aboutsummaryrefslogtreecommitdiff
path: root/doc
diff options
context:
space:
mode:
Diffstat (limited to 'doc')
-rw-r--r--doc/capture-output-file-with-parameter-reference.out24
-rw-r--r--doc/capture-output-file-with-parameter-reference.scm9
-rw-r--r--doc/capture-output-file.out23
-rw-r--r--doc/capture-output-file.scm8
-rw-r--r--doc/capture-stdout.out21
-rw-r--r--doc/capture-stdout.scm6
-rw-r--r--doc/ccwl.skb216
-rw-r--r--doc/ccwl.texi529
-rw-r--r--doc/checksum.out49
-rw-r--r--doc/checksum.scm16
-rw-r--r--doc/decompress-compile-run.out36
-rw-r--r--doc/decompress-compile-run.scm18
-rw-r--r--doc/hello-world.out13
-rw-r--r--doc/hello-world.scm5
-rw-r--r--doc/hello.tar.out2
15 files changed, 446 insertions, 529 deletions
diff --git a/doc/capture-output-file-with-parameter-reference.out b/doc/capture-output-file-with-parameter-reference.out
new file mode 100644
index 0000000..57369d2
--- /dev/null
+++ b/doc/capture-output-file-with-parameter-reference.out
@@ -0,0 +1,24 @@
+$ ccwl compile capture-output-file.scm > capture-output-file.cwl
+$ cwltool capture-output-file.cwl --archive hello.tar --extractfile hello.txt
+[workflow ] start
+[workflow ] starting step extract-specific-file
+[step extract-specific-file] start
+[job extract-specific-file] /tmp/751nydd1$ tar \
+ --extract \
+ --file \
+ /tmp/1zzw2n6m/stgc851e003-b5bd-437e-844b-311f6f66a7f1/hello.tar \
+ hello.txt
+[job extract-specific-file] completed success
+[step extract-specific-file] completed success
+[workflow ] completed success
+{
+ "extracted-file": {
+ "location": "file:///home/manimekalai/hello.txt",
+ "basename": "hello.txt",
+ "class": "File",
+ "checksum": "sha1$a0b65939670bc2c010f4d5d6a0b3e4e4590fb92b",
+ "size": 13,
+ "path": "/home/manimekalai/hello.txt"
+ }
+}
+Final process status is success
diff --git a/doc/capture-output-file-with-parameter-reference.scm b/doc/capture-output-file-with-parameter-reference.scm
new file mode 100644
index 0000000..3104fae
--- /dev/null
+++ b/doc/capture-output-file-with-parameter-reference.scm
@@ -0,0 +1,9 @@
+(define extract-specific-file
+ (command #:run "tar" "--extract" "--file" (input 'archive #:type 'File)
+ (input 'extractfile #:type 'string)
+ #:outputs (output 'extracted-file
+ #:type 'File
+ #:binding '((glob . "$(inputs.extractfile)")))))
+
+(workflow ((archive #:type File) (extractfile #:type string))
+ (extract-specific-file #:archive archive #:extractfile extractfile))
diff --git a/doc/capture-output-file.out b/doc/capture-output-file.out
new file mode 100644
index 0000000..32ee625
--- /dev/null
+++ b/doc/capture-output-file.out
@@ -0,0 +1,23 @@
+$ ccwl compile capture-output-file.scm > capture-output-file.cwl
+$ cwltool capture-output-file.cwl --archive hello.tar
+[workflow ] start
+[workflow ] starting step extract
+[step extract] start
+[job extract] /tmp/nrolttex$ tar \
+ --extract \
+ --file \
+ /tmp/z7pp7qwh/stg3ac272aa-3459-4f20-a033-86f53ba72caf/hello.tar
+[job extract] completed success
+[step extract] completed success
+[workflow ] completed success
+{
+ "extracted-file": {
+ "location": "file:///home/manimekalai/hello.txt",
+ "basename": "hello.txt",
+ "class": "File",
+ "checksum": "sha1$a0b65939670bc2c010f4d5d6a0b3e4e4590fb92b",
+ "size": 13,
+ "path": "/home/manimekalai/hello.txt"
+ }
+}
+Final process status is success
diff --git a/doc/capture-output-file.scm b/doc/capture-output-file.scm
new file mode 100644
index 0000000..b13549e
--- /dev/null
+++ b/doc/capture-output-file.scm
@@ -0,0 +1,8 @@
+(define extract
+ (command #:run "tar" "--extract" "--file" (input 'archive #:type 'File)
+ #:outputs (output 'extracted-file
+ #:type 'File
+ #:binding '((glob . "hello.txt")))))
+
+(workflow ((archive #:type File))
+ (extract #:archive archive))
diff --git a/doc/capture-stdout.out b/doc/capture-stdout.out
new file mode 100644
index 0000000..19568af
--- /dev/null
+++ b/doc/capture-stdout.out
@@ -0,0 +1,21 @@
+$ ccwl compile capture-stdout.scm > capture-stdout.cwl
+$ cwltool capture-stdout.cwl --message "Hello World!"
+[workflow ] start
+[workflow ] starting step print
+[step print] start
+[job print] /tmp/7zksx3xm$ echo \
+ 'Hello World!' > /tmp/7zksx3xm/51fe79d15e7790a9ded795304220d7a44aa84b48
+[job print] completed success
+[step print] completed success
+[workflow ] completed success
+{
+ "printed-message": {
+ "location": "file:///home/manimekalai/51fe79d15e7790a9ded795304220d7a44aa84b48",
+ "basename": "51fe79d15e7790a9ded795304220d7a44aa84b48",
+ "class": "File",
+ "checksum": "sha1$a0b65939670bc2c010f4d5d6a0b3e4e4590fb92b",
+ "size": 13,
+ "path": "/home/manimekalai/51fe79d15e7790a9ded795304220d7a44aa84b48"
+ }
+}
+Final process status is success
diff --git a/doc/capture-stdout.scm b/doc/capture-stdout.scm
new file mode 100644
index 0000000..1f26a95
--- /dev/null
+++ b/doc/capture-stdout.scm
@@ -0,0 +1,6 @@
+(define print
+ (command #:run "echo" (input 'message #:type 'string)
+ #:outputs (output 'printed-message #:type 'stdout)))
+
+(workflow ((message #:type string))
+ (print #:message message))
diff --git a/doc/ccwl.skb b/doc/ccwl.skb
new file mode 100644
index 0000000..c684caa
--- /dev/null
+++ b/doc/ccwl.skb
@@ -0,0 +1,216 @@
+(use-modules (skribilo lib)
+ (ccwl skribilo))
+
+(document :title [Concise Common Workflow Language]
+ (chapter :title [Introduction]
+ (p [,(abbr :short "CWL" :long "Common Workflow
+Language") is an open standard for describing analysis workflows and
+tools in a way that makes them portable and scalable across a variety
+of software and hardware environments.])
+ (p [,(abbr :short "ccwl" :long "Concise Common
+Workflow Language") is a concise syntax to express CWL workflows. It
+is implemented as an ,(abbr :short "EDSL" :long "Embedded Domain
+Specific Language") in the Scheme programming language, a minimalist
+dialect of the Lisp family of programming languages.])
+ (p [ccwl is a compiler to generate CWL workflows
+from concise descriptions in ccwl. In the future, ccwl will also have
+a runtime whereby users can interactively execute workflows while
+developing them.]))
+ (chapter :title [Tutorial]
+ (p [This tutorial will introduce you to writing
+workflows in ccwl. Some knowledge of CWL is assumed. To learn about
+CWL, please see the ,(ref :url "https://www.commonwl.org/user_guide/"
+:text "Common Workflow Language User Guide")])
+
+ (section :title [Important concepts]
+ (p [The CWL and ccwl workflow languages
+are statically typed programming languages where functions accept
+multiple named inputs and return multiple named outputs. Let 's break
+down what that means.])
+ (subsection :title [Static typing]
+ (p [In CWL ,the type of arguments accepted by a function and
+the type of outputs returned by that function are specified explicitly
+by the programmer ,and are known at compile time even before the code
+has been run. Hence ,we say that it is statically typed.]))
+ (subsection :title [Positional arguments and named arguments]
+ (p [In many languages ,the order of arguments passed to a
+function is significant. The position of each argument determines
+which formal argument it gets mapped to. For example ,passing
+positional arguments in Scheme looks like])
+ (prog :line #f [(foo 1 2)])
+ (p [In a language that supports named arguments ,the order of
+arguments is not significant. Each argument explicitly names the
+formal argument it gets mapped to. For example , in Scheme ,passing
+named arguments may look like]
+ (prog :line #f [(foo #:bar 1 #:baz 2)])))
+ (subsection :title [Multiple function arguments and return values]
+ (p [In most languages, functions accept multiple input
+arguments but only return a single output value. However, in CWL, a
+function can return multiple output values as well. These multiple
+outputs are unordered and are each addressed by a unique name.])))
+
+ (section :title [First example]
+ (p [As is tradition, let us start with a simple "Hello World"
+workflow in ccwl. This workflow accepts a string input and prints that
+string.])
+
+ (scheme-source "doc/hello-world.scm")
+
+ (p [The first form in this code defines the ,(code "print")
+command. This form is the equivalent of defining a
+,(code "CommandLineTool") class workflow in CWL. All arguments after
+,(code "#:run") specify the command that will be run. One of those
+arguments ,(code "(input 'message #:type 'string)") refers to a
+,(code "string") type input named ,(code "message"). Notice how the
+command definition is very close to a shell command, only that it is
+slightly annotated with inputs and their types.])
+
+ (p [The second form describes the actual workflow and is the
+equivalent of defining a ,(code "Workflow") class workflow in CWL. The
+form ,(code "((message #:type string))") specifies the inputs of the
+workflow. In this case, there is only one input---,(code "message") of
+type ,(code "string"). The body of the workflow specifies the commands
+that will be executed. The body of this workflow executes only a
+single command---the ,(code "print") command---passing the
+,(code "message") input of the workflow as the ,(code "message") input
+to the ,(code "print") command.])
+
+ (p [If this workflow is written to a file
+,(file "hello-world.scm"), we may compile it to CWL by running])
+
+ (prog :line #f [$ ccwl compile hello-world.scm])
+
+ (p [This prints a big chunk of generated CWL to standard
+output. We have achieved quite a lot of concision already! We write
+the generated CWL to a file and execute it using (command "cwltool")
+as follows. The expected output is also shown.])
+
+ (prog :line #f (source :file "doc/hello-world.out")))
+
+ (section :title [Capturing the standard output stream of a command]
+ (p [Let us return to the “Hello World” example in the previous
+section. But now ,let us capture the standard output of the
+,(code "print") command in an output object. The ccwl code is the same
+as earlier with only the addition of an ,(code "stdout") type output
+object to the command definition.])
+
+ (scheme-source "doc/capture-stdout.scm")
+
+ (p [Let's write this code to a file
+,(file "capture-stdout.scm"), generate CWL, write the generated CWL to
+,(file "capture-stdout.cwl"), and run it using ,(code "cwltool"). We
+might expect something like the output below. Notice how the standard
+output of the ,(code "print") command has been captured in the file
+,(file "51fe79d15e7790a9ded795304220d7a44aa84b48").])
+
+ (prog :line #f (source :file "doc/capture-stdout.out")))
+
+ (section :title [Capturing output files]
+ (p [In the previous section ,we captured the standard output
+stream of a command. But ,how do we capture any output files created
+by a command? Let us see.])
+
+ (p [Consider a tar archive ,(file "hello.tar") containing a file
+,(file "hello.txt").])
+
+ (prog :line #f (source :file "doc/hello.tar.out"))
+
+ (p [Let us write a workflow to extract the file
+,(file "hello.txt") from the archive. Everything in the following
+workflow except the ,(code "#:binding") parameter will already be
+familiar to you. The ,(code "#:binding") parameter sets the
+,(code "outputBinding") field in the generated CWL. In the example
+below, we set the ,(code "glob") field to look for a file named
+,(file "hello.txt").])
+
+ (scheme-source "doc/capture-output-file.scm")
+
+ (p [Writing this workflow to ,(file "capture-output-file.scm"),
+compiling and running it gives us the following output. Notice that
+the file ,(file "hello.txt") has been captured and is now present in
+our current working directory.])
+
+ (prog :line #f (source :file "doc/capture-output-file.out"))
+
+ (p [The above workflow is not awfully flexible. The name of the
+file to extract is hardcoded into the workflow. Let us modify the
+workflow to accept the name of the file to extract. We introduce
+,(code "extractfile"), a ,(code "string") type input that is passed to
+,(command "tar") and is referenced in the ,(code "glob") field.])
+
+ (scheme-source "doc/capture-output-file-with-parameter-reference.scm")
+
+ (p [Compiling and running this workflow gives us the following
+output.])
+
+ (prog :line #f (source :file "doc/capture-output-file-with-parameter-reference.out")))
+
+ (section :title [Workflow with multiple steps]
+ (p [Till now, we have only written trivial workflows with a
+single command. If we were only interested in executing single
+commands, we would hardly need a workflow language! So, in this
+section, let us write our first multi-step workflow and learn how to
+connect steps together in an arbitrary topology.])
+
+ (subsection :title [pipe]
+ (p [First ,the simplest of topologies---a linear chain
+representing sequential execution of steps. The following workflow
+decompresses a compressed C source file ,compiles and then executes
+it.])
+
+ (scheme-source "doc/decompress-compile-run.scm")
+
+ (p [Notice the ,(code "pipe") form in the body of the
+workflow. The ,(code "pipe") form specifies a list of steps to be
+executed sequentially. The workflow inputs coming into ,(code "pipe")
+are passed into the first step. Thereafter, the outputs of each step
+are passed as inputs into the next. Note that this has nothing to do
+with the Unix pipe. The inputs/outputs passed between steps are
+general CWL inputs/outputs. They need not be the standard stdin and
+stdout streams.])
+
+ ;; TODO: Add workflow graph
+
+ (p [Writing this worklow to
+,(file "decompress-compile-run.scm"), compiling and running it with
+the compressed C source file ,(file "hello.c.gz") gives us the
+following output.])
+
+ (prog :line #f (source :file "doc/decompress-compile-run.out"))
+
+ (p [The steps run in succession, and the stdout of the
+compiled executable is in
+,(file "c32c587f7afbdf87cf991c14a43edecf09cd93bf"). Success!]))
+
+ (subsection :title [tee]
+ (p [Next, the tee topology. The following workflow computes
+three different checksums of a given input file.])
+
+ (scheme-source "doc/checksum.scm")
+
+ (p [Notice the ,(code "tee") form in the body of the
+workflow. The ,(code "tee") form specifies a list of steps that are
+independent of each other. The workflow inputs coming into
+,(code "tee") are passed into every step contained in the body of the
+,(code "tee"). The outputs of each step are collected together and
+unioned as the output of the ,(code "tee").])
+
+ ;; TODO: Add workflow graph
+
+ (p [Writing this workflow to ,(file "checksum.scm"), compiling
+and running it with some file ,(file "hello.txt") gives us the
+following output.])
+
+ (prog :line #f (source :file "doc/checksum.out"))
+
+ (p [The MD5, SHA1 and SHA256 checksums are in the files
+,(file "112be1054505027982e64d56b0879049c12737c6"),
+,(file "d2f19c786fcd3feb329004c8747803fba581a02d") and
+,(file "0d2eaa5619c14b43326101200d0f27b0d8a1a4b1") respectively.]))))
+
+ (chapter :title [Contributing]
+ (p [ccwl is developed on GitHub at ,(ref
+:url "https://github.com/arunisaac/ccwl"). Feedback, suggestions,
+feature requests, bug reports and pull requests are all
+welcome. Unclear and unspecific error messages are considered a
+bug. Do report them!])))
diff --git a/doc/ccwl.texi b/doc/ccwl.texi
deleted file mode 100644
index afc7e7d..0000000
--- a/doc/ccwl.texi
+++ /dev/null
@@ -1,529 +0,0 @@
-\input texinfo
-@settitle Concise Common Workflow Language
-
-@include version.texi
-
-@copying
-Copyright @copyright{} 2021 Arun Isaac@*
-
-Permission is granted to copy, distribute and/or modify this document
-under the terms of the GNU Free Documentation License, Version 1.3 or
-any later version published by the Free Software Foundation; with no
-Invariant Sections, no Front-Cover Texts, and no Back-Cover Texts. A
-copy of the license is included in the section entitled ``GNU Free
-Documentation License''.
-@end copying
-
-@titlepage
-@title Concise Common Workflow Language
-@subtitle Writing Common Workflow Language workflows using ccwl
-@author The ccwl authors
-
-@page
-@vskip 0pt plus 1filll
-Edition @value{EDITION} @*
-@value{UPDATED} @*
-@insertcopying
-@end titlepage
-
-@contents
-
-@ifnottex
-@node Top
-@top Concise Common Workflow Language
-
-This manual documents @abbr{ccwl, Concise Common Workflow Language}
-version @value{VERSION}. ccwl is a concise syntax to express @abbr{CWL,
-Common Workflow Language} workflows.
-@end ifnottex
-
-@menu
-* Introduction:: What is ccwl?
-* Tutorial:: A quick tutorial to get started with ccwl
-* Contributing:: Contributing
-@end menu
-
-@node Introduction
-@chapter Introduction
-
-@abbr{CWL, Common Workflow Language} is an open standard for describing
-analysis workflows and tools in a way that makes them portable and
-scalable across a variety of software and hardware environments.
-
-@abbr{ccwl, Concise Common Workflow Language} is a concise syntax to
-express CWL workflows. It is implemented as an @abbr{EDSL, Embedded
-Domain Specific Language} in the Scheme programming language, a
-minimalist dialect of the Lisp family of programming languages.
-
-ccwl is a compiler to generate CWL workflows from concise descriptions
-in ccwl. In the future, ccwl will also have a runtime whereby users can
-interactively execute workflows while developing them.
-
-@node Tutorial
-@chapter Tutorial
-
-This tutorial will introduce you to writing workflows in ccwl. Some
-knowledge of CWL is assumed. To learn about CWL, please see the
-@url{https://www.commonwl.org/user_guide/, Common Workflow Language User
-Guide}.
-
-@menu
-* Important concepts:: Static typing, multiple named inputs and outputs
-* First example:: Our first ccwl workflow
-* Capturing stdout:: Capturing the standard output stream of a command
-* Capturing output files:: Capturing output files produced by a command
-* Workflow with multiple steps:: Connecting steps together in a graph
-@end menu
-
-@node Important concepts
-@section The CWL and ccwl workflow languages
-
-The CWL and ccwl workflow languages are statically typed programming
-languages where functions accept multiple named inputs and return
-multiple named outputs. Let's break down what that means.
-
-@subsection Static typing
-
-In CWL, the type of arguments accepted by a function and the type of
-outputs returned by that function are specified explicitly by the
-programmer, and are known at compile time even before the code has been
-run. Hence, we say that it is statically typed.
-
-@subsection Positional arguments and named arguments
-
-In many languages, the order of arguments passed to a function is
-significant. The position of each argument determines which formal
-argument it gets mapped to. For example, passing positional arguments in
-Scheme looks like
-
-@lisp
-(foo 1 2)
-@end lisp
-
-In a language that supports named arguments, the order of arguments is
-not significant. Each argument explicitly names the formal argument it
-gets mapped to. For example, in Scheme, passing named arguments may look
-like
-
-@lisp
-(foo #:bar 1 #:baz 2)
-@end lisp
-
-@subsection Multiple function arguments and return values
-
-In most languages, functions accept multiple input arguments but only
-return a single output value. However, in CWL, a function can return
-multiple output values as well. These multiple outputs are unordered and
-are each addressed by a unique name.
-
-@node First example
-@section First example
-
-As is tradition, let us start with a simple ``Hello World'' workflow in
-ccwl. This workflow accepts a string input and prints that string.
-
-@lisp
-(define print
- (command #:run "echo" (input 'message #:type 'string)))
-
-(workflow ((message #:type string))
- (print #:message message))
-@end lisp
-
-The first form in this code defines the @code{print} command. This form
-is the equivalent of defining a @code{CommandLineTool} class workflow in
-CWL. All arguments after @code{#:run} specify the command that will be
-run. One of those arguments @code{(input 'message #:type 'string)}
-refers to a @code{string} type input named @code{message}. Notice how
-the command definition is very close to a shell command, only that it is
-slightly annotated with inputs and their types.
-
-The second form describes the actual workflow and is the equivalent of
-defining a @code{Workflow} class workflow in CWL. The form
-@code{((message #:type string))} specifies the inputs of the
-workflow. In this case, there is only one input---@code{message} of type
-@code{string}. The body of the workflow specifies the commands that will
-be executed. The body of this workflow executes only a single
-command---the @code{print} command---passing the @code{message} input of
-the workflow as the @code{message} input to the @code{print} command.
-
-If this workflow is written to a file @file{hello-world.scm}, we may
-compile it to CWL by running
-
-@example
-$ ccwl compile hello-world.scm
-@end example
-
-This prints a big chunk of generated CWL to standard output. We have
-achieved quite a lot of concision already! We write the generated CWL to
-a file and execute it using @code{cwltool} as follows. The expected
-output is also shown.
-
-@example
-$ ccwl compile hello-world.scm > hello-world.cwl
-$ cwltool hello-world.cwl --message "Hello World!"
-[workflow ] start
-[workflow ] starting step echo
-[step echo] start
-[job echo] /tmp/zprgn3x0$ echo \
- 'Hello World!'
-Hello World!
-[job echo] completed success
-[step echo] completed success
-[workflow ] completed success
-@{@}
-Final process status is success
-@end example
-
-@node Capturing stdout
-@section Capturing the standard output stream of a command
-
-Let us return to the ``Hello World'' example in the previous
-section. But now, let us capture the standard output of the @code{print}
-command in an output object. The ccwl code is the same as earlier with
-only the addition of an @code{stdout} type output object to the command
-definition.
-
-@lisp
-(define print
- (command #:run "echo" (input 'message #:type 'string)
- #:outputs (output 'printed-message #:type 'stdout)))
-
-(workflow ((message #:type string))
- (print #:message message))
-@end lisp
-
-Let's write this code to a file @file{capture-stdout.scm}, generate CWL,
-write the generated CWL to @file{capture-stdout.cwl}, and run it using
-@code{cwltool}. We might expect something like the output below. Notice
-how the standard output of the @code{print} command has been captured in
-the file @file{51fe79d15e7790a9ded795304220d7a44aa84b48}.
-
-@example
-$ ccwl compile capture-stdout.scm > capture-stdout.cwl
-$ cwltool capture-stdout.cwl --message "Hello World!"
-[workflow ] start
-[workflow ] starting step print
-[step print] start
-[job print] /tmp/7zksx3xm$ echo \
- 'Hello World!' > /tmp/7zksx3xm/51fe79d15e7790a9ded795304220d7a44aa84b48
-[job print] completed success
-[step print] completed success
-[workflow ] completed success
-@{
- "printed-message": @{
- "location": "file:///home/manimekalai/51fe79d15e7790a9ded795304220d7a44aa84b48",
- "basename": "51fe79d15e7790a9ded795304220d7a44aa84b48",
- "class": "File",
- "checksum": "sha1$a0b65939670bc2c010f4d5d6a0b3e4e4590fb92b",
- "size": 13,
- "path": "/home/manimekalai/51fe79d15e7790a9ded795304220d7a44aa84b48"
- @}
-@}
-Final process status is success
-@end example
-
-@node Capturing output files
-@section Capturing output files
-
-In the previous section, we captured the standard output stream of a
-command. But, how do we capture any output files created by a command?
-Let us see.
-
-Consider a tar archive @file{hello.tar} containing a file
-@file{hello.txt}.
-
-@example
-$ tar --list --file hello.tar
-hello.txt
-@end example
-
-Let us write a workflow to extract the file @file{hello.txt} from the
-archive. Everything in the following workflow except the
-@code{#:binding} parameter will already be familiar to you. The
-@code{#:binding} parameter sets the @code{outputBinding} field in the
-generated CWL. In the example below, we set the @code{glob} field to
-look for a file named @file{hello.txt}.
-
-@lisp
-(define extract
- (command #:run "tar" "--extract" "--file" (input 'archive #:type 'File)
- #:outputs (output 'extracted-file
- #:type 'File
- #:binding '((glob . "hello.txt")))))
-
-(workflow ((archive #:type File))
- (extract #:archive archive))
-@end lisp
-
-Writing this workflow to @file{capture-output-file.scm}, compiling and
-running it gives us the following output. Notice that the file
-@file{hello.txt} has been captured and is now present in our current
-working directory.
-
-@example
-$ ccwl compile capture-output-file.scm > capture-output-file.cwl
-$ cwltool capture-output-file.cwl --archive hello.tar
-[workflow ] start
-[workflow ] starting step extract
-[step extract] start
-[job extract] /tmp/nrolttex$ tar \
- --extract \
- --file \
- /tmp/z7pp7qwh/stg3ac272aa-3459-4f20-a033-86f53ba72caf/hello.tar
-[job extract] completed success
-[step extract] completed success
-[workflow ] completed success
-@{
- "extracted-file": @{
- "location": "file:///home/manimekalai/hello.txt",
- "basename": "hello.txt",
- "class": "File",
- "checksum": "sha1$a0b65939670bc2c010f4d5d6a0b3e4e4590fb92b",
- "size": 13,
- "path": "/home/manimekalai/hello.txt"
- @}
-@}
-Final process status is success
-@end example
-
-The above workflow is not awfully flexible. The name of the file to
-extract is hardcoded into the workflow. Let us modify the workflow to
-accept the name of the file to extract. We introduce @code{extractfile},
-a @code{string} type input that is passed to @command{tar} and is
-referenced in the @code{glob} field.
-
-@lisp
-(define extract-specific-file
- (command #:run "tar" "--extract" "--file" (input 'archive #:type 'File)
- (input 'extractfile #:type 'string)
- #:outputs (output 'extracted-file
- #:type 'File
- #:binding '((glob . "$(inputs.extractfile)")))))
-
-(workflow ((archive #:type File) (extractfile #:type string))
- (extract-specific-file #:archive archive #:extractfile extractfile))
-@end lisp
-
-Compiling and running this workflow gives us the following output.
-
-@example
-$ ccwl compile capture-output-file.scm > capture-output-file.cwl
-$ cwltool capture-output-file.cwl --archive hello.tar --extractfile hello.txt
-[workflow ] start
-[workflow ] starting step extract-specific-file
-[step extract-specific-file] start
-[job extract-specific-file] /tmp/751nydd1$ tar \
- --extract \
- --file \
- /tmp/1zzw2n6m/stgc851e003-b5bd-437e-844b-311f6f66a7f1/hello.tar \
- hello.txt
-[job extract-specific-file] completed success
-[step extract-specific-file] completed success
-[workflow ] completed success
-@{
- "extracted-file": @{
- "location": "file:///home/manimekalai/hello.txt",
- "basename": "hello.txt",
- "class": "File",
- "checksum": "sha1$a0b65939670bc2c010f4d5d6a0b3e4e4590fb92b",
- "size": 13,
- "path": "/home/manimekalai/hello.txt"
- @}
-@}
-Final process status is success
-@end example
-
-@node Workflow with multiple steps
-@section Workflow with multiple steps
-
-Till now, we have only written trivial workflows with a single
-command. If we were only interested in executing single commands, we
-would hardly need a workflow language! So, in this section, let us write
-our first multi-step workflow and learn how to connect steps together in
-an arbitrary topology.
-
-@subsection pipe
-
-First, the simplest of topologies---a linear chain representing
-sequential execution of steps. The following workflow decompresses a
-compressed C source file, compiles and then executes it.
-
-@lisp
-(define decompress
- (command #:run "gzip" "--stdout" "--decompress" (input 'compressed #:type 'File)
- #:outputs (output 'decompressed #:type 'stdout)))
-
-(define compile
- (command #:run "gcc" "-x" "c" (input 'source #:type 'File)
- #:outputs (output 'executable
- #:type 'File
- #:binding '((glob . "a.out")))))
-
-(define run
- (command #:run (input 'executable)
- #:outputs (output 'stdout #:type 'stdout)))
-
-(workflow ((compressed-source #:type File))
- (pipe (decompress #:compressed compressed-source)
- (compile #:source decompressed)
- (run #:executable executable)))
-@end lisp
-
-Notice the @code{pipe} form in the body of the workflow. The @code{pipe}
-form specifies a list of steps to be executed sequentially. The workflow
-inputs coming into @code{pipe} are passed into the first
-step. Thereafter, the outputs of each step are passed as inputs into the
-next. Note that this has nothing to do with the Unix pipe. The
-inputs/outputs passed between steps are general CWL inputs/outputs. They
-need not be the standard stdin and stdout streams.
-
-@c TODO: Add workflow graph.
-
-Writing this worklow to @file{decompress-compile-run.scm}, compiling and
-running it with the compressed C source file @file{hello.c.gz} gives us
-the following output.
-
-@example
-$ ccwl compile decompress-compile-run.scm > decompress-compile-run.cwl
-$ cwltool decompress-compile-run.cwl --compressed-source hello.c.gz
-[workflow ] start
-[workflow ] starting step decompress
-[step decompress] start
-[job decompress] /tmp/3bsk5yfm$ gzip \
- --stdout \
- --decompress \
- /tmp/yn4wh0j8/stg1e0bc56d-f845-4a28-a685-1faf96129eac/hello.c.gz > /tmp/3bsk5yfm/eae8fb860f3b6eaf6ae2b9d9285b5c07cc457e90
-[job decompress] completed success
-[step decompress] completed success
-[workflow ] starting step compile
-[step compile] start
-[job compile] /tmp/lnjz1vik$ gcc \
- -x \
- c \
- /tmp/rpf9g_lj/stg1be6bb98-7101-4f46-9885-fe0a985dee73/eae8fb860f3b6eaf6ae2b9d9285b5c07cc457e90
-[job compile] completed success
-[step compile] completed success
-[workflow ] starting step run
-[step run] start
-[job run] /tmp/fftn945x$ /tmp/favjw7d5/stg2576ae91-5240-4731-b98d-dee0f8ef7703/a.out > /tmp/fftn945x/c32c587f7afbdf87cf991c14a43edecf09cd93bf
-[job run] completed success
-[step run] completed success
-[workflow ] completed success
-@{
- "stdout": @{
- "location": "file:///home/manimekalai/c32c587f7afbdf87cf991c14a43edecf09cd93bf",
- "basename": "c32c587f7afbdf87cf991c14a43edecf09cd93bf",
- "class": "File",
- "checksum": "sha1$a0b65939670bc2c010f4d5d6a0b3e4e4590fb92b",
- "size": 13,
- "path": "/home/manimekalai/c32c587f7afbdf87cf991c14a43edecf09cd93bf"
- @}
-@}
-Final process status is success
-@end example
-
-The steps run in succession, and the stdout of the compiled executable
-is in @file{c32c587f7afbdf87cf991c14a43edecf09cd93bf}. Success!
-
-@subsection tee
-
-Next, the tee topology. The following workflow computes three different
-checksums of a given input file.
-
-@lisp
-(define md5sum
- (command #:run "md5sum" (input 'file #:type 'File)
- #:outputs (output 'md5 #:type 'stdout)))
-
-(define sha1sum
- (command #:run "sha1sum" (input 'file #:type 'File)
- #:outputs (output 'sha1 #:type 'stdout)))
-
-(define sha256sum
- (command #:run "sha256sum" (input 'file #:type 'File)
- #:outputs (output 'sha256 #:type 'stdout)))
-
-(workflow ((file #:type File))
- (tee (md5sum #:file file)
- (sha1sum #:file file)
- (sha256sum #:file file)))
-@end lisp
-
-Notice the @code{tee} form in the body of the workflow. The @code{tee}
-form specifies a list of steps that are independent of each other. The
-workflow inputs coming into @code{tee} are passed into every step
-contained in the body of the @code{tee}. The outputs of each step are
-collected together and unioned as the output of the @code{tee}.
-
-@c TODO: Add workflow graph.
-
-Writing this workflow to @file{checksum.scm}, compiling and running it
-with some file @file{hello.txt} gives us the following output.
-
-@example
-$ ccwl compile checksum.scm > checksum.cwl
-$ cwltool checksum.cwl --file hello.txt
-[workflow ] start
-[workflow ] starting step sha256sum
-[step sha256sum] start
-[job sha256sum] /tmp/rjbcjppq$ sha256sum \
- /tmp/pc2bbl6o/stg2f7cdda0-9d89-47b7-96b6-fa377cc61c49/hello.txt > /tmp/rjbcjppq/0d2eaa5619c14b43326101200d0f27b0d8a1a4b1
-[job sha256sum] completed success
-[step sha256sum] completed success
-[workflow ] starting step sha1sum
-[step sha1sum] start
-[job sha1sum] /tmp/1cjtot5q$ sha1sum \
- /tmp/wliybbsp/stg993b2838-c803-4527-89d6-6a0cd7a0587a/hello.txt > /tmp/1cjtot5q/d2f19c786fcd3feb329004c8747803fba581a02d
-[job sha1sum] completed success
-[step sha1sum] completed success
-[workflow ] starting step md5sum
-[step md5sum] start
-[job md5sum] /tmp/z7fe89c7$ md5sum \
- /tmp/41nnygw9/stgebdc428b-ec84-4283-88ae-682c7f4628ac/hello.txt > /tmp/z7fe89c7/112be1054505027982e64d56b0879049c12737c6
-[job md5sum] completed success
-[step md5sum] completed success
-[workflow ] completed success
-@{
- "md5": @{
- "location": "file:///home/manimekalai/112be1054505027982e64d56b0879049c12737c6",
- "basename": "112be1054505027982e64d56b0879049c12737c6",
- "class": "File",
- "checksum": "sha1$dd2e54f3bd22a8bb4ffbf543151050ee9645baf2",
- "size": 98,
- "path": "/home/manimekalai/112be1054505027982e64d56b0879049c12737c6"
- @},
- "sha1": @{
- "location": "file:///home/manimekalai/d2f19c786fcd3feb329004c8747803fba581a02d",
- "basename": "d2f19c786fcd3feb329004c8747803fba581a02d",
- "class": "File",
- "checksum": "sha1$f4112d33f41bc98a114b35759c26eec9a9f4256c",
- "size": 106,
- "path": "/home/manimekalai/d2f19c786fcd3feb329004c8747803fba581a02d"
- @},
- "sha256": @{
- "location": "file:///home/manimekalai/0d2eaa5619c14b43326101200d0f27b0d8a1a4b1",
- "basename": "0d2eaa5619c14b43326101200d0f27b0d8a1a4b1",
- "class": "File",
- "checksum": "sha1$868ce04a610122b1c1f2846e5e9f9fc7a289d120",
- "size": 130,
- "path": "/home/manimekalai/0d2eaa5619c14b43326101200d0f27b0d8a1a4b1"
- @}
-@}
-Final process status is success
-@end example
-
-The MD5, SHA1 and SHA256 checksums are in the files
-@file{112be1054505027982e64d56b0879049c12737c6},
-@file{d2f19c786fcd3feb329004c8747803fba581a02d} and
-@file{0d2eaa5619c14b43326101200d0f27b0d8a1a4b1} respectively.
-
-@node Contributing
-@chapter Contributing
-
-ccwl is developed on GitHub at
-@url{https://github.com/arunisaac/ccwl}. Feedback, suggestions, feature
-requests, bug reports and pull requests are all welcome. Unclear and
-unspecific error messages are considered a bug. Do report them!
-
-@bye
diff --git a/doc/checksum.out b/doc/checksum.out
new file mode 100644
index 0000000..01d7155
--- /dev/null
+++ b/doc/checksum.out
@@ -0,0 +1,49 @@
+$ ccwl compile checksum.scm > checksum.cwl
+$ cwltool checksum.cwl --file hello.txt
+[workflow ] start
+[workflow ] starting step sha256sum
+[step sha256sum] start
+[job sha256sum] /tmp/rjbcjppq$ sha256sum \
+ /tmp/pc2bbl6o/stg2f7cdda0-9d89-47b7-96b6-fa377cc61c49/hello.txt > /tmp/rjbcjppq/0d2eaa5619c14b43326101200d0f27b0d8a1a4b1
+[job sha256sum] completed success
+[step sha256sum] completed success
+[workflow ] starting step sha1sum
+[step sha1sum] start
+[job sha1sum] /tmp/1cjtot5q$ sha1sum \
+ /tmp/wliybbsp/stg993b2838-c803-4527-89d6-6a0cd7a0587a/hello.txt > /tmp/1cjtot5q/d2f19c786fcd3feb329004c8747803fba581a02d
+[job sha1sum] completed success
+[step sha1sum] completed success
+[workflow ] starting step md5sum
+[step md5sum] start
+[job md5sum] /tmp/z7fe89c7$ md5sum \
+ /tmp/41nnygw9/stgebdc428b-ec84-4283-88ae-682c7f4628ac/hello.txt > /tmp/z7fe89c7/112be1054505027982e64d56b0879049c12737c6
+[job md5sum] completed success
+[step md5sum] completed success
+[workflow ] completed success
+{
+ "md5": {
+ "location": "file:///home/manimekalai/112be1054505027982e64d56b0879049c12737c6",
+ "basename": "112be1054505027982e64d56b0879049c12737c6",
+ "class": "File",
+ "checksum": "sha1$dd2e54f3bd22a8bb4ffbf543151050ee9645baf2",
+ "size": 98,
+ "path": "/home/manimekalai/112be1054505027982e64d56b0879049c12737c6"
+ },
+ "sha1": {
+ "location": "file:///home/manimekalai/d2f19c786fcd3feb329004c8747803fba581a02d",
+ "basename": "d2f19c786fcd3feb329004c8747803fba581a02d",
+ "class": "File",
+ "checksum": "sha1$f4112d33f41bc98a114b35759c26eec9a9f4256c",
+ "size": 106,
+ "path": "/home/manimekalai/d2f19c786fcd3feb329004c8747803fba581a02d"
+ },
+ "sha256": {
+ "location": "file:///home/manimekalai/0d2eaa5619c14b43326101200d0f27b0d8a1a4b1",
+ "basename": "0d2eaa5619c14b43326101200d0f27b0d8a1a4b1",
+ "class": "File",
+ "checksum": "sha1$868ce04a610122b1c1f2846e5e9f9fc7a289d120",
+ "size": 130,
+ "path": "/home/manimekalai/0d2eaa5619c14b43326101200d0f27b0d8a1a4b1"
+ }
+}
+Final process status is success
diff --git a/doc/checksum.scm b/doc/checksum.scm
new file mode 100644
index 0000000..206c2a0
--- /dev/null
+++ b/doc/checksum.scm
@@ -0,0 +1,16 @@
+(define md5sum
+ (command #:run "md5sum" (input 'file #:type 'File)
+ #:outputs (output 'md5 #:type 'stdout)))
+
+(define sha1sum
+ (command #:run "sha1sum" (input 'file #:type 'File)
+ #:outputs (output 'sha1 #:type 'stdout)))
+
+(define sha256sum
+ (command #:run "sha256sum" (input 'file #:type 'File)
+ #:outputs (output 'sha256 #:type 'stdout)))
+
+(workflow ((file #:type File))
+ (tee (md5sum #:file file)
+ (sha1sum #:file file)
+ (sha256sum #:file file)))
diff --git a/doc/decompress-compile-run.out b/doc/decompress-compile-run.out
new file mode 100644
index 0000000..7ab832e
--- /dev/null
+++ b/doc/decompress-compile-run.out
@@ -0,0 +1,36 @@
+$ ccwl compile decompress-compile-run.scm > decompress-compile-run.cwl
+$ cwltool decompress-compile-run.cwl --compressed-source hello.c.gz
+[workflow ] start
+[workflow ] starting step decompress
+[step decompress] start
+[job decompress] /tmp/3bsk5yfm$ gzip \
+ --stdout \
+ --decompress \
+ /tmp/yn4wh0j8/stg1e0bc56d-f845-4a28-a685-1faf96129eac/hello.c.gz > /tmp/3bsk5yfm/eae8fb860f3b6eaf6ae2b9d9285b5c07cc457e90
+[job decompress] completed success
+[step decompress] completed success
+[workflow ] starting step compile
+[step compile] start
+[job compile] /tmp/lnjz1vik$ gcc \
+ -x \
+ c \
+ /tmp/rpf9g_lj/stg1be6bb98-7101-4f46-9885-fe0a985dee73/eae8fb860f3b6eaf6ae2b9d9285b5c07cc457e90
+[job compile] completed success
+[step compile] completed success
+[workflow ] starting step run
+[step run] start
+[job run] /tmp/fftn945x$ /tmp/favjw7d5/stg2576ae91-5240-4731-b98d-dee0f8ef7703/a.out > /tmp/fftn945x/c32c587f7afbdf87cf991c14a43edecf09cd93bf
+[job run] completed success
+[step run] completed success
+[workflow ] completed success
+{
+ "stdout": {
+ "location": "file:///home/manimekalai/c32c587f7afbdf87cf991c14a43edecf09cd93bf",
+ "basename": "c32c587f7afbdf87cf991c14a43edecf09cd93bf",
+ "class": "File",
+ "checksum": "sha1$a0b65939670bc2c010f4d5d6a0b3e4e4590fb92b",
+ "size": 13,
+ "path": "/home/manimekalai/c32c587f7afbdf87cf991c14a43edecf09cd93bf"
+ }
+}
+Final process status is success
diff --git a/doc/decompress-compile-run.scm b/doc/decompress-compile-run.scm
new file mode 100644
index 0000000..437fb41
--- /dev/null
+++ b/doc/decompress-compile-run.scm
@@ -0,0 +1,18 @@
+(define decompress
+ (command #:run "gzip" "--stdout" "--decompress" (input 'compressed #:type 'File)
+ #:outputs (output 'decompressed #:type 'stdout)))
+
+(define compile
+ (command #:run "gcc" "-x" "c" (input 'source #:type 'File)
+ #:outputs (output 'executable
+ #:type 'File
+ #:binding '((glob . "a.out")))))
+
+(define run
+ (command #:run (input 'executable)
+ #:outputs (output 'stdout #:type 'stdout)))
+
+(workflow ((compressed-source #:type File))
+ (pipe (decompress #:compressed compressed-source)
+ (compile #:source decompressed)
+ (run #:executable executable)))
diff --git a/doc/hello-world.out b/doc/hello-world.out
new file mode 100644
index 0000000..3a783a1
--- /dev/null
+++ b/doc/hello-world.out
@@ -0,0 +1,13 @@
+$ ccwl compile hello-world.scm > hello-world.cwl
+$ cwltool hello-world.cwl --message "Hello World!"
+[workflow ] start
+[workflow ] starting step echo
+[step echo] start
+[job echo] /tmp/zprgn3x0$ echo \
+ 'Hello World!'
+Hello World!
+[job echo] completed success
+[step echo] completed success
+[workflow ] completed success
+{}
+Final process status is success \ No newline at end of file
diff --git a/doc/hello-world.scm b/doc/hello-world.scm
new file mode 100644
index 0000000..262b99f
--- /dev/null
+++ b/doc/hello-world.scm
@@ -0,0 +1,5 @@
+(define print
+ (command #:run "echo" (input 'message #:type 'string)))
+
+(workflow ((message #:type string))
+ (print #:message message))
diff --git a/doc/hello.tar.out b/doc/hello.tar.out
new file mode 100644
index 0000000..2d492b7
--- /dev/null
+++ b/doc/hello.tar.out
@@ -0,0 +1,2 @@
+$ tar --list --file hello.tar
+hello.txt