diff options
Diffstat (limited to 'Master/texmf-dist/tex/lualatex/arabluatex/arabluatex_voc.lua')
-rw-r--r-- | Master/texmf-dist/tex/lualatex/arabluatex/arabluatex_voc.lua | 108 |
1 files changed, 80 insertions, 28 deletions
diff --git a/Master/texmf-dist/tex/lualatex/arabluatex/arabluatex_voc.lua b/Master/texmf-dist/tex/lualatex/arabluatex/arabluatex_voc.lua index 02c3febe93c..6be30d12f99 100644 --- a/Master/texmf-dist/tex/lualatex/arabluatex/arabluatex_voc.lua +++ b/Master/texmf-dist/tex/lualatex/arabluatex/arabluatex_voc.lua @@ -161,6 +161,7 @@ buckwalter = { {a="F", b="aN"}, {a="K", b="iN"}, {a="o", b="\""}, + {a="P", b="o"}, -- pass on to \arbnull -- hard-coded connective alif {a="%[", b="ٱ"}, {a="L", b="ٱ"} -- BW safe @@ -201,11 +202,15 @@ hamza = { {a="(A)(')(u)", b="aآؤ%3"}, -- historic madda {a="(A)(')", b="aآء"}, -- historic madda -- initial (needs both ^ and %W patterns) - -- 'aw: the diphthong is to be resoved into 'awi' (next 4 lines) + -- 'aw: the diphthong is to be resolved into 'awi' (next 8 lines) + {a="^('aw)(o)('[%_%^%.]?[l'btjghxdrzs`fqkmnwy]%-)([%S]-o)", b="%1i"}, + {a="(%W)('aw)(o)('[%_%^%.]?[l'btjghxdrzs`fqkmnwy]%-)([%S]-o)", b="%1%2i"}, + {a="^('aw)(o)(\"?[uai])([%S]-o)", b="%1i"}, + {a="(%W)('aw)(o)(\"?[uai])([%S]-o)", b="%1%2i"}, {a="^('aw)(%s)(['][%_%^%.]?[l'btjghxdrzs`fqkmnwy]%-)", b="%1i%2%3"}, {a="(%W)('aw)(%s)(['][%_%^%.]?[l'btjghxdrzs`fqkmnwy]%-)", b="%1%2i%3%4"}, - {a="^('aw)(%s)([%(%[%|%<]?\"?[uai])", b="%1i%2%3"}, - {a="(%W)('aw)(%s)([%(%[%|%<]?\"?[uai])", b="%1%2i%3%4"}, + {a="^('aw)(%s)([%(%[%|%<]?\"?[uai])", b="%1i%2%3"}, --p + {a="(%W)('aw)(%s)([%(%[%|%<]?\"?[uai])", b="%1%2i%3%4"}, --p -- then the 'initial' rules for the remaining cases {a="^(')([ua])", b="أ%2"}, {a="^(')(i)", b="إ%2"}, @@ -298,7 +303,11 @@ hamzaeasy = { -- differences marked below with 'easy' {a="(A)(')", b="aاء"}, -- historic madda --easy (end) -- initial (needs both ^ and %W patterns) - -- 'aw: the diphthong is to be resoved into 'awi' (next 4 lines) + -- 'aw: the diphthong is to be resolved into 'awi' (next 8 lines) + {a="^('aw)(o)('[%_%^%.]?[l'btjghxdrzs`fqkmnwy]%-)([%S]-o)", b="%1i"}, + {a="(%W)('aw)(o)('[%_%^%.]?[l'btjghxdrzs`fqkmnwy]%-)([%S]-o)", b="%1%2i"}, + {a="^('aw)(o)(\"?[uai])([%S]-o)", b="%1i"}, + {a="(%W)('aw)(o)(\"?[uai])([%S]-o)", b="%1%2i"}, {a="^('aw)(%s)(['][%_%^%.]?[l'btjghxdrzs`fqkmnwy]%-)", b="%1i%2%3"}, {a="(%W)('aw)(%s)(['][%_%^%.]?[l'btjghxdrzs`fqkmnwy]%-)", b="%1%2i%3%4"}, {a="^('aw)(%s)([%(%[%|%<]?\"?[uai])", b="%1i%2%3"}, @@ -359,11 +368,18 @@ hamzaeasy = { -- differences marked below with 'easy' } tanwin = { + -- assimilations (begin) + {a="(o[%S]-)(%-?[uai]N[UI]?)(o)([rlmnwy])", b="%4%4"}, + {a="(%-?[uai]NU)(%s)([rlmnwy])", b="%1%2%3%3"}, + -- assimilations (end) + {a="(o[%S]-)(%-?[uai]N[UI]?)(o)([uai])", b="%4"}, {a="%-?uNU", b="ٌو"}, {a="%-?aNU", b="ًوا"}, {a="%-?iNU", b="ٍو"}, -- assimilations (begin) {a="%-?(uN)(%s)([rlmnwy])", b="ٌ%2%3%3"}, + {a="(o[%S]-)(%-?aN)(_A)(o)([rlmnwy])", b="%5%5"}, + {a="(o[%S]-)(%-?aN)(Y)(o)([rlmnwy])", b="%5%5"}, {a="%-?(aN)(_A)(%s)([rlmnwy])", b="ًى%3%4%4"}, {a="%-?(aN)(Y)(%s)([rlmnwy])", b="ًى%3%4%4"}, {a="(T)%-?(aN)(%s)([rlmnwy])", b="%1ً%3%4%4"}, @@ -371,6 +387,8 @@ tanwin = { {a="([^TA])%-?(aN)(%s)([rlmnwy])", b="%1ًا%3%4%4"}, {a="%-?(iNI?)(%s)([rlmnwy])", b="ٍ%2%3%3"}, -- assimilations (end) + {a="(o[%S]-)(%-?aN)(_A)(o)([uai])", b="%5"}, + {a="(o[%S]-)(%-?aN)(Y)(o)([uai])", b="%5"}, -- quoted tanwīn (begin) {a="%-?(\"uN)", b=""}, {a="(B)%-?(\"aN)", b="%1"}, @@ -392,11 +410,18 @@ tanwin = { } tanwineasy = { -- 'easy' requires some lines to be taken out: + -- assimilations (begin) +-- {a="(o[%S]-)(%-?[uai]N[UI]?)(o)([rlmnwy])", b="%4%4"}, +-- {a="(%-?[uai]NU)(%s)([rlmnwy])", b="%1%2%3%3"}, + -- assimilations (end) + {a="(o[%S]-)(%-?[uai]N[UI]?)(o)([uai])", b="%4"}, {a="%-?uNU", b="ٌو"}, {a="%-?aNU", b="ًوا"}, {a="%-?iNU", b="ٍو"}, -- assimilations (begin) -- {a="%-?(uN)(%s)([rlmnwy])", b="ٌ%2%3%3"}, +-- {a="(o[%S]-)(%-?aN)(_A)(o)([rlmnwy])", b="%5%5"}, +-- {a="(o[%S]-)(%-?aN)(Y)(o)([rlmnwy])", b="%5%5"}, -- {a="%-?(aN)(_A)(%s)([rlmnwy])", b="ًى%3%4%4"}, -- {a="%-?(aN)(Y)(%s)([rlmnwy])", b="ًى%3%4%4"}, -- {a="(T)%-?(aN)(%s)([rlmnwy])", b="%1ً%3%4%4"}, @@ -404,6 +429,8 @@ tanwineasy = { -- 'easy' requires some lines to be taken out: -- {a="([^TA])%-?(aN)(%s)([rlmnwy])", b="%1ًا%3%4%4"}, -- {a="%-?(iNI?)(%s)([rlmnwy])", b="ٍ%2%3%3"}, -- assimilations (end) + {a="(o[%S]-)(%-?aN)(_A)(o)([uai])", b="%5"}, + {a="(o[%S]-)(%-?aN)(Y)(o)([uai])", b="%5"}, -- quoted tanwīn (begin) {a="%-?(\"uN)", b=""}, {a="(B)%-?(\"aN)", b="%1"}, @@ -428,32 +455,39 @@ trigraphs = { -- trigraphs or more -- 'llatI / 'llad_I {a="^'ll(a)([%_]?[dt])", b="الّ%1%2"}, {a="([%(%[%|%<%s%-])'ll(a)([%_]?[dt])", b="%1الّ%2%3"}, --p - -- law: the diphthong is to be resoved into 'awi' (next 4 lines) + -- law: the diphthong is to be resolved into 'awi' (next 8 lines) + {a="^(law)(o)(['][%_%^%.]?[l'btjghxdrzs`fqkmnwy]%-)([%S]-o)", b="%1i"}, + {a="(%W)(law)(o)(['][%_%^%.]?[l'btjghxdrzs`fqkmnwy]%-)([%S]-o)", b="%1%2i"}, + {a="^(law)(o)(\"?[uai])([%S]-o)", b="%1i"}, + {a="(%W)(law)(o)(\"?[uai])([%S]-o)", b="%1%2i"}, {a="^(law)(%s)(['][%_%^%.]?[l'btjghxdrzs`fqkmnwy]%-)", b="%1i%2%3"}, {a="(%W)(law)(%s)(['][%_%^%.]?[l'btjghxdrzs`fqkmnwy]%-)", b="%1%2i%3%4"}, - {a="^(law)(%s)([%(%[%|%<]?\"?[uai])", b="%1i%2%3"}, - {a="(%W)(law)(%s)([%(%[%|%<]?\"?[uai])", b="%1%2i%3%4"}, + {a="^(law)(%s)([%(%[%|%<]?\"?[uai])", b="%1i%2%3"}, --p + {a="(%W)(law)(%s)([%(%[%|%<]?\"?[uai])", b="%1%2i%3%4"}, --p -- al- + lām {a="^(a)l%-(l)", b="ا%1ل%2%2"}, - {a="([%(%[%|%<%s%-])(a)l%-(l)", b="%1ا%2ل%3%3"}, --p + {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%-])(a)l%-([%_%^%.]?[tdrzsn])", b="%1ا%2ل%3%3"}, --p + {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%-])(a)([%_%^%.]?[tdrzsn])%-", b="%1ا%2ل%3"}, --p + {a="([%(%[%|%<%s%-o])(a)([%_%^%.]?[tdrzsn])%-", b="%1ا%2ل%3"}, --p -- al- + initial unstable hamza {a="^(a)l%-(\")([uai])", b="ا%1ل%3ٱ"}, - {a="([%(%[%|%<%s%-])(a)l%-(\")([uai])", b="%1ا%2ل%4ٱ"}, --p + {a="([%(%[%|%<%s%-o])(a)l%-(\")([uai])", b="%1ا%2ل%4ٱ"}, --p {a="^(a)l%-([uai])", b="ا%1ل%2ا"}, - {a="([%(%[%|%<%s%-])(a)l%-([uai])", b="%1ا%2ل%3ا"}, --p + {a="([%(%[%|%<%s%-o])(a)l%-([uai])", b="%1ا%2ل%3ا"}, --p -- li-/la- + art. + initial unstable hamza is a special orthography {a="l([ai])%-l%-(\")([uai])", b="ل%1ل%3ٱ"}, {a="l([ai])%-l%-([uai])", b="ل%1ل%2ا"}, -- al- + lunar consonant (i.e. what remains) {a="^(a)l%-", b="ا%1ل"}, - {a="([%(%[%|%<%s%-])(a)l%-", b="%1ا%2ل"}, --p + {a="([%(%[%|%<%s%-o])(a)l%-", b="%1ا%2ل"}, --p -- diphthongs to be resolved before ʾalif conjunctionis + {a="(aW)(o)(['][%_%^%.]?[l'btjghxdrzs`fqkmnwy]%-)([%S]-o)", b="awuا"}, + {a="(aw)(o)(['][%_%^%.]?[l'btjghxdrzs`fqkmnwy]%-)([%S]-o)", b="%1u"}, + {a="(ay)(o)(['][%_%^%.]?[l'btjghxdrzs`fqkmnwy]%-)([%S]-o)", b="%1i"}, {a="(aW)(%s)(['][%_%^%.]?[l'btjghxdrzs`fqkmnwy]%-)", b="awuا%2%3"}, {a="(aw)(%s)(['][%_%^%.]?[l'btjghxdrzs`fqkmnwy]%-)", b="%1u%2%3"}, {a="(ay)(%s)(['][%_%^%.]?[l'btjghxdrzs`fqkmnwy]%-)", b="%1i%2%3"}, @@ -489,7 +523,8 @@ trigraphs = { -- trigraphs or more idgham = { -- assimilations - {a="(n)(%s)([rlmnwy])", b="%1%2%3%3"} + {a="(n)(%s)([rlmnwy])", b="%1%2%3%3"}, + {a="(n)(o)([rlmnwy])([%S]-o)", b="%3"} } trigraphseasy = { -- differences marked below with 'easy' @@ -498,32 +533,39 @@ trigraphseasy = { -- differences marked below with 'easy' -- 'llatI / 'llad_I {a="^'ll(a)([%_]?[dt])", b="الّ%1%2"}, {a="([%(%[%|%<%s%-])'ll(a)([%_]?[dt])", b="%1الّ%2%3"}, --p - -- law: the diphthong is to be resoved into 'awi' (next 4 lines) + -- law: the diphthong is to be resloved into 'awi' (next 8 lines) + {a="^(law)(o)(['][%_%^%.]?[l'btjghxdrzs`fqkmnwy]%-)([%S]-o)", b="%1i"}, + {a="(%W)(law)(o)(['][%_%^%.]?[l'btjghxdrzs`fqkmnwy]%-)([%S]-o)", b="%1%2i"}, + {a="^(law)(o)(\"?[uai])([%S]-o)", b="%1i"}, + {a="(%W)(law)(o)(\"?[uai])([%S]-o)", b="%1%2i"}, {a="^(law)(%s)(['][%_%^%.]?[l'btjghxdrzs`fqkmnwy]%-)", b="%1i%2%3"}, {a="(%W)(law)(%s)(['][%_%^%.]?[l'btjghxdrzs`fqkmnwy]%-)", b="%1%2i%3%4"}, - {a="^(law)(%s)([%(%[%|%<]?\"?[uai])", b="%1i%2%3"}, - {a="(%W)(law)(%s)([%(%[%|%<]?\"?[uai])", b="%1%2i%3%4"}, + {a="^(law)(%s)([%(%[%|%<]?\"?[uai])", b="%1i%2%3"}, --p + {a="(%W)(law)(%s)([%(%[%|%<]?\"?[uai])", b="%1%2i%3%4"}, --p -- al- + lām (easy) {a="^(a)l%-(l)", b="ا%1ل%2"}, - {a="([%(%[%|%<%s%-])(a)l%-(l)", b="%1ا%2ل%3"}, --p + {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%-])(a)l%-([%_%^%.]?[tdrzsn])", b="%1ا%2ل%3"}, --p + {a="([%(%[%|%<%s%-o])(a)l%-([%_%^%.]?[tdrzsn])", b="%1ا%2ل%3"}, --p -- assim. art. + solar consonant (easy) {a="^(a)([%_%^%.]?[tdrzsn])%-", b="ا%1ل"}, - {a="([%(%[%|%<%s%-])(a)([%_%^%.]?[tdrzsn])%-", b="%1ا%2ل"}, --p + {a="([%(%[%|%<%s%-o])(a)([%_%^%.]?[tdrzsn])%-", b="%1ا%2ل"}, --p -- al- + initial unstable hamza {a="^(a)l%-(\")([uai])", b="ا%1ل%3ٱ"}, - {a="([%(%[%|%<%s%-])(a)l%-(\")([uai])", b="%1ا%2ل%4ٱ"}, --p + {a="([%(%[%|%<%s%-o])(a)l%-(\")([uai])", b="%1ا%2ل%4ٱ"}, --p {a="^(a)l%-([uai])", b="ا%1ل%2ا"}, - {a="([%(%[%|%<%s%-])(a)l%-([uai])", b="%1ا%2ل%3ا"}, --p + {a="([%(%[%|%<%s%-o])(a)l%-([uai])", b="%1ا%2ل%3ا"}, --p -- li-/la- + art. + initial unstable hamza is a special orthography {a="l([ai])%-l%-(\")([uai])", b="ل%1ل%3ٱ"}, {a="l([ai])%-l%-([uai])", b="ل%1ل%2ا"}, -- al- + lunar consonant (i.e. what remains) {a="^(a)l%-", b="ا%1ل"}, - {a="([%(%[%|%<%s%-])(a)l%-", b="%1ا%2ل"}, --p + {a="([%(%[%|%<%s%-o])(a)l%-", b="%1ا%2ل"}, --p -- diphthongs to be resolved before ʾalif conjunctionis + {a="(aW)(o)(['][%_%^%.]?[l'btjghxdrzs`fqkmnwy]%-)([%S]-o)", b="awuا"}, + {a="(aw)(o)(['][%_%^%.]?[l'btjghxdrzs`fqkmnwy]%-)([%S]-o)", b="%1u"}, + {a="(ay)(o)(['][%_%^%.]?[l'btjghxdrzs`fqkmnwy]%-)([%S]-o)", b="%1i"}, {a="(aW)(%s)(['][%_%^%.]?[l'btjghxdrzs`fqkmnwy]%-)", b="awuا%2%3"}, {a="(aw)(%s)(['][%_%^%.]?[l'btjghxdrzs`fqkmnwy]%-)", b="%1u%2%3"}, {a="(ay)(%s)(['][%_%^%.]?[l'btjghxdrzs`fqkmnwy]%-)", b="%1i%2%3"}, @@ -573,11 +615,20 @@ digraphs = { -- initial straight double quote gives a connective ʾalif {a="^\"[uai]", b="ٱ"}, {a="([%(%[%|%<%s%-])\"[uai]", b="%1ٱ"}, --p - {a="(aW)(%s)([uai])", b="awuا%2%3"}, + -- diphthongs to be resolved before ʾalif conjunctionis + {a="(aW)(o)(\"?[uai])([%S]-o)", b="awuا"}, + {a="(aW)(%s)([%(%[%|%<]?)([uai])", b="awuا%2%3%4"}, --p + {a="(aw)(o)(\"?[uai])([%S]-o)", b="%1u"}, + {a="(aw)(%s)([%(%[%|%<]?)(\"?[uai])", b="%1u%2%3ا"}, --p + {a="(ay)(o)(\"?[uai])([%S]-o)", b="%1i"}, + {a="(ay)(%s)([%(%[%|%<]?)(\"?[uai])", b="%1i%2%3ا"}, --p -- hyphen + initial alif without hamza: - {a="(%-)([uai])([%^%_%.%`]?)(%a)", b="%1ا%3%4"}, - {a="^([%(%[%|%<]?)([uai])", b="%1ا%2"}, -- initial alif without hamza --p - {a="(%s)([%(%[%|%<]?)([uai])", b="%1%2ا"}, -- initial alif without hamza --p + {a="([uai]%-)(\"?[uai])([%^%_%.%`]?)(%a)", b="%1ا%3%4"}, + -- initial alif without hamza + {a="^([%(%[%|%<]?)(\"?[uai])", b="%1ا%2"}, --p + -- initial alif without hamza + {a="(o[%S]-)([uaiUAIY])(o)(\"?[uai])", b="ا"}, + {a="(%s)([%(%[%|%<]?)(\"?[uai])", b="%1%2ا"}, --p {a="%-%-", b="ـ"}, {a="ؤؤ", b="ؤّ"}, {a="أأ", b="أّ"}, @@ -715,5 +766,6 @@ punctuation = { null = { {a="%|", b=""}, - {a="([^0-9])(%-)", b="%1"} + {a="([^0-9])(%-)", b="%1"}, + {a="o[%S]-o", b=""} } |