Added dissect_url

README.md

@@ -34,6 +34,34 @@ Example:
     00000008  01110010 01101100 01100100 00001010  |rld.|
     $
 
+### dissect\_url ###
+
+Split URLs into components and arguments.  Output is useful to see more easily
+what is or is not in the URL and/or compare URls using standard tools like diff.
+
+    $ dissect_url "proto://srv:port/a/query?par1=foo&par2=bar#joe&mary"
+    proto://srv:port
+        /a/query
+        ?
+            par1=foo&
+            par2=bar
+        #
+            joe
+
+Note that by removing all whitespace from the dissected URL you should get the
+original URL.
+
+To enter multiple URLs, simply omit the argument; script will go into filter
+mode, where you can enter URLs one per line.  Quit this mode by entering *EOF*
+(`Ctrl+D`) or an empty line.  From this mode, output will be separated like this:
+
+    $ dissect_url < two_urls
+    === url 01 =============================================
+    url1
+
+    === url 02 =============================================
+    url2
+
 
 ### mkexec.pl ###
 

bin/dissect_url

@@ -0,0 +1,23 @@
+#!/bin/bash
+
+dissect() {
+    echo $* | perl -pe '
+        s|(\w)(/[^/])|$1\n    $2|;
+        s|\?|\n    ?\n        |;
+        s|#|\n    #\n        |;
+        s|&|&\n        |g;'
+    echo ""
+}
+
+if [[ -n "$1" ]]; then
+    dissect "$1"
+else
+    i=0
+    while read url;
+    do
+        if [[ -z "$url" ]]; then exit 0; fi
+        i=`expr $i + 1`
+        printf "=== url %02d =============================================\n" $i
+        dissect "$url"
+    done
+fi