subtitle_analyzer package

Submodules

subtitle_analyzer.entry module

subtitle_analyzer.lib module

subtitle_analyzer.lib.extend_ranges(ranges, maxlen)

subtitle_analyzer.lib.find_phrases_pos(sentence, phrases, label)

subtitle_analyzer.lib.find_vocabs_pos(sentence, vocabs, label)

subtitle_analyzer.lib.make_markers(line_phrases)

subtitle_analyzer.lib.merge_ranges(ranges)

subtitle_analyzer.phrase_analyzer module

class subtitle_analyzer.phrase_analyzer.PhraseAnalyzer(lang)

Bases: object

To get phrase information from sentences with timestamp

get_line_phrases(sentences, external=False)

Parse sentences with timestamp into phrases and look up dictionary for explanation

Parameters:

• sentences (list) – sentences with timestamp information

• external (bool) – whether using external translation

subtitle_analyzer.phrase_ass_writer module

class subtitle_analyzer.phrase_ass_writer.PhraseASSWriter(using_marked_subs=True, cn_srtfile=None)

Bases: object

Write phrase information with time stamp into ass file

write(content, assfile, options)

Write phrase information into ass file

Parameters:

• content (list) – phrase information with time stamp

• assfile (str) – ass filename

• options (dict) – argument for ass format

subtitle_analyzer.tbr module

subtitle_analyzer.tbr.merge_content(npfile, vpfile)

subtitle_analyzer.tbr.test_read(npfile)

subtitle_analyzer.vocab_analyzer module

class subtitle_analyzer.vocab_analyzer.VocabAnalyzer(lang)

Bases: object

To get vocabulary information from sentences with timestamp

get_line_vocabs(sentences, external=False)

Parse sentences with timestamp into vocabularies and look up dictionary for explanation

Parameters:

• sentences (list) – sentences with timestamp information

• external (bool) – whether using external translation

subtitle_analyzer.vocab_ass_writer module

class subtitle_analyzer.vocab_ass_writer.VocabASSWriter(srtfile)

Bases: object

Write vocabulary information with time stamp into ass file

write(content, assfile, options)

Write vocabulary information into ass file

Parameters:

• content (list) – vocabulary information with time stamp

• assfile (str) – ass filename

• options (dict) – argument for ass format

Module contents

subtitle_analyzer pacakage

This module demostrates the usage of package subtitle_analyzer.

Install package

$ pip3 install --verbose subtitle_analyzer
$ python -m spacy download en_core_web_trf
$ python -m spacy download es_dep_news_trf

Use as executable

$ sta_vocab --srtfile movie.srt --lang en --assfile en_vocab.ass --external False

$ sta_phrase --srtfile movie.srt --lang en --assfile en_phrase.ass --external False

Write assfile with vocabulary information

from subtitlecore import Subtitle
from subtitle_analyzer import VocabAnalyzer
from subtitle_analyzer import VocabASSWriter
import json

def subtitle_vocab(srtfile, lang, assfile, external):

  phase = {"step": 1, "msg": "Start sentenizing"}
  print(json.dumps(phase), flush=True)

  sf = Subtitle(srtfile, lang)
  sens = sf.sentenize()
  for e in sens:
    print(e)

  phase = {"step": 2, "msg": "Finish sentenizing"}
  print(json.dumps(phase), flush=True)

  analyzer = VocabAnalyzer(lang)
  exs = analyzer.get_line_vocabs(sens, external)
  shown = exs[:20]

  phase = {"step": 3, "msg": "Finish vocabs dictionary lookup", "vocabs": shown}
  print(json.dumps(phase), flush=True)

  if assfile:
    ass_writer = VocabASSWriter(srtfile)
    ass_writer.write(exs, assfile, {"animation": False})

    phase = {"step": 4, "msg": "Finish ass saving"}
    print(json.dumps(phase), flush=True)

Write assfile with phrase information

from subtitlecore import Subtitle
from subtitle_analyzer import PhraseAnalyzer
from subtitle_analyzer import PhraseASSWriter
import json

def subtitle_phrase(srtfile, lang, assfile, external):

  phase = {"step": 1, "msg": "Start sentenizing"}
  print(json.dumps(phase), flush=True)

  sf = Subtitle(srtfile, lang)
  sens = sf.sentenize()
  for e in sens:
    print(e)

  phase = {"step": 2, "msg": "Finish sentenizing"}
  print(json.dumps(phase), flush=True)

  analyzer = PhraseAnalyzer(lang)
  exs = analyzer.get_line_phrases(sens, external)

  phase = {"step": 3, "msg": "Finish phrases dictionary lookup", "vocabs": exs[:10]}
  print(json.dumps(phase), flush=True)

  if assfile:
    ass_writer = PhraseASSWriter(srtfile)
    ass_writer.write(exs, assfile, {"animation": False})

    phase = {"step": 4, "msg": "Finish ass saving"}
    print(json.dumps(phase), flush=True)