Merge pull request #369 from afh/pull/utfcpp_subtree

Replace utfcpp submodule with partial subtree

.gitmodules

@@ -1,3 +0,0 @@
-[submodule "lib/utfcpp"]
-	path = lib/utfcpp
-	url = http://github.com/ledger/utfcpp.git

CMakeLists.txt

@@ -12,6 +12,9 @@ set(Ledger_VERSION_PATCH 1)
 set(Ledger_VERSION_PRERELEASE "-alpha.1")
 set(Ledger_VERSION_DATE  20141005)
 
+# Point CMake at any custom modules we may ship
+list(APPEND CMAKE_MODULE_PATH "${PROJECT_SOURCE_DIR}/cmake")
+
 enable_testing()
 
 add_definitions(-std=c++11)
@@ -244,13 +247,20 @@ endmacro(add_ledger_library_dependencies _target)
 
 ########################################################################
 
+include(FindUtfcpp)
+if (UTFCPP_FOUND)
+  include_directories("${UTFCPP_INCLUDE_DIR}")
+else()
+  message(FATAL_ERROR "Missing required header file: utf8.h\n"
+    "Define UTFCPP_PATH or install utfcpp locally into the source tree below lib/utfcpp/."
+    )
+endif()
+
 set(CMAKE_LIBRARY_OUTPUT_DIRECTORY ${PROJECT_BINARY_DIR})
 set(CMAKE_RUNTIME_OUTPUT_DIRECTORY ${PROJECT_BINARY_DIR})
 
 # add the binary tree to the search path for include files so that we will
-# find TutorialConfig.h
-include_directories("${PROJECT_SOURCE_DIR}/lib")
-include_directories("${PROJECT_SOURCE_DIR}/lib/utfcpp/source")
+# find system.hh
 include_directories("${PROJECT_BINARY_DIR}")
 
 configure_file(

acprep

@@ -490,17 +490,10 @@ class PrepareBuild(CommandLineApp):
     # Update local files with the latest information                        #
     #########################################################################
 
-    def phase_submodule(self, *args):
-        self.log.info('Executing phase: submodule')
-        if self.git_working_tree():
-            self.execute('git', 'submodule', 'init')
-            self.execute('git', 'submodule', 'update')
-
     def phase_pull(self, *args):
         self.log.info('Executing phase: pull')
         if self.git_working_tree():
             self.execute('git', 'pull')
-            self.phase_submodule()
 
     #########################################################################
     # Automatic installation of build dependencies                          #
@@ -569,6 +562,7 @@ class PrepareBuild(CommandLineApp):
                             'libedit-dev',
                             'texinfo',
                             'lcov',
+                            'libutfcpp-dev',
                             'sloccount'
                         ] + BoostInfo().dependencies('ubuntu-trusty')
                     elif re.search('saucy', info):
@@ -606,6 +600,7 @@ class PrepareBuild(CommandLineApp):
                             'libedit-dev',
                             'texinfo',
                             'lcov',
+                            'libutfcpp-dev',
                             'sloccount'
                         ] + BoostInfo().dependencies('ubuntu-precise')
                     else:
@@ -885,7 +880,6 @@ class PrepareBuild(CommandLineApp):
 
     def phase_config(self, *args):
         self.log.info('Executing phase: config')
-        self.phase_submodule()
         self.phase_configure(*args)
         if self.should_clean:
             self.phase_clean()

cmake/FindUtfcpp.cmake

@@ -0,0 +1,30 @@
+# - Try to find utfcpp
+# Once done, this will define
+#
+#  UTFCPP_FOUND        - system has utfcpp's utf8.h
+#  UTFCPP_PATH         - the utfcpp include directories
+
+include(CheckCXXSourceCompiles)
+
+set(UTFCPP_FOUND FALSE)
+
+find_path(UTFCPP_INCLUDE_DIR
+    NAMES utf8.h
+    HINTS  "${UTFCPP_PATH}" "${PROJECT_SOURCE_DIR}/lib/utfcpp/v2_0/source"
+)
+
+if (UTFCPP_INCLUDE_DIR)
+  set(CMAKE_REQUIRED_INCLUDES "${UTFCPP_INCLUDE_DIR}")
+  set(UTFCPP_FOUND TRUE)
+endif()
+
+check_cxx_source_compiles("
+#include <string>
+#include \"utf8.h\"
+
+int main(int argc, char** argv) {
+    std::string input = std::string(\"utfcpp\");
+    const char * p = input.c_str();
+    std::size_t len = input.length();
+    utf8::is_valid(p, p + len);
+}" HAVE_WORKING_UTFCPP)

doc/LICENSE-utfcpp → lib/utfcpp/v2_0/LICENSE

@@ -1,4 +1,4 @@
-Copyright 2006 Nemanja Trifunovic
+Boost Software License - Version 1.0 - August 17th, 2003
 
 Permission is hereby granted, free of charge, to any person or organization
 obtaining a copy of the software and accompanying documentation covered by

lib/utfcpp/v2_0/buildrelease.pl

@@ -0,0 +1,18 @@
+#! /usr/bin/perl
+
+$release_files = 'source/utf8.h  source/utf8/core.h source/utf8/checked.h source/utf8/unchecked.h doc/utf8cpp.html doc/ReleaseNotes';
+
+# First get the latest version
+`svn update`;
+
+# Then construct the name of the zip file
+$argc = @ARGV;
+if ($argc > 0) {
+    $zip_name = $ARGV[0];
+}
+else {
+    $zip_name = "utf8";
+}
+
+# Zip the files to an archive
+`zip $zip_name $release_files`; 

lib/utfcpp/v2_0/samples/Makefile

@@ -0,0 +1,5 @@
+CC = g++
+CFLAGS = -g -Wall -pedantic
+
+docsample: docsample.cpp ../source/utf8.h
+	$(CC) $(CFLAGS) docsample.cpp -odocsample

lib/utfcpp/v2_0/samples/docsample.cpp

@@ -0,0 +1,52 @@
+#include "../source/utf8.h"
+#include <iostream>
+#include <fstream>
+#include <string>
+#include <vector>
+
+
+using namespace std;
+
+int main(int argc, char** argv)
+{
+    if (argc != 2) {
+        cout << "\nUsage: docsample filename\n";
+        return 0;
+    }
+    const char* test_file_path = argv[1];
+    // Open the test file (must be UTF-8 encoded)
+    ifstream fs8(test_file_path);
+    if (!fs8.is_open()) {
+    cout << "Could not open " << test_file_path << endl;
+    return 0;
+    }
+
+    unsigned line_count = 1;
+    string line;
+    // Play with all the lines in the file
+    while (getline(fs8, line)) {
+        // check for invalid utf-8 (for a simple yes/no check, there is also utf8::is_valid function)
+        string::iterator end_it = utf8::find_invalid(line.begin(), line.end());
+        if (end_it != line.end()) {
+            cout << "Invalid UTF-8 encoding detected at line " << line_count << "\n";
+            cout << "This part is fine: " << string(line.begin(), end_it) << "\n";
+        }
+        // Get the line length (at least for the valid part)
+        int length = utf8::distance(line.begin(), end_it);
+        cout << "Length of line " << line_count << " is " << length <<  "\n";
+
+        // Convert it to utf-16
+        vector<unsigned short> utf16line;
+        utf8::utf8to16(line.begin(), end_it, back_inserter(utf16line));
+        // And back to utf-8;
+        string utf8line; 
+        utf8::utf16to8(utf16line.begin(), utf16line.end(), back_inserter(utf8line));
+        // Confirm that the conversion went OK:
+        if (utf8line != string(line.begin(), end_it))
+            cout << "Error in UTF-16 conversion at line: " << line_count << "\n";        
+
+        line_count++;
+    } 
+
+    return 0;
+}

lib/utfcpp/v2_0/source/utf8.h

@@ -0,0 +1,34 @@
+// Copyright 2006 Nemanja Trifunovic
+
+/*
+Permission is hereby granted, free of charge, to any person or organization
+obtaining a copy of the software and accompanying documentation covered by
+this license (the "Software") to use, reproduce, display, distribute,
+execute, and transmit the Software, and to prepare derivative works of the
+Software, and to permit third-parties to whom the Software is furnished to
+do so, all subject to the following:
+
+The copyright notices in the Software and this entire statement, including
+the above license grant, this restriction and the following disclaimer,
+must be included in all copies of the Software, in whole or in part, and
+all derivative works of the Software, unless such copies or derivative
+works are solely in the form of machine-executable object code generated by
+a source language processor.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE, TITLE AND NON-INFRINGEMENT. IN NO EVENT
+SHALL THE COPYRIGHT HOLDERS OR ANYONE DISTRIBUTING THE SOFTWARE BE LIABLE
+FOR ANY DAMAGES OR OTHER LIABILITY, WHETHER IN CONTRACT, TORT OR OTHERWISE,
+ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+DEALINGS IN THE SOFTWARE.
+*/
+
+
+#ifndef UTF8_FOR_CPP_2675DCD0_9480_4c0c_B92A_CC14C027B731
+#define UTF8_FOR_CPP_2675DCD0_9480_4c0c_B92A_CC14C027B731
+
+#include "utf8/checked.h"
+#include "utf8/unchecked.h"
+
+#endif // header guard