Mercurial Mercurial > hg > afl-material / changeset
summary | shortlog | changelog | graph | tags | bookmarks | branches | files | changeset | raw | gz | help
Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
updated
authorChristian Urban <christian dot urban at kcl dot ac dot uk>
Tue, 24 Sep 2013 01:56:53 +0100
changeset 96 9fcd3de53c06
parent 95 dbe49327b6c5
child 97 60a3ba90dd53
updated
progs/app1.scala file | annotate | diff | comparison | revisions
progs/app2.scala file | annotate | diff | comparison | revisions
progs/app3.scala file | annotate | diff | comparison | revisions
progs/app4.scala file | annotate | diff | comparison | revisions
progs/crawler1.scala file | annotate | diff | comparison | revisions
progs/crawler2.scala file | annotate | diff | comparison | revisions
progs/crawler3.scala file | annotate | diff | comparison | revisions 
--- a/progs/app1.scala	Tue Sep 24 01:12:36 2013 +0100
+++ b/progs/app1.scala	Tue Sep 24 01:56:53 2013 +0100
@@ -1,12 +1,3 @@
-def get_page(url: String) : String = { 
-  try {
-    Source.fromURL(url).take(10000).mkString  
-  }
-  catch {
-    case e => {
-      println("  Problem with: " + url)
-      ""
-    }
-  }
-}
-
+def get_page(url: String) : String = 
+  Try(Source.fromURL(url).take(10000).mkString) getOrElse 
+    { println(s"  Problem with: $url"); ""}
--- a/progs/app2.scala	Tue Sep 24 01:12:36 2013 +0100
+++ b/progs/app2.scala	Tue Sep 24 01:56:53 2013 +0100
@@ -3,13 +3,13 @@
 def unquote(s: String) = s.drop(1).dropRight(1)
 
 def get_all_URLs(page: String) : Set[String] = {
-  (http_pattern.findAllIn(page)).map { unquote(_) }.toSet
+  http_pattern.findAllIn(page).map(unquote).toSet
 }
 
 def crawl(url: String, n: Int) : Unit = {
   if (n == 0) ()
   else {
-    println("Visiting: " + n + " " + url)
+    println(s"Visiting: $n $url")
     for (u <- get_all_URLs(get_page(url))) crawl(u, n - 1)
   }
 }
--- a/progs/app3.scala	Tue Sep 24 01:12:36 2013 +0100
+++ b/progs/app3.scala	Tue Sep 24 01:56:53 2013 +0100
@@ -4,7 +4,7 @@
   if (n == 0) ()
   else if (my_urls.findFirstIn(url) == None) ()
   else {
-    println("Visiting: " + n + " " + url)
+    println(s"Visiting: $n $url")
     for (u <- get_all_URLs(get_page(url))) crawl(u, n - 1)
   }
 }
--- a/progs/app4.scala	Tue Sep 24 01:12:36 2013 +0100
+++ b/progs/app4.scala	Tue Sep 24 01:56:53 2013 +0100
@@ -6,7 +6,7 @@
 def crawl(url: String, n: Int) : Unit = {
   if (n == 0) ()
   else {
-    println("Visiting: " + n + " " + url)
+    println(s"Visiting: $n $url")
     val page = get_page(url)
     println(email_pattern.findAllIn(page).mkString("\n"))
     for (u <- get_all_URLs(page)) crawl(u, n - 1)
--- a/progs/crawler1.scala	Tue Sep 24 01:12:36 2013 +0100
+++ b/progs/crawler1.scala	Tue Sep 24 01:56:53 2013 +0100
@@ -1,18 +1,11 @@
 import io.Source
 import scala.util.matching.Regex
+import scala.util._
 
 // gets the first ~10K of a page
-def get_page(url: String) : String = { 
-  try {
-    Source.fromURL(url).take(10000).mkString  
-  }
-  catch {
-    case _ : Throwable => {
-      println(s"  Problem with: $url")
-      ""
-    }
-  }
-}
+def get_page(url: String) : String = 
+  Try(Source.fromURL(url).take(10000).mkString) getOrElse 
+    { println(s"  Problem with: $url"); ""}
 
 
 // regex for URLs
--- a/progs/crawler2.scala	Tue Sep 24 01:12:36 2013 +0100
+++ b/progs/crawler2.scala	Tue Sep 24 01:56:53 2013 +0100
@@ -1,18 +1,11 @@
 import io.Source
 import scala.util.matching.Regex
+import scala.util._
 
 // gets the first ~10K of a page
-def get_page(url: String) : String = { 
-  try {
-    Source.fromURL(url).take(10000).mkString  
-  }
-  catch {
-    case _ : Throwable => {
-      println(s"  Problem with: $url")
-      ""
-    }
-  }
-}
+def get_page(url: String) : String = 
+  Try(Source.fromURL(url).take(10000).mkString) getOrElse 
+    { println(s"  Problem with: $url"); ""}
 
 // staring URL for the crawler
 val startURL = """http://www.inf.kcl.ac.uk/staff/urbanc/"""
@@ -24,7 +17,7 @@
 def unquote(s: String) = s.drop(1).dropRight(1)
 
 def get_all_URLs(page: String) : Set[String] = {
-  (http_pattern.findAllIn(page)).map { unquote(_) }.toSet
+  http_pattern.findAllIn(page).map(unquote).toSet
 }
 
 // naive version - seraches until a given depth
--- a/progs/crawler3.scala	Tue Sep 24 01:12:36 2013 +0100
+++ b/progs/crawler3.scala	Tue Sep 24 01:56:53 2013 +0100
@@ -1,18 +1,11 @@
 import io.Source
 import scala.util.matching.Regex
+import scala.util._
 
 // gets the first ~10K of a page
-def get_page(url: String) : String = { 
-  try {
-    Source.fromURL(url).take(10000).mkString  
-  }
-  catch {
-    case _ : Throwable => {
-      println(s"  Problem with: $url")
-      ""
-    }
-  }
-}
+def get_page(url: String) : String = 
+  Try(Source.fromURL(url).take(10000).mkString) getOrElse 
+    { println(s"  Problem with: $url"); ""}
 
 // staring URL for the crawler
 val startURL = """http://www.inf.kcl.ac.uk/staff/urbanc/"""
@@ -27,7 +20,7 @@
 def unquote(s: String) = s.drop(1).dropRight(1)
 
 def get_all_URLs(page: String) : Set[String] = {
-  (http_pattern.findAllIn(page)).map { unquote(_) }.toSet
+  http_pattern.findAllIn(page).map(unquote).toSet
 }
 
 // naive version - seraches until a given depth
afl-material