In [1]:

    

from collatex import *

json_input = {
    "witnesses" : [ 
        {
            "id": "A",
            "tokens": [ 
                { "t" : "the" }, 
                { "t" : "black" }, 
                { "t" : "dog" } 
            ]
        },
        {
            "id": "B",
            "tokens": [ 
                { "t" : "the" }, 
                { "t" : "black", "tag" : "emph" }, 
                { "t" : "dingo" } 
            ]
        } 
    ]
}

collate_pretokenized_json(json_input, output="html2")


    

    






 

  
A
  
B
 
 

  
the
  
the
 
 

  
black
  
black
 
 

  
dog
  
dingo
 

In [2]:

    

def match_properties(token1_data, token2_data):
    return token1_data == token2_data

collate_pretokenized_json(json_input, properties_filter=match_properties, output="html2")


    

    






 

  
A
  
B
 
 

  
the
  
the
 
 

  
black
  
black
 
 

  
dog
  
dingo
 

In [ ]: