New ZipReader::ExtractCurrentEntryToString API.

New API which extract a zip entry into a memory buffer.

BUG=359428

Review URL: https://codereview.chromium.org/292443006

git-svn-id: svn://svn.chromium.org/chrome/trunk/src@278766 0039d316-1c4b-4281-b951-d872f2087c98

3 files changed, 107 insertions, 1 deletions

diff --git a/third_party/zlib/google/zip_reader.cc b/third_party/zlib/google/zip_reader.cc
index aa85fa3..80b60b3 100644
--- a/third_party/zlib/google/zip_reader.cc
+++ b/third_party/zlib/google/zip_reader.cc
@@ -344,6 +344,58 @@ bool ZipReader::ExtractCurrentEntryToFd(const int fd) {
 }
 #endif  // defined(OS_POSIX)
 
+bool ZipReader::ExtractCurrentEntryToString(
+    size_t max_read_bytes,
+    std::string* output) const {
+  DCHECK(output);
+  DCHECK(zip_file_);
+  DCHECK(max_read_bytes != 0);
+
+  if (current_entry_info()->is_directory()) {
+    output->clear();
+    return true;
+  }
+
+  const int open_result = unzOpenCurrentFile(zip_file_);
+  if (open_result != UNZ_OK)
+    return false;
+
+  // The original_size() is the best hint for the real size, so it saves
+  // doing reallocations for the common case when the uncompressed size is
+  // correct. However, we need to assume that the uncompressed size could be
+  // incorrect therefore this function needs to read as much data as possible.
+  std::string contents;
+  contents.reserve(std::min<size_t>(
+      max_read_bytes, current_entry_info()->original_size()));
+
+  bool success = true;  // This becomes false when something bad happens.
+  char buf[internal::kZipBufSize];
+  while (true) {
+    const int num_bytes_read = unzReadCurrentFile(zip_file_, buf,
+                                                  internal::kZipBufSize);
+    if (num_bytes_read == 0) {
+      // Reached the end of the file.
+      break;
+    } else if (num_bytes_read < 0) {
+      // If num_bytes_read < 0, then it's a specific UNZ_* error code.
+      success = false;
+      break;
+    } else if (num_bytes_read > 0) {
+      if (contents.size() + num_bytes_read > max_read_bytes) {
+        success = false;
+        break;
+      }
+      contents.append(buf, num_bytes_read);
+    }
+  }
+
+  unzCloseCurrentFile(zip_file_);
+  if (success)
+    output->swap(contents);
+
+  return success;
+}
+
 bool ZipReader::OpenInternal() {
   DCHECK(zip_file_);
 
diff --git a/third_party/zlib/google/zip_reader.h b/third_party/zlib/google/zip_reader.h
index 60b53ee..fa4186b 100644
--- a/third_party/zlib/google/zip_reader.h
+++ b/third_party/zlib/google/zip_reader.h
@@ -35,7 +35,7 @@ namespace zip {
 //     reader.AdvanceToNextEntry();
 //   }
 //
-// For simplicty, error checking is omitted in the example code above. The
+// For simplicity, error checking is omitted in the example code above. The
 // production code should check return values from all of these functions.
 //
 // This calls can also be used for random access of contents in a zip file
@@ -182,6 +182,21 @@ class ZipReader {
   bool ExtractCurrentEntryToFd(int fd);
 #endif
 
+  // Extracts the current entry into memory. If the current entry is a directory
+  // the |output| parameter is set to the empty string. If the current entry is
+  // a file, the |output| parameter is filled with its contents. Returns true on
+  // success. OpenCurrentEntryInZip() must be called beforehand.
+  // Note: the |output| parameter can be filled with a big amount of data, avoid
+  // passing it around by value, but by reference or pointer.
+  // Note: the value returned by EntryInfo::original_size() cannot be
+  // trusted, so the real size of the uncompressed contents can be different.
+  // Use max_read_bytes to limit the ammount of memory used to carry the entry.
+  // If the real size of the uncompressed data is bigger than max_read_bytes
+  // then false is returned. |max_read_bytes| must be non-zero.
+  bool ExtractCurrentEntryToString(
+      size_t max_read_bytes,
+      std::string* output) const;
+
   // Returns the current entry info. Returns NULL if the current entry is
   // not yet opened. OpenCurrentEntryInZip() must be called beforehand.
   EntryInfo* current_entry_info() const {
diff --git a/third_party/zlib/google/zip_reader_unittest.cc b/third_party/zlib/google/zip_reader_unittest.cc
index df20e6f..a137d9d 100644
--- a/third_party/zlib/google/zip_reader_unittest.cc
+++ b/third_party/zlib/google/zip_reader_unittest.cc
@@ -15,6 +15,7 @@
 #include "base/md5.h"
 #include "base/path_service.h"
 #include "base/run_loop.h"
+#include "base/strings/stringprintf.h"
 #include "base/strings/utf_string_conversions.h"
 #include "base/time/time.h"
 #include "testing/gtest/include/gtest/gtest.h"
@@ -534,4 +535,42 @@ TEST_F(ZipReaderTest, ExtractToFileAsync_Directory) {
   ASSERT_TRUE(base::DirectoryExists(target_file));
 }
 
+TEST_F(ZipReaderTest, ExtractCurrentEntryToString) {
+  // test_mismatch_size.zip contains files with names from 0.txt to 7.txt with
+  // sizes from 0 to 7 bytes respectively, being the contents of each file a
+  // substring of "0123456" starting at '0'.
+  base::FilePath test_zip_file =
+      test_data_dir_.AppendASCII("test_mismatch_size.zip");
+
+  ZipReader reader;
+  std::string contents;
+  ASSERT_TRUE(reader.Open(test_zip_file));
+
+  for (size_t i = 0; i < 8; i++) {
+    SCOPED_TRACE(base::StringPrintf("Processing %d.txt", static_cast<int>(i)));
+
+    base::FilePath file_name = base::FilePath::FromUTF8Unsafe(
+        base::StringPrintf("%d.txt", static_cast<int>(i)));
+    ASSERT_TRUE(reader.LocateAndOpenEntry(file_name));
+
+    if (i > 1) {
+      // Off by one byte read limit: must fail.
+      EXPECT_FALSE(reader.ExtractCurrentEntryToString(i - 1, &contents));
+    }
+
+    if (i > 0) {
+      // Exact byte read limit: must pass.
+      EXPECT_TRUE(reader.ExtractCurrentEntryToString(i, &contents));
+      EXPECT_EQ(i, contents.size());
+      EXPECT_EQ(0, memcmp(contents.c_str(), "0123456", i));
+    }
+
+    // More than necessary byte read limit: must pass.
+    EXPECT_TRUE(reader.ExtractCurrentEntryToString(16, &contents));
+    EXPECT_EQ(i, contents.size());
+    EXPECT_EQ(0, memcmp(contents.c_str(), "0123456", i));
+  }
+  reader.Close();
+}
+
 }  // namespace zip