From 6ce3396bec42e5c59aafd71ec06d6ba83002b0a9 Mon Sep 17 00:00:00 2001
From: Jon Crussell <jcrusse@sandia.gov>
Date: Thu, 20 Jun 2024 06:54:31 -0700
Subject: [PATCH] add support for rust with the go runtime

Tested on rust/examples/*.rs and works for all the examples except
`intellijrust_test_allinone.rs` which takes forever to analyze.
---
 rust/Go/rust_lexer_base.go  | 81 +++++++++++++++++++++++++++++++++++++
 rust/Go/rust_parser_base.go | 14 +++++++
 rust/Go/transformGrammar.py | 56 +++++++++++++++++++++++++
 3 files changed, 151 insertions(+)
 create mode 100644 rust/Go/rust_lexer_base.go
 create mode 100644 rust/Go/rust_parser_base.go
 create mode 100644 rust/Go/transformGrammar.py

diff --git a/rust/Go/rust_lexer_base.go b/rust/Go/rust_lexer_base.go
new file mode 100644
index 0000000000..72f924a44f
--- /dev/null
+++ b/rust/Go/rust_lexer_base.go
@@ -0,0 +1,81 @@
+package parser
+
+import (
+	"github.com/antlr4-go/antlr/v4"
+)
+
+type RustLexerBase struct {
+	*antlr.BaseLexer
+
+	lastToken  antlr.Token
+	lastToken2 antlr.Token
+}
+
+func (l *RustLexerBase) NextToken() antlr.Token {
+	next := l.BaseLexer.NextToken()
+
+	if next.GetChannel() == antlr.LexerDefaultTokenChannel {
+		// keep track of the last token on the default channel
+		l.lastToken2 = l.lastToken
+		l.lastToken = next
+	}
+
+	return next
+}
+
+func (l *RustLexerBase) SOF() bool {
+	return l.GetInputStream().LA(-1) <= 0
+}
+
+func (l *RustLexerBase) floatDotPossible() bool {
+	next := rune(l.GetInputStream().LA(1))
+	if next == '.' || next == '_' {
+		return false
+	}
+	if next == 'f' {
+		// 1.f32
+		if rune(l.GetInputStream().LA(2)) == '3' && rune(l.GetInputStream().LA(3)) == '2' {
+			return true
+		}
+		//1.f64
+		if rune(l.GetInputStream().LA(2)) == '6' && rune(l.GetInputStream().LA(3)) == '4' {
+			return true
+		}
+		return false
+	}
+	if next >= 'a' && next <= 'z' {
+		return false
+	}
+	if next >= 'A' && next <= 'Z' {
+		return false
+	}
+
+	return false
+}
+
+func (l *RustLexerBase) floatLiteralPossible() bool {
+	if l.lastToken == nil || l.lastToken2 == nil {
+		return true
+	}
+	if l.lastToken.GetTokenType() != RustLexerDOT {
+		return true
+	}
+
+	switch l.lastToken2.GetTokenType() {
+	case RustLexerCHAR_LITERAL, RustLexerSTRING_LITERAL,
+		RustLexerRAW_STRING_LITERAL, RustLexerBYTE_LITERAL,
+		RustLexerBYTE_STRING_LITERAL, RustLexerRAW_BYTE_STRING_LITERAL,
+		RustLexerINTEGER_LITERAL, RustLexerDEC_LITERAL, RustLexerHEX_LITERAL,
+		RustLexerOCT_LITERAL, RustLexerBIN_LITERAL, RustLexerKW_SUPER,
+		RustLexerKW_SELFVALUE, RustLexerKW_SELFTYPE, RustLexerKW_CRATE,
+		RustLexerKW_DOLLARCRATE, RustLexerGT, RustLexerRCURLYBRACE,
+		RustLexerRSQUAREBRACKET, RustLexerRPAREN, RustLexerKW_AWAIT,
+		RustLexerNON_KEYWORD_IDENTIFIER, RustLexerRAW_IDENTIFIER,
+		RustLexerKW_MACRORULES:
+		return false
+	default:
+		return true
+	}
+
+	return false
+}
diff --git a/rust/Go/rust_parser_base.go b/rust/Go/rust_parser_base.go
new file mode 100644
index 0000000000..899bde4511
--- /dev/null
+++ b/rust/Go/rust_parser_base.go
@@ -0,0 +1,14 @@
+package parser
+
+import (
+	"github.com/antlr4-go/antlr/v4"
+)
+
+// RustParserBase implementation.
+type RustParserBase struct {
+	*antlr.BaseParser
+}
+
+func (p *RustParserBase) next(expect int) bool {
+	return p.GetInputStream().LA(1) == expect
+}
diff --git a/rust/Go/transformGrammar.py b/rust/Go/transformGrammar.py
new file mode 100644
index 0000000000..56a0ccb026
--- /dev/null
+++ b/rust/Go/transformGrammar.py
@@ -0,0 +1,56 @@
+import sys, os, re, shutil
+from glob import glob
+from pathlib import Path
+
+def main(argv):
+    for file in glob("./*Lexer.g4"):
+        fix_lexer(file)
+    for file in glob("./*Parser.g4"):
+        fix_parser(file)
+
+def fix_lexer(file_path):
+    print("Altering " + file_path)
+    if not os.path.exists(file_path):
+        print(f"Could not find file: {file_path}")
+        sys.exit(1)
+    parts = os.path.split(file_path)
+    file_name = parts[-1]
+
+    shutil.move(file_path, file_path + ".bak")
+    input_file = open(file_path + ".bak",'r')
+    output_file = open(file_path, 'w')
+    for x in input_file:
+        if 'this.' in x and '}?' in x:
+            x = x.replace('this.', 'p.')
+        elif 'this.' in x:
+            x = x.replace('this.', 'l.')
+        output_file.write(x)
+        output_file.flush()
+
+    print("Writing ...")
+    input_file.close()
+    output_file.close()
+
+def fix_parser(file_path):
+    print("Altering " + file_path)
+    if not os.path.exists(file_path):
+        print(f"Could not find file: {file_path}")
+        sys.exit(1)
+    parts = os.path.split(file_path)
+    file_name = parts[-1]
+
+    shutil.move(file_path, file_path + ".bak")
+    input_file = open(file_path + ".bak",'r')
+    output_file = open(file_path, 'w')
+    for x in input_file:
+        if 'this.' in x:
+            x = x.replace('this.', 'p.')
+        output_file.write(x)
+        output_file.flush()
+
+    print("Writing ...")
+    input_file.close()
+    output_file.close()
+
+if __name__ == '__main__':
+    main(sys.argv)