# load the BHS app and data
BHS = use ("etcbc/BHSA",hoist=globals())

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

JHWHQuery = '''
book
  chapter
     verse
       word g_cons=JHWH 
'''

JHWHResults = BHS.search(JHWHQuery)

# Libraries for table formatting and regular expressions
import re
import pandas as pd
from IPython.display import display

# Initialize dictionary for storing results
resultDict = {}

# Process each item in the JHWHResults
for item in JHWHResults:
    node = item[3]
    # Get the pointed and unpointed representation of a word occurrence
    pointedWord = F.g_word.v(node)
    hebrewWord = F.g_word_utf8.v(node)
        
    # Remove cantillations in the BSHA (presented by digits)
    vocalizedWord = re.sub(r'\d', '', pointedWord)
    
    if vocalizedWord in resultDict:
        # If exists, increment the frequency count
        resultDict[vocalizedWord][0] += 1
    else:
        # Initialize count and store the first occurrence
        firstOccurrence = T.sectionFromNode(node)
        resultDict[vocalizedWord] = [1, firstOccurrence, hebrewWord]  

# Convert the dictionary into a DataFrame and sort by frequency
tableData = pd.DataFrame(
    [[key, value[0], value[1], value[2]] for key, value in resultDict.items()],
    columns=["Pointed Word", "Frequency", "First Occurrence", "Hebrew Word"]
)
tableData = tableData.sort_values(by="Frequency", ascending=False)

# Display the table
display(tableData)

import pandas as pd
from bokeh.plotting import figure, show, output_notebook
from bokeh.models import ColumnDataSource, HoverTool
from bokeh.layouts import column

# Enable Bokeh output in the notebook
output_notebook()

# Ensure tableData has the exact column names you need
tableData.columns = ["Pointed Word", "Frequency", "First Occurrence", "Hebrew Word"]

# Create a ColumnDataSource for the Bokeh plot
source = ColumnDataSource(tableData)

# Create a Bokeh figure for the bar chart
p = figure(
    x_range=tableData['Hebrew Word'].tolist(),  # convert x_range to list explicitly
    height=800, 
    width=1000,
    title="Frequency of Tetragrammaton vocalisation in biblical text",
    toolbar_location="right"
)

# Create bar chart
p.vbar(x='Hebrew Word', top='Frequency', width=0.5, source=source)

# Add labels and customizations
p.xaxis.axis_label = "Hebrew Word"
p.yaxis.axis_label = "Frequency"
p.xaxis.major_label_orientation = "horizontal"
p.xaxis.major_label_text_font_size = "26pt"  # Increase font size of x-axis labels

# Add hover tool
hover = HoverTool()
hover.tooltips = [
    ("Pointed Word", "@{Pointed Word}"),
    ("Frequency", "@Frequency"),
    ("First Occurrence", "@{First Occurrence}"),
    ("Hebrew Word", "@{Hebrew Word}")
]
p.add_tools(hover)

# Show the interactive plot
show(p)

adonaiQuery = '''
word g_cons=JHWH g_word~O.*W.*@
'''

adonaiResults = BHS.search(adonaiQuery)

BHS.table(adonaiResults, condensed=False, extraFeatures={'voc_lex'})

adonaiQuery2 = '''
word lex=JHWH/ g_word~O.*W.*@
'''

adonaiResults2 = BHS.search(adonaiQuery2)

featureList=Fall()
for item in adonaiResults2:
    Node=item[0]
    for feature in featureList:
        featureValue=Fs(feature).v(Node)
        if type(featureValue)!=type(None): print (feature,'=',featureValue)
    break

import re
import pandas as pd
from IPython.display import display

# Initialize dictionary for storing results
resultDict = {}

# Process each item in the JHWHResults
for item in JHWHResults:
    node = item[3]
    # Get the pointed and unpointed representation of a word occurrence
    pointedWord = F.g_word.v(node)
    hebrewWord = F.g_word_utf8.v(node)
        
    # Remove cantillations in the BHSA (presented by digits)
    vocalizedWord = re.sub(r'\d', '', pointedWord)
    
    if vocalizedWord in resultDict:
        # If it exists, add the count to the existing value
        resultDict[vocalizedWord][0] += 1 # Increase frequency count
    else:
        # If it doesn't exist, initialize the count and store firstOccurrence
        firstOccurrence = T.sectionFromNode(node)
        resultDict[vocalizedWord] = [1, firstOccurrence, hebrewWord]  

# Convert the dictionary into a DataFrame and sort by frequency
tableData = pd.DataFrame(
    [[key, value[0], value[1], value[2]] for key, value in resultDict.items()],
    columns=["Pointing", "Frequency", "First Occurrence", "Hebrew Word"]
)
tableData = tableData.sort_values(by="Frequency", ascending=False)

# Display the table
display(tableData)

qereQuery = '''
word qere_utf8 g_cons=JHWH
'''

qereResults = BHS.search(qereQuery)