diff --git a/LICENSE b/LICENSE
new file mode 100644
--- /dev/null
+++ b/LICENSE
@@ -0,0 +1,674 @@
+                    GNU GENERAL PUBLIC LICENSE
+                       Version 3, 29 June 2007
+
+ Copyright (C) 2007 Free Software Foundation, Inc. <http://fsf.org/>
+ 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.
+
+    <one line to give the program's name and a brief idea of what it does.>
+    Copyright (C) <year>  <name of author>
+
+    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 <http://www.gnu.org/licenses/>.
+
+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:
+
+    <program>  Copyright (C) <year>  <name of author>
+    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
+<http://www.gnu.org/licenses/>.
+
+  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
+<http://www.gnu.org/philosophy/why-not-lgpl.html>.
diff --git a/Setup.lhs b/Setup.lhs
new file mode 100644
--- /dev/null
+++ b/Setup.lhs
@@ -0,0 +1,3 @@
+#! /usr/bin/env runhaskell
+> import Distribution.Simple
+> main = defaultMain
diff --git a/example/Speed.hs b/example/Speed.hs
new file mode 100644
--- /dev/null
+++ b/example/Speed.hs
@@ -0,0 +1,82 @@
+module Main where
+
+import qualified Text.HTML.Tagchup.Tag    as Tag
+import qualified Text.HTML.Tagchup.Parser as Parser
+import qualified Text.HTML.Tagchup.Parser.Stream as Str
+import qualified Text.XML.Basic.Name.MixedCase as Name
+
+import System.Time (getClockTime, diffClockTimes, tdSec, tdPicosec, )
+
+import qualified Data.ByteString.Char8      as BS
+import qualified Data.ByteString.Lazy.Char8 as BL
+
+
+measureTime :: String -> IO () -> IO ()
+measureTime name act =
+   do putStr (name++": ")
+      timeA <- getClockTime
+      act
+      timeB <- getClockTime
+      let td = diffClockTimes timeB timeA
+      print (fromIntegral (tdSec td) +
+             fromInteger (tdPicosec td) * 1e-12 :: Double)
+
+number :: Int
+number = 100000
+
+main :: IO ()
+main =
+   do measureTime "String" $ print $
+         (last $ Parser.runSoup $ concat $ replicate number "<li>item</li>" :: Tag.T Name.T String)
+      measureTime "ByteString.Strict" $ print $
+         (last $ Parser.runSoup $ BS.concat $ replicate number $ BS.pack "<li>item</li>" :: Tag.T Name.T String)
+      measureTime "ByteString.Lazy" $ print $
+         (last $ Parser.runSoup $ BL.concat $ replicate number $ BL.pack "<li>item</li>" :: Tag.T Name.T String)
+
+      measureTime "Pointer.Strict" $ print $
+         (last $ Parser.runSoup $ Str.pointerFromByteStringStrict $ BS.concat $ replicate number $ BS.pack "<li>item</li>" :: Tag.T Name.T String)
+      measureTime "Pointer.Lazy" $ print $
+         (last $ Parser.runSoup $ Str.pointerFromByteStringLazy $ BL.concat $ replicate number $ BL.pack "<li>item</li>" :: Tag.T Name.T String)
+
+{-
+Results without inlining on euler:
+
+String: Close "li"
+2.182197
+ByteString.Strict: Close "li"
+2.704024
+ByteString.Lazy: Close "li"
+3.203038
+
+These figures remain, when Stream methods are inlined.
+
+
+Results without inlining on anubis:
+String: Close "li"
+3.507383
+ByteString.Strict: Close "li"
+4.406978
+ByteString.Lazy: Close "li"
+5.266979
+Pointer.Strict: Close "li"
+3.37898
+Pointer.Lazy: Close "li"
+3.185808
+
+
+The figures become worse, when MTL and Combinator functions are inlined, too:
+String: Close "li"
+3.56803
+ByteString.String: Close "li"
+4.314474
+ByteString.Lazy: Close "li"
+4.855984
+
+With the main parser functions inlined we get:
+tring: Close "li"
+2.951519
+ByteString.String: Close "li"
+2.910444
+ByteString.Lazy: Close "li"
+3.046311
+-}
diff --git a/example/Test.hs b/example/Test.hs
new file mode 100644
--- /dev/null
+++ b/example/Test.hs
@@ -0,0 +1,7 @@
+module Main where
+
+import Text.HTML.Tagchup.Test as Test
+
+main :: IO ()
+main =
+   putStrLn Test.laziness
diff --git a/example/Validate.hs b/example/Validate.hs
new file mode 100644
--- /dev/null
+++ b/example/Validate.hs
@@ -0,0 +1,36 @@
+{-
+Example program for TagSoup.
+Detects basic syntax errors like isolated ampersands and unquoted attribute values.
+-}
+module Main where
+
+import Text.HTML.Tagchup.Parser
+import qualified Text.XML.Basic.Position    as Position
+import qualified Text.HTML.Tagchup.PositionTag as PosTag
+import qualified Text.HTML.Tagchup.Tag         as Tag
+import qualified Text.XML.Basic.Name.MixedCase as Name
+
+import System.Environment (getArgs)
+
+import Data.Maybe (mapMaybe)
+
+
+validate :: FilePath -> String -> String
+validate fileName input =
+   let tags :: [PosTag.T Name.T String]
+       tags = runSoupWithPositionsName fileName input
+       warnings =
+          mapMaybe
+             (\(PosTag.Cons pos tag) ->
+                 fmap (\msg -> Position.toReportText pos ++ " " ++ msg) $
+                 Tag.maybeWarning tag)
+             tags
+   in  unlines warnings
+
+validateIO :: FilePath -> IO ()
+validateIO fileName =
+   putStrLn . validate fileName =<< readFile fileName
+
+
+main :: IO ()
+main = mapM_ validateIO =<< getArgs
diff --git a/src/Text/HTML/Tagchup/Format.hs b/src/Text/HTML/Tagchup/Format.hs
new file mode 100644
--- /dev/null
+++ b/src/Text/HTML/Tagchup/Format.hs
@@ -0,0 +1,90 @@
+{-|
+Convert a tag soup to its text representation
+respecting various conventions for merging open and close tags.
+-}
+module Text.HTML.Tagchup.Format (
+   xml, xmlCondensed, html, xhtml, htmlOrXhtml,
+   ) where
+
+import qualified Text.HTML.Tagchup.Tag as Tag
+import qualified Text.HTML.Basic.Tag      as TagH
+import qualified Text.XML.Basic.Name      as Name
+import qualified Text.XML.Basic.Format    as Fmt
+
+import Data.List.HT (viewL, )
+import Data.Maybe (fromMaybe, )
+import Control.Monad (guard, )
+
+
+{-
+*Text.HTML.Tagchup.Format> flip xml "" $ (Text.HTML.TagSoup.HT.Parser.runSoup "<?xml version=1.0 ?>" :: [Tag.T Text.XML.Basic.Name.LowerCase.T String])
+-}
+
+
+{- |
+All tags are formatted as they are.
+-}
+xml :: (Name.Tag name, Name.Attribute name, Fmt.C string) =>
+   [Tag.T name string] -> ShowS
+xml = Fmt.many Fmt.run
+
+
+{- |
+Adjacent corresponding open and close tags are merged to a self-closing tag.
+E.g. @<a></a>@ becomes @<a/>@.
+-}
+xmlCondensed :: (Name.Tag name, Name.Attribute name, Fmt.C string) =>
+   [Tag.T name string] -> ShowS
+xmlCondensed = xmlCondensedGen (==)
+
+{- |
+All tags that are defined being self-closing by the HTML standard
+are formatted only as open tag.
+E.g. @<br>@.
+-}
+html :: (Name.Tag name, Name.Attribute name, Fmt.C string) =>
+   [Tag.T name string] -> ShowS
+html =
+   Fmt.many Fmt.run .
+   filter (maybe True (not . TagH.isEmpty) . Tag.maybeClose)
+
+{- |
+All tags that are defined being self-closing by the XHTML standard
+are formatted as self-closing open tag.
+E.g. @<br/>@.
+-}
+xhtml :: (Name.Tag name, Name.Attribute name, Fmt.C string) =>
+   [Tag.T name string] -> ShowS
+xhtml =
+   xmlCondensedGen
+      -- e.g. <div></div> must not be merged to <div/>
+      (\nameOpen nameClose ->
+          nameOpen==nameClose && TagH.isEmpty nameOpen)
+
+{- |
+If the first tag is @<?xml ...?>@ then format in XHTML style,
+else in HTML style.
+-}
+htmlOrXhtml :: (Name.Tag name, Name.Attribute name, Fmt.C string) =>
+   [Tag.T name string] -> ShowS
+htmlOrXhtml tags =
+   fromMaybe (html tags) $
+      do (tag,_) <- viewL tags
+         (name,_) <- Tag.maybeProcessing tag
+         guard (Name.match "xml" name)
+         return (xhtml tags)
+
+
+xmlCondensedGen :: (Name.Tag name, Name.Attribute name, Fmt.C string) =>
+   (Tag.Name name -> Tag.Name name -> Bool) ->
+   [Tag.T name string] -> ShowS
+xmlCondensedGen check =
+   let recourse (Tag.Open nameOpen attrs : Tag.Close nameClose : ts) =
+          (if check nameOpen nameClose
+             then Tag.formatOpen True  nameOpen attrs
+             else Tag.formatOpen False nameOpen attrs .
+                  Tag.formatClose nameClose)
+          . recourse ts
+       recourse (t : ts) = Fmt.run t . recourse ts
+       recourse [] = id
+   in  recourse
diff --git a/src/Text/HTML/Tagchup/Parser.hs b/src/Text/HTML/Tagchup/Parser.hs
new file mode 100644
--- /dev/null
+++ b/src/Text/HTML/Tagchup/Parser.hs
@@ -0,0 +1,557 @@
+{-|
+Parse a string into our custom tag soup data structure.
+
+The parser works only on proper Unicode texts.
+That is, you must have decoded it before,
+e.g. using decoding functions from hxt or encoding package.
+'Text.HTML.Tagchup.Process.findMetaEncoding'
+can assist you retrieving the character set encoding
+from meta information of the document at hand.
+-}
+module Text.HTML.Tagchup.Parser (
+    CharType,
+    runSoup, runSoupWithPositions, runSoupWithPositionsName,
+    runTag, runInnerOfTag,
+  ) where
+
+import Text.HTML.Tagchup.Parser.Combinator
+   (allowFail, withDefault,
+    char, dropSpaces, getPos,
+    many, manyS, many0toN, many1toN,
+    many1Satisfy, readUntil,
+    satisfy, string,
+    emit, modifyEmission, )
+
+import qualified Text.HTML.Tagchup.Parser.Combinator as Parser
+import qualified Text.HTML.Tagchup.Parser.Status as Status
+
+import qualified Text.HTML.Tagchup.PositionTag as PosTag
+import qualified Text.HTML.Tagchup.Tag         as Tag
+import qualified Text.XML.Basic.Position    as Position
+import qualified Text.HTML.Basic.Character    as HTMLChar
+import qualified Text.XML.Basic.ProcessingInstruction as PI
+import qualified Text.XML.Basic.Attribute   as Attr
+import qualified Text.XML.Basic.Name        as Name
+import qualified Text.XML.Basic.Tag         as TagName
+
+import qualified Text.HTML.Tagchup.Parser.Stream as Stream
+
+import qualified Text.HTML.Basic.Entity as HTMLEntity
+
+import qualified Control.Monad.Exception.Synchronous as Exc
+
+import Control.Monad.Trans.Writer (runWriterT, )
+import Control.Monad.Trans.State (StateT(..), )
+import Control.Monad (mplus, msum, when, liftM, )
+
+import Data.Monoid (Monoid, mempty, mconcat, )
+
+import qualified Data.Map as Map
+
+import Data.Tuple.HT (mapSnd, )
+import Data.Char (isAlphaNum, isAscii, chr, ord, )
+import Data.Maybe (fromMaybe, maybeToList, )
+
+-- import qualified Numeric
+
+
+-- * run parser in several ways
+
+{- |
+Parse a single tag, throws an error if there is a syntax error.
+This is useful for parsing a match pattern.
+-}
+runTag ::
+   (Stream.C source, StringType sink, Show sink,
+    Name.Attribute name, Name.Tag name, Show name) =>
+   source -> Tag.T name sink
+runTag str =
+   let makeError msg =
+          error $ "runTag: " ++ msg
+       ((openTag, closeTag), warnings) =
+          fromMaybe (makeError "no parse at all") $
+          Parser.run "pattern string" parsePosTag str
+   in  if not (null warnings)
+         then
+           makeError
+              (unlines $ "parsing results in" : map show warnings)
+         else
+           case closeTag of
+              Nothing -> PosTag.tag_ openTag
+              _ -> makeError "self-closing tag not supported"
+
+{- |
+Parse the inner of a single tag.
+That is, @runTag \"\<bla\>\"@ is the same as @runInnerOfTag \"bla\"@.
+-}
+runInnerOfTag ::
+   (StringType sink, Show sink,
+    Name.Attribute name, Name.Tag name, Show name) =>
+   String -> Tag.T name sink
+runInnerOfTag str = runTag $ "<"++str++">"
+
+
+
+runSoupWithPositionsName ::
+   (Stream.C source, StringType sink,
+    Name.Attribute name, Name.Tag name) =>
+   FilePath -> source -> [PosTag.T name sink]
+runSoupWithPositionsName fileName =
+   PosTag.concatTexts .
+   Parser.runIdentity .
+   Parser.eval fileName
+      (liftM concat $ manyS parsePosTagMergeWarnings)
+
+
+-- | Parse an HTML document to a list of 'Tag.T'.
+-- Automatically expands out escape characters.
+runSoupWithPositions ::
+   (Stream.C source, StringType sink,
+    Name.Attribute name, Name.Tag name) =>
+   source -> [PosTag.T name sink]
+runSoupWithPositions =
+   runSoupWithPositionsName "input"
+
+-- | Like 'runSoupWithPositions' but hides source file positions.
+runSoup ::
+   (Stream.C source, StringType sink,
+    Name.Attribute name, Name.Tag name) =>
+   source -> [Tag.T name sink]
+runSoup = map PosTag.tag_ . runSoupWithPositions
+
+
+
+-- * parser parts
+
+type Warning = (Position.T, String)
+
+type Parser     source a = Parser.Full     source Warning a
+type ParserEmit source a = Parser.Emitting source Warning a
+
+
+parsePosTagMergeWarnings ::
+   (Stream.C source, StringType sink,
+    Name.Attribute name, Name.Tag name) =>
+   StateT (Status.T source) Maybe [PosTag.T name sink]
+parsePosTagMergeWarnings =
+   liftM (\((ot,ct),warns) ->
+      ot :
+      map (\(pos,warn) -> PosTag.cons pos $ Tag.Warning warn) warns ++
+      maybeToList ct) $
+   runWriterT parsePosTag
+
+parsePosTag ::
+   (Stream.C source, StringType sink,
+    Name.Attribute name, Name.Tag name) =>
+   Parser source (PosTag.T name sink, Maybe (PosTag.T name sink))
+parsePosTag = do
+   let omitClose :: Monad m => m t -> m (t, Maybe t)
+       omitClose = liftM (\t -> (t, Nothing))
+   pos <- getPos
+   mplus
+      (do char '<'
+          allowFail $ withDefault
+             (msum $
+                omitClose (parseSpecialTag pos) :
+                omitClose (parseProcessingTag pos) :
+                omitClose (parseCloseTag pos) :
+                parseOpenTag pos :
+                [])
+             (do emitWarning pos "A '<', that is not part of a tag. Encode it as &lt; please."
+                 omitClose (returnTag pos (Tag.Text $ stringFromChar '<'))))
+      (omitClose (parseText pos))
+
+
+{- |
+Parsing an open tag may also emit a close tag
+if the tag is self-closing, e.g. @<br/>@.
+
+For formatting self-closing tags correctly
+it would be better to emit tags in the order @open tag, close tag, warnings@.
+However, if there are infinitely many warnings,
+we don't know whether a self-closing slash comes
+and thus whether there is a close tag or not.
+This implies, that we cannot even emit the warnings.
+
+Thus we choose the order @open tag, warnings, close tag@.
+-}
+parseOpenTag ::
+   (Stream.C source, StringType sink,
+    Name.Attribute name, Name.Tag name) =>
+   Position.T ->
+   Parser source
+      (PosTag.T name sink, Maybe (PosTag.T name sink))
+parseOpenTag pos =
+   do name <- parseName
+      allowFail $
+         do dropSpaces
+            tag <- returningTag pos (Tag.Open name) $
+               modifyEmission (restrictWarnings 10) $ many parseAttribute
+            liftM ((,) tag) $ withDefault
+               (do closePos <- getPos
+                   string "/>"
+                   allowFail $ liftM Just $ returnTag closePos (Tag.Close name))
+               (do junkPos <- getPos
+                   readUntilTerm
+                      (\ junk ->
+                         emitWarningWhen
+                            (not $ null junk)
+                            junkPos ("Junk in opening tag: \"" ++ junk ++ "\""))
+                      ("Unterminated open tag \"" ++ Name.toString name ++ "\"") ">"
+                   return Nothing)
+
+parseCloseTag ::
+   (Stream.C source, Name.Tag name) =>
+   Position.T -> Parser source (PosTag.T name sink)
+parseCloseTag pos =
+   do char '/'
+      name <- parseName
+      allowFail $
+         do tag <- returnTag pos (Tag.Close name)
+            dropSpaces
+            junkPos <- getPos
+            readUntilTerm
+               (\ junk ->
+                  emitWarningWhen
+                     (not $ null junk)
+                     junkPos ("Junk in closing tag: \"" ++ junk ++"\""))
+               ("Unterminated closing tag \"" ++ Name.toString name ++"\"") ">"
+            return tag
+
+parseSpecialTag ::
+   (Stream.C source, Name.Tag name) =>
+   Position.T -> Parser source (PosTag.T name sink)
+parseSpecialTag pos =
+   do char '!'
+      msum $
+       (do string "--"
+           allowFail $ readUntilTerm
+              (\ cmt -> returnTag pos (Tag.Comment cmt))
+              "Unterminated comment" "-->") :
+       (do string TagName.cdataString
+           allowFail $ readUntilTerm
+              (\ cdata -> returnTag pos (Tag.Special TagName.cdata cdata))
+              "Unterminated cdata" "]]>") :
+       (do name <- parseName
+           allowFail $
+              do dropSpaces
+                 readUntilTerm
+                    (\ info -> returnTag pos (Tag.Special name info))
+                    ("Unterminated special tag \"" ++ Name.toString name ++ "\"") ">") :
+       []
+
+parseProcessingTag ::
+   (Stream.C source, StringType sink,
+    Name.Attribute name, Name.Tag name) =>
+   Position.T -> Parser source (PosTag.T name sink)
+parseProcessingTag pos =
+   do char '?'
+      name <- parseName
+      allowFail $
+         do dropSpaces
+            returningTag pos (Tag.Processing name) $
+               if Name.matchAny ["xml", "xml-stylesheet"] name
+                 then
+                   do attrs <- many parseAttribute
+                      junkPos <- getPos
+                      readUntilTerm
+                         (\ junk ->
+                            emitWarningWhen (not $ null junk) junkPos
+                               ("Junk in processing info tag: \"" ++ junk ++ "\""))
+                         ("Unterminated processing info tag \"" ++ Name.toString name ++ "\"") "?>"
+                      return $ PI.Known attrs
+                 else readUntilTerm (return . PI.Unknown)
+                         "Unterminated processing instruction" "?>"
+
+parseText ::
+   (Stream.C source, StringType sink) =>
+   Position.T -> Parser source (PosTag.T name sink)
+parseText pos =
+   returningTag pos Tag.Text (parseCharAsString (const True))
+--   returningTag pos Tag.Text (parseCharAsString ('<'/=))
+--   returningTag pos Tag.Text (parseString1 ('<'/=))
+
+
+parseAttribute ::
+   (Stream.C source, StringType sink, Name.Attribute name) =>
+   Parser source (Attr.T name sink)
+parseAttribute =
+   parseName >>= \name -> allowFail $
+   do dropSpaces
+      value <-
+         withDefault
+            (string "=" >> allowFail (dropSpaces >> parseValue))
+            (return mempty)
+      dropSpaces
+      return $ Attr.Cons name value
+
+parseName ::
+   (Stream.C source, Name.C pname) =>
+   Parser source pname
+parseName =
+   liftM Name.fromString $
+   -- we must restrict to ASCII alphanum characters in order to exclude umlauts
+   many1Satisfy (\c -> isAlphaNum c && isAscii c || c `elem` "_-.:")
+
+parseValue ::
+   (Stream.C source, StringType sink) =>
+   ParserEmit source sink
+parseValue =
+   (msum $
+      parseQuoted "Unterminated doubly quoted value string" '"' :
+      parseQuoted "Unterminated singly quoted value string" '\'' :
+      [])
+   `withDefault`
+   parseUnquotedValueAsString
+
+parseUnquotedValueChar ::
+   (Stream.C source) =>
+   ParserEmit source String
+parseUnquotedValueChar =
+   let parseValueChar =
+          do pos <- getPos
+             str <- parseUnicodeChar (not . flip elem " >\"\'")
+             let wrong = filter (not . isValidValueChar) str
+             allowFail $
+                emitWarningWhen (not (null wrong)) pos $
+                "Illegal characters in unquoted value: " ++ wrong
+             return str
+   in  liftM concat $ many parseValueChar
+
+parseUnquotedValueHTMLChar ::
+   (Stream.C source) =>
+   ParserEmit source [HTMLChar.T]
+parseUnquotedValueHTMLChar =
+   let parseValueChar =
+          do pos <- getPos
+             hc <- parseHTMLChar (not . flip elem " >\"\'")
+             {- We do the check after each parseHTMLChar
+                and not after (many parseValueChar)
+                in order to correctly interleave warnings. -}
+             allowFail $ mapM_ (checkUnquotedChar pos) hc
+             return hc
+   in  liftM concat $ many parseValueChar
+
+checkUnquotedChar :: Position.T -> HTMLChar.T -> ParserEmit source ()
+checkUnquotedChar pos x =
+   case x of
+      HTMLChar.Unicode c ->
+         emitWarningWhen (not (isValidValueChar c)) pos $
+            "Illegal characters in unquoted value: '" ++ c : "'"
+      _ -> return ()
+
+
+isValidValueChar :: Char -> Bool
+isValidValueChar c  =  isAlphaNum c || c `elem` "_-:."
+
+parseQuoted ::
+   (Stream.C source, StringType sink) =>
+   String -> Char -> Parser source sink
+parseQuoted termMsg quote =
+   char quote >>
+   (allowFail $
+    do str <- parseString (quote/=)
+       withDefault
+          (char quote >> return ())
+          (do termPos <- getPos
+              emitWarning termPos termMsg)
+       return str)
+
+{-
+Instead of using 'generateTag' we could also wrap the call to 'readUntilTerm'
+in 'mfix' in order to emit a tag, where some information is read later.
+-}
+readUntilTerm ::
+   (Stream.C source) =>
+   (String -> ParserEmit source a) -> String -> String -> ParserEmit source a
+readUntilTerm generateTag termWarning termPat =
+   do ~(termFound,str) <- readUntil termPat
+      result <- generateTag str
+      termPos <- getPos
+      emitWarningWhen (not termFound) termPos termWarning
+      return result
+
+
+class CharType char where
+   fromChar :: Char -> char
+   parseChar :: (Stream.C source) => (Char -> Bool) -> Parser source [char]
+   parseUnquotedValue :: (Stream.C source) => ParserEmit source [char]
+
+instance CharType Char where
+   fromChar = id
+   parseChar = parseUnicodeChar
+   parseUnquotedValue = parseUnquotedValueChar
+
+instance CharType HTMLChar.T where
+   fromChar = HTMLChar.Unicode
+   parseChar = parseHTMLChar
+   parseUnquotedValue = parseUnquotedValueHTMLChar
+
+
+class Monoid sink => StringType sink where
+   stringFromChar :: Char -> sink
+   parseCharAsString ::
+      (Stream.C source) =>
+      (Char -> Bool) -> Parser source sink
+   parseUnquotedValueAsString ::
+      (Stream.C source) =>
+      ParserEmit source sink
+
+instance CharType char => StringType [char] where
+   stringFromChar c = [fromChar c]
+   parseCharAsString = parseChar
+   parseUnquotedValueAsString = parseUnquotedValue
+
+
+parseString  ::
+   (Stream.C source, StringType sink) =>
+   (Char -> Bool) -> ParserEmit source sink
+parseString  p = liftM mconcat $ many  (parseCharAsString p)
+
+{-
+parseString1 ::
+   (Stream.C source, StringType sink) =>
+   (Char -> Bool) -> Parser     name source sink sink
+parseString1 p = liftM mconcat $ many1 (parseCharAsString p)
+-}
+
+
+
+parseUnicodeChar ::
+   (Stream.C source) =>
+   (Char -> Bool) -> Parser source String
+parseUnicodeChar p =
+   do pos <- getPos
+      x <- parseHTMLChar p
+      allowFail $ liftM concat $
+         mapM (htmlCharToString pos) x
+
+htmlCharToString ::
+   Position.T -> HTMLChar.T -> ParserEmit source String
+htmlCharToString pos x =
+   let returnChar c = return $ c:[]
+   in  case x of
+          HTMLChar.Unicode c -> returnChar c
+          HTMLChar.CharRef num -> returnChar (chr num)
+          HTMLChar.EntityRef name ->
+             maybe
+                (let refName = '&':name++";"
+                 in  emitWarning pos ("Unknown HTML entity " ++ refName) >>
+                     return refName)
+                returnChar
+                (Map.lookup name HTMLEntity.mapNameToChar)
+
+{- |
+Only well formed entity references are interpreted as single HTMLChars,
+whereas ill-formed entity references are interpreted as sequence of unicode characters without special meaning.
+E.g. "&amp ;" is considered as plain "&amp ;",
+and only "&amp;" is considered an escaped ampersand.
+It is a very common error in HTML documents to not escape an ampersand.
+With the interpretation used here,
+those ampersands are left as they are.
+
+At most one warning can be emitted.
+-}
+parseHTMLChar ::
+   (Stream.C source) =>
+   (Char -> Bool) -> Parser source [HTMLChar.T]
+parseHTMLChar p =
+   do pos <- getPos
+      c <- satisfy p
+      allowFail $
+        if c=='&'
+          then
+            withDefault
+              (do ent <-
+                     mplus
+                        (do char '#'
+                            digits <- allowFail $ many0toN 10 (satisfy isAlphaNum)
+                               -- exclude ';', '"', '<'
+                               -- include 'x'
+                            Exc.switch
+                               (\e ->
+                                  allowFail (emitWarning pos ("Error in numeric entity: " ++ e)) >>
+                                  return (map HTMLChar.fromUnicode ('&':'#':digits)))
+                               (return . (:[]) . HTMLChar.CharRef . ord)
+                               (HTMLEntity.numberToChar digits))
+                        (liftM ((:[]) . HTMLChar.EntityRef) $
+                         many1toN 10 (satisfy isAlphaNum))
+                  char ';'
+                  return ent)
+              (emitWarning pos "Non-terminated entity reference" >>
+               return [HTMLChar.Unicode '&'])
+          else return [HTMLChar.Unicode c]
+
+{-
+readHex :: (Num a) => String -> a
+readHex str =
+   case Numeric.readHex str of
+      [(n,"")] -> n
+      _ -> error "readHex: no parse"
+
+{-
+We cannot emit specific warnings,
+because the sub-parsers simply fail
+and then throw away the warnings.
+-}
+parseHTMLCharGenericWarning ::
+   (Stream.C source) =>
+   (Char -> Bool) -> Parser source [HTMLChar.T]
+parseHTMLCharGenericWarning p =
+   do pos <- getPos
+      c <- satisfy p
+      allowFail $
+        if c=='&'
+          then
+            withDefault
+              (do ent <-
+                     mplus
+                        (char '#' >>
+                         liftM HTMLChar.CharRef
+                            (mplus
+                               (char 'x' >> liftM readHex (many1toN 8 (satisfy isHexDigit)))
+                               (liftM read (many1toN 10 (satisfy isDigit)))))
+                        (liftM HTMLChar.EntityRef $ many1toN 10 (satisfy isAlphaNum))
+                  char ';'
+                  return [ent])
+              (emitWarning pos "Ill formed entity" >>
+               return [HTMLChar.Unicode '&'])
+          else return [HTMLChar.Unicode c]
+-}
+
+
+restrictWarnings :: Int -> [Warning] -> [Warning]
+restrictWarnings n =
+   uncurry (++) .
+   mapSnd
+      (\rest ->
+          case rest of
+             (pos, _) : _ ->
+                [(pos, "further warnings suppressed")]
+             _ -> []) .
+   splitAt n
+
+
+-- these functions have intentionally restricted types
+
+emitWarningWhen :: Bool -> Position.T -> String -> ParserEmit source ()
+emitWarningWhen cond pos msg =
+   when cond $ emitWarning pos msg
+
+emitWarning :: Position.T -> String -> ParserEmit source ()
+emitWarning = curry emit
+
+returnTag ::
+   Position.T ->
+   Tag.T name sink ->
+   ParserEmit source (PosTag.T name sink)
+returnTag p t = return (PosTag.cons p t)
+
+returningTag ::
+   (Monad m) =>
+   Position.T ->
+   (a -> Tag.T name sink) ->
+   m a ->
+   m (PosTag.T name sink)
+returningTag pos f =
+   liftM (PosTag.cons pos . f)
diff --git a/src/Text/HTML/Tagchup/Parser/Combinator.hs b/src/Text/HTML/Tagchup/Parser/Combinator.hs
new file mode 100644
--- /dev/null
+++ b/src/Text/HTML/Tagchup/Parser/Combinator.hs
@@ -0,0 +1,176 @@
+module Text.HTML.Tagchup.Parser.Combinator (
+   Parser.T, Full, Emitting, Fallible, Plain,
+   char, dropSpaces, getPos,
+   many, many1, manyS, many1S, manyNull, many1Null, many0toN, many1toN,
+   many1Satisfy, manySatisfy, readUntil,
+   satisfy, string,
+   emit, modifyEmission,
+   eval, run, write, gets,
+   withDefault, allowFail, allowEmit,
+   Identity, runIdentity, )
+  where
+
+
+import qualified Text.XML.Basic.Position as Position
+import qualified Text.HTML.Tagchup.Parser.Status as Status
+import qualified Text.HTML.Tagchup.Parser.Stream as Stream
+
+import qualified Text.HTML.Tagchup.Parser.Core as Parser
+import Text.HTML.Tagchup.Parser.Core hiding (run, )
+
+import Control.Monad.Trans.State (StateT(..), evalStateT, )
+-- import Control.Monad.Trans (lift, )
+import Control.Monad (liftM, liftM2, guard, )
+
+import Data.Monoid (Monoid)
+
+import Data.Char (isSpace)
+
+
+
+type Full     input w = Parser.T input [w] Maybe
+type Fallible input   = Parser.T input ()  Maybe
+type Emitting input w = Parser.T input [w] Identity
+type Plain    input   = Parser.T input ()  Identity
+
+
+write :: Monad fail =>
+   FilePath -> Parser.T input output fail () -> input -> fail output
+write fileName p =
+   liftM (\ ~(_,_,ws) -> ws) .
+   Parser.run p .
+   Status.Cons (Position.initialize fileName)
+
+run :: Monad fail =>
+   FilePath -> Parser.T input output fail a -> input -> fail (a, output)
+run fileName p =
+   liftM (\ ~(a,_,ws) -> (a,ws)) .
+   Parser.run p .
+   Status.Cons (Position.initialize fileName)
+
+eval ::  Monad fail =>
+   FilePath -> StateT (Status.T input) fail a -> input -> fail a
+eval fileName p =
+   evalStateT p .
+   Status.Cons (Position.initialize fileName)
+
+
+
+getPos ::
+   (Monoid output, Monad fail) =>
+   Parser.T input output fail Position.T
+getPos = gets Status.sourcePos
+
+satisfy ::
+   (Monoid output, Stream.C input) =>
+   (Char -> Bool) -> Parser.T input output Maybe Char
+satisfy p =
+   do c <- nextChar
+      if p c
+        then return c
+        else fail "character not matched"
+
+-- | does never fail
+many :: Monoid output =>
+   Parser.T input output Maybe a -> Parser.T input output Identity [a]
+many x =
+   {- It is better to have 'force' at the place it is,
+      instead of writing it to the recursive call,
+      because 'x' can cause an infinite loop. -}
+   withDefault (many1 x) (return [])
+
+-- | fails when trying the sub-parser the first time or never
+many1 :: Monoid output =>
+   Parser.T input output Maybe a -> Parser.T input output Maybe [a]
+many1 x = liftM2 (:) x (allowFail $ many x)
+
+
+-- | does never fail
+manyS ::
+   StateT s Maybe a -> StateT s Identity [a]
+manyS x =
+   withDefault' (many1S x) (return [])
+
+-- | fails when trying the sub-parser the first time or never
+many1S ::
+   StateT s Maybe a -> StateT s Maybe [a]
+many1S x = liftM2 (:) x (allowFail' $ manyS x)
+
+
+manyNull :: Monoid output =>
+   Parser.T input output Maybe () -> Parser.T input output Identity ()
+manyNull x =
+   withDefault (many1Null x) (return ())
+
+many1Null :: Monoid output =>
+   Parser.T input output Maybe () -> Parser.T input output Maybe ()
+many1Null x = x >> (allowFail $ manyNull x)
+
+
+many0toN :: Monoid output =>
+   Int -> Parser.T input output Maybe a -> Parser.T input output Identity [a]
+many0toN n x =
+   withDefault (guard (n>0) >> many1toN n x) (return [])
+
+-- | condition: n>0, this will not be checked
+many1toN :: Monoid output =>
+   Int -> Parser.T input output Maybe a -> Parser.T input output Maybe [a]
+many1toN n x = liftM2 (:) x (allowFail $ many0toN (pred n) x)
+
+
+manySatisfy ::
+   (Monoid output, Stream.C input) =>
+   (Char -> Bool) -> Parser.T input output Identity String
+manySatisfy =
+   allowEmit . many . satisfy
+
+many1Satisfy ::
+   (Monoid output, Stream.C input) =>
+   (Char -> Bool) -> Parser.T input output Maybe String
+many1Satisfy =
+   allowEmit . many1 . satisfy
+
+dropSpaces ::
+   (Monoid output, Stream.C input) =>
+   Parser.T input output Identity ()
+dropSpaces =
+   manySatisfy isSpace >> return ()
+
+
+char ::
+   (Monoid output, Stream.C input) =>
+   Char -> Parser.T input output Maybe Char
+char c = satisfy (c==)
+
+string ::
+   (Monoid output, Stream.C input) =>
+   String -> Parser.T input output Maybe String
+string = allowEmit . mapM char
+
+
+readUntil ::
+   (Monoid output, Stream.C input) =>
+   String -> Parser.T input output Identity (Bool,String)
+readUntil pattern =
+   let recourse =
+          foldr withDefault (return (False,[])) $
+          liftM (const (True,[])) (mapM char pattern) :
+          (do c <- nextChar
+              ~(found,str) <- allowFail recourse
+              return (found,c:str)) :
+          []
+   in  allowEmit recourse
+{-
+runStateT (readUntil "-->") (Position.initialize "input", "<!-- comment --> other stuff")
+-}
+
+
+
+emit :: Monad fail =>
+   w -> Parser.T input [w] fail ()
+emit w = tell [w]
+
+modifyEmission ::
+   (Monad fail, Monoid output) =>
+   (output -> output) -> Parser.T input output fail a -> Parser.T input output fail a
+modifyEmission f = censor f
diff --git a/src/Text/HTML/Tagchup/Parser/Core.hs b/src/Text/HTML/Tagchup/Parser/Core.hs
new file mode 100644
--- /dev/null
+++ b/src/Text/HTML/Tagchup/Parser/Core.hs
@@ -0,0 +1,97 @@
+module Text.HTML.Tagchup.Parser.Core (
+   T,
+   nextChar, withDefault, withDefault',
+   run, gets, tell, censor, mfix,
+   allowFail, allowFail', allowEmit,
+   module Control.Monad.Identity,
+   ) where
+
+
+import qualified Text.HTML.Tagchup.Parser.Status as Status
+import qualified Text.HTML.Tagchup.Parser.Stream as Stream
+import Data.Tuple.HT (mapSnd, )
+
+import qualified Control.Monad.Trans.State as State
+
+import Control.Monad.Trans.Writer (WriterT(..), mapWriterT, tell, censor, )
+import Control.Monad.Trans.State (StateT(..), mapStateT, )
+import Control.Monad.Fix (mfix)
+import Control.Monad.Identity (Identity(..), )
+import Control.Monad.Trans (lift, )
+import Control.Monad (liftM, )
+
+import Data.Monoid (Monoid, mempty, )
+
+
+{-
+We need to declare whether parts of the parser
+can or cannot fail and can or cannot emit something through the writer.
+This way we can get rid of the former functions 'force' and 'ignoreEmit'
+which generate errors at run-time
+if the assumptions of non-failing or non-emission were wrong.
+Now, since we declare this properties in types,
+runtime errors cannot happen.
+
+The downside is that we cannot easily extend that scheme
+to embedded monads that are sources of Chars.
+@StateT s Maybe@ and @MaybeT (State s)@ significantly differ
+in case of parser failures.
+The first one "resets" its state
+(more precisely, you would use 'mplus' to give alternative parsers a try,
+and 'mplus' would keep the original state),
+and the second one stays with the updated state.
+The second one would be close to @MaybeT (ReaderT Handle IO)@
+which would allow to use @hGetChar@ as character source,
+but for IO functions we had to maintain a list of characters
+that might have to be re-parsed by a parser alternative.
+-}
+type T input output fail = WriterT output (StateT (Status.T input) fail)
+
+
+run :: Monad fail =>
+   T input output fail a -> Status.T input -> fail (a, Status.T input, output)
+run p =
+   liftM (\((a,w),st) -> (a,st,w)) . runStateT (runWriterT p)
+
+
+nextChar :: (Monoid output, Stream.C input) =>
+   T input output Maybe Char
+nextChar =
+   lift $ Stream.getChar
+
+
+gets :: (Monoid output, Monad fail) =>
+   (Status.T input -> a) -> T input output fail a
+gets = lift . State.gets
+
+-- this replaces 'ignoreEmit'
+allowEmit ::
+   (Monad fail, Monoid output) =>
+   T input () fail a -> T input output fail a
+allowEmit =
+   mapWriterT (liftM (mapSnd (const mempty)))
+
+allowFail' ::
+   StateT s Identity a -> StateT s Maybe a
+allowFail' =
+   mapStateT (Just . runIdentity)
+
+-- this replaces 'force'
+allowFail :: T input output Identity a -> T input output Maybe a
+allowFail =
+   mapWriterT allowFail'
+
+withDefault' ::
+   StateT s Maybe a ->
+   StateT s Identity a ->
+   StateT s Identity a
+withDefault' p q =
+   StateT $ \st ->
+      maybe (runStateT q st) Identity (runStateT p st)
+
+withDefault ::
+   T input output Maybe a ->
+   T input output Identity a ->
+   T input output Identity a
+withDefault p q =
+   WriterT $ withDefault' (runWriterT p) (runWriterT q)
diff --git a/src/Text/HTML/Tagchup/Parser/Status.hs b/src/Text/HTML/Tagchup/Parser/Status.hs
new file mode 100644
--- /dev/null
+++ b/src/Text/HTML/Tagchup/Parser/Status.hs
@@ -0,0 +1,21 @@
+module Text.HTML.Tagchup.Parser.Status where
+
+import qualified Text.HTML.Tagchup.Parser.Stream as Stream
+import qualified Text.XML.Basic.Position as Position
+
+import Control.Monad.Trans.State (StateT(..), )
+
+
+data T stream =
+   Cons {
+      sourcePos :: Position.T,
+      source    :: stream
+   }
+   deriving Show
+
+
+instance Stream.C input => Stream.C (T input) where
+   getChar =
+      StateT $ \ (Cons pos str) ->
+         do (c,cs) <- runStateT Stream.getChar str
+            return (c, Cons (Position.updateOnChar c pos) cs)
diff --git a/src/Text/HTML/Tagchup/Parser/Stream.hs b/src/Text/HTML/Tagchup/Parser/Stream.hs
new file mode 100644
--- /dev/null
+++ b/src/Text/HTML/Tagchup/Parser/Stream.hs
@@ -0,0 +1,68 @@
+module Text.HTML.Tagchup.Parser.Stream where
+
+import Control.Monad.Trans.State (StateT(StateT), gets, put, )
+import Control.Monad (guard, mzero, )
+import qualified Data.List.HT as L
+
+import qualified Data.ByteString.Char8      as BS
+import qualified Data.ByteString.Lazy.Char8 as BL
+
+import qualified Prelude as P
+import Prelude hiding (Char, getChar, )
+
+
+class C stream where
+   getChar :: StateT stream Maybe P.Char
+
+
+class Char char where
+   toChar :: char -> P.Char
+
+instance Char P.Char where
+   toChar = id
+
+
+instance Char char => C [char] where
+   getChar = fmap toChar $ StateT L.viewL
+
+instance C BS.ByteString where
+   getChar = StateT BS.uncons
+
+instance C BL.ByteString where
+   getChar = StateT BL.uncons
+
+
+data PointerStrict =
+   PointerStrict {psSource :: !BS.ByteString, psIndex :: !Int}
+
+pointerFromByteStringStrict :: BS.ByteString -> PointerStrict
+pointerFromByteStringStrict str =
+   PointerStrict str 0
+
+instance C PointerStrict where
+   getChar =
+      do s <- gets psSource
+         i <- gets psIndex
+         guard (i < BS.length s)
+         put $ PointerStrict s (i+1)
+         return (BS.index s i)
+
+
+
+data PointerLazy =
+   PointerLazy {plSource :: ![BS.ByteString], plIndex :: !Int}
+
+pointerFromByteStringLazy :: BL.ByteString -> PointerLazy
+pointerFromByteStringLazy str =
+   PointerLazy (BL.toChunks str) 0
+
+instance C PointerLazy where
+   getChar =
+      do s <- gets plSource
+         i <- gets plIndex
+         case s of
+            [] -> mzero
+            (c:cs) ->
+               if i < BS.length c
+                 then put (PointerLazy s (i+1)) >> return (BS.index c i)
+                 else put (PointerLazy cs (i - BS.length c)) >> getChar
diff --git a/src/Text/HTML/Tagchup/PositionTag.hs b/src/Text/HTML/Tagchup/PositionTag.hs
new file mode 100644
--- /dev/null
+++ b/src/Text/HTML/Tagchup/PositionTag.hs
@@ -0,0 +1,81 @@
+module Text.HTML.Tagchup.PositionTag where
+
+import qualified Text.HTML.Tagchup.Tag as Tag
+import qualified Text.XML.Basic.Name as Name
+import qualified Text.XML.Basic.Position as Position
+
+import Data.Tuple.HT (mapFst, )
+import Data.Monoid (Monoid, mempty, mappend, )
+
+import qualified Data.Accessor.Basic as Accessor
+
+import Data.Foldable (Foldable(foldMap), )
+import Data.Traversable (Traversable(sequenceA), )
+import Control.Applicative (liftA, )
+
+
+data T name string =
+   Cons {
+      position_ :: Position.T,
+      tag_ :: Tag.T name string
+   }
+
+instance (Name.Attribute name, Show string, Show name) =>
+   Show (T name string) where
+  showsPrec p (Cons pos t) =
+     showParen (p > 10)
+        (showString "PosTag.cons " .
+         showsPrec 11 pos . showString " " .
+         showsPrec 11 t)
+
+{-
+> cons (Position.new "bla" 0 0) (Tag.Close $ Name.fromString "bla" :: Tag.T Text.XML.Basic.Name.LowerCase.T String)
+-}
+cons :: Position.T -> Tag.T name string -> T name string
+cons = Cons
+
+position :: Accessor.T (T name string) Position.T
+position = Accessor.fromSetGet (\n p -> p{position_ = n}) position_
+
+tag :: Accessor.T (T name string) (Tag.T name string)
+tag = Accessor.fromSetGet (\n p -> p{tag_ = n}) tag_
+
+lift ::
+   (Tag.T name0 string0 -> Tag.T name1 string1) ->
+   (T name0 string0 -> T name1 string1)
+lift f (Cons p t) = Cons p (f t)
+
+instance Functor (T name) where
+   fmap f = lift (fmap f)
+
+instance Foldable (T name) where
+   foldMap f = foldMap f . tag_
+
+instance Traversable (T name) where
+   sequenceA (Cons p t) = liftA (Cons p) $ sequenceA t
+
+
+textFromCData ::
+   (Name.Tag name) =>
+   T name String -> T name String
+textFromCData = lift Tag.textFromCData
+
+
+{- |
+Merge adjacent Text sections.
+-}
+concatTexts ::
+   Monoid string =>
+   [T name string] -> [T name string]
+concatTexts =
+   foldr
+      (\t ts ->
+         case t of
+            Cons pos (Tag.Text str0) ->
+               uncurry (:) $
+               mapFst (cons pos . Tag.Text . mappend str0) $
+               case ts of
+                  Cons _ (Tag.Text str1) : rest -> (str1,rest)
+                  _ -> (mempty,ts)
+            _ -> t:ts)
+      []
diff --git a/src/Text/HTML/Tagchup/Process.hs b/src/Text/HTML/Tagchup/Process.hs
new file mode 100644
--- /dev/null
+++ b/src/Text/HTML/Tagchup/Process.hs
@@ -0,0 +1,103 @@
+module Text.HTML.Tagchup.Process where
+
+import qualified Text.HTML.Tagchup.Tag as Tag
+import qualified Text.HTML.Tagchup.Tag.Match as Match
+
+import qualified Text.XML.Basic.Attribute as Attr
+import qualified Text.XML.Basic.Name as Name
+
+import qualified Data.Char as Char
+import           Data.List.HT (viewL, takeWhileRev, )
+import           Data.Tuple.HT (mapFst, )
+import           Data.Maybe (fromMaybe, mapMaybe, )
+import           Control.Monad (guard, liftM2, )
+
+
+-- * analyse soup
+
+{-
+Rather the same as wraxml:HTML.Tree.findMetaEncoding
+-}
+findMetaEncoding ::
+   (Name.Tag name, Name.Attribute name) =>
+   [Tag.T name String] -> Maybe String
+findMetaEncoding =
+   fmap (map Char.toLower . takeWhileRev ('='/=)) .
+   lookup "content-type" .
+   map (mapFst (map Char.toLower)) .
+   getMetaHTTPHeaders
+
+{- |
+Extract META tags which contain HTTP-EQUIV attribute
+and present these values like HTTP headers.
+-}
+getMetaHTTPHeaders ::
+   (Name.Tag name, Name.Attribute name) =>
+   [Tag.T name string] -> [(string, string)]
+getMetaHTTPHeaders =
+   mapMaybe
+      (\tag ->
+         do (name, attrs) <- Tag.maybeOpen tag
+            guard (Name.match "meta" name)
+            liftM2 (,)
+               (Attr.lookupLit "http-equiv" attrs)
+               (Attr.lookupLit "content" attrs)) .
+   getHeadTags
+
+getHeadTags ::
+   (Name.Tag name, Name.Attribute name) =>
+   [Tag.T name string] -> [Tag.T name string]
+getHeadTags =
+   takeWhile (not . Match.closeLit "head") .
+   drop 1 .
+   dropWhile (not . Match.openLit "head" (const True)) .
+   takeWhile (not . Match.openLit "body" (const True))
+
+
+-- * transform soup
+
+{- |
+Modify attributes and tags of certain parts.
+For limitations, see 'parts'.
+-}
+partAttrs ::
+   (Name.Tag name) =>
+   (Tag.Name name -> Bool) ->
+   (([Attr.T name string], [Tag.T name string]) ->
+    ([Attr.T name string], [Tag.T name string])) ->
+   [Tag.T name string] -> [Tag.T name string]
+partAttrs p f =
+   concatMap
+      (either
+          (\((name,attrs),part) ->
+              let (newAttrs, newPart) = f (attrs, part)
+              in  Tag.Open name newAttrs : newPart ++ [Tag.Close name])
+          id) .
+   parts p
+
+{- |
+Extract parts from the tag soup
+that are enclosed in corresponding open and close tags.
+If a close tag is missing, the soup end is considered as end of the part.
+However nested tags are not supported,
+e.g. in @<a><a></a></a>@ the second @<a>@ is considered
+to be enclosed in the first @<a>@ and the first @</a>@
+and the second @</a>@ is ignored.
+-}
+parts ::
+   (Name.Tag name) =>
+   (Tag.Name name -> Bool) ->
+   [Tag.T name string] ->
+   [Either
+       ((Tag.Name name, [Attr.T name string]), [Tag.T name string])
+       [Tag.T name string]]
+parts p =
+   let recourse ts =
+          let (prefix0,suffix0) = break (Match.open p (const True)) ts
+          in  Right prefix0 :
+              fromMaybe []
+                 (do (t, suffix1) <- viewL suffix0
+                     (name, attrs) <- Tag.maybeOpen t
+                     let (part,suffix2) = break (Match.close (name==)) suffix1
+                     return $ Left ((name, attrs), part) : recourse (drop 1 suffix2))
+   in  recourse
diff --git a/src/Text/HTML/Tagchup/Tag.hs b/src/Text/HTML/Tagchup/Tag.hs
new file mode 100644
--- /dev/null
+++ b/src/Text/HTML/Tagchup/Tag.hs
@@ -0,0 +1,336 @@
+module Text.HTML.Tagchup.Tag (
+   T(..), Name(..),
+   mapName,
+
+   open,       isOpen,       maybeOpen,
+   close,      isClose,      maybeClose,
+   text,       isText,       maybeText,   innerText,
+   comment,    isComment,    maybeComment,
+   special,    isSpecial,    maybeSpecial,
+   cdata,      isCData,      maybeCData,
+   processing, isProcessing, maybeProcessing,
+   warning,    isWarning,    maybeWarning,
+
+   formatOpen, formatClose,
+
+   textFromCData, concatTexts,
+   mapText, mapTextA,
+   ) where
+
+import qualified Text.XML.Basic.ProcessingInstruction as PI
+import qualified Text.XML.Basic.Attribute as Attr
+import qualified Text.XML.Basic.Name as Name
+import qualified Text.XML.Basic.Format as Fmt
+import Text.XML.Basic.Tag (Name(Name), cdata, )
+
+import Data.Tuple.HT (mapFst, )
+import Data.Maybe (mapMaybe, fromMaybe, )
+import Data.Monoid (Monoid, mempty, mappend, mconcat, )
+import Control.Monad (guard, )
+
+import Data.Foldable (Foldable(foldMap), )
+import Data.Traversable (Traversable(sequenceA), traverse, )
+import Control.Applicative (Applicative, pure, liftA, )
+
+
+-- * type definitions
+
+{- |
+An HTML element, a document is @[T]@.
+There is no requirement for 'Open' and 'Close' to match.
+
+The type parameter @string@ lets you choose between
+@[Char]@ for interpreted HTML entity references and
+@[HTMLChar.T]@ for uninterpreted HTML entities.
+You will most oftenly want plain @Char@,
+since @HTMLChar.T@ is only necessary if you want to know,
+whether a non-ASCII character was encoded as HTML entity
+or as non-ASCII Unicode character.
+-}
+data T name string =
+     Open (Name name) [Attr.T name string]
+        -- ^ An open tag with 'Attr.T's in their original order.
+   | Close (Name name)
+        -- ^ A closing tag
+   | Text string
+        -- ^ A text node, guaranteed not to be the empty string
+   | Comment String
+        -- ^ A comment
+   | Special (Name name) String
+        -- ^ A tag like @\<!DOCTYPE ...\>@
+   | Processing (Name name) (PI.T name string)
+        -- ^ A tag like @\<?xml ...\>@
+   | Warning String
+        -- ^ Mark a syntax error in the input file
+     deriving (Show, Eq, Ord)
+
+
+instance Functor (T name) where
+   fmap f tag =
+      case tag of
+         Open name attrs      -> Open name $ map (fmap f) attrs
+         Close name           -> Close name
+         Text string          -> Text $ f string
+         Comment string       -> Comment string
+         Special name content -> Special name content
+         Processing name proc -> Processing name $ fmap f proc
+         Warning string       -> Warning string
+
+
+instance Foldable (T name) where
+   foldMap f tag =
+      case tag of
+         Open _name attrs       -> foldMap (foldMap f) attrs
+         Close _name            -> mempty
+         Text string            -> f string
+         Comment _text          -> mempty
+         Special _name _content -> mempty
+         Processing _name proc  -> foldMap f proc
+         Warning _text          -> mempty
+
+
+instance Traversable (T name) where
+   sequenceA tag =
+      case tag of
+         Open name attrs      -> liftA (Open name) $ traverse sequenceA attrs
+         Close name           -> pure $ Close name
+         Text string          -> liftA Text $ string
+         Comment string       -> pure $ Comment string
+         Special name content -> pure $ Special name content
+         Processing name proc -> liftA (Processing name) $ sequenceA proc
+         Warning string       -> pure $ Warning string
+
+
+mapName ::
+   (Name name0 -> Name name1) ->
+   (Attr.Name name0 -> Attr.Name name1) ->
+   T name0 string -> T name1 string
+mapName f g tag =
+   case tag of
+      Open name attrs -> Open (f name) $ map (Attr.mapName g) attrs
+      Close name      -> Close (f name)
+      Text string     -> Text string
+      Comment string  -> Comment string
+      Special name content -> Special (f name) content
+      Processing name proc -> Processing (f name) $ PI.mapName g proc
+      Warning string       -> Warning string
+
+
+
+
+
+instance (Name.Tag name, Name.Attribute name, Fmt.C string) =>
+      Fmt.C (T name string) where
+   run t =
+      case t of
+         Open name attrs -> formatOpen False name attrs
+         Close name -> formatClose name
+         Text str -> Fmt.run str
+         Comment c ->
+            showString "<!--" . showString c . showString "-->"
+         Warning e ->
+            showString "<!-- Warning: " . showString e . showString " -->"
+         Special name str ->
+            Fmt.angle $
+            Fmt.exclam .
+            Fmt.name name .
+            if cdata == name
+              then showString str . showString "]]"
+              else Fmt.blank . showString str
+         Processing name p ->
+            Fmt.angle $
+            Fmt.quest .
+            Fmt.name name .
+            Fmt.run p .
+            Fmt.quest
+
+
+formatOpen :: (Name.Tag name, Name.Attribute name, Fmt.C string) =>
+   Bool -> Name name -> [Attr.T name string] -> ShowS
+formatOpen selfClosing name attrs =
+   Fmt.angle $
+   Fmt.name name .
+   Attr.formatListBlankHead attrs .
+   if selfClosing then Fmt.slash else id
+
+formatClose :: (Name.Tag name) =>
+   Name name -> ShowS
+formatClose name =
+   Fmt.angle $
+   Fmt.slash . Fmt.name name
+
+
+-- * constructors for the tag types
+
+open :: Name name -> [Attr.T name string] -> T name string
+open = Open
+
+close :: Name name -> T name string
+close = Close
+
+text :: string -> T name string
+text = Text
+
+comment :: String -> T name string
+comment = Comment
+
+special :: Name name -> String -> T name string
+special = Special
+
+processing :: Name name -> PI.T name string -> T name string
+processing = Processing
+
+warning :: String -> T name string
+warning = Warning
+
+
+
+-- * check for the tag types
+
+-- | Test if a 'T' is a 'Open'
+isOpen :: T name string -> Bool
+isOpen tag = case tag of (Open {}) -> True; _ -> False
+
+maybeOpen :: T name string -> Maybe (Name name, [Attr.T name string])
+maybeOpen tag = case tag of Open name attrs -> Just (name, attrs); _ -> Nothing
+
+
+-- | Test if a 'T' is a 'Close'
+isClose :: T name string -> Bool
+isClose tag = case tag of (Close {}) -> True; _ -> False
+
+maybeClose :: T name string -> Maybe (Name name)
+maybeClose tag = case tag of Close x -> Just x; _ -> Nothing
+
+
+-- | Test if a 'T' is a 'Text'
+isText :: T name string -> Bool
+isText tag = case tag of (Text {}) -> True; _ -> False
+
+-- | Extract the string from within 'Text', otherwise 'Nothing'
+maybeText :: T name string -> Maybe string
+maybeText tag = case tag of Text x -> Just x; _ -> Nothing
+-- maybeText tag = do Text x <- Just tag; return x
+
+-- | Extract all text content from tags (similar to Verbatim found in HaXml)
+innerText :: (Monoid string) => [T name string] -> string
+innerText = mconcat . mapMaybe maybeText
+
+
+isComment :: T name string -> Bool
+isComment tag = case tag of (Comment {}) -> True; _ -> False
+
+maybeComment :: T name string -> Maybe String
+maybeComment tag = case tag of Comment x -> Just x; _ -> Nothing
+
+
+isSpecial :: T name string -> Bool
+isSpecial tag = case tag of (Special {}) -> True; _ -> False
+
+maybeSpecial :: T name string -> Maybe (Name name, String)
+maybeSpecial tag = case tag of Special name content -> Just (name, content); _ -> Nothing
+
+
+isCData ::
+   (Name.Tag name) =>
+   T name string -> Bool
+isCData tag = case tag of (Special name _) -> cdata == name; _ -> False
+
+maybeCData ::
+   (Name.Tag name) =>
+   T name string -> Maybe String
+maybeCData tag =
+   do (name, content) <- maybeSpecial tag
+      guard (cdata == name)
+      return content
+
+
+isProcessing :: T name string -> Bool
+isProcessing tag = case tag of (Processing {}) -> True; _ -> False
+
+maybeProcessing :: T name string -> Maybe (Name name, PI.T name string)
+maybeProcessing tag = case tag of Processing target instr -> Just (target, instr); _ -> Nothing
+
+
+isWarning :: T name string -> Bool
+isWarning tag = case tag of (Warning {}) -> True; _ -> False
+
+maybeWarning :: T name string -> Maybe String
+maybeWarning tag = case tag of Warning x -> Just x; _ -> Nothing
+-- maybeWarning tag = do Warning x <- Just tag; return x
+
+
+
+-- * tag processing
+
+{- |
+Replace CDATA sections by plain text.
+-}
+textFromCData ::
+   (Name.Tag name) =>
+   T name String -> T name String
+textFromCData t =
+   fromMaybe t $
+      do (name, content) <- maybeSpecial t
+         guard (cdata == name)
+         return $ Text content
+
+{-
+   case t of
+      Special name text ->
+         if cdata == name
+           then Text text
+           else t
+      _ -> t
+-}
+
+{- |
+Merge adjacent Text sections.
+-}
+concatTexts ::
+   Monoid string =>
+   [T name string] -> [T name string]
+concatTexts =
+   foldr
+      (\t ts ->
+         case t of
+            Text str0 ->
+               uncurry (:) $
+               mapFst (Text . mappend str0) $
+               case ts of
+                  Text str1 : rest -> (str1,rest)
+                  _ -> (mempty,ts)
+            _ -> t:ts)
+      []
+
+
+{- |
+Modify content of a Text or a CDATA part.
+-}
+mapText ::
+   (Name.Tag name) =>
+   (String -> String) ->
+   T name String -> T name String
+mapText f t =
+   case t of
+      Text s -> Text $ f s
+      Special name s ->
+         Special name $
+            if cdata == name
+              then f s
+              else s
+      _ -> t
+
+mapTextA ::
+   (Name.Tag name, Applicative f) =>
+   (String -> f String) ->
+   T name String -> f (T name String)
+mapTextA f t =
+   case t of
+      Text s -> liftA Text $ f s
+      Special name s ->
+         liftA (Special name) $
+            if cdata == name
+              then f s
+              else pure s
+      _ -> pure t
diff --git a/src/Text/HTML/Tagchup/Tag/Match.hs b/src/Text/HTML/Tagchup/Tag/Match.hs
new file mode 100644
--- /dev/null
+++ b/src/Text/HTML/Tagchup/Tag/Match.hs
@@ -0,0 +1,89 @@
+module Text.HTML.Tagchup.Tag.Match where
+
+import qualified Text.HTML.Tagchup.Tag as Tag
+import qualified Text.XML.Basic.Attribute as Attr
+import qualified Text.XML.Basic.Name as Name
+
+
+ignore :: a -> Bool
+ignore _ = True
+
+
+-- | match an opening tag
+open :: (Tag.Name name -> Bool) -> ([Attr.T name string] -> Bool) -> Tag.T name string -> Bool
+open pName pAttrs (Tag.Open name attrs) =
+   pName name && pAttrs attrs
+open _ _ _ = False
+
+-- | match an closing tag
+close :: (Tag.Name name -> Bool) -> Tag.T name string -> Bool
+close pName (Tag.Close name) = pName name
+close _ _ = False
+
+-- | match a text
+text :: (string -> Bool) -> Tag.T name string -> Bool
+text p (Tag.Text str) = p str
+text _ _ = False
+
+comment :: (String -> Bool) -> Tag.T name string -> Bool
+comment p (Tag.Comment str) = p str
+comment _ _ = False
+
+special :: (Tag.Name name -> Bool) -> (String -> Bool) -> Tag.T name string -> Bool
+special pType pInfo (Tag.Special typ info) = pType typ && pInfo info
+special _ _ _ = False
+
+
+-- | match a opening tag's name literally
+openLit ::
+   (Name.Tag name) =>
+   String -> ([Attr.T name string] -> Bool) -> Tag.T name string -> Bool
+openLit name = open (Name.match name)
+
+-- | match a closing tag's name literally
+closeLit ::
+   (Name.Tag name) =>
+   String -> Tag.T name string -> Bool
+closeLit name = close (Name.match name)
+
+openAttrLit ::
+   (Name.Attribute name, Name.Tag name, Eq string) =>
+   String -> String -> string -> Tag.T name string -> Bool
+openAttrLit name attrName attrValue =
+   openLit name (Attr.anyLit attrName attrValue)
+
+{- |
+Match a tag with given name, that contains an attribute
+with given name, that satisfies a predicate.
+If an attribute occurs multiple times,
+all occurrences are checked.
+-}
+openAttrNameLit ::
+   (Name.Attribute name, Name.Tag name) =>
+   String -> String -> (string -> Bool) -> Tag.T name string -> Bool
+openAttrNameLit tagName attrName pAttrValue =
+   openLit tagName
+      (Attr.any (\(Attr.Cons name value) ->
+          Name.match attrName name && pAttrValue value))
+
+
+-- | Check if the 'Tag.T' is 'Tag.Open' and matches the given name
+openNameLit ::
+   (Name.Tag name) =>
+   String -> Tag.T name string -> Bool
+openNameLit name = openLit name ignore
+
+-- | Check if the 'Tag.T' is 'Tag.Close' and matches the given name
+closeNameLit ::
+   (Name.Tag name) =>
+   String -> Tag.T name string -> Bool
+closeNameLit name = closeLit name
+
+
+
+{-
+getTagContent :: String -> ([Attr.T name string] -> Bool) -> [Tag.T name string] -> [Tag.T name string]
+getTagContent name pAttrs =
+   takeWhile (not . tagCloseLit name) . drop 1 .
+   head . sections (tagOpenLit name pAttrs)
+-}
diff --git a/src/Text/HTML/Tagchup/Test.hs b/src/Text/HTML/Tagchup/Test.hs
new file mode 100644
--- /dev/null
+++ b/src/Text/HTML/Tagchup/Test.hs
@@ -0,0 +1,76 @@
+module Text.HTML.Tagchup.Test (
+    -- * Tests on laziness
+    laziness, lazyTags, lazyWarnings, restrictedWarnings,
+   ) where
+
+import qualified Text.HTML.Tagchup.Tag    as Tag
+import qualified Text.HTML.Tagchup.Parser as Parser
+import qualified Text.XML.Basic.Name.MixedCase as Name
+import Data.List (isPrefixOf, )
+
+{-
+*Text.HTML.TagSoup.HT> mapM print $ runSoup $ "</html " ++ cycle " abc=a_b&c"
+("anonymous input" (line 1, column 1),TagClose "html")
+("anonymous input" (line 1, column 9),TagWarning "Junk in closing tag: \"abc=a_b&c abc=a_b&c abc=a_b&c abc=a_b&c abc=a_b&c abc=a_b&c abc=a_b&c abc=a_b&c abc=a_b&c abc=a_b&c abc=a_b&c abc=a_b&c abc=a_b&c abc=a
+-}
+
+{- |
+This routine tests the laziness of the TagSoup parser.
+For each critical part of the parser we provide a test input
+with a token of infinite size.
+Then the output must be infinite too.
+If the laziness is broken, then the output will stop early.
+We collect the thousandth character of the output of each test case.
+If computation of the list stops somewhere,
+you have found a laziness stopper.
+-}
+laziness :: [Char]
+laziness = lazyTags ++ lazyWarnings ++ restrictedWarnings
+
+runSoup :: String -> [Tag.T Name.T String]
+runSoup = Parser.runSoup
+
+lazyTags :: [Char]
+lazyTags =
+   map ((!!1000) . show . runSoup) $
+      (cycle "Rhabarber") :
+      (repeat '&') :
+      ('&' : '#' : repeat '1') :
+      ('&' : repeat 'a') :
+      ("<"++cycle "html") :
+      ("<html "++cycle "name") :
+      ("<html "++cycle "na!me=value ") :
+      ("<html name="++cycle "value") :
+      ("<html name=\""++cycle "value") :
+      ("<html name="++cycle "val!ue") :
+      ("<html name="++cycle "val&ue") :
+      ("<html name="++cycle "va&l!ue") :
+      ("</"++cycle "html") :
+      ("</html "++cycle "junk") :
+      ("<!-- "++cycle "comment") :
+      ("<!"++cycle "doctype") :
+      ("<![CDATA["++cycle "content&am<") :
+      ("<!DOCTYPE"++cycle " description") :
+      ("<?xml "++cycle "name") :
+      ("<?custom "++cycle "name") :
+      (cycle "1<2 ") :
+      []
+
+lazyWarnings :: [Char]
+lazyWarnings =
+   map ((!!1000) . show . tail . runSoup) $
+      (repeat '&') :
+      ("<html "++cycle "na!me=value ") :
+      ("</html "++cycle "junk") :
+      (cycle "1<2 ") :
+      []
+
+restrictedWarnings :: [Char]
+restrictedWarnings =
+   map (last . show . head .
+        dropWhile (not . maybe False (isPrefixOf "further") . Tag.maybeWarning) .
+        runSoup) $
+      ("<html name="++cycle "val!ue") :
+      ("<html name="++cycle "val&ue") :
+      ("<html name="++cycle "va&l!ue") :
+      []
diff --git a/tagchup.cabal b/tagchup.cabal
new file mode 100644
--- /dev/null
+++ b/tagchup.cabal
@@ -0,0 +1,66 @@
+Name:           tagchup
+Version:        0.3.1
+License:        GPL
+License-File:   LICENSE
+Author:         Henning Thielemann <tagchup@henning-thielemann.de>
+Maintainer:     Henning Thielemann <tagchup@henning-thielemann.de>
+Homepage:       http://code.haskell.org/~thielema/tagchup/
+Category:       XML
+Synopsis:       alternative package for processing of tag soups
+Description:
+   Tagchup is a package for processing XML, HTML, XHTML documents
+   that can also be malformed.
+   It allows parsing, formatting and retrieval of such document.
+   All functions should be as lazy as possible.
+   .
+   I use a custom data structure based on types from xml-basic
+   for easy interchange with the wraxml package.
+   .
+   Its lazy monadic parser should be more comprehensible and easier to extend
+   than the one of tagsoup-0.6.
+   It also handles XML processing instructions and CDATA sections correctly.
+   .
+   The name Tagchup resembles Ketchup.
+Build-Type:  Simple
+Build-Depends:
+   xml-basic >=0.1 && <0.2,
+   transformers >=0.0 && <0.2,
+   explicit-exception >=0.1 && <0.2,
+   bytestring >=0.9.0.1 && <0.10,
+   containers >=0.1 && <0.3,
+   data-accessor >=0.2 && <0.3,
+   utility-ht >=0.0.1 && <0.1,
+   base >=3 && <4
+GHC-Options: -Wall
+Hs-Source-Dirs: src
+Exposed-Modules:
+   Text.HTML.Tagchup.Parser
+   Text.HTML.Tagchup.Format
+   Text.HTML.Tagchup.Tag
+   Text.HTML.Tagchup.Tag.Match
+   Text.HTML.Tagchup.PositionTag
+   Text.HTML.Tagchup.Process
+
+Other-Modules:
+   Text.HTML.Tagchup.Parser.Combinator
+   Text.HTML.Tagchup.Parser.Core
+   Text.HTML.Tagchup.Parser.Status
+   Text.HTML.Tagchup.Parser.Stream
+
+Executable: tagchuptest
+GHC-Options: -Wall
+Hs-Source-Dirs: src, .
+Other-Modules:
+   Text.HTML.Tagchup.Test
+Main-Is:     example/Test.hs
+
+Executable: tagchupspeed
+GHC-Options: -Wall
+Hs-Source-Dirs: src, .
+Build-Depends: old-time >=1.0 && <1.1
+Main-Is:     example/Speed.hs
+
+Executable: validate-tagchup
+GHC-Options: -Wall
+Hs-Source-Dirs: src, .
+Main-Is:     example/Validate.hs
