Python fileinput.hook_compressed() Examples
The following are 12
code examples of fileinput.hook_compressed().
You can vote up the ones you like or vote down the ones you don't like,
and go to the original project or source file by following the links above each example.
You may also want to check out all available functions/classes of the module
fileinput
, or try the search function
.
Example #1
Source File: indic_norm_tok.py From flores with Creative Commons Attribution Share Alike 4.0 International | 5 votes |
def main(): parser = argparse.ArgumentParser() parser.add_argument("--indic-nlp-path", required=True, help="path to Indic NLP Library root") parser.add_argument("--language", required=True) parser.add_argument("--remove-nuktas", default=False, action="store_true") parser.add_argument("input", help="input file; use - for stdin") args = parser.parse_args() try: sys.path.extend([ args.indic_nlp_path, os.path.join(args.indic_nlp_path, "src"), ]) from indicnlp.tokenize import indic_tokenize from indicnlp.normalize.indic_normalize import IndicNormalizerFactory except: raise Exception( "Cannot load Indic NLP Library, make sure --indic-nlp-path is correct" ) # create normalizer factory = IndicNormalizerFactory() normalizer = factory.get_normalizer( args.language, remove_nuktas=args.remove_nuktas, ) # normalize and tokenize for line in fileinput.input([args.input], openhook=fileinput.hook_compressed): line = normalizer.normalize(line.decode("utf-8")) line = " ".join(indic_tokenize.trivial_tokenize(line, args.language)) sys.stdout.write(line.encode("utf-8"))
Example #2
Source File: detok.py From fairseq with MIT License | 5 votes |
def main(): parser = argparse.ArgumentParser(description='') parser.add_argument('files', nargs='*', help='input files') args = parser.parse_args() detok = sacremoses.MosesDetokenizer() for line in fileinput.input(args.files, openhook=fileinput.hook_compressed): print(detok.detokenize(line.strip().split(' ')).replace(' @', '').replace('@ ', '').replace(' =', '=').replace('= ', '=').replace(' – ', '–'))
Example #3
Source File: test_fileinput.py From Fluid-Designer with GNU General Public License v3.0 | 5 votes |
def test_gz_ext_fake(self): original_open = gzip.open gzip.open = self.fake_open try: result = fileinput.hook_compressed("test.gz", 3) finally: gzip.open = original_open self.assertEqual(self.fake_open.invocation_count, 1) self.assertEqual(self.fake_open.last_invocation, (("test.gz", 3), {}))
Example #4
Source File: test_fileinput.py From Fluid-Designer with GNU General Public License v3.0 | 5 votes |
def test_bz2_ext_fake(self): original_open = bz2.BZ2File bz2.BZ2File = self.fake_open try: result = fileinput.hook_compressed("test.bz2", 4) finally: bz2.BZ2File = original_open self.assertEqual(self.fake_open.invocation_count, 1) self.assertEqual(self.fake_open.last_invocation, (("test.bz2", 4), {}))
Example #5
Source File: test_fileinput.py From Fluid-Designer with GNU General Public License v3.0 | 5 votes |
def do_test_use_builtin_open(self, filename, mode): original_open = self.replace_builtin_open(self.fake_open) try: result = fileinput.hook_compressed(filename, mode) finally: self.replace_builtin_open(original_open) self.assertEqual(self.fake_open.invocation_count, 1) self.assertEqual(self.fake_open.last_invocation, ((filename, mode), {}))
Example #6
Source File: test_fileinput.py From ironpython3 with Apache License 2.0 | 5 votes |
def test_gz_ext_fake(self): original_open = gzip.open gzip.open = self.fake_open try: result = fileinput.hook_compressed("test.gz", 3) finally: gzip.open = original_open self.assertEqual(self.fake_open.invocation_count, 1) self.assertEqual(self.fake_open.last_invocation, (("test.gz", 3), {}))
Example #7
Source File: test_fileinput.py From ironpython3 with Apache License 2.0 | 5 votes |
def test_bz2_ext_fake(self): original_open = bz2.BZ2File bz2.BZ2File = self.fake_open try: result = fileinput.hook_compressed("test.bz2", 4) finally: bz2.BZ2File = original_open self.assertEqual(self.fake_open.invocation_count, 1) self.assertEqual(self.fake_open.last_invocation, (("test.bz2", 4), {}))
Example #8
Source File: test_fileinput.py From ironpython3 with Apache License 2.0 | 5 votes |
def do_test_use_builtin_open(self, filename, mode): original_open = self.replace_builtin_open(self.fake_open) try: result = fileinput.hook_compressed(filename, mode) finally: self.replace_builtin_open(original_open) self.assertEqual(self.fake_open.invocation_count, 1) self.assertEqual(self.fake_open.last_invocation, ((filename, mode), {}))
Example #9
Source File: test_fileinput.py From Project-New-Reign---Nemesis-Main with GNU General Public License v3.0 | 5 votes |
def test_gz_ext_fake(self): original_open = gzip.open gzip.open = self.fake_open try: result = fileinput.hook_compressed("test.gz", 3) finally: gzip.open = original_open self.assertEqual(self.fake_open.invocation_count, 1) self.assertEqual(self.fake_open.last_invocation, (("test.gz", 3), {}))
Example #10
Source File: test_fileinput.py From Project-New-Reign---Nemesis-Main with GNU General Public License v3.0 | 5 votes |
def test_bz2_ext_fake(self): original_open = bz2.BZ2File bz2.BZ2File = self.fake_open try: result = fileinput.hook_compressed("test.bz2", 4) finally: bz2.BZ2File = original_open self.assertEqual(self.fake_open.invocation_count, 1) self.assertEqual(self.fake_open.last_invocation, (("test.bz2", 4), {}))
Example #11
Source File: test_fileinput.py From Project-New-Reign---Nemesis-Main with GNU General Public License v3.0 | 5 votes |
def do_test_use_builtin_open(self, filename, mode): original_open = self.replace_builtin_open(self.fake_open) try: result = fileinput.hook_compressed(filename, mode) finally: self.replace_builtin_open(original_open) self.assertEqual(self.fake_open.invocation_count, 1) self.assertEqual(self.fake_open.last_invocation, ((filename, mode), {}))
Example #12
Source File: gtf.py From seqc with GNU General Public License v2.0 | 5 votes |
def __iter__(self): """return an iterator over all non-header records in gtf""" hook = fileinput.hook_compressed with fileinput.input(self._files, openhook=hook, mode='r') as f: # get rid of header lines file_iterator = iter(f) first_record = next(file_iterator) while first_record.startswith('#'): first_record = next(file_iterator) yield first_record.split('\t') # avoid loss of first non-comment line for record in file_iterator: # now, run to exhaustion yield record.split('\t')