/* [This file is written in Japanese (Shift-JIS)] */ #ifndef JS static char *version_msg[] = { #else var version_msg = new Array( #endif "* Name: JIYAKU.C [C] - JIYAKU.JS [JavaScript]", "* Version: 2.52 ", "* Date: 2021-09-08 ", "* Author: SADAHIRO Tomoyuki", "* http://nomenclator.la.coocan.jp/chem/jiyaku/jiyaku.htm ", "* Copyright (C) 2000-2021 SADAHIRO Tomoyuki. All rights reserved.", "* Usage: Translation and transliteration of an English name ", " of chemical elements and substances into Japanese. ", "* 用途: 化合物の英語による化学名を日本語に字訳する。", #ifndef JS (char *)0 }; #else ""); #endif #ifndef JS static char *usage_msg[] = { "* -a は、もとの英語名を日本語名と併せて（交互に）出力します。", " この指定が無ければ日本語名のみを出力します。", "* -A は、-aオプションに合わせて、レコードごとに空行を置きます。", "* -i は、二元型名称の倒置（carbon dioxide「二酸化炭素」など）を行います。", " この指定が無ければ語順を変えずに字訳（および「多少の」翻訳）をします。", "* -I は、-i を指定しない結果と指定した結果を並べて出力します。", "* -h は、ヘルプ情報を出力します。字訳はしません。", "* -v は、バージョン情報を出力します。字訳はしません。", (char *)0 }; #endif #ifndef JS /**************************************************** * このファイルをCのソースとしてコンパイルするには * マクロ名 JS を定義しないで行う。 * * このファイルからJavaScriptコードを抽出するには * JSを定義したときのプリプロセッサの結果を用いる。 * * MS VC++ 6.0 ではコマンドラインから * \>CL /EP /C /DJS jiyaku.c >jiyaku.js * * LITEを定義すると簡略版になる（CでもJSでも可）。 * spaninvert(), invert() [二元型命名法の翻訳], * ousacid() [三価リン・ヒ素酸類型名] ほか、 * 超ウラン元素や、ある種の一般的でない名称のための * 処理を省略する。 * * *****************************************************/ #endif #ifndef NC /* * グローバル変数の使い方 * * g() self -> dest * glookahead() self -> dest * glookbehind() self -> dest * cvtitalic() self -> dest, using head and tail * cvtjapan() self -> dest * euphony() on self; using dest, head and tail * ousacid() on self; using head and tail * moveacid() on self; using head and tail * substnum() on self; calling g() * translnum() on self; using dest, head and tail * translele() on self; calling g(), translnum() etc. * invert() on str something, using head * spaninvert() self -> dest, using tail, calling g() etc. * jk() start self * * destの内容は、self2dest()マクロでselfに戻す。 * dest, head, tailは、いずれも一時的なバッファである。 * 同一のバッファを同時に2以上の目的で使用してはならない。 * */ #endif /* NC */ #ifndef NC /* * 処理における区切りの意味づけ * * '_' 文字区切り （以下の書式中、X はアルファベット大文字） * * [~XX|_] 非英字（XX 常に２文字） * [~^X|_] 大文字記号（X 常に１文字） # X : HI-ASCII のときにも利用。 * [~`X|_] 小文字記号（X 常に１文字） * [~&X|_] 第二バイト ASCII -> +0x80（X: HI-ASCII） * [$XXX_] 翻訳語 * $_ 翻訳語扱いのカナ * [XX_] カナ（XX 常に２文字） * /X_ カナ扱いの置き換え * [%X_] ate, ite, ideの変換までの保持（X 常に１文字） * [i#e] 変換前のide陰イオンをあらわすラベル * [a!e],[i!e] 変換前のate,ite陰イオンをあらわすラベル * '?' substnum() で数詞をあらわすラベル * '@' euphony(), ousacid(), moveacid() などにおける指標 * '@' はその処理の過程で順次適切な文字列に置換されねばならない。 * それぞれの処理の終了は通常 '@' の消滅を以て確認する。 * * ' ' '<' '>' '(' ')' '[' ']' '{' '}' * '*' '\'' '\"' '.' ',' ':' ';' '-' '=' * 倒置のときの括弧のネストを調べるのにつかう。 * * 文字列selfは、各文字が上の形式になるように順に置換される。 */ #endif /* NC */ /* 倒置を認めるか */ #ifndef JS /* コマンドラインオプションで指定させる */ int inv = 0; int alt = 0, alt2 = 0, inv2 = 0; #else var inv = true; #endif /* 倒置のレベル */ #ifndef JS const int invlev = 3; #else var invlev = 3; #endif /* selfとdestの長さをチェックする。[2004-09-25] */ #ifdef DEBUGGING int selflen, destlen; #endif /* 句読点のサイズ */ #ifndef JS const int lenpct = 5; #else var lenpct = 5; #endif /* 文字列バッファのサイズ */ #ifndef JS #define BUFSIZE (128) #define STRSIZE (BUFSIZE * 8) #endif /* hydrogen */ #define HYDRSTR "/H_" #define MUONSTR "/M_" /* translele() /L_ */ /* y の字訳 /Y_ */ /* aryl /R_ */ /* e の保護 /E_ */ /* -ideの例外 /I_ */ /* anhydride /A_ */ /* amic,anilic /C_ */ /* bi-ate,ite /B_ */ #ifndef JS #define HYDR(s) (HYDRSTR s) #define MUON(s) (MUONSTR s) #else #define HYDR(s) (HYDRSTR + s) #define MUON(s) (MUONSTR + s) #endif /* ending consonant with silent e */ #define ECONS "dlnt" #define VOWEL "aiueoy" #define LOWER "abcdefghijklmnopqrstuvwxyz" #define UPPER "ABCDEFGHIJKLMNOPQRSTUVWXYZ" #ifndef JS #include #include #include #include #define chrStrAt(s,n) (s)[n] #define memEQ(s1,s2,l) (!memcmp(s1,s2,l)) #define memNE(s1,s2,l) (memcmp(s1,s2,l)) #define strEQ(s1,s2) (!strcmp(s1,s2)) #define strNE(s1,s2) (strcmp(s1,s2)) #define isKANJI(c) ((0x81 <= (0xFF & c) && (0xFF & c) <= 0x9F || \ 0xE0 <= (0xFF & c) && (0xFF & c) <= 0xFC)) #else /* プリプロセッサによるマクロ置換に注意 */ #define strcat(i, j) i += j #define strcpy(i, j) i = j #define strEQ(i, j) (i == j) #define strNE(i, j) (i != j) #define strlen(i) i.length #define strchr(i, j) i.indexOf(j) #define strstr(i, j) i.indexOf(j) #define chrStrAt(s,n) s.charAt(n) #define NULL -1 #endif /* 共通のマクロ */ #define self2dest() strcpy(self,dest) #define chrmatch(i,j) (strchr(i,j) != NULL) #define strmatch(i,j) (strstr(i,j) != NULL) /* * グローバル変数の文字列 * 概要は冒頭の「グローバル変数の使い方」参照。 */ #ifndef JS char *self, *dest, *head, *tail; #else var self, dest, head, tail; #endif /* * 配列の定義 */ /* 配列のサイズ */ #define sizeSy 46 #define sizeJp 80 #define sizeZi 105 #define sizeNoEu 11 #define sizeEn 2 #define sizeEnok 6 #define sizeYl 9 #define sizeYlok 1 #define sizeUl 4 #define sizeUlok 3 #define sizeNoAt 32 #define sizeIt 40 #define sizeId 120 #define sizeIe 22 #define sizeVa 18 #define sizeNm 12 #define sizeNoI2 11 #define sizeNoI3 70 #define sizeI4 40 #define sizeI5 25 #define sizeI6 8 #define sizeI7 8 #define sizeI8 2 #define sizeI9 2 #define sizeI10 1 /* 配列の宣言 */ #ifndef JS char *es[sizeSy], *sy[sizeSy]; char *noi2[sizeNoI2], *noi3[sizeNoI3]; char *i4[sizeI4], *i5[sizeI5], *i6[sizeI6]; char *i7[sizeI7], *i8[sizeI8], *i9[sizeI9], *i10[sizeI10]; char *jr[sizeJp], *jc[sizeJp]; char *zr[sizeZi], *zc[sizeZi]; char *noeu[sizeNoEu]; char *en[sizeEn], *enok[sizeEnok]; char *yl[sizeYl], *ylok[sizeYlok]; char *ul[sizeUl], *ulok[sizeUlok]; char *noat[sizeNoAt]; char *it[sizeIt]; char *id[sizeId]; char *ie[sizeIe], *ka[sizeIe]; char *va[sizeVa]; char *num[sizeNm]; #else sy = new Array(sizeSy); es = new Array(sizeSy); noi2 = new Array(sizeNoI2); noi3 = new Array(sizeNoI3); i4 = new Array(sizeI4); i5 = new Array(sizeI5); i6 = new Array(sizeI6); i7 = new Array(sizeI7); i8 = new Array(sizeI8); i9 = new Array(sizeI9); i10 = new Array(sizeI10); jr = new Array(sizeJp); jc = new Array(sizeJp); zr = new Array(sizeZi); zc = new Array(sizeZi); noeu = new Array(sizeNoEu); en = new Array(sizeEn); enok = new Array(sizeEnok); yl = new Array(sizeYl); ylok = new Array(sizeYlok); ul = new Array(sizeUl); ulok = new Array(sizeUlok); noat = new Array(sizeNoAt); it = new Array(sizeIt); id = new Array(sizeId); ie = new Array(sizeIe); ka = new Array(sizeIe); va = new Array(sizeVa); num = new Array(sizeNm); #endif #ifndef JS /* 配列の初期化はＣでは関数で行う */ void initialize(void){ #endif /* * 句読点の配列の初期化 */ es[0] = "~SP|_"; sy[0] = " "; es[1] = "~ES|_"; sy[1] = "!"; es[2] = "~OP|_"; sy[2] = "("; es[3] = "~CL|_"; sy[3] = ")"; es[4] = "~ST|_"; sy[4] = "*"; es[5] = "~PL|_"; sy[5] = "+"; es[6] = "~CM|_"; sy[6] = ","; es[7] = "~HY|_"; sy[7] = "-"; es[8] = "~PE|_"; sy[8] = "."; es[9] = "~SL|_"; sy[9] = "/"; es[10]= "~ZE|_"; sy[10]= "0"; es[11]= "~ON|_"; sy[11]= "1"; es[12]= "~TW|_"; sy[12]= "2"; es[13]= "~TR|_"; sy[13]= "3"; es[14]= "~FO|_"; sy[14]= "4"; es[15]= "~FV|_"; sy[15]= "5"; es[16]= "~SX|_"; sy[16]= "6"; es[17]= "~SV|_"; sy[17]= "7"; es[18]= "~EI|_"; sy[18]= "8"; es[19]= "~NN|_"; sy[19]= "9"; es[20]= "~CN|_"; sy[20]= ":"; es[21]= "~SC|_"; sy[21]= ";"; es[22]= "~LT|_"; sy[22]= "<"; es[23]= "~EQ|_"; sy[23]= "="; es[24]= "~GT|_"; sy[24]= ">"; es[25]= "~QU|_"; sy[25]= "?"; es[26]= "~AT|_"; sy[26]= "@"; es[27]= "~LS|_"; sy[27]= "["; es[28]= "~RS|_"; sy[28]= "]"; es[29]= "~LB|_"; sy[29]= "{"; es[30]= "~RB|_"; sy[30]= "}"; es[31]= "~SQ|_"; sy[31]= "'"; es[32]= "~DQ|_"; sy[32]= "\""; es[33]= "~CR|_"; sy[33]= "\r"; es[34]= "~LF|_"; sy[34]= "\n"; es[35]= "~TB|_"; sy[35]= "\t"; es[36]= "~SH|_"; sy[36]= "#"; es[37]= "~DL|_"; sy[37]= "$"; es[38]= "~PC|_"; sy[38]= "%"; es[39]= "~AM|_"; sy[39]= "&"; es[40]= "~HT|_"; sy[40]= "^"; es[41]= "~BQ|_"; sy[41]= "`"; es[42]= "~YE|_"; sy[42]= "\\"; es[43]= "~LL|_"; sy[43]= "_"; es[44]= "~TD|_"; sy[44]= "~"; /*JS では削除される文字*/ es[45]= "~VB|_"; sy[45]= "|"; /*JS では削除される文字*/ /* 他の値 ~BG|_ [始端] ~FN|_ [終端] ~QT|_ [移動中止] ~FR|_ [縮合環] ~AC|_ [酸] ~AS|_ [大文字の後のase] ~NL|_ [ゼロ幅] ~BS|_ [直前の空白を削除] ~BB|_ [BS経由でスペースの代用] ~SS|_ [空白の代用] ~PS|_ [直後の空白を削除] ~UP|_ [大文字] ~LO|_ [小文字] ~GL|_ [ガリウム酸/没食子酸] ~AH|_ [酸性水素/ミュオニウム] ~DA|_ [第一塩、第二塩] ~HN|_ [水素の例外処理] ~AR|_ [アリール] ~YL|_ [イリデンなど] ~SN|_ [スズ] ~KK|_ [漢字] */ /* 二文字の英字列で、イタリックにしないもの（大小区別なし）*/ noi2[0] = "al"; noi2[1] = "ol"; noi2[2] = "yl"; noi2[3] = "en"; noi2[4] = "yn"; noi2[5] = "bi"; noi2[6] = "di"; noi2[7] = "de"; noi2[8] = "id"; noi2[9] = "io"; noi2[10]= "ic"; /* * 三文字の英字列で、イタリックにしないもの（大小区別なし） * OCT-8, NON-azoxy, -OSe- は別途対処する。 */ noi3[0] = "alk"; noi3[1] = "eth"; noi3[2] = "but"; noi3[3] = "hex"; noi3[4] = "oct"; noi3[5] = "non"; noi3[6] = "dec"; noi3[7] = "tri"; noi3[8] = "bis"; noi3[9] = "kis"; noi3[10]= "ane"; noi3[11]= "ene"; noi3[12]= "ine"; noi3[13]= "one"; noi3[14]= "yne"; noi3[15]= "ano"; noi3[16]= "eno"; noi3[17]= "ino"; noi3[18]= "ono"; noi3[19]= "yno"; noi3[20]= "aza"; noi3[21]= "azi"; noi3[22]= "azo"; noi3[23]= "azy"; noi3[24]= "oxa"; noi3[25]= "oxo"; noi3[26]= "oxy"; noi3[27]= "oic"; noi3[28]= "oyl"; noi3[29]= "ium"; noi3[30]= "hen"; noi3[31]= "apo"; noi3[32]= "des"; noi3[33]= "iso"; noi3[34]= "neo"; noi3[35]= "nor"; noi3[36]= "ion"; noi3[37]= "mer"; noi3[38]= "ter"; noi3[39]= "tin"; noi3[40]= "ate"; noi3[41]= "ete"; noi3[42]= "ite"; noi3[43]= "ide"; noi3[44]= "ole"; noi3[45]= "ato"; noi3[46]= "eto"; noi3[47]= "ito"; noi3[48]= "olo"; noi3[49]= "ulo"; noi3[50]= "ylo"; noi3[51]= "uid"; noi3[52]= "gel"; noi3[53]= "gas"; noi3[54]= "ase"; noi3[55]= "ose"; noi3[56]= "cub"; noi3[57]= "buf"; noi3[58]= "car"; noi3[59]= "cev"; noi3[60]= "con"; noi3[61]= "gon"; noi3[62]= "hop"; noi3[63]= "lup"; noi3[64]= "pin"; noi3[65]= "ros"; noi3[66]= "tax"; noi3[67]= "urs"; noi3[68]= "tar"; noi3[69]= "sol"; /* * イタリックの配列の初期化 */ i4[0] = "beta"; i4[1] = "zeta"; i4[2] = "iota"; i4[3] = "endo"; i4[4] = "anti"; i4[5] = "tert"; i4[6] = "peri"; i4[7] = "pros"; i4[8] = "tele"; i4[9] = "meso"; i4[10]= "ambo"; i4[11]= "keto"; i4[12]= "ribo"; i4[13]= "xylo"; i4[14]= "lyxo"; i4[15]= "allo"; i4[16]= "gulo"; i4[17]= "muco"; i4[18]= "talo"; i4[19]= "nido"; i4[20]= "asym"; i4[21]= "stat"; i4[22]= "prim"; i4[23]= "VIII"; i4[24]= "TBPY"; i4[25]= "PBPY"; i4[26]= "SAPR"; i4[27]= "HBPY"; i4[28]= "NADH"; i4[29]= "NADP"; i4[30]= "tRNA"; i4[31]= "mRNA"; i4[32]= "rRNA"; i4[33]= "UDPG"; i4[34]= "dATP"; i4[35]= "dUTP"; i4[36]= "SeSe"; i4[37]= "SeTe"; i4[38]= "TeSe"; i4[39]= "TeTe"; i5[0] = "alpha"; i5[1] = "gamma"; i5[2] = "delta"; i5[3] = "theta"; i5[4] = "kappa"; i5[5] = "sigma"; i5[6] = "omega"; i5[7] = "trans"; i5[8] = "threo"; i5[9] = "altro"; i5[10]= "gluco"; i5[11]= "manno"; i5[12]= "chiro"; i5[13]= "retro"; i5[14]= "cyclo"; i5[15]= "hapto"; i5[16]= "block"; i5[17]= "graft"; i5[18]= "quasi"; i5[19]= "amphi"; i5[20]= "unsym"; i5[21]= "NADPH"; i5[22]= "closo"; i5[23]= "hypho"; i5[24]= "klado"; i6[0] = "lambda"; i6[1] = "scyllo"; i6[2] = "active"; i6[3] = "cisoid"; i6[4] = "quadro"; i6[5] = "abcdeg"; /*corrinoids*/ i6[6] = "catena"; i6[7] = "rotaxa"; i7[0] = "epsilon"; i7[1] = "omicron"; i7[2] = "upsilon"; i7[3] = "glycero"; i7[4] = "erythro"; i7[5] = "arabino"; i7[6] = "galacto"; i7[7] = "arachno"; i8[0] = "aldehydo"; i8[1] = "transoid"; i9[0] = "triangulo"; i9[1] = "octahedro"; i10[0]= "tetrahedro"; /* * 日本文字の配列の初期化 */ jc[ 0]= "ア"; jr[ 0]= "QA_"; jc[ 1]= "イ"; jr[ 1]= "QI_"; jc[ 2]= "ウ"; jr[ 2]= "QU_"; jc[ 3]= "エ"; jr[ 3]= "QE_"; jc[ 4]= "オ"; jr[ 4]= "QO_"; jc[ 5]= "カ"; jr[ 5]= "KA_"; jc[ 6]= "キ"; jr[ 6]= "KI_"; jc[ 7]= "ク"; jr[ 7]= "KU_"; jc[ 8]= "ケ"; jr[ 8]= "KE_"; jc[ 9]= "コ"; jr[ 9]= "KO_"; jc[10]= "ガ"; jr[10]= "GA_"; jc[11]= "ギ"; jr[11]= "GI_"; jc[12]= "グ"; jr[12]= "GU_"; jc[13]= "ゲ"; jr[13]= "GE_"; jc[14]= "ゴ"; jr[14]= "GO_"; jc[15]= "サ"; jr[15]= "SA_"; jc[16]= "シ"; jr[16]= "SI_"; jc[17]= "ス"; jr[17]= "SU_"; jc[18]= "セ"; jr[18]= "SE_"; #ifdef WITH_BACK_SLASH jc[19]= "ソ\"; jr[19]= "SO_"; #else jc[19]= "ソ"; jr[19]= "SO_"; #endif jc[20]= "ザ"; jr[20]= "ZA_"; jc[21]= "ジ"; jr[21]= "ZI_"; jc[22]= "ズ"; jr[22]= "ZU_"; jc[23]= "ゼ"; jr[23]= "ZE_"; jc[24]= "ゾ"; jr[24]= "ZO_"; jc[25]= "タ"; jr[25]= "TA_"; jc[26]= "チ"; jr[26]= "TI_"; jc[27]= "ツ"; jr[27]= "TU_"; jc[28]= "テ"; jr[28]= "TE_"; jc[29]= "ト"; jr[29]= "TO_"; jc[30]= "ダ"; jr[30]= "DA_"; jc[31]= "ヂ"; jr[31]= "DI_"; jc[32]= "ヅ"; jr[32]= "DU_"; jc[33]= "デ"; jr[33]= "DE_"; jc[34]= "ド"; jr[34]= "DO_"; jc[35]= "ナ"; jr[35]= "NA_"; jc[36]= "ニ"; jr[36]= "NI_"; jc[37]= "ヌ"; jr[37]= "NU_"; jc[38]= "ネ"; jr[38]= "NE_"; jc[39]= "ノ"; jr[39]= "NO_"; jc[40]= "ハ"; jr[40]= "HA_"; jc[41]= "ヒ"; jr[41]= "HI_"; jc[42]= "フ"; jr[42]= "HU_"; jc[43]= "ヘ"; jr[43]= "HE_"; jc[44]= "ホ"; jr[44]= "HO_"; jc[45]= "バ"; jr[45]= "BA_"; jc[46]= "ビ"; jr[46]= "BI_"; jc[47]= "ブ"; jr[47]= "BU_"; jc[48]= "ベ"; jr[48]= "BE_"; jc[49]= "ボ"; jr[49]= "BO_"; jc[50]= "パ"; jr[50]= "PA_"; jc[51]= "ピ"; jr[51]= "PI_"; jc[52]= "プ"; jr[52]= "PU_"; jc[53]= "ペ"; jr[53]= "PE_"; jc[54]= "ポ"; jr[54]= "PO_"; jc[55]= "マ"; jr[55]= "MA_"; jc[56]= "ミ"; jr[56]= "MI_"; jc[57]= "ム"; jr[57]= "MU_"; jc[58]= "メ"; jr[58]= "ME_"; jc[59]= "モ"; jr[59]= "MO_"; jc[60]= "ヤ"; jr[60]= "YA_"; jc[61]= "ユ"; jr[61]= "YU_"; jc[62]= "ヨ"; jr[62]= "YO_"; jc[63]= "ラ"; jr[63]= "RA_"; jc[64]= "リ"; jr[64]= "RI_"; jc[65]= "ル"; jr[65]= "RU_"; jc[66]= "レ"; jr[66]= "RE_"; jc[67]= "ロ"; jr[67]= "RO_"; jc[68]= "ワ"; jr[68]= "WA_"; jc[69]= "ン"; jr[69]= "NN_"; jc[70]= "ァ"; jr[70]= "LA_"; jc[71]= "ィ"; jr[71]= "LI_"; jc[72]= "ゥ"; jr[72]= "LU_"; jc[73]= "ェ"; jr[73]= "LE_"; jc[74]= "ォ"; jr[74]= "LO_"; jc[75]= "ャ"; jr[75]= "XA_"; jc[76]= "ュ"; jr[76]= "XU_"; jc[77]= "ョ"; jr[77]= "XO_"; jc[78]= "ッ"; jr[78]= "TT_"; jc[79]= "ー"; jr[79]= "HH_"; zc[ 0] ="一"; zr[ 0] = "$1_"; zc[ 1] ="二"; zr[ 1] = "$2_"; zc[ 2] ="三"; zr[ 2] = "$3_"; zc[ 3] ="四"; zr[ 3] = "$4_"; zc[ 4] ="五"; zr[ 4] = "$5_"; zc[ 5] ="六"; zr[ 5] = "$6_"; zc[ 6] ="七"; zr[ 6] = "$7_"; zc[ 7] ="八"; zr[ 7] = "$8_"; zc[ 8] ="九"; zr[ 8] = "$9_"; #ifdef WITH_BACK_SLASH zc[ 9] ="十\"; zr[ 9] = "$10_"; #else zc[ 9] ="十"; zr[ 9] = "$10_"; #endif zc[10] ="酸"; zr[10] = "$SAN_"; zc[11] ="化"; zr[11] = "$KA_"; zc[12] ="物"; zr[12] = "$BUTU_"; zc[13] ="塩"; zr[13] = "$EN_"; zc[14] ="次"; zr[14] = "$HYP_"; zc[15] ="亜"; zr[15] = "$A_"; zc[16] ="過"; zr[16] = "$PER_"; zc[17] ="水"; zr[17] = "$SUI_"; zc[18] ="酢"; zr[18] = "$SAKU_"; zc[19] ="酪"; zr[19] = "$RAKU_"; zc[20] ="吉草"; zr[20] = "$VL_"; zc[21] ="安息香"; zr[21] = "$BZ_"; zc[22] ="没食子"; zr[22] = "$MOT_"; zc[23] ="酒"; zr[23] = "$SAKE_"; zc[24] ="石"; zr[24] = "$SEKI_"; zc[25] ="乳"; zr[25] = "$NYU_"; zc[26] ="葉"; zr[26] = "$YOU_"; zc[27] ="硫"; zr[27] = "$RYU_"; zc[28] ="硝"; zr[28] = "$SYO_"; zc[29] ="炭"; zr[29] = "$TAN_"; zc[30] ="金"; zr[30] = "$KIN_"; zc[31] ="銀"; zr[31] = "$GIN_"; zc[32] ="銅"; zr[32] = "$DOU_"; zc[33] ="鉄"; zr[33] = "$TETU_"; zc[34] ="白"; zr[34] = "$SIRO_"; zc[35] ="窒"; zr[35] = "$TITU_"; zc[36] ="素"; zr[36] = "$SO_"; zc[37] ="鉛"; zr[37] = "$NAM_"; zc[38] ="黄"; zr[38] = "$OU_"; zc[39] ="臭"; zr[39] = "$SYU_"; zc[40] ="馬"; zr[40] = "$UMA_"; zc[41] ="尿"; zr[41] = "$NYO_"; zc[42] ="和"; zr[42] = "$WA_"; zc[43] ="黒"; zr[43] = "$KURO_"; zc[44] ="超"; zr[44] = "$TYO_"; zc[45] ="重"; zr[45] = "$OMO_"; zc[46] ="多"; zr[46] = "$OOI_"; zc[47] ="第"; zr[47] = "$DAI_"; zc[48] ="無"; zr[48] = "$MU_"; zc[49] ="基"; zr[49] = "$KI_"; zc[50] ="皮"; zr[50] = "$HI_"; zc[51] ="環"; zr[51] = "$KAN_"; zc[52] ="状"; zr[52] = "$JOU_"; zc[53] ="角"; zr[53] = "$KADO_"; zc[54] ="核"; zr[54] = "$KAKU_"; zc[55] ="雷"; zr[55] = "$RAI_"; zc[56] ="糖"; zr[56] = "$TOU_"; zc[57] ="菊"; zr[57] = "$KIKU_"; zc[58] ="単"; zr[58] = "$MONO_"; zc[59] ="半"; zr[59] = "$HAN_"; zc[60] ="合"; zr[60] = "$GOU_"; zc[61] ="質"; zr[61] = "$SITSU_"; zc[62] ="酵"; zr[62] = "$KOU_"; zc[63] ="属"; zr[63] = "$ZOKU_"; zc[64] ="脂"; zr[64] = "$SHI_"; zc[65] ="肪"; zr[65] = "$BOU_"; zc[66] ="色"; zr[66] = "$IRO_"; zc[67] ="性"; zr[67] = "$SEI_"; zc[68] ="双"; zr[68] = "$SOU_"; zc[69] ="両"; zr[69] = "$RYO_"; zc[70] ="補"; zr[70] = "$HO_"; zc[71] ="脱"; zr[71] = "$DAT_"; zc[72] ="不足"; zr[72] = "$HUSOK_"; zc[73] ="過剰"; zr[73] = "$KAJO_"; zc[74] ="共役"; zr[74] = "$CONJ_"; zc[75] ="粘液"; zr[75] = "$NENEK_"; zc[76] ="還元"; zr[76] = "$RED_"; zc[77] ="転"; zr[77] = "$TEN_"; zc[78] ="写"; zr[78] = "$SYA_"; zc[79] ="移"; zr[79] = "$II_"; zc[80] ="細胞"; zr[80] = "$CYT_"; zc[81] ="内"; zr[81] = "$NAI_"; zc[82] ="外"; zr[82] = "$GAI_"; zc[83] ="加"; zr[83] = "$ADD_"; zc[84] ="分解"; zr[84] = "$DEC_"; zc[85] ="活"; zr[85] = "$KAT_"; zc[86] ="分子"; zr[86] = "$MOL_"; zc[87] ="種"; zr[87] = "$SHU_"; zc[88] ="級"; zr[88] = "$KYU_"; zc[89] ="原子"; zr[89] = "$ATOM_"; zc[90] ="芳香"; zr[90] = "$AR_"; zc[91] ="族"; zr[91] = "$ZK_"; zc[92] ="複製"; zr[92] = "$DUPL_"; zc[93] ="式"; zr[93] = "$SIKI_"; zc[94] ="体"; zr[94] = "$BODY_"; zc[95] ="供与"; zr[95] = "$DON_"; zc[96] ="受容"; zr[96] = "$ACC_"; zc[97] ="因子"; zr[97] = "$FAC_"; zc[98] ="残"; zr[98] = "$ZAN_"; zc[99] ="有"; zr[99] = "$YUU_"; zc[100]="機"; zr[100]= "$KIY_"; zc[101]="非"; zr[101]= "$NON_"; zc[102]="反"; zr[102]= "$ANTI_"; zc[103]="樹"; zr[103]= "$TREE_"; zc[104]="胆汁"; zr[104]= "$BILE_"; /* * ide陰イオン */ id[0] = "hydr"; id[1] = "deuter"; id[2] = "trit"; id[3] = "bor"; id[4] = "carb"; id[5] = "acetyl"; id[6] = "nitr"; id[7] = "cyan"; id[8] = "az"; id[9] = "ox"; id[10]= "ozon"; id[11]= "fluor"; id[12]= "silic"; id[13]= "phosph"; id[14]= "sulf"; id[15]= "chlor"; id[16]= "arsen"; id[17]= "selen"; id[18]= "brom"; id[19]= "antimon"; id[20]= "tellur"; id[21]= "iod"; id[22]= "halogen"; id[23]= "hal"; id[24]= "chalcogen"; id[25]= "stann"; id[26]= "plumb"; id[27]= "astat"; id[28]= "prot"; id[29]= "muon"; id[30]= "germ"; id[31]= "bismuth"; id[32]= "polon"; id[33]= "alumin"; id[34]= "gall"; id[35]= "ind"; id[36]= "thall"; id[37]= "zinc"; id[38]= "cadm"; id[39]= "mercur"; id[40]= "cupr"; id[41]= "argent"; id[42]= "aur"; id[43]= "nickel"; id[44]= "pallad"; id[45]= "platin"; id[46]= "cobalt"; id[47]= "rhod"; id[48]= "irid"; id[49]= "ferr"; id[50]= "ruthen"; id[51]= "osm"; id[52]= "mangan"; id[53]= "technet"; id[54]= "rhen"; id[55]= "chrom"; id[56]= "molybden"; id[57]= "tungst"; id[58]= "vanad"; id[59]= "niob"; id[60]= "tantal"; id[61]= "titan"; id[62]= "zircon"; id[63]= "hafn"; id[64]= "scand"; id[65]= "yttr"; id[66]= "lanthan"; id[67]= "cer"; id[68]= "praseodym"; id[69]= "neodym"; id[70]= "prometh"; id[71]= "samar"; id[72]= "europ"; id[73]= "gadolin"; /*terb -> erb */ id[74]= "dyspros"; id[75]= "holm"; id[76]= "erb"; id[77]= "thul"; /*ytterb -> erb */ id[78]= "lutet"; id[79]= "actin"; id[80]= "thor"; /*protactin -> actin */ id[81]= "uran"; id[82]= "neptun"; id[83]= "pluton"; id[84]= "americ"; id[85]= "cur"; id[86]= "berkel"; id[87]= "californ"; id[88]= "einstein"; id[89]= "ferm"; id[90]= "mendelev"; id[91]= "nobel"; id[92]= "lawrenc"; id[93]= "beryll"; id[94]= "magnes"; id[95]= "calc"; id[96]= "stront"; id[97]= "bar"; id[98]= "rad"; id[99]= "lith"; id[100]="natr"; id[101]="kal"; id[102]="rubid"; id[103]="ces"; /* also "caes" */ id[104]="franc"; id[105]="hel"; id[106]="neon"; id[107]="argon"; id[108]="krypton"; id[109]="xenon"; id[110]="radon"; id[111]="sod"; /*XXX*/ id[112]="potass"; /*XXX*/ id[113]="rutherford"; id[114]="dubn"; id[115]="seaborg"; id[116]="bohr"; id[117]="hass"; id[118]="meitner"; id[119]="pnict"; /* * ide の翻訳 */ ie[0] = "hydr%D_"; ka[0] = "$SUI_$SO_$KA_"; ie[1] = "bor%D_"; ka[1] = "$_HO_QU_$KA_"; ie[2] = "carb%D_"; ka[2] = "$TAN_$KA_"; ie[3] = "nitr%D_"; ka[3] = "$TITU_$KA_"; ie[4] = "cyan%D_"; ka[4] = "cyan$KA_"; ie[5] = "az%D_"; ka[5] = "QA_ZI_$KA_"; ie[6] = "hydrox%D_"; ka[6] = "$SUI_$SAN_$KA_"; ie[7] = "ox%D_"; ka[7] = "$SAN_$KA_"; ie[8] = "ozon%D_"; ka[8] = "QO_ZO_NN_$KA_"; ie[9] = "fluor%D_"; ka[9] = "$_HU_TT_$KA_"; ie[10]= "silic%D_"; ka[10]= "$_KE_QI_$KA_"; ie[11]= "phosph%D_"; ka[11]= "$_RI_NN_$KA_"; ie[12]= "sulf%D_"; ka[12]= "$RYU_$KA_"; ie[13]= "chlor%D_"; ka[13]= "$EN_$KA_"; ie[14]= "arsen%D_"; ka[14]= "$_HI_$KA_"; ie[15]= "brom%D_"; ka[15]= "$SYU_$KA_"; ie[16]= "antimon%D_"; ka[16]= "$_QA_NN_TI_MO_NN_$KA_"; ie[17]= "iod%D_"; ka[17]= "$_YO_QU_$KA_"; ie[18]= "hal%D_"; ka[18]= "$_HA_RO_GE_NN_$KA_"; ie[19]= "astat%D_"; ka[19]= "$_QA_SU_TA_TI_NN_$KA_"; ie[20]= "germ%D_"; ka[20]= "$_GE_RU_MA_NI_QU_MU_$KA_"; ie[21]= "acetyl%D_"; ka[21]= "$_QA_SE_TI_RE_NN_$KA_"; /* * ite陰イオン */ it[0] = "fluor"; it[1] = "chlor"; it[2] = "brom"; it[3] = "iod"; it[4] = "hal"; it[5] = "halogen"; it[6] = "sulf"; it[7] = "selen"; it[8] = "tellur"; it[9] = "thion"; it[10]= "nitr"; it[11]= "phosph"; it[12]= "phosphon"; it[13]= "phosphin"; it[14]= "phosphen"; it[15]= "arsen"; it[16]= "arson"; it[17]= "arsin"; it[18]= "arsenen"; it[19]= "antimon"; it[20]= "stibon"; it[21]= "stibin"; it[22]= "peroxo"; it[23]= "thio"; it[24]= "seleno"; it[25]= "telluro"; it[26]= "fluorid"; it[27]= "chlorid"; it[28]= "bromid"; it[29]= "iodid"; it[30]= "hydrazid"; it[31]= "amid"; it[32]= "imid"; it[33]= "azid"; it[34]= "nitrid"; it[35]= "cyanid"; it[36]= "cyanatid"; it[37]= "hydrazon"; it[38]= "stann"; it[39]= "plumb"; /* 酸でない'-ate' */ /* spaninvert()中str0,str1の制約から、27(=32-4-1)文字以内とせよ */ noat[0] = "ol"; noat[1] = "hydr"; noat[2] = "ammoni"; noat[3] = "conjug"; noat[4] = "alanin"; noat[5] = "arginin"; noat[6] = "asparagin"; noat[7] = "cystein"; noat[8] = "glutamin"; noat[9] = "glycin"; noat[10]= "histidin"; noat[11]= "leucin"; noat[12]= "lysin"; noat[13]= "ethionin"; /* methio-, ethio- */ noat[14]= "prolin"; noat[15]= "serin"; noat[16]= "threonin"; noat[17]= "tryptophan"; noat[18]= "tyrosin"; noat[19]= "valin"; noat[20]= "citrullin"; noat[21]= "cystin"; noat[22]= "ornithin"; noat[23]= "sarcosin"; noat[24]= "thyronin"; noat[25]= "thyroxin"; noat[26]= "porphyrin"; noat[27]= "phthalocyanin"; noat[28]= "diazo"; noat[29]= "diazot"; noat[30]= "chel"; noat[31]= "ly"; /* euphonyを禁ずる場合 */ noeu[0] = "a@"; noeu[1] = "i@"; noeu[2] = "e@"; noeu[3] = "o@"; noeu[4] = "y@"; noeu[5] = "u@"; noeu[6] = "yl@"; noeu[7] = "bis@"; noeu[8] = "tris@"; noeu[9] = "kis@"; noeu[10]= "ium@"; en[0] = "an@"; /* spiro[ane]-, cyclophan- */ en[1] = "en@"; /* en-yn */ yl[0] = "an@"; yl[1] = "en@"; yl[2] = "yn@"; yl[3] = "in@"; yl[4] = "on@"; yl[5] = "et@"; yl[6] = "id@"; yl[7] = "os@"; yl[8] = "ol@"; ul[0] = "os@"; /* os-ulose */ ul[1] = "ol@"; ul[2] = "en@"; ul[3] = "yn@"; /* noeu[] etc.に反してやはりeuphonyを認める */ enok[0] = "olean@"; /* olean-ene */ enok[1] = "formosan@"; /* formosan-ene */ enok[2] = "hasuban@"; /* hasuban-ene */ enok[3] = "guai@"; /* guai-ene */ enok[4] = "lycoren@"; /* lycoren-ene */ enok[5] = "roten@"; /* roten-ene */ ylok[0] = "non@"; /* non-3-yl */ ulok[0] = "icos@"; /* icos-ulose */ ulok[1] = "docos@"; /* docos-ulose */ ulok[2] = "acos@"; /* tetracos-ulose */ va[0] = "~OP|_~ZE|_~CL|_"; va[1] = "~OP|_~^I|_~CL|_"; va[2] = "~OP|_~^I|_~^I|_~CL|_"; va[3] = "~OP|_~^I|_~^I|_~^I|_~CL|_"; va[4] = "~OP|_~^I|_~^V|_~CL|_"; va[5] = "~OP|_~^V|_~CL|_"; va[6] = "~OP|_~^V|_~^I|_~CL|_"; va[7] = "~OP|_~^V|_~^I|_~^I|_~CL|_"; va[8] = "~OP|_~^V|_~^I|_~^I|_~^I|_~CL|_"; va[9] = "~OP|_~HY|_~^I|_~CL|_"; va[10]= "~OP|_~HY|_~^I|_~^I|_~CL|_"; va[11]= "~OP|_~HY|_~^I|_~^I|_~^I|_~CL|_"; va[12]= "~OP|_~HY|_~^I|_~^V|_~CL|_"; va[13]= "~OP|_~HY|_~^V|_~CL|_"; va[14]= "~OP|_~HY|_~^V|_~^I|_~CL|_"; va[15]= "~OP|_~HY|_~^V|_~^I|_~^I|_~CL|_"; va[16]= "~OP|_~HY|_~^V|_~^I|_~^I|_~^I|_~CL|_"; va[17]= "~OP|_~^I|_~^I|_~^I|_~CM|_~^V|_~CL|_"; num[0] = ""; num[1] = "hen"; num[2] = "do"; num[3] = "tri"; num[4] = "tetra"; num[5] = "penta"; num[6] = "hexa"; num[7] = "hepta"; num[8] = "octa"; num[9] = "nona"; num[10]= "deca"; num[11]= "undeca"; /* 以上、配列の定義 */ #ifndef JS } /* JSでは関数にしないので閉じ不要 */ #endif #ifndef NC /****************************************************************** * * 置換関数 [as like s/$bef/$aft/g of Perl] * befがaftの部分文字列を含んでも無限ループにならないよう改善。 * ******************************************************************/ #endif /* NC */ #ifndef JS void g(char * bef, char * aft) { char *p, *a, *d, *s; size_t blen; p = strstr(self, bef); if (!p) return; s = self; d = dest; blen = strlen(bef); while (p) { while (s < p) *d++ = *s++; for (a = aft; *a;) *d++ = *a++; s += blen; p = strstr(s, bef); } while (*s) *d++ = *s++; *d = '\0'; #ifdef DEBUGGING if (d - dest > destlen) destlen = d - dest + 1; if (destlen > selflen) selflen = destlen; #endif self2dest(); } #else function g(bef,aft) { if (self.indexOf(bef) == -1) { return; } var pos = 0; dest = ""; while ((pos = self.indexOf(bef)) != -1) { dest += self.substring(0,pos) + aft; self = self.substring(pos + bef.length, self.length); } dest += self; self = dest; } #endif #ifndef NC /****************************************************************** * * 置換関数（先読み） [as like s/$bef(?=[$list])/$aft/g of Perl] * ******************************************************************/ #endif /* NC */ #ifndef JS void glookahead(char* bef, char* list, char* aft) { char *p, *a, *d, *s; size_t blen; p = strstr(self, bef); if (!p) return; s = self; d = dest; blen = strlen(bef); while (p) { while (s < p) { *d++ = *s++; } if (strchr(list, s[blen])) { s += blen; for (a = aft; *a;) *d++ = *a++; } else { *d++ = *s++; /* go ahead by a byte */ } p = strstr(s, bef); } while (*s) *d++ = *s++; *d = '\0'; #ifdef DEBUGGING if (d - dest > destlen) destlen = d - dest + 1; if (destlen > selflen) selflen = destlen; #endif self2dest(); } #else function glookahead(bef,list,aft) { if (self.indexOf(bef) == -1) { return; } var pos = 0; var blen = bef.length; dest = ""; while ((pos = self.indexOf(bef)) != -1) { if (list.indexOf(self.substring(pos + blen, pos + blen + 1)) != -1) { dest += self.substring(0,pos) + aft; self = self.substring(pos + blen, self.length); } else { dest += self.substring(0, pos + 1); self = self.substring(pos + 1, self.length); } } dest += self; self = dest; } #endif #ifndef NC /****************************************************************** * * 置換関数（後読み） [as like s/(?<=[$list])$bef/$aft/g of Perl] * ******************************************************************/ #endif /* NC */ #ifndef JS void glookbehind(char* list, char* bef, char* aft) { char *p, *a, *d, *s; size_t blen; p = strstr(self, bef); if (!p) return; s = self; d = dest; blen = strlen(bef); while (p) { while (s < p) { *d++ = *s++; } if (s != self && strchr(list, s[-1])) { s += blen; for (a = aft; *a;) *d++ = *a++; } else { *d++ = *s++; /* go ahead by a byte */ } p = strstr(s, bef); } while (*s) *d++ = *s++; *d = '\0'; #ifdef DEBUGGING if (d - dest > destlen) destlen = d - dest + 1; if (destlen > selflen) selflen = destlen; #endif self2dest(); } #else function glookbehind(list,bef,aft) { if (self.indexOf(bef) == -1) { return; } var pos = 0; var blen = bef.length; dest = ""; while ((pos = self.indexOf(bef)) != -1) { if (pos > 0 && list.indexOf(self.substring(pos - 1, pos)) != -1) { dest += self.substring(0,pos) + aft; self = self.substring(pos + blen, self.length); } else { dest += self.substring(0, pos + 1); self = self.substring(pos + 1, self.length); } } dest += self; self = dest; } #endif #ifndef NC /******************************************************************** * * 関数 cvtitalic() * * 句読点や数字にはさまれた部分がイタリックかどうか判定し、 * その部分を変換する。 * それらは "~^X|_"（大文字）か "~`X|_"（小文字）の形式をとる。 * それ以外の英字は小文字に変換する。 * なお、以後の処理では、残った小文字の部分の解釈と変換を主とする。 * * 例えば、"~BG|_N~HY|_tert~HY|_butylacetamide~FN|_" なら、 * N と tert をイタリックと判定しなければならない。 * ********************************************************************/ /* 変数 abc a-z の文字列（定数） i 繰り返し変数 isIt フラグ no_italic=0 yes_italic=1 pos '_' の位置。 pct 英字 key の直後の句読点 lastpct 英字 key の直前の句読点 key 先頭から切り出した英字部分（Ｃではheadに） lenkey keyの長さ lowkey keyを小文字に変換した英文字列（Ｃではtailに） ch keyのある１文字（JS のみ） uc uppkeyのある１文字（JS のみ） */ #endif /* NC */ #ifndef JS void cvtitalic(void) #else function cvtitalic() #endif { #ifndef JS int i, isIt, lenkey; char *s, *key, *lowkey; char *pos, *pct_ptr, pct[8], lastpct[8]; char *abc = LOWER; #else var i, isIt, pos, key, lenkey, lowkey, pct, lastpct; var abc = LOWER; #endif g("_Base~", "_base~"); /* not B-ase */ glookbehind(UPPER, "ase~", "~AS|_~"); /* g() using dest */ strcpy(dest,""); /* also JS */ #ifndef JS s = self; while ((pos = strchr(s,'_')) != NULL) { #else while ((pos = self.indexOf('_')) != -1) { #endif strcpy(lastpct,pct); #ifndef JS key = head; pct_ptr = pct; while (s <= pos-lenpct) *key++ = *s++; while (s <= pos) *pct_ptr++ = *s++; *key = *pct_ptr = '\0'; key = head; /* ポインタを先頭に戻す */ #else key = self.substring(0, pos+1-lenpct); pct = self.substring(pos+1-lenpct, pos+1); self = self.substring(pos+1, self.length); #endif isIt = 0; /* フラグの初期化 */ lenkey = strlen(key); /* keyの長さ */ /* also JS */ /* keyの大小揃え */ #ifndef JS key = head; lowkey = tail; while (*key) *lowkey++ = (char) tolower(*key++); *lowkey = '\0'; /* ポインタを先頭に戻す */ key = head; lowkey = tail; #else lowkey = key.toLowerCase(); #endif /* 一文字（大小とも）の場合、イタリック */ if (lenkey == 1) { isIt = 1; } /* UPPERaseの置き換えはイタリック */ else if (strEQ(pct,"~AS|_")) { isIt = 1; } /* 二文字（大小とも）の場合、noi2[] をみる */ else if (lenkey == 2) { isIt = 1; if (strEQ(key, "Bi") || strEQ(key, "de")) { if (strEQ(pct,"~HY|_") || strEQ(pct,"~OP|_") || strEQ(pct,"~LS|_") || strEQ(pct,"~LB|_") ) { isIt = 0; } } else if (strNE(key,"Al")) { for (i=0; i < sizeNoI2; i++) { if (strEQ(lowkey,noi2[i])) { isIt = 0; break; } } } } else if (lenkey == 3) { isIt = 1; for (i=0; i < sizeNoI3; i++) { if (strEQ(lowkey,noi3[i])) { isIt = 0; break; } } /* epi[1,4]dioxino etc.*/ if (strEQ(key, "epi") && !strEQ(pct,"~HY|_")) { isIt = 0; } if (strEQ(key, "cob") && strEQ(pct,"~OP|_")) { isIt = 0; } } /* 母音を含まなければイタリック */ /* NULL:-1 in JS */ else if (strchr(lowkey,'a') == NULL && strchr(lowkey,'e') == NULL && strchr(lowkey,'i') == NULL && strchr(lowkey,'o') == NULL && strchr(lowkey,'u') == NULL && strchr(lowkey,'y') == NULL ) { isIt = 1; } /* abc, def など連番の縮合位置の記号（小文字）*/ /* NULL:-1 in JS */ else if (strmatch(abc,key)) { isIt = 1; } /* stuva, stuvwxabcde など非連続の縮合位置の記号（小文字）。通常、 前半(例えばstuv)は後半(例えばab)より後だが、チェックしていない。 */ if (isIt == 0) #ifndef JS { char* pos_sec = strchr(abc,key[lenkey-1]); if (pos_sec) { size_t seclen = pos_sec - abc + 1; if (lenkey - seclen > 0 && key[lenkey - seclen] == 'a' && memEQ(abc, key + lenkey - seclen, seclen)) { char* pos_ini = strchr(abc,key[0]); if (pos_ini && memEQ(pos_ini, key, lenkey - seclen)) isIt = 1; } } } #else { var pos_sec = abc.indexOf(key.substring(lenkey-1,lenkey)); if (pos_sec != -1) { var seclen = pos_sec + 1; if (lenkey - seclen > 0 && (abc.indexOf(key.substring(lenkey - seclen,lenkey)) != -1) && (abc.indexOf(key.substring(0,lenkey - seclen)) != -1)) { isIt = 1; } } } #endif /* 特定のイタリック文字列 */ /* also JS */ if (isIt == 0) { if (lenkey == 4) { for (i=0; i < sizeI4; i++) { if (strEQ(key,i4[i])) { isIt = 1; break; } } if (strEQ(key, "keto") && strNE(pct,"~HY|_")) { isIt = 0; } } else if (lenkey == 5) { for (i=0; i < sizeI5; i++) { if (strEQ(key,i5[i])) { isIt = 1; break; } } /* "cyclo" の前がハイフンのとき (e.g. 5,7α-cyclo) 後がハイフンでないとき */ if (strEQ(key, "cyclo") && (strNE(pct,"~HY|_") || strEQ(lastpct,"~HY|_")) ) { isIt = 0; } /* HTMLタグの混入に対処 */ if (strEQ(lowkey, "small") && strNE(pct, "~HY|_")) { isIt = 1; } } else if (lenkey == 6) { for (i=0; i < sizeI6; i++) { if (strEQ(key,i6[i])) { isIt = 1; break; } } } else if (lenkey == 7) { for (i=0; i < sizeI7; i++) { if (strEQ(key,i7[i])) { isIt = 1; break; } } } else if (lenkey == 8) { for (i=0; i < sizeI8; i++) { if (strEQ(key,i8[i])) { isIt = 1; break; } } } else if (lenkey == 9) { for (i=0; i < sizeI9; i++) { if (strEQ(key,i9[i])) { isIt = 1; break; } } } else if (lenkey == 10) { for (i=0; i < sizeI10; i++) { if (strEQ(key,i10[i])) { isIt = 1; break; } } } /* 11文字以上はイタリックなし */ } /* 変換結果をdestの後ろにつなげる */ /* also JS */ if (isIt == 0) { strcat(dest, lowkey); strcat(dest, pct); } else { for (i=0; i 15) { strcat(dest, "ERROR [Too Long Key]"); s = pos + 1; continue; } #else while ((pos = self.indexOf('_')) != -1) { #endif keynext = 0; /* フラグの初期化 */ /* '_' を含むところまでkeyをコピー */ #ifndef JS for (k = key; s <= pos;) *k++ = *s++; *k = '\0'; #else key = self.substring(0,pos+1); self = self.substring(pos+1, self.length); #endif if (chrStrAt(key,0) == '~') { /* イタリックの英字。'^' を含むのが大。'`' を含むのが小。 */ #ifndef JS if (key[1] == '^') { key[3] = '\0'; strcat(dest, key+2); } else if (key[1] == '`') { key[2] += 0x20; /* tolower */ key[3] = '\0'; strcat(dest, key+2); } else if (key[1] == '&') { /* C のみ */ key[2] &= 0x7F; key[3] = '\0'; strcat(dest, key+2); } #else if (key.indexOf('^') != -1) { dest += key.substring(2,3); } else if (key.indexOf('`') != -1) { dest += key.substring(2,3).toLowerCase(); } #endif else { /* 句読点への変換 */ /* also JS */ for (i=0; i < sizeSy; i++) { if (strEQ(key,es[i])) { strcat(dest,sy[i]); break; } } } /* ~ で始まるものは変換先がなくても無視する */ continue; } if (chrStrAt(key,0) == '$') { /* 漢字への変換 */ if (chrStrAt(key,1) == '_') continue; for (i=0; i < sizeZi; i++) { if (strEQ(key,zr[i])) { strcat(dest,zc[i]); keynext++; break; } } } else { /* 仮名への変換 */ for (i=0; i < sizeJp; i++) { if (strEQ(key,jr[i])) { strcat(dest,jc[i]); keynext++; break; } } } if (!keynext) { strcat(dest, "ERROR ["); strcat(dest, key); strcat(dest, "]"); } } /* end while */ self2dest(); /* also JS */ } #ifndef NC /******************************************************************** * * euphony() * * 引数の文字列 ending について * 記号を挟んで直前の文字の後に vowel を補う * * but-2-ene, bicyclohept-3-yl, hex-2-ulose など * ********************************************************************/ /* 変数 i 繰り返し変数 flag フラグ（1: 'a'を付ける、0: '@'を除く） from "|_" + ending to "|_@" + ending *p selfにおける'@'の位置 *pp selfにおける'|_@'の位置 head 先頭から切り出した部分（グローバル） pct key の直後の句読点 dest '@' の前の文字列。head + pct + '@' に等しい（グローバル） tail '@' の後の文字列を保持（グローバル） */ #endif /* NC */ #ifndef JS void euphony(const char * ending, const char * vowel) #else function euphony(ending, vowel) #endif { #ifndef JS int i, flag; char from[8]; char to[8]; char *p, *pp, *s, *h, *d, *t; char *pct_ptr, pct[8]; #else var i, flag, from, to, p, pp, pct; #endif /* 語尾の前に @ を付加する */ strcpy(from, "|_"); strcpy(to, "|_@"); strcat(from, ending); strcat(to, ending); g(from,to); /* selfをスキャンする */ while ((p = strchr(self,'@')) != NULL) { flag = 1; pp = strstr(self,"|_@"); /* Is '@' before symbol? */ /* 先端から、headとpctを取り出す */ #ifndef JS s = self; d = dest; h = head; t = tail; pct_ptr = pct; while (s < p-lenpct) *d++ = *h++ = *s++; while (s < p) *d++ = *pct_ptr++ = *s++; *d++ = *s++; /* move '@' */ while (*s) *t++ = *s++; *pct_ptr = *h = *t = *d = '\0'; #else head = self.substring(0, p-lenpct); pct = self.substring(p-lenpct, p); dest = self.substring(0, p+1); /* '@' 含む */ tail = self.substring(p+1, self.length); /* '@'含まない */ #endif if (strEQ(pct,"~BG|_")) { /* 前が始端なら '@' は削除 */ strcpy(self,head); strcat(self,pct); strcat(self,tail); } else if (p == pp + 2) { /* 前が記号なら '@' を前に移動 */ strcpy(self,head); strcat(self,"@"); strcat(self,pct); strcat(self,tail); } else { for (i=0; i< sizeNoEu; i++) { if (strmatch(dest,noeu[i])) { flag=0; break; } } if (strEQ(ending,"en") || strEQ(ending,"yn")) { for (i=0; i< sizeEn; i++) { if (strmatch(dest,en[i])) { flag=0; break; } } for (i=0; i< sizeEnok; i++) { if (strmatch(dest,enok[i])) { flag=1; break; } } } else if (strEQ(ending,"ulo")) { for (i=0; i< sizeUl; i++) { if (strmatch(dest,ul[i])) { flag=0; break; } } for (i=0; i< sizeUlok; i++) { if (strmatch(dest,ulok[i])) { flag=1; break; } } } else if (strEQ(ending,"yl")) { for (i=0; i (II)~AC|_ */ for (iv = 0; iv < sizeVa; iv++) { strcpy(from,"~AC|_"); strcat(from, va[iv]); strcpy(to, va[iv]); strcat(to, "~AC|_"); g(from,to); } while ((p = strchr(self,'@')) != NULL) { pp = strstr(self,"|_@"); /* '@' が記号の前であるか */ #ifndef JS s = self; h = head; t = tail; pct_ptr = pct; while (s < p-lenpct) *h++ = *s++; while (s < p) *pct_ptr++ = *s++; s++; /* out '@' */ while (*s) *t++ = *s++; *pct_ptr = *h = *t = '\0'; #else head = self.substring(0, p-lenpct); pct = self.substring(p-lenpct, p); tail = self.substring(p+1, self.length); /* '@'含まない */ #endif if (strEQ(pct,"~BG|_")) { /* 前が始端なら '@' は削除 */ strcpy(self,head); strcat(self,pct); strcat(self,tail); } else if (strEQ(pct,"~AC|_")) { /* "~AC|_@" となったら削除 */ strcpy(self,head); strcat(self,tail); } else if (strEQ(pct,"~SP|_")) { /* 途中の "~SP|_" は削除 */ strcpy(self,head); strcat(self,"@"); strcat(self,tail); } else if (p == pp + 2) { /* 前が記号なら '@' を前に移動 */ strcpy(self,head); strcat(self,"@"); strcat(self,pct); strcat(self,tail); } else { strcpy(self,head); strcat(self,pct); strcat(self,tail); } } /* end while */ g("~AC|_","$SAN_"); } #ifndef NC /******************************************************************** ** ** substnum() ** ** 数詞の置換を一般化する ** ** substnum("?foo", "?bar", 3, 9); なら、 ** g("trifoo", "tribar") などを 3〜9の範囲で行う。 ** '?' の位置に倍数接頭辞があるものとみなす。 ** fromとtoには、'?'が１個ずつ含まれなければならない。 ** num[0] = "" なので、0 のときは ? のない置換を行う。 ** ** str0とstr1は自動変数なので、長さ管理を期待している。 ** とりあえず長さは 64 とした。長すぎるものを渡してはいけない。 ** ********************************************************************/ #endif /* NC */ #ifndef JS void substnum (char *from, char *to, int ini, int fin) { char str0[64], str1[64], *p, *pp; int i; #else function substnum (from, to, ini, fin) { var i, p, pp, str0, str1; #endif p = strchr(from,'?'); pp = strchr(to, '?'); if (p == NULL || pp == NULL) { /* '?' を含まない */ return; } if (ini < 0) { ini = 0; } if (fin >= sizeNm) { fin = sizeNm - 1; } for (i=fin; i>=ini; i--) { /* 0を最初にしてはダメ */ #ifndef JS memcpy(str0, from, p - from); str0[p - from] = '\0'; strcat(str0, num[i]); strcat(str0, p + 1); /* '?' の次の文字から */ memcpy(str1, to , pp - to); str1[pp - to] = '\0'; strcat(str1, num[i]); strcat(str1, pp + 1); #else str0 = from.substring(0, p) + num[i] + from.substring(p + 1, from.length); str1 = to.substring(0, pp) + num[i] + to.substring(pp + 1, to.length); #endif g(str0,str1); } g("?",""); /* 余計な '?' があったときの用心 */ } #ifndef NC /******************************************************************** ** ** translnum() ** ** 数字・接頭辞の翻訳を行う（99まで） ** ********************************************************************/ #endif /* NC */ #ifndef JS void translnum () { char *p, *s, *d, *h, *t; int numpct; #else function translnum () { var p, pct, numpct; #endif g("$","$TMP_$"); while ((p = strstr(self,"$TMP_")) != NULL) { numpct = 0; #ifndef JS /* 記号の部分は巻戻す */ while (self + lenpct < p) { if (memEQ(p-lenpct,"~",1) || memEQ(p-2,"|_",2)) { p -= lenpct; numpct++; } else { break; } } s = self; d = dest; h = head; t = tail; while (s < p) *h++ = *s++; while (s < p + numpct * lenpct) *d++ = *s++; while (s < p + (numpct+1) * lenpct) s++; while (*s) *t++ = *s++; *h = *t = *d = '\0'; #else while (lenpct < p) { pct = self.substring(p-5,p); if (pct.indexOf("~") == 0 && pct.indexOf("|_") == 3) { p -= lenpct; numpct++; } else { break; } } head = self.substring(0, p); dest = self.substring(p, p+numpct*lenpct); tail = self.substring(p + (numpct+1)*lenpct, self.length); #endif strcpy(self, head); /* 記号の前まで */ strcat(self, "$DUM_"); strcat(self, dest); /* 記号群の部分 */ strcat(self, tail); /* "$TMP_" の後 */ } /* end while */ g("hyper$", "$TYO_$"); g("super$", "$PER_$"); g("per$", "$PER_$"); g("sub$", "$HYP_$"); g("hypo$", "$HYP_$"); g("hemi$", "$HAN_$"); g("sesqui$","$3_$2_$"); /* $NUM_ は数詞であることを示す */ if (strmatch(self,"acont")) { g("acont$","aconta$"); substnum("?triaconta$", "$3_$10_$NUM_?$", 0, 9); substnum("?tetraconta$", "$4_$10_$NUM_?$", 0, 9); substnum("?pentaconta$", "$5_$10_$NUM_?$", 0, 9); substnum("?hexaconta$", "$6_$10_$NUM_?$", 0, 9); substnum("?heptaconta$", "$7_$10_$NUM_?$", 0, 9); substnum("?octaconta$", "$8_$10_$NUM_?$", 0, 9); substnum("?nonaconta$", "$9_$10_$NUM_?$", 0, 9); } if (strmatch(self,"cos")) { g("heneicosa$", "$2_$10_$1_$"); g("heneicos$", "$2_$10_$1_$"); g("henicosa$", "$2_$10_$1_$"); g("henicos$", "$2_$10_$1_$"); substnum("?cosa$", "$2_$10_$NUM_?$", 2, 9); substnum("?cos$", "$2_$10_$NUM_?$", 2, 9); g("eicosa$", "$2_$10_$"); g("eicos$", "$2_$10_$"); g("icosa$", "$2_$10_$"); g("icos$", "$2_$10_$"); } g("undeca$", "$10_$1_$"); g("undec$", "$10_$1_$"); substnum("?deca$", "$10_$NUM_?$", 0, 9); substnum("?dec$", "$10_$NUM_?$", 0, 9); g("$NUM_hen$","$1_$"); g("$NUM_do$", "$2_$"); g("mono$", "$1_$"); g("di$", "$2_$"); g("tri$", "$3_$"); g("tetra$","$4_$"); g("tetr$", "$4_$"); g("penta$","$5_$"); g("pent$", "$5_$"); g("hexa$", "$6_$"); g("hex$", "$6_$"); g("hepta$","$7_$"); g("hept$", "$7_$"); g("octa$", "$8_$"); g("oct$", "$8_$"); g("nona$", "$9_$"); g("non$", "$9_$"); g("$NUM_",""); /* "$NUM_" を除去 */ g("$DUM_",""); /* "$DUM_" を除去 */ } #ifndef NC /******************************************************************** ** ** translele() ** ** 元素名の翻訳を行う ** ********************************************************************/ #endif /* NC */ #ifndef JS void translele () #else function translele () #endif { g("$", "~KK|_$"); if (strmatch(self,"um")){ g("lithium", "$_RI_TI_QU_MU_"); g("sodium", "$_NA_TO_RI_QU_MU_"); g("natrium", "$_NA_TO_RI_QU_MU_");/*XXX*/ g("potassium", "$_KA_RI_QU_MU_"); g("kalium", "$_KA_RI_QU_MU_"); /*XXX*/ g("rubidium", "$_RU_BI_ZI_QU_MU_"); g("cesium", "$_SE_SI_QU_MU_"); g("francium", "$_HU_RA_NN_SI_QU_MU_"); g("beryllium", "$_BE_RI_RI_QU_MU_"); g("magnesium", "$_MA_GU_NE_SI_QU_MU_"); g("calcium", "$_KA_RU_SI_QU_MU_"); g("strontium", "$_SU_TO_RO_NN_TI_QU_MU_"); g("barium", "$_BA_RI_QU_MU_"); g("radium", "$_RA_ZI_QU_MU_"); g("scandium", "$_SU_KA_NN_ZI_QU_MU_"); g("titanium", "$_TI_TA_NN_"); g("vanadium", "$_BA_NA_ZI_QU_MU_"); g("chromium", "$_KU_RO_MU_"); g("yttrium", "$_QI_TT_TO_RI_QU_MU_"); g("zirconium", "$_ZI_RU_KO_NI_QU_MU_"); g("niobium", "$_NI_QO_BU_"); g("molybdenum","$_MO_RI_BU_DE_NN_"); g("technetium","$_TE_KU_NE_TI_QU_MU_"); g("ruthenium", "$_RU_TE_NI_QU_MU_"); g("rhodium", "$_RO_ZI_QU_MU_"); g("palladium", "$_PA_RA_ZI_QU_MU_"); g("cadmium", "$_KA_DO_MI_QU_MU_"); g("lanthanum", "$_RA_NN_TA_NN_"); g("cerium", "$_SE_RI_QU_MU_"); g("praseodymium","$_PU_RA_SE_QO_ZI_MU_"); g("neodymium", "$_NE_QO_ZI_MU_"); g("promethium","$_PU_RO_ME_TI_QU_MU_"); g("samarium", "$_SA_MA_RI_QU_MU_"); g("europium", "$_YU_QU_RO_PI_QU_MU_"); g("gadolinium","$_GA_DO_RI_NI_QU_MU_"); g("ytterbium", "$_QI_TT_TE_RU_BI_QU_MU_"); g("terbium", "$_TE_RU_BI_QU_MU_"); g("dysprosium","$_ZI_SU_PU_RO_SI_QU_MU_"); g("holmium", "$_HO_RU_MI_QU_MU_"); g("erbium", "$_QE_RU_BI_QU_MU_"); g("thulium", "$_TU_RI_QU_MU_"); g("lutetium", "$_RU_TE_TI_QU_MU_"); g("protoactinium","$_PU_RO_TO_QA_KU_TI_NI_QU_MU_"); g("actinium", "$_QA_KU_TI_NI_QU_MU_"); g("thorium", "$_TO_RI_QU_MU_"); #ifndef LITE g("neptunium", "$_NE_PU_TU_NI_QU_MU_"); g("plutonium", "$_PU_RU_TO_NI_QU_MU_"); g("americium", "$_QA_ME_RI_SI_QU_MU_"); g("curium", "$_KI_XU_RI_QU_MU_"); g("berkelium", "$_BA_HH_KU_RI_QU_MU_"); g("californium","$_KA_RI_HO_RU_NI_QU_MU_"); g("einsteinium","$_QA_QI_NN_SU_TA_QI_NI_QU_MU_"); g("fermium", "$_HU_LE_RU_MI_QU_MU_"); g("mendelevium","$_ME_NN_DE_RE_BI_QU_MU_"); g("nobelium", "$_NO_HH_BE_RI_QU_MU_"); g("lawrencium", "$_RO_HH_RE_NN_SI_QU_MU_"); g("rutherfordium","$_RA_ZA_HO_HH_ZI_QU_MU_"); g("dubnium", "$_DO_BU_NI_QU_MU_"); g("seaborgium", "$_SI_HH_BO_HH_GI_QU_MU_"); g("bohrium", "$_BO_HH_RI_QU_MU_"); g("hassium", "$_HA_TT_SI_QU_MU_"); g("meitnerium", "$_MA_QI_TO_NE_RI_QU_MU_"); #endif /* LITE */ g("hafnium", "$_HA_HU_NI_QU_MU_"); g("tantalum", "$_TA_NN_TA_RU_"); g("rhenium", "$_RE_NI_QU_MU_"); g("osmium", "$_QO_SU_MI_QU_MU_"); g("iridium", "$_QI_RI_ZI_QU_MU_"); g("platinum", "$SIRO_$KIN_"); g("aluminum", "$_QA_RU_MI_NI_QU_MU_"); g("aluminium","$_QA_RU_MI_NI_QU_MU_"); g("gallium", "$_GA_RI_QU_MU_"); g("indium", "$_QI_NN_ZI_QU_MU_"); g("thallium", "$_TA_RI_QU_MU_"); g("germanium","$_GE_RU_MA_NI_QU_MU_"); g("polonium", "$_PO_RO_NI_QU_MU_"); g("helium", "$_HE_RI_QU_MU_"); g("selenium", "$_SE_RE_NN_"); g("tellurium","$_TE_RU_RU_"); g("uranium", "$_QU_RA_NN_"); g("muonium~", "$_MI_XU_QO_NI_QU_MU_~"); g("muonium", MUON("~AH|_")); g("protium", "$_PU_RO_TI_QU_MU_"); g("deuterium","$_ZI_XU_QU_TE_RI_QU_MU_"); g("tritium", "$_TO_RI_TI_QU_MU_"); } g("manganese","$_MA_NN_GA_NN_"); g("iron", "$TETU_"); g("copper", "$DOU_"); g("silver", "$GIN_"); g("gold", "$KIN_"); g("mercury", "$SUI_$GIN_"); /* 末尾が不安な元素名 */ if (strmatch(self,"on~") || strmatch(self,"on$")) { g("argon~", "$_QA_RU_GO_NN_~"); g("krypton~", "$_KU_RI_PU_TO_NN_~"); g("xenon~", "$_KI_SE_NO_NN_~"); g("neon~", "$_NE_QO_NN_~"); g("radon~", "$_RA_DO_NN_~"); g("carbon~", "$TAN_$SO_~"); g("silicon~", "$_KE_QI_$SO_~"); g("boron~", "$_HO_QU_$SO_~"); } g("sulfur~", "$RYU_$OU_~"); g("tungsten~", "$_TA_NN_GU_SU_TE_NN_~"); g("wolfram~", "$_TA_NN_GU_SU_TE_NN_~"); g("cobalt~", "$_KO_BA_RU_TO_~"); g("nickel~", "$_NI_TT_KE_RU_~"); g("zinc~", "$A_$NAM_~"); g("bismuth~", "$_BI_SU_MA_SU_~"); if (strmatch(self,"gen")) { g("oxygen~", "$SAN_$SO_~"); g("halogen~", "$_HA_RO_GE_NN_~"); g("chalcogen~","$_KA_RU_KO_GE_NN_~"); g("pnicogen~", "$_PU_NI_KO_GE_NN_~"); g("hydrogen~", "$SUI_$SO_~"); g("nitrogen~", "$TITU_$SO_~"); g("hydrogenob", "hydro~HN|_genob"); g("hydrogenas", "hydro~HN|_genas"); g("hydrogenosome~", "hydro~HN|_genosome~"); g("hydrogen", HYDR("~AH|_")); } if (strmatch(self,"arsenic")) { g("arsenic~SP|_acid", "$_HI_ic~SP|_acid"); g("arsenic~SP|_amide", "$_HI_ic~SP|_amide"); g("arsenic~SP|_diamide", "$_HI_ic~SP|_diamide"); g("arsenic~SP|_triamide", "$_HI_ic~SP|_triamide"); g("arsenic", "$_HI_$SO_"); } g("phosphorus", "$_RI_NN_"); g("lead", "$NAM_"); g("antimony", "$_QA_NN_TI_MO_NN_"); if (strmatch(self,"ine")) { g("fluorine", "$_HU_TT_$SO_"); g("chlorine", "$EN_$SO_"); g("bromine", "$SYU_$SO_"); g("iodine", "$_YO_QU_$SO_"); g("astatine", "$_QA_SU_TA_TI_NN_"); } /* 元素名の前の a は aqua か数詞くらい */ if (strmatch(self,"tin")) { substnum("?tin", "?~SN|_tin", 4, 10); g("aquatin", "aqua~SN|_tin"); g("cosatin", "cosa~SN|_tin"); g("contatin", "conta~SN|_tin"); g("amminetin", "ammine~SN|_tin"); g("ylenetin", "ylene~SN|_tin"); g("idenetin", "idene~SN|_tin"); g("ynetin", "yne~SN|_tin"); g("oxytin", "oxy~SN|_tin"); g("ditin", "di~SN|_tin"); g("tritin", "tri~SN|_tin"); glookbehind("ol", "tin", "~SN|_tin"); g("_tin~", "_$_SU_ZU_~"); g("~SN|_", ""); } g("~KK|_",""); if (chrmatch(self,'$')) { translnum(); } } #ifndef LITE #ifndef NC /******************************************************************** ** ** invert() ** ** 二元型命名法の倒置を行う ** ** 文字列の一時変数として、headをつかう ** （spaninvert() と抵触しないよう） ** ********************************************************************/ /* 変数 cnt_tok トークン（成分）の個数 electro[i] i 番目のトークンの電荷。1:正, -1:負, 0:中性、2:正（倒置不可）. 倒置可能な陰性成分の語尾は、 a!e -> %I_ (-ate) i!e -> %O_ (-ite) i#e -> %D_ (-ide) と変換する。倒置できない -ide （〜化物）は、%B_ とする。 */ #endif /* NC */ #ifndef JS char * invert(char *str, int cnt_tok) { char *p, *pp, **tok, **endptr, replace[4]; char tmphydro[32]; /* 二水素など移動用バッファ */ signed char localinv, salt, nolower, *electro, *ending; signed int i, iv, afterpos, cnt_i, firstneg, lenthis, lenhydro, afterneg; tok = calloc(cnt_tok, sizeof(char *)); endptr = calloc(cnt_tok, sizeof(char *)); electro = calloc(cnt_tok, sizeof(signed char)); ending = calloc(cnt_tok, sizeof(signed char)); /* メモリが取れなければ何もしない */ if (!tok || !endptr || !electro || !ending) return str; #else function invert(str, cnt_tok) { electro = new Array(cnt_tok); endptr = new Array(cnt_tok); ending = new Array(cnt_tok); var localinv, i, iv, ival, salt, pct, afterpos, firstneg, afterneg, replace, lenhydro, hp; #endif /* スペースによる分割 */ #ifndef JS p = str; for (i = 0; i < cnt_tok; i++) { while (*p == ' ') ++p; if (*p) { tok[i] = p++; while (*p && *p != ' ') ++p; *p++ = '\0'; } else tok[i] = NULL; } #else tok = str.split(" "); #endif localinv = salt = 1; /* 初期値：倒置でき、塩類である */ firstneg = -1; afterneg = cnt_tok; #ifndef JS for (i = 0; i < cnt_tok; i++) { if (!tok[i]) break; p = endptr[i] = tok[i] + strlen(tok[i]); electro[i] = ending[i] = 0; /* initial value */ /* 記号の部分は巻戻す */ while (tok[i] + lenpct < p) { if (memEQ(p-lenpct,"~",1) || memEQ(p-2,"|_",2)) { p -= lenpct; } else { break; } } /* 陰性成分風の語尾を探す */ if (memEQ(p-3,"a!e",3) || memEQ(p-3,"%I_",3)) { endptr[i] = p-3; ending[i] = 1; electro[i] = -1; } else if (memEQ(p-3,"i!e",3) || memEQ(p-3,"%O_",3)) { endptr[i] = p-3; ending[i] = 2; electro[i] = -1; } else if (memEQ(p-3,"i#e",3) || memEQ(p-3,"%D_",3)) { endptr[i] = p-3; ending[i] = 3; electro[i] = -1; } if (electro[i] < 0 && firstneg < 0) { firstneg = i; } if (electro[i] == 0 && afterneg == cnt_tok && firstneg >= 0) { afterneg = i; } } #else for (i = 0; i < cnt_tok; i++) { endptr[i] = p = tok[i].length; electro[i] = ending[i] = 0; /* 記号の部分は巻戻す */ while (lenpct < p) { pct = tok[i].substring(p-lenpct, p); if (pct.indexOf("~") == 0 && pct.indexOf("|_") == 3) { p -= lenpct; } else { break; } } /* 陰性成分風の語尾を探す */ if (tok[i].substring(p-3,p) == "a!e" || tok[i].substring(p-3,p) == "%I_") { endptr[i] = p-3; ending[i] = 1; electro[i] = -1; } else if (tok[i].substring(p-3,p) == "i!e" || tok[i].substring(p-3,p) == "%O_") { endptr[i] = p-3; ending[i] = 2; electro[i] = -1; } else if (tok[i].substring(p-3,p) == "i#e" || tok[i].substring(p-3,p) == "%D_") { endptr[i] = p-3; ending[i] = 3; electro[i] = -1; } if (electro[i] < 0 && firstneg < 0) { firstneg = i; } if (electro[i] == 0 && afterneg == cnt_tok && firstneg >= 0) { afterneg = i; } } #endif /* 陰性成分以前のトークンが陽性成分に相応しいか */ afterpos = firstneg; #ifndef JS for (i = 0; i < firstneg; i++) { if (!tok[i]) break; p = tok[i] + strlen(tok[i]); /* '\0'の位置 */ /* 記号の部分は巻もどす */ while (tok[i] + lenpct < p) { if (memEQ(p-lenpct,"~",1) || memEQ(p-2,"|_",2)) { p -= lenpct; } else { break; } } /* 翻訳語を含む : これだけではelectro[i]の値は未決定 */ if (chrmatch(tok[i],'$')) { electro[i] = 2; } else if (memEQ(p-3,"ium",3)) { electro[i] = chrmatch(tok[i],'~') ? 2 : 1; salt = 1; } else { salt = 0; } /* トークンが完全に翻訳されている */ pp = tok[i]; /* この関数内では pp はここだけ */ nolower = 1; while (*pp) { if (islower(*pp)) { nolower = 0; } pp++; } if (nolower) { electro[i] = 1; } /* 語尾を探す */ else if (memEQ(p-2,"ic",2)) { if (memEQ(p-8,"cyanur",6)) { electro[i] = 2; salt = 1; } else { electro[i] = 0; salt = 0; } } else if (memEQ(p-3,"ous",3)) { electro[i] = 0; salt = 0; } else if (memEQ(p-2,"yl",2) || memEQ(p-7,"ylidene",7) || memEQ(p-7,"ylidyne",7) || memEQ(p-5,"ylene",5) || memEQ(p-8,"glycerol",8) || memEQ(p-9,"cellulose",9)) { electro[i] = 1; salt = 0; } else if (memEQ(p-3,"ine",3) && memNE(p-9,"phosphine",9) && memNE(p-6,"arsine",6) && memNE(p-7,"stibine",7) && memNE(p-10,"bismuthine",10)) { electro[i] = 2; salt = 1; } if (electro[i] == 0) { afterpos = i; break; } else if (electro[i] != 1) { localinv = 0; } /* 倒置できない */ } /* end while */ #else for (i = 0; i < firstneg; i++) { p = tok[i].length; /* 末尾の位置 */ /* 記号の部分は巻戻す */ while (lenpct < p) { pct = tok[i].substring(p-lenpct, p); if (pct.indexOf("~") == 0 && pct.indexOf("|_") == 3) { p -= lenpct; } else { break; } } /* 翻訳語を含む */ /* これだけではelectro[i]の値は未決定 */ if (tok[i].indexOf('$') != -1) { electro[i] = 2; } else if (tok[i].substring(p-3,p) == "ium") { electro[i] = (tok[i].indexOf('~') != -1) ? 2 : 1; salt = 1; } else{ salt = 0; } /* トークンが完全に翻訳されている */ if (tok[i].toUpperCase() == tok[i]) { electro[i] = 1; } /* 語尾を探す */ else if (tok[i].substring(p-2,p) == "ic") { if (tok[i].substring(p-8,p-2) == "cyanur") { electro[i] = 2; salt = 1; } else { electro[i] = 0; salt = 0; } } else if (tok[i].substring(p-3,p) == "ous") { electro[i] = 0; salt = 0; } else if (tok[i].substring(p-2,p) == "yl" || tok[i].substring(p-7,p) == "ylidene" || tok[i].substring(p-7,p) == "ylidyne" || tok[i].substring(p-5,p) == "ylene" || tok[i].substring(p-8,p) == "glycerol" || tok[i].substring(p-9,p) == "cellulose") { electro[i] = 1; salt = 0; } else if (tok[i].substring(p-3,p) == "ine" && tok[i].substring(p-9,p) != "phosphine" && tok[i].substring(p-6,p) != "arsine" && tok[i].substring(p-7,p) != "stibine" && tok[i].substring(p-10,p) != "bismuthine") { electro[i] = 2; salt = 1; } if (electro[i] == 0) { afterpos = i; break; } else if (electro[i] != 1) { localinv = 0; } /* 倒置できない */ } /* end while */ #endif /* 陽性成分も陰性成分も存在しないとき */ if (firstneg <= 0 || afterneg <= 0) { localinv = 0; salt = 0; } /* 陰性成分の前のすべてが適切な陽性成分でないとき */ if (afterpos != firstneg) { localinv = 0; salt = 0; } /* 陽性成分がなく、陰性成分が最初のとき */ if (electro[0] == -1) { localinv = 0; salt = -1; } /* 水素塩の「水素」の移動 */ if (localinv || salt) { for (i = firstneg; i < afterneg; i++) { #ifndef JS char *hp, *tp; if (!tok[i]) break; p = tok[i]; /* 先頭の位置 */ /* 記号の部分を進める */ while (p < tok[i] + strlen(tok[i]) - lenpct) { if (memEQ(p,"~",1) || memEQ(p+3,"|_",2)) { p += lenpct; } else { break; } } hp = strstr(tok[i], "~AH|_"); tp = strchr(p, '~'); /* 「水素酸」の水素ではなく、 p と hp の間に記号がない */ if (hp && hp == tp && memNE(hp + lenpct, "a!e", 3) && memNE(hp + lenpct, "%I_", 3)) { lenhydro = lenpct; /* strlen(~AH|_); */ lenthis = 0; /* 移動部の長さ */ while (p < hp + lenhydro) { lenthis++; p++; } /* 先行記号、酸、水素、後続記号の順 */ memcpy(tmphydro, p-lenthis, lenthis); tmphydro[lenthis] = '\0'; while (p < endptr[i] + 3) { *(p-lenthis) = *p; p++; } /* phosphate(V)の(V)も移動 */ for (iv = 0; iv < sizeVa; iv++) { if (memEQ(p,va[iv],strlen(va[iv]))) { while (p < endptr[i] + 3 + strlen(va[iv])) { *(p-lenthis) = *p; p++; } break; } } memcpy(p-lenthis, tmphydro, lenthis); endptr[i] -= lenthis; } #else var hp, tp; p = 0; /* 先頭の位置 */ /* 記号の部分を進める */ while (tok[i].length - lenpct > p) { pct = tok[i].substring(p,p+lenpct); if (pct.indexOf("~") == 0 && pct.indexOf("|_") == 3) { p += lenpct; } else { break; } } hp = tok[i].indexOf("~AH|_"); tp = tok[i].substring(p,hp).indexOf('~'); if (tp == NULL && hp != tok[i].indexOf("~AH|_a!e") && hp != tok[i].indexOf("~AH|_%I_")) { lenhydro = lenpct; /* "~AH|_".length; */ /* 先行記号、酸、水素、後続記号の順 */ ival = -1; for (iv = 0; iv < sizeVa; iv++) { if (tok[i].substring(endptr[i]+3, endptr[i]+3+va[iv].length) == va[iv]) { ival = iv; break; } } tok[i] = tok[i].substring(0,p) + tok[i].substring(hp+lenhydro, endptr[i]+3+(ival >= 0 ? va[ival].length : 0)) + tok[i].substring(p,hp+lenhydro) + tok[i].substring( endptr[i]+3+(ival >= 0 ? va[ival].length : 0), tok[i].length); endptr[i] -= hp + lenhydro - p; } #endif } } /* 並べなおし */ if (localinv) { /* 倒置する二元化合物 */ strcpy(head,""); /* 初期化 */ cnt_i = 0; for (i = firstneg; i < afterneg; i++, cnt_i++) { #ifndef JS if (!tok[i]) break; #endif if (ending[i] == 1) { strcpy(replace,"%I_"); } else if (ending[i] == 2) { strcpy(replace,"%O_"); } else if (ending[i] == 3) { strcpy(replace,"%D_"); /* 〜化 */ } #ifndef JS memcpy(endptr[i],replace,3); #else tok[i] = tok[i].substring(0,endptr[i]) + replace + tok[i].substring(endptr[i]+3,tok[i].length); #endif if (cnt_i && chrStrAt(tok[i], 0) == '~') /*記号の前に空白*/ strcat(head, " "); strcat(head, tok[i]); strcat(head, "~QT|_"); /* 逆流止め */ } for (i = firstneg-1; i >= 0; i--, cnt_i++) { #ifndef JS if (!tok[i]) break; #endif if (cnt_i && chrStrAt(tok[i], 0) == '~') strcat(head, " "); strcat(head, tok[i]); /* 陽性成分は逆順 */ strcat(head, "~QT|_"); } for (i = afterneg; i < cnt_tok; i++, cnt_i++) { #ifndef JS if (!tok[i]) break; #endif if (cnt_i && chrStrAt(tok[i], 0) == '~') strcat(head, " "); strcat(head, tok[i]); strcat(head, "~QT|_"); } } else if (salt) { /* 倒置しない塩類 */ strcpy(head,""); /* 初期化 */ cnt_i = 0; for (i = firstneg-1; i >= 0; i--, cnt_i++) { #ifndef JS if (!tok[i]) break; #endif if (cnt_i) strcat(head, " "); strcat(head, tok[i]); /* 陽性成分は正順 */ strcat(head, "~QT|_"); } for (i = firstneg; i < afterneg; i++, cnt_i++) { #ifndef JS if (!tok[i]) break; #endif if (ending[i] == 1) { strcpy(replace,"%I_"); } else if (ending[i] == 2) { strcpy(replace,"%O_"); } else if (ending[i] == 3) { strcpy(replace,"%B_"); /* 〜化物 */ } #ifndef JS memcpy(endptr[i],replace,3); #else tok[i] = tok[i].substring(0,endptr[i]) + replace + tok[i].substring(endptr[i]+3,tok[i].length); #endif if (cnt_i) strcat(head, " "); strcat(head, tok[i]); strcat(head, "~QT|_"); /* 逆流止め */ if (ending[i] == 1 || ending[i] == 2) { /*「塩」は最後 */ if (salt > 0) { strcat(head,"$EN_"); } } } for (i = afterneg; i < cnt_tok; i++, cnt_i++) { #ifndef JS if (!tok[i]) break; #endif strcat(head, "~QT|_"); if (cnt_i) strcat(head, " "); strcat(head, tok[i]); } } else { for (i = 0; i < cnt_tok; i++) { #ifndef JS if (!tok[i]) break; #endif if (i == 0) { strcpy(head,tok[i]); /* 初期化 */ } else { strcat(head, " "); strcat(head, tok[i]); } } } #ifndef JS /* メモリの解放 */ free(tok); free(endptr); free(electro); free(ending); #endif return(head); } #endif /* LITE */ #ifndef LITE #ifndef NC /******************************************************************** ** ** spaninvert() ** ** 二元型命名法の倒置を行う範囲を定める ** ** 文字列の一時変数として、destとtailをつかう ** （invert() と抵触しないよう） ** ** str0とstr1は自動変数なので、長さ管理を期待している。 ** とりあえず長さは 32 とした。長すぎるものを渡してはいけない。 ** ********************************************************************/ /* 変数 paren カッコのネストレベル lev 規定レベル cnt トークンの数（スペースの個数＋1 に等しい） */ #endif /* NC */ #ifndef JS void spaninvert(void) { char *s, *d, *t; char str0[32], str1[32]; int i, lev, paren, cnt, havenest; #else function spaninvert() { var lev, paren, cnt, i, ch, to_tail; var str0, str1; var havenest, to_be_replaced; #endif /* -ate の 't' を '!' で伏せる。例外は -ate に戻す */ if (strmatch(self,"ate~")) { g("ate~", "@~"); /* -olate for -olic acid */ if (strmatch(self,"ol@")) { g("fol@", "fola!e"); g("chol@", "chola!e"); g("catechola!e", "catecholate"); /*またまた戻す*/ g("dolichola!e", "dolicholate"); g("glycol@", "glycola!e"); g("pipecol@", "pipecola!e"); g("propiol@", "propiola!e"); g("tetrol@", "tetrola!e"); #ifndef LITE g("behenol@", "behenola!e"); g("labdanol@", "labdanola!e"); g("mycol@", "mycola!e"); g("nitrol@", "nitrola!e"); g("nitrosol@", "nitrosola!e"); g("niccol@", "niccola!e"); g("helvol@", "helvola!e"); g("oleanol@", "oleanola!e"); g("reserpinol@", "reserpinola!e"); g("ursol@", "ursola!e"); #endif /* LITE */ } for (i=0; i < sizeNoAt; i++) { strcpy(str0, noat[i]); strcat(str0, "@"); strcpy(str1, noat[i]); strcat(str1, "ate"); g(str0,str1); } g("@", "a!e"); } /* -ide, -ite は決められたものだけ '#', '!' で伏せる */ if (strmatch(self,"ite~")) { g("_ite~", "_i!e~"); for (i=0; i < sizeIt; i++) { strcpy(str0, it[i]); strcat(str0, "ite~"); strcpy(str1, it[i]); strcat(str1, "i!e~"); g(str0,str1); } } if (strmatch(self,"ide~")) { /* ("_ide~") は変えない */ for (i=0; i < sizeId; i++) { strcpy(str0, id[i]); strcat(str0, "ide~"); strcpy(str1, id[i]); strcat(str1, "i#e~"); g(str0,str1); } glookbehind("bcdfghijklmnpqrstuvwxz", "oxi#e", "oxide"); /*aeoy*/ glookbehind("bcdfghijklmnpqrstuvwxz", "azi#e", "azide"); /*aeoy*/ glookbehind("bcdfghijklmnpqrstuvwxz", "hali#e", "halide"); /*aeoy*/ if (strmatch(self,"oxide~")) { g("hydroxide~", "hydroxi#e~"); g("suboxide~", "suboxi#e~"); g("peroxide~", "peroxi#e~"); g("dioxide~", "dioxi#e~"); g("sesquioxide~", "sesquioxi#e~"); g("trioxide~", "trioxi#e~"); g("tetroxide~", "tetroxi#e~"); g("pentoxide~", "pentoxi#e~"); g("heptoxide~", "heptoxi#e~"); } g("diazide~", "diazi#e~"); g("triazide~", "triazi#e~"); g("dihalide~", "dihali#e~"); g("trihalide~", "trihali#e~"); g("hydriodi#e", "hydriodide"); g("anhydri#e", "anhydride"); g("glyceri#e", "glyceride"); g("molozoni#e", "molozonide"); g("hydro", "hydro/I_"); g("/I_per", "per/I_"); g("/I_poly", "poly/I_"); g("/I_di", "di/I_"); substnum("/I_?", "?/I_", 2, 11); g("/I_deca", "deca/I_"); g("benzotri","benzotri/I_"); g("/I_oxi#e", "/I_oxide"); g("/I_sulfi#e", "/I_sulfide"); g("/I_seleni#e", "/I_selenide"); g("/I_telluri#e", "/I_telluride"); g("/I_fluori#e", "/I_fluoride"); g("/I_chlori#e", "/I_chloride"); g("/I_bromi#e", "/I_bromide"); g("/I_iodi#e", "/I_iodide"); g("/I_hali#e", "/I_halide"); g("/I_halogeni#e", "/I_halogenide"); g("/I_", ""); } for (lev = 0; lev <= invlev; lev++) { /* カッコを文字に変換 */ if (lev == 0) { g("~BG|_","<"); } if (lev == 0) { g("~FN|_",">"); } g("~OP|_","("); g("~CL|_",")"); g("~LS|_","["); g("~RS|_","]"); g("~LB|_","{"); g("~RB|_","}"); g("~SP|_"," "); paren = 0; havenest=0; #ifndef JS for (s = self; *s; ++s) { /* 開きカッコはネストレベルを上げる */ if (*s == '(' || *s == '[' || *s == '{') { paren++; if (paren != lev) { if (*s == '<') *s = '\''; else if (*s == '(') *s = '.'; else if (*s == '[') *s = ':'; else if (*s == '{') *s = '-'; } } /* ネストレベルが対象外の空白は置換 */ if (*s == ' ' && paren != lev) { *s = '*'; havenest = 1; } /* 閉じカッコはネストレベルを下げる */ if (*s == ')' || *s == ']' || *s == '}') { if (paren != lev) { if (*s == '>') *s = '\"'; else if (*s == ')') *s = ','; else if (*s == ']') *s = ';'; else if (*s == '}') *s = '='; } paren--; } } /* end while */ #else for (i = 0; i < self.length; i++) { ch = self.substring(i,i+1); to_be_replaced = 0; /* 開きカッコはネストレベルを上げる */ if (ch == '(' || ch == '[' || ch == '{') { paren++; if ( paren != lev) { if (ch == '<') { ch = '\''; to_be_replaced = 1; } else if (ch == '(') { ch = '.'; to_be_replaced = 1; } else if (ch == '[') { ch = ':'; to_be_replaced = 1; } else if (ch == '{') { ch = '-'; to_be_replaced = 1; } } } /* ネストレベルが対象外の空白は置換 */ if (ch == ' ' && paren != lev) { ch = '*'; to_be_replaced = 1; havenest = 1; } /* 閉じカッコはネストレベルを下げる */ if (ch == ')' || ch == ']' || ch == '}') { if ( paren != lev) { if (ch == '>') { ch = '\"'; to_be_replaced = 1; } else if (ch == ')') { ch = ','; to_be_replaced = 1; } else if (ch == ']') { ch = ';'; to_be_replaced = 1; } else if (ch == '}') { ch = '='; to_be_replaced = 1; } } paren--; } if (to_be_replaced == 1) { /* 置換 */ self = self.substring(0,i) + ch + self.substring(i+1,self.length); } } /* end while */ #endif /* 対象外の記号を元に戻す */ g("\'","~BG|_"); g("\"","~FN|_"); g(".","~OP|_"); g(",","~CL|_"); g(":","~LS|_"); g(";","~RS|_"); g("-","~LB|_"); g("=","~RB|_"); g("*","~SP|_"); #ifndef JS s = self; d = dest; while (*s) { /* 開きカッコから閉じカッコまで */ if (*s == '(' || *s == '[' || *s == '{' || *s == '<') { int trailsp = 0; *d++ = *s++; while (*s == ' ') /* 先頭の空白はinvertに渡さない */ *d++ = *s++; *d = '\0'; cnt = 0; /* スペースの個数の初期化 */ /* 閉じカッコの前までtailにコピー */ t = tail; while (*s && *s != ')' && *s != ']' && *s != '}' && *s != '>') { if (*s == ' ') { cnt++; } /* スペースの個数 */ *t++ = *s++; } /* 末尾の空白は別途コピーする */ while (tail < t && t[-1] == ' ') { --t; --cnt; ++trailsp; } *t = '\0'; if (tail == t) { 1; } /* 空白しかなければinvert()しない */ else if ((size_t)cnt == strlen(tail)) { strcat(dest,tail); } /* 空白があればinvert() */ else if (cnt) { strcat(dest,invert(tail, cnt+1)); } /* ネストがなければ */ else if (! havenest) { strcat(dest,invert(tail,1)); } else { strcat(dest,tail); } /* ポインタを'\0'の上に移動 */ d = dest + strlen(dest); if (trailsp) { while (trailsp--) *d++ = ' '; *d = '\0'; } /* 閉じカッコはwhileに戻ってからコピーされよう */ } else { *d++ = *s++; } } /* end while */ *d = '\0'; #else /* selfをスキャンする */ dest = tail = ""; /* 初期化 */ cnt = to_tail = 0; for (i=0; i') { /* 空白があればinvert() */ if (cnt) { dest += invert(tail, cnt+1); /* スペース + 1 */ } /* ネストがなければ */ else if (havenest == 0) { dest += invert(tail, 1); } else { dest += tail; } dest += ch; /* 閉じカッコをコピー */ cnt = to_tail = 0; /* 再初期化 */ tail = ""; } else if (to_tail == 1) { tail += ch; if (ch == ' ') cnt++; /* スペースの個数 */ } else { dest += ch; } } /* end while */ #endif self2dest(); g("<","~BG|_"); g(">","~FN|_"); g("(","~OP|_"); g(")","~CL|_"); g("[","~LS|_"); g("]","~RS|_"); g("{","~LB|_"); g("}","~RB|_"); g(" ","~SP|_"); } /* end for (lev) */ /* 元素陰イオンの解釈 */ if (chrmatch(self,'%')) { g("%B_~", "%D_$BUTU_~"); g("%B_", "%D_"); /* hydrogen..ide */ g("%I_", "%I_~NL|_"); /* ethyl acetate -> acetic~NL|_ethyl */ g("%O_", "%O_~NL|_"); /* moveacid() まで ~NL|_ が必要 */ /* bi- for translele() */ g("biselen%I_", "$OMO_selen%I_"); g("bichrom%I_", "$OMO_chrom%I_"); g("sulf%I_", "sulfuric"); g("sulf%O_", "sulfurous"); g("selen%O_", "selenious"); g("phosph%I_", "phosphoric"); g("phosph%O_", "phosphorous"); g("arsen%I_", "$_HI_ic"); g("halogen%O_", "$A_HA_RO_GE_NN_ic"); g("stann%O_", "$A_SU_ZU_ic"); g("plumb%O_", "$A_NA_MA_RI_ic"); g("alumin%I_", "$_QA_RU_MI_NN_ic"); g("vanad%I_", "vanadic"); g("molybden%D_","$_MO_RI_BU_DE_NN_%D_"); g("mangan%", "$_MA_NN_GA_NN_%"); g("ferr%", "$TETU_%"); g("cobalt%", "$_KO_BA_RU_TO_%"); g("nickel%", "$_NI_TT_KE_RU_%"); g("niccol%", "$_NI_TT_KE_RU_%"); g("cupr%", "$DOU_%"); g("zinc%", "$A_$NAM_%"); g("argent%", "$GIN_%"); g("stann%", "$_SU_ZU_%"); g("lanthan%", "$_RA_NN_TA_NN_%"); g("tantal%", "$_TA_NN_TA_RU_%"); g("tungst%", "$_TA_NN_GU_SU_TE_NN_%"); g("platin%", "$SIRO_$KIN_%"); g("oxylaur%", "oxylaurin%"); g("ylaur%", "yl$KIN_%"); g("laur%", "laurin%"); g("aur%", "$KIN_%"); g("mercur%", "$SUI_$GIN_%"); g("plumb%", "$NAM_%"); g("bismuth%", "$_BI_SU_MA_SU_%"); g("halogen%", "$_HA_RO_GE_NN_%"); g("chalcogen%", "$_KA_RU_KO_GE_NN_%"); g("pnict%", "$_PU_NI_KO_GE_NN_%"); g("neon%", "$_NE_QO_NN_%"); g("argon%", "$_QA_RU_GO_NN_%"); g("krypton%", "$_KU_RI_PU_TO_NN_%"); g("xenon%", "$_KI_SE_NO_NN_%"); g("radon%", "$_RA_DO_NN_%"); } if (strmatch(self,"%I_")) { /* gallate */ g("~GL|_gall%I_", "$MOT_ic"); /* barate */ g("ribar%I_", "ribaRU_%I_"); g("tribaRU_%I_", "tribar%I_"); /* cerate */ g("glycer%I_", "glycerin%I_"); g("lignocer%I_", "lignocerin%I_"); glookbehind("cn", "cer%I_", "ceRU_%I_"); g(HYDR("~AH|_%I_"), "$SUI_$SO_ic"); } /* 元素名にするためiumを付加 */ if (strmatch(self,"%D_") || strmatch(self,"%I_")) { g("%I_", "ium~NL|_%I_"); g("%D_", "ium~NL|_%D_"); g("iium~NL|_%I_", "ium~NL|_%I_"); /* calciate */ translele(); /* 無駄なiumを削除 */ g("ium~NL|_%I_", "%I_"); g("ium~NL|_%D_", "%D_"); } if (strmatch(self,"%I_")) { g("tartr%I_", "tartaric"); g("azel%I_", "azelaic"); g("%I_", "ic"); } /* 亜酸 */ g("o%O_", "ous"); /* thioite -> thious acid */ g("%O_", "ous"); /* 〜化物 */ if (strmatch(self,"%D_")) { g("|_borohydr%D_~", "|_hydr%D_~QT|_HO_QU_$SO_~"); /*XXX*/ g("borohydr%D_", "$_HO_QU_hydr%D_"); g("borofluor%D_", "$_HO_QU_fluor%D_"); g("silicofluor%D_", "$_KE_QI_fluor%D_"); g("bifluor%D_", "$OMO_fluor%D_"); g("polysulf%D_", "$OOI_sulf%D_"); g("subox%D_", "$A_ox%D_"); g("superox%D_", "$TYO_ox%D_"); /* "%D_" を「〜化」に訳す */ for (i=0; i < sizeIe; i++) { g(ie[i],ka[i]); } g("%D_", "$KA_"); } /* 不要なものを戻す */ g("a!e", "ate"); g("i!e", "ite"); g("i#e", "ide"); } #endif /* LITE */ #ifndef NC /******************************************************************** ** ** jk() ** ** 字訳を行う変換関数 ** ********************************************************************/ #endif /* NC */ #ifndef JS char * jk(char * engl) #else function set_inv (i) { inv = i; } function jk(engl) #endif { #ifndef JS int i; /* 繰り返し変数 */ size_t len; #else var i, len; #endif /* 例外処理のため空白文字を除去した文字列を作る */ len = strlen(engl); if (!len) { /* 空行 */ return ""; } /* 句読点や数字, HI-ASCIIのエスケープ */ { #ifndef JS unsigned char *fr = (unsigned char *)engl; unsigned char *to = (unsigned char *)self; char *e = engl + len; while (engl < e && e[-1] == ' ') --e; *e = '\0'; /* 行末の空白を無視 */ strcpy(self, "~BG|_"); to += lenpct; while (*fr && *fr == ' ') /* 行先頭の空白を無視 */ ++fr; for (; *fr; fr++) { if (isKANJI(*fr)) { *to++ = '~'; *to++ = '^'; *to++ = *fr++; *to++ = '|'; *to++ = '_'; *to++ = '~'; if (*fr < 0x80) { *to++ = '&'; *to++ = 0x80 | (unsigned char)*fr; } else { *to++ = '^'; *to++ = *fr; } *to++ = '|'; *to++ = '_'; } else if (isalpha(*fr)) { *to++ = *fr; } else if (isprint(*fr)) { /* other than alpha */ *to = '\0'; for (i=0; i < sizeSy; i++) { if (*fr == sy[i][0]) { strcat(self, es[i]); to += lenpct; break; } } if (*fr == ' ') { while (fr[1] == ' ') fr++; } } else { *to++ = '~'; *to++ = '^'; *to++ = *fr; *to++ = '|'; *to++ = '_'; } } *to = '\0'; strcat(self, "~FN|_"); #else strcpy(self, engl); g("~", ""); /* 使えない文字 */ g("|",""); g("_","~LW|_"); while (strmatch(self," ")) { g(" "," "); } self = "~BG|_" + self + "~FN|_"; while (strmatch(self,"~BG|_ ")) { g("~BG|_ ","~BG|_"); } while (strmatch(self," ~FN|_")) { g(" ~FN|_","~FN|_"); } for (i=0; i < sizeSy; i++) { if (sy[i] == '~' || sy[i] == '|' || sy[i] == '_') continue; g(sy[i], es[i]); } dest = ""; for (i=0; i< self.length;i++) { if (self.charCodeAt(i) > 128) { dest += "~^" + self.charAt(i) + "|_"; } else { dest += self.charAt(i); } } self = dest; #endif } if (strEQ(self,"~BG|_~FN|_")) { return ""; } /* OCT-8, NON-azoxy, -OSe- 用ラベル付け */ g("_OCT~","_OCT~UP|_~"); g("_NON~","_NON~UP|_~"); g("_OSe~","_OS~UP|_e~"), /* neo-inositol */ g("_neo~HY|_","_neo~LO|_~HY|_"); /* イタリックの判定と変換 */ /* これで訳すべき英字は小文字に揃う */ cvtitalic(); /* 硫黄 */ g("sulph","sulf"); g("protactin", "protoactin"); glookahead("caes", "aiy", "ces"); /*例外処理*/ if (strEQ(self,"~BG|_acetic~SP|_anhydride~FN|_")) { strcpy(self, "~BG|_/A_acetic~SP|_acid~FN|_"); } else if (strEQ(self,"~BG|_succinic~SP|_anhydride~FN|_")) { strcpy(self, "~BG|_/A_succinic~SP|_acid~FN|_"); } else if (strEQ(self,"~BG|_maleic~SP|_anhydride~FN|_")) { strcpy(self, "~BG|_/A_maleic~SP|_acid~FN|_"); } else if (strEQ(self,"~BG|_phthalic~SP|_anhydride~FN|_")) { strcpy(self, "~BG|_/A_phthalic~SP|_acid~FN|_"); } else if (strEQ(self,"~BG|_cyanogen~FN|_")) { strcpy(self, "~BG|_dicyan~FN|_"); } g("/A_", "$MU_$SUI_"); /* * but-2-eneなどはbuta-2-eneとして字訳。 */ g("en","e%n"); /* enkephalin etc. */ glookahead("e%n", "aeiouy~", "en"); g("ylide~","y%lide~"); g("~SP|_en", "~SP|_e%n"); g("~SP|_yn", "~SP|_y%n"); g("~SP|_yl", "~SP|_y%l"); g("~SP|_ulo", "~SP|_ul%o"); euphony("en", "a"); euphony("yn", "a"); euphony("yl", "a"); euphony("ulo", "o"); g("%",""); /* 戻す */ g("aspartica~","asparagin$SAN_~"); /* aspartic-n-yl */ g("glutamica~","glutamin$SAN_~"); /* glutamic-n-yl */ /* OCT-8, NON-azoxy, -OSe-, neo-inositol のイタリック化 */ g("_oct~UP|_~", "_~^O|_~^C|_~^T|_~"); g("_non~UP|_~", "_~^N|_~^O|_~^N|_~"); g("_OS~UP|_e~", "_~^O|_~^S|_~`E|_~"); g("_neo~LO|_~HY|_inosit", "_~`N|_~`E|_~`O|_~HY|_inosit"); g("~UP|_", ""); g("~LO|_", ""); /* * 生化学関連の翻訳 */ if (strmatch(self,"~SP|_~")) { g("coenzyme~SP|_~^", "coenzyme~SS|_~^"); g("penicillin~SP|_~^", "penicillin~SS|_~^"); g("prostaglandin~SP|_~^", "prostaglandin~SS|_~^"); g("thromboxane~SP|_~^", "thromboxane~SS|_~^"); g("vitamin~SP|_~^", "vitamin~SS|_~^"); g("chlorophyll~SP|_~`", "chlorophyll~SS|_~`"); g("chlorophyllide~SP|_~`", "chlorophyllide~SS|_~`"); g("pheophytin~SP|_~`", "pheophytin~SS|_~`"); g("pheofarnesin~SP|_~`", "pheofarnesin~SS|_~`"); g("pheophorbide~SP|_~`", "pheophorbide~SS|_~`"); } g("~FN|_", "~SP|_~FN|_"); g("~SP|_~^A|_~SP|_", "~SS|_~^A|_~SP|_"); g("~SP|_~^B|_~SP|_", "~SS|_~^B|_~SP|_"); g("~SP|_~^C|_~SP|_", "~SS|_~^C|_~SP|_"); g("~SP|_~^D|_~SP|_", "~SS|_~^D|_~SP|_"); g("~SP|_~^E|_~SP|_", "~SS|_~^E|_~SP|_"); g("~SP|_~^F|_~SP|_", "~SS|_~^F|_~SP|_"); g("~SP|_~^G|_~SP|_", "~SS|_~^G|_~SP|_"); g("~SP|_~^H|_~SP|_", "~SS|_~^H|_~SP|_"); g("~SP|_~^I|_~SP|_", "~SS|_~^I|_~SP|_"); g("~SP|_~^P|_~SP|_", "~SS|_~^P|_~SP|_"); g("~SP|_~^V|_~SP|_", "~SS|_~^V|_~SP|_"); g("~SP|_~^X|_~SP|_", "~SS|_~^X|_~SP|_"); g("~SP|_~FN|_", "~FN|_"); g("~SP|_~^I|_~^", "~SS|_~^I|_~^"); g("~SP|_~^V|_~^", "~SS|_~^V|_~^"); g("~SP|_~^X|_~^", "~SS|_~^X|_~^"); g("|_~SS|_", "|_~SP|_"); #ifndef LITE if (inv) { if (strmatch(self,"saccharide~")) { g("monosaccharide~","$MONO_$TOU_~"); g("polysaccharide~","$OOI_$TOU_~"); g("saccharide~", "$TOU_~"); } if (strmatch(self,"lipid~")) { g("glycolipid~", "$TOU_$SHI_$SITSU_~"); g("phospholipid~", "$_RI_NN_$SHI_$SITSU_~"); g("lipid~", "$SHI_$SITSU_~"); } if (strmatch(self,"protein~")) { g("chromoprotein~", "$IRO_$SO_TA_NN_PA_KU_$SITSU_~"); g("glycoprotein~", "$TOU_TA_NN_PA_KU_$SITSU_~"); g("metalloprotein~","$KIN_$ZOKU_TA_NN_PA_KU_$SITSU_~"); g("nucleoprotein~", "$KAKU_TA_NN_PA_KU_$SITSU_~"); g("phosphoprotein~","$_RI_NN_TA_NN_PA_KU_$SITSU_~"); g("protein~", "$_TA_NN_PA_KU_$SITSU_~"); } if (strmatch(self,"ase~")) { g("codehydrogenase~","~BS|_$HO_$DAT_$SUI_$SO_$KOU_$SO_~"); g("decarboxylase~", "~BS|_$DAT_$TAN_$SAN_$KOU_$SO_~"); g("dehydrogenase~", "~BS|_$DAT_$SUI_$SO_$KOU_$SO_~"); g("duplicase~", "~BS|_$DUPL_$KOU_$SO_~"); g("hydrolase~", "~BS|_$ADD_$SUI_$DEC_$KOU_$SO_~"); g("oxidoreductase~","~BS|_$SAN_$KA_$RED_$KOU_$SO_~"); g("reductase~", "~BS|_$RED_$KOU_$SO_~"); g("replicase~", "~BS|_$DUPL_$KOU_$SO_~"); g("transaminase~", "~BS|_QA_MI_NO_$KI_$TEN_$II_$KOU_$SO_~"); g("transcriptase~", "~BS|_$TEN_$SYA_$KOU_$SO_~"); g("transferase~", "~BS|_$TEN_$II_$KOU_$SO_~"); } if (strmatch(self,"zyme~")) { g("endoenzyme~", "$CYT_$NAI_$KOU_$SO_~"); g("exoenzyme~", "$CYT_$GAI_$KOU_$SO_~"); g("metalloenzyme~", "$KIN_$ZOKU_$KOU_$SO_~"); g("coenzyme~", "~BS|_$HO_$KOU_$SO_~"); g("isozyme~", "QI_SO_$KOU_$SO_~"); g("enzyme~", "$KOU_$SO_~"); } } else { g("transferase~", "~BB|_transferase~"); /* 残す */ } #endif /*LITE*/ /* * 元素名の翻訳 */ g("|_monoxide~", "|_monooxide~"); g("|_phosphonitrile~","|_HO_SU_HO_NI_TO_RI_RU_~"); g("|_cyanogen~", "|_SI_QA_NN_~"); g("pelargon", "pelar/L_gon"); g("hexenon", "hex/L_enon"); g("spiron", "spi/L_ron"); g("irone~", "iro/L_ne~"); g("sulfuryl", "sul/L_furyl"); if (strmatch(self,"uran")) { /* uranium */ g("selenuran", "selenu/L_ran"); g("telluran", "tellu/L_ran"); g("kauran", "kau/L_ran"); g("furan", "fu/L_ran"); /* and sulfuran */ g("curan", "cu/L_ran"); /* and mercuran */ } g("galanthan", "galan/L_than"); g("antimonyl", "anti/L_monyl"); g("theobromine", "theobro/L_mine"); /* a purine */ g("_hydrocarbon~", "_$TAN_$KA_$SUI_$SO_~"); g("ferrosilicon", "ferrosili/L_con"); if (strmatch(self,"tin~")) { g("biotin~", "biot/L_in~"); g("carotin~", "carot/L_in~"); g("cresotin~", "cresot/L_in~"); g("cefalotin~", "cefalot/L_in~"); g("indigotin~", "indigot/L_in~"); g("narcotin~", "narcot/L_in~"); g("nicotin~", "nicot/L_in~"); g("parotin~", "parot/L_in~"); g("voachalotin~","voachalot/L_in~"); } translele(); /* invert() の前に翻訳が必要 */ /* g("/L_", ""); まだ消さない */ #ifndef LITE /* 第一塩、第二塩 */ if (strmatch(self,"ic~") || strmatch(self,"ous~")) { g("ic~SP|_", "ic~DA|_~SP|_"); g("ous~SP|_", "ous~DA|_~SP|_"); g("ic~FN|_", "ic~DA|_~FN|_"); g("ous~FN|_", "ous~DA|_~FN|_"); g("~DA|_~SP|_~", "~SP|_~"); g("~DA|_~SP|_acid", "~SP|_acid"); g("antimonous~DA|_~", "$DAI_$1_QA_NN_TI_MO_NN_~"); g("antimonic~DA|_~", "$DAI_$2_QA_NN_TI_MO_NN_~"); g("argentous~", "$DAI_$1_$GIN_~"); g("argentic~", "$DAI_$2_$GIN_~"); g("_aurous~", "_$DAI_$1_$KIN_~"); g("_auric~DA|_~", "_$DAI_$2_$KIN_~"); g("chromous~", "$DAI_$1_KU_RO_MU_~"); g("chromic~DA|_~", "$DAI_$2_KU_RO_MU_~"); g("cobaltous~", "$DAI_$1_KO_BA_RU_TO_~"); g("cobaltic~", "$DAI_$2_KO_BA_RU_TO_~"); g("cuprous~", "$DAI_$1_$DOU_~"); g("cupric~", "$DAI_$2_$DOU_~"); g("ferrous~", "$DAI_$1_$TETU_~"); g("ferric~", "$DAI_$2_$TETU_~"); g("manganous~", "$DAI_$1_MA_NN_GA_NN_~"); g("manganic~DA|_~", "$DAI_$2_MA_NN_GA_NN_~"); g("mercurous~", "$DAI_$1_$SUI_$GIN_~"); g("mercuric~", "$DAI_$2_$SUI_$GIN_~"); g("nickelous~", "$DAI_$1_NI_TT_KE_RU_~"); g("nickelic~", "$DAI_$2_NI_TT_KE_RU_~"); g("palladous~", "$DAI_$1_PA_RA_ZI_QU_MU_~"); g("palladic~", "$DAI_$2_PA_RA_ZI_QU_MU_~"); g("platinous~", "$DAI_$1_$SIRO_$KIN_~"); g("platinic~DA|_~", "$DAI_$2_$SIRO_$KIN_~"); g("plumbous~DA|_~", "$DAI_$1_$NAM_~"); g("plumbic~DA|_~", "$DAI_$2_$NAM_~"); g("stannous~DA|_~", "$DAI_$1_SU_ZU_~"); g("stannic~DA|_~", "$DAI_$2_SU_ZU_~"); g("thallous~", "$DAI_$1_TA_RI_QU_MU_~"); g("thallic~", "$DAI_$2_TA_RI_QU_MU_~"); g("~DA|_", ""); } #endif /* LITE */ /* ~GL|_ for 没食子酸; gallate(III) etc. to gallium */ if (strmatch(self,"gallate~")) { g("|_gallate~", "|_~GL|_gallate~"); g("|_~GL|_gallate~OP|_","|_gallate~OP|_"); g("pyrogallate~", "pyro~GL|_gallate~"); g("subgallate~", "sub~GL|_gallate~"); } /* * 二元型化合物翻訳名の倒置 */ #ifndef LITE if (inv) { spaninvert(); } #endif /* LITE */ g("/L_", ""); /* translele() */ g("~GL|_",""); g(HYDR("~AH|_~"), "$SUI_$SO_~"); g(MUON("~AH|_~"), "$_MI_XU_QO_NI_QU_MU_~"); g(HYDRSTR, "hydrogen"); g(MUONSTR, "muonium"); g("~AH|_ate", "ate"); g("~AH|_", "~NL|_"); g("~HN|_", ""); g("ammonium~", "$_QA_NN_MO_NI_QU_MU_~"); /* 学術 diammonium */ /* * 酸の翻訳名 */ if (strmatch(self,"ic~")) { g("hydrohalic~", "$_HA_RO_GE_NN_$KA_$SUI_$SO_ic~"); g("hydrohalogenic~", "$_HA_RO_GE_NN_$KA_$SUI_$SO_ic~"); g("hydrochloric~", "$EN_ic~"); g("hydrobromic~", "$SYU_$KA_$SUI_$SO_ic~"); g("hydriodic~", "$_YO_QU_$KA_$SUI_$SO_ic~"); g("hydroiodic~", "$_YO_QU_$KA_$SUI_$SO_ic~"); g("hydrofluoric~", "$_HU_TT_$KA_$SUI_$SO_ic~"); g("hydroisocyanic~", "$_QI_SO_SI_QA_NN_$KA_$SUI_$SO_ic~"); g("hydrocyanic~", "$_SI_QA_NN_$KA_$SUI_$SO_ic~"); g("hydrazoic~", "$_QA_ZI_$KA_$SUI_$SO_ic~"); #ifndef LITE g("hydrosulfuric~", "$RYU_$KA_$SUI_$SO_ic~"); g("hydroselenic~", "$_SE_RE_NN_$KA_$SUI_$SO_ic~"); g("hydrotelluric~", "$_TE_RU_RU_$KA_$SUI_$SO_ic~"); g("mucobromic~", "mucoBU_romic~"); g("mucochloric~", "mucoKU_loric~"); glookbehind("aiueoylmnr_", "halic~", "$_HA_RO_GE_NN_ic~"); g("halogenic~", "$_HA_RO_GE_NN_ic~"); g("astatic~", "$_QA_SU_TA_TI_NN_ic~"); #endif /* LITE */ g("fluoric~", "$_HU_TT_$SO_ic~"); g("chloric~", "$EN_$SO_ic~"); g("bromic~", "$SYU_$SO_ic~"); g("iodic~", "$_YO_QU_$SO_ic~"); g("sulfuric~", "/B_$RYU_ic~"); g("selenic~", "/B_$_SE_RE_NN_ic~"); g("telluric~", "$_TE_RU_RU_ic~"); g("nitric~", "$SYO_ic~"); g("phosphoric~","$_RI_NN_ic~"); g("fulminic~", "$RAI_ic~"); g("carbonic~", "/B_$TAN_ic~"); g("borosilicic~","$_HO_QU_KE_QI_ic~"); g("silicic~", "$_KE_QI_ic~"); g("boric~", "$_HO_QU_ic~"); g("chromic~", "/B_$_KU_RO_MU_ic~"); g("manganic~", "$_MA_NN_GA_NN_ic~"); #ifndef LITE g("antimonic~", "$_QA_NN_TI_MO_NN_ic~"); g("stibic~", "$_QA_NN_TI_MO_NN_ic~"); g("stannic~", "$_SU_ZU_ic~"); g("plumbic~", "$NAM_ic~"); g("titanic~", "$_TI_TA_NN_ic~"); g("vanadic~", "$_BA_NA_ZI_NN_ic~"); g("niobic~", "$_NI_QO_BU_ic~"); g("molybdic~", "$_MO_RI_BU_DE_NN_ic~"); g("technetic~", "$_TE_KU_NE_TI_QU_MU_ic~"); g("tantalic~", "$_TA_NN_TA_RU_ic~"); g("tungstic~", "$_TA_NN_GU_SU_TE_NN_ic~"); g("wolframic~", "$_TA_NN_GU_SU_TE_NN_ic~"); g("rhenic~", "$_RE_NI_QU_MU_ic~"); g("osmic~", "$_QO_SU_MI_QU_MU_ic~"); g("platinic~", "$SIRO_$KIN_ic~"); g("hexen", "hex/L_en"); g("xenoic~", "$_KI_SE_NO_NN_ic~"); g("xenonic~", "$_KI_SE_NO_NN_ic~"); g("/L_", ""); #endif /* LITE */ g("basic~", "$EN_$KI_ic~"); } /* * 亜酸 */ if (strmatch(self,"ous~")) { g("fluorous~", "$A_HU_TT_$SO_ic~"); g("chlorous~", "$A_$EN_$SO_ic~"); g("bromous~", "$A_$SYU_$SO_ic~"); g("iodous~", "$A_YO_QU_$SO_ic~"); g("halous~", "$A_halogenic~"); g("halogenous~","$A_halogenic~"); g("sulfurous~", "/B_$A_$RYU_ic~"); g("selenious~", "/B_$A_selenic~"); g("|_tellurous~","|_$A_telluric~"); g("dithionous~","$A_dithionic~"); /* 亜二チオン酸ではない */ substnum("?decathionous~","$A_?decathionic~",2,9); substnum("?thionous~","$A_?thionic~",3,11); g("nitrous~", "$A_$SYO_ic~"); g("phosphorous~","$A_RI_NN_ic~"); g("arsenous~", "$A_HI_ic~"); g("arsenious~", "$A_HI_ic~"); g("antimonous~","$A_QA_NN_TI_MO_NN_ic~"); g("stannous~", "$A_SU_ZU_ic~"); g("plumbous~", "$A_NA_MA_RI_ic~"); #ifndef LITE ousacid(); /* 類型亜酸 */ #endif } /* * 有機酸翻訳名 */ if (strmatch(self,"ic~")) { #ifndef LITE g("kojic~", "$_koujiic~"); g("shikimic~", "$_sikimiic~"); g("chrysanthemic~","$KIKU_ic~"); g("chrysanthemumic~","$KIKU_ic~"); g("squaric~", "$4_$KADO_ic~"); g("quadratic~", "$4_$KADO_ic~"); g("thujic~", "thuyaic~"); g("atrolactic~","atrolactinic~"); /* lactic より前*/ g("citramalic~","citraMA_lic~"); /* malic より前*/ g("itamalic~", "itaMA_lic~"); /* malic より前*/ #endif /* LITE */ g("oxalacetic~","oxalo$SAKU_ic~"); g("acetic~", "$SAKU_ic~"); g("butyric~", "$RAKU_ic~"); g("valeric~", "$VL_ic~"); g("benzoic~", "$BZ_ic~"); g("gallic~", "$MOT_ic~"); g("carbolic~", "$SEKI_$TAN_ic~"); g("cinnamic~", "$_KE_QI_$HI_ic~"); g("camphoric~", "$_SI_XO_QU_NO_QU_ic~"); g("lactic~", "$NYU_ic~"); g("tartaric~", "/B_$SAKE_$SEKI_ic~"); g("formic~", "$_GI_ic~"); g("mesoxalic~", "meso$_SI_XU_QU_ic~"); g("binoxalic~", "$OMO_SI_XU_QU_ic~"); g("oxalic~", "$_SI_XU_QU_ic~"); g("succinic~", "/B_$_KO_HA_KU_ic~"); glookbehind("aeioyl_", "malic~","/B_$_RI_NN_GO_ic~"); g("citric~", "$_KU_QE_NN_ic~"); g("folic~", "$YOU_ic~"); g("nucleic~", "$KAKU_ic~"); g("mucic~", "$NENEK_ic~"); g("saccharic~", "$TOU_ic~"); g("clupanodonic~","$_QI_WA_SI_ic~"); g("_resinic~", "_$TREE_$SHI_ic~"); /* for resinate */ } g("biphthalic~", "$OMO_phthalic~"); g("bi/B_", "$OMO_"); g("/B_", ""); /* ハロゲン化水素塩 */ if (inv && strmatch(self,"ide~")) { g("hydrofluoride~", "$_HU_TT_$KA_$SUI_$SO_$SAN_$EN_~"); g("hydrochloride~", "$EN_$SAN_$EN_~"); g("hydrobromide~", "$SYU_$KA_$SUI_$SO_$SAN_$EN_~"); g("hydriodide~", "$_YO_QU_$KA_$SUI_$SO_$SAN_$EN_~"); g("hydroiodide~", "$_YO_QU_$KA_$SUI_$SO_$SAN_$EN_~"); g("hydrohalide~", "$_HA_RO_GE_NN_$KA_$SUI_$SO_$SAN_$EN_~"); g("hydrohalogenide~", "$_HA_RO_GE_NN_$KA_$SUI_$SO_$SAN_$EN_~"); } /* * その他の翻訳語 */ g("deuter","ZI_XU_QU_TE_r"); g("muon","MI_XU_on"); g("prometh","PU_RO_ME_th"); glookahead("europ", "ay", "YU_QU_rop"); /* e-uroporphyrin */ glookahead("europi", "do", "YU_QU_ropi"); g("yttri","QI_TT_TO_RI_"); g("berkel", "BA_HH_KU_l"); g("einstein", "QA_QI_NN_stain"); g("nobel", "NO_HH_BE_l"); g("lawrenc", "RO_HH_RE_NN_c"); g("rutherford","RA_ZA_HO_HH_d"); g("dubn", "DO_BU_n"); g("seaborg", "SI_HH_BO_HH_g"); g("meitner", "MA_QI_TO_NE_r"); g("tungst", "TA_NN_GU_st"); g("perruthen", "PE_RU_RU_TE_n"); g("perrhod", "PE_RU_RO_d"); g("perrhen", "PE_RU_RE_n"); g("perhal", "PE_RU_HA_l"); if (strmatch(self,"cur")) { g("curan", "KU_ran"); g("mercurochrom","MA_HH_KI_XU_RO_chrom"); g("mercur", "ME_RU_KU_r"); g("tubocurar", "tubokurar"); /* curium */ glookahead("cur", "ay", "KI_XU_r"); glookahead("curi", "do", "KI_XU_ri"); } g("conjugate", "$CONJ_"); g("$CONJ_~SP|_acid","$CONJ_$SAN_"); g("_inner~", "_$MOL_$NAI_~"); g("protonated", "proton$KA_"); g("anhydride", "$MU_$SUI_$BUTU_"); g("carbohydrate", "$TAN_$SUI_$KA_$BUTU_"); g("hydrate", "$SUI_$WA_$BUTU_"); g("ammoniate", "$_QA_NN_MO_NI_QA_$WA_$BUTU_"); g("atom~", "~BS|_$ATOM_~"); glookbehind(VOWEL, "acid~", "$SAN_~"); /* |_acid~ はまだ変換不可 */ g("_salt~", "_~BS|_$EN_~"); g("_group~", "_~BS|_$KI_~"); g("_base~", "_~BS|_$EN_$KI_~"); g("_residue~", "_~BS|_$ZAN_$KI_~"); g("_ring~", "_~BS|_$KAN_~"); g("_nucleus~", "_~BS|_$KAKU_~"); g("_compound~", "_~BS|_$KA_$GOU_$BUTU_~"); g("_species~", "_~BS|_$SHU_~"); g("_sugar~", "_~BS|_$TOU_~"); g("_glass~", "_~BS|_GA_RA_SU_~"); g("_alum~", "_~BS|_MI_XO_QU_BA_NN_~"); g("_amalgam~", "_~BS|_QA_MA_RU_GA_MU_~"); g("_metal~", "_~BS|_$KIN_$ZOKU_~"); g("_bile~", "_~BS|_$BILE_~"); g("_resin~", "_~BS|_$TREE_$SHI_~"); g("_cyclorubber~", "_~BS|_$KAN_$KA_GO_MU_~"); g("_rubber~", "_~BS|_GO_MU_~"); g("_water~", "_~BS|_$SUI_~"); g("_alcohol", "_~BS|_alcohol"); /* also alcoholate*/ g("_glycol~", "_~BS|_glycol~"); if (strmatch(self,"radical~")) { g("_radical~", "_~BS|_radical~"); g("_biradical~","_~BS|_biradical~"); g("_diradical~","_~BS|_diradical~"); substnum("_?radical~", "_~BS|_?radical~", 3,11); } if (strmatch(self,"ion~")) { g("_zwitterion~","_~BS|_$SOU_$SEI_ion~"); g("_cation~", "_~BS|_cation~"); g("_anion~", "_~BS|_anion~"); g("_dication~", "_~BS|_dication~"); g("_dianion~", "_~BS|_dianion~"); substnum("_?cation~", "_~BS|_?cation~", 3,11); substnum("_?anion~", "_~BS|_?anion~", 3,11); g("_ion~", "_~BS|_ion~"); } if (strmatch(self,"or~")) { if (inv) { g("_donor~", "_~BS|_$DON_$BODY_~"); g("_acceptor~", "_~BS|_$ACC_$BODY_~"); g("_receptor~", "_~BS|_$ACC_$BODY_~"); g("_factor~", "_~BS|_$FAC_~"); g("_cofactor~", "_~BS|_$HO_$FAC_~"); } else { g("_donor~", "_~BS|_donah~"); g("_acceptor~", "_~BS|_akceptah~"); g("_receptor~", "_~BS|_receptah~"); g("_factor~", "_~BS|_factah~"); g("_cofactor~", "_~BS|_cofactah~"); } } g("_deficient~", "_~BS|_$HUSOK_~"); g("_excess~", "_~BS|_$KAJO_~"); g("_active~SP|_~", "_$KAT_$SEI_~SP|_~"); g("~CM|_~SP|_~BS|_","~CM|_~SP|_"); /* comma + space */ g("~SP|_~BS|_", "~BB|_"); /* 空白の代わりに残す */ g("~BS|_", ""); if (strmatch(self,"al~")) { g("_achiral~", "_QA_KI_RA_RU_~PS|_~"); g("_chiral~", "_KI_RA_RU_~PS|_~"); g("_normal~", "_NO_RU_MA_RU_~PS|_~"); } if (strmatch(self,"ary~")) { g("_primary~", "_$DAI_$1_$KYU_~PS|_~"); g("_secondary~", "_$DAI_$2_$KYU_~PS|_~"); g("_tertiary~", "_$DAI_$3_$KYU_~PS|_~"); g("_quaternary~", "_$DAI_$4_$KYU_~PS|_~"); } if (strmatch(self,"cyclic")) { g("_cyclic~", "_$KAN_$JOU_~PS|_~"); g("acyclic", "$NON_$KAN_$SIKI_~PS|_"); g("alicyclic", "$SHI_$KAN_$SIKI_~PS|_"); g("monocyclic", "$MONO_$KAN_$SIKI_~PS|_"); g("bicyclic", "$2_$KAN_$SIKI_~PS|_"); g("polycyclic", "$OOI_$KAN_$SIKI_~PS|_"); g("cyclic~", "$KAN_$SIKI_~PS|_~"); } g("_racemic~", "_RA_SE_MI_~PS|_~"); g("antiaromatic", "$ANTI_$AR_$ZK_~PS|_"); g("aromatic", "$AR_$ZK_~PS|_"); g("aliphatic", "$SHI_$BOU_$ZK_~PS|_"); g("inorganic", "$MU_$KIY_~PS|_"); g("organic", "$YUU_$KIY_~PS|_"); g("organometallic", "$YUU_$KIY_$KIN_$ZOKU_~PS|_"); g("~PS|_~SP|_", "~BB|_"); /* 空白の代わりに残す */ g("~PS|_", ""); g("_fatty~SP|_", "_$SHI_$BOU_"); g("_fatty~HY|_", "_$SHI_$BOU_"); g("_fatty~", "_$SHI_$BOU_~"); g("_graphite~", "_$KURO_$NAM_~"); g("_diamond~", "_DA_QI_YA_MO_NN_DO_~"); g("_starch~", "_$_DE_NN_PU_NN_~"); g("_tar~", "_TA_HH_RU_~"); /* * urea関係 */ if (strmatch(self,"ur")) { g("urea~", "$NYO_$SO_~"); g("oxaluric~", "QO_xaluRU_ic~"); g("maleur", "MA_RE_QU_r"); g("lauric~", "laurinic~"); glookbehind("eioy_", "auric~","$KIN_ic~"); g("hippuric~", "$UMA_$NYO_ic~"); g("yluric~", "yl$NYO_ic~"); glookbehind("eioy_", "uric~","$NYO_ic~"); g("glycoluril","glycol~NL|_uril"); } /* * 倍数接頭辞などの翻訳 */ if (chrmatch(self,'$')) { translnum(); } /* * 翻訳は以上。以下は字訳。 */ /* * 置換官能基による母音脱落 */ g("monoxide","monooxide"); g("amid", "@Amid"); g("amin", "@Amin"); g("ol~", "@Ol~"); g("one~", "@One~"); g("oxid", "@Oxid"); if (chrmatch(self,'@')) { g("acetohex@Amid", "acetohexamyd"); glookbehind(LOWER, "non@Amid", "nonamid"); g("tetr@", "tetra@"); g("pent@", "penta@"); g("hex@", "hexa@"); g("hept@", "hepta@"); g("oct@", "octa@"); g("non@", "nona@"); g("dec@", "deca@"); g("icos@", "icosa@"); g("acos@", "acosa@"); g("docos@", "docosa@"); g("triacont@","triaconta@"); substnum("?cont@","?conta@",4,9); g("hect@", "hecta@"); /* 199まで */ substnum("ylene?@Amin","ylene?min",4,12); g("@A", "a"); g("@O", "o"); } /* * * 縮合環・ヘテロ環における母音脱落 * */ g("oct", "~FR|_oct"); /* bis-oct, not biso-ct */ if (strmatch(self,"iso")) { g("trisox", "tris~FR|_ox"); /* bisoxazole, bisoxy */ g("bisox", "bis~FR|_ox"); g("kisox", "kis~FR|_ox"); g("trisoval", "tris~FR|_oval"); /*iso-valine or bis-ovalene?*/ g("bisoval", "bis~FR|_oval"); g("kisoval", "kis~FR|_oval"); g("iso", "~FR|_iso"); } g("epi", "~FR|_epi"); g("epox", "~FR|_epox"); g("ind", "~FR|_ind"); g("iod", "~FR|_iod"); g("imino", "~FR|_imino"); g("imidazo","~FR|_imidazo"); g("ovalen", "~FR|_ovalen"); /* not o + val-lesamidine */ g("oxanthren","~FR|_oxanthren"); g("xanth", "~FR|_xanth"); g("oxyacanth","~FR|_QO_xiacanth"); g("oxy", "o~FR|_xy"); /* butoxy etc. */ g("ox", "~FR|_ox"); g("undec", "~FR|_undec"); g("zinc", "~FR|_zinc"); g("zircon", "~FR|_zircon"); g("az", "~FR|_az"); /* aza- azul- */ g("antimon","~FR|_antimon"); g("adamant","~FR|_adamant"); g("annul", "~FR|_annul"); g("benzalk","benzal~FR|_k"); g("alk", "~FR|_alk"); if (strmatch(self,"ac")) { g("acenaphth", "~FR|_acenaphth"); g("acephen", "~FR|_acephen"); g("aceanth", "~FR|_aceanth"); g("aconit", "~FR|_aconit"); g("acrid", "~FR|_acrid"); g("acr~FR|_ind","~FR|_acrind"); } if (strmatch(self,"ar")) { g("ars", "~FR|_ars"); g("aryl", "~FR|_aryl"); g("aryn", "~FR|_aryn"); g("aren", "~FR|_aren"); g("aroyl", "~FR|_aroyl"); g("aristol", "~FR|_aristol"); } if (strmatch(self,"eth")) { g("ethan", "~FR|_ethan"); g("ethen", "~FR|_ethen"); g("ethyn", "~FR|_ethyn"); g("ethyl", "~FR|_ethyl"); } g("androst","~FR|_androst"); g("anth", "~FR|_anth"); g("emet", "~FR|_emet"); g("ergo", "~FR|_ergo"); g("estr", "~FR|_estr"); /* 戻さない */ g("quinque","~NL|_quinKU_"); /* キンク */ #ifndef LITE g("abiet", "~FR|_abiet"); g("ajmal", "~FR|_ajmal"); g("akuamm", "~FR|_akuamm"), g("alsto", "~FR|_alsto"), g("ambros", "~FR|_ambros"); g("aspido", "~FR|_aspido"), g("atid", "~FR|_atid"); g("atis", "~FR|_atis"); g("eburnam","~FR|_eburnam"); g("eremophil","~FR|_eremophil"); g("eudesm", "~FR|_eudesm"); g("erythr", "~FR|_erythr"); g("iboga", "~FR|_iboga"); g("ophiobol","~NL|_QO_phiobol"); g("formosan","fo~FR|_rmosan"); g("ormosan", "~NL|_QO_rmosan"); g("olean", "~NL|_QO_lean"); g("urs", "~FR|_urs"); g("yohimb", "~FR|_yohimb"); #endif /* LITE */ /* * a,oの付加 */ g("guanabenz~", "guanabenzu~"); g("benz~", "benzo~"); g("naphth~", "naphtho~"); g("peryl~", "perylo~"); g("perylo", "perilo"); /* -yl で切らない */ /* HW名が関わらないようcycloで制限（cf.pentazole) */ if (strmatch(self,"cyclo")) { g("cyclo~FR|_oct", "cyclooct"); g("cycloprop~", "cyclopropa~"); /* propoxide */ g("cyclobut~", "cyclobuta~"); g("cyclopent~", "cyclopenta~"); g("cyclohex~", "cyclohexa~"); g("cyclohept~", "cyclohepta~"); g("cyclooct~", "cycloocta~"); g("cyclonon~", "cyclonona~"); g("cyclodec~", "cyclodeca~"); g("cyclo~FR|_alk~", "cycloalka~"); g("cyclo~FR|_undec~", "cycloundeca~"); substnum("cyclo?dec~","cyclo?deca~",2,9); } if (strmatch(self,"cos~")) { g("acos~", "acosa~"); g("docos~", "docosa~"); g("tricos~", "tricosa~"); g("icos~", "icosa~"); /* also eicosa */ } g("acont~", "aconta~"); g("hect~", "hecta~"); /* ついでに、切れ目を利用 */ if (strmatch(self,"rh")) { /* no-rh, not nor-h */ glookahead("rhen", VOWEL, "~FR|_rhen"); glookahead("rhod", VOWEL, "~FR|_rhod"); g("rhamn", "~FR|_rhamn"); g("rhea", "~FR|_rhea"); #ifndef LITE g("rhapont", "~FR|_rhapont"); /*before apo*/ g("rhein", "~FR|_rhein"); g("rhizo", "~FR|_rhizo"); g("rhyncho", "~FR|_rhyncho"); #endif /* LITE */ } glookahead("r", "hr", "r~FR|_"); g("apo", "~FR|_apo"); /*aporphine vs porphine */ g("iss", "is~FR|_s"); glookahead("isc", "eiy", "is~FR|_c"); glookahead("ish", VOWEL, "is~FR|_h"); g("sester","SE_SU_TA_"); g("heter~FR|_", "heter"); /* heter(o) */ g("ter~FR|_ra", "terra"); g("ter~FR|_ryl", "terryl"); g("ter~", "~NL|_TE_RU_~"); /* 環集合・テル, クアテル */ g("nor~", "~NL|_NO_RU_~"); /* 減炭・ノル */ g("bis~", "~NL|_BI_SU_~"); g("tris~","~NL|_TO_RI_SU_~"); g("kis~", "~NL|_KI_SU_~"); /* 元に戻す */ g("~FR|_",""); glookbehind("nl", "esterase~", "~NL|_esterase~"); glookahead("trans", "aeio", "TO_RA_NN_SU_"); /* trans=aldolase */ /* * 例外的字訳 */ g("_terpolymer", "_tahpolymer"); g("tautomer", "tohtomer"); g("plasma~", "plazma~"); if (strmatch(self,"gen")) { g("collagen", "collahgen"); g("cyanogen~", "cian~"); g("glycogen", "glycohgen"); #ifndef LITE g("fibrinogen", "fibrinohgen"); g("mitogen", "mitohgen"); g("phosphagen~","phosphahgen~"); g("plasmalogen","plazmalohgen"); g("plasminogen","plasminohgen"); g("resinogen", "rezinohgen"); g("zymogen", "zymohgen"); #endif /* LITE */ } if (strmatch(self,"ar")) { g("stearyl", "steQA_ryl"); g("calixaren","calikksu~AR|_aren"); g("resorcin", "resorcin~AR|_"); g("yl", "yl~AR|_"); g("het", "het~AR|_"); g("het~AR|_er", "heter~AR|_"); /* a/R_en では amine と結合して _enamine になる */ glookbehind("aeioy_","aren","a/R_ren"); glookbehind("aeioy_","aryl","a/R_ryl"); glookbehind("aeioy_","aryn","arayn"); g("~AR|_", ""); } if (strmatch(self,"chlor")) { g("chlorhex", "chloruhex"); g("chloramphenicol","chloramuphenicol"); g("chloromycetin","chloromaicetin"); } if (strmatch(self,"dur")) { g("osiduron", "osidowuron"); g("dural", "ZI_XU_ral"); /*duralumin*/ g("duren", "ZI_XU_ren"); /*durene*/ g("durid", "ZI_XU_rid"); /*duridine*/ g("durohydro", "ZI_XU_rohydro"); /*durohydroquinone*/ g("duroqui", "ZI_XU_roqui"); /*duroquinone*/ g("durol", "ZI_XU_rol"); /*durol*/ g("duryl", "ZI_XU_ril"); /*duryl*/ } if (strmatch(self,"glycyr")) { g("glycyrrhizic~", "glycyrrhizinic~"); g("glycyrrhetic~", "glycyrrhetinic~"); g("glycyrrhizin", "glytyrurhitin"); g("glycyrrh", "glytirurh"); } if (strmatch(self,"hydr")) { g("hydrangel", "hydroangel"); g("hydracryl", "hydroacril"); g("hydratrop", "hydroatrop"); g("hydrind", "hydroind"); g("hydriod", "hydroiod"); g("hydroxylami","hydroxilami"); g("xanthydr", "xantohydr"); } if (strmatch(self,"iso")) { g("sulfisoxazol","sulfuisokisazol"); g("isoxazo", "isooxazo"); g("erisocalci", "eruisocalci"); g("cortiso", "cortizo"); g("predniso", "prednizo"); } if (strmatch(self,"met")) { g("methemo", "metohemo"); g("methaqualon","metakalon"); g("metason", "metazon"); g("methason", "metazon"); g("methacryl", "metacril"); } if (strmatch(self,"orphin")) { g("dynorphin", "dainorphin"); g("morphine~", "moruhiNE_~"); g("morphin", "moruhin"); } if (strmatch(self,"oxy")) { g("carboxylic~","~NL|_karbonic~"); g("glyoxyl", "~NL|_glyoxil"); /* 接合名 */ g("cycloxygen", "cyclooxygen"); g("lipoxygen", "lipooxygen"); g("desoxy", "desuoxy"); } if (strmatch(self,"per")) { g("perox", "~NL|_per~NL|_ox"); #ifndef LITE g("tolperison", "tolperizon"); g("ypperite~", "iperite~"); #endif /* LITE */ } if (strmatch(self,"quin")) { g("camphorquinon","camforquinon"); g("quinine~", "KI_NI_HH_NE_~"); g("quinic~", "quinaic~"); g("quinaldic~", "quinaldinic~"); } if (strmatch(self,"res")) { g("resorcin~", "rezorcin~"); g("resorcyl", "resorcil"); g("_resin", "_rezin"); g("_resol~", "_rezol~"); g("_resite~", "_rezite~"); } if (strmatch(self,"ros")) { g("_rosin~", "_rozin~"); g("rosanilin", "rohzanilin"); } if (strmatch(self,"strychn")) { g("strychnine~","strykiniHH_NE_~"); g("strychnic~", "strykininic~"); g("strychn", "strykin"); } if (strmatch(self,"thre")) { g("threuron", "threwuron"); g("threul", "threwul"); g("indanthren", "indansren"); } if (strmatch(self,"ubi")) { g("ubichrom", "YU_bichrom"); g("ubidecar", "YU_bidecar"); g("ubihydro", "YU_bihydro"); g("ubiqui", "YU_biqui"); /*quinone, quitin*/ } if (strmatch(self,"xyl")) { g("hexyl", "hekisyl"); /* hexyl(ene) etc. ;*/ g("_xylic~", "_xililic~"); g("xyl", "xil"); } if (strmatch(self,"zym")) { g("lysozyme~", "lyzotihm~"); g("enzyme~", "QE_nzaim~"); /* urenzyme etc. */ g("isozyme~", "QA_isozaim~"); g("zym", "tim"); } #ifndef LITE g("bromfenac", "bromufenac"); g("_captan~", "_KI_XA_ptan~"); /* not mercaptan */ g("carbetho", "carboetho"); /* carbethoxy */ g("carbanion~", "carboanion~"); g("cefo", "ceHU_LO_"); g("chelat", "chileht"); g("dewar~SP|_benz", "DE_XU_wahbenz"); g("dewarbenz", "DE_XU_wahbenz"); glookbehind("aioy_", "ether", "QE_HH_ther"); g("fried", "frihd"); g("gyrase~", "jairehsu~"); g("kaempf", "kempf"); g("litmus~", "litmas~"); g("magenta~", "mazenta~"); g("mecloqualon", "meclokalon"); g("mineralocorticoid", "mineralcorticoid"); g("naphtha~", "nafsa~"); g("prism", "prizm"); g("twist", "tuist"); #endif /* LITE */ g("allophane~", "allofen~"); g("aspartame~", "aspartehm~"); g("carrageen", "caragihn"); g("crown", "kraun"); g("cellophane~", "cellohan~"); glookahead("cub","aey~", "KI_XU_b"); /* cubane */ g("_dopa~", "_dohpa~"); /* not for levodopa etc. */ g("duct", "dact"); g("eucalypt", "YU_HH_calypt"); g("fuller", "~NL|_fulahr"); g("gibberellic~", "jiberellinic~"); g("gibb", "jib"); g("ginkgo", "ginko"); g("multi", "malti"); g("nitren", "naitren"); g("pyrethroid", "pyresuroid"); g("silicone~", "silicohn~"); g("_soda~", "_sohda~"); g("thalidomid", "salidomaid"); if (strmatch(self,"in")) { g("ovalbumin", "ovoalbumin"); g("albumin", "QA_lbumin"); /* con-, lact-, etc. */ g("angiotensin","anziotensin"); g("blasticidin","blastosaidin"); g("calmodulin", "calmojulin"); g("casein", "kazein"); g("colchicin", "kolhitin"); g("cyclin", "saiklin"); g("flagellin", "flajelin"); g("gelatin", "zelatin"); g("margarine~", "mahgarine~"); g("niacin~", "naiacin~"); /* not for azoniacinnoline */ g("niacinamid", "naiacinamid"); g("niacinat", "naiacinat"); g("rhodanin", "rohdanin"); #ifndef LITE g("accelerin", "akcelerin"); g("acridarsin", "acridoarsin"); g("agglutinin", "aglutinin"); g("amphotericin","amufotericin"); g("ciguatoxin", "cigatoxin"); g("cycasin", "saicasin"); g("diazinon~", "daiazinon~"); g("endothelin", "endoselin"); g("idoxuridin", "idoksuuridin"); g("interferon", "intahferon"); g("interleukin","intahleukin"); g("nisin~", "naisin~"); g("nystatin", "naistatin"); g("oxethazain", "oxesazein"); g("physostigmin","phizostigmin"); g("turpentine~","terebin~"); g("vaccine~", "waktine~"); g("vaseline~", "waseline~"); #endif /* LITE */ } if (strmatch(self,"ol")) { g("macrolide~", "macrolaido~"); g("alcohol", "alcol"); g("cresol", "crezol"); g("pipecolic~", "pipecolinic~"); g("pipecol", "pipeKO_l"); g("propiol", "propiQO_l"); g("tetrol", "tetRO_l"); #ifndef LITE g("gossypol", "gosipol"); g("helvol", "helBO_l"); g("ichthammol", "ictamol"); g("oxprenolol", "okusuprenolol"); #endif /* LITE */ } if (strmatch(self,"undum~")) { g("corundum~", "corandamu~"); g("alundum~", "alandamu~"); g("carborundum~", "cahborandamu~"); } if (strmatch(self,"yl")) { g("cylindr", "cilindr"); g("neophyl", "neofyl"); g("tryptophyl", "tryptofyl"); g("beryll", "beril"); g("phyll", "fil"); g("scyll", "scil"); g("phenylephrin","phenilephrin"); g("carvacryl", "carvakryl"); g("acryl", "~NL|_acril"); /* 接合名 */ g("tricarballyl","tricarballil"); g("capryl", "kapril"); g("salicyl", "saRI_til"); g("piperonyl", "piperonil"); g("prehnityl", "prehnitil"); #ifndef LITE g("moxisylyt", "moxisiRI_t"); #endif /* LITE */ if (strmatch(self,"ylo")) { g("adenylo", "adenilo"); g("amylopectin", "amilopectin"); g("amylose", "amilose"); #ifndef LITE g("ascarylos", "ascarilos"); g("chylomicron", "chilomicron"); g("stylopin", "stilopin"); g("trachylob", "trachilob"); #endif /* LITE */ g("_nylon~", "_nailon~"); } } /* * アミド酸など */ if (strmatch(self,"am") || strmatch(self,"anil")) { g("adipa", "adip/C_a"); g("azelaa", "azela/C_a"); g("mala", "mal/C_a"); g("malea", "male/C_a"); g("oxala", "oxal/C_a"); g("phthala", "phthal/C_a"); g("pimela", "pimel/C_a"); g("sebaca", "sebac/C_a"); g("subera", "suber/C_a"); g("sulfena", "sulfen/C_a"); g("truxilla", "truxill/C_a"); g("ina", "in/C_a"); g("ona", "on/C_a"); g("ara", "ar/C_a"); g("ethin/C_a", "ethina"); if (strmatch(self,"_am")) { g("_amic~", "_QA_midoic~"); g("_amoyl", "_QA_moyl"); g("_amate", "_QA_mate"); g("_amato", "_QA_mato"); } if (strmatch(self,"_anil")) { g("_anilic~", "_QA_nilidoic~"); g("_anilat", "_QA_nilat"); g("_anilo", "_QA_nilo"); g("_anil~", "_QA_nil~"); } g("/C_", ""); } if (strmatch(self,"amic~")) { g("carbamic~", "carbaminic~"); g("glutamic~", "glutaminic~"); g("hydroxamic~","hydrokisamic~"); g("muramic~", "muraminic~"); g("oxamic~", "oxamidic~"); g("picramic~", "picraminic~"); g("sulfamic~", "sulfaminic~"); } if (strmatch(self,"anilic~")) { g("carbanilic~","carbanilidic~"); g("oxanilic~", "oxanilidic~"); } /* * 酸語幹の字訳例外 */ g("chaulmoogric~", "TI_XO_HH_RU_MU_HH_GU_RA_ic~"); g("chaulmoogr", "TI_XO_HH_RU_MU_HH_gr"); g("koji", "kouji"); g("oxalacet", "oxaloacet"); g("vaccen", "vakcen"); #ifndef LITE g("lysergic~", "lyzerginic~"); g("lyserg", "lyzerg"); g("nalidix", "nalidiks"); g("iotrox", "iotroks"); g("camsyl", "cansyl"); g("camsil", "cansil"); #endif /* LITE */ /* 接合名 */ g("malon", "~NL|_malon"); g("succin","~NL|_sukcin"); /* * 酸の字訳例外 */ if (strmatch(self,"ic~")) { g("arachic~", "QA_rakinic~"); g("azelaic~", "QA_zelainic~"); g("carbazic~", "carbazinic~"); g("chorismic~", "chorisminic~"); g("humic~", "huminic~"); g("pyridoxic~", "pyridoxinic~"); g("pyruvic~", "pyruvinic~"); g("toluic~", "toluilic~"); g("xanthic~", "xanthogenic~"); if (strmatch(self,"nic~")) { g("kainic~", "kaininic~"); g("styphnic~", "stifninic~"); g("tannic~", "tanninic~"); g("usnic~", "usninic~"); } if (strmatch(self,"bic~")) { g("ascorbic~", "ascorbinic~"); g("erythorbic~", "erythorbinic~"); g("sorbic~", "sorbinic~"); g("yohimbic~", "yohimbinic~"); } if (strmatch(self,"cic~")) { g("erucic~", "erucaic~"); g("leucic~", "leucinic~"); g("punicic~", "punicaic~"); g("sebacic~", "sebacinic~"); } if (strmatch(self,"dic~")) { g("acridic~", "acridinic~"); g("arachidic~", "arakidinic~"); g("brassidic~", "brassidinic~"); g("ricinelaidic~", "ricinelaidinic~"); g("elaidic~", "elaidinic~"); g("fusidic~", "fusidinic~"); g("phosphatidic~", "phosphatidinic~"); #ifndef LITE g("geddic~", "gedaic~"); g("gheddic~", "ghedaic~"); g("petroselidic~", "petroselidinic~"); #endif /* LITE */ } if (strmatch(self,"eic~")) { g("caffeic~", "caffeHH_ic~"); g("croceic~", "croceinic~"); g("cysteic~", "cysteinic~"); g("maleic~", "maleinic~"); g("linoleic~", "linohlic~"); g("ricinoleic~", "ricinohlic~"); g("oleic~", "oleinic~"); } if (strmatch(self,"lic~")) { g("angelic~", "angelicaic~"); g("ferulic~", "ferulaic~"); g("petroselic~", "petroselinic~"); g("pimelic~", "pimelinic~"); g("tiglic~", "tiglinic~"); g("vanillic~", "vanillinic~"); } if (strmatch(self,"pic~")) { g("adipic~", "QA_dipinic~"); g("chromotropic~", "kromoTO_ropic~"); g("hydnocarpic~", "hydnocarpusuic~"); g("sinapic~", "sinapinic~"); g("tropic~", "tropaic~"); } if (strmatch(self,"ric~")) { g("capric~", "caprinic~"); g("glyceric~", "glycerinic~"); g("hygric~", "hygrinic~"); g("lignoceric~", "lignocerinic~"); g("margaric~", "margarinic~"); g("picric~", "picrinic~"); g("stearic~", "stearinic~"); g("suberic~", "suberinic~"); g("veratric~", "veratrumic~"); } if (strmatch(self,"sic~")) { g("abscisic~", "absisinic~"); g("gentisic~", "gentizinic~"); g("melissic~", "melissinic~"); g("trimesic~", "trimesinic~"); } if (strmatch(self,"tic~")) { g("abietic~", "abietinic~"); g("aconitic~", "aconittic~"); g("aspartic~", "asparaginic~"); g("ceroplastic~", "ceroplastinic~"); g("cerotic~", "cerotinic~"); g("cresotic~", "cresotinic~"); g("isatic~", "isatinic~"); g("myristic~", "myristinic~"); g("nipecotic~", "nipecotinic~"); g("palmitic~", "palmitinic~"); g("pectic~", "pectinic~"); g("phytic~", "phytinic~"); g("stipitatic~", "stipitatinic~"); #ifndef LITE g("sapietic~", "sapietinic~"); g("traumatic~", "traumatinic~"); g("trimesitic~", "trimesitinic~"); #endif /* LITE */ } if (strmatch(self,"oic~")) { g("allantoic~", "alantoinic~"); g("caproic~", "capronic~"); g("hydantoic~", "hydantoinic~"); g("naphthoic~", "naphthoQE_ic~"); g("pantoic~", "pantoinic~"); g("pteroic~", "pteroinic~"); g("retinoic~", "retinoinic~"); #ifndef LITE g("canrenoic~", "canreno~NL|_ic~"); g("iopanoic~", "iopano~NL|_ic~"); #endif /* LITE */ g("thioic~", "thio~NL|_ic~"); g("selenoic~", "seleno~NL|_ic~"); g("telluroic~", "telluro~NL|_ic~"); g("ethenoic~", "ethenic~"); g("thenoic~", "theNO_ic~"); /* thiophenecarboxylic acid */ g("noic~", "nic~"); /*alkanoic acids*/ g("dioic~", "$2_ic~"); g("trioic~", "$3_ic~"); g("tetroic~", "$4_ic~"); g("pentoic~", "$5_ic~"); g("|_oic~", "|_ic~"); } } /* * "酸" の位置の調整（-icの後の文字まで動かす） * acetic-S acid 酢-S酸 * bis[acetic-[18O] [2H]acid] */ glookbehind("cosy", "~HY|_acid~", "~SP|_acid~"); /*ic,ous,oxo,oxy*/ moveacid(); /*この中で acid → $SAN_ */ g("acid~", "$SAN_~"); /* アミンは骨格の前だけ */ /* n, et, ol, yl, il の後 */ if (strmatch(self,"amin")) { g("amin", "@amin"); g("_en@a", "_ena"); g("_yn@a", "_yna"); g("dop@a", "dohpa"); g("hyoscy@a", "hiyostia"); g("methen@a", "methena"); g("osedi@a", "ose~NL|_dia"); /* lactosediamine */ g("phet@a", "pheta"); g("rhod@a", "rohda"); g("scopol@a", "scopola"); g("thiosin@a", "thiosina"); #ifndef LITE g("buphan@a", "buphana"); g("cinchon@a", "cinchona"); g("con@a", "cona"); g("crin@a", "crina"); g("dimorphol@a","dimorphola"); g("emet@a", "emeta"); g("guan@a", "guana"); g("lefet@am", "lefetam"); g("nicotian@a", "nicotiana"); g("prol@a", "prola"); g("quin@a", "quina"); g("surin@a", "surina"); #endif /* LITE */ g("phosphetamin", "phosphet@amin"); } g("imin", "@imin"); if (chrmatch(self,'@')) { g("ket@", "ket"); /* ketamine, ketimine */ g("nitr@", "nitro"); g("nitros@", "nitroso"); g("thion@am","thionam"); glookbehind("aeioy", "n@", "n~NL|_"); g("ol@", "ol~NL|_"); /* phospholamine, catecholamine */ g("one@", "one~NL|_"); /* quinoneimine */ g("et@", "et~NL|_"); g("yl@", "yl~NL|_"); g("il@", "il~NL|_"); /* sulfilimine, nitrilimine */ g("@", ""); /* @amin and @imin */ } /* アジド、類型名を考慮 */ if (strmatch(self,"azid")) { glookbehind("eio", "nazid", "nQA_zid"); g("phosphorazid", "phosphorQA_zid"); g("amidazid", "amidQA_zid"); } /* アミド・イミド */ g("anilid", "@anilid"); g("anisid", "@anisid"); if (strmatch(self,"mid")) { g("amid", "@amid"); g("imid", "@imid"); if (strmatch(self,"@am")) { glookahead("@amid", "bcdfghjklmnpqrstuvwxz", "amid"); /*aeioy*/ glookbehind("io", "b@amid", "bamid"); /* cobamide and analogs */ glookbehind("aeioyl_", "cer@amid", "ceramid"); g("glyceramid", "glycer@amid"); g("lignoceramid", "lignocer@amid"); #ifndef LITE g("acetazol@am", "acetazolam"); g("_ar@amid~", "_aramid~"); g("chlorprop@am","chlorpropam"); g("cefpir@am", "cefpiram"); g("cobam@am", "cobamam"); g("diclofen@am", "diclofenam"); g("disopyr@am", "disopyram"); g("ethenz@am", "ethenzam"); g("ethion@am", "ethionam"); g("glibencl@am", "glibenclam"); g("mur@am", "muram"); /* muramidase */ g("meth@am", "metham"); /* methamidophos */ g("metoclopr@am","metoclopram"); g("prothion@am", "prothionam"); g("tolaz@am", "tolazam"); g("tolbut@am", "tolbutam"); g("tiar@am", "tiaram"); g("tropic@am", "tropicam"); g("valles@am", "vallesam"); /*vallesamidine*/ g("zonis@am", "zonisam"); #endif /* LITE */ } if (strmatch(self,"@im")) { glookahead("@imid", "bcdfghjklmnpqrstuvwxz", "imid"); /*aeioy*/ g("per@imidin", "perimidin"); g("pyr@imid", "pyrimid"); /*pyrimido-*/ #ifndef LITE g("ethosux@im", "ethosukusim"); g("gluteth@im", "glutethim"); g("pr@imidon", "primidon"); #endif /* LITE */ } } if (chrmatch(self,'@')) { g("mucochlor@", "mucoculor@"); g("mucobrom@", "mucoburom@"); g("fluor@", "fluor"); g("chlor@", "chlor"); g("brom@", "brom"); g("iod@", "iod"); g("nitr@", "nitr"); g("nitros@", "nitros"); g("carb@", "carb"); g("cyan@", "cyan"); g("phosph@", "phosph"); g("sulf@", "sulf"); g("ox@", "ox"); g("ol@", "ol~NL|_@"); g("anthr@", "anthr"); g("@a", "QA_"); g("@i", "QI_"); } /* @amid, @imid etc. */ /* アルデヒド・オキシム */ if (strmatch(self,"ald")) { g("carbald", "carbaRU_d"); g("carboxald", "carboxaRU_d"); g("carbothiald", "carbothioald"); g("carboselenald", "carboselenoald"); g("carbotellurald", "carbotelluroald"); g("metaldehyd", "metaaldehyd"); g("paraldehyd", "paraaldehyd"); g("olald", "ol~NL|_QA_ld"); g("aldehyd", "QA_ldehyd"); g("aldoxim", "QA_ldoxim"); } g("onoxim", "on~NL|_oxim"); /* quinonoxime */ /* 炭素鎖（接合名）*/ g("phenacet","pheNA_cet"); g("acacet", "aKA_cet"); g("acet", "~NL|_QA_cet"); g("alanin", "~NL|_QA_lanin"); g("pyruv", "~NL|_pyruv"); g("glyc", "~NL|_glyc"); g("lact", "~NL|_lact"); /* lactam, indolelactate etc. */ g("undec", "~NL|_QU_ndec"); if (strmatch(self,"eth")) { g("phenethy", "HU_LE_NE_thy"); g("fenethy", "HU_LE_NE_thy"); g("ethan", "eth@an"); g("ethen", "eth@en"); g("ethyn", "eth@yn"); g("ethyl", "eth@yl"); g("meth@", "~NL|_meth"); glookbehind(ECONS, "eeth@", "e~NL|_eth"); glookbehind(VOWEL, "neth@", "n~NL|_eth"); glookbehind(VOWEL, "leth@", "l~NL|_eth"); g("@",""); } if (strmatch(self,"icos")) { g("henicos", "~NL|_henQI_cos"); g("heneicos", "~NL|_henQE_QI_cos"); g("eeicos", "e~NL|_QE_QI_cos"); g("tricos", "~NL|_TO_RI_cos"); g("furaneicos", "furan~NL|_QE_QI_cos"); g("pyraneicos", "pyran~NL|_QE_QI_cos"); glookbehind(ECONS, "eicos","e~NL|_QI_cos"); g("eicos","~NL|_QE_QI_cos"); glookbehind("oy", "licos","l~NL|_QI_cos"); g("nicos","n~NL|_QI_cos"); g("isicos","is~NL|_QI_cos"); /* bis, tris, tetrakis */ } if (strmatch(self,"iso")) { g("isocyan", "~NL|_isocian"); g("isothio", "~NL|_isothio"); g("isoseleno", "~NL|_isoseleno"); g("isotelluro", "~NL|_isotelluro"); g("isomerase", "~NL|_isomerase"); } if (strmatch(self,"nor")) { g("noradren", "nor~NL|_adren"); g("noracyl", "nor~NL|_acyl"); g("norepinephr","nor~NL|_epinephr"); g("norephedr", "nor~NL|_ephedr"); g("norethi", "nor~NL|_ethi"); } /* * 黙字のeの直後の子音 */ g("carb","~NL|_carb"); if (strmatch(self,"hydr")) { g("didehydr", "diDE_hidr"); g("adehydr", "aDE_hidr"); /*tetradehydro etc.*/ g("odehydr", "oDE_hidr"); /*codehydrogenase etc.*/ glookbehind("cpt", "hydr","hidr"); g("hydr", "~NL|_hydr"); } g("nitril", "~NL|_nitril"); g("quinon", "~NL|_quinon"); g("phosph", "~NL|_phosph"); /*ars は未対処*/ g("silicon","~NL|_silicon"); g("spiro", "~NL|_spiro"); /* cyclooctanespirocyclopentane */ g("sulf", "~NL|_sulf"); g("selen", "~NL|_selen"); g("selon", "~NL|_selon"); g("tellur", "~NL|_tellur"); g("tellon", "~NL|_tellon"); if (strmatch(self,"bor")) { g("boran", "~NL|_boran"); g("borin", "~NL|_borin"); g("boron", "~NL|_boron"); g("borylia", "~NL|_borilia"); } if (strmatch(self,"thi")) { g("isethion", "isetion"); /* e-thio の e が黙字にならぬよう */ g("|_methiodid","|_ME_TO_iodid"); g("|_ethiodid", "|_QE_TO_iodid"); g("methion", "ME_tion");/* methion-ine|ic */ g("ylethion", "ylQE_tion"); glookbehind(ECONS, "ethion","~NL|_thion"); g("ethion", "QE_tion"); /* ethion-ine|ic */ g("methi", "ME_TI_"); glookahead("thi", "aoy", "~NL|_thi"); } /* ヨード */ if (strmatch(self,"iod")) { g("iodid", "YO_HH_ZI_d"); /*挿入辞*/ glookbehind("aeioy_","iod","YO_HH_d"); g("yliod", "ylYO_HH_d"); g("period","perYO_HH_d"); } g("_ammono","_QA_NN_MO_no"); g("mono", "~NL|_mono"); g("bis", "~NL|_bis"); g("tris", "~NL|_tris"); if (strmatch(self,"non")) { glookbehind(ECONS, "enona", "e~NL|_nona"); glookbehind(ECONS, "enonyl","e~NL|_nonyl"); g("sele~NL|_non", "selenon"); g("~NL|_nonate~", "nonate~"); g("~NL|_nonato", "nonato"); g("~NL|_nonaphth", "nonaphth"); } if (strmatch(self,"tetr")) { g("etetrinon", "ete~NL|_trinon"); g("tetrin", "TE_TO_rin"); g("tetritol","TE_TO_ritol"); g("tetrityl","TE_TO_rityl"); g("tetrite~","TE_TO_rite~"); glookbehind(ECONS, "etetr", "e~NL|_tetr"); } glookbehind(ECONS, "e", "e@"); if (chrmatch(self,'@')) { g("@hen", "~NL|_hen"); g("@do", "~NL|_do"); g("@di", "~NL|_di"); g("@tri", "~NL|_tri"); g("@prop","~NL|_prop"); g("@but", "~NL|_but"); g("@pent","~NL|_pent"); g("@hex", "~NL|_hex"); g("@hept","~NL|_hept"); g("@oct", "~NL|_oct"); g("@hect","~NL|_hect"); g("@alk", "~NL|_alk"); g("@",""); } glookbehind(ECONS, "edec", "e~NL|_dec"); glookbehind(VOWEL, "noct", "n~NL|_oct"); glookbehind(VOWEL, "nalk", "n~NL|_alk"); g("benz", "~NL|_benz"); g("phthalein","~NL|_phthalein"); g("camphor~","$_shounou~"); /* ショウノウスルホン酸 */ /* * 語末 */ g("$", "~KK|_$"); g("~KK|_$SAN_", "$SAN_"); if (strmatch(self,"ate~")) { g("lyate~", "lyehto~"); g("phenidate~", "phenidehto~"); } if (strmatch(self,"mycin")) { g("aureomycin", "ohreomaicin"); g("thromycin", "sromaicin"); /* erythro etc. */ g("mitomycin", "maitomaicin"); g("puromycin", "PI_XU_romaicin"); g("mycin~", "maicin~"); } if (strmatch(self,"micin")) { g("elemicin~", "elemisin~"); g("micin~", "maicin~"); } if (strmatch(self,"yn")) { g("benzyn", "benzain"); g("pyridyn", "pyridain"); g("thiazyn", "thiazain"); } if (strmatch(self,"al~")) { #ifndef LITE g("anisal~", "anisaRU_~"); g("benzal~", "benzaRU_~"); g("cinnamal~", "cinnamaRU_~"); g("cumal~", "cumaRU_~"); g("phthal~", "phthaRU_~"); g("phthalal~", "phthalaRU_~"); g("saRI_tilal~","saRI_tilaRU_~"); g("vanillal~", "vanillaRU_~"); g("veratral~", "veratraRU_~"); #endif /* LITE */ g("crystal~", "crystaRU_~"); g("radical~", "radicaRU_~"); g("al~", "ahl~"); } if (strmatch(self,"t~")) { g("_unit~", "_yunit~"); g("_subunit~", "_sabuyunit~"); g("quat~", "quatto~"); g("stat~", "statto~"); glookbehind("ai", "uret~", "uretto~"); g("it~", "itto~"); g("ot~", "ohto~"); g("yt~", "itto~"); } g("pheneyl","phen~NL|_yl"); /*thiopheneyl etc.*/ g("pheneol","phen~NL|_ol"); /*thiopheneol etc.*/ g("glycerol~", "glycerin~"); glookahead("methylol", "~abcdfghjklmnopqrstuvwxyz", "ME_TI_RO_HH_RU_"); /* methylol, avoid "ole", or "oli" */ g("ol$SAN_", "ohl$SAN_"); if (strmatch(self,"sol~")) { g("_sol~", "_zolu~"); g("_hydrosol~", "_hydrozolu~"); g("_organosol~", "_organozolu~"); g("_plastisol~", "_plastizolu~"); } g("ol~", "ohl~"); g("oll~", "ohl~"); glookahead("calix", "bcdfghjklmnpqrstuvwxz~", "calikkusu"); /*aeioy*/ if (strmatch(self,"ex~")) { g("latex~", "latekkusu~"); g("plex~", "plekkusu~"); g("orex~", "orekusu~"); } if (strmatch(self,"os")) { g("os~FN|_","osu~FN|_"); g("os~SP|_","osu~SP|_"); g("os~", "ohsu~"); g("ose~", "ohsu~"); } g("dimer~", "daimah~"); g("mer~", "mah~"); #ifndef LITE g("eth~", "eSU_~"); g("fur~", "fuhr~"); g("ism~", "izm~"); #endif /* LITE */ if (strmatch(self,"e~")) { g("ole~", "ohl~"); g("ase~", "ahZE_~"); g("ate~", "ahto~"); g("ite~", "itto~"); g("ote~", "ohto~"); g("yte~", "itto~"); g("cycle~", "SA_icle~"); #ifndef LITE g("nce~", "NN_SU_~"); /* ance, ence */ g("some~", "SO_HH_MU_~"); #endif /* LITE */ g("ade~", "ad/E_~"); /* tetrade- */ g("|_ne~", "|_n/E_~"); g("|_de~", "|_d/E_~"); /* de-N-methyl */ g("|_dide~", "|_did/E_~"); /* -dide- */ g("|_tride~", "|_trid/E_~"); /* -tride- */ g("pre~KK|_$", "pr/E_$"); /* "preprotein */ g("e~", "~"); /* 語尾の e の脱落 */ } g("e$SAN_", "/E_$SAN_"); /* "-eic acid" */ g("/E_","e"); g("eazo","QA_zo"); /* * 基名・後ろの母音とつなげない */ g("inidene","inideNN_"); g("inidyne","inidyNN_"); g("ilidene","ilideNN_"); /*XXX*/ g("ilidyne","ilidyNN_"); /*XXX*/ if (strmatch(self,"yl")) { g("ylidene","~YL|_ilideNN_"); g("ylidyne","~YL|_ilidyNN_"); g("yliden", "~YL|_iliden"); g("ylidyn", "~YL|_ilidyn"); g("ylene", "~YL|_ileNN_"); /* maybe methylene, perylene, etc. */ g("ylen", "~YL|_ilen"); g("ylium", "~YL|_ilium"); g("ylid~", "~YL|_ilid~"); g("ylidar", "ylQI_dar"); /* idaric acid */ g("ylidur", "ylQI_dur"); /* iduronic acid */ g("ylan~", "ilan~"); g("ylin~", "ilin~"); g("ylio~", "iliQO_~"); g("yllin~", "illin~"); g("ylah", "ilah"); /* -ylal, -ylate, -ylase */ g("ylato", "ilato"); g("anylia", "anilia"); /* ylo接頭辞の処理。まだかなり不完全 */ if (strmatch(self,"ylo")) { g("ylo~", "ilo~"); g("yloin~", "iloin~"); g("ylon~", "ilon~"); g("yloyl", "iloyl"); g("yloleuc", "iRO_leuc"); g("yloct", "iRU_oct"); glookahead("ylol", "ei", "iRU_ol"); glookahead("ylor", "cmnt", "iRU_or"); g("ylosazon", "iRU_osazon"); g("yloxanthr", "iRU_oxanthr"); g("yloxanth", "QI_RO_~NL|_xanth"); g("yloxil~", "iRU_oxil~"); g("yloxilium", "iRU_oxilium"); g("yloxil", "QI_RO_xil"); /* xyl- */ glookahead("ylox", "aeioy","iRU_ox"); /*できるだけ少なく*/ g("ylylo", "ylQI_RO_~NL|_"); glookbehind("aeioy_", "ylo", "QI_RO_~NL|_"); g("amylo", "amilo~NL|_"); } g("ylil", "ilil"); g("ylyl", "ilyl"); g("yl~YL|_il", "ilil"); g("~YL|_", ""); g("yl","iRU_"); } g("a/R_ri", "aRI_HH_"); g("a/R_re", "aRE_HH_"); g("ammine","QA_NN_MI_NN_"); g("~KK|_", ""); /* * 等価字 */ g("exci","ekisi"); /*XXX*/ g("dz", "z"); /*XXX*/ g("tsu","tu"); /*XXX*/ g("ch","k"); g("ff","f"); g("pf","p"); g("kh","k"); /*XXX*/ g("gh","g"); g("ll","l"); g("pph","f"); g("ph","f"); g("rr","r"); /* also rrh */ g("rh","r"); glookahead("m", "bpmf", "n"); glookahead("sc", "eiy", "s"); g("th","t"); g("v","b"); g("xs","kis"); /*XXX*/ g("x","kis"); g("neuro","NI_XU_HH_RO_"); g("eu","oi"); /* ae, oe, ouは個別に対応する */ glookahead("coum", "aeio", "KU_m"); /* クマリンなど */ g("bourbon","BU_RU_bon"); g("ouaba", "QU_QA_ba"); /* ouaba-in, -genin */ /* g("ae","e"); */ /* g("oe","e"); */ /* g("ou","u"); */ /* yの判定：母音に挟まれた Y は子音 */ glookbehind("aiueoy_", "y", "/Y_"); /* 母音・記号の後の y は子音候補 */ g("y","i"); /* それ以外は i */ glookahead("/Y_", "aiueo", "y"); /* 母音が続けばヤ行 */ g("/Y_","i"); /* それ以外は i */ /* * カナ */ g("bb","TT_b"); glookahead("c", "ckq", "TT_"); g("dd","TT_d"); g("gg","TT_g"); g("kk","TT_k"); g("pp","TT_p"); g("ss","TT_s"); g("tt","TT_t"); g("zz","TT_z"); g("qua","KU_QA_"); g("qui","KI_"); g("quu","KU_"); /*XXX*/ g("que","KU_LE_"); g("quo","KU_LO_"); g("q", "k"); /*XXX*/ g("sha","SI_XA_"); g("shi","SI_"); g("shu","SI_XU_"); g("she","SI_LE_"); g("sho","SI_XO_"); g("sh", "SI_XU_"); g("ba","BA_"); g("bi","BI_"); g("bu","BU_"); g("be","BE_"); g("bo","BO_"); g("ca","KA_"); g("ci","SI_"); g("cu","KU_"); g("ce","SE_"); g("co","KO_"); g("da","DA_"); g("di","ZI_"); g("du","ZU_"); g("de","DE_"); g("do","DO_"); g("fa","HU_LA_"); g("fi","HU_LI_"); g("fu","HU_"); g("fe","HU_LE_"); g("fo","HO_"); g("ga","GA_"); g("gi","GI_"); g("gu","GU_"); g("ge","GE_"); g("go","GO_"); g("ha","HA_"); g("hi","HI_"); g("hu","HU_"); g("he","HE_"); g("ho","HO_"); g("ja","ZI_XA_"); g("ji","ZI_"); g("ju","ZI_XU_"); g("je","ZI_LE_"); g("jo","ZI_XO_"); g("ka","KA_"); g("ki","KI_"); g("ku","KU_"); g("ke","KE_"); g("ko","KO_"); g("la","RA_"); g("li","RI_"); g("lu","RU_"); g("le","RE_"); g("lo","RO_"); g("ma","MA_"); g("mi","MI_"); g("mu","MU_"); g("me","ME_"); g("mo","MO_"); g("na","NA_"); g("ni","NI_"); g("nu","NU_"); g("ne","NE_"); g("no","NO_"); g("pa","PA_"); g("pi","PI_"); g("pu","PU_"); g("pe","PE_"); g("po","PO_"); g("ra","RA_"); g("ri","RI_"); g("ru","RU_"); g("re","RE_"); g("ro","RO_"); g("sa","SA_"); g("si","SI_"); g("su","SU_"); g("se","SE_"); g("so","SO_"); g("ta","TA_"); g("ti","TI_"); g("tu","TU_"); g("te","TE_"); g("to","TO_"); g("wa","WA_"); g("wi","QU_LI_"); g("wu","QU_"); g("we","QU_LE_"); g("wo","QU_LO_"); g("ya","YA_"); g("yi","QI_"); g("yu","YU_"); g("ye","QI_QE_"); g("yo","YO_"); g("za","ZA_"); g("zi","ZI_"); g("zu","ZU_"); g("ze","ZE_"); g("zo","ZO_"); g("a", "QA_"); g("i", "QI_"); g("u", "QU_"); g("e", "QE_"); g("o", "QO_"); g("b", "BU_"); g("c", "KU_"); g("d", "DO_"); g("f", "HU_"); g("g", "GU_"); g("h", "HH_"); g("j", "ZI_XU_"); g("k", "KU_"); g("l", "RU_"); g("m", "MU_"); g("nn","NN_"); /*XXX*/ g("n", "NN_"); g("p", "PU_"); g("r", "RU_"); g("s", "SU_"); g("t", "TO_"); g("w", "QU_"); g("z", "ZU_"); /* * 日本文字に変換して出力 */ cvtjapan(); return self; } #ifndef JS void putmsg(char** p) { while (*p) puts(*p++); return; } void chgopt(char* p) { inv = inv2 = alt = alt2 = 0; /* all clear */ if (chrmatch(p,'a')) alt = 1; if (chrmatch(p,'A')) alt = alt2 = 1; if (chrmatch(p,'i')) inv = 1; if (chrmatch(p,'I')) inv2 = 1; return; } /* * Cにおけるmain関数。 * JSではフォームのオブジェクトを使用するので不要。 */ int main(int argc, char * argv[]) { int block = 1, maxbuff = 1; char buff[BUFSIZE], *line, *request; size_t buflen; /* メモリの確保 */ if ((line = malloc(BUFSIZE)) == NULL) { fprintf(stderr, "Error! on malloc: line."); exit(1); } if ((self = malloc(STRSIZE)) == NULL) { fprintf(stderr, "Error! on malloc: self."); exit(1); } if ((dest = malloc(STRSIZE)) == NULL) { fprintf(stderr, "Error! on malloc: dest."); exit(1); } if ((head = malloc(STRSIZE)) == NULL) { fprintf(stderr, "Error! on malloc: head."); exit(1); } if ((tail = malloc(STRSIZE)) == NULL) { fprintf(stderr, "Error! on malloc: tail."); exit(1); } /* コマンドライン */ if (1 < argc && *(argv[1]) == '-') { if (chrmatch(argv[1],'v')) { putmsg(version_msg); return 0; } if (chrmatch(argv[1],'h')) { putmsg(usage_msg); return 0; } chgopt(argv[1]); } /* 配列の初期化 */ initialize(); /* 読み込み */ do { strcpy(buff,""); /* 前の内容を消去 */ fgets(buff, BUFSIZE, stdin); /* 入力はbuffで受ける */ buflen = strlen(buff); if (buflen == 0) { break; } else if (buff[buflen-1] == '\n' || feof(stdin)) { if (buff[buflen-1] == '\n') buff[buflen-1] = '\0'; if (block>1) strcat(line, buff); else if (buflen == 0) { /* 空行 */ puts(""); continue; } request = block>1 ? line : buff; if (request[0] == '#' && request[1] == '-') { chgopt(buff); continue; } if (alt) puts(request); if (inv2) { inv = 0; puts(jk(request)); inv = 1; } puts(jk(request)); if (alt2) puts(""); block = 1; } else { if (block == 1) strcpy(line, buff); else strcat(line, buff); block++; if (maxbuff < block) { maxbuff++; line = realloc(line, maxbuff * BUFSIZE); if (line == NULL) { fprintf(stderr, "Error! on realloc: line."); exit(1); } self = realloc(self, maxbuff * STRSIZE); if (self == NULL) { fprintf(stderr, "Error! on realloc: self."); exit(1); } dest = realloc(dest, maxbuff * STRSIZE); if (dest == NULL) { fprintf(stderr, "Error! on realloc: dest."); exit(1); } head = realloc(head, maxbuff * STRSIZE); if (head == NULL) { fprintf(stderr, "Error! on realloc: head."); exit(1); } tail = realloc(tail, maxbuff * STRSIZE); if (tail == NULL) { fprintf(stderr, "Error! on realloc: tail."); exit(1); } } } } while (! feof(stdin)); #ifdef DEBUGGING { int maxsize = maxbuff * STRSIZE; fprintf(stderr, "size:%d\n", maxsize); fprintf(stderr, "self:%d\n", selflen); if (selflen > maxsize) fprintf(stderr, "OVERFLOW self!!\n"); fprintf(stderr, "dest:%d\n", destlen); if (destlen > maxsize) fprintf(stderr, "OVERFLOW dest!!\n"); } #endif return 0; } #endif /* END */