4252 lines
103 KiB
Groff
4252 lines
103 KiB
Groff
.\" $NetBSD: flex.1,v 1.12 2002/10/13 00:18:58 wiz Exp $
|
|
.\"
|
|
.TH FLEX 1 "April 1995" "Version 2.5"
|
|
.SH NAME
|
|
flex, lex \- fast lexical analyzer generator
|
|
.SH SYNOPSIS
|
|
.B flex
|
|
.B [\-bcdfhilnpstvwBFILTV78+? \-C[aefFmr] \-ooutput \-Pprefix \-Sskeleton]
|
|
.B [\-\-help \-\-version]
|
|
.I [filename ...]
|
|
.SH OVERVIEW
|
|
This manual describes
|
|
.I flex,
|
|
a tool for generating programs that perform pattern-matching on text.
|
|
The manual includes both tutorial and reference sections:
|
|
.nf
|
|
|
|
Description
|
|
a brief overview of the tool
|
|
|
|
Some Simple Examples
|
|
|
|
Format Of The Input File
|
|
|
|
Patterns
|
|
the extended regular expressions used by flex
|
|
|
|
How The Input Is Matched
|
|
the rules for determining what has been matched
|
|
|
|
Actions
|
|
how to specify what to do when a pattern is matched
|
|
|
|
The Generated Scanner
|
|
details regarding the scanner that flex produces;
|
|
how to control the input source
|
|
|
|
Start Conditions
|
|
introducing context into your scanners, and
|
|
managing "mini-scanners"
|
|
|
|
Multiple Input Buffers
|
|
how to manipulate multiple input sources; how to
|
|
scan from strings instead of files
|
|
|
|
End-of-file Rules
|
|
special rules for matching the end of the input
|
|
|
|
Miscellaneous Macros
|
|
a summary of macros available to the actions
|
|
|
|
Values Available To The User
|
|
a summary of values available to the actions
|
|
|
|
Interfacing With Yacc
|
|
connecting flex scanners together with yacc parsers
|
|
|
|
Options
|
|
flex command-line options, and the "%option"
|
|
directive
|
|
|
|
Performance Considerations
|
|
how to make your scanner go as fast as possible
|
|
|
|
Generating C++ Scanners
|
|
the (experimental) facility for generating C++
|
|
scanner classes
|
|
|
|
Incompatibilities With Lex And POSIX
|
|
how flex differs from AT\*[Am]T lex and the POSIX lex
|
|
standard
|
|
|
|
Diagnostics
|
|
those error messages produced by flex (or scanners
|
|
it generates) whose meanings might not be apparent
|
|
|
|
Files
|
|
files used by flex
|
|
|
|
Deficiencies / Bugs
|
|
known problems with flex
|
|
|
|
See Also
|
|
other documentation, related tools
|
|
|
|
Author
|
|
includes contact information
|
|
|
|
.fi
|
|
.SH DESCRIPTION
|
|
.I flex
|
|
is a tool for generating
|
|
.I scanners:
|
|
programs which recognized lexical patterns in text.
|
|
.I flex
|
|
reads
|
|
the given input files, or its standard input if no file names are given,
|
|
for a description of a scanner to generate.
|
|
The description is in the form of pairs
|
|
of regular expressions and C code, called
|
|
.I rules.
|
|
.I flex
|
|
generates as output a C source file,
|
|
.B lex.yy.c,
|
|
which defines a routine
|
|
.B yylex().
|
|
This file is compiled and linked with the
|
|
.B \-lfl
|
|
library to produce an executable.
|
|
When the executable is run,
|
|
it analyzes its input for occurrences
|
|
of the regular expressions.
|
|
Whenever it finds one, it executes
|
|
the corresponding C code.
|
|
.SH SOME SIMPLE EXAMPLES
|
|
.PP
|
|
First some simple examples to get the flavor of how one uses
|
|
.I flex.
|
|
The following
|
|
.I flex
|
|
input specifies a scanner which whenever it encounters the string
|
|
"username" will replace it with the user's login name:
|
|
.nf
|
|
|
|
%%
|
|
username printf( "%s", getlogin() );
|
|
|
|
.fi
|
|
By default, any text not matched by a
|
|
.I flex
|
|
scanner
|
|
is copied to the output, so the net effect of this scanner is
|
|
to copy its input file to its output with each occurrence
|
|
of "username" expanded.
|
|
In this input, there is just one rule.
|
|
"username" is the
|
|
.I pattern
|
|
and the "printf" is the
|
|
.I action.
|
|
The "%%" marks the beginning of the rules.
|
|
.PP
|
|
Here's another simple example:
|
|
.nf
|
|
|
|
int num_lines = 0, num_chars = 0;
|
|
|
|
%%
|
|
\\n ++num_lines; ++num_chars;
|
|
. ++num_chars;
|
|
|
|
%%
|
|
main()
|
|
{
|
|
yylex();
|
|
printf( "# of lines = %d, # of chars = %d\\n",
|
|
num_lines, num_chars );
|
|
}
|
|
|
|
.fi
|
|
This scanner counts the number of characters and the number
|
|
of lines in its input (it produces no output other than the
|
|
final report on the counts).
|
|
The first line
|
|
declares two globals, "num_lines" and "num_chars", which are accessible
|
|
both inside
|
|
.B yylex()
|
|
and in the
|
|
.B main()
|
|
routine declared after the second "%%".
|
|
There are two rules, one
|
|
which matches a newline ("\\n") and increments both the line count and
|
|
the character count, and one which matches any character other than
|
|
a newline (indicated by the "." regular expression).
|
|
.PP
|
|
A somewhat more complicated example:
|
|
.nf
|
|
|
|
/* scanner for a toy Pascal-like language */
|
|
|
|
%{
|
|
/* need this for the call to atof() below */
|
|
#include \*[Lt]math.h\*[Gt]
|
|
%}
|
|
|
|
DIGIT [0-9]
|
|
ID [a-z][a-z0-9]*
|
|
|
|
%%
|
|
|
|
{DIGIT}+ {
|
|
printf( "An integer: %s (%d)\\n", yytext,
|
|
atoi( yytext ) );
|
|
}
|
|
|
|
{DIGIT}+"."{DIGIT}* {
|
|
printf( "A float: %s (%g)\\n", yytext,
|
|
atof( yytext ) );
|
|
}
|
|
|
|
if|then|begin|end|procedure|function {
|
|
printf( "A keyword: %s\\n", yytext );
|
|
}
|
|
|
|
{ID} printf( "An identifier: %s\\n", yytext );
|
|
|
|
"+"|"-"|"*"|"/" printf( "An operator: %s\\n", yytext );
|
|
|
|
"{"[^}\\n]*"}" /* eat up one-line comments */
|
|
|
|
[ \\t\\n]+ /* eat up whitespace */
|
|
|
|
. printf( "Unrecognized character: %s\\n", yytext );
|
|
|
|
%%
|
|
|
|
main( argc, argv )
|
|
int argc;
|
|
char **argv;
|
|
{
|
|
++argv, --argc; /* skip over program name */
|
|
if ( argc \*[Gt] 0 )
|
|
yyin = fopen( argv[0], "r" );
|
|
else
|
|
yyin = stdin;
|
|
|
|
yylex();
|
|
}
|
|
|
|
.fi
|
|
This is the beginnings of a simple scanner for a language like
|
|
Pascal.
|
|
It identifies different types of
|
|
.I tokens
|
|
and reports on what it has seen.
|
|
.PP
|
|
The details of this example will be explained in the following
|
|
sections.
|
|
.SH FORMAT OF THE INPUT FILE
|
|
The
|
|
.I flex
|
|
input file consists of three sections, separated by a line with just
|
|
.B %%
|
|
in it:
|
|
.nf
|
|
|
|
definitions
|
|
%%
|
|
rules
|
|
%%
|
|
user code
|
|
|
|
.fi
|
|
The
|
|
.I definitions
|
|
section contains declarations of simple
|
|
.I name
|
|
definitions to simplify the scanner specification, and declarations of
|
|
.I start conditions,
|
|
which are explained in a later section.
|
|
.PP
|
|
Name definitions have the form:
|
|
.nf
|
|
|
|
name definition
|
|
|
|
.fi
|
|
The "name" is a word beginning with a letter or an underscore ('_')
|
|
followed by zero or more letters, digits, '_', or '-' (dash).
|
|
The definition is taken to begin at the first non-white-space character
|
|
following the name and continuing to the end of the line.
|
|
The definition can subsequently be referred to using "{name}", which
|
|
will expand to "(definition)".
|
|
For example,
|
|
.nf
|
|
|
|
DIGIT [0-9]
|
|
ID [a-z][a-z0-9]*
|
|
|
|
.fi
|
|
defines "DIGIT" to be a regular expression which matches a
|
|
single digit, and
|
|
"ID" to be a regular expression which matches a letter
|
|
followed by zero-or-more letters-or-digits.
|
|
A subsequent reference to
|
|
.nf
|
|
|
|
{DIGIT}+"."{DIGIT}*
|
|
|
|
.fi
|
|
is identical to
|
|
.nf
|
|
|
|
([0-9])+"."([0-9])*
|
|
|
|
.fi
|
|
and matches one-or-more digits followed by a '.' followed
|
|
by zero-or-more digits.
|
|
.PP
|
|
The
|
|
.I rules
|
|
section of the
|
|
.I flex
|
|
input contains a series of rules of the form:
|
|
.nf
|
|
|
|
pattern action
|
|
|
|
.fi
|
|
where the pattern must be unindented and the action must begin
|
|
on the same line.
|
|
.PP
|
|
See below for a further description of patterns and actions.
|
|
.PP
|
|
Finally, the user code section is simply copied to
|
|
.B lex.yy.c
|
|
verbatim.
|
|
It is used for companion routines which call or are called
|
|
by the scanner.
|
|
The presence of this section is optional;
|
|
if it is missing, the second
|
|
.B %%
|
|
in the input file may be skipped, too.
|
|
.PP
|
|
In the definitions and rules sections, any
|
|
.I indented
|
|
text or text enclosed in
|
|
.B %{
|
|
and
|
|
.B %}
|
|
is copied verbatim to the output (with the %{}'s removed).
|
|
The %{}'s must appear unindented on lines by themselves.
|
|
.PP
|
|
In the rules section,
|
|
any indented or %{} text appearing before the
|
|
first rule may be used to declare variables
|
|
which are local to the scanning routine and (after the declarations)
|
|
code which is to be executed whenever the scanning routine is entered.
|
|
Other indented or %{} text in the rule section is still copied to the output,
|
|
but its meaning is not well-defined and it may well cause compile-time
|
|
errors (this feature is present for
|
|
.I POSIX
|
|
compliance; see below for other such features).
|
|
.PP
|
|
In the definitions section (but not in the rules section),
|
|
an unindented comment (i.e., a line
|
|
beginning with "/*") is also copied verbatim to the output up
|
|
to the next "*/".
|
|
.SH PATTERNS
|
|
The patterns in the input are written using an extended set of regular
|
|
expressions.
|
|
These are:
|
|
.nf
|
|
|
|
x match the character 'x'
|
|
. any character (byte) except newline
|
|
[xyz] a "character class"; in this case, the pattern
|
|
matches either an 'x', a 'y', or a 'z'
|
|
[abj-oZ] a "character class" with a range in it; matches
|
|
an 'a', a 'b', any letter from 'j' through 'o',
|
|
or a 'Z'
|
|
[^A-Z] a "negated character class", i.e., any character
|
|
but those in the class. In this case, any
|
|
character EXCEPT an uppercase letter.
|
|
[^A-Z\\n] any character EXCEPT an uppercase letter or
|
|
a newline
|
|
r* zero or more r's, where r is any regular expression
|
|
r+ one or more r's
|
|
r? zero or one r's (that is, "an optional r")
|
|
r{2,5} anywhere from two to five r's
|
|
r{2,} two or more r's
|
|
r{4} exactly 4 r's
|
|
{name} the expansion of the "name" definition
|
|
(see above)
|
|
"[xyz]\\"foo"
|
|
the literal string: [xyz]"foo
|
|
\\X if X is an 'a', 'b', 'f', 'n', 'r', 't', or 'v',
|
|
then the ANSI-C interpretation of \\x.
|
|
Otherwise, a literal 'X' (used to escape
|
|
operators such as '*')
|
|
\\0 a NUL character (ASCII code 0)
|
|
\\123 the character with octal value 123
|
|
\\x2a the character with hexadecimal value 2a
|
|
(r) match an r; parentheses are used to override
|
|
precedence (see below)
|
|
|
|
|
|
rs the regular expression r followed by the
|
|
regular expression s; called "concatenation"
|
|
|
|
|
|
r|s either an r or an s
|
|
|
|
|
|
r/s an r but only if it is followed by an s. The
|
|
text matched by s is included when determining
|
|
whether this rule is the "longest match",
|
|
but is then returned to the input before
|
|
the action is executed. So the action only
|
|
sees the text matched by r. This type
|
|
of pattern is called trailing context".
|
|
(There are some combinations of r/s that flex
|
|
cannot match correctly; see notes in the
|
|
Deficiencies / Bugs section below regarding
|
|
"dangerous trailing context".)
|
|
^r an r, but only at the beginning of a line (i.e.,
|
|
which just starting to scan, or right after a
|
|
newline has been scanned).
|
|
r$ an r, but only at the end of a line (i.e., just
|
|
before a newline). Equivalent to "r/\\n".
|
|
|
|
Note that flex's notion of "newline" is exactly
|
|
whatever the C compiler used to compile flex
|
|
interprets '\\n' as; in particular, on some DOS
|
|
systems you must either filter out \\r's in the
|
|
input yourself, or explicitly use r/\\r\\n for "r$".
|
|
|
|
|
|
\*[Lt]s\*[Gt]r an r, but only in start condition s (see
|
|
below for discussion of start conditions)
|
|
\*[Lt]s1,s2,s3\*[Gt]r
|
|
same, but in any of start conditions s1,
|
|
s2, or s3
|
|
\*[Lt]*\*[Gt]r an r in any start condition, even an exclusive one.
|
|
|
|
|
|
\*[Lt]\*[Lt]EOF\*[Gt]\*[Gt] an end-of-file
|
|
\*[Lt]s1,s2\*[Gt]\*[Lt]\*[Lt]EOF\*[Gt]\*[Gt]
|
|
an end-of-file when in start condition s1 or s2
|
|
|
|
.fi
|
|
Note that inside of a character class, all regular expression operators
|
|
lose their special meaning except escape ('\\') and the character class
|
|
operators, '-', ']', and, at the beginning of the class, '^'.
|
|
.PP
|
|
The regular expressions listed above are grouped according to
|
|
precedence, from highest precedence at the top to lowest at the bottom.
|
|
Those grouped together have equal precedence.
|
|
For example,
|
|
.nf
|
|
|
|
foo|bar*
|
|
|
|
.fi
|
|
is the same as
|
|
.nf
|
|
|
|
(foo)|(ba(r*))
|
|
|
|
.fi
|
|
since the '*' operator has higher precedence than concatenation,
|
|
and concatenation higher than alternation ('|').
|
|
This pattern
|
|
therefore matches
|
|
.I either
|
|
the string "foo"
|
|
.I or
|
|
the string "ba" followed by zero-or-more r's.
|
|
To match "foo" or zero-or-more "bar"'s, use:
|
|
.nf
|
|
|
|
foo|(bar)*
|
|
|
|
.fi
|
|
and to match zero-or-more "foo"'s-or-"bar"'s:
|
|
.nf
|
|
|
|
(foo|bar)*
|
|
|
|
.fi
|
|
.PP
|
|
In addition to characters and ranges of characters, character classes
|
|
can also contain character class
|
|
.I expressions.
|
|
These are expressions enclosed inside
|
|
.B [:
|
|
and
|
|
.B :]
|
|
delimiters (which themselves must appear between the '[' and ']' of the
|
|
character class; other elements may occur inside the character class, too).
|
|
The valid expressions are:
|
|
.nf
|
|
|
|
[:alnum:] [:alpha:] [:blank:]
|
|
[:cntrl:] [:digit:] [:graph:]
|
|
[:lower:] [:print:] [:punct:]
|
|
[:space:] [:upper:] [:xdigit:]
|
|
|
|
.fi
|
|
These expressions all designate a set of characters equivalent to
|
|
the corresponding standard C
|
|
.B isXXX
|
|
function.
|
|
For example,
|
|
.B [:alnum:]
|
|
designates those characters for which
|
|
.B isalnum()
|
|
returns true - i.e., any alphabetic or numeric.
|
|
Some systems don't provide
|
|
.B isblank(),
|
|
so flex defines
|
|
.B [:blank:]
|
|
as a blank or a tab.
|
|
.PP
|
|
For example, the following character classes are all equivalent:
|
|
.nf
|
|
|
|
[[:alnum:]]
|
|
[[:alpha:][:digit:]
|
|
[[:alpha:]0-9]
|
|
[a-zA-Z0-9]
|
|
|
|
.fi
|
|
If your scanner is case-insensitive (the
|
|
.B \-i
|
|
flag), then
|
|
.B [:upper:]
|
|
and
|
|
.B [:lower:]
|
|
are equivalent to
|
|
.B [:alpha:].
|
|
.PP
|
|
Some notes on patterns:
|
|
.IP -
|
|
A negated character class such as the example "[^A-Z]"
|
|
above
|
|
.I will match a newline
|
|
unless "\\n" (or an equivalent escape sequence) is one of the
|
|
characters explicitly present in the negated character class
|
|
(e.g., "[^A-Z\\n]").
|
|
This is unlike how many other regular
|
|
expression tools treat negated character classes, but unfortunately
|
|
the inconsistency is historically entrenched.
|
|
Matching newlines means that a pattern like [^"]* can match the entire
|
|
input unless there's another quote in the input.
|
|
.IP -
|
|
A rule can have at most one instance of trailing context (the '/' operator
|
|
or the '$' operator).
|
|
The start condition, '^', and "\*[Lt]\*[Lt]EOF\*[Gt]\*[Gt]" patterns
|
|
can only occur at the beginning of a pattern, and, as well as with '/' and '$',
|
|
cannot be grouped inside parentheses.
|
|
A '^' which does not occur at
|
|
the beginning of a rule or a '$' which does not occur at the end of
|
|
a rule loses its special properties and is treated as a normal character.
|
|
.IP
|
|
The following are illegal:
|
|
.nf
|
|
|
|
foo/bar$
|
|
\*[Lt]sc1\*[Gt]foo\*[Lt]sc2\*[Gt]bar
|
|
|
|
.fi
|
|
Note that the first of these, can be written "foo/bar\\n".
|
|
.IP
|
|
The following will result in '$' or '^' being treated as a normal character:
|
|
.nf
|
|
|
|
foo|(bar$)
|
|
foo|^bar
|
|
|
|
.fi
|
|
If what's wanted is a "foo" or a bar-followed-by-a-newline, the following
|
|
could be used (the special '|' action is explained below):
|
|
.nf
|
|
|
|
foo |
|
|
bar$ /* action goes here */
|
|
|
|
.fi
|
|
A similar trick will work for matching a foo or a
|
|
bar-at-the-beginning-of-a-line.
|
|
.SH HOW THE INPUT IS MATCHED
|
|
When the generated scanner is run, it analyzes its input looking
|
|
for strings which match any of its patterns.
|
|
If it finds more than
|
|
one match, it takes the one matching the most text (for trailing
|
|
context rules, this includes the length of the trailing part, even
|
|
though it will then be returned to the input).
|
|
If it finds two
|
|
or more matches of the same length, the
|
|
rule listed first in the
|
|
.I flex
|
|
input file is chosen.
|
|
.PP
|
|
Once the match is determined, the text corresponding to the match
|
|
(called the
|
|
.I token)
|
|
is made available in the global character pointer
|
|
.B yytext,
|
|
and its length in the global integer
|
|
.B yyleng.
|
|
The
|
|
.I action
|
|
corresponding to the matched pattern is then executed (a more
|
|
detailed description of actions follows), and then the remaining
|
|
input is scanned for another match.
|
|
.PP
|
|
If no match is found, then the
|
|
.I default rule
|
|
is executed: the next character in the input is considered matched and
|
|
copied to the standard output.
|
|
Thus, the simplest legal
|
|
.I flex
|
|
input is:
|
|
.nf
|
|
|
|
%%
|
|
|
|
.fi
|
|
which generates a scanner that simply copies its input (one character
|
|
at a time) to its output.
|
|
.PP
|
|
Note that
|
|
.B yytext
|
|
can be defined in two different ways: either as a character
|
|
.I pointer
|
|
or as a character
|
|
.I array.
|
|
You can control which definition
|
|
.I flex
|
|
uses by including one of the special directives
|
|
.B %pointer
|
|
or
|
|
.B %array
|
|
in the first (definitions) section of your flex input.
|
|
The default is
|
|
.B %pointer,
|
|
unless you use the
|
|
.B -l
|
|
lex compatibility option, in which case
|
|
.B yytext
|
|
will be an array.
|
|
The advantage of using
|
|
.B %pointer
|
|
is substantially faster scanning and no buffer overflow when matching
|
|
very large tokens (unless you run out of dynamic memory).
|
|
The disadvantage
|
|
is that you are restricted in how your actions can modify
|
|
.B yytext
|
|
(see the next section), and calls to the
|
|
.B unput()
|
|
function destroys the present contents of
|
|
.B yytext,
|
|
which can be a considerable porting headache when moving between different
|
|
.I lex
|
|
versions.
|
|
.PP
|
|
The advantage of
|
|
.B %array
|
|
is that you can then modify
|
|
.B yytext
|
|
to your heart's content, and calls to
|
|
.B unput()
|
|
do not destroy
|
|
.B yytext
|
|
(see below).
|
|
Furthermore, existing
|
|
.I lex
|
|
programs sometimes access
|
|
.B yytext
|
|
externally using declarations of the form:
|
|
.nf
|
|
extern char yytext[];
|
|
.fi
|
|
This definition is erroneous when used with
|
|
.B %pointer,
|
|
but correct for
|
|
.B %array.
|
|
.PP
|
|
.B %array
|
|
defines
|
|
.B yytext
|
|
to be an array of
|
|
.B YYLMAX
|
|
characters, which defaults to a fairly large value.
|
|
You can change
|
|
the size by simply #define'ing
|
|
.B YYLMAX
|
|
to a different value in the first section of your
|
|
.I flex
|
|
input.
|
|
As mentioned above, with
|
|
.B %pointer
|
|
yytext grows dynamically to accommodate large tokens.
|
|
While this means your
|
|
.B %pointer
|
|
scanner can accommodate very large tokens (such as matching entire blocks
|
|
of comments), bear in mind that each time the scanner must resize
|
|
.B yytext
|
|
it also must rescan the entire token from the beginning, so matching such
|
|
tokens can prove slow.
|
|
.B yytext
|
|
presently does
|
|
.I not
|
|
dynamically grow if a call to
|
|
.B unput()
|
|
results in too much text being pushed back; instead, a run-time error results.
|
|
.PP
|
|
Also note that you cannot use
|
|
.B %array
|
|
with C++ scanner classes
|
|
(the
|
|
.B c++
|
|
option; see below).
|
|
.SH ACTIONS
|
|
Each pattern in a rule has a corresponding action, which can be any
|
|
arbitrary C statement.
|
|
The pattern ends at the first non-escaped
|
|
whitespace character; the remainder of the line is its action.
|
|
If the
|
|
action is empty, then when the pattern is matched the input token
|
|
is simply discarded.
|
|
For example, here is the specification for a program
|
|
which deletes all occurrences of "zap me" from its input:
|
|
.nf
|
|
|
|
%%
|
|
"zap me"
|
|
|
|
.fi
|
|
(It will copy all other characters in the input to the output since
|
|
they will be matched by the default rule.)
|
|
.PP
|
|
Here is a program which compresses multiple blanks and tabs down to
|
|
a single blank, and throws away whitespace found at the end of a line:
|
|
.nf
|
|
|
|
%%
|
|
[ \\t]+ putchar( ' ' );
|
|
[ \\t]+$ /* ignore this token */
|
|
|
|
.fi
|
|
.PP
|
|
If the action contains a '{', then the action spans till the balancing '}'
|
|
is found, and the action may cross multiple lines.
|
|
.I flex
|
|
knows about C strings and comments and won't be fooled by braces found
|
|
within them, but also allows actions to begin with
|
|
.B %{
|
|
and will consider the action to be all the text up to the next
|
|
.B %}
|
|
(regardless of ordinary braces inside the action).
|
|
.PP
|
|
An action consisting solely of a vertical bar ('|') means "same as
|
|
the action for the next rule." See below for an illustration.
|
|
.PP
|
|
Actions can include arbitrary C code, including
|
|
.B return
|
|
statements to return a value to whatever routine called
|
|
.B yylex().
|
|
Each time
|
|
.B yylex()
|
|
is called it continues processing tokens from where it last left
|
|
off until it either reaches
|
|
the end of the file or executes a return.
|
|
.PP
|
|
Actions are free to modify
|
|
.B yytext
|
|
except for lengthening it (adding
|
|
characters to its end--these will overwrite later characters in the
|
|
input stream).
|
|
This however does not apply when using
|
|
.B %array
|
|
(see above); in that case,
|
|
.B yytext
|
|
may be freely modified in any way.
|
|
.PP
|
|
Actions are free to modify
|
|
.B yyleng
|
|
except they should not do so if the action also includes use of
|
|
.B yymore()
|
|
(see below).
|
|
.PP
|
|
There are a number of special directives which can be included within
|
|
an action:
|
|
.IP -
|
|
.B ECHO
|
|
copies yytext to the scanner's output.
|
|
.IP -
|
|
.B BEGIN
|
|
followed by the name of a start condition places the scanner in the
|
|
corresponding start condition (see below).
|
|
.IP -
|
|
.B REJECT
|
|
directs the scanner to proceed on to the "second best" rule which matched the
|
|
input (or a prefix of the input).
|
|
The rule is chosen as described
|
|
above in "How the Input is Matched", and
|
|
.B yytext
|
|
and
|
|
.B yyleng
|
|
set up appropriately.
|
|
It may either be one which matched as much text
|
|
as the originally chosen rule but came later in the
|
|
.I flex
|
|
input file, or one which matched less text.
|
|
For example, the following will both count the
|
|
words in the input and call the routine special() whenever "frob" is seen:
|
|
.nf
|
|
|
|
int word_count = 0;
|
|
%%
|
|
|
|
frob special(); REJECT;
|
|
[^ \\t\\n]+ ++word_count;
|
|
|
|
.fi
|
|
Without the
|
|
.B REJECT,
|
|
any "frob"'s in the input would not be counted as words, since the
|
|
scanner normally executes only one action per token.
|
|
Multiple
|
|
.B REJECT's
|
|
are allowed, each one finding the next best choice to the currently
|
|
active rule.
|
|
For example, when the following scanner scans the token
|
|
"abcd", it will write "abcdabcaba" to the output:
|
|
.nf
|
|
|
|
%%
|
|
a |
|
|
ab |
|
|
abc |
|
|
abcd ECHO; REJECT;
|
|
.|\\n /* eat up any unmatched character */
|
|
|
|
.fi
|
|
(The first three rules share the fourth's action since they use
|
|
the special '|' action.)
|
|
.B REJECT
|
|
is a particularly expensive feature in terms of scanner performance;
|
|
if it is used in
|
|
.I any
|
|
of the scanner's actions it will slow down
|
|
.I all
|
|
of the scanner's matching.
|
|
Furthermore,
|
|
.B REJECT
|
|
cannot be used with the
|
|
.I -Cf
|
|
or
|
|
.I -CF
|
|
options (see below).
|
|
.IP
|
|
Note also that unlike the other special actions,
|
|
.B REJECT
|
|
is a
|
|
.I branch;
|
|
code immediately following it in the action will
|
|
.I not
|
|
be executed.
|
|
.IP -
|
|
.B yymore()
|
|
tells the scanner that the next time it matches a rule, the corresponding
|
|
token should be
|
|
.I appended
|
|
onto the current value of
|
|
.B yytext
|
|
rather than replacing it.
|
|
For example, given the input "mega-kludge"
|
|
the following will write "mega-mega-kludge" to the output:
|
|
.nf
|
|
|
|
%%
|
|
mega- ECHO; yymore();
|
|
kludge ECHO;
|
|
|
|
.fi
|
|
First "mega-" is matched and echoed to the output.
|
|
Then "kludge"
|
|
is matched, but the previous "mega-" is still hanging around at the
|
|
beginning of
|
|
.B yytext
|
|
so the
|
|
.B ECHO
|
|
for the "kludge" rule will actually write "mega-kludge".
|
|
.PP
|
|
Two notes regarding use of
|
|
.B yymore().
|
|
First,
|
|
.B yymore()
|
|
depends on the value of
|
|
.I yyleng
|
|
correctly reflecting the size of the current token, so you must not
|
|
modify
|
|
.I yyleng
|
|
if you are using
|
|
.B yymore().
|
|
Second, the presence of
|
|
.B yymore()
|
|
in the scanner's action entails a minor performance penalty in the
|
|
scanner's matching speed.
|
|
.IP -
|
|
.B yyless(n)
|
|
returns all but the first
|
|
.I n
|
|
characters of the current token back to the input stream, where they
|
|
will be rescanned when the scanner looks for the next match.
|
|
.B yytext
|
|
and
|
|
.B yyleng
|
|
are adjusted appropriately (e.g.,
|
|
.B yyleng
|
|
will now be equal to
|
|
.I n
|
|
).
|
|
For example, on the input "foobar" the following will write out
|
|
"foobarbar":
|
|
.nf
|
|
|
|
%%
|
|
foobar ECHO; yyless(3);
|
|
[a-z]+ ECHO;
|
|
|
|
.fi
|
|
An argument of 0 to
|
|
.B yyless
|
|
will cause the entire current input string to be scanned again.
|
|
Unless you've
|
|
changed how the scanner will subsequently process its input (using
|
|
.B BEGIN,
|
|
for example), this will result in an endless loop.
|
|
.PP
|
|
Note that
|
|
.B yyless
|
|
is a macro and can only be used in the flex input file, not from
|
|
other source files.
|
|
.IP -
|
|
.B unput(c)
|
|
puts the character
|
|
.I c
|
|
back onto the input stream.
|
|
It will be the next character scanned.
|
|
The following action will take the current token and cause it
|
|
to be rescanned enclosed in parentheses.
|
|
.nf
|
|
|
|
{
|
|
int i;
|
|
/* Copy yytext because unput() trashes yytext */
|
|
char *yycopy = strdup( yytext );
|
|
unput( ')' );
|
|
for ( i = yyleng - 1; i \*[Ge] 0; --i )
|
|
unput( yycopy[i] );
|
|
unput( '(' );
|
|
free( yycopy );
|
|
}
|
|
|
|
.fi
|
|
Note that since each
|
|
.B unput()
|
|
puts the given character back at the
|
|
.I beginning
|
|
of the input stream, pushing back strings must be done back-to-front.
|
|
.PP
|
|
An important potential problem when using
|
|
.B unput()
|
|
is that if you are using
|
|
.B %pointer
|
|
(the default), a call to
|
|
.B unput()
|
|
.I destroys
|
|
the contents of
|
|
.I yytext,
|
|
starting with its rightmost character and devouring one character to
|
|
the left with each call.
|
|
If you need the value of yytext preserved
|
|
after a call to
|
|
.B unput()
|
|
(as in the above example),
|
|
you must either first copy it elsewhere, or build your scanner using
|
|
.B %array
|
|
instead (see How The Input Is Matched).
|
|
.PP
|
|
Finally, note that you cannot put back
|
|
.B EOF
|
|
to attempt to mark the input stream with an end-of-file.
|
|
.IP -
|
|
.B input()
|
|
reads the next character from the input stream.
|
|
For example,
|
|
the following is one way to eat up C comments:
|
|
.nf
|
|
|
|
%%
|
|
"/*" {
|
|
register int c;
|
|
|
|
for ( ; ; )
|
|
{
|
|
while ( (c = input()) != '*' \*[Am]\*[Am]
|
|
c != EOF )
|
|
; /* eat up text of comment */
|
|
|
|
if ( c == '*' )
|
|
{
|
|
while ( (c = input()) == '*' )
|
|
;
|
|
if ( c == '/' )
|
|
break; /* found the end */
|
|
}
|
|
|
|
if ( c == EOF )
|
|
{
|
|
error( "EOF in comment" );
|
|
break;
|
|
}
|
|
}
|
|
}
|
|
|
|
.fi
|
|
(Note that if the scanner is compiled using
|
|
.B C++,
|
|
then
|
|
.B input()
|
|
is instead referred to as
|
|
.B yyinput(),
|
|
in order to avoid a name clash with the
|
|
.B C++
|
|
stream by the name of
|
|
.I input.)
|
|
.IP -
|
|
.B YY_FLUSH_BUFFER
|
|
flushes the scanner's internal buffer
|
|
so that the next time the scanner attempts to match a token, it will
|
|
first refill the buffer using
|
|
.B YY_INPUT
|
|
(see The Generated Scanner, below).
|
|
This action is a special case
|
|
of the more general
|
|
.B yy_flush_buffer()
|
|
function, described below in the section Multiple Input Buffers.
|
|
.IP -
|
|
.B yyterminate()
|
|
can be used in lieu of a return statement in an action.
|
|
It terminates
|
|
the scanner and returns a 0 to the scanner's caller, indicating "all done".
|
|
By default,
|
|
.B yyterminate()
|
|
is also called when an end-of-file is encountered.
|
|
It is a macro and may be redefined.
|
|
.SH THE GENERATED SCANNER
|
|
The output of
|
|
.I flex
|
|
is the file
|
|
.B lex.yy.c,
|
|
which contains the scanning routine
|
|
.B yylex(),
|
|
a number of tables used by it for matching tokens, and a number
|
|
of auxiliary routines and macros.
|
|
By default,
|
|
.B yylex()
|
|
is declared as follows:
|
|
.nf
|
|
|
|
int yylex()
|
|
{
|
|
... various definitions and the actions in here ...
|
|
}
|
|
|
|
.fi
|
|
(If your environment supports function prototypes, then it will
|
|
be "int yylex( void )".) This definition may be changed by defining
|
|
the "YY_DECL" macro.
|
|
For example, you could use:
|
|
.nf
|
|
|
|
#define YY_DECL float lexscan( a, b ) float a, b;
|
|
|
|
.fi
|
|
to give the scanning routine the name
|
|
.I lexscan,
|
|
returning a float, and taking two floats as arguments.
|
|
Note that
|
|
if you give arguments to the scanning routine using a
|
|
K\*[Am]R-style/non-prototyped function declaration, you must terminate
|
|
the definition with a semi-colon (;).
|
|
.PP
|
|
Whenever
|
|
.B yylex()
|
|
is called, it scans tokens from the global input file
|
|
.I yyin
|
|
(which defaults to stdin).
|
|
It continues until it either reaches
|
|
an end-of-file (at which point it returns the value 0) or
|
|
one of its actions executes a
|
|
.I return
|
|
statement.
|
|
.PP
|
|
If the scanner reaches an end-of-file, subsequent calls are undefined
|
|
unless either
|
|
.I yyin
|
|
is pointed at a new input file (in which case scanning continues from
|
|
that file), or
|
|
.B yyrestart()
|
|
is called.
|
|
.B yyrestart()
|
|
takes one argument, a
|
|
.B FILE *
|
|
pointer (which can be nil, if you've set up
|
|
.B YY_INPUT
|
|
to scan from a source other than
|
|
.I yyin),
|
|
and initializes
|
|
.I yyin
|
|
for scanning from that file.
|
|
Essentially there is no difference between
|
|
just assigning
|
|
.I yyin
|
|
to a new input file or using
|
|
.B yyrestart()
|
|
to do so; the latter is available for compatibility with previous versions
|
|
of
|
|
.I flex,
|
|
and because it can be used to switch input files in the middle of scanning.
|
|
It can also be used to throw away the current input buffer, by calling
|
|
it with an argument of
|
|
.I yyin;
|
|
but better is to use
|
|
.B YY_FLUSH_BUFFER
|
|
(see above).
|
|
Note that
|
|
.B yyrestart()
|
|
does
|
|
.I not
|
|
reset the start condition to
|
|
.B INITIAL
|
|
(see Start Conditions, below).
|
|
.PP
|
|
If
|
|
.B yylex()
|
|
stops scanning due to executing a
|
|
.I return
|
|
statement in one of the actions, the scanner may then be called again and it
|
|
will resume scanning where it left off.
|
|
.PP
|
|
By default (and for purposes of efficiency), the scanner uses
|
|
block-reads rather than simple
|
|
.I getc()
|
|
calls to read characters from
|
|
.I yyin.
|
|
The nature of how it gets its input can be controlled by defining the
|
|
.B YY_INPUT
|
|
macro.
|
|
YY_INPUT's calling sequence is "YY_INPUT(buf,result,max_size)".
|
|
Its action is to place up to
|
|
.I max_size
|
|
characters in the character array
|
|
.I buf
|
|
and return in the integer variable
|
|
.I result
|
|
either the
|
|
number of characters read or the constant YY_NULL (0 on Unix systems)
|
|
to indicate EOF.
|
|
The default YY_INPUT reads from the
|
|
global file-pointer "yyin".
|
|
.PP
|
|
A sample definition of YY_INPUT (in the definitions
|
|
section of the input file):
|
|
.nf
|
|
|
|
%{
|
|
#define YY_INPUT(buf,result,max_size) \\
|
|
{ \\
|
|
int c = getchar(); \\
|
|
result = (c == EOF) ? YY_NULL : (buf[0] = c, 1); \\
|
|
}
|
|
%}
|
|
|
|
.fi
|
|
This definition will change the input processing to occur
|
|
one character at a time.
|
|
.PP
|
|
When the scanner receives an end-of-file indication from YY_INPUT,
|
|
it then checks the
|
|
.B yywrap()
|
|
function.
|
|
If
|
|
.B yywrap()
|
|
returns false (zero), then it is assumed that the
|
|
function has gone ahead and set up
|
|
.I yyin
|
|
to point to another input file, and scanning continues.
|
|
If it returns
|
|
true (non-zero), then the scanner terminates, returning 0 to its
|
|
caller.
|
|
Note that in either case, the start condition remains unchanged;
|
|
it does
|
|
.I not
|
|
revert to
|
|
.B INITIAL.
|
|
.PP
|
|
If you do not supply your own version of
|
|
.B yywrap(),
|
|
then you must either use
|
|
.B %option noyywrap
|
|
(in which case the scanner behaves as though
|
|
.B yywrap()
|
|
returned 1), or you must link with
|
|
.B \-lfl
|
|
to obtain the default version of the routine, which always returns 1.
|
|
.PP
|
|
Three routines are available for scanning from in-memory buffers rather
|
|
than files:
|
|
.B yy_scan_string(), yy_scan_bytes(),
|
|
and
|
|
.B yy_scan_buffer().
|
|
See the discussion of them below in the section Multiple Input Buffers.
|
|
.PP
|
|
The scanner writes its
|
|
.B ECHO
|
|
output to the
|
|
.I yyout
|
|
global (default, stdout), which may be redefined by the user simply
|
|
by assigning it to some other
|
|
.B FILE
|
|
pointer.
|
|
.SH START CONDITIONS
|
|
.I flex
|
|
provides a mechanism for conditionally activating rules.
|
|
Any rule
|
|
whose pattern is prefixed with "\*[Lt]sc\*[Gt]" will only be active when
|
|
the scanner is in the start condition named "sc".
|
|
For example,
|
|
.nf
|
|
|
|
\*[Lt]STRING\*[Gt][^"]* { /* eat up the string body ... */
|
|
...
|
|
}
|
|
|
|
.fi
|
|
will be active only when the scanner is in the "STRING" start
|
|
condition, and
|
|
.nf
|
|
|
|
\*[Lt]INITIAL,STRING,QUOTE\*[Gt]\\. { /* handle an escape ... */
|
|
...
|
|
}
|
|
|
|
.fi
|
|
will be active only when the current start condition is
|
|
either "INITIAL", "STRING", or "QUOTE".
|
|
.PP
|
|
Start conditions
|
|
are declared in the definitions (first) section of the input
|
|
using unindented lines beginning with either
|
|
.B %s
|
|
or
|
|
.B %x
|
|
followed by a list of names.
|
|
The former declares
|
|
.I inclusive
|
|
start conditions, the latter
|
|
.I exclusive
|
|
start conditions.
|
|
A start condition is activated using the
|
|
.B BEGIN
|
|
action.
|
|
Until the next
|
|
.B BEGIN
|
|
action is executed, rules with the given start
|
|
condition will be active and
|
|
rules with other start conditions will be inactive.
|
|
If the start condition is
|
|
.I inclusive,
|
|
then rules with no start conditions at all will also be active.
|
|
If it is
|
|
.I exclusive,
|
|
then
|
|
.I only
|
|
rules qualified with the start condition will be active.
|
|
A set of rules contingent on the same exclusive start condition
|
|
describe a scanner which is independent of any of the other rules in the
|
|
.I flex
|
|
input.
|
|
Because of this,
|
|
exclusive start conditions make it easy to specify "mini-scanners"
|
|
which scan portions of the input that are syntactically different
|
|
from the rest (e.g., comments).
|
|
.PP
|
|
If the distinction between inclusive and exclusive start conditions
|
|
is still a little vague, here's a simple example illustrating the
|
|
connection between the two.
|
|
The set of rules:
|
|
.nf
|
|
|
|
%s example
|
|
%%
|
|
|
|
\*[Lt]example\*[Gt]foo do_something();
|
|
|
|
bar something_else();
|
|
|
|
.fi
|
|
is equivalent to
|
|
.nf
|
|
|
|
%x example
|
|
%%
|
|
|
|
\*[Lt]example\*[Gt]foo do_something();
|
|
|
|
\*[Lt]INITIAL,example\*[Gt]bar something_else();
|
|
|
|
.fi
|
|
Without the
|
|
.B \*[Lt]INITIAL,example\*[Gt]
|
|
qualifier, the
|
|
.I bar
|
|
pattern in the second example wouldn't be active (i.e., couldn't match)
|
|
when in start condition
|
|
.B example.
|
|
If we just used
|
|
.B \*[Lt]example\*[Gt]
|
|
to qualify
|
|
.I bar,
|
|
though, then it would only be active in
|
|
.B example
|
|
and not in
|
|
.B INITIAL,
|
|
while in the first example it's active in both, because in the first
|
|
example the
|
|
.B example
|
|
startion condition is an
|
|
.I inclusive
|
|
.B (%s)
|
|
start condition.
|
|
.PP
|
|
Also note that the special start-condition specifier
|
|
.B \*[Lt]*\*[Gt]
|
|
matches every start condition.
|
|
Thus, the above example could also have been written;
|
|
.nf
|
|
|
|
%x example
|
|
%%
|
|
|
|
\*[Lt]example\*[Gt]foo do_something();
|
|
|
|
\*[Lt]*\*[Gt]bar something_else();
|
|
|
|
.fi
|
|
.PP
|
|
The default rule (to
|
|
.B ECHO
|
|
any unmatched character) remains active in start conditions.
|
|
It
|
|
is equivalent to:
|
|
.nf
|
|
|
|
\*[Lt]*\*[Gt].|\\n ECHO;
|
|
|
|
.fi
|
|
.PP
|
|
.B BEGIN(0)
|
|
returns to the original state where only the rules with
|
|
no start conditions are active.
|
|
This state can also be
|
|
referred to as the start-condition "INITIAL", so
|
|
.B BEGIN(INITIAL)
|
|
is equivalent to
|
|
.B BEGIN(0).
|
|
(The parentheses around the start condition name are not required but
|
|
are considered good style.)
|
|
.PP
|
|
.B BEGIN
|
|
actions can also be given as indented code at the beginning
|
|
of the rules section.
|
|
For example, the following will cause
|
|
the scanner to enter the "SPECIAL" start condition whenever
|
|
.B yylex()
|
|
is called and the global variable
|
|
.I enter_special
|
|
is true:
|
|
.nf
|
|
|
|
int enter_special;
|
|
|
|
%x SPECIAL
|
|
%%
|
|
if ( enter_special )
|
|
BEGIN(SPECIAL);
|
|
|
|
\*[Lt]SPECIAL\*[Gt]blahblahblah
|
|
...more rules follow...
|
|
|
|
.fi
|
|
.PP
|
|
To illustrate the uses of start conditions,
|
|
here is a scanner which provides two different interpretations
|
|
of a string like "123.456".
|
|
By default it will treat it as
|
|
three tokens, the integer "123", a dot ('.'), and the integer "456".
|
|
But if the string is preceded earlier in the line by the string
|
|
"expect-floats"
|
|
it will treat it as a single token, the floating-point number
|
|
123.456:
|
|
.nf
|
|
|
|
%{
|
|
#include \*[Lt]math.h\*[Gt]
|
|
%}
|
|
%s expect
|
|
|
|
%%
|
|
expect-floats BEGIN(expect);
|
|
|
|
\*[Lt]expect\*[Gt][0-9]+"."[0-9]+ {
|
|
printf( "found a float, = %f\\n",
|
|
atof( yytext ) );
|
|
}
|
|
\*[Lt]expect\*[Gt]\\n {
|
|
/* that's the end of the line, so
|
|
* we need another "expect-number"
|
|
* before we'll recognize any more
|
|
* numbers
|
|
*/
|
|
BEGIN(INITIAL);
|
|
}
|
|
|
|
[0-9]+ {
|
|
printf( "found an integer, = %d\\n",
|
|
atoi( yytext ) );
|
|
}
|
|
|
|
"." printf( "found a dot\\n" );
|
|
|
|
.fi
|
|
Here is a scanner which recognizes (and discards) C comments while
|
|
maintaining a count of the current input line.
|
|
.nf
|
|
|
|
%x comment
|
|
%%
|
|
int line_num = 1;
|
|
|
|
"/*" BEGIN(comment);
|
|
|
|
\*[Lt]comment\*[Gt][^*\\n]* /* eat anything that's not a '*' */
|
|
\*[Lt]comment\*[Gt]"*"+[^*/\\n]* /* eat up '*'s not followed by '/'s */
|
|
\*[Lt]comment\*[Gt]\\n ++line_num;
|
|
\*[Lt]comment\*[Gt]"*"+"/" BEGIN(INITIAL);
|
|
|
|
.fi
|
|
This scanner goes to a bit of trouble to match as much
|
|
text as possible with each rule.
|
|
In general, when attempting to write
|
|
a high-speed scanner try to match as much possible in each rule, as
|
|
it's a big win.
|
|
.PP
|
|
Note that start-conditions names are really integer values and
|
|
can be stored as such.
|
|
Thus, the above could be extended in the
|
|
following fashion:
|
|
.nf
|
|
|
|
%x comment foo
|
|
%%
|
|
int line_num = 1;
|
|
int comment_caller;
|
|
|
|
"/*" {
|
|
comment_caller = INITIAL;
|
|
BEGIN(comment);
|
|
}
|
|
|
|
...
|
|
|
|
\*[Lt]foo\*[Gt]"/*" {
|
|
comment_caller = foo;
|
|
BEGIN(comment);
|
|
}
|
|
|
|
\*[Lt]comment\*[Gt][^*\\n]* /* eat anything that's not a '*' */
|
|
\*[Lt]comment\*[Gt]"*"+[^*/\\n]* /* eat up '*'s not followed by '/'s */
|
|
\*[Lt]comment\*[Gt]\\n ++line_num;
|
|
\*[Lt]comment\*[Gt]"*"+"/" BEGIN(comment_caller);
|
|
|
|
.fi
|
|
Furthermore, you can access the current start condition using
|
|
the integer-valued
|
|
.B YY_START
|
|
macro.
|
|
For example, the above assignments to
|
|
.I comment_caller
|
|
could instead be written
|
|
.nf
|
|
|
|
comment_caller = YY_START;
|
|
|
|
.fi
|
|
Flex provides
|
|
.B YYSTATE
|
|
as an alias for
|
|
.B YY_START
|
|
(since that is what's used by AT\*[Am]T
|
|
.I lex).
|
|
.PP
|
|
Note that start conditions do not have their own name-space; %s's and %x's
|
|
declare names in the same fashion as #define's.
|
|
.PP
|
|
Finally, here's an example of how to match C-style quoted strings using
|
|
exclusive start conditions, including expanded escape sequences (but
|
|
not including checking for a string that's too long):
|
|
.nf
|
|
|
|
%x str
|
|
|
|
%%
|
|
char string_buf[MAX_STR_CONST];
|
|
char *string_buf_ptr;
|
|
|
|
|
|
\\" string_buf_ptr = string_buf; BEGIN(str);
|
|
|
|
\*[Lt]str\*[Gt]\\" { /* saw closing quote - all done */
|
|
BEGIN(INITIAL);
|
|
*string_buf_ptr = '\\0';
|
|
/* return string constant token type and
|
|
* value to parser
|
|
*/
|
|
}
|
|
|
|
\*[Lt]str\*[Gt]\\n {
|
|
/* error - unterminated string constant */
|
|
/* generate error message */
|
|
}
|
|
|
|
\*[Lt]str\*[Gt]\\\\[0-7]{1,3} {
|
|
/* octal escape sequence */
|
|
int result;
|
|
|
|
(void) sscanf( yytext + 1, "%o", \*[Am]result );
|
|
|
|
if ( result \*[Gt] 0xff )
|
|
/* error, constant is out-of-bounds */
|
|
|
|
*string_buf_ptr++ = result;
|
|
}
|
|
|
|
\*[Lt]str\*[Gt]\\\\[0-9]+ {
|
|
/* generate error - bad escape sequence; something
|
|
* like '\\48' or '\\0777777'
|
|
*/
|
|
}
|
|
|
|
\*[Lt]str\*[Gt]\\\\n *string_buf_ptr++ = '\\n';
|
|
\*[Lt]str\*[Gt]\\\\t *string_buf_ptr++ = '\\t';
|
|
\*[Lt]str\*[Gt]\\\\r *string_buf_ptr++ = '\\r';
|
|
\*[Lt]str\*[Gt]\\\\b *string_buf_ptr++ = '\\b';
|
|
\*[Lt]str\*[Gt]\\\\f *string_buf_ptr++ = '\\f';
|
|
|
|
\*[Lt]str\*[Gt]\\\\(.|\\n) *string_buf_ptr++ = yytext[1];
|
|
|
|
\*[Lt]str\*[Gt][^\\\\\\n\\"]+ {
|
|
char *yptr = yytext;
|
|
|
|
while ( *yptr )
|
|
*string_buf_ptr++ = *yptr++;
|
|
}
|
|
|
|
.fi
|
|
.PP
|
|
Often, such as in some of the examples above, you wind up writing a
|
|
whole bunch of rules all preceded by the same start condition(s).
|
|
Flex makes this a little easier and cleaner by introducing a notion of
|
|
start condition
|
|
.I scope.
|
|
A start condition scope is begun with:
|
|
.nf
|
|
|
|
\*[Lt]SCs\*[Gt]{
|
|
|
|
.fi
|
|
where
|
|
.I SCs
|
|
is a list of one or more start conditions.
|
|
Inside the start condition
|
|
scope, every rule automatically has the prefix
|
|
.I \*[Lt]SCs\*[Gt]
|
|
applied to it, until a
|
|
.I '}'
|
|
which matches the initial
|
|
.I '{'.
|
|
So, for example,
|
|
.nf
|
|
|
|
\*[Lt]ESC\*[Gt]{
|
|
"\\\\n" return '\\n';
|
|
"\\\\r" return '\\r';
|
|
"\\\\f" return '\\f';
|
|
"\\\\0" return '\\0';
|
|
}
|
|
|
|
.fi
|
|
is equivalent to:
|
|
.nf
|
|
|
|
\*[Lt]ESC\*[Gt]"\\\\n" return '\\n';
|
|
\*[Lt]ESC\*[Gt]"\\\\r" return '\\r';
|
|
\*[Lt]ESC\*[Gt]"\\\\f" return '\\f';
|
|
\*[Lt]ESC\*[Gt]"\\\\0" return '\\0';
|
|
|
|
.fi
|
|
Start condition scopes may be nested.
|
|
.PP
|
|
Three routines are available for manipulating stacks of start conditions:
|
|
.TP
|
|
.B void yy_push_state(int new_state)
|
|
pushes the current start condition onto the top of the start condition
|
|
stack and switches to
|
|
.I new_state
|
|
as though you had used
|
|
.B BEGIN new_state
|
|
(recall that start condition names are also integers).
|
|
.TP
|
|
.B void yy_pop_state()
|
|
pops the top of the stack and switches to it via
|
|
.B BEGIN.
|
|
.TP
|
|
.B int yy_top_state()
|
|
returns the top of the stack without altering the stack's contents.
|
|
.PP
|
|
The start condition stack grows dynamically and so has no built-in
|
|
size limitation.
|
|
If memory is exhausted, program execution aborts.
|
|
.PP
|
|
To use start condition stacks, your scanner must include a
|
|
.B %option stack
|
|
directive (see Options below).
|
|
.SH MULTIPLE INPUT BUFFERS
|
|
Some scanners (such as those which support "include" files)
|
|
require reading from several input streams.
|
|
As
|
|
.I flex
|
|
scanners do a large amount of buffering, one cannot control
|
|
where the next input will be read from by simply writing a
|
|
.B YY_INPUT
|
|
which is sensitive to the scanning context.
|
|
.B YY_INPUT
|
|
is only called when the scanner reaches the end of its buffer, which
|
|
may be a long time after scanning a statement such as an "include"
|
|
which requires switching the input source.
|
|
.PP
|
|
To negotiate these sorts of problems,
|
|
.I flex
|
|
provides a mechanism for creating and switching between multiple
|
|
input buffers.
|
|
An input buffer is created by using:
|
|
.nf
|
|
|
|
YY_BUFFER_STATE yy_create_buffer( FILE *file, int size )
|
|
|
|
.fi
|
|
which takes a
|
|
.I FILE
|
|
pointer and a size and creates a buffer associated with the given
|
|
file and large enough to hold
|
|
.I size
|
|
characters (when in doubt, use
|
|
.B YY_BUF_SIZE
|
|
for the size).
|
|
It returns a
|
|
.B YY_BUFFER_STATE
|
|
handle, which may then be passed to other routines (see below).
|
|
The
|
|
.B YY_BUFFER_STATE
|
|
type is a pointer to an opaque
|
|
.B struct yy_buffer_state
|
|
structure, so you may safely initialize YY_BUFFER_STATE variables to
|
|
.B ((YY_BUFFER_STATE) 0)
|
|
if you wish, and also refer to the opaque structure in order to
|
|
correctly declare input buffers in source files other than that
|
|
of your scanner.
|
|
Note that the
|
|
.I FILE
|
|
pointer in the call to
|
|
.B yy_create_buffer
|
|
is only used as the value of
|
|
.I yyin
|
|
seen by
|
|
.B YY_INPUT;
|
|
if you redefine
|
|
.B YY_INPUT
|
|
so it no longer uses
|
|
.I yyin,
|
|
then you can safely pass a nil
|
|
.I FILE
|
|
pointer to
|
|
.B yy_create_buffer.
|
|
You select a particular buffer to scan from using:
|
|
.nf
|
|
|
|
void yy_switch_to_buffer( YY_BUFFER_STATE new_buffer )
|
|
|
|
.fi
|
|
switches the scanner's input buffer so subsequent tokens will
|
|
come from
|
|
.I new_buffer.
|
|
Note that
|
|
.B yy_switch_to_buffer()
|
|
may be used by yywrap() to set things up for continued scanning, instead
|
|
of opening a new file and pointing
|
|
.I yyin
|
|
at it.
|
|
Note also that switching input sources via either
|
|
.B yy_switch_to_buffer()
|
|
or
|
|
.B yywrap()
|
|
does
|
|
.I not
|
|
change the start condition.
|
|
.nf
|
|
|
|
void yy_delete_buffer( YY_BUFFER_STATE buffer )
|
|
|
|
.fi
|
|
is used to reclaim the storage associated with a buffer.
|
|
(
|
|
.B buffer
|
|
can be nil, in which case the routine does nothing.)
|
|
You can also clear the current contents of a buffer using:
|
|
.nf
|
|
|
|
void yy_flush_buffer( YY_BUFFER_STATE buffer )
|
|
|
|
.fi
|
|
This function discards the buffer's contents,
|
|
so the next time the scanner attempts to match a token from the
|
|
buffer, it will first fill the buffer anew using
|
|
.B YY_INPUT.
|
|
.PP
|
|
.B yy_new_buffer()
|
|
is an alias for
|
|
.B yy_create_buffer(),
|
|
provided for compatibility with the C++ use of
|
|
.I new
|
|
and
|
|
.I delete
|
|
for creating and destroying dynamic objects.
|
|
.PP
|
|
Finally, the
|
|
.B YY_CURRENT_BUFFER
|
|
macro returns a
|
|
.B YY_BUFFER_STATE
|
|
handle to the current buffer.
|
|
.PP
|
|
Here is an example of using these features for writing a scanner
|
|
which expands include files (the
|
|
.B \*[Lt]\*[Lt]EOF\*[Gt]\*[Gt]
|
|
feature is discussed below):
|
|
.nf
|
|
|
|
/* the "incl" state is used for picking up the name
|
|
* of an include file
|
|
*/
|
|
%x incl
|
|
|
|
%{
|
|
#define MAX_INCLUDE_DEPTH 10
|
|
YY_BUFFER_STATE include_stack[MAX_INCLUDE_DEPTH];
|
|
int include_stack_ptr = 0;
|
|
%}
|
|
|
|
%%
|
|
include BEGIN(incl);
|
|
|
|
[a-z]+ ECHO;
|
|
[^a-z\\n]*\\n? ECHO;
|
|
|
|
\*[Lt]incl\*[Gt][ \\t]* /* eat the whitespace */
|
|
\*[Lt]incl\*[Gt][^ \\t\\n]+ { /* got the include file name */
|
|
if ( include_stack_ptr \*[Ge] MAX_INCLUDE_DEPTH )
|
|
{
|
|
fprintf( stderr, "Includes nested too deeply" );
|
|
exit( 1 );
|
|
}
|
|
|
|
include_stack[include_stack_ptr++] =
|
|
YY_CURRENT_BUFFER;
|
|
|
|
yyin = fopen( yytext, "r" );
|
|
|
|
if ( ! yyin )
|
|
error( ... );
|
|
|
|
yy_switch_to_buffer(
|
|
yy_create_buffer( yyin, YY_BUF_SIZE ) );
|
|
|
|
BEGIN(INITIAL);
|
|
}
|
|
|
|
\*[Lt]\*[Lt]EOF\*[Gt]\*[Gt] {
|
|
if ( --include_stack_ptr \*[Lt] 0 )
|
|
{
|
|
yyterminate();
|
|
}
|
|
|
|
else
|
|
{
|
|
yy_delete_buffer( YY_CURRENT_BUFFER );
|
|
yy_switch_to_buffer(
|
|
include_stack[include_stack_ptr] );
|
|
}
|
|
}
|
|
|
|
.fi
|
|
Three routines are available for setting up input buffers for
|
|
scanning in-memory strings instead of files.
|
|
All of them create
|
|
a new input buffer for scanning the string, and return a corresponding
|
|
.B YY_BUFFER_STATE
|
|
handle (which you should delete with
|
|
.B yy_delete_buffer()
|
|
when done with it).
|
|
They also switch to the new buffer using
|
|
.B yy_switch_to_buffer(),
|
|
so the next call to
|
|
.B yylex()
|
|
will start scanning the string.
|
|
.TP
|
|
.B yy_scan_string(const char *str)
|
|
scans a NUL-terminated string.
|
|
.TP
|
|
.B yy_scan_bytes(const char *bytes, int len)
|
|
scans
|
|
.I len
|
|
bytes (including possibly NUL's)
|
|
starting at location
|
|
.I bytes.
|
|
.PP
|
|
Note that both of these functions create and scan a
|
|
.I copy
|
|
of the string or bytes.
|
|
(This may be desirable, since
|
|
.B yylex()
|
|
modifies the contents of the buffer it is scanning.) You can avoid the
|
|
copy by using:
|
|
.TP
|
|
.B yy_scan_buffer(char *base, yy_size_t size)
|
|
which scans in place the buffer starting at
|
|
.I base,
|
|
consisting of
|
|
.I size
|
|
bytes, the last two bytes of which
|
|
.I must
|
|
be
|
|
.B YY_END_OF_BUFFER_CHAR
|
|
(ASCII NUL).
|
|
These last two bytes are not scanned; thus, scanning
|
|
consists of
|
|
.B base[0]
|
|
through
|
|
.B base[size-2],
|
|
inclusive.
|
|
.IP
|
|
If you fail to set up
|
|
.I base
|
|
in this manner (i.e., forget the final two
|
|
.B YY_END_OF_BUFFER_CHAR
|
|
bytes), then
|
|
.B yy_scan_buffer()
|
|
returns a nil pointer instead of creating a new input buffer.
|
|
.IP
|
|
The type
|
|
.B yy_size_t
|
|
is an integral type to which you can cast an integer expression
|
|
reflecting the size of the buffer.
|
|
.SH END-OF-FILE RULES
|
|
The special rule "\*[Lt]\*[Lt]EOF\*[Gt]\*[Gt]" indicates
|
|
actions which are to be taken when an end-of-file is
|
|
encountered and yywrap() returns non-zero (i.e., indicates
|
|
no further files to process).
|
|
The action must finish
|
|
by doing one of four things:
|
|
.IP -
|
|
assigning
|
|
.I yyin
|
|
to a new input file (in previous versions of flex, after doing the
|
|
assignment you had to call the special action
|
|
.B YY_NEW_FILE;
|
|
this is no longer necessary);
|
|
.IP -
|
|
executing a
|
|
.I return
|
|
statement;
|
|
.IP -
|
|
executing the special
|
|
.B yyterminate()
|
|
action;
|
|
.IP -
|
|
or, switching to a new buffer using
|
|
.B yy_switch_to_buffer()
|
|
as shown in the example above.
|
|
.PP
|
|
\*[Lt]\*[Lt]EOF\*[Gt]\*[Gt] rules may not be used with other
|
|
patterns; they may only be qualified with a list of start
|
|
conditions.
|
|
If an unqualified \*[Lt]\*[Lt]EOF\*[Gt]\*[Gt] rule is given, it
|
|
applies to
|
|
.I all
|
|
start conditions which do not already have \*[Lt]\*[Lt]EOF\*[Gt]\*[Gt] actions.
|
|
To
|
|
specify an \*[Lt]\*[Lt]EOF\*[Gt]\*[Gt] rule for only the initial start condition, use
|
|
.nf
|
|
|
|
\*[Lt]INITIAL\*[Gt]\*[Lt]\*[Lt]EOF\*[Gt]\*[Gt]
|
|
|
|
.fi
|
|
.PP
|
|
These rules are useful for catching things like unclosed comments.
|
|
An example:
|
|
.nf
|
|
|
|
%x quote
|
|
%%
|
|
|
|
...other rules for dealing with quotes...
|
|
|
|
\*[Lt]quote\*[Gt]\*[Lt]\*[Lt]EOF\*[Gt]\*[Gt] {
|
|
error( "unterminated quote" );
|
|
yyterminate();
|
|
}
|
|
\*[Lt]\*[Lt]EOF\*[Gt]\*[Gt] {
|
|
if ( *++filelist )
|
|
yyin = fopen( *filelist, "r" );
|
|
else
|
|
yyterminate();
|
|
}
|
|
|
|
.fi
|
|
.SH MISCELLANEOUS MACROS
|
|
The macro
|
|
.B YY_USER_ACTION
|
|
can be defined to provide an action
|
|
which is always executed prior to the matched rule's action.
|
|
For example,
|
|
it could be #define'd to call a routine to convert yytext to lower-case.
|
|
When
|
|
.B YY_USER_ACTION
|
|
is invoked, the variable
|
|
.I yy_act
|
|
gives the number of the matched rule (rules are numbered starting with 1).
|
|
Suppose you want to profile how often each of your rules is matched.
|
|
The following would do the trick:
|
|
.nf
|
|
|
|
#define YY_USER_ACTION ++ctr[yy_act]
|
|
|
|
.fi
|
|
where
|
|
.I ctr
|
|
is an array to hold the counts for the different rules.
|
|
Note that the macro
|
|
.B YY_NUM_RULES
|
|
gives the total number of rules (including the default rule, even if
|
|
you use
|
|
.B \-s),
|
|
so a correct declaration for
|
|
.I ctr
|
|
is:
|
|
.nf
|
|
|
|
int ctr[YY_NUM_RULES];
|
|
|
|
.fi
|
|
.PP
|
|
The macro
|
|
.B YY_USER_INIT
|
|
may be defined to provide an action which is always executed before
|
|
the first scan (and before the scanner's internal initializations are done).
|
|
For example, it could be used to call a routine to read
|
|
in a data table or open a logging file.
|
|
.PP
|
|
The macro
|
|
.B yy_set_interactive(is_interactive)
|
|
can be used to control whether the current buffer is considered
|
|
.I interactive.
|
|
An interactive buffer is processed more slowly,
|
|
but must be used when the scanner's input source is indeed
|
|
interactive to avoid problems due to waiting to fill buffers
|
|
(see the discussion of the
|
|
.B \-I
|
|
flag below).
|
|
A non-zero value
|
|
in the macro invocation marks the buffer as interactive, a zero
|
|
value as non-interactive.
|
|
Note that use of this macro overrides
|
|
.B %option always-interactive
|
|
or
|
|
.B %option never-interactive
|
|
(see Options below).
|
|
.B yy_set_interactive()
|
|
must be invoked prior to beginning to scan the buffer that is
|
|
(or is not) to be considered interactive.
|
|
.PP
|
|
The macro
|
|
.B yy_set_bol(at_bol)
|
|
can be used to control whether the current buffer's scanning
|
|
context for the next token match is done as though at the
|
|
beginning of a line.
|
|
A non-zero macro argument makes rules anchored with
|
|
'^' active, while a zero argument makes '^' rules inactive.
|
|
.PP
|
|
The macro
|
|
.B YY_AT_BOL()
|
|
returns true if the next token scanned from the current buffer
|
|
will have '^' rules active, false otherwise.
|
|
.PP
|
|
In the generated scanner, the actions are all gathered in one large
|
|
switch statement and separated using
|
|
.B YY_BREAK,
|
|
which may be redefined.
|
|
By default, it is simply a "break", to separate
|
|
each rule's action from the following rule's.
|
|
Redefining
|
|
.B YY_BREAK
|
|
allows, for example, C++ users to
|
|
#define YY_BREAK to do nothing (while being very careful that every
|
|
rule ends with a "break" or a "return"!) to avoid suffering from
|
|
unreachable statement warnings where because a rule's action ends with
|
|
"return", the
|
|
.B YY_BREAK
|
|
is inaccessible.
|
|
.SH VALUES AVAILABLE TO THE USER
|
|
This section summarizes the various values available to the user
|
|
in the rule actions.
|
|
.IP -
|
|
.B char *yytext
|
|
holds the text of the current token.
|
|
It may be modified but not lengthened
|
|
(you cannot append characters to the end).
|
|
.IP
|
|
If the special directive
|
|
.B %array
|
|
appears in the first section of the scanner description, then
|
|
.B yytext
|
|
is instead declared
|
|
.B char yytext[YYLMAX],
|
|
where
|
|
.B YYLMAX
|
|
is a macro definition that you can redefine in the first section
|
|
if you don't like the default value (generally 8KB).
|
|
Using
|
|
.B %array
|
|
results in somewhat slower scanners, but the value of
|
|
.B yytext
|
|
becomes immune to calls to
|
|
.I input()
|
|
and
|
|
.I unput(),
|
|
which potentially destroy its value when
|
|
.B yytext
|
|
is a character pointer.
|
|
The opposite of
|
|
.B %array
|
|
is
|
|
.B %pointer,
|
|
which is the default.
|
|
.IP
|
|
You cannot use
|
|
.B %array
|
|
when generating C++ scanner classes
|
|
(the
|
|
.B \-+
|
|
flag).
|
|
.IP -
|
|
.B int yyleng
|
|
holds the length of the current token.
|
|
.IP -
|
|
.B FILE *yyin
|
|
is the file which by default
|
|
.I flex
|
|
reads from.
|
|
It may be redefined but doing so only makes sense before
|
|
scanning begins or after an EOF has been encountered.
|
|
Changing it in the midst of scanning will have unexpected results since
|
|
.I flex
|
|
buffers its input; use
|
|
.B yyrestart()
|
|
instead.
|
|
Once scanning terminates because an end-of-file
|
|
has been seen, you can assign
|
|
.I yyin
|
|
at the new input file and then call the scanner again to continue scanning.
|
|
.IP -
|
|
.B void yyrestart( FILE *new_file )
|
|
may be called to point
|
|
.I yyin
|
|
at the new input file.
|
|
The switch-over to the new file is immediate
|
|
(any previously buffered-up input is lost).
|
|
Note that calling
|
|
.B yyrestart()
|
|
with
|
|
.I yyin
|
|
as an argument thus throws away the current input buffer and continues
|
|
scanning the same input file.
|
|
.IP -
|
|
.B FILE *yyout
|
|
is the file to which
|
|
.B ECHO
|
|
actions are done.
|
|
It can be reassigned by the user.
|
|
.IP -
|
|
.B YY_CURRENT_BUFFER
|
|
returns a
|
|
.B YY_BUFFER_STATE
|
|
handle to the current buffer.
|
|
.IP -
|
|
.B YY_START
|
|
returns an integer value corresponding to the current start
|
|
condition.
|
|
You can subsequently use this value with
|
|
.B BEGIN
|
|
to return to that start condition.
|
|
.SH INTERFACING WITH YACC
|
|
One of the main uses of
|
|
.I flex
|
|
is as a companion to the
|
|
.I yacc
|
|
parser-generator.
|
|
.I yacc
|
|
parsers expect to call a routine named
|
|
.B yylex()
|
|
to find the next input token.
|
|
The routine is supposed to
|
|
return the type of the next token as well as putting any associated
|
|
value in the global
|
|
.B yylval.
|
|
To use
|
|
.I flex
|
|
with
|
|
.I yacc,
|
|
one specifies the
|
|
.B \-d
|
|
option to
|
|
.I yacc
|
|
to instruct it to generate the file
|
|
.B y.tab.h
|
|
containing definitions of all the
|
|
.B %tokens
|
|
appearing in the
|
|
.I yacc
|
|
input.
|
|
This file is then included in the
|
|
.I flex
|
|
scanner.
|
|
For example, if one of the tokens is "TOK_NUMBER",
|
|
part of the scanner might look like:
|
|
.nf
|
|
|
|
%{
|
|
#include "y.tab.h"
|
|
%}
|
|
|
|
%%
|
|
|
|
[0-9]+ yylval = atoi( yytext ); return TOK_NUMBER;
|
|
|
|
.fi
|
|
.SH OPTIONS
|
|
.I flex
|
|
has the following options:
|
|
.TP
|
|
.B \-b
|
|
Generate backing-up information to
|
|
.I lex.backup.
|
|
This is a list of scanner states which require backing up
|
|
and the input characters on which they do so.
|
|
By adding rules one
|
|
can remove backing-up states.
|
|
If
|
|
.I all
|
|
backing-up states are eliminated and
|
|
.B \-Cf
|
|
or
|
|
.B \-CF
|
|
is used, the generated scanner will run faster (see the
|
|
.B \-p
|
|
flag).
|
|
Only users who wish to squeeze every last cycle out of their
|
|
scanners need worry about this option.
|
|
(See the section on Performance Considerations below.)
|
|
.TP
|
|
.B \-c
|
|
is a do-nothing, deprecated option included for POSIX compliance.
|
|
.TP
|
|
.B \-d
|
|
makes the generated scanner run in
|
|
.I debug
|
|
mode.
|
|
Whenever a pattern is recognized and the global
|
|
.B yy_flex_debug
|
|
is non-zero (which is the default),
|
|
the scanner will write to
|
|
.I stderr
|
|
a line of the form:
|
|
.nf
|
|
|
|
--accepting rule at line 53 ("the matched text")
|
|
|
|
.fi
|
|
The line number refers to the location of the rule in the file
|
|
defining the scanner (i.e., the file that was fed to flex).
|
|
Messages are also generated when the scanner backs up, accepts the
|
|
default rule, reaches the end of its input buffer (or encounters
|
|
a NUL; at this point, the two look the same as far as the scanner's concerned),
|
|
or reaches an end-of-file.
|
|
.TP
|
|
.B \-f
|
|
specifies
|
|
.I fast scanner.
|
|
No table compression is done and stdio is bypassed.
|
|
The result is large but fast.
|
|
This option is equivalent to
|
|
.B \-Cfr
|
|
(see below).
|
|
.TP
|
|
.B \-h
|
|
generates a "help" summary of
|
|
.I flex's
|
|
options to
|
|
.I stdout
|
|
and then exits.
|
|
.B \-?
|
|
and
|
|
.B \-\-help
|
|
are synonyms for
|
|
.B \-h.
|
|
.TP
|
|
.B \-i
|
|
instructs
|
|
.I flex
|
|
to generate a
|
|
.I case-insensitive
|
|
scanner.
|
|
The case of letters given in the
|
|
.I flex
|
|
input patterns will
|
|
be ignored, and tokens in the input will be matched regardless of case.
|
|
The matched text given in
|
|
.I yytext
|
|
will have the preserved case (i.e., it will not be folded).
|
|
.TP
|
|
.B \-l
|
|
turns on maximum compatibility with the original AT\*[Am]T
|
|
.I lex
|
|
implementation.
|
|
Note that this does not mean
|
|
.I full
|
|
compatibility.
|
|
Use of this option costs a considerable amount of
|
|
performance, and it cannot be used with the
|
|
.B \-+, -f, -F, -Cf,
|
|
or
|
|
.B -CF
|
|
options.
|
|
For details on the compatibilities it provides, see the section
|
|
"Incompatibilities With Lex And POSIX" below.
|
|
This option also results
|
|
in the name
|
|
.B YY_FLEX_LEX_COMPAT
|
|
being #define'd in the generated scanner.
|
|
.TP
|
|
.B \-n
|
|
is another do-nothing, deprecated option included only for
|
|
POSIX compliance.
|
|
.TP
|
|
.B \-p
|
|
generates a performance report to stderr.
|
|
The report consists of comments regarding features of the
|
|
.I flex
|
|
input file which will cause a serious loss of performance in the resulting
|
|
scanner.
|
|
If you give the flag twice, you will also get comments regarding
|
|
features that lead to minor performance losses.
|
|
.IP
|
|
Note that the use of
|
|
.B REJECT,
|
|
.B %option yylineno,
|
|
and variable trailing context (see the Deficiencies / Bugs section below)
|
|
entails a substantial performance penalty; use of
|
|
.I yymore(),
|
|
the
|
|
.B ^
|
|
operator,
|
|
and the
|
|
.B \-I
|
|
flag entail minor performance penalties.
|
|
.TP
|
|
.B \-s
|
|
causes the
|
|
.I default rule
|
|
(that unmatched scanner input is echoed to
|
|
.I stdout)
|
|
to be suppressed.
|
|
If the scanner encounters input that does not
|
|
match any of its rules, it aborts with an error.
|
|
This option is
|
|
useful for finding holes in a scanner's rule set.
|
|
.TP
|
|
.B \-t
|
|
instructs
|
|
.I flex
|
|
to write the scanner it generates to standard output instead
|
|
of
|
|
.B lex.yy.c.
|
|
.TP
|
|
.B \-v
|
|
specifies that
|
|
.I flex
|
|
should write to
|
|
.I stderr
|
|
a summary of statistics regarding the scanner it generates.
|
|
Most of the statistics are meaningless to the casual
|
|
.I flex
|
|
user, but the first line identifies the version of
|
|
.I flex
|
|
(same as reported by
|
|
.B \-V),
|
|
and the next line the flags used when generating the scanner, including
|
|
those that are on by default.
|
|
.TP
|
|
.B \-w
|
|
suppresses warning messages.
|
|
.TP
|
|
.B \-B
|
|
instructs
|
|
.I flex
|
|
to generate a
|
|
.I batch
|
|
scanner, the opposite of
|
|
.I interactive
|
|
scanners generated by
|
|
.B \-I
|
|
(see below).
|
|
In general, you use
|
|
.B \-B
|
|
when you are
|
|
.I certain
|
|
that your scanner will never be used interactively, and you want to
|
|
squeeze a
|
|
.I little
|
|
more performance out of it.
|
|
If your goal is instead to squeeze out a
|
|
.I lot
|
|
more performance, you should be using the
|
|
.B \-Cf
|
|
or
|
|
.B \-CF
|
|
options (discussed below), which turn on
|
|
.B \-B
|
|
automatically anyway.
|
|
.TP
|
|
.B \-F
|
|
specifies that the
|
|
.ul
|
|
fast
|
|
scanner table representation should be used (and stdio
|
|
bypassed).
|
|
This representation is about as fast as the full table representation
|
|
.B (-f),
|
|
and for some sets of patterns will be considerably smaller (and for
|
|
others, larger).
|
|
In general, if the pattern set contains both "keywords"
|
|
and a catch-all, "identifier" rule, such as in the set:
|
|
.nf
|
|
|
|
"case" return TOK_CASE;
|
|
"switch" return TOK_SWITCH;
|
|
...
|
|
"default" return TOK_DEFAULT;
|
|
[a-z]+ return TOK_ID;
|
|
|
|
.fi
|
|
then you're better off using the full table representation.
|
|
If only
|
|
the "identifier" rule is present and you then use a hash table or some such
|
|
to detect the keywords, you're better off using
|
|
.B -F.
|
|
.IP
|
|
This option is equivalent to
|
|
.B \-CFr
|
|
(see below).
|
|
It cannot be used with
|
|
.B \-+.
|
|
.TP
|
|
.B \-I
|
|
instructs
|
|
.I flex
|
|
to generate an
|
|
.I interactive
|
|
scanner.
|
|
An interactive scanner is one that only looks ahead to decide
|
|
what token has been matched if it absolutely must.
|
|
It turns out that
|
|
always looking one extra character ahead, even if the scanner has already
|
|
seen enough text to disambiguate the current token, is a bit faster than
|
|
only looking ahead when necessary.
|
|
But scanners that always look ahead
|
|
give dreadful interactive performance; for example, when a user types
|
|
a newline, it is not recognized as a newline token until they enter
|
|
.I another
|
|
token, which often means typing in another whole line.
|
|
.IP
|
|
.I Flex
|
|
scanners default to
|
|
.I interactive
|
|
unless you use the
|
|
.B \-Cf
|
|
or
|
|
.B \-CF
|
|
table-compression options (see below).
|
|
That's because if you're looking
|
|
for high-performance you should be using one of these options, so if you
|
|
didn't,
|
|
.I flex
|
|
assumes you'd rather trade off a bit of run-time performance for intuitive
|
|
interactive behavior.
|
|
Note also that you
|
|
.I cannot
|
|
use
|
|
.B \-I
|
|
in conjunction with
|
|
.B \-Cf
|
|
or
|
|
.B \-CF.
|
|
Thus, this option is not really needed; it is on by default for all those
|
|
cases in which it is allowed.
|
|
.IP
|
|
You can force a scanner to
|
|
.I not
|
|
be interactive by using
|
|
.B \-B
|
|
(see above).
|
|
.TP
|
|
.B \-L
|
|
instructs
|
|
.I flex
|
|
not to generate
|
|
.B #line
|
|
directives.
|
|
Without this option,
|
|
.I flex
|
|
peppers the generated scanner
|
|
with #line directives so error messages in the actions will be correctly
|
|
located with respect to either the original
|
|
.I flex
|
|
input file (if the errors are due to code in the input file), or
|
|
.B lex.yy.c
|
|
(if the errors are
|
|
.I flex's
|
|
fault -- you should report these sorts of errors to the email address
|
|
given below).
|
|
.TP
|
|
.B \-T
|
|
makes
|
|
.I flex
|
|
run in
|
|
.I trace
|
|
mode.
|
|
It will generate a lot of messages to
|
|
.I stderr
|
|
concerning
|
|
the form of the input and the resultant non-deterministic and deterministic
|
|
finite automata.
|
|
This option is mostly for use in maintaining
|
|
.I flex.
|
|
.TP
|
|
.B \-V
|
|
prints the version number to
|
|
.I stdout
|
|
and exits.
|
|
.B \-\-version
|
|
is a synonym for
|
|
.B \-V.
|
|
.TP
|
|
.B \-7
|
|
instructs
|
|
.I flex
|
|
to generate a 7-bit scanner, i.e., one which can only recognized 7-bit
|
|
characters in its input.
|
|
The advantage of using
|
|
.B \-7
|
|
is that the scanner's tables can be up to half the size of those generated
|
|
using the
|
|
.B \-8
|
|
option (see below).
|
|
The disadvantage is that such scanners often hang
|
|
or crash if their input contains an 8-bit character.
|
|
.IP
|
|
Note, however, that unless you generate your scanner using the
|
|
.B \-Cf
|
|
or
|
|
.B \-CF
|
|
table compression options, use of
|
|
.B \-7
|
|
will save only a small amount of table space, and make your scanner
|
|
considerably less portable.
|
|
.I Flex's
|
|
default behavior is to generate an 8-bit scanner unless you use the
|
|
.B \-Cf
|
|
or
|
|
.B \-CF,
|
|
in which case
|
|
.I flex
|
|
defaults to generating 7-bit scanners unless your site was always
|
|
configured to generate 8-bit scanners (as will often be the case
|
|
with non-USA sites).
|
|
You can tell whether flex generated a 7-bit
|
|
or an 8-bit scanner by inspecting the flag summary in the
|
|
.B \-v
|
|
output as described above.
|
|
.IP
|
|
Note that if you use
|
|
.B \-Cfe
|
|
or
|
|
.B \-CFe
|
|
(those table compression options, but also using equivalence classes as
|
|
discussed see below), flex still defaults to generating an 8-bit
|
|
scanner, since usually with these compression options full 8-bit tables
|
|
are not much more expensive than 7-bit tables.
|
|
.TP
|
|
.B \-8
|
|
instructs
|
|
.I flex
|
|
to generate an 8-bit scanner, i.e., one which can recognize 8-bit
|
|
characters.
|
|
This flag is only needed for scanners generated using
|
|
.B \-Cf
|
|
or
|
|
.B \-CF,
|
|
as otherwise flex defaults to generating an 8-bit scanner anyway.
|
|
.IP
|
|
See the discussion of
|
|
.B \-7
|
|
above for flex's default behavior and the tradeoffs between 7-bit
|
|
and 8-bit scanners.
|
|
.TP
|
|
.B \-+
|
|
specifies that you want flex to generate a C++
|
|
scanner class.
|
|
See the section on Generating C++ Scanners below for
|
|
details.
|
|
.TP
|
|
.B \-C[aefFmr]
|
|
controls the degree of table compression and, more generally, trade-offs
|
|
between small scanners and fast scanners.
|
|
.IP
|
|
.B \-Ca
|
|
("align") instructs flex to trade off larger tables in the
|
|
generated scanner for faster performance because the elements of
|
|
the tables are better aligned for memory access and computation.
|
|
On some
|
|
RISC architectures, fetching and manipulating longwords is more efficient
|
|
than with smaller-sized units such as shortwords.
|
|
This option can
|
|
double the size of the tables used by your scanner.
|
|
.IP
|
|
.B \-Ce
|
|
directs
|
|
.I flex
|
|
to construct
|
|
.I equivalence classes,
|
|
i.e., sets of characters
|
|
which have identical lexical properties (for example, if the only
|
|
appearance of digits in the
|
|
.I flex
|
|
input is in the character class
|
|
"[0-9]" then the digits '0', '1', ..., '9' will all be put
|
|
in the same equivalence class).
|
|
Equivalence classes usually give
|
|
dramatic reductions in the final table/object file sizes (typically
|
|
a factor of 2-5) and are pretty cheap performance-wise (one array
|
|
look-up per character scanned).
|
|
.IP
|
|
.B \-Cf
|
|
specifies that the
|
|
.I full
|
|
scanner tables should be generated -
|
|
.I flex
|
|
should not compress the
|
|
tables by taking advantages of similar transition functions for
|
|
different states.
|
|
.IP
|
|
.B \-CF
|
|
specifies that the alternative fast scanner representation (described
|
|
above under the
|
|
.B \-F
|
|
flag)
|
|
should be used.
|
|
This option cannot be used with
|
|
.B \-+.
|
|
.IP
|
|
.B \-Cm
|
|
directs
|
|
.I flex
|
|
to construct
|
|
.I meta-equivalence classes,
|
|
which are sets of equivalence classes (or characters, if equivalence
|
|
classes are not being used) that are commonly used together.
|
|
Meta-equivalence
|
|
classes are often a big win when using compressed tables, but they
|
|
have a moderate performance impact (one or two "if" tests and one
|
|
array look-up per character scanned).
|
|
.IP
|
|
.B \-Cr
|
|
causes the generated scanner to
|
|
.I bypass
|
|
use of the standard I/O library (stdio) for input.
|
|
Instead of calling
|
|
.B fread()
|
|
or
|
|
.B getc(),
|
|
the scanner will use the
|
|
.B read()
|
|
system call, resulting in a performance gain which varies from system
|
|
to system, but in general is probably negligible unless you are also using
|
|
.B \-Cf
|
|
or
|
|
.B \-CF.
|
|
Using
|
|
.B \-Cr
|
|
can cause strange behavior if, for example, you read from
|
|
.I yyin
|
|
using stdio prior to calling the scanner (because the scanner will miss
|
|
whatever text your previous reads left in the stdio input buffer).
|
|
.IP
|
|
.B \-Cr
|
|
has no effect if you define
|
|
.B YY_INPUT
|
|
(see The Generated Scanner above).
|
|
.IP
|
|
A lone
|
|
.B \-C
|
|
specifies that the scanner tables should be compressed but neither
|
|
equivalence classes nor meta-equivalence classes should be used.
|
|
.IP
|
|
The options
|
|
.B \-Cf
|
|
or
|
|
.B \-CF
|
|
and
|
|
.B \-Cm
|
|
do not make sense together - there is no opportunity for meta-equivalence
|
|
classes if the table is not being compressed.
|
|
Otherwise the options
|
|
may be freely mixed, and are cumulative.
|
|
.IP
|
|
The default setting is
|
|
.B \-Cem,
|
|
which specifies that
|
|
.I flex
|
|
should generate equivalence classes
|
|
and meta-equivalence classes.
|
|
This setting provides the highest degree of table compression.
|
|
You can trade off
|
|
faster-executing scanners at the cost of larger tables with
|
|
the following generally being true:
|
|
.nf
|
|
|
|
slowest \*[Am] smallest
|
|
-Cem
|
|
-Cm
|
|
-Ce
|
|
-C
|
|
-C{f,F}e
|
|
-C{f,F}
|
|
-C{f,F}a
|
|
fastest \*[Am] largest
|
|
|
|
.fi
|
|
Note that scanners with the smallest tables are usually generated and
|
|
compiled the quickest, so
|
|
during development you will usually want to use the default, maximal
|
|
compression.
|
|
.IP
|
|
.B \-Cfe
|
|
is often a good compromise between speed and size for production
|
|
scanners.
|
|
.TP
|
|
.B \-ooutput
|
|
directs flex to write the scanner to the file
|
|
.B output
|
|
instead of
|
|
.B lex.yy.c.
|
|
If you combine
|
|
.B \-o
|
|
with the
|
|
.B \-t
|
|
option, then the scanner is written to
|
|
.I stdout
|
|
but its
|
|
.B #line
|
|
directives (see the
|
|
.B \\-L
|
|
option above) refer to the file
|
|
.B output.
|
|
.TP
|
|
.B \-Pprefix
|
|
changes the default
|
|
.I "yy"
|
|
prefix used by
|
|
.I flex
|
|
for all globally-visible variable and function names to instead be
|
|
.I prefix.
|
|
For example,
|
|
.B \-Pfoo
|
|
changes the name of
|
|
.B yytext
|
|
to
|
|
.B footext.
|
|
It also changes the name of the default output file from
|
|
.B lex.yy.c
|
|
to
|
|
.B lex.foo.c.
|
|
Here are all of the names affected:
|
|
.nf
|
|
|
|
yy_create_buffer
|
|
yy_delete_buffer
|
|
yy_flex_debug
|
|
yy_init_buffer
|
|
yy_flush_buffer
|
|
yy_load_buffer_state
|
|
yy_switch_to_buffer
|
|
yyin
|
|
yyleng
|
|
yylex
|
|
yylineno
|
|
yyout
|
|
yyrestart
|
|
yytext
|
|
yywrap
|
|
|
|
.fi
|
|
(If you are using a C++ scanner, then only
|
|
.B yywrap
|
|
and
|
|
.B yyFlexLexer
|
|
are affected.)
|
|
Within your scanner itself, you can still refer to the global variables
|
|
and functions using either version of their name; but externally, they
|
|
have the modified name.
|
|
.IP
|
|
This option lets you easily link together multiple
|
|
.I flex
|
|
programs into the same executable.
|
|
Note, though, that using this option also renames
|
|
.B yywrap(),
|
|
so you now
|
|
.I must
|
|
either
|
|
provide your own (appropriately-named) version of the routine for your
|
|
scanner, or use
|
|
.B %option noyywrap,
|
|
as linking with
|
|
.B \-lfl
|
|
no longer provides one for you by default.
|
|
.TP
|
|
.B \-Sskeleton_file
|
|
overrides the default skeleton file from which
|
|
.I flex
|
|
constructs its scanners.
|
|
You'll never need this option unless you are doing
|
|
.I flex
|
|
maintenance or development.
|
|
.PP
|
|
.I flex
|
|
also provides a mechanism for controlling options within the
|
|
scanner specification itself, rather than from the flex command-line.
|
|
This is done by including
|
|
.B %option
|
|
directives in the first section of the scanner specification.
|
|
You can specify multiple options with a single
|
|
.B %option
|
|
directive, and multiple directives in the first section of your flex input
|
|
file.
|
|
.PP
|
|
Most options are given simply as names, optionally preceded by the
|
|
word "no" (with no intervening whitespace) to negate their meaning.
|
|
A number are equivalent to flex flags or their negation:
|
|
.nf
|
|
|
|
7bit -7 option
|
|
8bit -8 option
|
|
align -Ca option
|
|
backup -b option
|
|
batch -B option
|
|
c++ -+ option
|
|
|
|
caseful or
|
|
case-sensitive opposite of -i (default)
|
|
|
|
case-insensitive or
|
|
caseless -i option
|
|
|
|
debug -d option
|
|
default opposite of -s option
|
|
ecs -Ce option
|
|
fast -F option
|
|
full -f option
|
|
interactive -I option
|
|
lex-compat -l option
|
|
meta-ecs -Cm option
|
|
perf-report -p option
|
|
read -Cr option
|
|
stdout -t option
|
|
verbose -v option
|
|
warn opposite of -w option
|
|
(use "%option nowarn" for -w)
|
|
|
|
array equivalent to "%array"
|
|
pointer equivalent to "%pointer" (default)
|
|
|
|
.fi
|
|
Some
|
|
.B %option's
|
|
provide features otherwise not available:
|
|
.TP
|
|
.B always-interactive
|
|
instructs flex to generate a scanner which always considers its input
|
|
"interactive".
|
|
Normally, on each new input file the scanner calls
|
|
.B isatty()
|
|
in an attempt to determine whether
|
|
the scanner's input source is interactive and thus should be read a
|
|
character at a time.
|
|
When this option is used, however, then no
|
|
such call is made.
|
|
.TP
|
|
.B main
|
|
directs flex to provide a default
|
|
.B main()
|
|
program for the scanner, which simply calls
|
|
.B yylex().
|
|
This option implies
|
|
.B noyywrap
|
|
(see below).
|
|
.TP
|
|
.B never-interactive
|
|
instructs flex to generate a scanner which never considers its input
|
|
"interactive" (again, no call made to
|
|
.B isatty()).
|
|
This is the opposite of
|
|
.B always-interactive.
|
|
.TP
|
|
.B stack
|
|
enables the use of start condition stacks (see Start Conditions above).
|
|
.TP
|
|
.B stdinit
|
|
if set (i.e.,
|
|
.B %option stdinit)
|
|
initializes
|
|
.I yyin
|
|
and
|
|
.I yyout
|
|
to
|
|
.I stdin
|
|
and
|
|
.I stdout,
|
|
instead of the default of
|
|
.I nil.
|
|
Some existing
|
|
.I lex
|
|
programs depend on this behavior, even though it is not compliant with
|
|
ANSI C, which does not require
|
|
.I stdin
|
|
and
|
|
.I stdout
|
|
to be compile-time constant.
|
|
.TP
|
|
.B yylineno
|
|
directs
|
|
.I flex
|
|
to generate a scanner that maintains the number of the current line
|
|
read from its input in the global variable
|
|
.B yylineno.
|
|
This option is implied by
|
|
.B %option lex-compat.
|
|
.TP
|
|
.B yywrap
|
|
if unset (i.e.,
|
|
.B %option noyywrap),
|
|
makes the scanner not call
|
|
.B yywrap()
|
|
upon an end-of-file, but simply assume that there are no more
|
|
files to scan (until the user points
|
|
.I yyin
|
|
at a new file and calls
|
|
.B yylex()
|
|
again).
|
|
.PP
|
|
.I flex
|
|
scans your rule actions to determine whether you use the
|
|
.B REJECT
|
|
or
|
|
.B yymore()
|
|
features.
|
|
The
|
|
.B reject
|
|
and
|
|
.B yymore
|
|
options are available to override its decision as to whether you use the
|
|
options, either by setting them (e.g.,
|
|
.B %option reject)
|
|
to indicate the feature is indeed used, or
|
|
unsetting them to indicate it actually is not used
|
|
(e.g.,
|
|
.B %option noyymore).
|
|
.PP
|
|
Three options take string-delimited values, offset with '=':
|
|
.nf
|
|
|
|
%option outfile="ABC"
|
|
|
|
.fi
|
|
is equivalent to
|
|
.B -oABC,
|
|
and
|
|
.nf
|
|
|
|
%option prefix="XYZ"
|
|
|
|
.fi
|
|
is equivalent to
|
|
.B -PXYZ.
|
|
Finally,
|
|
.nf
|
|
|
|
%option yyclass="foo"
|
|
|
|
.fi
|
|
only applies when generating a C++ scanner (
|
|
.B \-+
|
|
option).
|
|
It informs
|
|
.I flex
|
|
that you have derived
|
|
.B foo
|
|
as a subclass of
|
|
.B yyFlexLexer,
|
|
so
|
|
.I flex
|
|
will place your actions in the member function
|
|
.B foo::yylex()
|
|
instead of
|
|
.B yyFlexLexer::yylex().
|
|
It also generates a
|
|
.B yyFlexLexer::yylex()
|
|
member function that emits a run-time error (by invoking
|
|
.B yyFlexLexer::LexerError())
|
|
if called.
|
|
See Generating C++ Scanners, below, for additional information.
|
|
.PP
|
|
A number of options are available for lint purists who want to suppress
|
|
the appearance of unneeded routines in the generated scanner.
|
|
Each of the following, if unset
|
|
(e.g.,
|
|
.B %option nounput
|
|
), results in the corresponding routine not appearing in
|
|
the generated scanner:
|
|
.nf
|
|
|
|
input, unput
|
|
yy_push_state, yy_pop_state, yy_top_state
|
|
yy_scan_buffer, yy_scan_bytes, yy_scan_string
|
|
|
|
.fi
|
|
(though
|
|
.B yy_push_state()
|
|
and friends won't appear anyway unless you use
|
|
.B %option stack).
|
|
.SH PERFORMANCE CONSIDERATIONS
|
|
The main design goal of
|
|
.I flex
|
|
is that it generate high-performance scanners.
|
|
It has been optimized
|
|
for dealing well with large sets of rules.
|
|
Aside from the effects on scanner speed of the table compression
|
|
.B \-C
|
|
options outlined above,
|
|
there are a number of options/actions which degrade performance.
|
|
These are, from most expensive to least:
|
|
.nf
|
|
|
|
REJECT
|
|
%option yylineno
|
|
arbitrary trailing context
|
|
|
|
pattern sets that require backing up
|
|
%array
|
|
%option interactive
|
|
%option always-interactive
|
|
|
|
'^' beginning-of-line operator
|
|
yymore()
|
|
|
|
.fi
|
|
with the first three all being quite expensive and the last two
|
|
being quite cheap.
|
|
Note also that
|
|
.B unput()
|
|
is implemented as a routine call that potentially does quite a bit of
|
|
work, while
|
|
.B yyless()
|
|
is a quite-cheap macro; so if just putting back some excess text you
|
|
scanned, use
|
|
.B yyless().
|
|
.PP
|
|
.B REJECT
|
|
should be avoided at all costs when performance is important.
|
|
It is a particularly expensive option.
|
|
.PP
|
|
Getting rid of backing up is messy and often may be an enormous
|
|
amount of work for a complicated scanner.
|
|
In principal, one begins by using the
|
|
.B \-b
|
|
flag to generate a
|
|
.I lex.backup
|
|
file.
|
|
For example, on the input
|
|
.nf
|
|
|
|
%%
|
|
foo return TOK_KEYWORD;
|
|
foobar return TOK_KEYWORD;
|
|
|
|
.fi
|
|
the file looks like:
|
|
.nf
|
|
|
|
State #6 is non-accepting -
|
|
associated rule line numbers:
|
|
2 3
|
|
out-transitions: [ o ]
|
|
jam-transitions: EOF [ \\001-n p-\\177 ]
|
|
|
|
State #8 is non-accepting -
|
|
associated rule line numbers:
|
|
3
|
|
out-transitions: [ a ]
|
|
jam-transitions: EOF [ \\001-` b-\\177 ]
|
|
|
|
State #9 is non-accepting -
|
|
associated rule line numbers:
|
|
3
|
|
out-transitions: [ r ]
|
|
jam-transitions: EOF [ \\001-q s-\\177 ]
|
|
|
|
Compressed tables always back up.
|
|
|
|
.fi
|
|
The first few lines tell us that there's a scanner state in
|
|
which it can make a transition on an 'o' but not on any other
|
|
character, and that in that state the currently scanned text does not match
|
|
any rule.
|
|
The state occurs when trying to match the rules found
|
|
at lines 2 and 3 in the input file.
|
|
If the scanner is in that state and then reads
|
|
something other than an 'o', it will have to back up to find
|
|
a rule which is matched.
|
|
With a bit of headscratching one can see that this must be the
|
|
state it's in when it has seen "fo".
|
|
When this has happened,
|
|
if anything other than another 'o' is seen, the scanner will
|
|
have to back up to simply match the 'f' (by the default rule).
|
|
.PP
|
|
The comment regarding State #8 indicates there's a problem
|
|
when "foob" has been scanned.
|
|
Indeed, on any character other
|
|
than an 'a', the scanner will have to back up to accept "foo".
|
|
Similarly, the comment for State #9 concerns when "fooba" has
|
|
been scanned and an 'r' does not follow.
|
|
.PP
|
|
The final comment reminds us that there's no point going to
|
|
all the trouble of removing backing up from the rules unless
|
|
we're using
|
|
.B \-Cf
|
|
or
|
|
.B \-CF,
|
|
since there's no performance gain doing so with compressed scanners.
|
|
.PP
|
|
The way to remove the backing up is to add "error" rules:
|
|
.nf
|
|
|
|
%%
|
|
foo return TOK_KEYWORD;
|
|
foobar return TOK_KEYWORD;
|
|
|
|
fooba |
|
|
foob |
|
|
fo {
|
|
/* false alarm, not really a keyword */
|
|
return TOK_ID;
|
|
}
|
|
|
|
.fi
|
|
.PP
|
|
Eliminating backing up among a list of keywords can also be
|
|
done using a "catch-all" rule:
|
|
.nf
|
|
|
|
%%
|
|
foo return TOK_KEYWORD;
|
|
foobar return TOK_KEYWORD;
|
|
|
|
[a-z]+ return TOK_ID;
|
|
|
|
.fi
|
|
This is usually the best solution when appropriate.
|
|
.PP
|
|
Backing up messages tend to cascade.
|
|
With a complicated set of rules it's not uncommon to get hundreds
|
|
of messages.
|
|
If one can decipher them, though, it often
|
|
only takes a dozen or so rules to eliminate the backing up (though
|
|
it's easy to make a mistake and have an error rule accidentally match
|
|
a valid token.
|
|
A possible future
|
|
.I flex
|
|
feature will be to automatically add rules to eliminate backing up).
|
|
.PP
|
|
It's important to keep in mind that you gain the benefits of eliminating
|
|
backing up only if you eliminate
|
|
.I every
|
|
instance of backing up.
|
|
Leaving just one means you gain nothing.
|
|
.PP
|
|
.I Variable
|
|
trailing context (where both the leading and trailing parts do not have
|
|
a fixed length) entails almost the same performance loss as
|
|
.B REJECT
|
|
(i.e., substantial).
|
|
So when possible a rule like:
|
|
.nf
|
|
|
|
%%
|
|
mouse|rat/(cat|dog) run();
|
|
|
|
.fi
|
|
is better written:
|
|
.nf
|
|
|
|
%%
|
|
mouse/cat|dog run();
|
|
rat/cat|dog run();
|
|
|
|
.fi
|
|
or as
|
|
.nf
|
|
|
|
%%
|
|
mouse|rat/cat run();
|
|
mouse|rat/dog run();
|
|
|
|
.fi
|
|
Note that here the special '|' action does
|
|
.I not
|
|
provide any savings, and can even make things worse (see
|
|
Deficiencies / Bugs below).
|
|
.LP
|
|
Another area where the user can increase a scanner's performance
|
|
(and one that's easier to implement) arises from the fact that
|
|
the longer the tokens matched, the faster the scanner will run.
|
|
This is because with long tokens the processing of most input
|
|
characters takes place in the (short) inner scanning loop, and
|
|
does not often have to go through the additional work of setting up
|
|
the scanning environment (e.g.,
|
|
.B yytext)
|
|
for the action.
|
|
Recall the scanner for C comments:
|
|
.nf
|
|
|
|
%x comment
|
|
%%
|
|
int line_num = 1;
|
|
|
|
"/*" BEGIN(comment);
|
|
|
|
\*[Lt]comment\*[Gt][^*\\n]*
|
|
\*[Lt]comment\*[Gt]"*"+[^*/\\n]*
|
|
\*[Lt]comment\*[Gt]\\n ++line_num;
|
|
\*[Lt]comment\*[Gt]"*"+"/" BEGIN(INITIAL);
|
|
|
|
.fi
|
|
This could be sped up by writing it as:
|
|
.nf
|
|
|
|
%x comment
|
|
%%
|
|
int line_num = 1;
|
|
|
|
"/*" BEGIN(comment);
|
|
|
|
\*[Lt]comment\*[Gt][^*\\n]*
|
|
\*[Lt]comment\*[Gt][^*\\n]*\\n ++line_num;
|
|
\*[Lt]comment\*[Gt]"*"+[^*/\\n]*
|
|
\*[Lt]comment\*[Gt]"*"+[^*/\\n]*\\n ++line_num;
|
|
\*[Lt]comment\*[Gt]"*"+"/" BEGIN(INITIAL);
|
|
|
|
.fi
|
|
Now instead of each newline requiring the processing of another
|
|
action, recognizing the newlines is "distributed" over the other rules
|
|
to keep the matched text as long as possible.
|
|
Note that
|
|
.I adding
|
|
rules does
|
|
.I not
|
|
slow down the scanner! The speed of the scanner is independent
|
|
of the number of rules or (modulo the considerations given at the
|
|
beginning of this section) how complicated the rules are with
|
|
regard to operators such as '*' and '|'.
|
|
.PP
|
|
A final example in speeding up a scanner: suppose you want to scan
|
|
through a file containing identifiers and keywords, one per line
|
|
and with no other extraneous characters, and recognize all the
|
|
keywords.
|
|
A natural first approach is:
|
|
.nf
|
|
|
|
%%
|
|
asm |
|
|
auto |
|
|
break |
|
|
... etc ...
|
|
volatile |
|
|
while /* it's a keyword */
|
|
|
|
.|\\n /* it's not a keyword */
|
|
|
|
.fi
|
|
To eliminate the back-tracking, introduce a catch-all rule:
|
|
.nf
|
|
|
|
%%
|
|
asm |
|
|
auto |
|
|
break |
|
|
... etc ...
|
|
volatile |
|
|
while /* it's a keyword */
|
|
|
|
[a-z]+ |
|
|
.|\\n /* it's not a keyword */
|
|
|
|
.fi
|
|
Now, if it's guaranteed that there's exactly one word per line,
|
|
then we can reduce the total number of matches by a half by
|
|
merging in the recognition of newlines with that of the other
|
|
tokens:
|
|
.nf
|
|
|
|
%%
|
|
asm\\n |
|
|
auto\\n |
|
|
break\\n |
|
|
... etc ...
|
|
volatile\\n |
|
|
while\\n /* it's a keyword */
|
|
|
|
[a-z]+\\n |
|
|
.|\\n /* it's not a keyword */
|
|
|
|
.fi
|
|
One has to be careful here, as we have now reintroduced backing up
|
|
into the scanner.
|
|
In particular, while
|
|
.I we
|
|
know that there will never be any characters in the input stream
|
|
other than letters or newlines,
|
|
.I flex
|
|
can't figure this out, and it will plan for possibly needing to back up
|
|
when it has scanned a token like "auto" and then the next character
|
|
is something other than a newline or a letter.
|
|
Previously it would
|
|
then just match the "auto" rule and be done, but now it has no "auto"
|
|
rule, only a "auto\\n" rule.
|
|
To eliminate the possibility of backing up,
|
|
we could either duplicate all rules but without final newlines, or,
|
|
since we never expect to encounter such an input and therefore don't
|
|
how it's classified, we can introduce one more catch-all rule, this
|
|
one which doesn't include a newline:
|
|
.nf
|
|
|
|
%%
|
|
asm\\n |
|
|
auto\\n |
|
|
break\\n |
|
|
... etc ...
|
|
volatile\\n |
|
|
while\\n /* it's a keyword */
|
|
|
|
[a-z]+\\n |
|
|
[a-z]+ |
|
|
.|\\n /* it's not a keyword */
|
|
|
|
.fi
|
|
Compiled with
|
|
.B \-Cf,
|
|
this is about as fast as one can get a
|
|
.I flex
|
|
scanner to go for this particular problem.
|
|
.PP
|
|
A final note:
|
|
.I flex
|
|
is slow when matching NUL's, particularly when a token contains
|
|
multiple NUL's.
|
|
It's best to write rules which match
|
|
.I short
|
|
amounts of text if it's anticipated that the text will often include NUL's.
|
|
.PP
|
|
Another final note regarding performance: as mentioned above in the section
|
|
How the Input is Matched, dynamically resizing
|
|
.B yytext
|
|
to accommodate huge tokens is a slow process because it presently requires that
|
|
the (huge) token be rescanned from the beginning.
|
|
Thus if performance is
|
|
vital, you should attempt to match "large" quantities of text but not
|
|
"huge" quantities, where the cutoff between the two is at about 8K
|
|
characters/token.
|
|
.SH GENERATING C++ SCANNERS
|
|
.I flex
|
|
provides two different ways to generate scanners for use with C++.
|
|
The first way is to simply compile a scanner generated by
|
|
.I flex
|
|
using a C++ compiler instead of a C compiler.
|
|
You should not encounter
|
|
any compilations errors (please report any you find to the email address
|
|
given in the Author section below).
|
|
You can then use C++ code in your rule actions instead of C code.
|
|
Note that the default input source for your scanner remains
|
|
.I yyin,
|
|
and default echoing is still done to
|
|
.I yyout.
|
|
Both of these remain
|
|
.I FILE *
|
|
variables and not C++
|
|
.I streams.
|
|
.PP
|
|
You can also use
|
|
.I flex
|
|
to generate a C++ scanner class, using the
|
|
.B \-+
|
|
option (or, equivalently,
|
|
.B %option c++),
|
|
which is automatically specified if the name of the flex
|
|
executable ends in a '+', such as
|
|
.I flex++.
|
|
When using this option, flex defaults to generating the scanner to the file
|
|
.B lex.yy.cc
|
|
instead of
|
|
.B lex.yy.c.
|
|
The generated scanner includes the header file
|
|
.I FlexLexer.h,
|
|
which defines the interface to two C++ classes.
|
|
.PP
|
|
The first class,
|
|
.B FlexLexer,
|
|
provides an abstract base class defining the general scanner class
|
|
interface.
|
|
It provides the following member functions:
|
|
.TP
|
|
.B const char* YYText()
|
|
returns the text of the most recently matched token, the equivalent of
|
|
.B yytext.
|
|
.TP
|
|
.B int YYLeng()
|
|
returns the length of the most recently matched token, the equivalent of
|
|
.B yyleng.
|
|
.TP
|
|
.B int lineno() const
|
|
returns the current input line number
|
|
(see
|
|
.B %option yylineno),
|
|
or
|
|
.B 1
|
|
if
|
|
.B %option yylineno
|
|
was not used.
|
|
.TP
|
|
.B void set_debug( int flag )
|
|
sets the debugging flag for the scanner, equivalent to assigning to
|
|
.B yy_flex_debug
|
|
(see the Options section above).
|
|
Note that you must build the scanner using
|
|
.B %option debug
|
|
to include debugging information in it.
|
|
.TP
|
|
.B int debug() const
|
|
returns the current setting of the debugging flag.
|
|
.PP
|
|
Also provided are member functions equivalent to
|
|
.B yy_switch_to_buffer(),
|
|
.B yy_create_buffer()
|
|
(though the first argument is an
|
|
.B istream*
|
|
object pointer and not a
|
|
.B FILE*),
|
|
.B yy_flush_buffer(),
|
|
.B yy_delete_buffer(),
|
|
and
|
|
.B yyrestart()
|
|
(again, the first argument is a
|
|
.B istream*
|
|
object pointer).
|
|
.PP
|
|
The second class defined in
|
|
.I FlexLexer.h
|
|
is
|
|
.B yyFlexLexer,
|
|
which is derived from
|
|
.B FlexLexer.
|
|
It defines the following additional member functions:
|
|
.TP
|
|
.B
|
|
yyFlexLexer( istream* arg_yyin = 0, ostream* arg_yyout = 0 )
|
|
constructs a
|
|
.B yyFlexLexer
|
|
object using the given streams for input and output.
|
|
If not specified, the streams default to
|
|
.B cin
|
|
and
|
|
.B cout,
|
|
respectively.
|
|
.TP
|
|
.B virtual int yylex()
|
|
performs the same role is
|
|
.B yylex()
|
|
does for ordinary flex scanners: it scans the input stream, consuming
|
|
tokens, until a rule's action returns a value.
|
|
If you derive a subclass
|
|
.B S
|
|
from
|
|
.B yyFlexLexer
|
|
and want to access the member functions and variables of
|
|
.B S
|
|
inside
|
|
.B yylex(),
|
|
then you need to use
|
|
.B %option yyclass="S"
|
|
to inform
|
|
.I flex
|
|
that you will be using that subclass instead of
|
|
.B yyFlexLexer.
|
|
In this case, rather than generating
|
|
.B yyFlexLexer::yylex(),
|
|
.I flex
|
|
generates
|
|
.B S::yylex()
|
|
(and also generates a dummy
|
|
.B yyFlexLexer::yylex()
|
|
that calls
|
|
.B yyFlexLexer::LexerError()
|
|
if called).
|
|
.TP
|
|
.B
|
|
virtual void switch_streams(istream* new_in = 0,
|
|
.B
|
|
ostream* new_out = 0)
|
|
reassigns
|
|
.B yyin
|
|
to
|
|
.B new_in
|
|
(if non-nil)
|
|
and
|
|
.B yyout
|
|
to
|
|
.B new_out
|
|
(ditto), deleting the previous input buffer if
|
|
.B yyin
|
|
is reassigned.
|
|
.TP
|
|
.B
|
|
int yylex( istream* new_in, ostream* new_out = 0 )
|
|
first switches the input streams via
|
|
.B switch_streams( new_in, new_out )
|
|
and then returns the value of
|
|
.B yylex().
|
|
.PP
|
|
In addition,
|
|
.B yyFlexLexer
|
|
defines the following protected virtual functions which you can redefine
|
|
in derived classes to tailor the scanner:
|
|
.TP
|
|
.B
|
|
virtual int LexerInput( char* buf, int max_size )
|
|
reads up to
|
|
.B max_size
|
|
characters into
|
|
.B buf
|
|
and returns the number of characters read.
|
|
To indicate end-of-input, return 0 characters.
|
|
Note that "interactive" scanners (see the
|
|
.B \-B
|
|
and
|
|
.B \-I
|
|
flags) define the macro
|
|
.B YY_INTERACTIVE.
|
|
If you redefine
|
|
.B LexerInput()
|
|
and need to take different actions depending on whether or not
|
|
the scanner might be scanning an interactive input source, you can
|
|
test for the presence of this name via
|
|
.B #ifdef.
|
|
.TP
|
|
.B
|
|
virtual void LexerOutput( const char* buf, int size )
|
|
writes out
|
|
.B size
|
|
characters from the buffer
|
|
.B buf,
|
|
which, while NUL-terminated, may also contain "internal" NUL's if
|
|
the scanner's rules can match text with NUL's in them.
|
|
.TP
|
|
.B
|
|
virtual void LexerError( const char* msg )
|
|
reports a fatal error message.
|
|
The default version of this function writes the message to the stream
|
|
.B cerr
|
|
and exits.
|
|
.PP
|
|
Note that a
|
|
.B yyFlexLexer
|
|
object contains its
|
|
.I entire
|
|
scanning state.
|
|
Thus you can use such objects to create reentrant scanners.
|
|
You can instantiate multiple instances of the same
|
|
.B yyFlexLexer
|
|
class, and you can also combine multiple C++ scanner classes together
|
|
in the same program using the
|
|
.B \-P
|
|
option discussed above.
|
|
.PP
|
|
Finally, note that the
|
|
.B %array
|
|
feature is not available to C++ scanner classes; you must use
|
|
.B %pointer
|
|
(the default).
|
|
.PP
|
|
Here is an example of a simple C++ scanner:
|
|
.nf
|
|
|
|
// An example of using the flex C++ scanner class.
|
|
|
|
%{
|
|
int mylineno = 0;
|
|
%}
|
|
|
|
string \\"[^\\n"]+\\"
|
|
|
|
ws [ \\t]+
|
|
|
|
alpha [A-Za-z]
|
|
dig [0-9]
|
|
name ({alpha}|{dig}|\\$)({alpha}|{dig}|[_.\\-/$])*
|
|
num1 [-+]?{dig}+\\.?([eE][-+]?{dig}+)?
|
|
num2 [-+]?{dig}*\\.{dig}+([eE][-+]?{dig}+)?
|
|
number {num1}|{num2}
|
|
|
|
%%
|
|
|
|
{ws} /* skip blanks and tabs */
|
|
|
|
"/*" {
|
|
int c;
|
|
|
|
while((c = yyinput()) != 0)
|
|
{
|
|
if(c == '\\n')
|
|
++mylineno;
|
|
|
|
else if(c == '*')
|
|
{
|
|
if((c = yyinput()) == '/')
|
|
break;
|
|
else
|
|
unput(c);
|
|
}
|
|
}
|
|
}
|
|
|
|
{number} cout \*[Lt]\*[Lt] "number " \*[Lt]\*[Lt] YYText() \*[Lt]\*[Lt] '\\n';
|
|
|
|
\\n mylineno++;
|
|
|
|
{name} cout \*[Lt]\*[Lt] "name " \*[Lt]\*[Lt] YYText() \*[Lt]\*[Lt] '\\n';
|
|
|
|
{string} cout \*[Lt]\*[Lt] "string " \*[Lt]\*[Lt] YYText() \*[Lt]\*[Lt] '\\n';
|
|
|
|
%%
|
|
|
|
int main( int /* argc */, char** /* argv */ )
|
|
{
|
|
FlexLexer* lexer = new yyFlexLexer;
|
|
while(lexer-\*[Gt]yylex() != 0)
|
|
;
|
|
return 0;
|
|
}
|
|
.fi
|
|
If you want to create multiple (different) lexer classes, you use the
|
|
.B \-P
|
|
flag (or the
|
|
.B prefix=
|
|
option) to rename each
|
|
.B yyFlexLexer
|
|
to some other
|
|
.B xxFlexLexer.
|
|
You then can include
|
|
.B \*[Lt]FlexLexer.h\*[Gt]
|
|
in your other sources once per lexer class, first renaming
|
|
.B yyFlexLexer
|
|
as follows:
|
|
.nf
|
|
|
|
#undef yyFlexLexer
|
|
#define yyFlexLexer xxFlexLexer
|
|
#include \*[Lt]FlexLexer.h\*[Gt]
|
|
|
|
#undef yyFlexLexer
|
|
#define yyFlexLexer zzFlexLexer
|
|
#include \*[Lt]FlexLexer.h\*[Gt]
|
|
|
|
.fi
|
|
if, for example, you used
|
|
.B %option prefix="xx"
|
|
for one of your scanners and
|
|
.B %option prefix="zz"
|
|
for the other.
|
|
.PP
|
|
IMPORTANT: the present form of the scanning class is
|
|
.I experimental
|
|
and may change considerably between major releases.
|
|
.SH INCOMPATIBILITIES WITH LEX AND POSIX
|
|
.I flex
|
|
is a rewrite of the AT\*[Am]T Unix
|
|
.I lex
|
|
tool (the two implementations do not share any code, though),
|
|
with some extensions and incompatibilities, both of which
|
|
are of concern to those who wish to write scanners acceptable
|
|
to either implementation.
|
|
Flex is fully compliant with the POSIX
|
|
.I lex
|
|
specification, except that when using
|
|
.B %pointer
|
|
(the default), a call to
|
|
.B unput()
|
|
destroys the contents of
|
|
.B yytext,
|
|
which is counter to the POSIX specification.
|
|
.PP
|
|
In this section we discuss all of the known areas of incompatibility
|
|
between flex, AT\*[Am]T lex, and the POSIX specification.
|
|
.PP
|
|
.I flex's
|
|
.B \-l
|
|
option turns on maximum compatibility with the original AT\*[Am]T
|
|
.I lex
|
|
implementation, at the cost of a major loss in the generated scanner's
|
|
performance.
|
|
We note below which incompatibilities can be overcome
|
|
using the
|
|
.B \-l
|
|
option.
|
|
.PP
|
|
.I flex
|
|
is fully compatible with
|
|
.I lex
|
|
with the following exceptions:
|
|
.IP -
|
|
The undocumented
|
|
.I lex
|
|
scanner internal variable
|
|
.B yylineno
|
|
is not supported unless
|
|
.B \-l
|
|
or
|
|
.B %option yylineno
|
|
is used.
|
|
.IP
|
|
.B yylineno
|
|
should be maintained on a per-buffer basis, rather than a per-scanner
|
|
(single global variable) basis.
|
|
.IP
|
|
.B yylineno
|
|
is not part of the POSIX specification.
|
|
.IP -
|
|
The
|
|
.B input()
|
|
routine is not redefinable, though it may be called to read characters
|
|
following whatever has been matched by a rule.
|
|
If
|
|
.B input()
|
|
encounters an end-of-file the normal
|
|
.B yywrap()
|
|
processing is done.
|
|
A ``real'' end-of-file is returned by
|
|
.B input()
|
|
as
|
|
.I EOF.
|
|
.IP
|
|
Input is instead controlled by defining the
|
|
.B YY_INPUT
|
|
macro.
|
|
.IP
|
|
The
|
|
.I flex
|
|
restriction that
|
|
.B input()
|
|
cannot be redefined is in accordance with the POSIX specification,
|
|
which simply does not specify any way of controlling the
|
|
scanner's input other than by making an initial assignment to
|
|
.I yyin.
|
|
.IP -
|
|
The
|
|
.B unput()
|
|
routine is not redefinable.
|
|
This restriction is in accordance with POSIX.
|
|
.IP -
|
|
.I flex
|
|
scanners are not as reentrant as
|
|
.I lex
|
|
scanners.
|
|
In particular, if you have an interactive scanner and
|
|
an interrupt handler which long-jumps out of the scanner, and
|
|
the scanner is subsequently called again, you may get the following
|
|
message:
|
|
.nf
|
|
|
|
fatal flex scanner internal error--end of buffer missed
|
|
|
|
.fi
|
|
To reenter the scanner, first use
|
|
.nf
|
|
|
|
yyrestart( yyin );
|
|
|
|
.fi
|
|
Note that this call will throw away any buffered input; usually this
|
|
isn't a problem with an interactive scanner.
|
|
.IP
|
|
Also note that flex C++ scanner classes
|
|
.I are
|
|
reentrant, so if using C++ is an option for you, you should use
|
|
them instead.
|
|
See "Generating C++ Scanners" above for details.
|
|
.IP -
|
|
.B output()
|
|
is not supported.
|
|
Output from the
|
|
.B ECHO
|
|
macro is done to the file-pointer
|
|
.I yyout
|
|
(default
|
|
.I stdout).
|
|
.IP
|
|
.B output()
|
|
is not part of the POSIX specification.
|
|
.IP -
|
|
.I lex
|
|
does not support exclusive start conditions (%x), though they
|
|
are in the POSIX specification.
|
|
.IP -
|
|
When definitions are expanded,
|
|
.I flex
|
|
encloses them in parentheses.
|
|
With lex, the following:
|
|
.nf
|
|
|
|
NAME [A-Z][A-Z0-9]*
|
|
%%
|
|
foo{NAME}? printf( "Found it\\n" );
|
|
%%
|
|
|
|
.fi
|
|
will not match the string "foo" because when the macro
|
|
is expanded the rule is equivalent to "foo[A-Z][A-Z0-9]*?"
|
|
and the precedence is such that the '?' is associated with
|
|
"[A-Z0-9]*".
|
|
With
|
|
.I flex,
|
|
the rule will be expanded to
|
|
"foo([A-Z][A-Z0-9]*)?" and so the string "foo" will match.
|
|
.IP
|
|
Note that if the definition begins with
|
|
.B ^
|
|
or ends with
|
|
.B $
|
|
then it is
|
|
.I not
|
|
expanded with parentheses, to allow these operators to appear in
|
|
definitions without losing their special meanings.
|
|
But the
|
|
.B \*[Lt]s\*[Gt], /,
|
|
and
|
|
.B \*[Lt]\*[Lt]EOF\*[Gt]\*[Gt]
|
|
operators cannot be used in a
|
|
.I flex
|
|
definition.
|
|
.IP
|
|
Using
|
|
.B \-l
|
|
results in the
|
|
.I lex
|
|
behavior of no parentheses around the definition.
|
|
.IP
|
|
The POSIX specification is that the definition be enclosed in parentheses.
|
|
.IP -
|
|
Some implementations of
|
|
.I lex
|
|
allow a rule's action to begin on a separate line, if the rule's pattern
|
|
has trailing whitespace:
|
|
.nf
|
|
|
|
%%
|
|
foo|bar\*[Lt]space here\*[Gt]
|
|
{ foobar_action(); }
|
|
|
|
.fi
|
|
.I flex
|
|
does not support this feature.
|
|
.IP -
|
|
The
|
|
.I lex
|
|
.B %r
|
|
(generate a Ratfor scanner) option is not supported.
|
|
It is not part
|
|
of the POSIX specification.
|
|
.IP -
|
|
After a call to
|
|
.B unput(),
|
|
.I yytext
|
|
is undefined until the next token is matched, unless the scanner
|
|
was built using
|
|
.B %array.
|
|
This is not the case with
|
|
.I lex
|
|
or the POSIX specification.
|
|
The
|
|
.B \-l
|
|
option does away with this incompatibility.
|
|
.IP -
|
|
The precedence of the
|
|
.B {}
|
|
(numeric range) operator is different.
|
|
.I lex
|
|
interprets "abc{1,3}" as "match one, two, or
|
|
three occurrences of 'abc'", whereas
|
|
.I flex
|
|
interprets it as "match 'ab'
|
|
followed by one, two, or three occurrences of 'c'".
|
|
The latter is in agreement with the POSIX specification.
|
|
.IP -
|
|
The precedence of the
|
|
.B ^
|
|
operator is different.
|
|
.I lex
|
|
interprets "^foo|bar" as "match either 'foo' at the beginning of a line,
|
|
or 'bar' anywhere", whereas
|
|
.I flex
|
|
interprets it as "match either 'foo' or 'bar' if they come at the beginning
|
|
of a line".
|
|
The latter is in agreement with the POSIX specification.
|
|
.IP -
|
|
The special table-size declarations such as
|
|
.B %a
|
|
supported by
|
|
.I lex
|
|
are not required by
|
|
.I flex
|
|
scanners;
|
|
.I flex
|
|
ignores them.
|
|
.IP -
|
|
The name
|
|
.bd
|
|
FLEX_SCANNER
|
|
is #define'd so scanners may be written for use with either
|
|
.I flex
|
|
or
|
|
.I lex.
|
|
Scanners also include
|
|
.B YY_FLEX_MAJOR_VERSION
|
|
and
|
|
.B YY_FLEX_MINOR_VERSION
|
|
indicating which version of
|
|
.I flex
|
|
generated the scanner
|
|
(for example, for the 2.5 release, these defines would be 2 and 5
|
|
respectively).
|
|
.PP
|
|
The following
|
|
.I flex
|
|
features are not included in
|
|
.I lex
|
|
or the POSIX specification:
|
|
.nf
|
|
|
|
C++ scanners
|
|
%option
|
|
start condition scopes
|
|
start condition stacks
|
|
interactive/non-interactive scanners
|
|
yy_scan_string() and friends
|
|
yyterminate()
|
|
yy_set_interactive()
|
|
yy_set_bol()
|
|
YY_AT_BOL()
|
|
\*[Lt]\*[Lt]EOF\*[Gt]\*[Gt]
|
|
\*[Lt]*\*[Gt]
|
|
YY_DECL
|
|
YY_START
|
|
YY_USER_ACTION
|
|
YY_USER_INIT
|
|
#line directives
|
|
%{}'s around actions
|
|
multiple actions on a line
|
|
|
|
.fi
|
|
plus almost all of the flex flags.
|
|
The last feature in the list refers to the fact that with
|
|
.I flex
|
|
you can put multiple actions on the same line, separated with
|
|
semi-colons, while with
|
|
.I lex,
|
|
the following
|
|
.nf
|
|
|
|
foo handle_foo(); ++num_foos_seen;
|
|
|
|
.fi
|
|
is (rather surprisingly) truncated to
|
|
.nf
|
|
|
|
foo handle_foo();
|
|
|
|
.fi
|
|
.I flex
|
|
does not truncate the action.
|
|
Actions that are not enclosed in
|
|
braces are simply terminated at the end of the line.
|
|
.SH DIAGNOSTICS
|
|
.PP
|
|
.I warning, rule cannot be matched
|
|
indicates that the given rule
|
|
cannot be matched because it follows other rules that will
|
|
always match the same text as it.
|
|
For
|
|
example, in the following "foo" cannot be matched because it comes after
|
|
an identifier "catch-all" rule:
|
|
.nf
|
|
|
|
[a-z]+ got_identifier();
|
|
foo got_foo();
|
|
|
|
.fi
|
|
Using
|
|
.B REJECT
|
|
in a scanner suppresses this warning.
|
|
.PP
|
|
.I warning,
|
|
.B \-s
|
|
.I
|
|
option given but default rule can be matched
|
|
means that it is possible (perhaps only in a particular start condition)
|
|
that the default rule (match any single character) is the only one
|
|
that will match a particular input.
|
|
Since
|
|
.B \-s
|
|
was given, presumably this is not intended.
|
|
.PP
|
|
.I reject_used_but_not_detected undefined
|
|
or
|
|
.I yymore_used_but_not_detected undefined -
|
|
These errors can occur at compile time.
|
|
They indicate that the scanner uses
|
|
.B REJECT
|
|
or
|
|
.B yymore()
|
|
but that
|
|
.I flex
|
|
failed to notice the fact, meaning that
|
|
.I flex
|
|
scanned the first two sections looking for occurrences of these actions
|
|
and failed to find any, but somehow you snuck some in (via a #include
|
|
file, for example).
|
|
Use
|
|
.B %option reject
|
|
or
|
|
.B %option yymore
|
|
to indicate to flex that you really do use these features.
|
|
.PP
|
|
.I flex scanner jammed -
|
|
a scanner compiled with
|
|
.B \-s
|
|
has encountered an input string which wasn't matched by
|
|
any of its rules.
|
|
This error can also occur due to internal problems.
|
|
.PP
|
|
.I token too large, exceeds YYLMAX -
|
|
your scanner uses
|
|
.B %array
|
|
and one of its rules matched a string longer than the
|
|
.B YYLMAX
|
|
constant (8K bytes by default).
|
|
You can increase the value by
|
|
#define'ing
|
|
.B YYLMAX
|
|
in the definitions section of your
|
|
.I flex
|
|
input.
|
|
.PP
|
|
.I scanner requires \-8 flag to
|
|
.I use the character 'x' -
|
|
Your scanner specification includes recognizing the 8-bit character
|
|
.I 'x'
|
|
and you did not specify the \-8 flag, and your scanner defaulted to 7-bit
|
|
because you used the
|
|
.B \-Cf
|
|
or
|
|
.B \-CF
|
|
table compression options.
|
|
See the discussion of the
|
|
.B \-7
|
|
flag for details.
|
|
.PP
|
|
.I flex scanner push-back overflow -
|
|
you used
|
|
.B unput()
|
|
to push back so much text that the scanner's buffer could not hold
|
|
both the pushed-back text and the current token in
|
|
.B yytext.
|
|
Ideally the scanner should dynamically resize the buffer in this case, but at
|
|
present it does not.
|
|
.PP
|
|
.I
|
|
input buffer overflow, can't enlarge buffer because scanner uses REJECT -
|
|
the scanner was working on matching an extremely large token and needed
|
|
to expand the input buffer.
|
|
This doesn't work with scanners that use
|
|
.B
|
|
REJECT.
|
|
.PP
|
|
.I
|
|
fatal flex scanner internal error--end of buffer missed -
|
|
This can occur in an scanner which is reentered after a long-jump
|
|
has jumped out (or over) the scanner's activation frame.
|
|
Before reentering the scanner, use:
|
|
.nf
|
|
|
|
yyrestart( yyin );
|
|
|
|
.fi
|
|
or, as noted above, switch to using the C++ scanner class.
|
|
.PP
|
|
.I too many start conditions in \*[Lt]\*[Gt] construct! -
|
|
you listed more start conditions in a \*[Lt]\*[Gt] construct than exist (so
|
|
you must have listed at least one of them twice).
|
|
.SH FILES
|
|
.TP
|
|
.B \-lfl
|
|
library with which scanners must be linked.
|
|
.TP
|
|
.I lex.yy.c
|
|
generated scanner (called
|
|
.I lexyy.c
|
|
on some systems).
|
|
.TP
|
|
.I lex.yy.cc
|
|
generated C++ scanner class, when using
|
|
.B -+.
|
|
.TP
|
|
.I \*[Lt]FlexLexer.h\*[Gt]
|
|
header file defining the C++ scanner base class,
|
|
.B FlexLexer,
|
|
and its derived class,
|
|
.B yyFlexLexer.
|
|
.TP
|
|
.I flex.skl
|
|
skeleton scanner.
|
|
This file is only used when building flex, not when flex executes.
|
|
.TP
|
|
.I lex.backup
|
|
backing-up information for
|
|
.B \-b
|
|
flag (called
|
|
.I lex.bck
|
|
on some systems).
|
|
.SH DEFICIENCIES / BUGS
|
|
.PP
|
|
Some trailing context
|
|
patterns cannot be properly matched and generate
|
|
warning messages ("dangerous trailing context").
|
|
These are patterns where the ending of the
|
|
first part of the rule matches the beginning of the second
|
|
part, such as "zx*/xy*", where the 'x*' matches the 'x' at
|
|
the beginning of the trailing context.
|
|
(Note that the POSIX draft
|
|
states that the text matched by such patterns is undefined.)
|
|
.PP
|
|
For some trailing context rules, parts which are actually fixed-length are
|
|
not recognized as such, leading to the abovementioned performance loss.
|
|
In particular, parts using '|' or {n} (such as "foo{3}") are always
|
|
considered variable-length.
|
|
.PP
|
|
Combining trailing context with the special '|' action can result in
|
|
.I fixed
|
|
trailing context being turned into the more expensive
|
|
.I variable
|
|
trailing context.
|
|
For example, in the following:
|
|
.nf
|
|
|
|
%%
|
|
abc |
|
|
xyz/def
|
|
|
|
.fi
|
|
.PP
|
|
Use of
|
|
.B unput()
|
|
invalidates yytext and yyleng, unless the
|
|
.B %array
|
|
directive
|
|
or the
|
|
.B \-l
|
|
option has been used.
|
|
.PP
|
|
Pattern-matching of NUL's is substantially slower than matching other
|
|
characters.
|
|
.PP
|
|
Dynamic resizing of the input buffer is slow, as it entails rescanning
|
|
all the text matched so far by the current (generally huge) token.
|
|
.PP
|
|
Due to both buffering of input and read-ahead, you cannot intermix
|
|
calls to \*[Lt]stdio.h\*[Gt] routines, such as, for example,
|
|
.B getchar(),
|
|
with
|
|
.I flex
|
|
rules and expect it to work.
|
|
Call
|
|
.B input()
|
|
instead.
|
|
.PP
|
|
The total table entries listed by the
|
|
.B \-v
|
|
flag excludes the number of table entries needed to determine
|
|
what rule has been matched.
|
|
The number of entries is equal
|
|
to the number of DFA states if the scanner does not use
|
|
.B REJECT,
|
|
and somewhat greater than the number of states if it does.
|
|
.PP
|
|
.B REJECT
|
|
cannot be used with the
|
|
.B \-f
|
|
or
|
|
.B \-F
|
|
options.
|
|
.PP
|
|
The
|
|
.I flex
|
|
internal algorithms need documentation.
|
|
.SH SEE ALSO
|
|
.PP
|
|
lex(1), yacc(1), sed(1), awk(1).
|
|
.PP
|
|
John Levine, Tony Mason, and Doug Brown,
|
|
.I Lex \*[Am] Yacc,
|
|
O'Reilly and Associates.
|
|
Be sure to get the 2nd edition.
|
|
.PP
|
|
M. E. Lesk and E. Schmidt,
|
|
.I LEX \- Lexical Analyzer Generator
|
|
.PP
|
|
Alfred Aho, Ravi Sethi and Jeffrey Ullman,
|
|
.I Compilers: Principles, Techniques and Tools,
|
|
Addison-Wesley (1986).
|
|
Describes the pattern-matching techniques used by
|
|
.I flex
|
|
(deterministic finite automata).
|
|
.SH AUTHOR
|
|
Vern Paxson, with the help of many ideas and much inspiration from
|
|
Van Jacobson.
|
|
Original version by Jef Poskanzer.
|
|
The fast table
|
|
representation is a partial implementation of a design done by Van
|
|
Jacobson.
|
|
The implementation was done by Kevin Gong and Vern Paxson.
|
|
.PP
|
|
Thanks to the many
|
|
.I flex
|
|
beta-testers, feedbackers, and contributors, especially Francois Pinard,
|
|
Casey Leedom,
|
|
Robert Abramovitz,
|
|
Stan Adermann, Terry Allen, David Barker-Plummer, John Basrai,
|
|
Neal Becker, Nelson H.F. Beebe, benson@odi.com,
|
|
Karl Berry, Peter A. Bigot, Simon Blanchard,
|
|
Keith Bostic, Frederic Brehm, Ian Brockbank, Kin Cho, Nick Christopher,
|
|
Brian Clapper, J.T. Conklin,
|
|
Jason Coughlin, Bill Cox, Nick Cropper, Dave Curtis, Scott David
|
|
Daniels, Chris G. Demetriou, Theo Deraadt,
|
|
Mike Donahue, Chuck Doucette, Tom Epperly, Leo Eskin,
|
|
Chris Faylor, Chris Flatters, Jon Forrest, Jeffrey Friedl,
|
|
Joe Gayda, Kaveh R. Ghazi, Wolfgang Glunz,
|
|
Eric Goldman, Christopher M. Gould, Ulrich Grepel, Peer Griebel,
|
|
Jan Hajic, Charles Hemphill, NORO Hideo,
|
|
Jarkko Hietaniemi, Scott Hofmann,
|
|
Jeff Honig, Dana Hudes, Eric Hughes, John Interrante,
|
|
Ceriel Jacobs, Michal Jaegermann, Sakari Jalovaara, Jeffrey R. Jones,
|
|
Henry Juengst, Klaus Kaempf, Jonathan I. Kamens, Terrence O Kane,
|
|
Amir Katz, ken@ken.hilco.com, Kevin B. Kenny,
|
|
Steve Kirsch, Winfried Koenig, Marq Kole, Ronald Lamprecht,
|
|
Greg Lee, Rohan Lenard, Craig Leres, John Levine, Steve Liddle,
|
|
David Loffredo, Mike Long,
|
|
Mohamed el Lozy, Brian Madsen, Malte, Joe Marshall,
|
|
Bengt Martensson, Chris Metcalf,
|
|
Luke Mewburn, Jim Meyering, R. Alexander Milowski, Erik Naggum,
|
|
G.T. Nicol, Landon Noll, James Nordby, Marc Nozell,
|
|
Richard Ohnemus, Karsten Pahnke,
|
|
Sven Panne, Roland Pesch, Walter Pelissero, Gaumond
|
|
Pierre, Esmond Pitt, Jef Poskanzer, Joe Rahmeh, Jarmo Raiha,
|
|
Frederic Raimbault, Pat Rankin, Rick Richardson,
|
|
Kevin Rodgers, Kai Uwe Rommel, Jim Roskind, Alberto Santini,
|
|
Andreas Scherer, Darrell Schiebel, Raf Schietekat,
|
|
Doug Schmidt, Philippe Schnoebelen, Andreas Schwab,
|
|
Larry Schwimmer, Alex Siegel, Eckehard Stolz, Jan-Erik Strvmquist,
|
|
Mike Stump, Paul Stuart, Dave Tallman, Ian Lance Taylor,
|
|
Chris Thewalt, Richard M. Timoney, Jodi Tsai,
|
|
Paul Tuinenga, Gary Weik, Frank Whaley, Gerhard Wilhelms, Kent Williams, Ken
|
|
Yap, Ron Zellar, Nathan Zelle, David Zuhn,
|
|
and those whose names have slipped my marginal
|
|
mail-archiving skills but whose contributions are appreciated all the
|
|
same.
|
|
.PP
|
|
Thanks to Keith Bostic, Jon Forrest, Noah Friedman,
|
|
John Gilmore, Craig Leres, John Levine, Bob Mulcahy, G.T.
|
|
Nicol, Francois Pinard, Rich Salz, and Richard Stallman for help with various
|
|
distribution headaches.
|
|
.PP
|
|
Thanks to Esmond Pitt and Earle Horton for 8-bit character support; to
|
|
Benson Margulies and Fred Burke for C++ support; to Kent Williams and Tom
|
|
Epperly for C++ class support; to Ove Ewerlid for support of NUL's; and to
|
|
Eric Hughes for support of multiple buffers.
|
|
.PP
|
|
This work was primarily done when I was with the Real Time Systems Group
|
|
at the Lawrence Berkeley Laboratory in Berkeley, CA.
|
|
Many thanks to all there for the support I received.
|
|
.PP
|
|
Send comments to vern@ee.lbl.gov.
|