|
|
@ -104,13 +104,15 @@ class RuleAnalyzer(data: String) { |
|
|
|
*/ |
|
|
|
*/ |
|
|
|
fun consumeToAny(vararg seq:String): Boolean { |
|
|
|
fun consumeToAny(vararg seq:String): Boolean { |
|
|
|
|
|
|
|
|
|
|
|
start = pos |
|
|
|
var pos = pos //声明新变量记录匹配位置,不更改类本身的位置 |
|
|
|
|
|
|
|
|
|
|
|
while (!isEmpty) { |
|
|
|
while (pos != queue.length) { |
|
|
|
|
|
|
|
|
|
|
|
for (s in seq) { |
|
|
|
for (s in seq) { |
|
|
|
if (matches(s)) { |
|
|
|
if (matches(s)) { |
|
|
|
step = s.length //间隔数 |
|
|
|
step = s.length //间隔数 |
|
|
|
|
|
|
|
start = this.pos //匹配成功, 设置规则下次起始位置 |
|
|
|
|
|
|
|
this.pos = pos //匹配成功, 同步处理位置到类 |
|
|
|
return true //匹配就返回 true |
|
|
|
return true //匹配就返回 true |
|
|
|
} |
|
|
|
} |
|
|
|
} |
|
|
|
} |
|
|
@ -118,8 +120,6 @@ class RuleAnalyzer(data: String) { |
|
|
|
pos++ //逐个试探 |
|
|
|
pos++ //逐个试探 |
|
|
|
} |
|
|
|
} |
|
|
|
|
|
|
|
|
|
|
|
pos = start //匹配失败,位置回退 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
return false |
|
|
|
return false |
|
|
|
} |
|
|
|
} |
|
|
|
|
|
|
|
|
|
|
@ -151,7 +151,7 @@ class RuleAnalyzer(data: String) { |
|
|
|
else -> null |
|
|
|
else -> null |
|
|
|
} |
|
|
|
} |
|
|
|
} ): Boolean { |
|
|
|
} ): Boolean { |
|
|
|
start = pos |
|
|
|
var pos = pos //声明变量记录临时处理位置 |
|
|
|
var depth = 0 //嵌套深度 |
|
|
|
var depth = 0 //嵌套深度 |
|
|
|
var bracketsDepth = 0 //[]嵌套深度 |
|
|
|
var bracketsDepth = 0 //[]嵌套深度 |
|
|
|
|
|
|
|
|
|
|
@ -164,13 +164,13 @@ class RuleAnalyzer(data: String) { |
|
|
|
|
|
|
|
|
|
|
|
do { |
|
|
|
do { |
|
|
|
if (isEmpty) break |
|
|
|
if (isEmpty) break |
|
|
|
var c = consume() |
|
|
|
var c = queue[pos++] |
|
|
|
if (c != '\\') { //非转义字符 |
|
|
|
if (c != '\\') { //非转义字符 |
|
|
|
if (c == '\'' && !commits && !commit && !regex && !inDoubleQuote && !inOtherQuote) inSingleQuote = !inSingleQuote //匹配具有语法功能的单引号 |
|
|
|
if (c == '\'' && !commits && !commit && !regex && !inDoubleQuote && !inOtherQuote) inSingleQuote = !inSingleQuote //匹配具有语法功能的单引号 |
|
|
|
else if (c == '"' && !commits && !commit && !regex && !inSingleQuote && !inOtherQuote) inDoubleQuote = !inDoubleQuote //匹配具有语法功能的双引号 |
|
|
|
else if (c == '"' && !commits && !commit && !regex && !inSingleQuote && !inOtherQuote) inDoubleQuote = !inDoubleQuote //匹配具有语法功能的双引号 |
|
|
|
else if (c == '`' && !commits && !commit && !regex && !inSingleQuote && !inDoubleQuote) inOtherQuote = !inOtherQuote //匹配具有语法功能的'`' |
|
|
|
else if (c == '`' && !commits && !commit && !regex && !inSingleQuote && !inDoubleQuote) inOtherQuote = !inOtherQuote //匹配具有语法功能的'`' |
|
|
|
else if (c == '/' && !commits && !commit && !regex && !inSingleQuote && !inDoubleQuote && !inOtherQuote) { //匹配注释或正则起点 |
|
|
|
else if (c == '/' && !commits && !commit && !regex && !inSingleQuote && !inDoubleQuote && !inOtherQuote) { //匹配注释或正则起点 |
|
|
|
c = consume() |
|
|
|
c = queue[pos++] |
|
|
|
when(c){ |
|
|
|
when(c){ |
|
|
|
'/'->commit=true //匹配单行注释起点 |
|
|
|
'/'->commit=true //匹配单行注释起点 |
|
|
|
'*'->commits=true //匹配多行注释起点 |
|
|
|
'*'->commits=true //匹配多行注释起点 |
|
|
@ -178,7 +178,7 @@ class RuleAnalyzer(data: String) { |
|
|
|
} |
|
|
|
} |
|
|
|
} |
|
|
|
} |
|
|
|
else if(commits && c == '*') { //匹配多行注释终点 |
|
|
|
else if(commits && c == '*') { //匹配多行注释终点 |
|
|
|
c = consume() |
|
|
|
c = queue[pos++] |
|
|
|
if(c == '/')commits = false |
|
|
|
if(c == '/')commits = false |
|
|
|
} |
|
|
|
} |
|
|
|
else if(regex && c == '/') { //正则的终点或[]平衡 |
|
|
|
else if(regex && c == '/') { //正则的终点或[]平衡 |
|
|
@ -200,26 +200,29 @@ class RuleAnalyzer(data: String) { |
|
|
|
if (fn) depth++ else depth-- //嵌套或者闭合 |
|
|
|
if (fn) depth++ else depth-- //嵌套或者闭合 |
|
|
|
|
|
|
|
|
|
|
|
}else { //转义字符 |
|
|
|
}else { //转义字符 |
|
|
|
var next = consume() //拉出被转义字符 |
|
|
|
var next = queue[pos++] //拉出被转义字符 |
|
|
|
if(commit && next == 'n') commit = false //匹配单行注释终点。当前为\,下个为n,表示换行 |
|
|
|
if(commit && next == 'n') commit = false //匹配单行注释终点。当前为\,下个为n,表示换行 |
|
|
|
else if (!commits && !commit && next == '\\') { |
|
|
|
else if (!commits && !commit && next == '\\') { |
|
|
|
consume() //当前为\,下个为\,双重转义中"\\"表示转义字符本身,根据if条件"\\"字串不在注释中,则只能在字串或正则中 |
|
|
|
queue[pos++] //当前为\,下个为\,双重转义中"\\"表示转义字符本身,根据if条件"\\"字串不在注释中,则只能在字串或正则中 |
|
|
|
next = consume() //拉出下个字符,因为在双重转义的字串或正则中,类似于 \\/ 这样的结构才是转义结构 |
|
|
|
next = queue[pos++] //拉出下个字符,因为在双重转义的字串或正则中,类似于 \\/ 这样的结构才是转义结构 |
|
|
|
if(next == '\\')consume() //若为转义字符则继续拉出,因为双重转义中转义字符成对存在,即 \\\\ |
|
|
|
if(next == '\\')queue[pos++] //若为转义字符则继续拉出,因为双重转义中转义字符成对存在,即 \\\\ |
|
|
|
} |
|
|
|
} |
|
|
|
} |
|
|
|
} |
|
|
|
} while (depth > 0 || bracketsDepth >0) //拉出全部符合js语法的字段 |
|
|
|
} while (depth > 0 || bracketsDepth >0) //拉出全部符合js语法的字段 |
|
|
|
|
|
|
|
|
|
|
|
if(depth > 0 || bracketsDepth >0) start = pos |
|
|
|
return if(depth > 0 || bracketsDepth > 0) false else { |
|
|
|
|
|
|
|
this.pos = pos //同步位置 |
|
|
|
return pos > start |
|
|
|
true |
|
|
|
|
|
|
|
} |
|
|
|
} |
|
|
|
} |
|
|
|
|
|
|
|
|
|
|
|
/** |
|
|
|
/** |
|
|
|
* 在双重转义字串中拉出一个规则平衡组 |
|
|
|
* 在双重转义字串中拉出一个规则平衡组 |
|
|
|
*/ |
|
|
|
*/ |
|
|
|
fun chompRuleBalanced(open: Char = '[', close: Char = ']',f: ((Char) ->Boolean?)? = null ): Boolean { |
|
|
|
fun chompRuleBalanced(open: Char = '[', close: Char = ']',f: ((Char) ->Boolean?)? = null ): Boolean { |
|
|
|
start = pos |
|
|
|
|
|
|
|
|
|
|
|
var pos = pos //声明临时变量记录匹配位置,匹配成功后才同步到类的pos |
|
|
|
|
|
|
|
|
|
|
|
var depth = 0 //嵌套深度 |
|
|
|
var depth = 0 //嵌套深度 |
|
|
|
var otherDepth = 0 //其他对称符合嵌套深度 |
|
|
|
var otherDepth = 0 //其他对称符合嵌套深度 |
|
|
|
|
|
|
|
|
|
|
@ -228,7 +231,7 @@ class RuleAnalyzer(data: String) { |
|
|
|
|
|
|
|
|
|
|
|
do { |
|
|
|
do { |
|
|
|
if (isEmpty) break |
|
|
|
if (isEmpty) break |
|
|
|
val c = consume() |
|
|
|
val c = queue[pos++] |
|
|
|
if (c != ESC) { //非转义字符 |
|
|
|
if (c != ESC) { //非转义字符 |
|
|
|
if (c == '\'' && !inDoubleQuote) inSingleQuote = !inSingleQuote //匹配具有语法功能的单引号 |
|
|
|
if (c == '\'' && !inDoubleQuote) inSingleQuote = !inSingleQuote //匹配具有语法功能的单引号 |
|
|
|
else if (c == '"' && !inSingleQuote) inDoubleQuote = !inDoubleQuote //匹配具有语法功能的双引号 |
|
|
|
else if (c == '"' && !inSingleQuote) inDoubleQuote = !inDoubleQuote //匹配具有语法功能的双引号 |
|
|
@ -243,16 +246,19 @@ class RuleAnalyzer(data: String) { |
|
|
|
} |
|
|
|
} |
|
|
|
|
|
|
|
|
|
|
|
}else { //转义字符 |
|
|
|
}else { //转义字符 |
|
|
|
var next = consume() //拉出被转义字符,匹配\/、\"、\'等 |
|
|
|
var next = queue[pos++] //拉出被转义字符,匹配\/、\"、\'等 |
|
|
|
if (next == ESC) { |
|
|
|
if (next == ESC) { |
|
|
|
consume() //当前为\,下个为\,双重转义中"\\"表示转义字符本身,根据语法特征当前字段在字串或正则中 |
|
|
|
queue[pos++] //当前为\,下个为\,双重转义中"\\"表示转义字符本身,根据语法特征当前字段在字串或正则中 |
|
|
|
next = consume() //拉出下个字符,因为在双重转义的字串或正则中,类似于 \\/ 这样的结构才是转义结构 |
|
|
|
next = queue[pos++] //拉出下个字符,因为在双重转义的字串或正则中,类似于 \\/ 这样的结构才是转义结构 |
|
|
|
if(next == ESC)consume() //若为转义字符则继续拉出,因为双重转义中转义字符成对存在,即 \\\\ |
|
|
|
if(next == ESC)queue[pos++] //若为转义字符则继续拉出,因为双重转义中转义字符成对存在,即 \\\\ |
|
|
|
} |
|
|
|
} |
|
|
|
} |
|
|
|
} |
|
|
|
} while (depth > 0 || otherDepth > 0) //拉出一个平衡字串 |
|
|
|
} while (depth > 0 || otherDepth > 0) //拉出一个平衡字串 |
|
|
|
|
|
|
|
|
|
|
|
return !(depth > 0 || otherDepth > 0) //平衡返回false,不平衡返回true |
|
|
|
return if(depth > 0 || otherDepth > 0) false else { |
|
|
|
|
|
|
|
this.pos = pos //同步位置 |
|
|
|
|
|
|
|
true |
|
|
|
|
|
|
|
} |
|
|
|
} |
|
|
|
} |
|
|
|
|
|
|
|
|
|
|
|
/** |
|
|
|
/** |
|
|
@ -312,9 +318,7 @@ class RuleAnalyzer(data: String) { |
|
|
|
|
|
|
|
|
|
|
|
} else { |
|
|
|
} else { |
|
|
|
|
|
|
|
|
|
|
|
val start0 = start //记录当前规则开头位置 |
|
|
|
|
|
|
|
if(!chompRuleBalanced(queue[pos],next)) throw Error(queue.substring(0, start)+"后未平衡") //拉出一个筛选器,不平衡则报错 |
|
|
|
if(!chompRuleBalanced(queue[pos],next)) throw Error(queue.substring(0, start)+"后未平衡") //拉出一个筛选器,不平衡则报错 |
|
|
|
start = start0 //筛选器的开头不是本段规则开头,故恢复开头设置 |
|
|
|
|
|
|
|
splitRule(rule) //首段已匹配,但当前段匹配未完成,调用二段匹配 |
|
|
|
splitRule(rule) //首段已匹配,但当前段匹配未完成,调用二段匹配 |
|
|
|
|
|
|
|
|
|
|
|
} |
|
|
|
} |
|
|
@ -352,9 +356,7 @@ class RuleAnalyzer(data: String) { |
|
|
|
pos = st //位置推移到筛选器处 |
|
|
|
pos = st //位置推移到筛选器处 |
|
|
|
val next = if(queue[pos] == '[' ) ']' else ')' //平衡组末尾字符 |
|
|
|
val next = if(queue[pos] == '[' ) ']' else ')' //平衡组末尾字符 |
|
|
|
|
|
|
|
|
|
|
|
val start0 = start //记录当前规则开头位置 |
|
|
|
|
|
|
|
if(!chompRuleBalanced(queue[pos],next)) throw Error(queue.substring(0, start)+"后未平衡") //拉出一个筛选器,不平衡时返回true,表示未平衡 |
|
|
|
if(!chompRuleBalanced(queue[pos],next)) throw Error(queue.substring(0, start)+"后未平衡") //拉出一个筛选器,不平衡时返回true,表示未平衡 |
|
|
|
start = start0 //筛选器平衡,但筛选器的开头不是当前规则开头,故恢复开头设置 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
return splitRule(rule) //递归匹配 |
|
|
|
return splitRule(rule) //递归匹配 |
|
|
|
|
|
|
|
|
|
|
@ -376,9 +378,7 @@ class RuleAnalyzer(data: String) { |
|
|
|
val st = StringBuilder() |
|
|
|
val st = StringBuilder() |
|
|
|
|
|
|
|
|
|
|
|
while (!isEmpty && consumeTo(inner)) { //拉取成功返回true,ruleAnalyzes里的字符序列索引变量pos后移相应位置,否则返回false,且isEmpty为true |
|
|
|
while (!isEmpty && consumeTo(inner)) { //拉取成功返回true,ruleAnalyzes里的字符序列索引变量pos后移相应位置,否则返回false,且isEmpty为true |
|
|
|
|
|
|
|
val posPre = pos //记录上次结束位置 |
|
|
|
val start1 = start //记录拉取前起点 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
if (chompRuleBalanced {//拉出一个以[]为默认嵌套、以{}为补充嵌套的平衡字段 |
|
|
|
if (chompRuleBalanced {//拉出一个以[]为默认嵌套、以{}为补充嵌套的平衡字段 |
|
|
|
when (it) { |
|
|
|
when (it) { |
|
|
|
'{' -> true |
|
|
|
'{' -> true |
|
|
@ -389,14 +389,13 @@ class RuleAnalyzer(data: String) { |
|
|
|
val frv= fr(currBalancedString(startStep,endStep)) |
|
|
|
val frv= fr(currBalancedString(startStep,endStep)) |
|
|
|
if(frv != null) { |
|
|
|
if(frv != null) { |
|
|
|
|
|
|
|
|
|
|
|
st.append(queue.substring(start1,start)+frv) //压入内嵌规则前的内容,及内嵌规则解析得到的字符串 |
|
|
|
st.append(queue.substring(start,posPre)+frv) //压入内嵌规则前的内容,及内嵌规则解析得到的字符串 |
|
|
|
continue //获取内容成功,继续选择下个内嵌规则 |
|
|
|
continue //获取内容成功,继续选择下个内嵌规则 |
|
|
|
|
|
|
|
|
|
|
|
} |
|
|
|
} |
|
|
|
} |
|
|
|
} |
|
|
|
|
|
|
|
|
|
|
|
start = start1 //拉出字段不平衡,重置起点 |
|
|
|
pos += inner.length //拉出字段不平衡,inner只是个普通字串,跳到此inner后继续匹配 |
|
|
|
pos = start + inner.length //拉出字段不平衡,inner只是个普通字串,规则回退到开头,并跳到此inner后继续匹配 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
} |
|
|
|
} |
|
|
|
|
|
|
|
|
|
|
|