chd 0.1.1

data/libchdr/deps/zlib-1.2.11/doc/txtvsbin.txt

@@ -0,0 +1,107 @@
+A Fast Method for Identifying Plain Text Files
+==============================================
+
+
+Introduction
+------------
+
+Given a file coming from an unknown source, it is sometimes desirable
+to find out whether the format of that file is plain text.  Although
+this may appear like a simple task, a fully accurate detection of the
+file type requires heavy-duty semantic analysis on the file contents.
+It is, however, possible to obtain satisfactory results by employing
+various heuristics.
+
+Previous versions of PKZip and other zip-compatible compression tools
+were using a crude detection scheme: if more than 80% (4/5) of the bytes
+found in a certain buffer are within the range [7..127], the file is
+labeled as plain text, otherwise it is labeled as binary.  A prominent
+limitation of this scheme is the restriction to Latin-based alphabets.
+Other alphabets, like Greek, Cyrillic or Asian, make extensive use of
+the bytes within the range [128..255], and texts using these alphabets
+are most often misidentified by this scheme; in other words, the rate
+of false negatives is sometimes too high, which means that the recall
+is low.  Another weakness of this scheme is a reduced precision, due to
+the false positives that may occur when binary files containing large
+amounts of textual characters are misidentified as plain text.
+
+In this article we propose a new, simple detection scheme that features
+a much increased precision and a near-100% recall.  This scheme is
+designed to work on ASCII, Unicode and other ASCII-derived alphabets,
+and it handles single-byte encodings (ISO-8859, MacRoman, KOI8, etc.)
+and variable-sized encodings (ISO-2022, UTF-8, etc.).  Wider encodings
+(UCS-2/UTF-16 and UCS-4/UTF-32) are not handled, however.
+
+
+The Algorithm
+-------------
+
+The algorithm works by dividing the set of bytecodes [0..255] into three
+categories:
+- The white list of textual bytecodes:
+  9 (TAB), 10 (LF), 13 (CR), 32 (SPACE) to 255.
+- The gray list of tolerated bytecodes:
+  7 (BEL), 8 (BS), 11 (VT), 12 (FF), 26 (SUB), 27 (ESC).
+- The black list of undesired, non-textual bytecodes:
+  0 (NUL) to 6, 14 to 31.
+
+If a file contains at least one byte that belongs to the white list and
+no byte that belongs to the black list, then the file is categorized as
+plain text; otherwise, it is categorized as binary.  (The boundary case,
+when the file is empty, automatically falls into the latter category.)
+
+
+Rationale
+---------
+
+The idea behind this algorithm relies on two observations.
+
+The first observation is that, although the full range of 7-bit codes
+[0..127] is properly specified by the ASCII standard, most control
+characters in the range [0..31] are not used in practice.  The only
+widely-used, almost universally-portable control codes are 9 (TAB),
+10 (LF) and 13 (CR).  There are a few more control codes that are
+recognized on a reduced range of platforms and text viewers/editors:
+7 (BEL), 8 (BS), 11 (VT), 12 (FF), 26 (SUB) and 27 (ESC); but these
+codes are rarely (if ever) used alone, without being accompanied by
+some printable text.  Even the newer, portable text formats such as
+XML avoid using control characters outside the list mentioned here.
+
+The second observation is that most of the binary files tend to contain
+control characters, especially 0 (NUL).  Even though the older text
+detection schemes observe the presence of non-ASCII codes from the range
+[128..255], the precision rarely has to suffer if this upper range is
+labeled as textual, because the files that are genuinely binary tend to
+contain both control characters and codes from the upper range.  On the
+other hand, the upper range needs to be labeled as textual, because it
+is used by virtually all ASCII extensions.  In particular, this range is
+used for encoding non-Latin scripts.
+
+Since there is no counting involved, other than simply observing the
+presence or the absence of some byte values, the algorithm produces
+consistent results, regardless what alphabet encoding is being used.
+(If counting were involved, it could be possible to obtain different
+results on a text encoded, say, using ISO-8859-16 versus UTF-8.)
+
+There is an extra category of plain text files that are "polluted" with
+one or more black-listed codes, either by mistake or by peculiar design
+considerations.  In such cases, a scheme that tolerates a small fraction
+of black-listed codes would provide an increased recall (i.e. more true
+positives).  This, however, incurs a reduced precision overall, since
+false positives are more likely to appear in binary files that contain
+large chunks of textual data.  Furthermore, "polluted" plain text should
+be regarded as binary by general-purpose text detection schemes, because
+general-purpose text processing algorithms might not be applicable.
+Under this premise, it is safe to say that our detection method provides
+a near-100% recall.
+
+Experiments have been run on many files coming from various platforms
+and applications.  We tried plain text files, system logs, source code,
+formatted office documents, compiled object code, etc.  The results
+confirm the optimistic assumptions about the capabilities of this
+algorithm.
+
+
+--
+Cosmin Truta
+Last updated: 2006-May-28

data/libchdr/deps/zlib-1.2.11/gzclose.c

@@ -0,0 +1,25 @@
+/* gzclose.c -- zlib gzclose() function
+ * Copyright (C) 2004, 2010 Mark Adler
+ * For conditions of distribution and use, see copyright notice in zlib.h
+ */
+
+#include "gzguts.h"
+
+/* gzclose() is in a separate file so that it is linked in only if it is used.
+   That way the other gzclose functions can be used instead to avoid linking in
+   unneeded compression or decompression routines. */
+int ZEXPORT gzclose(file)
+    gzFile file;
+{
+#ifndef NO_GZCOMPRESS
+    gz_statep state;
+
+    if (file == NULL)
+        return Z_STREAM_ERROR;
+    state = (gz_statep)file;
+
+    return state->mode == GZ_READ ? gzclose_r(file) : gzclose_w(file);
+#else
+    return gzclose_r(file);
+#endif
+}

data/libchdr/deps/zlib-1.2.11/gzguts.h

@@ -0,0 +1,218 @@
+/* gzguts.h -- zlib internal header definitions for gz* operations
+ * Copyright (C) 2004, 2005, 2010, 2011, 2012, 2013, 2016 Mark Adler
+ * For conditions of distribution and use, see copyright notice in zlib.h
+ */
+
+#ifdef _LARGEFILE64_SOURCE
+#  ifndef _LARGEFILE_SOURCE
+#    define _LARGEFILE_SOURCE 1
+#  endif
+#  ifdef _FILE_OFFSET_BITS
+#    undef _FILE_OFFSET_BITS
+#  endif
+#endif
+
+#ifdef HAVE_HIDDEN
+#  define ZLIB_INTERNAL __attribute__((visibility ("hidden")))
+#else
+#  define ZLIB_INTERNAL
+#endif
+
+#include <stdio.h>
+#include "zlib.h"
+#ifdef STDC
+#  include <string.h>
+#  include <stdlib.h>
+#  include <limits.h>
+#endif
+
+#ifndef _POSIX_SOURCE
+#  define _POSIX_SOURCE
+#endif
+#include <fcntl.h>
+
+#ifdef _WIN32
+#  include <stddef.h>
+#endif
+
+#if defined(__TURBOC__) || defined(_MSC_VER) || defined(_WIN32)
+#  include <io.h>
+#endif
+
+#if defined(_WIN32) || defined(__CYGWIN__)
+#  define WIDECHAR
+#endif
+
+#ifdef WINAPI_FAMILY
+#  define open _open
+#  define read _read
+#  define write _write
+#  define close _close
+#endif
+
+#ifdef NO_DEFLATE       /* for compatibility with old definition */
+#  define NO_GZCOMPRESS
+#endif
+
+#if defined(STDC99) || (defined(__TURBOC__) && __TURBOC__ >= 0x550)
+#  ifndef HAVE_VSNPRINTF
+#    define HAVE_VSNPRINTF
+#  endif
+#endif
+
+#if defined(__CYGWIN__)
+#  ifndef HAVE_VSNPRINTF
+#    define HAVE_VSNPRINTF
+#  endif
+#endif
+
+#if defined(MSDOS) && defined(__BORLANDC__) && (BORLANDC > 0x410)
+#  ifndef HAVE_VSNPRINTF
+#    define HAVE_VSNPRINTF
+#  endif
+#endif
+
+#ifndef HAVE_VSNPRINTF
+#  ifdef MSDOS
+/* vsnprintf may exist on some MS-DOS compilers (DJGPP?),
+   but for now we just assume it doesn't. */
+#    define NO_vsnprintf
+#  endif
+#  ifdef __TURBOC__
+#    define NO_vsnprintf
+#  endif
+#  ifdef WIN32
+/* In Win32, vsnprintf is available as the "non-ANSI" _vsnprintf. */
+#    if !defined(vsnprintf) && !defined(NO_vsnprintf)
+#      if !defined(_MSC_VER) || ( defined(_MSC_VER) && _MSC_VER < 1500 )
+#         define vsnprintf _vsnprintf
+#      endif
+#    endif
+#  endif
+#  ifdef __SASC
+#    define NO_vsnprintf
+#  endif
+#  ifdef VMS
+#    define NO_vsnprintf
+#  endif
+#  ifdef __OS400__
+#    define NO_vsnprintf
+#  endif
+#  ifdef __MVS__
+#    define NO_vsnprintf
+#  endif
+#endif
+
+/* unlike snprintf (which is required in C99), _snprintf does not guarantee
+   null termination of the result -- however this is only used in gzlib.c where
+   the result is assured to fit in the space provided */
+#if defined(_MSC_VER) && _MSC_VER < 1900
+#  define snprintf _snprintf
+#endif
+
+#ifndef local
+#  define local static
+#endif
+/* since "static" is used to mean two completely different things in C, we
+   define "local" for the non-static meaning of "static", for readability
+   (compile with -Dlocal if your debugger can't find static symbols) */
+
+/* gz* functions always use library allocation functions */
+#ifndef STDC
+  extern voidp  malloc OF((uInt size));
+  extern void   free   OF((voidpf ptr));
+#endif
+
+/* get errno and strerror definition */
+#if defined UNDER_CE
+#  include <windows.h>
+#  define zstrerror() gz_strwinerror((DWORD)GetLastError())
+#else
+#  ifndef NO_STRERROR
+#    include <errno.h>
+#    define zstrerror() strerror(errno)
+#  else
+#    define zstrerror() "stdio error (consult errno)"
+#  endif
+#endif
+
+/* provide prototypes for these when building zlib without LFS */
+#if !defined(_LARGEFILE64_SOURCE) || _LFS64_LARGEFILE-0 == 0
+    ZEXTERN gzFile ZEXPORT gzopen64 OF((const char *, const char *));
+    ZEXTERN z_off64_t ZEXPORT gzseek64 OF((gzFile, z_off64_t, int));
+    ZEXTERN z_off64_t ZEXPORT gztell64 OF((gzFile));
+    ZEXTERN z_off64_t ZEXPORT gzoffset64 OF((gzFile));
+#endif
+
+/* default memLevel */
+#if MAX_MEM_LEVEL >= 8
+#  define DEF_MEM_LEVEL 8
+#else
+#  define DEF_MEM_LEVEL  MAX_MEM_LEVEL
+#endif
+
+/* default i/o buffer size -- double this for output when reading (this and
+   twice this must be able to fit in an unsigned type) */
+#define GZBUFSIZE 8192
+
+/* gzip modes, also provide a little integrity check on the passed structure */
+#define GZ_NONE 0
+#define GZ_READ 7247
+#define GZ_WRITE 31153
+#define GZ_APPEND 1     /* mode set to GZ_WRITE after the file is opened */
+
+/* values for gz_state how */
+#define LOOK 0      /* look for a gzip header */
+#define COPY 1      /* copy input directly */
+#define GZIP 2      /* decompress a gzip stream */
+
+/* internal gzip file state data structure */
+typedef struct {
+        /* exposed contents for gzgetc() macro */
+    struct gzFile_s x;      /* "x" for exposed */
+                            /* x.have: number of bytes available at x.next */
+                            /* x.next: next output data to deliver or write */
+                            /* x.pos: current position in uncompressed data */
+        /* used for both reading and writing */
+    int mode;               /* see gzip modes above */
+    int fd;                 /* file descriptor */
+    char *path;             /* path or fd for error messages */
+    unsigned size;          /* buffer size, zero if not allocated yet */
+    unsigned want;          /* requested buffer size, default is GZBUFSIZE */
+    unsigned char *in;      /* input buffer (double-sized when writing) */
+    unsigned char *out;     /* output buffer (double-sized when reading) */
+    int direct;             /* 0 if processing gzip, 1 if transparent */
+        /* just for reading */
+    int how;                /* 0: get header, 1: copy, 2: decompress */
+    z_off64_t start;        /* where the gzip data started, for rewinding */
+    int eof;                /* true if end of input file reached */
+    int past;               /* true if read requested past end */
+        /* just for writing */
+    int level;              /* compression level */
+    int strategy;           /* compression strategy */
+        /* seek request */
+    z_off64_t skip;         /* amount to skip (already rewound if backwards) */
+    int seek;               /* true if seek request pending */
+        /* error information */
+    int err;                /* error code */
+    char *msg;              /* error message */
+        /* zlib inflate or deflate stream */
+    z_stream strm;          /* stream structure in-place (not a pointer) */
+} gz_state;
+typedef gz_state FAR *gz_statep;
+
+/* shared functions */
+void ZLIB_INTERNAL gz_error OF((gz_statep, int, const char *));
+#if defined UNDER_CE
+char ZLIB_INTERNAL *gz_strwinerror OF((DWORD error));
+#endif
+
+/* GT_OFF(x), where x is an unsigned value, is true if x > maximum z_off64_t
+   value -- needed when comparing unsigned to z_off64_t, which is signed
+   (possible z_off64_t types off_t, off64_t, and long are all signed) */
+#ifdef INT_MAX
+#  define GT_OFF(x) (sizeof(int) == sizeof(z_off64_t) && (x) > INT_MAX)
+#else
+unsigned ZLIB_INTERNAL gz_intmax OF((void));
+#  define GT_OFF(x) (sizeof(int) == sizeof(z_off64_t) && (x) > gz_intmax())
+#endif