From f45ea0cb5c4109bc573da1d0b2289b451a29b068 Mon Sep 17 00:00:00 2001
From: "Kartik K. Agaram" <vc@akkartik.com>
Date: Fri, 19 Dec 2014 18:57:11 -0800
Subject: [PATCH] 441 - string 'find-next' for characters

---
 mu.arc   | 16 +++++++++++
 mu.arc.t | 88 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 104 insertions(+)

diff --git a/mu.arc b/mu.arc
index 72d47469..bb7cd6f2 100644
--- a/mu.arc
+++ b/mu.arc
@@ -1456,6 +1456,22 @@
   }
   (reply result:string-address))
 
+(init-fn find-next  ; string, character, index -> next index
+  (s:string-address <- next-input)
+  (needle:character <- next-input)  ; todo: unicode chars
+  (idx:integer <- next-input)
+  (len:integer <- length s:string-address/deref)
+  { begin
+    (eof?:boolean <- greater-or-equal idx:integer len:integer)
+    (break-if eof?:boolean)
+    (curr:byte <- index s:string-address/deref idx:integer)
+    (found?:boolean <- equal curr:byte needle:character)
+    (break-if found?:boolean)
+    (idx:integer <- add idx:integer 1:literal)
+    (loop)
+  }
+  (reply idx:integer))
+
 )  ; section 100 for system software
 
 ;; load all provided files and start at 'main'
diff --git a/mu.arc.t b/mu.arc.t
index 1c5cc132..2e284b7d 100644
--- a/mu.arc.t
+++ b/mu.arc.t
@@ -3321,6 +3321,94 @@
 (if (~memory-contains-array memory*.5 "hello, abc, def, and ghi!")
   (prn "F - 'interpolate' splices in any number of strings"))
 
+(reset)
+(new-trace "string-find-next")
+(add-code '((function main [
+              (1:string-address <- new "a/b")
+              (2:integer <- find-next 1:string-address ((#\/ literal)) 0:literal)
+             ])))
+(run 'main)
+(if (~is memory*.2 1)
+  (prn "F - 'find-next' finds first location of a character"))
+
+(reset)
+(new-trace "string-find-next-empty")
+(add-code '((function main [
+              (1:string-address <- new "")
+              (2:integer <- find-next 1:string-address ((#\/ literal)) 0:literal)
+             ])))
+(run 'main)
+(each routine completed-routines*
+  (aif rep.routine!error (prn "error - " it)))
+(if (~is memory*.2 0)
+  (prn "F - 'find-next' finds first location of a character"))
+
+(reset)
+(new-trace "string-find-next-initial")
+(add-code '((function main [
+              (1:string-address <- new "/abc")
+              (2:integer <- find-next 1:string-address ((#\/ literal)) 0:literal)
+             ])))
+(run 'main)
+(if (~is memory*.2 0)
+  (prn "F - 'find-next' handles prefix match"))
+
+(reset)
+(new-trace "string-find-next-final")
+(add-code '((function main [
+              (1:string-address <- new "abc/")
+              (2:integer <- find-next 1:string-address ((#\/ literal)) 0:literal)
+             ])))
+(run 'main)
+;? (prn memory*.2)
+(if (~is memory*.2 3)
+  (prn "F - 'find-next' handles suffix match"))
+
+(reset)
+(new-trace "string-find-next-missing")
+(add-code '((function main [
+              (1:string-address <- new "abc")
+              (2:integer <- find-next 1:string-address ((#\/ literal)) 0:literal)
+             ])))
+(run 'main)
+;? (prn memory*.2)
+(if (~is memory*.2 3)
+  (prn "F - 'find-next' handles no match"))
+
+(reset)
+(new-trace "string-find-next-invalid-index")
+(add-code '((function main [
+              (1:string-address <- new "abc")
+              (2:integer <- find-next 1:string-address ((#\/ literal)) 4:literal)
+             ])))
+;? (= dump-trace* (obj whitelist '("run")))
+(run 'main)
+(each routine completed-routines*
+  (aif rep.routine!error (prn "error - " it)))
+;? (prn memory*.2)
+(if (~is memory*.2 4)
+  (prn "F - 'find-next' skips invalid index (past end of string)"))
+
+(reset)
+(new-trace "string-find-next-first")
+(add-code '((function main [
+              (1:string-address <- new "ab/c/")
+              (2:integer <- find-next 1:string-address ((#\/ literal)) 0:literal)
+             ])))
+(run 'main)
+(if (~is memory*.2 2)
+  (prn "F - 'find-next' finds first of multiple options"))
+
+(reset)
+(new-trace "string-find-next-second")
+(add-code '((function main [
+              (1:string-address <- new "ab/c/")
+              (2:integer <- find-next 1:string-address ((#\/ literal)) 3:literal)
+             ])))
+(run 'main)
+(if (~is memory*.2 4)
+  (prn "F - 'find-next' finds second of multiple options"))
+
 )  ; section 100 for string utilities
 
 (reset)