addition of six Persian characters

4 files changed, 283 insertions, 81 deletions

diff --git a/arabluatex_fullvoc.lua b/arabluatex_fullvoc.lua
index 6d63192..99efb75 100644
--- a/arabluatex_fullvoc.lua
+++ b/arabluatex_fullvoc.lua
@@ -354,12 +354,16 @@ trigraphsfv = { -- trigraphs or more
    -- al- + lām
    {a="^(a)l%-(l)", b="ا%1ل%2%2"},
    {a="([%(%[%|%<%s%-o])(a)l%-(l)", b="%1ا%2ل%3%3"}, --p
-   -- al- + solar consonant
-   {a="^(a)l%-([%_%^%.]?[tdrzsn])", b="ا%1ل%2%2"},
-   {a="([%(%[%|%<%s%-o])(a)l%-([%_%^%.]?[tdrzsn])", b="%1ا%2ل%3%3"}, --p
-   -- assim. art. + solar consonant
-   {a="^(a)([%_%^%.]?[tdrzsn])%-", b="ا%1ل%2"},
-   {a="([%(%[%|%<%s%-o])(a)([%_%^%.]?[tdrzsn])%-", b="%1ا%2ل%3"}, --p
+   -- al- + solar consonant ('c' and '^n' are additional characters)
+   {a="^(a)l%-(%^n)", b="ا%1ل%2"}, -- ^n is lunar
+   {a="([%(%[%|%<%s%-o])(a)l%-(%^n)", b="%1ا%2ل%3"}, -- ^n is lunar --p
+   {a="^(a)l%-([%_%^%.]?[tdrzsnc])", b="ا%1ل%2%2"},
+   {a="([%(%[%|%<%s%-o])(a)l%-([%_%^%.]?[tdrzsnc])", b="%1ا%2ل%3%3"}, --p
+   -- assim. art. + solar consonant ('c' and '^n' are additional characters)
+   {a="^(a)(%^n)%-", b="ا%1ل"}, -- ^n is lunar
+   {a="([%(%[%|%<%s%-o])(a)(%^n)%-", b="%1ا%2ل"}, -- ^n is lunar --p
+   {a="^(a)([%_%^%.]?[tdrzsnc])%-", b="ا%1ل%2"},
+   {a="([%(%[%|%<%s%-o])(a)([%_%^%.]?[tdrzsnc])%-", b="%1ا%2ل%3"}, --p
    -- al- + initial unstable hamza
    {a="^(a)l%-(\"?[uai])", b="ا%1ل%2ٱ"},
    {a="([%(%[%|%<%s%-o])(a)l%-(\"?[uai])", b="%1ا%2ل%3ٱ"}, --p
@@ -378,15 +382,23 @@ trigraphsfv = { -- trigraphs or more
    -- art. with waṣla + lām
    {a="'l%-(l)", b="ٱل%1%1"},
    -- art. with waṣla + solar consonant
-   {a="'l%-([%_%^%.]?[tdrzsn])", b="ٱل%1%1"},
+   -- ('c' and '^n' are additional characters)
+   {a="'l%-(%^n)", b="ٱل%1"}, -- ^n is lunar
+   {a="'l%-([%_%^%.]?[tdrzsnc])", b="ٱل%1%1"},
    -- li-/la- + art. + lām
    {a="l([ai])%-l%-(l)", b="ل%1%2%2"},
    -- assim. art. with waṣla + solar consonant
-   {a="'([%_%^%.]?[tdrzsn])%-", b="ٱل%1"},
+   -- ('c' and '^n' are additional characters)
+   {a="'(%^n)%-", b="ٱل"}, -- ^n is lunar
+   {a="'([%_%^%.]?[tdrzsnc])%-", b="ٱل%1"},
    -- li-/la- + art. + solar consonant is a special orthography
-   {a="l([ai])%-l%-([%_%^%.]?[tdrzsn])", b="ل%1ل%2%2"},
+   -- ('c' and '^n' are additional characters)
+   {a="l([ai])%-l%-(%^n)", b="ل%1ل%2"}, -- ^n is lunar
+   {a="l([ai])%-l%-([%_%^%.]?[tdrzsnc])", b="ل%1ل%2%2"},
    -- li-/la- + assim. art. + solar consonant is a special orthography
-   {a="l([ai])%-([%_%^%.]?[tdrzsn])%-([%_%^%.]?[tdrzsn])", b="ل%1ل%3%3"},
+   -- ('c' and '^n' are additional characters)
+   {a="l([ai])%-(%^n)%-(%^n)", b="ل%1ل%3"}, -- ^n is lunar
+   {a="l([ai])%-([%_%^%.]?[tdrzsnc])%-([%_%^%.]?[tdrzsnc])", b="ل%1ل%3%3"},
    -- art. with waṣla + initial unstable hamza
    {a="'l%-(\"?[uai])", b="ٱل%1ٱ"},
    -- art. with waṣla + lunar consonant (i.e. what remains)
@@ -423,12 +435,16 @@ trigraphsfveasy = { -- trigraphs or more (see 'easy' tag below for the diffs)
    -- al- + lām
    {a="^(a)l%-(l)", b="ا%1ل%2%2"},
    {a="([%(%[%|%<%s%-o])(a)l%-(l)", b="%1ا%2ل%3%3"}, --p
-   -- al- + solar consonant
-   {a="^(a)l%-([%_%^%.]?[tdrzsn])", b="ا%1ل%2%2"},
-   {a="([%(%[%|%<%s%-o])(a)l%-([%_%^%.]?[tdrzsn])", b="%1ا%2ل%3%3"}, --p
-   -- assim. art. + solar consonant
-   {a="^(a)([%_%^%.]?[tdrzsn])%-", b="ا%1ل%2"},
-   {a="([%(%[%|%<%s%-o])(a)([%_%^%.]?[tdrzsn])%-", b="%1ا%2ل%3"}, --p
+   -- al- + solar consonant ('c' and '^n' are additional characters)
+   {a="^(a)l%-(%^n)", b="ا%1ل%2"}, -- ^n is lunar
+   {a="([%(%[%|%<%s%-o])(a)l%-(%^n)", b="%1ا%2ل%3"}, -- ^n is lunar --p
+   {a="^(a)l%-([%_%^%.]?[tdrzsnc])", b="ا%1ل%2%2"},
+   {a="([%(%[%|%<%s%-o])(a)l%-([%_%^%.]?[tdrzsnc])", b="%1ا%2ل%3%3"}, --p
+   -- assim. art. + solar consonant ('c' and '^n' are additional characters)
+   {a="^(a)(%^n)%-", b="ا%1ل"}, -- ^n is lunar
+   {a="([%(%[%|%<%s%-o])(a)(%^n)%-", b="%1ا%2ل"}, -- ^n is lunar --p
+   {a="^(a)([%_%^%.]?[tdrzsnc])%-", b="ا%1ل%2"},
+   {a="([%(%[%|%<%s%-o])(a)([%_%^%.]?[tdrzsnc])%-", b="%1ا%2ل%3"}, --p
    -- al- + initial unstable hamza
    {a="^(a)l%-(\"?[uai])", b="ا%1ل%2ٱ"},
    {a="([%(%[%|%<%s%-o])(a)l%-(\"?[uai])", b="%1ا%2ل%3ٱ"}, --p
@@ -447,15 +463,23 @@ trigraphsfveasy = { -- trigraphs or more (see 'easy' tag below for the diffs)
    -- art. with waṣla + lām
    {a="'l%-(l)", b="ٱل%1%1"},
    -- art. with waṣla + solar consonant
-   {a="'l%-([%_%^%.]?[tdrzsn])", b="ٱل%1%1"},
+   -- ('c' and '^n' are additional characters)
+   {a="'l%-(%^n)", b="ٱل%1"}, -- ^n is lunar
+   {a="'l%-([%_%^%.]?[tdrzsnc])", b="ٱل%1%1"},
    -- li-/la- + art. + lām
    {a="l([ai])%-l%-(l)", b="ل%1%2%2"},
    -- assim. art. with waṣla + solar consonant
-   {a="'([%_%^%.]?[tdrzsn])%-", b="ٱل%1"},
+   -- ('c' and '^n' are is an additional characters)
+   {a="'(%^n)%-", b="ٱل"}, -- ^n is lunar
+   {a="'([%_%^%.]?[tdrzsnc])%-", b="ٱل%1"},
    -- li-/la- + art. + solar consonant is a special orthography
-   {a="l([ai])%-l%-([%_%^%.]?[tdrzsn])", b="ل%1ل%2%2"},
+   -- ('c' and '^n' are additional characters)
+   {a="l([ai])%-l%-(%^n)", b="ل%1ل%2"}, -- ^n is lunar
+   {a="l([ai])%-l%-([%_%^%.]?[tdrzsnc])", b="ل%1ل%2%2"},
    -- li-/la- + assim. art. + solar consonant is a special orthography
-   {a="l([ai])%-([%_%^%.]?[tdrzsn])%-([%_%^%.]?[tdrzsn])", b="ل%1ل%3%3"},
+   -- ('c and '^n' are additional characters)
+   {a="l([ai])%-(%^n)%-(%^n)", b="ل%1ل%3"}, -- ^n is lunar
+   {a="l([ai])%-([%_%^%.]?[tdrzsnc])%-([%_%^%.]?[tdrzsnc])", b="ل%1ل%3%3"},
    -- art. with waṣla + initial unstable hamza
    {a="'l%-(\"?[uai])", b="ٱل%1ٱ"},   
    -- art. with waṣla + lunar consonant (i.e. what remains)
@@ -511,6 +535,8 @@ digraphsfvidgham = {
    {a="bb", b="بّ"},
    {a="BB", b="ـّ"},
    {a="([%_%^%.])([tghdsz])([tghdsz])", b="%1%2|%3"},
+   -- same as above for additional characters:
+   {a="([%_%^%.])([cn])([cn])", b="%1%2|%3"},
    {a="tt", b="تّ"},
    {a="%_t%_t", b="ثّ"},
    {a="jj", b="جّ"},
@@ -539,6 +565,14 @@ digraphsfvidgham = {
    {a="hh", b="هّ"},
    {a="ww", b="وّ"},
    {a="yy", b="يّ"},
+   -- additional characters + šaddah (begin)
+   {a="pp", b="پّ"},
+   {a="vv", b="ڤّ"},
+   {a="gg", b="گّ"},
+   {a="%^c%^c", b="چّ"},
+   {a="%^z%^z", b="ژّ"},
+   {a="%^n%^n", b="ڭّ"},
+   -- additional characters + šaddah (end)
    -- sukūn begin
    -- first, take out hyphen if any:
    {a="([%_%^%.]?[Bbtjghxdrzs%`fqklmnwy])%-([uaiUAI])", b="%1%2"},
@@ -565,6 +599,11 @@ digraphsfvidgham = {
    {a="%.t", b="ط"},
    {a="%.z", b="ظ"},
    {a="%.g", b="غ"},
+   -- additional characters (begin)
+   {a="%^c", b="چ"},
+   {a="%^z", b="ژ"},
+   {a="%^n", b="ڭ"},
+   -- additional characters (end)
    {a="(U)(A)", b="%1ا"},
    {a="WA", b="وْا"},
    {a="(a)W\"", b="%1وا"},
@@ -619,6 +658,8 @@ digraphsfv = {
    {a="bb", b="بّ"},
    {a="BB", b="ـّ"},
    {a="([%_%^%.])([tghdsz])([tghdsz])", b="%1%2|%3"},
+   -- same as above for additional characters:
+   {a="([%_%^%.])([cn])([cn])", b="%1%2|%3"},
    {a="tt", b="تّ"},
    {a="%_t%_t", b="ثّ"},
    {a="jj", b="جّ"},
@@ -647,6 +688,14 @@ digraphsfv = {
    {a="hh", b="هّ"},
    {a="ww", b="وّ"},
    {a="yy", b="يّ"},
+   -- additional characters + šaddah (begin)
+   {a="pp", b="پّ"},
+   {a="vv", b="ڤّ"},
+   {a="gg", b="گّ"},
+   {a="%^c%^c", b="چّ"},
+   {a="%^z%^z", b="ژّ"},
+   {a="%^n%^n", b="ڭّ"},
+   -- additional characters + šaddah (end)
    -- sukūn begin
    -- first, take out hyphen if any:
    {a="([%_%^%.]?[Bbtjghxdrzs%`fqklmnwy])%-([uaiUAI])", b="%1%2"},
@@ -673,6 +722,11 @@ digraphsfv = {
    {a="%.t", b="ط"},
    {a="%.z", b="ظ"},
    {a="%.g", b="غ"},
+   -- additional characters (begin)
+   {a="%^c", b="چ"},
+   {a="%^z", b="ژ"},
+   {a="%^n", b="ڭ"},
+   -- additional characters (end)
    {a="(U)(A)", b="%1ا"},
    {a="WA", b="وْا"},
    {a="(a)W\"", b="%1وا"},
@@ -727,6 +781,8 @@ digraphsfveasy = { -- see the differences under 'easy' marker below
    {a="bb", b="بّ"},
    {a="BB", b="ـّ"},
    {a="([%_%^%.])([tghdsz])([tghdsz])", b="%1%2|%3"},
+   -- same as above for additional characters:
+   {a="([%_%^%.])([cn])([cn])", b="%1%2|%3"},
    {a="tt", b="تّ"},
    {a="%_t%_t", b="ثّ"},
    {a="jj", b="جّ"},
@@ -755,6 +811,14 @@ digraphsfveasy = { -- see the differences under 'easy' marker below
    {a="hh", b="هّ"},
    {a="ww", b="وّ"},
    {a="yy", b="يّ"},
+   -- additional characters + šaddah (begin)
+   {a="pp", b="پّ"},
+   {a="vv", b="ڤّ"},
+   {a="gg", b="گّ"},
+   {a="%^c%^c", b="چّ"},
+   {a="%^z%^z", b="ژّ"},
+   {a="%^n%^n", b="ڭّ"},
+   -- additional characters + šaddah (end)
    -- sukūn begin ('easy' needs these rules to be taken out); but
    -- first take out every previously generated sukūn by hamza rules,
    -- so there be no need to edit them:
@@ -784,6 +848,11 @@ digraphsfveasy = { -- see the differences under 'easy' marker below
    {a="%.t", b="ط"},
    {a="%.z", b="ظ"},
    {a="%.g", b="غ"},
+   -- additional characters (begin)
+   {a="%^c", b="چ"},
+   {a="%^z", b="ژ"},
+   {a="%^n", b="ڭ"},
+   -- additional characters (end)
    {a="(U)(A)", b="%1ا"},
    {a="WA", b="وْا"},
    {a="(a)W\"", b="%1وا"},
@@ -821,6 +890,11 @@ singlefv = {
    {a="w", b="و"},
    {a="y", b="ي"},
    {a="T", b="ة"},
+   -- additional characters (begin)
+   {a="p", b="پ"},
+   {a="v", b="ڤ"},
+   {a="g", b="گ"},
+   -- additional characters (end)
    {a="\"$", b=""},
    {a="\"(%W)", b="%1"},
    {a="\"([^uaiUAI])", b="%1"},
@@ -849,6 +923,11 @@ singlefveasy = { -- see the differences under 'easy' tag below
    {a="w", b="و"},
    {a="y", b="ي"},
    {a="T", b="ة"},
+   -- additional characters (begin)
+   {a="p", b="پ"},
+   {a="v", b="ڤ"},
+   {a="g", b="گ"},
+   -- additional characters (end)
    -- easy (begin): \" needs to put back the sukūn
    {a="\"$", b="ْ"},
    {a="\"(%W)", b="ْ%1"},
diff --git a/arabluatex_novoc.lua b/arabluatex_novoc.lua
index 55eccdc..caf66f9 100644
--- a/arabluatex_novoc.lua
+++ b/arabluatex_novoc.lua
@@ -74,12 +74,16 @@ trigraphsnv = { -- trigraphs or more
    -- al- + lām
    {a="^(a)l%-(l)", b="ا%1ل%2"},
    {a="([%(%[%|%<%s%-])(a)l%-(l)", b="%1ا%2ل%3"}, --p
-   -- al- + solar consonant
-   {a="^(a)l%-([%_%^%.]?[tdrzsn])", b="ا%1ل%2"},
-   {a="([%(%[%|%<%s%-])(a)l%-([%_%^%.]?[tdrzsn])", b="%1ا%2ل%3"}, --p
-   -- assim. art. + solar consonant
-   {a="^(a)([%_%^%.]?[tdrzsn])%-", b="ا%1ل"},
-   {a="([%(%[%|%<%s%-])(a)([%_%^%.]?[tdrzsn])%-", b="%1ا%2ل"}, --p
+   -- al- + solar consonant ('c' and '^n' are additional characters)
+   {a="^(a)l%-(%^n)", b="ا%1ل%2"}, -- ^n is lunar
+   {a="([%(%[%|%<%s%-])(a)l%-(%^n)", b="%1ا%2ل%3"}, -- ^n is lunar --p   
+   {a="^(a)l%-([%_%^%.]?[tdrzsnc])", b="ا%1ل%2"},
+   {a="([%(%[%|%<%s%-])(a)l%-([%_%^%.]?[tdrzsnc])", b="%1ا%2ل%3"}, --p
+   -- assim. art. + solar consonant ('c' and '^n' are additional characters)
+   {a="^(a)(%^n)%-", b="ا%1ل"}, -- ^n is lunar
+   {a="([%(%[%|%<%s%-])(a)(%^n)%-", b="%1ا%2ل"}, -- ^n is lunar --p
+   {a="^(a)([%_%^%.]?[tdrzsnc])%-", b="ا%1ل"},
+   {a="([%(%[%|%<%s%-])(a)([%_%^%.]?[tdrzsnc])%-", b="%1ا%2ل"}, --p
    -- al- + initial unstable hamza
    {a="^(a)l%-(\")([uai])", b="ا%1لٱ%3"},
    {a="([%(%[%|%<%s%-])(a)l%-(\")([uai])", b="%1ا%2لٱ%4"}, --p
@@ -94,15 +98,23 @@ trigraphsnv = { -- trigraphs or more
    -- art. with waṣla + lām
    {a="'l%-(l)", b="ال%1"},
    -- art. with waṣla + solar consonant
-   {a="'l%-([%_%^%.]?[tdrzsn])", b="ال%1"},
+   -- ('c' and '^n' are additional characters)
+   {a="'l%-(%^n)", b="ال%1"}, -- ^n is lunar
+   {a="'l%-([%_%^%.]?[tdrzsnc])", b="ال%1"},
    -- li-/la- + art. + lām
    {a="l([ai])%-l%-(l)", b="ل%1%2"},
    -- assim. art. with waṣla + solar consonant
-   {a="'([%_%^%.]?[tdrzsn])%-", b="ال"},
+   -- ('c' and '^n' are additional characters)
+   {a="'(%^n)%-", b="ال"}, -- ^n is lunar
+   {a="'([%_%^%.]?[tdrzsnc])%-", b="ال"},
    -- li-/la- + art. + solar consonant is a special orthography
-   {a="l([ai])%-l%-([%_%^%.]?[tdrzsn])", b="ل%1ل%2"},
+   -- ('c' and '^n' are additional characters)
+   {a="l([ai])%-l%-(%^n)", b="ل%1ل%2"}, -- ^n is lunar
+   {a="l([ai])%-l%-([%_%^%.]?[tdrzsnc])", b="ل%1ل%2"},
    -- li-/la + assim. art. + solar consonant is a special orthography
-   {a="l([ai])%-([%_%^%.]?[tdrzsn])%-([%_%^%.]?[tdrzsn])", b="ل%1ل%3"},
+   -- ('c' and '^n' are additional characters)
+   {a="l([ai])%-(%^n)%-(%^n)", b="ل%1ل%3"}, -- ^n is lunar
+   {a="l([ai])%-([%_%^%.]?[tdrzsnc])%-([%_%^%.]?[tdrzsnc])", b="ل%1ل%3"},
    -- art. with waṣla + initial unstable hamza
    {a="'l%-(\")([uai])", b="الٱ%2"},
    {a="'l%-([uai])", b="الا%1"},   
diff --git a/arabluatex_trans.lua b/arabluatex_trans.lua
index 2b9fcdf..b21397d 100644
--- a/arabluatex_trans.lua
+++ b/arabluatex_trans.lua
@@ -213,12 +213,16 @@ trigraphstrdmg = { -- trigraphs or more
    -- al- + lām
    {a="^(a)l%-(l)", b="%1l-%2"},
    {a="([%(%[%|%<%s%-o])(a)l%-(l)", b="%1%2l-%3"}, --p
-   -- al- + solar consonant
-   {a="^(a)l%-([%_%^%.]?[tdrzsn])", b="%1%2-%2"},
-   {a="([%(%[%|%<%s%-o])(a)l%-([%_%^%.]?[tdrzsn])", b="%1%2%3-%3"}, --p
-   -- assim. art. + solar consonant
-   {a="^(a)([%_%^%.]?[tdrzsn])%-", b="%1%2-"},
-   {a="([%(%[%|%<%s%-o])(a)([%_%^%.]?[tdrzsn])%-", b="%1%2%3-"}, --p
+   -- al- + solar consonant ('c' and '^n' are additional characters)
+   {a="^(a)l%-(%^n)", b="%1l-%2"}, -- ^n is lunar
+   {a="([%(%[%|%<%s%-o])(a)l%-(%^n)", b="%1%2l-%3"}, --^n is lunar --p
+   {a="^(a)l%-([%_%^%.]?[tdrzsnc])", b="%1%2-%2"},
+   {a="([%(%[%|%<%s%-o])(a)l%-([%_%^%.]?[tdrzsnc])", b="%1%2%3-%3"}, --p
+   -- assim. art. + solar consonant ('c' and '^n' are additional characters)
+   {a="^(a)(%^n)%-", b="%1l-"}, -- ^n is lunar
+   {a="([%(%[%|%<%s%-o])(a)(%^n)%-", b="%1%2l-"}, --^n is lunar --p
+   {a="^(a)([%_%^%.]?[tdrzsnc])%-", b="%1%2-"},
+   {a="([%(%[%|%<%s%-o])(a)([%_%^%.]?[tdrzsnc])%-", b="%1%2%3-"}, --p
    -- al- + initial unstable hamza
    {a="^(a)l%-(\"?[uai])", b="%1l-%2"},
    {a="([%(%[%|%<%s%-o])(a)l%-(\"?[uai])", b="%1%2l-%3"}, --p
@@ -235,15 +239,23 @@ trigraphstrdmg = { -- trigraphs or more
    -- art. with waṣla + lām
    {a="'l%-(l)", b="'l-%1"},
    -- art. with waṣla + solar consonant
-   {a="'l%-([%_%^%.]?[tdrzsn])", b="'%1-%1"},
+   -- ('c' and '^n' are additional characters)
+   {a="'l%-(%^n)", b="'l-%1"}, -- ^n is lunar
+   {a="'l%-([%_%^%.]?[tdrzsnc])", b="'%1-%1"},
    -- li-/la- + art. + lām
    {a="l([ai])%-l%-(l)", b="l%1-%2%2"},
    -- assim. art. with waṣla + solar consonant
-   {a="'([%_%^%.]?[tdrzsn])%-", b="'%1-"},
+   -- ('c' and '^n' are additional characters)
+   {a="'(%^n)%-", b="'l-"}, -- ^n is lunar
+   {a="'([%_%^%.]?[tdrzsnc])%-", b="'%1-"},
    -- li-/la- + art. + solar consonant is a special orthography
-   {a="l([ai])%-l%-([%_%^%.]?[tdrzsn])", b="l%1-%2-%2"},
+   -- ('c' and '^n' are additional characters)
+   {a="l([ai])%-l%-(%^n)", b="l%1-l-%2"}, -- ^n is lunar
+   {a="l([ai])%-l%-([%_%^%.]?[tdrzsnc])", b="l%1-%2-%2"},
    -- li-/la- + assim. art. + solar consonant is a special orthography
-   {a="l([ai])%-([%_%^%.]?[tdrzsn])%-([%_%^%.]?[tdrzsn])", b="l%1-%2-%3"},
+   -- ('c' and '^n' are additional characters)
+   {a="l([ai])%-(%^n)%-(%^n)", b="l%1-l-%3"}, -- ^n is lunar
+   {a="l([ai])%-([%_%^%.]?[tdrzsnc])%-([%_%^%.]?[tdrzsnc])", b="l%1-%2-%3"},
    -- art. with waṣla + initial unstable hamza
    {a="'l%-(\"?[uai])", b="'l-%1"},
    -- art. with waṣla + lunar consonant (i.e. what remains)
@@ -353,6 +365,11 @@ digraphstrdmg = {
    {a="%.t", b="ṭ"},
    {a="%.z", b="ẓ"},
    {a="%.g", b="ġ"},
+   -- additional characters (begin)
+   {a="%^c", b="č"},
+   {a="%^z", b="ž"},
+   {a="%^n", b="g"},
+   -- additional characters (end)
    -- the following needs to be moved above shortening rules
 --   {a="(U)(A)", b="ū"},
    {a="WA", b="w"},
@@ -389,6 +406,11 @@ singletrdmg = {
    {a="w", b="w"},
    {a="y", b="y"},
    {a="T", b="t"},
+   -- additional characters (begin)
+   {a="p", b="p"},
+   {a="v", b="v"},
+   {a="g", b="g"}, -- for ^n → g see above
+   -- additional characters (end)
    {a="\"", b=""},
    {a="B", b=""}
 }
@@ -495,12 +517,16 @@ trigraphstrloc = { -- trigraphs or more
    -- al- + lām
    {a="^(a)l%-(l)", b="%1l-%2"},
    {a="(%s)(a)l%-(l)", b="%1%2l-%3"},
-   -- al- + solar consonant
-   {a="^(a)l%-([%_%^%.]?[tdrzsn])", b="%1l-%2"},
-   {a="(%s)(a)l%-([%_%^%.]?[tdrzsn])", b="%1%2l-%3"},
-   -- assim. art. + solar consonant
-   {a="^(a)([%_%^%.]?[tdrzsn])%-", b="%1l-"},
-   {a="(%s)(a)([%_%^%.]?[tdrzsn])%-", b="%1%2l-"},
+   -- al- + solar consonant ('c' and '^n' are additional characters)
+   {a="^(a)l%-(%^n)", b="%1l-%2"}, -- ^n is lunar
+   {a="(%s)(a)l%-(%^n)", b="%1%2l-%3"}, -- ^n is lunar
+   {a="^(a)l%-([%_%^%.]?[tdrzsnc])", b="%1l-%2"},
+   {a="(%s)(a)l%-([%_%^%.]?[tdrzsnc])", b="%1%2l-%3"},
+   -- assim. art. + solar consonant ('c' and '^n' are additional characters)
+   {a="^(a)(%^n)%-", b="%1l-"}, -- ^n is lunar
+   {a="(%s)(a)(%^n)%-", b="%1%2l-"}, -- ^n is lunar
+   {a="^(a)([%_%^%.]?[tdrzsnc])%-", b="%1l-"},
+   {a="(%s)(a)([%_%^%.]?[tdrzsnc])%-", b="%1%2l-"},
    -- al- + initial unstable hamza
    {a="^(a)l%-([uai])", b="%1l-%2"},
    {a="(%s)(a)l%-([uai])", b="%1%2l-%3"},
@@ -512,15 +538,23 @@ trigraphstrloc = { -- trigraphs or more
    -- art. with waṣla + lām
    {a="'l%-(l)", b="al-%1"},
    -- art. with waṣla + solar consonant
-   {a="'l%-([%_%^%.]?[tdrzsn])", b="al-%1"},
+   -- ('c' and '^n' are additional characters)
+   {a="'l%-(%^n)", b="al-%1"}, -- ^n is lunar
+   {a="'l%-([%_%^%.]?[tdrzsnc])", b="al-%1"},
    -- li-/la- + art. + lām
    {a="l([ai])%-l%-(l)", b="l%1-l-%2"},
    -- assim. art. with waṣla + solar consonant
-   {a="'([%_%^%.]?[tdrzsn])%-", b="al-"},
+   -- ('c' and '^n' are additional characters)
+   {a="'(%^n)%-", b="al-"}, -- ^n is lunar
+   {a="'([%_%^%.]?[tdrzsnc])%-", b="al-"},
    -- li-/la- + art. + solar consonant is a special orthography
-   {a="l([ai])%-l%-([%_%^%.]?[tdrzsn])", b="l%1-l-%2"},
+   -- ('c' and '^n' are additional characters)
+   {a="l([ai])%-l%-(%^n)", b="l%1-l-%2"}, -- ^n is lunar
+   {a="l([ai])%-l%-([%_%^%.]?[tdrzsnc])", b="l%1-l-%2"},
    -- li-/la- + assim. art. + solar consonant is a special orthography
-   {a="l([ai])%-([%_%^%.]?[tdrzsn])%-([%_%^%.]?[tdrzsn])", b="l%1-l-%3"},
+   -- ('c' and '^n' are additional characters)
+   {a="l([ai])%-(%^n)%-(%^n)", b="l%1-l-%3"}, -- ^n is lunar
+   {a="l([ai])%-([%_%^%.]?[tdrzsnc])%-([%_%^%.]?[tdrzsnc])", b="l%1-l-%3"},
    -- art. with waṣla + initial unstable hamza
    {a="'l%-([uai])", b="al-%1"},   
    -- art. with waṣla + lunar consonant (i.e. what remains)
@@ -576,6 +610,11 @@ digraphstrloc = {
    {a="%.t", b="ṭ"},
    {a="%.z", b="ẓ"},
    {a="%.g", b="gh"},
+   -- additional characters (begin)
+   {a="%^c", b="ch"},
+   {a="%^z", b="zh"},
+   {a="%^n", b="ñ"},
+   -- additional characters (end)
    {a="(U)(A)", b="ū"},
    {a="WA", b="w"},
    {a="(a)W", b="%1w"},
@@ -611,6 +650,11 @@ singletrloc = {
    {a="w", b="w"},
    {a="y", b="y"},
    {a="T", b="t"},
+   -- additional characters (begin)
+   {a="p", b="p"},
+   {a="v", b="v"},
+   {a="g", b="g"},
+   -- additional characters (end)
    {a="\"", b=""},
    {a="B", b=""}
 }
@@ -709,12 +753,16 @@ trigraphstrarabica = { -- trigraphs or more
    -- al- + lām
    {a="^(a)l%-(l)", b="%1l-%2"},
    {a="(%s)(a)l%-(l)", b="%1%2l-%3"},
-   -- al- + solar consonant
-   {a="^(a)l%-([%_%^%.]?[tdrzsn])", b="%1l-%2"},
-   {a="(%s)(a)l%-([%_%^%.]?[tdrzsn])", b="%1%2l-%3"},
-   -- assim. art. + solar consonant
-   {a="^(a)([%_%^%.]?[tdrzsn])%-", b="%1l-"},
-   {a="(%s)(a)([%_%^%.]?[tdrzsn])%-", b="%1%2l-"},
+   -- al- + solar consonant ('c' and '^n' are additional characters)
+   {a="^(a)l%-(%^n)", b="%1l-%2"}, -- ^n is lunar
+   {a="(%s)(a)l%-(%^n)", b="%1%2l-%3"}, -- ^n is lunar
+   {a="^(a)l%-([%_%^%.]?[tdrzsnc])", b="%1l-%2"},
+   {a="(%s)(a)l%-([%_%^%.]?[tdrzsnc])", b="%1%2l-%3"},
+   -- assim. art. + solar consonant ('c' and '^n' are additional characters)
+   {a="^(a)(%^n)%-", b="%1l-"}, -- ^n is lunar
+   {a="(%s)(a)(%^n)%-", b="%1%2l-"}, -- ^n is lunar
+   {a="^(a)([%_%^%.]?[tdrzsnc])%-", b="%1l-"},
+   {a="(%s)(a)([%_%^%.]?[tdrzsnc])%-", b="%1%2l-"},
    -- al- + initial unstable hamza
    {a="^(a)l%-([uai])", b="%1l-%2"},
    {a="(%s)(a)l%-([uai])", b="%1%2l-%3"},
@@ -726,15 +774,23 @@ trigraphstrarabica = { -- trigraphs or more
    -- art. with waṣla + lām
    {a="'l%-(l)", b="l-%1"},
    -- art. with waṣla + solar consonant
-   {a="'l%-([%_%^%.]?[tdrzsn])", b="l-%1"},
+   -- ('c' and '^n' are additional characters)
+   {a="'l%-(%^n)", b="l-%1"}, -- ^n is lunar
+   {a="'l%-([%_%^%.]?[tdrzsnc])", b="l-%1"},
    -- li-/la- + art. + lām
    {a="l([ai])%-l%-(l)", b="l%1-l-%2"},
    -- assim. art. with waṣla + solar consonant
-   {a="'([%_%^%.]?[tdrzsn])%-", b="l-"},
+   -- ('c' and '^n' are additional characters)
+   {a="'(%^n)%-", b="l-"}, -- ^n is lunar
+   {a="'([%_%^%.]?[tdrzsnc])%-", b="l-"},
    -- li-/la- + art. + solar consonant is a special orthography
-   {a="l([ai])%-l%-([%_%^%.]?[tdrzsn])", b="l%1-l-%2"},
+   -- ('c' and '^n' are additional characters)
+   {a="l([ai])%-l%-(%^n)", b="l%1-l-%2"}, -- ^n is lunar
+   {a="l([ai])%-l%-([%_%^%.]?[tdrzsnc])", b="l%1-l-%2"},
    -- li-/la- + assim. art. + solar consonant is a special orthography
-   {a="l([ai])%-([%_%^%.]?[tdrzsn])%-([%_%^%.]?[tdrzsn])", b="l%1-l-%3"},
+   -- ('c' and '^n' are additional characters)
+   {a="l([ai])%-(%^n)%-(%^n)", b="l%1-l-%3"}, -- ^n is lunar
+   {a="l([ai])%-([%_%^%.]?[tdrzsnc])%-([%_%^%.]?[tdrzsnc])", b="l%1-l-%3"},
    -- art. with waṣla + initial unstable hamza
    {a="'l%-([uai])", b="l-%1"},   
    -- art. with waṣla + lunar consonant (i.e. what remains)
@@ -790,6 +846,11 @@ digraphstrarabica = {
    {a="%.t", b="ṭ"},
    {a="%.z", b="ẓ"},
    {a="%.g", b="ġ"},
+   -- additional characters (begin)
+   {a="%^c", b="č"},
+   {a="%^z", b="ž"},
+   {a="%^n", b="g"},
+   -- additional characters (end)
    {a="(U)(A)", b="ū"},
    {a="WA", b="w"},
    {a="(a)W", b="%1w"},
@@ -825,6 +886,11 @@ singletrarabica = {
    {a="w", b="w"},
    {a="y", b="y"},
    {a="T", b="t"},
+   -- additional characters (begin)
+   {a="p", b="p"},
+   {a="v", b="v"},
+   {a="g", b="g"}, -- for ^n → g see above
+   -- additional characters (end)
    {a="\"", b=""},
    {a="B", b=""}
 }
diff --git a/arabluatex_voc.lua b/arabluatex_voc.lua
index 073b23f..6c63a88 100644
--- a/arabluatex_voc.lua
+++ b/arabluatex_voc.lua
@@ -471,12 +471,16 @@ trigraphs = { -- trigraphs or more
    -- al- + lām
    {a="^(a)l%-(l)", b="ا%1ل%2%2"},
    {a="([%(%[%|%<%s%-o])(a)l%-(l)", b="%1ا%2ل%3%3"}, --p
-   -- al- + solar consonant
-   {a="^(a)l%-([%_%^%.]?[tdrzsn])", b="ا%1ل%2%2"},
-   {a="([%(%[%|%<%s%-o])(a)l%-([%_%^%.]?[tdrzsn])", b="%1ا%2ل%3%3"}, --p
-   -- assim. art. + solar consonant
-   {a="^(a)([%_%^%.]?[tdrzsn])%-", b="ا%1ل%2"},
-   {a="([%(%[%|%<%s%-o])(a)([%_%^%.]?[tdrzsn])%-", b="%1ا%2ل%3"}, --p
+   -- al- + solar consonant ('c' and '^n' are additional characters)
+   {a="^(a)l%-(%^n)", b="ا%1ل%2"}, -- ^n is lunar
+   {a="([%(%[%|%<%s%-o])(a)l%-(%^n)", b="%1ا%2ل%3"},-- ^n is lunar --p
+   {a="^(a)l%-([%_%^%.]?[tdrzsnc])", b="ا%1ل%2%2"},
+   {a="([%(%[%|%<%s%-o])(a)l%-([%_%^%.]?[tdrzsnc])", b="%1ا%2ل%3%3"}, --p
+   -- assim. art. + solar consonant ('c' and '^n' are additional characters)
+   {a="^(a)(%^n)%-", b="ا%1ل"}, -- ^n is lunar
+   {a="([%(%[%|%<%s%-o])(a)(%^n)%-", b="%1ا%2ل"},-- ^n is lunar --p
+   {a="^(a)([%_%^%.]?[tdrzsnc])%-", b="ا%1ل%2"},
+   {a="([%(%[%|%<%s%-o])(a)([%_%^%.]?[tdrzsnc])%-", b="%1ا%2ل%3"}, --p
    -- al- + initial unstable hamza
    {a="^(a)l%-(\")([uai])", b="ا%1ل%3ٱ"},
    {a="([%(%[%|%<%s%-o])(a)l%-(\")([uai])", b="%1ا%2ل%4ٱ"}, --p
@@ -498,15 +502,23 @@ trigraphs = { -- trigraphs or more
    -- art. with waṣla + lām
    {a="'l%-(l)", b="ال%1%1"},
    -- art. with waṣla + solar consonant
-   {a="'l%-([%_%^%.]?[tdrzsn])", b="ال%1%1"},
+   -- ('c' and '^n' are additional characters)
+   {a="'l%-(%^n)", b="ال%1"}, -- ^n is lunar
+   {a="'l%-([%_%^%.]?[tdrzsnc])", b="ال%1%1"},
    -- li-/la- + art. + lām
    {a="l([ai])%-l%-(l)", b="ل%1%2%2"},
-   -- assim. art. with waṣla + solar consonant
-   {a="'([%_%^%.]?[tdrzsn])%-", b="ال%1"},
+   -- assim. art. with waṣla + solar consonant ('c' and '^n' are
+   -- additional characters)   
+   {a="'(%^n)%-", b="ال"}, -- ^n is lunar
+   {a="'([%_%^%.]?[tdrzsnc])%-", b="ال%1"},
    -- li-/la- + art. + solar consonant is a special orthography
-   {a="l([ai])%-l%-([%_%^%.]?[tdrzsn])", b="ل%1ل%2%2"},
+   -- ('c' and '^n' are additional characters)
+   {a="l([ai])%-l%-(%^n)", b="ل%1ل%2"}, -- '^n' is lunar
+   {a="l([ai])%-l%-([%_%^%.]?[tdrzsnc])", b="ل%1ل%2%2"},
    -- li-/la + assim. art. + solar consonant is a special orthography
-   {a="l([ai])%-([%_%^%.]?[tdrzsn])%-([%_%^%.]?[tdrzsn])", b="ل%1ل%3%3"},
+   -- ('c' and '^n' are additional characters)
+   {a="l([ai])%-(%^n)%-(%^n)", b="ل%1ل%3"}, -- ^n is lunar
+   {a="l([ai])%-([%_%^%.]?[tdrzsnc])%-([%_%^%.]?[tdrzsnc])", b="ل%1ل%3%3"},
    -- art. with waṣla + initial unstable hamza
    {a="'l%-(\")([uai])", b="ال%2ٱ"},
    {a="'l%-([uai])", b="ال%1ا"},   
@@ -549,12 +561,17 @@ trigraphseasy = { -- differences marked below with 'easy'
    -- al- + lām (easy)
    {a="^(a)l%-(l)", b="ا%1ل%2"},
    {a="([%(%[%|%<%s%-o])(a)l%-(l)", b="%1ا%2ل%3"}, --p
-   -- al- + solar consonant (easy)
-   {a="^(a)l%-([%_%^%.]?[tdrzsn])", b="ا%1ل%2"},
-   {a="([%(%[%|%<%s%-o])(a)l%-([%_%^%.]?[tdrzsn])", b="%1ا%2ل%3"}, --p
-   -- assim. art. + solar consonant (easy)
-   {a="^(a)([%_%^%.]?[tdrzsn])%-", b="ا%1ل"},
-   {a="([%(%[%|%<%s%-o])(a)([%_%^%.]?[tdrzsn])%-", b="%1ا%2ل"}, --p
+   -- al- + solar consonant (easy) ('c' and '^n' are additional characters)
+   {a="^(a)l%-(%^n)", b="ا%1ل%2"}, -- ^n is lunar
+   {a="([%(%[%|%<%s%-o])(a)l%-(%^n)", b="%1ا%2ل%3"}, -- ^n is lunar --p
+   {a="^(a)l%-([%_%^%.]?[tdrzsnc])", b="ا%1ل%2"},
+   {a="([%(%[%|%<%s%-o])(a)l%-([%_%^%.]?[tdrzsnc])", b="%1ا%2ل%3"}, --p
+   -- assim. art. + solar consonant (easy) ('c' and '^n' are
+   -- additional characters)
+   {a="^(a)(%^n)%-", b="ا%1ل"}, -- ^n is lunar
+   {a="([%(%[%|%<%s%-o])(a)(%^n)%-", b="%1ا%2ل"}, -- ^n is lunar --p
+   {a="^(a)([%_%^%.]?[tdrzsnc])%-", b="ا%1ل"},
+   {a="([%(%[%|%<%s%-o])(a)([%_%^%.]?[tdrzsnc])%-", b="%1ا%2ل"}, --p
    -- al- + initial unstable hamza
    {a="^(a)l%-(\")([uai])", b="ا%1ل%3ٱ"},
    {a="([%(%[%|%<%s%-o])(a)l%-(\")([uai])", b="%1ا%2ل%4ٱ"}, --p
@@ -576,15 +593,23 @@ trigraphseasy = { -- differences marked below with 'easy'
    -- art. with waṣla + lām (easy)
    {a="'l%-(l)", b="ال%1"},
    -- art. with waṣla + solar consonant (easy)
-   {a="'l%-([%_%^%.]?[tdrzsn])", b="ال%1"},
+   -- ('c' and '^n' are additional characters)
+   {a="'l%-(%^n)", b="ال%1"}, -- ^n is lunar
+   {a="'l%-([%_%^%.]?[tdrzsnc])", b="ال%1"},
    -- li-/la- + art. + lām (easy)
    {a="l([ai])%-l%-(l)", b="ل%1%2"},
    -- assim. art. with waṣla + solar consonant (easy)
-   {a="'([%_%^%.]?[tdrzsn])%-", b="ال"},
+   -- ('c' and '^n' are additional characters)
+   {a="'(%^n)%-", b="ال"}, -- ^n is lunar
+   {a="'([%_%^%.]?[tdrzsnc])%-", b="ال"},
    -- li-/la- + art. + solar consonant is a special orthography (easy)
-   {a="l([ai])%-l%-([%_%^%.]?[tdrzsn])", b="ل%1ل%2"},
+   -- ('c' and '^n' are additional characters)
+   {a="l([ai])%-l%-(%^n)", b="ل%1ل%2"}, -- ^n is lunar
+   {a="l([ai])%-l%-([%_%^%.]?[tdrzsnc])", b="ل%1ل%2"},
    -- li-/la + assim. art. + solar consonant is a special orthography (easy)
-   {a="l([ai])%-([%_%^%.]?[tdrzsn])%-([%_%^%.]?[tdrzsn])", b="ل%1ل%3"},
+   -- ('c' and '^n' are additional characters)
+   {a="l([ai])%-(%^n)%-(%^n)", b="ل%1ل%3"}, -- ^n is lunar
+   {a="l([ai])%-([%_%^%.]?[tdrzsnc])%-([%_%^%.]?[tdrzsnc])", b="ل%1ل%3"},
    -- art. with waṣla + initial unstable hamza
    {a="'l%-(\")([uai])", b="ال%2ٱ"},
    {a="'l%-([uai])", b="ال%1ا"},
@@ -640,6 +665,8 @@ digraphs = {
    {a="bb", b="بّ"},
    {a="BB", b="ـّ"},
    {a="([%_%^%.])([tghdsz])([tghdsz])", b="%1%2|%3"},
+   -- same as above for additional characters:
+   {a="([%_%^%.])([cn])([cn])", b="%1%2|%3"},
    {a="tt", b="تّ"},
    {a="%_t%_t", b="ثّ"},
    {a="jj", b="جّ"},
@@ -668,6 +695,14 @@ digraphs = {
    {a="hh", b="هّ"},
    {a="ww", b="وّ"},
    {a="yy", b="يّ"},
+   -- additional characters + šaddah (begin)
+   {a="pp", b="پّ"},
+   {a="vv", b="ڤّ"},
+   {a="gg", b="گّ"},
+   {a="%^c%^c", b="چّ"},
+   {a="%^z%^z", b="ژّ"},
+   {a="%^n%^n", b="ڭّ"},
+   -- additional characters + šaddah (end)
    {a="_t", b="ث"},
    {a="%^g", b="ج"},
    {a="%.h", b="ح"},
@@ -679,6 +714,11 @@ digraphs = {
    {a="%.t", b="ط"},
    {a="%.z", b="ظ"},
    {a="%.g", b="غ"},
+   -- additional characters (begin)
+   {a="%^c", b="چ"},
+   {a="%^z", b="ژ"},
+   {a="%^n", b="ڭ"},
+   -- additional characters (end)
    {a="(U)(A)", b="%1ا"},
    {a="WA", b="وا"},
    {a="(a)W\"", b="%1وْا"},
@@ -716,6 +756,11 @@ single = {
    {a="w", b="و"},
    {a="y", b="ي"},
    {a="T", b="ة"},
+   -- additional characters (begin)
+   {a="p", b="پ"},
+   {a="v", b="ڤ"},
+   {a="g", b="گ"},
+   -- additional characters (end)
    {a="\"$", b="ْ"},
    {a="\"(%W)", b="ْ%1"},
    {a="\"([^uaiUAI])", b="ْ%1"},