|
0
|
1 .\" Automatically generated by Pod::Man 2.25 (Pod::Simple 3.22)
|
|
|
2 .\"
|
|
|
3 .\" Standard preamble:
|
|
|
4 .\" ========================================================================
|
|
|
5 .de Sp \" Vertical space (when we can't use .PP)
|
|
|
6 .if t .sp .5v
|
|
|
7 .if n .sp
|
|
|
8 ..
|
|
|
9 .de Vb \" Begin verbatim text
|
|
|
10 .ft CW
|
|
|
11 .nf
|
|
|
12 .ne \\$1
|
|
|
13 ..
|
|
|
14 .de Ve \" End verbatim text
|
|
|
15 .ft R
|
|
|
16 .fi
|
|
|
17 ..
|
|
|
18 .\" Set up some character translations and predefined strings. \*(-- will
|
|
|
19 .\" give an unbreakable dash, \*(PI will give pi, \*(L" will give a left
|
|
|
20 .\" double quote, and \*(R" will give a right double quote. \*(C+ will
|
|
|
21 .\" give a nicer C++. Capital omega is used to do unbreakable dashes and
|
|
|
22 .\" therefore won't be available. \*(C` and \*(C' expand to `' in nroff,
|
|
|
23 .\" nothing in troff, for use with C<>.
|
|
|
24 .tr \(*W-
|
|
|
25 .ds C+ C\v'-.1v'\h'-1p'\s-2+\h'-1p'+\s0\v'.1v'\h'-1p'
|
|
|
26 .ie n \{\
|
|
|
27 . ds -- \(*W-
|
|
|
28 . ds PI pi
|
|
|
29 . if (\n(.H=4u)&(1m=24u) .ds -- \(*W\h'-12u'\(*W\h'-12u'-\" diablo 10 pitch
|
|
|
30 . if (\n(.H=4u)&(1m=20u) .ds -- \(*W\h'-12u'\(*W\h'-8u'-\" diablo 12 pitch
|
|
|
31 . ds L" ""
|
|
|
32 . ds R" ""
|
|
|
33 . ds C` ""
|
|
|
34 . ds C' ""
|
|
|
35 'br\}
|
|
|
36 .el\{\
|
|
|
37 . ds -- \|\(em\|
|
|
|
38 . ds PI \(*p
|
|
|
39 . ds L" ``
|
|
|
40 . ds R" ''
|
|
|
41 'br\}
|
|
|
42 .\"
|
|
|
43 .\" Escape single quotes in literal strings from groff's Unicode transform.
|
|
|
44 .ie \n(.g .ds Aq \(aq
|
|
|
45 .el .ds Aq '
|
|
|
46 .\"
|
|
|
47 .\" If the F register is turned on, we'll generate index entries on stderr for
|
|
|
48 .\" titles (.TH), headers (.SH), subsections (.SS), items (.Ip), and index
|
|
|
49 .\" entries marked with X<> in POD. Of course, you'll have to process the
|
|
|
50 .\" output yourself in some meaningful fashion.
|
|
|
51 .ie \nF \{\
|
|
|
52 . de IX
|
|
|
53 . tm Index:\\$1\t\\n%\t"\\$2"
|
|
|
54 ..
|
|
|
55 . nr % 0
|
|
|
56 . rr F
|
|
|
57 .\}
|
|
|
58 .el \{\
|
|
|
59 . de IX
|
|
|
60 ..
|
|
|
61 .\}
|
|
|
62 .\"
|
|
|
63 .\" Accent mark definitions (@(#)ms.acc 1.5 88/02/08 SMI; from UCB 4.2).
|
|
|
64 .\" Fear. Run. Save yourself. No user-serviceable parts.
|
|
|
65 . \" fudge factors for nroff and troff
|
|
|
66 .if n \{\
|
|
|
67 . ds #H 0
|
|
|
68 . ds #V .8m
|
|
|
69 . ds #F .3m
|
|
|
70 . ds #[ \f1
|
|
|
71 . ds #] \fP
|
|
|
72 .\}
|
|
|
73 .if t \{\
|
|
|
74 . ds #H ((1u-(\\\\n(.fu%2u))*.13m)
|
|
|
75 . ds #V .6m
|
|
|
76 . ds #F 0
|
|
|
77 . ds #[ \&
|
|
|
78 . ds #] \&
|
|
|
79 .\}
|
|
|
80 . \" simple accents for nroff and troff
|
|
|
81 .if n \{\
|
|
|
82 . ds ' \&
|
|
|
83 . ds ` \&
|
|
|
84 . ds ^ \&
|
|
|
85 . ds , \&
|
|
|
86 . ds ~ ~
|
|
|
87 . ds /
|
|
|
88 .\}
|
|
|
89 .if t \{\
|
|
|
90 . ds ' \\k:\h'-(\\n(.wu*8/10-\*(#H)'\'\h"|\\n:u"
|
|
|
91 . ds ` \\k:\h'-(\\n(.wu*8/10-\*(#H)'\`\h'|\\n:u'
|
|
|
92 . ds ^ \\k:\h'-(\\n(.wu*10/11-\*(#H)'^\h'|\\n:u'
|
|
|
93 . ds , \\k:\h'-(\\n(.wu*8/10)',\h'|\\n:u'
|
|
|
94 . ds ~ \\k:\h'-(\\n(.wu-\*(#H-.1m)'~\h'|\\n:u'
|
|
|
95 . ds / \\k:\h'-(\\n(.wu*8/10-\*(#H)'\z\(sl\h'|\\n:u'
|
|
|
96 .\}
|
|
|
97 . \" troff and (daisy-wheel) nroff accents
|
|
|
98 .ds : \\k:\h'-(\\n(.wu*8/10-\*(#H+.1m+\*(#F)'\v'-\*(#V'\z.\h'.2m+\*(#F'.\h'|\\n:u'\v'\*(#V'
|
|
|
99 .ds 8 \h'\*(#H'\(*b\h'-\*(#H'
|
|
|
100 .ds o \\k:\h'-(\\n(.wu+\w'\(de'u-\*(#H)/2u'\v'-.3n'\*(#[\z\(de\v'.3n'\h'|\\n:u'\*(#]
|
|
|
101 .ds d- \h'\*(#H'\(pd\h'-\w'~'u'\v'-.25m'\f2\(hy\fP\v'.25m'\h'-\*(#H'
|
|
|
102 .ds D- D\\k:\h'-\w'D'u'\v'-.11m'\z\(hy\v'.11m'\h'|\\n:u'
|
|
|
103 .ds th \*(#[\v'.3m'\s+1I\s-1\v'-.3m'\h'-(\w'I'u*2/3)'\s-1o\s+1\*(#]
|
|
|
104 .ds Th \*(#[\s+2I\s-2\h'-\w'I'u*3/5'\v'-.3m'o\v'.3m'\*(#]
|
|
|
105 .ds ae a\h'-(\w'a'u*4/10)'e
|
|
|
106 .ds Ae A\h'-(\w'A'u*4/10)'E
|
|
|
107 . \" corrections for vroff
|
|
|
108 .if v .ds ~ \\k:\h'-(\\n(.wu*9/10-\*(#H)'\s-2\u~\d\s+2\h'|\\n:u'
|
|
|
109 .if v .ds ^ \\k:\h'-(\\n(.wu*10/11-\*(#H)'\v'-.4m'^\v'.4m'\h'|\\n:u'
|
|
|
110 . \" for low resolution devices (crt and lpr)
|
|
|
111 .if \n(.H>23 .if \n(.V>19 \
|
|
|
112 \{\
|
|
|
113 . ds : e
|
|
|
114 . ds 8 ss
|
|
|
115 . ds o a
|
|
|
116 . ds d- d\h'-1'\(ga
|
|
|
117 . ds D- D\h'-1'\(hy
|
|
|
118 . ds th \o'bp'
|
|
|
119 . ds Th \o'LP'
|
|
|
120 . ds ae ae
|
|
|
121 . ds Ae AE
|
|
|
122 .\}
|
|
|
123 .rm #[ #] #H #V #F C
|
|
|
124 .\" ========================================================================
|
|
|
125 .\"
|
|
|
126 .IX Title "YYLEXER 1"
|
|
|
127 .TH YYLEXER 1 "2015-03-29" "perl v5.14.2" "MayaChemTools"
|
|
|
128 .\" For nroff, turn off justification. Always turn off hyphenation; it makes
|
|
|
129 .\" way too many mistakes in technical documents.
|
|
|
130 .if n .ad l
|
|
|
131 .nh
|
|
|
132 .SH "NAME"
|
|
|
133 Parsers::YYLexer
|
|
|
134 .SH "SYNOPSIS"
|
|
|
135 .IX Header "SYNOPSIS"
|
|
|
136 use Parseres::YYLexer;
|
|
|
137 .PP
|
|
|
138 use Parsers::YYLexer qw(:all);
|
|
|
139 .SH "DESCRIPTION"
|
|
|
140 .IX Header "DESCRIPTION"
|
|
|
141 \&\fBYYLexer\fR class provides the following methods:
|
|
|
142 .PP
|
|
|
143 new, GetYYLex, Next, Peek, SetupYYTabFile, StringifyYYLexer, YYLex
|
|
|
144 .PP
|
|
|
145 \&\fBParsers::YYLexer\fR class is derived from \fBParsers::Lexer\fR base class, which provides all
|
|
|
146 the underlying lexer functionality. \fBYYLexer\fR class is designed to be used with
|
|
|
147 \&\fByyparse\fR code generated by running \fBbyacc\fR on a parsers defined using
|
|
|
148 parser definition \fBParserName.yy\fR file.
|
|
|
149 .PP
|
|
|
150 \&\fIYYTabFile\fR containing mapping of token labels to integers must be explicitly
|
|
|
151 specified by the caller. This file is processed during new method invocation and
|
|
|
152 mapping of token labels to integers is loaded in a hash to be used later by \fBYYLex\fR
|
|
|
153 method to return token number and text pairs to the parser.
|
|
|
154 .SS "\s-1METHODS\s0"
|
|
|
155 .IX Subsection "METHODS"
|
|
|
156 .IP "\fBnew\fR" 4
|
|
|
157 .IX Item "new"
|
|
|
158 .Vb 1
|
|
|
159 \& $YYLexer = new Parsers::YYLexer($Input, @YYLexerTokensSpec);
|
|
|
160 .Ve
|
|
|
161 .Sp
|
|
|
162 Using specified \fIInput\fR and \fIYYLexerTokensSpec\fR, \fBnew\fR method generates a new
|
|
|
163 \&\fBYYLexer\fR and returns a reference to newly created \fBYYLexer\fR object.
|
|
|
164 .Sp
|
|
|
165 Examples:
|
|
|
166 .Sp
|
|
|
167 .Vb 10
|
|
|
168 \& # Tokens specifications supplied by the caller. It\*(Aqs an array containing references
|
|
|
169 \& # to arrays with each containing TokenLabel and TokenMatchRegex pair along with
|
|
|
170 \& # an option reference to code to be executed after a matched.
|
|
|
171 \& #
|
|
|
172 \& @LexerTokensSpec = (
|
|
|
173 \& [ \*(AqLETTER\*(Aq, qr/[a\-zA\-Z]/ ],
|
|
|
174 \& [ \*(AqNUMBER\*(Aq, qr/\ed+/ ],
|
|
|
175 \& [ \*(AqSPACE\*(Aq, qr/[ ]*/,
|
|
|
176 \& sub { my($This, $TokenLabel, $MatchedText) = @_; return \*(Aq\*(Aq; }
|
|
|
177 \& ],
|
|
|
178 \& [ \*(AqNEWLINE\*(Aq, qr/(?:\er\en|\er|\en)/,
|
|
|
179 \& sub { my($This, $TokenLabel, $MatchedText) = @_; return "\en"; }
|
|
|
180 \& ],
|
|
|
181 \& [ \*(AqCHAR\*(Aq, qr/./ ]
|
|
|
182 \& );
|
|
|
183 \&
|
|
|
184 \& # Input string...
|
|
|
185 \& $InputText = \*(Aqy = 3 + 4\*(Aq;
|
|
|
186 \&
|
|
|
187 \& $YLexer = new Parsers::YYLexer($InputText, @LexerTokensSpec);
|
|
|
188 \&
|
|
|
189 \& # Setup default token table file...
|
|
|
190 \& $YYTabFile = "Parsers/SimpleCalcParser.tab.ph";
|
|
|
191 \& $This\->SetupYYTabFile($YYTabFile);
|
|
|
192 \&
|
|
|
193 \& # Process input stream...
|
|
|
194 \& ($TokenNumber, $TokenText) = $YYLexer\->Lex();
|
|
|
195 \& print "TokenNumber: $TokenNumber; TokenText: $TokenText\en";
|
|
|
196 \&
|
|
|
197 \& # Input file...
|
|
|
198 \& $InputFile = "Input.txt";
|
|
|
199 \& open INPUTFILE, "$InputFile" or die "Couldn\*(Aqt open $InputFile: $!\en";
|
|
|
200 \& $Lexer = new Parsers::YYLexer(\e*INPUTFILE, @LexerTokensSpec);
|
|
|
201 \&
|
|
|
202 \& # Input file iterator...
|
|
|
203 \& $InputFile = "TestSimpleCalcParser.txt";
|
|
|
204 \& open INPUTFILE, "$InputFile" or die "Couldn\*(Aqt open $InputFile: $!\en";
|
|
|
205 \& $InputIterator = sub { return <INPUTFILE>; };
|
|
|
206 \& $Lexer = new Parsers::YYLexer($InputIterator, @LexerTokensSpec);
|
|
|
207 \&
|
|
|
208 \& # Usage with code generated by byacc from a parser definition
|
|
|
209 \& # file SimpleCalcParser.yy...
|
|
|
210 \&
|
|
|
211 \& $InputText = "3 + 4 +6\enx=3\eny=5\enx+y\enx+z\en";
|
|
|
212 \&
|
|
|
213 \& $YYLexer = new Parsers::YYLexer($InputText,@LexerTokensSpec);
|
|
|
214 \&
|
|
|
215 \& $YYLex = $YYLexer\->GetYYLex();
|
|
|
216 \&
|
|
|
217 \& $YYTabFile = "Parsers/SimpleCalcParser.tab.ph";
|
|
|
218 \& $YYLexer\->SetupYYTabFile($YYTabFile);
|
|
|
219 \&
|
|
|
220 \& $Debug = 0;
|
|
|
221 \& $SimpleCalcParser = new Parsers::SimpleCalcParser($YYLex,
|
|
|
222 \& \e&Parsers::SimpleCalcParser::yyerror, $Debug);
|
|
|
223 \&
|
|
|
224 \& $Value = $SimpleCalcParser\->yyparse();
|
|
|
225 \& print "Value = " . (defined($Value) ? "$Value" : "Undefined") . "\en";
|
|
|
226 .Ve
|
|
|
227 .IP "\fBGetYYLex\fR" 4
|
|
|
228 .IX Item "GetYYLex"
|
|
|
229 .Vb 1
|
|
|
230 \& $YYLex = $YYLexer\->GetYYLex();
|
|
|
231 .Ve
|
|
|
232 .Sp
|
|
|
233 Returns a curried verson of YYLexer as \fBYYLex\fR: yyparse in parser generated by
|
|
|
234 byacc expects it to call without passing any argument for the \fIYYLexer\fR object.
|
|
|
235 .IP "\fBNext\fR" 4
|
|
|
236 .IX Item "Next"
|
|
|
237 .Vb 1
|
|
|
238 \& ($TokenNumber, $TokenText) = $YYLexer\->Next();
|
|
|
239 .Ve
|
|
|
240 .Sp
|
|
|
241 Returns next available \fBTokenNumber\fR and any matched \fBTokenText\fR from
|
|
|
242 input stream by removing it from the input stream. Token number and text of
|
|
|
243 zero corresponds to end of input (\s-1EOI\s0).
|
|
|
244 .IP "\fBPeek\fR" 4
|
|
|
245 .IX Item "Peek"
|
|
|
246 .Vb 1
|
|
|
247 \& ($TokenNumber, $TokenText) = $YYLexer\->Peek();
|
|
|
248 .Ve
|
|
|
249 .Sp
|
|
|
250 Returns next available \fBTokenNumber\fR and any matched \fBTokenText\fR from
|
|
|
251 input stream by simply looking ahead and without removing it from the input stream.
|
|
|
252 Token number and text of zero corresponds to end of input (\s-1EOI\s0).
|
|
|
253 .IP "\fBSetupYYTabFile\fR" 4
|
|
|
254 .IX Item "SetupYYTabFile"
|
|
|
255 .Vb 1
|
|
|
256 \& $YYLexer = $YYLexer\->SetupYYTabFile($YYTabFile);
|
|
|
257 .Ve
|
|
|
258 .Sp
|
|
|
259 Processes token labels to integers data map in specified \fIYYTabFile\fR and returns
|
|
|
260 \&\fIYYLexer\fR.
|
|
|
261 .Sp
|
|
|
262 Notes:
|
|
|
263 .Sp
|
|
|
264 .Vb 10
|
|
|
265 \& . YYTabFile must be a complete path or available through @INC path in the
|
|
|
266 \& same directory where this package is located.
|
|
|
267 \& . Name of YYTabFile might start with any valid sub directory name in @INC
|
|
|
268 \& For example, "Parsers/<YYTablFile>" implies the tab file in parsers sub
|
|
|
269 \& directory under MayaChemTools lib directory as it would be already in @INC
|
|
|
270 \& path.
|
|
|
271 \& . YYTabFile must be explicitly set by the caller. The default YYTabFile name,
|
|
|
272 \& y.tab.ph, generated by byacc is not used implicitly to avoid confusion
|
|
|
273 \& among multiple distinct instances of YYLexer.
|
|
|
274 \& . YYTabFile is generated by byacc during its usage with \-d options and
|
|
|
275 \& contains mapping of token codes to token names/labels. YYLexer used this
|
|
|
276 \& file to map token labels to token codes before returning token code and
|
|
|
277 \& value pair back to yyparse function used by byacc.
|
|
|
278 \& . User defined token numbers start from 257
|
|
|
279 \& . Token number for any user defined token EOI is mapped to its value before
|
|
|
280 \& default token number of 0 for EOI.
|
|
|
281 \&
|
|
|
282 \& The format of YYTabFile generated by byacc during generation of parser code in
|
|
|
283 \& Perl code is:
|
|
|
284 \&
|
|
|
285 \& ... ...
|
|
|
286 \& $NUMBER=257;
|
|
|
287 \& $ADDOP=258;
|
|
|
288 \& $SUBOP=259;
|
|
|
289 \& ... ..
|
|
|
290 .Ve
|
|
|
291 .IP "\fBYYLex\fR" 4
|
|
|
292 .IX Item "YYLex"
|
|
|
293 .Vb 2
|
|
|
294 \& ($TokenNumber, $TokenText) = $YYLexer\->YYLex();
|
|
|
295 \& ($TokenNumber, $TokenText) = $YYLexer\->YYLex($Mode);
|
|
|
296 .Ve
|
|
|
297 .Sp
|
|
|
298 Returns available \fBTokenNumber\fR and any matched \fBTokenText\fR from
|
|
|
299 input stream by either removing it from the input stream or by simply looking
|
|
|
300 ahead and without removing it from the input stream. Token number and text of
|
|
|
301 zero corresponds to end of input (\s-1EOI\s0).
|
|
|
302 .Sp
|
|
|
303 Possible \fIMode\fR values: \fIPeek, Next\fR. Default: \fINext\fR.
|
|
|
304 .Sp
|
|
|
305 \&\fIYYLex\fR is designed to be used with \fByyparse\fR code generated by running
|
|
|
306 \&\fBbyacc\fR on a parsers defined using parser definition \fBParserName.yy\fR file.
|
|
|
307 .Sp
|
|
|
308 Notes:
|
|
|
309 .Sp
|
|
|
310 .Vb 5
|
|
|
311 \& . Token label and value pairs returned by Lexer from by base class, which
|
|
|
312 \& can\*(Aqt be mapped to token labels specified in YYTabFile are ignored.
|
|
|
313 \& . Token text of length 1 returned by Lexer from base class without a
|
|
|
314 \& corresponding explicit token label, which can\*(Aqt be mapped to a token
|
|
|
315 \& number using Perl ord function, is ignored.
|
|
|
316 .Ve
|
|
|
317 .IP "\fBStringifyYYLexer\fR" 4
|
|
|
318 .IX Item "StringifyYYLexer"
|
|
|
319 .Vb 1
|
|
|
320 \& $YYLexerString = $YYLexer\->StringifyYYLexer();
|
|
|
321 .Ve
|
|
|
322 .Sp
|
|
|
323 Returns a string containing information about \fIYYLexer\fR object.
|
|
|
324 .SH "AUTHOR"
|
|
|
325 .IX Header "AUTHOR"
|
|
|
326 Manish Sud <msud@san.rr.com>
|
|
|
327 .SH "SEE ALSO"
|
|
|
328 .IX Header "SEE ALSO"
|
|
|
329 Lexer.pm, SimpleCalcYYLexer.pm, SimpleCalcParser.yy
|
|
|
330 .SH "COPYRIGHT"
|
|
|
331 .IX Header "COPYRIGHT"
|
|
|
332 Copyright (C) 2015 Manish Sud. All rights reserved.
|
|
|
333 .PP
|
|
|
334 This file is part of MayaChemTools.
|
|
|
335 .PP
|
|
|
336 MayaChemTools is free software; you can redistribute it and/or modify it under
|
|
|
337 the terms of the \s-1GNU\s0 Lesser General Public License as published by the Free
|
|
|
338 Software Foundation; either version 3 of the License, or (at your option)
|
|
|
339 any later version.
|
