = clean_file(path)
    line_list = line_list0
    print_instructions()
    while True:
        print_searching(count)
        line_list, count = grep_line_list(line_list, line_list0, filename)
        print()
        print_results(line_list, count)

path = "C:\\Users\Dick\Desktop\Documents\\Notes\\ActiveWords.rtf"
filename = 'ActiveWords.rtf'

if __name__ == '__main__':
    main()