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

# <a href="http://laf-fabric.readthedocs.org/en/latest/" target="_blank"><img align="left" src="images/laf-fabric-small.png"/></a>
# <a href="http://www.persistent-identifier.nl/?identifier=urn%3Anbn%3Anl%3Aui%3A13-048i-71" target="_blank"><img align="left"src="images/DANS-logo_small.png"/></a>
# <a href="http://www.godgeleerdheid.vu.nl/etcbc" target="_blank"><img align="right" src="images/VU-ETCBC-small.png"/></a>
# <a href="https://www.academic-bible.com/en/online-bibles/biblia-hebraica-stuttgartensia-bhs/read-the-bible-text/" target="_blank"><img align="right" src="files/images/DBG-small.png"/></a>

# # Boundaries
# 
# Some clauses bridge the boundaries between verses. We will list all cases.
# We also check whether clauses ever cross a chapter boundary.

# In[1]:


import sys, os

import laf
from laf.fabric import LafFabric
from etcbc.preprocess import prepare
fabric = LafFabric()


# # Loading the feature data

# In[2]:


version = '4b'
API = fabric.load('etcbc{}'.format(version), 'lexicon,para', 'paragraphs', {
    "xmlids": {"node": False, "edge": False},
    "features": ('''
        otype 
    ''',
    '''
    '''),
    "prepare": prepare,
    "primary": False,
}, verbose='DETAIL')
exec(fabric.localnames.format(var='fabric'))


# # Result
# 
# We collect the verse- and chapter crossing clauses
# and print out the number of occurrences.

# In[5]:


inf('Inspecting all clauses')
chapter_cross = set()
verse_cross = set()
for c in F.otype.s('clause'):
    words = L.d('word', c)
    (first_word, last_word) = (words[0], words[-1])
    if L.u('chapter', first_word) != L.u('chapter', last_word):
        chapter_cross.add(c)
    if L.u('verse', first_word) != L.u('verse', last_word):
        verse_cross.add(c)
inf('Done')
print('# chapter crossing clauses: {:>4}'.format(len(chapter_cross)))
print('# verse   crossing clauses: {:>4}'.format(len(verse_cross)))


Here are the verse crossing clauses:
# In[9]:


for c in verse_cross:
    print('{}\n{}\n'.format(T.passage(c), T.words(L.d('word', c)).replace('\n', ' ')))


# In[ ]: