From 5e799b381a474625f20bc6d7b41cc13c7a9003c9 Mon Sep 17 00:00:00 2001
From: d6 <d_m@plastic-idolatry.com>
Date: Thu, 3 Feb 2022 01:32:35 -0500
Subject: [PATCH] get + and ? working in regex parser

---
 regex.tal | 59 +++++++++++++++++++++++++++++++++++++++++++++++++------
 1 file changed, 53 insertions(+), 6 deletions(-)

diff --git a/regex.tal b/regex.tal
index c11f4c2..e3e8453 100644
--- a/regex.tal
+++ b/regex.tal
@@ -52,6 +52,8 @@
 @stack-is-empty "stack 20 "is 20 "empty 00
 @arena-is-full "arena 20 "is 20 "full 00
 @star-invariant "star 20 "invariant 20 "failed 00
+@plus-invariant "plus 20 "invariant 20 "failed 00
+@qmark-invariant "question 20 "mark 20 "invariant 20 "failed 00
 
 ( REGEX MATCHING )
 
@@ -152,15 +154,21 @@
 @peek-to-star ( -> is-star^ )
     ;pos LDA2 LDA LIT '* EQU JMP2r
 
+( is pos currently pointing to a plus? )
+@peek-to-plus ( -> is-plus^ )
+    ;pos LDA2 LDA LIT '+ EQU JMP2r
+
+( is pos currently pointing to a qmark? )
+@peek-to-qmark ( -> is-qmark^ )
+    ;pos LDA2 LDA LIT '? EQU JMP2r
+
 ( just increment pos )
 @skip
     ;pos LDA2 INC2 ;pos STA2 JMP2r
 
 ( TODO: )
 ( 1. character groups: [] and [^] )
-( 2. one-or-more: + )
-( 3. zero-or-one: ? )
-( 4. symbolic escapes, e.g. \n )
+( 2. symbolic escapes, e.g. \n )
 
 ( STRETCH GOALS: )
 ( a. ^ and $ )
@@ -205,6 +213,8 @@
     DUP LIT ') EQU ;c-rpar JCN2
     DUP LIT '\ EQU ;c-esc  JCN2
     DUP LIT '* EQU ;c-star JCN2 
+    DUP LIT '+ EQU ;c-plus JCN2 
+    DUP LIT '? EQU ;c-qmark JCN2 
                    ;c-char JMP2
 
 ( either finalize the given r0/r1 or else wrap it in )
@@ -213,9 +223,13 @@
 ( we use this look-ahead approach rather than compiling )
 ( star nodes directly since the implementation is simpler. )
 @c-peek-and-finalize ( r0* r1* -> r2* )
-    ;peek-to-star JSR2 ( r0 r1 next-is-star? )
-    ,&next-is-star JCN ,&finally JMP ( r0 r1 )
-    &next-is-star ;skip JSR2 POP2 ;alloc-star JSR2 DUP2 ( star )
+    ;peek-to-star JSR2 ( r0 r1 next-is-star? ) ,&next-is-star JCN
+    ;peek-to-plus JSR2 ( r0 r1 next-is-plus? ) ,&next-is-plus JCN
+    ;peek-to-qmark JSR2 ( r0 r1 next-is-qmark? ) ,&next-is-qmark JCN
+    ,&finally JMP ( r0 r1 )
+    &next-is-star ;skip JSR2 POP2 ;alloc-star JSR2 DUP2 ,&finally JMP
+    &next-is-plus ;skip JSR2 POP2 ;alloc-plus JSR2 DUP2 ,&finally JMP
+    &next-is-qmark ;skip JSR2 POP2 ;alloc-qmark JSR2 DUP2 ,&finally JMP
     &finally ;push-next JSR2 ;compile-region-loop JMP2
 
 ( called when we reach EOF of the input string )
@@ -302,6 +316,20 @@
     POP
     ;star-invariant ;error! JSR2
 
+( called if we parse a "+" )
+( )
+( actually calling this means the code broke an invariant somewhere. )
+@c-plus ( c^ -> regex* )
+    POP
+    ;plus-invariant ;error! JSR2
+
+( called if we parse a "?" )
+( )
+( actually calling this means the code broke an invariant somewhere. )
+@c-qmark ( c^ -> regex* )
+    POP
+    ;qmark-invariant ;error! JSR2
+
 ( ALLOCATING REGEX NDOES )
 
 @alloc3 ( mode^ -> r* )
@@ -341,6 +369,25 @@
     ;set-next JSR2 ( [r] )
     STH2r JMP2r
 
+@alloc-plus ( expr* -> r* )
+    #05 ;alloc JSR2 STH2  ( expr [r] )
+    #05 STH2kr STA        ( expr [r] )
+    DUP2 STH2kr INC2 STA2 ( expr [r] )
+    #0000 STH2kr #0003 ADD2 STA2 ( expr [r] )
+    STH2r SWP2 STH2k ( r expr [expr] )
+    ;set-next JSR2 ( [expr] )
+    STH2r JMP2r
+
+@alloc-qmark ( expr* -> r* )
+    ;alloc-empty JSR2 STH2k ( expr e [e] )
+    OVR2 ;set-next JSR2 ( expr [e] )
+    #05 ;alloc JSR2 STH2  ( expr [r e] )
+    #04 STH2kr STA        ( expr [r e] )
+    STH2kr INC2 STA2 ( [r e] )
+    SWP2r STH2r STH2kr ( e r [r] )
+    #0003 ADD2 STA2 ( [r] )
+    STH2r JMP2r
+
 ( if r is 0000, allocate an empty node )
 @alloc-if-null ( r* -> r2* )
     ORAk ,&return JCN POP2 ;alloc-empty JSR2 &return JMP2r