Dgsh – Directed graph shell

Syntax

A dgsh script follows the syntax of a bash(1) shell script with the addition of multipipe blocks. A multipipe block contains one or more dgsh simple commands, other multipipe blocks, or pipelines of the previous two types of commands. The commands in a multipipe block are executed asynchronously (in parallel, in the background). Data may be redirected or piped into and out of a multipipe block. With multipipe blocks dgsh scripts form directed acyclic process graphs. It follows from the above description that multipipe blocks can be recursively composed.

As a simple example consider running the following command directly within dgsh

{{ echo hello & echo world & }} | paste

or by invoking dgsh with the command as an argument.

dgsh -c '{{ echo hello & echo world & }} | paste'

The command will run paste with input from the twoecho processes to output hello world. This is equivalent to running the following bash command, but with the flow of data appearing in the natural left-to-right order.

paste 

In the following larger example, which implements a directory listing similar
to that of the Windows DIR command,
the output of ls is distributed to
six commands:awk, which sums the number of bytes and passes the
result to the tr command that deletes
newline characters,wc, which counts the number of files,awk, which counts the number of bytes,grep, which counts the number of directories and passes the
result to the tr command that deletes newline characters,
three echo commands, which provide the headers
of the data output by the commands described above.
All six commands pass their output
to the cat command, which gathers their outputs
in order.
FREE=$(df -h . | awk '!/Use%/{print $4}')

ls -n |
tee |
{{
        # Reorder fields in DIR-like way
        awk '!/^total/ {print $6, $7, $8, $1, sprintf("%8d", $5), $9}' &

        # Count number of files
        wc -l | tr -d \\n &

        # Print label for number of files
        echo -n ' File(s) ' &

        # Tally number of bytes
        awk '{s += $5} END {printf("%d bytes\n", s)}' &

        # Count number of directories
        grep -c '^d' | tr -d \\n &

        # Print label for number of dirs and calculate free bytes
        echo " Dir(s) $FREE bytes free" &
}} |
cat

Formally, dgsh extends the syntax of the (modified) Unix Bourne-shell
when bash provided with the --dgsh argument
as follows.
<dgsh_block>     ::= '{{' <dgsh_list> '}}'<dgsh_list>      ::= <dgsh_list_item> '&'<dgsh_list_item> <dgsh_list><dgsh_list_item> ::= <simple_command><dgsh_block><dgsh_list_item> '|' <dgsh_list_item>

Report file type, length, and compression performance for data received from the standard input. The data never touches the disk. Demonstrates the use of an output multipipe to source many commands from one followed by an input multipipe to sink to one command the output of many and the use of dgsh-tee that is used both to propagate the same input to many commands and collect output from many commands orderly in a way that is transparent to users.

#!/usr/bin/env dgsh

tee |
{{
	echo -n 'File type:' &
	file - &

	echo -n 'Original size:' &
	wc -c &

	echo -n 'xz:' &
	xz -c | wc -c &

	echo -n 'bzip2:' &
	bzip2 -c | wc -c &

	echo -n 'gzip:' &
	gzip -c | wc -c &
}} |
cat

Process the git history, and list the authors and days of the week ordered by the number of their commits. Demonstrates streams and piping through a function.

#!/usr/bin/env dgsh

forder()
{
	sort |
	uniq -c |
	sort -rn
}

export -f forder

git log --format="%an:%ad" --date=default "$@" |
tee |
{{
	echo "Authors ordered by number of commits" &
	# Order by frequency
	awk -F: '{print $1}' |
	call 'forder' &

	echo "Days ordered by number of commits" &
	# Order by frequency
	awk -F: '{print substr($2, 1, 3)}' |
	call 'forder' &
}} |
cat

Process a directory containing C source code, and produce a summary of various metrics. Demonstrates nesting, commands without input.

#!/usr/bin/env dgsh

{{
	# C and header code
	find "$@" \( -name \*.c -or -name \*.h \) -type f -print0 |
	tee |
	{{

		# Average file name length
		# Convert to newline separation for counting
		echo -n 'FNAMELEN: ' &
		tr \\0 \\n |
		# Remove path
		sed 's|^.*/||' |
		# Maintain average
		awk '{s += length($1); n++} END {
			if (n>0)
				print s / n;
			else
				print 0; }' &

		xargs -0 /bin/cat |
		tee |
		{{
			# Remove strings and comments
			sed 's/#/@/g;s/\\[\\"'\'']/@/g;s/"[^"]*"/""/g;'"s/'[^']*'/''/g" |
			cpp -P 2>/dev/null |
			tee |
			{{
				# Structure definitions
				echo -n 'NSTRUCT: ' &
				egrep -c 'struct[   ]*{|struct[   ]*[a-zA-Z_][a-zA-Z0-9_]*[       ]*{' &
				#}} (match preceding openings)

				# Type definitions
				echo -n 'NTYPEDEF: ' &
				grep -cw typedef &

				# Use of void
				echo -n 'NVOID: ' &
				grep -cw void &

				# Use of gets
	  			echo -n 'NGETS: ' &
	  			grep -cw gets &

				# Average identifier length
				echo -n 'IDLEN: ' &
				tr -cs 'A-Za-z0-9_' '\n' |
				sort -u |
				awk '/^[A-Za-z]/ { len += length($1); n++ } END {
					if (n>0)
						print len / n;
					else
						print 0; }' &
			}} &

			# Lines and characters
			echo -n 'CHLINESCHAR: ' &
			wc -lc |
			awk '{OFS=":"; print $1, $2}' &

			# Non-comment characters (rounded thousands)
			# -traditional avoids expansion of tabs
			# We round it to avoid failing due to minor
			# differences between preprocessors in regression
			# testing
			echo -n 'NCCHAR: ' &
			sed 's/#/@/g' |
			cpp -traditional -P 2>/dev/null |
			wc -c |
			awk '{OFMT = "%.0f"; print $1/1000}' &

			# Number of comments
			echo -n 'NCOMMENT: ' &
			egrep -c '/\*|//' &

			# Occurences of the word Copyright
			echo -n 'NCOPYRIGHT: ' &
			grep -ci copyright &
		}} &
	}} &

	# C files
	find "$@" -name \*.c -type f -print0 |
	tee |
	{{
		# Convert to newline separation for counting
		tr \\0 \\n |
		tee |
		{{
			# Number of C files
			echo -n 'NCFILE: ' &
			wc -l &

			# Number of directories containing C files
			echo -n 'NCDIR: ' &
			sed 's,/[^/]*$,,;s,^.*/,,' |
			sort -u |
			wc -l &
		}} &

		# C code
		xargs -0 /bin/cat |
		tee |
		{{
			# Lines and characters
			echo -n 'CLINESCHAR: ' &
			wc -lc |
			awk '{OFS=":"; print $1, $2}' &

			# C code without comments and strings
			sed 's/#/@/g;s/\\[\\"'\'']/@/g;s/"[^"]*"/""/g;'"s/'[^']*'/''/g" |
			cpp -P 2>/dev/null |
			tee |
			{{
				# Number of functions
				echo -n 'NFUNCTION: ' &
				grep -c '^{' &

				# Number of gotos
				echo -n 'NGOTO: ' &
				grep -cw goto &

				# Occurrences of the register keyword
				echo -n 'NREGISTER: ' &
				grep -cw register &

				# Number of macro definitions
				echo -n 'NMACRO: ' &
				grep -c '@[   ]*define[   ][   ]*[a-zA-Z_][a-zA-Z0-9_]*(' &
				# Number of include directives
				echo -n 'NINCLUDE: ' &
				grep -c '@[   ]*include' &

				# Number of constants
				echo -n 'NCONST: ' &
				grep -ohw '[0-9][x0-9][0-9a-f]*' | wc -l &

			}} &
		}} &
	}} &

	# Header files
	echo -n 'NHFILE: ' &
	find "$@" -name \*.h -type f |
	wc -l &

}} |
# Gather and print the results
cat

List the names of duplicate files in the specified directory. Demonstrates the combination of streams with a relational join.

#!/usr/bin/env dgsh

# Create list of files
find "$@" -type f |

# Produce lines of the form
# MD5(filename)= 811bfd4b5974f39e986ddc037e1899e7
xargs openssl md5 |

# Convert each line into a "filename md5sum" pair
sed 's/^MD5(//;s/)= / /' |

# Sort by MD5 sum
sort -k2 |

tee |
{{

	# Print an MD5 sum for each file that appears more than once
	awk '{print $2}' | uniq -d &

	# Promote the stream to gather it
	cat &
}} |
# Join the repeated MD5 sums with the corresponding file names
# Join expects two inputs, second will come from scatter
# XXX make streaming input identifiers transparent to users
join -2 2 |

# Output same files on a single line
awk '
BEGIN {ORS=""}
$1 != prev && prev {print "\n"}
END {if (prev) print "\n"}
{if (prev) print " "; prev = $1; print $2}'

Highlight the words that are misspelled in the command's first argument. Demonstrates stream processing with multipipes and the avoidance of pass-through constructs to avoid deadlocks.

#!/usr/bin/env dgsh

export LC_ALL=C

tee |
{{
	{{
		# Find errors
		tr -cs A-Za-z \\n |
		tr A-Z a-z |
		sort -u &

		# Ensure dictionary is sorted consistently with our settings
		sort /usr/share/dict/words &
	}} |
	comm -23 &

	cat &
}} |
grep -F -f - -i --color -w -C 2

Read text from the standard input and list words containing a two-letter palindrome, words containing four consonants, and words longer than 12 characters.

#!/usr/bin/env dgsh

# Consistent sorting across machines
export LC_ALL=C

# Stream input from file
cat $1 |

# Split input one word per line
tr -cs a-zA-Z \\n |
# Create list of unique words
sort -u |
tee |
{{
	# Pass through the original words
	cat &

	# List two-letter palindromes
	sed 's/.*\(.\)\(.\)\2\1.*/p: \1\2-\2\1/;t
		g' &

	# List four consecutive consonants
	sed -E 's/.*([^aeiouyAEIOUY]{4}).*/c: \1/;t
		g' &

	# List length of words longer than 12 characters
	awk '{if (length($1) > 12) print "l:", length($1);
		else print ""}' &
}} |
# Paste the four streams side-by-side
paste |
# List only words satisfying one or more properties
fgrep :

Creates a report for a fixed-size web log file read from the standard input. Demonstrates the combined use of multipipe blocks, writeval and readval to store and retrieve values, and functions in the scatter block. Used to measure throughput increase achieved through parallelism.

#!/usr/bin/env dgsh

# Output the top X elements of the input by the number of their occurrences
# X is the first argument
toplist()
{
	uniq -c | sort -rn | head -$1
	echo
}

# Output the argument as a section header
header()
{
	echo
	echo "$1"
	echo "$1" | sed 's/./-/g'
}

# Consistent sorting
export LC_ALL=C

export -f toplist
export -f header


cat <<EOF
			WWW server statistics
			=====================

Summary
-------
EOF

tee |
{{

	awk '{s += $NF} END {print s / 1024 / 1024 / 1024}' |
	tee |
	{{
		# Number of transferred bytes
		echo -n 'Number of Gbytes transferred: ' &
		cat &

		dgsh-writeval -s nXBytes &
	}} &

	# Number of log file bytes
	echo -n 'MBytes log file size: ' &
	wc -c |
	awk '{print $1 / 1024 / 1024}' &

	# Host names
	awk '{print $1}' |
	tee |
	{{
		wc -l |
		tee |
		{{
			# Number of accesses
			echo -n 'Number of accesses: ' &
			cat &

			dgsh-writeval -s nAccess &
		}} &

		# Sorted hosts
		sort |
		tee |
		{{

			# Unique hosts
			uniq |
			tee |
			{{
				# Number of hosts
				echo -n 'Number of hosts: ' &
				wc -l &

				# Number of TLDs
				echo -n 'Number of top level domains: ' &
				awk -F. '$NF !~ /[0-9]/ {print $NF}' |
				sort -u |
				wc -l &
			}} &

			# Top 10 hosts
			{{
				 call 'header "Top 10 Hosts"' &
				 call 'toplist 10' &
			}} &
		}} &

		# Top 20 TLDs
		{{
			call 'header "Top 20 Level Domain Accesses"' &
			awk -F. '$NF !~ /^[0-9]/ {print $NF}' |
			sort |
			call 'toplist 20' &
		}} &

		# Domains
		awk -F. 'BEGIN {OFS = "."}
		            $NF !~ /^[0-9]/ {$1 = ""; print}' |
		sort |
		tee |
		{{
			# Number of domains
			echo -n 'Number of domains: ' &
			uniq |
			wc -l &

			# Top 10 domains
			{{
				 call 'header "Top 10 Domains"' &
				 call 'toplist 10' &
			}} &
		}} &
	}} &

	# Hosts by volume
	{{
		call 'header "Top 10 Hosts by Transfer"' &
		awk '    {bytes[$1] += $NF}
		END {for (h in bytes) print bytes[h], h}' |
		sort -rn |
		head -10 &
	}} &

	# Sorted page name requests
	awk '{print $7}' |
	sort |
	tee |
	{{

		# Top 20 area requests (input is already sorted)
		{{
			 call 'header "Top 20 Area Requests"' &
			 awk -F/ '{print $2}' |
			 call 'toplist 20' &
		}} &

		# Number of different pages
		echo -n 'Number of different pages: ' &
		uniq |
		wc -l &

		# Top 20 requests
		{{
			 call 'header "Top 20 Requests"' &
			 call 'toplist 20' &
		}} &
	}} &

	# Access time: dd/mmm/yyyy:hh:mm:ss
	awk '{print substr($4, 2)}' |
	tee |
	{{

		# Just dates
		awk -F: '{print $1}' |
		tee |
		{{

			uniq |
			wc -l |
			tee |
			{{
				# Number of days
				echo -n 'Number of days: ' &
				cat &
				#|store:nDays

				echo -n 'Accesses per day: ' &
				awk '
					BEGIN {
					"dgsh-readval -l -x -q -s nAccess" | getline NACCESS;}
					{print NACCESS / $1}' &

				echo -n 'MBytes per day: ' &
				awk '
					BEGIN {
					"dgsh-readval -l -x -q -s nXBytes" | getline NXBYTES;}
					{print NXBYTES / $1 / 1024 / 1024}' &
			}} &

			{{
				 call 'header "Accesses by Date"' &
				 uniq -c &
			}} &

			# Accesses by day of week
			{{
				 call 'header "Accesses by Day of Week"' &
				 sed 's|/|-|g' |
				 call '(date -f - +%a 2>/dev/null || gdate -f - +%a)' |
				 sort |
				 uniq -c |
				 sort -rn &
			}} &
		}} &

		# Hour
		{{
			call 'header "Accesses by Local Hour"' &
			awk -F: '{print $2}' |
			sort |
			uniq -c &
		}} &
	}} &
}} |
cat

Read text from the standard input and create files containing word, character, digram, and trigram frequencies.

#!/usr/bin/env dgsh

# Consistent sorting across machines
export LC_ALL=C


# Convert input into a ranked frequency list
ranked_frequency()
{
	awk '{count[$1]++} END {for (i in count) print count[i], i}' |
	# We want the standard sort here
	sort -rn
}

# Convert standard input to a ranked frequency list of specified n-grams
ngram()
{
	local N=$1

	perl -ne 'for ($i = 0; $i < length($_) - '$N'; $i++) {
		print substr($_, $i, '$N'), "\n";
	}' |
	ranked_frequency
}

export -f ranked_frequency
export -f ngram

tee <$1 |
{{
	# Split input one word per line
	tr -cs a-zA-Z \\n |
	tee |
	{{
		# Digram frequency
		call 'ngram 2 >digram.txt' &
		# Trigram frequency
		call 'ngram 3 >trigram.txt' &
		# Word frequency
		call 'ranked_frequency >words.txt' &
	}} &

	# Store number of characters to use in awk below
	wc -c |
	dgsh-writeval -s nchars &

	# Character frequency
	sed 's/./&\
/g' |
	# Print absolute
	call 'ranked_frequency' |
	awk 'BEGIN {
		"dgsh-readval -l -x -q -s nchars" | getline NCHARS
		OFMT = "%.2g%%"}
		{print $1, $2, $1 / NCHARS * 100}' > character.txt &
}}

Given as an argument a directory containing object files, show which symbols are declared with global visibility, but should have been declared with file-local (static) visibility instead. Demonstrates the use of dgsh-capable comm (1) to combine data from two sources.

#!/usr/bin/env dgsh

# Find object files
find "$1" -name \*.o |

# Print defined symbols
xargs nm |

tee |
{{

  # List all defined (exported) symbols
  awk 'NF == 3 && $2 ~ /[A-Z]/ {print $3}' | sort &

  # List all undefined (imported) symbols
  awk '$1 == "U" {print $2}' | sort &

}} |
# Print exports that are not imported
comm -23

Given two directory hierarchies A and B passed as input arguments (where these represent a project at different parts of its lifetime) copy the files of hierarchy A to a new directory, passed as a third argument, corresponding to the structure of directories in B. Demonstrates the use of join to process results from two inputs and the use of gather to order asynchronously produced results.

#!/usr/bin/env dgsh

if [ ! -d "$1" -o ! -d "$2" -o -z "$3" ]
then
  echo "Usage: $0 dir-1 dir-2 new-dir-name" 1>&2
  exit 1
fi

NEWDIR="$3"

export LC_ALL=C

line_signatures()
{
  find $1 -type f -name '*.[chly]' -print |
  # Split path name into directory and file
  sed 's|\(.*\)/\([^/]*\)|\1 \2|' |
  while read dir file
  do
    # Print "directory filename content" of lines with
    # at least one alphabetic character
    # The fields are separated by  and 
    sed -n "/[a-z]/s|^|$dir$file|p" "$dir/$file"
  done |
  # Error: multi-character tab '\001\001'
  sort -T `pwd` -t -k 2
}


export -f line_signatures


{{
  # Generate the signatures for the two hierarchies
  call 'line_signatures "$1"' -- "$1" &
  call 'line_signatures "$1"' -- "$2" &
}} |

# Join signatures on file name and content
join -t -1 2 -2 2 |

# Print filename dir1 dir2
sed 's///g' |
awk -F 'BEGIN{OFS=" "}{print $1, $3, $4}' |

# Unique occurrences
sort -u |
tee |
{{
  # Commands to copy
  awk '{print "mkdir -p '$NEWDIR'/" $3 ""}' |
  sort -u &

  awk '{print "cp " $2 "/" $1 " '$NEWDIR'/" $3 "/" $1 ""}' &
}} |
# Order: first make directories, then copy files
# TODO: dgsh-tee does not pass along first incoming stream
cat |
sh

Process the git history, and create two PNG diagrams depicting committer activity over time. The most active committers appear at the center vertical of the diagram. Demonstrates image processing, mixining of synchronous and asynchronous processing in a scatter block, and the use of an dgsh-compliant join command.

#!/usr/bin/env dgsh

# Commit history in the form of ascending Unix timestamps, emails
git log --pretty=tformat:'%at %ae' |
# Filter records according to timestamp: keep (100000, now) seconds
awk 'NF == 2 && $1 > 100000 && $1 < '`date +%s` |
sort -n |
tee |
{{
	{{
		# Calculate number of committers
		awk '{print $2}' |
		sort -u |
		wc -l |
		tee |
		{{
			dgsh-writeval -s committers1 &

			dgsh-writeval -s committers2 &
			dgsh-writeval -s committers3 &
		}} &

		# Calculate last commit timestamp in seconds
		tail -1 |
		awk '{print $1}' &

		# Calculate first commit timestamp in seconds
		head -1 |
		awk '{print $1}' &
	}} |
	# Gather last and first commit timestamp
	tee |
	# Make one space-delimeted record
	tr '\n' ' ' |
	# Compute the difference in days
	awk '{print int(($1 - $2) / 60 / 60 / 24)}' |
	# Store number of days
	dgsh-writeval -s days &

	sort -k2 &	# <timestamp, email>

	# Place committers left/right of the median
	# according to the number of their commits
	awk '{print $2}' |
	sort |
	uniq -c |
	sort -n |
	awk '
		BEGIN {
			"dgsh-readval -l -x -q -s committers1" | getline NCOMMITTERS
			l = 0; r = NCOMMITTERS;}
		{print NR % 2 ? l++ : --r, $2}' |
	sort -k2 &	# <left/right, email>

}} |
# Join committer positions with commit time stamps
# based on committer email
join -j 2 |		# <email, timestamp, left/right>
# Order by timestamp
sort -k 2n |
tee |
{{
	# Create portable bitmap
	echo 'P1' &

	{{
		dgsh-readval -l -q -s committers2 &
		dgsh-readval -l -q -s days &
	}} |
	cat |
	tr '\n' ' ' |
	awk '{print $1, $2}' &

	perl -na -e '
	BEGIN { open(my $ncf, "-|", "dgsh-readval -l -x -q -s committers3");
		$ncommitters = <$ncf>;
		@empty[$ncommitters - 1] = 0; @committers = @empty; }
		sub out { print join("", map($_ ? "1" : "0", @committers)), "\n"; }

		$day = int($F[1] / 60 / 60 / 24);
		$pday = $day if (!defined($pday));

		while ($day != $pday) {
			out();
			@committers = @empty;
			$pday++;
		}

		$committers[$F[2]] = 1;

		END { out(); }
		' &
}} |
cat |
# Enlarge points into discs through morphological convolution
pgmmorphconv -erode <(
cat <<EOF
P1
7 7
1 1 1 0 1 1 1
1 1 0 0 0 1 1
1 0 0 0 0 0 1
0 0 0 0 0 0 0
1 0 0 0 0 0 1
1 1 0 0 0 1 1
1 1 1 0 1 1 1
EOF
) |
tee |
{{
	# Full-scale image
	pnmtopng >large.png &
	# A smaller image
	pamscale -width 640 |
	pnmtopng >small.png &
}}

# Close dgsh-writeval
#dgsh-readval -l -x -q -s committers

Create two graphs: 1) a broadened pulse and the real part of its 2D Fourier transform, and 2) a simulated air wave and the amplitude of its 2D Fourier transform. Demonstrates using the tools of the Madagascar shared research environment for computational data analysis in geophysics and related fields. Also demonstrates the use of two scatter blocks in the same script, and the used of named streams.

#!/usr/bin/env dgsh

mkdir -p Fig

# The SConstruct SideBySideIso "Result" method
side_by_side_iso()
{
	vppen size=r vpstyle=n gridnum=2,1 /dev/stdin $*
}

export -f side_by_side_iso

# A broadened pulse and the real part of its 2D Fourier transform
sfspike n1=64 n2=64 d1=1 d2=1 nsp=2 k1=16,17 k2=5,5 mag=16,16 \
	label1='time' label2='space' unit1= unit2= |
sfsmooth rect2=2 |
sfsmooth rect2=2 |
tee |
{{
	sfgrey pclip=100 wanttitle=n &
	#dgsh-writeval -s pulse.vpl &

	sffft1 |
	sffft3 axis=2 pad=1 |
	sfreal |
	tee |
	{{
		sfwindow f1=1 |
		sfreverse which=3 &

		cat &
		#dgsh-tee -I |
		#dgsh-writeval -s ft2d &
	}} |
	sfcat axis=1 "<|" |	# dgsh-readval
	sfgrey pclip=100 wanttitle=n \
		label1="1/time" label2="1/space" &
	#dgsh-writeval -s ft2d.vpl &
}} |
call 'side_by_side_iso "<|" \
	   yscale=1.25 >Fig/ft2dofpulse.vpl' &

# A simulated air wave and the amplitude of its 2D Fourier transform
sfspike n1=64 d1=1 o1=32 nsp=4 k1=1,2,3,4 mag=1,3,3,1 \
	label1='time' unit1= |
sfspray n=32 d=1 o=0 |
sfput label2=space |
sflmostretch delay=0 v0=-1 |
tee |
{{
	sfwindow f2=1 |
	sfreverse which=2 &

	cat &
	#dgsh-tee -I | dgsh-writeval -s air &
}} |
sfcat axis=2 "<|" |
tee |
{{
	sfgrey pclip=100 wanttitle=n &
	#| dgsh-writeval -s airtx.vpl &
	sffft1 |
	sffft3 sign=1 |
	tee |
	{{
		sfreal &
		#| dgsh-writeval -s airftr &
		sfimag &
		#| dgsh-writeval -s airfti &
	}} |
	sfmath nostdin=y re=/dev/stdin im="<|" output="sqrt(re*re+im*im)" |
	tee |
	{{
		sfwindow f1=1 |
		sfreverse which=3 &

		cat &
		#dgsh-tee -I | dgsh-writeval -s airft1 &
	}} |
	sfcat axis=1 "<|" |
	sfgrey pclip=100 wanttitle=n label1="1/time" \
		label2="1/space" &
	#| dgsh-writeval -s airfk.vpl
}} |
call 'side_by_side_iso "<|" \
		yscale=1.25 >Fig/airwave.vpl' &
#call 'side_by_side_iso airtx.vpl airfk.vpl \

wait

Nuclear magnetic resonance in-phase/anti-phase channel conversion and processing in heteronuclear single quantum coherence spectroscopy. Demonstrate processing of NMR data using the NMRPipe family of programs.

#!/usr/bin/env dgsh

# The conversion is configured for the following file:
# http://www.bmrb.wisc.edu/ftp/pub/bmrb/timedomain/bmr6443/timedomain_data/c13-hsqc/june11-se-6426-CA.fid/fid
var2pipe -in $1            \
 -xN            1280            -yN     256    \
 -xT            640             -yT     128    \
 -xMODE         Complex -yMODE  Complex      \
 -xSW           8000    -ySW    6000      \
 -xOBS          599.4489584     -yOBS   60.7485301      \
 -xCAR          4.73    -yCAR   118.000      \
 -xLAB          1H      -yLAB   15N      \
 -ndim          2       -aq2D   States      \
-verb  |
tee |
{{
  # IP/AP channel conversion
  # See http://tech.groups.yahoo.com/group/nmrpipe/message/389
  nmrPipe |
  nmrPipe -fn SOL |
  nmrPipe -fn SP -off 0.5 -end 0.98 -pow 2 -c 0.5 |
  nmrPipe -fn ZF -auto |
  nmrPipe -fn FT |
  nmrPipe -fn PS -p0 177 -p1 0.0 -di |
  nmrPipe -fn EXT -left -sw -verb |
  nmrPipe -fn TP |
  nmrPipe -fn COADD -cList 1 0 -time |
  nmrPipe -fn SP -off 0.5 -end 0.98 -pow 1 -c 0.5 |
  nmrPipe -fn ZF -auto |
  nmrPipe -fn FT |
  nmrPipe -fn PS -p0 0 -p1 0 -di |
  nmrPipe -fn TP |
  nmrPipe -fn POLY -auto -verb >A &

  nmrPipe |
  nmrPipe -fn SOL |
  nmrPipe -fn SP -off 0.5 -end 0.98 -pow 2 -c 0.5 |
  nmrPipe -fn ZF -auto |
  nmrPipe -fn FT |
  nmrPipe -fn PS -p0 177 -p1 0.0 -di |
  nmrPipe -fn EXT -left -sw -verb |
  nmrPipe -fn TP |
  nmrPipe -fn COADD -cList 0 1 -time |
  nmrPipe -fn SP -off 0.5 -end 0.98 -pow 1 -c 0.5 |
  nmrPipe -fn ZF -auto |
  nmrPipe -fn FT |
  nmrPipe -fn PS -p0 -90 -p1 0 -di |
  nmrPipe -fn TP |
  nmrPipe -fn POLY -auto -verb >B &

}}

# We use temporary files rather than streams, because
# addNMR mmaps its input files. The diagram displayed in the
# example shows the notional data flow.
addNMR -in1 A -in2 B -out A+B.dgsh.ft2 -c1 1.0 -c2 1.25 -add
addNMR -in1 A -in2 B -out A-B.dgsh.ft2 -c1 1.0 -c2 1.25 -sub

Calculate the iterative FFT for n = 8 in parallel. Demonstrates combined use of permute and multipipe blocks.

#!/usr/bin/env dgsh

fft-input $1 |
perm 1,5,3,7,2,6,4,8 |
{{
	{{
		w 1 0 &
		w 1 0 &
	}} |
	perm 1,3,2,4 |
	{{
		w 2 0 &
		w 2 1 &
	}} &

	{{
		w 1 0 &
		w 1 0 &
	}} |
	perm 1,3,2,4 |
	{{
		w 2 0 &
		w 2 1 &
	}} &
}} |
perm 1,5,3,7,2,6,4,8 |
{{
	w 3 0 &

	w 3 1 &

	w 3 2 &

	w 3 3 &
}} |
perm 1,5,2,6,3,7,4,8 |
cat

Combine, update, aggregate, summarise results files, such as logs. Demonstrates combined use of tools adapted for use with dgsh: sort, comm, paste, join, and diff.

#!/usr/bin/env dgsh

PSDIR=$1

cp $PSDIR/results $PSDIR/res

# Sort result files
{{
	sort $PSDIR/f4s &
	sort $PSDIR/f5s &
}} |
# Remove noise
comm |
{{
	# Paste to master results file
	paste $PSDIR/res > results &

	# Join with selected records
	join $PSDIR/top > top_results &

	# Diff from previous results file
	diff $PSDIR/last > diff_last &
}}

Reorder columns in a CSV document. Demonstrates the combined use of tee, cut, and paste.

#!/usr/bin/env dgsh

tee |
{{
	cut -d , -f 5-6 - &

	cut -d , -f 2-4 - &
}} |
paste -d ,

Windows-like DIR command for the current directory. Nothing that couldn't be done with ls -l | awk. Demonstrates combined use of stores and streams.

#!/usr/bin/env dgsh

FREE=`df -h . | awk '!/Use%/{print $4}'`

ls -n |
tee |
{{
	# Reorder fields in DIR-like way
	awk '!/^total/ {print $6, $7, $8, $1, sprintf("%8d", $5), $9}' &

	# Count number of files
	wc -l | tr -d \\n &

	# Print label for number of files
	echo -n ' File(s) ' &

	# Tally number of bytes
	awk '{s += $5} END {printf("%d bytes\n", s)}' &

	# Count number of directories
	grep -c '^d' | tr -d \\n &

	# Print label for number of dirs and calculate free bytes
	echo " Dir(s) $FREE bytes free" &
}} |
cat