-
Notifications
You must be signed in to change notification settings - Fork 891
/
edits.rs
532 lines (480 loc) · 17.9 KB
/
edits.rs
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
//! Interface for generating fix edits from higher-level actions (e.g., "remove an argument").
use anyhow::{Context, Result};
use ruff_diagnostics::Edit;
use ruff_python_ast::parenthesize::parenthesized_range;
use ruff_python_ast::{self as ast, Arguments, ExceptHandler, Stmt};
use ruff_python_ast::{AnyNodeRef, ArgOrKeyword};
use ruff_python_codegen::Stylist;
use ruff_python_index::Indexer;
use ruff_python_trivia::textwrap::dedent_to;
use ruff_python_trivia::{
has_leading_content, is_python_whitespace, CommentRanges, PythonWhitespace, SimpleTokenKind,
SimpleTokenizer,
};
use ruff_source_file::{Locator, NewlineWithTrailingNewline, UniversalNewlines};
use ruff_text_size::{Ranged, TextLen, TextRange, TextSize};
use crate::cst::matchers::{match_function_def, match_indented_block, match_statement};
use crate::fix::codemods;
use crate::fix::codemods::CodegenStylist;
use crate::line_width::{IndentWidth, LineLength, LineWidthBuilder};
/// Return the `Fix` to use when deleting a `Stmt`.
///
/// In some cases, this is as simple as deleting the `Range` of the `Stmt`
/// itself. However, there are a few exceptions:
/// - If the `Stmt` is _not_ the terminal statement in a multi-statement line,
/// we need to delete up to the start of the next statement (and avoid
/// deleting any content that precedes the statement).
/// - If the `Stmt` is the terminal statement in a multi-statement line, we need
/// to avoid deleting any content that precedes the statement.
/// - If the `Stmt` has no trailing and leading content, then it's convenient to
/// remove the entire start and end lines.
/// - If the `Stmt` is the last statement in its parent body, replace it with a
/// `pass` instead.
pub(crate) fn delete_stmt(
stmt: &Stmt,
parent: Option<&Stmt>,
locator: &Locator,
indexer: &Indexer,
) -> Edit {
if parent.is_some_and(|parent| is_lone_child(stmt, parent)) {
// If removing this node would lead to an invalid syntax tree, replace
// it with a `pass`.
Edit::range_replacement("pass".to_string(), stmt.range())
} else {
if let Some(semicolon) = trailing_semicolon(stmt.end(), locator) {
let next = next_stmt_break(semicolon, locator);
Edit::deletion(stmt.start(), next)
} else if has_leading_content(stmt.start(), locator) {
Edit::range_deletion(stmt.range())
} else if let Some(start) = indexer.preceded_by_continuations(stmt.start(), locator) {
Edit::deletion(start, stmt.end())
} else {
let range = locator.full_lines_range(stmt.range());
Edit::range_deletion(range)
}
}
}
/// Generate a [`Edit`] to delete a comment (for example: a `noqa` directive).
pub(crate) fn delete_comment(range: TextRange, locator: &Locator) -> Edit {
let line_range = locator.line_range(range.start());
// Compute the leading space.
let prefix = locator.slice(TextRange::new(line_range.start(), range.start()));
let leading_space_len = prefix.text_len() - prefix.trim_whitespace_end().text_len();
// Compute the trailing space.
let suffix = locator.slice(TextRange::new(range.end(), line_range.end()));
let trailing_space_len = suffix.text_len() - suffix.trim_whitespace_start().text_len();
// Ex) `# noqa`
if line_range
== TextRange::new(
range.start() - leading_space_len,
range.end() + trailing_space_len,
)
{
let full_line_end = locator.full_line_end(line_range.end());
Edit::deletion(line_range.start(), full_line_end)
}
// Ex) `x = 1 # noqa`
else if range.end() + trailing_space_len == line_range.end() {
Edit::deletion(range.start() - leading_space_len, line_range.end())
}
// Ex) `x = 1 # noqa # type: ignore`
else if locator
.slice(TextRange::new(
range.end() + trailing_space_len,
line_range.end(),
))
.starts_with('#')
{
Edit::deletion(range.start(), range.end() + trailing_space_len)
}
// Ex) `x = 1 # noqa here`
else {
Edit::deletion(
range.start() + "# ".text_len(),
range.end() + trailing_space_len,
)
}
}
/// Generate a `Fix` to remove the specified imports from an `import` statement.
pub(crate) fn remove_unused_imports<'a>(
member_names: impl Iterator<Item = &'a str>,
stmt: &Stmt,
parent: Option<&Stmt>,
locator: &Locator,
stylist: &Stylist,
indexer: &Indexer,
) -> Result<Edit> {
match codemods::remove_imports(member_names, stmt, locator, stylist)? {
None => Ok(delete_stmt(stmt, parent, locator, indexer)),
Some(content) => Ok(Edit::range_replacement(content, stmt.range())),
}
}
#[derive(Debug, Copy, Clone)]
pub(crate) enum Parentheses {
/// Remove parentheses, if the removed argument is the only argument left.
Remove,
/// Preserve parentheses, even if the removed argument is the only argument
Preserve,
}
/// Generic function to remove arguments or keyword arguments in function
/// calls and class definitions. (For classes `args` should be considered
/// `bases`)
///
/// Supports the removal of parentheses when this is the only (kw)arg left.
/// For this behavior, set `remove_parentheses` to `true`.
pub(crate) fn remove_argument<T: Ranged>(
argument: &T,
arguments: &Arguments,
parentheses: Parentheses,
source: &str,
) -> Result<Edit> {
// Partition into arguments before and after the argument to remove.
let (before, after): (Vec<_>, Vec<_>) = arguments
.arguments_source_order()
.map(|arg| arg.range())
.filter(|range| argument.range() != *range)
.partition(|range| range.start() < argument.start());
if !after.is_empty() {
// Case 1: argument or keyword is _not_ the last node, so delete from the start of the
// argument to the end of the subsequent comma.
let mut tokenizer = SimpleTokenizer::starts_at(argument.end(), source);
// Find the trailing comma.
tokenizer
.find(|token| token.kind == SimpleTokenKind::Comma)
.context("Unable to find trailing comma")?;
// Find the next non-whitespace token.
let next = tokenizer
.find(|token| {
token.kind != SimpleTokenKind::Whitespace && token.kind != SimpleTokenKind::Newline
})
.context("Unable to find next token")?;
Ok(Edit::deletion(argument.start(), next.start()))
} else if let Some(previous) = before.iter().map(Ranged::end).max() {
// Case 2: argument or keyword is the last node, so delete from the start of the
// previous comma to the end of the argument.
let mut tokenizer = SimpleTokenizer::starts_at(previous, source);
// Find the trailing comma.
let comma = tokenizer
.find(|token| token.kind == SimpleTokenKind::Comma)
.context("Unable to find trailing comma")?;
Ok(Edit::deletion(comma.start(), argument.end()))
} else {
// Case 3: argument or keyword is the only node, so delete the arguments (but preserve
// parentheses, if needed).
Ok(match parentheses {
Parentheses::Remove => Edit::range_deletion(arguments.range()),
Parentheses::Preserve => Edit::range_replacement("()".to_string(), arguments.range()),
})
}
}
/// Generic function to add arguments or keyword arguments to function calls.
pub(crate) fn add_argument(
argument: &str,
arguments: &Arguments,
comment_ranges: &CommentRanges,
source: &str,
) -> Edit {
if let Some(last) = arguments.arguments_source_order().last() {
// Case 1: existing arguments, so append after the last argument.
let last = parenthesized_range(
match last {
ArgOrKeyword::Arg(arg) => arg.into(),
ArgOrKeyword::Keyword(keyword) => (&keyword.value).into(),
},
arguments.into(),
comment_ranges,
source,
)
.unwrap_or(last.range());
Edit::insertion(format!(", {argument}"), last.end())
} else {
// Case 2: no arguments. Add argument, without any trailing comma.
Edit::insertion(argument.to_string(), arguments.start() + TextSize::from(1))
}
}
/// Safely adjust the indentation of the indented block at [`TextRange`].
///
/// The [`TextRange`] is assumed to represent an entire indented block, including the leading
/// indentation of that block. For example, to dedent the body here:
/// ```python
/// if True:
/// print("Hello, world!")
/// ```
///
/// The range would be the entirety of ` print("Hello, world!")`.
pub(crate) fn adjust_indentation(
range: TextRange,
indentation: &str,
locator: &Locator,
indexer: &Indexer,
stylist: &Stylist,
) -> Result<String> {
// If the range includes a multi-line string, use LibCST to ensure that we don't adjust the
// whitespace _within_ the string.
if indexer.multiline_ranges().intersects(range) || indexer.fstring_ranges().intersects(range) {
let contents = locator.slice(range);
let module_text = format!("def f():{}{contents}", stylist.line_ending().as_str());
let mut tree = match_statement(&module_text)?;
let embedding = match_function_def(&mut tree)?;
let indented_block = match_indented_block(&mut embedding.body)?;
indented_block.indent = Some(indentation);
let module_text = indented_block.codegen_stylist(stylist);
let module_text = module_text
.strip_prefix(stylist.line_ending().as_str())
.unwrap()
.to_string();
Ok(module_text)
} else {
// Otherwise, we can do a simple adjustment ourselves.
let contents = locator.slice(range);
Ok(dedent_to(contents, indentation))
}
}
/// Determine if a vector contains only one, specific element.
fn is_only<T: PartialEq>(vec: &[T], value: &T) -> bool {
vec.len() == 1 && vec[0] == *value
}
/// Determine if a child is the only statement in its body.
fn is_lone_child(child: &Stmt, parent: &Stmt) -> bool {
match parent {
Stmt::FunctionDef(ast::StmtFunctionDef { body, .. })
| Stmt::ClassDef(ast::StmtClassDef { body, .. })
| Stmt::With(ast::StmtWith { body, .. }) => {
if is_only(body, child) {
return true;
}
}
Stmt::For(ast::StmtFor { body, orelse, .. })
| Stmt::While(ast::StmtWhile { body, orelse, .. }) => {
if is_only(body, child) || is_only(orelse, child) {
return true;
}
}
Stmt::If(ast::StmtIf {
body,
elif_else_clauses,
..
}) => {
if is_only(body, child)
|| elif_else_clauses
.iter()
.any(|ast::ElifElseClause { body, .. }| is_only(body, child))
{
return true;
}
}
Stmt::Try(ast::StmtTry {
body,
handlers,
orelse,
finalbody,
..
}) => {
if is_only(body, child)
|| is_only(orelse, child)
|| is_only(finalbody, child)
|| handlers.iter().any(|handler| match handler {
ExceptHandler::ExceptHandler(ast::ExceptHandlerExceptHandler {
body, ..
}) => is_only(body, child),
})
{
return true;
}
}
Stmt::Match(ast::StmtMatch { cases, .. }) => {
if cases.iter().any(|case| is_only(&case.body, child)) {
return true;
}
}
_ => {}
}
false
}
/// Return the location of a trailing semicolon following a `Stmt`, if it's part
/// of a multi-statement line.
fn trailing_semicolon(offset: TextSize, locator: &Locator) -> Option<TextSize> {
let contents = locator.after(offset);
for line in NewlineWithTrailingNewline::from(contents) {
let trimmed = line.trim_whitespace_start();
if trimmed.starts_with(';') {
let colon_offset = line.text_len() - trimmed.text_len();
return Some(offset + line.start() + colon_offset);
}
if !trimmed.starts_with('\\') {
break;
}
}
None
}
/// Find the next valid break for a `Stmt` after a semicolon.
fn next_stmt_break(semicolon: TextSize, locator: &Locator) -> TextSize {
let start_location = semicolon + TextSize::from(1);
for line in
NewlineWithTrailingNewline::with_offset(locator.after(start_location), start_location)
{
let trimmed = line.trim_whitespace();
// Skip past any continuations.
if trimmed.starts_with('\\') {
continue;
}
return if trimmed.is_empty() {
// If the line is empty, then despite the previous statement ending in a
// semicolon, we know that it's not a multi-statement line.
line.start()
} else {
// Otherwise, find the start of the next statement. (Or, anything that isn't
// whitespace.)
let relative_offset = line.find(|c: char| !is_python_whitespace(c)).unwrap();
line.start() + TextSize::try_from(relative_offset).unwrap()
};
}
locator.line_end(start_location)
}
/// Add leading whitespace to a snippet, if it's immediately preceded an identifier or keyword.
pub(crate) fn pad_start(mut content: String, start: TextSize, locator: &Locator) -> String {
// Ex) When converting `except(ValueError,)` from a tuple to a single argument, we need to
// insert a space before the fix, to achieve `except ValueError`.
if locator
.up_to(start)
.chars()
.last()
.is_some_and(|char| char.is_ascii_alphabetic())
{
content.insert(0, ' ');
}
content
}
/// Add trailing whitespace to a snippet, if it's immediately followed by an identifier or keyword.
pub(crate) fn pad_end(mut content: String, end: TextSize, locator: &Locator) -> String {
if locator
.after(end)
.chars()
.next()
.is_some_and(|char| char.is_ascii_alphabetic())
{
content.push(' ');
}
content
}
/// Add leading or trailing whitespace to a snippet, if it's immediately preceded or followed by
/// an identifier or keyword.
pub(crate) fn pad(content: String, range: TextRange, locator: &Locator) -> String {
pad_start(
pad_end(content, range.end(), locator),
range.start(),
locator,
)
}
/// Returns `true` if the fix fits within the maximum configured line length.
pub(crate) fn fits(
fix: &str,
node: AnyNodeRef,
locator: &Locator,
line_length: LineLength,
tab_size: IndentWidth,
) -> bool {
all_lines_fit(fix, node, locator, line_length.value() as usize, tab_size)
}
/// Returns `true` if all lines in the fix are shorter than the given line length.
fn all_lines_fit(
fix: &str,
node: AnyNodeRef,
locator: &Locator,
line_length: usize,
tab_size: IndentWidth,
) -> bool {
let prefix = locator.slice(TextRange::new(
locator.line_start(node.start()),
node.start(),
));
// Ensure that all lines are shorter than the line length limit.
fix.universal_newlines().enumerate().all(|(idx, line)| {
// If `template` is a multiline string, `col_offset` should only be applied to the first
// line:
// ```
// a = """{} -> offset = col_offset (= 4)
// {} -> offset = 0
// """.format(0, 1) -> offset = 0
// ```
let measured_length = if idx == 0 {
LineWidthBuilder::new(tab_size)
.add_str(prefix)
.add_str(&line)
.get()
} else {
LineWidthBuilder::new(tab_size).add_str(&line).get()
};
measured_length <= line_length
})
}
#[cfg(test)]
mod tests {
use anyhow::Result;
use ruff_python_parser::parse_suite;
use ruff_source_file::Locator;
use ruff_text_size::{Ranged, TextSize};
use crate::fix::edits::{next_stmt_break, trailing_semicolon};
#[test]
fn find_semicolon() -> Result<()> {
let contents = "x = 1";
let program = parse_suite(contents)?;
let stmt = program.first().unwrap();
let locator = Locator::new(contents);
assert_eq!(trailing_semicolon(stmt.end(), &locator), None);
let contents = "x = 1; y = 1";
let program = parse_suite(contents)?;
let stmt = program.first().unwrap();
let locator = Locator::new(contents);
assert_eq!(
trailing_semicolon(stmt.end(), &locator),
Some(TextSize::from(5))
);
let contents = "x = 1 ; y = 1";
let program = parse_suite(contents)?;
let stmt = program.first().unwrap();
let locator = Locator::new(contents);
assert_eq!(
trailing_semicolon(stmt.end(), &locator),
Some(TextSize::from(6))
);
let contents = r"
x = 1 \
; y = 1
"
.trim();
let program = parse_suite(contents)?;
let stmt = program.first().unwrap();
let locator = Locator::new(contents);
assert_eq!(
trailing_semicolon(stmt.end(), &locator),
Some(TextSize::from(10))
);
Ok(())
}
#[test]
fn find_next_stmt_break() {
let contents = "x = 1; y = 1";
let locator = Locator::new(contents);
assert_eq!(
next_stmt_break(TextSize::from(4), &locator),
TextSize::from(5)
);
let contents = "x = 1 ; y = 1";
let locator = Locator::new(contents);
assert_eq!(
next_stmt_break(TextSize::from(5), &locator),
TextSize::from(6)
);
let contents = r"
x = 1 \
; y = 1
"
.trim();
let locator = Locator::new(contents);
assert_eq!(
next_stmt_break(TextSize::from(10), &locator),
TextSize::from(12)
);
}
}