factor: trim using lists

[factor.git] / extra / robots / robots.factor

diff --git a/extra/robots/robots.factor b/extra/robots/robots.factor
index af039ef8c44792c63b3492cca3248331fe017975..6e61420d43ec9f3bf7f0700d9b7792802d41f6d2 100644 (file)
--- a/extra/robots/robots.factor
+++ b/extra/robots/robots.factor
@@ -1,13 +1,12 @@
 ! Copyright (C) 2009 Doug Coleman.
 ! See http://factorcode.org/license.txt for BSD license.
-USING: accessors arrays assocs calendar.format combinators
-combinators.short-circuit fry globs http.client kernel make
-math.parser multiline namespaces present regexp
-regexp.combinators sequences sets splitting splitting.monotonic
-unicode.case unicode.categories urls ;
+USING: accessors arrays assocs calendar.parser combinators
+combinators.short-circuit globs http.client kernel math.parser
+namespaces present regexp regexp.combinators sequences splitting
+splitting.monotonic unicode urls ;
 IN: robots
 
-! visit-time is GMT, request-rate is pages/second 
+! visit-time is GMT, request-rate is pages/second
 ! crawl-rate is seconds
 
 SYMBOL: robot-identities
@@ -29,20 +28,20 @@ visit-time request-rate crawl-delay unknowns ;
 : >robots.txt-url ( url -- url' )
     >url URL" robots.txt" derive-url ;
 
-: get-robots.txt ( url -- headers robots.txt )
-    >robots.txt-url http-get ;
+: get-robots.txt ( url -- robots.txt )
+    >robots.txt-url http-get nip ;
 
 : normalize-robots.txt ( string -- sitemaps seq )
-    string-lines
-    [ [ blank? ] trim ] map
-    [ "#" head? not ] filter harvest
-    [ ":" split1 [ [ blank? ] trim ] bi@ [ >lower ] dip  ] { } map>assoc
+    split-lines
+    [ [ unicode:blank? ] trim ] map
+    [ "#" head? ] reject harvest
+    [ ":" split1 [ [ unicode:blank? ] trim ] bi@ [ >lower ] dip  ] { } map>assoc
     [ first "sitemap" = ] partition [ values ] dip
     [
         {
-            [ [ first "user-agent" = ] bi@ and ]
+            [ [ first "user-agent" = ] both? ]
             [ nip first "user-agent" = not ]
-        } 2|| 
+        } 2||
     ] monotonic-split ;
 
 : <rules> ( -- rules )
@@ -64,7 +63,7 @@ visit-time request-rate crawl-delay unknowns ;
         { "crawl-delay" [ string>number >>crawl-delay ] }
         { "request-rate" [ string>number >>request-rate ] }
         {
-            "visit-time" [ "-" split1 [ hhmm>timestamp ] bi@ 2array
+            "visit-time" [ "-" split1 [ hhmm>duration ] bi@ 2array
             >>visit-time
         ] }
         [ pick unknowns>> push-at ]
@@ -97,6 +96,5 @@ PRIVATE>
         [ <rules> dup ] dip [ parse-robots.txt-line drop ] with each
     ] map ;
 
-: robots ( url -- robots )
-    >url
-    dup get-robots.txt nip parse-robots.txt <robots> ;
+: url>robots ( url -- robots )
+    >url dup get-robots.txt parse-robots.txt <robots> ;