Python BibleBook.appendLine方法代码示例

# 需要导入模块: from Bible import BibleBook [as 别名]
# 或者: from Bible.BibleBook import appendLine [as 别名]
    def __validateAndExtractBook( self, book ):
        """
        Check/validate and extract book data from the given XML book record
            finding chapter subelements.
        """

        if Globals.verbosityLevel > 3: print( _("Validating XML book...") )

        # Process the div attributes first
        BBB = bookName = bookShortName = bookNumber = None
        for attrib,value in book.items():
            if attrib=="bnumber":
                bookNumber = value
            elif attrib=="bname":
                bookName = value
            elif attrib=="bsname":
                bookShortName = value
            else: logging.warning( "Unprocessed '{}' attribute ({}) in book element".format( attrib, value ) )
        if bookNumber:
            try: BBB = Globals.BibleBooksCodes.getBBBFromReferenceNumber( bookNumber )
            except KeyError:
                logging.warning( "Unable to deduce which book is number={}, name={}, shortName={} -- ignoring it" \
                                                                        .format( bookNumber, bookName, bookShortName ) )
        elif bookName:
            BBB = self.genericBOS.getBBB( bookName )

        if BBB:
            if Globals.verbosityLevel > 2: print( _("Validating {} {}...").format( BBB, bookName ) )
            thisBook = BibleBook( self, BBB )
            thisBook.objectNameString = "Haggai XML Bible Book object"
            thisBook.objectTypeString = "Haggai"
            #thisBook.sourceFilepath = self.sourceFilepath
            for element in book:
                if element.tag == HaggaiXMLBible.captionTag:
                    sublocation = "caption in {}".format( BBB )
                    Globals.checkXMLNoAttributes( element, sublocation, 'jhl6' )
                    Globals.checkXMLNoSubelements( element, sublocation, 'jk21' )
                    Globals.checkXMLNoTail( element, sublocation, 'kjh6' )
                    thisBook.appendLine( 'mt', element.text )
                elif element.tag == HaggaiXMLBible.chapterTag:
                    sublocation = "chapter in {}".format( BBB )
                    Globals.checkXMLNoText( element, sublocation, 'j3jd' )
                    Globals.checkXMLNoTail( element, sublocation, 'al1d' )
                    self.__validateAndExtractChapter( BBB, thisBook, element )
                else: logging.error( "Expected to find '{}' but got '{}'".format( HaggaiXMLBible.chapterTag, element.tag ) )
            if Globals.verbosityLevel > 2: print( "  Saving {} into results...".format( BBB ) )
            self.saveBook( thisBook )

# 需要导入模块: from Bible import BibleBook [as 别名]
# 或者: from Bible.BibleBook import appendLine [as 别名]
    def __validateAndExtractBook( self, book ):
        """
        Check/validate and extract book data from the given XML book record
            finding chapter subelements.
        """

        if Globals.verbosityLevel > 3: print( _("Validating OpenSong XML book...") )

        # Process the div attributes first
        BBB = bookName = None
        for attrib,value in book.items():
            if attrib=="n":
                bookName = value
            else: logging.warning( "Unprocessed '{}' attribute ({}) in book element".format( attrib, value ) )
        if bookName:
            BBB = self.genericBOS.getBBB( bookName )
            if BBB:
                if Globals.verbosityLevel > 2: print( _("Validating {} {}...").format( BBB, bookName ) )
                thisBook = BibleBook( self, BBB )
                thisBook.objectNameString = "OpenSong XML Bible Book object"
                thisBook.objectTypeString = "OpenSong"
                #thisBook.sourceFilepath = self.sourceFilepath
                USFMAbbreviation = Globals.BibleBooksCodes.getUSFMAbbreviation( BBB )
                thisBook.appendLine( 'id', '{} imported by {}'.format( USFMAbbreviation.upper(), ProgNameVersion ) )
                thisBook.appendLine( 'h', bookName )
                thisBook.appendLine( 'mt1', bookName )
                for element in book:
                    if element.tag == OpenSongXMLBible.chapterTag:
                        sublocation = "chapter in {}".format( BBB )
                        Globals.checkXMLNoText( element, sublocation, 'j3jd' )
                        Globals.checkXMLNoTail( element, sublocation, 'al1d' )
                        self.__validateAndExtractChapter( BBB, thisBook, element )
                    else: logging.error( "Expected to find '{}' but got '{}'".format( OpenSongXMLBible.chapterTag, element.tag ) )
                if Globals.verbosityLevel > 2: print( "  Saving {} into results...".format( BBB ) )
                self.saveBook( thisBook )
            else: logging.error( _("OpenSong load doesn't recognize book name: '{}'").format( bookName ) ) # no BBB
        else: logging.error( _("OpenSong load can't find a book name") ) # no bookName

# 需要导入模块: from Bible import BibleBook [as 别名]
# 或者: from Bible.BibleBook import appendLine [as 别名]

#.........这里部分代码省略.........
            assert( parsingCode[5] in Greek.numberCodes )
            assert( parsingCode[6] in Greek.genderCodes )
            assert( parsingCode[7] in Greek.degreeCodes )

            return (bn,cn,vn,), (POSCode,parsingCode,), (bits[3],bits[4],bits[5],bits[6],)
        # end of unpackLine

        self.thisBook = BibleBook( self.name, BBB )
        self.thisBook.objectNameString = "Morph Greek NT Bible Book object"
        self.thisBook.objectTypeString = "MorphGNT"
        filepath = os.path.join( self.sourceFilepath, filename )
        if Globals.verbosityLevel > 2: print( "  Loading {}...".format( filename ) )
        lastLine, lineCount = '', 0
        lastC = lastV = None
        with open( filepath, encoding=encoding ) as myFile: # Automatically closes the file when done
            if 1: #try:
                for line in myFile:
                    lineCount += 1
                    if lineCount==1 and encoding.lower()=='utf-8' and line and line[0]==chr(65279): #U+FEFF
                        logging.info( "GreekNT: Detected UTF-16 Byte Order Marker in {}".format( filename ) )
                        line = line[1:] # Remove the UTF-8 Byte Order Marker
                    if line[-1]=='\n': line = line[:-1] # Removing trailing newline character
                    #if not line: continue # Just discard blank lines
                    lastLine = line
                    #print ( 'gNT file line is "' + line + '"' )
                    #if line[0]=='#': continue # Just discard comment lines
                    unpackedLine = unpackLine( line )
                    #print( unpackedLine )
                    ref, grammar, words = unpackedLine
                    bn, cn, vn = ref
                    POSCode, parsingCode = grammar
                    word1, word2, word3, word4 = words
                    if cn != lastC:
                        self.thisBook.appendLine( 'c', cn )
                        lastC, lastV = cn, None
                    if vn != lastV:
                        self.thisBook.appendLine( 'v', vn )
                        lastV = vn
                    self.thisBook.appendLine( 'vw', "{}/{}/{}/{}".format( word1, word2, word3, word4 ) )
                    self.thisBook.appendLine( 'g', "{}/{}".format( POSCode, parsingCode ) )
                    #reference = BBB,bits[0][1],bits[0][2], # Put the BBB into the reference
                    #lineTuples.append( (reference,bits[1],bits[2],) )
                    #print( reference,bits[1],bits[2] ); halt
            if 0: #except:
                logging.critical( "Invalid line in " + filepath + " -- line ignored at " + str(lineCount) )
                if lineCount > 1: print( 'Previous line was: ', lastLine )
                else: print( 'Possible encoding error -- expected', encoding )
        if self.thisBook:
            if Globals.verbosityLevel > 3: print( "    {} words loaded from {}".format( len(self.thisBook), filename ) )
            self.saveBook( self.thisBook )
            #self.books[BBB] = self.thisBook
    # end of loadBook


    def xanalyzeWords( self ):
        """ Go through the NT data and do some filing and sorting of the Greek words. """
        if Globals.verbosityLevel > 3: print( "analyzeWords: have {} books in the loaded NT".format( len(self.books) ) )
        self.wordCounts = {} # Wordcount organized by BBB
        self.wordCounts['Total'] = 0
        self.actualWordsToNormalized, self.normalizedWordsToActual, self.normalizedWordsToParsing, self.lemmasToNormalizedWords = {}, {}, {}, {}
        for BBB in self.books:
            wordCount = len(self.books[BBB])
            self.wordCounts[BBB] = wordCount
            self.wordCounts['Total'] += wordCount
            if Globals.verbosityLevel > 3: print( "  analyzeWords: {} has {} Greek words".format( BBB, wordCount ) )
            for reference,parsing,(punctuatedWord,actualWord,normalizedWord,lemma) in self.books[BBB]: # Stuff is: reference,parsing,words

# 需要导入模块: from Bible import BibleBook [as 别名]
# 或者: from Bible.BibleBook import appendLine [as 别名]

#.........这里部分代码省略.........
                    #if lastBookCode != -1: # Better save the last book
                        #self.saveBook( thisBook )
                    #BBB = Globals.BibleBooksCodes.getBBBFromYETBibleCode( bookCode )
                    #thisBook = BibleBook( self.name, BBB )
                    #thisBook.objectNameString = "YET Bible Book object"
                    #thisBook.objectTypeString = "YET"
                    #lastBookCode = bookCode
                    #lastChapterNumber = lastVerseNumber = -1

                #if chapterNumber != lastChapterNumber: # We've started a new chapter
                    #if Globals.debugFlag: assert( chapterNumber > lastChapterNumber or BBB=='ESG' ) # Esther Greek might be an exception
                    #if chapterNumber == 0:
                        #logging.info( "Have chapter zero in {} {} {} {}:{}".format( self.givenName, BBB, bookCode, chapterNumberString, verseNumberString ) )
                    #thisBook.appendLine( 'c', chapterNumberString )
                    #lastChapterNumber = chapterNumber
                    #lastVerseNumber = -1

                ## Handle the verse info
                #if verseNumber==lastVerseNumber and vText==lastVText:
                    #logging.warning( _("Ignored duplicate verse line in {} {} {} {}:{}").format( self.givenName, BBB, bookCode, chapterNumberString, verseNumberString ) )
                    #continue
                #if BBB=='PSA' and verseNumberString=='1' and vText.startswith('<') and self.givenName=='basic_english':
                    ## Move Psalm titles to verse zero
                    #verseNumber = 0
                #if verseNumber < lastVerseNumber:
                    #logging.warning( _("Ignored receding verse number (from {} to {}) in {} {} {} {}:{}").format( lastVerseNumber, verseNumber, self.givenName, BBB, bookCode, chapterNumberString, verseNumberString ) )
                #elif verseNumber == lastVerseNumber:
                    #if vText == lastVText:
                        #logging.warning( _("Ignored duplicated {} verse in {} {} {} {}:{}").format( verseNumber, self.givenName, BBB, bookCode, chapterNumberString, verseNumberString ) )
                    #else:
                        #logging.warning( _("Ignored duplicated {} verse number in {} {} {} {}:{}").format( verseNumber, self.givenName, BBB, bookCode, chapterNumberString, verseNumberString ) )
                #thisBook.appendLine( 'v', verseNumberString + ' ' + vText )
                #lastVText = vText
                #lastVerseNumber = verseNumber

        # Now process the books
        for BBB,bkData in bookDict.items():
            #print( "Processing", BBB )
            thisBook = BibleBook( self.name, BBB )
            thisBook.objectNameString = "YET Bible Book object"
            thisBook.objectTypeString = "YET"
            lastChapterNumberString = None
            for (chapterNumberString,verseNumberString), verseString in bkData.items():
                # Insert headings (can only occur before verses)
                if (BBB,chapterNumberString,verseNumberString) in headingDict:
                    heading, refList = headingDict[(BBB,chapterNumberString,verseNumberString)]
                    #print( 's', BBB, chapterNumberString, verseNumberString, repr(heading), refList )
                    thisBook.appendLine( 's', heading )
                    if refList:
                        refString = ""
                        #print( 's', BBB, chapterNumberString, verseNumberString, repr(heading), refList )
                        for ref in refList:
                            refString += ('; ' if refString else '') + ref
                        #print( 's', BBB, chapterNumberString, verseNumberString, repr(heading), refList, repr(refString) )
                        thisBook.appendLine( 'r', '('+refString+')' )
                # Insert footnotes and cross-references
                while( '\\ff' in verseString ):
                    #print( "footnote", repr(verseString) )
                    fIx = verseString.index( '\\ff' )
                    caller = verseString[fIx+3]
                    #print( "fcaller", repr(caller) )
                    assert( caller.isdigit() )
                    note = footnoteDict[(BBB,chapterNumberString,verseNumberString,caller)]
                    #print( "fnote", repr(note) )
                    verseString = verseString[:fIx] + '\\f + \\ft ' + note + '\\f*' + verseString[fIx+4:]
                    #print( "fvS", repr(verseString) )
                while( '\\xx' in verseString ):
                    #print( "xref", repr(verseString) )
                    fIx = verseString.index( '\\xx' )
                    caller = verseString[fIx+3]
                    #print( "xcaller", repr(caller) )
                    assert( caller.isdigit() )
                    note = xrefDict[(BBB,chapterNumberString,verseNumberString,caller)]
                    #print( "xnote", repr(note) )
                    verseString = verseString[:fIx] + '\\x - \\xt ' + note + '\\x*' + verseString[fIx+4:]
                    #print( "xvS", repr(verseString) )
                # Save the Bible data fields
                if chapterNumberString != lastChapterNumberString:
                    thisBook.appendLine( 'c', chapterNumberString )
                    lastChapterNumberString = chapterNumberString
                #print( BBB, chapterNumberString, verseNumberString, repr(verseString) )
                if verseString.startswith( '\\\\' ):  # It's an initial paragraph marker
                    if verseString[3]==' ': marker, verseString = verseString[2], verseString[4:]
                    elif verseString[4]==' ': marker, verseString = verseString[2:4], verseString[5:]
                    else: halt
                    #print( '', '\\'+marker )
                    thisBook.appendLine( marker, '' )
                assert( not verseString.startswith( '\\\\' ) )
                bits = verseString.split( '\\\\' ) # Split on paragraph markers (but not character markers)
                for j,bit in enumerate(bits):
                    #print( "loop", j, repr(bit), repr(verseString) )
                    if j==0: thisBook.appendLine( 'v', verseNumberString + ' ' + verseString.rstrip() )
                    else:
                        if bit[1]==' ': marker, bit = bit[0], bit[2:]
                        elif bit[2]==' ': marker, bit = bit[0:2], bit[3:]
                        else: halt
                        #print( "mV", marker, repr(bit), repr(verseString) )
                        thisBook.appendLine( marker, bit.rstrip() )
            self.saveBook( thisBook )
        self.doPostLoadProcessing()

# 需要导入模块: from Bible import BibleBook [as 别名]
# 或者: from Bible.BibleBook import appendLine [as 别名]
    def load( self ):
        """
        Load a single source file and load book elements.
        """
        if Globals.verbosityLevel > 2: print( _("Loading {}...").format( self.sourceFilepath ) )

        lastLine, lineCount = '', 0
        BBB = None
        lastBookNumber = lastChapterNumber = lastVerseNumber = -1
        lastVText = ''
        quoted = None
        with open( self.sourceFilepath, encoding=self.encoding ) as myFile: # Automatically closes the file when done
            for line in myFile:
                lineCount += 1
                #if lineCount==1 and self.encoding.lower()=='utf-8' and line[0]==chr(65279): #U+FEFF
                    #logging.info( "      CSVBible.load: Detected UTF-16 Byte Order Marker" )
                    #line = line[1:] # Remove the UTF-8 Byte Order Marker
                if line[-1]=='\n': line=line[:-1] # Removing trailing newline character
                if not line: continue # Just discard blank lines
                if line==' ': continue # Handle special case which has blanks on every second line -- HACK
                lastLine = line
                #print ( "CSV file line {} is {}".format( lineCount, repr(line) ) )
                if line[0]=='#': continue # Just discard comment lines
                if lineCount==1:
                    if line.startswith( '"Book",' ):
                        quoted = True
                        continue # Just discard header line
                    elif line.startswith( 'Book,' ):
                        quoted = False
                        continue # Just discard header line

                bits = line.split( ',', 3 )
                #print( lineCount, self.givenName, BBB, bits )
                if len(bits) == 4:
                    bString, chapterNumberString, verseNumberString, vText = bits
                    #print( "bString, chapterNumberString, verseNumberString, vText", bString, chapterNumberString, verseNumberString, vText )
                else: print( "Unexpected number of bits", self.givenName, BBB, bString, chapterNumberString, verseNumberString, vText, len(bits), bits )

                # Remove quote marks from these strings
                if quoted:
                    if len(bString)>=2 and bString[0]==bString[-1] and bString[0] in '"\'': bString = bString[1:-1]
                    if len(chapterNumberString)>=2 and chapterNumberString[0]==chapterNumberString[-1] and chapterNumberString[0] in '"\'': chapterNumberString = chapterNumberString[1:-1]
                    if len(verseNumberString)>=2 and verseNumberString[0]==verseNumberString[-1] and verseNumberString[0] in '"\'': verseNumberString = verseNumberString[1:-1]
                    if len(vText)>=2 and vText[0]==vText[-1] and vText[0] in '"\'': vText = vText[1:-1]
                    #print( "bString, chapterNumberString, verseNumberString, vText", bString, chapterNumberString, verseNumberString, vText )

                #if not bookCode and not chapterNumberString and not verseNumberString:
                    #print( "Skipping empty line in {} {} {} {}:{}".format( self.givenName, BBB, bookCode, chapterNumberString, verseNumberString ) )
                    #continue
                #if Globals.debugFlag: assert( 2  <= len(bookCode) <= 4 )
                #if Globals.debugFlag: assert( chapterNumberString.isdigit() )
                #if Globals.debugFlag: assert( verseNumberString.isdigit() )
                bookNumber = int( bString )
                chapterNumber = int( chapterNumberString )
                verseNumber = int( verseNumberString )

                if bookNumber != lastBookNumber: # We've started a new book
                    if lastBookNumber != -1: # Better save the last book
                        self.saveBook( thisBook )
                    BBB = Globals.BibleBooksCodes.getBBBFromReferenceNumber( bookNumber )  # Try to guess
                    assert( BBB )
                    thisBook = BibleBook( self, BBB )
                    thisBook.objectNameString = "CSV Bible Book object"
                    thisBook.objectTypeString = "CSV"
                    lastBookNumber = bookNumber
                    lastChapterNumber = lastVerseNumber = -1

                if chapterNumber != lastChapterNumber: # We've started a new chapter
                    if Globals.debugFlag: assert( chapterNumber > lastChapterNumber or BBB=='ESG' ) # Esther Greek might be an exception
                    if chapterNumber == 0:
                        logging.info( "Have chapter zero in {} {} {} {}:{}".format( self.givenName, BBB, bookNumber, chapterNumberString, verseNumberString ) )
                    thisBook.appendLine( 'c', chapterNumberString )
                    lastChapterNumber = chapterNumber
                    lastVerseNumber = -1

                # Now we have to convert any possible RTF codes to our internal codes
                vTextOriginal = vText
                # First do special characters
                vText = vText.replace( '\\ldblquote', '“' ).replace( '\\rdblquote', '”' ).replace( '\\lquote', '‘' ).replace( '\\rquote', '’' )
                vText = vText.replace( '\\emdash', '—' ).replace( '\\endash', '–' )
                # Now do Unicode characters
                while True: # Find patterns like \\'d3
                    match = re.search( r"\\'[0-9a-f][0-9a-f]", vText )
                    if not match: break
                    i = int( vText[match.start()+2:match.end()], 16 ) # Convert two hex characters to decimal
                    vText = vText[:match.start()] + chr( i ) + vText[match.end():]
                while True: # Find patterns like \\u253?
                    match = re.search( r"\\u[1-2][0-9][0-9]\?", vText )
                    if not match: break
                    i = int( vText[match.start()+2:match.end()-1] ) # Convert three digits to decimal
                    vText = vText[:match.start()] + chr( i ) + vText[match.end():]
                #if vText != vTextOriginal: print( repr(vTextOriginal) ); print( repr(vText) )

                ## Handle special formatting
                ##   [brackets] are for Italicized words
                ##   <brackets> are for the Words of Christ in Red
                ##   «brackets»  are for the Titles in the Book  of Psalms.
                #vText = vText.replace( '[', '\\add ' ).replace( ']', '\\add*' ) \
                    #.replace( '<', '\\wj ' ).replace( '>', '\\wj*' )
                #if vText and vText[0]=='«':
#.........这里部分代码省略.........

# 需要导入模块: from Bible import BibleBook [as 别名]
# 或者: from Bible.BibleBook import appendLine [as 别名]

#.........这里部分代码省略.........
                    print( BBBn, C, V, repr(text) )
                    if C==2: break
                del rows # Takes a lot of memory
        if Globals.debugFlag or Globals.verbosityLevel>2:
            print( "Testament={} BBB={} BBB1={}, bE={}, tLCE={} nR={}".format( testament, BBB, BBB1, booksExpected, textLineCountExpected, numRows ) )
        if BBB1 != BBB:
            logging.critical( "First book seems wrong: {} instead of {}".format( BBB1, BBB ) )
            loadErrors.append( "First book seems wrong: {} instead of {}".format( BBB1, BBB ) )
            if not BBB: BBB = BBB1
        if numRows != textLineCountExpected:
            logging.critical( "Row count seems wrong: {} instead of {}".format( numRows, textLineCountExpected ) )
            loadErrors.append( "Row count seems wrong: {} instead of {}".format( numRows, textLineCountExpected ) )
        #halt

        BOS = BibleOrganizationalSystem( "GENERIC-KJV-66-ENG" )

        # Create the first book
        thisBook = BibleBook( self.name, BBB )
        thisBook.objectNameString = "e-Sword Bible Book object"
        thisBook.objectTypeString = "e-Sword"

        verseList = BOS.getNumVersesList( BBB )
        numC, numV = len(verseList), verseList[0]
        nBBB = Globals.BibleBooksCodes.getReferenceNumber( BBB )
        C = V = 1

        bookCount = 0
        ourGlobals = {}
        continued = ourGlobals['haveParagraph'] = False
        haveLines = False
        while True:
            cursor.execute('select Scripture from Bible where Book=? and Chapter=? and Verse=?', (nBBB,C,V) )
            try:
                row = cursor.fetchone()
                line = row[0]
            except: # This reference is missing
                #print( "something wrong at", BBB, C, V )
                #if Globals.debugFlag: halt
                #print( row )
                line = None
            #print ( nBBB, BBB, C, V, 'e-Sw file line is "' + line + '"' )
            if line is None: logging.warning( "ESwordBible.load: Found missing verse line at {} {}:{}".format( BBB, C, V ) )
            else: # line is not None
                if not isinstance( line, str ):
                    if 'encryption' in self.settingsDict:
                        logging.critical( "ESwordBible.load: Unable to decrypt verse line at {} {}:{} {}".format( BBB, C, V, repr(line) ) )
                        break
                    else:
                        logging.critical( "ESwordBible.load: Probably encrypted module: Unable to decode verse line at {} {}:{} {} {}".format( BBB, C, V, repr(line), self.settingsDict ) )
                        break
                elif not line: logging.warning( "ESwordBible.load: Found blank verse line at {} {}:{}".format( BBB, C, V ) )
                else:
                    haveLines = True

                    # Some modules end lines with \r\n or have it in the middle!
                    #   (We just ignore these for now)
                    if '\r' in line or '\n' in line:
                        if Globals.debugFlag:
                            logging.warning( "ESwordBible.load: Found CR or LF characters in verse line at {} {}:{}".format( BBB, C, V ) )
                        #print( repr(line) )
                    while line and line[-1] in '\r\n': line = line[:-1] # Remove CR/LFs from the end
                    line = line.replace( '\r\n', ' ' ).replace( '\r', ' ' ).replace( '\n', ' ' ) # Replace CR/LFs in the middle

            #print( "e-Sword.load", BBB, C, V, repr(line) )
            self.handleLine( self.name, BBB, C, V, line, thisBook, ourGlobals )
            V += 1
            if V > numV:
                C += 1
                if C > numC: # Save this book now
                    if haveLines:
                        if Globals.verbosityLevel > 3: print( "Saving", BBB, bookCount+1 )
                        self.saveBook( thisBook )
                    #else: print( "Not saving", BBB )
                    bookCount += 1 # Not the number saved but the number we attempted to process
                    if bookCount >= booksExpected: break
                    BBB = BOS.getNextBookCode( BBB )
                    # Create the next book
                    thisBook = BibleBook( self.name, BBB )
                    thisBook.objectNameString = "e-Sword Bible Book object"
                    thisBook.objectTypeString = "e-Sword"
                    haveLines = False

                    verseList = BOS.getNumVersesList( BBB )
                    numC, numV = len(verseList), verseList[0]
                    nBBB = Globals.BibleBooksCodes.getReferenceNumber( BBB )
                    C = V = 1
                    #thisBook.appendLine( 'c', str(C) )
                else: # next chapter only
                    #thisBook.appendLine( 'c', str(C) )
                    numV = verseList[C-1]
                    V = 1

            if ourGlobals['haveParagraph']:
                thisBook.appendLine( 'p', '' )
                ourGlobals['haveParagraph'] = False

        if Globals.strictCheckingFlag or Globals.debugFlag: self.checkForExtraMaterial( cursor, BOS )
        cursor.close()
        if loadErrors: self.errorDictionary['Load Errors'] = loadErrors
        self.doPostLoadProcessing()

# 需要导入模块: from Bible import BibleBook [as 别名]
# 或者: from Bible.BibleBook import appendLine [as 别名]
    def load( self ):
        """
        Load a single source file and load book elements.
        """
        if Globals.verbosityLevel > 2: print( _("Loading {}...").format( self.sourceFilepath ) )

        status = 0 # 1 = getting chapters, 2 = getting verse data
        lastLine, lineCount = '', 0
        BBB = lastBBB = None
        bookDetails = {}
        with open( self.sourceFilepath, encoding=self.encoding ) as myFile: # Automatically closes the file when done
            for line in myFile:
                lineCount += 1
                if lineCount==1 and self.encoding.lower()=='utf-8' and line[0]==chr(65279): #U+FEFF
                    logging.info( "      DrupalBible.load: Detected UTF-16 Byte Order Marker" )
                    line = line[1:] # Remove the UTF-8 Byte Order Marker
                if line[-1]=='\n': line=line[:-1] # Removing trailing newline character
                if not line: continue # Just discard blank lines

                #print ( 'DB file line is "' + line + '"' )
                if line[0] == '#': continue # Just discard comment lines
                lastLine = line
                if lineCount == 1:
                    if line != '*Bible':
                        logging.warning( "Unknown DrupalBible first line: {}".format( repr(line) ) )

                elif status == 0:
                    if line == '*Chapter': status = 1
                    else: # Get the version name details
                        bits = line.split( '|' )
                        shortName, fullName, language = bits
                        self.name = fullName

                elif status == 1:
                    if line == '*Context': status = 2
                    else: # Get the book name details
                        bits = line.split( '|' )
                        bookCode, bookFullName, bookShortName, numChapters = bits
                        assert( bookShortName == bookCode )
                        BBBresult = Globals.BibleBooksCodes.getBBBFromDrupalBibleCode( bookCode )
                        BBB = BBBresult if isinstance( BBBresult, str ) else BBBresult[0] # Result can be string or list of strings (best guess first)
                        bookDetails[BBB] = bookFullName, bookShortName, numChapters

                elif status == 2: # Get the verse text
                    bits = line.split( '|' )
                    bookCode, chapterNumberString, verseNumberString, lineMark, verseText = bits
                    #chapterNumber, verseNumber = int( chapterNumberString ), int( verseNumberString )
                    if lineMark: print( repr(lineMark) ); halt
                    BBBresult = Globals.BibleBooksCodes.getBBBFromDrupalBibleCode( bookCode )
                    BBB = BBBresult if isinstance( BBBresult, str ) else BBBresult[0] # Result can be string or list of strings (best guess first)
                    if BBB != lastBBB:
                        if lastBBB is not None:
                            self.saveBook( thisBook )
                        thisBook = BibleBook( self.name, BBB )
                        thisBook.objectNameString = "DrupalBible Bible Book object"
                        thisBook.objectTypeString = "DrupalBible"
                        lastChapterNumberString = None
                        lastBBB = BBB
                    if chapterNumberString != lastChapterNumberString:
                        thisBook.appendLine( 'c', chapterNumberString )
                        lastChapterNumberString = chapterNumberString
                    verseText = verseText.replace( '<', '\\it ' ).replace( '>', '\\it*' )
                    thisBook.appendLine( 'v', verseNumberString + ' ' + verseText )

                else: halt

        # Save the final book
        self.saveBook( thisBook )
        self.doPostLoadProcessing()

# 需要导入模块: from Bible import BibleBook [as 别名]
# 或者: from Bible.BibleBook import appendLine [as 别名]

#.........这里部分代码省略.........
        cursor.execute( 'select * from Details' )
        row = cursor.fetchone()
        for key in row.keys():
            self.settingsDict[key] = row[key]
        #print( self.settingsDict ); halt
        if 'Description' in self.settingsDict and len(self.settingsDict['Description'])<40: self.name = self.settingsDict['Description']
        if 'Abbreviation' in self.settingsDict: self.abbreviation = self.settingsDict['Abbreviation']
        if 'encryption' in self.settingsDict: logging.critical( "{} is encrypted: level {}".format( self.sourceFilename, self.settingsDict['encryption'] ) )


        if self.settingsDict['OT'] and self.settingsDict['NT']:
            testament, BBB = 'BOTH', 'GEN'
            booksExpected, textLineCountExpected = 66, 31102
        elif self.settingsDict['OT']:
            testament, BBB = 'OT', 'GEN'
            booksExpected, textLineCountExpected = 39, 23145
        elif self.settingsDict['NT']:
            testament, BBB = 'NT', 'MAT'
            booksExpected, textLineCountExpected = 27, 7957

        BOS = BibleOrganizationalSystem( "GENERIC-KJV-66-ENG" )

        # Create the first book
        thisBook = BibleBook( self.name, BBB )
        thisBook.objectNameString = "MySword Bible Book object"
        thisBook.objectTypeString = "MySword"

        verseList = BOS.getNumVersesList( BBB )
        numC, numV = len(verseList), verseList[0]
        nBBB = Globals.BibleBooksCodes.getReferenceNumber( BBB )
        C = V = 1

        bookCount = 0
        ourGlobals = {}
        continued = ourGlobals['haveParagraph'] = False
        haveLines = False
        while True:
            cursor.execute('select Scripture from Bible where Book=? and Chapter=? and Verse=?', (nBBB,C,V) )
            try:
                row = cursor.fetchone()
                line = row[0]
            except: # This reference is missing
                #print( "something wrong at", BBB, C, V )
                #if Globals.debugFlag: halt
                #print( row )
                line = None
            #print ( nBBB, BBB, C, V, 'MySw file line is "' + line + '"' )
            if line is None: logging.warning( "MySwordBible.load: Found missing verse line at {} {}:{}".format( BBB, C, V ) )
            else: # line is not None
                if not isinstance( line, str ):
                    if 'encryption' in self.settingsDict:
                        logging.critical( "MySwordBible.load: Unable to decrypt verse line at {} {}:{} {}".format( BBB, C, V, repr(line) ) )
                        break
                    else:
                        logging.critical( "MySwordBible.load: Unable to decode verse line at {} {}:{} {} {}".format( BBB, C, V, repr(line), self.settingsDict ) )
                elif not line: logging.warning( "MySwordBible.load: Found blank verse line at {} {}:{}".format( BBB, C, V ) )
                else:
                    haveLines = True

                    # Some modules end lines with \r\n or have it in the middle!
                    #   (We just ignore these for now)
                    if '\r' in line or '\n' in line:
                        logging.warning( "MySwordBible.load: Found CR or LF characters in verse line at {} {}:{}".format( BBB, C, V ) )
                    while line and line[-1] in '\r\n': line = line[:-1]
                    line = line.replace( '\r\n', ' ' ).replace( '\r', ' ' ).replace( '\n', ' ' )

            #print( "MySword.load", BBB, C, V, repr(line) )
            handleLine( self.name, BBB, C, V, line, thisBook, ourGlobals )
            V += 1
            if V > numV:
                C += 1
                if C > numC: # Save this book now
                    if haveLines:
                        if Globals.verbosityLevel > 3: print( "Saving", BBB, bookCount+1 )
                        self.saveBook( thisBook )
                    #else: print( "Not saving", BBB )
                    bookCount += 1 # Not the number saved but the number we attempted to process
                    if bookCount >= booksExpected: break
                    BBB = BOS.getNextBookCode( BBB )
                    # Create the next book
                    thisBook = BibleBook( self.name, BBB )
                    thisBook.objectNameString = "MySword Bible Book object"
                    thisBook.objectTypeString = "MySword"
                    haveLines = False

                    verseList = BOS.getNumVersesList( BBB )
                    numC, numV = len(verseList), verseList[0]
                    nBBB = Globals.BibleBooksCodes.getReferenceNumber( BBB )
                    C = V = 1
                    #thisBook.appendLine( 'c', str(C) )
                else: # next chapter only
                    #thisBook.appendLine( 'c', str(C) )
                    numV = verseList[C-1]
                    V = 1

            if ourGlobals['haveParagraph']:
                thisBook.appendLine( 'p', '' )
                ourGlobals['haveParagraph'] = False
        cursor.close()
        self.doPostLoadProcessing()

# 需要导入模块: from Bible import BibleBook [as 别名]
# 或者: from Bible.BibleBook import appendLine [as 别名]

#.........这里部分代码省略.........

        # Process the attributes first
        bookCode = None
        for attrib,value in bookElement.items():
            if attrib == 'id':
                bookCode = value
            else:
                logging.warning( "bce3 Unprocessed {} attribute ({}) in {}".format( attrib, value, mainLocation ) )
        BBB = Globals.BibleBooksCodes.getBBBFromUSFM( bookCode )
        mainLocation = "{} USFX {} book".format( self.name, BBB )
        if Globals.verbosityLevel > 2:
            print( _("USFXXMLBible.loadBook: Loading {} from {}...").format( BBB, self.name ) )
        Globals.checkXMLNoText( self.tree, mainLocation, '4f6h' )
        Globals.checkXMLNoTail( self.tree, mainLocation, '1wk8' )

        # Now create our actual book
        self.thisBook = BibleBook( self.name, BBB )
        self.thisBook.objectNameString = "USFX XML Bible Book object"
        self.thisBook.objectTypeString = "USFX"

        C = V = '0'
        for element in bookElement:
            #print( "element", repr(element.tag) )
            location = "{} of {} {}:{}".format( element.tag, mainLocation, C, V )
            if element.tag == 'id':
                idText = clean( element.text )
                Globals.checkXMLNoTail( element, location, 'vsg3' )
                Globals.checkXMLNoSubelements( element, location, 'ksq2' )
                for attrib,value in element.items():
                    if attrib == 'id':
                        assert( value == bookCode )
                    else:
                        logging.warning( _("vsg4 Unprocessed {} attribute ({}) in {}").format( attrib, value, location ) )
                self.thisBook.appendLine( 'id', bookCode + ((' '+idText) if idText else '') )
            elif element.tag == 'ide':
                ideText = clean( element.text )
                Globals.checkXMLNoTail( element, location, 'jsa0' )
                Globals.checkXMLNoSubelements( element, location, 'ls01' )
                charset = None
                for attrib,value in element.items():
                    if attrib == 'charset': charset = value
                    else:
                        logging.warning( _("jx53 Unprocessed {} attribute ({}) in {}").format( attrib, value, location ) )
                self.thisBook.appendLine( 'ide', charset + ((' '+ideText) if ideText else '') )
            elif element.tag == 'h':
                hText = element.text
                Globals.checkXMLNoTail( element, location, 'dj35' )
                Globals.checkXMLNoAttributes( element, location, 'hs35' )
                Globals.checkXMLNoSubelements( element, location, 'hs32' )
                self.thisBook.appendLine( 'h', clean(hText) )
            elif element.tag == 'toc':
                tocText = element.text
                Globals.checkXMLNoTail( element, location, 'ss13' )
                Globals.checkXMLNoSubelements( element, location, 'js13' )
                level = None
                for attrib,value in element.items():
                    if attrib == 'level': # Seems compulsory
                        level = value
                    else:
                        logging.warning( _("dg36 Unprocessed {} attribute ({}) in {}").format( attrib, value, location ) )
                self.thisBook.appendLine( 'toc'+level, clean(tocText) )
            elif element.tag == 'c':
                Globals.checkXMLNoText( element, location, 'ks35' )
                Globals.checkXMLNoTail( element, location, 'gs35' )
                Globals.checkXMLNoSubelements( element, location, 'kdr3' ) # This is a milestone
                for attrib,value in element.items():

# 需要导入模块: from Bible import BibleBook [as 别名]
# 或者: from Bible.BibleBook import appendLine [as 别名]
    def load( self ):
        """
        Load a single source file and load book elements.
        """
        if Globals.verbosityLevel > 2: print( _("Loading {}...").format( self.sourceFilepath ) )

        lastLine, lineCount = '', 0
        BBB = None
        NRSVA_bookCode = NRSVA_chapterNumberString = NRSVA_verseNumberString = None
        subverseNumberString = sequenceNumberString = None
        lastBookCode = lastChapterNumber = lastVerseNumber = lastSequence = -1
        lastVText = ''
        with open( self.sourceFilepath, encoding=self.encoding ) as myFile: # Automatically closes the file when done
            for line in myFile:
                lineCount += 1
                #if lineCount==1 and self.encoding.lower()=='utf-8' and line[0]==chr(65279): #U+FEFF
                    #logging.info( "      UnboundBible.load: Detected UTF-16 Byte Order Marker" )
                    #line = line[1:] # Remove the UTF-8 Byte Order Marker
                if line[-1]=='\n': line=line[:-1] # Removing trailing newline character
                if not line: continue # Just discard blank lines
                lastLine = line
                #print ( 'UB file line is "' + line + '"' )
                if line[0]=='#':
                    hashBits = line[1:].split( '\t' )
                    if len(hashBits)==2 and hashBits[1]: # We have some valid meta-data
                        if hashBits[0] == 'name': self.name = hashBits[1]
                        elif hashBits[0] == 'filetype': self.filetype = hashBits[1]
                        elif hashBits[0] == 'copyright': self.copyright = hashBits[1]
                        elif hashBits[0] == 'abbreviation': self.abbreviation = hashBits[1]
                        elif hashBits[0] == 'language': self.language = hashBits[1]
                        elif hashBits[0] == 'note': self.note = hashBits[1]
                        elif hashBits[0] == 'columns': self.columns = hashBits[1]
# Should some of these be placed into self.settingsDict???
                        logging.warning( "Unknown UnboundBible meta-data field '{}' = '{}'".format( hashBits[0], hashBits[1] ) )
                    continue # Just discard comment lines

                bits = line.split( '\t' )
                #print( self.givenName, BBB, bits )
                if len(bits) == 4:
                    bookCode, chapterNumberString, verseNumberString, vText = bits
                elif len(bits) == 6:
                    bookCode, chapterNumberString, verseNumberString, subverseNumberString, sequenceNumberString, vText = bits
                elif len(bits) == 9:
                    NRSVA_bookCode, NRSVA_chapterNumberString, NRSVA_verseNumberString, bookCode, chapterNumberString, verseNumberString, subverseNumberString, sequenceNumberString, vText = bits
                elif len(bits) == 1 and self.givenName.startswith( 'lxx_a_parsing_' ):
                    logging.warning( _("Skipping bad '{}' line in {} {} {} {}:{}").format( line, self.givenName, BBB, bookCode, chapterNumberString, verseNumberString ) )
                    continue
                else: print( "Unexpected number of bits", self.givenName, BBB, bookCode, chapterNumberString, verseNumberString, len(bits), bits ); halt

                if NRSVA_bookCode: assert( len(NRSVA_bookCode) == 3 )
                if NRSVA_chapterNumberString: assert( NRSVA_chapterNumberString.isdigit() )
                if NRSVA_verseNumberString: assert( NRSVA_verseNumberString.isdigit() )

                if not bookCode and not chapterNumberString and not verseNumberString:
                    print( "Skipping empty line in {} {} {} {}:{}".format( self.givenName, BBB, bookCode, chapterNumberString, verseNumberString ) )
                    continue
                if Globals.debugFlag: assert( len(bookCode) == 3 )
                if Globals.debugFlag: assert( chapterNumberString.isdigit() )
                if Globals.debugFlag: assert( verseNumberString.isdigit() )

                if subverseNumberString:
                    logging.warning( _("subverseNumberString '{}' in {} {} {}:{}").format( subverseNumberString, BBB, bookCode, chapterNumberString, verseNumberString ) )

                vText = vText.strip() # Remove leading and trailing spaces
                if not vText: continue # Just ignore blank verses I think
                if vText == '+': continue # Not sure what this means in basic_english JHN 1:38

                chapterNumber = int( chapterNumberString )
                verseNumber = int( verseNumberString )
                if sequenceNumberString:
                    if Globals.debugFlag: assert( sequenceNumberString.isdigit() )
                    sequenceNumber = int( sequenceNumberString )
                    if Globals.debugFlag: assert( sequenceNumber > lastSequence or \
                        self.givenName in ('gothic_latin', 'hebrew_bhs_consonants', 'hebrew_bhs_vowels', 'latvian_nt', 'ukrainian_1871',) ) # Why???
                    lastSequence = sequenceNumber

                if bookCode != lastBookCode: # We've started a new book
                    if lastBookCode != -1: # Better save the last book
                        self.saveBook( thisBook )
                    BBB = Globals.BibleBooksCodes.getBBBFromUnboundBibleCode( bookCode )
                    thisBook = BibleBook( self, BBB )
                    thisBook.objectNameString = "Unbound Bible Book object"
                    thisBook.objectTypeString = "Unbound"
                    lastBookCode = bookCode
                    lastChapterNumber = lastVerseNumber = -1

                if chapterNumber != lastChapterNumber: # We've started a new chapter
                    if Globals.debugFlag: assert( chapterNumber > lastChapterNumber or BBB=='ESG' ) # Esther Greek might be an exception
                    if chapterNumber == 0:
                        logging.info( "Have chapter zero in {} {} {} {}:{}".format( self.givenName, BBB, bookCode, chapterNumberString, verseNumberString ) )
                    thisBook.appendLine( 'c', chapterNumberString )
                    lastChapterNumber = chapterNumber
                    lastVerseNumber = -1

                # Handle the verse info
                if verseNumber==lastVerseNumber and vText==lastVText:
                    logging.warning( _("Ignored duplicate verse line in {} {} {} {}:{}").format( self.givenName, BBB, bookCode, chapterNumberString, verseNumberString ) )
                    continue
                if BBB=='PSA' and verseNumberString=='1' and vText.startswith('<') and self.givenName=='basic_english':
                    # Move Psalm titles to verse zero
#.........这里部分代码省略.........

# 需要导入模块: from Bible import BibleBook [as 别名]
# 或者: from Bible.BibleBook import appendLine [as 别名]
    def load( self ):
        """
        Load a single source file and load book elements.
        """
        if Globals.verbosityLevel > 2: print( _("Loading {}...").format( self.sourceFilepath ) )

        lastLine, lineCount = '', 0
        BBB = None
        lastBookCode = lastChapterNumber = lastVerseNumber = -1
        lastVText = ''
        with open( self.sourceFilepath, encoding=self.encoding ) as myFile: # Automatically closes the file when done
            for line in myFile:
                lineCount += 1
                #if lineCount==1 and self.encoding.lower()=='utf-8' and line[0]==chr(65279): #U+FEFF
                    #logging.info( "      VPLBible.load: Detected UTF-16 Byte Order Marker" )
                    #line = line[1:] # Remove the UTF-8 Byte Order Marker
                if line[-1]=='\n': line=line[:-1] # Removing trailing newline character
                if not line: continue # Just discard blank lines
                lastLine = line
                #print ( 'VLP file line is "' + line + '"' )
                if line[0]=='#': continue # Just discard comment lines

                bits = line.split( ' ', 2 )
                #print( self.givenName, BBB, bits )
                if len(bits) == 3 and ':' in bits[1]:
                    bookCode, CVString, vText = bits
                    chapterNumberString, verseNumberString = CVString.split( ':' )
                else: print( "Unexpected number of bits", self.givenName, BBB, bookCode, chapterNumberString, verseNumberString, len(bits), bits )

                if not bookCode and not chapterNumberString and not verseNumberString:
                    print( "Skipping empty line in {} {} {} {}:{}".format( self.givenName, BBB, bookCode, chapterNumberString, verseNumberString ) )
                    continue
                if Globals.debugFlag: assert( 2  <= len(bookCode) <= 4 )
                if Globals.debugFlag: assert( chapterNumberString.isdigit() )
                if Globals.debugFlag: assert( verseNumberString.isdigit() )
                chapterNumber = int( chapterNumberString )
                verseNumber = int( verseNumberString )

                if bookCode != lastBookCode: # We've started a new book
                    if lastBookCode != -1: # Better save the last book
                        self.saveBook( thisBook )
                    if bookCode == 'Ge': BBB = 'GEN'
                    elif bookCode == 'Le': BBB = 'LEV'
                    elif bookCode == 'Jud': BBB = 'JDG'
                    elif bookCode == 'Es': BBB = 'EST'
                    elif bookCode == 'Pr': BBB = 'PRO'
                    elif bookCode == 'So': BBB = 'SNG'
                    elif bookCode == 'La': BBB = 'LAM'
                    elif bookCode == 'Jude': BBB = 'JDE'
                    else: BBB = Globals.BibleBooksCodes.getBBB( bookCode )  # Try to guess
                    assert( BBB )
                    thisBook = BibleBook( self, BBB )
                    thisBook.objectNameString = "VPL Bible Book object"
                    thisBook.objectTypeString = "VPL"
                    lastBookCode = bookCode
                    lastChapterNumber = lastVerseNumber = -1

                if chapterNumber != lastChapterNumber: # We've started a new chapter
                    if Globals.debugFlag: assert( chapterNumber > lastChapterNumber or BBB=='ESG' ) # Esther Greek might be an exception
                    if chapterNumber == 0:
                        logging.info( "Have chapter zero in {} {} {} {}:{}".format( self.givenName, BBB, bookCode, chapterNumberString, verseNumberString ) )
                    thisBook.appendLine( 'c', chapterNumberString )
                    lastChapterNumber = chapterNumber
                    lastVerseNumber = -1

                # Handle special formatting
                #   [brackets] are for Italicized words
                #   <brackets> are for the Words of Christ in Red
                #   «brackets»  are for the Titles in the Book  of Psalms.
                vText = vText.replace( '[', '\\add ' ).replace( ']', '\\add*' ) \
                    .replace( '<', '\\wj ' ).replace( '>', '\\wj*' )
                if vText and vText[0]=='«':
                    assert( BBB=='PSA' and verseNumberString=='1' )
                    vBits = vText[1:].split( '»' )
                    #print( "vBits", vBits )
                    thisBook.appendLine( 'd', vBits[0] ) # Psalm title
                    vText = vBits[1].lstrip()

                # Handle the verse info
                if verseNumber==lastVerseNumber and vText==lastVText:
                    logging.warning( _("Ignored duplicate verse line in {} {} {} {}:{}").format( self.givenName, BBB, bookCode, chapterNumberString, verseNumberString ) )
                    continue
                if BBB=='PSA' and verseNumberString=='1' and vText.startswith('&lt;') and self.givenName=='basic_english':
                    # Move Psalm titles to verse zero
                    verseNumber = 0
                if verseNumber < lastVerseNumber:
                    logging.warning( _("Ignored receding verse number (from {} to {}) in {} {} {} {}:{}").format( lastVerseNumber, verseNumber, self.givenName, BBB, bookCode, chapterNumberString, verseNumberString ) )
                elif verseNumber == lastVerseNumber:
                    if vText == lastVText:
                        logging.warning( _("Ignored duplicated {} verse in {} {} {} {}:{}").format( verseNumber, self.givenName, BBB, bookCode, chapterNumberString, verseNumberString ) )
                    else:
                        logging.warning( _("Ignored duplicated {} verse number in {} {} {} {}:{}").format( verseNumber, self.givenName, BBB, bookCode, chapterNumberString, verseNumberString ) )
                thisBook.appendLine( 'v', verseNumberString + ' ' + vText )
                lastVText = vText
                lastVerseNumber = verseNumber

        # Save the final book
        self.saveBook( thisBook )
        self.doPostLoadProcessing()