polserver/pol-core/bscript/compiler/file/PrettifyLineBuilder.h
turleypol 7627e3d353
"Preview/Initial"- Version sourcecode formatting feature (#626)
* Squash only prettify changes from escript_formating_try

* support of "format-off" / "format-on" comments to mark areas without
formatting

* fix typo

* added FormatterIdentLevel, FormatterMergeEmptyLines cfg entry
better line splits for dicts/arrays

* added several spacing options. the current setting list is now:
//LineWidth
FormatterLineWidth 80
// keep original keyword spelling
FormatterKeepKeywords 0
// number of spaces for ident
FormatterIdentLevel 2
// multiple newlines get merged to a single
FormatterMergeEmptyLines 1
// space between emtpy parenthesis eg foo() vs foo( )
FormatterEmptyParenthesisSpacing 0
// space between emtpy brackets eg struct{} vs struct{ }
FormatterEmptyBracketSpacing 0
// space after/before parenthesis in conditionals
// eg if ( true ) vs if (true)
FormatterConditionalParenthesisSpacing 1
// space after/before parenthesis
// eg foo( true ) vs foo(true)
FormatterParenthesisSpacing 1
// space after/before brackets
// eg array{ true } vs array{true}
FormatterBracketSpacing 1
// add space after delimiter comma or semi in for loops
// eg {1, 2, 3} vs {1,2,3}
FormatterDelimiterSpacing 1
// add space around assignment
// eg a := 1; vs a:=1;
FormatterAssignmentSpacing 1
// add space around comparison
// eg a == 1 vs a==1
FormatterComparisonSpacing 1
// add space around operations
// eg a + 1 vs a+1
FormatterOperatorSpacing 1
// use \r\n as newline instead of \n
FormatterWindowsLineEndings 0

* added tab support
// use tabs instead of spaces
FormatterUseTabs 0
// tab width
FormatterTabWidth 4

* extended example ecompile.cfg with formatter settings

* cleanup

* program args comma is optional...
fixed line comments in group splitting

* since tokenids are now correct no more guessing for linecomments needed

* comments use as start tokenid the whitespace token if its on the same
line

* splitted processing from linebuilding

* renamed TokenPart to FmtToken better matches the purpose.
Comments get directly stored as FmtToken
started with a context enum

* better(?) formatting for groups

* fix eof rawlines
added check that all comments/rawlines got parsed

* const correctness

* datatype adapted to antlr

* fixed warnings

* added InsertNewlineAtEOF

* add newline at the end if the original file had one
dont strip comment whitespace if its somejind of "header block"
use the defined lineending for /* */ comments

* docs

* \r\n is default on windows \n otherwise

* fixed warning

---------

Co-authored-by: Kevin Eady <8634912+KevinEady@users.noreply.github.com>
2024-02-26 21:21:44 +01:00

129 lines
3.5 KiB
C++

#pragma once
#include "bscript/compiler/file/SourceLocation.h"
#include <EscriptGrammar/EscriptParserBaseVisitor.h>
#include <memory>
#include <optional>
#include <string>
namespace Pol::Bscript::Compiler
{
// TODO: something like that to set in FileProcessor all needed meta info to define the actual style
enum class FmtContext
{
NONE = 0,
KEYWORD = 1, // space
KEYWORD_BREAKING,
LITERAL,
TERMINATOR, // terminatorStyle
OPENING_PARANTHESIS, //
OPENING_PARANTHESIS_ATTACHED, //
CLOSING_PARANTHESIS, // closing..
OPENING_BRACKET, //
OPENING_BRACKET_ATTACHED, //
CLOSING_BRACKET, //
DELIMITER, // delimiterStyle
DELIMITER_NONBREAKING, // really?
DELIMITER_SPACE_ATTACHED, // enum
ASSIGNMENT,
OPER_PREFIX,
OPER_PREFIX_SPACE,
OPER_POSTFIX,
BINARY_SPACE_ATTACHED,
BINARY_ATTACHED,
BINARY_SPACE_BREAK, // assignment
BINARY_ASSIGNMENT,
BINARY_SPACE,
BINARY_COMPARISON,
BINARY_OPERATOR,
BINARY_ELVIS,
BINARY_QUESTION,
SUFFIX_ATTACHED,
COLON,
FUNC_REF,
INTER_STRING,
INTER_STRING_PART,
INTER_STRING_END,
LINE_COMMENT,
COMMENT,
};
// structure to hold one token as string
struct FmtToken
{
enum Style
{
NONE = 0, // do nothing
ATTACHED = 1, // override SPACE of preceding token
SPACE = 2, // add a whitespace char after this token
BREAKPOINT = 4, // potential linebreak
FORCED_BREAK = 8, // force linebreak
};
std::string text = {};
Position pos = {};
Position pos_end = {};
int style = 0;
size_t group = 0;
size_t token_type = 0;
FmtContext context = FmtContext::NONE;
FmtToken() = default;
FmtToken( std::string&& text, const Position& pos, int style, size_t group, size_t token_type )
: text( std::move( text ) ),
pos( pos ),
pos_end( pos ),
style( style ),
group( group ),
token_type( token_type ){};
};
class PrettifyLineBuilder
{
public:
PrettifyLineBuilder() = default;
const std::vector<std::string>& formattedLines() const;
void setRawLines( std::vector<std::string> rawlines );
void setComments( std::vector<FmtToken> comments );
void setSkipLines( std::vector<Range> skiplines );
void addPart( FmtToken part );
void buildLine( size_t current_ident );
bool finalize();
const std::vector<FmtToken>& currentTokens() const;
int closingParenthesisStyle( size_t begin_size );
int closingBracketStyle( size_t begin_size );
int openingParenthesisStyle();
int openingBracketStyle();
int delimiterStyle();
int terminatorStyle();
int assignmentStyle();
int comparisonStyle();
int operatorStyle();
private:
std::vector<std::string> _rawlines = {};
std::vector<std::string> _lines = {};
std::vector<FmtToken> _line_parts = {};
std::vector<FmtToken> _comments = {};
std::vector<Range> _skiplines = {};
size_t _last_line = 0;
size_t _currident = 0;
size_t _currentgroup = 0;
void mergeRawContent( size_t nextlineno );
void mergeComments();
void mergeCommentsBefore( size_t nextlineno );
void addEmptyLines( size_t line_number );
void mergeEOFNonTokens();
std::string identSpacing();
std::string alignmentSpacing( size_t count );
};
} // namespace Pol::Bscript::Compiler
template <>
struct fmt::formatter<Pol::Bscript::Compiler::FmtToken> : fmt::formatter<std::string>
{
fmt::format_context::iterator format( const Pol::Bscript::Compiler::FmtToken& t,
fmt::format_context& ctx ) const;
};