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
|
//===--- TokenAnnotator.h - Format C++ code ---------------------*- C++ -*-===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
///
/// \file
/// This file implements a token annotator, i.e. creates
/// \c AnnotatedTokens out of \c FormatTokens with required extra information.
///
//===----------------------------------------------------------------------===//
#ifndef LLVM_CLANG_LIB_FORMAT_TOKENANNOTATOR_H
#define LLVM_CLANG_LIB_FORMAT_TOKENANNOTATOR_H
#include "UnwrappedLineParser.h"
namespace clang {
namespace format {
enum LineType {
LT_Invalid,
// Contains public/private/protected followed by TT_InheritanceColon.
LT_AccessModifier,
LT_ImportStatement,
LT_ObjCDecl, // An @interface, @implementation, or @protocol line.
LT_ObjCMethodDecl,
LT_ObjCProperty, // An @property line.
LT_Other,
LT_PreprocessorDirective,
LT_VirtualFunctionDecl,
LT_ArrayOfStructInitializer,
LT_CommentAbovePPDirective,
};
enum ScopeType {
// Contained in class declaration/definition.
ST_Class,
// Contained within function definition.
ST_Function,
// Contained within other scope block (loop, if/else, etc).
ST_Other,
};
class AnnotatedLine {
public:
AnnotatedLine(const UnwrappedLine &Line)
: First(Line.Tokens.front().Tok), Type(LT_Other), Level(Line.Level),
PPLevel(Line.PPLevel),
MatchingOpeningBlockLineIndex(Line.MatchingOpeningBlockLineIndex),
MatchingClosingBlockLineIndex(Line.MatchingClosingBlockLineIndex),
InPPDirective(Line.InPPDirective),
InPragmaDirective(Line.InPragmaDirective),
InMacroBody(Line.InMacroBody),
MustBeDeclaration(Line.MustBeDeclaration), MightBeFunctionDecl(false),
IsMultiVariableDeclStmt(false), Affected(false),
LeadingEmptyLinesAffected(false), ChildrenAffected(false),
ReturnTypeWrapped(false), IsContinuation(Line.IsContinuation),
FirstStartColumn(Line.FirstStartColumn) {
assert(!Line.Tokens.empty());
// Calculate Next and Previous for all tokens. Note that we must overwrite
// Next and Previous for every token, as previous formatting runs might have
// left them in a different state.
First->Previous = nullptr;
FormatToken *Current = First;
addChildren(Line.Tokens.front(), Current);
for (const UnwrappedLineNode &Node : llvm::drop_begin(Line.Tokens)) {
if (Node.Tok->MacroParent)
ContainsMacroCall = true;
Current->Next = Node.Tok;
Node.Tok->Previous = Current;
Current = Current->Next;
addChildren(Node, Current);
// FIXME: if we add children, previous will point to the token before
// the children; changing this requires significant changes across
// clang-format.
}
Last = Current;
Last->Next = nullptr;
}
void addChildren(const UnwrappedLineNode &Node, FormatToken *Current) {
Current->Children.clear();
for (const auto &Child : Node.Children) {
Children.push_back(new AnnotatedLine(Child));
if (Children.back()->ContainsMacroCall)
ContainsMacroCall = true;
Current->Children.push_back(Children.back());
}
}
size_t size() const {
size_t Size = 1;
for (const auto *Child : Children)
Size += Child->size();
return Size;
}
~AnnotatedLine() {
for (AnnotatedLine *Child : Children)
delete Child;
FormatToken *Current = First;
while (Current) {
Current->Children.clear();
Current->Role.reset();
Current = Current->Next;
}
}
bool isComment() const {
return First && First->is(tok::comment) && !First->getNextNonComment();
}
/// \c true if this line starts with the given tokens in order, ignoring
/// comments.
template <typename... Ts> bool startsWith(Ts... Tokens) const {
return First && First->startsSequence(Tokens...);
}
/// \c true if this line ends with the given tokens in reversed order,
/// ignoring comments.
/// For example, given tokens [T1, T2, T3, ...], the function returns true if
/// this line is like "... T3 T2 T1".
template <typename... Ts> bool endsWith(Ts... Tokens) const {
return Last && Last->endsSequence(Tokens...);
}
/// \c true if this line looks like a function definition instead of a
/// function declaration. Asserts MightBeFunctionDecl.
bool mightBeFunctionDefinition() const {
assert(MightBeFunctionDecl);
// Try to determine if the end of a stream of tokens is either the
// Definition or the Declaration for a function. It does this by looking for
// the ';' in foo(); and using that it ends with a ; to know this is the
// Definition, however the line could end with
// foo(); /* comment */
// or
// foo(); // comment
// or
// foo() // comment
// endsWith() ignores the comment.
return !endsWith(tok::semi);
}
/// \c true if this line starts a namespace definition.
bool startsWithNamespace() const {
return startsWith(tok::kw_namespace) || startsWith(TT_NamespaceMacro) ||
startsWith(tok::kw_inline, tok::kw_namespace) ||
startsWith(tok::kw_export, tok::kw_namespace);
}
FormatToken *getFirstNonComment() const {
assert(First);
return First->is(tok::comment) ? First->getNextNonComment() : First;
}
FormatToken *getLastNonComment() const {
assert(Last);
return Last->is(tok::comment) ? Last->getPreviousNonComment() : Last;
}
FormatToken *First;
FormatToken *Last;
SmallVector<AnnotatedLine *, 0> Children;
LineType Type;
unsigned Level;
unsigned PPLevel;
size_t MatchingOpeningBlockLineIndex;
size_t MatchingClosingBlockLineIndex;
bool InPPDirective;
bool InPragmaDirective;
bool InMacroBody;
bool MustBeDeclaration;
bool MightBeFunctionDecl;
bool IsMultiVariableDeclStmt;
/// \c True if this line contains a macro call for which an expansion exists.
bool ContainsMacroCall = false;
/// \c True if this line should be formatted, i.e. intersects directly or
/// indirectly with one of the input ranges.
bool Affected;
/// \c True if the leading empty lines of this line intersect with one of the
/// input ranges.
bool LeadingEmptyLinesAffected;
/// \c True if one of this line's children intersects with an input range.
bool ChildrenAffected;
/// \c True if breaking after last attribute group in function return type.
bool ReturnTypeWrapped;
/// \c True if this line should be indented by ContinuationIndent in addition
/// to the normal indention level.
bool IsContinuation;
unsigned FirstStartColumn;
private:
// Disallow copying.
AnnotatedLine(const AnnotatedLine &) = delete;
void operator=(const AnnotatedLine &) = delete;
};
/// Determines extra information about the tokens comprising an
/// \c UnwrappedLine.
class TokenAnnotator {
public:
TokenAnnotator(const FormatStyle &Style, const AdditionalKeywords &Keywords)
: Style(Style), IsCpp(Style.isCpp()),
LangOpts(getFormattingLangOpts(Style)), Keywords(Keywords) {
assert(IsCpp == LangOpts.CXXOperatorNames);
}
/// Adapts the indent levels of comment lines to the indent of the
/// subsequent line.
// FIXME: Can/should this be done in the UnwrappedLineParser?
void setCommentLineLevels(SmallVectorImpl<AnnotatedLine *> &Lines) const;
void annotate(AnnotatedLine &Line);
void calculateFormattingInformation(AnnotatedLine &Line) const;
private:
/// Calculate the penalty for splitting before \c Tok.
unsigned splitPenalty(const AnnotatedLine &Line, const FormatToken &Tok,
bool InFunctionDecl) const;
bool spaceRequiredBeforeParens(const FormatToken &Right) const;
bool spaceRequiredBetween(const AnnotatedLine &Line, const FormatToken &Left,
const FormatToken &Right) const;
bool spaceRequiredBefore(const AnnotatedLine &Line,
const FormatToken &Right) const;
bool mustBreakBefore(const AnnotatedLine &Line,
const FormatToken &Right) const;
bool canBreakBefore(const AnnotatedLine &Line,
const FormatToken &Right) const;
bool mustBreakForReturnType(const AnnotatedLine &Line) const;
void printDebugInfo(const AnnotatedLine &Line) const;
void calculateUnbreakableTailLengths(AnnotatedLine &Line) const;
void calculateArrayInitializerColumnList(AnnotatedLine &Line) const;
FormatToken *calculateInitializerColumnList(AnnotatedLine &Line,
FormatToken *CurrentToken,
unsigned Depth) const;
FormatStyle::PointerAlignmentStyle
getTokenReferenceAlignment(const FormatToken &PointerOrReference) const;
FormatStyle::PointerAlignmentStyle getTokenPointerOrReferenceAlignment(
const FormatToken &PointerOrReference) const;
const FormatStyle &Style;
bool IsCpp;
LangOptions LangOpts;
const AdditionalKeywords &Keywords;
SmallVector<ScopeType> Scopes;
};
} // end namespace format
} // end namespace clang
#endif
|