diff options
Diffstat (limited to 'Master/texmf-dist/doc/fonts/accfonts')
-rw-r--r-- | Master/texmf-dist/doc/fonts/accfonts/CHANGES | 300 | ||||
-rw-r--r-- | Master/texmf-dist/doc/fonts/accfonts/COPYING | 339 | ||||
-rw-r--r-- | Master/texmf-dist/doc/fonts/accfonts/README | 456 | ||||
-rwxr-xr-x | Master/texmf-dist/doc/fonts/accfonts/mkt1font | 980 | ||||
-rwxr-xr-x | Master/texmf-dist/doc/fonts/accfonts/vpl2ovp | 1070 | ||||
-rwxr-xr-x | Master/texmf-dist/doc/fonts/accfonts/vpl2vpl | 997 |
6 files changed, 4142 insertions, 0 deletions
diff --git a/Master/texmf-dist/doc/fonts/accfonts/CHANGES b/Master/texmf-dist/doc/fonts/accfonts/CHANGES new file mode 100644 index 00000000000..01af0961fc6 --- /dev/null +++ b/Master/texmf-dist/doc/fonts/accfonts/CHANGES @@ -0,0 +1,300 @@ +Changes to vpl2vpl between first (unnumbered) release and release 0.1 +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +When I first wrote vpl2vpl I was under the impression that the vpl +file output by afm2tfm could never contain accented character +definitions. The first (unnumbered) release of vpl2vpl thus did not +implement the -b option allowed for mkt1font (to block the use of +predefined accented characters). I have since become aware that in +the rather rare case of an afm file containing composite character +information, afm2tfm uses that information to build definitions of +accented characters; I have therefore introduced a -b option in +version 0.1. + +There were two bugs in the coding dealing with the -s option in the +first version of vpl2vpl. First, the shrink-factor specified by the +user was incorrectly applied to the underdot accent as well as to +dropped superscript accents. Second, the shrink-factor was not +correctly scaled in terms of the value of DESIGNUNITS (this chiefly +affected Computer Modern fonts). Both of these have been fixed in +version 0.1. + +Another bug affected those characters (quotesingle, quotedbl, +backslash, underscore, braceleft, bar and braceright) which +dvips.enc places in the lower half of the character set, but which +vpl2vpl removes to make room for the normal TeX inhabitants of their +"slots"; in the first version of the program it was not possible to +include these characters in the output font. This has also been +fixed in version 0.1. + +The handling of LIGTABLE information controlling kerning etc. has +been improved, to eliminate repeated instructions and "orphaned" +instructions with no LABEL. + +In the first version of vpl2vpl I deliberately did not allow for +double superscript accents on tall characters such as capital +letters, on the grounds that this would be bad typographic practice. +A specific request for one such character has led me to modify +version 0.1 of the program to make the creation of such characters +possible, but I would still argue against their use. + +Some minor improvements have been made to the code in various areas, +including checking for inappropriate input, calculation of italic +correction for characters with superscript accents, and placing of +dropped superscript accents. (However, it is likely that such +accents will still sometimes require manual intervention.) + + +Changes to mkt1font between first (unnumbered) release and release 0.1 +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +In the first release of mkt1font, kerning information for predefined +accented characters was taken from the input font, even if the -b +option had been specified to force the redefinition of such +characters. This has been fixed in version 0.1: if the -b option is +used, kerns for characters such as "eacute" are generalised from the +kerns for "e" in just the same way as happens for "emacron" etc. + +Similarly, predefined accented characters eliminated by the -b +option used to retain "ghost" entries among the unencoded characters +in the afm file. This too has been fixed in version 0.1. + +As of version 0.1, any composite character definitions contained in +the afm file of the input font are eliminated from the output font, +since they will almost certainly be incomplete, and (if the user has +specified -b) will probably be wrong as well. + +Version 0.1 can now properly process input fonts using MS-DOS file +format (with newline represented by CR/LF). It can also process +fonts in which the character "|" is used in the names of the +frequently used "noaccess def" and "noaccess put" definitions +(previously this fell foul of Perl's regular expression handler). + +As with vpl2vpl, I have modified version 0.1 of mkt1font to permit +the creation of tall characters bearing double superscript accents, +though I do not recommend the use of such characters. + +The "FontBBox" entries in the afm and pfb files now reflect any +increase in the maximum height or depth of characters in the output +font. + +Various other minor improvements have been made to the code, +including the placing of dropped superscript accents. (As with +vpl2vpl, however, it is likely that such accents will still +sometimes require manual intervention.) + + +Changes between release 0.1 and release 0.2 +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +A. Changes common to both programs +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +I have implemented the candrabindu ("moon-dot") accent sometimes +used in Indian-language material. This is achieved by overprinting a +breve with a dotaccent; a new command-line option (-c) has been +introduced to allow for font-specific adjustments in the placing of +the dotaccent. + +The user's command-line is now stored as a comment at the head of +the output file(s). + +The constraint on the ordering of definitions in a definition file +has been removed: it is no longer necessary to ensure that a +character is defined before it is used. + +Digraphs are now implemented: if the character specified as the +"accent" in a definition is not in fact a valid accent character, +the definition is interpreted as a request for a digraph formed from +the "character" followed by the "accent". + +A bug which placed superscript accents incorrectly over tall +characters already bearing "under" accents has been fixed. + +The vertical positioning of "under" accents has been adjusted: they +are now placed slightly lower than previously. + + +B. Changes to vpl2vpl +~~~~~~~~~~~~~~~~~~~~~ + +Fixed a bug which resulted in some accents in small caps fonts being +positioned at the wrong height. + +Fixed a bug which resulted in small amounts of LIGTABLE information +being lost. + + +C. Changes to mkt1font +~~~~~~~~~~~~~~~~~~~~~~ + +The internal organisation of the program has been cleaned up in a +number of respects. In particular, various subroutines are now +called with the appropriate formal parameters, rather than relying +on the existence of equivalent global variables; the fetching and +storing of character metric information is tidier and more +efficient; and kerning information is dealt with in the course of +the main program loop, rather than in a private (double) loop +afterwards. + +The -s option allowing "under" accents to be shrunk by a specified +factor, which was previously available only in vpl2vpl, has now been +implemented in mkt1font also. + +The output afm file previously sometimes contained spurious entries +for unencoded characters that duplicated items in the list of +encoded characters. This has been fixed. + +Despite the fix introduced in version 0.1, some predefined kerning +information continued to find its way into the afm file even when +the -b option was specified to block the use of predefined accented +characters. A new, improved fix is now in place to prevent this. An +error in a regular expression which generated some undesirable kerns +has also been corrected. + +The "FontBBox" entries in the afm and pfb files now reflect any +increase in the maximum width of characters in the output font, as +well as increases in their maximum height or depth. + +Fixed a bug causing the underbar accent to be too long. + +Fixed a bug causing "under" accents to be assigned the wrong depth: +this could result in the bottom of the accent failing to print +properly. + + +Changes between release 0.2 and release 0.21 +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +Changes common to both programs +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +The vertical positioning of "under" accents has been adjusted again +(the previous adjustment was a little too enthusiastic). They have +been raised slightly. + +The height at which characters are reckoned to be so tall that +superscript accents placed on them must be raised above the normal +level has been increased slightly (from 1.1 x xheight to 1.15 x +xheight). + +Changes between release 0.21 and release 0.211 +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +A. Changes to vpl2vpl +~~~~~~~~~~~~~~~~~~~~~ + +A single minor change has been made to vpl2vpl: this has been +necessitated by a change in the format of the LIGTABLE information +produced by version 8.1 of afm2tfm, which now adds identificatory +comments to lines referring to characters by means of octal +notation. Vpl2vpl strips out such comments. + + +B. Changes to mkt1font +~~~~~~~~~~~~~~~~~~~~~~ + +Minor bugfixes have been put in place: extra spaces in the the +"noaccess def" and "noaccess put" definitions are now permitted, and +so is a character named ".null". An error message has been improved. + +Changes between release 0.211 and release 0.212 +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +A. Changes to vpl2vpl +~~~~~~~~~~~~~~~~~~~~~ + +Fixed a bug in the "double superscript accent on small caps +character" routine. + + +B. Changes to mkt1font +~~~~~~~~~~~~~~~~~~~~~~ + +Fixed a bug which produced incorrect output in cases where the +character to be accented is defined as blank (e.g. space). + +Changes to between release 0.212 and release 0.22 +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +Changes common to both programs +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +The programs now recognise "commaaccent" as a valid subscript +accent. Note that they cannot replace this subscript with the +superscript form used with the letter "g" (any more than they can +substitute the apostrophe-like form of the caron that is used with +"L", "d", "l" and "t"). Note also that as there is no position for +this accent in either the standard TeX encoding or the dvips.enc +variant, vpl2vpl will not actually be able to use it to build new +characters without further modification. + +In the case where the definition file specifies, say, "z overdot" +and the font contains a predefined version named "zdotaccent", it +previously happened that the output font contained both characters. +This has been fixed: now only the character requested in the +definition file exists in the output. + +Changes between release 0.22 and release 0.221 +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +A. Changes to mkt1font +~~~~~~~~~~~~~~~~~~~~~~ + +Fixed a bug which caused the program to fail after incorrectly +identifying CharStrings definitions. + +Changes tbetween release 0.221 and release 0.222 +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +A. Changes to mkt1font +~~~~~~~~~~~~~~~~~~~~~~ + +Changed FamilyName to remove only the final one of a number of +hyphenated elements from the font name. + +Changes tbetween release 0.222 and release 0.23 +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +A. Changes to mkt1font +~~~~~~~~~~~~~~~~~~~~~~ + +No changes have in fact been made to mkt1font, but its version number +has been raised to 0.23 to confirm with those of vpl2vpl and vpl2ovp. + +B. Changes to vpl2vpl +~~~~~~~~~~~~~~~~~~~~~ + +A change has been introduced to permit the program to use the output +of the AFM conversion utility afm2pl, rather than the earlier afm2tfm. +This has been done because it has come to light that afm2tfm gives +incorrect values for the heights of some characters, which can cause +poor accent placement. Support for the output of afm2tfm has not been +withdrawn, but afm2pl is now definitely preferred. + +B. A new program: vpl2ovp +~~~~~~~~~~~~~~~~~~~~~~~~~ + +The greatest change as of 0.23 is the addition of a third program to +the suite. Vpl2ovp does essentially the same job as vpl2vpl, in that +it creates virtual fonts that contain arbitrarily accented characters, +but its output is a .ovp file suitable for use with Omega (the 16-bit +Unicode-aware development from TeX). Using vpl2ovp it is possible to +build substantial Unicode-compliant virtual fonts for use with Omega, +and a .def file for the set of characters I have included in my +earlier "IndUni" OpenType fonts is now included in the distribution. +(IndUni virtual fonts for Omega created with vpl2ovp are available at +http://bombay.indology.info/software/fonts/induni/index.html.) Glyphs +representing characters requiring more than a single codepoint are +stored in the Private Use Area, and a system of ligatures is provided +to allow them to be accessed. This system also permits +single-codepoint accented characters to be accessed through their +"decomposed" component parts. Thus if the characters a-macron (single +codepoint: U+0101) and a-macron-acute (two codepoints: U+0101 + +U+0301) are defined, the former will be accessible both as U+0101 +(a-macron) and as U+0061 + U+0304 ("a" + macron); the latter will be +accessible both as U+0101 + U+0301 (a-macron + acute) and U+0061 + +U+0304 + U+0301 ("a" + macron + acute). This is a considerable +advantage, given the different possible ways in which Unicode can be, +and is, used. + diff --git a/Master/texmf-dist/doc/fonts/accfonts/COPYING b/Master/texmf-dist/doc/fonts/accfonts/COPYING new file mode 100644 index 00000000000..a43ea2126fb --- /dev/null +++ b/Master/texmf-dist/doc/fonts/accfonts/COPYING @@ -0,0 +1,339 @@ + GNU GENERAL PUBLIC LICENSE + Version 2, June 1991 + + Copyright (C) 1989, 1991 Free Software Foundation, Inc. + 675 Mass Ave, Cambridge, MA 02139, 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 + + Appendix: 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) 19yy <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., 675 Mass Ave, Cambridge, MA 02139, 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) 19yy 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. diff --git a/Master/texmf-dist/doc/fonts/accfonts/README b/Master/texmf-dist/doc/fonts/accfonts/README new file mode 100644 index 00000000000..7f775f1b858 --- /dev/null +++ b/Master/texmf-dist/doc/fonts/accfonts/README @@ -0,0 +1,456 @@ + + + Mkt1font, vpl2vpl and vpl2ovp: programs to generate accented fonts + ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + + John D. Smith + ~~~~~~~~~~~~~ + + +These three programs, all made available under the GNU General Public +License, address the same requirement using the same basic algorithms: +their aim is to make it easy to create versions of existing fonts +containing whatever accented characters the user may need, arranged +according to whatever encoding he/she may favour. Mkt1font does this +by reading in the two files that define a Type 1 PostScript font and +writing out new versions of them; vpl2vpl does it by reading in the +file that defines a TeX virtual font and writing out a new version of +it; vpl2ovp does the same as vpl2vpl, but its output is a 16-bit +virtual font suitable for Omega, the Unicode-aware development from +TeX. In each case information about what accented characters are +required and where they should be located is supplied by means of a +simple definition file, which has the same format for both programs. + +Note that most Type 1 PostScript fonts are commercial products +subject to both copyright and licensing restrictions. If the license +for such a font forbids reverse-engineering it, it is presumably +illegal to run mkt1font on it; in any case it would certainly be a +serious breach of copyright to make modified versions of the font +available to third parties. The author of mkt1font will not be held +responsible for any such misuses of the software. (No such legal +problems surround the use of TeX virtual fonts, which merely specify +new ways to use existing fonts.) However, would-be users may wish to +note the existence of a body of high-quality freeware lookalikes for +many of the standard Type 1 fonts: like mkt1font and vpl2vpl, the +Ghostscript fonts developed by URW++ Design and Development +Incorporated are made available under the GNU General Public License +(see the file COPYING), which permits them to be modified and +redistributed provided that certain simple decencies are observed. +These fonts are available from many ftp sites, including those +forming the Comprehensive TeX Archive Network (CTAN), for example +ftp.tex.ac.uk: look for the most recent font archive file in the +directory /tex-archive/support/ghostscript/gnu/fonts. + +A detailed specification of the form of the definition file used by +mkt1font and vpl2vpl is given below in the instructions for using the +programs, but it may be helpful to give a quick idea of its contents +here. Each line of the file contains something similar to "128 x +acute", which is an instruction to create a new character formed from +"x" with an acute accent and located at position 128 in the character +set. Once a new character has been defined in this way, it "exists" in +just the same way as any other character, under the name "xacute" (or +whatever); thus it can even receive further accents. The two lines + + 129 e macron + 130 emacron breve + +will create a "long e" and a "long-or-short e" at the positions +specified. (If only the latter is desired, they can both be assigned +the same position in the encoding -- the second will overwrite the +first.) Subscript as well as superscript accents are available. Some +sample definition files are included to give an idea of the format: +note that two of these (CSX.def and Norman.def), used for Indian +language material in Roman script, contain the triple-accented +character "runderdotmacron acute"! + +In addition to accented characters proper, both programs can produce +digraphs -- single characters composed of pairs of other characters. +In itself this may seem to be of limited use, since the digraph +should always be indistinguishable from its two constituent +characters printed consecutively. However, some Unicode-style +encodings require that certain character-pairs be treated as +digraphs. In addition, use of a digraph in subsequent definitions +allows an accent to be applied to two characters as a pair: so, for +example, + + 131 k h + 131 kh underbar + +will produce a character consisting of an underlined "kh" at +position 131. + +The algorithms used in both programs take great care to secure the +most attractive results, placing accents centrally over/under their +characters at appropriate heights/depths, varying their position +according to the angle of slant in Italic and similar fonts, +providing new characters with kerning information (which will be +resolutely ignored by most word-processors), and -- in the case of +mkt1font -- giving hinting instructions to improve output on +low-resolution printers. However, users may feel that some +characters need "tweaking". This tends to happen when the part of +the character adjacent to the accent is highly asymmetrical: +subscript accents below "r" may need moving to the left, while +superscript accents above "d" may need moving to the right. It is +relatively easy to modify the output of vpl2vpl to make such +improvements by hand (vpl files are designed to be easy for humans +to read, and vpl2vpl identifies each character with a comment). Type +1 fonts are another matter; mkt1font generates a human-readable and +commented ".dis" file as well as the ".pfb" font file, and it is +possible to make changes to this and rebuild the pfb file with t1asm +(see below), but this is not quite as simple as modifying a TeX +virtual font. + +For details on how vpl2ovp handles access to accented characters by +means of a system of ligatures, see further the CHANGES file. + +The programs are written in Perl, and have not been tested on +systems other than Unix. (Apart from the #! line at the top, the +only Unix specificities the author is aware of are two references to +"/dev/null" in mkt1font and the general assumption that filenames +can be of any length.) At run time, mkt1font invokes two further +font utilities, t1asm and t1disasm, written by I. Lee Hetherington +and available from CTAN ftp sites: look in the directory +/tex-archive/fonts/utilities/t1utils. + +Detailed instructions for using the programs follow. In each case +these instructions can also be seen by typing the name of the program +with a "-h" option. + + +Mkt1font +~~~~~~~~ +Syntax: mkt1font -n fontname -d definition-file -a afm-file -f font-file + [-s shrink-factor] [-c candrabindu-adjustment] [-b] + +Mkt1font creates new Type 1 PostScript fonts based on existing fonts +("input fonts"). In order to do this it makes use of I. Lee +Hetherington's programs t1asm and t1disasm, which must be present on +the system. A successful run will generate an AFM file and a PFB +file, as well as a DIS file containing a disassembled version of the +PFB file (including useful comments). Four options must be specified +on the command line, as follows: + + -n should name the font it is intended to generate. Avoid names + such as "myfont", as both mkt1font and other programs attempt + to draw conclusions from the name; better would be something + like "Utopia_French-BoldItalic". The generated font files will + also use this for their basename. + + -d should refer to a font definition file. This file (which could + usefully be named, e.g., "French.def") should consist of lines + of character definitions, in the form + "number" "character" + or + "number" "character" "accent" + Here "number" represents the character's position in the new + encoding and may be expressed in decimal, octal or hex; + "character" names the character (e.g. "comma", "eight", "A") + or consists of the word ".notdef" (indicating that the + specified number's "slot" in the new encoding is to be empty); + and "accent" optionally names an accent to be placed on the + character. In addition to the standard accents available in + PostScript fonts, "underbar" and "underdot" are also available, + as are "under" versions of all the normal superscript accents + ("underdieresis", "underring", etc.). The Indian accent + "candrabindu" may also be specified: it is formed by + overprinting a breve with a dotaccent. Finally, "overdot" may + be used as a synonym for "dotaccent". + + If the character named in the "accent" position is not in fact + a valid accent character, the program interprets the definition + as a request for a digraph formed from the "character" and the + "accent". A digraph consisting of, say, "k" and "h" will be + indistinguishable from the letters "k" and "h" printed + consecutively, but the digraph "kh" can itself receive accents + like any other character: see next paragraph. + + A new character (such as "amacron" or "kh") may be freely + used in the "character" position of a further definition (such + as "amacron breve" or "kh underbar"). There is no constraint + on the ordering of definitions within a definition file. The + definition of "a macron" does not have to precede that of + "amacron breve": requests for "impossible" characters are + deferred until their constituents have had a chance to come into + being. + + "Slots" for which no new definition is given retain the + definition they have in the input font. + + The definition file may also contain blank lines and comments + (introduced by "#"). + + -a should refer to the AFM (Adobe Font Metrics) file for the input + font. + + -f should refer to the binary font file (PFB) for the input font. + (In fact the equivalent ASCII file (PFA) is also acceptable for + input, but the output font is always in PFB format.) + + -s may optionally give the factor, expressed as a per-thousand + value, by which normally superscript accents (such as dieresis, + ring) should be shrunk when they are used as subscript accents + (such as underdieresis, underring). Values of around 800 may be + found useful. + + -c may optionally give two comma-separated numerical values to + adjust the x and y coordinates of the dotaccent placed within a + breve to form the candrabindu accent. + + -b may optionally be specified to block the use of predefined + accented characters, forcing mkt1font to define its own + versions. This may be useful to secure a consistent appearance + in cases where a font designer does not share mkt1font's views + on where accents should be placed. + +The -h option prints this help. + + +Vpl2vpl +~~~~~~~ +Syntax: vpl2vpl -d definition-file [-s shrink-factor] + [-c candrabindu-adjustment] [-b] vpl-file + +Vpl2vpl creates new TeX virtual fonts based on existing virtual +fonts ("input fonts"). A successful run will read a vpl (Virtual +Property List) file and a definition file, and will generate a new +vpl file on standard output. The input font is assumed to adhere to +the standard TeX encoding for text fonts unless it was created with +the program afm2tfm, in which case it is assumed to conform to the +encoding specified in the file dvips.enc. In either case, the name +of the input font is assumed to be the name of the input file +without its .vpl extension: it must conform to normal TeX +conventions for naming fonts, as vpl2vpl attempts to draw +conclusions from it about the kind of font it is dealing with. + +In the case of a non-virtual font (such as the Computer Modern +fonts), use a pl (Property List) file, created with the standard +utility tftopl, as the input file in place of a vpl file; vpl2vpl +will make the necessary changes on the fly. + +A typical complete sequence of commands to create a new virtual +font might therefore be + tftopl cmr10.tfm cmr10.pl + vpl2vpl -d ISO-Latin1.def cmr10.pl >cmr10_isol1.vpl + vptovf cmr10_isol1.vpl cmr10_isol1.vf cmr10_isol1.tfm +for a Computer Modern font, or + afm2pl Times-Roman.afm rptmr.pl + pltotf rptmr.pl rptmr.tfm + vpl2vpl -d ISO-Latin1.def rptmr.pl >ptmr-isol1.vpl + vptovf ptmr-isol1.vpl ptmr-isol1.vf ptmr-isol1.tfm +for a PostScript font. + +Another approach for a PostScript font is to use afm2tfm: + afm2tfm Times-Roman.afm -t dvips.enc -v ptmr rptmr + vpl2vpl -d ISO-Latin1.def ptmr.vpl >ptmr-isol1.vpl + vptovf ptmr-isol1.vpl ptmr-isol1.vf ptmr-isol1.tfm +-- but this is now deprecated, as afm2tfm generates incorrect +values for the heights of some characters, and this can lead to +bad accent placing. + +In order to keep the whole upper half of the character set free for +the requirements of the encoding specified in the definition file, +certain modifications are made to input fonts following the +dvips.enc encoding to bring them into greater conformity with the +TeX norm. In particular, the characters dotaccent and hungarumlaut +are placed in the positions assigned by TeX ("5F, "7D), not those +enforced by dvips.enc ("C7, "CD). The f-ligatures, double quotes and +dashes are also moved from the upper half of the character set to +their normal TeX positions. As a result, the following characters +are not found in the lower half of the character set: quotesingle, +quotedbl, backslash, underscore, braceleft, bar, braceright. These +characters can, however, be assigned positions in the output font if +they are needed. (Indeed, they could all be explicitly restored to +their dvips.enc positions if this were desired.) + +Options: + + -d should refer to a font definition file. This file (which could + usefully be named, e.g., "French.def") should consist of lines + of character definitions, in the form + "number" "character" + or + "number" "character" "accent" + + Here "number" represents the character's position in the new + encoding and may be expressed in decimal, octal or hex; + "character" names the character (e.g. "comma", "eight", "A") or + consists of the word ".notdef" (indicating that the specified + number's "slot" in the new encoding is to be empty); and + "accent" optionally names an accent to be placed on the + character. In addition to the standard accents available in + PostScript fonts, "underbar" and "underdot" are also available, + as are "under" versions of all the normal superscript accents + ("underdieresis", "underring", etc.). The Indian accent + "candrabindu" may also be specified: it is formed by + overprinting a breve with a dotaccent. Finally, "overdot" may + be used as a synonym for "dotaccent". + + If the character named in the "accent" position is not in fact + a valid accent character, the program interprets the definition + as a request for a digraph formed from the "character" and the + "accent". A digraph consisting of, say, "k" and "h" will be + indistinguishable from the letters "k" and "h" printed + consecutively, but the digraph "kh" can itself receive accents + like any other character: see next paragraph. + + A new character (such as "amacron" or "kh") may be freely + used in the "character" position of a further definition (such + as "amacron breve" or "kh underbar"). There is no constraint + on the ordering of definitions within a definition file. The + definition of "a macron" does not have to precede that of + "amacron breve": requests for "impossible" characters are + deferred until their constituents have had a chance to come into + being. + + "Slots" for which no new definition is given retain the + definition they have in the input font. + + The definition file may also contain blank lines and comments + (introduced by "#"). + + -s may optionally give the factor, expressed as a per-thousand + value, by which normally superscript accents (such as dieresis, + ring) should be shrunk when they are used as subscript accents + (such as underdieresis, underring). Values of around 800 may be + found useful. + + -c may optionally give two comma-separated numerical values to + adjust the x and y coordinates of the dotaccent placed within a + breve to form the candrabindu accent. A coordinate scheme using + "DESIGNUNITS R 1000" is assumed. + + -b may optionally be specified to block the use of predefined + accented characters, forcing vpl2vpl to define its own + versions. This may be useful to secure a consistent appearance + in cases where a font designer does not share vpl2vpl's views + on where accents should be placed. + + -h prints this help. + + +Vpl2ovp +~~~~~~~ + +Syntax: vpl2ovp -d definition-file [-s shrink-factor] + [-c candrabindu-adjustment] [-b] vpl-file + +Vpl2ovp creates new Omega virtual fonts based on existing TeX +virtual fonts ("input fonts"). A successful run will read a vpl +(Virtual Property List) file and a definition file, and will generate +a new ovp file on standard output. The input font is assumed to adhere +to the standard TeX encoding for text fonts unless it was created with +the program afm2tfm, in which case it is assumed to conform to the +encoding specified in the file dvips.enc. In either case, the name +of the input font is assumed to be the name of the input file +without its .vpl extension: it must conform to normal TeX +conventions for naming fonts, as vpl2ovp attempts to draw +conclusions from it about the kind of font it is dealing with. + +In the case of a non-virtual font (such as the Computer Modern +fonts), use a pl (Property List) file, created with the standard +utility tftopl, as the input file in place of a vpl file; vpl2ovp +will make the necessary changes on the fly. + +A typical complete sequence of commands to create a new virtual +font might therefore be + tftopl cmr10.tfm cmr10.pl + vpl2ovp -d Unicode1.def cmr10.pl >cmr10-uni1.ovp + ovp2ovf cmr10-uni1.ovp cmr10-uni1.ovf cmr10-uni1.ofm +for a Computer Modern font, or + afm2pl Times-Roman.afm rptmr.pl + pltotf rptmr.pl rptmr.tfm + vpl2ovp -d Unicode1.def rptmr.pl >ptmr-uni1.ovp + ovp2ovf ptmr-uni1.ovp ptmr-uni1.ovf ptmr-uni1.ofm +for a PostScript font. + +Another approach for a PostScript font is to use afm2tfm: + afm2tfm Times-Roman.afm -t dvips.enc -v ptmr rptmr + vpl2ovp -d Unicode1.def ptmr.vpl >ptmr-uni1.ovp + ovp2ovf ptmr-uni1.ovp ptmr-uni1.ovf ptmr-uni1.ofm +-- but this is now deprecated, as afm2tfm generates incorrect +values for the heights of some characters, and this can lead to +bad accent placing. + +In order to keep the whole of the character range "F0-"FF free +for the requirements of the encoding specified in the definition +file, certain modifications are made to input fonts following the +dvips.enc encoding to bring them into greater conformity with the +TeX norm. In particular, the characters dotaccent and hungarumlaut +are placed in the positions assigned by TeX ("5F, "7D), not those +enforced by dvips.enc ("C7, "CD). The f-ligatures, double quotes +and dashes are also moved from the upper half of the character set +to their normal TeX positions. As a result, the following characters +are not found in the lower half of the character set: quotesingle, +quotedbl, backslash, underscore, braceleft, bar, braceright. These +characters can, however, be assigned positions in the output font if +they are needed. (Indeed, they could all be explicitly restored to +their dvips.enc positions if this were desired.) + +Options: + + -d should refer to a font definition file. This file (which could + usefully be named, e.g., "French.def") should consist of + lines of character definitions, in the form + "number" "character" + or + "number" "character" "accent" + Here "number" represents the character's position in the new + encoding and may be expressed in decimal, octal or hex; + "character" names the character (e.g. "comma", "eight", + "A") or consists of the word ".notdef" (indicating that + the specified number's "slot" in the new encoding is to be + empty); and "accent" optionally names an accent to be placed + on the character. In addition to the standard accents available + in PostScript fonts, "underbar" and "underdot" are also + available, as are "under" versions of all the normal + superscript accents ("underdieresis", "underring", etc.). + The Indian accent "candrabindu" may also be specified: it + is formed by overprinting a breve with a dotaccent. Finally, + "overdot" may be used as a synonym for "dotaccent". + + If the character named in the "accent" position is not in fact + a valid accent character, the program interprets the definition + as a request for a digraph formed from the "character" and the + "accent". A digraph consisting of, say, "k" and "h" will be + indistinguishable from the letters "k" and "h" printed + consecutively, but the digraph "kh" can itself receive accents + like any other character: see next paragraph. + + A new character (such as "amacron" or "kh") may be freely + used in the "character" position of a further definition (such + as "amacron breve" or "kh underbar"). There is no constraint + on the ordering of definitions within a definition file. The + definition of "a macron" does not have to precede that of + "amacron breve": requests for "impossible" characters are + deferred until their constituents have had a chance to come into + being. + + "Slots" for which no new definition is given retain the + definition they have in the input font. + + The definition file may also contain blank lines and comments + (introduced by "#"). + + -s may optionally give the factor, expressed as a per-thousand + value, by which normally superscript accents (such as dieresis, + ring) should be shrunk when they are used as subscript accents + (such as underdieresis, underring). Values of around 800 may be + found useful. + + -c may optionally give two comma-separated numerical values to + adjust the x and y coordinates of the dotaccent placed within a + breve to form the candrabindu accent. A coordinate scheme using + "DESIGNUNITS R 1000" is assumed. + + -b may optionally be specified to block the use of predefined + accented characters, forcing vpl2ovp to define its own + versions. This may be useful to secure a consistent appearance + in cases where a font designer does not share vpl2ovp's views + on where accents should be placed. + + -h prints this help. + + +John D. Smith +jds10@cam.ac.uk +http://bombay.indology.info diff --git a/Master/texmf-dist/doc/fonts/accfonts/mkt1font b/Master/texmf-dist/doc/fonts/accfonts/mkt1font new file mode 100755 index 00000000000..c092673cb3f --- /dev/null +++ b/Master/texmf-dist/doc/fonts/accfonts/mkt1font @@ -0,0 +1,980 @@ +#!/usr/bin/perl + +# Mkt1font: a program to generate accented Type 1 PostScript fonts +# Copyright (C) 1997 John D. Smith + +# 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., 675 Mass Ave, Cambridge, MA 02139, USA. + +$version = 0.23; +#-----------------------------------------------------------------------------# +$description = +"Syntax: mkt1font -n fontname -d definition-file -a afm-file -f font-file + [-s shrink-factor] [-c candrabindu-adjustment] [-b] + +Mkt1font creates new Type 1 PostScript fonts based on existing fonts +(\"input fonts\"). In order to do this it makes use of I. Lee +Hetherington's programs t1asm and t1disasm, which must be present on +the system. A successful run will generate an AFM file and a PFB +file, as well as a DIS file containing a disassembled version of the +PFB file (including useful comments). Four options must be specified +on the command line, as follows: + + -n should name the font it is intended to generate. Avoid names + such as \"myfont\", as both mkt1font and other programs attempt + to draw conclusions from the name; better would be something + like \"Utopia_French-BoldItalic\". The generated font files + will also use this for their basename. + + -d should refer to a font definition file. This file (which could + usefully be named, e.g., \"French.def\") should consist of + lines of character definitions, in the form + \"number\" \"character\" + or + \"number\" \"character\" \"accent\" + Here \"number\" represents the character's position in the new + encoding and may be expressed in decimal, octal or hex; + \"character\" names the character (e.g. \"comma\", \"eight\", + \"A\") or consists of the word \".notdef\" (indicating that + the specified number's \"slot\" in the new encoding is to be + empty); and \"accent\" optionally names an accent to be placed + on the character. In addition to the standard accents available + in PostScript fonts, \"underbar\" and \"underdot\" are also + available, as are \"under\" versions of all the normal + superscript accents (\"underdieresis\", \"underring\", etc.). + The Indian accent \"candrabindu\" may also be specified: it + is formed by overprinting a breve with a dotaccent. Finally, + \"overdot\" may be used as a synonym for \"dotaccent\". + + If the character named in the \"accent\" position is not in fact + a valid accent character, the program interprets the definition + as a request for a digraph formed from the \"character\" and the + \"accent\". A digraph consisting of, say, \"k\" and \"h\" will be + indistinguishable from the letters \"k\" and \"h\" printed + consecutively, but the digraph \"kh\" can itself receive accents + like any other character: see next paragraph. + + A new character (such as \"amacron\" or \"kh\") may be freely + used in the \"character\" position of a further definition (such + as \"amacron breve\" or \"kh underbar\"). There is no constraint + on the ordering of definitions within a definition file. The + definition of \"a macron\" does not have to precede that of + \"amacron breve\": requests for \"impossible\" characters are + deferred until their constituents have had a chance to come into + being. + + \"Slots\" for which no new definition is given retain the + definition they have in the input font. + + The definition file may also contain blank lines and comments + (introduced by \"\#\"). + + -a should refer to the AFM (Adobe Font Metrics) file for the input + font. + + -f should refer to the binary font file (PFB) for the input font. + (In fact the equivalent ASCII file (PFA) is also acceptable for + input, but the output font is always in PFB format.) + + -s may optionally give the factor, expressed as a per-thousand + value, by which normally superscript accents (such as dieresis, + ring) should be shrunk when they are used as subscript accents + (such as underdieresis, underring). Values of around 800 may be + found useful. + + -c may optionally give two comma-separated numerical values to + adjust the x and y coordinates of the dotaccent placed within a + breve to form the candrabindu accent. + + -b may optionally be specified to block the use of predefined + accented characters, forcing mkt1font to define its own + versions. This may be useful to secure a consistent appearance + in cases where a font designer does not share mkt1font's views + on where accents should be placed. + +The -h option prints this help. +"; +#-----------------------------------------------------------------------------# + +######################## +# Packages and constants +######################## +# +use File::Basename; +use Getopt::Std; +$cmdline = basename($0) . " " . join " ", @ARGV; +getopts('n:d:a:f:c:s:bh'); +if ($opt_h or !($opt_n && $opt_d && $opt_a && $opt_f) or ($#ARGV >= 0)) { + print STDERR $description; + exit 1; +} +($enc = basename($opt_d)) =~ s/\..*$//; +if ($opt_n =~ /\s/) { die "Font name cannot contain whitespace\n" } +($famname = $opt_n) =~ s/^(.*)-.*?$/$1/; +if ($opt_s) { $shrink = $opt_s / 1000 } else { $shrink = 1 } +@months = ( "January", "February", "March", "April", + "May", "June", "July", "August", + "September", "October", "November", "December" + ); +@lt = localtime; +$date = "$months[$lt[4]] $lt[3], ${ \($lt[5] + 1900) }"; +if ($opt_c) { ($cbx, $cby) = $opt_c =~ /^(.*),(.*)$/ } # candrabindu + +############### +# Read DEF file +############### +# +open DEF, $opt_d or die "Cannot open $opt_d: $!\n"; +while (<DEF>) { + next if (/^\s*$/ || /^\#/); + s/\s*(\#.*)?$//; + push @deflines, $_; +} +close DEF; + +############### +# Read AFM file +############### +# +# File header +# +open AFM, $opt_a or die "Cannot open $opt_a: $!\n"; +while (<AFM>) { + if (/^StartFontMetrics/) { + $afmhead = $_; + do { + $_ = <AFM>; + $afmhead .= $_; + } + until $_ =~ /^StartCharMetrics \d+\r?$/; + $afmhead =~ s/\r//gm; # Might be DOS file + $afmhead =~ /^FontName (.*)$/m; + $ofname = $1; + $afmbanner = "\nComment Based on $ofname; modified for $enc encoding"; + $afmbanner .= "\nComment by John Smiths's program mkt1font "; + $afmbanner .= "(v. $version) " if $version; + $afmbanner .= "on $date"; + $afmbanner .= "\nComment Command line: $cmdline"; + $afmhead =~ s/(\n^FontName )(.*)$/$1$opt_n/m; + $afmhead =~ s/(\n^FullName )(.*)$/$1$opt_n/m; + $afmhead =~ s/(\n^FamilyName )(.*)$/$1$famname/m; + $afmhead =~ s/\n^Comment /$afmbanner$&/m; + $afmhead =~ s/(\n^EncodingScheme ).*$/$1FontSpecific/m; + if ($afmhead =~ /\n^ItalicAngle (.*)$/m) { $italangle = $1 } + if ($afmhead =~ /\n^CapHeight (.*)$/m) { $capheight = $1 } + if ($afmhead =~ /\n^XHeight (.*)$/m) { $xheight = $1 } + if ($afmhead =~ /\n^FontBBox -?\d+ (-?\d+) (-?\d+) (-?\d+)$/m) { + ($maxdp, $maxrs, $maxht) = ($1, $2, $3); + } + } + # + # Encoded chars + # + if (/(^C (\d+) ; WX \d+ ; N ([a-zA-Z]+|\.notdef) ; B .* ;( L .* ;)?)\r?$/) { + $metrics_enc[$2] = "$1\n"; + } + # + # Unencoded chars + # + elsif (/(^C -1 ; WX \d+ ; N ([a-zA-Z]+|\.notdef) ; B .* ;( L .* ;)?)\r?$/) { + $metrics_unenc .= "$1\n"; + } + # + # Kerns etc. + # + if (/^EndCharMetrics\r?$/) { + $afmtail = $_; + do { + $_ = <AFM>; + $afmtail .= $_; + } + until eof(AFM); + $afmtail =~ s/[\r\cZ]//gm; # Might be DOS file + } +} +if ($afmtail =~ /(\A(?:.|\n)*^StartKernPairs )\d+\n((?:.|\n)*)(^EndKernPairs(?:.|\n)*\Z)/m) { + ($kstart, $kdefs, $kend) = ($1, $2, $3); +} +close AFM; + +############################### +# Read and disassemble PFB file +############################### +# +open PFB, $opt_f or die "Cannot open $opt_f: $!\n"; +$_ = <PFB>; +unless (/%!/) { die "File $opt_f is not a PostScript font\n" } +close PFB; +$disfile1 = "mkt1font$$.dis"; +system "t1disasm $opt_f >$disfile1 2>/dev/null"; +open DIS, $disfile1 or die "Cannot open disassembled font file: $!\n"; +while (<DIS>) { + # + # Locate crucial definitions + # + if (/^\/(.*?) ?{ ?noaccess def ?} ?executeonly def$/) { + $nd = $1; + ($rend = $nd) =~ s/\|/\\|/g; # Regexp version + next; + } + if (/^\/(.*?) ?{ ?noaccess put ?} ?executeonly def$/) { + $np = $1; + ($renp = $np) =~ s/\|/\\|/g; # Regexp version + next; + } + if (/^\/Subrs (\d+) array/) { + $subrsnum = $1; + do { + # + # Store subroutine definitions in @subrs + # + $l = $_ = <DIS>; + if (/^dup (\d+) {$/) { + $subrnum = $1; + $subrdef = $_; + do { + $_ = <DIS>; + $subrdef .= $_; + } + until /^\t} ?$renp$/; + } + # + # "correct" t1disasm output so t1asm will accept it as input + # + $subrdef =~ s/^(\t})($rend|$renp)$/$1 $2/m; + $subrs[$subrnum] = $subrdef; + } + until ($l !~ /^dup \d+ {$/); + next; + } + if (/^2 index \/CharStrings (\d+) dict dup begin/) { + # + # do *not* use "$" to anchor the end of this line, because + # it may end with an invisible trailing space! + # + $chdefsnum = $1; + do { + # + # Store character definitions in %chstrings + # + $l = $_ = <DIS>; + if (/^\/([a-zA-Z]+|\.notdef|\.null) {$/) { + $chname = $1; + $chdef = $_; + do { + $_ = <DIS>; + $chdef .= $_; + } + until /^\t} ?$rend$/; + } + # + #"correct" t1disasm output so t1asm will accept it as input + # + $chdef =~ s/^(\t})($rend|$renp)$/$1 $2/m; + $chstrings{$chname} = $chdef; + } + until ($l !~ /^\/([a-zA-Z]+|\.notdef|\.null) {$/); + next; + } + # + # File tail + # + if (/^end$/) { + $distail = $_; + do { + $_ = <DIS>; + $distail .= $_; + } + until eof(DIS); + } +} +close DIS; +unless ($nd) { die "Cannot find \"noaccess def\" definition\n" } +unless ($np) { die "Cannot find \"noaccess put\" definition\n" } +unless ($subrsnum) { die "Cannot find size of Subrs array\n" } +unless ($chdefsnum) { die "Cannot find size of CharStrings dict\n" } + +################## +# Set up constants +################## +# +$subacc = "(cedilla|ogonek|commaaccent)"; +$supacc = "(grave|acute|circumflex|tilde|macron|breve|dotaccent|overdot|dieresis|ring|hungarumlaut|caron|candrabindu)"; +$underacc = "(underdot|under$supacc)"; +$accents = "($subacc|$supacc|$underacc|underbar)"; +$underadp = -230; # depth of "under" accs +$underddp = -213; # depth of underdot +if ($opt_n =~ /Bold/) { $thk = 72 } else { $thk = 52 } # thickness and +$underbdp = -(82 + $thk); # depth of underbar +getcharinfo("macron"); +$accheight = $chht{macron}; # height of macron +$accdepth = $chdp{macron}; # "depth" of macron +$v1 = $accheight - $xheight; # vertical offset for double accents +$v2 = $capheight - $xheight; # vertical offset for accented caps etc +# +# Italic adjustment: tan(angle) +# +$itadj = sin($italangle * 3.14159 / 180) / cos($italangle * 3.14159 / 180); + +###################### +# Build the characters +###################### +# +# +# First build a list of definitions supplied by user +# +for (@deflines) { + if (/^\s*(\d+|0[0-7]+|0x[0-9a-fA-F]+)\s+([a-zA-Z]+?|\.notdef)(?:\s+([a-zA-Z]+))?$/) { + ($num, $char, $acc) = ($1, $2, $3); + $num = oct $num if $num =~ /^0/; + if ($num > 255) { die "Bad definition (number out of range): $_\n" } + $def = {}; + $def->{qdef} = $_; + $def->{num} = $num; + $def->{char} = $char; + $def->{acc} = $acc; + $def->{nchar} = $char . $acc; + push @nchars, $def->{nchar}; + push @defs, $def; + } + else { die "Bad definition: $_\n" } +} +# +# Work through the list +# +while (@defs) { + $def = shift @defs; + $qdef = $def->{qdef}; + $num = $def->{num}; + $char = $def->{char}; + $acc = $def->{acc}; + $nchar = $def->{nchar}; + # + # If we can't handle $char/$acc yet, but believe we will be able + # to later, send the definition to the back of the queue. In case + # it later turns out we were wrong, allow only five loops before + # giving up. + # + if (!grep / ; N $char ; /, @metrics_enc + and $metrics_unenc !~ / ; N $char ; /m) { + if (grep /^$char$/, @nchars) { + unless (++$def->{requeue} > 5) { + push @defs, $def; + next; + } + } + else { die "Bad definition (no such character): $qdef\n" } + } + if ($acc + and !grep / ; N $acc ; /, @metrics_enc + and $metrics_unenc !~ / ; N $acc ; /m + and $acc !~ /^$accents$/) { + if (grep /^$acc$/, @nchars) { + unless (++$def->{requeue} > 5) { + push @defs, $def; + next; + } + } + else { die "Bad definition (no such accent): $qdef\n" } + } + # + # First deal with .notdef + # + if ($nchar eq ".notdef") { + ($old = $metrics_enc[$num]) =~ s/^C $num/C -1/; + $metrics_unenc .= $old unless $metrics_unenc =~ /$old/m; + undef $metrics_enc[$num]; + } + # + # Now look for new char among existing encoded chars (unless blocked by -b) + # + else { + if (!($acc and $opt_b) + and @foundit = grep / ; N $nchar ; /, @metrics_enc) { + ($foundit = shift @foundit) =~ s/^C (\d+)/C $num/; + $prevnum = $1; + unless ($prevnum == $num) { + ($old = $metrics_enc[$num]) =~ s/^C $num/C -1/; + $metrics_unenc .= $old unless $metrics_unenc =~ /$old/m; + $metrics_enc[$num] = $foundit; + } + fixkerns($char, $acc); + } + # + # Next look among existing unencoded chars (unless blocked by -b) + # + elsif (!($acc and $opt_b) + and $metrics_unenc =~ s/^C -1 ; WX \d+ ; N $nchar ; B .* ;( L .* ;)?\n//m) { + ($foundit = $&) =~ s/^C -1/C $num$1/m; + $old = $metrics_enc[$num]; + if ($old) { + $old =~ s/^C $num/C -1/; + $metrics_unenc .= $old unless $metrics_unenc =~ /$old/m; + } + $metrics_enc[$num] = $foundit; + fixkerns($char, $acc); + } + # + # If it can't be built from sub-elements, issue a warning and move on + # + elsif (!$acc) { warn "No such character - ignoring definition: $qdef\n" } + # + # Now build the char + # + else { + # + # First get rid of predefined afm entries and synonyms + # + $metrics_unenc =~ s/^C -1 ; WX \d+ ; N $nchar ; B .* ;( L .* ;)?\n//m; + $kdefs =~ s/\nKPX .*$nchar .*$//gm; + if ($acc eq "overdot") { + $nchar2 = $char . "dotaccent"; + $metrics_unenc =~ s/^C -1 ; WX \d+ ; N $nchar2 ; B .* ;( L .* ;)?\n//m; + $kdefs =~ s/\nKPX .*$nchar2 .*$//gm; + delete $chstrings{$nchar2}; + } + # + # Go! + # + if ($acc =~ /^$subacc$/) { + subacc($num, $char, $acc, $nchar); + fixkerns($char, $acc); + } + elsif ($acc =~ /^$supacc$/) { + supacc($num, $char, $acc, $nchar); + fixkerns($char, $acc); + } + elsif ($acc =~ /^$underacc$/) { + underacc($num, $char, $acc, $nchar); + fixkerns($char, $acc); + } + elsif ($acc =~ /^underbar$/) { + underb($num, $char, $nchar); + fixkerns($char, $acc); + } + else { + digraph($num, $char, $acc, $nchar); + fixkerns($char, $acc); + } + } + } +} + +################ +# Write AFM file +################ +# +open OUTAFM, ">$opt_n.afm"; +foreach (@metrics_enc) { # Avoid duplicate entries + ($chname) = /( ; N [a-zA-Z]+ ; )/; + $metrics_unenc =~ s/^C -1 .*$chname.*\n//gm if $chname; +} +$chmetricnum = split(/\n/, $metrics_unenc); +$chmetricnum += grep /^C /, @metrics_enc; +$afmhead =~ s/^(FontBBox -?\d+ )-?\d+ -?\d+ -?\d+$/$1$maxdp $maxrs $maxht/m; +$afmhead =~ s/^(StartCharMetrics )\d+$/$1$chmetricnum/m; +$encoding = "/Encoding 256 array\n0 1 255 {1 index exch /.notdef put} for\n"; +print OUTAFM $afmhead; +for $i (0 .. 255) { + $line = $metrics_enc[$i]; + if ($line) { + print OUTAFM $line; + if ($line =~ /^C \d+ ; WX \d+ ; N ([a-zA-Z]*) ; /) { + $encoding .= "dup $i /$1 put\n"; + } + } +} +$encoding .= "readonly def\n"; +print OUTAFM $metrics_unenc; +# +# Tidy up kerns +# +if ($kdefs) { + $kdefs = join("\n", sort split /\n/, $kdefs); # sort + $kdefs .= "\n"; + $kdefs =~ s/((^KPX .*?)-?\d+$)\n\2.*$/$1/gm; # remove duplicates + $kdefs =~ s/^\s*\n//gm; # and blank lines + $knum = split(/\n/, $kdefs); + $afmtail = $kstart . $knum . "\n" . $kdefs . $kend; +} +# +# Eliminate composite character definitions +# +$afmtail =~ s/\n(Start|End)Composites.*$//gm; +$afmtail =~ s/\nCC .*;$//gm; +print OUTAFM $afmtail; +close OUTAFM; + +######################### +# Write DIS and PFB files +######################### +# +$disfile2 = "$opt_n.dis"; +open OUTDIS, ">$disfile2"; +$disbanner = "% Based on $ofname; modified for $enc encoding\n"; +$disbanner .= "% by John Smiths's program mkt1font "; +$disbanner .= "(v. $version) " if $version; +$disbanner .= "on $date\n"; +$disbanner .= "% Command line: $cmdline"; +open DIS, $disfile1; +while (<DIS>) { # get header + s/^(%!.*: ).*$/$1$opt_n\n$disbanner/; + s/^(\/FullName \().*(\).*)$/$1$opt_n$2/; + s/^(\/FamilyName \().*(\).*)$/$1$famname$2/; + s/^(\/FontName \/).*?( .*)$/$1$opt_n$2/; + s/^(\/FontBBox {-?\d+ )-?\d+ -?\d+ -?\d+/$1$maxdp $maxrs $maxht/m; + if (/^\/Encoding /) { + print OUTDIS $encoding; + next; + } + next if (/^\/UniqueID .*$/); + s /^(\/BlueValues \[.*)(\] def)$/$1 $accheight $accheight$2/; + if (/^(\/Subrs )\d+( array)$/) { + print OUTDIS "$1$subrsnum$2\n"; + last; + } + else { print OUTDIS } +} +close DIS; +unlink $disfile1; +foreach $subrdef (@subrs) { print OUTDIS $subrdef } +print OUTDIS "$nd\n2 index /CharStrings $chdefsnum dict dup begin\n"; +foreach $chdef (sort values %chstrings) { print OUTDIS $chdef } +print OUTDIS $distail; +close OUTDIS; +system "t1asm -b $disfile2 >$opt_n.pfb 2>/dev/null"; + +##################### +# End of main program +##################### + +sub subacc { + # + # Subscript accents + # + my ($num, $char, $acc, $nchar) = @_; + my ($old, $astr, $h, $H, $V, $chdef, $acdef, $pstr); + ($old = $metrics_enc[$num]) =~ s/^C $num/C -1/; + $metrics_unenc .= $old unless $metrics_unenc =~ /$old/m; + getcharinfo($char) unless defined $chwd{$char}; + getcharinfo($acc) unless defined $chwd{$acc}; + $astr = "C $num ; WX $chwd{$char} ; N $nchar ; B $chls{$char} "; + $astr .= "$chdp{$acc} $chrs{$char} $chht{$char} ;\n"; + $metrics_enc[$num] = $astr; + $h = int(($chwd{$char} - $chwd{$acc}) / 2 + $chls{$acc}); + unless (defined $hend{$char}) { findend($char, $chstrings{$char}) } + $H = $h - $hend{$char} - $chls{$char}; + $V = -$vend{$char}; + $chstrings{$char} =~ /^\/$char {\n(\t.+?hsbw\n(.|\n)*?)\tendchar\n\t} $rend\n/m; + $chdef = $1; + $chstrings{$acc} =~ /^\/$acc {\n\t.+? .+?hsbw\n((.|\n)+?\t} $rend\n)/m; + $acdef = $1; + $acdef = fixhints($nchar, $acc, $acdef, $h, 0); + $pstr = "/$nchar {\n$chdef % $nchar: start of $acc\n"; + $pstr .= "\t$H $V rmoveto\n$acdef"; + $chstrings{$nchar} = $pstr; + $chdefsnum += 1; +} + +sub supacc { + # + # Superscript accents + # + my ($num, $char, $acc, $nchar) = @_; + my ($old, $cb, $astr, $h, $v, $H, $V, $it, $chdef, $acdef, $pstr, $newchar); + ($old = $metrics_enc[$num]) =~ s/^C $num/C -1/; + $metrics_unenc .= $old unless $metrics_unenc =~ /$old/m; + if ($char eq "i") { $char = "dotlessi" } + if ($acc eq "overdot") { $acc = "dotaccent" } + if ($acc eq "candrabindu") { + $acc = "breve"; + $chstrings{"dotaccent"} =~ /^\/dotaccent {\n\t.+? .+?hsbw\n((.|\n)+?\t} $rend\n)/m; + $cb = $1; + } + getcharinfo($char) unless defined $chwd{$char}; + getcharinfo($acc) unless defined $chwd{$acc}; + $astr = "C $num ; WX $chwd{$char} ; N $nchar ; B "; + $astr .= "$chls{$char} $chdp{$char} $chrs{$char} "; + $v = $chht{$acc}; + if ($chht{$char} >= $accheight + $v2) { # double accs + $v += ($v1 + $v2); # on caps etc. + $it = ($v1 + $v2) * $itadj; + } + elsif ($chht{$char} > 1.15 * $xheight) { + if ($char =~ /$supacc$/ and $char !~ /under$supacc$/) { + $v += $v1; # double accents + $it = $v1 * $itadj; + } + else { + $v += $v2; # accented caps etc. + $it = $v2 * $itadj; + } + } + else { $it = 0 } + if ($v > $maxht) { $maxht = $v } + $astr .= "$v ;\n"; + $metrics_enc[$num] = $astr; + $v -= $chht{$acc}; + $h = int(($chwd{$char} - $chwd{$acc}) / 2 + $chls{$acc} - $it); + unless (defined $hend{$char}) { findend($char, $chstrings{$char}) } + $H = $h - $hend{$char} - $chls{$char}; + $V = $v - $vend{$char}; + $chstrings{$char} =~ /^\/$char {\n(\t.+?hsbw\n(.|\n)*?)\tendchar\n\t} $rend\n/m; + $chdef = $1; + $chstrings{$acc} =~ /^\/$acc {\n\t.+? .+?hsbw\n((.|\n)+?\t} $rend\n)/m; + $acdef = $1; + $acdef = fixhints($nchar, $acc, $acdef, $h, $v); + $pstr = "/$nchar {\n$chdef % $nchar: start of $acc\n"; + $pstr .= "\t$H $V rmoveto\n$acdef"; + if ($cb) { # candrabindu + getcharinfo("dotaccent") unless defined $chwd{dotaccent}; + $h = int(($chwd{$char} - $chwd{dotaccent}) / 2 + $chls{dotaccent} - $it); + $h += $cbx; + $v += $cby; + $cb = fixhints($nchar, "dotaccent", $cb, $h, $v); + $newchar = $char . $acc; + unless (defined $hend{$newchar}) { findend($newchar, $pstr) } + $H = $h - $hend{$newchar} - $chls{$char}; + $V = $v - $vend{$newchar}; + $pstr =~ s/\tendchar\n\t} $rend\n\Z//m; + $pstr .= " % $nchar: start of dotaccent\n\t$H $V rmoveto\n$cb"; + } + $chstrings{$nchar} = $pstr; + $chdefsnum += 1; +} + +sub underacc { + # + # Dropped accents + # + # The Fontographer hack below is necessary because Fontographer (which + # I have had to use to build TrueType and Macintosh versions of fonts) + # seems not to respect the depths for characters specified in afm files + # it has imported: it sets the depth to the lowest point in the path, + # whether or not a mark was made there. So it is not possible to + # implement (e.g.) underring by diving down low and then printing a + # ring at its normal height. + # + my ($num, $char, $acc, $nchar) = @_; + my ($old, $acname, $astr, $h, $v, $H, $V, $chdef, $acdef, $begin, $line, $end, $pstr); + ($old = $metrics_enc[$num]) =~ s/^C $num/C -1/; + $metrics_unenc .= $old unless $metrics_unenc =~ /$old/m; + $acc =~ s/^under//; + $acname = $acc; + if ($acc eq "dot") { $acc = "period" } + if ($acc eq "candrabindu") { die "Bad definition (no such accent): $qdef\n" } + getcharinfo($char) unless defined $chwd{$char}; + getcharinfo($acc) unless defined $chwd{$acc}; + if ($acc =~ /^$supacc$/) { + $v = int($underadp + ($chdp{$acc} - $accdepth) * $shrink); + } + else { $v = $underddp + $chdp{$acc} } + if ($v < $maxdp) { $maxdp = $v } + $astr = "C $num ; WX $chwd{$char} ; N $nchar ; B $chls{$char} "; + $astr .= "$v $chrs{$char} $chht{$char} ;\n"; + $metrics_enc[$num] = $astr; + if ($acc =~ /^$supacc$/) { + $h = int(($chwd{$char} - ($chwd{$acc} * $shrink)) / 2 + + $chls{$acc} * $shrink - ($v - $accdepth * $shrink) * $itadj); + } + else { + $h = int(($chwd{$char} - $chwd{$acc}) / 2 + $chls{$acc} - $v * $itadj); + } + unless (defined $hend{$char}) { findend($char, $chstrings{$char}) } + $H = $h - $hend{$char} - $chls{$char}; + if ($acc =~ /^$supacc$/) { $V = $underadp - $vend{$char} } + else { $V = $underddp - $vend{$char} } + # + # Adjustment for smaller, therefore lower, shrunken accent defs + # + if ($acc =~ /^$supacc$/) { + $V += int($chdp{$acc} * (1 - $shrink) / $shrink); + } + $chstrings{$char} =~ /^\/$char {\n(\t.+?hsbw\n(.|\n)*?)\tendchar\n\t} $rend\n/m; + $chdef = $1; + $chstrings{$acc} =~ /^\/$acc {\n\t.+? .+?hsbw\n((.|\n)+?\t} $rend\n)/m; + $acdef = $1; + if ($acc =~ /^$supacc$/ and $opt_s) { $acdef = fixshrink($acc, $acdef) } + if ($acc =~ /^$supacc$/) { + $acdef = fixhints($nchar, $acc, $acdef, $h, $underadp); + } + else { $acdef = fixhints($nchar, $acc, $acdef, $h, $underddp) } + # + # Bloody Fontographer! We can't just say + # if ($acc =~ /^$supacc$/) { $V -= $accdepth } + # Instead we have to go through the following rigmarole: + # + if ($acc =~ /^$supacc$/) { + if ($acdef =~ /^(.*moveto)$/m) { + ($begin, $line, $end) = ($`, $1, $'); + if ($line =~ /^\t(-?\d+) (-?\d+)( rmoveto)$/) { + $acdef = "$begin\t$1 " . ($2 - $accdepth) . $3 . $end; + } + elsif ($line =~ /^\t(-?\d+)( vmoveto)$/) { + $acdef = "$begin\t" . ($1 - $accdepth) . $2 . $end; + } + elsif ($line =~ /\t(-?\d+) hmoveto$/) { + $acdef = "$begin\t$1 " . (-$accdepth) . "rmoveto" . $end; + } + } + else { $acdef =~ s/\A/\t-$accdepth vmoveto\n/m } + } + $pstr = "/$nchar {\n$chdef % $nchar: start of $acname\n"; + $pstr .= "\t$H $V rmoveto\n$acdef"; + $chstrings{$nchar} = $pstr; + $chdefsnum += 1; +} + +sub underb { + # + # Underbar + # + my ($num, $char, $nchar) = @_; + my ($old, $astr, $l, $h, $v, $H, $V, $bdef, $chdef, $acdef, $pstr); + ($old = $metrics_enc[$num]) =~ s/^C $num/C -1/; + $metrics_unenc .= $old unless $metrics_unenc =~ /$old/m; + $v = $underbdp + $thk; + getcharinfo($char) unless defined $chwd{$char}; + $h = int(0.1 * $chwd{$char} - $underbdp * $itadj); + $l = int(0.8 * $chwd{$char}); + $astr = "C $num ; WX $chwd{$char} ; N $nchar ; B $chls{$char} "; + $astr .= "$underbdp $chrs{$char} $chht{$char} ;\n"; + $metrics_enc[$num] = $astr; + unless (defined $hend{$char}) { findend($char, $chstrings{$char}) } + $H = $h - $hend{$char} - $chls{$char}; + $V = -$vend{$char}; + $bdef = "\t$underbdp $thk hstem\n\t$v vmoveto\n\t-$thk vlineto\n\t"; + $bdef .= "$l hlineto\n\t$thk vlineto\n\tclosepath\n"; + $chstrings{$char} =~ /^\/$char {\n(\t.+?hsbw\n(.|\n)*?)\tendchar\n\t} $rend\n/m; + $chdef = $1; + $acdef = fixhints($nchar, "underbar", $bdef, $h, 0); + $pstr = "/$nchar {\n$chdef % $nchar: start of $acc\n"; + $pstr .= "\t$H $V rmoveto\n$acdef\tendchar\n\t} $nd\n"; + $chstrings{$nchar} = $pstr; + $chdefsnum += 1; +} + +sub digraph { + # + # Make a new character consisting of two existing characters + # + my ($num, $char, $acc, $nchar) = @_; + my ($old, $kern, $w, $newrs, $astr, $H, $V, $chdef, $acdef, $pstr); + ($old = $metrics_enc[$num]) =~ s/^C $num/C -1/; + $metrics_unenc .= $old unless $metrics_unenc =~ /$old/m; + getcharinfo($char) unless defined $chwd{$char}; + getcharinfo($acc) unless defined $chwd{$acc}; + if ($kdefs =~ /^KPX $char $acc (-?\d+)$/m) { $kern = $1 }; + $w = $chwd{$char} + $chwd{$acc} + $kern; + $newrs = $chrs{$char} + $chwd{$acc} + $kern; + if ($newrs > $maxrs) { $maxrs = $newrs } + $astr = "C $num ; WX " . $w . " ; N $nchar ; B $chls{$char} "; + $astr .= (min($chdp{$char}, $chdp{$acc})) . " $newrs "; + $astr .= (max($chht{$char}, $chht{$acc})) . " ;\n"; + $metrics_enc[$num] = $astr; + unless (defined $hend{$char}) { findend($char, $chstrings{$char}) } + $H = $chwd{$char} + $chls{$acc} + $kern - $hend{$char} - $chls{$char}; + $V = -$vend{$char}; + $chstrings{$char} =~ /^\/$char {\n(\t.+?hsbw\n(.|\n)*?)\tendchar\n\t} $rend\n/m; + ($chdef = $1) =~ s/-?\d+( hsbw\n)/$w$1/m; + $chstrings{$acc} =~ /^\/$acc {\n\t.+? .+?hsbw\n((.|\n)+?\t} $rend\n)/m; + $acdef = $1; + $acdef = fixhints($nchar, $acc, $acdef, ($chwd{$char} + $kern), 0); + $pstr = "/$nchar {\n$chdef % $nchar: start of $acc\n"; + $pstr .= "\t$H $V rmoveto\n$acdef"; + $chstrings{$nchar} = $pstr; + $chdefsnum += 1; +} + +sub max { + # + # Return greater of two values + # + my ($a, $b) = @_; + return $a > $b ? $a : $b; +} + +sub min { + # + # Return lesser of two values + # + my ($a, $b) = @_; + return $a > $b ? $b : $a; +} + +sub getcharinfo { + # + # Store character metric information + # + my $char = shift; + my $foundit; + my $metrics_all = join("", @metrics_enc) . $metrics_unenc; + if ($metrics_all =~ /^.* ; N $char ; .*$/m) { $foundit = $& } + else { die "Bad definition (no such character/accent): $char\n" } + $foundit =~ /^C (-?\d+) ; WX (\d+) ; N $char ; B (.+?) (.+?) (.+?) (.+?) ;/; + ($chnum{$char}, $chwd{$char}, $chls{$char}, + $chdp{$char}, $chrs{$char}, $chht{$char}) = ($1, $2, $3, $4, $5, $6); +} + +sub fixkerns { + # + # Generalise the kerning info contained in the afm file by applying + # it to new accented chars. Do not kern lower-case chars bearing + # superscript accents with capitals, quotes or a preceding "f". + # + my ($char, $acc) = @_; + my ($lchar, $rchar); + if ($acc =~ /^$accents$/) { $lchar = $rchar = $char } + else { + $lchar = $char; + $rchar = $acc; + } + if ($char =~ /^[a-z]/ and $acc =~ /^$supacc$/) { + if ($kdefs =~ /^(KPX $char)(( (?:[a-pr-z][a-zA-Z]*|q(?!uote).*?) )-?\d+)$/m) { + ($one, $three) = ($1, $3); + $kdefs =~ s[^(KPX $char)(( (?:[a-pr-z][a-zA-Z]*|q(?!uote).*?) )-?\d+)$] + [$&\n$1$acc$2]gm + unless $kdefs =~ /^$one$acc$three/m; + } + if ($kdefs =~ /^(KPX (?:[a-eg-pr-z][a-zA-Z]*|q(?!uote).*?) $char)( -?\d+)$/m) { + $one = $1; + $kdefs =~ s[^(KPX (?:[a-eg-pr-z][a-zA-Z]*|q(?!uote).*?) $char)( -?\d+)$] + [$&\n$1$acc$2]gm + unless $kdefs =~ /^$one$acc /m; + } + } + else { + if ($kdefs =~ /^(KPX )$rchar(( [a-zA-Z]+ )-?\d+)$/m) { + ($one, $three) = ($1, $3); + $kdefs =~ s[^(KPX )$rchar(( [a-zA-Z]+ )-?\d+)$] + [$&\n$1$char$acc$2]gm + unless $kdefs =~ /^$one$char$acc$three/m; + } + if ($kdefs =~ /^(KPX [a-zA-Z]+ )$char( -?\d+)$/m) { + $one = $1; + $kdefs =~ s[^(KPX [a-zA-Z]+ )$char( -?\d+)$] + [$&\n$1$char$acc$2]gm + unless $kdefs =~ /^$one$char$acc /m; + } + } +} + +sub fixshrink { + # + # Multiply all coordinates in a character definition by $shrink, + # creating new subroutines as necessary. + # + my ($ch, $chdef) = @_; + my (@chdef, $line, $snum, $subrdef); + @chdef = split(/\n/, $chdef); + $chdef = ""; + foreach $line (@chdef) { + if ($line =~ /^\t(\d+) .*call(other)?subr$/) { + $snum = $1; + $subrdef = $subrs[$snum]; + $subrdef = fixshrink($ch, $subrdef); + $subrdef =~ s/^(dup )$snum \{$/$1$subrsnum {\n % $nchar: shrink $ch/m; + $subrs[$subrsnum] = $subrdef; + $line =~ s/^\t$snum/\t$subrsnum/; + $subrsnum++; + } + else { $line =~ s/-?\d+/int($& * $shrink)/ge unless $line =~ /^dup / } + $chdef .= "$line\n"; + } + return $chdef; +} + +sub fixhints { + # + # Collect the hints from the accent definition, remove them, adjust + # for horizontal and vertical offset, and place them in a numbered + # subroutine. Have the definition call the subroutine. + # + my ($nchar, $acc, $acdef, $h, $v) = @_; + my $subrdef; + if ($subrdef = join("\n", grep /^\t.*[hv]stem$/, split(/\n/, $acdef))) { + $acdef = join("\n", grep !/^\t.*[hv]stem$/, split(/\n/, $acdef)) . "\n"; + } + elsif ($acdef =~ s/\A(?:\t(\d+) callsubr\n)((?:.|\n)*)\Z/$2/m) { + $subrdef = $subrs[$1]; + $subrdef = join("\n", grep /^\t.*[hv]stem$/, split(/\n/, $subrdef)) + } + $subrdef =~ s/^(\t)(-?\d+)( .*hstem)$/$1 . ($2 + $v) . $3/gme; + $subrdef =~ s/^(\t)(-?\d+)( .*vstem)$/$1 . ($2 + $h) . $3/gme; + if ($subrdef) { + $subrs[$subrsnum] = "dup $subrsnum {\n % $nchar: hints for $acc\n"; + $subrs[$subrsnum] .= "$subrdef\n\treturn\n\t} $np\n"; + $acdef = "\t$subrsnum 1 3 callothersubr\n\tpop\n\tcallsubr\n" . $acdef; + $subrsnum++; + } + return $acdef; +} + +sub findend { + # + # Calculate the current point reached at the end of the character + # definition. Place the horizontal offset in $hend{$char}, the + # vertical offset in $vend{$char}. + # + my ($char, $def) = @_; + my $line; + foreach $line (split /\n/, $def) { + SWITCH: { + $line =~ /^\t(-?\d+) h(line|move)to$/ + && do { + $hend{$char} += $1; + last SWITCH; + }; + $line =~ /^\t(-?\d+) v(line|move)to$/ + && do { + $vend{$char} += $1; + last SWITCH; + }; + $line =~ /^\t(-?\d+) (-?\d+) r(line|move)to$/ + && do { + $hend{$char} += $1; + $vend{$char} += $2; + last SWITCH; + }; + $line =~ /^\t(-?\d+) (-?\d+) (-?\d+) (-?\d+) hvcurveto$/ + && do { + $hend{$char} += ($1 + $2); + $vend{$char} += ($3 + $4); + last SWITCH; + }; + $line =~ /^\t(-?\d+) (-?\d+) (-?\d+) (-?\d+) vhcurveto$/ + && do { + $hend{$char} += ($2 + $4); + $vend{$char} += ($1 + $3); + last SWITCH; + }; + $line =~ /^\t(-?\d+) (-?\d+) (-?\d+) (-?\d+) (-?\d+) (-?\d+) rrcurveto$/ + && do { + $hend{$char} += ($1 + $3 + $5); + $vend{$char} += ($2 + $4 + $6); + last SWITCH; + }; + $line =~ /^\t(\d+) callsubr$/ + && do { + findend($char, $subrs[$1]); + last SWITCH; + }; + $line =~ /1 callothersubr$/ + && do { + print STDERR "Warning: definition of character $char uses Flex\n"; + last SWITCH; + }; + } + } +} diff --git a/Master/texmf-dist/doc/fonts/accfonts/vpl2ovp b/Master/texmf-dist/doc/fonts/accfonts/vpl2ovp new file mode 100755 index 00000000000..3bbc62ad669 --- /dev/null +++ b/Master/texmf-dist/doc/fonts/accfonts/vpl2ovp @@ -0,0 +1,1070 @@ +#!/usr/bin/perl + +# Vpl2ovp: a program to generate accented virtual fonts for Omega +# Copyright (C) 2008 John D. Smith + +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. + +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. + +# You should have received a copy of the GNU General Public License +# along with this program; if not, write to the Free Software +# Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. + +$version = 0.23; +#------------------------------------------------------------------------# +$description = +"Syntax: vpl2ovp -d definition-file [-s shrink-factor] + [-c candrabindu-adjustment] [-b] vpl-file + +Vpl2ovp creates new Omega virtual fonts based on existing TeX +virtual fonts (\"input fonts\"). A successful run will read a vpl +(Virtual Property List) file and a definition file, and will generate +a new ovp file on standard output. The input font is assumed to adhere +to the standard TeX encoding for text fonts unless it was created with +the program afm2tfm, in which case it is assumed to conform to the +encoding specified in the file dvips.enc. In either case, the name +of the input font is assumed to be the name of the input file +without its .vpl extension: it must conform to normal TeX +conventions for naming fonts, as vpl2ovp attempts to draw +conclusions from it about the kind of font it is dealing with. + +In the case of a non-virtual font (such as the Computer Modern +fonts), use a pl (Property List) file, created with the standard +utility tftopl, as the input file in place of a vpl file; vpl2ovp +will make the necessary changes on the fly. + +A typical complete sequence of commands to create a new virtual +font might therefore be + tftopl cmr10.tfm cmr10.pl + vpl2ovp -d Unicode1.def cmr10.pl >cmr10-uni1.ovp + ovp2ovf cmr10-uni1.ovp cmr10-uni1.ovf cmr10-uni1.ofm +for a Computer Modern font, or + afm2pl Times-Roman.afm rptmr.pl + pltotf rptmr.pl rptmr.tfm + vpl2ovp -d Unicode1.def rptmr.pl >ptmr-uni1.ovp + ovp2ovf ptmr-uni1.ovp ptmr-uni1.ovf ptmr-uni1.ofm +for a PostScript font. + +Another approach for a PostScript font is to use afm2tfm: + afm2tfm Times-Roman.afm -t dvips.enc -v ptmr rptmr + vpl2ovp -d Unicode1.def ptmr.vpl >ptmr-uni1.ovp + ovp2ovf ptmr-uni1.ovp ptmr-uni1.ovf ptmr-uni1.ofm +-- but this is now deprecated, as afm2tfm generates incorrect +values for the heights of some characters, and this can lead to +bad accent placing. + +In order to keep the whole of the character range \"F0-\"FF free +for the requirements of the encoding specified in the definition +file, certain modifications are made to input fonts following the +dvips.enc encoding to bring them into greater conformity with the +TeX norm. In particular, the characters dotaccent and hungarumlaut +are placed in the positions assigned by TeX (\"5F, \"7D), not those +enforced by dvips.enc (\"C7, \"CD). The f-ligatures, double quotes +and dashes are also moved from the upper half of the character set +to their normal TeX positions. As a result, the following characters +are not found in the lower half of the character set: quotesingle, +quotedbl, backslash, underscore, braceleft, bar, braceright. These +characters can, however, be assigned positions in the output font if +they are needed. (Indeed, they could all be explicitly restored to +their dvips.enc positions if this were desired.) + +Options: + + -d should refer to a font definition file. This file (which could + usefully be named, e.g., \"French.def\") should consist of + lines of character definitions, in the form + \"number\" \"character\" + or + \"number\" \"character\" \"accent\" + Here \"number\" represents the character's position in the new + encoding and may be expressed in decimal, octal or hex; + \"character\" names the character (e.g. \"comma\", \"eight\", + \"A\") or consists of the word \".notdef\" (indicating that + the specified number's \"slot\" in the new encoding is to be + empty); and \"accent\" optionally names an accent to be placed + on the character. In addition to the standard accents available + in PostScript fonts, \"underbar\" and \"underdot\" are also + available, as are \"under\" versions of all the normal + superscript accents (\"underdieresis\", \"underring\", etc.). + The Indian accent \"candrabindu\" may also be specified: it + is formed by overprinting a breve with a dotaccent. Finally, + \"overdot\" may be used as a synonym for \"dotaccent\". + + If the character named in the \"accent\" position is not in fact + a valid accent character, the program interprets the definition + as a request for a digraph formed from the \"character\" and the + \"accent\". A digraph consisting of, say, \"k\" and \"h\" will be + indistinguishable from the letters \"k\" and \"h\" printed + consecutively, but the digraph \"kh\" can itself receive accents + like any other character: see next paragraph. + + A new character (such as \"amacron\" or \"kh\") may be freely + used in the \"character\" position of a further definition (such + as \"amacron breve\" or \"kh underbar\"). There is no constraint + on the ordering of definitions within a definition file. The + definition of \"a macron\" does not have to precede that of + \"amacron breve\": requests for \"impossible\" characters are + deferred until their constituents have had a chance to come into + being. + + \"Slots\" for which no new definition is given retain the + definition they have in the input font. + + The definition file may also contain blank lines and comments + (introduced by \"\#\"). + + -s may optionally give the factor, expressed as a per-thousand + value, by which normally superscript accents (such as dieresis, + ring) should be shrunk when they are used as subscript accents + (such as underdieresis, underring). Values of around 800 may be + found useful. + + -c may optionally give two comma-separated numerical values to + adjust the x and y coordinates of the dotaccent placed within a + breve to form the candrabindu accent. A coordinate scheme using + \"DESIGNUNITS R 1000\" is assumed. + + -b may optionally be specified to block the use of predefined + accented characters, forcing vpl2ovp to define its own + versions. This may be useful to secure a consistent appearance + in cases where a font designer does not share vpl2ovp's views + on where accents should be placed. + + -h prints this help. +"; +#------------------------------------------------------------------------# + +######################## +# Packages and constants +######################## +# +use File::Basename; +use Getopt::Std; +$cmdline = basename($0) . " " . join " ", @ARGV; +getopts('d:s:c:bh'); +if ($opt_h or !$opt_d or $#ARGV != 0) { + print STDERR $description; + exit 1; +} + +$filename = $ARGV[0]; +$dummycodepoint = 0xF8FF; +($fontname = $filename) =~ s/\..*$//; +($encname = basename($opt_d)) =~ s/\..*$//; +$vtitle = "(VTITLE Font $fontname modified for $encname encoding by vpl2ovp"; +$vtitle .= " v. $version" if $version; +$vtitle .= ")\n(COMMENT Command line: $cmdline)"; +$vtitle .= "\n(OFMLEVEL H 0)"; + +# +# Flags for bold and small caps. These are probably a bit iffy, but +# there's not much that can be done about it. +# +if ($fontname =~ /(^p.*b[oi]?[c]?$|^[^p].*bx[a-z]*[0-9]+$)/) { $bold = 1 } +if ($fontname =~ /(^p.*c$|^[^p].*csc[a-z]*[0-9]+$)/) { $scaps = 1 } +if ($opt_s) { $shrink = $opt_s / 1000 } else { $shrink = 1 } + +# +# Array to convert from number to vpl representation +# +foreach $i (0 .. 0xFFFF) { + $nv[$i] = (chr($i) =~ /[0-9A-Za-z]/ ? "C " . chr $i : sprintf("H %04lX", $i)); +} + +# +# Now the encoding vectors. +# +@TeXenc = ( + "Gamma", "Delta", "Theta", "Lambda", + "Xi", "Pi", "Sigma", "Upsilon", + "Phi", "Psi", "Omega", "ff", + "fi", "fl", "ffi", "ffl", + "dotlessi", "dotlessj", "grave", "acute", + "caron", "breve", "macron", "ring", + "cedilla", "germandbls", "ae", "oe", + "oslash", "AE", "OE", "Oslash", + "space", "exclam", "quotedblright", "numbersign", + "dollar", "percent", "ampersand", "quoteright", + "parenleft", "parenright", "asterisk", "plus", + "comma", "hyphen", "period", "slash", + "zero", "one", "two", "three", + "four", "five", "six", "seven", + "eight", "nine", "colon", "semicolon", + "exclamdown", "equal", "questiondown", "question", + "at", "A", "B", "C", + "D", "E", "F", "G", + "H", "I", "J", "K", + "L", "M", "N", "O", + "P", "Q", "R", "S", + "T", "U", "V", "W", + "X", "Y", "Z", "bracketleft", + "quotedblleft", "bracketright", "circumflex", "dotaccent", + "quoteleft", "a", "b", "c", + "d", "e", "f", "g", + "h", "i", "j", "k", + "l", "m", "n", "o", + "p", "q", "r", "s", + "t", "u", "v", "w", + "x", "y", "z", "endash", + "emdash", "hungarumlaut", "tilde", "dieresis" +); + +@dvipsenc = ( + ".notdef", ".notdef", ".notdef", ".notdef", + ".notdef", ".notdef", ".notdef", ".notdef", + ".notdef", ".notdef", ".notdef", ".notdef", + ".notdef", "quotesingle", "exclamdown", "questiondown", + "dotlessi", "dotlessj", "grave", "acute", + "caron", "breve", "macron", "ring", + "cedilla", "germandbls", "ae", "oe", + "oslash", "AE", "OE", "Oslash", + "space", "exclam", "quotedbl", "numbersign", + "dollar", "percent", "ampersand", "quoteright", + "parenleft", "parenright", "asterisk", "plus", + "comma", "hyphen", "period", "slash", + "zero", "one", "two", "three", + "four", "five", "six", "seven", + "eight", "nine", "colon", "semicolon", + "less", "equal", "greater", "question", + "at", "A", "B", "C", + "D", "E", "F", "G", + "H", "I", "J", "K", + "L", "M", "N", "O", + "P", "Q", "R", "S", + "T", "U", "V", "W", + "X", "Y", "Z", "bracketleft", + "backslash", "bracketright", "circumflex", "underscore", + "quoteleft", "a", "b", "c", + "d", "e", "f", "g", + "h", "i", "j", "k", + "l", "m", "n", "o", + "p", "q", "r", "s", + "t", "u", "v", "w", + "x", "y", "z", "braceleft", + "bar", "braceright", "tilde", "dieresis", + "asciicircum", "asciitilde", "Ccedilla", "Iacute", + "Icircumflex", "atilde", "edieresis", "egrave", + "scaron", "zcaron", "Eth", "ff", + "ffi", "ffl", ".notdef", ".notdef", + ".notdef", ".notdef", "Scaron", ".notdef", + ".notdef", ".notdef", ".notdef", ".notdef", + "Ydieresis", ".notdef", "Zcaron", ".notdef", + ".notdef", ".notdef", ".notdef", ".notdef", + ".notdef", ".notdef", "cent", "sterling", + "fraction", "yen", "florin", "section", + "currency", "copyright", "quotedblleft", "guillemotleft", + "guilsinglleft", "guilsinglright", "fi", "fl", + "degree", "endash", "dagger", "daggerdbl", + "periodcentered", ".notdef", "paragraph", "bullet", + "quotesinglbase", "quotedblbase", "quotedblright", "guillemotright", + "ellipsis", "perthousand", ".notdef", ".notdef", + "Agrave", "Aacute", "Acircumflex", "Atilde", + "Adieresis", "Aring", ".notdef", "dotaccent", + "Egrave", "Eacute", "Ecircumflex", "Edieresis", + "Igrave", "hungarumlaut", "ogonek", "Idieresis", + "emdash", "Ntilde", "Ograve", "Oacute", + "Ocircumflex", "Otilde", "Odieresis", ".notdef", + ".notdef", "Ugrave", "Uacute", "Ucircumflex", + "Udieresis", "Yacute", "Thorn", ".notdef", + "agrave", "aacute", "acircumflex", "ordfeminine", + "adieresis", "aring", ".notdef", "ccedilla", + "Lslash", "eacute", "ecircumflex", "ordmasculine", + "igrave", "iacute", "icircumflex", "idieresis", + ".notdef", "ntilde", "ograve", "oacute", + "ocircumflex", "otilde", "odieresis", ".notdef", + "lslash", "ugrave", "uacute", "ucircumflex", + "udieresis", "yacute", "thorn", "ydieresis" +); + +@adobeenc=( + ".notdef", ".notdef", ".notdef", ".notdef", + ".notdef", ".notdef", ".notdef", ".notdef", + ".notdef", ".notdef", ".notdef", ".notdef", + ".notdef", ".notdef", ".notdef", ".notdef", + ".notdef", ".notdef", ".notdef", ".notdef", + ".notdef", ".notdef", ".notdef", ".notdef", + ".notdef", ".notdef", ".notdef", ".notdef", + ".notdef", ".notdef", ".notdef", ".notdef", + "space", "exclam", "quotedbl", "numbersign", + "dollar", "percent", "ampersand", "quoteright", + "parenleft", "parenright", "asterisk", "plus", + "comma", "hyphen", "period", "slash", + "zero", "one", "two", "three", + "four", "five", "six", "seven", + "eight", "nine", "colon", "semicolon", + "less", "equal", "greater", "question", + "at", "A", "B", "C", + "D", "E", "F", "G", + "H", "I", "J", "K", + "L", "M", "N", "O", + "P", "Q", "R", "S", + "T", "U", "V", "W", + "X", "Y", "Z", "bracketleft", + "backslash", "bracketright", "asciicircum", "underscore", + "quoteleft", "a", "b", "c", + "d", "e", "f", "g", + "h", "i", "j", "k", + "l", "m", "n", "o", + "p", "q", "r", "s", + "t", "u", "v", "w", + "x", "y", "z", "braceleft", + "bar", "braceright", "asciitilde", ".notdef", + ".notdef", ".notdef", ".notdef", ".notdef", + ".notdef", ".notdef", ".notdef", ".notdef", + ".notdef", ".notdef", ".notdef", ".notdef", + ".notdef", ".notdef", ".notdef", ".notdef", + ".notdef", ".notdef", ".notdef", ".notdef", + ".notdef", ".notdef", ".notdef", ".notdef", + ".notdef", ".notdef", ".notdef", ".notdef", + ".notdef", ".notdef", ".notdef", ".notdef", + ".notdef", "exclamdown", "cent", "sterling", + "fraction", "yen", "florin", "section", + "currency", "quotesingle", "quotedblleft", "guillemotleft", + "guilsinglleft", "guilsinglright", "fi", "fl", + ".notdef", "endash", "dagger", "daggerdbl", + "periodcentered", ".notdef", "paragraph", "bullet", + "quotesinglbase", "quotedblbase", "quotedblright", "guillemotright", + "ellipsis", "perthousand", ".notdef", "questiondown", + ".notdef", "grave", "acute", "circumflex", + "tilde", "macron", "breve", "dotaccent", + "dieresis", ".notdef", "ring", "cedilla", + ".notdef", "hungarumlaut", "ogonek", "caron", + "emdash", ".notdef", ".notdef", ".notdef", + ".notdef", ".notdef", ".notdef", ".notdef", + ".notdef", ".notdef", ".notdef", ".notdef", + ".notdef", ".notdef", ".notdef", ".notdef", + ".notdef", "AE", ".notdef", "ordfeminine", + ".notdef", ".notdef", ".notdef", ".notdef", + "Lslash", "Oslash", "OE", "ordmasculine", + ".notdef", ".notdef", ".notdef", ".notdef", + ".notdef", "ae", ".notdef", ".notdef", + ".notdef", "dotlessi", ".notdef", ".notdef", + "lslash", "oslash", "oe", "germandbls", + ".notdef", ".notdef", ".notdef", ".notdef" +); + +############### +# Read DEF file +############### +# +open DEF, $opt_d or die "Cannot open $opt_d: $!\n"; +while (<DEF>) { + next if (/^\s*$/ || /^\#/); + s/\s*(\#.*)?$//; + push @deflines, $_; +} +close DEF; + +############### +# Read VPL file +############### +# +# File header +# +$vplhead = <> or exit 1; +unless ($vplhead =~ /^\((VTITLE|FAMILY) /) { + die "$filename is not a vpl file: giving up\n" +} +do { + $_ = <>; + $vplhead .= $_; +} until ($_ =~ /^\(LIGTABLE$/ or eof); +if (eof) { + die "$filename does not seem to be a text font (no LIGTABLE): giving up\n"; +} +if ($vplhead =~ s/\A\(VTITLE(.*)$/$vtitle\n(COMMENT Old vtitle:$1/m) { + $vplhead =~ s/\n\(COMMENT Please edit that VTITLE .*\)$//m; + @enc = @dvipsenc; + $dvips = 1; +} +elsif ($vplhead =~ /\A\(FAMILY.*\)\n\(CODINGSCHEME ADOBESTANDARDENCODING\)$/m) { + $vplhead =~ s/\A/$vtitle\n/m; + @enc = @adobeenc; + $dvips = 0; +} +else { + $vplhead =~ s/\A/$vtitle\n/m; + @enc = @TeXenc; + $dvips = 0; +} +if ($vplhead =~ /^\(CODINGSCHEME TEX MATH SYMBOLS/m) { + die "$filename is a TeX math font: giving up\n"; +} +unless ($vplhead =~ s/^(\(CODINGSCHEME .*\+\s?)(\S+)\)$/$1$encname)/m) { + $vplhead =~ s/^(\(CODINGSCHEME .*)\)$/$1 + $encname)/m; +} +if ($vplhead =~ s/^\(DESIGNUNITS R (.+)\)\n//m) { $scale = $1 } +else { $scale = 1 } +$vplhead =~ s/^\(COMMENT.*DESIGNSIZE.*\)\n//gm; +$vplhead =~ s/^\(BOUNDARYCHAR.*\)\n//gm; +if ($vplhead =~ /^ \(SLANT R (.+)\)/m) { $slant = $1 } +if ($vplhead =~ /^ \(XHEIGHT [DR] (.+)\)/m) { $xheight = $1 } +unless ($vplhead =~ /^\(MAPFONT /m) { + if ($vplhead =~ /^\(DESIGNSIZE R (.*)\)$/m) { $dsize = $1 *$scale } + $mapfont = "\n(MAPFONT D 0\n (FONTNAME $fontname)\n (FONTDSIZE R $dsize)\n )"; + $vplhead =~ s/\n\(LIGTABLE\Z/$mapfont$&/m; +} +$vplhead =~ s/^(\(FONTDIMEN)/(SEVENBITSAFEFLAG FALSE)\n$1/m; +if ($opt_s) { + $vplhead =~ s[^(\(MAPFONT D )0(.*?)( \))] + [$&\n${1}1$2 (FONTAT R ${ \($shrink * $scale) })\n$3]ms; +} +@vplhead = split /^/, $vplhead; +foreach (@vplhead) { + s[(?<!(IGNSIZE|MAPFONT)) [RD] (-?)([0-9.]+)\)] + [" R " . $2 . $3/$scale . ")"]ge +} + +# +# Ligatures and kerns +# +do { + $_ = <>; + s/ \(comment .*$//i; + s/^( \((?:LABEL|KRN) )O ([0-7]+)(.*)$/$1 . sprintf("H %04lX", oct $2) . $3/e; +if (/ \(LIG /) { + s/O ([0-7]+)/sprintf("H %04lX", oct $1)/ge; + } + $ligs .= $_; +} until $_ =~ /^ \)/; +# +# Now build a hash to convert from vpl representation to char name +# and use it to make ligtable readable +# +foreach $i (0 .. 255) { $vc{$nv[$i]} = $enc[$i] } +$ligs =~ s/^( \((?:LABEL|KRN) )(\S+ \S+)(.*\))$/$1$vc{$2}$3/gm; +$ligs =~ s/^( \(LIG )(\S+ \S+) (\S+ \S+)\)$/$1$vc{$2} $vc{$3})/gm; +# +# Character definitions: store "encoded" defs in @chars, store *all* +# defs in %allchars +# +$_ = <>; +do { + if (/^\(CHARACTER/) { + $character = $_; + do { + $_ = <>; + $character .= $_; + } until $_ =~ /^ \)/; + storeinfo($character); + $_ = <>; + } +} until eof; +foreach $i (0 .. $#chars) { + if ($chars[$i] and $enc[$i] ne ".notdef") { + $allchars{$enc[$i]} = $chars[$i]; + } +} + +################## +# Set up constants +################## + +$subacc = "(cedilla|ogonek|commaaccent)"; +$supacc = "(grave|acute|circumflex|tilde|macron|breve|dotaccent|overdot|dieresis|ring|hungarumlaut|caron|candrabindu)"; +$underacc = "(underdot|under$supacc)"; +$accents = "($subacc|$supacc|$underacc|underbar)"; +$underadp = 0.230; # depth of "under" accs +$underddp = 0.213; # depth of underdot +if ($bold) { $thk = 0.072 } else { $thk = 0.052 } # thickness and +$underbdp = 0.082 + $thk; # depth of underbar +$capheight = $allchars{"X"}{ht}; +$accheight = $allchars{"macron"}{ht}; +$accdepth = $accheight - $thk * $scale; # probable approx. "depth" of macron +$v1 = $accheight - $xheight; # vertical offset for double accents +$v2 = $capheight - $xheight; # vertical offset for accented caps etc +if ($scaps) { # accented small caps + $scoffset = $allchars{"x"}{ht} - $xheight; + $v1 += $scoffset; +} +if ($opt_c) { # candrabindu + ($cbx, $cby) = $opt_c =~ /^(.*),(.*)$/; + $cbx += ($allchars{"breve"}{wd} - $allchars{"dotaccent"}{wd}) / 2; + $cbx /= 1000; + $cby /= 1000; +} + +###################### +# Build the characters +###################### +# +# First normalise dvips.enc encoding quirks +# +if ($dvips) { + chmove("fi", 014); + chmove("fl", 015); + chmove("quotedblright", 042); + chmove("quotedblleft", 0134); + chmove("dotaccent", 0137); + chmove("endash", 0173); + chmove("emdash", 0174); + chmove("hungarumlaut", 0175); +} +# +# Now build a list of definitions supplied by user +# +for (@deflines) { + if (/^\s*(\d+|0[0-7]+|0x[0-9a-fA-F]+)\s+([a-zA-Z]+?|\.notdef)(?:\s+([a-zA-Z]+))?$/) { + ($num, $char, $acc) = ($1, $2, $3); + $num = oct $num if $num =~ /^0/; + if ($num > 0xFFFF) { die "Bad definition (number out of range): $_\n" } + $def = {}; + $def->{qdef} = $_; + $def->{num} = $num; + $def->{char} = $char; + $def->{acc} = $acc; + if ($char eq "space") { $def->{nchar} = $acc } + else { $def->{nchar} = $char . $acc } + push @nchars, $def->{nchar}; + push @defs, $def; + } + else { die "Bad definition: $_\n" } +} +# +# Work through the list +# +while (@defs) { + $def = shift @defs; + $qdef = $def->{qdef}; + $num = $def->{num}; + $char = $def->{char}; + $acc = $def->{acc}; + $nchar = $def->{nchar}; + # + # If we can't handle $char/$acc yet, but believe we will be able + # to later, send the definition to the back of the queue. In case + # it later turns out we were wrong, allow only five loops before + # giving up. + # + if (!$allchars{$char} and $char ne ".notdef") { + if (grep /^$char$/, @nchars) { + unless (++$def->{requeue} > 5) { + push @defs, $def; + next; + } + } + else { die "Bad definition (no such character): $qdef\n" } + } + if ($acc and !$allchars{$acc} and $acc !~ /^$accents$/) { + if (grep /^$acc$/, @nchars) { + unless (++$def->{requeue} > 5) { + push @defs, $def; + next; + } + } + else { die "Bad definition (no such accent): $qdef\n" } + } + # + # Remove any existing claims on $num + # + @{ $allchars{$chars[$num]{id}}{num} } = grep !/$num/, + @{ $allchars{$chars[$num]{id}}{num} }; + # + # First deal with .notdef + # + if ($nchar eq ".notdef") { + undef $chars[$num]; + } + # + # Next look among existing chars (unless blocked by -b) + # + elsif (!($acc and $opt_b) and $allchars{$nchar}) { + push( @{ $allchars{$nchar}{num} }, $num); + $chars[$num] = $allchars{$nchar}; + } + # + # If it can't be built from sub-elements, issue a warning and move on + # + elsif (!$acc) { + warn "No such character - ignoring definition: $qdef\n"; + undef $chars[$num]; + } + # + # Now build the char + # + else { + # + # First get rid of predefined/duplicated ligtable statements + # and character definitions; also synonyms + # + $ligs =~ s/\n \((LABEL|KRN|LIG) ($nchar .*|.*$nchar)\)$//gm; + $allchars{$nchar} = (); + if ($acc eq "overdot") { + $nchar2 = $char . "dotaccent"; + $ligs =~ s/\n \((LABEL|KRN|LIG) ($nchar2 .*|.*$nchar2)\)$//gm; + delete $allchars{$nchar2}; + } + # + # If the character is not a single codepoint (i.e. if it is stored + # in the Private Use Area), store the info that will be needed to + # have it linked into the LIGTABLE + # + push @pualigs, "$char: (LIG $acc $nchar)"; + if (!defined $allchars{$acc}) { dummychar($dummycodepoint--, $acc) } + # + # Go! + # + if ($acc =~ /^$subacc$/) { + subacc($num, $char, $acc, $nchar); + fixkerns($char, $acc); + } + elsif ($acc =~ /^$supacc$/) { + supacc($num, $char, $acc, $nchar); + fixkerns($char, $acc); + } + elsif ($acc =~ /^$underacc$/) { + underacc($num, $char, $acc, $nchar); + fixkerns($char, $acc); + } + elsif ($acc =~ /^underbar$/) { + underb($num, $char, $nchar); + fixkerns($char, $acc); + } + else { + digraph($num, $char, $acc, $nchar); + fixkerns($char, $acc); + } + } +} + +################### +# Sort out ligtable +################### +# +# Pull in the Private Use Area ligatures +# +foreach $pualig (@pualigs) { + $pualig =~ s/^(.+)://; + $puaelm1 = $1; + unless ($ligs =~ s/(^ \(LABEL $puaelm1\)\n)/$1$pualig\n/m) { + $ligs =~ s[^( \)\n)] + [ \(LABEL $puaelm1\)\n$pualig\n \(STOP\)\n$1]m + } +} +# +# Convert to vpl representation, eliminating statements invoking +# "unencoded" characters +# +@liglist = split /\n/, $ligs; +$ligs = ""; +foreach (@liglist) { + if (/^( \(LIG \S+ )(\S+)\)$/) { + if ($n = ${ $allchars{$2}{num} }[0]) { + s/^( \(LIG \S+ )(\S+)\)$/$1$nv[$n])/; + } + else { next } + } + if (/^( \((?:LABEL|LIG|KRN) )([^ )]+)(.*)$/) { + ($one, $two, $three) = ($1, $2, $3); + foreach $n (@{ $allchars{$two}{num} }) { + $ligs .= "$one$nv[$n]$three\n"; + } + } + else { $ligs .= "$_\n" } +} +# +# Eliminate sequences orphaned by elimination of a LABEL +# +@liglist = split / \(STOP\)\n/, $ligs; +$ligs = ""; +foreach (@liglist) { + if (/^ \(LABEL /m) { $ligs .= "$_ (STOP)\n" } + elsif (/^ \)$/m) { $ligs .= $_ } +} +# +# Eliminate empty statements +# +$ligs =~ s/(^ \(LABEL .*\)\n)+ \(STOP\)\n//gm; +@ligs = split /^/, $ligs; +foreach (@ligs) { + s/ [RD] (-?)([0-9.]+)\)/" R " . $1 . $2\/$scale . ")"/ge +} + +#################### +# Output the results +#################### +# +print @vplhead, @ligs; +foreach $i (0 .. 0xFFFF) { if (defined $chars[$i]{id}) { printchar($i) } } + +##################### +# End of main program +##################### + +sub storeinfo { + # + # Extract info from a character definition and store it in @chars + # + my $char = shift; + my $num; + if ($char =~ /\A\(CHARACTER O ([0-7]+)/m) { $num = oct $1 } + elsif ($char =~ /\A\(CHARACTER C (.)/m) { $num = ord $1 } + $chars[$num]{id} = $enc[$num]; + push( @{ $chars[$num]{num} }, $num); + if ($char =~ /^ \(CHARWD R (.*?)\)$/m) { $chars[$num]{wd} = $1 } + if ($char =~ /^ \(CHARHT R (.*?)\)$/m) { $chars[$num]{ht} = $1 } + if ($char =~ /^ \(CHARDP R (.*?)\)$/m) { $chars[$num]{dp} = $1 } + if ($char =~ /^ \(CHARIC R (.*?)\)$/m) { $chars[$num]{ic} = $1 } + if ($char =~ /^ \(MAP\n((.|\n)*)^ \)/m) { $chars[$num]{map} = $1 } + else { $chars[$num]{map} = " (SETCHAR $nv[$num])\n" } + $chars[$num]{map} =~ s[(\(SETCHAR )O ([0-7]+)\)] + [$1 . sprintf("H %04lX", oct $2) . ")"]gme +} + +sub printchar { + # + # Extract info from @chars and build it into a character definition + # + my $num = shift; + my @ch; + push @ch, "(CHARACTER "; + if (chr($num) =~ /[0-9A-Za-z]/) { push @ch, "C " . chr($num) } + else { + push @ch, sprintf("H %04lX", $num); + push @ch, " (COMMENT " . $chars[$num]{id} . ")"; + } + push @ch, "\n"; + push @ch, " (CHARWD R " . $chars[$num]{wd} . ")\n" + if defined $chars[$num]{wd}; + push @ch, " (CHARHT R " . $chars[$num]{ht} . ")\n" + if defined $chars[$num]{ht}; + push @ch, " (CHARDP R " . $chars[$num]{dp} . ")\n" if $chars[$num]{dp}; + push @ch, " (CHARIC R " . $chars[$num]{ic} . ")\n" if $chars[$num]{ic}; + push @ch, " (MAP\n"; + push @ch, $chars[$num]{map}; + push @ch, " )\n"; + push @ch, " )\n"; + foreach (@ch) { + s/(?<!SELECTFONT) [RD] (-?)([0-9.]+)\)/" R " . $1 . $2\/$scale . ")"/ge + } + print @ch +} + +sub chmove { + # + # Move a character + # + my ($char, $num) = @_; + my $i; + foreach $i (@{ $allchars{$char}{num} }) { undef $chars[$i] } + @{ $allchars{$char}{num} } = (); + @{ $allchars{$chars[$num]{id}}{num} } = grep !/$num/, + @{ $allchars{$chars[$num]{id}}{num} }; + push( @{ $allchars{$char}{num} }, $num); + $chars[$num] = $allchars{$char}; +} + +sub max { + # + # Return greater of two values + # + my ($a, $b) = @_; + return $a > $b ? $a : $b; +} + +sub subacc { + # + # Subscript accents + # + my ($num, $char, $acc, $id) = @_; + my ($h, $s1, $s2, $s3); + $allchars{$id}{wd} = $allchars{$char}{wd}; + $allchars{$id}{ht} = $allchars{$char}{ht}; + $allchars{$id}{dp} = $allchars{$acc}{dp}; + $allchars{$id}{ic} = $allchars{$char}{ic}; + $allchars{$id}{id} = $id; + push( @{ $allchars{$id}{num} }, $num); + $s1 = $allchars{$char}{map}; + $s1 =~ s/\A (.*)\n\Z/(PUSH) $1 (POP)/s; + $h = sprintf("%.3f", ($allchars{$char}{wd} - $allchars{$acc}{wd}) / 2); + if ($h > 0) { $s2 = " (MOVERIGHT R $h) " } + elsif ($h < 0) { + $h = -$h; + $s2 = " (MOVELEFT R $h) "; + } + else { $s2 = " " } + $s3 = $allchars{$acc}{map}; + $s3 =~ s/\A.*(\(SETCHAR . .+?\)).*\Z/$1/s; + $allchars{$id}{map} = " $s1\n$s2$s3\n"; + $chars[$num] = $allchars{$id}; +} + +sub supacc { + # + # Superscript accents + # + my ($num, $char, $acc, $id) = @_; + my ($cb, $h, $hadj, $tallchar, $ic, $s1, $s2, $s3); + if ($char eq "i" and $allchars{"dotlessi"}) { $char = "dotlessi" } + if ($char eq "j" and $allchars{"dotlessj"}) { $char = "dotlessj" } + if ($acc eq "overdot") { $acc = "dotaccent" } + if ($acc eq "candrabindu") { + $acc = "breve"; + ($cb = $allchars{"dotaccent"}{map}) =~ s/\A.*(\(SETCHAR . .+?\)).*\Z/$1/s; + } + $allchars{$id}{wd} = $allchars{$char}{wd}; + $allchars{$id}{ht} = $allchars{$acc}{ht}; + $allchars{$id}{dp} = $allchars{$char}{dp}; + $allchars{$id}{id} = $id; + push( @{ $allchars{$id}{num} }, $num); + $s1 = $allchars{$char}{map}; + $s1 =~ s/\A (.*)\n\Z/(PUSH) $1 (POP)/s; + if ($scaps and $char =~ /^[a-z]/) { # accented small caps + $tallchar = 1; + if ($char =~ /$supacc$/ + and $char !~ /under$supacc$/) { # double accs + $s2 = " (MOVEUP R $v1)"; + $allchars{$id}{ht} += $v1; + $hadj = sprintf("%.3f", $v1 * $slant); + $ic = $allchars{$char}{ic}; + } + else { # single accs + $s2 = " (MOVEUP R $scoffset)"; + $allchars{$id}{ht} += $scoffset; + $hadj = sprintf("%.3f", $scoffset * $slant); + $ic = $allchars{$acc}{ic} + $hadj; + } + } + elsif ($allchars{$char}{ht} >= ($accheight + $v2)) { # double accs + $tallchar = 1; # on caps etc. + $s2 = " (MOVEUP R ${ \($v1 + $v2) })"; + $allchars{$id}{ht} += ($v1 + $v2); + $hadj = sprintf("%.3f", ($v1 + $v2) * $slant); + $ic = $allchars{$char}{ic}; + } + elsif ($allchars{$char}{ht} > 1.15 * $xheight) { + $tallchar = 1; + if ($char =~ /$supacc$/ + and $char !~ /under$supacc$/) { # double accs + $s2 = " (MOVEUP R $v1)"; + $allchars{$id}{ht} += $v1; + $hadj = sprintf("%.3f", $v1 * $slant); + $ic = $allchars{$char}{ic}; + } + else { # caps etc. + $s2 = " (MOVEUP R $v2)"; + $allchars{$id}{ht} += $v2; + $hadj = sprintf("%.3f", $v2 * $slant); + $ic = $allchars{$char}{ic}; + } + } + else { # single accs + $s2 = " "; + $ic = $allchars{$acc}{ic}; + } + $h = sprintf("%.3f", ($allchars{$char}{wd} - $allchars{$acc}{wd}) / 2); + unless ($tallchar) { $ic -= $h } + $allchars{$id}{ic} = $ic unless $ic < 0; + $h += $hadj; + if ($h > 0) { $s2 .= " (MOVERIGHT R $h) " } + elsif ($h < 0) { + $h = -$h; + $s2 .= " (MOVELEFT R $h) "; + } + else { $s2 .= " " } + $s3 = $allchars{$acc}{map}; + $s3 =~ s/\A.*(\(SETCHAR . .+?\)).*\Z/$1/s; + if ($cb) { # candrabindu + $cb = $s2 . $cb; + if ($cbx) { + unless (($cb =~ s/(MOVERIGHT R )([0-9.]+)/$1 . ($2 + $cbx * $scale)/e) + or ($cb =~ s/(MOVELEFT R )([0-9.]+)/$1 . ($2 - $cbx * $scale)/e)) { + $cb =~ s/^( +)/"$1(MOVERIGHT R " . ($cbx * $scale) . ") "/e; + } + } + if ($cby) { + unless ($cb =~ s/(MOVEUP R )([0-9.]+)/$1 . ($2 + $cby * $scale)/e) { + $cb =~ s/^( +)/"$1(MOVEUP R " . ($cby * $scale) . ") "/e; + } + } + $cb .= "\n"; + $s1 = "(PUSH) " . $s1; + $s3 .= " (POP)"; + } + $allchars{$id}{map} = " $s1\n$s2$s3\n$cb"; + $chars[$num] = $allchars{$id}; +} + +sub underacc { + # + # Dropped accents + # + my ($num, $char, $acc, $id) = @_; + my ($h, $v, $s1, $s2, $s3); + $acc =~ s/^under//; + if ($acc eq "dot") { $acc = "period" } + if ($acc eq "candrabindu") { die "Bad definition (no such accent): $qdef\n" } + $allchars{$id}{wd} = $allchars{$char}{wd}; + $allchars{$id}{ht} = $allchars{$char}{ht}; + $allchars{$id}{ic} = $allchars{$char}{ic}; + $allchars{$id}{id} = $id; + push( @{ $allchars{$id}{num} }, $num); + if ($acc =~ /^$supacc$/) { + $v = $allchars{$id}{dp} = $underadp * $scale * $shrink; + $v += ($accdepth * $shrink); + } + else { + $v = $allchars{$id}{dp} = $underddp * $scale + $allchars{$acc}{dp}; + } + $s1 = $allchars{$char}{map}; + $s1 =~ s/\A (.*)\n\Z/(PUSH) $1 (POP)/s; + if ($acc =~ /^$supacc$/) { + $h = ($allchars{$char}{wd} - ($allchars{$acc}{wd} * $shrink)) / 2 - $v * $slant; + if ($opt_s) { $s2 = " (SELECTFONT D 1)\n" } + } + else { + $h = ($allchars{$char}{wd} - $allchars{$acc}{wd}) / 2 - $v * $slant; + } + $h = sprintf("%.3f", $h); + if ($h > 0) { + $s2 .= " (MOVEDOWN R $v) (MOVERIGHT R $h) "; + } + elsif ($h < 0) { + $h = -$h; + $s2 .= " (MOVEDOWN R $v) (MOVELEFT R $h) "; + } + else { $s2 = " (MOVEDOWN R $v) " } + $s3 = $allchars{$acc}{map}; + $s3 =~ s/\A.*(\(SETCHAR . .+?\)).*\Z/$1/s; + if ($opt_s and $acc =~ /^$supacc$/) { $s3 .= "\n (SELECTFONT D 0)" } + $allchars{$id}{map} = " $s1\n$s2$s3\n"; + $chars[$num] = $allchars{$id}; +} + +sub underb { + # + # Underbar + # + my ($num, $char, $id) = @_; + my ($h, $w, $dp, $s1, $s2, $s3); + $allchars{$id}{wd} = $allchars{$char}{wd}; + $allchars{$id}{ht} = $allchars{$char}{ht}; + $allchars{$id}{dp} = $dp = $underbdp * $scale; + $allchars{$id}{ic} = $allchars{$char}{ic}; + $allchars{$id}{id} = $id; + push( @{ $allchars{$id}{num} }, $num); + $s1 = $allchars{$char}{map}; + $s1 =~ s/\A (.*)\n\Z/(PUSH) $1 (POP)/s; + $h = sprintf("%.3f", ($allchars{$id}{wd} / 10 - $dp * $slant)); + $w = sprintf("%.3f", ($allchars{$id}{wd} * 8 / 10)); + if ($h > 0) { + $s2 = " (MOVEDOWN R $dp) (MOVERIGHT R $h) "; + } + elsif ($h < 0) { + $h = -$h; + $s2 = " (MOVEDOWN R $dp) (MOVELEFT R $h) "; + } + else { $s2 .= " (MOVEDOWN R $dp) " } + $s3 = "(SETRULE R ${ \($thk) } R $w)"; + $allchars{$id}{map} = " $s1\n$s2$s3\n"; + $chars[$num] = $allchars{$id}; +} + +sub digraph { + # + # Make a new character consisting of two existing characters + # + my ($num, $char, $acc, $id) = @_; + my ($one, $two, $kern, $s1, $s2, $charZWJ); + # + # Fiddle the ligature info to include Zero Width Joiner + # + if (!defined $allchars{ZWJ}) { + dummychar(0x200D, ZWJ) + } + pop @pualigs; + $charZWJ = $char . "ZWJ"; + dummychar($dummycodepoint--, $charZWJ) unless defined $allchars{$charZWJ}; + push @pualigs, "$char: (LIG ZWJ $charZWJ)" + unless (grep /^$char: \(LIG ZWJ $charZWJ\)$/, @pualigs); + push @pualigs, "$charZWJ: (LIG $acc $id)"; + if ($ligs =~ /^ \(LABEL $char\)\n(.*?)\n \(KRN $acc R (-?[0-9.]+)\)\n/ms) { + ($one, $two) = ($1, $2); + } + $kern = $two if $one !~ /^ \(STOP\)$/m; + $allchars{$id}{wd} = $allchars{$char}{wd} + $allchars{$acc}{wd}; + $allchars{$id}{wd} += $kern; + $allchars{$id}{ht} = max($allchars{$char}{ht}, $allchars{$acc}{ht}); + $allchars{$id}{dp} = max($allchars{$char}{dp}, $allchars{$acc}{dp}); + $allchars{$id}{ic} = $allchars{$acc}{ic}; + $allchars{$id}{id} = $id; + push( @{ $allchars{$id}{num} }, $num); + $s1 = $allchars{$char}{map}; + chomp ($s2 = $allchars{$acc}{map}); + $s1 =~ s/(\(SETCHAR .*?\))/$1\n$s2/; + if ($kern) { + if ($kern < 0) { + $kern = -$kern; + $s1 =~ s/(\(SETCHAR .*?\))/$1 (MOVELEFT R $kern)/; + } + else { $s1 =~ s/(\(SETCHAR .*?\))/$1 (MOVERIGHT R $kern)/ } + } + $allchars{$id}{map} = $s1; + $chars[$num] = $allchars{$id}; +} + +sub dummychar { + # + # Make a new dummy character + # + my ($num, $id) = @_; + $allchars{$id}{wd} = 0; + $allchars{$id}{ht} = 0; + $allchars{$id}{dp} = 0; + $allchars{$id}{ic} = 0; + $allchars{$id}{id} = $id; + push( @{ $allchars{$id}{num} }, $num); + $allchars{$id}{map} = " (SETCHAR H 0020)\n"; + $chars[$num] = $allchars{$id}; +} + +sub fixkerns { + # + # Generalise the kerning info contained in the vpl file by applying + # it to new accented chars. Do not kern lower-case chars bearing + # superscript accents with capitals, quotes or a preceding "f". + # + my ($char, $acc) = @_; + my ($olabel, $nlabel, @liglist, $lchar, $rchar); + return if $char eq "space"; + if ($acc =~ /^$accents$/) { $lchar = $rchar = $char } + else { + $lchar = $char; + $rchar = $acc; + } + unless ($char =~ /^[a-z]/ and $acc =~ /^$supacc$/) { + $ligs =~ s[(\n \(LABEL )$rchar\)(?!\n \(LIG.*$)] + [$&$1$char$acc)]gm + unless $ligs =~ /\n \(LABEL $char$acc\)$/m; + $ligs =~ s[(\n \(LABEL )$rchar\)(\n \(LIG.*$)+(?!\n \(STOP\))] + [$&$1$char$acc)]gm + unless $ligs =~ /\n \(LABEL $char$acc\)$/m; + $ligs =~ s[(\n \(KRN )$lchar( .*)$] + [$&$1$char$acc$2]gm; + } + else { + if ($ligs =~ /\n \(LABEL $char\).*?\(STOP\)/s) { + $nlabel = $olabel = $&; + $nlabel =~ s/(\n \(LABEL $char)\)/$1$acc)/ + unless $ligs =~ /\n \(LABEL $char$acc\)/m; + $nlabel =~ s/\n \(LIG .*\)$//gm; + $nlabel =~ s/\n \(LABEL (?!$char$acc).*\)$//gm; + $nlabel =~ s/\n \(KRN ([A-Z]|quote).*\)$//gm; + $ligs =~ s/(\n \(LABEL )$char\).*?\(STOP\)/$olabel$nlabel/s; + } + @liglist = split /\n \(STOP\)/, $ligs; + foreach (@liglist) { + unless (/\n \(LABEL ([A-Zf]|quote).*\)$/m) { + s/(\n \(KRN $char)( .*\))$/$&$1$acc$2/gm; + } + } + $ligs = join("\n (STOP)", @liglist); + } +} diff --git a/Master/texmf-dist/doc/fonts/accfonts/vpl2vpl b/Master/texmf-dist/doc/fonts/accfonts/vpl2vpl new file mode 100755 index 00000000000..d1e34e19dda --- /dev/null +++ b/Master/texmf-dist/doc/fonts/accfonts/vpl2vpl @@ -0,0 +1,997 @@ +#!/usr/bin/perl + +# Vpl2vpl: a program to generate accented virtual fonts for TeX +# Copyright (C) 1997 John D. Smith + +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. + +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. + +# You should have received a copy of the GNU General Public License +# along with this program; if not, write to the Free Software +# Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. + +$version = 0.23; +#------------------------------------------------------------------------# +$description = +"Syntax: vpl2vpl -d definition-file [-s shrink-factor] + [-c candrabindu-adjustment] [-b] vpl-file + +Vpl2vpl creates new TeX virtual fonts based on existing virtual +fonts (\"input fonts\"). A successful run will read a vpl (Virtual +Property List) file and a definition file, and will generate a new +vpl file on standard output. The input font is assumed to adhere to +the standard TeX encoding for text fonts unless it was created with +the program afm2tfm, in which case it is assumed to conform to the +encoding specified in the file dvips.enc. In either case, the name +of the input font is assumed to be the name of the input file +without its .vpl extension: it must conform to normal TeX +conventions for naming fonts, as vpl2vpl attempts to draw +conclusions from it about the kind of font it is dealing with. + +In the case of a non-virtual font (such as the Computer Modern +fonts), use a pl (Property List) file, created with the standard +utility tftopl, as the input file in place of a vpl file; vpl2vpl +will make the necessary changes on the fly. + +A typical complete sequence of commands to create a new virtual +font might therefore be + tftopl cmr10.tfm cmr10.pl + vpl2vpl -d ISO-Latin1.def cmr10.pl >cmr10_isol1.vpl + vptovf cmr10_isol1.vpl cmr10_isol1.vf cmr10_isol1.tfm +for a Computer Modern font, or + afm2pl Times-Roman.afm rptmr.pl + pltotf rptmr.pl rptmr.tfm + vpl2vpl -d ISO-Latin1.def rptmr.pl >ptmr-isol1.vpl + vptovf ptmr-isol1.vpl ptmr-isol1.vf ptmr-isol1.tfm +for a PostScript font. + +Another approach for a PostScript font is to use afm2tfm: + afm2tfm Times-Roman.afm -t dvips.enc -v ptmr rptmr + vpl2vpl -d ISO-Latin1.def ptmr.vpl >ptmr-isol1.vpl + vptovf ptmr-isol1.vpl ptmr-isol1.vf ptmr-isol1.tfm +-- but this is now deprecated, as afm2tfm generates incorrect +values for the heights of some characters, and this can lead to +bad accent placing. + +In order to keep the whole upper half of the character set free for +the requirements of the encoding specified in the definition file, +certain modifications are made to input fonts following the +dvips.enc encoding to bring them into greater conformity with the +TeX norm. In particular, the characters dotaccent and hungarumlaut +are placed in the positions assigned by TeX (\"5F, \"7D), not those +enforced by dvips.enc (\"C7, \"CD). The f-ligatures, double quotes +and dashes are also moved from the upper half of the character set +to their normal TeX positions. As a result, the following characters +are not found in the lower half of the character set: quotesingle, +quotedbl, backslash, underscore, braceleft, bar, braceright. These +characters can, however, be assigned positions in the output font if +they are needed. (Indeed, they could all be explicitly restored to +their dvips.enc positions if this were desired.) + +Options: + + -d should refer to a font definition file. This file (which could + usefully be named, e.g., \"French.def\") should consist of + lines of character definitions, in the form + \"number\" \"character\" + or + \"number\" \"character\" \"accent\" + Here \"number\" represents the character's position in the new + encoding and may be expressed in decimal, octal or hex; + \"character\" names the character (e.g. \"comma\", \"eight\", + \"A\") or consists of the word \".notdef\" (indicating that + the specified number's \"slot\" in the new encoding is to be + empty); and \"accent\" optionally names an accent to be placed + on the character. In addition to the standard accents available + in PostScript fonts, \"underbar\" and \"underdot\" are also + available, as are \"under\" versions of all the normal + superscript accents (\"underdieresis\", \"underring\", etc.). + The Indian accent \"candrabindu\" may also be specified: it + is formed by overprinting a breve with a dotaccent. Finally, + \"overdot\" may be used as a synonym for \"dotaccent\". + + If the character named in the \"accent\" position is not in fact + a valid accent character, the program interprets the definition + as a request for a digraph formed from the \"character\" and the + \"accent\". A digraph consisting of, say, \"k\" and \"h\" will be + indistinguishable from the letters \"k\" and \"h\" printed + consecutively, but the digraph \"kh\" can itself receive accents + like any other character: see next paragraph. + + A new character (such as \"amacron\" or \"kh\") may be freely + used in the \"character\" position of a further definition (such + as \"amacron breve\" or \"kh underbar\"). There is no constraint + on the ordering of definitions within a definition file. The + definition of \"a macron\" does not have to precede that of + \"amacron breve\": requests for \"impossible\" characters are + deferred until their constituents have had a chance to come into + being. + + \"Slots\" for which no new definition is given retain the + definition they have in the input font. + + The definition file may also contain blank lines and comments + (introduced by \"\#\"). + + -s may optionally give the factor, expressed as a per-thousand + value, by which normally superscript accents (such as dieresis, + ring) should be shrunk when they are used as subscript accents + (such as underdieresis, underring). Values of around 800 may be + found useful. + + -c may optionally give two comma-separated numerical values to + adjust the x and y coordinates of the dotaccent placed within a + breve to form the candrabindu accent. A coordinate scheme using + \"DESIGNUNITS R 1000\" is assumed. + + -b may optionally be specified to block the use of predefined + accented characters, forcing vpl2vpl to define its own + versions. This may be useful to secure a consistent appearance + in cases where a font designer does not share vpl2vpl's views + on where accents should be placed. + + -h prints this help. +"; +#------------------------------------------------------------------------# + +######################## +# Packages and constants +######################## +# +use File::Basename; +use Getopt::Std; +$cmdline = basename($0) . " " . join " ", @ARGV; +getopts('d:s:c:bh'); +if ($opt_h or !$opt_d or $#ARGV != 0) { + print STDERR $description; + exit 1; +} + +$filename = $ARGV[0]; +($fontname = $filename) =~ s/\..*$//; +($encname = basename($opt_d)) =~ s/\..*$//; +$vtitle = "(VTITLE Font $fontname modified for $encname encoding by vpl2vpl"; +$vtitle .= " v. $version" if $version; +$vtitle .= ")\n(COMMENT Command line: $cmdline)"; + +# +# Flags for bold and small caps. These are probably a bit iffy, but +# there's not much that can be done about it. +# +if ($fontname =~ /(^p.*b[oi]?[c]?$|^[^p].*bx[a-z]*[0-9]+$)/) { $bold = 1 } +if ($fontname =~ /(^p.*c$|^[^p].*csc[a-z]*[0-9]+$)/) { $scaps = 1 } +if ($opt_s) { $shrink = $opt_s / 1000 } else { $shrink = 1 } + +# +# Array to convert from number to vpl representation +# +foreach $i (0 .. 255) { + $nv[$i] = (chr($i) =~ /[0-9A-Za-z]/ ? "C " . chr $i : sprintf("O %lo", $i)); +} + +# +# Now the encoding vectors. +# +@TeXenc = ( + "Gamma", "Delta", "Theta", "Lambda", + "Xi", "Pi", "Sigma", "Upsilon", + "Phi", "Psi", "Omega", "ff", + "fi", "fl", "ffi", "ffl", + "dotlessi", "dotlessj", "grave", "acute", + "caron", "breve", "macron", "ring", + "cedilla", "germandbls", "ae", "oe", + "oslash", "AE", "OE", "Oslash", + "space", "exclam", "quotedblright", "numbersign", + "dollar", "percent", "ampersand", "quoteright", + "parenleft", "parenright", "asterisk", "plus", + "comma", "hyphen", "period", "slash", + "zero", "one", "two", "three", + "four", "five", "six", "seven", + "eight", "nine", "colon", "semicolon", + "exclamdown", "equal", "questiondown", "question", + "at", "A", "B", "C", + "D", "E", "F", "G", + "H", "I", "J", "K", + "L", "M", "N", "O", + "P", "Q", "R", "S", + "T", "U", "V", "W", + "X", "Y", "Z", "bracketleft", + "quotedblleft", "bracketright", "circumflex", "dotaccent", + "quoteleft", "a", "b", "c", + "d", "e", "f", "g", + "h", "i", "j", "k", + "l", "m", "n", "o", + "p", "q", "r", "s", + "t", "u", "v", "w", + "x", "y", "z", "endash", + "emdash", "hungarumlaut", "tilde", "dieresis" +); + +@dvipsenc = ( + ".notdef", ".notdef", ".notdef", ".notdef", + ".notdef", ".notdef", ".notdef", ".notdef", + ".notdef", ".notdef", ".notdef", ".notdef", + ".notdef", "quotesingle", "exclamdown", "questiondown", + "dotlessi", "dotlessj", "grave", "acute", + "caron", "breve", "macron", "ring", + "cedilla", "germandbls", "ae", "oe", + "oslash", "AE", "OE", "Oslash", + "space", "exclam", "quotedbl", "numbersign", + "dollar", "percent", "ampersand", "quoteright", + "parenleft", "parenright", "asterisk", "plus", + "comma", "hyphen", "period", "slash", + "zero", "one", "two", "three", + "four", "five", "six", "seven", + "eight", "nine", "colon", "semicolon", + "less", "equal", "greater", "question", + "at", "A", "B", "C", + "D", "E", "F", "G", + "H", "I", "J", "K", + "L", "M", "N", "O", + "P", "Q", "R", "S", + "T", "U", "V", "W", + "X", "Y", "Z", "bracketleft", + "backslash", "bracketright", "circumflex", "underscore", + "quoteleft", "a", "b", "c", + "d", "e", "f", "g", + "h", "i", "j", "k", + "l", "m", "n", "o", + "p", "q", "r", "s", + "t", "u", "v", "w", + "x", "y", "z", "braceleft", + "bar", "braceright", "tilde", "dieresis", + "asciicircum", "asciitilde", "Ccedilla", "Iacute", + "Icircumflex", "atilde", "edieresis", "egrave", + "scaron", "zcaron", "Eth", "ff", + "ffi", "ffl", ".notdef", ".notdef", + ".notdef", ".notdef", "Scaron", ".notdef", + ".notdef", ".notdef", ".notdef", ".notdef", + "Ydieresis", ".notdef", "Zcaron", ".notdef", + ".notdef", ".notdef", ".notdef", ".notdef", + ".notdef", ".notdef", "cent", "sterling", + "fraction", "yen", "florin", "section", + "currency", "copyright", "quotedblleft", "guillemotleft", + "guilsinglleft", "guilsinglright", "fi", "fl", + "degree", "endash", "dagger", "daggerdbl", + "periodcentered", ".notdef", "paragraph", "bullet", + "quotesinglbase", "quotedblbase", "quotedblright", "guillemotright", + "ellipsis", "perthousand", ".notdef", ".notdef", + "Agrave", "Aacute", "Acircumflex", "Atilde", + "Adieresis", "Aring", ".notdef", "dotaccent", + "Egrave", "Eacute", "Ecircumflex", "Edieresis", + "Igrave", "hungarumlaut", "ogonek", "Idieresis", + "emdash", "Ntilde", "Ograve", "Oacute", + "Ocircumflex", "Otilde", "Odieresis", ".notdef", + ".notdef", "Ugrave", "Uacute", "Ucircumflex", + "Udieresis", "Yacute", "Thorn", ".notdef", + "agrave", "aacute", "acircumflex", "ordfeminine", + "adieresis", "aring", ".notdef", "ccedilla", + "Lslash", "eacute", "ecircumflex", "ordmasculine", + "igrave", "iacute", "icircumflex", "idieresis", + ".notdef", "ntilde", "ograve", "oacute", + "ocircumflex", "otilde", "odieresis", ".notdef", + "lslash", "ugrave", "uacute", "ucircumflex", + "udieresis", "yacute", "thorn", "ydieresis" +); + +@adobeenc=( + ".notdef", ".notdef", ".notdef", ".notdef", + ".notdef", ".notdef", ".notdef", ".notdef", + ".notdef", ".notdef", ".notdef", ".notdef", + ".notdef", ".notdef", ".notdef", ".notdef", + ".notdef", ".notdef", ".notdef", ".notdef", + ".notdef", ".notdef", ".notdef", ".notdef", + ".notdef", ".notdef", ".notdef", ".notdef", + ".notdef", ".notdef", ".notdef", ".notdef", + "space", "exclam", "quotedbl", "numbersign", + "dollar", "percent", "ampersand", "quoteright", + "parenleft", "parenright", "asterisk", "plus", + "comma", "hyphen", "period", "slash", + "zero", "one", "two", "three", + "four", "five", "six", "seven", + "eight", "nine", "colon", "semicolon", + "less", "equal", "greater", "question", + "at", "A", "B", "C", + "D", "E", "F", "G", + "H", "I", "J", "K", + "L", "M", "N", "O", + "P", "Q", "R", "S", + "T", "U", "V", "W", + "X", "Y", "Z", "bracketleft", + "backslash", "bracketright", "asciicircum", "underscore", + "quoteleft", "a", "b", "c", + "d", "e", "f", "g", + "h", "i", "j", "k", + "l", "m", "n", "o", + "p", "q", "r", "s", + "t", "u", "v", "w", + "x", "y", "z", "braceleft", + "bar", "braceright", "asciitilde", ".notdef", + ".notdef", ".notdef", ".notdef", ".notdef", + ".notdef", ".notdef", ".notdef", ".notdef", + ".notdef", ".notdef", ".notdef", ".notdef", + ".notdef", ".notdef", ".notdef", ".notdef", + ".notdef", ".notdef", ".notdef", ".notdef", + ".notdef", ".notdef", ".notdef", ".notdef", + ".notdef", ".notdef", ".notdef", ".notdef", + ".notdef", ".notdef", ".notdef", ".notdef", + ".notdef", "exclamdown", "cent", "sterling", + "fraction", "yen", "florin", "section", + "currency", "quotesingle", "quotedblleft", "guillemotleft", + "guilsinglleft", "guilsinglright", "fi", "fl", + ".notdef", "endash", "dagger", "daggerdbl", + "periodcentered", ".notdef", "paragraph", "bullet", + "quotesinglbase", "quotedblbase", "quotedblright", "guillemotright", + "ellipsis", "perthousand", ".notdef", "questiondown", + ".notdef", "grave", "acute", "circumflex", + "tilde", "macron", "breve", "dotaccent", + "dieresis", ".notdef", "ring", "cedilla", + ".notdef", "hungarumlaut", "ogonek", "caron", + "emdash", ".notdef", ".notdef", ".notdef", + ".notdef", ".notdef", ".notdef", ".notdef", + ".notdef", ".notdef", ".notdef", ".notdef", + ".notdef", ".notdef", ".notdef", ".notdef", + ".notdef", "AE", ".notdef", "ordfeminine", + ".notdef", ".notdef", ".notdef", ".notdef", + "Lslash", "Oslash", "OE", "ordmasculine", + ".notdef", ".notdef", ".notdef", ".notdef", + ".notdef", "ae", ".notdef", ".notdef", + ".notdef", "dotlessi", ".notdef", ".notdef", + "lslash", "oslash", "oe", "germandbls", + ".notdef", ".notdef", ".notdef", ".notdef" +); + +############### +# Read DEF file +############### +# +open DEF, $opt_d or die "Cannot open $opt_d: $!\n"; +while (<DEF>) { + next if (/^\s*$/ || /^\#/); + s/\s*(\#.*)?$//; + push @deflines, $_; +} +close DEF; + +############### +# Read VPL file +############### +# +# File header +# +$vplhead = <> or exit 1; +unless ($vplhead =~ /^\((VTITLE|FAMILY) /) { + die "$filename is not a vpl file: giving up\n" +} +do { + $_ = <>; + $vplhead .= $_; +} until ($_ =~ /^\(LIGTABLE$/ or eof); +if (eof) { + die "$filename does not seem to be a text font (no LIGTABLE): giving up\n"; +} +if ($vplhead =~ s/\A\(VTITLE(.*)$/$vtitle\n(COMMENT Old vtitle:$1/m) { + $vplhead =~ s/\n\(COMMENT Please edit that VTITLE .*\)$//m; + @enc = @dvipsenc; + $dvips = 1; +} +elsif ($vplhead =~ /\A\(FAMILY.*\)\n\(CODINGSCHEME ADOBESTANDARDENCODING\)$/m) { + $vplhead =~ s/\A/$vtitle\n/m; + @enc = @adobeenc; + $dvips = 0; +} +else { + $vplhead =~ s/\A/$vtitle\n/m; + @enc = @TeXenc; + $dvips = 0; +} +if ($vplhead =~ /^\(CODINGSCHEME TEX MATH SYMBOLS/m) { + die "$filename is a TeX math font: giving up\n"; +} +unless ($vplhead =~ s/^(\(CODINGSCHEME .*\+\s?)(\S+)\)$/$1$encname)/m) { + $vplhead =~ s/^(\(CODINGSCHEME .*)\)$/$1 + $encname)/m; +} +if ($vplhead =~ /^\(DESIGNUNITS R (.+)\)/m) { $scale = $1 } +else {$scale = 1 } +if ($vplhead =~ /^ \(SLANT R (.+)\)/m) { $slant = $1 } +if ($vplhead =~ /^ \(XHEIGHT [DR] (.+)\)/m) { $xheight = $1 } +unless ($vplhead =~ /^\(MAPFONT /m) { + if ($vplhead =~ /^\(DESIGNSIZE R (.*)\)$/m) { $dsize = $1 } + $mapfont = "\n(MAPFONT D 0\n (FONTNAME $fontname)\n (FONTDSIZE R $dsize)\n )"; + $vplhead =~ s/\n\(LIGTABLE\Z/$mapfont$&/m; +} +if ($opt_s) { + $vplhead =~ s[^(\(MAPFONT D )0(.*?)( \))] + [$&\n${1}1$2 (FONTAT R ${ \($shrink * $scale) })\n$3]ms; +} + +# +# Ligatures and kerns +# +do { + $_ = <>; + s/ \(comment .*$//i; + $ligs .= $_; +} until $_ =~ /^ \)/; +# +# Now build a hash to convert from vpl representation to char name +# and use it to make ligtable readable +# +foreach $i (0 .. 255) { $vc{$nv[$i]} = $enc[$i] } +$ligs =~ s/^( \((?:LABEL|KRN) )(\S+ \S+)(.*\))$/$1$vc{$2}$3/gm; +$ligs =~ s/^( \(LIG )(\S+ \S+) (\S+ \S+)\)$/$1$vc{$2} $vc{$3})/gm; + +# +# Character definitions: store "encoded" defs in @chars, store *all* +# defs in %allchars +# +$_ = <>; +do { + if (/^\(CHARACTER/) { + $character = $_; + do { + $_ = <>; + $character .= $_; + } until $_ =~ /^ \)/; + storeinfo($character); + $_ = <>; + } +} until eof; +foreach $i (0 .. $#chars) { + if ($chars[$i] and $enc[$i] ne ".notdef") { + $allchars{$enc[$i]} = $chars[$i]; + } +} + +################## +# Set up constants +################## + +$subacc = "(cedilla|ogonek|commaaccent)"; +$supacc = "(grave|acute|circumflex|tilde|macron|breve|dotaccent|overdot|dieresis|ring|hungarumlaut|caron|candrabindu)"; +$underacc = "(underdot|under$supacc)"; +$accents = "($subacc|$supacc|$underacc|underbar)"; +$underadp = 0.230; # depth of "under" accs +$underddp = 0.213; # depth of underdot +if ($bold) { $thk = 0.072 } else { $thk = 0.052 } # thickness and +$underbdp = 0.082 + $thk; # depth of underbar +$capheight = $allchars{"X"}{ht}; +$accheight = $allchars{"macron"}{ht}; +$accdepth = $accheight - $thk * $scale; # probable approx. "depth" of macron +$v1 = $accheight - $xheight; # vertical offset for double accents +$v2 = $capheight - $xheight; # vertical offset for accented caps etc +if ($scaps) { # accented small caps + $scoffset = $allchars{"x"}{ht} - $xheight; + $v1 += $scoffset; +} +if ($opt_c) { # candrabindu + ($cbx, $cby) = $opt_c =~ /^(.*),(.*)$/; + $cbx += ($allchars{"breve"}{wd} - $allchars{"dotaccent"}{wd}) / 2; + $cbx /= 1000; + $cby /= 1000; +} + +###################### +# Build the characters +###################### +# +# First normalise dvips.enc encoding quirks +# +if ($dvips) { + chmove("fi", 014); + chmove("fl", 015); + chmove("quotedblright", 042); + chmove("quotedblleft", 0134); + chmove("dotaccent", 0137); + chmove("endash", 0173); + chmove("emdash", 0174); + chmove("hungarumlaut", 0175); +} +# +# Now build a list of definitions supplied by user +# +for (@deflines) { + if (/^\s*(\d+|0[0-7]+|0x[0-9a-fA-F]+)\s+([a-zA-Z]+?|\.notdef)(?:\s+([a-zA-Z]+))?$/) { + ($num, $char, $acc) = ($1, $2, $3); + $num = oct $num if $num =~ /^0/; + if ($num > 255) { die "Bad definition (number out of range): $_\n" } + $def = {}; + $def->{qdef} = $_; + $def->{num} = $num; + $def->{char} = $char; + $def->{acc} = $acc; + $def->{nchar} = $char . $acc; + push @nchars, $def->{nchar}; + push @defs, $def; + } + else { die "Bad definition: $_\n" } +} +# +# Work through the list +# +while (@defs) { + $def = shift @defs; + $qdef = $def->{qdef}; + $num = $def->{num}; + $char = $def->{char}; + $acc = $def->{acc}; + $nchar = $def->{nchar}; + # + # If we can't handle $char/$acc yet, but believe we will be able + # to later, send the definition to the back of the queue. In case + # it later turns out we were wrong, allow only five loops before + # giving up. + # + if (!$allchars{$char} and $char ne ".notdef") { + if (grep /^$char$/, @nchars) { + unless (++$def->{requeue} > 5) { + push @defs, $def; + next; + } + } + else { die "Bad definition (no such character): $qdef\n" } + } + if ($acc and !$allchars{$acc} and $acc !~ /^$accents$/) { + if (grep /^$acc$/, @nchars) { + unless (++$def->{requeue} > 5) { + push @defs, $def; + next; + } + } + else { die "Bad definition (no such accent): $qdef\n" } + } + # + # Remove any existing claims on $num + # + @{ $allchars{$chars[$num]{id}}{num} } = grep !/$num/, + @{ $allchars{$chars[$num]{id}}{num} }; + # + # First deal with .notdef + # + if ($nchar eq ".notdef") { + undef $chars[$num]; + } + # + # Next look among existing chars (unless blocked by -b) + # + elsif (!($acc and $opt_b) and $allchars{$nchar}) { + push( @{ $allchars{$nchar}{num} }, $num); + $chars[$num] = $allchars{$nchar}; + } + # + # If it can't be built from sub-elements, issue a warning and move on + # + elsif (!$acc) { + warn "No such character - ignoring definition: $qdef\n"; + undef $chars[$num]; + } + # + # Now build the char + # + else { + # + # First get rid of predefined/duplicated ligtable statements + # and character definitions; also synonyms + # + $ligs =~ s/\n \((LABEL|KRN|LIG) ($nchar .*|.*$nchar)\)$//gm; + $allchars{$nchar} = (); + if ($acc eq "overdot") { + $nchar2 = $char . "dotaccent"; + $ligs =~ s/\n \((LABEL|KRN|LIG) ($nchar2 .*|.*$nchar2)\)$//gm; + delete $allchars{$nchar2}; + } + # + # Go! + # + if ($acc =~ /^$subacc$/) { + subacc($num, $char, $acc, $nchar); + fixkerns($char, $acc); + } + elsif ($acc =~ /^$supacc$/) { + supacc($num, $char, $acc, $nchar); + fixkerns($char, $acc); + } + elsif ($acc =~ /^$underacc$/) { + underacc($num, $char, $acc, $nchar); + fixkerns($char, $acc); + } + elsif ($acc =~ /^underbar$/) { + underb($num, $char, $nchar); + fixkerns($char, $acc); + } + else { + digraph($num, $char, $acc, $nchar); + fixkerns($char, $acc); + } + } +} + +################### +# Sort out ligtable +################### +# +# Convert to vpl representation, eliminating statements invoking +# "unencoded" characters +# +@liglist = split /\n/, $ligs; +$ligs = ""; +foreach (@liglist) { + if (/^( \(LIG \S+ )(\S+)\)$/) { + if ($n = ${ $allchars{$2}{num} }[0]) { + s/^( \(LIG \S+ )(\S+)\)$/$1$nv[$n])/; + } + else { next } + } + if (/^( \((?:LABEL|LIG|KRN) )([^ )]+)(.*)$/) { + ($one, $two, $three) = ($1, $2, $3); + foreach $n (@{ $allchars{$two}{num} }) { + $ligs .= "$one$nv[$n]$three\n"; + } + } + else { $ligs .= "$_\n" } +} +# +# Eliminate sequences orphaned by elimination of a LABEL +# +@liglist = split / \(STOP\)\n/, $ligs; +$ligs = ""; +foreach (@liglist) { + if (/^ \(LABEL /m) { $ligs .= "$_ (STOP)\n" } + elsif (/^ \)$/m) { $ligs .= $_ } +} +# +# Eliminate empty statements +# +$ligs =~ s/(^ \(LABEL .*\)\n)+ \(STOP\)\n//gm; + +#################### +# Output the results +#################### +# +print $vplhead, $ligs; +foreach $i (0 .. 255) { if (defined $chars[$i]{id}) { printchar($i) } } + +##################### +# End of main program +##################### + +sub storeinfo { + # + # Extract info from a character definition and store it in @chars + # + my $char = shift; + my $num; + if ($char =~ /\A\(CHARACTER O ([0-7]+)/m) { $num = oct $1 } + elsif ($char =~ /\A\(CHARACTER C (.)/m) { $num = ord $1 } + $chars[$num]{id} = $enc[$num]; + push( @{ $chars[$num]{num} }, $num); + if ($char =~ /^ \(CHARWD R (.*?)\)$/m) { $chars[$num]{wd} = $1 } + if ($char =~ /^ \(CHARHT R (.*?)\)$/m) { $chars[$num]{ht} = $1 } + if ($char =~ /^ \(CHARDP R (.*?)\)$/m) { $chars[$num]{dp} = $1 } + if ($char =~ /^ \(CHARIC R (.*?)\)$/m) { $chars[$num]{ic} = $1 } + if ($char =~ /^ \(MAP\n((.|\n)*)^ \)/m) { $chars[$num]{map} = $1 } + else { $chars[$num]{map} = " (SETCHAR $nv[$num])\n" } +} + +sub printchar { + # + # Extract info from @chars and build it into a character definition + # + my $num = shift; + print "(CHARACTER "; + if (chr($num) =~ /[0-9A-Za-z]/) { print "C " . chr($num) } + else { + printf "O %lo", $num; + print " (COMMENT " . $chars[$num]{id} . ")"; + } + print "\n"; + print " (CHARWD R " . $chars[$num]{wd} . ")\n" if $chars[$num]{wd}; + print " (CHARHT R " . $chars[$num]{ht} . ")\n" if $chars[$num]{ht}; + print " (CHARDP R " . $chars[$num]{dp} . ")\n" if $chars[$num]{dp}; + print " (CHARIC R " . $chars[$num]{ic} . ")\n" if $chars[$num]{ic}; + print " (MAP\n"; + print $chars[$num]{map}; + print " )\n"; + print " )\n"; +} + +sub chmove { + # + # Move a character + # + my ($char, $num) = @_; + my $i; + foreach $i (@{ $allchars{$char}{num} }) { undef $chars[$i] } + @{ $allchars{$char}{num} } = (); + @{ $allchars{$chars[$num]{id}}{num} } = grep !/$num/, + @{ $allchars{$chars[$num]{id}}{num} }; + push( @{ $allchars{$char}{num} }, $num); + $chars[$num] = $allchars{$char}; +} + +sub max { + # + # Return greater of two values + # + my ($a, $b) = @_; + return $a > $b ? $a : $b; +} + +sub subacc { + # + # Subscript accents + # + my ($num, $char, $acc, $id) = @_; + my ($h, $s1, $s2, $s3); + $allchars{$id}{wd} = $allchars{$char}{wd}; + $allchars{$id}{ht} = $allchars{$char}{ht}; + $allchars{$id}{dp} = $allchars{$acc}{dp}; + $allchars{$id}{ic} = $allchars{$char}{ic}; + $allchars{$id}{id} = $id; + push( @{ $allchars{$id}{num} }, $num); + $s1 = $allchars{$char}{map}; + $s1 =~ s/\A (.*)\n\Z/(PUSH) $1 (POP)/s; + $h = sprintf("%.3f", ($allchars{$char}{wd} - $allchars{$acc}{wd}) / 2); + if ($h > 0) { $s2 = " (MOVERIGHT R $h) " } + elsif ($h < 0) { + $h = -$h; + $s2 = " (MOVELEFT R $h) "; + } + else { $s2 = " " } + $s3 = $allchars{$acc}{map}; + $s3 =~ s/\A.*(\(SETCHAR . .+?\)).*\Z/$1/s; + $allchars{$id}{map} = " $s1\n$s2$s3\n"; + $chars[$num] = $allchars{$id}; +} + +sub supacc { + # + # Superscript accents + # + my ($num, $char, $acc, $id) = @_; + my ($cb, $h, $hadj, $tallchar, $ic, $s1, $s2, $s3); + if ($char eq "i" and $allchars{"dotlessi"}) { $char = "dotlessi" } + if ($char eq "j" and $allchars{"dotlessj"}) { $char = "dotlessj" } + if ($acc eq "overdot") { $acc = "dotaccent" } + if ($acc eq "candrabindu") { + $acc = "breve"; + ($cb = $allchars{"dotaccent"}{map}) =~ s/\A.*(\(SETCHAR . .+?\)).*\Z/$1/s; + } + $allchars{$id}{wd} = $allchars{$char}{wd}; + $allchars{$id}{ht} = $allchars{$acc}{ht}; + $allchars{$id}{dp} = $allchars{$char}{dp}; + $allchars{$id}{id} = $id; + push( @{ $allchars{$id}{num} }, $num); + $s1 = $allchars{$char}{map}; + $s1 =~ s/\A (.*)\n\Z/(PUSH) $1 (POP)/s; + if ($scaps and $char =~ /^[a-z]/) { # accented small caps + $tallchar = 1; + if ($char =~ /$supacc$/ + and $char !~ /under$supacc$/) { # double accs + $s2 = " (MOVEUP R $v1)"; + $allchars{$id}{ht} += $v1; + $hadj = sprintf("%.3f", $v1 * $slant); + $ic = $allchars{$char}{ic}; + } + else { # single accs + $s2 = " (MOVEUP R $scoffset)"; + $allchars{$id}{ht} += $scoffset; + $hadj = sprintf("%.3f", $scoffset * $slant); + $ic = $allchars{$acc}{ic} + $hadj; + } + } + elsif ($allchars{$char}{ht} >= ($accheight + $v2)) { # double accs + $tallchar = 1; # on caps etc. + $s2 = " (MOVEUP R ${ \($v1 + $v2) })"; + $allchars{$id}{ht} += ($v1 + $v2); + $hadj = sprintf("%.3f", ($v1 + $v2) * $slant); + $ic = $allchars{$char}{ic}; + } + elsif ($allchars{$char}{ht} > 1.15 * $xheight) { + $tallchar = 1; + if ($char =~ /$supacc$/ + and $char !~ /under$supacc$/) { # double accs + $s2 = " (MOVEUP R $v1)"; + $allchars{$id}{ht} += $v1; + $hadj = sprintf("%.3f", $v1 * $slant); + $ic = $allchars{$char}{ic}; + } + else { # caps etc. + $s2 = " (MOVEUP R $v2)"; + $allchars{$id}{ht} += $v2; + $hadj = sprintf("%.3f", $v2 * $slant); + $ic = $allchars{$char}{ic}; + } + } + else { # single accs + $s2 = " "; + $ic = $allchars{$acc}{ic}; + } + $h = sprintf("%.3f", ($allchars{$char}{wd} - $allchars{$acc}{wd}) / 2); + unless ($tallchar) { $ic -= $h } + $allchars{$id}{ic} = $ic unless $ic < 0; + $h += $hadj; + if ($h > 0) { $s2 .= " (MOVERIGHT R $h) " } + elsif ($h < 0) { + $h = -$h; + $s2 .= " (MOVELEFT R $h) "; + } + else { $s2 .= " " } + $s3 = $allchars{$acc}{map}; + $s3 =~ s/\A.*(\(SETCHAR . .+?\)).*\Z/$1/s; + if ($cb) { # candrabindu + $cb = $s2 . $cb; + if ($cbx) { + unless (($cb =~ s/(MOVERIGHT R )([0-9.]+)/$1 . ($2 + $cbx * $scale)/e) + or ($cb =~ s/(MOVELEFT R )([0-9.]+)/$1 . ($2 - $cbx * $scale)/e)) { + $cb =~ s/^( +)/"$1(MOVERIGHT R " . ($cbx * $scale) . ") "/e; + } + } + if ($cby) { + unless ($cb =~ s/(MOVEUP R )([0-9.]+)/$1 . ($2 + $cby * $scale)/e) { + $cb =~ s/^( +)/"$1(MOVEUP R " . ($cby * $scale) . ") "/e; + } + } + $cb .= "\n"; + $s1 = "(PUSH) " . $s1; + $s3 .= " (POP)"; + } + $allchars{$id}{map} = " $s1\n$s2$s3\n$cb"; + $chars[$num] = $allchars{$id}; +} + +sub underacc { + # + # Dropped accents + # + my ($num, $char, $acc, $id) = @_; + my ($h, $v, $s1, $s2, $s3); + $acc =~ s/^under//; + if ($acc eq "dot") { $acc = "period" } + if ($acc eq "candrabindu") { die "Bad definition (no such accent): $qdef\n" } + $allchars{$id}{wd} = $allchars{$char}{wd}; + $allchars{$id}{ht} = $allchars{$char}{ht}; + $allchars{$id}{ic} = $allchars{$char}{ic}; + $allchars{$id}{id} = $id; + push( @{ $allchars{$id}{num} }, $num); + if ($acc =~ /^$supacc$/) { + $v = $allchars{$id}{dp} = $underadp * $scale * $shrink; + $v += ($accdepth * $shrink); + } + else { + $v = $allchars{$id}{dp} = $underddp * $scale + $allchars{$acc}{dp}; + } + $s1 = $allchars{$char}{map}; + $s1 =~ s/\A (.*)\n\Z/(PUSH) $1 (POP)/s; + if ($acc =~ /^$supacc$/) { + $h = ($allchars{$char}{wd} - ($allchars{$acc}{wd} * $shrink)) / 2 - $v * $slant; + if ($opt_s) { $s2 = " (SELECTFONT D 1)\n" } + } + else { + $h = ($allchars{$char}{wd} - $allchars{$acc}{wd}) / 2 - $v * $slant; + } + $h = sprintf("%.3f", $h); + if ($h > 0) { + $s2 .= " (MOVEDOWN R $v) (MOVERIGHT R $h) "; + } + elsif ($h < 0) { + $h = -$h; + $s2 .= " (MOVEDOWN R $v) (MOVELEFT R $h) "; + } + else { $s2 = " (MOVEDOWN R $v) " } + $s3 = $allchars{$acc}{map}; + $s3 =~ s/\A.*(\(SETCHAR . .+?\)).*\Z/$1/s; + if ($opt_s and $acc =~ /^$supacc$/) { $s3 .= "\n (SELECTFONT D 0)" } + $allchars{$id}{map} = " $s1\n$s2$s3\n"; + $chars[$num] = $allchars{$id}; +} + +sub underb { + # + # Underbar + # + my ($num, $char, $id) = @_; + my ($h, $w, $dp, $s1, $s2, $s3); + $allchars{$id}{wd} = $allchars{$char}{wd}; + $allchars{$id}{ht} = $allchars{$char}{ht}; + $allchars{$id}{dp} = $dp = $underbdp * $scale; + $allchars{$id}{ic} = $allchars{$char}{ic}; + $allchars{$id}{id} = $id; + push( @{ $allchars{$id}{num} }, $num); + $s1 = $allchars{$char}{map}; + $s1 =~ s/\A (.*)\n\Z/(PUSH) $1 (POP)/s; + $h = sprintf("%.3f", ($allchars{$id}{wd} / 10 - $dp * $slant)); + $w = sprintf("%.3f", ($allchars{$id}{wd} * 8 / 10)); + if ($h > 0) { + $s2 = " (MOVEDOWN R $dp) (MOVERIGHT R $h) "; + } + elsif ($h < 0) { + $h = -$h; + $s2 = " (MOVEDOWN R $dp) (MOVELEFT R $h) "; + } + else { $s2 .= " (MOVEDOWN R $dp) " } + $s3 = "(SETRULE R ${ \($thk * $scale) } R $w)"; + $allchars{$id}{map} = " $s1\n$s2$s3\n"; + $chars[$num] = $allchars{$id}; +} + +sub digraph { + # + # Make a new character consisting of two existing characters + # + my ($num, $char, $acc, $id) = @_; + my ($one, $two, $kern, $s1, $s2); + if ($ligs =~ /^ \(LABEL $char\)\n(.*?)\n \(KRN $acc R (-?[0-9.]+)\)\n/ms) { + ($one, $two) = ($1, $2); + } + $kern = $two if $one !~ /^ \(STOP\)$/m; + $allchars{$id}{wd} = $allchars{$char}{wd} + $allchars{$acc}{wd}; + $allchars{$id}{wd} += $kern; + $allchars{$id}{ht} = max($allchars{$char}{ht}, $allchars{$acc}{ht}); + $allchars{$id}{dp} = max($allchars{$char}{dp}, $allchars{$acc}{dp}); + $allchars{$id}{ic} = $allchars{$acc}{ic}; + $allchars{$id}{id} = $id; + push( @{ $allchars{$id}{num} }, $num); + $s1 = $allchars{$char}{map}; + chomp ($s2 = $allchars{$acc}{map}); + $s1 =~ s/(\(SETCHAR .*?\))/$1\n$s2/; + if ($kern) { + if ($kern < 0) { + $kern = -$kern; + $s1 =~ s/(\(SETCHAR .*?\))/$1 (MOVELEFT R $kern)/; + } + else { $s1 =~ s/(\(SETCHAR .*?\))/$1 (MOVERIGHT R $kern)/ } + } + $allchars{$id}{map} = $s1; + $chars[$num] = $allchars{$id}; +} + +sub fixkerns { + # + # Generalise the kerning info contained in the vpl file by applying + # it to new accented chars. Do not kern lower-case chars bearing + # superscript accents with capitals, quotes or a preceding "f". + # + my ($char, $acc) = @_; + my ($olabel, $nlabel, @liglist, $lchar, $rchar); + if ($acc =~ /^$accents$/) { $lchar = $rchar = $char } + else { + $lchar = $char; + $rchar = $acc; + } + unless ($char =~ /^[a-z]/ and $acc =~ /^$supacc$/) { + $ligs =~ s[(\n \(LABEL )$rchar\)(?!\n \(LIG.*$)] + [$&$1$char$acc)]gm + unless $ligs =~ /\n \(LABEL $char$acc\)$/m; + $ligs =~ s[(\n \(LABEL )$rchar\)(\n \(LIG.*$)+(?!\n \(STOP\))] + [$&$1$char$acc)]gm + unless $ligs =~ /\n \(LABEL $char$acc\)$/m; + $ligs =~ s[(\n \(KRN )$lchar( .*)$] + [$&$1$char$acc$2]gm; + } + else { + if ($ligs =~ /\n \(LABEL $char\).*?\(STOP\)/s) { + $nlabel = $olabel = $&; + $nlabel =~ s/(\n \(LABEL $char)\)/$1$acc)/ + unless $ligs =~ /\n \(LABEL $char$acc\)/m; + $nlabel =~ s/\n \(LIG .*\)$//gm; + $nlabel =~ s/\n \(LABEL (?!$char$acc).*\)$//gm; + $nlabel =~ s/\n \(KRN ([A-Z]|quote).*\)$//gm; + $ligs =~ s/(\n \(LABEL )$char\).*?\(STOP\)/$olabel$nlabel/s; + } + @liglist = split /\n \(STOP\)/, $ligs; + foreach (@liglist) { + unless (/\n \(LABEL ([A-Zf]|quote).*\)$/m) { + s/(\n \(KRN $char)( .*\))$/$&$1$acc$2/gm; + } + } + $ligs = join("\n (STOP)", @liglist); + } +} |