textindex.py 文件源码

def main(input_dir):
    """Walk through all the not-yet-processed image files in the given
    directory, extracting any text from them and adding that text to an
    inverted index.
    """
    # Create a client object for the Vision API
    vision = VisionApi()
    # Create an Index object to build query the inverted index.
    index = Index()

    allfileslist = []
    # Recursively construct a list of all the files in the given input
    # directory.
    for folder, subs, files in os.walk(input_dir):
        for filename in files:
            allfileslist.append(os.path.join(folder, filename))

    fileslist = []
    for filename in allfileslist:
        # Look for text in any files that have not yet been processed.
        if index.document_is_processed(filename):
            continue
        fileslist.append(filename)

    for filenames in batch(fileslist):
        get_text_from_files(vision, index, filenames)
# [END get_text]