Rework CR/LF skip code to be more consistent.

Services (Issue #46)

- Odd cross-reference stream containing 3-byte generation number field for this
  16-bit value
- Odd empty hex strings

.gitignore

@@ -8,6 +8,8 @@
 /doc/pdfio.epub
 /packages
 /pdfio.xcodeproj/xcshareddata
+/pdfio-*.tar.gz*
+/pdfio-*.zip*
 /pdfiototext
 /testpdfio
 /testpdfio-*.pdf

CHANGES.md

@@ -7,6 +7,8 @@ v1.1.2 (TBD)
 
 - Fixed an issue with broken PDF files containing extra CR and/or LF separators
   after the object stream token (Issue #40)
+- Fixed an issue with PDF files produced by Microsoft Reporting Services
+  (Issue #46)
 
 
 v1.1.1 (March 20, 2023)

CONTRIBUTING.md

@@ -118,7 +118,7 @@ the source file and the copyright and licensing notice:
     //
     // Description of file contents.
     //
-    // Copyright YYYY by AUTHOR.
+    // Copyright © YYYY by AUTHOR.
     //
     // Licensed under Apache License v2.0.  See the file "LICENSE" for more
     // information.
@@ -330,7 +330,7 @@ typedef, for example:
 
 All constant names are uppercase with underscores between words, e.g.,
 `PDFIO_THIS_CONSTANT`, `PDFIO_THAT_CONSTANT`, etc.  Constants begin with the
-"PDFio\_" prefix to avoid conflicts with system constants.  Private constants
+"PDFIO\_" prefix to avoid conflicts with system constants.  Private constants
 start with an underscore, e.g., `_PDFIO_THIS_CONSTANT`,
 `_PDFIO_THAT_CONSTANT`, etc.
 
@@ -369,11 +369,12 @@ extensions MUST NOT be used.
 The following variables are defined in the makefile:
 
 - `AR`; the static library archiver command,
-- `ARFLAGS`; options for the static library archiver command,
+- `ARFLAGS`; options for the static library archiver,
 - `CC`; the C compiler command,
-- `CFLAGS`; options for the C compiler command,
+- `CFLAGS`; options for the C compiler,
 - `CODESIGN_IDENTITY`: the code signing identity,
 - `COMMONFLAGS`; common compiler optimization options,
+- `CPPFLAGS`; options for the C preprocessor,
 - `DESTDIR`/`DSTROOT`: the destination root directory when installing.
 - `DSO`; the shared library building command,
 - `DSOFLAGS`; options for the shared library building command,
@@ -395,4 +396,5 @@ The following standard targets are defined in the makefile:
   with debug printfs and the clang address sanitizer enabled.
 - `install`; installs all distribution files in their corresponding locations.
 - `install-shared`; same as `install` but also installs the shared library.
+- `macos`; same as `all` but creates a Universal Binary (X64 + ARM64).
 - `test`; runs the unit test program, building it as needed.

Makefile

@@ -21,7 +21,7 @@ CFLAGS		=
 CODESIGN_IDENTITY =	Developer ID
 COMMONFLAGS	=	-Os -g
 #COMMONFLAGS	=	-O0 -g -fsanitize=address
-CPPFLAGS	=	'-DPDFIO_VERSION="$(VERSION)"'
+CPPFLAGS	=
 DESTDIR		=	$(DSTROOT)
 DSO		=	cc
 DSOFLAGS	=
@@ -89,7 +89,7 @@ debug:
 	$(MAKE) -$(MAKEFLAGS) COMMONFLAGS="-g -fsanitize=address -DDEBUG=1" clean all
 
 macos:
-	$(MAKE) -$(MAKEFLAGS) COMMONFLAGS="-Os -mmacosx-version-min=10.14 -arch x86_64 -arch arm64" clean all
+	$(MAKE) -$(MAKEFLAGS) COMMONFLAGS="-Os -mmacosx-version-min=11 -arch x86_64 -arch arm64" clean all
 
 
 # Clean everything
@@ -191,7 +191,7 @@ ttf.o:			ttf.h
 # Make documentation using Codedoc <https://www.msweet.org/codedoc>
 DOCFLAGS	=	\
 			--author "Michael R Sweet" \
-			--copyright "Copyright (c) 2021-2022 by Michael R Sweet" \
+			--copyright "Copyright (c) 2021-2023 by Michael R Sweet" \
 			--docversion $(VERSION)
 
 .PHONY: doc

README.md

@@ -5,8 +5,6 @@ pdfio - PDF Read/Write Library
 ![Apache 2.0](https://img.shields.io/github/license/michaelrsweet/pdfio)
 [![Build Status](https://img.shields.io/github/workflow/status/michaelrsweet/pdfio/Build)](https://github.com/michaelrsweet/pdfio/actions/workflows/build.yml)
 [![Coverity Scan Status](https://img.shields.io/coverity/scan/22385.svg)](https://scan.coverity.com/projects/michaelrsweet-pdfio)
-[![LGTM Grade](https://img.shields.io/lgtm/grade/cpp/github/michaelrsweet/pdfio)](https://lgtm.com/projects/g/michaelrsweet/pdfio/context:cpp)
-[![LGTM Alerts](https://img.shields.io/lgtm/alerts/github/michaelrsweet/pdfio)](https://lgtm.com/projects/g/michaelrsweet/pdfio/)
 
 PDFio is a simple C library for reading and writing PDF files.  The primary
 goals of PDFio are:

SECURITY.md

@@ -5,6 +5,25 @@ This file describes how security issues are reported and handled, and what the
 expectations are for security issues reported to this project.
 
 
+Reporting a Security Bug
+------------------------
+
+For the purposes of this project, a security bug is a software defect that
+allows a *local or remote user* to gain unauthorized access or privileges on the
+host computer or to cause the software to crash.  Such defects should be
+reported to the project security advisory page at
+<https://github.com/michaelrsweet/pdfio/security/advisories>.
+
+Alternately, security bugs can be reported to "security AT msweet.org" using the
+PGP public key below.  Expect a response within 5 business days.  Any proposed
+embargo date should be at least 30 days and no more than 90 days in the future.
+
+> *Note:* If you've found a software defect that allows a *program* to gain
+> unauthorized access or privileges on the host computer or causes the program
+> to crash, that defect should be reported as an ordinary project issue at
+> <https://github.com/michaelrsweet/pdfio/issues>.
+
+
 Responsible Disclosure
 ----------------------
 
@@ -50,14 +69,6 @@ example:
     1.0rc1
 
 
-Reporting a Vulnerability
--------------------------
-
-Report all security issues to "security AT msweet.org".  Expect a response
-within 5 business days.  Any proposed embargo date should be at least 30 days
-and no more than 90 days in the future.
-
-
 PGP Public Key
 --------------
 

pdfio-content.h

@@ -1,7 +1,7 @@
 //
 // Public content header file for PDFio.
 //
-// Copyright © 2021 by Michael R Sweet.
+// Copyright © 2021-2023 by Michael R Sweet.
 //
 // Licensed under Apache License v2.0.  See the file "LICENSE" for more
 // information.
@@ -9,18 +9,7 @@
 
 #ifndef PDFIO_CONTENT_H
 #  define PDFIO_CONTENT_H
-
-//
-// Include necessary headers...
-//
-
 #  include "pdfio.h"
-
-
-//
-// C++ magic...
-//
-
 #  ifdef __cplusplus
 extern "C" {
 #  endif // __cplusplus
@@ -151,10 +140,6 @@ extern bool		pdfioPageDictAddFont(pdfio_dict_t *dict, const char *name, pdfio_ob
 extern bool		pdfioPageDictAddImage(pdfio_dict_t *dict, const char *name, pdfio_obj_t *obj) _PDFIO_PUBLIC;
 
 
-//
-// C++ magic...
-//
-
 #  ifdef __cplusplus
 }
 #  endif // __cplusplus

pdfio-file.c

@@ -1737,6 +1737,10 @@ load_xref(
         return (false);
       }
 
+      PDFIO_DEBUG("load_xref: tb.bufptr=%p, tb.bufend=%p, tb.bufptr[0]=0x%02x, tb.bufptr[0]=0x%02x\n", tb.bufptr, tb.bufend, tb.bufptr[0], tb.bufptr[1]);
+      if (tb.bufptr && tb.bufptr < tb.bufend && (tb.bufptr[0] == 0x0d || tb.bufptr[0] == 0x0a))
+	tb.bufptr ++;			// Skip trailing CR or LF after token
+
       _pdfioTokenFlush(&tb);
 
       obj->stream_offset = _pdfioFileTell(pdf);
@@ -1759,9 +1763,9 @@ load_xref(
       w_2     = w[0];
       w_3     = w[0] + w[1];
 
-      if (w[1] == 0 || w[2] > 2 || w[0] > sizeof(buffer) || w[1] > sizeof(buffer) || w[2] > sizeof(buffer) || w_total > sizeof(buffer))
+      if (w[1] == 0 || w[2] > 4 || w[0] > sizeof(buffer) || w[1] > sizeof(buffer) || w[2] > sizeof(buffer) || w_total > sizeof(buffer))
       {
-	_pdfioFileError(pdf, "Cross-reference stream has invalid W key.");
+	_pdfioFileError(pdf, "Cross-reference stream has invalid W key [%u %u %u].", (unsigned)w[0], (unsigned)w[1], (unsigned)w[2]);
 	return (false);
       }
 
@@ -1801,9 +1805,11 @@ load_xref(
 	    }
 	  }
 
+          // Offset
 	  for (i = 1, offset = buffer[w_2]; i < w[1]; i ++)
 	    offset = (offset << 8) | buffer[w_2 + i];
 
+          // Generation number
 	  switch (w[2])
 	  {
 	    default :
@@ -1815,6 +1821,19 @@ load_xref(
 	    case 2 :
 		generation = (buffer[w_3] << 8) | buffer[w_3 + 1];
 		break;
+	    case 3 :
+	        // Issue #46: Stupid Microsoft PDF generator using 3 bytes to
+	        // encode 16-bit generation numbers == 0 (probably a lazy coder
+	        // stuffing things into an array of 64-bit unsigned integers)
+		generation = (buffer[w_3] << 16) | (buffer[w_3 + 1] << 8) | buffer[w_3 + 2];
+		if (generation > 65535)
+		  generation = 65535;
+		break;
+	    case 4 : // Even stupider :)
+		generation = (buffer[w_3] << 24) | (buffer[w_3 + 1] << 16) | (buffer[w_3 + 2] << 8) | buffer[w_3 + 3];
+		if (generation > 65535)
+		  generation = 65535;
+		break;
 	  }
 
 	  // Create a placeholder for the object in memory...

pdfio-object.c

@@ -441,7 +441,8 @@ _pdfioObjLoad(pdfio_obj_t *obj)		// I - Object
     return (false);
   }
 
-  if (tb.bufptr && tb.bufptr < tb.bufend && (*(tb.bufptr) == 0x0d || *(tb.bufptr) == 0x0a))
+  PDFIO_DEBUG("_pdfioObjLoad: tb.bufptr=%p, tb.bufend=%p, tb.bufptr[0]=0x%02x, tb.bufptr[0]=0x%02x\n", tb.bufptr, tb.bufend, tb.bufptr[0], tb.bufptr[1]);
+  if (tb.bufptr && tb.bufptr < tb.bufend && (tb.bufptr[0] == 0x0d || tb.bufptr[0] == 0x0a))
     tb.bufptr ++;			// Skip trailing CR or LF after token
 
   _pdfioTokenFlush(&tb);

pdfio-private.h

@@ -9,17 +9,14 @@
 
 #ifndef PDFIO_PRIVATE_H
 #  define PDFIO_PRIVATE_H
-
-
 #  ifdef _WIN32
 #    define _CRT_SECURE_NO_WARNINGS	// Disable bogus VS warnings/errors...
 #  endif // _WIN32
-
-
 #  include "pdfio.h"
 #  include <stdarg.h>
 #  include <stdint.h>
 #  include <string.h>
+#  include <ctype.h>
 #  include <errno.h>
 #  include <inttypes.h>
 #  include <fcntl.h>
@@ -42,17 +39,15 @@
 #    define F_OK	00		// POSIX parameters/flags
 #    define W_OK	02
 #    define R_OK	04
-#    define O_RDONLY	_O_RDONLY
+#    define O_RDONLY	_O_RDONLY	// Map standard POSIX open flags
 #    define O_WRONLY	_O_WRONLY
 #    define O_CREAT	_O_CREAT
 #    define O_TRUNC	_O_TRUNC
 #    define O_BINARY	_O_BINARY
 #  else // !_WIN32
 #    include <unistd.h>
-#    define O_BINARY	0		// Used on Windows for binary files...
+#    define O_BINARY	0		// Map Windows-specific open flag
 #  endif // _WIN32
-#  include <string.h>
-#  include <ctype.h>
 #  include <zlib.h>
 
 

pdfio-stream.c

@@ -579,12 +579,6 @@ _pdfioStreamOpen(pdfio_obj_t *obj,	// I - Object
       st->flate.next_in  = (Bytef *)st->cbuffer;
       st->flate.avail_in = (uInt)rbytes;
 
-      if (st->cbuffer[0] == 0x0a)
-      {
-        st->flate.next_in ++;		// Skip newline
-        st->flate.avail_in --;
-      }
-
       PDFIO_DEBUG("_pdfioStreamOpen: avail_in=%u, cbuffer=<%02X%02X%02X%02X%02X%02X%02X%02X...>\n", st->flate.avail_in, st->cbuffer[0], st->cbuffer[1], st->cbuffer[2], st->cbuffer[3], st->cbuffer[4], st->cbuffer[5], st->cbuffer[6], st->cbuffer[7]);
 
       if ((status = inflateInit(&(st->flate))) != Z_OK)

pdfio-token.c

@@ -495,6 +495,13 @@ _pdfioTokenRead(_pdfio_token_t *tb,	// I - Token buffer/stack
 	  *bufptr++ = (char)ch;
 	  break;
 	}
+	else if (ch == '>')
+	{
+	  // Issue #46: Empty hex string from Microsoft PDF generator; treat as
+	  // empty literal string...
+	  *buffer = '(';
+	  break;
+	}
 	else if (!isspace(ch & 255) && !isxdigit(ch & 255))
 	{
 	  _pdfioFileError(tb->pdf, "Syntax error: '<%c'", ch);

pdfio.h

@@ -1,7 +1,7 @@
 //
 // Public header file for PDFio.
 //
-// Copyright © 2021-2022 by Michael R Sweet.
+// Copyright © 2021-2023 by Michael R Sweet.
 //
 // Licensed under Apache License v2.0.  See the file "LICENSE" for more
 // information.
@@ -9,27 +9,23 @@
 
 #ifndef PDFIO_H
 #  define PDFIO_H
-
-//
-// Include necessary headers...
-//
-
 #  include <stdio.h>
 #  include <stdlib.h>
 #  include <stdbool.h>
 #  include <sys/types.h>
 #  include <time.h>
-
-
-//
-// C++ magic...
-//
-
 #  ifdef __cplusplus
 extern "C" {
 #  endif // __cplusplus
 
 
+//
+// Version number...
+//
+
+#  define PDFIO_VERSION		"1.1.2"
+
+
 //
 // Visibility and other annotations...
 //
@@ -244,10 +240,6 @@ extern char		*pdfioStringCreate(pdfio_file_t *pdf, const char *s)  _PDFIO_PUBLIC
 extern char		*pdfioStringCreatef(pdfio_file_t *pdf, const char *format, ...) _PDFIO_FORMAT(2,3) _PDFIO_PUBLIC;
 
 
-//
-// C++ magic...
-//
-
 #  ifdef __cplusplus
 }
 #  endif // __cplusplus

pdfio.vcxproj

@@ -87,7 +87,7 @@
     <ClCompile>
       <WarningLevel>Level3</WarningLevel>
       <SDLCheck>true</SDLCheck>
-      <PreprocessorDefinitions>PDFIO_VERSION="1.1.1";WIN32;_DEBUG;_CONSOLE;%(PreprocessorDefinitions)</PreprocessorDefinitions>
+      <PreprocessorDefinitions>WIN32;_DEBUG;_CONSOLE;%(PreprocessorDefinitions)</PreprocessorDefinitions>
       <ConformanceMode>true</ConformanceMode>
     </ClCompile>
     <Link>
@@ -101,7 +101,7 @@
       <FunctionLevelLinking>true</FunctionLevelLinking>
       <IntrinsicFunctions>true</IntrinsicFunctions>
       <SDLCheck>true</SDLCheck>
-      <PreprocessorDefinitions>PDFIO_VERSION="1.1.1";WIN32;NDEBUG;_CONSOLE;%(PreprocessorDefinitions)</PreprocessorDefinitions>
+      <PreprocessorDefinitions>WIN32;NDEBUG;_CONSOLE;%(PreprocessorDefinitions)</PreprocessorDefinitions>
       <ConformanceMode>true</ConformanceMode>
     </ClCompile>
     <Link>
@@ -115,7 +115,7 @@
     <ClCompile>
       <WarningLevel>Level3</WarningLevel>
       <SDLCheck>true</SDLCheck>
-      <PreprocessorDefinitions>PDFIO_VERSION="1.1.1";_DEBUG;_CONSOLE;%(PreprocessorDefinitions)</PreprocessorDefinitions>
+      <PreprocessorDefinitions>_DEBUG;_CONSOLE;%(PreprocessorDefinitions)</PreprocessorDefinitions>
       <ConformanceMode>true</ConformanceMode>
     </ClCompile>
     <Link>
@@ -130,7 +130,7 @@
       <FunctionLevelLinking>true</FunctionLevelLinking>
       <IntrinsicFunctions>true</IntrinsicFunctions>
       <SDLCheck>true</SDLCheck>
-      <PreprocessorDefinitions>PDFIO_VERSION="1.1.1";NDEBUG;_CONSOLE;%(PreprocessorDefinitions)</PreprocessorDefinitions>
+      <PreprocessorDefinitions>NDEBUG;_CONSOLE;%(PreprocessorDefinitions)</PreprocessorDefinitions>
       <ConformanceMode>true</ConformanceMode>
     </ClCompile>
     <Link>

pdfio.xcodeproj/project.pbxproj

@@ -372,7 +372,7 @@
 				CLANG_WARN__DUPLICATE_METHOD_MATCH = YES;
 				CODE_SIGN_IDENTITY = "Apple Development";
 				COPY_PHASE_STRIP = NO;
-				CURRENT_PROJECT_VERSION = 1.1.1;
+				CURRENT_PROJECT_VERSION = 1.1.2;
 				DEBUG_INFORMATION_FORMAT = dwarf;
 				ENABLE_STRICT_OBJC_MSGSEND = YES;
 				ENABLE_TESTABILITY = YES;
@@ -381,7 +381,6 @@
 				GCC_PREPROCESSOR_DEFINITIONS = (
 					"$(inherited)",
 					"DEBUG=1",
-					"'PDFIO_VERSION=\"$(CURRENT_PROJECT_VERSION)\"'",
 				);
 				GCC_TREAT_IMPLICIT_FUNCTION_DECLARATIONS_AS_ERRORS = YES;
 				GCC_WARN_64_TO_32_BIT_CONVERSION = YES;
@@ -397,7 +396,7 @@
 				GCC_WARN_UNUSED_LABEL = YES;
 				GCC_WARN_UNUSED_PARAMETER = YES;
 				GCC_WARN_UNUSED_VARIABLE = YES;
-				MACOSX_DEPLOYMENT_TARGET = 10.14;
+				MACOSX_DEPLOYMENT_TARGET = 11.0;
 				MTL_ENABLE_DEBUG_INFO = INCLUDE_SOURCE;
 				MTL_FAST_MATH = YES;
 				ONLY_ACTIVE_ARCH = YES;
@@ -450,7 +449,7 @@
 				CLANG_WARN__DUPLICATE_METHOD_MATCH = YES;
 				CODE_SIGN_IDENTITY = "Apple Development";
 				COPY_PHASE_STRIP = NO;
-				CURRENT_PROJECT_VERSION = 1.1;
+				CURRENT_PROJECT_VERSION = 1.1.2;
 				DEBUG_INFORMATION_FORMAT = "dwarf-with-dsym";
 				ENABLE_HARDENED_RUNTIME = YES;
 				ENABLE_NS_ASSERTIONS = NO;
@@ -459,7 +458,6 @@
 				GCC_NO_COMMON_BLOCKS = YES;
 				GCC_PREPROCESSOR_DEFINITIONS = (
 					"$(inherited)",
-					"'PDFIO_VERSION=\"$(CURRENT_PROJECT_VERSION)\"'",
 				);
 				GCC_TREAT_IMPLICIT_FUNCTION_DECLARATIONS_AS_ERRORS = YES;
 				GCC_WARN_64_TO_32_BIT_CONVERSION = YES;
@@ -475,7 +473,7 @@
 				GCC_WARN_UNUSED_LABEL = YES;
 				GCC_WARN_UNUSED_PARAMETER = YES;
 				GCC_WARN_UNUSED_VARIABLE = YES;
-				MACOSX_DEPLOYMENT_TARGET = 10.14;
+				MACOSX_DEPLOYMENT_TARGET = 11.0;
 				MTL_ENABLE_DEBUG_INFO = NO;
 				MTL_FAST_MATH = YES;
 				RUN_CLANG_STATIC_ANALYZER = YES;
@@ -515,7 +513,7 @@
 				ENABLE_HARDENED_RUNTIME = YES;
 				GCC_DYNAMIC_NO_PIC = NO;
 				GCC_OPTIMIZATION_LEVEL = 0;
-				MACOSX_DEPLOYMENT_TARGET = 10.14;
+				MACOSX_DEPLOYMENT_TARGET = 11.0;
 				PRODUCT_BUNDLE_IDENTIFIER = org.msweet.testpdfio;
 				PRODUCT_NAME = "$(TARGET_NAME)";
 				PROVISIONING_PROFILE_SPECIFIER = "";
@@ -529,7 +527,7 @@
 				CODE_SIGN_STYLE = Automatic;
 				DEVELOPMENT_TEAM = "";
 				ENABLE_HARDENED_RUNTIME = YES;
-				MACOSX_DEPLOYMENT_TARGET = 10.14;
+				MACOSX_DEPLOYMENT_TARGET = 11.0;
 				PRODUCT_BUNDLE_IDENTIFIER = org.msweet.testpdfio;
 				PRODUCT_NAME = "$(TARGET_NAME)";
 				PROVISIONING_PROFILE_SPECIFIER = "";

pdfio_native.nuspec

@@ -3,7 +3,7 @@
     <metadata>
         <id>pdfio_native</id>
         <title>PDFio Library for VS2019+</title>
-        <version>1.1.1</version>
+        <version>1.1.2</version>
         <authors>Michael R Sweet</authors>
         <owners>michaelrsweet</owners>
         <projectUrl>https://github.com/michaelrsweet/pappl</projectUrl>
@@ -16,7 +16,7 @@
         <copyright>Copyright © 2019-2023 by Michael R Sweet</copyright>
         <tags>pdf file native</tags>
 	<dependencies>
-	    <dependency id="pdfio_native.redist" version="1.1.1" />
+	    <dependency id="pdfio_native.redist" version="1.1.2" />
 	    <dependency id="zlib_native.redist" version="1.2.11" />
 	</dependencies>
     </metadata>

pdfio_native.redist.nuspec

@@ -3,7 +3,7 @@
     <metadata>
         <id>pdfio_native.redist</id>
         <title>PDFio Library for VS2019+</title>
-        <version>1.1.1</version>
+        <version>1.1.2</version>
         <authors>Michael R Sweet</authors>
         <owners>michaelrsweet</owners>
         <projectUrl>https://github.com/michaelrsweet/pappl</projectUrl>
@@ -15,6 +15,9 @@
         <summary>PDFio is a simple C library for reading and writing PDF files. This package provides the redistributable content for the PDFio library. PDFio is licensed under the Apache License Version 2.0 with an (optional) exception to allow linking against GNU GPL2-only software.</summary>
         <copyright>Copyright © 2019-2023 by Michael R Sweet</copyright>
         <tags>pdf file native</tags>
+	<dependencies>
+	    <dependency id="zlib_native.redist" version="1.2.11" />
+	</dependencies>
     </metadata>
     <files>
         <file src="doc\pdfio-128.png" target="build\native" />