ZipUtilsRO rewrite based on Dalvik Zip rewrite

Change the way zip archives are handled.  This is necessary to deal with
very large (~1GB) APK files, for which our current approach of mapping
the entire file falls over.

We now do the classic scavenger hunt for the End Of Central Directory
magic on a buffer of data read from the file, instead of a memory-mapped
section.  We use what we find to create a map that covers the Central
Directory only.

If the caller is interested in unpacking the file contents, we have to
do an additional file read to discover the size of the Local File Header
section so we can skip past it.

This is based on Change I745fb15abb in the dalvik tree. Both
implementations share a common ancestry, but the cost of unifying them
outweighs the benefits of wrapping C calls.

Change-Id: Iddacb50fe913917c2845708a530872d65fdbe620

2 files changed, 27 insertions, 10 deletions

diff --git a/include/utils/ZipFileCRO.h b/include/utils/ZipFileCRO.h
index 30e0036..e38bf66 100644
--- a/include/utils/ZipFileCRO.h
+++ b/include/utils/ZipFileCRO.h
@@ -47,8 +47,8 @@ extern ZipEntryCRO ZipFileCRO_findEntryByName(ZipFileCRO zip,
         const char* fileName);
 
 extern bool ZipFileCRO_getEntryInfo(ZipFileCRO zip, ZipEntryCRO entry,
-        int* pMethod, long* pUncompLen,
-        long* pCompLen, off_t* pOffset, long* pModWhen, long* pCrc32);
+        int* pMethod, size_t* pUncompLen,
+        size_t* pCompLen, off_t* pOffset, long* pModWhen, long* pCrc32);
 
 extern bool ZipFileCRO_uncompressEntry(ZipFileCRO zip, ZipEntryCRO entry, int fd);
 
diff --git a/include/utils/ZipFileRO.h b/include/utils/ZipFileRO.h
index 51c4f2f..97d31f4 100644
--- a/include/utils/ZipFileRO.h
+++ b/include/utils/ZipFileRO.h
@@ -58,14 +58,19 @@ typedef void* ZipEntryRO;
 class ZipFileRO {
 public:
     ZipFileRO()
-        : mFd(-1), mFileMap(NULL), mHashTableSize(-1), mHashTable(NULL)
+        : mFd(-1), mFileName(NULL), mFileLength(-1),
+          mDirectoryMap(NULL),
+          mNumEntries(-1), mDirectoryOffset(-1),
+          mHashTableSize(-1), mHashTable(NULL)
         {}
     ~ZipFileRO() {
         free(mHashTable);
-        if (mFileMap)
-            mFileMap->release();
+        if (mDirectoryMap)
+            mDirectoryMap->release();
         if (mFd >= 0)
             close(mFd);
+        if (mFileName)
+            free(mFileName);
     }
 
     /*
@@ -118,8 +123,8 @@ public:
      * Returns "false" if "entry" is bogus or if the data in the Zip file
      * appears to be bad.
      */
-    bool getEntryInfo(ZipEntryRO entry, int* pMethod, long* pUncompLen,
-        long* pCompLen, off_t* pOffset, long* pModWhen, long* pCrc32) const;
+    bool getEntryInfo(ZipEntryRO entry, int* pMethod, size_t* pUncompLen,
+        size_t* pCompLen, off_t* pOffset, long* pModWhen, long* pCrc32) const;
 
     /*
      * Create a new FileMap object that maps a subset of the archive.  For
@@ -155,13 +160,13 @@ public:
      * Utility function: uncompress deflated data, buffer to buffer.
      */
     static bool inflateBuffer(void* outBuf, const void* inBuf,
-        long uncompLen, long compLen);
+        size_t uncompLen, size_t compLen);
 
     /*
      * Utility function: uncompress deflated data, buffer to fd.
      */
     static bool inflateBuffer(int fd, const void* inBuf,
-        long uncompLen, long compLen);
+        size_t uncompLen, size_t compLen);
 
     /*
      * Some basic functions for raw data manipulation.  "LE" means
@@ -179,6 +184,9 @@ private:
     ZipFileRO(const ZipFileRO& src);
     ZipFileRO& operator=(const ZipFileRO& src);
 
+    /* locate and parse the central directory */
+    bool mapCentralDirectory(void);
+
     /* parse the archive, prepping internal structures */
     bool parseZipArchive(void);
 
@@ -203,12 +211,21 @@ private:
     /* open Zip archive */
     int         mFd;
 
+    /* zip file name */
+    char*       mFileName;
+
+    /* length of file */
+    size_t      mFileLength;
+
     /* mapped file */
-    FileMap*    mFileMap;
+    FileMap*    mDirectoryMap;
 
     /* number of entries in the Zip archive */
     int         mNumEntries;
 
+    /* CD directory offset in the Zip archive */
+    off_t       mDirectoryOffset;
+
     /*
      * We know how many entries are in the Zip archive, so we have a
      * fixed-size hash table.  We probe for an empty slot.