mirror of
https://github.com/cloudwu/skynet.git
synced 2026-07-25 12:43:09 +00:00
add some lua library
This commit is contained in:
77
lpeg/HISTORY
Normal file
77
lpeg/HISTORY
Normal file
@@ -0,0 +1,77 @@
|
||||
HISTORY for LPeg 0.10
|
||||
|
||||
* Changes from version 0.9 to 0.10
|
||||
-------------------------------
|
||||
+ backtrack stack has configurable size
|
||||
+ better error messages
|
||||
+ Notation for non-terminals in 're' back to A instead o <A>
|
||||
+ experimental look-behind pattern
|
||||
+ support for external extensions
|
||||
+ works with Lua 5.2
|
||||
+ consumes less C stack
|
||||
|
||||
- "and" predicates do not keep captures
|
||||
|
||||
* Changes from version 0.8 to 0.9
|
||||
-------------------------------
|
||||
+ The accumulator capture was replaced by a fold capture;
|
||||
programs that used the old 'lpeg.Ca' will need small changes.
|
||||
+ Some support for character classes from old C locales.
|
||||
+ A new named-group capture.
|
||||
|
||||
* Changes from version 0.7 to 0.8
|
||||
-------------------------------
|
||||
+ New "match-time" capture.
|
||||
+ New "argument capture" that allows passing arguments into the pattern.
|
||||
+ Better documentation for 're'.
|
||||
+ Several small improvements for 're'.
|
||||
+ The 're' module has an incompatibility with previous versions:
|
||||
now, any use of a non-terminal must be enclosed in angle brackets
|
||||
(like <B>).
|
||||
|
||||
* Changes from version 0.6 to 0.7
|
||||
-------------------------------
|
||||
+ Several improvements in module 're':
|
||||
- better documentation;
|
||||
- support for most captures (all but accumulator);
|
||||
- limited repetitions p{n,m}.
|
||||
+ Small improvements in efficiency.
|
||||
+ Several small bugs corrected (special thanks to Hans Hagen
|
||||
and Taco Hoekwater).
|
||||
|
||||
* Changes from version 0.5 to 0.6
|
||||
-------------------------------
|
||||
+ Support for non-numeric indices in grammars.
|
||||
+ Some bug fixes (thanks to the luatex team).
|
||||
+ Some new optimizations; (thanks to Mike Pall).
|
||||
+ A new page layout (thanks to Andre Carregal).
|
||||
+ Minimal documentation for module 're'.
|
||||
|
||||
* Changes from version 0.4 to 0.5
|
||||
-------------------------------
|
||||
+ Several optimizations.
|
||||
+ lpeg.P now accepts booleans.
|
||||
+ Some new examples.
|
||||
+ A proper license.
|
||||
+ Several small improvements.
|
||||
|
||||
* Changes from version 0.3 to 0.4
|
||||
-------------------------------
|
||||
+ Static check for loops in repetitions and grammars.
|
||||
+ Removed label option in captures.
|
||||
+ The implementation of captures uses less memory.
|
||||
|
||||
* Changes from version 0.2 to 0.3
|
||||
-------------------------------
|
||||
+ User-defined patterns in Lua.
|
||||
+ Several new captures.
|
||||
|
||||
* Changes from version 0.1 to 0.2
|
||||
-------------------------------
|
||||
+ Several small corrections.
|
||||
+ Handles embedded zeros like any other character.
|
||||
+ Capture "name" can be any Lua value.
|
||||
+ Unlimited number of captures.
|
||||
+ Match gets an optional initial position.
|
||||
|
||||
(end of HISTORY)
|
||||
BIN
lpeg/lpeg-128.gif
Normal file
BIN
lpeg/lpeg-128.gif
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 4.8 KiB |
2405
lpeg/lpeg.c
Normal file
2405
lpeg/lpeg.c
Normal file
File diff suppressed because it is too large
Load Diff
38
lpeg/lpeg.h
Normal file
38
lpeg/lpeg.h
Normal file
@@ -0,0 +1,38 @@
|
||||
/*
|
||||
** $Id: lpeg.h,v 1.1 2009/12/23 16:15:36 roberto Exp $
|
||||
** LPeg - PEG pattern matching for Lua
|
||||
** Copyright 2009, Lua.org & PUC-Rio (see 'lpeg.html' for license)
|
||||
** written by Roberto Ierusalimschy
|
||||
*/
|
||||
|
||||
#ifndef lpeg_h
|
||||
#define lpeg_h
|
||||
|
||||
#include "lua.h"
|
||||
|
||||
|
||||
#define KEYNEWPATT "lpeg.newpf"
|
||||
|
||||
|
||||
/*
|
||||
** type of extension functions that define new "patterns" for LPEG
|
||||
** It should return the new current position or NULL if match fails
|
||||
*/
|
||||
typedef const char *(*PattFunc) (const char *s, /* current position */
|
||||
const char *e, /* string end */
|
||||
const char *o, /* string start */
|
||||
const void *ud); /* user data */
|
||||
|
||||
/*
|
||||
** function to create new patterns based on 'PattFunc' functions.
|
||||
** This function is available at *registry[KEYNEWPATT]. (Notice
|
||||
** the extra indirection; the userdata at the registry points to
|
||||
** a variable that points to the function. In ANSI C a void* cannot
|
||||
** point to a function.)
|
||||
*/
|
||||
typedef void (*Newpf) (lua_State *L,
|
||||
PattFunc f, /* pattern */
|
||||
const void *ud, /* (user) data to be passed to 'f' */
|
||||
size_t l); /* size of data to be passed to 'f' */
|
||||
|
||||
#endif
|
||||
1423
lpeg/lpeg.html
Normal file
1423
lpeg/lpeg.html
Normal file
File diff suppressed because it is too large
Load Diff
BIN
lpeg/lpeg.o
Normal file
BIN
lpeg/lpeg.o
Normal file
Binary file not shown.
42
lpeg/makefile
Normal file
42
lpeg/makefile
Normal file
@@ -0,0 +1,42 @@
|
||||
LIBNAME = lpeg
|
||||
LUADIR = /usr/include/lua5.1/
|
||||
|
||||
COPT = -O2 -DNDEBUG
|
||||
|
||||
CWARNS = -Wall -Wextra -pedantic \
|
||||
-Waggregate-return \
|
||||
-Wbad-function-cast \
|
||||
-Wcast-align \
|
||||
-Wcast-qual \
|
||||
-Wdeclaration-after-statement \
|
||||
-Wdisabled-optimization \
|
||||
-Wmissing-prototypes \
|
||||
-Wnested-externs \
|
||||
-Wpointer-arith \
|
||||
-Wshadow \
|
||||
-Wsign-compare \
|
||||
-Wstrict-prototypes \
|
||||
-Wundef \
|
||||
-Wwrite-strings \
|
||||
# -Wunreachable-code \
|
||||
|
||||
|
||||
CFLAGS = $(CWARNS) $(COPT) -ansi -I$(LUADIR)
|
||||
CC = gcc
|
||||
|
||||
# For Linux
|
||||
DLLFLAGS = -shared -fpic
|
||||
ENV =
|
||||
|
||||
# For Mac OS
|
||||
# ENV = MACOSX_DEPLOYMENT_TARGET=10.4
|
||||
# DLLFLAGS = -bundle -undefined dynamic_lookup
|
||||
|
||||
lpeg.so: lpeg.o
|
||||
env $(ENV) $(CC) $(DLLFLAGS) lpeg.o -o lpeg.so
|
||||
|
||||
lpeg.o: makefile lpeg.c lpeg.h
|
||||
|
||||
test: test.lua re.lua lpeg.so
|
||||
test.lua
|
||||
|
||||
486
lpeg/re.html
Normal file
486
lpeg/re.html
Normal file
@@ -0,0 +1,486 @@
|
||||
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
|
||||
"http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
|
||||
<html>
|
||||
<head>
|
||||
<title>LPeg.re - Regex syntax for LPEG</title>
|
||||
<link rel="stylesheet"
|
||||
href="http://www.inf.puc-rio.br/~roberto/lpeg/doc.css"
|
||||
type="text/css"/>
|
||||
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8"/>
|
||||
</head>
|
||||
<body>
|
||||
|
||||
<!-- $Id: re.html,v 1.17 2011/01/10 15:08:06 roberto Exp $ -->
|
||||
|
||||
<div id="container">
|
||||
|
||||
<div id="product">
|
||||
<div id="product_logo">
|
||||
<a href="http://www.inf.puc-rio.br/~roberto/lpeg/">
|
||||
<img alt="LPeg logo" src="lpeg-128.gif"/>
|
||||
</a>
|
||||
</div>
|
||||
<div id="product_name"><big><strong>LPeg.re</strong></big></div>
|
||||
<div id="product_description">
|
||||
Regex syntax for LPEG
|
||||
</div>
|
||||
</div> <!-- id="product" -->
|
||||
|
||||
<div id="main">
|
||||
|
||||
<div id="navigation">
|
||||
<h1>re</h1>
|
||||
|
||||
<ul>
|
||||
<li><a href="#basic">Basic Constructions</a></li>
|
||||
<li><a href="#func">Functions</a></li>
|
||||
<li><a href="#ex">Some Examples</a></li>
|
||||
<li><a href="#license">License</a></li>
|
||||
</ul>
|
||||
</li>
|
||||
</ul>
|
||||
</div> <!-- id="navigation" -->
|
||||
|
||||
<div id="content">
|
||||
|
||||
<h2><a name="basic"></a>The <code>re</code> Module</h2>
|
||||
|
||||
<p>
|
||||
The <code>re</code> module
|
||||
(provided by file <code>re.lua</code> in the distribution)
|
||||
supports a somewhat conventional regex syntax
|
||||
for pattern usage within <a href="lpeg.html">LPeg</a>.
|
||||
</p>
|
||||
|
||||
<p>
|
||||
The next table summarizes <code>re</code>'s syntax.
|
||||
A <code>p</code> represents an arbitrary pattern;
|
||||
<code>num</code> represents a number (<code>[0-9]+</code>);
|
||||
<code>name</code> represents an identifier
|
||||
(<code>[a-zA-Z][a-zA-Z0-9_]*</code>).
|
||||
Constructions are listed in order of decreasing precedence.
|
||||
<table border="1">
|
||||
<tbody><tr><td><b>Syntax</b></td><td><b>Description</b></td></tr>
|
||||
<tr><td><code>( p )</code></td> <td>grouping</td></tr>
|
||||
<tr><td><code>'string'</code></td> <td>literal string</td></tr>
|
||||
<tr><td><code>"string"</code></td> <td>literal string</td></tr>
|
||||
<tr><td><code>[class]</code></td> <td>character class</td></tr>
|
||||
<tr><td><code>.</code></td> <td>any character</td></tr>
|
||||
<tr><td><code>%name</code></td>
|
||||
<td>pattern <code>defs[name]</code> or a pre-defined pattern</td></tr>
|
||||
<tr><td><code>name</code></td><td>non terminal</td></tr>
|
||||
<tr><td><code><name></code></td><td>non terminal</td></tr>
|
||||
<tr><td><code>{}</code></td> <td>position capture</td></tr>
|
||||
<tr><td><code>{ p }</code></td> <td>simple capture</td></tr>
|
||||
<tr><td><code>{: p :}</code></td> <td>anonymous group capture</td></tr>
|
||||
<tr><td><code>{:name: p :}</code></td> <td>named group capture</td></tr>
|
||||
<tr><td><code>{~ p ~}</code></td> <td>substitution capture</td></tr>
|
||||
<tr><td><code>=name</code></td> <td>back reference
|
||||
</td></tr>
|
||||
<tr><td><code>p ?</code></td> <td>optional match</td></tr>
|
||||
<tr><td><code>p *</code></td> <td>zero or more repetitions</td></tr>
|
||||
<tr><td><code>p +</code></td> <td>one or more repetitions</td></tr>
|
||||
<tr><td><code>p^num</code></td> <td>exactly <code>n</code> repetitions</td></tr>
|
||||
<tr><td><code>p^+num</code></td>
|
||||
<td>at least <code>n</code> repetitions</td></tr>
|
||||
<tr><td><code>p^-num</code></td>
|
||||
<td>at most <code>n</code> repetitions</td></tr>
|
||||
<tr><td><code>p -> 'string'</code></td> <td>string capture</td></tr>
|
||||
<tr><td><code>p -> "string"</code></td> <td>string capture</td></tr>
|
||||
<tr><td><code>p -> {}</code></td> <td>table capture</td></tr>
|
||||
<tr><td><code>p -> name</code></td> <td>function/query/string capture
|
||||
equivalent to <code>p / defs[name]</code></td></tr>
|
||||
<tr><td><code>p => name</code></td> <td>match-time capture
|
||||
equivalent to <code>lpeg.Cmt(p, defs[name])</code></td></tr>
|
||||
<tr><td><code>& p</code></td> <td>and predicate</td></tr>
|
||||
<tr><td><code>! p</code></td> <td>not predicate</td></tr>
|
||||
<tr><td><code>p1 p2</code></td> <td>concatenation</td></tr>
|
||||
<tr><td><code>p1 / p2</code></td> <td>ordered choice</td></tr>
|
||||
<tr><td>(<code>name <- p</code>)<sup>+</sup></td> <td>grammar</td></tr>
|
||||
</tbody></table>
|
||||
<p>
|
||||
Any space appearing in a syntax description can be
|
||||
replaced by zero or more space characters and Lua-style comments
|
||||
(<code>--</code> until end of line).
|
||||
</p>
|
||||
|
||||
<p>
|
||||
Character classes define sets of characters.
|
||||
An initial <code>^</code> complements the resulting set.
|
||||
A range <em>x</em><code>-</code><em>y</em> includes in the set
|
||||
all characters with codes between the codes of <em>x</em> and <em>y</em>.
|
||||
A pre-defined class <code>%</code><em>name</em> includes all
|
||||
characters of that class.
|
||||
A simple character includes itself in the set.
|
||||
The only special characters inside a class are <code>^</code>
|
||||
(special only if it is the first character);
|
||||
<code>]</code>
|
||||
(can be included in the set as the first character,
|
||||
after the optional <code>^</code>);
|
||||
<code>%</code> (special only if followed by a letter);
|
||||
and <code>-</code>
|
||||
(can be included in the set as the first or the last character).
|
||||
</p>
|
||||
|
||||
<p>
|
||||
Currently the pre-defined classes are similar to those from the
|
||||
Lua's string library
|
||||
(<code>%a</code> for letters,
|
||||
<code>%A</code> for non letters, etc.).
|
||||
There is also a class <code>%nl</code>
|
||||
containing only the newline character,
|
||||
which is particularly handy for grammars written inside long strings,
|
||||
as long strings do not interpret escape sequences like <code>\n</code>.
|
||||
</p>
|
||||
|
||||
|
||||
<h2><a name="func">Functions</a></h2>
|
||||
|
||||
<h3><code>re.compile (string, [, defs])</code></h3>
|
||||
<p>
|
||||
Compiles the given string and
|
||||
returns an equivalent LPeg pattern.
|
||||
The given string may define either an expression or a grammar.
|
||||
The optional <code>defs</code> table provides extra Lua values
|
||||
to be used by the pattern.
|
||||
</p>
|
||||
|
||||
<h3><code>re.find (subject, pattern [, init])</code></h3>
|
||||
<p>
|
||||
Searches the given pattern in the given subject.
|
||||
If it finds a match,
|
||||
returns the index where this occurrence starts,
|
||||
plus the captures made by the pattern (if any).
|
||||
Otherwise, returns nil.
|
||||
</p>
|
||||
|
||||
<p>
|
||||
An optional numeric argument <code>init</code> makes the search
|
||||
starts at that position in the subject string.
|
||||
As usual in Lua libraries,
|
||||
a negative value counts from the end.
|
||||
</p>
|
||||
|
||||
<h3><code>re.match (subject, pattern)</code></h3>
|
||||
<p>
|
||||
Matches the given pattern against the given subject.
|
||||
</p>
|
||||
|
||||
<h3><code>re.updatelocale ()</code></h3>
|
||||
<p>
|
||||
Updates the pre-defined character classes to the current locale.
|
||||
</p>
|
||||
|
||||
|
||||
<h2><a name="ex">Some Examples</a></h2>
|
||||
|
||||
<h3>A complete simple program</h3>
|
||||
<p>
|
||||
The next code shows a simple complete Lua program using
|
||||
the <code>re</code> module:
|
||||
</p>
|
||||
<pre class="example">
|
||||
local re = require"re"
|
||||
|
||||
-- find the position of the first number in a string
|
||||
print(re.find("the number 423 is odd", "[0-9]+")) --> 12
|
||||
|
||||
-- similar, but also captures (and returns) the number
|
||||
print(re.find("the number 423 is odd", "{[0-9]+}")) --> 12 423
|
||||
|
||||
-- returns all words in a string
|
||||
print(re.match("the number 423 is odd", "({%a+} / .)*"))
|
||||
--> the number is odd
|
||||
</pre>
|
||||
|
||||
|
||||
<h3>Balanced parentheses</h3>
|
||||
<p>
|
||||
The following call will produce the same pattern produced by the
|
||||
Lua expression in the
|
||||
<a href="lpeg.html#balanced">balanced parentheses</a> example:
|
||||
</p>
|
||||
<pre class="example">
|
||||
b = re.compile[[ balanced <- "(" ([^()] / balanced)* ")" ]]
|
||||
</pre>
|
||||
|
||||
<h3>String reversal</h3>
|
||||
<p>
|
||||
The next example reverses a string:
|
||||
</p>
|
||||
<pre class="example">
|
||||
rev = re.compile[[ R <- (!.) -> '' / ({.} R) -> '%2%1']]
|
||||
print(rev:match"0123456789") --> 9876543210
|
||||
</pre>
|
||||
|
||||
<h3>CSV decoder</h3>
|
||||
<p>
|
||||
The next example replicates the <a href="lpeg.html#CSV">CSV decoder</a>:
|
||||
</p>
|
||||
<pre class="example">
|
||||
record = re.compile[[
|
||||
record <- ( field (',' field)* ) -> {} (%nl / !.)
|
||||
field <- escaped / nonescaped
|
||||
nonescaped <- { [^,"%nl]* }
|
||||
escaped <- '"' {~ ([^"] / '""' -> '"')* ~} '"'
|
||||
]]
|
||||
</pre>
|
||||
|
||||
<h3>Lua's long strings</h3>
|
||||
<p>
|
||||
The next example matches Lua long strings:
|
||||
</p>
|
||||
<pre class="example">
|
||||
c = re.compile([[
|
||||
longstring <- ('[' {:eq: '='* :} '[' close) -> void
|
||||
close <- ']' =eq ']' / . close
|
||||
]], {void = function () end})
|
||||
|
||||
print(c:match'[==[]]===]]]]==]===[]') --> 17
|
||||
</pre>
|
||||
|
||||
<h3>Abstract Syntax Trees</h3>
|
||||
<p>
|
||||
This example shows a simple way to build an
|
||||
abstract syntax tree (AST) for a given grammar.
|
||||
To keep our example simple,
|
||||
let us consider the following grammar
|
||||
for lists of names:
|
||||
</p>
|
||||
<pre class="example">
|
||||
p = re.compile[[
|
||||
listname <- (name s)*
|
||||
name <- [a-z][a-z]*
|
||||
s <- %s*
|
||||
]]
|
||||
</pre>
|
||||
<p>
|
||||
Now, we will add captures to build a corresponding AST.
|
||||
As a first step, the pattern will build a table to
|
||||
represent each non terminal;
|
||||
terminals will be represented by their corresponding strings:
|
||||
</p>
|
||||
<pre class="example">
|
||||
c = re.compile[[
|
||||
listname <- (name s)* -> {}
|
||||
name <- {[a-z][a-z]*} -> {}
|
||||
s <- %s*
|
||||
]]
|
||||
</pre>
|
||||
<p>
|
||||
Now, a match against <code>"hi hello bye"</code>
|
||||
results in the table
|
||||
<code>{{"hi"}, {"hello"}, {"bye"}}</code>.
|
||||
</p>
|
||||
<p>
|
||||
For such a simple grammar,
|
||||
this AST is more than enough;
|
||||
actually, the tables around each single name
|
||||
are already overkilling.
|
||||
More complex grammars,
|
||||
however, may need some more structure.
|
||||
Specifically,
|
||||
it would be useful if each table had
|
||||
a <code>tag</code> field telling what non terminal
|
||||
that table represents.
|
||||
We can add such a tag using
|
||||
<a href="lpeg.html/#cap-g">named group captures</a>:
|
||||
</p>
|
||||
<pre class="example">
|
||||
x = re.compile[[
|
||||
listname <- ({:tag: '' -> 'list':} (name s)*) -> {}
|
||||
name <- ({:tag: '' -> 'id':} {[a-z][a-z]*}) -> {}
|
||||
s <- ' '*
|
||||
]]
|
||||
</pre>
|
||||
<p>
|
||||
With these group captures,
|
||||
a match against <code>"hi hello bye"</code>
|
||||
results in the following table:
|
||||
</p>
|
||||
<pre class="example">
|
||||
{tag="list",
|
||||
{tag="id", "hi"},
|
||||
{tag="id", "hello"},
|
||||
{tag="id", "bye"}
|
||||
}
|
||||
</pre>
|
||||
|
||||
|
||||
<h3>Indented blocks</h3>
|
||||
<p>
|
||||
This example breaks indented blocks into tables,
|
||||
respecting the indentation:
|
||||
</p>
|
||||
<pre class="example">
|
||||
p = re.compile[[
|
||||
block <- ({:ident:' '*:} line
|
||||
((=ident !' ' line) / &(=ident ' ') block)*) -> {}
|
||||
line <- {[^%nl]*} %nl
|
||||
]]
|
||||
</pre>
|
||||
<p>
|
||||
As an example,
|
||||
consider the following text:
|
||||
</p>
|
||||
<pre class="example">
|
||||
t = p:match[[
|
||||
first line
|
||||
subline 1
|
||||
subline 2
|
||||
second line
|
||||
third line
|
||||
subline 3.1
|
||||
subline 3.1.1
|
||||
subline 3.2
|
||||
]]
|
||||
</pre>
|
||||
<p>
|
||||
The resulting table <code>t</code> will be like this:
|
||||
</p>
|
||||
<pre class="example">
|
||||
{'first line'; {'subline 1'; 'subline 2'; ident = ' '};
|
||||
'second line';
|
||||
'third line'; { 'subline 3.1'; {'subline 3.1.1'; ident = ' '};
|
||||
'subline 3.2'; ident = ' '};
|
||||
ident = ''}
|
||||
</pre>
|
||||
|
||||
<h3>Macro expander</h3>
|
||||
<p>
|
||||
This example implements a simple macro expander.
|
||||
Macros must be defined as part of the pattern,
|
||||
following some simple rules:
|
||||
</p>
|
||||
<pre class="example">
|
||||
p = re.compile[[
|
||||
text <- {~ item* ~}
|
||||
item <- macro / [^()] / '(' item* ')'
|
||||
arg <- ' '* {~ (!',' item)* ~}
|
||||
args <- '(' arg (',' arg)* ')'
|
||||
-- now we define some macros
|
||||
macro <- ('apply' args) -> '%1(%2)'
|
||||
/ ('add' args) -> '%1 + %2'
|
||||
/ ('mul' args) -> '%1 * %2'
|
||||
]]
|
||||
|
||||
print(p:match"add(mul(a,b), apply(f,x))") --> a * b + f(x)
|
||||
</pre>
|
||||
<p>
|
||||
A <code>text</code> is a sequence of items,
|
||||
wherein we apply a substitution capture to expand any macros.
|
||||
An <code>item</code> is either a macro,
|
||||
any character different from parentheses,
|
||||
or a parenthesized expression.
|
||||
A macro argument (<code>arg</code>) is a sequence
|
||||
of items different from a comma.
|
||||
(Note that a comma may appear inside an item,
|
||||
e.g., inside a parenthesized expression.)
|
||||
Again we do a substitution capture to expand any macro
|
||||
in the argument before expanding the outer macro.
|
||||
<code>args</code> is a list of arguments separated by commas.
|
||||
Finally we define the macros.
|
||||
Each macro is a string substitution;
|
||||
it replaces the macro name and its arguments by its corresponding string,
|
||||
with each <code>%</code><em>n</em> replaced by the <em>n</em>-th argument.
|
||||
</p>
|
||||
|
||||
<h3>Patterns</h3>
|
||||
<p>
|
||||
This example shows the complete syntax
|
||||
of patterns accepted by <code>re</code>.
|
||||
</p>
|
||||
<pre class="example">
|
||||
p = [=[
|
||||
|
||||
pattern <- exp !.
|
||||
exp <- S (alternative / grammar)
|
||||
|
||||
alternative <- seq ('/' S seq)*
|
||||
seq <- prefix*
|
||||
prefix <- '&' S prefix / '!' S prefix / suffix
|
||||
suffix <- primary S (([+*?]
|
||||
/ '^' [+-]? num
|
||||
/ '->' S (string / '{}' / name)
|
||||
/ '=>' S name) S)*
|
||||
|
||||
primary <- '(' exp ')' / string / class / defined
|
||||
/ '{:' (name ':')? exp ':}'
|
||||
/ '=' name
|
||||
/ '{}'
|
||||
/ '{~' exp '~}'
|
||||
/ '{' exp '}'
|
||||
/ '.'
|
||||
/ name S !arrow
|
||||
/ '<' name '>' -- old-style non terminals
|
||||
|
||||
grammar <- definition+
|
||||
definition <- name S arrow exp
|
||||
|
||||
class <- '[' '^'? item (!']' item)* ']'
|
||||
item <- defined / range / .
|
||||
range <- . '-' [^]]
|
||||
|
||||
S <- (%s / '--' [^%nl]*)* -- spaces and comments
|
||||
name <- [A-Za-z][A-Za-z0-9_]*
|
||||
arrow <- '<-'
|
||||
num <- [0-9]+
|
||||
string <- '"' [^"]* '"' / "'" [^']* "'"
|
||||
defined <- '%' name
|
||||
|
||||
]=]
|
||||
|
||||
print(re.match(p, p)) -- a self description must match itself
|
||||
</pre>
|
||||
|
||||
|
||||
|
||||
<h2><a name="license">License</a></h2>
|
||||
|
||||
<p>
|
||||
Copyright © 2008-2010 Lua.org, PUC-Rio.
|
||||
</p>
|
||||
<p>
|
||||
Permission is hereby granted, free of charge,
|
||||
to any person obtaining a copy of this software and
|
||||
associated documentation files (the "Software"),
|
||||
to deal in the Software without restriction,
|
||||
including without limitation the rights to use,
|
||||
copy, modify, merge, publish, distribute, sublicense,
|
||||
and/or sell copies of the Software,
|
||||
and to permit persons to whom the Software is
|
||||
furnished to do so,
|
||||
subject to the following conditions:
|
||||
</p>
|
||||
|
||||
<p>
|
||||
The above copyright notice and this permission notice
|
||||
shall be included in all copies or substantial portions of the Software.
|
||||
</p>
|
||||
|
||||
<p>
|
||||
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
||||
EXPRESS OR IMPLIED,
|
||||
INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
||||
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
|
||||
IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
|
||||
DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
|
||||
TORT OR OTHERWISE, ARISING FROM,
|
||||
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
|
||||
THE SOFTWARE.
|
||||
</p>
|
||||
|
||||
</div> <!-- id="content" -->
|
||||
|
||||
</div> <!-- id="main" -->
|
||||
|
||||
<div id="about">
|
||||
<p><small>
|
||||
$Id: re.html,v 1.17 2011/01/10 15:08:06 roberto Exp $
|
||||
</small></p>
|
||||
</div> <!-- id="about" -->
|
||||
|
||||
</div> <!-- id="container" -->
|
||||
|
||||
</body>
|
||||
</html>
|
||||
248
lpeg/re.lua
Normal file
248
lpeg/re.lua
Normal file
@@ -0,0 +1,248 @@
|
||||
-- $Id: re.lua,v 1.39 2010/11/04 19:44:18 roberto Exp $
|
||||
|
||||
-- imported functions and modules
|
||||
local tonumber, type, print, error = tonumber, type, print, error
|
||||
local setmetatable = setmetatable
|
||||
local m = require"lpeg"
|
||||
|
||||
-- 'm' will be used to parse expressions, and 'mm' will be used to
|
||||
-- create expressions; that is, 're' runs on 'm', creating patterns
|
||||
-- on 'mm'
|
||||
local mm = m
|
||||
|
||||
-- pattern's metatable
|
||||
local mt = getmetatable(mm.P(0))
|
||||
|
||||
|
||||
|
||||
-- No more global accesses after this point
|
||||
local version = _VERSION
|
||||
if version == "Lua 5.2" then _ENV = nil end
|
||||
|
||||
|
||||
local any = m.P(1)
|
||||
|
||||
|
||||
-- Pre-defined names
|
||||
local Predef = { nl = m.P"\n" }
|
||||
|
||||
|
||||
local mem
|
||||
local fmem
|
||||
local gmem
|
||||
|
||||
|
||||
local function updatelocale ()
|
||||
mm.locale(Predef)
|
||||
Predef.a = Predef.alpha
|
||||
Predef.c = Predef.cntrl
|
||||
Predef.d = Predef.digit
|
||||
Predef.g = Predef.graph
|
||||
Predef.l = Predef.lower
|
||||
Predef.p = Predef.punct
|
||||
Predef.s = Predef.space
|
||||
Predef.u = Predef.upper
|
||||
Predef.w = Predef.alnum
|
||||
Predef.x = Predef.xdigit
|
||||
Predef.A = any - Predef.a
|
||||
Predef.C = any - Predef.c
|
||||
Predef.D = any - Predef.d
|
||||
Predef.G = any - Predef.g
|
||||
Predef.L = any - Predef.l
|
||||
Predef.P = any - Predef.p
|
||||
Predef.S = any - Predef.s
|
||||
Predef.U = any - Predef.u
|
||||
Predef.W = any - Predef.w
|
||||
Predef.X = any - Predef.x
|
||||
mem = {} -- restart memoization
|
||||
fmem = {}
|
||||
gmem = {}
|
||||
local mt = {__mode = "v"}
|
||||
setmetatable(mem, mt)
|
||||
setmetatable(fmem, mt)
|
||||
setmetatable(gmem, mt)
|
||||
end
|
||||
|
||||
|
||||
updatelocale()
|
||||
|
||||
|
||||
|
||||
local I = m.P(function (s,i) print(i, s:sub(1, i-1)); return i end)
|
||||
|
||||
|
||||
local function getdef (id, Defs)
|
||||
local c = Defs and Defs[id]
|
||||
if not c then error("undefined name: " .. id) end
|
||||
return c
|
||||
end
|
||||
|
||||
|
||||
local function patt_error (s, i)
|
||||
local msg = (#s < i + 20) and s:sub(i)
|
||||
or s:sub(i,i+20) .. "..."
|
||||
msg = ("pattern error near '%s'"):format(msg)
|
||||
error(msg, 2)
|
||||
end
|
||||
|
||||
local function mult (p, n)
|
||||
local np = mm.P(true)
|
||||
while n >= 1 do
|
||||
if n%2 >= 1 then np = np * p end
|
||||
p = p * p
|
||||
n = n/2
|
||||
end
|
||||
return np
|
||||
end
|
||||
|
||||
local function equalcap (s, i, c)
|
||||
if type(c) ~= "string" then return nil end
|
||||
local e = #c + i
|
||||
if s:sub(i, e - 1) == c then return e else return nil end
|
||||
end
|
||||
|
||||
|
||||
local S = (m.S(" \f\n\r\t\v") + "--" * (any - Predef.nl)^0)^0
|
||||
|
||||
local name = m.R("AZ", "az") * m.R("AZ", "az", "__", "09")^0
|
||||
|
||||
local arrow = S * "<-"
|
||||
|
||||
local exp_follow = m.P"/" + ")" + "}" + ":}" + "~}" + (name * arrow) + -1
|
||||
|
||||
name = m.C(name)
|
||||
|
||||
|
||||
-- identifiers only have meaning in a given environment
|
||||
local Identifier = name * m.Carg(1)
|
||||
|
||||
local num = m.C(m.R"09"^1) * S / tonumber
|
||||
|
||||
local String = "'" * m.C((any - "'")^0) * "'" +
|
||||
'"' * m.C((any - '"')^0) * '"'
|
||||
|
||||
|
||||
local defined = "%" * Identifier / function (c,Defs)
|
||||
local cat = Defs and Defs[c] or Predef[c]
|
||||
if not cat then error ("name '" .. c .. "' undefined") end
|
||||
return cat
|
||||
end
|
||||
|
||||
local Range = m.Cs(any * (m.P"-"/"") * (any - "]")) / mm.R
|
||||
|
||||
local item = defined + Range + m.C(any)
|
||||
|
||||
local Class =
|
||||
"["
|
||||
* (m.C(m.P"^"^-1)) -- optional complement symbol
|
||||
* m.Cf(item * (item - "]")^0, mt.__add) /
|
||||
function (c, p) return c == "^" and any - p or p end
|
||||
* "]"
|
||||
|
||||
local function adddef (t, k, Defs, exp)
|
||||
if t[k] then
|
||||
error("'"..k.."' already defined as a rule")
|
||||
else
|
||||
t[k] = exp
|
||||
end
|
||||
return t
|
||||
end
|
||||
|
||||
local function firstdef (n, Defs, r) return adddef({n}, n, Defs, r) end
|
||||
|
||||
|
||||
|
||||
local exp = m.P{ "Exp",
|
||||
Exp = S * ( m.V"Grammar"
|
||||
+ m.Cf(m.V"Seq" * ("/" * S * m.V"Seq")^0, mt.__add) );
|
||||
Seq = m.Cf(m.Cc(m.P"") * m.V"Prefix"^0 , mt.__mul)
|
||||
* (#exp_follow + patt_error);
|
||||
Prefix = "&" * S * m.V"Prefix" / mt.__len
|
||||
+ "!" * S * m.V"Prefix" / mt.__unm
|
||||
+ m.V"Suffix";
|
||||
Suffix = m.Cf(m.V"Primary" * S *
|
||||
( ( m.P"+" * m.Cc(1, mt.__pow)
|
||||
+ m.P"*" * m.Cc(0, mt.__pow)
|
||||
+ m.P"?" * m.Cc(-1, mt.__pow)
|
||||
+ "^" * ( m.Cg(num * m.Cc(mult))
|
||||
+ m.Cg(m.C(m.S"+-" * m.R"09"^1) * m.Cc(mt.__pow))
|
||||
)
|
||||
+ "->" * S * ( m.Cg(String * m.Cc(mt.__div))
|
||||
+ m.P"{}" * m.Cc(nil, m.Ct)
|
||||
+ m.Cg(Identifier / getdef * m.Cc(mt.__div))
|
||||
)
|
||||
+ "=>" * S * m.Cg(Identifier / getdef * m.Cc(m.Cmt))
|
||||
) * S
|
||||
)^0, function (a,b,f) return f(a,b) end );
|
||||
Primary = "(" * m.V"Exp" * ")"
|
||||
+ String / mm.P
|
||||
+ Class
|
||||
+ defined
|
||||
+ "{:" * (name * ":" + m.Cc(nil)) * m.V"Exp" * ":}" /
|
||||
function (n, p) return mm.Cg(p, n) end
|
||||
+ "=" * name / function (n) return mm.Cmt(mm.Cb(n), equalcap) end
|
||||
+ m.P"{}" / mm.Cp
|
||||
+ "{~" * m.V"Exp" * "~}" / mm.Cs
|
||||
+ "{" * m.V"Exp" * "}" / mm.C
|
||||
+ m.P"." * m.Cc(any)
|
||||
+ name * -arrow / mm.V
|
||||
+ "<" * name * ">" / mm.V;
|
||||
Definition = Identifier * arrow * m.V"Exp";
|
||||
Grammar = m.Cf(m.V"Definition" / firstdef * m.Cg(m.V"Definition")^0, adddef) /
|
||||
mm.P
|
||||
}
|
||||
|
||||
local pattern = S * exp / mm.P * (-any + patt_error)
|
||||
|
||||
|
||||
local function compile (p, defs)
|
||||
if mm.type(p) == "pattern" then return p end -- already compiled
|
||||
local cp = pattern:match(p, 1, defs)
|
||||
if not cp then error("incorrect pattern", 3) end
|
||||
return cp
|
||||
end
|
||||
|
||||
local function match (s, p, i)
|
||||
local cp = mem[p]
|
||||
if not cp then
|
||||
cp = compile(p)
|
||||
mem[p] = cp
|
||||
end
|
||||
return cp:match(s, i or 1)
|
||||
end
|
||||
|
||||
local function find (s, p, i)
|
||||
local cp = fmem[p]
|
||||
if not cp then
|
||||
cp = compile(p)
|
||||
cp = mm.P{ mm.Cp() * cp + 1 * mm.V(1) }
|
||||
fmem[p] = cp
|
||||
end
|
||||
return cp:match(s, i or 1)
|
||||
end
|
||||
|
||||
local function gsub (s, p, rep)
|
||||
local g = gmem[p] or {} -- ensure gmem[p] is not collected while here
|
||||
gmem[p] = g
|
||||
local cp = g[rep]
|
||||
if not cp then
|
||||
cp = compile(p)
|
||||
cp = mm.Cs((cp / rep + 1)^0)
|
||||
g[rep] = cp
|
||||
end
|
||||
return cp:match(s)
|
||||
end
|
||||
|
||||
|
||||
-- exported names
|
||||
local re = {
|
||||
compile = compile,
|
||||
match = match,
|
||||
find = find,
|
||||
gsub = gsub,
|
||||
updatelocale = updatelocale,
|
||||
}
|
||||
|
||||
if version == "Lua 5.1" then _G.re = re end
|
||||
|
||||
return re
|
||||
1188
lpeg/test.lua
Executable file
1188
lpeg/test.lua
Executable file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user