Merge ee31096019 into 8f2c47cb07

- Explain pdfioObjGetSubtype and pdfioObjGetType values
- Provide example code and documentation for accessing common page object values

.github/workflows/build.yml

@@ -9,23 +9,26 @@ on:
 jobs:
   build-linux:
 
-    runs-on: ubuntu-20.04
+    runs-on: ubuntu-latest
 
     steps:
-    - uses: actions/checkout@v2
+    - name: Checkout PDFio sources
-    - name: update build environment
+      uses: actions/checkout@v4
+    - name: Update Build Environment
       run: sudo apt-get update --fix-missing -y
-    - name: install prerequisites
+    - name: Install Prerequisites
       run: sudo apt-get install -y cppcheck zlib1g-dev
-    - name: make
+    - name: Configure PDFio
+      run: ./configure --enable-debug --enable-sanitizer --enable-maintainer
+    - name: Build PDFio
       run: make "COMMONFLAGS=-g -fsanitize=address"
-    - name: test
+    - name: Test PDFio
       env:
         ASAN_OPTIONS: leak_check_at_exit=false
       run: make test
-    - name: clang static analyzer
+    - name: Run Clang Static Analyzer
       run: make CC=clang "GHA_ERROR=::error::" clang
-    - name: cppcheck
+    - name: Run cppcheck
       run: make "GHA_ERROR=::error::" cppcheck
 
   build-macos:
@@ -33,12 +36,15 @@ jobs:
     runs-on: macos-latest
 
     steps:
-    - uses: actions/checkout@v2
+    - name: Checkout PDFio sources
-    - name: make
+      uses: actions/checkout@v4
+    - name: Configure PDFio
+      run: ./configure --enable-debug --enable-sanitizer --enable-maintainer
+    - name: Build PDFio
       run: make "COMMONFLAGS=-g -fsanitize=address"
-    - name: test
+    - name: Test PDFio
       run: make test
-    - name: clang static analyzer
+    - name: Run Clang Static Analyzer
       run: make CC=clang "GHA_ERROR=::error::" clang
 
   build-windows:
@@ -46,10 +52,13 @@ jobs:
     runs-on: windows-latest
 
     steps:
-    - uses: actions/checkout@v2
+    - name: Checkout PDFio sources
-    - name: setup-msbuild
+      uses: actions/checkout@v4
+    - name: Setup MSBuild
       uses: microsoft/setup-msbuild@v1.0.2
-    - name: nuget restore
+    - name: Nuget Restore
       run: nuget restore pdfio.sln
-    - name: msbuild
+    - name: Build PDFio
       run: msbuild pdfio.sln
+    - name: Test PDFio
+      run: .\runtests.bat x64\Debug

.github/workflows/codeql.yml

@@ -23,15 +23,15 @@ jobs:
         language: [ cpp ]
 
     steps:
-      - name: Checkout
+      - name: Checkout PDFio sources
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
         with:
           submodules: recursive
 
-      - name: Update build environment
+      - name: Update Build Environment
         run: sudo apt-get update --fix-missing -y
 
-      - name: Install prerequisites
+      - name: Install Prerequisites
         run: sudo apt-get install -y zlib1g-dev
 
       - name: Initialize CodeQL

.github/workflows/coverity.yml

@@ -7,10 +7,11 @@ jobs:
     runs-on: ubuntu-latest
     environment: Coverity
     steps:
-      - uses: actions/checkout@v2
+      - name: Checkout PDFio sources
-      - name: update build environment
+        uses: actions/checkout@v4
+      - name: Update Build Environment
         run: sudo apt-get update --fix-missing -y
-      - name: install prerequisites
+      - name: Install Prerequisites
         run: sudo apt-get install -y zlib1g-dev
       - name: Download Coverity Build Tool
         run: |
@@ -20,11 +21,15 @@ jobs:
         env:
           TOKEN: ${{ secrets.COVERITY_SCAN_TOKEN }}
 
-      - name: Build with cov-build
+      - name: Configure PDFio
+        run: ./configure --enable-debug --enable-maintainer
+
+      - name: Build PDFio with cov-build
         run: |
           export PATH=`pwd`/cov-analysis-linux64/bin:$PATH
           cov-build --dir cov-int make
-      - name: Submit the result to Coverity Scan
+
+      - name: Submit the Result to Coverity Scan
         run: |
           tar czvf cov.tgz cov-int
           curl \

.gitignore

@@ -5,10 +5,18 @@
 *.so.1
 /.vs
 /afl-output
+/autom4te.cache
+/config.log
+/config.status
 /doc/pdfio.epub
+/Makefile
 /packages
+/pdfio.pc
 /pdfio.xcodeproj/xcshareddata
+/pdfio-*.tar.gz*
+/pdfio-*.zip*
 /pdfiototext
 /testpdfio
 /testpdfio-*.pdf
+/testttf
 /x64

CHANGES.md

@@ -2,8 +2,98 @@ Changes in PDFio
 ================
 
 
-v1.1.0 (February 3, 2023)
+v1.3.2 - YYYY-MM-DD
--------------------------
+-------------------
+
+- Added some more sanity checks to the TrueType font reader.
+- Updated documentation (Issue #77)
+- Fixed an issue when opening certain encrypted PDF files (Issue #62)
+
+
+v1.3.1 - 2024-08-05
+-------------------
+
+- CVE 2024-42358: Updated TrueType font reader to avoid large memory
+  allocations.
+- Fixed some documentation errors and added examples (Issue #68, Issue #69)
+
+
+v1.3.0 - 2024-06-28
+-------------------
+
+- Added `pdfioFileGetCatalog` API for accessing the root/catalog object of a
+  PDF file (Issue #67)
+- Updated number support to avoid locale issues (Issue #61)
+- Updated the PDFio private header to allow compilation with MingW; note that
+  MingW is NOT a supported toolchain for PDFio (Issue #66)
+- Optimized string pool code.
+
+
+v1.2.0 - 2024-01-24
+-------------------
+
+- Now use autoconf to configure the PDFio sources (Issue #54)
+- Added `pdfioFileCreateNumberObj` and `pdfioFileCreateStringObj` functions
+  (Issue #14)
+- Added `pdfioContentTextMeasure` function (Issue #17)
+- Added `pdfioContentTextNewLineShow` and `pdfioContentTextNewLineShowf`
+  functions (Issue #24)
+- Renamed `pdfioContentTextNextLine` to `pdfioContentTextNewLine`.
+- Updated the maximum number of object streams in a single file from 4096 to
+  8192 (Issue #58)
+- Updated the token reading code to protect against some obvious abuses of the
+  PDF format.
+- Updated the xref reading code to protect against loops.
+- Updated the object handling code to use a binary insertion algorithm -
+  provides a significant (~800x) improvement in open times.
+- Fixed handling of encrypted PDFs with per-object file IDs (Issue #42)
+- Fixed handling of of trailer dictionaries that started immediately after the
+  "trailer" keyword (Issue #58)
+- Fixed handling of invalid, but common, PDF files with a generation number of
+  65536 in the xref table (Issue #59)
+
+
+v1.1.4 - 2023-12-03
+-------------------
+
+- Fixed detection of encrypted strings that are too short (Issue #52)
+- Fixed a TrueType CMAP decoding bug.
+- Fixed a text rendering issue for Asian text.
+- Added a ToUnicode map for Unicode text to support text copying.
+
+
+v1.1.3 - 2023-11-15
+-------------------
+
+- Fixed Unicode font support (Issue #16)
+- Fixed missing initializer for 40-bit RC4 encryption (Issue #51)
+
+
+v1.1.2 - 2023-10-10
+-------------------
+
+- Updated `pdfioContentSetDashPattern` to support setting a solid (0 length)
+  dash pattern (Issue #41)
+- 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 Crystal Reports (Issue #45)
+- Fixed an issue with PDF files produced by Microsoft Reporting Services
+  (Issue #46)
+- Fixed support for compound filters where the filter array consists of a
+  single named filter (Issue #47)
+- Fixed builds on Windows - needed windows.h header for temporary files
+  (Issue #48)
+
+
+v1.1.1 - 2023-03-20
+-------------------
+
+- CVE-2023-28428: Fixed a potential denial-of-service with corrupt PDF files.
+- Fixed a few build issues.
+
+
+v1.1.0 - 2023-02-06
+-------------------
 
 - CVE-2023-24808: Fixed a potential denial-of-service with corrupt PDF files.
 - Added `pdfioFileCreateTemporary` function (Issue #29)
@@ -17,28 +107,28 @@ v1.1.0 (February 3, 2023)
 - Fixed `pdfioContentMatrixRotate` function.
 
 
-v1.0.1 (March 2, 2022)
+v1.0.1 - 2022-03-02
-----------------------
+-------------------
 
 - Added missing `pdfioPageGetNumStreams` and `pdfioPageOpenStream` functions.
 - Added demo pdfiototext utility.
 - Fixed bug in `pdfioStreamGetToken`.
 
 
-v1.0.0 (December 14, 2021)
+v1.0.0 - 2021-12-14
---------------------------
+-------------------
 
 - First stable release.
 
 
-v1.0rc1 (November 30, 2021)
+v1.0rc1 - 2021-11-30
----------------------------
+--------------------
 
 - Fixed a few stack/buffer overflow bugs discovered via fuzzing.
 
 
-v1.0b2 (November 7, 2021)
+v1.0b2 - 2021-11-07
--------------------------
+-------------------
 
 - Added `pdfioFileCreateOutput` API to support streaming output of PDF
   (Issue #21)
@@ -49,7 +139,7 @@ v1.0b2 (November 7, 2021)
 - Fixed some issues identified by a Coverity scan.
 
 
-v1.0b1 (August 30, 2021)
+v1.0b1 - 2021-08-30
-------------------------
+-------------------
 
 - Initial release

CONTRIBUTING.md

@@ -43,14 +43,17 @@ Contents
 Build System
 ------------
 
-The build system uses a simple POSIX makefile to build a static or shared
+The build system uses [GNU autoconf][AUTOCONF] to create a simple POSIX makefile
-library.  To improve portability, makefiles *must not* make use of features
+to build static and/or shared libraries.  To improve portability, makefiles
-unique to GNU make.  See the [Makefile Guidelines](#makefile-guidelines) section
+*must not* make use of features unique to GNU make.  See the
-for a description of the allowed make features and makefile guidelines.
+[Makefile Guidelines](#makefile-guidelines) section for a description of the
+allowed make features and makefile guidelines.
 
 An Xcode project is provided for macOS/iOS developers, and a Visual Studio
 solution and projects for Windows developers.
 
+[AUTOCONF]: https://www.gnu.org/software/autoconf/
+
 
 Version Numbering
 -----------------
@@ -118,7 +121,7 @@ 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 +333,7 @@ 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.
 
@@ -369,17 +372,19 @@ 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,
-- `DSONAME`: the root name of the shared library
 - `LDFLAGS`; options for the linker,
+- `LIBPDFIO`: the name of the primary (shared or static) library
+- `LIBPDFIO_STATIC`: the name of the secondary (static) library
 - `LIBS`; libraries for all programs,
+- `OPTIM`; common compiler optimization options,
 - `prefix`; the installation prefix directory,
 - `RANLIB`; the static library indexing command,
 - `SHELL`; the sh (POSIX shell) command,
@@ -388,11 +393,7 @@ The following variables are defined in the makefile:
 The following standard targets are defined in the makefile:
 
 - `all`; creates the static library and unit test program.
-- `all-shared`; creates a shared library appropriate for the local system.
 - `clean`; removes all target programs libraries, documentation files, and
   object files,
-- `debug`: creates a clean build of the static library and unit test program
-  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.
 - `test`; runs the unit test program, building it as needed.

Makefile

@@ -1,224 +0,0 @@
-#
-# Makefile for PDFio.
-#
-# Copyright © 2021-2023 by Michael R Sweet.
-#
-# Licensed under Apache License v2.0.  See the file "LICENSE" for more
-# information.
-#
-
-# POSIX makefile
-.POSIX:
-
-# Build silently
-.SILENT:
-
-# Variables
-AR		=	ar
-ARFLAGS		=	cr
-CC		=	cc
-CFLAGS		=
-CODESIGN_IDENTITY =	Developer ID
-COMMONFLAGS	=	-Os -g
-#COMMONFLAGS	=	-O0 -g -fsanitize=address
-CPPFLAGS	=	'-DPDFIO_VERSION="$(VERSION)"'
-DESTDIR		=	$(DSTROOT)
-DSO		=	cc
-DSOFLAGS	=
-DSONAME		=
-LDFLAGS		=
-LIBS		=	-lm -lz
-RANLIB		=	ranlib
-VERSION		=	1.1.0
-prefix		=	/usr/local
-
-
-# Base rules
-.SUFFIXES:	.c .h .o
-.c.o:
-	echo Compiling $<...
-	$(CC) $(CFLAGS) $(CPPFLAGS) $(COMMONFLAGS) -c $<
-
-
-# Files
-PUBHEADERS	=	\
-			pdfio.h \
-			pdfio-content.h
-PUBOBJS		=	\
-			pdfio-aes.o \
-			pdfio-array.o \
-			pdfio-common.o \
-			pdfio-content.o \
-			pdfio-crypto.o \
-			pdfio-dict.o \
-			pdfio-file.o \
-			pdfio-md5.o \
-			pdfio-object.o \
-			pdfio-page.o \
-			pdfio-rc4.o \
-			pdfio-sha256.o \
-			pdfio-stream.o \
-			pdfio-string.o \
-			pdfio-token.o \
-			pdfio-value.o
-LIBOBJS		=	\
-			$(PUBOBJS) \
-			ttf.o
-OBJS		=	\
-			$(LIBOBJS) \
-			pdfiototext.o \
-			testpdfio.o
-TARGETS		=	\
-			$(DSONAME) \
-			libpdfio.a \
-			pdfiototext \
-			testpdfio
-
-
-# Make everything
-all:		$(TARGETS)
-
-all-shared:
-	if test `uname` = Darwin; then \
-		$(MAKE) DSONAME="libpdfio.1.dylib" -$(MAKEFLAGS) all; \
-	else \
-		$(MAKE) COMMONFLAGS="-g -Os -fPIC" DSONAME="libpdfio.so.1" -$(MAKEFLAGS) all; \
-	fi
-
-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
-
-
-# Clean everything
-clean:
-	rm -f $(TARGETS) $(OBJS)
-
-
-# Install everything
-install:	$(TARGETS)
-	echo Installing header files to $(DESTDIR)$(prefix)/include...
-	-mkdir -p $(DESTDIR)$(prefix)/include
-	cp $(PUBHEADERS) $(DESTDIR)$(prefix)/include
-	echo Installing library files to $(DESTDIR)$(prefix)/lib...
-	-mkdir -p $(DESTDIR)$(prefix)/lib
-	cp libpdfio.a $(DESTDIR)$(prefix)/lib
-	$(RANLIB) $(DESTDIR)$(prefix)/lib/libpdfio.a
-	if test "x$(DSONAME)" = xlibpdfio.so.1; then \
-		cp $(DSONAME) $(DESTDIR)$(prefix)/lib; \
-		ln -sf libpdfio.so.1 $(DESTDIR)$(prefix)/lib/libpdfio.so; \
-	elif test "x$(DSONAME)" = xlibpdfio.1.dylib; then \
-		cp $(DSONAME) $(DESTDIR)$(prefix)/lib; \
-		codesign -s "$(CODESIGN_IDENTITY)" -o runtime --timestamp $(DESTDIR)$(prefix)/lib/libpdfio.1.dylib; \
-		ln -sf libpdfio.1.dylib $(DESTDIR)$(prefix)/lib/libpdfio.dylib; \
-	fi
-	echo Installing pkg-config files to $(DESTDIR)$(prefix)/lib/pkgconfig...
-	-mkdir -p $(DESTDIR)$(prefix)/lib/pkgconfig
-	echo 'prefix="$(prefix)"' >$(DESTDIR)$(prefix)/lib/pkgconfig/pdfio.pc
-	echo 'Version: $(VERSION)' >>$(DESTDIR)$(prefix)/lib/pkgconfig/pdfio.pc
-	cat pdfio.pc.in >>$(DESTDIR)$(prefix)/lib/pkgconfig/pdfio.pc
-	echo Installing documentation to $(DESTDIR)$(prefix)/share/doc/pdfio...
-	-mkdir -p $(DESTDIR)$(prefix)/share/doc/pdfio
-	cp doc/pdfio.html doc/pdfio-512.png LICENSE NOTICE $(DESTDIR)$(prefix)/share/doc/pdfio
-	echo Installing man page to $(DESTDIR)$(prefix)/share/man/man3...
-	-mkdir -p $(DESTDIR)$(prefix)/share/man/man3
-	cp doc/pdfio.3 $(DESTDIR)$(prefix)/share/man/man3
-
-install-shared:
-	if test `uname` = Darwin; then \
-		$(MAKE) DSONAME="libpdfio.1.dylib" -$(MAKEFLAGS) install; \
-	else \
-		$(MAKE) DSONAME="libpdfio.so.1" -$(MAKEFLAGS) install; \
-	fi
-
-
-# Test everything
-test:	testpdfio
-	./testpdfio
-
-valgrind:	testpdfio
-	valgrind --leak-check=full ./testpdfio
-
-
-# pdfio library
-libpdfio.a:		$(LIBOBJS)
-	echo Archiving $@...
-	$(AR) $(ARFLAGS) $@ $(LIBOBJS)
-	$(RANLIB) $@
-
-libpdfio.so.1:		$(LIBOBJS)
-	echo Linking $@...
-	$(CC) $(DSOFLAGS) $(COMMONFLAGS) -shared -o $@ -Wl,-soname,$@ $(LIBOBJS) $(LIBS)
-
-libpdfio.1.dylib:	$(LIBOBJS)
-	echo Linking $@...
-	$(CC) $(DSOFLAGS) $(COMMONFLAGS) -dynamiclib -o $@ -install_name $(prefix)/lib/$@ -current_version $(VERSION) -compatibility_version 1.0 $(LIBOBJS) $(LIBS)
-
-
-# pdfio1.def (Windows DLL exports file...)
-#
-# I'd love to use __declspec(dllexport) but MS puts it before the function
-# declaration instead of after like everyone else, and it breaks Codedoc and
-# other tools I rely on...
-pdfio1.def: $(LIBOBJS) Makefile
-	echo Generating $@...
-	echo "LIBRARY pdfio1" >$@
-	echo "VERSION 1.0" >>$@
-	echo "EXPORTS" >>$@
-	nm $(LIBOBJS) 2>/dev/null | grep "T _" | awk '{print $$3}' | \
-		grep -v '^_ttf' | sed -e '1,$$s/^_//' | sort >>$@
-
-
-# pdfio text extraction (demo, doesn't handle a lot of things yet)
-pdfiototext:		pdfiototext.o libpdfio.a
-	echo Linking $@...
-	$(CC) $(LDFLAGS) $(COMMONFLAGS) -o $@ pdfiototext.o libpdfio.a $(LIBS)
-
-
-# pdfio test program
-testpdfio:		testpdfio.o libpdfio.a
-	echo Linking $@...
-	$(CC) $(LDFLAGS) $(COMMONFLAGS) -o $@ testpdfio.o libpdfio.a $(LIBS)
-
-
-# Dependencies
-$(OBJS):		pdfio.h pdfio-private.h Makefile
-pdfio-content.o:	pdfio-content.h ttf.h
-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" \
-			--docversion $(VERSION)
-
-.PHONY: doc
-doc:
-	echo Generating documentation...
-	codedoc $(DOCFLAGS) --title "PDFio Programming Manual v$(VERSION)" $(PUBHEADERS) $(PUBOBJS:.o=.c) --body doc/pdfio.md --coverimage doc/pdfio-512.png pdfio.xml >doc/pdfio.html
-	codedoc $(DOCFLAGS) --title "PDFio Programming Manual v$(VERSION)" --body doc/pdfio.md --coverimage doc/pdfio-epub.png pdfio.xml --epub doc/pdfio.epub
-	codedoc $(DOCFLAGS) --title "pdf read/write library" --man pdfio --section 3 --body doc/pdfio.md pdfio.xml >doc/pdfio.3
-	rm -f pdfio.xml
-
-
-# Fuzz-test the library <>
-.PHONY: afl
-afl:
-	$(MAKE) -$(MAKEFLAGS) CC="afl-clang-fast" COMMONFLAGS="-g" clean all
-	test afl-output || rm -rf afl-output
-	afl-fuzz -x afl-pdf.dict -i afl-input -o afl-output -V 600 -e pdf -t 5000 ./testpdfio @@
-
-
-# Analyze code with the Clang static analyzer <https://clang-analyzer.llvm.org>
-clang:
-	clang $(CPPFLAGS) --analyze $(OBJS:.o=.c) 2>clang.log
-	rm -rf $(OBJS:.o=.plist)
-	test -s clang.log && (echo "$(GHA_ERROR)Clang detected issues."; echo ""; cat clang.log; exit 1) || exit 0
-
-
-# Analyze code using Cppcheck <http://cppcheck.sourceforge.net>
-cppcheck:
-	cppcheck $(CPPFLAGS) --template=gcc --addon=cert.py --suppressions-list=.cppcheck $(OBJS:.o=.c) 2>cppcheck.log
-	test -s cppcheck.log && (echo "$(GHA_ERROR)Cppcheck detected issues."; echo ""; cat cppcheck.log; exit 1) || exit 0

Makefile.in

@@ -0,0 +1,262 @@
+#
+# Makefile for PDFio.
+#
+# Copyright © 2021-2024 by Michael R Sweet.
+#
+# Licensed under Apache License v2.0.  See the file "LICENSE" for more
+# information.
+#
+
+# POSIX makefile
+.POSIX:
+
+
+# Build silently
+.SILENT:
+
+
+# Version number...
+PDFIO_VERSION		=	@PDFIO_VERSION@
+PDFIO_VERSION_MAJOR	=	@PDFIO_VERSION_MAJOR@
+PDFIO_VERSION_MINOR	=	@PDFIO_VERSION_MINOR@
+
+
+# Programs and options...
+AR		=	@AR@
+ARFLAGS		=	@ARFLAGS@
+CC		=	@CC@
+CFLAGS		=	@CFLAGS@ $(CPPFLAGS) $(OPTIM) $(WARNINGS)
+CODE_SIGN	=	@CODE_SIGN@
+CODESIGN_IDENTITY =	-
+CPPFLAGS	=	@CPPFLAGS@
+CSFLAGS		=	-s "$(CODESIGN_IDENTITY)" @CSFLAGS@ --timestamp
+DSOFLAGS	=	@DSOFLAGS@ $(CFLAGS)
+INSTALL		=	@INSTALL@
+LDFLAGS		=	@LDFLAGS@ $(OPTIM)
+LIBS		=	@LIBS@ -lm
+LN		=	@LN@
+OPTIM		=	@OPTIM@
+RANLIB		=	@RANLIB@
+RM		=	@RM@ -f
+RMDIR		=	@RMDIR@
+SHELL		=	/bin/sh
+WARNINGS	=	@WARNINGS@
+
+
+# Targets
+LIBPDFIO	=	@LIBPDFIO@
+LIBPDFIO_STATIC	=	@LIBPDFIO_STATIC@
+
+
+# Directories...
+bindir		=	@bindir@
+datadir		=	@datadir@
+datarootdir	=	@datarootdir@
+exec_prefix	=	@exec_prefix@
+includedir	=	@includedir@
+infodir		=	@infodir@
+libdir		=	@libdir@
+libexecdir	=	@libexecdir@
+localstatedir	=	@localstatedir@
+mandir		=	@mandir@
+oldincludedir	=	@oldincludedir@
+prefix		=	@prefix@
+sbindir		=	@sbindir@
+sharedstatedir	=	@sharedstatedir@
+srcdir		=	@srcdir@
+sysconfdir	=	@sysconfdir@
+top_srcdir	=	@top_srcdir@
+
+BUILDROOT	=	$(DSTROOT)$(RPM_BUILD_ROOT)$(DESTDIR)
+
+
+# Build commands...
+.SUFFIXES:	.c .h .o
+.c.o:
+	echo Compiling $<...
+	$(CC) $(CFLAGS) -c -o $@ $<
+
+
+# Files
+PUBHEADERS	=	\
+			pdfio.h \
+			pdfio-content.h
+PUBOBJS		=	\
+			pdfio-aes.o \
+			pdfio-array.o \
+			pdfio-common.o \
+			pdfio-content.o \
+			pdfio-crypto.o \
+			pdfio-dict.o \
+			pdfio-file.o \
+			pdfio-md5.o \
+			pdfio-object.o \
+			pdfio-page.o \
+			pdfio-rc4.o \
+			pdfio-sha256.o \
+			pdfio-stream.o \
+			pdfio-string.o \
+			pdfio-token.o \
+			pdfio-value.o
+LIBOBJS		=	\
+			$(PUBOBJS) \
+			ttf.o
+OBJS		=	\
+			$(LIBOBJS) \
+			pdfiototext.o \
+			testpdfio.o \
+			testttf.o
+TARGETS		=	\
+			$(LIBPDFIO) \
+			$(LIBPDFIO_STATIC) \
+			pdfiototext \
+			testpdfio \
+			testttf
+
+
+# Make everything
+all:		$(TARGETS)
+
+
+# Clean everything
+clean:
+	rm -f $(TARGETS) $(OBJS)
+
+
+# Install everything
+install:	$(TARGETS)
+	echo Installing header files to $(BUILDROOT)$(includedir)...
+	$(INSTALL) -d -m 755 $(BUILDROOT)$(includedir)
+	for file in $(PUBHEADERS); do \
+		$(INSTALL) -c -m 644 $$file $(BUILDROOT)$(includedir); \
+	done
+	echo Installing library files to $(BUILDROOT)$(libdir)...
+	$(INSTALL) -d -m 755 $(BUILDROOT)$(libdir)
+	if test "x$(LIBPDFIO_STATIC)" != x; then \
+		$(INSTALL) -c -m 644 $(LIBPDFIO_STATIC) $(BUILDROOT)$(libdir); \
+		$(RANLIB) $(BUILDROOT)$(libdir)/$(LIBPDFIO_STATIC); \
+	fi
+	if test "x$(LIBPDFIO)" = xlibpdfio.so.1; then \
+		$(INSTALL) -c -m 755 libpdfio.so.1 $(BUILDROOT)$(libdir); \
+		ln -sf libpdfio.so.1 $(BUILDROOT)$(libdir)/libpdfio.so; \
+	elif test "x$(LIBPDFIO)" = xlibpdfio.1.dylib; then \
+		$(INSTALL) -c -m 755 libpdfio.1.dylib $(BUILDROOT)$(libdir); \
+		codesign -s "$(CODESIGN_IDENTITY)" -o runtime --timestamp $(BUILDROOT)$(libdir)/libpdfio.1.dylib; \
+		ln -sf libpdfio.1.dylib $(BUILDROOT)$(libdir)/libpdfio.dylib; \
+	else \
+		$(INSTALL) -c -m 644 $(LIBPDFIO) $(BUILDROOT)$(libdir); \
+		$(RANLIB) $(BUILDROOT)$(libdir)/$(LIBPDFIO); \
+	fi
+	echo Installing pkg-config files to $(BUILDROOT)$(libdir)/pkgconfig...
+	$(INSTALL) -d -m 755 $(BUILDROOT)$(libdir)/pkgconfig
+	$(INSTALL) -c -m 644 pdfio.pc $(BUILDROOT)$(libdir)/pkgconfig
+	echo Installing documentation to $(BUILDROOT)$(datadir)/doc/pdfio...
+	$(INSTALL) -d -m 755 $(BUILDROOT)$(datadir)/doc/pdfio
+	for file in doc/pdfio.html doc/pdfio-512.png LICENSE NOTICE; do \
+		$(INSTALL) -c -m 644  $$file $(BUILDROOT)$(datadir)/doc/pdfio; \
+	done
+	echo Installing man page to $(BUILDROOT)$(mandir)/man3...
+	$(INSTALL) -d -m 755 $(BUILDROOT)$(mandir)/man3
+	$(INSTALL) -c -m 644 doc/pdfio.3 $(BUILDROOT)$(mandir)/man3
+
+
+# Test everything
+test:	testpdfio testttf
+	./testttf 2>test.log
+	./testpdfio 2>>test.log
+	LANG=fr_FR.UTF-8 ./testpdfio 2>>test.log
+
+
+valgrind:	testpdfio
+	valgrind --leak-check=full ./testpdfio
+
+
+# pdfio library
+libpdfio.a:		$(LIBOBJS)
+	echo Archiving $@...
+	$(RM) $@
+	$(AR) $(ARFLAGS) $@ $(LIBOBJS)
+	$(RANLIB) $@
+
+libpdfio.so.1:		$(LIBOBJS)
+	echo Linking $@...
+	$(CC) $(DSOFLAGS) -shared -o $@ -Wl,-soname,$@ $(LIBOBJS) $(LIBS)
+
+libpdfio.1.dylib:	$(LIBOBJS)
+	echo Linking $@...
+	$(CC) $(DSOFLAGS) -dynamiclib -o $@ -install_name $(libdir)/$@ -current_version $(PDFIO_VERSION_MAJOR).$(PDFIO_VERSION_MINOR) -compatibility_version 1.0 $(LIBOBJS) $(LIBS)
+
+
+# pdfio1.def (Windows DLL exports file...)
+#
+# I'd love to use __declspec(dllexport) but MS puts it before the function
+# declaration instead of after like everyone else, and it breaks Codedoc and
+# other tools I rely on...
+pdfio1.def: $(LIBOBJS) Makefile
+	echo Generating $@...
+	echo "LIBRARY pdfio1" >$@
+	echo "VERSION $(PDFIO_VERSION_MAJOR).$(PDFIO_VERSION_MINOR)" >>$@
+	echo "EXPORTS" >>$@
+	nm $(LIBOBJS) 2>/dev/null | grep "T _" | awk '{print $$3}' | \
+		grep -v '^_ttf' | sed -e '1,$$s/^_//' | sort >>$@
+
+
+# pdfio text extraction (demo, doesn't handle a lot of things yet)
+pdfiototext:		pdfiototext.o libpdfio.a
+	echo Linking $@...
+	$(CC) $(LDFLAGS) -o $@ pdfiototext.o libpdfio.a $(LIBS)
+
+
+# pdfio test program
+testpdfio:		testpdfio.o libpdfio.a
+	echo Linking $@...
+	$(CC) $(LDFLAGS) -o $@ testpdfio.o libpdfio.a $(LIBS)
+
+
+# TTF test program
+testttf:	ttf.o testttf.o
+	echo Linking $@...
+	$(CC) $(LDFLAGS) -o testttf ttf.o testttf.o $(LIBS)
+
+
+# Dependencies
+$(OBJS):		pdfio.h pdfio-private.h Makefile
+pdfio-content.o:	pdfio-content.h ttf.h
+testttf.o:		ttf.h
+ttf.o:			ttf.h
+
+
+# Make documentation using Codedoc <https://www.msweet.org/codedoc>
+DOCFLAGS	=	\
+			--author "Michael R Sweet" \
+			--copyright "Copyright (c) 2021-2024 by Michael R Sweet" \
+			--docversion $(PDFIO_VERSION)
+
+.PHONY: doc
+doc:
+	echo Generating documentation...
+	codedoc $(DOCFLAGS) --title "PDFio Programming Manual v$(PDFIO_VERSION)" $(PUBHEADERS) $(PUBOBJS:.o=.c) --body doc/pdfio.md --coverimage doc/pdfio-512.png pdfio.xml >doc/pdfio.html
+	codedoc $(DOCFLAGS) --title "PDFio Programming Manual v$(PDFIO_VERSION)" --body doc/pdfio.md --coverimage doc/pdfio-epub.png pdfio.xml --epub doc/pdfio.epub
+	codedoc $(DOCFLAGS) --title "pdf read/write library" --man pdfio --section 3 --body doc/pdfio.md pdfio.xml >doc/pdfio.3
+	rm -f pdfio.xml
+
+
+# Fuzz-test the library <https://lcamtuf.coredump.cx/afl/>
+.PHONY: afl
+afl:
+	$(MAKE) -$(MAKEFLAGS) CC="afl-clang-fast" COMMONFLAGS="-g" clean all
+	test afl-output || rm -rf afl-output
+	afl-fuzz -x afl-pdf.dict -i afl-input -o afl-output -V 600 -e pdf -t 5000 ./testpdfio @@
+
+
+# Analyze code with the Clang static analyzer <https://clang-analyzer.llvm.org>
+clang:
+	clang $(CPPFLAGS) --analyze $(OBJS:.o=.c) 2>clang.log
+	rm -rf $(OBJS:.o=.plist)
+	test -s clang.log && (echo "$(GHA_ERROR)Clang detected issues."; echo ""; cat clang.log; exit 1) || exit 0
+
+
+# Analyze code using Cppcheck <http://cppcheck.sourceforge.net>
+cppcheck:
+	cppcheck $(CPPFLAGS) --template=gcc --addon=cert.py --suppressions-list=.cppcheck $(OBJS:.o=.c) 2>cppcheck.log
+	test -s cppcheck.log && (echo "$(GHA_ERROR)Cppcheck detected issues."; echo ""; cat cppcheck.log; exit 1) || exit 0

NOTICE

@@ -1,6 +1,6 @@
 PDFio - PDF Read/Write Library
 
-Copyright © 2021-2023 by Michael R Sweet.
+Copyright © 2021-2024 by Michael R Sweet.
 
 (Optional) Exceptions to the Apache 2.0 License:
 ================================================

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:
@@ -30,7 +28,7 @@ PDFio requires the following to build the software:
 
 - A C99 compiler such as Clang, GCC, or MS Visual C
 - A POSIX-compliant `make` program
-- ZLIB (<https://www.zlib.net>) 1.0 or higher
+- ZLIB (<https://www.zlib.net>) 1.1 or higher
 
 IDE files for Xcode (macOS/iOS) and Visual Studio (Windows) are also provided.
 
@@ -38,15 +36,27 @@ IDE files for Xcode (macOS/iOS) and Visual Studio (Windows) are also provided.
 Documentation
 -------------
 
-See the man page (`pdfio.3`), frequently ask questions (`FAQ.md`), and full HTML
+See the man page (`pdfio.3`) and full HTML documentation (`pdfio.html`) for
-documentation (`pdfio.html`) for information on using PDFio.
+information on using PDFio.
 
 
-Installing pdfio
+Installing PDFio
 ----------------
 
-PDFio comes with a portable makefile that will work on any POSIX-compliant
+PDFio uses a configure script on Unix systems to generate a makefile:
-system with ZLIB installed.  To make it, run:
+
+    ./configure
+
+If you want a shared library, run:
+
+    ./configure --enable-shared
+
+The default installation location is "/usr/local".  Pass the `--prefix` option
+to make to install it to another location:
+
+    ./configure --prefix=/some/other/directory
+
+Once configured, run the following to make the library:
 
     make all
 
@@ -56,45 +66,7 @@ To test it, run:
 
 To install it, run:
 
-    make install
+    sudo make install
-
-If you want a shared library, run:
-
-    make all-shared
-    make install-shared
-
-The default installation location is "/usr/local".  Pass the `prefix` variable
-to make to install it to another location:
-
-    make install prefix=/some/other/directory
-
-The makefile installs the pdfio header to "${prefix}/include", the library to
-"${prefix}/lib", the `pkg-config` file to "${prefix}/lib/pkgconfig", the man
-page to "${prefix}/share/man/man3", and the documentation to
-"${prefix}/share/doc/pdfio".
-
-The makefile supports the following variables that can be specified in the make
-command or as environment variables:
-
-- `AR`: the library archiver (default "ar")
-- `ARFLAGS`: options for the library archiver (default "cr")
-- `CC`: the C compiler (default "cc")
-- `CFLAGS`: options for the C compiler (default "")
-- `CODESIGN_IDENTITY`: the identity to use when code signing the shared library
-  on macOS (default "Developer ID")
-- `COMMONFLAGS`: options for the C compiler and linker (typically architecture
-  and optimization options, default is "-Os -g")
-- `CPPFLAGS`: options for the C preprocessor (default "")
-- `DESTDIR` and `DSTROOT`: specifies a root directory when installing
-  (default is "", specify only one)
-- `DSOFLAGS`: options for the C compiler when linking the shared library
-  (default "")
-- `LDFLAGS`: options for the C compiler when linking the test programs
-  (default "")
-- `LIBS`: library options when linking the test programs (default "-lz")
-- `RANLIB`: program that generates a table-of-contents in a library
-  (default "ranlib")
-- `prefix`: specifies the installation directory (default "/usr/local")
 
 
 Visual Studio Project
@@ -113,15 +85,11 @@ generates a static library that will be installed under "/usr/local" with:
 
     sudo xcodebuild install
 
-You can reproduce this with the makefile using:
-
-    sudo make macos install
-
 
 Legal Stuff
 -----------
 
-PDFio is Copyright © 2021-2022 by Michael R Sweet.
+PDFio is Copyright © 2021-2024 by Michael R Sweet.
 
 This software is licensed under the Apache License Version 2.0 with an
 (optional) exception to allow linking against GPL2/LGPL2 software.  See the

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
 ----------------------
 
@@ -35,7 +54,7 @@ starting at 0.  A feature release has a "PATCH" value of 0, for example:
     1.1.0
     2.0.0
 
-Beta releases and release candidates are *not* prodution releases and use
+Beta releases and release candidates are *not* production releases and use
 semantic version numbers of the form:
 
     MAJOR.MINORbNUMBER
@@ -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
 --------------
 

configure.ac

@@ -0,0 +1,273 @@
+dnl
+dnl Configuration script for PDFio
+dnl
+dnl Copyright © 2023-2024 by Michael R Sweet
+dnl
+dnl Licensed under Apache License v2.0.  See the file "LICENSE" for more
+dnl information.
+dnl
+
+dnl ***********************************************************************
+dnl
+dnl Note: Using autoheader or automake on this project will break the PDFio
+dnl build system.  Use "autoconf -f" to regenerate the configure script if
+dnl you make changes to this file.
+dnl
+dnl ***********************************************************************
+
+
+dnl We need at least autoconf 2.70 for --runstatedir...
+AC_PREREQ([2.70])
+
+
+dnl Package name and version...
+AC_INIT([pdfio], [1.3.2], [https://github.com/michaelrsweet/pdfio/issues], [pdfio], [https://www.msweet.org/pdfio])
+
+PDFIO_VERSION="AC_PACKAGE_VERSION"
+PDFIO_VERSION_MAJOR="`echo AC_PACKAGE_VERSION | awk -F. '{print $1}'`"
+PDFIO_VERSION_MINOR="`echo AC_PACKAGE_VERSION | awk -F. '{printf("%d\n",$2);}'`"
+AC_SUBST([PDFIO_VERSION])
+AC_SUBST([PDFIO_VERSION_MAJOR])
+AC_SUBST([PDFIO_VERSION_MINOR])
+
+
+dnl This line is provided to ensure that you don't run the autoheader program
+dnl against this project.  Doing so is completely unsupported and WILL cause
+dnl problems!
+AH_TOP([#error "Somebody ran autoheader on this project which is unsupported and WILL cause problems."])
+
+
+dnl Get the build and host platforms and split the host_os value
+AC_CANONICAL_BUILD
+AC_CANONICAL_HOST
+
+[host_os_name="$(echo $host_os | sed -e '1,$s/[0-9.]*$//g')"]
+[host_os_version="$(echo $host_os | sed -e '1,$s/^[^0-9.]*//g' | awk -F. '{print $1 $2}')"]
+# Linux often does not yield an OS version we can use...
+AS_IF([test "x$host_os_version" = x], [
+    host_os_version="0"
+])
+
+
+dnl Compiler options...
+CFLAGS="${CFLAGS:=}"
+CPPFLAGS="${CPPFLAGS:=}"
+DSOFLAGS="${DSOFLAGS:=}"
+LDFLAGS="${LDFLAGS:=}"
+LIBS="${LIBS:=}"
+OPTIM="${OPTIM:=}"
+
+AC_SUBST([DSOFLAGS])
+AC_SUBST([OPTIM])
+
+
+dnl Standard programs...
+AC_PROG_CC
+AC_PROG_RANLIB
+AC_PATH_PROG([AR], [ar])
+AC_PATH_PROGS([CODE_SIGN], [codesign true])
+AC_PATH_PROG([MKDIR], [mkdir])
+AC_PATH_PROG([RM], [rm])
+AC_PATH_PROG([RMDIR], [rmdir])
+AC_PATH_PROG([LN], [ln])
+
+
+dnl Figure out the correct "ar" command flags...
+AS_IF([test "$ac_cv_prog_ranlib" = ":"], [
+    ARFLAGS="crs"
+], [
+    ARFLAGS="cr"
+])
+AC_SUBST([ARFLAGS])
+
+
+dnl install-sh
+AC_MSG_CHECKING([for install-sh script])
+INSTALL="$(pwd)/install-sh"
+AC_SUBST([INSTALL])
+AC_MSG_RESULT([using $INSTALL])
+
+
+dnl Check for pkg-config, which is used for some other tests later on...
+AC_PATH_TOOL([PKGCONFIG], [pkg-config])
+
+PKGCONFIG_CFLAGS="-I\${includedir}"
+PKGCONFIG_LIBS="-L\${libdir} -lpdfio"
+PKGCONFIG_LIBS_PRIVATE="-lm"
+PKGCONFIG_REQUIRES="zlib"
+AC_SUBST([PKGCONFIG_CFLAGS])
+AC_SUBST([PKGCONFIG_LIBS])
+AC_SUBST([PKGCONFIG_LIBS_PRIVATE])
+AC_SUBST([PKGCONFIG_REQUIRES])
+
+
+dnl ZLIB
+AC_MSG_CHECKING([for zlib via pkg-config])
+AS_IF([$PKGCONFIG --exists zlib], [
+    AC_MSG_RESULT([yes])
+    CPPFLAGS="$($PKGCONFIG --cflags zlib) $CPPFLAGS"
+    LIBS="$($PKGCONFIG --libs zlib) $LIBS"
+],[
+    AC_MSG_RESULT([no])
+    AC_CHECK_HEADER([zlib.h])
+    AC_CHECK_LIB([z], [inflateCopy])
+
+    AS_IF([test x$ac_cv_header_zlib_h != xyes -o x$ac_cv_lib_z_inflateCopy != xyes], [
+	AC_MSG_ERROR([Sorry, this software requires zlib 1.1 or higher.])
+    ])
+
+    PKGCONFIG_REQUIRES=""
+    PKGCONFIG_LIBS_PRIVATE="-lz $PKGCONFIG_LIBS_PRIVATE"
+])
+
+
+dnl Library target...
+AC_ARG_ENABLE([static], AS_HELP_STRING([--disable-static], [do not install static library]))
+AC_ARG_ENABLE([shared], AS_HELP_STRING([--enable-shared], [install shared library]))
+
+AS_IF([test x$enable_shared = xyes], [
+    AS_IF([test "$host_os_name" = darwin], [
+	LIBPDFIO="libpdfio.1.dylib"
+    ], [
+	LIBPDFIO="libpdfio.so.1"
+    ])
+
+    AS_IF([test x$enable_static != xno], [
+        LIBPDFIO_STATIC="libpdfio.a"
+    ], [
+	LIBPDFIO_STATIC=""
+    ])
+], [
+    LIBPDFIO="libpdfio.a"
+    LIBPDFIO_STATIC=""
+    PKGCONFIG_LIBS="$PKGCONFIG_LIBS $PKGCONFIG_LIBS_PRIVATE"
+    PKGCONFIG_LIBS_PRIVATE=""
+])
+
+AC_SUBST([LIBPDFIO])
+AC_SUBST([LIBPDFIO_STATIC])
+
+
+dnl Extra compiler options...
+AC_ARG_ENABLE([debug], AS_HELP_STRING([--enable-debug], [turn on debugging, default=no]))
+AC_ARG_ENABLE([maintainer], AS_HELP_STRING([--enable-maintainer], [turn on maintainer mode, default=no]))
+AC_ARG_ENABLE([sanitizer], AS_HELP_STRING([--enable-sanitizer], [build with AddressSanitizer, default=no]))
+
+AS_IF([test x$enable_debug = xyes], [
+    OPTIM="$OPTIM -g"
+    CSFLAGS=""
+], [
+    OPTIM="$OPTIM -g -Os"
+    CSFLAGS="-o runtime"
+])
+
+AC_SUBST([CSFLAGS])
+
+WARNINGS=""
+AC_SUBST([WARNINGS])
+
+AS_IF([test -n "$GCC"], [
+    AS_IF([test x$enable_sanitizer = xyes], [
+	# Use -fsanitize=address with debugging...
+	OPTIM="$OPTIM -fsanitize=address"
+    ], [
+	# Otherwise use the Fortify enhancements to catch any unbounded
+	# string operations...
+	CPPFLAGS="$CPPFLAGS -D_FORTIFY_SOURCE=2"
+    ])
+
+    dnl Show all standard warnings + unused variables when compiling...
+    WARNINGS="-Wall -Wunused"
+
+    dnl Drop some not-useful/unreliable warnings...
+    for warning in char-subscripts format-truncation format-y2k switch unused-result; do
+	AC_MSG_CHECKING([whether compiler supports -Wno-$warning])
+
+	OLDCFLAGS="$CFLAGS"
+	CFLAGS="$CFLAGS -Wno-$warning -Werror"
+
+	AC_COMPILE_IFELSE([AC_LANG_PROGRAM()], [
+	    AC_MSG_RESULT(yes)
+	    WARNINGS="$WARNINGS -Wno-$warning"
+        ], [
+	    AC_MSG_RESULT(no)
+	])
+
+	CFLAGS="$OLDCFLAGS"
+    done
+
+    dnl Maintainer mode enables -Werror...
+    AS_IF([test x$enable_maintainer = xyes], [
+	WARNINGS="$WARNINGS -Werror -Wno-error=deprecated"
+    ])
+
+    dnl See if PIE options are supported...
+    AC_MSG_CHECKING(whether compiler supports -fPIE)
+    OLDCFLAGS="$CFLAGS"
+    AS_CASE(["$host_os_name"],
+    [darwin*], [
+	CFLAGS="$CFLAGS -fPIC -fPIE -Wl,-pie"
+	AC_COMPILE_IFELSE([AC_LANG_PROGRAM([[]], [[]])],[
+	    OLDCFLAGS="-fPIC $OLDCFLAGS"
+	    LDFLAGS="-fPIE -Wl,-pie $LDFLAGS"
+	    AC_MSG_RESULT(yes)
+	],[
+	    AC_MSG_RESULT(no)
+	])
+    ], [*], [
+	CFLAGS="$CFLAGS -fPIC -fPIE -pie"
+	AC_COMPILE_IFELSE([AC_LANG_PROGRAM([[]], [[]])],[
+	    OLDCFLAGS="-fPIC $OLDCFLAGS"
+	    LDFLAGS="-fPIE -pie $LDFLAGS"
+	    AC_MSG_RESULT(yes)
+	],[
+	    AC_MSG_RESULT(no)
+	])
+    ])
+    CFLAGS="$OLDCFLAGS"
+
+    dnl OS-specific compiler options...
+    AC_MSG_CHECKING([for OS-specific compiler options])
+    AS_CASE(["$host_os_name"], [linux*], [
+    	# Make sure we get the full set of 64-bit Linux APIs from the headers...
+	CPPFLAGS="$CPPFLAGS -D__USE_MISC -D_GNU_SOURCE -D_TIME_BITS=64 -D_FILE_OFFSET_BITS=64"
+
+	# Mark read-only sections as relocatable to random addresses...
+	LDFLAGS="$LDFLAGS -Wl,-z,relro,-z,now"
+
+        AC_MSG_RESULT([-D__USE_MISC -D_GNU_SOURCE -D_TIME_BITS=64 -D_FILE_OFFSET_BITS=64 -Wl,-z,relro,-z,now])
+    ], [darwin*], [
+        # When not building for debug, target macOS 11 or later, "universal"
+        # binaries when possible...
+        AS_IF([echo "$CPPFLAGS $CFLAGS $LDFLAGS $OPTIM" | grep -q "\\-arch "], [
+            # Don't add architecture/min-version flags if they are already present
+            AC_MSG_RESULT([none])
+        ], [echo "$CPPFLAGS $CFLAGS $LDFLAGS $OPTIM" | grep -q "\\-mmacosx-version-"], [
+            # Don't add architecture/min-version flags if they are already present
+            AC_MSG_RESULT([none])
+        ], [test "$host_os_version" -ge 200 -a x$enable_debug != xyes], [
+	    # macOS 11.0 and higher support the Apple Silicon (arm64) CPUs
+	    OPTIM="$OPTIM -mmacosx-version-min=11.0 -arch x86_64 -arch arm64"
+            AC_MSG_RESULT([-mmacosx-version-min=11.0 -arch x86_64 -arch arm64])
+	], [
+	    # Don't add architecture/min-version flags if debug enabled
+            AC_MSG_RESULT([none])
+	])
+    ], [*], [
+        AC_MSG_RESULT([none])
+    ])
+])
+
+
+dnl Extra linker options...
+AC_ARG_WITH([dsoflags], AS_HELP_STRING([--with-dsoflags=...], [Specify additional DSOFLAGS]), [
+    DSOFLAGS="$withval $DSOFLAGS"
+])
+AC_ARG_WITH([ldflags], AS_HELP_STRING([--with-ldflags=...], [Specify additional LDFLAGS]), [
+    LDFLAGS="$withval $LDFLAGS"
+])
+
+
+dnl Generate the Makefile and pkg-config file...
+AC_CONFIG_FILES([Makefile pdfio.pc])
+AC_OUTPUT

doc/pdfio.3

@@ -1,4 +1,4 @@
-.TH pdfio 3 "pdf read/write library" "2022-07-03" "pdf read/write library"
+.TH pdfio 3 "pdf read/write library" "2024-10-09" "pdf read/write library"
 .SH NAME
 pdfio \- pdf read/write library
 .SH Introduction
@@ -34,7 +34,7 @@ PDFio is
 .I not
  concerned with rendering or viewing a PDF file, although a PDF RIP or viewer could be written using it.
 .PP
-PDFio is Copyright \[co] 2021\-2022 by Michael R Sweet and is licensed under the Apache License Version 2.0 with an (optional) exception to allow linking against GPL2/LGPL2 software. See the files "LICENSE" and "NOTICE" for more information.
+PDFio is Copyright \[co] 2021\-2024 by Michael R Sweet and is licensed under the Apache License Version 2.0 with an (optional) exception to allow linking against GPL2/LGPL2 software. See the files "LICENSE" and "NOTICE" for more information.
 .SS Requirements
 .PP
 PDFio requires the following to build the software:
@@ -46,6 +46,10 @@ A C99 compiler such as Clang, GCC, or MS Visual C
 .PP
 A POSIX\-compliant make program
 
+.IP \(bu 5
+.PP
+A POSIX\-compliant sh program
+
 .IP \(bu 5
 .PP
 ZLIB (https://www.zlib.net) 1.0 or higher
@@ -55,10 +59,11 @@ ZLIB (https://www.zlib.net) 1.0 or higher
 IDE files for Xcode (macOS/iOS) and Visual Studio (Windows) are also provided.
 .SS Installing pdfio
 .PP
-PDFio comes with a portable makefile that will work on any POSIX\-compliant system with ZLIB installed. To make it, run:
+PDFio comes with a configure script that creates a portable makefile that will work on any POSIX\-compliant system with ZLIB installed. To make it, run:
 .nf
 
-    make all
+    \./configure
+    make
 .fi
 .PP
 To test it, run:
@@ -70,78 +75,28 @@ To test it, run:
 To install it, run:
 .nf
 
-    make install
+    sudo make install
 .fi
 .PP
 If you want a shared library, run:
 .nf
 
-    make all\-shared
+    \./configure \-\-enable\-shared
-    make install\-shared
+    make
+    sudo make install
 .fi
 .PP
-The default installation location is "/usr/local". Pass the prefix variable to make to install it to another location:
+The default installation location is "/usr/local". Pass the \-\-prefix option to make to install it to another location:
 .nf
 
-    make install prefix=/some/other/directory
+    \./configure \-\-prefix=/some/other/directory
 .fi
 .PP
-The makefile installs the pdfio header to "${prefix}/include", the library to "${prefix}/lib", the pkg\-config file to "${prefix}/lib/pkgconfig", the man page to "${prefix}/share/man/man3", and the documentation to "${prefix}/share/doc/pdfio".
+Other configure options can be found using the \-\-help option:
-.PP
+.nf
-The makefile supports the following variables that can be specified in the make command or as environment variables:
-.IP \(bu 5
-.PP
-AR: the library archiver (default "ar")
-
-.IP \(bu 5
-.PP
-ARFLAGS: options for the library archiver (default "cr")
-
-.IP \(bu 5
-.PP
-CC: the C compiler (default "cc")
-
-.IP \(bu 5
-.PP
-CFLAGS: options for the C compiler (default "")
-
-.IP \(bu 5
-.PP
-CODESIGN_IDENTITY: the identity to use when code signing the shared library on macOS (default "Developer ID")
-
-.IP \(bu 5
-.PP
-COMMONFLAGS: options for the C compiler and linker (typically architecture and optimization options, default is "\-Os \-g")
-
-.IP \(bu 5
-.PP
-CPPFLAGS: options for the C preprocessor (default "")
-
-.IP \(bu 5
-.PP
-DESTDIR and DSTROOT: specifies a root directory when installing (default is "", specify only one)
-
-.IP \(bu 5
-.PP
-DSOFLAGS: options for the C compiler when linking the shared library (default "")
-
-.IP \(bu 5
-.PP
-LDFLAGS: options for the C compiler when linking the test programs (default "")
-
-.IP \(bu 5
-.PP
-LIBS: library options when linking the test programs (default "\-lz")
-
-.IP \(bu 5
-.PP
-RANLIB: program that generates a table\-of\-contents in a library (default "ranlib")
-
-.IP \(bu 5
-.PP
-prefix: specifies the installation directory (default "/usr/local")
-
 
+    \./configure \-\-help
+.fi
 .SS Visual Studio Project
 .PP
 The Visual Studio solution ("pdfio.sln") is provided for Windows developers and generates both a static library and DLL.
@@ -152,12 +107,6 @@ There is also an Xcode project ("pdfio.xcodeproj") you can use on macOS which ge
 
     sudo xcodebuild install
 .fi
-.PP
-You can reproduce this with the makefile using:
-.nf
-
-    sudo make macos install
-.fi
 .SS Detecting PDFio
 .PP
 PDFio can be detected using the pkg\-config command, for example:
@@ -218,10 +167,25 @@ pdfio_stream_t: An object stream
 You open an existing PDF file using the pdfioFileOpen function:
 .nf
 
-    pdfio_file_t *pdf = pdfioFileOpen("myinputfile.pdf", error_cb, error_data);
+    pdfio_file_t *pdf = pdfioFileOpen("myinputfile.pdf", password_cb, password_data,
+                                      error_cb, error_data);
 .fi
 .PP
-where the three arguments to the function are the filename ("myinputfile.pdf"), an optional error callback function (error_cb), and an optional pointer value for the error callback function (error_data). The error callback is called for both errors and warnings and accepts the pdfio_file_t pointer, a message string, and the callback pointer value, for example:
+where the five arguments to the function are the filename ("myinputfile.pdf"), an optional password callback function (password_cb) and data pointer value (password_data), and an optional error callback function (error_cb) and data pointer value (error_data). The password callback is called for encrypted PDF files that are not using the default password, for example:
+.nf
+
+    const char *
+    password_cb(void *data, const char *filename)
+    {
+      (void)data;     // This callback doesn't use the data pointer
+      (void)filename; // This callback doesn't use the filename
+    
+      // Return a password string for the file...
+      return ("Password42");
+    }
+.fi
+.PP
+The error callback is called for both errors and warnings and accepts the pdfio_file_t pointer, a message string, and the callback pointer value, for example:
 .nf
 
     bool
@@ -254,7 +218,90 @@ Each PDF file contains one or more pages. The pdfioFileGetNumPages function retu
     }
 .fi
 .PP
-Each page is represented by a "page tree" object (what pdfioFileGetPage returns) that specifies information about the page and one or more "content" objects that contain the images, fonts, text, and graphics that appear on the page. Use the pdfioPageGetNumStreams and pdfioPageOpenStream functions to access the content streams for each page.
+Each page is represented by a "page tree" object (what pdfioFileGetPage returns) that specifies information about the page and one or more "content" objects that contain the images, fonts, text, and graphics that appear on the page. Use the pdfioPageGetNumStreams and pdfioPageOpenStream functions to access the content streams for each page, and pdfioObjGetDict to get the associated page object dictionary. For example, if you want to display the media and crop boxes for a given page:
+.nf
+
+    pdfio_file_t  *pdf;             // PDF file
+    size_t        i;                // Looping var
+    size_t        count;            // Number of pages
+    pdfio_obj_t   *page;            // Current page
+    pdfio_dict_t  *dict;            // Current page dictionary
+    pdfio_array_t *media_box;       // MediaBox array
+    double        media_values[4];  // MediaBox values
+    pdfio_array_t *crop_box;        // CropBox array
+    double        crop_values[4];   // CropBox values
+    
+    // Iterate the pages in the PDF file
+    for (i = 0, count = pdfioFileGetNumPages(pdf); i < count; i ++)
+    {
+      page = pdfioFileGetPage(pdf, i);
+      dict = pdfioObjGetDict(page);
+    
+      media_box       = pdfioDictGetArray(dict, "MediaBox");
+      media_values[0] = pdfioArrayGetNumber(media_box, 0);
+      media_values[1] = pdfioArrayGetNumber(media_box, 1);
+      media_values[2] = pdfioArrayGetNumber(media_box, 2);
+      media_values[3] = pdfioArrayGetNumber(media_box, 3);
+    
+      crop_box       = pdfioDictGetArray(dict, "CropBox");
+      crop_values[0] = pdfioArrayGetNumber(crop_box, 0);
+      crop_values[1] = pdfioArrayGetNumber(crop_box, 1);
+      crop_values[2] = pdfioArrayGetNumber(crop_box, 2);
+      crop_values[3] = pdfioArrayGetNumber(crop_box, 3);
+    
+      printf("Page %u: MediaBox=[%g %g %g %g], CropBox=[%g %g %g %g]\\n",
+             (unsigned)(i + 1),
+             media_values[0], media_values[1], media_values[2], media_values[3],
+             crop_values[0], crop_values[1], crop_values[2], crop_values[3]);
+    }
+.fi
+.PP
+Page object dictionaries have several (mostly optional) key/value pairs, including:
+.IP \(bu 5
+.PP
+"Annots": An array of annotation dictionaries for the page; use pdfioDictGetArray to get the array
+
+.IP \(bu 5
+.PP
+"CropBox": The crop box as an array of four numbers for the left, bottom, right, and top coordinates of the target media; use pdfioDictGetArray to get a pointer to the array of numbers
+
+.IP \(bu 5
+.PP
+"Dur": The number of seconds the page should be displayed; use pdfioDictGetNumber to get the page duration value
+
+.IP \(bu 5
+.PP
+"Group": The dictionary of transparency group values for the page; use pdfioDictGetDict to get a pointer to the resources dictionary
+
+.IP \(bu 5
+.PP
+"LastModified": The date and time when this page was last modified; use pdfioDictGetDate to get the Unix time_t value
+
+.IP \(bu 5
+.PP
+"Parent": The parent page tree node object for this page; use pdfioDictGetObj to get a pointer to the object
+
+.IP \(bu 5
+.PP
+"MediaBox": The media box as an array of four numbers for the left, bottom, right, and top coordinates of the target media; use pdfioDictGetArray to get a pointer to the array of numbers
+
+.IP \(bu 5
+.PP
+"Resources": The dictionary of resources for the page; use pdfioDictGetDict to get a pointer to the resources dictionary
+
+.IP \(bu 5
+.PP
+"Rotate": A number indicating the number of degrees of counter\-clockwise rotation to apply to the page when viewing; use pdfioDictGetNumber to get the rotation angle
+
+.IP \(bu 5
+.PP
+"Thumb": A thumbnail image object for the page; use pdfioDictGetObj to get a pointer to the thumbnail image object
+
+.IP \(bu 5
+.PP
+"Trans": The page transition dictionary; use pdfioDictGetDict to get a pointer to the dictionary
+
+
 .PP
 The pdfioFileClose function closes a PDF file and frees all memory that was used for it:
 .nf
@@ -397,10 +444,10 @@ pdfioStreamWrite writes a buffer of data to the stream
 .PP
 The PDF content helper functions provide additional functions for writing specific PDF page stream commands.
 .PP
-When you are done writing the stream, call pdfioStreamCLose to close both the stream and the object.
+When you are done writing the stream, call pdfioStreamClose to close both the stream and the object.
 .SS PDF Content Helper Functions
 .PP
-PDFio includes many helper functions for embedding or writing specific kinds of content to a PDF file. These functions can be roughly grouped into ??? categories:
+PDFio includes many helper functions for embedding or writing specific kinds of content to a PDF file. These functions can be roughly grouped into five categories:
 .IP \(bu 5
 .PP
 Color Space Functions
@@ -552,6 +599,7 @@ will embed an OpenSans Regular TrueType font using the Windows CP1252 subset of
 will embed the NotoSansJP Regular OpenType font with full support for Unicode.
 .PP
 Note: Not all fonts support Unicode.
+
 .PP
 Image Object Functions
 .PP
@@ -799,7 +847,15 @@ pdfioContentTextMoveTo moves within the current line in a text block
 
 .IP \(bu 5
 .PP
-pdfioContentTextNextLine moves to the beginning of the next line in a text block
+pdfioContentTextNewLine moves to the beginning of the next line in a text block
+
+.IP \(bu 5
+.PP
+pdfioContentTextNewLineShow moves to the beginning of the next line in a text block and shows literal text with optional word and character spacing
+
+.IP \(bu 5
+.PP
+pdfioContentTextNewLineShowf moves to the beginning of the next line in a text block and shows formatted text with optional word and character spacing
 
 .IP \(bu 5
 .PP
@@ -814,6 +870,125 @@ pdfioContentTextShowf draws a formatted string in a text block
 pdfioContentTextShowJustified draws an array of literal strings with offsets between them
 
 
+.SH Examples
+.SS Read PDF Metadata
+.PP
+The following example function will open a PDF file and print the title, author, creation date, and number of pages:
+.nf
+
+    #include <pdfio.h>
+    #include <time.h>
+    
+    
+    void
+    show_pdf_info(const char *filename)
+    {
+      pdfio_file_t *pdf;
+      time_t       creation_date;
+      struct tm    *creation_tm;
+      char         creation_text[256];
+    
+    
+      // Open the PDF file with the default callbacks...
+      pdf = pdfioFileOpen(filename, /*password_cb*/NULL, /*password_cbdata*/NULL, /*error_cb*/NULL, /*error_cbdata*/NULL);
+      if (pdf == NULL)
+        return;
+    
+      // Get the creation date and convert to a string...
+      creation_date = pdfioFileGetCreationDate(pdf);
+      creation_tm   = localtime(&creation_date);
+      strftime(creation_text, sizeof(creation_text), "%c", &creation_tm);
+    
+      // Print file information to stdout...
+      printf("%s:\\n", filename);
+      printf("         Title: %s\\n", pdfioFileGetTitle(pdf));
+      printf("        Author: %s\\n", pdfioFileGetAuthor(pdf));
+      printf("    Created On: %s\\n", creation_text);
+      printf("  Number Pages: %u\\n", (unsigned)pdfioFileGetNumPages(pdf));
+    
+      // Close the PDF file...
+      pdfioFileClose(pdf);
+    }
+.fi
+.SS Create PDF File With Text and Image
+.PP
+The following example function will create a PDF file, embed a base font and the named JPEG or PNG image file, and then creates a page with the image centered on the page with the text centered below:
+.nf
+
+    #include <pdfio.h>
+    #include <pdfio\-content.h>
+    #include <string.h>
+    
+    
+    void
+    create_pdf_image_file(const char *pdfname, const char *imagename, const char *caption)
+    {
+      pdfio_file_t   *pdf;
+      pdfio_obj_t    *font;
+      pdfio_obj_t    *image;
+      pdfio_dict_t   *dict;
+      pdfio_stream_t *page;
+      double         width, height;
+      double         swidth, sheight;
+      double         tx, ty;
+    
+    
+      // Create the PDF file...
+      pdf = pdfioFileCreate(pdfname, /*version*/NULL, /*media_box*/NULL, /*crop_box*/NULL, /*error_cb*/NULL, /*error_cbdata*/NULL);
+    
+      // Create a Courier base font for the caption
+      font = pdfioFileCreateFontObjFromBase(pdf, "Courier");
+    
+      // Create an image object from the JPEG/PNG image file...
+      image = pdfioFileCreateImageObjFromFile(pdf, imagename, true);
+    
+      // Create a page dictionary with the font and image...
+      dict = pdfioDictCreate(pdf);
+      pdfioPageDictAddFont(dict, "F1", font);
+      pdfioPageDictAddImage(dict, "IM1", image);
+    
+      // Create the page and its content stream...
+      page = pdfioFileCreatePage(pdf, dict);
+    
+      // Position and scale the image on the page...
+      width  = pdfioImageGetWidth(image);
+      height = pdfioImageGetHeight(image);
+    
+      // Default media_box is "universal" 595.28x792 points (8.27x11in or 210x279mm)
+      // Use margins of 36 points (0.5in or 12.7mm) with another 36 points for the
+      // caption underneath...
+      swidth  = 595.28 \- 72.0;
+      sheight = swidth * height / width;
+      if (sheight > (792.0 \- 36.0 \- 72.0))
+      {
+        sheight = 792.0 \- 36.0 \- 72.0;
+        swidth  = sheight * width / height;
+      }
+    
+      tx = 0.5 * (595.28 \- swidth);
+      ty = 0.5 * (792 \- 36 \- sheight);
+    
+      pdfioContentDrawImage(page, "IM1", tx, ty + 36.0, swidth, sheight);
+    
+      // Draw the caption in black...
+      pdfioContentSetFillColorDeviceGray(page, 0.0);
+    
+      // Compute the starting point for the text \- Courier is monospaced with a
+      // nominal width of 0.6 times the text height...
+      tx = 0.5 * (595.28 \- 18.0 * 0.6 * strlen(caption));
+    
+      // Position and draw the caption underneath...
+      pdfioContentTextBegin(page);
+      pdfioContentSetTextFont(page, "F1", 18.0);
+      pdfioContentTextMoveTo(page, tx, ty);
+      pdfioContentTextShow(page, /*unicode*/false, caption);
+      pdfioContentTextEnd(page);
+    
+      // Close the page stream and the PDF file...
+      pdfioStreamClose(page);
+      pdfioFileClose(pdf);
+    }
+.fi
 
 .SH ENUMERATIONS
 .SS pdfio_cs_e
@@ -839,7 +1014,7 @@ PDFIO_ENCRYPTION_AES_128
 .TP 5
 PDFIO_ENCRYPTION_AES_256
 .br
-256-bit AES encryption (PDF 2.0)
+256-bit AES encryption (PDF 2.0) 
 .TP 5
 PDFIO_ENCRYPTION_NONE
 .br
@@ -1357,7 +1532,7 @@ bool  pdfioContentFillAndStroke (
 .fi
 .SS pdfioContentMatrixConcat
 Concatenate a matrix to the current graphics
-state.
+                               state.
 .PP
 .nf
 bool  pdfioContentMatrixConcat (
@@ -1507,6 +1682,9 @@ bool  pdfioContentSetDashPattern (
     double off
 );
 .fi
+.PP
+This function sets the stroke pattern when drawing lines.  If "on" and "off"
+are 0, a solid line is drawn.
 .SS pdfioContentSetFillColorDeviceCMYK
 Set device CMYK fill color.
 .PP
@@ -1771,6 +1949,20 @@ bool  pdfioContentTextEnd (
     pdfio_stream_t *st
 );
 .fi
+.SS pdfioContentTextMeasure
+Measure a text string and return its width.
+.PP
+.nf
+double  pdfioContentTextMeasure (
+    pdfio_obj_t *font,
+    const char *s,
+    double size
+);
+.fi
+.PP
+This function measures the given text string "s" and returns its width based
+on "size". The text string must always use the UTF-8 (Unicode) encoding but
+any control characters (such as newlines) are ignored.
 .SS pdfioContentTextMoveLine
 Move to the next line and offset.
 .PP
@@ -1791,14 +1983,49 @@ bool  pdfioContentTextMoveTo (
     double ty
 );
 .fi
-.SS pdfioContentTextNextLine
+.SS pdfioContentTextNewLine
 Move to the next line.
 .PP
 .nf
-bool  pdfioContentTextNextLine (
+bool  pdfioContentTextNewLine (
     pdfio_stream_t *st
 );
 .fi
+.SS pdfioContentTextNewLineShow
+Move to the next line and show text.
+.PP
+.nf
+bool  pdfioContentTextNewLineShow (
+    pdfio_stream_t *st,
+    double ws,
+    double cs,
+    bool unicode,
+    const char *s
+);
+.fi
+.PP
+This function moves to the next line and then shows some text with optional
+word and character spacing in a PDF content stream. The "unicode" argument
+specifies that the current font maps to full Unicode.  The "s" argument
+specifies a UTF-8 encoded string.
+.SS pdfioContentTextNewLineShowf
+Show formatted text.
+.PP
+.nf
+bool  pdfioContentTextNewLineShowf (
+    pdfio_stream_t *st,
+    double ws,
+    double cs,
+    bool unicode,
+    const char *format,
+    ...
+);
+.fi
+.PP
+This function moves to the next line and shows some formatted text with
+optional word and character spacing in a PDF content stream. The "unicode"
+argument specifies that the current font maps to full Unicode.  The "format"
+argument specifies a UTF-8 encoded \fBprintf\fR-style format string.
 .SS pdfioContentTextShow
 Show text.
 .PP
@@ -1981,6 +2208,7 @@ function "cb":
     }
 
 .fi
+
 The iteration continues as long as the callback returns \fBtrue\fR or all keys
 have been iterated.
 .SS pdfioDictSetArray
@@ -2122,7 +2350,7 @@ pdfio_file_t * pdfioFileCreate (
     pdfio_rect_t *media_box,
     pdfio_rect_t *crop_box,
     pdfio_error_cb_t error_cb,
-    void *error_data
+    void *error_cbdata
 );
 .fi
 .PP
@@ -2136,7 +2364,7 @@ The "media_box" and "crop_box" arguments specify the default MediaBox and
 CropBox for pages in the PDF file - if \fBNULL\fR then a default "Universal" size
 of 8.27x11in (the intersection of US Letter and ISO A4) is used.
 .PP
-The "error_cb" and "error_data" arguments specify an error handler callback
+The "error_cb" and "error_cbdata" arguments specify an error handler callback
 and its data pointer - if \fBNULL\fR the default error handler is used that
 writes error messages to \fBstderr\fR.
 .SS pdfioFileCreateArrayObj
@@ -2272,6 +2500,18 @@ Note: Currently PNG support is limited to grayscale, RGB, or indexed files
 without interlacing or alpha.  Transparency (masking) based on color/index
 .IP 5
 is supported.
+.SS pdfioFileCreateNumberObj
+Create a new object in a PDF file containing a number.
+.PP
+.nf
+pdfio_obj_t * pdfioFileCreateNumberObj (
+    pdfio_file_t *pdf,
+    double number
+);
+.fi
+.PP
+This function creates a new object with a number value in a PDF file.
+You must call \fIpdfioObjClose\fR to write the object to the file.
 .SS pdfioFileCreateObj
 Create a new object in a PDF file.
 .PP
@@ -2287,28 +2527,29 @@ Create a PDF file through an output callback.
 .nf
 pdfio_file_t * pdfioFileCreateOutput (
     pdfio_output_cb_t output_cb,
-    void *output_ctx,
+    void *output_cbdata,
     const char *version,
     pdfio_rect_t *media_box,
     pdfio_rect_t *crop_box,
     pdfio_error_cb_t error_cb,
-    void *error_data
+    void *error_cbdata
 );
 .fi
 .PP
 This function creates a new PDF file that is streamed though an output
-callback.  The "output_cb" and "output_ctx" arguments specify the output
+callback.  The "output_cb" and "output_cbdata" arguments specify the output
-callback and its context pointer which is called whenever data needs to be
+callback and its data pointer which is called whenever data needs to be
 written:
 .PP
 .nf
     ssize_t
-    output_cb(void *output_ctx, const void *buffer, size_t bytes)
+    output_cb(void *output_cbdata, const void *buffer, size_t bytes)
     {
-    // Write buffer to output and return the number of bytes written
+      // Write buffer to output and return the number of bytes written
     }
 
 .fi
+
 The "version" argument specifies the PDF version number for the file or
 \fBNULL\fR for the default ("2.0").
 .PP
@@ -2316,7 +2557,7 @@ The "media_box" and "crop_box" arguments specify the default MediaBox and
 CropBox for pages in the PDF file - if \fBNULL\fR then a default "Universal" size
 of 8.27x11in (the intersection of US Letter and ISO A4) is used.
 .PP
-The "error_cb" and "error_data" arguments specify an error handler callback
+The "error_cb" and "error_cbdata" arguments specify an error handler callback
 and its data pointer - if \fBNULL\fR the default error handler is used that
 writes error messages to \fBstderr\fR.
 .PP
@@ -2335,6 +2576,18 @@ pdfio_stream_t * pdfioFileCreatePage (
     pdfio_dict_t *dict
 );
 .fi
+.SS pdfioFileCreateStringObj
+Create a new object in a PDF file containing a string.
+.PP
+.nf
+pdfio_obj_t * pdfioFileCreateStringObj (
+    pdfio_file_t *pdf,
+    const char *string
+);
+.fi
+.PP
+This function creates a new object with a string value in a PDF file.
+You must call \fIpdfioObjClose\fR to write the object to the file.
 .SS pdfioFileCreateTemporary
 
 .PP
@@ -2346,7 +2599,7 @@ pdfio_file_t * pdfioFileCreateTemporary (
     pdfio_rect_t *media_box,
     pdfio_rect_t *crop_box,
     pdfio_error_cb_t error_cb,
-    void *error_data
+    void *error_cbdata
 );
 .fi
 .SS pdfioFileFindObj
@@ -2369,6 +2622,16 @@ const char * pdfioFileGetAuthor (
     pdfio_file_t *pdf
 );
 .fi
+.SS pdfioFileGetCatalog
+Get the document catalog dictionary.
+.PP
+.nf
+pdfio_dict_t * pdfioFileGetCatalog (
+    pdfio_file_t *pdf
+);
+.fi
+.PP
+
 .SS pdfioFileGetCreationDate
 Get the creation date for a PDF file.
 .PP
@@ -2494,22 +2757,22 @@ Open a PDF file for reading.
 pdfio_file_t * pdfioFileOpen (
     const char *filename,
     pdfio_password_cb_t password_cb,
-    void *password_data,
+    void *password_cbdata,
     pdfio_error_cb_t error_cb,
-    void *error_data
+    void *error_cbdata
 );
 .fi
 .PP
 This function opens an existing PDF file.  The "filename" argument specifies
 the name of the PDF file to create.
 .PP
-The "password_cb" and "password_data" arguments specify a password callback
+The "password_cb" and "password_cbdata" arguments specify a password callback
 and its data pointer for PDF files that use one of the standard Adobe
 "security" handlers.  The callback returns a password string or \fBNULL\fR to
 cancel the open.  If \fBNULL\fR is specified for the callback function and the
 PDF file requires a password, the open will always fail.
 .PP
-The "error_cb" and "error_data" arguments specify an error handler callback
+The "error_cb" and "error_cbdata" arguments specify an error handler callback
 and its data pointer - if \fBNULL\fR the default error handler is used that
 writes error messages to \fBstderr\fR.
 .SS pdfioFileSetAuthor
@@ -2616,7 +2879,7 @@ double  pdfioImageGetWidth (
 .fi
 .SS pdfioObjClose
 Close an object, writing any data as needed to the PDF
-file.
+                    file.
 .PP
 .nf
 bool  pdfioObjClose (
@@ -2689,6 +2952,29 @@ const char * pdfioObjGetSubtype (
     pdfio_obj_t *obj
 );
 .fi
+.PP
+This function returns an object's PDF subtype name, if any.  Common subtype
+names include:
+.PP
+.IP \(bu 5
+"CIDFontType0": A CID Type0 font
+.IP \(bu 5
+"CIDFontType2": A CID TrueType font
+.IP \(bu 5
+"Image": An image or image mask
+.IP \(bu 5
+"Form": A fillable form
+.IP \(bu 5
+"OpenType": An OpenType font
+.IP \(bu 5
+"Type0": A composite font
+.IP \(bu 5
+"Type1": A PostScript Type1 font
+.IP \(bu 5
+"Type3": A PDF Type3 font
+.IP \(bu 5
+"TrueType": A TrueType font</li>
+</ul>
 .SS pdfioObjGetType
 Get an object's type.
 .PP
@@ -2697,6 +2983,27 @@ const char * pdfioObjGetType (
     pdfio_obj_t *obj
 );
 .fi
+.PP
+This function returns an object's PDF type name, if any. Common type names
+include:
+.PP
+.IP \(bu 5
+"CMap": A character map for composite fonts
+.IP \(bu 5
+"Font": An embedded font (\fIpdfioObjGetSubtype\fR will tell you the
+  font format)
+.IP \(bu 5
+"FontDescriptor": A font descriptor
+.IP \(bu 5
+"Page": A (visible) page
+.IP \(bu 5
+"Pages": A page tree node
+.IP \(bu 5
+"Template": An invisible template page
+.IP \(bu 5
+"XObject": An image, image mask, or form (\fIpdfioObjGetSubtype\fR will
+  tell you which)</li>
+</ul>
 .SS pdfioObjOpenStream
 Open an object's (data) stream for reading.
 .PP
@@ -2802,6 +3109,13 @@ bool  pdfioStreamGetToken (
     size_t bufsize
 );
 .fi
+.PP
+This function reads a single PDF token from a stream.  Operator tokens,
+boolean values, and numbers are returned as-is in the provided string buffer.
+String values start with the opening parenthesis ('(') but have all escaping
+resolved and the terminating parenthesis removed.  Hexadecimal string values
+start with the opening angle bracket ('<') and have all whitespace and the
+terminating angle bracket removed.
 .SS pdfioStreamPeek
 Peek at data in a stream.
 .PP
@@ -3024,15 +3338,9 @@ PDF value types
 .nf
 typedef enum pdfio_valtype_e pdfio_valtype_t;
 .fi
-.SS state_t[4][4]
-4x4 AES state table
-.PP
-.nf
-typedef uint8_t state_t[4][4];
-.fi
 .SH AUTHOR
 .PP
 Michael R Sweet
 .SH COPYRIGHT
 .PP
-Copyright (c) 2021-2022 by Michael R Sweet
+Copyright (c) 2021-2024 by Michael R Sweet

doc/pdfio.md

@@ -15,7 +15,7 @@ goals of pdfio are:
 PDFio is *not* concerned with rendering or viewing a PDF file, although a PDF
 RIP or viewer could be written using it.
 
-PDFio is Copyright © 2021-2022 by Michael R Sweet and is licensed under the
+PDFio is Copyright © 2021-2024 by Michael R Sweet and is licensed under the
 Apache License Version 2.0 with an (optional) exception to allow linking against
 GPL2/LGPL2 software.  See the files "LICENSE" and "NOTICE" for more information.
 
@@ -27,6 +27,7 @@ PDFio requires the following to build the software:
 
 - A C99 compiler such as Clang, GCC, or MS Visual C
 - A POSIX-compliant `make` program
+- A POSIX-compliant `sh` program
 - ZLIB (<https://www.zlib.net>) 1.0 or higher
 
 IDE files for Xcode (macOS/iOS) and Visual Studio (Windows) are also provided.
@@ -35,10 +36,11 @@ IDE files for Xcode (macOS/iOS) and Visual Studio (Windows) are also provided.
 Installing pdfio
 ----------------
 
-PDFio comes with a portable makefile that will work on any POSIX-compliant
+PDFio comes with a configure script that creates a portable makefile that will
-system with ZLIB installed.  To make it, run:
+work on any POSIX-compliant system with ZLIB installed.  To make it, run:
 
-    make all
+    ./configure
+    make
 
 To test it, run:
 
@@ -46,45 +48,22 @@ To test it, run:
 
 To install it, run:
 
-    make install
+    sudo make install
 
 If you want a shared library, run:
 
-    make all-shared
+    ./configure --enable-shared
-    make install-shared
+    make
+    sudo make install
 
-The default installation location is "/usr/local".  Pass the `prefix` variable
+The default installation location is "/usr/local".  Pass the `--prefix` option
 to make to install it to another location:
 
-    make install prefix=/some/other/directory
+    ./configure --prefix=/some/other/directory
 
-The makefile installs the pdfio header to "${prefix}/include", the library to
+Other configure options can be found using the `--help` option:
-"${prefix}/lib", the `pkg-config` file to "${prefix}/lib/pkgconfig", the man
-page to "${prefix}/share/man/man3", and the documentation to
-"${prefix}/share/doc/pdfio".
 
-The makefile supports the following variables that can be specified in the make
+    ./configure --help
-command or as environment variables:
-
-- `AR`: the library archiver (default "ar")
-- `ARFLAGS`: options for the library archiver (default "cr")
-- `CC`: the C compiler (default "cc")
-- `CFLAGS`: options for the C compiler (default "")
-- `CODESIGN_IDENTITY`: the identity to use when code signing the shared library
-  on macOS (default "Developer ID")
-- `COMMONFLAGS`: options for the C compiler and linker (typically architecture
-  and optimization options, default is "-Os -g")
-- `CPPFLAGS`: options for the C preprocessor (default "")
-- `DESTDIR` and `DSTROOT`: specifies a root directory when installing
-  (default is "", specify only one)
-- `DSOFLAGS`: options for the C compiler when linking the shared library
-  (default "")
-- `LDFLAGS`: options for the C compiler when linking the test programs
-  (default "")
-- `LIBS`: library options when linking the test programs (default "-lz")
-- `RANLIB`: program that generates a table-of-contents in a library
-  (default "ranlib")
-- `prefix`: specifies the installation directory (default "/usr/local")
 
 
 Visual Studio Project
@@ -102,10 +81,6 @@ generates a static library that will be installed under "/usr/local" with:
 
     sudo xcodebuild install
 
-You can reproduce this with the makefile using:
-
-    sudo make macos install
-
 
 Detecting PDFio
 ---------------
@@ -163,15 +138,32 @@ Reading PDF Files
 You open an existing PDF file using the [`pdfioFileOpen`](@@) function:
 
 ```c
-pdfio_file_t *pdf = pdfioFileOpen("myinputfile.pdf", error_cb, error_data);
+pdfio_file_t *pdf = pdfioFileOpen("myinputfile.pdf", password_cb, password_data,
+                                  error_cb, error_data);
 
 ```
 
-where the three arguments to the function are the filename ("myinputfile.pdf"),
+where the five arguments to the function are the filename ("myinputfile.pdf"),
-an optional error callback function (`error_cb`), and an optional pointer value
+an optional password callback function (`password_cb`) and data pointer value
-for the error callback function (`error_data`).  The error callback is called
+(`password_data`), and an optional error callback function (`error_cb`) and data
-for both errors and warnings and accepts the `pdfio_file_t` pointer, a message
+pointer value (`error_data`).  The password callback is called for encrypted PDF
-string, and the callback pointer value, for example:
+files that are not using the default password, for example:
+
+```c
+const char *
+password_cb(void *data, const char *filename)
+{
+  (void)data;     // This callback doesn't use the data pointer
+  (void)filename; // This callback doesn't use the filename
+
+  // Return a password string for the file...
+  return ("Password42");
+}
+```
+
+The error callback is called for both errors and warnings and accepts the
+`pdfio_file_t` pointer, a message string, and the callback pointer value, for
+example:
 
 ```c
 bool
@@ -210,7 +202,74 @@ Each page is represented by a "page tree" object (what [`pdfioFileGetPage`](@@)
 returns) that specifies information about the page and one or more "content"
 objects that contain the images, fonts, text, and graphics that appear on the
 page.  Use the [`pdfioPageGetNumStreams`](@@) and [`pdfioPageOpenStream`](@@)
-functions to access the content streams for each page.
+functions to access the content streams for each page, and
+[`pdfioObjGetDict`](@@) to get the associated page object dictionary.  For
+example, if you want to display the media and crop boxes for a given page:
+
+```c
+pdfio_file_t  *pdf;             // PDF file
+size_t        i;                // Looping var
+size_t        count;            // Number of pages
+pdfio_obj_t   *page;            // Current page
+pdfio_dict_t  *dict;            // Current page dictionary
+pdfio_array_t *media_box;       // MediaBox array
+double        media_values[4];  // MediaBox values
+pdfio_array_t *crop_box;        // CropBox array
+double        crop_values[4];   // CropBox values
+
+// Iterate the pages in the PDF file
+for (i = 0, count = pdfioFileGetNumPages(pdf); i < count; i ++)
+{
+  page = pdfioFileGetPage(pdf, i);
+  dict = pdfioObjGetDict(page);
+
+  media_box       = pdfioDictGetArray(dict, "MediaBox");
+  media_values[0] = pdfioArrayGetNumber(media_box, 0);
+  media_values[1] = pdfioArrayGetNumber(media_box, 1);
+  media_values[2] = pdfioArrayGetNumber(media_box, 2);
+  media_values[3] = pdfioArrayGetNumber(media_box, 3);
+
+  crop_box       = pdfioDictGetArray(dict, "CropBox");
+  crop_values[0] = pdfioArrayGetNumber(crop_box, 0);
+  crop_values[1] = pdfioArrayGetNumber(crop_box, 1);
+  crop_values[2] = pdfioArrayGetNumber(crop_box, 2);
+  crop_values[3] = pdfioArrayGetNumber(crop_box, 3);
+
+  printf("Page %u: MediaBox=[%g %g %g %g], CropBox=[%g %g %g %g]\n",
+         (unsigned)(i + 1),
+         media_values[0], media_values[1], media_values[2], media_values[3],
+         crop_values[0], crop_values[1], crop_values[2], crop_values[3]);
+}
+```
+
+Page object dictionaries have several (mostly optional) key/value pairs,
+including:
+
+- "Annots": An array of annotation dictionaries for the page; use
+  [`pdfioDictGetArray`](@@) to get the array
+- "CropBox": The crop box as an array of four numbers for the left, bottom,
+  right, and top coordinates of the target media; use [`pdfioDictGetArray`](@@)
+  to get a pointer to the array of numbers
+- "Dur": The number of seconds the page should be displayed; use
+  [`pdfioDictGetNumber`](@@) to get the page duration value
+- "Group": The dictionary of transparency group values for the page; use
+  [`pdfioDictGetDict`](@@) to get a pointer to the resources dictionary
+- "LastModified": The date and time when this page was last modified; use
+  [`pdfioDictGetDate`](@@) to get the Unix `time_t` value
+- "Parent": The parent page tree node object for this page; use
+  [`pdfioDictGetObj`](@@) to get a pointer to the object
+- "MediaBox": The media box as an array of four numbers for the left, bottom,
+  right, and top coordinates of the target media; use [`pdfioDictGetArray`](@@)
+  to get a pointer to the array of numbers
+- "Resources": The dictionary of resources for the page; use
+  [`pdfioDictGetDict`](@@) to get a pointer to the resources dictionary
+- "Rotate": A number indicating the number of degrees of counter-clockwise
+  rotation to apply to the page when viewing; use [`pdfioDictGetNumber`](@@)
+  to get the rotation angle
+- "Thumb": A thumbnail image object for the page; use [`pdfioDictGetObj`](@@)
+  to get a pointer to the thumbnail image object
+- "Trans": The page transition dictionary; use [`pdfioDictGetDict`](@@) to get
+  a pointer to the dictionary
 
 The [`pdfioFileClose`](@@) function closes a PDF file and frees all memory that
 was used for it:
@@ -353,7 +412,7 @@ to the stream:
 The [PDF content helper functions](@) provide additional functions for writing
 specific PDF page stream commands.
 
-When you are done writing the stream, call [`pdfioStreamCLose`](@@) to close
+When you are done writing the stream, call [`pdfioStreamClose`](@@) to close
 both the stream and the object.
 
 
@@ -361,7 +420,7 @@ PDF Content Helper Functions
 ----------------------------
 
 PDFio includes many helper functions for embedding or writing specific kinds of
-content to a PDF file.  These functions can be roughly grouped into ???
+content to a PDF file.  These functions can be roughly grouped into five
 categories:
 
 - [Color Space Functions](@)
@@ -455,7 +514,7 @@ pdfio_obj_t *arial = pdfioFileCreateFontObjFromFile(pdf, "NotoSansJP-Regular.otf
 
 will embed the NotoSansJP Regular OpenType font with full support for Unicode.
 
-Note: Not all fonts support Unicode.
+> Note: Not all fonts support Unicode.
 
 
 ### Image Object Functions
@@ -584,9 +643,143 @@ escaping, as needed:
 - [`pdfioContentTextMoveLine`](@@) moves to the next line with an offset in a
   text block
 - [`pdfioContentTextMoveTo`](@@) moves within the current line in a text block
-- [`pdfioContentTextNextLine`](@@) moves to the beginning of the next line in a
+- [`pdfioContentTextNewLine`](@@) moves to the beginning of the next line in a
   text block
+- [`pdfioContentTextNewLineShow`](@@) moves to the beginning of the next line in a
+  text block and shows literal text with optional word and character spacing
+- [`pdfioContentTextNewLineShowf`](@@) moves to the beginning of the next line in a
+  text block and shows formatted text with optional word and character spacing
 - [`pdfioContentTextShow`](@@) draws a literal string in a text block
 - [`pdfioContentTextShowf`](@@) draws a formatted string in a text block
 - [`pdfioContentTextShowJustified`](@@) draws an array of literal strings with
   offsets between them
+
+
+Examples
+========
+
+Read PDF Metadata
+-----------------
+
+The following example function will open a PDF file and print the title, author,
+creation date, and number of pages:
+
+```c
+#include <pdfio.h>
+#include <time.h>
+
+
+void
+show_pdf_info(const char *filename)
+{
+  pdfio_file_t *pdf;
+  time_t       creation_date;
+  struct tm    *creation_tm;
+  char         creation_text[256];
+
+
+  // Open the PDF file with the default callbacks...
+  pdf = pdfioFileOpen(filename, /*password_cb*/NULL, /*password_cbdata*/NULL, /*error_cb*/NULL, /*error_cbdata*/NULL);
+  if (pdf == NULL)
+    return;
+
+  // Get the creation date and convert to a string...
+  creation_date = pdfioFileGetCreationDate(pdf);
+  creation_tm   = localtime(&creation_date);
+  strftime(creation_text, sizeof(creation_text), "%c", &creation_tm);
+
+  // Print file information to stdout...
+  printf("%s:\n", filename);
+  printf("         Title: %s\n", pdfioFileGetTitle(pdf));
+  printf("        Author: %s\n", pdfioFileGetAuthor(pdf));
+  printf("    Created On: %s\n", creation_text);
+  printf("  Number Pages: %u\n", (unsigned)pdfioFileGetNumPages(pdf));
+
+  // Close the PDF file...
+  pdfioFileClose(pdf);
+}
+```
+
+
+Create PDF File With Text and Image
+-----------------------------------
+
+The following example function will create a PDF file, embed a base font and the
+named JPEG or PNG image file, and then creates a page with the image centered on
+the page with the text centered below:
+
+```c
+#include <pdfio.h>
+#include <pdfio-content.h>
+#include <string.h>
+
+
+void
+create_pdf_image_file(const char *pdfname, const char *imagename, const char *caption)
+{
+  pdfio_file_t   *pdf;
+  pdfio_obj_t    *font;
+  pdfio_obj_t    *image;
+  pdfio_dict_t   *dict;
+  pdfio_stream_t *page;
+  double         width, height;
+  double         swidth, sheight;
+  double         tx, ty;
+
+
+  // Create the PDF file...
+  pdf = pdfioFileCreate(pdfname, /*version*/NULL, /*media_box*/NULL, /*crop_box*/NULL, /*error_cb*/NULL, /*error_cbdata*/NULL);
+
+  // Create a Courier base font for the caption
+  font = pdfioFileCreateFontObjFromBase(pdf, "Courier");
+
+  // Create an image object from the JPEG/PNG image file...
+  image = pdfioFileCreateImageObjFromFile(pdf, imagename, true);
+
+  // Create a page dictionary with the font and image...
+  dict = pdfioDictCreate(pdf);
+  pdfioPageDictAddFont(dict, "F1", font);
+  pdfioPageDictAddImage(dict, "IM1", image);
+
+  // Create the page and its content stream...
+  page = pdfioFileCreatePage(pdf, dict);
+
+  // Position and scale the image on the page...
+  width  = pdfioImageGetWidth(image);
+  height = pdfioImageGetHeight(image);
+
+  // Default media_box is "universal" 595.28x792 points (8.27x11in or 210x279mm)
+  // Use margins of 36 points (0.5in or 12.7mm) with another 36 points for the
+  // caption underneath...
+  swidth  = 595.28 - 72.0;
+  sheight = swidth * height / width;
+  if (sheight > (792.0 - 36.0 - 72.0))
+  {
+    sheight = 792.0 - 36.0 - 72.0;
+    swidth  = sheight * width / height;
+  }
+
+  tx = 0.5 * (595.28 - swidth);
+  ty = 0.5 * (792 - 36 - sheight);
+
+  pdfioContentDrawImage(page, "IM1", tx, ty + 36.0, swidth, sheight);
+
+  // Draw the caption in black...
+  pdfioContentSetFillColorDeviceGray(page, 0.0);
+
+  // Compute the starting point for the text - Courier is monospaced with a
+  // nominal width of 0.6 times the text height...
+  tx = 0.5 * (595.28 - 18.0 * 0.6 * strlen(caption));
+
+  // Position and draw the caption underneath...
+  pdfioContentTextBegin(page);
+  pdfioContentSetTextFont(page, "F1", 18.0);
+  pdfioContentTextMoveTo(page, tx, ty);
+  pdfioContentTextShow(page, /*unicode*/false, caption);
+  pdfioContentTextEnd(page);
+
+  // Close the page stream and the PDF file...
+  pdfioStreamClose(page);
+  pdfioFileClose(pdf);
+}
+```

install-sh

@@ -0,0 +1,232 @@
+#!/bin/sh
+#
+# Install a program, script, or datafile.
+#
+# Copyright 2008-2012 by Apple Inc.
+#
+# This script is not compatible with BSD (or any other) install program, as it
+# allows owner and group changes to fail with a warning and makes sure that the
+# destination directory permissions are as specified - BSD install and the
+# original X11 install script did not change permissions of existing
+# directories.  It also does not support the transform options since CUPS does
+# not use them...
+#
+# Original script from X11R5 (mit/util/scripts/install.sh)
+# Copyright 1991 by the Massachusetts Institute of Technology
+#
+# Permission to use, copy, modify, distribute, and sell this software and its
+# documentation for any purpose is hereby granted without fee, provided that
+# the above copyright notice appear in all copies and that both that
+# copyright notice and this permission notice appear in supporting
+# documentation, and that the name of M.I.T. not be used in advertising or
+# publicity pertaining to distribution of the software without specific,
+# written prior permission.  M.I.T. makes no representations about the
+# suitability of this software for any purpose.  It is provided "as is"
+# without express or implied warranty.
+#
+# Calling this script install-sh is preferred over install.sh, to prevent
+# `make' implicit rules from creating a file called install from it
+# when there is no Makefile.
+
+# set DOITPROG to echo to test this script
+# Don't use :- since 4.3BSD and earlier shells don't like it.
+doit="${DOITPROG-}"
+
+# Force umask to 022...
+umask 022
+
+# put in absolute paths if you don't have them in your path; or use env. vars.
+mvprog="${MVPROG-mv}"
+cpprog="${CPPROG-cp}"
+chmodprog="${CHMODPROG-chmod}"
+chownprog="${CHOWNPROG-chown}"
+chgrpprog="${CHGRPPROG-chgrp}"
+stripprog="${STRIPPROG-strip}"
+rmprog="${RMPROG-rm}"
+mkdirprog="${MKDIRPROG-mkdir}"
+gzipprog="${GZIPPROG-gzip}"
+
+transformbasename=""
+transform_arg=""
+instcmd="$mvprog"
+chmodcmd="$chmodprog 0755"
+chowncmd=""
+chgrpcmd=""
+stripcmd=""
+rmcmd="$rmprog -f"
+mvcmd="$mvprog"
+src=""
+dst=""
+dir_arg=""
+
+gzipcp() {
+	# gzipcp from to
+	$gzipprog -9 <"$1" >"$2"
+}
+
+while [ x"$1" != x ]; do
+	case $1 in
+		-c)
+		instcmd="$cpprog"
+		shift
+		continue
+		;;
+
+		-d)
+		dir_arg=true
+		shift
+		continue
+		;;
+
+		-m)
+		chmodcmd="$chmodprog $2"
+		shift
+		shift
+		continue
+		;;
+
+		-o)
+		chowncmd="$chownprog $2"
+		shift
+		shift
+		continue
+		;;
+
+		-g)
+		chgrpcmd="$chgrpprog $2"
+		shift
+		shift
+		continue
+		;;
+
+		-s)
+		stripcmd="$stripprog"
+		shift
+		continue
+		;;
+
+		-z)
+		instcmd="gzipcp"
+		shift
+		continue
+		;;
+
+		*)
+		if [ x"$src" = x ]; then
+			src="$1"
+		else
+			dst="$1"
+		fi
+		shift
+		continue
+		;;
+	esac
+done
+
+if [ x"$src" = x ]; then
+	echo "install-sh: No input file specified"
+	exit 1
+fi
+
+if [ x"$dir_arg" != x ]; then
+	dst="$src"
+	src=""
+
+	if [ -d "$dst" ]; then
+		instcmd=:
+	else
+		instcmd=$mkdirprog
+	fi
+else
+	# Waiting for this to be detected by the "$instcmd $src $dsttmp" command
+	# might cause directories to be created, which would be especially bad
+	# if $src (and thus $dsttmp) contains '*'.
+	if [ ! -f "$src" -a ! -d "$src" ]; then
+		echo "install: $src does not exist"
+		exit 1
+	fi
+
+	if [ x"$dst" = x ]; then
+		echo "install: No destination specified"
+		exit 1
+	fi
+
+	# If destination is a directory, append the input filename.
+	if [ -d "$dst" ]; then
+		dst="$dst/`basename $src`"
+	fi
+fi
+
+## this sed command emulates the dirname command
+dstdir="`echo $dst | sed -e 's,[^/]*$,,;s,/$,,;s,^$,.,'`"
+
+# Make sure that the destination directory exists.
+# This part is taken from Noah Friedman's mkinstalldirs script
+
+# Skip lots of stat calls in the usual case.
+if [ ! -d "$dstdir" ]; then
+	defaultIFS='
+	'
+	IFS="${IFS-${defaultIFS}}"
+
+	oIFS="${IFS}"
+	# Some sh's can't handle IFS=/ for some reason.
+	IFS='%'
+	set - `echo ${dstdir} | sed -e 's@/@%@g' -e 's@^%@/@'`
+	IFS="${oIFS}"
+
+	pathcomp=''
+
+	while [ $# -ne 0 ] ; do
+		pathcomp="${pathcomp}${1}"
+		shift
+
+		if [ ! -d "${pathcomp}" ]; then $doit $mkdirprog "${pathcomp}"; fi
+
+		pathcomp="${pathcomp}/"
+	done
+fi
+
+if [ x"$dir_arg" != x ]; then
+	# Make a directory...
+	$doit $instcmd $dst || exit 1
+
+	# Allow chown/chgrp to fail, but log a warning
+	if [ x"$chowncmd" != x ]; then $doit $chowncmd $dst || echo "warning: Unable to change owner of $dst!"; fi
+	if [ x"$chgrpcmd" != x ]; then $doit $chgrpcmd $dst || echo "warning: Unable to change group of $dst!"; fi
+	if [ x"$chmodcmd" != x ]; then $doit $chmodcmd $dst || exit 1; fi
+else
+	# Install a file...
+	dstfile="`basename $dst`"
+
+	# Check the destination file - for libraries just use the "-x" option
+	# to strip...
+	case "$dstfile" in
+		*.a | *.dylib | *.sl | *.sl.* | *.so | *.so.*)
+			stripopt="-x"
+			;;
+		*)
+			stripopt=""
+			;;
+	esac
+
+	# Make a temp file name in the proper directory.
+	dsttmp="$dstdir/#inst.$$#"
+
+	# Move or copy the file name to the temp name
+	$doit $instcmd $src $dsttmp || exit 1
+
+	# Update permissions and strip as needed, then move to the final name.
+	# If the chmod, strip, rm, or mv commands fail, remove the installed
+	# file...
+	if [ x"$stripcmd" != x ]; then $doit $stripcmd $stripopt "$dsttmp" || echo "warning: Unable to strip $dst!"; fi
+	if [ x"$chowncmd" != x ]; then $doit $chowncmd "$dsttmp" || echo "warning: Unable to change owner of $dst!"; fi
+	if [ x"$chgrpcmd" != x ]; then $doit $chgrpcmd "$dsttmp" || echo "warning: Unable to change group of $dst!"; fi
+
+	trap "rm -f ${dsttmp}" 0 &&
+	if [ x"$chmodcmd" != x ]; then $doit $chmodcmd "$dsttmp"; fi &&
+	$doit $rmcmd -f "$dstdir/$dstfile" &&
+	$doit $mvcmd "$dsttmp" "$dstdir/$dstfile"
+fi
+
+exit 0

makesrcdist

@@ -2,18 +2,61 @@
 #
 # makesrcdist - make a source distribution of pdfio.
 #
+# Usage:
+#
+#   ./makesrcdist [--snapshot] VERSION
+#
 
+# Support "--snapshot" option...
+if test "$1" == "--snapshot"; then
+    shift
+    snapshot=1
+else
+    snapshot=0
+fi
+
+# Get version...
 if test $# != 1; then
-	echo "Usage: ./makesrcdist version"
+    echo "Usage: ./makesrcdist [--snapshot] VERSION"
-	exit 1
+    exit 1
 fi
 
 version=$1
 
-echo Creating tag for release...
+# Check that version number has been updated everywhere...
-git tag -m "Tag $version" v$version
+if test $(grep AC_INIT configure.ac | awk '{print $2}') != "[$version],"; then
-git push origin v$version
+    echo "Still need to update AC_INIT version in 'configure.ac'."
+    exit 1
+fi
 
+if test $(grep PDFIO_VERSION= configure | awk -F \" '{print $2}') != "$version"; then
+    echo "Still need to run 'autoconf -f'."
+    exit 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
+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
+fi
+
+if test $(grep PDFIO_VERSION pdfio.h | awk -F \" '{print $2}') != "$version"; then
+    echo "Still need to update PDFIO_VERSION in 'pdfio.h'."
+    exit 1
+fi
+
+# Tag release...
+if test $snapshot = 0; then
+    echo Creating tag for release...
+    git tag -m "Tag $version" v$version
+    git push origin v$version
+fi
+
+# Make source archives...
 echo Creating pdfio-$version.tar.gz...
 git archive --format tar --prefix=pdfio-$version/ HEAD | gzip -v9 >pdfio-$version.tar.gz
 gpg --detach-sign pdfio-$version.tar.gz

pdfio-aes.c

@@ -10,10 +10,6 @@
 // (<https://github.com/kokke/tiny-AES-c>)
 //
 
-//
-// Include necessary headers...
-//
-
 #include "pdfio-private.h"
 
 
@@ -21,7 +17,7 @@
 // Local types...
 //
 
-typedef uint8_t state_t[4][4];		// 4x4 AES state table
+typedef uint8_t state_t[4][4];		// 4x4 AES state table @private@
 
 
 //

pdfio-array.c

@@ -7,10 +7,6 @@
 // information.
 //
 
-//
-// Include necessary headers...
-//
-
 #include "pdfio-private.h"
 
 
@@ -331,6 +327,30 @@ pdfioArrayCreate(pdfio_file_t *pdf)	// I - PDF file
 }
 
 
+//
+// '_pdfioArrayDecrypt()' - Decrypt values in an array.
+//
+
+bool					// O - `true` on success, `false` on error
+_pdfioArrayDecrypt(pdfio_file_t  *pdf,	// I - PDF file
+                   pdfio_obj_t   *obj,	// I - Object
+                   pdfio_array_t *a,	// I - Array
+                   size_t        depth)	// I - Depth
+{
+  size_t		i;		// Looping var
+  _pdfio_value_t	*v;		// Current value
+
+
+  for (i = a->num_values, v = a->values; i > 0; i --, v ++)
+  {
+    if (!_pdfioValueDecrypt(pdf, obj, v, depth))
+      return (false);
+  }
+
+  return (true);
+}
+
+
 //
 // '_pdfioArrayDebug()' - Print the contents of an array.
 //
@@ -343,6 +363,9 @@ _pdfioArrayDebug(pdfio_array_t *a,	// I - Array
   _pdfio_value_t	*v;		// Current value
 
 
+  if (!a)
+    return;
+
   putc('[', fp);
   for (i = a->num_values, v = a->values; i > 0; i --, v ++)
     _pdfioValueDebug(v, fp);

pdfio-common.c

@@ -1,16 +1,12 @@
 //
 // Common support functions for pdfio.
 //
-// Copyright © 2021-2023 by Michael R Sweet.
+// Copyright © 2021-2024 by Michael R Sweet.
 //
 // Licensed under Apache License v2.0.  See the file "LICENSE" for more
 // information.
 //
 
-//
-// Include necessary headers...
-//
-
 #include "pdfio-private.h"
 
 
@@ -145,7 +141,7 @@ _pdfioFileGets(pdfio_file_t *pdf,	// I - PDF file
 	*bufend = buffer + bufsize - 1;	// Pointer to end of buffer
 
 
-  PDFIO_DEBUG("_pdfioFileGets(pdf=%p, buffer=%p, bufsize=%lu) bufpos=%ld, buffer=%p, bufptr=%p, bufend=%p\n", pdf, buffer, (unsigned long)bufsize, (long)pdf->bufpos, pdf->buffer, pdf->bufptr, pdf->bufend);
+  PDFIO_DEBUG("_pdfioFileGets(pdf=%p, buffer=%p, bufsize=%lu) bufpos=%ld, buffer=%p, bufptr=%p, bufend=%p, offset=%lu\n", pdf, buffer, (unsigned long)bufsize, (long)pdf->bufpos, pdf->buffer, pdf->bufptr, pdf->bufend, (unsigned long)(pdf->bufpos + (pdf->bufptr - pdf->buffer)));
 
   while (!eol)
   {
@@ -265,7 +261,7 @@ _pdfioFilePrintf(pdfio_file_t *pdf,	// I - PDF file
 
   // Format the string...
   va_start(ap, format);
-  vsnprintf(buffer, sizeof(buffer), format, ap);
+  _pdfio_vsnprintf(pdf, buffer, sizeof(buffer), format, ap);
   va_end(ap);
 
   // Write it...
@@ -360,12 +356,12 @@ _pdfioFileSeek(pdfio_file_t *pdf,	// I - PDF file
                off_t        offset,	// I - Offset
                int          whence)	// I - Offset base
 {
-  PDFIO_DEBUG("_pdfioFileSeek(pdf=%p, offset=%ld, whence=%d)\n", pdf, (long)offset, whence);
+  PDFIO_DEBUG("_pdfioFileSeek(pdf=%p, offset=%ld, whence=%d) pdf->bufpos=%lu\n", pdf, (long)offset, whence, (unsigned long)(pdf ? pdf->bufpos : 0));
 
   // Adjust offset for relative seeks...
   if (whence == SEEK_CUR)
   {
-    offset += pdf->bufpos;
+    offset += pdf->bufpos + (pdf->bufptr - pdf->buffer);
     whence = SEEK_SET;
   }
 
@@ -375,9 +371,9 @@ _pdfioFileSeek(pdfio_file_t *pdf,	// I - PDF file
     if (whence != SEEK_END && offset >= pdf->bufpos && offset < (pdf->bufpos + pdf->bufend - pdf->buffer))
     {
       // Yes, seek within existing buffer...
-      pdf->bufptr = pdf->buffer + offset - pdf->bufpos;
+      pdf->bufptr = pdf->buffer + (offset - pdf->bufpos);
       PDFIO_DEBUG("_pdfioFileSeek: Seek within buffer, bufpos=%ld.\n", (long)pdf->bufpos);
-      PDFIO_DEBUG("_pdfioFileSeek: buffer=%p, bufptr=%p, bufend=%p\n", pdf->buffer, pdf->bufptr, pdf->bufend);
+      PDFIO_DEBUG("_pdfioFileSeek: buffer=%p, bufptr=%p(<%02X%02X...>), bufend=%p\n", pdf->buffer, pdf->bufptr, pdf->bufptr[0] & 255, pdf->bufptr[1] & 255, pdf->bufend);
       return (offset);
     }
 
@@ -408,7 +404,7 @@ _pdfioFileSeek(pdfio_file_t *pdf,	// I - PDF file
     return (-1);
   }
 
-  PDFIO_DEBUG("_pdfioFileSeek: Reset bufpos=%ld.\n", (long)pdf->bufpos);
+  PDFIO_DEBUG("_pdfioFileSeek: Reset bufpos=%ld, offset=%lu.\n", (long)pdf->bufpos, (unsigned long)offset);
   PDFIO_DEBUG("_pdfioFileSeek: buffer=%p, bufptr=%p, bufend=%p\n", pdf->buffer, pdf->bufptr, pdf->bufend);
 
   pdf->bufpos = offset;

pdfio-content.c

@@ -1,16 +1,12 @@
 //
 // Content helper functions 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.
 //
 
-//
-// Include necessary headers...
-//
-
 #include "pdfio-private.h"
 #include "pdfio-content.h"
 #include "ttf.h"
@@ -670,6 +666,9 @@ pdfioContentSave(pdfio_stream_t *st)	// I - Stream
 //
 // 'pdfioContentSetDashPattern()' - Set the stroke pattern.
 //
+// This function sets the stroke pattern when drawing lines.  If "on" and "off"
+// are 0, a solid line is drawn.
+//
 
 bool					// O - `true` on success, `false` on failure
 pdfioContentSetDashPattern(
@@ -678,7 +677,12 @@ pdfioContentSetDashPattern(
     double         on,			// I - On length
     double         off)			// I - Off length
 {
-  return (pdfioStreamPrintf(st, "[%g %g] %g d\n", on, off, phase));
+  if (on <= 0.0 && off <= 0.0)
+    return (pdfioStreamPrintf(st, "[] %g d\n", phase));
+  else if (fabs(on - off) < 0.001)
+    return (pdfioStreamPrintf(st, "[%g] %g d\n", on, phase));
+  else
+    return (pdfioStreamPrintf(st, "[%g %g] %g d\n", on, off, phase));
 }
 
 
@@ -1056,6 +1060,104 @@ pdfioContentTextEnd(pdfio_stream_t *st)	// I - Stream
 }
 
 
+//
+// 'pdfioContentTextMeasure()' - Measure a text string and return its width.
+//
+// This function measures the given text string "s" and returns its width based
+// on "size". The text string must always use the UTF-8 (Unicode) encoding but
+// any control characters (such as newlines) are ignored.
+//
+
+double					// O - Width
+pdfioContentTextMeasure(
+    pdfio_obj_t *font,			// I - Font object created by @link pdfioFileCreateFontObjFromFile@
+    const char  *s,			// I - UTF-8 string
+    double      size)			// I - Font size/height
+{
+  const char	*subtype;		// Font sub-type
+  ttf_t		*ttf = (ttf_t *)_pdfioObjGetExtension(font);
+					// TrueType font data
+  ttf_rect_t	extents;		// Text extents
+  int		ch;			// Unicode character
+  char		temp[1024],		// Temporary string
+		*tempptr;		// Pointer into temporary string
+
+
+  if ((subtype = pdfioObjGetSubtype(font)) == NULL || strcmp(subtype, "Type0"))
+  {
+    // Map non-CP1282 characters to '?', everything else as-is...
+    tempptr = temp;
+
+    while (*s && tempptr < (temp + sizeof(temp) - 3))
+    {
+      if ((*s & 0xe0) == 0xc0)
+      {
+	// Two-byte UTF-8
+        ch = ((s[0] & 0x1f) << 6) | (s[1] & 0x3f);
+	s += 2;
+      }
+      else if ((*s & 0xf0) == 0xe0)
+      {
+	// Three-byte UTF-8
+        ch = ((s[0] & 0x0f) << 12) | ((s[1] & 0x3f) << 6) | (s[2] & 0x3f);
+	s += 3;
+      }
+      else if ((*s & 0xf8) == 0xf0)
+      {
+	// Four-byte UTF-8
+        ch = ((s[0] & 0x07) << 18) | ((s[1] & 0x3f) << 12) | ((s[2] & 0x3f) << 6) | (s[3] & 0x3f);
+	s += 4;
+      }
+      else
+      {
+	ch = *s++;
+      }
+
+      if (ch > 255)
+      {
+	// Try mapping from Unicode to CP1252...
+	size_t i;			// Looping var
+
+	for (i = 0; i < (sizeof(_pdfio_cp1252) / sizeof(_pdfio_cp1252[0])); i ++)
+	{
+	  if (ch == _pdfio_cp1252[i])
+	    break;
+	}
+
+	if (i >= (sizeof(_pdfio_cp1252) / sizeof(_pdfio_cp1252[0])))
+	  ch = '?';			// Unsupported chars map to ?
+      }
+
+      if (ch < 128)
+      {
+        // ASCII
+	*tempptr++ = (char)ch;
+      }
+      else if (ch < 2048)
+      {
+        // 2-byte UTF-8
+        *tempptr++ = (char)(0xc0 | ((ch >> 6) & 0x1f));
+        *tempptr++ = (char)(0x80 | (ch & 0x3f));
+      }
+      else
+      {
+        // 3-byte UTF-8
+        *tempptr++ = (char)(0xe0 | ((ch >> 12) & 0x0f));
+        *tempptr++ = (char)(0x80 | ((ch >> 6) & 0x3f));
+        *tempptr++ = (char)(0x80 | (ch & 0x3f));
+      }
+    }
+
+    *tempptr = '\0';
+    s        = temp;
+  }
+
+  ttfGetExtents(ttf, (float)size, s, &extents);
+
+  return (extents.right - extents.left);
+}
+
+
 //
 // 'pdfioContentTextMoveLine()' - Move to the next line and offset.
 //
@@ -1085,7 +1187,21 @@ pdfioContentTextMoveTo(
 
 
 //
-// 'pdfioContentTextNextLine()' - Move to the next line.
+// 'pdfioContentTextNewLine()' - Move to the next line.
+//
+
+bool					// O - `true` on success, `false` on failure
+pdfioContentTextNewLine(
+    pdfio_stream_t *st)			// I - Stream
+{
+  return (pdfioStreamPuts(st, "T*\n"));
+}
+
+
+//
+// 'pdfioContentTextNextLine()' - Legacy function name preserved for binary compatibility.
+//
+// @private@
 //
 
 bool					// O - `true` on success, `false` on failure
@@ -1096,6 +1212,86 @@ pdfioContentTextNextLine(
 }
 
 
+//
+// 'pdfioContentTextNewLineShow()' - Move to the next line and show text.
+//
+// This function moves to the next line and then shows some text with optional
+// word and character spacing in a PDF content stream. The "unicode" argument
+// specifies that the current font maps to full Unicode.  The "s" argument
+// specifies a UTF-8 encoded string.
+//
+
+bool					// O - `true` on success, `false` on failure
+pdfioContentTextNewLineShow(
+    pdfio_stream_t *st,			// I - Stream
+    double         ws,			// I - Word spacing or `0.0` for none
+    double         cs,			// I - Character spacing or `0.0` for none
+    bool           unicode,		// I - Unicode text?
+    const char     *s)			// I - String to show
+{
+  bool	newline = false;		// New line?
+  char	op;				// Text operator
+
+
+  // Write word and/or character spacing as needed...
+  if (ws > 0.0 || cs > 0.0)
+  {
+    // Use " operator to show text with word and character spacing...
+    if (!pdfioStreamPrintf(st, "%g %g", ws, cs))
+      return (false);
+
+    op = '\"';
+  }
+  else
+  {
+    // Use ' operator to show text with the defaults...
+    op = '\'';
+  }
+
+  // Write the string...
+  if (!write_string(st, unicode, s, &newline))
+    return (false);
+
+  // Draw it...
+  if (newline)
+    return (pdfioStreamPrintf(st, "%c T*\n", op));
+  else
+    return (pdfioStreamPrintf(st, "%c\n", op));
+}
+
+
+//
+// 'pdfioContentTextNewLineShowf()' - Show formatted text.
+//
+// This function moves to the next line and shows some formatted text with
+// optional word and character spacing in a PDF content stream. The "unicode"
+// argument specifies that the current font maps to full Unicode.  The "format"
+// argument specifies a UTF-8 encoded `printf`-style format string.
+//
+
+bool					// O - `true` on success, `false` on failure
+pdfioContentTextNewLineShowf(
+    pdfio_stream_t *st,			// I - Stream
+    double         ws,			// I - Word spacing or `0.0` for none
+    double         cs,			// I - Character spacing or `0.0` for none
+    bool           unicode,		// I - Unicode text?
+    const char     *format,		// I - `printf`-style format string
+    ...)				// I - Additional arguments as needed
+{
+  char		buffer[8192];		// Text buffer
+  va_list	ap;			// Argument pointer
+
+
+  // Format the string...
+  va_start(ap, format);
+  vsnprintf(buffer, sizeof(buffer), format, ap);
+  va_end(ap);
+
+  // Show it...
+  return (pdfioContentTextNewLineShow(st, ws, cs, unicode, buffer));
+}
+
+
 //
 // 'pdfioContentTextShow()' - Show text.
 //
@@ -1128,9 +1324,9 @@ pdfioContentTextShow(
 //
 // 'pdfioContentTextShowf()' - Show formatted text.
 //
-// This function shows some text in a PDF content stream. The "unicode" argument
+// This function shows some formatted text in a PDF content stream. The
-// specifies that the current font maps to full Unicode.  The "format" argument
+// "unicode" argument specifies that the current font maps to full Unicode.
-// specifies a UTF-8 encoded `printf`-style format string.
+// The "format" argument specifies a UTF-8 encoded `printf`-style format string.
 //
 
 bool
@@ -1281,13 +1477,13 @@ pdfioFileCreateFontObjFromFile(
   pdfio_dict_t	*dict,			// Font dictionary
 		*desc,			// Font descriptor
 		*file;			// Font file dictionary
-  pdfio_obj_t	*obj,			// Font object
+  pdfio_obj_t	*obj = NULL,		// Font object
 		*desc_obj,		// Font descriptor object
 		*file_obj;		// Font file object
   const char	*basefont;		// Base font name
   pdfio_array_t	*bbox;			// Font bounding box array
   pdfio_stream_t *st;			// Font stream
-  int		fd;			// File
+  int		fd = -1;		// File
   unsigned char	buffer[16384];		// Read buffer
   ssize_t	bytes;			// Bytes read
 
@@ -1316,48 +1512,32 @@ pdfioFileCreateFontObjFromFile(
 
   // Create the font file dictionary and object...
   if ((file = pdfioDictCreate(pdf)) == NULL)
-  {
+    goto done;
-    ttfDelete(font);
-    close(fd);
-    return (NULL);
-  }
 
   pdfioDictSetName(file, "Filter", "FlateDecode");
 
   if ((file_obj = pdfioFileCreateObj(pdf, file)) == NULL)
-  {
+    goto done;
-    ttfDelete(font);
-    close(fd);
-    return (NULL);
-  }
 
   if ((st = pdfioObjCreateStream(file_obj, PDFIO_FILTER_FLATE)) == NULL)
-  {
+    goto done;
-    ttfDelete(font);
-    close(fd);
-    return (NULL);
-  }
 
   while ((bytes = read(fd, buffer, sizeof(buffer))) > 0)
   {
     if (!pdfioStreamWrite(st, buffer, (size_t)bytes))
     {
-      ttfDelete(font);
-      close(fd);
       pdfioStreamClose(st);
-      return (NULL);
+      goto done;
     }
   }
 
   close(fd);
+  fd = -1;
   pdfioStreamClose(st);
 
   // Create the font descriptor dictionary and object...
   if ((bbox = pdfioArrayCreate(pdf)) == NULL)
-  {
+    goto done;
-    ttfDelete(font);
-    return (NULL);
-  }
 
   ttfGetBounds(font, &bounds);
 
@@ -1367,10 +1547,7 @@ pdfioFileCreateFontObjFromFile(
   pdfioArrayAppendNumber(bbox, bounds.top);
 
   if ((desc = pdfioDictCreate(pdf)) == NULL)
-  {
+    goto done;
-    ttfDelete(font);
-    return (NULL);
-  }
 
   basefont = pdfioStringCreate(pdf, ttfGetPostScriptName(font));
 
@@ -1389,59 +1566,70 @@ pdfioFileCreateFontObjFromFile(
   pdfioDictSetNumber(desc, "StemV", ttfGetWeight(font) / 4 + 25);
 
   if ((desc_obj = pdfioFileCreateObj(pdf, desc)) == NULL)
-  {
+    goto done;
-    ttfDelete(font);
-    return (NULL);
-  }
 
   pdfioObjClose(desc_obj);
 
   if (unicode)
   {
     // Unicode (CID) font...
-    pdfio_dict_t	*cid2gid;	// CIDToGIDMap dictionary
+    pdfio_dict_t	*cid2gid,	// CIDToGIDMap dictionary
-    pdfio_obj_t		*cid2gid_obj;	// CIDToGIDMap object
+			*to_unicode;	// ToUnicode dictionary
+    pdfio_obj_t		*cid2gid_obj,	// CIDToGIDMap object
+			*to_unicode_obj;// ToUnicode object
     size_t		i,		// Looping var
+			start,		// Start character
 			num_cmap;	// Number of CMap entries
     const int		*cmap;		// CMap entries
+    int			min_glyph,	// First glyph
+			max_glyph;	// Last glyph
+    unsigned short	glyphs[65536];	// Glyph to Unicode mapping
     unsigned char	*bufptr,	// Pointer into buffer
 			*bufend;	// End of buffer
     pdfio_dict_t	*type2;		// CIDFontType2 font dictionary
     pdfio_obj_t		*type2_obj;	// CIDFontType2 font object
     pdfio_array_t	*descendants;	// Decendant font list
     pdfio_dict_t	*sidict;	// CIDSystemInfo dictionary
+    pdfio_array_t	*w_array,	// Width array
+			*temp_array;	// Temporary width sub-array
+    int			w0, w1;		// Widths
+
+    // Create a CIDSystemInfo mapping to Adobe UCS2 v0 (Unicode)
+    if ((sidict = pdfioDictCreate(pdf)) == NULL)
+      goto done;
+
+    pdfioDictSetString(sidict, "Registry", "Adobe");
+    pdfioDictSetString(sidict, "Ordering", "Identity");
+    pdfioDictSetNumber(sidict, "Supplement", 0);
 
     // Create a CIDToGIDMap object for the Unicode font...
     if ((cid2gid = pdfioDictCreate(pdf)) == NULL)
-    {
+      goto done;
-      ttfDelete(font);
-      return (NULL);
-    }
 
 #ifndef DEBUG
     pdfioDictSetName(cid2gid, "Filter", "FlateDecode");
 #endif // !DEBUG
 
     if ((cid2gid_obj = pdfioFileCreateObj(pdf, cid2gid)) == NULL)
-    {
+      goto done;
-      ttfDelete(font);
-      return (NULL);
-    }
 
 #ifdef DEBUG
     if ((st = pdfioObjCreateStream(cid2gid_obj, PDFIO_FILTER_NONE)) == NULL)
 #else
     if ((st = pdfioObjCreateStream(cid2gid_obj, PDFIO_FILTER_FLATE)) == NULL)
 #endif // DEBUG
-    {
+      goto done;
-      ttfDelete(font);
-      return (NULL);
-    }
 
-    cmap = ttfGetCMap(font, &num_cmap);
+    cmap      = ttfGetCMap(font, &num_cmap);
+    min_glyph = 65536;
+    max_glyph = 0;
+    memset(glyphs, 0, sizeof(glyphs));
+
+    PDFIO_DEBUG("pdfioFileCreateFontObjFromFile: num_cmap=%u\n", (unsigned)num_cmap);
 
     for (i = 0, bufptr = buffer, bufend = buffer + sizeof(buffer); i < num_cmap; i ++)
     {
+      PDFIO_DEBUG("pdfioFileCreateFontObjFromFile: cmap[%u]=%d\n", (unsigned)i, cmap[i]);
       if (cmap[i] < 0)
       {
         // Map undefined glyph to .notdef...
@@ -1453,6 +1641,12 @@ pdfioFileCreateFontObjFromFile(
         // Map to specified glyph...
         *bufptr++ = (unsigned char)(cmap[i] >> 8);
         *bufptr++ = (unsigned char)(cmap[i] & 255);
+
+        glyphs[cmap[i]] = (unsigned short)i;
+        if (cmap[i] < min_glyph)
+          min_glyph = cmap[i];
+        if (cmap[i] > max_glyph)
+          max_glyph = cmap[i];
       }
 
       if (bufptr >= bufend)
@@ -1461,8 +1655,7 @@ pdfioFileCreateFontObjFromFile(
         if (!pdfioStreamWrite(st, buffer, (size_t)(bufptr - buffer)))
         {
 	  pdfioStreamClose(st);
-          ttfDelete(font);
+	  goto done;
-          return (NULL);
         }
 
         bufptr = buffer;
@@ -1475,30 +1668,102 @@ pdfioFileCreateFontObjFromFile(
       if (!pdfioStreamWrite(st, buffer, (size_t)(bufptr - buffer)))
       {
 	pdfioStreamClose(st);
-	ttfDelete(font);
+	goto done;
-	return (NULL);
       }
     }
 
     pdfioStreamClose(st);
 
+    // ToUnicode mapping object
+    to_unicode = pdfioDictCreate(pdf);
+    pdfioDictSetName(to_unicode, "Type", "CMap");
+    pdfioDictSetName(to_unicode, "CMapName", "Adobe-Identity-UCS2");
+    pdfioDictSetDict(to_unicode, "CIDSystemInfo", sidict);
+
+#ifndef DEBUG
+    pdfioDictSetName(to_unicode, "Filter", "FlateDecode");
+#endif // !DEBUG
+
+    if ((to_unicode_obj = pdfioFileCreateObj(pdf, to_unicode)) == NULL)
+      goto done;
+
+#ifdef DEBUG
+    if ((st = pdfioObjCreateStream(to_unicode_obj, PDFIO_FILTER_NONE)) == NULL)
+#else
+    if ((st = pdfioObjCreateStream(to_unicode_obj, PDFIO_FILTER_FLATE)) == NULL)
+#endif // DEBUG
+      goto done;
+
+    pdfioStreamPuts(st,
+		    "stream\n"
+		    "/CIDInit /ProcSet findresource begin\n"
+		    "12 dict begin\n"
+		    "begincmap\n"
+		    "/CIDSystemInfo<<\n"
+		    "/Registry (Adobe)\n"
+		    "/Ordering (UCS2)\n"
+		    "/Supplement 0\n"
+		    ">> def\n"
+		    "/CMapName /Adobe-Identity-UCS2 def\n"
+		    "/CMapType 2 def\n"
+		    "1 begincodespacerange\n"
+		    "<0000> <FFFF>\n"
+		    "endcodespacerange\n"
+		    "1 beginbfrange\n"
+		    "<0000> <FFFF> <0000>\n"
+                    "endbfrange\n"
+                    "endcmap\n"
+                    "CMapName currentdict /CMap defineresource pop\n"
+                    "end\n"
+                    "end\n");
+
+    pdfioStreamClose(st);
+
     // Create a CIDFontType2 dictionary for the Unicode font...
     if ((type2 = pdfioDictCreate(pdf)) == NULL)
-    {
+      goto done;
-      ttfDelete(font);
-      return (NULL);
-    }
 
-    if ((sidict = pdfioDictCreate(pdf)) == NULL)
+    // Width array
-    {
+    if ((w_array = pdfioArrayCreate(pdf)) == NULL)
-      ttfDelete(font);
+      goto done;
-      return (NULL);
-    }
 
-    // CIDSystemInfo mapping to Adobe UCS2 v0 (Unicode)
+    for (start = 0, w0 = ttfGetWidth(font, 0), w1 = 0, i = 1; i < 65536; start = i, w0 = w1, i ++)
-    pdfioDictSetString(sidict, "Registry", "Adobe");
+    {
-    pdfioDictSetString(sidict, "Ordering", "Identity");
+      while (i < 65536 && (w1 = ttfGetWidth(font, (int)i)) == w0)
-    pdfioDictSetNumber(sidict, "Supplement", 0);
+        i ++;
+
+      if ((i - start) > 1)
+      {
+        // Encode a repeating sequence...
+        pdfioArrayAppendNumber(w_array, start);
+        pdfioArrayAppendNumber(w_array, i - 1);
+        pdfioArrayAppendNumber(w_array, w0);
+      }
+      else
+      {
+        // Encode a non-repeating sequence...
+        pdfioArrayAppendNumber(w_array, start);
+
+        if ((temp_array = pdfioArrayCreate(pdf)) == NULL)
+	  goto done;
+
+        pdfioArrayAppendNumber(temp_array, w0);
+        for (w0 = w1, i ++; i < 65536; w0 = w1, i ++)
+        {
+          if ((w1 = ttfGetWidth(font, (int)i)) == w0 && i < 65535)
+            break;
+
+	  pdfioArrayAppendNumber(temp_array, w0);
+        }
+
+        if (i == 65536)
+	  pdfioArrayAppendNumber(temp_array, w0);
+	else
+	  i --;
+
+        pdfioArrayAppendArray(w_array, temp_array);
+      }
+    }
 
     // Then the dictionary for the CID base font...
     pdfioDictSetName(type2, "Type", "Font");
@@ -1507,56 +1772,41 @@ pdfioFileCreateFontObjFromFile(
     pdfioDictSetDict(type2, "CIDSystemInfo", sidict);
     pdfioDictSetObj(type2, "CIDToGIDMap", cid2gid_obj);
     pdfioDictSetObj(type2, "FontDescriptor", desc_obj);
+    pdfioDictSetArray(type2, "W", w_array);
 
     if ((type2_obj = pdfioFileCreateObj(pdf, type2)) == NULL)
-    {
+      goto done;
-      ttfDelete(font);
-      return (NULL);
-    }
 
     pdfioObjClose(type2_obj);
 
     // Create a Type 0 font object...
     if ((descendants = pdfioArrayCreate(pdf)) == NULL)
-    {
+      goto done;
-      ttfDelete(font);
-      return (NULL);
-    }
 
     pdfioArrayAppendObj(descendants, type2_obj);
 
     if ((dict = pdfioDictCreate(pdf)) == NULL)
-    {
+      goto done;
-      ttfDelete(font);
-      return (NULL);
-    }
 
     pdfioDictSetName(dict, "Type", "Font");
     pdfioDictSetName(dict, "Subtype", "Type0");
     pdfioDictSetName(dict, "BaseFont", basefont);
     pdfioDictSetArray(dict, "DescendantFonts", descendants);
     pdfioDictSetName(dict, "Encoding", "Identity-H");
+    pdfioDictSetObj(dict, "ToUnicode", to_unicode_obj);
 
-    if ((obj = pdfioFileCreateObj(pdf, dict)) == NULL)
+    if ((obj = pdfioFileCreateObj(pdf, dict)) != NULL)
-      return (NULL);
+      pdfioObjClose(obj);
-
-    pdfioObjClose(obj);
   }
   else
   {
     // Simple (CP1282 or custom encoding) 8-bit font...
     if (ttfGetMaxChar(font) >= 255 && !pdf->cp1252_obj && !create_cp1252(pdf))
-    {
+      goto done;
-      ttfDelete(font);
-      return (NULL);
-    }
 
     // Create a TrueType font object...
     if ((dict = pdfioDictCreate(pdf)) == NULL)
-    {
+      goto done;
-      ttfDelete(font);
-      return (NULL);
-    }
 
     pdfioDictSetName(dict, "Type", "Font");
     pdfioDictSetName(dict, "Subtype", "TrueType");
@@ -1566,16 +1816,16 @@ pdfioFileCreateFontObjFromFile(
 
     pdfioDictSetObj(dict, "FontDescriptor", desc_obj);
 
-    if ((obj = pdfioFileCreateObj(pdf, dict)) == NULL)
+    if ((obj = pdfioFileCreateObj(pdf, dict)) != NULL)
-    {
+      pdfioObjClose(obj);
-      ttfDelete(font);
-      return (NULL);
-    }
-
-    pdfioObjClose(obj);
   }
 
-  ttfDelete(font);
+  done:
+
+  if (fd >= 0)
+    close(fd);
+
+  _pdfioObjSetExtension(obj, font, (_pdfio_extfree_t)ttfDelete);
 
   return (obj);
 }
@@ -2099,7 +2349,7 @@ pdfioPageDictAddColorSpace(
 bool					// O - `true` on success, `false` on failure
 pdfioPageDictAddFont(
     pdfio_dict_t *dict,			// I - Page dictionary
-    const char   *name,			// I - Font name
+    const char   *name,			// I - Font name; must not contain spaces
     pdfio_obj_t  *obj)			// I - Font object
 {
   pdfio_dict_t	*resources;		// Resource dictionary

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
@@ -126,8 +115,12 @@ extern bool		pdfioContentSetTextXScaling(pdfio_stream_t *st, double percent) _PD
 extern bool		pdfioContentStroke(pdfio_stream_t *st) _PDFIO_PUBLIC;
 extern bool		pdfioContentTextBegin(pdfio_stream_t *st) _PDFIO_PUBLIC;
 extern bool		pdfioContentTextEnd(pdfio_stream_t *st) _PDFIO_PUBLIC;
+extern double		pdfioContentTextMeasure(pdfio_obj_t *font, const char *s, double size) _PDFIO_PUBLIC;
 extern bool		pdfioContentTextMoveLine(pdfio_stream_t *st, double tx, double ty) _PDFIO_PUBLIC;
 extern bool		pdfioContentTextMoveTo(pdfio_stream_t *st, double tx, double ty) _PDFIO_PUBLIC;
+extern bool		pdfioContentTextNewLine(pdfio_stream_t *st) _PDFIO_PUBLIC;
+extern bool		pdfioContentTextNewLineShow(pdfio_stream_t *st, double ws, double cs, bool unicode, const char *s) _PDFIO_PUBLIC;
+extern bool		pdfioContentTextNewLineShowf(pdfio_stream_t *st, double ws, double cs, bool unicode, const char *format, ...) _PDFIO_PUBLIC _PDFIO_FORMAT(5,6);
 extern bool		pdfioContentTextNextLine(pdfio_stream_t *st) _PDFIO_PUBLIC;
 extern bool		pdfioContentTextShow(pdfio_stream_t *st, bool unicode, const char *s) _PDFIO_PUBLIC;
 extern bool		pdfioContentTextShowf(pdfio_stream_t *st, bool unicode, const char *format, ...) _PDFIO_PUBLIC _PDFIO_FORMAT(3,4);
@@ -151,10 +144,6 @@ 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-crypto.c

@@ -1,16 +1,12 @@
 //
 // Cryptographic support functions 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.
 //
 
-//
-// Include necessary headers...
-//
-
 #include "pdfio-private.h"
 #if _WIN32
 #  include <windows.h>
@@ -403,16 +399,23 @@ _pdfioCryptoMakeRandom(uint8_t *buffer,	// I - Buffer
 //
 
 _pdfio_crypto_cb_t			// O  - Decryption callback or `NULL` for none
- _pdfioCryptoMakeReader(
+_pdfioCryptoMakeReader(
      pdfio_file_t        *pdf,		// I  - PDF file
      pdfio_obj_t         *obj,		// I  - PDF object
      _pdfio_crypto_ctx_t *ctx,		// I  - Pointer to crypto context
      uint8_t             *iv,		// I  - Buffer for initialization vector
      size_t              *ivlen)	// IO - Size of initialization vector
 {
-  uint8_t	data[21];		/* Key data */
+  uint8_t	data[21];		// Key data
-  _pdfio_md5_t	md5;			/* MD5 state */
+  _pdfio_md5_t	md5;			// MD5 state
-  uint8_t	digest[16];		/* MD5 digest value */
+  uint8_t	digest[16];		// MD5 digest value
+#if PDFIO_OBJ_CRYPT
+  pdfio_array_t	*id_array;		// Object ID array
+  unsigned char	*id_value;		// Object ID value
+  size_t	id_len;			// Length of object ID
+  uint8_t	temp_key[16];		// File key for object
+#endif // PDFIO_OBJ_CRYPT
+  uint8_t	*file_key;		// Computed file key to use
 
 
   PDFIO_DEBUG("_pdfioCryptoMakeReader(pdf=%p, obj=%p(%d), ctx=%p, iv=%p, ivlen=%p(%d))\n", pdf, obj, (int)obj->number, ctx, iv, ivlen, (int)*ivlen);
@@ -424,6 +427,59 @@ _pdfio_crypto_cb_t			// O  - Decryption callback or `NULL` for none
     return (NULL);
   }
 
+#if PDFIO_OBJ_CRYPT
+  if ((id_array = pdfioDictGetArray(pdfioObjGetDict(obj), "ID")) != NULL)
+  {
+    // Object has its own ID that will get used for encryption...
+    _pdfio_md5_t md5;			// MD5 context
+    uint8_t	file_digest[16];	// MD5 digest of file ID and pad
+    uint8_t	user_pad[32],		// Padded user password
+		own_user_key[32],	// Calculated user key
+		pdf_user_key[32];	// Decrypted user key
+
+    PDFIO_DEBUG("_pdfioCryptoMakeReader: Per-object file ID.\n");
+
+    if ((id_value = pdfioArrayGetBinary(id_array, 0, &id_len)) == NULL)
+    {
+      *ivlen = 0;
+      return (NULL);
+    }
+
+    _pdfioCryptoMD5Init(&md5);
+    _pdfioCryptoMD5Append(&md5, pdf_passpad, 32);
+    _pdfioCryptoMD5Append(&md5, id_value, id_len);
+    _pdfioCryptoMD5Finish(&md5, file_digest);
+
+    make_owner_key(pdf->encryption, pdf->password, pdf->owner_key, user_pad);
+    make_file_key(pdf->encryption, pdf->permissions, id_value, id_len, user_pad, pdf->owner_key, temp_key);
+    make_user_key(id_value, id_len, own_user_key);
+
+    if (memcmp(own_user_key, pdf->user_key, sizeof(own_user_key)))
+    {
+      PDFIO_DEBUG("_pdfioCryptoMakeReader: Not user password, trying owner password.\n");
+
+      make_file_key(pdf->encryption, pdf->permissions, id_value, id_len, pdf->password, pdf->owner_key, temp_key);
+      make_user_key(id_value, id_len, own_user_key);
+
+      memcpy(pdf_user_key, pdf->user_key, sizeof(pdf_user_key));
+      decrypt_user_key(pdf->encryption, temp_key, pdf_user_key);
+
+      if (memcmp(pdf->password, pdf_user_key, 32) && memcmp(own_user_key, pdf_user_key, 16))
+      {
+	*ivlen = 0;
+	return (NULL);
+      }
+    }
+
+    file_key = temp_key;
+  }
+  else
+#endif // PDFIO_OBJ_CRYPT
+  {
+    // Use the default file key...
+    file_key = pdf->file_key;
+  }
+
   switch (pdf->encryption)
   {
     default :
@@ -432,7 +488,7 @@ _pdfio_crypto_cb_t			// O  - Decryption callback or `NULL` for none
 
     case PDFIO_ENCRYPTION_RC4_40 :
 	// Copy the key data for the MD5 hash.
-	memcpy(data, pdf->file_key, sizeof(pdf->file_key));
+	memcpy(data, file_key, 16);
 	data[16] = (uint8_t)obj->number;
 	data[17] = (uint8_t)(obj->number >> 8);
 	data[18] = (uint8_t)(obj->number >> 16);
@@ -446,12 +502,20 @@ _pdfio_crypto_cb_t			// O  - Decryption callback or `NULL` for none
 
         // Initialize the RC4 context using 40 bits of the digest...
 	_pdfioCryptoRC4Init(&ctx->rc4, digest, 5);
+	*ivlen = 0;
 	return ((_pdfio_crypto_cb_t)_pdfioCryptoRC4Crypt);
 
-    case PDFIO_ENCRYPTION_RC4_128 :
     case PDFIO_ENCRYPTION_AES_128 :
+        if (*ivlen < 16)
+        {
+          *ivlen = 0;
+          _pdfioFileError(pdf, "Value too short for AES encryption.");
+          return (NULL);
+        }
+
+    case PDFIO_ENCRYPTION_RC4_128 :
 	// Copy the key data for the MD5 hash.
-	memcpy(data, pdf->file_key, sizeof(pdf->file_key));
+	memcpy(data, file_key, 16);
 	data[16] = (uint8_t)obj->number;
 	data[17] = (uint8_t)(obj->number >> 8);
 	data[18] = (uint8_t)(obj->number >> 16);
@@ -487,7 +551,7 @@ _pdfio_crypto_cb_t			// O  - Decryption callback or `NULL` for none
 //
 
 _pdfio_crypto_cb_t			// O  - Encryption callback or `NULL` for none
- _pdfioCryptoMakeWriter(
+_pdfioCryptoMakeWriter(
      pdfio_file_t        *pdf,		// I  - PDF file
      pdfio_obj_t         *obj,		// I  - PDF object
      _pdfio_crypto_ctx_t *ctx,		// I  - Pointer to crypto context
@@ -592,6 +656,8 @@ _pdfioCryptoUnlock(
   revision = (int)pdfioDictGetNumber(encrypt_dict, "R");
   length   = (int)pdfioDictGetNumber(encrypt_dict, "Length");
 
+  PDFIO_DEBUG("_pdfioCryptoUnlock: handler=%p(%s), version=%d, revision=%d, length=%d\n", (void *)handler, handler ? handler : "(null)", version, revision, length);
+
   if (!handler || strcmp(handler, "Standard"))
   {
     _pdfioFileError(pdf, "Unsupported security handler '%s'.", handler ? handler : "(null)");
@@ -640,6 +706,8 @@ _pdfioCryptoUnlock(
     }
     else
     {
+      PDFIO_DEBUG("_pdfioCryptoUnlock: CFM=\"%s\"\n", cfm);
+
       if (length < 40 || length > 128)
 	length = 128;			// Default to 128 bits
 
@@ -765,17 +833,16 @@ _pdfioCryptoUnlock(
       {
         // Matches!
         memcpy(pdf->file_key, file_key, sizeof(pdf->file_key));
+        memcpy(pdf->password, pad, sizeof(pdf->password));
+
         return (true);
       }
 
-     /*
+      // Not the owner password, try the user password...
-      * Not the owner password, try the user password...
-      */
-
       make_file_key(pdf->encryption, pdf->permissions, file_id, file_idlen, pad, pdf->owner_key, file_key);
       PDFIO_DEBUG("_pdfioCryptoUnlock: Fuse=%02X%02X%02X%02X...%02X%02X%02X%02X\n", file_key[0], file_key[1], file_key[2], file_key[3], file_key[12], file_key[13], file_key[14], file_key[15]);
 
-      make_user_key(file_id, file_idlen, user_key);
+      make_user_key(file_id, file_idlen, own_user_key);
 
       memcpy(pdf_user_key, pdf->user_key, sizeof(pdf_user_key));
       decrypt_user_key(pdf->encryption, file_key, pdf_user_key);
@@ -783,10 +850,12 @@ _pdfioCryptoUnlock(
       PDFIO_DEBUG("_pdfioCryptoUnlock: Uuse=%02X%02X%02X%02X...%02X%02X%02X%02X\n", user_key[0], user_key[1], user_key[2], user_key[3], user_key[28], user_key[29], user_key[30], user_key[31]);
       PDFIO_DEBUG("_pdfioCryptoUnlock: Updf=%02X%02X%02X%02X...%02X%02X%02X%02X\n", pdf_user_key[0], pdf_user_key[1], pdf_user_key[2], pdf_user_key[3], pdf_user_key[28], pdf_user_key[29], pdf_user_key[30], pdf_user_key[31]);
 
-      if (!memcmp(pad, pdf_user_key, 32) || !memcmp(user_key, pdf_user_key, 16))
+      if (!memcmp(pad, pdf_user_key, 32) || !memcmp(own_user_key, pdf_user_key, 16))
       {
         // Matches!
         memcpy(pdf->file_key, file_key, sizeof(pdf->file_key));
+        memcpy(pdf->password, pad, sizeof(pdf->password));
+
         return (true);
       }
     }

pdfio-dict.c

@@ -7,10 +7,6 @@
 // information.
 //
 
-//
-// Include necessary headers...
-//
-
 #include "pdfio-private.h"
 
 
@@ -162,6 +158,30 @@ pdfioDictCreate(pdfio_file_t *pdf)	// I - PDF file
 }
 
 
+//
+// '_pdfioDictDecrypt()' - Decrypt the values in a dictionary.
+//
+
+bool					// O - `true` on success, `false` on error
+_pdfioDictDecrypt(pdfio_file_t *pdf,	// I - PDF file
+                  pdfio_obj_t  *obj,	// I - Object
+                  pdfio_dict_t *dict,	// I - Dictionary
+                  size_t       depth)	// I - Depth
+{
+  size_t	i;			// Looping var
+  _pdfio_pair_t	*pair;			// Current pair
+
+
+  for (i = dict->num_pairs, pair = dict->pairs; i > 0; i --, pair ++)
+  {
+    if (strcmp(pair->key, "ID") && !_pdfioValueDecrypt(pdf, obj, &pair->value, depth + 1))
+      return (false);
+  }
+
+  return (true);
+}
+
+
 //
 // '_pdfioDictDebug()' - Dump a dictionary to stderr.
 //
@@ -174,6 +194,9 @@ _pdfioDictDebug(pdfio_dict_t *dict,	// I - Dictionary
   _pdfio_pair_t	*pair;			// Current pair
 
 
+  if (!dict)
+    return;
+
   for (i = dict->num_pairs, pair = dict->pairs; i > 0; i --, pair ++)
   {
     fprintf(fp, "/%s", pair->key);
@@ -406,9 +429,27 @@ pdfioDictGetString(pdfio_dict_t *dict,	// I - Dictionary
 
 
   if (value && value->type == PDFIO_VALTYPE_STRING)
+  {
     return (value->value.string);
+  }
+  else if (value && value->type == PDFIO_VALTYPE_BINARY && value->value.binary.datalen < 4096)
+  {
+    // Convert binary string to regular string...
+    char	temp[4096];		// Temporary string
+
+    memcpy(temp, value->value.binary.data, value->value.binary.datalen);
+    temp[value->value.binary.datalen] = '\0';
+
+    free(value->value.binary.data);
+    value->type         = PDFIO_VALTYPE_STRING;
+    value->value.string = pdfioStringCreate(dict->pdf, temp);
+
+    return (value->value.string);
+  }
   else
+  {
     return (NULL);
+  }
 }
 
 
@@ -522,7 +563,7 @@ _pdfioDictRead(pdfio_file_t   *pdf,	// I - PDF file
   _pdfio_value_t	value;		// Dictionary value
 
 
-  PDFIO_DEBUG("_pdfioDictRead(pdf=%p)\n", pdf);
+  PDFIO_DEBUG("_pdfioDictRead(pdf=%p, obj=%p, tb=%p, depth=%lu)\n", pdf, obj, tb, (unsigned long)depth);
 
   // Create a dictionary and start reading...
   if ((dict = pdfioDictCreate(pdf)) == NULL)
@@ -534,6 +575,7 @@ _pdfioDictRead(pdfio_file_t   *pdf,	// I - PDF file
     if (!strcmp(key, ">>"))
     {
       // End of dictionary...
+      PDFIO_DEBUG("_pdfioDictRead: Returning dictionary value...\n");
       return (dict);
     }
     else if (key[0] != '/')
@@ -552,14 +594,14 @@ _pdfioDictRead(pdfio_file_t   *pdf,	// I - PDF file
 
     if (!_pdfioValueRead(pdf, obj, tb, &value, depth))
     {
-      _pdfioFileError(pdf, "Missing value for dictionary key.");
+      _pdfioFileError(pdf, "Missing value for dictionary key '%s'.", key + 1);
       break;
     }
 
     if (!_pdfioDictSetValue(dict, pdfioStringCreate(pdf, key + 1), &value))
       break;
 
-//    PDFIO_DEBUG("_pdfioDictRead: Set %s.\n", key);
+    PDFIO_DEBUG("_pdfioDictRead: Set %s.\n", key);
   }
 
   // Dictionary is invalid - pdfioFileClose will free the memory, return NULL

pdfio-object.c

@@ -1,16 +1,12 @@
 //
 // PDF object functions for PDFio.
 //
-// Copyright © 2021-2023 by Michael R Sweet.
+// Copyright © 2021-2024 by Michael R Sweet.
 //
 // Licensed under Apache License v2.0.  See the file "LICENSE" for more
 // information.
 //
 
-//
-// Include necessary headers...
-//
-
 #include "pdfio-private.h"
 
 
@@ -221,8 +217,13 @@ void
 _pdfioObjDelete(pdfio_obj_t *obj)	// I - Object
 {
   if (obj)
+  {
     pdfioStreamClose(obj->stream);
 
+    if (obj->datafree)
+      (obj->datafree)(obj->data);
+  }
+
   free(obj);
 }
 
@@ -267,6 +268,17 @@ pdfioObjGetDict(pdfio_obj_t *obj)	// I - Object
 }
 
 
+//
+// '_pdfioObjGetExtension()' - Get the extension pointer for an object.
+//
+
+void *					// O - Extension data
+_pdfioObjGetExtension(pdfio_obj_t *obj)	// I - Object
+{
+  return (obj->data);
+}
+
+
 //
 // 'pdfioObjGetGeneration()' - Get the object's generation number.
 //
@@ -321,6 +333,26 @@ pdfioObjGetLength(pdfio_obj_t *obj)	// I - Object
 }
 
 
+//
+// 'pdfioObjGetName()' - Get the name value associated with an object.
+//
+
+const char *				// O - Dictionary or `NULL` on error
+pdfioObjGetName(pdfio_obj_t *obj)	// I - Object
+{
+  if (!obj)
+    return (NULL);
+
+  if (obj->value.type == PDFIO_VALTYPE_NONE)
+    _pdfioObjLoad(obj);
+
+  if (obj->value.type == PDFIO_VALTYPE_NAME)
+    return (obj->value.value.name);
+  else
+    return (NULL);
+}
+
+
 //
 // 'pdfioObjGetNumber()' - Get the object's number.
 //
@@ -335,8 +367,21 @@ pdfioObjGetNumber(pdfio_obj_t *obj)	// I - Object
 //
 // 'pdfioObjGetSubtype()' - Get an object's subtype.
 //
+// This function returns an object's PDF subtype name, if any.  Common subtype
+// names include:
+//
+// - "CIDFontType0": A CID Type0 font
+// - "CIDFontType2": A CID TrueType font
+// - "Image": An image or image mask
+// - "Form": A fillable form
+// - "OpenType": An OpenType font
+// - "Type0": A composite font
+// - "Type1": A PostScript Type1 font
+// - "Type3": A PDF Type3 font
+// - "TrueType": A TrueType font
+//
 
-const char *				// O - Object subtype
+const char *				// O - Object subtype name or `NULL` for none
 pdfioObjGetSubtype(pdfio_obj_t *obj)	// I - Object
 {
   pdfio_dict_t	*dict;			// Object dictionary
@@ -352,8 +397,21 @@ pdfioObjGetSubtype(pdfio_obj_t *obj)	// I - Object
 //
 // 'pdfioObjGetType()' - Get an object's type.
 //
+// This function returns an object's PDF type name, if any. Common type names
+// include:
+//
+// - "CMap": A character map for composite fonts
+// - "Font": An embedded font (@link pdfioObjGetSubtype@ will tell you the
+//   font format)
+// - "FontDescriptor": A font descriptor
+// - "Page": A (visible) page
+// - "Pages": A page tree node
+// - "Template": An invisible template page
+// - "XObject": An image, image mask, or form (@link pdfioObjGetSubtype@ will
+//   tell you which)
+//
 
-const char *				// O - Object type
+const char *				// O - Object type name or `NULL` for none
 pdfioObjGetType(pdfio_obj_t *obj)	// I - Object
 {
   pdfio_dict_t	*dict;			// Object dictionary
@@ -420,6 +478,9 @@ _pdfioObjLoad(pdfio_obj_t *obj)		// I - Object
   }
 
   ptr += 3;
+  while (*ptr && isspace(*ptr & 255))
+    ptr ++;
+
   _pdfioFileConsume(obj->pdf, (size_t)(ptr - line));
 
   // Then grab the object value...
@@ -438,15 +499,29 @@ _pdfioObjLoad(pdfio_obj_t *obj)		// I - Object
     return (false);
   }
 
+  PDFIO_DEBUG("_pdfioObjLoad: tb.bufptr=%p, tb.bufend=%p, tb.bufptr[0]=0x%02x, tb.bufptr[1]=0x%02x\n", tb.bufptr, tb.bufend, tb.bufptr[0], tb.bufptr[1]);
+
   _pdfioTokenFlush(&tb);
 
   if (!strcmp(line, "stream"))
   {
-    // Yes, save its location...
+    // Yes, this is an embedded stream so save its location...
     obj->stream_offset = _pdfioFileTell(obj->pdf);
     PDFIO_DEBUG("_pdfioObjLoad: stream_offset=%lu.\n", (unsigned long)obj->stream_offset);
   }
 
+  // Decrypt as needed...
+  if (obj->pdf->encryption)
+  {
+    PDFIO_DEBUG("_pdfioObjLoad: Decrypting value...\n");
+
+    if (!_pdfioValueDecrypt(obj->pdf, obj, &obj->value, 0))
+    {
+      PDFIO_DEBUG("_pdfioObjLoad: Failed to decrypt.\n");
+      return (false);
+    }
+  }
+
   PDFIO_DEBUG("_pdfioObjLoad: ");
   PDFIO_DEBUG_VALUE(&obj->value);
   PDFIO_DEBUG("\n");
@@ -491,6 +566,21 @@ pdfioObjOpenStream(pdfio_obj_t *obj,	// I - Object
 }
 
 
+//
+// '_pdfioObjSetExtension()' - Set extension data for an object.
+//
+
+void
+_pdfioObjSetExtension(
+    pdfio_obj_t      *obj,		// I - Object
+    void             *data,		// I - Data
+    _pdfio_extfree_t datafree)		// I - Free function
+{
+  obj->data     = data;
+  obj->datafree = datafree;
+}
+
+
 //
 // 'write_obj_header()' - Write the object header...
 //

pdfio-page.c

@@ -7,10 +7,6 @@
 // information.
 //
 
-//
-// Include necessary headers...
-//
-
 #include "pdfio-private.h"
 
 

pdfio-private.h

@@ -1,7 +1,7 @@
 //
 // Private header file for PDFio.
 //
-// Copyright © 2021-2022 by Michael R Sweet.
+// Copyright © 2021-2024 by Michael R Sweet.
 //
 // Licensed under Apache License v2.0.  See the file "LICENSE" for more
 // information.
@@ -9,41 +9,23 @@
 
 #ifndef PDFIO_PRIVATE_H
 #  define PDFIO_PRIVATE_H
-
-//
-// Include necessary headers...
-//
-
 #  ifdef _WIN32
-/*
+#    define _CRT_SECURE_NO_WARNINGS	// Disable bogus VS warnings/errors...
- * Disable bogus VS warnings/errors...
- */
-
-#    define _CRT_SECURE_NO_WARNINGS
 #  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>
+#  include <locale.h>
 #  ifdef _WIN32
 #    include <io.h>
 #    include <direct.h>
-
+#    include <windows.h> // GetTempPathA
-/*
+#    define access	_access		// Map standard POSIX/C99 names
- * Microsoft renames the POSIX functions to _name, and introduces
- * a broken compatibility layer using the original names.  As a result,
- * random crashes can occur when, for example, strdup() allocates memory
- * from a different heap than used by malloc() and free().
- *
- * To avoid moronic problems like this, we #define the POSIX function
- * names to the corresponding non-standard Microsoft names.
- */
-
-#    define access	_access
 #    define close	_close
 #    define fileno	_fileno
 #    define lseek	_lseek
@@ -56,25 +38,20 @@
 #    define unlink	_unlink
 #    define vsnprintf	_vsnprintf
 #    define write	_write
-
+#    ifndef F_OK
-/*
+#      define F_OK	00		// POSIX parameters/flags
- * Map various parameters for POSIX...
+#      define W_OK	02
- */
+#      define R_OK	04
-
+#    endif // !F_OK
-#    define F_OK	00
+#    define O_RDONLY	_O_RDONLY	// Map standard POSIX open flags
-#    define W_OK	02
-#    define R_OK	04
-#    define O_RDONLY	_O_RDONLY
 #    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
+#    define O_BINARY	0		// Map Windows-specific open flag
 #  endif // _WIN32
-#  include <string.h>
-#  include <ctype.h>
 #  include <zlib.h>
 
 
@@ -118,6 +95,9 @@
 
 #  define PDFIO_MAX_DEPTH	32	// Maximum nesting depth for values
 
+typedef void (*_pdfio_extfree_t)(void *);
+					// Extension data free function
+
 typedef enum _pdfio_mode_e		// Read/write mode
 {
   _PDFIO_MODE_READ,			// Read a PDF file
@@ -247,6 +227,7 @@ typedef struct _pdfio_objmap_s		// PDF object map
 struct _pdfio_file_s			// PDF file structure
 {
   char		*filename;		// Filename
+  struct lconv	*loc;			// Locale data
   char		*version;		// Version number
   pdfio_rect_t	media_box,		// Default MediaBox value
 		crop_box;		// Default CropBox value
@@ -260,7 +241,8 @@ struct _pdfio_file_s			// PDF file structure
   pdfio_permission_t permissions;	// Access permissions (encrypted PDF files)
   uint8_t	file_key[16],		// File encryption key
 		owner_key[32],		// Owner encryption key
-		user_key[32];		// User encryption key
+		user_key[32],		// User encryption key
+		password[32];		// Padded password
   size_t	file_keylen,		// Length of file encryption key
 		owner_keylen,		// Length of owner encryption key
 		user_keylen;		// Length of user encryption key
@@ -288,7 +270,8 @@ struct _pdfio_file_s			// PDF file structure
 		alloc_dicts;		// Allocated dictionaries
   pdfio_dict_t	**dicts;		// Dictionaries
   size_t	num_objs,		// Number of objects
-		alloc_objs;		// Allocated objects
+		alloc_objs,		// Allocated objects
+		last_obj;		// Last object added
   pdfio_obj_t	**objs,			// Objects
 		*current_obj;		// Current object being written/read
   size_t	num_objmaps,		// Number of object maps
@@ -313,6 +296,8 @@ struct _pdfio_obj_s			// Object
   size_t	stream_length;		// Length of stream, if any
   _pdfio_value_t value;			// Dictionary/number/etc. value
   pdfio_stream_t *stream;		// Open stream, if any
+  void		*data;			// Extension data, if any
+  _pdfio_extfree_t datafree;		// Free callback for extension data
 };
 
 struct _pdfio_stream_s			// Stream
@@ -341,6 +326,10 @@ struct _pdfio_stream_s			// Stream
 // Functions...
 //
 
+extern double		_pdfio_strtod(pdfio_file_t *pdf, const char *s) _PDFIO_INTERNAL;
+extern ssize_t		_pdfio_vsnprintf(pdfio_file_t *pdf, char *buffer, size_t bufsize, const char *format, va_list ap) _PDFIO_INTERNAL;
+
+extern bool		_pdfioArrayDecrypt(pdfio_file_t *pdf, pdfio_obj_t *obj, pdfio_array_t *a, size_t depth) _PDFIO_INTERNAL;
 extern void		_pdfioArrayDebug(pdfio_array_t *a, FILE *fp) _PDFIO_INTERNAL;
 extern void		_pdfioArrayDelete(pdfio_array_t *a) _PDFIO_INTERNAL;
 extern _pdfio_value_t	*_pdfioArrayGetValue(pdfio_array_t *a, size_t n) _PDFIO_INTERNAL;
@@ -365,6 +354,7 @@ extern void		_pdfioCryptoSHA256Finish(_pdfio_sha256_t *ctx, uint8_t *Message_Dig
 extern bool		_pdfioCryptoUnlock(pdfio_file_t *pdf, pdfio_password_cb_t password_cb, void *password_data) _PDFIO_INTERNAL;
 
 extern void		_pdfioDictClear(pdfio_dict_t *dict, const char *key) _PDFIO_INTERNAL;
+extern bool		_pdfioDictDecrypt(pdfio_file_t *pdf, pdfio_obj_t *obj, pdfio_dict_t *dict, size_t depth) _PDFIO_INTERNAL;
 extern void		_pdfioDictDebug(pdfio_dict_t *dict, FILE *fp) _PDFIO_INTERNAL;
 extern void		_pdfioDictDelete(pdfio_dict_t *dict) _PDFIO_INTERNAL;
 extern _pdfio_value_t	*_pdfioDictGetValue(pdfio_dict_t *dict, const char *key) _PDFIO_INTERNAL;
@@ -391,7 +381,9 @@ extern off_t		_pdfioFileTell(pdfio_file_t *pdf) _PDFIO_INTERNAL;
 extern bool		_pdfioFileWrite(pdfio_file_t *pdf, const void *buffer, size_t bytes) _PDFIO_INTERNAL;
 
 extern void		_pdfioObjDelete(pdfio_obj_t *obj) _PDFIO_INTERNAL;
+extern void		*_pdfioObjGetExtension(pdfio_obj_t *obj) _PDFIO_INTERNAL;
 extern bool		_pdfioObjLoad(pdfio_obj_t *obj) _PDFIO_INTERNAL;
+extern void		_pdfioObjSetExtension(pdfio_obj_t *obj, void *data, _pdfio_extfree_t datafree) _PDFIO_INTERNAL;
 
 extern pdfio_stream_t	*_pdfioStreamCreate(pdfio_obj_t *obj, pdfio_obj_t *length_obj, pdfio_filter_t compression) _PDFIO_INTERNAL;
 extern pdfio_stream_t	*_pdfioStreamOpen(pdfio_obj_t *obj, bool decode) _PDFIO_INTERNAL;
@@ -406,9 +398,11 @@ extern void		_pdfioTokenPush(_pdfio_token_t *tb, const char *token) _PDFIO_INTER
 extern bool		_pdfioTokenRead(_pdfio_token_t *tb, char *buffer, size_t bufsize);
 
 extern _pdfio_value_t	*_pdfioValueCopy(pdfio_file_t *pdfdst, _pdfio_value_t *vdst, pdfio_file_t *pdfsrc, _pdfio_value_t *vsrc) _PDFIO_INTERNAL;
+extern bool		_pdfioValueDecrypt(pdfio_file_t *pdf, pdfio_obj_t *obj, _pdfio_value_t *v, size_t depth) _PDFIO_INTERNAL;
 extern void		_pdfioValueDebug(_pdfio_value_t *v, FILE *fp) _PDFIO_INTERNAL;
 extern void		_pdfioValueDelete(_pdfio_value_t *v) _PDFIO_INTERNAL;
 extern _pdfio_value_t	*_pdfioValueRead(pdfio_file_t *pdf, pdfio_obj_t *obj, _pdfio_token_t *ts, _pdfio_value_t *v, size_t depth) _PDFIO_INTERNAL;
 extern bool		_pdfioValueWrite(pdfio_file_t *pdf, pdfio_obj_t *obj, _pdfio_value_t *v, off_t *length) _PDFIO_INTERNAL;
 
+
 #endif // !PDFIO_PRIVATE_H

pdfio-sha256.c

@@ -1,7 +1,7 @@
 //
 // SHA-256 functions for PDFio.
 //
-// Copyright © 2021 by Michael R Sweet.
+// Copyright © 2021-2023 by Michael R Sweet.
 // Copyright © 2011 IETF Trust and the persons identified as authors of the
 // code.  All rights reserved.
 //
@@ -217,7 +217,7 @@ _pdfioCryptoSHA256Append(_pdfio_sha256_t *context, const uint8_t *message_array,
  */
 void
 _pdfioCryptoSHA256Finish(_pdfio_sha256_t *context,
-                 uint8_t Message_Digest[SHA256HashSize])
+                 uint8_t *Message_Digest)
 {
   SHA224_256ResultN(context, Message_Digest, SHA256HashSize);
 }

pdfio-stream.c

@@ -1,16 +1,12 @@
 //
 // PDF stream functions for PDFio.
 //
-// Copyright © 2021-2023 by Michael R Sweet.
+// Copyright © 2021-2024 by Michael R Sweet.
 //
 // Licensed under Apache License v2.0.  See the file "LICENSE" for more
 // information.
 //
 
-//
-// Include necessary headers...
-//
-
 #include "pdfio-private.h"
 
 
@@ -412,6 +408,7 @@ _pdfioStreamOpen(pdfio_obj_t *obj,	// I - Object
   pdfio_stream_t	*st;		// Stream
   pdfio_dict_t		*dict = pdfioObjGetDict(obj);
 					// Object dictionary
+  const char		*type;		// Object type
 
 
   PDFIO_DEBUG("_pdfioStreamOpen(obj=%p(%u), decode=%s)\n", obj, (unsigned)obj->number, decode ? "true" : "false");
@@ -438,7 +435,9 @@ _pdfioStreamOpen(pdfio_obj_t *obj,	// I - Object
     return (NULL);
   }
 
-  if (obj->pdf->encryption)
+  type = pdfioObjGetType(obj);
+
+  if (obj->pdf->encryption && (!type || strcmp(type, "XRef")))
   {
     uint8_t	iv[64];			// Initialization vector
     size_t	ivlen;			// Length of initialization vector, if any
@@ -452,6 +451,7 @@ _pdfioStreamOpen(pdfio_obj_t *obj,	// I - Object
       return (NULL);
     }
 
+    PDFIO_DEBUG("_pdfioStreamOpen: ivlen=%d\n", (int)ivlen);
     if (ivlen > 0)
       _pdfioFileConsume(st->pdf, ivlen);
 
@@ -464,11 +464,19 @@ _pdfioStreamOpen(pdfio_obj_t *obj,	// I - Object
     // Try to decode/decompress the contents of this object...
     const char	*filter = pdfioDictGetName(dict, "Filter");
 					// Filter value
+    pdfio_array_t *fa = pdfioDictGetArray(dict, "Filter");
+					// Filter array
+
+    if (!filter && fa && pdfioArrayGetSize(fa) == 1)
+    {
+      // Support single-valued arrays...
+      filter = pdfioArrayGetName(fa, 0);
+    }
 
     if (!filter)
     {
       // No single filter name, do we have a compound filter?
-      if (pdfioDictGetArray(dict, "Filter"))
+      if (fa)
       {
 	// TODO: Implement compound filters...
 	_pdfioFileError(st->pdf, "Unsupported compound stream filter.");
@@ -559,6 +567,7 @@ _pdfioStreamOpen(pdfio_obj_t *obj,	// I - Object
       else
         st->predictor = _PDFIO_PREDICTOR_NONE;
 
+      PDFIO_DEBUG("_pdfioStreamOpen: pos=%ld\n", (long)_pdfioFileTell(st->pdf));
       if (sizeof(st->cbuffer) > st->remaining)
 	rbytes = _pdfioFileRead(st->pdf, st->cbuffer, st->remaining);
       else
@@ -579,12 +588,6 @@ _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)
@@ -687,7 +690,7 @@ pdfioStreamPrintf(
 
   // Format the string...
   va_start(ap, format);
-  vsnprintf(buffer, sizeof(buffer), format, ap);
+  _pdfio_vsnprintf(st->pdf, buffer, sizeof(buffer), format, ap);
   va_end(ap);
 
   // Write the string...
@@ -1008,6 +1011,7 @@ stream_read(pdfio_stream_t *st,		// I - Stream
             size_t         bytes)	// I - Number of bytes to read
 {
   ssize_t	rbytes;			// Bytes read
+  uInt		avail_in, avail_out;	// Previous flate values
 
 
   if (st->filter == PDFIO_FILTER_NONE)
@@ -1062,7 +1066,7 @@ stream_read(pdfio_stream_t *st,		// I - Stream
 
       if ((status = inflate(&(st->flate), Z_NO_FLUSH)) < Z_OK)
       {
-	_pdfioFileError(st->pdf, "Unable to decompress stream data: %s", zstrerror(status));
+	_pdfioFileError(st->pdf, "Unable to decompress stream data for object %ld: %s", (long)st->obj->number, zstrerror(status));
 	return (-1);
       }
 
@@ -1113,12 +1117,15 @@ stream_read(pdfio_stream_t *st,		// I - Stream
 	  st->flate.avail_in = (uInt)rbytes;
 	}
 
+        avail_in  = st->flate.avail_in;
+        avail_out = st->flate.avail_out;
+
 	if ((status = inflate(&(st->flate), Z_NO_FLUSH)) < Z_OK)
 	{
-	  _pdfioFileError(st->pdf, "Unable to decompress stream data: %s", zstrerror(status));
+	  _pdfioFileError(st->pdf, "Unable to decompress stream data for object %ld: %s", (long)st->obj->number, zstrerror(status));
 	  return (-1);
 	}
-	else if (status == Z_STREAM_END)
+	else if (status == Z_STREAM_END || (avail_in == st->flate.avail_in && avail_out == st->flate.avail_out))
 	  break;
       }
 
@@ -1180,12 +1187,15 @@ stream_read(pdfio_stream_t *st,		// I - Stream
 	  st->flate.avail_in = (uInt)rbytes;
 	}
 
+        avail_in  = st->flate.avail_in;
+        avail_out = st->flate.avail_out;
+
 	if ((status = inflate(&(st->flate), Z_NO_FLUSH)) < Z_OK)
 	{
-	  _pdfioFileError(st->pdf, "Unable to decompress stream data: %s", zstrerror(status));
+	  _pdfioFileError(st->pdf, "Unable to decompress stream data for object %ld: %s", (long)st->obj->number, zstrerror(status));
 	  return (-1);
 	}
-	else if (status == Z_STREAM_END)
+	else if (status == Z_STREAM_END || (avail_in == st->flate.avail_in && avail_out == st->flate.avail_out))
 	  break;
       }
 

pdfio-string.c

@@ -1,16 +1,12 @@
 //
-// PDF dictionary functions for PDFio.
+// PDF string functions for PDFio.
 //
-// Copyright © 2021 by Michael R Sweet.
+// Copyright © 2021-2024 by Michael R Sweet.
 //
 // Licensed under Apache License v2.0.  See the file "LICENSE" for more
 // information.
 //
 
-//
-// Include necessary headers...
-//
-
 #include "pdfio-private.h"
 
 
@@ -18,7 +14,360 @@
 // Local functions...
 //
 
-static int	compare_strings(char **a, char **b);
+static size_t	find_string(pdfio_file_t *pdf, const char *s, int *rdiff);
+
+
+//
+// '_pdfio_strtod()' - Convert a string to a double value.
+//
+// This function wraps strtod() to avoid locale issues.
+//
+
+double					// O - Double value
+_pdfio_strtod(pdfio_file_t *pdf,	// I - PDF file
+              const char   *s)		// I - String
+{
+  char	temp[64],			// Temporary buffer
+	*tempptr;			// Pointer into temporary buffer
+
+
+  // See if the locale has a special decimal point string...
+  if (!pdf->loc)
+    return (strtod(s, NULL));
+
+  // Copy leading sign, numbers, period, and then numbers...
+  tempptr                = temp;
+  temp[sizeof(temp) - 1] = '\0';
+
+  while (*s && *s != '.')
+  {
+    if (tempptr < (temp + sizeof(temp) - 1))
+      *tempptr++ = *s++;
+    else
+      return (0.0);
+  }
+
+  if (*s == '.')
+  {
+    // Convert decimal point to locale equivalent...
+    size_t	declen = strlen(pdf->loc->decimal_point);
+					// Length of decimal point
+    s ++;
+
+    if (declen <= (sizeof(temp) - (size_t)(tempptr - temp)))
+    {
+      memcpy(tempptr, pdf->loc->decimal_point, declen);
+      tempptr += declen;
+    }
+    else
+    {
+      return (0.0);
+    }
+  }
+
+  // Copy any remaining characters...
+  while (*s)
+  {
+    if (tempptr < (temp + sizeof(temp) - 1))
+      *tempptr++ = *s++;
+    else
+      return (0.0);
+  }
+
+  // Nul-terminate the temporary string and convert the string...
+  *tempptr = '\0';
+
+  return (strtod(temp, NULL));
+}
+
+
+//
+// '_pdfio_vsnprintf()' - Format a string.
+//
+// This function emulates vsnprintf() to avoid locale issues.
+//
+
+ssize_t					// O - Number of bytes
+_pdfio_vsnprintf(pdfio_file_t *pdf,	// I - PDF file
+                 char         *buffer,	// I - Output buffer
+                 size_t       bufsize,	// I - Size of output buffer
+                 const char   *format,	// I - printf-style format string
+                 va_list      ap)	// I - Pointer to additional arguments
+{
+  char		*bufptr,		// Pointer to position in buffer
+		*bufend,		// Pointer to end of buffer
+		size,			// Size character (h, l, L)
+		type;			// Format type character
+  int		width,			// Width of field
+		prec;			// Number of characters of precision
+  char		tformat[100],		// Temporary format string for snprintf()
+		*tptr,			// Pointer into temporary format
+		temp[1024],		// Buffer for formatted numbers
+		*tempptr;		// Pointer into buffer
+  char		*s;			// Pointer to string
+  ssize_t	bytes;			// Total number of bytes needed
+  const char	*dec = pdf->loc ? pdf->loc->decimal_point : ".";
+					// Decimal point string
+  char		*decptr;		// Pointer to decimal point
+
+
+  // Loop through the format string, formatting as needed...
+  bufptr  = buffer;
+  bufend  = buffer + bufsize - 1;
+  *bufend = '\0';
+  bytes   = 0;
+
+  while (*format)
+  {
+    if (*format == '%')
+    {
+      // Format character...
+      tptr = tformat;
+      *tptr++ = *format++;
+
+      if (*format == '%')
+      {
+        if (bufptr < bufend)
+	  *bufptr++ = *format;
+        bytes ++;
+        format ++;
+	continue;
+      }
+      else if (strchr(" -+#\'", *format))
+      {
+        *tptr++ = *format++;
+      }
+
+      if (*format == '*')
+      {
+        // Get width from argument...
+	format ++;
+	width = va_arg(ap, int);
+
+	snprintf(tptr, sizeof(tformat) - (size_t)(tptr - tformat), "%d", width);
+	tptr += strlen(tptr);
+      }
+      else
+      {
+	width = 0;
+
+	while (isdigit(*format & 255))
+	{
+	  if (tptr < (tformat + sizeof(tformat) - 1))
+	    *tptr++ = *format;
+
+	  width = width * 10 + *format++ - '0';
+	}
+      }
+
+      if (*format == '.')
+      {
+	if (tptr < (tformat + sizeof(tformat) - 1))
+	  *tptr++ = *format;
+
+        format ++;
+
+        if (*format == '*')
+	{
+          // Get precision from argument...
+	  format ++;
+	  prec = va_arg(ap, int);
+
+	  snprintf(tptr, sizeof(tformat) - (size_t)(tptr - tformat), "%d", prec);
+	  tptr += strlen(tptr);
+	}
+	else
+	{
+	  prec = 0;
+
+	  while (isdigit(*format & 255))
+	  {
+	    if (tptr < (tformat + sizeof(tformat) - 1))
+	      *tptr++ = *format;
+
+	    prec = prec * 10 + *format++ - '0';
+	  }
+	}
+      }
+
+      if (*format == 'l' && format[1] == 'l')
+      {
+        size = 'L';
+
+	if (tptr < (tformat + sizeof(tformat) - 2))
+	{
+	  *tptr++ = 'l';
+	  *tptr++ = 'l';
+	}
+
+	format += 2;
+      }
+      else if (*format == 'h' || *format == 'l' || *format == 'L')
+      {
+	if (tptr < (tformat + sizeof(tformat) - 1))
+	  *tptr++ = *format;
+
+        size = *format++;
+      }
+      else
+      {
+        size = 0;
+      }
+
+      if (!*format)
+        break;
+
+      if (tptr < (tformat + sizeof(tformat) - 1))
+        *tptr++ = *format;
+
+      type  = *format++;
+      *tptr = '\0';
+
+      switch (type)
+      {
+	case 'E' : // Floating point formats
+	case 'G' :
+	case 'e' :
+	case 'f' :
+	case 'g' :
+	    if ((size_t)(width + 2) > sizeof(temp))
+	      break;
+
+	    snprintf(temp, sizeof(temp), tformat, va_arg(ap, double));
+
+	    if ((decptr = strstr(temp, dec)) != NULL)
+	    {
+	      // Convert locale decimal point to "."
+	      PDFIO_DEBUG("_pdfio_vsnprintf: Before \"%s\"\n", temp);
+	      tempptr = decptr + strlen(dec);
+	      if (tempptr > (decptr + 1))
+	        memmove(decptr + 1, tempptr, strlen(tempptr) + 1);
+	      *decptr = '.';
+
+	      // Strip trailing 0's...
+	      for (tempptr = temp + strlen(temp) - 1; tempptr > temp && *tempptr == '0'; tempptr --)
+		*tempptr = '\0';
+
+	      if (*tempptr == '.')
+		*tempptr = '\0';	// Strip trailing decimal point
+
+	      PDFIO_DEBUG("_pdfio_vsnprintf: After \"%s\"\n", temp);
+	    }
+
+            // Copy to the output buffer
+            bytes += (int)strlen(temp);
+
+            if (bufptr < bufend)
+	    {
+	      strncpy(bufptr, temp, (size_t)(bufend - bufptr - 1));
+	      bufptr += strlen(bufptr);
+	    }
+	    break;
+
+        case 'B' : // Integer formats
+	case 'X' :
+	case 'b' :
+        case 'd' :
+	case 'i' :
+	case 'o' :
+	case 'u' :
+	case 'x' :
+	    if ((size_t)(width + 2) > sizeof(temp))
+	      break;
+
+#  ifdef HAVE_LONG_LONG
+            if (size == 'L')
+	      snprintf(temp, sizeof(temp), tformat, va_arg(ap, long long));
+	    else
+#  endif // HAVE_LONG_LONG
+            if (size == 'l')
+	      snprintf(temp, sizeof(temp), tformat, va_arg(ap, long));
+	    else
+	      snprintf(temp, sizeof(temp), tformat, va_arg(ap, int));
+
+            bytes += (int)strlen(temp);
+
+	    if (bufptr < bufend)
+	    {
+	      strncpy(bufptr, temp, (size_t)(bufend - bufptr - 1));
+	      bufptr += strlen(bufptr);
+	    }
+	    break;
+
+	case 'p' : // Pointer value
+	    if ((size_t)(width + 2) > sizeof(temp))
+	      break;
+
+	    snprintf(temp, sizeof(temp), tformat, va_arg(ap, void *));
+
+            bytes += (int)strlen(temp);
+
+	    if (bufptr < bufend)
+	    {
+	      strncpy(bufptr, temp, (size_t)(bufend - bufptr - 1));
+	      bufptr += strlen(bufptr);
+	    }
+	    break;
+
+        case 'c' : // Character or character array
+	    bytes += width;
+
+	    if (bufptr < bufend)
+	    {
+	      if (width <= 1)
+	      {
+	        *bufptr++ = (char)va_arg(ap, int);
+	      }
+	      else
+	      {
+		if ((bufptr + width) > bufend)
+		  width = (int)(bufend - bufptr);
+
+		memcpy(bufptr, va_arg(ap, char *), (size_t)width);
+		bufptr += width;
+	      }
+	    }
+	    break;
+
+	case 's' : // String
+	    if ((s = va_arg(ap, char *)) == NULL)
+	      s = "(null)";
+
+            bytes += strlen(s);
+
+	    if (bufptr < bufend)
+	    {
+	      strncpy(bufptr, s, (size_t)(bufend - bufptr - 1));
+	      bufptr += strlen(bufptr);
+	    }
+	    break;
+
+	case 'n' : // Output number of chars so far
+	    *(va_arg(ap, int *)) = (int)bytes;
+	    break;
+      }
+    }
+    else
+    {
+      // Literal character...
+      bytes ++;
+
+      if (bufptr < bufend)
+        *bufptr++ = *format++;
+    }
+  }
+
+  // Nul-terminate the string and return the number of characters needed.
+  if (bufptr < bufend)
+  {
+    // Everything fit in the buffer...
+    *bufptr = '\0';
+  }
+
+  PDFIO_DEBUG("_pdfio_vsnprintf: Returning %ld \"%s\"\n", (long)bytes, buffer);
+
+  return (bytes);
+}
 
 
 //
@@ -36,8 +385,9 @@ pdfioStringCreate(
     pdfio_file_t *pdf,			// I - PDF file
     const char   *s)			// I - Nul-terminated string
 {
-  char	*news;				// New string
+  char		*news;			// New string
-  char	**match;			// Matching string
+  size_t	idx;			// Index into strings
+  int		diff;			// Different
 
 
   PDFIO_DEBUG("pdfioStringCreate(pdf=%p, s=\"%s\")\n", pdf, s);
@@ -47,8 +397,17 @@ pdfioStringCreate(
     return (NULL);
 
   // See if the string has already been added...
-  if (pdf->num_strings > 0 && (match = (char **)bsearch(&s, pdf->strings, pdf->num_strings, sizeof(char *), (int (*)(const void *, const void *))compare_strings)) != NULL)
+  if (pdf->num_strings > 0)
-    return (*match);
+  {
+    idx = find_string(pdf, s, &diff);
+    if (diff == 0)
+      return (pdf->strings[idx]);
+  }
+  else
+  {
+    idx  = 0;
+    diff = -1;
+  }
 
   // Not already added, so add it...
   if ((news = strdup(s)) == NULL)
@@ -69,11 +428,17 @@ pdfioStringCreate(
     pdf->alloc_strings += 128;
   }
 
-  // TODO: Change to insertion sort as needed...
+  // Insert the string...
-  pdf->strings[pdf->num_strings ++] = news;
+  if (diff > 0)
+    idx ++;
 
-  if (pdf->num_strings > 1)
+  PDFIO_DEBUG("pdfioStringCreate: Inserting \"%s\" at %u\n", news, (unsigned)idx);
-    qsort(pdf->strings, pdf->num_strings, sizeof(char *), (int (*)(const void *, const void *))compare_strings);
+
+  if (idx < pdf->num_strings)
+    memmove(pdf->strings + idx + 1, pdf->strings + idx, (pdf->num_strings - idx) * sizeof(char *));
+
+  pdf->strings[idx] = news;
+  pdf->num_strings ++;
 
   PDFIO_DEBUG("pdfioStringCreate: %lu strings\n", (unsigned long)pdf->num_strings);
 
@@ -124,17 +489,67 @@ _pdfioStringIsAllocated(
     pdfio_file_t *pdf,			// I - PDF file
     const char   *s)			// I - String
 {
-  return (pdf->num_strings > 0 && bsearch(&s, pdf->strings, pdf->num_strings, sizeof(char *), (int (*)(const void *, const void *))compare_strings) != NULL);
+  int	diff;				// Difference
+
+
+  if (pdf->num_strings == 0)
+    return (false);
+
+  find_string(pdf, s, &diff);
+
+  return (diff == 0);
 }
 
 
 //
-// 'compare_strings()' - Compare two strings.
+// 'find_string()' - Find an element in the array.
 //
 
-static int				// O - Result of comparison
+static size_t				// O - Index of match
-compare_strings(char **a,		// I - First string
+find_string(pdfio_file_t *pdf,		// I - PDF file
-                char **b)		// I - Second string
+	    const char   *s,		// I - String to find
+	    int          *rdiff)	// O - Difference of match
 {
-  return (strcmp(*a, *b));
+  size_t	left,			// Left side of search
+		right,			// Right side of search
+		current;		// Current element
+  int		diff;			// Comparison with current element
+
+
+  // Do a binary search for the string...
+  left  = 0;
+  right = pdf->num_strings - 1;
+
+  do
+  {
+    current = (left + right) / 2;
+    diff    = strcmp(s, pdf->strings[current]);
+
+    if (diff == 0)
+      break;
+    else if (diff < 0)
+      right = current;
+    else
+      left = current;
+  }
+  while ((right - left) > 1);
+
+  if (diff != 0)
+  {
+    // Check the last 1 or 2 elements...
+    if ((diff = strcmp(s, pdf->strings[left])) <= 0)
+    {
+      current = left;
+    }
+    else
+    {
+      diff    = strcmp(s, pdf->strings[right]);
+      current = right;
+    }
+  }
+
+  // Return the closest string and the difference...
+  *rdiff = diff;
+
+  return (current);
 }

pdfio-token.c

@@ -7,10 +7,6 @@
 // information.
 //
 
-//
-// Include necessary headers...
-//
-
 #include "pdfio-private.h"
 
 
@@ -212,9 +208,10 @@ _pdfioTokenRead(_pdfio_token_t *tb,	// I - Token buffer/stack
 	*bufend,			// End of buffer
 	state = '\0';			// Current state
   bool	saw_nul = false;		// Did we see a nul character?
+  size_t count = 0;			// Number of whitespace/comment bytes
+
 
 
-  //
   // "state" is:
   //
   // - '\0' for idle
@@ -233,21 +230,45 @@ _pdfioTokenRead(_pdfio_token_t *tb,	// I - Token buffer/stack
   // Skip leading whitespace...
   while ((ch = get_char(tb)) != EOF)
   {
+    count ++;
+
     if (ch == '%')
     {
       // Skip comment
+      PDFIO_DEBUG("_pdfioTokenRead: Skipping comment...\n");
       while ((ch = get_char(tb)) != EOF)
       {
+        count ++;
+
 	if (ch == '\n' || ch == '\r')
+	{
 	  break;
+	}
+	else if (count > 2048)
+	{
+	  _pdfioFileError(tb->pdf, "Comment too long.");
+	  *bufptr = '\0';
+	  return (false);
+	}
       }
     }
     else if (!isspace(ch))
+    {
       break;
+    }
+    else if (count > 2048)
+    {
+      _pdfioFileError(tb->pdf, "Too much whitespace.");
+      *bufptr = '\0';
+      return (false);
+    }
   }
 
   if (ch == EOF)
+  {
+    *bufptr = '\0';
     return (false);
+  }
 
   // Check for delimiters...
   if (strchr(PDFIO_DELIM_CHARS, ch) != NULL)
@@ -267,6 +288,8 @@ _pdfioTokenRead(_pdfio_token_t *tb,	// I - Token buffer/stack
     *bufptr++ = (char)ch;
   }
 
+  PDFIO_DEBUG("_pdfioTokenRead: state='%c'\n", state);
+
   switch (state)
   {
     case '(' : // Literal string
@@ -358,6 +381,7 @@ _pdfioTokenRead(_pdfio_token_t *tb,	// I - Token buffer/stack
 	  {
 	    // Out of space
 	    _pdfioFileError(tb->pdf, "Token too large.");
+	    *bufptr = '\0';
 	    return (false);
 	  }
 	}
@@ -365,6 +389,7 @@ _pdfioTokenRead(_pdfio_token_t *tb,	// I - Token buffer/stack
 	if (ch != ')')
 	{
 	  _pdfioFileError(tb->pdf, "Unterminated string literal.");
+	  *bufptr = '\0';
 	  return (false);
 	}
 
@@ -384,6 +409,7 @@ _pdfioTokenRead(_pdfio_token_t *tb,	// I - Token buffer/stack
           {
 	    // Out of space...
 	    _pdfioFileError(tb->pdf, "Token too large.");
+	    *bufptr = '\0';
 	    return (false);
           }
 
@@ -417,9 +443,17 @@ _pdfioTokenRead(_pdfio_token_t *tb,	// I - Token buffer/stack
 	  {
 	    // Out of space...
 	    _pdfioFileError(tb->pdf, "Token too large.");
+	    *bufptr = '\0';
 	    return (false);
 	  }
 	}
+
+	if (ch == '\r')
+	{
+	  // Look for a trailing LF
+	  if ((ch = get_char(tb)) != EOF && ch != '\n')
+	    tb->bufptr --;
+	}
 	break;
 
     case 'N' : // number
@@ -428,6 +462,7 @@ _pdfioTokenRead(_pdfio_token_t *tb,	// I - Token buffer/stack
 	  if (!isdigit(ch) && ch != '.')
 	  {
 	    // End of number...
+	    PDFIO_DEBUG("_pdfioTokenRead: End of number with ch=0x%02x\n", ch);
 	    tb->bufptr --;
 	    break;
 	  }
@@ -440,6 +475,7 @@ _pdfioTokenRead(_pdfio_token_t *tb,	// I - Token buffer/stack
 	  {
 	    // Out of space...
 	    _pdfioFileError(tb->pdf, "Token too large.");
+	    *bufptr = '\0';
 	    return (false);
 	  }
 	}
@@ -466,12 +502,17 @@ _pdfioTokenRead(_pdfio_token_t *tb,	// I - Token buffer/stack
 	      if (!isxdigit(tch & 255))
 	      {
 		_pdfioFileError(tb->pdf, "Bad # escape in name.");
+		*bufptr = '\0';
 		return (false);
 	      }
 	      else if (isdigit(tch))
+	      {
 		ch = ((ch & 255) << 4) | (tch - '0');
+	      }
 	      else
+	      {
 		ch = ((ch & 255) << 4) | (tolower(tch) - 'a' + 10);
+	      }
 	    }
 	  }
 
@@ -483,9 +524,17 @@ _pdfioTokenRead(_pdfio_token_t *tb,	// I - Token buffer/stack
 	  {
 	    // Out of space
 	    _pdfioFileError(tb->pdf, "Token too large.");
+	    *bufptr = '\0';
 	    return (false);
 	  }
 	}
+
+	if (bufptr == (buffer + 1))
+	{
+	  _pdfioFileError(tb->pdf, "Empty name.");
+	  *bufptr = '\0';
+	  return (false);
+	}
 	break;
 
     case '<' : // Potential hex string
@@ -495,12 +544,22 @@ _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);
+	  *bufptr = '\0';
 	  return (false);
 	}
 
+        count = 0;
+
         do
 	{
 	  if (isxdigit(ch))
@@ -509,25 +568,39 @@ _pdfioTokenRead(_pdfio_token_t *tb,	// I - Token buffer/stack
 	    {
 	      // Hex digit
 	      *bufptr++ = (char)ch;
+	      count = 0;
 	    }
 	    else
 	    {
 	      // Too large
 	      _pdfioFileError(tb->pdf, "Token too large.");
+	      *bufptr = '\0';
 	      return (false);
 	    }
 	  }
 	  else if (!isspace(ch))
 	  {
 	    _pdfioFileError(tb->pdf, "Invalid hex string character '%c'.", ch);
+	    *bufptr = '\0';
 	    return (false);
 	  }
+	  else
+	  {
+	    count ++;
+	    if (count > 2048)
+	    {
+	      _pdfioFileError(tb->pdf, "Too much whitespace.");
+	      *bufptr = '\0';
+	      return (false);
+	    }
+	  }
 	}
 	while ((ch = get_char(tb)) != EOF && ch != '>');
 
 	if (ch == EOF)
 	{
 	  _pdfioFileError(tb->pdf, "Unterminated hex string.");
+	  *bufptr = '\0';
 	  return (false);
 	}
 	break;
@@ -540,6 +613,7 @@ _pdfioTokenRead(_pdfio_token_t *tb,	// I - Token buffer/stack
 	else
 	{
 	  _pdfioFileError(tb->pdf, "Syntax error: '>%c'.", ch);
+	  *bufptr = '\0';
 	  return (false);
 	}
 	break;
@@ -547,7 +621,7 @@ _pdfioTokenRead(_pdfio_token_t *tb,	// I - Token buffer/stack
 
   *bufptr = '\0';
 
-//  PDFIO_DEBUG("_pdfioTokenRead: Read '%s'.\n", buffer);
+  PDFIO_DEBUG("_pdfioTokenRead: Read '%s'.\n", buffer);
 
   return (bufptr > buffer);
 }
@@ -584,7 +658,6 @@ get_char(_pdfio_token_t *tb)		// I - Token buffer
     tb->bufptr = tb->buffer;
     tb->bufend = tb->buffer + bytes;
 
-#if 0
 #ifdef DEBUG
     unsigned char *ptr;			// Pointer into buffer
 
@@ -598,7 +671,6 @@ get_char(_pdfio_token_t *tb)		// I - Token buffer
     }
     PDFIO_DEBUG("'\n");
 #endif // DEBUG
-#endif // 0
   }
 
   // Return the next character...

pdfio-value.c

@@ -1,17 +1,20 @@
 //
 // PDF value functions for PDFio.
 //
-// Copyright © 2021-2023 by Michael R Sweet.
+// Copyright © 2021-2024 by Michael R Sweet.
 //
 // Licensed under Apache License v2.0.  See the file "LICENSE" for more
 // information.
 //
 
+#include "pdfio-private.h"
+
+
 //
-// Include necessary headers...
+// Local functions...
 //
 
-#include "pdfio-private.h"
+static time_t	get_date_time(const char *s);
 
 
 //
@@ -109,6 +112,101 @@ _pdfioValueCopy(pdfio_file_t   *pdfdst,	// I - Destination PDF file
 }
 
 
+//
+// '_pdfioValueDecrypt()' - Decrypt a value.
+//
+
+bool					// O - `true` on success, `false` on error
+_pdfioValueDecrypt(pdfio_file_t   *pdf,	// I - PDF file
+                   pdfio_obj_t    *obj,	// I - Object
+                   _pdfio_value_t *v,	// I - Value
+                   size_t         depth)// I - Depth
+{
+  _pdfio_crypto_ctx_t	ctx;		// Decryption context
+  _pdfio_crypto_cb_t	cb;		// Decryption callback
+  size_t		ivlen;		// Number of initialization vector bytes
+  uint8_t		temp[32768];	// Temporary buffer for decryption
+  size_t		templen;	// Number of actual data bytes
+  time_t		timeval;	// Date/time value
+
+
+  if (depth > PDFIO_MAX_DEPTH)
+  {
+    _pdfioFileError(pdf, "Value too deep.");
+    return (false);
+  }
+
+  switch (v->type)
+  {
+    default :
+        // Do nothing
+        break;
+
+    case PDFIO_VALTYPE_ARRAY :
+        return (_pdfioArrayDecrypt(pdf, obj, v->value.array, depth + 1));
+        break;
+
+    case PDFIO_VALTYPE_DICT :
+        return (_pdfioDictDecrypt(pdf, obj, v->value.dict, depth + 1));
+        break;
+
+    case PDFIO_VALTYPE_BINARY :
+	// Decrypt the binary string...
+	if (v->value.binary.datalen > (sizeof(temp) - 32))
+	{
+	  _pdfioFileError(pdf, "Unable to read encrypted binary string - too long.");
+	  return (false);
+	}
+
+	ivlen = v->value.binary.datalen;
+	if ((cb = _pdfioCryptoMakeReader(pdf, obj, &ctx, v->value.binary.data, &ivlen)) == NULL)
+	  return (false);
+
+	templen = (cb)(&ctx, temp, v->value.binary.data + ivlen, v->value.binary.datalen - ivlen);
+
+	// Copy the decrypted string back to the value and adjust the length...
+	memcpy(v->value.binary.data, temp, templen);
+
+	if (pdf->encryption >= PDFIO_ENCRYPTION_AES_128)
+	  v->value.binary.datalen = templen - temp[templen - 1];
+	else
+	  v->value.binary.datalen = templen;
+	break;
+
+    case PDFIO_VALTYPE_STRING :
+        // Decrypt regular string...
+        templen = strlen(v->value.string);
+	if (templen > (sizeof(temp) - 33))
+	{
+	  _pdfioFileError(pdf, "Unable to read encrypted string - too long.");
+	  return (false);
+	}
+
+	ivlen = templen;
+	if ((cb = _pdfioCryptoMakeReader(pdf, obj, &ctx, (uint8_t *)v->value.string, &ivlen)) == NULL)
+	  return (false);
+
+	templen = (cb)(&ctx, temp, (uint8_t *)v->value.string + ivlen, templen - ivlen);
+	temp[templen] = '\0';
+
+        if ((timeval = get_date_time((char *)temp)) != 0)
+        {
+          // Change the type to date...
+          v->type       = PDFIO_VALTYPE_DATE;
+          v->value.date = timeval;
+        }
+        else
+        {
+          // Copy the decrypted string back to the value...
+	  v->value.string = pdfioStringCreate(pdf, (char *)temp);
+	}
+        break;
+  }
+
+  return (true);
+}
+
+
 //
 // '_pdfioValueDebug()' - Print the contents of a value.
 //
@@ -117,6 +215,9 @@ void
 _pdfioValueDebug(_pdfio_value_t *v,	// I - Value
 		 FILE           *fp)	// I - Output file
 {
+  if (!v)
+    return;
+
   switch (v->type)
   {
     case PDFIO_VALTYPE_ARRAY :
@@ -200,6 +301,7 @@ _pdfioValueRead(pdfio_file_t   *pdf,	// I - PDF file
                 size_t         depth)	// I - Depth of value
 {
   char		token[32768];		// Token buffer
+  time_t	timeval;		// Date/time value
 #ifdef DEBUG
   static const char * const valtypes[] =
   {
@@ -249,73 +351,10 @@ _pdfioValueRead(pdfio_file_t   *pdf,	// I - PDF file
     if ((v->value.dict = _pdfioDictRead(pdf, obj, tb, depth + 1)) == NULL)
       return (NULL);
   }
-  else if (!strncmp(token, "(D:", 3))
+  else if (!strncmp(token, "(D:", 3) && (timeval = get_date_time(token + 1)) != 0)
   {
-    // Possible date value of the form:
+    v->type       = PDFIO_VALTYPE_DATE;
-    //
+    v->value.date = timeval;
-    //   (D:YYYYMMDDhhmmssZ)
-    //   (D:YYYYMMDDhhmmss+HH'mm)
-    //   (D:YYYYMMDDhhmmss-HH'mm)
-    //
-    int		i;			// Looping var
-    struct tm	dateval;		// Date value
-    int		offset;			// Date offset
-
-    for (i = 3; i < 17; i ++)
-    {
-      if (!isdigit(token[i] & 255))
-        break;
-    }
-
-    if (i >= 17)
-    {
-      if (token[i] == 'Z')
-      {
-        i ++;
-      }
-      else if (token[i] == '-' || token[i] == '+')
-      {
-        if (isdigit(token[i + 1] & 255) && isdigit(token[i + 2] & 255) && token[i + 3] == '\'' && isdigit(token[i + 4] & 255) && isdigit(token[i + 5] & 255))
-        {
-          i += 6;
-          if (token[i] == '\'')
-            i ++;
-	}
-      }
-    }
-
-    if (token[i])
-    {
-      // Just a string...
-      v->type         = PDFIO_VALTYPE_STRING;
-      v->value.string = pdfioStringCreate(pdf, token + 1);
-    }
-    else
-    {
-      // Date value...
-      memset(&dateval, 0, sizeof(dateval));
-
-      dateval.tm_year = (token[3] - '0') * 1000 + (token[4] - '0') * 100 + (token[5] - '0') * 10 + token[6] - '0' - 1900;
-      dateval.tm_mon  = (token[7] - '0') * 10 + token[8] - '0' - 1;
-      dateval.tm_mday = (token[9] - '0') * 10 + token[10] - '0';
-      dateval.tm_hour = (token[11] - '0') * 10 + token[12] - '0';
-      dateval.tm_min  = (token[13] - '0') * 10 + token[14] - '0';
-      dateval.tm_sec  = (token[15] - '0') * 10 + token[16] - '0';
-
-      if (token[17] == 'Z')
-      {
-        offset = 0;
-      }
-      else
-      {
-        offset = (token[18] - '0') * 600 + (token[19] - '0') * 60 + (token[20] - '0') * 10 + token[21] - '0';
-        if (token[17] == '-')
-          offset = -offset;
-      }
-
-      v->type       = PDFIO_VALTYPE_DATE;
-      v->value.date = mktime(&dateval) + offset;
-    }
   }
   else if (token[0] == '(')
   {
@@ -367,33 +406,6 @@ _pdfioValueRead(pdfio_file_t   *pdf,	// I - PDF file
 
       *dataptr++ = (unsigned char)d;
     }
-
-    if (obj && pdf->encryption)
-    {
-      // Decrypt the string...
-      _pdfio_crypto_ctx_t ctx;		// Decryption context
-      _pdfio_crypto_cb_t cb;		// Decryption callback
-      size_t	ivlen;			// Number of initialization vector bytes
-      uint8_t	temp[32768];		// Temporary buffer for decryption
-      size_t	templen;		// Number of actual data bytes
-
-      if (v->value.binary.datalen > (sizeof(temp) - 32))
-      {
-	_pdfioFileError(pdf, "Unable to read encrypted binary string - too long.");
-	return (false);
-      }
-
-      cb      = _pdfioCryptoMakeReader(pdf, obj, &ctx, v->value.binary.data, &ivlen);
-      templen = (cb)(&ctx, temp, v->value.binary.data + ivlen, v->value.binary.datalen - ivlen);
-
-      // Copy the decrypted string back to the value and adjust the length...
-      memcpy(v->value.binary.data, temp, templen);
-
-      if (pdf->encryption >= PDFIO_ENCRYPTION_AES_128)
-        v->value.binary.datalen = templen - temp[templen - 1];
-      else
-	v->value.binary.datalen = templen;
-    }
   }
   else if (strchr("0123456789-+.", token[0]) != NULL)
   {
@@ -488,7 +500,7 @@ _pdfioValueRead(pdfio_file_t   *pdf,	// I - PDF file
 
     // If we get here, we have a number...
     v->type         = PDFIO_VALTYPE_NUMBER;
-    v->value.number = (double)strtod(token, NULL);
+    v->value.number = _pdfio_strtod(pdf, token);
   }
   else if (!strcmp(token, "true") || !strcmp(token, "false"))
   {
@@ -729,3 +741,76 @@ _pdfioValueWrite(pdfio_file_t   *pdf,	// I - PDF file
 
   return (false);
 }
+
+
+//
+// 'get_date_time()' - Convert PDF date/time value to time_t.
+//
+
+static time_t				// O - Time in seconds
+get_date_time(const char *s)		// I - PDF date/time value
+{
+  int		i;			// Looping var
+  struct tm	dateval;		// Date value
+  int		offset;			// Date offset
+
+
+  // Possible date value of the form:
+  //
+  //   (D:YYYYMMDDhhmmssZ)
+  //   (D:YYYYMMDDhhmmss+HH'mm)
+  //   (D:YYYYMMDDhhmmss-HH'mm)
+  //
+
+  for (i = 2; i < 16; i ++)
+  {
+    if (!isdigit(s[i] & 255) || !s[i])
+      break;
+  }
+
+  if (i >= 16)
+  {
+    if (s[i] == 'Z')
+    {
+      i ++;
+    }
+    else if (s[i] == '-' || s[i] == '+')
+    {
+      if (isdigit(s[i + 1] & 255) && isdigit(s[i + 2] & 255) && s[i + 3] == '\'' && isdigit(s[i + 4] & 255) && isdigit(s[i + 5] & 255))
+      {
+	i += 6;
+	if (s[i] == '\'')
+	  i ++;
+      }
+    }
+  }
+
+  if (s[i])
+  {
+    // Just a string...
+    return (0);
+  }
+
+  // Date value...
+  memset(&dateval, 0, sizeof(dateval));
+
+  dateval.tm_year = (s[2] - '0') * 1000 + (s[3] - '0') * 100 + (s[4] - '0') * 10 + s[5] - '0' - 1900;
+  dateval.tm_mon  = (s[6] - '0') * 10 + s[7] - '0' - 1;
+  dateval.tm_mday = (s[8] - '0') * 10 + s[9] - '0';
+  dateval.tm_hour = (s[10] - '0') * 10 + s[11] - '0';
+  dateval.tm_min  = (s[12] - '0') * 10 + s[13] - '0';
+  dateval.tm_sec  = (s[14] - '0') * 10 + s[15] - '0';
+
+  if (s[16] == 'Z')
+  {
+    offset = 0;
+  }
+  else
+  {
+    offset = (s[17] - '0') * 600 + (s[18] - '0') * 60 + (s[19] - '0') * 10 + s[20] - '0';
+    if (s[16] == '-')
+      offset = -offset;
+  }
+
+  return (mktime(&dateval) + offset);
+}

pdfio.h

@@ -1,7 +1,7 @@
 //
 // Public header file for PDFio.
 //
-// Copyright © 2021-2022 by Michael R Sweet.
+// Copyright © 2021-2024 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		"1.3.1"
+
+
 //
 // Visibility and other annotations...
 //
@@ -37,9 +33,11 @@ extern "C" {
 #  if defined(__has_extension) || defined(__GNUC__)
 #    define _PDFIO_PUBLIC	__attribute__ ((visibility("default")))
 #    define _PDFIO_FORMAT(a,b)	__attribute__ ((__format__(__printf__, a,b)))
+#    define _PDFIO_DEPRECATED	__attribute__ ((deprecated)) _PDFIO_PUBLIC
 #  else
 #    define _PDFIO_PUBLIC
 #    define _PDFIO_FORMAT(a,b)
+#    define _PDFIO_DEPRECATED
 #  endif // __has_extension || __GNUC__
 
 
@@ -67,7 +65,7 @@ typedef enum pdfio_encryption_e		// PDF encryption modes
   PDFIO_ENCRYPTION_RC4_40,		// 40-bit RC4 encryption (PDF 1.3)
   PDFIO_ENCRYPTION_RC4_128,		// 128-bit RC4 encryption (PDF 1.4)
   PDFIO_ENCRYPTION_AES_128,		// 128-bit AES encryption (PDF 1.6)
-  PDFIO_ENCRYPTION_AES_256		// 256-bit AES encryption (PDF 2.0)
+  PDFIO_ENCRYPTION_AES_256		// 256-bit AES encryption (PDF 2.0) @exclude all@
 } pdfio_encryption_t;
 typedef enum pdfio_filter_e		// Compression/decompression filters for streams
 {
@@ -184,13 +182,17 @@ extern bool		pdfioDictSetStringf(pdfio_dict_t *dict, const char *key, const char
 extern bool		pdfioFileClose(pdfio_file_t *pdf) _PDFIO_PUBLIC;
 extern pdfio_file_t	*pdfioFileCreate(const char *filename, const char *version, pdfio_rect_t *media_box, pdfio_rect_t *crop_box, pdfio_error_cb_t error_cb, void *error_data) _PDFIO_PUBLIC;
 extern pdfio_obj_t	*pdfioFileCreateArrayObj(pdfio_file_t *pdf, pdfio_array_t *array) _PDFIO_PUBLIC;
+extern pdfio_obj_t	*pdfioFileCreateNameObj(pdfio_file_t *pdf, const char *name) _PDFIO_PUBLIC;
+extern pdfio_obj_t	*pdfioFileCreateNumberObj(pdfio_file_t *pdf, double number) _PDFIO_PUBLIC;
 extern pdfio_obj_t	*pdfioFileCreateObj(pdfio_file_t *pdf, pdfio_dict_t *dict) _PDFIO_PUBLIC;
 extern pdfio_file_t	*pdfioFileCreateOutput(pdfio_output_cb_t output_cb, void *output_ctx, const char *version, pdfio_rect_t *media_box, pdfio_rect_t *crop_box, pdfio_error_cb_t error_cb, void *error_data) _PDFIO_PUBLIC;
 // TODO: Add number, array, string, etc. versions of pdfioFileCreateObject?
 extern pdfio_stream_t	*pdfioFileCreatePage(pdfio_file_t *pdf, pdfio_dict_t *dict) _PDFIO_PUBLIC;
+extern pdfio_obj_t	*pdfioFileCreateStringObj(pdfio_file_t *pdf, const char *s) _PDFIO_PUBLIC;
 extern pdfio_file_t	*pdfioFileCreateTemporary(char *buffer, size_t bufsize, const char *version, pdfio_rect_t *media_box, pdfio_rect_t *crop_box, pdfio_error_cb_t error_cb, void *error_data) _PDFIO_PUBLIC;
 extern pdfio_obj_t	*pdfioFileFindObj(pdfio_file_t *pdf, size_t number) _PDFIO_PUBLIC;
 extern const char	*pdfioFileGetAuthor(pdfio_file_t *pdf) _PDFIO_PUBLIC;
+extern pdfio_dict_t	*pdfioFileGetCatalog(pdfio_file_t *pdf) _PDFIO_PUBLIC;
 extern time_t		pdfioFileGetCreationDate(pdfio_file_t *pdf) _PDFIO_PUBLIC;
 extern const char	*pdfioFileGetCreator(pdfio_file_t *pdf) _PDFIO_PUBLIC;
 extern pdfio_array_t	*pdfioFileGetID(pdfio_file_t *pdf) _PDFIO_PUBLIC;
@@ -221,6 +223,7 @@ extern pdfio_array_t	*pdfioObjGetArray(pdfio_obj_t *obj) _PDFIO_PUBLIC;
 extern pdfio_dict_t	*pdfioObjGetDict(pdfio_obj_t *obj) _PDFIO_PUBLIC;
 extern unsigned short	pdfioObjGetGeneration(pdfio_obj_t *obj) _PDFIO_PUBLIC;
 extern size_t		pdfioObjGetLength(pdfio_obj_t *obj) _PDFIO_PUBLIC;
+extern const char	*pdfioObjGetName(pdfio_obj_t *obj) _PDFIO_PUBLIC;
 extern size_t		pdfioObjGetNumber(pdfio_obj_t *obj) _PDFIO_PUBLIC;
 extern const char	*pdfioObjGetSubtype(pdfio_obj_t *obj) _PDFIO_PUBLIC;
 extern const char	*pdfioObjGetType(pdfio_obj_t *obj) _PDFIO_PUBLIC;
@@ -244,10 +247,6 @@ 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.pc.in

@@ -1,6 +1,13 @@
+prefix=@prefix@
+exec_prefix=@exec_prefix@
+libdir=@libdir@
+includedir=@includedir@
+
 Name: pdfio
 Description: PDF read/write library
+Version: @PDFIO_VERSION@
 URL: https://www.msweet.org/pdfio
-Requires: zlib >= 1.0
+Requires: @PKGCONFIG_REQUIRES@
-Libs: -L${prefix}/lib -lpdfio -lm
+Libs: @PKGCONFIG_LIBS@
-Cflags: -I${prefix}/include
+Libs.private: @PKGCONFIG_LIBS_PRIVATE@
+Cflags: @PKGCONFIG_CFLAGS@

pdfio.vcxproj

@@ -87,7 +87,7 @@
     <ClCompile>
       <WarningLevel>Level3</WarningLevel>
       <SDLCheck>true</SDLCheck>
-      <PreprocessorDefinitions>PDFIO_VERSION="1.1.0";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="1.1.0";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="1.1.0";_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="1.1.0";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;
+				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 = "";

pdfio1.def

@@ -1,7 +1,8 @@
 LIBRARY pdfio1
-VERSION 1.0
+VERSION 1.3
 EXPORTS
 _pdfioArrayDebug
+_pdfioArrayDecrypt
 _pdfioArrayDelete
 _pdfioArrayGetValue
 _pdfioArrayRead
@@ -24,6 +25,7 @@ _pdfioCryptoSHA256Init
 _pdfioCryptoUnlock
 _pdfioDictClear
 _pdfioDictDebug
+_pdfioDictDecrypt
 _pdfioDictDelete
 _pdfioDictGetValue
 _pdfioDictRead
@@ -47,7 +49,9 @@ _pdfioFileSeek
 _pdfioFileTell
 _pdfioFileWrite
 _pdfioObjDelete
+_pdfioObjGetExtension
 _pdfioObjLoad
+_pdfioObjSetExtension
 _pdfioStreamCreate
 _pdfioStreamOpen
 _pdfioStringIsAllocated
@@ -59,9 +63,12 @@ _pdfioTokenPush
 _pdfioTokenRead
 _pdfioValueCopy
 _pdfioValueDebug
+_pdfioValueDecrypt
 _pdfioValueDelete
 _pdfioValueRead
 _pdfioValueWrite
+_pdfio_strtod
+_pdfio_vsnprintf
 pdfioArrayAppendArray
 pdfioArrayAppendBinary
 pdfioArrayAppendBoolean
@@ -136,8 +143,12 @@ pdfioContentSetTextXScaling
 pdfioContentStroke
 pdfioContentTextBegin
 pdfioContentTextEnd
+pdfioContentTextMeasure
 pdfioContentTextMoveLine
 pdfioContentTextMoveTo
+pdfioContentTextNewLine
+pdfioContentTextNewLineShow
+pdfioContentTextNewLineShowf
 pdfioContentTextNextLine
 pdfioContentTextShow
 pdfioContentTextShowJustified
@@ -176,12 +187,15 @@ pdfioFileCreateFontObjFromFile
 pdfioFileCreateICCObjFromFile
 pdfioFileCreateImageObjFromData
 pdfioFileCreateImageObjFromFile
+pdfioFileCreateNumberObj
 pdfioFileCreateObj
 pdfioFileCreateOutput
 pdfioFileCreatePage
+pdfioFileCreateStringObj
 pdfioFileCreateTemporary
 pdfioFileFindObj
 pdfioFileGetAuthor
+pdfioFileGetCatalog
 pdfioFileGetCreationDate
 pdfioFileGetCreator
 pdfioFileGetID

pdfio_native.nuspec

@@ -3,7 +3,7 @@
     <metadata>
         <id>pdfio_native</id>
         <title>PDFio Library for VS2019+</title>
-        <version>1.1.0</version>
+        <version>1.3.2</version>
         <authors>Michael R Sweet</authors>
         <owners>michaelrsweet</owners>
         <projectUrl>https://github.com/michaelrsweet/pappl</projectUrl>
@@ -13,10 +13,10 @@
         <requireLicenseAcceptance>false</requireLicenseAcceptance>
         <description>PDFio Library for VS2019+</description>
         <summary>PDFio is a simple C library for reading and writing PDF files. 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>
+        <copyright>Copyright © 2019-2024 by Michael R Sweet</copyright>
         <tags>pdf file native</tags>
 	<dependencies>
-	    <dependency id="pdfio_native.redist" version="1.1.0" />
+	    <dependency id="pdfio_native.redist" version="1.3.2" />
 	    <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>1.1.0</version>
+        <version>1.3.2</version>
         <authors>Michael R Sweet</authors>
         <owners>michaelrsweet</owners>
         <projectUrl>https://github.com/michaelrsweet/pappl</projectUrl>
@@ -13,8 +13,11 @@
         <requireLicenseAcceptance>false</requireLicenseAcceptance>
         <description>PDFio Library for VS2019+</description>
         <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>
+        <copyright>Copyright © 2019-2024 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" />

runtests.bat

@@ -0,0 +1,16 @@
+:: Script to run unit test program
+::
+:: Usage:
+::
+::   .\runtests.bat x64\{Debug|Release}
+::
+
+:: Copy dependent DLLs to the named build directory
+echo Copying DLLs
+copy packages\zlib_native.redist.1.2.11\build\native\bin\x64\Debug\*.dll %1
+copy packages\zlib_native.redist.1.2.11\build\native\bin\x64\Release\*.dll %1
+
+:: Run unit test program
+echo Running %1\testpdfio.exe
+cd %1
+testpdfio.exe

testpdfio.c

@@ -1,7 +1,7 @@
 //
 // Test program for PDFio.
 //
-// Copyright © 2021 by Michael R Sweet.
+// Copyright © 2021-2024 by Michael R Sweet.
 //
 // Licensed under Apache License v2.0.  See the file "LICENSE" for more
 // information.
@@ -10,16 +10,13 @@
 //
 //   ./testpdfio
 //
-//   ./testpdfio FILENAME [OBJECT-NUMBER] [FILENAME [OBJECT-NUMBER]] ...
+//   ./testpdfio [--verbose] FILENAME [OBJECT-NUMBER] [FILENAME [OBJECT-NUMBER]] ...
-//
-
-//
-// Include necessary headers...
 //
 
 #include "pdfio-private.h"
 #include "pdfio-content.h"
 #include <math.h>
+#include <locale.h>
 #ifndef M_PI
 #  define M_PI	3.14159265358979323846264338327950288
 #endif // M_PI
@@ -30,7 +27,7 @@
 //
 
 static int	do_crypto_tests(void);
-static int	do_test_file(const char *filename, int objnum, bool verbose);
+static int	do_test_file(const char *filename, int objnum, const char *password, bool verbose);
 static int	do_unit_tests(void);
 static int	draw_image(pdfio_stream_t *st, const char *name, double x, double y, double w, double h, const char *label);
 static bool	error_cb(pdfio_file_t *pdf, const char *message, bool *error);
@@ -40,18 +37,19 @@ static const char *password_cb(void *data, const char *filename);
 static int	read_unit_file(const char *filename, size_t num_pages, size_t first_image, bool is_output);
 static ssize_t	token_consume_cb(const char **s, size_t bytes);
 static ssize_t	token_peek_cb(const char **s, char *buffer, size_t bytes);
+static int	usage(FILE *fp);
 static int	verify_image(pdfio_file_t *pdf, size_t number);
 static int	write_alpha_test(pdfio_file_t *pdf, int number, pdfio_obj_t *font);
 static int	write_color_patch(pdfio_stream_t *st, bool device);
 static int	write_color_test(pdfio_file_t *pdf, int number, pdfio_obj_t *font);
-static int	write_font_test(pdfio_file_t *pdf, int number, pdfio_obj_t *font, bool unicode);
+static int	write_font_test(pdfio_file_t *pdf, int number, pdfio_obj_t *font, const char *textfontfile, bool unicode);
 static int	write_header_footer(pdfio_stream_t *st, const char *title, int number);
 static pdfio_obj_t *write_image_object(pdfio_file_t *pdf, _pdfio_predictor_t predictor);
 static int	write_images_test(pdfio_file_t *pdf, int number, pdfio_obj_t *font);
 static int	write_jpeg_test(pdfio_file_t *pdf, const char *title, int number, pdfio_obj_t *font, pdfio_obj_t *image);
 static int	write_png_test(pdfio_file_t *pdf, int number, pdfio_obj_t *font);
 static int	write_text_test(pdfio_file_t *pdf, int first_page, pdfio_obj_t *font, const char *filename);
-static int	write_unit_file(pdfio_file_t *inpdf, pdfio_file_t *outpdf, size_t *num_pages, size_t *first_image);
+static int	write_unit_file(pdfio_file_t *inpdf, const char *outname, pdfio_file_t *outpdf, size_t *num_pages, size_t *first_image);
 
 
 //
@@ -62,20 +60,33 @@ int					// O - Exit status
 main(int  argc,				// I - Number of command-line arguments
      char *argv[])			// I - Command-line arguments
 {
-  int	ret = 0;			// Return value
+  int		ret = 0;		// Return value
 
 
   if (argc > 1)
   {
     int		i;			// Looping var
+    const char	*password = NULL;	// Password
     bool	verbose = false;	// Be verbose?
 
     for (i = 1; i < argc; i ++)
     {
       if (!strcmp(argv[i], "--help"))
       {
-        puts("Usage: ./testpdfio [--help] [--verbose] [filename [objnum] ...]");
+        return (usage(stdout));
-        return (0);
+      }
+      else if (!strcmp(argv[i], "--password"))
+      {
+        i ++;
+        if (i < argc)
+        {
+          password = argv[i];
+        }
+        else
+        {
+          fputs("testpdfio: Missing password after '--password'.\n", stderr);
+          return (usage(stderr));
+        }
       }
       else if (!strcmp(argv[i], "--verbose"))
       {
@@ -83,24 +94,27 @@ main(int  argc,				// I - Number of command-line arguments
       }
       else if (argv[i][0] == '-')
       {
-        printf("Unknown option '%s'.\n\n", argv[i]);
+        fprintf(stderr, "testpdfio: Unknown option '%s'.\n", argv[i]);
-        puts("Usage: ./testpdfio [--help] [--verbose] [filename [objnum] ...]");
+        return (usage(stderr));
-        return (1);
       }
       else if ((i + 1) < argc && isdigit(argv[i + 1][0] & 255))
       {
         // filename.pdf object-number
-        if (do_test_file(argv[i], atoi(argv[i + 1]), verbose))
+        if (do_test_file(argv[i], atoi(argv[i + 1]), password, verbose))
 	  ret = 1;
 
 	i ++;
       }
-      else if (do_test_file(argv[i], 0, verbose))
+      else if (do_test_file(argv[i], 0, password, verbose))
+      {
         ret = 1;
+      }
     }
   }
   else
   {
+    fprintf(stderr, "testpdfio: Test locale is \"%s\".\n", setlocale(LC_ALL, getenv("LANG")));
+
 #if _WIN32
     // Windows puts executables in Platform/Configuration subdirs...
     if (!_access("../../testfiles", 0))
@@ -364,6 +378,7 @@ do_crypto_tests(void)
 static int				// O - Exit status
 do_test_file(const char *filename,	// I - PDF filename
              int        objnum,		// I - Object number to dump, if any
+             const char *password,	// I - Password for file
              bool       verbose)	// I - Be verbose?
 {
   bool		error = false;		// Have we shown an error yet?
@@ -382,7 +397,7 @@ do_test_file(const char *filename,	// I - PDF filename
     fflush(stdout);
   }
 
-  if ((pdf = pdfioFileOpen(filename, /*password_cb*/NULL, /*password_data*/NULL, (pdfio_error_cb_t)error_cb, &error)) != NULL)
+  if ((pdf = pdfioFileOpen(filename, password_cb, (void *)password, (pdfio_error_cb_t)error_cb, &error)) != NULL)
   {
     if (objnum)
     {
@@ -406,7 +421,7 @@ do_test_file(const char *filename,	// I - PDF filename
 
       filter = pdfioDictGetName(dict, "Filter");
 
-      if ((st = pdfioObjOpenStream(obj, (filter && !strcmp(filter, "FlateDecode")) ? PDFIO_FILTER_FLATE : PDFIO_FILTER_NONE)) == NULL)
+      if ((st = pdfioObjOpenStream(obj, filter && !strcmp(filter, "FlateDecode"))) == NULL)
       {
         _pdfioValueDebug(&obj->value, stdout);
 	putchar('\n');
@@ -455,7 +470,7 @@ do_test_file(const char *filename,	// I - PDF filename
 	      }
 	    }
 
-	    printf("    Page #%d is %gx%g.\n", (int)n + 1, media_box.x2, media_box.y2);
+	    printf("    Page #%d (obj %d) is %gx%g.\n", (int)n + 1, (int)pdfioObjGetNumber(obj), media_box.x2, media_box.y2);
 	  }
 	}
 
@@ -1045,7 +1060,7 @@ do_unit_tests(void)
   else
     goto fail;
 
-  if (write_unit_file(inpdf, outpdf, &num_pages, &first_image))
+  if (write_unit_file(inpdf, "testpdfio-out.pdf", outpdf, &num_pages, &first_image))
     goto fail;
 
   if (read_unit_file("testpdfio-out.pdf", num_pages, first_image, false))
@@ -1064,7 +1079,7 @@ do_unit_tests(void)
   else
     goto fail;
 
-  if (write_unit_file(inpdf, outpdf, &num_pages, &first_image))
+  if (write_unit_file(inpdf, "testpdfio-out2.pdf", outpdf, &num_pages, &first_image))
     goto fail;
 
   close(outfd);
@@ -1085,7 +1100,7 @@ do_unit_tests(void)
   else
     return (1);
 
-  if (write_unit_file(inpdf, outpdf, &num_pages, &first_image))
+  if (write_unit_file(inpdf, "testpdfio-rc4.pdf", outpdf, &num_pages, &first_image))
     return (1);
 
   if (read_unit_file("testpdfio-rc4.pdf", num_pages, first_image, false))
@@ -1104,7 +1119,7 @@ do_unit_tests(void)
   else
     return (1);
 
-  if (write_unit_file(inpdf, outpdf, &num_pages, &first_image))
+  if (write_unit_file(inpdf, "testpdfio-rc4p.pdf", outpdf, &num_pages, &first_image))
     return (1);
 
   if (read_unit_file("testpdfio-rc4p.pdf", num_pages, first_image, false))
@@ -1122,7 +1137,7 @@ do_unit_tests(void)
   else
     return (1);
 
-  if (write_unit_file(inpdf, outpdf, &num_pages, &first_image))
+  if (write_unit_file(inpdf, "testpdfio-aes.pdf", outpdf, &num_pages, &first_image))
     return (1);
 
   if (read_unit_file("testpdfio-aes.pdf", num_pages, first_image, false))
@@ -1140,7 +1155,7 @@ do_unit_tests(void)
   else
     return (1);
 
-  if (write_unit_file(inpdf, outpdf, &num_pages, &first_image))
+  if (write_unit_file(inpdf, "testpdfio-aesp.pdf", outpdf, &num_pages, &first_image))
     return (1);
 
   if (read_unit_file("testpdfio-aesp.pdf", num_pages, first_image, false))
@@ -1152,7 +1167,7 @@ do_unit_tests(void)
   else
     return (1);
 
-  if (write_unit_file(inpdf, outpdf, &num_pages, &first_image))
+  if (write_unit_file(inpdf, "<temporary>", outpdf, &num_pages, &first_image))
     return (1);
 
   if (read_unit_file(temppdf, num_pages, first_image, false))
@@ -1309,6 +1324,7 @@ read_unit_file(const char *filename,	// I - File to read
 	       bool       is_output)	// I - File written with output callback?
 {
   pdfio_file_t	*pdf;			// PDF file
+  pdfio_dict_t	*catalog;		// Catalog dictionary
   size_t	i;			// Looping var
   const char	*s;			// String
   bool		error = false;		// Error callback data
@@ -1321,6 +1337,83 @@ read_unit_file(const char *filename,	// I - File to read
   else
     return (1);
 
+  // Get the root object/catalog dictionary
+  fputs("pdfioFileGetCatalog: ", stdout);
+  if ((catalog = pdfioFileGetCatalog(pdf)) != NULL)
+  {
+    puts("PASS");
+  }
+  else
+  {
+    puts("FAIL (got NULL, expected dictionary)");
+    return (1);
+  }
+
+  // Verify some catalog values...
+  fputs("pdfioDictGetName(PageLayout): ", stdout);
+  if ((s = pdfioDictGetName(catalog, "PageLayout")) != NULL && !strcmp(s, "SinglePage"))
+  {
+    puts("PASS");
+  }
+  else if (s)
+  {
+    printf("FAIL (got '%s', expected 'SinglePage')\n", s);
+    return (1);
+  }
+  else
+  {
+    puts("FAIL (got NULL, expected 'SinglePage')");
+    return (1);
+  }
+
+  fputs("pdfioDictGetName(PageLayout): ", stdout);
+  if ((s = pdfioDictGetName(catalog, "PageLayout")) != NULL && !strcmp(s, "SinglePage"))
+  {
+    puts("PASS");
+  }
+  else if (s)
+  {
+    printf("FAIL (got '%s', expected 'SinglePage')\n", s);
+    return (1);
+  }
+  else
+  {
+    puts("FAIL (got NULL, expected 'SinglePage')");
+    return (1);
+  }
+
+  fputs("pdfioDictGetName(PageMode): ", stdout);
+  if ((s = pdfioDictGetName(catalog, "PageMode")) != NULL && !strcmp(s, "UseThumbs"))
+  {
+    puts("PASS");
+  }
+  else if (s)
+  {
+    printf("FAIL (got '%s', expected 'UseThumbs')\n", s);
+    return (1);
+  }
+  else
+  {
+    puts("FAIL (got NULL, expected 'UseThumbs')");
+    return (1);
+  }
+
+  fputs("pdfioDictGetString(Lang): ", stdout);
+  if ((s = pdfioDictGetString(catalog, "Lang")) != NULL && !strcmp(s, "en"))
+  {
+    puts("PASS");
+  }
+  else if (s)
+  {
+    printf("FAIL (got '%s', expected 'en')\n", s);
+    return (1);
+  }
+  else
+  {
+    puts("FAIL (got NULL, expected 'en')");
+    return (1);
+  }
+
   // Verify metadata...
   fputs("pdfioFileGetAuthor: ", stdout);
   if ((s = pdfioFileGetAuthor(pdf)) != NULL && !strcmp(s, "Michael R Sweet"))
@@ -1482,6 +1575,23 @@ token_peek_cb(const char **s,		// IO - Test string
 }
 
 
+//
+// 'usage()' - Show program usage.
+//
+
+static int				// O - Exit status
+usage(FILE *fp)				// I - Output file
+{
+  fputs("Usage: ./testpdfio [OPTIONS] [FILENAME [OBJNUM]] ...\n", fp);
+  fputs("Options:\n", fp);
+  fputs("  --help               Show program help.\n", fp);
+  fputs("  --password PASSWORD  Set PDF password.\n", fp);
+  fputs("  --verbose            Be verbose.\n", fp);
+
+  return (fp != stdout);
+}
+
+
 //
 // 'verify_image()' - Verify an image object.
 //
@@ -2229,14 +2339,20 @@ write_color_test(pdfio_file_t *pdf,	// I - PDF file
 //
 
 static int				// O - 1 on failure, 0 on success
-write_font_test(pdfio_file_t *pdf,	// I - PDF file
+write_font_test(
-                int          number,	// I - Page number
+    pdfio_file_t *pdf,			// I - PDF file
-		pdfio_obj_t  *font,	// I - Page number font
+    int          number,		// I - Page number
-		bool         unicode)	// I - Use Unicode font?
+    pdfio_obj_t  *font,			// I - Page number font
+    const char   *textfontfile,		// I - Text font file
+    bool         unicode)		// I - Use Unicode font?
 {
   pdfio_dict_t		*dict;		// Page dictionary
   pdfio_stream_t	*st;		// Page contents stream
-  pdfio_obj_t		*opensans;	// OpenSans-Regular font
+  pdfio_obj_t		*textfont;	// Text font
+  char			title[256],	// Page title
+			textname[256],	// Name of text font
+			*ptr;		// Pointer into name
+  double		width;		// Text width
   int			i;		// Looping var
   static const char * const welcomes[] =// "Welcome" in many languages
   {
@@ -2387,28 +2503,16 @@ write_font_test(pdfio_file_t *pdf,	// I - PDF file
     "Märr-ŋamathirri",
     "Ẹ ku abọ",
     "Kíimak 'oolal",
-    "Ngiyakwemukela"
+    "Ngiyakwemukela",
+    "いらっしゃいませ"
   };
 
 
-#if 0
+  printf("pdfioFileCreateFontObjFromFile(%s): ", textfontfile);
-  if (unicode)
+  if ((textfont = pdfioFileCreateFontObjFromFile(pdf, textfontfile, unicode)) != NULL)
-  {
+    puts("PASS");
-    fputs("pdfioFileCreateFontObjFromFile(NotoSansJP-Regular.otf): ", stdout);
-    if ((opensans = pdfioFileCreateFontObjFromFile(pdf, "testfiles/NotoSansJP-Regular.otf", true)) != NULL)
-      puts("PASS");
-    else
-      return (1);
-  }
   else
-#endif // 0
+    return (1);
-  {
-    fputs("pdfioFileCreateFontObjFromFile(OpenSans-Regular.ttf): ", stdout);
-    if ((opensans = pdfioFileCreateFontObjFromFile(pdf, "testfiles/OpenSans-Regular.ttf", unicode)) != NULL)
-      puts("PASS");
-    else
-      return (1);
-  }
 
   fputs("pdfioDictCreate: ", stdout);
   if ((dict = pdfioDictCreate(pdf)) != NULL)
@@ -2423,7 +2527,7 @@ write_font_test(pdfio_file_t *pdf,	// I - PDF file
     return (1);
 
   fputs("pdfioPageDictAddFont(F2): ", stdout);
-  if (pdfioPageDictAddFont(dict, "F2", opensans))
+  if (pdfioPageDictAddFont(dict, "F2", textfont))
     puts("PASS");
   else
     return (1);
@@ -2435,7 +2539,21 @@ write_font_test(pdfio_file_t *pdf,	// I - PDF file
   else
     return (1);
 
-  if (write_header_footer(st, unicode ? "Unicode TrueType Font Test" : "CP1252 TrueType Font Test", number))
+  if ((ptr = strrchr(textfontfile, '/')) != NULL)
+    strncpy(textname, ptr + 1, sizeof(textname) - 1);
+  else
+    strncpy(textname, textfontfile, sizeof(textname) - 1);
+
+  textname[sizeof(textname) - 1] = '\0';
+  if ((ptr = strrchr(textname, '.')) != NULL)
+    *ptr = '\0';
+
+  if (unicode)
+    snprintf(title, sizeof(title), "Unicode %s Font Test", textname);
+  else
+    snprintf(title, sizeof(title), "CP1252 %s Font Test", textname);
+
+  if (write_header_footer(st, title, number))
     goto error;
 
   fputs("pdfioContentTextBegin(): ", stdout);
@@ -2456,8 +2574,8 @@ write_font_test(pdfio_file_t *pdf,	// I - PDF file
   else
     goto error;
 
-  fputs("pdfioContentTextMoveTo(36.0, 702.0): ", stdout);
+  fputs("pdfioContentTextMoveTo(198.0, 702.0): ", stdout);
-  if (pdfioContentTextMoveTo(st, 36.0, 702.0))
+  if (pdfioContentTextMoveTo(st, 198.0, 702.0))
     puts("PASS");
   else
     return (1);
@@ -2466,18 +2584,36 @@ write_font_test(pdfio_file_t *pdf,	// I - PDF file
   {
     if (i > 0 && (i % 50) == 0)
     {
-      fputs("pdfioContentTextMoveTo(200.0, 600.0): ", stdout);
+      fputs("pdfioContentTextMoveTo(162.0, 600.0): ", stdout);
-      if (pdfioContentTextMoveTo(st, 200.0, 600.0))
+      if (pdfioContentTextMoveTo(st, 162.0, 600.0))
 	puts("PASS");
       else
 	return (1);
     }
 
+    printf("pdfioContentTextMeasure(\"%s\"): ", welcomes[i]);
+    if ((width = pdfioContentTextMeasure(textfont, welcomes[i], 10.0)) >= 0.0)
+      puts("PASS");
+    else
+      return (1);
+
+    printf("pdfioContextTextMoveTo(%g, 0.0): ", -width);
+    if (pdfioContentTextMoveTo(st, -width, 0.0))
+      puts("PASS");
+    else
+      return (1);
+
     printf("pdfioContentTextShowf(\"%s\"): ", welcomes[i]);
     if (pdfioContentTextShowf(st, unicode, "%s\n", welcomes[i]))
       puts("PASS");
     else
       return (1);
+
+    printf("pdfioContextTextMoveTo(%g, 0.0): ", width);
+    if (pdfioContentTextMoveTo(st, width, 0.0))
+      puts("PASS");
+    else
+      return (1);
   }
 
   fputs("pdfioContentTextEnd(): ", stdout);
@@ -3221,6 +3357,7 @@ write_text_test(pdfio_file_t *pdf,		// I - PDF file
 static int				// O - Exit status
 write_unit_file(
     pdfio_file_t *inpdf,		// I - Input PDF file
+    const char   *outname,		// I - Output PDF file name
     pdfio_file_t *outpdf,		// I - Output PDF file
     size_t       *num_pages,		// O - Number of pages
     size_t       *first_image)		// O - First image object
@@ -3230,8 +3367,26 @@ write_unit_file(
 			*gray_jpg,	// gray.jpg image
 			*helvetica,	// Helvetica font
 			*page;		// Page from test PDF file
+  pdfio_dict_t		*catalog;	// Catalog dictionary
 
 
+  // Get the root object/catalog dictionary
+  fputs("pdfioFileGetCatalog: ", stdout);
+  if ((catalog = pdfioFileGetCatalog(outpdf)) != NULL)
+  {
+    puts("PASS");
+  }
+  else
+  {
+    puts("FAIL (got NULL, expected dictionary)");
+    return (1);
+  }
+
+  // Set some catalog values...
+  pdfioDictSetName(catalog, "PageLayout", "SinglePage");
+  pdfioDictSetName(catalog, "PageMode", "UseThumbs");
+  pdfioDictSetString(catalog, "Lang", "en");
+
   // Set info values...
   fputs("pdfioFileGet/SetAuthor: ", stdout);
   pdfioFileSetAuthor(outpdf, "Michael R Sweet");
@@ -3390,14 +3545,17 @@ write_unit_file(
     return (1);
 
   // Test TrueType fonts...
-  if (write_font_test(outpdf, 9, helvetica, false))
+  if (write_font_test(outpdf, 9, helvetica, "testfiles/OpenSans-Regular.ttf", false))
     return (1);
 
-  if (write_font_test(outpdf, 10, helvetica, true))
+  if (write_font_test(outpdf, 10, helvetica, "testfiles/OpenSans-Regular.ttf", true))
+    return (1);
+
+  if (write_font_test(outpdf, 11, helvetica, "testfiles/NotoSansJP-Regular.otf", true))
     return (1);
 
   // Print this text file...
-  if (write_text_test(outpdf, 11, helvetica, "README.md"))
+  if (write_text_test(outpdf, 12, helvetica, "README.md"))
     return (1);
 
   fputs("pdfioFileGetNumPages: ", stdout);
@@ -3412,7 +3570,7 @@ write_unit_file(
   }
 
   // Close the new PDF file...
-  fputs("pdfioFileClose(...): ", stdout);
+  printf("pdfioFileClose(\"%s\"): ", outname);
   if (pdfioFileClose(outpdf))
     puts("PASS");
   else

testttf.c

@@ -0,0 +1,305 @@
+//
+// Unit test program for TTF library
+//
+//     https://github.com/michaelrsweet/ttf
+//
+// Copyright © 2018-2024 by Michael R Sweet.
+//
+// Licensed under Apache License v2.0.  See the file "LICENSE" for more
+// information.
+//
+// Usage:
+//
+//   ./testttf [FILENAME]
+//
+
+#include <stdio.h>
+#include "ttf.h"
+
+
+//
+// Local functions...
+//
+
+static void	error_cb(void *data, const char *message);
+static int	test_font(const char *filename);
+
+
+//
+// 'main()' - Main entry for unit tests.
+//
+
+int					// O - Exit status
+main(int  argc,				// I - Number of command-line arguments
+     char *argv[])			// I - Command-line arguments
+{
+  int		i;			// Looping var
+  int		errors = 0;		// Number of errors
+
+
+  if (argc > 1)
+  {
+    for (i = 1; i < argc; i ++)
+      errors += test_font(argv[i]);
+  }
+  else
+  {
+    // Test with the bundled TrueType files...
+    errors += test_font("testfiles/OpenSans-Bold.ttf");
+    errors += test_font("testfiles/OpenSans-Regular.ttf");
+    errors += test_font("testfiles/NotoSansJP-Regular.otf");
+  }
+
+  if (!errors)
+    puts("\nALL TESTS PASSED");
+  else
+    printf("\n%d TEST(S) FAILED\n", errors);
+
+  return (errors);
+}
+
+
+//
+// 'error_cb()' - Error callback.
+//
+
+static void
+error_cb(void       *data,		// I - User data (not used)
+         const char *message)		// I - Message string
+{
+  fprintf(stderr, "FAIL (%s)\n", message);
+}
+
+
+//
+// 'test_font()' - Test a font file.
+//
+
+static int				// O - Number of errors
+test_font(const char *filename)		// I - Font filename
+{
+  int		i,			// Looping var
+		errors = 0;		// Number of errors
+  ttf_t		*font;			// Font
+  const char	*value;			// Font (string) value
+  int		intvalue;		// Font (integer) value
+  float		realvalue;		// Font (real) value
+  ttf_rect_t	bounds;			// Bounds
+  ttf_rect_t	extents;		// Extents
+  size_t	num_fonts;		// Number of fonts
+  ttf_style_t	style;			// Font style
+  ttf_weight_t	weight;			// Font weight
+  static const char * const stretches[] =
+  {					// Font stretch strings
+    "TTF_STRETCH_NORMAL",		// normal
+    "TTF_STRETCH_ULTRA_CONDENSED",	// ultra-condensed
+    "TTF_STRETCH_EXTRA_CONDENSED",	// extra-condensed
+    "TTF_STRETCH_CONDENSED",		// condensed
+    "TTF_STRETCH_SEMI_CONDENSED",	// semi-condensed
+    "TTF_STRETCH_SEMI_EXPANDED",	// semi-expanded
+    "TTF_STRETCH_EXPANDED",		// expanded
+    "TTF_STRETCH_EXTRA_EXPANDED",	// extra-expanded
+    "TTF_STRETCH_ULTRA_EXPANDED"	// ultra-expanded
+  };
+  static const char * const strings[] =	// Test strings
+  {
+    "Hello, World!",			// English
+    "مرحبا بالعالم!",			// Arabic
+    "Bonjour le monde!",		// French
+    "Γειά σου Κόσμε!",			// Greek
+    "שלום עולם!",			// Hebrew
+    "Привет мир!",			// Russian
+    "こんにちは世界！"			// Japanese
+  };
+  static const char * const styles[] =	// Font style names
+  {
+    "TTF_STYLE_NORMAL",
+    "TTF_STYLE_ITALIC",
+    "TTF_STYLE_OBLIQUE"
+  };
+
+
+  printf("ttfCreate(\"%s\"): ", filename);
+  fflush(stdout);
+  if ((font = ttfCreate(filename, 0, error_cb, NULL)) != NULL)
+    puts("PASS");
+  else
+    errors ++;
+
+  fputs("ttfGetAscent: ", stdout);
+  if ((intvalue = ttfGetAscent(font)) > 0)
+  {
+    printf("PASS (%d)\n", intvalue);
+  }
+  else
+  {
+    printf("FAIL (%d)\n", intvalue);
+    errors ++;
+  }
+
+  fputs("ttfGetBounds: ", stdout);
+  if (ttfGetBounds(font, &bounds))
+  {
+    printf("PASS (%g %g %g %g)\n", bounds.left, bounds.bottom, bounds.right, bounds.top);
+  }
+  else
+  {
+    puts("FAIL");
+    errors ++;
+  }
+
+  fputs("ttfGetCapHeight: ", stdout);
+  if ((intvalue = ttfGetCapHeight(font)) > 0)
+  {
+    printf("PASS (%d)\n", intvalue);
+  }
+  else
+  {
+    printf("FAIL (%d)\n", intvalue);
+    errors ++;
+  }
+
+  fputs("ttfGetCopyright: ", stdout);
+  if ((value = ttfGetCopyright(font)) != NULL)
+  {
+    printf("PASS (%s)\n", value);
+  }
+  else
+  {
+    puts("WARNING (no copyright found)");
+  }
+
+  for (i = 0; i < (int)(sizeof(strings) / sizeof(strings[0])); i ++)
+  {
+    printf("ttfGetExtents(\"%s\"): ", strings[i]);
+    if (ttfGetExtents(font, 12.0f, strings[i], &extents))
+    {
+      printf("PASS (%.1f %.1f %.1f %.1f)\n", extents.left, extents.bottom, extents.right, extents.top);
+    }
+    else
+    {
+      puts("FAIL");
+      errors ++;
+    }
+  }
+
+  fputs("ttfGetFamily: ", stdout);
+  if ((value = ttfGetFamily(font)) != NULL)
+  {
+    printf("PASS (%s)\n", value);
+  }
+  else
+  {
+    puts("FAIL");
+    errors ++;
+  }
+
+  fputs("ttfGetItalicAngle: ", stdout);
+  if ((realvalue = ttfGetItalicAngle(font)) >= -180.0 && realvalue <= 180.0)
+  {
+    printf("PASS (%g)\n", realvalue);
+  }
+  else
+  {
+    printf("FAIL (%g)\n", realvalue);
+    errors ++;
+  }
+
+  fputs("ttfGetNumFonts: ", stdout);
+  if ((num_fonts = ttfGetNumFonts(font)) > 0)
+  {
+    printf("PASS (%u)\n", (unsigned)num_fonts);
+  }
+  else
+  {
+    puts("FAIL");
+    errors ++;
+  }
+
+  fputs("ttfGetPostScriptName: ", stdout);
+  if ((value = ttfGetPostScriptName(font)) != NULL)
+  {
+    printf("PASS (%s)\n", value);
+  }
+  else
+  {
+    puts("FAIL");
+    errors ++;
+  }
+
+  fputs("ttfGetStretch: ", stdout);
+  if ((intvalue = (int)ttfGetStretch(font)) >= TTF_STRETCH_NORMAL && intvalue <= TTF_STRETCH_ULTRA_EXPANDED)
+  {
+    printf("PASS (%s)\n", stretches[intvalue]);
+  }
+  else
+  {
+    printf("FAIL (%d)\n", intvalue);
+    errors ++;
+  }
+
+  fputs("ttfGetStyle: ", stdout);
+  if ((style = ttfGetStyle(font)) >= TTF_STYLE_NORMAL && style <= TTF_STYLE_ITALIC)
+  {
+    printf("PASS (%s)\n", styles[style]);
+  }
+  else
+  {
+    puts("FAIL");
+    errors ++;
+  }
+
+  fputs("ttfGetVersion: ", stdout);
+  if ((value = ttfGetVersion(font)) != NULL)
+  {
+    printf("PASS (%s)\n", value);
+  }
+  else
+  {
+    puts("FAIL");
+    errors ++;
+  }
+
+  fputs("ttfGetWeight: ", stdout);
+  if ((weight = ttfGetWeight(font)) >= 0)
+  {
+    printf("PASS (%u)\n", (unsigned)weight);
+  }
+  else
+  {
+    puts("FAIL");
+    errors ++;
+  }
+
+  fputs("ttfGetWidth(' '): ", stdout);
+  if ((intvalue = ttfGetWidth(font, ' ')) > 0)
+  {
+    printf("PASS (%d)\n", intvalue);
+  }
+  else
+  {
+    printf("FAIL (%d)\n", intvalue);
+    errors ++;
+  }
+
+  fputs("ttfGetXHeight: ", stdout);
+  if ((intvalue = ttfGetXHeight(font)) > 0)
+  {
+    printf("PASS (%d)\n", intvalue);
+  }
+  else
+  {
+    printf("FAIL (%d)\n", intvalue);
+    errors ++;
+  }
+
+  fputs("ttfIsFixedPitch: ", stdout);
+  if (ttfIsFixedPitch(font))
+    puts("PASS (true)");
+  else
+    puts("PASS (false)");
+
+  ttfDelete(font);
+
+  return (errors);
+}

ttf.c

@@ -3,16 +3,12 @@
 //
 //     https://github.com/michaelrsweet/ttf
 //
-// Copyright © 2018-2021 by Michael R Sweet.
+// Copyright © 2018-2024 by Michael R Sweet.
 //
 // Licensed under Apache License v2.0.  See the file "LICENSE" for more
 // information.
 //
 
-//
-// Include necessary headers...
-//
-
 #ifdef _WIN32
 #  define _CRT_SECURE_NO_WARNINGS
 #endif // _WIN32
@@ -66,7 +62,7 @@
 #  define O_CREAT	_O_CREAT
 #  define O_TRUNC	_O_TRUNC
 
-typedef __int64 ssize_t;		// POSIX type not present on Windows...
+typedef __int64 ssize_t;		// POSIX type not present on Windows... @private@
 
 #else
 #  include <unistd.h>
@@ -75,7 +71,7 @@ typedef __int64 ssize_t;		// POSIX type not present on Windows...
 
 
 //
-// DEBUG is typically defined for debug builds.  TTF_DEBUG maps to printf when
+// DEBUG is typically defined for debug builds.  TTF_DEBUG maps to fprintf when
 // DEBUG is defined and is a no-op otherwise...
 //
 
@@ -103,6 +99,8 @@ typedef __int64 ssize_t;		// POSIX type not present on Windows...
 //
 
 #define TTF_FONT_MAX_CHAR	262144	// Maximum number of character values
+#define TTF_FONT_MAX_GROUPS	65536	// Maximum number of sub-groups
+#define TTF_FONT_MAX_NAMES	16777216// Maximum size of names table we support
 
 
 //
@@ -258,7 +256,7 @@ typedef struct _ttf_off_hhea_s		// Horizontal header
 {
   short		ascender,		// Ascender
 		descender;		// Descender
-  int		numberOfHMetrics;	// Number of horizontal metrics
+  unsigned short numberOfHMetrics;	// Number of horizontal metrics
 } _ttf_off_hhea_t;
 
 typedef struct _ttf_off_os_2_s		// OS/2 information
@@ -301,7 +299,28 @@ static unsigned	seek_table(ttf_t *font, unsigned tag, unsigned offset, bool requ
 
 
 //
-// 'ttfCreate()' - Create a new font object for the named font family.
+// 'ttfCreate()' - Create a new font object for the named font file.
+//
+// This function creates a new font object for the named TrueType or OpenType
+// font file or collection.  The "filename" argument specifies the name of the
+// file to read.
+//
+// The "idx" argument specifies the font to load from a collection - the first
+// font is number `0`.  Once created, you can call the @link ttfGetNumFonts@
+// function to determine whether the loaded font file is a collection with more
+// than one font.
+//
+// The "err_cb" and "err_data" arguments specify a callback function and data
+// pointer for receiving error messages.  If `NULL`, errors are sent to the
+// `stderr` file.  The callback function receives the data pointer and a text
+// message string, for example:
+//
+// ```
+// void my_err_cb(void *err_data, const char *message)
+// {
+//   fprintf(stderr, "ERROR: %s\n", message);
+// }
+// ```
 //
 
 ttf_t *					// O - New font object
@@ -452,7 +471,7 @@ ttfCreate(const char   *filename,	// I - Filename
     font->cap_height = font->ascent;
 
   if (font->x_height == 0)
-    font->x_height   = 3 * font->ascent / 5;
+    font->x_height = 3 * font->ascent / 5;
 
   // Build a sparse glyph widths table...
   font->min_char = -1;
@@ -481,6 +500,11 @@ ttfCreate(const char   *filename,	// I - Filename
       else
 	font->widths[bin][i & 255] = widths[glyph];
     }
+
+#ifdef DEBUG
+    if (i >= ' ' && i < 127 && font->widths[0])
+      TTF_DEBUG("ttfCreate: width['%c']=%d(%d)\n", (char)i, font->widths[0][i].width, font->widths[0][i].left_bearing);
+#endif // DEBUG
   }
 
   // Cleanup and return the font...
@@ -549,6 +573,10 @@ ttfGetAscent(ttf_t *font)		// I - Font
 //
 // 'ttfGetBounds()' - Get the bounds of all characters in a font.
 //
+// This function gets the bounds of all characters in a font.  The "bounds"
+// argument is a pointer to a `ttf_rect_t` structure that will be filled with
+// the limits for characters in the font scaled to a 1000x1000 unit square.
+//
 
 ttf_rect_t *				// O - Bounds or `NULL` on error
 ttfGetBounds(ttf_t      *font,		// I - Font
@@ -630,8 +658,11 @@ ttfGetDescent(ttf_t *font)		// I - Font
 //
 // 'ttfGetExtents()' - Get the extents of a UTF-8 string.
 //
-// This function computes the extents of a UTF-8 string when rendered using the
+// This function computes the extents of the UTF-8 string "s" when rendered
-// specified font and size.
+// using the specified font "font" and size "size".  The "extents" argument is
+// a pointer to a `ttf_rect_t` structure that is filled with the extents of a
+// simple rendering of the string with no kerning or rewriting applied.  The
+// values are scaled using the specified font size.
 //
 
 ttf_rect_t *				// O - Pointer to extents or `NULL` on error
@@ -737,17 +768,6 @@ ttfGetFamily(ttf_t *font)		// I - Font
 }
 
 
-//
-// 'ttfIsFixedPitch()' - Determine whether a font is fixedpitch.
-//
-
-bool					// O - `true` if fixed pitch, `false` otherwise
-ttfIsFixedPitch(ttf_t *font)		// I - Font
-{
-  return (font ? font->is_fixed : false);
-}
-
-
 //
 // 'ttfGetItalicAngle()' - Get the italic angle.
 //
@@ -856,13 +876,14 @@ int					// O - Width in 1000ths
 ttfGetWidth(ttf_t *font,		// I - Font
             int   ch)			// I - Unicode character
 {
-  int	bin = ch >> 8;			// Bin in widths array
+  int	bin =  ch >> 8;			// Bin in widths array
 
 
   // Range check input...
   if (!font || ch < ' ' || ch == 0x7f)
     return (0);
-  else if (font->widths[bin])
+
+  if (font->widths[bin])
     return ((int)(1000.0f * font->widths[bin][ch & 255].width / font->units));
   else if (font->widths[0])		// .notdef
     return ((int)(1000.0f * font->widths[0][0].width / font->units));
@@ -882,6 +903,17 @@ ttfGetXHeight(ttf_t *font)		// I - Font
 }
 
 
+//
+// 'ttfIsFixedPitch()' - Determine whether a font is fixedpitch.
+//
+
+bool					// O - `true` if fixed pitch, `false` otherwise
+ttfIsFixedPitch(ttf_t *font)		// I - Font
+{
+  return (font ? font->is_fixed : false);
+}
+
+
 //
 // 'copy_name()' - Copy a name string from a font.
 //
@@ -1270,20 +1302,38 @@ read_cmap(ttf_t *font)			// I - Font
           for (i = 0; i < numGlyphIdArray; i ++)
             glyphIdArray[i] = read_ushort(font);
 
-#ifdef DEBUG
+          for (i = 0, segment = segments; i < segCount; i ++, segment ++)
-          for (i = 0; i < segCount; i ++)
+          {
-            TTF_DEBUG("read_cmap: segment[%d].startCode=%d, endCode=%d, idDelta=%d, idRangeOffset=%d\n", i, segments[i].startCode, segments[i].endCode, segments[i].idDelta, segments[i].idRangeOffset);
+            TTF_DEBUG("read_cmap: segment[%d].startCode=%d, endCode=%d, idDelta=%d, idRangeOffset=%d\n", i, segment->startCode, segment->endCode, segment->idDelta, segment->idRangeOffset);
 
+            if (segment->startCode > segment->endCode)
+            {
+	      errorf(font, "Bad cmap table segment %u to %u.", segments->startCode, segment->endCode);
+	      free(segments);
+	      free(glyphIdArray);
+	      return (false);
+            }
+
+            // Based on the end code of the segment table, allocate space for the
+            // uncompressed cmap table...
+            if (segment->endCode >= font->num_cmap)
+	      font->num_cmap = segment->endCode + 1;
+          }
+
+#ifdef DEBUG
           for (i = 0; i < numGlyphIdArray; i ++)
             TTF_DEBUG("read_cmap: glyphIdArray[%d]=%d\n", i, glyphIdArray[i]);
 #endif /* DEBUG */
 
-          // Based on the end code of the segent table, allocate space for the
+	  if (font->num_cmap == 0 || font->num_cmap > TTF_FONT_MAX_CHAR)
-          // uncompressed cmap table...
+	  {
-          segCount --;			// Last segment is not used (sigh)
+	    errorf(font, "Invalid cmap table with %u characters.", (unsigned)font->num_cmap);
+	    free(segments);
+	    free(glyphIdArray);
+	    return (false);
+	  }
 
-	  font->num_cmap = segments[segCount - 1].endCode + 1;
+	  font->cmap = cmapptr = (int *)malloc(font->num_cmap * sizeof(int));
-	  font->cmap     = cmapptr = (int *)malloc(font->num_cmap * sizeof(int));
 
 	  if (!font->cmap)
           {
@@ -1305,17 +1355,18 @@ read_cmap(ttf_t *font)			// I - Font
               {
                 // Use an "obscure indexing trick" (words from the spec, not
                 // mine) to look up the glyph index...
-                temp = segment->idRangeOffset / 2 + ch - segment->startCode + seg - segCount - 1;
+                temp = (int)(segment->idRangeOffset / 2 - segCount + (ch - segment->startCode) + (segment - segments));
 
-                if (temp < 0 || temp >= numGlyphIdArray || !glyphIdArray[temp])
+                TTF_DEBUG("read_cmap: ch=%d, temp=%d\n", ch, temp);
+                if (temp < 0 || temp >= numGlyphIdArray)
                   glyph = -1;
 		else
-		  glyph = ((glyphIdArray[temp] + segment->idDelta) & 65535) - 1;
+		  glyph = (glyphIdArray[temp] + segment->idDelta) & 65535;
               }
               else
               {
                 // Just use idDelta to compute a glyph index...
-                glyph = ((ch + segment->idDelta) & 65535) - 1;
+                glyph = (ch + segment->idDelta) & 65535;
 	      }
 
 	      cmapptr[ch] = glyph;
@@ -1353,6 +1404,12 @@ read_cmap(ttf_t *font)			// I - Font
 
 	  TTF_DEBUG("read_cmap: nGroups=%u\n", nGroups);
 
+	  if (nGroups > TTF_FONT_MAX_GROUPS)
+	  {
+	    errorf(font, "Invalid cmap table with %u groups.", nGroups);
+	    return (false);
+	  }
+
 	  if ((groups = (_ttf_off_cmap12_t *)calloc(nGroups, sizeof(_ttf_off_cmap12_t))) == NULL)
           {
             errorf(font, "Unable to allocate memory for cmap.");
@@ -1366,6 +1423,13 @@ read_cmap(ttf_t *font)			// I - Font
 	    group->startGlyphID  = read_ulong(font);
 	    TTF_DEBUG("read_cmap: [%u] startCharCode=%u, endCharCode=%u, startGlyphID=%u\n", gidx, group->startCharCode, group->endCharCode, group->startGlyphID);
 
+            if (group->startCharCode > group->endCharCode)
+            {
+	      errorf(font, "Bad cmap table segment %u to %u.", group->startCharCode, group->endCharCode);
+	      free(groups);
+	      return (false);
+            }
+
             if (group->endCharCode >= font->num_cmap)
               font->num_cmap = group->endCharCode + 1;
 	  }
@@ -1373,6 +1437,14 @@ read_cmap(ttf_t *font)			// I - Font
 	  // Based on the end code of the segent table, allocate space for the
 	  // uncompressed cmap table...
           TTF_DEBUG("read_cmap: num_cmap=%u\n", (unsigned)font->num_cmap);
+
+	  if (font->num_cmap == 0 || font->num_cmap > TTF_FONT_MAX_CHAR)
+	  {
+	    errorf(font, "Invalid cmap table with %u characters.", (unsigned)font->num_cmap);
+	    free(groups);
+	    return (false);
+	  }
+
 	  font->cmap = cmapptr = (int *)malloc(font->num_cmap * sizeof(int));
 
 	  if (!font->cmap)
@@ -1423,6 +1495,12 @@ read_cmap(ttf_t *font)			// I - Font
 
 	  TTF_DEBUG("read_cmap: nGroups=%u\n", nGroups);
 
+	  if (nGroups > TTF_FONT_MAX_GROUPS)
+	  {
+	    errorf(font, "Invalid cmap table with %u groups.", nGroups);
+	    return (false);
+	  }
+
 	  if ((groups = (_ttf_off_cmap13_t *)calloc(nGroups, sizeof(_ttf_off_cmap13_t))) == NULL)
 	  {
 	    errorf(font, "Unable to allocate memory for cmap.");
@@ -1436,6 +1514,13 @@ read_cmap(ttf_t *font)			// I - Font
 	    group->glyphID       = read_ulong(font);
 	    TTF_DEBUG("read_cmap: [%u] startCharCode=%u, endCharCode=%u, glyphID=%u\n", gidx, group->startCharCode, group->endCharCode, group->glyphID);
 
+            if (group->startCharCode > group->endCharCode)
+            {
+	      errorf(font, "Bad cmap table segment %u to %u.", group->startCharCode, group->endCharCode);
+	      free(groups);
+	      return (false);
+            }
+
             if (group->endCharCode >= font->num_cmap)
               font->num_cmap = group->endCharCode + 1;
 	  }
@@ -1443,6 +1528,14 @@ read_cmap(ttf_t *font)			// I - Font
 	  // Based on the end code of the segent table, allocate space for the
 	  // uncompressed cmap table...
           TTF_DEBUG("read_cmap: num_cmap=%u\n", (unsigned)font->num_cmap);
+
+	  if (font->num_cmap == 0 || font->num_cmap > TTF_FONT_MAX_CHAR)
+	  {
+	    errorf(font, "Invalid cmap table with %u characters.", (unsigned)font->num_cmap);
+	    free(groups);
+	    return (false);
+	  }
+
 	  font->cmap = cmapptr = (int *)malloc(font->num_cmap * sizeof(int));
 
 	  if (!font->cmap)
@@ -1562,7 +1655,7 @@ read_hmtx(ttf_t           *font,	// I - Font
           _ttf_off_hhea_t *hhea)	// O - hhea table data
 {
   unsigned	length;			// Length of hmtx table
-  int		i;			// Looping var
+  unsigned	i;			// Looping var
   _ttf_metric_t	*widths;		// Glyph metrics array
 
 
@@ -1582,6 +1675,8 @@ read_hmtx(ttf_t           *font,	// I - Font
   {
     widths[i].width        = (short)read_ushort(font);
     widths[i].left_bearing = (short)read_short(font);
+
+    TTF_DEBUG("read_hmtx: widths[%d].width=%d, .left_bearing=%d\n", i, widths[i].width, widths[i].left_bearing);
   }
 
   return (widths);
@@ -1639,8 +1734,15 @@ read_names(ttf_t *font)			// I - Font
     return (false);
 
   font->names.storage_size = length - (unsigned)offset;
+  if (font->names.storage_size > TTF_FONT_MAX_NAMES)
+  {
+    errorf(font, "Name table too large - %u bytes.", (unsigned)font->names.storage_size);
+    return (false);
+  }
+
   if ((font->names.storage = malloc(font->names.storage_size)) == NULL)
     return (false);
+
   memset(font->names.storage, 'A', font->names.storage_size);
 
   for (i = font->names.num_names, name = font->names.names; i > 0; i --, name ++)

ttf.h

@@ -3,7 +3,7 @@
 //
 //     https://github.com/michaelrsweet/ttf
 //
-// Copyright © 2018-2021 by Michael R Sweet.
+// Copyright © 2018-2024 by Michael R Sweet.
 //
 // Licensed under Apache License v2.0.  See the file "LICENSE" for more
 // information.
@@ -11,29 +11,23 @@
 
 #ifndef TTF_H
 #  define TTF_H
-
-//
-// Include necessary headers...
-//
-
 #  include <stdbool.h>
 #  include <sys/types.h>
-
 #  ifdef __cplusplus
 extern "C" {
-#  endif //
+#  endif // __cplusplus
 
 
 //
 // Types...
 //
 
-typedef struct _ttf_s ttf_t;	//// Font object
+typedef struct _ttf_s ttf_t;	// Font object
 
 typedef void (*ttf_err_cb_t)(void *data, const char *message);
-				//// Font error callback
+				// Font error callback
 
-typedef enum ttf_stretch_e	//// Font stretch
+typedef enum ttf_stretch_e	// Font stretch
 {
   TTF_STRETCH_NORMAL,		// normal
   TTF_STRETCH_ULTRA_CONDENSED,	// ultra-condensed
@@ -46,20 +40,20 @@ typedef enum ttf_stretch_e	//// Font stretch
   TTF_STRETCH_ULTRA_EXPANDED	// ultra-expanded
 } ttf_stretch_t;
 
-typedef enum ttf_style_e	//// Font style
+typedef enum ttf_style_e	// Font style
 {
   TTF_STYLE_NORMAL,		// Normal font
   TTF_STYLE_ITALIC,		// Italic font
   TTF_STYLE_OBLIQUE		// Oblique (angled) font
 } ttf_style_t;
 
-typedef enum ttf_variant_e	//// Font variant
+typedef enum ttf_variant_e	// Font variant
 {
   TTF_VARIANT_NORMAL,		// Normal font
   TTF_VARIANT_SMALL_CAPS	// Font whose lowercase letters are small capitals
 } ttf_variant_t;
 
-typedef enum ttf_weight_e	//// Font weight
+typedef enum ttf_weight_e	// Font weight
 {
   TTF_WEIGHT_100 = 100,		// Weight 100 (Thin)
   TTF_WEIGHT_200 = 200,		// Weight 200 (Extra/Ultra-Light)
@@ -72,7 +66,7 @@ typedef enum ttf_weight_e	//// Font weight
   TTF_WEIGHT_900 = 900		// Weight 900 (Black/Heavy)
 } ttf_weight_t;
 
-typedef struct ttf_rect_s	//// Bounding rectangle
+typedef struct ttf_rect_s	// Bounding rectangle
 {
   float	left;			// Left offset
   float	top;			// Top offset
@@ -89,8 +83,8 @@ extern ttf_t		*ttfCreate(const char *filename, size_t idx, ttf_err_cb_t err_cb,
 extern void		ttfDelete(ttf_t *font);
 extern int		ttfGetAscent(ttf_t *font);
 extern ttf_rect_t	*ttfGetBounds(ttf_t *font, ttf_rect_t *bounds);
-extern int		ttfGetCapHeight(ttf_t *font);
 extern const int	*ttfGetCMap(ttf_t *font, size_t *num_cmap);
+extern int		ttfGetCapHeight(ttf_t *font);
 extern const char	*ttfGetCopyright(ttf_t *font);
 extern int		ttfGetDescent(ttf_t *font);
 extern ttf_rect_t	*ttfGetExtents(ttf_t *font, float size, const char *s, ttf_rect_t *extents);
@@ -112,5 +106,4 @@ extern bool		ttfIsFixedPitch(ttf_t *font);
 #  ifdef __cplusplus
 }
 #  endif // __cplusplus
-
 #endif // !TTF_H