Improve Zip File Scanning on Mac

third_party/zlib/google/zip_reader.h

 // Copyright (c) 2011 The Chromium Authors. All rights reserved.
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE file.
 #ifndef THIRD_PARTY_ZLIB_GOOGLE_ZIP_READER_H_
 #define THIRD_PARTY_ZLIB_GOOGLE_ZIP_READER_H_
 
 #include <stddef.h>
 #include <stdint.h>
 
 #include <memory>
@@ skipping 141 matching lines @@
   //
   // Note that there is no CloseCurrentEntryInZip(). The the current entry
   // state is reset automatically as needed.
   bool OpenCurrentEntryInZip();
 
   // Locates an entry in the zip file and opens it. Returns true on
   // success. This function internally calls OpenCurrentEntryInZip() on
   // success. On failure, current_entry_info() becomes NULL.
   bool LocateAndOpenEntry(const base::FilePath& path_in_zip);
 
-  // Extracts the current entry in chunks to |delegate|.
-  bool ExtractCurrentEntry(WriterDelegate* delegate) const;
+  // Extracts |num_bytes_to_extract| bytes of the current entry to |delegate|,
+  // starting from the beginning of the entry. A negative value for
+  // |num_bytes_to_extract| means the entire current entry will be extracted.
+  // Returns false if file is too large to be extracted to |delegate| or if file
+  // is too small to fill |num_bytes_to_extract|.
+  bool ExtractCurrentEntry(WriterDelegate* delegate,
+                           int64_t num_bytes_to_extract) const;
 
   // Extracts the current entry to the given output file path. If the
   // current file is a directory, just creates a directory
   // instead. Returns true on success. OpenCurrentEntryInZip() must be
   // called beforehand.
   //
   // This function preserves the timestamp of the original entry. If that
   // timestamp is not valid, the timestamp will be set to the current time.
   bool ExtractCurrentEntryToFilePath(
       const base::FilePath& output_file_path) const;
@@ skipping 21 matching lines @@
   //
   // This function preserves the timestamp of the original entry. If that
   // timestamp is not valid, the timestamp will be set to the current time.
   bool ExtractCurrentEntryIntoDirectory(
       const base::FilePath& output_directory_path) const;
 
   // Extracts the current entry by writing directly to a platform file.
   // Does not close the file. Returns true on success.
   bool ExtractCurrentEntryToFile(base::File* file) const;
 
-  // 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;
+  // 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. 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. If |read_entire_file| is true, then
+  // |num_bytes| limits the ammount of memory used to carry the entry, and false
+  // is returned if the real size of the uncompressed data is bigger than
+  // |max_read_bytes|. Otherwise if |read_entire_file| is false, |num_bytes|

[satorux1, 2017/07/25 07:55:15]

nit: num_bytes and max_read_bytes are not consistent.

[mortonm, 2017/07/25 18:10:15]

Done.

+  // signifies the number of bytes to read from the file, and false is returned
+  // if the real size of the uncompressed data is smaller than |max_read_bytes|.
+  bool ExtractCurrentEntryToString(size_t num_bytes,
+                                   bool read_entire_file,

[satorux1, 2017/07/25 07:55:15]

zip_analyzier is the only caller of this function, so I think we can drop
|read_entire_file| parameter to simplify the function. How about:

bool ExtractCurrentEntryToString(size_t max_read_bytes,
                                 std::string* output) const;

Returns true if the entire content is read.

If the content is bigger than |max_read_bytes|,
returns false and |output| is filled with|max_read_bytes| of data.

If an error occurs, returns false, and |output| is set to the empty string.

[mortonm, 2017/07/25 18:10:15]

Done, I agree, this is a better way of writing this function. I still kept the
|num_bytes_to_extract| parameter in ExtractCurrentEntry(), since that function
needs to know how many bytes to extract from the entry and there is no member of
WriterDelegate that gives this value.

+                                   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 {
     return current_entry_info_.get();
   }
 
   // Returns the number of entries in the zip file.
   // Open() must be called beforehand.
   int num_entries() const { return num_entries_; }
@@ skipping 43 matching lines @@
  private:
   base::File* file_;
   int64_t file_length_;
 
   DISALLOW_COPY_AND_ASSIGN(FileWriterDelegate);
 };
 
 }  // namespace zip
 
 #endif  // THIRD_PARTY_ZLIB_GOOGLE_ZIP_READER_H_