Support preserved registers as identifiers

… in expressions

1 files changed, 181 insertions, 0 deletions

diff --git a/boot/tokenizer.s b/boot/tokenizer.s
new file mode 100644
index 0000000..2057c2e
--- /dev/null
+++ b/boot/tokenizer.s
@@ -0,0 +1,181 @@
+.global _tokenizer_initialize
+
+.section .rodata
+
+raw_classes:
+	.ascii "invalid\n"
+	.ascii "invalid\n"
+	.ascii "invalid\n"
+	.ascii "invalid\n"
+	.ascii "invalid\n"
+	.ascii "invalid\n"
+	.ascii "invalid\n"
+	.ascii "invalid\n"
+	.ascii "invalid\n"
+	.ascii "invalid\n"
+	.ascii "invalid\n"
+	.ascii "invalid\n"
+	.ascii "invalid\n"
+	.ascii "invalid\n"
+	.ascii "invalid\n"
+	.ascii "invalid\n"
+	.ascii "invalid\n"
+	.ascii "invalid\n"
+	.ascii "invalid\n"
+	.ascii "invalid\n"
+	.ascii "invalid\n"
+	.ascii "invalid\n"
+	.ascii "invalid\n"
+	.ascii "invalid\n"
+	.ascii "invalid\n"
+	.ascii "invalid\n"
+	.ascii "invalid\n"
+	.ascii "invalid\n"
+	.ascii "invalid\n"
+	.ascii "invalid\n"
+	.ascii "invalid\n"
+	.ascii "invalid\n"
+	.ascii "space\n"
+	.ascii "invalid\n"
+	.ascii "invalid\n"
+	.ascii "invalid\n"
+	.ascii "invalid\n"
+	.ascii "invalid\n"
+	.ascii "invalid\n"
+	.ascii "invalid\n"
+	.ascii "invalid\n"
+	.ascii "invalid\n"
+	.ascii "invalid\n"
+	.ascii "invalid\n"
+	.ascii "invalid\n"
+	.ascii "invalid\n"
+	.ascii "invalid\n"
+	.ascii "invalid\n"
+	.ascii "digit\n"
+	.ascii "digit\n"
+	.ascii "digit\n"
+	.ascii "digit\n"
+	.ascii "digit\n"
+	.ascii "digit\n"
+	.ascii "digit\n"
+	.ascii "digit\n"
+	.ascii "digit\n"
+	.ascii "digit\n"
+	.ascii "invalid\n"
+	.ascii "invalid\n"
+	.ascii "invalid\n"
+	.ascii "invalid\n"
+	.ascii "invalid\n"
+	.ascii "invalid\n"
+	.ascii "invalid\n"
+	.ascii "upper\n"
+	.ascii "upper\n"
+	.ascii "upper\n"
+	.ascii "upper\n"
+	.ascii "upper\n"
+	.ascii "upper\n"
+	.ascii "upper\n"
+	.ascii "upper\n"
+	.ascii "upper\n"
+	.ascii "upper\n"
+	.ascii "upper\n"
+	.ascii "upper\n"
+	.ascii "upper\n"
+	.ascii "upper\n"
+	.ascii "upper\n"
+	.ascii "upper\n"
+	.ascii "upper\n"
+	.ascii "upper\n"
+	.ascii "upper\n"
+	.ascii "upper\n"
+	.ascii "upper\n"
+	.ascii "upper\n"
+	.ascii "upper\n"
+	.ascii "upper\n"
+	.ascii "upper\n"
+	.ascii "upper\n"
+	.ascii "invalid\n"
+	.ascii "invalid\n"
+	.ascii "invalid\n"
+	.ascii "invalid\n"
+	.ascii "invalid\n"
+	.ascii "invalid\n"
+	.ascii "lower\n"
+	.ascii "lower\n"
+	.ascii "lower\n"
+	.ascii "lower\n"
+	.ascii "lower\n"
+	.ascii "lower\n"
+	.ascii "lower\n"
+	.ascii "lower\n"
+	.ascii "lower\n"
+	.ascii "lower\n"
+	.ascii "lower\n"
+	.ascii "lower\n"
+	.ascii "lower\n"
+	.ascii "lower\n"
+	.ascii "lower\n"
+	.ascii "lower\n"
+	.ascii "lower\n"
+	.ascii "lower\n"
+	.ascii "lower\n"
+	.ascii "lower\n"
+	.ascii "lower\n"
+	.ascii "lower\n"
+	.ascii "lower\n"
+	.ascii "lower\n"
+	.ascii "lower\n"
+	.ascii "lower\n"
+	.ascii "invalid\n"
+	.ascii "invalid\n"
+	.ascii "invalid\n"
+	.ascii "invalid\n"
+	.ascii "invalid\n"
+
+.section .bss
+.type class_names, @object
+.size class_names, 1024
+class_names: .zero 1024
+
+.section .data
+.type classes, @object
+.size classes, 512 # 128 characters * 4 byte.
+classes:
+
+.section .text
+
+# Initializes the classification table.
+#
+# Paramaters:
+# a0 - Raw input for the classification table.
+.type _tokenizer_classes, @function
+_tokenizer_classes:
+	# Prologue.
+	addi sp, sp, -8
+	sw ra, 4(sp)
+	sw s0, 0(sp)
+	addi s0, sp, 8
+
+	# Epilogue.
+	lw ra, 4(sp)
+	lw s0, 0(sp)
+	addi sp, sp, 8
+	ret
+
+# Initializes the lookup tables.
+.type _tokenizer_initialize, @function
+_tokenizer_initialize:
+	# Prologue.
+	addi sp, sp, -8
+	sw ra, 4(sp)
+	sw s0, 0(sp)
+	addi s0, sp, 8
+
+	la a0, raw_classes
+	call _tokenizer_classes
+
+	# Epilogue.
+	lw ra, 4(sp)
+	lw s0, 0(sp)
+	addi sp, sp, 8
+	ret