correzioni procedura salvataggio file e cartelle

bananaSPLIT/libbananasplit/libsplit.py

@@ -23,7 +23,9 @@ class bananaSPLITTER(threading.Thread):
 			self.docStruct = self.fileParams['docStruct']
 			self.settings = self.fileParams['settings']
 			self.fileName = self.fileParams['name']
+			self.outPath = self.paths['OUTworkPath']+slugify(self.fileName)
 			self.beginTime = time.time()
+			os.mkdir(self.outPath)
 			pass
 		else:
 			self.log.critical("Non e' stato fornito il nome di alcun file da splittare!")
@@ -31,25 +33,30 @@ class bananaSPLITTER(threading.Thread):
 	
 	def run(self):
 		self.log.info("Nuovo SPLITTER  su file: {}".format(self.fileName))
-		self.openFile()
-		self.remEmptyLines()
-		self.splitFile()
-		if self.settings['removeDuplicates']:
-			self.log.info("Controllo se ci sono dei duplicati..")
-			self.removeDuplicates()
-		else:
-			for idx, ff in enumerate(self.fileList):
-				ff['duplicate']=False
-				self.fileList[idx]=ff
-			print('Salto il controllo dei duplicati..')
-		if self.settings['saveSeparateFiles']:
-			self.saveSeparate()
-		if self.settings['saveBodyFile']:
-			self.saveBody()
+		try:
+			self.openFile()
+			self.remEmptyLines()
+			self.splitFile()
+			if self.settings['removeDuplicates']:
+				self.log.info("Controllo se ci sono dei duplicati..")
+				self.removeDuplicates()
+			else:
+				for idx, ff in enumerate(self.fileList):
+					ff['duplicate']=False
+					self.fileList[idx]=ff
+				print('Salto il controllo dei duplicati..')
+			if self.settings['saveSeparateFiles']:
+				self.saveSeparate()
+			if self.settings['saveBodyFile']:
+				self.saveBody()
+		except UnicodeDecodeError as ee:
+			self.log.critical("Il file [{}] contiene caratteri non compatibili con la codifica scelta! [{}]"
+							.format(self.fileParams['name'],ee))
 		pass
 		
 	def openFile(self):
 		try:
+			os.chdir(self.paths["INworkPath"])
 			self.log.info("Carico il contenuto..")
 			fp = open(self.fileParams['name'], mode='r', encoding=self.settings['encoding'])
 			self.rawFile = fp.readlines()
@@ -57,9 +64,6 @@ class bananaSPLITTER(threading.Thread):
 		except IOError as e:
 			self.log.critical("Impossibile aprire il file: {}! [{}]".format(self.fileName,e))
 			raise BaseException("OpenFile") 	
-		except UnicodeDecodeError as ee:
-			self.log.critical("Il file [{}] contiene caratteri non compatibili con la codifica scelta! [{}]"
-							.format(self.fileParams['name'],ee))
 		pass
 
 	def remEmptyLines(self):
@@ -204,11 +208,11 @@ class bananaSPLITTER(threading.Thread):
 				ff['duplicate'] = True
 				self.fileList[idx]=ff
 				self.duplicateNumber+=1
-		self.log.info("Ho rimosso {} duplicati di {} articoli..\n". format(self.duplicateNumber, len(duplicateList)))
+		self.log.info("Ho rimosso {} duplicati di {} articoli..". format(self.duplicateNumber, len(duplicateList)))
 		pass
 		
 	def saveSeparate(self):
-		os.mkdir(self.paths['OUTworkPath']+slugify(self.fileName))
+		os.chdir(self.outPath)
 		self.paths['OUTworkPath']=self.paths['OUTworkPath']+slugify(self.fileName)
 		self.log.info("Salvo gli articoli in file separati...")
 		self.log.debug("Persorso: {0}".format(self.paths['OUTworkPath'].format('nomeFile')))
@@ -220,7 +224,7 @@ class bananaSPLITTER(threading.Thread):
 														 docnum=self.bodyCounter,\
 														 papername=ff['newsPaperName'].strip(),\
 														 **ff['date'])
-					out=open(self.paths['OUTworkPath']+'{0}'.format(fName),'wb')
+					out=open('{0}'.format(fName),'wb')
 					if self.settings['includeTitle']:
 						ff['content'] = ff['title']+os.linesep+ff['content']
 					out.write(ff['content'].encode(self.settings['encoding']))
@@ -232,8 +236,9 @@ class bananaSPLITTER(threading.Thread):
 		pass
 	
 	def saveBody(self):
-		print('Salvo gli articoli in un singolo file vicino agli originali...')
-		print ('Persorso: {0}'.format(self.paths['OUTworkPath'].format('nomeFile')))
+		self.log.info('Salvo gli articoli in un singolo file vicino agli originali...')
+		os.chdir(self.outPath)
+		print ('Persorso: {0}'.format(self.outPath))
 		try:
 			fName=slugify(self.fileName)
 			fName='BODYFILE_{0}.txt'.format(fName[:self.settings['maxTitleLen']])

bananaSPLIT/libbananasplit/testEN.json

@@ -9,7 +9,7 @@
 	"name": "",
 		"paths": {
 			"INworkPath": "D:\\Emanuele\\Documenti\\workspace\\bananaSPLIT\\TestFiles\\",
-			"OUTworkPath": "D:\\Test\\Separati\\",
+			"OUTworkPath": "H:\\",
 			"OUTnameFormat": "TEST_{docnum}_{year:04d}{month:02d}{day:02d}_{title}.txt"
 		},
 		"docStruct": {

bananaSPLIT/libbananasplit/testITA.json

@@ -9,7 +9,7 @@
 		"name": "",
 		"paths": {
 			"INworkPath": "D:\\Emanuele\\Documenti\\workspace\\bananaSPLIT\\TestFiles\\",
-			"OUTworkPath": "D:\\Test\\Separati\\",
+			"OUTworkPath": "H:\\",
 			"OUTnameFormat": "TEST_{docnum}_{year:04d}{month:02d}{day:02d}_{title}.txt"
 		},
 		"docStruct": {

bananaSPLIT/libtestmain.py

@@ -5,6 +5,7 @@ Created on 1 dic 2019
 '''
 import os
 from glob import glob
+from copy import deepcopy
 from libsplit import bananaSPLITTER
 from libconfload import bananaCONF
 from libfancylogger import fancyLogger
@@ -16,16 +17,18 @@ confl.open()
 
 confl.use("testEN.json")
 splconf = confl.getParams("splitter")
-for f in glob(splconf["paths"]["INworkPath"]+"*.txt"):
+splist = []
+os.chdir(splconf["paths"]["INworkPath"])
+for f in glob("*.txt"):
 	splconf["name"] = f
-	splitter = bananaSPLITTER(fileParams=splconf, logger=logger)
-	splitter.openFile()
-	splitter.remEmptyLines()
-	splitter.splitFile()
-	splitter.removeDuplicates()
-	splitter.saveBody()
-	splitter.saveSeparate()
-
+	logger.info("-"*80)
+	splitter = bananaSPLITTER(fileParams=deepcopy(splconf), logger=logger)
+	splist.append(splitter)
+	splitter.start()
+	splitter.join()
+	del splitter
+
+logger.info("\n"+"="*50+"\n\tFINITO!!!\n"+"="*50)