1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359
|
/*----------------------------------------------------------------------
Compiler Generator Coco/R,
Copyright (c) 1990, 2004 Hanspeter Moessenboeck, University of Linz
extended by M. Loeberbauer & A. Woess, Univ. of Linz
with improvements by Pat Terry, Rhodes University
This program is free software; you can redistribute it and/or modify it
under the terms of the GNU General Public License as published by the
Free Software Foundation; either version 2, or (at your option) any
later version.
This program is distributed in the hope that it will be useful, but
WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
for more details.
You should have received a copy of the GNU General Public License along
with this program; if not, write to the Free Software Foundation, Inc.,
59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
As an exception, it is allowed to write an extension of Coco/R that is
used as a plugin in non-free software.
If not otherwise stated, any source code generated by Coco/R (other than
Coco/R itself) does not fall under the GNU General Public License.
-----------------------------------------------------------------------*/
-->begin
using System;
using System.IO;
using System.Collections.Generic;
-->namespace
public class Token {
public int kind; // token kind
public int pos; // token position in the source text (starting at 0)
public int col; // token column (starting at 1)
public int line; // token line (starting at 1)
public string val; // token value
public Token next; // ML 2005-03-11 Tokens are kept in linked list
}
//-----------------------------------------------------------------------------------
// Buffer
//-----------------------------------------------------------------------------------
public class Buffer {
// This Buffer supports the following cases:
// 1) seekable stream (file)
// a) whole stream in buffer
// b) part of stream in buffer
// 2) non seekable stream (network, console)
public const int EOF = char.MaxValue + 1;
const int MIN_BUFFER_LENGTH = 1024; // 1KB
const int MAX_BUFFER_LENGTH = MIN_BUFFER_LENGTH * 64; // 64KB
byte[] buf; // input buffer
int bufStart; // position of first byte in buffer relative to input stream
int bufLen; // length of buffer
int fileLen; // length of input stream (may change if the stream is no file)
int bufPos; // current position in buffer
Stream stream; // input stream (seekable)
bool isUserStream; // was the stream opened by the user?
public Buffer (Stream s, bool isUserStream) {
stream = s; this.isUserStream = isUserStream;
if (stream.CanSeek) {
fileLen = (int) stream.Length;
bufLen = Math.Min(fileLen, MAX_BUFFER_LENGTH);
bufStart = Int32.MaxValue; // nothing in the buffer so far
} else {
fileLen = bufLen = bufStart = 0;
}
buf = new byte[(bufLen>0) ? bufLen : MIN_BUFFER_LENGTH];
if (fileLen > 0) Pos = 0; // setup buffer to position 0 (start)
else bufPos = 0; // index 0 is already after the file, thus Pos = 0 is invalid
if (bufLen == fileLen && stream.CanSeek) Close();
}
protected Buffer(Buffer b) { // called in UTF8Buffer constructor
buf = b.buf;
bufStart = b.bufStart;
bufLen = b.bufLen;
fileLen = b.fileLen;
bufPos = b.bufPos;
stream = b.stream;
// keep destructor from closing the stream
b.stream = null;
isUserStream = b.isUserStream;
}
~Buffer() { Close(); }
protected void Close() {
if (!isUserStream && stream != null) {
stream.Close();
stream = null;
}
}
public virtual int Read () {
if (bufPos < bufLen) {
return buf[bufPos++];
} else if (Pos < fileLen) {
Pos = Pos; // shift buffer start to Pos
return buf[bufPos++];
} else if (stream != null && !stream.CanSeek && ReadNextStreamChunk() > 0) {
return buf[bufPos++];
} else {
return EOF;
}
}
public int Peek () {
int curPos = Pos;
int ch = Read();
Pos = curPos;
return ch;
}
public string GetString (int beg, int end) {
int len = end - beg;
char[] buf = new char[len];
int oldPos = Pos;
Pos = beg;
for (int i = 0; i < len; i++) buf[i] = (char) Read();
Pos = oldPos;
return new String(buf);
}
public int Pos {
get { return bufPos + bufStart; }
set {
if (value >= fileLen && stream != null && !stream.CanSeek) {
// Wanted position is after buffer and the stream
// is not seek-able e.g. network or console,
// thus we have to read the stream manually till
// the wanted position is in sight.
while (value >= fileLen && ReadNextStreamChunk() > 0);
}
if (value < 0 || value > fileLen) {
throw new FatalError("buffer out of bounds access, position: " + value);
}
if (value >= bufStart && value < bufStart + bufLen) { // already in buffer
bufPos = value - bufStart;
} else if (stream != null) { // must be swapped in
stream.Seek(value, SeekOrigin.Begin);
bufLen = stream.Read(buf, 0, buf.Length);
bufStart = value; bufPos = 0;
} else {
// set the position to the end of the file, Pos will return fileLen.
bufPos = fileLen - bufStart;
}
}
}
// Read the next chunk of bytes from the stream, increases the buffer
// if needed and updates the fields fileLen and bufLen.
// Returns the number of bytes read.
private int ReadNextStreamChunk() {
int free = buf.Length - bufLen;
if (free == 0) {
// in the case of a growing input stream
// we can neither seek in the stream, nor can we
// foresee the maximum length, thus we must adapt
// the buffer size on demand.
byte[] newBuf = new byte[bufLen * 2];
Array.Copy(buf, newBuf, bufLen);
buf = newBuf;
free = bufLen;
}
int read = stream.Read(buf, bufLen, free);
if (read > 0) {
fileLen = bufLen = (bufLen + read);
return read;
}
// end of stream reached
return 0;
}
}
//-----------------------------------------------------------------------------------
// UTF8Buffer
//-----------------------------------------------------------------------------------
public class UTF8Buffer: Buffer {
public UTF8Buffer(Buffer b): base(b) {}
public override int Read() {
int ch;
do {
ch = base.Read();
// until we find a uft8 start (0xxxxxxx or 11xxxxxx)
} while ((ch >= 128) && ((ch & 0xC0) != 0xC0) && (ch != EOF));
if (ch < 128 || ch == EOF) {
// nothing to do, first 127 chars are the same in ascii and utf8
// 0xxxxxxx or end of file character
} else if ((ch & 0xF0) == 0xF0) {
// 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx
int c1 = ch & 0x07; ch = base.Read();
int c2 = ch & 0x3F; ch = base.Read();
int c3 = ch & 0x3F; ch = base.Read();
int c4 = ch & 0x3F;
ch = (((((c1 << 6) | c2) << 6) | c3) << 6) | c4;
} else if ((ch & 0xE0) == 0xE0) {
// 1110xxxx 10xxxxxx 10xxxxxx
int c1 = ch & 0x0F; ch = base.Read();
int c2 = ch & 0x3F; ch = base.Read();
int c3 = ch & 0x3F;
ch = (((c1 << 6) | c2) << 6) | c3;
} else if ((ch & 0xC0) == 0xC0) {
// 110xxxxx 10xxxxxx
int c1 = ch & 0x1F; ch = base.Read();
int c2 = ch & 0x3F;
ch = (c1 << 6) | c2;
}
return ch;
}
}
//-----------------------------------------------------------------------------------
// Scanner
//-----------------------------------------------------------------------------------
public class Scanner {
const char EOL = '\n';
const int eofSym = 0; /* pdt */
-->declarations
public Buffer buffer; // scanner buffer
Token t; // current token
int ch; // current input character
int pos; // byte position of current character
int col; // column number of current character
int line; // line number of current character
int oldEols; // EOLs that appeared in a comment;
Dictionary<int, int> start; // maps first token character to start state
Token tokens; // list of tokens already peeked (first token is a dummy)
Token pt; // current peek token
char[] tval = new char[128]; // text of current token
int tlen; // length of current token
public Scanner (string fileName) {
try {
Stream stream = new FileStream(fileName, FileMode.Open, FileAccess.Read, FileShare.Read);
buffer = new Buffer(stream, false);
Init();
} catch (IOException) {
throw new FatalError("Cannot open file " + fileName);
}
}
public Scanner (Stream s) {
buffer = new Buffer(s, true);
Init();
}
void Init() {
pos = -1; line = 1; col = 0;
oldEols = 0;
NextCh();
if (ch == 0xEF) { // check optional byte order mark for UTF-8
NextCh(); int ch1 = ch;
NextCh(); int ch2 = ch;
if (ch1 != 0xBB || ch2 != 0xBF) {
throw new FatalError(String.Format("illegal byte order mark: EF {0,2:X} {1,2:X}", ch1, ch2));
}
buffer = new UTF8Buffer(buffer); col = 0;
NextCh();
}
start = new Dictionary<int, int>(128);
-->initialization
pt = tokens = new Token(); // first token is a dummy
}
void NextCh() {
if (oldEols > 0) { ch = EOL; oldEols--; }
else {
pos = buffer.Pos;
ch = buffer.Read(); col++;
// replace isolated '\r' by '\n' in order to make
// eol handling uniform across Windows, Unix and Mac
if (ch == '\r' && buffer.Peek() != '\n') ch = EOL;
if (ch == EOL) { line++; col = 0; }
}
-->casing1
}
void AddCh() {
if (tlen >= tval.Length) {
char[] newBuf = new char[2 * tval.Length];
Array.Copy(tval, 0, newBuf, 0, tval.Length);
tval = newBuf;
}
-->casing2
NextCh();
}
-->comments
void CheckLiteral() {
-->literals
}
Token NextToken() {
while (ch == ' ' ||
-->scan1
) NextCh();
-->scan2
t = new Token();
t.pos = pos; t.col = col; t.line = line;
int state;
try { state = start[ch]; } catch (KeyNotFoundException) { state = 0; }
tlen = 0; AddCh();
switch (state) {
case -1: { t.kind = eofSym; break; } // NextCh already done
case 0: { t.kind = noSym; break; } // NextCh already done
-->scan3
}
t.val = new String(tval, 0, tlen);
return t;
}
// get the next token (possibly a token already seen during peeking)
public Token Scan () {
if (tokens.next == null) {
return NextToken();
} else {
pt = tokens = tokens.next;
return tokens;
}
}
// peek for the next token, ignore pragmas
public Token Peek () {
if (pt.next == null) {
do {
pt = pt.next = NextToken();
} while (pt.kind > maxT); // skip pragmas
} else {
do {
pt = pt.next;
} while (pt.kind > maxT);
}
return pt;
}
// make sure that peeking starts at the current scan position
public void ResetPeek () { pt = tokens; }
} // end Scanner
$$$
|