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

# # Swapping of wordorders in XML source files (N1904LFT)

# ## Table of content <a class="anchor" id="TOC"></a>
# * <a href="#bullet1">1 - Introduction</a>
# * <a href="#bullet2">2 - Load Text-Fabric app and data</a>
# * <a href="#bullet3">3 - Performing the queries</a>
#     * <a href="#bullet3x1">3.1 - Swaps in wordorder</a>

# # 1 - Introduction <a class="anchor" id="bullet1"></a>
# ##### [Back to TOC](#TOC)
# 
# This notebook investigate the occurence of wordorder changes in the XML source files.

# # 2 - Load Text-Fabric app and data <a class="anchor" id="bullet2"></a>
# ##### [Back to TOC](#TOC)

# In[1]:


get_ipython().run_line_magic('load_ext', 'autoreload')
get_ipython().run_line_magic('autoreload', '2')


# In[2]:


# Loading the Text-Fabric code
# Note: it is assumed Text-Fabric is installed in your environment
from tf.fabric import Fabric
from tf.app import use


# In[3]:


# load the N1904 app and data
N1904 = use ("tonyjurg/Nestle1904LFT", version="0.6", hoist=globals())


# In[4]:


# The following will push the Text-Fabric stylesheet to this notebook (to facilitate proper display with notebook viewer)
N1904.dh(N1904.getCss())


# # 3 - Performing the queries <a class="anchor" id="bullet3"></a>

# ## 3.1 - Swaps in wordorder<a class="anchor" id="bullet3x1"></a>
# ##### [Back to TOC](#TOC)

# Differences in wordorder between TF and XML source data

# In[65]:


#range:
#print (F.otype.sInterval("word"))

for node in F.otype.s("word"):
    monad=F.monad.v(node)
    orig_order=F.orig_order.v(node)
    # too bad... it is not in the dataset anymore :(  -> needs to be added in next release again
    if monad != orig_order:
        print (node)


# In[ ]: