merge con il brance lib-devel

This commit is contained in:
2019-12-13 16:20:34 +01:00
15 changed files with 90423 additions and 2 deletions

2
.gitignore vendored
View File

@@ -1,6 +1,6 @@
/.DS_Store
/.project
/.pydevproject
bananaSPLIT/build
bananaSPLIT.exe.spec
bananaSPLIT/build
/TestFiles/

1
.settings/.gitignore vendored Normal file
View File

@@ -0,0 +1 @@
/org.eclipse.core.resources.prefs

13811
TestFiles/GUARDIAN 1993.txt Normal file

File diff suppressed because it is too large Load Diff

22792
TestFiles/NYT 1990.txt Normal file

File diff suppressed because it is too large Load Diff

23149
TestFiles/NYT 1994.txt Normal file

File diff suppressed because it is too large Load Diff

30024
TestFiles/NYT 1997.txt Normal file

File diff suppressed because it is too large Load Diff

1
TestFiles/README Normal file
View File

@@ -0,0 +1 @@
Qui si mettono i file di test per la versione GUI di bananaSPLIT

View File

@@ -1 +1,2 @@
*.py[ocd]
/bananaSPLIT.exe.spec

View File

View File

@@ -0,0 +1,83 @@
'''
Created on 2 nov 2019
@author: Emanuele Trabattoni
'''
import json,os,glob,copy
class bananaCONF(object):
'''
Carica e Salva file di configurazione per bananaSPLITTER
'''
def __init__(self, workdir=None, logger=None):
self.log = logger
self.fileList = None
self.workdir = None
self.inUse = None
self.settingsList = dict()
if workdir is not None:
self.workdir = workdir
os.chdir(workdir)
self.log.debug("Cerco le configurazioni in: [{}]".format(os.getcwd()))
else:
self.log.error("Non mi e' stata fornita una directory per i file di configurazione")
pass
def open(self):
self.log.info("Carico i file di configurazione")
self.fileList = glob.glob(r"*.json")
if len(self.fileList) > 0:
for f in self.fileList:
try:
fp = open(f)
tf = json.load(fp)
fName = f.split("\\")[-1]
self.settingsList[fName] = copy.deepcopy(tf)
self.log.info("Caricato correttamente: {}".format(fName))
fp.close()
except json.JSONDecodeError as e:
self.log.error("Impossibile leggere la configurazione:{}\n \
Controlla il file a riga: {} e colonna:{}" .format(e.doc, e.lineno, e.colno))
except IOError as ee:
self.log.error("Impossibile aprire il file: {}".format(ee))
except Exception as eee:
self.log.critical("Eccezione inaspettata: {}".format(eee))
else:
self.log.error("Non ho trovato alcun file di configurazione!")
pass
def reload(self):
self.settingsList = None
self.fileList = None
self.inUse = None
self.open()
pass
def use(self, toUse):
self.inUse = toUse
pass
def save(self):
self.log.info("Salvo la configurazione: {}".format(self.inUse))
try:
os.chdir(self.workdir)
f=open(self.inUse)
json.dump(self.settingsList[self.inUse], f)
f.close()
except IOError as e:
self.log.error("Impossibile salvare il file: {} - [{}]".format(self.inUse,e))
pass
def getFiles(self):
return self.fileList
def getParams(self, k):
return self.settingsList[self.inUse][k]
pass
def setParams(self, k, v):
self.settingsList[self.inUse][k]=dict(v)
pass

View File

@@ -0,0 +1,85 @@
'''
Created on 2 nov 2019
@author: Emanuele Trabattoni
'''
import sys, os
import json
import logging
import colorama
class fancyLogger(object):
'''
Colorizza il logger di python, per un' esperienza stile willy wonka
'''
def __init__(self, name="Logger", consoleLog=True, fileLog=True):
settings = json.load(open(os.getcwd()+r"\libbananasplit\testEN.json"))["logger"]
colorama.init(convert=True)
self.LRED = colorama.Fore.LIGHTRED_EX
self.RED = colorama.Fore.RED
self.LYELLOW = colorama.Fore.LIGHTYELLOW_EX
self.YELLOW = colorama.Fore.YELLOW
self.LBLUE = colorama.Fore.LIGHTBLUE_EX
self.BLUE = colorama.Fore.BLUE
self.LGREEN = colorama.Fore.LIGHTGREEN_EX
self.LGREEN = colorama.Fore.GREEN
self.WHITE = colorama.Fore.LIGHTWHITE_EX
self.RST = colorama.Style.RESET_ALL
# Setup Logger
self.LOGGER = logging.getLogger(name)
self.LOGGER.setLevel(logging.DEBUG)
self.LOGGER.propagate = False
FORMATTER = logging.Formatter((settings["logFormat"]), (settings["logTimeFormat"]))
if fileLog:
# File Logging
fh = logging.FileHandler((settings["logFile"]))
fh.setLevel(logging.DEBUG)
fh.setFormatter(FORMATTER)
self.LOGGER.addHandler(fh)
if consoleLog:
# Console Logging
cl= logging.StreamHandler(sys.stdout)
cl.setLevel(logging.DEBUG)
cl.setFormatter(FORMATTER)
self.LOGGER.addHandler(cl)
pass
def debug(self, msg="Undefined Debug"):
print(self.LBLUE, end='')
self.LOGGER.debug(msg)
print(self.RST, end='')
pass
def info(self, msg="Undefined Info"):
print(self.LGREEN, end='')
self.LOGGER.info(msg)
print(self.RST, end='')
pass
def warn(self, msg="Undefined Warning"):
print(self.LYELLOW, end='')
self.LOGGER.warning(msg)
print(self.RST, end='')
pass
def error(self, msg="Undefined Error"):
print(self.LRED, end='')
self.LOGGER.error(msg)
print(self.RST, end='')
pass
def critical(self, msg="Undefined Critical"):
print(self.RED, end='')
self.LOGGER.critical(msg)
print(self.RST, end='')
pass
def testColors(self):
self.debug("Test Debug")
self.info("Test Info")
self.warn("Test Warning")
self.error("Test Error")
self.critical("Test Critical")
pass

View File

@@ -0,0 +1,276 @@
'''
Created on 2 nov 2019
@author: Emanuele Trabattoni
'''
from slugify.slugify import slugify
import time, parse, re, copy, os, threading
class bananaSPLITTER(threading.Thread):
def __init__(self, fileParams=None, logger=None):
threading.Thread.__init__(self)
self.fileParams = fileParams
self.log = logger
self.rawFile = None
self.status = "first"
self.fileList = list()
self.bodyCounter=0
self.duplicateNumber=0
if fileParams is not None:
self.log.info("Sto operando sul file: {}..".format(self.fileParams['name']))
self.paths = self.fileParams['paths']
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()
pass
else:
self.log.critical("Non e' stato fornito il nome di alcun file da splittare!")
pass
def run(self):
self.log.info("Nuovo SPLITTER su file: {}".format(self.fileName))
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
self.log.warn('Salto il controllo dei duplicati..')
# se il parse e la rimozione dei duplicati e' andata bene
# preparo e inizio il salvataggio
if os.path.exists(self.outPath):
if self.settings['removeOldFiles']:
os.chdir(self.outPath)
for f in os.listdir(self.outPath):
os.remove(f)
else:
raise FileExistsError("Non posso sovrascrivere i vecchi file, eliminali manualmente!")
else:
os.mkdir(self.outPath)
os.chdir(self.outPath)
if self.settings['saveSeparateFiles']:
self.saveSeparate()
if self.settings['saveBodyFile']:
self.saveBody()
self.log.info("L'elaborazione del file ha richiesto {:4.2f} sec".format(time.time()-self.beginTime))
except UnicodeDecodeError as ee:
self.log.critical("Il file [{}] contiene caratteri non compatibili con la codifica scelta! [{}]"
.format(self.fileParams['name'],ee))
except FileExistsError as fe:
self.log.critical(fe)
except BaseException as ee:
self.log.warning(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()
fp.close()
except IOError as e:
self.log.critical("Impossibile aprire il file: {}! [{}]".format(self.fileName,e))
raise BaseException("OpenFile")
os.rmdir(self.outPath)
pass
def remEmptyLines(self):
self.log.info("Elimino righe vuote e caratteri inutili..")
tempContent = []
try:
for ll in self.rawFile:
for c in self.settings['delChars']:
ll = ll.replace(c,'')
if ll not in ['\n', '\r']:
tempContent.append(ll)
self.rawFile = copy.deepcopy(tempContent)
return True
except:
self.log.error("Errore inaspettato durante l'eliminazione delle righe vuote!")
raise BaseException("DelLines")
del tempContent
def splitFile(self): #porting del codice dal programma originale
self.log.info("Individuo il contenuto..")
self.bodyCounter=0
self.duplicateNumber=0
docNumber = 0
docSkipped = 0
docDate = {}
title = ''
prevLine = ''
newsPaperName = ''
titleBegin = False
tempBody = list()
docSep=re.compile(self.docStruct['docSep'])
for l in self.rawFile: #per ogni linea del file
lineWords = l.lstrip().split(' ') #dividi la riga in parole
if self.status == 'first':
#prendo il numero di documento per vedere se ci sono buchi
try:
try:
nn = parse.parse("{current:d} Of {total} Documents",l.strip().capitalize()).named
if nn["current"]-docNumber==1:
pass
else:
if self.settings["showSkipped"]:
self.log.warn("Il conto dei documenti non torna! LexisNexis \
ne ha saltato qualcuno!\nPrecedente:{0}-Attuale:{1}".format(docNumber,nn["current"]))
docSkipped+=1
docNumber = nn["current"]
except:
pass #non segnalare eccezione se il parse fallisce
# ricerco la data
if (lineWords[self.settings['monthPosition']]).capitalize() in self.docStruct['dateWords']:
try:
docDate=parse.parse(self.docStruct['dateFormat'],l).named
docDate['month']=docDate['month'].lstrip().rstrip().capitalize()
docDate['month']=self.docStruct['dateWords'].index(docDate['month'])+1
title = ''
titleBegin=True
# dopo la data inizia il titolo, ma prima si cerca il nome del giornale
if self.settings['getNewsPaperName']:
try:
if prevLine.split(' ')[0].strip().isalpha():
newsPaperName = prevLine.strip()
else:
newsPaperName = self.settings['nameNotFoundStr']
except:
self.log.warn("E' successo qualcosa mentre stavo cercando il nome della pubblicazione,\
controlla i file di uscita! [{}]".format(prevLine.strip()))
else:
newsPaperName = self.settings['nameNotFoundStr']
except:
self.log.warn("Ho trovato una riga ambigua.. potrebbe essere una data ma non so: [{}]". format(l.strip('\r\n')))
pass
elif lineWords[0] in self.docStruct['headWords']:
#cambio stato e inizializzo un nuovo documento da riempire
self.status = 'head'
newDoc=dict()
newDoc['title']=title
newDoc['date']=docDate
newDoc['newsPaperName'] = newsPaperName
titleBegin=False
else:
if titleBegin:
title += l.strip().capitalize()
except IndexError:
self.log.error("Errore inaspettato, contatta il tuo sviluppatore di fiducia!")
pass
elif self.status == 'head':
tempContent = list()
if lineWords[0] not in self.docStruct['headWords']: #se la prima parola non e' tra quelle di inizio
tempBody.append(l) # vuol dire che ho trovato l'articolo e aggiungo la prima riga al contenuto del documento
self.status = 'body'
pass
elif self.status == 'body':
if not lineWords[0] in self.docStruct['tailWords']: #se la prima parola non e' tra quelle di fine
if self.settings['delLF']:
tempBody.append(l.strip('\n')) #allora sto leggendo l'articolo
else:
tempBody.append(l)
else:
self.status = 'tail'
anomaly = False
if docSep.match(l) is not None: #controlla se ci sono articoli che non hanno le parole chiave finali
self.log.warn("Ho individuato una separatore valido prima che si chiusesse l'articolo precedente, controlla i tuoi file in uscita!\n\
L'errore dovrebbe essere intorno all'articolo {} ma non sono sicuro! \n\t\t[{}]".format(docNumber, l.strip()))
self.status = 'tail'
anomaly = True
pass
elif self.status == 'tail':
if docSep.match(l) is not None or anomaly:
self.status = 'first'
anomaly = False
if self.settings['delWordBreak']:
tempContent=[ll.replace('-\n', '') for ll in tempContent]
newDoc['content']=copy.deepcopy(''.join(tempBody))
self.fileList.append(copy.deepcopy(newDoc))
tempBody=list()
self.bodyCounter +=1
pass
else:
self.log.critical("Stato Interno Sconosciuto")
prevLine=l #salva sempre e comunque il contenuto della linea precedente
pass
#ricerca terminata, espongo i risultati
self.log.info("Nel file ho trovato {0} articoli..".format(self.bodyCounter))
if docSkipped > 0:
self.log.warn("Attentione, LexisNexis ne ha saltati {} !!!".format(docSkipped))
pass
pass
def removeDuplicates(self):
titleList=[]
duplicateList=[]
for idx, ff in enumerate(self.fileList):
if ff['title'] not in titleList:
titleList.append(ff['title'])
ff['duplicate']=False
self.fileList[idx]=ff
pass
else:
if ff['title'] not in duplicateList:
duplicateList.append(ff['title'])
if self.settings['showRemovedDuplicates']:
self.log.info("Duplicato: {}".format(ff['title'].strip()))
ff['duplicate'] = True
self.fileList[idx]=ff
self.duplicateNumber+=1
self.log.info("Ho rimosso {} duplicati di {} articoli..". format(self.duplicateNumber, len(duplicateList)))
pass
def saveSeparate(self):
outFileCounter = 0
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')))
for ff in self.fileList:
try:
if ff['duplicate'] == False:
fName=self.paths['OUTnameFormat'].format(title=slugify(ff['title'][:self.settings['maxTitleLen']]),\
filename=slugify(self.fileName),\
docnum=outFileCounter,\
papername=ff['newsPaperName'].strip(),\
**ff['date'])
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']))
out.close()
outFileCounter+=1
except IOError as e:
self.log.error("Qualcosa e\' andato storto, non riesco a scrivere il file: {}".format(e))
continue
if outFileCounter < self.bodyCounter:
raise BaseException("Ho salvato meno file rispetto a quelli trovati!")
pass
def saveBody(self):
self.log.info('Salvo gli articoli in un singolo file vicino agli originali...')
self.log.debug('Persorso: {0}'.format(self.outPath))
os.chdir(self.outPath)
try:
fName=slugify(self.fileName)
fName='BODYFILE_{0}.txt'.format(fName[:self.settings['maxTitleLen']])
fileContent = os.linesep.join([cc['content'] for cc in self.fileList])
out=open('{0}'.format(fName),'wb')
out.write(fileContent.encode(self.settings['encoding']))
out.close()
except IOError as e:
self.log.error("Qualcosa e\' andato storto, non riesco a scrivere il file: {}".format(e))
pass

View File

@@ -0,0 +1,83 @@
{
"version": "v1.1a",
"logger": {
"logFile": "D:\\Test\\bananaSPLIT.log",
"logFormat": "%(asctime)s|%(levelname)-8s| %(message)-50s",
"logTimeFormat": "%m-%d %H:%M:%S"
},
"splitter": {
"name": "",
"paths": {
"INworkPath": "D:\\Emanuele\\Documenti\\workspace\\bananaSPLIT\\TestFiles\\",
"OUTworkPath": "H:\\",
"OUTnameFormat": "TEST_{docnum}_{year:04d}{month:02d}{day:02d}_{title}.txt"
},
"docStruct": {
"docSep": "\\s*Copyright [(0-9)]+",
"dateFormat": "{month} {day:d}, {year:d}{}",
"dateWords": [
"January",
"February",
"March",
"April",
"May",
"June",
"July",
"August",
"September",
"October",
"November",
"December"
],
"headWords": [
"BYLINE:",
"SECTION:",
"LENGTH:",
"DATELINE:",
"HIGHLIGHT:",
"Email:"
],
"tailWords": [
"Newstex ID:",
"NOTES:",
"LANGUAGE:",
"GRAPHIC:",
"TYPE:",
"URL:",
"LOAD-DATE:",
"PUBLICATION-TYPE:",
"DOCUMENT-TYPE:",
"CHARTS:",
"JOURNAL-CODE:"
]
},
"settings": {
"encoding": "utf-8",
"monthPosition": 0,
"getNewsPaperName": true,
"nameNotFoundStr": "ND",
"includeTitle": true,
"removeDuplicates": true,
"showSkipped": true,
"showRemovedDuplicates": false,
"maxTitleLen": 32,
"loadTXT": true,
"loadDOCX": false,
"removeOldFiles": true,
"saveSeparateFiles": true,
"saveBodyFile": true,
"saveBodyNumber": true,
"delLF": false,
"delWordBreak": true,
"delChars": [
"'",
"@",
"#",
"$",
"%",
"^",
"&"
]
}
}
}

View File

@@ -0,0 +1,80 @@
{
"version": "v1.1a",
"logger": {
"logFile": "D:\\Test\\bananaSPLIT.log",
"logFormat": "%(asctime)s|%(levelname)-8s| %(message)-50s",
"logTimeFormat": "%m-%d %H:%M:%S"
},
"splitter": {
"name": "",
"paths": {
"INworkPath": "D:\\Emanuele\\Documenti\\workspace\\bananaSPLIT\\TestFiles\\",
"OUTworkPath": "H:\\",
"OUTnameFormat": "TEST_{docnum}_{year:04d}{month:02d}{day:02d}_{title}.txt"
},
"docStruct": {
"docSep": "Copyright [(0-9)]+",
"dateFormat": "{day:d} {month} {year:d} {}",
"dateWords": [
"Gennaio",
"Febbraio",
"Marzo",
"Aprile",
"Maggio",
"Giugno",
"Luglio",
"Agosto",
"Settembre",
"Ottobre",
"Novembre",
"Dicembre"
],
"headWords": [
"BYLINE:",
"SECTION:",
"LENGTH:",
"DATELINE:",
"HIGHLIGHT:",
"Email:"
],
"tailWords": [
"LANGUAGE:",
"GRAPHIC:",
"TYPE:",
"URL:",
"LOAD-DATE:",
"PUBLICATION-TYPE:",
"DOCUMENT-TYPE:",
"CHARTS:"
]
},
"settings": {
"encoding": "utf-8",
"monthPosition": 0,
"getNewsPaperName": true,
"nameNotFoundStr": "ND",
"includeTitle": true,
"removeDuplicates": true,
"showSkipped": false,
"showRemovedDuplicates": true,
"maxTitleLen": 32,
"loadTXT": true,
"loadDOCX": false,
"removeOldFiles": true,
"saveSeparateFiles": true,
"saveBodyFile": true,
"saveBodyNumber": true,
"delLF": false,
"delWordBreak": true,
"delChars": [
"'",
"@",
"#",
"$",
"%",
"^",
"&"
]
}
}
}

View File

@@ -0,0 +1,35 @@
'''
Created on 1 dic 2019
@author: Emanuele Trabattoni
'''
import os
from glob import glob
from copy import deepcopy
from libsplit import bananaSPLITTER
from libconfload import bananaCONF
from libfancylogger import fancyLogger
if __name__ == "__main__":
print("CWD-> "+os.getcwd())
logger = fancyLogger(fileLog = False)
confl = bananaCONF(workdir=r"./libbananasplit", logger=logger)
confl.open()
confl.use("testEN.json")
splconf = confl.getParams("splitter")
splist = []
os.chdir(splconf["paths"]["INworkPath"])
for f in glob("*.txt"):
splconf["name"] = f
logger.info("-"*80)
splitter = bananaSPLITTER(fileParams=deepcopy(splconf), logger=logger)
splist.append(splitter)
splitter.start()
splitter.join()
logger.info("\n"+"="*50+"\n\tFINITO!!!\n"+"="*50)