From 3782ca672106840fe5b52963d4e6c9514a36259e Mon Sep 17 00:00:00 2001
From: j <j@mailb.org>
Date: Fri, 22 Mar 2024 11:33:39 +0100
Subject: [PATCH] multiple languages

---
 management/commands/export_subtitles.py | 28 ++++++++++++++++++----
 management/commands/generate_clips.py   | 13 ++++++++--
 render.py                               | 32 ++++++++++++++++++++++---
 3 files changed, 63 insertions(+), 10 deletions(-)

diff --git a/management/commands/export_subtitles.py b/management/commands/export_subtitles.py
index 8782c77..c954e90 100644
--- a/management/commands/export_subtitles.py
+++ b/management/commands/export_subtitles.py
@@ -2,25 +2,43 @@ import json
 import os
 import subprocess
 
+import ox
+
 from django.core.management.base import BaseCommand
 from django.conf import settings
 
+from ...render import add_translations
+
 
 class Command(BaseCommand):
     help = 'export all subtitles for translations'
 
     def add_arguments(self, parser):
-        parser.add_argument('--lang', action='store', dest='lang', default="", help='subtitle language')
+        parser.add_argument('--lang', action='store', dest='lang', default=None, help='subtitle language')
 
     def handle(self, **options):
-        lang = options["lang"]
         import annotation.models
         import item.models
+        lang = options["lang"]
+        if lang:
+            lang = lang.split(',')
+            tlang = lang[1:]
+            lang = lang[0]
+        else:
+            tlang = None
+        if lang == "en":
+            lang = None
+
         for i in item.models.Item.objects.filter(data__type__contains='Voice Over').order_by('sort__title'):
             print("## %s %s" % (i.get("title"), i.public_id))
-
             for sub in i.annotations.all().filter(layer='subtitles').exclude(value='').filter(languages=lang).order_by("start"):
-                if not sub.languages:
-                    print(sub.value.strip() + "\n")
+                if tlang:
+                    value = add_translations(sub, tlang)
+                    value = ox.strip_tags(value)
+                else:
+                    value = sub.value.replace('<br/>', '<br>').replace('<br>\n', '\n').replace('<br>', '\n').strip()
+                    if sub.languages:
+                        value = ox.strip_tags(value)
+                print(value.strip() + "\n")
             print("\n\n\n")
 
diff --git a/management/commands/generate_clips.py b/management/commands/generate_clips.py
index d7ae9f8..23bc61c 100644
--- a/management/commands/generate_clips.py
+++ b/management/commands/generate_clips.py
@@ -33,6 +33,15 @@ class Command(BaseCommand):
 
     def handle(self, **options):
         prefix = options['prefix']
+        lang = options["lang"]
+        if lang:
+            lang = lang.split(',')
+            tlang = lang[1:]
+            lang = lang[0]
+        else:
+            tlang = None
+        if lang == "en":
+            lang = None
         clips = []
         for i in item.models.Item.objects.filter(sort__type='original'):
             qs = item.models.Item.objects.filter(data__title=i.data['title']).exclude(id=i.id)
@@ -103,8 +112,8 @@ class Command(BaseCommand):
                 os.unlink(target)
             os.symlink(src, target)
             subs = []
-            for sub in vo.annotations.filter(layer="subtitles", languages=options["lang"]).exclude(value="").order_by("start"):
-                sdata = get_srt(sub)
+            for sub in vo.annotations.filter(layer="subtitles", languages=lang).exclude(value="").order_by("start"):
+                sdata = get_srt(sub, lang=tlang)
                 subs.append(sdata)
             voice_over[fragment_id][batch] = {
                 "src": target,
diff --git a/render.py b/render.py
index 72d3cf9..f974547 100644
--- a/render.py
+++ b/render.py
@@ -566,9 +566,26 @@ def render_all(options):
         json.dump(_CACHE, fd)
 
 
-def get_srt(sub, offset=0):
+def add_translations(sub, lang):
+    value = sub.value.replace('<br/>', '<br>').replace('<br>\n', '\n').replace('<br>', '\n').strip()
+    if sub.languages:
+        value = ox.strip_tags(value)
+    if lang:
+        for slang in lang:
+            if slang == "en":
+                slang = None
+            for tsub in sub.item.annotations.filter(layer="subtitles", start=sub.start, end=sub.end, languages=slang):
+                tvalue = tsub.value.replace('<br/>', '<br>').replace('<br>\n', '\n').replace('<br>', '\n').strip()
+                if tsub.languages:
+                    tvalue = ox.strip_tags(tvalue)
+                value += '\n' + tvalue
+    return value
+
+def get_srt(sub, offset=0, lang=None):
     sdata = sub.json(keys=['in', 'out', 'value'])
-    sdata['value'] = sdata['value'].replace('<br/>', '<br>').replace('<br>\n', '\n').replace('<br>', '\n')
+    sdata['value'] = sdata['value'].replace('<br/>', '<br>').replace('<br>\n', '\n').replace('<br>', '\n').strip()
+    if lang:
+        sdata['value'] = add_translations(sub, lang)
     if offset:
         sdata["in"] += offset
         sdata["out"] += offset
@@ -592,6 +609,8 @@ def update_subtitles(options):
     duration = int(options['duration'])
     base = int(options['offset'])
     lang = options["lang"]
+    if lang and "," in lang:
+        lang = lang.split(',')
 
     _cache = os.path.join(prefix, "cache.json")
     if os.path.exists(_cache):
@@ -611,8 +630,15 @@ def update_subtitles(options):
                 vo = item.models.Item.objects.filter(data__batch__icontains=batch, data__title__startswith=fragment_id + '_').first()
                 if vo:
                     #print("%s => %s %s" % (clip['src'], vo, vo.get('batch')))
+                    if isinstance(lang, list):
+                        tlang = lang[1:]
+                        lang = lang[0]
+                    else:
+                        tlang = None
+                    if lang == "en":
+                        lang = None
                     for sub in vo.annotations.filter(layer="subtitles").filter(languages=lang).exclude(value="").order_by("start"):
-                        sdata = get_srt(sub, offset)
+                        sdata = get_srt(sub, offset, tlang)
                         subs.append(sdata)
                 else:
                     print("could not find vo for %s" % clip['src'])