diff options
Diffstat (limited to 'tex/context/base/font-ota.lua')
| -rw-r--r-- | tex/context/base/font-ota.lua | 427 |
1 files changed, 204 insertions, 223 deletions
diff --git a/tex/context/base/font-ota.lua b/tex/context/base/font-ota.lua index 9af5a3347..1f1534870 100644 --- a/tex/context/base/font-ota.lua +++ b/tex/context/base/font-ota.lua @@ -1,4 +1,4 @@ -if not modules then modules = { } end modules ['font-ota'] = { +if not modules then modules = { } end modules ['font-otx'] = { version = 1.001, comment = "companion to font-otf.lua (analysing)", author = "Hans Hagen, PRAGMA-ADE, Hasselt NL", @@ -6,7 +6,7 @@ if not modules then modules = { } end modules ['font-ota'] = { license = "see context related readme files" } --- this might become scrp-*.lua +-- context only local type = type @@ -26,21 +26,35 @@ local methods = allocate() analyzers.initializers = initializers analyzers.methods = methods -analyzers.useunicodemarks = false +---------.useunicodemarks = false local a_state = attributes.private('state') +local nuts = nodes.nuts +local tonut = nuts.tonut + +local getfield = nuts.getfield +local getnext = nuts.getnext +local getprev = nuts.getprev +local getid = nuts.getid +local getprop = nuts.getprop +local setprop = nuts.setprop +local getfont = nuts.getfont +local getsubtype = nuts.getsubtype +local getchar = nuts.getchar + +local traverse_id = nuts.traverse_id +local traverse_node_list = nuts.traverse +local end_of_math = nuts.end_of_math + local nodecodes = nodes.nodecodes local glyph_code = nodecodes.glyph local disc_code = nodecodes.disc local math_code = nodecodes.math -local traverse_id = node.traverse_id -local traverse_node_list = node.traverse -local end_of_math = node.end_of_math - local fontdata = fonts.hashes.identifiers local categories = characters and characters.categories or { } -- sorry, only in context +local chardata = characters and characters.data local otffeatures = fonts.constructors.newfeatures("otf") local registerotffeature = otffeatures.register @@ -87,63 +101,70 @@ local features = { pstf = s_pstf, } -analyzers.states = states -analyzers.features = features +analyzers.states = states +analyzers.features = features +analyzers.useunicodemarks = false -- todo: analyzers per script/lang, cross font, so we need an font id hash -> script -- e.g. latin -> hyphenate, arab -> 1/2/3 analyze -- its own namespace -function analyzers.setstate(head,font) +function analyzers.setstate(head,font) -- we can skip math local useunicodemarks = analyzers.useunicodemarks local tfmdata = fontdata[font] local descriptions = tfmdata.descriptions local first, last, current, n, done = nil, nil, head, 0, false -- maybe make n boolean + current = tonut(current) while current do - local id = current.id - if id == glyph_code and current.font == font then + local id = getid(current) + if id == glyph_code and getfont(current) == font then done = true - local char = current.char + local char = getchar(current) local d = descriptions[char] if d then - if d.class == "mark" or (useunicodemarks and categories[char] == "mn") then + if d.class == "mark" then done = true - current[a_state] = s_mark + setprop(current,a_state,s_mark) + elseif useunicodemarks and categories[char] == "mn" then + done = true + setprop(current,a_state,s_mark) elseif n == 0 then first, last, n = current, current, 1 - current[a_state] = s_init + setprop(current,a_state,s_init) else last, n = current, n+1 - current[a_state] = s_medi + setprop(current,a_state,s_medi) end else -- finish if first and first == last then - last[a_state] = s_isol + setprop(last,a_state,s_isol) elseif last then - last[a_state] = s_fina + setprop(last,a_state,s_fina) end first, last, n = nil, nil, 0 end elseif id == disc_code then - -- always in the middle - current[a_state] = s_medi + -- always in the middle .. it doesn't make much sense to assign a property + -- here ... we might at some point decide to flag the components when present + -- but even then it's kind of bogus + setprop(current,a_state,s_medi) last = current else -- finish if first and first == last then - last[a_state] = s_isol + setprop(last,a_state,s_isol) elseif last then - last[a_state] = s_fina + setprop(last,a_state,s_fina) end first, last, n = nil, nil, 0 if id == math_code then current = end_of_math(current) end end - current = current.next + current = getnext(current) end if first and first == last then - last[a_state] = s_isol + setprop(last,a_state,s_isol) elseif last then - last[a_state] = s_fina + setprop(last,a_state,s_fina) end return head, done end @@ -200,234 +221,194 @@ registerotffeature { -- latin methods.latn = analyzers.setstate - --- This info eventually can go into char-def and we will have a state --- table for generic then (unicode recognized all states but in practice --- only has only --- --- isolated : isol --- final : isol_fina --- medial : isol_fina_medi_init --- --- so in practice, without analyzer it's rather useless info which is --- why having it in char-def makes only sense for special purposes (like) --- like tracing cq. visualizing. - -local tatweel = 0x0640 -local zwnj = 0x200C -local zwj = 0x200D - -local isolated = { -- isol - [0x0600] = true, [0x0601] = true, [0x0602] = true, [0x0603] = true, - [0x0604] = true, - [0x0608] = true, [0x060B] = true, [0x0621] = true, [0x0674] = true, - [0x06DD] = true, - -- mandaic - [0x0856] = true, [0x0858] = true, [0x0857] = true, - -- n'ko - [0x07FA] = true, - -- also here: - [zwnj] = true, -} - -local final = { -- isol_fina - [0x0622] = true, [0x0623] = true, [0x0624] = true, [0x0625] = true, - [0x0627] = true, [0x0629] = true, [0x062F] = true, [0x0630] = true, - [0x0631] = true, [0x0632] = true, [0x0648] = true, [0x0671] = true, - [0x0672] = true, [0x0673] = true, [0x0675] = true, [0x0676] = true, - [0x0677] = true, [0x0688] = true, [0x0689] = true, [0x068A] = true, - [0x068B] = true, [0x068C] = true, [0x068D] = true, [0x068E] = true, - [0x068F] = true, [0x0690] = true, [0x0691] = true, [0x0692] = true, - [0x0693] = true, [0x0694] = true, [0x0695] = true, [0x0696] = true, - [0x0697] = true, [0x0698] = true, [0x0699] = true, [0x06C0] = true, - [0x06C3] = true, [0x06C4] = true, [0x06C5] = true, [0x06C6] = true, - [0x06C7] = true, [0x06C8] = true, [0x06C9] = true, [0x06CA] = true, - [0x06CB] = true, [0x06CD] = true, [0x06CF] = true, [0x06D2] = true, - [0x06D3] = true, [0x06D5] = true, [0x06EE] = true, [0x06EF] = true, - [0x0759] = true, [0x075A] = true, [0x075B] = true, [0x076B] = true, - [0x076C] = true, [0x0771] = true, [0x0773] = true, [0x0774] = true, - [0x0778] = true, [0x0779] = true, - [0x08AA] = true, [0x08AB] = true, [0x08AC] = true, - [0xFEF5] = true, [0xFEF7] = true, [0xFEF9] = true, [0xFEFB] = true, - -- syriac - [0x0710] = true, [0x0715] = true, [0x0716] = true, [0x0717] = true, - [0x0718] = true, [0x0719] = true, [0x0728] = true, [0x072A] = true, - [0x072C] = true, [0x071E] = true, - [0x072F] = true, [0x074D] = true, - -- mandaic - [0x0840] = true, [0x0849] = true, [0x0854] = true, [0x0846] = true, - [0x084F] = true -} - -local medial = { -- isol_fina_medi_init - [0x0626] = true, [0x0628] = true, [0x062A] = true, [0x062B] = true, - [0x062C] = true, [0x062D] = true, [0x062E] = true, [0x0633] = true, - [0x0634] = true, [0x0635] = true, [0x0636] = true, [0x0637] = true, - [0x0638] = true, [0x0639] = true, [0x063A] = true, [0x063B] = true, - [0x063C] = true, [0x063D] = true, [0x063E] = true, [0x063F] = true, - [0x0641] = true, [0x0642] = true, [0x0643] = true, - [0x0644] = true, [0x0645] = true, [0x0646] = true, [0x0647] = true, - [0x0649] = true, [0x064A] = true, [0x066E] = true, [0x066F] = true, - [0x0678] = true, [0x0679] = true, [0x067A] = true, [0x067B] = true, - [0x067C] = true, [0x067D] = true, [0x067E] = true, [0x067F] = true, - [0x0680] = true, [0x0681] = true, [0x0682] = true, [0x0683] = true, - [0x0684] = true, [0x0685] = true, [0x0686] = true, [0x0687] = true, - [0x069A] = true, [0x069B] = true, [0x069C] = true, [0x069D] = true, - [0x069E] = true, [0x069F] = true, [0x06A0] = true, [0x06A1] = true, - [0x06A2] = true, [0x06A3] = true, [0x06A4] = true, [0x06A5] = true, - [0x06A6] = true, [0x06A7] = true, [0x06A8] = true, [0x06A9] = true, - [0x06AA] = true, [0x06AB] = true, [0x06AC] = true, [0x06AD] = true, - [0x06AE] = true, [0x06AF] = true, [0x06B0] = true, [0x06B1] = true, - [0x06B2] = true, [0x06B3] = true, [0x06B4] = true, [0x06B5] = true, - [0x06B6] = true, [0x06B7] = true, [0x06B8] = true, [0x06B9] = true, - [0x06BA] = true, [0x06BB] = true, [0x06BC] = true, [0x06BD] = true, - [0x06BE] = true, [0x06BF] = true, [0x06C1] = true, [0x06C2] = true, - [0x06CC] = true, [0x06CE] = true, [0x06D0] = true, [0x06D1] = true, - [0x06FA] = true, [0x06FB] = true, [0x06FC] = true, [0x06FF] = true, - [0x0750] = true, [0x0751] = true, [0x0752] = true, [0x0753] = true, - [0x0754] = true, [0x0755] = true, [0x0756] = true, [0x0757] = true, - [0x0758] = true, [0x075C] = true, [0x075D] = true, [0x075E] = true, - [0x075F] = true, [0x0760] = true, [0x0761] = true, [0x0762] = true, - [0x0763] = true, [0x0764] = true, [0x0765] = true, [0x0766] = true, - [0x0767] = true, [0x0768] = true, [0x0769] = true, [0x076A] = true, - [0x076D] = true, [0x076E] = true, [0x076F] = true, [0x0770] = true, - [0x0772] = true, [0x0775] = true, [0x0776] = true, [0x0777] = true, - [0x077A] = true, [0x077B] = true, [0x077C] = true, [0x077D] = true, - [0x077E] = true, [0x077F] = true, - [0x08A0] = true, [0x08A2] = true, [0x08A4] = true, [0x08A5] = true, - [0x08A6] = true, [0x0620] = true, [0x08A8] = true, [0x08A9] = true, - [0x08A7] = true, [0x08A3] = true, - -- syriac - [0x0712] = true, [0x0713] = true, [0x0714] = true, [0x071A] = true, - [0x071B] = true, [0x071C] = true, [0x071D] = true, [0x071F] = true, - [0x0720] = true, [0x0721] = true, [0x0722] = true, [0x0723] = true, - [0x0724] = true, [0x0725] = true, [0x0726] = true, [0x0727] = true, - [0x0729] = true, [0x072B] = true, [0x072D] = true, [0x072E] = true, - [0x074E] = true, [0x074F] = true, - -- mandaic - [0x0841] = true, [0x0842] = true, [0x0843] = true, [0x0844] = true, - [0x0845] = true, [0x0847] = true, [0x0848] = true, [0x0855] = true, - [0x0851] = true, [0x084E] = true, [0x084D] = true, [0x084A] = true, - [0x084B] = true, [0x084C] = true, [0x0850] = true, [0x0852] = true, - [0x0853] = true, - -- n'ko - [0x07D7] = true, [0x07E8] = true, [0x07D9] = true, [0x07EA] = true, - [0x07CA] = true, [0x07DB] = true, [0x07CC] = true, [0x07DD] = true, - [0x07CE] = true, [0x07DF] = true, [0x07D4] = true, [0x07E5] = true, - [0x07E9] = true, [0x07E7] = true, [0x07E3] = true, [0x07E2] = true, - [0x07E0] = true, [0x07E1] = true, [0x07DE] = true, [0x07DC] = true, - [0x07D1] = true, [0x07DA] = true, [0x07D8] = true, [0x07D6] = true, - [0x07D2] = true, [0x07D0] = true, [0x07CF] = true, [0x07CD] = true, - [0x07CB] = true, [0x07D3] = true, [0x07E4] = true, [0x07D5] = true, - [0x07E6] = true, - -- also here: - [tatweel]= true, - [zwj] = true, -} +-------.dflt = analyzers.setstate % can be an option or just the default local arab_warned = { } --- todo: gref - local function warning(current,what) - local char = current.char + local char = getchar(current) if not arab_warned[char] then log.report("analyze","arab: character %C has no %a class",char,what) arab_warned[char] = true end end --- potential optimization: local medial_final = table.merged(medial,final) +local mappers = { + l = s_init, -- left + d = s_medi, -- double + c = s_medi, -- joiner + r = s_fina, -- right + u = s_isol, -- nonjoiner +} -local function finish(first,last) - if last then - if first == last then - local fc = first.char - if medial[fc] or final[fc] then - first[a_state] = s_isol - else - warning(first,"isol") - first[a_state] = s_error +local classifiers = { } -- we can also use this trick for devanagari + +local first_arabic, last_arabic = characters.blockrange("arabic") +local first_syriac, last_syriac = characters.blockrange("syriac") +local first_mandiac, last_mandiac = characters.blockrange("mandiac") +local first_nko, last_nko = characters.blockrange("nko") + +table.setmetatableindex(classifiers,function(t,k) + local c = chardata[k] + local v = false + if c then + local arabic = c.arabic + if arabic then + v = mappers[arabic] + if not v then + log.report("analyze","error in mapping arabic %C",k) + -- error + v = false end - else - local lc = last.char - if medial[lc] or final[lc] then - -- if laststate == 1 or laststate == 2 or laststate == 4 then - last[a_state] = s_fina + elseif k >= first_arabic and k <= last_arabic or k >= first_syriac and k <= last_syriac or + k >= first_mandiac and k <= last_mandiac or k >= first_nko and k <= last_nko then + if categories[k] == "mn" then + v = s_mark else - warning(last,"fina") - last[a_state] = s_error + v = s_rest end - end - first, last = nil, nil - elseif first then - -- first and last are either both set so we never com here - local fc = first.char - if medial[fc] or final[fc] then - first[a_state] = s_isol else - warning(first,"isol") - first[a_state] = s_error end - first = nil end - return first, last -end + t[k] = v + return v +end) function methods.arab(head,font,attr) - local useunicodemarks = analyzers.useunicodemarks - local tfmdata = fontdata[font] - local marks = tfmdata.resources.marks - local first, last, current, done = nil, nil, head, false + local first, last = nil, nil + local c_first, c_last = nil, nil + local current, done = head, false + current = tonut(current) while current do - local id = current.id - if id == glyph_code and current.font == font and current.subtype<256 and not current[a_state] then + local id = getid(current) + if id == glyph_code and getfont(current) == font and getsubtype(current)<256 and not getprop(current,a_state) then done = true - local char = current.char - if marks[char] or (useunicodemarks and categories[char] == "mn") then - current[a_state] = s_mark - elseif isolated[char] then -- can be zwj or zwnj too - first, last = finish(first,last) - current[a_state] = s_isol - first, last = nil, nil - elseif not first then - if medial[char] then - current[a_state] = s_init - first, last = first or current, current - elseif final[char] then - current[a_state] = s_isol + local char = getchar(current) + local classifier = classifiers[char] + if not classifier then + if last then + if c_last == s_medi or c_last == s_fina then + setprop(last,a_state,s_fina) + else + warning(last,"fina") + setprop(last,a_state,s_error) + end first, last = nil, nil - else -- no arab - first, last = finish(first,last) + elseif first then + if c_first == s_medi or c_first == s_fina then + setprop(first,a_state,s_isol) + else + warning(first,"isol") + setprop(first,a_state,s_error) + end + first = nil end - elseif medial[char] then - first, last = first or current, current - current[a_state] = s_medi - elseif final[char] then - if not last[a_state] == s_init then - -- tricky, we need to check what last may be ! - last[a_state] = s_medi + elseif classifier == s_mark then + setprop(current,a_state,s_mark) + elseif classifier == s_isol then + if last then + if c_last == s_medi or c_last == s_fina then + setprop(last,a_state,s_fina) + else + warning(last,"fina") + setprop(last,a_state,s_error) + end + first, last = nil, nil + elseif first then + if c_first == s_medi or c_first == s_fina then + setprop(first,a_state,s_isol) + else + warning(first,"isol") + setprop(first,a_state,s_error) + end + first = nil + end + setprop(current,a_state,s_isol) + elseif classifier == s_medi then + if first then + last = current + c_last = classifier + setprop(current,a_state,s_medi) + else + setprop(current,a_state,s_init) + first = current + c_first = classifier + end + elseif classifier == s_fina then + if last then + if getprop(last,a_state) ~= s_init then + setprop(last,a_state,s_medi) + end + setprop(current,a_state,s_fina) + first, last = nil, nil + elseif first then + -- if getprop(first,a_state) ~= s_init then + -- -- needs checking + -- setprop(first,a_state,s_medi) + -- end + setprop(current,a_state,s_fina) + first = nil + else + setprop(current,a_state,s_isol) + end + else -- classifier == s_rest + setprop(current,a_state,s_rest) + if last then + if c_last == s_medi or c_last == s_fina then + setprop(last,a_state,s_fina) + else + warning(last,"fina") + setprop(last,a_state,s_error) + end + first, last = nil, nil + elseif first then + if c_first == s_medi or c_first == s_fina then + setprop(first,a_state,s_isol) + else + warning(first,"isol") + setprop(first,a_state,s_error) + end + first = nil end - current[a_state] = s_fina - first, last = nil, nil - elseif char >= 0x0600 and char <= 0x06FF then -- needs checking - current[a_state] = s_rest - first, last = finish(first,last) - else -- no - first, last = finish(first,last) end else - if first or last then - first, last = finish(first,last) + if last then + if c_last == s_medi or c_last == s_fina then + setprop(last,a_state,s_fina) + else + warning(last,"fina") + setprop(last,a_state,s_error) + end + first, last = nil, nil + elseif first then + if c_first == s_medi or c_first == s_fina then + setprop(first,a_state,s_isol) + else + warning(first,"isol") + setprop(first,a_state,s_error) + end + first = nil end - if id == math_code then + if id == math_code then -- a bit duplicate as we test for glyphs twice current = end_of_math(current) end end - current = current.next + current = getnext(current) end - if first or last then - finish(first,last) + if last then + if c_last == s_medi or c_last == s_fina then + setprop(last,a_state,s_fina) + else + warning(last,"fina") + setprop(last,a_state,s_error) + end + elseif first then + if c_first == s_medi or c_first == s_fina then + setprop(first,a_state,s_isol) + else + warning(first,"isol") + setprop(first,a_state,s_error) + end end return head, done end |