| 1 | #!/usr/bin/perl -I/home/phil/perl/cpan/DataTableText/lib/ -I/home/phil/perl/cpan/NasmX86/lib/ -I/home/phil/perl/cpan/AsmC/lib/ | ||||||||||
| 2 | #------------------------------------------------------------------------------- | ||||||||||
| 3 | # Parse a Unisyn expression. | ||||||||||
| 4 | # Philip R Brenan at appaapps dot com, Appa Apps Ltd Inc., 2021 | ||||||||||
| 5 | #------------------------------------------------------------------------------- | ||||||||||
| 6 | # podDocumentation | ||||||||||
| 7 | # Finished in 13.14s, bytes: 2,655,008, execs: 465,858 | ||||||||||
| 8 | package Unisyn::Parse; | ||||||||||
| 9 | our $VERSION = "20210826"; | ||||||||||
| 10 | 1 | ▶ | use warnings FATAL => qw(all); | ||||||||
|
Subroutine
BEGIN: called CC=1 SCAR=0.0
| |||||||||||
| 11 | 1 | ▶ | use strict; | ||||||||
|
Subroutine
BEGIN: called CC=1 SCAR=0.0
| |||||||||||
| 12 | 1 | ▶ | use Carp qw(confess cluck); | ||||||||
|
Subroutine
BEGIN: called CC=1 SCAR=0.0
| |||||||||||
| 13 | 1 | ▶ | use Data::Dump qw(dump); | ||||||||
|
Subroutine
BEGIN: called CC=1 SCAR=0.0
| |||||||||||
| 14 | 1 | ▶ | use Data::Table::Text qw(:all !parse); | ||||||||
|
Subroutine
BEGIN: called CC=1 SCAR=0.0
| |||||||||||
| 15 | 1 | ▶ | use Nasm::X86 qw(:all); | ||||||||
|
Subroutine
BEGIN: called CC=1 SCAR=0.0
| |||||||||||
| 16 | 1 | ▶ | use feature qw(say current_sub); | ||||||||
|
Subroutine
BEGIN: called CC=1 SCAR=0.0
| |||||||||||
| 17 | 1 | ▶ | use utf8; | ||||||||
|
Subroutine
BEGIN: called CC=1 SCAR=0.0
| |||||||||||
| 18 | |||||||||||
| 19 | makeDieConfess; | ||||||||||
| 20 | |||||||||||
| 21 | my $develop = -e q(/home/phil/); # Developing | ||||||||||
| 22 | my $arena; # We always reload the actual arena address from rax and so this is permissible | ||||||||||
| 23 | our $debug = 0; # Include debug code if true - the tests will fail if you do | ||||||||||
| 24 | |||||||||||
| 25 | #D1 Create # Create a Unisyn parse of a utf8 string. | ||||||||||
| 26 | |||||||||||
| 27 | sub create($$) # Create a new unisyn parse from a utf8 string | ||||||||||
| 28 | 0 | ▶ | {my ($address, $size) = @_; # Address of utf8 source string to parse as a variable, length of string as a variable | ||||||||
|
Subroutine
create: not called CC=2 SCAR=17.9
| |||||||||||
| 29 | 0 | ▶ | @_ == 2 or confess; | ||||||||
|
Branch: 1 branch
| |||||||||||
| 30 | |||||||||||
| 31 | 0 | my $a = $arena = CreateArena; # Arena to hold parse tree - every parse tree gets its own arena so that we can free parses separately | |||||||||
| 32 | |||||||||||
| 33 | 0 | my $fail = V('fail'); | |||||||||
| 34 | 0 | my $parse = V('parse'); | |||||||||
| 35 | |||||||||||
| 36 | 0 | $address->setReg(rax); | |||||||||
| 37 | 0 | $size ->setReg(rdi); | |||||||||
| 38 | 0 | Shl rdi, 3; | |||||||||
| 39 | |||||||||||
| 40 | 0 | my $p = genHash(__PACKAGE__, # Description of parse | |||||||||
| 41 | arena => $a, # Arena containing tree | ||||||||||
| 42 | size8 => $size, # Size of source string as utf8 | ||||||||||
| 43 | address8 => $address, # Address of source string as utf8 | ||||||||||
| 44 | source32 => V(source32), # Source text as utf32 | ||||||||||
| 45 | sourceSize32 => V(sourceSize32), # Size of utf32 allocation | ||||||||||
| 46 | sourceLength32 => V(sourceLength32), # Length of utf32 string | ||||||||||
| 47 | parse => $parse, # Offset to the head of the parse tree | ||||||||||
| 48 | fails => $fail, # Number of failures encountered in this parse | ||||||||||
| 49 | ); | ||||||||||
| 50 | |||||||||||
| 51 | 0 | $p->parseUtf8; # Parse utf8 source string | |||||||||
| 52 | |||||||||||
| 53 | 0 | $p | |||||||||
| 54 | } | ||||||||||
| 55 | |||||||||||
| 56 | #D1 Parse # Parse Unisyn expressions | ||||||||||
| 57 | |||||||||||
| 58 | our $Lex = &lexicalData; # Lexical table definitions | ||||||||||
| 59 | |||||||||||
| 60 | our $ses = RegisterSize rax; # Size of an element on the stack | ||||||||||
| 61 | our ($w1, $w2, $w3) = (r8, r9, r10); # Work registers | ||||||||||
| 62 | our $prevChar = r11; # The previous character parsed | ||||||||||
| 63 | our $index = r12; # Index of current element | ||||||||||
| 64 | our $element = r13; # Contains the item being parsed | ||||||||||
| 65 | our $start = r14; # Start of the parse string | ||||||||||
| 66 | our $size = r15; # Length of the input string | ||||||||||
| 67 | our $parseStackBase = rsi; # The base of the parsing stack in the stack | ||||||||||
| 68 | our $arenaReg = rax; # The arena in which we are building the parse tree | ||||||||||
| 69 | our $indexScale = 4; # The size of a utf32 character | ||||||||||
| 70 | our $lexCodeOffset = 3; # The offset in a classified character to the lexical code. | ||||||||||
| 71 | our $bitsPerByte = 8; # The number of bits in a byte | ||||||||||
| 72 | |||||||||||
| 73 | our $Ascii = $$Lex{lexicals}{Ascii} {number}; # Ascii | ||||||||||
| 74 | our $assign = $$Lex{lexicals}{assign} {number}; # Assign | ||||||||||
| 75 | our $CloseBracket = $$Lex{lexicals}{CloseBracket} {number}; # Close bracket | ||||||||||
| 76 | our $empty = $$Lex{lexicals}{empty} {number}; # Empty element | ||||||||||
| 77 | our $NewLineSemiColon = $$Lex{lexicals}{NewLineSemiColon}{number}; # New line semicolon | ||||||||||
| 78 | our $OpenBracket = $$Lex{lexicals}{OpenBracket} {number}; # Open bracket | ||||||||||
| 79 | our $prefix = $$Lex{lexicals}{prefix} {number}; # Prefix operator | ||||||||||
| 80 | our $semiColon = $$Lex{lexicals}{semiColon} {number}; # Semicolon | ||||||||||
| 81 | our $suffix = $$Lex{lexicals}{suffix} {number}; # Suffix | ||||||||||
| 82 | our $term = $$Lex{lexicals}{term} {number}; # Term | ||||||||||
| 83 | our $variable = $$Lex{lexicals}{variable} {number}; # Variable | ||||||||||
| 84 | our $WhiteSpace = $$Lex{lexicals}{WhiteSpace} {number}; # Variable | ||||||||||
| 85 | our $firstSet = $$Lex{structure}{first}; # First symbols allowed | ||||||||||
| 86 | our $lastSet = $$Lex{structure}{last}; # Last symbols allowed | ||||||||||
| 87 | our $asciiNewLine = ord("\n"); # New line in ascii | ||||||||||
| 88 | our $asciiSpace = ord(' '); # Space in ascii | ||||||||||
| 89 | |||||||||||
| 90 | sub getAlpha($$$) #P Load the position of a lexical item in its alphabet from the current character. | ||||||||||
| 91 | {my ($register, $address, $index) = @_; # Register to load, address of start of string, index into string | ||||||||||
| 92 | Mov $register, "[$address+$indexScale*$index]"; # Load lexical code | ||||||||||
| 93 | } | ||||||||||
| 94 | |||||||||||
| 95 | sub getLexicalCode($$$) #P Load the lexical code of the current character in memory into the specified register. | ||||||||||
| 96 | {my ($register, $address, $index) = @_; # Register to load, address of start of string, index into string | ||||||||||
| 97 | Mov $register, "[$address+$indexScale*$index+$lexCodeOffset]"; # Load lexical code | ||||||||||
| 98 | } | ||||||||||
| 99 | |||||||||||
| 100 | sub putLexicalCode($$$$) #P Put the specified lexical code into the current character in memory. | ||||||||||
| 101 | {my ($register, $address, $index, $code) = @_; # Register used to load code, address of string, index into string, code to put | ||||||||||
| 102 | defined($code) or confess; | ||||||||||
| 103 | Mov $register, $code; | ||||||||||
| 104 | Mov "[$address+$indexScale*$index+$lexCodeOffset]", $register; # Save lexical code | ||||||||||
| 105 | } | ||||||||||
| 106 | |||||||||||
| 107 | sub loadCurrentChar() #P Load the details of the character currently being processed so that we have the index of the character in the upper half of the current character and the lexical type of the character in the lowest byte. | ||||||||||
| 108 | {my $r = $element."b"; # Classification byte | ||||||||||
| 109 | |||||||||||
| 110 | Mov $element, $index; # Load index of character as upper dword | ||||||||||
| 111 | Shl $element, $indexScale * $bitsPerByte; # Save the index of the character in the upper half of the register so that we know where the character came from. | ||||||||||
| 112 | getLexicalCode $r, $start, $index; # Load lexical classification as lowest byte | ||||||||||
| 113 | |||||||||||
| 114 | Cmp $r, $$Lex{bracketsBase}; # Brackets , due to their frequency, start after 0x10 with open even and close odd | ||||||||||
| 115 | IfGe # Brackets | ||||||||||
| 116 | Then | ||||||||||
| 117 | {And $r, 1 # Bracket: 0 - open, 1 - close | ||||||||||
| 118 | }, | ||||||||||
| 119 | Else | ||||||||||
| 120 | {Cmp $r, $Ascii; # Ascii is a type of variable | ||||||||||
| 121 | IfEq | ||||||||||
| 122 | Then | ||||||||||
| 123 | {Mov $r, $variable; | ||||||||||
| 124 | }, | ||||||||||
| 125 | Else | ||||||||||
| 126 | {Cmp $r, $NewLineSemiColon; # New line semicolon is a type of semi colon | ||||||||||
| 127 | IfEq | ||||||||||
| 128 | Then | ||||||||||
| 129 | {Mov $r, $semiColon; | ||||||||||
| 130 | }; | ||||||||||
| 131 | }; | ||||||||||
| 132 | }; | ||||||||||
| 133 | } | ||||||||||
| 134 | |||||||||||
| 135 | sub checkStackHas($) #P Check that we have at least the specified number of elements on the stack. | ||||||||||
| 136 | {my ($depth) = @_; # Number of elements required on the stack | ||||||||||
| 137 | Mov $w1, $parseStackBase; | ||||||||||
| 138 | Sub $w1, rsp; | ||||||||||
| 139 | Cmp $w1, $ses * $depth; | ||||||||||
| 140 | } | ||||||||||
| 141 | |||||||||||
| 142 | sub pushElement() #P Push the current element on to the stack. | ||||||||||
| 143 | {Push $element; | ||||||||||
| 144 | if ($debug) | ||||||||||
| 145 | {PrintOutStringNL "Push Element:"; | ||||||||||
| 146 | PrintOutRegisterInHex $element; | ||||||||||
| 147 | } | ||||||||||
| 148 | } | ||||||||||
| 149 | |||||||||||
| 150 | sub pushEmpty() #P Push the empty element on to the stack. | ||||||||||
| 151 | {Mov $w1, $index; | ||||||||||
| 152 | Shl $w1, $indexScale * $bitsPerByte; | ||||||||||
| 153 | Or $w1, $empty; | ||||||||||
| 154 | Push $w1; | ||||||||||
| 155 | if ($debug) | ||||||||||
| 156 | {PrintOutStringNL "Push Empty"; | ||||||||||
| 157 | } | ||||||||||
| 158 | } | ||||||||||
| 159 | |||||||||||
| 160 | sub lexicalNameFromLetter($) #P Lexical name for a lexical item described by its letter. | ||||||||||
| 161 | {my ($l) = @_; # Letter of the lexical item | ||||||||||
| 162 | my %l = $Lex->{treeTermLexicals}->%*; | ||||||||||
| 163 | my $n = $l{$l}; | ||||||||||
| 164 | confess "No such lexical: $l" unless $n; | ||||||||||
| 165 | $n->{short} | ||||||||||
| 166 | } | ||||||||||
| 167 | |||||||||||
| 168 | sub lexicalNumberFromLetter($) #P Lexical number for a lexical item described by its letter. | ||||||||||
| 169 | {my ($l) = @_; # Letter of the lexical item | ||||||||||
| 170 | my $n = lexicalNameFromLetter $l; | ||||||||||
| 171 | my $N = $Lex->{lexicals}{$n}{number}; | ||||||||||
| 172 | confess "No such lexical named: $n" unless defined $N; | ||||||||||
| 173 | $N | ||||||||||
| 174 | } | ||||||||||
| 175 | |||||||||||
| 176 | sub new($$) #P Create a new term in the parse tree rooted on the stack. | ||||||||||
| 177 | {my ($depth, $description) = @_; # Stack depth to be converted, text reason why we are creating a new term | ||||||||||
| 178 | PrintOutStringNL "New: $description" if $debug; | ||||||||||
| 179 | |||||||||||
| 180 | $arena->bs->getReg($arenaReg); # Address arena | ||||||||||
| 181 | my $t = $arena->CreateTree; # Create a tree in the arena to hold the details of the lexical elements on the stack | ||||||||||
| 182 | my $d = V(data); | ||||||||||
| 183 | $t->insert(V(key, 0), V(data, $term)); # Create a term - we only have terms at the moment in the parse tee - but that might change in the future | ||||||||||
| 184 | $t->insert(V(key, 1), V(data, $depth)); # The number of elements in the term | ||||||||||
| 185 | |||||||||||
| 186 | for my $i(1..$depth) # Each term, | ||||||||||
| 187 | {my $j = $depth + 1 - $i; | ||||||||||
| 188 | Pop $w1; | ||||||||||
| 189 | PrintOutRegisterInHex $w1 if $debug; | ||||||||||
| 190 | $d->getReg($w1); | ||||||||||
| 191 | $t->insert( V(key, 2 * $j ), $d); # The lexical type of each operand on the even keys below 16- which actually only takes 4 bits so this could be improved on. | ||||||||||
| 192 | |||||||||||
| 193 | Mov $w2, $w1; | ||||||||||
| 194 | Shr $w2, 32; # Offset in source | ||||||||||
| 195 | $d->getReg($w2); # Offset in source in lower dword | ||||||||||
| 196 | Cmp $w1."b", $term; # Check whether the lexical item on the stack is a term | ||||||||||
| 197 | |||||||||||
| 198 | IfEq # Insert a sub tree if we are inserting a term | ||||||||||
| 199 | Then | ||||||||||
| 200 | {$t->insertTree(V(key, 2 * $j + 1), $d); # A reference to another term | ||||||||||
| 201 | }, | ||||||||||
| 202 | Else # Insert the offset in the utf32 source if we are not on a term | ||||||||||
| 203 | {$t->insert (V(key, 2 * $j + 1), $d); # Offset in source | ||||||||||
| 204 | } | ||||||||||
| 205 | } | ||||||||||
| 206 | $t->first->setReg($w1); # Term | ||||||||||
| 207 | Shl $w1, 32; # Push offset to tree into the upper dword | ||||||||||
| 208 | Or $w1."b", $term; # Mark as a term tree | ||||||||||
| 209 | Push $w1; # Place simulated term on stack | ||||||||||
| 210 | } | ||||||||||
| 211 | |||||||||||
| 212 | sub error($) #P Die. | ||||||||||
| 213 | {my ($message) = @_; # Error message | ||||||||||
| 214 | PrintOutStringNL "Error: $message"; | ||||||||||
| 215 | PrintOutString "Element: "; | ||||||||||
| 216 | PrintOutRegisterInHex $element; | ||||||||||
| 217 | PrintOutString "Index : "; | ||||||||||
| 218 | PrintOutRegisterInHex $index; | ||||||||||
| 219 | Exit(0); | ||||||||||
| 220 | } | ||||||||||
| 221 | |||||||||||
| 222 | sub testSet($$) #P Test a set of items, setting the Zero Flag is one matches else clear the Zero flag. | ||||||||||
| 223 | {my ($set, $register) = @_; # Set of lexical letters, Register to test | ||||||||||
| 224 | my @n = map {sprintf("0x%x", lexicalNumberFromLetter $_)} split //, $set; # Each lexical item by number from letter | ||||||||||
| 225 | my $end = Label; | ||||||||||
| 226 | for my $n(@n) | ||||||||||
| 227 | {Cmp $register."b", $n; | ||||||||||
| 228 | Je $end | ||||||||||
| 229 | } | ||||||||||
| 230 | ClearZF; | ||||||||||
| 231 | SetLabel $end; | ||||||||||
| 232 | } | ||||||||||
| 233 | |||||||||||
| 234 | sub checkSet($) #P Check that one of a set of items is on the top of the stack or complain if it is not. | ||||||||||
| 235 | {my ($set) = @_; # Set of lexical letters | ||||||||||
| 236 | my @n = map {lexicalNumberFromLetter $_} split //, $set; | ||||||||||
| 237 | my $end = Label; | ||||||||||
| 238 | |||||||||||
| 239 | for my $n(@n) | ||||||||||
| 240 | {Cmp "byte[rsp]", $n; | ||||||||||
| 241 | Je $end | ||||||||||
| 242 | } | ||||||||||
| 243 | error("Expected one of: '$set' on the stack"); | ||||||||||
| 244 | ClearZF; | ||||||||||
| 245 | SetLabel $end; | ||||||||||
| 246 | } | ||||||||||
| 247 | |||||||||||
| 248 | sub reduce($) #P Convert the longest possible expression on top of the stack into a term at the specified priority. | ||||||||||
| 249 | {my ($priority) = @_; # Priority of the operators to reduce | ||||||||||
| 250 | $priority =~ m(\A(1|3)\Z); # Level: 1 - all operators, 2 - priority 2 operators | ||||||||||
| 251 | my ($success, $end) = map {Label} 1..2; # Exit points | ||||||||||
| 252 | |||||||||||
| 253 | checkStackHas 3; # At least three elements on the stack | ||||||||||
| 254 | IfGe | ||||||||||
| 255 | Then | ||||||||||
| 256 | {my ($l, $d, $r) = ($w1, $w2, $w3); | ||||||||||
| 257 | Mov $l, "[rsp+".(2*$ses)."]"; # Top 3 elements on the stack | ||||||||||
| 258 | Mov $d, "[rsp+".(1*$ses)."]"; | ||||||||||
| 259 | Mov $r, "[rsp+".(0*$ses)."]"; | ||||||||||
| 260 | |||||||||||
| 261 | if ($debug) | ||||||||||
| 262 | {PrintOutStringNL "Reduce 3:"; | ||||||||||
| 263 | PrintOutRegisterInHex $l, $d, $r; | ||||||||||
| 264 | } | ||||||||||
| 265 | |||||||||||
| 266 | testSet("t", $l); # Parse out infix operator expression | ||||||||||
| 267 | IfEq | ||||||||||
| 268 | Then | ||||||||||
| 269 | {testSet("t", $r); | ||||||||||
| 270 | IfEq | ||||||||||
| 271 | Then | ||||||||||
| 272 | {testSet($priority == 1 ? "ads" : 'd', $d); # Reduce all operators or just reduce infix priority 3 operators | ||||||||||
| 273 | IfEq | ||||||||||
| 274 | Then | ||||||||||
| 275 | {Add rsp, 3 * $ses; # Reorder into polish notation | ||||||||||
| 276 | Push $_ for $d, $l, $r; | ||||||||||
| 277 | new(3, "Term infix term"); | ||||||||||
| 278 | Jmp $success; | ||||||||||
| 279 | }; | ||||||||||
| 280 | }; | ||||||||||
| 281 | }; | ||||||||||
| 282 | |||||||||||
| 283 | testSet("b", $l); # Parse parenthesized term | ||||||||||
| 284 | IfEq | ||||||||||
| 285 | Then | ||||||||||
| 286 | {testSet("B", $r); | ||||||||||
| 287 | IfEq | ||||||||||
| 288 | Then | ||||||||||
| 289 | {testSet("t", $d); | ||||||||||
| 290 | IfEq | ||||||||||
| 291 | Then | ||||||||||
| 292 | {Add rsp, $ses; | ||||||||||
| 293 | new(1, "Bracketed term"); | ||||||||||
| 294 | new(2, "Brackets for term"); | ||||||||||
| 295 | PrintOutStringNL "Reduce by ( term )" if $debug; | ||||||||||
| 296 | Jmp $success; | ||||||||||
| 297 | }; | ||||||||||
| 298 | }; | ||||||||||
| 299 | }; | ||||||||||
| 300 | # KeepFree $l, $d, $r; | ||||||||||
| 301 | }; | ||||||||||
| 302 | |||||||||||
| 303 | checkStackHas 2; # At least two elements on the stack | ||||||||||
| 304 | IfGe # Convert an empty pair of parentheses to an empty term | ||||||||||
| 305 | Then | ||||||||||
| 306 | {my ($l, $r) = ($w1, $w2); | ||||||||||
| 307 | |||||||||||
| 308 | if ($debug) | ||||||||||
| 309 | {PrintOutStringNL "Reduce 2:"; | ||||||||||
| 310 | PrintOutRegisterInHex $l, $r; | ||||||||||
| 311 | } | ||||||||||
| 312 | |||||||||||
| 313 | # KeepFree $l, $r; # Why ? | ||||||||||
| 314 | Mov $l, "[rsp+".(1*$ses)."]"; # Top 3 elements on the stack | ||||||||||
| 315 | Mov $r, "[rsp+".(0*$ses)."]"; | ||||||||||
| 316 | testSet("b", $l); # Empty pair of parentheses | ||||||||||
| 317 | IfEq | ||||||||||
| 318 | Then | ||||||||||
| 319 | {testSet("B", $r); | ||||||||||
| 320 | IfEq | ||||||||||
| 321 | Then | ||||||||||
| 322 | {Add rsp, 2 * $ses; # Pop expression | ||||||||||
| 323 | Push $l; # Bracket as operator | ||||||||||
| 324 | new(1, "Empty brackets"); | ||||||||||
| 325 | Jmp $success; | ||||||||||
| 326 | }; | ||||||||||
| 327 | }; | ||||||||||
| 328 | testSet("s", $l); # Semi-colon, close implies remove unneeded semi | ||||||||||
| 329 | IfEq | ||||||||||
| 330 | Then | ||||||||||
| 331 | {testSet("B", $r); | ||||||||||
| 332 | IfEq | ||||||||||
| 333 | Then | ||||||||||
| 334 | {Add rsp, 2 * $ses; # Pop expression | ||||||||||
| 335 | Push $r; | ||||||||||
| 336 | PrintOutStringNL "Reduce by ;)" if $debug; | ||||||||||
| 337 | Jmp $success; | ||||||||||
| 338 | }; | ||||||||||
| 339 | }; | ||||||||||
| 340 | testSet("p", $l); # Prefix, term | ||||||||||
| 341 | IfEq | ||||||||||
| 342 | Then | ||||||||||
| 343 | {testSet("t", $r); | ||||||||||
| 344 | IfEq | ||||||||||
| 345 | Then | ||||||||||
| 346 | {new(2, "Prefix term"); | ||||||||||
| 347 | Jmp $success; | ||||||||||
| 348 | }; | ||||||||||
| 349 | }; | ||||||||||
| 350 | # KeepFree $l, $r; | ||||||||||
| 351 | }; | ||||||||||
| 352 | |||||||||||
| 353 | ClearZF; # Failed to match anything | ||||||||||
| 354 | Jmp $end; | ||||||||||
| 355 | |||||||||||
| 356 | SetLabel $success; # Successfully matched | ||||||||||
| 357 | SetZF; | ||||||||||
| 358 | |||||||||||
| 359 | SetLabel $end; # End | ||||||||||
| 360 | } # reduce | ||||||||||
| 361 | |||||||||||
| 362 | sub reduceMultiple($) #P Reduce existing operators on the stack. | ||||||||||
| 363 | {my ($priority) = @_; # Priority of the operators to reduce | ||||||||||
| 364 | K('count',99)->for(sub # An improbably high but finite number of reductions | ||||||||||
| 365 | {my ($index, $start, $next, $end) = @_; # Execute body | ||||||||||
| 366 | reduce($priority); | ||||||||||
| 367 | Jne $end; # Keep going as long as reductions are possible | ||||||||||
| 368 | }); | ||||||||||
| 369 | } | ||||||||||
| 370 | |||||||||||
| 371 | sub accept_a() #P Assign. | ||||||||||
| 372 | {checkSet("t"); | ||||||||||
| 373 | reduceMultiple 2; | ||||||||||
| 374 | PrintOutStringNL "accept a" if $debug; | ||||||||||
| 375 | pushElement; | ||||||||||
| 376 | } | ||||||||||
| 377 | |||||||||||
| 378 | sub accept_b #P Open. | ||||||||||
| 379 | {checkSet("abdps"); | ||||||||||
| 380 | PrintOutStringNL "accept b" if $debug; | ||||||||||
| 381 | pushElement; | ||||||||||
| 382 | } | ||||||||||
| 383 | |||||||||||
| 384 | sub accept_B #P Closing parenthesis. | ||||||||||
| 385 | {checkSet("bst"); | ||||||||||
| 386 | PrintOutStringNL "accept B" if $debug; | ||||||||||
| 387 | reduceMultiple 1; | ||||||||||
| 388 | pushElement; | ||||||||||
| 389 | reduceMultiple 1; | ||||||||||
| 390 | checkSet("bst"); | ||||||||||
| 391 | } | ||||||||||
| 392 | |||||||||||
| 393 | sub accept_d #P Infix but not assign or semi-colon. | ||||||||||
| 394 | {checkSet("t"); | ||||||||||
| 395 | PrintOutStringNL "accept d" if $debug; | ||||||||||
| 396 | pushElement; | ||||||||||
| 397 | } | ||||||||||
| 398 | |||||||||||
| 399 | sub accept_p #P Prefix. | ||||||||||
| 400 | {checkSet("abdps"); | ||||||||||
| 401 | PrintOutStringNL "accept p" if $debug; | ||||||||||
| 402 | pushElement; | ||||||||||
| 403 | } | ||||||||||
| 404 | |||||||||||
| 405 | sub accept_q #P Post fix. | ||||||||||
| 406 | {checkSet("t"); | ||||||||||
| 407 | PrintOutStringNL "accept q" if $debug; | ||||||||||
| 408 | IfEq # Post fix operator applied to a term | ||||||||||
| 409 | Then | ||||||||||
| 410 | {Pop $w1; | ||||||||||
| 411 | pushElement; | ||||||||||
| 412 | Push $w1; | ||||||||||
| 413 | new(2, "Postfix"); | ||||||||||
| 414 | } | ||||||||||
| 415 | } | ||||||||||
| 416 | |||||||||||
| 417 | sub accept_s #P Semi colon. | ||||||||||
| 418 | {checkSet("bst"); | ||||||||||
| 419 | PrintOutStringNL "accept s" if $debug; | ||||||||||
| 420 | Mov $w1, "[rsp]"; | ||||||||||
| 421 | testSet("s", $w1); | ||||||||||
| 422 | IfEq # Insert an empty element between two consecutive semicolons | ||||||||||
| 423 | Then | ||||||||||
| 424 | {pushEmpty; | ||||||||||
| 425 | }; | ||||||||||
| 426 | reduceMultiple 1; | ||||||||||
| 427 | pushElement; | ||||||||||
| 428 | } | ||||||||||
| 429 | |||||||||||
| 430 | sub accept_v #P Variable. | ||||||||||
| 431 | {checkSet("abdps"); | ||||||||||
| 432 | PrintOutStringNL "accept v" if $debug; | ||||||||||
| 433 | pushElement; | ||||||||||
| 434 | new(1, "Variable"); | ||||||||||
| 435 | V(count,99)->for(sub # Reduce prefix operators | ||||||||||
| 436 | {my ($index, $start, $next, $end) = @_; | ||||||||||
| 437 | checkStackHas 2; | ||||||||||
| 438 | Jl $end; | ||||||||||
| 439 | my ($l, $r) = ($w1, $w2); | ||||||||||
| 440 | Mov $l, "[rsp+".(1*$ses)."]"; | ||||||||||
| 441 | Mov $r, "[rsp+".(0*$ses)."]"; | ||||||||||
| 442 | testSet("p", $l); | ||||||||||
| 443 | Jne $end; | ||||||||||
| 444 | new(2, "Prefixed variable"); | ||||||||||
| 445 | }); | ||||||||||
| 446 | } | ||||||||||
| 447 | |||||||||||
| 448 | sub parseExpressionCode() #P Parse the string of classified lexical items addressed by register $start of length $length. The resulting parse tree (if any) is returned in r15. | ||||||||||
| 449 | {my $end = Label; | ||||||||||
| 450 | my $eb = $element."b"; # Contains a byte from the item being parsed | ||||||||||
| 451 | |||||||||||
| 452 | Cmp $size, 0; # Check for empty expression | ||||||||||
| 453 | Je $end; | ||||||||||
| 454 | |||||||||||
| 455 | loadCurrentChar; # Load current character | ||||||||||
| 456 | ### Need test for ignorable white space as first character | ||||||||||
| 457 | testSet($firstSet, $element); | ||||||||||
| 458 | IfNe | ||||||||||
| 459 | Then | ||||||||||
| 460 | {error(<<END =~ s(\n) ( )gsr); | ||||||||||
| 461 | Expression must start with 'opening parenthesis', 'prefix | ||||||||||
| 462 | operator', 'semi-colon' or 'variable'. | ||||||||||
| 463 | END | ||||||||||
| 464 | }; | ||||||||||
| 465 | |||||||||||
| 466 | testSet("v", $element); # Single variable | ||||||||||
| 467 | IfEq | ||||||||||
| 468 | Then | ||||||||||
| 469 | {pushElement; | ||||||||||
| 470 | new(1, "accept initial variable"); | ||||||||||
| 471 | }, | ||||||||||
| 472 | Else | ||||||||||
| 473 | {testSet("s", $element); # Semi | ||||||||||
| 474 | IfEq | ||||||||||
| 475 | Then | ||||||||||
| 476 | {pushEmpty; | ||||||||||
| 477 | new(1, "accept initial semicolon"); | ||||||||||
| 478 | }; | ||||||||||
| 479 | pushElement; | ||||||||||
| 480 | }; | ||||||||||
| 481 | |||||||||||
| 482 | Inc $index; # We have processed the first character above | ||||||||||
| 483 | Mov $prevChar, $element; # Initialize the previous lexical item | ||||||||||
| 484 | |||||||||||
| 485 | For # Parse each utf32 character after it has been classified | ||||||||||
| 486 | {my ($start, $end, $next) = @_; # Start and end of the classification loop | ||||||||||
| 487 | loadCurrentChar; # Load current character | ||||||||||
| 488 | |||||||||||
| 489 | PrintOutRegisterInHex $element if $debug; | ||||||||||
| 490 | |||||||||||
| 491 | Cmp $eb, $WhiteSpace; | ||||||||||
| 492 | Je $next; # Ignore white space | ||||||||||
| 493 | |||||||||||
| 494 | Cmp $eb, 1; # Brackets are singular but everything else can potential be a plurality | ||||||||||
| 495 | IfGt | ||||||||||
| 496 | Then | ||||||||||
| 497 | {Cmp $prevChar."b", $eb; # Compare with previous element known not to be white space or a bracket | ||||||||||
| 498 | Je $next | ||||||||||
| 499 | }; | ||||||||||
| 500 | Mov $prevChar, $element; # Save element to previous element now we know we are on a different element | ||||||||||
| 501 | |||||||||||
| 502 | for my $l(sort keys $Lex->{lexicals}->%*) # Each possible lexical item after classification | ||||||||||
| 503 | {my $x = $Lex->{lexicals}{$l}{letter}; | ||||||||||
| 504 | next unless $x; # Skip characters that do not have a letter defined for Tree::Term because the lexical items needed to layout a file of lexical items are folded down to the actual lexical items required to represent the language independent of the textual layout with white space. | ||||||||||
| 505 | |||||||||||
| 506 | my $n = $Lex->{lexicals}{$l}{number}; | ||||||||||
| 507 | Comment "Compare to $n for $l"; | ||||||||||
| 508 | Cmp $eb, $n; | ||||||||||
| 509 | |||||||||||
| 510 | IfEq | ||||||||||
| 511 | Then | ||||||||||
| 512 | {eval "accept_$x"; | ||||||||||
| 513 | Jmp $next | ||||||||||
| 514 | }; | ||||||||||
| 515 | } | ||||||||||
| 516 | error("Unexpected lexical item"); # Not selected | ||||||||||
| 517 | } $index, $size; | ||||||||||
| 518 | |||||||||||
| 519 | testSet($lastSet, $prevChar); # Last lexical element | ||||||||||
| 520 | IfNe # Incomplete expression | ||||||||||
| 521 | Then | ||||||||||
| 522 | {error("Incomplete expression"); | ||||||||||
| 523 | }; | ||||||||||
| 524 | |||||||||||
| 525 | K('count', 99)->for(sub # Remove trailing semicolons if present | ||||||||||
| 526 | {my ($index, $start, $next, $end) = @_; # Execute body | ||||||||||
| 527 | checkStackHas 2; | ||||||||||
| 528 | Jl $end; # Does not have two or more elements | ||||||||||
| 529 | Pop $w1; | ||||||||||
| 530 | testSet("s", $w1); # Check that the top most element is a semi colon | ||||||||||
| 531 | IfNe # Not a semi colon so put it back and finish the loop | ||||||||||
| 532 | Then | ||||||||||
| 533 | {Push $w1; | ||||||||||
| 534 | Jmp $end; | ||||||||||
| 535 | }; | ||||||||||
| 536 | }); | ||||||||||
| 537 | |||||||||||
| 538 | reduceMultiple 1; # Final reductions | ||||||||||
| 539 | |||||||||||
| 540 | checkStackHas 1; | ||||||||||
| 541 | IfNe # Incomplete expression | ||||||||||
| 542 | Then | ||||||||||
| 543 | {error("Multiple expressions on stack"); | ||||||||||
| 544 | }; | ||||||||||
| 545 | |||||||||||
| 546 | Pop r15; # The resulting parse tree | ||||||||||
| 547 | Shr r15, 32; # The offset of the resulting parse tree | ||||||||||
| 548 | SetLabel $end; | ||||||||||
| 549 | } # parseExpressionCode | ||||||||||
| 550 | |||||||||||
| 551 | sub parseExpression(@) #P Create a parser for an expression described by variables. | ||||||||||
| 552 | {my (@parameters) = @_; # Parameters describing expression | ||||||||||
| 553 | |||||||||||
| 554 | my $s = Subroutine | ||||||||||
| 555 | {my ($p) = @_; # Parameters | ||||||||||
| 556 | PushR $parseStackBase, map {"r$_"} 8..15; | ||||||||||
| 557 | $$p{source}->setReg($start); # Start of expression string after it has been classified | ||||||||||
| 558 | $$p{size} ->setReg($size); # Number of characters in the expression | ||||||||||
| 559 | |||||||||||
| 560 | Mov $parseStackBase, rsp; # Set base of parse stack | ||||||||||
| 561 | |||||||||||
| 562 | parseExpressionCode; | ||||||||||
| 563 | |||||||||||
| 564 | $$p{parse}->getReg(r15); # Number of characters in the expression | ||||||||||
| 565 | |||||||||||
| 566 | Mov rsp, $parseStackBase; # Remove parse stack | ||||||||||
| 567 | # Remove new frame | ||||||||||
| 568 | PopR; | ||||||||||
| 569 | } [qw(source size parse)], name => q(Unisyn::Parse::parse); | ||||||||||
| 570 | |||||||||||
| 571 | |||||||||||
| 572 | $s->call(@parameters); | ||||||||||
| 573 | } # parse | ||||||||||
| 574 | |||||||||||
| 575 | sub MatchBrackets(@) #P Replace the low three bytes of a utf32 bracket character with 24 bits of offset to the matching opening or closing bracket. Opening brackets have even codes from 0x10 to 0x4e while the corresponding closing bracket has a code one higher. | ||||||||||
| 576 | {my (@parameters) = @_; # Parameters | ||||||||||
| 577 | @_ >= 1 or confess; | ||||||||||
| 578 | |||||||||||
| 579 | my $s = Subroutine | ||||||||||
| 580 | {my ($p) = @_; # Parameters | ||||||||||
| 581 | Comment "Match brackets in utf32 text"; | ||||||||||
| 582 | |||||||||||
| 583 | my $finish = Label; | ||||||||||
| 584 | PushR xmm0, k7, r10, r11, r12, r13, r14, r15, rsi; # R15 current character address. r14 is the current classification. r13 the last classification code. r12 the stack depth. r11 the number of opening brackets found. r10 address of first utf32 character. | ||||||||||
| 585 | |||||||||||
| 586 | Mov rsi, rsp; # Save stack location so we can use the stack to record the brackets we have found | ||||||||||
| 587 | ClearRegisters r11, r12, r15; # Count the number of brackets and track the stack depth, index of each character | ||||||||||
| 588 | K(three, 3)->setMaskFirst(k7); # These are the number of bytes that we are going to use for the offsets of brackets which limits the size of a program to 24 million utf32 characters | ||||||||||
| 589 | $$p{fail} ->getReg(r11); # Clear failure indicator | ||||||||||
| 590 | $$p{opens} ->getReg(r11); # Clear count of opens | ||||||||||
| 591 | $$p{address}->setReg(r10); # Address of first utf32 character | ||||||||||
| 592 | my $w = RegisterSize eax; # Size of a utf32 character | ||||||||||
| 593 | |||||||||||
| 594 | $$p{size}->for(sub # Process each utf32 character in the block of memory | ||||||||||
| 595 | {my ($index, $start, $next, $end) = @_; | ||||||||||
| 596 | my $continue = Label; | ||||||||||
| 597 | |||||||||||
| 598 | Mov r14b, "[r10+$w*r15+3]"; # Classification character | ||||||||||
| 599 | |||||||||||
| 600 | Cmp r14, 0x10; # First bracket | ||||||||||
| 601 | Jl $continue; # Less than first bracket | ||||||||||
| 602 | Cmp r14, 0x4f; # Last bracket | ||||||||||
| 603 | Jg $continue; # Greater than last bracket | ||||||||||
| 604 | |||||||||||
| 605 | Test r14, 1; # Zero means that the bracket is an opener | ||||||||||
| 606 | IfZ sub # Save an opener then continue | ||||||||||
| 607 | {Push r15; # Save position in input | ||||||||||
| 608 | Push r14; # Save opening code | ||||||||||
| 609 | Inc r11; # Count number of opening brackets | ||||||||||
| 610 | Inc r12; # Number of brackets currently open | ||||||||||
| 611 | Jmp $continue; | ||||||||||
| 612 | }; | ||||||||||
| 613 | Cmp r12, 1; # Check that there is a bracket to match on the stack | ||||||||||
| 614 | IfLt sub # Nothing on stack | ||||||||||
| 615 | {Not r15; # Minus the offset at which the error occurred so that we can fail at zero | ||||||||||
| 616 | $$p{fail}->getReg(r15); # Position in input that caused the failure | ||||||||||
| 617 | Jmp $finish; # Return | ||||||||||
| 618 | }; | ||||||||||
| 619 | Mov r13, "[rsp]"; # Peek at the opening bracket code which is on top of the stack | ||||||||||
| 620 | Inc r13; # Expected closing bracket | ||||||||||
| 621 | Cmp r13, r14; # Check for match | ||||||||||
| 622 | IfNe sub # Mismatch | ||||||||||
| 623 | {Not r15; # Minus the offset at which the error occurred so that we can fail at zero | ||||||||||
| 624 | $$p{fail}->getReg(r15); # Position in input that caused the failure | ||||||||||
| 625 | Jmp $finish; # Return | ||||||||||
| 626 | }; | ||||||||||
| 627 | Pop r13; # The closing bracket matches the opening bracket | ||||||||||
| 628 | Pop r13; # Offset of opener | ||||||||||
| 629 | Dec r12; # Close off bracket sequence | ||||||||||
| 630 | Vpbroadcastq xmm0, r15; # Load offset of opener | ||||||||||
| 631 | Vmovdqu8 "[r10+$w*r13]\{k7}", xmm0; # Save offset of opener in the code for the closer - the classification is left intact so we still know what kind of bracket we have | ||||||||||
| 632 | Vpbroadcastq xmm0, r13; # Load offset of opener | ||||||||||
| 633 | Vmovdqu8 "[r10+$w*r15]\{k7}", xmm0; # Save offset of closer in the code for the openercloser - the classification is left intact so we still know what kind of bracket we have | ||||||||||
| 634 | SetLabel $continue; # Continue with next character | ||||||||||
| 635 | Inc r15; # Next character | ||||||||||
| 636 | }); | ||||||||||
| 637 | |||||||||||
| 638 | SetLabel $finish; | ||||||||||
| 639 | Mov rsp, rsi; # Restore stack | ||||||||||
| 640 | $$p{opens}->getReg(r11); # Number of brackets opened | ||||||||||
| 641 | PopR; | ||||||||||
| 642 | } [qw(address size fail opens)], name => q(Unisyn::Parse::MatchBrackets); | ||||||||||
| 643 | |||||||||||
| 644 | $s->call(@parameters); | ||||||||||
| 645 | } # MatchBrackets | ||||||||||
| 646 | |||||||||||
| 647 | sub ClassifyNewLines(@) #P Scan input string looking for opportunities to convert new lines into semi colons. | ||||||||||
| 648 | {my (@parameters) = @_; # Parameters | ||||||||||
| 649 | @_ >= 1 or confess; | ||||||||||
| 650 | |||||||||||
| 651 | my $s = Subroutine | ||||||||||
| 652 | {my ($p) = @_; # Parameters | ||||||||||
| 653 | my $current = r15; # Index of the current character | ||||||||||
| 654 | my $middle = r14; # Index of the middle character | ||||||||||
| 655 | my $first = r13; # Index of the first character | ||||||||||
| 656 | my $address = r12; # Address of input string | ||||||||||
| 657 | my $size = r11; # Length of input utf32 string | ||||||||||
| 658 | my($c1, $c2) = (r8."b", r9."b"); # Lexical codes being tested | ||||||||||
| 659 | |||||||||||
| 660 | PushR r8, r9, r10, r11, r12, r13, r14, r15; | ||||||||||
| 661 | |||||||||||
| 662 | $$p{address}->setReg($address); # Address of string | ||||||||||
| 663 | $$p{size} ->setReg($size); # Size of string | ||||||||||
| 664 | Mov $current, 2; Mov $middle, 1; Mov $first, 0; | ||||||||||
| 665 | |||||||||||
| 666 | For # Each character in input string | ||||||||||
| 667 | {my ($start, $end, $next) = @_; # Start, end and next labels | ||||||||||
| 668 | |||||||||||
| 669 | |||||||||||
| 670 | getLexicalCode $c1, $address, $middle; # Lexical code of the middle character | ||||||||||
| 671 | Cmp $c1, $WhiteSpace; | ||||||||||
| 672 | IfEq | ||||||||||
| 673 | Then | ||||||||||
| 674 | {getAlpha $c1, $address, $middle; | ||||||||||
| 675 | |||||||||||
| 676 | Cmp $c1, $asciiNewLine; | ||||||||||
| 677 | IfEq # Middle character is a insignificant new line and thus could be a semicolon | ||||||||||
| 678 | Then | ||||||||||
| 679 | {getLexicalCode $c1, $address, $first; | ||||||||||
| 680 | |||||||||||
| 681 | my sub makeSemiColon # Make a new line into a new line semicolon | ||||||||||
| 682 | {putLexicalCode $c2, $address, $middle, $NewLineSemiColon; | ||||||||||
| 683 | } | ||||||||||
| 684 | |||||||||||
| 685 | my sub check_bpv # Make new line if followed by 'b', 'p' or 'v' | ||||||||||
| 686 | {getLexicalCode $c1, $address, $current; | ||||||||||
| 687 | Cmp $c1, $OpenBracket; | ||||||||||
| 688 | |||||||||||
| 689 | IfEq | ||||||||||
| 690 | Then | ||||||||||
| 691 | {makeSemiColon; | ||||||||||
| 692 | }, | ||||||||||
| 693 | Else | ||||||||||
| 694 | {Cmp $c1, $prefix; | ||||||||||
| 695 | IfEq | ||||||||||
| 696 | Then | ||||||||||
| 697 | {makeSemiColon; | ||||||||||
| 698 | }, | ||||||||||
| 699 | Else | ||||||||||
| 700 | {Cmp $c1, $variable; | ||||||||||
| 701 | IfEq | ||||||||||
| 702 | Then | ||||||||||
| 703 | {makeSemiColon; | ||||||||||
| 704 | }; | ||||||||||
| 705 | }; | ||||||||||
| 706 | }; | ||||||||||
| 707 | } | ||||||||||
| 708 | |||||||||||
| 709 | Cmp $c1, $CloseBracket; # Check first character of sequence | ||||||||||
| 710 | IfEq | ||||||||||
| 711 | Then | ||||||||||
| 712 | {check_bpv; | ||||||||||
| 713 | }, | ||||||||||
| 714 | Else | ||||||||||
| 715 | {Cmp $c1, $suffix; | ||||||||||
| 716 | IfEq | ||||||||||
| 717 | Then | ||||||||||
| 718 | {check_bpv; | ||||||||||
| 719 | }, | ||||||||||
| 720 | Else | ||||||||||
| 721 | {Cmp $c1, $variable; | ||||||||||
| 722 | IfEq | ||||||||||
| 723 | Then | ||||||||||
| 724 | {check_bpv; | ||||||||||
| 725 | }; | ||||||||||
| 726 | }; | ||||||||||
| 727 | }; | ||||||||||
| 728 | }; | ||||||||||
| 729 | }; | ||||||||||
| 730 | |||||||||||
| 731 | Mov $first, $middle; Mov $middle, $current; # Find next lexical item | ||||||||||
| 732 | getLexicalCode $c1, $address, $current; # Current lexical code | ||||||||||
| 733 | Mov $middle, $current; | ||||||||||
| 734 | Inc $current; # Next possible character | ||||||||||
| 735 | For | ||||||||||
| 736 | {my ($start, $end, $next) = @_; | ||||||||||
| 737 | getLexicalCode $c2, $address, $current; # Lexical code of next character | ||||||||||
| 738 | Cmp $c1, $c2; | ||||||||||
| 739 | Jne $end; # Terminate when we are in a different lexical item | ||||||||||
| 740 | } $current, $size; | ||||||||||
| 741 | } $current, $size; | ||||||||||
| 742 | |||||||||||
| 743 | PopR; | ||||||||||
| 744 | } [qw(address size)], name => q(Unisyn::Parse::ClassifyNewLines); | ||||||||||
| 745 | |||||||||||
| 746 | $s->call(@parameters); | ||||||||||
| 747 | } # ClassifyNewLines | ||||||||||
| 748 | |||||||||||
| 749 | sub ClassifyWhiteSpace(@) #P Classify white space per: "lib/Unisyn/whiteSpace/whiteSpaceClassification.pl". | ||||||||||
| 750 | {my (@parameters) = @_; # Parameters | ||||||||||
| 751 | @_ >= 1 or confess; | ||||||||||
| 752 | |||||||||||
| 753 | my $s = Subroutine | ||||||||||
| 754 | {my ($p) = @_; # Parameters | ||||||||||
| 755 | my $eb = r15."b"; # Lexical type of current char | ||||||||||
| 756 | my $s = r14; # State of white space between 'a' | ||||||||||
| 757 | my $S = r13; # State of white space before 'a' | ||||||||||
| 758 | my $cb = r12."b"; # Actual character within alphabet | ||||||||||
| 759 | my $address = r11; # Address of input string | ||||||||||
| 760 | my $index = r10; # Index of current char | ||||||||||
| 761 | my ($w1, $w2) = (r8."b", r9."b"); # Temporary work registers | ||||||||||
| 762 | |||||||||||
| 763 | my sub getAlpha($;$) # Load the position of a lexical item in its alphabet from the current character | ||||||||||
| 764 | {my ($register, $indexReg) = @_; # Register to load, optional index register | ||||||||||
| 765 | getAlpha $register, $address, $index // $indexReg # Supplied index or default | ||||||||||
| 766 | }; | ||||||||||
| 767 | |||||||||||
| 768 | my sub getLexicalCode() # Load the lexical code of the current character in memory into the current character | ||||||||||
| 769 | {getLexicalCode $eb, $address, $index; # Supplied index or default | ||||||||||
| 770 | }; | ||||||||||
| 771 | |||||||||||
| 772 | my sub putLexicalCode($;$) # Put the specified lexical code into the current character in memory. | ||||||||||
| 773 | {my ($code, $indexReg) = @_; # Code, optional index register | ||||||||||
| 774 | putLexicalCode $w1, $address, ($indexReg//$index), $code; | ||||||||||
| 775 | }; | ||||||||||
| 776 | |||||||||||
| 777 | PushR r8, r9, r10, r11, r12, r13, r14, r15; | ||||||||||
| 778 | |||||||||||
| 779 | $$p{address}->setReg($address); # Address of string | ||||||||||
| 780 | Mov $s, -1; Mov $S, -1; Mov $index, 0; # Initial states, position | ||||||||||
| 781 | |||||||||||
| 782 | $$p{size}->for(sub # Each character in expression | ||||||||||
| 783 | {my ($indexVariable, $start, $next, $end) = @_; | ||||||||||
| 784 | |||||||||||
| 785 | $indexVariable->setReg($index); | ||||||||||
| 786 | getLexicalCode; # Current lexical code | ||||||||||
| 787 | |||||||||||
| 788 | Block # Trap space before new line and detect new line after ascii | ||||||||||
| 789 | {my ($start, $end) = @_; | ||||||||||
| 790 | Cmp $index, 0; Je $end; # Start beyond the first character so we can look back one character. | ||||||||||
| 791 | Cmp $eb, $Ascii; Jne $end; # Current is ascii | ||||||||||
| 792 | |||||||||||
| 793 | Mov $w1, "[$address+$indexScale*$index-$indexScale+$lexCodeOffset]"; # Previous lexical code | ||||||||||
| 794 | Cmp $w1, $Ascii; Jne $end; # Previous is ascii | ||||||||||
| 795 | |||||||||||
| 796 | if (1) # Check for 's' followed by 'n' and 'a' followed by 'n' | ||||||||||
| 797 | {Mov $w1, "[$address+$indexScale*$index-$indexScale]"; # Previous character | ||||||||||
| 798 | getAlpha $w2; # Current character | ||||||||||
| 799 | |||||||||||
| 800 | Cmp $w1, $asciiSpace; # Check for space followed by new line | ||||||||||
| 801 | IfEq | ||||||||||
| 802 | Then | ||||||||||
| 803 | {Cmp $w2, $asciiNewLine; | ||||||||||
| 804 | IfEq # Disallow 's' followed by 'n' | ||||||||||
| 805 | Then | ||||||||||
| 806 | {PrintErrStringNL "Space detected before new line at index:"; | ||||||||||
| 807 | PrintErrRegisterInHex $index; | ||||||||||
| 808 | PrintErrTraceBack; | ||||||||||
| 809 | Exit(1); | ||||||||||
| 810 | }; | ||||||||||
| 811 | }; | ||||||||||
| 812 | |||||||||||
| 813 | Cmp $w1, $asciiSpace; Je $end; # Check for 'a' followed by 'n' | ||||||||||
| 814 | Cmp $w1, $asciiNewLine; Je $end; # Current is 'a' but not 'n' or 's' | ||||||||||
| 815 | Cmp $w2, $asciiNewLine; Jne $end; # Current is 'n' | ||||||||||
| 816 | |||||||||||
| 817 | putLexicalCode $WhiteSpace; # Mark new line as significant | ||||||||||
| 818 | } | ||||||||||
| 819 | }; | ||||||||||
| 820 | |||||||||||
| 821 | Block # Spaces and new lines between other ascii | ||||||||||
| 822 | {my ($start, $end) = @_; | ||||||||||
| 823 | Cmp $s, -1; | ||||||||||
| 824 | IfEq # Looking for opening ascii | ||||||||||
| 825 | Then | ||||||||||
| 826 | {Cmp $eb, $Ascii; Jne $end; # Not ascii | ||||||||||
| 827 | getAlpha $cb; # Current character | ||||||||||
| 828 | Cmp $cb, $asciiNewLine; Je $end; # Skip over new lines | ||||||||||
| 829 | Cmp $cb, $asciiSpace; Je $end; # Skip over spaces | ||||||||||
| 830 | IfEq | ||||||||||
| 831 | Then | ||||||||||
| 832 | {Mov $s, $index; Inc $s; # Ascii not space nor new line | ||||||||||
| 833 | }; | ||||||||||
| 834 | Jmp $end; | ||||||||||
| 835 | }, | ||||||||||
| 836 | Else # Looking for closing ascii | ||||||||||
| 837 | {Cmp $eb, $Ascii; | ||||||||||
| 838 | IfNe # Not ascii | ||||||||||
| 839 | Then | ||||||||||
| 840 | {Mov $s, -1; | ||||||||||
| 841 | Jmp $end | ||||||||||
| 842 | }; | ||||||||||
| 843 | getAlpha $cb; # Current character | ||||||||||
| 844 | Cmp $cb, $asciiNewLine; Je $end; # Skip over new lines | ||||||||||
| 845 | Cmp $cb, $asciiSpace; Je $end; # Skip over spaces | ||||||||||
| 846 | |||||||||||
| 847 | For # Move over spaces and new lines between two ascii characters that are neither of new line or space | ||||||||||
| 848 | {my ($start, $end, $next) = @_; | ||||||||||
| 849 | getAlpha $cb, $s; # Check for 's' or 'n' | ||||||||||
| 850 | Cmp $cb, $asciiSpace; | ||||||||||
| 851 | IfEq | ||||||||||
| 852 | Then | ||||||||||
| 853 | {putLexicalCode $WhiteSpace, $s; # Mark as significant white space. | ||||||||||
| 854 | Jmp $next; | ||||||||||
| 855 | }; | ||||||||||
| 856 | Cmp $cb, $asciiNewLine; | ||||||||||
| 857 | IfEq | ||||||||||
| 858 | Then | ||||||||||
| 859 | {putLexicalCode $WhiteSpace; # Mark as significant new line | ||||||||||
| 860 | Jmp $next; | ||||||||||
| 861 | }; | ||||||||||
| 862 | } $s, $index; | ||||||||||
| 863 | |||||||||||
| 864 | Mov $s, $index; Inc $s; | ||||||||||
| 865 | }; | ||||||||||
| 866 | }; | ||||||||||
| 867 | |||||||||||
| 868 | Block # Note: 's' preceding 'a' are significant | ||||||||||
| 869 | {my ($start, $end) = @_; | ||||||||||
| 870 | Cmp $S, -1; | ||||||||||
| 871 | IfEq # Looking for 's' | ||||||||||
| 872 | Then | ||||||||||
| 873 | {Cmp $eb, $Ascii; # Not 'a' | ||||||||||
| 874 | IfNe | ||||||||||
| 875 | Then | ||||||||||
| 876 | {Mov $S, -1; | ||||||||||
| 877 | Jmp $end | ||||||||||
| 878 | }; | ||||||||||
| 879 | getAlpha $cb; # Actual character in alphabet | ||||||||||
| 880 | Cmp $cb, $asciiSpace; # Space | ||||||||||
| 881 | IfEq | ||||||||||
| 882 | Then | ||||||||||
| 883 | {Mov $S, $index; | ||||||||||
| 884 | Jmp $end; | ||||||||||
| 885 | }; | ||||||||||
| 886 | }, | ||||||||||
| 887 | Else # Looking for 'a' | ||||||||||
| 888 | {Cmp $eb, $Ascii; # Not 'a' | ||||||||||
| 889 | IfNe | ||||||||||
| 890 | Then | ||||||||||
| 891 | {Mov $S, -1; | ||||||||||
| 892 | Jmp $end | ||||||||||
| 893 | }; | ||||||||||
| 894 | getAlpha $cb; # Actual character in alphabet | ||||||||||
| 895 | Cmp $cb, $asciiSpace; Je $end; # Skip 's' | ||||||||||
| 896 | |||||||||||
| 897 | Cmp $cb, $asciiNewLine; | ||||||||||
| 898 | IfEq # New lines prevent 's' from preceding 'a' | ||||||||||
| 899 | Then | ||||||||||
| 900 | {Mov $s, -1; | ||||||||||
| 901 | Jmp $end | ||||||||||
| 902 | }; | ||||||||||
| 903 | |||||||||||
| 904 | For # Move over spaces to non space ascii | ||||||||||
| 905 | {my ($start, $end, $next) = @_; | ||||||||||
| 906 | putLexicalCode $WhiteSpace, $S; # Mark new line as significant | ||||||||||
| 907 | } $S, $index; | ||||||||||
| 908 | Mov $S, -1; # Look for next possible space | ||||||||||
| 909 | } | ||||||||||
| 910 | }; | ||||||||||
| 911 | }); | ||||||||||
| 912 | |||||||||||
| 913 | $$p{size}->for(sub # Invert white space so that significant white space becomes ascii and the remainder is ignored | ||||||||||
| 914 | {my ($indexVariable, $start, $next, $end) = @_; | ||||||||||
| 915 | |||||||||||
| 916 | $indexVariable->setReg($index); | ||||||||||
| 917 | getLexicalCode; # Current lexical code | ||||||||||
| 918 | |||||||||||
| 919 | Block # Invert non significant white space | ||||||||||
| 920 | {my ($start, $end) = @_; | ||||||||||
| 921 | Cmp $eb, $Ascii; | ||||||||||
| 922 | Jne $end; # Ascii | ||||||||||
| 923 | |||||||||||
| 924 | getAlpha $cb; # Actual character in alphabet | ||||||||||
| 925 | Cmp $cb, $asciiSpace; | ||||||||||
| 926 | IfEq | ||||||||||
| 927 | Then | ||||||||||
| 928 | {putLexicalCode $WhiteSpace; | ||||||||||
| 929 | Jmp $next; | ||||||||||
| 930 | }; | ||||||||||
| 931 | Cmp $cb, $asciiNewLine; | ||||||||||
| 932 | IfEq | ||||||||||
| 933 | Then | ||||||||||
| 934 | {putLexicalCode $WhiteSpace; # Mark new line as not significant | ||||||||||
| 935 | Jmp $next; | ||||||||||
| 936 | }; | ||||||||||
| 937 | }; | ||||||||||
| 938 | |||||||||||
| 939 | Block # Mark significant white space | ||||||||||
| 940 | {my ($start, $end) = @_; | ||||||||||
| 941 | Cmp $eb, $WhiteSpace; Jne $end; # Not significant white space | ||||||||||
| 942 | putLexicalCode $Ascii; # Mark as ascii | ||||||||||
| 943 | }; | ||||||||||
| 944 | }); | ||||||||||
| 945 | |||||||||||
| 946 | PopR; | ||||||||||
| 947 | } [qw(address size)], name => q(Unisyn::Parse::ClassifyWhiteSpace); | ||||||||||
| 948 | |||||||||||
| 949 | $s->call(@parameters); | ||||||||||
| 950 | } # ClassifyWhiteSpace | ||||||||||
| 951 | |||||||||||
| 952 | sub parseUtf8($@) #P Parse a unisyn expression encoded as utf8 and return the parse tree. | ||||||||||
| 953 | {my ($p, @parameters) = @_; # Parse, parameters | ||||||||||
| 954 | @_ >= 1 or confess; | ||||||||||
| 955 | |||||||||||
| 956 | my $s = Subroutine | ||||||||||
| 957 | {my ($p) = @_; # Parameters | ||||||||||
| 958 | |||||||||||
| 959 | PrintOutStringNL "ParseUtf8" if $debug; | ||||||||||
| 960 | |||||||||||
| 961 | PushR $arenaReg; PushZmm 0..1; # Used to hold arena and classifiers | ||||||||||
| 962 | |||||||||||
| 963 | my $source32 = $$p{source32}; | ||||||||||
| 964 | my $sourceSize32 = $$p{sourceSize32}; | ||||||||||
| 965 | my $sourceLength32 = $$p{sourceLength32}; | ||||||||||
| 966 | |||||||||||
| 967 | ConvertUtf8ToUtf32 u8 => $$p{address}, size8 => $$p{size}, # Convert to utf32 | ||||||||||
| 968 | u32 => $source32, size32 => $sourceSize32, | ||||||||||
| 969 | count => $sourceLength32; | ||||||||||
| 970 | |||||||||||
| 971 | if ($debug) | ||||||||||
| 972 | {PrintOutStringNL "After conversion from utf8 to utf32"; | ||||||||||
| 973 | $sourceSize32 ->outNL("Output Length: "); # Write output length | ||||||||||
| 974 | PrintUtf32($sourceLength32, $source32); # Print utf32 | ||||||||||
| 975 | } | ||||||||||
| 976 | |||||||||||
| 977 | Vmovdqu8 zmm0, "[".Rd(join ', ', $Lex->{lexicalLow} ->@*)."]"; # Each double is [31::24] Classification, [21::0] Utf32 start character | ||||||||||
| 978 | Vmovdqu8 zmm1, "[".Rd(join ', ', $Lex->{lexicalHigh}->@*)."]"; # Each double is [31::24] Range offset, [21::0] Utf32 end character | ||||||||||
| 979 | |||||||||||
| 980 | ClassifyWithInRangeAndSaveOffset address=>$source32, size=>$sourceLength32; # Alphabetic classification | ||||||||||
| 981 | if ($debug) | ||||||||||
| 982 | {PrintOutStringNL "After classification into alphabet ranges"; | ||||||||||
| 983 | PrintUtf32($sourceLength32, $source32); # Print classified utf32 | ||||||||||
| 984 | } | ||||||||||
| 985 | |||||||||||
| 986 | Vmovdqu8 zmm0, "[".Rd(join ', ', $Lex->{bracketsLow} ->@*)."]"; # Each double is [31::24] Classification, [21::0] Utf32 start character | ||||||||||
| 987 | Vmovdqu8 zmm1, "[".Rd(join ', ', $Lex->{bracketsHigh}->@*)."]"; # Each double is [31::24] Range offset, [21::0] Utf32 end character | ||||||||||
| 988 | |||||||||||
| 989 | ClassifyWithInRange address=>$source32, size=>$sourceLength32; # Bracket classification | ||||||||||
| 990 | if ($debug) | ||||||||||
| 991 | {PrintOutStringNL "After classification into brackets"; | ||||||||||
| 992 | PrintUtf32($sourceLength32, $source32); # Print classified brackets | ||||||||||
| 993 | } | ||||||||||
| 994 | |||||||||||
| 995 | my $opens = V(opens, -1); | ||||||||||
| 996 | MatchBrackets address=>$source32, size=>$sourceLength32, $opens, $$p{fail}; # Match brackets | ||||||||||
| 997 | if ($debug) | ||||||||||
| 998 | {PrintOutStringNL "After bracket matching"; | ||||||||||
| 999 | PrintUtf32($sourceLength32, $source32); # Print matched brackets | ||||||||||
| 1000 | } | ||||||||||
| 1001 | |||||||||||
| 1002 | ClassifyWhiteSpace address=>$source32, size=>$sourceLength32; # Classify white space | ||||||||||
| 1003 | if ($debug) | ||||||||||
| 1004 | {PrintOutStringNL "After white space classification"; | ||||||||||
| 1005 | PrintUtf32($sourceLength32, $source32); | ||||||||||
| 1006 | } | ||||||||||
| 1007 | |||||||||||
| 1008 | ClassifyNewLines address=>$source32, size=>$sourceLength32; # Classify new lines | ||||||||||
| 1009 | if ($debug) | ||||||||||
| 1010 | {PrintOutStringNL "After classifying new lines"; | ||||||||||
| 1011 | PrintUtf32($sourceLength32, $source32); | ||||||||||
| 1012 | } | ||||||||||
| 1013 | |||||||||||
| 1014 | $$p{arena}->setReg($arenaReg); # Rather than passing the arena as a parameter to all the parsing routines we put it in rax and access it from there when needed | ||||||||||
| 1015 | parseExpression source=>$source32, size=>$sourceLength32, $$p{parse}; | ||||||||||
| 1016 | |||||||||||
| 1017 | $$p{parse}->outNL if $debug; | ||||||||||
| 1018 | |||||||||||
| 1019 | PopZmm; PopR; | ||||||||||
| 1020 | } [qw(arena address size parse fail source32 sourceSize32 sourceLength32)], | ||||||||||
| 1021 | name => q(Unisyn::Parse::parseUtf8); | ||||||||||
| 1022 | |||||||||||
| 1023 | $s->call(arena => $p->arena->bs, | ||||||||||
| 1024 | address => $p->address8, | ||||||||||
| 1025 | size => $p->size8, | ||||||||||
| 1026 | source32 => $p->source32, | ||||||||||
| 1027 | sourceSize32 => $p->sourceSize32, | ||||||||||
| 1028 | sourceLength32 => $p->sourceLength32, | ||||||||||
| 1029 | parse => $p->parse, | ||||||||||
| 1030 | fail => $p->fails); | ||||||||||
| 1031 | } # parseUtf8 | ||||||||||
| 1032 | |||||||||||
| 1033 | #D1 Print # Print a parse tree | ||||||||||
| 1034 | |||||||||||
| 1035 | sub printLexicalItem($$$) # Print the utf8 string corresponding to a lexical item at a variable offset | ||||||||||
| 1036 | {my ($parse, $source32, $offset) = @_; # Parse tree, variable address of utf32 source representation, variable offset to lexical item in utf32 | ||||||||||
| 1037 | my $t = $parse->arena->DescribeTree; | ||||||||||
| 1038 | |||||||||||
| 1039 | my $s = Subroutine | ||||||||||
| 1040 | {my ($p, $s) = @_; # Parameters | ||||||||||
| 1041 | PushR zmm0, zmm1, rax, r14, r15; | ||||||||||
| 1042 | my $success = Label; | ||||||||||
| 1043 | |||||||||||
| 1044 | $$p{source32}->setReg(r14); | ||||||||||
| 1045 | $$p{offset}->setReg(r15); | ||||||||||
| 1046 | Vmovdqu8 zmm0, "[r14+4*r15]"; | ||||||||||
| 1047 | |||||||||||
| 1048 | Pextrw rax, xmm0, 1; # Extract lexical type of first element | ||||||||||
| 1049 | Vpbroadcastw zmm1, ax; # Broadcast | ||||||||||
| 1050 | Vpcmpeqw k0, zmm0, zmm1; # Check extent of first lexical item up to 16 | ||||||||||
| 1051 | Shr rax, 8; # Lexical type in lowest byte | ||||||||||
| 1052 | |||||||||||
| 1053 | Mov r15, 0x55555555; # Set odd positions to one where we know the match will fail | ||||||||||
| 1054 | Kmovq k1, r15; | ||||||||||
| 1055 | Korq k2, k0, k1; # Fill in odd positions | ||||||||||
| 1056 | |||||||||||
| 1057 | Kmovq r15, k2; | ||||||||||
| 1058 | Not r15; # Swap zeroes and ones | ||||||||||
| 1059 | Tzcnt r14, r15; # Trailing zero count is a factor two too big | ||||||||||
| 1060 | Shr r14, 1; # Normalized count of number of characters int name | ||||||||||
| 1061 | |||||||||||
| 1062 | Mov r15, 0xffff; # Zero out lexical type | ||||||||||
| 1063 | Vpbroadcastd zmm1, r15d; # Broadcast | ||||||||||
| 1064 | Vpandd zmm1, zmm0, zmm1; # Remove lexical type to leave index into alphabet | ||||||||||
| 1065 | |||||||||||
| 1066 | Cmp rax, $variable; # Test for variable | ||||||||||
| 1067 | IfEq | ||||||||||
| 1068 | Then | ||||||||||
| 1069 | {my $a = Rutf8 "\x{1D5D4}\x{1D5D5}\x{1D5D6}\x{1D5D7}\x{1D5D8}\x{1D5D9}\x{1D5DA}\x{1D5DB}\x{1D5DC}\x{1D5DD}\x{1D5DE}\x{1D5DF}\x{1D5E0}\x{1D5E1}\x{1D5E2}\x{1D5E3}\x{1D5E4}\x{1D5E5}\x{1D5E6}\x{1D5E7}\x{1D5E8}\x{1D5E9}\x{1D5EA}\x{1D5EB}\x{1D5EC}\x{1D5ED}\x{1D5EE}\x{1D5EF}\x{1D5F0}\x{1D5F1}\x{1D5F2}\x{1D5F3}\x{1D5F4}\x{1D5F5}\x{1D5F6}\x{1D5F7}\x{1D5F8}\x{1D5F9}\x{1D5FA}\x{1D5FB}\x{1D5FC}\x{1D5FD}\x{1D5FE}\x{1D5FF}\x{1D600}\x{1D601}\x{1D602}\x{1D603}\x{1D604}\x{1D605}\x{1D606}\x{1D607}\x{1D756}\x{1D757}\x{1D758}\x{1D759}\x{1D75A}\x{1D75B}\x{1D75C}\x{1D75D}\x{1D75E}\x{1D75F}\x{1D760}\x{1D761}\x{1D762}\x{1D763}\x{1D764}\x{1D765}\x{1D766}\x{1D767}\x{1D768}\x{1D769}\x{1D76A}\x{1D76B}\x{1D76C}\x{1D76D}\x{1D76E}\x{1D76F}\x{1D770}\x{1D771}\x{1D772}\x{1D773}\x{1D774}\x{1D775}\x{1D776}\x{1D777}\x{1D778}\x{1D779}\x{1D77A}\x{1D77B}\x{1D77C}\x{1D77D}\x{1D77E}\x{1D77F}\x{1D780}\x{1D781}\x{1D782}\x{1D783}\x{1D784}\x{1D785}\x{1D786}\x{1D787}\x{1D788}\x{1D789}\x{1D78A}\x{1D78B}\x{1D78C}\x{1D78D}\x{1D78E}\x{1D78F}"; | ||||||||||
| 1070 | PushR zmm1; | ||||||||||
| 1071 | V(loop)->getReg(r14)->for(sub # Write each letter out from its position on the stack | ||||||||||
| 1072 | {my ($index, $start, $next, $end) = @_; # Execute body | ||||||||||
| 1073 | $index->setReg(r14); # Index stack | ||||||||||
| 1074 | ClearRegisters r15; | ||||||||||
| 1075 | Mov r15b, "[rsp+4*r14]"; # Load alphabet offset from stack | ||||||||||
| 1076 | Shl r15, 2; # Each letter is 4 bytes wide in utf8 | ||||||||||
| 1077 | Mov r14, $a; # Alphabet address | ||||||||||
| 1078 | Mov r14d, "[r14+r15]"; # Alphabet letter as utf8 | ||||||||||
| 1079 | PushR r14; # utf8 is on the stack and it is 4 bytes wide | ||||||||||
| 1080 | Mov rax, rsp; | ||||||||||
| 1081 | Mov rdi, 4; | ||||||||||
| 1082 | PrintOutMemory; # Print letter from stack | ||||||||||
| 1083 | PopR; | ||||||||||
| 1084 | }); | ||||||||||
| 1085 | Jmp $success; | ||||||||||
| 1086 | }; | ||||||||||
| 1087 | |||||||||||
| 1088 | Cmp rax, $assign; # Test for operator | ||||||||||
| 1089 | IfEq | ||||||||||
| 1090 | Then | ||||||||||
| 1091 | {my $va = Rutf8 "\x{1D434}\x{1D435}\x{1D436}\x{1D437}\x{1D438}\x{1D439}\x{1D43A}\x{1D43B}\x{1D43C}\x{1D43D}\x{1D43E}\x{1D43F}\x{1D440}\x{1D441}\x{1D442}\x{1D443}\x{1D444}\x{1D445}\x{1D446}\x{1D447}\x{1D448}\x{1D449}\x{1D44A}\x{1D44B}\x{1D44C}\x{1D44D}\x{1D44E}\x{1D44F}\x{1D450}\x{1D451}\x{1D452}\x{1D453}\x{1D454}\x{1D456}\x{1D457}\x{1D458}\x{1D459}\x{1D45A}\x{1D45B}\x{1D45C}\x{1D45D}\x{1D45E}\x{1D45F}\x{1D460}\x{1D461}\x{1D462}\x{1D463}\x{1D464}\x{1D465}\x{1D466}\x{1D467}\x{1D6E2}\x{1D6E3}\x{1D6E4}\x{1D6E5}\x{1D6E6}\x{1D6E7}\x{1D6E8}\x{1D6E9}\x{1D6EA}\x{1D6EB}\x{1D6EC}\x{1D6ED}\x{1D6EE}\x{1D6EF}\x{1D6F0}\x{1D6F1}\x{1D6F2}\x{1D6F3}\x{1D6F4}\x{1D6F5}\x{1D6F6}\x{1D6F7}\x{1D6F8}\x{1D6F9}\x{1D6FA}\x{1D6FB}\x{1D6FC}\x{1D6FD}\x{1D6FE}\x{1D6FF}\x{1D700}\x{1D701}\x{1D702}\x{1D703}\x{1D704}\x{1D705}\x{1D706}\x{1D707}\x{1D708}\x{1D709}\x{1D70A}\x{1D70B}\x{1D70C}\x{1D70D}\x{1D70E}\x{1D70F}\x{1D710}\x{1D711}\x{1D712}\x{1D713}\x{1D714}\x{1D715}\x{1D716}\x{1D717}\x{1D718}\x{1D719}\x{1D71A}\x{1D71B}"; | ||||||||||
| 1092 | PushR zmm1; | ||||||||||
| 1093 | V(loop)->getReg(r14)->for(sub # Write each letter out from its position on the stack | ||||||||||
| 1094 | {my ($index, $start, $next, $end) = @_; # Execute body | ||||||||||
| 1095 | $index->setReg(r14); # Index stack | ||||||||||
| 1096 | ClearRegisters r15; | ||||||||||
| 1097 | Mov r15b, "[rsp+4*r14]"; # Load alphabet offset from stack | ||||||||||
| 1098 | Shl r15, 2; # Each letter is 4 bytes wide in utf8 | ||||||||||
| 1099 | Mov r14, $va; # Alphabet address | ||||||||||
| 1100 | Mov r14d, "[r14+r15]"; # Alphabet letter as utf8 | ||||||||||
| 1101 | PushR r14; # utf8 is on the stack and it is 4 bytes wide | ||||||||||
| 1102 | Mov rax, rsp; | ||||||||||
| 1103 | Mov rdi, 4; | ||||||||||
| 1104 | PrintOutMemory; # Print letter from stack | ||||||||||
| 1105 | PopR; | ||||||||||
| 1106 | Jmp $success; | ||||||||||
| 1107 | }); | ||||||||||
| 1108 | }; | ||||||||||
| 1109 | |||||||||||
| 1110 | SetLabel $success; | ||||||||||
| 1111 | PopR; | ||||||||||
| 1112 | } [qw(offset source32)], | ||||||||||
| 1113 | name => q(Unisyn::Parse::printLexicalItem); | ||||||||||
| 1114 | |||||||||||
| 1115 | $s->call(offset => $offset, source32 => $source32); | ||||||||||
| 1116 | } | ||||||||||
| 1117 | |||||||||||
| 1118 | sub print($) # Create a parser for an expression described by variables. | ||||||||||
| 1119 | {my ($parse) = @_; # Parse tree | ||||||||||
| 1120 | my $t = $parse->arena->DescribeTree; | ||||||||||
| 1121 | |||||||||||
| 1122 | PushR my ($depthR) = (r12); # Recursion depth | ||||||||||
| 1123 | |||||||||||
| 1124 | my $b = Subroutine # Print the spacing blanks to offset sub trees | ||||||||||
| 1125 | {V(loop, $depthR)->for(sub | ||||||||||
| 1126 | {PrintOutString " "; | ||||||||||
| 1127 | }); | ||||||||||
| 1128 | } [], name => "Nasm::X86::Tree::dump::spaces"; | ||||||||||
| 1129 | |||||||||||
| 1130 | my $s = Subroutine # Print a tree | ||||||||||
| 1131 | {my ($p, $s) = @_; # Parameters, sub definition | ||||||||||
| 1132 | |||||||||||
| 1133 | my $B = $$p{bs}; | ||||||||||
| 1134 | |||||||||||
| 1135 | $t->address->copy($$p{bs}); | ||||||||||
| 1136 | $t->first ->copy($$p{first}); | ||||||||||
| 1137 | $t->find(K(key, 0)); # Key 0 tells us the type of the element - normally a term | ||||||||||
| 1138 | |||||||||||
| 1139 | If ($t->found == 0, # Not found key 0 | ||||||||||
| 1140 | Then | ||||||||||
| 1141 | {PrintOutString "No type for node"; | ||||||||||
| 1142 | Exit(1); | ||||||||||
| 1143 | }); | ||||||||||
| 1144 | |||||||||||
| 1145 | If ($t->data != $term, # Expected a term | ||||||||||
| 1146 | Then | ||||||||||
| 1147 | {PrintOutString "Expected a term"; | ||||||||||
| 1148 | Exit(1); | ||||||||||
| 1149 | }); | ||||||||||
| 1150 | |||||||||||
| 1151 | my $operands = V(operands); # Number of operands | ||||||||||
| 1152 | $t->find(K(key, 1)); # Key 1 tells us the number of operands | ||||||||||
| 1153 | If ($t->found > 0, # Found key 1 | ||||||||||
| 1154 | Then | ||||||||||
| 1155 | {$operands->copy($t->data); # Number of operands | ||||||||||
| 1156 | }, | ||||||||||
| 1157 | Else | ||||||||||
| 1158 | {PrintOutString "Expected at least one operand"; | ||||||||||
| 1159 | Exit(1); | ||||||||||
| 1160 | }); | ||||||||||
| 1161 | |||||||||||
| 1162 | $operands->for(sub # Each operand | ||||||||||
| 1163 | {my ($index, $start, $next, $end) = @_; # Execute body | ||||||||||
| 1164 | my $i = 2 + $index * 2; my $j = $i + 1; # Operand type and value | ||||||||||
| 1165 | $t->find($i); my $key = V(key) ->copy($t->data); | ||||||||||
| 1166 | $t->find($j); my $data = V(data)->copy($t->data); | ||||||||||
| 1167 | |||||||||||
| 1168 | If ($key == $term, # Term | ||||||||||
| 1169 | Then | ||||||||||
| 1170 | {$b->call; | ||||||||||
| 1171 | PrintOutStringNL "Term"; | ||||||||||
| 1172 | Inc $depthR; # Increase indentation for sub terms | ||||||||||
| 1173 | $s->call($B, first => $data, $$p{source32}); # Print sub tree referenced by data field | ||||||||||
| 1174 | Dec $depthR; # Restore existing indentation | ||||||||||
| 1175 | $t->first ->copy($$p{first}); # Re-establish addressability to the tree after the recursive call | ||||||||||
| 1176 | }); | ||||||||||
| 1177 | |||||||||||
| 1178 | If ($key == $variable, # Variable | ||||||||||
| 1179 | Then | ||||||||||
| 1180 | {$b->call; | ||||||||||
| 1181 | PrintOutString "Variable: "; | ||||||||||
| 1182 | $parse->printLexicalItem($$p{source32}, $data); # Print the variable name | ||||||||||
| 1183 | PrintOutNL; | ||||||||||
| 1184 | }); | ||||||||||
| 1185 | |||||||||||
| 1186 | If ($key == $assign, # Assign | ||||||||||
| 1187 | Then | ||||||||||
| 1188 | {$b->call; | ||||||||||
| 1189 | PrintOutString "Assign: "; | ||||||||||
| 1190 | $parse->printLexicalItem($$p{source32}, $data); # Print the variable name | ||||||||||
| 1191 | PrintOutNL; | ||||||||||
| 1192 | }); | ||||||||||
| 1193 | |||||||||||
| 1194 | If ($index == 0, # Operator followed by indented operands | ||||||||||
| 1195 | Then | ||||||||||
| 1196 | {Inc $depthR; | ||||||||||
| 1197 | }); | ||||||||||
| 1198 | }); | ||||||||||
| 1199 | |||||||||||
| 1200 | Dec $depthR; # Reset indentation after operands | ||||||||||
| 1201 | } [qw(bs first source32)], name => "Nasm::X86::Tree::print"; | ||||||||||
| 1202 | |||||||||||
| 1203 | ClearRegisters $depthR; # Depth starts at zero | ||||||||||
| 1204 | |||||||||||
| 1205 | $s->call($parse->arena->bs, first => $parse->parse, $parse->source32); | ||||||||||
| 1206 | |||||||||||
| 1207 | PopR; | ||||||||||
| 1208 | |||||||||||
| 1209 | |||||||||||
| 1210 | #d | ||||||||||
| 1211 | sub lexicalData {do { | ||||||||||
| 1212 | my $a = bless({ | ||||||||||
| 1213 | alphabetRanges => 13, | ||||||||||
| 1214 | alphabets => { | ||||||||||
| 1215 | "circledLatinLetter" => "\x{24B6}\x{24B7}\x{24B8}\x{24B9}\x{24BA}\x{24BB}\x{24BC}\x{24BD}\x{24BE}\x{24BF}\x{24C0}\x{24C1}\x{24C2}\x{24C3}\x{24C4}\x{24C5}\x{24C6}\x{24C7}\x{24C8}\x{24C9}\x{24CA}\x{24CB}\x{24CC}\x{24CD}\x{24CE}\x{24CF}\x{24D0}\x{24D1}\x{24D2}\x{24D3}\x{24D4}\x{24D5}\x{24D6}\x{24D7}\x{24D8}\x{24D9}\x{24DA}\x{24DB}\x{24DC}\x{24DD}\x{24DE}\x{24DF}\x{24E0}\x{24E1}\x{24E2}\x{24E3}\x{24E4}\x{24E5}\x{24E6}\x{24E7}\x{24E8}\x{24E9}", | ||||||||||
| 1216 | "mathematicalBold" => "\x{1D400}\x{1D401}\x{1D402}\x{1D403}\x{1D404}\x{1D405}\x{1D406}\x{1D407}\x{1D408}\x{1D409}\x{1D40A}\x{1D40B}\x{1D40C}\x{1D40D}\x{1D40E}\x{1D40F}\x{1D410}\x{1D411}\x{1D412}\x{1D413}\x{1D414}\x{1D415}\x{1D416}\x{1D417}\x{1D418}\x{1D419}\x{1D41A}\x{1D41B}\x{1D41C}\x{1D41D}\x{1D41E}\x{1D41F}\x{1D420}\x{1D421}\x{1D422}\x{1D423}\x{1D424}\x{1D425}\x{1D426}\x{1D427}\x{1D428}\x{1D429}\x{1D42A}\x{1D42B}\x{1D42C}\x{1D42D}\x{1D42E}\x{1D42F}\x{1D430}\x{1D431}\x{1D432}\x{1D433}\x{1D6A8}\x{1D6A9}\x{1D6AA}\x{1D6AB}\x{1D6AC}\x{1D6AD}\x{1D6AE}\x{1D6AF}\x{1D6B0}\x{1D6B1}\x{1D6B2}\x{1D6B3}\x{1D6B4}\x{1D6B5}\x{1D6B6}\x{1D6B7}\x{1D6B8}\x{1D6B9}\x{1D6BA}\x{1D6BB}\x{1D6BC}\x{1D6BD}\x{1D6BE}\x{1D6BF}\x{1D6C0}\x{1D6C1}\x{1D6C2}\x{1D6C3}\x{1D6C4}\x{1D6C5}\x{1D6C6}\x{1D6C7}\x{1D6C8}\x{1D6C9}\x{1D6CA}\x{1D6CB}\x{1D6CC}\x{1D6CD}\x{1D6CE}\x{1D6CF}\x{1D6D0}\x{1D6D1}\x{1D6D2}\x{1D6D3}\x{1D6D4}\x{1D6D5}\x{1D6D6}\x{1D6D7}\x{1D6D8}\x{1D6D9}\x{1D6DA}\x{1D6DB}\x{1D6DC}\x{1D6DD}\x{1D6DE}\x{1D6DF}\x{1D6E0}\x{1D6E1}", | ||||||||||
| 1217 | "mathematicalBoldFraktur" => "\x{1D56C}\x{1D56D}\x{1D56E}\x{1D56F}\x{1D570}\x{1D571}\x{1D572}\x{1D573}\x{1D574}\x{1D575}\x{1D576}\x{1D577}\x{1D578}\x{1D579}\x{1D57A}\x{1D57B}\x{1D57C}\x{1D57D}\x{1D57E}\x{1D57F}\x{1D580}\x{1D581}\x{1D582}\x{1D583}\x{1D584}\x{1D585}\x{1D586}\x{1D587}\x{1D588}\x{1D589}\x{1D58A}\x{1D58B}\x{1D58C}\x{1D58D}\x{1D58E}\x{1D58F}\x{1D590}\x{1D591}\x{1D592}\x{1D593}\x{1D594}\x{1D595}\x{1D596}\x{1D597}\x{1D598}\x{1D599}\x{1D59A}\x{1D59B}\x{1D59C}\x{1D59D}\x{1D59E}\x{1D59F}", | ||||||||||
| 1218 | "mathematicalBoldItalic" => "\x{1D468}\x{1D469}\x{1D46A}\x{1D46B}\x{1D46C}\x{1D46D}\x{1D46E}\x{1D46F}\x{1D470}\x{1D471}\x{1D472}\x{1D473}\x{1D474}\x{1D475}\x{1D476}\x{1D477}\x{1D478}\x{1D479}\x{1D47A}\x{1D47B}\x{1D47C}\x{1D47D}\x{1D47E}\x{1D47F}\x{1D480}\x{1D481}\x{1D482}\x{1D483}\x{1D484}\x{1D485}\x{1D486}\x{1D487}\x{1D488}\x{1D489}\x{1D48A}\x{1D48B}\x{1D48C}\x{1D48D}\x{1D48E}\x{1D48F}\x{1D490}\x{1D491}\x{1D492}\x{1D493}\x{1D494}\x{1D495}\x{1D496}\x{1D497}\x{1D498}\x{1D499}\x{1D49A}\x{1D49B}\x{1D71C}\x{1D71D}\x{1D71E}\x{1D71F}\x{1D720}\x{1D721}\x{1D722}\x{1D723}\x{1D724}\x{1D725}\x{1D726}\x{1D727}\x{1D728}\x{1D729}\x{1D72A}\x{1D72B}\x{1D72C}\x{1D72D}\x{1D72E}\x{1D72F}\x{1D730}\x{1D731}\x{1D732}\x{1D733}\x{1D734}\x{1D735}\x{1D736}\x{1D737}\x{1D738}\x{1D739}\x{1D73A}\x{1D73B}\x{1D73C}\x{1D73D}\x{1D73E}\x{1D73F}\x{1D740}\x{1D741}\x{1D742}\x{1D743}\x{1D744}\x{1D745}\x{1D746}\x{1D747}\x{1D748}\x{1D749}\x{1D74A}\x{1D74B}\x{1D74C}\x{1D74D}\x{1D74E}\x{1D74F}\x{1D750}\x{1D751}\x{1D752}\x{1D753}\x{1D754}\x{1D755}", | ||||||||||
| 1219 | "mathematicalBoldScript" => "\x{1D4D0}\x{1D4D1}\x{1D4D2}\x{1D4D3}\x{1D4D4}\x{1D4D5}\x{1D4D6}\x{1D4D7}\x{1D4D8}\x{1D4D9}\x{1D4DA}\x{1D4DB}\x{1D4DC}\x{1D4DD}\x{1D4DE}\x{1D4DF}\x{1D4E0}\x{1D4E1}\x{1D4E2}\x{1D4E3}\x{1D4E4}\x{1D4E5}\x{1D4E6}\x{1D4E7}\x{1D4E8}\x{1D4E9}\x{1D4EA}\x{1D4EB}\x{1D4EC}\x{1D4ED}\x{1D4EE}\x{1D4EF}\x{1D4F0}\x{1D4F1}\x{1D4F2}\x{1D4F3}\x{1D4F4}\x{1D4F5}\x{1D4F6}\x{1D4F7}\x{1D4F8}\x{1D4F9}\x{1D4FA}\x{1D4FB}\x{1D4FC}\x{1D4FD}\x{1D4FE}\x{1D4FF}\x{1D500}\x{1D501}\x{1D502}\x{1D503}", | ||||||||||
| 1220 | "mathematicalDouble-struck" => "\x{1D538}\x{1D539}\x{1D53B}\x{1D53C}\x{1D53D}\x{1D53E}\x{1D540}\x{1D541}\x{1D542}\x{1D543}\x{1D544}\x{1D546}\x{1D54A}\x{1D54B}\x{1D54C}\x{1D54D}\x{1D54E}\x{1D54F}\x{1D550}\x{1D552}\x{1D553}\x{1D554}\x{1D555}\x{1D556}\x{1D557}\x{1D558}\x{1D559}\x{1D55A}\x{1D55B}\x{1D55C}\x{1D55D}\x{1D55E}\x{1D55F}\x{1D560}\x{1D561}\x{1D562}\x{1D563}\x{1D564}\x{1D565}\x{1D566}\x{1D567}\x{1D568}\x{1D569}\x{1D56A}\x{1D56B}", | ||||||||||
| 1221 | "mathematicalFraktur" => "\x{1D504}\x{1D505}\x{1D507}\x{1D508}\x{1D509}\x{1D50A}\x{1D50D}\x{1D50E}\x{1D50F}\x{1D510}\x{1D511}\x{1D512}\x{1D513}\x{1D514}\x{1D516}\x{1D517}\x{1D518}\x{1D519}\x{1D51A}\x{1D51B}\x{1D51C}\x{1D51E}\x{1D51F}\x{1D520}\x{1D521}\x{1D522}\x{1D523}\x{1D524}\x{1D525}\x{1D526}\x{1D527}\x{1D528}\x{1D529}\x{1D52A}\x{1D52B}\x{1D52C}\x{1D52D}\x{1D52E}\x{1D52F}\x{1D530}\x{1D531}\x{1D532}\x{1D533}\x{1D534}\x{1D535}\x{1D536}\x{1D537}", | ||||||||||
| 1222 | "mathematicalItalic" => "\x{1D434}\x{1D435}\x{1D436}\x{1D437}\x{1D438}\x{1D439}\x{1D43A}\x{1D43B}\x{1D43C}\x{1D43D}\x{1D43E}\x{1D43F}\x{1D440}\x{1D441}\x{1D442}\x{1D443}\x{1D444}\x{1D445}\x{1D446}\x{1D447}\x{1D448}\x{1D449}\x{1D44A}\x{1D44B}\x{1D44C}\x{1D44D}\x{1D44E}\x{1D44F}\x{1D450}\x{1D451}\x{1D452}\x{1D453}\x{1D454}\x{1D456}\x{1D457}\x{1D458}\x{1D459}\x{1D45A}\x{1D45B}\x{1D45C}\x{1D45D}\x{1D45E}\x{1D45F}\x{1D460}\x{1D461}\x{1D462}\x{1D463}\x{1D464}\x{1D465}\x{1D466}\x{1D467}\x{1D6E2}\x{1D6E3}\x{1D6E4}\x{1D6E5}\x{1D6E6}\x{1D6E7}\x{1D6E8}\x{1D6E9}\x{1D6EA}\x{1D6EB}\x{1D6EC}\x{1D6ED}\x{1D6EE}\x{1D6EF}\x{1D6F0}\x{1D6F1}\x{1D6F2}\x{1D6F3}\x{1D6F4}\x{1D6F5}\x{1D6F6}\x{1D6F7}\x{1D6F8}\x{1D6F9}\x{1D6FA}\x{1D6FB}\x{1D6FC}\x{1D6FD}\x{1D6FE}\x{1D6FF}\x{1D700}\x{1D701}\x{1D702}\x{1D703}\x{1D704}\x{1D705}\x{1D706}\x{1D707}\x{1D708}\x{1D709}\x{1D70A}\x{1D70B}\x{1D70C}\x{1D70D}\x{1D70E}\x{1D70F}\x{1D710}\x{1D711}\x{1D712}\x{1D713}\x{1D714}\x{1D715}\x{1D716}\x{1D717}\x{1D718}\x{1D719}\x{1D71A}\x{1D71B}", | ||||||||||
| 1223 | "mathematicalMonospace" => "\x{1D670}\x{1D671}\x{1D672}\x{1D673}\x{1D674}\x{1D675}\x{1D676}\x{1D677}\x{1D678}\x{1D679}\x{1D67A}\x{1D67B}\x{1D67C}\x{1D67D}\x{1D67E}\x{1D67F}\x{1D680}\x{1D681}\x{1D682}\x{1D683}\x{1D684}\x{1D685}\x{1D686}\x{1D687}\x{1D688}\x{1D689}\x{1D68A}\x{1D68B}\x{1D68C}\x{1D68D}\x{1D68E}\x{1D68F}\x{1D690}\x{1D691}\x{1D692}\x{1D693}\x{1D694}\x{1D695}\x{1D696}\x{1D697}\x{1D698}\x{1D699}\x{1D69A}\x{1D69B}\x{1D69C}\x{1D69D}\x{1D69E}\x{1D69F}\x{1D6A0}\x{1D6A1}\x{1D6A2}\x{1D6A3}", | ||||||||||
| 1224 | "mathematicalSans-serif" => "\x{1D5A0}\x{1D5A1}\x{1D5A2}\x{1D5A3}\x{1D5A4}\x{1D5A5}\x{1D5A6}\x{1D5A7}\x{1D5A8}\x{1D5A9}\x{1D5AA}\x{1D5AB}\x{1D5AC}\x{1D5AD}\x{1D5AE}\x{1D5AF}\x{1D5B0}\x{1D5B1}\x{1D5B2}\x{1D5B3}\x{1D5B4}\x{1D5B5}\x{1D5B6}\x{1D5B7}\x{1D5B8}\x{1D5B9}\x{1D5BA}\x{1D5BB}\x{1D5BC}\x{1D5BD}\x{1D5BE}\x{1D5BF}\x{1D5C0}\x{1D5C1}\x{1D5C2}\x{1D5C3}\x{1D5C4}\x{1D5C5}\x{1D5C6}\x{1D5C7}\x{1D5C8}\x{1D5C9}\x{1D5CA}\x{1D5CB}\x{1D5CC}\x{1D5CD}\x{1D5CE}\x{1D5CF}\x{1D5D0}\x{1D5D1}\x{1D5D2}\x{1D5D3}", | ||||||||||
| 1225 | "mathematicalSans-serifBold" => "\x{1D5D4}\x{1D5D5}\x{1D5D6}\x{1D5D7}\x{1D5D8}\x{1D5D9}\x{1D5DA}\x{1D5DB}\x{1D5DC}\x{1D5DD}\x{1D5DE}\x{1D5DF}\x{1D5E0}\x{1D5E1}\x{1D5E2}\x{1D5E3}\x{1D5E4}\x{1D5E5}\x{1D5E6}\x{1D5E7}\x{1D5E8}\x{1D5E9}\x{1D5EA}\x{1D5EB}\x{1D5EC}\x{1D5ED}\x{1D5EE}\x{1D5EF}\x{1D5F0}\x{1D5F1}\x{1D5F2}\x{1D5F3}\x{1D5F4}\x{1D5F5}\x{1D5F6}\x{1D5F7}\x{1D5F8}\x{1D5F9}\x{1D5FA}\x{1D5FB}\x{1D5FC}\x{1D5FD}\x{1D5FE}\x{1D5FF}\x{1D600}\x{1D601}\x{1D602}\x{1D603}\x{1D604}\x{1D605}\x{1D606}\x{1D607}\x{1D756}\x{1D757}\x{1D758}\x{1D759}\x{1D75A}\x{1D75B}\x{1D75C}\x{1D75D}\x{1D75E}\x{1D75F}\x{1D760}\x{1D761}\x{1D762}\x{1D763}\x{1D764}\x{1D765}\x{1D766}\x{1D767}\x{1D768}\x{1D769}\x{1D76A}\x{1D76B}\x{1D76C}\x{1D76D}\x{1D76E}\x{1D76F}\x{1D770}\x{1D771}\x{1D772}\x{1D773}\x{1D774}\x{1D775}\x{1D776}\x{1D777}\x{1D778}\x{1D779}\x{1D77A}\x{1D77B}\x{1D77C}\x{1D77D}\x{1D77E}\x{1D77F}\x{1D780}\x{1D781}\x{1D782}\x{1D783}\x{1D784}\x{1D785}\x{1D786}\x{1D787}\x{1D788}\x{1D789}\x{1D78A}\x{1D78B}\x{1D78C}\x{1D78D}\x{1D78E}\x{1D78F}", | ||||||||||
| 1226 | "mathematicalSans-serifBoldItalic" => "\x{1D63C}\x{1D63D}\x{1D63E}\x{1D63F}\x{1D640}\x{1D641}\x{1D642}\x{1D643}\x{1D644}\x{1D645}\x{1D646}\x{1D647}\x{1D648}\x{1D649}\x{1D64A}\x{1D64B}\x{1D64C}\x{1D64D}\x{1D64E}\x{1D64F}\x{1D650}\x{1D651}\x{1D652}\x{1D653}\x{1D654}\x{1D655}\x{1D656}\x{1D657}\x{1D658}\x{1D659}\x{1D65A}\x{1D65B}\x{1D65C}\x{1D65D}\x{1D65E}\x{1D65F}\x{1D660}\x{1D661}\x{1D662}\x{1D663}\x{1D664}\x{1D665}\x{1D666}\x{1D667}\x{1D668}\x{1D669}\x{1D66A}\x{1D66B}\x{1D66C}\x{1D66D}\x{1D66E}\x{1D66F}\x{1D790}\x{1D791}\x{1D792}\x{1D793}\x{1D794}\x{1D795}\x{1D796}\x{1D797}\x{1D798}\x{1D799}\x{1D79A}\x{1D79B}\x{1D79C}\x{1D79D}\x{1D79E}\x{1D79F}\x{1D7A0}\x{1D7A1}\x{1D7A2}\x{1D7A3}\x{1D7A4}\x{1D7A5}\x{1D7A6}\x{1D7A7}\x{1D7A8}\x{1D7A9}\x{1D7AA}\x{1D7AB}\x{1D7AC}\x{1D7AD}\x{1D7AE}\x{1D7AF}\x{1D7B0}\x{1D7B1}\x{1D7B2}\x{1D7B3}\x{1D7B4}\x{1D7B5}\x{1D7B6}\x{1D7B7}\x{1D7B8}\x{1D7B9}\x{1D7BA}\x{1D7BB}\x{1D7BC}\x{1D7BD}\x{1D7BE}\x{1D7BF}\x{1D7C0}\x{1D7C1}\x{1D7C2}\x{1D7C3}\x{1D7C4}\x{1D7C5}\x{1D7C6}\x{1D7C7}\x{1D7C8}\x{1D7C9}", | ||||||||||
| 1227 | "mathematicalSans-serifItalic" => "\x{1D608}\x{1D609}\x{1D60A}\x{1D60B}\x{1D60C}\x{1D60D}\x{1D60E}\x{1D60F}\x{1D610}\x{1D611}\x{1D612}\x{1D613}\x{1D614}\x{1D615}\x{1D616}\x{1D617}\x{1D618}\x{1D619}\x{1D61A}\x{1D61B}\x{1D61C}\x{1D61D}\x{1D61E}\x{1D61F}\x{1D620}\x{1D621}\x{1D622}\x{1D623}\x{1D624}\x{1D625}\x{1D626}\x{1D627}\x{1D628}\x{1D629}\x{1D62A}\x{1D62B}\x{1D62C}\x{1D62D}\x{1D62E}\x{1D62F}\x{1D630}\x{1D631}\x{1D632}\x{1D633}\x{1D634}\x{1D635}\x{1D636}\x{1D637}\x{1D638}\x{1D639}\x{1D63A}\x{1D63B}", | ||||||||||
| 1228 | "mathematicalScript" => "\x{1D49C}\x{1D49E}\x{1D49F}\x{1D4A2}\x{1D4A5}\x{1D4A6}\x{1D4A9}\x{1D4AA}\x{1D4AB}\x{1D4AC}\x{1D4AE}\x{1D4AF}\x{1D4B0}\x{1D4B1}\x{1D4B2}\x{1D4B3}\x{1D4B4}\x{1D4B5}\x{1D4B6}\x{1D4B7}\x{1D4B8}\x{1D4B9}\x{1D4BB}\x{1D4BD}\x{1D4BE}\x{1D4BF}\x{1D4C0}\x{1D4C1}\x{1D4C2}\x{1D4C3}\x{1D4C5}\x{1D4C6}\x{1D4C7}\x{1D4C8}\x{1D4C9}\x{1D4CA}\x{1D4CB}\x{1D4CC}\x{1D4CD}\x{1D4CE}\x{1D4CF}", | ||||||||||
| 1229 | "negativeCircledLatinLetter" => "\x{1F150}\x{1F151}\x{1F152}\x{1F153}\x{1F154}\x{1F155}\x{1F156}\x{1F157}\x{1F158}\x{1F159}\x{1F15A}\x{1F15B}\x{1F15C}\x{1F15D}\x{1F15E}\x{1F15F}\x{1F160}\x{1F161}\x{1F162}\x{1F163}\x{1F164}\x{1F165}\x{1F166}\x{1F167}\x{1F168}\x{1F169}", | ||||||||||
| 1230 | "negativeSquaredLatinLetter" => "\x{1F170}\x{1F171}\x{1F172}\x{1F173}\x{1F174}\x{1F175}\x{1F176}\x{1F177}\x{1F178}\x{1F179}\x{1F17A}\x{1F17B}\x{1F17C}\x{1F17D}\x{1F17E}\x{1F17F}\x{1F180}\x{1F181}\x{1F182}\x{1F183}\x{1F184}\x{1F185}\x{1F186}\x{1F187}\x{1F188}\x{1F189}", | ||||||||||
| 1231 | "semiColon" => "\x{27E2}", | ||||||||||
| 1232 | "squaredLatinLetter" => "\x{1F130}\x{1F131}\x{1F132}\x{1F133}\x{1F134}\x{1F135}\x{1F136}\x{1F137}\x{1F138}\x{1F139}\x{1F13A}\x{1F13B}\x{1F13C}\x{1F13D}\x{1F13E}\x{1F13F}\x{1F140}\x{1F141}\x{1F142}\x{1F143}\x{1F144}\x{1F145}\x{1F146}\x{1F147}\x{1F148}\x{1F149}\x{1F1A5}", | ||||||||||
| 1233 | }, | ||||||||||
| 1234 | brackets => 16, | ||||||||||
| 1235 | bracketsBase => 16, | ||||||||||
| 1236 | bracketsClose => [ | ||||||||||
| 1237 | "\x{2309}", | ||||||||||
| 1238 | "\x{230B}", | ||||||||||
| 1239 | "\x{232A}", | ||||||||||
| 1240 | "\x{2769}", | ||||||||||
| 1241 | "\x{276B}", | ||||||||||
| 1242 | "\x{276D}", | ||||||||||
| 1243 | "\x{276F}", | ||||||||||
| 1244 | "\x{2771}", | ||||||||||
| 1245 | "\x{2773}", | ||||||||||
| 1246 | "\x{2775}", | ||||||||||
| 1247 | "\x{27E7}", | ||||||||||
| 1248 | "\x{27E9}", | ||||||||||
| 1249 | "\x{27EB}", | ||||||||||
| 1250 | "\x{27ED}", | ||||||||||
| 1251 | "\x{27EF}", | ||||||||||
| 1252 | "\x{2984}", | ||||||||||
| 1253 | "\x{2986}", | ||||||||||
| 1254 | "\x{2988}", | ||||||||||
| 1255 | "\x{298A}", | ||||||||||
| 1256 | "\x{298C}", | ||||||||||
| 1257 | "\x{298E}", | ||||||||||
| 1258 | "\x{2990}", | ||||||||||
| 1259 | "\x{2992}", | ||||||||||
| 1260 | "\x{2994}", | ||||||||||
| 1261 | "\x{2996}", | ||||||||||
| 1262 | "\x{2998}", | ||||||||||
| 1263 | "\x{29FD}", | ||||||||||
| 1264 | "\x{2E29}", | ||||||||||
| 1265 | "\x{3009}", | ||||||||||
| 1266 | "\x{300B}", | ||||||||||
| 1267 | "\x{3011}", | ||||||||||
| 1268 | "\x{3015}", | ||||||||||
| 1269 | "\x{3017}", | ||||||||||
| 1270 | "\x{3019}", | ||||||||||
| 1271 | "\x{301B}", | ||||||||||
| 1272 | "\x{FD3F}", | ||||||||||
| 1273 | "\x{FF09}", | ||||||||||
| 1274 | "\x{FF60}", | ||||||||||
| 1275 | ], | ||||||||||
| 1276 | bracketsHigh => [ | ||||||||||
| 1277 | "0x1300230b", | ||||||||||
| 1278 | "0x1500232a", | ||||||||||
| 1279 | "0x23002775", | ||||||||||
| 1280 | "0x2d0027ef", | ||||||||||
| 1281 | "0x43002998", | ||||||||||
| 1282 | "0x450029fd", | ||||||||||
| 1283 | "0x47002e29", | ||||||||||
| 1284 | "0x4b00300b", | ||||||||||
| 1285 | "0x4d003011", | ||||||||||
| 1286 | "0x5500301b", | ||||||||||
| 1287 | "0x5700fd3f", | ||||||||||
| 1288 | "0x5900ff09", | ||||||||||
| 1289 | "0x5b00ff60", | ||||||||||
| 1290 | 0, | ||||||||||
| 1291 | 0, | ||||||||||
| 1292 | 0, | ||||||||||
| 1293 | ], | ||||||||||
| 1294 | bracketsLow => [ | ||||||||||
| 1295 | "0x10002308", | ||||||||||
| 1296 | "0x14002329", | ||||||||||
| 1297 | "0x16002768", | ||||||||||
| 1298 | "0x240027e6", | ||||||||||
| 1299 | "0x2e002983", | ||||||||||
| 1300 | "0x440029fc", | ||||||||||
| 1301 | "0x46002e28", | ||||||||||
| 1302 | "0x48003008", | ||||||||||
| 1303 | "0x4c003010", | ||||||||||
| 1304 | "0x4e003014", | ||||||||||
| 1305 | "0x5600fd3e", | ||||||||||
| 1306 | "0x5800ff08", | ||||||||||
| 1307 | "0x5a00ff5f", | ||||||||||
| 1308 | 0, | ||||||||||
| 1309 | 0, | ||||||||||
| 1310 | 0, | ||||||||||
| 1311 | ], | ||||||||||
| 1312 | bracketsOpen => [ | ||||||||||
| 1313 | "\x{2308}", | ||||||||||
| 1314 | "\x{230A}", | ||||||||||
| 1315 | "\x{2329}", | ||||||||||
| 1316 | "\x{2768}", | ||||||||||
| 1317 | "\x{276A}", | ||||||||||
| 1318 | "\x{276C}", | ||||||||||
| 1319 | "\x{276E}", | ||||||||||
| 1320 | "\x{2770}", | ||||||||||
| 1321 | "\x{2772}", | ||||||||||
| 1322 | "\x{2774}", | ||||||||||
| 1323 | "\x{27E6}", | ||||||||||
| 1324 | "\x{27E8}", | ||||||||||
| 1325 | "\x{27EA}", | ||||||||||
| 1326 | "\x{27EC}", | ||||||||||
| 1327 | "\x{27EE}", | ||||||||||
| 1328 | "\x{2983}", | ||||||||||
| 1329 | "\x{2985}", | ||||||||||
| 1330 | "\x{2987}", | ||||||||||
| 1331 | "\x{2989}", | ||||||||||
| 1332 | "\x{298B}", | ||||||||||
| 1333 | "\x{298D}", | ||||||||||
| 1334 | "\x{298F}", | ||||||||||
| 1335 | "\x{2991}", | ||||||||||
| 1336 | "\x{2993}", | ||||||||||
| 1337 | "\x{2995}", | ||||||||||
| 1338 | "\x{2997}", | ||||||||||
| 1339 | "\x{29FC}", | ||||||||||
| 1340 | "\x{2E28}", | ||||||||||
| 1341 | "\x{3008}", | ||||||||||
| 1342 | "\x{300A}", | ||||||||||
| 1343 | "\x{3010}", | ||||||||||
| 1344 | "\x{3014}", | ||||||||||
| 1345 | "\x{3016}", | ||||||||||
| 1346 | "\x{3018}", | ||||||||||
| 1347 | "\x{301A}", | ||||||||||
| 1348 | "\x{FD3E}", | ||||||||||
| 1349 | "\x{FF08}", | ||||||||||
| 1350 | "\x{FF5F}", | ||||||||||
| 1351 | ], | ||||||||||
| 1352 | lexicalAlpha => { | ||||||||||
| 1353 | "" => [ | ||||||||||
| 1354 | "circledLatinLetter", | ||||||||||
| 1355 | "mathematicalBoldFraktur", | ||||||||||
| 1356 | "mathematicalBoldScript", | ||||||||||
| 1357 | "mathematicalDouble-struck", | ||||||||||
| 1358 | "mathematicalFraktur", | ||||||||||
| 1359 | "mathematicalMonospace", | ||||||||||
| 1360 | "mathematicalSans-serif", | ||||||||||
| 1361 | "mathematicalSans-serifItalic", | ||||||||||
| 1362 | "mathematicalScript", | ||||||||||
| 1363 | "negativeSquaredLatinLetter", | ||||||||||
| 1364 | "semiColon", | ||||||||||
| 1365 | "squaredLatinLetter", | ||||||||||
| 1366 | ], | ||||||||||
| 1367 | "Ascii" => ["negativeCircledLatinLetter"], | ||||||||||
| 1368 | "assign" => ["mathematicalItalic"], | ||||||||||
| 1369 | "CloseBracket" => [], | ||||||||||
| 1370 | "dyad" => ["mathematicalBold"], | ||||||||||
| 1371 | "OpenBracket" => [], | ||||||||||
| 1372 | "prefix" => ["mathematicalBoldItalic"], | ||||||||||
| 1373 | "semiColon" => [], | ||||||||||
| 1374 | "suffix" => ["mathematicalSans-serifBoldItalic"], | ||||||||||
| 1375 | "term" => [], | ||||||||||
| 1376 | "variable" => ["mathematicalSans-serifBold"], | ||||||||||
| 1377 | }, | ||||||||||
| 1378 | lexicalHigh => [ | ||||||||||
| 1379 | 127, | ||||||||||
| 1380 | 10210, | ||||||||||
| 1381 | 119859, | ||||||||||
| 1382 | 119911, | ||||||||||
| 1383 | 119963, | ||||||||||
| 1384 | 120327, | ||||||||||
| 1385 | 120431, | ||||||||||
| 1386 | 872535777, | ||||||||||
| 1387 | 872535835, | ||||||||||
| 1388 | 872535893, | ||||||||||
| 1389 | 872535951, | ||||||||||
| 1390 | 872536009, | ||||||||||
| 1391 | 2147610985, | ||||||||||
| 1392 | 0, | ||||||||||
| 1393 | 0, | ||||||||||
| 1394 | 0, | ||||||||||
| 1395 | ], | ||||||||||
| 1396 | lexicalLow => [ | ||||||||||
| 1397 | 33554432, | ||||||||||
| 1398 | 134227938, | ||||||||||
| 1399 | 50451456, | ||||||||||
| 1400 | 84005940, | ||||||||||
| 1401 | 67228776, | ||||||||||
| 1402 | 100783572, | ||||||||||
| 1403 | 117560892, | ||||||||||
| 1404 | 50452136, | ||||||||||
| 1405 | 84006626, | ||||||||||
| 1406 | 67229468, | ||||||||||
| 1407 | 100783958, | ||||||||||
| 1408 | 117561232, | ||||||||||
| 1409 | 33681744, | ||||||||||
| 1410 | 0, | ||||||||||
| 1411 | 0, | ||||||||||
| 1412 | 0, | ||||||||||
| 1413 | ], | ||||||||||
| 1414 | lexicals => bless({ | ||||||||||
| 1415 | Ascii => bless({ letter => "a", like => "v", name => "Ascii", number => 2 }, "Unisyn::Parse::Lexical::Constant"), | ||||||||||
| 1416 | assign => bless({ letter => "a", like => "a", name => "assign", number => 5 }, "Unisyn::Parse::Lexical::Constant"), | ||||||||||
| 1417 | CloseBracket => bless({ letter => "B", like => "B", name => "CloseBracket", number => 1 }, "Unisyn::Parse::Lexical::Constant"), | ||||||||||
| 1418 | dyad => bless({ letter => "d", like => "d", name => "dyad", number => 3 }, "Unisyn::Parse::Lexical::Constant"), | ||||||||||
| 1419 | empty => bless({ letter => "e", like => "e", name => "empty", number => 10 }, "Unisyn::Parse::Lexical::Constant"), | ||||||||||
| 1420 | NewLineSemiColon => bless({ letter => "N", like => undef, name => "NewLineSemiColon", number => 12 }, "Unisyn::Parse::Lexical::Constant"), | ||||||||||
| 1421 | OpenBracket => bless({ letter => "b", like => "b", name => "OpenBracket", number => 0 }, "Unisyn::Parse::Lexical::Constant"), | ||||||||||
| 1422 | prefix => bless({ letter => "p", like => "p", name => "prefix", number => 4 }, "Unisyn::Parse::Lexical::Constant"), | ||||||||||
| 1423 | semiColon => bless({ letter => "s", like => "s", name => "semiColon", number => 8 }, "Unisyn::Parse::Lexical::Constant"), | ||||||||||
| 1424 | suffix => bless({ letter => "q", like => "q", name => "suffix", number => 7 }, "Unisyn::Parse::Lexical::Constant"), | ||||||||||
| 1425 | term => bless({ letter => "t", like => "t", name => "term", number => 9 }, "Unisyn::Parse::Lexical::Constant"), | ||||||||||
| 1426 | variable => bless({ letter => "v", like => "v", name => "variable", number => 6 }, "Unisyn::Parse::Lexical::Constant"), | ||||||||||
| 1427 | WhiteSpace => bless({ letter => "W", like => undef, name => "WhiteSpace", number => 11 }, "Unisyn::Parse::Lexical::Constant"), | ||||||||||
| 1428 | }, "Unisyn::Parse::Lexicals"), | ||||||||||
| 1429 | sampleLexicals => { | ||||||||||
| 1430 | brackets => [ | ||||||||||
| 1431 | 100663296, | ||||||||||
| 1432 | 83886080, | ||||||||||
| 1433 | 0, | ||||||||||
| 1434 | 0, | ||||||||||
| 1435 | 0, | ||||||||||
| 1436 | 100663296, | ||||||||||
| 1437 | 16777216, | ||||||||||
| 1438 | 16777216, | ||||||||||
| 1439 | 50331648, | ||||||||||
| 1440 | 0, | ||||||||||
| 1441 | 100663296, | ||||||||||
| 1442 | 16777216, | ||||||||||
| 1443 | 16777216, | ||||||||||
| 1444 | 134217728, | ||||||||||
| 1445 | ], | ||||||||||
| 1446 | nosemi => [ | ||||||||||
| 1447 | 100663296, | ||||||||||
| 1448 | 83886080, | ||||||||||
| 1449 | 0, | ||||||||||
| 1450 | 0, | ||||||||||
| 1451 | 0, | ||||||||||
| 1452 | 100663296, | ||||||||||
| 1453 | 16777216, | ||||||||||
| 1454 | 16777216, | ||||||||||
| 1455 | 50331648, | ||||||||||
| 1456 | 0, | ||||||||||
| 1457 | 100663296, | ||||||||||
| 1458 | 16777216, | ||||||||||
| 1459 | 16777216, | ||||||||||
| 1460 | ], | ||||||||||
| 1461 | s1 => [ | ||||||||||
| 1462 | 100663296, | ||||||||||
| 1463 | 83886080, | ||||||||||
| 1464 | 33554442, | ||||||||||
| 1465 | 33554464, | ||||||||||
| 1466 | 33554464, | ||||||||||
| 1467 | 33554497, | ||||||||||
| 1468 | 33554442, | ||||||||||
| 1469 | 33554464, | ||||||||||
| 1470 | 33554464, | ||||||||||
| 1471 | 33554464, | ||||||||||
| 1472 | ], | ||||||||||
| 1473 | v => [100663296], | ||||||||||
| 1474 | vav => [100663296, 83886080, 100663296], | ||||||||||
| 1475 | vnsvs => [ | ||||||||||
| 1476 | 100663296, | ||||||||||
| 1477 | 33554442, | ||||||||||
| 1478 | 33554464, | ||||||||||
| 1479 | 33554464, | ||||||||||
| 1480 | 33554464, | ||||||||||
| 1481 | 100663296, | ||||||||||
| 1482 | 33554464, | ||||||||||
| 1483 | 33554464, | ||||||||||
| 1484 | 33554464, | ||||||||||
| 1485 | ], | ||||||||||
| 1486 | vnv => [100663296, 33554442, 100663296], | ||||||||||
| 1487 | vnvs => [ | ||||||||||
| 1488 | 100663296, | ||||||||||
| 1489 | 33554442, | ||||||||||
| 1490 | 100663296, | ||||||||||
| 1491 | 33554464, | ||||||||||
| 1492 | 33554464, | ||||||||||
| 1493 | 33554464, | ||||||||||
| 1494 | 33554464, | ||||||||||
| 1495 | ], | ||||||||||
| 1496 | ws => [ | ||||||||||
| 1497 | 100663296, | ||||||||||
| 1498 | 83886080, | ||||||||||
| 1499 | 0, | ||||||||||
| 1500 | 0, | ||||||||||
| 1501 | 0, | ||||||||||
| 1502 | 100663296, | ||||||||||
| 1503 | 16777216, | ||||||||||
| 1504 | 16777216, | ||||||||||
| 1505 | 50331648, | ||||||||||
| 1506 | 0, | ||||||||||
| 1507 | 100663296, | ||||||||||
| 1508 | 16777216, | ||||||||||
| 1509 | 16777216, | ||||||||||
| 1510 | 134217728, | ||||||||||
| 1511 | 100663296, | ||||||||||
| 1512 | 83886080, | ||||||||||
| 1513 | 33554497, | ||||||||||
| 1514 | 50331648, | ||||||||||
| 1515 | 100663296, | ||||||||||
| 1516 | 134217728, | ||||||||||
| 1517 | ], | ||||||||||
| 1518 | }, | ||||||||||
| 1519 | sampleText => { | ||||||||||
| 1520 | brackets => "\x{1D5EE}\x{1D44E}\x{1D460}\x{1D460}\x{1D456}\x{1D454}\x{1D45B}\x{230A}\x{2329}\x{2768}\x{1D5EF}\x{1D5FD}\x{2769}\x{232A}\x{1D429}\x{1D425}\x{1D42E}\x{1D42C}\x{276A}\x{1D600}\x{1D5F0}\x{276B}\x{230B}\x{27E2}", | ||||||||||
| 1521 | nosemi => "\x{1D5EE}\x{1D44E}\x{1D460}\x{1D460}\x{1D456}\x{1D454}\x{1D45B}\x{230A}\x{2329}\x{2768}\x{1D5EF}\x{1D5FD}\x{2769}\x{232A}\x{1D429}\x{1D425}\x{1D42E}\x{1D42C}\x{276A}\x{1D600}\x{1D5F0}\x{276B}\x{230B}", | ||||||||||
| 1522 | s1 => "\x{1D5EE}\x{1D44E}\n A\n ", | ||||||||||
| 1523 | v => "\x{1D5EE}", | ||||||||||
| 1524 | vav => "\x{1D5EE}\x{1D44E}\x{1D5EF}", | ||||||||||
| 1525 | vnsvs => "\x{1D5EE}\x{1D5EE}\n \x{1D5EF}\x{1D5EF} ", | ||||||||||
| 1526 | vnv => "\x{1D5EE}\n\x{1D5EF}", | ||||||||||
| 1527 | vnvs => "\x{1D5EE}\n\x{1D5EF} ", | ||||||||||
| 1528 | ws => "\x{1D5EE}\x{1D44E}\x{1D460}\x{1D460}\x{1D456}\x{1D454}\x{1D45B}\x{230A}\x{2329}\x{2768}\x{1D5EF}\x{1D5FD}\x{2769}\x{232A}\x{1D429}\x{1D425}\x{1D42E}\x{1D42C}\x{276A}\x{1D600}\x{1D5F0}\x{276B}\x{230B}\x{27E2}\x{1D5EE}\x{1D5EE}\x{1D44E}\x{1D460}\x{1D460}\x{1D456}\x{1D454}\x{1D45B}A\x{1D429}\x{1D425}\x{1D42E}\x{1D42C}\x{1D5F0}\x{1D5F0}\x{27E2}", | ||||||||||
| 1529 | }, | ||||||||||
| 1530 | semiColon => "\x{27E2}", | ||||||||||
| 1531 | separator => "\x{205F}", | ||||||||||
| 1532 | structure => bless({ | ||||||||||
| 1533 | codes => bless({ | ||||||||||
| 1534 | a => bless({ | ||||||||||
| 1535 | letter => "a", | ||||||||||
| 1536 | name => "assignment operator", | ||||||||||
| 1537 | next => "bpv", | ||||||||||
| 1538 | short => "assign", | ||||||||||
| 1539 | }, "Tree::Term::LexicalCode"), | ||||||||||
| 1540 | B => bless({ | ||||||||||
| 1541 | letter => "B", | ||||||||||
| 1542 | name => "closing parenthesis", | ||||||||||
| 1543 | next => "aBdqs", | ||||||||||
| 1544 | short => "CloseBracket", | ||||||||||
| 1545 | }, "Tree::Term::LexicalCode"), | ||||||||||
| 1546 | b => bless({ | ||||||||||
| 1547 | letter => "b", | ||||||||||
| 1548 | name => "opening parenthesis", | ||||||||||
| 1549 | next => "bBpsv", | ||||||||||
| 1550 | short => "OpenBracket", | ||||||||||
| 1551 | }, "Tree::Term::LexicalCode"), | ||||||||||
| 1552 | d => bless({ letter => "d", name => "dyadic operator", next => "bpv", short => "dyad" }, "Tree::Term::LexicalCode"), | ||||||||||
| 1553 | p => bless({ letter => "p", name => "prefix operator", next => "bpv", short => "prefix" }, "Tree::Term::LexicalCode"), | ||||||||||
| 1554 | q => bless({ | ||||||||||
| 1555 | letter => "q", | ||||||||||
| 1556 | name => "suffix operator", | ||||||||||
| 1557 | next => "aBdqs", | ||||||||||
| 1558 | short => "suffix", | ||||||||||
| 1559 | }, "Tree::Term::LexicalCode"), | ||||||||||
| 1560 | s => bless({ letter => "s", name => "semi-colon", next => "bBpsv", short => "semiColon" }, "Tree::Term::LexicalCode"), | ||||||||||
| 1561 | t => bless({ letter => "t", name => "term", next => "aBdqs", short => "term" }, "Tree::Term::LexicalCode"), | ||||||||||
| 1562 | v => bless({ letter => "v", name => "variable", next => "aBdqs", short => "variable" }, "Tree::Term::LexicalCode"), | ||||||||||
| 1563 | }, "Tree::Term::Codes"), | ||||||||||
| 1564 | first => "bpsv", | ||||||||||
| 1565 | last => "Bqsv", | ||||||||||
| 1566 | }, "Tree::Term::LexicalStructure"), | ||||||||||
| 1567 | treeTermLexicals => 'fix', | ||||||||||
| 1568 | }, "Unisyn::Parse::Lexical::Tables"); | ||||||||||
| 1569 | $a->{treeTermLexicals} = $a->{structure}{codes}; | ||||||||||
| 1570 | $a; | ||||||||||
| 1571 | }} | ||||||||||
| 1572 | |||||||||||
| 1573 | #------------------------------------------------------------------------------- | ||||||||||
| 1574 | # Export - eeee | ||||||||||
| 1575 | #------------------------------------------------------------------------------- | ||||||||||
| 1576 | |||||||||||
| 1577 | use Exporter qw(import); | ||||||||||
| 1578 | |||||||||||
| 1579 | use vars qw(@ISA @EXPORT @EXPORT_OK %EXPORT_TAGS); | ||||||||||
| 1580 | |||||||||||
| 1581 | @ISA = qw(Exporter); | ||||||||||
| 1582 | @EXPORT = qw(); | ||||||||||
| 1583 | @EXPORT_OK = qw(); | ||||||||||
| 1584 | %EXPORT_TAGS = (all => [@EXPORT, @EXPORT_OK]); | ||||||||||
| 1585 | |||||||||||
| 1586 | # podDocumentation | ||||||||||
| 1587 | =pod | ||||||||||
| 1588 | |||||||||||
| 1589 | =encoding utf-8 | ||||||||||
| 1590 | |||||||||||
| 1591 | =head1 Name | ||||||||||
| 1592 | |||||||||||
| 1593 | Unisyn::Parse - Parse a Unisyn expression. | ||||||||||
| 1594 | |||||||||||
| 1595 | =head1 Synopsis | ||||||||||
| 1596 | |||||||||||
| 1597 | Parse the Unisyn expression: | ||||||||||
| 1598 | |||||||||||
| 1599 | 𝗮𝑎𝗯 | ||||||||||
| 1600 | |||||||||||
| 1601 | which assigns B<b> to B<a>. Parse this expression and print the resulting parse | ||||||||||
| 1602 | tree: | ||||||||||
| 1603 | |||||||||||
| 1604 | my $address = Rutf8 $Lex->{sampleText}{vav}; # Source in utf8 | ||||||||||
| 1605 | my $size = StringLength V(string, $address); # Length of source | ||||||||||
| 1606 | |||||||||||
| 1607 | my $parse = create K(address, $address), $size; # Create parse tree from source | ||||||||||
| 1608 | $parse->print; # Print parse tree | ||||||||||
| 1609 | |||||||||||
| 1610 | |||||||||||
| 1611 | To get: | ||||||||||
| 1612 | |||||||||||
| 1613 | ok Assemble(debug=>0, eq => <<END); # Assemble and run | ||||||||||
| 1614 | Assign: 𝑎 | ||||||||||
| 1615 | Term | ||||||||||
| 1616 | Variable: 𝗮 | ||||||||||
| 1617 | Term | ||||||||||
| 1618 | Variable: 𝗯 | ||||||||||
| 1619 | END | ||||||||||
| 1620 | |||||||||||
| 1621 | =head1 Description | ||||||||||
| 1622 | |||||||||||
| 1623 | Parse a Unisyn expression. | ||||||||||
| 1624 | |||||||||||
| 1625 | |||||||||||
| 1626 | Version "20210818". | ||||||||||
| 1627 | |||||||||||
| 1628 | |||||||||||
| 1629 | The following sections describe the methods in each functional area of this | ||||||||||
| 1630 | module. For an alphabetic listing of all methods by name see L<Index|/Index>. | ||||||||||
| 1631 | |||||||||||
| 1632 | |||||||||||
| 1633 | |||||||||||
| 1634 | =head1 Create | ||||||||||
| 1635 | |||||||||||
| 1636 | Create a Unisyn parse of a utf8 string. | ||||||||||
| 1637 | |||||||||||
| 1638 | =head2 create($address, $size) | ||||||||||
| 1639 | |||||||||||
| 1640 | Create a new unisyn parse from a utf8 string | ||||||||||
| 1641 | |||||||||||
| 1642 | Parameter Description | ||||||||||
| 1643 | 1 $address Address of utf8 source string to parse as a variable | ||||||||||
| 1644 | 2 $size Length of string as a variable | ||||||||||
| 1645 | |||||||||||
| 1646 | B<Example:> | ||||||||||
| 1647 | |||||||||||
| 1648 | |||||||||||
| 1649 | my $address = Rutf8 $Lex->{sampleText}{vav}; # Source in utf8 | ||||||||||
| 1650 | my $size = StringLength V(string, $address); # Length of source | ||||||||||
| 1651 | |||||||||||
| 1652 | |||||||||||
| 1653 | my $parse = create K(address, $address), $size; # Create parse tree from source # 𝗘𝘅𝗮𝗺𝗽𝗹𝗲 | ||||||||||
| 1654 | |||||||||||
| 1655 | $parse->print; # Print parse tree | ||||||||||
| 1656 | |||||||||||
| 1657 | ok Assemble(debug=>0, eq => <<END); | ||||||||||
| 1658 | Assign | ||||||||||
| 1659 | Term | ||||||||||
| 1660 | Variable | ||||||||||
| 1661 | Term | ||||||||||
| 1662 | Variable | ||||||||||
| 1663 | END | ||||||||||
| 1664 | |||||||||||
| 1665 | |||||||||||
| 1666 | =head1 Parse | ||||||||||
| 1667 | |||||||||||
| 1668 | Parse Unisyn expressions | ||||||||||
| 1669 | |||||||||||
| 1670 | =head1 Print | ||||||||||
| 1671 | |||||||||||
| 1672 | Print a parse tree | ||||||||||
| 1673 | |||||||||||
| 1674 | =head2 print($parse) | ||||||||||
| 1675 | |||||||||||
| 1676 | Create a parser for an expression: | ||||||||||
| 1677 | |||||||||||
| 1678 | 𝗮 = 𝗯 | ||||||||||
| 1679 | |||||||||||
| 1680 | by coding: | ||||||||||
| 1681 | |||||||||||
| 1682 | my $address = Rutf8 $Lex->{sampleText}{vav}; # Source in utf8 | ||||||||||
| 1683 | my $size = StringLength V(string, $address); # Length of source | ||||||||||
| 1684 | |||||||||||
| 1685 | my $parse = create K(address, $address), $size; # Create parse tree from source | ||||||||||
| 1686 | |||||||||||
| 1687 | $parse->print; # Print parse tree # 𝗘𝘅𝗮𝗺𝗽𝗹𝗲 | ||||||||||
| 1688 | |||||||||||
| 1689 | Parse the B<Unisyn> expression to get: | ||||||||||
| 1690 | |||||||||||
| 1691 | ok Assemble(debug=>0, eq => <<END); | ||||||||||
| 1692 | Assign | ||||||||||
| 1693 | Term | ||||||||||
| 1694 | Variable: 𝗮 | ||||||||||
| 1695 | Term | ||||||||||
| 1696 | Variable: 𝗯 | ||||||||||
| 1697 | END | ||||||||||
| 1698 | |||||||||||
| 1699 | |||||||||||
| 1700 | =head1 Hash Definitions | ||||||||||
| 1701 | |||||||||||
| 1702 | |||||||||||
| 1703 | |||||||||||
| 1704 | |||||||||||
| 1705 | =head2 Unisyn::Parse Definition | ||||||||||
| 1706 | |||||||||||
| 1707 | |||||||||||
| 1708 | Description of parse | ||||||||||
| 1709 | |||||||||||
| 1710 | |||||||||||
| 1711 | |||||||||||
| 1712 | |||||||||||
| 1713 | =head3 Output fields | ||||||||||
| 1714 | |||||||||||
| 1715 | |||||||||||
| 1716 | =head4 address | ||||||||||
| 1717 | |||||||||||
| 1718 | Address of source string as utf8 | ||||||||||
| 1719 | |||||||||||
| 1720 | =head4 arena | ||||||||||
| 1721 | |||||||||||
| 1722 | Arena containing tree | ||||||||||
| 1723 | |||||||||||
| 1724 | =head4 fails | ||||||||||
| 1725 | |||||||||||
| 1726 | Number of failures encountered in this parse | ||||||||||
| 1727 | |||||||||||
| 1728 | =head4 parse | ||||||||||
| 1729 | |||||||||||
| 1730 | Offset to the head of the parse tree | ||||||||||
| 1731 | |||||||||||
| 1732 | =head4 size | ||||||||||
| 1733 | |||||||||||
| 1734 | Size of source string as utf8 | ||||||||||
| 1735 | |||||||||||
| 1736 | |||||||||||
| 1737 | |||||||||||
| 1738 | =head1 Private Methods | ||||||||||
| 1739 | |||||||||||
| 1740 | =head2 getAlpha($register, $address, $index) | ||||||||||
| 1741 | |||||||||||
| 1742 | Load the position of a lexical item in its alphabet from the current character. | ||||||||||
| 1743 | |||||||||||
| 1744 | Parameter Description | ||||||||||
| 1745 | 1 $register Register to load | ||||||||||
| 1746 | 2 $address Address of start of string | ||||||||||
| 1747 | 3 $index Index into string | ||||||||||
| 1748 | |||||||||||
| 1749 | =head2 getLexicalCode($register, $address, $index) | ||||||||||
| 1750 | |||||||||||
| 1751 | Load the lexical code of the current character in memory into the specified register. | ||||||||||
| 1752 | |||||||||||
| 1753 | Parameter Description | ||||||||||
| 1754 | 1 $register Register to load | ||||||||||
| 1755 | 2 $address Address of start of string | ||||||||||
| 1756 | 3 $index Index into string | ||||||||||
| 1757 | |||||||||||
| 1758 | =head2 putLexicalCode($register, $address, $index, $code) | ||||||||||
| 1759 | |||||||||||
| 1760 | Put the specified lexical code into the current character in memory. | ||||||||||
| 1761 | |||||||||||
| 1762 | Parameter Description | ||||||||||
| 1763 | 1 $register Register used to load code | ||||||||||
| 1764 | 2 $address Address of string | ||||||||||
| 1765 | 3 $index Index into string | ||||||||||
| 1766 | 4 $code Code to put | ||||||||||
| 1767 | |||||||||||
| 1768 | =head2 loadCurrentChar() | ||||||||||
| 1769 | |||||||||||
| 1770 | Load the details of the character currently being processed so that we have the index of the character in the upper half of the current character and the lexical type of the character in the lowest byte. | ||||||||||
| 1771 | |||||||||||
| 1772 | |||||||||||
| 1773 | =head2 checkStackHas($depth) | ||||||||||
| 1774 | |||||||||||
| 1775 | Check that we have at least the specified number of elements on the stack. | ||||||||||
| 1776 | |||||||||||
| 1777 | Parameter Description | ||||||||||
| 1778 | 1 $depth Number of elements required on the stack | ||||||||||
| 1779 | |||||||||||
| 1780 | =head2 pushElement() | ||||||||||
| 1781 | |||||||||||
| 1782 | Push the current element on to the stack. | ||||||||||
| 1783 | |||||||||||
| 1784 | |||||||||||
| 1785 | =head2 pushEmpty() | ||||||||||
| 1786 | |||||||||||
| 1787 | Push the empty element on to the stack. | ||||||||||
| 1788 | |||||||||||
| 1789 | |||||||||||
| 1790 | =head2 lexicalNameFromLetter($l) | ||||||||||
| 1791 | |||||||||||
| 1792 | Lexical name for a lexical item described by its letter. | ||||||||||
| 1793 | |||||||||||
| 1794 | Parameter Description | ||||||||||
| 1795 | 1 $l Letter of the lexical item | ||||||||||
| 1796 | |||||||||||
| 1797 | =head2 lexicalNumberFromLetter($l) | ||||||||||
| 1798 | |||||||||||
| 1799 | Lexical number for a lexical item described by its letter. | ||||||||||
| 1800 | |||||||||||
| 1801 | Parameter Description | ||||||||||
| 1802 | 1 $l Letter of the lexical item | ||||||||||
| 1803 | |||||||||||
| 1804 | =head2 new($depth, $description) | ||||||||||
| 1805 | |||||||||||
| 1806 | Create a new term in the parse tree rooted on the stack. | ||||||||||
| 1807 | |||||||||||
| 1808 | Parameter Description | ||||||||||
| 1809 | 1 $depth Stack depth to be converted | ||||||||||
| 1810 | 2 $description Text reason why we are creating a new term | ||||||||||
| 1811 | |||||||||||
| 1812 | =head2 error($message) | ||||||||||
| 1813 | |||||||||||
| 1814 | Die. | ||||||||||
| 1815 | |||||||||||
| 1816 | Parameter Description | ||||||||||
| 1817 | 1 $message Error message | ||||||||||
| 1818 | |||||||||||
| 1819 | =head2 testSet($set, $register) | ||||||||||
| 1820 | |||||||||||
| 1821 | Test a set of items, setting the Zero Flag is one matches else clear the Zero flag. | ||||||||||
| 1822 | |||||||||||
| 1823 | Parameter Description | ||||||||||
| 1824 | 1 $set Set of lexical letters | ||||||||||
| 1825 | 2 $register Register to test | ||||||||||
| 1826 | |||||||||||
| 1827 | =head2 checkSet($set) | ||||||||||
| 1828 | |||||||||||
| 1829 | Check that one of a set of items is on the top of the stack or complain if it is not. | ||||||||||
| 1830 | |||||||||||
| 1831 | Parameter Description | ||||||||||
| 1832 | 1 $set Set of lexical letters | ||||||||||
| 1833 | |||||||||||
| 1834 | =head2 reduce($priority) | ||||||||||
| 1835 | |||||||||||
| 1836 | Convert the longest possible expression on top of the stack into a term at the specified priority. | ||||||||||
| 1837 | |||||||||||
| 1838 | Parameter Description | ||||||||||
| 1839 | 1 $priority Priority of the operators to reduce | ||||||||||
| 1840 | |||||||||||
| 1841 | =head2 reduceMultiple($priority) | ||||||||||
| 1842 | |||||||||||
| 1843 | Reduce existing operators on the stack. | ||||||||||
| 1844 | |||||||||||
| 1845 | Parameter Description | ||||||||||
| 1846 | 1 $priority Priority of the operators to reduce | ||||||||||
| 1847 | |||||||||||
| 1848 | =head2 accept_a() | ||||||||||
| 1849 | |||||||||||
| 1850 | Assign. | ||||||||||
| 1851 | |||||||||||
| 1852 | |||||||||||
| 1853 | =head2 accept_b() | ||||||||||
| 1854 | |||||||||||
| 1855 | Open. | ||||||||||
| 1856 | |||||||||||
| 1857 | |||||||||||
| 1858 | =head2 accept_B() | ||||||||||
| 1859 | |||||||||||
| 1860 | Closing parenthesis. | ||||||||||
| 1861 | |||||||||||
| 1862 | |||||||||||
| 1863 | =head2 accept_d() | ||||||||||
| 1864 | |||||||||||
| 1865 | Infix but not assign or semi-colon. | ||||||||||
| 1866 | |||||||||||
| 1867 | |||||||||||
| 1868 | =head2 accept_p() | ||||||||||
| 1869 | |||||||||||
| 1870 | Prefix. | ||||||||||
| 1871 | |||||||||||
| 1872 | |||||||||||
| 1873 | =head2 accept_q() | ||||||||||
| 1874 | |||||||||||
| 1875 | Post fix. | ||||||||||
| 1876 | |||||||||||
| 1877 | |||||||||||
| 1878 | =head2 accept_s() | ||||||||||
| 1879 | |||||||||||
| 1880 | Semi colon. | ||||||||||
| 1881 | |||||||||||
| 1882 | |||||||||||
| 1883 | =head2 accept_v() | ||||||||||
| 1884 | |||||||||||
| 1885 | Variable. | ||||||||||
| 1886 | |||||||||||
| 1887 | |||||||||||
| 1888 | =head2 parseExpressionCode() | ||||||||||
| 1889 | |||||||||||
| 1890 | Parse the string of classified lexical items addressed by register $start of length $length. The resulting parse tree (if any) is returned in r15. | ||||||||||
| 1891 | |||||||||||
| 1892 | |||||||||||
| 1893 | =head2 parseExpression(@parameters) | ||||||||||
| 1894 | |||||||||||
| 1895 | Create a parser for an expression described by variables. | ||||||||||
| 1896 | |||||||||||
| 1897 | Parameter Description | ||||||||||
| 1898 | 1 @parameters Parameters describing expression | ||||||||||
| 1899 | |||||||||||
| 1900 | =head2 MatchBrackets(@parameters) | ||||||||||
| 1901 | |||||||||||
| 1902 | Replace the low three bytes of a utf32 bracket character with 24 bits of offset to the matching opening or closing bracket. Opening brackets have even codes from 0x10 to 0x4e while the corresponding closing bracket has a code one higher. | ||||||||||
| 1903 | |||||||||||
| 1904 | Parameter Description | ||||||||||
| 1905 | 1 @parameters Parameters | ||||||||||
| 1906 | |||||||||||
| 1907 | =head2 ClassifyNewLines(@parameters) | ||||||||||
| 1908 | |||||||||||
| 1909 | Scan input string looking for opportunities to convert new lines into semi colons. | ||||||||||
| 1910 | |||||||||||
| 1911 | Parameter Description | ||||||||||
| 1912 | 1 @parameters Parameters | ||||||||||
| 1913 | |||||||||||
| 1914 | =head2 ClassifyWhiteSpace(@parameters) | ||||||||||
| 1915 | |||||||||||
| 1916 | Classify white space per: "lib/Unisyn/whiteSpace/whiteSpaceClassification.pl". | ||||||||||
| 1917 | |||||||||||
| 1918 | Parameter Description | ||||||||||
| 1919 | 1 @parameters Parameters | ||||||||||
| 1920 | |||||||||||
| 1921 | =head2 parseUtf8($p, @parameters) | ||||||||||
| 1922 | |||||||||||
| 1923 | Parse a unisyn expression encoded as utf8 and return the parse tree. | ||||||||||
| 1924 | |||||||||||
| 1925 | Parameter Description | ||||||||||
| 1926 | 1 $p Parse | ||||||||||
| 1927 | 2 @parameters Parameters | ||||||||||
| 1928 | |||||||||||
| 1929 | =head2 T($key, $expected, %options) | ||||||||||
| 1930 | |||||||||||
| 1931 | Test a parse. | ||||||||||
| 1932 | |||||||||||
| 1933 | Parameter Description | ||||||||||
| 1934 | 1 $key Key of text to be parsed | ||||||||||
| 1935 | 2 $expected Expected result | ||||||||||
| 1936 | 3 %options Options | ||||||||||
| 1937 | |||||||||||
| 1938 | |||||||||||
| 1939 | =head1 Index | ||||||||||
| 1940 | |||||||||||
| 1941 | |||||||||||
| 1942 | 1 L<accept_a|/accept_a> - Assign. | ||||||||||
| 1943 | |||||||||||
| 1944 | 2 L<accept_B|/accept_B> - Closing parenthesis. | ||||||||||
| 1945 | |||||||||||
| 1946 | 3 L<accept_b|/accept_b> - Open. | ||||||||||
| 1947 | |||||||||||
| 1948 | 4 L<accept_d|/accept_d> - Infix but not assign or semi-colon. | ||||||||||
| 1949 | |||||||||||
| 1950 | 5 L<accept_p|/accept_p> - Prefix. | ||||||||||
| 1951 | |||||||||||
| 1952 | 6 L<accept_q|/accept_q> - Post fix. | ||||||||||
| 1953 | |||||||||||
| 1954 | 7 L<accept_s|/accept_s> - Semi colon. | ||||||||||
| 1955 | |||||||||||
| 1956 | 8 L<accept_v|/accept_v> - Variable. | ||||||||||
| 1957 | |||||||||||
| 1958 | 9 L<checkSet|/checkSet> - Check that one of a set of items is on the top of the stack or complain if it is not. | ||||||||||
| 1959 | |||||||||||
| 1960 | 10 L<checkStackHas|/checkStackHas> - Check that we have at least the specified number of elements on the stack. | ||||||||||
| 1961 | |||||||||||
| 1962 | 11 L<ClassifyNewLines|/ClassifyNewLines> - Scan input string looking for opportunities to convert new lines into semi colons. | ||||||||||
| 1963 | |||||||||||
| 1964 | 12 L<ClassifyWhiteSpace|/ClassifyWhiteSpace> - Classify white space per: "lib/Unisyn/whiteSpace/whiteSpaceClassification. | ||||||||||
| 1965 | |||||||||||
| 1966 | 13 L<create|/create> - Create a new unisyn parse from a utf8 string | ||||||||||
| 1967 | |||||||||||
| 1968 | 14 L<error|/error> - Die. | ||||||||||
| 1969 | |||||||||||
| 1970 | 15 L<getAlpha|/getAlpha> - Load the position of a lexical item in its alphabet from the current character. | ||||||||||
| 1971 | |||||||||||
| 1972 | 16 L<getLexicalCode|/getLexicalCode> - Load the lexical code of the current character in memory into the specified register. | ||||||||||
| 1973 | |||||||||||
| 1974 | 17 L<lexicalNameFromLetter|/lexicalNameFromLetter> - Lexical name for a lexical item described by its letter. | ||||||||||
| 1975 | |||||||||||
| 1976 | 18 L<lexicalNumberFromLetter|/lexicalNumberFromLetter> - Lexical number for a lexical item described by its letter. | ||||||||||
| 1977 | |||||||||||
| 1978 | 19 L<loadCurrentChar|/loadCurrentChar> - Load the details of the character currently being processed so that we have the index of the character in the upper half of the current character and the lexical type of the character in the lowest byte. | ||||||||||
| 1979 | |||||||||||
| 1980 | 20 L<MatchBrackets|/MatchBrackets> - Replace the low three bytes of a utf32 bracket character with 24 bits of offset to the matching opening or closing bracket. | ||||||||||
| 1981 | |||||||||||
| 1982 | 21 L<new|/new> - Create a new term in the parse tree rooted on the stack. | ||||||||||
| 1983 | |||||||||||
| 1984 | 22 L<parseExpression|/parseExpression> - Create a parser for an expression described by variables. | ||||||||||
| 1985 | |||||||||||
| 1986 | 23 L<parseExpressionCode|/parseExpressionCode> - Parse the string of classified lexical items addressed by register $start of length $length. | ||||||||||
| 1987 | |||||||||||
| 1988 | 24 L<parseUtf8|/parseUtf8> - Parse a unisyn expression encoded as utf8 and return the parse tree. | ||||||||||
| 1989 | |||||||||||
| 1990 | 25 L<print|/print> - Create a parser for an expression described by variables. | ||||||||||
| 1991 | |||||||||||
| 1992 | 26 L<pushElement|/pushElement> - Push the current element on to the stack. | ||||||||||
| 1993 | |||||||||||
| 1994 | 27 L<pushEmpty|/pushEmpty> - Push the empty element on to the stack. | ||||||||||
| 1995 | |||||||||||
| 1996 | 28 L<putLexicalCode|/putLexicalCode> - Put the specified lexical code into the current character in memory. | ||||||||||
| 1997 | |||||||||||
| 1998 | 29 L<reduce|/reduce> - Convert the longest possible expression on top of the stack into a term at the specified priority. | ||||||||||
| 1999 | |||||||||||
| 2000 | 30 L<reduceMultiple|/reduceMultiple> - Reduce existing operators on the stack. | ||||||||||
| 2001 | |||||||||||
| 2002 | 31 L<T|/T> - Test a parse. | ||||||||||
| 2003 | |||||||||||
| 2004 | 32 L<testSet|/testSet> - Test a set of items, setting the Zero Flag is one matches else clear the Zero flag. | ||||||||||
| 2005 | |||||||||||
| 2006 | =head1 Installation | ||||||||||
| 2007 | |||||||||||
| 2008 | This module is written in 100% Pure Perl and, thus, it is easy to read, | ||||||||||
| 2009 | comprehend, use, modify and install via B<cpan>: | ||||||||||
| 2010 | |||||||||||
| 2011 | sudo cpan install Unisyn::Parse | ||||||||||
| 2012 | |||||||||||
| 2013 | =head1 Author | ||||||||||
| 2014 | |||||||||||
| 2015 | L<philiprbrenan@gmail.com|mailto:philiprbrenan@gmail.com> | ||||||||||
| 2016 | |||||||||||
| 2017 | L<http://www.appaapps.com|http://www.appaapps.com> | ||||||||||
| 2018 | |||||||||||
| 2019 | =head1 Copyright | ||||||||||
| 2020 | |||||||||||
| 2021 | Copyright (c) 2016-2021 Philip R Brenan. | ||||||||||
| 2022 | |||||||||||
| 2023 | This module is free software. It may be used, redistributed and/or modified | ||||||||||
| 2024 | under the same terms as Perl itself. | ||||||||||
| 2025 | |||||||||||
| 2026 | =cut | ||||||||||
| 2027 | |||||||||||
| 2028 | |||||||||||
| 2029 | |||||||||||
| 2030 | # Tests and documentation | ||||||||||
| 2031 | |||||||||||
| 2032 | sub test | ||||||||||
| 2033 | {my $p = __PACKAGE__; | ||||||||||
| 2034 | binmode($_, ":utf8") for *STDOUT, *STDERR; | ||||||||||
| 2035 | return if eval "eof(${p}::DATA)"; | ||||||||||
| 2036 | my $s = eval "join('', <${p}::DATA>)"; | ||||||||||
| 2037 | $@ and die $@; | ||||||||||
| 2038 | eval $s; | ||||||||||
| 2039 | $@ and die $@; | ||||||||||
| 2040 | 1 | ||||||||||
| 2041 | } | ||||||||||
| 2042 | |||||||||||
| 2043 | test unless caller; | ||||||||||
| 2044 | |||||||||||
| 2045 | 1; | ||||||||||
| 2046 | # podDocumentation | ||||||||||
| 2047 | #__DATA__ | ||||||||||
| 2048 | use Time::HiRes qw(time); | ||||||||||
| 2049 | use Test::More; | ||||||||||
| 2050 | |||||||||||
| 2051 | my $localTest = ((caller(1))[0]//'Unisyn::Parse') eq "Unisyn::Parse"; # Local testing mode | ||||||||||
| 2052 | |||||||||||
| 2053 | Test::More->builder->output("/dev/null") if $localTest; # Reduce number of confirmation messages during testing | ||||||||||
| 2054 | |||||||||||
| 2055 | if ($^O =~ m(bsd|linux|cygwin)i) # Supported systems | ||||||||||
| 2056 | {if (confirmHasCommandLineCommand(q(nasm)) and LocateIntelEmulator) # Network assembler and Intel Software Development emulator | ||||||||||
| 2057 | {plan tests => 3; | ||||||||||
| 2058 | } | ||||||||||
| 2059 | else | ||||||||||
| 2060 | {plan skip_all => qq(Nasm or Intel 64 emulator not available); | ||||||||||
| 2061 | } | ||||||||||
| 2062 | } | ||||||||||
| 2063 | else | ||||||||||
| 2064 | {plan skip_all => qq(Not supported on: $^O); | ||||||||||
| 2065 | } | ||||||||||
| 2066 | |||||||||||
| 2067 | my $startTime = time; # Tests | ||||||||||
| 2068 | |||||||||||
| 2069 | eval {goto latest} if !caller(0) and -e "/home/phil"; # Go to latest test if specified | ||||||||||
| 2070 | |||||||||||
| 2071 | sub T($$%) #P Test a parse. | ||||||||||
| 2072 | {my ($key, $expected, %options) = @_; # Key of text to be parsed, expected result, options | ||||||||||
| 2073 | my $source = $$Lex{sampleText}{$key}; # String to be parsed in utf8 | ||||||||||
| 2074 | defined $source or confess; | ||||||||||
| 2075 | my $address = Rutf8 $source; | ||||||||||
| 2076 | my $size = StringLength V(string, $address); | ||||||||||
| 2077 | |||||||||||
| 2078 | my $p = create V(address, $address), $size; | ||||||||||
| 2079 | |||||||||||
| 2080 | if ($options{print}) # Print the parse tree if requested | ||||||||||
| 2081 | {my $t = $arena->DescribeTree; | ||||||||||
| 2082 | $t->first->copy($p->parse); | ||||||||||
| 2083 | $t->dump; | ||||||||||
| 2084 | } | ||||||||||
| 2085 | |||||||||||
| 2086 | Assemble(debug => 0, eq => $expected); | ||||||||||
| 2087 | } | ||||||||||
| 2088 | |||||||||||
| 2089 | #latest: | ||||||||||
| 2090 | ok T(q(brackets), <<END, comments=>10, print=>1, debug => 0); | ||||||||||
| 2091 | Tree at: 0000 0000 0000 0618 length: 0000 0000 0000 0008 | ||||||||||
| 2092 | 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 | ||||||||||
| 2093 | 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0598 0000 0009 0000 0018 0000 0009 0000 0001 0000 0005 0000 0003 0000 0009 | ||||||||||
| 2094 | 0000 0658 00A0 0008 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0007 0000 0006 0000 0005 0000 0004 0000 0003 0000 0002 0000 0001 0000 0000 | ||||||||||
| 2095 | index: 0000 0000 0000 0000 key: 0000 0000 0000 0000 data: 0000 0000 0000 0009 | ||||||||||
| 2096 | index: 0000 0000 0000 0001 key: 0000 0000 0000 0001 data: 0000 0000 0000 0003 | ||||||||||
| 2097 | index: 0000 0000 0000 0002 key: 0000 0000 0000 0002 data: 0000 0000 0000 0005 | ||||||||||
| 2098 | index: 0000 0000 0000 0003 key: 0000 0000 0000 0003 data: 0000 0000 0000 0001 | ||||||||||
| 2099 | index: 0000 0000 0000 0004 key: 0000 0000 0000 0004 data: 0000 0000 0000 0009 | ||||||||||
| 2100 | index: 0000 0000 0000 0005 key: 0000 0000 0000 0005 data: 0000 0000 0000 0018 subTree | ||||||||||
| 2101 | index: 0000 0000 0000 0006 key: 0000 0000 0000 0006 data: 0000 0000 0000 0009 | ||||||||||
| 2102 | index: 0000 0000 0000 0007 key: 0000 0000 0000 0007 data: 0000 0000 0000 0598 subTree | ||||||||||
| 2103 | Tree at: 0000 0000 0000 0018 length: 0000 0000 0000 0004 | ||||||||||
| 2104 | 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 | ||||||||||
| 2105 | 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0006 0000 0001 0000 0009 | ||||||||||
| 2106 | 0000 0058 0000 0004 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0003 0000 0002 0000 0001 0000 0000 | ||||||||||
| 2107 | index: 0000 0000 0000 0000 key: 0000 0000 0000 0000 data: 0000 0000 0000 0009 | ||||||||||
| 2108 | index: 0000 0000 0000 0001 key: 0000 0000 0000 0001 data: 0000 0000 0000 0001 | ||||||||||
| 2109 | index: 0000 0000 0000 0002 key: 0000 0000 0000 0002 data: 0000 0000 0000 0006 | ||||||||||
| 2110 | index: 0000 0000 0000 0003 key: 0000 0000 0000 0003 data: 0000 0000 0000 0000 | ||||||||||
| 2111 | end | ||||||||||
| 2112 | Tree at: 0000 0000 0000 0598 length: 0000 0000 0000 0006 | ||||||||||
| 2113 | 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 | ||||||||||
| 2114 | 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0518 0000 0009 0000 0007 0000 0000 0000 0002 0000 0009 | ||||||||||
| 2115 | 0000 05D8 0020 0006 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0005 0000 0004 0000 0003 0000 0002 0000 0001 0000 0000 | ||||||||||
| 2116 | index: 0000 0000 0000 0000 key: 0000 0000 0000 0000 data: 0000 0000 0000 0009 | ||||||||||
| 2117 | index: 0000 0000 0000 0001 key: 0000 0000 0000 0001 data: 0000 0000 0000 0002 | ||||||||||
| 2118 | index: 0000 0000 0000 0002 key: 0000 0000 0000 0002 data: 0000 0000 0000 0000 | ||||||||||
| 2119 | index: 0000 0000 0000 0003 key: 0000 0000 0000 0003 data: 0000 0000 0000 0007 | ||||||||||
| 2120 | index: 0000 0000 0000 0004 key: 0000 0000 0000 0004 data: 0000 0000 0000 0009 | ||||||||||
| 2121 | index: 0000 0000 0000 0005 key: 0000 0000 0000 0005 data: 0000 0000 0000 0518 subTree | ||||||||||
| 2122 | Tree at: 0000 0000 0000 0518 length: 0000 0000 0000 0004 | ||||||||||
| 2123 | 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 | ||||||||||
| 2124 | 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0498 0000 0009 0000 0001 0000 0009 | ||||||||||
| 2125 | 0000 0558 0008 0004 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0003 0000 0002 0000 0001 0000 0000 | ||||||||||
| 2126 | index: 0000 0000 0000 0000 key: 0000 0000 0000 0000 data: 0000 0000 0000 0009 | ||||||||||
| 2127 | index: 0000 0000 0000 0001 key: 0000 0000 0000 0001 data: 0000 0000 0000 0001 | ||||||||||
| 2128 | index: 0000 0000 0000 0002 key: 0000 0000 0000 0002 data: 0000 0000 0000 0009 | ||||||||||
| 2129 | index: 0000 0000 0000 0003 key: 0000 0000 0000 0003 data: 0000 0000 0000 0498 subTree | ||||||||||
| 2130 | Tree at: 0000 0000 0000 0498 length: 0000 0000 0000 0008 | ||||||||||
| 2131 | 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 | ||||||||||
| 2132 | 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0418 0000 0009 0000 0298 0000 0009 0000 000E 0000 0003 0000 0003 0000 0009 | ||||||||||
| 2133 | 0000 04D8 00A0 0008 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0007 0000 0006 0000 0005 0000 0004 0000 0003 0000 0002 0000 0001 0000 0000 | ||||||||||
| 2134 | index: 0000 0000 0000 0000 key: 0000 0000 0000 0000 data: 0000 0000 0000 0009 | ||||||||||
| 2135 | index: 0000 0000 0000 0001 key: 0000 0000 0000 0001 data: 0000 0000 0000 0003 | ||||||||||
| 2136 | index: 0000 0000 0000 0002 key: 0000 0000 0000 0002 data: 0000 0000 0000 0003 | ||||||||||
| 2137 | index: 0000 0000 0000 0003 key: 0000 0000 0000 0003 data: 0000 0000 0000 000E | ||||||||||
| 2138 | index: 0000 0000 0000 0004 key: 0000 0000 0000 0004 data: 0000 0000 0000 0009 | ||||||||||
| 2139 | index: 0000 0000 0000 0005 key: 0000 0000 0000 0005 data: 0000 0000 0000 0298 subTree | ||||||||||
| 2140 | index: 0000 0000 0000 0006 key: 0000 0000 0000 0006 data: 0000 0000 0000 0009 | ||||||||||
| 2141 | index: 0000 0000 0000 0007 key: 0000 0000 0000 0007 data: 0000 0000 0000 0418 subTree | ||||||||||
| 2142 | Tree at: 0000 0000 0000 0298 length: 0000 0000 0000 0006 | ||||||||||
| 2143 | 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 | ||||||||||
| 2144 | 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0218 0000 0009 0000 0008 0000 0000 0000 0002 0000 0009 | ||||||||||
| 2145 | 0000 02D8 0020 0006 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0005 0000 0004 0000 0003 0000 0002 0000 0001 0000 0000 | ||||||||||
| 2146 | index: 0000 0000 0000 0000 key: 0000 0000 0000 0000 data: 0000 0000 0000 0009 | ||||||||||
| 2147 | index: 0000 0000 0000 0001 key: 0000 0000 0000 0001 data: 0000 0000 0000 0002 | ||||||||||
| 2148 | index: 0000 0000 0000 0002 key: 0000 0000 0000 0002 data: 0000 0000 0000 0000 | ||||||||||
| 2149 | index: 0000 0000 0000 0003 key: 0000 0000 0000 0003 data: 0000 0000 0000 0008 | ||||||||||
| 2150 | index: 0000 0000 0000 0004 key: 0000 0000 0000 0004 data: 0000 0000 0000 0009 | ||||||||||
| 2151 | index: 0000 0000 0000 0005 key: 0000 0000 0000 0005 data: 0000 0000 0000 0218 subTree | ||||||||||
| 2152 | Tree at: 0000 0000 0000 0218 length: 0000 0000 0000 0004 | ||||||||||
| 2153 | 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 | ||||||||||
| 2154 | 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0198 0000 0009 0000 0001 0000 0009 | ||||||||||
| 2155 | 0000 0258 0008 0004 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0003 0000 0002 0000 0001 0000 0000 | ||||||||||
| 2156 | index: 0000 0000 0000 0000 key: 0000 0000 0000 0000 data: 0000 0000 0000 0009 | ||||||||||
| 2157 | index: 0000 0000 0000 0001 key: 0000 0000 0000 0001 data: 0000 0000 0000 0001 | ||||||||||
| 2158 | index: 0000 0000 0000 0002 key: 0000 0000 0000 0002 data: 0000 0000 0000 0009 | ||||||||||
| 2159 | index: 0000 0000 0000 0003 key: 0000 0000 0000 0003 data: 0000 0000 0000 0198 subTree | ||||||||||
| 2160 | Tree at: 0000 0000 0000 0198 length: 0000 0000 0000 0006 | ||||||||||
| 2161 | 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 | ||||||||||
| 2162 | 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0118 0000 0009 0000 0009 0000 0000 0000 0002 0000 0009 | ||||||||||
| 2163 | 0000 01D8 0020 0006 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0005 0000 0004 0000 0003 0000 0002 0000 0001 0000 0000 | ||||||||||
| 2164 | index: 0000 0000 0000 0000 key: 0000 0000 0000 0000 data: 0000 0000 0000 0009 | ||||||||||
| 2165 | index: 0000 0000 0000 0001 key: 0000 0000 0000 0001 data: 0000 0000 0000 0002 | ||||||||||
| 2166 | index: 0000 0000 0000 0002 key: 0000 0000 0000 0002 data: 0000 0000 0000 0000 | ||||||||||
| 2167 | index: 0000 0000 0000 0003 key: 0000 0000 0000 0003 data: 0000 0000 0000 0009 | ||||||||||
| 2168 | index: 0000 0000 0000 0004 key: 0000 0000 0000 0004 data: 0000 0000 0000 0009 | ||||||||||
| 2169 | index: 0000 0000 0000 0005 key: 0000 0000 0000 0005 data: 0000 0000 0000 0118 subTree | ||||||||||
| 2170 | Tree at: 0000 0000 0000 0118 length: 0000 0000 0000 0004 | ||||||||||
| 2171 | 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 | ||||||||||
| 2172 | 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0098 0000 0009 0000 0001 0000 0009 | ||||||||||
| 2173 | 0000 0158 0008 0004 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0003 0000 0002 0000 0001 0000 0000 | ||||||||||
| 2174 | index: 0000 0000 0000 0000 key: 0000 0000 0000 0000 data: 0000 0000 0000 0009 | ||||||||||
| 2175 | index: 0000 0000 0000 0001 key: 0000 0000 0000 0001 data: 0000 0000 0000 0001 | ||||||||||
| 2176 | index: 0000 0000 0000 0002 key: 0000 0000 0000 0002 data: 0000 0000 0000 0009 | ||||||||||
| 2177 | index: 0000 0000 0000 0003 key: 0000 0000 0000 0003 data: 0000 0000 0000 0098 subTree | ||||||||||
| 2178 | Tree at: 0000 0000 0000 0098 length: 0000 0000 0000 0004 | ||||||||||
| 2179 | 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 | ||||||||||
| 2180 | 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 000A 0000 0006 0000 0001 0000 0009 | ||||||||||
| 2181 | 0000 00D8 0000 0004 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0003 0000 0002 0000 0001 0000 0000 | ||||||||||
| 2182 | index: 0000 0000 0000 0000 key: 0000 0000 0000 0000 data: 0000 0000 0000 0009 | ||||||||||
| 2183 | index: 0000 0000 0000 0001 key: 0000 0000 0000 0001 data: 0000 0000 0000 0001 | ||||||||||
| 2184 | index: 0000 0000 0000 0002 key: 0000 0000 0000 0002 data: 0000 0000 0000 0006 | ||||||||||
| 2185 | index: 0000 0000 0000 0003 key: 0000 0000 0000 0003 data: 0000 0000 0000 000A | ||||||||||
| 2186 | end | ||||||||||
| 2187 | end | ||||||||||
| 2188 | end | ||||||||||
| 2189 | end | ||||||||||
| 2190 | end | ||||||||||
| 2191 | Tree at: 0000 0000 0000 0418 length: 0000 0000 0000 0006 | ||||||||||
| 2192 | 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 | ||||||||||
| 2193 | 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0398 0000 0009 0000 0012 0000 0000 0000 0002 0000 0009 | ||||||||||
| 2194 | 0000 0458 0020 0006 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0005 0000 0004 0000 0003 0000 0002 0000 0001 0000 0000 | ||||||||||
| 2195 | index: 0000 0000 0000 0000 key: 0000 0000 0000 0000 data: 0000 0000 0000 0009 | ||||||||||
| 2196 | index: 0000 0000 0000 0001 key: 0000 0000 0000 0001 data: 0000 0000 0000 0002 | ||||||||||
| 2197 | index: 0000 0000 0000 0002 key: 0000 0000 0000 0002 data: 0000 0000 0000 0000 | ||||||||||
| 2198 | index: 0000 0000 0000 0003 key: 0000 0000 0000 0003 data: 0000 0000 0000 0012 | ||||||||||
| 2199 | index: 0000 0000 0000 0004 key: 0000 0000 0000 0004 data: 0000 0000 0000 0009 | ||||||||||
| 2200 | index: 0000 0000 0000 0005 key: 0000 0000 0000 0005 data: 0000 0000 0000 0398 subTree | ||||||||||
| 2201 | Tree at: 0000 0000 0000 0398 length: 0000 0000 0000 0004 | ||||||||||
| 2202 | 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 | ||||||||||
| 2203 | 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0318 0000 0009 0000 0001 0000 0009 | ||||||||||
| 2204 | 0000 03D8 0008 0004 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0003 0000 0002 0000 0001 0000 0000 | ||||||||||
| 2205 | index: 0000 0000 0000 0000 key: 0000 0000 0000 0000 data: 0000 0000 0000 0009 | ||||||||||
| 2206 | index: 0000 0000 0000 0001 key: 0000 0000 0000 0001 data: 0000 0000 0000 0001 | ||||||||||
| 2207 | index: 0000 0000 0000 0002 key: 0000 0000 0000 0002 data: 0000 0000 0000 0009 | ||||||||||
| 2208 | index: 0000 0000 0000 0003 key: 0000 0000 0000 0003 data: 0000 0000 0000 0318 subTree | ||||||||||
| 2209 | Tree at: 0000 0000 0000 0318 length: 0000 0000 0000 0004 | ||||||||||
| 2210 | 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 | ||||||||||
| 2211 | 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0013 0000 0006 0000 0001 0000 0009 | ||||||||||
| 2212 | 0000 0358 0000 0004 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0003 0000 0002 0000 0001 0000 0000 | ||||||||||
| 2213 | index: 0000 0000 0000 0000 key: 0000 0000 0000 0000 data: 0000 0000 0000 0009 | ||||||||||
| 2214 | index: 0000 0000 0000 0001 key: 0000 0000 0000 0001 data: 0000 0000 0000 0001 | ||||||||||
| 2215 | index: 0000 0000 0000 0002 key: 0000 0000 0000 0002 data: 0000 0000 0000 0006 | ||||||||||
| 2216 | index: 0000 0000 0000 0003 key: 0000 0000 0000 0003 data: 0000 0000 0000 0013 | ||||||||||
| 2217 | end | ||||||||||
| 2218 | end | ||||||||||
| 2219 | end | ||||||||||
| 2220 | end | ||||||||||
| 2221 | end | ||||||||||
| 2222 | end | ||||||||||
| 2223 | end | ||||||||||
| 2224 | END | ||||||||||
| 2225 | |||||||||||
| 2226 | #latest: | ||||||||||
| 2227 | ok T(q(vav), <<END, comments=>10, print=>1); | ||||||||||
| 2228 | Tree at: 0000 0000 0000 0118 length: 0000 0000 0000 0008 | ||||||||||
| 2229 | 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 | ||||||||||
| 2230 | 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0098 0000 0009 0000 0018 0000 0009 0000 0001 0000 0005 0000 0003 0000 0009 | ||||||||||
| 2231 | 0000 0158 00A0 0008 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0007 0000 0006 0000 0005 0000 0004 0000 0003 0000 0002 0000 0001 0000 0000 | ||||||||||
| 2232 | index: 0000 0000 0000 0000 key: 0000 0000 0000 0000 data: 0000 0000 0000 0009 | ||||||||||
| 2233 | index: 0000 0000 0000 0001 key: 0000 0000 0000 0001 data: 0000 0000 0000 0003 | ||||||||||
| 2234 | index: 0000 0000 0000 0002 key: 0000 0000 0000 0002 data: 0000 0000 0000 0005 | ||||||||||
| 2235 | index: 0000 0000 0000 0003 key: 0000 0000 0000 0003 data: 0000 0000 0000 0001 | ||||||||||
| 2236 | index: 0000 0000 0000 0004 key: 0000 0000 0000 0004 data: 0000 0000 0000 0009 | ||||||||||
| 2237 | index: 0000 0000 0000 0005 key: 0000 0000 0000 0005 data: 0000 0000 0000 0018 subTree | ||||||||||
| 2238 | index: 0000 0000 0000 0006 key: 0000 0000 0000 0006 data: 0000 0000 0000 0009 | ||||||||||
| 2239 | index: 0000 0000 0000 0007 key: 0000 0000 0000 0007 data: 0000 0000 0000 0098 subTree | ||||||||||
| 2240 | Tree at: 0000 0000 0000 0018 length: 0000 0000 0000 0004 | ||||||||||
| 2241 | 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 | ||||||||||
| 2242 | 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0006 0000 0001 0000 0009 | ||||||||||
| 2243 | 0000 0058 0000 0004 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0003 0000 0002 0000 0001 0000 0000 | ||||||||||
| 2244 | index: 0000 0000 0000 0000 key: 0000 0000 0000 0000 data: 0000 0000 0000 0009 | ||||||||||
| 2245 | index: 0000 0000 0000 0001 key: 0000 0000 0000 0001 data: 0000 0000 0000 0001 | ||||||||||
| 2246 | index: 0000 0000 0000 0002 key: 0000 0000 0000 0002 data: 0000 0000 0000 0006 | ||||||||||
| 2247 | index: 0000 0000 0000 0003 key: 0000 0000 0000 0003 data: 0000 0000 0000 0000 | ||||||||||
| 2248 | end | ||||||||||
| 2249 | Tree at: 0000 0000 0000 0098 length: 0000 0000 0000 0004 | ||||||||||
| 2250 | 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 | ||||||||||
| 2251 | 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0002 0000 0006 0000 0001 0000 0009 | ||||||||||
| 2252 | 0000 00D8 0000 0004 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0003 0000 0002 0000 0001 0000 0000 | ||||||||||
| 2253 | index: 0000 0000 0000 0000 key: 0000 0000 0000 0000 data: 0000 0000 0000 0009 | ||||||||||
| 2254 | index: 0000 0000 0000 0001 key: 0000 0000 0000 0001 data: 0000 0000 0000 0001 | ||||||||||
| 2255 | index: 0000 0000 0000 0002 key: 0000 0000 0000 0002 data: 0000 0000 0000 0006 | ||||||||||
| 2256 | index: 0000 0000 0000 0003 key: 0000 0000 0000 0003 data: 0000 0000 0000 0002 | ||||||||||
| 2257 | end | ||||||||||
| 2258 | end | ||||||||||
| 2259 | END | ||||||||||
| 2260 | |||||||||||
| 2261 | #latest: | ||||||||||
| 2262 | if (1) { #Tcreate #Tprint | ||||||||||
| 2263 | my $address = Rutf8 $Lex->{sampleText}{vav}; # Source in utf8 | ||||||||||
| 2264 | my $size = StringLength V(string, $address); # Length of source | ||||||||||
| 2265 | |||||||||||
| 2266 | my $parse = create K(address, $address), $size; # Create parse tree from source | ||||||||||
| 2267 | $parse->print; # Print parse tree | ||||||||||
| 2268 | |||||||||||
| 2269 | ok Assemble(debug=>0, eq => <<END); | ||||||||||
| 2270 | Assign: 𝑎 | ||||||||||
| 2271 | Term | ||||||||||
| 2272 | Variable: 𝗮 | ||||||||||
| 2273 | Term | ||||||||||
| 2274 | Variable: 𝗯 | ||||||||||
| 2275 | END | ||||||||||
| 2276 | } | ||||||||||
| 2277 | |||||||||||
| 2278 | #latest: | ||||||||||
| 2279 | ok T(q(brackets), <<END) if 0; | ||||||||||
| 2280 | ParseUtf8 | ||||||||||
| 2281 | END | ||||||||||
| 2282 | |||||||||||
| 2283 | #latest: | ||||||||||
| 2284 | ok T(q(brackets), <<END) if 0; | ||||||||||
| 2285 | ParseUtf8 | ||||||||||
| 2286 | END | ||||||||||
| 2287 | |||||||||||
| 2288 | |||||||||||
| 2289 | unlink $_ for qw(hash print2 sde-log.txt sde-ptr-check.out.txt z.txt); # Remove incidental files | ||||||||||
| 2290 | |||||||||||
| 2291 | say STDERR sprintf("# Finished in %.2fs, bytes: %s, execs: %s ", time - $startTime, | ||||||||||
| 2292 | map {numberWithCommas $_} | ||||||||||
| 2293 | $Nasm::X86::totalBytesAssembled, $Nasm::X86::instructionsExecuted); | ||||||||||