Fix #7301: Allow . and _ for node_id

In development of 3.0, Sphinx starts to obey to the rule of
"Identifier Normalization" of docutils.  This extends it to allow
dots(".") and underscores("_") for node identifier.

It allows Sphinx to generate node identifier from source string as
possible as it is (bacause dots and underscores are usually used in
many programming langauges).

This change will keep not to break hyperlinks as possible.
This commit is contained in:
Takeshi KOMIYA 2020-03-20 18:17:50 +09:00
parent dd85cb6588
commit 7bbf79c313
9 changed files with 137 additions and 63 deletions

View File

@ -370,7 +370,7 @@ class PyObject(ObjectDescription):
signode: desc_signature) -> None:
modname = self.options.get('module', self.env.ref_context.get('py:module'))
fullname = (modname + '.' if modname else '') + name_cls[0]
node_id = make_id(self.env, self.state.document, modname or '', name_cls[0])
node_id = make_id(self.env, self.state.document, '', fullname)
signode['ids'].append(node_id)
# Assign old styled node_id(fullname) not to break old hyperlinks (if possible)

View File

@ -9,6 +9,7 @@
"""
import re
import unicodedata
import warnings
from typing import Any, Callable, Iterable, List, Set, Tuple
from typing import cast
@ -436,6 +437,79 @@ def inline_all_toctrees(builder: "Builder", docnameset: Set[str], docname: str,
return tree
def _make_id(string: str) -> str:
"""Convert `string` into an identifier and return it.
This function is a modified version of ``docutils.nodes.make_id()`` of
docutils-0.16.
Changes:
* Allow to use dots (".") and underscores ("_") for an identifier
without a leading character.
# Author: David Goodger <goodger@python.org>
# Maintainer: docutils-develop@lists.sourceforge.net
# Copyright: This module has been placed in the public domain.
"""
id = string.lower()
id = id.translate(_non_id_translate_digraphs)
id = id.translate(_non_id_translate)
# get rid of non-ascii characters.
# 'ascii' lowercase to prevent problems with turkish locale.
id = unicodedata.normalize('NFKD', id).encode('ascii', 'ignore').decode('ascii')
# shrink runs of whitespace and replace by hyphen
id = _non_id_chars.sub('-', ' '.join(id.split()))
id = _non_id_at_ends.sub('', id)
return str(id)
_non_id_chars = re.compile('[^a-z0-9._]+')
_non_id_at_ends = re.compile('^[-0-9._]+|-+$')
_non_id_translate = {
0x00f8: u'o', # o with stroke
0x0111: u'd', # d with stroke
0x0127: u'h', # h with stroke
0x0131: u'i', # dotless i
0x0142: u'l', # l with stroke
0x0167: u't', # t with stroke
0x0180: u'b', # b with stroke
0x0183: u'b', # b with topbar
0x0188: u'c', # c with hook
0x018c: u'd', # d with topbar
0x0192: u'f', # f with hook
0x0199: u'k', # k with hook
0x019a: u'l', # l with bar
0x019e: u'n', # n with long right leg
0x01a5: u'p', # p with hook
0x01ab: u't', # t with palatal hook
0x01ad: u't', # t with hook
0x01b4: u'y', # y with hook
0x01b6: u'z', # z with stroke
0x01e5: u'g', # g with stroke
0x0225: u'z', # z with hook
0x0234: u'l', # l with curl
0x0235: u'n', # n with curl
0x0236: u't', # t with curl
0x0237: u'j', # dotless j
0x023c: u'c', # c with stroke
0x023f: u's', # s with swash tail
0x0240: u'z', # z with swash tail
0x0247: u'e', # e with stroke
0x0249: u'j', # j with stroke
0x024b: u'q', # q with hook tail
0x024d: u'r', # r with stroke
0x024f: u'y', # y with stroke
}
_non_id_translate_digraphs = {
0x00df: u'sz', # ligature sz
0x00e6: u'ae', # ae
0x0153: u'oe', # ligature oe
0x0238: u'db', # db digraph
0x0239: u'qp', # qp digraph
}
def make_id(env: "BuildEnvironment", document: nodes.document,
prefix: str = '', term: str = None) -> str:
"""Generate an appropriate node_id for given *prefix* and *term*."""
@ -447,12 +521,12 @@ def make_id(env: "BuildEnvironment", document: nodes.document,
# try to generate node_id by *term*
if prefix and term:
node_id = nodes.make_id(idformat % term)
node_id = _make_id(idformat % term)
if node_id == prefix:
# *term* is not good to generate a node_id.
node_id = None
elif term:
node_id = nodes.make_id(term)
node_id = _make_id(term)
if node_id == '':
node_id = None # fallback to None

View File

@ -320,13 +320,13 @@ def test_epub_anchor_id(app):
app.build()
html = (app.outdir / 'index.xhtml').read_text()
assert ('<p id="std-setting-staticfiles-finders">'
assert ('<p id="std-setting-staticfiles_finders">'
'<span id="std-setting-STATICFILES_FINDERS"></span>'
'blah blah blah</p>' in html)
assert ('<span id="std-setting-staticfiles-section"></span>'
assert ('<span id="std-setting-staticfiles_section"></span>'
'<span id="std-setting-STATICFILES_SECTION"></span>'
'<h1>blah blah blah</h1>' in html)
assert 'see <a class="reference internal" href="#std-setting-staticfiles-finders">' in html
assert 'see <a class="reference internal" href="#std-setting-staticfiles_finders">' in html
@pytest.mark.sphinx('epub', testroot='html_assets')

View File

@ -176,9 +176,9 @@ def test_html4_output(app, status, warning):
r'-| |-'),
],
'autodoc.html': [
(".//dl[@class='py class']/dt[@id='autodoc-target-class']", ''),
(".//dl[@class='py function']/dt[@id='autodoc-target-function']/em/span", r'\*\*'),
(".//dl[@class='py function']/dt[@id='autodoc-target-function']/em/span", r'kwds'),
(".//dl[@class='py class']/dt[@id='autodoc_target.class']", ''),
(".//dl[@class='py function']/dt[@id='autodoc_target.function']/em/span", r'\*\*'),
(".//dl[@class='py function']/dt[@id='autodoc_target.function']/em/span", r'kwds'),
(".//dd/p", r'Return spam\.'),
],
'extapi.html': [
@ -223,7 +223,7 @@ def test_html4_output(app, status, warning):
"[@class='reference internal']/code/span[@class='pre']", 'HOME'),
(".//a[@href='#with']"
"[@class='reference internal']/code/span[@class='pre']", '^with$'),
(".//a[@href='#grammar-token-try-stmt']"
(".//a[@href='#grammar-token-try_stmt']"
"[@class='reference internal']/code/span", '^statement$'),
(".//a[@href='#some-label'][@class='reference internal']/span", '^here$'),
(".//a[@href='#some-label'][@class='reference internal']/span", '^there$'),
@ -255,7 +255,7 @@ def test_html4_output(app, status, warning):
(".//dl/dt[@id='term-boson']", 'boson'),
# a production list
(".//pre/strong", 'try_stmt'),
(".//pre/a[@href='#grammar-token-try1-stmt']/code/span", 'try1_stmt'),
(".//pre/a[@href='#grammar-token-try1_stmt']/code/span", 'try1_stmt'),
# tests for ``only`` directive
(".//p", 'A global substitution.'),
(".//p", 'In HTML.'),
@ -263,7 +263,7 @@ def test_html4_output(app, status, warning):
(".//p", 'Always present'),
# tests for ``any`` role
(".//a[@href='#with']/span", 'headings'),
(".//a[@href='objects.html#func-without-body']/code/span", 'objects'),
(".//a[@href='objects.html#func_without_body']/code/span", 'objects'),
# tests for numeric labels
(".//a[@href='#id1'][@class='reference internal']/span", 'Testing various markup'),
# tests for smartypants
@ -275,18 +275,18 @@ def test_html4_output(app, status, warning):
(".//p", 'Il dit : « Cest “super” ! »'),
],
'objects.html': [
(".//dt[@id='mod-cls-meth1']", ''),
(".//dt[@id='errmod-error']", ''),
(".//dt[@id='mod.cls.meth1']", ''),
(".//dt[@id='errmod.error']", ''),
(".//dt/code", r'long\(parameter,\s* list\)'),
(".//dt/code", 'another one'),
(".//a[@href='#mod-cls'][@class='reference internal']", ''),
(".//a[@href='#mod.cls'][@class='reference internal']", ''),
(".//dl[@class='std userdesc']", ''),
(".//dt[@id='userdesc-myobj']", ''),
(".//a[@href='#userdesc-myobj'][@class='reference internal']", ''),
# docfields
(".//a[@class='reference internal'][@href='#timeint']/em", 'TimeInt'),
(".//a[@class='reference internal'][@href='#time']", 'Time'),
(".//a[@class='reference internal'][@href='#errmod-error']/strong", 'Error'),
(".//a[@class='reference internal'][@href='#errmod.error']/strong", 'Error'),
# C references
(".//span[@class='pre']", 'CFunction()'),
(".//a[@href='#c.Sphinx_DoSomething']", ''),
@ -325,7 +325,7 @@ def test_html4_output(app, status, warning):
'\\+p'),
(".//a[@class='reference internal'][@href='#cmdoption-perl-objc']/code/span",
'--ObjC\\+\\+'),
(".//a[@class='reference internal'][@href='#cmdoption-perl-plugin-option']/code/span",
(".//a[@class='reference internal'][@href='#cmdoption-perl-plugin.option']/code/span",
'--plugin.option'),
(".//a[@class='reference internal'][@href='#cmdoption-perl-arg-create-auth-token']"
"/code/span",

View File

@ -123,25 +123,25 @@ def test_domain_js_find_obj(app, status, warning):
('NestedParentA', ('roles', 'nestedparenta', 'class')))
assert (find_obj(None, None, 'NestedParentA.NestedChildA', 'class') ==
('NestedParentA.NestedChildA',
('roles', 'nestedparenta-nestedchilda', 'class')))
('roles', 'nestedparenta.nestedchilda', 'class')))
assert (find_obj(None, 'NestedParentA', 'NestedChildA', 'class') ==
('NestedParentA.NestedChildA',
('roles', 'nestedparenta-nestedchilda', 'class')))
('roles', 'nestedparenta.nestedchilda', 'class')))
assert (find_obj(None, None, 'NestedParentA.NestedChildA.subchild_1', 'func') ==
('NestedParentA.NestedChildA.subchild_1',
('roles', 'nestedparenta-nestedchilda-subchild-1', 'function')))
('roles', 'nestedparenta.nestedchilda.subchild_1', 'function')))
assert (find_obj(None, 'NestedParentA', 'NestedChildA.subchild_1', 'func') ==
('NestedParentA.NestedChildA.subchild_1',
('roles', 'nestedparenta-nestedchilda-subchild-1', 'function')))
('roles', 'nestedparenta.nestedchilda.subchild_1', 'function')))
assert (find_obj(None, 'NestedParentA.NestedChildA', 'subchild_1', 'func') ==
('NestedParentA.NestedChildA.subchild_1',
('roles', 'nestedparenta-nestedchilda-subchild-1', 'function')))
('roles', 'nestedparenta.nestedchilda.subchild_1', 'function')))
assert (find_obj('module_a.submodule', 'ModTopLevel', 'mod_child_2', 'meth') ==
('module_a.submodule.ModTopLevel.mod_child_2',
('module', 'module-a-submodule-modtoplevel-mod-child-2', 'method')))
('module', 'module_a.submodule.modtoplevel.mod_child_2', 'method')))
assert (find_obj('module_b.submodule', 'ModTopLevel', 'module_a.submodule', 'mod') ==
('module_a.submodule',
('module', 'module-module-a-submodule', 'module')))
('module', 'module-module_a.submodule', 'module')))
def test_get_full_qualified_name():

View File

@ -171,11 +171,11 @@ def test_resolve_xref_for_properties(app, status, warning):
app.builder.build_all()
content = (app.outdir / 'module.html').read_text()
assert ('Link to <a class="reference internal" href="#module-a-submodule-modtoplevel-prop"'
assert ('Link to <a class="reference internal" href="#module_a.submodule.modtoplevel.prop"'
' title="module_a.submodule.ModTopLevel.prop">'
'<code class="xref py py-attr docutils literal notranslate"><span class="pre">'
'prop</span> <span class="pre">attribute</span></code></a>' in content)
assert ('Link to <a class="reference internal" href="#module-a-submodule-modtoplevel-prop"'
assert ('Link to <a class="reference internal" href="#module_a.submodule.modtoplevel.prop"'
' title="module_a.submodule.ModTopLevel.prop">'
'<code class="xref py py-meth docutils literal notranslate"><span class="pre">'
'prop</span> <span class="pre">method</span></code></a>' in content)
@ -194,18 +194,18 @@ def test_domain_py_find_obj(app, status, warning):
assert (find_obj(None, None, 'NestedParentA', 'class') ==
[('NestedParentA', ('roles', 'nestedparenta', 'class'))])
assert (find_obj(None, None, 'NestedParentA.NestedChildA', 'class') ==
[('NestedParentA.NestedChildA', ('roles', 'nestedparenta-nestedchilda', 'class'))])
[('NestedParentA.NestedChildA', ('roles', 'nestedparenta.nestedchilda', 'class'))])
assert (find_obj(None, 'NestedParentA', 'NestedChildA', 'class') ==
[('NestedParentA.NestedChildA', ('roles', 'nestedparenta-nestedchilda', 'class'))])
[('NestedParentA.NestedChildA', ('roles', 'nestedparenta.nestedchilda', 'class'))])
assert (find_obj(None, None, 'NestedParentA.NestedChildA.subchild_1', 'meth') ==
[('NestedParentA.NestedChildA.subchild_1',
('roles', 'nestedparenta-nestedchilda-subchild-1', 'method'))])
('roles', 'nestedparenta.nestedchilda.subchild_1', 'method'))])
assert (find_obj(None, 'NestedParentA', 'NestedChildA.subchild_1', 'meth') ==
[('NestedParentA.NestedChildA.subchild_1',
('roles', 'nestedparenta-nestedchilda-subchild-1', 'method'))])
('roles', 'nestedparenta.nestedchilda.subchild_1', 'method'))])
assert (find_obj(None, 'NestedParentA.NestedChildA', 'subchild_1', 'meth') ==
[('NestedParentA.NestedChildA.subchild_1',
('roles', 'nestedparenta-nestedchilda-subchild-1', 'method'))])
('roles', 'nestedparenta.nestedchilda.subchild_1', 'method'))])
def test_get_full_qualified_name():
@ -483,61 +483,61 @@ def test_pymethod_options(app):
# method
assert_node(doctree[1][1][0], addnodes.index,
entries=[('single', 'meth1() (Class method)', 'class-meth1', '', None)])
entries=[('single', 'meth1() (Class method)', 'class.meth1', '', None)])
assert_node(doctree[1][1][1], ([desc_signature, ([desc_name, "meth1"],
[desc_parameterlist, ()])],
[desc_content, ()]))
assert 'Class.meth1' in domain.objects
assert domain.objects['Class.meth1'] == ('index', 'class-meth1', 'method')
assert domain.objects['Class.meth1'] == ('index', 'class.meth1', 'method')
# :classmethod:
assert_node(doctree[1][1][2], addnodes.index,
entries=[('single', 'meth2() (Class class method)', 'class-meth2', '', None)])
entries=[('single', 'meth2() (Class class method)', 'class.meth2', '', None)])
assert_node(doctree[1][1][3], ([desc_signature, ([desc_annotation, "classmethod "],
[desc_name, "meth2"],
[desc_parameterlist, ()])],
[desc_content, ()]))
assert 'Class.meth2' in domain.objects
assert domain.objects['Class.meth2'] == ('index', 'class-meth2', 'method')
assert domain.objects['Class.meth2'] == ('index', 'class.meth2', 'method')
# :staticmethod:
assert_node(doctree[1][1][4], addnodes.index,
entries=[('single', 'meth3() (Class static method)', 'class-meth3', '', None)])
entries=[('single', 'meth3() (Class static method)', 'class.meth3', '', None)])
assert_node(doctree[1][1][5], ([desc_signature, ([desc_annotation, "static "],
[desc_name, "meth3"],
[desc_parameterlist, ()])],
[desc_content, ()]))
assert 'Class.meth3' in domain.objects
assert domain.objects['Class.meth3'] == ('index', 'class-meth3', 'method')
assert domain.objects['Class.meth3'] == ('index', 'class.meth3', 'method')
# :async:
assert_node(doctree[1][1][6], addnodes.index,
entries=[('single', 'meth4() (Class method)', 'class-meth4', '', None)])
entries=[('single', 'meth4() (Class method)', 'class.meth4', '', None)])
assert_node(doctree[1][1][7], ([desc_signature, ([desc_annotation, "async "],
[desc_name, "meth4"],
[desc_parameterlist, ()])],
[desc_content, ()]))
assert 'Class.meth4' in domain.objects
assert domain.objects['Class.meth4'] == ('index', 'class-meth4', 'method')
assert domain.objects['Class.meth4'] == ('index', 'class.meth4', 'method')
# :property:
assert_node(doctree[1][1][8], addnodes.index,
entries=[('single', 'meth5() (Class property)', 'class-meth5', '', None)])
entries=[('single', 'meth5() (Class property)', 'class.meth5', '', None)])
assert_node(doctree[1][1][9], ([desc_signature, ([desc_annotation, "property "],
[desc_name, "meth5"])],
[desc_content, ()]))
assert 'Class.meth5' in domain.objects
assert domain.objects['Class.meth5'] == ('index', 'class-meth5', 'method')
assert domain.objects['Class.meth5'] == ('index', 'class.meth5', 'method')
# :abstractmethod:
assert_node(doctree[1][1][10], addnodes.index,
entries=[('single', 'meth6() (Class method)', 'class-meth6', '', None)])
entries=[('single', 'meth6() (Class method)', 'class.meth6', '', None)])
assert_node(doctree[1][1][11], ([desc_signature, ([desc_annotation, "abstract "],
[desc_name, "meth6"],
[desc_parameterlist, ()])],
[desc_content, ()]))
assert 'Class.meth6' in domain.objects
assert domain.objects['Class.meth6'] == ('index', 'class-meth6', 'method')
assert domain.objects['Class.meth6'] == ('index', 'class.meth6', 'method')
def test_pyclassmethod(app):
@ -552,13 +552,13 @@ def test_pyclassmethod(app):
[desc_content, (addnodes.index,
desc)])]))
assert_node(doctree[1][1][0], addnodes.index,
entries=[('single', 'meth() (Class class method)', 'class-meth', '', None)])
entries=[('single', 'meth() (Class class method)', 'class.meth', '', None)])
assert_node(doctree[1][1][1], ([desc_signature, ([desc_annotation, "classmethod "],
[desc_name, "meth"],
[desc_parameterlist, ()])],
[desc_content, ()]))
assert 'Class.meth' in domain.objects
assert domain.objects['Class.meth'] == ('index', 'class-meth', 'method')
assert domain.objects['Class.meth'] == ('index', 'class.meth', 'method')
def test_pystaticmethod(app):
@ -573,13 +573,13 @@ def test_pystaticmethod(app):
[desc_content, (addnodes.index,
desc)])]))
assert_node(doctree[1][1][0], addnodes.index,
entries=[('single', 'meth() (Class static method)', 'class-meth', '', None)])
entries=[('single', 'meth() (Class static method)', 'class.meth', '', None)])
assert_node(doctree[1][1][1], ([desc_signature, ([desc_annotation, "static "],
[desc_name, "meth"],
[desc_parameterlist, ()])],
[desc_content, ()]))
assert 'Class.meth' in domain.objects
assert domain.objects['Class.meth'] == ('index', 'class-meth', 'method')
assert domain.objects['Class.meth'] == ('index', 'class.meth', 'method')
def test_pyattribute(app):
@ -596,13 +596,13 @@ def test_pyattribute(app):
[desc_content, (addnodes.index,
desc)])]))
assert_node(doctree[1][1][0], addnodes.index,
entries=[('single', 'attr (Class attribute)', 'class-attr', '', None)])
entries=[('single', 'attr (Class attribute)', 'class.attr', '', None)])
assert_node(doctree[1][1][1], ([desc_signature, ([desc_name, "attr"],
[desc_annotation, ": str"],
[desc_annotation, " = ''"])],
[desc_content, ()]))
assert 'Class.attr' in domain.objects
assert domain.objects['Class.attr'] == ('index', 'class-attr', 'attribute')
assert domain.objects['Class.attr'] == ('index', 'class.attr', 'attribute')
def test_pydecorator_signature(app):
@ -648,10 +648,10 @@ def test_module_index(app):
assert index.generate() == (
[('d', [IndexEntry('docutils', 0, 'index', 'module-docutils', '', '', '')]),
('s', [IndexEntry('sphinx', 1, 'index', 'module-sphinx', '', '', ''),
IndexEntry('sphinx.builders', 2, 'index', 'module-sphinx-builders', '', '', ''), # NOQA
IndexEntry('sphinx.builders.html', 2, 'index', 'module-sphinx-builders-html', '', '', ''), # NOQA
IndexEntry('sphinx.config', 2, 'index', 'module-sphinx-config', '', '', ''),
IndexEntry('sphinx_intl', 0, 'index', 'module-sphinx-intl', '', '', '')])],
IndexEntry('sphinx.builders', 2, 'index', 'module-sphinx.builders', '', '', ''), # NOQA
IndexEntry('sphinx.builders.html', 2, 'index', 'module-sphinx.builders.html', '', '', ''), # NOQA
IndexEntry('sphinx.config', 2, 'index', 'module-sphinx.config', '', '', ''),
IndexEntry('sphinx_intl', 0, 'index', 'module-sphinx_intl', '', '', '')])],
False
)
@ -663,7 +663,7 @@ def test_module_index_submodule(app):
index = PythonModuleIndex(app.env.get_domain('py'))
assert index.generate() == (
[('s', [IndexEntry('sphinx', 1, '', '', '', '', ''),
IndexEntry('sphinx.config', 2, 'index', 'module-sphinx-config', '', '', '')])],
IndexEntry('sphinx.config', 2, 'index', 'module-sphinx.config', '', '', '')])],
False
)
@ -692,12 +692,12 @@ def test_modindex_common_prefix(app):
restructuredtext.parse(app, text)
index = PythonModuleIndex(app.env.get_domain('py'))
assert index.generate() == (
[('b', [IndexEntry('sphinx.builders', 1, 'index', 'module-sphinx-builders', '', '', ''), # NOQA
IndexEntry('sphinx.builders.html', 2, 'index', 'module-sphinx-builders-html', '', '', '')]), # NOQA
('c', [IndexEntry('sphinx.config', 0, 'index', 'module-sphinx-config', '', '', '')]),
[('b', [IndexEntry('sphinx.builders', 1, 'index', 'module-sphinx.builders', '', '', ''), # NOQA
IndexEntry('sphinx.builders.html', 2, 'index', 'module-sphinx.builders.html', '', '', '')]), # NOQA
('c', [IndexEntry('sphinx.config', 0, 'index', 'module-sphinx.config', '', '', '')]),
('d', [IndexEntry('docutils', 0, 'index', 'module-docutils', '', '', '')]),
('s', [IndexEntry('sphinx', 0, 'index', 'module-sphinx', '', '', ''),
IndexEntry('sphinx_intl', 0, 'index', 'module-sphinx-intl', '', '', '')])],
IndexEntry('sphinx_intl', 0, 'index', 'module-sphinx_intl', '', '', '')])],
True
)

View File

@ -84,7 +84,7 @@ def test_object_inventory(app):
refs = app.env.domaindata['py']['objects']
assert 'func_without_module' in refs
assert refs['func_without_module'] == ('objects', 'func-without-module', 'function')
assert refs['func_without_module'] == ('objects', 'func_without_module', 'function')
assert 'func_without_module2' in refs
assert 'mod.func_in_module' in refs
assert 'mod.Cls' in refs

View File

@ -870,7 +870,7 @@ def test_xml_refs_in_python_domain(app):
assert_elem(
para0[0],
['SEE THIS DECORATOR:', 'sensitive_variables()', '.'],
['sensitive-sensitive-variables'])
['sensitive.sensitive_variables'])
@sphinx_intl

View File

@ -189,9 +189,9 @@ def test_clean_astext():
('', '', 'id0'),
('term', '', 'term-0'),
('term', 'Sphinx', 'term-sphinx'),
('', 'io.StringIO', 'io-stringio'), # contains a dot
('', 'sphinx.setup_command', 'sphinx-setup-command'), # contains a dot
('', '_io.StringIO', 'io-stringio'), # starts with underscore
('', 'io.StringIO', 'io.stringio'), # contains a dot
('', 'sphinx.setup_command', 'sphinx.setup_command'), # contains a dot & underscore
('', '_io.StringIO', 'io.stringio'), # starts with underscore
('', '', 'sphinx'), # alphabets in unicode fullwidth characters
('', '悠好', 'id0'), # multibytes text (in Chinese)
('', 'Hello=悠好=こんにちは', 'hello'), # alphabets and multibytes text