Add support for 'repairing' damaged PDF files (Issue #45)

CHANGES.md

@@ -8,6 +8,7 @@ v1.5.0 - YYYY-MM-DD
 - Added `pdfioFileCreateICCObjFromData` API.
 - Added `pdfioFileGetModDate()` API (Issue #88)
 - Added support for using libpng to embed PNG images in PDF output (Issue #90)
+- Now support opening damaged PDF files (Issue #45)
 - Updated the pdf2txt example to support font encodings.
 
 

Makefile.in

@@ -15,7 +15,7 @@
 .SILENT:
 
 
-# Version number...
+# Version numbers...
 PDFIO_VERSION		=	@PDFIO_VERSION@
 PDFIO_VERSION_MAJOR	=	@PDFIO_VERSION_MAJOR@
 PDFIO_VERSION_MINOR	=	@PDFIO_VERSION_MINOR@

makesrcdist

@@ -21,40 +21,60 @@ if test $# != 1; then
     exit 1
 fi
 
+status=0
 version=$1
+version_major=$(echo $1 | awk -F. '{print $1}')
+version_minor=$(echo $1 | awk -F. '{print $2}')
 
 # Check that version number has been updated everywhere...
 if test $(grep AC_INIT configure.ac | awk '{print $2}') != "[$version],"; then
     echo "Still need to update AC_INIT version in 'configure.ac'."
-    exit 1
+    status=1
 fi
 
 if test $(head -4 CHANGES.md | tail -1 | awk '{print $1}') != "v$version"; then
     echo "Still need to update CHANGES.md version number."
-    exit 1
+    status=1
 fi
 if test $(head -4 CHANGES.md | tail -1 | awk '{print $3}') = "YYYY-MM-DD"; then
     echo "Still need to update CHANGES.md release date."
-    exit 1
+    status=1
 fi
 
 if test $(grep PDFIO_VERSION= configure | awk -F \" '{print $2}') != "$version"; then
     echo "Still need to run 'autoconf -f'."
-    exit 1
+    status=1
 fi
 
 if test $(grep '<version>' pdfio_native.nuspec | sed -E -e '1,$s/^.*<version>([0-9.]+).*$/\1/') != "$version"; then
     echo "Still need to update version in 'pdfio_native.nuspec'."
-    exit 1
+    status=1
 fi
 
 if test $(grep '<version>' pdfio_native.redist.nuspec | sed -E -e '1,$s/^.*<version>([0-9.]+).*$/\1/') != "$version"; then
     echo "Still need to update version in 'pdfio_native.redist.nuspec'."
-    exit 1
+    status=1
 fi
 
 if test $(grep PDFIO_VERSION pdfio.h | awk -F \" '{print $2}') != "$version"; then
     echo "Still need to update PDFIO_VERSION in 'pdfio.h'."
+    status=1
+fi
+if test $(grep PDFIO_VERSION_MAJOR pdfio.h | awk '{print $4}') != "$version_major"; then
+    echo "Still need to update PDFIO_VERSION_MAJOR in 'pdfio.h'."
+    status=1
+fi
+if test $(grep PDFIO_VERSION_MINOR pdfio.h | awk '{print $4}') != "$version_minor"; then
+    echo "Still need to update PDFIO_VERSION_MINOR in 'pdfio.h'."
+    status=1
+fi
+
+if test $(grep VERSION pdfio1.def | awk '{print $2}') != "$version_major.$version_minor"; then
+    echo "Still need to update VERSION in 'pdfio1.def'."
+    status=1
+fi
+
+if test $status = 1; then
     exit 1
 fi
 

pdfio-aes.c

@@ -1,7 +1,7 @@
 //
 // AES functions for PDFio.
 //
-// Copyright © 2021 by Michael R Sweet.
+// Copyright © 2021-2025 by Michael R Sweet.
 //
 // Licensed under Apache License v2.0.  See the file "LICENSE" for more
 // information.
@@ -76,18 +76,18 @@ static const uint8_t Rcon[11] =		// Round constants
 // Local functions...
 //
 
-static void	AddRoundKey(size_t round, state_t *state, const uint8_t *RoundKey);
-static void	SubBytes(state_t *state);
-static void	ShiftRows(state_t *state);
+static void	add_round_key(size_t round, state_t *state, const uint8_t *round_key);
+static void	sub_bytes(state_t *state);
+static void	shift_rows(state_t *state);
 static uint8_t	xtime(uint8_t x);
-static void	MixColumns(state_t *state);
-static uint8_t	Multiply(uint8_t x, uint8_t y);
-static void	InvMixColumns(state_t *state);
-static void	InvSubBytes(state_t *state);
-static void	InvShiftRows(state_t *state);
-static void	Cipher(state_t *state, const _pdfio_aes_t *ctx);
-static void	InvCipher(state_t *state, const _pdfio_aes_t *ctx);
-static void	XorWithIv(uint8_t *buf, const uint8_t *Iv);
+static void	mix_columns(state_t *state);
+static uint8_t	multiply(uint8_t x, uint8_t y);
+static void	inv_mix_columns(state_t *state);
+static void	inv_sub_bytes(state_t *state);
+static void	inv_shift_rows(state_t *state);
+static void	cipher(state_t *state, const _pdfio_aes_t *ctx);
+static void	inv_cipher(state_t *state, const _pdfio_aes_t *ctx);
+static void	xor_with_iv(uint8_t *buf, const uint8_t *Iv);
 
 
 //
@@ -106,7 +106,6 @@ _pdfioCryptoAESInit(
 		*rkptr,			// Current round_key values
 		*rkend,			// End of round_key values
 		tempa[4];		// Used for the column/row operations
-//  size_t	roundlen = keylen + 24;	// Length of round_key
   size_t	nwords = keylen / 4;	// Number of 32-bit words in key
 
 
@@ -188,8 +187,8 @@ _pdfioCryptoAESDecrypt(
   while (len > 15)
   {
     memcpy(next_iv, outbuffer, 16);
-    InvCipher((state_t *)outbuffer, ctx);
-    XorWithIv(outbuffer, ctx->iv);
+    inv_cipher((state_t *)outbuffer, ctx);
+    xor_with_iv(outbuffer, ctx->iv);
     memcpy(ctx->iv, next_iv, 16);
     outbuffer += 16;
     len -= 16;
@@ -231,8 +230,8 @@ _pdfioCryptoAESEncrypt(
 
   while (len > 15)
   {
-    XorWithIv(outbuffer, iv);
-    Cipher((state_t*)outbuffer, ctx);
+    xor_with_iv(outbuffer, iv);
+    cipher((state_t*)outbuffer, ctx);
     iv = outbuffer;
     outbuffer += 16;
     len -= 16;
@@ -244,8 +243,8 @@ _pdfioCryptoAESEncrypt(
     // Pad the final buffer with (16 - len)...
     memset(outbuffer + len, 16 - len, 16 - len);
 
-    XorWithIv(outbuffer, iv);
-    Cipher((state_t*)outbuffer, ctx);
+    xor_with_iv(outbuffer, iv);
+    cipher((state_t*)outbuffer, ctx);
     iv = outbuffer;
     outbytes += 16;
   }
@@ -257,24 +256,32 @@ _pdfioCryptoAESEncrypt(
 }
 
 
-// This function adds the round key to state.
+//
+// 'add_round_key()' - Add the round key to state.
+//
 // The round key is added to the state by an XOR function.
+//
+
 static void
-AddRoundKey(size_t round, state_t *state, const uint8_t *RoundKey)
+add_round_key(size_t        round,	// I - Which round
+              state_t       *state,	// I - Current state
+              const uint8_t *round_key)	// I - Key
 {
   unsigned	i;			// Looping var
   uint8_t	*sptr = (*state)[0];	// Pointer into state
 
 
-  for (RoundKey += round * 16, i = 16; i > 0; i --, sptr ++, RoundKey ++)
-    *sptr ^= *RoundKey;
+  for (round_key += round * 16, i = 16; i > 0; i --, sptr ++, round_key ++)
+    *sptr ^= *round_key;
 }
 
 
-// The SubBytes Function Substitutes the values in the
-// state matrix with values in an S-box.
+//
+// 'sub_bytes()' - Substitute the values in the state matrix with values in an S-box.
+//
+
 static void
-SubBytes(state_t *state)
+sub_bytes(state_t *state)		// I - Current state
 {
   unsigned	i;			// Looping var
   uint8_t	*sptr = (*state)[0];	// Pointer into state
@@ -284,11 +291,16 @@ SubBytes(state_t *state)
     *sptr = sbox[*sptr];
 }
 
-// The ShiftRows() function shifts the rows in the state to the left.
+
+//
+// 'shift_rows()' - Shift the rows in the state to the left.
+//
 // Each row is shifted with different offset.
 // Offset = Row number. So the first row is not shifted.
+//
+
 static void
-ShiftRows(state_t *state)
+shift_rows(state_t *state)		// I - Current state
 {
   uint8_t	*sptr = (*state)[0];	// Pointer into state
   uint8_t	temp;			// Temporary value
@@ -319,21 +331,29 @@ ShiftRows(state_t *state)
 }
 
 
-static uint8_t
-xtime(uint8_t x)
+//
+// 'xtime()' - Compute the AES xtime function.
+//
+
+static uint8_t				// O - xtime(x)
+xtime(uint8_t x)			// I - Column value
 {
   return ((uint8_t)((x << 1) ^ ((x >> 7) * 0x1b)));
 }
 
 
-// MixColumns function mixes the columns of the state matrix
+//
+// 'mix_columns()' - Mix the columns of the state matrix.
+//
+
 static void
-MixColumns(state_t *state)
+mix_columns(state_t *state)		// I - Current state
 {
   unsigned	i;			// Looping var
   uint8_t	*sptr = (*state)[0];	// Pointer into state
   uint8_t	Tmp, Tm, t;		// Temporary values
 
+
   for (i = 4; i > 0; i --, sptr += 4)
   {
     t       = sptr[0];
@@ -357,11 +377,15 @@ MixColumns(state_t *state)
 }
 
 
-// Multiply is used to multiply numbers in the field GF(2^8)
+//
+// 'multiply()' - Multiply numbers in the field GF(2^8)
+//
 // Note: The last call to xtime() is unneeded, but often ends up generating a smaller binary
 //       The compiler seems to be able to vectorize the operation better this way.
 //       See https://github.com/kokke/tiny-AES-c/pull/34
-static uint8_t Multiply(uint8_t x, uint8_t y)
+//
+
+static uint8_t multiply(uint8_t x, uint8_t y)
 {
   return (((y & 1) * x) ^
 	  ((y>>1 & 1) * xtime(x)) ^
@@ -371,11 +395,15 @@ static uint8_t Multiply(uint8_t x, uint8_t y)
 }
 
 
-// MixColumns function mixes the columns of the state matrix.
+//
+// 'mix_columns()' - Mix the columns of the state matrix.
+//
 // The method used to multiply may be difficult to understand for the inexperienced.
 // Please use the references to gain more information.
+//
+
 static void
-InvMixColumns(state_t *state)
+inv_mix_columns(state_t *state)		// I - Current state
 {
   unsigned	i;			// Looping var
   uint8_t	*sptr = (*state)[0];	// Pointer into state
@@ -389,18 +417,20 @@ InvMixColumns(state_t *state)
     c = sptr[2];
     d = sptr[3];
 
-    *sptr++ = Multiply(a, 0x0e) ^ Multiply(b, 0x0b) ^ Multiply(c, 0x0d) ^ Multiply(d, 0x09);
-    *sptr++ = Multiply(a, 0x09) ^ Multiply(b, 0x0e) ^ Multiply(c, 0x0b) ^ Multiply(d, 0x0d);
-    *sptr++ = Multiply(a, 0x0d) ^ Multiply(b, 0x09) ^ Multiply(c, 0x0e) ^ Multiply(d, 0x0b);
-    *sptr++ = Multiply(a, 0x0b) ^ Multiply(b, 0x0d) ^ Multiply(c, 0x09) ^ Multiply(d, 0x0e);
+    *sptr++ = multiply(a, 0x0e) ^ multiply(b, 0x0b) ^ multiply(c, 0x0d) ^ multiply(d, 0x09);
+    *sptr++ = multiply(a, 0x09) ^ multiply(b, 0x0e) ^ multiply(c, 0x0b) ^ multiply(d, 0x0d);
+    *sptr++ = multiply(a, 0x0d) ^ multiply(b, 0x09) ^ multiply(c, 0x0e) ^ multiply(d, 0x0b);
+    *sptr++ = multiply(a, 0x0b) ^ multiply(b, 0x0d) ^ multiply(c, 0x09) ^ multiply(d, 0x0e);
   }
 }
 
 
-// The SubBytes Function Substitutes the values in the
-// state matrix with values in an S-box.
+//
+// 'sub_bytes()' - Substitute the values in the state matrix with values in an S-box.
+//
+
 static void
-InvSubBytes(state_t *state)
+inv_sub_bytes(state_t *state)		// I - Current state
 {
   unsigned	i;			// Looping var
   uint8_t	*sptr = (*state)[0];	// Pointer into state
@@ -411,8 +441,12 @@ InvSubBytes(state_t *state)
 }
 
 
+//
+// 'inv_shift_rows()' - Shift the rows in the state to the right.
+//
+
 static void
-InvShiftRows(state_t *state)
+inv_shift_rows(state_t *state)		// I - Current state
 {
   uint8_t	*sptr = (*state)[0];	// Pointer into state
   uint8_t	temp;			// Temporary value
@@ -443,40 +477,52 @@ InvShiftRows(state_t *state)
 }
 
 
-// Cipher is the main function that encrypts the PlainText.
+//
+// 'cipher()' - Encrypt the PlainText.
+//
+
 static void
-Cipher(state_t *state, const _pdfio_aes_t *ctx)
+cipher(state_t            *state,	// I - Current state
+       const _pdfio_aes_t *ctx)		// I - AES context
 {
-  size_t round = 0;
+  size_t round = 0;			// Current round
+
 
   // Add the First round key to the state before starting the rounds.
-  AddRoundKey(0, state, ctx->round_key);
+  add_round_key(0, state, ctx->round_key);
 
   // There will be Nr rounds.
   // The first Nr-1 rounds are identical.
   // These Nr rounds are executed in the loop below.
-  // Last one without MixColumns()
+  // Last one without mix_columns()
   for (round = 1; round < ctx->round_size; round ++)
   {
-    SubBytes(state);
-    ShiftRows(state);
-    MixColumns(state);
-    AddRoundKey(round, state, ctx->round_key);
+    sub_bytes(state);
+    shift_rows(state);
+    mix_columns(state);
+    add_round_key(round, state, ctx->round_key);
   }
+
   // Add round key to last round
-  SubBytes(state);
-  ShiftRows(state);
-  AddRoundKey(ctx->round_size, state, ctx->round_key);
+  sub_bytes(state);
+  shift_rows(state);
+  add_round_key(ctx->round_size, state, ctx->round_key);
 }
 
 
+//
+// 'inv_cipher()' - Decrypt the CipherText.
+//
+
 static void
-InvCipher(state_t *state, const _pdfio_aes_t *ctx)
+inv_cipher(state_t            *state,	// I - Current state
+           const _pdfio_aes_t *ctx)	// I - AES context
 {
-  size_t round;
+  size_t round;				// Current round
+
 
   // Add the First round key to the state before starting the rounds.
-  AddRoundKey(ctx->round_size, state, ctx->round_key);
+  add_round_key(ctx->round_size, state, ctx->round_key);
 
   // There will be Nr rounds.
   // The first Nr-1 rounds are identical.
@@ -484,20 +530,25 @@ InvCipher(state_t *state, const _pdfio_aes_t *ctx)
   // Last one without InvMixColumn()
   for (round = ctx->round_size - 1; ; round --)
   {
-    InvShiftRows(state);
-    InvSubBytes(state);
-    AddRoundKey(round, state, ctx->round_key);
+    inv_shift_rows(state);
+    inv_sub_bytes(state);
+    add_round_key(round, state, ctx->round_key);
 
     if (round == 0)
       break;
 
-    InvMixColumns(state);
+    inv_mix_columns(state);
   }
 }
 
 
+//
+// 'xor_with_iv()' - XOR a block with the initialization vector.
+//
+
 static void
-XorWithIv(uint8_t *buf, const uint8_t *Iv)
+xor_with_iv(uint8_t       *buf,		// I - Block
+            const uint8_t *Iv)		// I - Initialization vector
 {
   // 16-byte block...
   *buf++ ^= *Iv++;

pdfio-file.c

@@ -25,6 +25,7 @@ static struct lconv	*get_lconv(void);
 static bool		load_obj_stream(pdfio_obj_t *obj);
 static bool		load_pages(pdfio_file_t *pdf, pdfio_obj_t *obj, size_t depth);
 static bool		load_xref(pdfio_file_t *pdf, off_t xref_offset, pdfio_password_cb_t password_cb, void *password_data);
+static bool		repair_xref(pdfio_file_t *pdf, pdfio_password_cb_t password_cb, void *password_data);
 static bool		write_pages(pdfio_file_t *pdf);
 static bool		write_trailer(pdfio_file_t *pdf);
 
@@ -1070,7 +1071,10 @@ pdfioFileOpen(
   xref_offset = (off_t)strtol(ptr + 9, NULL, 10);
 
   if (!load_xref(pdf, xref_offset, password_cb, password_cbdata))
-    goto error;
+  {
+    if (!repair_xref(pdf, password_cb, password_cbdata))
+      goto error;
+  }
 
   return (pdf);
 
@@ -2165,6 +2169,159 @@ load_xref(
 }
 
 
+//
+// 'repair_xref()' - Try to "repair" a PDF file and its cross-references...
+//
+
+static bool				// O - `true` on success, `false` on failure
+repair_xref(
+    pdfio_file_t        *pdf,		// I - PDF file
+    pdfio_password_cb_t password_cb,	// I - Password callback or `NULL` for none
+    void                *password_data)	// I - Password callback data, if any
+{
+  char		line[16384],		// Line from file
+		*ptr;			// Pointer into line
+  off_t		line_offset;		// Offset in file
+  intmax_t	number;			// Object number
+  int		generation;		// Generation number
+  size_t	i;			// Looping var
+  size_t	num_sobjs = 0;		// Number of object streams
+  pdfio_obj_t	*sobjs[16384];		// Object streams to load
+
+
+  // Read from the beginning of the file, looking for
+  if ((line_offset = _pdfioFileSeek(pdf, 0, SEEK_SET)) < 0)
+    return (false);
+
+  while (_pdfioFileGets(pdf, line, sizeof(line)))
+  {
+    // See if this is the start of an object...
+    if (line[0] >= '1' && line[0] <= '9')
+    {
+      // Maybe, look some more...
+      if ((number = strtoimax(line, &ptr, 10)) >= 1 && (generation = (int)strtol(ptr, &ptr, 10)) >= 0 && generation < 65536)
+      {
+        while (isspace(*ptr & 255))
+	  ptr ++;
+
+	if (!strncmp(ptr, "obj", 3))
+	{
+	  // Yes, start of an object...
+	  pdfio_obj_t	*obj;		// Object
+	  _pdfio_token_t tb;		// Token buffer/stack
+
+          PDFIO_DEBUG("OBJECT %ld %d at offset %ld\n", (long)number, generation, (long)line_offset);
+
+	  if ((obj = add_obj(pdf, (size_t)number, (unsigned short)generation, line_offset)) == NULL)
+	  {
+	    _pdfioFileError(pdf, "Unable to allocate memory for object.");
+	    return (false);
+	  }
+
+	  _pdfioTokenInit(&tb, pdf, (_pdfio_tconsume_cb_t)_pdfioFileConsume, (_pdfio_tpeek_cb_t)_pdfioFilePeek, pdf);
+
+	  if (!_pdfioValueRead(pdf, obj, &tb, &obj->value, 0))
+	  {
+	    _pdfioFileError(pdf, "Unable to read cross-reference stream dictionary.");
+	    return (false);
+	  }
+
+	  if (_pdfioTokenGet(&tb, line, sizeof(line)) && strcmp(line, "stream"))
+	  {
+	    const char *type = pdfioObjGetType(obj);
+					// Object type
+
+	    _pdfioTokenFlush(&tb);
+	    obj->stream_offset = _pdfioFileTell(pdf);
+
+	    if (type && !strcmp(type, "ObjStm") && num_sobjs < (sizeof(sobjs) / sizeof(sobjs[0])))
+	    {
+	      sobjs[num_sobjs] = obj;
+	      num_sobjs ++;
+	    }
+
+            if (type && !strcmp(type, "XRef") && !pdf->trailer_dict)
+            {
+              // Save the trailer dictionary...
+	      pdf->trailer_dict = pdfioObjGetDict(obj);
+	      pdf->encrypt_obj  = pdfioDictGetObj(pdf->trailer_dict, "Encrypt");
+	      pdf->id_array     = pdfioDictGetArray(pdf->trailer_dict, "ID");
+            }
+	  }
+	}
+      }
+    }
+    else if (!strncmp(line, "trailer", 7) && (!line[7] || isspace(line[7] & 255) || line[7] == '<'))
+    {
+      // Trailer dictionary
+      _pdfio_token_t tb;		// Token buffer/stack
+      _pdfio_value_t trailer;		// Trailer
+
+      if (line[7])
+      {
+	// Probably the start of the trailer dictionary, rewind the file so
+	// we can read it...
+	_pdfioFileSeek(pdf, line_offset + 7, SEEK_SET);
+      }
+
+      PDFIO_DEBUG("TRAILER at offset %ld\n", (long)line_offset);
+
+      _pdfioTokenInit(&tb, pdf, (_pdfio_tconsume_cb_t)_pdfioFileConsume, (_pdfio_tpeek_cb_t)_pdfioFilePeek, pdf);
+      if (!_pdfioValueRead(pdf, NULL, &tb, &trailer, 0))
+      {
+	_pdfioFileError(pdf, "Unable to read cross-reference stream dictionary.");
+	return (false);
+      }
+      else if (trailer.type != PDFIO_VALTYPE_DICT)
+      {
+	_pdfioFileError(pdf, "Trailer is not a dictionary.");
+	return (false);
+      }
+
+      _pdfioTokenFlush(&tb);
+
+      if (!pdf->trailer_dict)
+      {
+	// Save the trailer dictionary and grab the root (catalog) and info
+	// objects...
+	pdf->trailer_dict = trailer.value.dict;
+	pdf->encrypt_obj  = pdfioDictGetObj(pdf->trailer_dict, "Encrypt");
+	pdf->id_array     = pdfioDictGetArray(pdf->trailer_dict, "ID");
+      }
+    }
+
+    // Get the offset for the next line...
+    line_offset = _pdfioFileTell(pdf);
+  }
+
+  // If the trailer contains an Encrypt key, try unlocking the file...
+  if (pdf->encrypt_obj && !_pdfioCryptoUnlock(pdf, password_cb, password_data))
+    return (false);
+
+  // Load any stream objects...
+  for (i = 0; i < num_sobjs; i ++)
+  {
+    if (!load_obj_stream(sobjs[i]))
+      return (false);
+  }
+
+  // Once we have all of the xref tables loaded, get the important objects and
+  // build the pages array...
+  pdf->info_obj = pdfioDictGetObj(pdf->trailer_dict, "Info");
+
+  if ((pdf->root_obj = pdfioDictGetObj(pdf->trailer_dict, "Root")) == NULL)
+  {
+    _pdfioFileError(pdf, "Missing Root object.");
+    return (false);
+  }
+
+  PDFIO_DEBUG("repair_xref: Root=%p(%lu)\n", pdf->root_obj, (unsigned long)pdf->root_obj->number);
+
+  // Load pages...
+  return (load_pages(pdf, pdfioDictGetObj(pdfioObjGetDict(pdf->root_obj), "Pages"), 0));
+}
+
+
 //
 // 'write_pages()' - Write the PDF pages objects.
 //

pdfio-md5.c

@@ -1,7 +1,7 @@
 //
 // MD5 functions for PDFio.
 //
-// Copyright © 2021 by Michael R Sweet.
+// Copyright © 2021-2025 by Michael R Sweet.
 // Copyright © 1999 Aladdin Enterprises.  All rights reserved.
 //
 // This software is provided 'as-is', without any express or implied
@@ -108,231 +108,285 @@
 #define T63 0x2ad7d2bb
 #define T64 0xeb86d391
 
+
+//
+// Use the unoptimized (big-endian) implementation if we don't know the
+// endian-ness of the platform.
+//
+
+#ifdef __BYTE_ORDER__
+#  if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+#    define ARCH_IS_BIG_ENDIAN	0	// Use little endian optimized version
+#  else
+#    define ARCH_IS_BIG_ENDIAN	1	// Use generic version
+#  endif // __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+#elif !defined(ARCH_IS_BIG_ENDIAN)
+#  define ARCH_IS_BIG_ENDIAN	1	// Use generic version
+#endif // !ARCH_IS_BIG_ENDIAN
+
+
+//
+// 'md5_process()' - Hash a block of data.
+//
+
 static void
-md5_process(_pdfio_md5_t *pms, const uint8_t *data /*[64]*/)
+md5_process(_pdfio_md5_t  *pms,		// I - MD5 state
+            const uint8_t *data/*[64]*/)// I - Data
 {
-    uint32_t
-	a = pms->abcd[0], b = pms->abcd[1],
-	c = pms->abcd[2], d = pms->abcd[3];
-    uint32_t t;
+  uint32_t	a = pms->abcd[0],	// First word of state
+		b = pms->abcd[1],	// Second word of state
+		c = pms->abcd[2],	// Third word of state
+		d = pms->abcd[3];	// Fourth word of state
+  uint32_t	t;			// Temporary state
+
 
-#ifndef ARCH_IS_BIG_ENDIAN
-# define ARCH_IS_BIG_ENDIAN 1	/* slower, default implementation */
-#endif
 #if ARCH_IS_BIG_ENDIAN
+  // On big-endian machines, we must arrange the bytes in the right
+  // order.  (This also works on machines of unknown byte order.)
+  uint32_t	X[16];			// Little-endian representation
+  const uint8_t	*xp;			// Pointer into data
+  int		i;			// Looping var
 
-    /*
-     * On big-endian machines, we must arrange the bytes in the right
-     * order.  (This also works on machines of unknown byte order.)
-     */
-    uint32_t X[16];
-    const uint8_t *xp = data;
-    int i;
-
-    for (i = 0; i < 16; ++i, xp += 4)
-	X[i] = xp[0] + (unsigned)(xp[1] << 8) + (unsigned)(xp[2] << 16) + (unsigned)(xp[3] << 24);
+  for (i = 0, xp = data; i < 16; i ++, xp += 4)
+    X[i] = xp[0] + (unsigned)(xp[1] << 8) + (unsigned)(xp[2] << 16) + (unsigned)(xp[3] << 24);
 
 #else  /* !ARCH_IS_BIG_ENDIAN */
+  // On little-endian machines, we can process properly aligned data without copying it.
+  uint32_t	xbuf[16];		// Aligned buffer
+  const uint32_t *X;			// Pointer to little-endian representation
 
-    /*
-     * On little-endian machines, we can process properly aligned data
-     * without copying it.
-     */
-    uint32_t xbuf[16];
-    const uint32_t *X;
-
-    if (!((data - (const uint8_t *)0) & 3)) {
-	/* data are properly aligned */
-	X = (const uint32_t *)data;
-    } else {
-	/* not aligned */
-	memcpy(xbuf, data, 64);
-	X = xbuf;
-    }
-#endif
+  if (!((data - (const uint8_t *)0) & 3))
+  {
+    // data is properly aligned, use it directly...
+    X = (const uint32_t *)data;
+  }
+  else
+  {
+    // data is not aligned, copy to the aligned buffer...
+    memcpy(xbuf, data, 64);
+    X = xbuf;
+  }
+#endif // ARCH_IS_BIG_ENDIAN
 
 #define ROTATE_LEFT(x, n) (((x) << (n)) | ((x) >> (32 - (n))))
 
-    /* Round 1. */
-    /* Let [abcd k s i] denote the operation
-       a = b + ((a + F(b,c,d) + X[k] + T[i]) <<< s). */
-#define F(x, y, z) (((x) & (y)) | (~(x) & (z)))
-#define SET(a, b, c, d, k, s, Ti)\
-  t = a + F(b,c,d) + X[k] + Ti;\
-  a = ROTATE_LEFT(t, s) + b
-    /* Do the following 16 operations. */
-    SET(a, b, c, d,  0,  7,  T1);
-    SET(d, a, b, c,  1, 12,  T2);
-    SET(c, d, a, b,  2, 17,  T3);
-    SET(b, c, d, a,  3, 22,  T4);
-    SET(a, b, c, d,  4,  7,  T5);
-    SET(d, a, b, c,  5, 12,  T6);
-    SET(c, d, a, b,  6, 17,  T7);
-    SET(b, c, d, a,  7, 22,  T8);
-    SET(a, b, c, d,  8,  7,  T9);
-    SET(d, a, b, c,  9, 12, T10);
-    SET(c, d, a, b, 10, 17, T11);
-    SET(b, c, d, a, 11, 22, T12);
-    SET(a, b, c, d, 12,  7, T13);
-    SET(d, a, b, c, 13, 12, T14);
-    SET(c, d, a, b, 14, 17, T15);
-    SET(b, c, d, a, 15, 22, T16);
+  // Round 1.
+  // Let [abcd k s i] denote the operation
+  //   a = b + ((a + F(b,c,d) + X[k] + T[i]) <<< s).
+#define F(x, y, z)		(((x) & (y)) | (~(x) & (z)))
+#define SET(a, b, c, d, k, s, Ti) t = a + F(b,c,d) + X[k] + Ti; a = ROTATE_LEFT(t, s) + b
+
+  // Do the following 16 operations.
+  SET(a, b, c, d,  0,  7,  T1);
+  SET(d, a, b, c,  1, 12,  T2);
+  SET(c, d, a, b,  2, 17,  T3);
+  SET(b, c, d, a,  3, 22,  T4);
+  SET(a, b, c, d,  4,  7,  T5);
+  SET(d, a, b, c,  5, 12,  T6);
+  SET(c, d, a, b,  6, 17,  T7);
+  SET(b, c, d, a,  7, 22,  T8);
+  SET(a, b, c, d,  8,  7,  T9);
+  SET(d, a, b, c,  9, 12, T10);
+  SET(c, d, a, b, 10, 17, T11);
+  SET(b, c, d, a, 11, 22, T12);
+  SET(a, b, c, d, 12,  7, T13);
+  SET(d, a, b, c, 13, 12, T14);
+  SET(c, d, a, b, 14, 17, T15);
+  SET(b, c, d, a, 15, 22, T16);
+
 #undef SET
 
-     /* Round 2. */
-     /* Let [abcd k s i] denote the operation
-          a = b + ((a + G(b,c,d) + X[k] + T[i]) <<< s). */
-#define G(x, y, z) (((x) & (z)) | ((y) & ~(z)))
-#define SET(a, b, c, d, k, s, Ti)\
-  t = a + G(b,c,d) + X[k] + Ti;\
-  a = ROTATE_LEFT(t, s) + b
-     /* Do the following 16 operations. */
-    SET(a, b, c, d,  1,  5, T17);
-    SET(d, a, b, c,  6,  9, T18);
-    SET(c, d, a, b, 11, 14, T19);
-    SET(b, c, d, a,  0, 20, T20);
-    SET(a, b, c, d,  5,  5, T21);
-    SET(d, a, b, c, 10,  9, T22);
-    SET(c, d, a, b, 15, 14, T23);
-    SET(b, c, d, a,  4, 20, T24);
-    SET(a, b, c, d,  9,  5, T25);
-    SET(d, a, b, c, 14,  9, T26);
-    SET(c, d, a, b,  3, 14, T27);
-    SET(b, c, d, a,  8, 20, T28);
-    SET(a, b, c, d, 13,  5, T29);
-    SET(d, a, b, c,  2,  9, T30);
-    SET(c, d, a, b,  7, 14, T31);
-    SET(b, c, d, a, 12, 20, T32);
+  // Round 2.
+  // Let [abcd k s i] denote the operation
+  //   a = b + ((a + G(b,c,d) + X[k] + T[i]) <<< s).
+#define G(x, y, z)		(((x) & (z)) | ((y) & ~(z)))
+#define SET(a, b, c, d, k, s, Ti) t = a + G(b,c,d) + X[k] + Ti; a = ROTATE_LEFT(t, s) + b
+
+  // Do the following 16 operations.
+  SET(a, b, c, d,  1,  5, T17);
+  SET(d, a, b, c,  6,  9, T18);
+  SET(c, d, a, b, 11, 14, T19);
+  SET(b, c, d, a,  0, 20, T20);
+  SET(a, b, c, d,  5,  5, T21);
+  SET(d, a, b, c, 10,  9, T22);
+  SET(c, d, a, b, 15, 14, T23);
+  SET(b, c, d, a,  4, 20, T24);
+  SET(a, b, c, d,  9,  5, T25);
+  SET(d, a, b, c, 14,  9, T26);
+  SET(c, d, a, b,  3, 14, T27);
+  SET(b, c, d, a,  8, 20, T28);
+  SET(a, b, c, d, 13,  5, T29);
+  SET(d, a, b, c,  2,  9, T30);
+  SET(c, d, a, b,  7, 14, T31);
+  SET(b, c, d, a, 12, 20, T32);
+
 #undef SET
 
-     /* Round 3. */
-     /* Let [abcd k s t] denote the operation
-          a = b + ((a + H(b,c,d) + X[k] + T[i]) <<< s). */
-#define H(x, y, z) ((x) ^ (y) ^ (z))
-#define SET(a, b, c, d, k, s, Ti)\
-  t = a + H(b,c,d) + X[k] + Ti;\
-  a = ROTATE_LEFT(t, s) + b
-     /* Do the following 16 operations. */
-    SET(a, b, c, d,  5,  4, T33);
-    SET(d, a, b, c,  8, 11, T34);
-    SET(c, d, a, b, 11, 16, T35);
-    SET(b, c, d, a, 14, 23, T36);
-    SET(a, b, c, d,  1,  4, T37);
-    SET(d, a, b, c,  4, 11, T38);
-    SET(c, d, a, b,  7, 16, T39);
-    SET(b, c, d, a, 10, 23, T40);
-    SET(a, b, c, d, 13,  4, T41);
-    SET(d, a, b, c,  0, 11, T42);
-    SET(c, d, a, b,  3, 16, T43);
-    SET(b, c, d, a,  6, 23, T44);
-    SET(a, b, c, d,  9,  4, T45);
-    SET(d, a, b, c, 12, 11, T46);
-    SET(c, d, a, b, 15, 16, T47);
-    SET(b, c, d, a,  2, 23, T48);
+  // Round 3.
+  // Let [abcd k s t] denote the operation
+  //   a = b + ((a + H(b,c,d) + X[k] + T[i]) <<< s).
+#define H(x, y, z)		((x) ^ (y) ^ (z))
+#define SET(a, b, c, d, k, s, Ti) t = a + H(b,c,d) + X[k] + Ti; a = ROTATE_LEFT(t, s) + b
+
+  // Do the following 16 operations.
+  SET(a, b, c, d,  5,  4, T33);
+  SET(d, a, b, c,  8, 11, T34);
+  SET(c, d, a, b, 11, 16, T35);
+  SET(b, c, d, a, 14, 23, T36);
+  SET(a, b, c, d,  1,  4, T37);
+  SET(d, a, b, c,  4, 11, T38);
+  SET(c, d, a, b,  7, 16, T39);
+  SET(b, c, d, a, 10, 23, T40);
+  SET(a, b, c, d, 13,  4, T41);
+  SET(d, a, b, c,  0, 11, T42);
+  SET(c, d, a, b,  3, 16, T43);
+  SET(b, c, d, a,  6, 23, T44);
+  SET(a, b, c, d,  9,  4, T45);
+  SET(d, a, b, c, 12, 11, T46);
+  SET(c, d, a, b, 15, 16, T47);
+  SET(b, c, d, a,  2, 23, T48);
+
 #undef SET
 
-     /* Round 4. */
-     /* Let [abcd k s t] denote the operation
-          a = b + ((a + I(b,c,d) + X[k] + T[i]) <<< s). */
-#define I(x, y, z) ((y) ^ ((x) | ~(z)))
-#define SET(a, b, c, d, k, s, Ti)\
-  t = a + I(b,c,d) + X[k] + Ti;\
-  a = ROTATE_LEFT(t, s) + b
-     /* Do the following 16 operations. */
-    SET(a, b, c, d,  0,  6, T49);
-    SET(d, a, b, c,  7, 10, T50);
-    SET(c, d, a, b, 14, 15, T51);
-    SET(b, c, d, a,  5, 21, T52);
-    SET(a, b, c, d, 12,  6, T53);
-    SET(d, a, b, c,  3, 10, T54);
-    SET(c, d, a, b, 10, 15, T55);
-    SET(b, c, d, a,  1, 21, T56);
-    SET(a, b, c, d,  8,  6, T57);
-    SET(d, a, b, c, 15, 10, T58);
-    SET(c, d, a, b,  6, 15, T59);
-    SET(b, c, d, a, 13, 21, T60);
-    SET(a, b, c, d,  4,  6, T61);
-    SET(d, a, b, c, 11, 10, T62);
-    SET(c, d, a, b,  2, 15, T63);
-    SET(b, c, d, a,  9, 21, T64);
+  // Round 4.
+  // Let [abcd k s t] denote the operation
+  //   a = b + ((a + I(b,c,d) + X[k] + T[i]) <<< s).
+#define I(x, y, z)		((y) ^ ((x) | ~(z)))
+#define SET(a, b, c, d, k, s, Ti) t = a + I(b,c,d) + X[k] + Ti; a = ROTATE_LEFT(t, s) + b
+
+  // Do the following 16 operations.
+  SET(a, b, c, d,  0,  6, T49);
+  SET(d, a, b, c,  7, 10, T50);
+  SET(c, d, a, b, 14, 15, T51);
+  SET(b, c, d, a,  5, 21, T52);
+  SET(a, b, c, d, 12,  6, T53);
+  SET(d, a, b, c,  3, 10, T54);
+  SET(c, d, a, b, 10, 15, T55);
+  SET(b, c, d, a,  1, 21, T56);
+  SET(a, b, c, d,  8,  6, T57);
+  SET(d, a, b, c, 15, 10, T58);
+  SET(c, d, a, b,  6, 15, T59);
+  SET(b, c, d, a, 13, 21, T60);
+  SET(a, b, c, d,  4,  6, T61);
+  SET(d, a, b, c, 11, 10, T62);
+  SET(c, d, a, b,  2, 15, T63);
+  SET(b, c, d, a,  9, 21, T64);
+
 #undef SET
 
-     /* Then perform the following additions. (That is increment each
-        of the four registers by the value it had before this block
-        was started.) */
-    pms->abcd[0] += a;
-    pms->abcd[1] += b;
-    pms->abcd[2] += c;
-    pms->abcd[3] += d;
+  // Then perform the following additions. (That is increment each of the four
+  // registers by the value it had before this block was started.)
+  pms->abcd[0] += a;
+  pms->abcd[1] += b;
+  pms->abcd[2] += c;
+  pms->abcd[3] += d;
 }
 
+
+//
+// '_pdfioCryptoMD5Init()' - Initialize an MD5 hash.
+//
+
 void
-_pdfioCryptoMD5Init(_pdfio_md5_t *pms)
+_pdfioCryptoMD5Init(_pdfio_md5_t *pms)	// I - MD5 state
 {
     pms->count[0] = pms->count[1] = 0;
-    pms->abcd[0] = 0x67452301;
-    pms->abcd[1] = 0xefcdab89;
-    pms->abcd[2] = 0x98badcfe;
-    pms->abcd[3] = 0x10325476;
+    pms->abcd[0]  = 0x67452301;
+    pms->abcd[1]  = 0xefcdab89;
+    pms->abcd[2]  = 0x98badcfe;
+    pms->abcd[3]  = 0x10325476;
 }
 
+
+//
+// '_pdfioCryptoMD5Append()' - Append bytes to the MD5 hash.
+//
+
 void
-_pdfioCryptoMD5Append(_pdfio_md5_t *pms, const uint8_t *data, size_t nbytes)
+_pdfioCryptoMD5Append(
+    _pdfio_md5_t  *pms,			// I - MD5 state
+    const uint8_t *data,		// I - Data to add
+    size_t        nbytes)		// I - Number of bytes
 {
-    const uint8_t *p = data;
-    size_t left = nbytes;
-    size_t offset = (pms->count[0] >> 3) & 63;
-    uint32_t nbits = (uint32_t)(nbytes << 3);
+  const uint8_t	*p = data;		// Pointer into data
+  size_t	left = nbytes;		// Remaining bytes
+  size_t	offset = (pms->count[0] >> 3) & 63;
+					// Offset into state
+  uint32_t	nbits = (uint32_t)(nbytes << 3);
+					// Number of bits to add
 
-    if (nbytes == 0)
-	return;
 
-    /* Update the message length. */
-    pms->count[1] += (unsigned)(nbytes >> 29);
-    pms->count[0] += nbits;
-    if (pms->count[0] < nbits)
-	pms->count[1]++;
+  if (nbytes == 0)
+    return;
 
-    /* Process an initial partial block. */
-    if (offset) {
-	size_t copy = (offset + nbytes > 64 ? 64 - offset : nbytes);
+  // Update the message length.
+  pms->count[1] += (unsigned)(nbytes >> 29);
+  pms->count[0] += nbits;
+  if (pms->count[0] < nbits)
+    pms->count[1] ++;
 
-	memcpy(pms->buf + offset, p, copy);
-	if (offset + copy < 64)
-	    return;
-	p += copy;
-	left -= copy;
-	md5_process(pms, pms->buf);
-    }
+  // Process an initial partial block.
+  if (offset)
+  {
+    size_t copy = ((offset + nbytes) > 64 ? 64 - offset : nbytes);
+					// Number of bytes to copy
 
-    /* Process full blocks. */
-    for (; left >= 64; p += 64, left -= 64)
-	md5_process(pms, p);
+    memcpy(pms->buf + offset, p, copy);
 
-    /* Process a final partial block. */
-    if (left)
-	memcpy(pms->buf, p, left);
+    if ((offset + copy) < 64)
+      return;
+
+    p    += copy;
+    left -= copy;
+
+    md5_process(pms, pms->buf);
+  }
+
+  // Process full blocks.
+  for (; left >= 64; p += 64, left -= 64)
+    md5_process(pms, p);
+
+  // Copy a final partial block.
+  if (left)
+    memcpy(pms->buf, p, left);
 }
 
+
+//
+// '_pdfioCryptoMD5Finish()' - Finalize the MD5 hash.
+//
+
 void
-_pdfioCryptoMD5Finish(_pdfio_md5_t *pms, uint8_t digest[16])
+_pdfioCryptoMD5Finish(
+    _pdfio_md5_t *pms,			// I - MD5 state
+    uint8_t      digest[16])		// O - Digest value
 {
-    static const uint8_t pad[64] = {
-	0x80, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
-	0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
-	0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
-	0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
-    };
-    uint8_t data[8];
-    int i;
+  int		i;			// Looping var
+  uint8_t	data[8];		// Digest length data
+  static const uint8_t pad[64] =	// Padding bytes
+  {
+    0x80, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+    0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+    0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+    0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+    0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+    0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+    0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+    0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00
+  };
 
-    /* Save the length before padding. */
-    for (i = 0; i < 8; ++i)
-	data[i] = (uint8_t)(pms->count[i >> 2] >> ((i & 3) << 3));
-    /* Pad to 56 bytes mod 64. */
-    _pdfioCryptoMD5Append(pms, pad, ((55 - (pms->count[0] >> 3)) & 63) + 1);
-    /* Append the length. */
-    _pdfioCryptoMD5Append(pms, data, 8);
-    for (i = 0; i < 16; ++i)
-	digest[i] = (uint8_t)(pms->abcd[i >> 2] >> ((i & 3) << 3));
+
+  // Save the length before padding.
+  for (i = 0; i < 8; ++i)
+    data[i] = (uint8_t)(pms->count[i >> 2] >> ((i & 3) << 3));
+
+  // Pad to 56 bytes mod 64.
+  _pdfioCryptoMD5Append(pms, pad, ((55 - (pms->count[0] >> 3)) & 63) + 1);
+
+  // Append the length.
+  _pdfioCryptoMD5Append(pms, data, 8);
+
+  // Copy the digest from the state...
+  for (i = 0; i < 16; ++i)
+    digest[i] = (uint8_t)(pms->abcd[i >> 2] >> ((i & 3) << 3));
 }

pdfio.h

@@ -20,10 +20,12 @@ extern "C" {
 
 
 //
-// Version number...
+// Version numbers...
 //
 
-#  define PDFIO_VERSION		"1.4.1"
+#  define PDFIO_VERSION		"1.5.0"
+#  define PDFIO_VERSION_MAJOR	1
+#  define PDFIO_VERSION_MINOR	5
 
 
 //