def file_convert_to_txt_if_necessary(Prg, FileOrigAbsPath,
Converted__FileBaseNames__OrigNames):
BaseNameNoExt, ExtensionLow = util.basename_without_extension__ext(
FileOrigAbsPath, ExtensionLower=True)
if ExtensionLow in ExtensionsConvertable:
FilePathConvertedToText = util.filename_without_extension(
FileOrigAbsPath) + ".txt"
Converted__FileBaseNames__OrigNames[BaseNameNoExt] = FileOrigAbsPath
if not os.path.isfile(
FilePathConvertedToText): # convert if it's necessary
if ExtensionLow == ".pdf":
Converter = Prg["ConverterPdfToText"]
if ExtensionLow == ".htm" or ExtensionLow == ".html":
Converter = Prg["ConverterHtmlToText"]
if Converter(Prg, FileOrigAbsPath, FilePathConvertedToText):
info("Successful conversion to txt: " + FileOrigAbsPath)
else:
ConversionErrorMsg = f"Error, file conversion: {FileOrigAbsPath}"
util.log(Prg, ConversionErrorMsg)
info(ConversionErrorMsg)
def extract_all_labels(filenames, out_filepath=DATA_FOLDER+'labels.p', chunk_size=2000):
print "EXTRACTING ALL LABELS INTO {0}".format(out_filepath)
all_labels = []
label_dict = {}
filenames_chunks = util.chunks(filenames, chunk_size)
for i, chunk in enumerate(filenames_chunks):
pool = Pool(processes=util.CPU_COUNT)
chunk_labels = pool.map(extract_labels, chunk)
pool.close()
for filepath, labels in zip(chunk, chunk_labels):
if labels is not None:
file_id = util.filename_without_extension(filepath)
label_dict[file_id] = labels
all_labels += labels
print i+1, '/', len(filenames_chunks)
#Write labels to file
with open(out_filepath,'w') as f:
pickle.dump(label_dict, f)
print '\nLabels:'
print len(set(all_labels))
print Counter(all_labels)
def frog_process_files(files, verbose=True):
seen = []
start_time = time.time()
frogger = frog.Frog(frog.FrogOptions(parser=False,mwu=False,ner=False,morph=False,chunking=False, numThreads=8),'/etc/frog/frog.cfg')
for i, filename in enumerate(files):
with open(filename,'r') as in_file:
output = frogger.process_raw(in_file.read())
if verbose:
print ('> PROCESSING', filename, str(len(seen))+'/'+str(len(files)))
seen.append(filename)
#Timings (estimation of time remaining)
runtime = time.time() - start_time
per_document_time = runtime/len(seen)
remaining_time = (len(files)-len(seen))*per_document_time
total_time = remaining_time+runtime
print ("RUNTIME", duration_to_string(runtime),
"("+duration_to_string(per_document_time)+")",
'REMAINING', duration_to_string(remaining_time),
'TOTAL', duration_to_string(total_time))
frogged_filename = util.filename_without_extension(filename, '.txt')
with open(OUTPUT_FOLDER+frogged_filename+'.frog.out', 'w') as f:
f.write(output)
def extract_all_labels(filenames,
out_filepath=DATA_FOLDER + 'labels.p',
chunk_size=2000):
print "EXTRACTING ALL LABELS INTO {0}".format(out_filepath)
all_labels = []
label_dict = {}
filenames_chunks = util.chunks(filenames, chunk_size)
for i, chunk in enumerate(filenames_chunks):
pool = Pool(processes=util.CPU_COUNT)
chunk_labels = pool.map(extract_labels, chunk)
pool.close()
for filepath, labels in zip(chunk, chunk_labels):
if labels is not None:
file_id = util.filename_without_extension(filepath)
label_dict[file_id] = labels
all_labels += labels
print i + 1, '/', len(filenames_chunks)
#Write labels to file
with open(out_filepath, 'w') as f:
pickle.dump(label_dict, f)
print '\nLabels:'
print len(set(all_labels))
print Counter(all_labels)
def test_util_filename_extension__without_extension(self):
if self._test_exec("test_filename_extension__without_extension"):
Ext = util.filename_extension("file.py")
self.assertEqual(Ext, ".py")
Ext = util.filename_extension("noext")
self.assertEqual(Ext, "")
FnameOnly = util.filename_without_extension("file.py")
self.assertEqual(FnameOnly, "file")
def test_collect_docs_from_working_dir(self):
if self._test_exec("test_collect_docs_from_working_dir"):
Prg = self.Prg
FileName = "test_file_document_example.txt"
FilePath = os.path.join(Prg["DirDocuments"], FileName)
util.file_del(FilePath)
util.file_write(Prg, Fname=FilePath, Content="example text")
DocumentsAvailable = document.document_objects_collect_from_dir_documents(
Prg)
self.assertIn(util.filename_without_extension(FileName),
DocumentsAvailable)
util.file_del(FilePath)
def extract_plaintext(filepath, outpath):
with open(filepath) as fd:
#Filename without extension
file_id = util.filename_without_extension(filepath)
plain_text = []
try:
obj = xmltodict.parse(fd.read())
root = obj['open-rechtspraak']
metadata = root['rdf:RDF']
#############
# Extract content as plain text
#############
if 'inhoudsindicatie' in root:
summary = root['inhoudsindicatie']
as_plain_text(summary, plain_text)
if 'uitspraak' in root:
content = root['uitspraak']
as_plain_text(content, plain_text)
if 'conclusie' in root:
content = root['conclusie']
as_plain_text(content, plain_text)
#print filepath
#Write to outfile
with codecs.open(outpath+file_id+'.txt', 'w', 'utf-8') as f:
for line in plain_text:
print>>f, line
except KeyError, e:
#Skip silently
#print "ERROR:", sys.exc_info()[0]
#print "Skipping faulty:", filepath
#print "file_id:", file_id
return
except:
def extract_plaintext(filepath, outpath):
with open(filepath) as fd:
#Filename without extension
file_id = util.filename_without_extension(filepath)
plain_text = []
try:
obj = xmltodict.parse(fd.read())
root = obj['open-rechtspraak']
metadata = root['rdf:RDF']
#############
# Extract content as plain text
#############
if 'inhoudsindicatie' in root:
summary = root['inhoudsindicatie']
as_plain_text(summary, plain_text)
if 'uitspraak' in root:
content = root['uitspraak']
as_plain_text(content, plain_text)
if 'conclusie' in root:
content = root['conclusie']
as_plain_text(content, plain_text)
#print filepath
#Write to outfile
with codecs.open(outpath + file_id + '.txt', 'w', 'utf-8') as f:
for line in plain_text:
print >> f, line
except KeyError, e:
#Skip silently
#print "ERROR:", sys.exc_info()[0]
#print "Skipping faulty:", filepath
#print "file_id:", file_id
return
except:
def extract_labels(filepath):
with open(filepath) as fd:
#Filename without extension
file_id = util.filename_without_extension(filepath)
try:
obj = xmltodict.parse(fd.read())
root = obj['open-rechtspraak']
metadata = root['rdf:RDF']
#############
# Extract labels
#############
description = metadata['rdf:Description']
if type(description) is list:
description = description[0]
law_areas = description['dcterms:subject']
if type(law_areas) is not list:
law_areas = [law_areas]
text_labels = []
for x in law_areas:
labels = x['#text'].split('; ')
text_labels += labels
return text_labels
except KeyError, e:
#Skip silently
#print "ERROR:", sys.exc_info()[0]
#print "Skipping faulty:", filepath
#print "file_id:", file_id
return
except:
def extract_labels(filepath):
with open(filepath) as fd:
#Filename without extension
file_id = util.filename_without_extension(filepath)
try:
obj = xmltodict.parse(fd.read())
root = obj['open-rechtspraak']
metadata = root['rdf:RDF']
#############
# Extract labels
#############
description = metadata['rdf:Description']
if type(description) is list:
description = description[0]
law_areas = description['dcterms:subject']
if type(law_areas) is not list:
law_areas = [law_areas]
text_labels = []
for x in law_areas:
labels = x['#text'].split('; ')
text_labels += labels
return text_labels
except KeyError, e:
#Skip silently
#print "ERROR:", sys.exc_info()[0]
#print "Skipping faulty:", filepath
#print "file_id:", file_id
return
except:
def filter_and_lemma(chunk_size=2000):
files = glob.glob(INPUT_FOLDER+'*.frog.out')
lemmatized = {}
#Split all files in the list into chunks
file_chunks = util.chunks(files, chunk_size)
for i, chunk in enumerate(tqdm(file_chunks)):
pool = Pool(processes=util.CPU_COUNT)
filtered_lemmatized = pool.map(process, chunk)
pool.close()
for filename, value in zip(chunk, filtered_lemmatized):
file_id = util.filename_without_extension(filename, '.frog.out')
lemmatized[file_id] = value
#Order by key
ordered = OrderedDict(sorted(lemmatized.items()))
with open(DATA_FOLDER+'processed.p','w') as f:
pickle.dump(ordered,f)
print "Done!"
def doc_objects_delete__file_abspath(Prg, FileAbsPathWithExt):
BaseName = os.path.basename(FileAbsPathWithExt)
BaseNameNoExt = util.filename_without_extension(BaseName)
doc_objects_delete__basename(Prg, BaseNameNoExt)
util.file_del(FileAbsPathWithExt
) # del orig file in every case, if DocObj doesn't exis
