#!/usr/bin/env python
# coding: utf-8

# # Compare class with morph where morph=ADV (N1904LFT)

# The following script reads the xml atributes class and morph for tag w and compare them. It will analyse the words whenever morph atribute is 'adv' and the class atribute is unequal to 'adv'. It prints first a number of examples (with verse/word location) and finishes with a table showing the frequency of the cases where morph=adv is not matching class=adv.

# In[16]:


import os
import xml.etree.ElementTree as ET
from tabulate import tabulate

ResultDict = {}

def compare_class_and_morph(file_path):
    ExampleNumber = 0
    tree = ET.parse(file_path)
    root = tree.getroot()

    for w_tag in root.iter('w'):
        # Extract attributes class and morph for the tag w
        class_attr = w_tag.get('class')
        morph_attr = w_tag.get('morph')
        lemma_attr = w_tag.get('lemma')
        ref_attr = w_tag.get('ref')

        # Compare class and morph attributes
        if morph_attr.lower()=='adv' and class_attr!='adv':
            ExampleNumber += 1

            Mapping=f"lemma={lemma_attr}, morph={morph_attr}, class={class_attr}"    
            # Check if this Change already exists in ResultDict
            if Mapping in ResultDict:
               # If it exists, add the count to the existing value
               ResultDict[Mapping]+=1
            else:
               # If it doesn't exist, initialize the count as the value
               ResultDict[Mapping]=1
            if ExampleNumber<=NumberExamples: 
               print(f"At ref={ref_attr} found class={class_attr} and morph={morph_attr} for lemma={lemma_attr}")

    return 

# Following variable should contain the relative path and name of file to check
InputFile="xml/20230628/01-matthew.xml"
# How many difference to show prior to table
NumberExamples = 10

# First check if the file exists, then analyze its content
if os.path.exists(InputFile):
    print(f"Comparing atributes class morph for file {InputFile}\n\nResult:\n\n", end="")
    differences = compare_class_and_morph(InputFile)
    
    # Convert the dictionary into a list of key-value pairs and sort it according to frequency
    UnsortedTableData = [[key, value] for key, value in ResultDict.items()]
    TableData= sorted(UnsortedTableData, key=lambda row: row[1], reverse=True)

    # Produce the table
    headers = ["lemma, morph, class","frequency"]
    print(tabulate(TableData, headers=headers, tablefmt='fancy_grid'))
else:
    print(f"Could not find file {InputFile}.")

    


# In[ ]: