Question about reviseParagraphClassification

[KevinDanikowski]

reviseParagraphClassification returns paragraphs, but it doesn't look like the paragraphs get manipulated in any way, and that reviseParagraphs is where the new filtered data is. Is reviseParagraphs supposed to be returned instead of paragraphs ?

I added the python reference code for convenience.

def revise_paragraph_classification(paragraphs, max_heading_distance=MAX_HEADING_DISTANCE_DEFAULT):
    """
    Context-sensitive paragraph classification. Assumes that classify_pragraphs
    has already been called.
    """
    # copy classes
    for paragraph in paragraphs:
        paragraph.class_type = paragraph.cf_class

    # good headings
    for i, paragraph in enumerate(paragraphs):
        if not (paragraph.heading and paragraph.class_type == 'short'):
            continue
        j = i + 1
        distance = 0
        while j < len(paragraphs) and distance <= max_heading_distance:
            if paragraphs[j].class_type == 'good':
                paragraph.class_type = 'neargood'
                break
            distance += len(paragraphs[j].text)
            j += 1

    # classify short
    new_classes = {}
    for i, paragraph in enumerate(paragraphs):
        if paragraph.class_type != 'short':
            continue
        prev_neighbour = get_prev_neighbour(i, paragraphs, ignore_neargood=True)
        next_neighbour = get_next_neighbour(i, paragraphs, ignore_neargood=True)
        neighbours = set((prev_neighbour, next_neighbour))
        if neighbours == set(['good']):
            new_classes[i] = 'good'
        elif neighbours == set(['bad']):
            new_classes[i] = 'bad'
        # it must be set(['good', 'bad'])
        elif (prev_neighbour == 'bad' and get_prev_neighbour(i, paragraphs, ignore_neargood=False) == 'neargood') or \
             (next_neighbour == 'bad' and get_next_neighbour(i, paragraphs, ignore_neargood=False) == 'neargood'):
            new_classes[i] = 'good'
        else:
            new_classes[i] = 'bad'

    for i, c in new_classes.items():
        paragraphs[i].class_type = c

    # revise neargood
    for i, paragraph in enumerate(paragraphs):
        if paragraph.class_type != 'neargood':
            continue
        prev_neighbour = get_prev_neighbour(i, paragraphs, ignore_neargood=True)
        next_neighbour = get_next_neighbour(i, paragraphs, ignore_neargood=True)
        if (prev_neighbour, next_neighbour) == ('bad', 'bad'):
            paragraph.class_type = 'bad'
        else:
            paragraph.class_type = 'good'

    # more good headings
    for i, paragraph in enumerate(paragraphs):
        if not (paragraph.heading and paragraph.class_type == 'bad' and paragraph.cf_class != 'bad'):
            continue
        j = i + 1
        distance = 0
        while j < len(paragraphs) and distance <= max_heading_distance:
            if paragraphs[j].class_type == 'good':
                paragraph.class_type = 'good'
                break
            distance += len(paragraphs[j].text)
            j += 1