From 21a31755b61282654467593a0b4475d3ae1c2b77 Mon Sep 17 00:00:00 2001
From: d6 <d_m@plastic-idolatry.com>
Date: Sat, 19 Feb 2022 01:23:39 -0500
Subject: [PATCH] get regex searching working

---
 grep.tal  |  8 ++++----
 regex.tal | 38 ++++++++++++++++++++++++++++++++++----
 2 files changed, 38 insertions(+), 8 deletions(-)

diff --git a/grep.tal b/grep.tal
index b98cc4c..061e37f 100644
--- a/grep.tal
+++ b/grep.tal
@@ -3,7 +3,7 @@
 ( by d_m )
 
 ( print a character to STDOUT )
-%emit { #18 DEO }
+%emitt { #18 DEO }
 
 ( the first argument to grep is the regex )
 ( arguments are passed on STDIN, so we just )
@@ -18,8 +18,8 @@
 
 @println ( s* -> )
     &loop LDAk #00 EQU ,&eof JCN ( did we reach \0 ? )
-    LDAk emit INC2 ,&loop JMP    ( no so emit a char and repeat )
-    &eof #0a emit POP2 JMP2r     ( yes so emit \n and return )
+    LDAk emitt INC2 ,&loop JMP    ( no so emit a char and repeat )
+    &eof #0a emitt POP2 JMP2r     ( yes so emit \n and return )
 
 @r-read-stdin ( -> )
     #12 DEI #0a EQU ,&execute JCN     ( did we read \n ? )
@@ -34,7 +34,7 @@
     ,&need-regex JCN                  ( jump if unset )
 
                                       ( regex is set )
-    ;buffer ;regex LDA2 ;match JSR2   ( match regex )
+    ;buffer ;regex LDA2 ;search JSR2  ( search line for a regex match )
     #00 EQU ,&no-match JCN            ( did we match? )
     ;buffer ;println JSR2             ( print any match )
     &no-match BRK                     ( return )
diff --git a/regex.tal b/regex.tal
index eaa0b55..d89fd29 100644
--- a/regex.tal
+++ b/regex.tal
@@ -35,6 +35,14 @@
 %newline { #0a emit }
 %quit! { #01 #0f DEO BRK }
 
+( now that uxnasm throws errors about writing into the zero page   )
+( we have to do something like this to be able to compile library  )
+( code. we have to guess what offset to use since it needs to      )
+( avoid conficting with the program we're included in.             )
+(                                                                  )
+( remove this if needed when including it in other projects.       )
+|2000
+
 ( ERROR HANDLING )
 
 ( using error! will print the given message before causing )
@@ -66,9 +74,24 @@
 ( )
 ( returns true if the string, and false otherwise. )
 @match ( str* regex* -> bool^ )
+    #00 ;search-mode STA
     ;reset-stack JSR2
     ;loop JMP2
 
+( )
+@search ( str* regex* -> bool^ )
+    #01 ;search-mode STA STH2     ( s* [r*] )
+    &loop LDAk #00 EQU ,&eof JCN  ( s* [r*] )
+          ;reset-stack JSR2       ( s* [r*] )
+          DUP2 ;search-start STA2 ( s* [r*] )
+          DUP2 STH2kr ;loop JSR2  ( s* b^ [r*] )
+          ,&found JCN             ( s* [r*] )
+          INC2 ,&loop JMP         ( s+1* [r*] )
+    &found POP2 POP2r #01 JMP2r   ( 01 )
+    &eof ;reset-stack JSR2        ( s* [r*] )
+         DUP2 ;search-start STA2  ( s* [r*] )
+         STH2r ;loop JMP2         ( b^ )    
+
 ( loop used during matching )
 ( )
 ( we don't use the return stack here since that )
@@ -95,9 +118,11 @@
 ( follow the given address (next*) to continue matching )
 @goto-next ( str* next* -> bool^ )
     DUP2 #0000 GTH2 ,&has-next JCN
-    POP2 LDA null? ,&end-of-string JCN
-    ;goto-backtrack JMP2
-    &end-of-string #01 JMP2r
+    POP2 LDAk null? ,&end-of-string JCN
+    ;search-mode LDA ,&end-of-search JCN
+    POP2 ;goto-backtrack JMP2
+    &end-of-search DUP2 ;search-end STA2
+    &end-of-string POP2 #01 JMP2r
     &has-next ;loop JMP2
 
 ( handle the empty node -- just follow the next pointer ) 
@@ -133,6 +158,11 @@
 
 ( REGEX PARSING )
 
+( are we in searching mode? )
+@search-mode $1
+@search-start $2
+@search-end $2
+
 ( track the position in the input string )
 @pos $2
 
@@ -589,4 +619,4 @@
     &above POPr POP &below #00 JMP2r
 
 @iv-find ( c^ iv* -> bool^ )
-    )
\ No newline at end of file
+    )