Overview
Comment: | add syn |
---|---|
Downloads: | Tarball | ZIP archive | SQL archive |
Timelines: | family | ancestors | descendants | both | trunk |
Files: | files | file ages | folders |
SHA3-256: |
0f6a5bda236d515918b5adcb8247c4e2 |
User & Date: | lexi on 2022-04-26 02:02:04 |
Other Links: | manifest | tags |
Context
2022-04-28
| ||
21:01 | commit to preserve old code im about to axe, parvan is broken currently check-in: f996abb5e5 user: lexi tags: trunk | |
2022-04-26
| ||
02:02 | add syn check-in: 0f6a5bda23 user: lexi tags: trunk | |
2022-04-25
| ||
21:01 | add first parvan revision check-in: bf5f4fd9ca user: lexi tags: trunk | |
Changes
Modified parvan.lua from [760cd798bc] to [2e5da05ad6].
180 181 182 183 184 185 186 187 188 189 190 191 192 193 ... 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 ... 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 ... 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 ... 539 540 541 542 543 544 545 546 547 548 549 550 551 552 ... 605 606 607 608 609 610 611 612 613 614 615 616 617 618 ... 652 653 654 655 656 657 658 659 660 661 662 663 664 665 ... 711 712 713 714 715 716 717 718 719 720 721 722 723 724 ... 799 800 801 802 803 804 805 806 807 808 809 810 811 812 |
local qpack = function(f) return { encode = packer(f); decode = unpacker(f); } end local parse, marshal fmt.string = qpack "s4" fmt.u8 = qpack "I1" fmt.u16 = qpack "I2" fmt.u24 = qpack "I3" fmt.u32 = qpack "I4" fmt.list = function(t,ty) ty = ty or fmt.u32 return { encode = function(a) ................................................................................ return m end; } end fmt.form = { {'form', fmt.u16}; {'text', fmt.string}; } fmt.note = { {'kind', fmt.string}; {'paras', fmt.list(fmt.string)}; } fmt.meaning = { {'lit', fmt.string}; {'notes', fmt.list(fmt.note,fmt.u8)}; } fmt.def = { {'part', fmt.u8}; {'branch', fmt.list(fmt.string,fmt.u8)}; {'means', fmt.list(fmt.meaning,fmt.u8)}; {'forms', fmt.list(fmt.form,fmt.u16)}; } fmt.word = { {'defs', fmt.list(fmt.def,fmt.u8)}; } fmt.dictHeader = { {'lang', fmt.string}; {'meta', fmt.string}; {'partsOfSpeech', fmt.list(fmt.string,fmt.u16)}; } fmt.dict = { {'header', fmt.dictHeader}; {'words', fmt.map(fmt.string,fmt.word)}; } function marshal(ty, val) if ty.encode then return ty.encode(val) end local ac = {} ................................................................................ def.part = atomizePoS(def.part) end end d.header.partsOfSpeech = {} for v,i in pairs(posMap) do d.header.partsOfSpeech[i] = v end return marshal(fmt.dict, d) end local function readDict(file) local d = parse(fmt.dict, stream(file)) -- handle atoms for lit,w in pairs(d.words) do for j,def in ipairs(w.defs) do def.part = d.header.partsOfSpeech[def.part] end end return d ................................................................................ else id10t('[lit %s %s] is not a valid filter, “%s” should be either “pfx” or “sfx”',val,op,op) end end; }; form = { help = 'match against word\'s inflected forms'; syntax = '(<inflect> | <form> (set | is <inflect> | pfx <prefix> | sfx <suffix>))'; fn = function(e, k, op, v) end; }; part = { help = 'word has definitions for every <part> of speech'; syntax = '<part>…'; fn = function(e,...) ................................................................................ local matches = 0 for j,r in ipairs(d.branch) do if map[r] then matches = matches + 1 end end if matches == tgt then return true end end end }; } end local function safeopen(file,...) if type(file) == 'string' then ................................................................................ header = { lang = lang; meta = ""; partsOfSpeech = {}; branch = {}; }; words = {}; } local o = writeDict(new); fd:write(o) fd:close() end; }; coin = { ................................................................................ help = "add a meaning to a definition"; syntax = "<word> <def#> <meaning>"; write = true; exec = function(ctx,word,dn,m) local _,d = safeNavWord(ctx,word,dn) table.insert(d.means, {lit=m,notes={}}) end; }; mod = { help = "move, merge, split, or delete words or definitions"; syntax = { "<path> (drop | [move|merge|clobber] <path> | out [<part> [<root>…]])"; "path ::= <word>[(@<def#>[/<meaning#>[:<note#>]]|.)]"; }; ................................................................................ syntax = "[<command>]"; }; predicates = { help = "show available filter predicates"; nofile = true; syntax = "[<predicate>]"; }; dump = { exec = function(ctx) print(dump(ctx.dict)) end }; ls = { help = "list all words that meet any given <filter>"; syntax = {"[<filter>…]"; "filter ::= (<word>|<pred> <arg>…)"; ................................................................................ for j, def in ipairs(w.word.defs) do d=d .. '\n' .. meanings(def,true,j) end end io.stdout:write(d..'\n') end end function cmds.mod.exec(ctx, orig, oper, dest, ...) if (not orig) or not oper then id10t '`mod` requires at least an origin and an operation' end local op, dp = parsePath(orig) local w,d,m,n = safeNavWord(ctx, op.w,op.dn,op.mn,op.nn) |
> > | | | | | > > > > > > > > > > > | > > > > > | | > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > |
180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 ... 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 ... 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 ... 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 ... 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 ... 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 ... 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 ... 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 ... 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 |
local qpack = function(f) return { encode = packer(f); decode = unpacker(f); } end local parse, marshal fmt.string = qpack "s4" fmt.label = qpack "s2" fmt.tag = qpack "s1" fmt.u8 = qpack "I1" fmt.u16 = qpack "I2" fmt.u24 = qpack "I3" fmt.u32 = qpack "I4" fmt.list = function(t,ty) ty = ty or fmt.u32 return { encode = function(a) ................................................................................ return m end; } end fmt.form = { {'form', fmt.u16}; {'text', fmt.label}; } fmt.note = { {'kind', fmt.tag}; {'paras', fmt.list(fmt.string)}; } fmt.meaning = { {'lit', fmt.string}; {'notes', fmt.list(fmt.note,fmt.u8)}; } fmt.def = { {'part', fmt.u8}; {'branch', fmt.list(fmt.label,fmt.u8)}; {'means', fmt.list(fmt.meaning,fmt.u8)}; {'forms', fmt.list(fmt.form,fmt.u16)}; } fmt.word = { {'defs', fmt.list(fmt.def,fmt.u8)}; } fmt.dictHeader = { {'lang', fmt.tag}; {'meta', fmt.string}; {'partsOfSpeech', fmt.list(fmt.tag,fmt.u16)}; } fmt.synonymSet = { {'uid', fmt.u32}; -- IDs are persistent random values so they can be used -- as reliable identifiers even when merging exports in -- a parvan-unaware VCS {'members', fmt.list({ {'word', fmt.label}, {'def', fmt.u8}; },fmt.u16)}; } fmt.dict = { {'header', fmt.dictHeader}; {'words', fmt.map(fmt.string,fmt.word)}; {'synonyms', fmt.list(fmt.synonymSet)}; } function marshal(ty, val) if ty.encode then return ty.encode(val) end local ac = {} ................................................................................ def.part = atomizePoS(def.part) end end d.header.partsOfSpeech = {} for v,i in pairs(posMap) do d.header.partsOfSpeech[i] = v end return 'PV0\2'..marshal(fmt.dict, d) end local function readDict(file) local s = stream(file) local magic = s:next 'c4' if magic ~= 'PV0\2' then id10t 'not a parvan file' end local d = parse(fmt.dict, s) -- handle atoms for lit,w in pairs(d.words) do for j,def in ipairs(w.defs) do def.part = d.header.partsOfSpeech[def.part] end end return d ................................................................................ else id10t('[lit %s %s] is not a valid filter, “%s” should be either “pfx” or “sfx”',val,op,op) end end; }; form = { help = 'match against word\'s inflected forms'; syntax = '(<inflect> | <form> (set | is <inflect> | (pfx|sfx|match) <affix>))'; fn = function(e, k, op, v) end; }; part = { help = 'word has definitions for every <part> of speech'; syntax = '<part>…'; fn = function(e,...) ................................................................................ local matches = 0 for j,r in ipairs(d.branch) do if map[r] then matches = matches + 1 end end if matches == tgt then return true end end end }; note = { help = 'word has a matching note'; syntax = '([kind <kind> [<term>]] | term <term> | (min|max|count) <n>)'; fn = function(e, op, k, t) if op == 'kind' or op == 'term' then if op == 'term' and t then id10t('too many arguments for [note term <term>]') end for _,d in ipairs(e.word.defs) do for _,m in ipairs(d.means) do for _,n in ipairs(m.notes) do if op=='term' or n.kind == k then if op=='kind' and t == nil then return true end if string.find(table.concat(n.paras,'\n'), t or k, 1, true) ~= nil then return true end end end end end elseif op == 'min' or op == 'max' or op == 'count' then if t then id10t('too many arguments for [note %s <n>]',op) end local n = math.floor(tonumber(k)) local total = 0 for i,d in ipairs(e.word.defs) do for j,m in ipairs(d.means) do total = total + #m.notes if op == 'min' and total >= n then return true end if op == 'max' and total > n then return false end end end if op == 'count' then return total == n end if op == 'max' then return total <= n end return false end end; }; } end local function safeopen(file,...) if type(file) == 'string' then ................................................................................ header = { lang = lang; meta = ""; partsOfSpeech = {}; branch = {}; }; words = {}; synonyms = {}; } local o = writeDict(new); fd:write(o) fd:close() end; }; coin = { ................................................................................ help = "add a meaning to a definition"; syntax = "<word> <def#> <meaning>"; write = true; exec = function(ctx,word,dn,m) local _,d = safeNavWord(ctx,word,dn) table.insert(d.means, {lit=m,notes={}}) end; }; syn = { help = "manage synonym groups"; syntax = { "(show|purge) <path>"; "(link|drop) <word> <group#> <path>…"; "new <path> <path>…"; "clear <word> [<group#>]"; }; write = true; exec = function(ctx, op, tgtw, ...) local groups = {} local wp = parsePath(tgtw) local w,d = safeNavWord(ctx, wp.w, wp.dn) if not (op=='new' or op=='link' or op=='drop' or op=='clear' or op=='show' or op=='purge') then id10t('invalid operation “%s” for `syn`', op) end if op == 'new' then local links = {{word = wp.w, def = wp.dn or 1}} for i,l in ipairs{...} do local parsed = parsePath(l) links[i+1] = {word = parsed.w, def = parsed.dn or 1} end table.insert(ctx.dict.synonyms, { uid=math.random(0,0xffffFFFF); members=links; }) else -- assemble a list of groups for i,ss in ipairs(ctx.dict.synonyms) do for j,s in ipairs(ss.members) do if s.word == wp.w and (wp.dn == nil or s.def == wp.dn) then table.insert(groups, {set = ss, mem = s}) break end end end if op == 'show' then for i, g in ipairs(groups) do local w,d = safeNavWord(ctx, g.mem.word, g.mem.def) local function label(wd,defn) local fulldef = {} for i,v in ipairs(defn.means) do fulldef[i] = v.lit end fulldef = table.concat(fulldef, '; ') return string.format("%s(%s): %s",wd,defn.part,fulldef) end local others = {} for j, o in ipairs(g.set.members) do if not (o.word == g.mem.word and o.def == (wp.dn or 1)) then local ow, od = safeNavWord(ctx, o.word,o.def) table.insert(others, ' '..label(o.word,od)) end end io.stdout:write(string.format("% 4u) %s\n%s", i, label(g.mem.word,d),table.concat(others,'\n'))) end elseif op == 'link' or op == 'drop' then local tgtn, paths = (...), { select(2, ...) } end end end; }; mod = { help = "move, merge, split, or delete words or definitions"; syntax = { "<path> (drop | [move|merge|clobber] <path> | out [<part> [<root>…]])"; "path ::= <word>[(@<def#>[/<meaning#>[:<note#>]]|.)]"; }; ................................................................................ syntax = "[<command>]"; }; predicates = { help = "show available filter predicates"; nofile = true; syntax = "[<predicate>]"; }; export = { help = "create a text file dump compatible with source control"; }; dump = { exec = function(ctx) print(dump(ctx.dict)) end }; ls = { help = "list all words that meet any given <filter>"; syntax = {"[<filter>…]"; "filter ::= (<word>|<pred> <arg>…)"; ................................................................................ for j, def in ipairs(w.word.defs) do d=d .. '\n' .. meanings(def,true,j) end end io.stdout:write(d..'\n') end end function cmds.export.exec(ctx) local function san(str) local d = 0 local r = {} for i,cp in utf8.codes(str) do -- insert backslashes for characters that would -- disrupt strwords() parsing if cp == 0x5b then d = d + 1 elseif cp == 0x5d then if d >= 1 then d = d - 1 else table.insert(r, 0x5c) end end table.insert(r, cp) end return '[' .. utf8.char(table.unpack(r)) .. ']' end local function o(...) io.stdout:write(string.format(...)..'\n') end local d = ctx.dict o('pv0 %s %s', san(d.header.lang), san(d.header.meta)) for lit, w in pairs(d.words) do o('w %s',san(lit)) for i,def in ipairs(w.defs) do o('d %s',san(def.part)) for _,s in ipairs(d.synonyms) do for _,sm in ipairs(s.members) do if sm.word == w and sm.def == i then o('ds %u',s.uid) break end end end for j,r in ipairs(def.branch) do o('dr %s',san(r)) end for j,m in ipairs(def.means) do o('m %s', san(m.lit)) for k,n in ipairs(m.notes) do o('n %s', san(n.kind)) for a,p in ipairs(n.paras) do o('np %s', san(p)) end end end end end for _,s in ipairs(d.synonyms) do o('s %u', s.uid) end end function cmds.mod.exec(ctx, orig, oper, dest, ...) if (not orig) or not oper then id10t '`mod` requires at least an origin and an operation' end local op, dp = parsePath(orig) local w,d,m,n = safeNavWord(ctx, op.w,op.dn,op.mn,op.nn) |