File size: 3,937 Bytes
96d549d |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 |
import argparse
import os
import cv2
from tqdm import tqdm
import imgcomparison as ic
import mediaoutput
import sources
from analyzer import Analyzer
from slides import SlideDataHelper
class SlideSorter(Analyzer):
"""
Sorts the slides according to their timestamp.
"""
def __init__(self, source, outpath=None, timetable_loc=None, file_format=".png",
comparator=ic.AbsDiffHistComparator(0.98)):
"""
Default initializer
:param path: the path where the slides are located on disk
:param comparator: the comparator to determine, if two slides
are duplicates.
"""
self.comparator = comparator
self.writer = mediaoutput.NullWriter()
if outpath is not None:
if timetable_loc is None:
timetable_loc = os.path.join(outpath, 'timetable.txt')
self.file_format = file_format
self.writer = mediaoutput.TimetableWriter(outpath, timetable_loc, self.file_format)
self.source = source
def sort(self):
"""
Sorting the slides and write the new slides without duplicates
but with a timetable to disk.
"""
slides = []
with tqdm(total=len(self.source), desc="Sorting Slides: ") as pbar:
for i, slide in self.group_slides():
pbar.update(i)
if slide is not None:
slides.append(slide)
return slides
def group_slides(self):
"""
Groups the slides by eliminating duplicates.
:param slides: the list of slides possibly containing duplicates
:return: a list of slides without duplicates
"""
slides = []
sorted_slides = []
loop_counter = 0
page_counter = 1
for slide in self.source.contents():
slides.append(slide)
if slide.marked:
continue
found = False
for other in slides[:-1]:
if self.comparator.are_same(slide.img, other.img):
found = True
if other.marked:
other.reference.add_time(slide.time)
slide.reference = other.reference
slide.marked = True
else:
slide.reference = other
other.add_time(slide.time)
slide.marked = True
yield loop_counter, None
if not found:
slide.page_number = page_counter
yield loop_counter, slide
sorted_slides.append(slide)
page_counter += 1
loop_counter += 1
self.writer.write(sorted_slides)
self.writer.close()
def analyze(self):
for _, slide in self.group_slides():
if slide is None:
continue
yield slide
if __name__ == '__main__':
Parser = argparse.ArgumentParser(description="Slide Sorter")
Parser.add_argument("-d", "--inputslides", help="path of the sequentially sorted slides", default="slides/")
Parser.add_argument("-o", "--outpath", help="path to output slides", default="unique/", nargs='?')
Parser.add_argument("-f", "--fileformat", help="file format of the output images e.g. '.jpg'",
default=".jpg", nargs='?')
Parser.add_argument("-t", "--timetable",
help="path where the timetable should be written (default is the outpath+'timetable.txt')",
nargs='?', default=None)
Args = Parser.parse_args()
if Args.timetable is None:
Args.timetable = os.path.join(Args.outpath, "timetable.txt")
sorter = SlideSorter(sources.ListSource(SlideDataHelper(Args.inputslides).get_slides()), Args.outpath,
Args.timetable, Args.fileformat)
sorter.sort()
|