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

# # Running Text-Fabric (Nestle1904GBI)
# 
# Basic instructions on loading the Text-Fabric and start using it on your system.

# ## Table of content <a class="anchor" id="TOC">
# * [Step 1: Install Text-Fabric (if not yet installed)](#first-bullet)
# * [Step 2: Raise rate limit on Github](#second-bullet)
# * [Step 3: Load Text-Fabric code](#third-bullet)
# * [Step 4: Load app and data](#fourth-bullet)

# ## Step 1: Install Text-Fabric (if not yet installed) <a class="anchor" id="first-bullet"></a>
# ##### [back to TOC](#TOC)

# ### Python
# 
# You need to have Python on your system. Most systems have it out of the box,
# but alas, that is python2 and we need at least python **3.6**.
# 
# Install it from [python.org](https://www.python.org) or from
# [Anaconda](https://www.anaconda.com/products/distribution).
# 
# ### TF itself
# 
# ```
# pip3 install text-fabric
# ```
# 
# ### When using Jupyter notebook
# 
# You need [Jupyter](http://jupyter.org) or a platform like [Anaconda](https://www.anaconda.com/products/distribution) which includes Jupyter.
# 
# If it is not already installed:
# 
# ```
# pip3 install jupyter
# ```

# ## Step 2: Raise rate limit on Github <a class="anchor" id="second-bullet"></a>
# ##### [back to TOC](#TOC)
# 
# It may be required to increase rate limit for GitHub. [See instructions](https://annotation.github.io/text-fabric/tf/advanced/repo.html) on aquiring and setting the GHPERS variable. 
# See [here](https://www.howtogeek.com/789660/how-to-use-windows-cmd-environment-variables/#autotoc_anchor_2) if you want to set the varibale on windows using the command prompt.

# ## Step 3: Load Text-Fabric code <a class="anchor" id="third-bullet"></a>
# ##### [back to TOC](#TOC)

# In[1]:


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


# In[32]:


# Loading the New Testament TextFabric code

from tf.fabric import Fabric
from tf.app import use


# ## Step 4: Load app and data <a class="anchor" id="fourth-bullet"></a>
# ##### [back to TOC](#TOC)

# In[48]:


# load the app and data
N1904 = use ("tonyjurg/Nestle1904GBI:clone", hoist=globals())


# In[49]:


Search0 = '''
word sp=noun
'''
Search0 = NA.search(Search0)
N1904.show(Search0, start=1, end=3, condensed=True, extraFeatures={'sp', 'clauserule', 'phrasefunction', 'formaltag', 'functionaltag', 'type', 'case', 'ln'}, withNodes=False)


# # Dump some data

# In[42]:


show_book = T.nodeFromSection(('Jude',))

for verse in L.d(show_book, 'verse'):
    
    print('{} {}:{}'.format(*T.sectionFromNode(verse)))
    print('\t\t', T.text(verse))
    


# In[18]:


print(E.__dict__)


# In[20]:


print(N.__dict__)


# In[13]:


print(F.__dict__)


# In[15]:


print(L.__dict__)


# In[105]:


for chapter in L.d(show_book, 'chapter'):
    print(F.book.v(show_book), '§', F.chapter.v(chapter))
    
    for verse in L.d(chapter, 'verse'):
        book,chapter,vrs = T.sectionFromNode(verse)
        print(f'({chapter}:{vrs}) {T.text(verse)}', end='\n')
    print('\n')


# In[ ]:





# In[19]:


max=10
count=0
for node in F.otype.s('word'):
    functionaltag=F.functionaltag.v(node)
    formaltag=F.formaltag.v(node)
    if formaltag != functionaltag:
        count+=1
        book=F.book_long.v(node)
        chapter=F.chapter.v(node)
        verse=F.verse.v(node)
        word=F.word.v(node)
        print (count,' - ',book,chapter,':',verse,'=\t',word,'\tformaltag:',formaltag,'\tfunctionaltag:',functionaltag)
    if count==max: break
    


# In[20]:


# print value frequency for feature gn
ValueFreq = {}

for node in F.otype.s('word'):
    gn=F.gn.v(node)
    ValueFreq[gn] = ValueFreq.setdefault(gn, 0) + 1

print (ValueFreq)


# In[21]:


# print  frequency for feature ln,lex_dom being populated
ValueFreq = {}

for node in F.otype.s('word'):
    LnPresent='no'
    if F.ln.v(node)!='': LnPresent='yes'
    ValueFreq[LnPresent] = ValueFreq.setdefault(LnPresent, 0) + 1

print (ValueFreq)


# In[22]:


FeatureList = {'case', 'type', 'phrasetype', 'degree', 'mood', 'nu', 'number', 'person', 'sp', 'tense', 'voice', 'gn' }
for Feature in FeatureList:
    ValueFreq = {}
    for node in F.otype.s('word'):
        # implementation of pseudo: gn=F.{Feature}.v(node)
        Value= getattr(F, Feature).v(node)
        ValueFreq[Value] = ValueFreq.setdefault(Value, 0) + 1
    print ('Feature:',Feature,' Frequency:',ValueFreq)
    


# # Zip up the final product

# In[27]:


N1904.zipAll()


# In[ ]: