Bump version

utf8_encoder() was incorrectly dereferencing the pointer `state' before testing
it against null; fix by removing the variable initialisers.

.gitignore

@@ -1,2 +1,3 @@
 obj
 html
+.*.swp

COPYING

@@ -1,278 +1,674 @@
                     GNU GENERAL PUBLIC LICENSE
-                       Version 2, June 1991
+                       Version 3, 29 June 2007
 
- Copyright (C) 1989, 1991 Free Software Foundation, Inc.
+ Copyright (C) 2007 Free Software Foundation, Inc. <http://fsf.org/>
-                       59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  Everyone is permitted to copy and distribute verbatim copies
  of this license document, but changing it is not allowed.
 
                             Preamble
 
-  The licenses for most software are designed to take away your
+  The GNU General Public License is a free, copyleft license for
-freedom to share and change it.  By contrast, the GNU General Public
+software and other kinds of works.
-License is intended to guarantee your freedom to share and change free
+
-software--to make sure the software is free for all its users.  This
+  The licenses for most software and other practical works are designed
-General Public License applies to most of the Free Software
+to take away your freedom to share and change the works.  By contrast,
-Foundation's software and to any other program whose authors commit to
+the GNU General Public License is intended to guarantee your freedom to
-using it.  (Some other Free Software Foundation software is covered by
+share and change all versions of a program--to make sure it remains free
-the GNU Library General Public License instead.)  You can apply it to
+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
-this service if you wish), that you receive source code or can get it
+them if you wish), that you receive source code or can get it if you
-if you want it, that you can change the software or use pieces of it
+want it, that you can change the software or use pieces of it in new
-in new free programs; and that you know you can do these things.
+free programs, and that you know you can do these things.
 
-  To protect your rights, we need to make restrictions that forbid
+  To protect your rights, we need to prevent others from denying you
-anyone to deny you these rights or to ask you to surrender the rights.
+these rights or asking you to surrender the rights.  Therefore, you have
-These restrictions translate to certain responsibilities for you if you
+certain responsibilities if you distribute copies of the software, or if
-distribute copies of the software, or if you modify it.
+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 give the recipients all the rights that
+gratis or for a fee, you must pass on to the recipients the same
-you have.  You must make sure that they, too, receive or can get the
+freedoms that you received.  You must make sure that they, too, receive
-source code.  And you must show them these terms so they know their
+or can get the source code.  And you must show them these terms so they
-rights.
+know their rights.
 
-  We protect your rights with two steps: (1) copyright the software, and
+  Developers that use the GNU GPL protect your rights with two steps:
-(2) offer you this license which gives you legal permission to copy,
+(1) assert copyright on the software, and (2) offer you this License
-distribute and/or modify the software.
+giving you legal permission to copy, distribute and/or modify it.
 
-  Also, for each author's protection and ours, we want to make certain
+  For the developers' and authors' protection, the GPL clearly explains
-that everyone understands that there is no warranty for this free
+that there is no warranty for this free software.  For both users' and
-software.  If the software is modified by someone else and passed on, we
+authors' sake, the GPL requires that modified versions be marked as
-want its recipients to know that what they have is not the original, so
+changed, so that their problems will not be attributed erroneously to
-that any problems introduced by others will not reflect on the original
+authors of previous versions.
-authors' reputations.
 
-  Finally, any free program is threatened constantly by software
+  Some devices are designed to deny users access to install or run
-patents.  We wish to avoid the danger that redistributors of a free
+modified versions of the software inside them, although the manufacturer
-program will individually obtain patent licenses, in effect making the
+can do so.  This is fundamentally incompatible with the aim of
-program proprietary.  To prevent this, we have made it clear that any
+protecting users' freedom to change the software.  The systematic
-patent must be licensed for everyone's free use or not licensed at all.
+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.
-
-                    GNU GENERAL PUBLIC LICENSE
-   TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION
 
-  0. This License applies to any program or other work which contains
+                       TERMS AND CONDITIONS
-a notice placed by the copyright holder saying it may be distributed
-under the terms of this General Public License.  The "Program", below,
-refers to any such program or work, and a "work based on the Program"
-means either the Program or any derivative work under copyright law:
-that is to say, a work containing the Program or a portion of it,
-either verbatim or with modifications and/or translated into another
-language.  (Hereinafter, translation is included without limitation in
-the term "modification".)  Each licensee is addressed as "you".
 
-Activities other than copying, distribution and modification are not
+  0. Definitions.
-covered by this License; they are outside its scope.  The act of
-running the Program is not restricted, and the output from the Program
-is covered only if its contents constitute a work based on the
-Program (independent of having been made by running the Program).
-Whether that is true depends on what the Program does.
 
-  1. You may copy and distribute verbatim copies of the Program's
+  "This License" refers to version 3 of the GNU General Public License.
-source code as you receive it, in any medium, provided that you
-conspicuously and appropriately publish on each copy an appropriate
-copyright notice and disclaimer of warranty; keep intact all the
-notices that refer to this License and to the absence of any warranty;
-and give any other recipients of the Program a copy of this License
-along with the Program.
 
-You may charge a fee for the physical act of transferring a copy, and
+  "Copyright" also means copyright-like laws that apply to other kinds of
-you may at your option offer warranty protection in exchange for a fee.
+works, such as semiconductor masks.
 
-  2. You may modify your copy or copies of the Program or any portion
+  "The Program" refers to any copyrightable work licensed under this
-of it, thus forming a work based on the Program, and copy and
+License.  Each licensee is addressed as "you".  "Licensees" and
-distribute such modifications or work under the terms of Section 1
+"recipients" may be individuals or organizations.
-above, provided that you also meet all of these conditions:
 
-    a) You must cause the modified files to carry prominent notices
+  To "modify" a work means to copy from or adapt all or part of the work
-    stating that you changed the files and the date of any change.
+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.
 
-    b) You must cause any work that you distribute or publish, that in
+  A "covered work" means either the unmodified Program or a work based
-    whole or in part contains or is derived from the Program or any
+on the Program.
-    part thereof, to be licensed as a whole at no charge to all third
-    parties under the terms of this License.
 
-    c) If the modified program normally reads commands interactively
+  To "propagate" a work means to do anything with it that, without
-    when run, you must cause it, when started running for such
+permission, would make you directly or secondarily liable for
-    interactive use in the most ordinary way, to print or display an
+infringement under applicable copyright law, except executing it on a
-    announcement including an appropriate copyright notice and a
+computer or modifying a private copy.  Propagation includes copying,
-    notice that there is no warranty (or else, saying that you provide
+distribution (with or without modification), making available to the
-    a warranty) and that users may redistribute the program under
+public, and in some countries other activities as well.
-    these conditions, and telling the user how to view a copy of this
-    License.  (Exception: if the Program itself is interactive but
-    does not normally print such an announcement, your work based on
-    the Program is not required to print an announcement.)
-
-These requirements apply to the modified work as a whole.  If
-identifiable sections of that work are not derived from the Program,
-and can be reasonably considered independent and separate works in
-themselves, then this License, and its terms, do not apply to those
-sections when you distribute them as separate works.  But when you
-distribute the same sections as part of a whole which is a work based
-on the Program, the distribution of the whole must be on the terms of
-this License, whose permissions for other licensees extend to the
-entire whole, and thus to each and every part regardless of who wrote it.
 
-Thus, it is not the intent of this section to claim rights or contest
+  To "convey" a work means any kind of propagation that enables other
-your rights to work written entirely by you; rather, the intent is to
+parties to make or receive copies.  Mere interaction with a user through
-exercise the right to control the distribution of derivative or
+a computer network, with no transfer of a copy, is not conveying.
-collective works based on the Program.
 
-In addition, mere aggregation of another work not based on the Program
+  An interactive user interface displays "Appropriate Legal Notices"
-with the Program (or with a work based on the Program) on a volume of
+to the extent that it includes a convenient and prominently visible
-a storage or distribution medium does not bring the other work under
+feature that (1) displays an appropriate copyright notice, and (2)
-the scope of this License.
+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.
 
-  3. You may copy and distribute the Program (or a work based on it,
+  1. Source Code.
-under Section 2) in object code or executable form under the terms of
-Sections 1 and 2 above provided that you also do one of the following:
 
-    a) Accompany it with the complete corresponding machine-readable
+  The "source code" for a work means the preferred form of the work
-    source code, which must be distributed under the terms of Sections
+for making modifications to it.  "Object code" means any non-source
-    1 and 2 above on a medium customarily used for software interchange; or,
+form of a work.
 
-    b) Accompany it with a written offer, valid for at least three
+  A "Standard Interface" means an interface that either is an official
-    years, to give any third party, for a charge no more than your
+standard defined by a recognized standards body, or, in the case of
-    cost of physically performing source distribution, a complete
+interfaces specified for a particular programming language, one that
-    machine-readable copy of the corresponding source code, to be
+is widely used among developers working in that language.
-    distributed under the terms of Sections 1 and 2 above on a medium
-    customarily used for software interchange; or,
 
-    c) Accompany it with the information you received as to the offer
+  The "System Libraries" of an executable work include anything, other
-    to distribute corresponding source code.  (This alternative is
+than the work as a whole, that (a) is included in the normal form of
-    allowed only for noncommercial distribution and only if you
+packaging a Major Component, but which is not part of that Major
-    received the program in object code or executable form with such
+Component, and (b) serves only to enable use of the work with that
-    an offer, in accord with Subsection b above.)
+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 source code for a work means the preferred form of the work for
+  The "Corresponding Source" for a work in object code form means all
-making modifications to it.  For an executable work, complete source
+the source code needed to generate, install, and (for an executable
-code means all the source code for all modules it contains, plus any
+work) run the object code and to modify the work, including scripts to
-associated interface definition files, plus the scripts used to
+control those activities.  However, it does not include the work's
-control compilation and installation of the executable.  However, as a
+System Libraries, or general-purpose tools or generally available free
-special exception, the source code distributed need not include
+programs which are used unmodified in performing those activities but
-anything that is normally distributed (in either source or binary
+which are not part of the work.  For example, Corresponding Source
-form) with the major components (compiler, kernel, and so on) of the
+includes interface definition files associated with source files for
-operating system on which the executable runs, unless that component
+the work, and the source code for shared libraries and dynamically
-itself accompanies the executable.
+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.
 
-If distribution of executable or object code is made by offering
+  The Corresponding Source need not include anything that users
-access to copy from a designated place, then offering equivalent
+can regenerate automatically from other parts of the Corresponding
-access to copy the source code from the same place counts as
+Source.
-distribution of the source code, even though third parties are not
-compelled to copy the source along with the object code.
-
-  4. You may not copy, modify, sublicense, or distribute the Program
-except as expressly provided under this License.  Any attempt
-otherwise to copy, modify, sublicense or distribute the Program is
-void, and will automatically terminate your rights under this License.
-However, parties who have received copies, or rights, from you under
-this License will not have their licenses terminated so long as such
-parties remain in full compliance.
 
-  5. You are not required to accept this License, since you have not
+  The Corresponding Source for a work in source code form is that
-signed it.  However, nothing else grants you permission to modify or
+same work.
-distribute the Program or its derivative works.  These actions are
-prohibited by law if you do not accept this License.  Therefore, by
-modifying or distributing the Program (or any work based on the
-Program), you indicate your acceptance of this License to do so, and
-all its terms and conditions for copying, distributing or modifying
-the Program or works based on it.
 
-  6. Each time you redistribute the Program (or any work based on the
+  2. Basic Permissions.
-Program), the recipient automatically receives a license from the
+
-original licensor to copy, distribute or modify the Program subject to
+  All rights granted under this License are granted for the term of
-these terms and conditions.  You may not impose any further
+copyright on the Program, and are irrevocable provided the stated
-restrictions on the recipients' exercise of the rights granted herein.
+conditions are met.  This License explicitly affirms your unlimited
-You are not responsible for enforcing compliance by third parties to
+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.
 
-  7. If, as a consequence of a court judgment or allegation of patent
+  Each contributor grants you a non-exclusive, worldwide, royalty-free
-infringement or for any other reason (not limited to patent issues),
+patent license under the contributor's essential patent claims, to
-conditions are imposed on you (whether by court order, agreement or
+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
+excuse you from the conditions of this License.  If you cannot convey a
-distribute so as to satisfy simultaneously your obligations under this
+covered work so as to satisfy simultaneously your obligations under this
-License and any other pertinent obligations, then as a consequence you
+License and any other pertinent obligations, then as a consequence you may
-may not distribute the Program at all.  For example, if a patent
+not convey it at all.  For example, if you agree to terms that obligate you
-license would not permit royalty-free redistribution of the Program by
+to collect a royalty for further conveying from those to whom you convey
-all those who receive copies directly or indirectly through you, then
+the Program, the only way you could satisfy both those terms and this
-the only way you could satisfy both it and this License would be to
+License would be to refrain entirely from conveying the Program.
-refrain entirely from distribution of the Program.
 
-If any portion of this section is held invalid or unenforceable under
+  13. Use with the GNU Affero General Public License.
-any particular circumstance, the balance of the section is intended to
-apply and the section as a whole is intended to apply in other
-circumstances.
 
-It is not the purpose of this section to induce you to infringe any
+  Notwithstanding any other provision of this License, you have
-patents or other property right claims or to contest validity of any
+permission to link or combine any covered work with a work licensed
-such claims; this section has the sole purpose of protecting the
+under version 3 of the GNU Affero General Public License into a single
-integrity of the free software distribution system, which is
+combined work, and to convey the resulting work.  The terms of this
-implemented by public license practices.  Many people have made
+License will continue to apply to the part which is the covered work,
-generous contributions to the wide range of software distributed
+but the special requirements of the GNU Affero General Public License,
-through that system in reliance on consistent application of that
+section 13, concerning interaction through a network will apply to the
-system; it is up to the author/donor to decide if he or she is willing
+combination as such.
-to distribute software through any other system and a licensee cannot
-impose that choice.
 
-This section is intended to make thoroughly clear what is believed to
+  14. Revised Versions of this License.
-be a consequence of the rest of this License.
-
-  8. If the distribution and/or use of the Program is restricted in
-certain countries either by patents or by copyrighted interfaces, the
-original copyright holder who places the Program under this License
-may add an explicit geographical distribution limitation excluding
-those countries, so that distribution is permitted only in or among
-countries not thus excluded.  In such case, this License incorporates
-the limitation as if written in the body of this License.
 
-  9. The Free Software Foundation may publish revised and/or new versions
+  The Free Software Foundation may publish revised and/or new versions of
-of the General Public License from time to time.  Such new versions will
+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
+  Each version is given a distinguishing version number.  If the
-specifies a version number of this License which applies to it and "any
+Program specifies that a certain numbered version of the GNU General
-later version", you have the option of following the terms and conditions
+Public License "or any later version" applies to it, you have the
-either of that version or of any later version published by the Free
+option of following the terms and conditions either of that numbered
-Software Foundation.  If the Program does not specify a version number of
+version or of any later version published by the Free Software
-this License, you may choose any version ever published by the Free Software
+Foundation.  If the Program does not specify a version number of the
-Foundation.
+GNU General Public License, you may choose any version ever published
+by the Free Software Foundation.
 
-  10. If you wish to incorporate parts of the Program into other free
+  If the Program specifies that a proxy can decide which future
-programs whose distribution conditions are different, write to the author
+versions of the GNU General Public License can be used, that proxy's
-to ask for permission.  For software which is copyrighted by the Free
+public statement of acceptance of a version permanently authorizes you
-Software Foundation, write to the Free Software Foundation; we sometimes
+to choose that version for the Program.
-make exceptions for this.  Our decision will be guided by the two goals
-of preserving the free status of all derivatives of our free software and
-of promoting the sharing and reuse of software generally.
 
-                            NO WARRANTY
+  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.
 
-  11. BECAUSE THE PROGRAM IS LICENSED FREE OF CHARGE, THERE IS NO WARRANTY
+  15. Disclaimer of 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.
 
-  12. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
+  THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY
-WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY AND/OR
+APPLICABLE LAW.  EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT
-REDISTRIBUTE THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES,
+HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY
-INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING
+OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO,
-OUT OF THE USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED
+THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
-TO LOSS OF DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY
+PURPOSE.  THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM
-YOU OR THIRD PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER
+IS WITH YOU.  SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF
-PROGRAMS), EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE
+ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
-POSSIBILITY OF SUCH DAMAGES.
+
+  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>.

README

@@ -1,7 +1,7 @@
 libutf8
 ========================================================================
-(c)2006, Laurence Withers, <l@lwithers.me.uk>.
+(c)2006-2009, Laurence Withers, <l@lwithers.me.uk>.
-Released under the GNU GPLv2. See file COPYING or 
+Released under the GNU GPLv3. See file COPYING or 
 http://www.gnu.org/copyleft/gpl.html for details.
 
 Really Quick Instructions
@@ -12,6 +12,10 @@ To install: ./make.sh install
     (you might want to set PREFIX, by default it's /usr/local)
 Documentation is automatically built using doxygen.
 
+You might want to edit 'config' first. You might also want to set
+'INSTALL_PREFIX', which is prepended onto the destination of any
+installed file.
+
 Project Homepage
 ----------------
 

config

@@ -0,0 +1,36 @@
+# libutf8/config
+# kate: replace-trailing-space-save true; space-indent true; tab-width 4;
+# vim: syntax=sh:expandtab:ts=4:sw=4
+#
+#  (c)2009, Laurence Withers, <l@lwithers.me.uk>.
+#  Released under the GNU GPLv3. See file COPYING or
+#  http://www.gnu.org/copyleft/gpl.html for details.
+#
+# This file contains options used to build libutf8.
+
+
+# PREFIX is the most important option. Many other paths are derived from it, as follows:
+#
+#   PREFIX      | /                 | /usr              | /usr/local        | /opt/*
+#   ------------+-------------------+-------------------+-------------------+-----------------
+#   BINDIR      | /bin              | /usr/bin          | /usr/local/bin    | /opt/*/bin
+#   SBINDIR     | /sbin             | /usr/sbin         | /usr/local/sbin   | /opt/*/sbin
+#   LIBDIR      | /lib              | /usr/lib          | /usr/local/lib    | /opt/*/lib
+#   INCLUDEDIR  | /usr/include      | /usr/include      | /usr/local/include| /opt/*/include
+#   CONFIGDIR   | /etc              | /etc              | /usr/local/etc    | /etc/opt/*
+#   VARDIR      | /var              | /var              | /var              | /var/opt/*
+#   SHAREDIR    | /usr/share        | /usr/share        | /usr/local/share  | /opt/*/share
+#   DOCSDIR     | /usr/share/doc    | /usr/share/doc    | /usr/local/share/doc, /opt/*/doc
+#   WEBDIR      | /srv/http         | /srv/http         | /srv/http         | /opt/*/http
+#
+# Specific notes:
+#   When installing, all paths are prepended with INSTALL_PREFIX.
+#   Any parameter can be overridden by setting an environment variable.
+#   CGIDIR is set to ${WEBDIR}/cgi-bin .
+#
+[ -z "${PREFIX}" ] && PREFIX="/usr/local"
+source "scripts/paths"
+
+# Project-specific variables below.
+[ -z "${CC}" ] && CC="gcc"
+[ -z "${CFLAGS}" ] && CFLAGS="-g -O2 -W -Wall"

libutf8.kdevelop

@@ -1,168 +0,0 @@
-<?xml version = '1.0'?>
-<kdevelop>
-  <general>
-    <author>Laurence Withers</author>
-    <email>l@lwithers.me.uk</email>
-    <version>$VERSION$</version>
-    <projectmanagement>KDevCustomProject</projectmanagement>
-    <primarylanguage>C++</primarylanguage>
-    <ignoreparts/>
-    <projectdirectory>.</projectdirectory>
-    <absoluteprojectpath>false</absoluteprojectpath>
-    <description/>
-    <versioncontrol/>
-  </general>
-  <kdevcustomproject>
-    <run>
-      <mainprogram>/bin/true</mainprogram>
-      <directoryradio>executable</directoryradio>
-      <customdirectory>/</customdirectory>
-      <programargs/>
-      <terminal>false</terminal>
-      <autocompile>true</autocompile>
-      <envvars/>
-    </run>
-    <build>
-      <buildtool>make</buildtool>
-      <builddir/>
-    </build>
-    <make>
-      <abortonerror>false</abortonerror>
-      <numberofjobs>1</numberofjobs>
-      <prio>0</prio>
-      <dontact>false</dontact>
-      <makebin>./make.sh</makebin>
-      <defaulttarget>default</defaulttarget>
-      <makeoptions/>
-      <selectedenvironment>default</selectedenvironment>
-      <environments>
-        <default/>
-      </environments>
-    </make>
-    <general>
-      <activedir/>
-    </general>
-  </kdevcustomproject>
-  <kdevdebugger>
-    <general>
-      <dbgshell/>
-      <programargs/>
-      <gdbpath/>
-      <configGdbScript/>
-      <runShellScript/>
-      <runGdbScript/>
-      <breakonloadinglibs>true</breakonloadinglibs>
-      <separatetty>false</separatetty>
-      <floatingtoolbar>false</floatingtoolbar>
-    </general>
-    <display>
-      <staticmembers>false</staticmembers>
-      <demanglenames>true</demanglenames>
-      <outputradix>10</outputradix>
-    </display>
-  </kdevdebugger>
-  <kdevdoctreeview>
-    <ignoretocs>
-      <toc>ada</toc>
-      <toc>ada_bugs_gcc</toc>
-      <toc>bash</toc>
-      <toc>bash_bugs</toc>
-      <toc>clanlib</toc>
-      <toc>fortran_bugs_gcc</toc>
-      <toc>gnome1</toc>
-      <toc>gnustep</toc>
-      <toc>gtk</toc>
-      <toc>gtk_bugs</toc>
-      <toc>haskell</toc>
-      <toc>haskell_bugs_ghc</toc>
-      <toc>java_bugs_gcc</toc>
-      <toc>java_bugs_sun</toc>
-      <toc>kde2book</toc>
-      <toc>opengl</toc>
-      <toc>pascal_bugs_fp</toc>
-      <toc>php</toc>
-      <toc>php_bugs</toc>
-      <toc>perl</toc>
-      <toc>perl_bugs</toc>
-      <toc>python</toc>
-      <toc>python_bugs</toc>
-      <toc>qt-kdev3</toc>
-      <toc>ruby</toc>
-      <toc>ruby_bugs</toc>
-      <toc>sdl</toc>
-      <toc>sw</toc>
-      <toc>w3c-dom-level2-html</toc>
-      <toc>w3c-svg</toc>
-      <toc>w3c-uaag10</toc>
-      <toc>wxwidgets_bugs</toc>
-    </ignoretocs>
-    <ignoreqt_xml>
-      <toc>Guide to the Qt Translation Tools</toc>
-      <toc>Qt Assistant Manual</toc>
-      <toc>Qt Designer Manual</toc>
-      <toc>Qt Reference Documentation</toc>
-      <toc>qmake User Guide</toc>
-    </ignoreqt_xml>
-    <ignoredoxygen>
-      <toc>KDE Libraries (Doxygen)</toc>
-    </ignoredoxygen>
-  </kdevdoctreeview>
-  <kdevfilecreate>
-    <filetypes/>
-    <useglobaltypes>
-      <type ext="cpp" />
-      <type ext="h" />
-    </useglobaltypes>
-  </kdevfilecreate>
-  <cppsupportpart>
-    <filetemplates>
-      <interfacesuffix>.h</interfacesuffix>
-      <implementationsuffix>.cpp</implementationsuffix>
-    </filetemplates>
-  </cppsupportpart>
-  <kdevcppsupport>
-    <codecompletion>
-      <includeGlobalFunctions>true</includeGlobalFunctions>
-      <includeTypes>true</includeTypes>
-      <includeEnums>true</includeEnums>
-      <includeTypedefs>false</includeTypedefs>
-      <automaticCodeCompletion>true</automaticCodeCompletion>
-      <automaticArgumentsHint>true</automaticArgumentsHint>
-      <automaticHeaderCompletion>true</automaticHeaderCompletion>
-      <codeCompletionDelay>1</codeCompletionDelay>
-      <argumentsHintDelay>1</argumentsHintDelay>
-      <headerCompletionDelay>250</headerCompletionDelay>
-    </codecompletion>
-    <creategettersetter>
-      <prefixGet/>
-      <prefixSet>set</prefixSet>
-      <prefixVariable>m_,_</prefixVariable>
-      <parameterName>theValue</parameterName>
-      <inlineGet>true</inlineGet>
-      <inlineSet>true</inlineSet>
-    </creategettersetter>
-    <references/>
-  </kdevcppsupport>
-  <kdevdocumentation>
-    <projectdoc>
-      <docsystem/>
-      <docurl/>
-      <usermanualurl/>
-    </projectdoc>
-  </kdevdocumentation>
-  <kdevfileview>
-    <groups>
-      <hidenonprojectfiles>false</hidenonprojectfiles>
-      <hidenonlocation>false</hidenonlocation>
-    </groups>
-    <tree>
-      <hidepatterns>*.o,*.lo,CVS</hidepatterns>
-      <hidenonprojectfiles>false</hidenonprojectfiles>
-      <showvcsfields>false</showvcsfields>
-    </tree>
-  </kdevfileview>
-  <ctagspart>
-    <customArguments/>
-    <customTagfilePath/>
-  </ctagspart>
-</kdevelop>

libutf8.kdevelop.filelist

@@ -1,4 +0,0 @@
-# KDevelop Custom Project File List
-src/lib/BottomHeader.h
-src/lib/TopHeader.h
-src/lib/TopSource.cpp

make.sh

@@ -1,48 +1,33 @@
 #!/bin/bash
 # libutf8/make.sh
 #
-#  (c)2006, Laurence Withers, <l@lwithers.me.uk>.
+#  (c)2006-2009, Laurence Withers, <l@lwithers.me.uk>.
-#  Released under the GNU GPLv2. See file COPYING or
+#  Released under the GNU GPLv3. See file COPYING or
 #  http://www.gnu.org/copyleft/gpl.html for details.
 #
 
 
 # This file is the script used to build libutf8. There are some
-# options that can be edited; these are set below (or you can pass them
+# options that can be edited; these are set in the file 'config' (or you
-# in as variables).
+# can pass them in as environment variables).
-[ -z "${CC}" ] && CC="gcc"
+if [ ! -e "config" ]
-[ -z "${CXX}" ] && CXX="g++"
+then
-[ -z "${CFLAGS}" ] && CFLAGS="-g -O2 -W -Wall"
+    echo "Configuration file not found???"
-[ -z "${PREFIX}" ] && PREFIX="/usr/local"
+    exit 1
-[ -z "${LIBDIR}" ] && LIBDIR="${PREFIX}/lib"
+fi
-[ -z "${BINDIR}" ] && BINDIR="${PREFIX}/bin"
+source "./config" # don't fail on error, since last command in config might return false
-[ -z "${INCLUDEDIR}" ] && INCLUDEDIR="${PREFIX}/include"
-[ -z "${DOCSDIR}" ] && DOCSDIR="${PREFIX}/share/doc/libutf8"
-
-# for pkg-config
-[ -z "${PKGCONFDIR}" ] && PKGCONFDIR="${LIBDIR}/pkgconfig"
-[ -z "${FINALLIBDIR}" ] && FINALLIBDIR="${LIBDIR}"
-[ -z "${FINALINCLUDEDIR}" ] && FINALINCLUDEDIR="${INCLUDEDIR}"
-
-# for SDCC-built firmware
-[ -z "${HEXDIR}" ] && HEXDIR="${PREFIX}/share/firmware"
-[ -z "${SDCC}" ] && SDCC="sdcc"
 
 
 
 # Get version information
-source version || exit 1
+source "./version" || exit 1
 VERSION="${VERMAJOR}.${VERMINOR}.${VERMICRO}"
-if [ ! -z "${VEREXTRA}" ]
-then
-    VERSION="${VERSION}-${VEREXTRA}"
-fi
 
 
 
 # Get standard functions
 [ -z "${VERBOSE}" ] && VERBOSE="0"
-source scripts/functions.sh || exit 1
+source "./scripts/functions.sh" || exit 1
 
 
 # List of directories which will be emptied by clean.
@@ -59,6 +44,8 @@ OUTPUT_DIRS="obj html"
 #  MONOLITHIC_TESTS       if any file mentioned in this list is newer
 #                         than the output file, then we recreate it
 #  MONOLITHIC_SOURCE      a list (in order) of the source files
+#  MONOLITHIC_OPTIONS     will #define the options to match the respective
+#                         environment variables.
 #
 # Recognised formats are:
 #  none                   no special processing happens before each file
@@ -79,13 +66,16 @@ make_monolithic() {
     # extract options
     HASHLINE=0
     VERDEFINE=0
+    HASHDEFINE=0
     if [ "$2" == "C" ]
     then
         HASHLINE=1
         VERDEFINE=1
+        HASHDEFINE=1
     elif [ "$2" == "Ch" ]
     then
         HASHLINE=1
+        HASHDEFINE=1
     elif [ "$2" == "none" ]
     then
         HASHLINE=0 # dummy command
@@ -126,6 +116,14 @@ make_monolithic() {
             do_cmd_redir ${MONOLITHIC_OUT} echo "#define VEREXTRA \"${VEREXTRA}\"" || return 1
         fi
 
+        if [ ${HASHDEFINE} -ne 0 ]
+        then
+            for opt in ${MONOLITHIC_OPTIONS}
+            do
+                do_cmd_redir ${MONOLITHIC_OUT} echo "#define ${opt} ${!opt}" || return 1
+            done
+        fi
+
         for FILE in ${MONOLITHIC_SOURCE}
         do
             if [ ${HASHLINE} -ne 0 ]
@@ -153,6 +151,10 @@ build_dir_tree() {
         return 1
     fi
 
+    build_dir_tree_recurse "${INSTALL_PREFIX}$1"
+}
+
+build_dir_tree_recurse() {
     local DIR="$1"
 
     # if the directory already exists, return success
@@ -171,8 +173,9 @@ build_dir_tree() {
     mkdir "${DIR}" >& /dev/null
     if [ $? -ne 0 ]
     then
-        build_dir_tree $(dirname "${DIR}") || return 1
+        build_dir_tree_recurse $(dirname "${DIR}") || return 1
-        mkdir "${DIR}"
+	echo " Creating directory '${DIR}'"
+        do_cmd mkdir "${DIR}"
         if [ $? -ne 0 ]
         then
             print_failure "Failed to create directory '${DIR}'"
@@ -191,10 +194,10 @@ build_dir_tree() {
 # second is the destination. The third is the octal mode.
 install_file() {
     # figure out if $2 is a directory or not
-    DEST_FILE="$2"
+    DEST_FILE="${INSTALL_PREFIX}$2"
-    [ -d "$2" ] && DEST_FILE="$2/$(basename $1)"
+    [ -d "${DEST_FILE}" ] && DEST_FILE="${INSTALL_PREFIX}$2/$(basename $1)"
 
-    echo " Installing: '$1' -> '$2'"
+    echo " Installing: '$1' -> '${DEST_FILE}'"
     do_cmd cp -fP "$1" "${DEST_FILE}" || return 1
     do_cmd chmod "$3" "${DEST_FILE}" || return 1
 
@@ -206,10 +209,10 @@ install_file() {
 # This will install a header file. It is basically similar to 
 # install_file(), only we strip out the #line directives.
 install_header() {
-    DEST_FILE="$2"
+    DEST_FILE="${INSTALL_PREFIX}$2"
-    [ -d "$2" ] && DEST_FILE="$2/$(basename $1)"
+    [ -d "${DEST_FILE}" ] && DEST_FILE="${INSTALL_PREFIX}$2/$(basename $1)"
 
-    echo " Installing header: '$1' -> '$2'"
+    echo " Installing: '$1' -> '${DEST_FILE}'"
     do_cmd rm -f ${DEST_FILE} || exit 1
     do_cmd_redir ${DEST_FILE} sed -e "s,^#line.*,," $1 || exit 1
     do_cmd chmod "$3" "${DEST_FILE}" || return 1
@@ -223,9 +226,9 @@ install_header() {
 # second the symlink's source filename, and the third is the directory
 # in which to create the symlink.
 install_symlink() {
-    echo " Installing symlink: '$3/$2' -> '$1'"
+    echo " Installing symlink: '${INSTALL_PREFIX}$3/$1' -> '$2'"
 
-    ( do_cmd cd $3; ln -sf $2 $1 ) || return 1
+    ( do_cmd ln -sf $2 ${INSTALL_PREFIX}$3/$1 ) || return 1
 
     return 0
 }
@@ -272,6 +275,7 @@ do
         echo "Cleaning..."
         rm -rf ${OUTPUT_DIRS}
         print_success "Done"
+        true
     ;;
 
     # bad Kdevelop! bad!

run-test.sh

@@ -1,8 +1,8 @@
 #!/bin/bash
 # libutf8/test.sh
 #
-#  (c)2006, Laurence Withers, <l@lwithers.me.uk>.
+#  (c)2006-2009, Laurence Withers, <l@lwithers.me.uk>.
-#  Released under the GNU GPLv2. See file COPYING or
+#  Released under the GNU GPLv3. See file COPYING or
 #  http://www.gnu.org/copyleft/gpl.html for details.
 #
 
@@ -21,7 +21,7 @@ run_test() {
         return 1
     fi
 
-    LD_LIBRARY_PATH="obj" ${EXE} "$@" || return 1
+    LD_LIBRARY_PATH="obj" "${EXE}" "$@" || return 1
     return 0
 }
 
@@ -33,10 +33,10 @@ print_tests() {
     echo "---------------------------------------------------------------------"
     for EXE in obj/tests/*
     do
-        [ -x ${EXE} ] || continue
+        [ -x "${EXE}" ] || continue
-        NAME=$(echo ${EXE} | sed 's,obj/tests/,,')
+        NAME="$(echo "${EXE}" | sed 's,obj/tests/,,')"
         echo -ne "${NAME}\t"
-        LD_LIBRARY_PATH="obj" ${EXE} --print-summary
+        LD_LIBRARY_PATH="obj" "${EXE}" --print-summary
     done
 }
 

scripts/.gitignore

@@ -1,12 +1,20 @@
-build.c++.app
+build.app.c
-build.c++.lib
+build.app.c++
-build.c++.qtapp
+build.app.c++-qt
-build.c++.tests
+build.app.sh
-build.c.app
+build.docs.doxygen
-build.c.lib
+build.docs.none
-build.c.tests
+build.files.none
-build.doxygen.docs
+build.firmware.gpasm
-build.none.files
+build.firmware.sdcc
-build.sdcc.firmware
+build.lib.c
+build.lib.c++
+build.make.none
+build.module.c
+build.tests.c
+build.tests.c++
+
+config-printflags.sh
 module-create.sh
 release.sh
+version.sh

scripts/functions.sh

@@ -1,8 +1,7 @@
-#!/bin/bash
 # libutf8/scripts/functions.sh
 #
-#  (c)2006, Laurence Withers, <l@lwithers.me.uk>.
+#  (c)2006-2009, Laurence Withers, <l@lwithers.me.uk>.
-#  Released under the GNU GPLv2. See file COPYING or
+#  Released under the GNU GPLv3. See file COPYING or
 #  http://www.gnu.org/copyleft/gpl.html for details.
 #
 

scripts/paths

@@ -0,0 +1,64 @@
+# libutf8/scripts/paths
+#
+#  (c)2009, Laurence Withers, <l@lwithers.me.uk>.
+#  Released under the GNU GPLv3. See file COPYING or
+#  http://www.gnu.org/copyleft/gpl.html for details.
+#
+#  Default path setup. Not meant for editing; use environment variables 
+#  to override values if needed.
+#
+
+MY_PREFIX="${PREFIX}"
+[ "${MY_PREFIX}" == "/" ] && MY_PREFIX=""
+
+[ -z "${BINDIR}" ] && BINDIR="${PREFIX}/bin"
+[ -z "${SBINDIR}" ] && SBINDIR="${PREFIX}/sbin"
+[ -z "${LIBDIR}" ] && LIBDIR="${PREFIX}/lib"
+
+if [ -z "${INCLUDEDIR}" ]
+then
+    case "${PREFIX}" in
+    /) INCLUDEDIR="/usr/include" ;;
+    *) INCLUDEDIR="${PREFIX}/include" ;;
+    esac
+fi
+
+if [ -z "${CONFIGDIR}" ]
+then
+    case "${PREFIX}" in
+    / | /usr) CONFIGDIR="/etc" ;;
+    /opt*) CONFIGDIR="/etc${PREFIX}" ;;
+    *) CONFIGDIR="${PREFIX}/etc" ;;
+    esac
+fi
+
+if [ -z "${VARDIR}" ]
+then
+    case "${PREFIX}" in
+    / | /usr | /usr/local) VARDIR="/var" ;;
+    /opt*) VARDIR="/var${PREFIX}" ;;
+    *) VARDIR="${PREFIX}/var" ;;
+    esac
+fi
+
+if [ -z "${SHAREDIR}" ]
+then
+    case "${PREFIX}" in
+    /) SHAREDIR="/usr/share" ;;
+    *) SHAREDIR="${PREFIX}/share" ;;
+    esac
+fi
+[ -z "${DOCSDIR}" ] && DOCSDIR="${SHAREDIR}/doc"
+
+if [ -z "${SRVDIR}" ]
+then
+    case "${PREFIX}" in
+    / | /usr | /usr/local) SRVDIR="/srv" ;;
+    *) SRVDIR="${PREFIX}/srv" ;;
+    esac
+fi
+[ -z "${WEBDIR}" ] && WEBDIR="${SRVDIR}/http"
+[ -z "${CGIDIR}" ] && CGIDIR="${WEBDIR}/cgi-bin"
+ 
+# kate: replace-trailing-space-save true; space-indent true; tab-width 4;
+# vim: syntax=sh:expandtab:ts=4:sw=4

src/docs/.params

@@ -1 +1 @@
-doxygen docs docs
+docs doxygen docs

src/docs/Doxyfile.in

@@ -1,15 +1,15 @@
 # libutf8/src/docs/Doxyfile.in
 #
-#  (c)2006, Laurence Withers, <l@lwithers.me.uk>.
+#  (c)2006-2009, Laurence Withers, <l@lwithers.me.uk>.
-#  Released under the GNU GPLv2. See file COPYING or
+#  Released under the GNU GPLv3. See file COPYING or
 #  http://www.gnu.org/copyleft/gpl.html for details.
 #
 
+DOXYFILE_ENCODING      = UTF-8
 PROJECT_NAME           = libutf8
 OUTPUT_DIRECTORY       = 
 CREATE_SUBDIRS         = NO
 OUTPUT_LANGUAGE        = English
-USE_WINDOWS_ENCODING   = NO
 BRIEF_MEMBER_DESC      = YES
 REPEAT_BRIEF           = YES
 ABBREVIATE_BRIEF       = 
@@ -20,20 +20,30 @@ STRIP_FROM_PATH        =
 STRIP_FROM_INC_PATH    = 
 SHORT_NAMES            = NO
 JAVADOC_AUTOBRIEF      = NO
+QT_AUTOBRIEF           = NO
 MULTILINE_CPP_IS_BRIEF = YES
-DETAILS_AT_TOP         = YES
 INHERIT_DOCS           = YES
-DISTRIBUTE_GROUP_DOC   = NO
+SEPARATE_MEMBER_PAGES  = NO
 TAB_SIZE               = 4
 ALIASES                = 
-OPTIMIZE_OUTPUT_FOR_C  = NO
+OPTIMIZE_OUTPUT_FOR_C  = YES
 OPTIMIZE_OUTPUT_JAVA   = NO
+OPTIMIZE_FOR_FORTRAN   = NO
+OPTIMIZE_OUTPUT_VHDL   = NO
+BUILTIN_STL_SUPPORT    = NO
+CPP_CLI_SUPPORT        = NO
+SIP_SUPPORT            = NO
+IDL_PROPERTY_SUPPORT   = NO
+DISTRIBUTE_GROUP_DOC   = NO
 SUBGROUPING            = YES
+TYPEDEF_HIDES_STRUCT   = NO
+SYMBOL_CACHE_SIZE      = 0
 EXTRACT_ALL            = NO
 EXTRACT_PRIVATE        = NO
 EXTRACT_STATIC         = NO
 EXTRACT_LOCAL_CLASSES  = NO
 EXTRACT_LOCAL_METHODS  = NO
+EXTRACT_ANON_NSPACES   = NO
 HIDE_UNDOC_MEMBERS     = NO
 HIDE_UNDOC_CLASSES     = NO
 HIDE_FRIEND_COMPOUNDS  = YES
@@ -43,8 +53,9 @@ CASE_SENSE_NAMES       = YES
 HIDE_SCOPE_NAMES       = NO
 SHOW_INCLUDE_FILES     = NO
 INLINE_INFO            = YES
-SORT_MEMBER_DOCS       = YES
+SORT_MEMBER_DOCS       = NO
 SORT_BRIEF_DOCS        = NO
+SORT_GROUP_NAMES       = NO
 SORT_BY_SCOPE_NAME     = NO
 GENERATE_TODOLIST      = YES
 GENERATE_TESTLIST      = YES
@@ -54,7 +65,10 @@ ENABLED_SECTIONS       =
 MAX_INITIALIZER_LINES  = 30
 SHOW_USED_FILES        = NO
 SHOW_DIRECTORIES       = NO
+SHOW_FILES             = NO
+SHOW_NAMESPACES        = YES
 FILE_VERSION_FILTER    = 
+LAYOUT_FILE            = 
 QUIET                  = YES
 WARNINGS               = YES
 WARN_IF_UNDOCUMENTED   = YES
@@ -62,11 +76,14 @@ WARN_IF_DOC_ERROR      = YES
 WARN_NO_PARAMDOC       = YES
 WARN_FORMAT            = "$file:$line: $text"
 WARN_LOGFILE           = 
+INPUT                  = 
+INPUT_ENCODING         = UTF-8
 FILE_PATTERNS          = 
 RECURSIVE              = NO
 EXCLUDE                = 
 EXCLUDE_SYMLINKS       = NO
 EXCLUDE_PATTERNS       = 
+EXCLUDE_SYMBOLS        = 
 EXAMPLE_PATH           = 
 EXAMPLE_PATTERNS       = 
 EXAMPLE_RECURSIVE      = NO
@@ -79,6 +96,8 @@ INLINE_SOURCES         = NO
 STRIP_CODE_COMMENTS    = YES
 REFERENCED_BY_RELATION = YES
 REFERENCES_RELATION    = YES
+REFERENCES_LINK_SOURCE = YES
+USE_HTAGS              = NO
 VERBATIM_HEADERS       = NO
 ALPHABETICAL_INDEX     = YES
 COLS_IN_ALPHA_INDEX    = 5
@@ -90,29 +109,67 @@ HTML_HEADER            =
 HTML_FOOTER            = 
 HTML_STYLESHEET        = 
 HTML_ALIGN_MEMBERS     = YES
+HTML_DYNAMIC_SECTIONS  = YES
+GENERATE_DOCSET        = NO
+DOCSET_FEEDNAME        = "Doxygen generated docs"
+DOCSET_BUNDLE_ID       = org.doxygen.Project
 GENERATE_HTMLHELP      = NO
 CHM_FILE               = 
 HHC_LOCATION           = 
 GENERATE_CHI           = NO
+CHM_INDEX_ENCODING     = 
 BINARY_TOC             = NO
 TOC_EXPAND             = NO
+GENERATE_QHP           = NO
+QCH_FILE               = 
+QHP_NAMESPACE          = org.doxygen.Project
+QHP_VIRTUAL_FOLDER     = doc
+QHG_LOCATION           = 
 DISABLE_INDEX          = NO
 ENUM_VALUES_PER_LINE   = 4
 GENERATE_TREEVIEW      = NO
 TREEVIEW_WIDTH         = 250
+FORMULA_FONTSIZE       = 10
 GENERATE_LATEX         = NO
+LATEX_OUTPUT           = latex
+LATEX_CMD_NAME         = latex
+MAKEINDEX_CMD_NAME     = makeindex
+COMPACT_LATEX          = NO
+PAPER_TYPE             = a4wide
+EXTRA_PACKAGES         = 
+LATEX_HEADER           = 
+PDF_HYPERLINKS         = NO
+USE_PDFLATEX           = NO
+LATEX_BATCHMODE        = NO
+LATEX_HIDE_INDICES     = NO
 GENERATE_RTF           = NO
+RTF_OUTPUT             = rtf
+COMPACT_RTF            = NO
+RTF_HYPERLINKS         = NO
+RTF_STYLESHEET_FILE    = 
+RTF_EXTENSIONS_FILE    = 
 GENERATE_MAN           = NO
+MAN_OUTPUT             = man
+MAN_EXTENSION          = .3
+MAN_LINKS              = NO
 GENERATE_XML           = NO
+XML_OUTPUT             = xml
+XML_SCHEMA             = 
+XML_DTD                = 
+XML_PROGRAMLISTING     = YES
 GENERATE_AUTOGEN_DEF   = NO
 GENERATE_PERLMOD       = NO
+PERLMOD_LATEX          = NO
+PERLMOD_PRETTY         = YES
+PERLMOD_MAKEVAR_PREFIX = 
 ENABLE_PREPROCESSING   = YES
-MACRO_EXPANSION        = NO
+MACRO_EXPANSION        = YES
-EXPAND_ONLY_PREDEF     = NO
+EXPAND_ONLY_PREDEF     = YES
 SEARCH_INCLUDES        = YES
 INCLUDE_PATH           = 
 INCLUDE_FILE_PATTERNS  = 
-PREDEFINED             = DOXYGEN
+PREDEFINED             = DOXYGEN \
+                         __attribute__()=
 EXPAND_AS_DEFINED      = 
 SKIP_FUNCTION_MACROS   = YES
 TAGFILES               = 
@@ -121,8 +178,12 @@ ALLEXTERNALS           = NO
 EXTERNAL_GROUPS        = YES
 PERL_PATH              = /usr/bin/perl
 CLASS_DIAGRAMS         = YES
+MSCGEN_PATH            = 
 HIDE_UNDOC_RELATIONS   = YES
 HAVE_DOT               = YES
+DOT_FONTNAME           = FreeSans
+DOT_FONTSIZE           = 10
+DOT_FONTPATH           = 
 CLASS_GRAPH            = YES
 COLLABORATION_GRAPH    = YES
 GROUP_GRAPHS           = NO
@@ -131,13 +192,13 @@ TEMPLATE_RELATIONS     = NO
 INCLUDE_GRAPH          = NO
 INCLUDED_BY_GRAPH      = NO
 CALL_GRAPH             = NO
+CALLER_GRAPH           = NO
 GRAPHICAL_HIERARCHY    = YES
 DIRECTORY_GRAPH        = NO
 DOT_IMAGE_FORMAT       = png
 DOT_PATH               = 
 DOTFILE_DIRS           = 
-MAX_DOT_GRAPH_WIDTH    = 1024
+DOT_GRAPH_MAX_NODES    = 50
-MAX_DOT_GRAPH_HEIGHT   = 1024
 MAX_DOT_GRAPH_DEPTH    = 0
 DOT_TRANSPARENT        = YES
 DOT_MULTI_TARGETS      = YES

src/docs/MainPage.dox

@@ -1,7 +1,7 @@
 /* libutf8/src/docs/MainPage.dox
  *
- *  (c)2006, Laurence Withers, <l@lwithers.me.uk>.
+ *  (c)2006-2009, Laurence Withers, <l@lwithers.me.uk>.
- *  Released under the GNU GPLv2. See file COPYING or
+ *  Released under the GNU GPLv3. See file COPYING or
  *  http://www.gnu.org/copyleft/gpl.html for details.
 */
 
@@ -10,10 +10,9 @@
 \c libutf8 provides a C API for encoding and decoding UTF-8. It uses the C type \c wchar_t as its
 internal character representation. \c libutf8 is a "safe" decoder &mdash; it will not accept
 overlong byte sequences.
-
 */
 
 /* options for text editors
 kate: replace-trailing-space-save true; space-indent true; tab-width 4;
-vim: expandtab:ts=4:sw=4
+vim: expandtab:ts=4:sw=4:syntax=doxygen
 */

src/docs/build.docs

@@ -40,4 +40,4 @@ then
 fi
 
 # kate: replace-trailing-space-save true; space-indent true; tab-width 4;
-# vim: expandtab:ts=4:sw=4
+# vim: syntax=sh:expandtab:ts=4:sw=4

src/docs/build.install-docs

@@ -18,4 +18,4 @@ done
 
 print_success "Documentation installed"
 # kate: replace-trailing-space-save true; space-indent true; tab-width 4;
-# vim: expandtab:ts=4:sw=4
+# vim: syntax=sh:expandtab:ts=4:sw=4

src/docs/char_class_eol.dox

@@ -0,0 +1,28 @@
+/* libutf8/src/docs/MainPage.dox
+ *
+ *  (c)2006-2009, Laurence Withers, <l@lwithers.me.uk>.
+ *  Released under the GNU GPLv3. See file COPYING or
+ *  http://www.gnu.org/copyleft/gpl.html for details.
+*/
+
+/*! \page char_class_eol Character classification: end of line
+
+From <a href='http://unicode.org/reports/tr13/tr13-9.html'>Unicode Standard
+Annex #13 (Unicode newline guidelines)</a>:
+
+<ul>
+ <li>LF (000A)</li>
+ <li>VT (000B)</li>
+ <li>FF (000C)</li>
+ <li>CR (000D)</li>
+ <li>NEL (0085)</li>
+ <li>LS (2028)</li>
+ <li>PS (2029)</li>
+</ul>
+
+*/
+
+/* options for text editors
+kate: replace-trailing-space-save true; space-indent true; tab-width 4;
+vim: expandtab:ts=4:sw=4:syntax=doxygen
+*/

src/docs/char_class_whitespace.dox

@@ -0,0 +1,30 @@
+/* libutf8/src/docs/MainPage.dox
+ *
+ *  (c)2006-2009, Laurence Withers, <l@lwithers.me.uk>.
+ *  Released under the GNU GPLv3. See file COPYING or
+ *  http://www.gnu.org/copyleft/gpl.html for details.
+*/
+
+/*! \page char_class_whitespace Character classification: whitespace
+
+From <a href='http://www.unicode.org/Public/UNIDATA/'>PropList-4.1.0.txt</a>:
+
+<pre>0009..000D    ; White_Space # Cc   [5] <control-0009>..<control-000D>
+0020          ; White_Space # Zs       SPACE
+0085          ; White_Space # Cc       <control-0085>
+00A0          ; White_Space # Zs       NO-BREAK SPACE
+1680          ; White_Space # Zs       OGHAM SPACE MARK
+180E          ; White_Space # Zs       MONGOLIAN VOWEL SEPARATOR
+2000..200A    ; White_Space # Zs  [11] EN QUAD..HAIR SPACE
+2028          ; White_Space # Zl       LINE SEPARATOR
+2029          ; White_Space # Zp       PARAGRAPH SEPARATOR
+202F          ; White_Space # Zs       NARROW NO-BREAK SPACE
+205F          ; White_Space # Zs       MEDIUM MATHEMATICAL SPACE
+3000          ; White_Space # Zs       IDEOGRAPHIC SPACE</pre>
+
+*/
+
+/* options for text editors
+kate: replace-trailing-space-save true; space-indent true; tab-width 4;
+vim: expandtab:ts=4:sw=4:syntax=doxygen
+*/

src/libutf8/.params

@@ -1 +1 @@
-c lib libutf8 utf8.h
+lib c libutf8 utf8.h

src/libutf8/000_TopHeader.h

@@ -0,0 +1,21 @@
+/* libutf8/src/libutf8/000_TopHeader.h
+ *
+ *  (c)2006-2009, Laurence Withers, <l@lwithers.me.uk>.
+ *  Released under the GNU GPLv3. See file COPYING or
+ *  http://www.gnu.org/copyleft/gpl.html for details.
+*/
+
+#ifndef HEADER_LIBUTF8
+#define HEADER_LIBUTF8
+
+/* standard includes, or includes needed for type declarations */
+#include <wchar.h>
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+/* options for text editors
+kate: replace-trailing-space-save true; space-indent true; tab-width 4;
+vim: expandtab:ts=4:sw=4:syntax=c.doxygen
+*/

src/libutf8/000_TopSource.c

@@ -0,0 +1,19 @@
+/* libutf8/src/libutf8/000_TopSource.cpp
+ *
+ *  (c)2006-2009, Laurence Withers, <l@lwithers.me.uk>.
+ *  Released under the GNU GPLv3. See file COPYING or
+ *  http://www.gnu.org/copyleft/gpl.html for details.
+*/
+
+#include "utf8.h"
+
+// Below are all the includes used throughout the library.
+
+#include <errno.h>
+#include <stdint.h>
+#include <string.h>
+
+/* options for text editors
+kate: replace-trailing-space-save true; space-indent true; tab-width 4;
+vim: expandtab:ts=4:sw=4:syntax=c.doxygen
+*/

src/libutf8/100_ctype.c

@@ -0,0 +1,80 @@
+/* libutf8/src/libutf8/100_ctype.c
+ *
+ *  (c)2006-2009, Laurence Withers, <l@lwithers.me.uk>.
+ *  Released under the GNU GPLv3. See file COPYING or
+ *  http://www.gnu.org/copyleft/gpl.html for details.
+*/
+
+
+
+int
+utf8_isascii(wchar_t ch)
+{
+    return !(ch & ~0x7F);
+}
+
+
+
+int
+utf8_isspace(wchar_t ch)
+{
+    return((ch >= 0x0009 && ch <= 0x000D)
+            || ch == 0x0020
+            || ch == 0x0085
+            || ch == 0x00A0
+            || ch == 0x1680
+            || ch == 0x180E
+            || (ch >= 0x2000 && ch <= 0x200A)
+            || ch == 0x2028
+            || ch == 0x2029
+            || ch == 0x202F
+            || ch == 0x205F
+            || ch == 0x3000);
+}
+
+
+
+int
+utf8_iseol(wchar_t ch)
+{
+    return (ch >= 0x000A && ch <= 0x000D)
+        || ch == 0x0085
+        || ch == 0x2028
+        || ch == 0x2029;
+}
+
+
+
+int
+utf8_isucs4(wchar_t ch)
+{
+    return !(ch & (~((wchar_t)0x7FFFFFFF)))
+        && (ch < 0xD800 || ch > 0xDFFF)
+        && (ch != 0xFFFE) && (ch != 0xFFFF);
+}
+
+
+
+int
+utf8_isutf32(wchar_t ch)
+{
+    return ch >= 0 && ch <= 0x10FFFF
+        && (ch < 0xD800 || ch > 0xDFFF)
+        && (ch != 0xFFFE) && (ch != 0xFFFF);
+}
+
+
+
+int
+utf8_isutf16(wchar_t ch)
+{
+    return ch >= 0 && ch <= 0xFFFD
+        && (ch < 0xD800 || ch > 0xDFFF);
+}
+
+
+
+/* options for text editors
+kate: replace-trailing-space-save true; space-indent true; tab-width 4;
+vim: expandtab:ts=4:sw=4:syntax=c.doxygen
+*/

src/libutf8/100_ctype.h

@@ -0,0 +1,123 @@
+/* libutf8/src/libutf8/100_ctype.h
+ *
+ *  (c)2006-2009, Laurence Withers, <l@lwithers.me.uk>.
+ *  Released under the GNU GPLv3. See file COPYING or
+ *  http://www.gnu.org/copyleft/gpl.html for details.
+*/
+
+
+
+/*! \defgroup ctype Character classification
+
+This module contains functions for character classification. These are
+semantically equivalent to the \c is* functions defined in \c &lt;ctype.h&gt;,
+except that they work on \c wchar_t UCS chars and are independent of the
+system's current locale setting.
+
+\todo There are many char classification functions that haven't been
+      implemented yet. These will be added on demand.
+
+*/
+/*!@{*/
+
+
+
+/*! \brief Test if character is ASCII.
+
+\param ch Character to test.
+\retval nonzero if \a ch is ASCII.
+\retval 0 if \a ch is not ASCII.
+
+This function tests a UCS char to see if it lies within the range of characters
+that can be represented by ASCII (i.e. that the value of \a ch lies between 0
+and 127, inclusive).
+
+*/
+int utf8_isascii(wchar_t ch);
+
+
+
+/*! \brief Test if character is whitespace.
+
+\param ch Character to test.
+\retval nonzero if \a ch is whitespace.
+\retval 0 if \a ch is not whitespace.
+
+This function tests a UCS char to see if it should be classified as 
+\ref char_class_whitespace "whitespace".
+
+*/
+int utf8_isspace(wchar_t ch);
+
+
+
+/*! \brief Test if character is end-of-line.
+
+\param ch Character to test.
+\retval nonzero if \a ch is an EOL character.
+\retval 0 if \a ch is not an EOL character.
+
+This function tests a UCS char to see if it should be classified as 
+\ref char_class_eol "end-of-line". Note that both ASCII LR and CF are treated
+as EOL; it is up to the application to disambiguate the line ending in use.
+
+*/
+int utf8_iseol(wchar_t ch);
+
+
+
+/*! \brief Test if character is valid UCS-4 codepoint.
+
+\param ch The character to classify.
+\retval nonzero If \a ch is a valid UCS-4 character.
+\retval 0 If \a ch is not a valid UCS-4 character.
+
+This function will examine a \c wchar_t value and determine whether or not it
+is a valid UCS-4 character. Valid characters lie in the range
+0&ndash;0x7FFFFFFF but exclude:
+\li the UTF-16 surrogate code points (U+D800&ndash;U+DFFF, inclusive)
+\li the invalid code points U+FFFE and U+FFFF
+
+*/
+int utf8_isucs4(wchar_t ch);
+
+
+
+/*! \brief Test if character is valid UTF-32 (Unicode) codepoint.
+
+\param ch The character to classify.
+\retval nonzero If \a ch is a valid Unicode character.
+\retval 0 If \a ch is not a valid Unicode character.
+
+This function will examine a \c wchar_t value and determine whether or not it
+is a valid Unicode character. Valid characters lie in the range
+0&ndash;0x10FFFF but exclude:
+\li the UTF-16 surrogate code points (U+D800&ndash;U+DFFF, inclusive)
+\li the invalid code points U+FFFE and U+FFFF
+
+*/
+int utf8_isutf32(wchar_t ch);
+
+
+
+/*! \brief Test if character is valid UTF-16 (Unicode) codepoint.
+
+\param ch The character to classify.
+\retval nonzero If \a ch is a valid Unicode character.
+\retval 0 If \a ch is not a valid Unicode character.
+
+This function will examine a \c wchar_t value and determine whether or not it
+is a valid Unicode character that can be represented by a single UTF-16
+codepoint. Valid characters lie in the range 0&ndash;0xFFFD but exclude:
+\li the UTF-16 surrogate code points (U+D800&ndash;U+DFFF, inclusive)
+
+*/
+int utf8_isutf16(wchar_t ch);
+
+
+
+/*!@}*/
+/* options for text editors
+kate: replace-trailing-space-save true; space-indent true; tab-width 4;
+vim: expandtab:ts=4:sw=4:syntax=c.doxygen
+*/

src/libutf8/200_decode.c

@@ -1,17 +1,22 @@
-/* libutf8/src/lib/decode.c
+/* libutf8/src/libutf8/200_decode.c
  *
- *  (c)2006, Laurence Withers. Released under the GNU GPL. See file
+ *  (c)2006-2009, Laurence Withers, <l@lwithers.me.uk>.
- *  COPYING for more information / terms of license.
+ *  Released under the GNU GPLv3. See file COPYING or
+ *  http://www.gnu.org/copyleft/gpl.html for details.
 */
 
-wchar_t utf8_decode_char(const char* src, size_t* used)
+
+
+wchar_t
+utf8_decode_char(const char* src, size_t* used)
 {
     return utf8_decode_char2(src, 6, used);
 }
 
 
 
-wchar_t utf8_decode_char2(const char* src, size_t size, size_t* used)
+wchar_t
+utf8_decode_char2(const char* src, size_t size, size_t* used)
 {
     uint8_t ch;
     wchar_t ret, min;
@@ -19,7 +24,7 @@ wchar_t utf8_decode_char2(const char* src, size_t size, size_t* used)
 
     if(!src || !size) {
         errno = EINVAL;
-        return 0;
+        return (wchar_t)-1;
     }
     if(used) *used = 1;
     ch = *src++;
@@ -52,26 +57,26 @@ wchar_t utf8_decode_char2(const char* src, size_t size, size_t* used)
             ret = ch & 0x01;
         } else {
             errno = EILSEQ;
-            return 0;
+            return (wchar_t)-1;
         }
 
         while(remain--) {
             if(!--size) {
                 errno = EILSEQ;
-                return 0;
+                return (wchar_t)-1;
             }
             ch = *src++;
             if((ch & 0xC0) != 0x80) {
                 errno = EILSEQ;
-                return 0;
+                return (wchar_t)-1;
             }
             ret <<= 6;
             ret |= ch & 0x3F;
         }
 
-        if(ch < min) {
+        if(ret < min) {
             errno = EILSEQ;
-            return 0;
+            return (wchar_t)-1;
         }
 
         return ret;
@@ -81,14 +86,17 @@ wchar_t utf8_decode_char2(const char* src, size_t size, size_t* used)
 
 
 
-wchar_t utf8_decode_char_force(const char* src, size_t* used, wchar_t ilseq)
+wchar_t
+utf8_decode_char_force(const char* src, size_t* used, wchar_t ilseq)
 {
     return utf8_decode_char2_force(src, 6, used, ilseq);
 }
 
 
 
-wchar_t utf8_decode_char2_force(const char* src, size_t size, size_t* used, wchar_t ilseq)
+wchar_t
+utf8_decode_char2_force(const char* src, size_t size, size_t* used,
+    wchar_t ilseq)
 {
     uint8_t ch;
     wchar_t ret, min;
@@ -96,7 +104,7 @@ wchar_t utf8_decode_char2_force(const char* src, size_t size, size_t* used, wcha
 
     if(!src || !size) {
         errno = EINVAL;
-        return 0;
+        return (wchar_t)-1;
     }
     if(used) *used = 1;
     ch = *src++;
@@ -135,14 +143,14 @@ wchar_t utf8_decode_char2_force(const char* src, size_t size, size_t* used, wcha
             ret |= ch & 0x3F;
         }
 
-        if(ch < min) goto ILSEQ;
+        if(ret < min) goto ILSEQ;
 
         return ret;
     }
     return ch;
 
   ILSEQ:
-    // advance pointer to next valid char boundary
+    /* advance pointer to next valid char boundary */
     while(1) {
         if(!*src || !size) break;
         if((*src & 0xC0) == 0x80) break;
@@ -156,7 +164,8 @@ ILSEQ:
 
 
 
-wchar_t* utf8_decode(wchar_t* dest, size_t size, const char* src)
+wchar_t*
+utf8_decode(wchar_t* dest, size_t size, const char* src)
 {
     struct utf8_decode_state ctx;
     memset(&ctx, 0, sizeof(ctx));
@@ -176,7 +185,9 @@ wchar_t* utf8_decode(wchar_t* dest, size_t size, const char* src)
 
 
 
-wchar_t* utf8_decode2(wchar_t* dest, size_t size, size_t* written, const char* src, size_t amt)
+wchar_t*
+utf8_decode2(wchar_t* dest, size_t size, size_t* written, const char* src,
+    size_t amt)
 {
     struct utf8_decode_state ctx;
     memset(&ctx, 0, sizeof(ctx));
@@ -197,7 +208,8 @@ wchar_t* utf8_decode2(wchar_t* dest, size_t size, size_t* written, const char* s
 
 
 
-wchar_t* utf8_decode_force(wchar_t* dest, size_t size, const char* src)
+wchar_t*
+utf8_decode_force(wchar_t* dest, size_t size, const char* src)
 {
     struct utf8_decode_state ctx;
     memset(&ctx, 0, sizeof(ctx));
@@ -218,7 +230,9 @@ wchar_t* utf8_decode_force(wchar_t* dest, size_t size, const char* src)
 
 
 
-wchar_t* utf8_decode_force2(wchar_t* dest, size_t size, size_t* written, const char* src, size_t amt)
+wchar_t*
+utf8_decode_force2(wchar_t* dest, size_t size, size_t* written, const char* src,
+    size_t amt)
 {
     struct utf8_decode_state ctx;
     memset(&ctx, 0, sizeof(ctx));
@@ -232,3 +246,10 @@ wchar_t* utf8_decode_force2(wchar_t* dest, size_t size, size_t* written, const c
     if(written) *written = ctx.written;
     return dest;
 }
+
+
+
+/* options for text editors
+kate: replace-trailing-space-save true; space-indent true; tab-width 4;
+vim: expandtab:ts=4:sw=4:syntax=c.doxygen
+*/

src/libutf8/200_decode.h

@@ -1,10 +1,13 @@
-/* libutf8/src/lib/decode.h
+/* libutf8/src/libutf8/200_decode.h
  *
- *  (c)2006, Laurence Withers. Released under the GNU GPL. See file
+ *  (c)2006-2009, Laurence Withers, <l@lwithers.me.uk>.
- *  COPYING for more information / terms of license.
+ *  Released under the GNU GPLv3. See file COPYING or
+ *  http://www.gnu.org/copyleft/gpl.html for details.
 */
 
-/*! \defgroup decode UTF-8 decoding routines.
+
+
+/*! \defgroup decode UTF-8 decoding routines
 
 These routines decode UTF-8 data into C's wide character type \c wchar_t. Errors are reported
 through \c errno, with the following errors being of particular interest:
@@ -185,3 +188,7 @@ wchar_t* utf8_decode_force2(wchar_t* dest, size_t size, size_t* written, const c
 
 
 /*!@}*/
+/* options for text editors
+kate: replace-trailing-space-save true; space-indent true; tab-width 4;
+vim: expandtab:ts=4:sw=4:syntax=c.doxygen
+*/

src/libutf8/300_encode.c

@@ -1,16 +1,20 @@
-/* libutf8/src/lib/encode.c
+/* libutf8/src/libutf8/300_encode.c
  *
- *  (c)2006, Laurence Withers. Released under the GNU GPL. See file
+ *  (c)2006-2009, Laurence Withers, <l@lwithers.me.uk>.
- *  COPYING for more information / terms of license.
+ *  Released under the GNU GPLv3. See file COPYING or
+ *  http://www.gnu.org/copyleft/gpl.html for details.
 */
 
-char* utf8_encode_char(char* dest, size_t amt, wchar_t ch)
+
+
+char*
+utf8_encode_char(char* dest, size_t amt, wchar_t ch)
 {
     if(!dest || !amt) {
         errno = EINVAL;
         return 0;
     }
-    if(!utf8_isvalid(ch)) {
+    if(!utf8_isucs4(ch)) {
         errno = EILSEQ;
         return 0;
     }
@@ -75,26 +79,30 @@ char* utf8_encode_char(char* dest, size_t amt, wchar_t ch)
 
 
 
-char* utf8_encode_char_force(char* dest, size_t amt, wchar_t ch, wchar_t ilseq)
+char*
+utf8_encode_char_force(char* dest, size_t amt, wchar_t ch, wchar_t ilseq)
 {
-    if(!utf8_isvalid(ilseq)) {
+    if(!utf8_isucs4(ilseq)) {
         errno = EILSEQ;
         return 0;
     }
 
-    return utf8_encode_char(dest, amt, utf8_isvalid(ch) ? ch : ilseq);
+    return utf8_encode_char(dest, amt, utf8_isucs4(ch) ? ch : ilseq);
 }
 
 
 
-char* utf8_encode(char* dest, size_t amt, const wchar_t* src)
+char*
+utf8_encode(char* dest, size_t amt, const wchar_t* src)
 {
     return utf8_encode2(dest, amt, 0, src, -1);
 }
 
 
 
-char* utf8_encode2(char* dest, size_t amt, size_t* written, const wchar_t* src, size_t inamt)
+char*
+utf8_encode2(char* dest, size_t amt, size_t* written, const wchar_t* src,
+    size_t inamt)
 {
     struct utf8_encode_state ctx;
     memset(&ctx, 0, sizeof(ctx));
@@ -114,14 +122,17 @@ char* utf8_encode2(char* dest, size_t amt, size_t* written, const wchar_t* src,
 
 
 
-char* utf8_encode_force(char* dest, size_t amt, const wchar_t* src)
+char*
+utf8_encode_force(char* dest, size_t amt, const wchar_t* src)
 {
     return utf8_encode_force2(dest, amt, 0, src, -1);
 }
 
 
 
-char* utf8_encode_force2(char* dest, size_t amt, size_t* written, const wchar_t* src, size_t inamt)
+char*
+utf8_encode_force2(char* dest, size_t amt, size_t* written, const wchar_t* src,
+    size_t inamt)
 {
     struct utf8_encode_state ctx;
     memset(&ctx, 0, sizeof(ctx));
@@ -136,6 +147,9 @@ char* utf8_encode_force2(char* dest, size_t amt, size_t* written, const wchar_t*
     return dest;
 }
 
+
+
 /* options for text editors
 kate: replace-trailing-space-save true; space-indent true; tab-width 4;
+vim: expandtab:ts=4:sw=4:syntax=c.doxygen
 */

src/libutf8/300_encode.h

@@ -1,10 +1,13 @@
-/* libutf8/src/lib/encode.h
+/* libutf8/src/libutf8/300_encode.h
  *
- *  (c)2006, Laurence Withers. Released under the GNU GPL. See file
+ *  (c)2006-2009, Laurence Withers, <l@lwithers.me.uk>.
- *  COPYING for more information / terms of license.
+ *  Released under the GNU GPLv3. See file COPYING or
+ *  http://www.gnu.org/copyleft/gpl.html for details.
 */
 
-/*! \defgroup encode UTF-8 encoding routines.
+
+
+/*! \defgroup encode UTF-8 encoding routines
 
 The functions in this module allow encoding of UTF-8 characters. Errors are reported through
 \c errno, with the following errors being of particular interest:
@@ -138,7 +141,7 @@ char* utf8_encode_force2(char* dest, size_t amt, size_t* written, const wchar_t*
 
 
 /*!@}*/
-
 /* options for text editors
 kate: replace-trailing-space-save true; space-indent true; tab-width 4;
+vim: expandtab:ts=4:sw=4:syntax=c.doxygen
 */

src/libutf8/400_decode_state.c

@@ -1,9 +1,12 @@
-/* libutf8/src/lib/decode_ctx.c
+/* libutf8/src/libutf8/400_decode_state.c
  *
- *  (c)2006, Laurence Withers. Released under the GNU GPL. See file
+ *  (c)2006-2009, Laurence Withers, <l@lwithers.me.uk>.
- *  COPYING for more information / terms of license.
+ *  Released under the GNU GPLv3. See file COPYING or
+ *  http://www.gnu.org/copyleft/gpl.html for details.
 */
 
+
+
 enum utf8_decoder_state {
     utf8_state_none,
     utf8_state_multibyte1,
@@ -17,7 +20,8 @@ enum utf8_decoder_state {
 
 
 
-struct utf8_decode_state* utf8_decoder(struct utf8_decode_state* ctx)
+struct utf8_decode_state*
+utf8_decoder(struct utf8_decode_state* ctx)
 {
     wchar_t* wr;
     size_t avail;
@@ -41,7 +45,7 @@ loop:
         case utf8_state_none:
             if(!in && ctx->rd_remain < 0) {
                 *wr = 0;
-                ctx->complete = true;
+                ctx->complete = 1;
                 ++ctx->byte_offset;
                 return ctx;
             }
@@ -50,7 +54,7 @@ loop:
                 ++ctx->written;
                 --avail;
                 ++ctx->char_offset;
-                ctx->complete = true;
+                ctx->complete = 1;
                 if(in == 0x0A) {
                     ++ctx->line;
                     ctx->col = 0;
@@ -60,7 +64,7 @@ loop:
                 ctx->state = utf8_state_none;
                 break;
             }
-            ctx->complete = false;
+            ctx->complete = 0;
             if((in & 0xE0) == 0xC0) {
                 ctx->minch = 0x80;
                 ctx->state = utf8_state_multibyte1;
@@ -106,18 +110,18 @@ loop:
                     error_type = utf8_decode_error_overlong;
                     goto error;
                 } else {
-                    // validate codepoint
+                    /* validate codepoint */
-                    if(!utf8_isvalid(ctx->statech)) {
+                    if(!utf8_isucs4(ctx->statech)) {
                         error_type = utf8_decode_error_illegal_cp;
                         goto error;
                     }
 
-                    // add to output string
+                    /* add to output string */
                     *wr++ = ctx->statech;
                     ++ctx->written;
                     --avail;
                     ++ctx->char_offset;
-                    ctx->complete = true;
+                    ctx->complete = 1;
                     if(ctx->statech == 0x0A || ctx->statech == 0x2028) {
                         ++ctx->line;
                         ctx->col = 0;
@@ -172,15 +176,16 @@ error:
         goto loop;
     }
 
-    // shouldn't reach here
+    /* shouldn't reach here */
     errno = EILSEQ;
     return 0;
 }
 
 
 
-enum utf8_decode_error_action utf8_decode_error_callback_replace(
+enum utf8_decode_error_action
-    const struct utf8_decode_state* ctx, enum utf8_decode_error error, wchar_t* newch)
+utf8_decode_error_callback_replace(const struct utf8_decode_state* ctx,
+    enum utf8_decode_error error, wchar_t* newch)
 {
     (void)ctx;
     (void)error;
@@ -190,8 +195,9 @@ enum utf8_decode_error_action utf8_decode_error_callback_replace(
 
 
 
-enum utf8_decode_error_action utf8_decode_error_callback_skip(
+enum utf8_decode_error_action
-    const struct utf8_decode_state* ctx, enum utf8_decode_error error, wchar_t* newch)
+utf8_decode_error_callback_skip(const struct utf8_decode_state* ctx,
+    enum utf8_decode_error error, wchar_t* newch)
 {
     (void)ctx;
     (void)error;
@@ -199,6 +205,9 @@ enum utf8_decode_error_action utf8_decode_error_callback_skip(
     return utf8_decode_error_action_skip;
 }
 
+
+
 /* options for text editors
 kate: replace-trailing-space-save true; space-indent true; tab-width 4;
+vim: expandtab:ts=4:sw=4:syntax=c.doxygen
 */

src/libutf8/400_decode_state.h

@@ -1,10 +1,13 @@
-/* libutf8/src/lib/decode_ctx.h
+/* libutf8/src/libutf8/400_decode_state.h
  *
- *  (c)2006, Laurence Withers. Released under the GNU GPL. See file
+ *  (c)2006-2009, Laurence Withers, <l@lwithers.me.uk>.
- *  COPYING for more information / terms of license.
+ *  Released under the GNU GPLv3. See file COPYING or
+ *  http://www.gnu.org/copyleft/gpl.html for details.
 */
 
-/*! \defgroup decode_ctx UTF-8 stateful decoder.
+
+
+/*! \defgroup decode_ctx UTF-8 stateful decoder
 
 This UTF-8 decoder uses a structure to maintain state information between calls. This means that
 you can feed it a stream of data as it comes in without needing to store the entire document in a
@@ -19,6 +22,11 @@ character, or simply skipping the illegal byte sequence.
 
 
 
+/* opaque type */
+struct utf8_decode_state;
+
+
+
 /*! \brief Types of decoder error.
 
 These are the types of error that can be encountered by the decoder. This allows slightly more
@@ -27,19 +35,19 @@ to the callback function.
 
 */
 enum utf8_decode_error {
-    /// Lone continuation char encountered when start char expected.
+    /*! \brief Lone continuation char encountered when start char expected. */
     utf8_decode_error_lone_cchar,
 
-    /// Non-continuation char encountered within multibyte sequence.
+    /*! \brief Non-continuation char encountered within multibyte sequence. */
     utf8_decode_error_not_cchar,
 
-    /// Invalid start char (not ASCII).
+    /*! \brief Invalid start char (not ASCII). */
     utf8_decode_error_not_schar,
 
-    /// Overlong byte sequence.
+    /*! \brief Overlong byte sequence. */
     utf8_decode_error_overlong,
 
-    /// Illegal code positions (UTF-16 surrogates or 0xFFFE,0xFFFF).
+    /*! \brief Illegal code positions (UTF-16 surrogates or 0xFFFE,0xFFFF). */
     utf8_decode_error_illegal_cp
 };
 
@@ -52,13 +60,13 @@ error. These actions are specified by the error callback function's return value
 
 */
 enum utf8_decode_error_action {
-    /// Abort the conversion, returning EILSEQ.
+    /*! \brief Abort the conversion, returning EILSEQ. */
     utf8_decode_error_action_abort,
 
-    /// Skip the illegal byte sequence.
+    /*! \brief Skip the illegal byte sequence. */
     utf8_decode_error_action_skip,
 
-    /// Discard the illegal byte sequence and enter a replacement char.
+    /*! \brief Discard the illegal byte sequence and enter a replacement char. */
     utf8_decode_error_action_replace
 };
 
@@ -112,48 +120,48 @@ these variables aren't perfect, as they can be affected by errors and limitation
 
 */
 struct utf8_decode_state {
-    /// \c false if we are part-way through a multi-byte character.
+    /*! \brief 0 if we are part-way through a multi-byte character. */
-    bool complete;
+    int complete;
 
-    /// Data to read (current read position).
+    /*! \brief Data to read (current read position). */
     const char* rd;
 
-    /// Number of bytes remaining (current).
+    /*! \brief Number of bytes remaining (current). */
     int rd_remain;
 
-    /// Internal state; initialise to 0, don't change.
+    /*! \brief Internal state; initialise to 0, don't change. */
     int state;
 
-    /// Error callback (may be 0).
+    /*! \brief Error callback (may be 0). */
     utf8_decode_error_callback error_callback;
 
-    /// Pointer to output buffer.
+    /*! \brief Pointer to output buffer. */
     wchar_t* wr;
 
-    /// Number of characters that can be written.
+    /*! \brief Number of characters that can be written. */
     size_t wr_size;
 
-    /// Number of characters written on last call.
+    /*! \brief Number of characters written on last call. */
     size_t written;
 
-    /// Arbitrary data pointer for \a error_callback.
+    /*! \brief Arbitrary data pointer for \a error_callback. */
     void* data;
 
-    /// Current line (starting from 0).
+    /*! \brief Current line (starting from 0). */
     int line;
 
-    /// Current column (starting from 0).
+    /*! \brief Current column (starting from 0). */
     int col;
 
-    /// Character offset from start of data (starting from 0).
+    /*! \brief Character offset from start of data (starting from 0). */
     int char_offset;
 
-    /// Byte offset from start of data (starting from 0).
+    /*! \brief Byte offset from start of data (starting from 0). */
     int byte_offset;
 
-    /// Don't use this.
+    /*! \brief Don't use this. */
     wchar_t statech;
-    /// Don't use this.
+    /*! \brief Don't use this. */
     wchar_t minch;
 };
 
@@ -180,18 +188,18 @@ struct utf8_decode_state* utf8_decoder(struct utf8_decode_state* state);
 
 
 
-/// Standard error callback: use replacement char 0xFFFD.
+/*! \brief Standard error callback: use replacement char 0xFFFD. */
 enum utf8_decode_error_action utf8_decode_error_callback_replace(
     const struct utf8_decode_state* ctx, enum utf8_decode_error error, wchar_t* newch);
 
-/// Standard error callback: skip invalid chars.
+/*! \brief Standard error callback: skip invalid chars. */
 enum utf8_decode_error_action utf8_decode_error_callback_skip(
     const struct utf8_decode_state* ctx, enum utf8_decode_error error, wchar_t* newch);
 
 
 
 /*!@}*/
-
 /* options for text editors
 kate: replace-trailing-space-save true; space-indent true; tab-width 4;
+vim: expandtab:ts=4:sw=4:syntax=c.doxygen
 */

src/libutf8/500_encode_state.c

@@ -1,28 +1,34 @@
-/* libutf8/src/lib/encode_state.c
+/* libutf8/src/libutf8/500_encode_state.c
  *
- *  (c)2006, Laurence Withers. Released under the GNU GPL. See file
+ *  (c)2006-2009, Laurence Withers, <l@lwithers.me.uk>.
- *  COPYING for more information / terms of license.
+ *  Released under the GNU GPLv3. See file COPYING or
+ *  http://www.gnu.org/copyleft/gpl.html for details.
 */
 
-struct utf8_encode_state* utf8_encoder(struct utf8_encode_state* state)
+
+
+struct utf8_encode_state*
+utf8_encoder(struct utf8_encode_state* state)
 {
-    char* wr = state->wr, * ret;
+    char* wr, * ret, * endp;
-    char* endp = wr + state->wr_size - 1;
     wchar_t ch;
     enum utf8_encode_error_action error_action;
-    bool reencoding;
+    int reencoding;
 
     if(!state || !state->rd || !state->wr || state->wr_size < 7) {
         errno = EINVAL;
         return 0;
     }
 
+    wr = state->wr;
+    endp = wr + state->wr_size - 1;
+
     state->written = 0;
     while(state->rd_remain) {
         ch = *state->rd;
         if(!ch && state->rd_remain < 0) break;
 
-        reencoding = false;
+        reencoding = 0;
       reencode:
         ret = utf8_encode_char(wr, endp - wr, ch);
         if(!ret) {
@@ -38,7 +44,7 @@ struct utf8_encode_state* utf8_encoder(struct utf8_encode_state* state)
                 return 0;
 
             case utf8_encode_error_action_replace:
-                reencoding = true;
+                reencoding = 1;
                 goto reencode;
 
             case utf8_encode_error_action_skip:
@@ -65,8 +71,9 @@ struct utf8_encode_state* utf8_encoder(struct utf8_encode_state* state)
 
 
 
-enum utf8_encode_error_action utf8_encode_error_callback_replace(
+enum utf8_encode_error_action
-    const struct utf8_encode_state* state, wchar_t* newch)
+utf8_encode_error_callback_replace(const struct utf8_encode_state* state,
+    wchar_t* newch)
 {
     (void)state;
     *newch = 0xFFFD;
@@ -75,14 +82,18 @@ enum utf8_encode_error_action utf8_encode_error_callback_replace(
 
 
 
-enum utf8_encode_error_action utf8_encode_error_callback_skip(
+enum utf8_encode_error_action
-    const struct utf8_encode_state* state, wchar_t* newch)
+    utf8_encode_error_callback_skip(const struct utf8_encode_state* state,
+    wchar_t* newch)
 {
     (void)state;
     (void)newch;
     return utf8_encode_error_action_skip;
 }
 
+
+
 /* options for text editors
 kate: replace-trailing-space-save true; space-indent true; tab-width 4;
+vim: expandtab:ts=4:sw=4:syntax=c.doxygen
 */

src/libutf8/500_encode_state.h

@@ -1,10 +1,13 @@
-/* libutf8/src/lib/encode_state.h
+/* libutf8/src/libutf8/500_encode_state.h
  *
- *  (c)2006, Laurence Withers. Released under the GNU GPL. See file
+ *  (c)2006-2009, Laurence Withers, <l@lwithers.me.uk>.
- *  COPYING for more information / terms of license.
+ *  Released under the GNU GPLv3. See file COPYING or
+ *  http://www.gnu.org/copyleft/gpl.html for details.
 */
 
-/*! \defgroup encode_state UTF-8 stateful encoder.
+
+
+/*! \defgroup encode_state UTF-8 stateful encoder
 
 This UTF-8 encoder uses a structure to maintain state information between calls. This means that
 you can feed it a stream of data as it comes in without needing to store the entire source in a
@@ -20,6 +23,11 @@ character.
 
 
 
+/* opaque type */
+struct utf8_encode_state;
+
+
+
 /*! \brief Action to be taken after error callback.
 
 These are the possible actions that can be undertaken after a stateful encoding operation has
@@ -28,13 +36,13 @@ function's return value.
 
 */
 enum utf8_encode_error_action {
-    /// Abort the conversion, returning EILSEQ.
+    /*! \brief Abort the conversion, returning EILSEQ. */
     utf8_encode_error_action_abort,
 
-    /// Skip the illegal byte sequence.
+    /*! \brief Skip the illegal byte sequence. */
     utf8_encode_error_action_skip,
 
-    /// Discard the illegal byte sequence and enter a replacement char.
+    /*! \brief Discard the illegal byte sequence and enter a replacement char. */
     utf8_encode_error_action_replace
 };
 
@@ -55,11 +63,11 @@ it with something else, or abort the conversion entirely.
 typedef enum utf8_encode_error_action (*utf8_encode_error_callback)(
     const struct utf8_encode_state* state, wchar_t* newch);
 
-/// Standard error callback: use replacement char 0xFFFD.
+/*! \brief Standard error callback: use replacement char 0xFFFD. */
 enum utf8_encode_error_action utf8_encode_error_callback_replace(
     const struct utf8_encode_state* state, wchar_t* newch);
 
-/// Standard error callback: skip invalid chars.
+/*! \brief Standard error callback: skip invalid chars. */
 enum utf8_encode_error_action utf8_encode_error_callback_skip(
     const struct utf8_encode_state* state, wchar_t* newch);
 
@@ -87,34 +95,34 @@ start of the stream, and should always be accurate.
 
 */
 struct utf8_encode_state {
-    /// Current read position.
+    /*! \brief Current read position. */
     const wchar_t* rd;
 
-    /// Number of chars remaining (-ve means to scan for null char).
+    /*! \brief Number of chars remaining (-ve means to scan for null char). */
     int rd_remain;
 
-    /// Callback function used to handle illegal source characters.
+    /*! \brief Callback function used to handle illegal source characters. */
     utf8_encode_error_callback error_callback;
 
-    /// Output buffer.
+    /*! \brief Output buffer. */
     char* wr;
 
-    /// Output buffer size.
+    /*! \brief Output buffer size. */
     size_t wr_size;
 
-    /// Number of bytes written during last call.
+    /*! \brief Number of bytes written during last call. */
     size_t written;
 
-    /// Arbitrary pointer (useful for \a error_callback).
+    /*! \brief Arbitrary pointer (useful for \a error_callback). */
     void* data;
 
-    /// Current line (starting from 0).
+    /*! \brief Current line (starting from 0). */
     int line;
 
-    /// Current column (starting from 0).
+    /*! \brief Current column (starting from 0). */
     int col;
 
-    /// Character offset from start of data (starting from 0).
+    /*! \brief Character offset from start of data (starting from 0). */
     int char_offset;
 };
 
@@ -152,7 +160,7 @@ struct utf8_encode_state* utf8_encoder(struct utf8_encode_state* state);
 
 
 /*!@}*/
-
 /* options for text editors
 kate: replace-trailing-space-save true; space-indent true; tab-width 4;
+vim: expandtab:ts=4:sw=4:syntax=c.doxygen
 */

src/libutf8/999_BottomHeader.h

@@ -0,0 +1,17 @@
+/* libutf8/src/libutf8/999_BottomHeader.h
+ *
+ *  (c)2006-2009, Laurence Withers, <l@lwithers.me.uk>.
+ *  Released under the GNU GPLv3. See file COPYING or
+ *  http://www.gnu.org/copyleft/gpl.html for details.
+*/
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif
+
+/* options for text editors
+kate: replace-trailing-space-save true; space-indent true; tab-width 4;
+vim: expandtab:ts=4:sw=4:syntax=c.doxygen
+*/

src/libutf8/BottomHeader.h

@@ -1,11 +0,0 @@
-/* libutf8/src/lib/BottomHeader.h
- *
- *  (c)2006, Laurence Withers. Released under the GNU GPL. See file
- *  COPYING for more information / terms of license.
-*/
-
-#ifdef __cplusplus
-}
-#endif
-
-#endif

src/libutf8/ForwardDeclare.h

@@ -1,14 +0,0 @@
-/* libutf8/src/lib/ForwardDeclare.h
- *
- *  (c)2006, Laurence Withers. Released under the GNU GPL. See file
- *  COPYING for more information / terms of license.
-*/
-
-// This file simply contains forward declarations of all libutf8
-// classes, to facilitate header ordering, etc.
-
-// encode_state.h
-struct utf8_encode_state;
-
-// decode_state.h
-struct utf8_decode_state;

src/libutf8/TopHeader.h

@@ -1,16 +0,0 @@
-/* libutf8/src/lib/TopHeader.h
- *
- *  (c)2006, Laurence Withers. Released under the GNU GPL. See file
- *  COPYING for more information / terms of license.
-*/
-
-#ifndef HEADER_LIBUTF8
-#define HEADER_LIBUTF8
-
-// standard includes, or includes needed for type declarations
-#include <stdbool.h>
-#include <stddef.h>
-
-#ifdef __cplusplus
-extern "C" {
-#endif

src/libutf8/TopSource.c

@@ -1,13 +0,0 @@
-/* libutf8/src/lib/TopSource.cpp
- *
- *  (c)2006, Laurence Withers. Released under the GNU GPL. See file
- *  COPYING for more information / terms of license.
-*/
-
-#include "utf8.h"
-
-// Below are all the includes used throughout the library.
-
-#include <errno.h>
-#include <stdint.h>
-#include <string.h>

src/libutf8/build.install-lib

@@ -2,35 +2,37 @@ build_target libutf8
 
 # make paths (this is for Gentoo in particular)
 build_dir_tree "${LIBDIR}" || return 1
-build_dir_tree "${PKGCONFDIR}" || return 1
+build_dir_tree "${BINDIR}" || return 1
 build_dir_tree "${INCLUDEDIR}" || return 1
 
 # install library
 echo "Installing libraries into '${LIBDIR}'"
+source src/libutf8/soversion
 install_file ${libutf8} ${LIBDIR} 0755 || return 1
 BASE="${libutf8_BASE}.so"
 MAJOR="${BASE}.${SOMAJOR}"
-MINOR="${MAJOR}.${SOMINOR}"
+MICRO="${MAJOR}.${SOMICRO}"
-MICRO="${MINOR}.${SOMICRO}"
+install_symlink "${BASE}" "${MICRO}" "${LIBDIR}"
-install_symlink "${MINOR}" "${MICRO}" "${LIBDIR}"
-install_symlink "${MAJOR}" "${MINOR}" "${LIBDIR}"
-install_symlink "${BASE}" "${MAJOR}" "${LIBDIR}"
 
 # install header
 echo "Installing header file '${libutf8_HEADER}' into ${INCLUDEDIR}"
 install_header ${libutf8_HEADER} ${INCLUDEDIR} 0644 || return 1
 
-# install pkgconfig file
+# install config script
-echo "Installing package config file into ${PKGCONFDIR}"
+echo "Installing config script into ${BINDIR}"
-PKGCONFFILE=${PKGCONFDIR}/libutf8.pc
+CONFFILE="${INSTALL_PREFIX}${BINDIR}/libutf8-config"
-do_cmd rm -f ${PKGCONFFILE}
+
-do_cmd_redir ${PKGCONFFILE} sed \
+do_cmd rm -f "${CONFFILE}"
+do_cmd_redir "${CONFFILE}" sed \
     -e "s,@VERSION@,${VERSION}," \
-    -e "s,@LIBDIR@,${FINALLIBDIR}," \
+    -e "s,@DEP_CFLAGS@,${libutf8_DEP_CFLAGS}," \
-    -e "s,@INCLUDEDIR@,${FINALINCLUDEDIR}," \
+    -e "s,@DEP_LIBS@,${libutf8_DEP_LIBS}," \
-    src/libutf8/pkgconf.in
+    -e "s,@LIB_DIR@,${LIBDIR}," \
-do_cmd chmod 0644 ${PKGCONFFILE}
+    -e "s,@INCLUDE_DIR@,${INCLUDEDIR}," \
+    src/libutf8/config-script
+
+do_cmd chmod 0755 "${CONFFILE}"
 print_success "Done"
 
 # kate: replace-trailing-space-save true; space-indent true; tab-width 4;
-# vim: expandtab:ts=4:sw=4
+# vim: syntax=sh:expandtab:ts=4:sw=4

src/libutf8/build.lib

@@ -3,14 +3,18 @@
 #  libutf8_BUILT
 #  libutf8_HEADER
 #  libutf8_BASE
+#  libutf8_DEP_CFLAGS
+#  libutf8_DEP_LIBS
 
 if [ -z ${libutf8_BUILT} ]
 then
     libutf8_BASE=libutf8
     source src/libutf8/soversion
 
-    libutf8="obj/${libutf8_BASE}.so.${SOMAJOR}.${SOMINOR}.${SOMICRO}"
+    libutf8="obj/${libutf8_BASE}.so.${SOMAJOR}.${SOMICRO}"
-    SO_EXTRA="-lc"
+    libutf8_DEP_CFLAGS="" # @TODO@ cflags
+    libutf8_DEP_LIBS="" # @TODO@ libs
+    SO_EXTRA="${libutf8_DEP_CFLAGS} ${libutf8_DEP_LIBS} -lc"
 
     echo "Building library ${libutf8}..."
 
@@ -30,13 +34,14 @@ then
     then
         echo " Compiling"
 
-        SONAME="${libutf8_BASE}.so.${SOMAJOR}.${SOMINOR}"
+        SONAME="${libutf8_BASE}.so.${SOMAJOR}"
         do_cmd ${CC} ${CFLAGS} -Iobj -shared -fpic -o "${libutf8}" \
             -Wl,-soname,${SONAME} \
             ${SRC} ${SO_EXTRA} || return 1
 
-        # make tests work
+        # make tests and linking work
-        do_cmd ln -sf $(basename ${libutf8}) obj/${SONAME} || return 1
+        do_cmd ln -sf "$(basename "${libutf8}")" "obj/${SONAME}" || return 1
+        do_cmd ln -sf "$(basename "${libutf8}")" "obj/${libutf8_BASE}.so" || return 1
 
         print_success "Library built"
     else
@@ -48,4 +53,4 @@ then
 
 fi
 # kate: replace-trailing-space-save true; space-indent true; tab-width 4;
-# vim: expandtab:ts=4:sw=4
+# vim: syntax=sh:expandtab:ts=4:sw=4

src/libutf8/build.monolithic

@@ -8,14 +8,14 @@ MONOLITHIC_TESTS="src/libutf8/build.lib src/libutf8/build.monolithic"
 
 if [ -z "${libutf8_MONOLITHIC}" ]
 then
-    MONOLITHIC_SOURCE="$(echo src/libutf8/{TopHeader,ForwardDeclare,ctype,{de,en}code{,_state},BottomHeader}.h)"
+    MONOLITHIC_SOURCE="$(find src/libutf8/ -name '*.h' | sort)"
     make_monolithic ${HDR} Ch || return 1
 
-    MONOLITHIC_SOURCE="$(echo src/libutf8/{TopSource,ctype,{de,en}code{,_state}}.c)"
+    MONOLITHIC_SOURCE="$(find src/libutf8/ -name '*.c' | sort)"
     make_monolithic ${SRC} C || return 1
 
     libutf8_MONOLITHIC=1
     MONOLITHIC_DOC="${MONOLITHIC_DOC} ${HDR}"
 fi
 # kate: replace-trailing-space-save true; space-indent true; tab-width 4;
-# vim: expandtab:ts=4:sw=4
+# vim: syntax=sh:expandtab:ts=4:sw=4

src/libutf8/config-script

@@ -0,0 +1,98 @@
+#!/bin/bash
+# libutf8/src/libutf8/config-script
+#
+# libutf8-config template. Variables are finalised at install time.
+#
+dep_cflags="@DEP_CFLAGS@"
+dep_libs="@DEP_LIBS@"
+include_dir="@INCLUDE_DIR@"
+include_dir_set="no"
+lib_dir="@LIB_DIR@"
+lib_dir_set="no"
+
+
+
+usage() {
+    cat <<EOF
+Usage: libutf8-config [options]
+Options:
+        [--version]
+        [--libs]
+        [--libdir[=DIR]]
+        [--cflags]
+        [--includedir[=DIR]]
+EOF
+    exit $1
+}
+
+
+
+[ $# -eq 0 ] && usage 1 1>&2
+
+
+
+while [ $# -gt 0 ]
+do
+    case "$1" in
+        -*=*) 
+            optarg="$(echo "$1" | sed 's/[-_a-zA-Z0-9]*=//')"
+        ;;
+
+        *)
+            optarg=""
+        ;;
+    esac
+
+    case "$1" in
+        --libdir=*)
+            lib_dir="${optarg}"
+            lib_dir_set="yes"
+        ;;
+
+        --libdir)
+            echo_lib_dir="yes"
+        ;;
+
+        --includedir=*)
+            include_dir="${optarg}"
+            include_dir_set="yes"
+        ;;
+
+        --includedir)
+            echo_include_dir="yes"
+        ;;
+
+        --version)
+            echo "@VERSION@"
+            exit 0
+        ;;
+
+        --cflags)
+            [ "${include_dir}" != "/usr/include" ] && includes="-I${include_dir}"
+            echo_cflags="yes"
+        ;;
+
+        --libs)
+            echo_libs="yes"
+        ;;
+
+        *)
+            usage 1 1>&2
+        ;;
+    esac
+
+    shift
+done
+
+
+
+[ "${echo_prefix}" == "yes" ] && echo "${prefix}"
+[ "${echo_exec_prefix}" == "yes" ] && echo "${exec_prefix}"
+[ "${echo_cflags}" == "yes" ] && echo "${dep_cflags} ${includes}"
+[ "${echo_libs}" == "yes" ] && echo "${dep_libs} -L${lib_dir} -lutf8"
+true
+
+
+
+# vim: syntax=sh:expandtab:ts=4:sw=4
+# kate: replace-trailing-space-save true; space-indent true; tab-width 4;

src/libutf8/ctype.c

@@ -1,55 +0,0 @@
-/* libutf8/src/lib/ctype.c
- *
- *  (c)2006, Laurence Withers. Released under the GNU GPL. See file
- *  COPYING for more information / terms of license.
-*/
-
-bool utf8_isascii(wchar_t ch)
-{
-    return !(ch & ~0x7F);
-}
-
-
-
-/* From PropList-4.1.0.txt (http://www.unicode.org/Public/UNIDATA/)
-
-0009..000D    ; White_Space # Cc   [5] <control-0009>..<control-000D>
-0020          ; White_Space # Zs       SPACE
-0085          ; White_Space # Cc       <control-0085>
-00A0          ; White_Space # Zs       NO-BREAK SPACE
-1680          ; White_Space # Zs       OGHAM SPACE MARK
-180E          ; White_Space # Zs       MONGOLIAN VOWEL SEPARATOR
-2000..200A    ; White_Space # Zs  [11] EN QUAD..HAIR SPACE
-2028          ; White_Space # Zl       LINE SEPARATOR
-2029          ; White_Space # Zp       PARAGRAPH SEPARATOR
-202F          ; White_Space # Zs       NARROW NO-BREAK SPACE
-205F          ; White_Space # Zs       MEDIUM MATHEMATICAL SPACE
-3000          ; White_Space # Zs       IDEOGRAPHIC SPACE
-*/
-
-bool utf8_isspace(wchar_t ch)
-{
-    return((ch >= 0x0009 && ch <= 0x000D)
-            || ch == 0x0020
-            || ch == 0x0085
-            || ch == 0x00A0
-            || ch == 0x1680
-            || ch == 0x180E
-            || (ch >= 0x2000 && ch <= 0x200A)
-            || ch == 0x2028
-            || ch == 0x2029
-            || ch == 0x202F
-            || ch == 0x205F
-            || ch == 0x3000);
-}
-
-
-
-bool utf8_isvalid(wchar_t ch)
-{
-    return !(ch & (~((wchar_t)0x7FFFFFFF))) && (ch < 0xD800 || ch > 0xDFFF) && (ch != 0xFFFE) && (ch != 0xFFFF);
-}
-
-/* options for text editors
-kate: replace-trailing-space-save true; space-indent true; tab-width 4;
-*/

src/libutf8/ctype.h

@@ -1,46 +0,0 @@
-/* libutf8/src/lib/ctype.h
- *
- *  (c)2006, Laurence Withers. Released under the GNU GPL. See file
- *  COPYING for more information / terms of license.
-*/
-
-/*! \defgroup ctype Character classification
-
-This module contains functions for character classification. These are basically an extension of the
-\c is* functions defined in \c <ctype.h>.
-
-\todo There are many char classification functions that haven't been implemented yet. These won't be
-    implemented until they can be done in a proper, Unicode-safe fashion.
-
- */
-/*!@{*/
-
-
-
-/// Returns \c true if \a ch can be represented in ASCII.
-bool utf8_isascii(wchar_t ch);
-
-/// Returns \c true if \a ch is whitespace.
-bool utf8_isspace(wchar_t ch);
-
-/*! \brief Returns \c true if \a ch is a valid UCS-4 character.
-
-\param ch The character to classify.
-\retval true If \a ch is a valid UCS-4 character.
-\retval false If \a ch is not a valid UCS-4 character.
-
-This function will examine a \c wchar_t value and determine whether or not it is a valid UCS-4
-character. Valid characters lie in the range 0–0x7FFFFFFF but exclude:
-\li the UTF-16 surrogate code points (U+D800–U+DFFF, inclusive)
-\li the invalid code points U+FFFE and U+FFFF
-
-*/
-bool utf8_isvalid(wchar_t ch);
-
-
-
-/*!@}*/
-
-/* options for text editors
-kate: replace-trailing-space-save true; space-indent true; tab-width 4;
-*/

src/libutf8/pkgconf.in

@@ -1,21 +0,0 @@
-# libutf8/src/lib/clib/pkgconf.in
-#
-#  Metadata file for pkg-config
-#  ( http://www.freedesktop.org/software/pkgconfig/ )
-#
-#  (c)2006, Laurence Withers, <l@lwithers.me.uk>.
-#  Released under the GNU GPLv2. See file COPYING or
-#  http://www.gnu.org/copyleft/gpl.html for details.
-#
-
-# Name, description
-Name: @TODO@
-Description: @TODO@
-Version: @VERSION@
-
-# Requirements
-Requires:
-
-# Compilation information
-Libs: -L@LIBDIR@ -lutf8
-Cflags: -I@INCLUDEDIR@

src/libutf8/soversion

@@ -1,17 +1,15 @@
 # libutf8/src/libutf8/soversion
 #
-#  (c)2006, Laurence Withers, <l@lwithers.me.uk>.
+#  (c)2009, Laurence Withers, <l@lwithers.me.uk>.
-#  Released under the GNU GPLv2. See file COPYING or
+#  Released under the GNU GPLv3. See file COPYING or
 #  http://www.gnu.org/copyleft/gpl.html for details.
 #
 
 
 
-# SOMAJOR and SOMINOR are included in the library's soname. They need to
+# SOMAJOR is included in the library's soname, and needs to be bumped
-# be bumped on a binary-incompatible release. They are both single
+# after a binary-incompatible release. It is a single integer.
-# integers.
+SOMAJOR=1
-SOMAJOR=0
-SOMINOR=0
 
 # SOMICRO is bumped every time there is a binary-compatible release.
-SOMICRO=1
+SOMICRO=2

src/tests/.params

@@ -1 +1 @@
-c tests tests libutf8
+tests c tests libutf8

src/tests/build.default

@@ -1,3 +1,3 @@
 source src/tests/build.tests
 # kate: replace-trailing-space-save true; space-indent true; tab-width 4;
-# vim: expandtab:ts=4:sw=4
+# vim: syntax=sh:expandtab:ts=4:sw=4

src/tests/build.tests

@@ -6,15 +6,15 @@ build_target libutf8 || return 1
 
 if [ -z ${tests_BUILT} ]
 then
-    LIBS="${libutf8} "
+    LIBS="${libutf8} ${libutf8_DEP_CFLAGS} ${libutf8_DEP_LIBS} "
-    EXTRAS=""
+    EXTRAS="" # @TODO@ libs, cflags
 
     echo "Building test programs..."
     do_cmd mkdir -p obj/tests || return 1
 
     for SRC in src/tests/*.c
     do
-        TEST="obj/tests/$(basename ${SRC} | sed -e 's,.c$,,')"
+        TEST="obj/tests/$(basename "${SRC}" ".c")"
         MODIFIED=0
         for file in ${LIBS} ${SRC} src/tests/build.tests
         do
@@ -40,4 +40,4 @@ then
 fi
 
 # kate: replace-trailing-space-save true; space-indent true; tab-width 4;
-# vim: expandtab:ts=4:sw=4
+# vim: syntax=sh:expandtab:ts=4:sw=4

src/tests/decode.c

@@ -1,7 +1,8 @@
 /* libutf8/src/tests/decode.c
  *
- *  (c)2006, Laurence Withers. Released under the GNU GPL. See file
+ *  (c)2006-2009, Laurence Withers, <l@lwithers.me.uk>.
- *  COPYING for more information / terms of license.
+ *  Released under the GNU GPLv3. See file COPYING or
+ *  http://www.gnu.org/copyleft/gpl.html for details.
 */
 
 #include "utf8.h"
@@ -11,15 +12,18 @@
 
 
 
-void writeout(const wchar_t* x, int amt)
+void
+writeout(const wchar_t* x, int amt)
 {
-    fwrite(x, sizeof(wchar_t), amt, stdout);
+    int dummy;
+    dummy = fwrite(x, sizeof(wchar_t), amt, stdout);
 }
 
 
 
-enum utf8_decode_error_action error_callback(
+enum
-    const struct utf8_decode_state* ctx, enum utf8_decode_error error, wchar_t* newch)
+utf8_decode_error_action error_callback(const struct utf8_decode_state* ctx,
+    enum utf8_decode_error error, wchar_t* newch)
 {
     fprintf(stderr, "Line %d, col %d (char %d, byte %d): ",
             ctx->line + 1, ctx->col + 1, ctx->char_offset, ctx->byte_offset);
@@ -51,7 +55,8 @@ enum utf8_decode_error_action error_callback(
 
 
 
-int main(int argc, char* argv[])
+int
+main(int argc, char* argv[])
 {
     char inbuf[1024];
     wchar_t outbuf[1024];
@@ -68,19 +73,19 @@ int main(int argc, char* argv[])
         return 1;
     }
 
-    // set up ctx structure
+    /* set up ctx structure */
     memset(&ctx, 0, sizeof(ctx));
     ctx.wr = outbuf;
     ctx.wr_size = sizeof(outbuf) / sizeof(wchar_t);
     ctx.error_callback = error_callback;
 
-    // loop over input
+    /* loop over input */
     while(!feof(stdin)) {
-        // read input
+        /* read input */
         ctx.rd_remain = fread(inbuf, 1, sizeof(inbuf), stdin);
         ctx.rd = inbuf;
 
-        // decode it
+        /* decode it */
         while(ctx.rd_remain) {
             if(!utf8_decoder(&ctx)) {
                 perror("utf8_decoder");
@@ -89,7 +94,7 @@ int main(int argc, char* argv[])
                 return 1;
             }
 
-            // write output
+            /* write output */
             writeout(outbuf, ctx.written);
         }
     }
@@ -104,4 +109,5 @@ int main(int argc, char* argv[])
 
 /* options for text editors
 kate: replace-trailing-space-save true; space-indent true; tab-width 4;
+vim: expandtab:ts=4:sw=4:syntax=c.doxygen
 */

src/tests/random.c

@@ -1,7 +1,8 @@
 /* libutf8/src/tests/random.c
  *
- *  (c)2006, Laurence Withers. Released under the GNU GPL. See file
+ *  (c)2006-2009, Laurence Withers, <l@lwithers.me.uk>.
- *  COPYING for more information / terms of license.
+ *  Released under the GNU GPLv3. See file COPYING or
+ *  http://www.gnu.org/copyleft/gpl.html for details.
 */
 
 #include "utf8.h"
@@ -14,7 +15,8 @@
 
 
 
-void make_rand(wchar_t* buf, int ch)
+void
+make_rand(wchar_t* buf, int ch)
 {
     int fd = open("/dev/urandom", O_RDONLY);
     if(fd < 0) {
@@ -36,7 +38,8 @@ void make_rand(wchar_t* buf, int ch)
 
 
 
-int do_encode(char* dest, size_t size, wchar_t* src, size_t amt)
+int
+do_encode(char* dest, size_t size, wchar_t* src, size_t amt)
 {
     struct utf8_encode_state ctx;
     memset(&ctx, 0, sizeof(ctx));
@@ -64,14 +67,16 @@ int do_encode(char* dest, size_t size, wchar_t* src, size_t amt)
 
 
 
-int MIN(int x, int y)
+int
+MIN(int x, int y)
 {
     return (x < y) ? x : y;
 }
 
 
 
-void do_decode_easy(wchar_t* dest, size_t size, const char* src, size_t amt)
+void
+do_decode_easy(wchar_t* dest, size_t size, const char* src, size_t amt)
 {
     struct utf8_decode_state ctx;
     memset(&ctx, 0, sizeof(ctx));
@@ -99,7 +104,8 @@ void do_decode_easy(wchar_t* dest, size_t size, const char* src, size_t amt)
 
 
 
-void do_decode(wchar_t* dest, size_t size, const char* src, size_t amt)
+void
+do_decode(wchar_t* dest, size_t size, const char* src, size_t amt)
 {
     struct utf8_decode_state ctx;
     memset(&ctx, 0, sizeof(ctx));
@@ -130,7 +136,8 @@ void do_decode(wchar_t* dest, size_t size, const char* src, size_t amt)
 
 
 
-int main(int argc, char* argv[])
+int
+main(int argc, char* argv[])
 {
     wchar_t wbuf[1024], wbuf2[1025];
     char cbuf[8192];
@@ -162,4 +169,5 @@ int main(int argc, char* argv[])
 
 /* options for text editors
 kate: replace-trailing-space-save true; space-indent true; tab-width 4;
+vim: expandtab:ts=4:sw=4:syntax=c.doxygen
 */

src/tests/template

@@ -1,7 +1,7 @@
 /* libutf8/src/tests/???.c
  *
- *  (c)2006, Laurence Withers, <l@lwithers.me.uk>.
+ *  (c)2006-2009, Laurence Withers, <l@lwithers.me.uk>.
- *  Released under the GNU GPLv2. See file COPYING or
+ *  Released under the GNU GPLv3. See file COPYING or
  *  http://www.gnu.org/copyleft/gpl.html for details.
 */
 
@@ -17,15 +17,15 @@ int main(int argc, char* argv[])
     int ret = 0;
 
     if(argc == 2 && !strcmp(argv[1], "--print-summary")) {
-        printf("One line summary.\n");
+        fputs("One line summary.\n", stdout);
         return 0;
     }
 
     if(argc == 1) {
-        // empty argument list
+        /* empty argument list */
     }
 
-    // TODO
+    /* TODO */
 
     return ret;
 }

version

@@ -1,19 +1,17 @@
 # libutf8/version
 #
-#  (c)2006, Laurence Withers, <l@lwithers.me.uk>.
+#  (c)2006-2009, Laurence Withers, <l@lwithers.me.uk>.
-#  Released under the GNU GPLv2. See file COPYING or
+#  Released under the GNU GPLv3. See file COPYING or
 #  http://www.gnu.org/copyleft/gpl.html for details.
 #
 
 
 
 # VERSION contains the full version number of the library, which is 
-# expected to be in 'major.minor.micro' format. It can optionally be 
+# expected to be in 'major.minor.micro' format.
-# suffixed with a string.
 VERMAJOR=1
-VERMINOR=2
+VERMINOR=3
-VERMICRO=1
+VERMICRO=2
-VEREXTRA=""
 
 # kate: replace-trailing-space-save true; space-indent true; tab-width 4;
-# vim: expandtab:ts=4:sw=4
+# vim: expandtab:ts=4:sw=4:syntax=sh