背景
我想获取有关 APK 文件(包括拆分的 APK 文件)的信息，即使它们位于压缩的 zip 文件中(无需解压缩)。就我而言，这包括各种内容，例如包名称、版本代码、版本名称、应用标签、应用图标，以及它是否是拆分的 APK 文件。
请注意，我想在 Android 应用程序中完成所有操作，而不是使用 PC，因此可能无法使用某些工具。
问题
这意味着我不能使用 getPackageArchiveInfo函数，因为此函数需要 APK 文件的路径，并且仅适用于非拆分 apk 文件。
简而言之，没有框架函数可以做到这一点，所以我必须找到一种方法，方法是进入压缩文件，使用 InputStream 作为输入以在函数中解析它。
网上有各种解决方案，包括 Android 之外的解决方案，但我不知道有一种稳定且适用于所有情况的解决方案。许多甚至对于 Android 来说都可能是好的(例如 here )，但可能无法解析并且可能需要文件路径而不是 Uri/InputStream。
我发现并尝试过的
我找到了 this在 StackOverflow 上，但遗憾的是根据我的测试，它总是生成内容，但在极少数情况下它不是有效的 XML 内容。
到目前为止，我发现解析器无法解析这些应用程序包名称及其版本代码，因为输出 XML 内容无效:
使用 XML viewer和 XML validator ，以下是这些应用程序的问题:
<mnfs 开头. <activity theme="resourceID 0x7f13000b" label="Features & Tests" ... 中的“&”。 <manifest versionCode="resourceID 0xa" ="1.3.2" . 令人惊讶的是，我没有发现拆分 APK 文件有任何问题。仅适用于主要 APK 文件。
这是代码(也可用 here ):
MainActivity .kt
class MainActivity : AppCompatActivity() {
override fun onCreate(savedInstanceState: Bundle?) {
super.onCreate(savedInstanceState)
setContentView(R.layout.activity_main)
thread {
val problematicApkFiles = HashMap<ApplicationInfo, HashSet<String>>()
val installedApplications = packageManager.getInstalledPackages(0)
val startTime = System.currentTimeMillis()
for ((index, packageInfo) in installedApplications.withIndex()) {
val applicationInfo = packageInfo.applicationInfo
val packageName = packageInfo.packageName
// Log.d("AppLog", "$index/${installedApplications.size} parsing app $packageName ${packageInfo.versionCode}...")
val mainApkFilePath = applicationInfo.publicSourceDir
val parsedManifestOfMainApkFile =
try {
val parsedManifest = ManifestParser.parse(mainApkFilePath)
if (parsedManifest?.isSplitApk != false)
Log.e("AppLog", "$packageName - parsed normal APK, but failed to identify it as such")
parsedManifest?.manifestAttributes
} catch (e: Exception) {
Log.e("AppLog", e.toString())
null
}
if (parsedManifestOfMainApkFile == null) {
problematicApkFiles.getOrPut(applicationInfo, { HashSet() }).add(mainApkFilePath)
Log.e("AppLog", "$packageName - failed to parse main APK file $mainApkFilePath")
}
if (Build.VERSION.SDK_INT >= Build.VERSION_CODES.LOLLIPOP)
applicationInfo.splitPublicSourceDirs?.forEach {
val parsedManifestOfSplitApkFile =
try {
val parsedManifest = ManifestParser.parse(it)
if (parsedManifest?.isSplitApk != true)
Log.e("AppLog", "$packageName - parsed split APK, but failed to identify it as such")
parsedManifest?.manifestAttributes
} catch (e: Exception) {
Log.e("AppLog", e.toString())
null
}
if (parsedManifestOfSplitApkFile == null) {
Log.e("AppLog", "$packageName - failed to parse main APK file $it")
problematicApkFiles.getOrPut(applicationInfo, { HashSet() }).add(it)
}
}
}
val endTime = System.currentTimeMillis()
Log.d("AppLog", "done parsing. number of files we failed to parse:${problematicApkFiles.size} time taken:${endTime - startTime} ms")
if (problematicApkFiles.isNotEmpty()) {
Log.d("AppLog", "list of files that we failed to get their manifest:")
for (entry in problematicApkFiles) {
Log.d("AppLog", "packageName:${entry.key.packageName} , files:${entry.value}")
}
}
}
}
}
ManifestParser.kt
class ManifestParser{
var isSplitApk: Boolean? = null
var manifestAttributes: HashMap<String, String>? = null
companion object {
fun parse(file: File) = parse(java.io.FileInputStream(file))
fun parse(filePath: String) = parse(File(filePath))
fun parse(inputStream: InputStream): ManifestParser? {
val result = ManifestParser()
val manifestXmlString = ApkManifestFetcher.getManifestXmlFromInputStream(inputStream)
?: return null
val factory: DocumentBuilderFactory = DocumentBuilderFactory.newInstance()
val builder: DocumentBuilder = factory.newDocumentBuilder()
val document: Document? = builder.parse(manifestXmlString.byteInputStream())
if (document != null) {
document.documentElement.normalize()
val manifestNode: Node? = document.getElementsByTagName("manifest")?.item(0)
if (manifestNode != null) {
val manifestAttributes = HashMap<String, String>()
for (i in 0 until manifestNode.attributes.length) {
val node = manifestNode.attributes.item(i)
manifestAttributes[node.nodeName] = node.nodeValue
}
result.manifestAttributes = manifestAttributes
}
}
result.manifestAttributes?.let {
result.isSplitApk = (it["android:isFeatureSplit"]?.toBoolean()
?: false) || (it.containsKey("split"))
}
return result
}
}
}
ApkManifestFetcher.kt
object ApkManifestFetcher {
fun getManifestXmlFromFile(apkFile: File) = getManifestXmlFromInputStream(FileInputStream(apkFile))
fun getManifestXmlFromFilePath(apkFilePath: String) = getManifestXmlFromInputStream(FileInputStream(File(apkFilePath)))
fun getManifestXmlFromInputStream(ApkInputStream: InputStream): String? {
ZipInputStream(ApkInputStream).use { zipInputStream: ZipInputStream ->
while (true) {
val entry = zipInputStream.nextEntry ?: break
if (entry.name == "AndroidManifest.xml") {
// zip.getInputStream(entry).use { input ->
return decompressXML(zipInputStream.readBytes())
// }
}
}
}
return null
}
/**
* Binary XML doc ending Tag
*/
private var endDocTag = 0x00100101
/**
* Binary XML start Tag
*/
private var startTag = 0x00100102
/**
* Binary XML end Tag
*/
private var endTag = 0x00100103
/**
* Reference var for spacing
* Used in prtIndent()
*/
private var spaces = " "
/**
* Parse the 'compressed' binary form of Android XML docs
* such as for AndroidManifest.xml in .apk files
* Source: http://stackoverflow.com/questions/2097813/how-to-parse-the-androidmanifest-xml-file-inside-an-apk-package/4761689#4761689
*
* @param xml Encoded XML content to decompress
*/
private fun decompressXML(xml: ByteArray): String {
val resultXml = StringBuilder()
// Compressed XML file/bytes starts with 24x bytes of data,
// 9 32 bit words in little endian order (LSB first):
// 0th word is 03 00 08 00
// 3rd word SEEMS TO BE: Offset at then of StringTable
// 4th word is: Number of strings in string table
// WARNING: Sometime I indiscriminently display or refer to word in
// little endian storage format, or in integer format (ie MSB first).
val numbStrings = lew(xml, 4 * 4)
// StringIndexTable starts at offset 24x, an array of 32 bit LE offsets
// of the length/string data in the StringTable.
val sitOff = 0x24 // Offset of start of StringIndexTable
// StringTable, each string is represented with a 16 bit little endian
// character count, followed by that number of 16 bit (LE) (Unicode) chars.
val stOff = sitOff + numbStrings * 4 // StringTable follows StrIndexTable
// XMLTags, The XML tag tree starts after some unknown content after the
// StringTable. There is some unknown data after the StringTable, scan
// forward from this point to the flag for the start of an XML start tag.
var xmlTagOff = lew(xml, 3 * 4) // Start from the offset in the 3rd word.
// Scan forward until we find the bytes: 0x02011000(x00100102 in normal int)
run {
var ii = xmlTagOff
while (ii < xml.size - 4) {
if (lew(xml, ii) == startTag) {
xmlTagOff = ii
break
}
ii += 4
}
} // end of hack, scanning for start of first start tag
// XML tags and attributes:
// Every XML start and end tag consists of 6 32 bit words:
// 0th word: 02011000 for startTag and 03011000 for endTag
// 1st word: a flag?, like 38000000
// 2nd word: Line of where this tag appeared in the original source file
// 3rd word: FFFFFFFF ??
// 4th word: StringIndex of NameSpace name, or FFFFFFFF for default NS
// 5th word: StringIndex of Element Name
// (Note: 01011000 in 0th word means end of XML document, endDocTag)
// Start tags (not end tags) contain 3 more words:
// 6th word: 14001400 meaning??
// 7th word: Number of Attributes that follow this tag(follow word 8th)
// 8th word: 00000000 meaning??
// Attributes consist of 5 words:
// 0th word: StringIndex of Attribute Name's Namespace, or FFFFFFFF
// 1st word: StringIndex of Attribute Name
// 2nd word: StringIndex of Attribute Value, or FFFFFFF if ResourceId used
// 3rd word: Flags?
// 4th word: str ind of attr value again, or ResourceId of value
// TMP, dump string table to tr for debugging
//tr.addSelect("strings", null);
//for (int ii=0; ii<numbStrings; ii++) {
// // Length of string starts at StringTable plus offset in StrIndTable
// String str = compXmlString(xml, sitOff, stOff, ii);
// tr.add(String.valueOf(ii), str);
//}
//tr.parent();
// Step through the XML tree element tags and attributes
var off = xmlTagOff
var indent = 0
// var startTagLineNo = -2
while (off < xml.size) {
val tag0 = lew(xml, off)
//int tag1 = LEW(xml, off+1*4);
// val lineNo = lew(xml, off + 2 * 4)
//int tag3 = LEW(xml, off+3*4);
// val nameNsSi = lew(xml, off + 4 * 4)
val nameSi = lew(xml, off + 5 * 4)
if (tag0 == startTag) { // XML START TAG
// val tag6 = lew(xml, off + 6 * 4) // Expected to be 14001400
val numbAttrs = lew(xml, off + 7 * 4) // Number of Attributes to follow
//int tag8 = LEW(xml, off+8*4); // Expected to be 00000000
off += 9 * 4 // Skip over 6+3 words of startTag data
val name = compXmlString(xml, sitOff, stOff, nameSi)
//tr.addSelect(name, null);
// startTagLineNo = lineNo
// Look for the Attributes
val sb = StringBuffer()
for (ii in 0 until numbAttrs) {
// val attrNameNsSi = lew(xml, off) // AttrName Namespace Str Ind, or FFFFFFFF
val attrNameSi = lew(xml, off + 1 * 4) // AttrName String Index
val attrValueSi = lew(xml, off + 2 * 4) // AttrValue Str Ind, or FFFFFFFF
// val attrFlags = lew(xml, off + 3 * 4)
val attrResId = lew(xml, off + 4 * 4) // AttrValue ResourceId or dup AttrValue StrInd
off += 5 * 4 // Skip over the 5 words of an attribute
val attrName = compXmlString(xml, sitOff, stOff, attrNameSi)
val attrValue = if (attrValueSi != -1)
compXmlString(xml, sitOff, stOff, attrValueSi)
else
"resourceID 0x" + Integer.toHexString(attrResId)
sb.append(" $attrName=\"$attrValue\"")
//tr.add(attrName, attrValue);
}
resultXml.append(prtIndent(indent, "<$name$sb>"))
indent++
} else if (tag0 == endTag) { // XML END TAG
indent--
off += 6 * 4 // Skip over 6 words of endTag data
val name = compXmlString(xml, sitOff, stOff, nameSi)
resultXml.append(prtIndent(indent, "</$name>")) // (line $startTagLineNo-$lineNo)
//tr.parent(); // Step back up the NobTree
} else if (tag0 == endDocTag) { // END OF XML DOC TAG
break
} else {
// println(" Unrecognized tag code '" + Integer.toHexString(tag0)
// + "' at offset " + off
// )
break
}
} // end of while loop scanning tags and attributes of XML tree
// println(" end at offset $off")
return resultXml.toString()
} // end of decompressXML
/**
* Tool Method for decompressXML();
* Compute binary XML to its string format
* Source: Source: http://stackoverflow.com/questions/2097813/how-to-parse-the-androidmanifest-xml-file-inside-an-apk-package/4761689#4761689
*
* @param xml Binary-formatted XML
* @param sitOff
* @param stOff
* @param strInd
* @return String-formatted XML
*/
private fun compXmlString(xml: ByteArray, @Suppress("SameParameterValue") sitOff: Int, stOff: Int, strInd: Int): String? {
if (strInd < 0) return null
val strOff = stOff + lew(xml, sitOff + strInd * 4)
return compXmlStringAt(xml, strOff)
}
/**
* Tool Method for decompressXML();
* Apply indentation
*
* @param indent Indentation level
* @param str String to indent
* @return Indented string
*/
private fun prtIndent(indent: Int, str: String): String {
return spaces.substring(0, min(indent * 2, spaces.length)) + str
}
/**
* Tool method for decompressXML()
* Return the string stored in StringTable format at
* offset strOff. This offset points to the 16 bit string length, which
* is followed by that number of 16 bit (Unicode) chars.
*
* @param arr StringTable array
* @param strOff Offset to get string from
* @return String from StringTable at offset strOff
*/
private fun compXmlStringAt(arr: ByteArray, strOff: Int): String {
val strLen = (arr[strOff + 1] shl (8 and 0xff00)) or (arr[strOff].toInt() and 0xff)
val chars = ByteArray(strLen)
for (ii in 0 until strLen) {
chars[ii] = arr[strOff + 2 + ii * 2]
}
return String(chars) // Hack, just use 8 byte chars
} // end of compXmlStringAt
/**
* Return value of a Little Endian 32 bit word from the byte array
* at offset off.
*
* @param arr Byte array with 32 bit word
* @param off Offset to get word from
* @return Value of Little Endian 32 bit word specified
*/
private fun lew(arr: ByteArray, off: Int): Int {
return (arr[off + 3] shl 24 and -0x1000000 or ((arr[off + 2] shl 16) and 0xff0000)
or (arr[off + 1] shl 8 and 0xff00) or (arr[off].toInt() and 0xFF))
} // end of LEW
private infix fun Byte.shl(i: Int): Int = (this.toInt() shl i)
// private infix fun Int.shl(i: Int): Int = (this shl i)
}
问题
最佳答案
您可能必须处理您已经确定的所有特殊情况。
别名和十六进制引用可能会混淆它；这些都需要解决。
例如，从 manifest 回退至mnfs至少可以解决一个问题:
fun getRootNode(document: Document): Node? {
var node: Node? = document.getElementsByTagName("manifest")?.item(0)
if (node == null) {
node = document.getElementsByTagName("mnfs")?.item(0)
}
return node
}
“功能和测试”需要
TextUtils.htmlEncode()对于 &或其他解析器配置。使其解析单个
AndroidManifest.xml文件会使测试变得更容易，因为每个其他包可能会有更多意想不到的输入 - 直到它接近操作系统使用的 list 解析器(source code 可能有帮助)。可以看到，它可能会设置 cookie 来读取它。获取这个包名称列表并为每个包设置一个测试用例，那么问题就相当孤立了。但主要问题是这些 cookie 很可能对 3rd 方应用程序不可用。
关于android - 即使使用 InputStream，如何获得可靠且有效的 APK 文件 list 内容？，我们在Stack Overflow上找到一个类似的问题： https://stackoverflow.com/questions/60565299/