NSRegularExpression.swift

// This source file is part of the Swift.org open source project
//
// Copyright (c) 2014 - 2016 Apple Inc. and the Swift project authors
// Licensed under Apache License v2.0 with Runtime Library Exception
//
// See http://swift.org/LICENSE.txt for license information
// See http://swift.org/CONTRIBUTORS.txt for the list of Swift project authors
//

/* NSRegularExpression is a class used to represent and apply regular expressions. An instance of this class is an immutable representation of a compiled regular expression pattern and various option flags.
*/

import CoreFoundation

extensionNSRegularExpression{
publicstructOptions:OptionSet{
publicletrawValue:UInt
publicinit(rawValue:UInt){self.rawValue = rawValue }

publicstaticletcaseInsensitive=Options(rawValue:1 << 0) /* Match letters in the pattern independent of case. */
publicstaticletallowCommentsAndWhitespace=Options(rawValue:1 << 1) /* Ignore whitespace and #-prefixed comments in the pattern. */
publicstaticletignoreMetacharacters=Options(rawValue:1 << 2) /* Treat the entire pattern as a literal string. */
publicstaticletdotMatchesLineSeparators=Options(rawValue:1 << 3) /* Allow . to match any character, including line separators. */
publicstaticletanchorsMatchLines=Options(rawValue:1 << 4) /* Allow ^ and $ to match the start and end of lines. */
publicstaticletuseUnixLineSeparators=Options(rawValue:1 << 5) /* Treat only \n as a line separator (otherwise, all standard line separators are used). */
publicstaticletuseUnicodeWordBoundaries=Options(rawValue:1 << 6) /* Use Unicode TR#29 to specify word boundaries (otherwise, traditional regular expression word boundaries are used). */
}
}

openclassNSRegularExpression:NSObject,NSCopying,NSCoding{
internalvar_internal:_CFRegularExpression

openoverridefunc copy()->Any{
returncopy(with:nil)
}

openfunc copy(with zone:NSZone?=nil)->Any{
returnself
}

openfunc encode(with aCoder:NSCoder){
guard aCoder.allowsKeyedCoding else{
preconditionFailure("Unkeyed coding is unsupported.")
}

 aCoder.encode(self.pattern._nsObject, forKey:"NSPattern")
 aCoder.encode(self.options.rawValue._bridgeToObjectiveC(), forKey:"NSOptions")
}

publicrequiredconvenienceinit?(coder aDecoder:NSCoder){
guard aDecoder.allowsKeyedCoding else{
preconditionFailure("Unkeyed coding is unsupported.")
}

guardlet pattern = aDecoder.decodeObject(forKey:"NSPattern")as?NSString,
let options = aDecoder.decodeObject(forKey:"NSOptions")as?NSNumberelse{
returnnil
}

do{
tryself.init(pattern: pattern._swiftObject, options:Options(rawValue: options.uintValue))
}catch{
returnnil
}
}

openoverridefunc isEqual(_ object:Any?)->Bool{
guardlet other = object as?NSRegularExpressionelse{returnfalse}

returnself=== other
 || (self.pattern == other.pattern
 && self.options == other.options)
}

 /* An instance of NSRegularExpression is created from a regular expression pattern and a set of options. If the pattern is invalid, nil will be returned and an NSError will be returned by reference. The pattern syntax currently supported is that specified by ICU.
 */

publicinit(pattern:String, options:Options=[])throws{
varerror:Unmanaged<CFError>?
#if os(macOS) || os(iOS)
letopt=_CFRegularExpressionOptions(rawValue: options.rawValue)
#else
letopt=_CFRegularExpressionOptions(options.rawValue)
#endif
iflet regex =_CFRegularExpressionCreate(kCFAllocatorSystemDefault, pattern._cfObject, opt,&error){
 _internal = regex
}else{
throw error!.takeRetainedValue()
}
}

openvarpattern:String{
return_CFRegularExpressionGetPattern(_internal)._swiftObject
}

openvaroptions:Options{
#if os(macOS) || os(iOS)
letopt=_CFRegularExpressionGetOptions(_internal).rawValue
#else
letopt=_CFRegularExpressionGetOptions(_internal)
#endif

returnOptions(rawValue: opt)
}

openvarnumberOfCaptureGroups:Int{
return_CFRegularExpressionGetNumberOfCaptureGroups(_internal)
}

 /* This class method will produce a string by adding backslash escapes as necessary to the given string, to escape any characters that would otherwise be treated as pattern metacharacters.
 */
openclassfunc escapedPattern(for string:String)->String{
return_CFRegularExpressionCreateEscapedPattern(string._cfObject)._swiftObject
}
}

extensionNSRegularExpression{

publicstructMatchingOptions:OptionSet{
publicletrawValue:UInt
publicinit(rawValue:UInt){self.rawValue = rawValue }

publicstaticletreportProgress=MatchingOptions(rawValue:1 << 0) /* Call the block periodically during long-running match operations. */
publicstaticletreportCompletion=MatchingOptions(rawValue:1 << 1) /* Call the block once after the completion of any matching. */
publicstaticletanchored=MatchingOptions(rawValue:1 << 2) /* Limit matches to those at the start of the search range. */
publicstaticletwithTransparentBounds=MatchingOptions(rawValue:1 << 3) /* Allow matching to look beyond the bounds of the search range. */
publicstaticletwithoutAnchoringBounds=MatchingOptions(rawValue:1 << 4) /* Prevent ^ and $ from automatically matching the beginning and end of the search range. */
internalstaticletOmitResult=MatchingOptions(rawValue:1 << 13)
}

publicstructMatchingFlags:OptionSet{
publicletrawValue:UInt
publicinit(rawValue:UInt){self.rawValue = rawValue }

publicstaticletprogress=MatchingFlags(rawValue:1 << 0) /* Set when the block is called to report progress during a long-running match operation. */
publicstaticletcompleted=MatchingFlags(rawValue:1 << 1) /* Set when the block is called after completion of any matching. */
publicstaticlethitEnd=MatchingFlags(rawValue:1 << 2) /* Set when the current match operation reached the end of the search range. */
publicstaticletrequiredEnd=MatchingFlags(rawValue:1 << 3) /* Set when the current match depended on the location of the end of the search range. */
publicstaticletinternalError=MatchingFlags(rawValue:1 << 4) /* Set when matching failed due to an internal error. */
}
}

internalclass_NSRegularExpressionMatcher{
varregex:NSRegularExpression
varblock:(NSTextCheckingResult?,NSRegularExpression.MatchingFlags,UnsafeMutablePointer<ObjCBool>)->Void
init(regex:NSRegularExpression, block:@escaping(NSTextCheckingResult?,NSRegularExpression.MatchingFlags,UnsafeMutablePointer<ObjCBool>)->Void){
self.regex = regex
self.block = block
}
}

internalfunc _NSRegularExpressionMatch(_ context:UnsafeMutableRawPointer?, ranges:UnsafeMutablePointer<CFRange>?, count:CFIndex, options:_CFRegularExpressionMatchingOptions, stop:UnsafeMutablePointer<_DarwinCompatibleBoolean>)->Void{
letmatcher=unsafeBitCast(context, to: _NSRegularExpressionMatcher.self)
if ranges ==nil{
#if os(macOS) || os(iOS)
letopts= options.rawValue
#else
letopts= options
#endif
 stop.withMemoryRebound(to:ObjCBool.self, capacity:1,{
 matcher.block(nil,NSRegularExpression.MatchingFlags(rawValue: opts), $0)
})
}else{
letresult= ranges!.withMemoryRebound(to:NSRange.self, capacity: count){ rangePtr in
NSTextCheckingResult.regularExpressionCheckingResultWithRanges(rangePtr, count: count, regularExpression: matcher.regex)
}
#if os(macOS) || os(iOS)
letflags=NSRegularExpression.MatchingFlags(rawValue: options.rawValue)
#else
letflags=NSRegularExpression.MatchingFlags(rawValue: options)
#endif
 stop.withMemoryRebound(to:ObjCBool.self, capacity:1,{
 matcher.block(result, flags, $0)
})
}
}

extensionNSRegularExpression{

 /* The fundamental matching method on NSRegularExpression is a block iterator. There are several additional convenience methods, for returning all matches at once, the number of matches, the first match, or the range of the first match. Each match is specified by an instance of NSTextCheckingResult (of type NSTextCheckingTypeRegularExpression) in which the overall match range is given by the range property (equivalent to range at:0) and any capture group ranges are given by range at: for indexes from 1 to numberOfCaptureGroups. {NSNotFound, 0} is used if a particular capture group does not participate in the match.
 */

publicfunc enumerateMatches(in string:String, options:NSRegularExpression.MatchingOptions=[], range:NSRange, using block:@escaping(NSTextCheckingResult?,NSRegularExpression.MatchingFlags,UnsafeMutablePointer<ObjCBool>)->Swift.Void){
letmatcher=_NSRegularExpressionMatcher(regex:self, block: block)
withExtendedLifetime(matcher){(m:_NSRegularExpressionMatcher)->Voidin
#if os(macOS) || os(iOS)
letopts=_CFRegularExpressionMatchingOptions(rawValue: options.rawValue)
#else
letopts=_CFRegularExpressionMatchingOptions(options.rawValue)
#endif
_CFRegularExpressionEnumerateMatchesInString(_internal, string._cfObject, opts,CFRange(range),unsafeBitCast(matcher, to:UnsafeMutableRawPointer.self), _NSRegularExpressionMatch)
}
}

publicfunc matches(in string:String, options:NSRegularExpression.MatchingOptions=[], range:NSRange)->[NSTextCheckingResult]{
varmatches=[NSTextCheckingResult]()
enumerateMatches(in: string, options: options.subtracting(.reportProgress).subtracting(.reportCompletion), range: range){(result:NSTextCheckingResult?, flags:NSRegularExpression.MatchingFlags, stop:UnsafeMutablePointer<ObjCBool>)in
iflet match = result {
 matches.append(match)
}
}
return matches

}

publicfunc numberOfMatches(in string:String, options:NSRegularExpression.MatchingOptions=[], range:NSRange)->Int{
varcount=0
enumerateMatches(in: string, options: options.subtracting(.reportProgress).subtracting(.reportCompletion).union(.OmitResult), range: range){_,_,_ in
 count +=1
}
return count
}

publicfunc firstMatch(in string:String, options:NSRegularExpression.MatchingOptions=[], range:NSRange)->NSTextCheckingResult?{
varfirst:NSTextCheckingResult?
enumerateMatches(in: string, options: options.subtracting(.reportProgress).subtracting(.reportCompletion), range: range){(result:NSTextCheckingResult?, flags:NSRegularExpression.MatchingFlags, stop:UnsafeMutablePointer<ObjCBool>)in
 first = result
 stop.pointee =true
}
return first
}

publicfunc rangeOfFirstMatch(in string:String, options:NSRegularExpression.MatchingOptions=[], range:NSRange)->NSRange{
varfirstRange=NSRange(location: NSNotFound, length:0)
enumerateMatches(in: string, options: options.subtracting(.reportProgress).subtracting(.reportCompletion), range: range){(result:NSTextCheckingResult?, flags:NSRegularExpression.MatchingFlags, stop:UnsafeMutablePointer<ObjCBool>)in
iflet match = result {
 firstRange = match.range
}else{
 firstRange =NSRange(location:0, length:0)
}
 stop.pointee =true
}
return firstRange
}
}

/* By default, the block iterator method calls the block precisely once for each match, with a non-nil result and appropriate flags. The client may then stop the operation by setting the contents of stop to YES. If the NSMatchingReportProgress option is specified, the block will also be called periodically during long-running match operations, with nil result and NSMatchingProgress set in the flags, at which point the client may again stop the operation by setting the contents of stop to YES. If the NSMatchingReportCompletion option is specified, the block will be called once after matching is complete, with nil result and NSMatchingCompleted set in the flags, plus any additional relevant flags from among NSMatchingHitEnd, NSMatchingRequiredEnd, or NSMatchingInternalError. NSMatchingReportProgress and NSMatchingReportCompletion have no effect for methods other than the block iterator.

NSMatchingHitEnd is set in the flags passed to the block if the current match operation reached the end of the search range. NSMatchingRequiredEnd is set in the flags passed to the block if the current match depended on the location of the end of the search range. NSMatchingInternalError is set in the flags passed to the block if matching failed due to an internal error (such as an expression requiring exponential memory allocations) without examining the entire search range.

NSMatchingAnchored, NSMatchingWithTransparentBounds, and NSMatchingWithoutAnchoringBounds can apply to any match or replace method. If NSMatchingAnchored is specified, matches are limited to those at the start of the search range. If NSMatchingWithTransparentBounds is specified, matching may examine parts of the string beyond the bounds of the search range, for purposes such as word boundary detection, lookahead, etc. If NSMatchingWithoutAnchoringBounds is specified, ^ and $ will not automatically match the beginning and end of the search range (but will still match the beginning and end of the entire string). NSMatchingWithTransparentBounds and NSMatchingWithoutAnchoringBounds have no effect if the search range covers the entire string.

NSRegularExpression is designed to be immutable and threadsafe, so that a single instance can be used in matching operations on multiple threads at once. However, the string on which it is operating should not be mutated during the course of a matching operation (whether from another thread or from within the block used in the iteration).
*/

extensionNSRegularExpression{

 /* NSRegularExpression also provides find-and-replace methods for both immutable and mutable strings. The replacement is treated as a template, with $0 being replaced by the contents of the matched range, $1 by the contents of the first capture group, and so on. Additional digits beyond the maximum required to represent the number of capture groups will be treated as ordinary characters, as will a $ not followed by digits. Backslash will escape both $ and itself.
 */
publicfunc stringByReplacingMatches(in string:String, options:NSRegularExpression.MatchingOptions=[], range:NSRange, withTemplate templ:String)->String{
varstr:String=""
letlength= string.length
varpreviousRange=NSRange(location:0, length:0)
letresults=matches(in: string, options: options.subtracting(.reportProgress).subtracting(.reportCompletion), range: range)
letstart= string.utf16.startIndex

forresultin results {
letcurrentRange= result.range
letreplacement=replacementString(for: result, in: string, offset:0, template: templ)
if currentRange.location >NSMaxRange(previousRange){
letmin= string.utf16.index(start, offsetBy:NSMaxRange(previousRange))
letmax= string.utf16.index(start, offsetBy: currentRange.location)
 str +=String(string.utf16[min..<max])!
}
 str += replacement
 previousRange = currentRange
}

if length >NSMaxRange(previousRange){
letmin= string.utf16.index(start, offsetBy:NSMaxRange(previousRange))
letmax= string.utf16.index(start, offsetBy: length)
 str +=String(string.utf16[min..<max])!
}

return str
}

publicfunc replaceMatches(in string:NSMutableString, options:NSRegularExpression.MatchingOptions=[], range:NSRange, withTemplate templ:String)->Int{
letresults=matches(in: string._swiftObject, options: options.subtracting(.reportProgress).subtracting(.reportCompletion), range: range)
varcount=0
varoffset=0
forresultin results {
varcurrentRange= result.range
letreplacement=replacementString(for: result, in: string._swiftObject, offset: offset, template: templ)
 currentRange.location += offset

 string.replaceCharacters(in: currentRange, with: replacement)
 offset += replacement.length - currentRange.length
 count +=1
}
return count
}

 /* For clients implementing their own replace functionality, this is a method to perform the template substitution for a single result, given the string from which the result was matched, an offset to be added to the location of the result in the string (for example, in case modifications to the string moved the result since it was matched), and a replacement template.
 */
publicfunc replacementString(for result:NSTextCheckingResult, in string:String, offset:Int, template templ:String)->String{
 // ??? need to consider what happens if offset takes range out of bounds due to replacement
structonce{
staticletcharacterSet=CharacterSet(charactersIn:"\\$")
}
lettemplate= templ._nsObject
varrange= template.rangeOfCharacter(from: once.characterSet)
if range.length >0{
varnumberOfDigits=1
varorderOfMagnitude=10
letnumberOfRanges= result.numberOfRanges
letstr= templ._nsObject.mutableCopy(with:nil)as!NSMutableString
varlength= str.length
while(orderOfMagnitude < numberOfRanges && numberOfDigits <20){
 numberOfDigits +=1
 orderOfMagnitude *=10
}
while range.length >0{
varc= str.character(at: range.location)
if c ==unichar(unicodeScalarLiteral:"\\"){
 str.deleteCharacters(in: range)
 length -= range.length
 range.length =1
}elseif c ==unichar(unicodeScalarLiteral:"$"){
vargroupNumber:Int= NSNotFound
varidx=NSMaxRange(range)
while idx < length && idx <NSMaxRange(range)+ numberOfDigits {
 c = str.character(at: idx)
if c <unichar(unicodeScalarLiteral:"0") || c >unichar(unicodeScalarLiteral:"9"){
break
}
if groupNumber == NSNotFound {
 groupNumber =0
}

 groupNumber *=10
 groupNumber +=Int(c)- Int(unichar(unicodeScalarLiteral:"0"))
 idx +=1
}
if groupNumber != NSNotFound {
letrangeToReplace=NSRange(location: range.location, length: idx - range.location)
varsubstringRange=NSRange(location: NSNotFound, length:0)
varsubstring=""
if groupNumber < numberOfRanges {
 substringRange = result.range(at: groupNumber)
}
if substringRange.location != NSNotFound {
 substringRange.location += offset
}
if substringRange.location != NSNotFound && substringRange.length >0{
letstart= string.utf16.startIndex
letmin= string.utf16.index(start, offsetBy: substringRange.location)
letmax= string.utf16.index(start, offsetBy: substringRange.location + substringRange.length)
 substring =String(string.utf16[min..<max])!
}
 str.replaceCharacters(in: rangeToReplace, with: substring)

 length += substringRange.length - rangeToReplace.length
 range.length = substringRange.length
}
}
ifNSMaxRange(range)> length {
break
}
 range = str.rangeOfCharacter(from: once.characterSet, options:[], range:NSRange(location:NSMaxRange(range), length: length - NSMaxRange(range)))
}
return str._swiftObject
}
return templ
}

 /* This class method will produce a string by adding backslash escapes as necessary to the given string, to escape any characters that would otherwise be treated as template metacharacters. 
 */
openclassfunc escapedTemplate(for string:String)->String{
return_CFRegularExpressionCreateEscapedPattern(string._cfObject)._swiftObject
}
}