From: Michael McMaster Date: Thu, 19 May 2011 11:41:56 +0000 (+1000) Subject: ZIP Compression works! X-Git-Tag: v1.0.0~4 X-Git-Url: http://git.codesrc.com/gitweb.cgi?a=commitdiff_plain;h=ecf2cfbfa03a1928526a69aaa6e9e45706a7533f;p=libzipper.git ZIP Compression works! --- diff --git a/Compressor.cc b/Compressor.cc new file mode 100644 index 0000000..456385f --- /dev/null +++ b/Compressor.cc @@ -0,0 +1,139 @@ +// Copyright (C) 2011 Michael McMaster +// +// This file is part of libzipper. +// +// libzipper is free software: you can redistribute it and/or modify +// it under the terms of the GNU General Public License as published by +// the Free Software Foundation, either version 3 of the License, or +// (at your option) any later version. +// +// libzipper is distributed in the hope that it will be useful, +// but WITHOUT ANY WARRANTY; without even the implied warranty of +// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +// GNU General Public License for more details. +// +// You should have received a copy of the GNU General Public License +// along with libzipper. If not, see . + +#include "zipper.hh" +#include "Zip.hh" +#include "util.hh" + +#include + +#include + +using namespace zipper; + +class Compressor::CompressorImpl +{ +public: + virtual ~CompressorImpl() {} + + virtual void + addFile(const std::string& filename, const Reader& reader) = 0; +}; + +namespace +{ + class PlainCompressor : public Compressor::CompressorImpl + { + public: + PlainCompressor(const WriterPtr& writer) : m_writer(writer) {} + + virtual void + addFile(const std::string&, const Reader& reader) + { + enum Constants + { + ChunkSize = 64*1024 + }; + + uint8_t buffer[ChunkSize]; + zsize_t offset(0); + while (offset < reader.getSize()) + { + zsize_t bytes( + std::min(zsize_t(ChunkSize), reader.getSize() - offset)); + reader.readData(offset, bytes, &buffer[0]); + m_writer->writeData(offset, bytes, &buffer[0]); + offset += bytes; + } + } + private: + WriterPtr m_writer; + }; + + class ZipCompressor : public Compressor::CompressorImpl + { + public: + ZipCompressor(const WriterPtr& writer) : m_writer(writer) {} + + virtual ~ZipCompressor() + { + zipFinalise(m_records, m_writer); + } + + virtual void + addFile(const std::string& filename, const Reader& reader) + { + ZipFileRecord record; + zip(filename, reader, m_writer, record); + m_records.push_back(record); + } + private: + WriterPtr m_writer; + std::vector m_records; + }; +} + +Compressor::Compressor(ContainerFormat format, const WriterPtr& writer) +{ + switch (format) + { + case Container_none: + m_compressor = new PlainCompressor(writer); break; + + case Container_zip: + m_compressor = new ZipCompressor(writer); break; + + //case Container_none: + // m_compressor = new GzipCompressor(writer); break; + + default: + throw UnsupportedException("Unknown format"); + } +} + +Compressor::Compressor(ContainerFormat format, Writer& writer) : + m_compressor(NULL) +{ + WriterPtr ptr(&writer, dummy_delete()); + switch (format) + { + case Container_none: + m_compressor = new PlainCompressor(ptr); break; + + case Container_zip: + m_compressor = new ZipCompressor(ptr); break; + + //case Container_none: + // m_compressor = new GzipCompressor(ptr); break; + + default: + throw UnsupportedException("Unknown format"); + } +} + +Compressor::~Compressor() +{ + delete m_compressor; +} + +void +Compressor::addFile(const Reader& reader) +{ + m_compressor->addFile(reader.getSourceName(), reader); +} + + diff --git a/Container.cc b/Container.cc new file mode 100644 index 0000000..273f6d2 --- /dev/null +++ b/Container.cc @@ -0,0 +1,47 @@ +// Copyright (C) 2011 Michael McMaster +// +// This file is part of libzipper. +// +// libzipper is free software: you can redistribute it and/or modify +// it under the terms of the GNU General Public License as published by +// the Free Software Foundation, either version 3 of the License, or +// (at your option) any later version. +// +// libzipper is distributed in the hope that it will be useful, +// but WITHOUT ANY WARRANTY; without even the implied warranty of +// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +// GNU General Public License for more details. +// +// You should have received a copy of the GNU General Public License +// along with libzipper. If not, see . + +#include "zipper.hh" + +using namespace zipper; + +namespace +{ + struct Container info_none = + { Container_none, "application/octet-stream", 13 }; + struct Container info_zip = + { Container_zip, "application/zip", 0x1f }; + struct Container info_gzip = + { Container_gzip, "zpplication/x-gzip", 7 }; +} + +namespace zipper +{ + const Container& + getContainer(ContainerFormat format) + { + switch (format) + { + case Container_none: return info_none; + case Container_zip: return info_zip; + case Container_gzip: return info_gzip; + default: throw Exception("Unknown format type requested"); + } + + } +} + diff --git a/Decompressor.cc b/Decompressor.cc new file mode 100644 index 0000000..e51f9a6 --- /dev/null +++ b/Decompressor.cc @@ -0,0 +1,137 @@ +// Copyright (C) 2011 Michael McMaster +// +// This file is part of libzipper. +// +// libzipper is free software: you can redistribute it and/or modify +// it under the terms of the GNU General Public License as published by +// the Free Software Foundation, either version 3 of the License, or +// (at your option) any later version. +// +// libzipper is distributed in the hope that it will be useful, +// but WITHOUT ANY WARRANTY; without even the implied warranty of +// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +// GNU General Public License for more details. +// +// You should have received a copy of the GNU General Public License +// along with libzipper. If not, see . + +#include "zipper.hh" +#include "util.hh" + +#include "Unzip.hh" +#include "Ungzip.hh" + +using namespace zipper; + +namespace +{ + class PlainFile : public CompressedFile + { + public: + PlainFile(const ReaderPtr& reader) : + m_reader(reader) + {} + + virtual bool isDecompressSupported() const { return true; } + virtual const std::string& getPath() const + { + return m_reader->getSourceName(); + } + virtual zsize_t getCompressedSize() const + { + return m_reader->getSize(); + } + virtual zsize_t getUncompressedSize() const + { + return m_reader->getSize(); + } + + virtual void decompress(Writer& writer) + { + enum Constants + { + ChunkSize = 64*1024 + }; + zsize_t end(m_reader->getSize()); + + for (zsize_t pos(0); pos < end; pos += ChunkSize) + { + uint8_t buf[ChunkSize]; + size_t bytes( + std::min(zsize_t(ChunkSize), end - pos) + ); + m_reader->readData(pos, bytes, &buf[0]); + writer.writeData(pos, bytes, &buf[0]); + } + } + + private: + ReaderPtr m_reader; + }; +} + +class Decompressor::DecompressorImpl +{ +public: + DecompressorImpl(const ReaderPtr& reader) : + m_reader(reader), + m_format(Container_none) + { + if (isZip(reader)) + { + m_format = Container_zip; + m_entries = unzip(reader); + } + else if (isGzip(reader)) + { + m_format = Container_gzip; + m_entries = ungzip(reader); + } + else + { + m_format = Container_none; + m_entries.push_back( + CompressedFilePtr(new PlainFile(reader)) + ); + } + } + + ContainerFormat getContainerFormat() const { return m_format; } + + std::vector getEntries() const { return m_entries; } + +private: + ReaderPtr m_reader; + ContainerFormat m_format; + std::vector m_entries; +}; + +Decompressor::Decompressor(const ReaderPtr& reader) : + m_decompressor(new DecompressorImpl(reader)) +{ +} + +Decompressor::Decompressor(Reader& reader) : + m_decompressor( + new DecompressorImpl(ReaderPtr(&reader, dummy_delete())) + ) +{ +} + +Decompressor::~Decompressor() +{ + delete m_decompressor; +} + +ContainerFormat +Decompressor::getContainerFormat() const +{ + return m_decompressor->getContainerFormat(); +} + +std::vector +Decompressor::getEntries() const +{ + return m_decompressor->getEntries(); +} + diff --git a/Doxyfile.in b/Doxyfile.in new file mode 100644 index 0000000..6fc4093 --- /dev/null +++ b/Doxyfile.in @@ -0,0 +1,1661 @@ +# Doxyfile 1.7.1 + +# This file describes the settings to be used by the documentation system +# doxygen (www.doxygen.org) for a project +# +# All text after a hash (#) is considered a comment and will be ignored +# The format is: +# TAG = value [value, ...] +# For lists items can also be appended using: +# TAG += value [value, ...] +# Values that contain spaces should be placed between quotes (" ") + +#--------------------------------------------------------------------------- +# Project related configuration options +#--------------------------------------------------------------------------- + +# This tag specifies the encoding used for all characters in the config file +# that follow. The default is UTF-8 which is also the encoding used for all +# text before the first occurrence of this tag. Doxygen uses libiconv (or the +# iconv built into libc) for the transcoding. See +# http://www.gnu.org/software/libiconv for the list of possible encodings. + +DOXYFILE_ENCODING = UTF-8 + +# The PROJECT_NAME tag is a single word (or a sequence of words surrounded +# by quotes) that should identify the project. + +PROJECT_NAME = libzipper + +# The PROJECT_NUMBER tag can be used to enter a project or revision number. +# This could be handy for archiving the generated documentation or +# if some version control system is used. + +PROJECT_NUMBER = @libzipper_version@ + +# The OUTPUT_DIRECTORY tag is used to specify the (relative or absolute) +# base path where the generated documentation will be put. +# If a relative path is entered, it will be relative to the location +# where doxygen was started. If left blank the current directory will be used. + +OUTPUT_DIRECTORY = doc + +# If the CREATE_SUBDIRS tag is set to YES, then doxygen will create +# 4096 sub-directories (in 2 levels) under the output directory of each output +# format and will distribute the generated files over these directories. +# Enabling this option can be useful when feeding doxygen a huge amount of +# source files, where putting all generated files in the same directory would +# otherwise cause performance problems for the file system. + +CREATE_SUBDIRS = NO + +# The OUTPUT_LANGUAGE tag is used to specify the language in which all +# documentation generated by doxygen is written. Doxygen will use this +# information to generate all constant output in the proper language. +# The default language is English, other supported languages are: +# Afrikaans, Arabic, Brazilian, Catalan, Chinese, Chinese-Traditional, +# Croatian, Czech, Danish, Dutch, Esperanto, Farsi, Finnish, French, German, +# Greek, Hungarian, Italian, Japanese, Japanese-en (Japanese with English +# messages), Korean, Korean-en, Lithuanian, Norwegian, Macedonian, Persian, +# Polish, Portuguese, Romanian, Russian, Serbian, Serbian-Cyrilic, Slovak, +# Slovene, Spanish, Swedish, Ukrainian, and Vietnamese. + +OUTPUT_LANGUAGE = English + +# If the BRIEF_MEMBER_DESC tag is set to YES (the default) Doxygen will +# include brief member descriptions after the members that are listed in +# the file and class documentation (similar to JavaDoc). +# Set to NO to disable this. + +BRIEF_MEMBER_DESC = YES + +# If the REPEAT_BRIEF tag is set to YES (the default) Doxygen will prepend +# the brief description of a member or function before the detailed description. +# Note: if both HIDE_UNDOC_MEMBERS and BRIEF_MEMBER_DESC are set to NO, the +# brief descriptions will be completely suppressed. + +REPEAT_BRIEF = YES + +# This tag implements a quasi-intelligent brief description abbreviator +# that is used to form the text in various listings. Each string +# in this list, if found as the leading text of the brief description, will be +# stripped from the text and the result after processing the whole list, is +# used as the annotated text. Otherwise, the brief description is used as-is. +# If left blank, the following values are used ("$name" is automatically +# replaced with the name of the entity): "The $name class" "The $name widget" +# "The $name file" "is" "provides" "specifies" "contains" +# "represents" "a" "an" "the" + +ABBREVIATE_BRIEF = "The $name class" \ + "The $name widget" \ + "The $name file" \ + is \ + provides \ + specifies \ + contains \ + represents \ + a \ + an \ + the + +# If the ALWAYS_DETAILED_SEC and REPEAT_BRIEF tags are both set to YES then +# Doxygen will generate a detailed section even if there is only a brief +# description. + +ALWAYS_DETAILED_SEC = NO + +# If the INLINE_INHERITED_MEMB tag is set to YES, doxygen will show all +# inherited members of a class in the documentation of that class as if those +# members were ordinary class members. Constructors, destructors and assignment +# operators of the base classes will not be shown. + +INLINE_INHERITED_MEMB = NO + +# If the FULL_PATH_NAMES tag is set to YES then Doxygen will prepend the full +# path before files name in the file list and in the header files. If set +# to NO the shortest path that makes the file name unique will be used. + +FULL_PATH_NAMES = YES + +# If the FULL_PATH_NAMES tag is set to YES then the STRIP_FROM_PATH tag +# can be used to strip a user-defined part of the path. Stripping is +# only done if one of the specified strings matches the left-hand part of +# the path. The tag can be used to show relative paths in the file list. +# If left blank the directory from which doxygen is run is used as the +# path to strip. + +STRIP_FROM_PATH = + +# The STRIP_FROM_INC_PATH tag can be used to strip a user-defined part of +# the path mentioned in the documentation of a class, which tells +# the reader which header file to include in order to use a class. +# If left blank only the name of the header file containing the class +# definition is used. Otherwise one should specify the include paths that +# are normally passed to the compiler using the -I flag. + +STRIP_FROM_INC_PATH = + +# If the SHORT_NAMES tag is set to YES, doxygen will generate much shorter +# (but less readable) file names. This can be useful is your file systems +# doesn't support long names like on DOS, Mac, or CD-ROM. + +SHORT_NAMES = NO + +# If the JAVADOC_AUTOBRIEF tag is set to YES then Doxygen +# will interpret the first line (until the first dot) of a JavaDoc-style +# comment as the brief description. If set to NO, the JavaDoc +# comments will behave just like regular Qt-style comments +# (thus requiring an explicit @brief command for a brief description.) + +JAVADOC_AUTOBRIEF = NO + +# If the QT_AUTOBRIEF tag is set to YES then Doxygen will +# interpret the first line (until the first dot) of a Qt-style +# comment as the brief description. If set to NO, the comments +# will behave just like regular Qt-style comments (thus requiring +# an explicit \brief command for a brief description.) + +QT_AUTOBRIEF = NO + +# The MULTILINE_CPP_IS_BRIEF tag can be set to YES to make Doxygen +# treat a multi-line C++ special comment block (i.e. a block of //! or /// +# comments) as a brief description. This used to be the default behaviour. +# The new default is to treat a multi-line C++ comment block as a detailed +# description. Set this tag to YES if you prefer the old behaviour instead. + +MULTILINE_CPP_IS_BRIEF = NO + +# If the INHERIT_DOCS tag is set to YES (the default) then an undocumented +# member inherits the documentation from any documented member that it +# re-implements. + +INHERIT_DOCS = YES + +# If the SEPARATE_MEMBER_PAGES tag is set to YES, then doxygen will produce +# a new page for each member. If set to NO, the documentation of a member will +# be part of the file/class/namespace that contains it. + +SEPARATE_MEMBER_PAGES = NO + +# The TAB_SIZE tag can be used to set the number of spaces in a tab. +# Doxygen uses this value to replace tabs by spaces in code fragments. + +TAB_SIZE = 4 + +# This tag can be used to specify a number of aliases that acts +# as commands in the documentation. An alias has the form "name=value". +# For example adding "sideeffect=\par Side Effects:\n" will allow you to +# put the command \sideeffect (or @sideeffect) in the documentation, which +# will result in a user-defined paragraph with heading "Side Effects:". +# You can put \n's in the value part of an alias to insert newlines. + +ALIASES = + +# Set the OPTIMIZE_OUTPUT_FOR_C tag to YES if your project consists of C +# sources only. Doxygen will then generate output that is more tailored for C. +# For instance, some of the names that are used will be different. The list +# of all members will be omitted, etc. + +OPTIMIZE_OUTPUT_FOR_C = NO + +# Set the OPTIMIZE_OUTPUT_JAVA tag to YES if your project consists of Java +# sources only. Doxygen will then generate output that is more tailored for +# Java. For instance, namespaces will be presented as packages, qualified +# scopes will look different, etc. + +OPTIMIZE_OUTPUT_JAVA = NO + +# Set the OPTIMIZE_FOR_FORTRAN tag to YES if your project consists of Fortran +# sources only. Doxygen will then generate output that is more tailored for +# Fortran. + +OPTIMIZE_FOR_FORTRAN = NO + +# Set the OPTIMIZE_OUTPUT_VHDL tag to YES if your project consists of VHDL +# sources. Doxygen will then generate output that is tailored for +# VHDL. + +OPTIMIZE_OUTPUT_VHDL = NO + +# Doxygen selects the parser to use depending on the extension of the files it +# parses. With this tag you can assign which parser to use for a given extension. +# Doxygen has a built-in mapping, but you can override or extend it using this +# tag. The format is ext=language, where ext is a file extension, and language +# is one of the parsers supported by doxygen: IDL, Java, Javascript, CSharp, C, +# C++, D, PHP, Objective-C, Python, Fortran, VHDL, C, C++. For instance to make +# doxygen treat .inc files as Fortran files (default is PHP), and .f files as C +# (default is Fortran), use: inc=Fortran f=C. Note that for custom extensions +# you also need to set FILE_PATTERNS otherwise the files are not read by doxygen. + +EXTENSION_MAPPING = + +# If you use STL classes (i.e. std::string, std::vector, etc.) but do not want +# to include (a tag file for) the STL sources as input, then you should +# set this tag to YES in order to let doxygen match functions declarations and +# definitions whose arguments contain STL classes (e.g. func(std::string); v.s. +# func(std::string) {}). This also make the inheritance and collaboration +# diagrams that involve STL classes more complete and accurate. + +BUILTIN_STL_SUPPORT = NO + +# If you use Microsoft's C++/CLI language, you should set this option to YES to +# enable parsing support. + +CPP_CLI_SUPPORT = NO + +# Set the SIP_SUPPORT tag to YES if your project consists of sip sources only. +# Doxygen will parse them like normal C++ but will assume all classes use public +# instead of private inheritance when no explicit protection keyword is present. + +SIP_SUPPORT = NO + +# For Microsoft's IDL there are propget and propput attributes to indicate getter +# and setter methods for a property. Setting this option to YES (the default) +# will make doxygen to replace the get and set methods by a property in the +# documentation. This will only work if the methods are indeed getting or +# setting a simple type. If this is not the case, or you want to show the +# methods anyway, you should set this option to NO. + +IDL_PROPERTY_SUPPORT = YES + +# If member grouping is used in the documentation and the DISTRIBUTE_GROUP_DOC +# tag is set to YES, then doxygen will reuse the documentation of the first +# member in the group (if any) for the other members of the group. By default +# all members of a group must be documented explicitly. + +DISTRIBUTE_GROUP_DOC = NO + +# Set the SUBGROUPING tag to YES (the default) to allow class member groups of +# the same type (for instance a group of public functions) to be put as a +# subgroup of that type (e.g. under the Public Functions section). Set it to +# NO to prevent subgrouping. Alternatively, this can be done per class using +# the \nosubgrouping command. + +SUBGROUPING = YES + +# When TYPEDEF_HIDES_STRUCT is enabled, a typedef of a struct, union, or enum +# is documented as struct, union, or enum with the name of the typedef. So +# typedef struct TypeS {} TypeT, will appear in the documentation as a struct +# with name TypeT. When disabled the typedef will appear as a member of a file, +# namespace, or class. And the struct will be named TypeS. This can typically +# be useful for C code in case the coding convention dictates that all compound +# types are typedef'ed and only the typedef is referenced, never the tag name. + +TYPEDEF_HIDES_STRUCT = NO + +# The SYMBOL_CACHE_SIZE determines the size of the internal cache use to +# determine which symbols to keep in memory and which to flush to disk. +# When the cache is full, less often used symbols will be written to disk. +# For small to medium size projects (<1000 input files) the default value is +# probably good enough. For larger projects a too small cache size can cause +# doxygen to be busy swapping symbols to and from disk most of the time +# causing a significant performance penality. +# If the system has enough physical memory increasing the cache will improve the +# performance by keeping more symbols in memory. Note that the value works on +# a logarithmic scale so increasing the size by one will rougly double the +# memory usage. The cache size is given by this formula: +# 2^(16+SYMBOL_CACHE_SIZE). The valid range is 0..9, the default is 0, +# corresponding to a cache size of 2^16 = 65536 symbols + +SYMBOL_CACHE_SIZE = 0 + +#--------------------------------------------------------------------------- +# Build related configuration options +#--------------------------------------------------------------------------- + +# If the EXTRACT_ALL tag is set to YES doxygen will assume all entities in +# documentation are documented, even if no documentation was available. +# Private class members and static file members will be hidden unless +# the EXTRACT_PRIVATE and EXTRACT_STATIC tags are set to YES + +EXTRACT_ALL = NO + +# If the EXTRACT_PRIVATE tag is set to YES all private members of a class +# will be included in the documentation. + +EXTRACT_PRIVATE = NO + +# If the EXTRACT_STATIC tag is set to YES all static members of a file +# will be included in the documentation. + +EXTRACT_STATIC = NO + +# If the EXTRACT_LOCAL_CLASSES tag is set to YES classes (and structs) +# defined locally in source files will be included in the documentation. +# If set to NO only classes defined in header files are included. + +EXTRACT_LOCAL_CLASSES = YES + +# This flag is only useful for Objective-C code. When set to YES local +# methods, which are defined in the implementation section but not in +# the interface are included in the documentation. +# If set to NO (the default) only methods in the interface are included. + +EXTRACT_LOCAL_METHODS = NO + +# If this flag is set to YES, the members of anonymous namespaces will be +# extracted and appear in the documentation as a namespace called +# 'anonymous_namespace{file}', where file will be replaced with the base +# name of the file that contains the anonymous namespace. By default +# anonymous namespace are hidden. + +EXTRACT_ANON_NSPACES = NO + +# If the HIDE_UNDOC_MEMBERS tag is set to YES, Doxygen will hide all +# undocumented members of documented classes, files or namespaces. +# If set to NO (the default) these members will be included in the +# various overviews, but no documentation section is generated. +# This option has no effect if EXTRACT_ALL is enabled. + +HIDE_UNDOC_MEMBERS = NO + +# If the HIDE_UNDOC_CLASSES tag is set to YES, Doxygen will hide all +# undocumented classes that are normally visible in the class hierarchy. +# If set to NO (the default) these classes will be included in the various +# overviews. This option has no effect if EXTRACT_ALL is enabled. + +HIDE_UNDOC_CLASSES = NO + +# If the HIDE_FRIEND_COMPOUNDS tag is set to YES, Doxygen will hide all +# friend (class|struct|union) declarations. +# If set to NO (the default) these declarations will be included in the +# documentation. + +HIDE_FRIEND_COMPOUNDS = NO + +# If the HIDE_IN_BODY_DOCS tag is set to YES, Doxygen will hide any +# documentation blocks found inside the body of a function. +# If set to NO (the default) these blocks will be appended to the +# function's detailed documentation block. + +HIDE_IN_BODY_DOCS = NO + +# The INTERNAL_DOCS tag determines if documentation +# that is typed after a \internal command is included. If the tag is set +# to NO (the default) then the documentation will be excluded. +# Set it to YES to include the internal documentation. + +INTERNAL_DOCS = NO + +# If the CASE_SENSE_NAMES tag is set to NO then Doxygen will only generate +# file names in lower-case letters. If set to YES upper-case letters are also +# allowed. This is useful if you have classes or files whose names only differ +# in case and if your file system supports case sensitive file names. Windows +# and Mac users are advised to set this option to NO. + +CASE_SENSE_NAMES = NO + +# If the HIDE_SCOPE_NAMES tag is set to NO (the default) then Doxygen +# will show members with their full class and namespace scopes in the +# documentation. If set to YES the scope will be hidden. + +HIDE_SCOPE_NAMES = NO + +# If the SHOW_INCLUDE_FILES tag is set to YES (the default) then Doxygen +# will put a list of the files that are included by a file in the documentation +# of that file. + +SHOW_INCLUDE_FILES = YES + +# If the FORCE_LOCAL_INCLUDES tag is set to YES then Doxygen +# will list include files with double quotes in the documentation +# rather than with sharp brackets. + +FORCE_LOCAL_INCLUDES = NO + +# If the INLINE_INFO tag is set to YES (the default) then a tag [inline] +# is inserted in the documentation for inline members. + +INLINE_INFO = YES + +# If the SORT_MEMBER_DOCS tag is set to YES (the default) then doxygen +# will sort the (detailed) documentation of file and class members +# alphabetically by member name. If set to NO the members will appear in +# declaration order. + +SORT_MEMBER_DOCS = YES + +# If the SORT_BRIEF_DOCS tag is set to YES then doxygen will sort the +# brief documentation of file, namespace and class members alphabetically +# by member name. If set to NO (the default) the members will appear in +# declaration order. + +SORT_BRIEF_DOCS = NO + +# If the SORT_MEMBERS_CTORS_1ST tag is set to YES then doxygen +# will sort the (brief and detailed) documentation of class members so that +# constructors and destructors are listed first. If set to NO (the default) +# the constructors will appear in the respective orders defined by +# SORT_MEMBER_DOCS and SORT_BRIEF_DOCS. +# This tag will be ignored for brief docs if SORT_BRIEF_DOCS is set to NO +# and ignored for detailed docs if SORT_MEMBER_DOCS is set to NO. + +SORT_MEMBERS_CTORS_1ST = NO + +# If the SORT_GROUP_NAMES tag is set to YES then doxygen will sort the +# hierarchy of group names into alphabetical order. If set to NO (the default) +# the group names will appear in their defined order. + +SORT_GROUP_NAMES = NO + +# If the SORT_BY_SCOPE_NAME tag is set to YES, the class list will be +# sorted by fully-qualified names, including namespaces. If set to +# NO (the default), the class list will be sorted only by class name, +# not including the namespace part. +# Note: This option is not very useful if HIDE_SCOPE_NAMES is set to YES. +# Note: This option applies only to the class list, not to the +# alphabetical list. + +SORT_BY_SCOPE_NAME = NO + +# The GENERATE_TODOLIST tag can be used to enable (YES) or +# disable (NO) the todo list. This list is created by putting \todo +# commands in the documentation. + +GENERATE_TODOLIST = YES + +# The GENERATE_TESTLIST tag can be used to enable (YES) or +# disable (NO) the test list. This list is created by putting \test +# commands in the documentation. + +GENERATE_TESTLIST = YES + +# The GENERATE_BUGLIST tag can be used to enable (YES) or +# disable (NO) the bug list. This list is created by putting \bug +# commands in the documentation. + +GENERATE_BUGLIST = YES + +# The GENERATE_DEPRECATEDLIST tag can be used to enable (YES) or +# disable (NO) the deprecated list. This list is created by putting +# \deprecated commands in the documentation. + +GENERATE_DEPRECATEDLIST= YES + +# The ENABLED_SECTIONS tag can be used to enable conditional +# documentation sections, marked by \if sectionname ... \endif. + +ENABLED_SECTIONS = + +# The MAX_INITIALIZER_LINES tag determines the maximum number of lines +# the initial value of a variable or define consists of for it to appear in +# the documentation. If the initializer consists of more lines than specified +# here it will be hidden. Use a value of 0 to hide initializers completely. +# The appearance of the initializer of individual variables and defines in the +# documentation can be controlled using \showinitializer or \hideinitializer +# command in the documentation regardless of this setting. + +MAX_INITIALIZER_LINES = 30 + +# Set the SHOW_USED_FILES tag to NO to disable the list of files generated +# at the bottom of the documentation of classes and structs. If set to YES the +# list will mention the files that were used to generate the documentation. + +SHOW_USED_FILES = YES + +# If the sources in your project are distributed over multiple directories +# then setting the SHOW_DIRECTORIES tag to YES will show the directory hierarchy +# in the documentation. The default is NO. + +SHOW_DIRECTORIES = NO + +# Set the SHOW_FILES tag to NO to disable the generation of the Files page. +# This will remove the Files entry from the Quick Index and from the +# Folder Tree View (if specified). The default is YES. + +SHOW_FILES = YES + +# Set the SHOW_NAMESPACES tag to NO to disable the generation of the +# Namespaces page. This will remove the Namespaces entry from the Quick Index +# and from the Folder Tree View (if specified). The default is YES. + +SHOW_NAMESPACES = YES + +# The FILE_VERSION_FILTER tag can be used to specify a program or script that +# doxygen should invoke to get the current version for each file (typically from +# the version control system). Doxygen will invoke the program by executing (via +# popen()) the command , where is the value of +# the FILE_VERSION_FILTER tag, and is the name of an input file +# provided by doxygen. Whatever the program writes to standard output +# is used as the file version. See the manual for examples. + +FILE_VERSION_FILTER = + +# The LAYOUT_FILE tag can be used to specify a layout file which will be parsed +# by doxygen. The layout file controls the global structure of the generated +# output files in an output format independent way. The create the layout file +# that represents doxygen's defaults, run doxygen with the -l option. +# You can optionally specify a file name after the option, if omitted +# DoxygenLayout.xml will be used as the name of the layout file. + +LAYOUT_FILE = + +#--------------------------------------------------------------------------- +# configuration options related to warning and progress messages +#--------------------------------------------------------------------------- + +# The QUIET tag can be used to turn on/off the messages that are generated +# by doxygen. Possible values are YES and NO. If left blank NO is used. + +QUIET = NO + +# The WARNINGS tag can be used to turn on/off the warning messages that are +# generated by doxygen. Possible values are YES and NO. If left blank +# NO is used. + +WARNINGS = YES + +# If WARN_IF_UNDOCUMENTED is set to YES, then doxygen will generate warnings +# for undocumented members. If EXTRACT_ALL is set to YES then this flag will +# automatically be disabled. + +WARN_IF_UNDOCUMENTED = YES + +# If WARN_IF_DOC_ERROR is set to YES, doxygen will generate warnings for +# potential errors in the documentation, such as not documenting some +# parameters in a documented function, or documenting parameters that +# don't exist or using markup commands wrongly. + +WARN_IF_DOC_ERROR = YES + +# This WARN_NO_PARAMDOC option can be abled to get warnings for +# functions that are documented, but have no documentation for their parameters +# or return value. If set to NO (the default) doxygen will only warn about +# wrong or incomplete parameter documentation, but not about the absence of +# documentation. + +WARN_NO_PARAMDOC = NO + +# The WARN_FORMAT tag determines the format of the warning messages that +# doxygen can produce. The string should contain the $file, $line, and $text +# tags, which will be replaced by the file and line number from which the +# warning originated and the warning text. Optionally the format may contain +# $version, which will be replaced by the version of the file (if it could +# be obtained via FILE_VERSION_FILTER) + +WARN_FORMAT = "$file:$line: $text" + +# The WARN_LOGFILE tag can be used to specify a file to which warning +# and error messages should be written. If left blank the output is written +# to stderr. + +WARN_LOGFILE = + +#--------------------------------------------------------------------------- +# configuration options related to the input files +#--------------------------------------------------------------------------- + +# The INPUT tag can be used to specify the files and/or directories that contain +# documented source files. You may enter file names like "myfile.cpp" or +# directories like "/usr/src/myproject". Separate the files or directories +# with spaces. + +INPUT = @top_srcdir@ + +# This tag can be used to specify the character encoding of the source files +# that doxygen parses. Internally doxygen uses the UTF-8 encoding, which is +# also the default input encoding. Doxygen uses libiconv (or the iconv built +# into libc) for the transcoding. See http://www.gnu.org/software/libiconv for +# the list of possible encodings. + +INPUT_ENCODING = UTF-8 + +# If the value of the INPUT tag contains directories, you can use the +# FILE_PATTERNS tag to specify one or more wildcard pattern (like *.cpp +# and *.h) to filter out the source-files in the directories. If left +# blank the following patterns are tested: +# *.c *.cc *.cxx *.cpp *.c++ *.java *.ii *.ixx *.ipp *.i++ *.inl *.h *.hh *.hxx +# *.hpp *.h++ *.idl *.odl *.cs *.php *.php3 *.inc *.m *.mm *.py *.f90 + +FILE_PATTERNS = *.c \ + *.cc \ + *.cxx \ + *.cpp \ + *.c++ \ + *.d \ + *.java \ + *.ii \ + *.ixx \ + *.ipp \ + *.i++ \ + *.inl \ + *.h \ + *.hh \ + *.hxx \ + *.hpp \ + *.h++ \ + *.idl \ + *.odl \ + *.cs \ + *.php \ + *.php3 \ + *.inc \ + *.m \ + *.mm \ + *.dox \ + *.py \ + *.f90 \ + *.f \ + *.vhd \ + *.vhdl + +# The RECURSIVE tag can be used to turn specify whether or not subdirectories +# should be searched for input files as well. Possible values are YES and NO. +# If left blank NO is used. + +RECURSIVE = NO + +# The EXCLUDE tag can be used to specify files and/or directories that should +# excluded from the INPUT source files. This way you can easily exclude a +# subdirectory from a directory tree whose root is specified with the INPUT tag. + +EXCLUDE = + +# The EXCLUDE_SYMLINKS tag can be used select whether or not files or +# directories that are symbolic links (a Unix filesystem feature) are excluded +# from the input. + +EXCLUDE_SYMLINKS = NO + +# If the value of the INPUT tag contains directories, you can use the +# EXCLUDE_PATTERNS tag to specify one or more wildcard patterns to exclude +# certain files from those directories. Note that the wildcards are matched +# against the file with absolute path, so to exclude all test directories +# for example use the pattern */test/* + +EXCLUDE_PATTERNS = + +# The EXCLUDE_SYMBOLS tag can be used to specify one or more symbol names +# (namespaces, classes, functions, etc.) that should be excluded from the +# output. The symbol name can be a fully qualified name, a word, or if the +# wildcard * is used, a substring. Examples: ANamespace, AClass, +# AClass::ANamespace, ANamespace::*Test + +EXCLUDE_SYMBOLS = + +# The EXAMPLE_PATH tag can be used to specify one or more files or +# directories that contain example code fragments that are included (see +# the \include command). + +EXAMPLE_PATH = + +# If the value of the EXAMPLE_PATH tag contains directories, you can use the +# EXAMPLE_PATTERNS tag to specify one or more wildcard pattern (like *.cpp +# and *.h) to filter out the source-files in the directories. If left +# blank all files are included. + +EXAMPLE_PATTERNS = * + +# If the EXAMPLE_RECURSIVE tag is set to YES then subdirectories will be +# searched for input files to be used with the \include or \dontinclude +# commands irrespective of the value of the RECURSIVE tag. +# Possible values are YES and NO. If left blank NO is used. + +EXAMPLE_RECURSIVE = NO + +# The IMAGE_PATH tag can be used to specify one or more files or +# directories that contain image that are included in the documentation (see +# the \image command). + +IMAGE_PATH = + +# The INPUT_FILTER tag can be used to specify a program that doxygen should +# invoke to filter for each input file. Doxygen will invoke the filter program +# by executing (via popen()) the command , where +# is the value of the INPUT_FILTER tag, and is the name of an +# input file. Doxygen will then use the output that the filter program writes +# to standard output. If FILTER_PATTERNS is specified, this tag will be +# ignored. + +INPUT_FILTER = + +# The FILTER_PATTERNS tag can be used to specify filters on a per file pattern +# basis. Doxygen will compare the file name with each pattern and apply the +# filter if there is a match. The filters are a list of the form: +# pattern=filter (like *.cpp=my_cpp_filter). See INPUT_FILTER for further +# info on how filters are used. If FILTER_PATTERNS is empty, INPUT_FILTER +# is applied to all files. + +FILTER_PATTERNS = + +# If the FILTER_SOURCE_FILES tag is set to YES, the input filter (if set using +# INPUT_FILTER) will be used to filter the input files when producing source +# files to browse (i.e. when SOURCE_BROWSER is set to YES). + +FILTER_SOURCE_FILES = NO + +#--------------------------------------------------------------------------- +# configuration options related to source browsing +#--------------------------------------------------------------------------- + +# If the SOURCE_BROWSER tag is set to YES then a list of source files will +# be generated. Documented entities will be cross-referenced with these sources. +# Note: To get rid of all source code in the generated output, make sure also +# VERBATIM_HEADERS is set to NO. + +SOURCE_BROWSER = YES + +# Setting the INLINE_SOURCES tag to YES will include the body +# of functions and classes directly in the documentation. + +INLINE_SOURCES = NO + +# Setting the STRIP_CODE_COMMENTS tag to YES (the default) will instruct +# doxygen to hide any special comment blocks from generated source code +# fragments. Normal C and C++ comments will always remain visible. + +STRIP_CODE_COMMENTS = YES + +# If the REFERENCED_BY_RELATION tag is set to YES +# then for each documented function all documented +# functions referencing it will be listed. + +REFERENCED_BY_RELATION = NO + +# If the REFERENCES_RELATION tag is set to YES +# then for each documented function all documented entities +# called/used by that function will be listed. + +REFERENCES_RELATION = NO + +# If the REFERENCES_LINK_SOURCE tag is set to YES (the default) +# and SOURCE_BROWSER tag is set to YES, then the hyperlinks from +# functions in REFERENCES_RELATION and REFERENCED_BY_RELATION lists will +# link to the source code. Otherwise they will link to the documentation. + +REFERENCES_LINK_SOURCE = YES + +# If the USE_HTAGS tag is set to YES then the references to source code +# will point to the HTML generated by the htags(1) tool instead of doxygen +# built-in source browser. The htags tool is part of GNU's global source +# tagging system (see http://www.gnu.org/software/global/global.html). You +# will need version 4.8.6 or higher. + +USE_HTAGS = NO + +# If the VERBATIM_HEADERS tag is set to YES (the default) then Doxygen +# will generate a verbatim copy of the header file for each class for +# which an include is specified. Set to NO to disable this. + +VERBATIM_HEADERS = YES + +#--------------------------------------------------------------------------- +# configuration options related to the alphabetical class index +#--------------------------------------------------------------------------- + +# If the ALPHABETICAL_INDEX tag is set to YES, an alphabetical index +# of all compounds will be generated. Enable this if the project +# contains a lot of classes, structs, unions or interfaces. + +ALPHABETICAL_INDEX = YES + +# If the alphabetical index is enabled (see ALPHABETICAL_INDEX) then +# the COLS_IN_ALPHA_INDEX tag can be used to specify the number of columns +# in which this list will be split (can be a number in the range [1..20]) + +COLS_IN_ALPHA_INDEX = 5 + +# In case all classes in a project start with a common prefix, all +# classes will be put under the same header in the alphabetical index. +# The IGNORE_PREFIX tag can be used to specify one or more prefixes that +# should be ignored while generating the index headers. + +IGNORE_PREFIX = + +#--------------------------------------------------------------------------- +# configuration options related to the HTML output +#--------------------------------------------------------------------------- + +# If the GENERATE_HTML tag is set to YES (the default) Doxygen will +# generate HTML output. + +GENERATE_HTML = YES + +# The HTML_OUTPUT tag is used to specify where the HTML docs will be put. +# If a relative path is entered the value of OUTPUT_DIRECTORY will be +# put in front of it. If left blank `html' will be used as the default path. + +HTML_OUTPUT = html + +# The HTML_FILE_EXTENSION tag can be used to specify the file extension for +# each generated HTML page (for example: .htm,.php,.asp). If it is left blank +# doxygen will generate files with .html extension. + +HTML_FILE_EXTENSION = .html + +# The HTML_HEADER tag can be used to specify a personal HTML header for +# each generated HTML page. If it is left blank doxygen will generate a +# standard header. + +HTML_HEADER = + +# The HTML_FOOTER tag can be used to specify a personal HTML footer for +# each generated HTML page. If it is left blank doxygen will generate a +# standard footer. + +HTML_FOOTER = + +# The HTML_STYLESHEET tag can be used to specify a user-defined cascading +# style sheet that is used by each HTML page. It can be used to +# fine-tune the look of the HTML output. If the tag is left blank doxygen +# will generate a default style sheet. Note that doxygen will try to copy +# the style sheet file to the HTML output directory, so don't put your own +# stylesheet in the HTML output directory as well, or it will be erased! + +HTML_STYLESHEET = + +# The HTML_COLORSTYLE_HUE tag controls the color of the HTML output. +# Doxygen will adjust the colors in the stylesheet and background images +# according to this color. Hue is specified as an angle on a colorwheel, +# see http://en.wikipedia.org/wiki/Hue for more information. +# For instance the value 0 represents red, 60 is yellow, 120 is green, +# 180 is cyan, 240 is blue, 300 purple, and 360 is red again. +# The allowed range is 0 to 359. + +HTML_COLORSTYLE_HUE = 220 + +# The HTML_COLORSTYLE_SAT tag controls the purity (or saturation) of +# the colors in the HTML output. For a value of 0 the output will use +# grayscales only. A value of 255 will produce the most vivid colors. + +HTML_COLORSTYLE_SAT = 100 + +# The HTML_COLORSTYLE_GAMMA tag controls the gamma correction applied to +# the luminance component of the colors in the HTML output. Values below +# 100 gradually make the output lighter, whereas values above 100 make +# the output darker. The value divided by 100 is the actual gamma applied, +# so 80 represents a gamma of 0.8, The value 220 represents a gamma of 2.2, +# and 100 does not change the gamma. + +HTML_COLORSTYLE_GAMMA = 80 + +# If the HTML_TIMESTAMP tag is set to YES then the footer of each generated HTML +# page will contain the date and time when the page was generated. Setting +# this to NO can help when comparing the output of multiple runs. + +HTML_TIMESTAMP = YES + +# If the HTML_ALIGN_MEMBERS tag is set to YES, the members of classes, +# files or namespaces will be aligned in HTML using tables. If set to +# NO a bullet list will be used. + +HTML_ALIGN_MEMBERS = YES + +# If the HTML_DYNAMIC_SECTIONS tag is set to YES then the generated HTML +# documentation will contain sections that can be hidden and shown after the +# page has loaded. For this to work a browser that supports +# JavaScript and DHTML is required (for instance Mozilla 1.0+, Firefox +# Netscape 6.0+, Internet explorer 5.0+, Konqueror, or Safari). + +HTML_DYNAMIC_SECTIONS = NO + +# If the GENERATE_DOCSET tag is set to YES, additional index files +# will be generated that can be used as input for Apple's Xcode 3 +# integrated development environment, introduced with OSX 10.5 (Leopard). +# To create a documentation set, doxygen will generate a Makefile in the +# HTML output directory. Running make will produce the docset in that +# directory and running "make install" will install the docset in +# ~/Library/Developer/Shared/Documentation/DocSets so that Xcode will find +# it at startup. +# See http://developer.apple.com/tools/creatingdocsetswithdoxygen.html +# for more information. + +GENERATE_DOCSET = NO + +# When GENERATE_DOCSET tag is set to YES, this tag determines the name of the +# feed. A documentation feed provides an umbrella under which multiple +# documentation sets from a single provider (such as a company or product suite) +# can be grouped. + +DOCSET_FEEDNAME = "Doxygen generated docs" + +# When GENERATE_DOCSET tag is set to YES, this tag specifies a string that +# should uniquely identify the documentation set bundle. This should be a +# reverse domain-name style string, e.g. com.mycompany.MyDocSet. Doxygen +# will append .docset to the name. + +DOCSET_BUNDLE_ID = org.doxygen.Project + +# When GENERATE_PUBLISHER_ID tag specifies a string that should uniquely identify +# the documentation publisher. This should be a reverse domain-name style +# string, e.g. com.mycompany.MyDocSet.documentation. + +DOCSET_PUBLISHER_ID = org.doxygen.Publisher + +# The GENERATE_PUBLISHER_NAME tag identifies the documentation publisher. + +DOCSET_PUBLISHER_NAME = Publisher + +# If the GENERATE_HTMLHELP tag is set to YES, additional index files +# will be generated that can be used as input for tools like the +# Microsoft HTML help workshop to generate a compiled HTML help file (.chm) +# of the generated HTML documentation. + +GENERATE_HTMLHELP = NO + +# If the GENERATE_HTMLHELP tag is set to YES, the CHM_FILE tag can +# be used to specify the file name of the resulting .chm file. You +# can add a path in front of the file if the result should not be +# written to the html output directory. + +CHM_FILE = + +# If the GENERATE_HTMLHELP tag is set to YES, the HHC_LOCATION tag can +# be used to specify the location (absolute path including file name) of +# the HTML help compiler (hhc.exe). If non-empty doxygen will try to run +# the HTML help compiler on the generated index.hhp. + +HHC_LOCATION = + +# If the GENERATE_HTMLHELP tag is set to YES, the GENERATE_CHI flag +# controls if a separate .chi index file is generated (YES) or that +# it should be included in the master .chm file (NO). + +GENERATE_CHI = NO + +# If the GENERATE_HTMLHELP tag is set to YES, the CHM_INDEX_ENCODING +# is used to encode HtmlHelp index (hhk), content (hhc) and project file +# content. + +CHM_INDEX_ENCODING = + +# If the GENERATE_HTMLHELP tag is set to YES, the BINARY_TOC flag +# controls whether a binary table of contents is generated (YES) or a +# normal table of contents (NO) in the .chm file. + +BINARY_TOC = NO + +# The TOC_EXPAND flag can be set to YES to add extra items for group members +# to the contents of the HTML help documentation and to the tree view. + +TOC_EXPAND = NO + +# If the GENERATE_QHP tag is set to YES and both QHP_NAMESPACE and +# QHP_VIRTUAL_FOLDER are set, an additional index file will be generated +# that can be used as input for Qt's qhelpgenerator to generate a +# Qt Compressed Help (.qch) of the generated HTML documentation. + +GENERATE_QHP = NO + +# If the QHG_LOCATION tag is specified, the QCH_FILE tag can +# be used to specify the file name of the resulting .qch file. +# The path specified is relative to the HTML output folder. + +QCH_FILE = + +# The QHP_NAMESPACE tag specifies the namespace to use when generating +# Qt Help Project output. For more information please see +# http://doc.trolltech.com/qthelpproject.html#namespace + +QHP_NAMESPACE = org.doxygen.Project + +# The QHP_VIRTUAL_FOLDER tag specifies the namespace to use when generating +# Qt Help Project output. For more information please see +# http://doc.trolltech.com/qthelpproject.html#virtual-folders + +QHP_VIRTUAL_FOLDER = doc + +# If QHP_CUST_FILTER_NAME is set, it specifies the name of a custom filter to +# add. For more information please see +# http://doc.trolltech.com/qthelpproject.html#custom-filters + +QHP_CUST_FILTER_NAME = + +# The QHP_CUST_FILT_ATTRS tag specifies the list of the attributes of the +# custom filter to add. For more information please see +# +# Qt Help Project / Custom Filters. + +QHP_CUST_FILTER_ATTRS = + +# The QHP_SECT_FILTER_ATTRS tag specifies the list of the attributes this +# project's +# filter section matches. +# +# Qt Help Project / Filter Attributes. + +QHP_SECT_FILTER_ATTRS = + +# If the GENERATE_QHP tag is set to YES, the QHG_LOCATION tag can +# be used to specify the location of Qt's qhelpgenerator. +# If non-empty doxygen will try to run qhelpgenerator on the generated +# .qhp file. + +QHG_LOCATION = + +# If the GENERATE_ECLIPSEHELP tag is set to YES, additional index files +# will be generated, which together with the HTML files, form an Eclipse help +# plugin. To install this plugin and make it available under the help contents +# menu in Eclipse, the contents of the directory containing the HTML and XML +# files needs to be copied into the plugins directory of eclipse. The name of +# the directory within the plugins directory should be the same as +# the ECLIPSE_DOC_ID value. After copying Eclipse needs to be restarted before +# the help appears. + +GENERATE_ECLIPSEHELP = NO + +# A unique identifier for the eclipse help plugin. When installing the plugin +# the directory name containing the HTML and XML files should also have +# this name. + +ECLIPSE_DOC_ID = org.doxygen.Project + +# The DISABLE_INDEX tag can be used to turn on/off the condensed index at +# top of each HTML page. The value NO (the default) enables the index and +# the value YES disables it. + +DISABLE_INDEX = NO + +# This tag can be used to set the number of enum values (range [1..20]) +# that doxygen will group on one line in the generated HTML documentation. + +ENUM_VALUES_PER_LINE = 4 + +# The GENERATE_TREEVIEW tag is used to specify whether a tree-like index +# structure should be generated to display hierarchical information. +# If the tag value is set to YES, a side panel will be generated +# containing a tree-like index structure (just like the one that +# is generated for HTML Help). For this to work a browser that supports +# JavaScript, DHTML, CSS and frames is required (i.e. any modern browser). +# Windows users are probably better off using the HTML help feature. + +GENERATE_TREEVIEW = NO + +# By enabling USE_INLINE_TREES, doxygen will generate the Groups, Directories, +# and Class Hierarchy pages using a tree view instead of an ordered list. + +USE_INLINE_TREES = NO + +# If the treeview is enabled (see GENERATE_TREEVIEW) then this tag can be +# used to set the initial width (in pixels) of the frame in which the tree +# is shown. + +TREEVIEW_WIDTH = 250 + +# When the EXT_LINKS_IN_WINDOW option is set to YES doxygen will open +# links to external symbols imported via tag files in a separate window. + +EXT_LINKS_IN_WINDOW = NO + +# Use this tag to change the font size of Latex formulas included +# as images in the HTML documentation. The default is 10. Note that +# when you change the font size after a successful doxygen run you need +# to manually remove any form_*.png images from the HTML output directory +# to force them to be regenerated. + +FORMULA_FONTSIZE = 10 + +# Use the FORMULA_TRANPARENT tag to determine whether or not the images +# generated for formulas are transparent PNGs. Transparent PNGs are +# not supported properly for IE 6.0, but are supported on all modern browsers. +# Note that when changing this option you need to delete any form_*.png files +# in the HTML output before the changes have effect. + +FORMULA_TRANSPARENT = YES + +# When the SEARCHENGINE tag is enabled doxygen will generate a search box +# for the HTML output. The underlying search engine uses javascript +# and DHTML and should work on any modern browser. Note that when using +# HTML help (GENERATE_HTMLHELP), Qt help (GENERATE_QHP), or docsets +# (GENERATE_DOCSET) there is already a search function so this one should +# typically be disabled. For large projects the javascript based search engine +# can be slow, then enabling SERVER_BASED_SEARCH may provide a better solution. + +SEARCHENGINE = NO + +# When the SERVER_BASED_SEARCH tag is enabled the search engine will be +# implemented using a PHP enabled web server instead of at the web client +# using Javascript. Doxygen will generate the search PHP script and index +# file to put on the web server. The advantage of the server +# based approach is that it scales better to large projects and allows +# full text search. The disadvances is that it is more difficult to setup +# and does not have live searching capabilities. + +SERVER_BASED_SEARCH = NO + +#--------------------------------------------------------------------------- +# configuration options related to the LaTeX output +#--------------------------------------------------------------------------- + +# If the GENERATE_LATEX tag is set to YES (the default) Doxygen will +# generate Latex output. + +GENERATE_LATEX = NO + +# The LATEX_OUTPUT tag is used to specify where the LaTeX docs will be put. +# If a relative path is entered the value of OUTPUT_DIRECTORY will be +# put in front of it. If left blank `latex' will be used as the default path. + +LATEX_OUTPUT = latex + +# The LATEX_CMD_NAME tag can be used to specify the LaTeX command name to be +# invoked. If left blank `latex' will be used as the default command name. +# Note that when enabling USE_PDFLATEX this option is only used for +# generating bitmaps for formulas in the HTML output, but not in the +# Makefile that is written to the output directory. + +LATEX_CMD_NAME = latex + +# The MAKEINDEX_CMD_NAME tag can be used to specify the command name to +# generate index for LaTeX. If left blank `makeindex' will be used as the +# default command name. + +MAKEINDEX_CMD_NAME = makeindex + +# If the COMPACT_LATEX tag is set to YES Doxygen generates more compact +# LaTeX documents. This may be useful for small projects and may help to +# save some trees in general. + +COMPACT_LATEX = NO + +# The PAPER_TYPE tag can be used to set the paper type that is used +# by the printer. Possible values are: a4, a4wide, letter, legal and +# executive. If left blank a4wide will be used. + +PAPER_TYPE = a4wide + +# The EXTRA_PACKAGES tag can be to specify one or more names of LaTeX +# packages that should be included in the LaTeX output. + +EXTRA_PACKAGES = + +# The LATEX_HEADER tag can be used to specify a personal LaTeX header for +# the generated latex document. The header should contain everything until +# the first chapter. If it is left blank doxygen will generate a +# standard header. Notice: only use this tag if you know what you are doing! + +LATEX_HEADER = + +# If the PDF_HYPERLINKS tag is set to YES, the LaTeX that is generated +# is prepared for conversion to pdf (using ps2pdf). The pdf file will +# contain links (just like the HTML output) instead of page references +# This makes the output suitable for online browsing using a pdf viewer. + +PDF_HYPERLINKS = YES + +# If the USE_PDFLATEX tag is set to YES, pdflatex will be used instead of +# plain latex in the generated Makefile. Set this option to YES to get a +# higher quality PDF documentation. + +USE_PDFLATEX = YES + +# If the LATEX_BATCHMODE tag is set to YES, doxygen will add the \\batchmode. +# command to the generated LaTeX files. This will instruct LaTeX to keep +# running if errors occur, instead of asking the user for help. +# This option is also used when generating formulas in HTML. + +LATEX_BATCHMODE = NO + +# If LATEX_HIDE_INDICES is set to YES then doxygen will not +# include the index chapters (such as File Index, Compound Index, etc.) +# in the output. + +LATEX_HIDE_INDICES = NO + +# If LATEX_SOURCE_CODE is set to YES then doxygen will include +# source code with syntax highlighting in the LaTeX output. +# Note that which sources are shown also depends on other settings +# such as SOURCE_BROWSER. + +LATEX_SOURCE_CODE = NO + +#--------------------------------------------------------------------------- +# configuration options related to the RTF output +#--------------------------------------------------------------------------- + +# If the GENERATE_RTF tag is set to YES Doxygen will generate RTF output +# The RTF output is optimized for Word 97 and may not look very pretty with +# other RTF readers or editors. + +GENERATE_RTF = NO + +# The RTF_OUTPUT tag is used to specify where the RTF docs will be put. +# If a relative path is entered the value of OUTPUT_DIRECTORY will be +# put in front of it. If left blank `rtf' will be used as the default path. + +RTF_OUTPUT = rtf + +# If the COMPACT_RTF tag is set to YES Doxygen generates more compact +# RTF documents. This may be useful for small projects and may help to +# save some trees in general. + +COMPACT_RTF = NO + +# If the RTF_HYPERLINKS tag is set to YES, the RTF that is generated +# will contain hyperlink fields. The RTF file will +# contain links (just like the HTML output) instead of page references. +# This makes the output suitable for online browsing using WORD or other +# programs which support those fields. +# Note: wordpad (write) and others do not support links. + +RTF_HYPERLINKS = NO + +# Load stylesheet definitions from file. Syntax is similar to doxygen's +# config file, i.e. a series of assignments. You only have to provide +# replacements, missing definitions are set to their default value. + +RTF_STYLESHEET_FILE = + +# Set optional variables used in the generation of an rtf document. +# Syntax is similar to doxygen's config file. + +RTF_EXTENSIONS_FILE = + +#--------------------------------------------------------------------------- +# configuration options related to the man page output +#--------------------------------------------------------------------------- + +# If the GENERATE_MAN tag is set to YES (the default) Doxygen will +# generate man pages + +GENERATE_MAN = NO + +# The MAN_OUTPUT tag is used to specify where the man pages will be put. +# If a relative path is entered the value of OUTPUT_DIRECTORY will be +# put in front of it. If left blank `man' will be used as the default path. + +MAN_OUTPUT = man + +# The MAN_EXTENSION tag determines the extension that is added to +# the generated man pages (default is the subroutine's section .3) + +MAN_EXTENSION = .3 + +# If the MAN_LINKS tag is set to YES and Doxygen generates man output, +# then it will generate one additional man file for each entity +# documented in the real man page(s). These additional files +# only source the real man page, but without them the man command +# would be unable to find the correct page. The default is NO. + +MAN_LINKS = NO + +#--------------------------------------------------------------------------- +# configuration options related to the XML output +#--------------------------------------------------------------------------- + +# If the GENERATE_XML tag is set to YES Doxygen will +# generate an XML file that captures the structure of +# the code including all documentation. + +GENERATE_XML = NO + +# The XML_OUTPUT tag is used to specify where the XML pages will be put. +# If a relative path is entered the value of OUTPUT_DIRECTORY will be +# put in front of it. If left blank `xml' will be used as the default path. + +XML_OUTPUT = xml + +# The XML_SCHEMA tag can be used to specify an XML schema, +# which can be used by a validating XML parser to check the +# syntax of the XML files. + +XML_SCHEMA = + +# The XML_DTD tag can be used to specify an XML DTD, +# which can be used by a validating XML parser to check the +# syntax of the XML files. + +XML_DTD = + +# If the XML_PROGRAMLISTING tag is set to YES Doxygen will +# dump the program listings (including syntax highlighting +# and cross-referencing information) to the XML output. Note that +# enabling this will significantly increase the size of the XML output. + +XML_PROGRAMLISTING = YES + +#--------------------------------------------------------------------------- +# configuration options for the AutoGen Definitions output +#--------------------------------------------------------------------------- + +# If the GENERATE_AUTOGEN_DEF tag is set to YES Doxygen will +# generate an AutoGen Definitions (see autogen.sf.net) file +# that captures the structure of the code including all +# documentation. Note that this feature is still experimental +# and incomplete at the moment. + +GENERATE_AUTOGEN_DEF = NO + +#--------------------------------------------------------------------------- +# configuration options related to the Perl module output +#--------------------------------------------------------------------------- + +# If the GENERATE_PERLMOD tag is set to YES Doxygen will +# generate a Perl module file that captures the structure of +# the code including all documentation. Note that this +# feature is still experimental and incomplete at the +# moment. + +GENERATE_PERLMOD = NO + +# If the PERLMOD_LATEX tag is set to YES Doxygen will generate +# the necessary Makefile rules, Perl scripts and LaTeX code to be able +# to generate PDF and DVI output from the Perl module output. + +PERLMOD_LATEX = NO + +# If the PERLMOD_PRETTY tag is set to YES the Perl module output will be +# nicely formatted so it can be parsed by a human reader. This is useful +# if you want to understand what is going on. On the other hand, if this +# tag is set to NO the size of the Perl module output will be much smaller +# and Perl will parse it just the same. + +PERLMOD_PRETTY = YES + +# The names of the make variables in the generated doxyrules.make file +# are prefixed with the string contained in PERLMOD_MAKEVAR_PREFIX. +# This is useful so different doxyrules.make files included by the same +# Makefile don't overwrite each other's variables. + +PERLMOD_MAKEVAR_PREFIX = + +#--------------------------------------------------------------------------- +# Configuration options related to the preprocessor +#--------------------------------------------------------------------------- + +# If the ENABLE_PREPROCESSING tag is set to YES (the default) Doxygen will +# evaluate all C-preprocessor directives found in the sources and include +# files. + +ENABLE_PREPROCESSING = YES + +# If the MACRO_EXPANSION tag is set to YES Doxygen will expand all macro +# names in the source code. If set to NO (the default) only conditional +# compilation will be performed. Macro expansion can be done in a controlled +# way by setting EXPAND_ONLY_PREDEF to YES. + +MACRO_EXPANSION = NO + +# If the EXPAND_ONLY_PREDEF and MACRO_EXPANSION tags are both set to YES +# then the macro expansion is limited to the macros specified with the +# PREDEFINED and EXPAND_AS_DEFINED tags. + +EXPAND_ONLY_PREDEF = NO + +# If the SEARCH_INCLUDES tag is set to YES (the default) the includes files +# in the INCLUDE_PATH (see below) will be search if a #include is found. + +SEARCH_INCLUDES = YES + +# The INCLUDE_PATH tag can be used to specify one or more directories that +# contain include files that are not input files but should be processed by +# the preprocessor. + +INCLUDE_PATH = + +# You can use the INCLUDE_FILE_PATTERNS tag to specify one or more wildcard +# patterns (like *.h and *.hpp) to filter out the header-files in the +# directories. If left blank, the patterns specified with FILE_PATTERNS will +# be used. + +INCLUDE_FILE_PATTERNS = + +# The PREDEFINED tag can be used to specify one or more macro names that +# are defined before the preprocessor is started (similar to the -D option of +# gcc). The argument of the tag is a list of macros of the form: name +# or name=definition (no spaces). If the definition and the = are +# omitted =1 is assumed. To prevent a macro definition from being +# undefined via #undef or recursively expanded use the := operator +# instead of the = operator. + +PREDEFINED = + +# If the MACRO_EXPANSION and EXPAND_ONLY_PREDEF tags are set to YES then +# this tag can be used to specify a list of macro names that should be expanded. +# The macro definition that is found in the sources will be used. +# Use the PREDEFINED tag if you want to use a different macro definition. + +EXPAND_AS_DEFINED = + +# If the SKIP_FUNCTION_MACROS tag is set to YES (the default) then +# doxygen's preprocessor will remove all function-like macros that are alone +# on a line, have an all uppercase name, and do not end with a semicolon. Such +# function macros are typically used for boiler-plate code, and will confuse +# the parser if not removed. + +SKIP_FUNCTION_MACROS = YES + +#--------------------------------------------------------------------------- +# Configuration::additions related to external references +#--------------------------------------------------------------------------- + +# The TAGFILES option can be used to specify one or more tagfiles. +# Optionally an initial location of the external documentation +# can be added for each tagfile. The format of a tag file without +# this location is as follows: +# TAGFILES = file1 file2 ... +# Adding location for the tag files is done as follows: +# TAGFILES = file1=loc1 "file2 = loc2" ... +# where "loc1" and "loc2" can be relative or absolute paths or +# URLs. If a location is present for each tag, the installdox tool +# does not have to be run to correct the links. +# Note that each tag file must have a unique name +# (where the name does NOT include the path) +# If a tag file is not located in the directory in which doxygen +# is run, you must also specify the path to the tagfile here. + +TAGFILES = + +# When a file name is specified after GENERATE_TAGFILE, doxygen will create +# a tag file that is based on the input files it reads. + +GENERATE_TAGFILE = + +# If the ALLEXTERNALS tag is set to YES all external classes will be listed +# in the class index. If set to NO only the inherited external classes +# will be listed. + +ALLEXTERNALS = NO + +# If the EXTERNAL_GROUPS tag is set to YES all external groups will be listed +# in the modules index. If set to NO, only the current project's groups will +# be listed. + +EXTERNAL_GROUPS = YES + +# The PERL_PATH should be the absolute path and name of the perl script +# interpreter (i.e. the result of `which perl'). + +PERL_PATH = /usr/bin/perl + +#--------------------------------------------------------------------------- +# Configuration options related to the dot tool +#--------------------------------------------------------------------------- + +# If the CLASS_DIAGRAMS tag is set to YES (the default) Doxygen will +# generate a inheritance diagram (in HTML, RTF and LaTeX) for classes with base +# or super classes. Setting the tag to NO turns the diagrams off. Note that +# this option is superseded by the HAVE_DOT option below. This is only a +# fallback. It is recommended to install and use dot, since it yields more +# powerful graphs. + +CLASS_DIAGRAMS = YES + +# You can define message sequence charts within doxygen comments using the \msc +# command. Doxygen will then run the mscgen tool (see +# http://www.mcternan.me.uk/mscgen/) to produce the chart and insert it in the +# documentation. The MSCGEN_PATH tag allows you to specify the directory where +# the mscgen tool resides. If left empty the tool is assumed to be found in the +# default search path. + +MSCGEN_PATH = + +# If set to YES, the inheritance and collaboration graphs will hide +# inheritance and usage relations if the target is undocumented +# or is not a class. + +HIDE_UNDOC_RELATIONS = YES + +# If you set the HAVE_DOT tag to YES then doxygen will assume the dot tool is +# available from the path. This tool is part of Graphviz, a graph visualization +# toolkit from AT&T and Lucent Bell Labs. The other options in this section +# have no effect if this option is set to NO (the default) + +HAVE_DOT = NO + +# The DOT_NUM_THREADS specifies the number of dot invocations doxygen is +# allowed to run in parallel. When set to 0 (the default) doxygen will +# base this on the number of processors available in the system. You can set it +# explicitly to a value larger than 0 to get control over the balance +# between CPU load and processing speed. + +DOT_NUM_THREADS = 0 + +# By default doxygen will write a font called FreeSans.ttf to the output +# directory and reference it in all dot files that doxygen generates. This +# font does not include all possible unicode characters however, so when you need +# these (or just want a differently looking font) you can specify the font name +# using DOT_FONTNAME. You need need to make sure dot is able to find the font, +# which can be done by putting it in a standard location or by setting the +# DOTFONTPATH environment variable or by setting DOT_FONTPATH to the directory +# containing the font. + +DOT_FONTNAME = FreeSans.ttf + +# The DOT_FONTSIZE tag can be used to set the size of the font of dot graphs. +# The default size is 10pt. + +DOT_FONTSIZE = 10 + +# By default doxygen will tell dot to use the output directory to look for the +# FreeSans.ttf font (which doxygen will put there itself). If you specify a +# different font using DOT_FONTNAME you can set the path where dot +# can find it using this tag. + +DOT_FONTPATH = + +# If the CLASS_GRAPH and HAVE_DOT tags are set to YES then doxygen +# will generate a graph for each documented class showing the direct and +# indirect inheritance relations. Setting this tag to YES will force the +# the CLASS_DIAGRAMS tag to NO. + +CLASS_GRAPH = YES + +# If the COLLABORATION_GRAPH and HAVE_DOT tags are set to YES then doxygen +# will generate a graph for each documented class showing the direct and +# indirect implementation dependencies (inheritance, containment, and +# class references variables) of the class with other documented classes. + +COLLABORATION_GRAPH = YES + +# If the GROUP_GRAPHS and HAVE_DOT tags are set to YES then doxygen +# will generate a graph for groups, showing the direct groups dependencies + +GROUP_GRAPHS = YES + +# If the UML_LOOK tag is set to YES doxygen will generate inheritance and +# collaboration diagrams in a style similar to the OMG's Unified Modeling +# Language. + +UML_LOOK = NO + +# If set to YES, the inheritance and collaboration graphs will show the +# relations between templates and their instances. + +TEMPLATE_RELATIONS = NO + +# If the ENABLE_PREPROCESSING, SEARCH_INCLUDES, INCLUDE_GRAPH, and HAVE_DOT +# tags are set to YES then doxygen will generate a graph for each documented +# file showing the direct and indirect include dependencies of the file with +# other documented files. + +INCLUDE_GRAPH = YES + +# If the ENABLE_PREPROCESSING, SEARCH_INCLUDES, INCLUDED_BY_GRAPH, and +# HAVE_DOT tags are set to YES then doxygen will generate a graph for each +# documented header file showing the documented files that directly or +# indirectly include this file. + +INCLUDED_BY_GRAPH = YES + +# If the CALL_GRAPH and HAVE_DOT options are set to YES then +# doxygen will generate a call dependency graph for every global function +# or class method. Note that enabling this option will significantly increase +# the time of a run. So in most cases it will be better to enable call graphs +# for selected functions only using the \callgraph command. + +CALL_GRAPH = NO + +# If the CALLER_GRAPH and HAVE_DOT tags are set to YES then +# doxygen will generate a caller dependency graph for every global function +# or class method. Note that enabling this option will significantly increase +# the time of a run. So in most cases it will be better to enable caller +# graphs for selected functions only using the \callergraph command. + +CALLER_GRAPH = NO + +# If the GRAPHICAL_HIERARCHY and HAVE_DOT tags are set to YES then doxygen +# will graphical hierarchy of all classes instead of a textual one. + +GRAPHICAL_HIERARCHY = YES + +# If the DIRECTORY_GRAPH, SHOW_DIRECTORIES and HAVE_DOT tags are set to YES +# then doxygen will show the dependencies a directory has on other directories +# in a graphical way. The dependency relations are determined by the #include +# relations between the files in the directories. + +DIRECTORY_GRAPH = YES + +# The DOT_IMAGE_FORMAT tag can be used to set the image format of the images +# generated by dot. Possible values are png, jpg, or gif +# If left blank png will be used. + +DOT_IMAGE_FORMAT = png + +# The tag DOT_PATH can be used to specify the path where the dot tool can be +# found. If left blank, it is assumed the dot tool can be found in the path. + +DOT_PATH = + +# The DOTFILE_DIRS tag can be used to specify one or more directories that +# contain dot files that are included in the documentation (see the +# \dotfile command). + +DOTFILE_DIRS = + +# The DOT_GRAPH_MAX_NODES tag can be used to set the maximum number of +# nodes that will be shown in the graph. If the number of nodes in a graph +# becomes larger than this value, doxygen will truncate the graph, which is +# visualized by representing a node as a red box. Note that doxygen if the +# number of direct children of the root node in a graph is already larger than +# DOT_GRAPH_MAX_NODES then the graph will not be shown at all. Also note +# that the size of a graph can be further restricted by MAX_DOT_GRAPH_DEPTH. + +DOT_GRAPH_MAX_NODES = 50 + +# The MAX_DOT_GRAPH_DEPTH tag can be used to set the maximum depth of the +# graphs generated by dot. A depth value of 3 means that only nodes reachable +# from the root by following a path via at most 3 edges will be shown. Nodes +# that lay further from the root node will be omitted. Note that setting this +# option to 1 or 2 may greatly reduce the computation time needed for large +# code bases. Also note that the size of a graph can be further restricted by +# DOT_GRAPH_MAX_NODES. Using a depth of 0 means no depth restriction. + +MAX_DOT_GRAPH_DEPTH = 0 + +# Set the DOT_TRANSPARENT tag to YES to generate images with a transparent +# background. This is disabled by default, because dot on Windows does not +# seem to support this out of the box. Warning: Depending on the platform used, +# enabling this option may lead to badly anti-aliased labels on the edges of +# a graph (i.e. they become hard to read). + +DOT_TRANSPARENT = NO + +# Set the DOT_MULTI_TARGETS tag to YES allow dot to generate multiple output +# files in one run (i.e. multiple -o and -T options on the command line). This +# makes dot run faster, but since only newer versions of dot (>1.8.10) +# support this, this feature is disabled by default. + +DOT_MULTI_TARGETS = NO + +# If the GENERATE_LEGEND tag is set to YES (the default) Doxygen will +# generate a legend page explaining the meaning of the various boxes and +# arrows in the dot generated graphs. + +GENERATE_LEGEND = YES + +# If the DOT_CLEANUP tag is set to YES (the default) Doxygen will +# remove the intermediate dot files that are used to generate +# the various graphs. + +DOT_CLEANUP = YES diff --git a/Exception.cc b/Exception.cc index 0d82600..a5cf59c 100644 --- a/Exception.cc +++ b/Exception.cc @@ -19,18 +19,23 @@ using namespace zipper; -ZipException::ZipException(const std::string& what) : +Exception::Exception(const std::string& what) : std::runtime_error(what) { } -ZipFormatException::ZipFormatException(const std::string& what) : - ZipException(what) +FormatException::FormatException(const std::string& what) : + Exception(what) { } -ZipUnsupportedException::ZipUnsupportedException(const std::string& what) : - ZipException(what) +UnsupportedException::UnsupportedException(const std::string& what) : + Exception(what) +{ +} + +IOException::IOException(const std::string& what) : + Exception(what) { } diff --git a/FileReader.cc b/FileReader.cc new file mode 100644 index 0000000..8fc5a3b --- /dev/null +++ b/FileReader.cc @@ -0,0 +1,181 @@ +// Copyright (C) 2011 Michael McMaster +// +// This file is part of libzipper. +// +// libzipper is free software: you can redistribute it and/or modify +// it under the terms of the GNU General Public License as published by +// the Free Software Foundation, either version 3 of the License, or +// (at your option) any later version. +// +// libzipper is distributed in the hope that it will be useful, +// but WITHOUT ANY WARRANTY; without even the implied warranty of +// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +// GNU General Public License for more details. +// +// You should have received a copy of the GNU General Public License +// along with libzipper. If not, see . + +#include "zipper.hh" + +#include +#include + +#include +#include +#include +#include +#include + +using namespace zipper; + +class FileReader::FileReaderImpl +{ +public: + FileReaderImpl(const std::string& filename) : + m_filename(filename), + m_fd(-1), + m_closeOnExit(true) + { + m_fd = ::open(filename.c_str(), O_RDONLY); + + if (m_fd < 0) + { + char buf[1024]; + strerror_r(errno, buf, sizeof(buf)); + + std::stringstream message; + message << "Could not open file \"" << filename << "\": " << + buf; + throw IOException(message.str()); + } + initSize(); + } + + FileReaderImpl(const std::string& filename, int fd, bool closeFd) : + m_filename(filename), + m_fd(fd), + m_closeOnExit(closeFd) + { + initSize(); + } + + ~FileReaderImpl() + { + close(); + } + + const std::string& getSourceName() const { return m_filename; } + + zsize_t getSize() const { return m_size; } + + virtual void readData( + zsize_t offset, zsize_t bytes, uint8_t* dest + ) const + { + assert(m_fd >= 0); + + zsize_t bytesRead(0); + while(bytesRead < bytes) + { + ssize_t currentBytes( + pread( + m_fd, + dest + bytesRead, + bytes - bytesRead, + offset + bytesRead) + ); + + if (currentBytes > 0) + { + bytesRead += static_cast(currentBytes); + } + else if (currentBytes == 0) + { + throw FormatException("Unexpected end-of-file"); + } + else if ((currentBytes < 0) && (errno != EINTR)) + { + char buf[1024]; + strerror_r(errno, buf, sizeof(buf)); + throw IOException(buf); + } + } + } + +private: + void initSize() + { + // If we fail here, we need to essentially run the dtor manually. + // initSize is called from the constructors, and so the dtor will + // NOT run if an exception is thrown. + + struct stat buf; + int result(fstat(m_fd, &buf)); + if (result != 0) + { + int errnoLocal = errno; + close(); + + char buf[1024]; + strerror_r(errnoLocal, buf, sizeof(buf)); + + std::stringstream message; + message << "Could not get filesize for file " << + "\"" << m_filename << "\": " << buf; + throw IOException(message.str()); + } + else + { + m_size = buf.st_size; + } + } + + void close() + { + if ((m_fd >= 0) && m_closeOnExit) + { + ::close(m_fd); + m_fd = -1; + } + } + std::string m_filename; + int m_fd; + bool m_closeOnExit; + zsize_t m_size; +}; + +FileReader::FileReader(const std::string& filename) : + m_impl(new FileReaderImpl(filename)) +{ +} + +FileReader::FileReader(const std::string& filename, int fd, bool closeFd) : + m_impl(new FileReaderImpl(filename, fd, closeFd)) +{ +} + +FileReader::~FileReader() +{ + delete m_impl; +} + +const std::string& +FileReader::getSourceName() const +{ + return m_impl->getSourceName(); +} + +zsize_t +FileReader::getSize() const +{ + return m_impl->getSize(); +} + +void +FileReader::readData( + zsize_t offset, zsize_t bytes, uint8_t* dest + ) const +{ + return m_impl->readData(offset, bytes, dest); +} + diff --git a/FileWriter.cc b/FileWriter.cc new file mode 100644 index 0000000..b595a50 --- /dev/null +++ b/FileWriter.cc @@ -0,0 +1,148 @@ +// Copyright (C) 2011 Michael McMaster +// +// This file is part of libzipper. +// +// libzipper is free software: you can redistribute it and/or modify +// it under the terms of the GNU General Public License as published by +// the Free Software Foundation, either version 3 of the License, or +// (at your option) any later version. +// +// libzipper is distributed in the hope that it will be useful, +// but WITHOUT ANY WARRANTY; without even the implied warranty of +// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +// GNU General Public License for more details. +// +// You should have received a copy of the GNU General Public License +// along with libzipper. If not, see . + +#include "zipper.hh" + +#include +#include +#include + +#include +#include +#include +#include +#include + +using namespace zipper; + +class FileWriter::FileWriterImpl +{ +public: + FileWriterImpl(const std::string& filename, mode_t createPermissions) : + m_filename(filename), + m_fd(-1), + m_closeOnExit(true) + { + m_fd = + ::open( + filename.c_str(), + O_WRONLY | O_TRUNC | O_CREAT, + createPermissions); + + if (m_fd < 0) + { + char buf[1024]; + strerror_r(errno, buf, sizeof(buf)); + + std::stringstream message; + message << "Could not open file \"" << filename << "\": " << + buf; + throw IOException(message.str()); + } + } + + FileWriterImpl(const std::string& filename, int fd, bool closeFd) : + m_filename(filename), + m_fd(fd), + m_closeOnExit(closeFd) + { + } + + ~FileWriterImpl() + { + close(); + } + + virtual void writeData( + zsize_t offset, zsize_t bytes, const uint8_t* data + ) const + { + assert(m_fd >= 0); + + zsize_t bytesWritten(0); + while(bytesWritten < bytes) + { + ssize_t currentBytes( + pwrite( + m_fd, + data + bytesWritten, + bytes - bytesWritten, + offset + bytesWritten) + ); + + if (currentBytes >= 0) + { + bytesWritten += static_cast(currentBytes); + } + else if ((currentBytes < 0) && (errno != EINTR)) + { + char buf[1024]; + strerror_r(errno, buf, sizeof(buf)); + throw IOException(buf); + } + } + } + + zsize_t getSize() const + { + assert(m_fd >= 0); + zsize_t result(lseek(m_fd, 0, SEEK_END)); + return result; + } + +private: + void close() + { + if ((m_fd >= 0) && m_closeOnExit) + { + ::close(m_fd); + m_fd = -1; + } + } + + std::string m_filename; + int m_fd; + bool m_closeOnExit; +}; + +FileWriter::FileWriter(const std::string& filename, mode_t createPermissions) : + m_impl(new FileWriterImpl(filename, createPermissions)) +{ +} + +FileWriter::FileWriter(const std::string& filename, int fd, bool closeFd) : + m_impl(new FileWriterImpl(filename, fd, closeFd)) +{ +} + +FileWriter::~FileWriter() +{ + delete m_impl; +} + +void +FileWriter::writeData(zsize_t offset, zsize_t bytes, const uint8_t* data) +{ + m_impl->writeData(offset, bytes, data); +} + +zsize_t +FileWriter::getSize() const +{ + return m_impl->getSize(); +} + diff --git a/Makefile.am b/Makefile.am index aa6d4ec..287d6f0 100644 --- a/Makefile.am +++ b/Makefile.am @@ -15,6 +15,8 @@ # You should have received a copy of the GNU General Public License # along with libzipper. If not, see . +include doxygen.am + dist_noinst_SCRIPTS = autogen.sh EXTRA_DIST = \ @@ -27,11 +29,22 @@ EXTRA_DIST = \ lib_LTLIBRARIES = libzipper.la libzipper_la_SOURCES = \ + Compressor.cc \ CompressedFile.cc \ - Consumer.cc \ + Container.cc \ + Decompressor.cc \ Exception.cc \ - Provider.cc \ + FileReader.cc \ + FileWriter.cc \ + Reader.cc \ + Ungzip.cc \ + Ungzip.hh \ Unzip.cc \ + Unzip.hh \ + util.hh \ + Writer.cc \ + Zip.hh \ + Zip.cc \ zipper.hh libzipper_la_LDFLAGS = ${ZLIB_LIBS} @@ -46,3 +59,5 @@ zipper_LDADD = libzipper.la CXXFLAGS=-g -O2 -W -Wall -Werror -std=c++0x +MOSTLYCLEANFILES=$(DX_CLEANFILES) + diff --git a/README b/README index bbdb593..9810ba6 100644 --- a/README +++ b/README @@ -1,7 +1,7 @@ libzipper Michael McMaster -Flexible C++ interface for reading compressed files in +libzipper offers a flexible C++ interface for reading compressed files in multiple formats. Supported Formats diff --git a/Consumer.cc b/Reader.cc similarity index 97% rename from Consumer.cc rename to Reader.cc index fd102b8..fe0b377 100644 --- a/Consumer.cc +++ b/Reader.cc @@ -19,7 +19,7 @@ using namespace zipper; -Consumer::~Consumer() +Reader::~Reader() { } diff --git a/Ungzip.cc b/Ungzip.cc new file mode 100644 index 0000000..774d6c6 --- /dev/null +++ b/Ungzip.cc @@ -0,0 +1,309 @@ +// Copyright (C) 2011 Michael McMaster +// +// This file is part of libzipper. +// +// libzipper is free software: you can redistribute it and/or modify +// it under the terms of the GNU General Public License as published by +// the Free Software Foundation, either version 3 of the License, or +// (at your option) any later version. +// +// libzipper is distributed in the hope that it will be useful, +// but WITHOUT ANY WARRANTY; without even the implied warranty of +// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +// GNU General Public License for more details. +// +// You should have received a copy of the GNU General Public License +// along with libzipper. If not, see . + +#include "zipper.hh" +#include "Ungzip.hh" + +#include + +#include +#include +#include +#include + +#include + +using namespace zipper; + +namespace +{ + uint32_t + read32(const uint8_t* zipData) + { + // Read 4 bytes in little-endian order. + // Return results in host-endian. + return uint32_t( + zipData[0] | + (uint32_t(zipData[1]) << 8) | + (uint32_t(zipData[2]) << 16) | + (uint32_t(zipData[3]) << 24) + ); + } + + uint16_t + read16(const std::vector& zipData, size_t pos) + { + // Read 2 bytes in little-endian order. + // Return results in host-endian. + return uint16_t( + zipData[pos] | + (uint16_t(zipData[pos+1]) << 8) + ); + } + + + size_t + findNull(const std::vector& zipData, size_t start) + { + if (start >= zipData.size()) + { + throw FormatException("Unexpected end-of-file"); + } + + while (zipData[start] != 0) + { + ++start; + if (start >= zipData.size()) + { + throw FormatException("Unexpected end-of-file"); + } + } + return start; + } + + struct InflateDeleter + { + public: + InflateDeleter(z_stream* stream) : m_stream(stream) {} + ~InflateDeleter() + { + inflateEnd(m_stream); + + } + private: + z_stream* m_stream; + }; + + class FileEntry : public CompressedFile + { + public: + FileEntry( + const ReaderPtr& reader, + zsize_t dataOffset, + const std::string& filename + ) : + m_reader(reader), + m_dataOffset(dataOffset), + m_fileName(filename) + { + } + + virtual bool isDecompressSupported() const + { + return true; + } + + virtual const std::string& getPath() const + { + return m_fileName; + } + + virtual zsize_t getCompressedSize() const { return -1; } + virtual zsize_t getUncompressedSize() const { return -1; } + + virtual void decompress(Writer& writer) + { + enum + { + ChunkSize = 64*1024, + WindowBits = 15 + }; + + uint8_t inChunk[ChunkSize]; + uint8_t outChunk[ChunkSize]; + zsize_t endCompressedBytes = m_reader->getSize() - 8; // CRC+ISIZE + uint32_t crc(crc32(0, NULL, 0)); + + z_stream stream; + stream.zalloc = NULL; + stream.zfree = NULL; + stream.opaque = NULL; + int zlibErr(inflateInit2(&stream, -WindowBits)); + assert(zlibErr == Z_OK); + InflateDeleter deleter(&stream); + stream.next_in = NULL; + stream.avail_in = 0; + + bool finished(false); + zsize_t pos(m_dataOffset); + zsize_t outPos(0); + while (pos < endCompressedBytes) + { + if (stream.avail_in == 0) + { + stream.avail_in = + std::min( + zsize_t(ChunkSize), + endCompressedBytes - pos + ); + m_reader->readData( + pos, stream.avail_in, &inChunk[0] + ); + stream.next_in = reinterpret_cast(&inChunk); + pos += stream.avail_in; + } + + stream.next_out = reinterpret_cast(&outChunk); + stream.avail_out = sizeof(outChunk); + + zlibErr = inflate(&stream, Z_SYNC_FLUSH); + + finished = false; + if (zlibErr == Z_STREAM_END) + { + finished = true; + } + else if (zlibErr != Z_OK) + { + throw FormatException("Corrupt Data"); + } + + zsize_t bytesToWrite(sizeof(outChunk) - stream.avail_out); + writer.writeData(outPos, bytesToWrite, &outChunk[0]); + outPos += bytesToWrite; + crc = crc32(crc, &outChunk[0], bytesToWrite); + + if (finished) break; + } + + if (!finished) + { + // Ran out of data to process + throw FormatException("Corrupt Data"); + } + + uint8_t crcBuffer[4]; + ::memcpy(crcBuffer, stream.next_in, std::min(4u, stream.avail_in)); + + if (stream.avail_in < 4) + { + m_reader->readData( + pos, 4 - stream.avail_in, &crcBuffer[stream.avail_in] + ); + } + uint32_t savedCRC = read32(&crcBuffer[0]); + if (savedCRC != crc) + { + throw FormatException("Corrupt Data (CRC Failure)"); + } + } + + private: + ReaderPtr m_reader; + zsize_t m_dataOffset; + std::string m_fileName; + }; +} + +namespace zipper +{ + std::vector + ungzip(const ReaderPtr& reader) + { + enum + { + MaxHeader = 64*1024 // Artifical limit to simplify code + }; + + if (!isGzip(reader)) + { + throw FormatException("Invalid gzip file"); + } + + std::vector header( + std::min(reader->getSize(), zsize_t(MaxHeader))); + reader->readData(0, header.size(), &header[0]); + + if (header[2] != 8) // "deflate" method + { + throw UnsupportedException("Unknown gzip compression method"); + } + + bool fextra = (header[3] & 4) != 0; + bool fname = (header[3] & 8) != 0; + bool fcomment = (header[3] & 0x10) != 0; + bool fhcrc = (header[3] & 2) != 0; + + size_t offset(10); + + if (fextra) + { + if (offset + 2 > header.size()) + { + throw FormatException("Unexpected end-of-file"); + } + uint16_t fextraBytes(read16(header, offset)); + offset += 2; + + offset += fextraBytes; + } + + std::string embeddedName(reader->getSourceName()); + if (fname) + { + size_t nullOffset(findNull(header, offset)); + embeddedName = + std::string( + reinterpret_cast(&header[offset]), + nullOffset - offset); + offset = nullOffset + 1; + } + + if (fcomment) + { + size_t nullOffset(findNull(header, offset)); + offset = nullOffset + 1; + } + + if (fhcrc) + { + offset += 2; + } + + if (offset >= header.size()) + { + throw FormatException("Unexpected end-of-file"); + } + + std::vector result; + result.push_back( + CompressedFilePtr(new FileEntry(reader, offset, embeddedName))); + + return result; + } + + bool + isGzip(const ReaderPtr& reader) + { + enum Constants + { + MinFileBytes = 18, // Header + CRC + size + ID1 = 0x1f, + ID2 = 0x8b + }; + + bool isGzip(false); + if (reader->getSize() >= MinFileBytes) + { + uint8_t magic[2]; + reader->readData(0, sizeof(magic), &magic[0]); + isGzip = (magic[0] == ID1) && (magic[1] == ID2); + } + return isGzip; + } +} + diff --git a/Ungzip.hh b/Ungzip.hh new file mode 100644 index 0000000..95d445b --- /dev/null +++ b/Ungzip.hh @@ -0,0 +1,28 @@ +// Copyright (C) 2011 Michael McMaster +// +// This file is part of libzipper. +// +// libzipper is free software: you can redistribute it and/or modify +// it under the terms of the GNU General Public License as published by +// the Free Software Foundation, either version 3 of the License, or +// (at your option) any later version. +// +// libzipper is distributed in the hope that it will be useful, +// but WITHOUT ANY WARRANTY; without even the implied warranty of +// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +// GNU General Public License for more details. +// +// You should have received a copy of the GNU General Public License +// along with libzipper. If not, see . + +#include "zipper.hh" + +#include + +namespace zipper +{ + bool isGzip(const ReaderPtr& reader); + + std::vector ungzip(const ReaderPtr& reader); +} + diff --git a/Unzip.cc b/Unzip.cc index 6e2253c..7845d91 100644 --- a/Unzip.cc +++ b/Unzip.cc @@ -16,6 +16,7 @@ // along with libzipper. If not, see . #include "zipper.hh" +#include "Unzip.hh" #include @@ -23,12 +24,15 @@ #include #include +#include + using namespace zipper; namespace { + template uint32_t - read32(const std::vector& zipData, size_t pos) + read32(const T& zipData, size_t pos) { // Read 4 bytes in little-endian order. // Return results in host-endian. @@ -68,44 +72,47 @@ namespace { public: FileEntry( - ProviderPtr provider, + const ReaderPtr& reader, uint16_t versionNeeded, uint16_t gpFlag, uint16_t compressionMethod, - uint16_t lastModTime, - uint16_t lastModDate, - uint32_t crc32, - uint32_t compressedSize, - uint32_t uncompressedSize, - uint32_t localHeaderOffset, - std::string fileName, - std::string extra, - std::string comment + uint32_t crc, + zsize_t compressedSize, + zsize_t uncompressedSize, + zsize_t localHeaderOffset, + std::string fileName ) : - m_provider(provider), + m_reader(reader), m_versionNeeded(versionNeeded), m_gpFlag(gpFlag), m_compressionMethod(compressionMethod), - m_lastModTime(lastModTime), - m_lastModDate(lastModDate), - m_crc32(crc32), + m_crc(crc), m_compressedSize(compressedSize), m_uncompressedSize(uncompressedSize), m_localHeaderOffset(localHeaderOffset), - m_fileName(fileName), - m_extra(extra), - m_comment(comment) + m_fileName(fileName) { } - virtual bool isValid() const + virtual bool isDecompressSupported() const { return ((m_versionNeeded & 0xf) <= 20) && ((m_gpFlag & 0x1) == 0) && // Not encrypted - (m_compressionMethod <= 8); + ((m_compressionMethod == 0) || (m_compressionMethod == 8)); } - virtual void uncompress(Consumer& consumer) + virtual const std::string& getPath() const + { + return m_fileName; + } + + virtual zsize_t getCompressedSize() const { return m_compressedSize; } + virtual zsize_t getUncompressedSize() const + { + return m_uncompressedSize; + } + + virtual void decompress(Writer& writer) { enum { @@ -116,51 +123,51 @@ namespace }; std::vector localRecord(MinRecordBytes); - m_provider->zip_readData( + m_reader->readData( m_localHeaderOffset, MinRecordBytes, &localRecord[0] ); if (read32(localRecord, 0) != Signature) { - throw ZipFormatException("Invalid local ZIP record"); + throw FormatException("Invalid local ZIP record"); } // Don't trust the lengths for filename and extra content read from // the central records. At least for extra, these DO differ for // unknown reasons - size_t filenameLength(read16(localRecord, 26)); - size_t extraLength(read16(localRecord, 28)); + zsize_t filenameLength(read16(localRecord, 26)); + zsize_t extraLength(read16(localRecord, 28)); - zoff64_t startCompressedBytes( + zsize_t startCompressedBytes( m_localHeaderOffset + MinRecordBytes + filenameLength + extraLength ); - zoff64_t endCompressedBytes( + zsize_t endCompressedBytes( startCompressedBytes + m_compressedSize ); - if (endCompressedBytes > m_provider->zip_getSize()) + if (endCompressedBytes > m_reader->getSize()) { - throw ZipFormatException("Compressed file size is too long"); + throw FormatException("Compressed file size is too long"); } switch (m_compressionMethod) { case 0: // No compression { - for (zoff64_t pos(startCompressedBytes); + for (zsize_t pos(startCompressedBytes); pos < endCompressedBytes; pos += ChunkSize ) { uint8_t buf[ChunkSize]; - size_t bytes( - std::min(zoff64_t(ChunkSize), endCompressedBytes - pos) + zsize_t bytes( + std::min(zsize_t(ChunkSize), endCompressedBytes - pos) ); - m_provider->zip_readData(pos, bytes, &buf[0]); - consumer.zip_writeData(bytes, &buf[0]); + m_reader->readData(pos, bytes, &buf[0]); + writer.writeData(pos, bytes, &buf[0]); } }; break; @@ -178,23 +185,25 @@ namespace InflateDeleter deleter(&stream); stream.next_in = NULL; stream.avail_in = 0; + bool finished(false); - for (zoff64_t pos(startCompressedBytes); - pos < endCompressedBytes; - pos += ChunkSize - ) + zsize_t pos(startCompressedBytes); + zsize_t outPos(0); + uint32_t crc(crc32(0, NULL, 0)); + while (pos < endCompressedBytes) { if (stream.avail_in == 0) { stream.avail_in = std::min( - zoff64_t(ChunkSize), + zsize_t(ChunkSize), endCompressedBytes - pos ); - m_provider->zip_readData( + m_reader->readData( pos, stream.avail_in, &inChunk[0] ); stream.next_in = reinterpret_cast(&inChunk); + pos += stream.avail_in; } stream.next_out = reinterpret_cast(&outChunk); @@ -202,95 +211,167 @@ namespace zlibErr = inflate(&stream, Z_SYNC_FLUSH); - bool finished(false); + finished = false; if (zlibErr == Z_STREAM_END) { finished = true; + } else if (zlibErr != Z_OK) { - throw ZipFormatException("Corrupt Data"); + throw FormatException("Corrupt Data"); } - consumer.zip_writeData( - sizeof(outChunk) - stream.avail_out, + zsize_t bytesToWrite(sizeof(outChunk) - stream.avail_out); + writer.writeData( + outPos, + bytesToWrite, &outChunk[0] ); + outPos += bytesToWrite; + crc = crc32(crc, &outChunk[0], bytesToWrite); if (finished) break; } - }; break; + if (!finished) + { + // Ran out of data to process + throw FormatException("Corrupt Data"); + } + + if (m_gpFlag & 0x4) // CRC is after compressed data + { + uint8_t dataDescriptor[12]; + ::memcpy( + dataDescriptor, + stream.next_in, + std::min(12u, stream.avail_in)); + if (stream.avail_in < 12) + { + m_reader->readData( + pos, + 12 - stream.avail_in, + &dataDescriptor[stream.avail_in]); + } + m_crc = read32(dataDescriptor, 0); + m_compressedSize = read32(dataDescriptor, 4); + m_uncompressedSize = read32(dataDescriptor, 8); + } + + if (crc != m_crc) + { + throw FormatException("Corrupt Data (CRC failure)"); + } + + }; break; default: - throw ZipUnsupportedException("Unsupported compression scheme"); + throw UnsupportedException("Unsupported compression scheme"); }; } private: - ProviderPtr m_provider; + ReaderPtr m_reader; uint16_t m_versionNeeded; uint16_t m_gpFlag; uint16_t m_compressionMethod; - uint16_t m_lastModTime; - uint16_t m_lastModDate; - uint32_t m_crc32; - uint32_t m_compressedSize; - uint32_t m_uncompressedSize; - uint32_t m_localHeaderOffset; + uint32_t m_crc; + zsize_t m_compressedSize; + zsize_t m_uncompressedSize; + zsize_t m_localHeaderOffset; std::string m_fileName; - std::string m_extra; - std::string m_comment; }; -} -class Unzip::UnzipImpl -{ -public: - UnzipImpl(const ProviderPtr& provider) : - m_provider(provider) + bool readEndCentralDirectory( + const ReaderPtr& reader, + zsize_t& centralDirectoryBytes, + zsize_t& centralDirectoryOffset, + zsize_t& centralDirectoryEntries + ) { - readCentralDirectory(); - } + // Read the end of central directory record. This + // record enables us to find the remainding + // records without searching for record signatures. - std::vector - getEntries() const - { - return m_entries; - } + // TODO does not consider the Zip64 entries. -private: - ProviderPtr m_provider; - std::vector m_entries; + enum + { + MinRecordBytes = 22, // Minimum size with no comment + MaxCommentBytes = 65535, // 2 bytes to store comment length + Signature = 0x06054b50 + }; - struct EndCentralDirectory - { - size_t centralDirectoryBytes; - size_t centralDirectoryOffset; - size_t centralDirectoryEntries; - std::string zipFileComment; - }; - EndCentralDirectory m_endCentralDirectory; + zsize_t providerSize(reader->getSize()); + if (providerSize < MinRecordBytes) + { + throw FormatException("Too small"); + } + + size_t bufSize( + std::min(zsize_t(MinRecordBytes + MaxCommentBytes), providerSize) + ); + std::vector buffer(bufSize); + reader->readData(providerSize - bufSize, bufSize, &buffer[0]); + + // Need to search for this record, as it ends in a variable-length + // comment field. Search backwards, with the assumption that the + // comment doesn't exist, or is much smaller than the maximum + // length + + bool recordFound(false); + ssize_t pos(bufSize - MinRecordBytes); + for (; pos >= 0; --pos) + { + recordFound = (read32(buffer, pos) == Signature); + break; + } + + if (recordFound) + { + if (read16(buffer, pos + 4) != 0) + { + throw UnsupportedException("Spanned disks not supported"); + } - void readCentralDirectory() + centralDirectoryBytes = read32(buffer, pos + 12); + centralDirectoryOffset = read32(buffer, pos + 16); + centralDirectoryEntries = read16(buffer, pos + 10); + } + return recordFound; + } + + std::vector + readCentralDirectory(const ReaderPtr& reader) { - enum + enum Constants { MinRecordBytes = 46, Signature = 0x02014b50 }; - readEndCentralDirectory(); - - std::vector buffer( - m_endCentralDirectory.centralDirectoryBytes + zsize_t centralDirectoryBytes(0); + zsize_t centralDirectoryOffset(0); + zsize_t centralDirectoryEntries(0); + bool isZip( + readEndCentralDirectory( + reader, + centralDirectoryBytes, + centralDirectoryOffset, + centralDirectoryEntries + ) ); - m_provider->zip_readData( - m_endCentralDirectory.centralDirectoryOffset, - m_endCentralDirectory.centralDirectoryBytes, + assert(isZip); + + std::vector buffer(centralDirectoryBytes); + reader->readData( + centralDirectoryOffset, + centralDirectoryBytes, &buffer[0] ); - size_t pos(0); + zsize_t pos(0); + std::vector entries; while ((pos + MinRecordBytes) < buffer.size()) { if (read32(buffer, pos) != Signature) @@ -303,9 +384,7 @@ private: uint16_t versionNeeded(read16(buffer, pos + 6)); uint16_t gpFlag(read16(buffer, pos + 8)); uint16_t compressionMethod(read16(buffer, pos + 10)); - uint16_t lastModTime(read16(buffer, pos + 12)); - uint16_t lastModDate(read16(buffer, pos + 14)); - uint32_t crc32(read32(buffer, pos + 16)); + uint32_t crc(read32(buffer, pos + 16)); uint32_t compressedSize(read32(buffer, pos + 20)); uint32_t uncompressedSize(read32(buffer, pos + 24)); size_t fileNameLen(read16(buffer, pos + 28)); @@ -317,7 +396,7 @@ private: buffer.size() ) { - throw ZipFormatException("File comments are too long"); + throw FormatException("File comments are too long"); } std::string fileName( @@ -325,124 +404,48 @@ private: &buffer[pos + MinRecordBytes + fileNameLen] ); - std::string extra( - &buffer[pos+MinRecordBytes+fileNameLen], - &buffer[pos+MinRecordBytes+fileNameLen+extraLen] - ); - - std::string comment( - &buffer[pos+MinRecordBytes+fileNameLen+extraLen], - &buffer[pos+MinRecordBytes+fileNameLen+extraLen+commentLen] - ); - - m_entries.push_back( + entries.push_back( CompressedFilePtr( new FileEntry( - m_provider, + reader, versionNeeded, gpFlag, compressionMethod, - lastModTime, - lastModDate, - crc32, + crc, compressedSize, uncompressedSize, localHeaderOffset, - fileName, - extra, - comment + fileName ) ) ); pos += MinRecordBytes + fileNameLen + extraLen + commentLen; } + return entries; } - - void readEndCentralDirectory() - { - // Read the end of central directory record. This - // record enables us to find the remainding - // records without searching for record signatures. - - // TODO does not consider the Zip64 entries. - - enum - { - MinRecordBytes = 22, // Minimum size with no comment - MaxCommentBytes = 65535, // 2 bytes to store comment length - Signature = 0x06054b50 - }; - - zoff64_t providerSize(m_provider->zip_getSize()); - if (providerSize < MinRecordBytes) - { - throw ZipFormatException("Too small"); - } - - size_t bufSize( - std::min(zoff64_t(MinRecordBytes + MaxCommentBytes), providerSize) - ); - std::vector buffer(bufSize); - m_provider->zip_readData(providerSize - bufSize, bufSize, &buffer[0]); - - // Need to search for this record, as it ends in a variable-length - // comment field. Search backwards, with the assumption that the - // comment doesn't exist, or is much smaller than the maximum - // length - - bool recordFound(false); - ssize_t pos(bufSize - MinRecordBytes); - for (; pos >= 0; --pos) - { - recordFound = (read32(buffer, pos) == Signature); - break; - } - - if (!recordFound) - { - throw ZipFormatException("ZIP directory records not found"); - } - - if (read16(buffer, pos + 4) != 0) - { - throw ZipUnsupportedException("Spanned disks not supported"); - } - - m_endCentralDirectory.centralDirectoryBytes = read32(buffer, pos + 12); - m_endCentralDirectory.centralDirectoryOffset = - read32(buffer, pos + 16); - m_endCentralDirectory.centralDirectoryEntries = - read16(buffer, pos + 10); - - size_t commentLength(read16(buffer, pos + 20)); - size_t commentStart(pos + MinRecordBytes); - if (commentStart + commentLength > bufSize) - { - throw ZipFormatException("ZIP comment is too long"); - } - m_endCentralDirectory.zipFileComment = - std::string( - &buffer[commentStart], - &buffer[commentStart + commentLength] - ); - } - -}; - -Unzip::Unzip(const ProviderPtr& provider) : - m_unzipper(new UnzipImpl(provider)) -{ } -Unzip::~Unzip() +std::vector +zipper::unzip(const ReaderPtr& reader) { - delete m_unzipper; + return readCentralDirectory(reader); } -std::vector -Unzip::getEntries() const +bool +zipper::isZip(const ReaderPtr& reader) { - return m_unzipper->getEntries(); + zsize_t centralDirectoryBytes(0); + zsize_t centralDirectoryOffset(0); + zsize_t centralDirectoryEntries(0); + bool result( + readEndCentralDirectory( + reader, + centralDirectoryBytes, + centralDirectoryOffset, + centralDirectoryEntries + ) + ); + return result; } diff --git a/Unzip.hh b/Unzip.hh new file mode 100644 index 0000000..ab78f9f --- /dev/null +++ b/Unzip.hh @@ -0,0 +1,28 @@ +// Copyright (C) 2011 Michael McMaster +// +// This file is part of libzipper. +// +// libzipper is free software: you can redistribute it and/or modify +// it under the terms of the GNU General Public License as published by +// the Free Software Foundation, either version 3 of the License, or +// (at your option) any later version. +// +// libzipper is distributed in the hope that it will be useful, +// but WITHOUT ANY WARRANTY; without even the implied warranty of +// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +// GNU General Public License for more details. +// +// You should have received a copy of the GNU General Public License +// along with libzipper. If not, see . + +#include "zipper.hh" + +#include + +namespace zipper +{ + bool isZip(const ReaderPtr& reader); + + std::vector unzip(const ReaderPtr& reader); +} + diff --git a/Provider.cc b/Writer.cc similarity index 97% rename from Provider.cc rename to Writer.cc index 474ad71..8026e39 100644 --- a/Provider.cc +++ b/Writer.cc @@ -19,7 +19,7 @@ using namespace zipper; -Provider::~Provider() +Writer::~Writer() { } diff --git a/Zip.cc b/Zip.cc new file mode 100644 index 0000000..8048ece --- /dev/null +++ b/Zip.cc @@ -0,0 +1,296 @@ +// Copyright (C) 2011 Michael McMaster +// +// This file is part of libzipper. +// +// libzipper is free software: you can redistribute it and/or modify +// it under the terms of the GNU General Public License as published by +// the Free Software Foundation, either version 3 of the License, or +// (at your option) any later version. +// +// libzipper is distributed in the hope that it will be useful, +// but WITHOUT ANY WARRANTY; without even the implied warranty of +// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +// GNU General Public License for more details. +// +// You should have received a copy of the GNU General Public License +// along with libzipper. If not, see . + +#include "zipper.hh" +#include "Zip.hh" + +#include + +#include +#include +#include + +#include + +using namespace zipper; + +namespace +{ + void + write32(uint32_t value, uint8_t* zipData) + { + // Write 4 bytes in little-endian order. + zipData[0] = value & 0xff; + zipData[1] = (value >> 8) & 0xff; + zipData[2] = (value >> 16) & 0xff; + zipData[3] = (value >> 24) & 0xff; + } + + struct DeflateDeleter + { + public: + DeflateDeleter(z_stream* stream) : m_stream(stream) {} + ~DeflateDeleter() + { + deflateEnd(m_stream); + + } + private: + z_stream* m_stream; + }; +} + + +void +zipper::zip( + const std::string& filename, + const Reader& reader, + const WriterPtr& writer, + ZipFileRecord& outRecord) +{ + enum Constants + { + ChunkSize = 64*1024, + WindowBits = 15, + CRC32Pos = 14 + }; + + static uint8_t Header[] = + { + 0x50, 0x4b, 0x03, 0x04, // Header + 20, // Version (2.0) + 0, // File attributes + 0,0, // gp flag. + 8,0, // deflate method + 0,0, // file time + 0,0, // file date + 0,0,0,0, // CRC32 + 0,0,0,0, // Compressed size + 0,0,0,0 // Uncompressed size + }; + + zsize_t outPos(writer->getSize()); + outRecord.localHeaderOffset = outPos; + outRecord.filename = filename; + + // Write header + { + uint8_t buffer[ChunkSize]; + memcpy(buffer, Header, sizeof(Header)); + zsize_t pos(sizeof(Header)); + + std::string::size_type filenameSize(filename.size()); + if (filenameSize > (ChunkSize - pos)) + { + filenameSize = ChunkSize - pos; + } + buffer[pos++] = filenameSize & 0xff; + buffer[pos++] = (filenameSize >> 8); + buffer[pos++] = 0; // extra field len + buffer[pos++] = 0; // extra field len + memcpy(buffer + pos, filename.data(), filenameSize); + pos += filenameSize; + writer->writeData(outPos, pos, &buffer[0]); + outPos += pos; + } + + // Write compressed data + + uint8_t inChunk[ChunkSize]; + uint8_t outChunk[ChunkSize]; + + outRecord.uncompressedSize = 0; + outRecord.compressedSize = 0; + + z_stream stream; + stream.zalloc = NULL; + stream.zfree = NULL; + stream.opaque = NULL; + int zlibErr( + deflateInit2( + &stream, + Z_DEFAULT_COMPRESSION, + Z_DEFLATED, + -WindowBits, + MAX_MEM_LEVEL, + Z_DEFAULT_STRATEGY) + ); + + assert(zlibErr == Z_OK); + DeflateDeleter deleter(&stream); + stream.next_in = NULL; + stream.avail_in = 0; + + zsize_t pos(0); + zsize_t end(reader.getSize()); + outRecord.crc32 = crc32(0, NULL, 0); + + while (pos < end) + { + if (stream.avail_in == 0) + { + stream.avail_in = + std::min(zsize_t(ChunkSize), end - pos); + reader.readData( + pos, stream.avail_in, &inChunk[0]); + stream.next_in = reinterpret_cast(&inChunk); + pos += stream.avail_in; + outRecord.uncompressedSize += stream.avail_in; + outRecord.crc32 = + crc32(outRecord.crc32, stream.next_in, stream.avail_in); + } + + stream.next_out = reinterpret_cast(&outChunk); + stream.avail_out = sizeof(outChunk); + + zlibErr = deflate(&stream, (pos < end) ? Z_NO_FLUSH : Z_FINISH); + + if (zlibErr == Z_STREAM_END) + { + if (pos < end) + { + assert(!"zlib buffer unexpectedly empty"); + std::terminate(); + } + } + else if (zlibErr != Z_OK) + { + throw FormatException("Corrupt Data"); + } + + zsize_t bytesToWrite(sizeof(outChunk) - stream.avail_out); + writer->writeData( + outPos, + bytesToWrite, + &outChunk[0]); + outPos += bytesToWrite; + outRecord.compressedSize += bytesToWrite; + } + + // Go back and complete the header. + uint8_t trailer[12]; + write32(outRecord.crc32, &trailer[0]); + write32(outRecord.compressedSize, &trailer[4]); + write32(outRecord.uncompressedSize, &trailer[8]); + writer->writeData( + outRecord.localHeaderOffset + CRC32Pos, sizeof(trailer), &trailer[0]); +} + +void +zipper::zipFinalise( + const std::vector& records, + const WriterPtr& writer) +{ + enum Constants + { + ChunkSize = 64*1024 + }; + + static uint8_t FileHeader[] = + { + 0x50, 0x4b, 0x01, 0x02, // Header + 20, 0x00, // Version (2.0) + 20, 0x00, // Version Needed to extract (2.0) + 0,0, // gp flag. + 8,0, // deflate method + 0,0, // file time + 0,0 // file date + }; + + zsize_t outPos(writer->getSize()); + uint32_t centralDirOffset(outPos); + + for (size_t i = 0; i < records.size(); ++i) + { + uint8_t buffer[ChunkSize]; + memcpy(buffer, FileHeader, sizeof(FileHeader)); + zsize_t pos(sizeof(FileHeader)); + + write32(records[i].crc32, &buffer[pos]); + pos += 4; + + write32(records[i].compressedSize, &buffer[pos]); + pos += 4; + + write32(records[i].uncompressedSize, &buffer[pos]); + pos += 4; + + std::string::size_type filenameSize(records[i].filename.size()); + if (filenameSize > (ChunkSize - pos)) + { + filenameSize = ChunkSize - pos; + } + buffer[pos++] = filenameSize & 0xff; + buffer[pos++] = (filenameSize >> 8); + buffer[pos++] = 0; // extra field len + buffer[pos++] = 0; // extra field len + + buffer[pos++] = 0; // file comment len + buffer[pos++] = 0; // file comment len + + buffer[pos++] = 0; // disk number + buffer[pos++] = 0; // disk number + + buffer[pos++] = 0; // internal file attributes + buffer[pos++] = 0; // internal file attributes + + buffer[pos++] = 0; // external file attributes + buffer[pos++] = 0; // external file attributes + buffer[pos++] = 0; // external file attributes + buffer[pos++] = 0; // external file attributes + + write32(records[i].localHeaderOffset, &buffer[pos]); + pos += 4; + + memcpy(buffer + pos, records[i].filename.data(), filenameSize); + pos += filenameSize; + + writer->writeData(outPos, pos, &buffer[0]); + outPos += pos; + } + + uint32_t centralDirSize(writer->getSize() - centralDirOffset); + + { + // End-of-directory record. + static uint8_t EndDirectory[] = + { + 0x50, 0x4b, 0x05, 0x06, // Header + 0x00, 0x00, // Disk num + 0x00, 0x00 // Disk with central dir + }; + uint8_t buffer[ChunkSize]; + memcpy(buffer, EndDirectory, sizeof(EndDirectory)); + zsize_t pos(sizeof(EndDirectory)); + + buffer[pos++] = records.size() & 0xff; // Entries on this disk + buffer[pos++] = records.size() >> 8; + buffer[pos++] = records.size() & 0xff; // Total entries + buffer[pos++] = records.size() >> 8; + + write32(centralDirSize, &buffer[pos]); + pos += 4; + write32(centralDirOffset, &buffer[pos]); + pos += 4; + + buffer[pos++] = 0; // Zip comment length + buffer[pos++] = 0; // Zip comment length + + writer->writeData(outPos, pos, &buffer[0]); + outPos += pos; + } +} diff --git a/Zip.hh b/Zip.hh new file mode 100644 index 0000000..7680a61 --- /dev/null +++ b/Zip.hh @@ -0,0 +1,44 @@ +// Copyright (C) 2011 Michael McMaster +// +// This file is part of libzipper. +// +// libzipper is free software: you can redistribute it and/or modify +// it under the terms of the GNU General Public License as published by +// the Free Software Foundation, either version 3 of the License, or +// (at your option) any later version. +// +// libzipper is distributed in the hope that it will be useful, +// but WITHOUT ANY WARRANTY; without even the implied warranty of +// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +// GNU General Public License for more details. +// +// You should have received a copy of the GNU General Public License +// along with libzipper. If not, see . + +#include "zipper.hh" + +#include +#include + +namespace zipper +{ + struct ZipFileRecord + { + zsize_t localHeaderOffset; + uint32_t crc32; + uint32_t compressedSize; + uint32_t uncompressedSize; + std::string filename; + }; + + void zip( + const std::string& filename, + const Reader& reader, + const WriterPtr& writer, + ZipFileRecord& outRecord); + + void zipFinalise( + const std::vector& records, + const WriterPtr& writer); +} + diff --git a/configure.ac b/configure.ac index 69c6c96..e37dfa4 100644 --- a/configure.ac +++ b/configure.ac @@ -15,16 +15,30 @@ # You should have received a copy of the GNU General Public License # along with libzipper. If not, see . -AC_INIT([libzipper], [1.0.0], [michael@codesrc.com]) +AC_INIT([libzipper], m4_esyscmd_s([cat VERSION]), [michael@codesrc.com]) AC_CANONICAL_HOST AC_CANONICAL_TARGET AM_INIT_AUTOMAKE([foreign]) AC_CONFIG_HEADERS([autoconfig.h]) -AC_CONFIG_FILES([Makefile]) +AC_CONFIG_FILES([Makefile Doxyfile]) + +AC_SUBST([libzipper_version], m4_esyscmd_s([cat VERSION])) AC_PROG_CXX AC_PROG_LIBTOOL +DX_DOXYGEN_FEATURE([ON]) +DX_HTML_FEATURE([ON]) +DX_CHM_FEATURE(OFF) +DX_CHI_FEATURE(OFF) +DX_MAN_FEATURE(OFF) +DX_RTF_FEATURE(OFF) +DX_XML_FEATURE(OFF) +DX_PDF_FEATURE(OFF) +DX_PS_FEATURE(OFF) + +DX_INIT_DOXYGEN([libzipper], [Doxyfile], [doc]) + PKG_CHECK_MODULES([ZLIB], [zlib >= 1.2.3],, AC_MSG_ERROR([zlib 1.2.3 or newer not found.]) ) diff --git a/doxygen.am b/doxygen.am new file mode 100644 index 0000000..a46b5c2 --- /dev/null +++ b/doxygen.am @@ -0,0 +1,157 @@ +## --------------------------------- ## +## Format-independent Doxygen rules. ## +## --------------------------------- ## + +if DX_COND_doc + +## ------------------------------- ## +## Rules specific for HTML output. ## +## ------------------------------- ## + +if DX_COND_html + +DX_CLEAN_HTML = @DX_DOCDIR@/html + +endif DX_COND_html + +## ------------------------------ ## +## Rules specific for CHM output. ## +## ------------------------------ ## + +if DX_COND_chm + +DX_CLEAN_CHM = @DX_DOCDIR@/chm + +if DX_COND_chi + +DX_CLEAN_CHI = @DX_DOCDIR@/@PACKAGE@.chi + +endif DX_COND_chi + +endif DX_COND_chm + +## ------------------------------ ## +## Rules specific for MAN output. ## +## ------------------------------ ## + +if DX_COND_man + +DX_CLEAN_MAN = @DX_DOCDIR@/man + +endif DX_COND_man + +## ------------------------------ ## +## Rules specific for RTF output. ## +## ------------------------------ ## + +if DX_COND_rtf + +DX_CLEAN_RTF = @DX_DOCDIR@/rtf + +endif DX_COND_rtf + +## ------------------------------ ## +## Rules specific for XML output. ## +## ------------------------------ ## + +if DX_COND_xml + +DX_CLEAN_XML = @DX_DOCDIR@/xml + +endif DX_COND_xml + +## ----------------------------- ## +## Rules specific for PS output. ## +## ----------------------------- ## + +if DX_COND_ps + +DX_CLEAN_PS = @DX_DOCDIR@/@PACKAGE@.ps + +DX_PS_GOAL = doxygen-ps + +doxygen-ps: @DX_DOCDIR@/@PACKAGE@.ps + +@DX_DOCDIR@/@PACKAGE@.ps: @DX_DOCDIR@/@PACKAGE@.tag + cd @DX_DOCDIR@/latex; \ + rm -f *.aux *.toc *.idx *.ind *.ilg *.log *.out; \ + $(DX_LATEX) refman.tex; \ + $(MAKEINDEX_PATH) refman.idx; \ + $(DX_LATEX) refman.tex; \ + countdown=5; \ + while $(DX_EGREP) 'Rerun (LaTeX|to get cross-references right)' \ + refman.log > /dev/null 2>&1 \ + && test $$countdown -gt 0; do \ + $(DX_LATEX) refman.tex; \ + countdown=`expr $$countdown - 1`; \ + done; \ + $(DX_DVIPS) -o ../@PACKAGE@.ps refman.dvi + +endif DX_COND_ps + +## ------------------------------ ## +## Rules specific for PDF output. ## +## ------------------------------ ## + +if DX_COND_pdf + +DX_CLEAN_PDF = @DX_DOCDIR@/@PACKAGE@.pdf + +DX_PDF_GOAL = doxygen-pdf + +doxygen-pdf: @DX_DOCDIR@/@PACKAGE@.pdf + +@DX_DOCDIR@/@PACKAGE@.pdf: @DX_DOCDIR@/@PACKAGE@.tag + cd @DX_DOCDIR@/latex; \ + rm -f *.aux *.toc *.idx *.ind *.ilg *.log *.out; \ + $(DX_PDFLATEX) refman.tex; \ + $(DX_MAKEINDEX) refman.idx; \ + $(DX_PDFLATEX) refman.tex; \ + countdown=5; \ + while $(DX_EGREP) 'Rerun (LaTeX|to get cross-references right)' \ + refman.log > /dev/null 2>&1 \ + && test $$countdown -gt 0; do \ + $(DX_PDFLATEX) refman.tex; \ + countdown=`expr $$countdown - 1`; \ + done; \ + mv refman.pdf ../@PACKAGE@.pdf + +endif DX_COND_pdf + +## ------------------------------------------------- ## +## Rules specific for LaTeX (shared for PS and PDF). ## +## ------------------------------------------------- ## + +if DX_COND_latex + +DX_CLEAN_LATEX = @DX_DOCDIR@/latex + +endif DX_COND_latex + +.PHONY: doxygen-run doxygen-doc $(DX_PS_GOAL) $(DX_PDF_GOAL) + +.INTERMEDIATE: doxygen-run $(DX_PS_GOAL) $(DX_PDF_GOAL) + +doxygen-run: @DX_DOCDIR@/@PACKAGE@.tag + +doxygen-doc: doxygen-run $(DX_PS_GOAL) $(DX_PDF_GOAL) + +@DX_DOCDIR@/@PACKAGE@.tag: $(DX_CONFIG) $(pkginclude_HEADERS) + rm -rf @DX_DOCDIR@ + $(DX_ENV) $(DX_DOXYGEN) $(DX_CONFIG) + +DX_CLEANFILES = \ + @DX_DOCDIR@/@PACKAGE@.tag \ + -r \ + $(DX_CLEAN_HTML) \ + $(DX_CLEAN_CHM) \ + $(DX_CLEAN_CHI) \ + $(DX_CLEAN_MAN) \ + $(DX_CLEAN_RTF) \ + $(DX_CLEAN_XML) \ + $(DX_CLEAN_PS) \ + $(DX_CLEAN_PDF) \ + $(DX_CLEAN_LATEX) + +endif DX_COND_doc + diff --git a/util.hh b/util.hh new file mode 100644 index 0000000..fbce16a --- /dev/null +++ b/util.hh @@ -0,0 +1,32 @@ +// Copyright (C) 2011 Michael McMaster +// +// This file is part of libzipper. +// +// libzipper is free software: you can redistribute it and/or modify +// it under the terms of the GNU General Public License as published by +// the Free Software Foundation, either version 3 of the License, or +// (at your option) any later version. +// +// libzipper is distributed in the hope that it will be useful, +// but WITHOUT ANY WARRANTY; without even the implied warranty of +// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +// GNU General Public License for more details. +// +// You should have received a copy of the GNU General Public License +// along with libzipper. If not, see . + +#ifndef zipper_util_hh +#define zipper_util_hh + +namespace zipper +{ + template + struct + dummy_delete + { + void operator()(T*) {} + }; +} + +#endif + diff --git a/zipper.cc b/zipper.cc index 323aee8..97e0667 100644 --- a/zipper.cc +++ b/zipper.cc @@ -25,65 +25,22 @@ using namespace zipper; -class BasicBuffer : public Provider, public Consumer -{ -public: - BasicBuffer() - { - } - - BasicBuffer(const std::vector& buffer) : - m_buffer(buffer) - { - } - - const std::vector& getBuffer() const { return m_buffer; } - - virtual zoff64_t zip_getSize() const { return m_buffer.size(); } - - virtual void zip_readData( - zoff64_t offset, size_t bytes, uint8_t* dest - ) const - { - assert(offset + bytes <= m_buffer.size()); - for (size_t i(0); i < bytes; ++i) - { - dest[i] = m_buffer[offset + i]; - } - } - - virtual void zip_writeData( - size_t bytes, const uint8_t* data - ) - { - m_buffer.insert(m_buffer.begin(), data, data + bytes); - } -private: - std::vector m_buffer; -}; - - int main() { - int fd(open("test.zip", O_RDONLY)); - - std::vector buf(256*1024); - size_t bytes(::read(fd, &buf[0], buf.size())); - buf.resize(bytes); - - std::shared_ptr basicBuffer( - new BasicBuffer(buf) - ); - - Unzip unzip(basicBuffer); - std::vector entries(unzip.getEntries()); +/* + FileReader reader("test.zip"); + Decompressor decomp(reader); + std::vector entries(decomp.getEntries()); for (size_t f = 0; f < entries.size(); ++f) { - BasicBuffer out; - entries[f]->uncompress(out); - - int fout(open("zipOutput", O_WRONLY | O_CREAT | O_TRUNC, 0660)); - ::write(fout, &out.getBuffer()[0], out.getBuffer().size()); - close(fout); + FileWriter writer(entries[f]->getPath(), 0660); + entries[f]->decompress(writer); + } +*/ + FileReader reader("test"); + FileWriter writer("test.zip", 0660); + { + Compressor comp(Container_zip, writer); + comp.addFile(reader); } } diff --git a/zipper.hh b/zipper.hh index 9cd68a6..9964e95 100644 --- a/zipper.hh +++ b/zipper.hh @@ -15,82 +15,541 @@ // You should have received a copy of the GNU General Public License // along with libzipper. If not, see . +#ifndef zipper_hh +#define zipper_hh + #include #include #include #include -#include // size_t #include +#include // For mode_t + +/// \mainpage libzipper C++ (de)compression library +/// +/// \section intro Introduction +/// libzipper offers a flexible C++ interface for reading compressed files +/// in multiple formats. +/// +/// Homepage +/// +/// libzipper aims to provide applications a transparent method of accessing +/// compressed data. eg. libzipper is suited to reading XML config files that +/// are compressed to save space. +/// +/// libzipper is not a general-purpose archive management library, as it +/// does not provide access to the filesystem attributes of each file. +/// (ie. libzipper does not support the concepts of file owner, group, +/// permissions, or timestamps. +/// +/// \section formats Supported Formats +///
    +///
  • zip
    • +///
+/// +/// \section example_read Reading a compressed file into memory +/// +/// \code +/// #include +/// #include +/// #include +/// +/// class MemWriter : public zipper::Writer +/// { +/// public: +/// std::vector data; +/// virtual void writeData( +/// zsize_t offset, zsize_t bytes, const uint8_t* inData) +/// { +/// data.resize(std::max(offset + bytes, data.size())); +/// std::copy(inData, inData + bytes, &data[offset]); +/// } +/// virtual zsize_t getSize() const { return data.size(); } +/// }; +/// +/// std::vector readSavedGame(const std::string& filename) +/// { +/// // open the compressed input file. FileReader will throw an +/// // exception if an IO error occurs. +/// zipper::FileReader reader(filename); +/// +/// MemWriter writer; +/// +/// zipper::Decompressor decomp(reader); +/// +/// std::vector entries(decomp.getEntries()); +/// +/// if (!entries.empty()) +/// { +/// // Uncompress the first file. Will pass-though data as-is if the +/// // file is not compressed. +/// entries.front()->decompress(writer); +/// } +/// return writer.data; +/// } +/// +/// \endcode +/// +/// \section example_write Writing compressed files. +/// \code +/// #include +/// #include +/// #include +/// +/// class MemReader : public zipper::Reader +/// { +/// public: +/// MemReader(const vector& data) : m_data(data) {} +/// +/// virtual const std::string& getSourceName() const +/// { +/// static std::string Name("savedGame.dat"); +/// return Name; +/// } +/// +/// virtual zsize_t getSize() const { return m_data.size(); } +/// +/// virtual void readData( +/// zsize_t offset, zsize_t bytes, uint8_t* dest +/// ) const +/// { +/// std::copy(&m_data[offset], &m_data[offset + bytes], dest); +/// } +/// private: +/// std::vector m_data; +/// }; +/// +/// void writeSavedGame( +/// const std::string& filename, const std::vector& gameData +/// ) +/// { +/// zipper::FileWriter writer(filename); +/// zipper::Compressor comp(zipper::Container_zip, writer); +/// comp.addFile(MemReader(gameData)); +/// } +/// +/// \endcode +/// \namespace zipper +/// \brief The zipper namespace contains the libzipper public API. namespace zipper { - typedef uint64_t zoff64_t; + /// \typedef zsize_t + /// zsize_t should be used exclusively when dealing with file offsets + /// and sizes to support large files (>4Gb). + /// + /// Unlike size_t on some systems, zsize_t will be 64bit when compiling for + /// a 32bit target. + typedef uint64_t zsize_t; + + /// \enum ContainerFormat + /// ContainerFormat enumerates the compressed archive formats supported + /// by libzipper. + /// + /// An application can determine the supported formats by iterating + /// over the Container_begin to Container_end range. eg. + /// \code + /// for (int i = Container_begin; i < Container_end; ++i) + /// { + /// const Container& container(getContainer(ContainerFormat(i))); + /// } + /// \endcode + enum ContainerFormat + { + /// Iteration marker + Container_begin = 0, + + /// No container (eg. plain text) + Container_none = 0, + + /// ZIP + Container_zip, + + /// gzip. + Container_gzip, + + /// Iteration marker + Container_end + }; - class ZipException : public std::runtime_error + /// \struct Container + /// Provides libzipper capability details for a compressed archive + /// format. + /// \see getContainer + struct Container + { + /// \enum CapabilityBits allows a bitmask to be specified with a + /// combination of boolean flags. + enum CapabilityBits + { + /// Compression bit is set if the format is usable with Compressor + Compression = 1, + + /// Decompression bit is set if the format is usable with + /// Decompressor + Decompression = 2, + + /// EmbeddedFilenames bit is set if CompressedFile::getPath() is + /// supported + EmbeddedFilenames = 4, + + /// Archive bit is set if multiple compressed files may exist in + /// a single container. + Archive = 8, + + /// FileSize bit is set if the uncompressed size for each + /// compressed file is recorded in the container. + FileSize = 16 + }; + + /// %Container Type + ContainerFormat format; + + /// %Container Internet Media Type (aka MIME type). + /// eg. "application/zip" + std::string mediaType; + + /// Bitmask comprised of CapabilityBits enum values. + uint32_t capabilities; + }; + + /// \brief Returns the capability details of the given format. + const Container& getContainer(ContainerFormat format); + + /// \brief Base class for all exceptions thrown by libzipper + class Exception : public std::runtime_error { public: - ZipException(const std::string& what); + /// Exception ctor + /// \param what A description of the error encountered. + Exception(const std::string& what); }; - class ZipFormatException : public ZipException + /// \brief Exception thrown when the input data does not match + /// the expected Container format. + class FormatException : public Exception { public: - ZipFormatException(const std::string& what); + /// FormatException ctor + /// \param what A description of the error encountered. + FormatException(const std::string& what); }; - class ZipUnsupportedException : public ZipException + /// \brief Exception thrown when a Reader or Writer instance is unable + /// to satisfy an IO request due to an external error. + class IOException : public Exception { public: - ZipUnsupportedException(const std::string& what); + /// IOException ctor + /// \param what A description of the error encountered. + IOException(const std::string& what); }; - class Provider + /// \brief Exception thrown when an operation is requested on a compressed + /// archive that libzipper does not implement. + /// + /// This exception may be thrown even if libzipper advertises general + /// support for the Container format. eg. libzipper supports most + /// ZIP files, but an UnsupportedException will be thrown if given an + /// encrypted ZIP file. + class UnsupportedException : public Exception { public: - virtual ~Provider(); + /// UnsupportedException ctor + /// \param what A description of the error encountered. + UnsupportedException(const std::string& what); + }; - virtual zoff64_t zip_getSize() const = 0; + /// \brief Reader supplies input data to the compression/decompression + /// functions. + /// + /// Normally, an application using libzipper provides the Reader + /// implementation. The implementation could supply data from files, + /// in-memory buffers, or it could be generated on-the-fly. + /// + /// The Reader implementation must support random access, and must + /// determine at creation time the number of bytes available. The + /// Reader interface is not suitable for use with streaming data. + class Reader + { + public: + /// Reader dtor + virtual ~Reader(); - virtual void zip_readData( - zoff64_t offset, size_t bytes, uint8_t* dest + /// Returns a name for this source of the data. + /// + /// For file-based Reader implementations, this would normally be + /// the input filename. + virtual const std::string& getSourceName() const = 0; + + /// Returns the number of bytes available via readData() + /// + /// \invariant getSize() is stable throughout the lifetime + /// of the Reader instance. + virtual zsize_t getSize() const = 0; + + /// Copies data into the dest buffer + /// + /// An exception must be thrown if it is not possible to copy the + /// requested data into the supplied buffer (eg. file IO error). + /// + /// \pre offset + bytes <= getSize() + /// + /// \param offset Number of bytes to skip at the front of the data + /// source. + /// \param bytes Number of bytes to copy + /// \param dest Destination buffer. + /// + virtual void readData( + zsize_t offset, zsize_t bytes, uint8_t* dest ) const = 0; }; - typedef std::shared_ptr ProviderPtr; - class Consumer + /// \brief FileReader is a file-based implementation of the Reader + /// interface. + class FileReader : public Reader { public: - virtual ~Consumer(); + /// Read data from the supplied file. + FileReader(const std::string& filename); + + /// Read data from the supplied file. + /// + /// \param filename The value used by getSourceName(). This name + /// is arbitary, and does not need to be related to fd. + /// + /// \param fd The descriptor to source data from. The descriptor + /// must be open for reading, blocking, and seekable (ie. lseek(2)). + /// + /// \param closeFd If true, fd will be closed by this object + /// when it is no longer needed. + FileReader(const std::string& filename, int fd, bool closeFd); + + /// FileReader dtor + virtual ~FileReader(); - virtual void zip_writeData( - size_t bytes, const uint8_t* data + /// Inherited from Reader + virtual const std::string& getSourceName() const; + + /// Inherited from Reader + virtual zsize_t getSize() const; + + /// Inherited from Reader + virtual void readData( + zsize_t offset, zsize_t bytes, uint8_t* dest + ) const; + private: + FileReader(const FileReader&); + FileReader& operator=(const FileReader&); + + class FileReaderImpl; + FileReaderImpl* m_impl; + }; + + /// \typedef ReaderPtr + /// A shared pointer to a Reader + typedef std::shared_ptr ReaderPtr; + + /// \brief Writer accepts output data from the compression/decompression + /// functions. + /// + /// Normally, an application using libzipper provides the Writer + /// implementation. The implementation could write data to files, + /// in-memory buffers, or it could be simply discarded. + /// + /// The Writer implementation needs only to support sequential access. + class Writer + { + public: + /// Writer dtor + virtual ~Writer(); + + /// Returns the size of the written data. + virtual zsize_t getSize() const = 0; + + /// Accepts output from libzipper + /// + /// An exception must be thrown if it is not possible to accept + /// given data. (eg. file IO error). + /// + /// \param offset Number of bytes to skip at the front of the data + /// source. Skipped bytes will contain null characters if not already + /// assigned a value. + /// \param bytes Number of bytes in data + /// \param data Output from libzipper. + /// + virtual void writeData( + zsize_t offset, zsize_t bytes, const uint8_t* data ) = 0; }; + /// \typedef WriterPtr + /// A shared pointer to a Writer + typedef std::shared_ptr WriterPtr; + + /// \brief FileWrter is a file-based implementation of the Writer + /// interface. + class FileWriter : public Writer + { + public: + /// Write data to the supplied file. + /// If the file already exists, it will be truncated. + /// If the file does not exist, it will be created with the + /// given permissions. + /// + /// \param filename The file to open for writing. + /// + /// \param createPermissions The permissions set on the file if it is to + /// be created. + FileWriter(const std::string& filename, mode_t createPermissions); + + /// Write data to the supplied file. + /// + /// \param filename The filename reported in any exception error + /// messages. This name is arbitary, and does not need to be + /// related to fd. + /// + /// \param fd The descriptor to write data to. The descriptor + /// must be open for writing in blocking mode. + /// + /// \param closeFd If true, fd will be closed by this object + /// when it is no longer needed. + FileWriter(const std::string& filename, int fd, bool closeFd); + + /// FileWriter dtor + virtual ~FileWriter(); + + /// Inherited from Writer + virtual zsize_t getSize() const; + + /// Inherited from Writer + virtual void writeData( + zsize_t offset, zsize_t bytes, const uint8_t* data + ); + private: + FileWriter(const FileWriter&); + FileWriter& operator=(const FileWriter&); + + class FileWriterImpl; + FileWriterImpl* m_impl; + }; + + /// \brief CompressedFile represents an entry within a compressed archive. + /// + /// CompressedFile instances are created by Decompressor, and allow + /// selectively extracting the contents of an archive. class CompressedFile { public: + /// CompressedFile dtor virtual ~CompressedFile(); - virtual bool isValid() const = 0; - virtual void uncompress(Consumer& consumer) = 0; + + /// Return true if decompress is likely to succeed. + /// + /// isDecompressSupported may return false if libzipper doesn't know + /// how to deal with the compressed data. eg. encrypted files, + /// or ZIP files compressed with non-standard schemes. + virtual bool isDecompressSupported() const = 0; + + /// Decompress the file, and store the results via the given + /// writer object. + virtual void decompress(Writer& writer) = 0; + + /// Return the file path of the compressed file. + /// + /// Unix-style path separaters ('/') are returned, even if the + /// archive was created under an alternative OS. + virtual const std::string& getPath() const = 0; + + /// Return the compressed size of the file + /// + /// getCompressedSize() will return -1 of the FileSize capability + /// bit of the container is false. + virtual zsize_t getCompressedSize() const = 0; + + /// Return the uncompressed size of the file + /// + /// The decompress method will pass exactly this number of bytes + /// to the Writer. + /// + /// getUncompressedSize() will return -1 of the FileSize capability + /// bit of the container is false. + virtual zsize_t getUncompressedSize() const = 0; }; + /// \typedef CompressedFilePtr + /// A shared pointer to a CompressedFile typedef std::shared_ptr CompressedFilePtr; -// NO! Rename to Decompress. We want this to work for -any- container! -// bz2, tar, iso, gz, rar -// Similarly, rename the exceptions. - class Unzip + /// \brief Decompressor detects the compressed archive type of the data, + /// and creates suitable CompressedFile instances to access the compressed + /// data. + class Decompressor { public: - Unzip(const ProviderPtr& provider); - ~Unzip(); + /// Create a decompressor from the data made available by reader. + Decompressor(const ReaderPtr& reader); + + /// Create a decompressor from the data made available by reader. + /// + /// \param reader must remain in scope for the lifetime of the + /// Decompressor, and lifetime of any CompressedFile objects returned + /// from getEntries() + Decompressor(Reader& reader); + + /// Decompressor dtor + ~Decompressor(); + + /// Return the detected Container type of the compressed archive. + ContainerFormat getContainerFormat() const; + /// Return CompressedFile entries to represent the file entries within + /// a compressed archive. std::vector getEntries() const; private: - class UnzipImpl; - UnzipImpl* m_unzipper; + Decompressor(const Decompressor&); + Decompressor& operator=(const Decompressor&); + + class DecompressorImpl; + DecompressorImpl* m_decompressor; + }; + + /// \brief Compressor creates a compressed archive from the supplied + /// Reader objects. + /// data. + class Compressor + { + public: + /// Create a Compressor to output the given compressed archived format + /// to writer. + Compressor(ContainerFormat format, const WriterPtr& writer); + + /// Create a Compressor to output the given compressed archived format + /// to writer. + /// + /// \param writer must remain in scope for the lifetime of the + /// Compressor. + Compressor(ContainerFormat format, Writer& writer); + + /// \brief Compressor dtor + /// + /// Additional data may be passed to writer (given in ctor) to close + /// the compressed archive. + ~Compressor(); + + /// Compress the data given by reader, and add it to the compressed + /// archive. + void addFile(const Reader& reader); + + class CompressorImpl; + private: + Compressor(const Compressor&); + Compressor& operator=(const Compressor&); + + CompressorImpl* m_compressor; }; } +#endif +