the implementation of the 'arabica' transliteration needed more work; a couple of bugs also found their way into v1.8 in the processv1.8.1

3 files changed, 88 insertions, 16 deletions

diff --git a/arabluatex.dtx b/arabluatex.dtx
index 3e2c1d7..cd4e0c6 100644
--- a/arabluatex.dtx
+++ b/arabluatex.dtx
@@ -27,7 +27,7 @@
 %<package-info>\NeedsTeXFormat{LaTeX2e}[1999/12/01]
 %<package-info>\ProvidesPackage{arabluatex}
 %<*package-info>
-    [2017/03/30 v1.8 An ArabTeX-like interface for LuaLaTeX]
+    [2017/04/01 v1.8.1 An ArabTeX-like interface for LuaLaTeX]
 %</package-info>
 %
 %<*driver>
@@ -145,7 +145,7 @@
 \defaultfontfeatures{RawFeature={+liga}}
 \setmainfont{Old Standard}[SmallCapsFont={Latin Modern Roman Caps},
   RawFeature={+mark;+ccmp;+ss05;+ss06}]
-\usepackage{arabluatex}[2017/03/30]
+\usepackage{arabluatex}[2017/04/01]
 \usepackage[nopar]{quran}
 \usepackage{varioref}
 \usepackage{hyperxmp}
@@ -165,6 +165,7 @@
   pdflicenseurl={https://creativecommons.org/licenses/by-sa/4.0/legalcode},
   pdfmetalang={en-US}, pdftype={Text}, pdfkeywords={Arabic language,
     arabtex, luatex}}
+\usepackage[scale=1.5]{ccicons}
 \usepackage[toc,lot]{multitoc}
 \usepackage{paralist}
 \setdefaultitem{\textendash}{\textendash}{\textendash}{\textendash}
@@ -340,7 +341,8 @@
 % \subsection*{License applicable to this document}
 % \label{sec:documentation-license}
 % Copyright \textcopyright\ 2016--2017  Robert Alessi
-% 
+%
+% \ccbysa\
 % This document is licensed under the Creative Commons
 % Attribution-ShareAlike 4.0 International License. To view a copy of
 % this license, visit
@@ -965,7 +967,7 @@ vowels (see §~3).
 % \begin{quote}
 %   |.hay_aUTuN| \arb[voc]{.hay_aUTuN} \arb[trans]{.hay_aUTuN},
 %   |.sal_aUTuN| \arb[voc]{.sal_aUTuN} \arb[trans]{.sal_aUTuN},
-%   |mi^sk_aUTuN| \arb[voc]{mi^sk_aUTuN} \arb[trans]{mi^sk_aUTuN},
+%   |mi^sk_aUTuN| \arb[voc]{mi^sk_aUTuN} \arb[trans]{mi^s\-k_aUTuN},
 %   |tawr_aITuN| \arb[voc]{tawr_aITuN} \arb[trans]{tawr_aITuN}.
 %
 %   And so also: |al-rib_aIT-u| \arb[voc]{al-rib_aIT-u}
@@ -1594,11 +1596,11 @@ vowels (see §~3).
 % \begin{compactenum}[(a)]
 % \item \arb[trans]{'alif-u 'l-wa.sl-i}:---
 %   \begin{quote}
-%     |fI "istisqA'-a| \arb[voc]{fI "istisqA'-a} \arb[trans]{fI
-%     "istisqA'-a}, |wa-"istisqA'-u| \arb[voc]{wa-"istisqA'-u}
-%     \arb[trans]{wa-"is\-tisqA'-u}, |qAla| |"uhrub| |fa-lan|
-%     |tuqtala| \arb[voc]{qAla "uhrub fa-lan tuqtala} \arb[trans]{qAla
-%     "uhrub fa-lan tuqtala}.
+%     |fI "istiq.sA'-iN| \arb[voc]{fI "istiq.sA'-iN} \arb[trans]{fI
+%     "istiq.sA'-iN}, |wa-"istiq.sA'-uN| \arb[voc]{wa-"istiq.sA'-uN}
+%     \allowbreak\arb[trans]{wa-"istiq.sA'-uN}, |qAla| |"uhrub|
+%     |fa-lan| |tuqtala| \arb[voc]{qAla "uhrub fa-lan tuqtala}
+%     \arb[trans]{qAla "uhrub fa-lan tuqtala}.
 %   \end{quote}
 % \item \arb[trans]{sukUn}:---
 %   \begin{quote}
@@ -2452,7 +2454,7 @@ muhaddamaTaN mi'_danatu-hu}: \arb[trans]{ra'aytu
 %
 % \SetTranslitConvention{dmg}
 % \begin{arab}[trans]
-%   \LR{\textbf{\emph{\enquote*{dmg}} standard}:} 'at_A .sadIquN 'il_A
+%   \LR{\textbf{\emph{\enquote*{dmg}} standard:}} 'at_A .sadIquN 'il_A
 %   \cap{ju.hA} ya.tlubu min-hu .himAra-hu li-yarkaba-hu fI safraTiN
 %   qa.sIraTiN fa-qAla la-hu: \enquote{sawfa 'u`Idu-hu 'ilay-ka fI
 %   'l-masA'-i wa-'adfa`u la-ka 'ujraTaN.} fa-qAla \cap{ju.hA}:
@@ -2467,7 +2469,7 @@ muhaddamaTaN mi'_danatu-hu}: \arb[trans]{ra'aytu
 % 
 % \SetTranslitConvention{loc}
 % \begin{arab}[trans]
-%   \LR{\textbf{\emph{\enquote*{loc}} standard}:} 'at_A .sadIquN 'il_A
+%   \LR{\textbf{\emph{\enquote*{loc}} standard:}} 'at_A .sadIquN 'il_A
 %   \cap{ju.hA} ya.tlubu min-hu .himAra-hu li-yarkaba-hu fI safraTiN
 %   qa.sIraTiN fa-qAla la-hu: \enquote{sawfa 'u`Idu-hu 'ilay-ka fI
 %   'l-masA'-i wa-'adfa`u la-ka 'ujraTaN.} fa-qAla \cap{ju.hA}:
@@ -2483,7 +2485,7 @@ muhaddamaTaN mi'_danatu-hu}: \arb[trans]{ra'aytu
 %
 % \SetTranslitConvention{arabica}
 % \begin{arab}[trans]
-%   \LR{\textbf{\emph{\enquote*{arabica}} standard}:} 'at_A .sadIquN
+%   \LR{\textbf{\emph{\enquote*{arabica}} standard:}} 'at_A .sadIquN
 %   'il_A \cap{ju.hA} ya.tlubu min-hu .himAra-hu li-yarkaba-hu fI
 %   safraTiN qa.sIraTiN fa-qAla la-hu: \enquote{sawfa 'u`Idu-hu
 %   'ilay-ka fI 'l-masA'-i wa-'adfa`u la-ka 'ujraTaN.} fa-qAla
@@ -3084,7 +3086,7 @@ wa-ya.sIru ta.hta 'l-jild-i
 %    \begin{macrocode}
 \NeedsTeXFormat{LaTeX2e}
 \ProvidesPackage{arabluatex}%
-[2017/03/30 v1.8 An ArabTeX-like interface for LuaLaTeX]
+[2017/04/01 v1.8.1 An ArabTeX-like interface for LuaLaTeX]
 \RequirePackage{ifluatex}
 %    \end{macrocode}
 % \package{arabluatex} requires \LuaLaTeX\ of course. Issue a warning
diff --git a/arabluatex.lua b/arabluatex.lua
index 3b76376..eeef54b 100644
--- a/arabluatex.lua
+++ b/arabluatex.lua
@@ -497,8 +497,8 @@ end
 local function transarabica(str)
    str = string.gsub(str, "\\arb(%b{})", function(inside)
    inside = string.sub(inside, 2, -2)
-   for i = 1,#hamzatrloc do
-      inside = string.gsub(inside, hamzatrloc[i].a, hamzatrloc[i].b)
+   for i = 1,#hamzatrarabica do
+      inside = string.gsub(inside, hamzatrarabica[i].a, hamzatrarabica[i].b)
    end
    for i = 1,#tanwintrloc do
       inside  = string.gsub(inside, tanwintrloc[i].a, tanwintrloc[i].b)
diff --git a/arabluatex_trans.lua b/arabluatex_trans.lua
index e12eaa0..7820cd1 100644
--- a/arabluatex_trans.lua
+++ b/arabluatex_trans.lua
@@ -631,10 +631,78 @@ finaltrloc = {
 
 -- arabica
 
+hamzatrarabica = { -- ≠ from hamzatrloc: initial hamza has to be held
+   -- hard coded hamza
+   {a="|\"'", b="ʾ"},
+   {a="A\"'", b="ʾA"},
+   {a="[au]\"'", b="ʾ"},
+   {a="w\"'", b="ʾ"},
+   {a="i\"'", b="ʾ"},
+   {a="y\"'", b="ʾ"},
+   -- hamza takes tašdīd too
+   {a="''([Uu])", b="ʾʾ%1"},
+   {a="''([Aa])", b="ʾʾ%1"},
+   {a="''([Ii])", b="ʾʾ%1"},
+   -- initial long u and i (for a, see below)
+   {a="%'%_U", b="U"},
+   {a="%'%_I", b="I"},
+   -- taḫfīfu 'l-hamza
+   {a="^'u'([^uaiUAI])", b="U%1"},
+   {a="(%W)'u'([^uaiUAI])", b="%1U%2"},
+   {a="'u'([^uaiUAI])", b="ʾU"},
+   {a="^'i'([^uaiUAI])", b="I%1"},
+   {a="(%W)'i'([^uaiUAI])", b="%1I%2"},
+   {a="'i'([^uaiUAI])", b="ʾI"},
+   -- madda (historic writing below)
+   {a="^(')(A)", b="%2"},
+   {a="(%W)(')(A)", b="%1%3"},
+   {a="^'a'([^uaiUAI])", b="A%1"},
+   {a="(%W)'a'([^uaiUAI])", b="%1A%2"},
+   {a="'a'([^uaiUAI])", b="A%1"},
+   {a="^'a?A", b="A"},
+   {a="(%W)'a?A", b="%1A"},
+   {a="'a?A", b="ʾA"},
+   {a="(A)(')(i)$", b="%1ʾ%3"},
+   {a="(A)(')(i)(%W)", b="%1ʾ%3%4"},
+   {a="(A)(')(i)", b="%1ʾ%3"}, -- historic madda
+   {a="(A)(')", b="%1ʾ"}, -- historic madda
+   -- initial (needs both ^ and %W patterns):
+   -- hold it for now (see below, beginning of digraphs table)
+   {a="^(')([ua])", b="@%2"},
+   {a="^(')(i)", b="@%2"},
+   {a="(%W)(')([ua])", b="%1@%3"},
+   {a="(%W)(')(i)", b="%1@%3"},
+   -- final
+   {a="([Iy])(')(aN)$", b="%1ʾ%3"},
+   {a="([Iy])(')(aN)(%W)", b="%1ʾ%3%4"},
+   {a="([^uai])(')([uai]N?)$", b="%1ʾ%3"},
+   {a="([^uai])(')([uai]N?)(%W)", b="%1ʾ%3%4"},
+   {a="([UI])(')([uai])$", b="%1ʾ%3"},
+   {a="([UI])(')([uai])(%W)", b="%1ʾ%3%4"},
+   -- middle
+   {a="(U)(')", b="%1ʾ"},
+   {a="([Iy])(')", b="%1ʾ"},
+   {a="([^uai])(')([uU])", b="%1ʾ%3"},
+   {a="([^uai])(')([aA])", b="%1ʾ%3"},
+   {a="([^uai])(')([iI])", b="%1ʾ%3"},
+   {a="(u)(')([uU])", b="%1ʾ%3"},
+   {a="(u)(')([aA])", b="%1ʾ%3"},
+   {a="(u)(')([iI])", b="%1ʾ%3"},
+   {a="(a)(')([aA])", b="%1ʾ%3"},
+   {a="(a)(')([uU])", b="%1ʾ%3"},
+   {a="(a)(')([iI])", b="%1ʾ%3"},
+   {a="(i)(')([aA])", b="%1ʾ%3"},
+   {a="(i)(')([uU])", b="%1ʾ%3"},
+   {a="(i)(')([iI])", b="%1ʾ%3"},
+   {a="(a)(')([^uaiUAI])", b="%1ʾ%3"},
+   {a="(u)(')([^uaiUAI])", b="%1ʾ%3"},
+   {a="(i)(')([^uaiUAI])", b="%1ʾ%3"}
+}
+
 trigraphstrarabica = { -- trigraphs or more
    -- 'llatI / 'llad_I
    {a="^'ll(a)([%_]?[dt])", b="ll%1%2"},
-   {a="([%(%[%|%<%s])'ll(a)([%_]?[dt])", b="%1ll%2%3"}, --p
+   {a="([%-%(%[%|%<%s])'ll(a)([%_]?[dt])", b="%1ll%2%3"}, --p
    -- al- + lām
    {a="^(a)l%-(l)", b="%1l-%2"},
    {a="(%s)(a)l%-(l)", b="%1%2l-%3"},
@@ -682,6 +750,8 @@ trigraphstrarabica = { -- trigraphs or more
 }
 
 digraphstrarabica = {
+   {a="([uai]%-)(\"?[uai])", b="%1"}, -- hyphen + initial alif without hamza
+   {a="@", b=""}, -- remove the tag before the former hamza
    -- discard the ʾiʿrāb hyphen (begin)
    {a="(%-)(\"?[UI]na)(%p?%s)", b="%2%3"},
    {a="(%-)(\"?[UI]na)(%p?)$", b="%2%3"},