def __cloneFilesSources(self):
SOURCE_URL = FileManager.datasets['source']['url']
TRAINING_URL = FileManager.datasets['training']['url']
TESTING_URL = FileManager.datasets['testing']['url']
# foreach directory in '/Lang' folder ...
languagesExamplesCounter = {}
for languageFolder in [f for f in os.scandir(SOURCE_URL) if f.is_dir()]:
language = str(languageFolder.name).lower()
languagesExamplesCounter[language] = 0
# parse only selected languages
if language in ConfigurationManager.getLanguages():
# preparing empty {languageFolder.name} for each dataset
if not (os.path.isdir(os.path.join(TRAINING_URL, language))):
os.mkdir(os.path.join(TRAINING_URL, language))
if not (os.path.isdir(os.path.join(TESTING_URL, language))):
os.mkdir(os.path.join(TESTING_URL, language))
# count example foreach language
for exampleFolder in FileManager.getExamplesFolders(languageFolder.path):
for _ in FileManager.getExampleFiles(exampleFolder.path):
languagesExamplesCounter[language] += 1
# print languages with examples counter less than {TRAINING_EXAMPLES_NUMBER}
if languagesExamplesCounter[language] < TRAINING_EXAMPLES_NUMBER:
print(' > [dataset] the total number of examples for the '
+ language + ' is less than ' + str(TRAINING_EXAMPLES_NUMBER))
continue
# for this language, the total examples number could be less than {TRAINING_EXAMPLES_NUMBER}
indexesOfTrainingExamples = random.sample(
range(1, languagesExamplesCounter[language]),
TRAINING_EXAMPLES_NUMBER
)
# list all examples in {languageFolder.name} folder
exampleIndex = 0
for exampleFolder in FileManager.getExamplesFolders(languageFolder.path):
# list all examples versions in {exampleFolder.name} folder
for exampleVersionFile in FileManager.getExampleFiles(exampleFolder.path):
exampleIndex += 1
# move file to right dataset
if exampleIndex in indexesOfTrainingExamples:
DATASET_TYPE = TRAINING_URL
else:
DATASET_TYPE = TESTING_URL
# prepare destination folder
example = str(exampleVersionFile.name).lower()
exampleFolderUri = os.path.join(DATASET_TYPE, language, example)
os.mkdir(exampleFolderUri)
# copy the ORIGINAL source file content
originalFileUri = FileManager.getOriginalFileUrl(exampleFolderUri)
FileManager.createFile(originalFileUri)
shutil.copyfile(exampleVersionFile.path, originalFileUri)
# create the 'PARSED' version of the orginal file
parsedFileUri = FileManager.getParsedFileUrl(exampleFolderUri)
FileManager.createFile(parsedFileUri)
parser = Parser()
parser.initialize(originalFileUri, parsedFileUri)
parser.parse()
return self
