diff --git a/.boring b/.boring
new file mode 100644
--- /dev/null
+++ b/.boring
@@ -0,0 +1,116 @@
+# Boring file regexps:
+
+# Stuff that's boring for txt-sushi
+^dist$
+
+### compiler and interpreter intermediate files
+# haskell (ghc) interfaces
+\.hi$
+\.hi-boot$
+\.o-boot$
+# object files
+\.o$
+\.o\.cmd$
+# profiling haskell
+\.p_hi$
+\.p_o$
+# haskell program coverage resp. profiling info
+\.tix$
+\.prof$
+# fortran module files
+\.mod$
+# linux kernel
+\.ko\.cmd$
+\.mod\.c$
+(^|/)\.tmp_versions($|/)
+# *.ko files aren't boring by default because they might
+# be Korean translations rather than kernel modules
+# \.ko$
+# python, emacs, java byte code
+\.py[co]$
+\.elc$
+\.class$
+# objects and libraries; lo and la are libtool things
+\.(obj|a|exe|so|lo|la)$
+# compiled zsh configuration files
+\.zwc$
+# Common LISP output files for CLISP and CMUCL
+\.(fas|fasl|sparcf|x86f)$
+
+### build and packaging systems
+# cabal intermediates
+\.installed-pkg-config
+\.setup-config
+# standard cabal build dir, might not be boring for everybody
+# ^dist(/|$)
+# autotools
+(^|/)autom4te\.cache($|/)
+(^|/)config\.(log|status)$
+# microsoft web expression, visual studio metadata directories
+\_vti_cnf$
+\_vti_pvt$
+# gentoo tools
+\.revdep-rebuild.*
+# generated dependencies
+^\.depend$
+
+### version control systems
+# cvs
+(^|/)CVS($|/)
+\.cvsignore$
+# cvs, emacs locks
+^\.#
+# rcs
+(^|/)RCS($|/)
+,v$
+# subversion
+(^|/)\.svn($|/)
+# mercurial
+(^|/)\.hg($|/)
+# git
+(^|/)\.git($|/)
+# bzr
+\.bzr$
+# sccs
+(^|/)SCCS($|/)
+# darcs
+(^|/)_darcs($|/)
+(^|/)\.darcsrepo($|/)
+^\.darcs-temp-mail$
+-darcs-backup[[:digit:]]+$
+# gnu arch
+(^|/)(\+|,)
+(^|/)vssver\.scc$
+\.swp$
+(^|/)MT($|/)
+(^|/)\{arch\}($|/)
+(^|/).arch-ids($|/)
+# bitkeeper
+(^|/)BitKeeper($|/)
+(^|/)ChangeSet($|/)
+
+### miscellaneous
+# backup files
+~$
+\.bak$
+\.BAK$
+# patch originals and rejects
+\.orig$
+\.rej$
+# X server
+\..serverauth.*
+# image spam
+\#
+(^|/)Thumbs\.db$
+# vi, emacs tags
+(^|/)(tags|TAGS)$
+#(^|/)\.[^/]
+# core dumps
+(^|/|\.)core$
+# partial broken files (KIO copy operations)
+\.part$
+# waf files, see http://code.google.com/p/waf/
+(^|/)\.waf-[[:digit:].]+-[[:digit:]]+($|/)
+(^|/)\.lock-wscript$
+# mac os finder
+(^|/)\.DS_Store$
diff --git a/COPYING b/COPYING
new file mode 100644
--- /dev/null
+++ b/COPYING
@@ -0,0 +1,674 @@
+ GNU GENERAL PUBLIC LICENSE
+ Version 3, 29 June 2007
+
+ Copyright (C) 2007 Free Software Foundation, Inc.
+ Everyone is permitted to copy and distribute verbatim copies
+ of this license document, but changing it is not allowed.
+
+ Preamble
+
+ The GNU General Public License is a free, copyleft license for
+software and other kinds of works.
+
+ The licenses for most software and other practical works are designed
+to take away your freedom to share and change the works. By contrast,
+the GNU General Public License is intended to guarantee your freedom to
+share and change all versions of a program--to make sure it remains free
+software for all its users. We, the Free Software Foundation, use the
+GNU General Public License for most of our software; it applies also to
+any other work released this way by its authors. You can apply it to
+your programs, too.
+
+ When we speak of free software, we are referring to freedom, not
+price. Our General Public Licenses are designed to make sure that you
+have the freedom to distribute copies of free software (and charge for
+them if you wish), that you receive source code or can get it if you
+want it, that you can change the software or use pieces of it in new
+free programs, and that you know you can do these things.
+
+ To protect your rights, we need to prevent others from denying you
+these rights or asking you to surrender the rights. Therefore, you have
+certain responsibilities if you distribute copies of the software, or if
+you modify it: responsibilities to respect the freedom of others.
+
+ For example, if you distribute copies of such a program, whether
+gratis or for a fee, you must pass on to the recipients the same
+freedoms that you received. You must make sure that they, too, receive
+or can get the source code. And you must show them these terms so they
+know their rights.
+
+ Developers that use the GNU GPL protect your rights with two steps:
+(1) assert copyright on the software, and (2) offer you this License
+giving you legal permission to copy, distribute and/or modify it.
+
+ For the developers' and authors' protection, the GPL clearly explains
+that there is no warranty for this free software. For both users' and
+authors' sake, the GPL requires that modified versions be marked as
+changed, so that their problems will not be attributed erroneously to
+authors of previous versions.
+
+ Some devices are designed to deny users access to install or run
+modified versions of the software inside them, although the manufacturer
+can do so. This is fundamentally incompatible with the aim of
+protecting users' freedom to change the software. The systematic
+pattern of such abuse occurs in the area of products for individuals to
+use, which is precisely where it is most unacceptable. Therefore, we
+have designed this version of the GPL to prohibit the practice for those
+products. If such problems arise substantially in other domains, we
+stand ready to extend this provision to those domains in future versions
+of the GPL, as needed to protect the freedom of users.
+
+ Finally, every program is threatened constantly by software patents.
+States should not allow patents to restrict development and use of
+software on general-purpose computers, but in those that do, we wish to
+avoid the special danger that patents applied to a free program could
+make it effectively proprietary. To prevent this, the GPL assures that
+patents cannot be used to render the program non-free.
+
+ The precise terms and conditions for copying, distribution and
+modification follow.
+
+ TERMS AND CONDITIONS
+
+ 0. Definitions.
+
+ "This License" refers to version 3 of the GNU General Public License.
+
+ "Copyright" also means copyright-like laws that apply to other kinds of
+works, such as semiconductor masks.
+
+ "The Program" refers to any copyrightable work licensed under this
+License. Each licensee is addressed as "you". "Licensees" and
+"recipients" may be individuals or organizations.
+
+ To "modify" a work means to copy from or adapt all or part of the work
+in a fashion requiring copyright permission, other than the making of an
+exact copy. The resulting work is called a "modified version" of the
+earlier work or a work "based on" the earlier work.
+
+ A "covered work" means either the unmodified Program or a work based
+on the Program.
+
+ To "propagate" a work means to do anything with it that, without
+permission, would make you directly or secondarily liable for
+infringement under applicable copyright law, except executing it on a
+computer or modifying a private copy. Propagation includes copying,
+distribution (with or without modification), making available to the
+public, and in some countries other activities as well.
+
+ To "convey" a work means any kind of propagation that enables other
+parties to make or receive copies. Mere interaction with a user through
+a computer network, with no transfer of a copy, is not conveying.
+
+ An interactive user interface displays "Appropriate Legal Notices"
+to the extent that it includes a convenient and prominently visible
+feature that (1) displays an appropriate copyright notice, and (2)
+tells the user that there is no warranty for the work (except to the
+extent that warranties are provided), that licensees may convey the
+work under this License, and how to view a copy of this License. If
+the interface presents a list of user commands or options, such as a
+menu, a prominent item in the list meets this criterion.
+
+ 1. Source Code.
+
+ The "source code" for a work means the preferred form of the work
+for making modifications to it. "Object code" means any non-source
+form of a work.
+
+ A "Standard Interface" means an interface that either is an official
+standard defined by a recognized standards body, or, in the case of
+interfaces specified for a particular programming language, one that
+is widely used among developers working in that language.
+
+ The "System Libraries" of an executable work include anything, other
+than the work as a whole, that (a) is included in the normal form of
+packaging a Major Component, but which is not part of that Major
+Component, and (b) serves only to enable use of the work with that
+Major Component, or to implement a Standard Interface for which an
+implementation is available to the public in source code form. A
+"Major Component", in this context, means a major essential component
+(kernel, window system, and so on) of the specific operating system
+(if any) on which the executable work runs, or a compiler used to
+produce the work, or an object code interpreter used to run it.
+
+ The "Corresponding Source" for a work in object code form means all
+the source code needed to generate, install, and (for an executable
+work) run the object code and to modify the work, including scripts to
+control those activities. However, it does not include the work's
+System Libraries, or general-purpose tools or generally available free
+programs which are used unmodified in performing those activities but
+which are not part of the work. For example, Corresponding Source
+includes interface definition files associated with source files for
+the work, and the source code for shared libraries and dynamically
+linked subprograms that the work is specifically designed to require,
+such as by intimate data communication or control flow between those
+subprograms and other parts of the work.
+
+ The Corresponding Source need not include anything that users
+can regenerate automatically from other parts of the Corresponding
+Source.
+
+ The Corresponding Source for a work in source code form is that
+same work.
+
+ 2. Basic Permissions.
+
+ All rights granted under this License are granted for the term of
+copyright on the Program, and are irrevocable provided the stated
+conditions are met. This License explicitly affirms your unlimited
+permission to run the unmodified Program. The output from running a
+covered work is covered by this License only if the output, given its
+content, constitutes a covered work. This License acknowledges your
+rights of fair use or other equivalent, as provided by copyright law.
+
+ You may make, run and propagate covered works that you do not
+convey, without conditions so long as your license otherwise remains
+in force. You may convey covered works to others for the sole purpose
+of having them make modifications exclusively for you, or provide you
+with facilities for running those works, provided that you comply with
+the terms of this License in conveying all material for which you do
+not control copyright. Those thus making or running the covered works
+for you must do so exclusively on your behalf, under your direction
+and control, on terms that prohibit them from making any copies of
+your copyrighted material outside their relationship with you.
+
+ Conveying under any other circumstances is permitted solely under
+the conditions stated below. Sublicensing is not allowed; section 10
+makes it unnecessary.
+
+ 3. Protecting Users' Legal Rights From Anti-Circumvention Law.
+
+ No covered work shall be deemed part of an effective technological
+measure under any applicable law fulfilling obligations under article
+11 of the WIPO copyright treaty adopted on 20 December 1996, or
+similar laws prohibiting or restricting circumvention of such
+measures.
+
+ When you convey a covered work, you waive any legal power to forbid
+circumvention of technological measures to the extent such circumvention
+is effected by exercising rights under this License with respect to
+the covered work, and you disclaim any intention to limit operation or
+modification of the work as a means of enforcing, against the work's
+users, your or third parties' legal rights to forbid circumvention of
+technological measures.
+
+ 4. Conveying Verbatim Copies.
+
+ You may convey verbatim copies of the Program's source code as you
+receive it, in any medium, provided that you conspicuously and
+appropriately publish on each copy an appropriate copyright notice;
+keep intact all notices stating that this License and any
+non-permissive terms added in accord with section 7 apply to the code;
+keep intact all notices of the absence of any warranty; and give all
+recipients a copy of this License along with the Program.
+
+ You may charge any price or no price for each copy that you convey,
+and you may offer support or warranty protection for a fee.
+
+ 5. Conveying Modified Source Versions.
+
+ You may convey a work based on the Program, or the modifications to
+produce it from the Program, in the form of source code under the
+terms of section 4, provided that you also meet all of these conditions:
+
+ a) The work must carry prominent notices stating that you modified
+ it, and giving a relevant date.
+
+ b) The work must carry prominent notices stating that it is
+ released under this License and any conditions added under section
+ 7. This requirement modifies the requirement in section 4 to
+ "keep intact all notices".
+
+ c) You must license the entire work, as a whole, under this
+ License to anyone who comes into possession of a copy. This
+ License will therefore apply, along with any applicable section 7
+ additional terms, to the whole of the work, and all its parts,
+ regardless of how they are packaged. This License gives no
+ permission to license the work in any other way, but it does not
+ invalidate such permission if you have separately received it.
+
+ d) If the work has interactive user interfaces, each must display
+ Appropriate Legal Notices; however, if the Program has interactive
+ interfaces that do not display Appropriate Legal Notices, your
+ work need not make them do so.
+
+ A compilation of a covered work with other separate and independent
+works, which are not by their nature extensions of the covered work,
+and which are not combined with it such as to form a larger program,
+in or on a volume of a storage or distribution medium, is called an
+"aggregate" if the compilation and its resulting copyright are not
+used to limit the access or legal rights of the compilation's users
+beyond what the individual works permit. Inclusion of a covered work
+in an aggregate does not cause this License to apply to the other
+parts of the aggregate.
+
+ 6. Conveying Non-Source Forms.
+
+ You may convey a covered work in object code form under the terms
+of sections 4 and 5, provided that you also convey the
+machine-readable Corresponding Source under the terms of this License,
+in one of these ways:
+
+ a) Convey the object code in, or embodied in, a physical product
+ (including a physical distribution medium), accompanied by the
+ Corresponding Source fixed on a durable physical medium
+ customarily used for software interchange.
+
+ b) Convey the object code in, or embodied in, a physical product
+ (including a physical distribution medium), accompanied by a
+ written offer, valid for at least three years and valid for as
+ long as you offer spare parts or customer support for that product
+ model, to give anyone who possesses the object code either (1) a
+ copy of the Corresponding Source for all the software in the
+ product that is covered by this License, on a durable physical
+ medium customarily used for software interchange, for a price no
+ more than your reasonable cost of physically performing this
+ conveying of source, or (2) access to copy the
+ Corresponding Source from a network server at no charge.
+
+ c) Convey individual copies of the object code with a copy of the
+ written offer to provide the Corresponding Source. This
+ alternative is allowed only occasionally and noncommercially, and
+ only if you received the object code with such an offer, in accord
+ with subsection 6b.
+
+ d) Convey the object code by offering access from a designated
+ place (gratis or for a charge), and offer equivalent access to the
+ Corresponding Source in the same way through the same place at no
+ further charge. You need not require recipients to copy the
+ Corresponding Source along with the object code. If the place to
+ copy the object code is a network server, the Corresponding Source
+ may be on a different server (operated by you or a third party)
+ that supports equivalent copying facilities, provided you maintain
+ clear directions next to the object code saying where to find the
+ Corresponding Source. Regardless of what server hosts the
+ Corresponding Source, you remain obligated to ensure that it is
+ available for as long as needed to satisfy these requirements.
+
+ e) Convey the object code using peer-to-peer transmission, provided
+ you inform other peers where the object code and Corresponding
+ Source of the work are being offered to the general public at no
+ charge under subsection 6d.
+
+ A separable portion of the object code, whose source code is excluded
+from the Corresponding Source as a System Library, need not be
+included in conveying the object code work.
+
+ A "User Product" is either (1) a "consumer product", which means any
+tangible personal property which is normally used for personal, family,
+or household purposes, or (2) anything designed or sold for incorporation
+into a dwelling. In determining whether a product is a consumer product,
+doubtful cases shall be resolved in favor of coverage. For a particular
+product received by a particular user, "normally used" refers to a
+typical or common use of that class of product, regardless of the status
+of the particular user or of the way in which the particular user
+actually uses, or expects or is expected to use, the product. A product
+is a consumer product regardless of whether the product has substantial
+commercial, industrial or non-consumer uses, unless such uses represent
+the only significant mode of use of the product.
+
+ "Installation Information" for a User Product means any methods,
+procedures, authorization keys, or other information required to install
+and execute modified versions of a covered work in that User Product from
+a modified version of its Corresponding Source. The information must
+suffice to ensure that the continued functioning of the modified object
+code is in no case prevented or interfered with solely because
+modification has been made.
+
+ If you convey an object code work under this section in, or with, or
+specifically for use in, a User Product, and the conveying occurs as
+part of a transaction in which the right of possession and use of the
+User Product is transferred to the recipient in perpetuity or for a
+fixed term (regardless of how the transaction is characterized), the
+Corresponding Source conveyed under this section must be accompanied
+by the Installation Information. But this requirement does not apply
+if neither you nor any third party retains the ability to install
+modified object code on the User Product (for example, the work has
+been installed in ROM).
+
+ The requirement to provide Installation Information does not include a
+requirement to continue to provide support service, warranty, or updates
+for a work that has been modified or installed by the recipient, or for
+the User Product in which it has been modified or installed. Access to a
+network may be denied when the modification itself materially and
+adversely affects the operation of the network or violates the rules and
+protocols for communication across the network.
+
+ Corresponding Source conveyed, and Installation Information provided,
+in accord with this section must be in a format that is publicly
+documented (and with an implementation available to the public in
+source code form), and must require no special password or key for
+unpacking, reading or copying.
+
+ 7. Additional Terms.
+
+ "Additional permissions" are terms that supplement the terms of this
+License by making exceptions from one or more of its conditions.
+Additional permissions that are applicable to the entire Program shall
+be treated as though they were included in this License, to the extent
+that they are valid under applicable law. If additional permissions
+apply only to part of the Program, that part may be used separately
+under those permissions, but the entire Program remains governed by
+this License without regard to the additional permissions.
+
+ When you convey a copy of a covered work, you may at your option
+remove any additional permissions from that copy, or from any part of
+it. (Additional permissions may be written to require their own
+removal in certain cases when you modify the work.) You may place
+additional permissions on material, added by you to a covered work,
+for which you have or can give appropriate copyright permission.
+
+ Notwithstanding any other provision of this License, for material you
+add to a covered work, you may (if authorized by the copyright holders of
+that material) supplement the terms of this License with terms:
+
+ a) Disclaiming warranty or limiting liability differently from the
+ terms of sections 15 and 16 of this License; or
+
+ b) Requiring preservation of specified reasonable legal notices or
+ author attributions in that material or in the Appropriate Legal
+ Notices displayed by works containing it; or
+
+ c) Prohibiting misrepresentation of the origin of that material, or
+ requiring that modified versions of such material be marked in
+ reasonable ways as different from the original version; or
+
+ d) Limiting the use for publicity purposes of names of licensors or
+ authors of the material; or
+
+ e) Declining to grant rights under trademark law for use of some
+ trade names, trademarks, or service marks; or
+
+ f) Requiring indemnification of licensors and authors of that
+ material by anyone who conveys the material (or modified versions of
+ it) with contractual assumptions of liability to the recipient, for
+ any liability that these contractual assumptions directly impose on
+ those licensors and authors.
+
+ All other non-permissive additional terms are considered "further
+restrictions" within the meaning of section 10. If the Program as you
+received it, or any part of it, contains a notice stating that it is
+governed by this License along with a term that is a further
+restriction, you may remove that term. If a license document contains
+a further restriction but permits relicensing or conveying under this
+License, you may add to a covered work material governed by the terms
+of that license document, provided that the further restriction does
+not survive such relicensing or conveying.
+
+ If you add terms to a covered work in accord with this section, you
+must place, in the relevant source files, a statement of the
+additional terms that apply to those files, or a notice indicating
+where to find the applicable terms.
+
+ Additional terms, permissive or non-permissive, may be stated in the
+form of a separately written license, or stated as exceptions;
+the above requirements apply either way.
+
+ 8. Termination.
+
+ You may not propagate or modify a covered work except as expressly
+provided under this License. Any attempt otherwise to propagate or
+modify it is void, and will automatically terminate your rights under
+this License (including any patent licenses granted under the third
+paragraph of section 11).
+
+ However, if you cease all violation of this License, then your
+license from a particular copyright holder is reinstated (a)
+provisionally, unless and until the copyright holder explicitly and
+finally terminates your license, and (b) permanently, if the copyright
+holder fails to notify you of the violation by some reasonable means
+prior to 60 days after the cessation.
+
+ Moreover, your license from a particular copyright holder is
+reinstated permanently if the copyright holder notifies you of the
+violation by some reasonable means, this is the first time you have
+received notice of violation of this License (for any work) from that
+copyright holder, and you cure the violation prior to 30 days after
+your receipt of the notice.
+
+ Termination of your rights under this section does not terminate the
+licenses of parties who have received copies or rights from you under
+this License. If your rights have been terminated and not permanently
+reinstated, you do not qualify to receive new licenses for the same
+material under section 10.
+
+ 9. Acceptance Not Required for Having Copies.
+
+ You are not required to accept this License in order to receive or
+run a copy of the Program. Ancillary propagation of a covered work
+occurring solely as a consequence of using peer-to-peer transmission
+to receive a copy likewise does not require acceptance. However,
+nothing other than this License grants you permission to propagate or
+modify any covered work. These actions infringe copyright if you do
+not accept this License. Therefore, by modifying or propagating a
+covered work, you indicate your acceptance of this License to do so.
+
+ 10. Automatic Licensing of Downstream Recipients.
+
+ Each time you convey a covered work, the recipient automatically
+receives a license from the original licensors, to run, modify and
+propagate that work, subject to this License. You are not responsible
+for enforcing compliance by third parties with this License.
+
+ An "entity transaction" is a transaction transferring control of an
+organization, or substantially all assets of one, or subdividing an
+organization, or merging organizations. If propagation of a covered
+work results from an entity transaction, each party to that
+transaction who receives a copy of the work also receives whatever
+licenses to the work the party's predecessor in interest had or could
+give under the previous paragraph, plus a right to possession of the
+Corresponding Source of the work from the predecessor in interest, if
+the predecessor has it or can get it with reasonable efforts.
+
+ You may not impose any further restrictions on the exercise of the
+rights granted or affirmed under this License. For example, you may
+not impose a license fee, royalty, or other charge for exercise of
+rights granted under this License, and you may not initiate litigation
+(including a cross-claim or counterclaim in a lawsuit) alleging that
+any patent claim is infringed by making, using, selling, offering for
+sale, or importing the Program or any portion of it.
+
+ 11. Patents.
+
+ A "contributor" is a copyright holder who authorizes use under this
+License of the Program or a work on which the Program is based. The
+work thus licensed is called the contributor's "contributor version".
+
+ A contributor's "essential patent claims" are all patent claims
+owned or controlled by the contributor, whether already acquired or
+hereafter acquired, that would be infringed by some manner, permitted
+by this License, of making, using, or selling its contributor version,
+but do not include claims that would be infringed only as a
+consequence of further modification of the contributor version. For
+purposes of this definition, "control" includes the right to grant
+patent sublicenses in a manner consistent with the requirements of
+this License.
+
+ Each contributor grants you a non-exclusive, worldwide, royalty-free
+patent license under the contributor's essential patent claims, to
+make, use, sell, offer for sale, import and otherwise run, modify and
+propagate the contents of its contributor version.
+
+ In the following three paragraphs, a "patent license" is any express
+agreement or commitment, however denominated, not to enforce a patent
+(such as an express permission to practice a patent or covenant not to
+sue for patent infringement). To "grant" such a patent license to a
+party means to make such an agreement or commitment not to enforce a
+patent against the party.
+
+ If you convey a covered work, knowingly relying on a patent license,
+and the Corresponding Source of the work is not available for anyone
+to copy, free of charge and under the terms of this License, through a
+publicly available network server or other readily accessible means,
+then you must either (1) cause the Corresponding Source to be so
+available, or (2) arrange to deprive yourself of the benefit of the
+patent license for this particular work, or (3) arrange, in a manner
+consistent with the requirements of this License, to extend the patent
+license to downstream recipients. "Knowingly relying" means you have
+actual knowledge that, but for the patent license, your conveying the
+covered work in a country, or your recipient's use of the covered work
+in a country, would infringe one or more identifiable patents in that
+country that you have reason to believe are valid.
+
+ If, pursuant to or in connection with a single transaction or
+arrangement, you convey, or propagate by procuring conveyance of, a
+covered work, and grant a patent license to some of the parties
+receiving the covered work authorizing them to use, propagate, modify
+or convey a specific copy of the covered work, then the patent license
+you grant is automatically extended to all recipients of the covered
+work and works based on it.
+
+ A patent license is "discriminatory" if it does not include within
+the scope of its coverage, prohibits the exercise of, or is
+conditioned on the non-exercise of one or more of the rights that are
+specifically granted under this License. You may not convey a covered
+work if you are a party to an arrangement with a third party that is
+in the business of distributing software, under which you make payment
+to the third party based on the extent of your activity of conveying
+the work, and under which the third party grants, to any of the
+parties who would receive the covered work from you, a discriminatory
+patent license (a) in connection with copies of the covered work
+conveyed by you (or copies made from those copies), or (b) primarily
+for and in connection with specific products or compilations that
+contain the covered work, unless you entered into that arrangement,
+or that patent license was granted, prior to 28 March 2007.
+
+ Nothing in this License shall be construed as excluding or limiting
+any implied license or other defenses to infringement that may
+otherwise be available to you under applicable patent law.
+
+ 12. No Surrender of Others' Freedom.
+
+ If conditions are imposed on you (whether by court order, agreement or
+otherwise) that contradict the conditions of this License, they do not
+excuse you from the conditions of this License. If you cannot convey a
+covered work so as to satisfy simultaneously your obligations under this
+License and any other pertinent obligations, then as a consequence you may
+not convey it at all. For example, if you agree to terms that obligate you
+to collect a royalty for further conveying from those to whom you convey
+the Program, the only way you could satisfy both those terms and this
+License would be to refrain entirely from conveying the Program.
+
+ 13. Use with the GNU Affero General Public License.
+
+ Notwithstanding any other provision of this License, you have
+permission to link or combine any covered work with a work licensed
+under version 3 of the GNU Affero General Public License into a single
+combined work, and to convey the resulting work. The terms of this
+License will continue to apply to the part which is the covered work,
+but the special requirements of the GNU Affero General Public License,
+section 13, concerning interaction through a network will apply to the
+combination as such.
+
+ 14. Revised Versions of this License.
+
+ The Free Software Foundation may publish revised and/or new versions of
+the GNU General Public License from time to time. Such new versions will
+be similar in spirit to the present version, but may differ in detail to
+address new problems or concerns.
+
+ Each version is given a distinguishing version number. If the
+Program specifies that a certain numbered version of the GNU General
+Public License "or any later version" applies to it, you have the
+option of following the terms and conditions either of that numbered
+version or of any later version published by the Free Software
+Foundation. If the Program does not specify a version number of the
+GNU General Public License, you may choose any version ever published
+by the Free Software Foundation.
+
+ If the Program specifies that a proxy can decide which future
+versions of the GNU General Public License can be used, that proxy's
+public statement of acceptance of a version permanently authorizes you
+to choose that version for the Program.
+
+ Later license versions may give you additional or different
+permissions. However, no additional obligations are imposed on any
+author or copyright holder as a result of your choosing to follow a
+later version.
+
+ 15. Disclaimer of Warranty.
+
+ THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY
+APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT
+HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY
+OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO,
+THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
+PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM
+IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF
+ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
+
+ 16. Limitation of Liability.
+
+ IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
+WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS
+THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY
+GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE
+USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF
+DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD
+PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS),
+EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF
+SUCH DAMAGES.
+
+ 17. Interpretation of Sections 15 and 16.
+
+ If the disclaimer of warranty and limitation of liability provided
+above cannot be given local legal effect according to their terms,
+reviewing courts shall apply local law that most closely approximates
+an absolute waiver of all civil liability in connection with the
+Program, unless a warranty or assumption of liability accompanies a
+copy of the Program in return for a fee.
+
+ END OF TERMS AND CONDITIONS
+
+ How to Apply These Terms to Your New Programs
+
+ If you develop a new program, and you want it to be of the greatest
+possible use to the public, the best way to achieve this is to make it
+free software which everyone can redistribute and change under these terms.
+
+ To do so, attach the following notices to the program. It is safest
+to attach them to the start of each source file to most effectively
+state the exclusion of warranty; and each file should have at least
+the "copyright" line and a pointer to where the full notice is found.
+
+
+ Copyright (C)
+
+ This program is free software: you can redistribute it and/or modify
+ it under the terms of the GNU General Public License as published by
+ the Free Software Foundation, either version 3 of the License, or
+ (at your option) any later version.
+
+ This program is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ GNU General Public License for more details.
+
+ You should have received a copy of the GNU General Public License
+ along with this program. If not, see .
+
+Also add information on how to contact you by electronic and paper mail.
+
+ If the program does terminal interaction, make it output a short
+notice like this when it starts in an interactive mode:
+
+ Copyright (C)
+ This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
+ This is free software, and you are welcome to redistribute it
+ under certain conditions; type `show c' for details.
+
+The hypothetical commands `show w' and `show c' should show the appropriate
+parts of the General Public License. Of course, your program's commands
+might be different; for a GUI interface, you would use an "about box".
+
+ You should also get your employer (if you work as a programmer) or school,
+if any, to sign a "copyright disclaimer" for the program, if necessary.
+For more information on this, and how to apply and follow the GNU GPL, see
+.
+
+ The GNU General Public License does not permit incorporating your program
+into proprietary programs. If your program is a subroutine library, you
+may consider it more useful to permit linking proprietary applications with
+the library. If this is what you want to do, use the GNU Lesser General
+Public License instead of this License. But first, please read
+.
diff --git a/Setup.hs b/Setup.hs
new file mode 100644
--- /dev/null
+++ b/Setup.hs
@@ -0,0 +1,193 @@
+import Distribution.PackageDescription(PackageDescription)
+import Distribution.Simple
+import Distribution.Simple.LocalBuildInfo(LocalBuildInfo)
+
+import Text.ParserCombinators.Parsec
+
+import TxtSushi.SQLParser
+
+main = defaultMainWithHooks $ simpleUserHooks {runTests = runTxtSushiTests}
+
+--------------------------------------------------------------------------------
+-- Test code
+--------------------------------------------------------------------------------
+
+runTxtSushiTests :: Args -> Bool -> PackageDescription -> LocalBuildInfo -> IO ()
+runTxtSushiTests _ _ _ _ = do
+ let
+ -- test statement 1
+ stmt1 = SelectStatement {
+ columnSelections = [
+ ExpressionColumn {expression = ColumnExpression {column = ColumnIdentifier {maybeTableName = Just "table1", columnId = "col1"}}},
+ AllColumnsFrom {sourceTableName = "table2"}],
+ maybeFromTable = Just (
+ InnerJoin {
+ leftJoinTable = TableIdentifier {tableName = "table1", maybeTableAlias = Nothing},
+ rightJoinTable = TableIdentifier {tableName = "table2", maybeTableAlias = Nothing},
+ onCondition = FunctionExpression {
+ sqlFunction = SQLFunction {functionName = "=", minArgCount = 2, argCountIsFixed = True},
+ functionArguments = [
+ ColumnExpression {column = ColumnIdentifier {maybeTableName = Just "table1", columnId = "col1"}},
+ ColumnExpression {column = ColumnIdentifier {maybeTableName = Just "table2", columnId = "col1"}}]},
+ maybeTableAlias = Nothing}),
+ maybeWhereFilter = Nothing,
+ orderByItems = []}
+ stmt1_1Txt =
+ "select table1.col1, table2.* " ++
+ "from table1 inner join table2 on table1.col1 = table2.col1"
+ stmt1_2Txt =
+ "select table1.col1, table2.* " ++
+ "from table1 join table2 on table1.col1 = table2.col1"
+
+ -- test statement 2
+ stmt2 = SelectStatement {
+ columnSelections = [
+ ExpressionColumn {expression = ColumnExpression {column = ColumnIdentifier {maybeTableName = Just "table1", columnId = "col1"}}},
+ AllColumnsFrom {sourceTableName = "table2"}],
+ maybeFromTable = Just (
+ InnerJoin {
+ leftJoinTable = TableIdentifier {tableName = "table1", maybeTableAlias = Nothing},
+ rightJoinTable = TableIdentifier {tableName = "table2", maybeTableAlias = Nothing},
+ onCondition = FunctionExpression {
+ sqlFunction = SQLFunction {functionName = "=", minArgCount = 2, argCountIsFixed = True},
+ functionArguments = [
+ ColumnExpression {column = ColumnIdentifier {maybeTableName = Just "table1", columnId = "col1"}},
+ ColumnExpression {column = ColumnIdentifier {maybeTableName = Just "table2", columnId = "col1"}}]},
+ maybeTableAlias = Nothing}),
+ maybeWhereFilter = Just (
+ FunctionExpression {
+ sqlFunction = SQLFunction {functionName = "<>", minArgCount = 2, argCountIsFixed = True},
+ functionArguments = [
+ FunctionExpression {
+ sqlFunction = SQLFunction {functionName = "UPPER", minArgCount = 1, argCountIsFixed = True},
+ functionArguments = [ColumnExpression {column = ColumnIdentifier {maybeTableName = Just "table1", columnId = "col1"}}]},
+ FunctionExpression {
+ sqlFunction = SQLFunction {functionName = "LOWER", minArgCount = 1, argCountIsFixed = True},
+ functionArguments = [ColumnExpression {column = ColumnIdentifier {maybeTableName = Just "table1", columnId = "col1"}}]}]}),
+ orderByItems = []}
+ stmt2_1Txt =
+ "select table1.col1, table2.* " ++
+ "from table1 join table2 on table1.col1 = table2.col1 " ++
+ "where upper(table1.col1)<>lower(table1.col1)"
+ stmt2_2Txt =
+ "select table1.col1, table2.* " ++
+ "from table1 join table2 on table1.col1 = table2.col1 " ++
+ "where upper(table1.col1) <> lower(table1.col1)"
+
+ -- test statement 3
+ stmt3 = SelectStatement {
+ columnSelections = [
+ ExpressionColumn {expression = ColumnExpression {column = ColumnIdentifier {maybeTableName = Just "table1", columnId = "col1"}}},
+ AllColumnsFrom {sourceTableName = "table2"}],
+ maybeFromTable = Just (
+ InnerJoin {
+ leftJoinTable = TableIdentifier {tableName = "table1", maybeTableAlias = Nothing},
+ rightJoinTable = TableIdentifier {tableName = "table2", maybeTableAlias = Nothing},
+ onCondition = FunctionExpression {
+ sqlFunction = SQLFunction {functionName = "=", minArgCount = 2, argCountIsFixed = True},
+ functionArguments = [
+ ColumnExpression {column = ColumnIdentifier {maybeTableName = Just "table1", columnId = "col1"}},
+ ColumnExpression {column = ColumnIdentifier {maybeTableName = Just "table2", columnId = "col1"}}]},
+ maybeTableAlias = Nothing}),
+ maybeWhereFilter = Just (
+ FunctionExpression {
+ sqlFunction = SQLFunction {functionName = "<>", minArgCount = 2, argCountIsFixed = True},
+ functionArguments = [
+ FunctionExpression {
+ sqlFunction = SQLFunction {functionName = "UPPER", minArgCount = 1, argCountIsFixed = True},
+ functionArguments = [ColumnExpression {column = ColumnIdentifier {maybeTableName = Just "table1", columnId = "col1"}}]},
+ FunctionExpression {
+ sqlFunction = SQLFunction {functionName = "LOWER", minArgCount = 1, argCountIsFixed = True},
+ functionArguments = [ColumnExpression {column = ColumnIdentifier {maybeTableName = Just "table1", columnId = "col1"}}]}]}),
+ orderByItems = [OrderByItem {
+ orderExpression = ColumnExpression {column = ColumnIdentifier {maybeTableName = Just "table1", columnId = "firstName"}},
+ orderAscending = True}]}
+ stmt3_1Txt =
+ "select table1.col1, table2.* " ++
+ "from table1 join table2 on table1.col1 = table2.col1 " ++
+ "where upper(table1.col1)<>lower(table1.col1) order by table1.firstName asc"
+ stmt3_2Txt =
+ "select table1.col1, table2.* " ++
+ "from table1 join table2 on table1.col1 = table2.col1 " ++
+ "where upper(table1.col1)<>lower(table1.col1) order by table1.firstName"
+ stmt3_3Txt =
+ "select table1.col1, table2.* " ++
+ "from table1 join table2 on table1.col1 = table2.col1 " ++
+ "where upper (table1.col1) <> lower ( table1.col1 ) order by table1.firstName ascending"
+
+ -- test statement 4
+ stmt4 = SelectStatement {
+ columnSelections = [
+ ExpressionColumn {expression = ColumnExpression {column = ColumnIdentifier {maybeTableName = Just "table1", columnId = "col1"}}},
+ AllColumnsFrom {sourceTableName = "table2"}],
+ maybeFromTable = Just (
+ InnerJoin {
+ leftJoinTable = TableIdentifier {tableName = "table1", maybeTableAlias = Nothing},
+ rightJoinTable = TableIdentifier {tableName = "table2", maybeTableAlias = Nothing},
+ onCondition = FunctionExpression {
+ sqlFunction = SQLFunction {functionName = "=", minArgCount = 2, argCountIsFixed = True},
+ functionArguments = [
+ ColumnExpression {column = ColumnIdentifier {maybeTableName = Just "table1", columnId = "col1"}},
+ ColumnExpression {column = ColumnIdentifier {maybeTableName = Just "table2", columnId = "col1"}}]},
+ maybeTableAlias = Nothing}),
+ maybeWhereFilter = Just (
+ FunctionExpression {
+ sqlFunction = SQLFunction {functionName = "<>", minArgCount = 2, argCountIsFixed = True},
+ functionArguments = [
+ FunctionExpression {
+ sqlFunction = SQLFunction {functionName = "UPPER", minArgCount = 1, argCountIsFixed = True},
+ functionArguments = [ColumnExpression {column = ColumnIdentifier {maybeTableName = Just "table1", columnId = "col1"}}]},
+ FunctionExpression {
+ sqlFunction = SQLFunction {functionName = "LOWER", minArgCount = 1, argCountIsFixed = True},
+ functionArguments = [ColumnExpression {column = ColumnIdentifier {maybeTableName = Just "table1", columnId = "col1"}}]}]}),
+ orderByItems = [OrderByItem {
+ orderExpression = ColumnExpression {column = ColumnIdentifier {maybeTableName = Just "table1", columnId = "firstName"}},
+ orderAscending = False}]}
+ stmt4_1Txt =
+ "select table1.col1, table2.* " ++
+ "from table1 join table2 on table1.col1 = table2.col1 " ++
+ "where upper (table1.col1) <> lower ( table1.col1 ) order by table1.firstName descending"
+ stmt4_2Txt =
+ "select table1.col1, table2.* " ++
+ "from table1 join table2 on table1.col1 = table2.col1 " ++
+ "where upper (table1.col1) <> lower ( table1.col1 ) order by table1.firstName DESCENDING"
+ stmt4_3Txt =
+ "select table1.col1, table2.* " ++
+ "from table1 join table2 on table1.col1 = table2.col1 " ++
+ "where upper (table1.col1) <> lower ( table1.col1 ) order by table1.firstName desc"
+ stmt4_4Txt =
+ "select table1.col1, table2.* " ++
+ "from table1 join table2 on table1.col1 = table2.col1 " ++
+ "where upper (table1.col1) <> lower ( table1.col1 ) order by table1.firstName DESC"
+
+ testSqlSelect stmt1 stmt1_1Txt
+ testSqlSelect stmt1 stmt1_2Txt
+
+ testSqlSelect stmt2 stmt2_1Txt
+ testSqlSelect stmt2 stmt2_2Txt
+
+ testSqlSelect stmt3 stmt3_1Txt
+ testSqlSelect stmt3 stmt3_2Txt
+ testSqlSelect stmt3 stmt3_3Txt
+
+ testSqlSelect stmt4 stmt4_1Txt
+ testSqlSelect stmt4 stmt4_2Txt
+ testSqlSelect stmt4 stmt4_3Txt
+ testSqlSelect stmt4 stmt4_4Txt
+
+testSqlSelect :: SelectStatement -> String -> IO ()
+testSqlSelect expectedResult selectStatementText = do
+ let stmtParseResult = parse parseSelectStatement "" selectStatementText
+ colNums = take (length selectStatementText) ([1 .. 9] ++ cycle [0 .. 9])
+ putStrLn ""
+ putStrLn "Testing:"
+ putStrLn $ concat (map show colNums)
+ putStrLn selectStatementText
+ case stmtParseResult of
+ Left errMsg -> error $ show errMsg
+ Right selectStatement ->
+ if selectStatement == expectedResult
+ then
+ putStrLn "Success"
+ else
+ error $ "\n" ++ (show selectStatement) ++ "\nNOT EQUAL TO\n" ++ (show expectedResult)
diff --git a/TxtSushi/IO.hs b/TxtSushi/IO.hs
new file mode 100644
--- /dev/null
+++ b/TxtSushi/IO.hs
@@ -0,0 +1,213 @@
+{- |
+The 'FlatFile' module is for reading misc. 'FlatFile' formats like CSV or
+tab delimited
+-}
+module TxtSushi.IO (
+ formatTableWithWidths,
+ maxTableColumnWidths,
+ formatTable,
+ parseTable,
+ Format(Format),
+ csvFormat,
+ tabDelimitedFormat,
+ doubleQuote) where
+
+import Data.List
+import Util.ListUtil
+
+{- |
+'Format' allows you to specify different flat-file formats so that you
+can use 'parseTable' for CSV, tab-delimited etc.
+-}
+data Format = Format {
+ quote :: String,
+ fieldDelimiter :: String,
+ rowDelimiter :: String} deriving (Show)
+
+csvFormat = Format "\"" "," "\n"
+tabDelimitedFormat = Format "\"" "\t" "\n"
+
+{- |
+get a quote escape sequence for the given 'Format'
+-}
+doubleQuote :: Format -> String
+doubleQuote format = (quote format) ++ (quote format)
+
+formatTableWithWidths _ _ [] = []
+formatTableWithWidths boundaryString widths (row:tableTail) =
+ let
+ (initCells, [lastCell]) = splitAt (length row - 1) row
+ in
+ (concat $ zipWith ensureWidth widths initCells) ++ lastCell ++
+ "\n" ++ (formatTableWithWidths boundaryString widths tableTail)
+ where
+ ensureWidth width field =
+ let lengthField = length field
+ in
+ if width > lengthField then
+ field ++ (replicate (width - lengthField) ' ') ++ boundaryString
+ else
+ field ++ boundaryString
+
+{- |
+for a table, calculate the max width in characters for each column
+-}
+maxTableColumnWidths :: [[String]] -> [Int]
+maxTableColumnWidths [] = []
+maxTableColumnWidths table =
+ maxTableColumnWidthsInternal table []
+
+maxTableColumnWidthsInternal :: [[String]] -> [Int] -> [Int]
+maxTableColumnWidthsInternal [] prevMaxValues = prevMaxValues
+maxTableColumnWidthsInternal (row:tableTail) prevMaxValues
+ | seqList prevMaxValues = undefined
+ | otherwise = maxTableColumnWidthsInternal tableTail (maxRowFieldWidths row prevMaxValues)
+
+-- this filthy little function is for making the list strict... otherwise
+-- we run out of memory
+seqList [] = False
+seqList (head:tail)
+ | head `seq` False = undefined
+ | otherwise = seqList tail
+
+maxRowFieldWidths :: [String] -> [Int] -> [Int]
+maxRowFieldWidths row prevMaxValues =
+ zipWithD max (map length row) prevMaxValues
+{-
+ let colLengths = map length row
+ lengthOfRow = length row
+ lengthOfPrevMax = length prevMaxValues
+ maxPrefixList = zipWith max colLengths prevMaxValues
+ in
+ if lengthOfRow == lengthOfPrevMax then
+ maxPrefixList
+ else if lengthOfRow > lengthOfPrevMax then
+ maxPrefixList ++ (drop lengthOfPrevMax colLengths)
+ else
+ maxPrefixList ++ (drop lengthOfRow prevMaxValues)
+-}
+
+zipWithD :: (a -> a -> a) -> [a] -> [a] -> [a]
+zipWithD f (x:xt) (y:yt) = (f x y):(zipWithD f xt yt)
+zipWithD _ [] ys = ys
+zipWithD _ xs [] = xs
+
+{- |
+Format the given table (the 2D String array) into a flat-file string using
+the given 'Format'
+-}
+formatTable :: Format -> [[String]] -> String
+formatTable _ [] = ""
+formatTable format (headRow:tableTail) =
+ (formatRow format headRow) ++ (rowDelimiter format) ++ (formatTable format tableTail)
+
+{- |
+Format the row into a flat file sub-string using the given 'Format'
+-}
+formatRow :: Format -> [String] -> String
+formatRow _ [] = []
+formatRow format (headField:rowTail) =
+ -- we need to escape any quotes
+ let escapedField = encodeField format headField
+ in
+ -- use a field delimiter on all but the last field
+ if null rowTail then
+ escapedField
+ else
+ escapedField ++ (fieldDelimiter format) ++ (formatRow format rowTail)
+
+{- |
+encode the given text field if it contains any special formatting characters
+-}
+encodeField format field =
+ if (quote format) `isInfixOf` field then
+ let escapedField = replaceAll field (quote format) (doubleQuote format)
+ in (quote format) ++ escapedField ++ (quote format)
+ else if (rowDelimiter format) `isInfixOf` field ||
+ (fieldDelimiter format) `isInfixOf` field then
+ (quote format) ++ field ++ (quote format)
+ else
+ field
+
+{- |
+Parse the given text using the given flat file 'Format'. The result
+is a list of list of strings. The strings are fields and the string
+lists are rows
+-}
+parseTable :: Format -> String -> [[String]]
+parseTable _ [] = []
+parseTable format text =
+ let (nextLine, remainingText) = parseLine format text
+ in nextLine:(parseTable format remainingText)
+
+-- parse a row giving (rowFields, remainingText)
+parseLine :: Format -> String -> ([String], String)
+parseLine _ [] = ([], "")
+parseLine format text =
+ let (nextField, moreFieldsInRow, textRemainingAfterField) = parseField format text
+ in
+ -- if there are more fields, recursively add them to the row
+ if moreFieldsInRow then
+ let (rowTail, remainingText) = parseLine format textRemainingAfterField
+ in (nextField:rowTail, remainingText)
+
+ -- if there are no more fields return the current fields as a singleton
+ -- list
+ else
+ ([nextField], textRemainingAfterField)
+
+-- parse a field giving (field, moreFieldsInRow, remainingText)
+parseField :: Format -> String -> (String, Bool, String)
+parseField _ [] = ("", False, "")
+parseField format text =
+ -- check if this field is quoted or not
+ if (quote format) `isPrefixOf` text then
+ let tailOfQuote = drop (length (quote format)) text
+ in parseQuotedField format tailOfQuote
+ else
+ parseUnquotedField format text
+
+-- parse a quoted field giving (field, moreFieldsInRow, remainingText)
+parseQuotedField :: Format -> String -> (String, Bool, String)
+parseQuotedField _ [] = ("", False, "")
+parseQuotedField format text@(textHead:textTail) =
+ -- a double quote is an escaped quote, so add a quote to the field
+ if (doubleQuote format) `isPrefixOf` text then
+ let tailOfDoubleQuote = drop (length (doubleQuote format)) text
+ (fieldTail, moreFieldsInRow, remainingText) = parseQuotedField format tailOfDoubleQuote
+ in ((quote format) ++ fieldTail, moreFieldsInRow, remainingText)
+
+ -- a single quote is the end of the field, we can use parseUnquotedField to
+ -- chew up any chars between the ending quote and the next delimiter (there
+ -- really shouldn't be any if the text is formatted well, but you never
+ -- know)
+ else if (quote format) `isPrefixOf` text then
+ let tailOfQuote = drop (length (quote format)) text
+ (_, moreFieldsInRow, remainingText) = parseUnquotedField format tailOfQuote
+ in ("", moreFieldsInRow, remainingText)
+
+ -- just another character... toss it in the field and keep going
+ else
+ let (fieldTail, moreFieldsInRow, remainingText) = parseQuotedField format textTail
+ in (textHead:fieldTail, moreFieldsInRow, remainingText)
+
+-- parse an unquoted field giving (field, moreFieldsInRow, remainingText)
+parseUnquotedField :: Format -> String -> (String, Bool, String)
+parseUnquotedField _ [] = ("", False, "")
+parseUnquotedField format text@(textHead:textTail) =
+ -- if we hit a field delimiter: return an empty string and let caller know
+ -- there are more fields in this row
+ if (fieldDelimiter format) `isPrefixOf` text then
+ let tailOfDelimiter = drop (length (fieldDelimiter format)) text
+ in ([], True, tailOfDelimiter)
+
+ -- if we hit a row delimiter: return an empty string and let caller know there
+ -- are no more fields in this row
+ else if (rowDelimiter format) `isPrefixOf` text then
+ let tailOfDelimiter = drop (length (rowDelimiter format)) text
+ in ([], False, tailOfDelimiter)
+
+ -- just another character... toss it in the field and keep going
+ else
+ let (fieldTail, moreFieldsInRow, remainingText) = parseUnquotedField format textTail
+ in (textHead:fieldTail, moreFieldsInRow, remainingText)
diff --git a/TxtSushi/SQLExecution.hs b/TxtSushi/SQLExecution.hs
new file mode 100644
--- /dev/null
+++ b/TxtSushi/SQLExecution.hs
@@ -0,0 +1,404 @@
+-----------------------------------------------------------------------------
+-- |
+-- Module : TxtSushi.SQLExecution
+-- Copyright : (c) Keith Sheppard 2009
+-- License : GPL3 or greater
+-- Maintainer : keithshep@gmail.com
+-- Stability : experimental
+-- Portability : portable
+--
+-- Module for executing a SQL statement
+--
+-----------------------------------------------------------------------------
+
+module TxtSushi.SQLExecution (
+ select,
+ databaseTableToTextTable,
+ textTableToDatabaseTable) where
+
+import Data.Char
+import Data.List
+import qualified Data.Map as Map
+
+import TxtSushi.SQLParser
+import TxtSushi.Transform
+import Util.ListUtil
+
+-- | an SQL table data structure
+-- TODO: need allColumnsColumnIdentifiers and allColumnsTableRows so that
+-- we can filter and order on columns that are selected out. we also
+-- should track any column ordering that is in place
+data DatabaseTable = DatabaseTable {
+ -- | the columns in this table
+ columnIdentifiers :: [ColumnIdentifier],
+
+ -- | the actual table data
+ tableRows :: [[EvaluatedExpression]]}
+
+emptyTable = DatabaseTable [] []
+
+stringExpression :: String -> EvaluatedExpression
+stringExpression string = EvaluatedExpression {
+ preferredType = StringType,
+ maybeIntValue = maybeReadInt string,
+ maybeRealValue = maybeReadReal string,
+ stringValue = string,
+ maybeBoolValue = Just $
+ (map toLower string /= "false") && (string /= "") && (string /= "0")}
+
+intExpression int = EvaluatedExpression {
+ preferredType = IntType,
+ maybeIntValue = Just int,
+ maybeRealValue = Just $ fromIntegral int,
+ stringValue = show int,
+ maybeBoolValue = Just $ int /= 0}
+
+realExpression real = EvaluatedExpression {
+ preferredType = RealType,
+ maybeIntValue = Just $ floor real,
+ maybeRealValue = Just real,
+ stringValue = show real,
+ maybeBoolValue = Just $ real /= 0.0}
+
+boolExpression bool = EvaluatedExpression {
+ preferredType = BoolType,
+ maybeIntValue = Just $ if bool then 1 else 0,
+ maybeRealValue = Just $ if bool then 1.0 else 0.0,
+ stringValue = show bool,
+ maybeBoolValue = Just bool}
+
+intValue :: EvaluatedExpression -> Int
+intValue evalExpr = case maybeIntValue evalExpr of
+ Just int -> int
+ Nothing ->
+ error $ "failed to parse \"" ++ (stringValue evalExpr) ++
+ "\" as an integer value"
+
+realValue :: EvaluatedExpression -> Double
+realValue evalExpr = case maybeRealValue evalExpr of
+ Just real -> real
+ Nothing ->
+ error $ "failed to parse \"" ++ (stringValue evalExpr) ++
+ "\" to a numeric value"
+
+boolValue :: EvaluatedExpression -> Bool
+boolValue evalExpr = case maybeBoolValue evalExpr of
+ Just bool -> bool
+ Nothing ->
+ error $ "failed to parse \"" ++ (stringValue evalExpr) ++
+ "\" to a boolean value"
+
+data ExpressionType = StringType | RealType | IntType | BoolType deriving Eq
+
+data EvaluatedExpression = EvaluatedExpression {
+ preferredType :: ExpressionType,
+ stringValue :: String,
+ maybeRealValue :: Maybe Double,
+ maybeIntValue :: Maybe Int,
+ maybeBoolValue :: Maybe Bool}
+
+maybeReadBool :: String -> Maybe Bool
+maybeReadBool boolStr = case map toLower boolStr of
+ "true" -> Just True
+ "1" -> Just True
+ "1.0" -> Just True
+ "false" -> Just False
+ "0" -> Just False
+ "0.0" -> Just False
+ otherwise -> Nothing
+
+instance Eq EvaluatedExpression where
+ -- base off of the Ord definition
+ expr1 == expr2 = compare expr1 expr2 == EQ
+
+instance Ord EvaluatedExpression where
+ -- compare on bool based on preferred type
+ compare (EvaluatedExpression BoolType _ _ _ (Just b1)) (EvaluatedExpression _ _ _ _ (Just b2)) = compare b1 b2
+ compare (EvaluatedExpression _ _ _ _ (Just b1)) (EvaluatedExpression BoolType _ _ _ (Just b2)) = compare b1 b2
+
+ -- compare on int based on preferred type
+ compare (EvaluatedExpression IntType _ _ (Just i1) _) (EvaluatedExpression _ _ _ (Just i2) _) = compare i1 i2
+ compare (EvaluatedExpression _ _ _ (Just i1) _) (EvaluatedExpression IntType _ _ (Just i2) _) = compare i1 i2
+
+ -- compare on real based on preferred type
+ compare (EvaluatedExpression RealType _ (Just r1) _ _) (EvaluatedExpression _ _ (Just r2) _ _) = compare r1 r2
+ compare (EvaluatedExpression _ _ (Just r1) _ _) (EvaluatedExpression RealType _ (Just r2) _ _) = compare r1 r2
+
+ -- fall back on string type
+ compare expr1 expr2 = compare (stringValue expr1) (stringValue expr2)
+
+-- convert a text table to a database table by using the 1st row as column IDs
+textTableToDatabaseTable :: String -> [[String]] -> DatabaseTable
+textTableToDatabaseTable tableName (headerNames:tblRows) =
+ DatabaseTable (map makeColId headerNames) (map (map stringExpression) tblRows)
+ where
+ makeColId colName = ColumnIdentifier (Just tableName) colName
+
+databaseTableToTextTable :: DatabaseTable -> [[String]]
+databaseTableToTextTable dbTable =
+ let
+ headerRow = (map columnId (columnIdentifiers dbTable))
+ tailRows = map (map stringValue) (tableRows dbTable)
+ in
+ headerRow:tailRows
+
+-- | perform a SQL select with the given select statement on the
+-- given table map
+select :: SelectStatement -> (Map.Map String DatabaseTable) -> DatabaseTable
+select selectStatement tableMap =
+ let
+ -- TODO: do we need to care about the updated aliases for filtering
+ -- in the "where" part??
+ fromTbl = case maybeFromTable selectStatement of
+ Nothing -> emptyTable
+ Just fromTblExpr -> evalTableExpression fromTblExpr tableMap
+ filteredTbl = case maybeWhereFilter selectStatement of
+ Nothing -> fromTbl
+ Just expr -> filterRowsBy expr fromTbl
+ orderedTbl = orderRowsBy (orderByItems selectStatement) filteredTbl
+ selectedTbl =
+ evaluateColumnSelections (columnSelections selectStatement) orderedTbl
+ in
+ selectedTbl
+
+-- | sorts table rows by the given order by items
+orderRowsBy :: [OrderByItem] -> DatabaseTable -> DatabaseTable
+orderRowsBy [] dbTable = dbTable
+orderRowsBy orderBys dbTable =
+ let
+ -- curry in the order and col ID params to make a row comparison function
+ compareFunc = compareRowsOnOrderItems orderBys (columnIdentifiers dbTable)
+ in
+ dbTable {tableRows = sortBy compareFunc (tableRows dbTable)}
+
+-- | Compares two rows using the given OrderByItem and column ID's
+compareRowsOnOrderItems :: [OrderByItem] -> [ColumnIdentifier] -> [EvaluatedExpression] -> [EvaluatedExpression] -> Ordering
+compareRowsOnOrderItems orderBys colIds row1 row2 =
+ cascadingOrder $ toOrderList orderBys
+ where
+ toOrderList [] = []
+ toOrderList (orderBy:orderByTail) =
+ (compareRowsOnOrderItem orderBy colIds row1 row2):(toOrderList orderByTail)
+
+-- | Compares two rows using the given OrderByItem and column ID's
+compareRowsOnOrderItem :: OrderByItem -> [ColumnIdentifier] -> [EvaluatedExpression] -> [EvaluatedExpression] -> Ordering
+compareRowsOnOrderItem orderBy colIds row1 row2 =
+ let
+ orderExpr = orderExpression orderBy
+ row1Eval = evalExpression orderExpr colIds row1
+ row2Eval = evalExpression orderExpr colIds row2
+ rowComp = row1Eval `compare` row2Eval
+ in
+ if orderAscending orderBy then
+ rowComp
+ else
+ reverseOrdering rowComp
+
+-- | reverses the given ordering. pretty CRAZY huh???
+reverseOrdering :: Ordering -> Ordering
+reverseOrdering EQ = EQ
+reverseOrdering LT = GT
+reverseOrdering GT = LT
+
+-- | Evaluate the FROM table part, and returns the FROM table. Also returns
+-- a mapping of new table names from aliases etc.
+evalTableExpression :: TableExpression -> (Map.Map String DatabaseTable) -> DatabaseTable
+evalTableExpression tblExpr tableMap =
+ case tblExpr of
+ TableIdentifier tblName maybeTblAlias ->
+ let
+ -- find the from table map (error if missing)
+ noTblError = error $ "failed to find table named " ++ tblName
+ table = Map.findWithDefault noTblError tblName tableMap
+ in
+ maybeRename maybeTblAlias table
+
+ -- TODO inner join should allow joining on expressions too!!
+ InnerJoin leftJoinTblExpr rightJoinTblExpr onConditionExpr maybeTblAlias ->
+ let
+ leftJoinTbl = evalTableExpression leftJoinTblExpr tableMap
+ rightJoinTbl = evalTableExpression rightJoinTblExpr tableMap
+ joinCols = extractJoinCols onConditionExpr
+ joinIndices = joinColumnIndices leftJoinTbl rightJoinTbl joinCols
+ joinedTbl = innerJoin joinIndices leftJoinTbl rightJoinTbl
+ in
+ maybeRename maybeTblAlias joinedTbl
+
+ -- TODO implement me
+ CrossJoin leftJoinTbl maybeTblAlias rightJoinTbl ->
+ error "Sorry! CROSS JOIN is not yet implemented"
+ where
+ maybeRename :: (Maybe String) -> DatabaseTable -> DatabaseTable
+ maybeRename Nothing table = table
+ maybeRename (Just newName) table = table {
+ columnIdentifiers = map (\colId -> colId {maybeTableName = Just newName}) (columnIdentifiers table)}
+
+extractJoinCols (FunctionExpression sqlFunc [arg1, arg2]) =
+ case sqlFunc of
+ SQLFunction "AND" _ _ -> extractJoinCols arg1 ++ extractJoinCols arg2
+ SQLFunction "=" _ _ -> extractJoinColPair arg1 arg2
+
+ -- Only expecting "AND" or "="
+ otherwise -> onPartFormattingError
+ where
+ extractJoinColPair (ColumnExpression col1) (ColumnExpression col2) = [(col1, col2)]
+
+ -- Only expecting "AND" or "="
+ extractJoinColPair _ _ = onPartFormattingError
+
+-- Only expecting "AND" or "="
+extractJoinCols _ = onPartFormattingError
+
+onPartFormattingError =
+ error $ "The \"ON\" part of a join must only contain column equalities " ++
+ "joined together by \"AND\" like: " ++
+ "\"tbl1.id1 = table2.id1 AND tbl1.firstname = tbl2.name\""
+
+-- | perform an inner join using the given join indices on the given
+-- tables
+innerJoin :: [(Int, Int)] -> DatabaseTable -> DatabaseTable -> DatabaseTable
+innerJoin joinIndices leftJoinTbl rightJoinTbl = DatabaseTable {
+ columnIdentifiers = (columnIdentifiers leftJoinTbl) ++ (columnIdentifiers rightJoinTbl),
+ tableRows = joinTables joinIndices (tableRows leftJoinTbl) (tableRows rightJoinTbl)}
+
+-- | convert the column ID pairs into index pairs
+joinColumnIndices :: DatabaseTable -> DatabaseTable -> [(ColumnIdentifier, ColumnIdentifier)] -> [(Int, Int)]
+joinColumnIndices leftJoinTbl rightJoinTbl joinCols =
+ let
+ leftHeader = columnIdentifiers leftJoinTbl
+ rightHeader = columnIdentifiers rightJoinTbl
+ in
+ map (idPairToIndexPair leftHeader rightHeader) joinCols
+
+-- | convert the column ID pair into an index pair
+idPairToIndexPair :: [ColumnIdentifier] -> [ColumnIdentifier] -> (ColumnIdentifier, ColumnIdentifier) -> (Int, Int)
+idPairToIndexPair leftColIds rightColIds joinColPair@(leftColId, rightColId) =
+ let
+ maybePairInOrder = maybeIdPairToIndexPair leftColIds rightColIds joinColPair
+ maybePairSwapped = maybeIdPairToIndexPair leftColIds rightColIds (rightColId, leftColId)
+ in
+ case maybePairInOrder of
+ Just thePairInOrder -> thePairInOrder
+ Nothing ->
+ case maybePairSwapped of
+ Just thePairSwapped -> thePairSwapped
+ Nothing -> error "failed to find given columns"
+
+maybeIdPairToIndexPair :: [ColumnIdentifier] -> [ColumnIdentifier] -> (ColumnIdentifier, ColumnIdentifier) -> Maybe (Int, Int)
+maybeIdPairToIndexPair leftColIds rightColIds (leftColId, rightColId) = do
+ leftIndex <- findIndex (== leftColId) leftColIds
+ rightIndex <- findIndex (== rightColId) rightColIds
+ return (leftIndex, rightIndex)
+
+evaluateColumnSelections :: [ColumnSelection] -> DatabaseTable -> DatabaseTable
+evaluateColumnSelections colSelections dbTable =
+ let
+ selectionTbls = map ($ dbTable) (map evaluateColumnSelection colSelections)
+ in
+ foldl1' tableConcat selectionTbls
+
+tableConcat :: DatabaseTable -> DatabaseTable -> DatabaseTable
+tableConcat dbTable1 dbTable2 =
+ let
+ concatIds = (columnIdentifiers dbTable1) ++ (columnIdentifiers dbTable2)
+ concatRows = zipWith (++) (tableRows dbTable1) (tableRows dbTable2)
+ in
+ DatabaseTable concatIds concatRows
+
+evaluateColumnSelection :: ColumnSelection -> DatabaseTable -> DatabaseTable
+evaluateColumnSelection AllColumns dbTable = dbTable
+evaluateColumnSelection (AllColumnsFrom srcTblName) dbTable =
+ let
+ colIds = columnIdentifiers dbTable
+ indices = findIndices matchesSrcTblName (map maybeTableName colIds)
+ selectedColIds = selectIndices indices colIds
+ selectedColRows = map (selectIndices indices) (tableRows dbTable)
+ in
+ DatabaseTable selectedColIds selectedColRows
+ where
+ matchesSrcTblName Nothing = False
+ matchesSrcTblName (Just tblName) = tblName == srcTblName
+ selectIndices indices xs = [xs !! i | i <- indices]
+evaluateColumnSelection (ExpressionColumn expr) dbTable =
+ let
+ tblColIds = columnIdentifiers dbTable
+ exprColId = expressionIdentifier expr
+ evaluatedExprs = map (evalExpression expr tblColIds) (tableRows dbTable)
+ in
+ DatabaseTable [exprColId] (transpose [evaluatedExprs])
+
+-- | This is a little different that a strict equals compare in that it returns
+-- true if the query column has a Nothing table and the column name part
+-- matches the reference column's name. Also not that this makes it
+-- an asymetric comparison
+columnMatches :: ColumnIdentifier -> ColumnIdentifier -> Bool
+columnMatches (ColumnIdentifier Nothing queryColIdStr) referenceColumn =
+ -- In this case we don't care about the table name so
+ -- just check to make sure that the column names match up
+ queryColIdStr == columnId referenceColumn
+
+columnMatches queryColumn referenceColumn =
+ -- table name is important here so match on the whole object
+ queryColumn == referenceColumn
+
+-- | filters the database's table rows on the given expression
+filterRowsBy :: Expression -> DatabaseTable -> DatabaseTable
+filterRowsBy filterExpr table =
+ table {tableRows = filter myBoolEvalExpr (tableRows table)}
+ where myBoolEvalExpr row =
+ boolValue $ evalExpression filterExpr (columnIdentifiers table) row
+
+evalExpression :: Expression -> [ColumnIdentifier] -> [EvaluatedExpression] -> EvaluatedExpression
+-- Here's the easy stuff. evaluate constants
+evalExpression (StringConstantExpression string) _ _ = stringExpression string
+evalExpression (IntegerConstantExpression int) _ _ = intExpression int
+evalExpression (RealConstantExpression real) _ _ = realExpression real
+
+-- A little bit harder. evaluate a column expression
+evalExpression (ColumnExpression col) columnIds tblRow =
+ case findIndex (columnMatches col) columnIds of
+ Just colIndex -> tblRow !! colIndex
+ Nothing -> error $ "Failed to find column named: " ++ (prettyFormatColumn col)
+
+-- this is where the action is. evaluate a function
+evalExpression (FunctionExpression sqlFun funArgs) columnIds tblRow
+ -- String functions
+ | sqlFun == upperFunction = stringExpression $ map toUpper (stringValue (head evaluatedArgs))
+ | sqlFun == lowerFunction = stringExpression $ map toLower (stringValue (head evaluatedArgs))
+ | sqlFun == trimFunction = stringExpression $ trimSpace (stringValue (head evaluatedArgs))
+
+ -- algebraic infix functions
+ | sqlFun == multiplyFunction = algebraWithCoercion (*) (*) evaluatedArgs
+ | sqlFun == divideFunction = realExpression $ foldl1' (/) (map realValue evaluatedArgs)
+ | sqlFun == plusFunction = algebraWithCoercion (+) (+) evaluatedArgs
+ | sqlFun == minusFunction = algebraWithCoercion (-) (-) evaluatedArgs
+
+ -- boolean infix functions
+ | sqlFun == isFunction = boolExpression (arg1 == arg2)
+ | sqlFun == isNotFunction = boolExpression (arg1 /= arg2)
+ | sqlFun == lessThanFunction = boolExpression (arg1 < arg2)
+ | sqlFun == lessThanOrEqualToFunction = boolExpression (arg1 <= arg2)
+ | sqlFun == greaterThanFunction = boolExpression (arg1 > arg2)
+ | sqlFun == greaterThanOrEqualToFunction = boolExpression (arg1 >= arg2)
+ | sqlFun == andFunction = boolExpression $ (boolValue arg1) && (boolValue arg2)
+ | sqlFun == orFunction = boolExpression $ (boolValue arg1) || (boolValue arg2)
+
+ where
+ arg1 = head evaluatedArgs
+ arg2 = evaluatedArgs !! 1
+ evaluatedArgs = map evalArgExpr funArgs
+ evalArgExpr expr = evalExpression expr columnIds tblRow
+ algebraWithCoercion intFunc realFunc args =
+ if any useRealAlgebra args then
+ realExpression $ foldl1' realFunc (map realValue args)
+ else
+ intExpression $ foldl1' intFunc (map intValue args)
+
+ useRealAlgebra expr =
+ let prefType = preferredType expr
+ in prefType == StringType || prefType == RealType
+
+-- | trims leading and trailing spaces
+trimSpace :: String -> String
+trimSpace = f . f
+ where f = reverse . dropWhile isSpace
diff --git a/TxtSushi/SQLParser.hs b/TxtSushi/SQLParser.hs
new file mode 100644
--- /dev/null
+++ b/TxtSushi/SQLParser.hs
@@ -0,0 +1,704 @@
+-----------------------------------------------------------------------------
+-- |
+-- Module : TxtSushi.SQLParser
+-- Copyright : (c) Keith Sheppard 2009
+-- License : GPL3 or greater
+-- Maintainer : keithshep@gmail.com
+-- Stability : experimental
+-- Portability : portable
+--
+-- Module for parsing SQL
+--
+-----------------------------------------------------------------------------
+
+module TxtSushi.SQLParser (
+ allMaybeTableNames,
+ parseSelectStatement,
+ SelectStatement(..),
+ TableExpression(..),
+ ColumnIdentifier(..),
+ prettyFormatColumn,
+ ColumnSelection(..),
+ expressionIdentifier,
+ Expression(..),
+ OrderByItem(..),
+ prettyFormatWithArgs,
+ SQLFunction(..),
+
+ -- SQL functions with "normal" syntax
+ upperFunction,
+ lowerFunction,
+ trimFunction,
+
+ -- Algebraic infix SQL functions
+ multiplyFunction,
+ divideFunction,
+ plusFunction,
+ minusFunction,
+
+ -- Boolean infix SQL functions
+ isFunction,
+ isNotFunction,
+ lessThanFunction,
+ lessThanOrEqualToFunction,
+ greaterThanFunction,
+ greaterThanOrEqualToFunction,
+ andFunction,
+ orFunction,
+
+ -- Etc...
+ maybeReadInt,
+ maybeReadReal) where
+
+import Data.Char
+import Data.List
+import Text.ParserCombinators.Parsec
+import Text.ParserCombinators.Parsec.Expr
+import Util.ListUtil
+
+--------------------------------------------------------------------------------
+-- The data definition for select statements
+--------------------------------------------------------------------------------
+
+-- | represents a select statement
+-- TODO this should be moved inside the TableExpression type
+data SelectStatement = SelectStatement {
+ columnSelections :: [ColumnSelection],
+ maybeFromTable :: Maybe TableExpression,
+ maybeWhereFilter :: Maybe Expression,
+ orderByItems :: [OrderByItem]}
+ deriving (Show, Ord, Eq)
+
+data TableExpression =
+ TableIdentifier {
+ tableName :: String,
+ maybeTableAlias :: Maybe String} |
+ InnerJoin {
+ leftJoinTable :: TableExpression,
+ rightJoinTable :: TableExpression,
+ onCondition :: Expression,
+ maybeTableAlias :: Maybe String} |
+ CrossJoin {
+ leftJoinTable :: TableExpression,
+ rightJoinTable :: TableExpression,
+ maybeTableAlias :: Maybe String}
+ deriving (Show, Ord, Eq)
+
+-- | convenience function for extracting all of the table names used by the
+-- given table expression
+allMaybeTableNames :: (Maybe TableExpression) -> [String]
+allMaybeTableNames Nothing = []
+allMaybeTableNames (Just tblExp) = allTableNames tblExp
+
+allTableNames (TableIdentifier tblName _) = [tblName]
+allTableNames (InnerJoin lftTbl rtTbl _ _) =
+ (allTableNames lftTbl) ++ (allTableNames rtTbl)
+allTableNames (CrossJoin lftTbl rtTbl _) =
+ (allTableNames lftTbl) ++ (allTableNames rtTbl)
+
+data ColumnSelection =
+ AllColumns |
+ AllColumnsFrom {sourceTableName :: String} |
+ ExpressionColumn {expression :: Expression}
+ --QualifiedColumn {
+ -- qualifiedColumnId :: ColumnIdentifier}
+ deriving (Show, Ord, Eq)
+
+data ColumnIdentifier =
+ ColumnIdentifier {
+ maybeTableName :: Maybe String,
+ columnId :: String}
+ deriving (Show, Ord, Eq)
+
+-- | I wanted to leave the default Show, but I also wanted a pretty print, so
+-- here it is!
+prettyFormatColumn :: ColumnIdentifier -> String
+prettyFormatColumn (ColumnIdentifier (Just tblName) colId) = tblName ++ "." ++ colId
+prettyFormatColumn (ColumnIdentifier (Nothing) colId) = colId
+
+data Expression =
+ FunctionExpression {
+ sqlFunction :: SQLFunction,
+ functionArguments :: [Expression]} |
+ ColumnExpression {
+ column :: ColumnIdentifier} |
+ StringConstantExpression {
+ stringConstant :: String} |
+ IntegerConstantExpression {
+ intConstant :: Int} |
+ RealConstantExpression {
+ realConstant :: Double}
+ deriving (Show, Ord, Eq)
+
+expressionIdentifier :: Expression -> ColumnIdentifier
+expressionIdentifier (FunctionExpression func args) =
+ ColumnIdentifier Nothing ((prettyFormatWithArgs func) args)
+expressionIdentifier (ColumnExpression col) = col
+expressionIdentifier (StringConstantExpression str) =
+ ColumnIdentifier Nothing ("\"" ++ str ++ "\"")
+expressionIdentifier (IntegerConstantExpression int) =
+ ColumnIdentifier Nothing (show int)
+expressionIdentifier (RealConstantExpression real) =
+ ColumnIdentifier Nothing (show real)
+
+needsParens :: Expression -> Bool
+needsParens (FunctionExpression _ _) = True
+needsParens _ = False
+
+toArgString :: Expression -> String
+toArgString expr =
+ let exprFmt = prettyFormatColumn $ expressionIdentifier expr
+ in if needsParens expr then "(" ++ exprFmt ++ ")" else exprFmt
+
+prettyFormatWithArgs :: SQLFunction -> [Expression] -> String
+prettyFormatWithArgs sqlFunc funcArgs
+ | sqlFunc `elem` normalSyntaxFunctions = prettyFormatNormalFunctionExpression sqlFunc funcArgs
+ | or (map (sqlFunc `elem`) infixFunctions) = prettyFormatInfixFunctionExpression sqlFunc funcArgs
+
+prettyFormatInfixFunctionExpression :: SQLFunction -> [Expression] -> String
+prettyFormatInfixFunctionExpression sqlFunc funcArgs =
+ let
+ arg1 = head funcArgs
+ arg2 = funcArgs !! 1
+ in
+ toArgString arg1 ++ functionName sqlFunc ++ toArgString arg2
+
+prettyFormatNormalFunctionExpression :: SQLFunction -> [Expression] -> String
+prettyFormatNormalFunctionExpression sqlFunc funcArgs =
+ let argString = intercalate ", " (map toArgString funcArgs)
+ in functionName sqlFunc ++ "(" ++ argString ++ ")"
+
+data SQLFunction = SQLFunction {
+ functionName :: String,
+ minArgCount :: Int,
+ argCountIsFixed :: Bool}
+ deriving (Show, Ord, Eq)
+
+data OrderByItem = OrderByItem {
+ orderExpression :: Expression,
+ orderAscending :: Bool}
+ deriving (Show, Ord, Eq)
+
+-- | Parses a SQL select statement
+parseSelectStatement :: GenParser Char st SelectStatement
+parseSelectStatement = do
+ try $ upperOrLower "SELECT" >> spaces1
+ parseSelectBody
+
+-- | Parses all of the stuff that comes after "SELECT "
+parseSelectBody :: GenParser Char st SelectStatement
+parseSelectBody = do
+ columnVals <- parseColumnSelections
+ -- TODO need a better error message for missing "ON" etc. in
+ -- the from part, can do this by grabing "FROM" first
+ maybeFrom <- maybeParseFromPart
+ maybeWhere <- maybeParseWherePart
+ orderBy <- parseOrderByPart
+
+ spaces
+ eof
+
+ return SelectStatement {
+ columnSelections = columnVals,
+ maybeFromTable = maybeFrom,
+ maybeWhereFilter = maybeWhere,
+ orderByItems = orderBy}
+
+ where
+ maybeParseFromPart =
+ ifParseThen (spaces1 >> upperOrLower "FROM" >> spaces1) parseTableExpression
+
+ maybeParseWherePart =
+ ifParseThen (spaces1 >> upperOrLower "WHERE" >> spaces1) parseExpression
+
+-- | Parses the "ORDER BY ..." part of a select statement returning the list
+-- of OrderByItem's that were parsed (this list will be empty if there is no
+-- "ORDER BY" parsed
+parseOrderByPart :: GenParser Char st [OrderByItem]
+parseOrderByPart =
+ ifParseThenElse
+ -- if we see an "ORDER BY"
+ (spaces1 >> upperOrLower "ORDER" >> spaces1 >> upperOrLower "BY" >> spaces1)
+
+ -- then parse the order expression
+ (sepByAtLeast 1 parseOrderByItem parseCommaSeparator)
+
+ -- else there is nothing to sort by
+ (return [])
+
+ where
+ parseOrderByItem :: GenParser Char st OrderByItem
+ parseOrderByItem = do
+ orderExpr <- parseExpression
+ isAscending <- ifParseThenElse
+ -- if we parse "DESC"
+ (try parseDescending)
+
+ -- then return false, it isn't ascending
+ (return False)
+
+ -- else try to consume "ASC" but even if we don't it's still
+ -- ascending so return true
+ ((try parseAscending <|> return []) >> return True)
+
+ return $ OrderByItem orderExpr isAscending
+
+ parseAscending = spaces1 >> ((try $ upperOrLower "ASCENDING") <|> upperOrLower "ASC")
+ parseDescending = spaces1 >> ((try $ upperOrLower "DESCENDING") <|> upperOrLower "DESC")
+
+--------------------------------------------------------------------------------
+-- Functions for parsing the column names specified after "SELECT"
+--------------------------------------------------------------------------------
+
+parseColumnSelections =
+ sepBy1 parseAnyColType (try parseCommaSeparator)
+ where parseAnyColType = parseAllCols <|>
+ (try parseAllColsFromTbl) <|>
+ (try parseColExpression)
+
+parseAllCols = string "*" >> return AllColumns
+
+parseAllColsFromTbl = do
+ tableVal <- parseIdentifier
+ string ".*"
+
+ return $ AllColumnsFrom tableVal
+
+parseColExpression = parseExpression >>= \expr -> return $ ExpressionColumn expr
+
+parseColumnId = do
+ firstId <- parseIdentifier
+
+ maybeFullyQual <- maybeParse $ char '.'
+ case maybeFullyQual of
+ -- No '.' means it's a partially qualified column
+ Nothing -> return $ ColumnIdentifier Nothing firstId
+ Just _ -> do
+ secondId <- parseIdentifier
+ return $ ColumnIdentifier (Just firstId) secondId
+
+--------------------------------------------------------------------------------
+-- Functions for parsing the table part (after "FROM")
+--------------------------------------------------------------------------------
+
+parseTableExpression = do
+ nextTblChunk <- parseNextTblExpChunk
+
+ let ifInnerJoinParse = ifParseThenElse
+ -- if
+ parseInnerJoinKeywords
+ -- then
+ (parseInnerJoinRemainder nextTblChunk)
+ -- else
+ (return nextTblChunk)
+
+ ifCrossOrInnerJoinParse = ifParseThenElse
+ -- if
+ parseCrossJoinKeywords
+ -- then
+ (parseCrossJoinRemainder nextTblChunk)
+ -- else
+ ifInnerJoinParse
+
+ ifCrossOrInnerJoinParse
+
+parseNextTblExpChunk =
+ parenthesize parseTableExpression <|> parseTableIdentifier
+
+parseCrossJoinKeywords = do
+ spaces1
+ upperOrLower "CROSS"
+ spaces1
+ upperOrLower "JOIN"
+ spaces1
+
+parseInnerJoinKeywords = do
+ spaces1
+ maybeParse $ upperOrLower "INNER" >> spaces1
+ upperOrLower "JOIN"
+ spaces1
+
+parseInnerJoinRemainder leftTblExpr = do
+ rightTblExpr <- parseTableExpression
+
+ spaces1
+ upperOrLower "ON"
+ spaces1
+ onPart <- parseExpression
+
+ maybeAlias <- maybeParse $ spaces1 >> parseTableAlias
+
+ return InnerJoin {
+ leftJoinTable=leftTblExpr,
+ rightJoinTable=rightTblExpr,
+ onCondition=onPart,
+ maybeTableAlias=maybeAlias}
+
+parseCrossJoinRemainder leftTblExpr = do
+ rightTblExpr <- parseTableExpression
+ maybeAlias <- maybeParse $ spaces1 >> parseTableAlias
+
+ return CrossJoin {
+ leftJoinTable=leftTblExpr,
+ rightJoinTable=rightTblExpr,
+ maybeTableAlias=maybeAlias}
+
+parseTableIdentifier = do
+ theId <- parseIdentifier
+ maybeAlias <- maybeParse $ spaces1 >> parseTableAlias
+ return $ TableIdentifier theId maybeAlias
+
+parseTableAlias = upperOrLower "AS" >> spaces1 >> parseIdentifier
+
+--------------------------------------------------------------------------------
+-- Expression parsing: These can be after "SELECT", "WHERE" or "HAVING"
+--------------------------------------------------------------------------------
+
+parseExpression :: GenParser Char st Expression
+parseExpression =
+ let opTable = map (map parseInfixOp) infixFunctions
+ in buildExpressionParser opTable parseAnyNonInfixExpression
+
+parseAnyNonInfixExpression :: GenParser Char st Expression
+parseAnyNonInfixExpression =
+ parenthesize parseExpression <|>
+ parseStringConstant <|>
+ try parseRealConstant <|>
+ parseIntConstant <|>
+ parseAnyNormalFunction <|>
+ (parseColumnId >>= (\colId -> return $ ColumnExpression colId))
+
+parseStringConstant :: GenParser Char st Expression
+parseStringConstant =
+ quotedText True '"' >>= (\txt -> return $ StringConstantExpression txt)
+
+parseIntConstant :: GenParser Char st Expression
+parseIntConstant =
+ parseInt >>= (\int -> return $ IntegerConstantExpression int)
+
+parseInt :: GenParser Char st Int
+parseInt = do
+ digitTxt <- anyParseTxt
+ return $ read digitTxt
+ where
+ anyParseTxt = signedParseTxt <|> unsignedParseTxt "integer"
+ unsignedParseTxt = many1 digit
+ signedParseTxt = do
+ char '-'
+ unsignedDigitTxt <- unsignedParseTxt
+ return ('-':unsignedDigitTxt)
+
+-- | returns an int if it can be read from the string
+maybeReadInt :: String -> Maybe Int
+maybeReadInt intStr =
+ case parse (parseToEof parseInt) "" intStr of
+ Left _ -> Nothing
+ Right int -> Just int
+
+-- | returns a real if it can be read from the string
+maybeReadReal :: String -> Maybe Double
+maybeReadReal realStr =
+ case parse (parseToEof parseReal) "" realStr of
+ Left _ -> maybeReadInt realStr >>= (\int -> Just $ fromIntegral int)
+ Right real -> Just real
+
+parseToEof p = p >>= \x -> (eof >> return x)
+
+parseRealConstant :: GenParser Char st Expression
+parseRealConstant =
+ parseReal >>= (\real -> return $ RealConstantExpression real)
+
+parseReal :: GenParser Char st Double
+parseReal = do
+ realTxt <- anyParseTxt
+ return $ read realTxt
+ where
+ anyParseTxt = signedParseTxt <|> unsignedParseTxt "real"
+ unsignedParseTxt = do
+ intTxt <- many1 digit
+ char '.'
+ fracTxt <- many1 digit
+ return $ intTxt ++ "." ++ fracTxt
+ signedParseTxt = do
+ char '-'
+ unsignedDigitTxt <- unsignedParseTxt
+ return ('-':unsignedDigitTxt)
+
+parseAnyNormalFunction :: GenParser Char st Expression
+parseAnyNormalFunction =
+ let allParsers = map parseNormalFunction normalSyntaxFunctions
+ in choice allParsers
+
+parseNormalFunction sqlFunc = do
+ try $ (upperOrLower $ functionName sqlFunc)
+ spaces -- TODO careful here: what happens with upperVar? it breaks because of "upper" (maybe a blog entry!!)
+ args <- parenthesize $ argSepBy (minArgCount sqlFunc) parseExpression parseCommaSeparator
+ return $ FunctionExpression sqlFunc args
+ where argSepBy = if argCountIsFixed sqlFunc then sepByExactly else sepByAtLeast
+
+-- Functions with "normal" syntax --
+normalSyntaxFunctions = [upperFunction, lowerFunction, trimFunction]
+
+upperFunction = SQLFunction {
+ functionName = "UPPER",
+ minArgCount = 1,
+ argCountIsFixed = True}
+
+lowerFunction = SQLFunction {
+ functionName = "LOWER",
+ minArgCount = 1,
+ argCountIsFixed = True}
+
+trimFunction = SQLFunction {
+ functionName = "TRIM",
+ minArgCount = 1,
+ argCountIsFixed = True}
+
+-- Infix functions --
+infixFunctions =
+ [[multiplyFunction, divideFunction],
+ [plusFunction, minusFunction],
+ [isFunction, isNotFunction, lessThanFunction, lessThanOrEqualToFunction,
+ greaterThanFunction, greaterThanOrEqualToFunction],
+ [andFunction, orFunction]]
+
+-- | This function parses the operator part of the infix function and returns
+-- a function that excepts a left expression and right expression to form
+-- an Expression from the FunctionExpression constructor
+parseInfixOp infixFunc =
+ -- use the magic infix type, always assuming left associativity
+ Infix opParser AssocLeft
+ where
+ opParser =
+ if funcIsAlphaNum
+ then do
+ try (spaces1 >> (upperOrLower $ functionName infixFunc) >> spaces1)
+ return $ buildExpr
+ else do
+ try (spaces >> (upperOrLower $ functionName infixFunc) >> notOpChar) >> spaces
+ return $ buildExpr
+ buildExpr leftSubExpr rightSubExpr =
+ FunctionExpression {
+ sqlFunction = infixFunc,
+ functionArguments = [leftSubExpr, rightSubExpr]}
+ funcIsAlphaNum = any isAlphaNum (functionName infixFunc)
+ notOpChar =
+ notFollowedBy $ oneOf "*/+-=<>^"
+
+-- Algebraic
+multiplyFunction = SQLFunction {
+ functionName = "*",
+ minArgCount = 2,
+ argCountIsFixed = True}
+
+divideFunction = SQLFunction {
+ functionName = "/",
+ minArgCount = 2,
+ argCountIsFixed = True}
+
+plusFunction = SQLFunction {
+ functionName = "+",
+ minArgCount = 2,
+ argCountIsFixed = True}
+
+minusFunction = SQLFunction {
+ functionName = "-",
+ minArgCount = 2,
+ argCountIsFixed = True}
+
+-- Boolean
+isFunction = SQLFunction {
+ functionName = "=",
+ minArgCount = 2,
+ argCountIsFixed = True}
+
+isNotFunction = SQLFunction {
+ functionName = "<>",
+ minArgCount = 2,
+ argCountIsFixed = True}
+
+lessThanFunction = SQLFunction {
+ functionName = "<",
+ minArgCount = 2,
+ argCountIsFixed = True}
+
+lessThanOrEqualToFunction = SQLFunction {
+ functionName = "<=",
+ minArgCount = 2,
+ argCountIsFixed = True}
+
+greaterThanFunction = SQLFunction {
+ functionName = ">",
+ minArgCount = 2,
+ argCountIsFixed = True}
+
+greaterThanOrEqualToFunction = SQLFunction {
+ functionName = ">=",
+ minArgCount = 2,
+ argCountIsFixed = True}
+
+andFunction = SQLFunction {
+ functionName = "AND",
+ minArgCount = 2,
+ argCountIsFixed = True}
+
+orFunction = SQLFunction {
+ functionName = "OR",
+ minArgCount = 2,
+ argCountIsFixed = True}
+
+
+
+-- Functions with special syntax --
+specialFunctions = [substringFromFunction,
+ substringFromToFunction]
+
+-- | SUBSTRING(extraction_string FROM starting_position [FOR length]
+-- [COLLATE collation_name])
+-- TODO implement these
+substringFromFunction = SQLFunction {
+ functionName = "SUBSTRING",
+ minArgCount = 2,
+ argCountIsFixed = True}
+substringFromToFunction = SQLFunction {
+ functionName = "SUBSTRING",
+ minArgCount = 3,
+ argCountIsFixed = True}
+
+--------------------------------------------------------------------------------
+-- Parse utility functions
+--------------------------------------------------------------------------------
+
+-- | parses an identifier. you can use a tick '`' as a quote for
+-- an identifier with white-space
+parseIdentifier = do
+ let parseId = do
+ let idChar = alphaNum <|> char '_'
+ quotedText False '`' <|> many1 idChar
+ (parseId `genExcept` parseReservedWord) "identifier"
+
+quotedText allowEmpty quoteChar = do
+ let quote = char quoteChar
+ manyFunc = if allowEmpty then many else many1
+
+ quote
+ textValue <- manyFunc $ (anyChar `genExcept` quote) <|>
+ try (escapedQuote quoteChar)
+ quote
+
+ return textValue
+
+exceptChar parser theException = notFollowedBy theException >> parser
+
+escapedQuote quoteChar = string [quoteChar, quoteChar] >> return quoteChar
+
+parseCommaSeparator = spaces >> char ',' >> spaces
+
+-- | Wraps parentheses parsers around the given inner parser
+parenthesize :: GenParser Char st a -> GenParser Char st a
+parenthesize innerParser = do
+ char '('
+ spaces
+ innerParseResults <- innerParser
+ spaces
+ char ')'
+ return innerParseResults
+
+-- | Either parses the left or right parser returning the result of the
+-- successful parser
+eitherParse :: GenParser tok st a -> GenParser tok st b -> GenParser tok st (Either a b)
+eitherParse leftParser rightParser =
+ do {parseResult <- try leftParser; return $ Left parseResult} <|>
+ do {parseResult <- rightParser; return $ Right parseResult}
+
+-- parses 1 or more spaces
+spaces1 = skipMany1 space "whitespace"
+
+-- | if the ifParse parser succeeds return the result of thenParse, else
+-- return Nothing without parsing any input
+ifParseThen :: GenParser tok st a -> GenParser tok st b -> GenParser tok st (Maybe b)
+ifParseThen ifParse thenPart = do
+ ifResult <- maybeParse ifParse
+ case ifResult of
+ Just _ -> thenPart >>= (\x -> return $ Just x)
+ Nothing -> return Nothing
+
+-- | if ifParse succeeds then parse thenPart otherwise parse elsePart
+ifParseThenElse :: GenParser tok st a -> GenParser tok st b -> GenParser tok st b -> GenParser tok st b
+ifParseThenElse ifParse thenPart elsePart = do
+ ifResult <- maybeParse ifParse
+ case ifResult of
+ Just _ -> thenPart
+ Nothing -> elsePart
+
+parseReservedWord = do
+ let reservedWordParsers = map reservedWordParser reservedWords
+ choice reservedWordParsers
+ where reservedWordParser word = do
+ parseVal <- upperOrLower word
+ notFollowedBy alphaNum
+ return parseVal
+
+-- TODO are function names reserved... i don't think so
+reservedWords =
+ map functionName normalSyntaxFunctions ++
+ map functionName (concat infixFunctions) ++
+ map functionName specialFunctions ++
+ ["BY","CROSS", "FROM", "GROUP", "HAVING", "INNER", "JOIN", "ON", "ORDER", "SELECT", "WHERE"]
+
+-- | tries parsing both the upper and lower case versions of the given string
+upperOrLower :: String -> GenParser Char st String
+upperOrLower stringToParse =
+ string (map toUpper stringToParse) <|>
+ string (map toLower stringToParse) stringToParse
+
+-- | accepst the same input as the given parser except and input that matches
+-- theException parser
+genExcept :: (Show b) => GenParser tok st a -> GenParser tok st b -> GenParser tok st a
+genExcept parser theException = do
+ genNotFollowedBy theException
+ parser
+
+-- | a generic version of the notFollowedBy library function. We require
+-- Show types so that we can better report failures
+genNotFollowedBy :: (Show a) => GenParser tok st a -> GenParser tok st ()
+genNotFollowedBy theParser = try $ do
+ mayParseResult <- maybeParse theParser
+ case mayParseResult of
+ Nothing -> return ()
+ Just x -> unexpected $ show x
+
+-- | returns Just parseResult if the parse succeeds and Nothing if it fails
+maybeParse :: GenParser tok st a -> GenParser tok st (Maybe a)
+maybeParse parser =
+ (try parser >>= (\x -> return $ Just x)) <|>
+ return Nothing
+
+-- | parse `itemParser`s seperated by exactly `minCount` `sepParser`s
+sepByExactly :: Int -> GenParser tok st a -> GenParser tok st sep -> GenParser tok st [a]
+sepByExactly count itemParser sepParser =
+ let itemParsers = replicate count itemParser
+ in parseEach itemParsers
+ where
+ -- for an empty parser list return an empty result
+ parseEach [] = return []
+
+ -- for a parser list of 1 we don't want to use a separator
+ parseEach [lastParser] = lastParser >>= (\x -> return [x])
+
+ -- for lists greater than 1 we do need to care about the separator
+ parseEach (headParser:parserTail) = do
+ resultHead <- headParser
+ sepParser
+ resultTail <- parseEach parserTail
+
+ return $ resultHead:resultTail
+
+-- | parse `itemParser`s seperated by at least `minCount` `sepParser`s
+sepByAtLeast :: Int -> GenParser tok st a -> GenParser tok st sep -> GenParser tok st [a]
+sepByAtLeast minCount itemParser sepParser = do
+ minResults <- sepByExactly minCount itemParser sepParser
+ ifParseThenElse
+ sepParser
+ (sepBy1 itemParser sepParser >>= (\tailResults -> return $ minResults ++ tailResults))
+ (return minResults)
diff --git a/TxtSushi/Transform.hs b/TxtSushi/Transform.hs
new file mode 100644
--- /dev/null
+++ b/TxtSushi/Transform.hs
@@ -0,0 +1,162 @@
+{- |
+Simple table transformations
+-}
+module TxtSushi.Transform (
+ selectColumns,
+ sortColumns,
+ fileBasedSortTable,
+ mergeAllBy,
+ joinTables,
+ joinPresortedTables,
+ rowComparison) where
+
+import Data.List
+import System.Directory
+import System.IO
+
+import TxtSushi.IO
+
+{- |
+Create a new table by selecting the given 'columnIndices'
+-}
+selectColumns _ [] = []
+selectColumns columnIndices (headRow:tableTail) =
+ ([headRow !! i | i <- columnIndices]):(selectColumns columnIndices tableTail)
+
+removeColumns _ [] = []
+removeColumns columnIndices (headRow:tableTail) =
+ let indexesToSelect = [0 .. ((length headRow) - 1)] \\ columnIndices
+ in ([headRow !! i | i <- indexesToSelect]):(removeColumns columnIndices tableTail)
+
+-- | sort the given 'table' on the given columns
+sortColumns columns table =
+ sortBy (rowComparison columns) table
+
+-- | compare two rows based on given column balues
+rowComparison [] _ _ = EQ
+rowComparison (columnHead:columnsTail) row1 row2 =
+ let colComparison = (row1 !! columnHead) `compare` (row2 !! columnHead)
+ in
+ case colComparison of
+ EQ -> rowComparison columnsTail row1 row2
+ otherwise -> colComparison
+
+-- | merge two sorted lists into a single sorted list
+mergeBy comparisonFunction [] list2 = list2
+mergeBy comparisonFunction list1 [] = list1
+mergeBy comparisonFunction list1@(head1:tail1) list2@(head2:tail2) =
+ case head1 `comparisonFunction` head2 of
+ GT -> (head2:(mergeBy comparisonFunction list1 tail2))
+ otherwise -> (head1:(mergeBy comparisonFunction tail1 list2))
+
+-- | merge the sorted lists in the list to a list about 1/2 the size
+mergePairsBy _ [] = []
+mergePairsBy comparisonFunction singletonListList@(headList:[]) = singletonListList
+mergePairsBy comparisonFunction (list1:list2:listListTail) =
+ let mergedPair = mergeBy comparisonFunction list1 list2
+ in mergedPair:(mergePairsBy comparisonFunction listListTail)
+
+-- | merge a list of sorted lists into a single sorted list
+mergeAllBy _ [] = []
+mergeAllBy comparisonFunction listList =
+ let mergedPairs = mergePairsBy comparisonFunction listList
+ in
+ case mergedPairs of
+ singletonListHead:[] -> singletonListHead
+ otherwise -> mergeAllBy comparisonFunction mergedPairs
+
+{- |
+perform a table sort using files to keep from holding the whole list in memory
+-}
+fileBasedSortTable columns table = do
+ partialSortFiles <- bufferPartialSorts columns table
+ partialSortFileHandles <- (unwrapIOList [openFile file ReadMode | file <- partialSortFiles])
+ partialSortContents <- (unwrapIOList [hGetContents handle | handle <- partialSortFileHandles])
+ let partialSortTables = map (parseTable csvFormat) partialSortContents
+ return (partialSortTables, partialSortFileHandles, partialSortFiles)
+
+-- | unwrap a list of 'IO' boxed items
+unwrapIOList [] = do return []
+unwrapIOList (ioHead:ioTail) = do
+ unwrappedHead <- ioHead
+ unwrappedTail <- unwrapIOList ioTail
+ return (unwrappedHead:unwrappedTail)
+
+-- | create a list of parial sorts
+bufferPartialSorts columns [] = return []
+bufferPartialSorts columns table = do
+ let rowLimit = 100000
+ (rowsToSortNow, rowsToSortLater) = splitAt rowLimit table
+ sortedRows = sortColumns columns rowsToSortNow
+ sortBuffer <- bufferToTempFile sortedRows
+ otherSortBuffers <- bufferPartialSorts columns rowsToSortLater
+ return (sortBuffer:otherSortBuffers)
+
+-- | buffer the table to a temporary file and return a handle to that file
+bufferToTempFile table = do
+ tempDir <- getTemporaryDirectory
+ (tempFilePath, tempFileHandle) <- openTempFile tempDir "buffer.txt"
+ hPutStr tempFileHandle (formatTable csvFormat table)
+ hClose tempFileHandle
+ return tempFilePath
+
+-- | join together two tables on the given column index pairs
+joinTables :: (Ord o) => [(Int, Int)] -> [[o]] -> [[o]] -> [[o]]
+joinTables joinColumnZipList table1 table2 =
+ let
+ (joinColumns1, joinColumns2) = unzip joinColumnZipList
+ sortedTable1 = sortColumns joinColumns1 table1
+ sortedTable2 = sortColumns joinColumns2 table2
+ in
+ joinPresortedTables joinColumnZipList sortedTable1 sortedTable2
+
+-- | join together two tables that are presorted on the given column index pairs
+joinPresortedTables :: (Ord o) => [(Int, Int)] -> [[o]] -> [[o]] -> [[o]]
+joinPresortedTables joinColumnZipList sortedTable1 sortedTable2 =
+ let
+ (joinColumns1, joinColumns2) = unzip joinColumnZipList
+ rowEq1 = (\a b -> (rowComparison joinColumns1 a b) == EQ)
+ rowEq2 = (\a b -> (rowComparison joinColumns2 a b) == EQ)
+ tableGroups1 = groupBy rowEq1 sortedTable1
+ tableGroups2 = groupBy rowEq2 sortedTable2
+ in
+ joinGroupedTables joinColumnZipList tableGroups1 tableGroups2
+
+permutePrependRows [] _ = []
+permutePrependRows _ [] = []
+permutePrependRows (table1HeadRow:table1Tail) table2 =
+ let
+ prependHead = (table1HeadRow ++)
+ newTable2 = map prependHead table2
+ in
+ newTable2 ++ (permutePrependRows table1Tail table2)
+
+joinGroupedTables _ [] _ = []
+joinGroupedTables _ _ [] = []
+joinGroupedTables joinColumnZipList tableGroups1@(headTableGroup1:tableGroupsTail1) tableGroups2@(headTableGroup2:tableGroupsTail2) =
+ let
+ headRow1 = head headTableGroup1
+ headRow2 = head headTableGroup2
+ in
+ case asymmetricRowComparison joinColumnZipList headRow1 headRow2 of
+ -- drop the 1st group if its smaller
+ LT -> joinGroupedTables joinColumnZipList tableGroupsTail1 tableGroups2
+
+ -- drop the 2nd group if its smaller
+ GT -> joinGroupedTables joinColumnZipList tableGroups1 tableGroupsTail2
+
+ -- the two groups are equal so permute
+ otherwise ->
+ (permutePrependRows headTableGroup1 headTableGroup2) ++
+ (joinGroupedTables joinColumnZipList tableGroupsTail1 tableGroupsTail2)
+
+asymmetricRowComparison [] _ _ = EQ
+asymmetricRowComparison (columnsZipHead:columnsZipTail) row1 row2 =
+ let
+ (columnHead1, columnHead2) = columnsZipHead
+ colComparison = (row1 !! columnHead1) `compare` (row2 !! columnHead2)
+ in
+ case colComparison of
+ EQ -> asymmetricRowComparison columnsZipTail row1 row2
+ otherwise -> colComparison
+
diff --git a/Util/CommandLineArgument.hs b/Util/CommandLineArgument.hs
new file mode 100644
--- /dev/null
+++ b/Util/CommandLineArgument.hs
@@ -0,0 +1,213 @@
+module Util.CommandLineArgument (
+ extractCommandLineArguments,
+ formatCommandLine,
+ CommandLineDescription(CommandLineDescription),
+ options,
+ minTailArgumentCount,
+ tailArgumentNames,
+ tailArgumentCountIsFixed,
+ OptionDescription(OptionDescription),
+ isRequired,
+ optionFlag,
+ argumentNames,
+ minArgumentCount,
+ argumentCountIsFixed) where
+
+import Data.List
+import Data.Map (Map)
+import qualified Data.Map as Map
+--import Test.HUnit
+
+data CommandLineDescription = CommandLineDescription {
+ options :: [OptionDescription],
+
+ minTailArgumentCount :: Int,
+
+ tailArgumentNames :: [String],
+
+ tailArgumentCountIsFixed :: Bool} deriving (Show, Eq, Ord)
+
+-- | a data structure for describing command line arguments
+data OptionDescription = OptionDescription {
+
+ -- | determines if this is a required option or not
+ isRequired :: Bool,
+
+ {- |
+ What flag should we use. Eg: "-pretty-output"
+ -}
+ optionFlag :: String,
+
+ {- |
+ The name(s) to use for the argument(s).
+ -}
+ argumentNames :: [String],
+
+ {- |
+ the minimum number of args allowed
+ -}
+ minArgumentCount :: Int,
+
+ {- |
+ if true then 'minArgumentCount' is the upper threshold
+ -}
+ argumentCountIsFixed :: Bool} deriving (Show, Eq, Ord)
+
+space = " ";
+etc = "...";
+
+formatCommandLine commandLine =
+ let formattedOptions = formatOptions (options commandLine)
+ formattedTailArgs = formatTailArguments commandLine
+ in
+ if null formattedOptions || null formattedTailArgs then
+ formattedOptions ++ formattedTailArgs
+ else
+ formattedOptions ++ space ++ formattedTailArgs
+
+formatTailArguments commandLine =
+ let tailArgs = tailArgumentNames commandLine
+ minTailArgs = minTailArgumentCount commandLine
+ formattedTailArgs = intercalate space (take minTailArgs (cycle tailArgs))
+ in
+ if tailArgumentCountIsFixed commandLine then
+ formattedTailArgs
+ else
+ if null formattedTailArgs then etc
+ else formattedTailArgs ++ space ++ etc
+
+formatOptions :: [OptionDescription] -> String
+formatOptions [] = ""
+formatOptions (headOption:optionsTail) =
+ let argSubstring = argumentSubstring headOption
+ spacedArgSubstring = if null argSubstring then "" else space ++ argSubstring
+ requiredOptionString = (optionFlag headOption) ++ spacedArgSubstring
+ formattedOptionsTail = if null optionsTail then "" else space ++ (formatOptions optionsTail)
+ in
+ if isRequired headOption then
+ requiredOptionString ++ formattedOptionsTail
+ else
+ "[" ++ requiredOptionString ++ "]" ++ formattedOptionsTail
+
+argumentSubstring option =
+ let minArgs = minArgumentCount option
+ in
+ if argumentCountIsFixed option then
+ if minArgs == 0 then ""
+ else intercalate space (take minArgs (cycle (argumentNames option)))
+ else
+ -- take care of the bounded case
+ (intercalate space (take minArgs (cycle (argumentNames option)))) ++ space ++ etc
+
+extractCommandLineArguments ::
+ CommandLineDescription ->
+ [String] ->
+ (Map.Map OptionDescription [[String]], [String])
+extractCommandLineArguments cmdLineDesc argValues =
+ let unreservedArgCount = (length argValues) - (minTailArgumentCount cmdLineDesc)
+ (unreservedArgs, reservedArgs) = splitAt unreservedArgCount argValues
+ theOptions = options cmdLineDesc
+ (optionMap, remainingArgs) = extractOptions theOptions unreservedArgs
+ anyOptionsInReservedArgs =
+ let (hopefullyEmptyMap, _) = extractOptions theOptions reservedArgs
+ in not $ Map.null hopefullyEmptyMap
+ in
+ -- TODO this if else is really lame. we should replace all this
+ -- along w/ error handling with status codes
+ if anyOptionsInReservedArgs then
+ (Map.empty, [])
+ else
+ (optionMap, remainingArgs ++ reservedArgs)
+
+extractOptions ::
+ [OptionDescription] ->
+ [String] ->
+ (Map.Map OptionDescription [[String]], [String])
+extractOptions [] argValues = (Map.empty, argValues)
+extractOptions _ [] = (Map.empty, [])
+extractOptions optDescs argValues@(argHead:argTail) =
+ case (find (\optDesc -> optionFlag optDesc == argHead) optDescs) of
+ Nothing ->
+ (Map.empty, argValues)
+ Just optDesc ->
+ let (optArgs, afterOptArgs) = extractOption optDesc optDescs argValues
+ (tailArgsMap, afterTailArgs) = extractOptions optDescs afterOptArgs
+ in (addOptionArgsToMap tailArgsMap optDesc optArgs, afterTailArgs)
+
+extractOption ::
+ OptionDescription ->
+ [OptionDescription] ->
+ [String] ->
+ ([String], [String])
+extractOption optDesc allOptDescs (argHead:argTail) =
+ let optArgExtent = argumentExtent optDesc allOptDescs argTail
+ in splitAt optArgExtent argTail
+
+argumentExtent :: OptionDescription -> [OptionDescription] -> [String] -> Int
+argumentExtent optionDescription allOptDescs afterOptArgs =
+ let allOptFlags = map optionFlag allOptDescs
+ maybeNextArgIndex = findIndex (\arg -> any (== arg) allOptFlags) afterOptArgs
+ minArgCount = minArgumentCount optionDescription
+ isFixed = argumentCountIsFixed optionDescription
+ in
+ case maybeNextArgIndex of
+ Nothing ->
+ let afterOptLength = length afterOptArgs
+ in
+ if afterOptLength < minArgCount then missingParameters
+ else if isFixed then minArgCount
+ else afterOptLength
+ Just nextArgIndex ->
+ if nextArgIndex < minArgCount then missingParameters
+ else if isFixed then minArgCount
+ else nextArgIndex
+ where
+ missingParameters =
+ error $ "missing parameter(s) for " ++ (optionFlag optionDescription)
+
+addOptionArgsToMap ::
+ Map.Map OptionDescription [[String]] ->
+ OptionDescription ->
+ [String] ->
+ Map.Map OptionDescription [[String]]
+addOptionArgsToMap optArgMap opt args =
+ case (Map.lookup opt optArgMap) of
+ Nothing -> Map.insert opt [args] optArgMap
+ Just currArgs -> Map.insert opt (currArgs ++ [args]) optArgMap
+
+-- Test code
+{-
+byNameOption = OptionDescription
+ False -- isRequired
+ "-by-name" -- optionFlag
+ [] -- argumentNames
+ 0 -- minArgumentCount
+ True -- argumentCountIsFixed
+
+helpOption = OptionDescription
+ False -- isRequired
+ "-help" -- optionFlag
+ [] -- argumentNames
+ 0 -- minArgumentCount
+ True -- argumentCountIsFixed
+
+fancyPantsOption = OptionDescription
+ False -- isRequired
+ "-fancy" -- optionFlag
+ ["f1", "f2"] -- argumentNames
+ 2 -- minArgumentCount
+ False -- argumentCountIsFixed
+
+cmdLineOps1 = [byNameOption, helpOption, fancyPantsOption]
+
+cmdLineDesc1 = CommandLineDescription
+ cmdLineOps1 -- options
+ 1 -- minTailArgumentCount
+ "file/-" -- tailArgumentNames
+ True -- tailArgumentCountIsFixed
+cmdLine1 = ["-by-name", "-fancy", "f1arg", "f2arg", "-help", "-"]
+parsedCmd1 = extractOptions (options cmdLineDesc1) cmdLine1
+
+test1 = TestCase $ assertEqual
+ "options test" cmdLineOps1 (options cmdLineDesc1)
+-}
diff --git a/Util/IOUtil.hs b/Util/IOUtil.hs
new file mode 100644
--- /dev/null
+++ b/Util/IOUtil.hs
@@ -0,0 +1,35 @@
+module Util.IOUtil (
+ bufferStdioToTempFile,
+ getContentsFromFileOrStdin,
+ getAll) where
+
+import System.Directory
+import System.IO
+
+bufferStdioToTempFile = do
+ stdioText <- getContents
+ tempDir <- getTemporaryDirectory
+ (tempFilePath, tempFileHandle) <- openTempFile tempDir "stdiobuffer.txt"
+ hPutStr tempFileHandle stdioText
+ hClose tempFileHandle
+ return tempFilePath
+
+getContentsFromFileOrStdin filePath = do
+ if filePath == "-"
+ then do
+ getContents
+ else do
+ handle <- openFile filePath ReadMode
+ hGetContents handle
+
+getAll [] = []
+getAll (x:xt) = do
+ y <- x
+ yt <- getAll xt
+ return (y:yt)
+
+-- | returns an infinite list of gets from a monad
+keepGetting getAction = do
+ headVal <- getAction
+ tailVal <- keepGetting getAction
+ return (headVal:tailVal)
diff --git a/Util/ListUtil.hs b/Util/ListUtil.hs
new file mode 100644
--- /dev/null
+++ b/Util/ListUtil.hs
@@ -0,0 +1,27 @@
+module Util.ListUtil (
+ cascadingOrder,
+ replaceAll) where
+
+import Data.List
+
+{-
+replace all instances of 'targetSublist' found in 'list' with
+'replacementList'
+-}
+replaceAll :: (Eq a) => [a] -> [a] -> [a] -> [a]
+replaceAll [] _ _ = []
+replaceAll list@(listHead:listTail) targetSublist replacementList =
+ if targetSublist `isPrefixOf` list then
+ let remainingList = drop (length targetSublist) list
+ in replacementList ++ (replaceAll remainingList targetSublist replacementList)
+ else
+ listHead:(replaceAll listTail targetSublist replacementList)
+
+-- | applies a cascading order logic where 1st non-equal ordering defines
+-- the ordering for the list. If they're all equal (or the list is empty)
+-- then return EQ
+cascadingOrder :: [Ordering] -> Ordering
+cascadingOrder [] = EQ
+cascadingOrder (LT:_) = LT
+cascadingOrder (GT:_) = GT
+cascadingOrder (EQ:tailOrders) = cascadingOrder tailOrders
diff --git a/csvtopretty.hs b/csvtopretty.hs
new file mode 100644
--- /dev/null
+++ b/csvtopretty.hs
@@ -0,0 +1,38 @@
+import Data.List
+import System.Directory
+import System.Environment
+import System.Exit
+import System.IO
+
+import TxtSushi.IO
+import Util.IOUtil
+
+main = do
+ args <- getArgs
+
+ if (length args) /= 1
+ then do
+ hPutStrLn stderr $
+ "ERROR: program requires a single command line argument " ++
+ "(filename or '-')"
+ exitFailure
+ else do
+ let fileArg = head args
+ useStdio = (fileArg == "-")
+
+ file <- if useStdio then bufferStdioToTempFile else return fileArg
+
+ handle1 <- openFile file ReadMode
+ contents1 <- hGetContents handle1
+ handle2 <- openFile file ReadMode
+ contents2 <- hGetContents handle2
+
+ let table1 = parseTable csvFormat contents1
+ columnWidths = maxTableColumnWidths table1
+ table2 = parseTable csvFormat contents2
+ prettyTableText = formatTableWithWidths "|" columnWidths table2
+
+ putStr prettyTableText
+ hClose handle1
+ hClose handle2
+ if useStdio then removeFile file else return ()
diff --git a/csvtotab.hs b/csvtotab.hs
new file mode 100644
--- /dev/null
+++ b/csvtotab.hs
@@ -0,0 +1,23 @@
+import Data.List
+import System.Environment
+import System.Exit
+import System.IO
+
+import TxtSushi.IO
+import Util.IOUtil
+
+main = do
+ args <- getArgs
+
+ if (length args) /= 1
+ then do
+ hPutStrLn stderr $
+ "ERROR: program requires a single command line argument " ++
+ "(filename or '-')"
+ exitFailure
+ else do
+ contents <- getContentsFromFileOrStdin (last args)
+
+ let table = parseTable csvFormat contents
+ tabDelimitedText = formatTable tabDelimitedFormat table
+ putStr tabDelimitedText
diff --git a/examples/create-view-metricstats.bash b/examples/create-view-metricstats.bash
new file mode 100644
--- /dev/null
+++ b/examples/create-view-metricstats.bash
@@ -0,0 +1,17 @@
+#!/bin/bash
+
+# replicating 1st CREATE VIEW from
+# http://www.itl.nist.gov/div897/ctg/dm/sql_examples.htm
+#
+# CREATE VIEW METRIC_STATS (ID, MONTH, TEMP_C, RAIN_C) AS
+# SELECT ID,
+# MONTH,
+# (TEMP_F - 32) * 5 /9,
+# RAIN_I * 0.3937
+# FROM STATS;
+
+# After redirecting to metric_stats.csv we can simply use that as a table.
+# So, that's as close as TxtSushi gets to creating a view :-)
+../dist/build/tssql/tssql -table STATS stats.csv \
+'SELECT ID, MONTH, (TEMP_F - 32) * 5 /9, RAIN_I * 0.3937 FROM STATS' \
+> metric_stats.csv
diff --git a/examples/example1.csv b/examples/example1.csv
new file mode 100644
--- /dev/null
+++ b/examples/example1.csv
@@ -0,0 +1,242 @@
+"id","some val","other val"
+12,43,"hello 33"
+13,44,"hello 34"
+14,45,"hello 35"
+15,46,"hello 36"
+16,47,"hello 37"
+17,48,"hello 38"
+18,49,"hello 39"
+19,50,"hello 40"
+20,51,"hello 41"
+21,52,"hello 42"
+22,53,"hello 43"
+23,54,"hello 44"
+24,55,"hello 45"
+25,56,"hello 46"
+26,57,"hello 47"
+27,58,"hello 48"
+28,59,"hello 49"
+29,60,"hello 50"
+30,61,"hello 51"
+31,62,"hello 52"
+32,63,"hello 53"
+33,64,"hello 54"
+34,65,"hello 55"
+35,66,"hello 56"
+36,67,"hello 57"
+37,68,"hello 58"
+38,69,"hello 59"
+39,70,"hello 60"
+40,71,"hello 61"
+41,72,"hello 62"
+42,73,"hello 63"
+43,74,"hello 64"
+44,75,"hello 65"
+45,76,"hello 66"
+46,77,"hello 67"
+47,78,"hello 68"
+48,79,"hello 69"
+49,80,"hello 70"
+50,81,"hello 71"
+51,82,"hello 72"
+52,83,"hello 73"
+53,84,"hello 74"
+54,85,"hello 75"
+55,86,"hello 76"
+56,87,"hello 77"
+57,43,"hello 78"
+58,43,"hello 79"
+59,43,"hello 80"
+60,43,"hello 81"
+61,43,"hello 82"
+62,43,"hello 83"
+63,43,"hello 84"
+64,43,"hello 85"
+65,44,"hello 86"
+66,44,"hello 87"
+67,44,"hello 88"
+68,44,"hello 89"
+69,44,"hello 90"
+70,44,"hello 91"
+71,44,"hello 92"
+72,43,"hello 93"
+73,43,"hello 94"
+74,43,"hello 95"
+75,43,"hello 96"
+76,43,"hello 97"
+77,43,"hello 98"
+78,43,"hello 99"
+79,43,"hello 100"
+80,43,"hello 101"
+81,43,"hello 102"
+82,43,"hello 103"
+83,43,"hello 104"
+84,43,"hello 105"
+85,43,"hello 106"
+86,43,"hello 107"
+87,43,"hello 108"
+88,44,"hello 109"
+89,44,"hello 110"
+90,44,"hello 111"
+91,44,"hello 112"
+92,44,"hello 113"
+93,44,"hello 114"
+94,44,"hello 115"
+95,43,"hello 116"
+96,43,"hello 117"
+97,43,"hello 118"
+98,43,"hello 119"
+99,43,"hello 120"
+100,43,"hello 121"
+101,43,"hello 122"
+102,43,"hello 123"
+103,43,"hello 124"
+104,43,"hello 125"
+105,43,"hello 126"
+106,43,"hello 127"
+107,43,"hello 128"
+108,43,"hello 129"
+109,43,"hello 130"
+110,43,"hello 131"
+111,43,"hello 132"
+112,43,"hello 133"
+113,43,"hello 134"
+114,43,"hello 135"
+115,43,"hello 136"
+116,43,"hello 137"
+117,43,"hello 138"
+118,43,"hello 139"
+119,43,"hello 140"
+120,43,"hello 141"
+121,43,"hello 142"
+122,43,"hello 143"
+123,43,"hello 144"
+124,43,"hello 145"
+125,43,"hello 146"
+126,43,"hello 147"
+127,43,"hello 148"
+128,43,"hello 149"
+129,43,"hello 150"
+130,43,"hello 151"
+131,43,"hello 152"
+132,43,"hello 153"
+133,43,"hello 154"
+134,43,"hello 155"
+135,43,"hello 156"
+136,43,"hello 157"
+137,43,"hello 158"
+138,43,"hello 159"
+139,43,"hello 160"
+140,43,"hello 161"
+141,43,"hello 162"
+142,43,"hello 163"
+143,43,"hello 164"
+144,43,"hello 165"
+145,43,"hello 166"
+146,43,"hello 167"
+147,43,"hello 168"
+148,43,"hello 169"
+149,43,"hello 170"
+150,43,"hello 171"
+151,43,"hello 172"
+152,43,"hello 173"
+153,43,"hello 174"
+154,43,"hello 175"
+155,43,"hello 176"
+156,43,"hello 177"
+157,43,"hello 178"
+158,43,"hello 179"
+159,43,"hello 180"
+160,43,"hello 181"
+161,43,"hello 182"
+162,43,"hello 183"
+163,43,"hello 184"
+164,43,"hello 185"
+165,43,"hello 186"
+166,43,"hello 187"
+167,43,"hello 188"
+168,43,"hello 189"
+169,43,"hello 190"
+170,43,"hello 191"
+171,43,"hello 192"
+172,43,"hello 193"
+173,43,"hello 194"
+174,43,"hello 195"
+175,43,"hello 196"
+176,43,"hello 197"
+177,43,"hello 198"
+178,43,"hello 199"
+179,43,"hello 200"
+180,43,"hello 201"
+181,43,"hello 202"
+182,43,"hello 203"
+183,43,"hello 204"
+184,43,"hello 205"
+185,43,"hello 206"
+186,43,"hello 207"
+187,43,"hello 208"
+188,43,"hello 209"
+189,43,"hello 210"
+190,43,"hello 211"
+191,43,"hello 212"
+192,43,"hello 213"
+193,43,"hello 214"
+194,43,"hello 215"
+195,43,"hello 216"
+196,43,"hello 217"
+197,43,"hello 218"
+198,43,"hello 219"
+199,43,"hello 220"
+200,43,"hello 221"
+201,43,"hello 222"
+202,43,"hello 223"
+203,43,"hello 224"
+204,43,"hello 225"
+205,43,"hello 226"
+206,43,"hello 227"
+207,43,"hello 228"
+208,43,"hello 229"
+209,43,"hello 230"
+210,43,"hello 231"
+211,43,"hello 232"
+212,43,"hello 233"
+213,43,"hello 234"
+214,43,"hello 235"
+215,43,"hello 236"
+216,43,"hello 237"
+217,43,"hello 238"
+218,43,"hello 239"
+219,43,"hello 240"
+220,43,"hello 241"
+221,43,"hello 242"
+222,43,"hello 243"
+223,43,"hello 244"
+224,43,"hello 245"
+225,43,"hello 246"
+226,43,"hello 247"
+227,43,"hello 248"
+228,43,"hello 249"
+229,43,"hello 250"
+230,43,"hello 251"
+231,43,"hello 252"
+232,43,"hello 253"
+233,43,"hello 254"
+234,43,"hello 255"
+235,43,"hello 256"
+236,43,"hello 257"
+237,43,"hello 258"
+238,43,"hello 259"
+239,43,"hello 260"
+240,43,"hello 261"
+241,43,"hello 262"
+242,43,"hello 263"
+243,43,"hello 264"
+244,43,"hello 265"
+245,43,"hello 266"
+246,43,"hello 267"
+247,43,"hello '268"""
+248,"this
+-- has
+a couple of newlines","hello 269"
+249,43,"hello 270"
+250,43,"hello 271"
diff --git a/examples/example2.csv b/examples/example2.csv
new file mode 100644
--- /dev/null
+++ b/examples/example2.csv
@@ -0,0 +1,8 @@
+"id2","some val","other val"
+244,"some","hello 265"
+245,"other","hello 266"
+246,"values","hello 267"
+247,"than","hello '268"""
+248,"example","hello 269"
+249,"number","hello 270"
+250,"one","hello 271"
diff --git a/examples/join-stats-station.bash b/examples/join-stats-station.bash
new file mode 100644
--- /dev/null
+++ b/examples/join-stats-station.bash
@@ -0,0 +1,15 @@
+#!/bin/bash
+
+# replicating JOIN from
+# http://www.itl.nist.gov/div897/ctg/dm/sql_examples.htm
+#
+# SELECT LAT_N, CITY, TEMP_F
+# FROM STATS, STATION
+# WHERE MONTH = 7
+# AND STATS.ID = STATION.ID
+# ORDER BY TEMP_F;
+
+../dist/build/tssql/tssql -table STATION station.csv -table STATS stats.csv \
+'SELECT LAT_N, CITY, TEMP_F FROM STATS JOIN STATION ON STATS.ID = STATION.ID
+WHERE MONTH = 7 ORDER BY TEMP_F' \
+| ../dist/build/csvtopretty/csvtopretty -
diff --git a/examples/kitchen-sink.bash b/examples/kitchen-sink.bash
new file mode 100644
--- /dev/null
+++ b/examples/kitchen-sink.bash
@@ -0,0 +1,12 @@
+#!/bin/bash
+
+# Our kitchen sink example to exercise all of the TxtSushi functionality as
+# we can in one SELECT.
+# NOTE: the "+ 0" is needed to coerce id to an integer. Otherwise it is
+# sorted as text which is not what we want
+../dist/build/tssql/tssql \
+'select `example1.csv`.*, `example2.csv`.`other val`, `example2.csv`.id2
+from `example1.csv` join `example2.csv` on `example1.csv`.id = `example2.csv`.id2
+where `other val` <> "hello 269" and id2 > 246
+order by id + 0 asc' \
+| ../dist/build/csvtopretty/csvtopretty -
diff --git a/examples/query-mgi-markers.bash b/examples/query-mgi-markers.bash
new file mode 100644
--- /dev/null
+++ b/examples/query-mgi-markers.bash
@@ -0,0 +1,12 @@
+#!/bin/bash
+
+# An example of using TxtSushi to query one of the MGI (mouse genome informatics)
+# database reports
+
+wget -q -O - ftp://ftp.informatics.jax.org/pub/reports/MRK_List2.rpt | tabtocsv - \
+| tssql -table mgi - \
+'select `MGI Accession ID`, Symbol, Chr, trim(`cM Position`)
+from mgi where (Chr = 1 or Chr = 8 or Chr = 19) and trim(`cM Position`) = "N/A"
+order by Chr+0, Symbol' \
+| csvtopretty -
+
diff --git a/examples/select-station.bash b/examples/select-station.bash
new file mode 100644
--- /dev/null
+++ b/examples/select-station.bash
@@ -0,0 +1,11 @@
+#!/bin/bash
+
+# replicating SELECT from
+# http://www.itl.nist.gov/div897/ctg/dm/sql_examples.htm
+#
+# SELECT * FROM STATION
+# WHERE LAT_N > 39.7
+
+../dist/build/tssql/tssql -table STATION station.csv \
+'SELECT * FROM STATION WHERE LAT_N > 39.7' \
+| ../dist/build/csvtopretty/csvtopretty -
diff --git a/examples/station.csv b/examples/station.csv
new file mode 100644
--- /dev/null
+++ b/examples/station.csv
@@ -0,0 +1,4 @@
+ID,CITY,STATE,LAT_N,LONG_W
+13,Phoenix,AZ,33,112
+44,Denver,CO,40,105
+66,Caribou,ME,47,68
diff --git a/examples/stats.csv b/examples/stats.csv
new file mode 100644
--- /dev/null
+++ b/examples/stats.csv
@@ -0,0 +1,7 @@
+ID,MONTH,TEMP_F,RAIN_I
+13,1,57.4,0.31
+13,7,91.7,5.15
+44,1,27.3,0.18
+44,7,74.8,2.11
+66,1,6.7,2.1
+66,7,65.8,4.52
diff --git a/joincol.hs b/joincol.hs
new file mode 100644
--- /dev/null
+++ b/joincol.hs
@@ -0,0 +1,60 @@
+import Data.List
+import System.Directory
+import System.Environment
+import System.Exit
+import System.IO
+
+import TxtSushi.IO
+import TxtSushi.Transform
+import Util.IOUtil
+
+closeAll [] = do return ()
+closeAll (handle:tail) = do
+ hClose handle
+ closeAll tail
+
+removeAll [] = do return ()
+removeAll (file:tail) = do
+ removeFile file
+ removeAll tail
+
+main = do
+ args <- getArgs
+
+ let lenArgs = length args
+
+ if lenArgs < 4 || odd lenArgs
+ then do
+ hPutStrLn stderr $
+ "ERROR: program requires at least four arguments " ++
+ "(two or more join column arguments and two filenames), " ++
+ "also the argument count should be even"
+ exitFailure
+ else do
+ let lenNonFileArgs = (lenArgs - 2)
+ (nonFileArgs, fileName1:fileName2:[]) = splitAt lenNonFileArgs args
+ allJoinIndices = map read nonFileArgs :: [Int]
+ table1ColIndices = [allJoinIndices !! i | i <- [0, 2 .. (lenNonFileArgs - 1)]]
+ table2ColIndices = [allJoinIndices !! i | i <- [1, 3 .. (lenNonFileArgs - 1)]]
+ zippedColumnIndices = zip table1ColIndices table2ColIndices
+
+ contents1 <- getContentsFromFileOrStdin fileName1
+ contents2 <- getContentsFromFileOrStdin fileName2
+
+ let table1 = parseTable csvFormat contents1
+ table2 = parseTable csvFormat contents2
+
+ (partialSortTables1, partialSortFileHandles1, partialSortFiles1) <- fileBasedSortTable table1ColIndices table1
+ (partialSortTables2, partialSortFileHandles2, partialSortFiles2) <- fileBasedSortTable table2ColIndices table2
+
+ let sortedTable1 = mergeAllBy (rowComparison table1ColIndices) partialSortTables1
+ sortedTable2 = mergeAllBy (rowComparison table2ColIndices) partialSortTables2
+ joinedTable = joinPresortedTables zippedColumnIndices sortedTable1 sortedTable2
+ joinedTableText = formatTable csvFormat joinedTable
+
+ putStr joinedTableText
+
+ closeAll $ partialSortFileHandles1 ++ partialSortFileHandles2
+ removeAll $ partialSortFiles1 ++ partialSortFiles2
+
+ return ()
diff --git a/selectcol.hs b/selectcol.hs
new file mode 100644
--- /dev/null
+++ b/selectcol.hs
@@ -0,0 +1,51 @@
+import Data.List
+import System.Environment
+import System.Exit
+import System.IO
+
+import TxtSushi.IO
+import TxtSushi.Transform
+import Util.CommandLineArgument
+import Util.IOUtil
+
+{-
+byNameOption = OptionDescription
+ False -- isRequired
+ "-by-name" -- optionFlag
+ [] -- argumentNames
+ 0 -- minArgumentCount
+ True -- argumentCountIsFixed
+
+helpOption = OptionDescription
+ False -- isRequired
+ "-help" -- optionFlag
+ [] -- argumentNames
+ 0 -- minArgumentCount
+ True -- argumentCountIsFixed
+
+options = [helpOption, byNameOption]
+-}
+
+--toColumnIndices optionMap [] =
+
+main = do
+ args <- getArgs
+ progName <- getProgName
+
+ if (length args) <= 1
+ then do
+ error $ progName ++ " requires at least two arguments " ++
+ "(one column argument and a filename or '-')"
+ else do
+ let argCount = length args
+ (argsWithoutFile, [fileName]) = splitAt (argCount - 1) args
+ --(optionsMap, tailArgs) = extractOptions options argsWithoutFile
+ colIndices = map read (init args) :: [Int]
+
+ contents <- getContentsFromFileOrStdin fileName
+
+ let table = parseTable csvFormat contents
+ subsetTable = selectColumns colIndices table
+ subsetTableText = formatTable csvFormat subsetTable
+ putStr subsetTableText
+ return ()
diff --git a/selectcolname.hs b/selectcolname.hs
new file mode 100644
--- /dev/null
+++ b/selectcolname.hs
@@ -0,0 +1,38 @@
+import Data.List
+import System.Environment
+import System.Exit
+import System.IO
+
+import TxtSushi.IO
+import TxtSushi.Transform
+import Util.IOUtil
+
+maybeIndexToIndexOrError :: [String] -> [Maybe Int] -> [Int]
+maybeIndexToIndexOrError [] [] = []
+maybeIndexToIndexOrError (name:namesTail) (Nothing:indexTail) =
+ error $ "Could not find column header named \"" ++ name ++ "\""
+maybeIndexToIndexOrError (name:namesTail) ((Just index):indexTail) =
+ index:(maybeIndexToIndexOrError namesTail indexTail)
+
+main = do
+ args <- getArgs
+
+ if (length args) <= 1
+ then do
+ hPutStrLn stderr $
+ "ERROR: program requires at least two arguments " ++
+ "(one column name argument and a filename or '-')"
+ exitFailure
+ else do
+ contents <- getContentsFromFileOrStdin (last args)
+
+ let argsWithoutFile = init args
+ colNames = init args
+ table = parseTable csvFormat contents
+ header = head table
+ maybeColIndices = [elemIndex name header | name <- colNames]
+ colIndices = maybeIndexToIndexOrError colNames maybeColIndices
+ subsetTable = selectColumns colIndices table
+ subsetTableText = formatTable csvFormat subsetTable
+ putStr subsetTableText
+ return ()
diff --git a/sortcol.hs b/sortcol.hs
new file mode 100644
--- /dev/null
+++ b/sortcol.hs
@@ -0,0 +1,47 @@
+import Data.List
+import System.Directory
+import System.Environment
+import System.Exit
+import System.IO
+
+import TxtSushi.IO
+import TxtSushi.Transform
+import Util.IOUtil
+
+closeAll [] = do return ()
+closeAll (handle:tail) = do
+ hClose handle
+ closeAll tail
+
+removeAll [] = do return ()
+removeAll (file:tail) = do
+ removeFile file
+ removeAll tail
+
+main = do
+ args <- getArgs
+
+ if (length args) <= 1
+ then do
+ hPutStrLn stderr $
+ "ERROR: program requires at least two arguments " ++
+ "(one column argument and a filename or '-')"
+ exitFailure
+ else do
+ contents <- getContentsFromFileOrStdin (last args)
+
+ let argsWithoutFile = init args
+ colIndices = map read (init args) :: [Int]
+ table = parseTable csvFormat contents
+
+ (partialSortTables, partialSortFileHandles, partialSortFiles) <- fileBasedSortTable colIndices table
+
+ let sortedTable = mergeAllBy (rowComparison colIndices) partialSortTables
+ sortedTableText = formatTable csvFormat sortedTable
+
+ putStr sortedTableText
+
+ closeAll partialSortFileHandles
+ removeAll partialSortFiles
+
+ return ()
diff --git a/tabtocsv.hs b/tabtocsv.hs
new file mode 100644
--- /dev/null
+++ b/tabtocsv.hs
@@ -0,0 +1,23 @@
+import Data.List
+import System.Environment
+import System.Exit
+import System.IO
+
+import TxtSushi.IO
+import Util.IOUtil
+
+main = do
+ args <- getArgs
+
+ if (length args) /= 1
+ then do
+ hPutStrLn stderr $
+ "ERROR: program requires a single command line argument " ++
+ "(filename or '-')"
+ exitFailure
+ else do
+ contents <- getContentsFromFileOrStdin (last args)
+
+ let table = parseTable tabDelimitedFormat contents
+ csvText = formatTable csvFormat table
+ putStr csvText
diff --git a/tabtopretty.hs b/tabtopretty.hs
new file mode 100644
--- /dev/null
+++ b/tabtopretty.hs
@@ -0,0 +1,38 @@
+import Data.List
+import System.Directory
+import System.Environment
+import System.Exit
+import System.IO
+
+import TxtSushi.IO
+import Util.IOUtil
+
+main = do
+ args <- getArgs
+
+ if (length args) /= 1
+ then do
+ hPutStrLn stderr $
+ "ERROR: program requires a single command line argument " ++
+ "(filename or '-')"
+ exitFailure
+ else do
+ let fileArg = head args
+ useStdio = (fileArg == "-")
+
+ file <- if useStdio then bufferStdioToTempFile else return fileArg
+
+ handle1 <- openFile file ReadMode
+ contents1 <- hGetContents handle1
+ handle2 <- openFile file ReadMode
+ contents2 <- hGetContents handle2
+
+ let table1 = parseTable tabDelimitedFormat contents1
+ columnWidths = maxTableColumnWidths table1
+ table2 = parseTable tabDelimitedFormat contents2
+ prettyTableText = formatTableWithWidths "|" columnWidths table2
+
+ putStr prettyTableText
+ hClose handle1
+ hClose handle2
+ if useStdio then removeFile file else return ()
diff --git a/tssql.hs b/tssql.hs
new file mode 100644
--- /dev/null
+++ b/tssql.hs
@@ -0,0 +1,116 @@
+-----------------------------------------------------------------------------
+-- |
+-- Copyright : (c) Keith Sheppard 2009
+-- License : GPL3 or greater
+-- Maintainer : keithshep@gmail.com
+-- Stability : experimental
+-- Portability : portable
+--
+-- Main entry point for the TxtSushi SQL command line
+--
+-----------------------------------------------------------------------------
+import Data.List
+import qualified Data.Map as Map
+import System.Environment
+import System.Exit
+import System.IO
+
+import Text.ParserCombinators.Parsec
+
+import TxtSushi.IO
+import TxtSushi.SQLExecution
+import TxtSushi.SQLParser
+import TxtSushi.Transform
+import Util.CommandLineArgument
+import Util.IOUtil
+
+helpOption = OptionDescription {
+ isRequired = False,
+ optionFlag = "-help",
+ argumentNames = [],
+ minArgumentCount = 0,
+ argumentCountIsFixed = True}
+
+tableDefOption = OptionDescription {
+ isRequired = False,
+ optionFlag = "-table",
+ argumentNames = ["CSV-file-name", "table-name"],
+ minArgumentCount = 2,
+ argumentCountIsFixed = True}
+
+turtleSqlOpts = [helpOption, tableDefOption]
+
+sqlCmdLine = CommandLineDescription {
+ options = turtleSqlOpts,
+ minTailArgumentCount = 1,
+ tailArgumentNames = ["SQL-select-statement"],
+ tailArgumentCountIsFixed = True}
+
+validateTableNames :: [String] -> [String] -> Bool
+validateTableNames [] _ = True
+validateTableNames (argTblHead:argTblTail) selectTbls =
+ if argTblHead `elem` selectTbls then
+ validateTableNames argTblTail selectTbls
+ else
+ error $ "The given table name \"" ++ argTblHead ++
+ "\" does not appear in the SELECT statement"
+
+tableArgsToMap [] = Map.empty
+tableArgsToMap (currTableArgs:tailTableArgs) =
+ case currTableArgs of
+ [fileName, tableName] ->
+ Map.insert fileName tableName (tableArgsToMap tailTableArgs)
+ otherwise ->
+ error $ "the \"" ++ (optionFlag tableDefOption) ++
+ "\" option should have exactly two arguments"
+
+unwrapMapList [] = return []
+unwrapMapList ((key, value):mapTail) = do
+ unwrappedValue <- value
+ unwrappedTail <- unwrapMapList mapTail
+ return $ (key, unwrappedValue):unwrappedTail
+
+printUsage progName =
+ putStrLn $ "Usage: " ++ progName ++ " " ++ formatCommandLine sqlCmdLine
+
+main = do
+ args <- getArgs
+ progName <- getProgName
+
+ let (argMap, argTail) = extractCommandLineArguments sqlCmdLine args
+ showHelp = Map.member helpOption argMap || length argTail /= 1
+ parseOutcome = parse parseSelectStatement "" (head argTail)
+
+ if showHelp then printUsage progName else
+ case parseOutcome of
+ Left err -> print err
+ Right selectStmt ->
+ let
+ -- create a table file map from the user args
+ tableArgs = Map.findWithDefault [] tableDefOption argMap
+ tableArgMap = tableArgsToMap tableArgs
+
+ -- get a default table to file map from the select statement
+ selectTblNames = allMaybeTableNames (maybeFromTable selectStmt)
+ defaultTblMap = Map.fromList (zip selectTblNames selectTblNames)
+
+ -- join the two with arg values taking precidence over
+ -- the default values
+ finalTblFileMap = tableArgMap `Map.union` defaultTblMap
+ in
+ -- turn the files into strings
+ if validateTableNames (Map.keys tableArgMap) selectTblNames
+ then do
+ let contentsMap = Map.map getContentsFromFileOrStdin finalTblFileMap
+
+ unwrappedContents <- unwrapMapList $ Map.toList contentsMap
+
+ let unwrappedContentsMap = Map.fromList unwrappedContents
+ textTableMap = Map.map (parseTable csvFormat) unwrappedContentsMap
+ dbTableMap = Map.mapWithKey textTableToDatabaseTable textTableMap
+ selectedDbTable = select selectStmt dbTableMap
+ selectedTxtTable = databaseTableToTextTable selectedDbTable
+
+ putStr $ formatTable csvFormat selectedTxtTable
+ else
+ exitFailure
diff --git a/txt-sushi.cabal b/txt-sushi.cabal
new file mode 100644
--- /dev/null
+++ b/txt-sushi.cabal
@@ -0,0 +1,47 @@
+Name: txt-sushi
+Version: 0.1
+Synopsis: A collection of command line utilities for processing text tables
+Description:
+ TxtSushi is a collection of command line utilities for processing
+ comma-separated and tab-delimited files (AKA flat files, spreadsheets).
+ By focusing exclusively on processing text files with a tabular structure,
+ TxtSushi simplifies common tasks like filtering, joining and transformation
+ that would take some effort to accomplish with a more powerful scripting
+ language. TxtSushi's homepage is .
+License: GPL
+License-File: COPYING
+Author: Keith Sheppard
+Maintainer: keithshep@gmail.com
+Build-Type: Simple
+Category: Utils, Text, Database
+Cabal-Version: >=1.2
+
+Executable tssql
+ Main-Is: tssql.hs
+ Build-Depends: base,haskell98,directory,containers,parsec
+
+ -- creates highly optimized code (slow compile)
+ GHC-Options: -O2 -fvia-C
+
+ -- combine the following with the +RTS -xc -RTS runtime option for stack taces
+ --GHC-Options: -prof -auto-all
+
+Executable csvtotab
+ Main-Is: csvtotab.hs
+ Build-Depends: base,haskell98,directory,containers
+ GHC-Options: -O2 -fvia-C
+
+Executable tabtocsv
+ Main-Is: tabtocsv.hs
+ Build-Depends: base,haskell98,directory,containers
+ GHC-Options: -O2 -fvia-C
+
+Executable csvtopretty
+ Main-Is: csvtopretty.hs
+ Build-Depends: base,haskell98,directory,containers
+ GHC-Options: -O2 -fvia-C
+
+Executable tabtopretty
+ Main-Is: tabtopretty.hs
+ Build-Depends: base,haskell98,directory,containers
+ GHC-Options: -O2 -fvia-C