mirror of
https://github.com/django/django.git
synced 2024-12-22 09:05:43 +00:00
Dropped safeguards against very old versions of gettext.
gettext 0.19 was released in 2014.
This commit is contained in:
Claude Paroz
parent
2ff00251f9
commit
2c1f27d0d0
@ -79,8 +79,8 @@ class Command(BaseCommand):
|
||||
|
||||
if find_command(self.program) is None:
|
||||
raise CommandError(
|
||||
"Can't find %s. Make sure you have GNU gettext "
|
||||
"tools 0.15 or newer installed." % self.program
|
||||
f"Can't find {self.program}. Make sure you have GNU gettext "
|
||||
"tools 0.19 or newer installed."
|
||||
)
|
||||
|
||||
basedirs = [os.path.join("conf", "locale"), "locale"]
|
||||
|
||||
@ -19,7 +19,6 @@ from django.core.management.utils import (
|
||||
)
|
||||
from django.utils.encoding import DEFAULT_LOCALE_ENCODING
|
||||
from django.utils.functional import cached_property
|
||||
from django.utils.jslex import prepare_js_for_gettext
|
||||
from django.utils.regex_helper import _lazy_re_compile
|
||||
from django.utils.text import get_text_list
|
||||
from django.utils.translation import templatize
|
||||
@ -35,8 +34,8 @@ def check_programs(*programs):
|
||||
for program in programs:
|
||||
if find_command(program) is None:
|
||||
raise CommandError(
|
||||
"Can't find %s. Make sure you have GNU gettext tools 0.15 or "
|
||||
"newer installed." % program
|
||||
f"Can't find {program}. Make sure you have GNU gettext tools "
|
||||
"0.19 or newer installed."
|
||||
)
|
||||
|
||||
|
||||
@ -80,9 +79,7 @@ class BuildFile:
|
||||
|
||||
@cached_property
|
||||
def is_templatized(self):
|
||||
if self.domain == "djangojs":
|
||||
return self.command.gettext_version < (0, 18, 3)
|
||||
elif self.domain == "django":
|
||||
if self.domain == "django":
|
||||
file_ext = os.path.splitext(self.translatable.file)[1]
|
||||
return file_ext != ".py"
|
||||
return False
|
||||
@ -99,11 +96,7 @@ class BuildFile:
|
||||
"""
|
||||
if not self.is_templatized:
|
||||
return self.path
|
||||
extension = {
|
||||
"djangojs": "c",
|
||||
"django": "py",
|
||||
}.get(self.domain)
|
||||
filename = "%s.%s" % (self.translatable.file, extension)
|
||||
filename = f"{self.translatable.file}.py"
|
||||
return os.path.join(self.translatable.dirpath, filename)
|
||||
|
||||
def preprocess(self):
|
||||
@ -117,9 +110,7 @@ class BuildFile:
|
||||
with open(self.path, encoding="utf-8") as fp:
|
||||
src_data = fp.read()
|
||||
|
||||
if self.domain == "djangojs":
|
||||
content = prepare_js_for_gettext(src_data)
|
||||
elif self.domain == "django":
|
||||
if self.domain == "django":
|
||||
content = templatize(src_data, origin=self.path[2:])
|
||||
|
||||
with open(self.work_path, "w", encoding="utf-8") as fp:
|
||||
@ -349,11 +340,6 @@ class Command(BaseCommand):
|
||||
self.msgattrib_options = self.msgattrib_options[:] + ["--no-location"]
|
||||
self.xgettext_options = self.xgettext_options[:] + ["--no-location"]
|
||||
if options["add_location"]:
|
||||
if self.gettext_version < (0, 19):
|
||||
raise CommandError(
|
||||
"The --add-location option requires gettext 0.19 or later. "
|
||||
"You have %s." % ".".join(str(x) for x in self.gettext_version)
|
||||
)
|
||||
arg_add_location = "--add-location=%s" % options["add_location"]
|
||||
self.msgmerge_options = self.msgmerge_options[:] + [arg_add_location]
|
||||
self.msguniq_options = self.msguniq_options[:] + [arg_add_location]
|
||||
@ -636,12 +622,11 @@ class Command(BaseCommand):
|
||||
build_files.append(build_file)
|
||||
|
||||
if self.domain == "djangojs":
|
||||
is_templatized = build_file.is_templatized
|
||||
args = [
|
||||
"xgettext",
|
||||
"-d",
|
||||
self.domain,
|
||||
"--language=%s" % ("C" if is_templatized else "JavaScript",),
|
||||
"--language=JavaScript",
|
||||
"--keyword=gettext_noop",
|
||||
"--keyword=gettext_lazy",
|
||||
"--keyword=ngettext_lazy:1,2",
|
||||
|
||||
@ -1,250 +0,0 @@
|
||||
"""JsLex: a lexer for JavaScript"""
|
||||
|
||||
# Originally from https://bitbucket.org/ned/jslex
|
||||
import re
|
||||
|
||||
|
||||
class Tok:
|
||||
"""
|
||||
A specification for a token class.
|
||||
"""
|
||||
|
||||
num = 0
|
||||
|
||||
def __init__(self, name, regex, next=None):
|
||||
self.id = Tok.num
|
||||
Tok.num += 1
|
||||
self.name = name
|
||||
self.regex = regex
|
||||
self.next = next
|
||||
|
||||
|
||||
def literals(choices, prefix="", suffix=""):
|
||||
"""
|
||||
Create a regex from a space-separated list of literal `choices`.
|
||||
|
||||
If provided, `prefix` and `suffix` will be attached to each choice
|
||||
individually.
|
||||
"""
|
||||
return "|".join(prefix + re.escape(c) + suffix for c in choices.split())
|
||||
|
||||
|
||||
class Lexer:
|
||||
"""
|
||||
A generic multi-state regex-based lexer.
|
||||
"""
|
||||
|
||||
def __init__(self, states, first):
|
||||
self.regexes = {}
|
||||
self.toks = {}
|
||||
|
||||
for state, rules in states.items():
|
||||
parts = []
|
||||
for tok in rules:
|
||||
groupid = "t%d" % tok.id
|
||||
self.toks[groupid] = tok
|
||||
parts.append("(?P<%s>%s)" % (groupid, tok.regex))
|
||||
self.regexes[state] = re.compile("|".join(parts), re.MULTILINE | re.VERBOSE)
|
||||
|
||||
self.state = first
|
||||
|
||||
def lex(self, text):
|
||||
"""
|
||||
Lexically analyze `text`.
|
||||
|
||||
Yield pairs (`name`, `tokentext`).
|
||||
"""
|
||||
end = len(text)
|
||||
state = self.state
|
||||
regexes = self.regexes
|
||||
toks = self.toks
|
||||
start = 0
|
||||
|
||||
while start < end:
|
||||
for match in regexes[state].finditer(text, start):
|
||||
name = match.lastgroup
|
||||
tok = toks[name]
|
||||
toktext = match[name]
|
||||
start += len(toktext)
|
||||
yield (tok.name, toktext)
|
||||
|
||||
if tok.next:
|
||||
state = tok.next
|
||||
break
|
||||
|
||||
self.state = state
|
||||
|
||||
|
||||
class JsLexer(Lexer):
|
||||
"""
|
||||
A JavaScript lexer
|
||||
|
||||
>>> lexer = JsLexer()
|
||||
>>> list(lexer.lex("a = 1"))
|
||||
[('id', 'a'), ('ws', ' '), ('punct', '='), ('ws', ' '), ('dnum', '1')]
|
||||
|
||||
This doesn't properly handle non-ASCII characters in the JavaScript source.
|
||||
"""
|
||||
|
||||
# Because these tokens are matched as alternatives in a regex, longer
|
||||
# possibilities must appear in the list before shorter ones, for example,
|
||||
# '>>' before '>'.
|
||||
#
|
||||
# Note that we don't have to detect malformed JavaScript, only properly
|
||||
# lex correct JavaScript, so much of this is simplified.
|
||||
|
||||
# Details of JavaScript lexical structure are taken from
|
||||
# https://www.ecma-international.org/publications-and-standards/standards/ecma-262/
|
||||
|
||||
# A useful explanation of automatic semicolon insertion is at
|
||||
# http://inimino.org/~inimino/blog/javascript_semicolons
|
||||
|
||||
both_before = [
|
||||
Tok("comment", r"/\*(.|\n)*?\*/"),
|
||||
Tok("linecomment", r"//.*?$"),
|
||||
Tok("ws", r"\s+"),
|
||||
Tok(
|
||||
"keyword",
|
||||
literals(
|
||||
"""
|
||||
break case catch class const continue debugger
|
||||
default delete do else enum export extends
|
||||
finally for function if import in instanceof
|
||||
new return super switch this throw try typeof
|
||||
var void while with
|
||||
""",
|
||||
suffix=r"\b",
|
||||
),
|
||||
next="reg",
|
||||
),
|
||||
Tok("reserved", literals("null true false", suffix=r"\b"), next="div"),
|
||||
Tok(
|
||||
"id",
|
||||
r"""
|
||||
([a-zA-Z_$ ]|\\u[0-9a-fA-Z]{4}) # first char
|
||||
([a-zA-Z_$0-9]|\\u[0-9a-fA-F]{4})* # rest chars
|
||||
""",
|
||||
next="div",
|
||||
),
|
||||
Tok("hnum", r"0[xX][0-9a-fA-F]+", next="div"),
|
||||
Tok("onum", r"0[0-7]+"),
|
||||
Tok(
|
||||
"dnum",
|
||||
r"""
|
||||
( (0|[1-9][0-9]*) # DecimalIntegerLiteral
|
||||
\. # dot
|
||||
[0-9]* # DecimalDigits-opt
|
||||
([eE][-+]?[0-9]+)? # ExponentPart-opt
|
||||
|
|
||||
\. # dot
|
||||
[0-9]+ # DecimalDigits
|
||||
([eE][-+]?[0-9]+)? # ExponentPart-opt
|
||||
|
|
||||
(0|[1-9][0-9]*) # DecimalIntegerLiteral
|
||||
([eE][-+]?[0-9]+)? # ExponentPart-opt
|
||||
)
|
||||
""",
|
||||
next="div",
|
||||
),
|
||||
Tok(
|
||||
"punct",
|
||||
literals(
|
||||
"""
|
||||
>>>= === !== >>> <<= >>= <= >= == != << >> &&
|
||||
|| += -= *= %= &= |= ^=
|
||||
"""
|
||||
),
|
||||
next="reg",
|
||||
),
|
||||
Tok("punct", literals("++ -- ) ]"), next="div"),
|
||||
Tok("punct", literals("{ } ( [ . ; , < > + - * % & | ^ ! ~ ? : ="), next="reg"),
|
||||
Tok("string", r'"([^"\\]|(\\(.|\n)))*?"', next="div"),
|
||||
Tok("string", r"'([^'\\]|(\\(.|\n)))*?'", next="div"),
|
||||
]
|
||||
|
||||
both_after = [
|
||||
Tok("other", r"."),
|
||||
]
|
||||
|
||||
states = {
|
||||
# slash will mean division
|
||||
"div": both_before
|
||||
+ [
|
||||
Tok("punct", literals("/= /"), next="reg"),
|
||||
]
|
||||
+ both_after,
|
||||
# slash will mean regex
|
||||
"reg": both_before
|
||||
+ [
|
||||
Tok(
|
||||
"regex",
|
||||
r"""
|
||||
/ # opening slash
|
||||
# First character is..
|
||||
( [^*\\/[] # anything but * \ / or [
|
||||
| \\. # or an escape sequence
|
||||
| \[ # or a class, which has
|
||||
( [^\]\\] # anything but \ or ]
|
||||
| \\. # or an escape sequence
|
||||
)* # many times
|
||||
\]
|
||||
)
|
||||
# Following characters are same, except for excluding a star
|
||||
( [^\\/[] # anything but \ / or [
|
||||
| \\. # or an escape sequence
|
||||
| \[ # or a class, which has
|
||||
( [^\]\\] # anything but \ or ]
|
||||
| \\. # or an escape sequence
|
||||
)* # many times
|
||||
\]
|
||||
)* # many times
|
||||
/ # closing slash
|
||||
[a-zA-Z0-9]* # trailing flags
|
||||
""",
|
||||
next="div",
|
||||
),
|
||||
]
|
||||
+ both_after,
|
||||
}
|
||||
|
||||
def __init__(self):
|
||||
super().__init__(self.states, "reg")
|
||||
|
||||
|
||||
def prepare_js_for_gettext(js):
|
||||
"""
|
||||
Convert the JavaScript source `js` into something resembling C for
|
||||
xgettext.
|
||||
|
||||
What actually happens is that all the regex literals are replaced with
|
||||
"REGEX".
|
||||
"""
|
||||
|
||||
def escape_quotes(m):
|
||||
"""Used in a regex to properly escape double quotes."""
|
||||
s = m[0]
|
||||
if s == '"':
|
||||
return r"\""
|
||||
else:
|
||||
return s
|
||||
|
||||
lexer = JsLexer()
|
||||
c = []
|
||||
for name, tok in lexer.lex(js):
|
||||
if name == "regex":
|
||||
# C doesn't grok regexes, and they aren't needed for gettext,
|
||||
# so just output a string instead.
|
||||
tok = '"REGEX"'
|
||||
elif name == "string":
|
||||
# C doesn't have single-quoted strings, so make all strings
|
||||
# double-quoted.
|
||||
if tok.startswith("'"):
|
||||
guts = re.sub(r"\\.|.", escape_quotes, tok[1:-1])
|
||||
tok = '"' + guts + '"'
|
||||
elif name == "id":
|
||||
# C can't deal with Unicode escapes in identifiers. We don't
|
||||
# need them for gettext anyway, so replace them with something
|
||||
# innocuous
|
||||
tok = tok.replace("\\", "U")
|
||||
c.append(tok)
|
||||
return "".join(c)
|
||||
@ -306,6 +306,8 @@ Miscellaneous
|
||||
* Adding :attr:`.EmailMultiAlternatives.alternatives` is now only supported via
|
||||
the :meth:`~.EmailMultiAlternatives.attach_alternative` method.
|
||||
|
||||
* The minimum supported version of ``gettext`` is increased from 0.15 to 0.19.
|
||||
|
||||
.. _deprecated-features-5.2:
|
||||
|
||||
Features deprecated in 5.2
|
||||
|
||||
@ -1551,7 +1551,7 @@ Django comes with a tool, :djadmin:`django-admin makemessages
|
||||
commands from the GNU gettext toolset: ``xgettext``, ``msgfmt``,
|
||||
``msgmerge`` and ``msguniq``.
|
||||
|
||||
The minimum version of the ``gettext`` utilities supported is 0.15.
|
||||
The minimum version of the ``gettext`` utilities supported is 0.19.
|
||||
|
||||
To create or update a message file, run this command:
|
||||
|
||||
|
||||
@ -8,7 +8,6 @@ from subprocess import run
|
||||
from unittest import mock
|
||||
|
||||
from django.core.management import CommandError, call_command, execute_from_command_line
|
||||
from django.core.management.commands.makemessages import Command as MakeMessagesCommand
|
||||
from django.core.management.utils import find_command
|
||||
from django.test import SimpleTestCase, override_settings
|
||||
from django.test.utils import captured_stderr, captured_stdout
|
||||
@ -269,9 +268,6 @@ class CompilationErrorHandling(MessageCompilationTests):
|
||||
"django.core.management.utils.run",
|
||||
lambda *args, **kwargs: run(*args, env=env, **kwargs),
|
||||
):
|
||||
cmd = MakeMessagesCommand()
|
||||
if cmd.gettext_version < (0, 18, 3):
|
||||
self.skipTest("python-brace-format is a recent gettext addition.")
|
||||
stderr = StringIO()
|
||||
with self.assertRaisesMessage(
|
||||
CommandError, "compilemessages generated one or more errors"
|
||||
|
||||
@ -6,7 +6,7 @@ import time
|
||||
import warnings
|
||||
from io import StringIO
|
||||
from pathlib import Path
|
||||
from unittest import mock, skipIf, skipUnless
|
||||
from unittest import mock, skipUnless
|
||||
|
||||
from admin_scripts.tests import AdminScriptTestCase
|
||||
|
||||
@ -25,10 +25,6 @@ from .utils import POFileAssertionMixin, RunInTmpDirMixin, copytree
|
||||
|
||||
LOCALE = "de"
|
||||
has_xgettext = find_command("xgettext")
|
||||
gettext_version = MakeMessagesCommand().gettext_version if has_xgettext else None
|
||||
requires_gettext_019 = skipIf(
|
||||
has_xgettext and gettext_version < (0, 19), "gettext 0.19 required"
|
||||
)
|
||||
|
||||
|
||||
@skipUnless(has_xgettext, "xgettext is mandatory for extraction tests")
|
||||
@ -836,7 +832,6 @@ class LocationCommentsTests(ExtractorTests):
|
||||
self.assertLocationCommentNotPresent(self.PO_FILE, None, ".html.py")
|
||||
self.assertLocationCommentPresent(self.PO_FILE, 5, "templates", "test.html")
|
||||
|
||||
@requires_gettext_019
|
||||
def test_add_location_full(self):
|
||||
"""makemessages --add-location=full"""
|
||||
management.call_command(
|
||||
@ -848,7 +843,6 @@ class LocationCommentsTests(ExtractorTests):
|
||||
self.PO_FILE, "Translatable literal #6b", "templates", "test.html"
|
||||
)
|
||||
|
||||
@requires_gettext_019
|
||||
def test_add_location_file(self):
|
||||
"""makemessages --add-location=file"""
|
||||
management.call_command(
|
||||
@ -862,7 +856,6 @@ class LocationCommentsTests(ExtractorTests):
|
||||
self.PO_FILE, "Translatable literal #6b", "templates", "test.html"
|
||||
)
|
||||
|
||||
@requires_gettext_019
|
||||
def test_add_location_never(self):
|
||||
"""makemessages --add-location=never"""
|
||||
management.call_command(
|
||||
@ -871,24 +864,6 @@ class LocationCommentsTests(ExtractorTests):
|
||||
self.assertTrue(os.path.exists(self.PO_FILE))
|
||||
self.assertLocationCommentNotPresent(self.PO_FILE, None, "test.html")
|
||||
|
||||
@mock.patch(
|
||||
"django.core.management.commands.makemessages.Command.gettext_version",
|
||||
new=(0, 18, 99),
|
||||
)
|
||||
def test_add_location_gettext_version_check(self):
|
||||
"""
|
||||
CommandError is raised when using makemessages --add-location with
|
||||
gettext < 0.19.
|
||||
"""
|
||||
msg = (
|
||||
"The --add-location option requires gettext 0.19 or later. You have "
|
||||
"0.18.99."
|
||||
)
|
||||
with self.assertRaisesMessage(CommandError, msg):
|
||||
management.call_command(
|
||||
"makemessages", locale=[LOCALE], verbosity=0, add_location="full"
|
||||
)
|
||||
|
||||
|
||||
class NoObsoleteExtractorTests(ExtractorTests):
|
||||
work_subdir = "obsolete_translations"
|
||||
|
||||
@ -1,401 +0,0 @@
|
||||
"""Tests for jslex."""
|
||||
|
||||
# originally from https://bitbucket.org/ned/jslex
|
||||
|
||||
from django.test import SimpleTestCase
|
||||
from django.utils.jslex import JsLexer, prepare_js_for_gettext
|
||||
|
||||
|
||||
class JsTokensTest(SimpleTestCase):
|
||||
LEX_CASES = [
|
||||
# ids
|
||||
("a ABC $ _ a123", ["id a", "id ABC", "id $", "id _", "id a123"]),
|
||||
(
|
||||
"\\u1234 abc\\u0020 \\u0065_\\u0067",
|
||||
["id \\u1234", "id abc\\u0020", "id \\u0065_\\u0067"],
|
||||
),
|
||||
# numbers
|
||||
(
|
||||
"123 1.234 0.123e-3 0 1E+40 1e1 .123",
|
||||
[
|
||||
"dnum 123",
|
||||
"dnum 1.234",
|
||||
"dnum 0.123e-3",
|
||||
"dnum 0",
|
||||
"dnum 1E+40",
|
||||
"dnum 1e1",
|
||||
"dnum .123",
|
||||
],
|
||||
),
|
||||
("0x1 0xabCD 0XABcd", ["hnum 0x1", "hnum 0xabCD", "hnum 0XABcd"]),
|
||||
("010 0377 090", ["onum 010", "onum 0377", "dnum 0", "dnum 90"]),
|
||||
("0xa123ghi", ["hnum 0xa123", "id ghi"]),
|
||||
# keywords
|
||||
(
|
||||
"function Function FUNCTION",
|
||||
["keyword function", "id Function", "id FUNCTION"],
|
||||
),
|
||||
(
|
||||
"const constructor in inherits",
|
||||
["keyword const", "id constructor", "keyword in", "id inherits"],
|
||||
),
|
||||
("true true_enough", ["reserved true", "id true_enough"]),
|
||||
# strings
|
||||
(""" 'hello' "hello" """, ["string 'hello'", 'string "hello"']),
|
||||
(
|
||||
r""" 'don\'t' "don\"t" '"' "'" '\'' "\"" """,
|
||||
[
|
||||
r"""string 'don\'t'""",
|
||||
r'''string "don\"t"''',
|
||||
r"""string '"'""",
|
||||
r'''string "'"''',
|
||||
r"""string '\''""",
|
||||
r'''string "\""''',
|
||||
],
|
||||
),
|
||||
(r'"ƃuıxǝ⅂ ʇdıɹɔsɐʌɐſ\""', [r'string "ƃuıxǝ⅂ ʇdıɹɔsɐʌɐſ\""']),
|
||||
# comments
|
||||
("a//b", ["id a", "linecomment //b"]),
|
||||
(
|
||||
"/****/a/=2//hello",
|
||||
["comment /****/", "id a", "punct /=", "dnum 2", "linecomment //hello"],
|
||||
),
|
||||
(
|
||||
"/*\n * Header\n */\na=1;",
|
||||
["comment /*\n * Header\n */", "id a", "punct =", "dnum 1", "punct ;"],
|
||||
),
|
||||
# punctuation
|
||||
("a+++b", ["id a", "punct ++", "punct +", "id b"]),
|
||||
# regex
|
||||
(r"a=/a*/,1", ["id a", "punct =", "regex /a*/", "punct ,", "dnum 1"]),
|
||||
(r"a=/a*[^/]+/,1", ["id a", "punct =", "regex /a*[^/]+/", "punct ,", "dnum 1"]),
|
||||
(r"a=/a*\[^/,1", ["id a", "punct =", r"regex /a*\[^/", "punct ,", "dnum 1"]),
|
||||
(r"a=/\//,1", ["id a", "punct =", r"regex /\//", "punct ,", "dnum 1"]),
|
||||
# next two are from https://www-archive.mozilla.org/js/language/js20-2002-04/rationale/syntax.html#regular-expressions # NOQA
|
||||
(
|
||||
'for (var x = a in foo && "</x>" || mot ? z:/x:3;x<5;y</g/i) {xyz(x++);}',
|
||||
[
|
||||
"keyword for",
|
||||
"punct (",
|
||||
"keyword var",
|
||||
"id x",
|
||||
"punct =",
|
||||
"id a",
|
||||
"keyword in",
|
||||
"id foo",
|
||||
"punct &&",
|
||||
'string "</x>"',
|
||||
"punct ||",
|
||||
"id mot",
|
||||
"punct ?",
|
||||
"id z",
|
||||
"punct :",
|
||||
"regex /x:3;x<5;y</g",
|
||||
"punct /",
|
||||
"id i",
|
||||
"punct )",
|
||||
"punct {",
|
||||
"id xyz",
|
||||
"punct (",
|
||||
"id x",
|
||||
"punct ++",
|
||||
"punct )",
|
||||
"punct ;",
|
||||
"punct }",
|
||||
],
|
||||
),
|
||||
(
|
||||
'for (var x = a in foo && "</x>" || mot ? z/x:3;x<5;y</g/i) {xyz(x++);}',
|
||||
[
|
||||
"keyword for",
|
||||
"punct (",
|
||||
"keyword var",
|
||||
"id x",
|
||||
"punct =",
|
||||
"id a",
|
||||
"keyword in",
|
||||
"id foo",
|
||||
"punct &&",
|
||||
'string "</x>"',
|
||||
"punct ||",
|
||||
"id mot",
|
||||
"punct ?",
|
||||
"id z",
|
||||
"punct /",
|
||||
"id x",
|
||||
"punct :",
|
||||
"dnum 3",
|
||||
"punct ;",
|
||||
"id x",
|
||||
"punct <",
|
||||
"dnum 5",
|
||||
"punct ;",
|
||||
"id y",
|
||||
"punct <",
|
||||
"regex /g/i",
|
||||
"punct )",
|
||||
"punct {",
|
||||
"id xyz",
|
||||
"punct (",
|
||||
"id x",
|
||||
"punct ++",
|
||||
"punct )",
|
||||
"punct ;",
|
||||
"punct }",
|
||||
],
|
||||
),
|
||||
# Various "illegal" regexes that are valid according to the std.
|
||||
(
|
||||
r"""/????/, /++++/, /[----]/ """,
|
||||
["regex /????/", "punct ,", "regex /++++/", "punct ,", "regex /[----]/"],
|
||||
),
|
||||
# Stress cases from https://stackoverflow.com/questions/5533925/what-javascript-constructs-does-jslex-incorrectly-lex/5573409#5573409 # NOQA
|
||||
(r"""/\[/""", [r"""regex /\[/"""]),
|
||||
(r"""/[i]/""", [r"""regex /[i]/"""]),
|
||||
(r"""/[\]]/""", [r"""regex /[\]]/"""]),
|
||||
(r"""/a[\]]/""", [r"""regex /a[\]]/"""]),
|
||||
(r"""/a[\]]b/""", [r"""regex /a[\]]b/"""]),
|
||||
(r"""/[\]/]/gi""", [r"""regex /[\]/]/gi"""]),
|
||||
(r"""/\[[^\]]+\]/gi""", [r"""regex /\[[^\]]+\]/gi"""]),
|
||||
(
|
||||
r"""
|
||||
rexl.re = {
|
||||
NAME: /^(?![0-9])(?:\w)+|^"(?:[^"]|"")+"/,
|
||||
UNQUOTED_LITERAL: /^@(?:(?![0-9])(?:\w|\:)+|^"(?:[^"]|"")+")\[[^\]]+\]/,
|
||||
QUOTED_LITERAL: /^'(?:[^']|'')*'/,
|
||||
NUMERIC_LITERAL: /^[0-9]+(?:\.[0-9]*(?:[eE][-+][0-9]+)?)?/,
|
||||
SYMBOL: /^(?:==|=|<>|<=|<|>=|>|!~~|!~|~~|~|!==|!=|!~=|!~|!|&|\||\.|\:|,|\(|\)|\[|\]|\{|\}|\?|\:|;|@|\^|\/\+|\/|\*|\+|-)/
|
||||
};
|
||||
""", # NOQA
|
||||
[
|
||||
"id rexl",
|
||||
"punct .",
|
||||
"id re",
|
||||
"punct =",
|
||||
"punct {",
|
||||
"id NAME",
|
||||
"punct :",
|
||||
r"""regex /^(?![0-9])(?:\w)+|^"(?:[^"]|"")+"/""",
|
||||
"punct ,",
|
||||
"id UNQUOTED_LITERAL",
|
||||
"punct :",
|
||||
r"""regex /^@(?:(?![0-9])(?:\w|\:)+|^"(?:[^"]|"")+")\[[^\]]+\]/""",
|
||||
"punct ,",
|
||||
"id QUOTED_LITERAL",
|
||||
"punct :",
|
||||
r"""regex /^'(?:[^']|'')*'/""",
|
||||
"punct ,",
|
||||
"id NUMERIC_LITERAL",
|
||||
"punct :",
|
||||
r"""regex /^[0-9]+(?:\.[0-9]*(?:[eE][-+][0-9]+)?)?/""",
|
||||
"punct ,",
|
||||
"id SYMBOL",
|
||||
"punct :",
|
||||
r"""regex /^(?:==|=|<>|<=|<|>=|>|!~~|!~|~~|~|!==|!=|!~=|!~|!|&|\||\.|\:|,|\(|\)|\[|\]|\{|\}|\?|\:|;|@|\^|\/\+|\/|\*|\+|-)/""", # NOQA
|
||||
"punct }",
|
||||
"punct ;",
|
||||
],
|
||||
),
|
||||
(
|
||||
r"""
|
||||
rexl.re = {
|
||||
NAME: /^(?![0-9])(?:\w)+|^"(?:[^"]|"")+"/,
|
||||
UNQUOTED_LITERAL: /^@(?:(?![0-9])(?:\w|\:)+|^"(?:[^"]|"")+")\[[^\]]+\]/,
|
||||
QUOTED_LITERAL: /^'(?:[^']|'')*'/,
|
||||
NUMERIC_LITERAL: /^[0-9]+(?:\.[0-9]*(?:[eE][-+][0-9]+)?)?/,
|
||||
SYMBOL: /^(?:==|=|<>|<=|<|>=|>|!~~|!~|~~|~|!==|!=|!~=|!~|!|&|\||\.|\:|,|\(|\)|\[|\]|\{|\}|\?|\:|;|@|\^|\/\+|\/|\*|\+|-)/
|
||||
};
|
||||
str = '"';
|
||||
""", # NOQA
|
||||
[
|
||||
"id rexl",
|
||||
"punct .",
|
||||
"id re",
|
||||
"punct =",
|
||||
"punct {",
|
||||
"id NAME",
|
||||
"punct :",
|
||||
r"""regex /^(?![0-9])(?:\w)+|^"(?:[^"]|"")+"/""",
|
||||
"punct ,",
|
||||
"id UNQUOTED_LITERAL",
|
||||
"punct :",
|
||||
r"""regex /^@(?:(?![0-9])(?:\w|\:)+|^"(?:[^"]|"")+")\[[^\]]+\]/""",
|
||||
"punct ,",
|
||||
"id QUOTED_LITERAL",
|
||||
"punct :",
|
||||
r"""regex /^'(?:[^']|'')*'/""",
|
||||
"punct ,",
|
||||
"id NUMERIC_LITERAL",
|
||||
"punct :",
|
||||
r"""regex /^[0-9]+(?:\.[0-9]*(?:[eE][-+][0-9]+)?)?/""",
|
||||
"punct ,",
|
||||
"id SYMBOL",
|
||||
"punct :",
|
||||
r"""regex /^(?:==|=|<>|<=|<|>=|>|!~~|!~|~~|~|!==|!=|!~=|!~|!|&|\||\.|\:|,|\(|\)|\[|\]|\{|\}|\?|\:|;|@|\^|\/\+|\/|\*|\+|-)/""", # NOQA
|
||||
"punct }",
|
||||
"punct ;",
|
||||
"id str",
|
||||
"punct =",
|
||||
"""string '"'""",
|
||||
"punct ;",
|
||||
],
|
||||
),
|
||||
(
|
||||
r' this._js = "e.str(\"" + this.value.replace(/\\/g, "\\\\")'
|
||||
r'.replace(/"/g, "\\\"") + "\")"; ',
|
||||
[
|
||||
"keyword this",
|
||||
"punct .",
|
||||
"id _js",
|
||||
"punct =",
|
||||
r'''string "e.str(\""''',
|
||||
"punct +",
|
||||
"keyword this",
|
||||
"punct .",
|
||||
"id value",
|
||||
"punct .",
|
||||
"id replace",
|
||||
"punct (",
|
||||
r"regex /\\/g",
|
||||
"punct ,",
|
||||
r'string "\\\\"',
|
||||
"punct )",
|
||||
"punct .",
|
||||
"id replace",
|
||||
"punct (",
|
||||
r'regex /"/g',
|
||||
"punct ,",
|
||||
r'string "\\\""',
|
||||
"punct )",
|
||||
"punct +",
|
||||
r'string "\")"',
|
||||
"punct ;",
|
||||
],
|
||||
),
|
||||
]
|
||||
|
||||
|
||||
def make_function(input, toks):
|
||||
def test_func(self):
|
||||
lexer = JsLexer()
|
||||
result = [
|
||||
"%s %s" % (name, tok) for name, tok in lexer.lex(input) if name != "ws"
|
||||
]
|
||||
self.assertEqual(result, toks)
|
||||
|
||||
return test_func
|
||||
|
||||
|
||||
for i, (input, toks) in enumerate(JsTokensTest.LEX_CASES):
|
||||
setattr(JsTokensTest, "test_case_%d" % i, make_function(input, toks))
|
||||
|
||||
|
||||
GETTEXT_CASES = (
|
||||
(
|
||||
r"""
|
||||
a = 1; /* /[0-9]+/ */
|
||||
b = 0x2a0b / 1; // /[0-9]+/
|
||||
c = 3;
|
||||
""",
|
||||
r"""
|
||||
a = 1; /* /[0-9]+/ */
|
||||
b = 0x2a0b / 1; // /[0-9]+/
|
||||
c = 3;
|
||||
""",
|
||||
),
|
||||
(
|
||||
r"""
|
||||
a = 1.234e-5;
|
||||
/*
|
||||
* /[0-9+/
|
||||
*/
|
||||
b = .0123;
|
||||
""",
|
||||
r"""
|
||||
a = 1.234e-5;
|
||||
/*
|
||||
* /[0-9+/
|
||||
*/
|
||||
b = .0123;
|
||||
""",
|
||||
),
|
||||
(
|
||||
r"""
|
||||
x = y / z;
|
||||
alert(gettext("hello"));
|
||||
x /= 3;
|
||||
""",
|
||||
r"""
|
||||
x = y / z;
|
||||
alert(gettext("hello"));
|
||||
x /= 3;
|
||||
""",
|
||||
),
|
||||
(
|
||||
r"""
|
||||
s = "Hello \"th/foo/ere\"";
|
||||
s = 'He\x23llo \'th/foo/ere\'';
|
||||
s = 'slash quote \", just quote "';
|
||||
""",
|
||||
r"""
|
||||
s = "Hello \"th/foo/ere\"";
|
||||
s = "He\x23llo \'th/foo/ere\'";
|
||||
s = "slash quote \", just quote \"";
|
||||
""",
|
||||
),
|
||||
(
|
||||
r"""
|
||||
s = "Line continuation\
|
||||
continued /hello/ still the string";/hello/;
|
||||
""",
|
||||
r"""
|
||||
s = "Line continuation\
|
||||
continued /hello/ still the string";"REGEX";
|
||||
""",
|
||||
),
|
||||
(
|
||||
r"""
|
||||
var regex = /pattern/;
|
||||
var regex2 = /matter/gm;
|
||||
var regex3 = /[*/]+/gm.foo("hey");
|
||||
""",
|
||||
r"""
|
||||
var regex = "REGEX";
|
||||
var regex2 = "REGEX";
|
||||
var regex3 = "REGEX".foo("hey");
|
||||
""",
|
||||
),
|
||||
(
|
||||
r"""
|
||||
for (var x = a in foo && "</x>" || mot ? z:/x:3;x<5;y</g/i) {xyz(x++);}
|
||||
for (var x = a in foo && "</x>" || mot ? z/x:3;x<5;y</g/i) {xyz(x++);}
|
||||
""",
|
||||
r"""
|
||||
for (var x = a in foo && "</x>" || mot ? z:"REGEX"/i) {xyz(x++);}
|
||||
for (var x = a in foo && "</x>" || mot ? z/x:3;x<5;y<"REGEX") {xyz(x++);}
|
||||
""",
|
||||
),
|
||||
(
|
||||
"""
|
||||
\\u1234xyz = gettext('Hello there');
|
||||
""",
|
||||
r"""
|
||||
Uu1234xyz = gettext("Hello there");
|
||||
""",
|
||||
),
|
||||
)
|
||||
|
||||
|
||||
class JsToCForGettextTest(SimpleTestCase):
|
||||
pass
|
||||
|
||||
|
||||
def make_function(js, c):
|
||||
def test_func(self):
|
||||
self.assertEqual(prepare_js_for_gettext(js), c)
|
||||
|
||||
return test_func
|
||||
|
||||
|
||||
for i, pair in enumerate(GETTEXT_CASES):
|
||||
setattr(JsToCForGettextTest, "test_case_%d" % i, make_function(*pair))
|
||||
Loading…
Reference in New Issue
Block a user