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

# # A subtle bug in A.pretty()
# 
# 2019-04-12
# 
# Christiaan Erwich, Gyusang Jin and Cody Kingham spotted weird behaviour in displaying certain verses.
# 
# Look here in Psalm 18:49 :
# 
# ![ps18:49](images/Ps18-49.png)
# 
# The dashed circles enclose the words that are in this verse, the other words belong to the previous part.
# 
# When displaying the sentence atom, which started in the previous part, Text-Fabric *forgot* to remember to
# cutoff this sentence atom at the verse boundary.
# 
# And why was that?
# 
# The root cause is in a few lines in the generic TF display library, not in the BHSA TF-app.
# 
# ```
#       getBoundary(api, n) if d.condenseType is None else
# ```
# 
# Here TF computes the boundary slots of the node in question.
# The thing is, if there is a condense type active, we should not take the boundary of the node itself, but its container of the
# condense type.
# 
# However, in our case we have the situation that `d.condenseType` appeared to be `verse`.
# Yet, there is no condensing, because `d.condensed` is `False`.
# 
# So this part of the condition was wrong and should be:
# 
# ```
#       getBoundary(api, n) if not d.condensed or not d.condenseType else
# ```
# 
# [See the bug on GitHub](https://github.com/annotation/text-fabric/blob/421e7b577f00cbc782ca6ac9f3a132688071f59f/tf/applib/display.py#L435)
# 
# This indeed fixed the bug, as you see below.

# In[1]:


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


# In[2]:


from tf.applib.helpers import dm
from tf.app import use


# Note that we are developing/debugging code. We do not want to download code/data from github,
# and we want to look in our own github clone of the TF app.
# 
# Hence `'bhsa:clone'` and `checkout='local'`.

# In[3]:


A = use('bhsa:clone', checkout='local', hoist=globals())


# # Inspection
# 
# Before we knew what was the matter we made a lens to have a detailed view of our data:
# 
# We gathered all word nodes of Ps 18:47 - 49 and made a table of the objects they are contained in.

# In[4]:


v0 = T.nodeFromSection(('Psalms', 18, 47))
v1 = T.nodeFromSection(('Psalms', 18, 49))
w0 = L.d(v0, otype='word')[0]
w1 = L.d(v1, otype='word')[-1]
allWords = range(w0, w1 + 1)


# We are only interested in certain kind of objects.

# In[5]:


skipTypes = {'book', 'chapter', 'half_verse', 'lex', 'subphrase', 'word'}
nodeTypes = [x[0] for x in C.levels.data if x[0] not in skipTypes]
nodeTypes


# We represent the nodes of different types in slightly different ways.

# In[6]:


repNode = dict(
  verse=lambda n: '{} {}:{}'.format(*T.sectionFromNode(n)),
  sentence=lambda n: F.number.v(n),
  sentence_atom=lambda n: F.number.v(n),
  clause=lambda n: F.number.v(n),
  clause_atom=lambda n: F.number.v(n),
  phrase=lambda n: F.number.v(n),
  phrase_atom=lambda n: F.number.v(n),
)


# And we make a markdown table.

# In[7]:


rows = []
rows.append(' | '.join(nodeTypes))
rows.append(' | '.join(['---'] * len(nodeTypes)))


for w in allWords:
  parents = {F.otype.v(p): repNode[F.otype.v(p)](p) for p in L.u(w) if F.otype.v(p) in nodeTypes}
  rows.append(' | '.join(str(parents.get(nType, 'x')) for nType in nodeTypes))
  
dm('\n'.join(rows))


# This gave us the clue that we had a bunch of objects that crossed the verse boundary.

# # After the fix
# 
# We show the verse after the fix.

# In[8]:


n = T.nodeFromSection(('Psalms', 18, 49))


# In[9]:


A.plain(n)


# In[10]:


A.pretty(n)


# Other example:

# In[11]:


s1 = 1222671
A.show(((s1,),))


# In[ ]: