/usr/share/lua/5.1/leg/grammar.lua is in lua-leg 0.1.3-1.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 | --[=[
<%
project.title = "grammar"
project.description = "LPeg grammar manipulation"
project.version = "0.1.2"
project.date = _G.os.date'%B %d, %Y'
project.modules = { 'grammar', 'parser', 'scanner' }
%>
# Description
This module defines a handful of operations which can be applied to
[http://www.inf.puc-rio.br/~roberto/lpeg.html LPeg] patterns and grammars in
general.
# Dependencies
* [http://www.inf.puc-rio.br/~roberto/lpeg.html LPeg].
# Operations
## Piping
Pattern matching dissociates the notion of *matching* from the notion of
*capturing*: matching checks if a given string follows a certain pattern,
and capturing generates values according to the match made. This division
allows interesting possibilities:
* different problems can be solved by applying different captures to the same grammar;
* captures may be defined separately;
* captures may be done on top of other captures.
Accounting for the first and second bullets, the grammar given in
[parser.html parser] has no captures, enabling the user to reuse it to solve any
problems that require a Lua grammar. One good example is documentation
generation, described in a little more detail [#section_Example below].
The third bullet depicts a more interesting idea: a capture might take the
result of another capture as input, doing a further transformation of the
original data. This capture chaining, with the latter ones using the former's
output as its input, is very similar to [http://en.wikipedia.org/wiki/Pipeline_%28Unix%29 Unix pipelines],
so this mechanism was named **piping**.
## Completing
With piping, several levels of captures can be chained together up to the
most appropriate for the task at hand. Yet some levels might require extra rules, and modifications to existing ones, to ensure proper matching.
To avoid manual copying, the new grammar should redefine only the necessary
rules, copying the rest from the older grammar. This action is dubbed
**completing**.
## Applying
Once a new rule set is created and [#section_Completing completed], and
all captures are correctly [#section_Piping piped], all that's left is
to put them together, a process called **applying**. The result is a grammar ready for [http://www.inf.puc-rio.br/~roberto/lpeg.html#lpeg lpeg.P]
consumption, whose pattern will return the intended result when a match is made.
## Example
Let's consider the problem of documenting a Lua module. In this case, comments
must be captured before every function declaration when in the outermost scope:
``
-- -- the code to parse
subject = %[%[
-- -- Calculates the sum a+b.
-- -- An extra line.
function sum (a, b)
-- -- code
end
-- -- f1: assume a variable assignment is not a proper declaration for an
-- -- exported function
f1 = function ()
-- -- code
end
while true do
-- -- this function is not in the outermost scope
function aux() end
end
function something:other(a, ...)
-- -- a global function without comments
end
%]%]
``
In the code above only `sum` and `something:other` should be documented, as `f1` isn't properly (by our standards) declared and `aux` is not in the outermost scope.
By combining [http://www.inf.puc-rio.br/~roberto/lpeg.html LPeg] and the modules [scanner.html scanner], [parser.html parser] and [grammar.html grammar], this specific problem can be solved as follows:
``
-- -- change only the initial rule and make no captures
patt = grammar.apply(parser.rules, scanner.COMMENT^-1 %* lpeg.V'GlobalFunction', nil)
-- -- transform the new grammar into a LPeg pattern
patt = lpeg.P(patt)
-- -- making a pattern that matches any Lua statement, also without captures
Stat = lpeg.P( grammar.apply(parser.rules, lpeg.V'Stat', nil) )
-- -- a pattern which matches function declarations and skips statements in
-- -- inner scopes or undesired tokens
patt = (patt + Stat + scanner.ANY)^0
-- -- matching a string
patt:match(subject)
``
These are the relevant rules in [parser.html#section_The_Grammar the grammar]:
``
GlobalFunction = 'function' %* FuncName %* FuncBody
FuncName = ID %* ('.' %* ID)^0 %* (':' %* ID)^-1
FuncBody = '(' %* (ParList + EPSILON) %* ')' %* Block %* 'end'
ParList = NameList %* (',' %* '...')^-1
NameList = ID %* (',' %* ID)^0
ID = scanner.ID
EPSILON = lpeg.P(true)
``
It may seem that `ParList + EPSILON` could be substituted for `ParList^-1` (optionally match `ParList`), but then no captures would be made for empty parameter lists, and `GlobalFunction` would get all strings matched by `FuncBody`. The `EPSILON` rule acts in this manner as a placeholder in the argument list, avoiding any argument list processing in the capture function.
Since no captures are being made, [http://www.inf.puc-rio.br/~roberto/lpeg.html#basic lpeg.match] doesn't return anything interesting. Here are some possible captures:
``
-- -- some interesting captures bundled up in a table. Note that the table keys
-- -- match the grammar rules we want to add captures to. Whatever rules aren't in
-- -- the rules table below will come from parser.rules .
captures = {
%[1%] = function (...) -- the initial rule
return '<function>'..table.concat{...}..'</function>'
end,
GlobalFunction = function (name, parlist)
return '<name>'..name..'</name><parlist>'..(parlist or '')..'</parlist>'
end,
FuncName = grammar.C, -- capture the raw text
ParList = grammar.C, -- capture the raw text
COMMENT = scanner.comment2text, -- remove the comment trappings
}
-- -- spacing rule
local S = scanner.SPACE ^ 0
-- -- rules table
rules = {
%[1%] = ((lpeg.V'COMMENT' %*S) ^ 0) %*S%* lpeg.V'GlobalFunction',
COMMENT = scanner.COMMENT,
}
-- -- building the new grammar and adding the captures
patt = lpeg.P( grammar.apply(parser.rules, rules, captures) )
-- -- a pattern that matches a sequence of patts and concatenates the results
patt = (patt + Stat + scanner.ANY)^0 / function(...)
return table.concat({...}, '\n\n') -- some line breaks for easier reading
end
-- -- finally, matching a string
print(patt:match(subject))
``
`FuncBody` needs no captures, as `Block` and all its non-terminals have none; it
just needs to pass along any captures made by `ParList`. `NameList` and `ID` also have no captures, and the whole subject string is passed further.
The printed result is:
<pre class="example">
<function>Calculates the sum a+b. An extra line.<name>sum</name><parlist>a, b</parlist></function>
<br/>
<function><name>something:other</name><parlist>a, ...</parlist></function>
</pre>
--]=]
-- $Id: grammar.lua,v 1.3 2007/11/26 18:41:51 hanjos Exp $
-- basic functions
local assert = assert
local pairs = pairs
local type = type
-- imported modules
local lpeg = require 'lpeg'
-- imported functions
local P, V = lpeg.P, lpeg.V
-- module declaration
module 'leg.grammar'
--[[
Returns a pattern which matches any of the patterns received.
**Example:**
``
local g, s, m = require 'leg.grammar', require 'leg.scanner', require 'lpeg'
-- -- match numbers or operators, capture the numbers
print( (g.anyOf { '+', '-', '%*', '/', m.C(s.NUMBER) }):match '34.5@23 %* 56 / 45 - 45' )
-- --> prints 34.5
``
**Parameters:**
* `list`: a list of zero or more LPeg patterns or values which can be fed to [http://www.inf.puc-rio.br/~roberto/lpeg.html#lpeg lpeg.P].
**Returns:**
* a pattern which matches any of the patterns received.
--]]
function anyOf(list)
local patt = P(false)
for i = 1, #list, 1 do
patt = P(list[i]) + patt
end
return patt
end
--[=[
Returns a pattern which matches a list of `patt`s, separated by `sep`.
**Example:** matching comma-separated values:
``
local g, m = require 'leg.grammar', require 'lpeg'
-- -- separator
local sep = m.P',' + m.P'\n'
-- -- element: anything but sep, capture it
local elem = m.C((1 - sep)^0)
-- -- pattern
local patt = g.listOf(elem, sep)
-- -- matching
print( patt:match %[%[a, b, 'christmas eve'
d, evening; mate!
f%]%])
-- --> prints out "a b 'christmas eve' d evening; mate! f"
``
**Parameters:**
* `patt`: a LPeg pattern.
* `sep`: a LPeg pattern.
**Returns:**
* the following pattern: ``patt %* (sep %* patt)^0``
--]=]
function listOf(patt, sep)
patt, sep = P(patt), P(sep)
return patt * (sep * patt)^0
end
--[[
A capture function, made so that `patt / C` is equivalent to `m.C(patt)`. It's intended to be used in capture tables, such as those required by [#function_pipe pipe] and [#function_apply apply].
--]]
function C(...) return ... end
--[[
A capture function, made so that `patt / Ct` is equivalent to `m.Ct(patt)`. It's intended to be used in capture tables, such as those required by [#function_pipe pipe] and [#function_apply apply].
--]]
function Ct(...) return { ... } end
--[[
Creates a shallow copy of `grammar`.
**Parameters:**
* `grammar`: a regular table.
**Returns:**
* a newly created table, with `grammar`'s keys and values.
--]]
function copy(grammar)
local newt = {}
for k, v in pairs(grammar) do
newt[k] = v
end
return newt
end
--[[
[#section_Completing Completes] `dest` with `orig`.
**Parameters:**
* `dest`: the new grammar. Must be a table.
* `orig`: the original grammar. Must be a table.
**Returns:**
* `dest`, with new rules inherited from `orig`.
--]]
function complete (dest, orig)
for rule, patt in pairs(orig) do
if not dest[rule] then
dest[rule] = patt
end
end
return dest
end
--[[
[#section_Piping Pipes] the captures in `orig` to the ones in `dest`.
`dest` and `orig` should be tables, with each key storing a capture function. Each capture in `dest` will be altered to use the results for the matching one in `orig` as input, using function composition. Should `orig` possess keys not in `dest`, `dest` will copy them.
**Parameters:**
* `dest`: a capture table.
* `orig`: a capture table.
**Returns:**
* `dest`, suitably modified.
--]]
function pipe (dest, orig)
for k, vorig in pairs(orig) do
local vdest = dest[k]
if vdest then
dest[k] = function(...) return vdest(vorig(...)) end
else
dest[k] = vorig
end
end
return dest
end
--[[
[#section_Completing Completes] `rules` with `grammar` and then [#Applying applies] `captures`.
`rules` can either be:
* a single pattern, which is taken to be the new initial rule,
* a possibly incomplete LPeg grammar, as per [#function_complete complete], or
* `nil`, which means no new rules are added.
`captures` can either be:
* a capture table, as per [#function_pipe pipe], or
* `nil`, which means no captures are applied.
**Parameters:**
* `grammar`: the old grammar. It stays unmodified.
* `rules`: optional, the new rules.
* `captures`: optional, the final capture table.
**Returns:**
* `rules`, suitably augmented by `grammar` and `captures`.
--]]
function apply (grammar, rules, captures)
if rules == nil then
rules = {}
elseif type(rules) ~= 'table' then
rules = { rules }
end
complete(rules, grammar)
if type(grammar[1]) == 'string' then
rules[1] = lpeg.V(grammar[1])
end
if captures ~= nil then
assert(type(captures) == 'table', 'captures must be a table')
for rule, cap in pairs(captures) do
rules[rule] = rules[rule] / cap
end
end
return rules
end
|