FilesExpand file tree

 master

/

segment_parser.py

Copy path

Blame

More file actions

Blame

More file actions

Latest commit

 

History

History

History

58 lines (49 loc) · 1.68 KB

 master

/

segment_parser.py

Copy path

Top

File metadata and controls

• Code
• Blame

58 lines (49 loc) · 1.68 KB

Raw

Copy raw file

Download raw file

Open symbols panel

Edit and raw actions

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

from typing import Callable

def has_partial_sentence(text):

words = text.split()

if len(words) >= 2:

prev_word = text.split()[-2].strip()

if prev_word[-1] == ".":

return True

return False

def parse(

segments: list[dict],

fit_function: Callable,

allow_partial_sentences: bool = False,

):

captions = []

caption = {

"start": None,

"end": 0,

"words": [],

"text": "",

}

# Merge words that are not separated by spaces

for s, segment in enumerate(segments):

for w, word in enumerate(segment["words"]):

if w > 0 and word["word"][0] != " ":

segments[s]["words"][w-1]["word"] += word["word"]

segments[s]["words"][w-1]["end"] = word["end"]

del segments[s]["words"][w]

# Parse segments into captions that fit on the video

for segment in segments:

for word in segment["words"]:

if caption["start"] is None:

caption["start"] = word["start"]

text = caption["text"]+word["word"]

caption_fits = allow_partial_sentences or not has_partial_sentence(text)

caption_fits = caption_fits and fit_function(text)

if caption_fits:

caption["words"].append(word)

caption["end"] = word["end"]

caption["text"] = text

else:

captions.append(caption)

caption = {

"start": word["start"],

"end": word["end"],

"words": [word],

"text": word["word"],

}

captions.append(caption)

return captions