use H to encode the tāʾ marbūtah devoid of diacritical points

1 files changed, 47 insertions, 42 deletions

diff --git a/arabluatex_trans.lua b/arabluatex_trans.lua
index c5c0b05..8791b62 100644
--- a/arabluatex_trans.lua
+++ b/arabluatex_trans.lua
@@ -301,41 +301,41 @@ tanwintrdmg = {
    {a="%-?(uN)(O)(['][%_%^%.]?[l'btjghxdrzs`fqkmnwy]%-)([%S]-O)", b="\\arbup{uni}"},
    {a="%-?(aN)(_A)(O)(['][%_%^%.]?[l'btjghxdrzs`fqkmnwy]%-)([%S]-O)", b="ạ\\arbup{ni}"},
    {a="%-?(aN)(Y)(O)(['][%_%^%.]?[l'btjghxdrzs`fqkmnwy]%-)([%S]-O)", b="ạ\\arbup{ni}"},
-   {a="(T)%-?(aN)(O)(['][%_%^%.]?[l'btjghxdrzs`fqkmnwy]%-)([%S]-O)", b="t\\arbup{ani}"},
-   {a="([^TA])%-?(aN)(O)(['][%_%^%.]?[l'btjghxdrzs`fqkmnwy]%-)([%S]-O)", b="%1\\arbup{ani}"},
+   {a="([TH])%-?(aN)(O)(['][%_%^%.]?[l'btjghxdrzs`fqkmnwy]%-)([%S]-O)", b="t\\arbup{ani}"},
+   {a="([^TAH])%-?(aN)(O)(['][%_%^%.]?[l'btjghxdrzs`fqkmnwy]%-)([%S]-O)", b="%1\\arbup{ani}"},
    {a="%-?(iN)(O)(['][%_%^%.]?[l'btjghxdrzs`fqkmnwy]%-)([%S]-O)", b="\\arbup{ini}"},
    {a="%-?(uN)(%s)(['][%_%^%.]?[l'btjghxdrzs`fqkmnwy]%-)", b="\\arbup{uni}%2%3"},
    {a="%-?(aN)(_A)(%s)(['][%_%^%.]?[l'btjghxdrzs`fqkmnwy]%-)", b="ạ\\arbup{ni}%3%4"},
    {a="%-?(aN)(Y)(%s)(['][%_%^%.]?[l'btjghxdrzs`fqkmnwy]%-)", b="ạ\\arbup{ni}%3%4"},
-   {a="(T)%-?(aN)(%s)(['][%_%^%.]?[l'btjghxdrzs`fqkmnwy]%-)", b="t\\arbup{ani}%3%4"},
-   {a="([^TA])%-?(aN)(%s)(['][%_%^%.]?[l'btjghxdrzs`fqkmnwy]%-)", b="%1\\arbup{ani}%3%4"},
+   {a="([TH])%-?(aN)(%s)(['][%_%^%.]?[l'btjghxdrzs`fqkmnwy]%-)", b="t\\arbup{ani}%3%4"},
+   {a="([^TAH])%-?(aN)(%s)(['][%_%^%.]?[l'btjghxdrzs`fqkmnwy]%-)", b="%1\\arbup{ani}%3%4"},
    {a="%-?(iN)(%s)(['][%_%^%.]?[l'btjghxdrzs`fqkmnwy]%-)", b="\\arbup{ini}%2%3"},
    -- tanwīn preceding 'lla_dI/'llatI
    {a="%-?(uN)(O)('lla[%_]?[dt])([%S]-O)", b="\\arbup{uni}"},
    {a="%-?(aN)(_A)(O)('lla[%_]?[dt])([%S]-O)", b="ạ\\arbup{ni}"},
    {a="%-?(aN)(Y)(O)('lla[%_]?[dt])([%S]-O)", b="ạ\\arbup{ni}"},
-   {a="(T)%-?(aN)(O)('lla[%_]?[dt])([%S]-O)", b="t\\arbup{ani}"},
-   {a="([^TA])%-?(aN)(O)('lla[%_]?[dt])([%S]-O)", b="%1\\arbup{ani}"},
+   {a="([TH])%-?(aN)(O)('lla[%_]?[dt])([%S]-O)", b="t\\arbup{ani}"},
+   {a="([^TAH])%-?(aN)(O)('lla[%_]?[dt])([%S]-O)", b="%1\\arbup{ani}"},
    {a="%-?(iN)(O)('lla[%_]?[dt])([%S]-O)", b="\\arbup{ini}"},
    {a="%-?(uN)(%s)('lla[%_]?[dt])", b="\\arbup{uni}%2%3"},
    {a="%-?(aN)(_A)(%s)('lla[%_]?[dt])", b="ạ\\arbup{ni}%3%4"},
    {a="%-?(aN)(Y)(%s)('lla[%_]?[dt])", b="ạ\\arbup{ni}%3%4"},
-   {a="(T)%-?(aN)(%s)('lla[%_]?[dt])", b="t\\arbup{ani}%3%4"},
-   {a="([^TA])%-?(aN)(%s)('lla[%_]?[dt])", b="%1\\arbup{ani}%3%4"},
+   {a="([TH])%-?(aN)(%s)('lla[%_]?[dt])", b="t\\arbup{ani}%3%4"},
+   {a="([^TAH])%-?(aN)(%s)('lla[%_]?[dt])", b="%1\\arbup{ani}%3%4"},
    {a="%-?(iN)(%s)('lla[%_]?[dt])", b="\\arbup{ini}%2%3"},
    -- tanwīn + alif without hamza and kasra (ibn) or dhamma (uhrub)
    {a="%-?(uN)(O)([ui])([%S]-O)", b="\\arbup{un%3}"},
    {a="%-?(aN)(_A)(O)([ui])([%S]-O)", b="ạ\\arbup{n%4}"},
    {a="%-?(aN)(Y)(O)([ui])([%S]-O)", b="ạ\\arbup{n%4}"},
-   {a="(T)%-?(aN)(O)([ui])([%S]-O)", b="t\\arbup{an%4}"},
-   {a="([^TA])%-?(aN)(O)([ui])([%S]-O)", b="%1\\arbup{an%4}"},
+   {a="([TH])%-?(aN)(O)([ui])([%S]-O)", b="t\\arbup{an%4}"},
+   {a="([^TAH])%-?(aN)(O)([ui])([%S]-O)", b="%1\\arbup{an%4}"},
    {a="%-?(iN)(O)([ui])([%S]-O)", b="\\arbup{in%3}"},
    {a="(O[%S]-)([uai]N)(O)(\"?[ui])", b="'"},
    {a="%-?(uN)(%s)([ui])", b="\\arbup{un%3}%2'"},
    {a="%-?(aN)(_A)(%s)([ui])", b="ạ\\arbup{n%4}%3'"},
    {a="%-?(aN)(Y)(%s)([ui])", b="ạ\\arbup{n%4}%3'"},
-   {a="(T)%-?(aN)(%s)([ui])", b="t\\arbup{an%4}%3'"},
-   {a="([^TA])%-?(aN)(%s)([ui])", b="%1\\arbup{an%4}%3'"},
+   {a="([TH])%-?(aN)(%s)([ui])", b="t\\arbup{an%4}%3'"},
+   {a="([^TAH])%-?(aN)(%s)([ui])", b="%1\\arbup{an%4}%3'"},
    {a="%-?(iN)(%s)([ui])", b="\\arbup{in%3}%2'"},
    --
 -- {a="uN", b="\\arbup{un}"}, (now included in the last line of this table)
@@ -343,13 +343,13 @@ tanwintrdmg = {
    -- needed by \arbcolor:
    {a="%-?(aN)(O[%S]-%_AO)", b="ạ\\arbup{n}"},
    {a="%-?(aN)(O[%S]-YO)", b="ạ\\arbup{n}"},
-   {a="(O[%S]-TO)%-?(\"?aN)", b="\\arbup{an}"},
-   {a="(O[%S]-[^TA]O)%-?(\"?aN)", b="\\arbup{an}"},
+   {a="(O[%S]-[TH]O)%-?(\"?aN)", b="\\arbup{an}"},
+   {a="(O[%S]-[^TAH]O)%-?(\"?aN)", b="\\arbup{an}"},
    --
    {a="%-?(aN)(_A)", b="ạ\\arbup{n}"},
    {a="%-?(aN)(Y)", b="ạ\\arbup{n}"},
-   {a="(T)%-?(\"?aN)", b="t\\arbup{an}"},
-   {a="([^TA])%-?(\"?aN)", b="%1\\arbup{an}"},
+   {a="([TH])%-?(\"?aN)", b="t\\arbup{an}"},
+   {a="([^TAH])%-?(\"?aN)", b="%1\\arbup{an}"},
    {a="%-?([ui])N", b="\\arbup{%1n}"}
 }
 
@@ -499,18 +499,20 @@ digraphstrdmg = {
    {a="([%_]?[Uu])(%s)([%(%[%|%<]?['][%_%^%.]?[l'btjghxdrzs`fqkmnwy][%-l])", b="u%2%3"},
    {a="([%_]?[Ii])(%s)([%(%[%|%<]?['][%_%^%.]?[l'btjghxdrzs`fqkmnwy][%-l])", b="i%2%3"},
    {a="%-%-", b=""},
-   {a="iyyaT(%p*)$", b="īyaT%1"},
-   {a="iyyaT(%p*%s)", b="īyaT%1"},
+--   {a="iyyaT(%p*)$", b="īyaT%1"}, -- previously. is now:
+   {a="iyya([TH])(%p*)$", b="īya%1%2"},
+--   {a="iyyaT(%p*%s)", b="īyaT%1"}, -- previously. is now:
+   {a="iyya([TH])(%p*%s)", b="īya%1%2"},
    {a="iyy(%p*)$", b="ī%1"},
    {a="iyy(%p*%s)", b="ī%1"},
-   --   {a="T([^uai])", b="%1"},
-   {a="T(\\arbup)", b="t%1"},
-   {a="([a%'][%_%^%.]?[tdrzsln]%-)(%S-)T([%(%[%|%<%s])(a[%_%^%.]?[tdrzsln]%-)", b="%1%2h%3%4"}, --p
-   {a="T([%(%[%|%<%s])(a[%_%^%.]?[tdrzsln]%-)", b="t%1%2"}, --p
-   {a="T([%|\"])", b="t%1"},
-   {a="T(%p*%s)", b="h%1"},
-   {a="T(%p*)$", b="h%1"},
-   {a="T(%p*)(%W)", b="h%1%2"},
+   --   {a="[TH]([^uai])", b="%1"},
+   {a="[TH](\\arbup)", b="t%1"},
+   {a="([a%'][%_%^%.]?[tdrzsln]%-)(%S-)[TH]([%(%[%|%<%s])(a[%_%^%.]?[tdrzsln]%-)", b="%1%2h%3%4"}, --p
+   {a="[TH]([%(%[%|%<%s])(a[%_%^%.]?[tdrzsln]%-)", b="t%1%2"}, --p
+   {a="[TH]([%|\"])", b="t%1"},
+   {a="[TH](%p*%s)", b="h%1"},
+   {a="[TH](%p*)$", b="h%1"},
+   {a="[TH](%p*)(%W)", b="h%1%2"},
    {a="_t", b="ṯ"},
    {a="%^g", b="ǧ"},
    {a="%.h", b="ḥ"},
@@ -565,6 +567,7 @@ singletrdmg = {
    {a="y", b="y"},
    {a="T", b="t"},
    -- additional characters (begin)
+   {a="H", b="t"},
    {a="p", b="p"},
    {a="v", b="v"},
    {a="g", b="g"},
@@ -680,13 +683,13 @@ tanwintrloc = {
    -- needed by \arbcolor:
    {a="%-?(aN)(O[%S]-%_AO)", b="an"},
    {a="%-?(aN)(O[%S]-YO)", b="an"},
-   {a="(O[%S]-TO)%-?(\"?aN)", b="an"},
-   {a="(O[%S]-[^TA]O)%-?(\"?aN)", b="an"},
+   {a="(O[%S]-[TH]O)%-?(\"?aN)", b="an"},
+   {a="(O[%S]-[^TAH]O)%-?(\"?aN)", b="an"},
    --
    {a="%-?(aN)(_A)", b="an"},
    {a="%-?(aN)(Y)", b="an"},
-   {a="(T)%-?(\"?aN)", b="tan"},
-   {a="([^TA])%-?(\"?aN)", b="%1an"}
+   {a="([TH])%-?(\"?aN)", b="tan"},
+   {a="([^TAH])%-?(\"?aN)", b="%1an"}
 }
 
 trigraphstrloc = { -- trigraphs or more
@@ -773,12 +776,12 @@ digraphstrloc = {
    {a="iyy(%p*%s)", b="ī%1"},
    {a="iyy", b="īy"},
    {a="([tkdsg])(h)", b="%1'%2"},
-   --   {a="T([^uai])", b="h%1"},
-   {a="([a%']l%-)(%S-)T([%(%[%|%<%s])(al%-)", b="%1%2h%3%4"}, --p
-   {a="T([%(%[%|%<%s])(al%-)", b="t%1%2"}, --p
-   {a="T([%|\"])", b="t%1"},
-   {a="T(%p*)$", b="h%1"},
-   {a="T(%p*%s)", b="h%1"},
+   --   {a="[TH]([^uai])", b="h%1"},
+   {a="([a%']l%-)(%S-)[TH]([%(%[%|%<%s])(al%-)", b="%1%2h%3%4"}, --p
+   {a="[TH]([%(%[%|%<%s])(al%-)", b="t%1%2"}, --p
+   {a="[TH]([%|\"])", b="t%1"},
+   {a="[TH](%p*)$", b="h%1"},
+   {a="[TH](%p*%s)", b="h%1"},
    {a="_t", b="th"},
    {a="%^g", b="j"},
    {a="%.h", b="ḥ"},
@@ -832,6 +835,7 @@ singletrloc = {
    {a="y", b="y"},
    {a="T", b="t"},
    -- additional characters (begin)
+   {a="H", b="t"},
    {a="p", b="p"},
    {a="v", b="v"},
    {a="g", b="g"},
@@ -1027,12 +1031,12 @@ digraphstrarabica = {
    {a="%-%-", b=""},
    {a="iyy(%p*)$", b="ī%1"},
    {a="iyy(%p*%s)", b="ī%1"},
-   --   {a="T([^uai])", b="h%1"},
-   {a="([a%']l%-)(%S-)aT([%(%[%|%<%s])(al%-)", b="%1%2a%3%4"}, --p
-   {a="aT([%(%[%|%<%s])(al%-)", b="at%1%2"}, --p
-   {a="T([%|\"])", b="t%1"},
-   {a="aT(%p*)$", b="a%1"},
-   {a="aT(%p*%s)", b="a%1"},
+   --   {a="[TH]([^uai])", b="h%1"},
+   {a="([a%']l%-)(%S-)a[TH]([%(%[%|%<%s])(al%-)", b="%1%2a%3%4"}, --p
+   {a="a[TH]([%(%[%|%<%s])(al%-)", b="at%1%2"}, --p
+   {a="[TH]([%|\"])", b="t%1"},
+   {a="a[TH](%p*)$", b="a%1"},
+   {a="a[TH](%p*%s)", b="a%1"},
    {a="_t", b="ṯ"},
    {a="%^g", b="ǧ"},
    {a="%.h", b="ḥ"},
@@ -1086,6 +1090,7 @@ singletrarabica = {
    {a="y", b="y"},
    {a="T", b="t"},
    -- additional characters (begin)
+   {a="H", b="t"},
    {a="p", b="p"},
    {a="v", b="v"},
    {a="g", b="g"},