Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add option to preserve comments when parsing templates #2037

Open
wants to merge 4 commits into
base: main
Choose a base branch
from
Open
Show file tree
Hide file tree
Changes from 1 commit
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
fixup! Add option to preserve comments when parsing templates
  • Loading branch information
pawamoy committed Oct 10, 2024
commit 7b718193cb3292b27ae41a73a3d61c1d8e29a188
2 changes: 1 addition & 1 deletion CHANGES.rst
Original file line number Diff line number Diff line change
Expand Up @@ -9,7 +9,7 @@ Unreleased
- Use modern packaging metadata with ``pyproject.toml`` instead of ``setup.cfg``.
:pr:`1793`
- Use ``flit_core`` instead of ``setuptools`` as build backend.
- Add the ``preserve_comments`` parameter to ``Environment.parse`` to preserve comments in template ASTs. :pr:`2037`
- Preserve comments in ASTs when parsing templates with ``Environment.parse``. :pr:`2037`


Version 3.1.5
Expand Down
14 changes: 3 additions & 11 deletions src/jinja2/environment.py
Original file line number Diff line number Diff line change
Expand Up @@ -600,7 +600,6 @@ def parse(
source: str,
name: t.Optional[str] = None,
filename: t.Optional[str] = None,
preserve_comments: bool = False,
) -> nodes.Template:
"""Parse the sourcecode and return the abstract syntax tree. This
tree of nodes is used by the compiler to convert the template into
Expand All @@ -609,12 +608,9 @@ def parse(

If you are :ref:`developing Jinja extensions <writing-extensions>`
this gives you a good overview of the node tree generated.

.. versionchanged:: 3.2
Added `preserve_comments` parameter.
"""
try:
return self._parse(source, name, filename, preserve_comments)
return self._parse(source, name, filename)
except TemplateSyntaxError:
self.handle_exception(source=source)

Expand All @@ -623,12 +619,9 @@ def _parse(
source: str,
name: t.Optional[str],
filename: t.Optional[str],
preserve_comments: bool = False,
) -> nodes.Template:
"""Internal parsing function used by `parse` and `compile`."""
return Parser(
self, source, name, filename, preserve_comments=preserve_comments
).parse()
return Parser(self, source, name, filename).parse()

def lex(
self,
Expand Down Expand Up @@ -673,13 +666,12 @@ def _tokenize(
name: t.Optional[str],
filename: t.Optional[str] = None,
state: t.Optional[str] = None,
preserve_comments: bool = False,
) -> TokenStream:
"""Called by the parser to do the preprocessing and filtering
for all the extensions. Returns a :class:`~jinja2.lexer.TokenStream`.
"""
source = self.preprocess(source, name, filename)
stream = self.lexer.tokenize(source, name, filename, state, preserve_comments)
stream = self.lexer.tokenize(source, name, filename, state)

for ext in self.iter_extensions():
stream = ext.filter_stream(stream) # type: ignore
Expand Down
38 changes: 4 additions & 34 deletions src/jinja2/lexer.py
Original file line number Diff line number Diff line change
Expand Up @@ -146,22 +146,7 @@
f"({'|'.join(re.escape(x) for x in sorted(operators, key=lambda x: -len(x)))})"
)

comment_tokens = frozenset(
[
TOKEN_COMMENT_BEGIN,
TOKEN_COMMENT,
TOKEN_COMMENT_END,
TOKEN_LINECOMMENT_BEGIN,
TOKEN_LINECOMMENT_END,
TOKEN_LINECOMMENT,
]
)
ignored_tokens = frozenset(
[
TOKEN_WHITESPACE,
*comment_tokens,
]
)
ignored_tokens = frozenset([TOKEN_WHITESPACE])
ignore_if_empty = frozenset(
[TOKEN_WHITESPACE, TOKEN_DATA, TOKEN_COMMENT, TOKEN_LINECOMMENT]
)
Expand Down Expand Up @@ -612,37 +597,22 @@ def tokenize(
name: t.Optional[str] = None,
filename: t.Optional[str] = None,
state: t.Optional[str] = None,
preserve_comments: bool = False,
) -> TokenStream:
"""Calls tokeniter + tokenize and wraps it in a token stream.

.. versionchanged:: 3.2
Added `preserve_comments` parameter.
"""
"""Calls tokeniter + tokenize and wraps it in a token stream."""
stream = self.tokeniter(source, name, filename, state)
return TokenStream(
self.wrap(stream, name, filename, preserve_comments), name, filename
)
return TokenStream(self.wrap(stream, name, filename), name, filename)

def wrap(
self,
stream: t.Iterable[t.Tuple[int, str, str]],
name: t.Optional[str] = None,
filename: t.Optional[str] = None,
preserve_comments: bool = False,
) -> t.Iterator[Token]:
"""This is called with the stream as returned by `tokenize` and wraps
every token in a :class:`Token` and converts the value.

.. versionchanged:: 3.2
Added `preserve_comments` parameter.
"""
ignored = ignored_tokens
if preserve_comments:
ignored -= comment_tokens

for lineno, token, value_str in stream:
if token in ignored:
if token in ignored_tokens:
continue

value: t.Any = value_str
Expand Down
16 changes: 8 additions & 8 deletions src/jinja2/parser.py
Original file line number Diff line number Diff line change
Expand Up @@ -57,12 +57,9 @@ def __init__(
name: t.Optional[str] = None,
filename: t.Optional[str] = None,
state: t.Optional[str] = None,
preserve_comments: bool = False,
) -> None:
self.environment = environment
self.stream = environment._tokenize(
source, name, filename, state, preserve_comments
)
self.stream = environment._tokenize(source, name, filename, state)
self.name = name
self.filename = filename
self.closed = False
Expand Down Expand Up @@ -318,10 +315,13 @@ def parse_block(self) -> nodes.Block:
# with whitespace data
if node.required:
for body_node in node.body:
if not isinstance(body_node, nodes.Output) or any(
not isinstance(output_node, nodes.TemplateData)
or not output_node.data.isspace()
for output_node in body_node.nodes
if not isinstance(body_node, (nodes.Output, nodes.Comment)) or (
isinstance(body_node, nodes.Output)
Comment on lines +318 to +319
Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

note: This was needed to fix the logic and two failing tests:

FAILED tests/test_inheritance.py::TestInheritance::test_level1_required - jinja2.exceptions.TemplateSyntaxError: Required blocks can only contain comments or whitespace
FAILED tests/test_inheritance.py::TestInheritance::test_invalid_required - jinja2.exceptions.TemplateSyntaxError: Required blocks can only contain comments or whitespace

and any(
not isinstance(output_node, nodes.TemplateData)
or not output_node.data.isspace()
for output_node in body_node.nodes
)
):
self.fail("Required blocks can only contain comments or whitespace")

Expand Down
13 changes: 2 additions & 11 deletions tests/test_lexnparse.py
Original file line number Diff line number Diff line change
Expand Up @@ -315,27 +315,18 @@ def assert_error(code, expected):
assert_error("{% unknown_tag %}", "Encountered unknown tag 'unknown_tag'.")

def test_comment_preservation(self, env):
ast = env.parse("{# foo #}{{ bar }}", preserve_comments=True)
ast = env.parse("{# foo #}{{ bar }}")
assert len(ast.body) == 2
assert isinstance(ast.body[0], nodes.Comment)
assert ast.body[0].data == " foo "

ast = env.parse("{# foo #}{{ bar }}", preserve_comments=False)
assert len(ast.body) == 1
assert not isinstance(ast.body[0], nodes.Comment)

def test_line_comment_preservation(self, env):
env = Environment(line_comment_prefix="#")

ast = env.parse("# foo\n{{ bar }}", preserve_comments=True)
ast = env.parse("# foo\n{{ bar }}")
assert len(ast.body) == 2
assert isinstance(ast.body[0], nodes.Comment)
assert ast.body[0].data == " foo"

ast = env.parse("# foo\n{{ bar }}", preserve_comments=False)
assert len(ast.body) == 1
assert not isinstance(ast.body[0], nodes.Comment)


class TestSyntax:
def test_call(self, env):
Expand Down