Minimal cmake build script

move flags for MSVC

rename lump.txt to lump.md, add data/*.txt to .gitignore

diff --git a/.gitignore b/.gitignore
index 58d7ad6a8af74ddf27bcd415412b74a143331c1e..c516642b5f4962a572fd9cf3830612790cc1f22c 100644 (file)
--- a/.gitignore
+++ b/.gitignore
@@ -8,8 +8,8 @@
 *.dll
 *.dylib
 *.dSYM
-*.txt
 *.out
+data/*.txt
 bench/bench
 bench/icu
 bench/unistring

diff --git a/CMakeLists.txt b/CMakeLists.txt
new file mode 100644 (file)
index 0000000..4d0c1c3
--- /dev/null
+++ b/CMakeLists.txt
@@ -0,0 +1,22 @@
+cmake_minimum_required (VERSION 2.8)
+
+include (utils.cmake)
+
+disallow_intree_builds()
+
+project (utf8proc C)
+
+add_definitions (
+  -DUTF8PROC_EXPORTS
+)
+
+if (NOT MSVC)
+  set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -O2 -std=c99 -pedantic -Wall")
+endif ()
+
+add_library (utf8proc
+  utf8proc.c
+  utf8proc.h
+)
+
+set_property (TARGET utf8proc PROPERTY POSITION_INDEPENDENT_CODE ON)

diff --git a/NEWS.md b/NEWS.md
index ead7f6bd5814ed5038381ef945508824cc8c9f42..989aba53b2d9f71486d827341757e0bb41871426 100644 (file)
--- a/NEWS.md
+++ b/NEWS.md
@@ -105,7 +105,7 @@ Release of version 1.0.1
 
 2006-09-17:
 
-- added the `LUMP` option, which lumps certain characters together (see `lump.txt`) (also used for the PostgreSQL `unifold` function)
+- added the `LUMP` option, which lumps certain characters together (see `lump.md`) (also used for the PostgreSQL `unifold` function)
 - added the `STRIPMARK` option, which strips marking characters (or marks of composed characters)
 - deprecated ruby method `String#char_ary` in favour of `String#utf8chars`
 

diff --git a/lump.md b/lump.md
new file mode 100644 (file)
index 0000000..39186fb
--- /dev/null
+++ b/lump.md
@@ -0,0 +1,27 @@
+```
+U+0020      <-- all space characters (general category Zs)
+U+0027  '   <-- left/right single quotation mark U+2018..2019,
+                modifier letter apostrophe U+02BC,
+                modifier letter vertical line U+02C8
+U+002D  -   <-- all dash characters (general category Pd),
+                minus U+2212
+U+002F  /   <-- fraction slash U+2044,
+                division slash U+2215
+U+003A  :   <-- ratio U+2236
+U+003C  <   <-- single left-pointing angle quotation mark U+2039,
+                left-pointing angle bracket U+2329,
+                left angle bracket U+3008
+U+003E  >   <-- single right-pointing angle quotation mark U+203A,
+                right-pointing angle bracket U+232A,
+                right angle bracket U+3009
+U+005C  \   <-- set minus U+2216
+U+005E  ^   <-- modifier letter up arrowhead U+02C4,
+                modifier letter circumflex accent U+02C6,
+                caret U+2038,
+                up arrowhead U+2303
+U+005F  _   <-- all connector characters (general category Pc),
+                modifier letter low macron U+02CD
+U+0060  `   <-- modifier letter grave accent U+02CB
+U+007C  |   <-- divides U+2223
+U+007E  ~   <-- tilde operator U+223C
+```

diff --git a/lump.txt b/lump.txt
deleted file mode 100644 (file)
index 442cafb..0000000
--- a/lump.txt
+++ /dev/null
@@ -1,26 +0,0 @@
-U+0020      <-- all space characters (general category Zs)
-U+0027  '   <-- left/right single quotation mark U+2018..2019,
-                modifier letter apostrophe U+02BC,
-                modifier letter vertical line U+02C8
-U+002D  -   <-- all dash characters (general category Pd),
-                minus U+2212
-U+002F  /   <-- fraction slash U+2044,
-                division slash U+2215
-U+003A  :   <-- ratio U+2236
-U+003C  <   <-- single left-pointing angle quotation mark U+2039,
-                left-pointing angle bracket U+2329,
-                left angle bracket U+3008
-U+003E  >   <-- single right-pointing angle quotation mark U+203A,
-                right-pointing angle bracket U+232A,
-                right angle bracket U+3009
-U+005C  \   <-- set minus U+2216
-U+005E  ^   <-- modifier letter up arrowhead U+02C4,
-                modifier letter circumflex accent U+02C6,
-                caret U+2038,
-                up arrowhead U+2303
-U+005F  _   <-- all connector characters (general category Pc),
-                modifier letter low macron U+02CD
-U+0060  `   <-- modifier letter grave accent U+02CB
-U+007C  |   <-- divides U+2223
-U+007E  ~   <-- tilde operator U+223C
-

diff --git a/utf8proc.h b/utf8proc.h
index 06346c884b194a23e0ad0d7f20e47bae6479eb1f..0d647db9378aa146efd5ed8817f4f4989b59a938 100644 (file)
--- a/utf8proc.h
+++ b/utf8proc.h
@@ -140,7 +140,7 @@ extern "C" {
  *             is representing a single grapheme cluster (see UAX#29).
  *  LUMP:      Lumps certain characters together
  *             (e.g. HYPHEN U+2010 and MINUS U+2212 to ASCII "-").
- *             (See lump.txt for details.)
+ *             (See lump.md for details.)
  *             If NLF2LF is set, this includes a transformation of
  *             paragraph and line separators to ASCII line-feed (LF).
  *  STRIPMARK: Strips all character markings

diff --git a/utils.cmake b/utils.cmake
new file mode 100644 (file)
index 0000000..63fc426
--- /dev/null
+++ b/utils.cmake
@@ -0,0 +1,20 @@
+
+function (disallow_intree_builds)
+  # Adapted from LLVM's toplevel CMakeLists.txt file
+  if( CMAKE_SOURCE_DIR STREQUAL CMAKE_BINARY_DIR AND NOT MSVC_IDE )
+    message(FATAL_ERROR "
+      In-source builds are not allowed. CMake would overwrite the
+      makefiles distributed with utf8proc. Please create a directory
+      and run cmake from there. Building in a subdirectory is
+      fine, e.g.:
+      
+        mkdir build
+        cd build
+        cmake ..
+      
+      This process created the file `CMakeCache.txt' and the
+      directory `CMakeFiles'. Please delete them.
+      
+      ")
+  endif()
+endfunction()