Python FileUtils.recursivefilegetter方法代码示例

# 需要导入模块: import FileUtils [as 别名]
# 或者: from FileUtils import recursivefilegetter [as 别名]
def main():
    import FileCabinet
    import FileUtils
    import Volume2
    import Context
    import sys
    import os

    # DEFINE CONSTANTS.
    delim = '\t'
    debug = False
    felecterrors = ['fee', 'fea', 'fay', 'fays', 'fame', 'fell', 'funk', 'fold', 'haft', 'fat', 'fix', 'chafe', 'loft']
    selecttruths = ['see', 'sea', 'say', 'says', 'same', 'sell', 'sunk', 'sold', 'hast', 'sat', 'six', 'chase', 'lost']

    # Locate ourselves in the directory structure.

    cwd = os.getcwd()
    cwdparent = os.path.abspath(os.path.join(cwd, os.pardir))

    # We need to find a directory called 'rulesets,' which we expect to be located
    # either within the working directory or adjacent to it.

    if os.path.isdir(os.path.join(cwd, "rulesets")):
        rulepath = os.path.join(cwd, "rulesets")
    elif os.path.isdir(os.path.join(cwdparent, "rulesets")):
        rulepath = os.path.join(cwdparent, "rulesets")
    else:
        user = input("Please specify a path to the ruleset directory: ")
        if os.path.isdir(user):
            rulepath = user
        else:
            print("Invalid path.")
            sys.exit()

    # Use rulepath to load relevant rules inside modules.

    Volume2.importrules(rulepath)
    Context.importrules(rulepath)

    # Now we enter dialogue with the user. This is all a little 1982,
    # but what can I say? Wetware upgrades are expensive.

    def prompt(promptstring, options):
        user = input(promptstring)
        if user not in options:
            user = prompt(promptstring, options)
        return user

    # Ask the user to tell us how to find files to process.
    print("****************** CorrectOCR 0.1 ******************")
    print()
    print("Do you want the full spiel (explanations, caveats, etc.)")
    user = prompt("y/n : ", ["y", "n"])
    
    if user.lower() == "y":
        spielpath = os.path.join(cwd, "spiel.txt")
        with open(spielpath, encoding = 'utf-8') as file:
            filelines = file.readlines()
        for line in filelines:
            print(line, end='')

    print("\nThis script will correct .txt files, or extract text")
    print("from zipped archives containing one txt file for each page.")
    print("In either case it writes the cleaned files back to their")
    print("original locations with the new suffix '.clean.txt'.")
    print("\nDo you want to unpack .zip files or .txt files?")
    user = prompt("zip or txt: ", ["zip", "txt"])
    suffix = "." + user
    suffixlen = len(suffix)
    
    print("\nThere are two ways to identify the location of the")
    print("files to be corrected.")
    print("\n1. Provide the path to a folder that contains them. I'll")
    print("recursively search subdirectories of that folder as well. Or,")
    print("\n2. Provide a file holding a list of pairtree file identifiers,")
    print("e.g. HathiTrust Volume IDs. I can use those identifiers to infer")
    print("the paths to the files themselves.\n")

    user = prompt("Which option do you prefer (1 or 2)? ", ["1", "2"])
    
    if user == "1":
        rootpath = input("Path to the folder that contains source files: ")
        filelist = FileUtils.recursivefilegetter(rootpath, suffix)
 
    else:
        print("I expect the pairtree identifiers to be listed one per line,")
        print("and to be the only item on a line.")  
        filepath = input("Path to the file that contains pairtree identifiers: ")
        filelist = list()
        with open(filepath, encoding = 'utf-8') as file:
            filelines = file.readlines()

        print("Now I need a path to the folder that contains the pairtree structure.")
        print("If you have multiple folders for different libraries, this should be")
        print("the folder above them all. It should end with a slash.")
        rootpath = input("Path to the folder that contains pairtree: ")
        for line in filelines:
            line = line.rstrip()
            filepath, postfix = FileCabinet.pairtreepath(line, rootpath)
            filename = filepath + postfix + '/' + postfix + suffix
#.........这里部分代码省略.........