#!/usr/bin/env python # coding: utf-8 # ## Creating Text-Fabric dataset (from LowFat XML trees) # # Version: 0.4 (July 25, 2023 - major updates; changing feature names; updated documentation) # # ## Table of content # * 1 - Introduction # * 2 - Read LowFat XML data and store in pickle # * 2.1 - Import various libraries # * 2.2 - Initialize global data # * 2.3 - Add parent info to each node of the XML tree # * 2.4 - Process the XML data and store dataframe in pickle # * 3 - Production Text-Fabric from pickle input # * 3.1 - Load libraries and initialize some data # * 3.2 - Optionaly export to Excel for investigation # # 1 - Introduction # ##### [Back to TOC](#TOC) # # The source data for the conversion are the LowFat XML trees files representing the macula-greek version of the Nestle 1904 Greek New Testment (British Foreign Bible Society, 1904). The starting dataset is formatted according to Syntax diagram markup by the Global Bible Initiative (GBI). The most recent source data can be found on github https://github.com/Clear-Bible/macula-greek/tree/main/Nestle1904/lowfat. # # Attribution: "MACULA Greek Linguistic Datasets, available at https://github.com/Clear-Bible/macula-greek/". # # The production of the Text-Fabric files consist of two phases. First one is the creation of piclke files (section 2). The second phase is the the actual Text-Fabric creation process (section 3). The process can be depicted as follows: # #

# # 2 - Read LowFat XML data and store in pickle # ##### [Back to TOC](#TOC) # # This script harvests all information from the LowFat tree data (XML nodes), puts it into a Panda DataFrame and stores the result per book in a pickle file. Note: pickling (in Python) is serialising an object into a disk file (or buffer). See also the [Python3 documentation](https://docs.python.org/3/library/pickle.html). # # Within the context of this script, the term 'Leaf' refers to nodes that contain the Greek word as data. These nodes are also referred to as 'terminal nodes' since they do not have any children, similar to leaves on a tree. Additionally, Parent1 represents the parent of the leaf, Parent2 represents the parent of Parent1, and so on. For a visual representation, please refer to the following diagram. # #

# # For a full description of the source data see document [MACULA Greek Treebank for the Nestle 1904 Greek New Testament.pdf](https://github.com/Clear-Bible/macula-greek/blob/main/doc/MACULA%20Greek%20Treebank%20for%20the%20Nestle%201904%20Greek%20New%20Testament.pdf) # ## 2.1 - Import various libraries # ##### [Back to TOC](#TOC) # In[1]: import pandas as pd import sys import os import time import pickle import re #regular expressions from os import listdir from os.path import isfile, join import xml.etree.ElementTree as ET # ## 2.2 - Initialize global data # ##### [Back to TOC](#TOC) # # The following global data initializes the script, gathering the XML data to store it into the pickle files. # # IMPORTANT: To ensure proper creation of the Text-Fabric files on your system, it is crucial to adjust the values of BaseDir, InputDir, and OutputDir to match the location of the data and the operating system you are using. In this Jupyter Notebook, Windows is the operating system employed. # In[2]: BaseDir = 'D:\\' XmlDir = BaseDir+'xml\\' PklDir = BaseDir+'pkl\\' XlsxDir = BaseDir+'xlsx\\' # note: create output directory prior running this part # key: filename, [0]=book_long, [1]=book_num, [3]=book_short bo2book = {'01-matthew': ['Matthew', '1', 'Matt'], '02-mark': ['Mark', '2', 'Mark'], '03-luke': ['Luke', '3', 'Luke'], '04-john': ['John', '4', 'John'], '05-acts': ['Acts', '5', 'Acts'], '06-romans': ['Romans', '6', 'Rom'], '07-1corinthians': ['I_Corinthians', '7', '1Cor'], '08-2corinthians': ['II_Corinthians', '8', '2Cor'], '09-galatians': ['Galatians', '9', 'Gal'], '10-ephesians': ['Ephesians', '10', 'Eph'], '11-philippians': ['Philippians', '11', 'Phil'], '12-colossians': ['Colossians', '12', 'Col'], '13-1thessalonians':['I_Thessalonians', '13', '1Thess'], '14-2thessalonians':['II_Thessalonians','14', '2Thess'], '15-1timothy': ['I_Timothy', '15', '1Tim'], '16-2timothy': ['II_Timothy', '16', '2Tim'], '17-titus': ['Titus', '17', 'Titus'], '18-philemon': ['Philemon', '18', 'Phlm'], '19-hebrews': ['Hebrews', '19', 'Heb'], '20-james': ['James', '20', 'Jas'], '21-1peter': ['I_Peter', '21', '1Pet'], '22-2peter': ['II_Peter', '22', '2Pet'], '23-1john': ['I_John', '23', '1John'], '24-2john': ['II_John', '24', '2John'], '25-3john': ['III_John', '25', '3John'], '26-jude': ['Jude', '26', 'Jude'], '27-revelation': ['Revelation', '27', 'Rev']} # ## 2.3 - Add parent info to each node of the XML tree # ##### [Back to TOC](#TOC) # # In order to be able to traverse from the 'leafs' upto the root of the tree, it is required to add information to each node pointing to the parent of each node. The terminating nodes of an XML tree are called "leaf nodes" or "leaves." These nodes do not have any child elements and are located at the end of a branch in the XML tree. Leaf nodes contain the actual data or content within an XML document. In contrast, non-leaf nodes are called "internal nodes," which have one or more child elements. # # (Attribution: the concept of following functions is taken from https://stackoverflow.com/questions/2170610/access-elementtree-node-parent-node) # In[3]: def addParentInfo(et): for child in et: child.attrib['parent'] = et addParentInfo(child) def getParent(et): if 'parent' in et.attrib: return et.attrib['parent'] else: return None # ## 2.4 - Process the XML data and store dataframe in pickle # ##### [Back to TOC](#TOC) # # This code processes books in the correct order. Firstly, it parses the XML and adds parent information to each node. Then, it loops through the nodes and checks if it is a 'leaf' node, meaning it contains only one word. If it is a 'leaf' node, the following steps are performed: # # * Adds computed data to the 'leaf' nodes in memory. # * Traverses from the 'leaf' node up to the root and adds information from the parent, grandparent, and so on, to the 'leaf' node. # * Once it reaches the root, it stops and stores all the gathered information in a dataframe that will be added to the full_dataframe. # * After processing all the nodes for a specific book, the full_dataframe is exported to a pickle file specific to that book. # # Note that this script takes a long time to execute (due to the large number of itterations). However, once the XML data is converted to PKL, there is no need to rerun (unless the source XML data is updated). # In[9]: # set some globals WordOrder=1 # stores the word order as it is found in the XML files (unique number for each word in the full corpus) CollectedItems= 0 # process books in order for bo, bookinfo in bo2book.items(): CollectedItems=0 SentenceNumber=0 WordGroupNumber=0 full_df=pd.DataFrame({}) book_long=bookinfo[0] booknum=bookinfo[1] book_short=bookinfo[2] InputFile = os.path.join(XmlDir, f'{bo}.xml') OutputFile = os.path.join(PklDir, f'{bo}.pkl') print(f'Processing {book_long} at {InputFile}') DataFrameList = [] # Send XML document to parsing process tree = ET.parse(InputFile) # Now add all the parent info to the nodes in the xtree [important!] addParentInfo(tree.getroot()) start_time = time.time() # walk over all the XML data for elem in tree.iter(): if elem.tag == 'sentence': # add running number to 'sentence' tags SentenceNumber+=1 elem.set('SN', SentenceNumber) if elem.tag == 'wg': # add running number to 'wg' tags WordGroupNumber+=1 elem.set('WGN', WordGroupNumber) if elem.tag == 'w': # all nodes containing words are tagged with 'w' # show progress on screen CollectedItems+=1 if (CollectedItems%100==0): print (".",end='') #Leafref will contain list with book, chapter verse and wordnumber Leafref = re.sub(r'[!: ]'," ", elem.attrib.get('ref')).split() #push value for word_order to element tree elem.set('word_order', WordOrder) WordOrder+=1 # add some important computed data to the leaf elem.set('LeafName', elem.tag) elem.set('word', elem.text) elem.set('book_long', book_long) elem.set('booknum', int(booknum)) elem.set('book_short', book_short) elem.set('chapter', int(Leafref[1])) elem.set('verse', int(Leafref[2])) # folling code will trace down parents upto the tree and store found attributes parentnode=getParent(elem) index=0 while (parentnode): index+=1 elem.set('Parent{}Name'.format(index), parentnode.tag) elem.set('Parent{}Type'.format(index), parentnode.attrib.get('type')) elem.set('Parent{}Appos'.format(index), parentnode.attrib.get('appositioncontainer')) elem.set('Parent{}Class'.format(index), parentnode.attrib.get('class')) elem.set('Parent{}Rule'.format(index), parentnode.attrib.get('rule')) elem.set('Parent{}Role'.format(index), parentnode.attrib.get('role')) elem.set('Parent{}Cltype'.format(index), parentnode.attrib.get('cltype')) elem.set('Parent{}Unit'.format(index), parentnode.attrib.get('unit')) elem.set('Parent{}Junction'.format(index), parentnode.attrib.get('junction')) elem.set('Parent{}SN'.format(index), parentnode.attrib.get('SN')) elem.set('Parent{}WGN'.format(index), parentnode.attrib.get('WGN')) currentnode=parentnode parentnode=getParent(currentnode) elem.set('parents', int(index)) #this will add all elements found in the tree to a list of dataframes DataFrameChunk=pd.DataFrame(elem.attrib, index={'word_order'}) DataFrameList.append(DataFrameChunk) #store the resulting DataFrame per book into a pickle file for further processing full_df = pd.concat([df for df in DataFrameList]) output = open(r"{}".format(OutputFile), 'wb') pickle.dump(full_df, output) output.close() print("\nFound ",CollectedItems, " items in %s seconds\n" % (time.time() - start_time)) # # 3 - Nestle1904LFT Text-Fabric production from pickle input # ##### [Back to TOC](#TOC) # # This script creates the Text-Fabric files by recursive calling the TF walker function. # API info: https://annotation.github.io/text-fabric/tf/convert/walker.html # # The pickle files created by the script in section 2.4 are stored on Github location [/resources/pickle](https://github.com/tonyjurg/Nestle1904LFT/tree/main/resources/pickle). # ## 3.1 - Load libraries and initialize some data # ##### [Back to TOC](#TOC) # # The following global data initializes the Text-Fabric conversion script. # # IMPORTANT: To ensure the proper creation of the Text-Fabric files on your system, it is crucial to adjust the values of BaseDir, PklDir, etc., to match the location of the data and the operating system you are using. This Jupyter Notebook employs the Windows operating system. # In[2]: import pandas as pd import os import re import gc from tf.fabric import Fabric from tf.convert.walker import CV from tf.parameters import VERSION from datetime import date import pickle BaseDir = 'D:\\' XmlDir = BaseDir+'xml\\' PklDir = BaseDir+'pkl\\' XlsxDir = BaseDir+'xlsx\\' # key: filename, [0]=book_long, [1]=book_num, [3]=book_short bo2book = {'01-matthew': ['Matthew', '1', 'Matt'], '02-mark': ['Mark', '2', 'Mark'], '03-luke': ['Luke', '3', 'Luke'], '04-john': ['John', '4', 'John'], '05-acts': ['Acts', '5', 'Acts'], '06-romans': ['Romans', '6', 'Rom'], '07-1corinthians': ['I_Corinthians', '7', '1Cor'], '08-2corinthians': ['II_Corinthians', '8', '2Cor'], '09-galatians': ['Galatians', '9', 'Gal'], '10-ephesians': ['Ephesians', '10', 'Eph'], '11-philippians': ['Philippians', '11', 'Phil'], '12-colossians': ['Colossians', '12', 'Col'], '13-1thessalonians':['I_Thessalonians', '13', '1Thess'], '14-2thessalonians':['II_Thessalonians','14', '2Thess'], '15-1timothy': ['I_Timothy', '15', '1Tim'], '16-2timothy': ['II_Timothy', '16', '2Tim'], '17-titus': ['Titus', '17', 'Titus'], '18-philemon': ['Philemon', '18', 'Phlm'], '19-hebrews': ['Hebrews', '19', 'Heb'], '20-james': ['James', '20', 'Jas'], '21-1peter': ['I_Peter', '21', '1Pet'], '22-2peter': ['II_Peter', '22', '2Pet'], '23-1john': ['I_John', '23', '1John'], '24-2john': ['II_John', '24', '2John'], '25-3john': ['III_John', '25', '3John'], '26-jude': ['Jude', '26', 'Jude'], '27-revelation': ['Revelation', '27', 'Rev']} # ## 3.2 - Optionaly export to Excel for investigation # ##### [Back to TOC](#TOC) # # This step is optional. It will allow for manual examining the input data to the Text-Fabric conversion script. # In[11]: # test: sorting the data import openpyxl import pickle #if True: for bo in bo2book: ''' load all data into a dataframe process books in order (bookinfo is a list!) ''' InputFile = os.path.join(PklDir, f'{bo}.pkl') print(f'\tloading {InputFile}...') pkl_file = open(InputFile, 'rb') df = pickle.load(pkl_file) pkl_file.close() df.to_excel(os.path.join(XlsxDir, f'{bo}.xlsx'), index=False) # ## 3.3 - Running the TF walker function # ##### [Back to TOC](#TOC) # # API info: https://annotation.github.io/text-fabric/tf/convert/walker.html # # Explanatory notes about the data interpretation logic are incorporated within the Python code of the director function. # In[3]: TF = Fabric(locations=BaseDir, silent=False) cv = CV(TF) ############################################### # Common helper functions # ############################################### #Function to prevent errors during conversion due to missing data def sanitize(input): if isinstance(input, float): return '' if isinstance(input, type(None)): return '' else: return (input) # Function to expand the syntactic categories of words or wordgroup # See also "MACULA Greek Treebank for the Nestle 1904 Greek New Testament.pdf" # page 5&6 (section 2.4 Syntactic Categories at Clause Level) def ExpandRole(input): if input=="adv": return 'Adverbial' if input=="io": return 'Indirect Object' if input=="o": return 'Object' if input=="o2": return 'Second Object' if input=="s": return 'Subject' if input=="p": return 'Predicate' if input=="v": return 'Verbal' if input=="vc": return 'Verbal Copula' if input=='aux': return 'Auxiliar' return '' # Function to expantion of Part of Speech labels. See also the description in # "MACULA Greek Treebank for the Nestle 1904 Greek New Testament.pdf" page 6&7 # (2.2. Syntactic Categories at Word Level: Part of Speech Labels) def ExpandSP(input): if input=='adj': return 'Adjective' if input=='conj': return 'Conjunction' if input=='det': return 'Determiner' if input=='intj': return 'Interjection' if input=='noun': return 'Noun' if input=='num': return 'Numeral' if input=='prep': return 'Preposition' if input=='ptcl': return 'Particle' if input=='pron': return 'Pronoun' if input=='verb': return 'Verb' return '' ############################################### # The director routine # ############################################### def director(cv): ############################################### # Innitial setup of data etc. # ############################################### NoneType = type(None) # needed as tool to validate certain data IndexDict = {} # init an empty dictionary WordGroupDict={} # init a dummy dictionary PrevWordGroupSet = WordGroupSet = [] PrevWordGroupList = WordGroupList = [] RootWordGroup = 0 WordNumber=FoundWords=WordGroupTrack=0 # The following is required to recover succesfully from an abnormal condition # in the LowFat tree data where a element is labeled as # this number is arbitrary but should be high enough not to clash with 'real' WG numbers DummyWGN=200000 for bo,bookinfo in bo2book.items(): ############################################### # start of section executed for each book # ############################################### # note: bookinfo is a list! Split the data Book = bookinfo[0] BookNumber = int(bookinfo[1]) BookShort = bookinfo[2] BookLoc = os.path.join(PklDir, f'{bo}.pkl') # load data for this book into a dataframe. # make sure wordorder is correct print(f'\tWe are loading {BookLoc}...') pkl_file = open(BookLoc, 'rb') df_unsorted = pickle.load(pkl_file) pkl_file.close() ''' Fill dictionary of column names for this book sort to ensure proper wordorder ''' ItemsInRow=1 for itemname in df_unsorted.columns.to_list(): IndexDict.update({'i_{}'.format(itemname): ItemsInRow}) # This is to identify the collumn containing the key to sort upon if itemname=="{http://www.w3.org/XML/1998/namespace}id": SortKey=ItemsInRow-1 ItemsInRow+=1 df=df_unsorted.sort_values(by=df_unsorted.columns[SortKey]) del df_unsorted # Set up nodes for new book ThisBookPointer = cv.node('book') cv.feature(ThisBookPointer, book=Book, booknumber=BookNumber, bookshort=BookShort) ThisChapterPointer = cv.node('chapter') cv.feature(ThisChapterPointer, chapter=1) PreviousChapter=1 ThisVersePointer = cv.node('verse') cv.feature(ThisVersePointer, verse=1) PreviousVerse=1 ThisSentencePointer = cv.node('sentence') cv.feature(ThisSentencePointer, sentence=1) PreviousSentence=1 ############################################### # Iterate through words and construct objects # ############################################### for row in df.itertuples(): WordNumber += 1 FoundWords +=1 # Detect and act upon changes in sentences, verse and chapter # the order of terminating and creating the nodes is critical: # close verse - close chapter - open chapter - open verse NumberOfParents = sanitize(row[IndexDict.get("i_parents")]) ThisSentence=int(row[IndexDict.get("i_Parent{}SN".format(NumberOfParents-1))]) ThisVerse = sanitize(row[IndexDict.get("i_verse")]) ThisChapter = sanitize(row[IndexDict.get("i_chapter")]) if (ThisSentence!=PreviousSentence): cv.terminate(ThisSentencePointer) if (ThisVerse!=PreviousVerse): cv.terminate(ThisVersePointer) if (ThisChapter!=PreviousChapter): cv.terminate(ThisChapterPointer) PreviousChapter = ThisChapter ThisChapterPointer = cv.node('chapter') cv.feature(ThisChapterPointer, chapter=ThisChapter) if (ThisVerse!=PreviousVerse): PreviousVerse = ThisVerse ThisVersePointer = cv.node('verse') cv.feature(ThisVersePointer, verse=ThisVerse, chapter=ThisChapter) if (ThisSentence!=PreviousSentence): PreviousSentence=ThisSentence ThisSentencePointer = cv.node('sentence') cv.feature(ThisSentencePointer, verse=ThisVerse, chapter=ThisChapter) ############################################### # analyze and process tags # ############################################### PrevWordGroupList=WordGroupList WordGroupList=[] # stores current active WordGroup numbers for i in range(NumberOfParents-2,0,-1): # important: reversed itteration! _WGN=row[IndexDict.get("i_Parent{}WGN".format(i))] if isinstance(_WGN, type(None)): # handling conditions where XML data has e.g. Acts 26:12 # to recover, we need to create a dummy WG with a sufficient high WGN so it can never match any real WGN. WGN=DummyWGN else: WGN=int(_WGN) if WGN!='': WordGroupList.append(WGN) WordGroupDict[(WGN,0)]=WGN WGclass=sanitize(row[IndexDict.get("i_Parent{}Class".format(i))]) WGrule=sanitize(row[IndexDict.get("i_Parent{}Rule".format(i))]) WGtype=sanitize(row[IndexDict.get("i_Parent{}Type".format(i))]) if WGclass==WGrule==WGtype=='': WGclass='to be skipped?' if WGrule[-2:]=='CL' and WGclass=='': WGclass='cl*' # to simulate the way Logos presents this condition WordGroupDict[(WGN,6)]=WGclass WordGroupDict[(WGN,1)]=WGrule WordGroupDict[(WGN,8)]=WGtype WordGroupDict[(WGN,3)]=sanitize(row[IndexDict.get("i_Parent{}Junction".format(i))]) WordGroupDict[(WGN,2)]=sanitize(row[IndexDict.get("i_Parent{}Cltype".format(i))]) WordGroupDict[(WGN,7)]=sanitize(row[IndexDict.get("i_Parent{}Role".format(i))]) WordGroupDict[(WGN,9)]=sanitize(row[IndexDict.get("i_Parent{}Appos".format(i))]) WordGroupDict[(WGN,10)]=NumberOfParents-1-i # = number of parent wordgroups if not PrevWordGroupList==WordGroupList: if RootWordGroup != WordGroupList[0]: RootWordGroup = WordGroupList[0] SuspendableWordGoupList = [] # we have a new sentence. rebuild suspendable wordgroup list # some cleaning of data may be added here to save on memmory... #for k in range(6): del WordGroupDict[item,k] for item in reversed(PrevWordGroupList): if (item not in WordGroupList): # CLOSE/SUSPEND CASE SuspendableWordGoupList.append(item) cv.terminate(WordGroupDict[item,4]) for item in WordGroupList: if (item not in PrevWordGroupList): if (item in SuspendableWordGoupList): # RESUME CASE #print ('\n resume: '+str(item),end=' ') cv.resume(WordGroupDict[(item,4)]) else: # CREATE CASE #print ('\n create: '+str(item),end=' ') WordGroupDict[(item,4)]=cv.node('wg') WordGroupDict[(item,5)]=WordGroupTrack WordGroupTrack += 1 cv.feature(WordGroupDict[(item,4)], wgnum=WordGroupDict[(item,0)], junction=WordGroupDict[(item,3)], clausetype=WordGroupDict[(item,2)], wgrule=WordGroupDict[(item,1)], wgclass=WordGroupDict[(item,6)], wgrole=WordGroupDict[(item,7)],wgrolelong=ExpandRole(WordGroupDict[(item,7)]), wgtype=WordGroupDict[(item,8)],appos=WordGroupDict[(item,8)],wglevel=WordGroupDict[(item,10)]) # These roles are performed either by a WG or just a single word. Role=row[IndexDict.get("i_role")] ValidRoles=["adv","io","o","o2","s","p","v","vc","aux"] DistanceToRoleClause=0 if isinstance (Role,str) and Role in ValidRoles: # Role is assign to this word (uniqely) WordRole=Role WordRoleLong=ExpandRole(WordRole) else: # Role details needs to be taken from some uptree wordgroup WordRole=WordRoleLong='' for item in range(1,NumberOfParents-1): Role = sanitize(row[IndexDict.get("i_Parent{}Role".format(item))]) if isinstance (Role,str) and Role in ValidRoles: WordRole=Role WordRoleLong=ExpandRole(WordRole) DistanceToRoleClause=item break # Find the number of the WG containing the clause definition for item in range(1,NumberOfParents-1): WGrule = sanitize(row[IndexDict.get("i_Parent{}Rule".format(item))]) if row[IndexDict.get("i_Parent{}Class".format(item))]=='cl' or WGrule[-2:]=='CL': ContainedClause=sanitize(row[IndexDict.get("i_Parent{}WGN".format(item))]) break ############################################### # analyze and process tags # ############################################### # Determine syntactic categories at word level. PartOfSpeech=sanitize(row[IndexDict.get("i_class")]) PartOfSpeechFull=ExpandSP(PartOfSpeech) # The folling part of code reproduces feature 'word' and 'after' that are # currently containing incorrect data in a few specific cases. # See https://github.com/tonyjurg/Nestle1904LFT/blob/main/resources/identifying_odd_afters.ipynb # Get the word details and detect presence of punctuations word=sanitize(row[IndexDict.get("i_unicode")]) match = re.search(r"([\.·—,;])$", word) if match: # The group(0) method is used to retrieve the matched punctuation sign after=match.group(0)+' ' # Remove the punctuation from the end of the word word=word[:-1] else: after=' ' # Some attributes are not present inside some (small) books. The following is to prevent exceptions. degree='' if 'i_degree' in IndexDict: degree=sanitize(row[IndexDict.get("i_degree")]) subjref='' if 'i_subjref' in IndexDict: subjref=sanitize(row[IndexDict.get("i_subjref")]) # Create the word slots this_word = cv.slot() cv.feature(this_word, after= after, unicode= sanitize(row[IndexDict.get("i_unicode")]), word= word, monad= FoundWords, orig_order= sanitize(row[IndexDict.get("i_word_order")]), book= Book, booknumber= BookNumber, bookshort= BookShort, chapter= ThisChapter, ref= sanitize(row[IndexDict.get("i_ref")]), sp= PartOfSpeech, sp_full= PartOfSpeechFull, verse= ThisVerse, sentence= ThisSentence, normalized= sanitize(row[IndexDict.get("i_normalized")]), morph= sanitize(row[IndexDict.get("i_morph")]), strongs= sanitize(row[IndexDict.get("i_strong")]), lex_dom= sanitize(row[IndexDict.get("i_domain")]), ln= sanitize(row[IndexDict.get("i_ln")]), gloss= sanitize(row[IndexDict.get("i_gloss")]), gn= sanitize(row[IndexDict.get("i_gender")]), nu= sanitize(row[IndexDict.get("i_number")]), case= sanitize(row[IndexDict.get("i_case")]), lemma= sanitize(row[IndexDict.get("i_lemma")]), person= sanitize(row[IndexDict.get("i_person")]), mood= sanitize(row[IndexDict.get("i_mood")]), tense= sanitize(row[IndexDict.get("i_tense")]), number= sanitize(row[IndexDict.get("i_number")]), voice= sanitize(row[IndexDict.get("i_voice")]), degree= degree, type= sanitize(row[IndexDict.get("i_type")]), reference= sanitize(row[IndexDict.get("i_ref")]), subj_ref= subjref, nodeID= sanitize(row[4]), #this is a fixed position in dataframe wordrole= WordRole, wordrolelong= WordRoleLong, wordlevel= NumberOfParents-1, roleclausedistance = DistanceToRoleClause, containedclause = ContainedClause ) cv.terminate(this_word) ''' wrap up the book. At the end of the book we need to close all nodes in proper order. ''' # close all open WordGroup nodes for item in WordGroupList: #cv.feature(WordGroupDict[(item,4)], add some stats?) cv.terminate(WordGroupDict[item,4]) cv.terminate(ThisSentencePointer) cv.terminate(ThisVersePointer) cv.terminate(ThisChapterPointer) cv.terminate(ThisBookPointer) # clear dataframe for this book, clear the index dictionary del df IndexDict.clear() gc.collect() ############################################### # end of section executed for each book # ############################################### ############################################### # end of director function # ############################################### ############################################### # Output definitions # ############################################### slotType = 'word' otext = { # dictionary of config data for sections and text formats 'fmt:text-orig-full':'{word}{after}', 'sectionTypes':'book,chapter,verse', 'sectionFeatures':'book,chapter,verse', 'structureFeatures': 'book,chapter,verse', 'structureTypes': 'book,chapter,verse', } # configure metadata generic = { # dictionary of metadata meant for all features 'textFabriVersion': '{}'.format(VERSION), #imported from tf.parameter 'xmlSourceLocation': 'https://github.com/tonyjurg/Nestle1904LFT/tree/main/resources/xml/20230628', 'xmlSourceDate': 'June 28, 2023', 'author': 'Evangelists and apostles', 'availability': 'Creative Commons Attribution 4.0 International (CC BY 4.0)', 'converters': 'Tony Jurg', 'converterSource': 'https://github.com/tonyjurg/Nestle1904LFT/tree/main/resources/converter', 'converterVersion': '0.4', 'dataSource': 'MACULA Greek Linguistic Datasets, available at https://github.com/Clear-Bible/macula-greek/tree/main/Nestle1904/nodes', 'editors': 'Eberhart Nestle (1904)', 'sourceDescription': 'Greek New Testment (British Foreign Bible Society, 1904)', 'sourceFormat': 'XML (Low Fat tree XML data)', 'title': 'Greek New Testament (Nestle1904LFT)' } # set of integer valued feature names intFeatures = { 'booknumber', 'chapter', 'verse', 'sentence', 'wgnum', 'orig_order', 'monad', 'wglevel' } # per feature dicts with metadata featureMeta = { 'after': {'description': 'Characters (eg. punctuations) following the word'}, 'book': {'description': 'Book name'}, 'booknumber': {'description': 'NT book number (Matthew=1, Mark=2, ..., Revelation=27)'}, 'bookshort': {'description': 'Book name (abbreviated)'}, 'chapter': {'description': 'Chapter number inside book'}, 'verse': {'description': 'Verse number inside chapter'}, 'sentence': {'description': 'Sentence number (counted per chapter)'}, 'type': {'description': 'Wordgroup type information (verb, verbless, elided, minor, etc.)'}, 'wgrule': {'description': 'Wordgroup rule information'}, 'orig_order': {'description': 'Word order (in source XML file)'}, 'monad': {'description': 'Monad (word order in the corpus)'}, 'word': {'description': 'Word as it appears in the text (excl. punctuations)'}, 'unicode': {'description': 'Word as it arears in the text in Unicode (incl. punctuations)'}, 'ref': {'description': 'ref ID'}, 'sp': {'description': 'Part of Speech (abbreviated)'}, 'sp_full': {'description': 'Part of Speech (long description)'}, 'normalized': {'description': 'Surface word with accents normalized and trailing punctuations removed'}, 'lemma': {'description': 'Lexeme (lemma)'}, 'morph': {'description': 'Morphological tag (Sandborg-Petersen morphology)'}, # see also discussion on relation between lex_dom and ln # @ https://github.com/Clear-Bible/macula-greek/issues/29 'lex_dom': {'description': 'Lexical domain according to Semantic Dictionary of Biblical Greek, SDBG (not present everywhere?)'}, 'ln': {'description': 'Lauw-Nida lexical classification (not present everywhere?)'}, 'strongs': {'description': 'Strongs number'}, 'gloss': {'description': 'English gloss'}, 'gn': {'description': 'Gramatical gender (Masculine, Feminine, Neuter)'}, 'nu': {'description': 'Gramatical number (Singular, Plural)'}, 'case': {'description': 'Gramatical case (Nominative, Genitive, Dative, Accusative, Vocative)'}, 'person': {'description': 'Gramatical person of the verb (first, second, third)'}, 'mood': {'description': 'Gramatical mood of the verb (passive, etc)'}, 'tense': {'description': 'Gramatical tense of the verb (e.g. Present, Aorist)'}, 'number': {'description': 'Gramatical number of the verb'}, 'voice': {'description': 'Gramatical voice of the verb'}, 'degree': {'description': 'Degree (e.g. Comparitative, Superlative)'}, 'type': {'description': 'Gramatical type of noun or pronoun (e.g. Common, Personal)'}, 'reference': {'description': 'Reference (to nodeID in XML source data, not yet post-processes)'}, 'subj_ref': {'description': 'Subject reference (to nodeID in XML source data, not yet post-processes)'}, 'nodeID': {'description': 'Node ID (as in the XML source data, not yet post-processes)'}, 'junction': {'description': 'Junction data related to a wordgroup'}, 'wgnum': {'description': 'Wordgroup number (counted per book)'}, 'wgclass': {'description': 'Class of the wordgroup ()'}, 'wgrole': {'description': 'Role of the wordgroup (abbreviated)'}, 'wgrolelong': {'description': 'Role of the wordgroup (full)'}, 'wordrole': {'description': 'Role of the word (abbreviated)'}, 'wordrolelong':{'description': 'Role of the word (full)'}, 'wgtype': {'description': 'Wordgroup type details'}, 'clausetype': {'description': 'Clause type details'}, 'appos': {'description': 'Apposition details'}, 'wglevel': {'description': 'Number of parent wordgroups for a wordgroup'}, 'wordlevel': {'description': 'Number of parent wordgroups for a word'}, 'roleclausedistance': {'description': 'Distance to wordgroup defining the role of this word'}, 'containedclause': {'description': 'Contained clause (WG number)'} } ############################################### # the main function # ############################################### good = cv.walk( director, slotType, otext=otext, generic=generic, intFeatures=intFeatures, featureMeta=featureMeta, warn=True, force=False ) if good: print ("done") # In[4]: # First, I have to laod different modules that I use for analyzing the data and for plotting: import sys, os, collections import pandas as pd import numpy as np import re from tf.fabric import Fabric from tf.app import use # The following cell loads the TextFabric files from github repository. # In[11]: # Loading-the-New-Testament-Text-Fabric N1904 = use ("tonyjurg/Nestle1904LFT", version="0.4", hoist=globals()) # In[ ]: