diff options
author | Krasimir Georgiev <krasimir@google.com> | 2017-08-30 14:34:57 +0000 |
---|---|---|
committer | Krasimir Georgiev <krasimir@google.com> | 2017-08-30 14:34:57 +0000 |
commit | ad47c907670669c7f5af732f25ccf16d40c9f4d4 (patch) | |
tree | 3d19120e78857dc8423f00ecff9158ae4ddc2c0b /clang/lib/Format/UnwrappedLineParser.cpp | |
parent | 24aafa57992c1cd787602fb351e2d1a1be4649eb (diff) | |
download | bcm5719-llvm-ad47c907670669c7f5af732f25ccf16d40c9f4d4.tar.gz bcm5719-llvm-ad47c907670669c7f5af732f25ccf16d40c9f4d4.zip |
clang-format: Add preprocessor directive indentation
Summary:
This is an implementation for [bug 17362](https://bugs.llvm.org/attachment.cgi?bugid=17362) which adds support for indenting preprocessor statements inside if/ifdef/endif. This takes previous work from fmauch (https://github.com/fmauch/clang/tree/preprocessor_indent) and makes it into a full feature.
The context of this patch is that I'm a VMware intern, and I implemented this because VMware needs the feature. As such, some decisions were made based on what VMware wants, and I would appreciate suggestions on expanding this if necessary to use-cases other people may want.
This adds a new enum config option, `IndentPPDirectives`. Values are:
* `PPDIS_None` (in config: `None`):
```
#if FOO
#if BAR
#include <foo>
#endif
#endif
```
* `PPDIS_AfterHash` (in config: `AfterHash`):
```
#if FOO
# if BAR
# include <foo>
# endif
#endif
```
This is meant to work whether spaces or tabs are used for indentation. Preprocessor indentation is independent of indentation for non-preprocessor lines.
Preprocessor indentation also attempts to ignore include guards with the checks:
1. Include guards cover the entire file
2. Include guards don't have `#else`
3. Include guards begin with
```
#ifndef <var>
#define <var>
```
This patch allows `UnwrappedLineParser::PPBranchLevel` to be decremented to -1 (the initial value is -1) so the variable can be used for indent tracking.
Defects:
* This patch does not handle the case where there's code between the `#ifndef` and `#define` but all other conditions hold. This is because when the #define line is parsed, `UnwrappedLineParser::Lines` doesn't hold the previous code line yet, so we can't detect it. This is out of the scope of this patch.
* This patch does not handle cases where legitimate lines may be outside an include guard. Examples are `#pragma once` and `#pragma GCC diagnostic`, or anything else that does not change the meaning of the file if it's included multiple times.
* This does not detect when there is a single non-preprocessor line in front of an include-guard-like structure where other conditions hold because `ScopedLineState` hides the line.
* Preprocessor indentation throws off `TokenAnnotator::setCommentLineLevels` so the indentation of comments immediately before indented preprocessor lines is toggled on each run. Fixing this issue appears to be a major change and too much complexity for this patch.
Contributed by @euhlmann!
Reviewers: djasper, klimek, krasimir
Reviewed By: djasper, krasimir
Subscribers: krasimir, mzeren-vmw, cfe-commits
Tags: #clang
Differential Revision: https://reviews.llvm.org/D35955
llvm-svn: 312125
Diffstat (limited to 'clang/lib/Format/UnwrappedLineParser.cpp')
-rw-r--r-- | clang/lib/Format/UnwrappedLineParser.cpp | 60 |
1 files changed, 57 insertions, 3 deletions
diff --git a/clang/lib/Format/UnwrappedLineParser.cpp b/clang/lib/Format/UnwrappedLineParser.cpp index fdf98839019..c0cb461418b 100644 --- a/clang/lib/Format/UnwrappedLineParser.cpp +++ b/clang/lib/Format/UnwrappedLineParser.cpp @@ -231,10 +231,15 @@ UnwrappedLineParser::UnwrappedLineParser(const FormatStyle &Style, : Line(new UnwrappedLine), MustBreakBeforeNextToken(false), CurrentLines(&Lines), Style(Style), Keywords(Keywords), CommentPragmasRegex(Style.CommentPragmas), Tokens(nullptr), - Callback(Callback), AllTokens(Tokens), PPBranchLevel(-1) {} + Callback(Callback), AllTokens(Tokens), PPBranchLevel(-1), + IfNdefCondition(nullptr), FoundIncludeGuardStart(false), + IncludeGuardRejected(false) {} void UnwrappedLineParser::reset() { PPBranchLevel = -1; + IfNdefCondition = nullptr; + FoundIncludeGuardStart = false; + IncludeGuardRejected = false; Line.reset(new UnwrappedLine); CommentsBeforeNextToken.clear(); FormatTok = nullptr; @@ -679,7 +684,7 @@ void UnwrappedLineParser::conditionalCompilationEnd() { } } // Guard against #endif's without #if. - if (PPBranchLevel > 0) + if (PPBranchLevel > -1) --PPBranchLevel; if (!PPChainBranchIndex.empty()) PPChainBranchIndex.pop(); @@ -696,12 +701,35 @@ void UnwrappedLineParser::parsePPIf(bool IfDef) { if (IfDef && !IfNDef && FormatTok->TokenText == "SWIG") Unreachable = true; conditionalCompilationStart(Unreachable); + FormatToken *IfCondition = FormatTok; + // If there's a #ifndef on the first line, and the only lines before it are + // comments, it could be an include guard. + bool MaybeIncludeGuard = IfNDef; + if (!IncludeGuardRejected && !FoundIncludeGuardStart && MaybeIncludeGuard) { + for (auto &Line : Lines) { + if (!Line.Tokens.front().Tok->is(tok::comment)) { + MaybeIncludeGuard = false; + IncludeGuardRejected = true; + break; + } + } + } + --PPBranchLevel; parsePPUnknown(); + ++PPBranchLevel; + if (!IncludeGuardRejected && !FoundIncludeGuardStart && MaybeIncludeGuard) + IfNdefCondition = IfCondition; } void UnwrappedLineParser::parsePPElse() { + // If a potential include guard has an #else, it's not an include guard. + if (FoundIncludeGuardStart && PPBranchLevel == 0) + FoundIncludeGuardStart = false; conditionalCompilationAlternative(); + if (PPBranchLevel > -1) + --PPBranchLevel; parsePPUnknown(); + ++PPBranchLevel; } void UnwrappedLineParser::parsePPElIf() { parsePPElse(); } @@ -709,6 +737,17 @@ void UnwrappedLineParser::parsePPElIf() { parsePPElse(); } void UnwrappedLineParser::parsePPEndIf() { conditionalCompilationEnd(); parsePPUnknown(); + // If the #endif of a potential include guard is the last thing in the file, + // then we count it as a real include guard and subtract one from every + // preprocessor indent. + unsigned TokenPosition = Tokens->getPosition(); + FormatToken *PeekNext = AllTokens[TokenPosition]; + if (FoundIncludeGuardStart && PPBranchLevel == -1 && PeekNext->is(tok::eof)) { + for (auto &Line : Lines) { + if (Line.InPPDirective && Line.Level > 0) + --Line.Level; + } + } } void UnwrappedLineParser::parsePPDefine() { @@ -718,14 +757,26 @@ void UnwrappedLineParser::parsePPDefine() { parsePPUnknown(); return; } + if (IfNdefCondition && IfNdefCondition->TokenText == FormatTok->TokenText) { + FoundIncludeGuardStart = true; + for (auto &Line : Lines) { + if (!Line.Tokens.front().Tok->isOneOf(tok::comment, tok::hash)) { + FoundIncludeGuardStart = false; + break; + } + } + } + IfNdefCondition = nullptr; nextToken(); if (FormatTok->Tok.getKind() == tok::l_paren && FormatTok->WhitespaceRange.getBegin() == FormatTok->WhitespaceRange.getEnd()) { parseParens(); } + if (Style.IndentPPDirectives == FormatStyle::PPDIS_AfterHash) + Line->Level += PPBranchLevel + 1; addUnwrappedLine(); - Line->Level = 1; + ++Line->Level; // Errors during a preprocessor directive can only affect the layout of the // preprocessor directive, and thus we ignore them. An alternative approach @@ -739,7 +790,10 @@ void UnwrappedLineParser::parsePPUnknown() { do { nextToken(); } while (!eof()); + if (Style.IndentPPDirectives == FormatStyle::PPDIS_AfterHash) + Line->Level += PPBranchLevel + 1; addUnwrappedLine(); + IfNdefCondition = nullptr; } // Here we blacklist certain tokens that are not usually the first token in an |