def process_corpus(self, cutMedia=True):
"""
Take every eaf file from the source directory subtree, turn it
into a parsed json and store it in the target directory.
"""
Txt2JSON.process_corpus(self)
if not cutMedia:
return
mediaDir = os.path.join(self.corpusSettings['corpus_dir'], self.srcExt)
if 'media_dir' in self.corpusSettings:
mediaDir = self.corpusSettings['media_dir']
for path, dirs, files in os.walk(mediaDir):
# Process video files first
files = [fname for fname in files if fname.lower().endswith(('.avi', '.mts', '.mov'))] + \
[fname for fname in files if fname.lower().endswith('.mp4')] + \
[fname for fname in files if not fname.lower().endswith(('.avi', '.mts', '.mov', '.mp4'))]
for fname in files:
fileExt = os.path.splitext(fname.lower())[1]
if fileExt in self.mediaExtensions:
privacySegments = []
if fname in self.privacySegments:
privacySegments = self.privacySegments[fname]
fname = os.path.abspath(os.path.join(path, fname))
print('Cutting media file', fname)
self.mc.cut_media(fname,
usedFilenames=self.usedMediaFiles,
privacySegments=privacySegments)
def process_corpus(self, cutMedia=False):
"""
Take every eaf file from the source directory subtree, turn it
into a parsed json and store it in the target directory.
"""
Txt2JSON.process_corpus(self)
if not cutMedia:
return
for path, dirs, files in os.walk(os.path.join('..', self.srcExt)):
for fname in files:
fileExt = os.path.splitext(fname.lower())[1]
if fileExt in self.mediaExtensions:
fname = os.path.abspath(os.path.join(path, fname))
print('Cutting media file', fname)
self.mc.cut_media(fname)
def process_corpus(self):
"""
Take every Exmaralda file from the source directory subtree, turn it
into a parsed json and store it in the target directory.
Split all the corpus media files into overlapping chunks of
small duration.
This is the main function of the class.
"""
Txt2JSON.process_corpus(self)
for path, dirs, files in os.walk(
os.path.join(self.corpusSettings['corpus_dir'], self.srcExt)):
for fname in files:
fileExt = os.path.splitext(fname.lower())[1]
if fileExt in self.mediaExtensions:
fname = os.path.abspath(os.path.join(path, fname))
print('Cutting media file', fname)
self.mc.cut_media(fname)
def process_corpus(self, cutMedia=True, filenames = None, isToProcessCorpus = True):
"""
Take every eaf file from the source directory subtree, turn it
into a parsed json and store it in the target directory.
"""
if isToProcessCorpus:
Txt2JSON.process_corpus(self)
if not cutMedia:
return
print(os.path.join(self.corpusSettings['corpus_dir'],
self.srcExt))
for path, dirs, files in os.walk(os.path.join(self.corpusSettings['corpus_dir'],
self.srcExt)):
for fname in files:
if filenames and fname not in filenames:
continue
print('!!!!')
fileExt = os.path.splitext(fname.lower())[1]
if fileExt in self.mediaExtensions:
fname = os.path.abspath(os.path.join(path, fname))
print('Cutting media file', fname)
self.mc.cut_media(fname)
