fix split

OpenshotService/openshot_video_generator.py

@@ -234,6 +234,33 @@ def call_anchor(fileName,avatar):
 
     fr.close()
     fw.close()
+def sentence_time_ratio(text,maxLen):
+    
+    total_len = len(text)
+    if total_len > maxLen:
+        left_word = total_len % maxLen
+        times = int(math.ceil(total_len/maxLen))
+        if left_word < 5:
+            times+=1
+        sen_len = int(total_len/times)
+    
+        time_ratio = [None]*times
+        sentences = [None]*times
+        print(times,',',total_len,",",sen_len)
+        for t in range(times):
+            
+            sentences[t] = text[t*sen_len:t*sen_len+sen_len]
+            time_ratio[t] = len(sentences[t])/total_len
+    else:
+        
+        time_ratio = [1]
+        sen_len = total_len
+        sentences = [text]
+    
+    return sen_len, time_ratio, sentences
+        
+        
+    
 def parse_script(file_path,gt_list):
     with open(file_path, 'r') as f:
         raw_lines = [line.strip() for line in f]
@@ -256,40 +283,26 @@ def parse_script(file_path,gt_list):
         script['stop'] = stop_sec
         script['duration'] = abs(duration)
         dict_list.append(script)
+    '''
+    for dic in dict_list:
+        print(dic)
+    '''
     new_idx = 0
     splitted_dict = []
- 
     for dic in dict_list:
-        #螢幕寬度只能容納13個字
-        if len(dic['content'])>13:
-            times = math.ceil(len(dic['content'])/13)
-            time_ratio = [None] *times
-            left_words = len(dic['content'])%13
-            for t in range(times):
-                if t != (times-1):
-                    time_ratio[t] = 1 * dic['duration']/times
-                else:
-                    time_ratio[t] = 1 * dic['duration'] / times
-            for t in range(times):
-                if True:
-                #if time_ratio[t]>0.22:#about less than 3 words
-                    new_dic = {}
-                    new_dic['index'] = new_idx
-                    new_dic['content'] = dic['content'][t*13:t*13+13]
-                    start_plus = 0
-                    for t2 in range(t):
-                        start_plus += time_ratio[t2]
-                    new_dic['start'] =  dic['start'] + start_plus+0.1
-                    new_dic['stop'] = new_dic['start']+time_ratio[t]
-                    new_dic['duration'] = time_ratio[t]-0.05
-                    splitted_dict.append(new_dic)
-                    new_idx+=1
-                #else:
-                 #   splitted_dict[new_idx-1]['content']+=dic['content']
-        else:
-            dic['index'] = new_idx
+        sen_len, time_ratio, sentences = sentence_time_ratio(dic['content'],13)
+        for s in range(len(sentences)):
+            new_dict = {}
+            new_dict['index'] = new_idx
+            start = dic['start']
+            for t in range(s):
+                start += (dic['duration']*time_ratio[t])
+            new_dict['start'] = start
+            new_dict['duration'] = dic['duration'] * time_ratio[s]
+            new_dict['content'] = sentences[s]
             new_idx+=1
-            splitted_dict.append(dic)
+            splitted_dict.append(new_dict)
+    
     return splitted_dict
 def adjustSub_by_text_similarity(gts,gens):
     adjusted = [None]*len(gens)