freelawproject / bankruptcy-parser Goto Github PK

if text[-300:].find(form) == -1:
                continue

# Retrieve the longest sequence of consecutive pages, in case errant pages are captured
    longest_sublist = []
    current_sublist = [pages[0]]

    for i in range(1, len(pages)):
        if pages[i] == pages[i - 1] + 1:
            current_sublist.append(pages[i])
        else:
            if len(current_sublist) > len(longest_sublist):
                longest_sublist = current_sublist
            current_sublist = [pages[i]]

    # After the loop, check if the last current sublist is the longest
    if len(current_sublist) > len(longest_sublist):
        longest_sublist = current_sublist

    pages = longest_sublist