Commit Graph

428 Commits

Author SHA1 Message Date
Nico Weber 6029d4f3ae Formatter: Remove a fixme klimek fixed in r173168.
Add a few comments to the ObjC test cases.

llvm-svn: 173169
2013-01-22 16:53:59 +00:00
Manuel Klimek f92f7bc540 Implements more principled comment parsing.
Changing nextToken() in the UnwrappedLineParser to get the next
non-comment token. This allows us to correctly layout a whole class of
snippets, like:

if /* */(/* */ a /* */) /* */
  f() /* */; /* */
else /* */
  g();

Fixes a bug in the formatter where we would assume there is a previous
non-comment token.
Also adds the indent level of an unwrapped line to the debug output in
the parser.

llvm-svn: 173168
2013-01-22 16:31:55 +00:00
Daniel Jasper 50e7ab7185 Let the formatter be more restrictive for breaking around . and ->
Before:
aaaaaaaaaaaaaaa(aaaaaaaaa, aaaaaaaaa, aaaaaaaaaaaaaaaaaaaaaaa)
    .aaaaaaaaaaaaaaaaaa();

After:
aaaaaaaaaaaaaaa(aaaaaaaaa, aaaaaaaaa,
                aaaaaaaaaaaaaaaaaaaaaaa).aaaaaaaaaaaaaaaaaa();

llvm-svn: 173160
2013-01-22 14:28:24 +00:00
Daniel Jasper 0b8206029b Fix "*" formatting when creating arrays of pointers.
Before: A = new int * [10]();
After:  A = new int *[10]();
llvm-svn: 173150
2013-01-22 11:46:26 +00:00
Daniel Jasper 304a986a72 Remove "incorrect" aligning of trailing comments.
We used to align trailing comments belong to different things.
Before:
void f() { // some function..
}
int a;     // some variable..

After:
void f() { // some function..
}
int a; // some variable..

llvm-svn: 173100
2013-01-21 22:49:20 +00:00
Manuel Klimek 2cec01916c Fixes various problems around enum parsing.
Very similar to what we do for record definitions:
- tighten down what is an enum definition, so that we don't mistake a
  function for an enum
- allow common idioms around declarations (we'll want to handle that
  more centrally in the future)

We now correctly format:
enum X f() {
  a();
  return 42;
}

llvm-svn: 173075
2013-01-21 19:17:52 +00:00
Manuel Klimek a4fe1c13c0 Fixes formatting of empty blocks.
We now only put empty blocks into a single line, if all of:
- all tokens of the structural element fit into a single line
- we're not in a control flow statement

Note that we usually don't put record definitions into a single line, as
there's usually at least one more token (the semicolon) after the
closing brace. This doesn't hold when we are in a context where there is
no semicolon, like "enum E {}".

There were some missing tests around joining lines around the corner
cases of the allowed number of columns, so this patch adds some.

llvm-svn: 173055
2013-01-21 16:42:44 +00:00
Daniel Jasper c228619bb1 Fix parsing of templated declarations.
Before: template <template <typename T>, typename P > class X;
After:  template <template <typename T>, typename P> class X;

More importantly, the token annotations for the second ">" are now computed
correctly.

llvm-svn: 173047
2013-01-21 14:39:22 +00:00
Manuel Klimek ae610d173d Fixes indent in linkage specification blocks.
We now indent:
extern "C" {
int a;
}

without additional indent inside the extern "C" block.

llvm-svn: 173045
2013-01-21 14:32:05 +00:00
Manuel Klimek d5e782b010 Add regression test.
llvm-svn: 173042
2013-01-21 14:16:56 +00:00
Manuel Klimek cdee74db63 Fixes detection of class template specializations.
Now correctly formats:
template <> class A<int> {} a;

llvm-svn: 173038
2013-01-21 13:58:54 +00:00
Manuel Klimek 3c6b7c7d71 Allow for nested name specifiers in record declarations.
Now correctly formats:
class A::B {} n;

llvm-svn: 173019
2013-01-21 10:17:14 +00:00
Manuel Klimek 762dd189a4 Fix parsing of return statements.
Previously, we would not detect brace initializer lists in return
statements, thus:
 return (a)(b) { 1, 2, 3 };
would put the semicolon onto the next line.

llvm-svn: 173017
2013-01-21 10:07:49 +00:00
Sean Silva f1b49e237f Nuke SetUpBuildDumpLog.
Also, it was the only reason that `argc` and `argv` were being passed
into createDiagnostics, so remove those parameters and clean up callers.

llvm-svn: 172945
2013-01-20 01:58:28 +00:00
Dmitri Gribenko c137ec8b70 Comment parsing: add more tests for html character references
llvm-svn: 172923
2013-01-19 22:04:44 +00:00
Chris Lattner e8d968f31b fix the unit tests too.
llvm-svn: 172907
2013-01-19 18:30:39 +00:00
Chandler Carruth 4b41745e05 Re-sort all the headers. Lots of regressions have crept in here.
Manually fix the order of UnwrappedLineParser.cpp as that one didn't
have its associated header as the first header.

This also uncovered a subtle inclusion order dependency as CLog.h didn't
include LLVM.h to pick up using declarations it relied upon.

llvm-svn: 172892
2013-01-19 08:09:44 +00:00
Manuel Klimek da08761bb2 Fixes issues around pulling in the next line in simple if statements.
llvm-svn: 172822
2013-01-18 14:46:43 +00:00
Manuel Klimek d3b92fa61e Fixes problems with line merging in the face of preprocessor directives.
This patch prepares being able to test for and fix more problems (see
FIXME in the test for example).

Previously we would output unwrapped lines for preprocessor directives
at the point where we also parsed the hash token. Since often
projections only terminate (and thus output their own unwrapped line)
after peeking at the next token, this would lead to the formatter seeing
the preprocessor directives out-of-order (slightly earlier). To be able
to correctly identify lines to merge, the formatter needs a well-defined
order of unwrapped lines, which this patch introduces.

llvm-svn: 172819
2013-01-18 14:04:34 +00:00
Daniel Jasper 04468962ab Reduce penalty for splitting between ")" and ".".
').' is likely part of a builder pattern statement.
This is based upon a patch developed by Nico Weber. Thank you!

Before:
int foo() {
  return llvm::StringSwitch<Reference::Kind>(name).StartsWith(
      ".eh_frame_hdr", ORDER_EH_FRAMEHDR).StartsWith(
      ".eh_frame", ORDER_EH_FRAME).StartsWith(".init", ORDER_INIT).StartsWith(
      ".fini", ORDER_FINI).StartsWith(".hash", ORDER_HASH).Default(ORDER_TEXT);
}

After:
int foo() {
  return llvm::StringSwitch<Reference::Kind>(name)
         .StartsWith(".eh_frame_hdr", ORDER_EH_FRAMEHDR)
         .StartsWith(".eh_frame", ORDER_EH_FRAME)
         .StartsWith(".init", ORDER_INIT).StartsWith(".fini", ORDER_FINI)
         .StartsWith(".hash", ORDER_HASH).Default(ORDER_TEXT);
}

Probably not ideal, but makes many cases much more readable.

The changes to overriding-ftemplate-comments.cpp don't seem better or
worse. We should address those soon.

llvm-svn: 172804
2013-01-18 10:56:38 +00:00
Daniel Jasper 997b08ce3c Also align trailing line comments in include directives.
Before:
  #include <a> // for x
  #include <a/b/c> // for yz
After:
  #include <a>     // for x
  #include <a/b/c> // for yz

llvm-svn: 172799
2013-01-18 09:19:33 +00:00
Daniel Jasper aa701fa3ad Let the formatter align trailing line comments where possible.
Before:
int a; // comment
int bbbbb; // comment

After:
int a;     // comment
int bbbbb; // comment

llvm-svn: 172798
2013-01-18 08:44:07 +00:00
Nico Weber a5510af53e Formatter: After case blocks, "break" goes on the same line as the "}", PR14907.
Before:
switch (foo) {
case a: {
  int a = g();
  h(a);
}
  break;
}

Now:
switch (foo) {
case a: {
  int a = g();
  h(a);
} break;
}

llvm-svn: 172789
2013-01-18 05:50:57 +00:00
Nico Weber e3025672e9 Formatter: Enable @encode test.
This doesn't work right with pointers to pointers, but that's likely just a
dupe of PR14884.

llvm-svn: 172785
2013-01-18 05:11:47 +00:00
Nico Weber 250fe71366 Formatter: The contents of @selector() should be formatted as a selector.
Before: @selector(foo: )
Now: @selector(foo:)
llvm-svn: 172781
2013-01-18 02:43:57 +00:00
Nico Weber 80a82761bd Formatter: Get bit tests in ifs right.
It's generally not possible to know if 'a' '*' 'b' is a multiplication
expression or a variable declaration with a purely lexer-based approach. The
formatter currently uses a heuristic that classifies this token sequence as a
multiplication in rhs contexts (after '=' or 'return') and as a declaration
else.

Because of this, it gets bit tests in ifs, such as "if (a & b)" wrong. However,
declarations in ifs always have to be followed by '=', so this patch changes
the formatter to classify '&' as an operator if it's at the start of an if
statement.

Before:
  if (a& b)
  if (int* b = f())

Now:
  if (a & b)
  if (int* b = f())

llvm-svn: 172731
2013-01-17 17:17:19 +00:00
Daniel Jasper fefb1e6257 Allow breaking after the trailing const after a function declaration.
Before:
void aaaaaaaaaaaa(int aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa) const GUARDED_BY(
    aaaaaaaaaaaaa);

After:
void aaaaaaaaaaaa(int aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa) const
    GUARDED_BY(aaaaaaaaaaaaa);

llvm-svn: 172718
2013-01-17 13:31:52 +00:00
Daniel Jasper 11cb81cd6f Improve handling of comments in static initializers.
Also adding more tests.

We can now keep the formatting of something like:

static SomeType type = { aaaaaaaaaaaaaaaaaaaa, /* comment */
                         aaaaaaaaaaaaaaaaaaaa /* comment */,
                         /* comment */ aaaaaaaaaaaaaaaaaaaa,
                         aaaaaaaaaaaaaaaaaaaa, // comment
                         aaaaaaaaaaaaaaaaaaaa };

Note that the comment in the first line is handled like a trailing line comment
as that is likely what the user intended.

llvm-svn: 172711
2013-01-17 12:53:34 +00:00
Nico Weber 772fbfda45 Revert most of r172140.
r172140 changed the formatter to produce "-(id) foo" instead of "- (id)foo"
in google style, with a link to
http://google-styleguide.googlecode.com/svn/trunk/objcguide.xml#Method_Declarations_and_Definitions
as reference.  But now that I look at that link again, it seems I didn't
read it very carefully the first time round.

llvm-svn: 172703
2013-01-17 06:14:50 +00:00
Daniel Jasper 69987d5415 Fix a bug where we would move a following line into a comment.
Before: Constructor() : a(a), // comment a(a) {}
After:  Constructor() : a(a), // comment
                        a(a) {}

Needed this as a quick fix. Will add more tests for this in a future
commit.

llvm-svn: 172624
2013-01-16 17:00:50 +00:00
Daniel Jasper 8c5fba9f87 Fix parsing error in conditional expressions.
We used to incorrectly parse

aaaaaa ? aaaaaa(aaaaaa) : aaaaaaaa;

Due to an l_paren being followed by a colon, we assumed it to be part of
a constructor initializer. Thus, we never found the colon belonging to
the conditional expression, marked the line as bing incorrect and did
not format it.

llvm-svn: 172621
2013-01-16 16:23:19 +00:00
Daniel Jasper a1dc93a5bd Improve understanding of unary operators.
Before: int x = ** a;
After:  int x = **a;
llvm-svn: 172619
2013-01-16 16:04:06 +00:00
Daniel Jasper ced17f8cd5 Disable inlining of short ifs in Google style.
Various reasons seem to speak against it, so I am disabling this for
now.

Changed tests to still test this option.

llvm-svn: 172618
2013-01-16 15:44:34 +00:00
Daniel Jasper 9278eb95e3 Add option to avoid "bin-packing" of parameters.
"Bin-packing" here means allowing multiple parameters on one line, if a
function call/declaration is spread over multiple lines.

This is required by the Chromium style guide and probably desired for
the Google style guide. Not making changes to LLVM style as I don't have
enough data.

With this enabled, we format stuff like:
aaaaaaaaaaaaaaa(aaaaaaaaaa,
                aaaaaaaaaa,
		aaaaaaaaaaaaaaaaaaaaaaa).aaaaaaaaaaaaaaaaaa();

llvm-svn: 172617
2013-01-16 14:59:02 +00:00
Manuel Klimek 249981040b Add debugging support for split penalties.
llvm-svn: 172616
2013-01-16 14:55:28 +00:00
Alexander Kornienko ae6e53c15d Clang Format: A couple of tests for the trailing stuff case
llvm-svn: 172607
2013-01-16 11:45:16 +00:00
Alexander Kornienko 1231e066a8 Clang Format: Handle missing semicolon
llvm-svn: 172606
2013-01-16 11:43:46 +00:00
Daniel Jasper 736c14fac4 Never merge < and ::, as it produces different tokens.
Before: vector<::Type> t;
After:  vector< ::Type> t;
llvm-svn: 172601
2013-01-16 07:19:28 +00:00
Daniel Jasper c36492b598 Remove errors were if statements were incorrectly put on a single line.
Before: if (a)  // This comment confused clang-format f();
After:  if (a)  // No more confusion
          f();
llvm-svn: 172600
2013-01-16 07:02:34 +00:00
Manuel Klimek 99c7baa3cf Fix formatting of preprocessor directives (incluces, warnings & errors).
Treat tokens inside <> for includes and everything from the second token
of a warning / error on as an implicit string literal, e.g. do not
change its whitespace at all.

Now correctly formats:
 #include < path with space >
 #error Leave     all         white!!!!! space* alone!

Note that for #error and #warning we still format the space up to the
first token of the text, so:
   #  error   Text
will become
 #error Text

llvm-svn: 172536
2013-01-15 15:50:27 +00:00
Daniel Jasper 7194527d9f Improve operator kind detection in presence of comments.
We used to incorrectly identify some operators (*, &, +, -, etc.) if
there were comments around them.

Example:
Before: int a = /**/ - 1;
After:  int a = /**/ -1;

llvm-svn: 172533
2013-01-15 14:27:39 +00:00
Manuel Klimek e01bab587c Fixes various bugs around the keywords class, struct and union.
This switches to parsing record definitions only if we can clearly
identify them. We're specifically allowing common patterns for
visibility control through macros and attributes, but we cannot
currently fix all instances. This fixes all known bugs we have though.

Before:
static class A f() {
  return g();
} int x;

After:
static class A f() {
  return g();
}
int x;

llvm-svn: 172530
2013-01-15 13:38:33 +00:00
Manuel Klimek a54d1a99a2 Fixes formatting of nested brace initializers.
We now format this correctly:
Status::Rep Status::global_reps[3] = {
  { kGlobalRef, OK_CODE, NULL, NULL, NULL },
  { kGlobalRef, CANCELLED_CODE, NULL, NULL, NULL },
  { kGlobalRef, UNKNOWN_CODE, NULL, NULL, NULL }
};

- fixed a bug where BreakBeforeClosingBrace would be set on the wrong
  state
- added penalties for breaking between = and {, and between { and any
  other non-{ token

llvm-svn: 172433
2013-01-14 16:41:43 +00:00
Daniel Jasper 1b750edda1 Make single-line if statements optional.
Now, "if (a) return;" is only allowed, if this option is set.

Also add a Chromium style which is currently identical to Google style
except for this option.

llvm-svn: 172431
2013-01-14 16:24:39 +00:00
Daniel Jasper 3e9218e50a Fix a bug in the line merging.
If the first line of a merge would exactly fit into the column limit,
an unsigned overflow made us not break.

llvm-svn: 172426
2013-01-14 16:02:06 +00:00
Daniel Jasper 2ab0d01a8e Fix bug that would lead to joining preprocessor directives.
Before: #include "a.h" #include "b.h"
After:  #include "a.h"
        #include "b.h"
llvm-svn: 172424
2013-01-14 15:52:06 +00:00
Daniel Jasper 39825eaff5 Put simple preprocessor directives on a single line.
Before: #define A  \
          A
After:  #define A A
llvm-svn: 172423
2013-01-14 15:40:57 +00:00
Daniel Jasper 25837aa666 Put short if statements on a single line.
Before: if (a)
          return;
After:  if (a) return;

Not yet sure, whether this is always desired, but we can add options and
make this a style parameter as we go along.

llvm-svn: 172413
2013-01-14 14:14:23 +00:00
Daniel Jasper 13f23e17c7 Improve understanding post increment and decrement.
Before: (a->f()) ++;
        a[42] ++;
After:  (a->f())++;
        a[42]++;
llvm-svn: 172400
2013-01-14 12:18:19 +00:00
Alexander Kornienko 116ba68220 Custom DiagnosticConsumer parameter of reformat() + silence diagnostics in unit tests.
Summary:
Added tests for clang-format diagnostics. Added DiagnosticConsumer
argument to clang::format::reformat().

Reviewers: klimek, djasper

Reviewed By: djasper

CC: cfe-commits, thakis, rafael.espindola

Differential Revision: http://llvm-reviews.chandlerc.com/D290

llvm-svn: 172399
2013-01-14 11:34:14 +00:00