k
/
legado
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Merge branch 'master' into master

Browse Source
pull/1128/head
kunfei 3 years ago committed by GitHub
parent d473ff1f35 9cac73f303
commit ee0a6e63bd
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
6 changed files with 150 additions and 139 deletions
Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL
Show Stats Download Patch File Download Diff File
  1. 44
      app/src/main/java/io/legado/app/data/entities/BookChapter.kt
  2. 131
      app/src/main/java/io/legado/app/model/analyzeRule/AnalyzeRule.kt
  3. 14
      app/src/main/java/io/legado/app/model/analyzeRule/AnalyzeUrl.kt
  4. 91
      app/src/main/java/io/legado/app/model/analyzeRule/RuleAnalyzer.kt
  5. 7
      app/src/main/java/io/legado/app/service/help/ReadBook.kt
  6. 2
      app/src/main/java/io/legado/app/ui/book/read/page/provider/ChapterProvider.kt

44
app/src/main/java/io/legado/app/data/entities/BookChapter.kt
Unescape View File

@ -15,30 +15,30 @@ import kotlinx.parcelize.Parcelize
@Parcelize
@Entity(
tableName = "chapters",
primaryKeys = ["url", "bookUrl"],
indices = [(Index(value = ["bookUrl"], unique = false)),
(Index(value = ["bookUrl", "index"], unique = true))],
foreignKeys = [(ForeignKey(
entity = Book::class,
parentColumns = ["bookUrl"],
childColumns = ["bookUrl"],
onDelete = ForeignKey.CASCADE
))]
tableName = "chapters",
primaryKeys = ["url", "bookUrl"],
indices = [(Index(value = ["bookUrl"], unique = false)),
(Index(value = ["bookUrl", "index"], unique = true))],
foreignKeys = [(ForeignKey(
entity = Book::class,
parentColumns = ["bookUrl"],
childColumns = ["bookUrl"],
onDelete = ForeignKey.CASCADE
))]
) // 删除书籍时自动删除章节
data class BookChapter(
var url: String = "", // 章节地址
var title: String = "", // 章节标题
var baseUrl: String = "", //用来拼接相对url
var bookUrl: String = "", // 书籍地址
var index: Int = 0, // 章节序号
var resourceUrl: String? = null, // 音频真实URL
var tag: String? = null, //
var start: Long? = null, // 章节起始位置
var end: Long? = null, // 章节终止位置
var startFragmentId: String? = null, //EPUB书籍当前章节的fragmentId
var endFragmentId: String? = null, //EPUB书籍下一章节的fragmentId
var variable: String? = null //变量
var url: String = "", // 章节地址
var title: String = "", // 章节标题
var baseUrl: String = "", //用来拼接相对url
var bookUrl: String = "", // 书籍地址
var index: Int = 0, // 章节序号
var resourceUrl: String? = null, // 音频真实URL
var tag: String? = null, //
var start: Long? = null, // 章节起始位置
var end: Long? = null, // 章节终止位置
var startFragmentId: String? = null, //EPUB书籍当前章节的fragmentId
var endFragmentId: String? = null, //EPUB书籍下一章节的fragmentId
var variable: String? = null //变量
) : Parcelable {
@delegate:Transient

131
app/src/main/java/io/legado/app/model/analyzeRule/AnalyzeRule.kt
Unescape View File

@ -122,7 +122,7 @@ class AnalyzeRule(val ruleData: RuleDataInterface) : JsExtensions {
@JvmOverloads
fun getStringList(rule: String?, isUrl: Boolean = false): List<String>? {
if (rule.isNullOrEmpty()) return null
val ruleList = splitSourceRule(rule,true)
val ruleList = splitSourceRule(rule, true)
return getStringList(ruleList, isUrl)
}
@ -282,7 +282,7 @@ class AnalyzeRule(val ruleData: RuleDataInterface) : JsExtensions {
@Suppress("UNCHECKED_CAST")
fun getElements(ruleStr: String): List<Any> {
var result: Any? = null
val ruleList = splitSourceRule(ruleStr,true)
val ruleList = splitSourceRule(ruleStr, true)
content?.let { o ->
if (ruleList.isNotEmpty()) result = o
for (sourceRule in ruleList) {
@ -357,61 +357,34 @@ class AnalyzeRule(val ruleData: RuleDataInterface) : JsExtensions {
/**
* 分解规则生成规则列表
*/
fun splitSourceRule(ruleStr: String?,isList:Boolean = false): List<SourceRule> {
fun splitSourceRule(ruleStr: String?, isList: Boolean = false): List<SourceRule> {
if (ruleStr.isNullOrEmpty()) return ArrayList<SourceRule>()
val ruleList = ArrayList<SourceRule>()
//检测Mode
var mMode: Mode = Mode.Default
fun mode(ruleStr0:String)=when {
ruleStr0.startsWith("@@") -> {
mMode = Mode.Default
ruleStr0.substring(2)
}
ruleStr0.startsWith("@XPath:", true) -> {
mMode = Mode.XPath
ruleStr0.substring(7)
}
ruleStr0.startsWith("/") -> {//XPath特征很明显,无需配置单独的识别标头
mMode = Mode.XPath
ruleStr0
}
ruleStr0.startsWith("@Json:", true) -> {
mMode = Mode.Json
ruleStr0.substring(6)
}
( ruleStr0[1] == '.' || ruleStr0[1] == '[') && ruleStr0[0] == '$' || isJSON -> {
mMode = Mode.Json
ruleStr0
}
else -> {
mMode = Mode.Default
ruleStr0
}
}
//拆分为规则列表
var start = if(isList && ruleStr.startsWith(":")){ //仅首字符为:时为AllInOne，其实:与伪类选择器冲突，建议改成?更合理
var start = 0
//仅首字符为:时为AllInOne，其实:与伪类选择器冲突，建议改成?更合理
if (isList && ruleStr.startsWith(":")) {
mMode = Mode.Regex
isRegex = true
1
}else 0
start = 1
}
var tmp: String
val jsMatcher = JS_PATTERN.matcher(ruleStr)
while (jsMatcher.find()){
while (jsMatcher.find()) {
if (jsMatcher.start() > start) {
tmp = ruleStr.substring(start, jsMatcher.start()).trim { it <= ' ' }
if (tmp.isNotEmpty()) {
ruleList.add(SourceRule(mode(tmp), mMode))
ruleList.add(SourceRule(tmp, mMode))
}
}
ruleList.add(SourceRule(jsMatcher.group(2)?:jsMatcher.group(1), Mode.Js))
ruleList.add(SourceRule(jsMatcher.group(2) ?: jsMatcher.group(1), Mode.Js))
start = jsMatcher.end()
}
if (ruleStr.length > start){
if (ruleStr.length > start) {
tmp = ruleStr.substring(start).trim { it <= ' ' }
if (tmp.isNotEmpty()) {
ruleList.add(SourceRule(mode(tmp), mMode))
ruleList.add(SourceRule(tmp, mMode))
}
}
@ -437,43 +410,56 @@ class AnalyzeRule(val ruleData: RuleDataInterface) : JsExtensions {
init {
this.mode = mainMode
rule = when {
ruleStr.startsWith("@CSS:", true) -> {
mode = Mode.Default
ruleStr
}
ruleStr.startsWith("@@") -> {
mode = Mode.Default
ruleStr.substring(2)
}
ruleStr.startsWith("@XPath:", true) -> {
mode = Mode.XPath
ruleStr.substring(7)
}
ruleStr.startsWith("/") -> {//XPath特征很明显,无需配置单独的识别标头
mode = Mode.XPath
ruleStr
}
ruleStr.startsWith("@Json:", true) -> {
mode = Mode.Json
ruleStr.substring(6)
}
(ruleStr[1] == '.' || ruleStr[1] == '[') && ruleStr.startsWith("$.") || isJSON -> {
mode = Mode.Json
ruleStr
}
else -> {
ruleStr
}
}
//分离put
rule = splitPutRule(ruleStr, putMap)
rule = splitPutRule(rule, putMap)
//@get,{{ }}, 拆分
var start = 0
var tmp: String
val evalMatcher = evalPattern.matcher(rule)
if(evalMatcher.find()){
var modeX = mode == Mode.Js || mode == Mode.Regex
if (evalMatcher.start() > 0 ) {
tmp = rule.substring(0, evalMatcher.start())
modeX = modeX || tmp.contains("##")
splitRegex(tmp)
}
if(!modeX)mode = Mode.Regex
tmp = evalMatcher.group()
when {
tmp.startsWith("@get:", true) -> {
ruleType.add(getRuleType)
ruleParam.add(tmp.substring(6, tmp.lastIndex))
}
tmp.startsWith("{{") -> {
ruleType.add(jsRuleType)
ruleParam.add(tmp.substring(2, tmp.length - 2))
}
else -> {
splitRegex(tmp)
}
if (evalMatcher.find()) {
if (mode != Mode.Js && mode != Mode.Regex
&& evalMatcher.start() == 0
) {
mode = Mode.Regex
}
start = evalMatcher.end()
while (evalMatcher.find()){
do {
if (evalMatcher.start() > start) {
tmp = rule.substring(start, evalMatcher.start())
if (mode != Mode.Js && mode != Mode.Regex
&& start == 0 && !tmp.contains("##")
) {
mode = Mode.Regex
}
splitRegex(tmp)
}
tmp = evalMatcher.group()
@ -491,9 +477,8 @@ class AnalyzeRule(val ruleData: RuleDataInterface) : JsExtensions {
}
}
start = evalMatcher.end()
}
} while (evalMatcher.find())
}
if (rule.length > start) {
tmp = rule.substring(start)
splitRegex(tmp)
@ -509,11 +494,11 @@ class AnalyzeRule(val ruleData: RuleDataInterface) : JsExtensions {
val ruleStrArray = ruleStr.split("##")
val regexMatcher = regexPattern.matcher(ruleStrArray[0])
if(regexMatcher.find()) {
if (regexMatcher.find()) {
if (mode != Mode.Js && mode != Mode.Regex) {
mode = Mode.Regex
}
do{
do {
if (regexMatcher.start() > start) {
tmp = ruleStr.substring(start, regexMatcher.start())
ruleType.add(defaultRuleType)
@ -523,7 +508,7 @@ class AnalyzeRule(val ruleData: RuleDataInterface) : JsExtensions {
ruleType.add(tmp.substring(1).toInt())
ruleParam.add(tmp)
start = regexMatcher.end()
}while (regexMatcher.find())
} while (regexMatcher.find())
}
if (ruleStr.length > start) {
tmp = ruleStr.substring(start)

14
app/src/main/java/io/legado/app/model/analyzeRule/AnalyzeUrl.kt
Unescape View File

@ -84,7 +84,7 @@ class AnalyzeUrl(
ruleUrl = tmp.replace("@result", ruleUrl)
}
}
ruleUrl = evalJS(jsMatcher.group(2)?:jsMatcher.group(1), ruleUrl) as String
ruleUrl = evalJS(jsMatcher.group(2) ?: jsMatcher.group(1), ruleUrl) as String
start = jsMatcher.end()
}
if (ruleUrl.length > start) {
@ -116,14 +116,14 @@ class AnalyzeUrl(
bindings["book"] = book
//替换所有内嵌{{js}}
val url = analyze.innerRule("{{","}}"){
when(val jsEval = SCRIPT_ENGINE.eval(it, bindings)){
val url = analyze.innerRule("{{", "}}") {
when (val jsEval = SCRIPT_ENGINE.eval(it, bindings)) {
is String -> jsEval
jsEval is Double && jsEval % 1.0 == 0.0 -> String.format("%.0f", jsEval)
else -> jsEval.toString()
}
}
if(url.isNotEmpty())ruleUrl = url
if (url.isNotEmpty()) ruleUrl = url
}
//page
page?.let {
@ -143,7 +143,6 @@ class AnalyzeUrl(
* 处理URL
*/
private fun initUrl() { //replaceKeyPageJs已经替换掉额外内容，此处url是基础形式，可以直接切首个‘,’之前字符串。
val urlMatcher = paramPattern.matcher(ruleUrl)
urlHasQuery = if(urlMatcher.find())ruleUrl.substring(0,urlMatcher.start()) else ruleUrl
url = NetworkUtils.getAbsoluteURL(baseUrl,urlHasQuery )
@ -152,7 +151,6 @@ class AnalyzeUrl(
}
if(urlHasQuery.length != ruleUrl.length ) {
GSON.fromJsonObject<UrlOption>(ruleUrl.substring(urlMatcher.end()))?.let { option ->
option.method?.let {
if (it.equals("POST", true)) method = RequestMethod.POST
}
@ -190,9 +188,9 @@ class AnalyzeUrl(
RequestMethod.GET -> {
if (!useWebView) {
val pos = url.indexOf('?')
if(pos != -1) {
if (pos != -1) {
analyzeFields(url.substring(pos + 1))
url = url.substring(0,pos)
url = url.substring(0, pos)
}
}
}

91
app/src/main/java/io/legado/app/model/analyzeRule/RuleAnalyzer.kt
Unescape View File

@ -1,8 +1,9 @@
package io.legado.app.model.analyzeRule
import io.legado.app.utils.isJson
import java.util.ArrayList
import java.util.*
import java.util.regex.Pattern
import kotlin.collections.HashMap
//通用的规则切分处理
@ -70,6 +71,7 @@ class RuleAnalyzer(data: String, code: Boolean = false) {
}
return false
}
/**
* 从剩余字串中拉出一个字符串，直到但不包括匹配序列（匹配参数列表中一项即为匹配），或剩余字串用完。
* @param seq 匹配字符串序列
@ -369,8 +371,8 @@ class RuleAnalyzer(data: String, code: Boolean = false) {
*
* */
fun innerRule(
startStr:String,
endStr:String,
startStr: String,
endStr: String,
fr: (String) -> String?
): String {
@ -380,13 +382,18 @@ class RuleAnalyzer(data: String, code: Boolean = false) {
val posPre = pos //记录consumeTo匹配位置
if (consumeTo(endStr)) {
val frv = fr(queue.substring(posPre, pos))
st.append(queue.substring(startX, posPre - startStr.length) + frv) //压入内嵌规则前的内容，及内嵌规则解析得到的字符串
pos += endStr.length //跳过结束字符串
startX = pos //记录下次规则起点
st.append(
queue.substring(
startX,
posPre - startStr.length
) + frv
) //压入内嵌规则前的内容，及内嵌规则解析得到的字符串
pos += endStr.length //跳过结束字符串
startX = pos //记录下次规则起点
}
}
return if(startX == 0) queue else st.apply {
return if (startX == 0) queue else st.apply {
append(queue.substring(startX))
}.toString()
}
@ -394,8 +401,10 @@ class RuleAnalyzer(data: String, code: Boolean = false) {
//-----------此处向下的函数和变量都未被使用，但以后要用--------
val ruleTypeList = ArrayList<String>()
//设置平衡组函数，json或JavaScript时设置成chompCodeBalanced，否则为chompRuleBalanced
val chompBalanced = if (code) ::chompCodeBalanced else ::chompRuleBalanced
enum class Mode {
XPath, Json, Default, Js, Regex
}
@ -450,11 +459,11 @@ class RuleAnalyzer(data: String, code: Boolean = false) {
pos = st //位置回到筛选器处
val next = if (queue[pos] == '[') ']' else ')' //平衡组末尾字符
if (!chompBalanced(queue[pos], next)){
if (!chompBalanced(queue[pos], next)) {
ruleTypeList.clear()
rule.clear()
consumeToAny("<js>","@js:")
rule += queue.substring(0,pos)
consumeToAny("<js>", "@js:")
rule += queue.substring(0, pos)
ruleTypeList += queue.substring(pos, pos + 4) //设置组合类型
}
@ -472,7 +481,7 @@ class RuleAnalyzer(data: String, code: Boolean = false) {
var isMulu = false
var isreverse = false
var isAllInOne= false
var isAllInOne = false
var isFind = false
private val findName = ArrayList<String>()
@ -488,15 +497,15 @@ class RuleAnalyzer(data: String, code: Boolean = false) {
private val defaultRuleType = 0
@JvmOverloads
fun setContent(cont: String,type:String = ""): RuleAnalyzer {
fun setContent(cont: String, type: String = ""): RuleAnalyzer {
queue = cont
when(type){
when (type) {
"mulu" -> {
if(queue[0] =='-'){ //目录反转
if (queue[0] == '-') { //目录反转
isreverse = true
startX++
pos++
}else if(queue[0] =='?'){ //AllInOne
} else if (queue[0] == '?') { //AllInOne
isAllInOne = true
startX++
pos++
@ -505,8 +514,8 @@ class RuleAnalyzer(data: String, code: Boolean = false) {
}
"find" -> {
pos = queue.indexOf("::")
findName.add(queue.substring(startX,pos))
pos+=2
findName.add(queue.substring(startX, pos))
pos += 2
isFind = true
}
"url" -> {
@ -538,14 +547,15 @@ class RuleAnalyzer(data: String, code: Boolean = false) {
/**
* 参数字符串
*/
private val STARTSTRURL = arrayOf(",{",)
private val STARTSTRURL = arrayOf(",{")
private val regexPattern = Pattern.compile("\\$\\d{1,2}")
private val putPattern = Pattern.compile("@put:(\\{[^}]+?\\})", Pattern.CASE_INSENSITIVE)
private val getPattern = Pattern.compile("@get:\\{([^}]+?)\\}", Pattern.CASE_INSENSITIVE)
private val evalPattern = Pattern.compile("\\{\\{[\\w\\W]*?\\}\\}", Pattern.CASE_INSENSITIVE)
private val evalPattern =
Pattern.compile("\\{\\{[\\w\\W]*?\\}\\}", Pattern.CASE_INSENSITIVE)
val ENDSTR= mapOf(
val ENDSTR = mapOf(
"<js>" to "</js>",
"{{" to "}}",
)
@ -553,18 +563,35 @@ class RuleAnalyzer(data: String, code: Boolean = false) {
/**
* 规则起始字符串
*/
private val STARTSTR = arrayOf("@js:","<js>","</js>","##","@@","@"
,"{{@", "{{","}}"
,"}"
, "{@", "{/", "{$"
, "{class"
, "{id"
, "{tag"
, "{text"
, "{children"
,"/","$","@xpath:","@json:","@css:"
,"||", "&&", "%%"
,"@get:{","@put:{"
private val STARTSTR = arrayOf(
"@js:",
"<js>",
"</js>",
"##",
"@@",
"@",
"{{@",
"{{",
"}}",
"}",
"{@",
"{/",
"{$",
"{class",
"{id",
"{tag",
"{text",
"{children",
"/",
"$",
"@xpath:",
"@json:",
"@css:",
"||",
"&&",
"%%",
"@get:{",
"@put:{"
)
/**

7
app/src/main/java/io/legado/app/service/help/ReadBook.kt
Unescape View File

@ -415,10 +415,11 @@ object ReadBook {
else -> chapter.title
}
val contents = contentProcessor!!.getContent(book, chapter.title, content)
val textChapter = ChapterProvider.getTextChapter(book, chapter,contents,chapterSize)
val textChapter =
ChapterProvider.getTextChapter(book, chapter, contents, chapterSize)
val offset = chapter.index - durChapterIndex
if (upContent) callBack?.upContent(offset ,resetPageOffset)
if (upContent) callBack?.upContent(offset, resetPageOffset)
when (offset) {
0 -> {
curTextChapter = textChapter
@ -426,7 +427,7 @@ object ReadBook {
curPageChanged()
callBack?.contentLoadFinish()
}
- 1 -> {
-1 -> {
prevTextChapter = textChapter
}
1 -> {

2
app/src/main/java/io/legado/app/ui/book/read/page/provider/ChapterProvider.kt
Unescape View File

@ -113,7 +113,7 @@ object ChapterProvider {
} else if (book.getImageStyle() != Book.imgStyleText) {
content.replace(AppPattern.imgPattern.toRegex(), "\n\$0\n").split("\n")
.forEach { text ->
if(text.isNotBlank()){
if (text.isNotBlank()) {
if (!text.startsWith("<img src=\"")) { //非图片
val isTitle = index == 0
val textPaint = if (isTitle) titlePaint else contentPaint

Write Preview
Loading…
Cancel
Save