mirror of
https://github.com/davidhalter/parso.git
synced 2025-12-07 21:34:32 +08:00
source_to_unicode -> python_bytes_to_unicode.
This commit is contained in:
@@ -3,7 +3,7 @@ import os
|
|||||||
|
|
||||||
from parso._compatibility import FileNotFoundError, is_pypy
|
from parso._compatibility import FileNotFoundError, is_pypy
|
||||||
from parso.pgen2.pgen import generate_grammar
|
from parso.pgen2.pgen import generate_grammar
|
||||||
from parso.utils import split_lines, source_to_unicode, parse_version_string
|
from parso.utils import split_lines, python_bytes_to_unicode, parse_version_string
|
||||||
from parso.python.diff import DiffParser
|
from parso.python.diff import DiffParser
|
||||||
from parso.python.tokenize import tokenize_lines, tokenize
|
from parso.python.tokenize import tokenize_lines, tokenize
|
||||||
from parso.cache import parser_cache, load_module, save_module
|
from parso.cache import parser_cache, load_module, save_module
|
||||||
@@ -86,7 +86,7 @@ class Grammar(object):
|
|||||||
with open(path, 'rb') as f:
|
with open(path, 'rb') as f:
|
||||||
code = f.read()
|
code = f.read()
|
||||||
|
|
||||||
code = source_to_unicode(code)
|
code = python_bytes_to_unicode(code)
|
||||||
|
|
||||||
lines = split_lines(code, keepends=True)
|
lines = split_lines(code, keepends=True)
|
||||||
if diff_cache:
|
if diff_cache:
|
||||||
|
|||||||
@@ -406,10 +406,10 @@ if __name__ == "__main__":
|
|||||||
else:
|
else:
|
||||||
code = sys.stdin.read()
|
code = sys.stdin.read()
|
||||||
|
|
||||||
from parso.utils import source_to_unicode, parse_version_string
|
from parso.utils import python_bytes_to_unicode, parse_version_string
|
||||||
|
|
||||||
if isinstance(code, bytes):
|
if isinstance(code, bytes):
|
||||||
code = source_to_unicode(code)
|
code = python_bytes_to_unicode(code)
|
||||||
|
|
||||||
for token in tokenize(code, parse_version_string()):
|
for token in tokenize(code, parse_version_string()):
|
||||||
print(token)
|
print(token)
|
||||||
|
|||||||
@@ -48,7 +48,7 @@ def split_lines(string, keepends=False):
|
|||||||
return re.split('\n|\r\n', string)
|
return re.split('\n|\r\n', string)
|
||||||
|
|
||||||
|
|
||||||
def source_to_unicode(source, default_encoding='utf-8', errors='strict'):
|
def python_bytes_to_unicode(source, default_encoding='utf-8', errors='strict'):
|
||||||
"""
|
"""
|
||||||
`errors` can be 'strict', 'replace' or 'ignore'.
|
`errors` can be 'strict', 'replace' or 'ignore'.
|
||||||
"""
|
"""
|
||||||
|
|||||||
@@ -8,7 +8,7 @@ import re
|
|||||||
|
|
||||||
import parso
|
import parso
|
||||||
from parso._compatibility import total_ordering
|
from parso._compatibility import total_ordering
|
||||||
from parso.utils import source_to_unicode
|
from parso.utils import python_bytes_to_unicode
|
||||||
|
|
||||||
|
|
||||||
@total_ordering
|
@total_ordering
|
||||||
@@ -54,7 +54,7 @@ def test_normalizer_issue(normalizer_issue_case):
|
|||||||
for i in issues]
|
for i in issues]
|
||||||
|
|
||||||
with open(normalizer_issue_case.path, 'rb') as f:
|
with open(normalizer_issue_case.path, 'rb') as f:
|
||||||
code = source_to_unicode(f.read())
|
code = python_bytes_to_unicode(f.read())
|
||||||
|
|
||||||
desired = sort(collect_errors(code))
|
desired = sort(collect_errors(code))
|
||||||
|
|
||||||
|
|||||||
@@ -1,6 +1,6 @@
|
|||||||
from codecs import BOM_UTF8
|
from codecs import BOM_UTF8
|
||||||
|
|
||||||
from parso.utils import split_lines, source_to_unicode
|
from parso.utils import split_lines, python_bytes_to_unicode
|
||||||
import parso
|
import parso
|
||||||
|
|
||||||
|
|
||||||
@@ -20,12 +20,12 @@ def test_split_lines_keepends():
|
|||||||
assert split_lines('\n', keepends=True) == ['\n', '']
|
assert split_lines('\n', keepends=True) == ['\n', '']
|
||||||
|
|
||||||
|
|
||||||
def test_source_to_unicode_unicode_text():
|
def test_python_bytes_to_unicode_unicode_text():
|
||||||
source = (
|
source = (
|
||||||
b"# vim: fileencoding=utf-8\n"
|
b"# vim: fileencoding=utf-8\n"
|
||||||
b"# \xe3\x81\x82\xe3\x81\x84\xe3\x81\x86\xe3\x81\x88\xe3\x81\x8a\n"
|
b"# \xe3\x81\x82\xe3\x81\x84\xe3\x81\x86\xe3\x81\x88\xe3\x81\x8a\n"
|
||||||
)
|
)
|
||||||
actual = source_to_unicode(source)
|
actual = python_bytes_to_unicode(source)
|
||||||
expected = source.decode('utf-8')
|
expected = source.decode('utf-8')
|
||||||
assert actual == expected
|
assert actual == expected
|
||||||
|
|
||||||
|
|||||||
Reference in New Issue
Block a user