From 37b9da32d3b911091deb254f6cba2a137c471287 Mon Sep 17 00:00:00 2001 From: Marc Vertes Date: Thu, 12 Oct 2023 10:51:58 +0200 Subject: move to a direct byte code compiler (#8) * chore: refactor to keep only the new parser and bytecode vm * scanner: remove Token.value field * scanner: remove scanner.kind field * chore: move language specification in lang package This avoid a cyclic dependency in scanner_test which can now use the golang/GoSpec language specification for Go. * clean code * scanner: export scanner fields Also parser now generate function calls, including externals. * chore: fix lint issues * parser: handle strings * wip * parser: implement support for 'if, else, else if' statements Resolving labels in the compiler still in progress. * parser: support if statements, improve compiler * improve handling of functions * improve support of local variables * scanner: trim leading and trailing spaces * fixes to make fibonacci work * parser: improve README, fix function parameters parsing --- lang/spec.go | 43 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 43 insertions(+) create mode 100644 lang/spec.go (limited to 'lang/spec.go') diff --git a/lang/spec.go b/lang/spec.go new file mode 100644 index 0000000..c5b50a4 --- /dev/null +++ b/lang/spec.go @@ -0,0 +1,43 @@ +package lang + +const ( + CharIllegal = 1 << iota + CharOp + CharNum + CharAlpha + CharSep + CharLineSep + CharGroupSep + CharStr + CharBlock + StrEsc + StrNonl + ExcludeEnd // exclude end delimiter from content + EosValidEnd // end of input string terminates block or string token +) + +const ASCIILen = 1 << 7 // 128 + +type TokenProp struct { + TokenId + SkipSemi bool // automatic semicolon insertion after newline +} + +type Spec struct { + CharProp [ASCIILen]uint // special Character properties + End map[string]string // end delimiters, indexed by start + BlockProp map[string]uint // block properties + TokenProps map[string]TokenProp // token properties + DotNum bool // true if a number can start with '.' + IdAscii bool // true if an identifier can be in ASCII only + Num_ bool // true if a number can contain _ character +} + +// HasInit stores if a statement may contain a simple init statement +var HasInit = map[TokenId]bool{ + Case: true, + For: true, + If: true, + Select: true, + Switch: true, +} -- cgit v1.2.3