texlive[64447] trunk: texaccents (20sep22)
commits+karl at tug.org
commits+karl at tug.org
Tue Sep 20 00:37:10 CEST 2022
Revision: 64447
http://tug.org/svn/texlive?view=revision&revision=64447
Author: karl
Date: 2022-09-20 00:37:09 +0200 (Tue, 20 Sep 2022)
Log Message:
-----------
texaccents (20sep22)
Modified Paths:
--------------
trunk/Build/source/texk/texlive/linked_scripts/Makefile.am
trunk/Build/source/texk/texlive/linked_scripts/Makefile.in
trunk/Build/source/texk/texlive/linked_scripts/scripts.lst
trunk/Master/tlpkg/bin/tlpkg-ctan-check
trunk/Master/tlpkg/libexec/ctan2tds
trunk/Master/tlpkg/tlpsrc/collection-binextra.tlpsrc
Added Paths:
-----------
trunk/Build/source/texk/texlive/linked_scripts/texaccents/
trunk/Build/source/texk/texlive/linked_scripts/texaccents/texaccents.sno
trunk/Master/bin/aarch64-linux/texaccents
trunk/Master/bin/amd64-freebsd/texaccents
trunk/Master/bin/amd64-netbsd/texaccents
trunk/Master/bin/armhf-linux/texaccents
trunk/Master/bin/i386-cygwin/texaccents
trunk/Master/bin/i386-freebsd/texaccents
trunk/Master/bin/i386-linux/texaccents
trunk/Master/bin/i386-netbsd/texaccents
trunk/Master/bin/i386-solaris/texaccents
trunk/Master/bin/universal-darwin/texaccents
trunk/Master/bin/win32/texaccents.exe
trunk/Master/bin/x86_64-cygwin/texaccents
trunk/Master/bin/x86_64-darwinlegacy/texaccents
trunk/Master/bin/x86_64-linux/texaccents
trunk/Master/bin/x86_64-linuxmusl/texaccents
trunk/Master/bin/x86_64-solaris/texaccents
trunk/Master/texmf-dist/doc/man/man1/texaccents.1
trunk/Master/texmf-dist/doc/man/man1/texaccents.man1.pdf
trunk/Master/texmf-dist/doc/support/texaccents/
trunk/Master/texmf-dist/doc/support/texaccents/LICENSE
trunk/Master/texmf-dist/doc/support/texaccents/README.md
trunk/Master/texmf-dist/doc/support/texaccents/testaccents-in
trunk/Master/texmf-dist/doc/support/texaccents/texaccents.md
trunk/Master/texmf-dist/doc/support/texaccents/texaccents.pdf
trunk/Master/texmf-dist/doc/support/texaccents/texaccents.spt
trunk/Master/texmf-dist/doc/support/texaccents/texaccents.tex
trunk/Master/texmf-dist/scripts/texaccents/
trunk/Master/texmf-dist/scripts/texaccents/texaccents.sno
trunk/Master/texmf-dist/source/support/texaccents/
trunk/Master/texmf-dist/source/support/texaccents/compiler.inc
trunk/Master/texmf-dist/source/support/texaccents/delete.inc
trunk/Master/texmf-dist/source/support/texaccents/grepl.inc
trunk/Master/texmf-dist/source/support/texaccents/newline.inc
trunk/Master/texmf-dist/source/support/texaccents/systype.inc
trunk/Master/tlpkg/tlpsrc/texaccents.tlpsrc
Modified: trunk/Build/source/texk/texlive/linked_scripts/Makefile.am
===================================================================
--- trunk/Build/source/texk/texlive/linked_scripts/Makefile.am 2022-09-19 20:28:42 UTC (rev 64446)
+++ trunk/Build/source/texk/texlive/linked_scripts/Makefile.am 2022-09-19 22:37:09 UTC (rev 64447)
@@ -75,6 +75,7 @@
pdfxup/pdfxup \
pst-pdf/ps4pdf \
simpdftex/simpdftex \
+ texaccents/texaccents.sno \
texlive-extra/allcm.sh \
texlive-extra/allneeded.sh \
texlive-extra/dvi2fax.sh \
Modified: trunk/Build/source/texk/texlive/linked_scripts/Makefile.in
===================================================================
--- trunk/Build/source/texk/texlive/linked_scripts/Makefile.in 2022-09-19 20:28:42 UTC (rev 64446)
+++ trunk/Build/source/texk/texlive/linked_scripts/Makefile.in 2022-09-19 22:37:09 UTC (rev 64447)
@@ -289,6 +289,7 @@
pdfxup/pdfxup \
pst-pdf/ps4pdf \
simpdftex/simpdftex \
+ texaccents/texaccents.sno \
texlive-extra/allcm.sh \
texlive-extra/allneeded.sh \
texlive-extra/dvi2fax.sh \
Modified: trunk/Build/source/texk/texlive/linked_scripts/scripts.lst
===================================================================
--- trunk/Build/source/texk/texlive/linked_scripts/scripts.lst 2022-09-19 20:28:42 UTC (rev 64446)
+++ trunk/Build/source/texk/texlive/linked_scripts/scripts.lst 2022-09-19 22:37:09 UTC (rev 64447)
@@ -16,6 +16,7 @@
pdfxup/pdfxup
pst-pdf/ps4pdf
simpdftex/simpdftex
+texaccents/texaccents.sno
texlive-extra/allcm.sh
texlive-extra/allneeded.sh
texlive-extra/dvi2fax.sh
Added: trunk/Build/source/texk/texlive/linked_scripts/texaccents/texaccents.sno
===================================================================
--- trunk/Build/source/texk/texlive/linked_scripts/texaccents/texaccents.sno (rev 0)
+++ trunk/Build/source/texk/texlive/linked_scripts/texaccents/texaccents.sno 2022-09-19 22:37:09 UTC (rev 64447)
@@ -0,0 +1,274 @@
+#!/usr/bin/env snobol4
+# texaccents.sno
+# version 1.0.1
+# 2022.08.23 -- 2022.09.17
+# guido.milanese at unicatt.it
+# Transforms LaTeX accents to their UTF8 equivalents
+# accepts both LaTeX and Bibtex codes:
+# examples: \'a \'{a} {\"a} and even {\'{a}}
+# tables of accents imported from:
+# https://github.com/hayk314/LaTex-handler -- Author: Hayk Aleksanyan
+# with my integrations, including ligatures as \ae{}
+# requires snobol4: see http://www.regressive.org/snobol4/csnobol4/curr/
+
+#################################################################
+# MIT License - Copyright (c) 2022 Guido Milanese
+# See file LICENSE in this package
+#################################################################
+
+******************************************************
+* FUNCTIONS
+******************************************************
+
+*-- Function INITIALISE
+*-- opens files, imports functions
+ define("initialise()")
+ :(initialise_end)
+initialise
+initialise_bg
+* INCLUDE FILES
+-include "delete.inc"
+-include "host.inc"
+-include "newline.inc"
+-include "grepl.inc" ;* essential! calls repl internally
+ MAX = 8000000 ;* max size of input/output files = 8 megs
+ NL = newline()
+ HELP_MSG = "texaccents 1.0.1" NL
++ "Converts legacy (La)TeX accents and ligatures to Unicode" NL
++ "Usage: texaccents.sno INFILE OUTFILE" NL
++ "--help print this help, then exit" NL
++ "--version print version number, then exit" NL
++ "Report bugs to <guido.milanese at unicatt.it>" NL
++ "CTAN page of the package: <https://www.ctan.org/pkg/texaccents>"
+
+ VERS_MSG = "texaccents 1.0.1" NL NL
++ "Copyright (c) 2022 Guido Milanese" NL NL
++ "This is free software; see the source for copying conditions. There is NO" NL
++ "warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE." NL nl
++ "Written by Guido Milanese <guido.milanese at unicatt.it>"
+
+
+#######################################################
+# opens input / output files
+#######################################################
+* Defines and checks Input & Output
+* help request -- exits. Both "--help" and "-help" are valid
+ ((host(2,2) ? "-help") (Terminal = HELP_MSG)) :s(end)
+* version request -- exits. Both "--version" and "-version" are valid
+ ((host(2,2) ? "-version") (Terminal = VERS_MSG)) :s(end)
+* Normal input-output with error messages.
+* Error messages are used by MAIN if necessary
+ (~(infile = host(2,2)) ((Terminal = HELP_MSG) (ERROR_MSG = "Input error"))) :s(freturn)
+ (~(outfile = host(2,3)) ((Terminal = HELP_MSG) (ERROR_MSG = "Output error"))) :s(freturn)
+ INPUT('r_f',1,"B " MAX, Infile) :f(freturn)
+ Terminal = "Reading text from " Infile
+ OUTPUT('w_f',2,"B " MAX, Outfile) :f(freturn)
+initialise_rt initialise = r_f :(return)
+initialise_end
+
+#####################################################################################
+*-- Function NORMACC
+*-- Changes TeX accents without curly brackets to the standard form
+*-- \'a --> \'{a}
+*-- and replaces ligatures such as \ae --> æ | \oe --> œ
+*-- requires GREPL
+#####################################################################################
+ define("normacc(Pass)")
+ P_shortacc = notany('{')
++ ((('\' any("'`" '"' "^=~.")) . Pre_shortacc)
++ (any(&ucase &lcase) . Letter_shortacc)) . V_shortacc
+ :(normacc_end)
+normacc
+normacc_bg Pass ? P_shortacc :f(normacc_lg)
+ Pass ? V_shortacc = Pre_shortacc '{' Letter_shortacc '}' :(normacc_bg)
+normacc_lg Pass2 = grepl(Pass,
++ "\ae{} \oe{} \AE{} \OE{} \dh{} \DH{} \th{} \TH{} \o{} \O{} \l{} \L{} ",
++ "æ œ Æ Œ ð Ð þ Þ ø Ø ł Ł ")
+ Terminal = "Ligatures tranformed"
+normacc_rt normacc = Pass2 :(return)
+normacc_end
+*
+* The pattern to normalise accents -- as \'a -- is defined as follows:
+* 1. there must be no '{' before backslash: otherwise the pattern would trap also
+* BibTex codes such as {\'a}
+* 2. find a backslash followed by any char of the list. Saved as "Pre_sortacc"
+* 3. find the accented letter. Saved as Letter_shortacc
+* 4. The whole structure is saved as V_shortacc
+* The programme will save the whole structure and substitute it in the text with:
+* Pre_shortacc (as \') + '{' + Letter_shortacc + '}'
+* in this way the short form -- \'a -- is transformed to the canonical \'{a}
+*
+* Ligatures and special chars are simply replaced with GREPL.
+
+#####################################################################################
+*-- Function CLEANACC
+*-- Substitutes plain letters to Unicode accents, using the sets provides by TRANSACC
+*-- \'{a} will output á
+#####################################################################################
+ define("cleanacc(Text,Acc1,Acc2)") :(cleanacc_end)
+* Acc1 is the original LaTeX code e.g. \"{a}
+* Acc2, at the time of calling the function, is e.g. \"{ä}
+cleanacc
+cleanacc_bg
+* removes paretheses: \"{ä} --> \"ä
+ Acc2 = delete(Acc2,"{}")
+* moves 2 chars and saves what remains, i.e. the letter
+* \"ä --> ä
+ Acc2 ? len(2) (rem . Acc2)
+* in text replaces e.g. \"{a} with ä
+* the substitution is done ONCE for the whole text
+ Text = repl(Text,Acc1,Acc2)
+ Terminal = "Working on " Acc2
+cleanacc_rt cleanacc = Text :(return)
+cleanacc_end
+
+#######################################################
+*-- Function TRANSACC
+*-- transforms LaTeX/Bibtex accents to Unicode
+#######################################################
+ define("transacc(Pass)")
+* Pass is the input text
+*
+* Accents used by Latex, e.g. \'{a} = acute accent over 'a'
+ Lat_acc =
++ any('"' "'" "`" 'H' '^' 'v' 'u' 'c' '.' 'd' 'k' '~' '=' 'b' 'r' )
++ . V_lat_acc
+*
+* The pattern says:
+* '\' + Lat_acc OR ('{\' + Lat_acc + '{' OR nothing)
+* any letter, saved as C_noacc + '}' + '}' OR nothing
+* Lat_acc is already defined above and saved ad V_lat_acc
+* Examples \'{a} -- {\'a} -- {\'{a}} (\'a was already "normalised")
+ P_lat_code =
++ (
++ (('\' Lat_acc '{') | ('{\' Lat_acc ('{' | '') ))
++ (any(&lcase &ucase) . C_noacc) '}' ('}' | '') ) . V_lat_code
+ :(transacc_end)
+transacc
+transacc_bg
+latcode_bg V_lat_code = ;* cleans previous value
+ V_lat_code_2 = ;* cleans previous value
+* Scans input text to locate the pattern
+* if no other LaTeX accents, fails and returns to main
+* if yes, goes to the section that transforms this accent.
+* e.g. if the accent is umlaut, will jump to TR"
+* After each transformation we have:
+* 1. the original code, e.g. \"{a} or \"a or {\"a}
+* 2. the transformed code, e.g. \"{ä} or \"ä or {\"ä}
+* Each section calls CLEANCLODE
+* CLEANCODE will remove all the {}\ and the LaTeX accent
+* and substitute in the input text e.g. \"{ä} with ä
+ Pass ? P_lat_code :f(latcode_nd)
+ :($('TR' V_lat_acc))
+
+TR" ;* umlaut
+ V_lat_code_2 = grepl(V_lat_code,
++ "A a B b C c E e H h I i K k M m N n O o P p Q q S s T t U u V v W w X x Y y Z z ",
++ "Ä ä B̈ b̈ C̈ c̈ Ë ë Ḧ ḧ Ï ï K̈ k̈ M̈ m̈ N̈ n̈ Ö ö P̈ p̈ Q̈ q̈ S̈ s̈ T̈ ẗ Ü ü V̈ v̈ Ẅ ẅ Ẍ ẍ Ÿ ÿ Z̈ z̈ ")
+ Pass = cleanacc(Pass,V_lat_code,V_lat_code_2) :(latcode_bg)
+
+TR' ;* acute
+ V_lat_code_2 = grepl(V_lat_code,
++ "A a B b C c D d E e F f G g H h I i J j K k L l M m N n O o P p Q q R r S s T t U u V v W w X x Y y Z z ",
++ "Á á B́ b́ Ć ć D́ d́ É é F́ f́ Ǵ ǵ H́ h́ Í í J́ ȷ́ Ḱ ḱ Ĺ ĺ Ḿ ḿ Ń ń Ó ó Ṕ ṕ Q́ q́ Ŕ ŕ Ś ś T́ t́ Ú ú V́ v́ Ẃ ẃ X́ x́ Ý ý Ź ź ")
+ Pass = cleanacc(Pass,V_lat_code,V_lat_code_2) :(latcode_bg)
+
+TRH ;* double acute - \H{o} Hungarian
+ V_lat_code_2 = grepl(V_lat_code,
++ "A a E e I i M m O o U u ",
++ "A̋ a̋ E̋ e̋ I̋ i̋ M̋ m̋ Ő ő Ű ű ")
+ Pass = cleanacc(Pass,V_lat_code,V_lat_code_2) :(latcode_bg)
+
+TR` ;* grave
+ V_lat_code_2 = grepl(V_lat_code,
++ "A a Æ æ E e H h I i K k M m N n O o R r S s T t U u V v W w X x Y y Z z ",
++ "À à Æ̀ æ̀ È è H̀ h̀ Ì ì K̀ k̀ M̀ m̀ Ǹ ǹ Ò ò R̀ r̀ S̀ s̀ T̀ t̀ Ù ù V̀ v̀ Ẁ ẁ X̀ x̀ Ỳ ỳ Z̀ z̀ ")
+ Pass = cleanacc(Pass,V_lat_code,V_lat_code_2) :(latcode_bg)
+
+TR^ ;* circumflex \^{o}
+ V_lat_code_2 = grepl(V_lat_code,
++ "A a B b C c D d E e G g H h I i J j K k L l M m N n O o R r S s T t U u V v W w X x Y y Z z ",
++ "Â â B̂ b̂ Ĉ ĉ D̂ d̂ Ê ê Ĝ ĝ Ĥ ĥ Î î Ĵ ĵ K̂ k̂ L̂ l̂ M̂ m̂ N̂ n̂ Ô ô R̂ r̂ Ŝ ŝ T̂ t̂ Û û V̂ v̂ Ŵ ŵ X̂ x̂ Ŷ ŷ Ẑ ẑ ")
+ Pass = cleanacc(Pass,V_lat_code,V_lat_code_2) :(latcode_bg)
+
+TRv ;* caron hraceck \v{s}
+* For accents that are also normal letters
+* we need to restore the accent to its original value
+* This applies to: v u c d k b r
+ V_lat_code_2 = grepl(V_lat_code,
++ "A a B b C c D d E e F f G g H h I i J j K k L l M m N n O o P p Q q R r S s T t U u V v W w X x Y y Z z ",
++ "Ǎ ǎ B̌ b̌ Č č Ď ď Ě ě F̌ f̌ Ǧ ǧ Ȟ ȟ Ǐ ǐ J̌ ǰ Ǩ ǩ Ľ ľ M̌ m̌ Ň ň Ǒ ǒ P̌ p̌ Q̌ q̌ Ř ř Š š Ť ť Ǔ ǔ V̌ v̌ W̌ w̌ X̌ x̌ Y̌ y̌ Ž ž ")
+ V_lat_code_2 = repl(V_lat_code_2,"\v̌","\v")
+ Pass = cleanacc(Pass,V_lat_code,V_lat_code_2) :(latcode_bg)
+
+TRu ;* breve \u{o}
+ V_lat_code_2 = grepl(V_lat_code,
++ "A a C c E e G g I i K k M m N n O o P p R r T t U u V v X x Y y ",
++ "Ă ă C̆ c̆ Ĕ ĕ Ğ ğ Ĭ ĭ K̆ k̆ M̆ m̆ N̆ n̆ Ŏ ŏ P̆ p̆ R̆ r̆ T̆ t̆ Ŭ ŭ V̆ v̆ X̆ x̆ Y̆ y̆ ")
+ V_lat_code_2 = repl(V_lat_code_2,"\ŭ","\u")
+ Pass = cleanacc(Pass,V_lat_code,V_lat_code_2) :(latcode_bg)
+
+TRc ;* cedilla \c{c}
+ V_lat_code_2 = grepl(V_lat_code,
++ "A a B b C c D d E e G g H h I i K k L l M m N n O o Q q R r S s T t U u X x Z z ",
++ "A̧ a̧ B̧ b̧ Ç ç Ḑ ḑ Ȩ ȩ Ģ ģ Ḩ ḩ I̧ i̧ Ķ ķ Ļ ļ M̧ m̧ Ņ ņ O̧ o̧ Q̧ q̧ Ŗ ŗ Ş ş Ţ ţ U̧ u̧ X̧ x̧ Z̧ z̧ ")
+ V_lat_code_2 = repl(V_lat_code_2,"\ç","\c")
+ Pass = cleanacc(Pass,V_lat_code,V_lat_code_2) :(latcode_bg)
+
+TR. ;* dot \.{o}
+ V_lat_code_2 = grepl(V_lat_code,
++ "A a B b C c D d E e F f G g H h I i K k L l M m N n O o P p Q q R r S s T t U u V v W w X x Y y Z z ",
++ "Ȧ ȧ Ḃ ḃ Ċ ċ Ḋ ḋ Ė ė Ḟ ḟ Ġ ġ Ḣ ḣ İ i̇̀ K̇ k̇ L̇ l̇ Ṁ ṁ Ṅ ṅ Ȯ ȯ Ṗ ṗ Q̇ q̇ Ṙ ṙ Ṡ ṡ Ṫ ṫ U̇ u̇ V̇ v̇ Ẇ ẇ Ẋ ẋ Ẏ ẏ Ż ż ")
+ Pass = cleanacc(Pass,V_lat_code,V_lat_code_2) :(latcode_bg)
+
+TRd ;* dot under the letter \d{u}
+ V_lat_code_2 = grepl(V_lat_code,
++ "A a B b C c D d E e F f G g H h I i J j K k L l M m N n O o P p Q q R r S s T t U u V v W w X x Y y Z z ",
++ "Ạ ạ Ḅ ḅ C̣ c̣ Ḍ ḍ Ẹ ẹ F̣ f̣ G̣ g̣ Ḥ ḥ Ị ị J̣ j̣ Ḳ ḳ Ḷ ḷ Ṃ ṃ Ṇ ṇ Ọ ọ P̣ p̣ Q̣ q̣ Ṛ ṛ Ṣ ṣ Ṭ ṭ Ụ ụ Ṿ ṿ Ẉ ẉ X̣ x̣ Ỵ ỵ Ẓ ẓ ")
+ V_lat_code_2 = repl(V_lat_code_2,"\ḍ","\d")
+ Pass = cleanacc(Pass,V_lat_code,V_lat_code_2) :(latcode_bg)
+
+TRk ;* ogonek \k{a}
+ V_lat_code_2 = grepl(V_lat_code,
++ "A a E e I i O o U u Y y ",
++ "Ą ą Ę ę Į į Ǫ ǫ Ų ų Y̨ y̨ ")
+ Pass = cleanacc(Pass,V_lat_code,V_lat_code_2) :(latcode_bg)
+
+TR~ ;* tilde \~o
+ V_lat_code_2 = grepl(V_lat_code,
++ "A a E e I i N n O o U u V v Y y ",
++ "Ã ã Ẽ ẽ Ĩ ĩ Ñ ñ Õ õ Ũ ũ Ṽ ṽ Ỹ ỹ ")
+ Pass = cleanacc(Pass,V_lat_code,V_lat_code_2) :(latcode_bg)
+
+TR= ;* macron \=a \={a}
+ V_lat_code_2 = grepl(V_lat_code,
++ "A a B b C c D d E e G g I i J j K k M m N n O o P p Q q R r S s T t U u V v W w X x Y y Z z ",
++ "Ā ā B̄ b̄ C̄ c̄ D̄ d̄ Ē ē Ḡ ḡ Ī ī J̄ j̄ K̄ k̄ M̄ m̄ N̄ n̄ Ō ō P̄ p̄ Q̄ q̄ R̄ r̄ S̄ s̄ T̄ t̄ Ū ū V̄ v̄ W̄ w̄ X̄ x̄ Ȳ ȳ Z̄ z̄ ")
+ Pass = cleanacc(Pass,V_lat_code,V_lat_code_2) :(latcode_bg)
+
+TRb ;* bar under the letter \b{a}
+ V_lat_code_2 = grepl(V_lat_code,
++ "A a B b C c D d E e G g H h I i J j K k L l M m N n O o P p R r S s T t U u X x Y y Z z ",
++ "A̱ a̱ Ḇ ḇ C̱ c̱ Ḏ ḏ E̱ e̱ G̱ g̱ H̱ ẖ I̱ i̱ J̱ j̱ Ḵ ḵ Ḻ ḻ M̱ m̱ Ṉ ṉ O̱ o̱ P̱ p̱ Ṟ ṟ S̱ s̱ Ṯ ṯ U̱ u̱ X̱ x̱ Y̱ y̱ Ẕ ẕ ")
+ V_lat_code_2 = repl(V_lat_code_2,"\ḇ","\b")
+ Pass = cleanacc(Pass,V_lat_code,V_lat_code_2) :(latcode_bg)
+
+TRr ;* ring over the letter \r{a}
+ V_lat_code_2 = grepl(V_lat_code,
++ "A a B b C c D d E e F f G g H h I i J j K k L l M m N n O o P p Q q r R S s U u V v W w X x Y y Z z ",
++ "Å å B̊ b̊ C̊ c̊ D̊ d̊ E̊ e̊ F̊ f̊ G̊ g̊ H̊ h̊ I̊ i̊ J̊ j̊ K̊ k̊ L̊ l̊ M̊ m̊ N̊ n̊ O̊ o̊ P̊ p̊ Q̊ q̊ r̊ R̊ S̊ s̊ Ů ů V̊ v̊ W̊ ẘ X̊ x̊ Y̊ ẙ Z̊ z̊ ")
+ V_lat_code_2 = repl(V_lat_code_2,"\r̊","\r")
+ Pass = cleanacc(Pass,V_lat_code,V_lat_code_2) :(latcode_bg)
+
+latcode_nd
+ transacc = Pass :(return)
+transacc_end
+
+#######################################################
+# MAIN
+#######################################################
+ (~(texfile = initialise()) (terminal = "Could not start programme - " ERROR_MSG)) :s(end)
+ Texfile = normacc(Texfile)
+ (((w_f = transacc(texfile)) (Terminal = "Done. File " Outfile " written")),
++ (Terminal = "Conversion failed"))
+end
Property changes on: trunk/Build/source/texk/texlive/linked_scripts/texaccents/texaccents.sno
___________________________________________________________________
Added: svn:executable
## -0,0 +1 ##
+*
\ No newline at end of property
Added: trunk/Master/bin/aarch64-linux/texaccents
===================================================================
--- trunk/Master/bin/aarch64-linux/texaccents (rev 0)
+++ trunk/Master/bin/aarch64-linux/texaccents 2022-09-19 22:37:09 UTC (rev 64447)
@@ -0,0 +1 @@
+link ../../texmf-dist/scripts/texaccents/texaccents.sno
\ No newline at end of file
Property changes on: trunk/Master/bin/aarch64-linux/texaccents
___________________________________________________________________
Added: svn:special
## -0,0 +1 ##
+*
\ No newline at end of property
Added: trunk/Master/bin/amd64-freebsd/texaccents
===================================================================
--- trunk/Master/bin/amd64-freebsd/texaccents (rev 0)
+++ trunk/Master/bin/amd64-freebsd/texaccents 2022-09-19 22:37:09 UTC (rev 64447)
@@ -0,0 +1 @@
+link ../../texmf-dist/scripts/texaccents/texaccents.sno
\ No newline at end of file
Property changes on: trunk/Master/bin/amd64-freebsd/texaccents
___________________________________________________________________
Added: svn:special
## -0,0 +1 ##
+*
\ No newline at end of property
Added: trunk/Master/bin/amd64-netbsd/texaccents
===================================================================
--- trunk/Master/bin/amd64-netbsd/texaccents (rev 0)
+++ trunk/Master/bin/amd64-netbsd/texaccents 2022-09-19 22:37:09 UTC (rev 64447)
@@ -0,0 +1 @@
+link ../../texmf-dist/scripts/texaccents/texaccents.sno
\ No newline at end of file
Property changes on: trunk/Master/bin/amd64-netbsd/texaccents
___________________________________________________________________
Added: svn:special
## -0,0 +1 ##
+*
\ No newline at end of property
Added: trunk/Master/bin/armhf-linux/texaccents
===================================================================
--- trunk/Master/bin/armhf-linux/texaccents (rev 0)
+++ trunk/Master/bin/armhf-linux/texaccents 2022-09-19 22:37:09 UTC (rev 64447)
@@ -0,0 +1 @@
+link ../../texmf-dist/scripts/texaccents/texaccents.sno
\ No newline at end of file
Property changes on: trunk/Master/bin/armhf-linux/texaccents
___________________________________________________________________
Added: svn:special
## -0,0 +1 ##
+*
\ No newline at end of property
Added: trunk/Master/bin/i386-cygwin/texaccents
===================================================================
--- trunk/Master/bin/i386-cygwin/texaccents (rev 0)
+++ trunk/Master/bin/i386-cygwin/texaccents 2022-09-19 22:37:09 UTC (rev 64447)
@@ -0,0 +1 @@
+link ../../texmf-dist/scripts/texaccents/texaccents.sno
\ No newline at end of file
Property changes on: trunk/Master/bin/i386-cygwin/texaccents
___________________________________________________________________
Added: svn:special
## -0,0 +1 ##
+*
\ No newline at end of property
Added: trunk/Master/bin/i386-freebsd/texaccents
===================================================================
--- trunk/Master/bin/i386-freebsd/texaccents (rev 0)
+++ trunk/Master/bin/i386-freebsd/texaccents 2022-09-19 22:37:09 UTC (rev 64447)
@@ -0,0 +1 @@
+link ../../texmf-dist/scripts/texaccents/texaccents.sno
\ No newline at end of file
Property changes on: trunk/Master/bin/i386-freebsd/texaccents
___________________________________________________________________
Added: svn:special
## -0,0 +1 ##
+*
\ No newline at end of property
Added: trunk/Master/bin/i386-linux/texaccents
===================================================================
--- trunk/Master/bin/i386-linux/texaccents (rev 0)
+++ trunk/Master/bin/i386-linux/texaccents 2022-09-19 22:37:09 UTC (rev 64447)
@@ -0,0 +1 @@
+link ../../texmf-dist/scripts/texaccents/texaccents.sno
\ No newline at end of file
Property changes on: trunk/Master/bin/i386-linux/texaccents
___________________________________________________________________
Added: svn:special
## -0,0 +1 ##
+*
\ No newline at end of property
Added: trunk/Master/bin/i386-netbsd/texaccents
===================================================================
--- trunk/Master/bin/i386-netbsd/texaccents (rev 0)
+++ trunk/Master/bin/i386-netbsd/texaccents 2022-09-19 22:37:09 UTC (rev 64447)
@@ -0,0 +1 @@
+link ../../texmf-dist/scripts/texaccents/texaccents.sno
\ No newline at end of file
Property changes on: trunk/Master/bin/i386-netbsd/texaccents
___________________________________________________________________
Added: svn:special
## -0,0 +1 ##
+*
\ No newline at end of property
Added: trunk/Master/bin/i386-solaris/texaccents
===================================================================
--- trunk/Master/bin/i386-solaris/texaccents (rev 0)
+++ trunk/Master/bin/i386-solaris/texaccents 2022-09-19 22:37:09 UTC (rev 64447)
@@ -0,0 +1 @@
+link ../../texmf-dist/scripts/texaccents/texaccents.sno
\ No newline at end of file
Property changes on: trunk/Master/bin/i386-solaris/texaccents
___________________________________________________________________
Added: svn:special
## -0,0 +1 ##
+*
\ No newline at end of property
Added: trunk/Master/bin/universal-darwin/texaccents
===================================================================
--- trunk/Master/bin/universal-darwin/texaccents (rev 0)
+++ trunk/Master/bin/universal-darwin/texaccents 2022-09-19 22:37:09 UTC (rev 64447)
@@ -0,0 +1 @@
+link ../../texmf-dist/scripts/texaccents/texaccents.sno
\ No newline at end of file
Property changes on: trunk/Master/bin/universal-darwin/texaccents
___________________________________________________________________
Added: svn:special
## -0,0 +1 ##
+*
\ No newline at end of property
Added: trunk/Master/bin/win32/texaccents.exe
===================================================================
(Binary files differ)
Index: trunk/Master/bin/win32/texaccents.exe
===================================================================
--- trunk/Master/bin/win32/texaccents.exe 2022-09-19 20:28:42 UTC (rev 64446)
+++ trunk/Master/bin/win32/texaccents.exe 2022-09-19 22:37:09 UTC (rev 64447)
Property changes on: trunk/Master/bin/win32/texaccents.exe
___________________________________________________________________
Added: svn:executable
## -0,0 +1 ##
+*
\ No newline at end of property
Added: svn:mime-type
## -0,0 +1 ##
+application/octet-stream
\ No newline at end of property
Added: trunk/Master/bin/x86_64-cygwin/texaccents
===================================================================
--- trunk/Master/bin/x86_64-cygwin/texaccents (rev 0)
+++ trunk/Master/bin/x86_64-cygwin/texaccents 2022-09-19 22:37:09 UTC (rev 64447)
@@ -0,0 +1 @@
+link ../../texmf-dist/scripts/texaccents/texaccents.sno
\ No newline at end of file
Property changes on: trunk/Master/bin/x86_64-cygwin/texaccents
___________________________________________________________________
Added: svn:special
## -0,0 +1 ##
+*
\ No newline at end of property
Added: trunk/Master/bin/x86_64-darwinlegacy/texaccents
===================================================================
--- trunk/Master/bin/x86_64-darwinlegacy/texaccents (rev 0)
+++ trunk/Master/bin/x86_64-darwinlegacy/texaccents 2022-09-19 22:37:09 UTC (rev 64447)
@@ -0,0 +1 @@
+link ../../texmf-dist/scripts/texaccents/texaccents.sno
\ No newline at end of file
Property changes on: trunk/Master/bin/x86_64-darwinlegacy/texaccents
___________________________________________________________________
Added: svn:special
## -0,0 +1 ##
+*
\ No newline at end of property
Added: trunk/Master/bin/x86_64-linux/texaccents
===================================================================
--- trunk/Master/bin/x86_64-linux/texaccents (rev 0)
+++ trunk/Master/bin/x86_64-linux/texaccents 2022-09-19 22:37:09 UTC (rev 64447)
@@ -0,0 +1 @@
+link ../../texmf-dist/scripts/texaccents/texaccents.sno
\ No newline at end of file
Property changes on: trunk/Master/bin/x86_64-linux/texaccents
___________________________________________________________________
Added: svn:special
## -0,0 +1 ##
+*
\ No newline at end of property
Added: trunk/Master/bin/x86_64-linuxmusl/texaccents
===================================================================
--- trunk/Master/bin/x86_64-linuxmusl/texaccents (rev 0)
+++ trunk/Master/bin/x86_64-linuxmusl/texaccents 2022-09-19 22:37:09 UTC (rev 64447)
@@ -0,0 +1 @@
+link ../../texmf-dist/scripts/texaccents/texaccents.sno
\ No newline at end of file
Property changes on: trunk/Master/bin/x86_64-linuxmusl/texaccents
___________________________________________________________________
Added: svn:special
## -0,0 +1 ##
+*
\ No newline at end of property
Added: trunk/Master/bin/x86_64-solaris/texaccents
===================================================================
--- trunk/Master/bin/x86_64-solaris/texaccents (rev 0)
+++ trunk/Master/bin/x86_64-solaris/texaccents 2022-09-19 22:37:09 UTC (rev 64447)
@@ -0,0 +1 @@
+link ../../texmf-dist/scripts/texaccents/texaccents.sno
\ No newline at end of file
Property changes on: trunk/Master/bin/x86_64-solaris/texaccents
___________________________________________________________________
Added: svn:special
## -0,0 +1 ##
+*
\ No newline at end of property
Added: trunk/Master/texmf-dist/doc/man/man1/texaccents.1
===================================================================
--- trunk/Master/texmf-dist/doc/man/man1/texaccents.1 (rev 0)
+++ trunk/Master/texmf-dist/doc/man/man1/texaccents.1 2022-09-19 22:37:09 UTC (rev 64447)
@@ -0,0 +1,15 @@
+.\" Manpage for texaccents
+.\" Contact guido.milanese at unicatt.it to correct errors or typos.
+.TH man 8 "17th September 2022" "1.0.1" "texaccents man page"
+.SH NAME
+texaccents - Converts legacy (La)TeX accents and ligatures to Unicode
+.SH DESCRIPTION
+A Snobol script. Example: \={a} ('a' with macron) will be converted to ā.
+.SH OPTIONS
+No options besides --help and --version.
+.SH AUTHOR
+Guido Milanese (guido.milanese at unicatt.it)
+.SH BUGS
+Please send bug reports or other correspondence to guido.milanese at unicatt.it
+.SH SEE ALSO
+CTAN page of the package: https://www.ctan.org/pkg/texaccents
Property changes on: trunk/Master/texmf-dist/doc/man/man1/texaccents.1
___________________________________________________________________
Added: svn:eol-style
## -0,0 +1 ##
+native
\ No newline at end of property
Added: trunk/Master/texmf-dist/doc/man/man1/texaccents.man1.pdf
===================================================================
(Binary files differ)
Index: trunk/Master/texmf-dist/doc/man/man1/texaccents.man1.pdf
===================================================================
--- trunk/Master/texmf-dist/doc/man/man1/texaccents.man1.pdf 2022-09-19 20:28:42 UTC (rev 64446)
+++ trunk/Master/texmf-dist/doc/man/man1/texaccents.man1.pdf 2022-09-19 22:37:09 UTC (rev 64447)
Property changes on: trunk/Master/texmf-dist/doc/man/man1/texaccents.man1.pdf
___________________________________________________________________
Added: svn:mime-type
## -0,0 +1 ##
+application/pdf
\ No newline at end of property
Added: trunk/Master/texmf-dist/doc/support/texaccents/LICENSE
===================================================================
--- trunk/Master/texmf-dist/doc/support/texaccents/LICENSE (rev 0)
+++ trunk/Master/texmf-dist/doc/support/texaccents/LICENSE 2022-09-19 22:37:09 UTC (rev 64447)
@@ -0,0 +1,9 @@
+MIT License
+
+Copyright (c) 2022 Guido Milanese
+
+Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the "Software"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice (including the next paragraph) shall be included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
Added: trunk/Master/texmf-dist/doc/support/texaccents/README.md
===================================================================
--- trunk/Master/texmf-dist/doc/support/texaccents/README.md (rev 0)
+++ trunk/Master/texmf-dist/doc/support/texaccents/README.md 2022-09-19 22:37:09 UTC (rev 64447)
@@ -0,0 +1,9 @@
+# TeXaccents
+
+A standalone utility designed to convert legacy (La)TeX (text mode, no math) and BibTeX codes for "accented" characters to Unicode equivalents. For example, `\={a}` ('a' with macron) will be converted to `ā`.
+
+Current version: 2022/09/18 version 1.0.1
+Windows version: 2022/09/18 version 1.0.1
+
+This project is licensed under the MIT License: see https://opensource.org/licenses/MIT
+
Property changes on: trunk/Master/texmf-dist/doc/support/texaccents/README.md
___________________________________________________________________
Added: svn:eol-style
## -0,0 +1 ##
+native
\ No newline at end of property
Added: trunk/Master/texmf-dist/doc/support/texaccents/testaccents-in
===================================================================
--- trunk/Master/texmf-dist/doc/support/texaccents/testaccents-in (rev 0)
+++ trunk/Master/texmf-dist/doc/support/texaccents/testaccents-in 2022-09-19 22:37:09 UTC (rev 64447)
@@ -0,0 +1,28 @@
+\"{a}
+\'{a}
+\H{a}
+\`{a}
+\^{a}
+\v{a}
+\u{a}
+\c{c}
+\.{a}
+\d{a}
+\k{a}
+\~{a}
+\={a}
+\b{a}
+\r{a}
+\ae{}
+\oe{}
+\AE{}
+\OE{}
+\dh{}
+\DH{}
+\th{}
+\TH{}
+\o{}
+\O{}
+\l{}
+\L{}
+
Added: trunk/Master/texmf-dist/doc/support/texaccents/texaccents.md
===================================================================
--- trunk/Master/texmf-dist/doc/support/texaccents/texaccents.md (rev 0)
+++ trunk/Master/texmf-dist/doc/support/texaccents/texaccents.md 2022-09-19 22:37:09 UTC (rev 64447)
@@ -0,0 +1,139 @@
+---
+abstract: |
+ TeXaccents is a standalone utility designed to convert legacy (La)TeX ligatures and codes for "accented" characters to Unicode equivalents (text mode, no math) . For example, `\={a}` ('a' with macron) will be converted to `ā`.
+author:
+- "Guido Milanese[^1]"
+date: 17^th^ September 2022
+lang: en
+title: |
+ TeXaccents\
+ version 1.0.1
+fontfamily: libertine
+fontsize: 12pt
+---
+
+# General information
+
+Even if modern compilers handle Unicode encoding, (La) and files
+featuring "legacy" encoding for non-Ascii characters are still very
+common, and users may need to incorporate old code into new texts that
+make use of modern text encoding.
+
+Several utilities are available online that claim to be able to convert
+legacy (La) encoding to standard Unicode. See:
+
+- *Simple LaTeX to Text Converter*. A complex programme, able to deal
+ with maths. Insofar as non-Ascii chars are concerned, it fails
+ sometimes, at least according to my tests. See
+ <https://pylatexenc.readthedocs.io/en/latest/latexwalker/>. Written
+ in Python.
+
+- *LaTeX handler*. Converts non-Ascii (La) encoding to Unicode.
+ However, it does not seem to be able to deal with the legacy
+ encoding, e.g. `{\a}` instead of `\{a}` or `\a`. It does not convert
+ simple ligatures as `\ae{}` `\oe{}`. I used the tables provided by
+ this programme as a starting point. Written in Python. See
+ <https://github.com/hayk314/LaTex-handler>.
+
+- *Pandoc* is the standard programme for any text format conversion
+ (<https://pandoc.org/>). It converts almost all the accents (thorn
+ and eth missing?), but (if I have checked this correctly) normalises
+ files stripping non-standard fields. This can be a problem for
+ scholars who frequently use non-standard fields, such as e.g.
+ "shorttitle", required by not a few bibliographic styles.
+
+*TeXaccents* should be able to transform (La) normal text or "accents"
+(not "math" accents) to their Unicode equivalent. The programme deals
+with the following codes (*not all the fonts are able to output all the
+required Unicode glyphs of this table!*):
+
+ | NAME | \tex | Unicode |
+ |--------------- |------- |---------|
+ | Umlaut | \"{a} | ä |
+ | acute | \'{a} | á |
+ | double acute | \H{a} | a̋ |
+ | grave | \`{a} | à |
+ | circumflex | \^{a} | â |
+ | caron hraceck | \v{a} | ǎ |
+ | breve | \u{a} | ă |
+ | cedilla | \c{c} | ç |
+ | dot | \.{a} | ȧ |
+ | dot under | \d{a} | ạ |
+ | ogonek | \k{a} | ą |
+ | tilde | \~{a} | ã |
+ | macron | \={a} | ā |
+ | bar under | \b{a} | a̱ |
+ | ring over | \r{a} | å |
+
+The programme should recognize the following varieties:
+
+::: {.center}
+`\'a` -- `\'{a}` -- `{\'a}` -- `{{\'a}}`
+:::
+
+It transforms also the encoding for : `æ œ Æ Œ ð Ð þ Þ ø Ø ł Ł`.
+Checking the page
+<https://www.utf8-chartable.de/unicode-utf8-table.pl?number=512> I could
+not find a legacy text mode encoding for:
+**ƀ Ƀ đ Đ ǥ Ǥ ħ Ħ ɨ Ɨ ŧ Ŧ ƶ Ƶ** (some chars are accessible in math
+mode).
+
+# Setup
+
+## From source
+The programme is written in Snobol
+(<https://en.wikipedia.org/wiki/SNOBOL> or
+<https://it.wikipedia.org/wiki/SNOBOL>) and should run on any platform.
+Steps:
+
+1. Install Snobol4 (version 2.3, March 2022) from
+ <http://www.regressive.org/snobol4/csnobol4/curr/>. Make sure to
+ install the compiler in a folder listed in your `PATH` or add the
+ folder to your path. On Linux the folder `snobol4` is installed
+ under `/usr/local/bin/`, which is normally listed in the PATH of a
+ standard Linux system.
+
+2. Test the compiler running `snobol4` from the command line. Leave the
+ compiler with `Ctr-C` or writing `end`.
+
+3. Copy `texaccents.sno` and all the provided `*.inc` files
+
+> `compiler.inc` `delete.inc` `grepl.inc` `newline.inc` `systype.inc`
+
+to a folder of your choice (e.g. `/home/<user>/bin`).
+
+4. In this folder, run
+ `snobol4 texaccents.sno testaccents-in testaccents-out` to test the
+ programme. The test file contains all the accents listed above. See
+ the result typing `cat testaccents-out` (Unixes / Powershell) or
+ `type testaccents-out` (Windows/Dos prompt), or open the file with
+ your text editor. The output file name is just a suggestion, of
+ course.
+
+## Windows standalone version
+If preferred, a Windows EXE standalone file is provided. It was compiled using
+Spitbol (see <https://github.com/spitbol/windows-nt>); the source code has been slightly adapted to Spitbol (basically only input/output syntax). From any directory, run `texaccents.exe INPUT OUTPUT`. To test the programme, run `texaccents.exe testaccents-in testaccents-out`. As above, the output file name is just a suggestion.
+
+# History
+
+- 25^th^ July 2022. First version (after trying unsuccesfully to
+ convert an old file with existing utilities)
+- 17^th^ August 2022. First complete version (0.9).
+- 27^rd^ August 2022. This version (1.0) with documentation and
+ comments.
+- 17^th^ September 2022. Windows standalone executable. Manual page written.
+ Version message added; help message improved. In the source, a regular
+ shebang according to the recommendation of CTAN
+ (<https://tug.org/texlive/pkgcontrib.html>) was added. Documentation updated
+ accordingly.
+
+# Contacts / todo
+
+Bugs / suggestions / improvements: please write to
+[guido.milanese\@unicatt.it](guido.milanese at unicatt.it) using
+*TeXaccents* as subject of the mail.
+
+Genoa, Italy, 17^th^ September 2022
+
+[^1]: Università Cattolica d.S.C., Dipartimento di scienze storiche e
+ filologiche, via Trieste 17, I-25121 Brescia
Property changes on: trunk/Master/texmf-dist/doc/support/texaccents/texaccents.md
___________________________________________________________________
Added: svn:eol-style
## -0,0 +1 ##
+native
\ No newline at end of property
Added: trunk/Master/texmf-dist/doc/support/texaccents/texaccents.pdf
===================================================================
(Binary files differ)
Index: trunk/Master/texmf-dist/doc/support/texaccents/texaccents.pdf
===================================================================
--- trunk/Master/texmf-dist/doc/support/texaccents/texaccents.pdf 2022-09-19 20:28:42 UTC (rev 64446)
+++ trunk/Master/texmf-dist/doc/support/texaccents/texaccents.pdf 2022-09-19 22:37:09 UTC (rev 64447)
Property changes on: trunk/Master/texmf-dist/doc/support/texaccents/texaccents.pdf
___________________________________________________________________
Added: svn:mime-type
## -0,0 +1 ##
+application/pdf
\ No newline at end of property
Added: trunk/Master/texmf-dist/doc/support/texaccents/texaccents.spt
===================================================================
--- trunk/Master/texmf-dist/doc/support/texaccents/texaccents.spt (rev 0)
+++ trunk/Master/texmf-dist/doc/support/texaccents/texaccents.spt 2022-09-19 22:37:09 UTC (rev 64447)
@@ -0,0 +1,278 @@
+* WARNING - SPITBOL REQUIRES CR+LF LINE ENDINGS
+* THE CTAN TEAM WAS INFORMED ABOUT THIS SPECIAL NEED
+*
+* texaccents.spt
+* version 1.0.1
+* 2022.09.17
+* Windows version of texaccents.sno
+* guido.milanese at unicatt.it
+* Transforms LaTeX accents to their UTF8 equivalents
+* accepts both LaTeX and Bibtex codes:
+* examples: \'a \'{a} {\"a} and even {\'{a}}
+* tables of accents imported from:
+* https://github.com/hayk314/LaTex-handler -- Author: Hayk Aleksanyan
+* with my integrations, including ligatures as \ae{}
+* requires spitbol: https://github.com/spitbol/windows-nt
+
+*****************************************************************
+* MIT License - Copyright (c) 2022 Guido Milanese
+* See file LICENSE in this package
+*****************************************************************
+
+******************************************************
+* FUNCTIONS
+******************************************************
+
+*-- Function INITIALISE
+*-- opens files, imports functions
+ define("initialise()")
+ :(initialise_end)
+initialise
+initialise_bg
+* INCLUDE FILES
+
+-include "args.inc"
+-include "delete.inc"
+-include "host.inc"
+-include "grepl.inc" ;* essential! calls repl internally
+ MAX = 4000000 ;* max size of input/output files = 4 megs
+ NL = char(13) char(10)
+
+ HELP_MSG = "texaccents 1.0.1" NL
++ "Converts legacy (La)TeX accents and ligatures to Unicode" NL
++ "Usage: texaccents.sno INFILE OUTFILE" NL
++ "--help print this help, then exit" NL
++ "--version print version number, then exit" NL
++ "Report bugs to <guido.milanese at unicatt.it>" NL
++ "CTAN page of the package: <https://www.ctan.org/pkg/texaccents>"
+
+ VERS_MSG = "texaccents 1.0.1" NL NL
++ "Copyright (c) 2022 Guido Milanese" NL NL
++ "This is free software; see the source for copying conditions. There is NO" NL
++ "warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE." NL nl
++ "Written by Guido Milanese <guido.milanese at unicatt.it>"
+
+*******************************************************
+* opens input / output files
+*******************************************************
+* Defines and checks Input & Output
+* help request -- exits. Both "--help" and "-help" are valid
+ ((argv[1] ? "-help") (Terminal = HELP_MSG)) :s(end)
+* version request -- exits. Both "--version" and "-version" are valid
+ ((argv[1] ? "-version") (Terminal = VERS_MSG)) :s(end)
+* Normal input-output with error messages.
+* Error messages are used by MAIN if necessary
+ (~(infile = argv[1]) ((Terminal = HELP_MSG) (ERROR_MSG = "Input error"))) :s(freturn)
+ (~(outfile = argv[2]) ((Terminal = HELP_MSG) (ERROR_MSG = "Output error"))) :s(freturn)
+ INPUT('r_f',1, infile '[-R' MAX ']') :f(freturn)
+ Terminal = "Reading text from " Infile
+ OUTPUT('w_f',2,Outfile '[-r' MAX ']') :f(freturn)
+initialise_rt initialise = r_f :(return)
+initialise_end
+
+*************************************************************************************
+*-- Function NORMACC
+*-- Changes TeX accents without curly brackets to the standard form
+*-- \'a --> \'{a}
+*-- and replaces ligatures such as \ae --> æ | \oe --> œ
+*-- requires GREPL
+*************************************************************************************
+ define("normacc(Pass)")
+ P_shortacc = notany('{')
++ ((('\' any("'`" '"' "^=~.")) . Pre_shortacc)
++ (any(&ucase &lcase) . Letter_shortacc)) . V_shortacc
+ :(normacc_end)
+normacc
+normacc_bg Pass ? P_shortacc :f(normacc_lg)
+ Pass ? V_shortacc = Pre_shortacc '{' Letter_shortacc '}' :(normacc_bg)
+normacc_lg Pass2 = grepl(Pass,
++ "\ae{} \oe{} \AE{} \OE{} \dh{} \DH{} \th{} \TH{} \o{} \O{} \l{} \L{} ",
++ "æ œ Æ Œ ð Ð þ Þ ø Ø ł Ł ")
+ Terminal = "Ligatures tranformed"
+normacc_rt normacc = Pass2 :(return)
+normacc_end
+*
+* The pattern to normalise accents -- as \'a -- is defined as follows:
+* 1. there must be no '{' before backslash: otherwise the pattern would trap also
+* BibTex codes such as {\'a}
+* 2. find a backslash followed by any char of the list. Saved as "Pre_sortacc"
+* 3. find the accented letter. Saved as Letter_shortacc
+* 4. The whole structure is saved as V_shortacc
+* The programme will save the whole structure and substitute it in the text with:
+* Pre_shortacc (as \') + '{' + Letter_shortacc + '}'
+* in this way the short form -- \'a -- is transformed to the canonical \'{a}
+*
+* Ligatures and special chars are simply replaced with GREPL.
+
+*************************************************************************************
+*-- Function CLEANACC
+*-- Substitutes plain letters to Unicode accents, using the sets provides by TRANSACC
+*-- \'{a} will output á
+*************************************************************************************
+ define("cleanacc(Text,Acc1,Acc2)") :(cleanacc_end)
+* Acc1 is the original LaTeX code e.g. \"{a}
+* Acc2, at the time of calling the function, is e.g. \"{ä}
+cleanacc
+cleanacc_bg
+* removes paretheses: \"{ä} --> \"ä
+ Acc2 = delete(Acc2,"{}")
+* moves 2 chars and saves what remains, i.e. the letter
+* \"ä --> ä
+ Acc2 ? len(2) (rem . Acc2)
+* in text replaces e.g. \"{a} with ä
+* the substitution is done ONCE for the whole text
+ Text = repl(Text,Acc1,Acc2)
+ Terminal = "Working on " Acc1
+cleanacc_rt cleanacc = Text :(return)
+cleanacc_end
+
+*******************************************************
+*-- Function TRANSACC
+*-- transforms LaTeX/Bibtex accents to Unicode
+*******************************************************
+ define("transacc(Pass)")
+* Pass is the input text
+*
+* Accents used by Latex, e.g. \'{a} = acute accent over 'a'
+ Lat_acc =
++ any('"' "'" "`" 'H' '^' 'v' 'u' 'c' '.' 'd' 'k' '~' '=' 'b' 'r' )
++ . V_lat_acc
+*
+* The pattern says:
+* '\' + Lat_acc OR ('{\' + Lat_acc + '{' OR nothing)
+* any letter, saved as C_noacc + '}' + '}' OR nothing
+* Lat_acc is already defined above and saved ad V_lat_acc
+* Examples \'{a} -- {\'a} -- {\'{a}} (\'a was already "normalised")
+ P_lat_code =
++ (
++ (('\' Lat_acc '{') | ('{\' Lat_acc ('{' | '') ))
++ (any(&lcase &ucase) . C_noacc) '}' ('}' | '') ) . V_lat_code
+ :(transacc_end)
+transacc
+transacc_bg
+latcode_bg V_lat_code = ;* cleans previous value
+ V_lat_code_2 = ;* cleans previous value
+* Scans input text to locate the pattern
+* if no other LaTeX accents, fails and returns to main
+* if yes, goes to the section that transforms this accent.
+* e.g. if the accent is umlaut, will jump to TR"
+* After each transformation we have:
+* 1. the original code, e.g. \"{a} or \"a or {\"a}
+* 2. the transformed code, e.g. \"{ä} or \"ä or {\"ä}
+* Each section calls CLEANCLODE
+* CLEANCODE will remove all the {}\ and the LaTeX accent
+* and substitute in the input text e.g. \"{ä} with ä
+ Pass ? P_lat_code :f(latcode_nd)
+ :($('TR' V_lat_acc))
+
+TR" ;* umlaut
+ V_lat_code_2 = grepl(V_lat_code,
++ "A a B b C c E e H h I i K k M m N n O o P p Q q S s T t U u V v W w X x Y y Z z ",
++ "Ä ä B̈ b̈ C̈ c̈ Ë ë Ḧ ḧ Ï ï K̈ k̈ M̈ m̈ N̈ n̈ Ö ö P̈ p̈ Q̈ q̈ S̈ s̈ T̈ ẗ Ü ü V̈ v̈ Ẅ ẅ Ẍ ẍ Ÿ ÿ Z̈ z̈ ")
+ Pass = cleanacc(Pass,V_lat_code,V_lat_code_2) :(latcode_bg)
+
+TR' ;* acute
+ V_lat_code_2 = grepl(V_lat_code,
++ "A a B b C c D d E e F f G g H h I i J j K k L l M m N n O o P p Q q R r S s T t U u V v W w X x Y y Z z ",
++ "Á á B́ b́ Ć ć D́ d́ É é F́ f́ Ǵ ǵ H́ h́ Í í J́ ȷ́ Ḱ ḱ Ĺ ĺ Ḿ ḿ Ń ń Ó ó Ṕ ṕ Q́ q́ Ŕ ŕ Ś ś T́ t́ Ú ú V́ v́ Ẃ ẃ X́ x́ Ý ý Ź ź ")
+ Pass = cleanacc(Pass,V_lat_code,V_lat_code_2) :(latcode_bg)
+
+TRH ;* double acute - \H{o} Hungarian
+ V_lat_code_2 = grepl(V_lat_code,
++ "A a E e I i M m O o U u ",
++ "A̋ a̋ E̋ e̋ I̋ i̋ M̋ m̋ Ő ő Ű ű ")
+ Pass = cleanacc(Pass,V_lat_code,V_lat_code_2) :(latcode_bg)
+
+TR` ;* grave
+ V_lat_code_2 = grepl(V_lat_code,
++ "A a Æ æ E e H h I i K k M m N n O o R r S s T t U u V v W w X x Y y Z z ",
++ "À à Æ̀ æ̀ È è H̀ h̀ Ì ì K̀ k̀ M̀ m̀ Ǹ ǹ Ò ò R̀ r̀ S̀ s̀ T̀ t̀ Ù ù V̀ v̀ Ẁ ẁ X̀ x̀ Ỳ ỳ Z̀ z̀ ")
+ Pass = cleanacc(Pass,V_lat_code,V_lat_code_2) :(latcode_bg)
+
+TR^ ;* circumflex \^{o}
+ V_lat_code_2 = grepl(V_lat_code,
++ "A a B b C c D d E e G g H h I i J j K k L l M m N n O o R r S s T t U u V v W w X x Y y Z z ",
++ "Â â B̂ b̂ Ĉ ĉ D̂ d̂ Ê ê Ĝ ĝ Ĥ ĥ Î î Ĵ ĵ K̂ k̂ L̂ l̂ M̂ m̂ N̂ n̂ Ô ô R̂ r̂ Ŝ ŝ T̂ t̂ Û û V̂ v̂ Ŵ ŵ X̂ x̂ Ŷ ŷ Ẑ ẑ ")
+ Pass = cleanacc(Pass,V_lat_code,V_lat_code_2) :(latcode_bg)
+
+TRv ;* caron hraceck \v{s}
+* For accents that are also normal letters
+* we need to restore the accent to its original value
+* This applies to: v u c d k b r
+ V_lat_code_2 = grepl(V_lat_code,
++ "A a B b C c D d E e F f G g H h I i J j K k L l M m N n O o P p Q q R r S s T t U u V v W w X x Y y Z z ",
++ "Ǎ ǎ B̌ b̌ Č č Ď ď Ě ě F̌ f̌ Ǧ ǧ Ȟ ȟ Ǐ ǐ J̌ ǰ Ǩ ǩ Ľ ľ M̌ m̌ Ň ň Ǒ ǒ P̌ p̌ Q̌ q̌ Ř ř Š š Ť ť Ǔ ǔ V̌ v̌ W̌ w̌ X̌ x̌ Y̌ y̌ Ž ž ")
+ V_lat_code_2 = repl(V_lat_code_2,"\v̌","\v")
+ Pass = cleanacc(Pass,V_lat_code,V_lat_code_2) :(latcode_bg)
+
+TRu ;* breve \u{o}
+ V_lat_code_2 = grepl(V_lat_code,
++ "A a C c E e G g I i K k M m N n O o P p R r T t U u V v X x Y y ",
++ "Ă ă C̆ c̆ Ĕ ĕ Ğ ğ Ĭ ĭ K̆ k̆ M̆ m̆ N̆ n̆ Ŏ ŏ P̆ p̆ R̆ r̆ T̆ t̆ Ŭ ŭ V̆ v̆ X̆ x̆ Y̆ y̆ ")
+ V_lat_code_2 = repl(V_lat_code_2,"\ŭ","\u")
+ Pass = cleanacc(Pass,V_lat_code,V_lat_code_2) :(latcode_bg)
+
+TRc ;* cedilla \c{c}
+ V_lat_code_2 = grepl(V_lat_code,
++ "A a B b C c D d E e G g H h I i K k L l M m N n O o Q q R r S s T t U u X x Z z ",
++ "A̧ a̧ B̧ b̧ Ç ç Ḑ ḑ Ȩ ȩ Ģ ģ Ḩ ḩ I̧ i̧ Ķ ķ Ļ ļ M̧ m̧ Ņ ņ O̧ o̧ Q̧ q̧ Ŗ ŗ Ş ş Ţ ţ U̧ u̧ X̧ x̧ Z̧ z̧ ")
+ V_lat_code_2 = repl(V_lat_code_2,"\ç","\c")
+ Pass = cleanacc(Pass,V_lat_code,V_lat_code_2) :(latcode_bg)
+
+TR. ;* dot \.{o}
+ V_lat_code_2 = grepl(V_lat_code,
++ "A a B b C c D d E e F f G g H h I i K k L l M m N n O o P p Q q R r S s T t U u V v W w X x Y y Z z ",
++ "Ȧ ȧ Ḃ ḃ Ċ ċ Ḋ ḋ Ė ė Ḟ ḟ Ġ ġ Ḣ ḣ İ i̇̀ K̇ k̇ L̇ l̇ Ṁ ṁ Ṅ ṅ Ȯ ȯ Ṗ ṗ Q̇ q̇ Ṙ ṙ Ṡ ṡ Ṫ ṫ U̇ u̇ V̇ v̇ Ẇ ẇ Ẋ ẋ Ẏ ẏ Ż ż ")
+ Pass = cleanacc(Pass,V_lat_code,V_lat_code_2) :(latcode_bg)
+
+TRd ;* dot under the letter \d{u}
+ V_lat_code_2 = grepl(V_lat_code,
++ "A a B b C c D d E e F f G g H h I i J j K k L l M m N n O o P p Q q R r S s T t U u V v W w X x Y y Z z ",
++ "Ạ ạ Ḅ ḅ C̣ c̣ Ḍ ḍ Ẹ ẹ F̣ f̣ G̣ g̣ Ḥ ḥ Ị ị J̣ j̣ Ḳ ḳ Ḷ ḷ Ṃ ṃ Ṇ ṇ Ọ ọ P̣ p̣ Q̣ q̣ Ṛ ṛ Ṣ ṣ Ṭ ṭ Ụ ụ Ṿ ṿ Ẉ ẉ X̣ x̣ Ỵ ỵ Ẓ ẓ ")
+ V_lat_code_2 = repl(V_lat_code_2,"\ḍ","\d")
+ Pass = cleanacc(Pass,V_lat_code,V_lat_code_2) :(latcode_bg)
+
+TRk ;* ogonek \k{a}
+ V_lat_code_2 = grepl(V_lat_code,
++ "A a E e I i O o U u Y y ",
++ "Ą ą Ę ę Į į Ǫ ǫ Ų ų Y̨ y̨ ")
+ Pass = cleanacc(Pass,V_lat_code,V_lat_code_2) :(latcode_bg)
+
+TR~ ;* tilde \~o
+ V_lat_code_2 = grepl(V_lat_code,
++ "A a E e I i N n O o U u V v Y y ",
++ "Ã ã Ẽ ẽ Ĩ ĩ Ñ ñ Õ õ Ũ ũ Ṽ ṽ Ỹ ỹ ")
+ Pass = cleanacc(Pass,V_lat_code,V_lat_code_2) :(latcode_bg)
+
+TR= ;* macron \=a \={a}
+ V_lat_code_2 = grepl(V_lat_code,
++ "A a B b C c D d E e G g I i J j K k M m N n O o P p Q q R r S s T t U u V v W w X x Y y Z z ",
++ "Ā ā B̄ b̄ C̄ c̄ D̄ d̄ Ē ē Ḡ ḡ Ī ī J̄ j̄ K̄ k̄ M̄ m̄ N̄ n̄ Ō ō P̄ p̄ Q̄ q̄ R̄ r̄ S̄ s̄ T̄ t̄ Ū ū V̄ v̄ W̄ w̄ X̄ x̄ Ȳ ȳ Z̄ z̄ ")
+ Pass = cleanacc(Pass,V_lat_code,V_lat_code_2) :(latcode_bg)
+
+TRb ;* bar under the letter \b{a}
+ V_lat_code_2 = grepl(V_lat_code,
++ "A a B b C c D d E e G g H h I i J j K k L l M m N n O o P p R r S s T t U u X x Y y Z z ",
++ "A̱ a̱ Ḇ ḇ C̱ c̱ Ḏ ḏ E̱ e̱ G̱ g̱ H̱ ẖ I̱ i̱ J̱ j̱ Ḵ ḵ Ḻ ḻ M̱ m̱ Ṉ ṉ O̱ o̱ P̱ p̱ Ṟ ṟ S̱ s̱ Ṯ ṯ U̱ u̱ X̱ x̱ Y̱ y̱ Ẕ ẕ ")
+ V_lat_code_2 = repl(V_lat_code_2,"\ḇ","\b")
+ Pass = cleanacc(Pass,V_lat_code,V_lat_code_2) :(latcode_bg)
+
+TRr ;* ring over the letter \r{a}
+ V_lat_code_2 = grepl(V_lat_code,
++ "A a B b C c D d E e F f G g H h I i J j K k L l M m N n O o P p Q q r R S s U u V v W w X x Y y Z z ",
++ "Å å B̊ b̊ C̊ c̊ D̊ d̊ E̊ e̊ F̊ f̊ G̊ g̊ H̊ h̊ I̊ i̊ J̊ j̊ K̊ k̊ L̊ l̊ M̊ m̊ N̊ n̊ O̊ o̊ P̊ p̊ Q̊ q̊ r̊ R̊ S̊ s̊ Ů ů V̊ v̊ W̊ ẘ X̊ x̊ Y̊ ẙ Z̊ z̊ ")
+ V_lat_code_2 = repl(V_lat_code_2,"\r̊","\r")
+ Pass = cleanacc(Pass,V_lat_code,V_lat_code_2) :(latcode_bg)
+
+latcode_nd
+ transacc = Pass :(return)
+transacc_end
+
+*******************************************************
+* MAIN
+*******************************************************
+ (~(texfile = initialise()) (terminal = "Could not start programme - " ERROR_MSG)) :s(end)
+ Texfile = normacc(Texfile)
+ (((w_f = transacc(texfile)) (Terminal = "Done. File " Outfile " written")),
++ (Terminal = "Conversion failed"))
+END
Added: trunk/Master/texmf-dist/doc/support/texaccents/texaccents.tex
===================================================================
--- trunk/Master/texmf-dist/doc/support/texaccents/texaccents.tex (rev 0)
+++ trunk/Master/texmf-dist/doc/support/texaccents/texaccents.tex 2022-09-19 22:37:09 UTC (rev 64447)
@@ -0,0 +1,258 @@
+% TEXACCENTS.TEX
+% Documentation for texaccents.sno / texaccents.spt
+% version 1.0.1 -- 17th september 2022
+% author: guido.milanese at unicatt.it
+% tex file produced from markdown source
+% using `pandoc texaccents.md -s -o texaccents.tex`
+% and compiled with lualatex
+% Line 35 was added: \microtypesetup{nopatch=item}
+% See: https://github.com/schlcht/microtype/issues/4
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+%
+% Options for packages loaded elsewhere
+\PassOptionsToPackage{unicode}{hyperref}
+\PassOptionsToPackage{hyphens}{url}
+%
+\documentclass[
+ 12pt,
+ english,
+]{article}
+\usepackage{amsmath,amssymb}
+\usepackage[]{libertine}
+\usepackage{iftex}
+\ifPDFTeX
+ \usepackage[T1]{fontenc}
+ \usepackage[utf8]{inputenc}
+ \usepackage{textcomp} % provide euro and other symbols
+\else % if luatex or xetex
+ \usepackage{unicode-math}
+ \defaultfontfeatures{Scale=MatchLowercase}
+ \defaultfontfeatures[\rmfamily]{Ligatures=TeX,Scale=1}
+\fi
+% Use upquote if available, for straight quotes in verbatim environments
+\IfFileExists{upquote.sty}{\usepackage{upquote}}{}
+\IfFileExists{microtype.sty}{% use microtype if available
+ \usepackage[]{microtype}
+ \UseMicrotypeSet[protrusion]{basicmath} % disable protrusion for tt fonts
+ \microtypesetup{nopatch=item}
+}{}
+\makeatletter
+\@ifundefined{KOMAClassName}{% if non-KOMA class
+ \IfFileExists{parskip.sty}{%
+ \usepackage{parskip}
+ }{% else
+ \setlength{\parindent}{0pt}
+ \setlength{\parskip}{6pt plus 2pt minus 1pt}}
+}{% if KOMA class
+ \KOMAoptions{parskip=half}}
+\makeatother
+\usepackage{xcolor}
+\IfFileExists{xurl.sty}{\usepackage{xurl}}{} % add URL line breaks if available
+\IfFileExists{bookmark.sty}{\usepackage{bookmark}}{\usepackage{hyperref}}
+\hypersetup{
+ pdftitle={TeXaccents version 1.0.1},
+ pdfauthor={Guido Milanese},
+ pdflang={en},
+ hidelinks,
+ pdfcreator={LaTeX via pandoc}}
+\urlstyle{same} % disable monospaced font for URLs
+\setlength{\emergencystretch}{3em} % prevent overfull lines
+\providecommand{\tightlist}{%
+ \setlength{\itemsep}{0pt}\setlength{\parskip}{0pt}}
+\setcounter{secnumdepth}{-\maxdimen} % remove section numbering
+\ifXeTeX
+ % Load polyglossia as late as possible: uses bidi with RTL langages (e.g. Hebrew, Arabic)
+ \usepackage{polyglossia}
+ \setmainlanguage[]{english}
+\else
+ \usepackage[main=english]{babel}
+% get rid of language-specific shorthands (see #6817):
+\let\LanguageShortHands\languageshorthands
+\def\languageshorthands#1{}
+\fi
+\ifLuaTeX
+ \usepackage{selnolig} % disable illegal ligatures
+\fi
+
+\title{TeXaccents\\
+version 1.0.1}
+\author{Guido Milanese\footnote{Università Cattolica d.S.C.,
+ Dipartimento di scienze storiche e filologiche, via Trieste 17,
+ I-25121 Brescia}}
+\date{17\textsuperscript{th} September 2022}
+
+\begin{document}
+\maketitle
+\begin{abstract}
+TeXaccents is a standalone utility designed to convert legacy (La)TeX
+ligatures and codes for ``accented'' characters to Unicode equivalents
+(text mode, no math) . For example, \texttt{\textbackslash{}=\{a\}} (`a'
+with macron) will be converted to \texttt{ā}.
+\end{abstract}
+
+\hypertarget{general-information}{%
+\section{General information}\label{general-information}}
+
+Even if modern compilers handle Unicode encoding, (La) and files
+featuring ``legacy'' encoding for non-Ascii characters are still very
+common, and users may need to incorporate old code into new texts that
+make use of modern text encoding.
+
+Several utilities are available online that claim to be able to convert
+legacy (La) encoding to standard Unicode. See:
+
+\begin{itemize}
+\item
+ \emph{Simple LaTeX to Text Converter}. A complex programme, able to
+ deal with maths. Insofar as non-Ascii chars are concerned, it fails
+ sometimes, at least according to my tests. See
+ \url{https://pylatexenc.readthedocs.io/en/latest/latexwalker/}.
+ Written in Python.
+\item
+ \emph{LaTeX handler}. Converts non-Ascii (La) encoding to Unicode.
+ However, it does not seem to be able to deal with the legacy encoding,
+ e.g.~\texttt{\{\textbackslash{}a\}} instead of
+ \texttt{\textbackslash{}\{a\}} or \texttt{\textbackslash{}a}. It does
+ not convert simple ligatures as \texttt{\textbackslash{}ae\{\}}
+ \texttt{\textbackslash{}oe\{\}}. I used the tables provided by this
+ programme as a starting point. Written in Python. See
+ \url{https://github.com/hayk314/LaTex-handler}.
+\item
+ \emph{Pandoc} is the standard programme for any text format conversion
+ (\url{https://pandoc.org/}). It converts almost all the accents (thorn
+ and eth missing?), but (if I have checked this correctly) normalises
+ files stripping non-standard fields. This can be a problem for
+ scholars who frequently use non-standard fields, such as e.g.
+ ``shorttitle'', required by not a few bibliographic styles.
+\end{itemize}
+
+\emph{TeXaccents} should be able to transform (La) normal text or
+``accents'' (not ``math'' accents) to their Unicode equivalent. The
+programme deals with the following codes (\emph{not all the fonts are
+able to output all the required Unicode glyphs of this table!}):
+
+\begin{verbatim}
+| NAME | \tex | Unicode |
+|--------------- |------- |---------|
+| Umlaut | \"{a} | ä |
+| acute | \'{a} | á |
+| double acute | \H{a} | a̋ |
+| grave | \`{a} | à |
+| circumflex | \^{a} | â |
+| caron hraceck | \v{a} | ǎ |
+| breve | \u{a} | ă |
+| cedilla | \c{c} | ç |
+| dot | \.{a} | ȧ |
+| dot under | \d{a} | ạ |
+| ogonek | \k{a} | ą |
+| tilde | \~{a} | ã |
+| macron | \={a} | ā |
+| bar under | \b{a} | a̱ |
+| ring over | \r{a} | å |
+\end{verbatim}
+
+The programme should recognize the following varieties:
+
+\texttt{\textbackslash{}\textquotesingle{}a} --
+\texttt{\textbackslash{}\textquotesingle{}\{a\}} --
+\texttt{\{\textbackslash{}\textquotesingle{}a\}} --
+\texttt{\{\{\textbackslash{}\textquotesingle{}a\}\}}
+
+It transforms also the encoding for : \texttt{æ~œ~Æ~Œ~ð~Ð~þ~Þ~ø~Ø~ł~Ł}.
+Checking the page
+\url{https://www.utf8-chartable.de/unicode-utf8-table.pl?number=512} I
+could not find a legacy text mode encoding for:
+\textbf{ƀ~Ƀ~đ~Đ~ǥ~Ǥ~ħ~Ħ~ɨ~Ɨ~ŧ~Ŧ~ƶ~Ƶ} (some chars are accessible in math
+mode).
+
+\hypertarget{setup}{%
+\section{Setup}\label{setup}}
+
+\hypertarget{from-source}{%
+\subsection{From source}\label{from-source}}
+
+The programme is written in Snobol
+(\url{https://en.wikipedia.org/wiki/SNOBOL} or
+\url{https://it.wikipedia.org/wiki/SNOBOL}) and should run on any
+platform. Steps:
+
+\begin{enumerate}
+\def\labelenumi{\arabic{enumi}.}
+\item
+ Install Snobol4 (version 2.3, March 2022) from
+ \url{http://www.regressive.org/snobol4/csnobol4/curr/}. Make sure to
+ install the compiler in a folder listed in your \texttt{PATH} or add
+ the folder to your path. On Linux the folder \texttt{snobol4} is
+ installed under \texttt{/usr/local/bin/}, which is normally listed in
+ the PATH of a standard Linux system.
+\item
+ Test the compiler running \texttt{snobol4} from the command line.
+ Leave the compiler with \texttt{Ctr-C} or writing \texttt{end}.
+\item
+ Copy \texttt{texaccents.sno} and all the provided \texttt{*.inc} files
+\end{enumerate}
+
+\begin{quote}
+\texttt{compiler.inc}~\texttt{delete.inc}~\texttt{grepl.inc}~\texttt{newline.inc}~\texttt{systype.inc}
+\end{quote}
+
+to a folder of your choice
+(e.g.~\texttt{/home/\textless{}user\textgreater{}/bin}).
+
+\begin{enumerate}
+\def\labelenumi{\arabic{enumi}.}
+\setcounter{enumi}{3}
+\tightlist
+\item
+ In this folder, run
+ \texttt{snobol4\ texaccents.sno\ testaccents-in\ testaccents-out} to
+ test the programme. The test file contains all the accents listed
+ above. See the result typing \texttt{cat~testaccents-out} (Unixes /
+ Powershell) or \texttt{type~testaccents-out} (Windows/Dos prompt), or
+ open the file with your text editor. The output file name is just a
+ suggestion, of course.
+\end{enumerate}
+
+\hypertarget{windows-standalone-version}{%
+\subsection{Windows standalone
+version}\label{windows-standalone-version}}
+
+If preferred, a Windows EXE standalone file is provided. It was compiled
+using Spitbol (see \url{https://github.com/spitbol/windows-nt}); the
+source code has been slightly adapted to Spitbol (basically only
+input/output syntax). From any directory, run
+\texttt{texaccents.exe\ INPUT\ OUTPUT}. To test the programme, run
+\texttt{texaccents.exe\ testaccents-in\ testaccents-out}. As above, the
+output file name is just a suggestion.
+
+\hypertarget{history}{%
+\section{History}\label{history}}
+
+\begin{itemize}
+\tightlist
+\item
+ 25\textsuperscript{th} July 2022. First version (after trying
+ unsuccesfully to convert an old file with existing utilities)
+\item
+ 17\textsuperscript{th} August 2022. First complete version (0.9).
+\item
+ 27\textsuperscript{rd} August 2022. This version (1.0) with
+ documentation and comments.
+\item
+ 17\textsuperscript{th} September 2022. Windows standalone executable.
+ Manual page written. Version message added; help message improved. In
+ the source, a regular shebang according to the recommendation of CTAN
+ (\url{https://tug.org/texlive/pkgcontrib.html}) was added.
+ Documentation updated accordingly.
+\end{itemize}
+
+\hypertarget{contacts-todo}{%
+\section{Contacts / todo}\label{contacts-todo}}
+
+Bugs / suggestions / improvements: please write to
+\url{guido.milanese at unicatt.it} using \emph{TeXaccents} as subject of
+the mail.
+
+Genoa, Italy, 17\textsuperscript{th} September 2022
+
+\end{document}
Property changes on: trunk/Master/texmf-dist/doc/support/texaccents/texaccents.tex
___________________________________________________________________
Added: svn:eol-style
## -0,0 +1 ##
+native
\ No newline at end of property
Added: trunk/Master/texmf-dist/scripts/texaccents/texaccents.sno
===================================================================
--- trunk/Master/texmf-dist/scripts/texaccents/texaccents.sno (rev 0)
+++ trunk/Master/texmf-dist/scripts/texaccents/texaccents.sno 2022-09-19 22:37:09 UTC (rev 64447)
@@ -0,0 +1,274 @@
+#!/usr/bin/env snobol4
+# texaccents.sno
+# version 1.0.1
+# 2022.08.23 -- 2022.09.17
+# guido.milanese at unicatt.it
+# Transforms LaTeX accents to their UTF8 equivalents
+# accepts both LaTeX and Bibtex codes:
+# examples: \'a \'{a} {\"a} and even {\'{a}}
+# tables of accents imported from:
+# https://github.com/hayk314/LaTex-handler -- Author: Hayk Aleksanyan
+# with my integrations, including ligatures as \ae{}
+# requires snobol4: see http://www.regressive.org/snobol4/csnobol4/curr/
+
+#################################################################
+# MIT License - Copyright (c) 2022 Guido Milanese
+# See file LICENSE in this package
+#################################################################
+
+******************************************************
+* FUNCTIONS
+******************************************************
+
+*-- Function INITIALISE
+*-- opens files, imports functions
+ define("initialise()")
+ :(initialise_end)
+initialise
+initialise_bg
+* INCLUDE FILES
+-include "delete.inc"
+-include "host.inc"
+-include "newline.inc"
+-include "grepl.inc" ;* essential! calls repl internally
+ MAX = 8000000 ;* max size of input/output files = 8 megs
+ NL = newline()
+ HELP_MSG = "texaccents 1.0.1" NL
++ "Converts legacy (La)TeX accents and ligatures to Unicode" NL
++ "Usage: texaccents.sno INFILE OUTFILE" NL
++ "--help print this help, then exit" NL
++ "--version print version number, then exit" NL
++ "Report bugs to <guido.milanese at unicatt.it>" NL
++ "CTAN page of the package: <https://www.ctan.org/pkg/texaccents>"
+
+ VERS_MSG = "texaccents 1.0.1" NL NL
++ "Copyright (c) 2022 Guido Milanese" NL NL
++ "This is free software; see the source for copying conditions. There is NO" NL
++ "warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE." NL nl
++ "Written by Guido Milanese <guido.milanese at unicatt.it>"
+
+
+#######################################################
+# opens input / output files
+#######################################################
+* Defines and checks Input & Output
+* help request -- exits. Both "--help" and "-help" are valid
+ ((host(2,2) ? "-help") (Terminal = HELP_MSG)) :s(end)
+* version request -- exits. Both "--version" and "-version" are valid
+ ((host(2,2) ? "-version") (Terminal = VERS_MSG)) :s(end)
+* Normal input-output with error messages.
+* Error messages are used by MAIN if necessary
+ (~(infile = host(2,2)) ((Terminal = HELP_MSG) (ERROR_MSG = "Input error"))) :s(freturn)
+ (~(outfile = host(2,3)) ((Terminal = HELP_MSG) (ERROR_MSG = "Output error"))) :s(freturn)
+ INPUT('r_f',1,"B " MAX, Infile) :f(freturn)
+ Terminal = "Reading text from " Infile
+ OUTPUT('w_f',2,"B " MAX, Outfile) :f(freturn)
+initialise_rt initialise = r_f :(return)
+initialise_end
+
+#####################################################################################
+*-- Function NORMACC
+*-- Changes TeX accents without curly brackets to the standard form
+*-- \'a --> \'{a}
+*-- and replaces ligatures such as \ae --> æ | \oe --> œ
+*-- requires GREPL
+#####################################################################################
+ define("normacc(Pass)")
+ P_shortacc = notany('{')
++ ((('\' any("'`" '"' "^=~.")) . Pre_shortacc)
++ (any(&ucase &lcase) . Letter_shortacc)) . V_shortacc
+ :(normacc_end)
+normacc
+normacc_bg Pass ? P_shortacc :f(normacc_lg)
+ Pass ? V_shortacc = Pre_shortacc '{' Letter_shortacc '}' :(normacc_bg)
+normacc_lg Pass2 = grepl(Pass,
++ "\ae{} \oe{} \AE{} \OE{} \dh{} \DH{} \th{} \TH{} \o{} \O{} \l{} \L{} ",
++ "æ œ Æ Œ ð Ð þ Þ ø Ø ł Ł ")
+ Terminal = "Ligatures tranformed"
+normacc_rt normacc = Pass2 :(return)
+normacc_end
+*
+* The pattern to normalise accents -- as \'a -- is defined as follows:
+* 1. there must be no '{' before backslash: otherwise the pattern would trap also
+* BibTex codes such as {\'a}
+* 2. find a backslash followed by any char of the list. Saved as "Pre_sortacc"
+* 3. find the accented letter. Saved as Letter_shortacc
+* 4. The whole structure is saved as V_shortacc
+* The programme will save the whole structure and substitute it in the text with:
+* Pre_shortacc (as \') + '{' + Letter_shortacc + '}'
+* in this way the short form -- \'a -- is transformed to the canonical \'{a}
+*
+* Ligatures and special chars are simply replaced with GREPL.
+
+#####################################################################################
+*-- Function CLEANACC
+*-- Substitutes plain letters to Unicode accents, using the sets provides by TRANSACC
+*-- \'{a} will output á
+#####################################################################################
+ define("cleanacc(Text,Acc1,Acc2)") :(cleanacc_end)
+* Acc1 is the original LaTeX code e.g. \"{a}
+* Acc2, at the time of calling the function, is e.g. \"{ä}
+cleanacc
+cleanacc_bg
+* removes paretheses: \"{ä} --> \"ä
+ Acc2 = delete(Acc2,"{}")
+* moves 2 chars and saves what remains, i.e. the letter
+* \"ä --> ä
+ Acc2 ? len(2) (rem . Acc2)
+* in text replaces e.g. \"{a} with ä
+* the substitution is done ONCE for the whole text
+ Text = repl(Text,Acc1,Acc2)
+ Terminal = "Working on " Acc2
+cleanacc_rt cleanacc = Text :(return)
+cleanacc_end
+
+#######################################################
+*-- Function TRANSACC
+*-- transforms LaTeX/Bibtex accents to Unicode
+#######################################################
+ define("transacc(Pass)")
+* Pass is the input text
+*
+* Accents used by Latex, e.g. \'{a} = acute accent over 'a'
+ Lat_acc =
++ any('"' "'" "`" 'H' '^' 'v' 'u' 'c' '.' 'd' 'k' '~' '=' 'b' 'r' )
++ . V_lat_acc
+*
+* The pattern says:
+* '\' + Lat_acc OR ('{\' + Lat_acc + '{' OR nothing)
+* any letter, saved as C_noacc + '}' + '}' OR nothing
+* Lat_acc is already defined above and saved ad V_lat_acc
+* Examples \'{a} -- {\'a} -- {\'{a}} (\'a was already "normalised")
+ P_lat_code =
++ (
++ (('\' Lat_acc '{') | ('{\' Lat_acc ('{' | '') ))
++ (any(&lcase &ucase) . C_noacc) '}' ('}' | '') ) . V_lat_code
+ :(transacc_end)
+transacc
+transacc_bg
+latcode_bg V_lat_code = ;* cleans previous value
+ V_lat_code_2 = ;* cleans previous value
+* Scans input text to locate the pattern
+* if no other LaTeX accents, fails and returns to main
+* if yes, goes to the section that transforms this accent.
+* e.g. if the accent is umlaut, will jump to TR"
+* After each transformation we have:
+* 1. the original code, e.g. \"{a} or \"a or {\"a}
+* 2. the transformed code, e.g. \"{ä} or \"ä or {\"ä}
+* Each section calls CLEANCLODE
+* CLEANCODE will remove all the {}\ and the LaTeX accent
+* and substitute in the input text e.g. \"{ä} with ä
+ Pass ? P_lat_code :f(latcode_nd)
+ :($('TR' V_lat_acc))
+
+TR" ;* umlaut
+ V_lat_code_2 = grepl(V_lat_code,
++ "A a B b C c E e H h I i K k M m N n O o P p Q q S s T t U u V v W w X x Y y Z z ",
++ "Ä ä B̈ b̈ C̈ c̈ Ë ë Ḧ ḧ Ï ï K̈ k̈ M̈ m̈ N̈ n̈ Ö ö P̈ p̈ Q̈ q̈ S̈ s̈ T̈ ẗ Ü ü V̈ v̈ Ẅ ẅ Ẍ ẍ Ÿ ÿ Z̈ z̈ ")
+ Pass = cleanacc(Pass,V_lat_code,V_lat_code_2) :(latcode_bg)
+
+TR' ;* acute
+ V_lat_code_2 = grepl(V_lat_code,
++ "A a B b C c D d E e F f G g H h I i J j K k L l M m N n O o P p Q q R r S s T t U u V v W w X x Y y Z z ",
++ "Á á B́ b́ Ć ć D́ d́ É é F́ f́ Ǵ ǵ H́ h́ Í í J́ ȷ́ Ḱ ḱ Ĺ ĺ Ḿ ḿ Ń ń Ó ó Ṕ ṕ Q́ q́ Ŕ ŕ Ś ś T́ t́ Ú ú V́ v́ Ẃ ẃ X́ x́ Ý ý Ź ź ")
+ Pass = cleanacc(Pass,V_lat_code,V_lat_code_2) :(latcode_bg)
+
+TRH ;* double acute - \H{o} Hungarian
+ V_lat_code_2 = grepl(V_lat_code,
++ "A a E e I i M m O o U u ",
++ "A̋ a̋ E̋ e̋ I̋ i̋ M̋ m̋ Ő ő Ű ű ")
+ Pass = cleanacc(Pass,V_lat_code,V_lat_code_2) :(latcode_bg)
+
+TR` ;* grave
+ V_lat_code_2 = grepl(V_lat_code,
++ "A a Æ æ E e H h I i K k M m N n O o R r S s T t U u V v W w X x Y y Z z ",
++ "À à Æ̀ æ̀ È è H̀ h̀ Ì ì K̀ k̀ M̀ m̀ Ǹ ǹ Ò ò R̀ r̀ S̀ s̀ T̀ t̀ Ù ù V̀ v̀ Ẁ ẁ X̀ x̀ Ỳ ỳ Z̀ z̀ ")
+ Pass = cleanacc(Pass,V_lat_code,V_lat_code_2) :(latcode_bg)
+
+TR^ ;* circumflex \^{o}
+ V_lat_code_2 = grepl(V_lat_code,
++ "A a B b C c D d E e G g H h I i J j K k L l M m N n O o R r S s T t U u V v W w X x Y y Z z ",
++ "Â â B̂ b̂ Ĉ ĉ D̂ d̂ Ê ê Ĝ ĝ Ĥ ĥ Î î Ĵ ĵ K̂ k̂ L̂ l̂ M̂ m̂ N̂ n̂ Ô ô R̂ r̂ Ŝ ŝ T̂ t̂ Û û V̂ v̂ Ŵ ŵ X̂ x̂ Ŷ ŷ Ẑ ẑ ")
+ Pass = cleanacc(Pass,V_lat_code,V_lat_code_2) :(latcode_bg)
+
+TRv ;* caron hraceck \v{s}
+* For accents that are also normal letters
+* we need to restore the accent to its original value
+* This applies to: v u c d k b r
+ V_lat_code_2 = grepl(V_lat_code,
++ "A a B b C c D d E e F f G g H h I i J j K k L l M m N n O o P p Q q R r S s T t U u V v W w X x Y y Z z ",
++ "Ǎ ǎ B̌ b̌ Č č Ď ď Ě ě F̌ f̌ Ǧ ǧ Ȟ ȟ Ǐ ǐ J̌ ǰ Ǩ ǩ Ľ ľ M̌ m̌ Ň ň Ǒ ǒ P̌ p̌ Q̌ q̌ Ř ř Š š Ť ť Ǔ ǔ V̌ v̌ W̌ w̌ X̌ x̌ Y̌ y̌ Ž ž ")
+ V_lat_code_2 = repl(V_lat_code_2,"\v̌","\v")
+ Pass = cleanacc(Pass,V_lat_code,V_lat_code_2) :(latcode_bg)
+
+TRu ;* breve \u{o}
+ V_lat_code_2 = grepl(V_lat_code,
++ "A a C c E e G g I i K k M m N n O o P p R r T t U u V v X x Y y ",
++ "Ă ă C̆ c̆ Ĕ ĕ Ğ ğ Ĭ ĭ K̆ k̆ M̆ m̆ N̆ n̆ Ŏ ŏ P̆ p̆ R̆ r̆ T̆ t̆ Ŭ ŭ V̆ v̆ X̆ x̆ Y̆ y̆ ")
+ V_lat_code_2 = repl(V_lat_code_2,"\ŭ","\u")
+ Pass = cleanacc(Pass,V_lat_code,V_lat_code_2) :(latcode_bg)
+
+TRc ;* cedilla \c{c}
+ V_lat_code_2 = grepl(V_lat_code,
++ "A a B b C c D d E e G g H h I i K k L l M m N n O o Q q R r S s T t U u X x Z z ",
++ "A̧ a̧ B̧ b̧ Ç ç Ḑ ḑ Ȩ ȩ Ģ ģ Ḩ ḩ I̧ i̧ Ķ ķ Ļ ļ M̧ m̧ Ņ ņ O̧ o̧ Q̧ q̧ Ŗ ŗ Ş ş Ţ ţ U̧ u̧ X̧ x̧ Z̧ z̧ ")
+ V_lat_code_2 = repl(V_lat_code_2,"\ç","\c")
+ Pass = cleanacc(Pass,V_lat_code,V_lat_code_2) :(latcode_bg)
+
+TR. ;* dot \.{o}
+ V_lat_code_2 = grepl(V_lat_code,
++ "A a B b C c D d E e F f G g H h I i K k L l M m N n O o P p Q q R r S s T t U u V v W w X x Y y Z z ",
++ "Ȧ ȧ Ḃ ḃ Ċ ċ Ḋ ḋ Ė ė Ḟ ḟ Ġ ġ Ḣ ḣ İ i̇̀ K̇ k̇ L̇ l̇ Ṁ ṁ Ṅ ṅ Ȯ ȯ Ṗ ṗ Q̇ q̇ Ṙ ṙ Ṡ ṡ Ṫ ṫ U̇ u̇ V̇ v̇ Ẇ ẇ Ẋ ẋ Ẏ ẏ Ż ż ")
+ Pass = cleanacc(Pass,V_lat_code,V_lat_code_2) :(latcode_bg)
+
+TRd ;* dot under the letter \d{u}
+ V_lat_code_2 = grepl(V_lat_code,
++ "A a B b C c D d E e F f G g H h I i J j K k L l M m N n O o P p Q q R r S s T t U u V v W w X x Y y Z z ",
++ "Ạ ạ Ḅ ḅ C̣ c̣ Ḍ ḍ Ẹ ẹ F̣ f̣ G̣ g̣ Ḥ ḥ Ị ị J̣ j̣ Ḳ ḳ Ḷ ḷ Ṃ ṃ Ṇ ṇ Ọ ọ P̣ p̣ Q̣ q̣ Ṛ ṛ Ṣ ṣ Ṭ ṭ Ụ ụ Ṿ ṿ Ẉ ẉ X̣ x̣ Ỵ ỵ Ẓ ẓ ")
+ V_lat_code_2 = repl(V_lat_code_2,"\ḍ","\d")
+ Pass = cleanacc(Pass,V_lat_code,V_lat_code_2) :(latcode_bg)
+
+TRk ;* ogonek \k{a}
+ V_lat_code_2 = grepl(V_lat_code,
++ "A a E e I i O o U u Y y ",
++ "Ą ą Ę ę Į į Ǫ ǫ Ų ų Y̨ y̨ ")
+ Pass = cleanacc(Pass,V_lat_code,V_lat_code_2) :(latcode_bg)
+
+TR~ ;* tilde \~o
+ V_lat_code_2 = grepl(V_lat_code,
++ "A a E e I i N n O o U u V v Y y ",
++ "Ã ã Ẽ ẽ Ĩ ĩ Ñ ñ Õ õ Ũ ũ Ṽ ṽ Ỹ ỹ ")
+ Pass = cleanacc(Pass,V_lat_code,V_lat_code_2) :(latcode_bg)
+
+TR= ;* macron \=a \={a}
+ V_lat_code_2 = grepl(V_lat_code,
++ "A a B b C c D d E e G g I i J j K k M m N n O o P p Q q R r S s T t U u V v W w X x Y y Z z ",
++ "Ā ā B̄ b̄ C̄ c̄ D̄ d̄ Ē ē Ḡ ḡ Ī ī J̄ j̄ K̄ k̄ M̄ m̄ N̄ n̄ Ō ō P̄ p̄ Q̄ q̄ R̄ r̄ S̄ s̄ T̄ t̄ Ū ū V̄ v̄ W̄ w̄ X̄ x̄ Ȳ ȳ Z̄ z̄ ")
+ Pass = cleanacc(Pass,V_lat_code,V_lat_code_2) :(latcode_bg)
+
+TRb ;* bar under the letter \b{a}
+ V_lat_code_2 = grepl(V_lat_code,
++ "A a B b C c D d E e G g H h I i J j K k L l M m N n O o P p R r S s T t U u X x Y y Z z ",
++ "A̱ a̱ Ḇ ḇ C̱ c̱ Ḏ ḏ E̱ e̱ G̱ g̱ H̱ ẖ I̱ i̱ J̱ j̱ Ḵ ḵ Ḻ ḻ M̱ m̱ Ṉ ṉ O̱ o̱ P̱ p̱ Ṟ ṟ S̱ s̱ Ṯ ṯ U̱ u̱ X̱ x̱ Y̱ y̱ Ẕ ẕ ")
+ V_lat_code_2 = repl(V_lat_code_2,"\ḇ","\b")
+ Pass = cleanacc(Pass,V_lat_code,V_lat_code_2) :(latcode_bg)
+
+TRr ;* ring over the letter \r{a}
+ V_lat_code_2 = grepl(V_lat_code,
++ "A a B b C c D d E e F f G g H h I i J j K k L l M m N n O o P p Q q r R S s U u V v W w X x Y y Z z ",
++ "Å å B̊ b̊ C̊ c̊ D̊ d̊ E̊ e̊ F̊ f̊ G̊ g̊ H̊ h̊ I̊ i̊ J̊ j̊ K̊ k̊ L̊ l̊ M̊ m̊ N̊ n̊ O̊ o̊ P̊ p̊ Q̊ q̊ r̊ R̊ S̊ s̊ Ů ů V̊ v̊ W̊ ẘ X̊ x̊ Y̊ ẙ Z̊ z̊ ")
+ V_lat_code_2 = repl(V_lat_code_2,"\r̊","\r")
+ Pass = cleanacc(Pass,V_lat_code,V_lat_code_2) :(latcode_bg)
+
+latcode_nd
+ transacc = Pass :(return)
+transacc_end
+
+#######################################################
+# MAIN
+#######################################################
+ (~(texfile = initialise()) (terminal = "Could not start programme - " ERROR_MSG)) :s(end)
+ Texfile = normacc(Texfile)
+ (((w_f = transacc(texfile)) (Terminal = "Done. File " Outfile " written")),
++ (Terminal = "Conversion failed"))
+end
Property changes on: trunk/Master/texmf-dist/scripts/texaccents/texaccents.sno
___________________________________________________________________
Added: svn:executable
## -0,0 +1 ##
+*
\ No newline at end of property
Added: trunk/Master/texmf-dist/source/support/texaccents/compiler.inc
===================================================================
--- trunk/Master/texmf-dist/source/support/texaccents/compiler.inc (rev 0)
+++ trunk/Master/texmf-dist/source/support/texaccents/compiler.inc 2022-09-19 22:37:09 UTC (rev 64447)
@@ -0,0 +1,14 @@
+* Compiler.inc
+* Gregory White <glwhite at netconnect.com.au>
+* Posted to the Snobol list (March 2003)
+* and adapted as a function
+
+ DEFINE('COMPILER()') :(COMPILER_END)
+compiler
+IDprocessor :($('COMPILER' SIZE(DATE())))
+COMPILER17 compiler = 'SPITBOL' :(return)
+COMPILER19 compiler = 'CSNOBOL4' :(return)
+COMPILER20 compiler = 'SNOBOL4+' :(return)
+compiler_end
+* Uses the different size of DATE() to detect the compiler used
+
Property changes on: trunk/Master/texmf-dist/source/support/texaccents/compiler.inc
___________________________________________________________________
Added: svn:eol-style
## -0,0 +1 ##
+native
\ No newline at end of property
Added: trunk/Master/texmf-dist/source/support/texaccents/delete.inc
===================================================================
--- trunk/Master/texmf-dist/source/support/texaccents/delete.inc (rev 0)
+++ trunk/Master/texmf-dist/source/support/texaccents/delete.inc 2022-09-19 22:37:09 UTC (rev 64447)
@@ -0,0 +1,21 @@
+******************************************
+* DELETE
+* Deletes String in Text
+******************************************
+#################################################################
+# MIT License - Copyright (c) 2009 Guido Milanese
+# See file LICENSE in this package
+#################################################################
+* Guido Milanese 2004
+* removed error message, 2009
+* <guido.milanese at unicatt.it>
+* Example:
+* String = delete(String,";,:.") ;* deletes any char listed in "..."
+ define('delete(String,Txt)') :(delete_end)
+delete
+ ~(String ? any(Txt)) :s(freturn)
+delete_loop
+ String ? any(Txt) = '' :s(delete_loop)f(delete_return)
+delete_return delete = String :(return)
+delete_end
+
Property changes on: trunk/Master/texmf-dist/source/support/texaccents/delete.inc
___________________________________________________________________
Added: svn:eol-style
## -0,0 +1 ##
+native
\ No newline at end of property
Added: trunk/Master/texmf-dist/source/support/texaccents/grepl.inc
===================================================================
--- trunk/Master/texmf-dist/source/support/texaccents/grepl.inc (rev 0)
+++ trunk/Master/texmf-dist/source/support/texaccents/grepl.inc 2022-09-19 22:37:09 UTC (rev 64447)
@@ -0,0 +1,63 @@
+* Function GREPL
+* replaces all the items in SET1 with all the items in SET2
+* SET1/2 must have the form "ITEM ITEM ITEM " -- space at the end
+* guido.milanese at unicatt.it
+* requires "repl.inc"
+* 31.07.2022
+#################################################################
+# MIT License - Copyright (c) 2022 Guido Milanese
+# See file LICENSE in this package
+#################################################################
+ define("grepl(Pass,Set1,Set2)datum,I,N,T1,T2,A1,A2")
+-include "repl.inc"
+ :(grepl_end)
+grepl
+grepl_bg
+ T1 = TABLE()
+ T2 = TABLE()
+ N = 0
+grepl1 N = N + 1
+ Set1 ? break(' ') . datum len(1) rem . Set1 :f(grepl1_nd)
+ T1[N] = datum :(grepl1)
+grepl1_nd
+
+ N = 0
+grepl2 N = N + 1
+ Set2 ? break(' ') . datum len(1) rem . Set2 :f(grepl2_nd)
+ T2[N] = datum :(grepl2)
+grepl2_nd
+ A1 = convert(T1,"ARRAY")
+ A2 = convert(T2,"ARRAY")
+grepl3_bg I = I + 1
+ Pass = repl(Pass,A1[I,2],A2[I,2]) :S(grepl3_bg)F(grepl3_nd)
+grepl3_nd
+grepl_rt grepl = Pass :(return)
+grepl_end
+
+*********************************************************************
+* This function, as Phil Budne's "repl", replaces string/string
+* but, as standard "replace", can replace a set with another set.
+* In this way also Unicode chars can be replaced with no limitation
+* since they are treated as strings.
+* Text = "aiuole"
+* S1 = "a e i o u "
+* S2 = "1 2 3 4 5 "
+* Text2 = grepl(Text,S1,S2)
+* will output: "1354l2"
+* But also:
+* Text = "aiuole"
+* S1 = "a e i o u "
+* S2 = "ā ē ī ō ū "
+* will output: "āīūōlē"
+* the standard REPLACE ("aeiou" / "āēīōū") will fail
+* because Unicode chars (>127 ASCII) do not have the same length of chars <127.
+* Step by step:
+* create two tables for sets: T1 and T2
+* feed the tables scanning thes two sets (items must be separeted by spaces)
+* convert from tables to arrays
+* use REPL converting string/string in PASS:
+* each item of SET1 is replaced by the corresponding item in S2
+* if SET2 is shorter the exceeding item in SET1 is left unchanged
+* if SET1 is shorter the exceeding item in SET2 is not used
+* Please notice that separating items by spaces makes it possible to substitute
+* also sets of strings, such as e.g. LaTeX accents.
Property changes on: trunk/Master/texmf-dist/source/support/texaccents/grepl.inc
___________________________________________________________________
Added: svn:eol-style
## -0,0 +1 ##
+native
\ No newline at end of property
Added: trunk/Master/texmf-dist/source/support/texaccents/newline.inc
===================================================================
--- trunk/Master/texmf-dist/source/support/texaccents/newline.inc (rev 0)
+++ trunk/Master/texmf-dist/source/support/texaccents/newline.inc 2022-09-19 22:37:09 UTC (rev 64447)
@@ -0,0 +1,23 @@
+* NEWLINE
+* Checks OS and compiler type to set newline
+* Part of this function uses code posted by
+* Gregory White <glwhite at netconnect.com.au>
+* on the Snobol list in March 2003
+* Guido Milanese <guido.milanese at unicatt.it>
+#################################################################
+# MIT License - Copyright (c) 2003 Guido Milanese
+# See file LICENSE in this package
+#################################################################
+ define('newline()compiler_type')
+-include "compiler.inc"
+-include "systype.inc"
+ :(newline_end)
+newline
+* Compiler being used. If it is Snobol4+, that does not have
+* the HOST() function, assumes that the newline is Dos type
+snobol4 (compiler_type = compiler()) ? "SNOBOL4+" :f(other)
+ newline = char(13) char(10) :(return)
+* otherwise finds through HOST the OS type and sets newline
+* accordingly
+other newline = systype() :(return)
+newline_end
Property changes on: trunk/Master/texmf-dist/source/support/texaccents/newline.inc
___________________________________________________________________
Added: svn:eol-style
## -0,0 +1 ##
+native
\ No newline at end of property
Added: trunk/Master/texmf-dist/source/support/texaccents/systype.inc
===================================================================
--- trunk/Master/texmf-dist/source/support/texaccents/systype.inc (rev 0)
+++ trunk/Master/texmf-dist/source/support/texaccents/systype.inc 2022-09-19 22:37:09 UTC (rev 64447)
@@ -0,0 +1,17 @@
+* SYSTYPE
+* Sets new_line value according to OS
+* Guido Milanese <guido.milanese at unicatt.it>
+* March 2003
+#################################################################
+# MIT License - Copyright (c) 2003 Guido Milanese
+# See file LICENSE in this package
+#################################################################
+ DEFINE('SYSTYPE()os') :(SYSTYPE_END)
+SYSTYPE os = replace(host(),&UCASE,&LCASE)
+UNIX os ? ('nix' | 'nux') :f(DOS)
+ systype = char(10) :(return)
+DOS systype = char(13) char(10) :s(return)
+ :(freturn)
+SYSTYPE_END
+* 'os' is the string returned by host().
+* The function does not work under snobol4+, requires Spitbol or CSnobol4.
Property changes on: trunk/Master/texmf-dist/source/support/texaccents/systype.inc
___________________________________________________________________
Added: svn:eol-style
## -0,0 +1 ##
+native
\ No newline at end of property
Modified: trunk/Master/tlpkg/bin/tlpkg-ctan-check
===================================================================
--- trunk/Master/tlpkg/bin/tlpkg-ctan-check 2022-09-19 20:28:42 UTC (rev 64446)
+++ trunk/Master/tlpkg/bin/tlpkg-ctan-check 2022-09-19 22:37:09 UTC (rev 64447)
@@ -778,7 +778,7 @@
tex-ewd tex-font-errors-cheatsheet tex-gyre tex-gyre-math tex-ini-files
tex-label tex-locale tex-nutshell tex-overview tex-ps
tex-refs tex-virtual-academy-pl tex-vpat
- tex4ebook texapi texbytopic texcount
+ tex4ebook texaccents texapi texbytopic texcount
texdate texdef texdiff texdimens texdirflatten texdoc texdraw
texfot texinfo texilikechaps texilikecover
texliveonfly texloganalyser texlogfilter texlogos texlogsieve
Modified: trunk/Master/tlpkg/libexec/ctan2tds
===================================================================
--- trunk/Master/tlpkg/libexec/ctan2tds 2022-09-19 20:28:42 UTC (rev 64446)
+++ trunk/Master/tlpkg/libexec/ctan2tds 2022-09-19 22:37:09 UTC (rev 64447)
@@ -1349,7 +1349,6 @@
'tex-implementors', "die 'skipping, verbatim mail archive'",
'tex-it', "die 'skipping, old support'",
'tex_it', "die 'skipping, old support'",
- 'texaccents', "die 'skipping, snobol? and no doc source/man page'",
'texdoc', "&MAKEflatten",
'texdoctk', "die 'skipping, moribund, only in tl'",
'texemplar', "die 'skipping, await request, 199x'",
@@ -2929,6 +2928,7 @@
'shipunov', 'NULL', # .bat in scripts
'stex', 'NULL', # handled in post fn
'tex-vpat', 'NULL',
+ 'texaccents', '\.inc',
'texdraw', 'NULL',
'texosquery', 'java|\.batch$|' . $standardsource,
'thailatex', 'NULL', # no gain in splitting up
@@ -3604,6 +3604,7 @@
'sty2dtx' => '\.pl$',
'svn-multi' => 'svn-multi\.pl$',
'tex4ebook' => 'tex4ebook$',
+ 'texaccents' => 'texaccents.sno',
'texcount' => '\.pl$',
'texdef' => '\.pl$',
'texdiff' => 'texdiff$',
@@ -3692,6 +3693,7 @@
'splitindex' => '\.1$',
'srcredact' => '\.1$',
'sty2dtx' => '\.1$',
+ 'texaccents' => '\.1$',
'texdiff' => 'texdiff.1',
'texdirflatten' => 'texdirflatten.1',
'texdoc' => '\.1$',
@@ -4529,6 +4531,11 @@
# handwritten .bat
&SYSTEM ("$MV $s.bat $platdir/");
next; # no wrapper
+
+ } elsif ($s eq "texaccents.sno") {
+ # provided .exe
+ &SYSTEM ("$MV texaccents.exe $platdir/");
+ next; # no wrapper
}
# next bit of ugliness: can be better to use the GUI wrapper
Modified: trunk/Master/tlpkg/tlpsrc/collection-binextra.tlpsrc
===================================================================
--- trunk/Master/tlpkg/tlpsrc/collection-binextra.tlpsrc 2022-09-19 20:28:42 UTC (rev 64446)
+++ trunk/Master/tlpkg/tlpsrc/collection-binextra.tlpsrc 2022-09-19 22:37:09 UTC (rev 64447)
@@ -85,6 +85,7 @@
depend sty2dtx
depend synctex
depend tex4ebook
+depend texaccents
depend texcount
depend texdef
depend texdiff
Added: trunk/Master/tlpkg/tlpsrc/texaccents.tlpsrc
===================================================================
--- trunk/Master/tlpkg/tlpsrc/texaccents.tlpsrc (rev 0)
+++ trunk/Master/tlpkg/tlpsrc/texaccents.tlpsrc 2022-09-19 22:37:09 UTC (rev 64447)
@@ -0,0 +1,2 @@
+binpattern f bin/${ARCH}/${PKGNAME}
+
More information about the tex-live-commits
mailing list.