.functions: Improve `httpcompression` and move it to its own file

Closes #162.

2 files changed, 127 insertions, 6 deletions

diff --git a/.functions b/.functions
index 5a2788b..418852e 100644
--- a/.functions
+++ b/.functions
@@ -112,12 +112,6 @@ function gz() {
 	printf "gzip: %d bytes (%2.2f%%)\n" "$gzipsize" "$ratio"
 }
 
-# Test if HTTP compression (RFC 2616 + SDCH) is enabled for a given URL.
-# Send a fake UA string for sites that sniff it instead of using the Accept-Encoding header. (Looking at you, ajax.googleapis.com!)
-function httpcompression() {
-	local encoding="$(curl -LIs -H 'User-Agent: Mozilla/5 Gecko' -H 'Accept-Encoding: gzip,deflate,compress,sdch' "$1" | grep '^Content-Encoding:')" && echo "$1 is encoded using ${encoding#* }" || echo "$1 is not using any encoding"
-}
-
 # Syntax-highlight JSON strings or files
 # Usage: `json '{"foo":42}'` or `echo '{"foo":42}' | json`
 function json() {
diff --git a/bin/httpcompression b/bin/httpcompression
new file mode 100755
index 0000000..444f719
--- /dev/null
+++ b/bin/httpcompression
@@ -0,0 +1,127 @@
+#!/usr/bin/env bash
+
+# Test if HTTP compression (RFC 2616 + SDCH) is enabled for a given URL
+
+declare -r hUA="Mozilla/5.0 Gecko"
+declare -r hAE="Accept-Encoding: gzip, deflate, sdch"
+declare -r maxConTime=15
+declare -r maxTime=30
+
+declare availDicts="" dict="" dictClientID="" dicts="" headers="" i="" \
+        indent="" url="" encoding="" urlHeaders=""
+
+headers="$( curl --connect-timeout $maxConTime \
+                 -A "$hUA"    `# Send a fake UA string for sites
+                               # that sniff it instead of using
+                               # the Accept-Encoding header` \
+                 -D -         `# Get response headers` \
+                 -H "$hAE"     \
+                 -L           `# If the page was moved to a different
+                               # location, redo the request` \
+                 -m $maxTime   \
+                 -s           `# Don\'t show the progress meter` \
+                 -S           `# Show error messages` \
+                 -o /dev/null `# Ignore content` \
+                 "$1" )" \
+&& ( \
+
+	url="$1"
+
+	# Iterate over the headers of all redirects
+	while [ -n "$headers" ]; do
+
+		# Get headers for the "current" URL
+		urlHeaders="$( printf "%s" "$headers" |
+		               sed -n '1,/^HTTP/p' )"
+
+		# Remove the headers for the "current" URL
+		headers="${headers/"$urlHeaders"/}"
+
+		# ----------------------------------------------------------------------
+		# | SDCH                                                               |
+		# ----------------------------------------------------------------------
+
+		# SDCH Specification:
+		# - www.blogs.zeenor.com/wp-content/uploads/2011/01/Shared_Dictionary_Compression_over_HTTP.pdf
+
+		# Check if the server advertised any dictionaries
+		dicts="$( printf "%s" "$urlHeaders" |
+		          grep -i 'Get-Dictionary:' |
+		          cut -d':' -f2 |
+		          sed s/,/\ /g )"
+
+		if [ -n "$dicts" ]; then
+
+			availDicts=""
+			dict=""
+
+			for i in $dicts; do
+
+				# Check If the dictionary location is specified as a path,
+				# and if so, construct it's URL from the host name of the
+				# referrer URL
+				[[ "$i" != http* ]] \
+				    && dict="$(printf "$url" |
+				               sed -En 's/([^/]*\/\/)?([^/]*)\/?.*/\1\2/p')"
+
+				dict="$dict$i"
+
+				# Request the dictionaries from the server and
+				# construct the `Avail-Dictionary` header value
+				#
+				# [ The user agent identifier for a dictionary is defined
+				#   as the URL-safe base64 encoding (as described in RFC
+				#   3548, section 4 [RFC3548]) of the first 48 bits (bits
+				#   0..47) of the dictionary's SHA-256 digest ]
+				#
+				dictClientID="$( curl --connect-timeout $maxConTime \
+				                      -A "$hUA" -LsS -m $maxTime "$dict" |
+				                 openssl dgst -sha256 -binary |
+				                 openssl base64 |
+				                 cut -c 1-8 |
+				                 sed -e 's/\+/-/' -e 's/\//_/' )"
+
+				[ -n $availDicts ] && availDicts="$adics,$dictClientID" \
+				                   || availDicts="$dictClientID"
+
+			done
+
+			# Redo the request (advertising the available dictionaries)
+			# and replace the old resulted headers with the new ones
+			urlHeaders="$( curl --connect-timeout $maxConTime \
+			                    -A "$hUA" -D - -H "$hAE" \
+			                    -H "Avail-Dictionary: $availDicts" \
+			                    -m $maxTime -o /dev/null -sS "$1" )"
+		fi
+
+		# ----------------------------------------------------------------------
+
+		# Get the content encoding header values
+		encoding="$( printf "%s" "$urlHeaders" |
+		             grep -i 'Content-Encoding:' |
+		             cut -d' ' -f2 |
+		             tr "\r" "," |
+		             tr -d "\n" |
+		             sed 's/,$//' )"
+
+		[ -n "$encoding" ] && encoding="[$encoding]"
+
+		# Print the output for the "current" URL
+		if [ "$url" != "$1" ]; then
+			printf "%s\n" "$indent$url $encoding"
+			indent="  "$indent
+		else
+			printf "\n%s\n" " $1 $encoding"
+			indent=" ↳"
+		fi
+
+		# Get the next URL value
+		url="$( printf "%s" "$urlHeaders" |
+		        grep -i 'Location' |
+		        sed -e 's/Location://' |
+		        tr -d '\r' )"
+
+	done
+	printf "\n"
+
+) || printf ""