def test_regex_values():
assert pe.compile('A <- "a" "b"',
flags=pe.NONE).match('ab').value() is None
assert pe.compile('A <- "a" "b"',
flags=pe.REGEX).match('ab').value() is None
assert pe.compile('A <- "a" ~"b" "c"',
flags=pe.NONE).match('abc').value() == 'b'
assert pe.compile('A <- "a" ~"b" "c"',
flags=pe.REGEX).match('abc').value() == 'b'
def compile():
INI = pe.compile(r'''
Start <- (Comment* Section)* Comment* EOF
Section <- Header Body
Header <- Space* Title Space* (EOL / EOF)
Title <- '[' ~(![\]=\n\r] .)* ']'
Body <- (Comment* Pair)*
Pair <- Space* Key ('=' val:Value)?
Key <- !Title (![=\n\r] .)+
Value <- ('\\' EOL / !EOL .)*
Comment <- (Space* ';' (!EOL .)* / Space+) (EOL / EOF)
/ EOL
Space <- [\t ]
EOL <- '\r\n' / [\n\r]
EOF <- !.
''',
actions={
'Start': Pack(dict),
'Section': Pack(tuple),
'Body': Pack(dict),
'Pair': lambda key, val=None: (key, val),
'Key': Capture(str.strip),
'Value': Capture(_normalize_multiline),
},
parser='machine',
flags=pe.OPTIMIZE)
return lambda s: INI.match(s).value()
def test_inline():
assert (iload(r'A <- "a"') == gload(r'A <- "a"'))
assert (iload(r'A <- B B <- "a"') == gload(r'A <- "a" B <- "a"'))
assert (iload(r'A <- B B <- C C <- "a"') == gload(
r'A <- "a" B <- "a" C <- "a"'))
assert (iload(r'A <- "a" A') == gload(r'A <- "a" A'))
assert (iload(r'A <- "a" B B <- A') == gload(r'A <- "a" A B <- "a" B'))
assert (iload(r'A <- "a" B B <- "b" A') == gload(
r'A <- "a" "b" A B <- "b" "a" B'))
assert pe.compile('A <- "a" B B <- "b"',
flags=pe.NONE).match('ab').value() is None
assert pe.compile('A <- "a" B B <- "b"',
flags=pe.INLINE).match('ab').value() is None
assert pe.compile('A <- "a" B B <- ~"b"',
flags=pe.NONE).match('ab').value() == 'b'
assert pe.compile('A <- "a" B B <- ~"b"',
flags=pe.INLINE).match('ab').value() == 'b'
def test_multi_range_charclass(parser):
p = pe.compile(
r'''
Start <- ["] CHAR* ["]
CHAR <- [ !#-\[\]-\U0010ffff]
''',
parser=parser,
)
assert p.match('""') is not None
assert p.match('"a"') is not None
assert p.match('"ab"') is not None
assert p.match('"1a"') is not None
assert p.match('"1"') is not None
assert p.match('"\U0010ffff"') is not None
assert p.match('"a1"') is not None
def compile():
Json = pe.compile(r'''
# Syntactic rules
Start <- Spacing Value EOF
Value <- Object / Array / String / Number / Constant
Object <- LBRACE (Member (COMMA Member)*)? RBRACE
Member <- String COLON Value
Array <- LBRACK (Value (COMMA Value)*)? RBRACK
String <- ["] CHAR* ( ESC CHAR* )* ["]
Number <- INTEGER FRACTION? EXPONENT?
Constant <- TRUE / FALSE / NULL
# Lexical rules
CHAR <- [ !#-\[\]-\U0010ffff]
ESC <- '\\' ( ["\\/bfnrt]
/ 'u' HEX HEX HEX HEX )
HEX <- [0-9a-fA-F]
INTEGER <- "-"? ("0" / [1-9] [0-9]*)
FRACTION <- "." [0-9]+
EXPONENT <- [eE] [-+]? [0-9]+
TRUE <- "true"
FALSE <- "false"
NULL <- "null"
LBRACE <- "{" Spacing
RBRACE <- Spacing "}"
LBRACK <- "[" Spacing
RBRACK <- Spacing "]"
COMMA <- Spacing "," Spacing
COLON <- Spacing ":" Spacing
Spacing <- [\t\n\r ]*
EOF <- Spacing !.
''',
actions={
'Object': Pack(dict),
'Member': Pack(tuple),
'Array': Pack(list),
'String': Capture(json_unescape),
'Number': Capture(float),
'TRUE': Constant(True),
'FALSE': Constant(False),
'NULL': Constant(None),
},
parser='machine',
flags=pe.OPTIMIZE)
return lambda s: Json.match(s, flags=pe.STRICT).value()
def compile():
parser = pe.compile(
r'''
Start <- Spacing Expr EOL? EOF
Expr <- Term ((PLUS / MINUS) Term)*
Term <- Factor ((TIMES / DIVIDE) Factor)*
Factor <- Sign* (LPAR Expr RPAR
/ INTEGER )
Sign <- NEG / POS
INTEGER <- ~( '0' / [1-9] [0-9]* ) Spacing
PLUS <- '+' Spacing
MINUS <- '-' Spacing
TIMES <- '*' Spacing
DIVIDE <- '/' Spacing
LPAR <- '(' Spacing
RPAR <- ')' Spacing
NEG <- '-' Spacing
POS <- '+' Spacing
Spacing <- [ \t\n\f\v\r]*
EOL <- '\r\n' / [\n\r]
EOF <- !.
''',
actions={
'Expr': reduce_infix,
'Term': reduce_infix,
'Factor': reduce_prefix,
'INTEGER': int,
'PLUS': Constant(add),
'MINUS': Constant(sub),
'TIMES': Constant(mul),
'DIVIDE': Constant(div),
'NEG': Constant(neg),
},
flags=pe.OPTIMIZE
)
return lambda s: parser.match(s).value()
Json = pe.compile(r'''
Start <- Spacing Value Spacing EOF
Value <- Object / Array / String / Number / Constant / BADVALUE
Object <- LBRACE (Member (COMMA Member)*)? BADCOMMA? RBRACE
Member <- String COLON Value
Array <- LBRACK (Value (COMMA Value)*)? BADCOMMA? RBRACK
String <- ["] ~( (!["\\] .)* ('\\' . / (!["\\] .)+)* ) ["]
Number <- Integer / Float
Constant <- TRUE / FALSE / NULL
Integer <- INTEGER ![.eE]
Float <- INTEGER FRACTION? EXPONENT?
INTEGER <- "-"? ("0" / [1-9] [0-9]*)
FRACTION <- "." [0-9]+
EXPONENT <- [eE] [-+]? [0-9]+
TRUE <- "true"
FALSE <- "false"
NULL <- "null"
LBRACE <- "{" Spacing
RBRACE <- Spacing "}"
LBRACK <- "[" Spacing
RBRACK <- Spacing "]"
COMMA <- Spacing "," Spacing
COLON <- Spacing ":" Spacing
Spacing <- [\t\n\f\r ]*
EOF <- !.
BADVALUE <- ![}\]] .
BADCOMMA <- ',' &(RBRACE / RBRACK)
''',
actions={
'Object': Pair(dict),
'Array': Pack(list),
'Integer': Capture(int),
'Float': Capture(float),
'TRUE': Constant(True),
'FALSE': Constant(False),
'NULL': Constant(None),
'BADVALUE': Fail('unexpected JSON value'),
'BADCOMMA': Fail('trailing commas are not allowed'),
})
import pe
X = pe.compile(r'''
Start <- Expr (EOL Expr)* EOF
Expr <- Term PLUS Expr
/ (Sign Sign)+ Term MINUS Expr
/ Term
Sign <- [-+] Spacing
Term <- Factor TIMES Term
/ Factor DIVIDE Term
/ Factor
Factor <- LPAREN Expr RPAREN
/ Atom
Atom <- NAME / NUMBER
NAME <- [a-bA-B_] [a-bA-B0-9_]* Spacing
NUMBER <- ('0' / [1-9] [0-9]*) Spacing
PLUS <- '+' Spacing
MINUS <- '-' Spacing
TIMES <- '*' Spacing
DIVIDE <- '/' Spacing
LPAREN <- '(' Spacing
RPAREN <- ')' Spacing
EOL <- '\r\n' / [\n\r]
EOF <- [ \t\n\v\f\r]* !.
Spacing <- ' '*
''')
def _match(s):
return X.match(s, flags=pe.STRICT | pe.MEMOIZE)
peg_acceptor = pe.compile(r'''
# Hierarchical syntax
Grammar <- Spacing Definition+ EndOfFile
Definition <- Identifier LEFTARROW Expression
Expression <- Sequence (SLASH Sequence)*
Sequence <- Prefix*
Prefix <- (AND / NOT)? Suffix
Suffix <- Primary (QUESTION / STAR / PLUS)?
Primary <- Identifier !LEFTARROW
/ OPEN Expression CLOSE
/ Literal
/ Class
/ DOT
# Lexical syntax
Identifier <- IdentStart IdentCont* Spacing
IdentStart <- [a-zA-Z_]
IdentCont <- IdentStart / [0-9]
Literal <- ['] (!['] Char)* ['] Spacing
/ ["] (!["] Char)* ["] Spacing
Class <- '[' (!']' Range)* ']' Spacing
Range <- Char '-' Char / Char
Char <- '\\' [nrt'"\[\]\\]
/ '\\' [0-2] [0-7] [0-7]
/ '\\' [0-7] [0-7]?
/ !'\\' .
LEFTARROW <- '<-' Spacing
SLASH <- '/' Spacing
AND <- '&' Spacing
NOT <- '!' Spacing
QUESTION <- '?' Spacing
STAR <- '*' Spacing
PLUS <- '+' Spacing
OPEN <- '(' Spacing
CLOSE <- ')' Spacing
DOT <- '.' Spacing
Spacing <- (Space / Comment)*
Comment <- '#' (!EndOfLine .)* EndOfLine
Space <- ' ' / '\t' / EndOfLine
EndOfLine <- '\r\n' / '\n' / '\r'
EndOfFile <- !.
''')
'key': Pack(tuple),
'basic_string': toml_unescape,
'ml_basic_string': Join(toml_unescape),
'dec_int': int,
'hex_int': lambda x: int(x, 16),
'oct_int': lambda x: int(x, 8),
'bin_int': lambda x: int(x, 2),
'float': Capture(float),
'true': Constant(True),
'false': Constant(False),
'flexible_date_time': datetime.datetime,
'local_time': datetime.time,
'time_offset': toml_time_offset,
'sec_frac': toml_sec_frac,
'DIGIT2': Capture(int),
'DIGIT4': Capture(int),
'array': Pack(list),
'std_table': Table,
'inline_table': Pack(dict),
'array_table': ArrayTable,
}
TOML = pe.compile(grammar, actions=actions, flags=pe.NONE)
if __name__ == '__main__':
import sys
with open(sys.argv[1]) as fh:
m = TOML.match(fh.read())
if m:
print(m.value())
