def _loadBookMP(self, BBB, filename=None):
"""
Used for multiprocessing.
NOTE: You should ensure that preload() has been called first.
"""
if BibleOrgSysGlobals.debugFlag and debuggingThisModule:
print("USXXMLBible._loadBookMP( {}, {} )".format(BBB, filename))
assert self.preloadDone
if BBB in self.books: return # Already loaded
if BBB in self.triedLoadingBook:
logging.warning(
"We had already tried loading USX {} for {}".format(
BBB, self.name))
return # We've already attempted to load this book
self.triedLoadingBook[BBB] = True
if BibleOrgSysGlobals.verbosityLevel > 2 or BibleOrgSysGlobals.debugFlag:
print(
_(" USXXMLBible: Loading {} from {} from {}…").format(
BBB, self.name, self.sourceFolder))
if filename is None: filename = self.possibleFilenameDict[BBB]
UBB = USXXMLBibleBook(self, BBB)
UBB.load(filename, self.givenFolderName, self.encoding)
UBB.validateMarkers()
#for j, something in enumerate( UBB._processedLines ):
#print( j, something )
#if j > 100: break
#for j, something in enumerate( sorted(UBB._CVIndex) ):
#print( j, something )
#if j > 50: break
#halt
return UBB
def _loadBookMP( self, BBB, filename=None ):
"""
Used for multiprocessing.
NOTE: You should ensure that preload() has been called first.
"""
if BibleOrgSysGlobals.debugFlag and debuggingThisModule:
print( "USXXMLBible._loadBookMP( {}, {} )".format( BBB, filename ) )
assert self.preloadDone
if BBB in self.books: return # Already loaded
if BBB in self.triedLoadingBook:
logging.warning( "We had already tried loading USX {} for {}".format( BBB, self.name ) )
return # We've already attempted to load this book
self.triedLoadingBook[BBB] = True
if BibleOrgSysGlobals.verbosityLevel > 2 or BibleOrgSysGlobals.debugFlag: print( _(" USXXMLBible: Loading {} from {} from {}…").format( BBB, self.name, self.sourceFolder ) )
if filename is None: filename = self.possibleFilenameDict[BBB]
UBB = USXXMLBibleBook( self, BBB )
UBB.load( filename, self.givenFolderName, self.encoding )
UBB.validateMarkers()
#for j, something in enumerate( UBB._processedLines ):
#print( j, something )
#if j > 100: break
#for j, something in enumerate( sorted(UBB._CVIndex) ):
#print( j, something )
#if j > 50: break
#halt
return UBB
def loadBook( self, BBB, filename=None ):
"""
Used for multiprocessing.
"""
if Globals.verbosityLevel > 2: print( "USXXMLBible.loadBook( {}, {} )".format( BBB, filename ) )
if BBB in self.books: return # Already loaded
if BBB in self.triedLoadingBook:
logging.warning( "We had already tried loading USX {} for {}".format( BBB, self.name ) )
return # We've already attempted to load this book
self.triedLoadingBook[BBB] = True
if Globals.verbosityLevel > 2 or Globals.debugFlag: print( _(" USXXMLBible: Loading {} from {} from {}...").format( BBB, self.name, self.sourceFolder ) )
if filename is None: filename = self.possibleFilenameDict[BBB]
UBB = USXXMLBibleBook( self.name, BBB )
UBB.load( filename, self.givenFolderName, self.encoding )
UBB.validateMarkers()
#for j, something in enumerate( UBB._processedLines ):
#print( j, something )
#if j > 100: break
#for j, something in enumerate( sorted(UBB._CVIndex) ):
#print( j, something )
#if j > 50: break
#halt
self.saveBook( UBB )
def load( self ):
"""
Load the books.
"""
def loadSSFData( ssfFilepath, encoding='utf-8' ):
"""Process the SSF data from the given filepath.
Returns a dictionary."""
if BibleOrgSysGlobals.verbosityLevel > 2: print( _("Loading SSF data from {!r}").format( ssfFilepath ) )
lastLine, lineCount, status, settingsDict = '', 0, 0, {}
with open( ssfFilepath, encoding=encoding ) as myFile: # Automatically closes the file when done
for line in myFile:
lineCount += 1
if lineCount==1 and line and line[0]==chr(65279): #U+FEFF
logging.info( "USXXMLBible.load: Detected UTF-16 Byte Order Marker in {}".format( ssfFilepath ) )
line = line[1:] # Remove the Byte Order Marker
if line[-1]=='\n': line = line[:-1] # Remove trailing newline character
line = line.strip() # Remove leading and trailing whitespace
if not line: continue # Just discard blank lines
lastLine = line
processed = False
if status==0 and line=="<ScriptureText>":
status = 1
processed = True
elif status==1 and line=="</ScriptureText>":
status = 2
processed = True
elif status==1 and line[0]=='<' and line.endswith('/>'): # Handle a self-closing (empty) field
fieldname = line[1:-3] if line.endswith(' />') else line[1:-2] # Handle it with or without a space
if ' ' not in fieldname:
settingsDict[fieldname] = ''
processed = True
elif ' ' in fieldname: # Some fields (like "Naming") may contain attributes
bits = fieldname.split( None, 1 )
assert( len(bits)==2 )
fieldname = bits[0]
attributes = bits[1]
#print( "attributes = {!r}".format( attributes) )
settingsDict[fieldname] = (contents, attributes)
processed = True
elif status==1 and line[0]=='<' and line[-1]=='>':
ix1 = line.find('>')
ix2 = line.find('</')
if ix1!=-1 and ix2!=-1 and ix2>ix1:
fieldname = line[1:ix1]
contents = line[ix1+1:ix2]
if ' ' not in fieldname and line[ix2+2:-1]==fieldname:
settingsDict[fieldname] = contents
processed = True
elif ' ' in fieldname: # Some fields (like "Naming") may contain attributes
bits = fieldname.split( None, 1 )
assert( len(bits)==2 )
fieldname = bits[0]
attributes = bits[1]
#print( "attributes = {!r}".format( attributes) )
if line[ix2+2:-1]==fieldname:
settingsDict[fieldname] = (contents, attributes)
processed = True
if not processed: logging.error( "Unexpected {!r} line in SSF file".format( line ) )
if BibleOrgSysGlobals.verbosityLevel > 2:
print( " " + _("Got {} SSF entries:").format( len(settingsDict) ) )
if BibleOrgSysGlobals.verbosityLevel > 3:
for key in sorted(settingsDict):
print( " {}: {}".format( key, settingsDict[key] ) )
self.ssfDict = settingsDict # We'll keep a copy of just the SSF settings
self.settingsDict = settingsDict.copy() # This will be all the combined settings
# end of loadSSFData
if BibleOrgSysGlobals.verbosityLevel > 1: print( _("USXXMLBible: Loading {} from {}...").format( self.name, self.givenFolderName ) )
# Do a preliminary check on the contents of our folder
foundFiles, foundFolders = [], []
for something in os.listdir( self.givenFolderName ):
somepath = os.path.join( self.givenFolderName, something )
if os.path.isdir( somepath ): foundFolders.append( something )
elif os.path.isfile( somepath ): foundFiles.append( something )
else: logging.error( "Not sure what {!r} is in {}!".format( somepath, self.givenFolderName ) )
if foundFolders: logging.info( "USXXMLBible.load: Surprised to see subfolders in {!r}: {}".format( self.givenFolderName, foundFolders ) )
if not foundFiles:
if BibleOrgSysGlobals.verbosityLevel > 0: print( "USXXMLBible.load: Couldn't find any files in {!r}".format( self.givenFolderName ) )
return # No use continuing
if 0: # We don't have a getSSFFilenames function
# Attempt to load the metadata file
ssfFilepathList = self.USXFilenamesObject.getSSFFilenames( searchAbove=True, auto=True )
if len(ssfFilepathList) == 1: # Seems we found the right one
loadSSFData( ssfFilepathList[0] )
# Load the books one by one -- assuming that they have regular Paratext style filenames
# DON'T KNOW WHY THIS DOESN'T WORK
if 0 and BibleOrgSysGlobals.maxProcesses > 1: # Load all the books as quickly as possible
parameters = []
for BBB,filename in self.USXFilenamesObject.getConfirmedFilenames():
parameters.append( BBB )
#print( "parameters", parameters )
with multiprocessing.Pool( processes=BibleOrgSysGlobals.maxProcesses ) as pool: # start worker processes
results = pool.map( self.loadBook, parameters ) # have the pool do our loads
print( "results", results )
assert( len(results) == len(parameters) )
for j, UBB in enumerate( results ):
BBB = parameters[j]
self.books[BBB] = UBB
# Make up our book name dictionaries while we're at it
assumedBookNames = UBB.getAssumedBookNames()
for assumedBookName in assumedBookNames:
self.BBBToNameDict[BBB] = assumedBookName
assumedBookNameLower = assumedBookName.lower()
self.bookNameDict[assumedBookNameLower] = BBB # Store the deduced book name (just lower case)
self.combinedBookNameDict[assumedBookNameLower] = BBB # Store the deduced book name (just lower case)
if ' ' in assumedBookNameLower: self.combinedBookNameDict[assumedBookNameLower.replace(' ','')] = BBB # Store the deduced book name (lower case without spaces)
else: # Just single threaded
for BBB,filename in self.USXFilenamesObject.getConfirmedFilenames():
UBB = USXXMLBibleBook( self, BBB )
UBB.load( filename, self.givenFolderName, self.encoding )
UBB.validateMarkers()
#print( UBB )
self.saveBook( UBB )
#self.books[BBB] = UBB
## Make up our book name dictionaries while we're at it
#assumedBookNames = UBB.getAssumedBookNames()
#for assumedBookName in assumedBookNames:
#self.BBBToNameDict[BBB] = assumedBookName
#assumedBookNameLower = assumedBookName.lower()
#self.bookNameDict[assumedBookNameLower] = BBB # Store the deduced book name (just lower case)
#self.combinedBookNameDict[assumedBookNameLower] = BBB # Store the deduced book name (just lower case)
#if ' ' in assumedBookNameLower: self.combinedBookNameDict[assumedBookNameLower.replace(' ','')] = BBB # Store the deduced book name (lower case without spaces)
if not self.books: # Didn't successfully load any regularly named books -- maybe the files have weird names??? -- try to be intelligent here
if BibleOrgSysGlobals.verbosityLevel > 2:
print( "USXXMLBible.load: Didn't find any regularly named USX files in {!r}".format( self.givenFolderName ) )
for thisFilename in foundFiles:
# Look for BBB in the ID line (which should be the first line in a USX file)
isUSX = False
thisPath = os.path.join( self.givenFolderName, thisFilename )
with open( thisPath ) as possibleUSXFile: # Automatically closes the file when done
for line in possibleUSXFile:
if line.startswith( '\\id ' ):
USXId = line[4:].strip()[:3] # Take the first three non-blank characters after the space after id
if BibleOrgSysGlobals.verbosityLevel > 2: print( "Have possible USX ID {!r}".format( USXId ) )
BBB = BibleOrgSysGlobals.BibleBooksCodes.getBBBFromUSFM( USXId )
if BibleOrgSysGlobals.verbosityLevel > 2: print( "BBB is {!r}".format( BBB ) )
isUSX = True
break # We only look at the first line
if isUSX:
UBB = USXXMLBibleBook( self, BBB )
UBB.load( self.givenFolderName, thisFilename, self.encoding )
UBB.validateMarkers()
print( UBB )
self.books[BBB] = UBB
# Make up our book name dictionaries while we're at it
assumedBookNames = UBB.getAssumedBookNames()
for assumedBookName in assumedBookNames:
self.BBBToNameDict[BBB] = assumedBookName
assumedBookNameLower = assumedBookName.lower()
self.bookNameDict[assumedBookNameLower] = BBB # Store the deduced book name (just lower case)
self.combinedBookNameDict[assumedBookNameLower] = BBB # Store the deduced book name (just lower case)
if ' ' in assumedBookNameLower: self.combinedBookNameDict[assumedBookNameLower.replace(' ','')] = BBB # Store the deduced book name (lower case without spaces)
if self.books: print( "USXXMLBible.load: Found {} irregularly named USX files".format( len(self.books) ) )
self.doPostLoadProcessing()
def load(self):
"""
Load the books.
"""
def loadSSFData(ssfFilepath, encoding='utf-8'):
"""Process the SSF data from the given filepath.
Returns a dictionary."""
if BibleOrgSysGlobals.verbosityLevel > 2:
print(_("Loading SSF data from {!r}").format(ssfFilepath))
lastLine, lineCount, status, settingsDict = '', 0, 0, {}
with open(ssfFilepath, encoding=encoding
) as myFile: # Automatically closes the file when done
for line in myFile:
lineCount += 1
if lineCount == 1 and line and line[0] == chr(
65279): #U+FEFF
logging.info(
"USXXMLBible.load: Detected UTF-16 Byte Order Marker in {}"
.format(ssfFilepath))
line = line[1:] # Remove the Byte Order Marker
if line[-1] == '\n':
line = line[:-1] # Remove trailing newline character
line = line.strip(
) # Remove leading and trailing whitespace
if not line: continue # Just discard blank lines
lastLine = line
processed = False
if status == 0 and line == "<ScriptureText>":
status = 1
processed = True
elif status == 1 and line == "</ScriptureText>":
status = 2
processed = True
elif status == 1 and line[0] == '<' and line.endswith(
'/>'): # Handle a self-closing (empty) field
fieldname = line[1:-3] if line.endswith(
' />') else line[
1:-2] # Handle it with or without a space
if ' ' not in fieldname:
settingsDict[fieldname] = ''
processed = True
elif ' ' in fieldname: # Some fields (like "Naming") may contain attributes
bits = fieldname.split(None, 1)
assert (len(bits) == 2)
fieldname = bits[0]
attributes = bits[1]
#print( "attributes = {!r}".format( attributes) )
settingsDict[fieldname] = (contents, attributes)
processed = True
elif status == 1 and line[0] == '<' and line[-1] == '>':
ix1 = line.find('>')
ix2 = line.find('</')
if ix1 != -1 and ix2 != -1 and ix2 > ix1:
fieldname = line[1:ix1]
contents = line[ix1 + 1:ix2]
if ' ' not in fieldname and line[
ix2 + 2:-1] == fieldname:
settingsDict[fieldname] = contents
processed = True
elif ' ' in fieldname: # Some fields (like "Naming") may contain attributes
bits = fieldname.split(None, 1)
assert (len(bits) == 2)
fieldname = bits[0]
attributes = bits[1]
#print( "attributes = {!r}".format( attributes) )
if line[ix2 + 2:-1] == fieldname:
settingsDict[fieldname] = (contents,
attributes)
processed = True
if not processed:
logging.error(
"Unexpected {!r} line in SSF file".format(line))
if BibleOrgSysGlobals.verbosityLevel > 2:
print(" " +
_("Got {} SSF entries:").format(len(settingsDict)))
if BibleOrgSysGlobals.verbosityLevel > 3:
for key in sorted(settingsDict):
print(" {}: {}".format(key, settingsDict[key]))
self.ssfDict = settingsDict # We'll keep a copy of just the SSF settings
self.settingsDict = settingsDict.copy(
) # This will be all the combined settings
# end of loadSSFData
if BibleOrgSysGlobals.verbosityLevel > 1:
print(
_("USXXMLBible: Loading {} from {}...").format(
self.name, self.givenFolderName))
# Do a preliminary check on the contents of our folder
foundFiles, foundFolders = [], []
for something in os.listdir(self.givenFolderName):
somepath = os.path.join(self.givenFolderName, something)
if os.path.isdir(somepath): foundFolders.append(something)
elif os.path.isfile(somepath): foundFiles.append(something)
else:
logging.error("Not sure what {!r} is in {}!".format(
somepath, self.givenFolderName))
if foundFolders:
logging.info(
"USXXMLBible.load: Surprised to see subfolders in {!r}: {}".
format(self.givenFolderName, foundFolders))
if not foundFiles:
if BibleOrgSysGlobals.verbosityLevel > 0:
print(
"USXXMLBible.load: Couldn't find any files in {!r}".format(
self.givenFolderName))
return # No use continuing
if 0: # We don't have a getSSFFilenames function
# Attempt to load the metadata file
ssfFilepathList = self.USXFilenamesObject.getSSFFilenames(
searchAbove=True, auto=True)
if len(ssfFilepathList) == 1: # Seems we found the right one
loadSSFData(ssfFilepathList[0])
# Load the books one by one -- assuming that they have regular Paratext style filenames
# DON'T KNOW WHY THIS DOESN'T WORK
if 0 and BibleOrgSysGlobals.maxProcesses > 1: # Load all the books as quickly as possible
parameters = []
for BBB, filename in self.USXFilenamesObject.getConfirmedFilenames(
):
parameters.append(BBB)
#print( "parameters", parameters )
with multiprocessing.Pool(processes=BibleOrgSysGlobals.maxProcesses
) as pool: # start worker processes
results = pool.map(self.loadBook,
parameters) # have the pool do our loads
print("results", results)
assert (len(results) == len(parameters))
for j, UBB in enumerate(results):
BBB = parameters[j]
self.books[BBB] = UBB
# Make up our book name dictionaries while we're at it
assumedBookNames = UBB.getAssumedBookNames()
for assumedBookName in assumedBookNames:
self.BBBToNameDict[BBB] = assumedBookName
assumedBookNameLower = assumedBookName.lower()
self.bookNameDict[
assumedBookNameLower] = BBB # Store the deduced book name (just lower case)
self.combinedBookNameDict[
assumedBookNameLower] = BBB # Store the deduced book name (just lower case)
if ' ' in assumedBookNameLower:
self.combinedBookNameDict[
assumedBookNameLower.replace(
' ', ''
)] = BBB # Store the deduced book name (lower case without spaces)
else: # Just single threaded
for BBB, filename in self.USXFilenamesObject.getConfirmedFilenames(
):
UBB = USXXMLBibleBook(self, BBB)
UBB.load(filename, self.givenFolderName, self.encoding)
UBB.validateMarkers()
#print( UBB )
self.saveBook(UBB)
#self.books[BBB] = UBB
## Make up our book name dictionaries while we're at it
#assumedBookNames = UBB.getAssumedBookNames()
#for assumedBookName in assumedBookNames:
#self.BBBToNameDict[BBB] = assumedBookName
#assumedBookNameLower = assumedBookName.lower()
#self.bookNameDict[assumedBookNameLower] = BBB # Store the deduced book name (just lower case)
#self.combinedBookNameDict[assumedBookNameLower] = BBB # Store the deduced book name (just lower case)
#if ' ' in assumedBookNameLower: self.combinedBookNameDict[assumedBookNameLower.replace(' ','')] = BBB # Store the deduced book name (lower case without spaces)
if not self.books: # Didn't successfully load any regularly named books -- maybe the files have weird names??? -- try to be intelligent here
if BibleOrgSysGlobals.verbosityLevel > 2:
print(
"USXXMLBible.load: Didn't find any regularly named USX files in {!r}"
.format(self.givenFolderName))
for thisFilename in foundFiles:
# Look for BBB in the ID line (which should be the first line in a USX file)
isUSX = False
thisPath = os.path.join(self.givenFolderName, thisFilename)
with open(
thisPath
) as possibleUSXFile: # Automatically closes the file when done
for line in possibleUSXFile:
if line.startswith('\\id '):
USXId = line[4:].strip(
)[:
3] # Take the first three non-blank characters after the space after id
if BibleOrgSysGlobals.verbosityLevel > 2:
print(
"Have possible USX ID {!r}".format(USXId))
BBB = BibleOrgSysGlobals.BibleBooksCodes.getBBBFromUSFM(
USXId)
if BibleOrgSysGlobals.verbosityLevel > 2:
print("BBB is {!r}".format(BBB))
isUSX = True
break # We only look at the first line
if isUSX:
UBB = USXXMLBibleBook(self, BBB)
UBB.load(self.givenFolderName, thisFilename, self.encoding)
UBB.validateMarkers()
print(UBB)
self.books[BBB] = UBB
# Make up our book name dictionaries while we're at it
assumedBookNames = UBB.getAssumedBookNames()
for assumedBookName in assumedBookNames:
self.BBBToNameDict[BBB] = assumedBookName
assumedBookNameLower = assumedBookName.lower()
self.bookNameDict[
assumedBookNameLower] = BBB # Store the deduced book name (just lower case)
self.combinedBookNameDict[
assumedBookNameLower] = BBB # Store the deduced book name (just lower case)
if ' ' in assumedBookNameLower:
self.combinedBookNameDict[
assumedBookNameLower.replace(
' ', ''
)] = BBB # Store the deduced book name (lower case without spaces)
if self.books:
print("USXXMLBible.load: Found {} irregularly named USX files".
format(len(self.books)))
self.doPostLoadProcessing()
def loadBooks( self ):
"""
Load the books.
"""
if BibleOrgSysGlobals.verbosityLevel > 1:
print( _("USXXMLBible: Loading {} books from {}…").format( self.name, self.givenFolderName ) )
if not self.preloadDone: self.preload()
# Do a preliminary check on the contents of our folder
foundFiles, foundFolders = [], []
for something in os.listdir( self.givenFolderName ):
somepath = os.path.join( self.givenFolderName, something )
if os.path.isdir( somepath ): foundFolders.append( something )
elif os.path.isfile( somepath ): foundFiles.append( something )
else: logging.error( "Not sure what {!r} is in {}!".format( somepath, self.givenFolderName ) )
if foundFolders: logging.info( "USXXMLBible.loadBooks: Surprised to see subfolders in {!r}: {}".format( self.givenFolderName, foundFolders ) )
if not foundFiles:
if BibleOrgSysGlobals.verbosityLevel > 0: print( "USXXMLBible.loadBooks: Couldn't find any files in {!r}".format( self.givenFolderName ) )
return # No use continuing
#if 0: # We don't have a getSSFFilenames function
## Attempt to load the metadata file
#ssfFilepathList = self.USXFilenamesObject.getSSFFilenames( searchAbove=True, auto=True )
#if len(ssfFilepathList) == 1: # Seems we found the right one
#PTXSettingsDict = loadPTX7ProjectData( ssfFilepathList[0] )
#if PTXSettingsDict:
#if 'PTX' not in self.suppliedMetadata: self.suppliedMetadata['PTX'] = {}
#self.suppliedMetadata['PTX']['SSF'] = PTXSettingsDict
#self.applySuppliedMetadata( 'SSF' ) # Copy some to BibleObject.settingsDict
# Load the books one by one -- assuming that they have regular Paratext style filenames
if BibleOrgSysGlobals.maxProcesses > 1: # Load all the books as quickly as possible
parameters = []
for BBB,filename in self.USXFilenamesObject.getConfirmedFilenameTuples():
parameters.append( BBB )
#print( "parameters", parameters )
if BibleOrgSysGlobals.verbosityLevel > 1:
print( _("Loading {} {} books using {} CPUs…").format( len(parameters), 'USX', BibleOrgSysGlobals.maxProcesses ) )
print( _(" NOTE: Outputs (including error and warning messages) from loading various books may be interspersed.") )
with multiprocessing.Pool( processes=BibleOrgSysGlobals.maxProcesses ) as pool: # start worker processes
results = pool.map( self._loadBookMP, parameters ) # have the pool do our loads
#print( "results", results )
#assert len(results) == len(parameters)
for j, UBB in enumerate( results ):
BBB = parameters[j]
#self.books[BBB] = UBB
self.stashBook( UBB )
# Make up our book name dictionaries while we're at it
assumedBookNames = UBB.getAssumedBookNames()
for assumedBookName in assumedBookNames:
self.BBBToNameDict[BBB] = assumedBookName
assumedBookNameLower = assumedBookName.lower()
self.bookNameDict[assumedBookNameLower] = BBB # Store the deduced book name (just lower case)
self.combinedBookNameDict[assumedBookNameLower] = BBB # Store the deduced book name (just lower case)
if ' ' in assumedBookNameLower: self.combinedBookNameDict[assumedBookNameLower.replace(' ','')] = BBB # Store the deduced book name (lower case without spaces)
else: # Just single threaded
#print( self.USXFilenamesObject.getConfirmedFilenameTuples() ); halt
for BBB,filename in self.possibleFilenameDict.items():
self.loadBook( BBB, filename ) # also saves it
#UBB = USXXMLBibleBook( self, BBB )
#UBB.load( filename, self.givenFolderName, self.encoding )
#UBB.validateMarkers()
#print( UBB )
#self.stashBook( UBB )
if not self.books: # Didn't successfully load any regularly named books -- maybe the files have weird names??? -- try to be intelligent here
if BibleOrgSysGlobals.verbosityLevel > 2:
print( "USXXMLBible.loadBooks: Didn't find any regularly named USX files in {!r}".format( self.givenFolderName ) )
for thisFilename in foundFiles:
# Look for BBB in the ID line (which should be the first line in a USX file)
isUSX = False
thisPath = os.path.join( self.givenFolderName, thisFilename )
try:
with open( thisPath ) as possibleUSXFile: # Automatically closes the file when done
for line in possibleUSXFile:
if line.startswith( '\\id ' ):
USXId = line[4:].strip()[:3] # Take the first three non-blank characters after the space after id
if BibleOrgSysGlobals.verbosityLevel > 2: print( "Have possible USX ID {!r}".format( USXId ) )
BBB = BibleOrgSysGlobals.BibleBooksCodes.getBBBFromUSFM( USXId )
if BibleOrgSysGlobals.verbosityLevel > 2: print( "BBB is {!r}".format( BBB ) )
isUSX = True
break # We only look at the first line
except UnicodeDecodeError: isUSX = False
if isUSX:
UBB = USXXMLBibleBook( self, BBB )
UBB.load( self.givenFolderName, thisFilename, self.encoding )
UBB.validateMarkers()
print( UBB )
self.books[BBB] = UBB
# Make up our book name dictionaries while we're at it
assumedBookNames = UBB.getAssumedBookNames()
for assumedBookName in assumedBookNames:
self.BBBToNameDict[BBB] = assumedBookName
assumedBookNameLower = assumedBookName.lower()
self.bookNameDict[assumedBookNameLower] = BBB # Store the deduced book name (just lower case)
self.combinedBookNameDict[assumedBookNameLower] = BBB # Store the deduced book name (just lower case)
if ' ' in assumedBookNameLower: self.combinedBookNameDict[assumedBookNameLower.replace(' ','')] = BBB # Store the deduced book name (lower case without spaces)
if self.books: print( "USXXMLBible.loadBooks: Found {} irregularly named USX files".format( len(self.books) ) )
self.doPostLoadProcessing()