add licenses before distribution

Thought a bit about whether having OR instead of AND
changes performance, and concluded it probably didn't.

In particular, think about when it jumps to the inner
part of the if/else condition

README.md

@@ -1,21 +1,73 @@
-Desiderata
+# wc: count words in <50 lines of C
 
-- Simple: Simple operation in terms of counting spaces and \n.
-- Avoid "off by one" errors; make sure an empty file is reported as such.
-  - Words as space or enter, followed by nonspace, followed by space? Make sure two spaces aren't two words?
-- Keep Linux only. 
-- No flags. Only count words, not lines.
-- Allow piping, as well as reading files.
-  - Wonder how normal utilities handle this.
-- Could use zig? => Not for now
+## Desiderata
 
-Steps:
+- Simple: Just count words as delimited by spaces, tabs, newlines.
+- Allow: reading files, piping to the utility, and reading from stdin.
+- Separate utilities for counting different things, like lines and characters, into their own tools.
+- Avoid off-by-one errors.
+- Linux only.
+- Small.
+
+## Comparison with other historical versions wc.
+
+The version in wc/wc.c in this repository sits at 43 lines. It decides to read from stdin if the number of arguments fed to it is otherwise zero, and uses the linux `read` function to read character by character. It doesn't have flags, instead, there are further utilities in the src/extra/ folder for counting characters and lines, sitting at 33 and 35 lines of code, respectively. This version also has little error checking.
+
+[Here](https://github.com/dspinellis/unix-history-repo/blob/Research-V7-Snapshot-Development/usr/src/cmd/wc.c) is a version of wc from UNIX V7, at 86 lines. It allows for counting characters, words and lines. I couldn't find a version in UNIX V6, so I'm guessing this is one of the earliest versions of this program. It decides to read from stdin if the number of arguments fed to it is zero, and reads character by character using the standard C `getc` function.
+
+The busybox version ([git.busybox.net](https://git.busybox.net/busybox/tree/coreutils/wc.c)) of wc sits at 257 lines (162 with comments stripped), while striving to be [POSIX-compliant](https://pubs.opengroup.org/onlinepubs/9699919799/), meaning it has a fair number of flags and a bit of complexity. It reads character by character by using the standard `getc` function, and decides to read from stdin or not using its own `fopen_or_warn_stdin` function. It uses two GOTOs to get around, and has some incomplete Unicode support.
+
+The [plan9](https://9p.io/sources/plan9/sys/src/cmd/wc.c) version implements some sort of table method in 331 lines. It uses plan9 rather than Unix libraries and methods, and seems to read from stdin if the number of args is 0.
+
+The plan9port version of wc ([github](https://github.com/9fans/plan9port/blob/master/src/cmd/wc.c)) also implements some sort of table method, in 352 lines. It reads from stdin if the number of args is 0, and uses the Linux `read` function to read character by character.
+
+The [FreeBSD version](https://cgit.freebsd.org/src/tree/usr.bin/wc/wc.c) sits at 367 lines. It has enough new things that I can't parse all that it's doing: in lines 137-143, what is capabilities mode? what is casper?, but otherwise it decides whether to read from stdin by the number of arguments, in line 157. It uses a combination of fstat and read, depending on the type of file.
+
+Finally, the GNU utils version ([github](https://github.com/coreutils/coreutils/tree/master/src/wc.c), [savannah](http://git.savannah.gnu.org/gitweb/?p=coreutils.git;a=blob;f=src/wc.c;hb=HEAD)) is a bit over 1K lines of C. It does many things and checks many possible failure modes. I think it detects whether it should be reading from stdin using some very wrapped fstat, and it reads character by character using its own custom function.
+
+So this utility started out reasonably small, then started getting more and more complex. [The POSIX committee](https://pubs.opengroup.org/onlinepubs/9699919799/) ended up codifying that implementation, and now we are stuck with it because even implementations like busybox which strive to be quite small try to keep to POSIX.
+
+## Usage examples
+
+```
+echo "En un lugar de la Mancha" | ww
+cat README.md | ww
+ww README.md 
+ww # write something, then exit with Ctrl+D
+```
+
+## Relationship with cat-v
+
+Does one really need to spend 1k lines of C code to count characters, words and lines? There are many versions of this rant one could give, but the best and probably best known is [this one](to do: locate) by cat-v, named for the explosion of options. 
+
+[ add sad busybox comment on its cat implementation ] 
+
+## Steps:
 
 - [x] Look into how C utilities both read from stdin and from files.
 - [x] Program first version of the utility
-- [ ] Compare with other implementations, see how they do it, after I've read my own version
-  - [ ] Compare with gnu utils, 
-  - Compare with musl/busybox implementations, 
-  - Maybe make some pull requests, if I'm doing something better?
-- [ ] Install to ww, but check that ww is empty (installing to wc2 or smth would mean that you don't save that many keypresses vs wc -w)
-- [ ] ...
+- [x] Compare with other implementations, see how they do it, after I've created my own version
+  - [x] Compare with gnu utils.
+    
+  - [x] Compare with busybox implementation
+  - Compare with other projects: <https://github.com/leecannon/zig-coreutils>, <https://github.com/keiranrowan/tiny-core/tree/master>.
+- [x] Install to ww, but check that ww is empty (installing to wc2 or smth would mean that you don't save that many keypresses vs wc -w)
+- [x] Look specifically at how other versions do stuff.
+  - [x] Distinguish between reading from stdin and reading from a file
+    - If it doesn't have arguments, read from stdin. 
+  - [x] Open files, read characters.
+- [x] Write version that counts lines (lc)
+  - [ ] Take into account what happens if file doesn't end in newline.
+  - [ ] Count EOF as word & line separator
+  - [ ] Document it
+- [ ] Document reading from user-inputed stdin (end with Ctrl+D)
+- [ ] Possible follow-up: Write simple versions for other coreutils. <https://git.busybox.net/busybox/tree/coreutils/>? Would be a really nice project. 
+  - Get it working on a DuskOS/CollapseOS machine? Or, find a minimalistic kernel that could use them?
+- [ ] add chc, or charcounter (cc is "c compiler")
+- [ ] Pitch to lwn.net?
+
+Discarded:
+
+- ~~[ ] Could use zig? => Not for now~~
+- ~~Maybe make some pull requests, if I'm doing something better? => doesn't seem like it~~
+- ~~[ ] Write man files?~~

historical/LICENSES/busybox-LICENSE

@@ -0,0 +1,348 @@
+--- A note on GPL versions
+
+BusyBox is distributed under version 2 of the General Public License (included
+in its entirety, below).  Version 2 is the only version of this license which
+this version of BusyBox (or modified versions derived from this one) may be
+distributed under.
+
+------------------------------------------------------------------------
+		    GNU GENERAL PUBLIC LICENSE
+		       Version 2, June 1991
+
+ Copyright (C) 1989, 1991 Free Software Foundation, Inc.
+     51 Franklin St, Fifth Floor, Boston, MA  02110-1301  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
+freedom to share and change it.  By contrast, the GNU General Public
+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
+General Public License applies to most of the Free Software
+Foundation's software and to any other program whose authors commit to
+using it.  (Some other Free Software Foundation software is covered by
+the GNU Library General Public License instead.)  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
+if you want it, that you can change the software or use pieces of it
+in new free programs; and that you know you can do these things.
+
+  To protect your rights, we need to make restrictions that forbid
+anyone to deny you these rights or to ask you to surrender the rights.
+These restrictions translate to certain responsibilities for you if you
+distribute copies of the software, or if you modify it.
+
+  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
+you have.  You must make sure that they, too, receive or can get the
+source code.  And you must show them these terms so they know their
+rights.
+
+  We protect your rights with two steps: (1) copyright the software, and
+(2) offer you this license which gives you legal permission to copy,
+distribute and/or modify the software.
+
+  Also, for each author's protection and ours, we want to make certain
+that everyone understands that there is no warranty for this free
+software.  If the software is modified by someone else and passed on, we
+want its recipients to know that what they have is not the original, so
+that any problems introduced by others will not reflect on the original
+authors' reputations.
+
+  Finally, any free program is threatened constantly by software
+patents.  We wish to avoid the danger that redistributors of a free
+program will individually obtain patent licenses, in effect making the
+program proprietary.  To prevent this, we have made it clear that any
+patent must be licensed for everyone's free use or not licensed at all.
+
+  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
+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
+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
+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
+you may at your option offer warranty protection in exchange for a fee.
+
+  2. You may modify your copy or copies of the Program or any portion
+of it, thus forming a work based on the Program, and copy and
+distribute such modifications or work under the terms of Section 1
+above, provided that you also meet all of these conditions:
+
+    a) You must cause the modified files to carry prominent notices
+    stating that you changed the files and the date of any change.
+
+    b) You must cause any work that you distribute or publish, that in
+    whole or in part contains or is derived from the Program or any
+    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
+    when run, you must cause it, when started running for such
+    interactive use in the most ordinary way, to print or display an
+    announcement including an appropriate copyright notice and a
+    notice that there is no warranty (or else, saying that you provide
+    a warranty) and that users may redistribute the program under
+    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
+your rights to work written entirely by you; rather, the intent is to
+exercise the right to control the distribution of derivative or
+collective works based on the Program.
+
+In addition, mere aggregation of another work not based on the Program
+with the Program (or with a work based on the Program) on a volume of
+a storage or distribution medium does not bring the other work under
+the scope of this License.
+
+  3. You may copy and distribute the Program (or a work based on it,
+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
+    source code, which must be distributed under the terms of Sections
+    1 and 2 above on a medium customarily used for software interchange; or,
+
+    b) Accompany it with a written offer, valid for at least three
+    years, to give any third party, for a charge no more than your
+    cost of physically performing source distribution, a complete
+    machine-readable copy of the corresponding source code, to be
+    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
+    to distribute corresponding source code.  (This alternative is
+    allowed only for noncommercial distribution and only if you
+    received the program in object code or executable form with such
+    an offer, in accord with Subsection b above.)
+
+The source code for a work means the preferred form of the work for
+making modifications to it.  For an executable work, complete source
+code means all the source code for all modules it contains, plus any
+associated interface definition files, plus the scripts used to
+control compilation and installation of the executable.  However, as a
+special exception, the source code distributed need not include
+anything that is normally distributed (in either source or binary
+form) with the major components (compiler, kernel, and so on) of the
+operating system on which the executable runs, unless that component
+itself accompanies the executable.
+
+If distribution of executable or object code is made by offering
+access to copy from a designated place, then offering equivalent
+access to copy the source code from the same place counts as
+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
+signed it.  However, nothing else grants you permission to modify or
+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
+Program), the recipient automatically receives a license from the
+original licensor to copy, distribute or modify the Program subject to
+these terms and conditions.  You may not impose any further
+restrictions on the recipients' exercise of the rights granted herein.
+You are not responsible for enforcing compliance by third parties to
+this License.
+
+  7. If, as a consequence of a court judgment or allegation of patent
+infringement or for any other reason (not limited to patent issues),
+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
+distribute so as to satisfy simultaneously your obligations under this
+License and any other pertinent obligations, then as a consequence you
+may not distribute the Program at all.  For example, if a patent
+license would not permit royalty-free redistribution of the Program by
+all those who receive copies directly or indirectly through you, then
+the only way you could satisfy both it and this License would be to
+refrain entirely from distribution of the Program.
+
+If any portion of this section is held invalid or unenforceable under
+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
+patents or other property right claims or to contest validity of any
+such claims; this section has the sole purpose of protecting the
+integrity of the free software distribution system, which is
+implemented by public license practices.  Many people have made
+generous contributions to the wide range of software distributed
+through that system in reliance on consistent application of that
+system; it is up to the author/donor to decide if he or she is willing
+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
+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
+of the General Public License from time to time.  Such new versions will
+be similar in spirit to the present version, but may differ in detail to
+address new problems or concerns.
+
+Each version is given a distinguishing version number.  If the Program
+specifies a version number of this License which applies to it and "any
+later version", you have the option of following the terms and conditions
+either of that version or of any later version published by the Free
+Software Foundation.  If the Program does not specify a version number of
+this 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
+programs whose distribution conditions are different, write to the author
+to ask for permission.  For software which is copyrighted by the Free
+Software Foundation, write to the Free Software Foundation; we sometimes
+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
+
+  11. BECAUSE THE PROGRAM IS LICENSED FREE OF CHARGE, THERE IS NO WARRANTY
+FOR THE PROGRAM, TO THE EXTENT PERMITTED BY APPLICABLE LAW.  EXCEPT WHEN
+OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES
+PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED
+OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
+MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE.  THE ENTIRE RISK AS
+TO THE QUALITY AND PERFORMANCE OF THE PROGRAM IS WITH YOU.  SHOULD THE
+PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF ALL NECESSARY SERVICING,
+REPAIR OR CORRECTION.
+
+  12. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
+WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY AND/OR
+REDISTRIBUTE 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.
+
+		     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
+convey 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 2 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, write to the Free Software
+    Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
+
+
+Also add information on how to contact you by electronic and paper mail.
+
+If the program is interactive, make it output a short notice like this
+when it starts in an interactive mode:
+
+    Gnomovision version 69, Copyright (C) year  name of author
+    Gnomovision 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, the commands you use may
+be called something other than `show w' and `show c'; they could even be
+mouse-clicks or menu items--whatever suits your program.
+
+You should also get your employer (if you work as a programmer) or your
+school, if any, to sign a "copyright disclaimer" for the program, if
+necessary.  Here is a sample; alter the names:
+
+  Yoyodyne, Inc., hereby disclaims all copyright interest in the program
+  `Gnomovision' (which makes passes at compilers) written by James Hacker.
+
+  <signature of Ty Coon>, 1 April 1989
+  Ty Coon, President of Vice
+
+This 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 Library General
+Public License instead of this License.

historical/LICENSES/plan9-LICENSE

@@ -0,0 +1,49 @@
+Copyright © 2021 Plan 9 Foundation
+Portions Copyright © 2001-2008 Russ Cox
+Portions Copyright © 2008-2009 Google Inc.
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
+IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY
+CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
+TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
+SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+
+===================================================================
+
+This software is derived from Plan 9, originally copyright Lucent Technologies
+and distributed under the Lucent Public License, Version 1.02.
+Lucent was bought by Alcatel, which was bought by Nokia.
+On March 23, 2021, Nokia announced the transfer of the Plan 9 copyrights to the
+Plan 9 Foundation, which in turn relicensed Plan 9 under the the MIT license,
+reproduced above.
+
+There are a few exceptions, noted with LICENSE files in their own directories:
+
+The bzip2 program uses the bzip2 license; see src/cmd/bzip2/LICENSE.
+
+The fonts from Bigelow and Holmes were licensed only for Plan 9 itself,
+not for derivatives like Plan 9 from User Space.
+
+Plan 9 from User Space arranged a separate agreement with B&H to include
+the bitmap fonts in the font/luc, font/lucm, font/lucsans, and font/pelm
+directories. Other bitmap fonts have other licenses. See font/LICENSE.
+
+The Lucida Sans Unicode PostScript fonts were licensed from B&H only for Plan 9
+itself, not derivatives like Plan 9 from User Space. In their place, Plan 9 from
+User Space provides Luxi Sans, also by B&H but available under a more liberal
+license, and Deja Vu, a Unicode extension of the Bitstream Vera family of fonts.
+Luxi Sans is similar to Lucida Sans, but it has no Unicode support.
+Deja Vu does have good Unicode support.

historical/LICENSES/plan9port-LICENSE

@@ -0,0 +1,49 @@
+Copyright © 2021 Plan 9 Foundation
+Portions Copyright © 2001-2008 Russ Cox
+Portions Copyright © 2008-2009 Google Inc.
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
+IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY
+CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
+TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
+SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+
+===================================================================
+
+This software is derived from Plan 9, originally copyright Lucent Technologies
+and distributed under the Lucent Public License, Version 1.02.
+Lucent was bought by Alcatel, which was bought by Nokia.
+On March 23, 2021, Nokia announced the transfer of the Plan 9 copyrights to the
+Plan 9 Foundation, which in turn relicensed Plan 9 under the the MIT license,
+reproduced above.
+
+There are a few exceptions, noted with LICENSE files in their own directories:
+
+The bzip2 program uses the bzip2 license; see src/cmd/bzip2/LICENSE.
+
+The fonts from Bigelow and Holmes were licensed only for Plan 9 itself,
+not for derivatives like Plan 9 from User Space.
+
+Plan 9 from User Space arranged a separate agreement with B&H to include
+the bitmap fonts in the font/luc, font/lucm, font/lucsans, and font/pelm
+directories. Other bitmap fonts have other licenses. See font/LICENSE.
+
+The Lucida Sans Unicode PostScript fonts were licensed from B&H only for Plan 9
+itself, not derivatives like Plan 9 from User Space. In their place, Plan 9 from
+User Space provides Luxi Sans, also by B&H but available under a more liberal
+license, and Deja Vu, a Unicode extension of the Bitstream Vera family of fonts.
+Luxi Sans is similar to Lucida Sans, but it has no Unicode support.
+Deja Vu does have good Unicode support.

historical/busybox-wc.c

@@ -0,0 +1,257 @@
+/* vi: set sw=4 ts=4: */
+/*
+ * wc implementation for busybox
+ *
+ * Copyright (C) 2003  Manuel Novoa III  <mjn3@codepoet.org>
+ *
+ * Licensed under GPLv2 or later, see file LICENSE in this source tree.
+ */
+/* Mar 16, 2003      Manuel Novoa III   (mjn3@codepoet.org)
+ *
+ * Rewritten to fix a number of problems and do some size optimizations.
+ * Problems in the previous busybox implementation (besides bloat) included:
+ *  1) broken 'wc -c' optimization (read note below)
+ *  2) broken handling of '-' args
+ *  3) no checking of ferror on EOF returns
+ *  4) isprint() wasn't considered when word counting.
+ *
+ * NOTES:
+ *
+ * The previous busybox wc attempted an optimization using stat for the
+ * case of counting chars only.  I omitted that because it was broken.
+ * It didn't take into account the possibility of input coming from a
+ * pipe, or input from a file with file pointer not at the beginning.
+ *
+ * To implement such a speed optimization correctly, not only do you
+ * need the size, but also the file position.  Note also that the
+ * file position may be past the end of file.  Consider the example
+ * (adapted from example in gnu wc.c)
+ *
+ *      echo hello > /tmp/testfile &&
+ *      (dd ibs=1k skip=1 count=0 &> /dev/null; wc -c) < /tmp/testfile
+ *
+ * for which 'wc -c' should output '0'.
+ */
+//config:config WC
+//config:	bool "wc (4.7 kb)"
+//config:	default y
+//config:	help
+//config:	wc is used to print the number of bytes, words, and lines,
+//config:	in specified files.
+//config:
+//config:config FEATURE_WC_LARGE
+//config:	bool "Support very large counts"
+//config:	default y
+//config:	depends on WC
+//config:	help
+//config:	Use "unsigned long long" for counter variables.
+
+//applet:IF_WC(APPLET(wc, BB_DIR_USR_BIN, BB_SUID_DROP))
+
+//kbuild:lib-$(CONFIG_WC) += wc.o
+
+/* BB_AUDIT SUSv3 compliant. */
+/* http://www.opengroup.org/onlinepubs/007904975/utilities/wc.html */
+
+#include "libbb.h"
+#include "unicode.h"
+
+#if !ENABLE_LOCALE_SUPPORT
+# undef isprint
+# undef isspace
+# define isprint(c) ((unsigned)((c) - 0x20) <= (0x7e - 0x20))
+# define isspace(c) ((c) == ' ')
+#endif
+
+#if ENABLE_FEATURE_WC_LARGE
+# define COUNT_T unsigned long long
+# define COUNT_FMT "llu"
+#else
+# define COUNT_T unsigned
+# define COUNT_FMT "u"
+#endif
+
+/* We support -m even when UNICODE_SUPPORT is off,
+ * we just don't advertise it in help text,
+ * since it is the same as -c in this case.
+ */
+
+//usage:#define wc_trivial_usage
+//usage:       "[-c"IF_UNICODE_SUPPORT("m")"lwL] [FILE]..."
+//usage:
+//usage:#define wc_full_usage "\n\n"
+//usage:       "Count lines, words, and bytes for FILEs (or stdin)\n"
+//usage:     "\n	-c	Count bytes"
+//usage:	IF_UNICODE_SUPPORT(
+//usage:     "\n	-m	Count characters"
+//usage:	)
+//usage:     "\n	-l	Count newlines"
+//usage:     "\n	-w	Count words"
+//usage:     "\n	-L	Print longest line length"
+//usage:
+//usage:#define wc_example_usage
+//usage:       "$ wc /etc/passwd\n"
+//usage:       "     31      46    1365 /etc/passwd\n"
+
+/* Order is important if we want to be compatible with
+ * column order in "wc -cmlwL" output:
+ */
+enum {
+	WC_LINES    = 0, /* -l */
+	WC_WORDS    = 1, /* -w */
+	WC_UNICHARS = 2, /* -m */
+	WC_BYTES    = 3, /* -c */
+	WC_LENGTH   = 4, /* -L */
+	NUM_WCS     = 5,
+};
+
+int wc_main(int argc, char **argv) MAIN_EXTERNALLY_VISIBLE;
+int wc_main(int argc UNUSED_PARAM, char **argv)
+{
+	const char *arg;
+	const char *start_fmt = " %9"COUNT_FMT + 1;
+	const char *fname_fmt = " %s\n";
+	COUNT_T *pcounts;
+	COUNT_T counts[NUM_WCS];
+	COUNT_T totals[NUM_WCS];
+	int num_files;
+	smallint status = EXIT_SUCCESS;
+	unsigned print_type;
+
+	init_unicode();
+
+	print_type = getopt32(argv, "lwmcL");
+
+	if (print_type == 0) {
+		print_type = (1 << WC_LINES) | (1 << WC_WORDS) | (1 << WC_BYTES);
+	}
+
+	argv += optind;
+	if (!argv[0]) {
+		*--argv = (char *) bb_msg_standard_input;
+		fname_fmt = "\n";
+	}
+	if (!argv[1]) { /* zero or one filename? */
+		if (!((print_type-1) & print_type)) /* exactly one option? */
+			start_fmt = "%"COUNT_FMT;
+	}
+
+	memset(totals, 0, sizeof(totals));
+
+	pcounts = counts;
+
+	num_files = 0;
+	while ((arg = *argv++) != NULL) {
+		FILE *fp;
+		const char *s;
+		unsigned u;
+		unsigned linepos;
+		smallint in_word;
+
+		++num_files;
+		fp = fopen_or_warn_stdin(arg);
+		if (!fp) {
+			status = EXIT_FAILURE;
+			continue;
+		}
+
+		memset(counts, 0, sizeof(counts));
+		linepos = 0;
+		in_word = 0;
+
+		while (1) {
+			int c;
+			/* Our -w doesn't match GNU wc exactly... oh well */
+
+			c = getc(fp);
+			if (c == EOF) {
+				if (ferror(fp)) {
+					bb_simple_perror_msg(arg);
+					status = EXIT_FAILURE;
+				}
+				goto DO_EOF;  /* Treat an EOF as '\r'. */
+			}
+
+			/* Cater for -c and -m */
+			++counts[WC_BYTES];
+			if (unicode_status != UNICODE_ON /* every byte is a new char */
+			 || (c & 0xc0) != 0x80 /* it isn't a 2nd+ byte of a Unicode char */
+			) {
+				++counts[WC_UNICHARS];
+			}
+
+			if (isprint_asciionly(c)) { /* FIXME: not unicode-aware */
+				++linepos;
+				if (!isspace(c)) {
+					in_word = 1;
+					continue;
+				}
+			} else if ((unsigned)(c - 9) <= 4) {
+				/* \t  9
+				 * \n 10
+				 * \v 11
+				 * \f 12
+				 * \r 13
+				 */
+				if (c == '\t') {
+					linepos = (linepos | 7) + 1;
+				} else {  /* '\n', '\r', '\f', or '\v' */
+ DO_EOF:
+					if (linepos > counts[WC_LENGTH]) {
+						counts[WC_LENGTH] = linepos;
+					}
+					if (c == '\n') {
+						++counts[WC_LINES];
+					}
+					if (c != '\v') {
+						linepos = 0;
+					}
+				}
+			} else {
+				continue;
+			}
+
+			counts[WC_WORDS] += in_word;
+			in_word = 0;
+			if (c == EOF) {
+				break;
+			}
+		}
+
+		fclose_if_not_stdin(fp);
+
+		if (totals[WC_LENGTH] < counts[WC_LENGTH]) {
+			totals[WC_LENGTH] = counts[WC_LENGTH];
+		}
+		totals[WC_LENGTH] -= counts[WC_LENGTH];
+
+ OUTPUT:
+		/* coreutils wc tries hard to print pretty columns
+		 * (saves results for all files, finds max col len etc...)
+		 * we won't try that hard, it will bloat us too much */
+		s = start_fmt;
+		u = 0;
+		do {
+			if (print_type & (1 << u)) {
+				printf(s, pcounts[u]);
+				s = " %9"COUNT_FMT; /* Ok... restore the leading space. */
+			}
+			totals[u] += pcounts[u];
+		} while (++u < NUM_WCS);
+		printf(fname_fmt, arg);
+	}
+
+	/* If more than one file was processed, we want the totals.  To save some
+	 * space, we set the pcounts ptr to the totals array.  This has the side
+	 * effect of trashing the totals array after outputting it, but that's
+	 * irrelavent since we no longer need it. */
+	if (num_files > 1) {
+		num_files = 0;  /* Make sure we don't get here again. */
+		arg = "total";
+		pcounts = totals;
+		--argv;
+		goto OUTPUT;
+	}
+
+	fflush_stdout_and_exit(status);
+}

historical/busybox-wc_comments_stripped.c

@@ -0,0 +1,165 @@
+#include "libbb.h"
+#include "unicode.h"
+
+/* Copyright (C) 2003  Manuel Novoa III  <mjn3@codepoet.org>
+/*
+/* Licensed under GPLv2 or later, see file LICENSE in this source tree.
+#if !ENABLE_LOCALE_SUPPORT
+# undef isprint
+# undef isspace
+# define isprint(c) ((unsigned)((c) - 0x20) <= (0x7e - 0x20))
+# define isspace(c) ((c) == ' ')
+#endif
+
+#if ENABLE_FEATURE_WC_LARGE
+# define COUNT_T unsigned long long
+# define COUNT_FMT "llu"
+#else
+# define COUNT_T unsigned
+# define COUNT_FMT "u"
+#endif
+
+enum {
+	WC_LINES    = 0, /* -l */
+	WC_WORDS    = 1, /* -w */
+	WC_UNICHARS = 2, /* -m */
+	WC_BYTES    = 3, /* -c */
+	WC_LENGTH   = 4, /* -L */
+	NUM_WCS     = 5,
+};
+
+int wc_main(int argc, char **argv) MAIN_EXTERNALLY_VISIBLE;
+int wc_main(int argc UNUSED_PARAM, char **argv)
+{
+	const char *arg;
+	const char *start_fmt = " %9"COUNT_FMT + 1;
+	const char *fname_fmt = " %s\n";
+	COUNT_T *pcounts;
+	COUNT_T counts[NUM_WCS];
+	COUNT_T totals[NUM_WCS];
+	int num_files;
+	smallint status = EXIT_SUCCESS;
+	unsigned print_type;
+
+	init_unicode();
+
+	print_type = getopt32(argv, "lwmcL");
+
+	if (print_type == 0) {
+		print_type = (1 << WC_LINES) | (1 << WC_WORDS) | (1 << WC_BYTES);
+	}
+
+	argv += optind;
+	if (!argv[0]) {
+		*--argv = (char *) bb_msg_standard_input;
+		fname_fmt = "\n";
+	}
+	if (!argv[1]) { /* zero or one filename? */
+		if (!((print_type-1) & print_type)) /* exactly one option? */
+			start_fmt = "%"COUNT_FMT;
+	}
+
+	memset(totals, 0, sizeof(totals));
+
+	pcounts = counts;
+
+	num_files = 0;
+	while ((arg = *argv++) != NULL) {
+		FILE *fp;
+		const char *s;
+		unsigned u;
+		unsigned linepos;
+		smallint in_word;
+
+		++num_files;
+		fp = fopen_or_warn_stdin(arg);
+		if (!fp) {
+			status = EXIT_FAILURE;
+			continue;
+		}
+
+		memset(counts, 0, sizeof(counts));
+		linepos = 0;
+		in_word = 0;
+
+		while (1) {
+			int c;
+
+			c = getc(fp);
+			if (c == EOF) {
+				if (ferror(fp)) {
+					bb_simple_perror_msg(arg);
+					status = EXIT_FAILURE;
+				}
+				goto DO_EOF;  /* Treat an EOF as '\r'. */
+			}
+
+			++counts[WC_BYTES];
+			if (unicode_status != UNICODE_ON /* every byte is a new char */
+			 || (c & 0xc0) != 0x80 /* it isn't a 2nd+ byte of a Unicode char */
+			) {
+				++counts[WC_UNICHARS];
+			}
+
+			if (isprint_asciionly(c)) { /* FIXME: not unicode-aware */
+				++linepos;
+				if (!isspace(c)) {
+					in_word = 1;
+					continue;
+				}
+			} else if ((unsigned)(c - 9) <= 4) {
+				if (c == '\t') {
+					linepos = (linepos | 7) + 1;
+				} else {  /* '\n', '\r', '\f', or '\v' */
+ DO_EOF:
+					if (linepos > counts[WC_LENGTH]) {
+						counts[WC_LENGTH] = linepos;
+					}
+					if (c == '\n') {
+						++counts[WC_LINES];
+					}
+					if (c != '\v') {
+						linepos = 0;
+					}
+				}
+			} else {
+				continue;
+			}
+
+			counts[WC_WORDS] += in_word;
+			in_word = 0;
+			if (c == EOF) {
+				break;
+			}
+		}
+
+		fclose_if_not_stdin(fp);
+
+		if (totals[WC_LENGTH] < counts[WC_LENGTH]) {
+			totals[WC_LENGTH] = counts[WC_LENGTH];
+		}
+		totals[WC_LENGTH] -= counts[WC_LENGTH];
+
+ OUTPUT:
+		s = start_fmt;
+		u = 0;
+		do {
+			if (print_type & (1 << u)) {
+				printf(s, pcounts[u]);
+				s = " %9"COUNT_FMT; /* Ok... restore the leading space. */
+			}
+			totals[u] += pcounts[u];
+		} while (++u < NUM_WCS);
+		printf(fname_fmt, arg);
+	}
+
+	if (num_files > 1) {
+		num_files = 0;  /* Make sure we don't get here again. */
+		arg = "total";
+		pcounts = totals;
+		--argv;
+		goto OUTPUT;
+	}
+
+	fflush_stdout_and_exit(status);
+}

historical/openbsd-wc.c

@@ -0,0 +1,304 @@
+/*	$OpenBSD: wc.c,v 1.31 2022/12/04 23:50:50 cheloha Exp $	*/
+
+/*
+ * Copyright (c) 1980, 1987, 1991, 1993
+ *	The Regents of the University of California.  All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the name of the University nor the names of its contributors
+ *    may be used to endorse or promote products derived from this software
+ *    without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE.
+ */
+
+#include <sys/stat.h>
+
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <locale.h>
+#include <ctype.h>
+#include <err.h>
+#include <unistd.h>
+#include <util.h>
+#include <wchar.h>
+#include <wctype.h>
+
+#define	_MAXBSIZE (64 * 1024)
+
+int64_t	tlinect, twordct, tcharct;
+int	doline, doword, dochar, humanchar, multibyte;
+int	rval;
+extern char *__progname;
+
+static void print_counts(int64_t, int64_t, int64_t, const char *);
+static void format_and_print(int64_t);
+static void cnt(const char *);
+
+int
+main(int argc, char *argv[])
+{
+	int ch;
+
+	setlocale(LC_CTYPE, "");
+
+	if (pledge("stdio rpath", NULL) == -1)
+		err(1, "pledge");
+
+	while ((ch = getopt(argc, argv, "lwchm")) != -1)
+		switch(ch) {
+		case 'l':
+			doline = 1;
+			break;
+		case 'w':
+			doword = 1;
+			break;
+		case 'm':
+			if (MB_CUR_MAX > 1)
+				multibyte = 1;
+			/* FALLTHROUGH */
+		case 'c':
+			dochar = 1;
+			break;
+		case 'h':
+			humanchar = 1;
+			break;
+		default:
+			fprintf(stderr,
+			    "usage: %s [-c | -m] [-hlw] [file ...]\n",
+			    __progname);
+			return 1;
+		}
+	argv += optind;
+	argc -= optind;
+
+	/*
+	 * wc is unusual in that its flags are on by default, so,
+	 * if you don't get any arguments, you have to turn them
+	 * all on.
+	 */
+	if (!doline && !doword && !dochar)
+		doline = doword = dochar = 1;
+
+	if (!*argv) {
+		cnt(NULL);
+	} else {
+		int dototal = (argc > 1);
+
+		do {
+			cnt(*argv);
+		} while(*++argv);
+
+		if (dototal)
+			print_counts(tlinect, twordct, tcharct, "total");
+	}
+
+	return rval;
+}
+
+static void
+cnt(const char *path)
+{
+	static char *buf;
+	static size_t bufsz;
+
+	FILE *stream;
+	const char *file;
+	char *C;
+	wchar_t wc;
+	short gotsp;
+	ssize_t len;
+	int64_t linect, wordct, charct;
+	struct stat sbuf;
+	int fd;
+
+	linect = wordct = charct = 0;
+	stream = NULL;
+	if (path != NULL) {
+		file = path;
+		if ((fd = open(file, O_RDONLY)) == -1) {
+			warn("%s", file);
+			rval = 1;
+			return;
+		}
+	} else  {
+		file = "(stdin)";
+		fd = STDIN_FILENO;
+	}
+
+	if (!multibyte) {
+		if (bufsz < _MAXBSIZE &&
+		    (buf = realloc(buf, _MAXBSIZE)) == NULL)
+			err(1, NULL);
+
+		/*
+		 * According to POSIX, a word is a "maximal string of
+		 * characters delimited by whitespace."  Nothing is said
+		 * about a character being printing or non-printing.
+		 */
+		if (doword) {
+			gotsp = 1;
+			while ((len = read(fd, buf, _MAXBSIZE)) > 0) {
+				charct += len;
+				for (C = buf; len--; ++C) {
+					if (isspace((unsigned char)*C)) {
+						gotsp = 1;
+						if (*C == '\n')
+							++linect;
+					} else if (gotsp) {
+						gotsp = 0;
+						++wordct;
+					}
+				}
+			}
+			if (len == -1) {
+				warn("%s", file);
+				rval = 1;
+			}
+		}
+		/*
+		 * Line counting is split out because it's a lot
+		 * faster to get lines than to get words, since
+		 * the word count requires some logic.
+		 */
+		else if (doline) {
+			while ((len = read(fd, buf, _MAXBSIZE)) > 0) {
+				charct += len;
+				for (C = buf; len--; ++C)
+					if (*C == '\n')
+						++linect;
+			}
+			if (len == -1) {
+				warn("%s", file);
+				rval = 1;
+			}
+		}
+		/*
+		 * If all we need is the number of characters and
+		 * it's a directory or a regular or linked file, just
+		 * stat the puppy.  We avoid testing for it not being
+		 * a special device in case someone adds a new type
+		 * of inode.
+		 */
+		else if (dochar) {
+			mode_t ifmt;
+
+			if (fstat(fd, &sbuf)) {
+				warn("%s", file);
+				rval = 1;
+			} else {
+				ifmt = sbuf.st_mode & S_IFMT;
+				if (ifmt == S_IFREG || ifmt == S_IFLNK
+				    || ifmt == S_IFDIR) {
+					charct = sbuf.st_size;
+				} else {
+					while ((len = read(fd, buf, _MAXBSIZE)) > 0)
+						charct += len;
+					if (len == -1) {
+						warn("%s", file);
+						rval = 1;
+					}
+				}
+			}
+		}
+	} else {
+		if (path == NULL)
+			stream = stdin;
+		else if ((stream = fdopen(fd, "r")) == NULL) {
+			warn("%s", file);
+			close(fd);
+			rval = 1;
+			return;
+		}
+
+		gotsp = 1;
+		while ((len = getline(&buf, &bufsz, stream)) > 0) {
+			const char *end = buf + len;
+			for (C = buf; C < end; C += len) {
+				++charct;
+				len = mbtowc(&wc, C, MB_CUR_MAX);
+				if (len == -1) {
+					mbtowc(NULL, NULL,
+					    MB_CUR_MAX);
+					len = 1;
+					wc = L'?';
+				} else if (len == 0)
+					len = 1;
+				if (iswspace(wc)) {
+					gotsp = 1;
+					if (wc == L'\n')
+						++linect;
+				} else if (gotsp) {
+					gotsp = 0;
+					++wordct;
+				}
+			}
+		}
+		if (ferror(stream)) {
+			warn("%s", file);
+			rval = 1;
+		}
+	}
+
+	print_counts(linect, wordct, charct, path);
+
+	/*
+	 * Don't bother checking doline, doword, or dochar -- speeds
+	 * up the common case
+	 */
+	tlinect += linect;
+	twordct += wordct;
+	tcharct += charct;
+
+	if ((stream == NULL ? close(fd) : fclose(stream)) != 0) {
+		warn("%s", file);
+		rval = 1;
+	}
+}
+
+static void
+format_and_print(int64_t v)
+{
+	if (humanchar) {
+		char result[FMT_SCALED_STRSIZE];
+
+		fmt_scaled((long long)v, result);
+		printf("%7s", result);
+	} else {
+		printf(" %7lld", v);
+	}
+}
+
+static void
+print_counts(int64_t lines, int64_t words, int64_t chars, const char *name)
+{
+	if (doline)
+		format_and_print(lines);
+	if (doword)
+		format_and_print(words);
+	if (dochar)
+		format_and_print(chars);
+
+	if (name)
+		printf(" %s\n", name);
+	else
+		printf("\n");
+}

historical/plan9-wc.c

@@ -0,0 +1,118 @@
+/*
+ * Count bytes within runes, if it fits in a uvlong, and other things.
+ */
+#include <u.h>
+#include <libc.h>
+#include <bio.h>
+
+/* flags, per-file counts, and total counts */
+static int pline, pword, prune, pbadr, pchar;
+static uvlong nline, nword, nrune, nbadr, nchar;
+static uvlong tnline, tnword, tnrune, tnbadr, tnchar;
+
+enum{Space, Word};
+
+static void
+wc(Biobuf *bin)
+{
+	int where;
+	long r;
+
+	nline = 0;
+	nword = 0;
+	nrune = 0;
+	nbadr = 0;
+	where = Space;
+	while ((long)(r = Bgetrune(bin)) >= 0) {
+		nrune++;
+		if(r == Runeerror) {
+			nbadr++;
+			continue;
+		}
+		if(r == '\n')
+			nline++;
+		if(where == Word){
+			if(isspacerune(r))
+				where = Space;
+		}else
+			if(isspacerune(r) == 0){
+				where = Word;
+				nword++;
+			}
+	}
+	nchar = Boffset(bin);
+	tnline += nline;
+	tnword += nword;
+	tnrune += nrune;
+	tnbadr += nbadr;
+	tnchar += nchar;
+}
+
+static void
+report(uvlong nline, uvlong nword, uvlong nrune, uvlong nbadr, uvlong nchar, char *fname)
+{
+	char line[1024], *s, *e;
+
+	s = line;
+	e = line + sizeof line;
+	line[0] = 0;
+	if(pline)
+		s = seprint(s, e, " %7llud", nline);
+	if(pword)
+		s = seprint(s, e, " %7llud", nword);
+	if(prune)
+		s = seprint(s, e, " %7llud", nrune);
+	if(pbadr)
+		s = seprint(s, e, " %7llud", nbadr);
+	if(pchar)
+		s = seprint(s, e, " %7llud", nchar);
+	if(fname != nil)
+		seprint(s, e, " %s",   fname);
+	print("%s\n", line+1);
+}
+
+void
+main(int argc, char *argv[])
+{
+	char *sts;
+	Biobuf sin, *bin;
+	int i;
+
+	sts = nil;
+	ARGBEGIN {
+	case 'l': pline++; break;
+	case 'w': pword++; break;
+	case 'r': prune++; break;
+	case 'b': pbadr++; break;
+	case 'c': pchar++; break;
+	default:
+		fprint(2, "Usage: %s [-lwrbc] [file ...]\n", argv0);
+		exits("usage");
+	} ARGEND
+	if(pline+pword+prune+pbadr+pchar == 0){
+		pline = 1;
+		pword = 1;
+		pchar = 1;
+	}
+	if(argc == 0){
+		Binit(&sin, 0, OREAD);
+		wc(&sin);
+		report(nline, nword, nrune, nbadr, nchar, nil);
+		Bterm(&sin);
+	}else{
+		for(i = 0; i < argc; i++){
+			bin = Bopen(argv[i], OREAD);
+			if(bin == nil){
+				perror(argv[i]);
+				sts = "can't open";
+				continue;
+			}
+			wc(bin);
+			report(nline, nword, nrune, nbadr, nchar, argv[i]);
+			Bterm(bin);
+		}
+		if(argc>1)
+			report(tnline, tnword, tnrune, tnbadr, tnchar, "total");
+	}
+	exits(sts);
+}

historical/plan9port-wc.c

@@ -0,0 +1,352 @@
+/*
+ * wc -- count things in utf-encoded text files
+ * Bugs:
+ *	The only white space characters recognized are ' ', '\t' and '\n', even though
+ *	ISO 10646 has many more blanks scattered through it.
+ *	Should count characters that cannot occur in any rune (hex f0-ff) separately.
+ *	Should count non-canonical runes (e.g. hex c1,80 instead of hex 40).
+ */
+#include <u.h>
+#include <libc.h>
+#define	NBUF	(8*1024)
+uvlong nline, tnline, pline;
+uvlong nword, tnword, pword;
+uvlong nrune, tnrune, prune;
+uvlong nbadr, tnbadr, pbadr;
+uvlong nchar, tnchar, pchar;
+void count(int, char *);
+void report(uvlong, uvlong, uvlong, uvlong, uvlong, char *);
+void
+main(int argc, char *argv[])
+{
+	char *status="";
+	int i, f;
+	ARGBEGIN {
+	case 'l': pline++; break;
+	case 'w': pword++; break;
+	case 'r': prune++; break;
+	case 'b': pbadr++; break;
+	case 'c': pchar++; break;
+	default:
+		fprint(2, "Usage: %s [-lwrbc] [file ...]\n", argv0);
+		exits("usage");
+	} ARGEND
+	if(pline+pword+prune+pbadr+pchar == 0) {
+		pline = 1;
+		pword = 1;
+		pchar = 1;
+	}
+	if(argc==0)
+		count(0, 0);
+	else{
+		for(i=0;i<argc;i++){
+			f=open(argv[i], OREAD);
+			if(f<0){
+				perror(argv[i]);
+				status="can't open";
+			}
+			else{
+				count(f, argv[i]);
+				tnline+=nline;
+				tnword+=nword;
+				tnrune+=nrune;
+				tnbadr+=nbadr;
+				tnchar+=nchar;
+				close(f);
+			}
+		}
+		if(argc>1)
+			report(tnline, tnword, tnrune, tnbadr, tnchar, "total");
+	}
+	exits(status);
+}
+void
+report(uvlong nline, uvlong nword, uvlong nrune, uvlong nbadr, uvlong nchar, char *fname)
+{
+	char line[1024], word[128];
+	line[0] = '\0';
+	if(pline){
+		sprint(word, " %7llud", nline);
+		strcat(line, word);
+	}
+	if(pword){
+		sprint(word, " %7llud", nword);
+		strcat(line, word);
+	}
+	if(prune){
+		sprint(word, " %7llud", nrune);
+		strcat(line, word);
+	}
+	if(pbadr){
+		sprint(word, " %7llud", nbadr);
+		strcat(line, word);
+	}
+	if(pchar){
+		sprint(word, " %7llud", nchar);
+		strcat(line, word);
+	}
+	if(fname){
+		sprint(word, " %s",   fname);
+		strcat(line, word);
+	}
+	print("%s\n", line+1);
+}
+/*
+ * How it works.  Start in statesp.  Each time we read a character,
+ * increment various counts, and do state transitions according to the
+ * following table.  If we're not in statesp or statewd when done, the
+ * file ends with a partial rune.
+ *        |                character
+ *  state |09,20| 0a  |00-7f|80-bf|c0-df|e0-ef|f0-f7|f8-ff
+ * -------+-----+-----+-----+-----+-----+-----+-----+-----
+ * statesp|ASP  |ASPN |AWDW |AWDWX|AC2W |AC3W |AC4W |AWDWX
+ * statewd|ASP  |ASPN |AWD  |AWDX |AC2  |AC3  |AC4  |AWDX
+ * statec2|ASPX |ASPNX|AWDX |AWDR |AC2X |AC3X |AC4X |AWDX
+ * statec3|ASPX |ASPNX|AWDX |AC2R |AC2X |AC3X |AC4X |AWDX
+ * statec4|ASPX |ASPNX|AWDX |AC3R |AC2X |AC3X |AC4X |AWDX	f4 8f bf bf
+ */
+enum{			/* actions */
+	AC2,		/* enter statec2 */
+	AC2R,		/* enter statec2, don't count a rune */
+	AC2W,		/* enter statec2, count a word */
+	AC2X,		/* enter statec2, count a bad rune */
+	AC3,		/* enter statec3 */
+	AC3R,		/* enter statec3, don't count a rune */
+	AC3W,		/* enter statec3, count a word */
+	AC3X,		/* enter statec3, count a bad rune */
+	AC4,		/* enter statec4 */
+	AC4W,		/* enter statec4, count a word */
+	AC4X,		/* enter statec4, count a bad rune */
+	ASP,		/* enter statesp */
+	ASPN,		/* enter statesp, count a newline */
+	ASPNX,		/* enter statesp, count a newline, count a bad rune */
+	ASPX,		/* enter statesp, count a bad rune */
+	AWD,		/* enter statewd */
+	AWDR,		/* enter statewd, don't count a rune */
+	AWDW,		/* enter statewd, count a word */
+	AWDWX,		/* enter statewd, count a word, count a bad rune */
+	AWDX,		/* enter statewd, count a bad rune */
+};
+uchar statesp[256]={	/* looking for the start of a word */
+AWDW, AWDW, AWDW, AWDW, AWDW, AWDW, AWDW, AWDW,	/* 00-07 */
+AWDW, ASP,  ASPN, AWDW, AWDW, AWDW, AWDW, AWDW,	/* 08-0f */
+AWDW, AWDW, AWDW, AWDW, AWDW, AWDW, AWDW, AWDW,	/* 10-17 */
+AWDW, AWDW, AWDW, AWDW, AWDW, AWDW, AWDW, AWDW,	/* 18-1f */
+ASP,  AWDW, AWDW, AWDW, AWDW, AWDW, AWDW, AWDW,	/* 20-27 */
+AWDW, AWDW, AWDW, AWDW, AWDW, AWDW, AWDW, AWDW,	/* 28-2f */
+AWDW, AWDW, AWDW, AWDW, AWDW, AWDW, AWDW, AWDW,	/* 30-37 */
+AWDW, AWDW, AWDW, AWDW, AWDW, AWDW, AWDW, AWDW,	/* 38-3f */
+AWDW, AWDW, AWDW, AWDW, AWDW, AWDW, AWDW, AWDW,	/* 40-47 */
+AWDW, AWDW, AWDW, AWDW, AWDW, AWDW, AWDW, AWDW,	/* 48-4f */
+AWDW, AWDW, AWDW, AWDW, AWDW, AWDW, AWDW, AWDW,	/* 50-57 */
+AWDW, AWDW, AWDW, AWDW, AWDW, AWDW, AWDW, AWDW,	/* 58-5f */
+AWDW, AWDW, AWDW, AWDW, AWDW, AWDW, AWDW, AWDW,	/* 60-67 */
+AWDW, AWDW, AWDW, AWDW, AWDW, AWDW, AWDW, AWDW,	/* 68-6f */
+AWDW, AWDW, AWDW, AWDW, AWDW, AWDW, AWDW, AWDW,	/* 70-77 */
+AWDW, AWDW, AWDW, AWDW, AWDW, AWDW, AWDW, AWDW,	/* 78-7f */
+AWDWX,AWDWX,AWDWX,AWDWX,AWDWX,AWDWX,AWDWX,AWDWX,/* 80-87 */
+AWDWX,AWDWX,AWDWX,AWDWX,AWDWX,AWDWX,AWDWX,AWDWX,/* 88-8f */
+AWDWX,AWDWX,AWDWX,AWDWX,AWDWX,AWDWX,AWDWX,AWDWX,/* 90-97 */
+AWDWX,AWDWX,AWDWX,AWDWX,AWDWX,AWDWX,AWDWX,AWDWX,/* 98-9f */
+AWDWX,AWDWX,AWDWX,AWDWX,AWDWX,AWDWX,AWDWX,AWDWX,/* a0-a7 */
+AWDWX,AWDWX,AWDWX,AWDWX,AWDWX,AWDWX,AWDWX,AWDWX,/* a8-af */
+AWDWX,AWDWX,AWDWX,AWDWX,AWDWX,AWDWX,AWDWX,AWDWX,/* b0-b7 */
+AWDWX,AWDWX,AWDWX,AWDWX,AWDWX,AWDWX,AWDWX,AWDWX,/* b8-bf */
+AC2W, AC2W, AC2W, AC2W, AC2W, AC2W, AC2W, AC2W,	/* c0-c7 */
+AC2W, AC2W, AC2W, AC2W, AC2W, AC2W, AC2W, AC2W,	/* c8-cf */
+AC2W, AC2W, AC2W, AC2W, AC2W, AC2W, AC2W, AC2W,	/* d0-d7 */
+AC2W, AC2W, AC2W, AC2W, AC2W, AC2W, AC2W, AC2W,	/* d8-df */
+AC3W, AC3W, AC3W, AC3W, AC3W, AC3W, AC3W, AC3W,	/* e0-e7 */
+AC3W, AC3W, AC3W, AC3W, AC3W, AC3W, AC3W, AC3W,	/* e8-ef */
+AC4W, AC4W, AC4W, AC4W, AC4W, AC4W, AC4W, AC4W, /* f0-f7 */
+AWDWX,AWDWX,AWDWX,AWDWX,AWDWX,AWDWX,AWDWX,AWDWX,/* f8-ff */
+};
+uchar statewd[256]={	/* looking for the next character in a word */
+AWD,  AWD,  AWD,  AWD,  AWD,  AWD,  AWD,  AWD,	/* 00-07 */
+AWD,  ASP,  ASPN, AWD,  AWD,  AWD,  AWD,  AWD,	/* 08-0f */
+AWD,  AWD,  AWD,  AWD,  AWD,  AWD,  AWD,  AWD,	/* 10-17 */
+AWD,  AWD,  AWD,  AWD,  AWD,  AWD,  AWD,  AWD,	/* 18-1f */
+ASP,  AWD,  AWD,  AWD,  AWD,  AWD,  AWD,  AWD,	/* 20-27 */
+AWD,  AWD,  AWD,  AWD,  AWD,  AWD,  AWD,  AWD,	/* 28-2f */
+AWD,  AWD,  AWD,  AWD,  AWD,  AWD,  AWD,  AWD,	/* 30-37 */
+AWD,  AWD,  AWD,  AWD,  AWD,  AWD,  AWD,  AWD,	/* 38-3f */
+AWD,  AWD,  AWD,  AWD,  AWD,  AWD,  AWD,  AWD,	/* 40-47 */
+AWD,  AWD,  AWD,  AWD,  AWD,  AWD,  AWD,  AWD,	/* 48-4f */
+AWD,  AWD,  AWD,  AWD,  AWD,  AWD,  AWD,  AWD,	/* 50-57 */
+AWD,  AWD,  AWD,  AWD,  AWD,  AWD,  AWD,  AWD,	/* 58-5f */
+AWD,  AWD,  AWD,  AWD,  AWD,  AWD,  AWD,  AWD,	/* 60-67 */
+AWD,  AWD,  AWD,  AWD,  AWD,  AWD,  AWD,  AWD,	/* 68-6f */
+AWD,  AWD,  AWD,  AWD,  AWD,  AWD,  AWD,  AWD,	/* 70-77 */
+AWD,  AWD,  AWD,  AWD,  AWD,  AWD,  AWD,  AWD,	/* 78-7f */
+AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX,	/* 80-87 */
+AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX,	/* 88-8f */
+AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX,	/* 90-97 */
+AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX,	/* 98-9f */
+AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX,	/* a0-a7 */
+AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX,	/* a8-af */
+AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX,	/* b0-b7 */
+AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX,	/* b8-bf */
+AC2,  AC2,  AC2,  AC2,  AC2,  AC2,  AC2,  AC2,	/* c0-c7 */
+AC2,  AC2,  AC2,  AC2,  AC2,  AC2,  AC2,  AC2,	/* c8-cf */
+AC2,  AC2,  AC2,  AC2,  AC2,  AC2,  AC2,  AC2,	/* d0-d7 */
+AC2,  AC2,  AC2,  AC2,  AC2,  AC2,  AC2,  AC2,	/* d8-df */
+AC3,  AC3,  AC3,  AC3,  AC3,  AC3,  AC3,  AC3,	/* e0-e7 */
+AC3,  AC3,  AC3,  AC3,  AC3,  AC3,  AC3,  AC3,	/* e8-ef */
+AC4,  AC4,  AC4,  AC4,  AC4,  AC4,  AC4,  AC4,	/* f0-f7 */
+AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX,	/* f8-ff */
+};
+uchar statec2[256]={	/* looking for 10xxxxxx to complete a rune */
+AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX,	/* 00-07 */
+AWDX, ASPX, ASPNX,AWDX, AWDX, AWDX, AWDX, AWDX,	/* 08-0f */
+AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX,	/* 10-17 */
+AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX,	/* 18-1f */
+ASPX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX,	/* 20-27 */
+AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX,	/* 28-2f */
+AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX,	/* 30-37 */
+AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX,	/* 38-3f */
+AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX,	/* 40-47 */
+AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX,	/* 48-4f */
+AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX,	/* 50-57 */
+AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX,	/* 58-5f */
+AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX,	/* 60-67 */
+AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX,	/* 68-6f */
+AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX,	/* 70-77 */
+AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX,	/* 78-7f */
+AWDR, AWDR, AWDR, AWDR, AWDR, AWDR, AWDR, AWDR,	/* 80-87 */
+AWDR, AWDR, AWDR, AWDR, AWDR, AWDR, AWDR, AWDR,	/* 88-8f */
+AWDR, AWDR, AWDR, AWDR, AWDR, AWDR, AWDR, AWDR,	/* 90-97 */
+AWDR, AWDR, AWDR, AWDR, AWDR, AWDR, AWDR, AWDR,	/* 98-9f */
+AWDR, AWDR, AWDR, AWDR, AWDR, AWDR, AWDR, AWDR,	/* a0-a7 */
+AWDR, AWDR, AWDR, AWDR, AWDR, AWDR, AWDR, AWDR,	/* a8-af */
+AWDR, AWDR, AWDR, AWDR, AWDR, AWDR, AWDR, AWDR,	/* b0-b7 */
+AWDR, AWDR, AWDR, AWDR, AWDR, AWDR, AWDR, AWDR,	/* b8-bf */
+AC2X, AC2X, AC2X, AC2X, AC2X, AC2X, AC2X, AC2X,	/* c0-c7 */
+AC2X, AC2X, AC2X, AC2X, AC2X, AC2X, AC2X, AC2X,	/* c8-cf */
+AC2X, AC2X, AC2X, AC2X, AC2X, AC2X, AC2X, AC2X,	/* d0-d7 */
+AC2X, AC2X, AC2X, AC2X, AC2X, AC2X, AC2X, AC2X,	/* d8-df */
+AC3X, AC3X, AC3X, AC3X, AC3X, AC3X, AC3X, AC3X,	/* e0-e7 */
+AC3X, AC3X, AC3X, AC3X, AC3X, AC3X, AC3X, AC3X,	/* e8-ef */
+AC4X, AC4X, AC4X, AC4X, AC4X, AC4X, AC4X, AC4X,	/* f0-f7 */
+AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX,	/* f8-ff */
+};
+uchar statec3[256]={	/* looking for 10xxxxxx,10xxxxxx to complete a rune */
+AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX,	/* 00-07 */
+AWDX, ASPX, ASPNX,AWDX, AWDX, AWDX, AWDX, AWDX,	/* 08-0f */
+AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX,	/* 10-17 */
+AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX,	/* 18-1f */
+ASPX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX,	/* 20-27 */
+AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX,	/* 28-2f */
+AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX,	/* 30-37 */
+AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX,	/* 38-3f */
+AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX,	/* 40-47 */
+AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX,	/* 48-4f */
+AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX,	/* 50-57 */
+AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX,	/* 58-5f */
+AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX,	/* 60-67 */
+AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX,	/* 68-6f */
+AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX,	/* 70-77 */
+AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX,	/* 78-7f */
+AC2R, AC2R, AC2R, AC2R, AC2R, AC2R, AC2R, AC2R,	/* 80-87 */
+AC2R, AC2R, AC2R, AC2R, AC2R, AC2R, AC2R, AC2R,	/* 88-8f */
+AC2R, AC2R, AC2R, AC2R, AC2R, AC2R, AC2R, AC2R,	/* 90-97 */
+AC2R, AC2R, AC2R, AC2R, AC2R, AC2R, AC2R, AC2R,	/* 98-9f */
+AC2R, AC2R, AC2R, AC2R, AC2R, AC2R, AC2R, AC2R,	/* a0-a7 */
+AC2R, AC2R, AC2R, AC2R, AC2R, AC2R, AC2R, AC2R,	/* a8-af */
+AC2R, AC2R, AC2R, AC2R, AC2R, AC2R, AC2R, AC2R,	/* b0-b7 */
+AC2R, AC2R, AC2R, AC2R, AC2R, AC2R, AC2R, AC2R,	/* b8-bf */
+AC2X, AC2X, AC2X, AC2X, AC2X, AC2X, AC2X, AC2X,	/* c0-c7 */
+AC2X, AC2X, AC2X, AC2X, AC2X, AC2X, AC2X, AC2X,	/* c8-cf */
+AC2X, AC2X, AC2X, AC2X, AC2X, AC2X, AC2X, AC2X,	/* d0-d7 */
+AC2X, AC2X, AC2X, AC2X, AC2X, AC2X, AC2X, AC2X,	/* d8-df */
+AC3X, AC3X, AC3X, AC3X, AC3X, AC3X, AC3X, AC3X,	/* e0-e7 */
+AC3X, AC3X, AC3X, AC3X, AC3X, AC3X, AC3X, AC3X,	/* e8-ef */
+AC4X, AC4X, AC4X, AC4X, AC4X, AC4X, AC4X, AC4X,	/* f0-f7 */
+AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX,	/* f8-ff */
+};
+uchar statec4[256]={	/* looking for 10xxxxxx,10xxxxxx,10xxxxxx to complete a rune */
+AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX,	/* 00-07 */
+AWDX, ASPX, ASPNX,AWDX, AWDX, AWDX, AWDX, AWDX,	/* 08-0f */
+AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX,	/* 10-17 */
+AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX,	/* 18-1f */
+ASPX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX,	/* 20-27 */
+AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX,	/* 28-2f */
+AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX,	/* 30-37 */
+AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX,	/* 38-3f */
+AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX,	/* 40-47 */
+AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX,	/* 48-4f */
+AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX,	/* 50-57 */
+AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX,	/* 58-5f */
+AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX,	/* 60-67 */
+AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX,	/* 68-6f */
+AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX,	/* 70-77 */
+AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX,	/* 78-7f */
+AC3R, AC3R, AC3R, AC3R, AC3R, AC3R, AC3R, AC3R,	/* 80-87 */
+AC3R, AC3R, AC3R, AC3R, AC3R, AC3R, AC3R, AC3R,	/* 88-8f */
+AC3R, AC3R, AC3R, AC3R, AC3R, AC3R, AC3R, AC3R,	/* 90-97 */
+AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX,	/* 98-9f */
+AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX,	/* a0-a7 */
+AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX,	/* a8-af */
+AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX,	/* b0-b7 */
+AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX,	/* b8-bf */
+AC2X, AC2X, AC2X, AC2X, AC2X, AC2X, AC2X, AC2X,	/* c0-c7 */
+AC2X, AC2X, AC2X, AC2X, AC2X, AC2X, AC2X, AC2X,	/* c8-cf */
+AC2X, AC2X, AC2X, AC2X, AC2X, AC2X, AC2X, AC2X,	/* d0-d7 */
+AC2X, AC2X, AC2X, AC2X, AC2X, AC2X, AC2X, AC2X,	/* d8-df */
+AC3X, AC3X, AC3X, AC3X, AC3X, AC3X, AC3X, AC3X,	/* e0-e7 */
+AC3X, AC3X, AC3X, AC3X, AC3X, AC3X, AC3X, AC3X,	/* e8-ef */
+AC4X, AC4X, AC4X, AC4X, AC4X, AC4X, AC4X, AC4X,	/* f0-f7 */
+AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX, AWDX,	/* f8-ff */
+};
+void
+count(int f, char *name)
+{
+	int n;
+	uchar buf[NBUF];
+	uchar *bufp, *ebuf;
+	uchar *state=statesp;
+
+	nline = 0;
+	nword = 0;
+	nrune = 0;
+	nbadr = 0;
+	nchar = 0;
+
+	for(;;){
+		n=read(f, buf, NBUF);
+		if(n<=0)
+			break;
+		nchar+=n;
+		nrune+=n;	/* might be too large, gets decreased later */
+		bufp=buf;
+		ebuf=buf+n;
+		do{
+			switch(state[*bufp]){
+			case AC2:   state=statec2;                   break;
+			case AC2R:  state=statec2; --nrune;          break;
+			case AC2W:  state=statec2; nword++;          break;
+			case AC2X:  state=statec2;          nbadr++; break;
+			case AC3:   state=statec3;                   break;
+			case AC3R:  state=statec3; --nrune;          break;
+			case AC3W:  state=statec3; nword++;          break;
+			case AC3X:  state=statec3;          nbadr++; break;
+			case AC4:   state=statec4;                   break;
+			case AC4W:  state=statec4; nword++;          break;
+			case AC4X:  state=statec4;          nbadr++; break;
+			case ASP:   state=statesp;                   break;
+			case ASPN:  state=statesp; nline++;          break;
+			case ASPNX: state=statesp; nline++; nbadr++; break;
+			case ASPX:  state=statesp;          nbadr++; break;
+			case AWD:   state=statewd;                   break;
+			case AWDR:  state=statewd; --nrune;          break;
+			case AWDW:  state=statewd; nword++;          break;
+			case AWDWX: state=statewd; nword++; nbadr++; break;
+			case AWDX:  state=statewd;          nbadr++; break;
+			}
+		}while(++bufp!=ebuf);
+	}
+	if(state!=statesp && state!=statewd)
+		nbadr++;
+	if(n<0)
+		fprint(2, "%s: %r\n", name);
+	report(nline, nword, nrune, nbadr, nchar, name);
+}

historical/unix-v7-wc.c

@@ -0,0 +1,86 @@
+/* wc line and word count */
+
+#include <stdio.h>
+
+main(argc, argv)
+char **argv;
+{
+	int i, token;
+	register FILE *fp;
+	long linect, wordct, charct;
+	long tlinect=0, twordct=0, tcharct=0;
+	char *wd;
+	register int c;
+
+	wd = "lwc";
+	if(argc > 1 && *argv[1] == '-') {
+		wd = ++argv[1];
+		argc--;
+		argv++;
+	}
+
+	i = 1;
+	fp = stdin;
+	do {
+		if(argc>1 && (fp=fopen(argv[i], "r")) == NULL) {
+			fprintf(stderr, "wc: can't open %s\n", argv[i]);
+			continue;
+		}
+		linect = 0;
+		wordct = 0;
+		charct = 0;
+		token = 0;
+		for(;;) {
+			c = getc(fp);
+			if (c == EOF)
+				break;
+			charct++;
+			if(' '<c&&c<0177) {
+				if(!token) {
+					wordct++;
+					token++;
+				}
+				continue;
+			}
+			if(c=='\n')
+				linect++;
+			else if(c!=' '&&c!='\t')
+				continue;
+			token = 0;
+		}
+		/* print lines, words, chars */
+		wcp(wd, charct, wordct, linect);
+		if(argc>1) {
+			printf(" %s\n", argv[i]);
+		} else
+			printf("\n");
+		fclose(fp);
+		tlinect += linect;
+		twordct += wordct;
+		tcharct += charct;
+	} while(++i<argc);
+	if(argc > 2) {
+		wcp(wd, tcharct, twordct, tlinect);
+		printf(" total\n");
+	}
+	exit(0);
+}
+
+wcp(wd, charct, wordct, linect)
+register char *wd;
+long charct; long wordct; long linect;
+{
+	while (*wd) switch (*wd++) {
+	case 'l':
+		printf("%7ld", linect);
+		break;
+
+	case 'w':
+		printf("%7ld ", wordct);
+		break;
+
+	case 'c':
+		printf("%7ld", charct);
+		break;
+	}
+}

src/extra/chc/chc.c

@@ -0,0 +1,32 @@
+#include <stdio.h>
+#include <unistd.h>
+
+int chc(FILE* fp)
+{
+    register int c;
+    int num_chars = 0;
+    while ((c = getc(fp)) != EOF) {
+			num_chars ++;
+    }
+    printf("%i\n", num_chars);
+    return 0;
+}
+
+int main(int argc, char** argv)
+{
+    if (argc == 1) {
+        return chc(stdin);
+    } else if (argc > 1) {
+        FILE* fp = fopen(argv[1], "r");
+        if (!fp) {
+            perror("Could not open file");
+            return 1;
+        }
+				return chc(fp) && fclose(fp);
+    } else {
+        printf("Usage: chc file.txt\n");
+        printf("   or: cat file.txt | chc\n");
+        printf("   or: chc # read from user-inputted stdin\n");
+    }
+    return 0;
+}

src/extra/chc/makefile

@@ -0,0 +1,40 @@
+# Interface: 
+#   make
+#   make build
+#   make format
+
+# Compiler
+CC=gcc
+# CC=tcc # <= faster compilation
+
+# Main file
+SRC=chc.c
+OUT=chc
+
+## Flags
+DEBUG= #'-g'
+STANDARD=-std=c99
+WARNINGS=-Wall
+OPTIMIZED=-O3
+# OPTIMIZED=-O3  #-Ofast
+
+## Formatter
+STYLE_BLUEPRINT=webkit
+FORMATTER=clang-format -i -style=$(STYLE_BLUEPRINT)
+
+## make build
+build: $(SRC)
+	$(CC) $(OPTIMIZED) $(DEBUG) $(SRC) -o $(OUT)
+
+format: $(SRC)
+	$(FORMATTER) $(SRC)
+
+install:
+	cp -n $(OUT) /bin/$(OUT)
+
+test: $(OUT)
+	/bin/echo -e "123\n45 67" | ./$(OUT)
+	/bin/echo -n "" | ./chc
+	/bin/echo "  xx x" | ./$(OUT)
+	./$(OUT) $(SRC)
+	./$(OUT) nonexistent_file || true

src/extra/lc/lc.c

@@ -0,0 +1,35 @@
+#include <stdio.h>
+#include <unistd.h>
+
+int lc(FILE* fp)
+{
+    int num_lines = 0;
+    register int c;
+    while ((c = getc(fp)) != EOF) {
+        if (c == '\n' ) {
+					num_lines ++;
+        }
+    }
+		// num_lines += (c != '\n');  // < judgment call, adds a line if the last line isn't followed by a newline.
+    printf("%i\n", num_lines);
+    return 0;
+}
+
+int main(int argc, char** argv)
+{
+    if (argc == 1) {
+        return lc(stdin);
+    } else if (argc > 1) {
+        FILE* fp = fopen(argv[1], "r");
+        if (!fp) {
+            perror("Could not open file");
+            return 1;
+        }
+				return lc(fp) && fclose(fp);
+    } else {
+        printf("Usage: lc file.txt\n");
+        printf("   or: cat file.txt | lc\n");
+        printf("   or: lc # read from user-inputted stdin\n");
+    }
+    return 0;
+}

src/extra/lc/makefile

@@ -8,14 +8,14 @@ CC=gcc
 # CC=tcc # <= faster compilation
 
 # Main file
-SRC=ww.c
-OUT=ww
+SRC=lc.c
+OUT=lc
 
 ## Flags
 DEBUG= #'-g'
 STANDARD=-std=c99
 WARNINGS=-Wall
-OPTIMIZED=-O0
+OPTIMIZED=-O3
 # OPTIMIZED=-O3  #-Ofast
 
 ## Formatter
@@ -29,9 +29,12 @@ build: $(SRC)
 format: $(SRC)
 	$(FORMATTER) $(SRC)
 
+install:
+	cp -n $(OUT) /bin/$(OUT)
+
 test: $(OUT)
 	/bin/echo -e "123\n45 67" | ./$(OUT)
-	/bin/echo -n "" | ./ww
+	/bin/echo -n "" | ./lc
 	/bin/echo "  xx x" | ./$(OUT) -w
 	./$(OUT) $(SRC)
 	./$(OUT) nonexistent_file || true

src/makefile

@@ -0,0 +1,40 @@
+# Interface: 
+#   make
+#   make build
+#   make format
+
+# Compiler
+CC=gcc
+# CC=tcc # <= faster compilation
+
+# Main file
+SRC=wc.c
+OUT=wc
+
+## Flags
+DEBUG= #'-g'
+STANDARD=-std=c99
+WARNINGS=-Wall
+OPTIMIZED=-O3
+# OPTIMIZED=-O3  #-Ofast
+
+## Formatter
+STYLE_BLUEPRINT=webkit
+FORMATTER=clang-format -i -style=$(STYLE_BLUEPRINT)
+
+## make build
+build: $(SRC)
+	$(CC) $(OPTIMIZED) $(DEBUG) $(SRC) -o $(OUT)
+
+format: $(SRC)
+	$(FORMATTER) $(SRC)
+
+install:
+	cp -n $(OUT) /bin/ww ## don't overwrite old standard wc.
+
+test: $(OUT)
+	/bin/echo -e "123\n45 67" | ./$(OUT)
+	/bin/echo -n "" | ./wc
+	/bin/echo "  xx x" | ./$(OUT) -w
+	./$(OUT) $(SRC)
+	./$(OUT) nonexistent_file || true

src/wc.c

@@ -0,0 +1,44 @@
+#include <stdio.h>
+#include <unistd.h>
+
+int wc(FILE* fp)
+{
+    register int c;
+    int word = 0, num_words = 0;
+    while ((c = getc(fp)) != EOF) {
+        if (c != ' ' && c != '\n' && c != '\t') {
+            word = 1;
+        } else {
+            if (word) {
+              num_words++;
+              word = 0;
+            }
+        }
+    }
+		num_words+=word;
+    printf("%i\n", num_words);
+    return 0;
+}
+
+int main(int argc, char** argv)
+{
+    if (argc == 1) {
+        return wc(stdin);
+    } else if (argc > 1) {
+        FILE* fp = fopen(argv[1], "r");
+        if (!fp) {
+            perror("Could not open file");
+            return 1;
+        }
+				int wc_status = wc(fp);
+				int fclose_status = fclose(fp);
+				return (wc_status == 0) && (fclose_status ==0);
+				// can't do return wc_status == 0 && fclose_status == 0;
+				// because then if wc returns with -1, fclose is not called.
+    } else {
+        printf("Usage: wc file.txt\n");
+        printf("   or: cat file.txt | wc\n");
+        printf("   or: wc # read from user-inputted stdin\n");
+    }
+    return 0;
+}

ww.c

@@ -1,50 +0,0 @@
-#include <stdio.h>
-#include <unistd.h> // read, isatty
-
-// STDIN_FILENO
-int process_fn(int fn)
-{
-    char c[1];
-		int seen_word=0;
-		int seen_sep_after_word=0;
-		int num_words = 0;
-    while (read(fn, c, sizeof(c)) > 0) {
-				if(*c != '\n' && *c != ' ' && *c != '\t'){
-					seen_word = 1;
-				} else if(seen_word) {
-					seen_sep_after_word = 1;
-				} else {
-					// see a separator, but haven't seen a word: do nothing
-					// exercise: what happens if you only track seen_sep,
-					// instead of seen_sep_after_word?
-					// test with: $ echo " x x" | ./wc
-				}
-				if(seen_word && seen_sep_after_word){
-					num_words++;
-					seen_sep_after_word = seen_word = 0;
-				}
-    }
-		if(seen_word){
-			num_words++;
-		}
-		printf("%i\n",num_words);
-    return 0;
-}
-
-int main(int argc, char** argv)
-{
-		if (!isatty(STDIN_FILENO)) {
-        return process_fn(STDIN_FILENO);
-    } else if (argc > 1) {
-        FILE* fp = fopen(argv[1], "r");
-        if (!fp) {
-            perror("Could not open file");
-            return 1;
-        }
-        return process_fn(fileno(fp));
-    } else {
-        printf("Usage: ww file.txt\n");
-				printf("   or: cat file.txt | ww\n");
-    }
-    return 0;
-}