package acgtk
Abstract Categorial Grammar development toolkit
Install
Dune Dependency
Authors
Maintainers
Sources
acg-2.1.0-20240219.tar.gz
sha512=5d380a947658fb1201895cb4cb449b1f60f54914c563e85181d628a89f045c1dd7b5b2226bb7865dd090f87caa9187e0ea6c7a4ee3dc3dda340d404c4e76c7c2
doc/src/acgtk.grammars/data_lexer.ml.html
Source file data_lexer.ml
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211(* to generate as comment the character corresponding to a unicode code: perl -C -pe 's/(0x([\dA-Fa-f]{1,4}))/sprintf("%s (*%s*)",$1,chr(hex($2)))/eg' FILE Add the -i option to change the file in place. *) type context = NoContext | Signature | Lexicon type brackets = Round | Square let brackets = ref [] let kind_to_char = function Round -> '(' | Square -> '[' let add_bracket br loc = brackets := (loc, br) :: !brackets let remove_bracket br loc = match !brackets with | [] -> Errors.(LexingErrors.emit Lexing_l.UnstartedBracket ~loc) | (_, k) :: tl when k = br -> brackets := tl | (loc, k) :: _ -> Errors.(LexingErrors.emit (Lexing_l.MismatchParentheses (kind_to_char k)) ~loc) let check_brackets () = match !brackets with | [] -> () | (loc, k) :: _ -> Errors.(LexingErrors.emit (Lexing_l.MismatchParentheses (kind_to_char k)) ~loc) let ctx = ref NoContext let set c = ctx := c let get_loc = Sedlexing.lexing_positions let subscripts = [%sedlex.regexp? 0x1D63 (*ᵣ*) | 0x1D64 (*ᵤ*) | 0x1D65 (*ᵥ*) | 0x1D66 (*ᵦ*) | 0x1D67 (*ᵧ*) | 0x1D68 (*ᵨ*) | 0x1D69 (*ᵩ*) | 0x1D6A (*ᵪ*) | 0x2080 (*₀*) | 0x2081 (*₁*) | 0x2082 (*₂*) | 0x2083 (*₃*) | 0x2084 (*₄*) | 0x2085 (*₅*) | 0x2086 (*₆*) | 0x2087 (*₇*) | 0x2088 (*₈*) | 0x2089 (*₉*) | 0x208A (*₊*) | 0x208B (*₋*) | 0x208C (*₌*) | 0x208D (*₍*) | 0x208E (*₎*) | 0x208F (**) | 0x2090 (*ₐ*) | 0x2091 (*ₑ*) | 0x2092 (*ₒ*) | 0x2093 (*ₓ*) | 0x2094 (*ₔ*) | 0x2095 (*ₕ*) | 0x2096 (*ₖ*) | 0x2097 (*ₗ*) | 0x2098 (*ₘ*) | 0x2099 (*ₙ*) | 0x209A (*ₚ*) | 0x209B (*ₛ*) | 0x209C (*ₜ*) | 0x2C7C (*ⱼ*) ] let superscripts = [%sedlex.regexp? 0xB2 (*²*) | 0xB3 (*³*) | 0xB9 (*¹*) | 0x2070 (*⁰*) | 0x2071 (*ⁱ*) | 0x2074 (*⁴*) | 0x2075 (*⁵*) | 0x2076 (*⁶*) | 0x2077 (*⁷*) | 0x2078 (*⁸*) | 0x2079 (*⁹*) | 0x207A (*⁺*) | 0x207B (*⁻*) | 0x207C (*⁼*) | 0x207D (*⁽*) | 0x207E (*⁾*) | 0x207F (*ⁿ*) ] let id = [%sedlex.regexp? id_start, Star id_continue, Star (subscripts | superscripts), Star '\'' ] let symbols_base = [%sedlex.regexp? '|' | '!' | '"' | '#' | '$' | '%' | '&' | '*' | '+' | '-' | '/'| '\'' | '<' | '>' | '?' | '@' | '^' | '`' | '~' | '\\' | 0x00AC (*¬*) | 0xD7 (*×*) | 0xB7 (*·*) | 0xF7 (*÷*) | 0x2200 (*∀*) | 0x2201 (*∁*) | 0x2202 (*∂*) | 0x2203 (*∃*) | 0x2204 (*∄*) | 0x2205 (*∅*) | 0x2206 (*∆*) | 0x2207 (*∇*) | 0x2208 (*∈*) | 0x2209 (*∉*) | 0x220A (*∊*) | 0x220B (*∋*) | 0x220C (*∌*) | 0x220D (*∍*) | 0x220E (*∎*) | 0x220F (*∏*) | 0x2210 (*∐*) | 0x2211 (*∑*) | 0x2212 (*−*) | 0x2213 (*∓*) | 0x2214 (*∔*) | 0x2215 (*∕*) | 0x2216 (*∖*) | 0x2217 (*∗*) | 0x2218 (*∘*) | 0x2219 (*∙*) | 0x221A (*√*) | 0x221B (*∛*) | 0x221C (*∜*) | 0x221D (*∝*) | 0x221E (*∞*) | 0x221F (*∟*) | 0x2220 (*∠*) | 0x2221 (*∡*) | 0x2222 (*∢*) | 0x2223 (*∣*) | 0x2224 (*∤*) | 0x2225 (*∥*) | 0x2226 (*∦*) | 0x2227 (*∧*) | 0x2228 (*∨*) | 0x2229 (*∩*) | 0x222A (*∪*) | 0x222B (*∫*) | 0x222C (*∬*) | 0x222D (*∭*) | 0x222E (*∮*) | 0x222F (*∯*) | 0x2230 (*∰*) | 0x2231 (*∱*) | 0x2232 (*∲*) | 0x2233 (*∳*) | 0x2234 (*∴*) | 0x2235 (*∵*) | 0x2236 (*∶*) | 0x2237 (*∷*) | 0x2238 (*∸*) | 0x2239 (*∹*) | 0x223A (*∺*) | 0x223B (*∻*) | 0x223C (*∼*) | 0x223D (*∽*) | 0x223E (*∾*) | 0x223F (*∿*) | 0x2240 (*≀*) | 0x2241 (*≁*) | 0x2242 (*≂*) | 0x2243 (*≃*) | 0x2244 (*≄*) | 0x2245 (*≅*) | 0x2246 (*≆*) | 0x2247 (*≇*) | 0x2248 (*≈*) | 0x2249 (*≉*) | 0x224A (*≊*) | 0x224B (*≋*) | 0x224C (*≌*) | 0x224D (*≍*) | 0x224E (*≎*) | 0x224F (*≏*) | 0x2250 (*≐*) | 0x2251 (*≑*) | 0x2252 (*≒*) | 0x2253 (*≓*) | 0x2254 (*≔*) | 0x2255 (*≕*) | 0x2256 (*≖*) | 0x2257 (*≗*) | 0x2258 (*≘*) | 0x2259 (*≙*) | 0x225A (*≚*) | 0x225B (*≛*) | 0x225C (*≜*) | 0x225D (*≝*) | 0x225E (*≞*) | 0x225F (*≟*) | 0x2260 (*≠*) | 0x2261 (*≡*) | 0x2262 (*≢*) | 0x2263 (*≣*) | 0x2264 (*≤*) | 0x2265 (*≥*) | 0x2266 (*≦*) | 0x2267 (*≧*) | 0x2268 (*≨*) | 0x2269 (*≩*) | 0x226A (*≪*) | 0x226B (*≫*) | 0x226C (*≬*) | 0x226D (*≭*) | 0x226E (*≮*) | 0x226F (*≯*) | 0x2270 (*≰*) | 0x2271 (*≱*) | 0x2272 (*≲*) | 0x2273 (*≳*) | 0x2274 (*≴*) | 0x2275 (*≵*) | 0x2276 (*≶*) | 0x2277 (*≷*) | 0x2278 (*≸*) | 0x2279 (*≹*) | 0x227A (*≺*) | 0x227B (*≻*) | 0x227C (*≼*) | 0x227D (*≽*) | 0x227E (*≾*) | 0x227F (*≿*) | 0x2280 (*⊀*) | 0x2281 (*⊁*) | 0x2282 (*⊂*) | 0x2283 (*⊃*) | 0x2284 (*⊄*) | 0x2285 (*⊅*) | 0x2286 (*⊆*) | 0x2287 (*⊇*) | 0x2288 (*⊈*) | 0x2289 (*⊉*) | 0x228A (*⊊*) | 0x228B (*⊋*) | 0x228C (*⊌*) | 0x228D (*⊍*) | 0x228E (*⊎*) | 0x228F (*⊏*) | 0x2290 (*⊐*) | 0x2291 (*⊑*) | 0x2292 (*⊒*) | 0x2293 (*⊓*) | 0x2294 (*⊔*) | 0x2295 (*⊕*) | 0x2296 (*⊖*) | 0x2297 (*⊗*) | 0x2298 (*⊘*) | 0x2299 (*⊙*) | 0x229A (*⊚*) | 0x229B (*⊛*) | 0x229C (*⊜*) | 0x229D (*⊝*) | 0x229E (*⊞*) | 0x229F (*⊟*) | 0x22A0 (*⊠*) | 0x22A1 (*⊡*) | 0x22A2 (*⊢*) | 0x22A3 (*⊣*) | 0x22A4 (*⊤*) | 0x22A5 (*⊥*) | 0x22A6 (*⊦*) | 0x22A7 (*⊧*) | 0x22A8 (*⊨*) | 0x22A9 (*⊩*) | 0x22AA (*⊪*) | 0x22AB (*⊫*) | 0x22AC (*⊬*) | 0x22AD (*⊭*) | 0x22AE (*⊮*) | 0x22AF (*⊯*) | 0x22B0 (*⊰*) | 0x22B1 (*⊱*) | 0x22B2 (*⊲*) | 0x22B3 (*⊳*) | 0x22B4 (*⊴*) | 0x22B5 (*⊵*) | 0x22B6 (*⊶*) | 0x22B7 (*⊷*) | 0x22B8 (*⊸*) | 0x22B9 (*⊹*) | 0x22BA (*⊺*) | 0x22BB (*⊻*) | 0x22BC (*⊼*) | 0x22BD (*⊽*) | 0x22BE (*⊾*) | 0x22BF (*⊿*) | 0x22C0 (*⋀*) | 0x22C1 (*⋁*) | 0x22C2 (*⋂*) | 0x22C3 (*⋃*) | 0x22C4 (*⋄*) | 0x22C5 (*⋅*) | 0x22C6 (*⋆*) | 0x22C7 (*⋇*) | 0x22C8 (*⋈*) | 0x22C9 (*⋉*) | 0x22CA (*⋊*) | 0x22CB (*⋋*) | 0x22CC (*⋌*) | 0x22CD (*⋍*) | 0x22CE (*⋎*) | 0x22CF (*⋏*) | 0x22D0 (*⋐*) | 0x22D1 (*⋑*) | 0x22D2 (*⋒*) | 0x22D3 (*⋓*) | 0x22D4 (*⋔*) | 0x22D5 (*⋕*) | 0x22D6 (*⋖*) | 0x22D7 (*⋗*) | 0x22D8 (*⋘*) | 0x22D9 (*⋙*) | 0x22DA (*⋚*) | 0x22DB (*⋛*) | 0x22DC (*⋜*) | 0x22DD (*⋝*) | 0x22DE (*⋞*) | 0x22DF (*⋟*) | 0x22E0 (*⋠*) | 0x22E1 (*⋡*) | 0x22E2 (*⋢*) | 0x22E3 (*⋣*) | 0x22E4 (*⋤*) | 0x22E5 (*⋥*) | 0x22E6 (*⋦*) | 0x22E7 (*⋧*) | 0x22E8 (*⋨*) | 0x22E9 (*⋩*) | 0x22EA (*⋪*) | 0x22EB (*⋫*) | 0x22EC (*⋬*) | 0x22ED (*⋭*) | 0x22EE (*⋮*) | 0x22EF (*⋯*) | 0x22F0 (*⋰*) | 0x22F1 (*⋱*) | 0x22F2 (*⋲*) | 0x22F3 (*⋳*) | 0x22F4 (*⋴*) | 0x22F5 (*⋵*) | 0x22F6 (*⋶*) | 0x22F7 (*⋷*) | 0x22F8 (*⋸*) | 0x22F9 (*⋹*) | 0x22FA (*⋺*) | 0x22FB (*⋻*) | 0x22FC (*⋼*) | 0x22FD (*⋽*) | 0x22FE (*⋾*) (* arrows but linear and intuitionistic ones *) | 0x2190 (*←*) | 0x2191 (*↑*) | 0x2193 (*↓*) | 0x2194 (*↔*) | 0x2195 (*↕*) | 0x2196 (*↖*) | 0x2197 (*↗*) | 0x2198 (*↘*) | 0x2199 (*↙*) | 0x219A (*↚*) | 0x219B (*↛*) | 0x219C (*↜*) | 0x219D (*↝*) | 0x219E (*↞*) | 0x219F (*↟*) | 0x21A0 (*↠*) | 0x21A1 (*↡*) | 0x21A2 (*↢*) | 0x21A3 (*↣*) | 0x21A4 (*↤*) | 0x21A5 (*↥*) | 0x21A6 (*↦*) | 0x21A7 (*↧*) | 0x21A8 (*↨*) | 0x21A9 (*↩*) | 0x21AA (*↪*) | 0x21AB (*↫*) | 0x21AC (*↬*) | 0x21AD (*↭*) | 0x21AE (*↮*) | 0x21AF (*↯*) | 0x21B0 (*↰*) | 0x21B1 (*↱*) | 0x21B2 (*↲*) | 0x21B3 (*↳*) | 0x21B4 (*↴*) | 0x21B5 (*↵*) | 0x21B6 (*↶*) | 0x21B7 (*↷*) | 0x21B8 (*↸*) | 0x21B9 (*↹*) | 0x21BA (*↺*) | 0x21BB (*↻*) | 0x21BC (*↼*) | 0x21BD (*↽*) | 0x21BE (*↾*) | 0x21BF (*↿*) | 0x21C0 (*⇀*) | 0x21C1 (*⇁*) | 0x21C2 (*⇂*) | 0x21C3 (*⇃*) | 0x21C4 (*⇄*) | 0x21C5 (*⇅*) | 0x21C6 (*⇆*) | 0x21C7 (*⇇*) | 0x21C8 (*⇈*) | 0x21C9 (*⇉*) | 0x21CA (*⇊*) | 0x21CB (*⇋*) | 0x21CC (*⇌*) | 0x21CD (*⇍*) | 0x21CE (*⇎*) | 0x21CF (*⇏*) | 0x21D0 (*⇐*) | 0x21D1 (*⇑*) | 0x21D3 (*⇓*) | 0x21D4 (*⇔*) | 0x21D5 (*⇕*) | 0x21D6 (*⇖*) | 0x21D7 (*⇗*) | 0x21D8 (*⇘*) | 0x21D9 (*⇙*) | 0x21DA (*⇚*) | 0x21DB (*⇛*) | 0x21DC (*⇜*) | 0x21DD (*⇝*) | 0x21DE (*⇞*) | 0x21DF (*⇟*) | 0x21E0 (*⇠*) | 0x21E1 (*⇡*) | 0x21E2 (*⇢*) | 0x21E3 (*⇣*) | 0x21E4 (*⇤*) | 0x21E5 (*⇥*) | 0x21E6 (*⇦*) | 0x21E7 (*⇧*) | 0x21E8 (*⇨*) | 0x21E9 (*⇩*) | 0x21EA (*⇪*) | 0x21EB (*⇫*) | 0x21EC (*⇬*) | 0x21ED (*⇭*) | 0x21EE (*⇮*) | 0x21EF (*⇯*) | 0x21F0 (*⇰*) | 0x21F1 (*⇱*) | 0x21F2 (*⇲*) | 0x21F3 (*⇳*) | 0x21F4 (*⇴*) | 0x21F5 (*⇵*) | 0x21F6 (*⇶*) | 0x21F7 (*⇷*) | 0x21F8 (*⇸*) | 0x21F9 (*⇹*) | 0x21FA (*⇺*) | 0x21FB (*⇻*) | 0x21FC (*⇼*) | 0x21FD (*⇽*) | 0x21FE (*⇾*) | 0x21FF (*⇿*) ] let symbols = [%sedlex.regexp? Plus symbols_base, Star (subscripts | superscripts), Opt ('_', Star (id_continue)), Star (subscripts | superscripts) ] let rec eat_comment buf n = if n = 0 then lex buf else try match%sedlex buf with | "(*" -> eat_comment buf (n + 1) | "*)" -> eat_comment buf (n - 1) | eof -> Errors.(LexingErrors.emit Lexing_l.UnterminatedComment ~loc:(get_loc buf)) | any -> eat_comment buf n | _ -> assert false with | Sedlexing.MalFormed -> Errors.(LexingErrors.emit Lexing_l.Malformed ~loc:(get_loc buf)) and lex buf = try match%sedlex buf with | white_space -> lex buf | '\010' | '\013' | "\013\010" -> lex buf | "(*" -> eat_comment buf 1 | "*)" -> Errors.(LexingErrors.emit Lexing_l.UnstartedComment ~loc:(get_loc buf)) | eof -> check_brackets (); Data_parser.EOI | "signature" -> check_brackets (); if !ctx = NoContext then let () = set Signature in Data_parser.SIG_OPEN (get_loc buf) else Data_parser.IDENT (Sedlexing.Utf8.lexeme buf, get_loc buf) | "lexicon" -> check_brackets (); if !ctx = NoContext then let () = set Lexicon in Data_parser.LEX_OPEN (get_loc buf) else Data_parser.IDENT (Sedlexing.Utf8.lexeme buf, get_loc buf) | "nl_lexicon" -> check_brackets (); if !ctx = NoContext then let () = set Lexicon in Data_parser.NL_LEX_OPEN (get_loc buf) else Data_parser.IDENT (Sedlexing.Utf8.lexeme buf, get_loc buf) | '=' -> check_brackets (); Data_parser.EQUAL (get_loc buf) | "<<" -> check_brackets (); set NoContext; Data_parser.COMPOSE (get_loc buf) | ';' -> check_brackets (); Data_parser.SEMICOLON (get_loc buf) | ':' -> check_brackets (); Data_parser.COLON (get_loc buf) | ',' -> Data_parser.COMMA (get_loc buf) | '(' -> let loc = get_loc buf in add_bracket Round loc; Data_parser.LPAREN loc | ')' -> let loc = get_loc buf in remove_bracket Round loc; Data_parser.RPAREN loc | '[' -> let loc = get_loc buf in add_bracket Square loc; Data_parser.LSQBRACKET loc | ']' -> let loc = get_loc buf in remove_bracket Square loc; Data_parser.RSQBRACKET loc | '.' -> Data_parser.DOT (get_loc buf) | "end" -> check_brackets (); set NoContext; Data_parser.END_OF_DEC (get_loc buf) | "type" -> check_brackets (); Data_parser.TYPE (get_loc buf) | "prefix" -> check_brackets (); Data_parser.PREFIX (get_loc buf) | "infix" -> check_brackets (); Data_parser.INFIX (get_loc buf) | "binder" -> check_brackets (); Data_parser.BINDER (get_loc buf) | "lambda" | (0x03BB (*λ*), 0x2070 (*⁰*)) (* λ⁰ *) -> Data_parser.LAMBDA0 (get_loc buf) | "Lambda" | 0x03BB (*λ*) (* λ *)-> Data_parser.LAMBDA (get_loc buf) | "->" | 0x2192 (*→*) (* "→" *) -> Data_parser.LIN_ARROW (get_loc buf) | "=>" | 0x21D2 (*⇒*) (* "⇒" *) -> Data_parser.ARROW (get_loc buf) | ":=" -> Data_parser.COLON_EQUAL (get_loc buf) | id -> Data_parser.IDENT (Sedlexing.Utf8.lexeme buf, get_loc buf) | '\\', id -> let n = Sedlexing.Utf8.lexeme buf in Data_parser.IDENT (String.sub n 1 (String.length n - 1), get_loc buf) | symbols -> Data_parser.SYMBOL (Sedlexing.Utf8.lexeme buf, get_loc buf) | any -> Errors.(LexingErrors.emit (Lexing_l.BadChar (Sedlexing.Utf8.lexeme buf)) ~loc:(get_loc buf)) | _ -> assert false with | Sedlexing.MalFormed -> Errors.(LexingErrors.emit Lexing_l.Malformed ~loc:(get_loc buf))