String transformers that can split and merge strings.
"""
import re
-import sys
from abc import ABC, abstractmethod
from collections import defaultdict
from dataclasses import dataclass
ClassVar,
Collection,
Dict,
+ Final,
Iterable,
Iterator,
List,
+ Literal,
Optional,
Sequence,
Set,
Union,
)
-if sys.version_info < (3, 8):
- from typing_extensions import Final, Literal
-else:
- from typing import Literal, Final
-
from mypy_extensions import trait
from black.comments import contains_pragma_comment
from black.lines import Line, append_leaves
-from black.mode import Feature
+from black.mode import Feature, Mode
from black.nodes import (
CLOSING_BRACKETS,
OPENING_BRACKETS,
from black.rusty import Err, Ok, Result
from black.strings import (
assert_is_leaf_string,
+ count_chars_in_width,
get_string_prefix,
has_triple_quotes,
normalize_string_quotes,
+ str_width,
)
from blib2to3.pgen2 import token
from blib2to3.pytree import Leaf, Node
# types
T = TypeVar("T")
LN = Union[Leaf, Node]
-Transformer = Callable[[Line, Collection[Feature]], Iterator[Line]]
+Transformer = Callable[[Line, Collection[Feature], Mode], Iterator[Line]]
Index = int
NodeType = int
ParserState = int
TResult = Result[T, CannotTransform] # (T)ransform Result
TMatchResult = TResult[List[Index]]
+SPLIT_SAFE_CHARS = frozenset(["\u3001", "\u3002", "\uff0c"]) # East Asian stops
+
def TErr(err_msg: str) -> Err[CannotTransform]:
"""(T)ransform Err
return Err(cant_transform)
-def hug_power_op(line: Line, features: Collection[Feature]) -> Iterator[Line]:
+def hug_power_op(
+ line: Line, features: Collection[Feature], mode: Mode
+) -> Iterator[Line]:
"""A transformer which normalizes spacing around power operators."""
# Performance optimization to avoid unnecessary Leaf clones and other ops.
"""
Returns:
* Ok(string_indices) such that for each index, `line.leaves[index]`
- is our target string if a match was able to be made. For
- transformers that don't result in more lines (e.g. StringMerger,
- StringParenStripper), multiple matches and transforms are done at
- once to reduce the complexity.
- OR
+ is our target string if a match was able to be made. For
+ transformers that don't result in more lines (e.g. StringMerger,
+ StringParenStripper), multiple matches and transforms are done at
+ once to reduce the complexity.
+ OR
* Err(CannotTransform), if no match could be made.
"""
"""
Yields:
* Ok(new_line) where new_line is the new transformed line.
- OR
+ OR
* Err(CannotTransform) if the transformation failed for some reason. The
- `do_match(...)` template method should usually be used to reject
- the form of the given Line, but in some cases it is difficult to
- know whether or not a Line meets the StringTransformer's
- requirements until the transformation is already midway.
+ `do_match(...)` template method should usually be used to reject
+ the form of the given Line, but in some cases it is difficult to
+ know whether or not a Line meets the StringTransformer's
+ requirements until the transformation is already midway.
Side Effects:
This method should NOT mutate @line directly, but it MAY mutate the
yield an CannotTransform after that point.)
"""
- def __call__(self, line: Line, _features: Collection[Feature]) -> Iterator[Line]:
+ def __call__(
+ self, line: Line, _features: Collection[Feature], _mode: Mode
+ ) -> Iterator[Line]:
"""
StringTransformer instances have a call signature that mirrors that of
the Transformer type.
Returns:
* A list of the custom splits that are mapped to @string, if any
- exist.
- OR
+ exist.
+ OR
* [], otherwise.
Side Effects:
Requirements:
(A) The line contains adjacent strings such that ALL of the validation checks
listed in StringMerger._validate_msg(...)'s docstring pass.
- OR
+ OR
(B) The line contains a string which uses line continuation backslashes.
Transformations:
Depending on which of the two requirements above where met, either:
(A) The string group associated with the target string is merged.
- OR
+ OR
(B) All line-continuation backslashes are removed from the target string.
Collaborations:
characters have been escaped.
"""
assert_is_leaf_string(string)
+ if "f" in string_prefix:
+ string = _toggle_fexpr_quotes(string, QUOTE)
+ # After quotes toggling, quotes in expressions won't be escaped
+ # because quotes can't be reused in f-strings. So we can simply
+ # let the escaping logic below run without knowing f-string
+ # expressions.
RE_EVEN_BACKSLASHES = r"(?:(?<!\\)(?:\\\\)*)"
naked_string = string[len(string_prefix) + 1 : -1]
LL[lpar_or_rpar_idx].remove() # Remove lpar.
replace_child(LL[idx], string_leaf)
new_line.append(string_leaf)
+ # replace comments
+ old_comments = new_line.comments.pop(id(LL[idx]), [])
+ new_line.comments.setdefault(id(string_leaf), []).extend(old_comments)
else:
LL[lpar_or_rpar_idx].remove() # This is a rpar.
Requirements:
* The target string value is responsible for the line going over the
- line length limit. It follows that after all of black's other line
- split methods have been exhausted, this line (or one of the resulting
- lines after all line splits are performed) would still be over the
- line_length limit unless we split this string.
- AND
+ line length limit. It follows that after all of black's other line
+ split methods have been exhausted, this line (or one of the resulting
+ lines after all line splits are performed) would still be over the
+ line_length limit unless we split this string.
+ AND
+
* The target string is NOT a "pointless" string (i.e. a string that has
- no parent or siblings).
- AND
+ no parent or siblings).
+ AND
+
* The target string is not followed by an inline comment that appears
- to be a pragma.
- AND
+ to be a pragma.
+ AND
+
* The target string is not a multiline (i.e. triple-quote) string.
"""
Returns:
* Ok(None), if ALL of the requirements are met.
- OR
+ OR
* Err(CannotTransform), if ANY of the requirements are NOT met.
"""
LL = line.leaves
# WMA4 the length of the inline comment.
offset += len(comment_leaf.value)
- max_string_length = self.line_length - offset
+ max_string_length = count_chars_in_width(str(line), self.line_length - offset)
return max_string_length
@staticmethod
if LL[0].type != token.STRING:
return None
- # If the string is surrounded by commas (or is the first/last child)...
- prev_sibling = LL[0].prev_sibling
- next_sibling = LL[0].next_sibling
- if not prev_sibling and not next_sibling and parent_type(LL[0]) == syms.atom:
- # If it's an atom string, we need to check the parent atom's siblings.
- parent = LL[0].parent
- assert parent is not None # For type checkers.
- prev_sibling = parent.prev_sibling
- next_sibling = parent.next_sibling
- if (not prev_sibling or prev_sibling.type == token.COMMA) and (
- not next_sibling or next_sibling.type == token.COMMA
+ matching_nodes = [
+ syms.listmaker,
+ syms.dictsetmaker,
+ syms.testlist_gexp,
+ ]
+ # If the string is an immediate child of a list/set/tuple literal...
+ if (
+ parent_type(LL[0]) in matching_nodes
+ or parent_type(LL[0].parent) in matching_nodes
):
- return 0
+ # And the string is surrounded by commas (or is the first/last child)...
+ prev_sibling = LL[0].prev_sibling
+ next_sibling = LL[0].next_sibling
+ if (
+ not prev_sibling
+ and not next_sibling
+ and parent_type(LL[0]) == syms.atom
+ ):
+ # If it's an atom string, we need to check the parent atom's siblings.
+ parent = LL[0].parent
+ assert parent is not None # For type checkers.
+ prev_sibling = parent.prev_sibling
+ next_sibling = parent.next_sibling
+ if (not prev_sibling or prev_sibling.type == token.COMMA) and (
+ not next_sibling or next_sibling.type == token.COMMA
+ ):
+ return 0
return None
return any(iter_fexpr_spans(s))
+def _toggle_fexpr_quotes(fstring: str, old_quote: str) -> str:
+ """
+ Toggles quotes used in f-string expressions that are `old_quote`.
+
+ f-string expressions can't contain backslashes, so we need to toggle the
+ quotes if the f-string itself will end up using the same quote. We can
+ simply toggle without escaping because, quotes can't be reused in f-string
+ expressions. They will fail to parse.
+
+ NOTE: If PEP 701 is accepted, above statement will no longer be true.
+ Though if quotes can be reused, we can simply reuse them without updates or
+ escaping, once Black figures out how to parse the new grammar.
+ """
+ new_quote = "'" if old_quote == '"' else '"'
+ parts = []
+ previous_index = 0
+ for start, end in iter_fexpr_spans(fstring):
+ parts.append(fstring[previous_index:start])
+ parts.append(fstring[start:end].replace(old_quote, new_quote))
+ previous_index = end
+ parts.append(fstring[previous_index:])
+ return "".join(parts)
+
+
class StringSplitter(BaseStringSplitter, CustomSplitMapMixin):
"""
StringTransformer that splits "atom" strings (i.e. strings which exist on
Requirements:
* The line consists ONLY of a single string (possibly prefixed by a
- string operator [e.g. '+' or '==']), MAYBE a string trailer, and MAYBE
- a trailing comma.
- AND
+ string operator [e.g. '+' or '==']), MAYBE a string trailer, and MAYBE
+ a trailing comma.
+ AND
* All of the requirements listed in BaseStringSplitter's docstring.
Transformations:
is_valid_index(string_idx + 1) and LL[string_idx + 1].type == token.COMMA
)
- def max_last_string() -> int:
+ def max_last_string_column() -> int:
"""
Returns:
- The max allowed length of the string value used for the last
- line we will construct.
+ The max allowed width of the string value used for the last
+ line we will construct. Note that this value means the width
+ rather than the number of characters (e.g., many East Asian
+ characters expand to two columns).
"""
result = self.line_length
result -= line.depth * 4
result -= string_op_leaves_length
return result
- # --- Calculate Max Break Index (for string value)
+ # --- Calculate Max Break Width (for string value)
# We start with the line length limit
- max_break_idx = self.line_length
+ max_break_width = self.line_length
# The last index of a string of length N is N-1.
- max_break_idx -= 1
+ max_break_width -= 1
# Leading whitespace is not present in the string value (e.g. Leaf.value).
- max_break_idx -= line.depth * 4
- if max_break_idx < 0:
+ max_break_width -= line.depth * 4
+ if max_break_width < 0:
yield TErr(
f"Unable to split {LL[string_idx].value} at such high of a line depth:"
f" {line.depth}"
# line limit.
use_custom_breakpoints = bool(
custom_splits
- and all(csplit.break_idx <= max_break_idx for csplit in custom_splits)
+ and all(csplit.break_idx <= max_break_width for csplit in custom_splits)
)
# Temporary storage for the remaining chunk of the string line that
if use_custom_breakpoints:
return len(custom_splits) > 1
else:
- return len(rest_value) > max_last_string()
+ return str_width(rest_value) > max_last_string_column()
string_line_results: List[Ok[Line]] = []
while more_splits_should_be_made():
break_idx = csplit.break_idx
else:
# Algorithmic Split (automatic)
- max_bidx = max_break_idx - string_op_leaves_length
+ max_bidx = (
+ count_chars_in_width(rest_value, max_break_width)
+ - string_op_leaves_length
+ )
maybe_break_idx = self._get_break_idx(rest_value, max_bidx)
if maybe_break_idx is None:
# If we are unable to algorithmically determine a good split
# Try to fit them all on the same line with the last substring...
if (
- len(temp_value) <= max_last_string()
+ str_width(temp_value) <= max_last_string_column()
or LL[string_idx + 1].type == token.COMMA
):
last_line.append(rest_leaf)
section of this classes' docstring would be be met by returning @i.
"""
is_space = string[i] == " "
+ is_split_safe = is_valid_index(i - 1) and string[i - 1] in SPLIT_SAFE_CHARS
is_not_escaped = True
j = i - 1
and len(string[:i]) >= self.MIN_SUBSTR_SIZE
)
return (
- is_space
+ (is_space or is_split_safe)
and is_not_escaped
and is_big_enough
and not breaks_unsplittable_expression(i)
addition to the requirements listed below:
* The line is a return/yield statement, which returns/yields a string.
- OR
+ OR
* The line is part of a ternary expression (e.g. `x = y if cond else
- z`) such that the line starts with `else <string>`, where <string> is
- some string.
- OR
+ z`) such that the line starts with `else <string>`, where <string> is
+ some string.
+ OR
* The line is an assert statement, which ends with a string.
- OR
+ OR
* The line is an assignment statement (e.g. `x = <string>` or `x +=
- <string>`) such that the variable is being assigned the value of some
- string.
- OR
+ <string>`) such that the variable is being assigned the value of some
+ string.
+ OR
* The line is a dictionary key assignment where some valid key is being
- assigned the value of some string.
- OR
+ assigned the value of some string.
+ OR
* The line is an lambda expression and the value is a string.
- OR
+ OR
* The line starts with an "atom" string that prefers to be wrapped in
- parens. It's preferred to be wrapped when the string is surrounded by
- commas (or is the first/last child).
+ parens. It's preferred to be wrapped when it's is an immediate child of
+ a list/set/tuple literal, AND the string is surrounded by commas (or is
+ the first/last child).
Transformations:
The chosen string is wrapped in parentheses and then split at the LPAR.
if string_idx is not None:
string_value = line.leaves[string_idx].value
- # If the string has no spaces...
- if " " not in string_value:
+ # If the string has neither spaces nor East Asian stops...
+ if not any(
+ char == " " or char in SPLIT_SAFE_CHARS for char in string_value
+ ):
# And will still violate the line length limit when split...
- max_string_length = self.line_length - ((line.depth + 1) * 4)
- if len(string_value) > max_string_length:
+ max_string_width = self.line_length - ((line.depth + 1) * 4)
+ if str_width(string_value) > max_string_width:
# And has no associated custom splits...
if not self.has_custom_splits(string_value):
# Then we should NOT put this string on its own line.
Returns:
The index directly after the last leaf which is apart of the string
trailer, if a "trailer" exists.
- OR
+ OR
@string_idx + 1, if no string "trailer" exists.
"""
assert leaves[string_idx].type == token.STRING
"""
Pre-conditions:
* On the first call to this function, @leaf MUST be the leaf that
- was directly after the string leaf in question (e.g. if our target
- string is `line.leaves[i]` then the first call to this method must
- be `line.leaves[i + 1]`).
+ was directly after the string leaf in question (e.g. if our target
+ string is `line.leaves[i]` then the first call to this method must
+ be `line.leaves[i + 1]`).
* On the next call to this function, the leaf parameter passed in
- MUST be the leaf directly following @leaf.
+ MUST be the leaf directly following @leaf.
Returns:
True iff @leaf is apart of the string's trailer.
projects / etc / vim.git / blobdiff