internal::GenericRegex

Engine/source/persistence/rapidjson/internal/regex.h

Regular expression engine with subset of ECMAscript grammar.

More...

Classes:

class

internal::GenericRegex::Frag

class

internal::GenericRegex::Range

class

internal::GenericRegex::State

Private Types

enum

Operator {
  kZeroOrOne 
  kZeroOrMore 
  kOneOrMore 
  kConcatenation 
  kAlternation 
  kLeftParenthesis 
}

Public Types

Encoding::Ch

Ch

Encoding

EncodingType

Public Friends

class

GenericRegexSearch

Private Static Attributes

const unsigned

kAnyCharacterClass

For '.'.

const unsigned

kInfinityQuantifier

const unsigned

kRangeCharacterClass

const unsigned

kRangeNegationFlag

Private Attributes

Allocator *

allocator_

bool

anchorBegin_

bool

anchorEnd_

Allocator *

ownAllocator_

SizeType

rangeCount_

Stack< Allocator >

ranges_

SizeType

root_

SizeType

stateCount_

Stack< Allocator >

states_

Public Functions

GenericRegex(const Ch * source, Allocator * allocator)

~GenericRegex()

bool

IsValid()

Private Functions

SizeType

Append(SizeType l1, SizeType l2)

bool

CharacterEscape(DecodedStream< InputStream, Encoding > & ds, unsigned * escapedCodepoint)

void

CloneTopOperand(Stack< Allocator > & operandStack)

bool

Eval(Stack< Allocator > & operandStack, Operator op)

bool

EvalQuantifier(Stack< Allocator > & operandStack, unsigned n, unsigned m)

Range &

GetRange(SizeType index)

const Range &

GetRange(SizeType index)

State &

GetState(SizeType index)

const State &

GetState(SizeType index)

void

ImplicitConcatenation(Stack< Allocator > & atomCountStack, Stack< Allocator > & operatorStack)

SizeType

NewRange(unsigned codepoint)

SizeType

NewState(SizeType out, SizeType out1, unsigned codepoint)

void

Parse(DecodedStream< InputStream, Encoding > & ds)

bool

ParseRange(DecodedStream< InputStream, Encoding > & ds, SizeType * range)

bool

ParseUnsigned(DecodedStream< InputStream, Encoding > & ds, unsigned * u)

void

Patch(SizeType l, SizeType s)

void

PushOperand(Stack< Allocator > & operandStack, unsigned codepoint)

Private Static Functions

SizeType

Min(SizeType a, SizeType b)

Detailed Description

Regular expression engine with subset of ECMAscript grammar.

Supported regular expression syntax:

```
ab
```
Concatenation
```
a|b
```
Alternation
```
a
```
? Zero or one
```
a*
```
Zero or more
```
a+
```
One or more
```
a{3}
```
Exactly 3 times
```
a{3
```
,} At least 3 times
```
a{3
```
,5} 3 to 5 times
(ab) Grouping
```
^a
```
At the beginning
```
a$
```
At the end
. Any character
[abc] Character classes
[a-c] Character class range
[a-z0-9_] Character class combination
[^abc] Negated character classes
[^a-c] Negated character class range
[] Backspace (U+0008)
```
\
```
| \\ ... Escape characters
```
\f
```
Form feed (U+000C)
```
\n
```
Line feed (U+000A)
```
\r
```
Carriage return (U+000D)
```
\t
```
Tab (U+0009)
```
\v
```
Vertical tab (U+000B)

note:
This is a Thompson NFA engine, implemented with reference to Cox, Russ. "Regular Expression Matching Can Be Simple And Fast (but is slow in Java, Perl, PHP, Python, Ruby,...).", https://swtch.com/~rsc/regexp/regexp1.html

Private Types

Operator

Enumerator

kZeroOrOne
kZeroOrMore
kOneOrMore
kConcatenation
kAlternation
kLeftParenthesis

Public Types

typedef Encoding::Ch Ch

typedef Encoding EncodingType

Public Friends

Private Static Attributes

const unsigned kAnyCharacterClass

For '.'.

const unsigned kInfinityQuantifier

const unsigned kRangeCharacterClass

const unsigned kRangeNegationFlag

Private Attributes

Allocator * allocator_

bool anchorBegin_

bool anchorEnd_

Allocator * ownAllocator_

SizeType rangeCount_

Stack< Allocator > ranges_

SizeType root_

SizeType stateCount_

Stack< Allocator > states_

Public Functions

GenericRegex(const Ch * source, Allocator * allocator)

~GenericRegex()

IsValid()

Private Functions

Append(SizeType l1, SizeType l2)

CharacterEscape(DecodedStream< InputStream, Encoding > & ds, unsigned * escapedCodepoint)

CloneTopOperand(Stack< Allocator > & operandStack)

Eval(Stack< Allocator > & operandStack, Operator op)

EvalQuantifier(Stack< Allocator > & operandStack, unsigned n, unsigned m)

GetRange(SizeType index)

GetRange(SizeType index)

GetState(SizeType index)

GetState(SizeType index)

ImplicitConcatenation(Stack< Allocator > & atomCountStack, Stack< Allocator > & operatorStack)

NewRange(unsigned codepoint)

NewState(SizeType out, SizeType out1, unsigned codepoint)

Parse(DecodedStream< InputStream, Encoding > & ds)

ParseRange(DecodedStream< InputStream, Encoding > & ds, SizeType * range)

ParseUnsigned(DecodedStream< InputStream, Encoding > & ds, unsigned * u)

Patch(SizeType l, SizeType s)

PushOperand(Stack< Allocator > & operandStack, unsigned codepoint)

Private Static Functions

Min(SizeType a, SizeType b)