SCP: PCRE2 support.

Add PCRE2 support as an alternative to the original PCRE. PCRE2 is
actively maintained and has a cleaner API than its predecessor.

- Use a function interface around regular expressions to isolate and
  reduce the preprocessor #if/#endif forest. Abide by a single function
  declaration/implementation approach, vs. multiple function
  implentations within an #if/#endif forest.

- Clean up the code so that work isn't recreated or duplicated, such as
  compiling regexps.

Platform notes:

- cmake: PCRE2 is the default RegEx support. To revert to PCRE, add
  "-DPREFER_PCRE" to the cmake configuration command line.

- makefile: PCRE remains the default RegEx support out of respect for
  tradition (cue Chaim Topol singing "Tradition".) Enable PCRE2 by
  defining "USE_PCRE2=<some value>" from the make command line or shell
  environment.

- Visual Studio Projects: Untouched. Externally built libraries provide
  regular expression support residing in a specific place in the file
  system, which is outside the control of SIMH proper.

sim_defs.h:

- Change EXPECT::size from int32 to size_t for increased
  cross-platform/64-bit compatibility (i.e., array indices and offsets
  should be size_t, where practicable.)

- Add typedefs for EXPECT regex support independence: sim_regex_t,
  sim_re_capture_t.

- Add regular expression context to EXPTAB that maintains state when
  processing the captured matches, making the function interface clean.
  Tracks intermediate state while processing captured matches.

Author: bscottm

.travis/deps.sh

@@ -27,6 +27,7 @@ install_linux() {
     sudo apt-get install -ym libegl1-mesa-dev libgles2-mesa-dev
     sudo apt-get install -ym libsdl2-dev libfreetype6-dev libsdl2-ttf-dev
     sudo apt-get install -ym libpcap-dev libvdeplug-dev
+    sudo apt-get install -ym libpcre2-dev libpcre2-8-0
     sudo apt-get install -ym cmake cmake-data
 }
 
@@ -37,6 +38,7 @@ install_mingw64() {
         mingw-w64-x86_64-gcc \
 	mingw-w64-x86_64-make \
         mingw-w64-x86_64-pcre \
+        mingw-w64-x86_64-pcre2 \
 	mingw-w64-x86_64-freetype \
         mingw-w64-x86_64-SDL2 \
 	mingw-w64-x86_64-SDL2_ttf \
@@ -50,6 +52,7 @@ install_ucrt64() {
         mingw-w64-ucrt-x86_64-gcc \
 	mingw-w64-ucrt-x86_64-make \
         mingw-w64-ucrt-x86_64-pcre \
+        mingw-w64-ucrt-x86_64-pcre2 \
 	mingw-w64-ucrt-x86_64-freetype \
         mingw-w64-ucrt-x86_64-SDL2 \
 	mingw-w64-ucrt-x86_64-SDL2_ttf \

CMakeLists.txt

@@ -183,7 +183,7 @@ option(WITH_REGEX
        TRUE)
 option(PREFER_PCRE
        "Prefer (=1)/ignore (=0) Prefer PCRE over PCRE2 (def: ignore)"
-       TRUE)
+       FALSE)
 option(WITH_NETWORK
        "Enable (=1)/disable (=0) simulator networking support. (def: enabled)"
        TRUE)

README-CMake.md

@@ -830,6 +830,7 @@ following the table.
 | `BUILD_SHARED_DEPS`  | platform-specific  | Build dependencies as shared libraries/DLLs on Windows. Does nothing on Linux/macOS. Disabled by default on Windows to ensure that the simulators link against static libraries. |
 | `WITH_ASYNC`         | enabled            | Asynchronous I/O and threading support. |
 | `WITH_REGEX`         | enabled            | PCRE regular expression support. |
+| `PREFER_PCRE`        | disabled           | Prefer the original PCRE regular expression library over PCRE2. The default is PCRE2, which is more actively maintained. |
 | `WITH_NETWORK`       | enabled            | Simulator networking support. `WITH_PCAP`, `WITH_SLIRP`, `WITH_VDE` and `WITH_TAP` only have meaning if `WITH_NETWORK` is enabled. |
 | `WITH_PCAP`          | enabled            | libpcap (packet capture) support. |
 | `WITH_SLIRP`         | enabled            | SLIRP UDP network support. |

cmake/CMake-Maintainers.md

@@ -221,9 +221,7 @@ The top-level `CMakeLists.txt` drives CMake's configure/generate phase, which ha
     is separate for the time being for functional clarity.
   - `thread_lib` (`pthreads-dep.cmake`): Platform threading support. Usually empty for Linux and macOS
     platforms, adds the _PThreads4W_ external dependency for Windows native and XP platforms.
-  - `simh_regexp`: Regular expression support, if the `WITH_REGEX` option is `True`. PCRE is effectively
-    the only regular expression library that ends up in the `simh_regexp` interface library at the
-    moment. There is support for PCRE2, but it requires changes to `scp.c` to actually make it useful.
+  - `simh_regexp`: Regular expression support, if the `WITH_REGEX` option is `True`.
   - `simh_video`: Graphics, input controller and sound support, based on [SDL2][libsdl2], if the
     `WITH_VIDEO` option is `True`. Empty interface library if `WITH_VIDEO` is `False`. `simh_video` also
     pulls in `libpng` and `SDL_ttf`, along with their dependencies.
@@ -352,9 +350,7 @@ SIMH includes six `find_package` scripts:
   capture library; `libpcap` and it's Win32 equivalent are dynamically loaded at run time. The headers are
   only needed for `libpcap`'s function prototypes.
 
-- `FindPCRE.cmake`, `FindPCRE2.cmake`: Locate PCRE and PCRE2 libraries and headers. SIMH does not support
-  PCRE2 yet, however, finding the PCRE2 headers and library are included to make PCRE2 support easier at
-  some point in the future.
+- `FindPCRE.cmake`, `FindPCRE2.cmake`: Locate PCRE and PCRE2 libraries and headers.
 
 - `FindPTW.cmake`: "PTW" is shorthand for the Windows PThreads4w POSIX threads compatibility library.
 

cmake/dep-link.cmake

@@ -195,9 +195,8 @@ if (WITH_REGEX)
     ELSEIF (NOT PREFER_PCRE AND PCRE2_FOUND)
         target_compile_definitions(simh_regexp INTERFACE HAVE_PCRE2_H)
         target_include_directories(simh_regexp INTERFACE ${PCRE2_INCLUDE_DIRS})
-        if (NOT WIN32)
             target_link_libraries(simh_regexp INTERFACE ${PCRE2_LIBRARY})
-        else ()
+        if (WIN32)
             ## Use static linkage (vice DLL) on Windows:
             target_compile_definitions(simh_regexp INTERFACE PCRE2_STATIC)
         endif ()

cmake/dep-locate.cmake

@@ -19,6 +19,8 @@ if (WITH_REGEX)
             find_package(PCRE)
         endif ()
     else ()
+        ## There isn't a difference between the vcpkg and LEGACY strategy.
+        ## SIMH provides its own FindPCRE2.cmake module...
         find_package(PCRE2)
     endif ()
 endif ()
@@ -111,7 +113,7 @@ include (ExternalProject)
 
 # Source URLs (to make it easy to update versions):
 set(ZLIB_SOURCE_URL     "https://github.com/madler/zlib/archive/v1.2.13.zip")
-set(PCRE2_SOURCE_URL    "https://github.com/PCRE2Project/pcre2/releases/download/pcre2-10.40/pcre2-10.40.zip")
+set(PCRE2_SOURCE_URL    "https://github.com/PCRE2Project/pcre2/releases/download/pcre2-10.42/pcre2-10.42.zip")
 ## PCRE needs multiple URLs to chase a working SF mirror:
 list(APPEND PCRE_SOURCE_URL
     "https://sourceforge.net/projects/pcre/files/pcre/8.45/pcre-8.45.zip/download?use_mirror=cytranet"
@@ -178,10 +180,17 @@ IF (WITH_REGEX AND NOT (PCRE_FOUND OR PCRE2_FOUND OR TARGET unofficial::pcre::pc
     if (NOT PREFER_PCRE)
         set(PCRE_URL ${PCRE2_SOURCE_URL})
         list(APPEND PCRE_CMAKE_ARGS 
-            -DPCRE2_BUILD_PCREGREP:Bool=Off
+            -DPCRE2_BUILD_PCRE2_8:Bool=On
+            -DPCRE2_BUILD_PCRE2GREP:Bool=Off
+            -DPCRE2_STATIC_RUNTIME:Bool=On
             -DPCRE2_SUPPORT_LIBEDIT:Bool=Off
             -DPCRE2_SUPPORT_LIBREADLINE:Bool=Off
         )
+        if (WIN32)
+            list(APPEND PCRE_CMAKE_ARGS
+                -DBUILD_STATIC_LIBS:Bool=On
+            )
+        endif ()
 
         # IF(MSVC)
         #   list(APPEND PCRE_CMAKE_ARGS -DINSTALL_MSVC_PDB=On)

makefile

@@ -603,14 +603,39 @@ ifeq (${WIN32},)  #*nix Environments (&& cygwin)
       LIBEXT = $(LIBEXTSAVE)
     endif
   endif
-  # Find PCRE RegEx library.
-  ifneq (,$(call find_include,pcre))
-    ifneq (,$(call find_lib,pcre))
-      OS_CCDEFS += -DHAVE_PCRE_H
-      OS_LDFLAGS += -lpcre
-      $(info using libpcre: $(call find_lib,pcre) $(call find_include,pcre))
-      ifeq ($(LD_SEARCH_NEEDED),$(call need_search,pcre))
-        OS_LDFLAGS += -L$(dir $(call find_lib,pcre))
+  ## RegEx: Prefer the PCRE library over PCRE2 for historical reasons. Only detect
+  ## and use PCRE2 if USE_PCRE2 is set as a command line variable or in the
+  ## environment.
+  FALLBACK_PCRE=yes
+  ifdef USE_PCRE2
+    # Find the PCRE2 RegEx library
+    ifneq (,$(call find_include,pcre2))
+      PCRE2_LIB=pcre2-8
+      ifneq (,$(call find_lib,${PCRE2_LIB}))
+	OS_CCDEFS += -DHAVE_PCRE2_H
+	OS_LDFLAGS += -l${PCRE2_LIB}
+        $(info using libpcre2-8: $(call find_lib,${PCRE2_LIB}) $(call find_include,pcre2))
+	ifeq ($(LD_SEARCH_NEEDED),$(call need_search,${PCRE2_LIB}))
+	  OS_LDFLAGS += -L$(dir $(call find_lib,${{PCRE2_LIB}}))
+	endif
+	FALLBACK_PCRE=
+      endif
+    endif
+    ifneq ($(FALLBACK_PCRE),)
+      $(info *** Info *** PCRE2 not detected, falling back to PCRE)
+    endif
+  endif
+  # Find PCRE RegEx library, either because we didn't want PCRE2 or we didn't
+  # find PCRE2.
+  ifneq (${FALLBACK_PCRE},)
+    ifneq (,$(call find_include,pcre))
+      ifneq (,$(call find_lib,pcre))
+	OS_CCDEFS += -DHAVE_PCRE_H
+	OS_LDFLAGS += -lpcre
+        $(info using libpcre: $(call find_lib,pcre) $(call find_include,pcre))
+	ifeq ($(LD_SEARCH_NEEDED),$(call need_search,pcre))
+	  OS_LDFLAGS += -L$(dir $(call find_lib,pcre))
+	endif
       endif
     endif
   endif