Comparing changes

RustPython/RustPython#4426 has been merged. We can simplify code using text in comment tokens.

Ref #998 Co-authored-by: Charlie Marsh <charlie.r.marsh@gmail.com>

For every available rule registry.rs currently defines: 1. A CheckCode variant to identify the rule. 2. A CheckKind variant to represent violations of the rule. 3. A mapping from the CheckCode variant to a placeholder CheckKind instance. 4. A mapping from the CheckKind variant to CheckCode. 5. A mapping from the CheckKind to a string description. 6. A mapping from the CheckKind to a boolean indicating if autofix is available. 7. A mapping from the CheckKind to a string describing the autofix if available. Since registry.rs defines all of this for every single rule and ruff has hundreds of rules, this results in the lines specific to a particular rule to be hundreds of lines apart, making the code cumbersome to read and edit. This commit introduces a new Violation trait so that the rule-specific details of the above steps 5.-7. can be defined next to the rule implementation. The idea is that once all CheckCode/CheckKind variants have been converted to this new approach then the steps 1.-4. in registry.rs could simply be generated via a declarative macro, e.g: define_rule_mapping!( E501 => pycodestyle::LineTooLong, ... ); (where `pycodestyle::LineTooLong` would be a struct that implements the new Violation trait). The define_rule_mapping! macro would then take care of generating the CheckCode and CheckKind enums, as well as all of the implementations for the previously mentioned mappings, by simply calling the methods of the new Violation trait. There is another nice benefit from this approach: We want to introduce more thorough documentation for rules and we want the documentation of a rule to be defined close by the implementation (so that it's easier to check if they match and that they're less likely to become out of sync). Since these new Violation structs can be defined close by the implementation of a rule we can also use them as an anchor point for the documentation of a rule by simply adding the documentation in the form of a Rust doc comment to the struct.

# The changes of this commit were generated using the following code: # (followed by cargo +nightly fmt) import re import subprocess import io indent = ' ' * 4 def split_words(s): return re.split(r'\b', s) def checkkind_match_arms(f, strip_some=False): bodies = {} while (line := next(f).rstrip()) != indent * 2 + '}': if line.lstrip().startswith('//'): continue if line.strip() == '': continue parts = line.split('=>', maxsplit=1) if parts[0].strip() == '_': break left, body = parts left = left.strip() body = body.strip() if body == '{': body = '' while (line := next(f).rstrip()) != indent * 3 + '}': body += line + '\n' else: body = body.rstrip(',') kind = split_words(left)[3] if strip_some: body = re.sub('\)$', '', re.sub(r'Some\(', '', body, 1).rstrip(), 1) if ('(' in left and not '(..)' in left) or '{' in left: body = ( 'let ' + left.replace('CheckKind::', '').replace('CheckCode::', '') + ' = self;\n' + body ) bodies[kind] = body return bodies with open('src/registry.rs') as f: orig_registry_code = f.read() # simplify the parsing of multiline match arms registry_code = subprocess.check_output( ['rustfmt', '+nightly', '--config', 'force_multiline_blocks=true'], encoding='utf-8', input=orig_registry_code, ) f = io.StringIO(registry_code) # 1. Parse the CheckCode enum while next(f).strip() != 'pub enum CheckCode {': pass checkcode_lines = [] while (line := next(f).strip().rstrip(',')) != '}': checkcode_lines.append(line) # 2. Parse the CheckKind enum while next(f).strip() != 'pub enum CheckKind {': pass struct_defs = {} while (line := next(f).strip()) != '}': if line.startswith('//'): continue line = line.rstrip(',') line = re.sub(r'{', '{ pub ', line) line = re.sub(r'\(', '(pub ', line) line = re.sub(',', ', pub', line) kind = split_words(line)[1] struct_defs[kind] = 'pub struct ' + line + (';' * (line[-1] != '}')) # 3. parse the kind() impl for CheckKind while next(f).rstrip() != " pub fn kind(&self) -> CheckKind {": pass assert next(f).strip() == 'match self {' placeholders = checkkind_match_arms(f) # 4. parse the CheckKind -> CheckCode mapping while next(f).strip() != "pub fn code(&self) -> &'static CheckCode {": pass assert next(f).strip() == 'match self {' kind2code = {} while (line := next(f).strip().rstrip(',')) != '}': if line.startswith('//'): continue parts = re.split(r'\b', line) kind2code[parts[3]] = parts[-2] code2kind = {code: kind for kind, code in kind2code.items()} # 5. parse the body() impl for CheckKind while next(f).rstrip() != " pub fn body(&self) -> String {": pass assert next(f).strip() == 'match self {' bodies = checkkind_match_arms(f) # 6. find fixable always_fixable = [] sometimes_fixable = [] while next(f).strip() != "// Always-fixable checks.": pass while (line := next(f).strip()) != '// Conditionally-fixable checks.': always_fixable.append(split_words(line)[3]) while (line := next(f).strip()) != '// Non-fixable checks.': sometimes_fixable.append(split_words(line)[3]) # 7. find autofix message while next(f).rstrip() != indent + "pub fn commit(&self) -> Option<String> {": pass assert next(f).strip() == 'match self {' autofix_msg = checkkind_match_arms(f, strip_some=True) reg = '''\ macro_rules! define_rule_mapping { ($($code:ident => $mod:ident::$name:ident,)+) => { // TODO: implement }; } define_rule_mapping!( ''' for line in checkcode_lines: if line.startswith('//'): reg += indent + line + '\n' continue code = line reg += indent + code + ' => violations::' + code2kind[code] + ',\n' reg += ');\n\n' with open('src/registry.rs', 'w') as f: marker = '#[derive' f.write(orig_registry_code.replace(marker, reg + marker, 1)) out = '''\ use itertools::Itertools; use crate::define_violation; use crate::flake8_debugger::types::DebuggerUsingType; use crate::flake8_pytest_style::types::{ParametrizeNameType, ParametrizeValuesType, ParametrizeValuesRowType}; use crate::flake8_quotes::settings::Quote; use crate::flake8_tidy_imports::settings::Strictness; use crate::pyupgrade::types::Primitive; use crate::registry::{ Branch, DeferralKeyword, EqCmpop, IsCmpop, LiteralType, MockReference, UnusedCodes, }; use crate::violation::{AlwaysAutofixableViolation, Violation}; ''' for line in checkcode_lines: if line.startswith('//'): out += '\n' + line + '\n\n' continue code = line kind = code2kind[code] out += 'define_violation!(' + struct_defs[kind] + ');\n' if kind in always_fixable: out += f'impl AlwaysAutofixableViolation for {kind} {{\n' else: out += f'impl Violation for {kind} {{\n' out += 'fn message(&self) -> String {' out += bodies[kind] out += '}' if kind in always_fixable: out += 'fn autofix_title(&self) -> String {' out += autofix_msg[kind] out += '}' elif kind in sometimes_fixable: out += 'fn autofix_title_formatter(&self) -> Option<fn(&Self) -> String> {' out += 'todo!()' out += '}' out += 'fn placeholder() -> Self {' out += placeholders[code].replace('CheckKind::', '') out += '}' out += '}\n\n' with open('src/violations.rs', 'w') as f: f.write(out) with open('src/lib.rs', 'r') as f: mod = f.read() with open('src/lib.rs', 'w') as f: marker = 'mod violation;' f.write(mod.replace(marker, marker + '\nmod violations;'))

…ofixes

The changes in this commit were generated by running: for f in $(find src -name '*.rs'); do sed -Ei 's/use crate::registry::.*;/\0use crate::violations;/g' $f; done for f in $(find src -name '*.rs'); do sed -Ei 's/CheckKind::([A-Z])/violations::\1/g' $f; done git checkout src/registry.rs src/lib.rs src/lib_wasm.rs src/violations.rs cargo +nightly fmt

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Comparing changes

Open a pull request

Commits on Jan 7, 2023

This comparison is taking too long to generate.